From ca34ce29fc4b0e929cc6aada40829d17ab50fee4 Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Mon, 8 Aug 2022 09:47:23 -0700 Subject: bpf: Improve docstring for BPF_F_USER_BUILD_ID flag Most tools which use bpf_get_stack or bpf_get_stackid symbolicate the stack - meaning the stack of addresses in the target process' address space is transformed into meaningful symbol names. The BPF_F_USER_BUILD_ID flag eases this process by finding the build_id of the file-backed vma which the address falls in and translating the address to an offset within the backing file. To be more specific, the offset is a "file offset" from the beginning of the backing file. The symbols in ET_DYN ELF objects have a st_value which is also described as an "offset" - but an offset in the process address space, relative to the base address of the object. It's necessary to translate between the "file offset" and "virtual address offset" during symbolication before they can be directly compared. Failure to do so can lead to confusing bugs, so this patch clarifies language in the documentation in an attempt to keep this from happening. Signed-off-by: Dave Marchevsky Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20220808164723.3107500-1-davemarchevsky@fb.com --- include/uapi/linux/bpf.h | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 7bf9ba1329be..534e33fb1029 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3008,8 +3008,18 @@ union bpf_attr { * **BPF_F_USER_STACK** * Collect a user space stack instead of a kernel stack. * **BPF_F_USER_BUILD_ID** - * Collect buildid+offset instead of ips for user stack, - * only valid if **BPF_F_USER_STACK** is also specified. + * Collect (build_id, file_offset) instead of ips for user + * stack, only valid if **BPF_F_USER_STACK** is also + * specified. + * + * *file_offset* is an offset relative to the beginning + * of the executable or shared object file backing the vma + * which the *ip* falls in. It is *not* an offset relative + * to that object's base address. Accordingly, it must be + * adjusted by adding (sh_addr - sh_offset), where + * sh_{addr,offset} correspond to the executable section + * containing *file_offset* in the object, for comparisons + * to symbols' st_value to be valid. * * **bpf_get_stack**\ () can collect up to * **PERF_MAX_STACK_DEPTH** both kernel and user frames, subject -- cgit v1.2.3-59-g8ed1b From c8996c98f703b09afe77a1d247dae691c9849dc1 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Tue, 9 Aug 2022 08:08:02 +0200 Subject: bpf: Add BPF-helper for accessing CLOCK_TAI Commit 3dc6ffae2da2 ("timekeeping: Introduce fast accessor to clock tai") introduced a fast and NMI-safe accessor for CLOCK_TAI. Especially in time sensitive networks (TSN), where all nodes are synchronized by Precision Time Protocol (PTP), it's helpful to have the possibility to generate timestamps based on CLOCK_TAI instead of CLOCK_MONOTONIC. With a BPF helper for TAI in place, it becomes very convenient to correlate activity across different machines in the network. Use cases for such a BPF helper include functionalities such as Tx launch time (e.g. ETF and TAPRIO Qdiscs) and timestamping. Note: CLOCK_TAI is nothing new per se, only the NMI-safe variant of it is. Signed-off-by: Jesper Dangaard Brouer [Kurt: Wrote changelog and renamed helper] Signed-off-by: Kurt Kanzenbach Link: https://lore.kernel.org/r/20220809060803.5773-2-kurt@linutronix.de Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 13 +++++++++++++ kernel/bpf/core.c | 1 + kernel/bpf/helpers.c | 14 ++++++++++++++ tools/include/uapi/linux/bpf.h | 13 +++++++++++++ 5 files changed, 42 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 20c26aed7896..a627a02cf8ab 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2349,6 +2349,7 @@ extern const struct bpf_func_proto bpf_get_numa_node_id_proto; extern const struct bpf_func_proto bpf_tail_call_proto; extern const struct bpf_func_proto bpf_ktime_get_ns_proto; extern const struct bpf_func_proto bpf_ktime_get_boot_ns_proto; +extern const struct bpf_func_proto bpf_ktime_get_tai_ns_proto; extern const struct bpf_func_proto bpf_get_current_pid_tgid_proto; extern const struct bpf_func_proto bpf_get_current_uid_gid_proto; extern const struct bpf_func_proto bpf_get_current_comm_proto; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 534e33fb1029..7d1e2794d83e 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5341,6 +5341,18 @@ union bpf_attr { * **-EACCES** if the SYN cookie is not valid. * * **-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin. + * + * u64 bpf_ktime_get_tai_ns(void) + * Description + * A nonsettable system-wide clock derived from wall-clock time but + * ignoring leap seconds. This clock does not experience + * discontinuities and backwards jumps caused by NTP inserting leap + * seconds as CLOCK_REALTIME does. + * + * See: **clock_gettime**\ (**CLOCK_TAI**) + * Return + * Current *ktime*. + * */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5551,6 +5563,7 @@ union bpf_attr { FN(tcp_raw_gen_syncookie_ipv6), \ FN(tcp_raw_check_syncookie_ipv4), \ FN(tcp_raw_check_syncookie_ipv6), \ + FN(ktime_get_tai_ns), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index c1e10d088dbb..639437f36928 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2623,6 +2623,7 @@ const struct bpf_func_proto bpf_get_numa_node_id_proto __weak; const struct bpf_func_proto bpf_ktime_get_ns_proto __weak; const struct bpf_func_proto bpf_ktime_get_boot_ns_proto __weak; const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto __weak; +const struct bpf_func_proto bpf_ktime_get_tai_ns_proto __weak; const struct bpf_func_proto bpf_get_current_pid_tgid_proto __weak; const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 1f961f9982d2..a95eb9fb01ff 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -198,6 +198,18 @@ const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto = { .ret_type = RET_INTEGER, }; +BPF_CALL_0(bpf_ktime_get_tai_ns) +{ + /* NMI safe access to clock tai */ + return ktime_get_tai_fast_ns(); +} + +const struct bpf_func_proto bpf_ktime_get_tai_ns_proto = { + .func = bpf_ktime_get_tai_ns, + .gpl_only = false, + .ret_type = RET_INTEGER, +}; + BPF_CALL_0(bpf_get_current_pid_tgid) { struct task_struct *task = current; @@ -1617,6 +1629,8 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_ktime_get_ns_proto; case BPF_FUNC_ktime_get_boot_ns: return &bpf_ktime_get_boot_ns_proto; + case BPF_FUNC_ktime_get_tai_ns: + return &bpf_ktime_get_tai_ns_proto; case BPF_FUNC_ringbuf_output: return &bpf_ringbuf_output_proto; case BPF_FUNC_ringbuf_reserve: diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index f58d58e1d547..e174ad28aeb7 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -5341,6 +5341,18 @@ union bpf_attr { * **-EACCES** if the SYN cookie is not valid. * * **-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin. + * + * u64 bpf_ktime_get_tai_ns(void) + * Description + * A nonsettable system-wide clock derived from wall-clock time but + * ignoring leap seconds. This clock does not experience + * discontinuities and backwards jumps caused by NTP inserting leap + * seconds as CLOCK_REALTIME does. + * + * See: **clock_gettime**\ (**CLOCK_TAI**) + * Return + * Current *ktime*. + * */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5551,6 +5563,7 @@ union bpf_attr { FN(tcp_raw_gen_syncookie_ipv6), \ FN(tcp_raw_check_syncookie_ipv4), \ FN(tcp_raw_check_syncookie_ipv6), \ + FN(ktime_get_tai_ns), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3-59-g8ed1b From 4961d0772578e8737afe61370743f3bc22867111 Mon Sep 17 00:00:00 2001 From: Quentin Monnet Date: Fri, 12 Aug 2022 16:37:27 +0100 Subject: bpf: Clear up confusion in bpf_skb_adjust_room()'s documentation Adding or removing room space _below_ layers 2 or 3, as the description mentions, is ambiguous. This was written with a mental image of the packet with layer 2 at the top, layer 3 under it, and so on. But it has led users to believe that it was on lower layers (before the beginning of the L2 and L3 headers respectively). Let's make it more explicit, and specify between which layers the room space is adjusted. Reported-by: Rumen Telbizov Signed-off-by: Quentin Monnet Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20220812153727.224500-3-quentin@isovalent.com --- include/uapi/linux/bpf.h | 6 ++++-- tools/include/uapi/linux/bpf.h | 6 ++++-- 2 files changed, 8 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 7d1e2794d83e..934a2a8beb87 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2573,10 +2573,12 @@ union bpf_attr { * There are two supported modes at this time: * * * **BPF_ADJ_ROOM_MAC**: Adjust room at the mac layer - * (room space is added or removed below the layer 2 header). + * (room space is added or removed between the layer 2 and + * layer 3 headers). * * * **BPF_ADJ_ROOM_NET**: Adjust room at the network layer - * (room space is added or removed below the layer 3 header). + * (room space is added or removed between the layer 3 and + * layer 4 headers). * * The following flags are supported at this time: * diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index e174ad28aeb7..1d6085e15fc8 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -2573,10 +2573,12 @@ union bpf_attr { * There are two supported modes at this time: * * * **BPF_ADJ_ROOM_MAC**: Adjust room at the mac layer - * (room space is added or removed below the layer 2 header). + * (room space is added or removed between the layer 2 and + * layer 3 headers). * * * **BPF_ADJ_ROOM_NET**: Adjust room at the network layer - * (room space is added or removed below the layer 3 header). + * (room space is added or removed between the layer 3 and + * layer 4 headers). * * The following flags are supported at this time: * -- cgit v1.2.3-59-g8ed1b