02 Oct, 2009
1 commit
-
When using %*s, sscanf should honor conversion specifiers immediately
following the %*s. For example, the following code should find the
position of the end of the string "hello".int end;
char buf[] = "hello world";
sscanf(buf, "%*s%n", &end);
printf("%d\n", end);Ideally, sscanf would advance the fmt and str pointers the same as it
would without the *, but the code for that is rather complicated and is
not included in the patch.Signed-off-by: Andy Spencer
Acked-by: WANG Cong
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
25 Sep, 2009
1 commit
-
Conflicts:
drivers/staging/Kconfig
drivers/staging/Makefile
drivers/staging/cpc-usb/TODO
drivers/staging/cpc-usb/cpc-usb_drv.c
drivers/staging/cpc-usb/cpc.h
drivers/staging/cpc-usb/cpc_int.h
drivers/staging/cpc-usb/cpcusb.h
23 Sep, 2009
1 commit
-
Jens Rosenboom noticed that a possibly unaligned const char*
is cast to a const struct in6_addr *.Avoid this at the cost of a struct in6_addr copy on the stack.
Signed-off-by: Joe Perches
Signed-off-by: David S. Miller
22 Sep, 2009
1 commit
-
Signed-off-by: Marcin Slusarz
Reviewed-by: Frederic Weisbecker
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
18 Sep, 2009
2 commits
-
Remove the duplicate comment of bstr_printf that is the same as the
vsnprintf.Add the 's' option to the comment for the pointer function. This is
more of an internal function so the little duplication of the comment
here is OK.Reported-by: Zhaolei
Cc: Linus Torvalds
Signed-off-by: Steven Rostedt -
On PowerPC64 function pointers do not point directly at the functions,
but instead point to pointers to the functions. The output of %pF expects
to point to a pointer to the function, whereas %pS will show the function
itself.mcount returns the direct pointer to the function and not the pointer to
the pointer. Thus %pS must be used to show this. The function tracer
requires printing of the functions without offsets and uses the %pf
instead.%pF produces run_local_timers+0x4/0x1f
%pf produces just run_local_timersFor PowerPC64, we need to use the direct pointer, and we only have
%pS which will produce .run_local_timers+0x4/0x1fThis patch creates a %ps that matches the %pf as %pS matches %pF.
Cc: Linus Torvalds
Cc: Zhao Lei
Acked-by: Benjamin Herrenschmidt
Signed-off-by: Steven Rostedt
29 Aug, 2009
1 commit
-
Signed-off-by: Joe Perches
Tested-by: Jens Rosenboom
Signed-off-by: David S. Miller
30 Apr, 2009
1 commit
-
A printf format specifier which would allow us to print a pure
function name has been suggested by Andrew Morton a couple of
months ago.The current %pF is very convenient to print a function symbol,
but often we only want to print the name of the function, without
its asm offset.That's what %pf does in this patch. The lowecase f has been chosen
for its intuitive meaning of a 'weak kind of %pF'.The support for this new format would be welcome by the tracing code
where the need to print pure function names is often needed. This is
also true for other parts of the kernel:$ git-grep -E "kallsyms_lookup\(.+?\)"
arch/blackfin/kernel/traps.c: symname = kallsyms_lookup(address, &symsize, &offset, &modname, namebuf);
arch/powerpc/xmon/xmon.c: name = kallsyms_lookup(pc, &size, &offset, NULL, tmpstr);
arch/sh/kernel/cpu/sh5/unwind.c: sym = kallsyms_lookup(pc, NULL, &offset, NULL, namebuf);
arch/x86/kernel/ftrace.c: kallsyms_lookup((unsigned long) syscall, NULL, NULL, NULL, str);
kernel/kprobes.c: sym = kallsyms_lookup((unsigned long)p->addr, NULL,
kernel/lockdep.c: return kallsyms_lookup((unsigned long)key, NULL, NULL, NULL, str);
kernel/trace/ftrace.c: kallsyms_lookup(rec->ip, NULL, NULL, NULL, str);
kernel/trace/ftrace.c: kallsyms_lookup(rec->ip, NULL, NULL, NULL, str);
kernel/trace/ftrace.c: kallsyms_lookup((unsigned long)rec->ops->func, NULL, NULL, NULL, str);
kernel/trace/ftrace.c: kallsyms_lookup(rec->ip, NULL, NULL, NULL, str);
kernel/trace/ftrace.c: kallsyms_lookup(rec->ip, NULL, NULL, NULL, str);
kernel/trace/ftrace.c: kallsyms_lookup(rec->ip, NULL, NULL, &modname, str);
kernel/trace/ftrace.c: kallsyms_lookup(*ptr, NULL, NULL, NULL, str);
kernel/trace/trace_functions.c: kallsyms_lookup(ip, NULL, NULL, NULL, str);
kernel/trace/trace_output.c: kallsyms_lookup(address, NULL, NULL, NULL, str);Changes in v2:
- Add the explanation of the %pf role for vsnprintf() and bstr_printf()
- Change the comments by dropping the "asm offset" notion and only
define the %pf against the actual function offset notion.Signed-off-by: Frederic Weisbecker
Acked-by: Mike Frysinger
Cc: Linus Torvalds
Cc: Zhaolei
Cc: Tom Zanussi
Cc: Li Zefan
Cc: Andrew Morton
Cc: Steven Rostedt
LKML-Reference:
Signed-off-by: Ingo Molnar
08 Apr, 2009
2 commits
-
Impact: new feature, extend vsprintf format strings
hh is used as length modifier for signed char or unsigned char.
It is supported by glibc, we add kernel support now.Signed-off-by: Zhao Lei
Acked-by: Lai Jiangshan
Acked-by: Frederic Weisbecker
Cc: torvalds@linux-foundation.org
Cc: Steven Rostedt
LKML-Reference:
Signed-off-by: Ingo Molnar -
printk("%Q");
Output before patch: %QQ
Output after patch: %QSigned-off-by: Zhao Lei
Acked-by: Lai Jiangshan
Acked-by: Frederic Weisbecker
Cc: torvalds@linux-foundation.org
Cc: Steven Rostedt
LKML-Reference:
Signed-off-by: Ingo Molnar
14 Mar, 2009
2 commits
-
Impact: cleanup
Rename FORMAT_TYPE_WITDH
to => FORMAT_TYPE_WIDTHCc: Frederic Weisbecker
Cc: Jeremy Fitzhardinge
Signed-off-by: Ingo Molnar -
Jeremy Fitzhardinge reported:
> Change fef20d9c1380f04ba9492d6463148db07b413708, "vsprintf:
> unify the format decoding layer for its 3 users", causes a
> regression in xenbus which results in no devices getting
> attached to a new domain.%.*s is broken - fix it.
Reported-by: Jeremy Fitzhardinge
Cc: Frederic Weisbecker
Cc: Linus Torvalds
Signed-off-by: Ingo Molnar
10 Mar, 2009
1 commit
-
Sitsofe Wheeler found and bisected that while unifying the
vsprintf format decoding in:fef20d9: vsprintf: unify the format decoding layer for its 3 users
The sign flag has been dropped out in favour of
precise types (ie: LONG/ULONG).But the format helper number() still needs this flag to keep track of
the signedness unless it will consider all numbers as unsigned.Also add an explicit cast to int (for %d) while parsing with va_arg()
to ensure the highest bit is well extended on the 64 bits number that
hosts the value in case of negative values.Reported-Bisected-Tested-by: Sitsofe Wheeler
Signed-off-by: Frederic Weisbecker
Cc: Lai Jiangshan
Cc: Steven Rostedt
Cc: Linus Torvalds
LKML-Reference:
Signed-off-by: Ingo Molnar
07 Mar, 2009
2 commits
-
An new optimization is making its way to ftrace. Its purpose is to
make trace_printk() consuming less memory and be faster.Written by Lai Jiangshan, the approach is to delay the formatting
job from tracing time to output time.Currently, a call to trace_printk() will format the whole string and
insert it into the ring buffer. Then you can read it on /debug/tracing/trace
file.The new implementation stores the address of the format string and
the binary parameters into the ring buffer, making the packet more compact
and faster to insert.
Later, when the user exports the traces, the format string is retrieved
with the binary parameters and the formatting job is eventually done.The new implementation rewrites a lot of format decoding bits from
vsnprintf() function, making now 3 differents functions to maintain
in their duplicated parts of printf format decoding bits.Suggested by Ingo Molnar, this patch tries to factorize the most
possible common bits from these functions.
The real common part between them is the format decoding. Although
they do somewhat similar jobs, their way to export or import the parameters
is very different. Thus, only the decoding layer is extracted, unless you see
other parts that could be worth factorized.Changes in V2:
- Address a suggestion from Linus to group the format_decode() parameters inside
a structure.Changes in v3:
- Address other cleanups suggested by Ingo and Linus such as passing the
printf_spec struct to the format helpers: pointer()/number()/string()
Note that this struct is passed by copy and not by address. This is to
avoid side effects because these functions often change these values and the
changes shoudn't be persistant when a callee helper returns.
It would be too risky.- Various cleanups (code alignement, switch/case instead of if/else fountains).
- Fix a bug that printed the first format specifier following a %p
Changes in v4:
- drop unapropriate const qualifier loss while casting fmt to a char *
(thanks to Vegard Nossum for having pointed this out).Signed-off-by: Frederic Weisbecker
Cc: Linus Torvalds
Acked-by: Steven Rostedt
LKML-Reference:
Signed-off-by: Ingo Molnar -
Impact: add new APIs for binary trace printk infrastructure
vbin_printf(): write args to binary buffer, string is copied
when "%s" is occurred.bstr_printf(): read from binary buffer for args and format a string
[fweisbec@gmail.com: rebase]
Signed-off-by: Lai Jiangshan
Signed-off-by: Frederic Weisbecker
Cc: Linus Torvalds
LKML-Reference:
Signed-off-by: Ingo Molnar
07 Jan, 2009
1 commit
-
It decodes "\n" as 0, which is bad, because stray echo into backlight
will turn your backlight off, etc...Signed-off-by: Pavel Machek
Cc: Yi Yang
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
04 Jan, 2009
1 commit
-
Before, when we only ever printed out the pointer value itself, a NULL
pointer would never cause issues and might as well be printed out as
just its numeric value.However, with the extended %p formats, especially %pR, we might validly
want to print out resources for debugging. And sometimes they don't
even exist, and the resource pointer is just NULL. Print it out as
such, rather than oopsing.This is a more generic version of a patch done by Trent Piepho (catching
all %p cases rather than just %pR, and using "(null)" instead of
"[NULL]" to match glibc).Requested-by: Trent Piepho
Acked-by: Harvey Harrison
Signed-off-by: Linus Torvalds
25 Nov, 2008
1 commit
-
Add %pm to omit the colons when printing a mac address.
Signed-off-by: Harvey Harrison
Signed-off-by: David S. Miller
04 Nov, 2008
1 commit
-
put_dec_trunc prints the digits in reverse order and is reversed
inside number(). Continue using put_dec_trunc, but reverse each quad
in ip4_addr_string.[Noticed by Julius Volz]
Signed-off-by: Harvey Harrison
Signed-off-by: David S. Miller
30 Oct, 2008
2 commits
-
Signed-off-by: Harvey Harrison
Signed-off-by: David S. Miller -
For use in printing IPv4, or IPv6 addresses in the usual way:
%i4 and %I4 are currently equivalent and print the address in
dot-separated decimal x.x.x.x%I6 prints 16-bit network order hex with colon separators:
xxxx:xxxx:xxxx:xxxx:xxxx:xxxx:xxxx:xxxx%i6 omits the colons.
Signed-off-by: Harvey Harrison
Signed-off-by: David S. Miller
29 Oct, 2008
1 commit
-
Takes a pointer to a IPv6 address and formats it in the usual
colon-separated hex format:
xxxx:xxxx:xxxx:xxxx:xxxx:xxxx:xxxx:xxxxEach 16 bit word is printed in network-endian byteorder.
%#p6 is also supported and will omit the colons.
%p6 is a replacement for NIP6_FMT and NIP6()
%#p6 is a replacement for NIP6_SEQFMT and NIP6()Note that NIP6() took a struct in6_addr whereas this takes a pointer
to a struct in6_addr.Signed-off-by: Harvey Harrison
Signed-off-by: David S. Miller
28 Oct, 2008
1 commit
-
Add format specifiers for printing out six colon-separated bytes:
MAC addresses (%pM):
xx:xx:xx:xx:xx:xx%#pM is also supported and omits the colon separators.
Signed-off-by: Harvey Harrison
Signed-off-by: David S. Miller
21 Oct, 2008
1 commit
-
Add a %pR option to the kernel vsnprintf that prints the range of
addresses inside a struct resource passed by pointer.Signed-off-by: Linus Torvalds
Signed-off-by: Benjamin Herrenschmidt
Signed-off-by: Linus Torvalds
17 Oct, 2008
4 commits
-
Open-code them rather than using defining macros. The function bodies are now
next to their kerneldoc comments as a bonus.Add casts to the signed cases as they call into the unsigned versions.
Avoids the sparse warnings:
lib/vsprintf.c:249:1: warning: incorrect type in argument 3 (different signedness)
lib/vsprintf.c:249:1: expected unsigned long *res
lib/vsprintf.c:249:1: got long *res
lib/vsprintf.c:249:1: warning: incorrect type in argument 3 (different signedness)
lib/vsprintf.c:249:1: expected unsigned long *res
lib/vsprintf.c:249:1: got long *res
lib/vsprintf.c:251:1: warning: incorrect type in argument 3 (different signedness)
lib/vsprintf.c:251:1: expected unsigned long long *res
lib/vsprintf.c:251:1: got long long *res
lib/vsprintf.c:251:1: warning: incorrect type in argument 3 (different signedness)
lib/vsprintf.c:251:1: expected unsigned long long *res
lib/vsprintf.c:251:1: got long long *resSigned-off-by: Harvey Harrison
Signed-off-by: Linus Torvalds -
Remove extra lines before the EXPORT_SYMBOL()s
Signed-off-by: Harvey Harrison
Signed-off-by: Linus Torvalds -
The default base is 10 unless there is a leading zero, in which
case the base will be guessed as 8.The base will only be guesed as 16 when the string starts with '0x'
the third character is a valid hex digit.Signed-off-by: Harvey Harrison
Signed-off-by: Linus Torvalds -
Add documentation in kerneldoc for new printk format extensions
This patch documents the new %pS/%pF options in printk in kernel doc.
Hope I didn't miss any other extension.
Signed-off-by: Andi Kleen
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
10 Sep, 2008
1 commit
-
It was introduced by "vsprintf: add support for '%pS' and '%pF' pointer
formats" in commit 0fe1ef24f7bd0020f29ffe287dfdb9ead33ca0b2. However,
the current way its coded doesn't work on parisc64. For two reasons: 1)
parisc isn't in the #ifdef and 2) parisc has a different format for
function descriptorsMake dereference_function_descriptor() more accommodating by allowing
architecture overrides. I put the three overrides (for parisc64, ppc64
and ia64) in arch/kernel/module.c because that's where the kernel
internal linker which knows how to deal with function descriptors sits.Signed-off-by: James Bottomley
Acked-by: Benjamin Herrenschmidt
Acked-by: Tony Luck
Acked-by: Kyle McMartin
Signed-off-by: Linus Torvalds
13 Aug, 2008
1 commit
-
Fix wrong conversion function used by strict_strtou*
Signed-off-by: Yi Yang
Reported-by: Swen Schillig
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
07 Jul, 2008
4 commits
-
They print out a pointer in symbolic format, if possible (ie using
symbolic KALLSYMS information). The '%pS' format is for regular direct
pointers (which can point to data or code and that you find on the stack
during backtraces etc), while '%pF' is for C function pointer types.On most architectures, the two mean exactly the same thing, but some
architectures use an indirect pointer for C function pointers, where the
function pointer points to a function descriptor (which in turn contains
the actual pointer to the code). The '%pF' code automatically does the
appropriate function descriptor dereference on such architectures.Signed-off-by: Linus Torvalds
-
This expands the kernel '%p' handling with an arbitrary alphanumberic
specifier extension string immediately following the '%p'. Right now
it's just being ignored, but the next commit will start adding some
specific pointer type extensions.NOTE! The reason the extension is appended to the '%p' is to allow
minimal gcc type checking: gcc will still see the '%p' and will check
that the argument passed in is indeed a pointer, and yet will not
complain about the extended information that gcc doesn't understand
about (on the other hand, it also won't actually check that the pointer
type and the extension are compatible).Alphanumeric characters were chosen because there is no sane existing
use for a string format with a hex pointer representation immediately
followed by alphanumerics (which is what such a format string would have
traditionally resulted in).Signed-off-by: Linus Torvalds
-
The actual code is the same, just split out into a helper function.
This makes it easier to read, and allows for simple future extension
of %p handling.Signed-off-by: Linus Torvalds
-
The actual code is the same, just split out into a helper function.
This makes it easier to read, and allows for future sharing of the
string code.Signed-off-by: Linus Torvalds
24 Feb, 2008
1 commit
-
lib/vsprintf.c: Fix bug omitting minus sign of numbers (module_param)
Signed-off-by: Hoang-Nam Nguyen
Cc: Yi Yang
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
10 Feb, 2008
1 commit
-
In arch/x86/boot/printf.c gets rid of unused tail of digits: const char
*digits = "0123456789abcdefghijklmnopqrstuvwxyz"; (we are using 0-9a-f
only)Uses smaller/faster lowercasing (by ORing with 0x20)
if we know that we work on numbers/digits. Makes
strtoul smaller, and also we are getting rid ofstatic const char small_digits[] = "0123456789abcdefx";
static const char large_digits[] = "0123456789ABCDEFX";since this works equally well:
static const char digits[16] = "0123456789ABCDEF";
Size savings:
$ size vmlinux.org vmlinux
text data bss dec hex filename
877320 112252 90112 1079684 107984 vmlinux.org
877048 112252 90112 1079412 107874 vmlinuxIt may be also a tiny bit faster because code has less
branches now, but I doubt it is measurable.[ hugh@veritas.com: uppercase pointers fix ]
Signed-off-by: Denys Vlasenko
Cc: Andi Kleen
Signed-off-by: Andrew Morton
Signed-off-by: Ingo Molnar
Signed-off-by: Thomas Gleixner
09 Feb, 2008
1 commit
-
Currently, for every sysfs node, the callers will be responsible for
implementing store operation, so many many callers are doing duplicate
things to validate input, they have the same mistakes because they are
calling simple_strtol/ul/ll/uul, especially for module params, they are
just numeric, but you can echo such values as 0x1234xxx, 07777888 and
1234aaa, for these cases, module params store operation just ignores
succesive invalid char and converts prefix part to a numeric although input
is acctually invalid.This patch tries to fix the aforementioned issues and implements
strict_strtox serial functions, kernel/params.c uses them to strictly
validate input, so module params will reject such values as 0x1234xxxx and
returns an error:write error: Invalid argument
Any modules which export numeric sysfs node can use strict_strtox instead of
simple_strtox to reject any invalid input.Here are some test results:
Before applying this patch:
[root@yangyi-dev /]# cat /sys/module/e1000/parameters/copybreak
4096
[root@yangyi-dev /]# echo 0x1000 > /sys/module/e1000/parameters/copybreak
[root@yangyi-dev /]# cat /sys/module/e1000/parameters/copybreak
4096
[root@yangyi-dev /]# echo 0x1000g > /sys/module/e1000/parameters/copybreak
[root@yangyi-dev /]# cat /sys/module/e1000/parameters/copybreak
4096
[root@yangyi-dev /]# echo 0x1000gggggggg > /sys/module/e1000/parameters/copybreak
[root@yangyi-dev /]# cat /sys/module/e1000/parameters/copybreak
4096
[root@yangyi-dev /]# echo 010000 > /sys/module/e1000/parameters/copybreak
[root@yangyi-dev /]# cat /sys/module/e1000/parameters/copybreak
4096
[root@yangyi-dev /]# echo 0100008 > /sys/module/e1000/parameters/copybreak
[root@yangyi-dev /]# cat /sys/module/e1000/parameters/copybreak
4096
[root@yangyi-dev /]# echo 010000aaaaa > /sys/module/e1000/parameters/copybreak
[root@yangyi-dev /]# cat /sys/module/e1000/parameters/copybreak
4096
[root@yangyi-dev /]#After applying this patch:
[root@yangyi-dev /]# cat /sys/module/e1000/parameters/copybreak
4096
[root@yangyi-dev /]# echo 0x1000 > /sys/module/e1000/parameters/copybreak
[root@yangyi-dev /]# cat /sys/module/e1000/parameters/copybreak
4096
[root@yangyi-dev /]# echo 0x1000g > /sys/module/e1000/parameters/copybreak
-bash: echo: write error: Invalid argument
[root@yangyi-dev /]# cat /sys/module/e1000/parameters/copybreak
4096
[root@yangyi-dev /]# echo 0x1000gggggggg > /sys/module/e1000/parameters/copybreak
-bash: echo: write error: Invalid argument
[root@yangyi-dev /]# echo 010000 > /sys/module/e1000/parameters/copybreak
[root@yangyi-dev /]# echo 0100008 > /sys/module/e1000/parameters/copybreak
-bash: echo: write error: Invalid argument
[root@yangyi-dev /]# echo 010000aaaaa > /sys/module/e1000/parameters/copybreak
-bash: echo: write error: Invalid argument
[root@yangyi-dev /]# cat /sys/module/e1000/parameters/copybreak
4096
[root@yangyi-dev /]# echo -n 4096 > /sys/module/e1000/parameters/copybreak
[root@yangyi-dev /]# cat /sys/module/e1000/parameters/copybreak
4096
[root@yangyi-dev /]#[akpm@linux-foundation.org: fix compiler warnings]
[akpm@linux-foundation.org: fix off-by-one found by tiwai@suse.de]
Signed-off-by: Yi Yang
Cc: Greg KH
Cc: "Randy.Dunlap"
Cc: Takashi Iwai
Cc: Hugh Dickins
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
01 Aug, 2007
1 commit
-
kasprintf pulls in kmalloc which proved to be fatal for at least
bootimage target on alpha.
Move it to a separate file so only users of kasprintf are exposed
to the dependency on kmalloc.Signed-off-by: Sam Ravnborg
Cc: Jeremy Fitzhardinge
Cc: Meelis Roos
Cc: Richard Henderson
Cc: Ivan Kokshaysky
Cc: Jay Estabrook
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
17 Jul, 2007
2 commits
-
Optimize integer-to-string conversion in vsprintf.c for base 10. This is
by far the most used conversion, and in some use cases it impacts
performance. For example, top reads /proc/$PID/stat for every process, and
with 4000 processes decimal conversion alone takes noticeable time.Using code from
http://www.cs.uiowa.edu/~jones/bcd/decimal.html
(with permission from the author, Douglas W. Jones)binary-to-decimal-string conversion is done in groups of five digits at
once, using only additions/subtractions/shifts (with -O2; -Os throws in
some multiply instructions).On i386 arch gcc 4.1.2 -O2 generates ~500 bytes of code.
This patch is run tested. Userspace benchmark/test is also attached.
I tested it on PIII and AMD64 and new code is generally ~2.5 times
faster. On AMD64:# ./vsprintf_verify-O2
Original decimal conv: .......... 151 ns per iteration
Patched decimal conv: .......... 62 ns per iteration
Testing correctness
12895992590592 ok... [Ctrl-C]
# ./vsprintf_verify-O2
Original decimal conv: .......... 151 ns per iteration
Patched decimal conv: .......... 62 ns per iteration
Testing correctness
26025406464 ok... [Ctrl-C]More realistic test: top from busybox project was modified to
report how many us it took to scan /proc (this does not account
any processing done after that, like sorting process list),
and then I test it with 4000 processes:#!/bin/sh
i=4000
while test $i != 0; do
sleep 30 &
let i--
done
busybox top -b -n3 >/dev/nullon unpatched kernel:
top: 4120 processes took 102864 microseconds to scan
top: 4120 processes took 91757 microseconds to scan
top: 4120 processes took 92517 microseconds to scan
top: 4120 processes took 92581 microseconds to scanon patched kernel:
top: 4120 processes took 75460 microseconds to scan
top: 4120 processes took 66451 microseconds to scan
top: 4120 processes took 67267 microseconds to scan
top: 4120 processes took 67618 microseconds to scanThe speedup comes from much faster generation of /proc/PID/stat
by sprintf() calls inside the kernel.Signed-off-by: Douglas W Jones
Signed-off-by: Denys Vlasenko
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
* There is no point in having full "0...9a...z" constant vector,
if we use only "0...9a...f" (and "x" for "0x").* Post-decrement usually needs a few more instructions, so use
pre decrement instead where makes sense:
- while (i < precision--) {
+ while (i base 8 or 16), we can avoid using division
in a loop and use mask/shift, obtaining much faster conversion.
(More complex optimization for base 10 case is in the second patch).Overall, size vsprintf.o shows ~80 bytes smaller text section
with this patch applied.Signed-off-by: Douglas W Jones
Signed-off-by: Denys Vlasenko
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds