This is a note to let you know that I've just added the patch titled
perf trace: Use the right bpf_probe_read(_str) variant for reading user data
to the 6.5-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
perf-trace-use-the-right-bpf_probe_read-_str-variant.patch
and it can be found in the queue-6.5 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit 097a2ac5029479b556903657b63227b62e0f9079
Author: Thomas Richter <tmricht@xxxxxxxxxxxxx>
Date: Thu Oct 19 10:26:42 2023 +0200
perf trace: Use the right bpf_probe_read(_str) variant for reading user data
[ Upstream commit 5069211e2f0b47e75119805e23ae6352d871e263 ]
Perf test case 111 Check open filename arg using perf trace + vfs_getname
fails on s390. This is caused by a failing function
bpf_probe_read() in file util/bpf_skel/augmented_raw_syscalls.bpf.c.
The root cause is the lookup by address. Function bpf_probe_read()
is used. This function works only for architectures
with ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE.
On s390 is not possible to determine from the address to which
address space the address belongs to (user or kernel space).
Replace bpf_probe_read() by bpf_probe_read_kernel()
and bpf_probe_read_str() by bpf_probe_read_user_str() to
explicity specify the address space the address refers to.
Output before:
# ./perf trace -eopen,openat -- touch /tmp/111
libbpf: prog 'sys_enter': BPF program load failed: Invalid argument
libbpf: prog 'sys_enter': -- BEGIN PROG LOAD LOG --
reg type unsupported for arg#0 function sys_enter#75
0: R1=ctx(off=0,imm=0) R10=fp0
; int sys_enter(struct syscall_enter_args *args)
0: (bf) r6 = r1 ; R1=ctx(off=0,imm=0) R6_w=ctx(off=0,imm=0)
; return bpf_get_current_pid_tgid();
1: (85) call bpf_get_current_pid_tgid#14 ; R0_w=scalar()
2: (63) *(u32 *)(r10 -8) = r0 ; R0_w=scalar() R10=fp0 fp-8=????mmmm
3: (bf) r2 = r10 ; R2_w=fp0 R10=fp0
;
.....
lines deleted here
.....
23: (bf) r3 = r6 ; R3_w=ctx(off=0,imm=0) R6=ctx(off=0,imm=0)
24: (85) call bpf_probe_read#4
unknown func bpf_probe_read#4
processed 23 insns (limit 1000000) max_states_per_insn 0 \
total_states 2 peak_states 2 mark_read 2
-- END PROG LOAD LOG --
libbpf: prog 'sys_enter': failed to load: -22
libbpf: failed to load object 'augmented_raw_syscalls_bpf'
libbpf: failed to load BPF skeleton 'augmented_raw_syscalls_bpf': -22
....
Output after:
# ./perf test -Fv 111
111: Check open filename arg using perf trace + vfs_getname :
--- start ---
1.085 ( 0.011 ms): touch/320753 openat(dfd: CWD, filename: \
"/tmp/temporary_file.SWH85", \
flags: CREAT|NOCTTY|NONBLOCK|WRONLY, mode: IRUGO|IWUGO) = 3
---- end ----
Check open filename arg using perf trace + vfs_getname: Ok
#
Test with the sleep command shows:
Output before:
# ./perf trace -e *sleep sleep 1.234567890
0.000 (1234.681 ms): sleep/63114 clock_nanosleep(rqtp: \
{ .tv_sec: 0, .tv_nsec: 0 }, rmtp: 0x3ffe0979720) = 0
#
Output after:
# ./perf trace -e *sleep sleep 1.234567890
0.000 (1234.686 ms): sleep/64277 clock_nanosleep(rqtp: \
{ .tv_sec: 1, .tv_nsec: 234567890 }, rmtp: 0x3fff3df9ea0) = 0
#
Fixes: 14e4b9f4289a ("perf trace: Raw augmented syscalls fix libbpf 1.0+ compatibility")
Signed-off-by: Thomas Richter <tmricht@xxxxxxxxxxxxx>
Co-developed-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Acked-by: Ilya Leoshkevich <iii@xxxxxxxxxxxxx>
Tested-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Cc: Ian Rogers <irogers@xxxxxxxxxx>
Cc: gor@xxxxxxxxxxxxx
Cc: hca@xxxxxxxxxxxxx
Cc: sumanthk@xxxxxxxxxxxxx
Cc: svens@xxxxxxxxxxxxx
Link: https://lore.kernel.org/r/20231019082642.3286650-1-tmricht@xxxxxxxxxxxxx
Signed-off-by: Namhyung Kim <namhyung@xxxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/tools/perf/examples/bpf/augmented_raw_syscalls.c b/tools/perf/examples/bpf/augmented_raw_syscalls.c
index 9a03189d33d38..74fa9e642b424 100644
--- a/tools/perf/examples/bpf/augmented_raw_syscalls.c
+++ b/tools/perf/examples/bpf/augmented_raw_syscalls.c
@@ -147,7 +147,7 @@ static inline
unsigned int augmented_arg__read_str(struct augmented_arg *augmented_arg, const void *arg, unsigned int arg_len)
{
unsigned int augmented_len = sizeof(*augmented_arg);
- int string_len = bpf_probe_read_str(&augmented_arg->value, arg_len, arg);
+ int string_len = bpf_probe_read_user_str(&augmented_arg->value, arg_len, arg);
augmented_arg->size = augmented_arg->err = 0;
/*
@@ -196,7 +196,7 @@ int sys_enter_connect(struct syscall_enter_args *args)
if (socklen > sizeof(augmented_args->saddr))
socklen = sizeof(augmented_args->saddr);
- bpf_probe_read(&augmented_args->saddr, socklen, sockaddr_arg);
+ bpf_probe_read_user(&augmented_args->saddr, socklen, sockaddr_arg);
return augmented__output(args, augmented_args, len + socklen);
}
@@ -215,7 +215,7 @@ int sys_enter_sendto(struct syscall_enter_args *args)
if (socklen > sizeof(augmented_args->saddr))
socklen = sizeof(augmented_args->saddr);
- bpf_probe_read(&augmented_args->saddr, socklen, sockaddr_arg);
+ bpf_probe_read_user(&augmented_args->saddr, socklen, sockaddr_arg);
return augmented__output(args, augmented_args, len + socklen);
}
@@ -305,7 +305,7 @@ int sys_enter_perf_event_open(struct syscall_enter_args *args)
if (augmented_args == NULL)
goto failure;
- if (bpf_probe_read(&augmented_args->__data, sizeof(*attr), attr) < 0)
+ if (bpf_probe_read_user(&augmented_args->__data, sizeof(*attr), attr) < 0)
goto failure;
attr_read = (const struct perf_event_attr_size *)augmented_args->__data;
@@ -319,7 +319,7 @@ int sys_enter_perf_event_open(struct syscall_enter_args *args)
goto failure;
// Now that we read attr->size and tested it against the size limits, read it completely
- if (bpf_probe_read(&augmented_args->__data, size, attr) < 0)
+ if (bpf_probe_read_user(&augmented_args->__data, size, attr) < 0)
goto failure;
return augmented__output(args, augmented_args, len + size);
@@ -341,7 +341,7 @@ int sys_enter_clock_nanosleep(struct syscall_enter_args *args)
if (size > sizeof(augmented_args->__data))
goto failure;
- bpf_probe_read(&augmented_args->__data, size, rqtp_arg);
+ bpf_probe_read_user(&augmented_args->__data, size, rqtp_arg);
return augmented__output(args, augmented_args, len + size);
failure:
@@ -380,7 +380,7 @@ int sys_enter(struct syscall_enter_args *args)
if (augmented_args == NULL)
return 1;
- bpf_probe_read(&augmented_args->args, sizeof(augmented_args->args), args);
+ bpf_probe_read_kernel(&augmented_args->args, sizeof(augmented_args->args), args);
/*
* Jump to syscall specific augmenter, even if the default one,
@@ -401,7 +401,7 @@ int sys_exit(struct syscall_exit_args *args)
if (pid_filter__has(&pids_filtered, getpid()))
return 0;
- bpf_probe_read(&exit_args, sizeof(exit_args), args);
+ bpf_probe_read_kernel(&exit_args, sizeof(exit_args), args);
/*
* Jump to syscall specific return augmenter, even if the default one,
* "!raw_syscalls:unaugmented" that will just return 1 to return the
