LDP
/
man-pages
mirror of https://github.com/mkerrisk/man-pages
0
1
Fork 0
Code Releases Activity
22,909 Commits 1 Branch 197 Tags 93 MiB
Commit Graph

402 Commits

Author SHA1 Message Date
Michael Kerrisk 627b50ce7c futex.2: Elaborate on why "requeue" operations can be preferable to FUTEX_WAKE 
Cowritten-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:48 +01:00
Michael Kerrisk 8297383e9e futex.2: Clean-ups and FIXME removeal after feedback from Thomas Gleixner 
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:48 +01:00
Michael Kerrisk 27dd3a6e79 futex.2: Remove warning that FUTEX_REQUEUE is broken 
Darren Hart pointed me to the comments from Rich Felker
that there are valid use cases for FUTEX_REQUEUE.

    From: Rich Felker <dalias@libc.org>
    Date: Wed, 29 Oct 2014 22:43:17 -0400
    To: Darren Hart <dvhart@infradead.org>
    Cc: GLIBC Devel <libc-alpha@sourceware.org>, ...
    Subject: Re: Add futex wrapper to glibc?

    On Wed, Oct 29, 2014 at 06:59:15PM -0700, Darren Hart wrote:
    [...]
    > I wonder though... can we not wrap FUTEX_REQUEUE? It's fundamentally
    > broken.  FUTEX_CMP_REQUEUE should *always* be used instead. The glibc
    > wrapper is one way to encourage developers to do the right thing
    > (don't expose the bad op in the header).

    You're mistaken here. There are plenty of valid ways to use
    FUTEX_REQUEUE - for example if the calling thread is requeuing the
    target(s) to a lock that the calling thread owns. Just because it
    doesn't meet the needs of the way glibc was using it internally
    doesn't mean it's useless for other applications.

Reported-by: Darren Hart <dvhart@infradead.org>
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:48 +01:00
Michael Kerrisk da56650ae4 futex.2: srcfix 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:48 +01:00
Michael Kerrisk fd1056148b futex.2: Minor wording fixes 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:48 +01:00
Michael Kerrisk 55f9e85ead futex.2: Minor wording fixes 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:48 +01:00
Michael Kerrisk b0f35fbb09 futex.2: tfix 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:48 +01:00
Michael Kerrisk c0dc758efd futex.2: Rewrap some source lines (no content changes) 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:48 +01:00
Michael Kerrisk 9d32a39b82 futex.2: Minor wording fixes 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:48 +01:00
Michael Kerrisk d45f244c6d futex.2: Minor wording fixes 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:48 +01:00
Michael Kerrisk 7e8dcabcb1 futex.2: Reword paragraph describing futex word 
Reported-by: Davidlohr Bueso <dave@stgolabs.net>
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:48 +01:00
Michael Kerrisk 02f7b623c9 futex.2: NOTES: futexes are also used to implement read-write locks and barriers 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:48 +01:00
Michael Kerrisk e0074751c9 futex.2: SEE ALSO: add pthread_mutexattr_getprotocol(3) 
Reported-by: Davidlohr Bueso <dave@stgolabs.net>
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:48 +01:00
Michael Kerrisk 36a90a75ce futex.2: wfix 
Reported-by: Heinrich Schuchardt <xypron.glpk@gmx.de>
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:48 +01:00
Michael Kerrisk d6bb5a38db futex.2: Tidy up some FIXMEs 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:48 +01:00
Michael Kerrisk cf44281c66 futex.2: Point out that futexes are used to implement higher-level abstractions 
Reported-by: Thomas Gleixner <tglx@linutronix.de>
Reported-by: Torvald Riegel <triegel@redhat.com>
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:48 +01:00
Michael Kerrisk 78bbcd9faf futex.2: Remove an obsolete FIXME 
Reviewed-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:48 +01:00
Michael Kerrisk cabee29d5e futex.2: tfix 
Reported-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:48 +01:00
Michael Kerrisk e61abc2018 futex.2: tfix 
Reported-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:48 +01:00
Michael Kerrisk a5c5a06aba futex.2: Clarify return value details 
Reporte-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:48 +01:00
Michael Kerrisk 943ccc5228 futex.2: Remove detail about kernel internals 
As commented on by Davidlohr Bueso:

    This to me reads a bit too much into the kernel (fastpath,
    refcnt, vmas). Why not just mention that it avoids overhead
    in the kernel or something? I don't recall any manpage
    mentioning such details, but I could be wrong.

Reported-by: Davidlohr Bueso <dave@stgolabs.net>
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:48 +01:00
Heinrich Schuchardt 10022b8e63 futex.2: Casting utime to uint32_t 
The kernel uses the following cast:

  if (cmd == FUTEX_REQUEUE || cmd == FUTEX_CMP_REQUEUE ||
      cmd == FUTEX_CMP_REQUEUE_PI || cmd == FUTEX_WAKE_OP)
    val2 = (u32) (unsigned long) utime;

This ensures that always the least significant four bytes of the
pointer are used, both on ILP32 and LP64 systems.

On a big endian system a simple cast from 64 bit pointer to 32 bit
integer would return the most significant four bytes.

We have to make the reader of the man-page aware of the usage
of the least significant bytes.

Signed-off-by: Heinrich Schuchardt <xypron.glpk@gmx.de>
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:48 +01:00
Heinrich Schuchardt c6dc40a2c9 futex.2: Use known types 
Type u32 is not exposed to the user.  Instead, refer to uint32_t,
which is defined in ISO/IEC 9899:1999.

Signed-off-by: Heinrich Schuchardt <xypron.glpk@gmx.de>
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:48 +01:00
Heinrich Schuchardt d725ab772e futex.2: tfix 
Signed-off-by: Heinrich Schuchardt <xypron.glpk@gmx.de>
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:48 +01:00
Michael Kerrisk 78e856927e futex.2: wfix 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:48 +01:00
Michael Kerrisk 0c3ec26b07 futex.2: Minor wording fixes 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:48 +01:00
Heinrich Schuchardt 8e754e12c5 futex.2: explanation of blocking 
Use shorter sentences.

Signed-off-by: Heinrich Schuchardt <xypron.glpk@gmx.de>
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:48 +01:00
Heinrich Schuchardt b80daba225 futex.2: explanation of blocking behavior 
Shorten overlong sentence.
Highlight futex().
Tfix.

Signed-off-by: Heinrich Schuchardt <xypron.glpk@gmx.de>
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:47 +01:00
Heinrich Schuchardt 344df36631 futex.2: clarify address mapping 
Using the word "physical" address should make the text easier to
make.

Avoid negations like "may not be equal".

Signed-off-by: Heinrich Schuchardt <xypron.glpk@gmx.de>
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:47 +01:00
Heinrich Schuchardt 594536fb2c futex.2: tfix 
Signed-off-by: Heinrich Schuchardt <xypron.glpk@gmx.de>
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:47 +01:00
Michael Kerrisk 4c8cb0ffe6 futex.2: Rewrap some long source lines 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:47 +01:00
Michael Kerrisk 83e80dda44 futex.2: ffix 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:47 +01:00
Heinrich Schuchardt 63ad44cb92 futex.2: simplify example 
Do not duplicate coding.

Signed-off-by: Heinrich Schuchardt <xypron.glpk@gmx.de>
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:47 +01:00
Heinrich Schuchardt 92a4669004 futex.2: futex.2: Fix error check in EXAMPLE: fork() fails with -1 
Signed-off-by: Heinrich Schuchardt <xypron.glpk@gmx.de>
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:47 +01:00
Michael Kerrisk 357646628c futex.2: tfix 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:47 +01:00
Michael Kerrisk 077981d467 futex.2: Wrap sentences at line boundaries 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:47 +01:00
Michael Kerrisk 74f58a643b futex.2: Explicitly mark FIXMEs added by Torvald Riegel 
Mainly so I can keep track of who said what should be fixed/checked

Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:47 +01:00
Torvald Riegel 4b35dc5dab futex.2: Terminology fixes 
Here is the result of a first pass over futex.2.  I tried to
do nothing that is too controversial.  I tried to apply the
terminology that at least Darren and I had in mind
consistently; but please check again.

The major changes are in how futexes are described in the
introductory parts of the page.  I hope it's easier to understand
now.  I've also tried to add some more precision to the the
description of the synchronization semantics (e.g., it makes a
difference whether we claim something is atomic (without further
qualification), or just atomic wrt.  other futex operations).
In some cases, that adds some verbosity to the text -- but I
believe that this is worth the clarity and consistency in using
terms, for example.

Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:47 +01:00
Michael Kerrisk 77da5febea futex.2: tfix 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:47 +01:00
Michael Kerrisk 305cc4153b futex.2: Add EXAMPLE program 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:47 +01:00
Michael Kerrisk 02182e7c8c futex.2: srcfix: FIXME 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:47 +01:00
Michael Kerrisk 1af427a43d futex.2: srcfix 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:47 +01:00
Michael Kerrisk 47f5c4baf5 futex.2: srcfix: FIXME 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:47 +01:00
Michael Kerrisk f529fd2013 futex Since Linux 2.6.22, EINTR can no longer occur on spurious wakeup 
As reported by Rich Felker:

    I see no code in the kernel whereby a "spurious wakeup",
    or anything other than interruption by a signal handler
    that's not SA_RESTART, can cause futex to fail with EINTR.
    In general, overloading of EINTR and/or spurious EINTRs
    from a syscall make it impossible to use that syscall for
    implementing any function where EINTR is a mandatory
    failure on interruption-by-signal, since there is no way
    for userspace to distinguish whether the EINTR occurred
    as a result of an interrupting signal or some other
    reason. The kernel folks have gone to great lengths to fix
    spurious EINTRs (see signal(7) for history), especially by
    non-interrupting signal handlers, including in futex, and
    allowing EINTR here would be contrary to that goal.

     It's my belief that the "or a spurious wakeup" text should
     simply be removed.

     The reason I'm raising this topic is its relevance to a
     thread on libc-alpha:

     [RFC] mutex destruction (#13690): problem description and workarounds

The bug and mailing list discussions to which Rich refers are:
     https://sourceware.org/bugzilla/show_bug.cgi?id=13690
     https://sourceware.org/ml/libc-alpha/2014-12/threads.html#0001

Torvald Riegel also reported the same issue, and Thomas Gleixner
noted that the "EINTR on spurious wakeup" behavior went away in
Linux 2.6.22. See the LKML thread, "futex() man page update help
request", Jan 2015:
http://thread.gmane.org/gmane.linux.kernel/1703405/focus=7734

Reported-by: Rich Felker <dalias@libc.org>
Reported-by: Torvald Riegel <triegel@redhat.com>
Reported-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Michael Kerrisk <mtknpages@gmail.com>
 2015-12-15 14:39:47 +01:00
Michael Kerrisk 9732dd8b3f futex.2: Various fixes after review from Davidlohr Bueso 
Reviewed-by: Davidlohr Bueso <dave@stgolabs.net>
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:47 +01:00
Michael Kerrisk 2abcba676a futex.2: Remove FUTEX_REQUEUE EINVAL error case 
Thomas Gleixner confirmed my reading that this case does
not apply.

Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:47 +01:00
Michael Kerrisk 9e2b90ee42 futex.2: Add an attmpt at a defintion of PI-aware futexes 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:47 +01:00
Michael Kerrisk 7bd3ffbc52 futex.2: srcfix 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:47 +01:00
Michael Kerrisk d9d5be6bea futex.2: tfix 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:46 +01:00
Michael Kerrisk 809ca3ae64 futex.2: Note that the kernel only "knows" about a futex in the contended case 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:46 +01:00
Michael Kerrisk a663ca5a12 futex.2: Add some subsection headings 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:46 +01:00
Michael Kerrisk e219551457 futex.2: srcfix 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:46 +01:00
Michael Kerrisk ed44c7c071 futex.2: Rewrite text on intended users of futexes 
Eliminate some redundant text.

Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:46 +01:00
Michael Kerrisk abb571e8b7 futex.2: Add text on pairing of FUTEX_WAIT_REQUEUE_PI + FUTEX_CMP_REQUEUE_PI 
Reported-by: Darren Hart <dvhart@linux.intel.com>
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:46 +01:00
Michael Kerrisk f1d2171d38 futex.2: srcfix 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:46 +01:00
Michael Kerrisk bdc5957afa futex.2: Process/thread rewordings 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:46 +01:00
Michael Kerrisk a59564304a futex.2: srcfix 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:46 +01:00
Michael Kerrisk 6700de2462 futex.2: tfix 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:46 +01:00
Michael Kerrisk 7d20efd7b0 futex.2: Add overview of priority inheritance 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:46 +01:00
Michael Kerrisk b565548bfa futex.2: Add brief description of the priority inversion problem 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:46 +01:00
Michael Kerrisk dd003bef7a futex.2: srcfix: FIXME 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:46 +01:00
Michael Kerrisk 8fe019c733 futex.2: SEE ALSO: add Documentation/robust-futex-ABI.txt 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:46 +01:00
Michael Kerrisk 4cf9289452 futex.2: tfix 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:46 +01:00
Michael Kerrisk baf0f1f470 futex.2: Note that syscall() must be employed 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:46 +01:00
Michael Kerrisk 4c2222812b futex.2: SEEL ALSO: add author details + other minor tweaks 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:46 +01:00
Michael Kerrisk 939ca89f38 futex.2: wfix 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:46 +01:00
Michael Kerrisk d4ba43283d futex.2: wfix 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:46 +01:00
Michael Kerrisk a282e5b050 futex.2: wfix 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:46 +01:00
Michael Kerrisk 30ebf7b4a1 futex.2: srcfix: FIXME 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:46 +01:00
Michael Kerrisk 7f315ae3e5 futex.2: ffix 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:46 +01:00
Michael Kerrisk 43d16602be futex.2: srcfix: FIXME 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:46 +01:00
Michael Kerrisk 64191e8f09 futex.2: srcfix: FIXME 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:46 +01:00
Michael Kerrisk f2bf5121d5 futex.2: srcfix 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:46 +01:00
Michael Kerrisk 53ba4030d1 futex.2: grfix 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:46 +01:00
Michael Kerrisk 4e566b1ebd futex.2: wfix 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:45 +01:00
Michael Kerrisk e45f973525 futex.2: Clarify that FUTEX_PRIVATE_FLAG relates to *thread* synchronization 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:45 +01:00
Michael Kerrisk f19904c01c futex.2: wfix: mention "virtual" when talking about memory addreses 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:45 +01:00
Michael Kerrisk 70b06b9033 futex.2: srcfix 
Various minor fixes to source

Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:45 +01:00
Michael Kerrisk a59fca7505 futex.2: wfix 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:45 +01:00
Michael Kerrisk 21b060bae6 futex.2: wfix 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:45 +01:00
Michael Kerrisk 5d67b190a1 futex.2: srcfix: FIXME 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:45 +01:00
Michael Kerrisk f0c0d61cd8 futex.2: ERRORS: add EINVAL case for FUTEX_CMP_REQUEUE_PI 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:45 +01:00
Michael Kerrisk 99c0ac69d9 futex.2: srcfix: FIXME 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:45 +01:00
Michael Kerrisk 9786b3ca15 futex.2: ERRORS: Add EINVAL case for FUTEX_CMP_REQUEUE_PI 
Reported-by: Darren Hart <dvhart@linux.intel.com>
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:45 +01:00
Michael Kerrisk 75299c8d17 futex.2: Fix EINVAL description for FUTEX_CMP_REQUEUE_PI 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:45 +01:00
Michael Kerrisk 6fbeb8f4a0 futex.2: Minor improvement to FUTEX_CMP_REQUEUE_PI text 
Reported-by: Darren Hart <dvhart@linux.intel.com>
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:45 +01:00
Michael Kerrisk 55a8bca383 futex.2: srcfix: remove obsolete FIXME 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:45 +01:00
Michael Kerrisk 1f043693de futex.2: tfix 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:45 +01:00
Michael Kerrisk f48516d113 futex.2: ERRORS: added EAGAIN case for FUTEX_WAIT_REQUEUE_PI 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:45 +01:00
Michael Kerrisk 63bea7dcbb futex.2: Describe 'timeout' argument of FUTEX_WAIT_REQUEUE_PI 2015-12-15 14:39:45 +01:00
Michael Kerrisk a4e6991290 futex.2: srcfix: FIXME 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:45 +01:00
Thomas Gleixner 6ff1b4c013 futex.2: Document FUTEX_WAIT_REQUEUE_PI 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:45 +01:00
Michael Kerrisk c6d8cf213c futex.2: srcfix 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:45 +01:00
Michael Kerrisk 936876a994 futex.2: wfix 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:45 +01:00
Michael Kerrisk de5a3bb47d futex.2: wfix 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:45 +01:00
Michael Kerrisk a696857697 futex.2: srcfix 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:45 +01:00
Michael Kerrisk 768d3c2355 futex.2: Use 'val2' as the term for 'timeout' cast to 'u32' 
This simplifies the text somewhat, so we don't need
to repeatedly describe how 'timeout' is cast 'u32'.

Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:45 +01:00
Michael Kerrisk 99c0041df4 futex.2: ERRORS: add another EINVAL case (uaddr2) for FUTEX_CMP_REQUEUE_PI 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:45 +01:00
Michael Kerrisk f9250b1a1a futex.2: ERRORS: add EINVAL case for FUTEX_CMP_REQUEUE_PI 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:45 +01:00
Michael Kerrisk 025e137469 futex.2: ffix 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:45 +01:00
Michael Kerrisk 476debd7ea futex.2: ERRORS: place two similar EINVAL cases together 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:44 +01:00
Michael Kerrisk 662c0da854 futex.2: ERRORS: add EDEADLK case for FUTEX_CMP_REQUEUE_PI 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:44 +01:00
Michael Kerrisk dc2742a8aa futex.2: ERRORS: add EPERM case for FUTEX_CMP_REQUEUE_PI 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:44 +01:00
Michael Kerrisk 04331c3fd8 futex.2: wfix for EPERM error 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:44 +01:00
Michael Kerrisk 5eeca85632 futex.2: srcfix: add FIXME for "spurios wakeup" question from Rich Felker 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:44 +01:00
Michael Kerrisk 2043f2c133 futex.2: ERRORS: added EINVAL case for FUTEX_CMP_REQUEUE_PI 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:44 +01:00
Michael Kerrisk 670b34f8e8 futex.2: srcfix: FIXME 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:44 +01:00
Michael Kerrisk 794bb106f4 futex.2: ERRORS: add ENOSYS case for FUTEX_WAIT_REQUEUE_PI 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:44 +01:00
Michael Kerrisk 4945ff19bb futex.2: ERRORS: add ENOSYS case for FUTEX_CMP_REQUEUE_PI 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:44 +01:00
Michael Kerrisk a2ebebcdc7 futex.2: wfix for ENOSYS error 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:44 +01:00
Michael Kerrisk 8f2068bbe4 futex.2: ERRORS: add EAGAIN case for FUTEX_CMP_REQUEUE_PI (uaddr futex != val3) 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:44 +01:00
Michael Kerrisk aaec90325b futex.2: ERRORS: add EAGAIN case for FUTEX_CMP_REQUEUE_PI (uaddr2 owner exiting) 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:44 +01:00
Michael Kerrisk 8727670917 futex.2: tfix 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:44 +01:00
Michael Kerrisk ce5602fde5 futex.2: wfix 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:44 +01:00
Michael Kerrisk 360f773c2b futex.2: ERRORS: add ESRCH case for FUTEX_CMP_REQUEUE_PI 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:44 +01:00
Michael Kerrisk 2ed261994a futex.2: SEE ALSO: add pointer to Hart LWN.net article 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:44 +01:00
Michael Kerrisk f6af90e736 futex.2: ffix (ASCII art layout) 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:44 +01:00
Michael Kerrisk c8b921bd42 futex.2: tfix 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:44 +01:00
Michael Kerrisk c84cf68c3b futex.2: wfix 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:44 +01:00
Michael Kerrisk be37667386 futex.2: srcfix: FIXME 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:44 +01:00
Michael Kerrisk fc57e6bb5e futex.2: srcfix: FIXME 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:44 +01:00
Michael Kerrisk e34a8fb6c3 futex.2: ERRORS: Add ENOMEM case for FUTEX_CMP_REQUEUE_PI 
Reported-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:44 +01:00
Michael Kerrisk 9e54d26d3c futex.2: Add further details for FUTEX_CMP_REQUEUE_PI 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:44 +01:00
Darren Hart f812a08b1d futex.2: Describe FUTEX_CMP_REQUEUE_PI 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:44 +01:00
Michael Kerrisk 084744ef24 futex.2: Note arguments ignored by FUTEX_TRYLOCK_PI 
Reported-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:44 +01:00
Michael Kerrisk 11a194bff8 futex.2: wfix 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:44 +01:00
Michael Kerrisk 0b76182603 futex.2: srfix: FIXME 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:43 +01:00
Michael Kerrisk c0091dd3ff futex.2: srcfix: FIXME 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:43 +01:00
Michael Kerrisk badbf70cad futex.2: Replace instances of EWOULDBLOCK by EAGAIN 
On Linux, the two error numbers are the same. The kernel
code for futexes is somehwat inconsistent, using EAGAIN
in some places, and EWOULDBLOCK in others. Let's make the
manual page consistent at least.

This change requires reordering of one entry in ERRORS.

Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:43 +01:00
Michael Kerrisk fa0388c309 futex.2: Rework FUTEXT_TRYLOCK_PI text a litte + add FIXMEs 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:43 +01:00
Michael Kerrisk 67833bec78 futex.2: Rework FUTEX_LOCK_PI text and add FIXMEs 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:43 +01:00
Michael Kerrisk b52e1cd4a8 futex.2: Further tweaks to PI introductory text 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:43 +01:00
Michael Kerrisk f5ad572fcf futex.2: ffix 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:43 +01:00
Michael Kerrisk 0483b6cce7 futex.2: Add more references to SEE ALSO 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:43 +01:00
Michael Kerrisk 79d918c7af futex.2: Rework Hart/Guniguntala text 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:43 +01:00
Michael Kerrisk 7c16fbff95 futex.2: Integrate text from Darren Hart on PI Mutexes 
From the 2009 Real-Time Linux Workshop paper
Requeue-PI: Making Glibc Condvars PI-Aware
Darren Hart, Dinakar Guniguntala
http://lwn.net/images/conf/rtlws11/papers/proc/p10.pdf

Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:43 +01:00
Michael Kerrisk b4d4f5c537 futex.2: srcfix: Remove obsolete FIXME 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:43 +01:00
Michael Kerrisk bd90a5f9c3 futex.2: Add subsection for PI futexes 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:43 +01:00
Michael Kerrisk 9ce19cf1b7 futex.2: Fix discussion of FUTEX_LOCK_PI 'timeout' argument 
Reading futex_lock_pi(), it appears that the timeout is *not*
interpreted in the same way as for FUTEX_WAKE.

Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:43 +01:00
Michael Kerrisk a8b5b324e3 futex.2: RETURN VALUE: add FUTEX_WAKE_OP 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:43 +01:00
Michael Kerrisk 22c15de938 futex.2: RETURN VALUE: add FUTEX_WAIT_REQUEUE_PI 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:43 +01:00
Michael Kerrisk dddd395a8d futex.2: RETURN VALUE: add FUTEX_CMP_REQUEUE_PI 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:43 +01:00
Michael Kerrisk 52bb928f26 futex.2: RETURN VALUE: add FUTEX_UNLOCK_PI 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:43 +01:00
Michael Kerrisk 5c716eef68 futex.2: RETURN VALUE: add FUTEX_TRYLOCK_PI 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:43 +01:00
Michael Kerrisk bf02a260f4 futex.2: RETURN VALUE: add FUTEX_LOCK_PI 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:43 +01:00
Michael Kerrisk b884566b97 futex.2: RETURN VALUE: add FUTEX_WAKE_BITSET 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:43 +01:00
Michael Kerrisk 7bcc535166 futex.2: RETURN VALUE: add FUTEX_WAIT_BITSET 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:43 +01:00
Michael Kerrisk 7446a8373c futex.2: RETURN VALUE: mention FUTEX_WAKE_BITSET under FUTEX_WAIT 
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:43 +01:00
Michael Kerrisk 8f23887259 futex.2: Remove uneeded reference to ERRORS section 
(The need to read ERRORS is implied.)

Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:43 +01:00
Michael Kerrisk dcad19c0c1 futex.2: RETURN VALUE: add placeholder for various operations 
There are still several operations whose return value
is not yet described.

Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
 2015-12-15 14:39:43 +01:00