Initial support for libtraceevent man pages - Documentation directory,
templates, configurations, Makefiles.
The first man page is also part of the patch - summary of the library
and all its APIs.
Building of the documentation is integrated into the libtraceevent build
process, new targets are added to its Makefile:
make help
make doc
make doc-clean
make doc-install
make doc-uninstall
Signed-off-by: Tzvetomir Stoyanov <tstoyanov@vmware.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linux-trace-devel@vger.kernel.org
Link: http://lore.kernel.org/linux-trace-devel/20190503091119.23399-2-tstoyanov@vmware.com
Link: http://lkml.kernel.org/r/20190510200106.104812629@goodmis.org
[ Replaced tracefs tracing/events to tracefs events in DESCRIPTION section ]
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
If fgets() fails due to any other error besides end-of-file, the version
char array may not even be null-terminated.
Signed-off-by: Donald Yandt <donald.yandt@gmail.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Avi Kivity <avi@scylladb.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Yanmin Zhang <yanmin_zhang@linux.intel.com>
Fixes: a1645ce12a ("perf: 'perf kvm' tool for monitoring guest performance from host")
Link: http://lkml.kernel.org/r/20190514110100.22019-1-donald.yandt@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Perf cannot parse UPI (Intel's "Ultra Path Interconnect" [1]) events.
# perf stat -e UPI_DATA_BANDWIDTH_TX
event syntax error: 'UPI_DATA_BANDWIDTH_TX'
\___ parser error
Run 'perf list' for a list of valid events
The JSON lists call the box UPI LL, while perf calls it upi. Add
conversion support to JSON to convert the unit properly.
Committer notes:
[1] https://en.wikipedia.org/wiki/Intel_Ultra_Path_Interconnect
"The Intel Ultra Path Interconnect (UPI) is a point-to-point processor
interconnect developed by Intel which replaced the Intel QuickPath
Interconnect (QPI) in Xeon Skylake-SP platforms starting in 2017.
UPI is a low-latency coherent interconnect for scalable multiprocessor
systems with a shared address space. It uses a directory-based home
snoop coherency protocol with a transfer speed of up to 10.4 GT/s.
Supporting processors typically have two or three UPI links."
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/1557234991-130456-1-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
With support for Python 2 or 3 and PySide 1 or 2 (Qt 4 or 5), it is
useful to see what versions are in use. Add an 'About' dialog box that
displays Python, PySide, Qt and database server (SQLite or PostgreSQL)
version numbers.
Committer testing:
$ python ~acme/libexec/perf-core/scripts/python/exported-sql-viewer.py ~/c/adrian.hunter/simple-retpoline.db
Then go to 'Help', then 'About', select all the lines with the mouse
press 'Control+C', then, on the same terminal press control+shift+V
which shows my current environment:
Python version: 2.7.16
PySide version: 1
Qt version: 4.8.7
SQLite version: 3.26.0
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20190503120828.25326-7-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Add a context menu (right-click) that provides options for copying to
clipboard, including, for trees, the ability to copy only the cell under
the mouse pointer.
Committer testing:
$ python ~acme/libexec/perf-core/scripts/python/exported-sql-viewer.py ~/c/adrian.hunter/simple-retpoline.db
Simply right click and pick "Copy selection", that at this point has
just the first line, not expanded, then see what was copied by pressing
shift+control+v on a terminal:
Call Path,Object,Count,Time (ns),Time (%),Branch Count,Branch Count (%)
▶ simple-retpolin,,,,,,
Ditto after expanding, i.e. the selection continues to be just one
line:
Call Path Object Count Time (ns) Time (%) Branch Count Branch Count (%)
▼ simple-retpolin
Now select all the lines with the mouse and control+shift+v again:
Call Path Object Count Time (ns) Time (%) Branch Count Branch Count (%)
▼ 14503:14503
▼ _start ld-2.28.so 1 156267 100.0 10602 100.0
▶ unknown unknown 1 2276 1.5 1 0.0
▶ _dl_start ld-2.28.so 1 137047 87.7 10088 95.2
▶ _dl_init ld-2.28.so 1 9142 5.9 326 3.1
▼ _start simple-retpoline 1 7457 4.8 182 1.7
▶ unknown unknown 1 805 10.8 1 0.5
▶ __libc_start_main libc-2.28.so 1 6347 85.1 179 98.4
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20190503120828.25326-6-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
As preparation for adding support for copying to clipboard, keep track of
what level each item is in tree items.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20190503120828.25326-4-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Fix the following error if shrink / enlarge font is used with the help
window.
Traceback (most recent call last):
File "tools/perf/scripts/python/exported-sql-viewer.py", line 2791, in ShrinkFont
ShrinkFont(win.view)
AttributeError: 'HelpWindow' object has no attribute 'view'
Committer testing:
Before, matches above output:
$ python ~acme/libexec/perf-core/scripts/python/exported-sql-viewer.py ~/c/adrian.hunter/simple-retpoline.db
Traceback (most recent call last):
File "/home/acme/libexec/perf-core/scripts/python/exported-sql-viewer.py", line 2780, in EnlargeFont
EnlargeFont(win.view)
AttributeError: 'HelpWindow' object has no attribute 'view'
$
After:
No more tracebacks, but the fonts don't get enlarged, which is kinda
frustrating...
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20190503120828.25326-2-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
As preparation for adding support for copying to clipboard, create view
in TreeWindowBase instead of derived classes.
Committer testing:
Tested using an old .db used to test some older patches:
$ python ~acme/libexec/perf-core/scripts/python/exported-sql-viewer.py ~/c/adrian.hunter/simple-retpoline.db
Nothing breaks.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20190503120828.25326-3-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Icelake and later platforms support collecting XMM registers with PEBS
event.
Add support for 'perf script' to dump them, and support for the register
parser in 'perf record -I=' ... to configure them.
For now they are just printed in hex, we could potentially later add
other formats too.
Committer testing:
Before:
# perf record -IXMM0
Warning:
unknown register XMM0, check man page or run 'perf record -I?'
Usage: perf record [<options>] [<command>]
or: perf record [<options>] -- <command> [<options>]
#
# perf record -I?
available registers: AX BX CX DX SI DI BP SP IP FLAGS CS SS R8 R9 R10 R11 R12 R13 R14 R15
Usage: perf record [<options>] [<command>]
or: perf record [<options>] -- <command> [<options>]
#
After:
# perf record -IXMM0
Error:
The sys_perf_event_open() syscall returned with 22 (Invalid argument) for event (cycles).
/bin/dmesg | grep -i perf may provide additional information.
#
# perf record -I?
available registers: AX BX CX DX SI DI BP SP IP FLAGS CS SS R8 R9 R10 R11 R12 R13 R14 R15 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 XMM9 XMM10 XMM11 XMM12 XMM13 XMM14 XMM15
Usage: perf record [<options>] [<command>]
or: perf record [<options>] -- <command> [<options>]
-I, --intr-regs[=<any register>]
sample selected machine registers on interrupt, use -I ? to list register names
#
More work is needed to, when faced with such error, warn the user that
that register is not available on the running platform.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20190506141926.13659-1-kan.liang@linux.intel.com
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Add quotes around the register name and suggest using 'perf record -I?'
to get the list of available registers.
Before:
# perf record -Idi,xmm20,xmm1
Warning:
unknown register xmm20, check man page
Usage: perf record [<options>] [<command>]
or: perf record [<options>] -- <command> [<options>]
-I, --intr-regs[=<any register>]
sample selected machine registers on interrupt, use -I ? to list register names
#
# perf record -Idi,xmm20,xmm1
Warning:
unknown register "xmm20", check man page or run "perf record -I?"
Usage: perf record [<options>] [<command>]
or: perf record [<options>] -- <command> [<options>]
-I, --intr-regs[=<any register>]
sample selected machine registers on interrupt, use -I ? to list register names
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lkml.kernel.org/n/tip-9a9hyuum8c0oggg86xd3sxc5@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
$ perf record -h -I
Usage: perf record [<options>] [<command>]
or: perf record [<options>] -- <command> [<options>]
-I, --intr-regs[=<any register>]
sample selected machine registers on interrupt, use -I ? to list register names
$ m
$ perf record -I ?
Workload failed: No such file or directory
$
After:
$ perf record -h -I
Usage: perf record [<options>] [<command>]
or: perf record [<options>] -- <command> [<options>]
-I, --intr-regs[=<any register>]
sample selected machine registers on interrupt, use '-I?' to list register names
$
$ perf record -I?
available registers: AX BX CX DX SI DI BP SP IP FLAGS CS SS R8 R9 R10 R11 R12 R13 R14 R15
Usage: perf record [<options>] [<command>]
or: perf record [<options>] -- <command> [<options>]
-I, --intr-regs[=<any register>]
sample selected machine registers on interrupt, use '-I?' to list register names
$
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Fixes: bcc84ec65a ("perf record: Add ability to name registers to record")
Link: https://lkml.kernel.org/n/tip-r0xhfhy5radmkhhcbcfs5izf@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
When running 'make -C tools clean' I noticed that a revision controlled
file was being deleted:
$ git diff
diff --git a/tools/pci/pcitest.sh b/tools/pci/pcitest.sh
deleted file mode 100644
index 75ed48ff2990..000000000000
--- a/tools/pci/pcitest.sh
+++ /dev/null
@@ -1,72 +0,0 @@
-#!/bin/sh
-# SPDX-License-Identifier: GPL-2.0
-
-echo "BAR tests"
-echo
<SNIP>
So I changed the make variables to fix that, testing it should produce
the same intended result while not deleting revision controlled files.
$ make O=/tmp/build/pci -C tools/pci install
make: Entering directory '/home/acme/git/perf/tools/pci'
make -f /home/acme/git/perf/tools/build/Makefile.build dir=. obj=pcitest
install -d -m 755 /usr/bin; \
for program in /tmp/build/pci/pcitest pcitest.sh; do \
install $program /usr/bin; \
done
install: cannot change permissions of ‘/usr/bin’: Operation not permitted
install: cannot create regular file '/usr/bin/pcitest': Permission denied
install: cannot create regular file '/usr/bin/pcitest.sh': Permission denied
make: *** [Makefile:46: install] Error 1
make: Leaving directory '/home/acme/git/perf/tools/pci'
$ ls -la /tmp/build/pci/pcitest
-rwxrwxr-x. 1 acme acme 27152 May 13 13:52 /tmp/build/pci/pcitest
$ /tmp/build/pci/pcitest
can't open PCI Endpoint Test device: No such file or directory
$
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kishon Vijay Abraham I <kishon@ti.com>
Cc: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Fixes: 1ce78ce094 ("tools: PCI: Change pcitest compiling process")
Link: https://lkml.kernel.org/n/tip-9re6bd7eh9epi3koslkv3ocn@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
To get the changes in:
878068ea27 ("perf/x86: Support outputting XMM registers")
That will be used in a followup patch to allow users to ask for some or
all of those registers to be collected in certain contatexts.
This silences the following perf build warning:
Warning: Kernel ABI header at 'tools/arch/x86/include/uapi/asm/perf_regs.h' differs from latest version at 'arch/x86/include/uapi/asm/perf_regs.h'
diff -u tools/arch/x86/include/uapi/asm/perf_regs.h arch/x86/include/uapi/asm/perf_regs.h
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lkml.kernel.org/n/tip-6pjnnrzqt3x3n2cd6br3wk7k@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
To get the changes in:
59073aaf6d ("kvm: x86: Add exception payload fields to kvm_vcpu_events")
This silences the following perf build warning:
Warning: Kernel ABI header at 'tools/arch/x86/include/uapi/asm/kvm.h' differs from latest version at 'arch/x86/include/uapi/asm/kvm.h'
diff -u tools/arch/x86/include/uapi/asm/kvm.h arch/x86/include/uapi/asm/kvm.h
The changes in this file are in something not used at this time in any
tools/perf/ tool.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jim Mattson <jmattson@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Link: https://lkml.kernel.org/n/tip-6uh8tpraons0h22dmxgfyony@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
To bring in the change made in this cset:
b69656fa7e ("x86/uaccess: Fix up the fixup")
Silencing this perf build warning:
Warning: Kernel ABI header at 'tools/arch/x86/lib/memcpy_64.S' differs from latest version at 'arch/x86/lib/memcpy_64.S'
diff -u tools/arch/x86/lib/memcpy_64.S arch/x86/lib/memcpy_64.S
No changes in the tooling using this, that was just to ease some objtool
return checking.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lkml.kernel.org/n/tip-j0mxgqkuibhw5qid9saaspdu@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
When compiled with libunwind, perf does some preparatory work when
processing side-band events. This is not needed when report actually
don't unwind dwarf callchains, so it's disabled with
dwarf_callchain_users bool.
However we could move that check to higher level and shield more
unwanted code for normal report processing, giving us following speed up
on kernel build profile:
Before:
$ perf record make -j40
...
$ ll ../../perf.data
-rw-------. 1 jolsa jolsa 461783932 Apr 26 09:11 perf.data
$ perf stat -e cycles:u,instructions:u perf report -i perf.data > out
Performance counter stats for 'perf report -i perf.data':
78,669,920,155 cycles:u
99,076,431,951 instructions:u # 1.26 insn per cycle
55.382823668 seconds time elapsed
27.512341000 seconds user
27.712871000 seconds sys
After:
$ perf stat -e cycles:u,instructions:u perf report -i perf.data > out
Performance counter stats for 'perf report -i perf.data':
59,626,798,904 cycles:u
88,583,575,849 instructions:u # 1.49 insn per cycle
21.296935559 seconds time elapsed
20.010191000 seconds user
1.202935000 seconds sys
The speed is higher with profile having many side-band events,
because these trigger libunwind preparatory code.
This does not apply for perf compiled with libdw for dwarf unwind,
only for build with libunwind.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20190426073804.17238-1-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Install directories of header and library files are hard coded in
pkg-config template file.
They must be configurable, the Makefile should set them on the
compilation / install stage.
Signed-off-by: Tzvetomir Stoyanov <tstoyanov@vmware.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20190418211556.5a12adc3@oasis.local.home
Link: http://lkml.kernel.org/r/20190329144546.5819-1-tstoyanov@vmware.com
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This patch add support for DWARF register mappings and libdw registers
initialization, which is used by perf callchain analyzing when
--call-graph=dwarf is given.
Here is the elfutils csky backend patch set:
https://sourceware.org/ml/elfutils-devel/2019-q2/msg00007.html
Signed-off-by: Mao Han <han_mao@c-sky.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: linux-arch@vger.kernel.org
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1555860794-10572-1-git-send-email-guoren@kernel.org
Signed-off-by: Guo Ren <ren_guo@c-sky.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
There are a couple of spelling mistakes in test assert messages. Fix them.
Signed-off-by: Colin King <colin.king@canonical.com>
Reviewed-by: Mukesh Ojha <mojha@codeaurora.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: kernel-janitors@vger.kernel.org
Link: http://lkml.kernel.org/r/20190417105539.5902-1-colin.king@canonical.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The hist__account_cycles() function is executed when the
hist_iter__branch_callback() is called.
But it looks it's not necessary. In hist__account_cycles, it already
walks on all branch entries.
This patch moves the hist__account_cycles out of callback, now the data
processing is much faster than before.
Previous code has an issue that the ch[offset].num++ (in
__symbol__account_cycles) is executed repeatedly since
hist__account_cycles is called in each hist_iter__branch_callback, so
the counting of ch[offset].num is not correct (too big).
With this patch, the issue is fixed. And we don't need the code of
"ch->reset >= ch->num / 2" to check if there are too many overlaps (in
annotation__count_and_fill), otherwise some data would be hidden.
Now, we can try, for example:
perf record -b ...
perf annotate or perf report -s symbol
The before/after output should be no change.
v3:
---
Fix the crash in stdio mode.
Like previous code, it needs the checking of ui__has_annotation()
before hist__account_cycles()
v2:
---
1. Cover the similar perf report
2. Remove the checking code "ch->reset >= ch->num / 2"
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1552684577-29041-1-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Add wait_var_event_interruptible() to allow interruptible waits for events.
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Allow used DNS resolver keys to be invalidated after use if the caller is
doing its own caching of the results. This reduces the amount of resources
required.
Fix AFS to invalidate DNS results to kill off permanent failure records
that get lodged in the resolver keyring and prevent future lookups from
happening.
Fixes: 0a5143f2f8 ("afs: Implement VL server rotation")
Signed-off-by: David Howells <dhowells@redhat.com>
Fix it such that afs_cell records always have a VL server list record
attached, even if it's a dummy one, so that various checks can be removed.
Signed-off-by: David Howells <dhowells@redhat.com>
When afs_update_cell() replaces the cell->vl_servers list, it uses RCU
protocol so that proc is protected, but doesn't take ->vl_servers_lock to
protect afs_start_vl_iteration() (which does actually take a shared lock).
Fix this by making afs_update_cell() take an exclusive lock when replacing
->vl_servers.
Fixes: 0a5143f2f8 ("afs: Implement VL server rotation")
Signed-off-by: David Howells <dhowells@redhat.com>
afs_xattr_get_yfs() tries to free yacl, which may hold an error value (say
if yfs_fs_fetch_opaque_acl() failed and returned an error).
Fix this by allocating yacl up front (since it's a fixed-length struct,
unlike afs_acl) and passing it in to the RPC function. This also allows
the flags to be placed in the object rather than passing them through to
the RPC function.
Fixes: ae46578b96 ("afs: Get YFS ACLs and information through xattrs")
Signed-off-by: David Howells <dhowells@redhat.com>
Fix incorrect error handling in afs_xattr_get_acl() where there appears to
be a redundant assignment before return, but in fact the return should be a
goto to the error handling at the end of the function.
Fixes: 260f082bae ("afs: Get an AFS3 ACL as an xattr")
Addresses-Coverity: ("Unused Value")
Reported-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Joe Perches <joe@perches.com>
- error out if a user specifies a directory instead of a file from
"Save" menu of GUI interfaces
- do not overwrite .config if there is no change in the configuration
- create parent directories as needed when a user specifies a new file
path from "Save" menu of menuconfig/nconfig
- fix potential buffer overflow
- some trivial cleanups
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1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=hgra
-----END PGP SIGNATURE-----
Merge tag 'kconfig-v5.2' of git://git.kernel.org/pub/scm/linux/kernel/git/masahiroy/linux-kbuild
Pull Kconfig updates from Masahiro Yamada:
- error out if a user specifies a directory instead of a file from
"Save" menu of GUI interfaces
- do not overwrite .config if there is no change in the configuration
- create parent directories as needed when a user specifies a new file
path from "Save" menu of menuconfig/nconfig
- fix potential buffer overflow
- some trivial cleanups
* tag 'kconfig-v5.2' of git://git.kernel.org/pub/scm/linux/kernel/git/masahiroy/linux-kbuild:
kconfig: make conf_get_autoconfig_name() static
kconfig: use snprintf for formatting pathnames
kconfig: remove useless NULL pointer check in conf_write_dep()
kconfig: make parent directories for the saved .config as needed
kconfig: do not write .config if the content is the same
kconfig: do not accept a directory for configuration output
kconfig: remove trailing whitespaces
kconfig: Make nconf-cfg.sh executable
- Update the ACPICA code in the kernel to upstream revision 20190509
including one regression fix:
* Prevent excessive ACPI debug messages from being printed
by moving the ACPI_DEBUG_DEFAULT definition to the right
place (Erik Schmauss).
- Set the enable_for_wake bits for wakeup GPEs during suspend to
idle to allow acpi_enable_all_wakeup_gpes() to enable them as
aproppriate and make wakeup devices sighaling events through ACPI
GPEs work with suspend-to-idle again (Rajat Jain).
- Use 64 bits to store the return values of _ADR which are assumed
to be 64-bit by some bus specs and may contain nonzero bits in the
upper 32 bits part for some devices (Pierre-Louis Bossart).
- Fix two minor issues with the ACPI documentation (Sakari Ailus).
-----BEGIN PGP SIGNATURE-----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=/71L
-----END PGP SIGNATURE-----
Merge tag 'acpi-5.2-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm
Pull more ACPI updates from Rafael Wysocki:
"These fix two regressions introduced during the 5.0 cycle, in ACPICA
and in device PM, cause the values returned by _ADR to be stored in 64
bits and fix two ACPI documentation issues.
Specifics:
- Update the ACPICA code in the kernel to upstream revision 20190509
including one regression fix:
* Prevent excessive ACPI debug messages from being printed by
moving the ACPI_DEBUG_DEFAULT definition to the right place
(Erik Schmauss).
- Set the enable_for_wake bits for wakeup GPEs during suspend to idle
to allow acpi_enable_all_wakeup_gpes() to enable them as
aproppriate and make wakeup devices sighaling events through ACPI
GPEs work with suspend-to-idle again (Rajat Jain).
- Use 64 bits to store the return values of _ADR which are assumed to
be 64-bit by some bus specs and may contain nonzero bits in the
upper 32 bits part for some devices (Pierre-Louis Bossart).
- Fix two minor issues with the ACPI documentation (Sakari Ailus)"
* tag 'acpi-5.2-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
ACPI: PM: Set enable_for_wake for wakeup GPEs during suspend-to-idle
Documentation: ACPI: Direct references are allowed to devices only
Documentation: ACPI: Use tabs for graph ASL indentation
ACPICA: Update version to 20190509
ACPICA: Linux: move ACPI_DEBUG_DEFAULT flag out of ifndef
ACPI: bus: change _ADR representation to 64 bits
- Fix recent regression causing kernels built with CONFIG_PM
unset to crash on systems that support the Performance and
Energy Bias Hint (EPB) by avoiding to compile the EPB-related
code depending on CONFIG_PM when it is unset (Rafael Wysocki).
- Clean up the transition notifier invocation code in the cpufreq
core and change some users of cpufreq transition notifiers
accordingly (Viresh Kumar).
- Change MAINTAINERS to cover the schedutil governor as part of
cpufreq (Viresh Kumar).
- Simplify cpufreq_init_policy() to avoid redundant computations
(Yue Hu).
- Add explanatory comment to the cpufreq core (Rafael Wysocki).
- Introduce a new flag, GENPD_FLAG_RPM_ALWAYS_ON, to the generic
power domains (genpd) framework along with the first user of it
(Leonard Crestez).
-----BEGIN PGP SIGNATURE-----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=LqTN
-----END PGP SIGNATURE-----
Merge tag 'pm-5.2-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm
Pull more power management updates from Rafael Wysocki:
"These fix a recent regression causing kernels built with CONFIG_PM
unset to crash on systems that support the Performance and Energy Bias
Hint (EPB), clean up the cpufreq core and some users of transition
notifiers and introduce a new power domain flag into the generic power
domains framework (genpd).
Specifics:
- Fix recent regression causing kernels built with CONFIG_PM unset to
crash on systems that support the Performance and Energy Bias Hint
(EPB) by avoiding to compile the EPB-related code depending on
CONFIG_PM when it is unset (Rafael Wysocki).
- Clean up the transition notifier invocation code in the cpufreq
core and change some users of cpufreq transition notifiers
accordingly (Viresh Kumar).
- Change MAINTAINERS to cover the schedutil governor as part of
cpufreq (Viresh Kumar).
- Simplify cpufreq_init_policy() to avoid redundant computations (Yue
Hu).
- Add explanatory comment to the cpufreq core (Rafael Wysocki).
- Introduce a new flag, GENPD_FLAG_RPM_ALWAYS_ON, to the generic
power domains (genpd) framework along with the first user of it
(Leonard Crestez)"
* tag 'pm-5.2-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
soc: imx: gpc: Use GENPD_FLAG_RPM_ALWAYS_ON for ERR009619
PM / Domains: Add GENPD_FLAG_RPM_ALWAYS_ON flag
cpufreq: Update MAINTAINERS to include schedutil governor
cpufreq: Don't find governor for setpolicy drivers in cpufreq_init_policy()
cpufreq: Explain the kobject_put() in cpufreq_policy_alloc()
cpufreq: Call transition notifier only once for each policy
x86: intel_epb: Take CONFIG_PM into account
Pull crypto fixes from Herbert Xu:
"This fixes a number of issues in the chelsio and caam drivers"
* 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6:
Revert "crypto: caam/jr - Remove extra memory barrier during job ring dequeue"
crypto: caam - fix caam_dump_sg that iterates through scatterlist
crypto: caam - fix DKP detection logic
MAINTAINERS: Maintainer for Chelsio crypto driver
crypto: chelsio - count incomplete block in IV
crypto: chelsio - Fix softlockup with heavy I/O
crypto: chelsio - Fix NULL pointer dereference
In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.
This patch aims to suppress 3 missing-break-in-switch false positives
on some architectures.
Acked-by: Arnd Bergmann <arnd@arndb.de>
Cc: Deepa Dinamani <deepa.kernel@gmail.com>
Cc: Gustavo A. R. Silva <gustavo@embeddedor.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Jann Horn <jannh@google.com>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Fix afs_release() to go through the cleanup part of the function if
FMODE_WRITE is set rather than exiting through vfs_fsync() (which skips the
cleanup). The cleanup involves discarding the refs on the key used for
file ops and the writeback key record.
Also fix afs_evict_inode() to clean up any left over wb keys attached to
the inode/vnode when it is removed.
Fixes: 5a81327616 ("afs: Do better accretion of small writes on newly created content")
Signed-off-by: David Howells <dhowells@redhat.com>
media_device_cleanup() and v4l2_m2m_unregister_media_controller() were
missing in the probe error path.
While at it, re-order calls in the remove path to unregister/cleanup
things in the reverse order they were initialized/registered.
Signed-off-by: Jonas Karlman <jonas@kwiboo.se>
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
v4l2-compliance complains that ->bus_info is empty.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
This makes the function more generic so it can easily be re-used when
adding support for the decoding functionality.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Those calls are needed to restore a clean PM state when the probe fails
or when the driver is unloaded such that future ->probe() calls can
initialize runtime PM again.
Signed-off-by: Jonas Karlman <jonas@kwiboo.se>
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Pass -1 to video_register_device() to let the core assign the first
free id instead of trying to get id 0.
In practice it doesn't make a difference since video_register_device()
is not strict about id requests and will anyway pick the first free id
starting at the id passed in argument, and passing -1 has the same
effect as passing 0. But let's comply with the API doc and pass -1
here.
Signed-off-by: Jonas Karlman <jonas@kwiboo.se>
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
* pm-cpufreq:
cpufreq: Update MAINTAINERS to include schedutil governor
cpufreq: Don't find governor for setpolicy drivers in cpufreq_init_policy()
cpufreq: Explain the kobject_put() in cpufreq_policy_alloc()
cpufreq: Call transition notifier only once for each policy
* pm-domains:
soc: imx: gpc: Use GENPD_FLAG_RPM_ALWAYS_ON for ERR009619
PM / Domains: Add GENPD_FLAG_RPM_ALWAYS_ON flag
* acpi-bus:
ACPI: bus: change _ADR representation to 64 bits
* acpi-doc:
Documentation: ACPI: Direct references are allowed to devices only
Documentation: ACPI: Use tabs for graph ASL indentation
* acpi-pm:
ACPI: PM: Set enable_for_wake for wakeup GPEs during suspend-to-idle
The directive specified in the documentation to add an exception
for a single file in a Makefile was inverted.
Signed-off-by: Raphael Gault <raphael.gault@arm.com>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/522362a1b934ee39d0af0abb231f68e160ecf1a8.1557874043.git.jpoimboe@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Commit 345c0dbf3a ("ext4: protect journal inode's blocks using
block_validity") failed to add an exception for the journal inode in
ext4_check_blockref(), which is the function used by ext4_get_branch()
for indirect blocks. This caused attempts to read from the ext3-style
journals to fail with:
[ 848.968550] EXT4-fs error (device sdb7): ext4_get_branch:171: inode #8: block 30343695: comm jbd2/sdb7-8: invalid block
Fix this by adding the missing exception check.
Fixes: 345c0dbf3a ("ext4: protect journal inode's blocks using block_validity")
Reported-by: Arthur Marsh <arthur.marsh@internode.on.net>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
This is being sent to get a fix for the gcc 9.1 build warnings, and I've
also pulled in some bug fix patches that were posted in the last two
weeks.
- Avoid the gcc 9.1 warning about overflowing a union member
- Fix the wrong callback type for a single response netlink to doit
- Bug fixes from more usage of the mlx5 devx interface
-----BEGIN PGP SIGNATURE-----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=Lo/s
-----END PGP SIGNATURE-----
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma
Pull more rdma updates from Jason Gunthorpe:
"This is being sent to get a fix for the gcc 9.1 build warnings, and
I've also pulled in some bug fix patches that were posted in the last
two weeks.
- Avoid the gcc 9.1 warning about overflowing a union member
- Fix the wrong callback type for a single response netlink to doit
- Bug fixes from more usage of the mlx5 devx interface"
* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma:
net/mlx5: Set completion EQs as shared resources
IB/mlx5: Verify DEVX general object type correctly
RDMA/core: Change system parameters callback from dumpit to doit
RDMA: Directly cast the sockaddr union to sockaddr
Merge more updates from Andrew Morton:
- a couple of hotfixes
- almost all of the rest of MM
- lib/ updates
- binfmt_elf updates
- autofs updates
- quite a lot of misc fixes and updates
- reiserfs, fatfs
- signals
- exec
- cpumask
- rapidio
- sysctl
- pids
- eventfd
- gcov
- panic
- pps
- gdb script updates
- ipc updates
* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (126 commits)
mm: memcontrol: fix NUMA round-robin reclaim at intermediate level
mm: memcontrol: fix recursive statistics correctness & scalabilty
mm: memcontrol: move stat/event counting functions out-of-line
mm: memcontrol: make cgroup stats and events query API explicitly local
drivers/virt/fsl_hypervisor.c: prevent integer overflow in ioctl
drivers/virt/fsl_hypervisor.c: dereferencing error pointers in ioctl
mm, memcg: rename ambiguously named memory.stat counters and functions
arch: remove <asm/sizes.h> and <asm-generic/sizes.h>
treewide: replace #include <asm/sizes.h> with #include <linux/sizes.h>
fs/block_dev.c: Remove duplicate header
fs/cachefiles/namei.c: remove duplicate header
include/linux/sched/signal.h: replace `tsk' with `task'
fs/coda/psdev.c: remove duplicate header
ipc: do cyclic id allocation for the ipc object.
ipc: conserve sequence numbers in ipcmni_extend mode
ipc: allow boot time extension of IPCMNI from 32k to 16M
ipc/mqueue: optimize msg_get()
ipc/mqueue: remove redundant wq task assignment
ipc: prevent lockup on alloc_msg and free_msg
scripts/gdb: print cached rate in lx-clk-summary
...
When a cgroup is reclaimed on behalf of a configured limit, reclaim
needs to round-robin through all NUMA nodes that hold pages of the memcg
in question. However, when assembling the mask of candidate NUMA nodes,
the code only consults the *local* cgroup LRU counters, not the
recursive counters for the entire subtree. Cgroup limits are frequently
configured against intermediate cgroups that do not have memory on their
own LRUs. In this case, the node mask will always come up empty and
reclaim falls back to scanning only the current node.
If a cgroup subtree has some memory on one node but the processes are
bound to another node afterwards, the limit reclaim will never age or
reclaim that memory anymore.
To fix this, use the recursive LRU counts for a cgroup subtree to
determine which nodes hold memory of that cgroup.
The code has been broken like this forever, so it doesn't seem to be a
problem in practice. I just noticed it while reviewing the way the LRU
counters are used in general.
Link: http://lkml.kernel.org/r/20190412151507.2769-5-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Reviewed-by: Roman Gushchin <guro@fb.com>
Cc: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Right now, when somebody needs to know the recursive memory statistics
and events of a cgroup subtree, they need to walk the entire subtree and
sum up the counters manually.
There are two issues with this:
1. When a cgroup gets deleted, its stats are lost. The state counters
should all be 0 at that point, of course, but the events are not.
When this happens, the event counters, which are supposed to be
monotonic, can go backwards in the parent cgroups.
2. During regular operation, we always have a certain number of lazily
freed cgroups sitting around that have been deleted, have no tasks,
but have a few cache pages remaining. These groups' statistics do not
change until we eventually hit memory pressure, but somebody
watching, say, memory.stat on an ancestor has to iterate those every
time.
This patch addresses both issues by introducing recursive counters at
each level that are propagated from the write side when stats change.
Upward propagation happens when the per-cpu caches spill over into the
local atomic counter. This is the same thing we do during charge and
uncharge, except that the latter uses atomic RMWs, which are more
expensive; stat changes happen at around the same rate. In a sparse
file test (page faults and reclaim at maximum CPU speed) with 5 cgroup
nesting levels, perf shows __mod_memcg_page state at ~1%.
Link: http://lkml.kernel.org/r/20190412151507.2769-4-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Reviewed-by: Roman Gushchin <guro@fb.com>
Cc: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Tzvetomir Stoyanov