This patch introduces a new BPF script to test the BPF prologue adding
routines. The new script probes at null_lseek, which is the function pointer
used when we try to lseek on '/dev/null'.
The null_lseek function is chosen because it is used by function pointers, so
we don't need to consider inlining and LTO.
By extracting file->f_mode, bpf-script-test-prologue.c should know whether the
file is writable or readonly. According to llseek_loop() and
bpf-script-test-prologue.c, one fourth of total lseeks should be collected.
Committer note:
Testing it:
# perf test -v BPF
<SNIP>
Kernel build dir is set to /lib/modules/4.3.0+/build
set env: KBUILD_DIR=/lib/modules/4.3.0+/build
unset env: KBUILD_OPTS
include option is set to -nostdinc -isystem /usr/lib/gcc/x86_64-redhat-linux/4.9.2/include -I/home/git/linux/arch/x86/include -Iarch/x86/include/generated/uapi -Iarch/x86/include/generated -I/home/git/linux/include -Iinclude -I/home/git/linux/arch/x86/include/uapi -Iarch/x86/include/generated/uapi -I/home/git/linux/include/uapi -Iinclude/generated/uapi -include /home/git/linux/include/linux/kconfig.h
set env: NR_CPUS=4
set env: LINUX_VERSION_CODE=0x40300
set env: CLANG_EXEC=/usr/libexec/icecc/bin/clang
set env: CLANG_OPTIONS=-xc
set env: KERNEL_INC_OPTIONS= -nostdinc -isystem /usr/lib/gcc/x86_64-redhat-linux/4.9.2/include -I/home/git/linux/arch/x86/include -Iarch/x86/include/generated/uapi -Iarch/x86/include/generated -I/home/git/linux/include -Iinclude -I/home/git/linux/arch/x86/include/uapi -Iarch/x86/include/generated/uapi -I/home/git/linux/include/uapi -Iinclude/generated/uapi -include /home/git/linux/include/linux/kconfig.h
set env: WORKING_DIR=/lib/modules/4.3.0+/build
set env: CLANG_SOURCE=-
llvm compiling command template: echo '/*
* bpf-script-test-prologue.c
* Test BPF prologue
*/
#ifndef LINUX_VERSION_CODE
# error Need LINUX_VERSION_CODE
# error Example: for 4.2 kernel, put 'clang-opt="-DLINUX_VERSION_CODE=0x40200" into llvm section of ~/.perfconfig'
#endif
#define SEC(NAME) __attribute__((section(NAME), used))
#include <uapi/linux/fs.h>
#define FMODE_READ 0x1
#define FMODE_WRITE 0x2
static void (*bpf_trace_printk)(const char *fmt, int fmt_size, ...) =
(void *) 6;
SEC("func=null_lseek file->f_mode offset orig")
int bpf_func__null_lseek(void *ctx, int err, unsigned long f_mode,
unsigned long offset, unsigned long orig)
{
if (err)
return 0;
if (f_mode & FMODE_WRITE)
return 0;
if (offset & 1)
return 0;
if (orig == SEEK_CUR)
return 0;
return 1;
}
char _license[] SEC("license") = "GPL";
int _version SEC("version") = LINUX_VERSION_CODE;
' | $CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS -DLINUX_VERSION_CODE=$LINUX_VERSION_CODE $CLANG_OPTIONS $KERNEL_INC_OPTIONS -Wno-unused-value -Wno-pointer-sign -working-directory $WORKING_DIR -c "$CLANG_SOURCE" -target bpf -O2 -o -
libbpf: loading object '[bpf_prologue_test]' from buffer
libbpf: section .strtab, size 135, link 0, flags 0, type=3
libbpf: section .text, size 0, link 0, flags 6, type=1
libbpf: section .data, size 0, link 0, flags 3, type=1
libbpf: section .bss, size 0, link 0, flags 3, type=8
libbpf: section func=null_lseek file->f_mode offset orig, size 112, link 0, flags 6, type=1
libbpf: found program func=null_lseek file->f_mode offset orig
libbpf: section license, size 4, link 0, flags 3, type=1
libbpf: license of [bpf_prologue_test] is GPL
libbpf: section version, size 4, link 0, flags 3, type=1
libbpf: kernel version of [bpf_prologue_test] is 40300
libbpf: section .symtab, size 168, link 1, flags 0, type=2
bpf: config program 'func=null_lseek file->f_mode offset orig'
symbol:null_lseek file:(null) line:0 offset:0 return:0 lazy:(null)
parsing arg: file->f_mode into file, f_mode(1)
parsing arg: offset into offset
parsing arg: orig into orig
bpf: config 'func=null_lseek file->f_mode offset orig' is ok
Looking at the vmlinux_path (7 entries long)
Using /lib/modules/4.3.0+/build/vmlinux for symbols
Open Debuginfo file: /lib/modules/4.3.0+/build/vmlinux
Try to find probe point from debuginfo.
Matched function: null_lseek
Probe point found: null_lseek+0
Searching 'file' variable in context.
Converting variable file into trace event.
converting f_mode in file
f_mode type is unsigned int.
Searching 'offset' variable in context.
Converting variable offset into trace event.
offset type is long long int.
Searching 'orig' variable in context.
Converting variable orig into trace event.
orig type is int.
Found 1 probe_trace_events.
Opening /sys/kernel/debug/tracing//kprobe_events write=1
Writing event: p:perf_bpf_probe/func _text+4840528 f_mode=+68(%di):u32 offset=%si:s64 orig=%dx:s32
libbpf: don't need create maps for [bpf_prologue_test]
prologue: pass validation
prologue: slow path
prologue: fetch arg 0, base reg is %di
prologue: arg 0: offset 68
prologue: fetch arg 1, base reg is %si
prologue: fetch arg 2, base reg is %dx
add bpf event perf_bpf_probe:func and attach bpf program 3
adding perf_bpf_probe:func
adding perf_bpf_probe:func to 0x51672c0
mmap size 1052672B
Opening /sys/kernel/debug/tracing//kprobe_events write=1
Opening /sys/kernel/debug/tracing//uprobe_events write=1
Parsing probe_events: p:perf_bpf_probe/func _text+4840528 f_mode=+68(%di):u32 offset=%si:s64 orig=%dx:s32
Group:perf_bpf_probe Event:func probe:p
Writing event: -:perf_bpf_probe/func
test child finished with 0
---- end ----
Test BPF filter: Ok
#
Signed-off-by: Wang Nan <wangnan0@huawei.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1447675815-166222-13-git-send-email-wangnan0@huawei.com
[ Added tools/perf/tests/llvm-src-prologue.c to .gitignore ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This patch generates a prologue for each 'struct probe_trace_event' for
fetching arguments for BPF programs.
After bpf__probe(), iterate over each program to check whether prologues are
required. If none of the 'struct perf_probe_event' programs will attach to have
at least one argument, simply skip preprocessor hooking. For those who a
prologue is required, call bpf__gen_prologue() and paste the original
instruction after the prologue.
Signed-off-by: Wang Nan <wangnan0@huawei.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1447675815-166222-12-git-send-email-wangnan0@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This patch generates a prologue for a BPF program which fetches arguments for
it. With this patch, the program can have arguments as follow:
SEC("lock_page=__lock_page page->flags")
int lock_page(struct pt_regs *ctx, int err, unsigned long flags)
{
return 1;
}
This patch passes at most 3 arguments from r3, r4 and r5. r1 is still the ctx
pointer. r2 is used to indicate if dereferencing was done successfully.
This patch uses r6 to hold ctx (struct pt_regs) and r7 to hold stack pointer
for result. Result of each arguments first store on stack:
low address
BPF_REG_FP - 24 ARG3
BPF_REG_FP - 16 ARG2
BPF_REG_FP - 8 ARG1
BPF_REG_FP
high address
Then loaded into r3, r4 and r5.
The output prologue for offn(...off2(off1(reg)))) should be:
r6 <- r1 // save ctx into a callee saved register
r7 <- fp
r7 <- r7 - stack_offset // pointer to result slot
/* load r3 with the offset in pt_regs of 'reg' */
(r7) <- r3 // make slot valid
r3 <- r3 + off1 // prepare to read unsafe pointer
r2 <- 8
r1 <- r7 // result put onto stack
call probe_read // read unsafe pointer
jnei r0, 0, err // error checking
r3 <- (r7) // read result
r3 <- r3 + off2 // prepare to read unsafe pointer
r2 <- 8
r1 <- r7
call probe_read
jnei r0, 0, err
...
/* load r2, r3, r4 from stack */
goto success
err:
r2 <- 1
/* load r3, r4, r5 with 0 */
goto usercode
success:
r2 <- 0
usercode:
r1 <- r6 // restore ctx
// original user code
If all of arguments reside in register (dereferencing is not
required), gen_prologue_fastpath() will be used to create
fast prologue:
r3 <- (r1 + offset of reg1)
r4 <- (r1 + offset of reg2)
r5 <- (r1 + offset of reg3)
r2 <- 0
P.S.
eBPF calling convention is defined as:
* r0 - return value from in-kernel function, and exit value
for eBPF program
* r1 - r5 - arguments from eBPF program to in-kernel function
* r6 - r9 - callee saved registers that in-kernel function will
preserve
* r10 - read-only frame pointer to access stack
Committer note:
At least testing if it builds and loads:
# cat test_probe_arg.c
struct pt_regs;
__attribute__((section("lock_page=__lock_page page->flags"), used))
int func(struct pt_regs *ctx, int err, unsigned long flags)
{
return 1;
}
char _license[] __attribute__((section("license"), used)) = "GPL";
int _version __attribute__((section("version"), used)) = 0x40300;
# perf record -e ./test_probe_arg.c usleep 1
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.016 MB perf.data ]
# perf evlist
perf_bpf_probe:lock_page
#
Signed-off-by: He Kuang <hekuang@huawei.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1447675815-166222-11-git-send-email-wangnan0@huawei.com
Signed-off-by: Wang Nan <wangnan0@huawei.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
By extending the syntax of BPF object section names, this patch allows users to
config probing options like what they can do in 'perf probe'.
The error message in 'perf probe' is also updated.
Test result:
For following BPF file test_probe_glob.c:
# cat test_probe_glob.c
__attribute__((section("inlines=no;func=SyS_dup?"), used))
int func(void *ctx)
{
return 1;
}
char _license[] __attribute__((section("license"), used)) = "GPL";
int _version __attribute__((section("version"), used)) = 0x40300;
#
# ./perf record -e ./test_probe_glob.c ls /
...
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.013 MB perf.data ]
# ./perf evlist
perf_bpf_probe:func_1
perf_bpf_probe:func
After changing "inlines=no" to "inlines=yes":
# ./perf record -e ./test_probe_glob.c ls /
...
[ perf record: Woken up 2 times to write data ]
[ perf record: Captured and wrote 0.013 MB perf.data ]
# ./perf evlist
perf_bpf_probe:func_3
perf_bpf_probe:func_2
perf_bpf_probe:func_1
perf_bpf_probe:func
Then test 'force':
Use following program:
# cat test_probe_force.c
__attribute__((section("func=sys_write"), used))
int funca(void *ctx)
{
return 1;
}
__attribute__((section("force=yes;func=sys_write"), used))
int funcb(void *ctx)
{
return 1;
}
char _license[] __attribute__((section("license"), used)) = "GPL";
int _version __attribute__((section("version"), used)) = 0x40300;
#
# perf record -e ./test_probe_force.c usleep 1
Error: event "func" already exists.
Hint: Remove existing event by 'perf probe -d'
or force duplicates by 'perf probe -f'
or set 'force=yes' in BPF source.
event syntax error: './test_probe_force.c'
\___ Probe point exist. Try 'perf probe -d "*"' and set 'force=yes'
(add -v to see detail)
...
Then replace 'force=no' to 'force=yes':
# vim test_probe_force.c
# perf record -e ./test_probe_force.c usleep 1
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.017 MB perf.data ]
# perf evlist
perf_bpf_probe:func_1
perf_bpf_probe:func
#
Signed-off-by: Wang Nan <wangnan0@huawei.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1447675815-166222-7-git-send-email-wangnan0@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
If both LIBBPF and DWARF are detected, it is possible to create prologue
for eBPF programs to help them access kernel data. HAVE_BPF_PROLOGUE and
CONFIG_BPF_PROLOGUE are added as flags for this feature.
PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET is introduced in commit
63ab024a5b ("perf tools:
regs_query_register_offset() infrastructure"), which indicates that an
architecture supports converting name of a register to its offset in
'struct pt_regs'. Without this support, BPF_PROLOGUE should be turned
off.
Signed-off-by: Wang Nan <wangnan0@huawei.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1447675815-166222-9-git-send-email-wangnan0@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This patch is a preparation for BPF prologue support which allows
generating a series of BPF bytecode for fetching kernel data before
calling program code. With the newly introduced multiple instances
support, perf is able to create different prologues for different kprobe
points.
Before this patch, a bpf_program can be loaded into kernel only once,
and get the only resulting fd. What this patch does is to allow creating
and loading different variants of one bpf_program, then fetching their
fds.
Here we describe the basic idea in this patch. The detailed description
of the newly introduced APIs can be found in comments in the patch body.
The key of this patch is the new mechanism in bpf_program__load().
Instead of loading BPF program into kernel directly, it calls a
'pre-processor' to generate program instances which would be finally
loaded into the kernel based on the original code. To enable the
generation of multiple instances, libbpf passes an index to the
pre-processor so it know which instance is being loaded.
Pre-processor should be called from libbpf's user (perf) using
bpf_program__set_prep(). The number of instances and the relationship
between indices and the target instance should be clear when calling
bpf_program__set_prep().
To retrieve a fd for a specific instance of a program,
bpf_program__nth_fd() is introduced. It returns the resulting fd
according to index.
Signed-off-by: He Kuang <hekuang@huawei.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: He Kuang <hekuang@huawei.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1447675815-166222-8-git-send-email-wangnan0@huawei.com
Signed-off-by: Wang Nan <wangnan0@huawei.com>
[ Enclosed multi-line if/else blocks with {}, (*func_ptr)() -> func_ptr() ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
$ rpm -q glibc
glibc-2.12-1.166.el6_7.1.x86_64
<SNIP>
CC /tmp/build/perf/tests/llvm.o
cc1: warnings being treated as errors
tests/llvm.c: In function ‘test_llvm__fetch_bpf_obj’:
tests/llvm.c:53: error: declaration of ‘index’ shadows a global declaration
/usr/include/string.h:489: error: shadowed declaration is here
<SNIP>
CC /tmp/build/perf/tests/bpf.o
cc1: warnings being treated as errors
tests/bpf.c: In function ‘__test__bpf’:
tests/bpf.c:149: error: declaration of ‘index’ shadows a global declaration
/usr/include/string.h:489: error: shadowed declaration is here
<SNIP>
Cc: He Kuang <hekuang@huawei.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: pi3orama@163.com
Cc: Wang Nan <wangnan0@huawei.com>
Cc: Zefan Li <lizefan@huawei.com>
Fixes: b31de018a6 ("perf test: Enhance the LLVM test: update basic BPF test program")
Fixes: ba1fae431e ("perf test: Add 'perf test BPF'")
Link: http://lkml.kernel.org/n/tip-akpo4r750oya2phxoh9e3447@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Pull perf/urgent fixes from Arnaldo Carvalho de Melo:
- Do not change the key of an object in a rbtree, this time it was
the one for DSOs lookup by its long_name, and the noticed symptom was
with 'perf buildid-list --with-hits' (Adrian Hunter)
- 'perf inject' is a pipe, events it doesn't touch should be passed
on, PERF_RECORD_LOST wasn't, fix it (Adrian Hunter)
- Make 'perf buildid-list' request event ordering, as it needs to
first get the mmap events to be able to mark wich DSOs had hits
(Adrian Hunter)
- Fix memory leaks on failure in 'perf probe' (Masami Hiramatsu, Wang Nan)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
When probing with a glob, errors in add_probe_trace_event() won't be
passed to debuginfo__find_trace_events() because it would be modified by
probe_point_search_cb(). It causes a segfault if perf fails to find an
argument for a probe point matched by the glob. For example:
# ./perf probe -v -n 'SyS_dup? oldfd'
probe-definition(0): SyS_dup? oldfd
symbol:SyS_dup? file:(null) line:0 offset:0 return:0 lazy:(null)
parsing arg: oldfd into oldfd
1 arguments
Looking at the vmlinux_path (7 entries long)
Using /lib/modules/4.3.0-rc4+/build/vmlinux for symbols
Open Debuginfo file: /lib/modules/4.3.0-rc4+/build/vmlinux
Try to find probe point from debuginfo.
Matched function: SyS_dup3
found inline addr: 0xffffffff812095c0
Probe point found: SyS_dup3+0
Searching 'oldfd' variable in context.
Converting variable oldfd into trace event.
oldfd type is long int.
found inline addr: 0xffffffff812096d4
Probe point found: SyS_dup2+36
Searching 'oldfd' variable in context.
Failed to find 'oldfd' in this function.
Matched function: SyS_dup3
Probe point found: SyS_dup3+0
Searching 'oldfd' variable in context.
Converting variable oldfd into trace event.
oldfd type is long int.
Matched function: SyS_dup2
Probe point found: SyS_dup2+0
Searching 'oldfd' variable in context.
Converting variable oldfd into trace event.
oldfd type is long int.
Found 4 probe_trace_events.
Opening /sys/kernel/debug/tracing//kprobe_events write=1
Writing event: p:probe/SyS_dup3 _text+2135488 oldfd=%di:s64
Segmentation fault (core dumped)
#
This patch ensures that add_probe_trace_event() doesn't touches
tf->ntevs and tf->tevs if those functions fail.
After the patch:
# perf probe 'SyS_dup? oldfd'
Failed to find 'oldfd' in this function.
Added new events:
probe:SyS_dup3 (on SyS_dup? with oldfd)
probe:SyS_dup3_1 (on SyS_dup? with oldfd)
probe:SyS_dup2 (on SyS_dup? with oldfd)
You can now use it in all perf tools, such as:
perf record -e probe:SyS_dup2 -aR sleep 1
Signed-off-by: Wang Nan <wangnan0@huawei.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1447417761-156094-3-git-send-email-wangnan0@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Commit 4598a0a6d2 ("perf symbols: Improve DSO long names lookup speed
with rbtree") Added a tree to lookup dsos by long name. That tree gets
corrupted whenever a dso long name is changed because the tree is not
updated.
One effect of that is buildid-list does not work with the 'with-hits'
option because dso lookup fails and results in two structs for the same
dso. The first has the buildid but no hits, the second has hits but no
buildid. e.g.
Before:
$ tools/perf/perf record ls
arch certs CREDITS Documentation firmware include
ipc Kconfig lib Makefile net REPORTING-BUGS
scripts sound usr block COPYING crypto
drivers fs init Kbuild kernel MAINTAINERS
mm README samples security tools virt
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.012 MB perf.data (11 samples) ]
$ tools/perf/perf buildid-list
574da826c66538a8d9060d393a8866289bd06005 [kernel.kallsyms]
30c94dc66a1fe95180c3d68d2b89e576d5ae213c /lib/x86_64-linux-gnu/libc-2.19.so
$ tools/perf/perf buildid-list -H
574da826c66538a8d9060d393a8866289bd06005 [kernel.kallsyms]
0000000000000000000000000000000000000000 /lib/x86_64-linux-gnu/libc-2.19.so
After:
$ tools/perf/perf buildid-list -H
574da826c66538a8d9060d393a8866289bd06005 [kernel.kallsyms]
30c94dc66a1fe95180c3d68d2b89e576d5ae213c /lib/x86_64-linux-gnu/libc-2.19.so
The fix is to record the root of the tree on the dso so that
dso__set_long_name() can update the tree when the long name changes.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Douglas Hatch <doug.hatch@hp.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Scott J Norton <scott.norton@hp.com>
Cc: Waiman Long <Waiman.Long@hp.com>
Fixes: 4598a0a6d2 ("perf symbols: Improve DSO long names lookup speed with rbtree")
Link: http://lkml.kernel.org/r/1447408112-1920-2-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Pull perf/urgent fixes from Arnaldo Carvalho de Melo:
- Fix 'd' hotkey for filtering by DSO in the top/report
TUI browser (Arnaldo Carvalho de Melo)
- Allow forcing reading of non-root owned /tmp/perf-PID JIT
symbol maps (Arnaldo Carvalho de Melo)
- Rebuild rbtree when adjusting symbols for kcore (Adrian Hunter)
- Actually install tmon in the tools/ install rule (Kamal Mostafa)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
When the root user tries to read a file owned by some other user we get:
# ls -la perf.data
-rw-------. 1 acme acme 20032 Nov 12 15:50 perf.data
# perf report
File perf.data not owned by current user or root (use -f to override)
# perf report -f | grep -v ^# | head -2
30.96% ls [kernel.vmlinux] [k] do_set_pte
28.24% ls libc-2.20.so [.] intel_check_word
#
That wasn't happening when the symbol code tried to read a JIT map,
where the same check was done but no forcing was possible, fix it.
Reported-by: Brendan Gregg <brendan.d.gregg@gmail.com>
Tested-by: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://permalink.gmane.org/gmane.linux.kernel.perf.user/2380
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Normally symbols are read from the DSO and adjusted, if need be, so that
the symbol start matches the file offset in the DSO file (we want the
file offset because that is what we know from MMAP events). That is done
by dso__load_sym() which inserts the symbols *after* adjusting them.
In the case of kcore, the symbols have been read from kallsyms and the
symbol start is the memory address. The symbols have to be adjusted to
match the kcore file offsets. dso__split_kallsyms_for_kcore() does that,
but now the adjustment is being done *after* the symbols have been
inserted. It appears dso__split_kallsyms_for_kcore() was assuming that
changing the symbol start would not change the order in the rbtree -
which is, of course, not guaranteed.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Tested-by: Wang Nan <wangnan0@huawei.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
Link: http://lkml.kernel.org/r/563CB241.2090701@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Pull perf/urgent fixes from Arnaldo Carvalho de Melo:
- Add missing newlines to some pr_err() calls (Arnaldo Carvalho de Melo)
- Print full source file paths when using
'perf annotate --print-line --full-paths' (Michael Petlan)
- Fix 'perf probe -d' when just one out of uprobes and kprobes is
enabled (Wang Nan)
- Add compiler.h to list.h to fix 'make perf-tar-src-pkg' generated
tarballs, i.e. out of tree building (Arnaldo Carvalho de Melo)
- Add the llvm-src-base.c and llvm-src-kbuild.c files, generated by the
'perf test' LLVM entries, when running it in-tree, to .gitignore (Yunlong Song)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Before:
[acme@zoo linux]$ perf evlist
WARNING: The perf.data file's data size field is 0 which is unexpected.
Was the 'perf record' command properly terminated?
non matching sample_type[acme@zoo linux]$
After:
[acme@zoo linux]$ perf evlist
WARNING: The perf.data file's data size field is 0 which is unexpected.
Was the 'perf record' command properly terminated?
non matching sample_type
[acme@zoo linux]$
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-wscok3a2s7yrj8156oc2r6qe@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The --full-paths option did not show the full source file paths in the 'perf
annotate' tool, because the value of the option was not propagated into the
related functions.
With this patch the value of the --full-paths option is known to the function
that composes the srcline string, so it prints the full path when necessary.
Committer Note:
This affects annotate when the --print-line option is used:
# perf annotate -h 2>&1 | grep print-line
-l, --print-line print matching source lines (may be slow)
Looking just at the lines that should be affected by this change:
Before:
# perf annotate --print-line --full-paths --stdio fput | grep '\.[ch]:[0-9]\+'
94.44 atomic64_64.h:114
5.56 file_table.c:265
file_table.c:265 5.56 : ffffffff81219a00: callq ffffffff81769360 <__fentry__>
atomic64_64.h:114 94.44 : ffffffff81219a05: lock decq 0x38(%rdi)
After:
# perf annotate --print-line --full-paths --stdio fput | grep '\.[ch]:[0-9]\+'
94.44 /home/git/linux/arch/x86/include/asm/atomic64_64.h:114
5.56 /home/git/linux/fs/file_table.c:265
/home/git/linux/fs/file_table.c:265 5.56 : ffffffff81219a00: callq ffffffff81769360 <__fentry__>
/home/git/linux/arch/x86/include/asm/atomic64_64.h:114 94.44 : ffffffff81219a05: lock decq 0x38(%rdi)
#
Signed-off-by: Michael Petlan <mpetlan@redhat.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Link: http://permalink.gmane.org/gmane.linux.kernel.perf.user/2365
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The perf_lock_task_context() function disables preemption across its
RCU read-side critical section because that critical section acquires
a scheduler lock. If there was a preemption during that RCU read-side
critical section, the rcu_read_unlock() could attempt to acquire scheduler
locks, resulting in deadlock.
However, recent optimizations to expedited grace periods mean that IPI
handlers that execute during preemptible RCU read-side critical sections
can now cause the subsequent rcu_read_unlock() to acquire scheduler locks.
Disabling preemption does nothiing to prevent these IPI handlers from
executing, so these optimizations introduced a deadlock. In theory,
this deadlock could be avoided by pulling all wakeups and printk()s out
from rnp->lock critical sections, but in practice this would re-introduce
some RCU CPU stall warning bugs.
Given that acquiring scheduler locks entails disabling interrupts, these
deadlocks can be avoided by disabling interrupts (instead of disabling
preemption) across any RCU read-side critical that acquires scheduler
locks and holds them across the rcu_read_unlock(). This commit therefore
makes this change for perf_lock_task_context().
Reported-by: Dave Jones <davej@codemonkey.org.uk>
Reported-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Stephane Eranian <eranian@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20151104134838.GR29027@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:
Fixes:
- libbpf error reporting improvements, using a strerror interface to
more precisely tell the user about problems with the provided
scriptlet, be it in C or as a ready made object file (Wang Nan)
- Do not be case sensitive when searching for matching 'perf test'
entries (Arnaldo Carvalho de Melo)
- Inform the user about objdump failures in 'perf annotate' (Andi Kleen)
Infrastructure changes:
- Improve the LLVM 'perf test' entry, introduce a new ones for
BPF and kbuild tests to check the environment used by clang to
compile .c scriptlets (Wang Nan)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This patch adds a kbuild testcase to check whether kernel headers can be
correctly found.
For example:
# mv /lib/modules/4.3.0-rc5{,.bak}
# perf test LLVM
38: Test LLVM searching and compiling : Skip
# perf test -v LLVM
...
<stdin>:11:10: fatal error: 'uapi/linux/fs.h' file not found
#include <uapi/linux/fs.h>
^
1 error generated.
ERROR: unable to compile -
Hint: Check error message shown above.
Hint: You can also pre-compile it into .o using:
clang -target bpf -O2 -c -
with proper -I and -D options.
Failed to compile test case: 'Test kbuild searching'
test child finished with -2
Signed-off-by: Wang Nan <wangnan0@huawei.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1446817783-86722-7-git-send-email-wangnan0@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This patch replaces the original toy BPF program with the previously
introduced bpf-script-example.c. Dynamically embeddeding it into
'llvm-src-base.c'.
The newly introduced BPF program attaches a BPF program to
'sys_epoll_pwait()'. perf itself never use that syscall, so further test
can verify their result with it. The program would generate 1 sample in
every 2 calls of epoll_pwait() system call.
Since the resulting BPF object is useful per se for further tests,
test_llvm__fetch_bpf_obj() is introduced for creating BPF objects from
source. The LLVM test was rewritten to use it.
Committer note:
Running it:
[root@zoo wb]# perf test -v LLVM
35: Test LLVM searching and compiling :
--- start ---
test child forked, pid 17740
Kernel build dir is set to /lib/modules/4.3.0-rc1+/build
set env: KBUILD_DIR=/lib/modules/4.3.0-rc1+/build
unset env: KBUILD_OPTS
include option is set to -nostdinc -isystem /usr/lib/gcc/x86_64-redhat-linux/4.9.2/include -I/home/git/linux/arch/x86/include -Iarch/x86/include/generated/uapi -Iarch/x86/include/generated -I/home/git/linux/include -Iinclude -I/home/git/linux/arch/x86/include/uapi -Iarch/x86/include/generated/uapi -I/home/git/linux/include/uapi -Iinclude/generated/uapi -include /home/git/linux/include/linux/kconfig.h
set env: NR_CPUS=4
set env: LINUX_VERSION_CODE=0x40300
set env: CLANG_EXEC=/usr/libexec/icecc/bin/clang
set env: CLANG_OPTIONS=-xc
set env: KERNEL_INC_OPTIONS= -nostdinc -isystem /usr/lib/gcc/x86_64-redhat-linux/4.9.2/include -I/home/git/linux/arch/x86/include -Iarch/x86/include/generated/uapi -Iarch/x86/include/generated -I/home/git/linux/include -Iinclude -I/home/git/linux/arch/x86/include/uapi -Iarch/x86/include/generated/uapi -I/home/git/linux/include/uapi -Iinclude/generated/uapi -include /home/git/linux/include/linux/kconfig.h
set env: WORKING_DIR=/lib/modules/4.3.0-rc1+/build
set env: CLANG_SOURCE=-
llvm compiling command template: echo '/*
* bpf-script-example.c
* Test basic LLVM building
*/
#ifndef LINUX_VERSION_CODE
# error Need LINUX_VERSION_CODE
# error Example: for 4.2 kernel, put 'clang-opt="-DLINUX_VERSION_CODE=0x40200" into llvm section of ~/.perfconfig'
#endif
#define BPF_ANY 0
#define BPF_MAP_TYPE_ARRAY 2
#define BPF_FUNC_map_lookup_elem 1
#define BPF_FUNC_map_update_elem 2
static void *(*bpf_map_lookup_elem)(void *map, void *key) =
(void *) BPF_FUNC_map_lookup_elem;
static void *(*bpf_map_update_elem)(void *map, void *key, void *value, int flags) =
(void *) BPF_FUNC_map_update_elem;
struct bpf_map_def {
unsigned int type;
unsigned int key_size;
unsigned int value_size;
unsigned int max_entries;
};
#define SEC(NAME) __attribute__((section(NAME), used))
struct bpf_map_def SEC("maps") flip_table = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(int),
.value_size = sizeof(int),
.max_entries = 1,
};
SEC("func=sys_epoll_pwait")
int bpf_func__sys_epoll_pwait(void *ctx)
{
int ind =0;
int *flag = bpf_map_lookup_elem(&flip_table, &ind);
int new_flag;
if (!flag)
return 0;
/* flip flag and store back */
new_flag = !*flag;
bpf_map_update_elem(&flip_table, &ind, &new_flag, BPF_ANY);
return new_flag;
}
char _license[] SEC("license") = "GPL";
int _version SEC("version") = LINUX_VERSION_CODE;
' | $CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS -DLINUX_VERSION_CODE=$LINUX_VERSION_CODE $CLANG_OPTIONS $KERNEL_INC_OPTIONS -Wno-unused-value -Wno-pointer-sign -working-directory $WORKING_DIR -c "$CLANG_SOURCE" -target bpf -O2 -o -
test child finished with 0
---- end ----
Test LLVM searching and compiling: Ok
[root@zoo wb]#
Signed-off-by: Wang Nan <wangnan0@huawei.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1446817783-86722-6-git-send-email-wangnan0@huawei.com
Signed-off-by: He Kuang <hekuang@huawei.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
A series of bpf loader related error codes were introduced to help error
reporting. Functions were improved to return these new error codes.
Functions which return pointers were adjusted to encode error codes into
return value using the ERR_PTR() interface.
bpf_loader_strerror() was improved to convert these error messages to
strings. It checks the error codes and calls libbpf_strerror() and
strerror_r() accordingly, so caller don't need to consider checking the
range of the error code.
In bpf__strerror_load(), print kernel version of running kernel and the
object's 'version' section to notify user how to fix his/her program.
v1 -> v2:
Use macro for error code.
Fetch error message based on array index, eliminate for-loop.
Print version strings.
Before:
# perf record -e ./test_kversion_nomatch_program.o sleep 1
event syntax error: './test_kversion_nomatch_program.o'
\___ Failed to load program: Validate your program and check 'license'/'version' sections in your object
SKIP
After:
# perf record -e ./test_kversion_nomatch_program.o ls
event syntax error: './test_kversion_nomatch_program.o'
\___ 'version' (4.4.0) doesn't match running kernel (4.3.0)
SKIP
Signed-off-by: Wang Nan <wangnan0@huawei.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1446818289-87444-1-git-send-email-wangnan0@huawei.com
[ Add 'static inline' to bpf__strerror_prepare_load() when LIBBPF is disabled ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
In this patch, a series of libbpf specific error numbers and
libbpf_strerror() are introduced to help reporting errors.
Functions are updated to pass correct the error number through the
CHECK_ERR() macro.
All users of bpf_object__open{_buffer}() and bpf_program__title() in
perf are modified accordingly. In addition, due to the error codes
changing, bpf__strerror_load() is also modified to use them.
bpf__strerror_head() is also changed accordingly so it can parse libbpf
errors. bpf_loader_strerror() is introduced for that purpose, and will
be improved by the following patch.
load_program() is improved not to dump log buffer if it is empty. log
buffer is also used to deduce whether the error was caused by an invalid
program or other problem.
v1 -> v2:
- Using macro for error code.
- Fetch error message based on array index, eliminate for-loop.
- Use log buffer to detect the reason of failure. 3 new error code
are introduced to replace LIBBPF_ERRNO__LOAD.
In v1:
# perf record -e ./test_ill_program.o ls
event syntax error: './test_ill_program.o'
\___ Failed to load program: Validate your program and check 'license'/'version' sections in your object
SKIP
# perf record -e ./test_kversion_nomatch_program.o ls
event syntax error: './test_kversion_nomatch_program.o'
\___ Failed to load program: Validate your program and check 'license'/'version' sections in your object
SKIP
# perf record -e ./test_big_program.o ls
event syntax error: './test_big_program.o'
\___ Failed to load program: Validate your program and check 'license'/'version' sections in your object
SKIP
In v2:
# perf record -e ./test_ill_program.o ls
event syntax error: './test_ill_program.o'
\___ Kernel verifier blocks program loading
SKIP
# perf record -e ./test_kversion_nomatch_program.o
event syntax error: './test_kversion_nomatch_program.o'
\___ Incorrect kernel version
SKIP
(Will be further improved by following patches)
# perf record -e ./test_big_program.o
event syntax error: './test_big_program.o'
\___ Program too big
SKIP
Signed-off-by: Wang Nan <wangnan0@huawei.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1446817783-86722-2-git-send-email-wangnan0@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
When the browser fails to annotate it is difficult for users to find out
what went wrong.
Add some errors for objdump failures that are displayed in the UI.
Note it would be even better to handle these errors smarter, like
falling back to the binary when the debug info is somehow corrupted. But
for now just giving a better error is an improvement.
Committer note:
This works for --stdio, where errors just scroll by the screen:
# perf annotate --stdio intel_idle
Failure running objdump --start-address=0xffffffff81418290 --stop-address=0xffffffff814183ae -l -d --no-show-raw -S -C /root/.debug/.build-id/28/2777c262e6b3c0451375163c9a81c893218ab1 2>/dev/null|grep -v /root/.debug/.build-id/28/2777c262e6b3c0451375163c9a81c893218ab1|expand
Percent | Source code & Disassembly of vmlinux for cycles:pp
------------------------------------------------------------------
And with that one can use that command line to try to find out more about what
happened instead of getting a blank screen, an improvement.
We need tho to improve this further to get it to work with other UIs, like
--tui and --gtk, where it continues showing a blank screen, no messages, as
the pr_err() used is enough just for --stdio.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/1446779167-18949-1-git-send-email-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The -i flag was incorrectly listed as a short flag for --no-inherit. It
should have only been listed as a short flag for --input.
This documentation error has existed since the --input flag was
introduced in 6810fc915f (perf trace: Add
option to analyze events in a file versus live).
Signed-off-by: Peter Feiner <pfeiner@google.com>
Cc: David Ahern <dsahern@gmail.com>
Link: http://lkml.kernel.org/r/1446657706-14518-1-git-send-email-pfeiner@google.com
Fixes: 6810fc915f ("perf trace: Add option to analyze events in a file versus live")
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
