09 Apr, 2018
4 commits
-
As stated in tests/llvm-src-base.c, the name of the bpf function should
be "bpf_func__SyS_epoll_pwait" but this clang test fails as it tries to
lookup "bpf_func__SyS_epoll_wait".Before applying patch:
55: builtin clang support :
55.1: builtin clang compile C source to IR : FAILED!
55.2: builtin clang compile C source to ELF object : SkipAfter applying patch:
55: builtin clang support :
55.1: builtin clang compile C source to IR : Ok
55.2: builtin clang compile C source to ELF object : OkSigned-off-by: Sandipan Das
Tested-by: Arnaldo Carvalho de Melo
Cc: Jiri Olsa
Cc: Naveen N. Rao
Fixes: e67d52d411c3 ("perf clang: Update test case to use real BPF script")
Link: http://lkml.kernel.org/r/20180404180419.19056-3-sandipan@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo -
The clang API calls used by perf have changed in recent releases and
builds succeed with libclang-3.9 only. This introduces compatibility
with libclang-4.0 and above.Without this patch, we will see the following compilation errors with
libclang-4.0+:util/c++/clang.cpp: In function ‘clang::CompilerInvocation* perf::createCompilerInvocation(llvm::opt::ArgStringList, llvm::StringRef&, clang::DiagnosticsEngine&)’:
util/c++/clang.cpp:62:33: error: ‘IK_C’ was not declared in this scope
Opts.Inputs.emplace_back(Path, IK_C);
^~~~
util/c++/clang.cpp: In function ‘std::unique_ptr perf::getModuleFromSource(llvm::opt::ArgStringList, llvm::StringRef, llvm::IntrusiveRefCntPtr)’:
util/c++/clang.cpp:75:26: error: no matching function for call to ‘clang::CompilerInstance::setInvocation(clang::CompilerInvocation*)’
Clang.setInvocation(&*CI);
^
In file included from util/c++/clang.cpp:14:0:
/usr/include/clang/Frontend/CompilerInstance.h:231:8: note: candidate: void clang::CompilerInstance::setInvocation(std::shared_ptr)
void setInvocation(std::shared_ptr Value);
^~~~~~~~~~~~~Committer testing:
Tested on Fedora 27 after installing the clang-devel and llvm-devel
packages, versions:# rpm -qa | egrep llvm\|clang
llvm-5.0.1-6.fc27.x86_64
clang-libs-5.0.1-5.fc27.x86_64
clang-5.0.1-5.fc27.x86_64
clang-tools-extra-5.0.1-5.fc27.x86_64
llvm-libs-5.0.1-6.fc27.x86_64
llvm-devel-5.0.1-6.fc27.x86_64
clang-devel-5.0.1-5.fc27.x86_64
#Make sure you don't have some older version lying around in /usr/local,
etc, then:$ make LIBCLANGLLVM=1 -C tools/perf install-bin
And in the end perf will be linked agains these libraries:
# ldd ~/bin/perf | egrep -i llvm\|clang
libclangAST.so.5 => /lib64/libclangAST.so.5 (0x00007f8bb2eb4000)
libclangBasic.so.5 => /lib64/libclangBasic.so.5 (0x00007f8bb29e3000)
libclangCodeGen.so.5 => /lib64/libclangCodeGen.so.5 (0x00007f8bb23f7000)
libclangDriver.so.5 => /lib64/libclangDriver.so.5 (0x00007f8bb2060000)
libclangFrontend.so.5 => /lib64/libclangFrontend.so.5 (0x00007f8bb1d06000)
libclangLex.so.5 => /lib64/libclangLex.so.5 (0x00007f8bb1a3e000)
libclangTooling.so.5 => /lib64/libclangTooling.so.5 (0x00007f8bb17d4000)
libclangEdit.so.5 => /lib64/libclangEdit.so.5 (0x00007f8bb15c5000)
libclangSema.so.5 => /lib64/libclangSema.so.5 (0x00007f8bb0cc9000)
libclangAnalysis.so.5 => /lib64/libclangAnalysis.so.5 (0x00007f8bb0a23000)
libclangParse.so.5 => /lib64/libclangParse.so.5 (0x00007f8bb0725000)
libclangSerialization.so.5 => /lib64/libclangSerialization.so.5 (0x00007f8bb039a000)
libLLVM-5.0.so => /lib64/libLLVM-5.0.so (0x00007f8bace98000)
libclangASTMatchers.so.5 => /lib64/../lib64/libclangASTMatchers.so.5 (0x00007f8bab735000)
libclangFormat.so.5 => /lib64/../lib64/libclangFormat.so.5 (0x00007f8bab4b2000)
libclangRewrite.so.5 => /lib64/../lib64/libclangRewrite.so.5 (0x00007f8bab2a1000)
libclangToolingCore.so.5 => /lib64/../lib64/libclangToolingCore.so.5 (0x00007f8bab08e000)
#Signed-off-by: Sandipan Das
Tested-by: Arnaldo Carvalho de Melo
Cc: Jiri Olsa
Cc: Naveen N. Rao
Fixes: 00b86691c77c ("perf clang: Add builtin clang support ant test case")
Link: http://lkml.kernel.org/r/20180404180419.19056-2-sandipan@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo -
For libclang, some distro packages provide static libraries (.a) while
some provide shared libraries (.so). Currently, perf code can only be
linked with static libraries. This makes perf build possible for both
cases.Signed-off-by: Sandipan Das
Cc: Jiri Olsa
Cc: Naveen N. Rao
Fixes: d58ac0bf8d1e ("perf build: Add clang and llvm compile and linking support")
Link: http://lkml.kernel.org/r/20180404180419.19056-1-sandipan@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo -
The only thing that is needed there is a forward declaration for 'struct
nsinfo', so disentanble this, which in turns allows built-in clang
builds, i.e. 'make LIBCLANGLLVM=1 -C tools/perf'.Cc: Adrian Hunter
Cc: David Ahern
Cc: Jiri Olsa
Cc: Namhyung Kim
Cc: Naveen N. Rao
Cc: Sandipan Das
Cc: Wang Nan
Link: https://lkml.kernel.org/n/tip-vq26rsuwq1cqylpcyvq89c84@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo
06 Apr, 2018
4 commits
-
The per-browser screen refresh routine (ui_browser->refresh()) should
return the first row that should be cleaned after the rows just printed,
in case not all rows available on the screen gets filled.When moving the extra title lines logic from the hists browser to the
generic ui_browser class, one piece of that logic remained in the hists
browser and then when going back from the annotate browser to the hists
browser in a case where fewer lines were displayed in the hists browser,
for instance when filtering the entries per substring, one line of the
annotate browser would remain on the screen, fix that.Example of the screen artifact:
================================================================================
Samples: 73K of event 'cycles:ppp', 4000 Hz, Event count (approx.): 45172901394
Overhead Shared O Symbol
0.30% [kernel] [k] __indirect_thunk_start
0.09% [kernel] [k] __x86_indirect_thunk_r10
│ lfence
================================================================================Here from 'perf top' the view was zoomed with '/thunk' to functions
having that substring, then the first was annotated and from the
annotate browser ESC was pressed, then the first lines were overwritten,
but the 'lfence' line remained due to the off by one bug fixed in this
cset.Cc: Adrian Hunter
Cc: Andi Kleen
Cc: David Ahern
Cc: Jin Yao
Cc: Jiri Olsa
Cc: Namhyung Kim
Cc: Wang Nan
Fixes: ef9ff6017e3c ("perf ui browser: Move the extra title lines from the hists browser")
Link: https://lkml.kernel.org/n/tip-odryfso74eaarm0z3e4v9owx@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo -
To help in fixing problems in the browser.
Cc: Adrian Hunter
Cc: David Ahern
Cc: Jiri Olsa
Cc: Namhyung Kim
Cc: Wang Nan
Link: https://lkml.kernel.org/n/tip-uj0n76yqh5bf98i0edckd47t@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo -
In preparation for supporting AUX area sampling buffers,
auxtrace_queues__add_buffer() needs to be more generic. To that end, move
CPU filtering into it.Signed-off-by: Adrian Hunter
Cc: Jiri Olsa
Link: http://lkml.kernel.org/r/1520327598-1317-8-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo -
The following message, emitted when samples are lost due to system
overload, had one 'samples' too many, ditch it:Processed 25333 samples and lost 20.88% samples!
Cc: Adrian Hunter
Cc: David Ahern
Cc: Jiri Olsa
Cc: Namhyung Kim
Cc: Wang Nan
Cc: Kan Liang
Link: https://lkml.kernel.org/n/tip-oev1469y02hmfere6r2kkxp6@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo
05 Apr, 2018
4 commits
-
Now that we can have extra title lines we should use ui_browser->rows
and not ->height when drawing lines, as well as adding
ui_browser->extra_title_lines to browser->y when cleaning unused lines
at the bottom, otherwise we end up clobbering with spaces the last line
just shown by ui_browser->refresh() routine.Cc: Adrian Hunter
Cc: Andi Kleen
Cc: David Ahern
Cc: Jin Yao
Cc: Jiri Olsa
Cc: Namhyung Kim
Cc: Wang Nan
Fixes: ef9ff6017e3c ("perf ui browser: Move the extra title lines from the hists browser")
Link: https://lkml.kernel.org/n/tip-dfcpokt1pm5ixm8n9pxwtstz@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo -
Now that we can have extra title lines we should use ui_browser->rows
and not ->height when drawing lines, as it will use ui_browser__gotorc()
and that will take the extra title lines into account, which was causing
an off by one at the end of the vertical line drawn by
__ui_browser__vline(), fix it.The visual effect was that the last line, with status messages, was
being overwritten by the vertical line, looking like:Press 'h' for help on│key bindings
Cc: Adrian Hunter
Cc: Andi Kleen
Cc: David Ahern
Cc: Jin Yao
Cc: Jiri Olsa
Cc: Namhyung Kim
Cc: Wang Nan
Fixes: ef9ff6017e3c ("perf ui browser: Move the extra title lines from the hists browser")
Link: https://lkml.kernel.org/n/tip-08y1ln3xjn76zvizz1i1dsvn@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo -
To match what is shown in the main 'perf report/top' title lines, i.e.
if a group is being shown, either a real group (recorded with "-e
'{a,b,c}') or a forced group (using 'perf report --group' for a
perf.data file recorded without {}) we will show multiple columns,
one per event, but we were failing to show the group details, so, for:# perf report --header-only | grep cmdline
# cmdline : /home/acme/bin/perf record -e {cycles,instructions,cache-misses}
# perf report --groupThe first line was showing just "cycles", now it shows the correct line,
which is:Samples: 578 of events 'anon group { cycles, instructions, cache-misses }', 4000 Hz, Event count (approx.): 487421794
syscall_return_via_sysret /lib/modules/4.16.0-rc7/build/vmlinux
0.22 2.97 0.00 │ ↓ jmp 6c
│ mov %cr3,%rdi
1.33 10.89 4.00 │ ↓ jmp 62
│ mov %rdi,%raxCc: Adrian Hunter
Cc: Andi Kleen
Cc: David Ahern
Cc: Jin Yao
Cc: Jiri Olsa
Cc: Namhyung Kim
Cc: Wang Nan
Fixes: 6920e2854e9a ("perf annotate browser: Show extra title line with event information")
Link: https://lkml.kernel.org/n/tip-i41tqh17c2dabnyzjh99r1oz@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo -
In preparation for supporting AUX area sampling buffers,
auxtrace_queues__add_buffer() needs to be more generic. To that end,
move memory allocation for struct buffer into it.Signed-off-by: Adrian Hunter
Cc: Jiri Olsa
Link: http://lkml.kernel.org/r/1520327598-1317-7-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo
04 Apr, 2018
5 commits
-
…nux/kernel/git/acme/linux into perf/core
Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:
- Show only failing syscalls with 'perf trace --failure' (Arnaldo Carvalho de Melo)
e.g: See what 'openat' syscalls are failing:
# perf trace --failure -e openat
762.323 ( 0.007 ms): VideoCapture/4566 openat(dfd: CWD, filename: /dev/video2) = -1 ENOENT No such file or directory
<SNIP N /dev/videoN open attempts... sigh, where is that improvised camera lid?!? >
790.228 ( 0.008 ms): VideoCapture/4566 openat(dfd: CWD, filename: /dev/video63) = -1 ENOENT No such file or directory
^C#- Show information about the event (freq, nr_samples, total period/nr_events) in
the annotate --tui and --stdio2 'perf annotate' output, similar to the
first line in the 'perf report --tui', but just for the samples for a
the annotated symbol (Arnaldo Carvalho de Melo)- Introduce 'perf version --build-options' to show what features were
linked, aliased as well as a shorter 'perf -vv' (Jin Yao)- Add a "dso_size" sort order (Kim Phillips)
- Remove redundant ')' in the tracepoint output in 'perf trace' (Changbin Du)
- Synchronize x86's cpufeatures.h, no effect on toolss (Arnaldo Carvalho de Melo)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org> -
There is a redundant ')' at the tail of each event. So remove it.
$ sudo perf trace --no-syscalls -e 'kmem:*' -a
899.342 kmem:kfree:(vfs_writev+0xb9) call_site=ffffffff9c453979 ptr=(nil))
899.344 kmem:kfree:(___sys_recvmsg+0x188) call_site=ffffffff9c9b8b88 ptr=(nil))Signed-off-by: Changbin Du
Tested-by: Arnaldo Carvalho de Melo
Cc: Jiri Olsa
Cc: Namhyung Kim
Cc: Peter Zijlstra
Link: http://lkml.kernel.org/r/1520937601-24952-1-git-send-email-changbin.du@intel.com
Signed-off-by: Arnaldo Carvalho de Melo -
To match the recently added event header information to --tui, e.g.:
# perf annotate --ignore-vmlinux --stdio2 _raw_spin_lock_irqsave
Samples: 128 of event 'cycles:ppp', 4000 Hz, Event count (approx.): 48617682
_raw_spin_lock_irqsave() /proc/kcore
0.78 nop
7.03 push %rbx
3.12 pushfq
6.25 pop %rax
nop
mov %rax,%rbx
3.12 cli
nop
xor %eax,%eax
mov $0x1,%edx
79.69 lock cmpxchg %edx,(%rdi)
test %eax,%eax
↓ jne 2b
mov %rbx,%rax
pop %rbx
← retq
2b: mov %eax,%esi
→ callq *ffffffffb30eaed0
mov %rbx,%rax
pop %rbx
← retq
#Cc: Adrian Hunter
Cc: David Ahern
Cc: Jiri Olsa
Cc: Martin Liška
Cc: Namhyung Kim
Cc: Wang Nan
Link: https://lkml.kernel.org/n/tip-ujy46x7cldyhyxelyf2b9quy@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo -
So at the top we'll have two lines, like this, from 'perf report':
# perf report --group --ignore-vmlinux
=====================================================================================================
Samples: 46 of events 'cycles', 4000 Hz, Event count (approx.): 5154895
_raw_spin_lock_irqsave /proc/kcore
Percent │ nop
│ push %rbx
0.00 14.29 0.00 │ pushfq
9.09 0.00 0.00 │ pop %rax
9.09 0.00 20.00 │ nop
│ mov %rax,%rbx
│ cli
4.55 7.14 0.00 │ nop
│ xor %eax,%eax
│ mov $0x1,%edx
│ lock cmpxchg %edx,(%rdi)
77.27 78.57 70.00 │ test %eax,%eax
│ ↓ jne 2b
│ mov %rbx,%rax
0.00 0.00 10.00 │ pop %rbx
│ ← retq
│2b: mov %eax,%esi
│ → callq queued_spin_lock_slowpath
│ mov %rbx,%rax
│ pop %rbx
Press 'h' for help on│key bindings
=====================================================================================================9.09 + 9.09 + 4.55 + 77.27 = 100
14.29 + 7.14 + 78.57 = 100
20 + 70 + 10 = 100We can do the math by using 't' to toggle from 'percent' to nr
=====================================================================================================
Samples: 46 of events 'cycles', 4000 Hz, Event count (approx.): 5154895
_raw_spin_lock_irqsave /proc/kcore
Period │ nop
│ push %rbx
0 79273 0 │ pushfq
190455 0 0 │ pop %rax
198038 0 3045 │ nop
│ mov %rax,%rbx
│ cli
217233 32562 0 │ nop
│ xor %eax,%eax
│ mov $0x1,%edx
│ lock cmpxchg %edx,(%rdi)
3421649 979174 28273 │ test %eax,%eax
│ ↓ jne 2b
│ mov %rbx,%rax
0 0 5193 │ pop %rbx
│ ← retq
│2b: mov %eax,%esi
│ → callq queued_spin_lock_slowpath
│ mov %rbx,%rax
│ pop %rbx
Press 'h' for help on│key bindings
=====================================================================================================79273 + 190455 + 198038 + 3045 + 217233 + 32562 + 3421649 + 979174 + 28273 + 5193 = 5154895
Or number of samples:
=====================================================================================================
ooSamples: 46 of events 'cycles', 4000 Hz, Event count (approx.): 5154895
_raw_spin_lock_irqsave /proc/kcore
Samples │ nop
│ push %rbx
0 2 0 │ pushfq
2 0 0 │ pop %rax
2 0 2 │ nop
│ mov %rax,%rbx
│ cli
1 1 0 │ nop
│ xor %eax,%eax
│ mov $0x1,%edx
│ lock cmpxchg %edx,(%rdi)
17 11 7 │ test %eax,%eax
│ ↓ jne 2b
│ mov %rbx,%rax
0 0 1 │ pop %rbx
│ ← retq
│2b: mov %eax,%esi
│ → callq queued_spin_lock_slowpath
│ mov %rbx,%rax
│ pop %rbx
Press 'h' for help on key bindings
=====================================================================================================2 + 2 + 2 + 2 + 1 + 1 + 17 + 11 + 7 + 1 = 46
Suggested-by: Martin Liška
Cc: Adrian Hunter
Cc: David Ahern
Cc: Jiri Olsa
Cc: Linus Torvalds
Cc: Namhyung Kim
Cc: Wang Nan
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=196935
Link: https://lkml.kernel.org/n/tip-ezccyxld50wtwyt66np6aomo@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo -
To print a string using the total period (nr_events) and the number of
samples for a given annotation, i.e. for a given symbol, the counterpart
to hists__scnprintf_samples_period(), that is for all the samples in a
session (be it a live session, think 'perf top' or a perf.data file,
think 'perf report').Cc: Adrian Hunter
Cc: David Ahern
Cc: Jiri Olsa
Cc: Martin Liška
Cc: Namhyung Kim
Cc: Wang Nan
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=196935
Link: https://lkml.kernel.org/n/tip-goj2wu4fxutc8vd46mw3yg14@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo
03 Apr, 2018
10 commits
-
This will be useful for the annotate browser as well, that wants to have
extra title lines, i.e. the current ui_browser unconditionally reserves
the first line for a browser title and the last one for status messages.But some browsers, like the buckets one (hists browser) needs extra
lines to show headers, allowing it to be shown or not, press 'H' in
'perf top' or 'perf report' to see this feature.So move that logic to the core ui_browser used by the hists_browser
('perf top' and 'perf report' main interface) so that it can be used by
the annotate browser too.Cc: Adrian Hunter
Cc: David Ahern
Cc: Jiri Olsa
Cc: Martin Liška
Cc: Namhyung Kim
Cc: Wang Nan
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=196935
Link: https://lkml.kernel.org/n/tip-r38xm3ut37ulbg1o5tn5iise@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo -
The previous patch made this function useful to non-TUI parts of the
tools, but left it where the function from what it was carved, so that
the patch showed more clearly the process.Now just move it outside the TUI parts so that we can finally use it,
even when the TUI code doesn't get built/linked.Cc: Adrian Hunter
Cc: David Ahern
Cc: Jiri Olsa
Cc: Martin Liška
Cc: Namhyung Kim
Cc: Wang Nan
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=196935
Link: https://lkml.kernel.org/n/tip-hqj7hvcr3mu5lvcqp3cssio6@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo -
That is not use any struct hists_browser internals, so that it can be
shared with the other UIs and tools.Cc: Adrian Hunter
Cc: David Ahern
Cc: Jiri Olsa
Cc: Martin Liška
Cc: Namhyung Kim
Cc: Wang Nan
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=196935
Link: https://lkml.kernel.org/n/tip-w8mczjnqnbcj9yzfkv9ja6ro@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo -
Rename it to hists_browser__scnprintf_title() to better reflect that it
provides a scnprintf-like function operating on a hists_browser
instance.This paves the way to have a non-hists_browser specific function to
scnprintf format a title with per evsel information to use in other
tools or UIs.Cc: Adrian Hunter
Cc: David Ahern
Cc: Jiri Olsa
Cc: Martin Liška
Cc: Namhyung Kim
Cc: Wang Nan
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=196935
Link: https://lkml.kernel.org/n/tip-sntpyzxsnme9jvuz2qntwoh2@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo -
Pul removal of obsolete architecture ports from Arnd Bergmann:
"This removes the entire architecture code for blackfin, cris, frv,
m32r, metag, mn10300, score, and tile, including the associated device
drivers.I have been working with the (former) maintainers for each one to
ensure that my interpretation was right and the code is definitely
unused in mainline kernels. Many had fond memories of working on the
respective ports to start with and getting them included in upstream,
but also saw no point in keeping the port alive without any users.In the end, it seems that while the eight architectures are extremely
different, they all suffered the same fate: There was one company in
charge of an SoC line, a CPU microarchitecture and a software
ecosystem, which was more costly than licensing newer off-the-shelf
CPU cores from a third party (typically ARM, MIPS, or RISC-V). It
seems that all the SoC product lines are still around, but have not
used the custom CPU architectures for several years at this point. In
contrast, CPU instruction sets that remain popular and have actively
maintained kernel ports tend to all be used across multiple licensees.[ See the new nds32 port merged in the previous commit for the next
generation of "one company in charge of an SoC line, a CPU
microarchitecture and a software ecosystem" - Linus ]The removal came out of a discussion that is now documented at
https://lwn.net/Articles/748074/. Unlike the original plans, I'm not
marking any ports as deprecated but remove them all at once after I
made sure that they are all unused. Some architectures (notably tile,
mn10300, and blackfin) are still being shipped in products with old
kernels, but those products will never be updated to newer kernel
releases.After this series, we still have a few architectures without mainline
gcc support:- unicore32 and hexagon both have very outdated gcc releases, but the
maintainers promised to work on providing something newer. At least
in case of hexagon, this will only be llvm, not gcc.- openrisc, risc-v and nds32 are still in the process of finishing
their support or getting it added to mainline gcc in the first
place. They all have patched gcc-7.3 ports that work to some
degree, but complete upstream support won't happen before gcc-8.1.
Csky posted their first kernel patch set last week, their situation
will be similar[ Palmer Dabbelt points out that RISC-V support is in mainline gcc
since gcc-7, although gcc-7.3.0 is the recommended minimum - Linus ]"This really says it all:
2498 files changed, 95 insertions(+), 467668 deletions(-)
* tag 'arch-removal' of git://git.kernel.org/pub/scm/linux/kernel/git/arnd/asm-generic: (74 commits)
MAINTAINERS: UNICORE32: Change email account
staging: iio: remove iio-trig-bfin-timer driver
tty: hvc: remove tile driver
tty: remove bfin_jtag_comm and hvc_bfin_jtag drivers
serial: remove tile uart driver
serial: remove m32r_sio driver
serial: remove blackfin drivers
serial: remove cris/etrax uart drivers
usb: Remove Blackfin references in USB support
usb: isp1362: remove blackfin arch glue
usb: musb: remove blackfin port
usb: host: remove tilegx platform glue
pwm: remove pwm-bfin driver
i2c: remove bfin-twi driver
spi: remove blackfin related host drivers
watchdog: remove bfin_wdt driver
can: remove bfin_can driver
mmc: remove bfin_sdh driver
input: misc: remove blackfin rotary driver
input: keyboard: remove bf54x driver
... -
Since a new option '--build-options' is created for 'perf version', so
we need to document it.Signed-off-by: Jin Yao
Acked-by: Jiri Olsa
Cc: Alexander Shishkin
Cc: Andi Kleen
Cc: Jin Yao
Cc: Kan Liang
Cc: Peter Zijlstra
Link: http://lkml.kernel.org/r/1522402036-22915-7-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo -
We keep having bug reports that when users build perf on their own, but
they don't install some needed libraries such as libelf,
libbfd/libibery.The perf can build, but it is missing important functionality.
This patch provides a new option '-vv' for perf which will print the
compiled-in status of libraries.The 'perf -vv' is mapped to 'perf version --build-options'.
For example:
$ ./perf -vv
perf version 4.13.rc5.g6727c5
dwarf: [ on ] # HAVE_DWARF_SUPPORT
dwarf_getlocations: [ on ] # HAVE_DWARF_GETLOCATIONS_SUPPORT
glibc: [ on ] # HAVE_GLIBC_SUPPORT
gtk2: [ on ] # HAVE_GTK2_SUPPORT
libaudit: [ OFF ] # HAVE_LIBAUDIT_SUPPORT
libbfd: [ on ] # HAVE_LIBBFD_SUPPORT
libelf: [ on ] # HAVE_LIBELF_SUPPORT
libnuma: [ on ] # HAVE_LIBNUMA_SUPPORT
numa_num_possible_cpus: [ on ] # HAVE_LIBNUMA_SUPPORT
libperl: [ on ] # HAVE_LIBPERL_SUPPORT
libpython: [ on ] # HAVE_LIBPYTHON_SUPPORT
libslang: [ on ] # HAVE_SLANG_SUPPORT
libcrypto: [ on ] # HAVE_LIBCRYPTO_SUPPORT
libunwind: [ on ] # HAVE_LIBUNWIND_SUPPORT
libdw-dwarf-unwind: [ on ] # HAVE_DWARF_SUPPORT
zlib: [ on ] # HAVE_ZLIB_SUPPORT
lzma: [ on ] # HAVE_LZMA_SUPPORT
get_cpuid: [ on ] # HAVE_AUXTRACE_SUPPORT
bpf: [ on ] # HAVE_LIBBPF_SUPPORTv3:
One bug is found in v2. It didn't process the option like '-vabc'
correctly. Fix this bug.v2:
Use a global variable version_verbose to record the number of 'v'.
Signed-off-by: Jin Yao
Tested-by: Arnaldo Carvalho de Melo
Acked-by: Jiri Olsa
Cc: Alexander Shishkin
Cc: Andi Kleen
Cc: Jin Yao
Cc: Kan Liang
Cc: Peter Zijlstra
Link: http://lkml.kernel.org/r/1522402036-22915-6-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo -
This patch checks the values passed by CFLAGS (-DHAVE_XXX) and then
print the status of libraries.For example, if HAVE_DWARF_SUPPORT is defined, that means the library
"dwarf" is compiled-in. The patch will print the status "on" for this
library otherwise it print the status "OFF".A new option '--build-options' created for 'perf version' supports the
printing of library status.For example:
$ ./perf version --build-options
or
./perf --version --build-options
or
./perf -v --build-optionsperf version 4.13.rc5.g6727c5
dwarf: [ on ] # HAVE_DWARF_SUPPORT
dwarf_getlocations: [ on ] # HAVE_DWARF_GETLOCATIONS_SUPPORT
glibc: [ on ] # HAVE_GLIBC_SUPPORT
gtk2: [ on ] # HAVE_GTK2_SUPPORT
libaudit: [ OFF ] # HAVE_LIBAUDIT_SUPPORT
libbfd: [ on ] # HAVE_LIBBFD_SUPPORT
libelf: [ on ] # HAVE_LIBELF_SUPPORT
libnuma: [ on ] # HAVE_LIBNUMA_SUPPORT
numa_num_possible_cpus: [ on ] # HAVE_LIBNUMA_SUPPORT
libperl: [ on ] # HAVE_LIBPERL_SUPPORT
libpython: [ on ] # HAVE_LIBPYTHON_SUPPORT
libslang: [ on ] # HAVE_SLANG_SUPPORT
libcrypto: [ on ] # HAVE_LIBCRYPTO_SUPPORT
libunwind: [ on ] # HAVE_LIBUNWIND_SUPPORT
libdw-dwarf-unwind: [ on ] # HAVE_DWARF_SUPPORT
zlib: [ on ] # HAVE_ZLIB_SUPPORT
lzma: [ on ] # HAVE_LZMA_SUPPORT
get_cpuid: [ on ] # HAVE_AUXTRACE_SUPPORT
bpf: [ on ] # HAVE_LIBBPF_SUPPORTv4:
1. Also print the macro name. That would make it easier
to grep around in the source looking for where code
related a particular features is located.2. Update since HAVE_DWARF_GETLOCATIONS is renamed to
HAVE_DWARF_GETLOCATIONS_SUPPORTv3:
Remove following unnecessary help message.
1. [ on ]: library is compiled-in
[ OFF ]: library is disabled in make configuration
OR library is not installed in build environment2. Create '--build-options' option.
3. Use standard option parsing API 'parse_options'.
v2:
1. Use IS_BUILTIN macro to replace #ifdef/#endif block.
2. Print color for on/OFF.
Signed-off-by: Jin Yao
Suggested-by: Arnaldo Carvalho de Melo
Suggested-by: Ingo Molnar
Suggested-by: Jiri Olsa
Tested-by: Arnaldo Carvalho de Melo
Acked-by: Jiri Olsa
Cc: Alexander Shishkin
Cc: Andi Kleen
Cc: Jin Yao
Cc: Kan Liang
Cc: Peter Zijlstra
Link: http://lkml.kernel.org/r/1522402036-22915-5-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo -
In Makefile.config, to make all libraries flags have _SUPPORT suffix,
rename HAVE_DWARF_GETLOCATIONS to HAVE_DWARF_GETLOCATIONS_SUPPORTSigned-off-by: Jin Yao
Suggested-by: Ingo Molnar
Acked-by: Jiri Olsa
Cc: Alexander Shishkin
Cc: Andi Kleen
Cc: Jin Yao
Cc: Kan Liang
Cc: Peter Zijlstra
Link: http://lkml.kernel.org/r/1522402036-22915-4-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo -
For most of libraries, in perf.config, they are recorded with -DHAVE_XXX in
CFLAGS according to if the libraries are compiled-in. Then C code then will
know if the library is compiled-in or not.While for glibc, no -DHAVE_GLIBC_SUPPORT exists.
For python and perl libraries, only -DNO_PYTHON and -DNO_LIBPERL exist.
To make the code more consistent, the patch creates -DHAVE_LIBPYTHON_SUPPORT
and -DHAVE_LIBPERL_SUPPORT if the python and perl libraries are compiled-in.Since the existing flags -DNO_PYTHON and -DNO_LIBPERL are being used in many
places in C code, this patch doesn't remove them. In a follow-up patch, we will
recontruct the C code and then use HAVE_XXX instead.v3:
Move 'CFLAGS += -DHAVE_LIBPYTHON_SUPPORT' and 'CFLAGS +=
-DHAVE_LIBPERL_SUPPORT' to other places to avoid duplicated feature checking.v2:
Create -DHAVE_GLIBC_SUPPORT, -DHAVE_LIBPYTHON_SUPPORT and
-DHAVE_LIBPERL_SUPPORT.Signed-off-by: Jin Yao
Acked-by: Jiri Olsa
Cc: Alexander Shishkin
Cc: Andi Kleen
Cc: Jin Yao
Cc: Kan Liang
Cc: Peter Zijlstra
Link: http://lkml.kernel.org/r/1522402036-22915-3-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo
02 Apr, 2018
2 commits
-
For instance:
# perf probe "vfs_getname=getname_flags:72 pathname=result->name:string"
Added new event:
probe:vfs_getname (on getname_flags:72 with pathname=result->name:string)You can now use it in all perf tools, such as:
perf record -e probe:vfs_getname -aR sleep 1
# perf trace --failure sleep 1
0.043 ( 0.010 ms): sleep/10978 access(filename: /etc/ld.so.preload, mode: R) = -1 ENOENT No such file or directoryFor reference, here are all the syscalls in this case:
# perf trace sleep 1
? ( ): sleep/10976 ... [continued]: execve()) = 0
0.027 ( 0.001 ms): sleep/10976 brk() = 0x55bdc2d04000
0.044 ( 0.010 ms): sleep/10976 access(filename: /etc/ld.so.preload, mode: R) = -1 ENOENT No such file or directory
0.057 ( 0.006 ms): sleep/10976 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
0.064 ( 0.002 ms): sleep/10976 fstat(fd: 3, statbuf: 0x7fffac22b370) = 0
0.067 ( 0.003 ms): sleep/10976 mmap(len: 111457, prot: READ, flags: PRIVATE, fd: 3) = 0x7feec8615000
0.071 ( 0.001 ms): sleep/10976 close(fd: 3) = 0
0.080 ( 0.007 ms): sleep/10976 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC) = 3
0.088 ( 0.002 ms): sleep/10976 read(fd: 3, buf: 0x7fffac22b538, count: 832) = 832
0.092 ( 0.001 ms): sleep/10976 fstat(fd: 3, statbuf: 0x7fffac22b3d0) = 0
0.094 ( 0.002 ms): sleep/10976 mmap(len: 8192, prot: READ|WRITE, flags: PRIVATE|ANONYMOUS) = 0x7feec8613000
0.099 ( 0.004 ms): sleep/10976 mmap(len: 3889792, prot: EXEC|READ, flags: PRIVATE|DENYWRITE, fd: 3) = 0x7feec8057000
0.104 ( 0.007 ms): sleep/10976 mprotect(start: 0x7feec8203000, len: 2097152) = 0
0.112 ( 0.005 ms): sleep/10976 mmap(addr: 0x7feec8403000, len: 24576, prot: READ|WRITE, flags: PRIVATE|DENYWRITE|FIXED, fd: 3, off: 1753088) = 0x7feec8403000
0.120 ( 0.003 ms): sleep/10976 mmap(addr: 0x7feec8409000, len: 14976, prot: READ|WRITE, flags: PRIVATE|ANONYMOUS|FIXED) = 0x7feec8409000
0.128 ( 0.001 ms): sleep/10976 close(fd: 3) = 0
0.139 ( 0.001 ms): sleep/10976 arch_prctl(option: 4098, arg2: 140663540761856) = 0
0.186 ( 0.004 ms): sleep/10976 mprotect(start: 0x7feec8403000, len: 16384, prot: READ) = 0
0.204 ( 0.003 ms): sleep/10976 mprotect(start: 0x55bdc0ec3000, len: 4096, prot: READ) = 0
0.209 ( 0.004 ms): sleep/10976 mprotect(start: 0x7feec8631000, len: 4096, prot: READ) = 0
0.214 ( 0.010 ms): sleep/10976 munmap(addr: 0x7feec8615000, len: 111457) = 0
0.269 ( 0.001 ms): sleep/10976 brk() = 0x55bdc2d04000
0.271 ( 0.002 ms): sleep/10976 brk(brk: 0x55bdc2d25000) = 0x55bdc2d25000
0.274 ( 0.001 ms): sleep/10976 brk() = 0x55bdc2d25000
0.278 ( 0.007 ms): sleep/10976 open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
0.288 ( 0.001 ms): sleep/10976 fstat(fd: 3, statbuf: 0x7feec8408aa0) = 0
0.290 ( 0.003 ms): sleep/10976 mmap(len: 113045344, prot: READ, flags: PRIVATE, fd: 3) = 0x7feec1488000
0.297 ( 0.001 ms): sleep/10976 close(fd: 3) = 0
0.325 (1000.193 ms): sleep/10976 nanosleep(rqtp: 0x7fffac22c0b0) = 0
1000.560 ( 0.006 ms): sleep/10976 close(fd: 1) = 0
1000.573 ( 0.005 ms): sleep/10976 close(fd: 2) = 0
1000.596 ( ): sleep/10976 exit_group()
#And can be done systemwide, etc, with backtraces:
# perf trace --max-stack=16 --failure sleep 1
0.048 ( 0.015 ms): sleep/11092 access(filename: /etc/ld.so.preload, mode: R) = -1 ENOENT No such file or directory
__access (inlined)
dl_main (/usr/lib64/ld-2.26.so)
#Or for some specific syscalls:
# perf trace --max-stack=16 -e openat --failure cat /tmp/rien
cat: /tmp/rien: No such file or directory
0.251 ( 0.012 ms): cat/11106 openat(dfd: CWD, filename: /tmp/rien) = -1 ENOENT No such file or directory
__libc_open64 (inlined)
main (/usr/bin/cat)
__libc_start_main (/usr/lib64/libc-2.26.so)
_start (/usr/bin/cat)
#Look for inotify* syscalls that fail, system wide, for 2 seconds, with backtraces:
# perf trace -a --max-stack=16 --failure -e inotify* sleep 2
819.165 ( 0.058 ms): gmain/1724 inotify_add_watch(fd: 8, pathname: /home/acme/~, mask: 16789454) = -1 ENOENT No such file or directory
__GI_inotify_add_watch (inlined)
_ik_watch (/usr/lib64/libgio-2.0.so.0.5400.3)
_ip_start_watching (/usr/lib64/libgio-2.0.so.0.5400.3)
im_scan_missing (/usr/lib64/libgio-2.0.so.0.5400.3)
g_timeout_dispatch (/usr/lib64/libglib-2.0.so.0.5400.3)
g_main_context_dispatch (/usr/lib64/libglib-2.0.so.0.5400.3)
g_main_context_iterate.isra.23 (/usr/lib64/libglib-2.0.so.0.5400.3)
g_main_context_iteration (/usr/lib64/libglib-2.0.so.0.5400.3)
glib_worker_main (/usr/lib64/libglib-2.0.so.0.5400.3)
g_thread_proxy (/usr/lib64/libglib-2.0.so.0.5400.3)
start_thread (/usr/lib64/libpthread-2.26.so)
__GI___clone (inlined)
#Cc: Adrian Hunter
Cc: David Ahern
Cc: Jiri Olsa
Cc: Namhyung Kim
Cc: Wang Nan
Link: https://lkml.kernel.org/n/tip-8f7d3mngaxvi7tlzloz3n7cs@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo -
Add DSO size to perf report/top sort output list.
This includes adding a map__size fn to map.h, which is
approximately equal to the DSO data file_size:DSO file size map (end-start) file / (end-start)
libwebkit2gtk-4.0.so.37.24.9 43260072 41295872 95%
libglib-2.0.so.0.5400.1 1125680 1118208 99%
libc-2.26.so 1960656 1925120 101%
libdbus-1.so.3.14.13 309456 303104 102%Sample output:
$ ./perf report -s dso_size,dso
Samples: 2K of event 'cycles:uppp', Event count (approx.): 128373340
Overhead DSO size Shared Object
90.62% unknown [unknown]
2.87% 1118208 libglib-2.0.so.0.5400.1
1.92% 303104 libdbus-1.so.3.14.13
1.42% 1925120 libc-2.26.so
0.77% 41295872 libwebkit2gtk-4.0.so.37.24.9
0.61% 335872 libgobject-2.0.so.0.5400.1
0.41% 1052672 libgdk-3.so.0.2200.25
0.36% 106496 libpthread-2.26.so
0.29% 221184 dbus-daemon
0.17% 159744 ld-2.26.so
0.13% 49152 libwayland-client.so.0.3.0
0.12% 1642496 libgio-2.0.so.0.5400.1
0.09% 7327744 libgtk-3.so.0.2200.25
0.09% 12324864 libmozjs-52.so.0.0.0
0.05% 4796416 perf
0.04% 843776 libgjs.so.0.0.0
0.03% 1409024 libmutter-clutter-1.soCommitter testing:
To sort by DSO size, use:
# perf report -F dso_size,dso,overhead -s dso_size
3465216 libdns-export.so.174.0.1 0.00%
3522560 libgc.so.1.0.3 0.00%
3538944 libbfd-2.29-13.fc27.so 0.59%
3670016 libunistring.so.2.1.0 0.00%
3723264 libguile-2.0.so.22.8.1 0.00%
3776512 libgio-2.0.so.0.5400.3 0.00%
3891200 libc-2.26.so 0.96%
3944448 libmozjs-17.0.so 0.00%
4218880 libperl.so.5.26.1 0.18%
4452352 libpython2.7.so.1.0 0.02%
4472832 perf 0.02%
4603904 git 0.01%
4751360 libcrypto.so.1.1.0g 0.00%
5005312 libslang.so.2.3.1 0.00%
7315456 libgtk-3.so.0.2200.26 0.09%
8818688 i965_dri.so 2.46%
8818688 i965_dri.so (deleted) 1.26%
12414976 libmozjs-52.so.0.0.0 0.03%
23642112 cc1 2.02%
27889664 [kernel.kallsyms] 25.41%
80834560 libxul.so (deleted) 15.68%
98078720 chrome 32.03%
1056964608 [kernel.kallsyms] 1.59%
#Signed-off-by: Kim Phillips
Tested-by: Arnaldo Carvalho de Melo
Cc: Alexander Shishkin
Cc: Andi Kleen
Cc: Jin Yao
Cc: Jiri Olsa
Cc: Maxim Kuvyrkov
Cc: Milian Wolff
Cc: Namhyung Kim
Cc: Peter Zijlstra
Link: http://lkml.kernel.org/r/20180327060956.1c01ebe67a2a941bb4468c6f@arm.com
Signed-off-by: Arnaldo Carvalho de Melo
28 Mar, 2018
8 commits
-
Add CPU measurement counter facility event description files (json
files) for IBM z14.Signed-off-by: Thomas Richter
Reviewed-by: Hendrik Brueckner
Cc: Heiko Carstens
Cc: Martin Schwidefsky
Link: http://lkml.kernel.org/r/20180326082538.2258-5-tmricht@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo -
Add CPU measurement counter facility event description files (json
files) for IBM z13.Signed-off-by: Thomas Richter
Reviewed-by: Hendrik Brueckner
Cc: Heiko Carstens
Cc: Martin Schwidefsky
Link: http://lkml.kernel.org/r/20180326082538.2258-4-tmricht@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo -
Add CPU measurement counter facility event description files (json
files) for IBM zEC12 and zBC12.Signed-off-by: Thomas Richter
Reviewed-by: Hendrik Brueckner
Cc: Heiko Carstens
Cc: Martin Schwidefsky
Link: http://lkml.kernel.org/r/20180326082538.2258-3-tmricht@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo -
Add CPU measurement counter facility event description files (json
files) for IBM z196.Signed-off-by: Thomas Richter
Reviewed-by: Hendrik Brueckner
Cc: Heiko Carstens
Cc: Martin Schwidefsky
Link: http://lkml.kernel.org/r/20180326082538.2258-2-tmricht@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo -
Add CPU measurement counter facility event description files (JSON
files) for IBM z10EC and z10BC.Signed-off-by: Thomas Richter
Reviewed-by: Hendrik Brueckner
Cc: Heiko Carstens
Cc: Martin Schwidefsky
Link: http://lkml.kernel.org/r/20180326082538.2258-1-tmricht@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo -
The previous patch is insufficient to cure the reported 'perf trace'
segfault, as it only cures the perf_mmap__read_done() case, moving the
segfault to perf_mmap__read_init() functio, fix it by doing the same
refcount check.Cc: Adrian Hunter
Cc: Arnaldo Carvalho de Melo
Cc: David Ahern
Cc: Jiri Olsa
Cc: Kan Liang
Cc: Namhyung Kim
Cc: Wang Nan
Fixes: 8872481bd048 ("perf mmap: Introduce perf_mmap__read_init()")
Link: https://lkml.kernel.org/r/20180326144127.GF18897@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo -
There is a segmentation fault when running 'perf trace'. For example:
[root@jouet e]# perf trace -e *chdir -o /tmp/bla perf report --ignore-vmlinux -i ../perf.data
The perf_mmap__consume() could unmap the mmap. It needs to check the
refcnt in perf_mmap__read_done().Reported-by: Arnaldo Carvalho de Melo
Signed-off-by: Kan Liang
Cc: Jiri Olsa
Cc: Namhyung Kim
Cc: Wang Nan
Fixes: ee023de05f35 ("perf mmap: Introduce perf_mmap__read_done()")
Link: http://lkml.kernel.org/r/1522071729-16776-1-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo -
Currently the "opts" variable is not zero-ed and we keep on adding to
it, ending up with:$ check-headers.sh 2>&1
+ opts=' "-B"'
+ opts=' "-B" "-B"'
+ opts=' "-B" "-B" "-B"'
+ opts=' "-B" "-B" "-B" "-B"'
+ opts=' "-B" "-B" "-B" "-B" "-B"'
+ opts=' "-B" "-B" "-B" "-B" "-B" "-B"'Fix this by initializing it in the check() function, right before
starting the loop.Signed-off-by: Jiri Olsa
Tested-by: Arnaldo Carvalho de Melo
Cc: Alexander Shishkin
Cc: David Ahern
Cc: Namhyung Kim
Cc: Peter Zijlstra
Link: http://lkml.kernel.org/r/20180321140515.2252-1-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo
24 Mar, 2018
3 commits
-
These types of jumps were confusing the annotate browser:
entry_SYSCALL_64 /lib/modules/4.16.0-rc5-00086-gdf09348f78dc/build/vmlinux
entry_SYSCALL_64 /lib/modules/4.16.0-rc5-00086-gdf09348f78dc/build/vmlinux
Percent│ffffffff81a00020: swapgs
│ffffffff81a00128: ↓ jae ffffffff81a00139
│ffffffff81a00155: → jmpq *0x825d2d(%rip) # ffffffff82225e88I.e. the syscall_return_via_sysret function is actually "inside" the
entry_SYSCALL_64 function, and the offsets in jumps like these (+0x53)
are relative to syscall_return_via_sysret, not to syscall_return_via_sysret.Or this may be some artifact in how the assembler marks the start and
end of a function and how this ends up in the ELF symtab for vmlinux,
i.e. syscall_return_via_sysret() isn't "inside" entry_SYSCALL_64, but
just right after it.From readelf -sw vmlinux:
80267: ffffffff81a00020 315 NOTYPE GLOBAL DEFAULT 1 entry_SYSCALL_64
316: ffffffff81a000e6 0 NOTYPE LOCAL DEFAULT 1 syscall_return_via_sysret0xffffffff81a00020 + 315 > 0xffffffff81a000e6
So instead of looking for offsets after that last '+' sign, calculate
offsets for jump target addresses that are inside the function being
disassembled from the absolute address, 0xffffffff81a00139 in this case,
subtracting from it the objdump address for the start of the function
being disassembled, entry_SYSCALL_64() in this case.So, before this patch:
entry_SYSCALL_64 /lib/modules/4.16.0-rc5-00086-gdf09348f78dc/build/vmlinux
Percent│ pop %r10
│ pop %r9
│ pop %r8
│ pop %rax
│ pop %rsi
│ pop %rdx
│ pop %rsi
│ mov %rsp,%rdi
│ mov %gs:0x5004,%rsp
│ pushq 0x28(%rdi)
│ pushq (%rdi)
│ push %rax
│ ↑ jmp 6c
│ mov %cr3,%rdi
│ ↑ jmp 62
│ mov %rdi,%rax
│ and $0x7ff,%rdi
│ bt %rdi,%gs:0x2219a
│ ↑ jae 53
│ btr %rdi,%gs:0x2219a
│ mov %rax,%rdi
│ ↑ jmp 5bAfter:
entry_SYSCALL_64 /lib/modules/4.16.0-rc5-00086-gdf09348f78dc/build/vmlinux
0.65 │ → jne swapgs_restore_regs_and_return_to_usermode
│ pop %r10
│ pop %r9
│ pop %r8
│ pop %rax
│ pop %rsi
│ pop %rdx
│ pop %rsi
│ mov %rsp,%rdi
│ mov %gs:0x5004,%rsp
│ pushq 0x28(%rdi)
│ pushq (%rdi)
│ push %rax
│ ↓ jmp 132
│ mov %cr3,%rdi
│ ┌──jmp 128
│ │ mov %rdi,%rax
│ │ and $0x7ff,%rdi
│ │ bt %rdi,%gs:0x2219a
│ │↓ jae 119
│ │ btr %rdi,%gs:0x2219a
│ │ mov %rax,%rdi
│ │↓ jmp 121
│119:│ mov %rax,%rdi
│ │ bts $0x3f,%rdi
│121:│ or $0x800,%rdi
│128:└─→or $0x1000,%rdi
│ mov %rdi,%cr3
│132: pop %rax
│ pop %rdi
│ pop %rsp
│ → jmpq *0x825d2d(%rip) # ffffffff82225e88With those at least navigating to the right destination, an improvement
for these cases seems to be to be to somehow mark those inner functions,
which in this case could be:entry_SYSCALL_64 /lib/modules/4.16.0-rc5-00086-gdf09348f78dc/build/vmlinux
│syscall_return_via_sysret:
│ pop %r15
│ pop %r14
│ pop %r13
│ pop %r12
│ pop %rbp
│ pop %rbx
│ pop %rsi
│ pop %r10
│ pop %r9
│ pop %r8
│ pop %rax
│ pop %rsi
│ pop %rdx
│ pop %rsi
│ mov %rsp,%rdi
│ mov %gs:0x5004,%rsp
│ pushq 0x28(%rdi)
│ pushq (%rdi)
│ push %rax
│ ↓ jmp 132
│ mov %cr3,%rdi
│ ┌──jmp 128
│ │ mov %rdi,%rax
│ │ and $0x7ff,%rdi
│ │ bt %rdi,%gs:0x2219a
│ │↓ jae 119
│ │ btr %rdi,%gs:0x2219a
│ │ mov %rax,%rdi
│ │↓ jmp 121
│119:│ mov %rax,%rdi
│ │ bts $0x3f,%rdi
│121:│ or $0x800,%rdi
│128:└─→or $0x1000,%rdi
│ mov %rdi,%cr3
│132: pop %rax
│ pop %rdi
│ pop %rsp
│ → jmpq *0x825d2d(%rip) # ffffffff82225e88This all gets much better viewed if one uses 'perf report --ignore-vmlinux'
forcing the usage of /proc/kcore + /proc/kallsyms, when the above
actually gets down to:# perf report --ignore-vmlinux
## do '/64', will show the function names containing '64',
## navigate to /entry_SYSCALL_64_after_hwframe.annotation,
## press 'A' to annotate, then 'P' to print that annotation
## to a file
## From another xterm (or see on screen, this 'P' thing is for
## getting rid of those right side scroll bars/spaces):
# cat /entry_SYSCALL_64_after_hwframe.annotation
entry_SYSCALL_64_after_hwframe() /proc/kcore
Event: cycles:pppPercent
Disassembly of section load0:ffffffff9aa00044 :
11.97 push %rax
4.85 push %rdi
push %rsi
2.59 push %rdx
2.27 push %rcx
0.32 pushq $0xffffffffffffffda
1.29 push %r8
xor %r8d,%r8d
1.62 push %r9
0.65 xor %r9d,%r9d
1.62 push %r10
xor %r10d,%r10d
5.50 push %r11
xor %r11d,%r11d
3.56 push %rbx
xor %ebx,%ebx
4.21 push %rbp
xor %ebp,%ebp
2.59 push %r12
0.97 xor %r12d,%r12d
3.24 push %r13
xor %r13d,%r13d
2.27 push %r14
xor %r14d,%r14d
4.21 push %r15
xor %r15d,%r15d
0.97 mov %rsp,%rdi
5.50 → callq do_syscall_64
14.56 mov 0x58(%rsp),%rcx
7.44 mov 0x80(%rsp),%r11
0.32 cmp %rcx,%r11
→ jne swapgs_restore_regs_and_return_to_usermode
0.32 shl $0x10,%rcx
0.32 sar $0x10,%rcx
3.24 cmp %rcx,%r11
→ jne swapgs_restore_regs_and_return_to_usermode
2.27 cmpq $0x33,0x88(%rsp)
1.29 → jne swapgs_restore_regs_and_return_to_usermode
mov 0x30(%rsp),%r11
8.74 cmp %r11,0x90(%rsp)
→ jne swapgs_restore_regs_and_return_to_usermode
0.32 test $0x10100,%r11
→ jne swapgs_restore_regs_and_return_to_usermode
0.32 cmpq $0x2b,0xa0(%rsp)
0.65 → jne swapgs_restore_regs_and_return_to_usermodeI.e. using kallsyms makes the function start/end be done differently
than using what is in the vmlinux ELF symtab and actually the hits
goes to entry_SYSCALL_64_after_hwframe, which is a GLOBAL() after the
start of entry_SYSCALL_64:ENTRY(entry_SYSCALL_64)
UNWIND_HINT_EMPTY
pushq $__USER_CS /* pt_regs->cs */
pushq %rcx /* pt_regs->ip */
GLOBAL(entry_SYSCALL_64_after_hwframe)
pushq %rax /* pt_regs->orig_ax */PUSH_AND_CLEAR_REGS rax=$-ENOSYS
And it goes and ends at:
cmpq $__USER_DS, SS(%rsp) /* SS must match SYSRET */
jne swapgs_restore_regs_and_return_to_usermode/*
* We win! This label is here just for ease of understanding
* perf profiles. Nothing jumps here.
*/
syscall_return_via_sysret:
/* rcx and r11 are already restored (see code above) */
UNWIND_HINT_EMPTY
POP_REGS pop_rdi=0 skip_r11rcx=1So perhaps some people should really just play with '--ignore-vmlinux'
to force /proc/kcore + kallsyms.One idea is to do both, i.e. have a vmlinux annotation and a
kcore+kallsyms one, when possible, and even show the patched location,
etc.Reported-by: Linus Torvalds
Cc: Adrian Hunter
Cc: Andi Kleen
Cc: David Ahern
Cc: Jin Yao
Cc: Jiri Olsa
Cc: Namhyung Kim
Cc: Wang Nan
Link: https://lkml.kernel.org/n/tip-r11knxv8voesav31xokjiuo6@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo -
That strchr() in jump__scnprintf() needs to be nuked somehow, as it,
IIRC is already done in jump__parse() and if needed at scnprintf() time,
should be stashed in the struct filled in parse() time.For now jus defer it to just before where it is used.
Cc: Adrian Hunter
Cc: Andi Kleen
Cc: David Ahern
Cc: Jin Yao
Cc: Jiri Olsa
Cc: Namhyung Kim
Cc: Wang Nan
Link: https://lkml.kernel.org/n/tip-j0t5hagnphoz9xw07bh3ha3g@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo -
For instance:
entry_SYSCALL_64 /lib/modules/4.16.0-rc5-00086-gdf09348f78dc/build/vmlinux
5.50 │ → callq do_syscall_64
14.56 │ mov 0x58(%rsp),%rcx
7.44 │ mov 0x80(%rsp),%r11
0.32 │ cmp %rcx,%r11
│ → jne swapgs_restore_regs_and_return_to_usermode
0.32 │ shl $0x10,%rcx
0.32 │ sar $0x10,%rcx
3.24 │ cmp %rcx,%r11
│ → jne swapgs_restore_regs_and_return_to_usermode
2.27 │ cmpq $0x33,0x88(%rsp)
1.29 │ → jne swapgs_restore_regs_and_return_to_usermode
│ mov 0x30(%rsp),%r11
8.74 │ cmp %r11,0x90(%rsp)
│ → jne swapgs_restore_regs_and_return_to_usermode
0.32 │ test $0x10100,%r11
│ → jne swapgs_restore_regs_and_return_to_usermode
0.32 │ cmpq $0x2b,0xa0(%rsp)
0.65 │ → jne swapgs_restore_regs_and_return_to_usermodeIt'll behave just like a "call" instruction, i.e. press enter or right
arrow over one such line and the browser will navigate to the annotated
disassembly of that function, which when exited, via left arrow or esc,
will come back to the calling function.Now to support jump to an offset on a different function...
Reported-by: Linus Torvalds
Cc: Adrian Hunter
Cc: Andi Kleen
Cc: David Ahern
Cc: Jin Yao
Cc: Jiri Olsa
Cc: Namhyung Kim
Cc: Wang Nan
Link: https://lkml.kernel.org/n/tip-78o508mqvr8inhj63ddtw7mo@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo