mirror of
https://github.com/torvalds/linux
synced 2024-07-21 10:41:44 +00:00
2e5c4dd7f8
Currently, there is a problem with tracex2, as it doesn't print the
histogram properly and the results are misleading. (all results report
as 0)
The problem is caused by a change in arguments of the function to which
the kprobe connects. This tracex2 bpf program uses kprobe (attached
to __x64_sys_write) to figure out the size of the write system call. In
order to achieve this, the third argument 'count' must be intact.
The following is a prototype of the sys_write variant. (checked with
pfunct)
~/git/linux$ pfunct -P fs/read_write.o | grep sys_write
ssize_t ksys_write(unsigned int fd, const char * buf, size_t count);
long int __x64_sys_write(const struct pt_regs * regs);
... cross compile with s390x ...
long int __s390_sys_write(struct pt_regs * regs);
Since the nature of SYSCALL_WRAPPER function wraps the argument once,
additional process of argument extraction is required to properly parse
the argument.
#define BPF_KSYSCALL(name, args...)
... snip ...
struct pt_regs *regs = LINUX_HAS_SYSCALL_WRAPPER \
? (struct pt_regs *)PT_REGS_PARM1(ctx) \
: ctx; \
In order to fix this problem, the BPF_SYSCALL macro has been used. This
reduces the hassle of parsing arguments from pt_regs. Since the macro
uses the CORE version of argument extraction, additional portability
comes too.
Signed-off-by: Daniel T. Lee <danieltimlee@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20221224071527.2292-5-danieltimlee@gmail.com
100 lines
2.3 KiB
C
100 lines
2.3 KiB
C
/* Copyright (c) 2013-2015 PLUMgrid, http://plumgrid.com
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of version 2 of the GNU General Public
|
|
* License as published by the Free Software Foundation.
|
|
*/
|
|
#include "vmlinux.h"
|
|
#include <linux/version.h>
|
|
#include <bpf/bpf_helpers.h>
|
|
#include <bpf/bpf_tracing.h>
|
|
#include <bpf/bpf_core_read.h>
|
|
|
|
struct {
|
|
__uint(type, BPF_MAP_TYPE_HASH);
|
|
__type(key, long);
|
|
__type(value, long);
|
|
__uint(max_entries, 1024);
|
|
} my_map SEC(".maps");
|
|
|
|
/* kprobe is NOT a stable ABI. If kernel internals change this bpf+kprobe
|
|
* example will no longer be meaningful
|
|
*/
|
|
SEC("kprobe/kfree_skb_reason")
|
|
int bpf_prog2(struct pt_regs *ctx)
|
|
{
|
|
long loc = 0;
|
|
long init_val = 1;
|
|
long *value;
|
|
|
|
/* read ip of kfree_skb_reason caller.
|
|
* non-portable version of __builtin_return_address(0)
|
|
*/
|
|
BPF_KPROBE_READ_RET_IP(loc, ctx);
|
|
|
|
value = bpf_map_lookup_elem(&my_map, &loc);
|
|
if (value)
|
|
*value += 1;
|
|
else
|
|
bpf_map_update_elem(&my_map, &loc, &init_val, BPF_ANY);
|
|
return 0;
|
|
}
|
|
|
|
static unsigned int log2(unsigned int v)
|
|
{
|
|
unsigned int r;
|
|
unsigned int shift;
|
|
|
|
r = (v > 0xFFFF) << 4; v >>= r;
|
|
shift = (v > 0xFF) << 3; v >>= shift; r |= shift;
|
|
shift = (v > 0xF) << 2; v >>= shift; r |= shift;
|
|
shift = (v > 0x3) << 1; v >>= shift; r |= shift;
|
|
r |= (v >> 1);
|
|
return r;
|
|
}
|
|
|
|
static unsigned int log2l(unsigned long v)
|
|
{
|
|
unsigned int hi = v >> 32;
|
|
if (hi)
|
|
return log2(hi) + 32;
|
|
else
|
|
return log2(v);
|
|
}
|
|
|
|
struct hist_key {
|
|
char comm[16];
|
|
u64 pid_tgid;
|
|
u64 uid_gid;
|
|
u64 index;
|
|
};
|
|
|
|
struct {
|
|
__uint(type, BPF_MAP_TYPE_PERCPU_HASH);
|
|
__uint(key_size, sizeof(struct hist_key));
|
|
__uint(value_size, sizeof(long));
|
|
__uint(max_entries, 1024);
|
|
} my_hist_map SEC(".maps");
|
|
|
|
SEC("ksyscall/write")
|
|
int BPF_KSYSCALL(bpf_prog3, unsigned int fd, const char *buf, size_t count)
|
|
{
|
|
long init_val = 1;
|
|
long *value;
|
|
struct hist_key key;
|
|
|
|
key.index = log2l(count);
|
|
key.pid_tgid = bpf_get_current_pid_tgid();
|
|
key.uid_gid = bpf_get_current_uid_gid();
|
|
bpf_get_current_comm(&key.comm, sizeof(key.comm));
|
|
|
|
value = bpf_map_lookup_elem(&my_hist_map, &key);
|
|
if (value)
|
|
__sync_fetch_and_add(value, 1);
|
|
else
|
|
bpf_map_update_elem(&my_hist_map, &key, &init_val, BPF_ANY);
|
|
return 0;
|
|
}
|
|
char _license[] SEC("license") = "GPL";
|
|
u32 _version SEC("version") = LINUX_VERSION_CODE;
|