mirrors
/
linux-stable
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
1
0
Fork 0
Code Issues Releases Wiki Activity
linux-stable/net/core/skmsg.c

1256 lines
29 KiB
C
Raw Normal View History

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 00:45:58 +00:00
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2017 - 2018 Covalent IO, Inc. http://covalent.io */
#include <linux/skmsg.h>
#include <linux/skbuff.h>
#include <linux/scatterlist.h>
#include <net/sock.h>
#include <net/tcp.h>
bpf: Fix running sk_skb program types with ktls KTLS uses a stream parser to collect TLS messages and send them to the upper layer tls receive handler. This ensures the tls receiver has a full TLS header to parse when it is run. However, when a socket has BPF_SK_SKB_STREAM_VERDICT program attached before KTLS is enabled we end up with two stream parsers running on the same socket. The result is both try to run on the same socket. First the KTLS stream parser runs and calls read_sock() which will tcp_read_sock which in turn calls tcp_rcv_skb(). This dequeues the skb from the sk_receive_queue. When this is done KTLS code then data_ready() callback which because we stacked KTLS on top of the bpf stream verdict program has been replaced with sk_psock_start_strp(). This will in turn kick the stream parser again and eventually do the same thing KTLS did above calling into tcp_rcv_skb() and dequeuing a skb from the sk_receive_queue. At this point the data stream is broke. Part of the stream was handled by the KTLS side some other bytes may have been handled by the BPF side. Generally this results in either missing data or more likely a "Bad Message" complaint from the kTLS receive handler as the BPF program steals some bytes meant to be in a TLS header and/or the TLS header length is no longer correct. We've already broke the idealized model where we can stack ULPs in any order with generic callbacks on the TX side to handle this. So in this patch we do the same thing but for RX side. We add a sk_psock_strp_enabled() helper so TLS can learn a BPF verdict program is running and add a tls_sw_has_ctx_rx() helper so BPF side can learn there is a TLS ULP on the socket. Then on BPF side we omit calling our stream parser to avoid breaking the data stream for the KTLS receiver. Then on the KTLS side we call BPF_SK_SKB_STREAM_VERDICT once the KTLS receiver is done with the packet but before it posts the msg to userspace. This gives us symmetry between the TX and RX halfs and IMO makes it usable again. On the TX side we process packets in this order BPF -> TLS -> TCP and on the receive side in the reverse order TCP -> TLS -> BPF. Discovered while testing OpenSSL 3.0 Alpha2.0 release. Fixes: d829e9c4112b5 ("tls: convert to generic sk_msg interface") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/159079361946.5745.605854335665044485.stgit@john-Precision-5820-Tower Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-29 23:06:59 +00:00
#include <net/tls.h>
net/sock: Introduce trace_sk_data_ready() As suggested by Cong, introduce a tracepoint for all ->sk_data_ready() callback implementations. For example: <...> iperf-609 [002] ..... 70.660425: sk_data_ready: family=2 protocol=6 func=sock_def_readable iperf-609 [002] ..... 70.660436: sk_data_ready: family=2 protocol=6 func=sock_def_readable <...> Suggested-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Peilin Ye <peilin.ye@bytedance.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-01-20 00:45:16 +00:00
#include <trace/events/sock.h>
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 00:45:58 +00:00
static bool sk_msg_try_coalesce_ok(struct sk_msg *msg, int elem_first_coalesce)
{
if (msg->sg.end > msg->sg.start &&
elem_first_coalesce < msg->sg.end)
return true;
if (msg->sg.end < msg->sg.start &&
(elem_first_coalesce > msg->sg.start ||
elem_first_coalesce < msg->sg.end))
return true;
return false;
}
int sk_msg_alloc(struct sock *sk, struct sk_msg *msg, int len,
int elem_first_coalesce)
{
struct page_frag *pfrag = sk_page_frag(sk);
bpf, sockmap: Fix memleak in tcp_bpf_sendmsg while sk msg is full If tcp_bpf_sendmsg() is running while sk msg is full. When sk_msg_alloc() returns -ENOMEM error, tcp_bpf_sendmsg() goes to wait_for_memory. If partial memory has been alloced by sk_msg_alloc(), that is, msg_tx->sg.size is greater than osize after sk_msg_alloc(), memleak occurs. To fix we use sk_msg_trim() to release the allocated memory, then goto wait for memory. Other call paths of sk_msg_alloc() have the similar issue, such as tls_sw_sendmsg(), so handle sk_msg_trim logic inside sk_msg_alloc(), as Cong Wang suggested. This issue can cause the following info: WARNING: CPU: 3 PID: 7950 at net/core/stream.c:208 sk_stream_kill_queues+0xd4/0x1a0 Call Trace: <TASK> inet_csk_destroy_sock+0x55/0x110 __tcp_close+0x279/0x470 tcp_close+0x1f/0x60 inet_release+0x3f/0x80 __sock_release+0x3d/0xb0 sock_close+0x11/0x20 __fput+0x92/0x250 task_work_run+0x6a/0xa0 do_exit+0x33b/0xb60 do_group_exit+0x2f/0xa0 get_signal+0xb6/0x950 arch_do_signal_or_restart+0xac/0x2a0 exit_to_user_mode_prepare+0xa9/0x200 syscall_exit_to_user_mode+0x12/0x30 do_syscall_64+0x46/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xae </TASK> WARNING: CPU: 3 PID: 2094 at net/ipv4/af_inet.c:155 inet_sock_destruct+0x13c/0x260 Call Trace: <TASK> __sk_destruct+0x24/0x1f0 sk_psock_destroy+0x19b/0x1c0 process_one_work+0x1b3/0x3c0 kthread+0xe6/0x110 ret_from_fork+0x22/0x30 </TASK> Fixes: 604326b41a6f ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Wang Yufen <wangyufen@huawei.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20220304081145.2037182-3-wangyufen@huawei.com
2022-03-04 08:11:43 +00:00
u32 osize = msg->sg.size;
bpf, sockmap: convert to generic sk_msg interface Add a generic sk_msg layer, and convert current sockmap and later kTLS over to make use of it. While sk_buff handles network packet representation from netdevice up to socket, sk_msg handles data representation from application to socket layer. This means that sk_msg framework spans across ULP users in the kernel, and enables features such as introspection or filtering of data with the help of BPF programs that operate on this data structure. Latter becomes in particular useful for kTLS where data encryption is deferred into the kernel, and as such enabling the kernel to perform L7 introspection and policy based on BPF for TLS connections where the record is being encrypted after BPF has run and came to a verdict. In order to get there, first step is to transform open coding of scatter-gather list handling into a common core framework that subsystems can use. The code itself has been split and refactored into three bigger pieces: i) the generic sk_msg API which deals with managing the scatter gather ring, providing helpers for walking and mangling, transferring application data from user space into it, and preparing it for BPF pre/post-processing, ii) the plain sock map itself where sockets can be attached to or detached from; these bits are independent of i) which can now be used also without sock map, and iii) the integration with plain TCP as one protocol to be used for processing L7 application data (later this could e.g. also be extended to other protocols like UDP). The semantics are the same with the old sock map code and therefore no change of user facing behavior or APIs. While pursuing this work it also helped finding a number of bugs in the old sockmap code that we've fixed already in earlier commits. The test_sockmap kselftest suite passes through fine as well. Joint work with John. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-13 00:45:58 +00:00
int ret = 0;
len -= msg->sg.size;
while (len > 0) {
struct scatterlist *sge;
u32 orig_offset;
int use, i;
bpf, sockmap: Fix memleak in tcp_bpf_sendmsg while sk msg is full If tcp_bpf_sendmsg() is running while sk msg is full. When sk_msg_alloc() returns -ENOMEM error, tcp_bpf_sendmsg() goes to wait_for_memory. If partial memory has been alloced by sk_msg_alloc(), that is, msg_tx->sg.size is greater than osize after sk_msg_alloc(), memleak occurs. To fix we use sk_msg_trim() to release the allocated memory, then goto wait for memory. Other call paths of sk_msg_alloc() have the similar issue, such as tls_sw_sendmsg(), so handle sk_msg_trim logic inside sk_msg_alloc(), as Cong Wang suggested. This issue can cause the following info: WARNING: CPU: 3 PID: 7950 at net/core/stream.c:208 sk_stream_kill_queues+0xd4/0x1a0 Call Trace: <TASK> inet_csk_destroy_sock+0x55/0x110 __tcp_close+0x279/0x470 tcp_close+0x1f/0x60 inet_release+0x3f/0x80 __sock_release+0x3d/0xb0 sock_close+0x11/0x20 __fput+0x92/0x250 task_work_run+0x6a/0xa0 do_exit+0x33b/0xb60 do_group_exit+0x2f/0xa0 get_signal+0xb6/0x950 arch_do_signal_or_restart+0xac/0x2a0 exit_to_user_mode_prepare+0xa9/0x200 syscall_exit_to_user_mode+0x12/0x30 do_syscall_64+0x46/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xae </TASK> WARNING: CPU: 3 PID: 2094 at net/ipv4/af_inet.c:155 inet_sock_destruct+0x13c/0x260 Call Trace: <TASK> __sk_destruct+0x24/0x1f0 sk_psock_destroy+0x19b/0x1c0 process_one_work+0x1b3/0x3c0 kthread+0xe6/0x110 ret_from_fork+0x22/0x30 </TASK> Fixes: 604326b41a6f ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Wang Yufen <wangyufen@huawei.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20220304081145.2037182-3-wangyufen@huawei.com
2022-03-04 08:11:43 +00:00
if (!sk_page_frag_refill(sk, pfrag)) {
ret = -ENOMEM;
goto msg_trim;
}
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 00:45:58 +00:00
orig_offset = pfrag->offset;
use = min_t(int, len, pfrag->size - orig_offset);
bpf, sockmap: Fix memleak in tcp_bpf_sendmsg while sk msg is full If tcp_bpf_sendmsg() is running while sk msg is full. When sk_msg_alloc() returns -ENOMEM error, tcp_bpf_sendmsg() goes to wait_for_memory. If partial memory has been alloced by sk_msg_alloc(), that is, msg_tx->sg.size is greater than osize after sk_msg_alloc(), memleak occurs. To fix we use sk_msg_trim() to release the allocated memory, then goto wait for memory. Other call paths of sk_msg_alloc() have the similar issue, such as tls_sw_sendmsg(), so handle sk_msg_trim logic inside sk_msg_alloc(), as Cong Wang suggested. This issue can cause the following info: WARNING: CPU: 3 PID: 7950 at net/core/stream.c:208 sk_stream_kill_queues+0xd4/0x1a0 Call Trace: <TASK> inet_csk_destroy_sock+0x55/0x110 __tcp_close+0x279/0x470 tcp_close+0x1f/0x60 inet_release+0x3f/0x80 __sock_release+0x3d/0xb0 sock_close+0x11/0x20 __fput+0x92/0x250 task_work_run+0x6a/0xa0 do_exit+0x33b/0xb60 do_group_exit+0x2f/0xa0 get_signal+0xb6/0x950 arch_do_signal_or_restart+0xac/0x2a0 exit_to_user_mode_prepare+0xa9/0x200 syscall_exit_to_user_mode+0x12/0x30 do_syscall_64+0x46/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xae </TASK> WARNING: CPU: 3 PID: 2094 at net/ipv4/af_inet.c:155 inet_sock_destruct+0x13c/0x260 Call Trace: <TASK> __sk_destruct+0x24/0x1f0 sk_psock_destroy+0x19b/0x1c0 process_one_work+0x1b3/0x3c0 kthread+0xe6/0x110 ret_from_fork+0x22/0x30 </TASK> Fixes: 604326b41a6f ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Wang Yufen <wangyufen@huawei.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20220304081145.2037182-3-wangyufen@huawei.com
2022-03-04 08:11:43 +00:00
if (!sk_wmem_schedule(sk, use)) {
ret = -ENOMEM;
goto msg_trim;
}
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 00:45:58 +00:00
i = msg->sg.end;
sk_msg_iter_var_prev(i);
sge = &msg->sg.data[i];
if (sk_msg_try_coalesce_ok(msg, elem_first_coalesce) &&
sg_page(sge) == pfrag->page &&
sge->offset + sge->length == orig_offset) {
sge->length += use;
} else {
if (sk_msg_full(msg)) {
ret = -ENOSPC;
break;
}
sge = &msg->sg.data[msg->sg.end];
sg_unmark_end(sge);
sg_set_page(sge, pfrag->page, use, orig_offset);
get_page(pfrag->page);
sk_msg_iter_next(msg, end);
}
sk_mem_charge(sk, use);
msg->sg.size += use;
pfrag->offset += use;
len -= use;
}
return ret;
bpf, sockmap: Fix memleak in tcp_bpf_sendmsg while sk msg is full If tcp_bpf_sendmsg() is running while sk msg is full. When sk_msg_alloc() returns -ENOMEM error, tcp_bpf_sendmsg() goes to wait_for_memory. If partial memory has been alloced by sk_msg_alloc(), that is, msg_tx->sg.size is greater than osize after sk_msg_alloc(), memleak occurs. To fix we use sk_msg_trim() to release the allocated memory, then goto wait for memory. Other call paths of sk_msg_alloc() have the similar issue, such as tls_sw_sendmsg(), so handle sk_msg_trim logic inside sk_msg_alloc(), as Cong Wang suggested. This issue can cause the following info: WARNING: CPU: 3 PID: 7950 at net/core/stream.c:208 sk_stream_kill_queues+0xd4/0x1a0 Call Trace: <TASK> inet_csk_destroy_sock+0x55/0x110 __tcp_close+0x279/0x470 tcp_close+0x1f/0x60 inet_release+0x3f/0x80 __sock_release+0x3d/0xb0 sock_close+0x11/0x20 __fput+0x92/0x250 task_work_run+0x6a/0xa0 do_exit+0x33b/0xb60 do_group_exit+0x2f/0xa0 get_signal+0xb6/0x950 arch_do_signal_or_restart+0xac/0x2a0 exit_to_user_mode_prepare+0xa9/0x200 syscall_exit_to_user_mode+0x12/0x30 do_syscall_64+0x46/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xae </TASK> WARNING: CPU: 3 PID: 2094 at net/ipv4/af_inet.c:155 inet_sock_destruct+0x13c/0x260 Call Trace: <TASK> __sk_destruct+0x24/0x1f0 sk_psock_destroy+0x19b/0x1c0 process_one_work+0x1b3/0x3c0 kthread+0xe6/0x110 ret_from_fork+0x22/0x30 </TASK> Fixes: 604326b41a6f ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Wang Yufen <wangyufen@huawei.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20220304081145.2037182-3-wangyufen@huawei.com
2022-03-04 08:11:43 +00:00
msg_trim:
sk_msg_trim(sk, msg, osize);
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 00:45:58 +00:00
}
EXPORT_SYMBOL_GPL(sk_msg_alloc);
tls: convert to generic sk_msg interface Convert kTLS over to make use of sk_msg interface for plaintext and encrypted scattergather data, so it reuses all the sk_msg helpers and data structure which later on in a second step enables to glue this to BPF. This also allows to remove quite a bit of open coded helpers which are covered by the sk_msg API. Recent changes in kTLs 80ece6a03aaf ("tls: Remove redundant vars from tls record structure") and 4e6d47206c32 ("tls: Add support for inplace records encryption") changed the data path handling a bit; while we've kept the latter optimization intact, we had to undo the former change to better fit the sk_msg model, hence the sg_aead_in and sg_aead_out have been brought back and are linked into the sk_msg sgs. Now the kTLS record contains a msg_plaintext and msg_encrypted sk_msg each. In the original code, the zerocopy_from_iter() has been used out of TX but also RX path. For the strparser skb-based RX path, we've left the zerocopy_from_iter() in decrypt_internal() mostly untouched, meaning it has been moved into tls_setup_from_iter() with charging logic removed (as not used from RX). Given RX path is not based on sk_msg objects, we haven't pursued setting up a dummy sk_msg to call into sk_msg_zerocopy_from_iter(), but it could be an option to prusue in a later step. 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 00:45:59 +00:00
int sk_msg_clone(struct sock *sk, struct sk_msg *dst, struct sk_msg *src,
u32 off, u32 len)
{
int i = src->sg.start;
struct scatterlist *sge = sk_msg_elem(src, i);
Optimize sk_msg_clone() by data merge to end dst sg entry Function sk_msg_clone has been modified to merge the data from source sg entry to destination sg entry if the cloned data resides in same page and is contiguous to the end entry of destination sk_msg. This improves kernel tls throughput to the tune of 10%. When the user space tls application calls sendmsg() with MSG_MORE, it leads to calling sk_msg_clone() with new data being cloned placed continuous to previously cloned data. Without this optimization, a new SG entry in the destination sk_msg i.e. rec->msg_plaintext in tls_clone_plaintext_msg() gets used. This leads to exhaustion of sg entries in rec->msg_plaintext even before a full 16K of allowable record data is accumulated. Hence we lose oppurtunity to encrypt and send a full 16K record. With this patch, the kernel tls can accumulate full 16K of record data irrespective of the size of data passed in sendmsg() with MSG_MORE. Signed-off-by: Vakul Garg <vakul.garg@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-16 01:42:44 +00:00
struct scatterlist *sgd = NULL;
tls: convert to generic sk_msg interface Convert kTLS over to make use of sk_msg interface for plaintext and encrypted scattergather data, so it reuses all the sk_msg helpers and data structure which later on in a second step enables to glue this to BPF. This also allows to remove quite a bit of open coded helpers which are covered by the sk_msg API. Recent changes in kTLs 80ece6a03aaf ("tls: Remove redundant vars from tls record structure") and 4e6d47206c32 ("tls: Add support for inplace records encryption") changed the data path handling a bit; while we've kept the latter optimization intact, we had to undo the former change to better fit the sk_msg model, hence the sg_aead_in and sg_aead_out have been brought back and are linked into the sk_msg sgs. Now the kTLS record contains a msg_plaintext and msg_encrypted sk_msg each. In the original code, the zerocopy_from_iter() has been used out of TX but also RX path. For the strparser skb-based RX path, we've left the zerocopy_from_iter() in decrypt_internal() mostly untouched, meaning it has been moved into tls_setup_from_iter() with charging logic removed (as not used from RX). Given RX path is not based on sk_msg objects, we haven't pursued setting up a dummy sk_msg to call into sk_msg_zerocopy_from_iter(), but it could be an option to prusue in a later step. 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 00:45:59 +00:00
u32 sge_len, sge_off;
while (off) {
if (sge->length > off)
break;
off -= sge->length;
sk_msg_iter_var_next(i);
if (i == src->sg.end && off)
return -ENOSPC;
sge = sk_msg_elem(src, i);
}
while (len) {
sge_len = sge->length - off;
if (sge_len > len)
sge_len = len;
Optimize sk_msg_clone() by data merge to end dst sg entry Function sk_msg_clone has been modified to merge the data from source sg entry to destination sg entry if the cloned data resides in same page and is contiguous to the end entry of destination sk_msg. This improves kernel tls throughput to the tune of 10%. When the user space tls application calls sendmsg() with MSG_MORE, it leads to calling sk_msg_clone() with new data being cloned placed continuous to previously cloned data. Without this optimization, a new SG entry in the destination sk_msg i.e. rec->msg_plaintext in tls_clone_plaintext_msg() gets used. This leads to exhaustion of sg entries in rec->msg_plaintext even before a full 16K of allowable record data is accumulated. Hence we lose oppurtunity to encrypt and send a full 16K record. With this patch, the kernel tls can accumulate full 16K of record data irrespective of the size of data passed in sendmsg() with MSG_MORE. Signed-off-by: Vakul Garg <vakul.garg@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-16 01:42:44 +00:00
if (dst->sg.end)
sgd = sk_msg_elem(dst, dst->sg.end - 1);
if (sgd &&
(sg_page(sge) == sg_page(sgd)) &&
(sg_virt(sge) + off == sg_virt(sgd) + sgd->length)) {
sgd->length += sge_len;
dst->sg.size += sge_len;
} else if (!sk_msg_full(dst)) {
sge_off = sge->offset + off;
sk_msg_page_add(dst, sg_page(sge), sge_len, sge_off);
} else {
return -ENOSPC;
}
tls: convert to generic sk_msg interface Convert kTLS over to make use of sk_msg interface for plaintext and encrypted scattergather data, so it reuses all the sk_msg helpers and data structure which later on in a second step enables to glue this to BPF. This also allows to remove quite a bit of open coded helpers which are covered by the sk_msg API. Recent changes in kTLs 80ece6a03aaf ("tls: Remove redundant vars from tls record structure") and 4e6d47206c32 ("tls: Add support for inplace records encryption") changed the data path handling a bit; while we've kept the latter optimization intact, we had to undo the former change to better fit the sk_msg model, hence the sg_aead_in and sg_aead_out have been brought back and are linked into the sk_msg sgs. Now the kTLS record contains a msg_plaintext and msg_encrypted sk_msg each. In the original code, the zerocopy_from_iter() has been used out of TX but also RX path. For the strparser skb-based RX path, we've left the zerocopy_from_iter() in decrypt_internal() mostly untouched, meaning it has been moved into tls_setup_from_iter() with charging logic removed (as not used from RX). Given RX path is not based on sk_msg objects, we haven't pursued setting up a dummy sk_msg to call into sk_msg_zerocopy_from_iter(), but it could be an option to prusue in a later step. 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 00:45:59 +00:00
off = 0;
len -= sge_len;
sk_mem_charge(sk, sge_len);
sk_msg_iter_var_next(i);
if (i == src->sg.end && len)
return -ENOSPC;
sge = sk_msg_elem(src, i);
}
return 0;
}
EXPORT_SYMBOL_GPL(sk_msg_clone);
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 00:45:58 +00:00
void sk_msg_return_zero(struct sock *sk, struct sk_msg *msg, int bytes)
{
int i = msg->sg.start;
do {
struct scatterlist *sge = sk_msg_elem(msg, i);
if (bytes < sge->length) {
sge->length -= bytes;
sge->offset += bytes;
sk_mem_uncharge(sk, bytes);
break;
}
sk_mem_uncharge(sk, sge->length);
bytes -= sge->length;
sge->length = 0;
sge->offset = 0;
sk_msg_iter_var_next(i);
} while (bytes && i != msg->sg.end);
msg->sg.start = i;
}
EXPORT_SYMBOL_GPL(sk_msg_return_zero);
void sk_msg_return(struct sock *sk, struct sk_msg *msg, int bytes)
{
int i = msg->sg.start;
do {
struct scatterlist *sge = &msg->sg.data[i];
int uncharge = (bytes < sge->length) ? bytes : sge->length;
sk_mem_uncharge(sk, uncharge);
bytes -= uncharge;
sk_msg_iter_var_next(i);
} while (i != msg->sg.end);
}
EXPORT_SYMBOL_GPL(sk_msg_return);
static int sk_msg_free_elem(struct sock *sk, struct sk_msg *msg, u32 i,
bool charge)
{
struct scatterlist *sge = sk_msg_elem(msg, i);
u32 len = sge->length;
bpf, sockmap: Ensure SO_RCVBUF memory is observed on ingress redirect Fix sockmap sk_skb programs so that they observe sk_rcvbuf limits. This allows users to tune SO_RCVBUF and sockmap will honor them. We can refactor the if(charge) case out in later patches. But, keep this fix to the point. Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path") Suggested-by: Jakub Sitnicki <jakub@cloudflare.com> Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/160556568657.73229.8404601585878439060.stgit@john-XPS-13-9370
2020-11-16 22:28:06 +00:00
/* When the skb owns the memory we free it from consume_skb path. */
if (!msg->skb) {
if (charge)
sk_mem_uncharge(sk, 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 00:45:58 +00:00
put_page(sg_page(sge));
bpf, sockmap: Ensure SO_RCVBUF memory is observed on ingress redirect Fix sockmap sk_skb programs so that they observe sk_rcvbuf limits. This allows users to tune SO_RCVBUF and sockmap will honor them. We can refactor the if(charge) case out in later patches. But, keep this fix to the point. Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path") Suggested-by: Jakub Sitnicki <jakub@cloudflare.com> Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/160556568657.73229.8404601585878439060.stgit@john-XPS-13-9370
2020-11-16 22:28:06 +00:00
}
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 00:45:58 +00:00
memset(sge, 0, sizeof(*sge));
return len;
}
static int __sk_msg_free(struct sock *sk, struct sk_msg *msg, u32 i,
bool charge)
{
struct scatterlist *sge = sk_msg_elem(msg, i);
int freed = 0;
while (msg->sg.size) {
msg->sg.size -= sge->length;
freed += sk_msg_free_elem(sk, msg, i, charge);
sk_msg_iter_var_next(i);
sk_msg_check_to_free(msg, i, msg->sg.size);
sge = sk_msg_elem(msg, i);
}
net/core/skmsg: Delete an unnecessary check before the function call “consume_skb” The consume_skb() function performs also input parameter validation. Thus the test around the call is not needed. This issue was detected by using the Coccinelle software. Signed-off-by: Markus Elfring <elfring@users.sourceforge.net> Acked-by: Song Liu <songliubraving@fb.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-08-22 16:00:40 +00:00
consume_skb(msg->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 00:45:58 +00:00
sk_msg_init(msg);
return freed;
}
int sk_msg_free_nocharge(struct sock *sk, struct sk_msg *msg)
{
return __sk_msg_free(sk, msg, msg->sg.start, false);
}
EXPORT_SYMBOL_GPL(sk_msg_free_nocharge);
int sk_msg_free(struct sock *sk, struct sk_msg *msg)
{
return __sk_msg_free(sk, msg, msg->sg.start, true);
}
EXPORT_SYMBOL_GPL(sk_msg_free);
static void __sk_msg_free_partial(struct sock *sk, struct sk_msg *msg,
u32 bytes, bool charge)
{
struct scatterlist *sge;
u32 i = msg->sg.start;
while (bytes) {
sge = sk_msg_elem(msg, i);
if (!sge->length)
break;
if (bytes < sge->length) {
if (charge)
sk_mem_uncharge(sk, bytes);
sge->length -= bytes;
sge->offset += bytes;
msg->sg.size -= bytes;
break;
}
msg->sg.size -= sge->length;
bytes -= sge->length;
sk_msg_free_elem(sk, msg, i, charge);
sk_msg_iter_var_next(i);
sk_msg_check_to_free(msg, i, bytes);
}
msg->sg.start = i;
}
void sk_msg_free_partial(struct sock *sk, struct sk_msg *msg, u32 bytes)
{
__sk_msg_free_partial(sk, msg, bytes, true);
}
EXPORT_SYMBOL_GPL(sk_msg_free_partial);
void sk_msg_free_partial_nocharge(struct sock *sk, struct sk_msg *msg,
u32 bytes)
{
__sk_msg_free_partial(sk, msg, bytes, false);
}
void sk_msg_trim(struct sock *sk, struct sk_msg *msg, int len)
{
int trim = msg->sg.size - len;
u32 i = msg->sg.end;
if (trim <= 0) {
WARN_ON(trim < 0);
return;
}
sk_msg_iter_var_prev(i);
msg->sg.size = len;
while (msg->sg.data[i].length &&
trim >= msg->sg.data[i].length) {
trim -= msg->sg.data[i].length;
sk_msg_free_elem(sk, msg, i, true);
sk_msg_iter_var_prev(i);
if (!trim)
goto out;
}
msg->sg.data[i].length -= trim;
sk_mem_uncharge(sk, trim);
net/tls: fix sk_msg trim on fallback to copy mode sk_msg_trim() tries to only update curr pointer if it falls into the trimmed region. The logic, however, does not take into the account pointer wrapping that sk_msg_iter_var_prev() does nor (as John points out) the fact that msg->sg is a ring buffer. This means that when the message was trimmed completely, the new curr pointer would have the value of MAX_MSG_FRAGS - 1, which is neither smaller than any other value, nor would it actually be correct. Special case the trimming to 0 length a little bit and rework the comparison between curr and end to take into account wrapping. This bug caused the TLS code to not copy all of the message, if zero copy filled in fewer sg entries than memcopy would need. Big thanks to Alexander Potapenko for the non-KMSAN reproducer. v2: - take into account that msg->sg is a ring buffer (John). Link: https://lore.kernel.org/netdev/20191030160542.30295-1-jakub.kicinski@netronome.com/ (v1) Fixes: d829e9c4112b ("tls: convert to generic sk_msg interface") Reported-by: syzbot+f8495bff23a879a6d0bd@syzkaller.appspotmail.com Reported-by: syzbot+6f50c99e8f6194bf363f@syzkaller.appspotmail.com Co-developed-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-11-04 23:36:57 +00:00
/* Adjust copybreak if it falls into the trimmed part of last buf */
if (msg->sg.curr == i && msg->sg.copybreak > msg->sg.data[i].length)
msg->sg.copybreak = msg->sg.data[i].length;
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 00:45:58 +00:00
out:
net/tls: fix sk_msg trim on fallback to copy mode sk_msg_trim() tries to only update curr pointer if it falls into the trimmed region. The logic, however, does not take into the account pointer wrapping that sk_msg_iter_var_prev() does nor (as John points out) the fact that msg->sg is a ring buffer. This means that when the message was trimmed completely, the new curr pointer would have the value of MAX_MSG_FRAGS - 1, which is neither smaller than any other value, nor would it actually be correct. Special case the trimming to 0 length a little bit and rework the comparison between curr and end to take into account wrapping. This bug caused the TLS code to not copy all of the message, if zero copy filled in fewer sg entries than memcopy would need. Big thanks to Alexander Potapenko for the non-KMSAN reproducer. v2: - take into account that msg->sg is a ring buffer (John). Link: https://lore.kernel.org/netdev/20191030160542.30295-1-jakub.kicinski@netronome.com/ (v1) Fixes: d829e9c4112b ("tls: convert to generic sk_msg interface") Reported-by: syzbot+f8495bff23a879a6d0bd@syzkaller.appspotmail.com Reported-by: syzbot+6f50c99e8f6194bf363f@syzkaller.appspotmail.com Co-developed-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-11-04 23:36:57 +00:00
sk_msg_iter_var_next(i);
msg->sg.end = i;
/* If we trim data a full sg elem before curr pointer update
* copybreak and current so that any future copy operations
* start at new copy location.
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 00:45:58 +00:00
* However trimed data that has not yet been used in a copy op
* does not require an update.
*/
net/tls: fix sk_msg trim on fallback to copy mode sk_msg_trim() tries to only update curr pointer if it falls into the trimmed region. The logic, however, does not take into the account pointer wrapping that sk_msg_iter_var_prev() does nor (as John points out) the fact that msg->sg is a ring buffer. This means that when the message was trimmed completely, the new curr pointer would have the value of MAX_MSG_FRAGS - 1, which is neither smaller than any other value, nor would it actually be correct. Special case the trimming to 0 length a little bit and rework the comparison between curr and end to take into account wrapping. This bug caused the TLS code to not copy all of the message, if zero copy filled in fewer sg entries than memcopy would need. Big thanks to Alexander Potapenko for the non-KMSAN reproducer. v2: - take into account that msg->sg is a ring buffer (John). Link: https://lore.kernel.org/netdev/20191030160542.30295-1-jakub.kicinski@netronome.com/ (v1) Fixes: d829e9c4112b ("tls: convert to generic sk_msg interface") Reported-by: syzbot+f8495bff23a879a6d0bd@syzkaller.appspotmail.com Reported-by: syzbot+6f50c99e8f6194bf363f@syzkaller.appspotmail.com Co-developed-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-11-04 23:36:57 +00:00
if (!msg->sg.size) {
msg->sg.curr = msg->sg.start;
msg->sg.copybreak = 0;
} else if (sk_msg_iter_dist(msg->sg.start, msg->sg.curr) >=
sk_msg_iter_dist(msg->sg.start, msg->sg.end)) {
sk_msg_iter_var_prev(i);
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 00:45:58 +00:00
msg->sg.curr = i;
msg->sg.copybreak = msg->sg.data[i].length;
}
}
EXPORT_SYMBOL_GPL(sk_msg_trim);
int sk_msg_zerocopy_from_iter(struct sock *sk, struct iov_iter *from,
struct sk_msg *msg, u32 bytes)
{
int i, maxpages, ret = 0, num_elems = sk_msg_elem_used(msg);
const int to_max_pages = MAX_MSG_FRAGS;
struct page *pages[MAX_MSG_FRAGS];
ssize_t orig, copied, use, offset;
orig = msg->sg.size;
while (bytes > 0) {
i = 0;
maxpages = to_max_pages - num_elems;
if (maxpages == 0) {
ret = -EFAULT;
goto out;
}
iov_iter: advancing variants of iov_iter_get_pages{,_alloc}() Most of the users immediately follow successful iov_iter_get_pages() with advancing by the amount it had returned. Provide inline wrappers doing that, convert trivial open-coded uses of those. BTW, iov_iter_get_pages() never returns more than it had been asked to; such checks in cifs ought to be removed someday... Reviewed-by: Jeff Layton <jlayton@kernel.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2022-06-09 14:28:36 +00:00
copied = iov_iter_get_pages2(from, pages, bytes, maxpages,
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 00:45:58 +00:00
&offset);
if (copied <= 0) {
ret = -EFAULT;
goto out;
}
bytes -= copied;
msg->sg.size += copied;
while (copied) {
use = min_t(int, copied, PAGE_SIZE - offset);
sg_set_page(&msg->sg.data[msg->sg.end],
pages[i], use, offset);
sg_unmark_end(&msg->sg.data[msg->sg.end]);
sk_mem_charge(sk, use);
offset = 0;
copied -= use;
sk_msg_iter_next(msg, end);
num_elems++;
i++;
}
/* When zerocopy is mixed with sk_msg_*copy* operations we
* may have a copybreak set in this case clear and prefer
* zerocopy remainder when possible.
*/
msg->sg.copybreak = 0;
msg->sg.curr = msg->sg.end;
}
out:
/* Revert iov_iter updates, msg will need to use 'trim' later if it
* also needs to be cleared.
*/
if (ret)
iov_iter_revert(from, msg->sg.size - orig);
return ret;
}
EXPORT_SYMBOL_GPL(sk_msg_zerocopy_from_iter);
int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from,
struct sk_msg *msg, u32 bytes)
{
int ret = -ENOSPC, i = msg->sg.curr;
struct scatterlist *sge;
u32 copy, buf_size;
void *to;
do {
sge = sk_msg_elem(msg, i);
/* This is possible if a trim operation shrunk the buffer */
if (msg->sg.copybreak >= sge->length) {
msg->sg.copybreak = 0;
sk_msg_iter_var_next(i);
if (i == msg->sg.end)
break;
sge = sk_msg_elem(msg, i);
}
buf_size = sge->length - msg->sg.copybreak;
copy = (buf_size > bytes) ? bytes : buf_size;
to = sg_virt(sge) + msg->sg.copybreak;
msg->sg.copybreak += copy;
if (sk->sk_route_caps & NETIF_F_NOCACHE_COPY)
ret = copy_from_iter_nocache(to, copy, from);
else
ret = copy_from_iter(to, copy, from);
if (ret != copy) {
ret = -EFAULT;
goto out;
}
bytes -= copy;
if (!bytes)
break;
msg->sg.copybreak = 0;
sk_msg_iter_var_next(i);
} while (i != msg->sg.end);
out:
msg->sg.curr = i;
return ret;
}
EXPORT_SYMBOL_GPL(sk_msg_memcopy_from_iter);
skmsg: Extract __tcp_bpf_recvmsg() and tcp_bpf_wait_data() Although these two functions are only used by TCP, they are not specific to TCP at all, both operate on skmsg and ingress_msg, so fit in net/core/skmsg.c very well. And we will need them for non-TCP, so rename and move them to skmsg.c and export them to modules. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20210331023237.41094-13-xiyou.wangcong@gmail.com
2021-03-31 02:32:33 +00:00
/* Receive sk_msg from psock->ingress_msg to @msg. */
int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
int len, int flags)
{
struct iov_iter *iter = &msg->msg_iter;
int peek = flags & MSG_PEEK;
struct sk_msg *msg_rx;
int i, copied = 0;
msg_rx = sk_psock_peek_msg(psock);
while (copied != len) {
struct scatterlist *sge;
if (unlikely(!msg_rx))
break;
i = msg_rx->sg.start;
do {
struct page *page;
int copy;
sge = sk_msg_elem(msg_rx, i);
copy = sge->length;
page = sg_page(sge);
if (copied + copy > len)
copy = len - copied;
copy = copy_page_to_iter(page, sge->offset, copy, iter);
skmsg: Schedule psock work if the cached skb exists on the psock In sk_psock_backlog function, for ingress direction skb, if no new data packet arrives after the skb is cached, the cached skb does not have a chance to be added to the receive queue of psock. As a result, the cached skb cannot be received by the upper-layer application. Fix this by reschedule the psock work to dispose the cached skb in sk_msg_recvmsg function. Fixes: 604326b41a6f ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Liu Jian <liujian56@huawei.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20220907071311.60534-1-liujian56@huawei.com
2022-09-07 07:13:11 +00:00
if (!copy) {
copied = copied ? copied : -EFAULT;
goto out;
}
skmsg: Extract __tcp_bpf_recvmsg() and tcp_bpf_wait_data() Although these two functions are only used by TCP, they are not specific to TCP at all, both operate on skmsg and ingress_msg, so fit in net/core/skmsg.c very well. And we will need them for non-TCP, so rename and move them to skmsg.c and export them to modules. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20210331023237.41094-13-xiyou.wangcong@gmail.com
2021-03-31 02:32:33 +00:00
copied += copy;
if (likely(!peek)) {
sge->offset += copy;
sge->length -= copy;
if (!msg_rx->skb)
sk_mem_uncharge(sk, copy);
msg_rx->sg.size -= copy;
if (!sge->length) {
sk_msg_iter_var_next(i);
if (!msg_rx->skb)
put_page(page);
}
} else {
/* Lets not optimize peek case if copy_page_to_iter
* didn't copy the entire length lets just break.
*/
if (copy != sge->length)
skmsg: Schedule psock work if the cached skb exists on the psock In sk_psock_backlog function, for ingress direction skb, if no new data packet arrives after the skb is cached, the cached skb does not have a chance to be added to the receive queue of psock. As a result, the cached skb cannot be received by the upper-layer application. Fix this by reschedule the psock work to dispose the cached skb in sk_msg_recvmsg function. Fixes: 604326b41a6f ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Liu Jian <liujian56@huawei.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20220907071311.60534-1-liujian56@huawei.com
2022-09-07 07:13:11 +00:00
goto out;
skmsg: Extract __tcp_bpf_recvmsg() and tcp_bpf_wait_data() Although these two functions are only used by TCP, they are not specific to TCP at all, both operate on skmsg and ingress_msg, so fit in net/core/skmsg.c very well. And we will need them for non-TCP, so rename and move them to skmsg.c and export them to modules. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20210331023237.41094-13-xiyou.wangcong@gmail.com
2021-03-31 02:32:33 +00:00
sk_msg_iter_var_next(i);
}
if (copied == len)
break;
skmsg: Fix wrong last sg check in sk_msg_recvmsg() Fix one kernel NULL pointer dereference as below: [ 224.462334] Call Trace: [ 224.462394] __tcp_bpf_recvmsg+0xd3/0x380 [ 224.462441] ? sock_has_perm+0x78/0xa0 [ 224.462463] tcp_bpf_recvmsg+0x12e/0x220 [ 224.462494] inet_recvmsg+0x5b/0xd0 [ 224.462534] __sys_recvfrom+0xc8/0x130 [ 224.462574] ? syscall_trace_enter+0x1df/0x2e0 [ 224.462606] ? __do_page_fault+0x2de/0x500 [ 224.462635] __x64_sys_recvfrom+0x24/0x30 [ 224.462660] do_syscall_64+0x5d/0x1d0 [ 224.462709] entry_SYSCALL_64_after_hwframe+0x65/0xca In commit 9974d37ea75f ("skmsg: Fix invalid last sg check in sk_msg_recvmsg()"), we change last sg check to sg_is_last(), but in sockmap redirection case (without stream_parser/stream_verdict/ skb_verdict), we did not mark the end of the scatterlist. Check the sk_msg_alloc, sk_msg_page_add, and bpf_msg_push_data functions, they all do not mark the end of sg. They are expected to use sg.end for end judgment. So the judgment of '(i != msg_rx->sg.end)' is added back here. Fixes: 9974d37ea75f ("skmsg: Fix invalid last sg check in sk_msg_recvmsg()") Signed-off-by: Liu Jian <liujian56@huawei.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20220809094915.150391-1-liujian56@huawei.com
2022-08-09 09:49:15 +00:00
} while ((i != msg_rx->sg.end) && !sg_is_last(sge));
skmsg: Extract __tcp_bpf_recvmsg() and tcp_bpf_wait_data() Although these two functions are only used by TCP, they are not specific to TCP at all, both operate on skmsg and ingress_msg, so fit in net/core/skmsg.c very well. And we will need them for non-TCP, so rename and move them to skmsg.c and export them to modules. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20210331023237.41094-13-xiyou.wangcong@gmail.com
2021-03-31 02:32:33 +00:00
if (unlikely(peek)) {
msg_rx = sk_psock_next_msg(psock, msg_rx);
if (!msg_rx)
break;
continue;
}
msg_rx->sg.start = i;
skmsg: Fix wrong last sg check in sk_msg_recvmsg() Fix one kernel NULL pointer dereference as below: [ 224.462334] Call Trace: [ 224.462394] __tcp_bpf_recvmsg+0xd3/0x380 [ 224.462441] ? sock_has_perm+0x78/0xa0 [ 224.462463] tcp_bpf_recvmsg+0x12e/0x220 [ 224.462494] inet_recvmsg+0x5b/0xd0 [ 224.462534] __sys_recvfrom+0xc8/0x130 [ 224.462574] ? syscall_trace_enter+0x1df/0x2e0 [ 224.462606] ? __do_page_fault+0x2de/0x500 [ 224.462635] __x64_sys_recvfrom+0x24/0x30 [ 224.462660] do_syscall_64+0x5d/0x1d0 [ 224.462709] entry_SYSCALL_64_after_hwframe+0x65/0xca In commit 9974d37ea75f ("skmsg: Fix invalid last sg check in sk_msg_recvmsg()"), we change last sg check to sg_is_last(), but in sockmap redirection case (without stream_parser/stream_verdict/ skb_verdict), we did not mark the end of the scatterlist. Check the sk_msg_alloc, sk_msg_page_add, and bpf_msg_push_data functions, they all do not mark the end of sg. They are expected to use sg.end for end judgment. So the judgment of '(i != msg_rx->sg.end)' is added back here. Fixes: 9974d37ea75f ("skmsg: Fix invalid last sg check in sk_msg_recvmsg()") Signed-off-by: Liu Jian <liujian56@huawei.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20220809094915.150391-1-liujian56@huawei.com
2022-08-09 09:49:15 +00:00
if (!sge->length && (i == msg_rx->sg.end || sg_is_last(sge))) {
skmsg: Extract __tcp_bpf_recvmsg() and tcp_bpf_wait_data() Although these two functions are only used by TCP, they are not specific to TCP at all, both operate on skmsg and ingress_msg, so fit in net/core/skmsg.c very well. And we will need them for non-TCP, so rename and move them to skmsg.c and export them to modules. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20210331023237.41094-13-xiyou.wangcong@gmail.com
2021-03-31 02:32:33 +00:00
msg_rx = sk_psock_dequeue_msg(psock);
kfree_sk_msg(msg_rx);
}
msg_rx = sk_psock_peek_msg(psock);
}
skmsg: Schedule psock work if the cached skb exists on the psock In sk_psock_backlog function, for ingress direction skb, if no new data packet arrives after the skb is cached, the cached skb does not have a chance to be added to the receive queue of psock. As a result, the cached skb cannot be received by the upper-layer application. Fix this by reschedule the psock work to dispose the cached skb in sk_msg_recvmsg function. Fixes: 604326b41a6f ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Liu Jian <liujian56@huawei.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20220907071311.60534-1-liujian56@huawei.com
2022-09-07 07:13:11 +00:00
out:
skmsg: Extract __tcp_bpf_recvmsg() and tcp_bpf_wait_data() Although these two functions are only used by TCP, they are not specific to TCP at all, both operate on skmsg and ingress_msg, so fit in net/core/skmsg.c very well. And we will need them for non-TCP, so rename and move them to skmsg.c and export them to modules. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20210331023237.41094-13-xiyou.wangcong@gmail.com
2021-03-31 02:32:33 +00:00
return copied;
}
EXPORT_SYMBOL_GPL(sk_msg_recvmsg);
skmsg: Extract and reuse sk_msg_is_readable() tcp_bpf_sock_is_readable() is pretty much generic, we can extract it and reuse it for non-TCP sockets. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20211008203306.37525-3-xiyou.wangcong@gmail.com
2021-10-08 20:33:04 +00:00
bool sk_msg_is_readable(struct sock *sk)
{
struct sk_psock *psock;
bool empty = true;
rcu_read_lock();
psock = sk_psock(sk);
if (likely(psock))
empty = list_empty(&psock->ingress_msg);
rcu_read_unlock();
return !empty;
}
EXPORT_SYMBOL_GPL(sk_msg_is_readable);
skmsg: pass gfp argument to alloc_sk_msg() syzbot found that alloc_sk_msg() could be called from a non sleepable context. sk_psock_verdict_recv() uses rcu_read_lock() protection. We need the callers to pass a gfp_t argument to avoid issues. syzbot report was: BUG: sleeping function called from invalid context at include/linux/sched/mm.h:274 in_atomic(): 0, irqs_disabled(): 0, non_block: 0, pid: 3613, name: syz-executor414 preempt_count: 0, expected: 0 RCU nest depth: 1, expected: 0 INFO: lockdep is turned off. CPU: 0 PID: 3613 Comm: syz-executor414 Not tainted 6.0.0-syzkaller-09589-g55be6084c8e0 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/22/2022 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x1e3/0x2cb lib/dump_stack.c:106 __might_resched+0x538/0x6a0 kernel/sched/core.c:9877 might_alloc include/linux/sched/mm.h:274 [inline] slab_pre_alloc_hook mm/slab.h:700 [inline] slab_alloc_node mm/slub.c:3162 [inline] slab_alloc mm/slub.c:3256 [inline] kmem_cache_alloc_trace+0x59/0x310 mm/slub.c:3287 kmalloc include/linux/slab.h:600 [inline] kzalloc include/linux/slab.h:733 [inline] alloc_sk_msg net/core/skmsg.c:507 [inline] sk_psock_skb_ingress_self+0x5c/0x330 net/core/skmsg.c:600 sk_psock_verdict_apply+0x395/0x440 net/core/skmsg.c:1014 sk_psock_verdict_recv+0x34d/0x560 net/core/skmsg.c:1201 tcp_read_skb+0x4a1/0x790 net/ipv4/tcp.c:1770 tcp_rcv_established+0x129d/0x1a10 net/ipv4/tcp_input.c:5971 tcp_v4_do_rcv+0x479/0xac0 net/ipv4/tcp_ipv4.c:1681 sk_backlog_rcv include/net/sock.h:1109 [inline] __release_sock+0x1d8/0x4c0 net/core/sock.c:2906 release_sock+0x5d/0x1c0 net/core/sock.c:3462 tcp_sendmsg+0x36/0x40 net/ipv4/tcp.c:1483 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg net/socket.c:734 [inline] __sys_sendto+0x46d/0x5f0 net/socket.c:2117 __do_sys_sendto net/socket.c:2129 [inline] __se_sys_sendto net/socket.c:2125 [inline] __x64_sys_sendto+0xda/0xf0 net/socket.c:2125 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x2b/0x70 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Fixes: 43312915b5ba ("skmsg: Get rid of unncessary memset()") Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Cong Wang <cong.wang@bytedance.com> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2022-10-15 21:24:41 +00:00
static struct sk_msg *alloc_sk_msg(gfp_t gfp)
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 00:45:58 +00:00
{
struct sk_msg *msg;
skmsg: pass gfp argument to alloc_sk_msg() syzbot found that alloc_sk_msg() could be called from a non sleepable context. sk_psock_verdict_recv() uses rcu_read_lock() protection. We need the callers to pass a gfp_t argument to avoid issues. syzbot report was: BUG: sleeping function called from invalid context at include/linux/sched/mm.h:274 in_atomic(): 0, irqs_disabled(): 0, non_block: 0, pid: 3613, name: syz-executor414 preempt_count: 0, expected: 0 RCU nest depth: 1, expected: 0 INFO: lockdep is turned off. CPU: 0 PID: 3613 Comm: syz-executor414 Not tainted 6.0.0-syzkaller-09589-g55be6084c8e0 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/22/2022 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x1e3/0x2cb lib/dump_stack.c:106 __might_resched+0x538/0x6a0 kernel/sched/core.c:9877 might_alloc include/linux/sched/mm.h:274 [inline] slab_pre_alloc_hook mm/slab.h:700 [inline] slab_alloc_node mm/slub.c:3162 [inline] slab_alloc mm/slub.c:3256 [inline] kmem_cache_alloc_trace+0x59/0x310 mm/slub.c:3287 kmalloc include/linux/slab.h:600 [inline] kzalloc include/linux/slab.h:733 [inline] alloc_sk_msg net/core/skmsg.c:507 [inline] sk_psock_skb_ingress_self+0x5c/0x330 net/core/skmsg.c:600 sk_psock_verdict_apply+0x395/0x440 net/core/skmsg.c:1014 sk_psock_verdict_recv+0x34d/0x560 net/core/skmsg.c:1201 tcp_read_skb+0x4a1/0x790 net/ipv4/tcp.c:1770 tcp_rcv_established+0x129d/0x1a10 net/ipv4/tcp_input.c:5971 tcp_v4_do_rcv+0x479/0xac0 net/ipv4/tcp_ipv4.c:1681 sk_backlog_rcv include/net/sock.h:1109 [inline] __release_sock+0x1d8/0x4c0 net/core/sock.c:2906 release_sock+0x5d/0x1c0 net/core/sock.c:3462 tcp_sendmsg+0x36/0x40 net/ipv4/tcp.c:1483 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg net/socket.c:734 [inline] __sys_sendto+0x46d/0x5f0 net/socket.c:2117 __do_sys_sendto net/socket.c:2129 [inline] __se_sys_sendto net/socket.c:2125 [inline] __x64_sys_sendto+0xda/0xf0 net/socket.c:2125 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x2b/0x70 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Fixes: 43312915b5ba ("skmsg: Get rid of unncessary memset()") Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Cong Wang <cong.wang@bytedance.com> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2022-10-15 21:24:41 +00:00
msg = kzalloc(sizeof(*msg), gfp | __GFP_NOWARN);
skmsg: Get rid of unncessary memset() We always allocate skmsg with kzalloc(), so there is no need to call memset(0) on it, the only thing we need from sk_msg_init() is sg_init_marker(). So introduce a new helper which is just kzalloc()+sg_init_marker(), this saves an unncessary memset(0) for skmsg on fast path. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20220615162014.89193-5-xiyou.wangcong@gmail.com
2022-06-15 16:20:14 +00:00
if (unlikely(!msg))
bpf, sockmap: Avoid returning unneeded EAGAIN when redirecting to self If a socket redirects to itself and it is under memory pressure it is possible to get a socket stuck so that recv() returns EAGAIN and the socket can not advance for some time. This happens because when redirecting a skb to the same socket we received the skb on we first check if it is OK to enqueue the skb on the receiving socket by checking memory limits. But, if the skb is itself the object holding the memory needed to enqueue the skb we will keep retrying from kernel side and always fail with EAGAIN. Then userspace will get a recv() EAGAIN error if there are no skbs in the psock ingress queue. This will continue until either some skbs get kfree'd causing the memory pressure to reduce far enough that we can enqueue the pending packet or the socket is destroyed. In some cases its possible to get a socket stuck for a noticeable amount of time if the socket is only receiving skbs from sk_skb verdict programs. To reproduce I make the socket memory limits ridiculously low so sockets are always under memory pressure. More often though if under memory pressure it looks like a spurious EAGAIN error on user space side causing userspace to retry and typically enough has moved on the memory side that it works. To fix skip memory checks and skb_orphan if receiving on the same sock as already assigned. For SK_PASS cases this is easy, its always the same socket so we can just omit the orphan/set_owner pair. For backlog cases we need to check skb->sk and decide if the orphan and set_owner pair are needed. Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/160556572660.73229.12566203819812939627.stgit@john-XPS-13-9370
2020-11-16 22:28:46 +00:00
return NULL;
skmsg: Get rid of unncessary memset() We always allocate skmsg with kzalloc(), so there is no need to call memset(0) on it, the only thing we need from sk_msg_init() is sg_init_marker(). So introduce a new helper which is just kzalloc()+sg_init_marker(), this saves an unncessary memset(0) for skmsg on fast path. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20220615162014.89193-5-xiyou.wangcong@gmail.com
2022-06-15 16:20:14 +00:00
sg_init_marker(msg->sg.data, NR_MSG_FRAG_IDS);
return msg;
}
bpf, sockmap: Avoid returning unneeded EAGAIN when redirecting to self If a socket redirects to itself and it is under memory pressure it is possible to get a socket stuck so that recv() returns EAGAIN and the socket can not advance for some time. This happens because when redirecting a skb to the same socket we received the skb on we first check if it is OK to enqueue the skb on the receiving socket by checking memory limits. But, if the skb is itself the object holding the memory needed to enqueue the skb we will keep retrying from kernel side and always fail with EAGAIN. Then userspace will get a recv() EAGAIN error if there are no skbs in the psock ingress queue. This will continue until either some skbs get kfree'd causing the memory pressure to reduce far enough that we can enqueue the pending packet or the socket is destroyed. In some cases its possible to get a socket stuck for a noticeable amount of time if the socket is only receiving skbs from sk_skb verdict programs. To reproduce I make the socket memory limits ridiculously low so sockets are always under memory pressure. More often though if under memory pressure it looks like a spurious EAGAIN error on user space side causing userspace to retry and typically enough has moved on the memory side that it works. To fix skip memory checks and skb_orphan if receiving on the same sock as already assigned. For SK_PASS cases this is easy, its always the same socket so we can just omit the orphan/set_owner pair. For backlog cases we need to check skb->sk and decide if the orphan and set_owner pair are needed. Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/160556572660.73229.12566203819812939627.stgit@john-XPS-13-9370
2020-11-16 22:28:46 +00:00
skmsg: Get rid of unncessary memset() We always allocate skmsg with kzalloc(), so there is no need to call memset(0) on it, the only thing we need from sk_msg_init() is sg_init_marker(). So introduce a new helper which is just kzalloc()+sg_init_marker(), this saves an unncessary memset(0) for skmsg on fast path. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20220615162014.89193-5-xiyou.wangcong@gmail.com
2022-06-15 16:20:14 +00:00
static struct sk_msg *sk_psock_create_ingress_msg(struct sock *sk,
struct sk_buff *skb)
{
if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf)
bpf, sockmap: Avoid returning unneeded EAGAIN when redirecting to self If a socket redirects to itself and it is under memory pressure it is possible to get a socket stuck so that recv() returns EAGAIN and the socket can not advance for some time. This happens because when redirecting a skb to the same socket we received the skb on we first check if it is OK to enqueue the skb on the receiving socket by checking memory limits. But, if the skb is itself the object holding the memory needed to enqueue the skb we will keep retrying from kernel side and always fail with EAGAIN. Then userspace will get a recv() EAGAIN error if there are no skbs in the psock ingress queue. This will continue until either some skbs get kfree'd causing the memory pressure to reduce far enough that we can enqueue the pending packet or the socket is destroyed. In some cases its possible to get a socket stuck for a noticeable amount of time if the socket is only receiving skbs from sk_skb verdict programs. To reproduce I make the socket memory limits ridiculously low so sockets are always under memory pressure. More often though if under memory pressure it looks like a spurious EAGAIN error on user space side causing userspace to retry and typically enough has moved on the memory side that it works. To fix skip memory checks and skb_orphan if receiving on the same sock as already assigned. For SK_PASS cases this is easy, its always the same socket so we can just omit the orphan/set_owner pair. For backlog cases we need to check skb->sk and decide if the orphan and set_owner pair are needed. Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/160556572660.73229.12566203819812939627.stgit@john-XPS-13-9370
2020-11-16 22:28:46 +00:00
return NULL;
bpf, sockmap: Ensure SO_RCVBUF memory is observed on ingress redirect Fix sockmap sk_skb programs so that they observe sk_rcvbuf limits. This allows users to tune SO_RCVBUF and sockmap will honor them. We can refactor the if(charge) case out in later patches. But, keep this fix to the point. Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path") Suggested-by: Jakub Sitnicki <jakub@cloudflare.com> Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/160556568657.73229.8404601585878439060.stgit@john-XPS-13-9370
2020-11-16 22:28:06 +00:00
skmsg: Get rid of unncessary memset() We always allocate skmsg with kzalloc(), so there is no need to call memset(0) on it, the only thing we need from sk_msg_init() is sg_init_marker(). So introduce a new helper which is just kzalloc()+sg_init_marker(), this saves an unncessary memset(0) for skmsg on fast path. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20220615162014.89193-5-xiyou.wangcong@gmail.com
2022-06-15 16:20:14 +00:00
if (!sk_rmem_schedule(sk, skb, skb->truesize))
bpf, sockmap: Avoid returning unneeded EAGAIN when redirecting to self If a socket redirects to itself and it is under memory pressure it is possible to get a socket stuck so that recv() returns EAGAIN and the socket can not advance for some time. This happens because when redirecting a skb to the same socket we received the skb on we first check if it is OK to enqueue the skb on the receiving socket by checking memory limits. But, if the skb is itself the object holding the memory needed to enqueue the skb we will keep retrying from kernel side and always fail with EAGAIN. Then userspace will get a recv() EAGAIN error if there are no skbs in the psock ingress queue. This will continue until either some skbs get kfree'd causing the memory pressure to reduce far enough that we can enqueue the pending packet or the socket is destroyed. In some cases its possible to get a socket stuck for a noticeable amount of time if the socket is only receiving skbs from sk_skb verdict programs. To reproduce I make the socket memory limits ridiculously low so sockets are always under memory pressure. More often though if under memory pressure it looks like a spurious EAGAIN error on user space side causing userspace to retry and typically enough has moved on the memory side that it works. To fix skip memory checks and skb_orphan if receiving on the same sock as already assigned. For SK_PASS cases this is easy, its always the same socket so we can just omit the orphan/set_owner pair. For backlog cases we need to check skb->sk and decide if the orphan and set_owner pair are needed. Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/160556572660.73229.12566203819812939627.stgit@john-XPS-13-9370
2020-11-16 22:28:46 +00:00
return 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 00:45:58 +00:00
skmsg: pass gfp argument to alloc_sk_msg() syzbot found that alloc_sk_msg() could be called from a non sleepable context. sk_psock_verdict_recv() uses rcu_read_lock() protection. We need the callers to pass a gfp_t argument to avoid issues. syzbot report was: BUG: sleeping function called from invalid context at include/linux/sched/mm.h:274 in_atomic(): 0, irqs_disabled(): 0, non_block: 0, pid: 3613, name: syz-executor414 preempt_count: 0, expected: 0 RCU nest depth: 1, expected: 0 INFO: lockdep is turned off. CPU: 0 PID: 3613 Comm: syz-executor414 Not tainted 6.0.0-syzkaller-09589-g55be6084c8e0 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/22/2022 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x1e3/0x2cb lib/dump_stack.c:106 __might_resched+0x538/0x6a0 kernel/sched/core.c:9877 might_alloc include/linux/sched/mm.h:274 [inline] slab_pre_alloc_hook mm/slab.h:700 [inline] slab_alloc_node mm/slub.c:3162 [inline] slab_alloc mm/slub.c:3256 [inline] kmem_cache_alloc_trace+0x59/0x310 mm/slub.c:3287 kmalloc include/linux/slab.h:600 [inline] kzalloc include/linux/slab.h:733 [inline] alloc_sk_msg net/core/skmsg.c:507 [inline] sk_psock_skb_ingress_self+0x5c/0x330 net/core/skmsg.c:600 sk_psock_verdict_apply+0x395/0x440 net/core/skmsg.c:1014 sk_psock_verdict_recv+0x34d/0x560 net/core/skmsg.c:1201 tcp_read_skb+0x4a1/0x790 net/ipv4/tcp.c:1770 tcp_rcv_established+0x129d/0x1a10 net/ipv4/tcp_input.c:5971 tcp_v4_do_rcv+0x479/0xac0 net/ipv4/tcp_ipv4.c:1681 sk_backlog_rcv include/net/sock.h:1109 [inline] __release_sock+0x1d8/0x4c0 net/core/sock.c:2906 release_sock+0x5d/0x1c0 net/core/sock.c:3462 tcp_sendmsg+0x36/0x40 net/ipv4/tcp.c:1483 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg net/socket.c:734 [inline] __sys_sendto+0x46d/0x5f0 net/socket.c:2117 __do_sys_sendto net/socket.c:2129 [inline] __se_sys_sendto net/socket.c:2125 [inline] __x64_sys_sendto+0xda/0xf0 net/socket.c:2125 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x2b/0x70 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Fixes: 43312915b5ba ("skmsg: Get rid of unncessary memset()") Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Cong Wang <cong.wang@bytedance.com> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2022-10-15 21:24:41 +00:00
return alloc_sk_msg(GFP_KERNEL);
bpf, sockmap: Avoid returning unneeded EAGAIN when redirecting to self If a socket redirects to itself and it is under memory pressure it is possible to get a socket stuck so that recv() returns EAGAIN and the socket can not advance for some time. This happens because when redirecting a skb to the same socket we received the skb on we first check if it is OK to enqueue the skb on the receiving socket by checking memory limits. But, if the skb is itself the object holding the memory needed to enqueue the skb we will keep retrying from kernel side and always fail with EAGAIN. Then userspace will get a recv() EAGAIN error if there are no skbs in the psock ingress queue. This will continue until either some skbs get kfree'd causing the memory pressure to reduce far enough that we can enqueue the pending packet or the socket is destroyed. In some cases its possible to get a socket stuck for a noticeable amount of time if the socket is only receiving skbs from sk_skb verdict programs. To reproduce I make the socket memory limits ridiculously low so sockets are always under memory pressure. More often though if under memory pressure it looks like a spurious EAGAIN error on user space side causing userspace to retry and typically enough has moved on the memory side that it works. To fix skip memory checks and skb_orphan if receiving on the same sock as already assigned. For SK_PASS cases this is easy, its always the same socket so we can just omit the orphan/set_owner pair. For backlog cases we need to check skb->sk and decide if the orphan and set_owner pair are needed. Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/160556572660.73229.12566203819812939627.stgit@john-XPS-13-9370
2020-11-16 22:28:46 +00:00
}
static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb,
skmsg: Lose offset info in sk_psock_skb_ingress If sockmap enable strparser, there are lose offset info in sk_psock_skb_ingress(). If the length determined by parse_msg function is not skb->len, the skb will be converted to sk_msg multiple times, and userspace app will get the data multiple times. Fix this by get the offset and length from strp_msg. And as Cong suggested, add one bit in skb->_sk_redir to distinguish enable or disable strparser. Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Liu Jian <liujian56@huawei.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Cong Wang <cong.wang@bytedance.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20211029141216.211899-1-liujian56@huawei.com
2021-10-29 14:12:14 +00:00
u32 off, u32 len,
bpf, sockmap: Avoid returning unneeded EAGAIN when redirecting to self If a socket redirects to itself and it is under memory pressure it is possible to get a socket stuck so that recv() returns EAGAIN and the socket can not advance for some time. This happens because when redirecting a skb to the same socket we received the skb on we first check if it is OK to enqueue the skb on the receiving socket by checking memory limits. But, if the skb is itself the object holding the memory needed to enqueue the skb we will keep retrying from kernel side and always fail with EAGAIN. Then userspace will get a recv() EAGAIN error if there are no skbs in the psock ingress queue. This will continue until either some skbs get kfree'd causing the memory pressure to reduce far enough that we can enqueue the pending packet or the socket is destroyed. In some cases its possible to get a socket stuck for a noticeable amount of time if the socket is only receiving skbs from sk_skb verdict programs. To reproduce I make the socket memory limits ridiculously low so sockets are always under memory pressure. More often though if under memory pressure it looks like a spurious EAGAIN error on user space side causing userspace to retry and typically enough has moved on the memory side that it works. To fix skip memory checks and skb_orphan if receiving on the same sock as already assigned. For SK_PASS cases this is easy, its always the same socket so we can just omit the orphan/set_owner pair. For backlog cases we need to check skb->sk and decide if the orphan and set_owner pair are needed. Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/160556572660.73229.12566203819812939627.stgit@john-XPS-13-9370
2020-11-16 22:28:46 +00:00
struct sk_psock *psock,
struct sock *sk,
struct sk_msg *msg)
{
bpf, sockmap: Avoid failures from skb_to_sgvec when skb has frag_list When skb has a frag_list its possible for skb_to_sgvec() to fail. This happens when the scatterlist has fewer elements to store pages than would be needed for the initial skb plus any of its frags. This case appears rare, but is possible when running an RX parser/verdict programs exposed to the internet. Currently, when this happens we throw an error, break the pipe, and kfree the msg. This effectively breaks the application or forces it to do a retry. Lets catch this case and handle it by doing an skb_linearize() on any skb we receive with frags. At this point skb_to_sgvec should not fail because the failing conditions would require frags to be in place. Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/160556576837.73229.14800682790808797635.stgit@john-XPS-13-9370
2020-11-16 22:29:28 +00:00
int num_sge, copied;
bpf, sockmap: Avoid returning unneeded EAGAIN when redirecting to self If a socket redirects to itself and it is under memory pressure it is possible to get a socket stuck so that recv() returns EAGAIN and the socket can not advance for some time. This happens because when redirecting a skb to the same socket we received the skb on we first check if it is OK to enqueue the skb on the receiving socket by checking memory limits. But, if the skb is itself the object holding the memory needed to enqueue the skb we will keep retrying from kernel side and always fail with EAGAIN. Then userspace will get a recv() EAGAIN error if there are no skbs in the psock ingress queue. This will continue until either some skbs get kfree'd causing the memory pressure to reduce far enough that we can enqueue the pending packet or the socket is destroyed. In some cases its possible to get a socket stuck for a noticeable amount of time if the socket is only receiving skbs from sk_skb verdict programs. To reproduce I make the socket memory limits ridiculously low so sockets are always under memory pressure. More often though if under memory pressure it looks like a spurious EAGAIN error on user space side causing userspace to retry and typically enough has moved on the memory side that it works. To fix skip memory checks and skb_orphan if receiving on the same sock as already assigned. For SK_PASS cases this is easy, its always the same socket so we can just omit the orphan/set_owner pair. For backlog cases we need to check skb->sk and decide if the orphan and set_owner pair are needed. Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/160556572660.73229.12566203819812939627.stgit@john-XPS-13-9370
2020-11-16 22:28:46 +00:00
skmsg: Lose offset info in sk_psock_skb_ingress If sockmap enable strparser, there are lose offset info in sk_psock_skb_ingress(). If the length determined by parse_msg function is not skb->len, the skb will be converted to sk_msg multiple times, and userspace app will get the data multiple times. Fix this by get the offset and length from strp_msg. And as Cong suggested, add one bit in skb->_sk_redir to distinguish enable or disable strparser. Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Liu Jian <liujian56@huawei.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Cong Wang <cong.wang@bytedance.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20211029141216.211899-1-liujian56@huawei.com
2021-10-29 14:12:14 +00:00
num_sge = skb_to_sgvec(skb, msg->sg.data, off, len);
bpf, sockmap: Call skb_linearize only when required in sk_psock_skb_ingress_enqueue The skb_to_sgvec fails only when the number of frag_list and frags exceeds MAX_MSG_FRAGS. Therefore, we can call skb_linearize only when the conversion fails. Signed-off-by: Liu Jian <liujian56@huawei.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20220427115150.210213-1-liujian56@huawei.com
2022-04-27 11:51:50 +00:00
if (num_sge < 0) {
/* skb linearize may fail with ENOMEM, but lets simply try again
* later if this happens. Under memory pressure we don't want to
* drop the skb. We need to linearize the skb so that the mapping
* in skb_to_sgvec can not error.
*/
if (skb_linearize(skb))
return -EAGAIN;
num_sge = skb_to_sgvec(skb, msg->sg.data, off, len);
if (unlikely(num_sge < 0))
return num_sge;
}
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 00:45:58 +00:00
skmsg: Lose offset info in sk_psock_skb_ingress If sockmap enable strparser, there are lose offset info in sk_psock_skb_ingress(). If the length determined by parse_msg function is not skb->len, the skb will be converted to sk_msg multiple times, and userspace app will get the data multiple times. Fix this by get the offset and length from strp_msg. And as Cong suggested, add one bit in skb->_sk_redir to distinguish enable or disable strparser. Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Liu Jian <liujian56@huawei.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Cong Wang <cong.wang@bytedance.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20211029141216.211899-1-liujian56@huawei.com
2021-10-29 14:12:14 +00:00
copied = 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 00:45:58 +00:00
msg->sg.start = 0;
bpf: sockmap fix msg->sg.size account on ingress skb When converting a skb to msg->sg we forget to set the size after the latest ktls/tls code conversion. This patch can be reached by doing a redir into ingress path from BPF skb sock recv hook. Then trying to read the size fails. Fix this by setting the size. Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-05-13 14:19:55 +00:00
msg->sg.size = copied;
net: skmsg: fix TLS 1.3 crash with full sk_msg TLS 1.3 started using the entry at the end of the SG array for chaining-in the single byte content type entry. This mostly works: [ E E E E E E . . ] ^ ^ start end E < content type / [ E E E E E E C . ] ^ ^ start end (Where E denotes a populated SG entry; C denotes a chaining entry.) If the array is full, however, the end will point to the start: [ E E E E E E E E ] ^ start end And we end up overwriting the start: E < content type / [ C E E E E E E E ] ^ start end The sg array is supposed to be a circular buffer with start and end markers pointing anywhere. In case where start > end (i.e. the circular buffer has "wrapped") there is an extra entry reserved at the end to chain the two halves together. [ E E E E E E . . l ] (Where l is the reserved entry for "looping" back to front. As suggested by John, let's reserve another entry for chaining SG entries after the main circular buffer. Note that this entry has to be pointed to by the end entry so its position is not fixed. Examples of full messages: [ E E E E E E E E . l ] ^ ^ start end <---------------. [ E E . E E E E E E l ] ^ ^ end start Now the end will always point to an unused entry, so TLS 1.3 can always use it. Fixes: 130b392c6cd6 ("net: tls: Add tls 1.3 support") Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com> Reviewed-by: Simon Horman <simon.horman@netronome.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-11-27 20:16:41 +00:00
msg->sg.end = num_sge;
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 00:45:58 +00:00
msg->skb = skb;
sk_psock_queue_msg(psock, msg);
bpf: sk_msg, fix socket data_ready events When a skb verdict program is in-use and either another BPF program redirects to that socket or the new SK_PASS support is used the data_ready callback does not wake up application. Instead because the stream parser/verdict is using the sk data_ready callback we wake up the stream parser/verdict block. Fix this by adding a helper to check if the stream parser block is enabled on the sk and if so call the saved pointer which is the upper layers wake up function. This fixes application stalls observed when an application is waiting for data in a blocking read(). Fixes: d829e9c4112b ("tls: convert to generic sk_msg interface") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-12-20 19:35:33 +00:00
sk_psock_data_ready(sk, 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 00:45:58 +00:00
return copied;
}
skmsg: Lose offset info in sk_psock_skb_ingress If sockmap enable strparser, there are lose offset info in sk_psock_skb_ingress(). If the length determined by parse_msg function is not skb->len, the skb will be converted to sk_msg multiple times, and userspace app will get the data multiple times. Fix this by get the offset and length from strp_msg. And as Cong suggested, add one bit in skb->_sk_redir to distinguish enable or disable strparser. Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Liu Jian <liujian56@huawei.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Cong Wang <cong.wang@bytedance.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20211029141216.211899-1-liujian56@huawei.com
2021-10-29 14:12:14 +00:00
static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb,
u32 off, u32 len);
bpf, sockmap: Handle memory acct if skb_verdict prog redirects to self If the skb_verdict_prog redirects an skb knowingly to itself, fix your BPF program this is not optimal and an abuse of the API please use SK_PASS. That said there may be cases, such as socket load balancing, where picking the socket is hashed based or otherwise picks the same socket it was received on in some rare cases. If this happens we don't want to confuse userspace giving them an EAGAIN error if we can avoid it. To avoid double accounting in these cases. At the moment even if the skb has already been charged against the sockets rcvbuf and forward alloc we check it again and do set_owner_r() causing it to be orphaned and recharged. For one this is useless work, but more importantly we can have a case where the skb could be put on the ingress queue, but because we are under memory pressure we return EAGAIN. The trouble here is the skb has already been accounted for so any rcvbuf checks include the memory associated with the packet already. This rolls up and can result in unnecessary EAGAIN errors in userspace read() calls. Fix by doing an unlikely check and skipping checks if skb->sk == sk. Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/160556574804.73229.11328201020039674147.stgit@john-XPS-13-9370
2020-11-16 22:29:08 +00:00
skmsg: Lose offset info in sk_psock_skb_ingress If sockmap enable strparser, there are lose offset info in sk_psock_skb_ingress(). If the length determined by parse_msg function is not skb->len, the skb will be converted to sk_msg multiple times, and userspace app will get the data multiple times. Fix this by get the offset and length from strp_msg. And as Cong suggested, add one bit in skb->_sk_redir to distinguish enable or disable strparser. Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Liu Jian <liujian56@huawei.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Cong Wang <cong.wang@bytedance.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20211029141216.211899-1-liujian56@huawei.com
2021-10-29 14:12:14 +00:00
static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb,
u32 off, u32 len)
bpf, sockmap: Avoid returning unneeded EAGAIN when redirecting to self If a socket redirects to itself and it is under memory pressure it is possible to get a socket stuck so that recv() returns EAGAIN and the socket can not advance for some time. This happens because when redirecting a skb to the same socket we received the skb on we first check if it is OK to enqueue the skb on the receiving socket by checking memory limits. But, if the skb is itself the object holding the memory needed to enqueue the skb we will keep retrying from kernel side and always fail with EAGAIN. Then userspace will get a recv() EAGAIN error if there are no skbs in the psock ingress queue. This will continue until either some skbs get kfree'd causing the memory pressure to reduce far enough that we can enqueue the pending packet or the socket is destroyed. In some cases its possible to get a socket stuck for a noticeable amount of time if the socket is only receiving skbs from sk_skb verdict programs. To reproduce I make the socket memory limits ridiculously low so sockets are always under memory pressure. More often though if under memory pressure it looks like a spurious EAGAIN error on user space side causing userspace to retry and typically enough has moved on the memory side that it works. To fix skip memory checks and skb_orphan if receiving on the same sock as already assigned. For SK_PASS cases this is easy, its always the same socket so we can just omit the orphan/set_owner pair. For backlog cases we need to check skb->sk and decide if the orphan and set_owner pair are needed. Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/160556572660.73229.12566203819812939627.stgit@john-XPS-13-9370
2020-11-16 22:28:46 +00:00
{
struct sock *sk = psock->sk;
struct sk_msg *msg;
bpf, sockmap: Fix potential memory leak on unlikely error case If skb_linearize is needed and fails we could leak a msg on the error handling. To fix ensure we kfree the msg block before returning error. Found during code review. Fixes: 4363023d2668e ("bpf, sockmap: Avoid failures from skb_to_sgvec when skb has frag_list") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Cong Wang <cong.wang@bytedance.com> Link: https://lore.kernel.org/bpf/20210712195546.423990-2-john.fastabend@gmail.com
2021-07-12 19:55:45 +00:00
int err;
bpf, sockmap: Avoid returning unneeded EAGAIN when redirecting to self If a socket redirects to itself and it is under memory pressure it is possible to get a socket stuck so that recv() returns EAGAIN and the socket can not advance for some time. This happens because when redirecting a skb to the same socket we received the skb on we first check if it is OK to enqueue the skb on the receiving socket by checking memory limits. But, if the skb is itself the object holding the memory needed to enqueue the skb we will keep retrying from kernel side and always fail with EAGAIN. Then userspace will get a recv() EAGAIN error if there are no skbs in the psock ingress queue. This will continue until either some skbs get kfree'd causing the memory pressure to reduce far enough that we can enqueue the pending packet or the socket is destroyed. In some cases its possible to get a socket stuck for a noticeable amount of time if the socket is only receiving skbs from sk_skb verdict programs. To reproduce I make the socket memory limits ridiculously low so sockets are always under memory pressure. More often though if under memory pressure it looks like a spurious EAGAIN error on user space side causing userspace to retry and typically enough has moved on the memory side that it works. To fix skip memory checks and skb_orphan if receiving on the same sock as already assigned. For SK_PASS cases this is easy, its always the same socket so we can just omit the orphan/set_owner pair. For backlog cases we need to check skb->sk and decide if the orphan and set_owner pair are needed. Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/160556572660.73229.12566203819812939627.stgit@john-XPS-13-9370
2020-11-16 22:28:46 +00:00
bpf, sockmap: Handle memory acct if skb_verdict prog redirects to self If the skb_verdict_prog redirects an skb knowingly to itself, fix your BPF program this is not optimal and an abuse of the API please use SK_PASS. That said there may be cases, such as socket load balancing, where picking the socket is hashed based or otherwise picks the same socket it was received on in some rare cases. If this happens we don't want to confuse userspace giving them an EAGAIN error if we can avoid it. To avoid double accounting in these cases. At the moment even if the skb has already been charged against the sockets rcvbuf and forward alloc we check it again and do set_owner_r() causing it to be orphaned and recharged. For one this is useless work, but more importantly we can have a case where the skb could be put on the ingress queue, but because we are under memory pressure we return EAGAIN. The trouble here is the skb has already been accounted for so any rcvbuf checks include the memory associated with the packet already. This rolls up and can result in unnecessary EAGAIN errors in userspace read() calls. Fix by doing an unlikely check and skipping checks if skb->sk == sk. Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/160556574804.73229.11328201020039674147.stgit@john-XPS-13-9370
2020-11-16 22:29:08 +00:00
/* If we are receiving on the same sock skb->sk is already assigned,
* skip memory accounting and owner transition seeing it already set
* correctly.
*/
if (unlikely(skb->sk == sk))
skmsg: Lose offset info in sk_psock_skb_ingress If sockmap enable strparser, there are lose offset info in sk_psock_skb_ingress(). If the length determined by parse_msg function is not skb->len, the skb will be converted to sk_msg multiple times, and userspace app will get the data multiple times. Fix this by get the offset and length from strp_msg. And as Cong suggested, add one bit in skb->_sk_redir to distinguish enable or disable strparser. Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Liu Jian <liujian56@huawei.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Cong Wang <cong.wang@bytedance.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20211029141216.211899-1-liujian56@huawei.com
2021-10-29 14:12:14 +00:00
return sk_psock_skb_ingress_self(psock, skb, off, len);
bpf, sockmap: Avoid returning unneeded EAGAIN when redirecting to self If a socket redirects to itself and it is under memory pressure it is possible to get a socket stuck so that recv() returns EAGAIN and the socket can not advance for some time. This happens because when redirecting a skb to the same socket we received the skb on we first check if it is OK to enqueue the skb on the receiving socket by checking memory limits. But, if the skb is itself the object holding the memory needed to enqueue the skb we will keep retrying from kernel side and always fail with EAGAIN. Then userspace will get a recv() EAGAIN error if there are no skbs in the psock ingress queue. This will continue until either some skbs get kfree'd causing the memory pressure to reduce far enough that we can enqueue the pending packet or the socket is destroyed. In some cases its possible to get a socket stuck for a noticeable amount of time if the socket is only receiving skbs from sk_skb verdict programs. To reproduce I make the socket memory limits ridiculously low so sockets are always under memory pressure. More often though if under memory pressure it looks like a spurious EAGAIN error on user space side causing userspace to retry and typically enough has moved on the memory side that it works. To fix skip memory checks and skb_orphan if receiving on the same sock as already assigned. For SK_PASS cases this is easy, its always the same socket so we can just omit the orphan/set_owner pair. For backlog cases we need to check skb->sk and decide if the orphan and set_owner pair are needed. Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/160556572660.73229.12566203819812939627.stgit@john-XPS-13-9370
2020-11-16 22:28:46 +00:00
msg = sk_psock_create_ingress_msg(sk, skb);
if (!msg)
return -EAGAIN;
/* This will transition ownership of the data from the socket where
* the BPF program was run initiating the redirect to the socket
* we will eventually receive this data on. The data will be released
* from skb_consume found in __tcp_bpf_recvmsg() after its been copied
* into user buffers.
*/
skb_set_owner_r(skb, sk);
skmsg: Lose offset info in sk_psock_skb_ingress If sockmap enable strparser, there are lose offset info in sk_psock_skb_ingress(). If the length determined by parse_msg function is not skb->len, the skb will be converted to sk_msg multiple times, and userspace app will get the data multiple times. Fix this by get the offset and length from strp_msg. And as Cong suggested, add one bit in skb->_sk_redir to distinguish enable or disable strparser. Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Liu Jian <liujian56@huawei.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Cong Wang <cong.wang@bytedance.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20211029141216.211899-1-liujian56@huawei.com
2021-10-29 14:12:14 +00:00
err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg);
bpf, sockmap: Fix potential memory leak on unlikely error case If skb_linearize is needed and fails we could leak a msg on the error handling. To fix ensure we kfree the msg block before returning error. Found during code review. Fixes: 4363023d2668e ("bpf, sockmap: Avoid failures from skb_to_sgvec when skb has frag_list") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Cong Wang <cong.wang@bytedance.com> Link: https://lore.kernel.org/bpf/20210712195546.423990-2-john.fastabend@gmail.com
2021-07-12 19:55:45 +00:00
if (err < 0)
kfree(msg);
return err;
bpf, sockmap: Avoid returning unneeded EAGAIN when redirecting to self If a socket redirects to itself and it is under memory pressure it is possible to get a socket stuck so that recv() returns EAGAIN and the socket can not advance for some time. This happens because when redirecting a skb to the same socket we received the skb on we first check if it is OK to enqueue the skb on the receiving socket by checking memory limits. But, if the skb is itself the object holding the memory needed to enqueue the skb we will keep retrying from kernel side and always fail with EAGAIN. Then userspace will get a recv() EAGAIN error if there are no skbs in the psock ingress queue. This will continue until either some skbs get kfree'd causing the memory pressure to reduce far enough that we can enqueue the pending packet or the socket is destroyed. In some cases its possible to get a socket stuck for a noticeable amount of time if the socket is only receiving skbs from sk_skb verdict programs. To reproduce I make the socket memory limits ridiculously low so sockets are always under memory pressure. More often though if under memory pressure it looks like a spurious EAGAIN error on user space side causing userspace to retry and typically enough has moved on the memory side that it works. To fix skip memory checks and skb_orphan if receiving on the same sock as already assigned. For SK_PASS cases this is easy, its always the same socket so we can just omit the orphan/set_owner pair. For backlog cases we need to check skb->sk and decide if the orphan and set_owner pair are needed. Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/160556572660.73229.12566203819812939627.stgit@john-XPS-13-9370
2020-11-16 22:28:46 +00:00
}
/* Puts an skb on the ingress queue of the socket already assigned to the
* skb. In this case we do not need to check memory limits or skb_set_owner_r
* because the skb is already accounted for here.
*/
skmsg: Lose offset info in sk_psock_skb_ingress If sockmap enable strparser, there are lose offset info in sk_psock_skb_ingress(). If the length determined by parse_msg function is not skb->len, the skb will be converted to sk_msg multiple times, and userspace app will get the data multiple times. Fix this by get the offset and length from strp_msg. And as Cong suggested, add one bit in skb->_sk_redir to distinguish enable or disable strparser. Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Liu Jian <liujian56@huawei.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Cong Wang <cong.wang@bytedance.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20211029141216.211899-1-liujian56@huawei.com
2021-10-29 14:12:14 +00:00
static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb,
u32 off, u32 len)
bpf, sockmap: Avoid returning unneeded EAGAIN when redirecting to self If a socket redirects to itself and it is under memory pressure it is possible to get a socket stuck so that recv() returns EAGAIN and the socket can not advance for some time. This happens because when redirecting a skb to the same socket we received the skb on we first check if it is OK to enqueue the skb on the receiving socket by checking memory limits. But, if the skb is itself the object holding the memory needed to enqueue the skb we will keep retrying from kernel side and always fail with EAGAIN. Then userspace will get a recv() EAGAIN error if there are no skbs in the psock ingress queue. This will continue until either some skbs get kfree'd causing the memory pressure to reduce far enough that we can enqueue the pending packet or the socket is destroyed. In some cases its possible to get a socket stuck for a noticeable amount of time if the socket is only receiving skbs from sk_skb verdict programs. To reproduce I make the socket memory limits ridiculously low so sockets are always under memory pressure. More often though if under memory pressure it looks like a spurious EAGAIN error on user space side causing userspace to retry and typically enough has moved on the memory side that it works. To fix skip memory checks and skb_orphan if receiving on the same sock as already assigned. For SK_PASS cases this is easy, its always the same socket so we can just omit the orphan/set_owner pair. For backlog cases we need to check skb->sk and decide if the orphan and set_owner pair are needed. Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/160556572660.73229.12566203819812939627.stgit@john-XPS-13-9370
2020-11-16 22:28:46 +00:00
{
skmsg: pass gfp argument to alloc_sk_msg() syzbot found that alloc_sk_msg() could be called from a non sleepable context. sk_psock_verdict_recv() uses rcu_read_lock() protection. We need the callers to pass a gfp_t argument to avoid issues. syzbot report was: BUG: sleeping function called from invalid context at include/linux/sched/mm.h:274 in_atomic(): 0, irqs_disabled(): 0, non_block: 0, pid: 3613, name: syz-executor414 preempt_count: 0, expected: 0 RCU nest depth: 1, expected: 0 INFO: lockdep is turned off. CPU: 0 PID: 3613 Comm: syz-executor414 Not tainted 6.0.0-syzkaller-09589-g55be6084c8e0 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/22/2022 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x1e3/0x2cb lib/dump_stack.c:106 __might_resched+0x538/0x6a0 kernel/sched/core.c:9877 might_alloc include/linux/sched/mm.h:274 [inline] slab_pre_alloc_hook mm/slab.h:700 [inline] slab_alloc_node mm/slub.c:3162 [inline] slab_alloc mm/slub.c:3256 [inline] kmem_cache_alloc_trace+0x59/0x310 mm/slub.c:3287 kmalloc include/linux/slab.h:600 [inline] kzalloc include/linux/slab.h:733 [inline] alloc_sk_msg net/core/skmsg.c:507 [inline] sk_psock_skb_ingress_self+0x5c/0x330 net/core/skmsg.c:600 sk_psock_verdict_apply+0x395/0x440 net/core/skmsg.c:1014 sk_psock_verdict_recv+0x34d/0x560 net/core/skmsg.c:1201 tcp_read_skb+0x4a1/0x790 net/ipv4/tcp.c:1770 tcp_rcv_established+0x129d/0x1a10 net/ipv4/tcp_input.c:5971 tcp_v4_do_rcv+0x479/0xac0 net/ipv4/tcp_ipv4.c:1681 sk_backlog_rcv include/net/sock.h:1109 [inline] __release_sock+0x1d8/0x4c0 net/core/sock.c:2906 release_sock+0x5d/0x1c0 net/core/sock.c:3462 tcp_sendmsg+0x36/0x40 net/ipv4/tcp.c:1483 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg net/socket.c:734 [inline] __sys_sendto+0x46d/0x5f0 net/socket.c:2117 __do_sys_sendto net/socket.c:2129 [inline] __se_sys_sendto net/socket.c:2125 [inline] __x64_sys_sendto+0xda/0xf0 net/socket.c:2125 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x2b/0x70 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Fixes: 43312915b5ba ("skmsg: Get rid of unncessary memset()") Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Cong Wang <cong.wang@bytedance.com> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2022-10-15 21:24:41 +00:00
struct sk_msg *msg = alloc_sk_msg(GFP_ATOMIC);
bpf, sockmap: Avoid returning unneeded EAGAIN when redirecting to self If a socket redirects to itself and it is under memory pressure it is possible to get a socket stuck so that recv() returns EAGAIN and the socket can not advance for some time. This happens because when redirecting a skb to the same socket we received the skb on we first check if it is OK to enqueue the skb on the receiving socket by checking memory limits. But, if the skb is itself the object holding the memory needed to enqueue the skb we will keep retrying from kernel side and always fail with EAGAIN. Then userspace will get a recv() EAGAIN error if there are no skbs in the psock ingress queue. This will continue until either some skbs get kfree'd causing the memory pressure to reduce far enough that we can enqueue the pending packet or the socket is destroyed. In some cases its possible to get a socket stuck for a noticeable amount of time if the socket is only receiving skbs from sk_skb verdict programs. To reproduce I make the socket memory limits ridiculously low so sockets are always under memory pressure. More often though if under memory pressure it looks like a spurious EAGAIN error on user space side causing userspace to retry and typically enough has moved on the memory side that it works. To fix skip memory checks and skb_orphan if receiving on the same sock as already assigned. For SK_PASS cases this is easy, its always the same socket so we can just omit the orphan/set_owner pair. For backlog cases we need to check skb->sk and decide if the orphan and set_owner pair are needed. Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/160556572660.73229.12566203819812939627.stgit@john-XPS-13-9370
2020-11-16 22:28:46 +00:00
struct sock *sk = psock->sk;
bpf, sockmap: Fix potential memory leak on unlikely error case If skb_linearize is needed and fails we could leak a msg on the error handling. To fix ensure we kfree the msg block before returning error. Found during code review. Fixes: 4363023d2668e ("bpf, sockmap: Avoid failures from skb_to_sgvec when skb has frag_list") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Cong Wang <cong.wang@bytedance.com> Link: https://lore.kernel.org/bpf/20210712195546.423990-2-john.fastabend@gmail.com
2021-07-12 19:55:45 +00:00
int err;
bpf, sockmap: Avoid returning unneeded EAGAIN when redirecting to self If a socket redirects to itself and it is under memory pressure it is possible to get a socket stuck so that recv() returns EAGAIN and the socket can not advance for some time. This happens because when redirecting a skb to the same socket we received the skb on we first check if it is OK to enqueue the skb on the receiving socket by checking memory limits. But, if the skb is itself the object holding the memory needed to enqueue the skb we will keep retrying from kernel side and always fail with EAGAIN. Then userspace will get a recv() EAGAIN error if there are no skbs in the psock ingress queue. This will continue until either some skbs get kfree'd causing the memory pressure to reduce far enough that we can enqueue the pending packet or the socket is destroyed. In some cases its possible to get a socket stuck for a noticeable amount of time if the socket is only receiving skbs from sk_skb verdict programs. To reproduce I make the socket memory limits ridiculously low so sockets are always under memory pressure. More often though if under memory pressure it looks like a spurious EAGAIN error on user space side causing userspace to retry and typically enough has moved on the memory side that it works. To fix skip memory checks and skb_orphan if receiving on the same sock as already assigned. For SK_PASS cases this is easy, its always the same socket so we can just omit the orphan/set_owner pair. For backlog cases we need to check skb->sk and decide if the orphan and set_owner pair are needed. Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/160556572660.73229.12566203819812939627.stgit@john-XPS-13-9370
2020-11-16 22:28:46 +00:00
if (unlikely(!msg))
return -EAGAIN;
bpf, sockmap: Fix incorrect fwd_alloc accounting Incorrect accounting fwd_alloc can result in a warning when the socket is torn down, [18455.319240] WARNING: CPU: 0 PID: 24075 at net/core/stream.c:208 sk_stream_kill_queues+0x21f/0x230 [...] [18455.319543] Call Trace: [18455.319556] inet_csk_destroy_sock+0xba/0x1f0 [18455.319577] tcp_rcv_state_process+0x1b4e/0x2380 [18455.319593] ? lock_downgrade+0x3a0/0x3a0 [18455.319617] ? tcp_finish_connect+0x1e0/0x1e0 [18455.319631] ? sk_reset_timer+0x15/0x70 [18455.319646] ? tcp_schedule_loss_probe+0x1b2/0x240 [18455.319663] ? lock_release+0xb2/0x3f0 [18455.319676] ? __release_sock+0x8a/0x1b0 [18455.319690] ? lock_downgrade+0x3a0/0x3a0 [18455.319704] ? lock_release+0x3f0/0x3f0 [18455.319717] ? __tcp_close+0x2c6/0x790 [18455.319736] ? tcp_v4_do_rcv+0x168/0x370 [18455.319750] tcp_v4_do_rcv+0x168/0x370 [18455.319767] __release_sock+0xbc/0x1b0 [18455.319785] __tcp_close+0x2ee/0x790 [18455.319805] tcp_close+0x20/0x80 This currently happens because on redirect case we do skb_set_owner_r() with the original sock. This increments the fwd_alloc memory accounting on the original sock. Then on redirect we may push this into the queue of the psock we are redirecting to. When the skb is flushed from the queue we give the memory back to the original sock. The problem is if the original sock is destroyed/closed with skbs on another psocks queue then the original sock will not have a way to reclaim the memory before being destroyed. Then above warning will be thrown sockA sockB sk_psock_strp_read() sk_psock_verdict_apply() -- SK_REDIRECT -- sk_psock_skb_redirect() skb_queue_tail(psock_other->ingress_skb..) sk_close() sock_map_unref() sk_psock_put() sk_psock_drop() sk_psock_zap_ingress() At this point we have torn down our own psock, but have the outstanding skb in psock_other. Note that SK_PASS doesn't have this problem because the sk_psock_drop() logic releases the skb, its still associated with our psock. To resolve lets only account for sockets on the ingress queue that are still associated with the current socket. On the redirect case we will check memory limits per 6fa9201a89898, but will omit fwd_alloc accounting until skb is actually enqueued. When the skb is sent via skb_send_sock_locked or received with sk_psock_skb_ingress memory will be claimed on psock_other. Fixes: 6fa9201a89898 ("bpf, sockmap: Avoid returning unneeded EAGAIN when redirecting to self") Reported-by: Andrii Nakryiko <andrii@kernel.org> Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/161731444013.68884.4021114312848535993.stgit@john-XPS-13-9370
2021-04-01 22:00:40 +00:00
skb_set_owner_r(skb, sk);
skmsg: Lose offset info in sk_psock_skb_ingress If sockmap enable strparser, there are lose offset info in sk_psock_skb_ingress(). If the length determined by parse_msg function is not skb->len, the skb will be converted to sk_msg multiple times, and userspace app will get the data multiple times. Fix this by get the offset and length from strp_msg. And as Cong suggested, add one bit in skb->_sk_redir to distinguish enable or disable strparser. Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Liu Jian <liujian56@huawei.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Cong Wang <cong.wang@bytedance.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20211029141216.211899-1-liujian56@huawei.com
2021-10-29 14:12:14 +00:00
err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg);
bpf, sockmap: Fix potential memory leak on unlikely error case If skb_linearize is needed and fails we could leak a msg on the error handling. To fix ensure we kfree the msg block before returning error. Found during code review. Fixes: 4363023d2668e ("bpf, sockmap: Avoid failures from skb_to_sgvec when skb has frag_list") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Cong Wang <cong.wang@bytedance.com> Link: https://lore.kernel.org/bpf/20210712195546.423990-2-john.fastabend@gmail.com
2021-07-12 19:55:45 +00:00
if (err < 0)
kfree(msg);
return err;
bpf, sockmap: Avoid returning unneeded EAGAIN when redirecting to self If a socket redirects to itself and it is under memory pressure it is possible to get a socket stuck so that recv() returns EAGAIN and the socket can not advance for some time. This happens because when redirecting a skb to the same socket we received the skb on we first check if it is OK to enqueue the skb on the receiving socket by checking memory limits. But, if the skb is itself the object holding the memory needed to enqueue the skb we will keep retrying from kernel side and always fail with EAGAIN. Then userspace will get a recv() EAGAIN error if there are no skbs in the psock ingress queue. This will continue until either some skbs get kfree'd causing the memory pressure to reduce far enough that we can enqueue the pending packet or the socket is destroyed. In some cases its possible to get a socket stuck for a noticeable amount of time if the socket is only receiving skbs from sk_skb verdict programs. To reproduce I make the socket memory limits ridiculously low so sockets are always under memory pressure. More often though if under memory pressure it looks like a spurious EAGAIN error on user space side causing userspace to retry and typically enough has moved on the memory side that it works. To fix skip memory checks and skb_orphan if receiving on the same sock as already assigned. For SK_PASS cases this is easy, its always the same socket so we can just omit the orphan/set_owner pair. For backlog cases we need to check skb->sk and decide if the orphan and set_owner pair are needed. Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/160556572660.73229.12566203819812939627.stgit@john-XPS-13-9370
2020-11-16 22:28:46 +00:00
}
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 00:45:58 +00:00
static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb,
u32 off, u32 len, bool ingress)
{
bpf, sockmap: Fix skb refcnt race after locking changes There is a race where skb's from the sk_psock_backlog can be referenced after userspace side has already skb_consumed() the sk_buff and its refcnt dropped to zer0 causing use after free. The flow is the following: while ((skb = skb_peek(&psock->ingress_skb)) sk_psock_handle_Skb(psock, skb, ..., ingress) if (!ingress) ... sk_psock_skb_ingress sk_psock_skb_ingress_enqueue(skb) msg->skb = skb sk_psock_queue_msg(psock, msg) skb_dequeue(&psock->ingress_skb) The sk_psock_queue_msg() puts the msg on the ingress_msg queue. This is what the application reads when recvmsg() is called. An application can read this anytime after the msg is placed on the queue. The recvmsg hook will also read msg->skb and then after user space reads the msg will call consume_skb(skb) on it effectively free'ing it. But, the race is in above where backlog queue still has a reference to the skb and calls skb_dequeue(). If the skb_dequeue happens after the user reads and free's the skb we have a use after free. The !ingress case does not suffer from this problem because it uses sendmsg_*(sk, msg) which does not pass the sk_buff further down the stack. The following splat was observed with 'test_progs -t sockmap_listen': [ 1022.710250][ T2556] general protection fault, ... [...] [ 1022.712830][ T2556] Workqueue: events sk_psock_backlog [ 1022.713262][ T2556] RIP: 0010:skb_dequeue+0x4c/0x80 [ 1022.713653][ T2556] Code: ... [...] [ 1022.720699][ T2556] Call Trace: [ 1022.720984][ T2556] <TASK> [ 1022.721254][ T2556] ? die_addr+0x32/0x80^M [ 1022.721589][ T2556] ? exc_general_protection+0x25a/0x4b0 [ 1022.722026][ T2556] ? asm_exc_general_protection+0x22/0x30 [ 1022.722489][ T2556] ? skb_dequeue+0x4c/0x80 [ 1022.722854][ T2556] sk_psock_backlog+0x27a/0x300 [ 1022.723243][ T2556] process_one_work+0x2a7/0x5b0 [ 1022.723633][ T2556] worker_thread+0x4f/0x3a0 [ 1022.723998][ T2556] ? __pfx_worker_thread+0x10/0x10 [ 1022.724386][ T2556] kthread+0xfd/0x130 [ 1022.724709][ T2556] ? __pfx_kthread+0x10/0x10 [ 1022.725066][ T2556] ret_from_fork+0x2d/0x50 [ 1022.725409][ T2556] ? __pfx_kthread+0x10/0x10 [ 1022.725799][ T2556] ret_from_fork_asm+0x1b/0x30 [ 1022.726201][ T2556] </TASK> To fix we add an skb_get() before passing the skb to be enqueued in the engress queue. This bumps the skb->users refcnt so that consume_skb() and kfree_skb will not immediately free the sk_buff. With this we can be sure the skb is still around when we do the dequeue. Then we just need to decrement the refcnt or free the skb in the backlog case which we do by calling kfree_skb() on the ingress case as well as the sendmsg case. Before locking change from fixes tag we had the sock locked so we couldn't race with user and there was no issue here. Fixes: 799aa7f98d53e ("skmsg: Avoid lock_sock() in sk_psock_backlog()") Reported-by: Jiri Olsa <jolsa@kernel.org> Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Tested-by: Xu Kuohai <xukuohai@huawei.com> Tested-by: Jiri Olsa <jolsa@kernel.org> Link: https://lore.kernel.org/bpf/20230901202137.214666-1-john.fastabend@gmail.com
2023-09-01 20:21:37 +00:00
int err = 0;
bpf, sockmap: Remove dropped data on errors in redirect case In the sk_skb redirect case we didn't handle the case where we overrun the sk_rmem_alloc entry on ingress redirect or sk_wmem_alloc on egress. Because we didn't have anything implemented we simply dropped the skb. This meant data could be dropped if socket memory accounting was in place. This fixes the above dropped data case by moving the memory checks later in the code where we actually do the send or recv. This pushes those checks into the workqueue and allows us to return an EAGAIN error which in turn allows us to try again later from the workqueue. Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/160226863689.5692.13861422742592309285.stgit@john-Precision-5820-Tower
2020-10-09 18:37:17 +00:00
if (!ingress) {
if (!sock_writeable(psock->sk))
return -EAGAIN;
skmsg: Avoid lock_sock() in sk_psock_backlog() We do not have to lock the sock to avoid losing sk_socket, instead we can purge all the ingress queues when we close the socket. Sending or receiving packets after orphaning socket makes no sense. We do purge these queues when psock refcnt reaches zero but here we want to purge them explicitly in sock_map_close(). There are also some nasty race conditions on testing bit SK_PSOCK_TX_ENABLED and queuing/canceling the psock work, we can expand psock->ingress_lock a bit to protect them too. As noticed by John, we still have to lock the psock->work, because the same work item could be running concurrently on different CPU's. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210331023237.41094-5-xiyou.wangcong@gmail.com
2021-03-31 02:32:25 +00:00
return skb_send_sock(psock->sk, skb, off, len);
bpf, sockmap: Remove dropped data on errors in redirect case In the sk_skb redirect case we didn't handle the case where we overrun the sk_rmem_alloc entry on ingress redirect or sk_wmem_alloc on egress. Because we didn't have anything implemented we simply dropped the skb. This meant data could be dropped if socket memory accounting was in place. This fixes the above dropped data case by moving the memory checks later in the code where we actually do the send or recv. This pushes those checks into the workqueue and allows us to return an EAGAIN error which in turn allows us to try again later from the workqueue. Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/160226863689.5692.13861422742592309285.stgit@john-Precision-5820-Tower
2020-10-09 18:37:17 +00:00
}
bpf, sockmap: Fix skb refcnt race after locking changes There is a race where skb's from the sk_psock_backlog can be referenced after userspace side has already skb_consumed() the sk_buff and its refcnt dropped to zer0 causing use after free. The flow is the following: while ((skb = skb_peek(&psock->ingress_skb)) sk_psock_handle_Skb(psock, skb, ..., ingress) if (!ingress) ... sk_psock_skb_ingress sk_psock_skb_ingress_enqueue(skb) msg->skb = skb sk_psock_queue_msg(psock, msg) skb_dequeue(&psock->ingress_skb) The sk_psock_queue_msg() puts the msg on the ingress_msg queue. This is what the application reads when recvmsg() is called. An application can read this anytime after the msg is placed on the queue. The recvmsg hook will also read msg->skb and then after user space reads the msg will call consume_skb(skb) on it effectively free'ing it. But, the race is in above where backlog queue still has a reference to the skb and calls skb_dequeue(). If the skb_dequeue happens after the user reads and free's the skb we have a use after free. The !ingress case does not suffer from this problem because it uses sendmsg_*(sk, msg) which does not pass the sk_buff further down the stack. The following splat was observed with 'test_progs -t sockmap_listen': [ 1022.710250][ T2556] general protection fault, ... [...] [ 1022.712830][ T2556] Workqueue: events sk_psock_backlog [ 1022.713262][ T2556] RIP: 0010:skb_dequeue+0x4c/0x80 [ 1022.713653][ T2556] Code: ... [...] [ 1022.720699][ T2556] Call Trace: [ 1022.720984][ T2556] <TASK> [ 1022.721254][ T2556] ? die_addr+0x32/0x80^M [ 1022.721589][ T2556] ? exc_general_protection+0x25a/0x4b0 [ 1022.722026][ T2556] ? asm_exc_general_protection+0x22/0x30 [ 1022.722489][ T2556] ? skb_dequeue+0x4c/0x80 [ 1022.722854][ T2556] sk_psock_backlog+0x27a/0x300 [ 1022.723243][ T2556] process_one_work+0x2a7/0x5b0 [ 1022.723633][ T2556] worker_thread+0x4f/0x3a0 [ 1022.723998][ T2556] ? __pfx_worker_thread+0x10/0x10 [ 1022.724386][ T2556] kthread+0xfd/0x130 [ 1022.724709][ T2556] ? __pfx_kthread+0x10/0x10 [ 1022.725066][ T2556] ret_from_fork+0x2d/0x50 [ 1022.725409][ T2556] ? __pfx_kthread+0x10/0x10 [ 1022.725799][ T2556] ret_from_fork_asm+0x1b/0x30 [ 1022.726201][ T2556] </TASK> To fix we add an skb_get() before passing the skb to be enqueued in the engress queue. This bumps the skb->users refcnt so that consume_skb() and kfree_skb will not immediately free the sk_buff. With this we can be sure the skb is still around when we do the dequeue. Then we just need to decrement the refcnt or free the skb in the backlog case which we do by calling kfree_skb() on the ingress case as well as the sendmsg case. Before locking change from fixes tag we had the sock locked so we couldn't race with user and there was no issue here. Fixes: 799aa7f98d53e ("skmsg: Avoid lock_sock() in sk_psock_backlog()") Reported-by: Jiri Olsa <jolsa@kernel.org> Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Tested-by: Xu Kuohai <xukuohai@huawei.com> Tested-by: Jiri Olsa <jolsa@kernel.org> Link: https://lore.kernel.org/bpf/20230901202137.214666-1-john.fastabend@gmail.com
2023-09-01 20:21:37 +00:00
skb_get(skb);
err = sk_psock_skb_ingress(psock, skb, off, len);
if (err < 0)
kfree_skb(skb);
return err;
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 00:45:58 +00:00
}
bpf, sockmap: On cleanup we additionally need to remove cached skb Its possible if a socket is closed and the receive thread is under memory pressure it may have cached a skb. We need to ensure these skbs are free'd along with the normal ingress_skb queue. Before 799aa7f98d53 ("skmsg: Avoid lock_sock() in sk_psock_backlog()") tear down and backlog processing both had sock_lock for the common case of socket close or unhash. So it was not possible to have both running in parrallel so all we would need is the kfree in those kernels. But, latest kernels include the commit 799aa7f98d5e and this requires a bit more work. Without the ingress_lock guarding reading/writing the state->skb case its possible the tear down could run before the state update causing it to leak memory or worse when the backlog reads the state it could potentially run interleaved with the tear down and we might end up free'ing the state->skb from tear down side but already have the reference from backlog side. To resolve such races we wrap accesses in ingress_lock on both sides serializing tear down and backlog case. In both cases this only happens after an EAGAIN error case so having an extra lock in place is likely fine. The normal path will skip the locks. Note, we check state->skb before grabbing lock. This works because we can only enqueue with the mutex we hold already. Avoiding a race on adding state->skb after the check. And if tear down path is running that is also fine if the tear down path then removes state->skb we will simply set skb=NULL and the subsequent goto is skipped. This slight complication avoids locking in normal case. With this fix we no longer see this warning splat from tcp side on socket close when we hit the above case with redirect to ingress self. [224913.935822] WARNING: CPU: 3 PID: 32100 at net/core/stream.c:208 sk_stream_kill_queues+0x212/0x220 [224913.935841] Modules linked in: fuse overlay bpf_preload x86_pkg_temp_thermal intel_uncore wmi_bmof squashfs sch_fq_codel efivarfs ip_tables x_tables uas xhci_pci ixgbe mdio xfrm_algo xhci_hcd wmi [224913.935897] CPU: 3 PID: 32100 Comm: fgs-bench Tainted: G I 5.14.0-rc1alu+ #181 [224913.935908] Hardware name: Dell Inc. Precision 5820 Tower/002KVM, BIOS 1.9.2 01/24/2019 [224913.935914] RIP: 0010:sk_stream_kill_queues+0x212/0x220 [224913.935923] Code: 8b 83 20 02 00 00 85 c0 75 20 5b 5d 41 5c 41 5d 41 5e 41 5f c3 48 89 df e8 2b 11 fe ff eb c3 0f 0b e9 7c ff ff ff 0f 0b eb ce <0f> 0b 5b 5d 41 5c 41 5d 41 5e 41 5f c3 90 0f 1f 44 00 00 41 57 41 [224913.935932] RSP: 0018:ffff88816271fd38 EFLAGS: 00010206 [224913.935941] RAX: 0000000000000ae8 RBX: ffff88815acd5240 RCX: dffffc0000000000 [224913.935948] RDX: 0000000000000003 RSI: 0000000000000ae8 RDI: ffff88815acd5460 [224913.935954] RBP: ffff88815acd5460 R08: ffffffff955c0ae8 R09: fffffbfff2e6f543 [224913.935961] R10: ffffffff9737aa17 R11: fffffbfff2e6f542 R12: ffff88815acd5390 [224913.935967] R13: ffff88815acd5480 R14: ffffffff98d0c080 R15: ffffffff96267500 [224913.935974] FS: 00007f86e6bd1700(0000) GS:ffff888451cc0000(0000) knlGS:0000000000000000 [224913.935981] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [224913.935988] CR2: 000000c0008eb000 CR3: 00000001020e0005 CR4: 00000000003706e0 [224913.935994] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [224913.936000] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [224913.936007] Call Trace: [224913.936016] inet_csk_destroy_sock+0xba/0x1f0 [224913.936033] __tcp_close+0x620/0x790 [224913.936047] tcp_close+0x20/0x80 [224913.936056] inet_release+0x8f/0xf0 [224913.936070] __sock_release+0x72/0x120 [224913.936083] sock_close+0x14/0x20 Fixes: a136678c0bdbb ("bpf: sk_msg, zap ingress queue on psock down") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Link: https://lore.kernel.org/bpf/20210727160500.1713554-3-john.fastabend@gmail.com
2021-07-27 16:04:59 +00:00
static void sk_psock_skb_state(struct sk_psock *psock,
struct sk_psock_work_state *state,
int len, int off)
{
spin_lock_bh(&psock->ingress_lock);
if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) {
state->len = len;
state->off = off;
}
spin_unlock_bh(&psock->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 00:45:58 +00:00
static void sk_psock_backlog(struct work_struct *work)
{
bpf, sockmap: Convert schedule_work into delayed_work 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
2023-05-23 02:56:06 +00:00
struct delayed_work *dwork = to_delayed_work(work);
struct sk_psock *psock = container_of(dwork, struct sk_psock, work);
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 00:45:58 +00:00
struct sk_psock_work_state *state = &psock->work_state;
bpf, sockmap: On cleanup we additionally need to remove cached skb Its possible if a socket is closed and the receive thread is under memory pressure it may have cached a skb. We need to ensure these skbs are free'd along with the normal ingress_skb queue. Before 799aa7f98d53 ("skmsg: Avoid lock_sock() in sk_psock_backlog()") tear down and backlog processing both had sock_lock for the common case of socket close or unhash. So it was not possible to have both running in parrallel so all we would need is the kfree in those kernels. But, latest kernels include the commit 799aa7f98d5e and this requires a bit more work. Without the ingress_lock guarding reading/writing the state->skb case its possible the tear down could run before the state update causing it to leak memory or worse when the backlog reads the state it could potentially run interleaved with the tear down and we might end up free'ing the state->skb from tear down side but already have the reference from backlog side. To resolve such races we wrap accesses in ingress_lock on both sides serializing tear down and backlog case. In both cases this only happens after an EAGAIN error case so having an extra lock in place is likely fine. The normal path will skip the locks. Note, we check state->skb before grabbing lock. This works because we can only enqueue with the mutex we hold already. Avoiding a race on adding state->skb after the check. And if tear down path is running that is also fine if the tear down path then removes state->skb we will simply set skb=NULL and the subsequent goto is skipped. This slight complication avoids locking in normal case. With this fix we no longer see this warning splat from tcp side on socket close when we hit the above case with redirect to ingress self. [224913.935822] WARNING: CPU: 3 PID: 32100 at net/core/stream.c:208 sk_stream_kill_queues+0x212/0x220 [224913.935841] Modules linked in: fuse overlay bpf_preload x86_pkg_temp_thermal intel_uncore wmi_bmof squashfs sch_fq_codel efivarfs ip_tables x_tables uas xhci_pci ixgbe mdio xfrm_algo xhci_hcd wmi [224913.935897] CPU: 3 PID: 32100 Comm: fgs-bench Tainted: G I 5.14.0-rc1alu+ #181 [224913.935908] Hardware name: Dell Inc. Precision 5820 Tower/002KVM, BIOS 1.9.2 01/24/2019 [224913.935914] RIP: 0010:sk_stream_kill_queues+0x212/0x220 [224913.935923] Code: 8b 83 20 02 00 00 85 c0 75 20 5b 5d 41 5c 41 5d 41 5e 41 5f c3 48 89 df e8 2b 11 fe ff eb c3 0f 0b e9 7c ff ff ff 0f 0b eb ce <0f> 0b 5b 5d 41 5c 41 5d 41 5e 41 5f c3 90 0f 1f 44 00 00 41 57 41 [224913.935932] RSP: 0018:ffff88816271fd38 EFLAGS: 00010206 [224913.935941] RAX: 0000000000000ae8 RBX: ffff88815acd5240 RCX: dffffc0000000000 [224913.935948] RDX: 0000000000000003 RSI: 0000000000000ae8 RDI: ffff88815acd5460 [224913.935954] RBP: ffff88815acd5460 R08: ffffffff955c0ae8 R09: fffffbfff2e6f543 [224913.935961] R10: ffffffff9737aa17 R11: fffffbfff2e6f542 R12: ffff88815acd5390 [224913.935967] R13: ffff88815acd5480 R14: ffffffff98d0c080 R15: ffffffff96267500 [224913.935974] FS: 00007f86e6bd1700(0000) GS:ffff888451cc0000(0000) knlGS:0000000000000000 [224913.935981] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [224913.935988] CR2: 000000c0008eb000 CR3: 00000001020e0005 CR4: 00000000003706e0 [224913.935994] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [224913.936000] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [224913.936007] Call Trace: [224913.936016] inet_csk_destroy_sock+0xba/0x1f0 [224913.936033] __tcp_close+0x620/0x790 [224913.936047] tcp_close+0x20/0x80 [224913.936056] inet_release+0x8f/0xf0 [224913.936070] __sock_release+0x72/0x120 [224913.936083] sock_close+0x14/0x20 Fixes: a136678c0bdbb ("bpf: sk_msg, zap ingress queue on psock down") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Link: https://lore.kernel.org/bpf/20210727160500.1713554-3-john.fastabend@gmail.com
2021-07-27 16:04:59 +00:00
struct sk_buff *skb = NULL;
bpf, sockmap: Improved check for empty queue We noticed some rare sk_buffs were stepping past the queue when system was under memory pressure. The general theory is to skip enqueueing sk_buffs when its not necessary which is the normal case with a system that is properly provisioned for the task, no memory pressure and enough cpu assigned. But, if we can't allocate memory due to an ENOMEM error when enqueueing the sk_buff into the sockmap receive queue we push it onto a delayed workqueue to retry later. When a new sk_buff is received we then check if that queue is empty. However, there is a problem with simply checking the queue length. When a sk_buff is being processed from the ingress queue but not yet on the sockmap msg receive queue its possible to also recv a sk_buff through normal path. It will check the ingress queue which is zero and then skip ahead of the pkt being processed. Previously we used sock lock from both contexts which made the problem harder to hit, but not impossible. To fix instead of popping the skb from the queue entirely we peek the skb from the queue and do the copy there. This ensures checks to the queue length are non-zero while skb is being processed. Then finally when the entire skb has been copied to user space queue or another socket we pop it off the queue. This way the queue length check allows bypassing the queue only after the list has been completely processed. To reproduce issue we run NGINX compliance test with sockmap running and observe some flakes in our testing that we attributed to this issue. Fixes: 04919bed948dc ("tcp: Introduce tcp_read_skb()") Suggested-by: Jakub Sitnicki <jakub@cloudflare.com> 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/20230523025618.113937-5-john.fastabend@gmail.com
2023-05-23 02:56:08 +00:00
u32 len = 0, off = 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 00:45:58 +00:00
bool ingress;
int ret;
skmsg: Avoid lock_sock() in sk_psock_backlog() We do not have to lock the sock to avoid losing sk_socket, instead we can purge all the ingress queues when we close the socket. Sending or receiving packets after orphaning socket makes no sense. We do purge these queues when psock refcnt reaches zero but here we want to purge them explicitly in sock_map_close(). There are also some nasty race conditions on testing bit SK_PSOCK_TX_ENABLED and queuing/canceling the psock work, we can expand psock->ingress_lock a bit to protect them too. As noticed by John, we still have to lock the psock->work, because the same work item could be running concurrently on different CPU's. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210331023237.41094-5-xiyou.wangcong@gmail.com
2021-03-31 02:32:25 +00:00
mutex_lock(&psock->work_mutex);
bpf, sockmap: Improved check for empty queue We noticed some rare sk_buffs were stepping past the queue when system was under memory pressure. The general theory is to skip enqueueing sk_buffs when its not necessary which is the normal case with a system that is properly provisioned for the task, no memory pressure and enough cpu assigned. But, if we can't allocate memory due to an ENOMEM error when enqueueing the sk_buff into the sockmap receive queue we push it onto a delayed workqueue to retry later. When a new sk_buff is received we then check if that queue is empty. However, there is a problem with simply checking the queue length. When a sk_buff is being processed from the ingress queue but not yet on the sockmap msg receive queue its possible to also recv a sk_buff through normal path. It will check the ingress queue which is zero and then skip ahead of the pkt being processed. Previously we used sock lock from both contexts which made the problem harder to hit, but not impossible. To fix instead of popping the skb from the queue entirely we peek the skb from the queue and do the copy there. This ensures checks to the queue length are non-zero while skb is being processed. Then finally when the entire skb has been copied to user space queue or another socket we pop it off the queue. This way the queue length check allows bypassing the queue only after the list has been completely processed. To reproduce issue we run NGINX compliance test with sockmap running and observe some flakes in our testing that we attributed to this issue. Fixes: 04919bed948dc ("tcp: Introduce tcp_read_skb()") Suggested-by: Jakub Sitnicki <jakub@cloudflare.com> 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/20230523025618.113937-5-john.fastabend@gmail.com
2023-05-23 02:56:08 +00:00
if (unlikely(state->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 00:45:58 +00:00
len = state->len;
off = state->off;
}
bpf, sockmap: Improved check for empty queue We noticed some rare sk_buffs were stepping past the queue when system was under memory pressure. The general theory is to skip enqueueing sk_buffs when its not necessary which is the normal case with a system that is properly provisioned for the task, no memory pressure and enough cpu assigned. But, if we can't allocate memory due to an ENOMEM error when enqueueing the sk_buff into the sockmap receive queue we push it onto a delayed workqueue to retry later. When a new sk_buff is received we then check if that queue is empty. However, there is a problem with simply checking the queue length. When a sk_buff is being processed from the ingress queue but not yet on the sockmap msg receive queue its possible to also recv a sk_buff through normal path. It will check the ingress queue which is zero and then skip ahead of the pkt being processed. Previously we used sock lock from both contexts which made the problem harder to hit, but not impossible. To fix instead of popping the skb from the queue entirely we peek the skb from the queue and do the copy there. This ensures checks to the queue length are non-zero while skb is being processed. Then finally when the entire skb has been copied to user space queue or another socket we pop it off the queue. This way the queue length check allows bypassing the queue only after the list has been completely processed. To reproduce issue we run NGINX compliance test with sockmap running and observe some flakes in our testing that we attributed to this issue. Fixes: 04919bed948dc ("tcp: Introduce tcp_read_skb()") Suggested-by: Jakub Sitnicki <jakub@cloudflare.com> 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/20230523025618.113937-5-john.fastabend@gmail.com
2023-05-23 02:56:08 +00:00
while ((skb = skb_peek(&psock->ingress_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 00:45:58 +00:00
len = skb->len;
off = 0;
skmsg: Lose offset info in sk_psock_skb_ingress If sockmap enable strparser, there are lose offset info in sk_psock_skb_ingress(). If the length determined by parse_msg function is not skb->len, the skb will be converted to sk_msg multiple times, and userspace app will get the data multiple times. Fix this by get the offset and length from strp_msg. And as Cong suggested, add one bit in skb->_sk_redir to distinguish enable or disable strparser. Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Liu Jian <liujian56@huawei.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Cong Wang <cong.wang@bytedance.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20211029141216.211899-1-liujian56@huawei.com
2021-10-29 14:12:14 +00:00
if (skb_bpf_strparser(skb)) {
struct strp_msg *stm = strp_msg(skb);
off = stm->offset;
len = stm->full_len;
}
skmsg: Move sk_redir from TCP_SKB_CB to skb Currently TCP_SKB_CB() is hard-coded in skmsg code, it certainly does not work for any other non-TCP protocols. We can move them to skb ext, but it introduces a memory allocation on fast path. Fortunately, we only need to a word-size to store all the information, because the flags actually only contains 1 bit so can be just packed into the lowest bit of the "pointer", which is stored as unsigned long. Inside struct sk_buff, '_skb_refdst' can be reused because skb dst is no longer needed after ->sk_data_ready() so we can just drop it. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-5-xiyou.wangcong@gmail.com
2021-02-23 18:49:29 +00:00
ingress = skb_bpf_ingress(skb);
skb_bpf_redirect_clear(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 00:45:58 +00:00
do {
ret = -EIO;
skmsg: Avoid lock_sock() in sk_psock_backlog() We do not have to lock the sock to avoid losing sk_socket, instead we can purge all the ingress queues when we close the socket. Sending or receiving packets after orphaning socket makes no sense. We do purge these queues when psock refcnt reaches zero but here we want to purge them explicitly in sock_map_close(). There are also some nasty race conditions on testing bit SK_PSOCK_TX_ENABLED and queuing/canceling the psock work, we can expand psock->ingress_lock a bit to protect them too. As noticed by John, we still have to lock the psock->work, because the same work item could be running concurrently on different CPU's. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210331023237.41094-5-xiyou.wangcong@gmail.com
2021-03-31 02:32:25 +00:00
if (!sock_flag(psock->sk, SOCK_DEAD))
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 00:45:58 +00:00
ret = sk_psock_handle_skb(psock, skb, off,
len, ingress);
if (ret <= 0) {
if (ret == -EAGAIN) {
bpf, sockmap: Improved check for empty queue We noticed some rare sk_buffs were stepping past the queue when system was under memory pressure. The general theory is to skip enqueueing sk_buffs when its not necessary which is the normal case with a system that is properly provisioned for the task, no memory pressure and enough cpu assigned. But, if we can't allocate memory due to an ENOMEM error when enqueueing the sk_buff into the sockmap receive queue we push it onto a delayed workqueue to retry later. When a new sk_buff is received we then check if that queue is empty. However, there is a problem with simply checking the queue length. When a sk_buff is being processed from the ingress queue but not yet on the sockmap msg receive queue its possible to also recv a sk_buff through normal path. It will check the ingress queue which is zero and then skip ahead of the pkt being processed. Previously we used sock lock from both contexts which made the problem harder to hit, but not impossible. To fix instead of popping the skb from the queue entirely we peek the skb from the queue and do the copy there. This ensures checks to the queue length are non-zero while skb is being processed. Then finally when the entire skb has been copied to user space queue or another socket we pop it off the queue. This way the queue length check allows bypassing the queue only after the list has been completely processed. To reproduce issue we run NGINX compliance test with sockmap running and observe some flakes in our testing that we attributed to this issue. Fixes: 04919bed948dc ("tcp: Introduce tcp_read_skb()") Suggested-by: Jakub Sitnicki <jakub@cloudflare.com> 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/20230523025618.113937-5-john.fastabend@gmail.com
2023-05-23 02:56:08 +00:00
sk_psock_skb_state(psock, state, len, off);
bpf, sockmap: Convert schedule_work into delayed_work 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
2023-05-23 02:56:06 +00:00
/* Delay slightly to prioritize any
* other work that might be here.
*/
if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED))
schedule_delayed_work(&psock->work, 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 00:45:58 +00:00
goto end;
}
/* Hard errors break pipe and stop xmit. */
sk_psock_report_error(psock, ret ? -ret : EPIPE);
sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED);
goto end;
}
off += ret;
len -= ret;
} while (len);
bpf, sockmap: Improved check for empty queue We noticed some rare sk_buffs were stepping past the queue when system was under memory pressure. The general theory is to skip enqueueing sk_buffs when its not necessary which is the normal case with a system that is properly provisioned for the task, no memory pressure and enough cpu assigned. But, if we can't allocate memory due to an ENOMEM error when enqueueing the sk_buff into the sockmap receive queue we push it onto a delayed workqueue to retry later. When a new sk_buff is received we then check if that queue is empty. However, there is a problem with simply checking the queue length. When a sk_buff is being processed from the ingress queue but not yet on the sockmap msg receive queue its possible to also recv a sk_buff through normal path. It will check the ingress queue which is zero and then skip ahead of the pkt being processed. Previously we used sock lock from both contexts which made the problem harder to hit, but not impossible. To fix instead of popping the skb from the queue entirely we peek the skb from the queue and do the copy there. This ensures checks to the queue length are non-zero while skb is being processed. Then finally when the entire skb has been copied to user space queue or another socket we pop it off the queue. This way the queue length check allows bypassing the queue only after the list has been completely processed. To reproduce issue we run NGINX compliance test with sockmap running and observe some flakes in our testing that we attributed to this issue. Fixes: 04919bed948dc ("tcp: Introduce tcp_read_skb()") Suggested-by: Jakub Sitnicki <jakub@cloudflare.com> 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/20230523025618.113937-5-john.fastabend@gmail.com
2023-05-23 02:56:08 +00:00
skb = skb_dequeue(&psock->ingress_skb);
bpf, sockmap: Fix skb refcnt race after locking changes There is a race where skb's from the sk_psock_backlog can be referenced after userspace side has already skb_consumed() the sk_buff and its refcnt dropped to zer0 causing use after free. The flow is the following: while ((skb = skb_peek(&psock->ingress_skb)) sk_psock_handle_Skb(psock, skb, ..., ingress) if (!ingress) ... sk_psock_skb_ingress sk_psock_skb_ingress_enqueue(skb) msg->skb = skb sk_psock_queue_msg(psock, msg) skb_dequeue(&psock->ingress_skb) The sk_psock_queue_msg() puts the msg on the ingress_msg queue. This is what the application reads when recvmsg() is called. An application can read this anytime after the msg is placed on the queue. The recvmsg hook will also read msg->skb and then after user space reads the msg will call consume_skb(skb) on it effectively free'ing it. But, the race is in above where backlog queue still has a reference to the skb and calls skb_dequeue(). If the skb_dequeue happens after the user reads and free's the skb we have a use after free. The !ingress case does not suffer from this problem because it uses sendmsg_*(sk, msg) which does not pass the sk_buff further down the stack. The following splat was observed with 'test_progs -t sockmap_listen': [ 1022.710250][ T2556] general protection fault, ... [...] [ 1022.712830][ T2556] Workqueue: events sk_psock_backlog [ 1022.713262][ T2556] RIP: 0010:skb_dequeue+0x4c/0x80 [ 1022.713653][ T2556] Code: ... [...] [ 1022.720699][ T2556] Call Trace: [ 1022.720984][ T2556] <TASK> [ 1022.721254][ T2556] ? die_addr+0x32/0x80^M [ 1022.721589][ T2556] ? exc_general_protection+0x25a/0x4b0 [ 1022.722026][ T2556] ? asm_exc_general_protection+0x22/0x30 [ 1022.722489][ T2556] ? skb_dequeue+0x4c/0x80 [ 1022.722854][ T2556] sk_psock_backlog+0x27a/0x300 [ 1022.723243][ T2556] process_one_work+0x2a7/0x5b0 [ 1022.723633][ T2556] worker_thread+0x4f/0x3a0 [ 1022.723998][ T2556] ? __pfx_worker_thread+0x10/0x10 [ 1022.724386][ T2556] kthread+0xfd/0x130 [ 1022.724709][ T2556] ? __pfx_kthread+0x10/0x10 [ 1022.725066][ T2556] ret_from_fork+0x2d/0x50 [ 1022.725409][ T2556] ? __pfx_kthread+0x10/0x10 [ 1022.725799][ T2556] ret_from_fork_asm+0x1b/0x30 [ 1022.726201][ T2556] </TASK> To fix we add an skb_get() before passing the skb to be enqueued in the engress queue. This bumps the skb->users refcnt so that consume_skb() and kfree_skb will not immediately free the sk_buff. With this we can be sure the skb is still around when we do the dequeue. Then we just need to decrement the refcnt or free the skb in the backlog case which we do by calling kfree_skb() on the ingress case as well as the sendmsg case. Before locking change from fixes tag we had the sock locked so we couldn't race with user and there was no issue here. Fixes: 799aa7f98d53e ("skmsg: Avoid lock_sock() in sk_psock_backlog()") Reported-by: Jiri Olsa <jolsa@kernel.org> Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Tested-by: Xu Kuohai <xukuohai@huawei.com> Tested-by: Jiri Olsa <jolsa@kernel.org> Link: https://lore.kernel.org/bpf/20230901202137.214666-1-john.fastabend@gmail.com
2023-09-01 20:21:37 +00:00
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 00:45:58 +00:00
}
end:
skmsg: Avoid lock_sock() in sk_psock_backlog() We do not have to lock the sock to avoid losing sk_socket, instead we can purge all the ingress queues when we close the socket. Sending or receiving packets after orphaning socket makes no sense. We do purge these queues when psock refcnt reaches zero but here we want to purge them explicitly in sock_map_close(). There are also some nasty race conditions on testing bit SK_PSOCK_TX_ENABLED and queuing/canceling the psock work, we can expand psock->ingress_lock a bit to protect them too. As noticed by John, we still have to lock the psock->work, because the same work item could be running concurrently on different CPU's. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210331023237.41094-5-xiyou.wangcong@gmail.com
2021-03-31 02:32:25 +00:00
mutex_unlock(&psock->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 00:45:58 +00:00
}
struct sk_psock *sk_psock_init(struct sock *sk, int node)
{
net: sk_msg: Simplify sk_psock initialization Initializing psock->sk_proto and other saved callbacks is only done in sk_psock_update_proto, after sk_psock_init has returned. The logic for this is difficult to follow, and needlessly complex. Instead, initialize psock->sk_proto whenever we allocate a new psock. Additionally, assert the following invariants: * The SK has no ULP: ULP does it's own finagling of sk->sk_prot * sk_user_data is unused: we need it to store sk_psock Protect our access to sk_user_data with sk_callback_lock, which is what other users like reuseport arrays, etc. do. The result is that an sk_psock is always fully initialized, and that psock->sk_proto is always the "original" struct proto. The latter allows us to use psock->sk_proto when initializing IPv6 TCP / UDP callbacks for sockmap. Signed-off-by: Lorenz Bauer <lmb@cloudflare.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20200821102948.21918-2-lmb@cloudflare.com
2020-08-21 10:29:43 +00:00
struct sk_psock *psock;
struct proto *prot;
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 00:45:58 +00:00
net: sk_msg: Simplify sk_psock initialization Initializing psock->sk_proto and other saved callbacks is only done in sk_psock_update_proto, after sk_psock_init has returned. The logic for this is difficult to follow, and needlessly complex. Instead, initialize psock->sk_proto whenever we allocate a new psock. Additionally, assert the following invariants: * The SK has no ULP: ULP does it's own finagling of sk->sk_prot * sk_user_data is unused: we need it to store sk_psock Protect our access to sk_user_data with sk_callback_lock, which is what other users like reuseport arrays, etc. do. The result is that an sk_psock is always fully initialized, and that psock->sk_proto is always the "original" struct proto. The latter allows us to use psock->sk_proto when initializing IPv6 TCP / UDP callbacks for sockmap. Signed-off-by: Lorenz Bauer <lmb@cloudflare.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20200821102948.21918-2-lmb@cloudflare.com
2020-08-21 10:29:43 +00:00
write_lock_bh(&sk->sk_callback_lock);
sock: redo the psock vs ULP protection check Commit 8a59f9d1e3d4 ("sock: Introduce sk->sk_prot->psock_update_sk_prot()") has moved the inet_csk_has_ulp(sk) check from sk_psock_init() to the new tcp_bpf_update_proto() function. I'm guessing that this was done to allow creating psocks for non-inet sockets. Unfortunately the destruction path for psock includes the ULP unwind, so we need to fail the sk_psock_init() itself. Otherwise if ULP is already present we'll notice that later, and call tcp_update_ulp() with the sk_proto of the ULP itself, which will most likely result in the ULP looping its callbacks. Fixes: 8a59f9d1e3d4 ("sock: Introduce sk->sk_prot->psock_update_sk_prot()") Signed-off-by: Jakub Kicinski <kuba@kernel.org> Reviewed-by: John Fastabend <john.fastabend@gmail.com> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Tested-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/r/20220620191353.1184629-2-kuba@kernel.org Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2022-06-20 19:13:53 +00:00
if (sk_is_inet(sk) && inet_csk_has_ulp(sk)) {
psock = ERR_PTR(-EINVAL);
goto out;
}
net: sk_msg: Simplify sk_psock initialization Initializing psock->sk_proto and other saved callbacks is only done in sk_psock_update_proto, after sk_psock_init has returned. The logic for this is difficult to follow, and needlessly complex. Instead, initialize psock->sk_proto whenever we allocate a new psock. Additionally, assert the following invariants: * The SK has no ULP: ULP does it's own finagling of sk->sk_prot * sk_user_data is unused: we need it to store sk_psock Protect our access to sk_user_data with sk_callback_lock, which is what other users like reuseport arrays, etc. do. The result is that an sk_psock is always fully initialized, and that psock->sk_proto is always the "original" struct proto. The latter allows us to use psock->sk_proto when initializing IPv6 TCP / UDP callbacks for sockmap. Signed-off-by: Lorenz Bauer <lmb@cloudflare.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20200821102948.21918-2-lmb@cloudflare.com
2020-08-21 10:29:43 +00:00
if (sk->sk_user_data) {
psock = ERR_PTR(-EBUSY);
goto out;
}
psock = kzalloc_node(sizeof(*psock), GFP_ATOMIC | __GFP_NOWARN, node);
if (!psock) {
psock = ERR_PTR(-ENOMEM);
goto out;
}
prot = READ_ONCE(sk->sk_prot);
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 00:45:58 +00:00
psock->sk = sk;
net: sk_msg: Simplify sk_psock initialization Initializing psock->sk_proto and other saved callbacks is only done in sk_psock_update_proto, after sk_psock_init has returned. The logic for this is difficult to follow, and needlessly complex. Instead, initialize psock->sk_proto whenever we allocate a new psock. Additionally, assert the following invariants: * The SK has no ULP: ULP does it's own finagling of sk->sk_prot * sk_user_data is unused: we need it to store sk_psock Protect our access to sk_user_data with sk_callback_lock, which is what other users like reuseport arrays, etc. do. The result is that an sk_psock is always fully initialized, and that psock->sk_proto is always the "original" struct proto. The latter allows us to use psock->sk_proto when initializing IPv6 TCP / UDP callbacks for sockmap. Signed-off-by: Lorenz Bauer <lmb@cloudflare.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20200821102948.21918-2-lmb@cloudflare.com
2020-08-21 10:29:43 +00:00
psock->eval = __SK_NONE;
psock->sk_proto = prot;
psock->saved_unhash = prot->unhash;
bpf, sockmap: Fix sk->sk_forward_alloc warn_on in sk_stream_kill_queues During TCP sockmap redirect pressure test, the following warning is triggered: WARNING: CPU: 3 PID: 2145 at net/core/stream.c:205 sk_stream_kill_queues+0xbc/0xd0 CPU: 3 PID: 2145 Comm: iperf Kdump: loaded Tainted: G W 5.10.0+ #9 Call Trace: inet_csk_destroy_sock+0x55/0x110 inet_csk_listen_stop+0xbb/0x380 tcp_close+0x41b/0x480 inet_release+0x42/0x80 __sock_release+0x3d/0xa0 sock_close+0x11/0x20 __fput+0x9d/0x240 task_work_run+0x62/0x90 exit_to_user_mode_prepare+0x110/0x120 syscall_exit_to_user_mode+0x27/0x190 entry_SYSCALL_64_after_hwframe+0x44/0xa9 The reason we observed is that: When the listener is closing, a connection may have completed the three-way handshake but not accepted, and the client has sent some packets. The child sks in accept queue release by inet_child_forget()->inet_csk_destroy_sock(), but psocks of child sks have not released. To fix, add sock_map_destroy to release psocks. Signed-off-by: Wang Yufen <wangyufen@huawei.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20220524075311.649153-1-wangyufen@huawei.com
2022-05-24 07:53:11 +00:00
psock->saved_destroy = prot->destroy;
net: sk_msg: Simplify sk_psock initialization Initializing psock->sk_proto and other saved callbacks is only done in sk_psock_update_proto, after sk_psock_init has returned. The logic for this is difficult to follow, and needlessly complex. Instead, initialize psock->sk_proto whenever we allocate a new psock. Additionally, assert the following invariants: * The SK has no ULP: ULP does it's own finagling of sk->sk_prot * sk_user_data is unused: we need it to store sk_psock Protect our access to sk_user_data with sk_callback_lock, which is what other users like reuseport arrays, etc. do. The result is that an sk_psock is always fully initialized, and that psock->sk_proto is always the "original" struct proto. The latter allows us to use psock->sk_proto when initializing IPv6 TCP / UDP callbacks for sockmap. Signed-off-by: Lorenz Bauer <lmb@cloudflare.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20200821102948.21918-2-lmb@cloudflare.com
2020-08-21 10:29:43 +00:00
psock->saved_close = prot->close;
psock->saved_write_space = sk->sk_write_space;
bpf, sockmap: convert to generic sk_msg interface Add a generic sk_msg layer, and convert current sockmap and later kTLS over to make use of it. While sk_buff handles network packet representation from netdevice up to socket, sk_msg handles data representation from application to socket layer. This means that sk_msg framework spans across ULP users in the kernel, and enables features such as introspection or filtering of data with the help of BPF programs that operate on this data structure. Latter becomes in particular useful for kTLS where data encryption is deferred into the kernel, and as such enabling the kernel to perform L7 introspection and policy based on BPF for TLS connections where the record is being encrypted after BPF has run and came to a verdict. In order to get there, first step is to transform open coding of scatter-gather list handling into a common core framework that subsystems can use. The code itself has been split and refactored into three bigger pieces: i) the generic sk_msg API which deals with managing the scatter gather ring, providing helpers for walking and mangling, transferring application data from user space into it, and preparing it for BPF pre/post-processing, ii) the plain sock map itself where sockets can be attached to or detached from; these bits are independent of i) which can now be used also without sock map, and iii) the integration with plain TCP as one protocol to be used for processing L7 application data (later this could e.g. also be extended to other protocols like UDP). The semantics are the same with the old sock map code and therefore no change of user facing behavior or APIs. While pursuing this work it also helped finding a number of bugs in the old sockmap code that we've fixed already in earlier commits. The test_sockmap kselftest suite passes through fine as well. Joint work with John. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-13 00:45:58 +00:00
INIT_LIST_HEAD(&psock->link);
spin_lock_init(&psock->link_lock);
bpf, sockmap: Convert schedule_work into delayed_work 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
2023-05-23 02:56:06 +00:00
INIT_DELAYED_WORK(&psock->work, sk_psock_backlog);
skmsg: Avoid lock_sock() in sk_psock_backlog() We do not have to lock the sock to avoid losing sk_socket, instead we can purge all the ingress queues when we close the socket. Sending or receiving packets after orphaning socket makes no sense. We do purge these queues when psock refcnt reaches zero but here we want to purge them explicitly in sock_map_close(). There are also some nasty race conditions on testing bit SK_PSOCK_TX_ENABLED and queuing/canceling the psock work, we can expand psock->ingress_lock a bit to protect them too. As noticed by John, we still have to lock the psock->work, because the same work item could be running concurrently on different CPU's. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210331023237.41094-5-xiyou.wangcong@gmail.com
2021-03-31 02:32:25 +00:00
mutex_init(&psock->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 00:45:58 +00:00
INIT_LIST_HEAD(&psock->ingress_msg);
skmsg: Introduce a spinlock to protect ingress_msg Currently we rely on lock_sock to protect ingress_msg, it is too big for this, we can actually just use a spinlock to protect this list like protecting other skb queues. __tcp_bpf_recvmsg() is still special because of peeking, it still has to use lock_sock. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210331023237.41094-3-xiyou.wangcong@gmail.com
2021-03-31 02:32:23 +00:00
spin_lock_init(&psock->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 00:45:58 +00:00
skb_queue_head_init(&psock->ingress_skb);
sk_psock_set_state(psock, SK_PSOCK_TX_ENABLED);
refcount_set(&psock->refcnt, 1);
net: fix refcount bug in sk_psock_get (2) 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>
2022-08-05 07:48:34 +00:00
__rcu_assign_sk_user_data_with_flags(sk, psock,
SK_USER_DATA_NOCOPY |
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 00:45:58 +00:00
sock_hold(sk);
net: sk_msg: Simplify sk_psock initialization Initializing psock->sk_proto and other saved callbacks is only done in sk_psock_update_proto, after sk_psock_init has returned. The logic for this is difficult to follow, and needlessly complex. Instead, initialize psock->sk_proto whenever we allocate a new psock. Additionally, assert the following invariants: * The SK has no ULP: ULP does it's own finagling of sk->sk_prot * sk_user_data is unused: we need it to store sk_psock Protect our access to sk_user_data with sk_callback_lock, which is what other users like reuseport arrays, etc. do. The result is that an sk_psock is always fully initialized, and that psock->sk_proto is always the "original" struct proto. The latter allows us to use psock->sk_proto when initializing IPv6 TCP / UDP callbacks for sockmap. Signed-off-by: Lorenz Bauer <lmb@cloudflare.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20200821102948.21918-2-lmb@cloudflare.com
2020-08-21 10:29:43 +00:00
out:
write_unlock_bh(&sk->sk_callback_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 00:45:58 +00:00
return psock;
}
EXPORT_SYMBOL_GPL(sk_psock_init);
struct sk_psock_link *sk_psock_link_pop(struct sk_psock *psock)
{
struct sk_psock_link *link;
spin_lock_bh(&psock->link_lock);
link = list_first_entry_or_null(&psock->link, struct sk_psock_link,
list);
if (link)
list_del(&link->list);
spin_unlock_bh(&psock->link_lock);
return link;
}
skmsg: Make __sk_psock_purge_ingress_msg() static It is only used within skmsg.c so can become static. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-8-xiyou.wangcong@gmail.com
2021-02-23 18:49:32 +00:00
static void __sk_psock_purge_ingress_msg(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 00:45:58 +00:00
{
struct sk_msg *msg, *tmp;
list_for_each_entry_safe(msg, tmp, &psock->ingress_msg, list) {
list_del(&msg->list);
sk_msg_free(psock->sk, msg);
kfree(msg);
}
}
skmsg: Avoid lock_sock() in sk_psock_backlog() We do not have to lock the sock to avoid losing sk_socket, instead we can purge all the ingress queues when we close the socket. Sending or receiving packets after orphaning socket makes no sense. We do purge these queues when psock refcnt reaches zero but here we want to purge them explicitly in sock_map_close(). There are also some nasty race conditions on testing bit SK_PSOCK_TX_ENABLED and queuing/canceling the psock work, we can expand psock->ingress_lock a bit to protect them too. As noticed by John, we still have to lock the psock->work, because the same work item could be running concurrently on different CPU's. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210331023237.41094-5-xiyou.wangcong@gmail.com
2021-03-31 02:32:25 +00:00
static void __sk_psock_zap_ingress(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 00:45:58 +00:00
{
skmsg: Move sk_redir from TCP_SKB_CB to skb Currently TCP_SKB_CB() is hard-coded in skmsg code, it certainly does not work for any other non-TCP protocols. We can move them to skb ext, but it introduces a memory allocation on fast path. Fortunately, we only need to a word-size to store all the information, because the flags actually only contains 1 bit so can be just packed into the lowest bit of the "pointer", which is stored as unsigned long. Inside struct sk_buff, '_skb_refdst' can be reused because skb dst is no longer needed after ->sk_data_ready() so we can just drop it. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-5-xiyou.wangcong@gmail.com
2021-02-23 18:49:29 +00:00
struct sk_buff *skb;
skmsg: Lock ingress_skb when purging Currently we purge the ingress_skb queue only when psock refcnt goes down to 0, so locking the queue is not necessary, but in order to be called during ->close, we have to lock it here. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210331023237.41094-2-xiyou.wangcong@gmail.com
2021-03-31 02:32:22 +00:00
while ((skb = skb_dequeue(&psock->ingress_skb)) != NULL) {
skmsg: Move sk_redir from TCP_SKB_CB to skb Currently TCP_SKB_CB() is hard-coded in skmsg code, it certainly does not work for any other non-TCP protocols. We can move them to skb ext, but it introduces a memory allocation on fast path. Fortunately, we only need to a word-size to store all the information, because the flags actually only contains 1 bit so can be just packed into the lowest bit of the "pointer", which is stored as unsigned long. Inside struct sk_buff, '_skb_refdst' can be reused because skb dst is no longer needed after ->sk_data_ready() so we can just drop it. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-5-xiyou.wangcong@gmail.com
2021-02-23 18:49:29 +00:00
skb_bpf_redirect_clear(skb);
skmsg: Increase sk->sk_drops when dropping packets It is hard to observe packet drops without increasing relevant drop counters, here we should increase sk->sk_drops which is a protocol-independent counter. Fortunately psock is always associated with a struct sock, we can just use psock->sk. Suggested-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210615021342.7416-9-xiyou.wangcong@gmail.com
2021-06-15 02:13:42 +00:00
sock_drop(psock->sk, skb);
skmsg: Move sk_redir from TCP_SKB_CB to skb Currently TCP_SKB_CB() is hard-coded in skmsg code, it certainly does not work for any other non-TCP protocols. We can move them to skb ext, but it introduces a memory allocation on fast path. Fortunately, we only need to a word-size to store all the information, because the flags actually only contains 1 bit so can be just packed into the lowest bit of the "pointer", which is stored as unsigned long. Inside struct sk_buff, '_skb_refdst' can be reused because skb dst is no longer needed after ->sk_data_ready() so we can just drop it. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-5-xiyou.wangcong@gmail.com
2021-02-23 18:49:29 +00:00
}
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 00:45:58 +00:00
__sk_psock_purge_ingress_msg(psock);
}
static void sk_psock_link_destroy(struct sk_psock *psock)
{
struct sk_psock_link *link, *tmp;
list_for_each_entry_safe(link, tmp, &psock->link, list) {
list_del(&link->list);
sk_psock_free_link(link);
}
}
bpf, sock_map: Move cancel_work_sync() out of sock lock Stanislav reported a lockdep warning, which is caused by the cancel_work_sync() called inside sock_map_close(), as analyzed below by Jakub: psock->work.func = sk_psock_backlog() ACQUIRE psock->work_mutex sk_psock_handle_skb() skb_send_sock() __skb_send_sock() sendpage_unlocked() kernel_sendpage() sock->ops->sendpage = inet_sendpage() sk->sk_prot->sendpage = tcp_sendpage() ACQUIRE sk->sk_lock tcp_sendpage_locked() RELEASE sk->sk_lock RELEASE psock->work_mutex sock_map_close() ACQUIRE sk->sk_lock sk_psock_stop() sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED) cancel_work_sync() __cancel_work_timer() __flush_work() // wait for psock->work to finish RELEASE sk->sk_lock We can move the cancel_work_sync() out of the sock lock protection, but still before saved_close() was called. Fixes: 799aa7f98d53 ("skmsg: Avoid lock_sock() in sk_psock_backlog()") Reported-by: Stanislav Fomichev <sdf@google.com> Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Tested-by: Jakub Sitnicki <jakub@cloudflare.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20221102043417.279409-1-xiyou.wangcong@gmail.com
2022-11-02 04:34:17 +00:00
void sk_psock_stop(struct sk_psock *psock)
skmsg: Avoid lock_sock() in sk_psock_backlog() We do not have to lock the sock to avoid losing sk_socket, instead we can purge all the ingress queues when we close the socket. Sending or receiving packets after orphaning socket makes no sense. We do purge these queues when psock refcnt reaches zero but here we want to purge them explicitly in sock_map_close(). There are also some nasty race conditions on testing bit SK_PSOCK_TX_ENABLED and queuing/canceling the psock work, we can expand psock->ingress_lock a bit to protect them too. As noticed by John, we still have to lock the psock->work, because the same work item could be running concurrently on different CPU's. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210331023237.41094-5-xiyou.wangcong@gmail.com
2021-03-31 02:32:25 +00:00
{
spin_lock_bh(&psock->ingress_lock);
sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED);
sk_psock_cork_free(psock);
spin_unlock_bh(&psock->ingress_lock);
}
bpf: Clean up sockmap related Kconfigs As suggested by John, clean up sockmap related Kconfigs: Reduce the scope of CONFIG_BPF_STREAM_PARSER down to TCP stream parser, to reflect its name. Make the rest sockmap code simply depend on CONFIG_BPF_SYSCALL and CONFIG_INET, the latter is still needed at this point because of TCP/UDP proto update. And leave CONFIG_NET_SOCK_MSG untouched, as it is used by non-sockmap cases. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Reviewed-by: Lorenz Bauer <lmb@cloudflare.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-2-xiyou.wangcong@gmail.com
2021-02-23 18:49:26 +00:00
static void sk_psock_done_strp(struct sk_psock *psock);
skmsg: Use rcu work for destroying psock The RCU callback sk_psock_destroy() only queues work psock->gc, so we can just switch to rcu work to simplify the code. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210331023237.41094-6-xiyou.wangcong@gmail.com
2021-03-31 02:32:26 +00:00
static void sk_psock_destroy(struct work_struct *work)
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 00:45:58 +00:00
{
skmsg: Use rcu work for destroying psock The RCU callback sk_psock_destroy() only queues work psock->gc, so we can just switch to rcu work to simplify the code. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210331023237.41094-6-xiyou.wangcong@gmail.com
2021-03-31 02:32:26 +00:00
struct sk_psock *psock = container_of(to_rcu_work(work),
struct sk_psock, 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 00:45:58 +00:00
/* No sk_callback_lock since already detached. */
bpf: sockmap, only stop/flush strp if it was enabled at some point If we try to call strp_done on a parser that has never been initialized, because the sockmap user is only using TX side for example we get the following error. [ 883.422081] WARNING: CPU: 1 PID: 208 at kernel/workqueue.c:3030 __flush_work+0x1ca/0x1e0 ... [ 883.422095] Workqueue: events sk_psock_destroy_deferred [ 883.422097] RIP: 0010:__flush_work+0x1ca/0x1e0 This had been wrapped in a 'if (psock->parser.enabled)' logic which was broken because the strp_done() was never actually being called because we do a strp_stop() earlier in the tear down logic will set parser.enabled to false. This could result in a use after free if work was still in the queue and was resolved by the patch here, 1d79895aef18f ("sk_msg: Always cancel strp work before freeing the psock"). However, calling strp_stop(), done by the patch marked in the fixes tag, only is useful if we never initialized a strp parser program and never initialized the strp to start with. Because if we had initialized a stream parser strp_stop() would have been called by sk_psock_drop() earlier in the tear down process. By forcing the strp to stop we get past the WARNING in strp_done that checks the stopped flag but calling cancel_work_sync on work that has never been initialized is also wrong and generates the warning above. To fix check if the parser program exists. If the program exists then the strp work has been initialized and must be sync'd and cancelled before free'ing any structures. If no program exists we never initialized the stream parser in the first place so skip the sync/cancel logic implemented by strp_done. Finally, remove the strp_done its not needed and in the case where we are using the stream parser has already been called. Fixes: e8e3437762ad9 ("bpf: Stop the psock parser before canceling its work") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-05-13 14:19:19 +00:00
bpf: Clean up sockmap related Kconfigs As suggested by John, clean up sockmap related Kconfigs: Reduce the scope of CONFIG_BPF_STREAM_PARSER down to TCP stream parser, to reflect its name. Make the rest sockmap code simply depend on CONFIG_BPF_SYSCALL and CONFIG_INET, the latter is still needed at this point because of TCP/UDP proto update. And leave CONFIG_NET_SOCK_MSG untouched, as it is used by non-sockmap cases. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Reviewed-by: Lorenz Bauer <lmb@cloudflare.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-2-xiyou.wangcong@gmail.com
2021-02-23 18:49:26 +00:00
sk_psock_done_strp(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 00:45:58 +00:00
bpf, sockmap: Convert schedule_work into delayed_work 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
2023-05-23 02:56:06 +00:00
cancel_delayed_work_sync(&psock->work);
bpf, sockmap: Improved check for empty queue We noticed some rare sk_buffs were stepping past the queue when system was under memory pressure. The general theory is to skip enqueueing sk_buffs when its not necessary which is the normal case with a system that is properly provisioned for the task, no memory pressure and enough cpu assigned. But, if we can't allocate memory due to an ENOMEM error when enqueueing the sk_buff into the sockmap receive queue we push it onto a delayed workqueue to retry later. When a new sk_buff is received we then check if that queue is empty. However, there is a problem with simply checking the queue length. When a sk_buff is being processed from the ingress queue but not yet on the sockmap msg receive queue its possible to also recv a sk_buff through normal path. It will check the ingress queue which is zero and then skip ahead of the pkt being processed. Previously we used sock lock from both contexts which made the problem harder to hit, but not impossible. To fix instead of popping the skb from the queue entirely we peek the skb from the queue and do the copy there. This ensures checks to the queue length are non-zero while skb is being processed. Then finally when the entire skb has been copied to user space queue or another socket we pop it off the queue. This way the queue length check allows bypassing the queue only after the list has been completely processed. To reproduce issue we run NGINX compliance test with sockmap running and observe some flakes in our testing that we attributed to this issue. Fixes: 04919bed948dc ("tcp: Introduce tcp_read_skb()") Suggested-by: Jakub Sitnicki <jakub@cloudflare.com> 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/20230523025618.113937-5-john.fastabend@gmail.com
2023-05-23 02:56:08 +00:00
__sk_psock_zap_ingress(psock);
skmsg: Avoid lock_sock() in sk_psock_backlog() We do not have to lock the sock to avoid losing sk_socket, instead we can purge all the ingress queues when we close the socket. Sending or receiving packets after orphaning socket makes no sense. We do purge these queues when psock refcnt reaches zero but here we want to purge them explicitly in sock_map_close(). There are also some nasty race conditions on testing bit SK_PSOCK_TX_ENABLED and queuing/canceling the psock work, we can expand psock->ingress_lock a bit to protect them too. As noticed by John, we still have to lock the psock->work, because the same work item could be running concurrently on different CPU's. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210331023237.41094-5-xiyou.wangcong@gmail.com
2021-03-31 02:32:25 +00:00
mutex_destroy(&psock->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 00:45:58 +00:00
psock_progs_drop(&psock->progs);
sk_psock_link_destroy(psock);
sk_psock_cork_free(psock);
if (psock->sk_redir)
sock_put(psock->sk_redir);
bpf, sockmap: af_unix stream sockets need to hold ref for pair sock AF_UNIX stream sockets are a paired socket. So sending on one of the pairs will lookup the paired socket as part of the send operation. It is possible however to put just one of the pairs in a BPF map. This currently increments the refcnt on the sock in the sockmap to ensure it is not free'd by the stack before sockmap cleans up its state and stops any skbs being sent/recv'd to that socket. But we missed a case. If the peer socket is closed it will be free'd by the stack. However, the paired socket can still be referenced from BPF sockmap side because we hold a reference there. Then if we are sending traffic through BPF sockmap to that socket it will try to dereference the free'd pair in its send logic creating a use after free. And following splat: [59.900375] BUG: KASAN: slab-use-after-free in sk_wake_async+0x31/0x1b0 [59.901211] Read of size 8 at addr ffff88811acbf060 by task kworker/1:2/954 [...] [59.905468] Call Trace: [59.905787] <TASK> [59.906066] dump_stack_lvl+0x130/0x1d0 [59.908877] print_report+0x16f/0x740 [59.910629] kasan_report+0x118/0x160 [59.912576] sk_wake_async+0x31/0x1b0 [59.913554] sock_def_readable+0x156/0x2a0 [59.914060] unix_stream_sendmsg+0x3f9/0x12a0 [59.916398] sock_sendmsg+0x20e/0x250 [59.916854] skb_send_sock+0x236/0xac0 [59.920527] sk_psock_backlog+0x287/0xaa0 To fix let BPF sockmap hold a refcnt on both the socket in the sockmap and its paired socket. It wasn't obvious how to contain the fix to bpf_unix logic. The primarily problem with keeping this logic in bpf_unix was: In the sock close() we could handle the deref by having a close handler. But, when we are destroying the psock through a map delete operation we wouldn't have gotten any signal thorugh the proto struct other than it being replaced. If we do the deref from the proto replace its too early because we need to deref the sk_pair after the backlog worker has been stopped. Given all this it seems best to just cache it at the end of the psock and eat 8B for the af_unix and vsock users. Notice dgram sockets are OK because they handle locking already. Fixes: 94531cfcbe79 ("af_unix: Add unix_stream_proto for sockmap") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20231129012557.95371-2-john.fastabend@gmail.com
2023-11-29 01:25:56 +00:00
if (psock->sk_pair)
sock_put(psock->sk_pair);
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 00:45:58 +00:00
sock_put(psock->sk);
kfree(psock);
}
void sk_psock_drop(struct sock *sk, struct sk_psock *psock)
{
write_lock_bh(&sk->sk_callback_lock);
bpf: sockmap/tls, close can race with map free When a map free is called and in parallel a socket is closed we have two paths that can potentially reset the socket prot ops, the bpf close() path and the map free path. This creates a problem with which prot ops should be used from the socket closed side. If the map_free side completes first then we want to call the original lowest level ops. However, if the tls path runs first we want to call the sockmap ops. Additionally there was no locking around prot updates in TLS code paths so the prot ops could be changed multiple times once from TLS path and again from sockmap side potentially leaving ops pointed at either TLS or sockmap when psock and/or tls context have already been destroyed. To fix this race first only update ops inside callback lock so that TLS, sockmap and lowest level all agree on prot state. Second and a ULP callback update() so that lower layers can inform the upper layer when they are being removed allowing the upper layer to reset prot ops. This gets us close to allowing sockmap and tls to be stacked in arbitrary order but will save that patch for *next trees. v4: - make sure we don't free things for device; - remove the checks which swap the callbacks back only if TLS is at the top. Reported-by: syzbot+06537213db7ba2745c4a@syzkaller.appspotmail.com Fixes: 02c558b2d5d6 ("bpf: sockmap, support for msg_peek in sk_msg with redirect ingress") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com> Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-07-19 17:29:22 +00:00
sk_psock_restore_proto(sk, psock);
rcu_assign_sk_user_data(sk, NULL);
sock_map: Rename skb_parser and skb_verdict These two eBPF programs are tied to BPF_SK_SKB_STREAM_PARSER and BPF_SK_SKB_STREAM_VERDICT, rename them to reflect the fact they are only used for TCP. And save the name 'skb_verdict' for general use later. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Reviewed-by: Lorenz Bauer <lmb@cloudflare.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-6-xiyou.wangcong@gmail.com
2021-02-23 18:49:30 +00:00
if (psock->progs.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 00:45:58 +00:00
sk_psock_stop_strp(sk, psock);
sock_map: Introduce BPF_SK_SKB_VERDICT Reusing BPF_SK_SKB_STREAM_VERDICT is possible but its name is confusing and more importantly we still want to distinguish them from user-space. So we can just reuse the stream verdict code but introduce a new type of eBPF program, skb_verdict. Users are not allowed to attach stream_verdict and skb_verdict programs to the same map. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210331023237.41094-10-xiyou.wangcong@gmail.com
2021-03-31 02:32:30 +00:00
else if (psock->progs.stream_verdict || psock->progs.skb_verdict)
bpf, sockmap: Allow skipping sk_skb parser program Currently, we often run with a nop parser namely one that just does this, 'return skb->len'. This happens when either our verdict program can handle streaming data or it is only looking at socket data such as IP addresses and other metadata associated with the flow. The second case is common for a L3/L4 proxy for instance. So lets allow loading programs without the parser then we can skip the stream parser logic and avoid having to add a BPF program that is effectively a nop. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/160239297866.8495.13345662302749219672.stgit@john-Precision-5820-Tower
2020-10-11 05:09:38 +00:00
sk_psock_stop_verdict(sk, 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 00:45:58 +00:00
write_unlock_bh(&sk->sk_callback_lock);
bpf, sock_map: Move cancel_work_sync() out of sock lock Stanislav reported a lockdep warning, which is caused by the cancel_work_sync() called inside sock_map_close(), as analyzed below by Jakub: psock->work.func = sk_psock_backlog() ACQUIRE psock->work_mutex sk_psock_handle_skb() skb_send_sock() __skb_send_sock() sendpage_unlocked() kernel_sendpage() sock->ops->sendpage = inet_sendpage() sk->sk_prot->sendpage = tcp_sendpage() ACQUIRE sk->sk_lock tcp_sendpage_locked() RELEASE sk->sk_lock RELEASE psock->work_mutex sock_map_close() ACQUIRE sk->sk_lock sk_psock_stop() sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED) cancel_work_sync() __cancel_work_timer() __flush_work() // wait for psock->work to finish RELEASE sk->sk_lock We can move the cancel_work_sync() out of the sock lock protection, but still before saved_close() was called. Fixes: 799aa7f98d53 ("skmsg: Avoid lock_sock() in sk_psock_backlog()") Reported-by: Stanislav Fomichev <sdf@google.com> Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Tested-by: Jakub Sitnicki <jakub@cloudflare.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20221102043417.279409-1-xiyou.wangcong@gmail.com
2022-11-02 04:34:17 +00:00
sk_psock_stop(psock);
bpf, sockmap: Zap ingress queues after stopping strparser We don't want strparser to run and pass skbs into skmsg handlers when the psock is null. We just sk_drop them in this case. When removing a live socket from map it means extra drops that we do not need to incur. Move the zap below strparser close to avoid this condition. This way we stop the stream parser first stopping it from processing packets and then delete the psock. Fixes: a136678c0bdbb ("bpf: sk_msg, zap ingress queue on psock down") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Link: https://lore.kernel.org/bpf/20210727160500.1713554-2-john.fastabend@gmail.com
2021-07-27 16:04:58 +00:00
skmsg: Use rcu work for destroying psock The RCU callback sk_psock_destroy() only queues work psock->gc, so we can just switch to rcu work to simplify the code. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210331023237.41094-6-xiyou.wangcong@gmail.com
2021-03-31 02:32:26 +00:00
INIT_RCU_WORK(&psock->rwork, sk_psock_destroy);
queue_rcu_work(system_wq, &psock->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 00:45:58 +00:00
}
EXPORT_SYMBOL_GPL(sk_psock_drop);
static int sk_psock_map_verd(int verdict, bool redir)
{
switch (verdict) {
case SK_PASS:
return redir ? __SK_REDIRECT : __SK_PASS;
case SK_DROP:
default:
break;
}
return __SK_DROP;
}
int sk_psock_msg_verdict(struct sock *sk, struct sk_psock *psock,
struct sk_msg *msg)
{
struct bpf_prog *prog;
int ret;
rcu_read_lock();
prog = READ_ONCE(psock->progs.msg_parser);
if (unlikely(!prog)) {
ret = __SK_PASS;
goto out;
}
sk_msg_compute_data_pointers(msg);
msg->sk = sk;
bpf: Use bpf_prog_run_pin_on_cpu() at simple call sites. All of these cases are strictly of the form: preempt_disable(); BPF_PROG_RUN(...); preempt_enable(); Replace this with bpf_prog_run_pin_on_cpu() which wraps BPF_PROG_RUN() with: migrate_disable(); BPF_PROG_RUN(...); migrate_enable(); On non RT enabled kernels this maps to preempt_disable/enable() and on RT enabled kernels this solely prevents migration, which is sufficient as there is no requirement to prevent reentrancy to any BPF program from a preempting task. The only requirement is that the program stays on the same CPU. Therefore, this is a trivially correct transformation. The seccomp loop does not need protection over the loop. It only needs protection per BPF filter program [ tglx: Converted to bpf_prog_run_pin_on_cpu() ] Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20200224145643.691493094@linutronix.de
2020-02-24 14:01:43 +00:00
ret = bpf_prog_run_pin_on_cpu(prog, 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 00:45:58 +00:00
ret = sk_psock_map_verd(ret, msg->sk_redir);
psock->apply_bytes = msg->apply_bytes;
if (ret == __SK_REDIRECT) {
bpf, sockmap: Fix missing BPF_F_INGRESS flag when using apply_bytes When redirecting, we use sk_msg_to_ingress() to get the BPF_F_INGRESS flag from the msg->flags. If apply_bytes is used and it is larger than the current data being processed, sk_psock_msg_verdict() will not be called when sendmsg() is called again. At this time, the msg->flags is 0, and we lost the BPF_F_INGRESS flag. So we need to save the BPF_F_INGRESS flag in sk_psock and use it when redirection. Fixes: 8934ce2fd081 ("bpf: sockmap redirect ingress support") Signed-off-by: Pengcheng Yang <yangpc@wangsu.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/1669718441-2654-3-git-send-email-yangpc@wangsu.com
2022-11-29 10:40:39 +00:00
if (psock->sk_redir) {
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 00:45:58 +00:00
sock_put(psock->sk_redir);
bpf, sockmap: Fix missing BPF_F_INGRESS flag when using apply_bytes When redirecting, we use sk_msg_to_ingress() to get the BPF_F_INGRESS flag from the msg->flags. If apply_bytes is used and it is larger than the current data being processed, sk_psock_msg_verdict() will not be called when sendmsg() is called again. At this time, the msg->flags is 0, and we lost the BPF_F_INGRESS flag. So we need to save the BPF_F_INGRESS flag in sk_psock and use it when redirection. Fixes: 8934ce2fd081 ("bpf: sockmap redirect ingress support") Signed-off-by: Pengcheng Yang <yangpc@wangsu.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/1669718441-2654-3-git-send-email-yangpc@wangsu.com
2022-11-29 10:40:39 +00:00
psock->sk_redir = NULL;
}
if (!msg->sk_redir) {
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 00:45:58 +00:00
ret = __SK_DROP;
goto out;
}
bpf, sockmap: Fix missing BPF_F_INGRESS flag when using apply_bytes When redirecting, we use sk_msg_to_ingress() to get the BPF_F_INGRESS flag from the msg->flags. If apply_bytes is used and it is larger than the current data being processed, sk_psock_msg_verdict() will not be called when sendmsg() is called again. At this time, the msg->flags is 0, and we lost the BPF_F_INGRESS flag. So we need to save the BPF_F_INGRESS flag in sk_psock and use it when redirection. Fixes: 8934ce2fd081 ("bpf: sockmap redirect ingress support") Signed-off-by: Pengcheng Yang <yangpc@wangsu.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/1669718441-2654-3-git-send-email-yangpc@wangsu.com
2022-11-29 10:40:39 +00:00
psock->redir_ingress = sk_msg_to_ingress(msg);
psock->sk_redir = msg->sk_redir;
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 00:45:58 +00:00
sock_hold(psock->sk_redir);
}
out:
rcu_read_unlock();
return ret;
}
EXPORT_SYMBOL_GPL(sk_psock_msg_verdict);
skmsg: Pass source psock to sk_psock_skb_redirect() sk_psock_skb_redirect() only takes skb as a parameter, we will need to know where this skb is from, so just pass the source psock to this function as a new parameter. This patch prepares for the next one. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210615021342.7416-8-xiyou.wangcong@gmail.com
2021-06-15 02:13:41 +00:00
static int sk_psock_skb_redirect(struct sk_psock *from, struct sk_buff *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 00:45:58 +00:00
{
struct sk_psock *psock_other;
struct sock *sk_other;
skmsg: Move sk_redir from TCP_SKB_CB to skb Currently TCP_SKB_CB() is hard-coded in skmsg code, it certainly does not work for any other non-TCP protocols. We can move them to skb ext, but it introduces a memory allocation on fast path. Fortunately, we only need to a word-size to store all the information, because the flags actually only contains 1 bit so can be just packed into the lowest bit of the "pointer", which is stored as unsigned long. Inside struct sk_buff, '_skb_refdst' can be reused because skb dst is no longer needed after ->sk_data_ready() so we can just drop it. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-5-xiyou.wangcong@gmail.com
2021-02-23 18:49:29 +00:00
sk_other = skb_bpf_redirect_fetch(skb);
bpf, sockmap: Remove dropped data on errors in redirect case In the sk_skb redirect case we didn't handle the case where we overrun the sk_rmem_alloc entry on ingress redirect or sk_wmem_alloc on egress. Because we didn't have anything implemented we simply dropped the skb. This meant data could be dropped if socket memory accounting was in place. This fixes the above dropped data case by moving the memory checks later in the code where we actually do the send or recv. This pushes those checks into the workqueue and allows us to return an EAGAIN error which in turn allows us to try again later from the workqueue. Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/160226863689.5692.13861422742592309285.stgit@john-Precision-5820-Tower
2020-10-09 18:37:17 +00:00
/* This error is a buggy BPF program, it returned a redirect
* return code, but then didn't set a redirect interface.
*/
bpf: Refactor sockmap redirect code so its easy to reuse We will need this block of code called from tls context shortly lets refactor the redirect logic so its easy to use. This also cleans up the switch stmt so we have fewer fallthrough cases. No logic changes are intended. Fixes: d829e9c4112b5 ("tls: convert to generic sk_msg interface") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/159079360110.5745.7024009076049029819.stgit@john-Precision-5820-Tower Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-29 23:06:41 +00:00
if (unlikely(!sk_other)) {
skmsg: Lose offset info in sk_psock_skb_ingress If sockmap enable strparser, there are lose offset info in sk_psock_skb_ingress(). If the length determined by parse_msg function is not skb->len, the skb will be converted to sk_msg multiple times, and userspace app will get the data multiple times. Fix this by get the offset and length from strp_msg. And as Cong suggested, add one bit in skb->_sk_redir to distinguish enable or disable strparser. Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Liu Jian <liujian56@huawei.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Cong Wang <cong.wang@bytedance.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20211029141216.211899-1-liujian56@huawei.com
2021-10-29 14:12:14 +00:00
skb_bpf_redirect_clear(skb);
skmsg: Increase sk->sk_drops when dropping packets It is hard to observe packet drops without increasing relevant drop counters, here we should increase sk->sk_drops which is a protocol-independent counter. Fortunately psock is always associated with a struct sock, we can just use psock->sk. Suggested-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210615021342.7416-9-xiyou.wangcong@gmail.com
2021-06-15 02:13:42 +00:00
sock_drop(from->sk, skb);
skmsg: Teach sk_psock_verdict_apply() to return errors Currently sk_psock_verdict_apply() is void, but it handles some error conditions too. Its caller is impossible to learn whether it succeeds or fails, especially sk_psock_verdict_recv(). Make it return int to indicate error cases and propagate errors to callers properly. Fixes: ef5659280eb1 ("bpf, sockmap: Allow skipping sk_skb parser program") Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210615021342.7416-7-xiyou.wangcong@gmail.com
2021-06-15 02:13:40 +00:00
return -EIO;
bpf: Refactor sockmap redirect code so its easy to reuse We will need this block of code called from tls context shortly lets refactor the redirect logic so its easy to use. This also cleans up the switch stmt so we have fewer fallthrough cases. No logic changes are intended. Fixes: d829e9c4112b5 ("tls: convert to generic sk_msg interface") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/159079360110.5745.7024009076049029819.stgit@john-Precision-5820-Tower Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-29 23:06:41 +00:00
}
psock_other = sk_psock(sk_other);
bpf, sockmap: Remove dropped data on errors in redirect case In the sk_skb redirect case we didn't handle the case where we overrun the sk_rmem_alloc entry on ingress redirect or sk_wmem_alloc on egress. Because we didn't have anything implemented we simply dropped the skb. This meant data could be dropped if socket memory accounting was in place. This fixes the above dropped data case by moving the memory checks later in the code where we actually do the send or recv. This pushes those checks into the workqueue and allows us to return an EAGAIN error which in turn allows us to try again later from the workqueue. Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/160226863689.5692.13861422742592309285.stgit@john-Precision-5820-Tower
2020-10-09 18:37:17 +00:00
/* This error indicates the socket is being torn down or had another
* error that caused the pipe to break. We can't send a packet on
* a socket that is in this state so we drop the skb.
*/
skmsg: Avoid lock_sock() in sk_psock_backlog() We do not have to lock the sock to avoid losing sk_socket, instead we can purge all the ingress queues when we close the socket. Sending or receiving packets after orphaning socket makes no sense. We do purge these queues when psock refcnt reaches zero but here we want to purge them explicitly in sock_map_close(). There are also some nasty race conditions on testing bit SK_PSOCK_TX_ENABLED and queuing/canceling the psock work, we can expand psock->ingress_lock a bit to protect them too. As noticed by John, we still have to lock the psock->work, because the same work item could be running concurrently on different CPU's. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210331023237.41094-5-xiyou.wangcong@gmail.com
2021-03-31 02:32:25 +00:00
if (!psock_other || sock_flag(sk_other, SOCK_DEAD)) {
skmsg: Clear skb redirect pointer before dropping it When we drop skb inside sk_psock_skb_redirect(), we have to clear its skb->_sk_redir pointer too, otherwise kfree_skb() would misinterpret it as a valid skb->_skb_refdst and dst_release() would eventually complain. Fixes: e3526bb92a20 ("skmsg: Move sk_redir from TCP_SKB_CB to skb") Reported-by: Jiang Wang <jiang.wang@bytedance.com> Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210615021342.7416-5-xiyou.wangcong@gmail.com
2021-06-15 02:13:38 +00:00
skb_bpf_redirect_clear(skb);
skmsg: Increase sk->sk_drops when dropping packets It is hard to observe packet drops without increasing relevant drop counters, here we should increase sk->sk_drops which is a protocol-independent counter. Fortunately psock is always associated with a struct sock, we can just use psock->sk. Suggested-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210615021342.7416-9-xiyou.wangcong@gmail.com
2021-06-15 02:13:42 +00:00
sock_drop(from->sk, skb);
skmsg: Teach sk_psock_verdict_apply() to return errors Currently sk_psock_verdict_apply() is void, but it handles some error conditions too. Its caller is impossible to learn whether it succeeds or fails, especially sk_psock_verdict_recv(). Make it return int to indicate error cases and propagate errors to callers properly. Fixes: ef5659280eb1 ("bpf, sockmap: Allow skipping sk_skb parser program") Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210615021342.7416-7-xiyou.wangcong@gmail.com
2021-06-15 02:13:40 +00:00
return -EIO;
skmsg: Avoid lock_sock() in sk_psock_backlog() We do not have to lock the sock to avoid losing sk_socket, instead we can purge all the ingress queues when we close the socket. Sending or receiving packets after orphaning socket makes no sense. We do purge these queues when psock refcnt reaches zero but here we want to purge them explicitly in sock_map_close(). There are also some nasty race conditions on testing bit SK_PSOCK_TX_ENABLED and queuing/canceling the psock work, we can expand psock->ingress_lock a bit to protect them too. As noticed by John, we still have to lock the psock->work, because the same work item could be running concurrently on different CPU's. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210331023237.41094-5-xiyou.wangcong@gmail.com
2021-03-31 02:32:25 +00:00
}
spin_lock_bh(&psock_other->ingress_lock);
if (!sk_psock_test_state(psock_other, SK_PSOCK_TX_ENABLED)) {
spin_unlock_bh(&psock_other->ingress_lock);
skmsg: Clear skb redirect pointer before dropping it When we drop skb inside sk_psock_skb_redirect(), we have to clear its skb->_sk_redir pointer too, otherwise kfree_skb() would misinterpret it as a valid skb->_skb_refdst and dst_release() would eventually complain. Fixes: e3526bb92a20 ("skmsg: Move sk_redir from TCP_SKB_CB to skb") Reported-by: Jiang Wang <jiang.wang@bytedance.com> Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210615021342.7416-5-xiyou.wangcong@gmail.com
2021-06-15 02:13:38 +00:00
skb_bpf_redirect_clear(skb);
skmsg: Increase sk->sk_drops when dropping packets It is hard to observe packet drops without increasing relevant drop counters, here we should increase sk->sk_drops which is a protocol-independent counter. Fortunately psock is always associated with a struct sock, we can just use psock->sk. Suggested-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210615021342.7416-9-xiyou.wangcong@gmail.com
2021-06-15 02:13:42 +00:00
sock_drop(from->sk, skb);
skmsg: Teach sk_psock_verdict_apply() to return errors Currently sk_psock_verdict_apply() is void, but it handles some error conditions too. Its caller is impossible to learn whether it succeeds or fails, especially sk_psock_verdict_recv(). Make it return int to indicate error cases and propagate errors to callers properly. Fixes: ef5659280eb1 ("bpf, sockmap: Allow skipping sk_skb parser program") Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210615021342.7416-7-xiyou.wangcong@gmail.com
2021-06-15 02:13:40 +00:00
return -EIO;
bpf: Refactor sockmap redirect code so its easy to reuse We will need this block of code called from tls context shortly lets refactor the redirect logic so its easy to use. This also cleans up the switch stmt so we have fewer fallthrough cases. No logic changes are intended. Fixes: d829e9c4112b5 ("tls: convert to generic sk_msg interface") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/159079360110.5745.7024009076049029819.stgit@john-Precision-5820-Tower Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-29 23:06:41 +00:00
}
bpf, sockmap: Remove dropped data on errors in redirect case In the sk_skb redirect case we didn't handle the case where we overrun the sk_rmem_alloc entry on ingress redirect or sk_wmem_alloc on egress. Because we didn't have anything implemented we simply dropped the skb. This meant data could be dropped if socket memory accounting was in place. This fixes the above dropped data case by moving the memory checks later in the code where we actually do the send or recv. This pushes those checks into the workqueue and allows us to return an EAGAIN error which in turn allows us to try again later from the workqueue. Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/160226863689.5692.13861422742592309285.stgit@john-Precision-5820-Tower
2020-10-09 18:37:17 +00:00
skb_queue_tail(&psock_other->ingress_skb, skb);
bpf, sockmap: Convert schedule_work into delayed_work 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
2023-05-23 02:56:06 +00:00
schedule_delayed_work(&psock_other->work, 0);
skmsg: Avoid lock_sock() in sk_psock_backlog() We do not have to lock the sock to avoid losing sk_socket, instead we can purge all the ingress queues when we close the socket. Sending or receiving packets after orphaning socket makes no sense. We do purge these queues when psock refcnt reaches zero but here we want to purge them explicitly in sock_map_close(). There are also some nasty race conditions on testing bit SK_PSOCK_TX_ENABLED and queuing/canceling the psock work, we can expand psock->ingress_lock a bit to protect them too. As noticed by John, we still have to lock the psock->work, because the same work item could be running concurrently on different CPU's. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210331023237.41094-5-xiyou.wangcong@gmail.com
2021-03-31 02:32:25 +00:00
spin_unlock_bh(&psock_other->ingress_lock);
skmsg: Teach sk_psock_verdict_apply() to return errors Currently sk_psock_verdict_apply() is void, but it handles some error conditions too. Its caller is impossible to learn whether it succeeds or fails, especially sk_psock_verdict_recv(). Make it return int to indicate error cases and propagate errors to callers properly. Fixes: ef5659280eb1 ("bpf, sockmap: Allow skipping sk_skb parser program") Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210615021342.7416-7-xiyou.wangcong@gmail.com
2021-06-15 02:13:40 +00:00
return 0;
bpf: Refactor sockmap redirect code so its easy to reuse We will need this block of code called from tls context shortly lets refactor the redirect logic so its easy to use. This also cleans up the switch stmt so we have fewer fallthrough cases. No logic changes are intended. Fixes: d829e9c4112b5 ("tls: convert to generic sk_msg interface") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/159079360110.5745.7024009076049029819.stgit@john-Precision-5820-Tower Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-29 23:06:41 +00:00
}
skmsg: Pass source psock to sk_psock_skb_redirect() sk_psock_skb_redirect() only takes skb as a parameter, we will need to know where this skb is from, so just pass the source psock to this function as a new parameter. This patch prepares for the next one. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210615021342.7416-8-xiyou.wangcong@gmail.com
2021-06-15 02:13:41 +00:00
static void sk_psock_tls_verdict_apply(struct sk_buff *skb,
struct sk_psock *from, int verdict)
bpf: Fix running sk_skb program types with ktls KTLS uses a stream parser to collect TLS messages and send them to the upper layer tls receive handler. This ensures the tls receiver has a full TLS header to parse when it is run. However, when a socket has BPF_SK_SKB_STREAM_VERDICT program attached before KTLS is enabled we end up with two stream parsers running on the same socket. The result is both try to run on the same socket. First the KTLS stream parser runs and calls read_sock() which will tcp_read_sock which in turn calls tcp_rcv_skb(). This dequeues the skb from the sk_receive_queue. When this is done KTLS code then data_ready() callback which because we stacked KTLS on top of the bpf stream verdict program has been replaced with sk_psock_start_strp(). This will in turn kick the stream parser again and eventually do the same thing KTLS did above calling into tcp_rcv_skb() and dequeuing a skb from the sk_receive_queue. At this point the data stream is broke. Part of the stream was handled by the KTLS side some other bytes may have been handled by the BPF side. Generally this results in either missing data or more likely a "Bad Message" complaint from the kTLS receive handler as the BPF program steals some bytes meant to be in a TLS header and/or the TLS header length is no longer correct. We've already broke the idealized model where we can stack ULPs in any order with generic callbacks on the TX side to handle this. So in this patch we do the same thing but for RX side. We add a sk_psock_strp_enabled() helper so TLS can learn a BPF verdict program is running and add a tls_sw_has_ctx_rx() helper so BPF side can learn there is a TLS ULP on the socket. Then on BPF side we omit calling our stream parser to avoid breaking the data stream for the KTLS receiver. Then on the KTLS side we call BPF_SK_SKB_STREAM_VERDICT once the KTLS receiver is done with the packet but before it posts the msg to userspace. This gives us symmetry between the TX and RX halfs and IMO makes it usable again. On the TX side we process packets in this order BPF -> TLS -> TCP and on the receive side in the reverse order TCP -> TLS -> BPF. Discovered while testing OpenSSL 3.0 Alpha2.0 release. Fixes: d829e9c4112b5 ("tls: convert to generic sk_msg interface") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/159079361946.5745.605854335665044485.stgit@john-Precision-5820-Tower Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-29 23:06:59 +00:00
{
switch (verdict) {
case __SK_REDIRECT:
skmsg: Pass source psock to sk_psock_skb_redirect() sk_psock_skb_redirect() only takes skb as a parameter, we will need to know where this skb is from, so just pass the source psock to this function as a new parameter. This patch prepares for the next one. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210615021342.7416-8-xiyou.wangcong@gmail.com
2021-06-15 02:13:41 +00:00
sk_psock_skb_redirect(from, skb);
bpf: Fix running sk_skb program types with ktls KTLS uses a stream parser to collect TLS messages and send them to the upper layer tls receive handler. This ensures the tls receiver has a full TLS header to parse when it is run. However, when a socket has BPF_SK_SKB_STREAM_VERDICT program attached before KTLS is enabled we end up with two stream parsers running on the same socket. The result is both try to run on the same socket. First the KTLS stream parser runs and calls read_sock() which will tcp_read_sock which in turn calls tcp_rcv_skb(). This dequeues the skb from the sk_receive_queue. When this is done KTLS code then data_ready() callback which because we stacked KTLS on top of the bpf stream verdict program has been replaced with sk_psock_start_strp(). This will in turn kick the stream parser again and eventually do the same thing KTLS did above calling into tcp_rcv_skb() and dequeuing a skb from the sk_receive_queue. At this point the data stream is broke. Part of the stream was handled by the KTLS side some other bytes may have been handled by the BPF side. Generally this results in either missing data or more likely a "Bad Message" complaint from the kTLS receive handler as the BPF program steals some bytes meant to be in a TLS header and/or the TLS header length is no longer correct. We've already broke the idealized model where we can stack ULPs in any order with generic callbacks on the TX side to handle this. So in this patch we do the same thing but for RX side. We add a sk_psock_strp_enabled() helper so TLS can learn a BPF verdict program is running and add a tls_sw_has_ctx_rx() helper so BPF side can learn there is a TLS ULP on the socket. Then on BPF side we omit calling our stream parser to avoid breaking the data stream for the KTLS receiver. Then on the KTLS side we call BPF_SK_SKB_STREAM_VERDICT once the KTLS receiver is done with the packet but before it posts the msg to userspace. This gives us symmetry between the TX and RX halfs and IMO makes it usable again. On the TX side we process packets in this order BPF -> TLS -> TCP and on the receive side in the reverse order TCP -> TLS -> BPF. Discovered while testing OpenSSL 3.0 Alpha2.0 release. Fixes: d829e9c4112b5 ("tls: convert to generic sk_msg interface") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/159079361946.5745.605854335665044485.stgit@john-Precision-5820-Tower Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-29 23:06:59 +00:00
break;
case __SK_PASS:
case __SK_DROP:
default:
break;
}
}
int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb)
{
struct bpf_prog *prog;
int ret = __SK_PASS;
rcu_read_lock();
sock_map: Rename skb_parser and skb_verdict These two eBPF programs are tied to BPF_SK_SKB_STREAM_PARSER and BPF_SK_SKB_STREAM_VERDICT, rename them to reflect the fact they are only used for TCP. And save the name 'skb_verdict' for general use later. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Reviewed-by: Lorenz Bauer <lmb@cloudflare.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-6-xiyou.wangcong@gmail.com
2021-02-23 18:49:30 +00:00
prog = READ_ONCE(psock->progs.stream_verdict);
bpf: Fix running sk_skb program types with ktls KTLS uses a stream parser to collect TLS messages and send them to the upper layer tls receive handler. This ensures the tls receiver has a full TLS header to parse when it is run. However, when a socket has BPF_SK_SKB_STREAM_VERDICT program attached before KTLS is enabled we end up with two stream parsers running on the same socket. The result is both try to run on the same socket. First the KTLS stream parser runs and calls read_sock() which will tcp_read_sock which in turn calls tcp_rcv_skb(). This dequeues the skb from the sk_receive_queue. When this is done KTLS code then data_ready() callback which because we stacked KTLS on top of the bpf stream verdict program has been replaced with sk_psock_start_strp(). This will in turn kick the stream parser again and eventually do the same thing KTLS did above calling into tcp_rcv_skb() and dequeuing a skb from the sk_receive_queue. At this point the data stream is broke. Part of the stream was handled by the KTLS side some other bytes may have been handled by the BPF side. Generally this results in either missing data or more likely a "Bad Message" complaint from the kTLS receive handler as the BPF program steals some bytes meant to be in a TLS header and/or the TLS header length is no longer correct. We've already broke the idealized model where we can stack ULPs in any order with generic callbacks on the TX side to handle this. So in this patch we do the same thing but for RX side. We add a sk_psock_strp_enabled() helper so TLS can learn a BPF verdict program is running and add a tls_sw_has_ctx_rx() helper so BPF side can learn there is a TLS ULP on the socket. Then on BPF side we omit calling our stream parser to avoid breaking the data stream for the KTLS receiver. Then on the KTLS side we call BPF_SK_SKB_STREAM_VERDICT once the KTLS receiver is done with the packet but before it posts the msg to userspace. This gives us symmetry between the TX and RX halfs and IMO makes it usable again. On the TX side we process packets in this order BPF -> TLS -> TCP and on the receive side in the reverse order TCP -> TLS -> BPF. Discovered while testing OpenSSL 3.0 Alpha2.0 release. Fixes: d829e9c4112b5 ("tls: convert to generic sk_msg interface") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/159079361946.5745.605854335665044485.stgit@john-Precision-5820-Tower Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-29 23:06:59 +00:00
if (likely(prog)) {
bpf, sockmap: Add memory accounting so skbs on ingress lists are visible Move skb->sk assignment out of sk_psock_bpf_run() and into individual callers. Then we can use proper skb_set_owner_r() call to assign a sk to a skb. This improves things by also charging the truesize against the sockets sk_rmem_alloc counter. With this done we get some accounting in place to ensure the memory associated with skbs on the workqueue are still being accounted for somewhere. Finally, by using skb_set_owner_r the destructor is setup so we can just let the normal skb_kfree logic recover the memory. Combined with previous patch dropping skb_orphan() we now can recover from memory pressure and maintain accounting. Note, we will charge the skbs against their originating socket even if being redirected into another socket. Once the skb completes the redirect op the kfree_skb will give the memory back. This is important because if we charged the socket we are redirecting to (like it was done before this series) the sock_writeable() test could fail because of the skb trying to be sent is already charged against the socket. Also TLS case is special. Here we wait until we have decided not to simply PASS the packet up the stack. In the case where we PASS the packet up the stack we already have an skb which is accounted for on the TLS socket context. For the parser case we continue to just set/clear skb->sk this is because the skb being used here may be combined with other skbs or turned into multiple skbs depending on the parser logic. For example the parser could request a payload length greater than skb->len so that the strparser needs to collect multiple skbs. At any rate the final result will be handled in the strparser recv callback. Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/160226867513.5692.10579573214635925960.stgit@john-Precision-5820-Tower
2020-10-09 18:37:55 +00:00
skb->sk = psock->sk;
skmsg: Move sk_redir from TCP_SKB_CB to skb Currently TCP_SKB_CB() is hard-coded in skmsg code, it certainly does not work for any other non-TCP protocols. We can move them to skb ext, but it introduces a memory allocation on fast path. Fortunately, we only need to a word-size to store all the information, because the flags actually only contains 1 bit so can be just packed into the lowest bit of the "pointer", which is stored as unsigned long. Inside struct sk_buff, '_skb_refdst' can be reused because skb dst is no longer needed after ->sk_data_ready() so we can just drop it. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-5-xiyou.wangcong@gmail.com
2021-02-23 18:49:29 +00:00
skb_dst_drop(skb);
skb_bpf_redirect_clear(skb);
skmsg: Get rid of sk_psock_bpf_run() It is now nearly identical to bpf_prog_run_pin_on_cpu() and it has an unused parameter 'psock', so we can just get rid of it and call bpf_prog_run_pin_on_cpu() directly. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-9-xiyou.wangcong@gmail.com
2021-02-23 18:49:33 +00:00
ret = bpf_prog_run_pin_on_cpu(prog, skb);
skmsg: Move sk_redir from TCP_SKB_CB to skb Currently TCP_SKB_CB() is hard-coded in skmsg code, it certainly does not work for any other non-TCP protocols. We can move them to skb ext, but it introduces a memory allocation on fast path. Fortunately, we only need to a word-size to store all the information, because the flags actually only contains 1 bit so can be just packed into the lowest bit of the "pointer", which is stored as unsigned long. Inside struct sk_buff, '_skb_refdst' can be reused because skb dst is no longer needed after ->sk_data_ready() so we can just drop it. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-5-xiyou.wangcong@gmail.com
2021-02-23 18:49:29 +00:00
ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb));
bpf, sockmap: Add memory accounting so skbs on ingress lists are visible Move skb->sk assignment out of sk_psock_bpf_run() and into individual callers. Then we can use proper skb_set_owner_r() call to assign a sk to a skb. This improves things by also charging the truesize against the sockets sk_rmem_alloc counter. With this done we get some accounting in place to ensure the memory associated with skbs on the workqueue are still being accounted for somewhere. Finally, by using skb_set_owner_r the destructor is setup so we can just let the normal skb_kfree logic recover the memory. Combined with previous patch dropping skb_orphan() we now can recover from memory pressure and maintain accounting. Note, we will charge the skbs against their originating socket even if being redirected into another socket. Once the skb completes the redirect op the kfree_skb will give the memory back. This is important because if we charged the socket we are redirecting to (like it was done before this series) the sock_writeable() test could fail because of the skb trying to be sent is already charged against the socket. Also TLS case is special. Here we wait until we have decided not to simply PASS the packet up the stack. In the case where we PASS the packet up the stack we already have an skb which is accounted for on the TLS socket context. For the parser case we continue to just set/clear skb->sk this is because the skb being used here may be combined with other skbs or turned into multiple skbs depending on the parser logic. For example the parser could request a payload length greater than skb->len so that the strparser needs to collect multiple skbs. At any rate the final result will be handled in the strparser recv callback. Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/160226867513.5692.10579573214635925960.stgit@john-Precision-5820-Tower
2020-10-09 18:37:55 +00:00
skb->sk = NULL;
bpf: Fix running sk_skb program types with ktls KTLS uses a stream parser to collect TLS messages and send them to the upper layer tls receive handler. This ensures the tls receiver has a full TLS header to parse when it is run. However, when a socket has BPF_SK_SKB_STREAM_VERDICT program attached before KTLS is enabled we end up with two stream parsers running on the same socket. The result is both try to run on the same socket. First the KTLS stream parser runs and calls read_sock() which will tcp_read_sock which in turn calls tcp_rcv_skb(). This dequeues the skb from the sk_receive_queue. When this is done KTLS code then data_ready() callback which because we stacked KTLS on top of the bpf stream verdict program has been replaced with sk_psock_start_strp(). This will in turn kick the stream parser again and eventually do the same thing KTLS did above calling into tcp_rcv_skb() and dequeuing a skb from the sk_receive_queue. At this point the data stream is broke. Part of the stream was handled by the KTLS side some other bytes may have been handled by the BPF side. Generally this results in either missing data or more likely a "Bad Message" complaint from the kTLS receive handler as the BPF program steals some bytes meant to be in a TLS header and/or the TLS header length is no longer correct. We've already broke the idealized model where we can stack ULPs in any order with generic callbacks on the TX side to handle this. So in this patch we do the same thing but for RX side. We add a sk_psock_strp_enabled() helper so TLS can learn a BPF verdict program is running and add a tls_sw_has_ctx_rx() helper so BPF side can learn there is a TLS ULP on the socket. Then on BPF side we omit calling our stream parser to avoid breaking the data stream for the KTLS receiver. Then on the KTLS side we call BPF_SK_SKB_STREAM_VERDICT once the KTLS receiver is done with the packet but before it posts the msg to userspace. This gives us symmetry between the TX and RX halfs and IMO makes it usable again. On the TX side we process packets in this order BPF -> TLS -> TCP and on the receive side in the reverse order TCP -> TLS -> BPF. Discovered while testing OpenSSL 3.0 Alpha2.0 release. Fixes: d829e9c4112b5 ("tls: convert to generic sk_msg interface") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/159079361946.5745.605854335665044485.stgit@john-Precision-5820-Tower Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-29 23:06:59 +00:00
}
skmsg: Pass source psock to sk_psock_skb_redirect() sk_psock_skb_redirect() only takes skb as a parameter, we will need to know where this skb is from, so just pass the source psock to this function as a new parameter. This patch prepares for the next one. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210615021342.7416-8-xiyou.wangcong@gmail.com
2021-06-15 02:13:41 +00:00
sk_psock_tls_verdict_apply(skb, psock, ret);
bpf: Fix running sk_skb program types with ktls KTLS uses a stream parser to collect TLS messages and send them to the upper layer tls receive handler. This ensures the tls receiver has a full TLS header to parse when it is run. However, when a socket has BPF_SK_SKB_STREAM_VERDICT program attached before KTLS is enabled we end up with two stream parsers running on the same socket. The result is both try to run on the same socket. First the KTLS stream parser runs and calls read_sock() which will tcp_read_sock which in turn calls tcp_rcv_skb(). This dequeues the skb from the sk_receive_queue. When this is done KTLS code then data_ready() callback which because we stacked KTLS on top of the bpf stream verdict program has been replaced with sk_psock_start_strp(). This will in turn kick the stream parser again and eventually do the same thing KTLS did above calling into tcp_rcv_skb() and dequeuing a skb from the sk_receive_queue. At this point the data stream is broke. Part of the stream was handled by the KTLS side some other bytes may have been handled by the BPF side. Generally this results in either missing data or more likely a "Bad Message" complaint from the kTLS receive handler as the BPF program steals some bytes meant to be in a TLS header and/or the TLS header length is no longer correct. We've already broke the idealized model where we can stack ULPs in any order with generic callbacks on the TX side to handle this. So in this patch we do the same thing but for RX side. We add a sk_psock_strp_enabled() helper so TLS can learn a BPF verdict program is running and add a tls_sw_has_ctx_rx() helper so BPF side can learn there is a TLS ULP on the socket. Then on BPF side we omit calling our stream parser to avoid breaking the data stream for the KTLS receiver. Then on the KTLS side we call BPF_SK_SKB_STREAM_VERDICT once the KTLS receiver is done with the packet but before it posts the msg to userspace. This gives us symmetry between the TX and RX halfs and IMO makes it usable again. On the TX side we process packets in this order BPF -> TLS -> TCP and on the receive side in the reverse order TCP -> TLS -> BPF. Discovered while testing OpenSSL 3.0 Alpha2.0 release. Fixes: d829e9c4112b5 ("tls: convert to generic sk_msg interface") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/159079361946.5745.605854335665044485.stgit@john-Precision-5820-Tower Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-29 23:06:59 +00:00
rcu_read_unlock();
return ret;
}
EXPORT_SYMBOL_GPL(sk_psock_tls_strp_read);
skmsg: Teach sk_psock_verdict_apply() to return errors Currently sk_psock_verdict_apply() is void, but it handles some error conditions too. Its caller is impossible to learn whether it succeeds or fails, especially sk_psock_verdict_recv(). Make it return int to indicate error cases and propagate errors to callers properly. Fixes: ef5659280eb1 ("bpf, sockmap: Allow skipping sk_skb parser program") Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210615021342.7416-7-xiyou.wangcong@gmail.com
2021-06-15 02:13:40 +00:00
static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb,
int verdict)
bpf: Refactor sockmap redirect code so its easy to reuse We will need this block of code called from tls context shortly lets refactor the redirect logic so its easy to use. This also cleans up the switch stmt so we have fewer fallthrough cases. No logic changes are intended. Fixes: d829e9c4112b5 ("tls: convert to generic sk_msg interface") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/159079360110.5745.7024009076049029819.stgit@john-Precision-5820-Tower Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-29 23:06:41 +00:00
{
struct sock *sk_other;
skmsg: Teach sk_psock_verdict_apply() to return errors Currently sk_psock_verdict_apply() is void, but it handles some error conditions too. Its caller is impossible to learn whether it succeeds or fails, especially sk_psock_verdict_recv(). Make it return int to indicate error cases and propagate errors to callers properly. Fixes: ef5659280eb1 ("bpf, sockmap: Allow skipping sk_skb parser program") Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210615021342.7416-7-xiyou.wangcong@gmail.com
2021-06-15 02:13:40 +00:00
int err = 0;
skmsg: Lose offset info in sk_psock_skb_ingress If sockmap enable strparser, there are lose offset info in sk_psock_skb_ingress(). If the length determined by parse_msg function is not skb->len, the skb will be converted to sk_msg multiple times, and userspace app will get the data multiple times. Fix this by get the offset and length from strp_msg. And as Cong suggested, add one bit in skb->_sk_redir to distinguish enable or disable strparser. Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Liu Jian <liujian56@huawei.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Cong Wang <cong.wang@bytedance.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20211029141216.211899-1-liujian56@huawei.com
2021-10-29 14:12:14 +00:00
u32 len, off;
bpf: Refactor sockmap redirect code so its easy to reuse We will need this block of code called from tls context shortly lets refactor the redirect logic so its easy to use. This also cleans up the switch stmt so we have fewer fallthrough cases. No logic changes are intended. Fixes: d829e9c4112b5 ("tls: convert to generic sk_msg interface") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/159079360110.5745.7024009076049029819.stgit@john-Precision-5820-Tower Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-29 23:06:41 +00:00
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 00:45:58 +00:00
switch (verdict) {
bpf: skb_verdict, support SK_PASS on RX BPF path Add SK_PASS verdict support to SK_SKB_VERDICT programs. Now that support for redirects exists we can implement SK_PASS as a redirect to the same socket. This simplifies the BPF programs and avoids an extra map lookup on RX path for simple visibility cases. Further, reduces user (BPF programmer in this context) confusion when their program drops skb due to lack of support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-12-20 19:35:32 +00:00
case __SK_PASS:
skmsg: Teach sk_psock_verdict_apply() to return errors Currently sk_psock_verdict_apply() is void, but it handles some error conditions too. Its caller is impossible to learn whether it succeeds or fails, especially sk_psock_verdict_recv(). Make it return int to indicate error cases and propagate errors to callers properly. Fixes: ef5659280eb1 ("bpf, sockmap: Allow skipping sk_skb parser program") Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210615021342.7416-7-xiyou.wangcong@gmail.com
2021-06-15 02:13:40 +00:00
err = -EIO;
bpf: skb_verdict, support SK_PASS on RX BPF path Add SK_PASS verdict support to SK_SKB_VERDICT programs. Now that support for redirects exists we can implement SK_PASS as a redirect to the same socket. This simplifies the BPF programs and avoids an extra map lookup on RX path for simple visibility cases. Further, reduces user (BPF programmer in this context) confusion when their program drops skb due to lack of support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-12-20 19:35:32 +00:00
sk_other = psock->sk;
if (sock_flag(sk_other, SOCK_DEAD) ||
bpf, sockmap: Incorrectly handling copied_seq The read_skb() logic is incrementing the tcp->copied_seq which is used for among other things calculating how many outstanding bytes can be read by the application. This results in application errors, if the application does an ioctl(FIONREAD) we return zero because this is calculated from the copied_seq value. To fix this we move tcp->copied_seq accounting into the recv handler so that we update these when the recvmsg() hook is called and data is in fact copied into user buffers. This gives an accurate FIONREAD value as expected and improves ACK handling. Before we were calling the tcp_rcv_space_adjust() which would update 'number of bytes copied to user in last RTT' which is wrong for programs returning SK_PASS. The bytes are only copied to the user when recvmsg is handled. Doing the fix for recvmsg is straightforward, but fixing redirect and SK_DROP pkts is a bit tricker. Build a tcp_psock_eat() helper and then call this from skmsg handlers. This fixes another issue where a broken socket with a BPF program doing a resubmit could hang the receiver. This happened because although read_skb() consumed the skb through sock_drop() it did not update the copied_seq. Now if a single reccv socket is redirecting to many sockets (for example for lb) the receiver sk will be hung even though we might expect it to continue. The hang comes from not updating the copied_seq numbers and memory pressure resulting from that. We have a slight layer problem of calling tcp_eat_skb even if its not a TCP socket. To fix we could refactor and create per type receiver handlers. I decided this is more work than we want in the fix and we already have some small tweaks depending on caller that use the helper skb_bpf_strparser(). So we extend that a bit and always set the strparser bit when it is in use and then we can gate the seq_copied updates on this. Fixes: 04919bed948dc ("tcp: Introduce tcp_read_skb()") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20230523025618.113937-9-john.fastabend@gmail.com
2023-05-23 02:56:12 +00:00
!sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED))
bpf: skb_verdict, support SK_PASS on RX BPF path Add SK_PASS verdict support to SK_SKB_VERDICT programs. Now that support for redirects exists we can implement SK_PASS as a redirect to the same socket. This simplifies the BPF programs and avoids an extra map lookup on RX path for simple visibility cases. Further, reduces user (BPF programmer in this context) confusion when their program drops skb due to lack of support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-12-20 19:35:32 +00:00
goto out_free;
skmsg: Move sk_redir from TCP_SKB_CB to skb Currently TCP_SKB_CB() is hard-coded in skmsg code, it certainly does not work for any other non-TCP protocols. We can move them to skb ext, but it introduces a memory allocation on fast path. Fortunately, we only need to a word-size to store all the information, because the flags actually only contains 1 bit so can be just packed into the lowest bit of the "pointer", which is stored as unsigned long. Inside struct sk_buff, '_skb_refdst' can be reused because skb dst is no longer needed after ->sk_data_ready() so we can just drop it. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-5-xiyou.wangcong@gmail.com
2021-02-23 18:49:29 +00:00
skb_bpf_set_ingress(skb);
bpf, sockmap: On receive programs try to fast track SK_PASS ingress When we receive an skb and the ingress skb verdict program returns SK_PASS we currently set the ingress flag and put it on the workqueue so it can be turned into a sk_msg and put on the sk_msg ingress queue. Then finally telling userspace with data_ready hook. Here we observe that if the workqueue is empty then we can try to convert into a sk_msg type and call data_ready directly without bouncing through a workqueue. Its a common pattern to have a recv verdict program for visibility that always returns SK_PASS. In this case unless there is an ENOMEM error or we overrun the socket we can avoid the workqueue completely only using it when we fall back to error cases caused by memory pressure. By doing this we eliminate another case where data may be dropped if errors occur on memory limits in workqueue. Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/160226859704.5692.12929678876744977669.stgit@john-Precision-5820-Tower
2020-10-09 18:36:37 +00:00
/* If the queue is empty then we can submit directly
* into the msg queue. If its not empty we have to
* queue work otherwise we may get OOO data. Otherwise,
* if sk_psock_skb_ingress errors will be handled by
* retrying later from workqueue.
*/
if (skb_queue_empty(&psock->ingress_skb)) {
skmsg: Lose offset info in sk_psock_skb_ingress If sockmap enable strparser, there are lose offset info in sk_psock_skb_ingress(). If the length determined by parse_msg function is not skb->len, the skb will be converted to sk_msg multiple times, and userspace app will get the data multiple times. Fix this by get the offset and length from strp_msg. And as Cong suggested, add one bit in skb->_sk_redir to distinguish enable or disable strparser. Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Liu Jian <liujian56@huawei.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Cong Wang <cong.wang@bytedance.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20211029141216.211899-1-liujian56@huawei.com
2021-10-29 14:12:14 +00:00
len = skb->len;
off = 0;
if (skb_bpf_strparser(skb)) {
struct strp_msg *stm = strp_msg(skb);
off = stm->offset;
len = stm->full_len;
}
err = sk_psock_skb_ingress_self(psock, skb, off, len);
bpf, sockmap: On receive programs try to fast track SK_PASS ingress When we receive an skb and the ingress skb verdict program returns SK_PASS we currently set the ingress flag and put it on the workqueue so it can be turned into a sk_msg and put on the sk_msg ingress queue. Then finally telling userspace with data_ready hook. Here we observe that if the workqueue is empty then we can try to convert into a sk_msg type and call data_ready directly without bouncing through a workqueue. Its a common pattern to have a recv verdict program for visibility that always returns SK_PASS. In this case unless there is an ENOMEM error or we overrun the socket we can avoid the workqueue completely only using it when we fall back to error cases caused by memory pressure. By doing this we eliminate another case where data may be dropped if errors occur on memory limits in workqueue. Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/160226859704.5692.12929678876744977669.stgit@john-Precision-5820-Tower
2020-10-09 18:36:37 +00:00
}
if (err < 0) {
skmsg: Avoid lock_sock() in sk_psock_backlog() We do not have to lock the sock to avoid losing sk_socket, instead we can purge all the ingress queues when we close the socket. Sending or receiving packets after orphaning socket makes no sense. We do purge these queues when psock refcnt reaches zero but here we want to purge them explicitly in sock_map_close(). There are also some nasty race conditions on testing bit SK_PSOCK_TX_ENABLED and queuing/canceling the psock work, we can expand psock->ingress_lock a bit to protect them too. As noticed by John, we still have to lock the psock->work, because the same work item could be running concurrently on different CPU's. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210331023237.41094-5-xiyou.wangcong@gmail.com
2021-03-31 02:32:25 +00:00
spin_lock_bh(&psock->ingress_lock);
if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) {
skb_queue_tail(&psock->ingress_skb, skb);
bpf, sockmap: Convert schedule_work into delayed_work 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
2023-05-23 02:56:06 +00:00
schedule_delayed_work(&psock->work, 0);
skmsg: Fix a memory leak in sk_psock_verdict_apply() If the dest psock does not set SK_PSOCK_TX_ENABLED, the skb can't be queued anywhere so must be dropped. This one is found during code review. Fixes: 799aa7f98d53 ("skmsg: Avoid lock_sock() in sk_psock_backlog()") Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210615021342.7416-6-xiyou.wangcong@gmail.com
2021-06-15 02:13:39 +00:00
err = 0;
skmsg: Avoid lock_sock() in sk_psock_backlog() We do not have to lock the sock to avoid losing sk_socket, instead we can purge all the ingress queues when we close the socket. Sending or receiving packets after orphaning socket makes no sense. We do purge these queues when psock refcnt reaches zero but here we want to purge them explicitly in sock_map_close(). There are also some nasty race conditions on testing bit SK_PSOCK_TX_ENABLED and queuing/canceling the psock work, we can expand psock->ingress_lock a bit to protect them too. As noticed by John, we still have to lock the psock->work, because the same work item could be running concurrently on different CPU's. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210331023237.41094-5-xiyou.wangcong@gmail.com
2021-03-31 02:32:25 +00:00
}
spin_unlock_bh(&psock->ingress_lock);
bpf, sockmap: Incorrectly handling copied_seq The read_skb() logic is incrementing the tcp->copied_seq which is used for among other things calculating how many outstanding bytes can be read by the application. This results in application errors, if the application does an ioctl(FIONREAD) we return zero because this is calculated from the copied_seq value. To fix this we move tcp->copied_seq accounting into the recv handler so that we update these when the recvmsg() hook is called and data is in fact copied into user buffers. This gives an accurate FIONREAD value as expected and improves ACK handling. Before we were calling the tcp_rcv_space_adjust() which would update 'number of bytes copied to user in last RTT' which is wrong for programs returning SK_PASS. The bytes are only copied to the user when recvmsg is handled. Doing the fix for recvmsg is straightforward, but fixing redirect and SK_DROP pkts is a bit tricker. Build a tcp_psock_eat() helper and then call this from skmsg handlers. This fixes another issue where a broken socket with a BPF program doing a resubmit could hang the receiver. This happened because although read_skb() consumed the skb through sock_drop() it did not update the copied_seq. Now if a single reccv socket is redirecting to many sockets (for example for lb) the receiver sk will be hung even though we might expect it to continue. The hang comes from not updating the copied_seq numbers and memory pressure resulting from that. We have a slight layer problem of calling tcp_eat_skb even if its not a TCP socket. To fix we could refactor and create per type receiver handlers. I decided this is more work than we want in the fix and we already have some small tweaks depending on caller that use the helper skb_bpf_strparser(). So we extend that a bit and always set the strparser bit when it is in use and then we can gate the seq_copied updates on this. Fixes: 04919bed948dc ("tcp: Introduce tcp_read_skb()") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20230523025618.113937-9-john.fastabend@gmail.com
2023-05-23 02:56:12 +00:00
if (err < 0)
skmsg: Fix a memory leak in sk_psock_verdict_apply() If the dest psock does not set SK_PSOCK_TX_ENABLED, the skb can't be queued anywhere so must be dropped. This one is found during code review. Fixes: 799aa7f98d53 ("skmsg: Avoid lock_sock() in sk_psock_backlog()") Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210615021342.7416-6-xiyou.wangcong@gmail.com
2021-06-15 02:13:39 +00:00
goto out_free;
bpf, sockmap: On receive programs try to fast track SK_PASS ingress When we receive an skb and the ingress skb verdict program returns SK_PASS we currently set the ingress flag and put it on the workqueue so it can be turned into a sk_msg and put on the sk_msg ingress queue. Then finally telling userspace with data_ready hook. Here we observe that if the workqueue is empty then we can try to convert into a sk_msg type and call data_ready directly without bouncing through a workqueue. Its a common pattern to have a recv verdict program for visibility that always returns SK_PASS. In this case unless there is an ENOMEM error or we overrun the socket we can avoid the workqueue completely only using it when we fall back to error cases caused by memory pressure. By doing this we eliminate another case where data may be dropped if errors occur on memory limits in workqueue. Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/160226859704.5692.12929678876744977669.stgit@john-Precision-5820-Tower
2020-10-09 18:36:37 +00:00
}
bpf, sockmap: Skb verdict SK_PASS to self already checked rmem limits For sk_skb case where skb_verdict program returns SK_PASS to continue to pass packet up the stack, the memory limits were already checked before enqueuing in skb_queue_tail from TCP side. So, lets remove the extra checks here. The theory is if the TCP stack believes we have memory to receive the packet then lets trust the stack and not double check the limits. In fact the accounting here can cause a drop if sk_rmem_alloc has increased after the stack accepted this packet, but before the duplicate check here. And worse if this happens because TCP stack already believes the data has been received there is no retransmit. Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/160226857664.5692.668205469388498375.stgit@john-Precision-5820-Tower
2020-10-09 18:36:16 +00:00
break;
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 00:45:58 +00:00
case __SK_REDIRECT:
bpf, sockmap: Incorrectly handling copied_seq The read_skb() logic is incrementing the tcp->copied_seq which is used for among other things calculating how many outstanding bytes can be read by the application. This results in application errors, if the application does an ioctl(FIONREAD) we return zero because this is calculated from the copied_seq value. To fix this we move tcp->copied_seq accounting into the recv handler so that we update these when the recvmsg() hook is called and data is in fact copied into user buffers. This gives an accurate FIONREAD value as expected and improves ACK handling. Before we were calling the tcp_rcv_space_adjust() which would update 'number of bytes copied to user in last RTT' which is wrong for programs returning SK_PASS. The bytes are only copied to the user when recvmsg is handled. Doing the fix for recvmsg is straightforward, but fixing redirect and SK_DROP pkts is a bit tricker. Build a tcp_psock_eat() helper and then call this from skmsg handlers. This fixes another issue where a broken socket with a BPF program doing a resubmit could hang the receiver. This happened because although read_skb() consumed the skb through sock_drop() it did not update the copied_seq. Now if a single reccv socket is redirecting to many sockets (for example for lb) the receiver sk will be hung even though we might expect it to continue. The hang comes from not updating the copied_seq numbers and memory pressure resulting from that. We have a slight layer problem of calling tcp_eat_skb even if its not a TCP socket. To fix we could refactor and create per type receiver handlers. I decided this is more work than we want in the fix and we already have some small tweaks depending on caller that use the helper skb_bpf_strparser(). So we extend that a bit and always set the strparser bit when it is in use and then we can gate the seq_copied updates on this. Fixes: 04919bed948dc ("tcp: Introduce tcp_read_skb()") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20230523025618.113937-9-john.fastabend@gmail.com
2023-05-23 02:56:12 +00:00
tcp_eat_skb(psock->sk, skb);
skmsg: Pass source psock to sk_psock_skb_redirect() sk_psock_skb_redirect() only takes skb as a parameter, we will need to know where this skb is from, so just pass the source psock to this function as a new parameter. This patch prepares for the next one. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210615021342.7416-8-xiyou.wangcong@gmail.com
2021-06-15 02:13:41 +00:00
err = sk_psock_skb_redirect(psock, skb);
bpf: Refactor sockmap redirect code so its easy to reuse We will need this block of code called from tls context shortly lets refactor the redirect logic so its easy to use. This also cleans up the switch stmt so we have fewer fallthrough cases. No logic changes are intended. Fixes: d829e9c4112b5 ("tls: convert to generic sk_msg interface") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/159079360110.5745.7024009076049029819.stgit@john-Precision-5820-Tower Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-29 23:06:41 +00:00
break;
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 00:45:58 +00:00
case __SK_DROP:
default:
out_free:
bpf, sockmap: Incorrectly handling copied_seq The read_skb() logic is incrementing the tcp->copied_seq which is used for among other things calculating how many outstanding bytes can be read by the application. This results in application errors, if the application does an ioctl(FIONREAD) we return zero because this is calculated from the copied_seq value. To fix this we move tcp->copied_seq accounting into the recv handler so that we update these when the recvmsg() hook is called and data is in fact copied into user buffers. This gives an accurate FIONREAD value as expected and improves ACK handling. Before we were calling the tcp_rcv_space_adjust() which would update 'number of bytes copied to user in last RTT' which is wrong for programs returning SK_PASS. The bytes are only copied to the user when recvmsg is handled. Doing the fix for recvmsg is straightforward, but fixing redirect and SK_DROP pkts is a bit tricker. Build a tcp_psock_eat() helper and then call this from skmsg handlers. This fixes another issue where a broken socket with a BPF program doing a resubmit could hang the receiver. This happened because although read_skb() consumed the skb through sock_drop() it did not update the copied_seq. Now if a single reccv socket is redirecting to many sockets (for example for lb) the receiver sk will be hung even though we might expect it to continue. The hang comes from not updating the copied_seq numbers and memory pressure resulting from that. We have a slight layer problem of calling tcp_eat_skb even if its not a TCP socket. To fix we could refactor and create per type receiver handlers. I decided this is more work than we want in the fix and we already have some small tweaks depending on caller that use the helper skb_bpf_strparser(). So we extend that a bit and always set the strparser bit when it is in use and then we can gate the seq_copied updates on this. Fixes: 04919bed948dc ("tcp: Introduce tcp_read_skb()") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20230523025618.113937-9-john.fastabend@gmail.com
2023-05-23 02:56:12 +00:00
skb_bpf_redirect_clear(skb);
tcp_eat_skb(psock->sk, skb);
skmsg: Increase sk->sk_drops when dropping packets It is hard to observe packet drops without increasing relevant drop counters, here we should increase sk->sk_drops which is a protocol-independent counter. Fortunately psock is always associated with a struct sock, we can just use psock->sk. Suggested-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210615021342.7416-9-xiyou.wangcong@gmail.com
2021-06-15 02:13:42 +00:00
sock_drop(psock->sk, 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 00:45:58 +00:00
}
skmsg: Teach sk_psock_verdict_apply() to return errors Currently sk_psock_verdict_apply() is void, but it handles some error conditions too. Its caller is impossible to learn whether it succeeds or fails, especially sk_psock_verdict_recv(). Make it return int to indicate error cases and propagate errors to callers properly. Fixes: ef5659280eb1 ("bpf, sockmap: Allow skipping sk_skb parser program") Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210615021342.7416-7-xiyou.wangcong@gmail.com
2021-06-15 02:13:40 +00:00
return err;
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 00:45:58 +00:00
}
bpf: Clean up sockmap related Kconfigs As suggested by John, clean up sockmap related Kconfigs: Reduce the scope of CONFIG_BPF_STREAM_PARSER down to TCP stream parser, to reflect its name. Make the rest sockmap code simply depend on CONFIG_BPF_SYSCALL and CONFIG_INET, the latter is still needed at this point because of TCP/UDP proto update. And leave CONFIG_NET_SOCK_MSG untouched, as it is used by non-sockmap cases. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Reviewed-by: Lorenz Bauer <lmb@cloudflare.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-2-xiyou.wangcong@gmail.com
2021-02-23 18:49:26 +00:00
static void sk_psock_write_space(struct sock *sk)
{
struct sk_psock *psock;
void (*write_space)(struct sock *sk) = NULL;
rcu_read_lock();
psock = sk_psock(sk);
if (likely(psock)) {
if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED))
bpf, sockmap: Convert schedule_work into delayed_work 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
2023-05-23 02:56:06 +00:00
schedule_delayed_work(&psock->work, 0);
bpf: Clean up sockmap related Kconfigs As suggested by John, clean up sockmap related Kconfigs: Reduce the scope of CONFIG_BPF_STREAM_PARSER down to TCP stream parser, to reflect its name. Make the rest sockmap code simply depend on CONFIG_BPF_SYSCALL and CONFIG_INET, the latter is still needed at this point because of TCP/UDP proto update. And leave CONFIG_NET_SOCK_MSG untouched, as it is used by non-sockmap cases. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Reviewed-by: Lorenz Bauer <lmb@cloudflare.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-2-xiyou.wangcong@gmail.com
2021-02-23 18:49:26 +00:00
write_space = psock->saved_write_space;
}
rcu_read_unlock();
if (write_space)
write_space(sk);
}
#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 00:45:58 +00:00
static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb)
{
bpf, sockmap: RCU dereferenced psock may be used outside RCU block If an ingress verdict program specifies message sizes greater than skb->len and there is an ENOMEM error due to memory pressure we may call the rcv_msg handler outside the strp_data_ready() caller context. This is because on an ENOMEM error the strparser will retry from a workqueue. The caller currently protects the use of psock by calling the strp_data_ready() inside a rcu_read_lock/unlock block. But, in above workqueue error case the psock is accessed outside the read_lock/unlock block of the caller. So instead of using psock directly we must do a look up against the sk again to ensure the psock is available. There is an an ugly piece here where we must handle the case where we paused the strp and removed the psock. On psock removal we first pause the strparser and then remove the psock. If the strparser is paused while an skb is scheduled on the workqueue the skb will be dropped on the flow and kfree_skb() is called. If the workqueue manages to get called before we pause the strparser but runs the rcvmsg callback after the psock is removed we will hit the unlikely case where we run the sockmap rcvmsg handler but do not have a psock. For now we will follow strparser logic and drop the skb on the floor with skb_kfree(). This is ugly because the data is dropped. To date this has not caused problems in practice because either the application controlling the sockmap is coordinating with the datapath so that skbs are "flushed" before removal or we simply wait for the sock to be closed before removing it. This patch fixes the describe RCU bug and dropping the skb doesn't make things worse. Future patches will improve this by allowing the normal case where skbs are not merged to skip the strparser altogether. In practice many (most?) use cases have no need to merge skbs so its both a code complexity hit as seen above and a performance issue. For example, in the Cilium case we always set the strparser up to return sbks 1:1 without any merging and have avoided above issues. Fixes: e91de6afa81c1 ("bpf: Fix running sk_skb program types with ktls") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Martin KaFai Lau <kafai@fb.com> Link: https://lore.kernel.org/bpf/159312679888.18340.15248924071966273998.stgit@john-XPS-13-9370
2020-06-25 23:13:18 +00:00
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 00:45:58 +00:00
struct bpf_prog *prog;
int ret = __SK_DROP;
bpf, sockmap: RCU dereferenced psock may be used outside RCU block If an ingress verdict program specifies message sizes greater than skb->len and there is an ENOMEM error due to memory pressure we may call the rcv_msg handler outside the strp_data_ready() caller context. This is because on an ENOMEM error the strparser will retry from a workqueue. The caller currently protects the use of psock by calling the strp_data_ready() inside a rcu_read_lock/unlock block. But, in above workqueue error case the psock is accessed outside the read_lock/unlock block of the caller. So instead of using psock directly we must do a look up against the sk again to ensure the psock is available. There is an an ugly piece here where we must handle the case where we paused the strp and removed the psock. On psock removal we first pause the strparser and then remove the psock. If the strparser is paused while an skb is scheduled on the workqueue the skb will be dropped on the flow and kfree_skb() is called. If the workqueue manages to get called before we pause the strparser but runs the rcvmsg callback after the psock is removed we will hit the unlikely case where we run the sockmap rcvmsg handler but do not have a psock. For now we will follow strparser logic and drop the skb on the floor with skb_kfree(). This is ugly because the data is dropped. To date this has not caused problems in practice because either the application controlling the sockmap is coordinating with the datapath so that skbs are "flushed" before removal or we simply wait for the sock to be closed before removing it. This patch fixes the describe RCU bug and dropping the skb doesn't make things worse. Future patches will improve this by allowing the normal case where skbs are not merged to skip the strparser altogether. In practice many (most?) use cases have no need to merge skbs so its both a code complexity hit as seen above and a performance issue. For example, in the Cilium case we always set the strparser up to return sbks 1:1 without any merging and have avoided above issues. Fixes: e91de6afa81c1 ("bpf: Fix running sk_skb program types with ktls") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Martin KaFai Lau <kafai@fb.com> Link: https://lore.kernel.org/bpf/159312679888.18340.15248924071966273998.stgit@john-XPS-13-9370
2020-06-25 23:13:18 +00:00
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 00:45:58 +00:00
rcu_read_lock();
bpf, sockmap: RCU dereferenced psock may be used outside RCU block If an ingress verdict program specifies message sizes greater than skb->len and there is an ENOMEM error due to memory pressure we may call the rcv_msg handler outside the strp_data_ready() caller context. This is because on an ENOMEM error the strparser will retry from a workqueue. The caller currently protects the use of psock by calling the strp_data_ready() inside a rcu_read_lock/unlock block. But, in above workqueue error case the psock is accessed outside the read_lock/unlock block of the caller. So instead of using psock directly we must do a look up against the sk again to ensure the psock is available. There is an an ugly piece here where we must handle the case where we paused the strp and removed the psock. On psock removal we first pause the strparser and then remove the psock. If the strparser is paused while an skb is scheduled on the workqueue the skb will be dropped on the flow and kfree_skb() is called. If the workqueue manages to get called before we pause the strparser but runs the rcvmsg callback after the psock is removed we will hit the unlikely case where we run the sockmap rcvmsg handler but do not have a psock. For now we will follow strparser logic and drop the skb on the floor with skb_kfree(). This is ugly because the data is dropped. To date this has not caused problems in practice because either the application controlling the sockmap is coordinating with the datapath so that skbs are "flushed" before removal or we simply wait for the sock to be closed before removing it. This patch fixes the describe RCU bug and dropping the skb doesn't make things worse. Future patches will improve this by allowing the normal case where skbs are not merged to skip the strparser altogether. In practice many (most?) use cases have no need to merge skbs so its both a code complexity hit as seen above and a performance issue. For example, in the Cilium case we always set the strparser up to return sbks 1:1 without any merging and have avoided above issues. Fixes: e91de6afa81c1 ("bpf: Fix running sk_skb program types with ktls") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Martin KaFai Lau <kafai@fb.com> Link: https://lore.kernel.org/bpf/159312679888.18340.15248924071966273998.stgit@john-XPS-13-9370
2020-06-25 23:13:18 +00:00
sk = strp->sk;
psock = sk_psock(sk);
if (unlikely(!psock)) {
skmsg: Increase sk->sk_drops when dropping packets It is hard to observe packet drops without increasing relevant drop counters, here we should increase sk->sk_drops which is a protocol-independent counter. Fortunately psock is always associated with a struct sock, we can just use psock->sk. Suggested-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210615021342.7416-9-xiyou.wangcong@gmail.com
2021-06-15 02:13:42 +00:00
sock_drop(sk, skb);
bpf, sockmap: RCU dereferenced psock may be used outside RCU block If an ingress verdict program specifies message sizes greater than skb->len and there is an ENOMEM error due to memory pressure we may call the rcv_msg handler outside the strp_data_ready() caller context. This is because on an ENOMEM error the strparser will retry from a workqueue. The caller currently protects the use of psock by calling the strp_data_ready() inside a rcu_read_lock/unlock block. But, in above workqueue error case the psock is accessed outside the read_lock/unlock block of the caller. So instead of using psock directly we must do a look up against the sk again to ensure the psock is available. There is an an ugly piece here where we must handle the case where we paused the strp and removed the psock. On psock removal we first pause the strparser and then remove the psock. If the strparser is paused while an skb is scheduled on the workqueue the skb will be dropped on the flow and kfree_skb() is called. If the workqueue manages to get called before we pause the strparser but runs the rcvmsg callback after the psock is removed we will hit the unlikely case where we run the sockmap rcvmsg handler but do not have a psock. For now we will follow strparser logic and drop the skb on the floor with skb_kfree(). This is ugly because the data is dropped. To date this has not caused problems in practice because either the application controlling the sockmap is coordinating with the datapath so that skbs are "flushed" before removal or we simply wait for the sock to be closed before removing it. This patch fixes the describe RCU bug and dropping the skb doesn't make things worse. Future patches will improve this by allowing the normal case where skbs are not merged to skip the strparser altogether. In practice many (most?) use cases have no need to merge skbs so its both a code complexity hit as seen above and a performance issue. For example, in the Cilium case we always set the strparser up to return sbks 1:1 without any merging and have avoided above issues. Fixes: e91de6afa81c1 ("bpf: Fix running sk_skb program types with ktls") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Martin KaFai Lau <kafai@fb.com> Link: https://lore.kernel.org/bpf/159312679888.18340.15248924071966273998.stgit@john-XPS-13-9370
2020-06-25 23:13:18 +00:00
goto out;
}
sock_map: Rename skb_parser and skb_verdict These two eBPF programs are tied to BPF_SK_SKB_STREAM_PARSER and BPF_SK_SKB_STREAM_VERDICT, rename them to reflect the fact they are only used for TCP. And save the name 'skb_verdict' for general use later. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Reviewed-by: Lorenz Bauer <lmb@cloudflare.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-6-xiyou.wangcong@gmail.com
2021-02-23 18:49:30 +00:00
prog = READ_ONCE(psock->progs.stream_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 00:45:58 +00:00
if (likely(prog)) {
bpf, sockmap: Fix incorrect fwd_alloc accounting Incorrect accounting fwd_alloc can result in a warning when the socket is torn down, [18455.319240] WARNING: CPU: 0 PID: 24075 at net/core/stream.c:208 sk_stream_kill_queues+0x21f/0x230 [...] [18455.319543] Call Trace: [18455.319556] inet_csk_destroy_sock+0xba/0x1f0 [18455.319577] tcp_rcv_state_process+0x1b4e/0x2380 [18455.319593] ? lock_downgrade+0x3a0/0x3a0 [18455.319617] ? tcp_finish_connect+0x1e0/0x1e0 [18455.319631] ? sk_reset_timer+0x15/0x70 [18455.319646] ? tcp_schedule_loss_probe+0x1b2/0x240 [18455.319663] ? lock_release+0xb2/0x3f0 [18455.319676] ? __release_sock+0x8a/0x1b0 [18455.319690] ? lock_downgrade+0x3a0/0x3a0 [18455.319704] ? lock_release+0x3f0/0x3f0 [18455.319717] ? __tcp_close+0x2c6/0x790 [18455.319736] ? tcp_v4_do_rcv+0x168/0x370 [18455.319750] tcp_v4_do_rcv+0x168/0x370 [18455.319767] __release_sock+0xbc/0x1b0 [18455.319785] __tcp_close+0x2ee/0x790 [18455.319805] tcp_close+0x20/0x80 This currently happens because on redirect case we do skb_set_owner_r() with the original sock. This increments the fwd_alloc memory accounting on the original sock. Then on redirect we may push this into the queue of the psock we are redirecting to. When the skb is flushed from the queue we give the memory back to the original sock. The problem is if the original sock is destroyed/closed with skbs on another psocks queue then the original sock will not have a way to reclaim the memory before being destroyed. Then above warning will be thrown sockA sockB sk_psock_strp_read() sk_psock_verdict_apply() -- SK_REDIRECT -- sk_psock_skb_redirect() skb_queue_tail(psock_other->ingress_skb..) sk_close() sock_map_unref() sk_psock_put() sk_psock_drop() sk_psock_zap_ingress() At this point we have torn down our own psock, but have the outstanding skb in psock_other. Note that SK_PASS doesn't have this problem because the sk_psock_drop() logic releases the skb, its still associated with our psock. To resolve lets only account for sockets on the ingress queue that are still associated with the current socket. On the redirect case we will check memory limits per 6fa9201a89898, but will omit fwd_alloc accounting until skb is actually enqueued. When the skb is sent via skb_send_sock_locked or received with sk_psock_skb_ingress memory will be claimed on psock_other. Fixes: 6fa9201a89898 ("bpf, sockmap: Avoid returning unneeded EAGAIN when redirecting to self") Reported-by: Andrii Nakryiko <andrii@kernel.org> Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/161731444013.68884.4021114312848535993.stgit@john-XPS-13-9370
2021-04-01 22:00:40 +00:00
skb->sk = sk;
skmsg: Move sk_redir from TCP_SKB_CB to skb Currently TCP_SKB_CB() is hard-coded in skmsg code, it certainly does not work for any other non-TCP protocols. We can move them to skb ext, but it introduces a memory allocation on fast path. Fortunately, we only need to a word-size to store all the information, because the flags actually only contains 1 bit so can be just packed into the lowest bit of the "pointer", which is stored as unsigned long. Inside struct sk_buff, '_skb_refdst' can be reused because skb dst is no longer needed after ->sk_data_ready() so we can just drop it. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-5-xiyou.wangcong@gmail.com
2021-02-23 18:49:29 +00:00
skb_dst_drop(skb);
skb_bpf_redirect_clear(skb);
skmsg: Get rid of sk_psock_bpf_run() It is now nearly identical to bpf_prog_run_pin_on_cpu() and it has an unused parameter 'psock', so we can just get rid of it and call bpf_prog_run_pin_on_cpu() directly. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-9-xiyou.wangcong@gmail.com
2021-02-23 18:49:33 +00:00
ret = bpf_prog_run_pin_on_cpu(prog, skb);
bpf, sockmap: Incorrectly handling copied_seq The read_skb() logic is incrementing the tcp->copied_seq which is used for among other things calculating how many outstanding bytes can be read by the application. This results in application errors, if the application does an ioctl(FIONREAD) we return zero because this is calculated from the copied_seq value. To fix this we move tcp->copied_seq accounting into the recv handler so that we update these when the recvmsg() hook is called and data is in fact copied into user buffers. This gives an accurate FIONREAD value as expected and improves ACK handling. Before we were calling the tcp_rcv_space_adjust() which would update 'number of bytes copied to user in last RTT' which is wrong for programs returning SK_PASS. The bytes are only copied to the user when recvmsg is handled. Doing the fix for recvmsg is straightforward, but fixing redirect and SK_DROP pkts is a bit tricker. Build a tcp_psock_eat() helper and then call this from skmsg handlers. This fixes another issue where a broken socket with a BPF program doing a resubmit could hang the receiver. This happened because although read_skb() consumed the skb through sock_drop() it did not update the copied_seq. Now if a single reccv socket is redirecting to many sockets (for example for lb) the receiver sk will be hung even though we might expect it to continue. The hang comes from not updating the copied_seq numbers and memory pressure resulting from that. We have a slight layer problem of calling tcp_eat_skb even if its not a TCP socket. To fix we could refactor and create per type receiver handlers. I decided this is more work than we want in the fix and we already have some small tweaks depending on caller that use the helper skb_bpf_strparser(). So we extend that a bit and always set the strparser bit when it is in use and then we can gate the seq_copied updates on this. Fixes: 04919bed948dc ("tcp: Introduce tcp_read_skb()") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20230523025618.113937-9-john.fastabend@gmail.com
2023-05-23 02:56:12 +00:00
skb_bpf_set_strparser(skb);
skmsg: Move sk_redir from TCP_SKB_CB to skb Currently TCP_SKB_CB() is hard-coded in skmsg code, it certainly does not work for any other non-TCP protocols. We can move them to skb ext, but it introduces a memory allocation on fast path. Fortunately, we only need to a word-size to store all the information, because the flags actually only contains 1 bit so can be just packed into the lowest bit of the "pointer", which is stored as unsigned long. Inside struct sk_buff, '_skb_refdst' can be reused because skb dst is no longer needed after ->sk_data_ready() so we can just drop it. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-5-xiyou.wangcong@gmail.com
2021-02-23 18:49:29 +00:00
ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb));
bpf, sockmap: Fix incorrect fwd_alloc accounting Incorrect accounting fwd_alloc can result in a warning when the socket is torn down, [18455.319240] WARNING: CPU: 0 PID: 24075 at net/core/stream.c:208 sk_stream_kill_queues+0x21f/0x230 [...] [18455.319543] Call Trace: [18455.319556] inet_csk_destroy_sock+0xba/0x1f0 [18455.319577] tcp_rcv_state_process+0x1b4e/0x2380 [18455.319593] ? lock_downgrade+0x3a0/0x3a0 [18455.319617] ? tcp_finish_connect+0x1e0/0x1e0 [18455.319631] ? sk_reset_timer+0x15/0x70 [18455.319646] ? tcp_schedule_loss_probe+0x1b2/0x240 [18455.319663] ? lock_release+0xb2/0x3f0 [18455.319676] ? __release_sock+0x8a/0x1b0 [18455.319690] ? lock_downgrade+0x3a0/0x3a0 [18455.319704] ? lock_release+0x3f0/0x3f0 [18455.319717] ? __tcp_close+0x2c6/0x790 [18455.319736] ? tcp_v4_do_rcv+0x168/0x370 [18455.319750] tcp_v4_do_rcv+0x168/0x370 [18455.319767] __release_sock+0xbc/0x1b0 [18455.319785] __tcp_close+0x2ee/0x790 [18455.319805] tcp_close+0x20/0x80 This currently happens because on redirect case we do skb_set_owner_r() with the original sock. This increments the fwd_alloc memory accounting on the original sock. Then on redirect we may push this into the queue of the psock we are redirecting to. When the skb is flushed from the queue we give the memory back to the original sock. The problem is if the original sock is destroyed/closed with skbs on another psocks queue then the original sock will not have a way to reclaim the memory before being destroyed. Then above warning will be thrown sockA sockB sk_psock_strp_read() sk_psock_verdict_apply() -- SK_REDIRECT -- sk_psock_skb_redirect() skb_queue_tail(psock_other->ingress_skb..) sk_close() sock_map_unref() sk_psock_put() sk_psock_drop() sk_psock_zap_ingress() At this point we have torn down our own psock, but have the outstanding skb in psock_other. Note that SK_PASS doesn't have this problem because the sk_psock_drop() logic releases the skb, its still associated with our psock. To resolve lets only account for sockets on the ingress queue that are still associated with the current socket. On the redirect case we will check memory limits per 6fa9201a89898, but will omit fwd_alloc accounting until skb is actually enqueued. When the skb is sent via skb_send_sock_locked or received with sk_psock_skb_ingress memory will be claimed on psock_other. Fixes: 6fa9201a89898 ("bpf, sockmap: Avoid returning unneeded EAGAIN when redirecting to self") Reported-by: Andrii Nakryiko <andrii@kernel.org> Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/161731444013.68884.4021114312848535993.stgit@john-XPS-13-9370
2021-04-01 22:00:40 +00:00
skb->sk = 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 00:45:58 +00:00
}
sk_psock_verdict_apply(psock, skb, ret);
bpf, sockmap: RCU dereferenced psock may be used outside RCU block If an ingress verdict program specifies message sizes greater than skb->len and there is an ENOMEM error due to memory pressure we may call the rcv_msg handler outside the strp_data_ready() caller context. This is because on an ENOMEM error the strparser will retry from a workqueue. The caller currently protects the use of psock by calling the strp_data_ready() inside a rcu_read_lock/unlock block. But, in above workqueue error case the psock is accessed outside the read_lock/unlock block of the caller. So instead of using psock directly we must do a look up against the sk again to ensure the psock is available. There is an an ugly piece here where we must handle the case where we paused the strp and removed the psock. On psock removal we first pause the strparser and then remove the psock. If the strparser is paused while an skb is scheduled on the workqueue the skb will be dropped on the flow and kfree_skb() is called. If the workqueue manages to get called before we pause the strparser but runs the rcvmsg callback after the psock is removed we will hit the unlikely case where we run the sockmap rcvmsg handler but do not have a psock. For now we will follow strparser logic and drop the skb on the floor with skb_kfree(). This is ugly because the data is dropped. To date this has not caused problems in practice because either the application controlling the sockmap is coordinating with the datapath so that skbs are "flushed" before removal or we simply wait for the sock to be closed before removing it. This patch fixes the describe RCU bug and dropping the skb doesn't make things worse. Future patches will improve this by allowing the normal case where skbs are not merged to skip the strparser altogether. In practice many (most?) use cases have no need to merge skbs so its both a code complexity hit as seen above and a performance issue. For example, in the Cilium case we always set the strparser up to return sbks 1:1 without any merging and have avoided above issues. Fixes: e91de6afa81c1 ("bpf: Fix running sk_skb program types with ktls") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Martin KaFai Lau <kafai@fb.com> Link: https://lore.kernel.org/bpf/159312679888.18340.15248924071966273998.stgit@john-XPS-13-9370
2020-06-25 23:13:18 +00:00
out:
bpf, sockmap: RCU splat with redirect and strparser error or TLS There are two paths to generate the below RCU splat the first and most obvious is the result of the BPF verdict program issuing a redirect on a TLS socket (This is the splat shown below). Unlike the non-TLS case the caller of the *strp_read() hooks does not wrap the call in a rcu_read_lock/unlock. Then if the BPF program issues a redirect action we hit the RCU splat. However, in the non-TLS socket case the splat appears to be relatively rare, because the skmsg caller into the strp_data_ready() is wrapped in a rcu_read_lock/unlock. Shown here, static void sk_psock_strp_data_ready(struct sock *sk) { struct sk_psock *psock; rcu_read_lock(); psock = sk_psock(sk); if (likely(psock)) { if (tls_sw_has_ctx_rx(sk)) { psock->parser.saved_data_ready(sk); } else { write_lock_bh(&sk->sk_callback_lock); strp_data_ready(&psock->parser.strp); write_unlock_bh(&sk->sk_callback_lock); } } rcu_read_unlock(); } If the above was the only way to run the verdict program we would be safe. But, there is a case where the strparser may throw an ENOMEM error while parsing the skb. This is a result of a failed skb_clone, or alloc_skb_for_msg while building a new merged skb when the msg length needed spans multiple skbs. This will in turn put the skb on the strp_wrk workqueue in the strparser code. The skb will later be dequeued and verdict programs run, but now from a different context without the rcu_read_lock()/unlock() critical section in sk_psock_strp_data_ready() shown above. In practice I have not seen this yet, because as far as I know most users of the verdict programs are also only working on single skbs. In this case no merge happens which could trigger the above ENOMEM errors. In addition the system would need to be under memory pressure. For example, we can't hit the above case in selftests because we missed having tests to merge skbs. (Added in later patch) To fix the below splat extend the rcu_read_lock/unnlock block to include the call to sk_psock_tls_verdict_apply(). This will fix both TLS redirect case and non-TLS redirect+error case. Also remove psock from the sk_psock_tls_verdict_apply() function signature its not used there. [ 1095.937597] WARNING: suspicious RCU usage [ 1095.940964] 5.7.0-rc7-02911-g463bac5f1ca79 #1 Tainted: G W [ 1095.944363] ----------------------------- [ 1095.947384] include/linux/skmsg.h:284 suspicious rcu_dereference_check() usage! [ 1095.950866] [ 1095.950866] other info that might help us debug this: [ 1095.950866] [ 1095.957146] [ 1095.957146] rcu_scheduler_active = 2, debug_locks = 1 [ 1095.961482] 1 lock held by test_sockmap/15970: [ 1095.964501] #0: ffff9ea6b25de660 (sk_lock-AF_INET){+.+.}-{0:0}, at: tls_sw_recvmsg+0x13a/0x840 [tls] [ 1095.968568] [ 1095.968568] stack backtrace: [ 1095.975001] CPU: 1 PID: 15970 Comm: test_sockmap Tainted: G W 5.7.0-rc7-02911-g463bac5f1ca79 #1 [ 1095.977883] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014 [ 1095.980519] Call Trace: [ 1095.982191] dump_stack+0x8f/0xd0 [ 1095.984040] sk_psock_skb_redirect+0xa6/0xf0 [ 1095.986073] sk_psock_tls_strp_read+0x1d8/0x250 [ 1095.988095] tls_sw_recvmsg+0x714/0x840 [tls] v2: Improve commit message to identify non-TLS redirect plus error case condition as well as more common TLS case. In the process I decided doing the rcu_read_unlock followed by the lock/unlock inside branches was unnecessarily complex. We can just extend the current rcu block and get the same effeective without the shuffling and branching. Thanks Martin! Fixes: e91de6afa81c1 ("bpf: Fix running sk_skb program types with ktls") Reported-by: Jakub Sitnicki <jakub@cloudflare.com> Reported-by: kernel test robot <rong.a.chen@intel.com> Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Martin KaFai Lau <kafai@fb.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/159312677907.18340.11064813152758406626.stgit@john-XPS-13-9370
2020-06-25 23:12:59 +00:00
rcu_read_unlock();
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 00:45:58 +00:00
}
static int sk_psock_strp_read_done(struct strparser *strp, int err)
{
return err;
}
static int sk_psock_strp_parse(struct strparser *strp, struct sk_buff *skb)
{
skmsg: Get rid of struct sk_psock_parser struct sk_psock_parser is embedded in sk_psock, it is unnecessary as skb verdict also uses ->saved_data_ready. We can simply fold these fields into sk_psock, and get rid of ->enabled. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-3-xiyou.wangcong@gmail.com
2021-02-23 18:49:27 +00:00
struct sk_psock *psock = container_of(strp, struct sk_psock, strp);
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 00:45:58 +00:00
struct bpf_prog *prog;
int ret = skb->len;
rcu_read_lock();
sock_map: Rename skb_parser and skb_verdict These two eBPF programs are tied to BPF_SK_SKB_STREAM_PARSER and BPF_SK_SKB_STREAM_VERDICT, rename them to reflect the fact they are only used for TCP. And save the name 'skb_verdict' for general use later. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Reviewed-by: Lorenz Bauer <lmb@cloudflare.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-6-xiyou.wangcong@gmail.com
2021-02-23 18:49:30 +00:00
prog = READ_ONCE(psock->progs.stream_parser);
bpf, sockmap: Add memory accounting so skbs on ingress lists are visible Move skb->sk assignment out of sk_psock_bpf_run() and into individual callers. Then we can use proper skb_set_owner_r() call to assign a sk to a skb. This improves things by also charging the truesize against the sockets sk_rmem_alloc counter. With this done we get some accounting in place to ensure the memory associated with skbs on the workqueue are still being accounted for somewhere. Finally, by using skb_set_owner_r the destructor is setup so we can just let the normal skb_kfree logic recover the memory. Combined with previous patch dropping skb_orphan() we now can recover from memory pressure and maintain accounting. Note, we will charge the skbs against their originating socket even if being redirected into another socket. Once the skb completes the redirect op the kfree_skb will give the memory back. This is important because if we charged the socket we are redirecting to (like it was done before this series) the sock_writeable() test could fail because of the skb trying to be sent is already charged against the socket. Also TLS case is special. Here we wait until we have decided not to simply PASS the packet up the stack. In the case where we PASS the packet up the stack we already have an skb which is accounted for on the TLS socket context. For the parser case we continue to just set/clear skb->sk this is because the skb being used here may be combined with other skbs or turned into multiple skbs depending on the parser logic. For example the parser could request a payload length greater than skb->len so that the strparser needs to collect multiple skbs. At any rate the final result will be handled in the strparser recv callback. Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/160226867513.5692.10579573214635925960.stgit@john-Precision-5820-Tower
2020-10-09 18:37:55 +00:00
if (likely(prog)) {
skb->sk = psock->sk;
skmsg: Get rid of sk_psock_bpf_run() It is now nearly identical to bpf_prog_run_pin_on_cpu() and it has an unused parameter 'psock', so we can just get rid of it and call bpf_prog_run_pin_on_cpu() directly. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-9-xiyou.wangcong@gmail.com
2021-02-23 18:49:33 +00:00
ret = bpf_prog_run_pin_on_cpu(prog, skb);
bpf, sockmap: Add memory accounting so skbs on ingress lists are visible Move skb->sk assignment out of sk_psock_bpf_run() and into individual callers. Then we can use proper skb_set_owner_r() call to assign a sk to a skb. This improves things by also charging the truesize against the sockets sk_rmem_alloc counter. With this done we get some accounting in place to ensure the memory associated with skbs on the workqueue are still being accounted for somewhere. Finally, by using skb_set_owner_r the destructor is setup so we can just let the normal skb_kfree logic recover the memory. Combined with previous patch dropping skb_orphan() we now can recover from memory pressure and maintain accounting. Note, we will charge the skbs against their originating socket even if being redirected into another socket. Once the skb completes the redirect op the kfree_skb will give the memory back. This is important because if we charged the socket we are redirecting to (like it was done before this series) the sock_writeable() test could fail because of the skb trying to be sent is already charged against the socket. Also TLS case is special. Here we wait until we have decided not to simply PASS the packet up the stack. In the case where we PASS the packet up the stack we already have an skb which is accounted for on the TLS socket context. For the parser case we continue to just set/clear skb->sk this is because the skb being used here may be combined with other skbs or turned into multiple skbs depending on the parser logic. For example the parser could request a payload length greater than skb->len so that the strparser needs to collect multiple skbs. At any rate the final result will be handled in the strparser recv callback. Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/160226867513.5692.10579573214635925960.stgit@john-Precision-5820-Tower
2020-10-09 18:37:55 +00:00
skb->sk = 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 00:45:58 +00:00
rcu_read_unlock();
return ret;
}
/* Called with socket lock held. */
bpf: sk_msg, fix socket data_ready events When a skb verdict program is in-use and either another BPF program redirects to that socket or the new SK_PASS support is used the data_ready callback does not wake up application. Instead because the stream parser/verdict is using the sk data_ready callback we wake up the stream parser/verdict block. Fix this by adding a helper to check if the stream parser block is enabled on the sk and if so call the saved pointer which is the upper layers wake up function. This fixes application stalls observed when an application is waiting for data in a blocking read(). Fixes: d829e9c4112b ("tls: convert to generic sk_msg interface") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-12-20 19:35:33 +00:00
static void sk_psock_strp_data_ready(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 00:45:58 +00:00
{
struct sk_psock *psock;
net/sock: Introduce trace_sk_data_ready() As suggested by Cong, introduce a tracepoint for all ->sk_data_ready() callback implementations. For example: <...> iperf-609 [002] ..... 70.660425: sk_data_ready: family=2 protocol=6 func=sock_def_readable iperf-609 [002] ..... 70.660436: sk_data_ready: family=2 protocol=6 func=sock_def_readable <...> Suggested-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Peilin Ye <peilin.ye@bytedance.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-01-20 00:45:16 +00:00
trace_sk_data_ready(sk);
bpf, sockmap: convert to generic sk_msg interface Add a generic sk_msg layer, and convert current sockmap and later kTLS over to make use of it. While sk_buff handles network packet representation from netdevice up to socket, sk_msg handles data representation from application to socket layer. This means that sk_msg framework spans across ULP users in the kernel, and enables features such as introspection or filtering of data with the help of BPF programs that operate on this data structure. Latter becomes in particular useful for kTLS where data encryption is deferred into the kernel, and as such enabling the kernel to perform L7 introspection and policy based on BPF for TLS connections where the record is being encrypted after BPF has run and came to a verdict. In order to get there, first step is to transform open coding of scatter-gather list handling into a common core framework that subsystems can use. The code itself has been split and refactored into three bigger pieces: i) the generic sk_msg API which deals with managing the scatter gather ring, providing helpers for walking and mangling, transferring application data from user space into it, and preparing it for BPF pre/post-processing, ii) the plain sock map itself where sockets can be attached to or detached from; these bits are independent of i) which can now be used also without sock map, and iii) the integration with plain TCP as one protocol to be used for processing L7 application data (later this could e.g. also be extended to other protocols like UDP). The semantics are the same with the old sock map code and therefore no change of user facing behavior or APIs. While pursuing this work it also helped finding a number of bugs in the old sockmap code that we've fixed already in earlier commits. The test_sockmap kselftest suite passes through fine as well. Joint work with John. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-13 00:45:58 +00:00
rcu_read_lock();
psock = sk_psock(sk);
if (likely(psock)) {
bpf: Fix running sk_skb program types with ktls KTLS uses a stream parser to collect TLS messages and send them to the upper layer tls receive handler. This ensures the tls receiver has a full TLS header to parse when it is run. However, when a socket has BPF_SK_SKB_STREAM_VERDICT program attached before KTLS is enabled we end up with two stream parsers running on the same socket. The result is both try to run on the same socket. First the KTLS stream parser runs and calls read_sock() which will tcp_read_sock which in turn calls tcp_rcv_skb(). This dequeues the skb from the sk_receive_queue. When this is done KTLS code then data_ready() callback which because we stacked KTLS on top of the bpf stream verdict program has been replaced with sk_psock_start_strp(). This will in turn kick the stream parser again and eventually do the same thing KTLS did above calling into tcp_rcv_skb() and dequeuing a skb from the sk_receive_queue. At this point the data stream is broke. Part of the stream was handled by the KTLS side some other bytes may have been handled by the BPF side. Generally this results in either missing data or more likely a "Bad Message" complaint from the kTLS receive handler as the BPF program steals some bytes meant to be in a TLS header and/or the TLS header length is no longer correct. We've already broke the idealized model where we can stack ULPs in any order with generic callbacks on the TX side to handle this. So in this patch we do the same thing but for RX side. We add a sk_psock_strp_enabled() helper so TLS can learn a BPF verdict program is running and add a tls_sw_has_ctx_rx() helper so BPF side can learn there is a TLS ULP on the socket. Then on BPF side we omit calling our stream parser to avoid breaking the data stream for the KTLS receiver. Then on the KTLS side we call BPF_SK_SKB_STREAM_VERDICT once the KTLS receiver is done with the packet but before it posts the msg to userspace. This gives us symmetry between the TX and RX halfs and IMO makes it usable again. On the TX side we process packets in this order BPF -> TLS -> TCP and on the receive side in the reverse order TCP -> TLS -> BPF. Discovered while testing OpenSSL 3.0 Alpha2.0 release. Fixes: d829e9c4112b5 ("tls: convert to generic sk_msg interface") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/159079361946.5745.605854335665044485.stgit@john-Precision-5820-Tower Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-29 23:06:59 +00:00
if (tls_sw_has_ctx_rx(sk)) {
skmsg: Get rid of struct sk_psock_parser struct sk_psock_parser is embedded in sk_psock, it is unnecessary as skb verdict also uses ->saved_data_ready. We can simply fold these fields into sk_psock, and get rid of ->enabled. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-3-xiyou.wangcong@gmail.com
2021-02-23 18:49:27 +00:00
psock->saved_data_ready(sk);
bpf: Fix running sk_skb program types with ktls KTLS uses a stream parser to collect TLS messages and send them to the upper layer tls receive handler. This ensures the tls receiver has a full TLS header to parse when it is run. However, when a socket has BPF_SK_SKB_STREAM_VERDICT program attached before KTLS is enabled we end up with two stream parsers running on the same socket. The result is both try to run on the same socket. First the KTLS stream parser runs and calls read_sock() which will tcp_read_sock which in turn calls tcp_rcv_skb(). This dequeues the skb from the sk_receive_queue. When this is done KTLS code then data_ready() callback which because we stacked KTLS on top of the bpf stream verdict program has been replaced with sk_psock_start_strp(). This will in turn kick the stream parser again and eventually do the same thing KTLS did above calling into tcp_rcv_skb() and dequeuing a skb from the sk_receive_queue. At this point the data stream is broke. Part of the stream was handled by the KTLS side some other bytes may have been handled by the BPF side. Generally this results in either missing data or more likely a "Bad Message" complaint from the kTLS receive handler as the BPF program steals some bytes meant to be in a TLS header and/or the TLS header length is no longer correct. We've already broke the idealized model where we can stack ULPs in any order with generic callbacks on the TX side to handle this. So in this patch we do the same thing but for RX side. We add a sk_psock_strp_enabled() helper so TLS can learn a BPF verdict program is running and add a tls_sw_has_ctx_rx() helper so BPF side can learn there is a TLS ULP on the socket. Then on BPF side we omit calling our stream parser to avoid breaking the data stream for the KTLS receiver. Then on the KTLS side we call BPF_SK_SKB_STREAM_VERDICT once the KTLS receiver is done with the packet but before it posts the msg to userspace. This gives us symmetry between the TX and RX halfs and IMO makes it usable again. On the TX side we process packets in this order BPF -> TLS -> TCP and on the receive side in the reverse order TCP -> TLS -> BPF. Discovered while testing OpenSSL 3.0 Alpha2.0 release. Fixes: d829e9c4112b5 ("tls: convert to generic sk_msg interface") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/159079361946.5745.605854335665044485.stgit@john-Precision-5820-Tower Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-29 23:06:59 +00:00
} else {
write_lock_bh(&sk->sk_callback_lock);
skmsg: Get rid of struct sk_psock_parser struct sk_psock_parser is embedded in sk_psock, it is unnecessary as skb verdict also uses ->saved_data_ready. We can simply fold these fields into sk_psock, and get rid of ->enabled. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-3-xiyou.wangcong@gmail.com
2021-02-23 18:49:27 +00:00
strp_data_ready(&psock->strp);
bpf: Fix running sk_skb program types with ktls KTLS uses a stream parser to collect TLS messages and send them to the upper layer tls receive handler. This ensures the tls receiver has a full TLS header to parse when it is run. However, when a socket has BPF_SK_SKB_STREAM_VERDICT program attached before KTLS is enabled we end up with two stream parsers running on the same socket. The result is both try to run on the same socket. First the KTLS stream parser runs and calls read_sock() which will tcp_read_sock which in turn calls tcp_rcv_skb(). This dequeues the skb from the sk_receive_queue. When this is done KTLS code then data_ready() callback which because we stacked KTLS on top of the bpf stream verdict program has been replaced with sk_psock_start_strp(). This will in turn kick the stream parser again and eventually do the same thing KTLS did above calling into tcp_rcv_skb() and dequeuing a skb from the sk_receive_queue. At this point the data stream is broke. Part of the stream was handled by the KTLS side some other bytes may have been handled by the BPF side. Generally this results in either missing data or more likely a "Bad Message" complaint from the kTLS receive handler as the BPF program steals some bytes meant to be in a TLS header and/or the TLS header length is no longer correct. We've already broke the idealized model where we can stack ULPs in any order with generic callbacks on the TX side to handle this. So in this patch we do the same thing but for RX side. We add a sk_psock_strp_enabled() helper so TLS can learn a BPF verdict program is running and add a tls_sw_has_ctx_rx() helper so BPF side can learn there is a TLS ULP on the socket. Then on BPF side we omit calling our stream parser to avoid breaking the data stream for the KTLS receiver. Then on the KTLS side we call BPF_SK_SKB_STREAM_VERDICT once the KTLS receiver is done with the packet but before it posts the msg to userspace. This gives us symmetry between the TX and RX halfs and IMO makes it usable again. On the TX side we process packets in this order BPF -> TLS -> TCP and on the receive side in the reverse order TCP -> TLS -> BPF. Discovered while testing OpenSSL 3.0 Alpha2.0 release. Fixes: d829e9c4112b5 ("tls: convert to generic sk_msg interface") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/159079361946.5745.605854335665044485.stgit@john-Precision-5820-Tower Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-29 23:06:59 +00:00
write_unlock_bh(&sk->sk_callback_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 00:45:58 +00:00
}
rcu_read_unlock();
}
bpf: Clean up sockmap related Kconfigs As suggested by John, clean up sockmap related Kconfigs: Reduce the scope of CONFIG_BPF_STREAM_PARSER down to TCP stream parser, to reflect its name. Make the rest sockmap code simply depend on CONFIG_BPF_SYSCALL and CONFIG_INET, the latter is still needed at this point because of TCP/UDP proto update. And leave CONFIG_NET_SOCK_MSG untouched, as it is used by non-sockmap cases. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Reviewed-by: Lorenz Bauer <lmb@cloudflare.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-2-xiyou.wangcong@gmail.com
2021-02-23 18:49:26 +00:00
int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock)
{
bpf, sockmap: Fix bug that strp_done cannot be called strp_done is only called when psock->progs.stream_parser is not NULL, but stream_parser was set to NULL by sk_psock_stop_strp(), called by sk_psock_drop() earlier. So, strp_done can never be called. Introduce SK_PSOCK_RX_ENABLED to mark whether there is strp on psock. Change the condition for calling strp_done from judging whether stream_parser is set to judging whether this flag is set. This flag is only set once when strp_init() succeeds, and will never be cleared later. Fixes: c0d95d3380ee ("bpf, sockmap: Re-evaluate proto ops when psock is removed from sockmap") Signed-off-by: Xu Kuohai <xukuohai@huawei.com> Reviewed-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/r/20230804073740.194770-3-xukuohai@huaweicloud.com Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-08-04 07:37:38 +00:00
int ret;
bpf: Clean up sockmap related Kconfigs As suggested by John, clean up sockmap related Kconfigs: Reduce the scope of CONFIG_BPF_STREAM_PARSER down to TCP stream parser, to reflect its name. Make the rest sockmap code simply depend on CONFIG_BPF_SYSCALL and CONFIG_INET, the latter is still needed at this point because of TCP/UDP proto update. And leave CONFIG_NET_SOCK_MSG untouched, as it is used by non-sockmap cases. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Reviewed-by: Lorenz Bauer <lmb@cloudflare.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-2-xiyou.wangcong@gmail.com
2021-02-23 18:49:26 +00:00
static const struct strp_callbacks cb = {
.rcv_msg = sk_psock_strp_read,
.read_sock_done = sk_psock_strp_read_done,
.parse_msg = sk_psock_strp_parse,
};
bpf, sockmap: Fix bug that strp_done cannot be called strp_done is only called when psock->progs.stream_parser is not NULL, but stream_parser was set to NULL by sk_psock_stop_strp(), called by sk_psock_drop() earlier. So, strp_done can never be called. Introduce SK_PSOCK_RX_ENABLED to mark whether there is strp on psock. Change the condition for calling strp_done from judging whether stream_parser is set to judging whether this flag is set. This flag is only set once when strp_init() succeeds, and will never be cleared later. Fixes: c0d95d3380ee ("bpf, sockmap: Re-evaluate proto ops when psock is removed from sockmap") Signed-off-by: Xu Kuohai <xukuohai@huawei.com> Reviewed-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/r/20230804073740.194770-3-xukuohai@huaweicloud.com Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-08-04 07:37:38 +00:00
ret = strp_init(&psock->strp, sk, &cb);
if (!ret)
sk_psock_set_state(psock, SK_PSOCK_RX_STRP_ENABLED);
return ret;
bpf: Clean up sockmap related Kconfigs As suggested by John, clean up sockmap related Kconfigs: Reduce the scope of CONFIG_BPF_STREAM_PARSER down to TCP stream parser, to reflect its name. Make the rest sockmap code simply depend on CONFIG_BPF_SYSCALL and CONFIG_INET, the latter is still needed at this point because of TCP/UDP proto update. And leave CONFIG_NET_SOCK_MSG untouched, as it is used by non-sockmap cases. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Reviewed-by: Lorenz Bauer <lmb@cloudflare.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-2-xiyou.wangcong@gmail.com
2021-02-23 18:49:26 +00:00
}
void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock)
{
skmsg: Get rid of struct sk_psock_parser struct sk_psock_parser is embedded in sk_psock, it is unnecessary as skb verdict also uses ->saved_data_ready. We can simply fold these fields into sk_psock, and get rid of ->enabled. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-3-xiyou.wangcong@gmail.com
2021-02-23 18:49:27 +00:00
if (psock->saved_data_ready)
bpf: Clean up sockmap related Kconfigs As suggested by John, clean up sockmap related Kconfigs: Reduce the scope of CONFIG_BPF_STREAM_PARSER down to TCP stream parser, to reflect its name. Make the rest sockmap code simply depend on CONFIG_BPF_SYSCALL and CONFIG_INET, the latter is still needed at this point because of TCP/UDP proto update. And leave CONFIG_NET_SOCK_MSG untouched, as it is used by non-sockmap cases. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Reviewed-by: Lorenz Bauer <lmb@cloudflare.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-2-xiyou.wangcong@gmail.com
2021-02-23 18:49:26 +00:00
return;
skmsg: Get rid of struct sk_psock_parser struct sk_psock_parser is embedded in sk_psock, it is unnecessary as skb verdict also uses ->saved_data_ready. We can simply fold these fields into sk_psock, and get rid of ->enabled. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-3-xiyou.wangcong@gmail.com
2021-02-23 18:49:27 +00:00
psock->saved_data_ready = sk->sk_data_ready;
bpf: Clean up sockmap related Kconfigs As suggested by John, clean up sockmap related Kconfigs: Reduce the scope of CONFIG_BPF_STREAM_PARSER down to TCP stream parser, to reflect its name. Make the rest sockmap code simply depend on CONFIG_BPF_SYSCALL and CONFIG_INET, the latter is still needed at this point because of TCP/UDP proto update. And leave CONFIG_NET_SOCK_MSG untouched, as it is used by non-sockmap cases. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Reviewed-by: Lorenz Bauer <lmb@cloudflare.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-2-xiyou.wangcong@gmail.com
2021-02-23 18:49:26 +00:00
sk->sk_data_ready = sk_psock_strp_data_ready;
sk->sk_write_space = sk_psock_write_space;
}
void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock)
{
bpf, sockmap: Re-evaluate proto ops when psock is removed from sockmap When a sock is added to a sock map we evaluate what proto op hooks need to be used. However, when the program is removed from the sock map we have not been evaluating if that changes the required program layout. Before the patch listed in the 'fixes' tag this was not causing failures because the base program set handles all cases. Specifically, the case with a stream parser and the case with out a stream parser are both handled. With the fix below we identified a race when running with a proto op that attempts to read skbs off both the stream parser and the skb->receive_queue. Namely, that a race existed where when the stream parser is empty checking the skb->receive_queue from recvmsg at the precies moment when the parser is paused and the receive_queue is not empty could result in skipping the stream parser. This may break a RX policy depending on the parser to run. The fix tag then loads a specific proto ops that resolved this race. But, we missed removing that proto ops recv hook when the sock is removed from the sockmap. The result is the stream parser is stopped so no more skbs will be aggregated there, but the hook and BPF program continues to be attached on the psock. User space will then get an EBUSY when trying to read the socket because the recvmsg() handler is now waiting on a stopped stream parser. To fix we rerun the proto ops init() function which will look at the new set of progs attached to the psock and rest the proto ops hook to the correct handlers. And in the above case where we remove the sock from the sock map the RX prog will no longer be listed so the proto ops is removed. Fixes: c5d2177a72a16 ("bpf, sockmap: Fix race in ingress receive verdict with redirect to self") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20211119181418.353932-3-john.fastabend@gmail.com
2021-11-19 18:14:18 +00:00
psock_set_prog(&psock->progs.stream_parser, NULL);
skmsg: Get rid of struct sk_psock_parser struct sk_psock_parser is embedded in sk_psock, it is unnecessary as skb verdict also uses ->saved_data_ready. We can simply fold these fields into sk_psock, and get rid of ->enabled. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-3-xiyou.wangcong@gmail.com
2021-02-23 18:49:27 +00:00
if (!psock->saved_data_ready)
bpf: Clean up sockmap related Kconfigs As suggested by John, clean up sockmap related Kconfigs: Reduce the scope of CONFIG_BPF_STREAM_PARSER down to TCP stream parser, to reflect its name. Make the rest sockmap code simply depend on CONFIG_BPF_SYSCALL and CONFIG_INET, the latter is still needed at this point because of TCP/UDP proto update. And leave CONFIG_NET_SOCK_MSG untouched, as it is used by non-sockmap cases. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Reviewed-by: Lorenz Bauer <lmb@cloudflare.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-2-xiyou.wangcong@gmail.com
2021-02-23 18:49:26 +00:00
return;
skmsg: Get rid of struct sk_psock_parser struct sk_psock_parser is embedded in sk_psock, it is unnecessary as skb verdict also uses ->saved_data_ready. We can simply fold these fields into sk_psock, and get rid of ->enabled. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-3-xiyou.wangcong@gmail.com
2021-02-23 18:49:27 +00:00
sk->sk_data_ready = psock->saved_data_ready;
psock->saved_data_ready = NULL;
strp_stop(&psock->strp);
bpf: Clean up sockmap related Kconfigs As suggested by John, clean up sockmap related Kconfigs: Reduce the scope of CONFIG_BPF_STREAM_PARSER down to TCP stream parser, to reflect its name. Make the rest sockmap code simply depend on CONFIG_BPF_SYSCALL and CONFIG_INET, the latter is still needed at this point because of TCP/UDP proto update. And leave CONFIG_NET_SOCK_MSG untouched, as it is used by non-sockmap cases. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Reviewed-by: Lorenz Bauer <lmb@cloudflare.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-2-xiyou.wangcong@gmail.com
2021-02-23 18:49:26 +00:00
}
static void sk_psock_done_strp(struct sk_psock *psock)
{
/* Parser has been stopped */
bpf, sockmap: Fix bug that strp_done cannot be called strp_done is only called when psock->progs.stream_parser is not NULL, but stream_parser was set to NULL by sk_psock_stop_strp(), called by sk_psock_drop() earlier. So, strp_done can never be called. Introduce SK_PSOCK_RX_ENABLED to mark whether there is strp on psock. Change the condition for calling strp_done from judging whether stream_parser is set to judging whether this flag is set. This flag is only set once when strp_init() succeeds, and will never be cleared later. Fixes: c0d95d3380ee ("bpf, sockmap: Re-evaluate proto ops when psock is removed from sockmap") Signed-off-by: Xu Kuohai <xukuohai@huawei.com> Reviewed-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/r/20230804073740.194770-3-xukuohai@huaweicloud.com Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-08-04 07:37:38 +00:00
if (sk_psock_test_state(psock, SK_PSOCK_RX_STRP_ENABLED))
skmsg: Get rid of struct sk_psock_parser struct sk_psock_parser is embedded in sk_psock, it is unnecessary as skb verdict also uses ->saved_data_ready. We can simply fold these fields into sk_psock, and get rid of ->enabled. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-3-xiyou.wangcong@gmail.com
2021-02-23 18:49:27 +00:00
strp_done(&psock->strp);
bpf: Clean up sockmap related Kconfigs As suggested by John, clean up sockmap related Kconfigs: Reduce the scope of CONFIG_BPF_STREAM_PARSER down to TCP stream parser, to reflect its name. Make the rest sockmap code simply depend on CONFIG_BPF_SYSCALL and CONFIG_INET, the latter is still needed at this point because of TCP/UDP proto update. And leave CONFIG_NET_SOCK_MSG untouched, as it is used by non-sockmap cases. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Reviewed-by: Lorenz Bauer <lmb@cloudflare.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-2-xiyou.wangcong@gmail.com
2021-02-23 18:49:26 +00:00
}
#else
static void sk_psock_done_strp(struct sk_psock *psock)
{
}
#endif /* CONFIG_BPF_STREAM_PARSER */
net: Introduce a new proto_ops ->read_skb() Currently both splice() and sockmap use ->read_sock() to read skb from receive queue, but for sockmap we only read one entire skb at a time, so ->read_sock() is too conservative to use. Introduce a new proto_ops ->read_skb() which supports this sematic, with this we can finally pass the ownership of skb to recv actors. For non-TCP protocols, all ->read_sock() can be simply converted to ->read_skb(). Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20220615162014.89193-3-xiyou.wangcong@gmail.com
2022-06-15 16:20:12 +00:00
static int sk_psock_verdict_recv(struct sock *sk, struct sk_buff *skb)
bpf, sockmap: Allow skipping sk_skb parser program Currently, we often run with a nop parser namely one that just does this, 'return skb->len'. This happens when either our verdict program can handle streaming data or it is only looking at socket data such as IP addresses and other metadata associated with the flow. The second case is common for a L3/L4 proxy for instance. So lets allow loading programs without the parser then we can skip the stream parser logic and avoid having to add a BPF program that is effectively a nop. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/160239297866.8495.13345662302749219672.stgit@john-Precision-5820-Tower
2020-10-11 05:09:38 +00:00
{
struct sk_psock *psock;
struct bpf_prog *prog;
int ret = __SK_DROP;
net: Introduce a new proto_ops ->read_skb() Currently both splice() and sockmap use ->read_sock() to read skb from receive queue, but for sockmap we only read one entire skb at a time, so ->read_sock() is too conservative to use. Introduce a new proto_ops ->read_skb() which supports this sematic, with this we can finally pass the ownership of skb to recv actors. For non-TCP protocols, all ->read_sock() can be simply converted to ->read_skb(). Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20220615162014.89193-3-xiyou.wangcong@gmail.com
2022-06-15 16:20:12 +00:00
int len = skb->len;
bpf, sockmap: Allow skipping sk_skb parser program Currently, we often run with a nop parser namely one that just does this, 'return skb->len'. This happens when either our verdict program can handle streaming data or it is only looking at socket data such as IP addresses and other metadata associated with the flow. The second case is common for a L3/L4 proxy for instance. So lets allow loading programs without the parser then we can skip the stream parser logic and avoid having to add a BPF program that is effectively a nop. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/160239297866.8495.13345662302749219672.stgit@john-Precision-5820-Tower
2020-10-11 05:09:38 +00:00
rcu_read_lock();
psock = sk_psock(sk);
if (unlikely(!psock)) {
len = 0;
bpf, sockmap: Incorrectly handling copied_seq The read_skb() logic is incrementing the tcp->copied_seq which is used for among other things calculating how many outstanding bytes can be read by the application. This results in application errors, if the application does an ioctl(FIONREAD) we return zero because this is calculated from the copied_seq value. To fix this we move tcp->copied_seq accounting into the recv handler so that we update these when the recvmsg() hook is called and data is in fact copied into user buffers. This gives an accurate FIONREAD value as expected and improves ACK handling. Before we were calling the tcp_rcv_space_adjust() which would update 'number of bytes copied to user in last RTT' which is wrong for programs returning SK_PASS. The bytes are only copied to the user when recvmsg is handled. Doing the fix for recvmsg is straightforward, but fixing redirect and SK_DROP pkts is a bit tricker. Build a tcp_psock_eat() helper and then call this from skmsg handlers. This fixes another issue where a broken socket with a BPF program doing a resubmit could hang the receiver. This happened because although read_skb() consumed the skb through sock_drop() it did not update the copied_seq. Now if a single reccv socket is redirecting to many sockets (for example for lb) the receiver sk will be hung even though we might expect it to continue. The hang comes from not updating the copied_seq numbers and memory pressure resulting from that. We have a slight layer problem of calling tcp_eat_skb even if its not a TCP socket. To fix we could refactor and create per type receiver handlers. I decided this is more work than we want in the fix and we already have some small tweaks depending on caller that use the helper skb_bpf_strparser(). So we extend that a bit and always set the strparser bit when it is in use and then we can gate the seq_copied updates on this. Fixes: 04919bed948dc ("tcp: Introduce tcp_read_skb()") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20230523025618.113937-9-john.fastabend@gmail.com
2023-05-23 02:56:12 +00:00
tcp_eat_skb(sk, skb);
skmsg: Increase sk->sk_drops when dropping packets It is hard to observe packet drops without increasing relevant drop counters, here we should increase sk->sk_drops which is a protocol-independent counter. Fortunately psock is always associated with a struct sock, we can just use psock->sk. Suggested-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210615021342.7416-9-xiyou.wangcong@gmail.com
2021-06-15 02:13:42 +00:00
sock_drop(sk, skb);
bpf, sockmap: Allow skipping sk_skb parser program Currently, we often run with a nop parser namely one that just does this, 'return skb->len'. This happens when either our verdict program can handle streaming data or it is only looking at socket data such as IP addresses and other metadata associated with the flow. The second case is common for a L3/L4 proxy for instance. So lets allow loading programs without the parser then we can skip the stream parser logic and avoid having to add a BPF program that is effectively a nop. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/160239297866.8495.13345662302749219672.stgit@john-Precision-5820-Tower
2020-10-11 05:09:38 +00:00
goto out;
}
sock_map: Rename skb_parser and skb_verdict These two eBPF programs are tied to BPF_SK_SKB_STREAM_PARSER and BPF_SK_SKB_STREAM_VERDICT, rename them to reflect the fact they are only used for TCP. And save the name 'skb_verdict' for general use later. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Reviewed-by: Lorenz Bauer <lmb@cloudflare.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-6-xiyou.wangcong@gmail.com
2021-02-23 18:49:30 +00:00
prog = READ_ONCE(psock->progs.stream_verdict);
sock_map: Introduce BPF_SK_SKB_VERDICT Reusing BPF_SK_SKB_STREAM_VERDICT is possible but its name is confusing and more importantly we still want to distinguish them from user-space. So we can just reuse the stream verdict code but introduce a new type of eBPF program, skb_verdict. Users are not allowed to attach stream_verdict and skb_verdict programs to the same map. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210331023237.41094-10-xiyou.wangcong@gmail.com
2021-03-31 02:32:30 +00:00
if (!prog)
prog = READ_ONCE(psock->progs.skb_verdict);
bpf, sockmap: Allow skipping sk_skb parser program Currently, we often run with a nop parser namely one that just does this, 'return skb->len'. This happens when either our verdict program can handle streaming data or it is only looking at socket data such as IP addresses and other metadata associated with the flow. The second case is common for a L3/L4 proxy for instance. So lets allow loading programs without the parser then we can skip the stream parser logic and avoid having to add a BPF program that is effectively a nop. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/160239297866.8495.13345662302749219672.stgit@john-Precision-5820-Tower
2020-10-11 05:09:38 +00:00
if (likely(prog)) {
skmsg: Move sk_redir from TCP_SKB_CB to skb Currently TCP_SKB_CB() is hard-coded in skmsg code, it certainly does not work for any other non-TCP protocols. We can move them to skb ext, but it introduces a memory allocation on fast path. Fortunately, we only need to a word-size to store all the information, because the flags actually only contains 1 bit so can be just packed into the lowest bit of the "pointer", which is stored as unsigned long. Inside struct sk_buff, '_skb_refdst' can be reused because skb dst is no longer needed after ->sk_data_ready() so we can just drop it. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-5-xiyou.wangcong@gmail.com
2021-02-23 18:49:29 +00:00
skb_dst_drop(skb);
skb_bpf_redirect_clear(skb);
skmsg: Get rid of sk_psock_bpf_run() It is now nearly identical to bpf_prog_run_pin_on_cpu() and it has an unused parameter 'psock', so we can just get rid of it and call bpf_prog_run_pin_on_cpu() directly. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-9-xiyou.wangcong@gmail.com
2021-02-23 18:49:33 +00:00
ret = bpf_prog_run_pin_on_cpu(prog, skb);
skmsg: Move sk_redir from TCP_SKB_CB to skb Currently TCP_SKB_CB() is hard-coded in skmsg code, it certainly does not work for any other non-TCP protocols. We can move them to skb ext, but it introduces a memory allocation on fast path. Fortunately, we only need to a word-size to store all the information, because the flags actually only contains 1 bit so can be just packed into the lowest bit of the "pointer", which is stored as unsigned long. Inside struct sk_buff, '_skb_refdst' can be reused because skb dst is no longer needed after ->sk_data_ready() so we can just drop it. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-5-xiyou.wangcong@gmail.com
2021-02-23 18:49:29 +00:00
ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb));
bpf, sockmap: Allow skipping sk_skb parser program Currently, we often run with a nop parser namely one that just does this, 'return skb->len'. This happens when either our verdict program can handle streaming data or it is only looking at socket data such as IP addresses and other metadata associated with the flow. The second case is common for a L3/L4 proxy for instance. So lets allow loading programs without the parser then we can skip the stream parser logic and avoid having to add a BPF program that is effectively a nop. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/160239297866.8495.13345662302749219672.stgit@john-Precision-5820-Tower
2020-10-11 05:09:38 +00:00
}
tcp: handle pure FIN case correctly When skb->len==0, the recv_actor() returns 0 too, but we also use 0 for error conditions. This patch amends this by propagating the errors to tcp_read_skb() so that we can distinguish skb->len==0 case from error cases. Fixes: 04919bed948d ("tcp: Introduce tcp_read_skb()") Reported-by: Eric Dumazet <edumazet@google.com> Cc: John Fastabend <john.fastabend@gmail.com> Cc: Jakub Sitnicki <jakub@cloudflare.com> Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-17 19:54:45 +00:00
ret = sk_psock_verdict_apply(psock, skb, ret);
if (ret < 0)
len = ret;
bpf, sockmap: Allow skipping sk_skb parser program Currently, we often run with a nop parser namely one that just does this, 'return skb->len'. This happens when either our verdict program can handle streaming data or it is only looking at socket data such as IP addresses and other metadata associated with the flow. The second case is common for a L3/L4 proxy for instance. So lets allow loading programs without the parser then we can skip the stream parser logic and avoid having to add a BPF program that is effectively a nop. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/160239297866.8495.13345662302749219672.stgit@john-Precision-5820-Tower
2020-10-11 05:09:38 +00:00
out:
rcu_read_unlock();
return len;
}
static void sk_psock_verdict_data_ready(struct sock *sk)
{
struct socket *sock = sk->sk_socket;
net: annotate data-races around sock->ops IPV6_ADDRFORM socket option is evil, because it can change sock->ops while other threads might read it. Same issue for sk->sk_family being set to AF_INET. Adding READ_ONCE() over sock->ops reads is needed for sockets that might be impacted by IPV6_ADDRFORM. Note that mptcp_is_tcpsk() can also overwrite sock->ops. Adding annotations for all sk->sk_family reads will require more patches :/ BUG: KCSAN: data-race in ____sys_sendmsg / do_ipv6_setsockopt write to 0xffff888109f24ca0 of 8 bytes by task 4470 on cpu 0: do_ipv6_setsockopt+0x2c5e/0x2ce0 net/ipv6/ipv6_sockglue.c:491 ipv6_setsockopt+0x57/0x130 net/ipv6/ipv6_sockglue.c:1012 udpv6_setsockopt+0x95/0xa0 net/ipv6/udp.c:1690 sock_common_setsockopt+0x61/0x70 net/core/sock.c:3663 __sys_setsockopt+0x1c3/0x230 net/socket.c:2273 __do_sys_setsockopt net/socket.c:2284 [inline] __se_sys_setsockopt net/socket.c:2281 [inline] __x64_sys_setsockopt+0x66/0x80 net/socket.c:2281 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd read to 0xffff888109f24ca0 of 8 bytes by task 4469 on cpu 1: sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x349/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmmsg+0x263/0x500 net/socket.c:2643 __do_sys_sendmmsg net/socket.c:2672 [inline] __se_sys_sendmmsg net/socket.c:2669 [inline] __x64_sys_sendmmsg+0x57/0x60 net/socket.c:2669 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd value changed: 0xffffffff850e32b8 -> 0xffffffff850da890 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 4469 Comm: syz-executor.1 Not tainted 6.4.0-rc5-syzkaller-00313-g4c605260bc60 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/25/2023 Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com> Link: https://lore.kernel.org/r/20230808135809.2300241-1-edumazet@google.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2023-08-08 13:58:09 +00:00
const struct proto_ops *ops;
bpf, sockmap: Wake up polling after data copy When TCP stack has data ready to read sk_data_ready() is called. Sockmap overwrites this with its own handler to call into BPF verdict program. But, the original TCP socket had sock_def_readable that would additionally wake up any user space waiters with sk_wake_async(). Sockmap saved the callback when the socket was created so call the saved data ready callback and then we can wake up any epoll() logic waiting on the read. Note we call on 'copied >= 0' to account for returning 0 when a FIN is received because we need to wake up user for this as well so they can do the recvmsg() -> 0 and detect the shutdown. Fixes: 04919bed948dc ("tcp: Introduce tcp_read_skb()") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20230523025618.113937-8-john.fastabend@gmail.com
2023-05-23 02:56:11 +00:00
int copied;
bpf, sockmap: Allow skipping sk_skb parser program Currently, we often run with a nop parser namely one that just does this, 'return skb->len'. This happens when either our verdict program can handle streaming data or it is only looking at socket data such as IP addresses and other metadata associated with the flow. The second case is common for a L3/L4 proxy for instance. So lets allow loading programs without the parser then we can skip the stream parser logic and avoid having to add a BPF program that is effectively a nop. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/160239297866.8495.13345662302749219672.stgit@john-Precision-5820-Tower
2020-10-11 05:09:38 +00:00
net/sock: Introduce trace_sk_data_ready() As suggested by Cong, introduce a tracepoint for all ->sk_data_ready() callback implementations. For example: <...> iperf-609 [002] ..... 70.660425: sk_data_ready: family=2 protocol=6 func=sock_def_readable iperf-609 [002] ..... 70.660436: sk_data_ready: family=2 protocol=6 func=sock_def_readable <...> Suggested-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Peilin Ye <peilin.ye@bytedance.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-01-20 00:45:16 +00:00
trace_sk_data_ready(sk);
net: annotate data-races around sock->ops IPV6_ADDRFORM socket option is evil, because it can change sock->ops while other threads might read it. Same issue for sk->sk_family being set to AF_INET. Adding READ_ONCE() over sock->ops reads is needed for sockets that might be impacted by IPV6_ADDRFORM. Note that mptcp_is_tcpsk() can also overwrite sock->ops. Adding annotations for all sk->sk_family reads will require more patches :/ BUG: KCSAN: data-race in ____sys_sendmsg / do_ipv6_setsockopt write to 0xffff888109f24ca0 of 8 bytes by task 4470 on cpu 0: do_ipv6_setsockopt+0x2c5e/0x2ce0 net/ipv6/ipv6_sockglue.c:491 ipv6_setsockopt+0x57/0x130 net/ipv6/ipv6_sockglue.c:1012 udpv6_setsockopt+0x95/0xa0 net/ipv6/udp.c:1690 sock_common_setsockopt+0x61/0x70 net/core/sock.c:3663 __sys_setsockopt+0x1c3/0x230 net/socket.c:2273 __do_sys_setsockopt net/socket.c:2284 [inline] __se_sys_setsockopt net/socket.c:2281 [inline] __x64_sys_setsockopt+0x66/0x80 net/socket.c:2281 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd read to 0xffff888109f24ca0 of 8 bytes by task 4469 on cpu 1: sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x349/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmmsg+0x263/0x500 net/socket.c:2643 __do_sys_sendmmsg net/socket.c:2672 [inline] __se_sys_sendmmsg net/socket.c:2669 [inline] __x64_sys_sendmmsg+0x57/0x60 net/socket.c:2669 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd value changed: 0xffffffff850e32b8 -> 0xffffffff850da890 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 4469 Comm: syz-executor.1 Not tainted 6.4.0-rc5-syzkaller-00313-g4c605260bc60 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/25/2023 Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com> Link: https://lore.kernel.org/r/20230808135809.2300241-1-edumazet@google.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2023-08-08 13:58:09 +00:00
if (unlikely(!sock))
bpf, sockmap: Allow skipping sk_skb parser program Currently, we often run with a nop parser namely one that just does this, 'return skb->len'. This happens when either our verdict program can handle streaming data or it is only looking at socket data such as IP addresses and other metadata associated with the flow. The second case is common for a L3/L4 proxy for instance. So lets allow loading programs without the parser then we can skip the stream parser logic and avoid having to add a BPF program that is effectively a nop. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/160239297866.8495.13345662302749219672.stgit@john-Precision-5820-Tower
2020-10-11 05:09:38 +00:00
return;
net: annotate data-races around sock->ops IPV6_ADDRFORM socket option is evil, because it can change sock->ops while other threads might read it. Same issue for sk->sk_family being set to AF_INET. Adding READ_ONCE() over sock->ops reads is needed for sockets that might be impacted by IPV6_ADDRFORM. Note that mptcp_is_tcpsk() can also overwrite sock->ops. Adding annotations for all sk->sk_family reads will require more patches :/ BUG: KCSAN: data-race in ____sys_sendmsg / do_ipv6_setsockopt write to 0xffff888109f24ca0 of 8 bytes by task 4470 on cpu 0: do_ipv6_setsockopt+0x2c5e/0x2ce0 net/ipv6/ipv6_sockglue.c:491 ipv6_setsockopt+0x57/0x130 net/ipv6/ipv6_sockglue.c:1012 udpv6_setsockopt+0x95/0xa0 net/ipv6/udp.c:1690 sock_common_setsockopt+0x61/0x70 net/core/sock.c:3663 __sys_setsockopt+0x1c3/0x230 net/socket.c:2273 __do_sys_setsockopt net/socket.c:2284 [inline] __se_sys_setsockopt net/socket.c:2281 [inline] __x64_sys_setsockopt+0x66/0x80 net/socket.c:2281 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd read to 0xffff888109f24ca0 of 8 bytes by task 4469 on cpu 1: sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x349/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmmsg+0x263/0x500 net/socket.c:2643 __do_sys_sendmmsg net/socket.c:2672 [inline] __se_sys_sendmmsg net/socket.c:2669 [inline] __x64_sys_sendmmsg+0x57/0x60 net/socket.c:2669 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd value changed: 0xffffffff850e32b8 -> 0xffffffff850da890 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 4469 Comm: syz-executor.1 Not tainted 6.4.0-rc5-syzkaller-00313-g4c605260bc60 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/25/2023 Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com> Link: https://lore.kernel.org/r/20230808135809.2300241-1-edumazet@google.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2023-08-08 13:58:09 +00:00
ops = READ_ONCE(sock->ops);
if (!ops || !ops->read_skb)
return;
copied = ops->read_skb(sk, sk_psock_verdict_recv);
bpf, sockmap: Wake up polling after data copy When TCP stack has data ready to read sk_data_ready() is called. Sockmap overwrites this with its own handler to call into BPF verdict program. But, the original TCP socket had sock_def_readable that would additionally wake up any user space waiters with sk_wake_async(). Sockmap saved the callback when the socket was created so call the saved data ready callback and then we can wake up any epoll() logic waiting on the read. Note we call on 'copied >= 0' to account for returning 0 when a FIN is received because we need to wake up user for this as well so they can do the recvmsg() -> 0 and detect the shutdown. Fixes: 04919bed948dc ("tcp: Introduce tcp_read_skb()") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20230523025618.113937-8-john.fastabend@gmail.com
2023-05-23 02:56:11 +00:00
if (copied >= 0) {
struct sk_psock *psock;
rcu_read_lock();
psock = sk_psock(sk);
bpf, skmsg: Fix NULL pointer dereference in sk_psock_skb_ingress_enqueue Fix NULL pointer data-races in sk_psock_skb_ingress_enqueue() which syzbot reported [1]. [1] BUG: KCSAN: data-race in sk_psock_drop / sk_psock_skb_ingress_enqueue write to 0xffff88814b3278b8 of 8 bytes by task 10724 on cpu 1: sk_psock_stop_verdict net/core/skmsg.c:1257 [inline] sk_psock_drop+0x13e/0x1f0 net/core/skmsg.c:843 sk_psock_put include/linux/skmsg.h:459 [inline] sock_map_close+0x1a7/0x260 net/core/sock_map.c:1648 unix_release+0x4b/0x80 net/unix/af_unix.c:1048 __sock_release net/socket.c:659 [inline] sock_close+0x68/0x150 net/socket.c:1421 __fput+0x2c1/0x660 fs/file_table.c:422 __fput_sync+0x44/0x60 fs/file_table.c:507 __do_sys_close fs/open.c:1556 [inline] __se_sys_close+0x101/0x1b0 fs/open.c:1541 __x64_sys_close+0x1f/0x30 fs/open.c:1541 do_syscall_64+0xd3/0x1d0 entry_SYSCALL_64_after_hwframe+0x6d/0x75 read to 0xffff88814b3278b8 of 8 bytes by task 10713 on cpu 0: sk_psock_data_ready include/linux/skmsg.h:464 [inline] sk_psock_skb_ingress_enqueue+0x32d/0x390 net/core/skmsg.c:555 sk_psock_skb_ingress_self+0x185/0x1e0 net/core/skmsg.c:606 sk_psock_verdict_apply net/core/skmsg.c:1008 [inline] sk_psock_verdict_recv+0x3e4/0x4a0 net/core/skmsg.c:1202 unix_read_skb net/unix/af_unix.c:2546 [inline] unix_stream_read_skb+0x9e/0xf0 net/unix/af_unix.c:2682 sk_psock_verdict_data_ready+0x77/0x220 net/core/skmsg.c:1223 unix_stream_sendmsg+0x527/0x860 net/unix/af_unix.c:2339 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg+0x140/0x180 net/socket.c:745 ____sys_sendmsg+0x312/0x410 net/socket.c:2584 ___sys_sendmsg net/socket.c:2638 [inline] __sys_sendmsg+0x1e9/0x280 net/socket.c:2667 __do_sys_sendmsg net/socket.c:2676 [inline] __se_sys_sendmsg net/socket.c:2674 [inline] __x64_sys_sendmsg+0x46/0x50 net/socket.c:2674 do_syscall_64+0xd3/0x1d0 entry_SYSCALL_64_after_hwframe+0x6d/0x75 value changed: 0xffffffff83d7feb0 -> 0x0000000000000000 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 10713 Comm: syz-executor.4 Tainted: G W 6.8.0-syzkaller-08951-gfe46a7dd189e #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 02/29/2024 Prior to this, commit 4cd12c6065df ("bpf, sockmap: Fix NULL pointer dereference in sk_psock_verdict_data_ready()") fixed one NULL pointer similarly due to no protection of saved_data_ready. Here is another different caller causing the same issue because of the same reason. So we should protect it with sk_callback_lock read lock because the writer side in the sk_psock_drop() uses "write_lock_bh(&sk->sk_callback_lock);". To avoid errors that could happen in future, I move those two pairs of lock into the sk_psock_data_ready(), which is suggested by John Fastabend. Fixes: 604326b41a6f ("bpf, sockmap: convert to generic sk_msg interface") Reported-by: syzbot+aa8c8ec2538929f18f2d@syzkaller.appspotmail.com Signed-off-by: Jason Xing <kernelxing@tencent.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: John Fastabend <john.fastabend@gmail.com> Closes: https://syzkaller.appspot.com/bug?extid=aa8c8ec2538929f18f2d Link: https://lore.kernel.org/all/20240329134037.92124-1-kerneljasonxing@gmail.com Link: https://lore.kernel.org/bpf/20240404021001.94815-1-kerneljasonxing@gmail.com
2024-04-04 02:10:01 +00:00
if (psock)
bpf, sockmap: Fix NULL pointer dereference in sk_psock_verdict_data_ready() syzbot reported the following NULL pointer dereference issue [1]: BUG: kernel NULL pointer dereference, address: 0000000000000000 [...] RIP: 0010:0x0 [...] Call Trace: <TASK> sk_psock_verdict_data_ready+0x232/0x340 net/core/skmsg.c:1230 unix_stream_sendmsg+0x9b4/0x1230 net/unix/af_unix.c:2293 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg+0x221/0x270 net/socket.c:745 ____sys_sendmsg+0x525/0x7d0 net/socket.c:2584 ___sys_sendmsg net/socket.c:2638 [inline] __sys_sendmsg+0x2b0/0x3a0 net/socket.c:2667 do_syscall_64+0xf9/0x240 entry_SYSCALL_64_after_hwframe+0x6f/0x77 If sk_psock_verdict_data_ready() and sk_psock_stop_verdict() are called concurrently, psock->saved_data_ready can be NULL, causing the above issue. This patch fixes this issue by calling the appropriate data ready function using the sk_psock_data_ready() helper and protecting it from concurrency with sk->sk_callback_lock. Fixes: 6df7f764cd3c ("bpf, sockmap: Wake up polling after data copy") Reported-by: syzbot+fd7b34375c1c8ce29c93@syzkaller.appspotmail.com Signed-off-by: Shigeru Yoshida <syoshida@redhat.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Tested-by: syzbot+fd7b34375c1c8ce29c93@syzkaller.appspotmail.com Acked-by: John Fastabend <john.fastabend@gmail.com> Closes: https://syzkaller.appspot.com/bug?extid=fd7b34375c1c8ce29c93 [1] Link: https://lore.kernel.org/bpf/20240218150933.6004-1-syoshida@redhat.com
2024-02-18 15:09:33 +00:00
sk_psock_data_ready(sk, psock);
bpf, sockmap: Wake up polling after data copy When TCP stack has data ready to read sk_data_ready() is called. Sockmap overwrites this with its own handler to call into BPF verdict program. But, the original TCP socket had sock_def_readable that would additionally wake up any user space waiters with sk_wake_async(). Sockmap saved the callback when the socket was created so call the saved data ready callback and then we can wake up any epoll() logic waiting on the read. Note we call on 'copied >= 0' to account for returning 0 when a FIN is received because we need to wake up user for this as well so they can do the recvmsg() -> 0 and detect the shutdown. Fixes: 04919bed948dc ("tcp: Introduce tcp_read_skb()") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20230523025618.113937-8-john.fastabend@gmail.com
2023-05-23 02:56:11 +00:00
rcu_read_unlock();
}
bpf, sockmap: Allow skipping sk_skb parser program Currently, we often run with a nop parser namely one that just does this, 'return skb->len'. This happens when either our verdict program can handle streaming data or it is only looking at socket data such as IP addresses and other metadata associated with the flow. The second case is common for a L3/L4 proxy for instance. So lets allow loading programs without the parser then we can skip the stream parser logic and avoid having to add a BPF program that is effectively a nop. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/160239297866.8495.13345662302749219672.stgit@john-Precision-5820-Tower
2020-10-11 05:09:38 +00:00
}
void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock)
{
skmsg: Get rid of struct sk_psock_parser struct sk_psock_parser is embedded in sk_psock, it is unnecessary as skb verdict also uses ->saved_data_ready. We can simply fold these fields into sk_psock, and get rid of ->enabled. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-3-xiyou.wangcong@gmail.com
2021-02-23 18:49:27 +00:00
if (psock->saved_data_ready)
bpf, sockmap: Allow skipping sk_skb parser program Currently, we often run with a nop parser namely one that just does this, 'return skb->len'. This happens when either our verdict program can handle streaming data or it is only looking at socket data such as IP addresses and other metadata associated with the flow. The second case is common for a L3/L4 proxy for instance. So lets allow loading programs without the parser then we can skip the stream parser logic and avoid having to add a BPF program that is effectively a nop. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/160239297866.8495.13345662302749219672.stgit@john-Precision-5820-Tower
2020-10-11 05:09:38 +00:00
return;
skmsg: Get rid of struct sk_psock_parser struct sk_psock_parser is embedded in sk_psock, it is unnecessary as skb verdict also uses ->saved_data_ready. We can simply fold these fields into sk_psock, and get rid of ->enabled. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-3-xiyou.wangcong@gmail.com
2021-02-23 18:49:27 +00:00
psock->saved_data_ready = sk->sk_data_ready;
bpf, sockmap: Allow skipping sk_skb parser program Currently, we often run with a nop parser namely one that just does this, 'return skb->len'. This happens when either our verdict program can handle streaming data or it is only looking at socket data such as IP addresses and other metadata associated with the flow. The second case is common for a L3/L4 proxy for instance. So lets allow loading programs without the parser then we can skip the stream parser logic and avoid having to add a BPF program that is effectively a nop. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/160239297866.8495.13345662302749219672.stgit@john-Precision-5820-Tower
2020-10-11 05:09:38 +00:00
sk->sk_data_ready = sk_psock_verdict_data_ready;
sk->sk_write_space = sk_psock_write_space;
}
void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock)
{
bpf, sockmap: Re-evaluate proto ops when psock is removed from sockmap When a sock is added to a sock map we evaluate what proto op hooks need to be used. However, when the program is removed from the sock map we have not been evaluating if that changes the required program layout. Before the patch listed in the 'fixes' tag this was not causing failures because the base program set handles all cases. Specifically, the case with a stream parser and the case with out a stream parser are both handled. With the fix below we identified a race when running with a proto op that attempts to read skbs off both the stream parser and the skb->receive_queue. Namely, that a race existed where when the stream parser is empty checking the skb->receive_queue from recvmsg at the precies moment when the parser is paused and the receive_queue is not empty could result in skipping the stream parser. This may break a RX policy depending on the parser to run. The fix tag then loads a specific proto ops that resolved this race. But, we missed removing that proto ops recv hook when the sock is removed from the sockmap. The result is the stream parser is stopped so no more skbs will be aggregated there, but the hook and BPF program continues to be attached on the psock. User space will then get an EBUSY when trying to read the socket because the recvmsg() handler is now waiting on a stopped stream parser. To fix we rerun the proto ops init() function which will look at the new set of progs attached to the psock and rest the proto ops hook to the correct handlers. And in the above case where we remove the sock from the sock map the RX prog will no longer be listed so the proto ops is removed. Fixes: c5d2177a72a16 ("bpf, sockmap: Fix race in ingress receive verdict with redirect to self") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20211119181418.353932-3-john.fastabend@gmail.com
2021-11-19 18:14:18 +00:00
psock_set_prog(&psock->progs.stream_verdict, NULL);
psock_set_prog(&psock->progs.skb_verdict, NULL);
skmsg: Get rid of struct sk_psock_parser struct sk_psock_parser is embedded in sk_psock, it is unnecessary as skb verdict also uses ->saved_data_ready. We can simply fold these fields into sk_psock, and get rid of ->enabled. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-3-xiyou.wangcong@gmail.com
2021-02-23 18:49:27 +00:00
if (!psock->saved_data_ready)
bpf, sockmap: Allow skipping sk_skb parser program Currently, we often run with a nop parser namely one that just does this, 'return skb->len'. This happens when either our verdict program can handle streaming data or it is only looking at socket data such as IP addresses and other metadata associated with the flow. The second case is common for a L3/L4 proxy for instance. So lets allow loading programs without the parser then we can skip the stream parser logic and avoid having to add a BPF program that is effectively a nop. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/160239297866.8495.13345662302749219672.stgit@john-Precision-5820-Tower
2020-10-11 05:09:38 +00:00
return;
skmsg: Get rid of struct sk_psock_parser struct sk_psock_parser is embedded in sk_psock, it is unnecessary as skb verdict also uses ->saved_data_ready. We can simply fold these fields into sk_psock, and get rid of ->enabled. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20210223184934.6054-3-xiyou.wangcong@gmail.com
2021-02-23 18:49:27 +00:00
sk->sk_data_ready = psock->saved_data_ready;
psock->saved_data_ready = NULL;
bpf, sockmap: Allow skipping sk_skb parser program Currently, we often run with a nop parser namely one that just does this, 'return skb->len'. This happens when either our verdict program can handle streaming data or it is only looking at socket data such as IP addresses and other metadata associated with the flow. The second case is common for a L3/L4 proxy for instance. So lets allow loading programs without the parser then we can skip the stream parser logic and avoid having to add a BPF program that is effectively a nop. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/160239297866.8495.13345662302749219672.stgit@john-Precision-5820-Tower
2020-10-11 05:09:38 +00:00
}