net-timestamp: bpf extension to equip applications transparently
Subsystems (10)
v9 cover net-timestamp: bpf extension to equip applications transparently
"Timestamping is key to debugging network stack latency. With SO_TIMESTAMPING, bugs that are otherwise incorrectly assumed to be network issues can be attributed to the kernel." This is extracted from the talk "SO_TIMESTAMPING: Powering Fleetwide RPC Monitoring" addressed by Willem de Bruijn at netdevconf 0x17).
There are a few areas that need optimization with the consideration of easier use and less performance impact, which I highlighted and mainly discussed at netconf 2024 with Willem de Bruijn and John Fastabend:
uAPI compatibility, extra system call overhead, and the need for application modification. I initially managed to solve these issues by writing a kernel module that hooks various key functions. However, this approach is not suitable for the next kernel release. Therefore, a BPF extension was proposed. During recent period, Martin KaFai Lau provides invaluable suggestions about BPF along the way. Many thanks here!
In this series, only support foundamental codes and tx for TCP. This approach mostly relies on existing SO_TIMESTAMPING feature, users only needs to pass certain flags through bpf_setsocktopt() to a separate tsflags. Please see the last selftest patch in this series.
---
v8
1. adjust some commit messages and titles
2. add sk cookie in selftests
3. handle the NULL pointer in hwstamp
4. use kfunc to do selective sampling
v7
1. target bpf-next tree
2. simplely and directly stop timestamping callbacks calling a few BPF CALLS due to safety concern.
3. add more new testcases and adjust the existing testcases
4. revise some comments of new timestamping callbacks
5. remove a few BPF CGROUP locks
RFC v6
In the meantime, any suggestions and reviews are welcome!
1. handle those safety problem by using the correct method.
2. support bpf_getsockopt.
3. adjust the position of BPF_SOCK_OPS_TS_TCP_SND_CB
4. fix mishandling the hardware timestamp error
5. add more corresponding tests
v5
1. handle the safety issus when someone tries to call unrelated bpf helpers.
2. avoid adding direct function call in the hot path like __dev_queue_xmit()
3. remove reporting the hardware timestamp and tskey since they can be fetched through the existing helper with the help of bpf_skops_init_skb(), please see the selftest.
4. add new sendmsg callback in tcp_sendmsg, and introduce tskey_bpf used by bpf program to correlate tcp_sendmsg with other hook points in patch [13/15].
v4
1. introduce sk->sk_bpf_cb_flags to let user use bpf_setsockopt() (Martin)
2. introduce SKBTX_BPF to enable the bpf SO_TIMESTAMPING feature (Martin)
3. introduce bpf map in tests (Martin)
4. I choose to make this series as simple as possible, so I only support most cases in the tx path for TCP protocol.
v3
1. support UDP proto by introducing a new generation point.
2. for OPT_ID, introducing sk_tskey_bpf_offset to compute the delta between the current socket key and bpf socket key. It is desiged for UDP, which also applies to TCP.
3. support bpf_getsockopt()
4. use cgroup static key instead.
5. add one simple bpf selftest to show how it can be used.
6. remove the rx support from v2 because the number of patches could exceed the limit of one series.
V2
1. Introduce tsflag requestors so that we are able to extend more in the future. Besides, it enables TX flags for bpf extension feature separately without breaking users. It is suggested by Vadim Fedorenko.
2. introduce a static key to control the whole feature. (Willem)
3. Open the gate of bpf_setsockopt for the SO_TIMESTAMPING feature in some TX/RX cases, not all the cases.
Jason Xing (12):
bpf: add support for bpf_setsockopt()
bpf: prepare for timestamping callbacks use
bpf: stop unsafely accessing TCP fields in bpf callbacks
bpf: stop calling some sock_op BPF CALLs in new timestamping callbacks
net-timestamp: prepare for isolating two modes of SO_TIMESTAMPING
bpf: support SCM_TSTAMP_SCHED of SO_TIMESTAMPING
bpf: support sw SCM_TSTAMP_SND of SO_TIMESTAMPING
bpf: support hw SCM_TSTAMP_SND of SO_TIMESTAMPING
bpf: support SCM_TSTAMP_ACK of SO_TIMESTAMPING
bpf: add a new callback in tcp_tx_timestamp()
bpf: support selective sampling for bpf timestamping selftests/bpf: add simple bpf tests in the tx path for timestamping
feature
include/linux/filter.h | 1 + include/linux/skbuff.h | 12 +- include/net/sock.h | 10 + include/net/tcp.h | 5 +- include/uapi/linux/bpf.h | 30 ++ kernel/bpf/btf.c | 1 + net/core/dev.c | 3 +- net/core/filter.c | 75 ++++- net/core/skbuff.c | 48 ++- net/core/sock.c | 15 + net/dsa/user.c | 2 +- net/ipv4/tcp.c | 4 + net/ipv4/tcp_input.c | 2 + net/ipv4/tcp_output.c | 2 + net/socket.c | 2 +- tools/include/uapi/linux/bpf.h | 23 ++ .../bpf/prog_tests/so_timestamping.c | 79 +++++ .../selftests/bpf/progs/so_timestamping.c | 312 ++++++++++++++++++ 18 files changed, 612 insertions(+), 14 deletions(-) create mode 100644 tools/testing/selftests/bpf/prog_tests/so_timestamping.c create mode 100644 tools/testing/selftests/bpf/progs/so_timestamping.c
Signature · 1 line
2.43.5
PATCH v9 1/12 bpf: add support for bpf_setsockopt()
Users can write the following code to enable the bpf extension:
int flags = SK_BPF_CB_TX_TIMESTAMPING;
int opts = SK_BPF_CB_FLAGS;bpf_setsockopt(skops, SOL_SOCKET, opts, &flags, sizeof(flags));
--- include/net/sock.h | 3 +++ include/uapi/linux/bpf.h | 8 ++++++++ net/core/filter.c | 23 +++++++++++++++++++++++ tools/include/uapi/linux/bpf.h | 1 + 4 files changed, 35 insertions(+)
include/net/sock.h +3 -0
@@ -303,6 +303,7 @@ struct sk_filter;* @sk_stamp: time stamp of last packet received * @sk_stamp_seq: lock for accessing sk_stamp on 32 bit architectures only * @sk_tsflags: SO_TIMESTAMPING flags +* @sk_bpf_cb_flags: used in bpf_setsockopt() * @sk_use_task_frag: allow sk_page_frag() to use current->task_frag. * Sockets that can be used under memory reclaim should * set this to false.
@@ -445,6 +446,8 @@ struct sock {u32 sk_reserved_mem;int sk_forward_alloc;u32 sk_tsflags; +#define SK_BPF_CB_FLAG_TEST (SK ,FLAG ) ((SK)->sk_bpf_cb_flags & (FLAG)) +u32 sk_bpf_cb_flags;__cacheline_group_end (sock_write_rxtx);__cacheline_group_begin (sock_write_tx);
include/uapi/linux/bpf.h +8 -0
@@ -6913,6 +6913,13 @@ enum { BPF_SOCK_OPS_ALL_CB_FLAGS = 0x7F, }; +/* Definitions for bpf_sk_cb_flags */ +enum { +SK_BPF_CB_TX_TIMESTAMPING =1 <<0 , +SK_BPF_CB_MASK = (SK_BPF_CB_TX_TIMESTAMPING -1 ) | +SK_BPF_CB_TX_TIMESTAMPING +}; +/* List of known BPF sock_ops operators. * New entries can only be added at the end */
@@ -7091,6 +7098,7 @@ enum {TCP_BPF_SYN_IP =1006 ,/* Copy the IP[46] and TCP header */ TCP_BPF_SYN_MAC =1007 ,/* Copy the MAC, IP[46], and TCP header */ TCP_BPF_SOCK_OPS_CB_FLAGS =1008 ,/* Get or Set TCP sock ops flags */ + SK_BPF_CB_FLAGS = 1009, /* Used to set socket bpf flags */ }; enum {
net/core/filter.c +23 -0
@@ -5222,6 +5222,25 @@ static const struct bpf_func_proto bpf_get_socket_uid_proto = { .arg1_type = ARG_PTR_TO_CTX, }; +static int sk_bpf_set_get_cb_flags (struct sock *sk,char *optval,bool getopt) +{ +u32 sk_bpf_cb_flags; + +if (getopt) { + *(u32 *)optval = sk->sk_bpf_cb_flags; +return 0 ; + } + + sk_bpf_cb_flags = *(u32 *)optval; + +if (sk_bpf_cb_flags & ~SK_BPF_CB_MASK ) +return -EINVAL ; + + sk->sk_bpf_cb_flags = sk_bpf_cb_flags; + +return 0 ; +} +static int sol_socket_sockopt (struct sock *sk,int optname,char *optval,int *optlen,bool getopt)
@@ -5238,6 +5257,7 @@ static int sol_socket_sockopt(struct sock *sk, int optname,case SO_MAX_PACING_RATE :case SO_BINDTOIFINDEX :case SO_TXREHASH : +case SK_BPF_CB_FLAGS :if (*optlen !=sizeof (int ))return -EINVAL ;break ;
@@ -5247,6 +5267,9 @@ static int sol_socket_sockopt(struct sock *sk, int optname,return -EINVAL ; } +if (optname ==SK_BPF_CB_FLAGS ) +return sk_bpf_set_get_cb_flags (sk, optval, getopt); +if (getopt) {if (optname ==SO_BINDTODEVICE )return -EINVAL ;
tools/include/uapi/linux/bpf.h +1 -0
@@ -7091,6 +7091,7 @@ enum {TCP_BPF_SYN_IP =1006 ,/* Copy the IP[46] and TCP header */ TCP_BPF_SYN_MAC =1007 ,/* Copy the MAC, IP[46], and TCP header */ TCP_BPF_SOCK_OPS_CB_FLAGS =1008 ,/* Get or Set TCP sock ops flags */ + SK_BPF_CB_FLAGS = 1009, /* Used to set socket bpf flags */ }; enum {
Signature · 1 line
2.43.5
Martin KaFai Lau
reviewerRe: [PATCH bpf-next v9 01/12] bpf: add support for bpf_setsockopt()
Quoted 4 lines · Jason Xing
Users can write the following code to enable the bpf extension:
int flags =SK_BPF_CB_TX_TIMESTAMPING;
int opts =SK_BPF_CB_FLAGS;bpf_setsockopt(skops, SOL_SOCKET, opts, &flags, sizeof(flags));
The commit message should explain what is added/changed and why it is needed.
The above only tells how it is used, and the subject "bpf: add support for bpf_setsockopt()" is unclear. Add what support? Also, both get- and set-sockopt() are changed.
Subject: "bpf: Add networking timestamping support to bpf_get/setsockopt()"
What: The new SK_BPF_CB_FLAGS and new SK_BPF_CB_TX_TIMESTAMPING are added to bpf_get/setsockopt.
Why: The later patch will implement the BPF networking timestamping. The BPF program will use bpf_setsockopt(SK_BPF_CB_FLAGS, SK_BPF_CB_TX_TIMESTAMPING) to enable the BPF networking timestamping on a socket.
Re: [PATCH bpf-next v9 01/12] bpf: add support for bpf_setsockopt()
Quoted 12 lines · Martin KaFai Lau
Quoted 4 lines · Jason Xing
Users can write the following code to enable the bpf extension:
int flags =SK_BPF_CB_TX_TIMESTAMPING;
int opts =SK_BPF_CB_FLAGS;bpf_setsockopt(skops, SOL_SOCKET, opts, &flags, sizeof(flags));The commit message should explain what is added/changed and why it is needed. The above only tells how it is used, and the subject "bpf: add support for
bpf_setsockopt()" is unclear. Add what support? Also, both get- and set-sockopt() are changed.
Quoted 8 lines
Subject: "bpf: Add networking timestamping support to bpf_get/setsockopt()"
What: The new
SK_BPF_CB_FLAGSand newSK_BPF_CB_TX_TIMESTAMPINGare added to bpf_get/setsockopt.Why: The later patch will implement the BPF networking timestamping. The BPF program will use
bpf_setsockopt(SK_BPF_CB_FLAGS, SK_BPF_CB_TX_TIMESTAMPING)to enable the BPF networking timestamping on a socket.
Thanks. Learning a lot on how to write a good description, I will adjust commit messages as you suggested.
Thanks,
Jason
PATCH v9 2/12 bpf: prepare for timestamping callbacks use
In reply to Jason XingLater, four callback points to report information to user space based on this patch will be introduced.
As to skb initialization here, users can follow these three steps as below to fetch the shared info from the exported skb in the bpf prog:
1. skops_kern = bpf_cast_to_kern_ctx(skops);
2. skb = skops_kern->skb;
3. shinfo = bpf_core_cast(skb->head + skb->end, struct skb_shared_info);
More details can be seen in the last selftest patch of the series.
--- include/net/sock.h | 7 +++++++ net/core/sock.c | 15 +++++++++++++++ 2 files changed, 22 insertions(+)
include/net/sock.h +7 -0
@@ -2923,6 +2923,13 @@ int sock_set_timestamping(struct sock *sk, int optname, struct so_timestamping timestamping);void sock_enable_timestamps (struct sock *sk); +#if defined(CONFIG_CGROUP_BPF ) +void bpf_skops_tx_timestamping (struct sock *sk,struct sk_buff *skb,int op); +#else +static inline void bpf_skops_tx_timestamping (struct sock *sk,struct sk_buff *skb,int op) +{ +} +#endif void sock_no_linger (struct sock *sk);void sock_set_keepalive (struct sock *sk);void sock_set_priority (struct sock *sk,u32 priority);
net/core/sock.c +15 -0
@@ -948,6 +948,21 @@ int sock_set_timestamping(struct sock *sk, int optname,return 0 ; } +#if defined(CONFIG_CGROUP_BPF ) +void bpf_skops_tx_timestamping (struct sock *sk,struct sk_buff *skb,int op) +{ +struct bpf_sock_ops_kern sock_ops; + +memset (&sock_ops,0 , offsetof(struct bpf_sock_ops_kern , temp)); + sock_ops.op = op; + sock_ops.is_fullsock =1 ; + sock_ops.sk = sk; +bpf_skops_init_skb (&sock_ops, skb,0 ); +/* Timestamping bpf extension supports only TCP and UDP full socket */ +__cgroup_bpf_run_filter_sock_ops (sk, &sock_ops,CGROUP_SOCK_OPS ); +} +#endif +void sock_set_keepalive (struct sock *sk) {lock_sock (sk);
Signature · 1 line
2.43.5
Martin KaFai Lau
reviewerRe: [PATCH bpf-next v9 02/12] bpf: prepare for timestamping callbacks use
Quoted 11 lines · Jason Xing
Later, four callback points to report information to user space based on this patch will be introduced.
As to skb initialization here, users can follow these three steps as below to fetch the shared info from the exported skb in the bpf prog:
1.skops_kern=bpf_cast_to_kern_ctx(skops);
2. skb =skops_kern->skb;
3. shinfo =bpf_core_cast(skb->head + skb->end, struct skb_shared_info);More details can be seen in the last selftest patch of the series.
This BPF program example is not useful in this commit message. It is not how this change will be used in the kernel. People will naturally be required to look at the selftest to see how the bpf prog can get to the skb and tskey, etc.
The commit message should focus on explaining "what" has changed and "why" it is necessary. The "why" part ("four callback points to report...") is mostly present but could be clearer.
Subject: bpf: Prepare the sock_ops ctx and call bpf prog for TX timestamping
(What)
This patch introduces a new bpf_skops_tx_timestamping() function that prepares the "struct bpf_sock_ops" ctx and then executes the sockops BPF program.
(Why)
The subsequent patch will utilize bpf_skops_tx_timestamping() at the existing TX timestamping kernel callbacks (__sk_tstamp_tx specifically) to call the sockops BPF program.
Quoted 34 lines
Signed-off-by Jason Xing <[email protected]>--- include/net/sock.h | 7 +++++++ net/core/sock.c | 15 +++++++++++++++ 2 files changed, 22 insertions(+)include/net/sock.h +7
-0@@ -2923,6 +2923,13 @@ int sock_set_timestamping(struct sock *sk, int optname, struct so_timestamping timestamping);void sock_enable_timestamps (struct sock *sk); +#if defined(CONFIG_CGROUP_BPF ) +void bpf_skops_tx_timestamping (struct sock *sk,struct sk_buff *skb,int op); +#else +static inline void bpf_skops_tx_timestamping (struct sock *sk,struct sk_buff *skb,int op) +{ +} +#endif void sock_no_linger (struct sock *sk);void sock_set_keepalive (struct sock *sk);void sock_set_priority (struct sock *sk,u32 priority);net/core/sock.c +1
-0@@ -948,6 +948,21 @@ int sock_set_timestamping(struct sock *sk, int optname,return 0 ; } +#if defined(CONFIG_CGROUP_BPF )
net/core/sock.c int sock_set_timestamping(struct sock *sk, int optname, · line 961
Quoted 10 lines
net/core/sock.c +10
-0+void bpf_skops_tx_timestamping (struct sock *sk,struct sk_buff *skb,int op) +{ +struct bpf_sock_ops_kern sock_ops; + +memset (&sock_ops,0 , offsetof(struct bpf_sock_ops_kern , temp)); + sock_ops.op = op; + sock_ops.is_fullsock =1 ; + sock_ops.sk = sk; +bpf_skops_init_skb (&sock_ops, skb,0 ); +/* Timestamping bpf extension supports only TCP and UDP full socket */
nit: After our earlier discussions, it's clear that the above is_fullsock = 1; is always true for all sk here. This comment has become redundant. Let's remove it.
Quoted 7 lines
net/core/sock.c +4
-0+ __cgroup_bpf_run_filter_sock_ops(sk, &sock_ops, CGROUP_SOCK_OPS); +} +#endif +void sock_set_keepalive (struct sock *sk) {lock_sock (sk);
Re: [PATCH bpf-next v9 02/12] bpf: prepare for timestamping callbacks use
Quoted 24 lines · Martin KaFai Lau
Quoted 11 lines · Jason Xing
Later, four callback points to report information to user space based on this patch will be introduced.
As to skb initialization here, users can follow these three steps as below to fetch the shared info from the exported skb in the bpf prog:
1.skops_kern=bpf_cast_to_kern_ctx(skops);
2. skb =skops_kern->skb;
3. shinfo =bpf_core_cast(skb->head + skb->end, struct skb_shared_info);More details can be seen in the last selftest patch of the series.
This BPF program example is not useful in this commit message. It is not how this change will be used in the kernel. People will naturally be required to look at the selftest to see how the bpf prog can get to the skb and tskey, etc.
The commit message should focus on explaining "what" has changed and "why" it is necessary. The "why" part ("four callback points to report...") is mostly present but could be clearer.
Subject: bpf: Prepare the
sock_opsctx and call bpf prog for TX timestamping
Quoted 8 lines
(What)
This patch introduces a newbpf_skops_tx_timestamping()function that prepares the "structbpf_sock_ops" ctx and then executes the sockops BPF program.(Why)
The subsequent patch will utilizebpf_skops_tx_timestamping()at the existing TX timestamping kernel callbacks (__sk_tstamp_txspecifically) to call the sockops BPF program.
Thanks, Will update it.
Quoted 35 lines
Quoted 35 lines
Signed-off-by Jason Xing <[email protected]>--- include/net/sock.h | 7 +++++++ net/core/sock.c | 15 +++++++++++++++ 2 files changed, 22 insertions(+)include/net/sock.h +7
-0@@ -2923,6 +2923,13 @@ int sock_set_timestamping(struct sock *sk, int optname, struct so_timestamping timestamping);void sock_enable_timestamps (struct sock *sk); +#if defined(CONFIG_CGROUP_BPF ) +void bpf_skops_tx_timestamping (struct sock *sk,struct sk_buff *skb,int op); +#else +static inline void bpf_skops_tx_timestamping (struct sock *sk,struct sk_buff *skb,int op) +{ +} +#endif void sock_no_linger (struct sock *sk);void sock_set_keepalive (struct sock *sk);void sock_set_priority (struct sock *sk,u32 priority);net/core/sock.c +0
-0@@ -948,6 +948,21 @@ int sock_set_timestamping(struct sock *sk, int optname,return 0 ; }
Quoted 14 lines
net/core/sock.c int sock_set_timestamping(struct sock *sk, int optname, · line 961
Quoted 11 lines
net/core/sock.c +11
-0+#if defined(CONFIG_CGROUP_BPF ) +void bpf_skops_tx_timestamping (struct sock *sk,struct sk_buff *skb,int op) +{ +struct bpf_sock_ops_kern sock_ops; + +memset (&sock_ops,0 , offsetof(struct bpf_sock_ops_kern , temp)); + sock_ops.op = op; + sock_ops.is_fullsock =1 ; + sock_ops.sk = sk; +bpf_skops_init_skb (&sock_ops, skb,0 ); +/* Timestamping bpf extension supports only TCP and UDP full socket */ nit: After our earlier discussions, it's clear that the above
is_fullsock= 1; is always true for all sk here. This comment has become redundant. Let's remove it.
Will do it.
Thanks,
Jason
Quoted 9 lines
Quoted 8 lines
net/core/sock.c +4
-0+ __cgroup_bpf_run_filter_sock_ops(sk, &sock_ops, CGROUP_SOCK_OPS); +} +#endif +void sock_set_keepalive (struct sock *sk) {lock_sock (sk);
PATCH v9 3/12 bpf: stop unsafely accessing TCP fields in bpf callbacks
In reply to Jason XingThe "is_locked_tcp_sock" flag is added to indicate that the callback site has a tcp_sock locked.
Apply the new member is_locked_tcp_sock in the existing callbacks where is_fullsock is set to 1 can stop UDP socket accessing struct tcp_sock and stop TCP socket without sk lock protecting does the similar thing, or else it could be catastrophe leading to panic.
To keep it simple, instead of distinguishing between read and write access, users aren't allowed all read/write access to the tcp_sock through the older bpf_sock_ops ctx. The new timestamping callbacks can use newer helpers to read everything from a sk (e.g. bpf_core_cast), so nothing is lost.
--- include/linux/filter.h | 1 + include/net/tcp.h | 1 + net/core/filter.c | 8 ++++---- net/ipv4/tcp_input.c | 2 ++ net/ipv4/tcp_output.c | 2 ++ 5 files changed, 10 insertions(+), 4 deletions(-)
include/linux/filter.h +1 -0
@@ -1508,6 +1508,7 @@ struct bpf_sock_ops_kern {void *skb_data_end;u8 op;u8 is_fullsock; +u8 is_locked_tcp_sock;u8 remaining_opt_len;u64 temp;/* temp and everything after is not * initialized to 0 before calling
include/net/tcp.h +1 -0
@@ -2649,6 +2649,7 @@ static inline int tcp_call_bpf(struct sock *sk, int op, u32 nargs, u32 *args)memset (&sock_ops,0 , offsetof(struct bpf_sock_ops_kern , temp));if (sk_fullsock (sk)) { sock_ops.is_fullsock =1 ; + sock_ops.is_locked_tcp_sock =1 ;sock_owned_by_me (sk); }
net/core/filter.c +4 -4
@@ -10381,10 +10381,10 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, } \ *insn++ =BPF_LDX_MEM (BPF_FIELD_SIZEOF ( \ struct bpf_sock_ops_kern, \ - is_fullsock), \ + is_locked_tcp_sock), \ fullsock_reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern , \ - is_fullsock)); \ + is_locked_tcp_sock)); \ *insn++ =BPF_JMP_IMM (BPF_JEQ , fullsock_reg,0 , jmp); \if (si->dst_reg == si->src_reg) \ *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg, \
@@ -10469,10 +10469,10 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, temp)); \ *insn++ =BPF_LDX_MEM (BPF_FIELD_SIZEOF ( \ struct bpf_sock_ops_kern, \ - is_fullsock), \ + is_locked_tcp_sock), \ reg, si->dst_reg, \ offsetof(struct bpf_sock_ops_kern , \ - is_fullsock)); \ + is_locked_tcp_sock)); \ *insn++ =BPF_JMP_IMM (BPF_JEQ , reg,0 ,2 ); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, sk),\
net/ipv4/tcp_input.c +2 -0
@@ -169,6 +169,7 @@ static void bpf_skops_parse_hdr(struct sock *sk, struct sk_buff *skb)memset (&sock_ops,0 , offsetof(struct bpf_sock_ops_kern , temp)); sock_ops.op =BPF_SOCK_OPS_PARSE_HDR_OPT_CB ; sock_ops.is_fullsock =1 ; + sock_ops.is_locked_tcp_sock =1 ; sock_ops.sk = sk;bpf_skops_init_skb (&sock_ops, skb,tcp_hdrlen (skb));
@@ -185,6 +186,7 @@ static void bpf_skops_established(struct sock *sk, int bpf_op,memset (&sock_ops,0 , offsetof(struct bpf_sock_ops_kern , temp)); sock_ops.op = bpf_op; sock_ops.is_fullsock =1 ; + sock_ops.is_locked_tcp_sock =1 ; sock_ops.sk = sk;/* sk with TCP_REPAIR_ON does not have skb in tcp_finish_connect */ if (skb)
net/ipv4/tcp_output.c +2 -0
@@ -522,6 +522,7 @@ static void bpf_skops_hdr_opt_len(struct sock *sk, struct sk_buff *skb,sock_owned_by_me (sk); sock_ops.is_fullsock =1 ; + sock_ops.is_locked_tcp_sock =1 ; sock_ops.sk = sk; }
@@ -567,6 +568,7 @@ static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb,sock_owned_by_me (sk); sock_ops.is_fullsock =1 ; + sock_ops.is_locked_tcp_sock =1 ; sock_ops.sk = sk; }
Signature · 1 line
2.43.5
Martin KaFai Lau
reviewerRe: [PATCH bpf-next v9 03/12] bpf: stop unsafely accessing TCP fields in bpf callbacks
Quoted 2 lines · Jason Xing
The "
is_locked_tcp_sock" flag is added to indicate that the callback site has atcp_socklocked.
It should mention that the later TX timestamping callbacks will not own the lock. This is what this patch is primarily for. We know the background, but future code readers may not. We will eventually become the readers of this patch in a few years' time.
Quoted 2 lines
Apply the new member
is_locked_tcp_sockin the existing callbacks
It is hard to read "Apply the new member....". "Apply" could mean a few things. "Set to 1" is clearer.
Quoted 1 line
where
is_fullsockis set to 1 can stop UDP socket accessing struct
The UDP part is future proof. This set does not support UDP which has to be clear in the commit message. This has been brought up before also.
Quoted 8 lines
tcp_sockand stop TCP socket without sk lock protecting does the similar thing, or else it could be catastrophe leading to panic.To keep it simple, instead of distinguishing between read and write access, users aren't allowed all read/write access to the
tcp_sockthrough the olderbpf_sock_opsctx. The new timestamping callbacks can use newer helpers to read everything from a sk (e.g.bpf_core_cast), so nothing is lost.
(Subject):
bpf: Prevent unsafe access to the sock fields in the BPF timestamping callback
(Why):
The subsequent patch will implement BPF TX timestamping. It will call the sockops BPF program without holding the sock lock.
This breaks the current assumption that all sock ops programs will hold the sock lock. The sock's fields of the uapi's bpf_sock_ops requires this assumption.
(What and How):
To address this,
a new "u8 is_locked_tcp_sock;" field is added. This patch sets it in the current sock_ops callbacks. The "is_fullsock" test is then replaced by the "is_locked_tcp_sock" test during sock_ops_convert_ctx_access().
The new TX timestamping callbacks added in the subsequent patch will not have this set. This will prevent unsafe access from the new timestamping callbacks.
Potentially, we could allow read-only access. However, this would require identifying which callback is read-safe-only and also requires additional BPF instruction rewrites in the covert_ctx. Since the BPF program can always read everything from a socket (e.g., by using bpf_core_cast), this patch keeps it simple and disables all read and write access to any socket fields through the bpf_sock_ops UAPI from the new TX timestamping callback.
Moreover, note that some of the fields in bpf_sock_ops are specific to tcp_sock, and sock_ops currently only supports tcp_sock. In the future, UDP timestamping will be added, which will also break this assumption. The same idea used in this patch will be reused. Considering that the current sock_ops only supports tcp_sock, the variable is named is_locked_"tcp"_sock.
Re: [PATCH bpf-next v9 03/12] bpf: stop unsafely accessing TCP fields in bpf callbacks
Quoted 57 lines · Martin KaFai Lau
Quoted 2 lines · Jason Xing
The "
is_locked_tcp_sock" flag is added to indicate that the callback site has atcp_socklocked.It should mention that the later TX timestamping callbacks will not own the lock. This is what this patch is primarily for. We know the background, but future code readers may not. We will eventually become the readers of this patch in a few years' time.
Quoted 2 lines
Apply the new member
is_locked_tcp_sockin the existing callbacksIt is hard to read "Apply the new member....". "Apply" could mean a few things. "Set to 1" is clearer.
Quoted 1 line
where
is_fullsockis set to 1 can stop UDP socket accessing structThe UDP part is future proof. This set does not support UDP which has to be clear in the commit message. This has been brought up before also.
Quoted 8 lines
tcp_sockand stop TCP socket without sk lock protecting does the similar thing, or else it could be catastrophe leading to panic.To keep it simple, instead of distinguishing between read and write access, users aren't allowed all read/write access to the
tcp_sockthrough the olderbpf_sock_opsctx. The new timestamping callbacks can use newer helpers to read everything from a sk (e.g.bpf_core_cast), so nothing is lost.(Subject):
bpf: Prevent unsafe access to the sock fields in the BPF timestamping callback(Why):
The subsequent patch will implement BPF TX timestamping. It will call the sockops BPF program without holding the sock lock.This breaks the current assumption that all sock ops programs will hold the sock lock. The sock's fields of the uapi's
bpf_sock_opsrequires this assumption.(What and How):
To address this,
a new "u8is_locked_tcp_sock;" field is added. This patch sets it in the currentsock_opscallbacks. The "is_fullsock" test is then replaced by the "is_locked_tcp_sock" test duringsock_ops_convert_ctx_access().The new TX timestamping callbacks added in the subsequent patch will not have this set. This will prevent unsafe access from the new timestamping callbacks.
Potentially, we could allow read-only access. However, this would require identifying which callback is read-safe-only and also requires additional BPF instruction rewrites in the
covert_ctx. Since the BPF program can always read everything from a socket (e.g., by usingbpf_core_cast), this patch keeps it simple and disables all read and write access to any socket fields through thebpf_sock_opsUAPI from the new TX timestamping callback.
Quoted 5 lines
Moreover, note that some of the fields in
bpf_sock_opsare specific totcp_sock, andsock_opscurrently only supportstcp_sock. In the future, UDP timestamping will be added, which will also break this assumption. The same idea used in this patch will be reused. Considering that the currentsock_opsonly supportstcp_sock, the variable is named is_locked_"tcp"_sock.
Thanks so much for polishing the commit message. I appreciate it!
Will adjust it.
Thanks,
Jason
PATCH v9 4/12 bpf: stop calling some sock_op BPF CALLs in new timestamping callbacks
In reply to Jason XingConsidering the potential invalid access issues, calling bpf_sock_ops_setsockopt/getsockopt, bpf_sock_ops_cb_flags_set, and the bpf_sock_ops_load_hdr_opt in the new timestamping callbacks will return -EOPNOTSUPP error value.
It also prevents the UDP socket trying to access TCP fields in the bpf extension for SO_TIMESTAMPING for the same consideration.
--- net/core/filter.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+)
net/core/filter.c +17 -0
@@ -5523,6 +5523,11 @@ static int __bpf_setsockopt(struct sock *sk, int level, int optname,return -EINVAL ; } +static bool is_locked_tcp_sock_ops (struct bpf_sock_ops_kern *bpf_sock) +{ +return bpf_sock->op <=BPF_SOCK_OPS_WRITE_HDR_OPT_CB ; +} +static int _bpf_setsockopt (struct sock *sk,int level,int optname,char *optval,int optlen) {
@@ -5673,6 +5678,9 @@ static const struct bpf_func_proto bpf_sock_addr_getsockopt_proto = { BPF_CALL_5(bpf_sock_ops_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, int, level, int, optname, char *, optval, int, optlen) { +if (!is_locked_tcp_sock_ops (bpf_sock)) +return -EOPNOTSUPP ; +return _bpf_setsockopt (bpf_sock->sk, level, optname, optval, optlen); }
@@ -5758,6 +5766,9 @@ static int bpf_sock_ops_get_syn(struct bpf_sock_ops_kern *bpf_sock, BPF_CALL_5(bpf_sock_ops_getsockopt, struct bpf_sock_ops_kern *, bpf_sock, int, level, int, optname, char *, optval, int, optlen) { +if (!is_locked_tcp_sock_ops (bpf_sock)) +return -EOPNOTSUPP ; +if (IS_ENABLED (CONFIG_INET ) && level ==SOL_TCP && optname >=TCP_BPF_SYN && optname <=TCP_BPF_SYN_MAC ) {int ret, copy_len =0 ;
@@ -5800,6 +5811,9 @@ BPF_CALL_2(bpf_sock_ops_cb_flags_set, struct bpf_sock_ops_kern *, bpf_sock,struct sock *sk = bpf_sock->sk;int val = argval &BPF_SOCK_OPS_ALL_CB_FLAGS ; +if (!is_locked_tcp_sock_ops (bpf_sock)) +return -EOPNOTSUPP ; +if (!IS_ENABLED (CONFIG_INET ) || !sk_fullsock (sk))return -EINVAL ;
@@ -7609,6 +7623,9 @@ BPF_CALL_4(bpf_sock_ops_load_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock,u8 search_kind, search_len, copy_len, magic_len;int ret; +if (!is_locked_tcp_sock_ops (bpf_sock)) +return -EOPNOTSUPP ; +/* 2 byte is the minimal option len except TCPOPT_NOP and * TCPOPT_EOL which are useless for the bpf prog to learn * and this helper disallow loading them also.
Signature · 1 line
2.43.5
Martin KaFai Lau
reviewerRe: [PATCH bpf-next v9 04/12] bpf: stop calling some sock_op BPF CALLs in new timestamping callbacks
Quoted 4 lines · Jason Xing
Considering the potential invalid access issues, calling bpf_sock_ops_setsockopt/getsockopt,
bpf_sock_ops_cb_flags_set, and thebpf_sock_ops_load_hdr_optin the new timestamping callbacks will return-EOPNOTSUPPerror value.
The "why" part is mostly missing. Why they are not safe to be used in the TX timestamping callbacks?
Quoted 3 lines
It also prevents the UDP socket trying to access TCP fields in the bpf extension for
SO_TIMESTAMPINGfor the same consideration.
Let's remove this UDP part to avoid confusion. UDP has very little to do with disabling the helpers here.
"BPF_CALL" in the subject is not clear either. "BPF_CALL" can mean many things, such as calling BPF helpers, calling BPF kfuncs, or calling its own BPF subprograms, etc. In this case, it is the calling BPF helpers.
(Subject)
bpf: Disable unsafe helpers in TX timestamping callbacks
(Why)
New TX timestamping sock_ops callbacks will be added in the subsequent patch. Some of the existing BPF helpers will not be safe to be used in the TX timestamping callbacks.
The bpf_sock_ops_setsockopt, bpf_sock_ops_getsockopt, and bpf_sock_ops_cb_flags_set require owning the sock lock. TX timestamping callbacks will not own the lock.
The bpf_sock_ops_load_hdr_opt needs the skb->data pointing to the TCP header. This will not be true in the TX timestamping callbacks.
(What and How)
At the beginning of these helpers, this patch checks the bpf_sock->op to ensure these helpers are used by the existing sock_ops callbacks only.
Re: [PATCH bpf-next v9 04/12] bpf: stop calling some sock_op BPF CALLs in new timestamping callbacks
Quoted 32 lines · Martin KaFai Lau
Quoted 4 lines · Jason Xing
Considering the potential invalid access issues, calling bpf_sock_ops_setsockopt/getsockopt,
bpf_sock_ops_cb_flags_set, and thebpf_sock_ops_load_hdr_optin the new timestamping callbacks will return-EOPNOTSUPPerror value.The "why" part is mostly missing. Why they are not safe to be used in the TX timestamping callbacks?
Quoted 3 lines
It also prevents the UDP socket trying to access TCP fields in the bpf extension for
SO_TIMESTAMPINGfor the same consideration.Let's remove this UDP part to avoid confusion. UDP has very little to do with disabling the helpers here.
"
BPF_CALL" in the subject is not clear either. "BPF_CALL" can mean many things, such as calling BPF helpers, calling BPF kfuncs, or calling its own BPF subprograms, etc. In this case, it is the calling BPF helpers.(Subject)
bpf: Disable unsafe helpers in TX timestamping callbacks(Why)
New TX timestampingsock_opscallbacks will be added in the subsequent patch. Some of the existing BPF helpers will not be safe to be used in the TX timestamping callbacks.The
bpf_sock_ops_setsockopt,bpf_sock_ops_getsockopt, andbpf_sock_ops_cb_flags_setrequire owning the sock lock. TX timestamping callbacks will not own the lock.
Quoted 6 lines
The
bpf_sock_ops_load_hdr_optneeds theskb->datapointing to the TCP header. This will not be true in the TX timestamping callbacks.(What and How)
At the beginning of these helpers, this patch checks thebpf_sock->opto ensure these helpers are used by the existingsock_opscallbacks only.
Many thanks here! I will use them in the commit message.
Thanks,
Jason
PATCH v9 5/12 net-timestamp: prepare for isolating two modes of SO_TIMESTAMPING
In reply to Jason XingNo functional changes here, only add test to see if the orig_skb matches the usage of application SO_TIMESTAMPING. And it's good to support two modes in parallel later in this series.
--- net/core/skbuff.c | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-)
net/core/skbuff.c +20 -1
@@ -5539,18 +5539,37 @@ void skb_complete_tx_timestamp(struct sk_buff *skb, }EXPORT_SYMBOL_GPL (skb_complete_tx_timestamp); +static bool skb_tstamp_tx_report_so_timestamping (struct sk_buff *skb, +int tstype,bool sw) +{ +switch (tstype) { +case SCM_TSTAMP_SCHED : +return skb_shinfo (skb)->tx_flags &SKBTX_SCHED_TSTAMP ; +case SCM_TSTAMP_SND : +return skb_shinfo (skb)->tx_flags & (sw ?SKBTX_SW_TSTAMP : +SKBTX_HW_TSTAMP ); +case SCM_TSTAMP_ACK : +return TCP_SKB_CB (skb)->txstamp_ack; + } + +return false; +} +void __skb_tstamp_tx (struct sk_buff *orig_skb,const struct sk_buff *ack_skb,struct skb_shared_hwtstamps *hwtstamps,struct sock *sk,int tstype) { +bool tsonly, opt_stats = false, sw = hwtstamps ? false : true;struct sk_buff *skb; -bool tsonly, opt_stats = false;u32 tsflags;if (!sk)return ; +if (!skb_tstamp_tx_report_so_timestamping (orig_skb, tstype, sw)) +return ; + tsflags =READ_ONCE (sk->sk_tsflags);if (!hwtstamps && !(tsflags &SOF_TIMESTAMPING_OPT_TX_SWHW ) &&skb_shinfo (orig_skb)->tx_flags &SKBTX_IN_PROGRESS )
Signature · 1 line
2.43.5
PATCH v9 6/12 bpf: support SCM_TSTAMP_SCHED of SO_TIMESTAMPING
In reply to Jason XingSupport SCM_TSTAMP_SCHED case. Introduce SKBTX_BPF used as an indicator telling us whether the skb should be traced by the bpf prog.
--- include/linux/skbuff.h | 6 +++++- include/uapi/linux/bpf.h | 4 ++++ net/core/dev.c | 3 ++- net/core/skbuff.c | 20 ++++++++++++++++++++ tools/include/uapi/linux/bpf.h | 4 ++++ 5 files changed, 35 insertions(+), 2 deletions(-)
include/linux/skbuff.h +5 -1
@@ -489,10 +489,14 @@ enum {/* generate software time stamp when entering packet scheduling */ SKBTX_SCHED_TSTAMP =1 <<6 , + +/* used for bpf extension when a bpf program is loaded */ + SKBTX_BPF = 1 << 7, };#define SKBTX_ANY_SW_TSTAMP (SKBTX_SW_TSTAMP | \ - SKBTX_SCHED_TSTAMP) + SKBTX_SCHED_TSTAMP | \ + SKBTX_BPF)#define SKBTX_ANY_TSTAMP (SKBTX_HW_TSTAMP | \ SKBTX_HW_TSTAMP_USE_CYCLES | \ SKBTX_ANY_SW_TSTAMP)
include/uapi/linux/bpf.h +4 -0
@@ -7032,6 +7032,10 @@ enum {* by the kernel or the * earlier bpf-progs. */ + BPF_SOCK_OPS_TS_SCHED_OPT_CB, /* Called when skb is passing through +* dev layer when SK_BPF_CB_TX_TIMESTAMPING +* feature is on. +*/ };/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
net/core/dev.c +2 -1
@@ -4500,7 +4500,8 @@ int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)skb_reset_mac_header (skb);skb_assert_len (skb); -if (unlikely (skb_shinfo (skb)->tx_flags &SKBTX_SCHED_TSTAMP )) +if (unlikely (skb_shinfo (skb)->tx_flags & + (SKBTX_SCHED_TSTAMP |SKBTX_BPF )))__skb_tstamp_tx (skb,NULL ,NULL , skb->sk,SCM_TSTAMP_SCHED );/* Disable soft irqs for various locks below. Also
net/core/skbuff.c +20 -0
@@ -5555,6 +5555,23 @@ static bool skb_tstamp_tx_report_so_timestamping(struct sk_buff *skb,return false; } +static void skb_tstamp_tx_report_bpf_timestamping (struct sk_buff *skb, +struct sock *sk, +int tstype) +{ +int op; + +switch (tstype) { +case SCM_TSTAMP_SCHED : + op =BPF_SOCK_OPS_TS_SCHED_OPT_CB ; +break ; +default : +return ; + } + +bpf_skops_tx_timestamping (sk, skb, op); +} + void __skb_tstamp_tx(struct sk_buff *orig_skb, const struct sk_buff *ack_skb, struct skb_shared_hwtstamps *hwtstamps,
@@ -5567,6 +5584,9 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,if (!sk)return ; +if (skb_shinfo (orig_skb)->tx_flags &SKBTX_BPF ) +skb_tstamp_tx_report_bpf_timestamping (orig_skb, sk, tstype); +if (!skb_tstamp_tx_report_so_timestamping (orig_skb, tstype, sw))return ;
tools/include/uapi/linux/bpf.h +4 -0
@@ -7025,6 +7025,10 @@ enum {* by the kernel or the * earlier bpf-progs. */ + BPF_SOCK_OPS_TS_SCHED_OPT_CB, /* Called when skb is passing through +* dev layer when SK_BPF_CB_TX_TIMESTAMPING +* feature is on. +*/ };/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
Signature · 1 line
2.43.5
Martin KaFai Lau
reviewerRe: [PATCH bpf-next v9 06/12] bpf: support SCM_TSTAMP_SCHED of SO_TIMESTAMPING
Quoted 3 lines · Jason Xing
Support
SCM_TSTAMP_SCHEDcase. IntroduceSKBTX_BPFused as an indicator telling us whether the skb should be traced by the bpf prog.
The BPF side does not exactly support SCM_TSTAMP_SCHED as a report value.
What this patch does is:
Add a new sock_ops callback, BPF_SOCK_OPS_TS_SCHED_OPT_CB. This callback will occur at the same timestamping point as the user space's SCM_TSTAMP_SCHED. The BPF program can use it to get the same SCM_TSTAMP_SCHED timestamp without modifying the user-space application.
A new SKBTX_BPF flag is added to mark skb_shinfo(skb)->tx_flags, ensuring that the new BPF timestamping and the current user space's SO_TIMESTAMPING do not interfere with each other.
I would remove most of the SO_TIMESTAMPING comments from the commit messages. The timestamping points are the same but there is not much overlapping on the API side.
Subject could be:
bpf: Add BPF_SOCK_OPS_TS_SCHED_OPT_CB callback
[ The same probably for patch 7-9. ]
Quoted 112 lines
Signed-off-by Jason Xing <[email protected]>--- include/linux/skbuff.h | 6 +++++- include/uapi/linux/bpf.h | 4 ++++ net/core/dev.c | 3 ++- net/core/skbuff.c | 20 ++++++++++++++++++++ tools/include/uapi/linux/bpf.h | 4 ++++ 5 files changed, 35 insertions(+), 2 deletions(-)include/linux/skbuff.h +5
-1@@ -489,10 +489,14 @@ enum {/* generate software time stamp when entering packet scheduling */ SKBTX_SCHED_TSTAMP =1 <<6 , + +/* used for bpf extension when a bpf program is loaded */ + SKBTX_BPF = 1 << 7, };#define SKBTX_ANY_SW_TSTAMP (SKBTX_SW_TSTAMP | \ - SKBTX_SCHED_TSTAMP) + SKBTX_SCHED_TSTAMP | \ + SKBTX_BPF)#define SKBTX_ANY_TSTAMP (SKBTX_HW_TSTAMP | \ SKBTX_HW_TSTAMP_USE_CYCLES | \ SKBTX_ANY_SW_TSTAMP)include/uapi/linux/bpf.h +4
-0@@ -7032,6 +7032,10 @@ enum {* by the kernel or the * earlier bpf-progs. */ + BPF_SOCK_OPS_TS_SCHED_OPT_CB, /* Called when skb is passing through +* dev layer when SK_BPF_CB_TX_TIMESTAMPING +* feature is on. +*/ };/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect net/core/dev.c +2
-1@@ -4500,7 +4500,8 @@ int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)skb_reset_mac_header (skb);skb_assert_len (skb); -if (unlikely (skb_shinfo (skb)->tx_flags &SKBTX_SCHED_TSTAMP )) +if (unlikely (skb_shinfo (skb)->tx_flags & + (SKBTX_SCHED_TSTAMP |SKBTX_BPF )))__skb_tstamp_tx (skb,NULL ,NULL , skb->sk,SCM_TSTAMP_SCHED );/* Disable soft irqs for various locks below. Also net/core/skbuff.c +20
-0@@ -5555,6 +5555,23 @@ static bool skb_tstamp_tx_report_so_timestamping(struct sk_buff *skb,return false; } +static void skb_tstamp_tx_report_bpf_timestamping (struct sk_buff *skb, +struct sock *sk, +int tstype) +{ +int op; + +switch (tstype) { +case SCM_TSTAMP_SCHED : + op =BPF_SOCK_OPS_TS_SCHED_OPT_CB ; +break ; +default : +return ; + } + +bpf_skops_tx_timestamping (sk, skb, op); +} + void __skb_tstamp_tx(struct sk_buff *orig_skb, const struct sk_buff *ack_skb, struct skb_shared_hwtstamps *hwtstamps,@@ -5567,6 +5584,9 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,if (!sk)return ; +if (skb_shinfo (orig_skb)->tx_flags &SKBTX_BPF ) +skb_tstamp_tx_report_bpf_timestamping (orig_skb, sk, tstype); +if (!skb_tstamp_tx_report_so_timestamping (orig_skb, tstype, sw))return ;tools/include/uapi/linux/bpf.h +4
-0@@ -7025,6 +7025,10 @@ enum {* by the kernel or the * earlier bpf-progs. */ + BPF_SOCK_OPS_TS_SCHED_OPT_CB, /* Called when skb is passing through +* dev layer when SK_BPF_CB_TX_TIMESTAMPING +* feature is on. +*/ };/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
Re: [PATCH bpf-next v9 06/12] bpf: support SCM_TSTAMP_SCHED of SO_TIMESTAMPING
Quoted 19 lines · Martin KaFai Lau
Quoted 3 lines · Jason Xing
Support
SCM_TSTAMP_SCHEDcase. IntroduceSKBTX_BPFused as an indicator telling us whether the skb should be traced by the bpf prog.The BPF side does not exactly support
SCM_TSTAMP_SCHEDas a report value.What this patch does is:
Add a new
sock_opscallback,BPF_SOCK_OPS_TS_SCHED_OPT_CB. This callback will occur at the same timestamping point as the user space'sSCM_TSTAMP_SCHED. The BPF program can use it to get the sameSCM_TSTAMP_SCHEDtimestamp without modifying the user-space application.A new
SKBTX_BPFflag is added to mark skb_shinfo(skb)->tx_flags, ensuring that the new BPF timestamping and the current user space'sSO_TIMESTAMPINGdo not interfere with each other.
Quoted 8 lines
I would remove most of the
SO_TIMESTAMPINGcomments from the commit messages. The timestamping points are the same but there is not much overlapping on the API side.Subject could be:
bpf: AddBPF_SOCK_OPS_TS_SCHED_OPT_CBcallback[ The same probably for patch 7-9. ]
Thanks. I will similarly adjust them as well :)
Thanks,
Jason
PATCH v9 7/12 bpf: support sw SCM_TSTAMP_SND of SO_TIMESTAMPING
In reply to Jason XingSupport sw SCM_TSTAMP_SND case. Then users will get the software timestamp when the driver is about to send the skb. Later, the hardware timestamp will be supported.
--- include/linux/skbuff.h | 2 +- include/uapi/linux/bpf.h | 4 ++++ net/core/skbuff.c | 10 ++++++++-- tools/include/uapi/linux/bpf.h | 4 ++++ 4 files changed, 17 insertions(+), 3 deletions(-)
include/linux/skbuff.h +1 -1
@@ -4568,7 +4568,7 @@ void skb_tstamp_tx(struct sk_buff *orig_skb,static inline void skb_tx_timestamp (struct sk_buff *skb) {skb_clone_tx_timestamp (skb); -if (skb_shinfo (skb)->tx_flags &SKBTX_SW_TSTAMP ) +if (skb_shinfo (skb)->tx_flags & (SKBTX_SW_TSTAMP |SKBTX_BPF ))skb_tstamp_tx (skb,NULL ); }
include/uapi/linux/bpf.h +4 -0
@@ -7036,6 +7036,10 @@ enum {* dev layer when SK_BPF_CB_TX_TIMESTAMPING * feature is on. */ + BPF_SOCK_OPS_TS_SW_OPT_CB, /* Called when skb is about to send +* to the nic when SK_BPF_CB_TX_TIMESTAMPING +* feature is on. +*/ };/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
net/core/skbuff.c +8 -2
@@ -5557,7 +5557,8 @@ static bool skb_tstamp_tx_report_so_timestamping(struct sk_buff *skb,static void skb_tstamp_tx_report_bpf_timestamping (struct sk_buff *skb,struct sock *sk, -int tstype) +int tstype, +bool sw) {int op;
@@ -5565,6 +5566,11 @@ static void skb_tstamp_tx_report_bpf_timestamping(struct sk_buff *skb,case SCM_TSTAMP_SCHED : op =BPF_SOCK_OPS_TS_SCHED_OPT_CB ;break ; +case SCM_TSTAMP_SND : +if (!sw) +return ; + op =BPF_SOCK_OPS_TS_SW_OPT_CB ; +break ;default :return ; }
@@ -5585,7 +5591,7 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,return ;if (skb_shinfo (orig_skb)->tx_flags &SKBTX_BPF ) -skb_tstamp_tx_report_bpf_timestamping (orig_skb, sk, tstype); +skb_tstamp_tx_report_bpf_timestamping (orig_skb, sk, tstype, sw);if (!skb_tstamp_tx_report_so_timestamping (orig_skb, tstype, sw))return ;
tools/include/uapi/linux/bpf.h +4 -0
@@ -7029,6 +7029,10 @@ enum {* dev layer when SK_BPF_CB_TX_TIMESTAMPING * feature is on. */ + BPF_SOCK_OPS_TS_SW_OPT_CB, /* Called when skb is about to send +* to the nic when SK_BPF_CB_TX_TIMESTAMPING +* feature is on. +*/ };/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
Signature · 1 line
2.43.5
PATCH v9 8/12 bpf: support hw SCM_TSTAMP_SND of SO_TIMESTAMPING
In reply to Jason XingSupport hw SCM_TSTAMP_SND case. Then bpf program can fetch the hwstamp from skb directly.
To avoid changing so many callers using SKBTX_HW_TSTAMP from drivers, replace SKBTX_HW_TSTAMP with SKBTX_HW_TSTAMP_NOBPF.
--- include/linux/skbuff.h | 4 +++- include/uapi/linux/bpf.h | 4 ++++ net/core/skbuff.c | 6 ++---- net/dsa/user.c | 2 +- net/socket.c | 2 +- tools/include/uapi/linux/bpf.h | 4 ++++ 6 files changed, 15 insertions(+), 7 deletions(-)
include/linux/skbuff.h +3 -1
@@ -470,7 +470,7 @@ struct skb_shared_hwtstamps {/* Definitions for tx_flags in struct skb_shared_info */ enum {/* generate hardware time stamp */ -SKBTX_HW_TSTAMP =1 <<0 , +SKBTX_HW_TSTAMP_NOBPF =1 <<0 ,/* generate software time stamp when queueing packet to NIC */ SKBTX_SW_TSTAMP =1 <<1 ,
@@ -494,6 +494,8 @@ enum { SKBTX_BPF = 1 << 7, }; +#define SKBTX_HW_TSTAMP (SKBTX_HW_TSTAMP_NOBPF | SKBTX_BPF) +#define SKBTX_ANY_SW_TSTAMP (SKBTX_SW_TSTAMP | \ SKBTX_SCHED_TSTAMP | \ SKBTX_BPF)
include/uapi/linux/bpf.h +4 -0
@@ -7040,6 +7040,10 @@ enum {* to the nic when SK_BPF_CB_TX_TIMESTAMPING * feature is on. */ + BPF_SOCK_OPS_TS_HW_OPT_CB, /* Called in hardware phase when +* SK_BPF_CB_TX_TIMESTAMPING feature +* is on. +*/ };/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
net/core/skbuff.c +2 -4
@@ -5547,7 +5547,7 @@ static bool skb_tstamp_tx_report_so_timestamping(struct sk_buff *skb,return skb_shinfo (skb)->tx_flags &SKBTX_SCHED_TSTAMP ;case SCM_TSTAMP_SND :return skb_shinfo (skb)->tx_flags & (sw ?SKBTX_SW_TSTAMP : -SKBTX_HW_TSTAMP ); +SKBTX_HW_TSTAMP_NOBPF );case SCM_TSTAMP_ACK :return TCP_SKB_CB (skb)->txstamp_ack; }
@@ -5567,9 +5567,7 @@ static void skb_tstamp_tx_report_bpf_timestamping(struct sk_buff *skb, op =BPF_SOCK_OPS_TS_SCHED_OPT_CB ;break ;case SCM_TSTAMP_SND : -if (!sw) -return ; - op =BPF_SOCK_OPS_TS_SW_OPT_CB ; + op = sw ?BPF_SOCK_OPS_TS_SW_OPT_CB :BPF_SOCK_OPS_TS_HW_OPT_CB ;break ;default :return ;
net/dsa/user.c +1 -1
@@ -897,7 +897,7 @@ static void dsa_skb_tx_timestamp(struct dsa_user_priv *p, {struct dsa_switch *ds = p->dp->ds; -if (!(skb_shinfo (skb)->tx_flags &SKBTX_HW_TSTAMP )) +if (!(skb_shinfo (skb)->tx_flags &SKBTX_HW_TSTAMP_NOBPF ))return ;if (!ds->ops->port_txtstamp)
net/socket.c +1 -1
@@ -676,7 +676,7 @@ void __sock_tx_timestamp(__u32 tsflags, __u8 *tx_flags)u8 flags = *tx_flags;if (tsflags &SOF_TIMESTAMPING_TX_HARDWARE ) { - flags |=SKBTX_HW_TSTAMP ; + flags |=SKBTX_HW_TSTAMP_NOBPF ;/* PTP hardware clocks can provide a free running cycle counter * as a time base for virtual clocks. Tell driver to use the
tools/include/uapi/linux/bpf.h +4 -0
@@ -7033,6 +7033,10 @@ enum {* to the nic when SK_BPF_CB_TX_TIMESTAMPING * feature is on. */ + BPF_SOCK_OPS_TS_HW_OPT_CB, /* Called in hardware phase when +* SK_BPF_CB_TX_TIMESTAMPING feature +* is on. +*/ };/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
Signature · 1 line
2.43.5
PATCH v9 9/12 bpf: support SCM_TSTAMP_ACK of SO_TIMESTAMPING
In reply to Jason XingSupport the ACK timestamp case. Extend txstamp_ack to two bits:
1 stands for SO_TIMESTAMPING mode, 2 bpf extension. The latter will be used later.
--- include/net/tcp.h | 4 ++-- include/uapi/linux/bpf.h | 5 +++++ net/core/skbuff.c | 5 ++++- tools/include/uapi/linux/bpf.h | 5 +++++ 4 files changed, 16 insertions(+), 3 deletions(-)
include/net/tcp.h +2 -2
@@ -958,10 +958,10 @@ struct tcp_skb_cb {__u8 sacked;/* State flags for SACK. */ __u8 ip_dsfield;/* IPv4 tos or IPv6 dsfield */ - __u8 txstamp_ack:1, /* Record TX timestamp for ack? */ + __u8 txstamp_ack:2, /* Record TX timestamp for ack? */ eor:1, /* Is skb MSG_EOR marked? */ has_rxtstamp:1, /* SKB has a RX timestamp */ - unused:5; + unused:4;__u32 ack_seq;/* Sequence number ACK'd */ union { struct {
include/uapi/linux/bpf.h +5 -0
@@ -7044,6 +7044,11 @@ enum {* SK_BPF_CB_TX_TIMESTAMPING feature * is on. */ + BPF_SOCK_OPS_TS_ACK_OPT_CB, /* Called when all the skbs in the +* same sendmsg call are acked +* when SK_BPF_CB_TX_TIMESTAMPING +* feature is on. +*/ };/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
net/core/skbuff.c +4 -1
@@ -5549,7 +5549,7 @@ static bool skb_tstamp_tx_report_so_timestamping(struct sk_buff *skb,return skb_shinfo (skb)->tx_flags & (sw ?SKBTX_SW_TSTAMP :SKBTX_HW_TSTAMP_NOBPF );case SCM_TSTAMP_ACK : -return TCP_SKB_CB (skb)->txstamp_ack; +return TCP_SKB_CB (skb)->txstamp_ack ==1 ; }return false;
@@ -5569,6 +5569,9 @@ static void skb_tstamp_tx_report_bpf_timestamping(struct sk_buff *skb,case SCM_TSTAMP_SND : op = sw ?BPF_SOCK_OPS_TS_SW_OPT_CB :BPF_SOCK_OPS_TS_HW_OPT_CB ;break ; +case SCM_TSTAMP_ACK : + op =BPF_SOCK_OPS_TS_ACK_OPT_CB ; +break ;default :return ; }
tools/include/uapi/linux/bpf.h +5 -0
@@ -7037,6 +7037,11 @@ enum {* SK_BPF_CB_TX_TIMESTAMPING feature * is on. */ + BPF_SOCK_OPS_TS_ACK_OPT_CB, /* Called when all the skbs in the +* same sendmsg call are acked +* when SK_BPF_CB_TX_TIMESTAMPING +* feature is on. +*/ };/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
Signature · 1 line
2.43.5
Re: [PATCH bpf-next v9 09/12] bpf: support SCM_TSTAMP_ACK of SO_TIMESTAMPING
Quoted 50 lines · Jason Xing
Support the ACK timestamp case. Extend
txstamp_ackto two bits:
1 stands forSO_TIMESTAMPINGmode, 2 bpf extension. The latter will be used later.Signed-off-by Jason Xing <[email protected]>--- include/net/tcp.h | 4 ++-- include/uapi/linux/bpf.h | 5 +++++ net/core/skbuff.c | 5 ++++- tools/include/uapi/linux/bpf.h | 5 +++++ 4 files changed, 16 insertions(+), 3 deletions(-)include/net/tcp.h +2
-2@@ -958,10 +958,10 @@ struct tcp_skb_cb {__u8 sacked;/* State flags for SACK. */ __u8 ip_dsfield;/* IPv4 tos or IPv6 dsfield */ - __u8 txstamp_ack:1, /* Record TX timestamp for ack? */ + __u8 txstamp_ack:2, /* Record TX timestamp for ack? */ eor:1, /* Is skb MSG_EOR marked? */ has_rxtstamp:1, /* SKB has a RX timestamp */ - unused:5; + unused:4;__u32 ack_seq;/* Sequence number ACK'd */ union { struct {include/uapi/linux/bpf.h +5
-0@@ -7044,6 +7044,11 @@ enum {* SK_BPF_CB_TX_TIMESTAMPING feature * is on. */ + BPF_SOCK_OPS_TS_ACK_OPT_CB, /* Called when all the skbs in the +* same sendmsg call are acked +* when SK_BPF_CB_TX_TIMESTAMPING +* feature is on. +*/ };/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect net/core/skbuff.c +0
-0
net/core/skbuff.c static bool skb_tstamp_tx_report_so_timestamping(struct sk_buff *skb, · line 5552
Quoted 5 lines
net/core/skbuff.c +1
-1@@ -5549,7 +5549,7 @@ static bool skb_tstamp_tx_report_so_timestamping(struct sk_buff *skb,return skb_shinfo (skb)->tx_flags & (sw ?SKBTX_SW_TSTAMP :SKBTX_HW_TSTAMP_NOBPF );case SCM_TSTAMP_ACK : -return TCP_SKB_CB (skb)->txstamp_ack; +return TCP_SKB_CB (skb)->txstamp_ack ==1 ;
For the two to coexist, this should be txstamp_ack & 1
And in the patch that introduces the BPF bit, txstamp_ack |= 2, rather than txstamp_ack = 2.
And let's define labels rather than use constants directly:
#define TSTAMP_ACK_SK 0x1 #define TSTAMP_ACK_BPF 0x2
Re: [PATCH bpf-next v9 09/12] bpf: support SCM_TSTAMP_ACK of SO_TIMESTAMPING
Quoted 60 lines · Willem de Bruijn
Quoted 50 lines · Jason Xing
Support the ACK timestamp case. Extend
txstamp_ackto two bits:
1 stands forSO_TIMESTAMPINGmode, 2 bpf extension. The latter will be used later.Signed-off-by Jason Xing <[email protected]>--- include/net/tcp.h | 4 ++-- include/uapi/linux/bpf.h | 5 +++++ net/core/skbuff.c | 5 ++++- tools/include/uapi/linux/bpf.h | 5 +++++ 4 files changed, 16 insertions(+), 3 deletions(-)include/net/tcp.h +2
-2@@ -958,10 +958,10 @@ struct tcp_skb_cb {__u8 sacked;/* State flags for SACK. */ __u8 ip_dsfield;/* IPv4 tos or IPv6 dsfield */ - __u8 txstamp_ack:1, /* Record TX timestamp for ack? */ + __u8 txstamp_ack:2, /* Record TX timestamp for ack? */ eor:1, /* Is skb MSG_EOR marked? */ has_rxtstamp:1, /* SKB has a RX timestamp */ - unused:5; + unused:4;__u32 ack_seq;/* Sequence number ACK'd */ union { struct {include/uapi/linux/bpf.h +5
-0@@ -7044,6 +7044,11 @@ enum {* SK_BPF_CB_TX_TIMESTAMPING feature * is on. */ + BPF_SOCK_OPS_TS_ACK_OPT_CB, /* Called when all the skbs in the +* same sendmsg call are acked +* when SK_BPF_CB_TX_TIMESTAMPING +* feature is on. +*/ };/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect net/core/skbuff.c +0
-0net/core/skbuff.c static bool skb_tstamp_tx_report_so_timestamping(struct sk_buff *skb, · line 5552
Quoted 5 lines
net/core/skbuff.c +1
-1@@ -5549,7 +5549,7 @@ static bool skb_tstamp_tx_report_so_timestamping(struct sk_buff *skb,return skb_shinfo (skb)->tx_flags & (sw ?SKBTX_SW_TSTAMP :SKBTX_HW_TSTAMP_NOBPF );case SCM_TSTAMP_ACK : -return TCP_SKB_CB (skb)->txstamp_ack; +return TCP_SKB_CB (skb)->txstamp_ack ==1 ;For the two to coexist, this should be
txstamp_ack& 1
Quoted 6 lines
And in the patch that introduces the BPF bit,
txstamp_ack|= 2, rather thantxstamp_ack= 2.And let's define labels rather than use constants directly:
#define TSTAMP_ACK_SK 0x1 #define TSTAMP_ACK_BPF 0x2
Thanks. Will do it.
PATCH v9 10/12 bpf: add a new callback in tcp_tx_timestamp()
In reply to Jason XingIntroduce the callback to correlate tcp_sendmsg timestamp with other points, like SND/SW/ACK. For instance, let bpf prog trace the beginning of tcp_sendmsg_locked() and then store the sendmsg timestamp at the bpf_sk_storage, so that in tcp_tx_timestamp() we can correlate the timestamp with tskey which can be found in other sending points. More details can be found in the selftest.
--- include/uapi/linux/bpf.h | 5 +++++ net/ipv4/tcp.c | 4 ++++ tools/include/uapi/linux/bpf.h | 5 +++++ 3 files changed, 14 insertions(+)
include/uapi/linux/bpf.h +5 -0
@@ -7049,6 +7049,11 @@ enum {* when SK_BPF_CB_TX_TIMESTAMPING * feature is on. */ + BPF_SOCK_OPS_TS_SND_CB, /* Called when every sendmsg syscall +* is triggered. It's used to correlate +* sendmsg timestamp with corresponding +* tskey. +*/ };/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
net/ipv4/tcp.c +4 -0
@@ -492,6 +492,10 @@ static void tcp_tx_timestamp(struct sock *sk, struct sockcm_cookie *sockc)if (tsflags &SOF_TIMESTAMPING_TX_RECORD_MASK ) shinfo->tskey =TCP_SKB_CB (skb)->seq + skb->len -1 ; } + +if (cgroup_bpf_enabled (CGROUP_SOCK_OPS ) && +SK_BPF_CB_FLAG_TEST (sk,SK_BPF_CB_TX_TIMESTAMPING ) && skb) +bpf_skops_tx_timestamping (sk, skb,BPF_SOCK_OPS_TS_SND_CB ); }static bool tcp_stream_is_readable (struct sock *sk,int target)
tools/include/uapi/linux/bpf.h +5 -0
@@ -7042,6 +7042,11 @@ enum {* when SK_BPF_CB_TX_TIMESTAMPING * feature is on. */ + BPF_SOCK_OPS_TS_SND_CB, /* Called when every sendmsg syscall +* is triggered. It's used to correlate +* sendmsg timestamp with corresponding +* tskey. +*/ };/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
Signature · 1 line
2.43.5
PATCH v9 11/12 bpf: support selective sampling for bpf timestamping
In reply to Jason XingUse __bpf_kfunc feature to allow bpf prog dynamically and selectively to sample/track the skb. For example, the bpf prog will limit tracking X numbers of packets and then will stop there instead of tracing all the sendmsgs of matched flow all along.
--- kernel/bpf/btf.c | 1 + net/core/filter.c | 27 ++++++++++++++++++++++++++- 2 files changed, 27 insertions(+), 1 deletion(-)
kernel/bpf/btf.c +1 -0
@@ -8535,6 +8535,7 @@ static int bpf_prog_type_to_kfunc_hook(enum bpf_prog_type prog_type)case BPF_PROG_TYPE_CGROUP_SOCK_ADDR :case BPF_PROG_TYPE_CGROUP_SOCKOPT :case BPF_PROG_TYPE_CGROUP_SYSCTL : +case BPF_PROG_TYPE_SOCK_OPS :return BTF_KFUNC_HOOK_CGROUP ;case BPF_PROG_TYPE_SCHED_ACT :return BTF_KFUNC_HOOK_SCHED_ACT ;
net/core/filter.c +26 -1
@@ -12102,6 +12102,21 @@ __bpf_kfunc int bpf_sk_assign_tcp_reqsk(struct __sk_buff *s, struct sock *sk,#endif } +__bpf_kfunc int bpf_sock_ops_enable_tx_tstamp(struct bpf_sock_ops_kern *skops) +{ +struct sk_buff *skb; + +if (skops->op !=BPF_SOCK_OPS_TS_SND_CB ) +return -EOPNOTSUPP ; + + skb = skops->skb; +TCP_SKB_CB (skb)->txstamp_ack =2 ; +skb_shinfo (skb)->tx_flags |=SKBTX_BPF ; +skb_shinfo (skb)->tskey =TCP_SKB_CB (skb)->seq + skb->len -1 ; + +return 0 ; +} +__bpf_kfunc_end_defs (); int bpf_dynptr_from_skb_rdonly(struct __sk_buff *skb, u64 flags,
@@ -12135,6 +12150,10 @@ BTF_KFUNCS_START(bpf_kfunc_check_set_tcp_reqsk) BTF_ID_FLAGS(func, bpf_sk_assign_tcp_reqsk, KF_TRUSTED_ARGS)BTF_KFUNCS_END (bpf_kfunc_check_set_tcp_reqsk) +BTF_KFUNCS_START (bpf_kfunc_check_set_sock_ops ) +BTF_ID_FLAGS (func, bpf_sock_ops_enable_tx_tstamp,KF_TRUSTED_ARGS ) +BTF_KFUNCS_END (bpf_kfunc_check_set_sock_ops) + static const struct btf_kfunc_id_set bpf_kfunc_set_skb = { .owner =THIS_MODULE , .set = &bpf_kfunc_check_set_skb,
@@ -12155,6 +12174,11 @@ static const struct btf_kfunc_id_set bpf_kfunc_set_tcp_reqsk = { .set = &bpf_kfunc_check_set_tcp_reqsk, }; +static const struct btf_kfunc_id_set bpf_kfunc_set_sock_ops = { + .owner =THIS_MODULE , + .set = &bpf_kfunc_check_set_sock_ops, +}; +static int __init bpf_kfunc_init (void ) {int ret;
@@ -12173,7 +12197,8 @@ static int __init bpf_kfunc_init(void) ret = ret ?:register_btf_kfunc_id_set (BPF_PROG_TYPE_XDP , &bpf_kfunc_set_xdp); ret = ret ?:register_btf_kfunc_id_set (BPF_PROG_TYPE_CGROUP_SOCK_ADDR , &bpf_kfunc_set_sock_addr); -return ret ?:register_btf_kfunc_id_set (BPF_PROG_TYPE_SCHED_CLS , &bpf_kfunc_set_tcp_reqsk); + ret = ret ?:register_btf_kfunc_id_set (BPF_PROG_TYPE_SCHED_CLS , &bpf_kfunc_set_tcp_reqsk); +return ret ?:register_btf_kfunc_id_set (BPF_PROG_TYPE_SOCK_OPS , &bpf_kfunc_set_sock_ops); }late_initcall (bpf_kfunc_init);
Signature · 1 line
2.43.5
Martin KaFai Lau
reviewerRe: [PATCH bpf-next v9 11/12] bpf: support selective sampling for bpf timestamping
Quoted 1 line · Jason Xing
Use
__bpf_kfuncfeature to allow bpf prog dynamically and selectively
s/Use/Add/
Remove "dynamically". A kfunc can only be called dynamically at runtime.
Like:
"Add the bpf_sock_ops_enable_tx_tstamp kfunc to allow BPF programs to selectively enable TX timestamping on a skb during tcp_sendmsg..."
Quoted 26 lines
to sample/track the skb. For example, the bpf prog will limit tracking X numbers of packets and then will stop there instead of tracing all the sendmsgs of matched flow all along.
Quoted 1 line
Signed-off-by Jason Xing <[email protected]>--- kernel/bpf/btf.c | 1 + net/core/filter.c | 27 ++++++++++++++++++++++++++- 2 files changed, 27 insertions(+), 1 deletion(-)kernel/bpf/btf.c +1
-0@@ -8535,6 +8535,7 @@ static int bpf_prog_type_to_kfunc_hook(enum bpf_prog_type prog_type)case BPF_PROG_TYPE_CGROUP_SOCK_ADDR :case BPF_PROG_TYPE_CGROUP_SOCKOPT :case BPF_PROG_TYPE_CGROUP_SYSCTL : +case BPF_PROG_TYPE_SOCK_OPS :return BTF_KFUNC_HOOK_CGROUP ;case BPF_PROG_TYPE_SCHED_ACT :return BTF_KFUNC_HOOK_SCHED_ACT ;net/core/filter.c +0
-0
net/core/filter.c __bpf_kfunc int bpf_sk_assign_tcp_reqsk(struct __sk_buff *s, struct sock *sk, · line 12105
Quoted 4 lines
net/core/filter.c +1
-0@@ -12102,6 +12102,21 @@ __bpf_kfunc int bpf_sk_assign_tcp_reqsk(struct __sk_buff *s, struct sock *sk,#endif } +__bpf_kfunc int bpf_sock_ops_enable_tx_tstamp(struct bpf_sock_ops_kern *skops)
I am ok to always enable txstamp_ack here. Please still add a second "u64 flags" argument such that future disable/enable is still possible.
net/core/filter.c __bpf_kfunc int bpf_sk_assign_tcp_reqsk(struct __sk_buff *s, struct sock *sk, · line 12113
Quoted 7 lines
net/core/filter.c +7
-0+{ +struct sk_buff *skb; + +if (skops->op !=BPF_SOCK_OPS_TS_SND_CB ) + return -EOPNOTSUPP;> + + skb = skops->skb; +TCP_SKB_CB (skb)->txstamp_ack =2 ;
Willem (thanks!) has already mentioned there is a bug.
This also brought up that a test is missing: the bpf timestamping and user space's SO_TIMESTAMPING can work without interfering others. The current test only has SK_BPF_CB_TX_TIMESTAMPING on. A test is needed when both SK_BPF_CB_TX_TIMESTAMPING and the user space's SO_TIMESTAMPING are on. The expectation is both of them will work together.
Quoted 42 lines
net/core/filter.c +17
-1+skb_shinfo (skb)->tx_flags |=SKBTX_BPF ; +skb_shinfo (skb)->tskey =TCP_SKB_CB (skb)->seq + skb->len -1 ; + +return 0 ; +} +__bpf_kfunc_end_defs (); int bpf_dynptr_from_skb_rdonly(struct __sk_buff *skb, u64 flags,@@ -12135,6 +12150,10 @@ BTF_KFUNCS_START(bpf_kfunc_check_set_tcp_reqsk) BTF_ID_FLAGS(func, bpf_sk_assign_tcp_reqsk, KF_TRUSTED_ARGS)BTF_KFUNCS_END (bpf_kfunc_check_set_tcp_reqsk) +BTF_KFUNCS_START (bpf_kfunc_check_set_sock_ops ) +BTF_ID_FLAGS (func, bpf_sock_ops_enable_tx_tstamp,KF_TRUSTED_ARGS ) +BTF_KFUNCS_END (bpf_kfunc_check_set_sock_ops) + static const struct btf_kfunc_id_set bpf_kfunc_set_skb = { .owner =THIS_MODULE , .set = &bpf_kfunc_check_set_skb,@@ -12155,6 +12174,11 @@ static const struct btf_kfunc_id_set bpf_kfunc_set_tcp_reqsk = { .set = &bpf_kfunc_check_set_tcp_reqsk, }; +static const struct btf_kfunc_id_set bpf_kfunc_set_sock_ops = { + .owner =THIS_MODULE , + .set = &bpf_kfunc_check_set_sock_ops, +}; +static int __init bpf_kfunc_init (void ) {int ret;@@ -12173,7 +12197,8 @@ static int __init bpf_kfunc_init(void) ret = ret ?:register_btf_kfunc_id_set (BPF_PROG_TYPE_XDP , &bpf_kfunc_set_xdp); ret = ret ?:register_btf_kfunc_id_set (BPF_PROG_TYPE_CGROUP_SOCK_ADDR , &bpf_kfunc_set_sock_addr); -return ret ?:register_btf_kfunc_id_set (BPF_PROG_TYPE_SCHED_CLS , &bpf_kfunc_set_tcp_reqsk); + ret = ret ?:register_btf_kfunc_id_set (BPF_PROG_TYPE_SCHED_CLS , &bpf_kfunc_set_tcp_reqsk); +return ret ?:register_btf_kfunc_id_set (BPF_PROG_TYPE_SOCK_OPS , &bpf_kfunc_set_sock_ops); }late_initcall (bpf_kfunc_init);
Re: [PATCH bpf-next v9 11/12] bpf: support selective sampling for bpf timestamping
Quoted 4 lines · Martin KaFai Lau
Quoted 1 line · Jason Xing
Use
__bpf_kfuncfeature to allow bpf prog dynamically and selectively
Quoted 8 lines
s/Use/Add/
Remove "dynamically". A kfunc can only be called dynamically at runtime.
Like:
"Add the
bpf_sock_ops_enable_tx_tstampkfunc to allow BPF programs to selectively enable TX timestamping on a skb duringtcp_sendmsg..."
Will adjust it.
Quoted 30 lines
Quoted 30 lines
to sample/track the skb. For example, the bpf prog will limit tracking X numbers of packets and then will stop there instead of tracing all the sendmsgs of matched flow all along.
Quoted 1 line
Signed-off-by Jason Xing <[email protected]>--- kernel/bpf/btf.c | 1 + net/core/filter.c | 27 ++++++++++++++++++++++++++- 2 files changed, 27 insertions(+), 1 deletion(-)kernel/bpf/btf.c +1
-0@@ -8535,6 +8535,7 @@ static int bpf_prog_type_to_kfunc_hook(enum bpf_prog_type prog_type)case BPF_PROG_TYPE_CGROUP_SOCK_ADDR :case BPF_PROG_TYPE_CGROUP_SOCKOPT :case BPF_PROG_TYPE_CGROUP_SYSCTL : +case BPF_PROG_TYPE_SOCK_OPS :return BTF_KFUNC_HOOK_CGROUP ;case BPF_PROG_TYPE_SCHED_ACT :return BTF_KFUNC_HOOK_SCHED_ACT ;net/core/filter.c +0
-0@@ -12102,6 +12102,21 @@ __bpf_kfunc int bpf_sk_assign_tcp_reqsk(struct __sk_buff *s, struct sock *sk,#endif }
Quoted 4 lines
net/core/filter.c __bpf_kfunc int bpf_sk_assign_tcp_reqsk(struct __sk_buff *s, struct sock *sk, · line 12105
Quoted 1 line
net/core/filter.c +1
-0+__bpf_kfunc int bpf_sock_ops_enable_tx_tstamp(struct bpf_sock_ops_kern *skops)I am ok to always enable
txstamp_ackhere. Please still add a second "u64 flags" argument such that future disable/enable is still possible.
Ok. Will do it.
Quoted 11 lines
net/core/filter.c __bpf_kfunc int bpf_sk_assign_tcp_reqsk(struct __sk_buff *s, struct sock *sk, · line 12113
Quoted 8 lines
net/core/filter.c +7
-0+{ +struct sk_buff *skb; + +if (skops->op !=BPF_SOCK_OPS_TS_SND_CB ) + return -EOPNOTSUPP;> + + skb = skops->skb; +TCP_SKB_CB (skb)->txstamp_ack =2 ;Willem (thanks!) has already mentioned there is a bug.
Quoted 5 lines
This also brought up that a test is missing: the bpf timestamping and user space's
SO_TIMESTAMPINGcan work without interfering others. The current test only hasSK_BPF_CB_TX_TIMESTAMPINGon. A test is needed when bothSK_BPF_CB_TX_TIMESTAMPINGand the user space'sSO_TIMESTAMPINGare on. The expectation is both of them will work together.
Yeah, I did miss this particular test. Let me figure out how to test it in a proper way.
Thanks,
Jason
Quoted 44 lines
Quoted 43 lines
net/core/filter.c +17
-1+skb_shinfo (skb)->tx_flags |=SKBTX_BPF ; +skb_shinfo (skb)->tskey =TCP_SKB_CB (skb)->seq + skb->len -1 ; + +return 0 ; +} +__bpf_kfunc_end_defs (); int bpf_dynptr_from_skb_rdonly(struct __sk_buff *skb, u64 flags,@@ -12135,6 +12150,10 @@ BTF_KFUNCS_START(bpf_kfunc_check_set_tcp_reqsk) BTF_ID_FLAGS(func, bpf_sk_assign_tcp_reqsk, KF_TRUSTED_ARGS)BTF_KFUNCS_END (bpf_kfunc_check_set_tcp_reqsk) +BTF_KFUNCS_START (bpf_kfunc_check_set_sock_ops ) +BTF_ID_FLAGS (func, bpf_sock_ops_enable_tx_tstamp,KF_TRUSTED_ARGS ) +BTF_KFUNCS_END (bpf_kfunc_check_set_sock_ops) + static const struct btf_kfunc_id_set bpf_kfunc_set_skb = { .owner =THIS_MODULE , .set = &bpf_kfunc_check_set_skb,@@ -12155,6 +12174,11 @@ static const struct btf_kfunc_id_set bpf_kfunc_set_tcp_reqsk = { .set = &bpf_kfunc_check_set_tcp_reqsk, }; +static const struct btf_kfunc_id_set bpf_kfunc_set_sock_ops = { + .owner =THIS_MODULE , + .set = &bpf_kfunc_check_set_sock_ops, +}; +static int __init bpf_kfunc_init (void ) {int ret;@@ -12173,7 +12197,8 @@ static int __init bpf_kfunc_init(void) ret = ret ?:register_btf_kfunc_id_set (BPF_PROG_TYPE_XDP , &bpf_kfunc_set_xdp); ret = ret ?:register_btf_kfunc_id_set (BPF_PROG_TYPE_CGROUP_SOCK_ADDR , &bpf_kfunc_set_sock_addr); -return ret ?:register_btf_kfunc_id_set (BPF_PROG_TYPE_SCHED_CLS , &bpf_kfunc_set_tcp_reqsk); + ret = ret ?:register_btf_kfunc_id_set (BPF_PROG_TYPE_SCHED_CLS , &bpf_kfunc_set_tcp_reqsk); +return ret ?:register_btf_kfunc_id_set (BPF_PROG_TYPE_SOCK_OPS , &bpf_kfunc_set_sock_ops); }late_initcall (bpf_kfunc_init);
PATCH v9 12/12 selftests/bpf: add simple bpf tests in the tx path for timestamping feature
In reply to Jason XingBpf prog calculates a couple of latency delta between each tx points which SO_TIMESTAMPING feature has already implemented. It can be used in the real world to diagnose the behaviour in the tx path.
Also, check the safety issues by accessing a few bpf calls in bpf_test_access_bpf_calls().
There remains a few realistic things[1][2] to highlight:
1. in general a packet may pass through multiple qdiscs. For instance with bonding or tunnel virtual devices in the egress path.
2. packets may be resent, in which case an ACK might precede a repeat SCHED and SND.
3. erroneous or malicious peers may also just never send an ACK.
[1]: https://lore.kernel.org/all/[email protected]/
[2]: https://lore.kernel.org/all/[email protected]/
--- .../bpf/prog_tests/so_timestamping.c | 79 +++++ .../selftests/bpf/progs/so_timestamping.c | 312 ++++++++++++++++++ 2 files changed, 391 insertions(+) create mode 100644 tools/testing/selftests/bpf/prog_tests/so_timestamping.c create mode 100644 tools/testing/selftests/bpf/progs/so_timestamping.c
tools/testing/selftests/bpf/prog_tests/so_timestamping.c new file +79 -0
@@ -0,0 +1,79 @@ +#include "test_progs.h" +#include "network_helpers.h" + +#include "so_timestamping.skel.h" + +#define CG_NAME "/so-timestamping-test" + +static const char addr4_str[] ="127.0.0.1" ; +static const char addr6_str[] ="::1" ; +static struct so_timestamping *skel; + +static void test_tcp (int family) +{ +struct so_timestamping__bss *bss = skel->bss; +char buf[] ="testing testing" ; +int sfd =-1 , cfd =-1 ; +int n; + +memset (bss,0 ,sizeof (*bss)); + + sfd =start_server (family,SOCK_STREAM , + family ==AF_INET6 ? addr6_str : addr4_str,0 ,0 ); +if (!ASSERT_OK_FD (sfd,"start_server" )) + goto out; + + cfd =connect_to_fd (sfd,0 ); +if (!ASSERT_OK_FD (cfd,"connect_to_fd_server" )) + goto out; + + n =write (cfd, buf,sizeof (buf)); +if (!ASSERT_EQ (n,sizeof (buf),"send to server" )) + goto out; + +ASSERT_EQ (bss->nr_active,1 ,"nr_active" ); +ASSERT_EQ (bss->nr_snd,2 ,"nr_snd" ); +ASSERT_EQ (bss->nr_sched,1 ,"nr_sched" ); +ASSERT_EQ (bss->nr_txsw,1 ,"nr_txsw" ); +ASSERT_EQ (bss->nr_ack,1 ,"nr_ack" ); + +out: +if (sfd >=0 ) +close (sfd); +if (cfd >=0 ) +close (cfd); +} + +void test_so_timestamping (void ) +{ +struct netns_obj *ns; +int cg_fd; + + cg_fd =test__join_cgroup (CG_NAME ); +if (!ASSERT_OK_FD (cg_fd,"join cgroup" )) +return ; + + ns =netns_new ("so_timestamping_ns" , true); +if (!ASSERT_OK_PTR (ns,"create ns" )) + goto done; + + skel =so_timestamping__open_and_load (); +if (!ASSERT_OK_PTR (skel,"open and load skel" )) + goto done; + +if (!ASSERT_OK (so_timestamping__attach (skel),"attach skel" )) + goto done; + + skel->links.skops_sockopt = +bpf_program__attach_cgroup (skel->progs.skops_sockopt, cg_fd); +if (!ASSERT_OK_PTR (skel->links.skops_sockopt,"attach cgroup" )) + goto done; + +test_tcp (AF_INET6 ); +test_tcp (AF_INET ); + +done: +so_timestamping__destroy (skel); +netns_free (ns); +close (cg_fd); +}
tools/testing/selftests/bpf/progs/so_timestamping.c new file +312 -0
312 lines not on this page · raw message
Signature · 1 line
2.43.5
Martin KaFai Lau
reviewerRe: [PATCH bpf-next v9 12/12] selftests/bpf: add simple bpf tests in the tx path for timestamping feature
Quoted 3 lines · Jason Xing
--- .../bpf/prog_tests/so_timestamping.c | 79 +++++ .../selftests/bpf/progs/so_timestamping.c | 312 ++++++++++++++++++
A bike shedding. s/so_timestamping.c/net_timestamping.c/
Quoted 68 lines
tools/testing/selftests/bpf/progs/so_timestamping.c new file +62
-0@@ -0,0 +1,312 @@ +#include "vmlinux.h" +#include "bpf_tracing_net.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_misc.h" +#include "bpf_kfuncs.h" +#define BPF_PROG_TEST_TCP_HDR_OPTIONS +#include "test_tcp_hdr_options.h" +#include <errno.h> + +#define SK_BPF_CB_FLAGS 1009 +#define SK_BPF_CB_TX_TIMESTAMPING 1 + +int nr_active; +int nr_snd; +int nr_passive; +int nr_sched; +int nr_txsw; +int nr_ack; + +struct sockopt_test { +int opt; +int new; +}; + +static const struct sockopt_test sol_socket_tests[] = { + { .opt =SK_BPF_CB_FLAGS , .new =SK_BPF_CB_TX_TIMESTAMPING , }, + { .opt =0 , }, +}; + +struct loop_ctx { +void *ctx; +const struct sock *sk; +}; + +struct sk_stg { +__u64 sendmsg_ns;/* record ts when sendmsg is called */ +}; + +struct sk_tskey { +u64 cookie; +u32 tskey; +}; + +struct delay_info { +u64 sendmsg_ns;/* record ts when sendmsg is called */ +u32 sched_delay;/* SCHED_OPT_CB - sendmsg_ns */ +u32 sw_snd_delay;/* SW_OPT_CB - SCHED_OPT_CB */ +u32 ack_delay;/* ACK_OPT_CB - SW_OPT_CB */ +}; + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct sk_stg); +} sk_stg_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, struct sk_tskey); + __type(value, struct delay_info);
tools/testing/selftests/bpf/progs/so_timestamping.c line 72
Quoted 10 lines
tools/testing/selftests/bpf/progs/so_timestamping.c new file +10
-0+__uint (max_entries,1024 ); +} time_map SEC(".maps"); + +static u64 delay_tolerance_nsec =10000000000 ;/* 10 second as an example */ + +extern int bpf_sock_ops_enable_tx_tstamp(struct bpf_sock_ops_kern *skops) __ksym; + +static int bpf_test_sockopt_int (void *ctx,const struct sock *sk, +const struct sockopt_test *t, +int level)
This should be the only one that is needed even when supporting the future RX timestamping.
TX and RX timestamping need to be tested independently. Looping it will either enabling them together or disabling them together. It cannot test whether RX will work by itself.
Thus, the bpf_loop won't help. Lets remove it to simplify the test.
Quoted 41 lines
tools/testing/selftests/bpf/progs/so_timestamping.c new file +41
-0+{ +int new, opt, tmp; + + opt = t->opt; + new = t->new; + +if (bpf_setsockopt (ctx, level, opt, &new,sizeof (new))) +return 1 ; + +if (bpf_getsockopt (ctx, level, opt, &tmp,sizeof (tmp)) || + tmp != new) +return 1 ; + +return 0 ; +} + +static int bpf_test_socket_sockopt (__u32 i,struct loop_ctx *lc) +{ +const struct sockopt_test *t; + +if (i >=ARRAY_SIZE (sol_socket_tests)) +return 1 ; + + t = &sol_socket_tests[i]; +if (!t->opt) +return 1 ; + +return bpf_test_sockopt_int (lc->ctx, lc->sk, t,SOL_SOCKET ); +} + +static int bpf_test_sockopt (void *ctx,const struct sock *sk) +{ +struct loop_ctx lc = { .ctx = ctx, .sk = sk, }; +int n; + + n =bpf_loop (ARRAY_SIZE (sol_socket_tests), bpf_test_socket_sockopt, &lc,0 ); +if (n !=ARRAY_SIZE (sol_socket_tests)) +return -1 ; + +return 0 ; +}
tools/testing/selftests/bpf/progs/so_timestamping.c line 123
Quoted 10 lines
tools/testing/selftests/bpf/progs/so_timestamping.c new file +10
-0+ +static bool bpf_test_access_sockopt (void *ctx) +{ +const struct sockopt_test *t; +int tmp, ret, i =0 ; +int level =SOL_SOCKET ; + + t = &sol_socket_tests[i]; + +for (; t->opt;) {
It really does not need a loop here. It only needs to test "one" optname to ensure it is -EOPNOTSUPP.
Quoted 9 lines
tools/testing/selftests/bpf/progs/so_timestamping.c new file +9
-0+ ret =bpf_setsockopt (ctx, level, t->opt, (void *)&t->new,sizeof (t->new)); +if (ret != -EOPNOTSUPP ) +return true; + + ret =bpf_getsockopt (ctx, level, t->opt, &tmp,sizeof (tmp)); +if (ret != -EOPNOTSUPP ) +return true; + +if (++i >=ARRAY_SIZE (sol_socket_tests))
tools/testing/selftests/bpf/progs/so_timestamping.c line 142
Quoted 10 lines
tools/testing/selftests/bpf/progs/so_timestamping.c new file +10
-0+break ; + } + +return false; +} + +/* Adding a simple test to see if we can get an expected value */ +static bool bpf_test_access_load_hdr_opt (struct bpf_sock_ops *skops) +{ +struct tcp_opt reg_opt;
Just noticed this one. Use a plain u8 array. Then no need to include the "test_tcp_hdr_options.h" from an unrelated test.
tools/testing/selftests/bpf/progs/so_timestamping.c line 146
Quoted 4 lines
tools/testing/selftests/bpf/progs/so_timestamping.c new file +4
-0+int load_flags =0 ; +int ret; + + reg_opt.kind =TCPOPT_EXP ;
The kind could be any integer, e.g. 2.
Quoted 8 lines
tools/testing/selftests/bpf/progs/so_timestamping.c new file +8
-0+ reg_opt.len =0 ; + reg_opt.data32 =0 ; + ret =bpf_load_hdr_opt (skops, ®_opt,sizeof (reg_opt), load_flags); +if (ret != -EOPNOTSUPP ) +return true; + +return false; +}
Re: [PATCH bpf-next v9 12/12] selftests/bpf: add simple bpf tests in the tx path for timestamping feature
Quoted 7 lines · Martin KaFai Lau
Quoted 3 lines · Jason Xing
--- .../bpf/prog_tests/so_timestamping.c | 79 +++++ .../selftests/bpf/progs/so_timestamping.c | 312 ++++++++++++++++++A bike shedding. s/so_timestamping.c/net_timestamping.c/
Will rename them.
Quoted 83 lines
Quoted 69 lines
tools/testing/selftests/bpf/progs/so_timestamping.c new file +62
-0@@ -0,0 +1,312 @@ +#include "vmlinux.h" +#include "bpf_tracing_net.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_misc.h" +#include "bpf_kfuncs.h" +#define BPF_PROG_TEST_TCP_HDR_OPTIONS +#include "test_tcp_hdr_options.h" +#include <errno.h> + +#define SK_BPF_CB_FLAGS 1009 +#define SK_BPF_CB_TX_TIMESTAMPING 1 + +int nr_active; +int nr_snd; +int nr_passive; +int nr_sched; +int nr_txsw; +int nr_ack; + +struct sockopt_test { +int opt; +int new; +}; + +static const struct sockopt_test sol_socket_tests[] = { + { .opt =SK_BPF_CB_FLAGS , .new =SK_BPF_CB_TX_TIMESTAMPING , }, + { .opt =0 , }, +}; + +struct loop_ctx { +void *ctx; +const struct sock *sk; +}; + +struct sk_stg { +__u64 sendmsg_ns;/* record ts when sendmsg is called */ +}; + +struct sk_tskey { +u64 cookie; +u32 tskey; +}; + +struct delay_info { +u64 sendmsg_ns;/* record ts when sendmsg is called */ +u32 sched_delay;/* SCHED_OPT_CB - sendmsg_ns */ +u32 sw_snd_delay;/* SW_OPT_CB - SCHED_OPT_CB */ +u32 ack_delay;/* ACK_OPT_CB - SW_OPT_CB */ +}; + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct sk_stg); +} sk_stg_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, struct sk_tskey); + __type(value, struct delay_info);tools/testing/selftests/bpf/progs/so_timestamping.c line 72
Quoted 10 lines
tools/testing/selftests/bpf/progs/so_timestamping.c new file +10
-0+__uint (max_entries,1024 ); +} time_map SEC(".maps"); + +static u64 delay_tolerance_nsec =10000000000 ;/* 10 second as an example */ + +extern int bpf_sock_ops_enable_tx_tstamp(struct bpf_sock_ops_kern *skops) __ksym; + +static int bpf_test_sockopt_int (void *ctx,const struct sock *sk, +const struct sockopt_test *t, +int level)This should be the only one that is needed even when supporting the future RX timestamping.
Quoted 5 lines
TX and RX timestamping need to be tested independently. Looping it will either enabling them together or disabling them together. It cannot test whether RX will work by itself.
Thus, the
bpf_loopwon't help. Lets remove it to simplify the test.
Got it. Will remove it.
Quoted 70 lines
Quoted 42 lines
tools/testing/selftests/bpf/progs/so_timestamping.c new file +41
-0+{ +int new, opt, tmp; + + opt = t->opt; + new = t->new; + +if (bpf_setsockopt (ctx, level, opt, &new,sizeof (new))) +return 1 ; + +if (bpf_getsockopt (ctx, level, opt, &tmp,sizeof (tmp)) || + tmp != new) +return 1 ; + +return 0 ; +} + +static int bpf_test_socket_sockopt (__u32 i,struct loop_ctx *lc) +{ +const struct sockopt_test *t; + +if (i >=ARRAY_SIZE (sol_socket_tests)) +return 1 ; + + t = &sol_socket_tests[i]; +if (!t->opt) +return 1 ; + +return bpf_test_sockopt_int (lc->ctx, lc->sk, t,SOL_SOCKET ); +} + +static int bpf_test_sockopt (void *ctx,const struct sock *sk) +{ +struct loop_ctx lc = { .ctx = ctx, .sk = sk, }; +int n; + + n =bpf_loop (ARRAY_SIZE (sol_socket_tests), bpf_test_socket_sockopt, &lc,0 ); +if (n !=ARRAY_SIZE (sol_socket_tests)) +return -1 ; + +return 0 ; +}tools/testing/selftests/bpf/progs/so_timestamping.c line 123
Quoted 10 lines
tools/testing/selftests/bpf/progs/so_timestamping.c new file +10
-0+ +static bool bpf_test_access_sockopt (void *ctx) +{ +const struct sockopt_test *t; +int tmp, ret, i =0 ; +int level =SOL_SOCKET ; + + t = &sol_socket_tests[i]; + +for (; t->opt;) {It really does not need a loop here. It only needs to test "one" optname to ensure it is
-EOPNOTSUPP.Quoted 14 lines
tools/testing/selftests/bpf/progs/so_timestamping.c new file +14
-0+ ret =bpf_setsockopt (ctx, level, t->opt, (void *)&t->new,sizeof (t->new)); +if (ret != -EOPNOTSUPP ) +return true; + + ret =bpf_getsockopt (ctx, level, t->opt, &tmp,sizeof (tmp)); +if (ret != -EOPNOTSUPP ) +return true; + +if (++i >=ARRAY_SIZE (sol_socket_tests)) +break ; + } + +return false; +}
Quoted 8 lines
tools/testing/selftests/bpf/progs/so_timestamping.c line 142
Quoted 5 lines
tools/testing/selftests/bpf/progs/so_timestamping.c new file +5
-0+ +/* Adding a simple test to see if we can get an expected value */ +static bool bpf_test_access_load_hdr_opt (struct bpf_sock_ops *skops) +{ +struct tcp_opt reg_opt;Just noticed this one. Use a plain u8 array. Then no need to include the "
test_tcp_hdr_options.h" from an unrelated test.
Will update it.
Thanks,
Jason
Quoted 16 lines
tools/testing/selftests/bpf/progs/so_timestamping.c line 146
Quoted 5 lines
tools/testing/selftests/bpf/progs/so_timestamping.c new file +4
-0+int load_flags =0 ; +int ret; + + reg_opt.kind =TCPOPT_EXP ;The kind could be any integer, e.g. 2.
Quoted 8 lines
tools/testing/selftests/bpf/progs/so_timestamping.c new file +8
-0+ reg_opt.len =0 ; + reg_opt.data32 =0 ; + ret =bpf_load_hdr_opt (skops, ®_opt,sizeof (reg_opt), load_flags); +if (ret != -EOPNOTSUPP ) +return true; + +return false; +}
Martin KaFai Lau
reviewerQuoted 17 lines · Jason Xing
"Timestamping is key to debugging network stack latency. With
SO_TIMESTAMPING, bugs that are otherwise incorrectly assumed to be network issues can be attributed to the kernel." This is extracted from the talk "SO_TIMESTAMPING: Powering Fleetwide RPC Monitoring" addressed by Willem de Bruijn at netdevconf0x17).There are a few areas that need optimization with the consideration of easier use and less performance impact, which I highlighted and mainly discussed at netconf 2024 with Willem de Bruijn and John Fastabend:
uAPI compatibility, extra system call overhead, and the need for application modification. I initially managed to solve these issues by writing a kernel module that hooks various key functions. However, this approach is not suitable for the next kernel release. Therefore, a BPF extension was proposed. During recent period, Martin KaFai Lau provides invaluable suggestions about BPF along the way. Many thanks here!
Quoted 1 line
In this series, only support foundamental codes and tx for TCP.
typo: fundamental.... This had been brought up before (in v7?).
By fundamental, I suspect you meant (?) bpf timestamping infrastructure, like: "This series adds the BPF networking timestamping infrastructure. This series also adds TX timestamping support for TCP. The RX timestamping and UDP support will be added in the future."
Quoted 1 line
This approach mostly relies on existing
SO_TIMESTAMPINGfeature, users
It reuses most of the tx timestamping callback that is currently enabled by the SO_TIMESTAMPING. However, I don't think there is a lot of overlap in term of the SO_TIMESTAMPING api which does feel like API reuse when first reading this comment.
Quoted 107 lines
only needs to pass certain flags through
bpf_setsocktopt()to a separate tsflags. Please see the last selftest patch in this series.---
v81. adjust some commit messages and titles
2. add sk cookie in selftests
3. handle the NULL pointer in hwstamp
4. use kfunc to do selective samplingv7
1. target bpf-next tree
2. simplely and directly stop timestamping callbacks calling a few BPF CALLS due to safety concern.
3. add more new testcases and adjust the existing testcases
4. revise some comments of new timestamping callbacks
5. remove a few BPF CGROUP locksRFC v6
In the meantime, any suggestions and reviews are welcome!1. handle those safety problem by using the correct method.
2. supportbpf_getsockopt.
3. adjust the position ofBPF_SOCK_OPS_TS_TCP_SND_CB
4. fix mishandling the hardware timestamp error
5. add more corresponding testsv5
1. handle the safety issus when someone tries to call unrelated bpf helpers.
2. avoid adding direct function call in the hot path like__dev_queue_xmit()
3. remove reporting the hardware timestamp and tskey since they can be fetched through the existing helper with the help ofbpf_skops_init_skb(), please see the selftest.
4. add new sendmsg callback intcp_sendmsg, and introducetskey_bpfused by bpf program to correlatetcp_sendmsgwith other hook points in patch [13/15].v4
1. introduce
sk->sk_bpf_cb_flagsto let user usebpf_setsockopt()(Martin)
2. introduceSKBTX_BPFto enable the bpfSO_TIMESTAMPINGfeature (Martin)
3. introduce bpf map in tests (Martin)
4. I choose to make this series as simple as possible, so I only support most cases in the tx path for TCP protocol.v3
1. support UDP proto by introducing a new generation point.
2. forOPT_ID, introducingsk_tskey_bpf_offsetto compute the delta between the current socket key and bpf socket key. It is desiged for UDP, which also applies to TCP.
3. supportbpf_getsockopt()
4. use cgroup static key instead.
5. add one simple bpf selftest to show how it can be used.
6. remove the rx support from v2 because the number of patches could exceed the limit of one series.V2
1. Introduce tsflag requestors so that we are able to extend more in the future. Besides, it enables TX flags for bpf extension feature separately without breaking users. It is suggested by Vadim Fedorenko.
2. introduce a static key to control the whole feature. (Willem)
3. Open the gate ofbpf_setsockoptfor theSO_TIMESTAMPINGfeature in some TX/RX cases, not all the cases.Jason Xing (12):
bpf: add support forbpf_setsockopt()
bpf: prepare for timestamping callbacks use
bpf: stop unsafely accessing TCP fields in bpf callbacks
bpf: stop calling somesock_opBPF CALLs in new timestamping callbacks
net-timestamp: prepare for isolating two modes ofSO_TIMESTAMPING
bpf: supportSCM_TSTAMP_SCHEDofSO_TIMESTAMPING
bpf: support swSCM_TSTAMP_SNDofSO_TIMESTAMPING
bpf: support hwSCM_TSTAMP_SNDofSO_TIMESTAMPING
bpf: supportSCM_TSTAMP_ACKofSO_TIMESTAMPING
bpf: add a new callback intcp_tx_timestamp()
bpf: support selective sampling for bpf timestamping selftests/bpf: add simple bpf tests in the tx path for timestamping
featureinclude/linux/filter.h | 1 + include/linux/skbuff.h | 12 +- include/net/sock.h | 10 + include/net/tcp.h | 5 +- include/uapi/linux/bpf.h | 30 ++ kernel/bpf/btf.c | 1 + net/core/dev.c | 3 +- net/core/filter.c | 75 ++++- net/core/skbuff.c | 48 ++- net/core/sock.c | 15 + net/dsa/user.c | 2 +- net/ipv4/tcp.c | 4 + net/ipv4/tcp_input.c | 2 + net/ipv4/tcp_output.c | 2 + net/socket.c | 2 +- tools/include/uapi/linux/bpf.h | 23 ++ .../bpf/prog_tests/so_timestamping.c | 79 +++++ .../selftests/bpf/progs/so_timestamping.c | 312 ++++++++++++++++++ 18 files changed, 612 insertions(+), 14 deletions(-)create mode 100644
tools/testing/selftests/bpf/prog_tests/so_timestamping.ccreate mode 100644tools/testing/selftests/bpf/progs/so_timestamping.c
Quoted 19 lines · Martin KaFai Lau
Quoted 17 lines · Jason Xing
"Timestamping is key to debugging network stack latency. With
SO_TIMESTAMPING, bugs that are otherwise incorrectly assumed to be network issues can be attributed to the kernel." This is extracted from the talk "SO_TIMESTAMPING: Powering Fleetwide RPC Monitoring" addressed by Willem de Bruijn at netdevconf0x17).There are a few areas that need optimization with the consideration of easier use and less performance impact, which I highlighted and mainly discussed at netconf 2024 with Willem de Bruijn and John Fastabend:
uAPI compatibility, extra system call overhead, and the need for application modification. I initially managed to solve these issues by writing a kernel module that hooks various key functions. However, this approach is not suitable for the next kernel release. Therefore, a BPF extension was proposed. During recent period, Martin KaFai Lau provides invaluable suggestions about BPF along the way. Many thanks here!
Quoted 3 lines
Quoted 1 line
In this series, only support foundamental codes and tx for TCP.
typo: fundamental.... This had been brought up before (in v7?).
Oh, right!
Quoted 5 lines
By fundamental, I suspect you meant (?) bpf timestamping infrastructure, like:
"This series adds the BPF networking timestamping infrastructure. This series also adds TX timestamping support for TCP. The RX timestamping and UDP support will be added in the future."
Right!
Quoted 6 lines
Quoted 2 lines
This approach mostly relies on existing
SO_TIMESTAMPINGfeature, usersIt reuses most of the tx timestamping callback that is currently enabled by the
SO_TIMESTAMPING. However, I don't think there is a lot of overlap in term of theSO_TIMESTAMPINGapi which does feel like API reuse when first reading this comment.
I'm going to refine them. Thanks for the review!
Thanks,
Jason
Quoted 109 lines
Quoted 108 lines
only needs to pass certain flags through
bpf_setsocktopt()to a separate tsflags. Please see the last selftest patch in this series.---
v81. adjust some commit messages and titles
2. add sk cookie in selftests
3. handle the NULL pointer in hwstamp
4. use kfunc to do selective samplingv7
1. target bpf-next tree
2. simplely and directly stop timestamping callbacks calling a few BPF CALLS due to safety concern.
3. add more new testcases and adjust the existing testcases
4. revise some comments of new timestamping callbacks
5. remove a few BPF CGROUP locksRFC v6
In the meantime, any suggestions and reviews are welcome!1. handle those safety problem by using the correct method.
2. supportbpf_getsockopt.
3. adjust the position ofBPF_SOCK_OPS_TS_TCP_SND_CB
4. fix mishandling the hardware timestamp error
5. add more corresponding testsv5
1. handle the safety issus when someone tries to call unrelated bpf helpers.
2. avoid adding direct function call in the hot path like__dev_queue_xmit()
3. remove reporting the hardware timestamp and tskey since they can be fetched through the existing helper with the help ofbpf_skops_init_skb(), please see the selftest.
4. add new sendmsg callback intcp_sendmsg, and introducetskey_bpfused by bpf program to correlatetcp_sendmsgwith other hook points in patch [13/15].v4
1. introduce
sk->sk_bpf_cb_flagsto let user usebpf_setsockopt()(Martin)
2. introduceSKBTX_BPFto enable the bpfSO_TIMESTAMPINGfeature (Martin)
3. introduce bpf map in tests (Martin)
4. I choose to make this series as simple as possible, so I only support most cases in the tx path for TCP protocol.v3
1. support UDP proto by introducing a new generation point.
2. forOPT_ID, introducingsk_tskey_bpf_offsetto compute the delta between the current socket key and bpf socket key. It is desiged for UDP, which also applies to TCP.
3. supportbpf_getsockopt()
4. use cgroup static key instead.
5. add one simple bpf selftest to show how it can be used.
6. remove the rx support from v2 because the number of patches could exceed the limit of one series.V2
1. Introduce tsflag requestors so that we are able to extend more in the future. Besides, it enables TX flags for bpf extension feature separately without breaking users. It is suggested by Vadim Fedorenko.
2. introduce a static key to control the whole feature. (Willem)
3. Open the gate ofbpf_setsockoptfor theSO_TIMESTAMPINGfeature in some TX/RX cases, not all the cases.Jason Xing (12):
bpf: add support forbpf_setsockopt()
bpf: prepare for timestamping callbacks use
bpf: stop unsafely accessing TCP fields in bpf callbacks
bpf: stop calling somesock_opBPF CALLs in new timestamping callbacks
net-timestamp: prepare for isolating two modes ofSO_TIMESTAMPING
bpf: supportSCM_TSTAMP_SCHEDofSO_TIMESTAMPING
bpf: support swSCM_TSTAMP_SNDofSO_TIMESTAMPING
bpf: support hwSCM_TSTAMP_SNDofSO_TIMESTAMPING
bpf: supportSCM_TSTAMP_ACKofSO_TIMESTAMPING
bpf: add a new callback intcp_tx_timestamp()
bpf: support selective sampling for bpf timestamping selftests/bpf: add simple bpf tests in the tx path for timestamping
featureinclude/linux/filter.h | 1 + include/linux/skbuff.h | 12 +- include/net/sock.h | 10 + include/net/tcp.h | 5 +- include/uapi/linux/bpf.h | 30 ++ kernel/bpf/btf.c | 1 + net/core/dev.c | 3 +- net/core/filter.c | 75 ++++- net/core/skbuff.c | 48 ++- net/core/sock.c | 15 + net/dsa/user.c | 2 +- net/ipv4/tcp.c | 4 + net/ipv4/tcp_input.c | 2 + net/ipv4/tcp_output.c | 2 + net/socket.c | 2 +- tools/include/uapi/linux/bpf.h | 23 ++ .../bpf/prog_tests/so_timestamping.c | 79 +++++ .../selftests/bpf/progs/so_timestamping.c | 312 ++++++++++++++++++ 18 files changed, 612 insertions(+), 14 deletions(-)create mode 100644
tools/testing/selftests/bpf/prog_tests/so_timestamping.ccreate mode 100644tools/testing/selftests/bpf/progs/so_timestamping.c