)]}'
{
  "log": [
    {
      "commit": "d2fd89962cd5de6b1fb9c1c789b56bc16f58f121",
      "tree": "0c07ea2d059d715e6f0d9c8778ea1e1382dfbc95",
      "parents": [
        "c0887eedb4498e20e7895508b7af8e419e397405"
      ],
      "author": {
        "name": "Randy Dunlap",
        "email": "randy.dunlap@oracle.com",
        "time": "Wed Jun 27 14:09:48 2007 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@woody.linux-foundation.org",
        "time": "Thu Jun 28 11:34:53 2007 -0700"
      },
      "message": "eventfd: clean compile when CONFIG_EVENTFD\u003dn\n\nFix gcc warning and add parameter checking when CONFIG_EVENTFD\u003dn:\n\nfs/aio.c: In function \u0027aio_complete\u0027:\nfs/aio.c:955: warning: statement with no effect\n\nSigned-off-by: Randy Dunlap \u003crandy.dunlap@oracle.com\u003e\nCc: Davide Libenzi \u003cdavidel@xmailserver.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n"
    },
    {
      "commit": "e1ad7468c77ddb94b0615d5f50fa255525fde0f0",
      "tree": "856be1a028fece7e1fa10b7b585096839913fe2e",
      "parents": [
        "83f5d1266926c75890f1bc4678e49d79483cb573"
      ],
      "author": {
        "name": "Davide Libenzi",
        "email": "davidel@xmailserver.org",
        "time": "Thu May 10 22:23:19 2007 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@woody.linux-foundation.org",
        "time": "Fri May 11 08:29:36 2007 -0700"
      },
      "message": "signal/timer/event: eventfd core\n\nThis is a very simple and light file descriptor, that can be used as event\nwait/dispatch by userspace (both wait and dispatch) and by the kernel\n(dispatch only).  It can be used instead of pipe(2) in all cases where those\nwould simply be used to signal events.  Their kernel overhead is much lower\nthan pipes, and they do not consume two fds.  When used in the kernel, it can\noffer an fd-bridge to enable, for example, functionalities like KAIO or\nsyslets/threadlets to signal to an fd the completion of certain operations.\nBut more in general, an eventfd can be used by the kernel to signal readiness,\nin a POSIX poll/select way, of interfaces that would otherwise be incompatible\nwith it.  The API is:\n\nint eventfd(unsigned int count);\n\nThe eventfd API accepts an initial \"count\" parameter, and returns an eventfd\nfd.  It supports poll(2) (POLLIN, POLLOUT, POLLERR), read(2) and write(2).\n\nThe POLLIN flag is raised when the internal counter is greater than zero.\n\nThe POLLOUT flag is raised when at least a value of \"1\" can be written to the\ninternal counter.\n\nThe POLLERR flag is raised when an overflow in the counter value is detected.\n\nThe write(2) operation can never overflow the counter, since it blocks (unless\nO_NONBLOCK is set, in which case -EAGAIN is returned).\n\nBut the eventfd_signal() function can do it, since it\u0027s supposed to not sleep\nduring its operation.\n\nThe read(2) function reads the __u64 counter value, and reset the internal\nvalue to zero.  If the value read is equal to (__u64) -1, an overflow happened\non the internal counter (due to 2^64 eventfd_signal() posts that has never\nbeen retired - unlickely, but possible).\n\nThe write(2) call writes an __u64 count value, and adds it to the current\ncounter.  The eventfd fd supports O_NONBLOCK also.\n\nOn the kernel side, we have:\n\nstruct file *eventfd_fget(int fd);\nint eventfd_signal(struct file *file, unsigned int n);\n\nThe eventfd_fget() should be called to get a struct file* from an eventfd fd\n(this is an fget() + check of f_op being an eventfd fops pointer).\n\nThe kernel can then call eventfd_signal() every time it wants to post an event\nto userspace.  The eventfd_signal() function can be called from any context.\nAn eventfd() simple test and bench is available here:\n\nhttp://www.xmailserver.org/eventfd-bench.c\n\nThis is the eventfd-based version of pipetest-4 (pipe(2) based):\n\nhttp://www.xmailserver.org/pipetest-4.c\n\nNot that performance matters much in the eventfd case, but eventfd-bench\nshows almost as double as performance than pipetest-4.\n\n[akpm@linux-foundation.org: fix i386 build]\n[akpm@linux-foundation.org: add sys_eventfd to sys_ni.c]\nSigned-off-by: Davide Libenzi \u003cdavidel@xmailserver.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n"
    }
  ]
}