CppCheck founds a few wrong arguments in format strings and a NULL
pointer dereference.
Amended version with fixed strcmp() usage.
Signed-off-by: Boris Egorov <egorov@linux.com>
This code is not PIC clean which means it fails to build on hardened
32bit x86 systems (i.e. building as PIE).
While here, optimize the existing cpuid logic slightly.
URL: https://bugs.gentoo.org/518936
Signed-off-by: Mike Frysinger <vapier@gentoo.org>
This patch comes from openSUSE / SLE. Original author was probably
Petr Uzel.
Internal SUSE references: fate310255, sr226509
VMmware backdoor assembler code has been fixed for old clang compiler
(travis), see
see http://llvm.org/bugs/show_bug.cgi?id=9379
CC: Stanislav Brabec <sbrabec@suse.cz>
CC: Petr Uzel <petr.uzel@suse.cz>
Signed-off-by: Ruediger Meier <ruediger.meier@ga-group.nl>
This patch comes originally from openSUSE / SLE. Author was probably
Petr Uzel.
Internal SUSE references: fate310255, sr226509
In comparison to the original patch we have slightly corrected iSeries
and pSeries detection according to Alexander Graf's comments on
util-linux@vger.kernel.org. Maybe we would need to add some more code
to detect pSeries emulated by Qemu/KVM.
CC: Stanislav Brabec <sbrabec@suse.cz>
CC: Petr Uzel <petr.uzel@suse.cz>
CC: Alexander Graf <agraf@suse.de>
Signed-off-by: Ruediger Meier <ruediger.meier@ga-group.nl>
- add HYPER_VBOX
- improve HYPER_VMWARE
This patch comes from openSUSE / SLE. Original author was probably
Petr Uzel.
Internal SUSE references: fate310255, sr226509
CC: Stanislav Brabec <sbrabec@suse.cz>
CC: Petr Uzel <petr.uzel@suse.cz>
Signed-off-by: Ruediger Meier <ruediger.meier@ga-group.nl>
* rename flags functions to scols_table_enable_*
* rename *_no_foo() functions to _nofoo()
* output formats are mutually exclusive, so don't use flags there
* don't assume symbols in scols_new_table(), use scols_table_set_symbols()
Signed-off-by: Karel Zak <kzak@redhat.com>
There are systems where the size file does not exist. Most badly even
lscpu -p would abort allthough it does not use the size:
$ lscpu -p
lscpu: error: cannot open
/sys/devices/system/cpu/cpu0/cache/index0/size: No such file or directory
This patch does not abort in this case and prints "unknown size" in
human-readable case. For examle on this qemu pcc test machine:
$ lscpu
Architecture: ppc
CPU op-mode(s): 32-bit
Byte Order: Big Endian
CPU(s): 1
On-line CPU(s) list: 0
Thread(s) per core: 1
Core(s) per socket: 1
Socket(s): 1
Model: Power Macintosh
BogoMIPS: 33.25
L1d cache: unknown size
L1i cache: unknown size
Signed-off-by: Ruediger Meier <ruediger.meier@ga-group.nl>
Not all file systems support the d_type field and simply checking for
d_type == DT_DIR in is_node_dirent would cause the test suite to fail
if run on (for example) XFS.
The simple fix is to check for DT_DIR or DT_UNKNOWN in is_node_dirent.
Signed-off-by: Stewart Smith <stewart@linux.vnet.ibm.com>
lscpu fails to print proper NUMA node values in a system with
discontinuous nodes. This patch adds support by creating a nodeidx
array to map node numbers.
Based on patch from Madhavan Srinivasan <maddy@linux.vnet.ibm.com>.
Reported-by: Madhavan Srinivasan <maddy@linux.vnet.ibm.com>
Signed-off-by: Karel Zak <kzak@redhat.com>
lscpu don't work correctly on my system with:
$ cat /sys/devices/system/cpu/possible
0-1,4-5,8-9,12-13
[kzak@redhat.com: - coding style,
- add commit message
- add real_cpu_num() macro,
- fix functions where we need idx as well as CPU number]
Signed-off-by: Karel Zak <kzak@redhat.com>
The lscpu tool only shows the current and max CPU frequencies, however,
in many scenarios this is not enough. If there are energy saving situations
(like some CPUs being idle, or not fully used) the cpugov can lower this value.
Signed-off-by: Davidlohr Bueso <davidlohr@hp.com>
The existing 'CPU MHz' is usually dynamic value, which CPU governor
changes up on needs of CPU demand. Assuming lscpu is used to gather
information to a hardware inventory the dynamic value is misleading. For
inventing the maximum MHz value is more sensible.
Signed-off-by: Sami Kerola <kerolasa@iki.fi>
read_basicinfo() relies on sysfs cpu directories
"/sys/devices/system/cpu/cpu%d" with assumption that cpu
logical number %d is always sequentially assigned for all
CPUs. However, this assumption is not correct with CPU
hot-remove operation since it removes a target sysfs cpu
directory after it is ejected. As a result, lscpu may not
recognize all CPUs.
The issue can be easily reproduced on KVM or VirtualBox,
which supports CPU eject operation, as follows.
1) The system has 4 CPUs
$ lscpu -a -e
CPU NODE SOCKET CORE L1d:L1i:L2 ONLINE
0 0 0 0 0:0:0 yes
1 0 1 1 1:1:1 yes
2 0 2 2 2:2:2 yes
3 0 3 3 3:3:3 yes
2) Eject cpu2
# echo 1 > /sys/bus/acpi/devices/LNXCPU:02/eject
3) lscpu no longer recognizes cpu3 after cpu2 is ejected
$ lscpu -a -e
CPU NODE SOCKET CORE L1d:L1i:L2 ONLINE
0 0 0 0 0:0:0 yes
1 0 1 1 1:1:1 yes
The following changes are made to address this issue.
- Use maxcpus to allocate and parse bitmaps.
- Set desc->ncpu from cpu/present, which includes both on-line
and off-line CPUs.
- Add is_cpu_present() to check if a CPU is present. Ejected
CPUs are not present.
[kzak@redhat.com: - read also /sys/devices/system/cpu/possible mask to
determine maximal number of CPUs,
- err() if possible mask is not found in /sys]
Signed-off-by: Toshi Kani <toshi.kani@hp.com>
Signed-off-by: Karel Zak <kzak@redhat.com>
Passing the --all, --online or --offline options for the output summary
doesn't make much sense. It should be limited to the two list output options.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
sys-utils/lscpu.c:1084:8: warning: declaration of 'buf' shadows a previous local [-Wshadow]
sys-utils/lscpu.c:1077:7: warning: shadowed declaration is here [-Wshadow]
sys-utils/lscpu.c:1144:9: warning: declaration of 'buf' shadows a previous local [-Wshadow]
sys-utils/lscpu.c:1077:7: warning: shadowed declaration is here [-Wshadow]
sys-utils/lscpu.c:1196:8: warning: declaration of 'buf' shadows a previous local [-Wshadow]
sys-utils/lscpu.c:1077:7: warning: shadowed declaration is here [-Wshadow]
sys-utils/lscpu.c:1197:7: warning: declaration of 'i' shadows a previous local [-Wshadow]
sys-utils/lscpu.c:1078:6: warning: shadowed declaration is here [-Wshadow]
Signed-off-by: Sami Kerola <kerolasa@iki.fi>
lscpu.c: In function ‘has_pci_device’:
lscpu.c:425:11: warning: comparison between signed and unsigned integer expressions [-Wsign-compare]
lscpu.c:425:28: warning: comparison between signed and unsigned integer expressions [-Wsign-compare]
Signed-off-by: Karel Zak <kzak@redhat.com>
With -Wall -Werror, compilation of lscpu.c fails with:
Making all in sys-utils
make[2]: Entering directory `/home/petr/upstream/util-linux/sys-utils'
gcc -std=gnu99 -DHAVE_CONFIG_H -I. -I.. -include ../config.h -I../include -DLOCALEDIR=\"/usr/share/locale\" -fsigned-char -Wall -Werror -MT lscpu.o -MD -MP -MF .deps/lscpu.Tpo -c -o lscpu.o lscpu.c
lscpu.c: In function ‘print_parsable’:
lscpu.c:971:7: error: operation on ‘p’ may be undefined [-Werror=sequence-point]
cc1: all warnings being treated as errors
Fix by splitting the pointer increment to separate statement.
Signed-off-by: Petr Uzel <petr.uzel@suse.cz>
The tool misspellings (https://github.com/lyda/misspell-check)
detected several typos. Command used:
$ git ls-files | grep -v ^po/ | misspellings -f -
* isosize: Fix typo in usage string.
* configure.ac: Fix typo in help string of --enable-most-builds option.
* fdisk: Fix typo in man page.
* libblkid, blkid, mount: Likewise.
* Fix various typos in docs and in source code comments.
Signed-off-by: Bernhard Voelker <mail@bernhard-voelker.de>
The string format is not being passed triggering:
lscpu.c: In function ‘read_hypervisor’:
lscpu.c:545:4: warning: format not a string literal and no format arguments
lscpu.c: In function ‘get_cell_header’:
lscpu.c:904:2: warning: format not a string literal and no format arguments
lscpu.c:904:2: warning: format not a string literal and no format arguments
Signed-off-by: Davidlohr Bueso <dave@gnu.org>
Some people complained about the first letter of Yes/No as seen in the
online and configured column in the human readabe output being a capital
letter instead of the expected lower case letter.
So let's try to make everbody happy and convert them to lower case.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Disallow superfluous commands for lscpu like e.g. "lscpu bla" and let it
fail print the help text instead.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Implement "--offline" option which only prints offline cpus. As a side effect
we can get rid of the internal "allcpus" flag, since if we want to print
informations for online and offline cpus we simply set both flags.
When reading sysfs attributes of cpus this is now done for all cpus, since
e.g. the topology informations of the online cpus may influence the
topology informations of the offline cpus. This mainly because online cpus
may contain masks which include offline cpus while offline cpus have a
missing topology directory.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
The modifier mod->allcpus must be set earlier and also must be used
earlier. The current code only reads sysfs attributes from online
cpus but skips offline cpus.
So initialize mod->allcpus earlier.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
A couple of these functions already have been copied to chcpu.c,
so it makes sense to move these functions into an own file.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
However I'd like to see one change if you don't object: printing just "N" or
"Y" instead of "No" and "Yes" in the human readable output looks a bit ugly to
me.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Some vendors have several hypervisors. Therefore it makes sense to not only
print out the hypervisor vendor but also the name of the hypervisor.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Karel Zak <kzak@redhat.com>
The parsable output includes only lines of online CPUs. To also include
lines for all offline CPUs the "--all" option can be specified.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
lscpu only prints lines for online CPUs. At least for the human readable
list the offline CPUs are of interest as well. In order to distinguish
between online and offline CPUs introduce the "Online" column.
By default the human readable output now displays online and offline CPUs.
The parsable output is not changed. It will print only lines for online
CPUs as it used to do.
[kzak@redhat.com: - minor changes]
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Karel Zak <kzak@redhat.com>
CPUs may be in a configured or deconfigured state depending if the CPU resource
may be used by the guest. If a CPU is in configured state the guest may use it
(i.e. set it online). It it is in deconfigured state it cannot use it before
changing its state to configured. Display this CPU attribute as well.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Based on patch from Heiko Carstens <heiko.carstens@de.ibm.com>:
lscpu currently only supports a parsable output which contains a row for
each cpu and its attributes. This output contains only comas as separators
and is hard to read for humans.
Therefore add a new option "-e | --extended" which outputs the rows in a
much more readable (and non-parsable) form. Just like for the -p option a
list of columns can be specified that shall be included in the output.
By default this option will print all columns that contain data.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Karel Zak <kzak@redhat.com>
Add a --version option like most other tools have it.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Karel Zak <kzak@redhat.com>
First check path before accessing files to be sure they actually exist. This is
necessary when also informations for offline CPUs will be printed. Since we do
not necessarily know if "cpu is offline" means the same as "path does not
exist" just check for it.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Simplify the logic to "always print a ',' for each cache except if it is the
last one. This is also a preparation patch for printing the cache column for
offline CPUs where it would print one colon too much because of the current
logic.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
The extended parsable output prints a colon instead of comma between each
item. The case where a CPU doesn't belong to any cache was not converted.
Just fix this.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Fix typo where the comma operator has been introduced.
Use a semicolon instead so we end up with simple assignment expressions.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
This is a preparation patch for chcpu. If a cpu should be added to
a cpu_set where the cpu doesn't fit into the cpu_set this got silently
ignored.
Since the cpu-list is user space provided it should be checked if cpus
are specified that are completely out of range of the system.
In order to do that add a parameter which specifies if cpulist_parse()
should fail if it parses a cpu-list with "impossible" cpus.
The current callers have been converted so they behave like before.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Print also the physical cpu address for each logical cpu in parsable
output if selected and present via sysfs.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
When running in different dispatching mode the virtual cpus may
have different polarizations.
E.g. in "vertical" mode cpus may have a polarization of "vertical:high"
which means the virtual cpu has dedicated physical cpu assigned.
Print this information in the parsable output.
Note that this breaks the current rule that
a) the parseable output contains only numbers
b) these numbers are equal or increased in each line
Since however this new item must be selected with the "list" argument
this shouldn't be a problem.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
A virtual guest my run in either "horiziontal" or "vertical" mode
which is the mode in which the underlying hypervisor schedules the
guest cpu.
Since this is of interest print this in the readable output.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
The readable output prints also informations like cores per socket etc.
On newer kernel versions on s390 this information is available via
/proc/sysinfo. However it does not contain the layout of the guest but
the layout of the real machine.
Nevertheless this is better than random guessing with completely broken
numbers like we have it now on s390. If the information is not available
we fall back to old mechanism with more or less random numbers.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
The fallback calculation of nthreads did not consider books.
In order to avoid division/multiply by/with zero make sure each number
used is at least "1".
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Completely virtualized architectures like s390 may have multiple
virtual sockets and/or cores where each of them has a different
number of cores and cpus.
So the general assumption within the allocation scheme that e.g.
each socket contains the same number of cores is not necessarily
true. To make sure the arrays are always large enough we simply
allocate enough memory so that each array could hold cpu masks
for all present cpus.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
... to allow define output columns, for example:
$ lscpu --parse=CPU,CORE,NODE,CACHE
# CPU,Core,Node,L1d:L1i:L2
0,0,0,0:0:0
1,1,0,1:1:0
Note that CPU caches are separated by ":" in the new format. The
output for --parse (without the list of the columns) is backwardly
compatible, it means:
$ lscpu --parse
# CPU,Core,Socket,Node,,L1d,L1i,L2
0,0,0,0,,0,0,0
1,1,0,0,,1,1,0
Signed-off-by: Karel Zak <kzak@redhat.com>
This patch adds support for books in cpu topology output. Books are
currently only present on the s390 architecture, however it looks like
others will follow to use the extra scheduling domain of the kernel.
Books are logically between sockets and nodes. In order to not break
any existing tools that might parse the output of lscpu the output
is changed so that books will follow nodes:
CPU,Core,Socket,Node,Book
In addition the readable output is changed from
"CPU socket(s):" to "Socket(s) per book:" or simply "Socket(s):" in the
absence of books.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
s390 has a "bogomips per cpu" string instead of a "bogomips" string in
/proc/sysinfo. So add a second bogomips lookup which detects the s390
variant.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
On Thu, Mar 24, 2011 at 01:45:34PM +0100, Jan Engelhardt wrote:
> On a 24-thread/6-core SPARC T1, lscpu would wrongly output "5
> threads per core".
>
> It seems that the 6c T1 is simply an 8c T1 where 2c are disabled
> (offering a lesser model for a lower price, and all that marketing
> fluff). So the machine description header of the 6c T1 reports 32
> threads, but only goes on to provide 24 elements thereafter, which
> is why Linux will report threads 24-31 as "offline". So far so good.
>
> But lscpu would take the number of all (online and offline) threads
> (32) and divides it by the number of online cores (6), which yields
> an odd 5.33 threads/core.
>
> Simply pick the number of online threads.
Based on Jan's patch.
Reported-by: Jan Engelhardt <jengelh@medozas.de>
Signed-off-by: Karel Zak <kzak@redhat.com>
[kzak@redhat.com: - cleanup lscpu(1) usage text
- use <disk> rather than <device> in partx(8)
usage text]
Signed-off-by: Benno Schulenberg <bensberg@justemail.net>
Signed-off-by: Karel Zak <kzak@redhat.com>
Solaris lacks err, errx, warn and warnx. This also means the err.h header
doesn't exist. Removed err.h include from all files, and included err.h from
c.h instead if it exists, otherwise alternatives are provided.
Signed-off-by: Fabian Groffen <grobian@gentoo.org>
Autoconf contains the right magic to determine the endianness on many
platforms next to Linux. This reverses previous commits to move away
from WORDS_BIGENDIAN:
"use __BYTE_ORDER rather than AC specific WORDS_BIGENDIAN"
This is necessary to compile on non Linux platforms like Darwin and
Solaris.
Signed-off-by: Fabian Groffen <grobian@gentoo.org>
This problem was observed on an x86_64 Mobile AMD Sempron 3700+ where kernel_max
returned "0" as the index of the highest CPU.
As a consequence, several variables in lscpu, which relied on maxcpus >= 1 (in
particular the 'len' value) were set to 0, resulting in the following errors:
host>./lscpu
lscpu: failed to read: /sys/devices/system/cpu/online: No such file or directory
host> cat /sys/devices/system/cpu/kernel_max
0
The fix used by this patch is to interpret kernel_max as an index and maxcpus as
a count >= 1, tested to work.
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: Karel Zak <kzak@redhat.com>
CAI Qian and I agree that GPLv2+ is better for lscpu.c. This license
is more compatible (than v3) with the rest of the util-linux package.
We need to link the code with functions from lib/ -- mix GPLv3 and
GPLv2 is bad idea.
Note that it was only Cai and I who did significant changes to
lscpu.c, all others changes from others developers was trivial (fix
typos, add _(), ...).
Signed-off-by: CAI Qian <caiqian@redhat.com>
Signed-off-by: Karel Zak <kzak@redhat.com>
# echo 0 >/sys/devices/system/cpu/cpu3/online
# echo 0 >/sys/devices/system/cpu/cpu2/online
# grep processor /proc/cpuinfo
processor : 0
processor : 1
# lscpu
lscpu: error: cannot open
/sys/devices/system/cpu/cpu2/cache/index0/shared_cpu_map: No such file or directory
This patch also add a new "On-line CPU(s):" line to the lscpu(1)
output.
Addresses: http://bugzilla.redhat.com/show_bug.cgi?id=623012
Signed-off-by: Karel Zak <kzak@redhat.com>
LC_CTYPE is necessary to print correctly some non English characters,
set LC_ALL for the sake of brevity.
Example:
$ LANG=fr_FR lscpu -p | head -n 1
\# La suite est en format analysable, transmissible ? d'autres
instead of:
\# La suite est en format analysable, transmissible à d'autres
Signed-off-by: Francesco Cosoleto <cosoleto@gmail.com>
Fixes commit c9239f23ac. The author
didn't care for matching constraints when resorting the register
constraints. The eax register (with the cpuid opcode) is now in
operand 1, not zero anymore.
Signed-off-by: Henne Vogelsang <hvogel@opensuse.org>
This patch add "CPU op-mode(s):" field that prints all supported CPU
operation modes. The field is based on CPU flags:
rm (real mode) 16-bit
tm (transparent mode) 32-bit
lm (long mode) 64-bit
Example:
$ lscpu
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
CPU(s): 2
Thread(s) per core: 1
Core(s) per socket: 2
CPU socket(s): 1
NUMA node(s): 1
Vendor ID: GenuineIntel
CPU family: 6
Model: 15
Stepping: 11
CPU MHz: 1600.000
Virtualization: VT-x
L1d cache: 32K
L1i cache: 32K
L2 cache: 4096K
Signed-off-by: Karel Zak <kzak@redhat.com>
If we build lscpu as PIE, we currently get a build failure:
lscpu.c: In function 'main':
lscpu.c:333: error: can't find a register in class 'BREG' while reloading 'asm'
lscpu.c:333: error: 'asm' operand has impossible constraints
make[2]: *** [lscpu.o] Error 1
So we need a little bit of register shuffling to keep gcc happy.
Signed-off-by: Mike Frysinger <vapier@gentoo.org>
This patch adds two new fields:
* "Hypervisor vendor" -- based on CPUID and hypervisor specific
PCI devices. lscpu(1) supports KVM, XEN, Microsoft HV now.
* "Virtualization type"
- "none" = Xen dom0
- "full" = full virtualization (KVM, Xen, ...)
- "para" = Xen paravirtualization
Co-Author: Ky Srinivasan <ksrinivasan@novell.com>
Signed-off-by: Karel Zak <kzak@redhat.com>
This patch added a --sysroot command-line option for testing purpose. It
also sorted cache names, and displayed cache information in a sorted
manner instead of randomly before. In addition, it had some other minor
fixes.
Signed-off-by: Cai Qian <qcai@redhat.com>