diff options
author | 2018-12-05 13:16:24 -0500 | |
---|---|---|
committer | 2018-12-05 13:23:38 -0500 | |
commit | 14a4467a0a5eacb2ebbe3aab1b4e25af3519c76a (patch) | |
tree | 541647056606d3e0aa1e06e62d2b40417623f8cb /tools/perf/examples/bpf/augmented_raw_syscalls.c | |
parent | media: pixfmt-meta-d4xx.rst: Add a license to it (diff) | |
parent | Merge tag 'media/v4.20-4' of git://git.kernel.org/pub/scm/linux/kernel/git/mc... (diff) | |
download | linux-14a4467a0a5eacb2ebbe3aab1b4e25af3519c76a.tar.gz linux-14a4467a0a5eacb2ebbe3aab1b4e25af3519c76a.tar.bz2 linux-14a4467a0a5eacb2ebbe3aab1b4e25af3519c76a.zip |
Merge commit '0072a0c14d5b7cb72c611d396f143f5dcd73ebe2' into patchwork
Merge from Upstream after the latest media fixes branch, because we
need one patch that it is there.
* commit '0072a0c14d5b7cb72c611d396f143f5dcd73ebe2': (1108 commits)
ide: Change to use DEFINE_SHOW_ATTRIBUTE macro
ide: pmac: add of_node_put()
drivers/tty: add missing of_node_put()
drivers/sbus/char: add of_node_put()
sbus: char: add of_node_put()
Linux 4.20-rc5
PCI: Fix incorrect value returned from pcie_get_speed_cap()
MAINTAINERS: Update linux-mips mailing list address
ocfs2: fix potential use after free
mm/khugepaged: fix the xas_create_range() error path
mm/khugepaged: collapse_shmem() do not crash on Compound
mm/khugepaged: collapse_shmem() without freezing new_page
mm/khugepaged: minor reorderings in collapse_shmem()
mm/khugepaged: collapse_shmem() remember to clear holes
mm/khugepaged: fix crashes due to misaccounted holes
mm/khugepaged: collapse_shmem() stop if punched or truncated
mm/huge_memory: fix lockdep complaint on 32-bit i_size_read()
mm/huge_memory: splitting set mapping+index before unfreeze
mm/huge_memory: rename freeze_page() to unmap_page()
initramfs: clean old path before creating a hardlink
...
Diffstat (limited to 'tools/perf/examples/bpf/augmented_raw_syscalls.c')
-rw-r--r-- | tools/perf/examples/bpf/augmented_raw_syscalls.c | 131 |
1 files changed, 131 insertions, 0 deletions
diff --git a/tools/perf/examples/bpf/augmented_raw_syscalls.c b/tools/perf/examples/bpf/augmented_raw_syscalls.c new file mode 100644 index 000000000000..90a19336310b --- /dev/null +++ b/tools/perf/examples/bpf/augmented_raw_syscalls.c @@ -0,0 +1,131 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Augment the raw_syscalls tracepoints with the contents of the pointer arguments. + * + * Test it with: + * + * perf trace -e tools/perf/examples/bpf/augmented_raw_syscalls.c cat /etc/passwd > /dev/null + * + * This exactly matches what is marshalled into the raw_syscall:sys_enter + * payload expected by the 'perf trace' beautifiers. + * + * For now it just uses the existing tracepoint augmentation code in 'perf + * trace', in the next csets we'll hook up these with the sys_enter/sys_exit + * code that will combine entry/exit in a strace like way. + */ + +#include <stdio.h> +#include <linux/socket.h> + +/* bpf-output associated map */ +struct bpf_map SEC("maps") __augmented_syscalls__ = { + .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(u32), + .max_entries = __NR_CPUS__, +}; + +struct syscall_enter_args { + unsigned long long common_tp_fields; + long syscall_nr; + unsigned long args[6]; +}; + +struct syscall_exit_args { + unsigned long long common_tp_fields; + long syscall_nr; + long ret; +}; + +struct augmented_filename { + unsigned int size; + int reserved; + char value[256]; +}; + +#define SYS_OPEN 2 +#define SYS_OPENAT 257 + +SEC("raw_syscalls:sys_enter") +int sys_enter(struct syscall_enter_args *args) +{ + struct { + struct syscall_enter_args args; + struct augmented_filename filename; + } augmented_args; + unsigned int len = sizeof(augmented_args); + const void *filename_arg = NULL; + + probe_read(&augmented_args.args, sizeof(augmented_args.args), args); + /* + * Yonghong and Edward Cree sayz: + * + * https://www.spinics.net/lists/netdev/msg531645.html + * + * >> R0=inv(id=0) R1=inv2 R6=ctx(id=0,off=0,imm=0) R7=inv64 R10=fp0,call_-1 + * >> 10: (bf) r1 = r6 + * >> 11: (07) r1 += 16 + * >> 12: (05) goto pc+2 + * >> 15: (79) r3 = *(u64 *)(r1 +0) + * >> dereference of modified ctx ptr R1 off=16 disallowed + * > Aha, we at least got a different error message this time. + * > And indeed llvm has done that optimisation, rather than the more obvious + * > 11: r3 = *(u64 *)(r1 +16) + * > because it wants to have lots of reads share a single insn. You may be able + * > to defeat that optimisation by adding compiler barriers, idk. Maybe someone + * > with llvm knowledge can figure out how to stop it (ideally, llvm would know + * > when it's generating for bpf backend and not do that). -O0? ¯\_(ツ)_/¯ + * + * The optimization mostly likes below: + * + * br1: + * ... + * r1 += 16 + * goto merge + * br2: + * ... + * r1 += 20 + * goto merge + * merge: + * *(u64 *)(r1 + 0) + * + * The compiler tries to merge common loads. There is no easy way to + * stop this compiler optimization without turning off a lot of other + * optimizations. The easiest way is to add barriers: + * + * __asm__ __volatile__("": : :"memory") + * + * after the ctx memory access to prevent their down stream merging. + */ + switch (augmented_args.args.syscall_nr) { + case SYS_OPEN: filename_arg = (const void *)args->args[0]; + __asm__ __volatile__("": : :"memory"); + break; + case SYS_OPENAT: filename_arg = (const void *)args->args[1]; + break; + } + + if (filename_arg != NULL) { + augmented_args.filename.reserved = 0; + augmented_args.filename.size = probe_read_str(&augmented_args.filename.value, + sizeof(augmented_args.filename.value), + filename_arg); + if (augmented_args.filename.size < sizeof(augmented_args.filename.value)) { + len -= sizeof(augmented_args.filename.value) - augmented_args.filename.size; + len &= sizeof(augmented_args.filename.value) - 1; + } + } else { + len = sizeof(augmented_args.args); + } + + perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, &augmented_args, len); + return 0; +} + +SEC("raw_syscalls:sys_exit") +int sys_exit(struct syscall_exit_args *args) +{ + return 1; /* 0 as soon as we start copying data returned by the kernel, e.g. 'read' */ +} + +license(GPL); |