14 Jan, 2009
4 commits
-
Signed-off-by: Heiko Carstens
-
Signed-off-by: Heiko Carstens
-
Not a single architecture has wired up sys_pselect7 plus it is the
only system call with seven parameters. Just make it static and
rename it to do_pselect which will do the work for sys_pselect6.Signed-off-by: Heiko Carstens
-
Since we (Analog Devices) updated our Blackfin kernel to 2.6.28, we've
seen occasional 5-second hangs from telnet. telnetd calls select with a
NULL timeout, but with the new kernel, the system call occasionally
returns 0, which causes telnet to call sleep (5). This did not happen
with earlier kernels.The code in sys_pselect7 looks a bit strange, in particular the variable
"to" is initialized to NULL, then changed if a non-null timeout was
passed in, but not used further. It needs to be passed to
core_sys_select instead of &end_time.This bug was introduced by 8ff3e8e85fa6c312051134b3953e397feb639f51
("select: switch select() and poll() over to hrtimers").Signed-off-by: Bernd Schmidt
Reviewed-by: Ulrich Drepper
Tested-by: Robin Getz
Cc: stable@kernel.org
Signed-off-by: Linus Torvalds
07 Jan, 2009
1 commit
-
f_op->poll is the only vfs operation which is not allowed to sleep. It's
because poll and select implementation used task state to synchronize
against wake ups, which doesn't have to be the case anymore as wait/wake
interface can now use custom wake up functions. The non-sleep restriction
can be a bit tricky because ->poll is not called from an atomic context
and the result of accidentally sleeping in ->poll only shows up as
temporary busy looping when the timing is right or rather wrong.This patch converts poll/select to use custom wake up function and use
separate triggered variable to synchronize against wake up events. The
only added overhead is an extra function call during wake up and
negligible.This patch removes the one non-sleep exception from vfs locking rules and
is beneficial to userland filesystem implementations like FUSE, 9p or
peculiar fs like spufs as it's very difficult for those to implement
non-sleeping poll method.While at it, make the following cosmetic changes to make poll.h and
select.c checkpatch friendly.* s/type * symbol/type *symbol/ : three places in poll.h
* remove blank line before EXPORT_SYMBOL() : two places in select.cOleg: spotted missing barrier in poll_schedule_timeout()
Davide: spotted missing write barrier in pollwake()Signed-off-by: Tejun Heo
Cc: Eric Van Hensbergen
Cc: Ron Minnich
Cc: Ingo Molnar
Cc: Christoph Hellwig
Signed-off-by: Miklos Szeredi
Cc: Davide Libenzi
Cc: Brad Boyer
Cc: Al Viro
Cc: Roland McGrath
Cc: Mauro Carvalho Chehab
Signed-off-by: Andrew Morton
Cc: Davide Libenzi
Cc: Oleg Nesterov
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
27 Oct, 2008
1 commit
-
Some userland apps seem to pass in a "0" for the seconds, and several
seconds worth of usecs to select(). The old kernels accepted this just
fine, so the new kernels must too.However, due to the upscaling of the microseconds to nanoseconds we had
some cases where we got math overflow, and depending on the GCC version
(due to inlining decisions) that actually resulted in an -EINVAL return.This patch fixes this by adding the excess microseconds to the seconds
field.Also with thanks to Marcin Slusarz for spotting some implementation bugs
in the diagnostics patches.Reported-by: Carlos R. Mafra
Signed-off-by: Arjan van de Ven
Signed-off-by: Linus Torvalds
08 Sep, 2008
2 commits
-
the slack estimator used unsigned math; however for very short delay it's
possible that by the time you calculate the timeout, it's already passed and
you get a negative time/slack... in an unsigned variable... which then gets
turned into a 100 msec delay rather than zero.This patch fixes this by using a signed typee in the right places.
Signed-off-by: Arjan van de Ven
-
(based on lkml review)
* use rt_task()
* task_nice() has a signSigned-off-by: Arjan van de Ven
06 Sep, 2008
3 commits
-
This patch makes the select() and poll() hrtimers use the new range
feature and settings from the task struct.In addition, this includes the estimate_accuracy() function that Linus
posted to lkml, but changed entirely based on other peoples lkml feedback.Signed-off-by: Arjan van de Ven
-
With lots of help, input and cleanups from Thomas Gleixner
This patch switches select() and poll() over to hrtimers.
The core of the patch is replacing the "s64 timeout" with a
"struct timespec end_time" in all the plumbing.But most of the diffstat comes from using the just introduced helpers:
poll_select_set_timeout
poll_select_copy_remaining
timespec_add_safe
which make manipulating the timespec easier and less error-prone.Signed-off-by: Arjan van de Ven
Signed-off-by: Thomas Gleixner -
This patch adds 2 helpers that will be used for the hrtimer based select/poll:
poll_select_set_timeout() is a helper that takes a timeout (as a second, nanosecond
pair) and turns that into a "struct timespec" that represents the absolute end time.
This is a common operation in the many select() and poll() variants and needs various,
common, sanity checks.poll_select_copy_remaining() is a helper that takes care of copying the remaining
time to userspace, as select(), pselect() and ppoll() do. This function comes in
both a natural and a compat implementation (due to datastructure differences).Signed-off-by: Thomas Gleixner
Signed-off-by: Arjan van de Ven
23 Jun, 2008
1 commit
-
Christian Borntraeger reported that reinstating cond_resched() with
CONFIG_PREEMPT caused a performance regression on lmbench:For example select file 500:
23 microseconds
32 microsecondsand that's really because we totally unnecessarily do the cond_resched()
in the innermost loop of select(), which is just silly.This moves it out from the innermost loop (which only ever loops ove the
bits in a single "unsigned long" anyway), which makes the performance
regression go away.Reported-and-tested-by: Christian Borntraeger
Signed-off-by: Linus Torvalds
02 May, 2008
2 commits
-
Initial splitoff of the low-level stuff; taken to fdtable.h
Signed-off-by: Al Viro
-
... instead of open-coding it
Signed-off-by: Al Viro
30 Apr, 2008
2 commits
-
Change all the #ifdef TIF_RESTORE_SIGMASK conditionals in non-arch code to
#ifdef HAVE_SET_RESTORE_SIGMASK. If arch code defines it first, the generic
set_restore_sigmask() using TIF_RESTORE_SIGMASK is not defined.Signed-off-by: Roland McGrath
Cc: Oleg Nesterov
Cc: Ingo Molnar
Cc: Thomas Gleixner
Cc: Martin Schwidefsky
Cc: Heiko Carstens
Cc: "Luck, Tony"
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
This adds the set_restore_sigmask() inline in and
replaces every set_thread_flag(TIF_RESTORE_SIGMASK) with a call to it. No
change, but abstracts the details of the flag protocol from all the calls.Signed-off-by: Roland McGrath
Cc: Oleg Nesterov
Cc: Ingo Molnar
Cc: Thomas Gleixner
Cc: Martin Schwidefsky
Cc: Heiko Carstens
Cc: "Luck, Tony"
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
22 Apr, 2008
1 commit
-
These are small cleanups all over the tree.
Trivial style and comment changes to
fs/select.c, kernel/signal.c, kernel/stop_machine.c & mm/pdflush.cSigned-off-by: Pavel Machek
Signed-off-by: Jesper Juhl
07 Feb, 2008
1 commit
-
schedule_timeout(jiffies) waits for at least jiffies - 1. Add 1 jiffie to
the timeout_jiffies calculated in sys_poll() to wait at least
timeout_msecs, like poll() manpage says.Signed-off-by: Karsten Wiese
Cc: Ingo Molnar
Cc: Thomas Gleixner
Cc: "H. Peter Anvin"
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
20 Oct, 2007
1 commit
-
fs/select, remove unused macros
this is due to preparation for global BIT macro
Signed-off-by: Jiri Slaby
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
17 Oct, 2007
3 commits
-
Lomesh reported poll returning EINTR during suspend/resume cycle. This is
caused by the STOP/CONT cycle that the freezer uses, generating a pending
signal for what in effect is an ignored signal. In general poll is a
little eager in returning EINTR, when it could try not bother userspace and
simply restart the syscall. Both select and ppoll do use ERESTARTNOHAND to
restart the syscall. Oleg points out that simply using ERESTARTNOHAND will
cause poll to restart with original timeout value. which could ultimately
lead to process never returning to userspace. Instead use
ERESTART_RESTARTBLOCK, and restart poll with updated timeout value.
Inspired by Manfred's use ERESTARTNOHAND in poll patch.[bunk@kernel.org: do_restart_poll() can become static]
Cc: Manfred Spraul
Cc: Oleg Nesterov
Cc: Roland McGrath
Cc: "Agarwal, Lomesh"
Signed-off-by: Chris Wright
Signed-off-by: Adrian Bunk
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
do_poll() checks signal_pending() but returns 0 when interrupted. This means
the caller has to check signal_pending() again.Change it to return -EINTR when signal_pending() and count == 0.
Signed-off-by: Oleg Nesterov
Cc: Andi Kleen
Cc: Davide Libenzi
Cc: Vadim Lobanov
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Cleanup. Lessens both the source and compiled code (100 bytes) and imho makes
the code much more understandable.With this patch "struct poll_list *head" always points to on-stack stack_pps,
so we can remove all "is it on-stack" and "was it initialized" checks.Also, move poll_initwait/poll_freewait and -EINTR detection closer to the
do_poll()'s callsite.[akpm@linux-foundation.org: fix warning (size_t != uint)]
Signed-off-by: Oleg Nesterov
Looks-good-to: Andi Kleen
Cc: Davide Libenzi
Cc: Vadim Lobanov
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
12 Sep, 2007
1 commit
-
Taneli Vähäkangas reported that commit
786d7e1612f0b0adb6046f19b906609e4fe8b1ba aka "Fix rmmod/read/write races
in /proc entries" broke SBCL + SLIME combo.The old code in do_select() used DEFAULT_POLLMASK, if couldn't find
->poll handler. The new code makes ->poll always there and returns 0 by
default, which is not correct. Return DEFAULT_POLLMASK instead.Steps to reproduce:
install emacs, SBCL, SLIME
emacs
M-x slime in *inferior-lisp* buffer
[watch it doing "Connecting to Swank on port X.."]Please, apply before 2.6.23.
P.S.: why SBCL can't just read(2) /proc/cpuinfo is a mystery.
Signed-off-by: Alexey Dobriyan
Cc: T Taneli Vahakangas
Cc: Oleg Nesterov
Cc: "Eric W. Biederman"
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
09 May, 2007
3 commits
-
Signed-off-by: WANG Cong
Signed-off-by: Adrian Bunk -
ROUND_UP macro cleanup use,ALIGN or DIV_ROUND_UP where ever appropriate.
Signed-off-by: Milind Arun Choudhary
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Remove includes of where it is not used/needed.
Suggested by Al Viro.Builds cleanly on x86_64, i386, alpha, ia64, powerpc, sparc,
sparc64, and arm (all 59 defconfigs).Signed-off-by: Randy Dunlap
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
11 Dec, 2006
1 commit
-
Currently, each fdtable supports three dynamically-sized arrays of data: the
fdarray and two fdsets. The code allows the number of fds supported by the
fdarray (fdtable->max_fds) to differ from the number of fds supported by each
of the fdsets (fdtable->max_fdset).In practice, it is wasteful for these two sizes to differ: whenever we hit a
limit on the smaller-capacity structure, we will reallocate the entire fdtable
and all the dynamic arrays within it, so any delta in the memory used by the
larger-capacity structure will never be touched at all.Rather than hogging this excess, we shouldn't even allocate it in the first
place, and keep the capacities of the fdarray and the fdsets equal. This
patch removes fdtable->max_fdset. As an added bonus, most of the supporting
code becomes simpler.Signed-off-by: Vadim Lobanov
Cc: Christoph Hellwig
Cc: Al Viro
Cc: Dipankar Sarma
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
30 Sep, 2006
1 commit
-
POSIX states that poll() shall fail with EINVAL if nfds > OPEN_MAX. In
this context, POSIX is referring to sysconf(OPEN_MAX), which is the value
of current->signal->rlim[RLIMIT_NOFILE].rlim_cur in the linux kernel, not
the compile-time constant which happens to also be named OPEN_MAX. In the
current code, an application may poll up to max_fdset file descriptors,
even if this exceeds RLIMIT_NOFILE. The current code also breaks
applications which poll more than max_fdset descriptors, which worked circa
2.4.18 when the check was against NR_OPEN, which is 1024*1024. This patch
enforces the limit precisely as POSIX defines, even if RLIMIT_NOFILE has
been changed at run time with ulimit -n.To elaborate on the rationale for this, there are three cases:
1) RLIMIT_NOFILE is at the default value of 1024
In this (default) case, the patch changes nothing. Calls with nfds > 1024
fail with EINVAL both before and after the patch, and calls with nfds
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
26 Jun, 2006
1 commit
-
If you do a poll() call with timeout -1, the wait will be a big number
(depending on HZ) instead of infinite wait, since -1 is passed to the
msecs_to_jiffies function.Signed-off-by: Frode Isaksen
Acked-by: Nishanth Aravamudan
Cc: David Woodhouse
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
23 Jun, 2006
1 commit
-
The "count" and "pt" variables are declared and modified by do_poll(), as
well as accessed and written indirectly in the do_pollfd() subroutine.This patch pulls all handling of these variables into the do_poll()
function, thereby eliminating the odd use of indirection in do_pollfd().
This is done by pulling the "struct pollfd" traversal loop from do_pollfd()
into its only caller do_poll(). As an added bonus, the patch saves a few
clock cycles, and also adds comments to make the code easier to follow.Signed-off-by: Vadim Lobanov
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
11 Apr, 2006
2 commits
-
If SELECT_STACK_ALLOC is not a multiple of sizeof(long) then stack_fds[]
would be shorter than SELECT_STACK_ALLOC bytes and could overflow later in
the function. Fixed by simply rearranging the test later to work on
sizeof(stack_fds) Currently SELECT_STACK_ALLOC is 256 so this doesn't
happen, but it's nasty to have things like this hidden in the code. What
if later someone decides to change SELECT_STACK_ALLOC to 300?Signed-off-by: Mitchell Blank Jr
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
fs/select.c: In function `core_sys_select':
fs/select.c:339: warning: assignment from incompatible pointer type
fs/select.c:376: warning: comparison of distinct pointer types lacks a castBy using a void* we can remove lots of casts rather than adding more.
Cc: Jes Sorensen
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
01 Apr, 2006
1 commit
-
Commit 70674f95c0a2ea694d5c39f4e514f538a09be36f:
[PATCH] Optimize select/poll by putting small data sets on the stack
resulted in the poll stack being 4-byte aligned on 64-bit architectures,
causing misaligned accesses to elements in the array.This patch fixes it by declaring the stack in terms of 'long' instead
of 'char'.Force alignment of poll and select stacks to long to avoid unaligned
access on 64 bit architectures.Signed-off-by: Jes Sorensen
Signed-off-by: Linus Torvalds
29 Mar, 2006
3 commits
-
Mark the f_ops members of inodes as const, as well as fix the
ripple-through this causes by places that copy this f_ops and then "do
stuff" with it.Signed-off-by: Arjan van de Ven
Signed-off-by: Alexey Dobriyan
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Cc: Andi Kleen
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Optimize select and poll by a using stack space for small fd sets
This brings back an old optimization from Linux 2.0. Using the stack is
faster than kmalloc. On a Intel P4 system it speeds up a select of a
single pty fd by about 13% (~4000 cycles -> ~3500)It also saves memory because a daemon hanging in select or poll will
usually save one or two less pages. This can add up - e.g. if you have 10
daemons blocking in poll/select you save 40KB of memory.I did a patch for this long ago, but it was never applied. This version is
a reimplementation of the old patch that tries to be less intrusive. I
only did the minimal changes needed for the stack allocation.The cut off point before external memory is allocated is currently at
832bytes. The system calls always allocate this much memory on the stack.These 832 bytes are divided into 256 bytes frontend data (for the select
bitmaps of the pollfds) and the rest of the space for the wait queues used
by the low level drivers. There are some extreme cases where this won't
work out for select and it falls back to allocating memory too early -
especially with very sparse large select bitmaps - but the majority of
processes who only have a small number of file descriptors should be ok.
[TBD: 832/256 might not be the best split for select or poll]I suspect more optimizations might be possible, but they would be more
complicated. One way would be to cache the select/poll context over
multiple system calls because typically the input values should be similar.
Problem is when to flush the file descriptors out though.Signed-off-by: Andi Kleen
Cc: Eric Dumazet
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
18 Feb, 2006
1 commit
-
I got all of these backwards. We want to return
min(input timeout, new timeout)
to userspace to prevent increasing the time-remaining value.
Thanks to Ernst Herzberg for reporting and diagnosing.
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
12 Feb, 2006
1 commit
-
With David Woodhouse
select() presently has a habit of increasing the value of the user's
`timeout' argument on return.We were writing back a timeout larger than the original. We _deliberately_
round up, since we know we must wait at _least_ as long as the caller asks
us to.The patch adds a couple of helper functions for magnitude comparison of
timespecs and of timevals, and uses them to prevent the various poll and
select functions from returning a timeout which is larger than the one which
was passed in.The patch also fixes a bug in compat_sys_pselect7(): it was adding the new
timeout value to the old one and was returning that. It should just return
the new timeout value.(We have various handy timespec/timeval-to-from-nsec conversion functions in
time.h. But this code open-codes it all).Cc: "David S. Miller"
Cc: Andi Kleen
Cc: Ulrich Drepper
Cc: Thomas Gleixner
Cc: george anzinger
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
08 Feb, 2006
1 commit
-
Signed-off-by: Al Viro
19 Jan, 2006
1 commit
-
The following implementation of ppoll() and pselect() system calls
depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the
thread_info.These system calls have to change the signal mask during their
operation, and signal handlers must be invoked using the new, temporary
signal mask. The old signal mask must be restored either upon successful
exit from the system call, or upon returning from the invoked signal
handler if the system call is interrupted. We can't simply restore the
original signal mask and return to userspace, since the restored signal
mask may actually block the signal which interrupted the system call.The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit
path to trap into do_signal() just as TIF_SIGPENDING does, and by
causing do_signal() to use the saved signal mask instead of the current
signal mask when setting up the stack frame for the signal handler -- or
by causing do_signal() to simply restore the saved signal mask in the
case where there is no handler to be invoked.The first patch implements the sys_pselect() and sys_ppoll() system
calls, which are present only if TIF_RESTORE_SIGMASK is defined. That
#ifdef should go away in time when all architectures have implemented
it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC
kernel (in the -mm tree), and the third patch then removes the
arch-specific implementations of sys_rt_sigsuspend() and replaces them
with generic versions using the same trick.The fourth and fifth patches, provided by David Howells, implement
TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch
adds the syscalls to the i386 syscall table.This patch:
Add the pselect() and ppoll() system calls, providing core routines usable by
the original select() and poll() system calls and also the new calls (with
their semantics w.r.t timeouts).Signed-off-by: David Woodhouse
Cc: Michael Kerrisk
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
