From 391145ba2accc48b596f3d438af1a6255b62a555 Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Tue, 31 Oct 2023 14:56:24 -0700 Subject: bpf: Add __bpf_kfunc_{start,end}_defs macros BPF kfuncs are meant to be called from BPF programs. Accordingly, most kfuncs are not called from anywhere in the kernel, which the -Wmissing-prototypes warning is unhappy about. We've peppered __diag_ignore_all("-Wmissing-prototypes", ... everywhere kfuncs are defined in the codebase to suppress this warning. This patch adds two macros meant to bound one or many kfunc definitions. All existing kfunc definitions which use these __diag calls to suppress -Wmissing-prototypes are migrated to use the newly-introduced macros. A new __diag_ignore_all - for "-Wmissing-declarations" - is added to the __bpf_kfunc_start_defs macro based on feedback from Andrii on an earlier version of this patch [0] and another recent mailing list thread [1]. In the future we might need to ignore different warnings or do other kfunc-specific things. This change will make it easier to make such modifications for all kfunc defs. [0]: https://lore.kernel.org/bpf/CAEf4BzaE5dRWtK6RPLnjTW-MW9sx9K3Fn6uwqCTChK2Dcb1Xig@mail.gmail.com/ [1]: https://lore.kernel.org/bpf/ZT+2qCc%2FaXep0%2FLf@krava/ Signed-off-by: Dave Marchevsky Suggested-by: Andrii Nakryiko Acked-by: Andrii Nakryiko Cc: Jiri Olsa Acked-by: Jiri Olsa Acked-by: David Vernet Acked-by: Yafang Shao Link: https://lore.kernel.org/r/20231031215625.2343848-1-davemarchevsky@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/btf.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/btf.h b/include/linux/btf.h index c2231c64d60b..dc5ce962f600 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -84,6 +84,15 @@ */ #define __bpf_kfunc __used noinline +#define __bpf_kfunc_start_defs() \ + __diag_push(); \ + __diag_ignore_all("-Wmissing-declarations", \ + "Global kfuncs as their definitions will be in BTF");\ + __diag_ignore_all("-Wmissing-prototypes", \ + "Global kfuncs as their definitions will be in BTF") + +#define __bpf_kfunc_end_defs() __diag_pop() + /* * Return the name of the passed struct, if exists, or halt the build if for * example the structure gets renamed. In this way, developers have to revisit -- cgit v1.2.3 From 15fb6f2b6c4c3c129adc2412ae12ec15e60a6adb Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Tue, 31 Oct 2023 14:56:25 -0700 Subject: bpf: Add __bpf_hook_{start,end} macros Not all uses of __diag_ignore_all(...) in BPF-related code in order to suppress warnings are wrapping kfunc definitions. Some "hook point" definitions - small functions meant to be used as attach points for fentry and similar BPF progs - need to suppress -Wmissing-declarations. We could use __bpf_kfunc_{start,end}_defs added in the previous patch in such cases, but this might be confusing to someone unfamiliar with BPF internals. Instead, this patch adds __bpf_hook_{start,end} macros, currently having the same effect as __bpf_kfunc_{start,end}_defs, then uses them to suppress warnings for two hook points in the kernel itself and some bpf_testmod hook points as well. Signed-off-by: Dave Marchevsky Cc: Yafang Shao Acked-by: Jiri Olsa Acked-by: Yafang Shao Link: https://lore.kernel.org/r/20231031215625.2343848-2-davemarchevsky@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/btf.h | 2 ++ kernel/cgroup/rstat.c | 9 +++------ net/socket.c | 8 ++------ tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c | 6 ++---- 4 files changed, 9 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/btf.h b/include/linux/btf.h index dc5ce962f600..59d404e22814 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -92,6 +92,8 @@ "Global kfuncs as their definitions will be in BTF") #define __bpf_kfunc_end_defs() __diag_pop() +#define __bpf_hook_start() __bpf_kfunc_start_defs() +#define __bpf_hook_end() __bpf_kfunc_end_defs() /* * Return the name of the passed struct, if exists, or halt the build if for diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index d80d7a608141..c0adb7254b45 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -156,19 +156,16 @@ static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos, * optimize away the callsite. Therefore, __weak is needed to ensure that the * call is still emitted, by telling the compiler that we don't know what the * function might eventually be. - * - * __diag_* below are needed to dismiss the missing prototype warning. */ -__diag_push(); -__diag_ignore_all("-Wmissing-prototypes", - "kfuncs which will be used in BPF programs"); + +__bpf_hook_start(); __weak noinline void bpf_rstat_flush(struct cgroup *cgrp, struct cgroup *parent, int cpu) { } -__diag_pop(); +__bpf_hook_end(); /* see cgroup_rstat_flush() */ static void cgroup_rstat_flush_locked(struct cgroup *cgrp) diff --git a/net/socket.c b/net/socket.c index 0d1c4e78fc7f..3379c64217a4 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1685,20 +1685,16 @@ struct file *__sys_socket_file(int family, int type, int protocol) * Therefore, __weak is needed to ensure that the call is still * emitted, by telling the compiler that we don't know what the * function might eventually be. - * - * __diag_* below are needed to dismiss the missing prototype warning. */ -__diag_push(); -__diag_ignore_all("-Wmissing-prototypes", - "A fmod_ret entry point for BPF programs"); +__bpf_hook_start(); __weak noinline int update_socket_protocol(int family, int type, int protocol) { return protocol; } -__diag_pop(); +__bpf_hook_end(); int __sys_socket(int family, int type, int protocol) { diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index a5e246f7b202..91907b321f91 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -39,9 +39,7 @@ struct bpf_testmod_struct_arg_4 { int b; }; -__diag_push(); -__diag_ignore_all("-Wmissing-prototypes", - "Global functions as their definitions will be in bpf_testmod.ko BTF"); +__bpf_hook_start(); noinline int bpf_testmod_test_struct_arg_1(struct bpf_testmod_struct_arg_2 a, int b, int c) { @@ -335,7 +333,7 @@ noinline int bpf_fentry_shadow_test(int a) } EXPORT_SYMBOL_GPL(bpf_fentry_shadow_test); -__diag_pop(); +__bpf_hook_end(); static struct bin_attribute bin_attr_bpf_testmod_file __ro_after_init = { .attr = { .name = "bpf_testmod", .mode = 0666, }, -- cgit v1.2.3 From f55d8e60f10909dbc5524e261041e1d28d7d20d8 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 28 Oct 2023 21:25:11 +0200 Subject: net: ethtool: Fix documentation of ethtool_sprintf() This function takes a pointer to a pointer, unlike sprintf() which is passed a plain pointer. Fix up the documentation to make this clear. Fixes: 7888fe53b706 ("ethtool: Add common function for filling out strings") Cc: Alexander Duyck Cc: Justin Stitt Cc: stable@vger.kernel.org Signed-off-by: Andrew Lunn Reviewed-by: Justin Stitt Link: https://lore.kernel.org/r/20231028192511.100001-1-andrew@lunn.ch Signed-off-by: Paolo Abeni --- include/linux/ethtool.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 226a36ed5aa1..689028257fcc 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -1045,10 +1045,10 @@ static inline int ethtool_mm_frag_size_min_to_add(u32 val_min, u32 *val_add, /** * ethtool_sprintf - Write formatted string to ethtool string data - * @data: Pointer to start of string to update + * @data: Pointer to a pointer to the start of string to update * @fmt: Format of string to write * - * Write formatted string to data. Update data to point at start of + * Write formatted string to *data. Update *data to point at start of * next string. */ extern __printf(2, 3) void ethtool_sprintf(u8 **data, const char *fmt, ...); -- cgit v1.2.3 From e8ae8ad479e2d037daa33756e5e72850a7bd37a9 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 24 Oct 2023 09:53:33 +1100 Subject: Fix termination state for idr_for_each_entry_ul() The comment for idr_for_each_entry_ul() states after normal termination @entry is left with the value NULL This is not correct in the case where UINT_MAX has an entry in the idr. In that case @entry will be non-NULL after termination. No current code depends on the documentation being correct, but to save future code we should fix it. Also fix idr_for_each_entry_continue_ul(). While this is not documented as leaving @entry as NULL, the mellanox driver appears to depend on it doing so. So make that explicit in the documentation as well as in the code. Fixes: e33d2b74d805 ("idr: fix overflow case for idr_for_each_entry_ul()") Cc: Matthew Wilcox Cc: Chris Mi Cc: Cong Wang Signed-off-by: NeilBrown Signed-off-by: David S. Miller --- include/linux/idr.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/idr.h b/include/linux/idr.h index a0dce14090a9..da5f5fa4a3a6 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -200,7 +200,7 @@ static inline void idr_preload_end(void) */ #define idr_for_each_entry_ul(idr, entry, tmp, id) \ for (tmp = 0, id = 0; \ - tmp <= id && ((entry) = idr_get_next_ul(idr, &(id))) != NULL; \ + ((entry) = tmp <= id ? idr_get_next_ul(idr, &(id)) : NULL) != NULL; \ tmp = id, ++id) /** @@ -224,10 +224,12 @@ static inline void idr_preload_end(void) * @id: Entry ID. * * Continue to iterate over entries, continuing after the current position. + * After normal termination @entry is left with the value NULL. This + * is convenient for a "not found" value. */ #define idr_for_each_entry_continue_ul(idr, entry, tmp, id) \ for (tmp = id; \ - tmp <= id && ((entry) = idr_get_next_ul(idr, &(id))) != NULL; \ + ((entry) = tmp <= id ? idr_get_next_ul(idr, &(id)) : NULL) != NULL; \ tmp = id, ++id) /* -- cgit v1.2.3 From cdbab6236605dc11780779d9af689aea7d58cab1 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 31 Oct 2023 06:19:45 +0000 Subject: tcp: fix fastopen code vs usec TS After blamed commit, TFO client-ack-dropped-then-recovery-ms-timestamps packetdrill test failed. David Morley and Neal Cardwell started investigating and Neal pointed that we had : tcp_conn_request() tcp_try_fastopen() -> tcp_fastopen_create_child -> child = inet_csk(sk)->icsk_af_ops->syn_recv_sock() -> tcp_create_openreq_child() -> copy req_usec_ts from req: newtp->tcp_usec_ts = treq->req_usec_ts; // now the new TFO server socket always does usec TS, no matter // what the route options are... send_synack() -> tcp_make_synack() // disable tcp_rsk(req)->req_usec_ts if route option is not present: if (tcp_rsk(req)->req_usec_ts < 0) tcp_rsk(req)->req_usec_ts = dst_tcp_usec_ts(dst); tcp_conn_request() has the initial dst, we can initialize tcp_rsk(req)->req_usec_ts there instead of later in send_synack(); This means tcp_rsk(req)->req_usec_ts can be a boolean. Many thanks to David an Neal for their help. Fixes: 614e8316aa4c ("tcp: add support for usec resolution in TCP TS values") Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-lkp/202310302216.f79d78bc-oliver.sang@intel.com Suggested-by: Neal Cardwell Signed-off-by: Eric Dumazet Cc: David Morley Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- include/linux/tcp.h | 2 +- net/ipv4/syncookies.c | 2 +- net/ipv4/tcp_input.c | 7 ++++--- net/ipv4/tcp_output.c | 2 -- 4 files changed, 6 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index ec4e9367f5b0..68f3d315d2e1 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -152,7 +152,7 @@ struct tcp_request_sock { u64 snt_synack; /* first SYNACK sent time */ bool tfo_listener; bool is_mptcp; - s8 req_usec_ts; + bool req_usec_ts; #if IS_ENABLED(CONFIG_MPTCP) bool drop_req; #endif diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 98b25e5d147b..d37282c06e3d 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -306,7 +306,7 @@ struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, treq->af_specific = af_ops; treq->syn_tos = TCP_SKB_CB(skb)->ip_dsfield; - treq->req_usec_ts = -1; + treq->req_usec_ts = false; #if IS_ENABLED(CONFIG_MPTCP) treq->is_mptcp = sk_is_mptcp(sk); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 50aaa1527150..bcb55d98004c 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -7115,7 +7115,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, req->syncookie = want_cookie; tcp_rsk(req)->af_specific = af_ops; tcp_rsk(req)->ts_off = 0; - tcp_rsk(req)->req_usec_ts = -1; + tcp_rsk(req)->req_usec_ts = false; #if IS_ENABLED(CONFIG_MPTCP) tcp_rsk(req)->is_mptcp = 0; #endif @@ -7143,9 +7143,10 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, if (!dst) goto drop_and_free; - if (tmp_opt.tstamp_ok) + if (tmp_opt.tstamp_ok) { + tcp_rsk(req)->req_usec_ts = dst_tcp_usec_ts(dst); tcp_rsk(req)->ts_off = af_ops->init_ts_off(net, skb); - + } if (!want_cookie && !isn) { int max_syn_backlog = READ_ONCE(net->ipv4.sysctl_max_syn_backlog); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index f558c054cf6e..0d8dd5b7e2e5 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3693,8 +3693,6 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, mss = tcp_mss_clamp(tp, dst_metric_advmss(dst)); memset(&opts, 0, sizeof(opts)); - if (tcp_rsk(req)->req_usec_ts < 0) - tcp_rsk(req)->req_usec_ts = dst_tcp_usec_ts(dst); now = tcp_clock_ns(); #ifdef CONFIG_SYN_COOKIES if (unlikely(synack_type == TCP_SYNACK_COOKIE && ireq->tstamp_ok)) -- cgit v1.2.3