From 70a217f1976f75a6cfe8223e5669ad7b405daaad Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 20 Aug 2020 12:00:14 -0700 Subject: tcp: Use a struct to represent a saved_syn The TCP_SAVE_SYN has both the network header and tcp header. The total length of the saved syn packet is currently stored in the first 4 bytes (u32) of an array and the actual packet data is stored after that. A later patch will add a bpf helper that allows to get the tcp header alone from the saved syn without the network header. It will be more convenient to have a direct offset to a specific header instead of re-parsing it. This requires to separately store the network hdrlen. The total header length (i.e. network + tcp) is still needed for the current usage in getsockopt. Although this total length can be obtained by looking into the tcphdr and then get the (th->doff << 2), this patch chooses to directly store the tcp hdrlen in the second four bytes of this newly created "struct saved_syn". By using a new struct, it can give a readable name to each individual header length. Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Reviewed-by: Eric Dumazet Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20200820190014.2883694-1-kafai@fb.com --- include/net/request_sock.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index b2eb8b4ba697..7d9ed99a77bd 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -41,6 +41,12 @@ struct request_sock_ops { int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req); +struct saved_syn { + u32 network_hdrlen; + u32 tcp_hdrlen; + u8 data[]; +}; + /* struct request_sock - mini sock to represent a connection request */ struct request_sock { @@ -60,7 +66,7 @@ struct request_sock { struct timer_list rsk_timer; const struct request_sock_ops *rsk_ops; struct sock *sk; - u32 *saved_syn; + struct saved_syn *saved_syn; u32 secid; u32 peer_secid; }; -- cgit v1.2.3 From 2b8ee4f05d4f6a6c427ad30dd6c1bb49eb2efd3b Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 20 Aug 2020 12:00:21 -0700 Subject: tcp: bpf: Add TCP_BPF_DELACK_MAX setsockopt This change is mostly from an internal patch and adapts it from sysctl config to the bpf_setsockopt setup. The bpf_prog can set the max delay ack by using bpf_setsockopt(TCP_BPF_DELACK_MAX). This max delay ack can be communicated to its peer through bpf header option. The receiving peer can then use this max delay ack and set a potentially lower rto by using bpf_setsockopt(TCP_BPF_RTO_MIN) which will be introduced in the next patch. Another later selftest patch will also use it like the above to show how to write and parse bpf tcp header option. Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Reviewed-by: Eric Dumazet Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20200820190021.2884000-1-kafai@fb.com --- include/net/inet_connection_sock.h | 1 + include/uapi/linux/bpf.h | 1 + net/core/filter.c | 8 ++++++++ net/ipv4/tcp.c | 2 ++ net/ipv4/tcp_output.c | 2 ++ tools/include/uapi/linux/bpf.h | 1 + 6 files changed, 15 insertions(+) (limited to 'include/net') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index aa8893c68c50..da7264a1ebfc 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -86,6 +86,7 @@ struct inet_connection_sock { struct timer_list icsk_retransmit_timer; struct timer_list icsk_delack_timer; __u32 icsk_rto; + __u32 icsk_delack_max; __u32 icsk_pmtu_cookie; const struct tcp_congestion_ops *icsk_ca_ops; const struct inet_connection_sock_af_ops *icsk_af_ops; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a1bbaff7a0af..7b905cb0213e 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4257,6 +4257,7 @@ enum { enum { TCP_BPF_IW = 1001, /* Set TCP initial congestion window */ TCP_BPF_SNDCWND_CLAMP = 1002, /* Set sndcwnd_clamp */ + TCP_BPF_DELACK_MAX = 1003, /* Max delay ack in usecs */ }; struct bpf_perf_event_value { diff --git a/net/core/filter.c b/net/core/filter.c index c847b1285acd..80fe7420f609 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4459,6 +4459,7 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname, } else { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); + unsigned long timeout; if (optlen != sizeof(int)) return -EINVAL; @@ -4480,6 +4481,13 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname, tp->snd_ssthresh = val; } break; + case TCP_BPF_DELACK_MAX: + timeout = usecs_to_jiffies(val); + if (timeout > TCP_DELACK_MAX || + timeout < TCP_TIMEOUT_MIN) + return -EINVAL; + inet_csk(sk)->icsk_delack_max = timeout; + break; case TCP_SAVE_SYN: if (val < 0 || val > 1) ret = -EINVAL; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 87d3036d8bd8..44c353a39ad4 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -418,6 +418,7 @@ void tcp_init_sock(struct sock *sk) INIT_LIST_HEAD(&tp->tsorted_sent_queue); icsk->icsk_rto = TCP_TIMEOUT_INIT; + icsk->icsk_delack_max = TCP_DELACK_MAX; tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); minmax_reset(&tp->rtt_min, tcp_jiffies32, ~0U); @@ -2685,6 +2686,7 @@ int tcp_disconnect(struct sock *sk, int flags) icsk->icsk_backoff = 0; icsk->icsk_probes_out = 0; icsk->icsk_rto = TCP_TIMEOUT_INIT; + icsk->icsk_delack_max = TCP_DELACK_MAX; tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd = TCP_INIT_CWND; tp->snd_cwnd_cnt = 0; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 85ff417bda7f..44ffa4891beb 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3741,6 +3741,8 @@ void tcp_send_delayed_ack(struct sock *sk) ato = min(ato, max_ato); } + ato = min_t(u32, ato, inet_csk(sk)->icsk_delack_max); + /* Stay within the limit we were given */ timeout = jiffies + ato; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index a1bbaff7a0af..7b905cb0213e 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4257,6 +4257,7 @@ enum { enum { TCP_BPF_IW = 1001, /* Set TCP initial congestion window */ TCP_BPF_SNDCWND_CLAMP = 1002, /* Set sndcwnd_clamp */ + TCP_BPF_DELACK_MAX = 1003, /* Max delay ack in usecs */ }; struct bpf_perf_event_value { -- cgit v1.2.3 From ca584ba070864c606f3a54faaafe774726d5b4a1 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 20 Aug 2020 12:00:27 -0700 Subject: tcp: bpf: Add TCP_BPF_RTO_MIN for bpf_setsockopt This patch adds bpf_setsockopt(TCP_BPF_RTO_MIN) to allow bpf prog to set the min rto of a connection. It could be used together with the earlier patch which has added bpf_setsockopt(TCP_BPF_DELACK_MAX). A later selftest patch will communicate the max delay ack in a bpf tcp header option and then the receiving side can use bpf_setsockopt(TCP_BPF_RTO_MIN) to set a shorter rto. Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Reviewed-by: Eric Dumazet Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20200820190027.2884170-1-kafai@fb.com --- include/net/inet_connection_sock.h | 1 + include/net/tcp.h | 2 +- include/uapi/linux/bpf.h | 1 + net/core/filter.c | 7 +++++++ net/ipv4/tcp.c | 2 ++ tools/include/uapi/linux/bpf.h | 1 + 6 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index da7264a1ebfc..c738abeb3265 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -86,6 +86,7 @@ struct inet_connection_sock { struct timer_list icsk_retransmit_timer; struct timer_list icsk_delack_timer; __u32 icsk_rto; + __u32 icsk_rto_min; __u32 icsk_delack_max; __u32 icsk_pmtu_cookie; const struct tcp_congestion_ops *icsk_ca_ops; diff --git a/include/net/tcp.h b/include/net/tcp.h index eab6c7510b5b..dda778c782fe 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -699,7 +699,7 @@ static inline void tcp_fast_path_check(struct sock *sk) static inline u32 tcp_rto_min(struct sock *sk) { const struct dst_entry *dst = __sk_dst_get(sk); - u32 rto_min = TCP_RTO_MIN; + u32 rto_min = inet_csk(sk)->icsk_rto_min; if (dst && dst_metric_locked(dst, RTAX_RTO_MIN)) rto_min = dst_metric_rtt(dst, RTAX_RTO_MIN); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 7b905cb0213e..1ae20058b574 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4258,6 +4258,7 @@ enum { TCP_BPF_IW = 1001, /* Set TCP initial congestion window */ TCP_BPF_SNDCWND_CLAMP = 1002, /* Set sndcwnd_clamp */ TCP_BPF_DELACK_MAX = 1003, /* Max delay ack in usecs */ + TCP_BPF_RTO_MIN = 1004, /* Min delay ack in usecs */ }; struct bpf_perf_event_value { diff --git a/net/core/filter.c b/net/core/filter.c index 80fe7420f609..075ab71b985c 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4488,6 +4488,13 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname, return -EINVAL; inet_csk(sk)->icsk_delack_max = timeout; break; + case TCP_BPF_RTO_MIN: + timeout = usecs_to_jiffies(val); + if (timeout > TCP_RTO_MIN || + timeout < TCP_TIMEOUT_MIN) + return -EINVAL; + inet_csk(sk)->icsk_rto_min = timeout; + break; case TCP_SAVE_SYN: if (val < 0 || val > 1) ret = -EINVAL; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 44c353a39ad4..6075cb091a20 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -418,6 +418,7 @@ void tcp_init_sock(struct sock *sk) INIT_LIST_HEAD(&tp->tsorted_sent_queue); icsk->icsk_rto = TCP_TIMEOUT_INIT; + icsk->icsk_rto_min = TCP_RTO_MIN; icsk->icsk_delack_max = TCP_DELACK_MAX; tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); minmax_reset(&tp->rtt_min, tcp_jiffies32, ~0U); @@ -2686,6 +2687,7 @@ int tcp_disconnect(struct sock *sk, int flags) icsk->icsk_backoff = 0; icsk->icsk_probes_out = 0; icsk->icsk_rto = TCP_TIMEOUT_INIT; + icsk->icsk_rto_min = TCP_RTO_MIN; icsk->icsk_delack_max = TCP_DELACK_MAX; tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd = TCP_INIT_CWND; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 7b905cb0213e..1ae20058b574 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4258,6 +4258,7 @@ enum { TCP_BPF_IW = 1001, /* Set TCP initial congestion window */ TCP_BPF_SNDCWND_CLAMP = 1002, /* Set sndcwnd_clamp */ TCP_BPF_DELACK_MAX = 1003, /* Max delay ack in usecs */ + TCP_BPF_RTO_MIN = 1004, /* Min delay ack in usecs */ }; struct bpf_perf_event_value { -- cgit v1.2.3 From 72be0fe6ba76282704cb84952bd5a1eb47910290 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 20 Aug 2020 12:00:39 -0700 Subject: bpf: tcp: Add bpf_skops_established() In tcp_init_transfer(), it currently calls the bpf prog to give it a chance to handle the just "ESTABLISHED" event (e.g. do setsockopt on the newly established sk). Right now, it is done by calling the general purpose tcp_call_bpf(). In the later patch, it also needs to pass the just-received skb which concludes the 3 way handshake. E.g. the SYNACK received at the active side. The bpf prog can then learn some specific header options written by the peer's bpf-prog and potentially do setsockopt on the newly established sk. Thus, instead of reusing the general purpose tcp_call_bpf(), a new function bpf_skops_established() is added to allow passing the "skb" to the bpf prog. The actual skb passing from bpf_skops_established() to the bpf prog will happen together in a later patch which has the necessary bpf pieces. A "skb" arg is also added to tcp_init_transfer() such that it can then be passed to bpf_skops_established(). Calling the new bpf_skops_established() instead of tcp_call_bpf() should be a noop in this patch. Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20200820190039.2884750-1-kafai@fb.com --- include/net/tcp.h | 2 +- net/ipv4/tcp_fastopen.c | 2 +- net/ipv4/tcp_input.c | 32 ++++++++++++++++++++++++++++---- 3 files changed, 30 insertions(+), 6 deletions(-) (limited to 'include/net') diff --git a/include/net/tcp.h b/include/net/tcp.h index dda778c782fe..c186dbf731e1 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -394,7 +394,7 @@ void tcp_metrics_init(void); bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst); void tcp_close(struct sock *sk, long timeout); void tcp_init_sock(struct sock *sk); -void tcp_init_transfer(struct sock *sk, int bpf_op); +void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb); __poll_t tcp_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait); int tcp_getsockopt(struct sock *sk, int level, int optname, diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 09b62de04eea..af2814c9342a 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -295,7 +295,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, refcount_set(&req->rsk_refcnt, 2); /* Now finish processing the fastopen child socket. */ - tcp_init_transfer(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB); + tcp_init_transfer(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB, skb); tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 9072d9160df9..7b0faa2bfe32 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -138,6 +138,29 @@ void clean_acked_data_flush(void) EXPORT_SYMBOL_GPL(clean_acked_data_flush); #endif +#ifdef CONFIG_CGROUP_BPF +static void bpf_skops_established(struct sock *sk, int bpf_op, + struct sk_buff *skb) +{ + struct bpf_sock_ops_kern sock_ops; + + sock_owned_by_me(sk); + + memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp)); + sock_ops.op = bpf_op; + sock_ops.is_fullsock = 1; + sock_ops.sk = sk; + /* skb will be passed to the bpf prog in a later patch. */ + + BPF_CGROUP_RUN_PROG_SOCK_OPS(&sock_ops); +} +#else +static void bpf_skops_established(struct sock *sk, int bpf_op, + struct sk_buff *skb) +{ +} +#endif + static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb, unsigned int len) { @@ -5808,7 +5831,7 @@ discard: } EXPORT_SYMBOL(tcp_rcv_established); -void tcp_init_transfer(struct sock *sk, int bpf_op) +void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); @@ -5829,7 +5852,7 @@ void tcp_init_transfer(struct sock *sk, int bpf_op) tp->snd_cwnd = tcp_init_cwnd(tp, __sk_dst_get(sk)); tp->snd_cwnd_stamp = tcp_jiffies32; - tcp_call_bpf(sk, bpf_op, 0, NULL); + bpf_skops_established(sk, bpf_op, skb); tcp_init_congestion_control(sk); tcp_init_buffer_space(sk); } @@ -5848,7 +5871,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb) sk_mark_napi_id(sk, skb); } - tcp_init_transfer(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB); + tcp_init_transfer(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB, skb); /* Prevent spurious tcp_cwnd_restart() on first data * packet. @@ -6320,7 +6343,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) } else { tcp_try_undo_spurious_syn(sk); tp->retrans_stamp = 0; - tcp_init_transfer(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB); + tcp_init_transfer(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB, + skb); WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); } smp_mb(); -- cgit v1.2.3 From 331fca4315efa3bbd258fbdf8209d59d253c0480 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 20 Aug 2020 12:00:52 -0700 Subject: bpf: tcp: Add bpf_skops_hdr_opt_len() and bpf_skops_write_hdr_opt() The bpf prog needs to parse the SYN header to learn what options have been sent by the peer's bpf-prog before writing its options into SYNACK. This patch adds a "syn_skb" arg to tcp_make_synack() and send_synack(). This syn_skb will eventually be made available (as read-only) to the bpf prog. This will be the only SYN packet available to the bpf prog during syncookie. For other regular cases, the bpf prog can also use the saved_syn. When writing options, the bpf prog will first be called to tell the kernel its required number of bytes. It is done by the new bpf_skops_hdr_opt_len(). The bpf prog will only be called when the new BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG is set in tp->bpf_sock_ops_cb_flags. When the bpf prog returns, the kernel will know how many bytes are needed and then update the "*remaining" arg accordingly. 4 byte alignment will be included in the "*remaining" before this function returns. The 4 byte aligned number of bytes will also be stored into the opts->bpf_opt_len. "bpf_opt_len" is a newly added member to the struct tcp_out_options. Then the new bpf_skops_write_hdr_opt() will call the bpf prog to write the header options. The bpf prog is only called if it has reserved spaces before (opts->bpf_opt_len > 0). The bpf prog is the last one getting a chance to reserve header space and writing the header option. These two functions are half implemented to highlight the changes in TCP stack. The actual codes preparing the bpf running context and invoking the bpf prog will be added in the later patch with other necessary bpf pieces. Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/bpf/20200820190052.2885316-1-kafai@fb.com --- include/net/tcp.h | 6 ++- include/uapi/linux/bpf.h | 3 +- net/ipv4/tcp_input.c | 5 +- net/ipv4/tcp_ipv4.c | 5 +- net/ipv4/tcp_output.c | 105 ++++++++++++++++++++++++++++++++++++----- net/ipv6/tcp_ipv6.c | 5 +- tools/include/uapi/linux/bpf.h | 3 +- 7 files changed, 109 insertions(+), 23 deletions(-) (limited to 'include/net') diff --git a/include/net/tcp.h b/include/net/tcp.h index c186dbf731e1..3e768a6b8264 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -455,7 +455,8 @@ enum tcp_synack_type { struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, struct request_sock *req, struct tcp_fastopen_cookie *foc, - enum tcp_synack_type synack_type); + enum tcp_synack_type synack_type, + struct sk_buff *syn_skb); int tcp_disconnect(struct sock *sk, int flags); void tcp_finish_connect(struct sock *sk, struct sk_buff *skb); @@ -2035,7 +2036,8 @@ struct tcp_request_sock_ops { int (*send_synack)(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, struct tcp_fastopen_cookie *foc, - enum tcp_synack_type synack_type); + enum tcp_synack_type synack_type, + struct sk_buff *syn_skb); }; extern const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 010ed2abcb66..18d0e128bc3c 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4175,8 +4175,9 @@ enum { BPF_SOCK_OPS_RTT_CB_FLAG = (1<<3), BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG = (1<<4), BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG = (1<<5), + BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG = (1<<6), /* Mask of all currently supported cb flags */ - BPF_SOCK_OPS_ALL_CB_FLAGS = 0x3F, + BPF_SOCK_OPS_ALL_CB_FLAGS = 0x7F, }; /* List of known BPF sock_ops operators. diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index b520450170d1..8c9da4b65dae 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6824,7 +6824,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, } if (fastopen_sk) { af_ops->send_synack(fastopen_sk, dst, &fl, req, - &foc, TCP_SYNACK_FASTOPEN); + &foc, TCP_SYNACK_FASTOPEN, skb); /* Add the child socket directly into the accept queue */ if (!inet_csk_reqsk_queue_add(sk, req, fastopen_sk)) { reqsk_fastopen_remove(fastopen_sk, req, false); @@ -6842,7 +6842,8 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, tcp_timeout_init((struct sock *)req)); af_ops->send_synack(sk, dst, &fl, req, &foc, !want_cookie ? TCP_SYNACK_NORMAL : - TCP_SYNACK_COOKIE); + TCP_SYNACK_COOKIE, + skb); if (want_cookie) { reqsk_free(req); return 0; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 5084333b5ab6..631a5ee0dd4e 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -965,7 +965,8 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, struct tcp_fastopen_cookie *foc, - enum tcp_synack_type synack_type) + enum tcp_synack_type synack_type, + struct sk_buff *syn_skb) { const struct inet_request_sock *ireq = inet_rsk(req); struct flowi4 fl4; @@ -976,7 +977,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, if (!dst && (dst = inet_csk_route_req(sk, &fl4, req)) == NULL) return -1; - skb = tcp_make_synack(sk, dst, req, foc, synack_type); + skb = tcp_make_synack(sk, dst, req, foc, synack_type, syn_skb); if (skb) { __tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 44ffa4891beb..673db6879e46 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -438,6 +438,7 @@ struct tcp_out_options { u8 ws; /* window scale, 0 to disable */ u8 num_sack_blocks; /* number of SACK blocks to include */ u8 hash_size; /* bytes in hash_location */ + u8 bpf_opt_len; /* length of BPF hdr option */ __u8 *hash_location; /* temporary pointer, overloaded */ __u32 tsval, tsecr; /* need to include OPTION_TS */ struct tcp_fastopen_cookie *fastopen_cookie; /* Fast open cookie */ @@ -452,6 +453,59 @@ static void mptcp_options_write(__be32 *ptr, struct tcp_out_options *opts) #endif } +#ifdef CONFIG_CGROUP_BPF +/* req, syn_skb and synack_type are used when writing synack */ +static void bpf_skops_hdr_opt_len(struct sock *sk, struct sk_buff *skb, + struct request_sock *req, + struct sk_buff *syn_skb, + enum tcp_synack_type synack_type, + struct tcp_out_options *opts, + unsigned int *remaining) +{ + if (likely(!BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), + BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG)) || + !*remaining) + return; + + /* The bpf running context preparation and the actual bpf prog + * calling will be implemented in a later PATCH together with + * other bpf pieces. + */ +} + +static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb, + struct request_sock *req, + struct sk_buff *syn_skb, + enum tcp_synack_type synack_type, + struct tcp_out_options *opts) +{ + if (likely(!opts->bpf_opt_len)) + return; + + /* The bpf running context preparation and the actual bpf prog + * calling will be implemented in a later PATCH together with + * other bpf pieces. + */ +} +#else +static void bpf_skops_hdr_opt_len(struct sock *sk, struct sk_buff *skb, + struct request_sock *req, + struct sk_buff *syn_skb, + enum tcp_synack_type synack_type, + struct tcp_out_options *opts, + unsigned int *remaining) +{ +} + +static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb, + struct request_sock *req, + struct sk_buff *syn_skb, + enum tcp_synack_type synack_type, + struct tcp_out_options *opts) +{ +} +#endif + /* Write previously computed TCP options to the packet. * * Beware: Something in the Internet is very sensitive to the ordering of @@ -691,6 +745,8 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, } } + bpf_skops_hdr_opt_len(sk, skb, NULL, NULL, 0, opts, &remaining); + return MAX_TCP_OPTION_SPACE - remaining; } @@ -701,7 +757,8 @@ static unsigned int tcp_synack_options(const struct sock *sk, struct tcp_out_options *opts, const struct tcp_md5sig_key *md5, struct tcp_fastopen_cookie *foc, - enum tcp_synack_type synack_type) + enum tcp_synack_type synack_type, + struct sk_buff *syn_skb) { struct inet_request_sock *ireq = inet_rsk(req); unsigned int remaining = MAX_TCP_OPTION_SPACE; @@ -758,6 +815,9 @@ static unsigned int tcp_synack_options(const struct sock *sk, smc_set_option_cond(tcp_sk(sk), ireq, opts, &remaining); + bpf_skops_hdr_opt_len((struct sock *)sk, skb, req, syn_skb, + synack_type, opts, &remaining); + return MAX_TCP_OPTION_SPACE - remaining; } @@ -826,6 +886,15 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK; } + if (unlikely(BPF_SOCK_OPS_TEST_FLAG(tp, + BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG))) { + unsigned int remaining = MAX_TCP_OPTION_SPACE - size; + + bpf_skops_hdr_opt_len(sk, skb, NULL, NULL, 0, opts, &remaining); + + size = MAX_TCP_OPTION_SPACE - remaining; + } + return size; } @@ -1213,6 +1282,9 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, } #endif + /* BPF prog is the last one writing header option */ + bpf_skops_write_hdr_opt(sk, skb, NULL, NULL, 0, &opts); + INDIRECT_CALL_INET(icsk->icsk_af_ops->send_check, tcp_v6_send_check, tcp_v4_send_check, sk, skb); @@ -3336,20 +3408,20 @@ int tcp_send_synack(struct sock *sk) } /** - * tcp_make_synack - Prepare a SYN-ACK. - * sk: listener socket - * dst: dst entry attached to the SYNACK - * req: request_sock pointer - * foc: cookie for tcp fast open - * synack_type: Type of synback to prepare - * - * Allocate one skb and build a SYNACK packet. - * @dst is consumed : Caller should not use it again. + * tcp_make_synack - Allocate one skb and build a SYNACK packet. + * @sk: listener socket + * @dst: dst entry attached to the SYNACK. It is consumed and caller + * should not use it again. + * @req: request_sock pointer + * @foc: cookie for tcp fast open + * @synack_type: Type of synack to prepare + * @syn_skb: SYN packet just received. It could be NULL for rtx case. */ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, struct request_sock *req, struct tcp_fastopen_cookie *foc, - enum tcp_synack_type synack_type) + enum tcp_synack_type synack_type, + struct sk_buff *syn_skb) { struct inet_request_sock *ireq = inet_rsk(req); const struct tcp_sock *tp = tcp_sk(sk); @@ -3408,8 +3480,11 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, md5 = tcp_rsk(req)->af_specific->req_md5_lookup(sk, req_to_sk(req)); #endif skb_set_hash(skb, tcp_rsk(req)->txhash, PKT_HASH_TYPE_L4); + /* bpf program will be interested in the tcp_flags */ + TCP_SKB_CB(skb)->tcp_flags = TCPHDR_SYN | TCPHDR_ACK; tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5, - foc, synack_type) + sizeof(*th); + foc, synack_type, + syn_skb) + sizeof(*th); skb_push(skb, tcp_header_size); skb_reset_transport_header(skb); @@ -3441,6 +3516,9 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, rcu_read_unlock(); #endif + bpf_skops_write_hdr_opt((struct sock *)sk, skb, req, syn_skb, + synack_type, &opts); + skb->skb_mstamp_ns = now; tcp_add_tx_delay(skb, tp); @@ -3936,7 +4014,8 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) int res; tcp_rsk(req)->txhash = net_tx_rndhash(); - res = af_ops->send_synack(sk, NULL, &fl, req, NULL, TCP_SYNACK_NORMAL); + res = af_ops->send_synack(sk, NULL, &fl, req, NULL, TCP_SYNACK_NORMAL, + NULL); if (!res) { __TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 305870a72352..87a633e1fbef 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -501,7 +501,8 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, struct tcp_fastopen_cookie *foc, - enum tcp_synack_type synack_type) + enum tcp_synack_type synack_type, + struct sk_buff *syn_skb) { struct inet_request_sock *ireq = inet_rsk(req); struct ipv6_pinfo *np = tcp_inet6_sk(sk); @@ -515,7 +516,7 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, IPPROTO_TCP)) == NULL) goto done; - skb = tcp_make_synack(sk, dst, req, foc, synack_type); + skb = tcp_make_synack(sk, dst, req, foc, synack_type, syn_skb); if (skb) { __tcp_v6_send_check(skb, &ireq->ir_v6_loc_addr, diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 010ed2abcb66..18d0e128bc3c 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4175,8 +4175,9 @@ enum { BPF_SOCK_OPS_RTT_CB_FLAG = (1<<3), BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG = (1<<4), BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG = (1<<5), + BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG = (1<<6), /* Mask of all currently supported cb flags */ - BPF_SOCK_OPS_ALL_CB_FLAGS = 0x3F, + BPF_SOCK_OPS_ALL_CB_FLAGS = 0x7F, }; /* List of known BPF sock_ops operators. -- cgit v1.2.3 From 0813a841566f0962a5551be7749b43c45f0022a0 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 20 Aug 2020 12:01:04 -0700 Subject: bpf: tcp: Allow bpf prog to write and parse TCP header option MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Note: The TCP changes here is mainly to implement the bpf pieces into the bpf_skops_*() functions introduced in the earlier patches. ] The earlier effort in BPF-TCP-CC allows the TCP Congestion Control algorithm to be written in BPF. It opens up opportunities to allow a faster turnaround time in testing/releasing new congestion control ideas to production environment. The same flexibility can be extended to writing TCP header option. It is not uncommon that people want to test new TCP header option to improve the TCP performance. Another use case is for data-center that has a more controlled environment and has more flexibility in putting header options for internal only use. For example, we want to test the idea in putting maximum delay ACK in TCP header option which is similar to a draft RFC proposal [1]. This patch introduces the necessary BPF API and use them in the TCP stack to allow BPF_PROG_TYPE_SOCK_OPS program to parse and write TCP header options. It currently supports most of the TCP packet except RST. Supported TCP header option: ─────────────────────────── This patch allows the bpf-prog to write any option kind. Different bpf-progs can write its own option by calling the new helper bpf_store_hdr_opt(). The helper will ensure there is no duplicated option in the header. By allowing bpf-prog to write any option kind, this gives a lot of flexibility to the bpf-prog. Different bpf-prog can write its own option kind. It could also allow the bpf-prog to support a recently standardized option on an older kernel. Sockops Callback Flags: ────────────────────── The bpf program will only be called to parse/write tcp header option if the following newly added callback flags are enabled in tp->bpf_sock_ops_cb_flags: BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG A few words on the PARSE CB flags. When the above PARSE CB flags are turned on, the bpf-prog will be called on packets received at a sk that has at least reached the ESTABLISHED state. The parsing of the SYN-SYNACK-ACK will be discussed in the "3 Way HandShake" section. The default is off for all of the above new CB flags, i.e. the bpf prog will not be called to parse or write bpf hdr option. There are details comment on these new cb flags in the UAPI bpf.h. sock_ops->skb_data and bpf_load_hdr_opt() ───────────────────────────────────────── sock_ops->skb_data and sock_ops->skb_data_end covers the whole TCP header and its options. They are read only. The new bpf_load_hdr_opt() helps to read a particular option "kind" from the skb_data. Please refer to the comment in UAPI bpf.h. It has details on what skb_data contains under different sock_ops->op. 3 Way HandShake ─────────────── The bpf-prog can learn if it is sending SYN or SYNACK by reading the sock_ops->skb_tcp_flags. * Passive side When writing SYNACK (i.e. sock_ops->op == BPF_SOCK_OPS_WRITE_HDR_OPT_CB), the received SYN skb will be available to the bpf prog. The bpf prog can use the SYN skb (which may carry the header option sent from the remote bpf prog) to decide what bpf header option should be written to the outgoing SYNACK skb. The SYN packet can be obtained by getsockopt(TCP_BPF_SYN*). More on this later. Also, the bpf prog can learn if it is in syncookie mode (by checking sock_ops->args[0] == BPF_WRITE_HDR_TCP_SYNACK_COOKIE). The bpf prog can store the received SYN pkt by using the existing bpf_setsockopt(TCP_SAVE_SYN). The example in a later patch does it. [ Note that the fullsock here is a listen sk, bpf_sk_storage is not very useful here since the listen sk will be shared by many concurrent connection requests. Extending bpf_sk_storage support to request_sock will add weight to the minisock and it is not necessary better than storing the whole ~100 bytes SYN pkt. ] When the connection is established, the bpf prog will be called in the existing PASSIVE_ESTABLISHED_CB callback. At that time, the bpf prog can get the header option from the saved syn and then apply the needed operation to the newly established socket. The later patch will use the max delay ack specified in the SYN header and set the RTO of this newly established connection as an example. The received ACK (that concludes the 3WHS) will also be available to the bpf prog during PASSIVE_ESTABLISHED_CB through the sock_ops->skb_data. It could be useful in syncookie scenario. More on this later. There is an existing getsockopt "TCP_SAVED_SYN" to return the whole saved syn pkt which includes the IP[46] header and the TCP header. A few "TCP_BPF_SYN*" getsockopt has been added to allow specifying where to start getting from, e.g. starting from TCP header, or from IP[46] header. The new getsockopt(TCP_BPF_SYN*) will also know where it can get the SYN's packet from: - (a) the just received syn (available when the bpf prog is writing SYNACK) and it is the only way to get SYN during syncookie mode. or - (b) the saved syn (available in PASSIVE_ESTABLISHED_CB and also other existing CB). The bpf prog does not need to know where the SYN pkt is coming from. The getsockopt(TCP_BPF_SYN*) will hide this details. Similarly, a flags "BPF_LOAD_HDR_OPT_TCP_SYN" is also added to bpf_load_hdr_opt() to read a particular header option from the SYN packet. * Fastopen Fastopen should work the same as the regular non fastopen case. This is a test in a later patch. * Syncookie For syncookie, the later example patch asks the active side's bpf prog to resend the header options in ACK. The server can use bpf_load_hdr_opt() to look at the options in this received ACK during PASSIVE_ESTABLISHED_CB. * Active side The bpf prog will get a chance to write the bpf header option in the SYN packet during WRITE_HDR_OPT_CB. The received SYNACK pkt will also be available to the bpf prog during the existing ACTIVE_ESTABLISHED_CB callback through the sock_ops->skb_data and bpf_load_hdr_opt(). * Turn off header CB flags after 3WHS If the bpf prog does not need to write/parse header options beyond the 3WHS, the bpf prog can clear the bpf_sock_ops_cb_flags to avoid being called for header options. Or the bpf-prog can select to leave the UNKNOWN_HDR_OPT_CB_FLAG on so that the kernel will only call it when there is option that the kernel cannot handle. [1]: draft-wang-tcpm-low-latency-opt-00 https://tools.ietf.org/html/draft-wang-tcpm-low-latency-opt-00 Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200820190104.2885895-1-kafai@fb.com --- include/linux/bpf-cgroup.h | 25 +++ include/linux/filter.h | 4 + include/net/tcp.h | 49 ++++++ include/uapi/linux/bpf.h | 300 ++++++++++++++++++++++++++++++++- net/core/filter.c | 365 +++++++++++++++++++++++++++++++++++++++++ net/ipv4/tcp_input.c | 20 ++- net/ipv4/tcp_minisocks.c | 1 + net/ipv4/tcp_output.c | 104 +++++++++++- tools/include/uapi/linux/bpf.h | 300 ++++++++++++++++++++++++++++++++- 9 files changed, 1150 insertions(+), 18 deletions(-) (limited to 'include/net') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 64f367044e25..2f98d2fce62e 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -279,6 +279,31 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_UDP6_RECVMSG, NULL) +/* The SOCK_OPS"_SK" macro should be used when sock_ops->sk is not a + * fullsock and its parent fullsock cannot be traced by + * sk_to_full_sk(). + * + * e.g. sock_ops->sk is a request_sock and it is under syncookie mode. + * Its listener-sk is not attached to the rsk_listener. + * In this case, the caller holds the listener-sk (unlocked), + * set its sock_ops->sk to req_sk, and call this SOCK_OPS"_SK" with + * the listener-sk such that the cgroup-bpf-progs of the + * listener-sk will be run. + * + * Regardless of syncookie mode or not, + * calling bpf_setsockopt on listener-sk will not make sense anyway, + * so passing 'sock_ops->sk == req_sk' to the bpf prog is appropriate here. + */ +#define BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(sock_ops, sk) \ +({ \ + int __ret = 0; \ + if (cgroup_bpf_enabled) \ + __ret = __cgroup_bpf_run_filter_sock_ops(sk, \ + sock_ops, \ + BPF_CGROUP_SOCK_OPS); \ + __ret; \ +}) + #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) \ ({ \ int __ret = 0; \ diff --git a/include/linux/filter.h b/include/linux/filter.h index c427dfa5f908..995625950cc1 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1241,8 +1241,12 @@ struct bpf_sock_ops_kern { u32 reply; u32 replylong[4]; }; + struct sk_buff *syn_skb; + struct sk_buff *skb; + void *skb_data_end; u8 op; u8 is_fullsock; + u8 remaining_opt_len; u64 temp; /* temp and everything after is not * initialized to 0 before calling * the BPF program. New fields that diff --git a/include/net/tcp.h b/include/net/tcp.h index 3e768a6b8264..1f967b4e22f6 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2235,6 +2235,55 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, int len, int flags); #endif /* CONFIG_NET_SOCK_MSG */ +#ifdef CONFIG_CGROUP_BPF +/* Copy the listen sk's HDR_OPT_CB flags to its child. + * + * During 3-Way-HandShake, the synack is usually sent from + * the listen sk with the HDR_OPT_CB flags set so that + * bpf-prog will be called to write the BPF hdr option. + * + * In fastopen, the child sk is used to send synack instead + * of the listen sk. Thus, inheriting the HDR_OPT_CB flags + * from the listen sk gives the bpf-prog a chance to write + * BPF hdr option in the synack pkt during fastopen. + * + * Both fastopen and non-fastopen child will inherit the + * HDR_OPT_CB flags to keep the bpf-prog having a consistent + * behavior when deciding to clear this cb flags (or not) + * during the PASSIVE_ESTABLISHED_CB. + * + * In the future, other cb flags could be inherited here also. + */ +static inline void bpf_skops_init_child(const struct sock *sk, + struct sock *child) +{ + tcp_sk(child)->bpf_sock_ops_cb_flags = + tcp_sk(sk)->bpf_sock_ops_cb_flags & + (BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG | + BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG | + BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG); +} + +static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops, + struct sk_buff *skb, + unsigned int end_offset) +{ + skops->skb = skb; + skops->skb_data_end = skb->data + end_offset; +} +#else +static inline void bpf_skops_init_child(const struct sock *sk, + struct sock *child) +{ +} + +static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops, + struct sk_buff *skb, + unsigned int end_offset) +{ +} +#endif + /* Call BPF_SOCK_OPS program that returns an int. If the return value * is < 0, then the BPF op failed (for example if the loaded BPF * program does not support the chosen operation or there is no BPF diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 18d0e128bc3c..f67ec5d9e57d 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3395,6 +3395,120 @@ union bpf_attr { * A non-negative value equal to or less than *size* on success, * or a negative error in case of failure. * + * long bpf_load_hdr_opt(struct bpf_sock_ops *skops, void *searchby_res, u32 len, u64 flags) + * Description + * Load header option. Support reading a particular TCP header + * option for bpf program (BPF_PROG_TYPE_SOCK_OPS). + * + * If *flags* is 0, it will search the option from the + * sock_ops->skb_data. The comment in "struct bpf_sock_ops" + * has details on what skb_data contains under different + * sock_ops->op. + * + * The first byte of the *searchby_res* specifies the + * kind that it wants to search. + * + * If the searching kind is an experimental kind + * (i.e. 253 or 254 according to RFC6994). It also + * needs to specify the "magic" which is either + * 2 bytes or 4 bytes. It then also needs to + * specify the size of the magic by using + * the 2nd byte which is "kind-length" of a TCP + * header option and the "kind-length" also + * includes the first 2 bytes "kind" and "kind-length" + * itself as a normal TCP header option also does. + * + * For example, to search experimental kind 254 with + * 2 byte magic 0xeB9F, the searchby_res should be + * [ 254, 4, 0xeB, 0x9F, 0, 0, .... 0 ]. + * + * To search for the standard window scale option (3), + * the searchby_res should be [ 3, 0, 0, .... 0 ]. + * Note, kind-length must be 0 for regular option. + * + * Searching for No-Op (0) and End-of-Option-List (1) are + * not supported. + * + * *len* must be at least 2 bytes which is the minimal size + * of a header option. + * + * Supported flags: + * * **BPF_LOAD_HDR_OPT_TCP_SYN** to search from the + * saved_syn packet or the just-received syn packet. + * + * Return + * >0 when found, the header option is copied to *searchby_res*. + * The return value is the total length copied. + * + * **-EINVAL** If param is invalid + * + * **-ENOMSG** The option is not found + * + * **-ENOENT** No syn packet available when + * **BPF_LOAD_HDR_OPT_TCP_SYN** is used + * + * **-ENOSPC** Not enough space. Only *len* number of + * bytes are copied. + * + * **-EFAULT** Cannot parse the header options in the packet + * + * **-EPERM** This helper cannot be used under the + * current sock_ops->op. + * + * long bpf_store_hdr_opt(struct bpf_sock_ops *skops, const void *from, u32 len, u64 flags) + * Description + * Store header option. The data will be copied + * from buffer *from* with length *len* to the TCP header. + * + * The buffer *from* should have the whole option that + * includes the kind, kind-length, and the actual + * option data. The *len* must be at least kind-length + * long. The kind-length does not have to be 4 byte + * aligned. The kernel will take care of the padding + * and setting the 4 bytes aligned value to th->doff. + * + * This helper will check for duplicated option + * by searching the same option in the outgoing skb. + * + * This helper can only be called during + * BPF_SOCK_OPS_WRITE_HDR_OPT_CB. + * + * Return + * 0 on success, or negative error in case of failure: + * + * **-EINVAL** If param is invalid + * + * **-ENOSPC** Not enough space in the header. + * Nothing has been written + * + * **-EEXIST** The option has already existed + * + * **-EFAULT** Cannot parse the existing header options + * + * **-EPERM** This helper cannot be used under the + * current sock_ops->op. + * + * long bpf_reserve_hdr_opt(struct bpf_sock_ops *skops, u32 len, u64 flags) + * Description + * Reserve *len* bytes for the bpf header option. The + * space will be used by bpf_store_hdr_opt() later in + * BPF_SOCK_OPS_WRITE_HDR_OPT_CB. + * + * If bpf_reserve_hdr_opt() is called multiple times, + * the total number of bytes will be reserved. + * + * This helper can only be called during + * BPF_SOCK_OPS_HDR_OPT_LEN_CB. + * + * Return + * 0 on success, or negative error in case of failure: + * + * **-EINVAL** if param is invalid + * + * **-ENOSPC** Not enough space in the header. + * + * **-EPERM** This helper cannot be used under the + * current sock_ops->op. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3539,6 +3653,9 @@ union bpf_attr { FN(skc_to_tcp_request_sock), \ FN(skc_to_udp6_sock), \ FN(get_task_stack), \ + FN(load_hdr_opt), \ + FN(store_hdr_opt), \ + FN(reserve_hdr_opt), /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -4165,6 +4282,36 @@ struct bpf_sock_ops { __u64 bytes_received; __u64 bytes_acked; __bpf_md_ptr(struct bpf_sock *, sk); + /* [skb_data, skb_data_end) covers the whole TCP header. + * + * BPF_SOCK_OPS_PARSE_HDR_OPT_CB: The packet received + * BPF_SOCK_OPS_HDR_OPT_LEN_CB: Not useful because the + * header has not been written. + * BPF_SOCK_OPS_WRITE_HDR_OPT_CB: The header and options have + * been written so far. + * BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB: The SYNACK that concludes + * the 3WHS. + * BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: The ACK that concludes + * the 3WHS. + * + * bpf_load_hdr_opt() can also be used to read a particular option. + */ + __bpf_md_ptr(void *, skb_data); + __bpf_md_ptr(void *, skb_data_end); + __u32 skb_len; /* The total length of a packet. + * It includes the header, options, + * and payload. + */ + __u32 skb_tcp_flags; /* tcp_flags of the header. It provides + * an easy way to check for tcp_flags + * without parsing skb_data. + * + * In particular, the skb_tcp_flags + * will still be available in + * BPF_SOCK_OPS_HDR_OPT_LEN even though + * the outgoing header has not + * been written yet. + */ }; /* Definitions for bpf_sock_ops_cb_flags */ @@ -4173,8 +4320,48 @@ enum { BPF_SOCK_OPS_RETRANS_CB_FLAG = (1<<1), BPF_SOCK_OPS_STATE_CB_FLAG = (1<<2), BPF_SOCK_OPS_RTT_CB_FLAG = (1<<3), - BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG = (1<<4), + /* Call bpf for all received TCP headers. The bpf prog will be + * called under sock_ops->op == BPF_SOCK_OPS_PARSE_HDR_OPT_CB + * + * Please refer to the comment in BPF_SOCK_OPS_PARSE_HDR_OPT_CB + * for the header option related helpers that will be useful + * to the bpf programs. + * + * It could be used at the client/active side (i.e. connect() side) + * when the server told it that the server was in syncookie + * mode and required the active side to resend the bpf-written + * options. The active side can keep writing the bpf-options until + * it received a valid packet from the server side to confirm + * the earlier packet (and options) has been received. The later + * example patch is using it like this at the active side when the + * server is in syncookie mode. + * + * The bpf prog will usually turn this off in the common cases. + */ + BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG = (1<<4), + /* Call bpf when kernel has received a header option that + * the kernel cannot handle. The bpf prog will be called under + * sock_ops->op == BPF_SOCK_OPS_PARSE_HDR_OPT_CB. + * + * Please refer to the comment in BPF_SOCK_OPS_PARSE_HDR_OPT_CB + * for the header option related helpers that will be useful + * to the bpf programs. + */ BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG = (1<<5), + /* Call bpf when the kernel is writing header options for the + * outgoing packet. The bpf prog will first be called + * to reserve space in a skb under + * sock_ops->op == BPF_SOCK_OPS_HDR_OPT_LEN_CB. Then + * the bpf prog will be called to write the header option(s) + * under sock_ops->op == BPF_SOCK_OPS_WRITE_HDR_OPT_CB. + * + * Please refer to the comment in BPF_SOCK_OPS_HDR_OPT_LEN_CB + * and BPF_SOCK_OPS_WRITE_HDR_OPT_CB for the header option + * related helpers that will be useful to the bpf programs. + * + * The kernel gets its chance to reserve space and write + * options first before the BPF program does. + */ BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG = (1<<6), /* Mask of all currently supported cb flags */ BPF_SOCK_OPS_ALL_CB_FLAGS = 0x7F, @@ -4233,6 +4420,63 @@ enum { */ BPF_SOCK_OPS_RTT_CB, /* Called on every RTT. */ + BPF_SOCK_OPS_PARSE_HDR_OPT_CB, /* Parse the header option. + * It will be called to handle + * the packets received at + * an already established + * connection. + * + * sock_ops->skb_data: + * Referring to the received skb. + * It covers the TCP header only. + * + * bpf_load_hdr_opt() can also + * be used to search for a + * particular option. + */ + BPF_SOCK_OPS_HDR_OPT_LEN_CB, /* Reserve space for writing the + * header option later in + * BPF_SOCK_OPS_WRITE_HDR_OPT_CB. + * Arg1: bool want_cookie. (in + * writing SYNACK only) + * + * sock_ops->skb_data: + * Not available because no header has + * been written yet. + * + * sock_ops->skb_tcp_flags: + * The tcp_flags of the + * outgoing skb. (e.g. SYN, ACK, FIN). + * + * bpf_reserve_hdr_opt() should + * be used to reserve space. + */ + BPF_SOCK_OPS_WRITE_HDR_OPT_CB, /* Write the header options + * Arg1: bool want_cookie. (in + * writing SYNACK only) + * + * sock_ops->skb_data: + * Referring to the outgoing skb. + * It covers the TCP header + * that has already been written + * by the kernel and the + * earlier bpf-progs. + * + * sock_ops->skb_tcp_flags: + * The tcp_flags of the outgoing + * skb. (e.g. SYN, ACK, FIN). + * + * bpf_store_hdr_opt() should + * be used to write the + * option. + * + * bpf_load_hdr_opt() can also + * be used to search for a + * particular option that + * has already been written + * by the kernel or the + * earlier bpf-progs. + */ }; /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect @@ -4262,6 +4506,60 @@ enum { TCP_BPF_SNDCWND_CLAMP = 1002, /* Set sndcwnd_clamp */ TCP_BPF_DELACK_MAX = 1003, /* Max delay ack in usecs */ TCP_BPF_RTO_MIN = 1004, /* Min delay ack in usecs */ + /* Copy the SYN pkt to optval + * + * BPF_PROG_TYPE_SOCK_OPS only. It is similar to the + * bpf_getsockopt(TCP_SAVED_SYN) but it does not limit + * to only getting from the saved_syn. It can either get the + * syn packet from: + * + * 1. the just-received SYN packet (only available when writing the + * SYNACK). It will be useful when it is not necessary to + * save the SYN packet for latter use. It is also the only way + * to get the SYN during syncookie mode because the syn + * packet cannot be saved during syncookie. + * + * OR + * + * 2. the earlier saved syn which was done by + * bpf_setsockopt(TCP_SAVE_SYN). + * + * The bpf_getsockopt(TCP_BPF_SYN*) option will hide where the + * SYN packet is obtained. + * + * If the bpf-prog does not need the IP[46] header, the + * bpf-prog can avoid parsing the IP header by using + * TCP_BPF_SYN. Otherwise, the bpf-prog can get both + * IP[46] and TCP header by using TCP_BPF_SYN_IP. + * + * >0: Total number of bytes copied + * -ENOSPC: Not enough space in optval. Only optlen number of + * bytes is copied. + * -ENOENT: The SYN skb is not available now and the earlier SYN pkt + * is not saved by setsockopt(TCP_SAVE_SYN). + */ + TCP_BPF_SYN = 1005, /* Copy the TCP header */ + TCP_BPF_SYN_IP = 1006, /* Copy the IP[46] and TCP header */ +}; + +enum { + BPF_LOAD_HDR_OPT_TCP_SYN = (1ULL << 0), +}; + +/* args[0] value during BPF_SOCK_OPS_HDR_OPT_LEN_CB and + * BPF_SOCK_OPS_WRITE_HDR_OPT_CB. + */ +enum { + BPF_WRITE_HDR_TCP_CURRENT_MSS = 1, /* Kernel is finding the + * total option spaces + * required for an established + * sk in order to calculate the + * MSS. No skb is actually + * sent. + */ + BPF_WRITE_HDR_TCP_SYNACK_COOKIE = 2, /* Kernel is in syncookie mode + * when sending a SYN. + */ }; struct bpf_perf_event_value { diff --git a/net/core/filter.c b/net/core/filter.c index 1608f4b3987f..ab5603d5b62a 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4669,9 +4669,82 @@ static const struct bpf_func_proto bpf_sock_ops_setsockopt_proto = { .arg5_type = ARG_CONST_SIZE, }; +static int bpf_sock_ops_get_syn(struct bpf_sock_ops_kern *bpf_sock, + int optname, const u8 **start) +{ + struct sk_buff *syn_skb = bpf_sock->syn_skb; + const u8 *hdr_start; + int ret; + + if (syn_skb) { + /* sk is a request_sock here */ + + if (optname == TCP_BPF_SYN) { + hdr_start = syn_skb->data; + ret = tcp_hdrlen(syn_skb); + } else { + /* optname == TCP_BPF_SYN_IP */ + hdr_start = skb_network_header(syn_skb); + ret = skb_network_header_len(syn_skb) + + tcp_hdrlen(syn_skb); + } + } else { + struct sock *sk = bpf_sock->sk; + struct saved_syn *saved_syn; + + if (sk->sk_state == TCP_NEW_SYN_RECV) + /* synack retransmit. bpf_sock->syn_skb will + * not be available. It has to resort to + * saved_syn (if it is saved). + */ + saved_syn = inet_reqsk(sk)->saved_syn; + else + saved_syn = tcp_sk(sk)->saved_syn; + + if (!saved_syn) + return -ENOENT; + + if (optname == TCP_BPF_SYN) { + hdr_start = saved_syn->data + + saved_syn->network_hdrlen; + ret = saved_syn->tcp_hdrlen; + } else { + /* optname == TCP_BPF_SYN_IP */ + hdr_start = saved_syn->data; + ret = saved_syn->network_hdrlen + + saved_syn->tcp_hdrlen; + } + } + + *start = hdr_start; + return ret; +} + BPF_CALL_5(bpf_sock_ops_getsockopt, struct bpf_sock_ops_kern *, bpf_sock, int, level, int, optname, char *, optval, int, optlen) { + if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP && + optname >= TCP_BPF_SYN && optname <= TCP_BPF_SYN_IP) { + int ret, copy_len = 0; + const u8 *start; + + ret = bpf_sock_ops_get_syn(bpf_sock, optname, &start); + if (ret > 0) { + copy_len = ret; + if (optlen < copy_len) { + copy_len = optlen; + ret = -ENOSPC; + } + + memcpy(optval, start, copy_len); + } + + /* Zero out unused buffer at the end */ + memset(optval + copy_len, 0, optlen - copy_len); + + return ret; + } + return _bpf_getsockopt(bpf_sock->sk, level, optname, optval, optlen); } @@ -6165,6 +6238,232 @@ static const struct bpf_func_proto bpf_sk_assign_proto = { .arg3_type = ARG_ANYTHING, }; +static const u8 *bpf_search_tcp_opt(const u8 *op, const u8 *opend, + u8 search_kind, const u8 *magic, + u8 magic_len, bool *eol) +{ + u8 kind, kind_len; + + *eol = false; + + while (op < opend) { + kind = op[0]; + + if (kind == TCPOPT_EOL) { + *eol = true; + return ERR_PTR(-ENOMSG); + } else if (kind == TCPOPT_NOP) { + op++; + continue; + } + + if (opend - op < 2 || opend - op < op[1] || op[1] < 2) + /* Something is wrong in the received header. + * Follow the TCP stack's tcp_parse_options() + * and just bail here. + */ + return ERR_PTR(-EFAULT); + + kind_len = op[1]; + if (search_kind == kind) { + if (!magic_len) + return op; + + if (magic_len > kind_len - 2) + return ERR_PTR(-ENOMSG); + + if (!memcmp(&op[2], magic, magic_len)) + return op; + } + + op += kind_len; + } + + return ERR_PTR(-ENOMSG); +} + +BPF_CALL_4(bpf_sock_ops_load_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock, + void *, search_res, u32, len, u64, flags) +{ + bool eol, load_syn = flags & BPF_LOAD_HDR_OPT_TCP_SYN; + const u8 *op, *opend, *magic, *search = search_res; + u8 search_kind, search_len, copy_len, magic_len; + int ret; + + /* 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. + */ + if (len < 2 || flags & ~BPF_LOAD_HDR_OPT_TCP_SYN) + return -EINVAL; + + search_kind = search[0]; + search_len = search[1]; + + if (search_len > len || search_kind == TCPOPT_NOP || + search_kind == TCPOPT_EOL) + return -EINVAL; + + if (search_kind == TCPOPT_EXP || search_kind == 253) { + /* 16 or 32 bit magic. +2 for kind and kind length */ + if (search_len != 4 && search_len != 6) + return -EINVAL; + magic = &search[2]; + magic_len = search_len - 2; + } else { + if (search_len) + return -EINVAL; + magic = NULL; + magic_len = 0; + } + + if (load_syn) { + ret = bpf_sock_ops_get_syn(bpf_sock, TCP_BPF_SYN, &op); + if (ret < 0) + return ret; + + opend = op + ret; + op += sizeof(struct tcphdr); + } else { + if (!bpf_sock->skb || + bpf_sock->op == BPF_SOCK_OPS_HDR_OPT_LEN_CB) + /* This bpf_sock->op cannot call this helper */ + return -EPERM; + + opend = bpf_sock->skb_data_end; + op = bpf_sock->skb->data + sizeof(struct tcphdr); + } + + op = bpf_search_tcp_opt(op, opend, search_kind, magic, magic_len, + &eol); + if (IS_ERR(op)) + return PTR_ERR(op); + + copy_len = op[1]; + ret = copy_len; + if (copy_len > len) { + ret = -ENOSPC; + copy_len = len; + } + + memcpy(search_res, op, copy_len); + return ret; +} + +static const struct bpf_func_proto bpf_sock_ops_load_hdr_opt_proto = { + .func = bpf_sock_ops_load_hdr_opt, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE, + .arg4_type = ARG_ANYTHING, +}; + +BPF_CALL_4(bpf_sock_ops_store_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock, + const void *, from, u32, len, u64, flags) +{ + u8 new_kind, new_kind_len, magic_len = 0, *opend; + const u8 *op, *new_op, *magic = NULL; + struct sk_buff *skb; + bool eol; + + if (bpf_sock->op != BPF_SOCK_OPS_WRITE_HDR_OPT_CB) + return -EPERM; + + if (len < 2 || flags) + return -EINVAL; + + new_op = from; + new_kind = new_op[0]; + new_kind_len = new_op[1]; + + if (new_kind_len > len || new_kind == TCPOPT_NOP || + new_kind == TCPOPT_EOL) + return -EINVAL; + + if (new_kind_len > bpf_sock->remaining_opt_len) + return -ENOSPC; + + /* 253 is another experimental kind */ + if (new_kind == TCPOPT_EXP || new_kind == 253) { + if (new_kind_len < 4) + return -EINVAL; + /* Match for the 2 byte magic also. + * RFC 6994: the magic could be 2 or 4 bytes. + * Hence, matching by 2 byte only is on the + * conservative side but it is the right + * thing to do for the 'search-for-duplication' + * purpose. + */ + magic = &new_op[2]; + magic_len = 2; + } + + /* Check for duplication */ + skb = bpf_sock->skb; + op = skb->data + sizeof(struct tcphdr); + opend = bpf_sock->skb_data_end; + + op = bpf_search_tcp_opt(op, opend, new_kind, magic, magic_len, + &eol); + if (!IS_ERR(op)) + return -EEXIST; + + if (PTR_ERR(op) != -ENOMSG) + return PTR_ERR(op); + + if (eol) + /* The option has been ended. Treat it as no more + * header option can be written. + */ + return -ENOSPC; + + /* No duplication found. Store the header option. */ + memcpy(opend, from, new_kind_len); + + bpf_sock->remaining_opt_len -= new_kind_len; + bpf_sock->skb_data_end += new_kind_len; + + return 0; +} + +static const struct bpf_func_proto bpf_sock_ops_store_hdr_opt_proto = { + .func = bpf_sock_ops_store_hdr_opt, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE, + .arg4_type = ARG_ANYTHING, +}; + +BPF_CALL_3(bpf_sock_ops_reserve_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock, + u32, len, u64, flags) +{ + if (bpf_sock->op != BPF_SOCK_OPS_HDR_OPT_LEN_CB) + return -EPERM; + + if (flags || len < 2) + return -EINVAL; + + if (len > bpf_sock->remaining_opt_len) + return -ENOSPC; + + bpf_sock->remaining_opt_len -= len; + + return 0; +} + +static const struct bpf_func_proto bpf_sock_ops_reserve_hdr_opt_proto = { + .func = bpf_sock_ops_reserve_hdr_opt, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, +}; + #endif /* CONFIG_INET */ bool bpf_helper_changes_pkt_data(void *func) @@ -6193,6 +6492,9 @@ bool bpf_helper_changes_pkt_data(void *func) func == bpf_lwt_seg6_store_bytes || func == bpf_lwt_seg6_adjust_srh || func == bpf_lwt_seg6_action || +#endif +#ifdef CONFIG_INET + func == bpf_sock_ops_store_hdr_opt || #endif func == bpf_lwt_in_push_encap || func == bpf_lwt_xmit_push_encap) @@ -6565,6 +6867,12 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; #ifdef CONFIG_INET + case BPF_FUNC_load_hdr_opt: + return &bpf_sock_ops_load_hdr_opt_proto; + case BPF_FUNC_store_hdr_opt: + return &bpf_sock_ops_store_hdr_opt_proto; + case BPF_FUNC_reserve_hdr_opt: + return &bpf_sock_ops_reserve_hdr_opt_proto; case BPF_FUNC_tcp_sock: return &bpf_tcp_sock_proto; #endif /* CONFIG_INET */ @@ -7364,6 +7672,20 @@ static bool sock_ops_is_valid_access(int off, int size, return false; info->reg_type = PTR_TO_SOCKET_OR_NULL; break; + case offsetof(struct bpf_sock_ops, skb_data): + if (size != sizeof(__u64)) + return false; + info->reg_type = PTR_TO_PACKET; + break; + case offsetof(struct bpf_sock_ops, skb_data_end): + if (size != sizeof(__u64)) + return false; + info->reg_type = PTR_TO_PACKET_END; + break; + case offsetof(struct bpf_sock_ops, skb_tcp_flags): + bpf_ctx_record_field_size(info, size_default); + return bpf_ctx_narrow_access_ok(off, size, + size_default); default: if (size != size_default) return false; @@ -8701,6 +9023,49 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, case offsetof(struct bpf_sock_ops, sk): SOCK_OPS_GET_SK(); break; + case offsetof(struct bpf_sock_ops, skb_data_end): + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, + skb_data_end), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_ops_kern, + skb_data_end)); + break; + case offsetof(struct bpf_sock_ops, skb_data): + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, + skb), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_ops_kern, + skb)); + *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data), + si->dst_reg, si->dst_reg, + offsetof(struct sk_buff, data)); + break; + case offsetof(struct bpf_sock_ops, skb_len): + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, + skb), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_ops_kern, + skb)); + *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, len), + si->dst_reg, si->dst_reg, + offsetof(struct sk_buff, len)); + break; + case offsetof(struct bpf_sock_ops, skb_tcp_flags): + off = offsetof(struct sk_buff, cb); + off += offsetof(struct tcp_skb_cb, tcp_flags); + *target_size = sizeof_field(struct tcp_skb_cb, tcp_flags); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, + skb), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_ops_kern, + skb)); + *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct tcp_skb_cb, + tcp_flags), + si->dst_reg, si->dst_reg, off); + break; } return insn - insn_buf; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 8c9da4b65dae..319cc7fd5117 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -146,6 +146,7 @@ static void bpf_skops_parse_hdr(struct sock *sk, struct sk_buff *skb) BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG); bool parse_all_opt = BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG); + struct bpf_sock_ops_kern sock_ops; if (likely(!unknown_opt && !parse_all_opt)) return; @@ -161,12 +162,15 @@ static void bpf_skops_parse_hdr(struct sock *sk, struct sk_buff *skb) return; } - /* BPF prog will have access to the sk and skb. - * - * The bpf running context preparation and the actual bpf prog - * calling will be implemented in a later PATCH together with - * other bpf pieces. - */ + sock_owned_by_me(sk); + + 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.sk = sk; + bpf_skops_init_skb(&sock_ops, skb, tcp_hdrlen(skb)); + + BPF_CGROUP_RUN_PROG_SOCK_OPS(&sock_ops); } static void bpf_skops_established(struct sock *sk, int bpf_op, @@ -180,7 +184,9 @@ static void bpf_skops_established(struct sock *sk, int bpf_op, sock_ops.op = bpf_op; sock_ops.is_fullsock = 1; sock_ops.sk = sk; - /* skb will be passed to the bpf prog in a later patch. */ + /* sk with TCP_REPAIR_ON does not have skb in tcp_finish_connect */ + if (skb) + bpf_skops_init_skb(&sock_ops, skb, tcp_hdrlen(skb)); BPF_CGROUP_RUN_PROG_SOCK_OPS(&sock_ops); } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 495dda2449fe..56c306e3cd2f 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -548,6 +548,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->fastopen_req = NULL; RCU_INIT_POINTER(newtp->fastopen_rsk, NULL); + bpf_skops_init_child(sk, newsk); tcp_bpf_clone(sk, newsk); __TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 673db6879e46..ab79d36ed07f 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -454,6 +454,18 @@ static void mptcp_options_write(__be32 *ptr, struct tcp_out_options *opts) } #ifdef CONFIG_CGROUP_BPF +static int bpf_skops_write_hdr_opt_arg0(struct sk_buff *skb, + enum tcp_synack_type synack_type) +{ + if (unlikely(!skb)) + return BPF_WRITE_HDR_TCP_CURRENT_MSS; + + if (unlikely(synack_type == TCP_SYNACK_COOKIE)) + return BPF_WRITE_HDR_TCP_SYNACK_COOKIE; + + return 0; +} + /* req, syn_skb and synack_type are used when writing synack */ static void bpf_skops_hdr_opt_len(struct sock *sk, struct sk_buff *skb, struct request_sock *req, @@ -462,15 +474,60 @@ static void bpf_skops_hdr_opt_len(struct sock *sk, struct sk_buff *skb, struct tcp_out_options *opts, unsigned int *remaining) { + struct bpf_sock_ops_kern sock_ops; + int err; + if (likely(!BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG)) || !*remaining) return; - /* The bpf running context preparation and the actual bpf prog - * calling will be implemented in a later PATCH together with - * other bpf pieces. - */ + /* *remaining has already been aligned to 4 bytes, so *remaining >= 4 */ + + /* init sock_ops */ + memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp)); + + sock_ops.op = BPF_SOCK_OPS_HDR_OPT_LEN_CB; + + if (req) { + /* The listen "sk" cannot be passed here because + * it is not locked. It would not make too much + * sense to do bpf_setsockopt(listen_sk) based + * on individual connection request also. + * + * Thus, "req" is passed here and the cgroup-bpf-progs + * of the listen "sk" will be run. + * + * "req" is also used here for fastopen even the "sk" here is + * a fullsock "child" sk. It is to keep the behavior + * consistent between fastopen and non-fastopen on + * the bpf programming side. + */ + sock_ops.sk = (struct sock *)req; + sock_ops.syn_skb = syn_skb; + } else { + sock_owned_by_me(sk); + + sock_ops.is_fullsock = 1; + sock_ops.sk = sk; + } + + sock_ops.args[0] = bpf_skops_write_hdr_opt_arg0(skb, synack_type); + sock_ops.remaining_opt_len = *remaining; + /* tcp_current_mss() does not pass a skb */ + if (skb) + bpf_skops_init_skb(&sock_ops, skb, 0); + + err = BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(&sock_ops, sk); + + if (err || sock_ops.remaining_opt_len == *remaining) + return; + + opts->bpf_opt_len = *remaining - sock_ops.remaining_opt_len; + /* round up to 4 bytes */ + opts->bpf_opt_len = (opts->bpf_opt_len + 3) & ~3; + + *remaining -= opts->bpf_opt_len; } static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb, @@ -479,13 +536,42 @@ static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb, enum tcp_synack_type synack_type, struct tcp_out_options *opts) { - if (likely(!opts->bpf_opt_len)) + u8 first_opt_off, nr_written, max_opt_len = opts->bpf_opt_len; + struct bpf_sock_ops_kern sock_ops; + int err; + + if (likely(!max_opt_len)) return; - /* The bpf running context preparation and the actual bpf prog - * calling will be implemented in a later PATCH together with - * other bpf pieces. - */ + memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp)); + + sock_ops.op = BPF_SOCK_OPS_WRITE_HDR_OPT_CB; + + if (req) { + sock_ops.sk = (struct sock *)req; + sock_ops.syn_skb = syn_skb; + } else { + sock_owned_by_me(sk); + + sock_ops.is_fullsock = 1; + sock_ops.sk = sk; + } + + sock_ops.args[0] = bpf_skops_write_hdr_opt_arg0(skb, synack_type); + sock_ops.remaining_opt_len = max_opt_len; + first_opt_off = tcp_hdrlen(skb) - max_opt_len; + bpf_skops_init_skb(&sock_ops, skb, first_opt_off); + + err = BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(&sock_ops, sk); + + if (err) + nr_written = 0; + else + nr_written = max_opt_len - sock_ops.remaining_opt_len; + + if (nr_written < max_opt_len) + memset(skb->data + first_opt_off + nr_written, TCPOPT_NOP, + max_opt_len - nr_written); } #else static void bpf_skops_hdr_opt_len(struct sock *sk, struct sk_buff *skb, diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 18d0e128bc3c..f67ec5d9e57d 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3395,6 +3395,120 @@ union bpf_attr { * A non-negative value equal to or less than *size* on success, * or a negative error in case of failure. * + * long bpf_load_hdr_opt(struct bpf_sock_ops *skops, void *searchby_res, u32 len, u64 flags) + * Description + * Load header option. Support reading a particular TCP header + * option for bpf program (BPF_PROG_TYPE_SOCK_OPS). + * + * If *flags* is 0, it will search the option from the + * sock_ops->skb_data. The comment in "struct bpf_sock_ops" + * has details on what skb_data contains under different + * sock_ops->op. + * + * The first byte of the *searchby_res* specifies the + * kind that it wants to search. + * + * If the searching kind is an experimental kind + * (i.e. 253 or 254 according to RFC6994). It also + * needs to specify the "magic" which is either + * 2 bytes or 4 bytes. It then also needs to + * specify the size of the magic by using + * the 2nd byte which is "kind-length" of a TCP + * header option and the "kind-length" also + * includes the first 2 bytes "kind" and "kind-length" + * itself as a normal TCP header option also does. + * + * For example, to search experimental kind 254 with + * 2 byte magic 0xeB9F, the searchby_res should be + * [ 254, 4, 0xeB, 0x9F, 0, 0, .... 0 ]. + * + * To search for the standard window scale option (3), + * the searchby_res should be [ 3, 0, 0, .... 0 ]. + * Note, kind-length must be 0 for regular option. + * + * Searching for No-Op (0) and End-of-Option-List (1) are + * not supported. + * + * *len* must be at least 2 bytes which is the minimal size + * of a header option. + * + * Supported flags: + * * **BPF_LOAD_HDR_OPT_TCP_SYN** to search from the + * saved_syn packet or the just-received syn packet. + * + * Return + * >0 when found, the header option is copied to *searchby_res*. + * The return value is the total length copied. + * + * **-EINVAL** If param is invalid + * + * **-ENOMSG** The option is not found + * + * **-ENOENT** No syn packet available when + * **BPF_LOAD_HDR_OPT_TCP_SYN** is used + * + * **-ENOSPC** Not enough space. Only *len* number of + * bytes are copied. + * + * **-EFAULT** Cannot parse the header options in the packet + * + * **-EPERM** This helper cannot be used under the + * current sock_ops->op. + * + * long bpf_store_hdr_opt(struct bpf_sock_ops *skops, const void *from, u32 len, u64 flags) + * Description + * Store header option. The data will be copied + * from buffer *from* with length *len* to the TCP header. + * + * The buffer *from* should have the whole option that + * includes the kind, kind-length, and the actual + * option data. The *len* must be at least kind-length + * long. The kind-length does not have to be 4 byte + * aligned. The kernel will take care of the padding + * and setting the 4 bytes aligned value to th->doff. + * + * This helper will check for duplicated option + * by searching the same option in the outgoing skb. + * + * This helper can only be called during + * BPF_SOCK_OPS_WRITE_HDR_OPT_CB. + * + * Return + * 0 on success, or negative error in case of failure: + * + * **-EINVAL** If param is invalid + * + * **-ENOSPC** Not enough space in the header. + * Nothing has been written + * + * **-EEXIST** The option has already existed + * + * **-EFAULT** Cannot parse the existing header options + * + * **-EPERM** This helper cannot be used under the + * current sock_ops->op. + * + * long bpf_reserve_hdr_opt(struct bpf_sock_ops *skops, u32 len, u64 flags) + * Description + * Reserve *len* bytes for the bpf header option. The + * space will be used by bpf_store_hdr_opt() later in + * BPF_SOCK_OPS_WRITE_HDR_OPT_CB. + * + * If bpf_reserve_hdr_opt() is called multiple times, + * the total number of bytes will be reserved. + * + * This helper can only be called during + * BPF_SOCK_OPS_HDR_OPT_LEN_CB. + * + * Return + * 0 on success, or negative error in case of failure: + * + * **-EINVAL** if param is invalid + * + * **-ENOSPC** Not enough space in the header. + * + * **-EPERM** This helper cannot be used under the + * current sock_ops->op. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3539,6 +3653,9 @@ union bpf_attr { FN(skc_to_tcp_request_sock), \ FN(skc_to_udp6_sock), \ FN(get_task_stack), \ + FN(load_hdr_opt), \ + FN(store_hdr_opt), \ + FN(reserve_hdr_opt), /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -4165,6 +4282,36 @@ struct bpf_sock_ops { __u64 bytes_received; __u64 bytes_acked; __bpf_md_ptr(struct bpf_sock *, sk); + /* [skb_data, skb_data_end) covers the whole TCP header. + * + * BPF_SOCK_OPS_PARSE_HDR_OPT_CB: The packet received + * BPF_SOCK_OPS_HDR_OPT_LEN_CB: Not useful because the + * header has not been written. + * BPF_SOCK_OPS_WRITE_HDR_OPT_CB: The header and options have + * been written so far. + * BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB: The SYNACK that concludes + * the 3WHS. + * BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: The ACK that concludes + * the 3WHS. + * + * bpf_load_hdr_opt() can also be used to read a particular option. + */ + __bpf_md_ptr(void *, skb_data); + __bpf_md_ptr(void *, skb_data_end); + __u32 skb_len; /* The total length of a packet. + * It includes the header, options, + * and payload. + */ + __u32 skb_tcp_flags; /* tcp_flags of the header. It provides + * an easy way to check for tcp_flags + * without parsing skb_data. + * + * In particular, the skb_tcp_flags + * will still be available in + * BPF_SOCK_OPS_HDR_OPT_LEN even though + * the outgoing header has not + * been written yet. + */ }; /* Definitions for bpf_sock_ops_cb_flags */ @@ -4173,8 +4320,48 @@ enum { BPF_SOCK_OPS_RETRANS_CB_FLAG = (1<<1), BPF_SOCK_OPS_STATE_CB_FLAG = (1<<2), BPF_SOCK_OPS_RTT_CB_FLAG = (1<<3), - BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG = (1<<4), + /* Call bpf for all received TCP headers. The bpf prog will be + * called under sock_ops->op == BPF_SOCK_OPS_PARSE_HDR_OPT_CB + * + * Please refer to the comment in BPF_SOCK_OPS_PARSE_HDR_OPT_CB + * for the header option related helpers that will be useful + * to the bpf programs. + * + * It could be used at the client/active side (i.e. connect() side) + * when the server told it that the server was in syncookie + * mode and required the active side to resend the bpf-written + * options. The active side can keep writing the bpf-options until + * it received a valid packet from the server side to confirm + * the earlier packet (and options) has been received. The later + * example patch is using it like this at the active side when the + * server is in syncookie mode. + * + * The bpf prog will usually turn this off in the common cases. + */ + BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG = (1<<4), + /* Call bpf when kernel has received a header option that + * the kernel cannot handle. The bpf prog will be called under + * sock_ops->op == BPF_SOCK_OPS_PARSE_HDR_OPT_CB. + * + * Please refer to the comment in BPF_SOCK_OPS_PARSE_HDR_OPT_CB + * for the header option related helpers that will be useful + * to the bpf programs. + */ BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG = (1<<5), + /* Call bpf when the kernel is writing header options for the + * outgoing packet. The bpf prog will first be called + * to reserve space in a skb under + * sock_ops->op == BPF_SOCK_OPS_HDR_OPT_LEN_CB. Then + * the bpf prog will be called to write the header option(s) + * under sock_ops->op == BPF_SOCK_OPS_WRITE_HDR_OPT_CB. + * + * Please refer to the comment in BPF_SOCK_OPS_HDR_OPT_LEN_CB + * and BPF_SOCK_OPS_WRITE_HDR_OPT_CB for the header option + * related helpers that will be useful to the bpf programs. + * + * The kernel gets its chance to reserve space and write + * options first before the BPF program does. + */ BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG = (1<<6), /* Mask of all currently supported cb flags */ BPF_SOCK_OPS_ALL_CB_FLAGS = 0x7F, @@ -4233,6 +4420,63 @@ enum { */ BPF_SOCK_OPS_RTT_CB, /* Called on every RTT. */ + BPF_SOCK_OPS_PARSE_HDR_OPT_CB, /* Parse the header option. + * It will be called to handle + * the packets received at + * an already established + * connection. + * + * sock_ops->skb_data: + * Referring to the received skb. + * It covers the TCP header only. + * + * bpf_load_hdr_opt() can also + * be used to search for a + * particular option. + */ + BPF_SOCK_OPS_HDR_OPT_LEN_CB, /* Reserve space for writing the + * header option later in + * BPF_SOCK_OPS_WRITE_HDR_OPT_CB. + * Arg1: bool want_cookie. (in + * writing SYNACK only) + * + * sock_ops->skb_data: + * Not available because no header has + * been written yet. + * + * sock_ops->skb_tcp_flags: + * The tcp_flags of the + * outgoing skb. (e.g. SYN, ACK, FIN). + * + * bpf_reserve_hdr_opt() should + * be used to reserve space. + */ + BPF_SOCK_OPS_WRITE_HDR_OPT_CB, /* Write the header options + * Arg1: bool want_cookie. (in + * writing SYNACK only) + * + * sock_ops->skb_data: + * Referring to the outgoing skb. + * It covers the TCP header + * that has already been written + * by the kernel and the + * earlier bpf-progs. + * + * sock_ops->skb_tcp_flags: + * The tcp_flags of the outgoing + * skb. (e.g. SYN, ACK, FIN). + * + * bpf_store_hdr_opt() should + * be used to write the + * option. + * + * bpf_load_hdr_opt() can also + * be used to search for a + * particular option that + * has already been written + * by the kernel or the + * earlier bpf-progs. + */ }; /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect @@ -4262,6 +4506,60 @@ enum { TCP_BPF_SNDCWND_CLAMP = 1002, /* Set sndcwnd_clamp */ TCP_BPF_DELACK_MAX = 1003, /* Max delay ack in usecs */ TCP_BPF_RTO_MIN = 1004, /* Min delay ack in usecs */ + /* Copy the SYN pkt to optval + * + * BPF_PROG_TYPE_SOCK_OPS only. It is similar to the + * bpf_getsockopt(TCP_SAVED_SYN) but it does not limit + * to only getting from the saved_syn. It can either get the + * syn packet from: + * + * 1. the just-received SYN packet (only available when writing the + * SYNACK). It will be useful when it is not necessary to + * save the SYN packet for latter use. It is also the only way + * to get the SYN during syncookie mode because the syn + * packet cannot be saved during syncookie. + * + * OR + * + * 2. the earlier saved syn which was done by + * bpf_setsockopt(TCP_SAVE_SYN). + * + * The bpf_getsockopt(TCP_BPF_SYN*) option will hide where the + * SYN packet is obtained. + * + * If the bpf-prog does not need the IP[46] header, the + * bpf-prog can avoid parsing the IP header by using + * TCP_BPF_SYN. Otherwise, the bpf-prog can get both + * IP[46] and TCP header by using TCP_BPF_SYN_IP. + * + * >0: Total number of bytes copied + * -ENOSPC: Not enough space in optval. Only optlen number of + * bytes is copied. + * -ENOENT: The SYN skb is not available now and the earlier SYN pkt + * is not saved by setsockopt(TCP_SAVE_SYN). + */ + TCP_BPF_SYN = 1005, /* Copy the TCP header */ + TCP_BPF_SYN_IP = 1006, /* Copy the IP[46] and TCP header */ +}; + +enum { + BPF_LOAD_HDR_OPT_TCP_SYN = (1ULL << 0), +}; + +/* args[0] value during BPF_SOCK_OPS_HDR_OPT_LEN_CB and + * BPF_SOCK_OPS_WRITE_HDR_OPT_CB. + */ +enum { + BPF_WRITE_HDR_TCP_CURRENT_MSS = 1, /* Kernel is finding the + * total option spaces + * required for an established + * sk in order to calculate the + * MSS. No skb is actually + * sent. + */ + BPF_WRITE_HDR_TCP_SYNACK_COOKIE = 2, /* Kernel is in syncookie mode + * when sending a SYN. + */ }; struct bpf_perf_event_value { -- cgit v1.2.3 From 267cf9fa43d1c9d525d5d818a8651f2900e3aa9e Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 20 Aug 2020 12:01:23 -0700 Subject: tcp: bpf: Optionally store mac header in TCP_SAVE_SYN This patch is adapted from Eric's patch in an earlier discussion [1]. The TCP_SAVE_SYN currently only stores the network header and tcp header. This patch allows it to optionally store the mac header also if the setsockopt's optval is 2. It requires one more bit for the "save_syn" bit field in tcp_sock. This patch achieves this by moving the syn_smc bit next to the is_mptcp. The syn_smc is currently used with the TCP experimental option. Since syn_smc is only used when CONFIG_SMC is enabled, this patch also puts the "IS_ENABLED(CONFIG_SMC)" around it like the is_mptcp did with "IS_ENABLED(CONFIG_MPTCP)". The mac_hdrlen is also stored in the "struct saved_syn" to allow a quick offset from the bpf prog if it chooses to start getting from the network header or the tcp header. [1]: https://lore.kernel.org/netdev/CANn89iLJNWh6bkH7DNhy_kmcAexuUCccqERqe7z2QsvPhGrYPQ@mail.gmail.com/ Suggested-by: Eric Dumazet Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/bpf/20200820190123.2886935-1-kafai@fb.com --- include/linux/tcp.h | 13 ++++++++----- include/net/request_sock.h | 1 + include/uapi/linux/bpf.h | 1 + net/core/filter.c | 27 ++++++++++++++++++++++----- net/ipv4/tcp.c | 3 ++- net/ipv4/tcp_input.c | 14 +++++++++++++- tools/include/uapi/linux/bpf.h | 1 + 7 files changed, 48 insertions(+), 12 deletions(-) (limited to 'include/net') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 29d166263ae7..56ff2952edaf 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -239,14 +239,13 @@ struct tcp_sock { repair : 1, frto : 1;/* F-RTO (RFC5682) activated in CA_Loss */ u8 repair_queue; - u8 syn_data:1, /* SYN includes data */ + u8 save_syn:2, /* Save headers of SYN packet */ + syn_data:1, /* SYN includes data */ syn_fastopen:1, /* SYN includes Fast Open option */ syn_fastopen_exp:1,/* SYN includes Fast Open exp. option */ syn_fastopen_ch:1, /* Active TFO re-enabling probe */ syn_data_acked:1,/* data in SYN is acked by SYN-ACK */ - save_syn:1, /* Save headers of SYN packet */ - is_cwnd_limited:1,/* forward progress limited by snd_cwnd? */ - syn_smc:1; /* SYN includes SMC */ + is_cwnd_limited:1;/* forward progress limited by snd_cwnd? */ u32 tlp_high_seq; /* snd_nxt at the time of TLP */ u32 tcp_tx_delay; /* delay (in usec) added to TX packets */ @@ -393,6 +392,9 @@ struct tcp_sock { #if IS_ENABLED(CONFIG_MPTCP) bool is_mptcp; #endif +#if IS_ENABLED(CONFIG_SMC) + bool syn_smc; /* SYN includes SMC */ +#endif #ifdef CONFIG_TCP_MD5SIG /* TCP AF-Specific parts; only used by MD5 Signature support so far */ @@ -488,7 +490,8 @@ static inline void tcp_saved_syn_free(struct tcp_sock *tp) static inline u32 tcp_saved_syn_len(const struct saved_syn *saved_syn) { - return saved_syn->network_hdrlen + saved_syn->tcp_hdrlen; + return saved_syn->mac_hdrlen + saved_syn->network_hdrlen + + saved_syn->tcp_hdrlen; } struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 7d9ed99a77bd..29e41ff3ec93 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -42,6 +42,7 @@ struct request_sock_ops { int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req); struct saved_syn { + u32 mac_hdrlen; u32 network_hdrlen; u32 tcp_hdrlen; u8 data[]; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index f67ec5d9e57d..544b89a64918 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4540,6 +4540,7 @@ enum { */ TCP_BPF_SYN = 1005, /* Copy the TCP header */ 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 */ }; enum { diff --git a/net/core/filter.c b/net/core/filter.c index ab5603d5b62a..47eef9a0be6a 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4682,11 +4682,16 @@ static int bpf_sock_ops_get_syn(struct bpf_sock_ops_kern *bpf_sock, if (optname == TCP_BPF_SYN) { hdr_start = syn_skb->data; ret = tcp_hdrlen(syn_skb); - } else { - /* optname == TCP_BPF_SYN_IP */ + } else if (optname == TCP_BPF_SYN_IP) { hdr_start = skb_network_header(syn_skb); ret = skb_network_header_len(syn_skb) + tcp_hdrlen(syn_skb); + } else { + /* optname == TCP_BPF_SYN_MAC */ + hdr_start = skb_mac_header(syn_skb); + ret = skb_mac_header_len(syn_skb) + + skb_network_header_len(syn_skb) + + tcp_hdrlen(syn_skb); } } else { struct sock *sk = bpf_sock->sk; @@ -4706,12 +4711,24 @@ static int bpf_sock_ops_get_syn(struct bpf_sock_ops_kern *bpf_sock, if (optname == TCP_BPF_SYN) { hdr_start = saved_syn->data + + saved_syn->mac_hdrlen + saved_syn->network_hdrlen; ret = saved_syn->tcp_hdrlen; + } else if (optname == TCP_BPF_SYN_IP) { + hdr_start = saved_syn->data + + saved_syn->mac_hdrlen; + ret = saved_syn->network_hdrlen + + saved_syn->tcp_hdrlen; } else { - /* optname == TCP_BPF_SYN_IP */ + /* optname == TCP_BPF_SYN_MAC */ + + /* TCP_SAVE_SYN may not have saved the mac hdr */ + if (!saved_syn->mac_hdrlen) + return -ENOENT; + hdr_start = saved_syn->data; - ret = saved_syn->network_hdrlen + + ret = saved_syn->mac_hdrlen + + saved_syn->network_hdrlen + saved_syn->tcp_hdrlen; } } @@ -4724,7 +4741,7 @@ BPF_CALL_5(bpf_sock_ops_getsockopt, struct bpf_sock_ops_kern *, bpf_sock, int, level, int, optname, char *, optval, int, optlen) { if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP && - optname >= TCP_BPF_SYN && optname <= TCP_BPF_SYN_IP) { + optname >= TCP_BPF_SYN && optname <= TCP_BPF_SYN_MAC) { int ret, copy_len = 0; const u8 *start; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 6075cb091a20..57a568875539 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3211,7 +3211,8 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname, break; case TCP_SAVE_SYN: - if (val < 0 || val > 1) + /* 0: disable, 1: enable, 2: start from ether_header */ + if (val < 0 || val > 2) err = -EINVAL; else tp->save_syn = val; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 319cc7fd5117..4337841faeff 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6676,13 +6676,25 @@ static void tcp_reqsk_record_syn(const struct sock *sk, if (tcp_sk(sk)->save_syn) { u32 len = skb_network_header_len(skb) + tcp_hdrlen(skb); struct saved_syn *saved_syn; + u32 mac_hdrlen; + void *base; + + if (tcp_sk(sk)->save_syn == 2) { /* Save full header. */ + base = skb_mac_header(skb); + mac_hdrlen = skb_mac_header_len(skb); + len += mac_hdrlen; + } else { + base = skb_network_header(skb); + mac_hdrlen = 0; + } saved_syn = kmalloc(struct_size(saved_syn, data, len), GFP_ATOMIC); if (saved_syn) { + saved_syn->mac_hdrlen = mac_hdrlen; saved_syn->network_hdrlen = skb_network_header_len(skb); saved_syn->tcp_hdrlen = tcp_hdrlen(skb); - memcpy(saved_syn->data, skb_network_header(skb), len); + memcpy(saved_syn->data, base, len); req->saved_syn = saved_syn; } } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index f67ec5d9e57d..544b89a64918 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4540,6 +4540,7 @@ enum { */ TCP_BPF_SYN = 1005, /* Copy the TCP header */ 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 */ }; enum { -- cgit v1.2.3 From 1f00d375af84fbcdb6dd6c79fd7c3d02d2390338 Mon Sep 17 00:00:00 2001 From: KP Singh Date: Tue, 25 Aug 2020 20:29:13 +0200 Subject: bpf: Renames in preparation for bpf_local_storage A purely mechanical change to split the renaming from the actual generalization. Flags/consts: SK_STORAGE_CREATE_FLAG_MASK BPF_LOCAL_STORAGE_CREATE_FLAG_MASK BPF_SK_STORAGE_CACHE_SIZE BPF_LOCAL_STORAGE_CACHE_SIZE MAX_VALUE_SIZE BPF_LOCAL_STORAGE_MAX_VALUE_SIZE Structs: bucket bpf_local_storage_map_bucket bpf_sk_storage_map bpf_local_storage_map bpf_sk_storage_data bpf_local_storage_data bpf_sk_storage_elem bpf_local_storage_elem bpf_sk_storage bpf_local_storage The "sk" member in bpf_local_storage is also updated to "owner" in preparation for changing the type to void * in a subsequent patch. Functions: selem_linked_to_sk selem_linked_to_storage selem_alloc bpf_selem_alloc __selem_unlink_sk bpf_selem_unlink_storage_nolock __selem_link_sk bpf_selem_link_storage_nolock selem_unlink_sk __bpf_selem_unlink_storage sk_storage_update bpf_local_storage_update __sk_storage_lookup bpf_local_storage_lookup bpf_sk_storage_map_free bpf_local_storage_map_free bpf_sk_storage_map_alloc bpf_local_storage_map_alloc bpf_sk_storage_map_alloc_check bpf_local_storage_map_alloc_check bpf_sk_storage_map_check_btf bpf_local_storage_map_check_btf Signed-off-by: KP Singh Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20200825182919.1118197-2-kpsingh@chromium.org --- include/net/sock.h | 4 +- net/core/bpf_sk_storage.c | 488 ++++++++++++----------- tools/testing/selftests/bpf/progs/map_ptr_kern.c | 6 +- 3 files changed, 255 insertions(+), 243 deletions(-) (limited to 'include/net') diff --git a/include/net/sock.h b/include/net/sock.h index 064637d1ddf6..18423cc9cde8 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -246,7 +246,7 @@ struct sock_common { /* public: */ }; -struct bpf_sk_storage; +struct bpf_local_storage; /** * struct sock - network layer representation of sockets @@ -517,7 +517,7 @@ struct sock { void (*sk_destruct)(struct sock *sk); struct sock_reuseport __rcu *sk_reuseport_cb; #ifdef CONFIG_BPF_SYSCALL - struct bpf_sk_storage __rcu *sk_bpf_storage; + struct bpf_local_storage __rcu *sk_bpf_storage; #endif struct rcu_head sk_rcu; }; diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index 281200dc0a01..f975e2d01207 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -12,33 +12,32 @@ #include #include -#define SK_STORAGE_CREATE_FLAG_MASK \ - (BPF_F_NO_PREALLOC | BPF_F_CLONE) +#define BPF_LOCAL_STORAGE_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_CLONE) -struct bucket { +struct bpf_local_storage_map_bucket { struct hlist_head list; raw_spinlock_t lock; }; -/* Thp map is not the primary owner of a bpf_sk_storage_elem. - * Instead, the sk->sk_bpf_storage is. +/* Thp map is not the primary owner of a bpf_local_storage_elem. + * Instead, the container object (eg. sk->sk_bpf_storage) is. * - * The map (bpf_sk_storage_map) is for two purposes - * 1. Define the size of the "sk local storage". It is + * The map (bpf_local_storage_map) is for two purposes + * 1. Define the size of the "local storage". It is * the map's value_size. * * 2. Maintain a list to keep track of all elems such * that they can be cleaned up during the map destruction. * * When a bpf local storage is being looked up for a - * particular sk, the "bpf_map" pointer is actually used + * particular object, the "bpf_map" pointer is actually used * as the "key" to search in the list of elem in - * sk->sk_bpf_storage. + * the respective bpf_local_storage owned by the object. * - * Hence, consider sk->sk_bpf_storage is the mini-map - * with the "bpf_map" pointer as the searching key. + * e.g. sk->sk_bpf_storage is the mini-map with the "bpf_map" pointer + * as the searching key. */ -struct bpf_sk_storage_map { +struct bpf_local_storage_map { struct bpf_map map; /* Lookup elem does not require accessing the map. * @@ -46,55 +45,57 @@ struct bpf_sk_storage_map { * link/unlink the elem from the map. Having * multiple buckets to improve contention. */ - struct bucket *buckets; + struct bpf_local_storage_map_bucket *buckets; u32 bucket_log; u16 elem_size; u16 cache_idx; }; -struct bpf_sk_storage_data { +struct bpf_local_storage_data { /* smap is used as the searching key when looking up - * from sk->sk_bpf_storage. + * from the object's bpf_local_storage. * * Put it in the same cacheline as the data to minimize * the number of cachelines access during the cache hit case. */ - struct bpf_sk_storage_map __rcu *smap; + struct bpf_local_storage_map __rcu *smap; u8 data[] __aligned(8); }; -/* Linked to bpf_sk_storage and bpf_sk_storage_map */ -struct bpf_sk_storage_elem { - struct hlist_node map_node; /* Linked to bpf_sk_storage_map */ - struct hlist_node snode; /* Linked to bpf_sk_storage */ - struct bpf_sk_storage __rcu *sk_storage; +/* Linked to bpf_local_storage and bpf_local_storage_map */ +struct bpf_local_storage_elem { + struct hlist_node map_node; /* Linked to bpf_local_storage_map */ + struct hlist_node snode; /* Linked to bpf_local_storage */ + struct bpf_local_storage __rcu *local_storage; struct rcu_head rcu; /* 8 bytes hole */ /* The data is stored in aother cacheline to minimize * the number of cachelines access during a cache hit. */ - struct bpf_sk_storage_data sdata ____cacheline_aligned; + struct bpf_local_storage_data sdata ____cacheline_aligned; }; -#define SELEM(_SDATA) container_of((_SDATA), struct bpf_sk_storage_elem, sdata) +#define SELEM(_SDATA) \ + container_of((_SDATA), struct bpf_local_storage_elem, sdata) #define SDATA(_SELEM) (&(_SELEM)->sdata) -#define BPF_SK_STORAGE_CACHE_SIZE 16 +#define BPF_LOCAL_STORAGE_CACHE_SIZE 16 static DEFINE_SPINLOCK(cache_idx_lock); -static u64 cache_idx_usage_counts[BPF_SK_STORAGE_CACHE_SIZE]; +static u64 cache_idx_usage_counts[BPF_LOCAL_STORAGE_CACHE_SIZE]; -struct bpf_sk_storage { - struct bpf_sk_storage_data __rcu *cache[BPF_SK_STORAGE_CACHE_SIZE]; - struct hlist_head list; /* List of bpf_sk_storage_elem */ - struct sock *sk; /* The sk that owns the the above "list" of - * bpf_sk_storage_elem. +struct bpf_local_storage { + struct bpf_local_storage_data __rcu *cache[BPF_LOCAL_STORAGE_CACHE_SIZE]; + struct hlist_head list; /* List of bpf_local_storage_elem */ + struct sock *owner; /* The object that owns the above "list" of + * bpf_local_storage_elem. */ struct rcu_head rcu; raw_spinlock_t lock; /* Protect adding/removing from the "list" */ }; -static struct bucket *select_bucket(struct bpf_sk_storage_map *smap, - struct bpf_sk_storage_elem *selem) +static struct bpf_local_storage_map_bucket * +select_bucket(struct bpf_local_storage_map *smap, + struct bpf_local_storage_elem *selem) { return &smap->buckets[hash_ptr(selem, smap->bucket_log)]; } @@ -111,21 +112,21 @@ static int omem_charge(struct sock *sk, unsigned int size) return -ENOMEM; } -static bool selem_linked_to_sk(const struct bpf_sk_storage_elem *selem) +static bool selem_linked_to_storage(const struct bpf_local_storage_elem *selem) { return !hlist_unhashed(&selem->snode); } -static bool selem_linked_to_map(const struct bpf_sk_storage_elem *selem) +static bool selem_linked_to_map(const struct bpf_local_storage_elem *selem) { return !hlist_unhashed(&selem->map_node); } -static struct bpf_sk_storage_elem *selem_alloc(struct bpf_sk_storage_map *smap, - struct sock *sk, void *value, - bool charge_omem) +static struct bpf_local_storage_elem * +bpf_selem_alloc(struct bpf_local_storage_map *smap, struct sock *sk, + void *value, bool charge_omem) { - struct bpf_sk_storage_elem *selem; + struct bpf_local_storage_elem *selem; if (charge_omem && omem_charge(sk, smap->elem_size)) return NULL; @@ -143,89 +144,93 @@ static struct bpf_sk_storage_elem *selem_alloc(struct bpf_sk_storage_map *smap, return NULL; } -/* sk_storage->lock must be held and selem->sk_storage == sk_storage. +/* local_storage->lock must be held and selem->local_storage == local_storage. * The caller must ensure selem->smap is still valid to be * dereferenced for its smap->elem_size and smap->cache_idx. */ -static bool __selem_unlink_sk(struct bpf_sk_storage *sk_storage, - struct bpf_sk_storage_elem *selem, - bool uncharge_omem) +static bool +bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, + struct bpf_local_storage_elem *selem, + bool uncharge_omem) { - struct bpf_sk_storage_map *smap; - bool free_sk_storage; + struct bpf_local_storage_map *smap; + bool free_local_storage; struct sock *sk; smap = rcu_dereference(SDATA(selem)->smap); - sk = sk_storage->sk; + sk = local_storage->owner; - /* All uncharging on sk->sk_omem_alloc must be done first. - * sk may be freed once the last selem is unlinked from sk_storage. + /* All uncharging on the owner must be done first. + * The owner may be freed once the last selem is unlinked + * from local_storage. */ if (uncharge_omem) atomic_sub(smap->elem_size, &sk->sk_omem_alloc); - free_sk_storage = hlist_is_singular_node(&selem->snode, - &sk_storage->list); - if (free_sk_storage) { - atomic_sub(sizeof(struct bpf_sk_storage), &sk->sk_omem_alloc); - sk_storage->sk = NULL; + free_local_storage = hlist_is_singular_node(&selem->snode, + &local_storage->list); + if (free_local_storage) { + atomic_sub(sizeof(struct bpf_local_storage), &sk->sk_omem_alloc); + local_storage->owner = NULL; /* After this RCU_INIT, sk may be freed and cannot be used */ RCU_INIT_POINTER(sk->sk_bpf_storage, NULL); - /* sk_storage is not freed now. sk_storage->lock is - * still held and raw_spin_unlock_bh(&sk_storage->lock) + /* local_storage is not freed now. local_storage->lock is + * still held and raw_spin_unlock_bh(&local_storage->lock) * will be done by the caller. * * Although the unlock will be done under * rcu_read_lock(), it is more intutivie to - * read if kfree_rcu(sk_storage, rcu) is done - * after the raw_spin_unlock_bh(&sk_storage->lock). + * read if kfree_rcu(local_storage, rcu) is done + * after the raw_spin_unlock_bh(&local_storage->lock). * - * Hence, a "bool free_sk_storage" is returned + * Hence, a "bool free_local_storage" is returned * to the caller which then calls the kfree_rcu() * after unlock. */ } hlist_del_init_rcu(&selem->snode); - if (rcu_access_pointer(sk_storage->cache[smap->cache_idx]) == + if (rcu_access_pointer(local_storage->cache[smap->cache_idx]) == SDATA(selem)) - RCU_INIT_POINTER(sk_storage->cache[smap->cache_idx], NULL); + RCU_INIT_POINTER(local_storage->cache[smap->cache_idx], NULL); kfree_rcu(selem, rcu); - return free_sk_storage; + return free_local_storage; } -static void selem_unlink_sk(struct bpf_sk_storage_elem *selem) +static void __bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem) { - struct bpf_sk_storage *sk_storage; - bool free_sk_storage = false; + struct bpf_local_storage *local_storage; + bool free_local_storage = false; - if (unlikely(!selem_linked_to_sk(selem))) + if (unlikely(!selem_linked_to_storage(selem))) /* selem has already been unlinked from sk */ return; - sk_storage = rcu_dereference(selem->sk_storage); - raw_spin_lock_bh(&sk_storage->lock); - if (likely(selem_linked_to_sk(selem))) - free_sk_storage = __selem_unlink_sk(sk_storage, selem, true); - raw_spin_unlock_bh(&sk_storage->lock); + local_storage = rcu_dereference(selem->local_storage); + raw_spin_lock_bh(&local_storage->lock); + if (likely(selem_linked_to_storage(selem))) + free_local_storage = + bpf_selem_unlink_storage_nolock(local_storage, selem, true); + raw_spin_unlock_bh(&local_storage->lock); - if (free_sk_storage) - kfree_rcu(sk_storage, rcu); + if (free_local_storage) + kfree_rcu(local_storage, rcu); } -static void __selem_link_sk(struct bpf_sk_storage *sk_storage, - struct bpf_sk_storage_elem *selem) +static void +bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage, + struct bpf_local_storage_elem *selem) { - RCU_INIT_POINTER(selem->sk_storage, sk_storage); - hlist_add_head(&selem->snode, &sk_storage->list); + RCU_INIT_POINTER(selem->local_storage, local_storage); + hlist_add_head(&selem->snode, &local_storage->list); } -static void selem_unlink_map(struct bpf_sk_storage_elem *selem) +static void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem) { - struct bpf_sk_storage_map *smap; - struct bucket *b; + struct bpf_local_storage_map *smap; + struct bpf_local_storage_map_bucket *b; if (unlikely(!selem_linked_to_map(selem))) /* selem has already be unlinked from smap */ @@ -239,10 +244,10 @@ static void selem_unlink_map(struct bpf_sk_storage_elem *selem) raw_spin_unlock_bh(&b->lock); } -static void selem_link_map(struct bpf_sk_storage_map *smap, - struct bpf_sk_storage_elem *selem) +static void bpf_selem_link_map(struct bpf_local_storage_map *smap, + struct bpf_local_storage_elem *selem) { - struct bucket *b = select_bucket(smap, selem); + struct bpf_local_storage_map_bucket *b = select_bucket(smap, selem); raw_spin_lock_bh(&b->lock); RCU_INIT_POINTER(SDATA(selem)->smap, smap); @@ -250,31 +255,31 @@ static void selem_link_map(struct bpf_sk_storage_map *smap, raw_spin_unlock_bh(&b->lock); } -static void selem_unlink(struct bpf_sk_storage_elem *selem) +static void bpf_selem_unlink(struct bpf_local_storage_elem *selem) { - /* Always unlink from map before unlinking from sk_storage + /* Always unlink from map before unlinking from local_storage * because selem will be freed after successfully unlinked from - * the sk_storage. + * the local_storage. */ - selem_unlink_map(selem); - selem_unlink_sk(selem); + bpf_selem_unlink_map(selem); + __bpf_selem_unlink_storage(selem); } -static struct bpf_sk_storage_data * -__sk_storage_lookup(struct bpf_sk_storage *sk_storage, - struct bpf_sk_storage_map *smap, - bool cacheit_lockit) +static struct bpf_local_storage_data * +bpf_local_storage_lookup(struct bpf_local_storage *local_storage, + struct bpf_local_storage_map *smap, + bool cacheit_lockit) { - struct bpf_sk_storage_data *sdata; - struct bpf_sk_storage_elem *selem; + struct bpf_local_storage_data *sdata; + struct bpf_local_storage_elem *selem; /* Fast path (cache hit) */ - sdata = rcu_dereference(sk_storage->cache[smap->cache_idx]); + sdata = rcu_dereference(local_storage->cache[smap->cache_idx]); if (sdata && rcu_access_pointer(sdata->smap) == smap) return sdata; /* Slow path (cache miss) */ - hlist_for_each_entry_rcu(selem, &sk_storage->list, snode) + hlist_for_each_entry_rcu(selem, &local_storage->list, snode) if (rcu_access_pointer(SDATA(selem)->smap) == smap) break; @@ -286,33 +291,33 @@ __sk_storage_lookup(struct bpf_sk_storage *sk_storage, /* spinlock is needed to avoid racing with the * parallel delete. Otherwise, publishing an already * deleted sdata to the cache will become a use-after-free - * problem in the next __sk_storage_lookup(). + * problem in the next bpf_local_storage_lookup(). */ - raw_spin_lock_bh(&sk_storage->lock); - if (selem_linked_to_sk(selem)) - rcu_assign_pointer(sk_storage->cache[smap->cache_idx], + raw_spin_lock_bh(&local_storage->lock); + if (selem_linked_to_storage(selem)) + rcu_assign_pointer(local_storage->cache[smap->cache_idx], sdata); - raw_spin_unlock_bh(&sk_storage->lock); + raw_spin_unlock_bh(&local_storage->lock); } return sdata; } -static struct bpf_sk_storage_data * +static struct bpf_local_storage_data * sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit) { - struct bpf_sk_storage *sk_storage; - struct bpf_sk_storage_map *smap; + struct bpf_local_storage *sk_storage; + struct bpf_local_storage_map *smap; sk_storage = rcu_dereference(sk->sk_bpf_storage); if (!sk_storage) return NULL; - smap = (struct bpf_sk_storage_map *)map; - return __sk_storage_lookup(sk_storage, smap, cacheit_lockit); + smap = (struct bpf_local_storage_map *)map; + return bpf_local_storage_lookup(sk_storage, smap, cacheit_lockit); } -static int check_flags(const struct bpf_sk_storage_data *old_sdata, +static int check_flags(const struct bpf_local_storage_data *old_sdata, u64 map_flags) { if (old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_NOEXIST) @@ -327,10 +332,10 @@ static int check_flags(const struct bpf_sk_storage_data *old_sdata, } static int sk_storage_alloc(struct sock *sk, - struct bpf_sk_storage_map *smap, - struct bpf_sk_storage_elem *first_selem) + struct bpf_local_storage_map *smap, + struct bpf_local_storage_elem *first_selem) { - struct bpf_sk_storage *prev_sk_storage, *sk_storage; + struct bpf_local_storage *prev_sk_storage, *sk_storage; int err; err = omem_charge(sk, sizeof(*sk_storage)); @@ -344,10 +349,10 @@ static int sk_storage_alloc(struct sock *sk, } INIT_HLIST_HEAD(&sk_storage->list); raw_spin_lock_init(&sk_storage->lock); - sk_storage->sk = sk; + sk_storage->owner = sk; - __selem_link_sk(sk_storage, first_selem); - selem_link_map(smap, first_selem); + bpf_selem_link_storage_nolock(sk_storage, first_selem); + bpf_selem_link_map(smap, first_selem); /* Publish sk_storage to sk. sk->sk_lock cannot be acquired. * Hence, atomic ops is used to set sk->sk_bpf_storage * from NULL to the newly allocated sk_storage ptr. @@ -357,17 +362,17 @@ static int sk_storage_alloc(struct sock *sk, * the sk->sk_bpf_storage, the sk_storage->lock must * be held before setting sk->sk_bpf_storage to NULL. */ - prev_sk_storage = cmpxchg((struct bpf_sk_storage **)&sk->sk_bpf_storage, + prev_sk_storage = cmpxchg((struct bpf_local_storage **)&sk->sk_bpf_storage, NULL, sk_storage); if (unlikely(prev_sk_storage)) { - selem_unlink_map(first_selem); + bpf_selem_unlink_map(first_selem); err = -EAGAIN; goto uncharge; /* Note that even first_selem was linked to smap's * bucket->list, first_selem can be freed immediately * (instead of kfree_rcu) because - * bpf_sk_storage_map_free() does a + * bpf_local_storage_map_free() does a * synchronize_rcu() before walking the bucket->list. * Hence, no one is accessing selem from the * bucket->list under rcu_read_lock(). @@ -387,15 +392,14 @@ uncharge: * Otherwise, it will become a leak (and other memory issues * during map destruction). */ -static struct bpf_sk_storage_data *sk_storage_update(struct sock *sk, - struct bpf_map *map, - void *value, - u64 map_flags) +static struct bpf_local_storage_data * +bpf_local_storage_update(struct sock *sk, struct bpf_map *map, void *value, + u64 map_flags) { - struct bpf_sk_storage_data *old_sdata = NULL; - struct bpf_sk_storage_elem *selem; - struct bpf_sk_storage *sk_storage; - struct bpf_sk_storage_map *smap; + struct bpf_local_storage_data *old_sdata = NULL; + struct bpf_local_storage_elem *selem; + struct bpf_local_storage *local_storage; + struct bpf_local_storage_map *smap; int err; /* BPF_EXIST and BPF_NOEXIST cannot be both set */ @@ -404,15 +408,15 @@ static struct bpf_sk_storage_data *sk_storage_update(struct sock *sk, unlikely((map_flags & BPF_F_LOCK) && !map_value_has_spin_lock(map))) return ERR_PTR(-EINVAL); - smap = (struct bpf_sk_storage_map *)map; - sk_storage = rcu_dereference(sk->sk_bpf_storage); - if (!sk_storage || hlist_empty(&sk_storage->list)) { - /* Very first elem for this sk */ + smap = (struct bpf_local_storage_map *)map; + local_storage = rcu_dereference(sk->sk_bpf_storage); + if (!local_storage || hlist_empty(&local_storage->list)) { + /* Very first elem for the owner */ err = check_flags(NULL, map_flags); if (err) return ERR_PTR(err); - selem = selem_alloc(smap, sk, value, true); + selem = bpf_selem_alloc(smap, sk, value, true); if (!selem) return ERR_PTR(-ENOMEM); @@ -428,25 +432,26 @@ static struct bpf_sk_storage_data *sk_storage_update(struct sock *sk, if ((map_flags & BPF_F_LOCK) && !(map_flags & BPF_NOEXIST)) { /* Hoping to find an old_sdata to do inline update - * such that it can avoid taking the sk_storage->lock + * such that it can avoid taking the local_storage->lock * and changing the lists. */ - old_sdata = __sk_storage_lookup(sk_storage, smap, false); + old_sdata = + bpf_local_storage_lookup(local_storage, smap, false); err = check_flags(old_sdata, map_flags); if (err) return ERR_PTR(err); - if (old_sdata && selem_linked_to_sk(SELEM(old_sdata))) { + if (old_sdata && selem_linked_to_storage(SELEM(old_sdata))) { copy_map_value_locked(map, old_sdata->data, value, false); return old_sdata; } } - raw_spin_lock_bh(&sk_storage->lock); + raw_spin_lock_bh(&local_storage->lock); - /* Recheck sk_storage->list under sk_storage->lock */ - if (unlikely(hlist_empty(&sk_storage->list))) { - /* A parallel del is happening and sk_storage is going + /* Recheck local_storage->list under local_storage->lock */ + if (unlikely(hlist_empty(&local_storage->list))) { + /* A parallel del is happening and local_storage is going * away. It has just been checked before, so very * unlikely. Return instead of retry to keep things * simple. @@ -455,7 +460,7 @@ static struct bpf_sk_storage_data *sk_storage_update(struct sock *sk, goto unlock_err; } - old_sdata = __sk_storage_lookup(sk_storage, smap, false); + old_sdata = bpf_local_storage_lookup(local_storage, smap, false); err = check_flags(old_sdata, map_flags); if (err) goto unlock_err; @@ -466,50 +471,52 @@ static struct bpf_sk_storage_data *sk_storage_update(struct sock *sk, goto unlock; } - /* sk_storage->lock is held. Hence, we are sure + /* local_storage->lock is held. Hence, we are sure * we can unlink and uncharge the old_sdata successfully * later. Hence, instead of charging the new selem now * and then uncharge the old selem later (which may cause * a potential but unnecessary charge failure), avoid taking * a charge at all here (the "!old_sdata" check) and the - * old_sdata will not be uncharged later during __selem_unlink_sk(). + * old_sdata will not be uncharged later during + * bpf_selem_unlink_storage_nolock(). */ - selem = selem_alloc(smap, sk, value, !old_sdata); + selem = bpf_selem_alloc(smap, sk, value, !old_sdata); if (!selem) { err = -ENOMEM; goto unlock_err; } /* First, link the new selem to the map */ - selem_link_map(smap, selem); + bpf_selem_link_map(smap, selem); - /* Second, link (and publish) the new selem to sk_storage */ - __selem_link_sk(sk_storage, selem); + /* Second, link (and publish) the new selem to local_storage */ + bpf_selem_link_storage_nolock(local_storage, selem); /* Third, remove old selem, SELEM(old_sdata) */ if (old_sdata) { - selem_unlink_map(SELEM(old_sdata)); - __selem_unlink_sk(sk_storage, SELEM(old_sdata), false); + bpf_selem_unlink_map(SELEM(old_sdata)); + bpf_selem_unlink_storage_nolock(local_storage, SELEM(old_sdata), + false); } unlock: - raw_spin_unlock_bh(&sk_storage->lock); + raw_spin_unlock_bh(&local_storage->lock); return SDATA(selem); unlock_err: - raw_spin_unlock_bh(&sk_storage->lock); + raw_spin_unlock_bh(&local_storage->lock); return ERR_PTR(err); } static int sk_storage_delete(struct sock *sk, struct bpf_map *map) { - struct bpf_sk_storage_data *sdata; + struct bpf_local_storage_data *sdata; sdata = sk_storage_lookup(sk, map, false); if (!sdata) return -ENOENT; - selem_unlink(SELEM(sdata)); + bpf_selem_unlink(SELEM(sdata)); return 0; } @@ -521,7 +528,7 @@ static u16 cache_idx_get(void) spin_lock(&cache_idx_lock); - for (i = 0; i < BPF_SK_STORAGE_CACHE_SIZE; i++) { + for (i = 0; i < BPF_LOCAL_STORAGE_CACHE_SIZE; i++) { if (cache_idx_usage_counts[i] < min_usage) { min_usage = cache_idx_usage_counts[i]; res = i; @@ -548,8 +555,8 @@ static void cache_idx_free(u16 idx) /* Called by __sk_destruct() & bpf_sk_storage_clone() */ void bpf_sk_storage_free(struct sock *sk) { - struct bpf_sk_storage_elem *selem; - struct bpf_sk_storage *sk_storage; + struct bpf_local_storage_elem *selem; + struct bpf_local_storage *sk_storage; bool free_sk_storage = false; struct hlist_node *n; @@ -565,7 +572,7 @@ void bpf_sk_storage_free(struct sock *sk) * Thus, no elem can be added-to or deleted-from the * sk_storage->list by the bpf_prog or by the bpf-map's syscall. * - * It is racing with bpf_sk_storage_map_free() alone + * It is racing with bpf_local_storage_map_free() alone * when unlinking elem from the sk_storage->list and * the map's bucket->list. */ @@ -574,8 +581,9 @@ void bpf_sk_storage_free(struct sock *sk) /* Always unlink from map before unlinking from * sk_storage. */ - selem_unlink_map(selem); - free_sk_storage = __selem_unlink_sk(sk_storage, selem, true); + bpf_selem_unlink_map(selem); + free_sk_storage = bpf_selem_unlink_storage_nolock(sk_storage, + selem, true); } raw_spin_unlock_bh(&sk_storage->lock); rcu_read_unlock(); @@ -584,14 +592,14 @@ void bpf_sk_storage_free(struct sock *sk) kfree_rcu(sk_storage, rcu); } -static void bpf_sk_storage_map_free(struct bpf_map *map) +static void bpf_local_storage_map_free(struct bpf_map *map) { - struct bpf_sk_storage_elem *selem; - struct bpf_sk_storage_map *smap; - struct bucket *b; + struct bpf_local_storage_elem *selem; + struct bpf_local_storage_map *smap; + struct bpf_local_storage_map_bucket *b; unsigned int i; - smap = (struct bpf_sk_storage_map *)map; + smap = (struct bpf_local_storage_map *)map; cache_idx_free(smap->cache_idx); @@ -604,10 +612,10 @@ static void bpf_sk_storage_map_free(struct bpf_map *map) /* bpf prog and the userspace can no longer access this map * now. No new selem (of this map) can be added - * to the sk->sk_bpf_storage or to the map bucket's list. + * to the owner->storage or to the map bucket's list. * * The elem of this map can be cleaned up here - * or + * or when the storage is freed e.g. * by bpf_sk_storage_free() during __sk_destruct(). */ for (i = 0; i < (1U << smap->bucket_log); i++) { @@ -615,26 +623,26 @@ static void bpf_sk_storage_map_free(struct bpf_map *map) rcu_read_lock(); /* No one is adding to b->list now */ - while ((selem = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(&b->list)), - struct bpf_sk_storage_elem, - map_node))) { - selem_unlink(selem); + while ((selem = hlist_entry_safe( + rcu_dereference_raw(hlist_first_rcu(&b->list)), + struct bpf_local_storage_elem, map_node))) { + bpf_selem_unlink(selem); cond_resched_rcu(); } rcu_read_unlock(); } - /* bpf_sk_storage_free() may still need to access the map. - * e.g. bpf_sk_storage_free() has unlinked selem from the map + /* While freeing the storage we may still need to access the map. + * + * e.g. when bpf_sk_storage_free() has unlinked selem from the map * which then made the above while((selem = ...)) loop - * exited immediately. + * exit immediately. * - * However, the bpf_sk_storage_free() still needs to access - * the smap->elem_size to do the uncharging in - * __selem_unlink_sk(). + * However, while freeing the storage one still needs to access the + * smap->elem_size to do the uncharging in + * bpf_selem_unlink_storage_nolock(). * - * Hence, wait another rcu grace period for the - * bpf_sk_storage_free() to finish. + * Hence, wait another rcu grace period for the storage to be freed. */ synchronize_rcu(); @@ -645,14 +653,15 @@ static void bpf_sk_storage_map_free(struct bpf_map *map) /* U16_MAX is much more than enough for sk local storage * considering a tcp_sock is ~2k. */ -#define MAX_VALUE_SIZE \ +#define BPF_LOCAL_STORAGE_MAX_VALUE_SIZE \ min_t(u32, \ - (KMALLOC_MAX_SIZE - MAX_BPF_STACK - sizeof(struct bpf_sk_storage_elem)), \ - (U16_MAX - sizeof(struct bpf_sk_storage_elem))) + (KMALLOC_MAX_SIZE - MAX_BPF_STACK - \ + sizeof(struct bpf_local_storage_elem)), \ + (U16_MAX - sizeof(struct bpf_local_storage_elem))) -static int bpf_sk_storage_map_alloc_check(union bpf_attr *attr) +static int bpf_local_storage_map_alloc_check(union bpf_attr *attr) { - if (attr->map_flags & ~SK_STORAGE_CREATE_FLAG_MASK || + if (attr->map_flags & ~BPF_LOCAL_STORAGE_CREATE_FLAG_MASK || !(attr->map_flags & BPF_F_NO_PREALLOC) || attr->max_entries || attr->key_size != sizeof(int) || !attr->value_size || @@ -663,15 +672,15 @@ static int bpf_sk_storage_map_alloc_check(union bpf_attr *attr) if (!bpf_capable()) return -EPERM; - if (attr->value_size > MAX_VALUE_SIZE) + if (attr->value_size > BPF_LOCAL_STORAGE_MAX_VALUE_SIZE) return -E2BIG; return 0; } -static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr) +static struct bpf_map *bpf_local_storage_map_alloc(union bpf_attr *attr) { - struct bpf_sk_storage_map *smap; + struct bpf_local_storage_map *smap; unsigned int i; u32 nbuckets; u64 cost; @@ -707,7 +716,8 @@ static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr) raw_spin_lock_init(&smap->buckets[i].lock); } - smap->elem_size = sizeof(struct bpf_sk_storage_elem) + attr->value_size; + smap->elem_size = + sizeof(struct bpf_local_storage_elem) + attr->value_size; smap->cache_idx = cache_idx_get(); return &smap->map; @@ -719,10 +729,10 @@ static int notsupp_get_next_key(struct bpf_map *map, void *key, return -ENOTSUPP; } -static int bpf_sk_storage_map_check_btf(const struct bpf_map *map, - const struct btf *btf, - const struct btf_type *key_type, - const struct btf_type *value_type) +static int bpf_local_storage_map_check_btf(const struct bpf_map *map, + const struct btf *btf, + const struct btf_type *key_type, + const struct btf_type *value_type) { u32 int_data; @@ -738,7 +748,7 @@ static int bpf_sk_storage_map_check_btf(const struct bpf_map *map, static void *bpf_fd_sk_storage_lookup_elem(struct bpf_map *map, void *key) { - struct bpf_sk_storage_data *sdata; + struct bpf_local_storage_data *sdata; struct socket *sock; int fd, err; @@ -756,14 +766,15 @@ static void *bpf_fd_sk_storage_lookup_elem(struct bpf_map *map, void *key) static int bpf_fd_sk_storage_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { - struct bpf_sk_storage_data *sdata; + struct bpf_local_storage_data *sdata; struct socket *sock; int fd, err; fd = *(int *)key; sock = sockfd_lookup(fd, &err); if (sock) { - sdata = sk_storage_update(sock->sk, map, value, map_flags); + sdata = bpf_local_storage_update(sock->sk, map, value, + map_flags); sockfd_put(sock); return PTR_ERR_OR_ZERO(sdata); } @@ -787,14 +798,14 @@ static int bpf_fd_sk_storage_delete_elem(struct bpf_map *map, void *key) return err; } -static struct bpf_sk_storage_elem * +static struct bpf_local_storage_elem * bpf_sk_storage_clone_elem(struct sock *newsk, - struct bpf_sk_storage_map *smap, - struct bpf_sk_storage_elem *selem) + struct bpf_local_storage_map *smap, + struct bpf_local_storage_elem *selem) { - struct bpf_sk_storage_elem *copy_selem; + struct bpf_local_storage_elem *copy_selem; - copy_selem = selem_alloc(smap, newsk, NULL, true); + copy_selem = bpf_selem_alloc(smap, newsk, NULL, true); if (!copy_selem) return NULL; @@ -810,9 +821,9 @@ bpf_sk_storage_clone_elem(struct sock *newsk, int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk) { - struct bpf_sk_storage *new_sk_storage = NULL; - struct bpf_sk_storage *sk_storage; - struct bpf_sk_storage_elem *selem; + struct bpf_local_storage *new_sk_storage = NULL; + struct bpf_local_storage *sk_storage; + struct bpf_local_storage_elem *selem; int ret = 0; RCU_INIT_POINTER(newsk->sk_bpf_storage, NULL); @@ -824,8 +835,8 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk) goto out; hlist_for_each_entry_rcu(selem, &sk_storage->list, snode) { - struct bpf_sk_storage_elem *copy_selem; - struct bpf_sk_storage_map *smap; + struct bpf_local_storage_elem *copy_selem; + struct bpf_local_storage_map *smap; struct bpf_map *map; smap = rcu_dereference(SDATA(selem)->smap); @@ -833,7 +844,7 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk) continue; /* Note that for lockless listeners adding new element - * here can race with cleanup in bpf_sk_storage_map_free. + * here can race with cleanup in bpf_local_storage_map_free. * Try to grab map refcnt to make sure that it's still * alive and prevent concurrent removal. */ @@ -849,8 +860,8 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk) } if (new_sk_storage) { - selem_link_map(smap, copy_selem); - __selem_link_sk(new_sk_storage, copy_selem); + bpf_selem_link_map(smap, copy_selem); + bpf_selem_link_storage_nolock(new_sk_storage, copy_selem); } else { ret = sk_storage_alloc(newsk, smap, copy_selem); if (ret) { @@ -861,7 +872,8 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk) goto out; } - new_sk_storage = rcu_dereference(copy_selem->sk_storage); + new_sk_storage = + rcu_dereference(copy_selem->local_storage); } bpf_map_put(map); } @@ -879,7 +891,7 @@ out: BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk, void *, value, u64, flags) { - struct bpf_sk_storage_data *sdata; + struct bpf_local_storage_data *sdata; if (flags > BPF_SK_STORAGE_GET_F_CREATE) return (unsigned long)NULL; @@ -895,7 +907,7 @@ BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk, * destruction). */ refcount_inc_not_zero(&sk->sk_refcnt)) { - sdata = sk_storage_update(sk, map, value, BPF_NOEXIST); + sdata = bpf_local_storage_update(sk, map, value, BPF_NOEXIST); /* sk must be a fullsock (guaranteed by verifier), * so sock_gen_put() is unnecessary. */ @@ -922,15 +934,15 @@ BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk) static int sk_storage_map_btf_id; const struct bpf_map_ops sk_storage_map_ops = { - .map_alloc_check = bpf_sk_storage_map_alloc_check, - .map_alloc = bpf_sk_storage_map_alloc, - .map_free = bpf_sk_storage_map_free, + .map_alloc_check = bpf_local_storage_map_alloc_check, + .map_alloc = bpf_local_storage_map_alloc, + .map_free = bpf_local_storage_map_free, .map_get_next_key = notsupp_get_next_key, .map_lookup_elem = bpf_fd_sk_storage_lookup_elem, .map_update_elem = bpf_fd_sk_storage_update_elem, .map_delete_elem = bpf_fd_sk_storage_delete_elem, - .map_check_btf = bpf_sk_storage_map_check_btf, - .map_btf_name = "bpf_sk_storage_map", + .map_check_btf = bpf_local_storage_map_check_btf, + .map_btf_name = "bpf_local_storage_map", .map_btf_id = &sk_storage_map_btf_id, }; @@ -1022,7 +1034,7 @@ bpf_sk_storage_diag_alloc(const struct nlattr *nla_stgs) u32 nr_maps = 0; int rem, err; - /* bpf_sk_storage_map is currently limited to CAP_SYS_ADMIN as + /* bpf_local_storage_map is currently limited to CAP_SYS_ADMIN as * the map_alloc_check() side also does. */ if (!bpf_capable()) @@ -1072,13 +1084,13 @@ err_free: } EXPORT_SYMBOL_GPL(bpf_sk_storage_diag_alloc); -static int diag_get(struct bpf_sk_storage_data *sdata, struct sk_buff *skb) +static int diag_get(struct bpf_local_storage_data *sdata, struct sk_buff *skb) { struct nlattr *nla_stg, *nla_value; - struct bpf_sk_storage_map *smap; + struct bpf_local_storage_map *smap; /* It cannot exceed max nlattr's payload */ - BUILD_BUG_ON(U16_MAX - NLA_HDRLEN < MAX_VALUE_SIZE); + BUILD_BUG_ON(U16_MAX - NLA_HDRLEN < BPF_LOCAL_STORAGE_MAX_VALUE_SIZE); nla_stg = nla_nest_start(skb, SK_DIAG_BPF_STORAGE); if (!nla_stg) @@ -1114,9 +1126,9 @@ static int bpf_sk_storage_diag_put_all(struct sock *sk, struct sk_buff *skb, { /* stg_array_type (e.g. INET_DIAG_BPF_SK_STORAGES) */ unsigned int diag_size = nla_total_size(0); - struct bpf_sk_storage *sk_storage; - struct bpf_sk_storage_elem *selem; - struct bpf_sk_storage_map *smap; + struct bpf_local_storage *sk_storage; + struct bpf_local_storage_elem *selem; + struct bpf_local_storage_map *smap; struct nlattr *nla_stgs; unsigned int saved_len; int err = 0; @@ -1169,8 +1181,8 @@ int bpf_sk_storage_diag_put(struct bpf_sk_storage_diag *diag, { /* stg_array_type (e.g. INET_DIAG_BPF_SK_STORAGES) */ unsigned int diag_size = nla_total_size(0); - struct bpf_sk_storage *sk_storage; - struct bpf_sk_storage_data *sdata; + struct bpf_local_storage *sk_storage; + struct bpf_local_storage_data *sdata; struct nlattr *nla_stgs; unsigned int saved_len; int err = 0; @@ -1197,8 +1209,8 @@ int bpf_sk_storage_diag_put(struct bpf_sk_storage_diag *diag, saved_len = skb->len; for (i = 0; i < diag->nr_maps; i++) { - sdata = __sk_storage_lookup(sk_storage, - (struct bpf_sk_storage_map *)diag->maps[i], + sdata = bpf_local_storage_lookup(sk_storage, + (struct bpf_local_storage_map *)diag->maps[i], false); if (!sdata) @@ -1235,19 +1247,19 @@ struct bpf_iter_seq_sk_storage_map_info { unsigned skip_elems; }; -static struct bpf_sk_storage_elem * +static struct bpf_local_storage_elem * bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info, - struct bpf_sk_storage_elem *prev_selem) + struct bpf_local_storage_elem *prev_selem) { - struct bpf_sk_storage *sk_storage; - struct bpf_sk_storage_elem *selem; + struct bpf_local_storage *sk_storage; + struct bpf_local_storage_elem *selem; u32 skip_elems = info->skip_elems; - struct bpf_sk_storage_map *smap; + struct bpf_local_storage_map *smap; u32 bucket_id = info->bucket_id; u32 i, count, n_buckets; - struct bucket *b; + struct bpf_local_storage_map_bucket *b; - smap = (struct bpf_sk_storage_map *)info->map; + smap = (struct bpf_local_storage_map *)info->map; n_buckets = 1U << smap->bucket_log; if (bucket_id >= n_buckets) return NULL; @@ -1257,7 +1269,7 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info, count = 0; while (selem) { selem = hlist_entry_safe(selem->map_node.next, - struct bpf_sk_storage_elem, map_node); + struct bpf_local_storage_elem, map_node); if (!selem) { /* not found, unlock and go to the next bucket */ b = &smap->buckets[bucket_id++]; @@ -1265,7 +1277,7 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info, skip_elems = 0; break; } - sk_storage = rcu_dereference_raw(selem->sk_storage); + sk_storage = rcu_dereference_raw(selem->local_storage); if (sk_storage) { info->skip_elems = skip_elems + count; return selem; @@ -1278,7 +1290,7 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info, raw_spin_lock_bh(&b->lock); count = 0; hlist_for_each_entry(selem, &b->list, map_node) { - sk_storage = rcu_dereference_raw(selem->sk_storage); + sk_storage = rcu_dereference_raw(selem->local_storage); if (sk_storage && count >= skip_elems) { info->bucket_id = i; info->skip_elems = count; @@ -1297,7 +1309,7 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info, static void *bpf_sk_storage_map_seq_start(struct seq_file *seq, loff_t *pos) { - struct bpf_sk_storage_elem *selem; + struct bpf_local_storage_elem *selem; selem = bpf_sk_storage_map_seq_find_next(seq->private, NULL); if (!selem) @@ -1330,11 +1342,11 @@ DEFINE_BPF_ITER_FUNC(bpf_sk_storage_map, struct bpf_iter_meta *meta, void *value) static int __bpf_sk_storage_map_seq_show(struct seq_file *seq, - struct bpf_sk_storage_elem *selem) + struct bpf_local_storage_elem *selem) { struct bpf_iter_seq_sk_storage_map_info *info = seq->private; struct bpf_iter__bpf_sk_storage_map ctx = {}; - struct bpf_sk_storage *sk_storage; + struct bpf_local_storage *sk_storage; struct bpf_iter_meta meta; struct bpf_prog *prog; int ret = 0; @@ -1345,8 +1357,8 @@ static int __bpf_sk_storage_map_seq_show(struct seq_file *seq, ctx.meta = &meta; ctx.map = info->map; if (selem) { - sk_storage = rcu_dereference_raw(selem->sk_storage); - ctx.sk = sk_storage->sk; + sk_storage = rcu_dereference_raw(selem->local_storage); + ctx.sk = sk_storage->owner; ctx.value = SDATA(selem)->data; } ret = bpf_iter_run_prog(prog, &ctx); @@ -1363,13 +1375,13 @@ static int bpf_sk_storage_map_seq_show(struct seq_file *seq, void *v) static void bpf_sk_storage_map_seq_stop(struct seq_file *seq, void *v) { struct bpf_iter_seq_sk_storage_map_info *info = seq->private; - struct bpf_sk_storage_map *smap; - struct bucket *b; + struct bpf_local_storage_map *smap; + struct bpf_local_storage_map_bucket *b; if (!v) { (void)__bpf_sk_storage_map_seq_show(seq, v); } else { - smap = (struct bpf_sk_storage_map *)info->map; + smap = (struct bpf_local_storage_map *)info->map; b = &smap->buckets[info->bucket_id]; raw_spin_unlock_bh(&b->lock); } diff --git a/tools/testing/selftests/bpf/progs/map_ptr_kern.c b/tools/testing/selftests/bpf/progs/map_ptr_kern.c index 473665cac67e..982a2d8aa844 100644 --- a/tools/testing/selftests/bpf/progs/map_ptr_kern.c +++ b/tools/testing/selftests/bpf/progs/map_ptr_kern.c @@ -589,7 +589,7 @@ static inline int check_stack(void) return 1; } -struct bpf_sk_storage_map { +struct bpf_local_storage_map { struct bpf_map map; } __attribute__((preserve_access_index)); @@ -602,8 +602,8 @@ struct { static inline int check_sk_storage(void) { - struct bpf_sk_storage_map *sk_storage = - (struct bpf_sk_storage_map *)&m_sk_storage; + struct bpf_local_storage_map *sk_storage = + (struct bpf_local_storage_map *)&m_sk_storage; struct bpf_map *map = (struct bpf_map *)&m_sk_storage; VERIFY(check(&sk_storage->map, map, sizeof(__u32), sizeof(__u32), 0)); -- cgit v1.2.3 From 4cc9ce4e739961a7b9e6b2f3b27a72124d356373 Mon Sep 17 00:00:00 2001 From: KP Singh Date: Tue, 25 Aug 2020 20:29:14 +0200 Subject: bpf: Generalize caching for sk_storage. Provide the a ability to define local storage caches on a per-object type basis. The caches and caching indices for different objects should not be inter-mixed as suggested in: https://lore.kernel.org/bpf/20200630193441.kdwnkestulg5erii@kafai-mbp.dhcp.thefacebook.com/ "Caching a sk-storage at idx=0 of a sk should not stop an inode-storage to be cached at the same idx of a inode." Signed-off-by: KP Singh Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20200825182919.1118197-3-kpsingh@chromium.org --- include/net/bpf_sk_storage.h | 19 +++++++++++++++++++ net/core/bpf_sk_storage.c | 31 +++++++++++++++---------------- 2 files changed, 34 insertions(+), 16 deletions(-) (limited to 'include/net') diff --git a/include/net/bpf_sk_storage.h b/include/net/bpf_sk_storage.h index 5036c94c0503..950c5aaba15e 100644 --- a/include/net/bpf_sk_storage.h +++ b/include/net/bpf_sk_storage.h @@ -3,6 +3,9 @@ #ifndef _BPF_SK_STORAGE_H #define _BPF_SK_STORAGE_H +#include +#include + struct sock; void bpf_sk_storage_free(struct sock *sk); @@ -15,6 +18,22 @@ struct sk_buff; struct nlattr; struct sock; +#define BPF_LOCAL_STORAGE_CACHE_SIZE 16 + +struct bpf_local_storage_cache { + spinlock_t idx_lock; + u64 idx_usage_counts[BPF_LOCAL_STORAGE_CACHE_SIZE]; +}; + +#define DEFINE_BPF_STORAGE_CACHE(name) \ +static struct bpf_local_storage_cache name = { \ + .idx_lock = __SPIN_LOCK_UNLOCKED(name.idx_lock), \ +} + +u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache); +void bpf_local_storage_cache_idx_free(struct bpf_local_storage_cache *cache, + u16 idx); + #ifdef CONFIG_BPF_SYSCALL int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk); struct bpf_sk_storage_diag * diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index f975e2d01207..ec61ee7c7ee4 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -14,6 +14,8 @@ #define BPF_LOCAL_STORAGE_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_CLONE) +DEFINE_BPF_STORAGE_CACHE(sk_cache); + struct bpf_local_storage_map_bucket { struct hlist_head list; raw_spinlock_t lock; @@ -78,10 +80,6 @@ struct bpf_local_storage_elem { #define SELEM(_SDATA) \ container_of((_SDATA), struct bpf_local_storage_elem, sdata) #define SDATA(_SELEM) (&(_SELEM)->sdata) -#define BPF_LOCAL_STORAGE_CACHE_SIZE 16 - -static DEFINE_SPINLOCK(cache_idx_lock); -static u64 cache_idx_usage_counts[BPF_LOCAL_STORAGE_CACHE_SIZE]; struct bpf_local_storage { struct bpf_local_storage_data __rcu *cache[BPF_LOCAL_STORAGE_CACHE_SIZE]; @@ -521,16 +519,16 @@ static int sk_storage_delete(struct sock *sk, struct bpf_map *map) return 0; } -static u16 cache_idx_get(void) +u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache) { u64 min_usage = U64_MAX; u16 i, res = 0; - spin_lock(&cache_idx_lock); + spin_lock(&cache->idx_lock); for (i = 0; i < BPF_LOCAL_STORAGE_CACHE_SIZE; i++) { - if (cache_idx_usage_counts[i] < min_usage) { - min_usage = cache_idx_usage_counts[i]; + if (cache->idx_usage_counts[i] < min_usage) { + min_usage = cache->idx_usage_counts[i]; res = i; /* Found a free cache_idx */ @@ -538,18 +536,19 @@ static u16 cache_idx_get(void) break; } } - cache_idx_usage_counts[res]++; + cache->idx_usage_counts[res]++; - spin_unlock(&cache_idx_lock); + spin_unlock(&cache->idx_lock); return res; } -static void cache_idx_free(u16 idx) +void bpf_local_storage_cache_idx_free(struct bpf_local_storage_cache *cache, + u16 idx) { - spin_lock(&cache_idx_lock); - cache_idx_usage_counts[idx]--; - spin_unlock(&cache_idx_lock); + spin_lock(&cache->idx_lock); + cache->idx_usage_counts[idx]--; + spin_unlock(&cache->idx_lock); } /* Called by __sk_destruct() & bpf_sk_storage_clone() */ @@ -601,7 +600,7 @@ static void bpf_local_storage_map_free(struct bpf_map *map) smap = (struct bpf_local_storage_map *)map; - cache_idx_free(smap->cache_idx); + bpf_local_storage_cache_idx_free(&sk_cache, smap->cache_idx); /* Note that this map might be concurrently cloned from * bpf_sk_storage_clone. Wait for any existing bpf_sk_storage_clone @@ -718,7 +717,7 @@ static struct bpf_map *bpf_local_storage_map_alloc(union bpf_attr *attr) smap->elem_size = sizeof(struct bpf_local_storage_elem) + attr->value_size; - smap->cache_idx = cache_idx_get(); + smap->cache_idx = bpf_local_storage_cache_idx_get(&sk_cache); return &smap->map; } -- cgit v1.2.3 From f836a56e84ffc9f1a1cd73f77e10404ca46a4616 Mon Sep 17 00:00:00 2001 From: KP Singh Date: Tue, 25 Aug 2020 20:29:15 +0200 Subject: bpf: Generalize bpf_sk_storage Refactor the functionality in bpf_sk_storage.c so that concept of storage linked to kernel objects can be extended to other objects like inode, task_struct etc. Each new local storage will still be a separate map and provide its own set of helpers. This allows for future object specific extensions and still share a lot of the underlying implementation. This includes the changes suggested by Martin in: https://lore.kernel.org/bpf/20200725013047.4006241-1-kafai@fb.com/ adding new map operations to support bpf_local_storage maps: * storages for different kernel objects to optionally have different memory charging strategy (map_local_storage_charge, map_local_storage_uncharge) * Functionality to extract the storage pointer from a pointer to the owning object (map_owner_storage_ptr) Co-developed-by: Martin KaFai Lau Signed-off-by: Martin KaFai Lau Signed-off-by: KP Singh Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200825182919.1118197-4-kpsingh@chromium.org --- include/linux/bpf.h | 8 ++ include/net/bpf_sk_storage.h | 52 +++++++++ include/uapi/linux/bpf.h | 8 +- net/core/bpf_sk_storage.c | 238 +++++++++++++++++++++++++++-------------- tools/include/uapi/linux/bpf.h | 8 +- 5 files changed, 228 insertions(+), 86 deletions(-) (limited to 'include/net') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 81f38e2fda78..8c443b93ac11 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -34,6 +34,8 @@ struct btf_type; struct exception_table_entry; struct seq_operations; struct bpf_iter_aux_info; +struct bpf_local_storage; +struct bpf_local_storage_map; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; @@ -104,6 +106,12 @@ struct bpf_map_ops { __poll_t (*map_poll)(struct bpf_map *map, struct file *filp, struct poll_table_struct *pts); + /* Functions called by bpf_local_storage maps */ + int (*map_local_storage_charge)(struct bpf_local_storage_map *smap, + void *owner, u32 size); + void (*map_local_storage_uncharge)(struct bpf_local_storage_map *smap, + void *owner, u32 size); + struct bpf_local_storage __rcu ** (*map_owner_storage_ptr)(void *owner); /* BTF name and id of struct allocated by map_alloc */ const char * const map_btf_name; int *map_btf_id; diff --git a/include/net/bpf_sk_storage.h b/include/net/bpf_sk_storage.h index 950c5aaba15e..9e631b5466e3 100644 --- a/include/net/bpf_sk_storage.h +++ b/include/net/bpf_sk_storage.h @@ -3,8 +3,15 @@ #ifndef _BPF_SK_STORAGE_H #define _BPF_SK_STORAGE_H +#include +#include +#include #include #include +#include +#include +#include +#include struct sock; @@ -13,6 +20,7 @@ void bpf_sk_storage_free(struct sock *sk); extern const struct bpf_func_proto bpf_sk_storage_get_proto; extern const struct bpf_func_proto bpf_sk_storage_delete_proto; +struct bpf_local_storage_elem; struct bpf_sk_storage_diag; struct sk_buff; struct nlattr; @@ -34,6 +42,50 @@ u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache); void bpf_local_storage_cache_idx_free(struct bpf_local_storage_cache *cache, u16 idx); +/* Helper functions for bpf_local_storage */ +int bpf_local_storage_map_alloc_check(union bpf_attr *attr); + +struct bpf_local_storage_map *bpf_local_storage_map_alloc(union bpf_attr *attr); + +struct bpf_local_storage_data * +bpf_local_storage_lookup(struct bpf_local_storage *local_storage, + struct bpf_local_storage_map *smap, + bool cacheit_lockit); + +void bpf_local_storage_map_free(struct bpf_local_storage_map *smap); + +int bpf_local_storage_map_check_btf(const struct bpf_map *map, + const struct btf *btf, + const struct btf_type *key_type, + const struct btf_type *value_type); + +void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage, + struct bpf_local_storage_elem *selem); + +bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, + struct bpf_local_storage_elem *selem, + bool uncharge_omem); + +void bpf_selem_unlink(struct bpf_local_storage_elem *selem); + +void bpf_selem_link_map(struct bpf_local_storage_map *smap, + struct bpf_local_storage_elem *selem); + +void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem); + +struct bpf_local_storage_elem * +bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, void *value, + bool charge_mem); + +int +bpf_local_storage_alloc(void *owner, + struct bpf_local_storage_map *smap, + struct bpf_local_storage_elem *first_selem); + +struct bpf_local_storage_data * +bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, + void *value, u64 map_flags); + #ifdef CONFIG_BPF_SYSCALL int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk); struct bpf_sk_storage_diag * diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 544b89a64918..2cbd137eed86 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3765,9 +3765,13 @@ enum { BPF_F_SYSCTL_BASE_NAME = (1ULL << 0), }; -/* BPF_FUNC_sk_storage_get flags */ +/* BPF_FUNC__storage_get flags */ enum { - BPF_SK_STORAGE_GET_F_CREATE = (1ULL << 0), + BPF_LOCAL_STORAGE_GET_F_CREATE = (1ULL << 0), + /* BPF_SK_STORAGE_GET_F_CREATE is only kept for backward compatibility + * and BPF_LOCAL_STORAGE_GET_F_CREATE must be used instead. + */ + BPF_SK_STORAGE_GET_F_CREATE = BPF_LOCAL_STORAGE_GET_F_CREATE, }; /* BPF_FUNC_read_branch_records flags. */ diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index ec61ee7c7ee4..cd8b7017913b 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -84,7 +84,7 @@ struct bpf_local_storage_elem { struct bpf_local_storage { struct bpf_local_storage_data __rcu *cache[BPF_LOCAL_STORAGE_CACHE_SIZE]; struct hlist_head list; /* List of bpf_local_storage_elem */ - struct sock *owner; /* The object that owns the above "list" of + void *owner; /* The object that owns the above "list" of * bpf_local_storage_elem. */ struct rcu_head rcu; @@ -110,6 +110,33 @@ static int omem_charge(struct sock *sk, unsigned int size) return -ENOMEM; } +static int mem_charge(struct bpf_local_storage_map *smap, void *owner, u32 size) +{ + struct bpf_map *map = &smap->map; + + if (!map->ops->map_local_storage_charge) + return 0; + + return map->ops->map_local_storage_charge(smap, owner, size); +} + +static void mem_uncharge(struct bpf_local_storage_map *smap, void *owner, + u32 size) +{ + struct bpf_map *map = &smap->map; + + if (map->ops->map_local_storage_uncharge) + map->ops->map_local_storage_uncharge(smap, owner, size); +} + +static struct bpf_local_storage __rcu ** +owner_storage(struct bpf_local_storage_map *smap, void *owner) +{ + struct bpf_map *map = &smap->map; + + return map->ops->map_owner_storage_ptr(owner); +} + static bool selem_linked_to_storage(const struct bpf_local_storage_elem *selem) { return !hlist_unhashed(&selem->snode); @@ -120,13 +147,13 @@ static bool selem_linked_to_map(const struct bpf_local_storage_elem *selem) return !hlist_unhashed(&selem->map_node); } -static struct bpf_local_storage_elem * -bpf_selem_alloc(struct bpf_local_storage_map *smap, struct sock *sk, - void *value, bool charge_omem) +struct bpf_local_storage_elem * +bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, + void *value, bool charge_mem) { struct bpf_local_storage_elem *selem; - if (charge_omem && omem_charge(sk, smap->elem_size)) + if (charge_mem && mem_charge(smap, owner, smap->elem_size)) return NULL; selem = kzalloc(smap->elem_size, GFP_ATOMIC | __GFP_NOWARN); @@ -136,8 +163,8 @@ bpf_selem_alloc(struct bpf_local_storage_map *smap, struct sock *sk, return selem; } - if (charge_omem) - atomic_sub(smap->elem_size, &sk->sk_omem_alloc); + if (charge_mem) + mem_uncharge(smap, owner, smap->elem_size); return NULL; } @@ -146,32 +173,32 @@ bpf_selem_alloc(struct bpf_local_storage_map *smap, struct sock *sk, * The caller must ensure selem->smap is still valid to be * dereferenced for its smap->elem_size and smap->cache_idx. */ -static bool -bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, - struct bpf_local_storage_elem *selem, - bool uncharge_omem) +bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, + struct bpf_local_storage_elem *selem, + bool uncharge_mem) { struct bpf_local_storage_map *smap; bool free_local_storage; - struct sock *sk; + void *owner; smap = rcu_dereference(SDATA(selem)->smap); - sk = local_storage->owner; + owner = local_storage->owner; /* All uncharging on the owner must be done first. * The owner may be freed once the last selem is unlinked * from local_storage. */ - if (uncharge_omem) - atomic_sub(smap->elem_size, &sk->sk_omem_alloc); + if (uncharge_mem) + mem_uncharge(smap, owner, smap->elem_size); free_local_storage = hlist_is_singular_node(&selem->snode, &local_storage->list); if (free_local_storage) { - atomic_sub(sizeof(struct bpf_local_storage), &sk->sk_omem_alloc); + mem_uncharge(smap, owner, sizeof(struct bpf_local_storage)); local_storage->owner = NULL; - /* After this RCU_INIT, sk may be freed and cannot be used */ - RCU_INIT_POINTER(sk->sk_bpf_storage, NULL); + + /* After this RCU_INIT, owner may be freed and cannot be used */ + RCU_INIT_POINTER(*owner_storage(smap, owner), NULL); /* local_storage is not freed now. local_storage->lock is * still held and raw_spin_unlock_bh(&local_storage->lock) @@ -209,23 +236,22 @@ static void __bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem) local_storage = rcu_dereference(selem->local_storage); raw_spin_lock_bh(&local_storage->lock); if (likely(selem_linked_to_storage(selem))) - free_local_storage = - bpf_selem_unlink_storage_nolock(local_storage, selem, true); + free_local_storage = bpf_selem_unlink_storage_nolock( + local_storage, selem, true); raw_spin_unlock_bh(&local_storage->lock); if (free_local_storage) kfree_rcu(local_storage, rcu); } -static void -bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage, - struct bpf_local_storage_elem *selem) +void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage, + struct bpf_local_storage_elem *selem) { RCU_INIT_POINTER(selem->local_storage, local_storage); hlist_add_head(&selem->snode, &local_storage->list); } -static void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem) +void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem) { struct bpf_local_storage_map *smap; struct bpf_local_storage_map_bucket *b; @@ -242,8 +268,8 @@ static void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem) raw_spin_unlock_bh(&b->lock); } -static void bpf_selem_link_map(struct bpf_local_storage_map *smap, - struct bpf_local_storage_elem *selem) +void bpf_selem_link_map(struct bpf_local_storage_map *smap, + struct bpf_local_storage_elem *selem) { struct bpf_local_storage_map_bucket *b = select_bucket(smap, selem); @@ -253,7 +279,7 @@ static void bpf_selem_link_map(struct bpf_local_storage_map *smap, raw_spin_unlock_bh(&b->lock); } -static void bpf_selem_unlink(struct bpf_local_storage_elem *selem) +void bpf_selem_unlink(struct bpf_local_storage_elem *selem) { /* Always unlink from map before unlinking from local_storage * because selem will be freed after successfully unlinked from @@ -263,7 +289,7 @@ static void bpf_selem_unlink(struct bpf_local_storage_elem *selem) __bpf_selem_unlink_storage(selem); } -static struct bpf_local_storage_data * +struct bpf_local_storage_data * bpf_local_storage_lookup(struct bpf_local_storage *local_storage, struct bpf_local_storage_map *smap, bool cacheit_lockit) @@ -329,40 +355,45 @@ static int check_flags(const struct bpf_local_storage_data *old_sdata, return 0; } -static int sk_storage_alloc(struct sock *sk, +int bpf_local_storage_alloc(void *owner, struct bpf_local_storage_map *smap, struct bpf_local_storage_elem *first_selem) { - struct bpf_local_storage *prev_sk_storage, *sk_storage; + struct bpf_local_storage *prev_storage, *storage; + struct bpf_local_storage **owner_storage_ptr; int err; - err = omem_charge(sk, sizeof(*sk_storage)); + err = mem_charge(smap, owner, sizeof(*storage)); if (err) return err; - sk_storage = kzalloc(sizeof(*sk_storage), GFP_ATOMIC | __GFP_NOWARN); - if (!sk_storage) { + storage = kzalloc(sizeof(*storage), GFP_ATOMIC | __GFP_NOWARN); + if (!storage) { err = -ENOMEM; goto uncharge; } - INIT_HLIST_HEAD(&sk_storage->list); - raw_spin_lock_init(&sk_storage->lock); - sk_storage->owner = sk; - bpf_selem_link_storage_nolock(sk_storage, first_selem); + INIT_HLIST_HEAD(&storage->list); + raw_spin_lock_init(&storage->lock); + storage->owner = owner; + + bpf_selem_link_storage_nolock(storage, first_selem); bpf_selem_link_map(smap, first_selem); - /* Publish sk_storage to sk. sk->sk_lock cannot be acquired. - * Hence, atomic ops is used to set sk->sk_bpf_storage - * from NULL to the newly allocated sk_storage ptr. + + owner_storage_ptr = + (struct bpf_local_storage **)owner_storage(smap, owner); + /* Publish storage to the owner. + * Instead of using any lock of the kernel object (i.e. owner), + * cmpxchg will work with any kernel object regardless what + * the running context is, bh, irq...etc. * - * From now on, the sk->sk_bpf_storage pointer is protected - * by the sk_storage->lock. Hence, when freeing - * the sk->sk_bpf_storage, the sk_storage->lock must - * be held before setting sk->sk_bpf_storage to NULL. + * From now on, the owner->storage pointer (e.g. sk->sk_bpf_storage) + * is protected by the storage->lock. Hence, when freeing + * the owner->storage, the storage->lock must be held before + * setting owner->storage ptr to NULL. */ - prev_sk_storage = cmpxchg((struct bpf_local_storage **)&sk->sk_bpf_storage, - NULL, sk_storage); - if (unlikely(prev_sk_storage)) { + prev_storage = cmpxchg(owner_storage_ptr, NULL, storage); + if (unlikely(prev_storage)) { bpf_selem_unlink_map(first_selem); err = -EAGAIN; goto uncharge; @@ -380,8 +411,8 @@ static int sk_storage_alloc(struct sock *sk, return 0; uncharge: - kfree(sk_storage); - atomic_sub(sizeof(*sk_storage), &sk->sk_omem_alloc); + kfree(storage); + mem_uncharge(smap, owner, sizeof(*storage)); return err; } @@ -390,38 +421,37 @@ uncharge: * Otherwise, it will become a leak (and other memory issues * during map destruction). */ -static struct bpf_local_storage_data * -bpf_local_storage_update(struct sock *sk, struct bpf_map *map, void *value, - u64 map_flags) +struct bpf_local_storage_data * +bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, + void *value, u64 map_flags) { struct bpf_local_storage_data *old_sdata = NULL; struct bpf_local_storage_elem *selem; struct bpf_local_storage *local_storage; - struct bpf_local_storage_map *smap; int err; /* BPF_EXIST and BPF_NOEXIST cannot be both set */ if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST) || /* BPF_F_LOCK can only be used in a value with spin_lock */ - unlikely((map_flags & BPF_F_LOCK) && !map_value_has_spin_lock(map))) + unlikely((map_flags & BPF_F_LOCK) && + !map_value_has_spin_lock(&smap->map))) return ERR_PTR(-EINVAL); - smap = (struct bpf_local_storage_map *)map; - local_storage = rcu_dereference(sk->sk_bpf_storage); + local_storage = rcu_dereference(*owner_storage(smap, owner)); if (!local_storage || hlist_empty(&local_storage->list)) { /* Very first elem for the owner */ err = check_flags(NULL, map_flags); if (err) return ERR_PTR(err); - selem = bpf_selem_alloc(smap, sk, value, true); + selem = bpf_selem_alloc(smap, owner, value, true); if (!selem) return ERR_PTR(-ENOMEM); - err = sk_storage_alloc(sk, smap, selem); + err = bpf_local_storage_alloc(owner, smap, selem); if (err) { kfree(selem); - atomic_sub(smap->elem_size, &sk->sk_omem_alloc); + mem_uncharge(smap, owner, smap->elem_size); return ERR_PTR(err); } @@ -439,7 +469,7 @@ bpf_local_storage_update(struct sock *sk, struct bpf_map *map, void *value, if (err) return ERR_PTR(err); if (old_sdata && selem_linked_to_storage(SELEM(old_sdata))) { - copy_map_value_locked(map, old_sdata->data, + copy_map_value_locked(&smap->map, old_sdata->data, value, false); return old_sdata; } @@ -464,7 +494,8 @@ bpf_local_storage_update(struct sock *sk, struct bpf_map *map, void *value, goto unlock_err; if (old_sdata && (map_flags & BPF_F_LOCK)) { - copy_map_value_locked(map, old_sdata->data, value, false); + copy_map_value_locked(&smap->map, old_sdata->data, value, + false); selem = SELEM(old_sdata); goto unlock; } @@ -478,7 +509,7 @@ bpf_local_storage_update(struct sock *sk, struct bpf_map *map, void *value, * old_sdata will not be uncharged later during * bpf_selem_unlink_storage_nolock(). */ - selem = bpf_selem_alloc(smap, sk, value, !old_sdata); + selem = bpf_selem_alloc(smap, owner, value, !old_sdata); if (!selem) { err = -ENOMEM; goto unlock_err; @@ -591,17 +622,12 @@ void bpf_sk_storage_free(struct sock *sk) kfree_rcu(sk_storage, rcu); } -static void bpf_local_storage_map_free(struct bpf_map *map) +void bpf_local_storage_map_free(struct bpf_local_storage_map *smap) { struct bpf_local_storage_elem *selem; - struct bpf_local_storage_map *smap; struct bpf_local_storage_map_bucket *b; unsigned int i; - smap = (struct bpf_local_storage_map *)map; - - bpf_local_storage_cache_idx_free(&sk_cache, smap->cache_idx); - /* Note that this map might be concurrently cloned from * bpf_sk_storage_clone. Wait for any existing bpf_sk_storage_clone * RCU read section to finish before proceeding. New RCU @@ -646,7 +672,16 @@ static void bpf_local_storage_map_free(struct bpf_map *map) synchronize_rcu(); kvfree(smap->buckets); - kfree(map); + kfree(smap); +} + +static void sk_storage_map_free(struct bpf_map *map) +{ + struct bpf_local_storage_map *smap; + + smap = (struct bpf_local_storage_map *)map; + bpf_local_storage_cache_idx_free(&sk_cache, smap->cache_idx); + bpf_local_storage_map_free(smap); } /* U16_MAX is much more than enough for sk local storage @@ -658,7 +693,7 @@ static void bpf_local_storage_map_free(struct bpf_map *map) sizeof(struct bpf_local_storage_elem)), \ (U16_MAX - sizeof(struct bpf_local_storage_elem))) -static int bpf_local_storage_map_alloc_check(union bpf_attr *attr) +int bpf_local_storage_map_alloc_check(union bpf_attr *attr) { if (attr->map_flags & ~BPF_LOCAL_STORAGE_CREATE_FLAG_MASK || !(attr->map_flags & BPF_F_NO_PREALLOC) || @@ -677,7 +712,7 @@ static int bpf_local_storage_map_alloc_check(union bpf_attr *attr) return 0; } -static struct bpf_map *bpf_local_storage_map_alloc(union bpf_attr *attr) +struct bpf_local_storage_map *bpf_local_storage_map_alloc(union bpf_attr *attr) { struct bpf_local_storage_map *smap; unsigned int i; @@ -717,8 +752,19 @@ static struct bpf_map *bpf_local_storage_map_alloc(union bpf_attr *attr) smap->elem_size = sizeof(struct bpf_local_storage_elem) + attr->value_size; - smap->cache_idx = bpf_local_storage_cache_idx_get(&sk_cache); + return smap; +} + +static struct bpf_map *sk_storage_map_alloc(union bpf_attr *attr) +{ + struct bpf_local_storage_map *smap; + + smap = bpf_local_storage_map_alloc(attr); + if (IS_ERR(smap)) + return ERR_CAST(smap); + + smap->cache_idx = bpf_local_storage_cache_idx_get(&sk_cache); return &smap->map; } @@ -728,10 +774,10 @@ static int notsupp_get_next_key(struct bpf_map *map, void *key, return -ENOTSUPP; } -static int bpf_local_storage_map_check_btf(const struct bpf_map *map, - const struct btf *btf, - const struct btf_type *key_type, - const struct btf_type *value_type) +int bpf_local_storage_map_check_btf(const struct bpf_map *map, + const struct btf *btf, + const struct btf_type *key_type, + const struct btf_type *value_type) { u32 int_data; @@ -772,8 +818,9 @@ static int bpf_fd_sk_storage_update_elem(struct bpf_map *map, void *key, fd = *(int *)key; sock = sockfd_lookup(fd, &err); if (sock) { - sdata = bpf_local_storage_update(sock->sk, map, value, - map_flags); + sdata = bpf_local_storage_update( + sock->sk, (struct bpf_local_storage_map *)map, value, + map_flags); sockfd_put(sock); return PTR_ERR_OR_ZERO(sdata); } @@ -862,7 +909,7 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk) bpf_selem_link_map(smap, copy_selem); bpf_selem_link_storage_nolock(new_sk_storage, copy_selem); } else { - ret = sk_storage_alloc(newsk, smap, copy_selem); + ret = bpf_local_storage_alloc(newsk, smap, copy_selem); if (ret) { kfree(copy_selem); atomic_sub(smap->elem_size, @@ -906,7 +953,9 @@ BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk, * destruction). */ refcount_inc_not_zero(&sk->sk_refcnt)) { - sdata = bpf_local_storage_update(sk, map, value, BPF_NOEXIST); + sdata = bpf_local_storage_update( + sk, (struct bpf_local_storage_map *)map, value, + BPF_NOEXIST); /* sk must be a fullsock (guaranteed by verifier), * so sock_gen_put() is unnecessary. */ @@ -931,11 +980,33 @@ BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk) return -ENOENT; } +static int sk_storage_charge(struct bpf_local_storage_map *smap, + void *owner, u32 size) +{ + return omem_charge(owner, size); +} + +static void sk_storage_uncharge(struct bpf_local_storage_map *smap, + void *owner, u32 size) +{ + struct sock *sk = owner; + + atomic_sub(size, &sk->sk_omem_alloc); +} + +static struct bpf_local_storage __rcu ** +sk_storage_ptr(void *owner) +{ + struct sock *sk = owner; + + return &sk->sk_bpf_storage; +} + static int sk_storage_map_btf_id; const struct bpf_map_ops sk_storage_map_ops = { .map_alloc_check = bpf_local_storage_map_alloc_check, - .map_alloc = bpf_local_storage_map_alloc, - .map_free = bpf_local_storage_map_free, + .map_alloc = sk_storage_map_alloc, + .map_free = sk_storage_map_free, .map_get_next_key = notsupp_get_next_key, .map_lookup_elem = bpf_fd_sk_storage_lookup_elem, .map_update_elem = bpf_fd_sk_storage_update_elem, @@ -943,6 +1014,9 @@ const struct bpf_map_ops sk_storage_map_ops = { .map_check_btf = bpf_local_storage_map_check_btf, .map_btf_name = "bpf_local_storage_map", .map_btf_id = &sk_storage_map_btf_id, + .map_local_storage_charge = sk_storage_charge, + .map_local_storage_uncharge = sk_storage_uncharge, + .map_owner_storage_ptr = sk_storage_ptr, }; const struct bpf_func_proto bpf_sk_storage_get_proto = { diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 544b89a64918..2cbd137eed86 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3765,9 +3765,13 @@ enum { BPF_F_SYSCTL_BASE_NAME = (1ULL << 0), }; -/* BPF_FUNC_sk_storage_get flags */ +/* BPF_FUNC__storage_get flags */ enum { - BPF_SK_STORAGE_GET_F_CREATE = (1ULL << 0), + BPF_LOCAL_STORAGE_GET_F_CREATE = (1ULL << 0), + /* BPF_SK_STORAGE_GET_F_CREATE is only kept for backward compatibility + * and BPF_LOCAL_STORAGE_GET_F_CREATE must be used instead. + */ + BPF_SK_STORAGE_GET_F_CREATE = BPF_LOCAL_STORAGE_GET_F_CREATE, }; /* BPF_FUNC_read_branch_records flags. */ -- cgit v1.2.3 From 450af8d0f6be2e7dd2a528a3fb054bb726bf1747 Mon Sep 17 00:00:00 2001 From: KP Singh Date: Tue, 25 Aug 2020 20:29:16 +0200 Subject: bpf: Split bpf_local_storage to bpf_sk_storage A purely mechanical change: bpf_sk_storage.c = bpf_sk_storage.c + bpf_local_storage.c bpf_sk_storage.h = bpf_sk_storage.h + bpf_local_storage.h Signed-off-by: KP Singh Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20200825182919.1118197-5-kpsingh@chromium.org --- include/linux/bpf_local_storage.h | 163 +++++++++ include/net/bpf_sk_storage.h | 61 +--- kernel/bpf/Makefile | 1 + kernel/bpf/bpf_local_storage.c | 600 ++++++++++++++++++++++++++++++++++ net/core/bpf_sk_storage.c | 672 +------------------------------------- 5 files changed, 766 insertions(+), 731 deletions(-) create mode 100644 include/linux/bpf_local_storage.h create mode 100644 kernel/bpf/bpf_local_storage.c (limited to 'include/net') diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h new file mode 100644 index 000000000000..b2c9463f36a1 --- /dev/null +++ b/include/linux/bpf_local_storage.h @@ -0,0 +1,163 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2019 Facebook + * Copyright 2020 Google LLC. + */ + +#ifndef _BPF_LOCAL_STORAGE_H +#define _BPF_LOCAL_STORAGE_H + +#include +#include +#include +#include +#include +#include + +#define BPF_LOCAL_STORAGE_CACHE_SIZE 16 + +struct bpf_local_storage_map_bucket { + struct hlist_head list; + raw_spinlock_t lock; +}; + +/* Thp map is not the primary owner of a bpf_local_storage_elem. + * Instead, the container object (eg. sk->sk_bpf_storage) is. + * + * The map (bpf_local_storage_map) is for two purposes + * 1. Define the size of the "local storage". It is + * the map's value_size. + * + * 2. Maintain a list to keep track of all elems such + * that they can be cleaned up during the map destruction. + * + * When a bpf local storage is being looked up for a + * particular object, the "bpf_map" pointer is actually used + * as the "key" to search in the list of elem in + * the respective bpf_local_storage owned by the object. + * + * e.g. sk->sk_bpf_storage is the mini-map with the "bpf_map" pointer + * as the searching key. + */ +struct bpf_local_storage_map { + struct bpf_map map; + /* Lookup elem does not require accessing the map. + * + * Updating/Deleting requires a bucket lock to + * link/unlink the elem from the map. Having + * multiple buckets to improve contention. + */ + struct bpf_local_storage_map_bucket *buckets; + u32 bucket_log; + u16 elem_size; + u16 cache_idx; +}; + +struct bpf_local_storage_data { + /* smap is used as the searching key when looking up + * from the object's bpf_local_storage. + * + * Put it in the same cacheline as the data to minimize + * the number of cachelines access during the cache hit case. + */ + struct bpf_local_storage_map __rcu *smap; + u8 data[] __aligned(8); +}; + +/* Linked to bpf_local_storage and bpf_local_storage_map */ +struct bpf_local_storage_elem { + struct hlist_node map_node; /* Linked to bpf_local_storage_map */ + struct hlist_node snode; /* Linked to bpf_local_storage */ + struct bpf_local_storage __rcu *local_storage; + struct rcu_head rcu; + /* 8 bytes hole */ + /* The data is stored in aother cacheline to minimize + * the number of cachelines access during a cache hit. + */ + struct bpf_local_storage_data sdata ____cacheline_aligned; +}; + +struct bpf_local_storage { + struct bpf_local_storage_data __rcu *cache[BPF_LOCAL_STORAGE_CACHE_SIZE]; + struct hlist_head list; /* List of bpf_local_storage_elem */ + void *owner; /* The object that owns the above "list" of + * bpf_local_storage_elem. + */ + struct rcu_head rcu; + raw_spinlock_t lock; /* Protect adding/removing from the "list" */ +}; + +/* U16_MAX is much more than enough for sk local storage + * considering a tcp_sock is ~2k. + */ +#define BPF_LOCAL_STORAGE_MAX_VALUE_SIZE \ + min_t(u32, \ + (KMALLOC_MAX_SIZE - MAX_BPF_STACK - \ + sizeof(struct bpf_local_storage_elem)), \ + (U16_MAX - sizeof(struct bpf_local_storage_elem))) + +#define SELEM(_SDATA) \ + container_of((_SDATA), struct bpf_local_storage_elem, sdata) +#define SDATA(_SELEM) (&(_SELEM)->sdata) + +#define BPF_LOCAL_STORAGE_CACHE_SIZE 16 + +struct bpf_local_storage_cache { + spinlock_t idx_lock; + u64 idx_usage_counts[BPF_LOCAL_STORAGE_CACHE_SIZE]; +}; + +#define DEFINE_BPF_STORAGE_CACHE(name) \ +static struct bpf_local_storage_cache name = { \ + .idx_lock = __SPIN_LOCK_UNLOCKED(name.idx_lock), \ +} + +u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache); +void bpf_local_storage_cache_idx_free(struct bpf_local_storage_cache *cache, + u16 idx); + +/* Helper functions for bpf_local_storage */ +int bpf_local_storage_map_alloc_check(union bpf_attr *attr); + +struct bpf_local_storage_map *bpf_local_storage_map_alloc(union bpf_attr *attr); + +struct bpf_local_storage_data * +bpf_local_storage_lookup(struct bpf_local_storage *local_storage, + struct bpf_local_storage_map *smap, + bool cacheit_lockit); + +void bpf_local_storage_map_free(struct bpf_local_storage_map *smap); + +int bpf_local_storage_map_check_btf(const struct bpf_map *map, + const struct btf *btf, + const struct btf_type *key_type, + const struct btf_type *value_type); + +void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage, + struct bpf_local_storage_elem *selem); + +bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, + struct bpf_local_storage_elem *selem, + bool uncharge_omem); + +void bpf_selem_unlink(struct bpf_local_storage_elem *selem); + +void bpf_selem_link_map(struct bpf_local_storage_map *smap, + struct bpf_local_storage_elem *selem); + +void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem); + +struct bpf_local_storage_elem * +bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, void *value, + bool charge_mem); + +int +bpf_local_storage_alloc(void *owner, + struct bpf_local_storage_map *smap, + struct bpf_local_storage_elem *first_selem); + +struct bpf_local_storage_data * +bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, + void *value, u64 map_flags); + +#endif /* _BPF_LOCAL_STORAGE_H */ diff --git a/include/net/bpf_sk_storage.h b/include/net/bpf_sk_storage.h index 9e631b5466e3..3c516dd07caf 100644 --- a/include/net/bpf_sk_storage.h +++ b/include/net/bpf_sk_storage.h @@ -12,6 +12,7 @@ #include #include #include +#include struct sock; @@ -26,66 +27,6 @@ struct sk_buff; struct nlattr; struct sock; -#define BPF_LOCAL_STORAGE_CACHE_SIZE 16 - -struct bpf_local_storage_cache { - spinlock_t idx_lock; - u64 idx_usage_counts[BPF_LOCAL_STORAGE_CACHE_SIZE]; -}; - -#define DEFINE_BPF_STORAGE_CACHE(name) \ -static struct bpf_local_storage_cache name = { \ - .idx_lock = __SPIN_LOCK_UNLOCKED(name.idx_lock), \ -} - -u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache); -void bpf_local_storage_cache_idx_free(struct bpf_local_storage_cache *cache, - u16 idx); - -/* Helper functions for bpf_local_storage */ -int bpf_local_storage_map_alloc_check(union bpf_attr *attr); - -struct bpf_local_storage_map *bpf_local_storage_map_alloc(union bpf_attr *attr); - -struct bpf_local_storage_data * -bpf_local_storage_lookup(struct bpf_local_storage *local_storage, - struct bpf_local_storage_map *smap, - bool cacheit_lockit); - -void bpf_local_storage_map_free(struct bpf_local_storage_map *smap); - -int bpf_local_storage_map_check_btf(const struct bpf_map *map, - const struct btf *btf, - const struct btf_type *key_type, - const struct btf_type *value_type); - -void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage, - struct bpf_local_storage_elem *selem); - -bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, - struct bpf_local_storage_elem *selem, - bool uncharge_omem); - -void bpf_selem_unlink(struct bpf_local_storage_elem *selem); - -void bpf_selem_link_map(struct bpf_local_storage_map *smap, - struct bpf_local_storage_elem *selem); - -void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem); - -struct bpf_local_storage_elem * -bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, void *value, - bool charge_mem); - -int -bpf_local_storage_alloc(void *owner, - struct bpf_local_storage_map *smap, - struct bpf_local_storage_elem *first_selem); - -struct bpf_local_storage_data * -bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, - void *value, u64 map_flags); - #ifdef CONFIG_BPF_SYSCALL int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk); struct bpf_sk_storage_diag * diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 19e137aae40e..6961ff400cba 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -12,6 +12,7 @@ obj-$(CONFIG_BPF_JIT) += dispatcher.o ifeq ($(CONFIG_NET),y) obj-$(CONFIG_BPF_SYSCALL) += devmap.o obj-$(CONFIG_BPF_SYSCALL) += cpumap.o +obj-$(CONFIG_BPF_SYSCALL) += bpf_local_storage.o obj-$(CONFIG_BPF_SYSCALL) += offload.o obj-$(CONFIG_BPF_SYSCALL) += net_namespace.o endif diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c new file mode 100644 index 000000000000..ffa7d11fc2bd --- /dev/null +++ b/kernel/bpf/bpf_local_storage.c @@ -0,0 +1,600 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define BPF_LOCAL_STORAGE_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_CLONE) + +static struct bpf_local_storage_map_bucket * +select_bucket(struct bpf_local_storage_map *smap, + struct bpf_local_storage_elem *selem) +{ + return &smap->buckets[hash_ptr(selem, smap->bucket_log)]; +} + +static int mem_charge(struct bpf_local_storage_map *smap, void *owner, u32 size) +{ + struct bpf_map *map = &smap->map; + + if (!map->ops->map_local_storage_charge) + return 0; + + return map->ops->map_local_storage_charge(smap, owner, size); +} + +static void mem_uncharge(struct bpf_local_storage_map *smap, void *owner, + u32 size) +{ + struct bpf_map *map = &smap->map; + + if (map->ops->map_local_storage_uncharge) + map->ops->map_local_storage_uncharge(smap, owner, size); +} + +static struct bpf_local_storage __rcu ** +owner_storage(struct bpf_local_storage_map *smap, void *owner) +{ + struct bpf_map *map = &smap->map; + + return map->ops->map_owner_storage_ptr(owner); +} + +static bool selem_linked_to_storage(const struct bpf_local_storage_elem *selem) +{ + return !hlist_unhashed(&selem->snode); +} + +static bool selem_linked_to_map(const struct bpf_local_storage_elem *selem) +{ + return !hlist_unhashed(&selem->map_node); +} + +struct bpf_local_storage_elem * +bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, + void *value, bool charge_mem) +{ + struct bpf_local_storage_elem *selem; + + if (charge_mem && mem_charge(smap, owner, smap->elem_size)) + return NULL; + + selem = kzalloc(smap->elem_size, GFP_ATOMIC | __GFP_NOWARN); + if (selem) { + if (value) + memcpy(SDATA(selem)->data, value, smap->map.value_size); + return selem; + } + + if (charge_mem) + mem_uncharge(smap, owner, smap->elem_size); + + return NULL; +} + +/* local_storage->lock must be held and selem->local_storage == local_storage. + * The caller must ensure selem->smap is still valid to be + * dereferenced for its smap->elem_size and smap->cache_idx. + */ +bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, + struct bpf_local_storage_elem *selem, + bool uncharge_mem) +{ + struct bpf_local_storage_map *smap; + bool free_local_storage; + void *owner; + + smap = rcu_dereference(SDATA(selem)->smap); + owner = local_storage->owner; + + /* All uncharging on the owner must be done first. + * The owner may be freed once the last selem is unlinked + * from local_storage. + */ + if (uncharge_mem) + mem_uncharge(smap, owner, smap->elem_size); + + free_local_storage = hlist_is_singular_node(&selem->snode, + &local_storage->list); + if (free_local_storage) { + mem_uncharge(smap, owner, sizeof(struct bpf_local_storage)); + local_storage->owner = NULL; + + /* After this RCU_INIT, owner may be freed and cannot be used */ + RCU_INIT_POINTER(*owner_storage(smap, owner), NULL); + + /* local_storage is not freed now. local_storage->lock is + * still held and raw_spin_unlock_bh(&local_storage->lock) + * will be done by the caller. + * + * Although the unlock will be done under + * rcu_read_lock(), it is more intutivie to + * read if kfree_rcu(local_storage, rcu) is done + * after the raw_spin_unlock_bh(&local_storage->lock). + * + * Hence, a "bool free_local_storage" is returned + * to the caller which then calls the kfree_rcu() + * after unlock. + */ + } + hlist_del_init_rcu(&selem->snode); + if (rcu_access_pointer(local_storage->cache[smap->cache_idx]) == + SDATA(selem)) + RCU_INIT_POINTER(local_storage->cache[smap->cache_idx], NULL); + + kfree_rcu(selem, rcu); + + return free_local_storage; +} + +static void __bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem) +{ + struct bpf_local_storage *local_storage; + bool free_local_storage = false; + + if (unlikely(!selem_linked_to_storage(selem))) + /* selem has already been unlinked from sk */ + return; + + local_storage = rcu_dereference(selem->local_storage); + raw_spin_lock_bh(&local_storage->lock); + if (likely(selem_linked_to_storage(selem))) + free_local_storage = bpf_selem_unlink_storage_nolock( + local_storage, selem, true); + raw_spin_unlock_bh(&local_storage->lock); + + if (free_local_storage) + kfree_rcu(local_storage, rcu); +} + +void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage, + struct bpf_local_storage_elem *selem) +{ + RCU_INIT_POINTER(selem->local_storage, local_storage); + hlist_add_head(&selem->snode, &local_storage->list); +} + +void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem) +{ + struct bpf_local_storage_map *smap; + struct bpf_local_storage_map_bucket *b; + + if (unlikely(!selem_linked_to_map(selem))) + /* selem has already be unlinked from smap */ + return; + + smap = rcu_dereference(SDATA(selem)->smap); + b = select_bucket(smap, selem); + raw_spin_lock_bh(&b->lock); + if (likely(selem_linked_to_map(selem))) + hlist_del_init_rcu(&selem->map_node); + raw_spin_unlock_bh(&b->lock); +} + +void bpf_selem_link_map(struct bpf_local_storage_map *smap, + struct bpf_local_storage_elem *selem) +{ + struct bpf_local_storage_map_bucket *b = select_bucket(smap, selem); + + raw_spin_lock_bh(&b->lock); + RCU_INIT_POINTER(SDATA(selem)->smap, smap); + hlist_add_head_rcu(&selem->map_node, &b->list); + raw_spin_unlock_bh(&b->lock); +} + +void bpf_selem_unlink(struct bpf_local_storage_elem *selem) +{ + /* Always unlink from map before unlinking from local_storage + * because selem will be freed after successfully unlinked from + * the local_storage. + */ + bpf_selem_unlink_map(selem); + __bpf_selem_unlink_storage(selem); +} + +struct bpf_local_storage_data * +bpf_local_storage_lookup(struct bpf_local_storage *local_storage, + struct bpf_local_storage_map *smap, + bool cacheit_lockit) +{ + struct bpf_local_storage_data *sdata; + struct bpf_local_storage_elem *selem; + + /* Fast path (cache hit) */ + sdata = rcu_dereference(local_storage->cache[smap->cache_idx]); + if (sdata && rcu_access_pointer(sdata->smap) == smap) + return sdata; + + /* Slow path (cache miss) */ + hlist_for_each_entry_rcu(selem, &local_storage->list, snode) + if (rcu_access_pointer(SDATA(selem)->smap) == smap) + break; + + if (!selem) + return NULL; + + sdata = SDATA(selem); + if (cacheit_lockit) { + /* spinlock is needed to avoid racing with the + * parallel delete. Otherwise, publishing an already + * deleted sdata to the cache will become a use-after-free + * problem in the next bpf_local_storage_lookup(). + */ + raw_spin_lock_bh(&local_storage->lock); + if (selem_linked_to_storage(selem)) + rcu_assign_pointer(local_storage->cache[smap->cache_idx], + sdata); + raw_spin_unlock_bh(&local_storage->lock); + } + + return sdata; +} + +static int check_flags(const struct bpf_local_storage_data *old_sdata, + u64 map_flags) +{ + if (old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_NOEXIST) + /* elem already exists */ + return -EEXIST; + + if (!old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_EXIST) + /* elem doesn't exist, cannot update it */ + return -ENOENT; + + return 0; +} + +int bpf_local_storage_alloc(void *owner, + struct bpf_local_storage_map *smap, + struct bpf_local_storage_elem *first_selem) +{ + struct bpf_local_storage *prev_storage, *storage; + struct bpf_local_storage **owner_storage_ptr; + int err; + + err = mem_charge(smap, owner, sizeof(*storage)); + if (err) + return err; + + storage = kzalloc(sizeof(*storage), GFP_ATOMIC | __GFP_NOWARN); + if (!storage) { + err = -ENOMEM; + goto uncharge; + } + + INIT_HLIST_HEAD(&storage->list); + raw_spin_lock_init(&storage->lock); + storage->owner = owner; + + bpf_selem_link_storage_nolock(storage, first_selem); + bpf_selem_link_map(smap, first_selem); + + owner_storage_ptr = + (struct bpf_local_storage **)owner_storage(smap, owner); + /* Publish storage to the owner. + * Instead of using any lock of the kernel object (i.e. owner), + * cmpxchg will work with any kernel object regardless what + * the running context is, bh, irq...etc. + * + * From now on, the owner->storage pointer (e.g. sk->sk_bpf_storage) + * is protected by the storage->lock. Hence, when freeing + * the owner->storage, the storage->lock must be held before + * setting owner->storage ptr to NULL. + */ + prev_storage = cmpxchg(owner_storage_ptr, NULL, storage); + if (unlikely(prev_storage)) { + bpf_selem_unlink_map(first_selem); + err = -EAGAIN; + goto uncharge; + + /* Note that even first_selem was linked to smap's + * bucket->list, first_selem can be freed immediately + * (instead of kfree_rcu) because + * bpf_local_storage_map_free() does a + * synchronize_rcu() before walking the bucket->list. + * Hence, no one is accessing selem from the + * bucket->list under rcu_read_lock(). + */ + } + + return 0; + +uncharge: + kfree(storage); + mem_uncharge(smap, owner, sizeof(*storage)); + return err; +} + +/* sk cannot be going away because it is linking new elem + * to sk->sk_bpf_storage. (i.e. sk->sk_refcnt cannot be 0). + * Otherwise, it will become a leak (and other memory issues + * during map destruction). + */ +struct bpf_local_storage_data * +bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, + void *value, u64 map_flags) +{ + struct bpf_local_storage_data *old_sdata = NULL; + struct bpf_local_storage_elem *selem; + struct bpf_local_storage *local_storage; + int err; + + /* BPF_EXIST and BPF_NOEXIST cannot be both set */ + if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST) || + /* BPF_F_LOCK can only be used in a value with spin_lock */ + unlikely((map_flags & BPF_F_LOCK) && + !map_value_has_spin_lock(&smap->map))) + return ERR_PTR(-EINVAL); + + local_storage = rcu_dereference(*owner_storage(smap, owner)); + if (!local_storage || hlist_empty(&local_storage->list)) { + /* Very first elem for the owner */ + err = check_flags(NULL, map_flags); + if (err) + return ERR_PTR(err); + + selem = bpf_selem_alloc(smap, owner, value, true); + if (!selem) + return ERR_PTR(-ENOMEM); + + err = bpf_local_storage_alloc(owner, smap, selem); + if (err) { + kfree(selem); + mem_uncharge(smap, owner, smap->elem_size); + return ERR_PTR(err); + } + + return SDATA(selem); + } + + if ((map_flags & BPF_F_LOCK) && !(map_flags & BPF_NOEXIST)) { + /* Hoping to find an old_sdata to do inline update + * such that it can avoid taking the local_storage->lock + * and changing the lists. + */ + old_sdata = + bpf_local_storage_lookup(local_storage, smap, false); + err = check_flags(old_sdata, map_flags); + if (err) + return ERR_PTR(err); + if (old_sdata && selem_linked_to_storage(SELEM(old_sdata))) { + copy_map_value_locked(&smap->map, old_sdata->data, + value, false); + return old_sdata; + } + } + + raw_spin_lock_bh(&local_storage->lock); + + /* Recheck local_storage->list under local_storage->lock */ + if (unlikely(hlist_empty(&local_storage->list))) { + /* A parallel del is happening and local_storage is going + * away. It has just been checked before, so very + * unlikely. Return instead of retry to keep things + * simple. + */ + err = -EAGAIN; + goto unlock_err; + } + + old_sdata = bpf_local_storage_lookup(local_storage, smap, false); + err = check_flags(old_sdata, map_flags); + if (err) + goto unlock_err; + + if (old_sdata && (map_flags & BPF_F_LOCK)) { + copy_map_value_locked(&smap->map, old_sdata->data, value, + false); + selem = SELEM(old_sdata); + goto unlock; + } + + /* local_storage->lock is held. Hence, we are sure + * we can unlink and uncharge the old_sdata successfully + * later. Hence, instead of charging the new selem now + * and then uncharge the old selem later (which may cause + * a potential but unnecessary charge failure), avoid taking + * a charge at all here (the "!old_sdata" check) and the + * old_sdata will not be uncharged later during + * bpf_selem_unlink_storage_nolock(). + */ + selem = bpf_selem_alloc(smap, owner, value, !old_sdata); + if (!selem) { + err = -ENOMEM; + goto unlock_err; + } + + /* First, link the new selem to the map */ + bpf_selem_link_map(smap, selem); + + /* Second, link (and publish) the new selem to local_storage */ + bpf_selem_link_storage_nolock(local_storage, selem); + + /* Third, remove old selem, SELEM(old_sdata) */ + if (old_sdata) { + bpf_selem_unlink_map(SELEM(old_sdata)); + bpf_selem_unlink_storage_nolock(local_storage, SELEM(old_sdata), + false); + } + +unlock: + raw_spin_unlock_bh(&local_storage->lock); + return SDATA(selem); + +unlock_err: + raw_spin_unlock_bh(&local_storage->lock); + return ERR_PTR(err); +} + +u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache) +{ + u64 min_usage = U64_MAX; + u16 i, res = 0; + + spin_lock(&cache->idx_lock); + + for (i = 0; i < BPF_LOCAL_STORAGE_CACHE_SIZE; i++) { + if (cache->idx_usage_counts[i] < min_usage) { + min_usage = cache->idx_usage_counts[i]; + res = i; + + /* Found a free cache_idx */ + if (!min_usage) + break; + } + } + cache->idx_usage_counts[res]++; + + spin_unlock(&cache->idx_lock); + + return res; +} + +void bpf_local_storage_cache_idx_free(struct bpf_local_storage_cache *cache, + u16 idx) +{ + spin_lock(&cache->idx_lock); + cache->idx_usage_counts[idx]--; + spin_unlock(&cache->idx_lock); +} + +void bpf_local_storage_map_free(struct bpf_local_storage_map *smap) +{ + struct bpf_local_storage_elem *selem; + struct bpf_local_storage_map_bucket *b; + unsigned int i; + + /* Note that this map might be concurrently cloned from + * bpf_sk_storage_clone. Wait for any existing bpf_sk_storage_clone + * RCU read section to finish before proceeding. New RCU + * read sections should be prevented via bpf_map_inc_not_zero. + */ + synchronize_rcu(); + + /* bpf prog and the userspace can no longer access this map + * now. No new selem (of this map) can be added + * to the owner->storage or to the map bucket's list. + * + * The elem of this map can be cleaned up here + * or when the storage is freed e.g. + * by bpf_sk_storage_free() during __sk_destruct(). + */ + for (i = 0; i < (1U << smap->bucket_log); i++) { + b = &smap->buckets[i]; + + rcu_read_lock(); + /* No one is adding to b->list now */ + while ((selem = hlist_entry_safe( + rcu_dereference_raw(hlist_first_rcu(&b->list)), + struct bpf_local_storage_elem, map_node))) { + bpf_selem_unlink(selem); + cond_resched_rcu(); + } + rcu_read_unlock(); + } + + /* While freeing the storage we may still need to access the map. + * + * e.g. when bpf_sk_storage_free() has unlinked selem from the map + * which then made the above while((selem = ...)) loop + * exit immediately. + * + * However, while freeing the storage one still needs to access the + * smap->elem_size to do the uncharging in + * bpf_selem_unlink_storage_nolock(). + * + * Hence, wait another rcu grace period for the storage to be freed. + */ + synchronize_rcu(); + + kvfree(smap->buckets); + kfree(smap); +} + +int bpf_local_storage_map_alloc_check(union bpf_attr *attr) +{ + if (attr->map_flags & ~BPF_LOCAL_STORAGE_CREATE_FLAG_MASK || + !(attr->map_flags & BPF_F_NO_PREALLOC) || + attr->max_entries || + attr->key_size != sizeof(int) || !attr->value_size || + /* Enforce BTF for userspace sk dumping */ + !attr->btf_key_type_id || !attr->btf_value_type_id) + return -EINVAL; + + if (!bpf_capable()) + return -EPERM; + + if (attr->value_size > BPF_LOCAL_STORAGE_MAX_VALUE_SIZE) + return -E2BIG; + + return 0; +} + +struct bpf_local_storage_map *bpf_local_storage_map_alloc(union bpf_attr *attr) +{ + struct bpf_local_storage_map *smap; + unsigned int i; + u32 nbuckets; + u64 cost; + int ret; + + smap = kzalloc(sizeof(*smap), GFP_USER | __GFP_NOWARN); + if (!smap) + return ERR_PTR(-ENOMEM); + bpf_map_init_from_attr(&smap->map, attr); + + nbuckets = roundup_pow_of_two(num_possible_cpus()); + /* Use at least 2 buckets, select_bucket() is undefined behavior with 1 bucket */ + nbuckets = max_t(u32, 2, nbuckets); + smap->bucket_log = ilog2(nbuckets); + cost = sizeof(*smap->buckets) * nbuckets + sizeof(*smap); + + ret = bpf_map_charge_init(&smap->map.memory, cost); + if (ret < 0) { + kfree(smap); + return ERR_PTR(ret); + } + + smap->buckets = kvcalloc(sizeof(*smap->buckets), nbuckets, + GFP_USER | __GFP_NOWARN); + if (!smap->buckets) { + bpf_map_charge_finish(&smap->map.memory); + kfree(smap); + return ERR_PTR(-ENOMEM); + } + + for (i = 0; i < nbuckets; i++) { + INIT_HLIST_HEAD(&smap->buckets[i].list); + raw_spin_lock_init(&smap->buckets[i].lock); + } + + smap->elem_size = + sizeof(struct bpf_local_storage_elem) + attr->value_size; + + return smap; +} + +int bpf_local_storage_map_check_btf(const struct bpf_map *map, + const struct btf *btf, + const struct btf_type *key_type, + const struct btf_type *value_type) +{ + u32 int_data; + + if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT) + return -EINVAL; + + int_data = *(u32 *)(key_type + 1); + if (BTF_INT_BITS(int_data) != 32 || BTF_INT_OFFSET(int_data)) + return -EINVAL; + + return 0; +} diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index cd8b7017913b..f29d9a9b4ea4 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -7,97 +7,14 @@ #include #include #include +#include #include #include #include #include -#define BPF_LOCAL_STORAGE_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_CLONE) - DEFINE_BPF_STORAGE_CACHE(sk_cache); -struct bpf_local_storage_map_bucket { - struct hlist_head list; - raw_spinlock_t lock; -}; - -/* Thp map is not the primary owner of a bpf_local_storage_elem. - * Instead, the container object (eg. sk->sk_bpf_storage) is. - * - * The map (bpf_local_storage_map) is for two purposes - * 1. Define the size of the "local storage". It is - * the map's value_size. - * - * 2. Maintain a list to keep track of all elems such - * that they can be cleaned up during the map destruction. - * - * When a bpf local storage is being looked up for a - * particular object, the "bpf_map" pointer is actually used - * as the "key" to search in the list of elem in - * the respective bpf_local_storage owned by the object. - * - * e.g. sk->sk_bpf_storage is the mini-map with the "bpf_map" pointer - * as the searching key. - */ -struct bpf_local_storage_map { - struct bpf_map map; - /* Lookup elem does not require accessing the map. - * - * Updating/Deleting requires a bucket lock to - * link/unlink the elem from the map. Having - * multiple buckets to improve contention. - */ - struct bpf_local_storage_map_bucket *buckets; - u32 bucket_log; - u16 elem_size; - u16 cache_idx; -}; - -struct bpf_local_storage_data { - /* smap is used as the searching key when looking up - * from the object's bpf_local_storage. - * - * Put it in the same cacheline as the data to minimize - * the number of cachelines access during the cache hit case. - */ - struct bpf_local_storage_map __rcu *smap; - u8 data[] __aligned(8); -}; - -/* Linked to bpf_local_storage and bpf_local_storage_map */ -struct bpf_local_storage_elem { - struct hlist_node map_node; /* Linked to bpf_local_storage_map */ - struct hlist_node snode; /* Linked to bpf_local_storage */ - struct bpf_local_storage __rcu *local_storage; - struct rcu_head rcu; - /* 8 bytes hole */ - /* The data is stored in aother cacheline to minimize - * the number of cachelines access during a cache hit. - */ - struct bpf_local_storage_data sdata ____cacheline_aligned; -}; - -#define SELEM(_SDATA) \ - container_of((_SDATA), struct bpf_local_storage_elem, sdata) -#define SDATA(_SELEM) (&(_SELEM)->sdata) - -struct bpf_local_storage { - struct bpf_local_storage_data __rcu *cache[BPF_LOCAL_STORAGE_CACHE_SIZE]; - struct hlist_head list; /* List of bpf_local_storage_elem */ - void *owner; /* The object that owns the above "list" of - * bpf_local_storage_elem. - */ - struct rcu_head rcu; - raw_spinlock_t lock; /* Protect adding/removing from the "list" */ -}; - -static struct bpf_local_storage_map_bucket * -select_bucket(struct bpf_local_storage_map *smap, - struct bpf_local_storage_elem *selem) -{ - return &smap->buckets[hash_ptr(selem, smap->bucket_log)]; -} - static int omem_charge(struct sock *sk, unsigned int size) { /* same check as in sock_kmalloc() */ @@ -110,223 +27,6 @@ static int omem_charge(struct sock *sk, unsigned int size) return -ENOMEM; } -static int mem_charge(struct bpf_local_storage_map *smap, void *owner, u32 size) -{ - struct bpf_map *map = &smap->map; - - if (!map->ops->map_local_storage_charge) - return 0; - - return map->ops->map_local_storage_charge(smap, owner, size); -} - -static void mem_uncharge(struct bpf_local_storage_map *smap, void *owner, - u32 size) -{ - struct bpf_map *map = &smap->map; - - if (map->ops->map_local_storage_uncharge) - map->ops->map_local_storage_uncharge(smap, owner, size); -} - -static struct bpf_local_storage __rcu ** -owner_storage(struct bpf_local_storage_map *smap, void *owner) -{ - struct bpf_map *map = &smap->map; - - return map->ops->map_owner_storage_ptr(owner); -} - -static bool selem_linked_to_storage(const struct bpf_local_storage_elem *selem) -{ - return !hlist_unhashed(&selem->snode); -} - -static bool selem_linked_to_map(const struct bpf_local_storage_elem *selem) -{ - return !hlist_unhashed(&selem->map_node); -} - -struct bpf_local_storage_elem * -bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, - void *value, bool charge_mem) -{ - struct bpf_local_storage_elem *selem; - - if (charge_mem && mem_charge(smap, owner, smap->elem_size)) - return NULL; - - selem = kzalloc(smap->elem_size, GFP_ATOMIC | __GFP_NOWARN); - if (selem) { - if (value) - memcpy(SDATA(selem)->data, value, smap->map.value_size); - return selem; - } - - if (charge_mem) - mem_uncharge(smap, owner, smap->elem_size); - - return NULL; -} - -/* local_storage->lock must be held and selem->local_storage == local_storage. - * The caller must ensure selem->smap is still valid to be - * dereferenced for its smap->elem_size and smap->cache_idx. - */ -bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, - struct bpf_local_storage_elem *selem, - bool uncharge_mem) -{ - struct bpf_local_storage_map *smap; - bool free_local_storage; - void *owner; - - smap = rcu_dereference(SDATA(selem)->smap); - owner = local_storage->owner; - - /* All uncharging on the owner must be done first. - * The owner may be freed once the last selem is unlinked - * from local_storage. - */ - if (uncharge_mem) - mem_uncharge(smap, owner, smap->elem_size); - - free_local_storage = hlist_is_singular_node(&selem->snode, - &local_storage->list); - if (free_local_storage) { - mem_uncharge(smap, owner, sizeof(struct bpf_local_storage)); - local_storage->owner = NULL; - - /* After this RCU_INIT, owner may be freed and cannot be used */ - RCU_INIT_POINTER(*owner_storage(smap, owner), NULL); - - /* local_storage is not freed now. local_storage->lock is - * still held and raw_spin_unlock_bh(&local_storage->lock) - * will be done by the caller. - * - * Although the unlock will be done under - * rcu_read_lock(), it is more intutivie to - * read if kfree_rcu(local_storage, rcu) is done - * after the raw_spin_unlock_bh(&local_storage->lock). - * - * Hence, a "bool free_local_storage" is returned - * to the caller which then calls the kfree_rcu() - * after unlock. - */ - } - hlist_del_init_rcu(&selem->snode); - if (rcu_access_pointer(local_storage->cache[smap->cache_idx]) == - SDATA(selem)) - RCU_INIT_POINTER(local_storage->cache[smap->cache_idx], NULL); - - kfree_rcu(selem, rcu); - - return free_local_storage; -} - -static void __bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem) -{ - struct bpf_local_storage *local_storage; - bool free_local_storage = false; - - if (unlikely(!selem_linked_to_storage(selem))) - /* selem has already been unlinked from sk */ - return; - - local_storage = rcu_dereference(selem->local_storage); - raw_spin_lock_bh(&local_storage->lock); - if (likely(selem_linked_to_storage(selem))) - free_local_storage = bpf_selem_unlink_storage_nolock( - local_storage, selem, true); - raw_spin_unlock_bh(&local_storage->lock); - - if (free_local_storage) - kfree_rcu(local_storage, rcu); -} - -void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage, - struct bpf_local_storage_elem *selem) -{ - RCU_INIT_POINTER(selem->local_storage, local_storage); - hlist_add_head(&selem->snode, &local_storage->list); -} - -void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem) -{ - struct bpf_local_storage_map *smap; - struct bpf_local_storage_map_bucket *b; - - if (unlikely(!selem_linked_to_map(selem))) - /* selem has already be unlinked from smap */ - return; - - smap = rcu_dereference(SDATA(selem)->smap); - b = select_bucket(smap, selem); - raw_spin_lock_bh(&b->lock); - if (likely(selem_linked_to_map(selem))) - hlist_del_init_rcu(&selem->map_node); - raw_spin_unlock_bh(&b->lock); -} - -void bpf_selem_link_map(struct bpf_local_storage_map *smap, - struct bpf_local_storage_elem *selem) -{ - struct bpf_local_storage_map_bucket *b = select_bucket(smap, selem); - - raw_spin_lock_bh(&b->lock); - RCU_INIT_POINTER(SDATA(selem)->smap, smap); - hlist_add_head_rcu(&selem->map_node, &b->list); - raw_spin_unlock_bh(&b->lock); -} - -void bpf_selem_unlink(struct bpf_local_storage_elem *selem) -{ - /* Always unlink from map before unlinking from local_storage - * because selem will be freed after successfully unlinked from - * the local_storage. - */ - bpf_selem_unlink_map(selem); - __bpf_selem_unlink_storage(selem); -} - -struct bpf_local_storage_data * -bpf_local_storage_lookup(struct bpf_local_storage *local_storage, - struct bpf_local_storage_map *smap, - bool cacheit_lockit) -{ - struct bpf_local_storage_data *sdata; - struct bpf_local_storage_elem *selem; - - /* Fast path (cache hit) */ - sdata = rcu_dereference(local_storage->cache[smap->cache_idx]); - if (sdata && rcu_access_pointer(sdata->smap) == smap) - return sdata; - - /* Slow path (cache miss) */ - hlist_for_each_entry_rcu(selem, &local_storage->list, snode) - if (rcu_access_pointer(SDATA(selem)->smap) == smap) - break; - - if (!selem) - return NULL; - - sdata = SDATA(selem); - if (cacheit_lockit) { - /* spinlock is needed to avoid racing with the - * parallel delete. Otherwise, publishing an already - * deleted sdata to the cache will become a use-after-free - * problem in the next bpf_local_storage_lookup(). - */ - raw_spin_lock_bh(&local_storage->lock); - if (selem_linked_to_storage(selem)) - rcu_assign_pointer(local_storage->cache[smap->cache_idx], - sdata); - raw_spin_unlock_bh(&local_storage->lock); - } - - return sdata; -} - static struct bpf_local_storage_data * sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit) { @@ -341,202 +41,6 @@ sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit) return bpf_local_storage_lookup(sk_storage, smap, cacheit_lockit); } -static int check_flags(const struct bpf_local_storage_data *old_sdata, - u64 map_flags) -{ - if (old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_NOEXIST) - /* elem already exists */ - return -EEXIST; - - if (!old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_EXIST) - /* elem doesn't exist, cannot update it */ - return -ENOENT; - - return 0; -} - -int bpf_local_storage_alloc(void *owner, - struct bpf_local_storage_map *smap, - struct bpf_local_storage_elem *first_selem) -{ - struct bpf_local_storage *prev_storage, *storage; - struct bpf_local_storage **owner_storage_ptr; - int err; - - err = mem_charge(smap, owner, sizeof(*storage)); - if (err) - return err; - - storage = kzalloc(sizeof(*storage), GFP_ATOMIC | __GFP_NOWARN); - if (!storage) { - err = -ENOMEM; - goto uncharge; - } - - INIT_HLIST_HEAD(&storage->list); - raw_spin_lock_init(&storage->lock); - storage->owner = owner; - - bpf_selem_link_storage_nolock(storage, first_selem); - bpf_selem_link_map(smap, first_selem); - - owner_storage_ptr = - (struct bpf_local_storage **)owner_storage(smap, owner); - /* Publish storage to the owner. - * Instead of using any lock of the kernel object (i.e. owner), - * cmpxchg will work with any kernel object regardless what - * the running context is, bh, irq...etc. - * - * From now on, the owner->storage pointer (e.g. sk->sk_bpf_storage) - * is protected by the storage->lock. Hence, when freeing - * the owner->storage, the storage->lock must be held before - * setting owner->storage ptr to NULL. - */ - prev_storage = cmpxchg(owner_storage_ptr, NULL, storage); - if (unlikely(prev_storage)) { - bpf_selem_unlink_map(first_selem); - err = -EAGAIN; - goto uncharge; - - /* Note that even first_selem was linked to smap's - * bucket->list, first_selem can be freed immediately - * (instead of kfree_rcu) because - * bpf_local_storage_map_free() does a - * synchronize_rcu() before walking the bucket->list. - * Hence, no one is accessing selem from the - * bucket->list under rcu_read_lock(). - */ - } - - return 0; - -uncharge: - kfree(storage); - mem_uncharge(smap, owner, sizeof(*storage)); - return err; -} - -/* sk cannot be going away because it is linking new elem - * to sk->sk_bpf_storage. (i.e. sk->sk_refcnt cannot be 0). - * Otherwise, it will become a leak (and other memory issues - * during map destruction). - */ -struct bpf_local_storage_data * -bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, - void *value, u64 map_flags) -{ - struct bpf_local_storage_data *old_sdata = NULL; - struct bpf_local_storage_elem *selem; - struct bpf_local_storage *local_storage; - int err; - - /* BPF_EXIST and BPF_NOEXIST cannot be both set */ - if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST) || - /* BPF_F_LOCK can only be used in a value with spin_lock */ - unlikely((map_flags & BPF_F_LOCK) && - !map_value_has_spin_lock(&smap->map))) - return ERR_PTR(-EINVAL); - - local_storage = rcu_dereference(*owner_storage(smap, owner)); - if (!local_storage || hlist_empty(&local_storage->list)) { - /* Very first elem for the owner */ - err = check_flags(NULL, map_flags); - if (err) - return ERR_PTR(err); - - selem = bpf_selem_alloc(smap, owner, value, true); - if (!selem) - return ERR_PTR(-ENOMEM); - - err = bpf_local_storage_alloc(owner, smap, selem); - if (err) { - kfree(selem); - mem_uncharge(smap, owner, smap->elem_size); - return ERR_PTR(err); - } - - return SDATA(selem); - } - - if ((map_flags & BPF_F_LOCK) && !(map_flags & BPF_NOEXIST)) { - /* Hoping to find an old_sdata to do inline update - * such that it can avoid taking the local_storage->lock - * and changing the lists. - */ - old_sdata = - bpf_local_storage_lookup(local_storage, smap, false); - err = check_flags(old_sdata, map_flags); - if (err) - return ERR_PTR(err); - if (old_sdata && selem_linked_to_storage(SELEM(old_sdata))) { - copy_map_value_locked(&smap->map, old_sdata->data, - value, false); - return old_sdata; - } - } - - raw_spin_lock_bh(&local_storage->lock); - - /* Recheck local_storage->list under local_storage->lock */ - if (unlikely(hlist_empty(&local_storage->list))) { - /* A parallel del is happening and local_storage is going - * away. It has just been checked before, so very - * unlikely. Return instead of retry to keep things - * simple. - */ - err = -EAGAIN; - goto unlock_err; - } - - old_sdata = bpf_local_storage_lookup(local_storage, smap, false); - err = check_flags(old_sdata, map_flags); - if (err) - goto unlock_err; - - if (old_sdata && (map_flags & BPF_F_LOCK)) { - copy_map_value_locked(&smap->map, old_sdata->data, value, - false); - selem = SELEM(old_sdata); - goto unlock; - } - - /* local_storage->lock is held. Hence, we are sure - * we can unlink and uncharge the old_sdata successfully - * later. Hence, instead of charging the new selem now - * and then uncharge the old selem later (which may cause - * a potential but unnecessary charge failure), avoid taking - * a charge at all here (the "!old_sdata" check) and the - * old_sdata will not be uncharged later during - * bpf_selem_unlink_storage_nolock(). - */ - selem = bpf_selem_alloc(smap, owner, value, !old_sdata); - if (!selem) { - err = -ENOMEM; - goto unlock_err; - } - - /* First, link the new selem to the map */ - bpf_selem_link_map(smap, selem); - - /* Second, link (and publish) the new selem to local_storage */ - bpf_selem_link_storage_nolock(local_storage, selem); - - /* Third, remove old selem, SELEM(old_sdata) */ - if (old_sdata) { - bpf_selem_unlink_map(SELEM(old_sdata)); - bpf_selem_unlink_storage_nolock(local_storage, SELEM(old_sdata), - false); - } - -unlock: - raw_spin_unlock_bh(&local_storage->lock); - return SDATA(selem); - -unlock_err: - raw_spin_unlock_bh(&local_storage->lock); - return ERR_PTR(err); -} - static int sk_storage_delete(struct sock *sk, struct bpf_map *map) { struct bpf_local_storage_data *sdata; @@ -550,38 +54,6 @@ static int sk_storage_delete(struct sock *sk, struct bpf_map *map) return 0; } -u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache) -{ - u64 min_usage = U64_MAX; - u16 i, res = 0; - - spin_lock(&cache->idx_lock); - - for (i = 0; i < BPF_LOCAL_STORAGE_CACHE_SIZE; i++) { - if (cache->idx_usage_counts[i] < min_usage) { - min_usage = cache->idx_usage_counts[i]; - res = i; - - /* Found a free cache_idx */ - if (!min_usage) - break; - } - } - cache->idx_usage_counts[res]++; - - spin_unlock(&cache->idx_lock); - - return res; -} - -void bpf_local_storage_cache_idx_free(struct bpf_local_storage_cache *cache, - u16 idx) -{ - spin_lock(&cache->idx_lock); - cache->idx_usage_counts[idx]--; - spin_unlock(&cache->idx_lock); -} - /* Called by __sk_destruct() & bpf_sk_storage_clone() */ void bpf_sk_storage_free(struct sock *sk) { @@ -622,59 +94,6 @@ void bpf_sk_storage_free(struct sock *sk) kfree_rcu(sk_storage, rcu); } -void bpf_local_storage_map_free(struct bpf_local_storage_map *smap) -{ - struct bpf_local_storage_elem *selem; - struct bpf_local_storage_map_bucket *b; - unsigned int i; - - /* Note that this map might be concurrently cloned from - * bpf_sk_storage_clone. Wait for any existing bpf_sk_storage_clone - * RCU read section to finish before proceeding. New RCU - * read sections should be prevented via bpf_map_inc_not_zero. - */ - synchronize_rcu(); - - /* bpf prog and the userspace can no longer access this map - * now. No new selem (of this map) can be added - * to the owner->storage or to the map bucket's list. - * - * The elem of this map can be cleaned up here - * or when the storage is freed e.g. - * by bpf_sk_storage_free() during __sk_destruct(). - */ - for (i = 0; i < (1U << smap->bucket_log); i++) { - b = &smap->buckets[i]; - - rcu_read_lock(); - /* No one is adding to b->list now */ - while ((selem = hlist_entry_safe( - rcu_dereference_raw(hlist_first_rcu(&b->list)), - struct bpf_local_storage_elem, map_node))) { - bpf_selem_unlink(selem); - cond_resched_rcu(); - } - rcu_read_unlock(); - } - - /* While freeing the storage we may still need to access the map. - * - * e.g. when bpf_sk_storage_free() has unlinked selem from the map - * which then made the above while((selem = ...)) loop - * exit immediately. - * - * However, while freeing the storage one still needs to access the - * smap->elem_size to do the uncharging in - * bpf_selem_unlink_storage_nolock(). - * - * Hence, wait another rcu grace period for the storage to be freed. - */ - synchronize_rcu(); - - kvfree(smap->buckets); - kfree(smap); -} - static void sk_storage_map_free(struct bpf_map *map) { struct bpf_local_storage_map *smap; @@ -684,78 +103,6 @@ static void sk_storage_map_free(struct bpf_map *map) bpf_local_storage_map_free(smap); } -/* U16_MAX is much more than enough for sk local storage - * considering a tcp_sock is ~2k. - */ -#define BPF_LOCAL_STORAGE_MAX_VALUE_SIZE \ - min_t(u32, \ - (KMALLOC_MAX_SIZE - MAX_BPF_STACK - \ - sizeof(struct bpf_local_storage_elem)), \ - (U16_MAX - sizeof(struct bpf_local_storage_elem))) - -int bpf_local_storage_map_alloc_check(union bpf_attr *attr) -{ - if (attr->map_flags & ~BPF_LOCAL_STORAGE_CREATE_FLAG_MASK || - !(attr->map_flags & BPF_F_NO_PREALLOC) || - attr->max_entries || - attr->key_size != sizeof(int) || !attr->value_size || - /* Enforce BTF for userspace sk dumping */ - !attr->btf_key_type_id || !attr->btf_value_type_id) - return -EINVAL; - - if (!bpf_capable()) - return -EPERM; - - if (attr->value_size > BPF_LOCAL_STORAGE_MAX_VALUE_SIZE) - return -E2BIG; - - return 0; -} - -struct bpf_local_storage_map *bpf_local_storage_map_alloc(union bpf_attr *attr) -{ - struct bpf_local_storage_map *smap; - unsigned int i; - u32 nbuckets; - u64 cost; - int ret; - - smap = kzalloc(sizeof(*smap), GFP_USER | __GFP_NOWARN); - if (!smap) - return ERR_PTR(-ENOMEM); - bpf_map_init_from_attr(&smap->map, attr); - - nbuckets = roundup_pow_of_two(num_possible_cpus()); - /* Use at least 2 buckets, select_bucket() is undefined behavior with 1 bucket */ - nbuckets = max_t(u32, 2, nbuckets); - smap->bucket_log = ilog2(nbuckets); - cost = sizeof(*smap->buckets) * nbuckets + sizeof(*smap); - - ret = bpf_map_charge_init(&smap->map.memory, cost); - if (ret < 0) { - kfree(smap); - return ERR_PTR(ret); - } - - smap->buckets = kvcalloc(sizeof(*smap->buckets), nbuckets, - GFP_USER | __GFP_NOWARN); - if (!smap->buckets) { - bpf_map_charge_finish(&smap->map.memory); - kfree(smap); - return ERR_PTR(-ENOMEM); - } - - for (i = 0; i < nbuckets; i++) { - INIT_HLIST_HEAD(&smap->buckets[i].list); - raw_spin_lock_init(&smap->buckets[i].lock); - } - - smap->elem_size = - sizeof(struct bpf_local_storage_elem) + attr->value_size; - - return smap; -} - static struct bpf_map *sk_storage_map_alloc(union bpf_attr *attr) { struct bpf_local_storage_map *smap; @@ -774,23 +121,6 @@ static int notsupp_get_next_key(struct bpf_map *map, void *key, return -ENOTSUPP; } -int bpf_local_storage_map_check_btf(const struct bpf_map *map, - const struct btf *btf, - const struct btf_type *key_type, - const struct btf_type *value_type) -{ - u32 int_data; - - if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT) - return -EINVAL; - - int_data = *(u32 *)(key_type + 1); - if (BTF_INT_BITS(int_data) != 32 || BTF_INT_OFFSET(int_data)) - return -EINVAL; - - return 0; -} - static void *bpf_fd_sk_storage_lookup_elem(struct bpf_map *map, void *key) { struct bpf_local_storage_data *sdata; -- cgit v1.2.3 From 30897832d8b97e93833fb52c0a02951db3692ed2 Mon Sep 17 00:00:00 2001 From: KP Singh Date: Tue, 25 Aug 2020 20:29:18 +0200 Subject: bpf: Allow local storage to be used from LSM programs Adds support for both bpf_{sk, inode}_storage_{get, delete} to be used in LSM programs. These helpers are not used for tracing programs (currently) as their usage is tied to the life-cycle of the object and should only be used where the owning object won't be freed (when the owning object is passed as an argument to the LSM hook). Thus, they are safer to use in LSM hooks than tracing. Usage of local storage in tracing programs will probably follow a per function based whitelist approach. Since the UAPI helper signature for bpf_sk_storage expect a bpf_sock, it, leads to a compilation warning for LSM programs, it's also updated to accept a void * pointer instead. Signed-off-by: KP Singh Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20200825182919.1118197-7-kpsingh@chromium.org --- include/net/bpf_sk_storage.h | 2 ++ include/uapi/linux/bpf.h | 7 +++++-- kernel/bpf/bpf_lsm.c | 21 ++++++++++++++++++++- net/core/bpf_sk_storage.c | 25 +++++++++++++++++++++++++ tools/include/uapi/linux/bpf.h | 7 +++++-- 5 files changed, 57 insertions(+), 5 deletions(-) (limited to 'include/net') diff --git a/include/net/bpf_sk_storage.h b/include/net/bpf_sk_storage.h index 3c516dd07caf..119f4c9c3a9c 100644 --- a/include/net/bpf_sk_storage.h +++ b/include/net/bpf_sk_storage.h @@ -20,6 +20,8 @@ void bpf_sk_storage_free(struct sock *sk); extern const struct bpf_func_proto bpf_sk_storage_get_proto; extern const struct bpf_func_proto bpf_sk_storage_delete_proto; +extern const struct bpf_func_proto sk_storage_get_btf_proto; +extern const struct bpf_func_proto sk_storage_delete_btf_proto; struct bpf_local_storage_elem; struct bpf_sk_storage_diag; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index b6bfcd085a76..0e1cdf806fe1 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2808,7 +2808,7 @@ union bpf_attr { * * **-ERANGE** if resulting value was out of range. * - * void *bpf_sk_storage_get(struct bpf_map *map, struct bpf_sock *sk, void *value, u64 flags) + * void *bpf_sk_storage_get(struct bpf_map *map, void *sk, void *value, u64 flags) * Description * Get a bpf-local-storage from a *sk*. * @@ -2824,6 +2824,9 @@ union bpf_attr { * "type". The bpf-local-storage "type" (i.e. the *map*) is * searched against all bpf-local-storages residing at *sk*. * + * *sk* is a kernel **struct sock** pointer for LSM program. + * *sk* is a **struct bpf_sock** pointer for other program types. + * * An optional *flags* (**BPF_SK_STORAGE_GET_F_CREATE**) can be * used such that a new bpf-local-storage will be * created if one does not exist. *value* can be used @@ -2836,7 +2839,7 @@ union bpf_attr { * **NULL** if not found or there was an error in adding * a new bpf-local-storage. * - * long bpf_sk_storage_delete(struct bpf_map *map, struct bpf_sock *sk) + * long bpf_sk_storage_delete(struct bpf_map *map, void *sk) * Description * Delete a bpf-local-storage from a *sk*. * Return diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index fb278144e9fd..9cd1428c7199 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -11,6 +11,8 @@ #include #include #include +#include +#include /* For every LSM hook that allows attachment of BPF programs, declare a nop * function where a BPF program can be attached. @@ -45,10 +47,27 @@ int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog, return 0; } +static const struct bpf_func_proto * +bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + switch (func_id) { + case BPF_FUNC_inode_storage_get: + return &bpf_inode_storage_get_proto; + case BPF_FUNC_inode_storage_delete: + return &bpf_inode_storage_delete_proto; + case BPF_FUNC_sk_storage_get: + return &sk_storage_get_btf_proto; + case BPF_FUNC_sk_storage_delete: + return &sk_storage_delete_btf_proto; + default: + return tracing_prog_func_proto(func_id, prog); + } +} + const struct bpf_prog_ops lsm_prog_ops = { }; const struct bpf_verifier_ops lsm_verifier_ops = { - .get_func_proto = tracing_prog_func_proto, + .get_func_proto = bpf_lsm_func_proto, .is_valid_access = btf_ctx_access, }; diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index f29d9a9b4ea4..55fae03b4cc3 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -12,6 +12,7 @@ #include #include #include +#include DEFINE_BPF_STORAGE_CACHE(sk_cache); @@ -377,6 +378,30 @@ const struct bpf_func_proto bpf_sk_storage_delete_proto = { .arg2_type = ARG_PTR_TO_SOCKET, }; +BTF_ID_LIST(sk_storage_btf_ids) +BTF_ID_UNUSED +BTF_ID(struct, sock) + +const struct bpf_func_proto sk_storage_get_btf_proto = { + .func = bpf_sk_storage_get, + .gpl_only = false, + .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_BTF_ID, + .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, + .arg4_type = ARG_ANYTHING, + .btf_id = sk_storage_btf_ids, +}; + +const struct bpf_func_proto sk_storage_delete_btf_proto = { + .func = bpf_sk_storage_delete, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_BTF_ID, + .btf_id = sk_storage_btf_ids, +}; + struct bpf_sk_storage_diag { u32 nr_maps; struct bpf_map *maps[]; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index b6bfcd085a76..0e1cdf806fe1 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -2808,7 +2808,7 @@ union bpf_attr { * * **-ERANGE** if resulting value was out of range. * - * void *bpf_sk_storage_get(struct bpf_map *map, struct bpf_sock *sk, void *value, u64 flags) + * void *bpf_sk_storage_get(struct bpf_map *map, void *sk, void *value, u64 flags) * Description * Get a bpf-local-storage from a *sk*. * @@ -2824,6 +2824,9 @@ union bpf_attr { * "type". The bpf-local-storage "type" (i.e. the *map*) is * searched against all bpf-local-storages residing at *sk*. * + * *sk* is a kernel **struct sock** pointer for LSM program. + * *sk* is a **struct bpf_sock** pointer for other program types. + * * An optional *flags* (**BPF_SK_STORAGE_GET_F_CREATE**) can be * used such that a new bpf-local-storage will be * created if one does not exist. *value* can be used @@ -2836,7 +2839,7 @@ union bpf_attr { * **NULL** if not found or there was an error in adding * a new bpf-local-storage. * - * long bpf_sk_storage_delete(struct bpf_map *map, struct bpf_sock *sk) + * long bpf_sk_storage_delete(struct bpf_map *map, void *sk) * Description * Delete a bpf-local-storage from a *sk*. * Return -- cgit v1.2.3 From 1742b3d528690ae7773cf7bf2f01a90ee1de2fe0 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Fri, 28 Aug 2020 10:26:15 +0200 Subject: xsk: i40e: ice: ixgbe: mlx5: Pass buffer pool to driver instead of umem MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Replace the explicit umem reference passed to the driver in AF_XDP zero-copy mode with the buffer pool instead. This in preparation for extending the functionality of the zero-copy mode so that umems can be shared between queues on the same netdev and also between netdevs. In this commit, only an umem reference has been added to the buffer pool struct. But later commits will add other entities to it. These are going to be entities that are different between different queue ids and netdevs even though the umem is shared between them. Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Acked-by: Björn Töpel Link: https://lore.kernel.org/bpf/1598603189-32145-2-git-send-email-magnus.karlsson@intel.com --- drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 2 +- drivers/net/ethernet/intel/i40e/i40e_main.c | 29 +-- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 10 +- drivers/net/ethernet/intel/i40e/i40e_txrx.h | 2 +- drivers/net/ethernet/intel/i40e/i40e_xsk.c | 81 ++++---- drivers/net/ethernet/intel/i40e/i40e_xsk.h | 4 +- drivers/net/ethernet/intel/ice/ice.h | 18 +- drivers/net/ethernet/intel/ice/ice_base.c | 16 +- drivers/net/ethernet/intel/ice/ice_lib.c | 2 +- drivers/net/ethernet/intel/ice/ice_main.c | 10 +- drivers/net/ethernet/intel/ice/ice_txrx.c | 8 +- drivers/net/ethernet/intel/ice/ice_txrx.h | 2 +- drivers/net/ethernet/intel/ice/ice_xsk.c | 136 ++++++------- drivers/net/ethernet/intel/ice/ice_xsk.h | 7 +- drivers/net/ethernet/intel/ixgbe/ixgbe.h | 2 +- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 34 ++-- .../net/ethernet/intel/ixgbe/ixgbe_txrx_common.h | 7 +- drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c | 61 +++--- drivers/net/ethernet/mellanox/mlx5/core/Makefile | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en.h | 19 +- drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c | 5 +- .../net/ethernet/mellanox/mlx5/core/en/xsk/pool.c | 217 +++++++++++++++++++++ .../net/ethernet/mellanox/mlx5/core/en/xsk/pool.h | 27 +++ .../net/ethernet/mellanox/mlx5/core/en/xsk/rx.h | 10 +- .../net/ethernet/mellanox/mlx5/core/en/xsk/setup.c | 12 +- .../net/ethernet/mellanox/mlx5/core/en/xsk/setup.h | 2 +- .../net/ethernet/mellanox/mlx5/core/en/xsk/tx.c | 14 +- .../net/ethernet/mellanox/mlx5/core/en/xsk/tx.h | 6 +- .../net/ethernet/mellanox/mlx5/core/en/xsk/umem.c | 217 --------------------- .../net/ethernet/mellanox/mlx5/core/en/xsk/umem.h | 29 --- .../net/ethernet/mellanox/mlx5/core/en_ethtool.c | 2 +- .../ethernet/mellanox/mlx5/core/en_fs_ethtool.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 49 ++--- drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 16 +- include/linux/netdevice.h | 10 +- include/net/xdp_sock_drv.h | 7 +- include/net/xsk_buff_pool.h | 4 +- net/ethtool/channels.c | 2 +- net/ethtool/ioctl.c | 2 +- net/xdp/xdp_umem.c | 45 ++--- net/xdp/xsk_buff_pool.c | 5 +- 41 files changed, 575 insertions(+), 560 deletions(-) create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.h delete mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.c delete mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.h (limited to 'include/net') diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 825c104ecba1..dc1577156bb6 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -1967,7 +1967,7 @@ static int i40e_set_ringparam(struct net_device *netdev, (new_rx_count == vsi->rx_rings[0]->count)) return 0; - /* If there is a AF_XDP UMEM attached to any of Rx rings, + /* If there is a AF_XDP page pool attached to any of Rx rings, * disallow changing the number of descriptors -- regardless * if the netdev is running or not. */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 2e433fdbf2c3..cbf2a4454499 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -3122,12 +3122,12 @@ static void i40e_config_xps_tx_ring(struct i40e_ring *ring) } /** - * i40e_xsk_umem - Retrieve the AF_XDP ZC if XDP and ZC is enabled + * i40e_xsk_pool - Retrieve the AF_XDP buffer pool if XDP and ZC is enabled * @ring: The Tx or Rx ring * - * Returns the UMEM or NULL. + * Returns the AF_XDP buffer pool or NULL. **/ -static struct xdp_umem *i40e_xsk_umem(struct i40e_ring *ring) +static struct xsk_buff_pool *i40e_xsk_pool(struct i40e_ring *ring) { bool xdp_on = i40e_enabled_xdp_vsi(ring->vsi); int qid = ring->queue_index; @@ -3138,7 +3138,7 @@ static struct xdp_umem *i40e_xsk_umem(struct i40e_ring *ring) if (!xdp_on || !test_bit(qid, ring->vsi->af_xdp_zc_qps)) return NULL; - return xdp_get_umem_from_qid(ring->vsi->netdev, qid); + return xdp_get_xsk_pool_from_qid(ring->vsi->netdev, qid); } /** @@ -3157,7 +3157,7 @@ static int i40e_configure_tx_ring(struct i40e_ring *ring) u32 qtx_ctl = 0; if (ring_is_xdp(ring)) - ring->xsk_umem = i40e_xsk_umem(ring); + ring->xsk_pool = i40e_xsk_pool(ring); /* some ATR related tx ring init */ if (vsi->back->flags & I40E_FLAG_FD_ATR_ENABLED) { @@ -3280,12 +3280,13 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq); kfree(ring->rx_bi); - ring->xsk_umem = i40e_xsk_umem(ring); - if (ring->xsk_umem) { + ring->xsk_pool = i40e_xsk_pool(ring); + if (ring->xsk_pool) { ret = i40e_alloc_rx_bi_zc(ring); if (ret) return ret; - ring->rx_buf_len = xsk_umem_get_rx_frame_size(ring->xsk_umem); + ring->rx_buf_len = + xsk_umem_get_rx_frame_size(ring->xsk_pool->umem); /* For AF_XDP ZC, we disallow packets to span on * multiple buffers, thus letting us skip that * handling in the fast-path. @@ -3368,8 +3369,8 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) ring->tail = hw->hw_addr + I40E_QRX_TAIL(pf_q); writel(0, ring->tail); - if (ring->xsk_umem) { - xsk_buff_set_rxq_info(ring->xsk_umem, &ring->xdp_rxq); + if (ring->xsk_pool) { + xsk_buff_set_rxq_info(ring->xsk_pool->umem, &ring->xdp_rxq); ok = i40e_alloc_rx_buffers_zc(ring, I40E_DESC_UNUSED(ring)); } else { ok = !i40e_alloc_rx_buffers(ring, I40E_DESC_UNUSED(ring)); @@ -3380,7 +3381,7 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) */ dev_info(&vsi->back->pdev->dev, "Failed to allocate some buffers on %sRx ring %d (pf_q %d)\n", - ring->xsk_umem ? "UMEM enabled " : "", + ring->xsk_pool ? "AF_XDP ZC enabled " : "", ring->queue_index, pf_q); } @@ -12644,7 +12645,7 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi, */ if (need_reset && prog) for (i = 0; i < vsi->num_queue_pairs; i++) - if (vsi->xdp_rings[i]->xsk_umem) + if (vsi->xdp_rings[i]->xsk_pool) (void)i40e_xsk_wakeup(vsi->netdev, i, XDP_WAKEUP_RX); @@ -12923,8 +12924,8 @@ static int i40e_xdp(struct net_device *dev, switch (xdp->command) { case XDP_SETUP_PROG: return i40e_xdp_setup(vsi, xdp->prog); - case XDP_SETUP_XSK_UMEM: - return i40e_xsk_umem_setup(vsi, xdp->xsk.umem, + case XDP_SETUP_XSK_POOL: + return i40e_xsk_pool_setup(vsi, xdp->xsk.pool, xdp->xsk.queue_id); default: return -EINVAL; diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 3e5c566ceb01..f14bfc33844c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -636,7 +636,7 @@ void i40e_clean_tx_ring(struct i40e_ring *tx_ring) unsigned long bi_size; u16 i; - if (ring_is_xdp(tx_ring) && tx_ring->xsk_umem) { + if (ring_is_xdp(tx_ring) && tx_ring->xsk_pool) { i40e_xsk_clean_tx_ring(tx_ring); } else { /* ring already cleared, nothing to do */ @@ -1335,7 +1335,7 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring) rx_ring->skb = NULL; } - if (rx_ring->xsk_umem) { + if (rx_ring->xsk_pool) { i40e_xsk_clean_rx_ring(rx_ring); goto skip_free; } @@ -1369,7 +1369,7 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring) } skip_free: - if (rx_ring->xsk_umem) + if (rx_ring->xsk_pool) i40e_clear_rx_bi_zc(rx_ring); else i40e_clear_rx_bi(rx_ring); @@ -2579,7 +2579,7 @@ int i40e_napi_poll(struct napi_struct *napi, int budget) * budget and be more aggressive about cleaning up the Tx descriptors. */ i40e_for_each_ring(ring, q_vector->tx) { - bool wd = ring->xsk_umem ? + bool wd = ring->xsk_pool ? i40e_clean_xdp_tx_irq(vsi, ring) : i40e_clean_tx_irq(vsi, ring, budget); @@ -2607,7 +2607,7 @@ int i40e_napi_poll(struct napi_struct *napi, int budget) budget_per_ring = budget; i40e_for_each_ring(ring, q_vector->rx) { - int cleaned = ring->xsk_umem ? + int cleaned = ring->xsk_pool ? i40e_clean_rx_irq_zc(ring, budget_per_ring) : i40e_clean_rx_irq(ring, budget_per_ring); diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index 4036893d6825..703b644fd71f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -388,7 +388,7 @@ struct i40e_ring { struct i40e_channel *ch; struct xdp_rxq_info xdp_rxq; - struct xdp_umem *xsk_umem; + struct xsk_buff_pool *xsk_pool; } ____cacheline_internodealigned_in_smp; static inline bool ring_uses_build_skb(struct i40e_ring *ring) diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 8ce57b507a21..00e9fe6394f2 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -29,14 +29,16 @@ static struct xdp_buff **i40e_rx_bi(struct i40e_ring *rx_ring, u32 idx) } /** - * i40e_xsk_umem_enable - Enable/associate a UMEM to a certain ring/qid + * i40e_xsk_pool_enable - Enable/associate an AF_XDP buffer pool to a + * certain ring/qid * @vsi: Current VSI - * @umem: UMEM - * @qid: Rx ring to associate UMEM to + * @pool: buffer pool + * @qid: Rx ring to associate buffer pool with * * Returns 0 on success, <0 on failure **/ -static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem, +static int i40e_xsk_pool_enable(struct i40e_vsi *vsi, + struct xsk_buff_pool *pool, u16 qid) { struct net_device *netdev = vsi->netdev; @@ -53,7 +55,8 @@ static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem, qid >= netdev->real_num_tx_queues) return -EINVAL; - err = xsk_buff_dma_map(umem, &vsi->back->pdev->dev, I40E_RX_DMA_ATTR); + err = xsk_buff_dma_map(pool->umem, &vsi->back->pdev->dev, + I40E_RX_DMA_ATTR); if (err) return err; @@ -80,21 +83,22 @@ static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem, } /** - * i40e_xsk_umem_disable - Disassociate a UMEM from a certain ring/qid + * i40e_xsk_pool_disable - Disassociate an AF_XDP buffer pool from a + * certain ring/qid * @vsi: Current VSI - * @qid: Rx ring to associate UMEM to + * @qid: Rx ring to associate buffer pool with * * Returns 0 on success, <0 on failure **/ -static int i40e_xsk_umem_disable(struct i40e_vsi *vsi, u16 qid) +static int i40e_xsk_pool_disable(struct i40e_vsi *vsi, u16 qid) { struct net_device *netdev = vsi->netdev; - struct xdp_umem *umem; + struct xsk_buff_pool *pool; bool if_running; int err; - umem = xdp_get_umem_from_qid(netdev, qid); - if (!umem) + pool = xdp_get_xsk_pool_from_qid(netdev, qid); + if (!pool) return -EINVAL; if_running = netif_running(vsi->netdev) && i40e_enabled_xdp_vsi(vsi); @@ -106,7 +110,7 @@ static int i40e_xsk_umem_disable(struct i40e_vsi *vsi, u16 qid) } clear_bit(qid, vsi->af_xdp_zc_qps); - xsk_buff_dma_unmap(umem, I40E_RX_DMA_ATTR); + xsk_buff_dma_unmap(pool->umem, I40E_RX_DMA_ATTR); if (if_running) { err = i40e_queue_pair_enable(vsi, qid); @@ -118,20 +122,21 @@ static int i40e_xsk_umem_disable(struct i40e_vsi *vsi, u16 qid) } /** - * i40e_xsk_umem_setup - Enable/disassociate a UMEM to/from a ring/qid + * i40e_xsk_pool_setup - Enable/disassociate an AF_XDP buffer pool to/from + * a ring/qid * @vsi: Current VSI - * @umem: UMEM to enable/associate to a ring, or NULL to disable - * @qid: Rx ring to (dis)associate UMEM (from)to + * @pool: Buffer pool to enable/associate to a ring, or NULL to disable + * @qid: Rx ring to (dis)associate buffer pool (from)to * - * This function enables or disables a UMEM to a certain ring. + * This function enables or disables a buffer pool to a certain ring. * * Returns 0 on success, <0 on failure **/ -int i40e_xsk_umem_setup(struct i40e_vsi *vsi, struct xdp_umem *umem, +int i40e_xsk_pool_setup(struct i40e_vsi *vsi, struct xsk_buff_pool *pool, u16 qid) { - return umem ? i40e_xsk_umem_enable(vsi, umem, qid) : - i40e_xsk_umem_disable(vsi, qid); + return pool ? i40e_xsk_pool_enable(vsi, pool, qid) : + i40e_xsk_pool_disable(vsi, qid); } /** @@ -191,7 +196,7 @@ bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count) rx_desc = I40E_RX_DESC(rx_ring, ntu); bi = i40e_rx_bi(rx_ring, ntu); do { - xdp = xsk_buff_alloc(rx_ring->xsk_umem); + xdp = xsk_buff_alloc(rx_ring->xsk_pool->umem); if (!xdp) { ok = false; goto no_buffers; @@ -358,11 +363,11 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) i40e_finalize_xdp_rx(rx_ring, xdp_xmit); i40e_update_rx_stats(rx_ring, total_rx_bytes, total_rx_packets); - if (xsk_umem_uses_need_wakeup(rx_ring->xsk_umem)) { + if (xsk_umem_uses_need_wakeup(rx_ring->xsk_pool->umem)) { if (failure || rx_ring->next_to_clean == rx_ring->next_to_use) - xsk_set_rx_need_wakeup(rx_ring->xsk_umem); + xsk_set_rx_need_wakeup(rx_ring->xsk_pool->umem); else - xsk_clear_rx_need_wakeup(rx_ring->xsk_umem); + xsk_clear_rx_need_wakeup(rx_ring->xsk_pool->umem); return (int)total_rx_packets; } @@ -385,11 +390,12 @@ static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget) dma_addr_t dma; while (budget-- > 0) { - if (!xsk_umem_consume_tx(xdp_ring->xsk_umem, &desc)) + if (!xsk_umem_consume_tx(xdp_ring->xsk_pool->umem, &desc)) break; - dma = xsk_buff_raw_get_dma(xdp_ring->xsk_umem, desc.addr); - xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_umem, dma, + dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool->umem, + desc.addr); + xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool->umem, dma, desc.len); tx_bi = &xdp_ring->tx_bi[xdp_ring->next_to_use]; @@ -416,7 +422,7 @@ static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget) I40E_TXD_QW1_CMD_SHIFT); i40e_xdp_ring_update_tail(xdp_ring); - xsk_umem_consume_tx_done(xdp_ring->xsk_umem); + xsk_umem_consume_tx_done(xdp_ring->xsk_pool->umem); i40e_update_tx_stats(xdp_ring, sent_frames, total_bytes); } @@ -448,7 +454,7 @@ static void i40e_clean_xdp_tx_buffer(struct i40e_ring *tx_ring, **/ bool i40e_clean_xdp_tx_irq(struct i40e_vsi *vsi, struct i40e_ring *tx_ring) { - struct xdp_umem *umem = tx_ring->xsk_umem; + struct xsk_buff_pool *bp = tx_ring->xsk_pool; u32 i, completed_frames, xsk_frames = 0; u32 head_idx = i40e_get_head(tx_ring); struct i40e_tx_buffer *tx_bi; @@ -488,13 +494,13 @@ skip: tx_ring->next_to_clean -= tx_ring->count; if (xsk_frames) - xsk_umem_complete_tx(umem, xsk_frames); + xsk_umem_complete_tx(bp->umem, xsk_frames); i40e_arm_wb(tx_ring, vsi, completed_frames); out_xmit: - if (xsk_umem_uses_need_wakeup(tx_ring->xsk_umem)) - xsk_set_tx_need_wakeup(tx_ring->xsk_umem); + if (xsk_umem_uses_need_wakeup(tx_ring->xsk_pool->umem)) + xsk_set_tx_need_wakeup(tx_ring->xsk_pool->umem); return i40e_xmit_zc(tx_ring, I40E_DESC_UNUSED(tx_ring)); } @@ -526,7 +532,7 @@ int i40e_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags) if (queue_id >= vsi->num_queue_pairs) return -ENXIO; - if (!vsi->xdp_rings[queue_id]->xsk_umem) + if (!vsi->xdp_rings[queue_id]->xsk_pool) return -ENXIO; ring = vsi->xdp_rings[queue_id]; @@ -565,7 +571,7 @@ void i40e_xsk_clean_rx_ring(struct i40e_ring *rx_ring) void i40e_xsk_clean_tx_ring(struct i40e_ring *tx_ring) { u16 ntc = tx_ring->next_to_clean, ntu = tx_ring->next_to_use; - struct xdp_umem *umem = tx_ring->xsk_umem; + struct xsk_buff_pool *bp = tx_ring->xsk_pool; struct i40e_tx_buffer *tx_bi; u32 xsk_frames = 0; @@ -585,14 +591,15 @@ void i40e_xsk_clean_tx_ring(struct i40e_ring *tx_ring) } if (xsk_frames) - xsk_umem_complete_tx(umem, xsk_frames); + xsk_umem_complete_tx(bp->umem, xsk_frames); } /** - * i40e_xsk_any_rx_ring_enabled - Checks if Rx rings have AF_XDP UMEM attached + * i40e_xsk_any_rx_ring_enabled - Checks if Rx rings have an AF_XDP + * buffer pool attached * @vsi: vsi * - * Returns true if any of the Rx rings has an AF_XDP UMEM attached + * Returns true if any of the Rx rings has an AF_XDP buffer pool attached **/ bool i40e_xsk_any_rx_ring_enabled(struct i40e_vsi *vsi) { @@ -600,7 +607,7 @@ bool i40e_xsk_any_rx_ring_enabled(struct i40e_vsi *vsi) int i; for (i = 0; i < vsi->num_queue_pairs; i++) { - if (xdp_get_umem_from_qid(netdev, i)) + if (xdp_get_xsk_pool_from_qid(netdev, i)) return true; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.h b/drivers/net/ethernet/intel/i40e/i40e_xsk.h index c524c142127f..7adfd8539247 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.h +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.h @@ -5,12 +5,12 @@ #define _I40E_XSK_H_ struct i40e_vsi; -struct xdp_umem; +struct xsk_buff_pool; struct zero_copy_allocator; int i40e_queue_pair_disable(struct i40e_vsi *vsi, int queue_pair); int i40e_queue_pair_enable(struct i40e_vsi *vsi, int queue_pair); -int i40e_xsk_umem_setup(struct i40e_vsi *vsi, struct xdp_umem *umem, +int i40e_xsk_pool_setup(struct i40e_vsi *vsi, struct xsk_buff_pool *pool, u16 qid); bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 cleaned_count); int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget); diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index fe140ff38f74..65583f0a1797 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -321,9 +321,9 @@ struct ice_vsi { struct ice_ring **xdp_rings; /* XDP ring array */ u16 num_xdp_txq; /* Used XDP queues */ u8 xdp_mapping_mode; /* ICE_MAP_MODE_[CONTIG|SCATTER] */ - struct xdp_umem **xsk_umems; - u16 num_xsk_umems_used; - u16 num_xsk_umems; + struct xsk_buff_pool **xsk_pools; + u16 num_xsk_pools_used; + u16 num_xsk_pools; } ____cacheline_internodealigned_in_smp; /* struct that defines an interrupt vector */ @@ -507,25 +507,25 @@ static inline void ice_set_ring_xdp(struct ice_ring *ring) } /** - * ice_xsk_umem - get XDP UMEM bound to a ring + * ice_xsk_pool - get XSK buffer pool bound to a ring * @ring - ring to use * - * Returns a pointer to xdp_umem structure if there is an UMEM present, + * Returns a pointer to xdp_umem structure if there is a buffer pool present, * NULL otherwise. */ -static inline struct xdp_umem *ice_xsk_umem(struct ice_ring *ring) +static inline struct xsk_buff_pool *ice_xsk_pool(struct ice_ring *ring) { - struct xdp_umem **umems = ring->vsi->xsk_umems; + struct xsk_buff_pool **pools = ring->vsi->xsk_pools; u16 qid = ring->q_index; if (ice_ring_is_xdp(ring)) qid -= ring->vsi->num_xdp_txq; - if (qid >= ring->vsi->num_xsk_umems || !umems || !umems[qid] || + if (qid >= ring->vsi->num_xsk_pools || !pools || !pools[qid] || !ice_is_xdp_ena_vsi(ring->vsi)) return NULL; - return umems[qid]; + return pools[qid]; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index 87008476d8fe..3c92448e2554 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -308,12 +308,12 @@ int ice_setup_rx_ctx(struct ice_ring *ring) xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, ring->q_index); - ring->xsk_umem = ice_xsk_umem(ring); - if (ring->xsk_umem) { + ring->xsk_pool = ice_xsk_pool(ring); + if (ring->xsk_pool) { xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq); ring->rx_buf_len = - xsk_umem_get_rx_frame_size(ring->xsk_umem); + xsk_umem_get_rx_frame_size(ring->xsk_pool->umem); /* For AF_XDP ZC, we disallow packets to span on * multiple buffers, thus letting us skip that * handling in the fast-path. @@ -324,7 +324,7 @@ int ice_setup_rx_ctx(struct ice_ring *ring) NULL); if (err) return err; - xsk_buff_set_rxq_info(ring->xsk_umem, &ring->xdp_rxq); + xsk_buff_set_rxq_info(ring->xsk_pool->umem, &ring->xdp_rxq); dev_info(dev, "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n", ring->q_index); @@ -417,9 +417,9 @@ int ice_setup_rx_ctx(struct ice_ring *ring) ring->tail = hw->hw_addr + QRX_TAIL(pf_q); writel(0, ring->tail); - if (ring->xsk_umem) { - if (!xsk_buff_can_alloc(ring->xsk_umem, num_bufs)) { - dev_warn(dev, "UMEM does not provide enough addresses to fill %d buffers on Rx ring %d\n", + if (ring->xsk_pool) { + if (!xsk_buff_can_alloc(ring->xsk_pool->umem, num_bufs)) { + dev_warn(dev, "XSK buffer pool does not provide enough addresses to fill %d buffers on Rx ring %d\n", num_bufs, ring->q_index); dev_warn(dev, "Change Rx ring/fill queue size to avoid performance issues\n"); @@ -428,7 +428,7 @@ int ice_setup_rx_ctx(struct ice_ring *ring) err = ice_alloc_rx_bufs_zc(ring, num_bufs); if (err) - dev_info(dev, "Failed to allocate some buffers on UMEM enabled Rx ring %d (pf_q %d)\n", + dev_info(dev, "Failed to allocate some buffers on XSK buffer pool enabled Rx ring %d (pf_q %d)\n", ring->q_index, pf_q); return 0; } diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index f2682776f8c8..feeb5cdccdc5 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -1743,7 +1743,7 @@ int ice_vsi_cfg_xdp_txqs(struct ice_vsi *vsi) return ret; for (i = 0; i < vsi->num_xdp_txq; i++) - vsi->xdp_rings[i]->xsk_umem = ice_xsk_umem(vsi->xdp_rings[i]); + vsi->xdp_rings[i]->xsk_pool = ice_xsk_pool(vsi->xdp_rings[i]); return ret; } diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 4634b48949bb..2297ee7dba26 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -2273,7 +2273,7 @@ static int ice_xdp_alloc_setup_rings(struct ice_vsi *vsi) if (ice_setup_tx_ring(xdp_ring)) goto free_xdp_rings; ice_set_ring_xdp(xdp_ring); - xdp_ring->xsk_umem = ice_xsk_umem(xdp_ring); + xdp_ring->xsk_pool = ice_xsk_pool(xdp_ring); } return 0; @@ -2517,13 +2517,13 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, if (if_running) ret = ice_up(vsi); - if (!ret && prog && vsi->xsk_umems) { + if (!ret && prog && vsi->xsk_pools) { int i; ice_for_each_rxq(vsi, i) { struct ice_ring *rx_ring = vsi->rx_rings[i]; - if (rx_ring->xsk_umem) + if (rx_ring->xsk_pool) napi_schedule(&rx_ring->q_vector->napi); } } @@ -2549,8 +2549,8 @@ static int ice_xdp(struct net_device *dev, struct netdev_bpf *xdp) switch (xdp->command) { case XDP_SETUP_PROG: return ice_xdp_setup_prog(vsi, xdp->prog, xdp->extack); - case XDP_SETUP_XSK_UMEM: - return ice_xsk_umem_setup(vsi, xdp->xsk.umem, + case XDP_SETUP_XSK_POOL: + return ice_xsk_pool_setup(vsi, xdp->xsk.pool, xdp->xsk.queue_id); default: return -EINVAL; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 9d0d6b0025cf..b061dc10703d 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -145,7 +145,7 @@ void ice_clean_tx_ring(struct ice_ring *tx_ring) { u16 i; - if (ice_ring_is_xdp(tx_ring) && tx_ring->xsk_umem) { + if (ice_ring_is_xdp(tx_ring) && tx_ring->xsk_pool) { ice_xsk_clean_xdp_ring(tx_ring); goto tx_skip_free; } @@ -375,7 +375,7 @@ void ice_clean_rx_ring(struct ice_ring *rx_ring) if (!rx_ring->rx_buf) return; - if (rx_ring->xsk_umem) { + if (rx_ring->xsk_pool) { ice_xsk_clean_rx_ring(rx_ring); goto rx_skip_free; } @@ -1616,7 +1616,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget) * budget and be more aggressive about cleaning up the Tx descriptors. */ ice_for_each_ring(ring, q_vector->tx) { - bool wd = ring->xsk_umem ? + bool wd = ring->xsk_pool ? ice_clean_tx_irq_zc(ring, budget) : ice_clean_tx_irq(ring, budget); @@ -1646,7 +1646,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget) * comparison in the irq context instead of many inside the * ice_clean_rx_irq function and makes the codebase cleaner. */ - cleaned = ring->xsk_umem ? + cleaned = ring->xsk_pool ? ice_clean_rx_irq_zc(ring, budget_per_ring) : ice_clean_rx_irq(ring, budget_per_ring); work_done += cleaned; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index 51b4df7a59d2..e9f60d550fcb 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -295,7 +295,7 @@ struct ice_ring { struct rcu_head rcu; /* to avoid race on free */ struct bpf_prog *xdp_prog; - struct xdp_umem *xsk_umem; + struct xsk_buff_pool *xsk_pool; /* CL3 - 3rd cacheline starts here */ struct xdp_rxq_info xdp_rxq; /* CLX - the below items are only accessed infrequently and should be diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 20ac5fca68c6..8b70e8c5bc3a 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -236,7 +236,7 @@ static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx) if (err) goto free_buf; ice_set_ring_xdp(xdp_ring); - xdp_ring->xsk_umem = ice_xsk_umem(xdp_ring); + xdp_ring->xsk_pool = ice_xsk_pool(xdp_ring); } err = ice_setup_rx_ctx(rx_ring); @@ -260,21 +260,21 @@ free_buf: } /** - * ice_xsk_alloc_umems - allocate a UMEM region for an XDP socket - * @vsi: VSI to allocate the UMEM on + * ice_xsk_alloc_pools - allocate a buffer pool for an XDP socket + * @vsi: VSI to allocate the buffer pool on * * Returns 0 on success, negative on error */ -static int ice_xsk_alloc_umems(struct ice_vsi *vsi) +static int ice_xsk_alloc_pools(struct ice_vsi *vsi) { - if (vsi->xsk_umems) + if (vsi->xsk_pools) return 0; - vsi->xsk_umems = kcalloc(vsi->num_xsk_umems, sizeof(*vsi->xsk_umems), + vsi->xsk_pools = kcalloc(vsi->num_xsk_pools, sizeof(*vsi->xsk_pools), GFP_KERNEL); - if (!vsi->xsk_umems) { - vsi->num_xsk_umems = 0; + if (!vsi->xsk_pools) { + vsi->num_xsk_pools = 0; return -ENOMEM; } @@ -282,73 +282,73 @@ static int ice_xsk_alloc_umems(struct ice_vsi *vsi) } /** - * ice_xsk_remove_umem - Remove an UMEM for a certain ring/qid + * ice_xsk_remove_pool - Remove an buffer pool for a certain ring/qid * @vsi: VSI from which the VSI will be removed - * @qid: Ring/qid associated with the UMEM + * @qid: Ring/qid associated with the buffer pool */ -static void ice_xsk_remove_umem(struct ice_vsi *vsi, u16 qid) +static void ice_xsk_remove_pool(struct ice_vsi *vsi, u16 qid) { - vsi->xsk_umems[qid] = NULL; - vsi->num_xsk_umems_used--; + vsi->xsk_pools[qid] = NULL; + vsi->num_xsk_pools_used--; - if (vsi->num_xsk_umems_used == 0) { - kfree(vsi->xsk_umems); - vsi->xsk_umems = NULL; - vsi->num_xsk_umems = 0; + if (vsi->num_xsk_pools_used == 0) { + kfree(vsi->xsk_pools); + vsi->xsk_pools = NULL; + vsi->num_xsk_pools = 0; } } /** - * ice_xsk_umem_disable - disable a UMEM region + * ice_xsk_pool_disable - disable a buffer pool region * @vsi: Current VSI * @qid: queue ID * * Returns 0 on success, negative on failure */ -static int ice_xsk_umem_disable(struct ice_vsi *vsi, u16 qid) +static int ice_xsk_pool_disable(struct ice_vsi *vsi, u16 qid) { - if (!vsi->xsk_umems || qid >= vsi->num_xsk_umems || - !vsi->xsk_umems[qid]) + if (!vsi->xsk_pools || qid >= vsi->num_xsk_pools || + !vsi->xsk_pools[qid]) return -EINVAL; - xsk_buff_dma_unmap(vsi->xsk_umems[qid], ICE_RX_DMA_ATTR); - ice_xsk_remove_umem(vsi, qid); + xsk_buff_dma_unmap(vsi->xsk_pools[qid]->umem, ICE_RX_DMA_ATTR); + ice_xsk_remove_pool(vsi, qid); return 0; } /** - * ice_xsk_umem_enable - enable a UMEM region + * ice_xsk_pool_enable - enable a buffer pool region * @vsi: Current VSI - * @umem: pointer to a requested UMEM region + * @pool: pointer to a requested buffer pool region * @qid: queue ID * * Returns 0 on success, negative on failure */ static int -ice_xsk_umem_enable(struct ice_vsi *vsi, struct xdp_umem *umem, u16 qid) +ice_xsk_pool_enable(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid) { int err; if (vsi->type != ICE_VSI_PF) return -EINVAL; - if (!vsi->num_xsk_umems) - vsi->num_xsk_umems = min_t(u16, vsi->num_rxq, vsi->num_txq); - if (qid >= vsi->num_xsk_umems) + if (!vsi->num_xsk_pools) + vsi->num_xsk_pools = min_t(u16, vsi->num_rxq, vsi->num_txq); + if (qid >= vsi->num_xsk_pools) return -EINVAL; - err = ice_xsk_alloc_umems(vsi); + err = ice_xsk_alloc_pools(vsi); if (err) return err; - if (vsi->xsk_umems && vsi->xsk_umems[qid]) + if (vsi->xsk_pools && vsi->xsk_pools[qid]) return -EBUSY; - vsi->xsk_umems[qid] = umem; - vsi->num_xsk_umems_used++; + vsi->xsk_pools[qid] = pool; + vsi->num_xsk_pools_used++; - err = xsk_buff_dma_map(vsi->xsk_umems[qid], ice_pf_to_dev(vsi->back), + err = xsk_buff_dma_map(vsi->xsk_pools[qid]->umem, ice_pf_to_dev(vsi->back), ICE_RX_DMA_ATTR); if (err) return err; @@ -357,17 +357,17 @@ ice_xsk_umem_enable(struct ice_vsi *vsi, struct xdp_umem *umem, u16 qid) } /** - * ice_xsk_umem_setup - enable/disable a UMEM region depending on its state + * ice_xsk_pool_setup - enable/disable a buffer pool region depending on its state * @vsi: Current VSI - * @umem: UMEM to enable/associate to a ring, NULL to disable + * @pool: buffer pool to enable/associate to a ring, NULL to disable * @qid: queue ID * * Returns 0 on success, negative on failure */ -int ice_xsk_umem_setup(struct ice_vsi *vsi, struct xdp_umem *umem, u16 qid) +int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid) { - bool if_running, umem_present = !!umem; - int ret = 0, umem_failure = 0; + bool if_running, pool_present = !!pool; + int ret = 0, pool_failure = 0; if_running = netif_running(vsi->netdev) && ice_is_xdp_ena_vsi(vsi); @@ -375,26 +375,26 @@ int ice_xsk_umem_setup(struct ice_vsi *vsi, struct xdp_umem *umem, u16 qid) ret = ice_qp_dis(vsi, qid); if (ret) { netdev_err(vsi->netdev, "ice_qp_dis error = %d\n", ret); - goto xsk_umem_if_up; + goto xsk_pool_if_up; } } - umem_failure = umem_present ? ice_xsk_umem_enable(vsi, umem, qid) : - ice_xsk_umem_disable(vsi, qid); + pool_failure = pool_present ? ice_xsk_pool_enable(vsi, pool, qid) : + ice_xsk_pool_disable(vsi, qid); -xsk_umem_if_up: +xsk_pool_if_up: if (if_running) { ret = ice_qp_ena(vsi, qid); - if (!ret && umem_present) + if (!ret && pool_present) napi_schedule(&vsi->xdp_rings[qid]->q_vector->napi); else if (ret) netdev_err(vsi->netdev, "ice_qp_ena error = %d\n", ret); } - if (umem_failure) { - netdev_err(vsi->netdev, "Could not %sable UMEM, error = %d\n", - umem_present ? "en" : "dis", umem_failure); - return umem_failure; + if (pool_failure) { + netdev_err(vsi->netdev, "Could not %sable buffer pool, error = %d\n", + pool_present ? "en" : "dis", pool_failure); + return pool_failure; } return ret; @@ -425,7 +425,7 @@ bool ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, u16 count) rx_buf = &rx_ring->rx_buf[ntu]; do { - rx_buf->xdp = xsk_buff_alloc(rx_ring->xsk_umem); + rx_buf->xdp = xsk_buff_alloc(rx_ring->xsk_pool->umem); if (!rx_buf->xdp) { ret = true; break; @@ -645,11 +645,11 @@ int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget) ice_finalize_xdp_rx(rx_ring, xdp_xmit); ice_update_rx_ring_stats(rx_ring, total_rx_packets, total_rx_bytes); - if (xsk_umem_uses_need_wakeup(rx_ring->xsk_umem)) { + if (xsk_umem_uses_need_wakeup(rx_ring->xsk_pool->umem)) { if (failure || rx_ring->next_to_clean == rx_ring->next_to_use) - xsk_set_rx_need_wakeup(rx_ring->xsk_umem); + xsk_set_rx_need_wakeup(rx_ring->xsk_pool->umem); else - xsk_clear_rx_need_wakeup(rx_ring->xsk_umem); + xsk_clear_rx_need_wakeup(rx_ring->xsk_pool->umem); return (int)total_rx_packets; } @@ -682,11 +682,11 @@ static bool ice_xmit_zc(struct ice_ring *xdp_ring, int budget) tx_buf = &xdp_ring->tx_buf[xdp_ring->next_to_use]; - if (!xsk_umem_consume_tx(xdp_ring->xsk_umem, &desc)) + if (!xsk_umem_consume_tx(xdp_ring->xsk_pool->umem, &desc)) break; - dma = xsk_buff_raw_get_dma(xdp_ring->xsk_umem, desc.addr); - xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_umem, dma, + dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool->umem, desc.addr); + xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool->umem, dma, desc.len); tx_buf->bytecount = desc.len; @@ -703,7 +703,7 @@ static bool ice_xmit_zc(struct ice_ring *xdp_ring, int budget) if (tx_desc) { ice_xdp_ring_update_tail(xdp_ring); - xsk_umem_consume_tx_done(xdp_ring->xsk_umem); + xsk_umem_consume_tx_done(xdp_ring->xsk_pool->umem); } return budget > 0 && work_done; @@ -777,10 +777,10 @@ bool ice_clean_tx_irq_zc(struct ice_ring *xdp_ring, int budget) xdp_ring->next_to_clean = ntc; if (xsk_frames) - xsk_umem_complete_tx(xdp_ring->xsk_umem, xsk_frames); + xsk_umem_complete_tx(xdp_ring->xsk_pool->umem, xsk_frames); - if (xsk_umem_uses_need_wakeup(xdp_ring->xsk_umem)) - xsk_set_tx_need_wakeup(xdp_ring->xsk_umem); + if (xsk_umem_uses_need_wakeup(xdp_ring->xsk_pool->umem)) + xsk_set_tx_need_wakeup(xdp_ring->xsk_pool->umem); ice_update_tx_ring_stats(xdp_ring, total_packets, total_bytes); xmit_done = ice_xmit_zc(xdp_ring, ICE_DFLT_IRQ_WORK); @@ -814,7 +814,7 @@ ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, if (queue_id >= vsi->num_txq) return -ENXIO; - if (!vsi->xdp_rings[queue_id]->xsk_umem) + if (!vsi->xdp_rings[queue_id]->xsk_pool) return -ENXIO; ring = vsi->xdp_rings[queue_id]; @@ -833,20 +833,20 @@ ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, } /** - * ice_xsk_any_rx_ring_ena - Checks if Rx rings have AF_XDP UMEM attached + * ice_xsk_any_rx_ring_ena - Checks if Rx rings have AF_XDP buff pool attached * @vsi: VSI to be checked * - * Returns true if any of the Rx rings has an AF_XDP UMEM attached + * Returns true if any of the Rx rings has an AF_XDP buff pool attached */ bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi) { int i; - if (!vsi->xsk_umems) + if (!vsi->xsk_pools) return false; - for (i = 0; i < vsi->num_xsk_umems; i++) { - if (vsi->xsk_umems[i]) + for (i = 0; i < vsi->num_xsk_pools; i++) { + if (vsi->xsk_pools[i]) return true; } @@ -854,7 +854,7 @@ bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi) } /** - * ice_xsk_clean_rx_ring - clean UMEM queues connected to a given Rx ring + * ice_xsk_clean_rx_ring - clean buffer pool queues connected to a given Rx ring * @rx_ring: ring to be cleaned */ void ice_xsk_clean_rx_ring(struct ice_ring *rx_ring) @@ -872,7 +872,7 @@ void ice_xsk_clean_rx_ring(struct ice_ring *rx_ring) } /** - * ice_xsk_clean_xdp_ring - Clean the XDP Tx ring and its UMEM queues + * ice_xsk_clean_xdp_ring - Clean the XDP Tx ring and its buffer pool queues * @xdp_ring: XDP_Tx ring */ void ice_xsk_clean_xdp_ring(struct ice_ring *xdp_ring) @@ -896,5 +896,5 @@ void ice_xsk_clean_xdp_ring(struct ice_ring *xdp_ring) } if (xsk_frames) - xsk_umem_complete_tx(xdp_ring->xsk_umem, xsk_frames); + xsk_umem_complete_tx(xdp_ring->xsk_pool->umem, xsk_frames); } diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.h b/drivers/net/ethernet/intel/ice/ice_xsk.h index fc1a06b4df36..fad783690134 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.h +++ b/drivers/net/ethernet/intel/ice/ice_xsk.h @@ -9,7 +9,8 @@ struct ice_vsi; #ifdef CONFIG_XDP_SOCKETS -int ice_xsk_umem_setup(struct ice_vsi *vsi, struct xdp_umem *umem, u16 qid); +int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool, + u16 qid); int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget); bool ice_clean_tx_irq_zc(struct ice_ring *xdp_ring, int budget); int ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, u32 flags); @@ -19,8 +20,8 @@ void ice_xsk_clean_rx_ring(struct ice_ring *rx_ring); void ice_xsk_clean_xdp_ring(struct ice_ring *xdp_ring); #else static inline int -ice_xsk_umem_setup(struct ice_vsi __always_unused *vsi, - struct xdp_umem __always_unused *umem, +ice_xsk_pool_setup(struct ice_vsi __always_unused *vsi, + struct xsk_buff_pool __always_unused *pool, u16 __always_unused qid) { return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index 1e8a809233a0..de0fc6ecf491 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -350,7 +350,7 @@ struct ixgbe_ring { struct ixgbe_rx_queue_stats rx_stats; }; struct xdp_rxq_info xdp_rxq; - struct xdp_umem *xsk_umem; + struct xsk_buff_pool *xsk_pool; u16 ring_idx; /* {rx,tx,xdp}_ring back reference idx */ u16 rx_buf_len; } ____cacheline_internodealigned_in_smp; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 2f8a4cfc5fa1..c498465b3000 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -3156,7 +3156,7 @@ int ixgbe_poll(struct napi_struct *napi, int budget) #endif ixgbe_for_each_ring(ring, q_vector->tx) { - bool wd = ring->xsk_umem ? + bool wd = ring->xsk_pool ? ixgbe_clean_xdp_tx_irq(q_vector, ring, budget) : ixgbe_clean_tx_irq(q_vector, ring, budget); @@ -3176,7 +3176,7 @@ int ixgbe_poll(struct napi_struct *napi, int budget) per_ring_budget = budget; ixgbe_for_each_ring(ring, q_vector->rx) { - int cleaned = ring->xsk_umem ? + int cleaned = ring->xsk_pool ? ixgbe_clean_rx_irq_zc(q_vector, ring, per_ring_budget) : ixgbe_clean_rx_irq(q_vector, ring, @@ -3471,9 +3471,9 @@ void ixgbe_configure_tx_ring(struct ixgbe_adapter *adapter, u32 txdctl = IXGBE_TXDCTL_ENABLE; u8 reg_idx = ring->reg_idx; - ring->xsk_umem = NULL; + ring->xsk_pool = NULL; if (ring_is_xdp(ring)) - ring->xsk_umem = ixgbe_xsk_umem(adapter, ring); + ring->xsk_pool = ixgbe_xsk_pool(adapter, ring); /* disable queue to avoid issues while updating state */ IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), 0); @@ -3713,8 +3713,8 @@ static void ixgbe_configure_srrctl(struct ixgbe_adapter *adapter, srrctl = IXGBE_RX_HDR_SIZE << IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT; /* configure the packet buffer length */ - if (rx_ring->xsk_umem) { - u32 xsk_buf_len = xsk_umem_get_rx_frame_size(rx_ring->xsk_umem); + if (rx_ring->xsk_pool) { + u32 xsk_buf_len = xsk_umem_get_rx_frame_size(rx_ring->xsk_pool->umem); /* If the MAC support setting RXDCTL.RLPML, the * SRRCTL[n].BSIZEPKT is set to PAGE_SIZE and @@ -4059,12 +4059,12 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter, u8 reg_idx = ring->reg_idx; xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq); - ring->xsk_umem = ixgbe_xsk_umem(adapter, ring); - if (ring->xsk_umem) { + ring->xsk_pool = ixgbe_xsk_pool(adapter, ring); + if (ring->xsk_pool) { WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, MEM_TYPE_XSK_BUFF_POOL, NULL)); - xsk_buff_set_rxq_info(ring->xsk_umem, &ring->xdp_rxq); + xsk_buff_set_rxq_info(ring->xsk_pool->umem, &ring->xdp_rxq); } else { WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, MEM_TYPE_PAGE_SHARED, NULL)); @@ -4119,8 +4119,8 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter, #endif } - if (ring->xsk_umem && hw->mac.type != ixgbe_mac_82599EB) { - u32 xsk_buf_len = xsk_umem_get_rx_frame_size(ring->xsk_umem); + if (ring->xsk_pool && hw->mac.type != ixgbe_mac_82599EB) { + u32 xsk_buf_len = xsk_umem_get_rx_frame_size(ring->xsk_pool->umem); rxdctl &= ~(IXGBE_RXDCTL_RLPMLMASK | IXGBE_RXDCTL_RLPML_EN); @@ -4142,7 +4142,7 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter, IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(reg_idx), rxdctl); ixgbe_rx_desc_queue_enable(adapter, ring); - if (ring->xsk_umem) + if (ring->xsk_pool) ixgbe_alloc_rx_buffers_zc(ring, ixgbe_desc_unused(ring)); else ixgbe_alloc_rx_buffers(ring, ixgbe_desc_unused(ring)); @@ -5292,7 +5292,7 @@ static void ixgbe_clean_rx_ring(struct ixgbe_ring *rx_ring) u16 i = rx_ring->next_to_clean; struct ixgbe_rx_buffer *rx_buffer = &rx_ring->rx_buffer_info[i]; - if (rx_ring->xsk_umem) { + if (rx_ring->xsk_pool) { ixgbe_xsk_clean_rx_ring(rx_ring); goto skip_free; } @@ -5984,7 +5984,7 @@ static void ixgbe_clean_tx_ring(struct ixgbe_ring *tx_ring) u16 i = tx_ring->next_to_clean; struct ixgbe_tx_buffer *tx_buffer = &tx_ring->tx_buffer_info[i]; - if (tx_ring->xsk_umem) { + if (tx_ring->xsk_pool) { ixgbe_xsk_clean_tx_ring(tx_ring); goto out; } @@ -10146,7 +10146,7 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog) */ if (need_reset && prog) for (i = 0; i < adapter->num_rx_queues; i++) - if (adapter->xdp_ring[i]->xsk_umem) + if (adapter->xdp_ring[i]->xsk_pool) (void)ixgbe_xsk_wakeup(adapter->netdev, i, XDP_WAKEUP_RX); @@ -10160,8 +10160,8 @@ static int ixgbe_xdp(struct net_device *dev, struct netdev_bpf *xdp) switch (xdp->command) { case XDP_SETUP_PROG: return ixgbe_xdp_setup(dev, xdp->prog); - case XDP_SETUP_XSK_UMEM: - return ixgbe_xsk_umem_setup(adapter, xdp->xsk.umem, + case XDP_SETUP_XSK_POOL: + return ixgbe_xsk_pool_setup(adapter, xdp->xsk.pool, xdp->xsk.queue_id); default: diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h index 7887ae4aaf4f..2aeec78029bc 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h @@ -28,9 +28,10 @@ void ixgbe_irq_rearm_queues(struct ixgbe_adapter *adapter, u64 qmask); void ixgbe_txrx_ring_disable(struct ixgbe_adapter *adapter, int ring); void ixgbe_txrx_ring_enable(struct ixgbe_adapter *adapter, int ring); -struct xdp_umem *ixgbe_xsk_umem(struct ixgbe_adapter *adapter, - struct ixgbe_ring *ring); -int ixgbe_xsk_umem_setup(struct ixgbe_adapter *adapter, struct xdp_umem *umem, +struct xsk_buff_pool *ixgbe_xsk_pool(struct ixgbe_adapter *adapter, + struct ixgbe_ring *ring); +int ixgbe_xsk_pool_setup(struct ixgbe_adapter *adapter, + struct xsk_buff_pool *pool, u16 qid); void ixgbe_zca_free(struct zero_copy_allocator *alloc, unsigned long handle); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c index ec7121f352e2..8ad954fcdc38 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c @@ -8,8 +8,8 @@ #include "ixgbe.h" #include "ixgbe_txrx_common.h" -struct xdp_umem *ixgbe_xsk_umem(struct ixgbe_adapter *adapter, - struct ixgbe_ring *ring) +struct xsk_buff_pool *ixgbe_xsk_pool(struct ixgbe_adapter *adapter, + struct ixgbe_ring *ring) { bool xdp_on = READ_ONCE(adapter->xdp_prog); int qid = ring->ring_idx; @@ -17,11 +17,11 @@ struct xdp_umem *ixgbe_xsk_umem(struct ixgbe_adapter *adapter, if (!xdp_on || !test_bit(qid, adapter->af_xdp_zc_qps)) return NULL; - return xdp_get_umem_from_qid(adapter->netdev, qid); + return xdp_get_xsk_pool_from_qid(adapter->netdev, qid); } -static int ixgbe_xsk_umem_enable(struct ixgbe_adapter *adapter, - struct xdp_umem *umem, +static int ixgbe_xsk_pool_enable(struct ixgbe_adapter *adapter, + struct xsk_buff_pool *pool, u16 qid) { struct net_device *netdev = adapter->netdev; @@ -35,7 +35,7 @@ static int ixgbe_xsk_umem_enable(struct ixgbe_adapter *adapter, qid >= netdev->real_num_tx_queues) return -EINVAL; - err = xsk_buff_dma_map(umem, &adapter->pdev->dev, IXGBE_RX_DMA_ATTR); + err = xsk_buff_dma_map(pool->umem, &adapter->pdev->dev, IXGBE_RX_DMA_ATTR); if (err) return err; @@ -59,13 +59,13 @@ static int ixgbe_xsk_umem_enable(struct ixgbe_adapter *adapter, return 0; } -static int ixgbe_xsk_umem_disable(struct ixgbe_adapter *adapter, u16 qid) +static int ixgbe_xsk_pool_disable(struct ixgbe_adapter *adapter, u16 qid) { - struct xdp_umem *umem; + struct xsk_buff_pool *pool; bool if_running; - umem = xdp_get_umem_from_qid(adapter->netdev, qid); - if (!umem) + pool = xdp_get_xsk_pool_from_qid(adapter->netdev, qid); + if (!pool) return -EINVAL; if_running = netif_running(adapter->netdev) && @@ -75,7 +75,7 @@ static int ixgbe_xsk_umem_disable(struct ixgbe_adapter *adapter, u16 qid) ixgbe_txrx_ring_disable(adapter, qid); clear_bit(qid, adapter->af_xdp_zc_qps); - xsk_buff_dma_unmap(umem, IXGBE_RX_DMA_ATTR); + xsk_buff_dma_unmap(pool->umem, IXGBE_RX_DMA_ATTR); if (if_running) ixgbe_txrx_ring_enable(adapter, qid); @@ -83,11 +83,12 @@ static int ixgbe_xsk_umem_disable(struct ixgbe_adapter *adapter, u16 qid) return 0; } -int ixgbe_xsk_umem_setup(struct ixgbe_adapter *adapter, struct xdp_umem *umem, +int ixgbe_xsk_pool_setup(struct ixgbe_adapter *adapter, + struct xsk_buff_pool *pool, u16 qid) { - return umem ? ixgbe_xsk_umem_enable(adapter, umem, qid) : - ixgbe_xsk_umem_disable(adapter, qid); + return pool ? ixgbe_xsk_pool_enable(adapter, pool, qid) : + ixgbe_xsk_pool_disable(adapter, qid); } static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter, @@ -149,7 +150,7 @@ bool ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 count) i -= rx_ring->count; do { - bi->xdp = xsk_buff_alloc(rx_ring->xsk_umem); + bi->xdp = xsk_buff_alloc(rx_ring->xsk_pool->umem); if (!bi->xdp) { ok = false; break; @@ -344,11 +345,11 @@ int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector, q_vector->rx.total_packets += total_rx_packets; q_vector->rx.total_bytes += total_rx_bytes; - if (xsk_umem_uses_need_wakeup(rx_ring->xsk_umem)) { + if (xsk_umem_uses_need_wakeup(rx_ring->xsk_pool->umem)) { if (failure || rx_ring->next_to_clean == rx_ring->next_to_use) - xsk_set_rx_need_wakeup(rx_ring->xsk_umem); + xsk_set_rx_need_wakeup(rx_ring->xsk_pool->umem); else - xsk_clear_rx_need_wakeup(rx_ring->xsk_umem); + xsk_clear_rx_need_wakeup(rx_ring->xsk_pool->umem); return (int)total_rx_packets; } @@ -373,6 +374,7 @@ void ixgbe_xsk_clean_rx_ring(struct ixgbe_ring *rx_ring) static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget) { + struct xsk_buff_pool *pool = xdp_ring->xsk_pool; union ixgbe_adv_tx_desc *tx_desc = NULL; struct ixgbe_tx_buffer *tx_bi; bool work_done = true; @@ -387,12 +389,11 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget) break; } - if (!xsk_umem_consume_tx(xdp_ring->xsk_umem, &desc)) + if (!xsk_umem_consume_tx(pool->umem, &desc)) break; - dma = xsk_buff_raw_get_dma(xdp_ring->xsk_umem, desc.addr); - xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_umem, dma, - desc.len); + dma = xsk_buff_raw_get_dma(pool->umem, desc.addr); + xsk_buff_raw_dma_sync_for_device(pool->umem, dma, desc.len); tx_bi = &xdp_ring->tx_buffer_info[xdp_ring->next_to_use]; tx_bi->bytecount = desc.len; @@ -418,7 +419,7 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget) if (tx_desc) { ixgbe_xdp_ring_update_tail(xdp_ring); - xsk_umem_consume_tx_done(xdp_ring->xsk_umem); + xsk_umem_consume_tx_done(pool->umem); } return !!budget && work_done; @@ -439,7 +440,7 @@ bool ixgbe_clean_xdp_tx_irq(struct ixgbe_q_vector *q_vector, { u16 ntc = tx_ring->next_to_clean, ntu = tx_ring->next_to_use; unsigned int total_packets = 0, total_bytes = 0; - struct xdp_umem *umem = tx_ring->xsk_umem; + struct xsk_buff_pool *pool = tx_ring->xsk_pool; union ixgbe_adv_tx_desc *tx_desc; struct ixgbe_tx_buffer *tx_bi; u32 xsk_frames = 0; @@ -484,10 +485,10 @@ bool ixgbe_clean_xdp_tx_irq(struct ixgbe_q_vector *q_vector, q_vector->tx.total_packets += total_packets; if (xsk_frames) - xsk_umem_complete_tx(umem, xsk_frames); + xsk_umem_complete_tx(pool->umem, xsk_frames); - if (xsk_umem_uses_need_wakeup(tx_ring->xsk_umem)) - xsk_set_tx_need_wakeup(tx_ring->xsk_umem); + if (xsk_umem_uses_need_wakeup(pool->umem)) + xsk_set_tx_need_wakeup(pool->umem); return ixgbe_xmit_zc(tx_ring, q_vector->tx.work_limit); } @@ -511,7 +512,7 @@ int ixgbe_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags) if (test_bit(__IXGBE_TX_DISABLED, &ring->state)) return -ENETDOWN; - if (!ring->xsk_umem) + if (!ring->xsk_pool) return -ENXIO; if (!napi_if_scheduled_mark_missed(&ring->q_vector->napi)) { @@ -526,7 +527,7 @@ int ixgbe_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags) void ixgbe_xsk_clean_tx_ring(struct ixgbe_ring *tx_ring) { u16 ntc = tx_ring->next_to_clean, ntu = tx_ring->next_to_use; - struct xdp_umem *umem = tx_ring->xsk_umem; + struct xsk_buff_pool *pool = tx_ring->xsk_pool; struct ixgbe_tx_buffer *tx_bi; u32 xsk_frames = 0; @@ -546,5 +547,5 @@ void ixgbe_xsk_clean_tx_ring(struct ixgbe_ring *tx_ring) } if (xsk_frames) - xsk_umem_complete_tx(umem, xsk_frames); + xsk_umem_complete_tx(pool->umem, xsk_frames); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index 10e6886c96ba..0b3eaa102751 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -24,7 +24,7 @@ mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \ en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o \ en_selftest.o en/port.o en/monitor_stats.o en/health.o \ - en/reporter_tx.o en/reporter_rx.o en/params.o en/xsk/umem.o \ + en/reporter_tx.o en/reporter_rx.o en/params.o en/xsk/pool.o \ en/xsk/setup.o en/xsk/rx.o en/xsk/tx.o en/devlink.o # diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 0cc2080fd847..4f33658da25a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -442,7 +442,7 @@ struct mlx5e_xdpsq { struct mlx5e_cq cq; /* read only */ - struct xdp_umem *umem; + struct xsk_buff_pool *xsk_pool; struct mlx5_wq_cyc wq; struct mlx5e_xdpsq_stats *stats; mlx5e_fp_xmit_xdp_frame_check xmit_xdp_frame_check; @@ -606,7 +606,7 @@ struct mlx5e_rq { struct page_pool *page_pool; /* AF_XDP zero-copy */ - struct xdp_umem *umem; + struct xsk_buff_pool *xsk_pool; struct work_struct recover_work; @@ -729,12 +729,13 @@ struct mlx5e_hv_vhca_stats_agent { #endif struct mlx5e_xsk { - /* UMEMs are stored separately from channels, because we don't want to - * lose them when channels are recreated. The kernel also stores UMEMs, - * but it doesn't distinguish between zero-copy and non-zero-copy UMEMs, - * so rely on our mechanism. + /* XSK buffer pools are stored separately from channels, + * because we don't want to lose them when channels are + * recreated. The kernel also stores buffer pool, but it doesn't + * distinguish between zero-copy and non-zero-copy UMEMs, so + * rely on our mechanism. */ - struct xdp_umem **umems; + struct xsk_buff_pool **pools; u16 refcnt; bool ever_used; }; @@ -893,7 +894,7 @@ struct mlx5e_xsk_param; struct mlx5e_rq_param; int mlx5e_open_rq(struct mlx5e_channel *c, struct mlx5e_params *params, struct mlx5e_rq_param *param, struct mlx5e_xsk_param *xsk, - struct xdp_umem *umem, struct mlx5e_rq *rq); + struct xsk_buff_pool *xsk_pool, struct mlx5e_rq *rq); int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq, int wait_time); void mlx5e_deactivate_rq(struct mlx5e_rq *rq); void mlx5e_close_rq(struct mlx5e_rq *rq); @@ -903,7 +904,7 @@ int mlx5e_open_icosq(struct mlx5e_channel *c, struct mlx5e_params *params, struct mlx5e_sq_param *param, struct mlx5e_icosq *sq); void mlx5e_close_icosq(struct mlx5e_icosq *sq); int mlx5e_open_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params, - struct mlx5e_sq_param *param, struct xdp_umem *umem, + struct mlx5e_sq_param *param, struct xsk_buff_pool *xsk_pool, struct mlx5e_xdpsq *sq, bool is_redirect); void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index 0e6946fc121f..c9f0d2be6dd1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -445,7 +445,7 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq) } while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq))); if (xsk_frames) - xsk_umem_complete_tx(sq->umem, xsk_frames); + xsk_umem_complete_tx(sq->xsk_pool->umem, xsk_frames); sq->stats->cqes += i; @@ -475,7 +475,7 @@ void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq) } if (xsk_frames) - xsk_umem_complete_tx(sq->umem, xsk_frames); + xsk_umem_complete_tx(sq->xsk_pool->umem, xsk_frames); } int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, @@ -563,4 +563,3 @@ void mlx5e_set_xmit_fp(struct mlx5e_xdpsq *sq, bool is_mpw) sq->xmit_xdp_frame = is_mpw ? mlx5e_xmit_xdp_frame_mpwqe : mlx5e_xmit_xdp_frame; } - diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c new file mode 100644 index 000000000000..8ccd9203ee25 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c @@ -0,0 +1,217 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2019-2020, Mellanox Technologies inc. All rights reserved. */ + +#include +#include "pool.h" +#include "setup.h" +#include "en/params.h" + +static int mlx5e_xsk_map_pool(struct mlx5e_priv *priv, + struct xsk_buff_pool *pool) +{ + struct device *dev = priv->mdev->device; + + return xsk_buff_dma_map(pool->umem, dev, 0); +} + +static void mlx5e_xsk_unmap_pool(struct mlx5e_priv *priv, + struct xsk_buff_pool *pool) +{ + return xsk_buff_dma_unmap(pool->umem, 0); +} + +static int mlx5e_xsk_get_pools(struct mlx5e_xsk *xsk) +{ + if (!xsk->pools) { + xsk->pools = kcalloc(MLX5E_MAX_NUM_CHANNELS, + sizeof(*xsk->pools), GFP_KERNEL); + if (unlikely(!xsk->pools)) + return -ENOMEM; + } + + xsk->refcnt++; + xsk->ever_used = true; + + return 0; +} + +static void mlx5e_xsk_put_pools(struct mlx5e_xsk *xsk) +{ + if (!--xsk->refcnt) { + kfree(xsk->pools); + xsk->pools = NULL; + } +} + +static int mlx5e_xsk_add_pool(struct mlx5e_xsk *xsk, struct xsk_buff_pool *pool, u16 ix) +{ + int err; + + err = mlx5e_xsk_get_pools(xsk); + if (unlikely(err)) + return err; + + xsk->pools[ix] = pool; + return 0; +} + +static void mlx5e_xsk_remove_pool(struct mlx5e_xsk *xsk, u16 ix) +{ + xsk->pools[ix] = NULL; + + mlx5e_xsk_put_pools(xsk); +} + +static bool mlx5e_xsk_is_pool_sane(struct xsk_buff_pool *pool) +{ + return xsk_umem_get_headroom(pool->umem) <= 0xffff && + xsk_umem_get_chunk_size(pool->umem) <= 0xffff; +} + +void mlx5e_build_xsk_param(struct xsk_buff_pool *pool, struct mlx5e_xsk_param *xsk) +{ + xsk->headroom = xsk_umem_get_headroom(pool->umem); + xsk->chunk_size = xsk_umem_get_chunk_size(pool->umem); +} + +static int mlx5e_xsk_enable_locked(struct mlx5e_priv *priv, + struct xsk_buff_pool *pool, u16 ix) +{ + struct mlx5e_params *params = &priv->channels.params; + struct mlx5e_xsk_param xsk; + struct mlx5e_channel *c; + int err; + + if (unlikely(mlx5e_xsk_get_pool(&priv->channels.params, &priv->xsk, ix))) + return -EBUSY; + + if (unlikely(!mlx5e_xsk_is_pool_sane(pool))) + return -EINVAL; + + err = mlx5e_xsk_map_pool(priv, pool); + if (unlikely(err)) + return err; + + err = mlx5e_xsk_add_pool(&priv->xsk, pool, ix); + if (unlikely(err)) + goto err_unmap_pool; + + mlx5e_build_xsk_param(pool, &xsk); + + if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { + /* XSK objects will be created on open. */ + goto validate_closed; + } + + if (!params->xdp_prog) { + /* XSK objects will be created when an XDP program is set, + * and the channels are reopened. + */ + goto validate_closed; + } + + c = priv->channels.c[ix]; + + err = mlx5e_open_xsk(priv, params, &xsk, pool, c); + if (unlikely(err)) + goto err_remove_pool; + + mlx5e_activate_xsk(c); + + /* Don't wait for WQEs, because the newer xdpsock sample doesn't provide + * any Fill Ring entries at the setup stage. + */ + + err = mlx5e_xsk_redirect_rqt_to_channel(priv, priv->channels.c[ix]); + if (unlikely(err)) + goto err_deactivate; + + return 0; + +err_deactivate: + mlx5e_deactivate_xsk(c); + mlx5e_close_xsk(c); + +err_remove_pool: + mlx5e_xsk_remove_pool(&priv->xsk, ix); + +err_unmap_pool: + mlx5e_xsk_unmap_pool(priv, pool); + + return err; + +validate_closed: + /* Check the configuration in advance, rather than fail at a later stage + * (in mlx5e_xdp_set or on open) and end up with no channels. + */ + if (!mlx5e_validate_xsk_param(params, &xsk, priv->mdev)) { + err = -EINVAL; + goto err_remove_pool; + } + + return 0; +} + +static int mlx5e_xsk_disable_locked(struct mlx5e_priv *priv, u16 ix) +{ + struct xsk_buff_pool *pool = mlx5e_xsk_get_pool(&priv->channels.params, + &priv->xsk, ix); + struct mlx5e_channel *c; + + if (unlikely(!pool)) + return -EINVAL; + + if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) + goto remove_pool; + + /* XSK RQ and SQ are only created if XDP program is set. */ + if (!priv->channels.params.xdp_prog) + goto remove_pool; + + c = priv->channels.c[ix]; + mlx5e_xsk_redirect_rqt_to_drop(priv, ix); + mlx5e_deactivate_xsk(c); + mlx5e_close_xsk(c); + +remove_pool: + mlx5e_xsk_remove_pool(&priv->xsk, ix); + mlx5e_xsk_unmap_pool(priv, pool); + + return 0; +} + +static int mlx5e_xsk_enable_pool(struct mlx5e_priv *priv, struct xsk_buff_pool *pool, + u16 ix) +{ + int err; + + mutex_lock(&priv->state_lock); + err = mlx5e_xsk_enable_locked(priv, pool, ix); + mutex_unlock(&priv->state_lock); + + return err; +} + +static int mlx5e_xsk_disable_pool(struct mlx5e_priv *priv, u16 ix) +{ + int err; + + mutex_lock(&priv->state_lock); + err = mlx5e_xsk_disable_locked(priv, ix); + mutex_unlock(&priv->state_lock); + + return err; +} + +int mlx5e_xsk_setup_pool(struct net_device *dev, struct xsk_buff_pool *pool, u16 qid) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + struct mlx5e_params *params = &priv->channels.params; + u16 ix; + + if (unlikely(!mlx5e_qid_get_ch_if_in_group(params, qid, MLX5E_RQ_GROUP_XSK, &ix))) + return -EINVAL; + + return pool ? mlx5e_xsk_enable_pool(priv, pool, ix) : + mlx5e_xsk_disable_pool(priv, ix); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.h new file mode 100644 index 000000000000..dca0010a0866 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2019-2020, Mellanox Technologies inc. All rights reserved. */ + +#ifndef __MLX5_EN_XSK_POOL_H__ +#define __MLX5_EN_XSK_POOL_H__ + +#include "en.h" + +static inline struct xsk_buff_pool *mlx5e_xsk_get_pool(struct mlx5e_params *params, + struct mlx5e_xsk *xsk, u16 ix) +{ + if (!xsk || !xsk->pools) + return NULL; + + if (unlikely(ix >= params->num_channels)) + return NULL; + + return xsk->pools[ix]; +} + +struct mlx5e_xsk_param; +void mlx5e_build_xsk_param(struct xsk_buff_pool *pool, struct mlx5e_xsk_param *xsk); + +/* .ndo_bpf callback. */ +int mlx5e_xsk_setup_pool(struct net_device *dev, struct xsk_buff_pool *pool, u16 qid); + +#endif /* __MLX5_EN_XSK_POOL_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h index d147b2f13b54..3dd056a11bae 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h @@ -19,10 +19,10 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi, u32 cqe_bcnt); -static inline int mlx5e_xsk_page_alloc_umem(struct mlx5e_rq *rq, +static inline int mlx5e_xsk_page_alloc_pool(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info) { - dma_info->xsk = xsk_buff_alloc(rq->umem); + dma_info->xsk = xsk_buff_alloc(rq->xsk_pool->umem); if (!dma_info->xsk) return -ENOMEM; @@ -38,13 +38,13 @@ static inline int mlx5e_xsk_page_alloc_umem(struct mlx5e_rq *rq, static inline bool mlx5e_xsk_update_rx_wakeup(struct mlx5e_rq *rq, bool alloc_err) { - if (!xsk_umem_uses_need_wakeup(rq->umem)) + if (!xsk_umem_uses_need_wakeup(rq->xsk_pool->umem)) return alloc_err; if (unlikely(alloc_err)) - xsk_set_rx_need_wakeup(rq->umem); + xsk_set_rx_need_wakeup(rq->xsk_pool->umem); else - xsk_clear_rx_need_wakeup(rq->umem); + xsk_clear_rx_need_wakeup(rq->xsk_pool->umem); return false; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c index dd9df519d383..662a1dafeaad 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c @@ -45,7 +45,7 @@ static void mlx5e_build_xsk_cparam(struct mlx5e_priv *priv, } int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params, - struct mlx5e_xsk_param *xsk, struct xdp_umem *umem, + struct mlx5e_xsk_param *xsk, struct xsk_buff_pool *pool, struct mlx5e_channel *c) { struct mlx5e_channel_param *cparam; @@ -64,7 +64,7 @@ int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params, if (unlikely(err)) goto err_free_cparam; - err = mlx5e_open_rq(c, params, &cparam->rq, xsk, umem, &c->xskrq); + err = mlx5e_open_rq(c, params, &cparam->rq, xsk, pool, &c->xskrq); if (unlikely(err)) goto err_close_rx_cq; @@ -72,13 +72,13 @@ int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params, if (unlikely(err)) goto err_close_rq; - /* Create a separate SQ, so that when the UMEM is disabled, we could + /* Create a separate SQ, so that when the buff pool is disabled, we could * close this SQ safely and stop receiving CQEs. In other case, e.g., if - * the XDPSQ was used instead, we might run into trouble when the UMEM + * the XDPSQ was used instead, we might run into trouble when the buff pool * is disabled and then reenabled, but the SQ continues receiving CQEs - * from the old UMEM. + * from the old buff pool. */ - err = mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, umem, &c->xsksq, true); + err = mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, pool, &c->xsksq, true); if (unlikely(err)) goto err_close_tx_cq; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.h index 0dd11b81c046..ca20f1ff5e39 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.h @@ -12,7 +12,7 @@ bool mlx5e_validate_xsk_param(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk, struct mlx5_core_dev *mdev); int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params, - struct mlx5e_xsk_param *xsk, struct xdp_umem *umem, + struct mlx5e_xsk_param *xsk, struct xsk_buff_pool *pool, struct mlx5e_channel *c); void mlx5e_close_xsk(struct mlx5e_channel *c); void mlx5e_activate_xsk(struct mlx5e_channel *c); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c index 4d892f6cecb3..5f9470207bb0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c @@ -2,7 +2,7 @@ /* Copyright (c) 2019 Mellanox Technologies. */ #include "tx.h" -#include "umem.h" +#include "pool.h" #include "en/xdp.h" #include "en/params.h" #include @@ -66,7 +66,7 @@ static void mlx5e_xsk_tx_post_err(struct mlx5e_xdpsq *sq, bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget) { - struct xdp_umem *umem = sq->umem; + struct xsk_buff_pool *pool = sq->xsk_pool; struct mlx5e_xdp_info xdpi; struct mlx5e_xdp_xmit_data xdptxd; bool work_done = true; @@ -87,7 +87,7 @@ bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget) break; } - if (!xsk_umem_consume_tx(umem, &desc)) { + if (!xsk_umem_consume_tx(pool->umem, &desc)) { /* TX will get stuck until something wakes it up by * triggering NAPI. Currently it's expected that the * application calls sendto() if there are consumed, but @@ -96,11 +96,11 @@ bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget) break; } - xdptxd.dma_addr = xsk_buff_raw_get_dma(umem, desc.addr); - xdptxd.data = xsk_buff_raw_get_data(umem, desc.addr); + xdptxd.dma_addr = xsk_buff_raw_get_dma(pool->umem, desc.addr); + xdptxd.data = xsk_buff_raw_get_data(pool->umem, desc.addr); xdptxd.len = desc.len; - xsk_buff_raw_dma_sync_for_device(umem, xdptxd.dma_addr, xdptxd.len); + xsk_buff_raw_dma_sync_for_device(pool->umem, xdptxd.dma_addr, xdptxd.len); ret = INDIRECT_CALL_2(sq->xmit_xdp_frame, mlx5e_xmit_xdp_frame_mpwqe, mlx5e_xmit_xdp_frame, sq, &xdptxd, &xdpi, check_result); @@ -119,7 +119,7 @@ bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget) mlx5e_xdp_mpwqe_complete(sq); mlx5e_xmit_xdp_doorbell(sq); - xsk_umem_consume_tx_done(umem); + xsk_umem_consume_tx_done(pool->umem); } return !(budget && work_done); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h index 39fa0a705856..ddb61d5bc2db 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h @@ -15,13 +15,13 @@ bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget); static inline void mlx5e_xsk_update_tx_wakeup(struct mlx5e_xdpsq *sq) { - if (!xsk_umem_uses_need_wakeup(sq->umem)) + if (!xsk_umem_uses_need_wakeup(sq->xsk_pool->umem)) return; if (sq->pc != sq->cc) - xsk_clear_tx_need_wakeup(sq->umem); + xsk_clear_tx_need_wakeup(sq->xsk_pool->umem); else - xsk_set_tx_need_wakeup(sq->umem); + xsk_set_tx_need_wakeup(sq->xsk_pool->umem); } #endif /* __MLX5_EN_XSK_TX_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.c deleted file mode 100644 index 331ca2b0f8a4..000000000000 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.c +++ /dev/null @@ -1,217 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB -/* Copyright (c) 2019 Mellanox Technologies. */ - -#include -#include "umem.h" -#include "setup.h" -#include "en/params.h" - -static int mlx5e_xsk_map_umem(struct mlx5e_priv *priv, - struct xdp_umem *umem) -{ - struct device *dev = priv->mdev->device; - - return xsk_buff_dma_map(umem, dev, 0); -} - -static void mlx5e_xsk_unmap_umem(struct mlx5e_priv *priv, - struct xdp_umem *umem) -{ - return xsk_buff_dma_unmap(umem, 0); -} - -static int mlx5e_xsk_get_umems(struct mlx5e_xsk *xsk) -{ - if (!xsk->umems) { - xsk->umems = kcalloc(MLX5E_MAX_NUM_CHANNELS, - sizeof(*xsk->umems), GFP_KERNEL); - if (unlikely(!xsk->umems)) - return -ENOMEM; - } - - xsk->refcnt++; - xsk->ever_used = true; - - return 0; -} - -static void mlx5e_xsk_put_umems(struct mlx5e_xsk *xsk) -{ - if (!--xsk->refcnt) { - kfree(xsk->umems); - xsk->umems = NULL; - } -} - -static int mlx5e_xsk_add_umem(struct mlx5e_xsk *xsk, struct xdp_umem *umem, u16 ix) -{ - int err; - - err = mlx5e_xsk_get_umems(xsk); - if (unlikely(err)) - return err; - - xsk->umems[ix] = umem; - return 0; -} - -static void mlx5e_xsk_remove_umem(struct mlx5e_xsk *xsk, u16 ix) -{ - xsk->umems[ix] = NULL; - - mlx5e_xsk_put_umems(xsk); -} - -static bool mlx5e_xsk_is_umem_sane(struct xdp_umem *umem) -{ - return xsk_umem_get_headroom(umem) <= 0xffff && - xsk_umem_get_chunk_size(umem) <= 0xffff; -} - -void mlx5e_build_xsk_param(struct xdp_umem *umem, struct mlx5e_xsk_param *xsk) -{ - xsk->headroom = xsk_umem_get_headroom(umem); - xsk->chunk_size = xsk_umem_get_chunk_size(umem); -} - -static int mlx5e_xsk_enable_locked(struct mlx5e_priv *priv, - struct xdp_umem *umem, u16 ix) -{ - struct mlx5e_params *params = &priv->channels.params; - struct mlx5e_xsk_param xsk; - struct mlx5e_channel *c; - int err; - - if (unlikely(mlx5e_xsk_get_umem(&priv->channels.params, &priv->xsk, ix))) - return -EBUSY; - - if (unlikely(!mlx5e_xsk_is_umem_sane(umem))) - return -EINVAL; - - err = mlx5e_xsk_map_umem(priv, umem); - if (unlikely(err)) - return err; - - err = mlx5e_xsk_add_umem(&priv->xsk, umem, ix); - if (unlikely(err)) - goto err_unmap_umem; - - mlx5e_build_xsk_param(umem, &xsk); - - if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { - /* XSK objects will be created on open. */ - goto validate_closed; - } - - if (!params->xdp_prog) { - /* XSK objects will be created when an XDP program is set, - * and the channels are reopened. - */ - goto validate_closed; - } - - c = priv->channels.c[ix]; - - err = mlx5e_open_xsk(priv, params, &xsk, umem, c); - if (unlikely(err)) - goto err_remove_umem; - - mlx5e_activate_xsk(c); - - /* Don't wait for WQEs, because the newer xdpsock sample doesn't provide - * any Fill Ring entries at the setup stage. - */ - - err = mlx5e_xsk_redirect_rqt_to_channel(priv, priv->channels.c[ix]); - if (unlikely(err)) - goto err_deactivate; - - return 0; - -err_deactivate: - mlx5e_deactivate_xsk(c); - mlx5e_close_xsk(c); - -err_remove_umem: - mlx5e_xsk_remove_umem(&priv->xsk, ix); - -err_unmap_umem: - mlx5e_xsk_unmap_umem(priv, umem); - - return err; - -validate_closed: - /* Check the configuration in advance, rather than fail at a later stage - * (in mlx5e_xdp_set or on open) and end up with no channels. - */ - if (!mlx5e_validate_xsk_param(params, &xsk, priv->mdev)) { - err = -EINVAL; - goto err_remove_umem; - } - - return 0; -} - -static int mlx5e_xsk_disable_locked(struct mlx5e_priv *priv, u16 ix) -{ - struct xdp_umem *umem = mlx5e_xsk_get_umem(&priv->channels.params, - &priv->xsk, ix); - struct mlx5e_channel *c; - - if (unlikely(!umem)) - return -EINVAL; - - if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) - goto remove_umem; - - /* XSK RQ and SQ are only created if XDP program is set. */ - if (!priv->channels.params.xdp_prog) - goto remove_umem; - - c = priv->channels.c[ix]; - mlx5e_xsk_redirect_rqt_to_drop(priv, ix); - mlx5e_deactivate_xsk(c); - mlx5e_close_xsk(c); - -remove_umem: - mlx5e_xsk_remove_umem(&priv->xsk, ix); - mlx5e_xsk_unmap_umem(priv, umem); - - return 0; -} - -static int mlx5e_xsk_enable_umem(struct mlx5e_priv *priv, struct xdp_umem *umem, - u16 ix) -{ - int err; - - mutex_lock(&priv->state_lock); - err = mlx5e_xsk_enable_locked(priv, umem, ix); - mutex_unlock(&priv->state_lock); - - return err; -} - -static int mlx5e_xsk_disable_umem(struct mlx5e_priv *priv, u16 ix) -{ - int err; - - mutex_lock(&priv->state_lock); - err = mlx5e_xsk_disable_locked(priv, ix); - mutex_unlock(&priv->state_lock); - - return err; -} - -int mlx5e_xsk_setup_umem(struct net_device *dev, struct xdp_umem *umem, u16 qid) -{ - struct mlx5e_priv *priv = netdev_priv(dev); - struct mlx5e_params *params = &priv->channels.params; - u16 ix; - - if (unlikely(!mlx5e_qid_get_ch_if_in_group(params, qid, MLX5E_RQ_GROUP_XSK, &ix))) - return -EINVAL; - - return umem ? mlx5e_xsk_enable_umem(priv, umem, ix) : - mlx5e_xsk_disable_umem(priv, ix); -} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.h deleted file mode 100644 index bada94973586..000000000000 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.h +++ /dev/null @@ -1,29 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ -/* Copyright (c) 2019 Mellanox Technologies. */ - -#ifndef __MLX5_EN_XSK_UMEM_H__ -#define __MLX5_EN_XSK_UMEM_H__ - -#include "en.h" - -static inline struct xdp_umem *mlx5e_xsk_get_umem(struct mlx5e_params *params, - struct mlx5e_xsk *xsk, u16 ix) -{ - if (!xsk || !xsk->umems) - return NULL; - - if (unlikely(ix >= params->num_channels)) - return NULL; - - return xsk->umems[ix]; -} - -struct mlx5e_xsk_param; -void mlx5e_build_xsk_param(struct xdp_umem *umem, struct mlx5e_xsk_param *xsk); - -/* .ndo_bpf callback. */ -int mlx5e_xsk_setup_umem(struct net_device *dev, struct xdp_umem *umem, u16 qid); - -int mlx5e_xsk_resize_reuseq(struct xdp_umem *umem, u32 nentries); - -#endif /* __MLX5_EN_XSK_UMEM_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 08270987c506..5cb1e4839eb7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -32,7 +32,7 @@ #include "en.h" #include "en/port.h" -#include "en/xsk/umem.h" +#include "en/xsk/pool.h" #include "lib/clock.h" void mlx5e_ethtool_get_drvinfo(struct mlx5e_priv *priv, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c index 83c9b2bbc4af..b416a8ee2eed 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c @@ -33,7 +33,7 @@ #include #include "en.h" #include "en/params.h" -#include "en/xsk/umem.h" +#include "en/xsk/pool.h" struct mlx5e_ethtool_rule { struct list_head list; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index aebcf73f8546..f598683dc906 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -57,7 +57,7 @@ #include "en/monitor_stats.h" #include "en/health.h" #include "en/params.h" -#include "en/xsk/umem.h" +#include "en/xsk/pool.h" #include "en/xsk/setup.h" #include "en/xsk/rx.h" #include "en/xsk/tx.h" @@ -363,7 +363,7 @@ static void mlx5e_rq_err_cqe_work(struct work_struct *recover_work) static int mlx5e_alloc_rq(struct mlx5e_channel *c, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk, - struct xdp_umem *umem, + struct xsk_buff_pool *xsk_pool, struct mlx5e_rq_param *rqp, struct mlx5e_rq *rq) { @@ -389,9 +389,9 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, rq->mdev = mdev; rq->hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu); rq->xdpsq = &c->rq_xdpsq; - rq->umem = umem; + rq->xsk_pool = xsk_pool; - if (rq->umem) + if (rq->xsk_pool) rq->stats = &c->priv->channel_stats[c->ix].xskrq; else rq->stats = &c->priv->channel_stats[c->ix].rq; @@ -477,7 +477,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, if (xsk) { err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq, MEM_TYPE_XSK_BUFF_POOL, NULL); - xsk_buff_set_rxq_info(rq->umem, &rq->xdp_rxq); + xsk_buff_set_rxq_info(rq->xsk_pool->umem, &rq->xdp_rxq); } else { /* Create a page_pool and register it with rxq */ pp_params.order = 0; @@ -816,11 +816,11 @@ void mlx5e_free_rx_descs(struct mlx5e_rq *rq) int mlx5e_open_rq(struct mlx5e_channel *c, struct mlx5e_params *params, struct mlx5e_rq_param *param, struct mlx5e_xsk_param *xsk, - struct xdp_umem *umem, struct mlx5e_rq *rq) + struct xsk_buff_pool *xsk_pool, struct mlx5e_rq *rq) { int err; - err = mlx5e_alloc_rq(c, params, xsk, umem, param, rq); + err = mlx5e_alloc_rq(c, params, xsk, xsk_pool, param, rq); if (err) return err; @@ -925,7 +925,7 @@ static int mlx5e_alloc_xdpsq_db(struct mlx5e_xdpsq *sq, int numa) static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params, - struct xdp_umem *umem, + struct xsk_buff_pool *xsk_pool, struct mlx5e_sq_param *param, struct mlx5e_xdpsq *sq, bool is_redirect) @@ -941,9 +941,9 @@ static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c, sq->uar_map = mdev->mlx5e_res.bfreg.map; sq->min_inline_mode = params->tx_min_inline_mode; sq->hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu); - sq->umem = umem; + sq->xsk_pool = xsk_pool; - sq->stats = sq->umem ? + sq->stats = sq->xsk_pool ? &c->priv->channel_stats[c->ix].xsksq : is_redirect ? &c->priv->channel_stats[c->ix].xdpsq : @@ -1408,13 +1408,13 @@ void mlx5e_close_icosq(struct mlx5e_icosq *sq) } int mlx5e_open_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params, - struct mlx5e_sq_param *param, struct xdp_umem *umem, + struct mlx5e_sq_param *param, struct xsk_buff_pool *xsk_pool, struct mlx5e_xdpsq *sq, bool is_redirect) { struct mlx5e_create_sq_param csp = {}; int err; - err = mlx5e_alloc_xdpsq(c, params, umem, param, sq, is_redirect); + err = mlx5e_alloc_xdpsq(c, params, xsk_pool, param, sq, is_redirect); if (err) return err; @@ -1907,7 +1907,7 @@ static u8 mlx5e_enumerate_lag_port(struct mlx5_core_dev *mdev, int ix) static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, struct mlx5e_params *params, struct mlx5e_channel_param *cparam, - struct xdp_umem *umem, + struct xsk_buff_pool *xsk_pool, struct mlx5e_channel **cp) { int cpu = cpumask_first(mlx5_comp_irq_get_affinity_mask(priv->mdev, ix)); @@ -1946,9 +1946,9 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, if (unlikely(err)) goto err_napi_del; - if (umem) { - mlx5e_build_xsk_param(umem, &xsk); - err = mlx5e_open_xsk(priv, params, &xsk, umem, c); + if (xsk_pool) { + mlx5e_build_xsk_param(xsk_pool, &xsk); + err = mlx5e_open_xsk(priv, params, &xsk, xsk_pool, c); if (unlikely(err)) goto err_close_queues; } @@ -2309,12 +2309,12 @@ int mlx5e_open_channels(struct mlx5e_priv *priv, mlx5e_build_channel_param(priv, &chs->params, cparam); for (i = 0; i < chs->num; i++) { - struct xdp_umem *umem = NULL; + struct xsk_buff_pool *xsk_pool = NULL; if (chs->params.xdp_prog) - umem = mlx5e_xsk_get_umem(&chs->params, chs->params.xsk, i); + xsk_pool = mlx5e_xsk_get_pool(&chs->params, chs->params.xsk, i); - err = mlx5e_open_channel(priv, i, &chs->params, cparam, umem, &chs->c[i]); + err = mlx5e_open_channel(priv, i, &chs->params, cparam, xsk_pool, &chs->c[i]); if (err) goto err_close_channels; } @@ -3892,13 +3892,14 @@ static bool mlx5e_xsk_validate_mtu(struct net_device *netdev, u16 ix; for (ix = 0; ix < chs->params.num_channels; ix++) { - struct xdp_umem *umem = mlx5e_xsk_get_umem(&chs->params, chs->params.xsk, ix); + struct xsk_buff_pool *xsk_pool = + mlx5e_xsk_get_pool(&chs->params, chs->params.xsk, ix); struct mlx5e_xsk_param xsk; - if (!umem) + if (!xsk_pool) continue; - mlx5e_build_xsk_param(umem, &xsk); + mlx5e_build_xsk_param(xsk_pool, &xsk); if (!mlx5e_validate_xsk_param(new_params, &xsk, mdev)) { u32 hr = mlx5e_get_linear_rq_headroom(new_params, &xsk); @@ -4423,8 +4424,8 @@ static int mlx5e_xdp(struct net_device *dev, struct netdev_bpf *xdp) switch (xdp->command) { case XDP_SETUP_PROG: return mlx5e_xdp_set(dev, xdp->prog); - case XDP_SETUP_XSK_UMEM: - return mlx5e_xsk_setup_umem(dev, xdp->xsk.umem, + case XDP_SETUP_XSK_POOL: + return mlx5e_xsk_setup_pool(dev, xdp->xsk.pool, xdp->xsk.queue_id); default: return -EINVAL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 65828af120b7..b33f9f21848f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -281,8 +281,8 @@ static inline int mlx5e_page_alloc_pool(struct mlx5e_rq *rq, static inline int mlx5e_page_alloc(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info) { - if (rq->umem) - return mlx5e_xsk_page_alloc_umem(rq, dma_info); + if (rq->xsk_pool) + return mlx5e_xsk_page_alloc_pool(rq, dma_info); else return mlx5e_page_alloc_pool(rq, dma_info); } @@ -313,7 +313,7 @@ static inline void mlx5e_page_release(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info, bool recycle) { - if (rq->umem) + if (rq->xsk_pool) /* The `recycle` parameter is ignored, and the page is always * put into the Reuse Ring, because there is no way to return * the page to the userspace when the interface goes down. @@ -400,14 +400,14 @@ static int mlx5e_alloc_rx_wqes(struct mlx5e_rq *rq, u16 ix, u8 wqe_bulk) int err; int i; - if (rq->umem) { + if (rq->xsk_pool) { int pages_desired = wqe_bulk << rq->wqe.info.log_num_frags; /* Check in advance that we have enough frames, instead of * allocating one-by-one, failing and moving frames to the * Reuse Ring. */ - if (unlikely(!xsk_buff_can_alloc(rq->umem, pages_desired))) + if (unlikely(!xsk_buff_can_alloc(rq->xsk_pool->umem, pages_desired))) return -ENOMEM; } @@ -505,8 +505,8 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) /* Check in advance that we have enough frames, instead of allocating * one-by-one, failing and moving frames to the Reuse Ring. */ - if (rq->umem && - unlikely(!xsk_buff_can_alloc(rq->umem, MLX5_MPWRQ_PAGES_PER_WQE))) { + if (rq->xsk_pool && + unlikely(!xsk_buff_can_alloc(rq->xsk_pool->umem, MLX5_MPWRQ_PAGES_PER_WQE))) { err = -ENOMEM; goto err; } @@ -754,7 +754,7 @@ INDIRECT_CALLABLE_SCOPE bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq) * the driver when it refills the Fill Ring. * 2. Otherwise, busy poll by rescheduling the NAPI poll. */ - if (unlikely(alloc_err == -ENOMEM && rq->umem)) + if (unlikely(alloc_err == -ENOMEM && rq->xsk_pool)) return true; return false; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b0e303f6603f..d088dd866825 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -618,7 +618,7 @@ struct netdev_queue { /* Subordinate device that the queue has been assigned to */ struct net_device *sb_dev; #ifdef CONFIG_XDP_SOCKETS - struct xdp_umem *umem; + struct xsk_buff_pool *pool; #endif /* * write-mostly part @@ -751,7 +751,7 @@ struct netdev_rx_queue { struct net_device *dev; struct xdp_rxq_info xdp_rxq; #ifdef CONFIG_XDP_SOCKETS - struct xdp_umem *umem; + struct xsk_buff_pool *pool; #endif } ____cacheline_aligned_in_smp; @@ -879,7 +879,7 @@ enum bpf_netdev_command { /* BPF program for offload callbacks, invoked at program load time. */ BPF_OFFLOAD_MAP_ALLOC, BPF_OFFLOAD_MAP_FREE, - XDP_SETUP_XSK_UMEM, + XDP_SETUP_XSK_POOL, }; struct bpf_prog_offload_ops; @@ -913,9 +913,9 @@ struct netdev_bpf { struct { struct bpf_offloaded_map *offmap; }; - /* XDP_SETUP_XSK_UMEM */ + /* XDP_SETUP_XSK_POOL */ struct { - struct xdp_umem *umem; + struct xsk_buff_pool *pool; u16 queue_id; } xsk; }; diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index ccf848f7efa4..5dc8d3c0dcd4 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -14,7 +14,8 @@ void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries); bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc); void xsk_umem_consume_tx_done(struct xdp_umem *umem); -struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev, u16 queue_id); +struct xsk_buff_pool *xdp_get_xsk_pool_from_qid(struct net_device *dev, + u16 queue_id); void xsk_set_rx_need_wakeup(struct xdp_umem *umem); void xsk_set_tx_need_wakeup(struct xdp_umem *umem); void xsk_clear_rx_need_wakeup(struct xdp_umem *umem); @@ -125,8 +126,8 @@ static inline void xsk_umem_consume_tx_done(struct xdp_umem *umem) { } -static inline struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev, - u16 queue_id) +static inline struct xsk_buff_pool * +xdp_get_xsk_pool_from_qid(struct net_device *dev, u16 queue_id) { return NULL; } diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index 6842990e2712..f851b0a68324 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -13,6 +13,7 @@ struct xsk_buff_pool; struct xdp_rxq_info; struct xsk_queue; struct xdp_desc; +struct xdp_umem; struct device; struct page; @@ -42,13 +43,14 @@ struct xsk_buff_pool { u32 frame_len; bool dma_need_sync; bool unaligned; + struct xdp_umem *umem; void *addrs; struct device *dev; struct xdp_buff_xsk *free_heads[]; }; /* AF_XDP core. */ -struct xsk_buff_pool *xp_create(struct page **pages, u32 nr_pages, u32 chunks, +struct xsk_buff_pool *xp_create(struct xdp_umem *umem, u32 chunks, u32 chunk_size, u32 headroom, u64 size, bool unaligned); void xp_set_fq(struct xsk_buff_pool *pool, struct xsk_queue *fq); diff --git a/net/ethtool/channels.c b/net/ethtool/channels.c index 9ef54cdcf662..78d990bfb90f 100644 --- a/net/ethtool/channels.c +++ b/net/ethtool/channels.c @@ -223,7 +223,7 @@ int ethnl_set_channels(struct sk_buff *skb, struct genl_info *info) from_channel = channels.combined_count + min(channels.rx_count, channels.tx_count); for (i = from_channel; i < old_total; i++) - if (xdp_get_umem_from_qid(dev, i)) { + if (xdp_get_xsk_pool_from_qid(dev, i)) { GENL_SET_ERR_MSG(info, "requested channel counts are too low for existing zerocopy AF_XDP sockets"); return -EINVAL; } diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 441794e0034f..2e6a678df741 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -1706,7 +1706,7 @@ static noinline_for_stack int ethtool_set_channels(struct net_device *dev, min(channels.rx_count, channels.tx_count); to_channel = curr.combined_count + max(curr.rx_count, curr.tx_count); for (i = from_channel; i < to_channel; i++) - if (xdp_get_umem_from_qid(dev, i)) + if (xdp_get_xsk_pool_from_qid(dev, i)) return -EINVAL; ret = dev->ethtool_ops->set_channels(dev, &channels); diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index e97db37354e4..0b5f3b04216f 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -51,8 +51,9 @@ void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs) * not know if the device has more tx queues than rx, or the opposite. * This might also change during run time. */ -static int xdp_reg_umem_at_qid(struct net_device *dev, struct xdp_umem *umem, - u16 queue_id) +static int xdp_reg_xsk_pool_at_qid(struct net_device *dev, + struct xsk_buff_pool *pool, + u16 queue_id) { if (queue_id >= max_t(unsigned int, dev->real_num_rx_queues, @@ -60,31 +61,31 @@ static int xdp_reg_umem_at_qid(struct net_device *dev, struct xdp_umem *umem, return -EINVAL; if (queue_id < dev->real_num_rx_queues) - dev->_rx[queue_id].umem = umem; + dev->_rx[queue_id].pool = pool; if (queue_id < dev->real_num_tx_queues) - dev->_tx[queue_id].umem = umem; + dev->_tx[queue_id].pool = pool; return 0; } -struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev, - u16 queue_id) +struct xsk_buff_pool *xdp_get_xsk_pool_from_qid(struct net_device *dev, + u16 queue_id) { if (queue_id < dev->real_num_rx_queues) - return dev->_rx[queue_id].umem; + return dev->_rx[queue_id].pool; if (queue_id < dev->real_num_tx_queues) - return dev->_tx[queue_id].umem; + return dev->_tx[queue_id].pool; return NULL; } -EXPORT_SYMBOL(xdp_get_umem_from_qid); +EXPORT_SYMBOL(xdp_get_xsk_pool_from_qid); -static void xdp_clear_umem_at_qid(struct net_device *dev, u16 queue_id) +static void xdp_clear_xsk_pool_at_qid(struct net_device *dev, u16 queue_id) { if (queue_id < dev->real_num_rx_queues) - dev->_rx[queue_id].umem = NULL; + dev->_rx[queue_id].pool = NULL; if (queue_id < dev->real_num_tx_queues) - dev->_tx[queue_id].umem = NULL; + dev->_tx[queue_id].pool = NULL; } int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, @@ -102,10 +103,10 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, if (force_zc && force_copy) return -EINVAL; - if (xdp_get_umem_from_qid(dev, queue_id)) + if (xdp_get_xsk_pool_from_qid(dev, queue_id)) return -EBUSY; - err = xdp_reg_umem_at_qid(dev, umem, queue_id); + err = xdp_reg_xsk_pool_at_qid(dev, umem->pool, queue_id); if (err) return err; @@ -132,8 +133,8 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, goto err_unreg_umem; } - bpf.command = XDP_SETUP_XSK_UMEM; - bpf.xsk.umem = umem; + bpf.command = XDP_SETUP_XSK_POOL; + bpf.xsk.pool = umem->pool; bpf.xsk.queue_id = queue_id; err = dev->netdev_ops->ndo_bpf(dev, &bpf); @@ -147,7 +148,7 @@ err_unreg_umem: if (!force_zc) err = 0; /* fallback to copy mode */ if (err) - xdp_clear_umem_at_qid(dev, queue_id); + xdp_clear_xsk_pool_at_qid(dev, queue_id); return err; } @@ -162,8 +163,8 @@ void xdp_umem_clear_dev(struct xdp_umem *umem) return; if (umem->zc) { - bpf.command = XDP_SETUP_XSK_UMEM; - bpf.xsk.umem = NULL; + bpf.command = XDP_SETUP_XSK_POOL; + bpf.xsk.pool = NULL; bpf.xsk.queue_id = umem->queue_id; err = umem->dev->netdev_ops->ndo_bpf(umem->dev, &bpf); @@ -172,7 +173,7 @@ void xdp_umem_clear_dev(struct xdp_umem *umem) WARN(1, "failed to disable umem!\n"); } - xdp_clear_umem_at_qid(umem->dev, umem->queue_id); + xdp_clear_xsk_pool_at_qid(umem->dev, umem->queue_id); dev_put(umem->dev); umem->dev = NULL; @@ -373,8 +374,8 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) if (err) goto out_account; - umem->pool = xp_create(umem->pgs, umem->npgs, chunks, chunk_size, - headroom, size, unaligned_chunks); + umem->pool = xp_create(umem, chunks, chunk_size, headroom, size, + unaligned_chunks); if (!umem->pool) { err = -ENOMEM; goto out_pin; diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index a2044c245215..f3df3cba3d73 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -29,7 +29,7 @@ void xp_destroy(struct xsk_buff_pool *pool) kvfree(pool); } -struct xsk_buff_pool *xp_create(struct page **pages, u32 nr_pages, u32 chunks, +struct xsk_buff_pool *xp_create(struct xdp_umem *umem, u32 chunks, u32 chunk_size, u32 headroom, u64 size, bool unaligned) { @@ -54,6 +54,7 @@ struct xsk_buff_pool *xp_create(struct page **pages, u32 nr_pages, u32 chunks, pool->chunk_size = chunk_size; pool->unaligned = unaligned; pool->frame_len = chunk_size - headroom - XDP_PACKET_HEADROOM; + pool->umem = umem; INIT_LIST_HEAD(&pool->free_list); for (i = 0; i < pool->free_heads_cnt; i++) { @@ -63,7 +64,7 @@ struct xsk_buff_pool *xp_create(struct page **pages, u32 nr_pages, u32 chunks, pool->free_heads[i] = xskb; } - err = xp_addr_map(pool, pages, nr_pages); + err = xp_addr_map(pool, umem->pgs, umem->npgs); if (!err) return pool; -- cgit v1.2.3 From c4655761d3cf62bf5f86650e79349c1bfa5c6285 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Fri, 28 Aug 2020 10:26:16 +0200 Subject: xsk: i40e: ice: ixgbe: mlx5: Rename xsk zero-copy driver interfaces MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Rename the AF_XDP zero-copy driver interface functions to better reflect what they do after the replacement of umems with buffer pools in the previous commit. Mostly it is about replacing the umem name from the function names with xsk_buff and also have them take the a buffer pool pointer instead of a umem. The various ring functions have also been renamed in the process so that they have the same naming convention as the internal functions in xsk_queue.h. This so that it will be clearer what they do and also for consistency. Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Acked-by: Björn Töpel Link: https://lore.kernel.org/bpf/1598603189-32145-3-git-send-email-magnus.karlsson@intel.com --- drivers/net/ethernet/intel/i40e/i40e_main.c | 6 +- drivers/net/ethernet/intel/i40e/i40e_xsk.c | 34 +++--- drivers/net/ethernet/intel/ice/ice_base.c | 6 +- drivers/net/ethernet/intel/ice/ice_xsk.c | 28 ++--- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 6 +- drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c | 32 +++--- drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c | 4 +- .../net/ethernet/mellanox/mlx5/core/en/xsk/pool.c | 12 +-- .../net/ethernet/mellanox/mlx5/core/en/xsk/rx.h | 8 +- .../net/ethernet/mellanox/mlx5/core/en/xsk/tx.c | 10 +- .../net/ethernet/mellanox/mlx5/core/en/xsk/tx.h | 6 +- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 4 +- include/net/xdp_sock.h | 1 + include/net/xdp_sock_drv.h | 114 +++++++++++---------- net/ethtool/channels.c | 2 +- net/ethtool/ioctl.c | 2 +- net/xdp/xdp_umem.c | 24 ++--- net/xdp/xsk.c | 45 ++++---- 19 files changed, 179 insertions(+), 167 deletions(-) (limited to 'include/net') diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index cbf2a4454499..05c6d3ea11e6 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -3138,7 +3138,7 @@ static struct xsk_buff_pool *i40e_xsk_pool(struct i40e_ring *ring) if (!xdp_on || !test_bit(qid, ring->vsi->af_xdp_zc_qps)) return NULL; - return xdp_get_xsk_pool_from_qid(ring->vsi->netdev, qid); + return xsk_get_pool_from_qid(ring->vsi->netdev, qid); } /** @@ -3286,7 +3286,7 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) if (ret) return ret; ring->rx_buf_len = - xsk_umem_get_rx_frame_size(ring->xsk_pool->umem); + xsk_pool_get_rx_frame_size(ring->xsk_pool); /* For AF_XDP ZC, we disallow packets to span on * multiple buffers, thus letting us skip that * handling in the fast-path. @@ -3370,7 +3370,7 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) writel(0, ring->tail); if (ring->xsk_pool) { - xsk_buff_set_rxq_info(ring->xsk_pool->umem, &ring->xdp_rxq); + xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq); ok = i40e_alloc_rx_buffers_zc(ring, I40E_DESC_UNUSED(ring)); } else { ok = !i40e_alloc_rx_buffers(ring, I40E_DESC_UNUSED(ring)); diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 00e9fe6394f2..95b9a7e280fa 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -55,8 +55,7 @@ static int i40e_xsk_pool_enable(struct i40e_vsi *vsi, qid >= netdev->real_num_tx_queues) return -EINVAL; - err = xsk_buff_dma_map(pool->umem, &vsi->back->pdev->dev, - I40E_RX_DMA_ATTR); + err = xsk_pool_dma_map(pool, &vsi->back->pdev->dev, I40E_RX_DMA_ATTR); if (err) return err; @@ -97,7 +96,7 @@ static int i40e_xsk_pool_disable(struct i40e_vsi *vsi, u16 qid) bool if_running; int err; - pool = xdp_get_xsk_pool_from_qid(netdev, qid); + pool = xsk_get_pool_from_qid(netdev, qid); if (!pool) return -EINVAL; @@ -110,7 +109,7 @@ static int i40e_xsk_pool_disable(struct i40e_vsi *vsi, u16 qid) } clear_bit(qid, vsi->af_xdp_zc_qps); - xsk_buff_dma_unmap(pool->umem, I40E_RX_DMA_ATTR); + xsk_pool_dma_unmap(pool, I40E_RX_DMA_ATTR); if (if_running) { err = i40e_queue_pair_enable(vsi, qid); @@ -196,7 +195,7 @@ bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count) rx_desc = I40E_RX_DESC(rx_ring, ntu); bi = i40e_rx_bi(rx_ring, ntu); do { - xdp = xsk_buff_alloc(rx_ring->xsk_pool->umem); + xdp = xsk_buff_alloc(rx_ring->xsk_pool); if (!xdp) { ok = false; goto no_buffers; @@ -363,11 +362,11 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) i40e_finalize_xdp_rx(rx_ring, xdp_xmit); i40e_update_rx_stats(rx_ring, total_rx_bytes, total_rx_packets); - if (xsk_umem_uses_need_wakeup(rx_ring->xsk_pool->umem)) { + if (xsk_uses_need_wakeup(rx_ring->xsk_pool)) { if (failure || rx_ring->next_to_clean == rx_ring->next_to_use) - xsk_set_rx_need_wakeup(rx_ring->xsk_pool->umem); + xsk_set_rx_need_wakeup(rx_ring->xsk_pool); else - xsk_clear_rx_need_wakeup(rx_ring->xsk_pool->umem); + xsk_clear_rx_need_wakeup(rx_ring->xsk_pool); return (int)total_rx_packets; } @@ -390,12 +389,11 @@ static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget) dma_addr_t dma; while (budget-- > 0) { - if (!xsk_umem_consume_tx(xdp_ring->xsk_pool->umem, &desc)) + if (!xsk_tx_peek_desc(xdp_ring->xsk_pool, &desc)) break; - dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool->umem, - desc.addr); - xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool->umem, dma, + dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc.addr); + xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, desc.len); tx_bi = &xdp_ring->tx_bi[xdp_ring->next_to_use]; @@ -422,7 +420,7 @@ static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget) I40E_TXD_QW1_CMD_SHIFT); i40e_xdp_ring_update_tail(xdp_ring); - xsk_umem_consume_tx_done(xdp_ring->xsk_pool->umem); + xsk_tx_release(xdp_ring->xsk_pool); i40e_update_tx_stats(xdp_ring, sent_frames, total_bytes); } @@ -494,13 +492,13 @@ skip: tx_ring->next_to_clean -= tx_ring->count; if (xsk_frames) - xsk_umem_complete_tx(bp->umem, xsk_frames); + xsk_tx_completed(bp, xsk_frames); i40e_arm_wb(tx_ring, vsi, completed_frames); out_xmit: - if (xsk_umem_uses_need_wakeup(tx_ring->xsk_pool->umem)) - xsk_set_tx_need_wakeup(tx_ring->xsk_pool->umem); + if (xsk_uses_need_wakeup(tx_ring->xsk_pool)) + xsk_set_tx_need_wakeup(tx_ring->xsk_pool); return i40e_xmit_zc(tx_ring, I40E_DESC_UNUSED(tx_ring)); } @@ -591,7 +589,7 @@ void i40e_xsk_clean_tx_ring(struct i40e_ring *tx_ring) } if (xsk_frames) - xsk_umem_complete_tx(bp->umem, xsk_frames); + xsk_tx_completed(bp, xsk_frames); } /** @@ -607,7 +605,7 @@ bool i40e_xsk_any_rx_ring_enabled(struct i40e_vsi *vsi) int i; for (i = 0; i < vsi->num_queue_pairs; i++) { - if (xdp_get_xsk_pool_from_qid(netdev, i)) + if (xsk_get_pool_from_qid(netdev, i)) return true; } diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index 3c92448e2554..fe4320e2d1f2 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -313,7 +313,7 @@ int ice_setup_rx_ctx(struct ice_ring *ring) xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq); ring->rx_buf_len = - xsk_umem_get_rx_frame_size(ring->xsk_pool->umem); + xsk_pool_get_rx_frame_size(ring->xsk_pool); /* For AF_XDP ZC, we disallow packets to span on * multiple buffers, thus letting us skip that * handling in the fast-path. @@ -324,7 +324,7 @@ int ice_setup_rx_ctx(struct ice_ring *ring) NULL); if (err) return err; - xsk_buff_set_rxq_info(ring->xsk_pool->umem, &ring->xdp_rxq); + xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq); dev_info(dev, "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n", ring->q_index); @@ -418,7 +418,7 @@ int ice_setup_rx_ctx(struct ice_ring *ring) writel(0, ring->tail); if (ring->xsk_pool) { - if (!xsk_buff_can_alloc(ring->xsk_pool->umem, num_bufs)) { + if (!xsk_buff_can_alloc(ring->xsk_pool, num_bufs)) { dev_warn(dev, "XSK buffer pool does not provide enough addresses to fill %d buffers on Rx ring %d\n", num_bufs, ring->q_index); dev_warn(dev, "Change Rx ring/fill queue size to avoid performance issues\n"); diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 8b70e8c5bc3a..dffef377c5cb 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -311,7 +311,7 @@ static int ice_xsk_pool_disable(struct ice_vsi *vsi, u16 qid) !vsi->xsk_pools[qid]) return -EINVAL; - xsk_buff_dma_unmap(vsi->xsk_pools[qid]->umem, ICE_RX_DMA_ATTR); + xsk_pool_dma_unmap(vsi->xsk_pools[qid], ICE_RX_DMA_ATTR); ice_xsk_remove_pool(vsi, qid); return 0; @@ -348,7 +348,7 @@ ice_xsk_pool_enable(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid) vsi->xsk_pools[qid] = pool; vsi->num_xsk_pools_used++; - err = xsk_buff_dma_map(vsi->xsk_pools[qid]->umem, ice_pf_to_dev(vsi->back), + err = xsk_pool_dma_map(vsi->xsk_pools[qid], ice_pf_to_dev(vsi->back), ICE_RX_DMA_ATTR); if (err) return err; @@ -425,7 +425,7 @@ bool ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, u16 count) rx_buf = &rx_ring->rx_buf[ntu]; do { - rx_buf->xdp = xsk_buff_alloc(rx_ring->xsk_pool->umem); + rx_buf->xdp = xsk_buff_alloc(rx_ring->xsk_pool); if (!rx_buf->xdp) { ret = true; break; @@ -645,11 +645,11 @@ int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget) ice_finalize_xdp_rx(rx_ring, xdp_xmit); ice_update_rx_ring_stats(rx_ring, total_rx_packets, total_rx_bytes); - if (xsk_umem_uses_need_wakeup(rx_ring->xsk_pool->umem)) { + if (xsk_uses_need_wakeup(rx_ring->xsk_pool)) { if (failure || rx_ring->next_to_clean == rx_ring->next_to_use) - xsk_set_rx_need_wakeup(rx_ring->xsk_pool->umem); + xsk_set_rx_need_wakeup(rx_ring->xsk_pool); else - xsk_clear_rx_need_wakeup(rx_ring->xsk_pool->umem); + xsk_clear_rx_need_wakeup(rx_ring->xsk_pool); return (int)total_rx_packets; } @@ -682,11 +682,11 @@ static bool ice_xmit_zc(struct ice_ring *xdp_ring, int budget) tx_buf = &xdp_ring->tx_buf[xdp_ring->next_to_use]; - if (!xsk_umem_consume_tx(xdp_ring->xsk_pool->umem, &desc)) + if (!xsk_tx_peek_desc(xdp_ring->xsk_pool, &desc)) break; - dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool->umem, desc.addr); - xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool->umem, dma, + dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc.addr); + xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, desc.len); tx_buf->bytecount = desc.len; @@ -703,7 +703,7 @@ static bool ice_xmit_zc(struct ice_ring *xdp_ring, int budget) if (tx_desc) { ice_xdp_ring_update_tail(xdp_ring); - xsk_umem_consume_tx_done(xdp_ring->xsk_pool->umem); + xsk_tx_release(xdp_ring->xsk_pool); } return budget > 0 && work_done; @@ -777,10 +777,10 @@ bool ice_clean_tx_irq_zc(struct ice_ring *xdp_ring, int budget) xdp_ring->next_to_clean = ntc; if (xsk_frames) - xsk_umem_complete_tx(xdp_ring->xsk_pool->umem, xsk_frames); + xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames); - if (xsk_umem_uses_need_wakeup(xdp_ring->xsk_pool->umem)) - xsk_set_tx_need_wakeup(xdp_ring->xsk_pool->umem); + if (xsk_uses_need_wakeup(xdp_ring->xsk_pool)) + xsk_set_tx_need_wakeup(xdp_ring->xsk_pool); ice_update_tx_ring_stats(xdp_ring, total_packets, total_bytes); xmit_done = ice_xmit_zc(xdp_ring, ICE_DFLT_IRQ_WORK); @@ -896,5 +896,5 @@ void ice_xsk_clean_xdp_ring(struct ice_ring *xdp_ring) } if (xsk_frames) - xsk_umem_complete_tx(xdp_ring->xsk_pool->umem, xsk_frames); + xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames); } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index c498465b3000..c4d41f8aad4a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -3714,7 +3714,7 @@ static void ixgbe_configure_srrctl(struct ixgbe_adapter *adapter, /* configure the packet buffer length */ if (rx_ring->xsk_pool) { - u32 xsk_buf_len = xsk_umem_get_rx_frame_size(rx_ring->xsk_pool->umem); + u32 xsk_buf_len = xsk_pool_get_rx_frame_size(rx_ring->xsk_pool); /* If the MAC support setting RXDCTL.RLPML, the * SRRCTL[n].BSIZEPKT is set to PAGE_SIZE and @@ -4064,7 +4064,7 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter, WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, MEM_TYPE_XSK_BUFF_POOL, NULL)); - xsk_buff_set_rxq_info(ring->xsk_pool->umem, &ring->xdp_rxq); + xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq); } else { WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, MEM_TYPE_PAGE_SHARED, NULL)); @@ -4120,7 +4120,7 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter, } if (ring->xsk_pool && hw->mac.type != ixgbe_mac_82599EB) { - u32 xsk_buf_len = xsk_umem_get_rx_frame_size(ring->xsk_pool->umem); + u32 xsk_buf_len = xsk_pool_get_rx_frame_size(ring->xsk_pool); rxdctl &= ~(IXGBE_RXDCTL_RLPMLMASK | IXGBE_RXDCTL_RLPML_EN); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c index 8ad954fcdc38..6af34da45b8d 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c @@ -17,7 +17,7 @@ struct xsk_buff_pool *ixgbe_xsk_pool(struct ixgbe_adapter *adapter, if (!xdp_on || !test_bit(qid, adapter->af_xdp_zc_qps)) return NULL; - return xdp_get_xsk_pool_from_qid(adapter->netdev, qid); + return xsk_get_pool_from_qid(adapter->netdev, qid); } static int ixgbe_xsk_pool_enable(struct ixgbe_adapter *adapter, @@ -35,7 +35,7 @@ static int ixgbe_xsk_pool_enable(struct ixgbe_adapter *adapter, qid >= netdev->real_num_tx_queues) return -EINVAL; - err = xsk_buff_dma_map(pool->umem, &adapter->pdev->dev, IXGBE_RX_DMA_ATTR); + err = xsk_pool_dma_map(pool, &adapter->pdev->dev, IXGBE_RX_DMA_ATTR); if (err) return err; @@ -64,7 +64,7 @@ static int ixgbe_xsk_pool_disable(struct ixgbe_adapter *adapter, u16 qid) struct xsk_buff_pool *pool; bool if_running; - pool = xdp_get_xsk_pool_from_qid(adapter->netdev, qid); + pool = xsk_get_pool_from_qid(adapter->netdev, qid); if (!pool) return -EINVAL; @@ -75,7 +75,7 @@ static int ixgbe_xsk_pool_disable(struct ixgbe_adapter *adapter, u16 qid) ixgbe_txrx_ring_disable(adapter, qid); clear_bit(qid, adapter->af_xdp_zc_qps); - xsk_buff_dma_unmap(pool->umem, IXGBE_RX_DMA_ATTR); + xsk_pool_dma_unmap(pool, IXGBE_RX_DMA_ATTR); if (if_running) ixgbe_txrx_ring_enable(adapter, qid); @@ -150,7 +150,7 @@ bool ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 count) i -= rx_ring->count; do { - bi->xdp = xsk_buff_alloc(rx_ring->xsk_pool->umem); + bi->xdp = xsk_buff_alloc(rx_ring->xsk_pool); if (!bi->xdp) { ok = false; break; @@ -345,11 +345,11 @@ int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector, q_vector->rx.total_packets += total_rx_packets; q_vector->rx.total_bytes += total_rx_bytes; - if (xsk_umem_uses_need_wakeup(rx_ring->xsk_pool->umem)) { + if (xsk_uses_need_wakeup(rx_ring->xsk_pool)) { if (failure || rx_ring->next_to_clean == rx_ring->next_to_use) - xsk_set_rx_need_wakeup(rx_ring->xsk_pool->umem); + xsk_set_rx_need_wakeup(rx_ring->xsk_pool); else - xsk_clear_rx_need_wakeup(rx_ring->xsk_pool->umem); + xsk_clear_rx_need_wakeup(rx_ring->xsk_pool); return (int)total_rx_packets; } @@ -389,11 +389,11 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget) break; } - if (!xsk_umem_consume_tx(pool->umem, &desc)) + if (!xsk_tx_peek_desc(pool, &desc)) break; - dma = xsk_buff_raw_get_dma(pool->umem, desc.addr); - xsk_buff_raw_dma_sync_for_device(pool->umem, dma, desc.len); + dma = xsk_buff_raw_get_dma(pool, desc.addr); + xsk_buff_raw_dma_sync_for_device(pool, dma, desc.len); tx_bi = &xdp_ring->tx_buffer_info[xdp_ring->next_to_use]; tx_bi->bytecount = desc.len; @@ -419,7 +419,7 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget) if (tx_desc) { ixgbe_xdp_ring_update_tail(xdp_ring); - xsk_umem_consume_tx_done(pool->umem); + xsk_tx_release(pool); } return !!budget && work_done; @@ -485,10 +485,10 @@ bool ixgbe_clean_xdp_tx_irq(struct ixgbe_q_vector *q_vector, q_vector->tx.total_packets += total_packets; if (xsk_frames) - xsk_umem_complete_tx(pool->umem, xsk_frames); + xsk_tx_completed(pool, xsk_frames); - if (xsk_umem_uses_need_wakeup(pool->umem)) - xsk_set_tx_need_wakeup(pool->umem); + if (xsk_uses_need_wakeup(pool)) + xsk_set_tx_need_wakeup(pool); return ixgbe_xmit_zc(tx_ring, q_vector->tx.work_limit); } @@ -547,5 +547,5 @@ void ixgbe_xsk_clean_tx_ring(struct ixgbe_ring *tx_ring) } if (xsk_frames) - xsk_umem_complete_tx(pool->umem, xsk_frames); + xsk_tx_completed(pool, xsk_frames); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index c9f0d2be6dd1..d521449186cc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -445,7 +445,7 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq) } while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq))); if (xsk_frames) - xsk_umem_complete_tx(sq->xsk_pool->umem, xsk_frames); + xsk_tx_completed(sq->xsk_pool, xsk_frames); sq->stats->cqes += i; @@ -475,7 +475,7 @@ void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq) } if (xsk_frames) - xsk_umem_complete_tx(sq->xsk_pool->umem, xsk_frames); + xsk_tx_completed(sq->xsk_pool, xsk_frames); } int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c index 8ccd9203ee25..3503e7711178 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c @@ -11,13 +11,13 @@ static int mlx5e_xsk_map_pool(struct mlx5e_priv *priv, { struct device *dev = priv->mdev->device; - return xsk_buff_dma_map(pool->umem, dev, 0); + return xsk_pool_dma_map(pool, dev, 0); } static void mlx5e_xsk_unmap_pool(struct mlx5e_priv *priv, struct xsk_buff_pool *pool) { - return xsk_buff_dma_unmap(pool->umem, 0); + return xsk_pool_dma_unmap(pool, 0); } static int mlx5e_xsk_get_pools(struct mlx5e_xsk *xsk) @@ -64,14 +64,14 @@ static void mlx5e_xsk_remove_pool(struct mlx5e_xsk *xsk, u16 ix) static bool mlx5e_xsk_is_pool_sane(struct xsk_buff_pool *pool) { - return xsk_umem_get_headroom(pool->umem) <= 0xffff && - xsk_umem_get_chunk_size(pool->umem) <= 0xffff; + return xsk_pool_get_headroom(pool) <= 0xffff && + xsk_pool_get_chunk_size(pool) <= 0xffff; } void mlx5e_build_xsk_param(struct xsk_buff_pool *pool, struct mlx5e_xsk_param *xsk) { - xsk->headroom = xsk_umem_get_headroom(pool->umem); - xsk->chunk_size = xsk_umem_get_chunk_size(pool->umem); + xsk->headroom = xsk_pool_get_headroom(pool); + xsk->chunk_size = xsk_pool_get_chunk_size(pool); } static int mlx5e_xsk_enable_locked(struct mlx5e_priv *priv, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h index 3dd056a11bae..7f88ccf67fdd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h @@ -22,7 +22,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq, static inline int mlx5e_xsk_page_alloc_pool(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info) { - dma_info->xsk = xsk_buff_alloc(rq->xsk_pool->umem); + dma_info->xsk = xsk_buff_alloc(rq->xsk_pool); if (!dma_info->xsk) return -ENOMEM; @@ -38,13 +38,13 @@ static inline int mlx5e_xsk_page_alloc_pool(struct mlx5e_rq *rq, static inline bool mlx5e_xsk_update_rx_wakeup(struct mlx5e_rq *rq, bool alloc_err) { - if (!xsk_umem_uses_need_wakeup(rq->xsk_pool->umem)) + if (!xsk_uses_need_wakeup(rq->xsk_pool)) return alloc_err; if (unlikely(alloc_err)) - xsk_set_rx_need_wakeup(rq->xsk_pool->umem); + xsk_set_rx_need_wakeup(rq->xsk_pool); else - xsk_clear_rx_need_wakeup(rq->xsk_pool->umem); + xsk_clear_rx_need_wakeup(rq->xsk_pool); return false; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c index 5f9470207bb0..aa91cbdfe969 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c @@ -87,7 +87,7 @@ bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget) break; } - if (!xsk_umem_consume_tx(pool->umem, &desc)) { + if (!xsk_tx_peek_desc(pool, &desc)) { /* TX will get stuck until something wakes it up by * triggering NAPI. Currently it's expected that the * application calls sendto() if there are consumed, but @@ -96,11 +96,11 @@ bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget) break; } - xdptxd.dma_addr = xsk_buff_raw_get_dma(pool->umem, desc.addr); - xdptxd.data = xsk_buff_raw_get_data(pool->umem, desc.addr); + xdptxd.dma_addr = xsk_buff_raw_get_dma(pool, desc.addr); + xdptxd.data = xsk_buff_raw_get_data(pool, desc.addr); xdptxd.len = desc.len; - xsk_buff_raw_dma_sync_for_device(pool->umem, xdptxd.dma_addr, xdptxd.len); + xsk_buff_raw_dma_sync_for_device(pool, xdptxd.dma_addr, xdptxd.len); ret = INDIRECT_CALL_2(sq->xmit_xdp_frame, mlx5e_xmit_xdp_frame_mpwqe, mlx5e_xmit_xdp_frame, sq, &xdptxd, &xdpi, check_result); @@ -119,7 +119,7 @@ bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget) mlx5e_xdp_mpwqe_complete(sq); mlx5e_xmit_xdp_doorbell(sq); - xsk_umem_consume_tx_done(pool->umem); + xsk_tx_release(pool); } return !(budget && work_done); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h index ddb61d5bc2db..a05085035f23 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h @@ -15,13 +15,13 @@ bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget); static inline void mlx5e_xsk_update_tx_wakeup(struct mlx5e_xdpsq *sq) { - if (!xsk_umem_uses_need_wakeup(sq->xsk_pool->umem)) + if (!xsk_uses_need_wakeup(sq->xsk_pool)) return; if (sq->pc != sq->cc) - xsk_clear_tx_need_wakeup(sq->xsk_pool->umem); + xsk_clear_tx_need_wakeup(sq->xsk_pool); else - xsk_set_tx_need_wakeup(sq->xsk_pool->umem); + xsk_set_tx_need_wakeup(sq->xsk_pool); } #endif /* __MLX5_EN_XSK_TX_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index f598683dc906..26834625556d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -477,7 +477,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, if (xsk) { err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq, MEM_TYPE_XSK_BUFF_POOL, NULL); - xsk_buff_set_rxq_info(rq->xsk_pool->umem, &rq->xdp_rxq); + xsk_pool_set_rxq_info(rq->xsk_pool, &rq->xdp_rxq); } else { /* Create a page_pool and register it with rxq */ pp_params.order = 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index b33f9f21848f..57034c58b971 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -407,7 +407,7 @@ static int mlx5e_alloc_rx_wqes(struct mlx5e_rq *rq, u16 ix, u8 wqe_bulk) * allocating one-by-one, failing and moving frames to the * Reuse Ring. */ - if (unlikely(!xsk_buff_can_alloc(rq->xsk_pool->umem, pages_desired))) + if (unlikely(!xsk_buff_can_alloc(rq->xsk_pool, pages_desired))) return -ENOMEM; } @@ -506,7 +506,7 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) * one-by-one, failing and moving frames to the Reuse Ring. */ if (rq->xsk_pool && - unlikely(!xsk_buff_can_alloc(rq->xsk_pool->umem, MLX5_MPWRQ_PAGES_PER_WQE))) { + unlikely(!xsk_buff_can_alloc(rq->xsk_pool, MLX5_MPWRQ_PAGES_PER_WQE))) { err = -ENOMEM; goto err; } diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index c9d87cc40c11..ccf6cb54f9a6 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -52,6 +52,7 @@ struct xdp_sock { struct net_device *dev; struct xdp_umem *umem; struct list_head flush_node; + struct xsk_buff_pool *pool; u16 queue_id; bool zc; enum { diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index 5dc8d3c0dcd4..a7c7d2eff860 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -11,48 +11,50 @@ #ifdef CONFIG_XDP_SOCKETS -void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries); -bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc); -void xsk_umem_consume_tx_done(struct xdp_umem *umem); -struct xsk_buff_pool *xdp_get_xsk_pool_from_qid(struct net_device *dev, - u16 queue_id); -void xsk_set_rx_need_wakeup(struct xdp_umem *umem); -void xsk_set_tx_need_wakeup(struct xdp_umem *umem); -void xsk_clear_rx_need_wakeup(struct xdp_umem *umem); -void xsk_clear_tx_need_wakeup(struct xdp_umem *umem); -bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem); +void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries); +bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc); +void xsk_tx_release(struct xsk_buff_pool *pool); +struct xsk_buff_pool *xsk_get_pool_from_qid(struct net_device *dev, + u16 queue_id); +void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool); +void xsk_set_tx_need_wakeup(struct xsk_buff_pool *pool); +void xsk_clear_rx_need_wakeup(struct xsk_buff_pool *pool); +void xsk_clear_tx_need_wakeup(struct xsk_buff_pool *pool); +bool xsk_uses_need_wakeup(struct xsk_buff_pool *pool); -static inline u32 xsk_umem_get_headroom(struct xdp_umem *umem) +static inline u32 xsk_pool_get_headroom(struct xsk_buff_pool *pool) { - return XDP_PACKET_HEADROOM + umem->headroom; + return XDP_PACKET_HEADROOM + pool->headroom; } -static inline u32 xsk_umem_get_chunk_size(struct xdp_umem *umem) +static inline u32 xsk_pool_get_chunk_size(struct xsk_buff_pool *pool) { - return umem->chunk_size; + return pool->chunk_size; } -static inline u32 xsk_umem_get_rx_frame_size(struct xdp_umem *umem) +static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool) { - return xsk_umem_get_chunk_size(umem) - xsk_umem_get_headroom(umem); + return xsk_pool_get_chunk_size(pool) - xsk_pool_get_headroom(pool); } -static inline void xsk_buff_set_rxq_info(struct xdp_umem *umem, +static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq) { - xp_set_rxq_info(umem->pool, rxq); + xp_set_rxq_info(pool, rxq); } -static inline void xsk_buff_dma_unmap(struct xdp_umem *umem, +static inline void xsk_pool_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs) { - xp_dma_unmap(umem->pool, attrs); + xp_dma_unmap(pool, attrs); } -static inline int xsk_buff_dma_map(struct xdp_umem *umem, struct device *dev, - unsigned long attrs) +static inline int xsk_pool_dma_map(struct xsk_buff_pool *pool, + struct device *dev, unsigned long attrs) { - return xp_dma_map(umem->pool, dev, attrs, umem->pgs, umem->npgs); + struct xdp_umem *umem = pool->umem; + + return xp_dma_map(pool, dev, attrs, umem->pgs, umem->npgs); } static inline dma_addr_t xsk_buff_xdp_get_dma(struct xdp_buff *xdp) @@ -69,14 +71,14 @@ static inline dma_addr_t xsk_buff_xdp_get_frame_dma(struct xdp_buff *xdp) return xp_get_frame_dma(xskb); } -static inline struct xdp_buff *xsk_buff_alloc(struct xdp_umem *umem) +static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool) { - return xp_alloc(umem->pool); + return xp_alloc(pool); } -static inline bool xsk_buff_can_alloc(struct xdp_umem *umem, u32 count) +static inline bool xsk_buff_can_alloc(struct xsk_buff_pool *pool, u32 count) { - return xp_can_alloc(umem->pool, count); + return xp_can_alloc(pool, count); } static inline void xsk_buff_free(struct xdp_buff *xdp) @@ -86,14 +88,15 @@ static inline void xsk_buff_free(struct xdp_buff *xdp) xp_free(xskb); } -static inline dma_addr_t xsk_buff_raw_get_dma(struct xdp_umem *umem, u64 addr) +static inline dma_addr_t xsk_buff_raw_get_dma(struct xsk_buff_pool *pool, + u64 addr) { - return xp_raw_get_dma(umem->pool, addr); + return xp_raw_get_dma(pool, addr); } -static inline void *xsk_buff_raw_get_data(struct xdp_umem *umem, u64 addr) +static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr) { - return xp_raw_get_data(umem->pool, addr); + return xp_raw_get_data(pool, addr); } static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp) @@ -103,83 +106,83 @@ static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp) xp_dma_sync_for_cpu(xskb); } -static inline void xsk_buff_raw_dma_sync_for_device(struct xdp_umem *umem, +static inline void xsk_buff_raw_dma_sync_for_device(struct xsk_buff_pool *pool, dma_addr_t dma, size_t size) { - xp_dma_sync_for_device(umem->pool, dma, size); + xp_dma_sync_for_device(pool, dma, size); } #else -static inline void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries) +static inline void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries) { } -static inline bool xsk_umem_consume_tx(struct xdp_umem *umem, - struct xdp_desc *desc) +static inline bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, + struct xdp_desc *desc) { return false; } -static inline void xsk_umem_consume_tx_done(struct xdp_umem *umem) +static inline void xsk_tx_release(struct xsk_buff_pool *pool) { } static inline struct xsk_buff_pool * -xdp_get_xsk_pool_from_qid(struct net_device *dev, u16 queue_id) +xsk_get_pool_from_qid(struct net_device *dev, u16 queue_id) { return NULL; } -static inline void xsk_set_rx_need_wakeup(struct xdp_umem *umem) +static inline void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool) { } -static inline void xsk_set_tx_need_wakeup(struct xdp_umem *umem) +static inline void xsk_set_tx_need_wakeup(struct xsk_buff_pool *pool) { } -static inline void xsk_clear_rx_need_wakeup(struct xdp_umem *umem) +static inline void xsk_clear_rx_need_wakeup(struct xsk_buff_pool *pool) { } -static inline void xsk_clear_tx_need_wakeup(struct xdp_umem *umem) +static inline void xsk_clear_tx_need_wakeup(struct xsk_buff_pool *pool) { } -static inline bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem) +static inline bool xsk_uses_need_wakeup(struct xsk_buff_pool *pool) { return false; } -static inline u32 xsk_umem_get_headroom(struct xdp_umem *umem) +static inline u32 xsk_pool_get_headroom(struct xsk_buff_pool *pool) { return 0; } -static inline u32 xsk_umem_get_chunk_size(struct xdp_umem *umem) +static inline u32 xsk_pool_get_chunk_size(struct xsk_buff_pool *pool) { return 0; } -static inline u32 xsk_umem_get_rx_frame_size(struct xdp_umem *umem) +static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool) { return 0; } -static inline void xsk_buff_set_rxq_info(struct xdp_umem *umem, +static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq) { } -static inline void xsk_buff_dma_unmap(struct xdp_umem *umem, +static inline void xsk_pool_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs) { } -static inline int xsk_buff_dma_map(struct xdp_umem *umem, struct device *dev, - unsigned long attrs) +static inline int xsk_pool_dma_map(struct xsk_buff_pool *pool, + struct device *dev, unsigned long attrs) { return 0; } @@ -194,12 +197,12 @@ static inline dma_addr_t xsk_buff_xdp_get_frame_dma(struct xdp_buff *xdp) return 0; } -static inline struct xdp_buff *xsk_buff_alloc(struct xdp_umem *umem) +static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool) { return NULL; } -static inline bool xsk_buff_can_alloc(struct xdp_umem *umem, u32 count) +static inline bool xsk_buff_can_alloc(struct xsk_buff_pool *pool, u32 count) { return false; } @@ -208,12 +211,13 @@ static inline void xsk_buff_free(struct xdp_buff *xdp) { } -static inline dma_addr_t xsk_buff_raw_get_dma(struct xdp_umem *umem, u64 addr) +static inline dma_addr_t xsk_buff_raw_get_dma(struct xsk_buff_pool *pool, + u64 addr) { return 0; } -static inline void *xsk_buff_raw_get_data(struct xdp_umem *umem, u64 addr) +static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr) { return NULL; } @@ -222,7 +226,7 @@ static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp) { } -static inline void xsk_buff_raw_dma_sync_for_device(struct xdp_umem *umem, +static inline void xsk_buff_raw_dma_sync_for_device(struct xsk_buff_pool *pool, dma_addr_t dma, size_t size) { diff --git a/net/ethtool/channels.c b/net/ethtool/channels.c index 78d990bfb90f..9ecda09ecb11 100644 --- a/net/ethtool/channels.c +++ b/net/ethtool/channels.c @@ -223,7 +223,7 @@ int ethnl_set_channels(struct sk_buff *skb, struct genl_info *info) from_channel = channels.combined_count + min(channels.rx_count, channels.tx_count); for (i = from_channel; i < old_total; i++) - if (xdp_get_xsk_pool_from_qid(dev, i)) { + if (xsk_get_pool_from_qid(dev, i)) { GENL_SET_ERR_MSG(info, "requested channel counts are too low for existing zerocopy AF_XDP sockets"); return -EINVAL; } diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 2e6a678df741..925b5731bf0c 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -1706,7 +1706,7 @@ static noinline_for_stack int ethtool_set_channels(struct net_device *dev, min(channels.rx_count, channels.tx_count); to_channel = curr.combined_count + max(curr.rx_count, curr.tx_count); for (i = from_channel; i < to_channel; i++) - if (xdp_get_xsk_pool_from_qid(dev, i)) + if (xsk_get_pool_from_qid(dev, i)) return -EINVAL; ret = dev->ethtool_ops->set_channels(dev, &channels); diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index 0b5f3b04216f..adde4d576b38 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -51,9 +51,9 @@ void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs) * not know if the device has more tx queues than rx, or the opposite. * This might also change during run time. */ -static int xdp_reg_xsk_pool_at_qid(struct net_device *dev, - struct xsk_buff_pool *pool, - u16 queue_id) +static int xsk_reg_pool_at_qid(struct net_device *dev, + struct xsk_buff_pool *pool, + u16 queue_id) { if (queue_id >= max_t(unsigned int, dev->real_num_rx_queues, @@ -68,8 +68,8 @@ static int xdp_reg_xsk_pool_at_qid(struct net_device *dev, return 0; } -struct xsk_buff_pool *xdp_get_xsk_pool_from_qid(struct net_device *dev, - u16 queue_id) +struct xsk_buff_pool *xsk_get_pool_from_qid(struct net_device *dev, + u16 queue_id) { if (queue_id < dev->real_num_rx_queues) return dev->_rx[queue_id].pool; @@ -78,9 +78,9 @@ struct xsk_buff_pool *xdp_get_xsk_pool_from_qid(struct net_device *dev, return NULL; } -EXPORT_SYMBOL(xdp_get_xsk_pool_from_qid); +EXPORT_SYMBOL(xsk_get_pool_from_qid); -static void xdp_clear_xsk_pool_at_qid(struct net_device *dev, u16 queue_id) +static void xsk_clear_pool_at_qid(struct net_device *dev, u16 queue_id) { if (queue_id < dev->real_num_rx_queues) dev->_rx[queue_id].pool = NULL; @@ -103,10 +103,10 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, if (force_zc && force_copy) return -EINVAL; - if (xdp_get_xsk_pool_from_qid(dev, queue_id)) + if (xsk_get_pool_from_qid(dev, queue_id)) return -EBUSY; - err = xdp_reg_xsk_pool_at_qid(dev, umem->pool, queue_id); + err = xsk_reg_pool_at_qid(dev, umem->pool, queue_id); if (err) return err; @@ -119,7 +119,7 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, * Also for supporting drivers that do not implement this * feature. They will always have to call sendto(). */ - xsk_set_tx_need_wakeup(umem); + xsk_set_tx_need_wakeup(umem->pool); } dev_hold(dev); @@ -148,7 +148,7 @@ err_unreg_umem: if (!force_zc) err = 0; /* fallback to copy mode */ if (err) - xdp_clear_xsk_pool_at_qid(dev, queue_id); + xsk_clear_pool_at_qid(dev, queue_id); return err; } @@ -173,7 +173,7 @@ void xdp_umem_clear_dev(struct xdp_umem *umem) WARN(1, "failed to disable umem!\n"); } - xdp_clear_xsk_pool_at_qid(umem->dev, umem->queue_id); + xsk_clear_pool_at_qid(umem->dev, umem->queue_id); dev_put(umem->dev); umem->dev = NULL; diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index c3231620d210..befc9a4331e1 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -39,8 +39,10 @@ bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs) READ_ONCE(xs->umem->fq); } -void xsk_set_rx_need_wakeup(struct xdp_umem *umem) +void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool) { + struct xdp_umem *umem = pool->umem; + if (umem->need_wakeup & XDP_WAKEUP_RX) return; @@ -49,8 +51,9 @@ void xsk_set_rx_need_wakeup(struct xdp_umem *umem) } EXPORT_SYMBOL(xsk_set_rx_need_wakeup); -void xsk_set_tx_need_wakeup(struct xdp_umem *umem) +void xsk_set_tx_need_wakeup(struct xsk_buff_pool *pool) { + struct xdp_umem *umem = pool->umem; struct xdp_sock *xs; if (umem->need_wakeup & XDP_WAKEUP_TX) @@ -66,8 +69,10 @@ void xsk_set_tx_need_wakeup(struct xdp_umem *umem) } EXPORT_SYMBOL(xsk_set_tx_need_wakeup); -void xsk_clear_rx_need_wakeup(struct xdp_umem *umem) +void xsk_clear_rx_need_wakeup(struct xsk_buff_pool *pool) { + struct xdp_umem *umem = pool->umem; + if (!(umem->need_wakeup & XDP_WAKEUP_RX)) return; @@ -76,8 +81,9 @@ void xsk_clear_rx_need_wakeup(struct xdp_umem *umem) } EXPORT_SYMBOL(xsk_clear_rx_need_wakeup); -void xsk_clear_tx_need_wakeup(struct xdp_umem *umem) +void xsk_clear_tx_need_wakeup(struct xsk_buff_pool *pool) { + struct xdp_umem *umem = pool->umem; struct xdp_sock *xs; if (!(umem->need_wakeup & XDP_WAKEUP_TX)) @@ -93,11 +99,11 @@ void xsk_clear_tx_need_wakeup(struct xdp_umem *umem) } EXPORT_SYMBOL(xsk_clear_tx_need_wakeup); -bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem) +bool xsk_uses_need_wakeup(struct xsk_buff_pool *pool) { - return umem->flags & XDP_UMEM_USES_NEED_WAKEUP; + return pool->umem->flags & XDP_UMEM_USES_NEED_WAKEUP; } -EXPORT_SYMBOL(xsk_umem_uses_need_wakeup); +EXPORT_SYMBOL(xsk_uses_need_wakeup); void xp_release(struct xdp_buff_xsk *xskb) { @@ -155,12 +161,12 @@ static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len, struct xdp_buff *xsk_xdp; int err; - if (len > xsk_umem_get_rx_frame_size(xs->umem)) { + if (len > xsk_pool_get_rx_frame_size(xs->pool)) { xs->rx_dropped++; return -ENOSPC; } - xsk_xdp = xsk_buff_alloc(xs->umem); + xsk_xdp = xsk_buff_alloc(xs->pool); if (!xsk_xdp) { xs->rx_dropped++; return -ENOSPC; @@ -249,27 +255,28 @@ void __xsk_map_flush(void) } } -void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries) +void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries) { - xskq_prod_submit_n(umem->cq, nb_entries); + xskq_prod_submit_n(pool->umem->cq, nb_entries); } -EXPORT_SYMBOL(xsk_umem_complete_tx); +EXPORT_SYMBOL(xsk_tx_completed); -void xsk_umem_consume_tx_done(struct xdp_umem *umem) +void xsk_tx_release(struct xsk_buff_pool *pool) { struct xdp_sock *xs; rcu_read_lock(); - list_for_each_entry_rcu(xs, &umem->xsk_tx_list, list) { + list_for_each_entry_rcu(xs, &pool->umem->xsk_tx_list, list) { __xskq_cons_release(xs->tx); xs->sk.sk_write_space(&xs->sk); } rcu_read_unlock(); } -EXPORT_SYMBOL(xsk_umem_consume_tx_done); +EXPORT_SYMBOL(xsk_tx_release); -bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc) +bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc) { + struct xdp_umem *umem = pool->umem; struct xdp_sock *xs; rcu_read_lock(); @@ -296,7 +303,7 @@ out: rcu_read_unlock(); return false; } -EXPORT_SYMBOL(xsk_umem_consume_tx); +EXPORT_SYMBOL(xsk_tx_peek_desc); static int xsk_wakeup(struct xdp_sock *xs, u8 flags) { @@ -359,7 +366,7 @@ static int xsk_generic_xmit(struct sock *sk) skb_put(skb, len); addr = desc.addr; - buffer = xsk_buff_raw_get_data(xs->umem, addr); + buffer = xsk_buff_raw_get_data(xs->pool, addr); err = skb_store_bits(skb, 0, buffer, len); /* This is the backpressure mechanism for the Tx path. * Reserve space in the completion queue and only proceed @@ -762,6 +769,8 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname, return PTR_ERR(umem); } + xs->pool = umem->pool; + /* Make sure umem is ready before it can be seen by others */ smp_wmb(); WRITE_ONCE(xs->umem, umem); -- cgit v1.2.3 From 1c1efc2af158869795d3334a12fed2afd9c51539 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Fri, 28 Aug 2020 10:26:17 +0200 Subject: xsk: Create and free buffer pool independently from umem MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Create and free the buffer pool independently from the umem. Move these operations that are performed on the buffer pool from the umem create and destroy functions to new create and destroy functions just for the buffer pool. This so that in later commits we can instantiate multiple buffer pools per umem when sharing a umem between HW queues and/or devices. We also erradicate the back pointer from the umem to the buffer pool as this will not work when we introduce the possibility to have multiple buffer pools per umem. Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Acked-by: Björn Töpel Link: https://lore.kernel.org/bpf/1598603189-32145-4-git-send-email-magnus.karlsson@intel.com --- include/net/xdp_sock.h | 3 +- include/net/xsk_buff_pool.h | 13 +++- net/xdp/xdp_umem.c | 164 ++++---------------------------------------- net/xdp/xdp_umem.h | 4 +- net/xdp/xsk.c | 74 +++++++++++++++++--- net/xdp/xsk.h | 3 + net/xdp/xsk_buff_pool.c | 150 ++++++++++++++++++++++++++++++++++++---- net/xdp/xsk_queue.h | 12 ++-- 8 files changed, 236 insertions(+), 187 deletions(-) (limited to 'include/net') diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index ccf6cb54f9a6..ea2b020c4fbc 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -20,13 +20,12 @@ struct xdp_buff; struct xdp_umem { struct xsk_queue *fq; struct xsk_queue *cq; - struct xsk_buff_pool *pool; u64 size; u32 headroom; u32 chunk_size; + u32 chunks; struct user_struct *user; refcount_t users; - struct work_struct work; struct page **pgs; u32 npgs; u16 queue_id; diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index f851b0a68324..4025486cc057 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -14,6 +14,7 @@ struct xdp_rxq_info; struct xsk_queue; struct xdp_desc; struct xdp_umem; +struct xdp_sock; struct device; struct page; @@ -46,16 +47,22 @@ struct xsk_buff_pool { struct xdp_umem *umem; void *addrs; struct device *dev; + refcount_t users; + struct work_struct work; struct xdp_buff_xsk *free_heads[]; }; /* AF_XDP core. */ -struct xsk_buff_pool *xp_create(struct xdp_umem *umem, u32 chunks, - u32 chunk_size, u32 headroom, u64 size, - bool unaligned); +struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, + struct xdp_umem *umem); +int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev, + u16 queue_id, u16 flags); void xp_set_fq(struct xsk_buff_pool *pool, struct xsk_queue *fq); void xp_destroy(struct xsk_buff_pool *pool); void xp_release(struct xdp_buff_xsk *xskb); +void xp_get_pool(struct xsk_buff_pool *pool); +void xp_put_pool(struct xsk_buff_pool *pool); +void xp_clear_dev(struct xsk_buff_pool *pool); /* AF_XDP, and XDP core. */ void xp_free(struct xdp_buff_xsk *xskb); diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index adde4d576b38..f290345fb6c7 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -47,160 +47,41 @@ void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs) spin_unlock_irqrestore(&umem->xsk_tx_list_lock, flags); } -/* The umem is stored both in the _rx struct and the _tx struct as we do - * not know if the device has more tx queues than rx, or the opposite. - * This might also change during run time. - */ -static int xsk_reg_pool_at_qid(struct net_device *dev, - struct xsk_buff_pool *pool, - u16 queue_id) -{ - if (queue_id >= max_t(unsigned int, - dev->real_num_rx_queues, - dev->real_num_tx_queues)) - return -EINVAL; - - if (queue_id < dev->real_num_rx_queues) - dev->_rx[queue_id].pool = pool; - if (queue_id < dev->real_num_tx_queues) - dev->_tx[queue_id].pool = pool; - - return 0; -} - -struct xsk_buff_pool *xsk_get_pool_from_qid(struct net_device *dev, - u16 queue_id) +static void xdp_umem_unpin_pages(struct xdp_umem *umem) { - if (queue_id < dev->real_num_rx_queues) - return dev->_rx[queue_id].pool; - if (queue_id < dev->real_num_tx_queues) - return dev->_tx[queue_id].pool; + unpin_user_pages_dirty_lock(umem->pgs, umem->npgs, true); - return NULL; + kfree(umem->pgs); + umem->pgs = NULL; } -EXPORT_SYMBOL(xsk_get_pool_from_qid); -static void xsk_clear_pool_at_qid(struct net_device *dev, u16 queue_id) +static void xdp_umem_unaccount_pages(struct xdp_umem *umem) { - if (queue_id < dev->real_num_rx_queues) - dev->_rx[queue_id].pool = NULL; - if (queue_id < dev->real_num_tx_queues) - dev->_tx[queue_id].pool = NULL; + if (umem->user) { + atomic_long_sub(umem->npgs, &umem->user->locked_vm); + free_uid(umem->user); + } } -int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, - u16 queue_id, u16 flags) +void xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, + u16 queue_id) { - bool force_zc, force_copy; - struct netdev_bpf bpf; - int err = 0; - - ASSERT_RTNL(); - - force_zc = flags & XDP_ZEROCOPY; - force_copy = flags & XDP_COPY; - - if (force_zc && force_copy) - return -EINVAL; - - if (xsk_get_pool_from_qid(dev, queue_id)) - return -EBUSY; - - err = xsk_reg_pool_at_qid(dev, umem->pool, queue_id); - if (err) - return err; - umem->dev = dev; umem->queue_id = queue_id; - if (flags & XDP_USE_NEED_WAKEUP) { - umem->flags |= XDP_UMEM_USES_NEED_WAKEUP; - /* Tx needs to be explicitly woken up the first time. - * Also for supporting drivers that do not implement this - * feature. They will always have to call sendto(). - */ - xsk_set_tx_need_wakeup(umem->pool); - } - dev_hold(dev); - - if (force_copy) - /* For copy-mode, we are done. */ - return 0; - - if (!dev->netdev_ops->ndo_bpf || !dev->netdev_ops->ndo_xsk_wakeup) { - err = -EOPNOTSUPP; - goto err_unreg_umem; - } - - bpf.command = XDP_SETUP_XSK_POOL; - bpf.xsk.pool = umem->pool; - bpf.xsk.queue_id = queue_id; - - err = dev->netdev_ops->ndo_bpf(dev, &bpf); - if (err) - goto err_unreg_umem; - - umem->zc = true; - return 0; - -err_unreg_umem: - if (!force_zc) - err = 0; /* fallback to copy mode */ - if (err) - xsk_clear_pool_at_qid(dev, queue_id); - return err; } void xdp_umem_clear_dev(struct xdp_umem *umem) { - struct netdev_bpf bpf; - int err; - - ASSERT_RTNL(); - - if (!umem->dev) - return; - - if (umem->zc) { - bpf.command = XDP_SETUP_XSK_POOL; - bpf.xsk.pool = NULL; - bpf.xsk.queue_id = umem->queue_id; - - err = umem->dev->netdev_ops->ndo_bpf(umem->dev, &bpf); - - if (err) - WARN(1, "failed to disable umem!\n"); - } - - xsk_clear_pool_at_qid(umem->dev, umem->queue_id); - dev_put(umem->dev); umem->dev = NULL; umem->zc = false; } -static void xdp_umem_unpin_pages(struct xdp_umem *umem) -{ - unpin_user_pages_dirty_lock(umem->pgs, umem->npgs, true); - - kfree(umem->pgs); - umem->pgs = NULL; -} - -static void xdp_umem_unaccount_pages(struct xdp_umem *umem) -{ - if (umem->user) { - atomic_long_sub(umem->npgs, &umem->user->locked_vm); - free_uid(umem->user); - } -} - static void xdp_umem_release(struct xdp_umem *umem) { - rtnl_lock(); xdp_umem_clear_dev(umem); - rtnl_unlock(); ida_simple_remove(&umem_ida, umem->id); @@ -214,20 +95,12 @@ static void xdp_umem_release(struct xdp_umem *umem) umem->cq = NULL; } - xp_destroy(umem->pool); xdp_umem_unpin_pages(umem); xdp_umem_unaccount_pages(umem); kfree(umem); } -static void xdp_umem_release_deferred(struct work_struct *work) -{ - struct xdp_umem *umem = container_of(work, struct xdp_umem, work); - - xdp_umem_release(umem); -} - void xdp_get_umem(struct xdp_umem *umem) { refcount_inc(&umem->users); @@ -238,10 +111,8 @@ void xdp_put_umem(struct xdp_umem *umem) if (!umem) return; - if (refcount_dec_and_test(&umem->users)) { - INIT_WORK(&umem->work, xdp_umem_release_deferred); - schedule_work(&umem->work); - } + if (refcount_dec_and_test(&umem->users)) + xdp_umem_release(umem); } static int xdp_umem_pin_pages(struct xdp_umem *umem, unsigned long address) @@ -357,6 +228,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) umem->size = size; umem->headroom = headroom; umem->chunk_size = chunk_size; + umem->chunks = chunks; umem->npgs = (u32)npgs; umem->pgs = NULL; umem->user = NULL; @@ -374,16 +246,8 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) if (err) goto out_account; - umem->pool = xp_create(umem, chunks, chunk_size, headroom, size, - unaligned_chunks); - if (!umem->pool) { - err = -ENOMEM; - goto out_pin; - } return 0; -out_pin: - xdp_umem_unpin_pages(umem); out_account: xdp_umem_unaccount_pages(umem); return err; diff --git a/net/xdp/xdp_umem.h b/net/xdp/xdp_umem.h index 32067fe98f65..93e96be6f4de 100644 --- a/net/xdp/xdp_umem.h +++ b/net/xdp/xdp_umem.h @@ -8,8 +8,8 @@ #include -int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, - u16 queue_id, u16 flags); +void xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, + u16 queue_id); void xdp_umem_clear_dev(struct xdp_umem *umem); bool xdp_umem_validate_queues(struct xdp_umem *umem); void xdp_get_umem(struct xdp_umem *umem); diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index befc9a4331e1..5739f1951d7a 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -105,6 +105,46 @@ bool xsk_uses_need_wakeup(struct xsk_buff_pool *pool) } EXPORT_SYMBOL(xsk_uses_need_wakeup); +struct xsk_buff_pool *xsk_get_pool_from_qid(struct net_device *dev, + u16 queue_id) +{ + if (queue_id < dev->real_num_rx_queues) + return dev->_rx[queue_id].pool; + if (queue_id < dev->real_num_tx_queues) + return dev->_tx[queue_id].pool; + + return NULL; +} +EXPORT_SYMBOL(xsk_get_pool_from_qid); + +void xsk_clear_pool_at_qid(struct net_device *dev, u16 queue_id) +{ + if (queue_id < dev->real_num_rx_queues) + dev->_rx[queue_id].pool = NULL; + if (queue_id < dev->real_num_tx_queues) + dev->_tx[queue_id].pool = NULL; +} + +/* The buffer pool is stored both in the _rx struct and the _tx struct as we do + * not know if the device has more tx queues than rx, or the opposite. + * This might also change during run time. + */ +int xsk_reg_pool_at_qid(struct net_device *dev, struct xsk_buff_pool *pool, + u16 queue_id) +{ + if (queue_id >= max_t(unsigned int, + dev->real_num_rx_queues, + dev->real_num_tx_queues)) + return -EINVAL; + + if (queue_id < dev->real_num_rx_queues) + dev->_rx[queue_id].pool = pool; + if (queue_id < dev->real_num_tx_queues) + dev->_tx[queue_id].pool = pool; + + return 0; +} + void xp_release(struct xdp_buff_xsk *xskb) { xskb->pool->free_heads[xskb->pool->free_heads_cnt++] = xskb; @@ -281,7 +321,7 @@ bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc) rcu_read_lock(); list_for_each_entry_rcu(xs, &umem->xsk_tx_list, list) { - if (!xskq_cons_peek_desc(xs->tx, desc, umem)) { + if (!xskq_cons_peek_desc(xs->tx, desc, pool)) { xs->tx->queue_empty_descs++; continue; } @@ -349,7 +389,7 @@ static int xsk_generic_xmit(struct sock *sk) if (xs->queue_id >= xs->dev->real_num_tx_queues) goto out; - while (xskq_cons_peek_desc(xs->tx, &desc, xs->umem)) { + while (xskq_cons_peek_desc(xs->tx, &desc, xs->pool)) { char *buffer; u64 addr; u32 len; @@ -667,6 +707,9 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) goto out_unlock; } + /* Share the buffer pool with the other socket. */ + xp_get_pool(umem_xs->pool); + xs->pool = umem_xs->pool; xdp_get_umem(umem_xs->umem); WRITE_ONCE(xs->umem, umem_xs->umem); sockfd_put(sock); @@ -675,9 +718,21 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) goto out_unlock; } else { /* This xsk has its own umem. */ - err = xdp_umem_assign_dev(xs->umem, dev, qid, flags); - if (err) + xdp_umem_assign_dev(xs->umem, dev, qid); + xs->pool = xp_create_and_assign_umem(xs, xs->umem); + if (!xs->pool) { + err = -ENOMEM; + xdp_umem_clear_dev(xs->umem); goto out_unlock; + } + + err = xp_assign_dev(xs->pool, dev, qid, flags); + if (err) { + xp_destroy(xs->pool); + xs->pool = NULL; + xdp_umem_clear_dev(xs->umem); + goto out_unlock; + } } xs->dev = dev; @@ -769,8 +824,6 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname, return PTR_ERR(umem); } - xs->pool = umem->pool; - /* Make sure umem is ready before it can be seen by others */ smp_wmb(); WRITE_ONCE(xs->umem, umem); @@ -800,7 +853,7 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname, &xs->umem->cq; err = xsk_init_queue(entries, q, true); if (optname == XDP_UMEM_FILL_RING) - xp_set_fq(xs->umem->pool, *q); + xp_set_fq(xs->pool, *q); mutex_unlock(&xs->mutex); return err; } @@ -1028,7 +1081,8 @@ static int xsk_notifier(struct notifier_block *this, xsk_unbind_dev(xs); - /* Clear device references in umem. */ + /* Clear device references. */ + xp_clear_dev(xs->pool); xdp_umem_clear_dev(xs->umem); } mutex_unlock(&xs->mutex); @@ -1073,7 +1127,7 @@ static void xsk_destruct(struct sock *sk) if (!sock_flag(sk, SOCK_DEAD)) return; - xdp_put_umem(xs->umem); + xp_put_pool(xs->pool); sk_refcnt_debug_dec(sk); } @@ -1081,8 +1135,8 @@ static void xsk_destruct(struct sock *sk) static int xsk_create(struct net *net, struct socket *sock, int protocol, int kern) { - struct sock *sk; struct xdp_sock *xs; + struct sock *sk; if (!ns_capable(net->user_ns, CAP_NET_RAW)) return -EPERM; diff --git a/net/xdp/xsk.h b/net/xdp/xsk.h index 455ddd480f3d..a00e3e2a9ef1 100644 --- a/net/xdp/xsk.h +++ b/net/xdp/xsk.h @@ -51,5 +51,8 @@ void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs, struct xdp_sock **map_entry); int xsk_map_inc(struct xsk_map *map); void xsk_map_put(struct xsk_map *map); +void xsk_clear_pool_at_qid(struct net_device *dev, u16 queue_id); +int xsk_reg_pool_at_qid(struct net_device *dev, struct xsk_buff_pool *pool, + u16 queue_id); #endif /* XSK_H_ */ diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index f3df3cba3d73..e58c54d68c3d 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -2,8 +2,14 @@ #include #include +#include +#include +#include +#include #include "xsk_queue.h" +#include "xdp_umem.h" +#include "xsk.h" static void xp_addr_unmap(struct xsk_buff_pool *pool) { @@ -29,38 +35,40 @@ void xp_destroy(struct xsk_buff_pool *pool) kvfree(pool); } -struct xsk_buff_pool *xp_create(struct xdp_umem *umem, u32 chunks, - u32 chunk_size, u32 headroom, u64 size, - bool unaligned) +struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, + struct xdp_umem *umem) { struct xsk_buff_pool *pool; struct xdp_buff_xsk *xskb; int err; u32 i; - pool = kvzalloc(struct_size(pool, free_heads, chunks), GFP_KERNEL); + pool = kvzalloc(struct_size(pool, free_heads, umem->chunks), + GFP_KERNEL); if (!pool) goto out; - pool->heads = kvcalloc(chunks, sizeof(*pool->heads), GFP_KERNEL); + pool->heads = kvcalloc(umem->chunks, sizeof(*pool->heads), GFP_KERNEL); if (!pool->heads) goto out; - pool->chunk_mask = ~((u64)chunk_size - 1); - pool->addrs_cnt = size; - pool->heads_cnt = chunks; - pool->free_heads_cnt = chunks; - pool->headroom = headroom; - pool->chunk_size = chunk_size; - pool->unaligned = unaligned; - pool->frame_len = chunk_size - headroom - XDP_PACKET_HEADROOM; + pool->chunk_mask = ~((u64)umem->chunk_size - 1); + pool->addrs_cnt = umem->size; + pool->heads_cnt = umem->chunks; + pool->free_heads_cnt = umem->chunks; + pool->headroom = umem->headroom; + pool->chunk_size = umem->chunk_size; + pool->unaligned = umem->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG; + pool->frame_len = umem->chunk_size - umem->headroom - + XDP_PACKET_HEADROOM; pool->umem = umem; INIT_LIST_HEAD(&pool->free_list); + refcount_set(&pool->users, 1); for (i = 0; i < pool->free_heads_cnt; i++) { xskb = &pool->heads[i]; xskb->pool = pool; - xskb->xdp.frame_sz = chunk_size - headroom; + xskb->xdp.frame_sz = umem->chunk_size - umem->headroom; pool->free_heads[i] = xskb; } @@ -87,6 +95,120 @@ void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq) } EXPORT_SYMBOL(xp_set_rxq_info); +int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev, + u16 queue_id, u16 flags) +{ + struct xdp_umem *umem = pool->umem; + bool force_zc, force_copy; + struct netdev_bpf bpf; + int err = 0; + + ASSERT_RTNL(); + + force_zc = flags & XDP_ZEROCOPY; + force_copy = flags & XDP_COPY; + + if (force_zc && force_copy) + return -EINVAL; + + if (xsk_get_pool_from_qid(dev, queue_id)) + return -EBUSY; + + err = xsk_reg_pool_at_qid(dev, pool, queue_id); + if (err) + return err; + + if (flags & XDP_USE_NEED_WAKEUP) { + umem->flags |= XDP_UMEM_USES_NEED_WAKEUP; + /* Tx needs to be explicitly woken up the first time. + * Also for supporting drivers that do not implement this + * feature. They will always have to call sendto(). + */ + umem->need_wakeup = XDP_WAKEUP_TX; + } + + if (force_copy) + /* For copy-mode, we are done. */ + return 0; + + if (!dev->netdev_ops->ndo_bpf || !dev->netdev_ops->ndo_xsk_wakeup) { + err = -EOPNOTSUPP; + goto err_unreg_pool; + } + + bpf.command = XDP_SETUP_XSK_POOL; + bpf.xsk.pool = pool; + bpf.xsk.queue_id = queue_id; + + err = dev->netdev_ops->ndo_bpf(dev, &bpf); + if (err) + goto err_unreg_pool; + + umem->zc = true; + return 0; + +err_unreg_pool: + if (!force_zc) + err = 0; /* fallback to copy mode */ + if (err) + xsk_clear_pool_at_qid(dev, queue_id); + return err; +} + +void xp_clear_dev(struct xsk_buff_pool *pool) +{ + struct xdp_umem *umem = pool->umem; + struct netdev_bpf bpf; + int err; + + ASSERT_RTNL(); + + if (!umem->dev) + return; + + if (umem->zc) { + bpf.command = XDP_SETUP_XSK_POOL; + bpf.xsk.pool = NULL; + bpf.xsk.queue_id = umem->queue_id; + + err = umem->dev->netdev_ops->ndo_bpf(umem->dev, &bpf); + + if (err) + WARN(1, "failed to disable umem!\n"); + } + + xsk_clear_pool_at_qid(umem->dev, umem->queue_id); +} + +static void xp_release_deferred(struct work_struct *work) +{ + struct xsk_buff_pool *pool = container_of(work, struct xsk_buff_pool, + work); + + rtnl_lock(); + xp_clear_dev(pool); + rtnl_unlock(); + + xdp_put_umem(pool->umem); + xp_destroy(pool); +} + +void xp_get_pool(struct xsk_buff_pool *pool) +{ + refcount_inc(&pool->users); +} + +void xp_put_pool(struct xsk_buff_pool *pool) +{ + if (!pool) + return; + + if (refcount_dec_and_test(&pool->users)) { + INIT_WORK(&pool->work, xp_release_deferred); + schedule_work(&pool->work); + } +} + void xp_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs) { dma_addr_t *dma; diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index bf42cfd74b89..2d883f631c85 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -166,9 +166,9 @@ static inline bool xp_validate_desc(struct xsk_buff_pool *pool, static inline bool xskq_cons_is_valid_desc(struct xsk_queue *q, struct xdp_desc *d, - struct xdp_umem *umem) + struct xsk_buff_pool *pool) { - if (!xp_validate_desc(umem->pool, d)) { + if (!xp_validate_desc(pool, d)) { q->invalid_descs++; return false; } @@ -177,14 +177,14 @@ static inline bool xskq_cons_is_valid_desc(struct xsk_queue *q, static inline bool xskq_cons_read_desc(struct xsk_queue *q, struct xdp_desc *desc, - struct xdp_umem *umem) + struct xsk_buff_pool *pool) { while (q->cached_cons != q->cached_prod) { struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring; u32 idx = q->cached_cons & q->ring_mask; *desc = ring->desc[idx]; - if (xskq_cons_is_valid_desc(q, desc, umem)) + if (xskq_cons_is_valid_desc(q, desc, pool)) return true; q->cached_cons++; @@ -236,11 +236,11 @@ static inline bool xskq_cons_peek_addr_unchecked(struct xsk_queue *q, u64 *addr) static inline bool xskq_cons_peek_desc(struct xsk_queue *q, struct xdp_desc *desc, - struct xdp_umem *umem) + struct xsk_buff_pool *pool) { if (q->cached_prod == q->cached_cons) xskq_cons_get_entries(q); - return xskq_cons_read_desc(q, desc, umem); + return xskq_cons_read_desc(q, desc, pool); } static inline void xskq_cons_release(struct xsk_queue *q) -- cgit v1.2.3 From 7361f9c3d71955c624fdad5676c99fc88a8249e9 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Fri, 28 Aug 2020 10:26:18 +0200 Subject: xsk: Move fill and completion rings to buffer pool MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Move the fill and completion rings from the umem to the buffer pool. This so that we in a later commit can share the umem between multiple HW queue ids. In this case, we need one fill and completion ring per queue id. As the buffer pool is per queue id and napi id this is a natural place for it and one umem struture can be shared between these buffer pools. Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Acked-by: Björn Töpel Link: https://lore.kernel.org/bpf/1598603189-32145-5-git-send-email-magnus.karlsson@intel.com --- include/net/xdp_sock.h | 4 ++-- include/net/xsk_buff_pool.h | 2 +- net/xdp/xdp_umem.c | 15 -------------- net/xdp/xsk.c | 48 +++++++++++++++++++++++++-------------------- net/xdp/xsk_buff_pool.c | 20 ++++++++++++++----- net/xdp/xsk_diag.c | 12 +++++++----- 6 files changed, 52 insertions(+), 49 deletions(-) (limited to 'include/net') diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index ea2b020c4fbc..2a284e137e9a 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -18,8 +18,6 @@ struct xsk_queue; struct xdp_buff; struct xdp_umem { - struct xsk_queue *fq; - struct xsk_queue *cq; u64 size; u32 headroom; u32 chunk_size; @@ -77,6 +75,8 @@ struct xdp_sock { struct list_head map_list; /* Protects map_list */ spinlock_t map_list_lock; + struct xsk_queue *fq_tmp; /* Only as tmp storage before bind */ + struct xsk_queue *cq_tmp; /* Only as tmp storage before bind */ }; #ifdef CONFIG_XDP_SOCKETS diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index 4025486cc057..380d9aeedbea 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -30,6 +30,7 @@ struct xdp_buff_xsk { struct xsk_buff_pool { struct xsk_queue *fq; + struct xsk_queue *cq; struct list_head free_list; dma_addr_t *dma_pages; struct xdp_buff_xsk *heads; @@ -57,7 +58,6 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, struct xdp_umem *umem); int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev, u16 queue_id, u16 flags); -void xp_set_fq(struct xsk_buff_pool *pool, struct xsk_queue *fq); void xp_destroy(struct xsk_buff_pool *pool); void xp_release(struct xdp_buff_xsk *xskb); void xp_get_pool(struct xsk_buff_pool *pool); diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index f290345fb6c7..7d86a637367f 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -85,16 +85,6 @@ static void xdp_umem_release(struct xdp_umem *umem) ida_simple_remove(&umem_ida, umem->id); - if (umem->fq) { - xskq_destroy(umem->fq); - umem->fq = NULL; - } - - if (umem->cq) { - xskq_destroy(umem->cq); - umem->cq = NULL; - } - xdp_umem_unpin_pages(umem); xdp_umem_unaccount_pages(umem); @@ -278,8 +268,3 @@ struct xdp_umem *xdp_umem_create(struct xdp_umem_reg *mr) return umem; } - -bool xdp_umem_validate_queues(struct xdp_umem *umem) -{ - return umem->fq && umem->cq; -} diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 5739f1951d7a..dacd34034973 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -36,7 +36,7 @@ static DEFINE_PER_CPU(struct list_head, xskmap_flush_list); bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs) { return READ_ONCE(xs->rx) && READ_ONCE(xs->umem) && - READ_ONCE(xs->umem->fq); + (xs->pool->fq || READ_ONCE(xs->fq_tmp)); } void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool) @@ -46,7 +46,7 @@ void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool) if (umem->need_wakeup & XDP_WAKEUP_RX) return; - umem->fq->ring->flags |= XDP_RING_NEED_WAKEUP; + pool->fq->ring->flags |= XDP_RING_NEED_WAKEUP; umem->need_wakeup |= XDP_WAKEUP_RX; } EXPORT_SYMBOL(xsk_set_rx_need_wakeup); @@ -76,7 +76,7 @@ void xsk_clear_rx_need_wakeup(struct xsk_buff_pool *pool) if (!(umem->need_wakeup & XDP_WAKEUP_RX)) return; - umem->fq->ring->flags &= ~XDP_RING_NEED_WAKEUP; + pool->fq->ring->flags &= ~XDP_RING_NEED_WAKEUP; umem->need_wakeup &= ~XDP_WAKEUP_RX; } EXPORT_SYMBOL(xsk_clear_rx_need_wakeup); @@ -254,7 +254,7 @@ static int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, static void xsk_flush(struct xdp_sock *xs) { xskq_prod_submit(xs->rx); - __xskq_cons_release(xs->umem->fq); + __xskq_cons_release(xs->pool->fq); sock_def_readable(&xs->sk); } @@ -297,7 +297,7 @@ void __xsk_map_flush(void) void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries) { - xskq_prod_submit_n(pool->umem->cq, nb_entries); + xskq_prod_submit_n(pool->cq, nb_entries); } EXPORT_SYMBOL(xsk_tx_completed); @@ -331,7 +331,7 @@ bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc) * if there is space in it. This avoids having to implement * any buffering in the Tx path. */ - if (xskq_prod_reserve_addr(umem->cq, desc->addr)) + if (xskq_prod_reserve_addr(pool->cq, desc->addr)) goto out; xskq_cons_release(xs->tx); @@ -369,7 +369,7 @@ static void xsk_destruct_skb(struct sk_buff *skb) unsigned long flags; spin_lock_irqsave(&xs->tx_completion_lock, flags); - xskq_prod_submit_addr(xs->umem->cq, addr); + xskq_prod_submit_addr(xs->pool->cq, addr); spin_unlock_irqrestore(&xs->tx_completion_lock, flags); sock_wfree(skb); @@ -413,7 +413,7 @@ static int xsk_generic_xmit(struct sock *sk) * if there is space in it. This avoids having to implement * any buffering in the Tx path. */ - if (unlikely(err) || xskq_prod_reserve(xs->umem->cq)) { + if (unlikely(err) || xskq_prod_reserve(xs->pool->cq)) { kfree_skb(skb); goto out; } @@ -606,6 +606,8 @@ static int xsk_release(struct socket *sock) xskq_destroy(xs->rx); xskq_destroy(xs->tx); + xskq_destroy(xs->fq_tmp); + xskq_destroy(xs->cq_tmp); sock_orphan(sk); sock->sk = NULL; @@ -633,6 +635,11 @@ static struct socket *xsk_lookup_xsk_from_fd(int fd) return sock; } +static bool xsk_validate_queues(struct xdp_sock *xs) +{ + return xs->fq_tmp && xs->cq_tmp; +} + static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) { struct sockaddr_xdp *sxdp = (struct sockaddr_xdp *)addr; @@ -689,6 +696,12 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) goto out_unlock; } + if (xs->fq_tmp || xs->cq_tmp) { + /* Do not allow setting your own fq or cq. */ + err = -EINVAL; + goto out_unlock; + } + sock = xsk_lookup_xsk_from_fd(sxdp->sxdp_shared_umem_fd); if (IS_ERR(sock)) { err = PTR_ERR(sock); @@ -713,7 +726,7 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) xdp_get_umem(umem_xs->umem); WRITE_ONCE(xs->umem, umem_xs->umem); sockfd_put(sock); - } else if (!xs->umem || !xdp_umem_validate_queues(xs->umem)) { + } else if (!xs->umem || !xsk_validate_queues(xs)) { err = -EINVAL; goto out_unlock; } else { @@ -849,11 +862,9 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname, return -EINVAL; } - q = (optname == XDP_UMEM_FILL_RING) ? &xs->umem->fq : - &xs->umem->cq; + q = (optname == XDP_UMEM_FILL_RING) ? &xs->fq_tmp : + &xs->cq_tmp; err = xsk_init_queue(entries, q, true); - if (optname == XDP_UMEM_FILL_RING) - xp_set_fq(xs->pool, *q); mutex_unlock(&xs->mutex); return err; } @@ -920,7 +931,7 @@ static int xsk_getsockopt(struct socket *sock, int level, int optname, if (extra_stats) { stats.rx_ring_full = xs->rx_queue_full; stats.rx_fill_ring_empty_descs = - xs->umem ? xskq_nb_queue_empty_descs(xs->umem->fq) : 0; + xs->pool ? xskq_nb_queue_empty_descs(xs->pool->fq) : 0; stats.tx_ring_empty_descs = xskq_nb_queue_empty_descs(xs->tx); } else { stats.rx_dropped += xs->rx_queue_full; @@ -1022,7 +1033,6 @@ static int xsk_mmap(struct file *file, struct socket *sock, unsigned long size = vma->vm_end - vma->vm_start; struct xdp_sock *xs = xdp_sk(sock->sk); struct xsk_queue *q = NULL; - struct xdp_umem *umem; unsigned long pfn; struct page *qpg; @@ -1034,16 +1044,12 @@ static int xsk_mmap(struct file *file, struct socket *sock, } else if (offset == XDP_PGOFF_TX_RING) { q = READ_ONCE(xs->tx); } else { - umem = READ_ONCE(xs->umem); - if (!umem) - return -EINVAL; - /* Matches the smp_wmb() in XDP_UMEM_REG */ smp_rmb(); if (offset == XDP_UMEM_PGOFF_FILL_RING) - q = READ_ONCE(umem->fq); + q = READ_ONCE(xs->fq_tmp); else if (offset == XDP_UMEM_PGOFF_COMPLETION_RING) - q = READ_ONCE(umem->cq); + q = READ_ONCE(xs->cq_tmp); } if (!q) diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index e58c54d68c3d..36287d2c5095 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -65,6 +65,11 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, INIT_LIST_HEAD(&pool->free_list); refcount_set(&pool->users, 1); + pool->fq = xs->fq_tmp; + pool->cq = xs->cq_tmp; + xs->fq_tmp = NULL; + xs->cq_tmp = NULL; + for (i = 0; i < pool->free_heads_cnt; i++) { xskb = &pool->heads[i]; xskb->pool = pool; @@ -81,11 +86,6 @@ out: return NULL; } -void xp_set_fq(struct xsk_buff_pool *pool, struct xsk_queue *fq) -{ - pool->fq = fq; -} - void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq) { u32 i; @@ -189,6 +189,16 @@ static void xp_release_deferred(struct work_struct *work) xp_clear_dev(pool); rtnl_unlock(); + if (pool->fq) { + xskq_destroy(pool->fq); + pool->fq = NULL; + } + + if (pool->cq) { + xskq_destroy(pool->cq); + pool->cq = NULL; + } + xdp_put_umem(pool->umem); xp_destroy(pool); } diff --git a/net/xdp/xsk_diag.c b/net/xdp/xsk_diag.c index 21e9c2d123ee..52675ea067bf 100644 --- a/net/xdp/xsk_diag.c +++ b/net/xdp/xsk_diag.c @@ -46,6 +46,7 @@ static int xsk_diag_put_rings_cfg(const struct xdp_sock *xs, static int xsk_diag_put_umem(const struct xdp_sock *xs, struct sk_buff *nlskb) { + struct xsk_buff_pool *pool = xs->pool; struct xdp_umem *umem = xs->umem; struct xdp_diag_umem du = {}; int err; @@ -67,10 +68,11 @@ static int xsk_diag_put_umem(const struct xdp_sock *xs, struct sk_buff *nlskb) err = nla_put(nlskb, XDP_DIAG_UMEM, sizeof(du), &du); - if (!err && umem->fq) - err = xsk_diag_put_ring(umem->fq, XDP_DIAG_UMEM_FILL_RING, nlskb); - if (!err && umem->cq) { - err = xsk_diag_put_ring(umem->cq, XDP_DIAG_UMEM_COMPLETION_RING, + if (!err && pool->fq) + err = xsk_diag_put_ring(pool->fq, + XDP_DIAG_UMEM_FILL_RING, nlskb); + if (!err && pool->cq) { + err = xsk_diag_put_ring(pool->cq, XDP_DIAG_UMEM_COMPLETION_RING, nlskb); } return err; @@ -83,7 +85,7 @@ static int xsk_diag_put_stats(const struct xdp_sock *xs, struct sk_buff *nlskb) du.n_rx_dropped = xs->rx_dropped; du.n_rx_invalid = xskq_nb_invalid_descs(xs->rx); du.n_rx_full = xs->rx_queue_full; - du.n_fill_ring_empty = xs->umem ? xskq_nb_queue_empty_descs(xs->umem->fq) : 0; + du.n_fill_ring_empty = xs->pool ? xskq_nb_queue_empty_descs(xs->pool->fq) : 0; du.n_tx_invalid = xskq_nb_invalid_descs(xs->tx); du.n_tx_ring_empty = xskq_nb_queue_empty_descs(xs->tx); return nla_put(nlskb, XDP_DIAG_STATS, sizeof(du), &du); -- cgit v1.2.3 From c2d3d6a474629e30428b1622af3d551f560cd1d8 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Fri, 28 Aug 2020 10:26:19 +0200 Subject: xsk: Move queue_id, dev and need_wakeup to buffer pool MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Move queue_id, dev, and need_wakeup from the umem to the buffer pool. This so that we in a later commit can share the umem between multiple HW queues. There is one buffer pool per dev and queue id, so these variables should belong to the buffer pool, not the umem. Need_wakeup is also something that is set on a per napi level, so there is usually one per device and queue id. So move this to the buffer pool too. Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Acked-by: Björn Töpel Link: https://lore.kernel.org/bpf/1598603189-32145-6-git-send-email-magnus.karlsson@intel.com --- include/net/xdp_sock.h | 3 --- include/net/xsk_buff_pool.h | 4 ++++ net/xdp/xdp_umem.c | 22 ++-------------------- net/xdp/xdp_umem.h | 4 ---- net/xdp/xsk.c | 34 +++++++++++++--------------------- net/xdp/xsk.h | 7 ------- net/xdp/xsk_buff_pool.c | 39 ++++++++++++++++++++++----------------- net/xdp/xsk_diag.c | 4 ++-- 8 files changed, 43 insertions(+), 74 deletions(-) (limited to 'include/net') diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index 2a284e137e9a..b052f1c005a9 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -26,11 +26,8 @@ struct xdp_umem { refcount_t users; struct page **pgs; u32 npgs; - u16 queue_id; - u8 need_wakeup; u8 flags; int id; - struct net_device *dev; bool zc; spinlock_t xsk_tx_list_lock; struct list_head xsk_tx_list; diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index 380d9aeedbea..2d948905f05f 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -43,11 +43,15 @@ struct xsk_buff_pool { u32 headroom; u32 chunk_size; u32 frame_len; + u16 queue_id; + u8 cached_need_wakeup; + bool uses_need_wakeup; bool dma_need_sync; bool unaligned; struct xdp_umem *umem; void *addrs; struct device *dev; + struct net_device *netdev; refcount_t users; struct work_struct work; struct xdp_buff_xsk *free_heads[]; diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index 7d86a637367f..3e612fc818fa 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -63,26 +63,9 @@ static void xdp_umem_unaccount_pages(struct xdp_umem *umem) } } -void xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, - u16 queue_id) -{ - umem->dev = dev; - umem->queue_id = queue_id; - - dev_hold(dev); -} - -void xdp_umem_clear_dev(struct xdp_umem *umem) -{ - dev_put(umem->dev); - umem->dev = NULL; - umem->zc = false; -} - static void xdp_umem_release(struct xdp_umem *umem) { - xdp_umem_clear_dev(umem); - + umem->zc = false; ida_simple_remove(&umem_ida, umem->id); xdp_umem_unpin_pages(umem); @@ -181,8 +164,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) return -EINVAL; } - if (mr->flags & ~(XDP_UMEM_UNALIGNED_CHUNK_FLAG | - XDP_UMEM_USES_NEED_WAKEUP)) + if (mr->flags & ~XDP_UMEM_UNALIGNED_CHUNK_FLAG) return -EINVAL; if (!unaligned_chunks && !is_power_of_2(chunk_size)) diff --git a/net/xdp/xdp_umem.h b/net/xdp/xdp_umem.h index 93e96be6f4de..67bf3f34d6c2 100644 --- a/net/xdp/xdp_umem.h +++ b/net/xdp/xdp_umem.h @@ -8,10 +8,6 @@ #include -void xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, - u16 queue_id); -void xdp_umem_clear_dev(struct xdp_umem *umem); -bool xdp_umem_validate_queues(struct xdp_umem *umem); void xdp_get_umem(struct xdp_umem *umem); void xdp_put_umem(struct xdp_umem *umem); void xdp_add_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs); diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index dacd34034973..9f1b906ed0e7 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -41,13 +41,11 @@ bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs) void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool) { - struct xdp_umem *umem = pool->umem; - - if (umem->need_wakeup & XDP_WAKEUP_RX) + if (pool->cached_need_wakeup & XDP_WAKEUP_RX) return; pool->fq->ring->flags |= XDP_RING_NEED_WAKEUP; - umem->need_wakeup |= XDP_WAKEUP_RX; + pool->cached_need_wakeup |= XDP_WAKEUP_RX; } EXPORT_SYMBOL(xsk_set_rx_need_wakeup); @@ -56,7 +54,7 @@ void xsk_set_tx_need_wakeup(struct xsk_buff_pool *pool) struct xdp_umem *umem = pool->umem; struct xdp_sock *xs; - if (umem->need_wakeup & XDP_WAKEUP_TX) + if (pool->cached_need_wakeup & XDP_WAKEUP_TX) return; rcu_read_lock(); @@ -65,19 +63,17 @@ void xsk_set_tx_need_wakeup(struct xsk_buff_pool *pool) } rcu_read_unlock(); - umem->need_wakeup |= XDP_WAKEUP_TX; + pool->cached_need_wakeup |= XDP_WAKEUP_TX; } EXPORT_SYMBOL(xsk_set_tx_need_wakeup); void xsk_clear_rx_need_wakeup(struct xsk_buff_pool *pool) { - struct xdp_umem *umem = pool->umem; - - if (!(umem->need_wakeup & XDP_WAKEUP_RX)) + if (!(pool->cached_need_wakeup & XDP_WAKEUP_RX)) return; pool->fq->ring->flags &= ~XDP_RING_NEED_WAKEUP; - umem->need_wakeup &= ~XDP_WAKEUP_RX; + pool->cached_need_wakeup &= ~XDP_WAKEUP_RX; } EXPORT_SYMBOL(xsk_clear_rx_need_wakeup); @@ -86,7 +82,7 @@ void xsk_clear_tx_need_wakeup(struct xsk_buff_pool *pool) struct xdp_umem *umem = pool->umem; struct xdp_sock *xs; - if (!(umem->need_wakeup & XDP_WAKEUP_TX)) + if (!(pool->cached_need_wakeup & XDP_WAKEUP_TX)) return; rcu_read_lock(); @@ -95,13 +91,13 @@ void xsk_clear_tx_need_wakeup(struct xsk_buff_pool *pool) } rcu_read_unlock(); - umem->need_wakeup &= ~XDP_WAKEUP_TX; + pool->cached_need_wakeup &= ~XDP_WAKEUP_TX; } EXPORT_SYMBOL(xsk_clear_tx_need_wakeup); bool xsk_uses_need_wakeup(struct xsk_buff_pool *pool) { - return pool->umem->flags & XDP_UMEM_USES_NEED_WAKEUP; + return pool->uses_need_wakeup; } EXPORT_SYMBOL(xsk_uses_need_wakeup); @@ -478,16 +474,16 @@ static __poll_t xsk_poll(struct file *file, struct socket *sock, __poll_t mask = datagram_poll(file, sock, wait); struct sock *sk = sock->sk; struct xdp_sock *xs = xdp_sk(sk); - struct xdp_umem *umem; + struct xsk_buff_pool *pool; if (unlikely(!xsk_is_bound(xs))) return mask; - umem = xs->umem; + pool = xs->pool; - if (umem->need_wakeup) { + if (pool->cached_need_wakeup) { if (xs->zc) - xsk_wakeup(xs, umem->need_wakeup); + xsk_wakeup(xs, pool->cached_need_wakeup); else /* Poll needs to drive Tx also in copy mode */ __xsk_sendmsg(sk); @@ -731,11 +727,9 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) goto out_unlock; } else { /* This xsk has its own umem. */ - xdp_umem_assign_dev(xs->umem, dev, qid); xs->pool = xp_create_and_assign_umem(xs, xs->umem); if (!xs->pool) { err = -ENOMEM; - xdp_umem_clear_dev(xs->umem); goto out_unlock; } @@ -743,7 +737,6 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) if (err) { xp_destroy(xs->pool); xs->pool = NULL; - xdp_umem_clear_dev(xs->umem); goto out_unlock; } } @@ -1089,7 +1082,6 @@ static int xsk_notifier(struct notifier_block *this, /* Clear device references. */ xp_clear_dev(xs->pool); - xdp_umem_clear_dev(xs->umem); } mutex_unlock(&xs->mutex); } diff --git a/net/xdp/xsk.h b/net/xdp/xsk.h index a00e3e2a9ef1..da1f73e43924 100644 --- a/net/xdp/xsk.h +++ b/net/xdp/xsk.h @@ -11,13 +11,6 @@ #define XSK_NEXT_PG_CONTIG_SHIFT 0 #define XSK_NEXT_PG_CONTIG_MASK BIT_ULL(XSK_NEXT_PG_CONTIG_SHIFT) -/* Flags for the umem flags field. - * - * The NEED_WAKEUP flag is 1 due to the reuse of the flags field for public - * flags. See inlude/uapi/include/linux/if_xdp.h. - */ -#define XDP_UMEM_USES_NEED_WAKEUP BIT(1) - struct xdp_ring_offset_v1 { __u64 producer; __u64 consumer; diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index 36287d2c5095..436648a04f6a 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -95,10 +95,9 @@ void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq) } EXPORT_SYMBOL(xp_set_rxq_info); -int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev, +int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *netdev, u16 queue_id, u16 flags) { - struct xdp_umem *umem = pool->umem; bool force_zc, force_copy; struct netdev_bpf bpf; int err = 0; @@ -111,27 +110,30 @@ int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev, if (force_zc && force_copy) return -EINVAL; - if (xsk_get_pool_from_qid(dev, queue_id)) + if (xsk_get_pool_from_qid(netdev, queue_id)) return -EBUSY; - err = xsk_reg_pool_at_qid(dev, pool, queue_id); + err = xsk_reg_pool_at_qid(netdev, pool, queue_id); if (err) return err; if (flags & XDP_USE_NEED_WAKEUP) { - umem->flags |= XDP_UMEM_USES_NEED_WAKEUP; + pool->uses_need_wakeup = true; /* Tx needs to be explicitly woken up the first time. * Also for supporting drivers that do not implement this * feature. They will always have to call sendto(). */ - umem->need_wakeup = XDP_WAKEUP_TX; + pool->cached_need_wakeup = XDP_WAKEUP_TX; } + dev_hold(netdev); + if (force_copy) /* For copy-mode, we are done. */ return 0; - if (!dev->netdev_ops->ndo_bpf || !dev->netdev_ops->ndo_xsk_wakeup) { + if (!netdev->netdev_ops->ndo_bpf || + !netdev->netdev_ops->ndo_xsk_wakeup) { err = -EOPNOTSUPP; goto err_unreg_pool; } @@ -140,44 +142,47 @@ int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev, bpf.xsk.pool = pool; bpf.xsk.queue_id = queue_id; - err = dev->netdev_ops->ndo_bpf(dev, &bpf); + err = netdev->netdev_ops->ndo_bpf(netdev, &bpf); if (err) goto err_unreg_pool; - umem->zc = true; + pool->netdev = netdev; + pool->queue_id = queue_id; + pool->umem->zc = true; return 0; err_unreg_pool: if (!force_zc) err = 0; /* fallback to copy mode */ if (err) - xsk_clear_pool_at_qid(dev, queue_id); + xsk_clear_pool_at_qid(netdev, queue_id); return err; } void xp_clear_dev(struct xsk_buff_pool *pool) { - struct xdp_umem *umem = pool->umem; struct netdev_bpf bpf; int err; ASSERT_RTNL(); - if (!umem->dev) + if (!pool->netdev) return; - if (umem->zc) { + if (pool->umem->zc) { bpf.command = XDP_SETUP_XSK_POOL; bpf.xsk.pool = NULL; - bpf.xsk.queue_id = umem->queue_id; + bpf.xsk.queue_id = pool->queue_id; - err = umem->dev->netdev_ops->ndo_bpf(umem->dev, &bpf); + err = pool->netdev->netdev_ops->ndo_bpf(pool->netdev, &bpf); if (err) - WARN(1, "failed to disable umem!\n"); + WARN(1, "Failed to disable zero-copy!\n"); } - xsk_clear_pool_at_qid(umem->dev, umem->queue_id); + xsk_clear_pool_at_qid(pool->netdev, pool->queue_id); + dev_put(pool->netdev); + pool->netdev = NULL; } static void xp_release_deferred(struct work_struct *work) diff --git a/net/xdp/xsk_diag.c b/net/xdp/xsk_diag.c index 52675ea067bf..5bd8ea9d206a 100644 --- a/net/xdp/xsk_diag.c +++ b/net/xdp/xsk_diag.c @@ -59,8 +59,8 @@ static int xsk_diag_put_umem(const struct xdp_sock *xs, struct sk_buff *nlskb) du.num_pages = umem->npgs; du.chunk_size = umem->chunk_size; du.headroom = umem->headroom; - du.ifindex = umem->dev ? umem->dev->ifindex : 0; - du.queue_id = umem->queue_id; + du.ifindex = pool->netdev ? pool->netdev->ifindex : 0; + du.queue_id = pool->queue_id; du.flags = 0; if (umem->zc) du.flags |= XDP_DU_F_ZEROCOPY; -- cgit v1.2.3 From a5aa8e529e3667eb377ec132d4b4926dee065a45 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Fri, 28 Aug 2020 10:26:20 +0200 Subject: xsk: Move xsk_tx_list and its lock to buffer pool MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Move the xsk_tx_list and the xsk_tx_list_lock from the umem to the buffer pool. This so that we in a later commit can share the umem between multiple HW queues. There is one xsk_tx_list per device and queue id, so it should be located in the buffer pool. Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Acked-by: Björn Töpel Link: https://lore.kernel.org/bpf/1598603189-32145-7-git-send-email-magnus.karlsson@intel.com --- include/net/xdp_sock.h | 4 +--- include/net/xsk_buff_pool.h | 5 +++++ net/xdp/xdp_umem.c | 26 -------------------------- net/xdp/xdp_umem.h | 2 -- net/xdp/xsk.c | 15 ++++++--------- net/xdp/xsk_buff_pool.c | 26 ++++++++++++++++++++++++++ 6 files changed, 38 insertions(+), 40 deletions(-) (limited to 'include/net') diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index b052f1c005a9..9a61d05ec132 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -29,8 +29,6 @@ struct xdp_umem { u8 flags; int id; bool zc; - spinlock_t xsk_tx_list_lock; - struct list_head xsk_tx_list; }; struct xsk_map { @@ -57,7 +55,7 @@ struct xdp_sock { /* Protects multiple processes in the control path */ struct mutex mutex; struct xsk_queue *tx ____cacheline_aligned_in_smp; - struct list_head list; + struct list_head tx_list; /* Mutual exclusion of NAPI TX thread and sendmsg error paths * in the SKB destructor callback. */ diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index 2d948905f05f..83f100c6d440 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -52,6 +52,9 @@ struct xsk_buff_pool { void *addrs; struct device *dev; struct net_device *netdev; + struct list_head xsk_tx_list; + /* Protects modifications to the xsk_tx_list */ + spinlock_t xsk_tx_list_lock; refcount_t users; struct work_struct work; struct xdp_buff_xsk *free_heads[]; @@ -67,6 +70,8 @@ void xp_release(struct xdp_buff_xsk *xskb); void xp_get_pool(struct xsk_buff_pool *pool); void xp_put_pool(struct xsk_buff_pool *pool); void xp_clear_dev(struct xsk_buff_pool *pool); +void xp_add_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs); +void xp_del_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs); /* AF_XDP, and XDP core. */ void xp_free(struct xdp_buff_xsk *xskb); diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index 3e612fc818fa..77515925f3c5 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -23,30 +23,6 @@ static DEFINE_IDA(umem_ida); -void xdp_add_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs) -{ - unsigned long flags; - - if (!xs->tx) - return; - - spin_lock_irqsave(&umem->xsk_tx_list_lock, flags); - list_add_rcu(&xs->list, &umem->xsk_tx_list); - spin_unlock_irqrestore(&umem->xsk_tx_list_lock, flags); -} - -void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs) -{ - unsigned long flags; - - if (!xs->tx) - return; - - spin_lock_irqsave(&umem->xsk_tx_list_lock, flags); - list_del_rcu(&xs->list); - spin_unlock_irqrestore(&umem->xsk_tx_list_lock, flags); -} - static void xdp_umem_unpin_pages(struct xdp_umem *umem) { unpin_user_pages_dirty_lock(umem->pgs, umem->npgs, true); @@ -205,8 +181,6 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) umem->pgs = NULL; umem->user = NULL; umem->flags = mr->flags; - INIT_LIST_HEAD(&umem->xsk_tx_list); - spin_lock_init(&umem->xsk_tx_list_lock); refcount_set(&umem->users, 1); diff --git a/net/xdp/xdp_umem.h b/net/xdp/xdp_umem.h index 67bf3f34d6c2..181fdda2f2a8 100644 --- a/net/xdp/xdp_umem.h +++ b/net/xdp/xdp_umem.h @@ -10,8 +10,6 @@ void xdp_get_umem(struct xdp_umem *umem); void xdp_put_umem(struct xdp_umem *umem); -void xdp_add_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs); -void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs); struct xdp_umem *xdp_umem_create(struct xdp_umem_reg *mr); #endif /* XDP_UMEM_H_ */ diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 9f1b906ed0e7..067e85424d36 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -51,14 +51,13 @@ EXPORT_SYMBOL(xsk_set_rx_need_wakeup); void xsk_set_tx_need_wakeup(struct xsk_buff_pool *pool) { - struct xdp_umem *umem = pool->umem; struct xdp_sock *xs; if (pool->cached_need_wakeup & XDP_WAKEUP_TX) return; rcu_read_lock(); - list_for_each_entry_rcu(xs, &umem->xsk_tx_list, list) { + list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) { xs->tx->ring->flags |= XDP_RING_NEED_WAKEUP; } rcu_read_unlock(); @@ -79,14 +78,13 @@ EXPORT_SYMBOL(xsk_clear_rx_need_wakeup); void xsk_clear_tx_need_wakeup(struct xsk_buff_pool *pool) { - struct xdp_umem *umem = pool->umem; struct xdp_sock *xs; if (!(pool->cached_need_wakeup & XDP_WAKEUP_TX)) return; rcu_read_lock(); - list_for_each_entry_rcu(xs, &umem->xsk_tx_list, list) { + list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) { xs->tx->ring->flags &= ~XDP_RING_NEED_WAKEUP; } rcu_read_unlock(); @@ -302,7 +300,7 @@ void xsk_tx_release(struct xsk_buff_pool *pool) struct xdp_sock *xs; rcu_read_lock(); - list_for_each_entry_rcu(xs, &pool->umem->xsk_tx_list, list) { + list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) { __xskq_cons_release(xs->tx); xs->sk.sk_write_space(&xs->sk); } @@ -312,11 +310,10 @@ EXPORT_SYMBOL(xsk_tx_release); bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc) { - struct xdp_umem *umem = pool->umem; struct xdp_sock *xs; rcu_read_lock(); - list_for_each_entry_rcu(xs, &umem->xsk_tx_list, list) { + list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) { if (!xskq_cons_peek_desc(xs->tx, desc, pool)) { xs->tx->queue_empty_descs++; continue; @@ -524,7 +521,7 @@ static void xsk_unbind_dev(struct xdp_sock *xs) WRITE_ONCE(xs->state, XSK_UNBOUND); /* Wait for driver to stop using the xdp socket. */ - xdp_del_sk_umem(xs->umem, xs); + xp_del_xsk(xs->pool, xs); xs->dev = NULL; synchronize_net(); dev_put(dev); @@ -744,7 +741,7 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) xs->dev = dev; xs->zc = xs->umem->zc; xs->queue_id = qid; - xdp_add_sk_umem(xs->umem, xs); + xp_add_xsk(xs->pool, xs); out_unlock: if (err) { diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index 436648a04f6a..dbd913ef4928 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -11,6 +11,30 @@ #include "xdp_umem.h" #include "xsk.h" +void xp_add_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs) +{ + unsigned long flags; + + if (!xs->tx) + return; + + spin_lock_irqsave(&pool->xsk_tx_list_lock, flags); + list_add_rcu(&xs->tx_list, &pool->xsk_tx_list); + spin_unlock_irqrestore(&pool->xsk_tx_list_lock, flags); +} + +void xp_del_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs) +{ + unsigned long flags; + + if (!xs->tx) + return; + + spin_lock_irqsave(&pool->xsk_tx_list_lock, flags); + list_del_rcu(&xs->tx_list); + spin_unlock_irqrestore(&pool->xsk_tx_list_lock, flags); +} + static void xp_addr_unmap(struct xsk_buff_pool *pool) { vunmap(pool->addrs); @@ -63,6 +87,8 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, XDP_PACKET_HEADROOM; pool->umem = umem; INIT_LIST_HEAD(&pool->free_list); + INIT_LIST_HEAD(&pool->xsk_tx_list); + spin_lock_init(&pool->xsk_tx_list_lock); refcount_set(&pool->users, 1); pool->fq = xs->fq_tmp; -- cgit v1.2.3 From 7f7ffa4e9c38f01d380ed9df6adb238fd5e6eea5 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Fri, 28 Aug 2020 10:26:21 +0200 Subject: xsk: Move addrs from buffer pool to umem MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Replicate the addrs pointer in the buffer pool to the umem. This mapping will be the same for all buffer pools sharing the same umem. In the buffer pool we leave the addrs pointer for performance reasons. Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Acked-by: Björn Töpel Link: https://lore.kernel.org/bpf/1598603189-32145-8-git-send-email-magnus.karlsson@intel.com --- include/net/xdp_sock.h | 1 + net/xdp/xdp_umem.c | 22 ++++++++++++++++++++++ net/xdp/xsk_buff_pool.c | 21 ++------------------- 3 files changed, 25 insertions(+), 19 deletions(-) (limited to 'include/net') diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index 9a61d05ec132..126d24364b5a 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -18,6 +18,7 @@ struct xsk_queue; struct xdp_buff; struct xdp_umem { + void *addrs; u64 size; u32 headroom; u32 chunk_size; diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index 77515925f3c5..77604c30aa0f 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -39,11 +39,27 @@ static void xdp_umem_unaccount_pages(struct xdp_umem *umem) } } +static void xdp_umem_addr_unmap(struct xdp_umem *umem) +{ + vunmap(umem->addrs); + umem->addrs = NULL; +} + +static int xdp_umem_addr_map(struct xdp_umem *umem, struct page **pages, + u32 nr_pages) +{ + umem->addrs = vmap(pages, nr_pages, VM_MAP, PAGE_KERNEL); + if (!umem->addrs) + return -ENOMEM; + return 0; +} + static void xdp_umem_release(struct xdp_umem *umem) { umem->zc = false; ida_simple_remove(&umem_ida, umem->id); + xdp_umem_addr_unmap(umem); xdp_umem_unpin_pages(umem); xdp_umem_unaccount_pages(umem); @@ -192,8 +208,14 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) if (err) goto out_account; + err = xdp_umem_addr_map(umem, umem->pgs, umem->npgs); + if (err) + goto out_unpin; + return 0; +out_unpin: + xdp_umem_unpin_pages(umem); out_account: xdp_umem_unaccount_pages(umem); return err; diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index dbd913ef4928..c56387439f67 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -35,26 +35,11 @@ void xp_del_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs) spin_unlock_irqrestore(&pool->xsk_tx_list_lock, flags); } -static void xp_addr_unmap(struct xsk_buff_pool *pool) -{ - vunmap(pool->addrs); -} - -static int xp_addr_map(struct xsk_buff_pool *pool, - struct page **pages, u32 nr_pages) -{ - pool->addrs = vmap(pages, nr_pages, VM_MAP, PAGE_KERNEL); - if (!pool->addrs) - return -ENOMEM; - return 0; -} - void xp_destroy(struct xsk_buff_pool *pool) { if (!pool) return; - xp_addr_unmap(pool); kvfree(pool->heads); kvfree(pool); } @@ -64,7 +49,6 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, { struct xsk_buff_pool *pool; struct xdp_buff_xsk *xskb; - int err; u32 i; pool = kvzalloc(struct_size(pool, free_heads, umem->chunks), @@ -86,6 +70,7 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, pool->frame_len = umem->chunk_size - umem->headroom - XDP_PACKET_HEADROOM; pool->umem = umem; + pool->addrs = umem->addrs; INIT_LIST_HEAD(&pool->free_list); INIT_LIST_HEAD(&pool->xsk_tx_list); spin_lock_init(&pool->xsk_tx_list_lock); @@ -103,9 +88,7 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, pool->free_heads[i] = xskb; } - err = xp_addr_map(pool, umem->pgs, umem->npgs); - if (!err) - return pool; + return pool; out: xp_destroy(pool); -- cgit v1.2.3 From 921b68692abb4fd02237b6875b2056bc59435116 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Fri, 28 Aug 2020 10:26:22 +0200 Subject: xsk: Enable sharing of dma mappings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Enable the sharing of dma mappings by moving them out from the buffer pool. Instead we put each dma mapped umem region in a list in the umem structure. If dma has already been mapped for this umem and device, it is not mapped again and the existing dma mappings are reused. Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Acked-by: Björn Töpel Link: https://lore.kernel.org/bpf/1598603189-32145-9-git-send-email-magnus.karlsson@intel.com --- include/net/xdp_sock.h | 1 + include/net/xsk_buff_pool.h | 13 ++++ net/xdp/xdp_umem.c | 1 + net/xdp/xsk_buff_pool.c | 183 ++++++++++++++++++++++++++++++++++---------- 4 files changed, 156 insertions(+), 42 deletions(-) (limited to 'include/net') diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index 126d24364b5a..282aeba0d20f 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -30,6 +30,7 @@ struct xdp_umem { u8 flags; int id; bool zc; + struct list_head xsk_dma_list; }; struct xsk_map { diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index 83f100c6d440..356d0ac74eba 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -28,10 +28,23 @@ struct xdp_buff_xsk { struct list_head free_list_node; }; +struct xsk_dma_map { + dma_addr_t *dma_pages; + struct device *dev; + struct net_device *netdev; + refcount_t users; + struct list_head list; /* Protected by the RTNL_LOCK */ + u32 dma_pages_cnt; + bool dma_need_sync; +}; + struct xsk_buff_pool { struct xsk_queue *fq; struct xsk_queue *cq; struct list_head free_list; + /* For performance reasons, each buff pool has its own array of dma_pages + * even when they are identical. + */ dma_addr_t *dma_pages; struct xdp_buff_xsk *heads; u64 chunk_mask; diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index 77604c30aa0f..a7227b447228 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -198,6 +198,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) umem->user = NULL; umem->flags = mr->flags; + INIT_LIST_HEAD(&umem->xsk_dma_list); refcount_set(&umem->users, 1); err = xdp_umem_account_pages(umem); diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index c56387439f67..547eb41f7837 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -104,6 +104,25 @@ void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq) } EXPORT_SYMBOL(xp_set_rxq_info); +static void xp_disable_drv_zc(struct xsk_buff_pool *pool) +{ + struct netdev_bpf bpf; + int err; + + ASSERT_RTNL(); + + if (pool->umem->zc) { + bpf.command = XDP_SETUP_XSK_POOL; + bpf.xsk.pool = NULL; + bpf.xsk.queue_id = pool->queue_id; + + err = pool->netdev->netdev_ops->ndo_bpf(pool->netdev, &bpf); + + if (err) + WARN(1, "Failed to disable zero-copy!\n"); + } +} + int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *netdev, u16 queue_id, u16 flags) { @@ -122,6 +141,8 @@ int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *netdev, if (xsk_get_pool_from_qid(netdev, queue_id)) return -EBUSY; + pool->netdev = netdev; + pool->queue_id = queue_id; err = xsk_reg_pool_at_qid(netdev, pool, queue_id); if (err) return err; @@ -155,11 +176,15 @@ int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *netdev, if (err) goto err_unreg_pool; - pool->netdev = netdev; - pool->queue_id = queue_id; + if (!pool->dma_pages) { + WARN(1, "Driver did not DMA map zero-copy buffers"); + goto err_unreg_xsk; + } pool->umem->zc = true; return 0; +err_unreg_xsk: + xp_disable_drv_zc(pool); err_unreg_pool: if (!force_zc) err = 0; /* fallback to copy mode */ @@ -170,25 +195,10 @@ err_unreg_pool: void xp_clear_dev(struct xsk_buff_pool *pool) { - struct netdev_bpf bpf; - int err; - - ASSERT_RTNL(); - if (!pool->netdev) return; - if (pool->umem->zc) { - bpf.command = XDP_SETUP_XSK_POOL; - bpf.xsk.pool = NULL; - bpf.xsk.queue_id = pool->queue_id; - - err = pool->netdev->netdev_ops->ndo_bpf(pool->netdev, &bpf); - - if (err) - WARN(1, "Failed to disable zero-copy!\n"); - } - + xp_disable_drv_zc(pool); xsk_clear_pool_at_qid(pool->netdev, pool->queue_id); dev_put(pool->netdev); pool->netdev = NULL; @@ -233,70 +243,159 @@ void xp_put_pool(struct xsk_buff_pool *pool) } } -void xp_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs) +static struct xsk_dma_map *xp_find_dma_map(struct xsk_buff_pool *pool) +{ + struct xsk_dma_map *dma_map; + + list_for_each_entry(dma_map, &pool->umem->xsk_dma_list, list) { + if (dma_map->netdev == pool->netdev) + return dma_map; + } + + return NULL; +} + +static struct xsk_dma_map *xp_create_dma_map(struct device *dev, struct net_device *netdev, + u32 nr_pages, struct xdp_umem *umem) +{ + struct xsk_dma_map *dma_map; + + dma_map = kzalloc(sizeof(*dma_map), GFP_KERNEL); + if (!dma_map) + return NULL; + + dma_map->dma_pages = kvcalloc(nr_pages, sizeof(*dma_map->dma_pages), GFP_KERNEL); + if (!dma_map) { + kfree(dma_map); + return NULL; + } + + dma_map->netdev = netdev; + dma_map->dev = dev; + dma_map->dma_need_sync = false; + dma_map->dma_pages_cnt = nr_pages; + refcount_set(&dma_map->users, 0); + list_add(&dma_map->list, &umem->xsk_dma_list); + return dma_map; +} + +static void xp_destroy_dma_map(struct xsk_dma_map *dma_map) +{ + list_del(&dma_map->list); + kvfree(dma_map->dma_pages); + kfree(dma_map); +} + +static void __xp_dma_unmap(struct xsk_dma_map *dma_map, unsigned long attrs) { dma_addr_t *dma; u32 i; - if (pool->dma_pages_cnt == 0) - return; - - for (i = 0; i < pool->dma_pages_cnt; i++) { - dma = &pool->dma_pages[i]; + for (i = 0; i < dma_map->dma_pages_cnt; i++) { + dma = &dma_map->dma_pages[i]; if (*dma) { - dma_unmap_page_attrs(pool->dev, *dma, PAGE_SIZE, + dma_unmap_page_attrs(dma_map->dev, *dma, PAGE_SIZE, DMA_BIDIRECTIONAL, attrs); *dma = 0; } } + xp_destroy_dma_map(dma_map); +} + +void xp_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs) +{ + struct xsk_dma_map *dma_map; + + if (pool->dma_pages_cnt == 0) + return; + + dma_map = xp_find_dma_map(pool); + if (!dma_map) { + WARN(1, "Could not find dma_map for device"); + return; + } + + if (!refcount_dec_and_test(&dma_map->users)) + return; + + __xp_dma_unmap(dma_map, attrs); kvfree(pool->dma_pages); pool->dma_pages_cnt = 0; pool->dev = NULL; } EXPORT_SYMBOL(xp_dma_unmap); -static void xp_check_dma_contiguity(struct xsk_buff_pool *pool) +static void xp_check_dma_contiguity(struct xsk_dma_map *dma_map) { u32 i; - for (i = 0; i < pool->dma_pages_cnt - 1; i++) { - if (pool->dma_pages[i] + PAGE_SIZE == pool->dma_pages[i + 1]) - pool->dma_pages[i] |= XSK_NEXT_PG_CONTIG_MASK; + for (i = 0; i < dma_map->dma_pages_cnt - 1; i++) { + if (dma_map->dma_pages[i] + PAGE_SIZE == dma_map->dma_pages[i + 1]) + dma_map->dma_pages[i] |= XSK_NEXT_PG_CONTIG_MASK; else - pool->dma_pages[i] &= ~XSK_NEXT_PG_CONTIG_MASK; + dma_map->dma_pages[i] &= ~XSK_NEXT_PG_CONTIG_MASK; } } +static int xp_init_dma_info(struct xsk_buff_pool *pool, struct xsk_dma_map *dma_map) +{ + pool->dma_pages = kvcalloc(dma_map->dma_pages_cnt, sizeof(*pool->dma_pages), GFP_KERNEL); + if (!pool->dma_pages) + return -ENOMEM; + + pool->dev = dma_map->dev; + pool->dma_pages_cnt = dma_map->dma_pages_cnt; + pool->dma_need_sync = dma_map->dma_need_sync; + refcount_inc(&dma_map->users); + memcpy(pool->dma_pages, dma_map->dma_pages, + pool->dma_pages_cnt * sizeof(*pool->dma_pages)); + + return 0; +} + int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev, unsigned long attrs, struct page **pages, u32 nr_pages) { + struct xsk_dma_map *dma_map; dma_addr_t dma; + int err; u32 i; - pool->dma_pages = kvcalloc(nr_pages, sizeof(*pool->dma_pages), - GFP_KERNEL); - if (!pool->dma_pages) - return -ENOMEM; + dma_map = xp_find_dma_map(pool); + if (dma_map) { + err = xp_init_dma_info(pool, dma_map); + if (err) + return err; - pool->dev = dev; - pool->dma_pages_cnt = nr_pages; - pool->dma_need_sync = false; + return 0; + } - for (i = 0; i < pool->dma_pages_cnt; i++) { + dma_map = xp_create_dma_map(dev, pool->netdev, nr_pages, pool->umem); + if (!dma_map) + return -ENOMEM; + + for (i = 0; i < dma_map->dma_pages_cnt; i++) { dma = dma_map_page_attrs(dev, pages[i], 0, PAGE_SIZE, DMA_BIDIRECTIONAL, attrs); if (dma_mapping_error(dev, dma)) { - xp_dma_unmap(pool, attrs); + __xp_dma_unmap(dma_map, attrs); return -ENOMEM; } if (dma_need_sync(dev, dma)) - pool->dma_need_sync = true; - pool->dma_pages[i] = dma; + dma_map->dma_need_sync = true; + dma_map->dma_pages[i] = dma; } if (pool->unaligned) - xp_check_dma_contiguity(pool); + xp_check_dma_contiguity(dma_map); + + err = xp_init_dma_info(pool, dma_map); + if (err) { + __xp_dma_unmap(dma_map, attrs); + return err; + } + return 0; } EXPORT_SYMBOL(xp_dma_map); -- cgit v1.2.3 From 8ef4e27eb3f03edfbfbe5657b8061f2a47757037 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Fri, 28 Aug 2020 10:26:23 +0200 Subject: xsk: Rearrange internal structs for better performance MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Rearrange the xdp_sock, xdp_umem and xsk_buff_pool structures so that they get smaller and align better to the cache lines. In the previous commits of this patch set, these structs have been reordered with the focus on functionality and simplicity, not performance. This patch improves throughput performance by around 3%. Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Acked-by: Björn Töpel Link: https://lore.kernel.org/bpf/1598603189-32145-10-git-send-email-magnus.karlsson@intel.com --- include/net/xdp_sock.h | 13 +++++++------ include/net/xsk_buff_pool.h | 27 +++++++++++++++------------ 2 files changed, 22 insertions(+), 18 deletions(-) (limited to 'include/net') diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index 282aeba0d20f..1a9559c0cbdd 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -23,13 +23,13 @@ struct xdp_umem { u32 headroom; u32 chunk_size; u32 chunks; + u32 npgs; struct user_struct *user; refcount_t users; - struct page **pgs; - u32 npgs; u8 flags; - int id; bool zc; + struct page **pgs; + int id; struct list_head xsk_dma_list; }; @@ -42,7 +42,7 @@ struct xsk_map { struct xdp_sock { /* struct sock must be the first member of struct xdp_sock */ struct sock sk; - struct xsk_queue *rx; + struct xsk_queue *rx ____cacheline_aligned_in_smp; struct net_device *dev; struct xdp_umem *umem; struct list_head flush_node; @@ -54,8 +54,7 @@ struct xdp_sock { XSK_BOUND, XSK_UNBOUND, } state; - /* Protects multiple processes in the control path */ - struct mutex mutex; + struct xsk_queue *tx ____cacheline_aligned_in_smp; struct list_head tx_list; /* Mutual exclusion of NAPI TX thread and sendmsg error paths @@ -72,6 +71,8 @@ struct xdp_sock { struct list_head map_list; /* Protects map_list */ spinlock_t map_list_lock; + /* Protects multiple processes in the control path */ + struct mutex mutex; struct xsk_queue *fq_tmp; /* Only as tmp storage before bind */ struct xsk_queue *cq_tmp; /* Only as tmp storage before bind */ }; diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index 356d0ac74eba..38d03a64c9ea 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -39,9 +39,22 @@ struct xsk_dma_map { }; struct xsk_buff_pool { - struct xsk_queue *fq; - struct xsk_queue *cq; + /* Members only used in the control path first. */ + struct device *dev; + struct net_device *netdev; + struct list_head xsk_tx_list; + /* Protects modifications to the xsk_tx_list */ + spinlock_t xsk_tx_list_lock; + refcount_t users; + struct xdp_umem *umem; + struct work_struct work; struct list_head free_list; + u32 heads_cnt; + u16 queue_id; + + /* Data path members as close to free_heads at the end as possible. */ + struct xsk_queue *fq ____cacheline_aligned_in_smp; + struct xsk_queue *cq; /* For performance reasons, each buff pool has its own array of dma_pages * even when they are identical. */ @@ -51,25 +64,15 @@ struct xsk_buff_pool { u64 addrs_cnt; u32 free_list_cnt; u32 dma_pages_cnt; - u32 heads_cnt; u32 free_heads_cnt; u32 headroom; u32 chunk_size; u32 frame_len; - u16 queue_id; u8 cached_need_wakeup; bool uses_need_wakeup; bool dma_need_sync; bool unaligned; - struct xdp_umem *umem; void *addrs; - struct device *dev; - struct net_device *netdev; - struct list_head xsk_tx_list; - /* Protects modifications to the xsk_tx_list */ - spinlock_t xsk_tx_list_lock; - refcount_t users; - struct work_struct work; struct xdp_buff_xsk *free_heads[]; }; -- cgit v1.2.3 From 9647c57b11e563f5b33a49ef72b347753917c21c Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Fri, 28 Aug 2020 10:26:24 +0200 Subject: xsk: i40e: ice: ixgbe: mlx5: Test for dma_need_sync earlier for better performance MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Test for dma_need_sync earlier to increase performance. xsk_buff_dma_sync_for_cpu() takes an xdp_buff as parameter and from that the xsk_buff_pool reference is dug out. Perf shows that this dereference causes a lot of cache misses. But as the buffer pool is now sent down to the driver at zero-copy initialization time, we might as well use this pointer directly, instead of going via the xsk_buff and we can do so already in xsk_buff_dma_sync_for_cpu() instead of in xp_dma_sync_for_cpu. This gets rid of these cache misses. Throughput increases with 3% for the xdpsock l2fwd sample application on my machine. Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Acked-by: Björn Töpel Link: https://lore.kernel.org/bpf/1598603189-32145-11-git-send-email-magnus.karlsson@intel.com --- drivers/net/ethernet/intel/i40e/i40e_xsk.c | 2 +- drivers/net/ethernet/intel/ice/ice_xsk.c | 2 +- drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c | 4 ++-- include/net/xdp_sock_drv.h | 7 +++++-- include/net/xsk_buff_pool.h | 3 --- 6 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include/net') diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 95b9a7e280fa..2a1153d8957b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -314,7 +314,7 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) bi = i40e_rx_bi(rx_ring, rx_ring->next_to_clean); (*bi)->data_end = (*bi)->data + size; - xsk_buff_dma_sync_for_cpu(*bi); + xsk_buff_dma_sync_for_cpu(*bi, rx_ring->xsk_pool); xdp_res = i40e_run_xdp_zc(rx_ring, *bi); if (xdp_res) { diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index dffef377c5cb..797886524054 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -595,7 +595,7 @@ int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget) rx_buf = &rx_ring->rx_buf[rx_ring->next_to_clean]; rx_buf->xdp->data_end = rx_buf->xdp->data + size; - xsk_buff_dma_sync_for_cpu(rx_buf->xdp); + xsk_buff_dma_sync_for_cpu(rx_buf->xdp, rx_ring->xsk_pool); xdp_res = ice_run_xdp_zc(rx_ring, rx_buf->xdp); if (xdp_res) { diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c index 6af34da45b8d..3771857cf887 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c @@ -287,7 +287,7 @@ int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector, } bi->xdp->data_end = bi->xdp->data + size; - xsk_buff_dma_sync_for_cpu(bi->xdp); + xsk_buff_dma_sync_for_cpu(bi->xdp, rx_ring->xsk_pool); xdp_res = ixgbe_run_xdp_zc(adapter, rx_ring, bi->xdp); if (xdp_res) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c index a33a1f762c70..902ce77d0178 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c @@ -48,7 +48,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, xdp->data_end = xdp->data + cqe_bcnt32; xdp_set_data_meta_invalid(xdp); - xsk_buff_dma_sync_for_cpu(xdp); + xsk_buff_dma_sync_for_cpu(xdp, rq->xsk_pool); prefetch(xdp->data); rcu_read_lock(); @@ -99,7 +99,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq, xdp->data_end = xdp->data + cqe_bcnt; xdp_set_data_meta_invalid(xdp); - xsk_buff_dma_sync_for_cpu(xdp); + xsk_buff_dma_sync_for_cpu(xdp, rq->xsk_pool); prefetch(xdp->data); if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_RESP_SEND)) { diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index a7c7d2eff860..5b1ee8a9976d 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -99,10 +99,13 @@ static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr) return xp_raw_get_data(pool, addr); } -static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp) +static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool) { struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp); + if (!pool->dma_need_sync) + return; + xp_dma_sync_for_cpu(xskb); } @@ -222,7 +225,7 @@ static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr) return NULL; } -static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp) +static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool) { } diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index 38d03a64c9ea..907537dddcac 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -114,9 +114,6 @@ static inline dma_addr_t xp_get_frame_dma(struct xdp_buff_xsk *xskb) void xp_dma_sync_for_cpu_slow(struct xdp_buff_xsk *xskb); static inline void xp_dma_sync_for_cpu(struct xdp_buff_xsk *xskb) { - if (!xskb->pool->dma_need_sync) - return; - xp_dma_sync_for_cpu_slow(xskb); } -- cgit v1.2.3 From b5aea28dca13456c1a08b9b2ef8a8b92598ac426 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Fri, 28 Aug 2020 10:26:25 +0200 Subject: xsk: Add shared umem support between queue ids MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add support to share a umem between queue ids on the same device. This mode can be invoked with the XDP_SHARED_UMEM bind flag. Previously, sharing was only supported within the same queue id and device, and you shared one set of fill and completion rings. However, note that when sharing a umem between queue ids, you need to create a fill ring and a completion ring and tie them to the socket before you do the bind with the XDP_SHARED_UMEM flag. This so that the single-producer single-consumer semantics can be upheld. Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Acked-by: Björn Töpel Link: https://lore.kernel.org/bpf/1598603189-32145-12-git-send-email-magnus.karlsson@intel.com --- include/net/xsk_buff_pool.h | 2 ++ net/xdp/xsk.c | 44 ++++++++++++++++++++++++++++++-------------- net/xdp/xsk_buff_pool.c | 26 ++++++++++++++++++++++++-- 3 files changed, 56 insertions(+), 16 deletions(-) (limited to 'include/net') diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index 907537dddcac..0140d086dc84 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -81,6 +81,8 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, struct xdp_umem *umem); int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev, u16 queue_id, u16 flags); +int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_umem *umem, + struct net_device *dev, u16 queue_id); void xp_destroy(struct xsk_buff_pool *pool); void xp_release(struct xdp_buff_xsk *xskb); void xp_get_pool(struct xsk_buff_pool *pool); diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 067e85424d36..ea8d2ec8386e 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -689,12 +689,6 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) goto out_unlock; } - if (xs->fq_tmp || xs->cq_tmp) { - /* Do not allow setting your own fq or cq. */ - err = -EINVAL; - goto out_unlock; - } - sock = xsk_lookup_xsk_from_fd(sxdp->sxdp_shared_umem_fd); if (IS_ERR(sock)) { err = PTR_ERR(sock); @@ -707,15 +701,41 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) sockfd_put(sock); goto out_unlock; } - if (umem_xs->dev != dev || umem_xs->queue_id != qid) { + if (umem_xs->dev != dev) { err = -EINVAL; sockfd_put(sock); goto out_unlock; } - /* Share the buffer pool with the other socket. */ - xp_get_pool(umem_xs->pool); - xs->pool = umem_xs->pool; + if (umem_xs->queue_id != qid) { + /* Share the umem with another socket on another qid */ + xs->pool = xp_create_and_assign_umem(xs, + umem_xs->umem); + if (!xs->pool) { + sockfd_put(sock); + goto out_unlock; + } + + err = xp_assign_dev_shared(xs->pool, umem_xs->umem, + dev, qid); + if (err) { + xp_destroy(xs->pool); + sockfd_put(sock); + goto out_unlock; + } + } else { + /* Share the buffer pool with the other socket. */ + if (xs->fq_tmp || xs->cq_tmp) { + /* Do not allow setting your own fq or cq. */ + err = -EINVAL; + sockfd_put(sock); + goto out_unlock; + } + + xp_get_pool(umem_xs->pool); + xs->pool = umem_xs->pool; + } + xdp_get_umem(umem_xs->umem); WRITE_ONCE(xs->umem, umem_xs->umem); sockfd_put(sock); @@ -847,10 +867,6 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname, mutex_unlock(&xs->mutex); return -EBUSY; } - if (!xs->umem) { - mutex_unlock(&xs->mutex); - return -EINVAL; - } q = (optname == XDP_UMEM_FILL_RING) ? &xs->fq_tmp : &xs->cq_tmp; diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index 547eb41f7837..795d7c81c0ca 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -123,8 +123,8 @@ static void xp_disable_drv_zc(struct xsk_buff_pool *pool) } } -int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *netdev, - u16 queue_id, u16 flags) +static int __xp_assign_dev(struct xsk_buff_pool *pool, + struct net_device *netdev, u16 queue_id, u16 flags) { bool force_zc, force_copy; struct netdev_bpf bpf; @@ -193,6 +193,28 @@ err_unreg_pool: return err; } +int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev, + u16 queue_id, u16 flags) +{ + return __xp_assign_dev(pool, dev, queue_id, flags); +} + +int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_umem *umem, + struct net_device *dev, u16 queue_id) +{ + u16 flags; + + /* One fill and completion ring required for each queue id. */ + if (!pool->fq || !pool->cq) + return -EINVAL; + + flags = umem->zc ? XDP_ZEROCOPY : XDP_COPY; + if (pool->uses_need_wakeup) + flags |= XDP_USE_NEED_WAKEUP; + + return __xp_assign_dev(pool, dev, queue_id, flags); +} + void xp_clear_dev(struct xsk_buff_pool *pool) { if (!pool->netdev) -- cgit v1.2.3