1. 15 Oct, 2010 1 commit
    • Arnd Bergmann's avatar
      llseek: automatically add .llseek fop · 6038f373
      Arnd Bergmann authored
      All file_operations should get a .llseek operation so we can make
      nonseekable_open the default for future file operations without a
      .llseek pointer.
      
      The three cases that we can automatically detect are no_llseek, seq_lseek
      and default_llseek. For cases where we can we can automatically prove that
      the file offset is always ignored, we use noop_llseek, which maintains
      the current behavior of not returning an error from a seek.
      
      New drivers should normally not use noop_llseek but instead use no_llseek
      and call nonseekable_open at open time.  Existing drivers can be converted
      to do the same when the maintainer knows for certain that no user code
      relies on calling seek on the device file.
      
      The generated code is often incorrectly indented and right now contains
      comments that clarify for each added line why a specific variant was
      chosen. In the version that gets submitted upstream, the comments will
      be gone and I will manually fix the indentation, because there does not
      seem to be a way to do that using coccinelle.
      
      Some amount of new code is currently sitting in linux-next that should get
      the same modifications, which I will do at the end of the merge window.
      
      Many thanks to Julia Lawall for helping me learn to write a semantic
      patch that does all this.
      
      ===== begin semantic patch =====
      // This adds an llseek= method to all file operations,
      // as a preparation for making no_llseek the default.
      //
      // The rules are
      // - use no_llseek explicitly if we do nonseekable_open
      // - use seq_lseek for sequential files
      // - use default_llseek if we know we access f_pos
      // - use noop_llseek if we know we don't access f_pos,
      //   but we still want to allow users to call lseek
      //
      @ open1 exists @
      identifier nested_open;
      @@
      nested_open(...)
      {
      <+...
      nonseekable_open(...)
      ...+>
      }
      
      @ open exists@
      identifier open_f;
      identifier i, f;
      identifier open1.nested_open;
      @@
      int open_f(struct inode *i, struct file *f)
      {
      <+...
      (
      nonseekable_open(...)
      |
      nested_open(...)
      )
      ...+>
      }
      
      @ read disable optional_qualifier exists @
      identifier read_f;
      identifier f, p, s, off;
      type ssize_t, size_t, loff_t;
      expression E;
      identifier func;
      @@
      ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off)
      {
      <+...
      (
         *off = E
      |
         *off += E
      |
         func(..., off, ...)
      |
         E = *off
      )
      ...+>
      }
      
      @ read_no_fpos disable optional_qualifier exists @
      identifier read_f;
      identifier f, p, s, off;
      type ssize_t, size_t, loff_t;
      @@
      ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off)
      {
      ... when != off
      }
      
      @ write @
      identifier write_f;
      identifier f, p, s, off;
      type ssize_t, size_t, loff_t;
      expression E;
      identifier func;
      @@
      ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off)
      {
      <+...
      (
        *off = E
      |
        *off += E
      |
        func(..., off, ...)
      |
        E = *off
      )
      ...+>
      }
      
      @ write_no_fpos @
      identifier write_f;
      identifier f, p, s, off;
      type ssize_t, size_t, loff_t;
      @@
      ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off)
      {
      ... when != off
      }
      
      @ fops0 @
      identifier fops;
      @@
      struct file_operations fops = {
       ...
      };
      
      @ has_llseek depends on fops0 @
      identifier fops0.fops;
      identifier llseek_f;
      @@
      struct file_operations fops = {
      ...
       .llseek = llseek_f,
      ...
      };
      
      @ has_read depends on fops0 @
      identifier fops0.fops;
      identifier read_f;
      @@
      struct file_operations fops = {
      ...
       .read = read_f,
      ...
      };
      
      @ has_write depends on fops0 @
      identifier fops0.fops;
      identifier write_f;
      @@
      struct file_operations fops = {
      ...
       .write = write_f,
      ...
      };
      
      @ has_open depends on fops0 @
      identifier fops0.fops;
      identifier open_f;
      @@
      struct file_operations fops = {
      ...
       .open = open_f,
      ...
      };
      
      // use no_llseek if we call nonseekable_open
      ////////////////////////////////////////////
      @ nonseekable1 depends on !has_llseek && has_open @
      identifier fops0.fops;
      identifier nso ~= "nonseekable_open";
      @@
      struct file_operations fops = {
      ...  .open = nso, ...
      +.llseek = no_llseek, /* nonseekable */
      };
      
      @ nonseekable2 depends on !has_llseek @
      identifier fops0.fops;
      identifier open.open_f;
      @@
      struct file_operations fops = {
      ...  .open = open_f, ...
      +.llseek = no_llseek, /* open uses nonseekable */
      };
      
      // use seq_lseek for sequential files
      /////////////////////////////////////
      @ seq depends on !has_llseek @
      identifier fops0.fops;
      identifier sr ~= "seq_read";
      @@
      struct file_operations fops = {
      ...  .read = sr, ...
      +.llseek = seq_lseek, /* we have seq_read */
      };
      
      // use default_llseek if there is a readdir
      ///////////////////////////////////////////
      @ fops1 depends on !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
      identifier fops0.fops;
      identifier readdir_e;
      @@
      // any other fop is used that changes pos
      struct file_operations fops = {
      ... .readdir = readdir_e, ...
      +.llseek = default_llseek, /* readdir is present */
      };
      
      // use default_llseek if at least one of read/write touches f_pos
      /////////////////////////////////////////////////////////////////
      @ fops2 depends on !fops1 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
      identifier fops0.fops;
      identifier read.read_f;
      @@
      // read fops use offset
      struct file_operations fops = {
      ... .read = read_f, ...
      +.llseek = default_llseek, /* read accesses f_pos */
      };
      
      @ fops3 depends on !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
      identifier fops0.fops;
      identifier write.write_f;
      @@
      // write fops use offset
      struct file_operations fops = {
      ... .write = write_f, ...
      +	.llseek = default_llseek, /* write accesses f_pos */
      };
      
      // Use noop_llseek if neither read nor write accesses f_pos
      ///////////////////////////////////////////////////////////
      
      @ fops4 depends on !fops1 && !fops2 && !fops3 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
      identifier fops0.fops;
      identifier read_no_fpos.read_f;
      identifier write_no_fpos.write_f;
      @@
      // write fops use offset
      struct file_operations fops = {
      ...
       .write = write_f,
       .read = read_f,
      ...
      +.llseek = noop_llseek, /* read and write both use no f_pos */
      };
      
      @ depends on has_write && !has_read && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
      identifier fops0.fops;
      identifier write_no_fpos.write_f;
      @@
      struct file_operations fops = {
      ... .write = write_f, ...
      +.llseek = noop_llseek, /* write uses no f_pos */
      };
      
      @ depends on has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
      identifier fops0.fops;
      identifier read_no_fpos.read_f;
      @@
      struct file_operations fops = {
      ... .read = read_f, ...
      +.llseek = noop_llseek, /* read uses no f_pos */
      };
      
      @ depends on !has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
      identifier fops0.fops;
      @@
      struct file_operations fops = {
      ...
      +.llseek = noop_llseek, /* no read or write fn */
      };
      ===== End semantic patch =====
      Signed-off-by: default avatarArnd Bergmann <arnd@arndb.de>
      Cc: Julia Lawall <julia@diku.dk>
      Cc: Christoph Hellwig <hch@infradead.org>
      6038f373
  2. 20 May, 2010 1 commit
  3. 30 Mar, 2010 1 commit
    • Tejun Heo's avatar
      include cleanup: Update gfp.h and slab.h includes to prepare for breaking... · 5a0e3ad6
      Tejun Heo authored
      include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
      
      percpu.h is included by sched.h and module.h and thus ends up being
      included when building most .c files.  percpu.h includes slab.h which
      in turn includes gfp.h making everything defined by the two files
      universally available and complicating inclusion dependencies.
      
      percpu.h -> slab.h dependency is about to be removed.  Prepare for
      this change by updating users of gfp and slab facilities include those
      headers directly instead of assuming availability.  As this conversion
      needs to touch large number of source files, the following script is
      used as the basis of conversion.
      
        http://userweb.kernel.org/~tj/misc/slabh-sweep.py
      
      The script does the followings.
      
      * Scan files for gfp and slab usages and update includes such that
        only the necessary includes are there.  ie. if only gfp is used,
        gfp.h, if slab is used, slab.h.
      
      * When the script inserts a new include, it looks at the include
        blocks and try to put the new include such that its order conforms
        to its surrounding.  It's put in the include block which contains
        core kernel includes, in the same order that the rest are ordered -
        alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
        doesn't seem to be any matching order.
      
      * If the script can't find a place to put a new include (mostly
        because the file doesn't have fitting include block), it prints out
        an error message indicating which .h file needs to be added to the
        file.
      
      The conversion was done in the following steps.
      
      1. The initial automatic conversion of all .c files updated slightly
         over 4000 files, deleting around 700 includes and adding ~480 gfp.h
         and ~3000 slab.h inclusions.  The script emitted errors for ~400
         files.
      
      2. Each error was manually checked.  Some didn't need the inclusion,
         some needed manual addition while adding it to implementation .h or
         embedding .c file was more appropriate for others.  This step added
         inclusions to around 150 files.
      
      3. The script was run again and the output was compared to the edits
         from #2 to make sure no file was left behind.
      
      4. Several build tests were done and a couple of problems were fixed.
         e.g. lib/decompress_*.c used malloc/free() wrappers around slab
         APIs requiring slab.h to be added manually.
      
      5. The script was run on all .h files but without automatically
         editing them as sprinkling gfp.h and slab.h inclusions around .h
         files could easily lead to inclusion dependency hell.  Most gfp.h
         inclusion directives were ignored as stuff from gfp.h was usually
         wildly available and often used in preprocessor macros.  Each
         slab.h inclusion directive was examined and added manually as
         necessary.
      
      6. percpu.h was updated not to include slab.h.
      
      7. Build test were done on the following configurations and failures
         were fixed.  CONFIG_GCOV_KERNEL was turned off for all tests (as my
         distributed build env didn't work with gcov compiles) and a few
         more options had to be turned off depending on archs to make things
         build (like ipr on powerpc/64 which failed due to missing writeq).
      
         * x86 and x86_64 UP and SMP allmodconfig and a custom test config.
         * powerpc and powerpc64 SMP allmodconfig
         * sparc and sparc64 SMP allmodconfig
         * ia64 SMP allmodconfig
         * s390 SMP allmodconfig
         * alpha SMP allmodconfig
         * um on x86_64 SMP allmodconfig
      
      8. percpu.h modifications were reverted so that it could be applied as
         a separate patch and serve as bisection point.
      
      Given the fact that I had only a couple of failures from tests on step
      6, I'm fairly confident about the coverage of this conversion patch.
      If there is a breakage, it's likely to be something in one of the arch
      headers which should be easily discoverable easily on most builds of
      the specific arch.
      Signed-off-by: default avatarTejun Heo <tj@kernel.org>
      Guess-its-ok-by: default avatarChristoph Lameter <cl@linux-foundation.org>
      Cc: Ingo Molnar <mingo@redhat.com>
      Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
      5a0e3ad6
  4. 22 Dec, 2009 1 commit
  5. 18 Feb, 2009 1 commit
  6. 14 Jan, 2009 2 commits
  7. 05 Sep, 2008 1 commit
  8. 24 Jul, 2008 4 commits
    • Ulrich Drepper's avatar
      flag parameters: check magic constants · e38b36f3
      Ulrich Drepper authored
      This patch adds test that ensure the boundary conditions for the various
      constants introduced in the previous patches is met.  No code is generated.
      
      [akpm@linux-foundation.org: fix alpha]
      Signed-off-by: default avatarUlrich Drepper <drepper@redhat.com>
      Acked-by: default avatarDavide Libenzi <davidel@xmailserver.org>
      Cc: Michael Kerrisk <mtk.manpages@googlemail.com>
      Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
      Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
      e38b36f3
    • Ulrich Drepper's avatar
      flag parameters: NONBLOCK in timerfd_create · 6b1ef0e6
      Ulrich Drepper authored
      This patch adds support for the TFD_NONBLOCK flag to timerfd_create.  The
      additional changes needed are minimal.
      
      The following test must be adjusted for architectures other than x86 and
      x86-64 and in case the syscall numbers changed.
      
      ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
      #include <fcntl.h>
      #include <stdio.h>
      #include <time.h>
      #include <unistd.h>
      #include <sys/syscall.h>
      
      #ifndef __NR_timerfd_create
      # ifdef __x86_64__
      #  define __NR_timerfd_create 283
      # elif defined __i386__
      #  define __NR_timerfd_create 322
      # else
      #  error "need __NR_timerfd_create"
      # endif
      #endif
      
      #define TFD_NONBLOCK O_NONBLOCK
      
      int
      main (void)
      {
        int fd = syscall (__NR_timerfd_create, CLOCK_REALTIME, 0);
        if (fd == -1)
          {
            puts ("timerfd_create(0) failed");
            return 1;
          }
        int fl = fcntl (fd, F_GETFL);
        if (fl == -1)
          {
            puts ("fcntl failed");
            return 1;
          }
        if (fl & O_NONBLOCK)
          {
            puts ("timerfd_create(0) set non-blocking mode");
            return 1;
          }
        close (fd);
      
        fd = syscall (__NR_timerfd_create, CLOCK_REALTIME, TFD_NONBLOCK);
        if (fd == -1)
          {
            puts ("timerfd_create(TFD_NONBLOCK) failed");
            return 1;
          }
        fl = fcntl (fd, F_GETFL);
        if (fl == -1)
          {
            puts ("fcntl failed");
            return 1;
          }
        if ((fl & O_NONBLOCK) == 0)
          {
            puts ("timerfd_create(TFD_NONBLOCK) set non-blocking mode");
            return 1;
          }
        close (fd);
      
        puts ("OK");
      
        return 0;
      }
      ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
      Signed-off-by: default avatarUlrich Drepper <drepper@redhat.com>
      Acked-by: default avatarDavide Libenzi <davidel@xmailserver.org>
      Cc: Michael Kerrisk <mtk.manpages@googlemail.com>
      Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
      Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
      6b1ef0e6
    • Ulrich Drepper's avatar
      flag parameters: timerfd_create · 11fcb6c1
      Ulrich Drepper authored
      The timerfd_create syscall already has a flags parameter.  It just is
      unused so far.  This patch changes this by introducing the TFD_CLOEXEC
      flag to set the close-on-exec flag for the returned file descriptor.
      
      A new name TFD_CLOEXEC is introduced which in this implementation must
      have the same value as O_CLOEXEC.
      
      The following test must be adjusted for architectures other than x86 and
      x86-64 and in case the syscall numbers changed.
      
      ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
      #include <fcntl.h>
      #include <stdio.h>
      #include <time.h>
      #include <unistd.h>
      #include <sys/syscall.h>
      
      #ifndef __NR_timerfd_create
      # ifdef __x86_64__
      #  define __NR_timerfd_create 283
      # elif defined __i386__
      #  define __NR_timerfd_create 322
      # else
      #  error "need __NR_timerfd_create"
      # endif
      #endif
      
      #define TFD_CLOEXEC O_CLOEXEC
      
      int
      main (void)
      {
        int fd = syscall (__NR_timerfd_create, CLOCK_REALTIME, 0);
        if (fd == -1)
          {
            puts ("timerfd_create(0) failed");
            return 1;
          }
        int coe = fcntl (fd, F_GETFD);
        if (coe == -1)
          {
            puts ("fcntl failed");
            return 1;
          }
        if (coe & FD_CLOEXEC)
          {
            puts ("timerfd_create(0) set close-on-exec flag");
            return 1;
          }
        close (fd);
      
        fd = syscall (__NR_timerfd_create, CLOCK_REALTIME, TFD_CLOEXEC);
        if (fd == -1)
          {
            puts ("timerfd_create(TFD_CLOEXEC) failed");
            return 1;
          }
        coe = fcntl (fd, F_GETFD);
        if (coe == -1)
          {
            puts ("fcntl failed");
            return 1;
          }
        if ((coe & FD_CLOEXEC) == 0)
          {
            puts ("timerfd_create(TFD_CLOEXEC) set close-on-exec flag");
            return 1;
          }
        close (fd);
      
        puts ("OK");
      
        return 0;
      }
      ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
      Signed-off-by: default avatarUlrich Drepper <drepper@redhat.com>
      Acked-by: default avatarDavide Libenzi <davidel@xmailserver.org>
      Cc: Michael Kerrisk <mtk.manpages@googlemail.com>
      Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
      Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
      11fcb6c1
    • Ulrich Drepper's avatar
      flag parameters: anon_inode_getfd extension · 7d9dbca3
      Ulrich Drepper authored
      This patch just extends the anon_inode_getfd interface to take an additional
      parameter with a flag value.  The flag value is passed on to
      get_unused_fd_flags in anticipation for a use with the O_CLOEXEC flag.
      
      No actual semantic changes here, the changed callers all pass 0 for now.
      
      [akpm@linux-foundation.org: KVM fix]
      Signed-off-by: default avatarUlrich Drepper <drepper@redhat.com>
      Acked-by: default avatarDavide Libenzi <davidel@xmailserver.org>
      Cc: Michael Kerrisk <mtk.manpages@googlemail.com>
      Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
      Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
      7d9dbca3
  9. 01 May, 2008 1 commit
    • Al Viro's avatar
      [PATCH] sanitize anon_inode_getfd() · 2030a42c
      Al Viro authored
      a) none of the callers even looks at inode or file returned by anon_inode_getfd()
      b) any caller that would try to look at those would be racy, since by the time
      it returns we might have raced with close() from another thread and that
      file would be pining for fjords.
      Signed-off-by: default avatarAl Viro <viro@zeniv.linux.org.uk>
      2030a42c
  10. 29 Apr, 2008 1 commit
  11. 05 Feb, 2008 1 commit
    • Davide Libenzi's avatar
      timerfd: new timerfd API · 4d672e7a
      Davide Libenzi authored
      This is the new timerfd API as it is implemented by the following patch:
      
      int timerfd_create(int clockid, int flags);
      int timerfd_settime(int ufd, int flags,
      		    const struct itimerspec *utmr,
      		    struct itimerspec *otmr);
      int timerfd_gettime(int ufd, struct itimerspec *otmr);
      
      The timerfd_create() API creates an un-programmed timerfd fd.  The "clockid"
      parameter can be either CLOCK_MONOTONIC or CLOCK_REALTIME.
      
      The timerfd_settime() API give new settings by the timerfd fd, by optionally
      retrieving the previous expiration time (in case the "otmr" parameter is not
      NULL).
      
      The time value specified in "utmr" is absolute, if the TFD_TIMER_ABSTIME bit
      is set in the "flags" parameter.  Otherwise it's a relative time.
      
      The timerfd_gettime() API returns the next expiration time of the timer, or
      {0, 0} if the timerfd has not been set yet.
      
      Like the previous timerfd API implementation, read(2) and poll(2) are
      supported (with the same interface).  Here's a simple test program I used to
      exercise the new timerfd APIs:
      
      http://www.xmailserver.org/timerfd-test2.c
      
      [akpm@linux-foundation.org: coding-style cleanups]
      [akpm@linux-foundation.org: fix ia64 build]
      [akpm@linux-foundation.org: fix m68k build]
      [akpm@linux-foundation.org: fix mips build]
      [akpm@linux-foundation.org: fix alpha, arm, blackfin, cris, m68k, s390, sparc and sparc64 builds]
      [heiko.carstens@de.ibm.com: fix s390]
      [akpm@linux-foundation.org: fix powerpc build]
      [akpm@linux-foundation.org: fix sparc64 more]
      Signed-off-by: default avatarDavide Libenzi <davidel@xmailserver.org>
      Cc: Michael Kerrisk <mtk-manpages@gmx.net>
      Cc: Thomas Gleixner <tglx@linutronix.de>
      Cc: Davide Libenzi <davidel@xmailserver.org>
      Cc: Michael Kerrisk <mtk-manpages@gmx.net>
      Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
      Signed-off-by: default avatarHeiko Carstens <heiko.carstens@de.ibm.com>
      Cc: Michael Kerrisk <mtk.manpages@gmail.com>
      Cc: Davide Libenzi <davidel@xmailserver.org>
      Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
      Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
      4d672e7a
  12. 26 Jul, 2007 1 commit
    • Davide Libenzi's avatar
      make timerfd return a u64 and fix the __put_user · 09828402
      Davide Libenzi authored
      Davi fixed a missing cast in the __put_user(), that was making timerfd
      return a single byte instead of the full value.
      
      Talking with Michael about the timerfd man page, we think it'd be better to
      use a u64 for the returned value, to align it with the eventfd
      implementation.
      
      This is an ABI change.  The timerfd code is new in 2.6.22 and if we merge this
      into 2.6.23 then we should also merge it into 2.6.22.x.  That will leave a few
      early 2.6.22 kernels out in the wild which might misbehave when a future
      timerfd-enabled glibc is run on them.
      
      mtk says: The difference would be that read() will only return 4 bytes, while
      the application will expect 8.  If the application is checking the size of
      returned value, as it should, then it will be able to detect the problem (it
      could even be sophisticated enough to know that if this is a 4-byte return,
      then it is running on an old 2.6.22 kernel).  If the application is not
      checking the return from read(), then its 8-byte buffer will not be filled --
      the contents of the last 4 bytes will be undefined, so the u64 value as a
      whole will be junk.
      Signed-off-by: default avatarDavide Libenzi <davidel@xmailserver.org>
      Cc: Michael Kerrisk <mtk-manpages@gmx.net>
      Cc: Davi Arnaut <davi@haxent.com.br>
      Cc: <stable@kernel.org>
      Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
      Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
      09828402
  13. 18 May, 2007 1 commit
  14. 11 May, 2007 1 commit
    • Davide Libenzi's avatar
      signal/timer/event: timerfd core · b215e283
      Davide Libenzi authored
      This patch introduces a new system call for timers events delivered though
      file descriptors.  This allows timer event to be used with standard POSIX
      poll(2), select(2) and read(2).  As a consequence of supporting the Linux
      f_op->poll subsystem, they can be used with epoll(2) too.
      
      The system call is defined as:
      
      int timerfd(int ufd, int clockid, int flags, const struct itimerspec *utmr);
      
      The "ufd" parameter allows for re-use (re-programming) of an existing timerfd
      w/out going through the close/open cycle (same as signalfd).  If "ufd" is -1,
      s new file descriptor will be created, otherwise the existing "ufd" will be
      re-programmed.
      
      The "clockid" parameter is either CLOCK_MONOTONIC or CLOCK_REALTIME.  The time
      specified in the "utmr->it_value" parameter is the expiry time for the timer.
      
      If the TFD_TIMER_ABSTIME flag is set in "flags", this is an absolute time,
      otherwise it's a relative time.
      
      If the time specified in the "utmr->it_interval" is not zero (.tv_sec == 0,
      tv_nsec == 0), this is the period at which the following ticks should be
      generated.
      
      The "utmr->it_interval" should be set to zero if only one tick is requested.
      Setting the "utmr->it_value" to zero will disable the timer, or will create a
      timerfd without the timer enabled.
      
      The function returns the new (or same, in case "ufd" is a valid timerfd
      descriptor) file, or -1 in case of error.
      
      As stated before, the timerfd file descriptor supports poll(2), select(2) and
      epoll(2).  When a timer event happened on the timerfd, a POLLIN mask will be
      returned.
      
      The read(2) call can be used, and it will return a u32 variable holding the
      number of "ticks" that happened on the interface since the last call to
      read(2).  The read(2) call supportes the O_NONBLOCK flag too, and EAGAIN will
      be returned if no ticks happened.
      
      A quick test program, shows timerfd working correctly on my amd64 box:
      
      http://www.xmailserver.org/timerfd-test.c
      
      [akpm@linux-foundation.org: add sys_timerfd to sys_ni.c]
      Signed-off-by: default avatarDavide Libenzi <davidel@xmailserver.org>
      Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
      Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
      b215e283