Skip to content

K
kernel_linux

OpenHarmony / kernel_linux
上一次同步 3 年多

通知 13
Star 8
Fork 2
K
kernel_linux
切换分支/标签
  1. 26 7月, 2008 3 次提交
  3. 25 7月, 2008 8 次提交
    • H
      ipsec: ipcomp - Decompress into frags if necessary · 7d7e5a60
      由 Herbert Xu 提交于 
      When decompressing extremely large packets allocating them through
kmalloc is prone to failure.  Therefore it's better to use page
frags instead.
Signed-off-by: NHerbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      7d7e5a60
    • H
      ipsec: ipcomp - Merge IPComp implementations · 6fccab67
      由 Herbert Xu 提交于 
      This patch merges the IPv4/IPv6 IPComp implementations since most
of the code is identical.  As a result future enhancements will no
longer need to be duplicated.
Signed-off-by: NHerbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      6fccab67
    • D
      pkt_sched: Fix locking in shutdown_scheduler_queue() · cffe1c5d
      由 David S. Miller 提交于 
      Qdisc locks need to be held with BH disabled.
Tested-by: NIngo Molnar <mingo@elte.hu>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      cffe1c5d
    • U
      flag parameters: check magic constants · e38b36f3
      由 Ulrich Drepper 提交于 
      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: NUlrich Drepper <drepper@redhat.com>
Acked-by: NDavide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@googlemail.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      e38b36f3
    • U
      flag parameters: NONBLOCK in socket and socketpair · 77d27200
      由 Ulrich Drepper 提交于 
      This patch introduces support for the SOCK_NONBLOCK flag in socket,
socketpair, and  paccept.  To do this the internal function sock_attach_fd
gets an additional parameter which it uses to set the appropriate flag for
the file descriptor.

Given that in modern, scalable programs almost all socket connections are
non-blocking and the minimal additional cost for the new functionality
I see no reason not to add this code.

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 <pthread.h>
#include <stdio.h>
#include <unistd.h>
#include <netinet/in.h>
#include <sys/socket.h>
#include <sys/syscall.h>

#ifndef __NR_paccept
# ifdef __x86_64__
#  define __NR_paccept 288
# elif defined __i386__
#  define SYS_PACCEPT 18
#  define USE_SOCKETCALL 1
# else
#  error "need __NR_paccept"
# endif
#endif

#ifdef USE_SOCKETCALL
# define paccept(fd, addr, addrlen, mask, flags) \
  ({ long args[6] = { \
       (long) fd, (long) addr, (long) addrlen, (long) mask, 8, (long) flags }; \
     syscall (__NR_socketcall, SYS_PACCEPT, args); })
#else
# define paccept(fd, addr, addrlen, mask, flags) \
  syscall (__NR_paccept, fd, addr, addrlen, mask, 8, flags)
#endif

#define PORT 57392

#define SOCK_NONBLOCK O_NONBLOCK

static pthread_barrier_t b;

static void *
tf (void *arg)
{
  pthread_barrier_wait (&b);
  int s = socket (AF_INET, SOCK_STREAM, 0);
  struct sockaddr_in sin;
  sin.sin_family = AF_INET;
  sin.sin_addr.s_addr = htonl (INADDR_LOOPBACK);
  sin.sin_port = htons (PORT);
  connect (s, (const struct sockaddr *) &sin, sizeof (sin));
  close (s);
  pthread_barrier_wait (&b);

  pthread_barrier_wait (&b);
  s = socket (AF_INET, SOCK_STREAM, 0);
  sin.sin_port = htons (PORT);
  connect (s, (const struct sockaddr *) &sin, sizeof (sin));
  close (s);
  pthread_barrier_wait (&b);

  return NULL;
}

int
main (void)
{
  int fd;
  fd = socket (PF_INET, SOCK_STREAM, 0);
  if (fd == -1)
    {
      puts ("socket(0) failed");
      return 1;
    }
  int fl = fcntl (fd, F_GETFL);
  if (fl == -1)
    {
      puts ("fcntl failed");
      return 1;
    }
  if (fl & O_NONBLOCK)
    {
      puts ("socket(0) set non-blocking mode");
      return 1;
    }
  close (fd);

  fd = socket (PF_INET, SOCK_STREAM|SOCK_NONBLOCK, 0);
  if (fd == -1)
    {
      puts ("socket(SOCK_NONBLOCK) failed");
      return 1;
    }
  fl = fcntl (fd, F_GETFL);
  if (fl == -1)
    {
      puts ("fcntl failed");
      return 1;
    }
  if ((fl & O_NONBLOCK) == 0)
    {
      puts ("socket(SOCK_NONBLOCK) does not set non-blocking mode");
      return 1;
    }
  close (fd);

  int fds[2];
  if (socketpair (PF_UNIX, SOCK_STREAM, 0, fds) == -1)
    {
      puts ("socketpair(0) failed");
      return 1;
    }
  for (int i = 0; i < 2; ++i)
    {
      fl = fcntl (fds[i], F_GETFL);
      if (fl == -1)
        {
          puts ("fcntl failed");
          return 1;
        }
      if (fl & O_NONBLOCK)
        {
          printf ("socketpair(0) set non-blocking mode for fds[%d]\n", i);
          return 1;
        }
      close (fds[i]);
    }

  if (socketpair (PF_UNIX, SOCK_STREAM|SOCK_NONBLOCK, 0, fds) == -1)
    {
      puts ("socketpair(SOCK_NONBLOCK) failed");
      return 1;
    }
  for (int i = 0; i < 2; ++i)
    {
      fl = fcntl (fds[i], F_GETFL);
      if (fl == -1)
        {
          puts ("fcntl failed");
          return 1;
        }
      if ((fl & O_NONBLOCK) == 0)
        {
          printf ("socketpair(SOCK_NONBLOCK) does not set non-blocking mode for fds[%d]\n", i);
          return 1;
        }
      close (fds[i]);
    }

  pthread_barrier_init (&b, NULL, 2);

  struct sockaddr_in sin;
  pthread_t th;
  if (pthread_create (&th, NULL, tf, NULL) != 0)
    {
      puts ("pthread_create failed");
      return 1;
    }

  int s = socket (AF_INET, SOCK_STREAM, 0);
  int reuse = 1;
  setsockopt (s, SOL_SOCKET, SO_REUSEADDR, &reuse, sizeof (reuse));
  sin.sin_family = AF_INET;
  sin.sin_addr.s_addr = htonl (INADDR_LOOPBACK);
  sin.sin_port = htons (PORT);
  bind (s, (struct sockaddr *) &sin, sizeof (sin));
  listen (s, SOMAXCONN);

  pthread_barrier_wait (&b);

  int s2 = paccept (s, NULL, 0, NULL, 0);
  if (s2 < 0)
    {
      puts ("paccept(0) failed");
      return 1;
    }

  fl = fcntl (s2, F_GETFL);
  if (fl & O_NONBLOCK)
    {
      puts ("paccept(0) set non-blocking mode");
      return 1;
    }
  close (s2);
  close (s);

  pthread_barrier_wait (&b);

  s = socket (AF_INET, SOCK_STREAM, 0);
  sin.sin_port = htons (PORT);
  setsockopt (s, SOL_SOCKET, SO_REUSEADDR, &reuse, sizeof (reuse));
  bind (s, (struct sockaddr *) &sin, sizeof (sin));
  listen (s, SOMAXCONN);

  pthread_barrier_wait (&b);

  s2 = paccept (s, NULL, 0, NULL, SOCK_NONBLOCK);
  if (s2 < 0)
    {
      puts ("paccept(SOCK_NONBLOCK) failed");
      return 1;
    }

  fl = fcntl (s2, F_GETFL);
  if ((fl & O_NONBLOCK) == 0)
    {
      puts ("paccept(SOCK_NONBLOCK) does not set non-blocking mode");
      return 1;
    }
  close (s2);
  close (s);

  pthread_barrier_wait (&b);
  puts ("OK");

  return 0;
}
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Signed-off-by: NUlrich Drepper <drepper@redhat.com>
Acked-by: NDavide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@googlemail.com>
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      77d27200
    • U
      flag parameters: paccept w/out set_restore_sigmask · c019bbc6
      由 Ulrich Drepper 提交于 
      Some platforms do not have support to restore the signal mask in the
return path from a syscall.  For those platforms syscalls like pselect are
not defined at all.  This is, I think, not a good choice for paccept()
since paccept() adds more value on top of accept() than just the signal
mask handling.

Therefore this patch defines a scaled down version of the sys_paccept
function for those platforms.  It returns -EINVAL in case the signal mask
is non-NULL but behaves the same otherwise.

Note that I explicitly included <linux/thread_info.h>.  I saw that it is
currently included but indirectly two levels down.  There is too much risk
in relying on this.  The header might change and then suddenly the
function definition would change without anyone immediately noticing.
Signed-off-by: NUlrich Drepper <drepper@redhat.com>
Cc: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@googlemail.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      c019bbc6
    • U
      flag parameters: paccept · aaca0bdc
      由 Ulrich Drepper 提交于 
      This patch is by far the most complex in the series.  It adds a new syscall
paccept.  This syscall differs from accept in that it adds (at the userlevel)
two additional parameters:

- a signal mask
- a flags value

The flags parameter can be used to set flag like SOCK_CLOEXEC.  This is
imlpemented here as well.  Some people argued that this is a property which
should be inherited from the file desriptor for the server but this is against
POSIX.  Additionally, we really want the signal mask parameter as well
(similar to pselect, ppoll, etc).  So an interface change in inevitable.

The flag value is the same as for socket and socketpair.  I think diverging
here will only create confusion.  Similar to the filesystem interfaces where
the use of the O_* constants differs, it is acceptable here.

The signal mask is handled as for pselect etc.  The mask is temporarily
installed for the thread and removed before the call returns.  I modeled the
code after pselect.  If there is a problem it's likely also in pselect.

For architectures which use socketcall I maintained this interface instead of
adding a system call.  The symmetry shouldn't be broken.

The following test must be adjusted for architectures other than x86 and
x86-64 and in case the syscall numbers changed.

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#include <errno.h>
#include <fcntl.h>
#include <pthread.h>
#include <signal.h>
#include <stdio.h>
#include <unistd.h>
#include <netinet/in.h>
#include <sys/socket.h>
#include <sys/syscall.h>

#ifndef __NR_paccept
# ifdef __x86_64__
#  define __NR_paccept 288
# elif defined __i386__
#  define SYS_PACCEPT 18
#  define USE_SOCKETCALL 1
# else
#  error "need __NR_paccept"
# endif
#endif

#ifdef USE_SOCKETCALL
# define paccept(fd, addr, addrlen, mask, flags) \
  ({ long args[6] = { \
       (long) fd, (long) addr, (long) addrlen, (long) mask, 8, (long) flags }; \
     syscall (__NR_socketcall, SYS_PACCEPT, args); })
#else
# define paccept(fd, addr, addrlen, mask, flags) \
  syscall (__NR_paccept, fd, addr, addrlen, mask, 8, flags)
#endif

#define PORT 57392

#define SOCK_CLOEXEC O_CLOEXEC

static pthread_barrier_t b;

static void *
tf (void *arg)
{
  pthread_barrier_wait (&b);
  int s = socket (AF_INET, SOCK_STREAM, 0);
  struct sockaddr_in sin;
  sin.sin_family = AF_INET;
  sin.sin_addr.s_addr = htonl (INADDR_LOOPBACK);
  sin.sin_port = htons (PORT);
  connect (s, (const struct sockaddr *) &sin, sizeof (sin));
  close (s);

  pthread_barrier_wait (&b);
  s = socket (AF_INET, SOCK_STREAM, 0);
  sin.sin_port = htons (PORT);
  connect (s, (const struct sockaddr *) &sin, sizeof (sin));
  close (s);
  pthread_barrier_wait (&b);

  pthread_barrier_wait (&b);
  sleep (2);
  pthread_kill ((pthread_t) arg, SIGUSR1);

  return NULL;
}

static void
handler (int s)
{
}

int
main (void)
{
  pthread_barrier_init (&b, NULL, 2);

  struct sockaddr_in sin;
  pthread_t th;
  if (pthread_create (&th, NULL, tf, (void *) pthread_self ()) != 0)
    {
      puts ("pthread_create failed");
      return 1;
    }

  int s = socket (AF_INET, SOCK_STREAM, 0);
  int reuse = 1;
  setsockopt (s, SOL_SOCKET, SO_REUSEADDR, &reuse, sizeof (reuse));
  sin.sin_family = AF_INET;
  sin.sin_addr.s_addr = htonl (INADDR_LOOPBACK);
  sin.sin_port = htons (PORT);
  bind (s, (struct sockaddr *) &sin, sizeof (sin));
  listen (s, SOMAXCONN);

  pthread_barrier_wait (&b);

  int s2 = paccept (s, NULL, 0, NULL, 0);
  if (s2 < 0)
    {
      puts ("paccept(0) failed");
      return 1;
    }

  int coe = fcntl (s2, F_GETFD);
  if (coe & FD_CLOEXEC)
    {
      puts ("paccept(0) set close-on-exec-flag");
      return 1;
    }
  close (s2);

  pthread_barrier_wait (&b);

  s2 = paccept (s, NULL, 0, NULL, SOCK_CLOEXEC);
  if (s2 < 0)
    {
      puts ("paccept(SOCK_CLOEXEC) failed");
      return 1;
    }

  coe = fcntl (s2, F_GETFD);
  if ((coe & FD_CLOEXEC) == 0)
    {
      puts ("paccept(SOCK_CLOEXEC) does not set close-on-exec flag");
      return 1;
    }
  close (s2);

  pthread_barrier_wait (&b);

  struct sigaction sa;
  sa.sa_handler = handler;
  sa.sa_flags = 0;
  sigemptyset (&sa.sa_mask);
  sigaction (SIGUSR1, &sa, NULL);

  sigset_t ss;
  pthread_sigmask (SIG_SETMASK, NULL, &ss);
  sigaddset (&ss, SIGUSR1);
  pthread_sigmask (SIG_SETMASK, &ss, NULL);

  sigdelset (&ss, SIGUSR1);
  alarm (4);
  pthread_barrier_wait (&b);

  errno = 0 ;
  s2 = paccept (s, NULL, 0, &ss, 0);
  if (s2 != -1 || errno != EINTR)
    {
      puts ("paccept did not fail with EINTR");
      return 1;
    }

  close (s);

  puts ("OK");

  return 0;
}
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

[akpm@linux-foundation.org: make it compile]
[akpm@linux-foundation.org: add sys_ni stub]
Signed-off-by: NUlrich Drepper <drepper@redhat.com>
Acked-by: NDavide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@googlemail.com>
Cc: <linux-arch@vger.kernel.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Roland McGrath <roland@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      aaca0bdc
    • U
      flag parameters: socket and socketpair · a677a039
      由 Ulrich Drepper 提交于 
      This patch adds support for flag values which are ORed to the type passwd
to socket and socketpair.  The additional code is minimal.  The flag
values in this implementation can and must match the O_* flags.  This
avoids overhead in the conversion.

The internal functions sock_alloc_fd and sock_map_fd get a new parameters
and all callers are changed.

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#include <fcntl.h>
#include <stdio.h>
#include <unistd.h>
#include <netinet/in.h>
#include <sys/socket.h>

#define PORT 57392

/* For Linux these must be the same.  */
#define SOCK_CLOEXEC O_CLOEXEC

int
main (void)
{
  int fd;
  fd = socket (PF_INET, SOCK_STREAM, 0);
  if (fd == -1)
    {
      puts ("socket(0) failed");
      return 1;
    }
  int coe = fcntl (fd, F_GETFD);
  if (coe == -1)
    {
      puts ("fcntl failed");
      return 1;
    }
  if (coe & FD_CLOEXEC)
    {
      puts ("socket(0) set close-on-exec flag");
      return 1;
    }
  close (fd);

  fd = socket (PF_INET, SOCK_STREAM|SOCK_CLOEXEC, 0);
  if (fd == -1)
    {
      puts ("socket(SOCK_CLOEXEC) failed");
      return 1;
    }
  coe = fcntl (fd, F_GETFD);
  if (coe == -1)
    {
      puts ("fcntl failed");
      return 1;
    }
  if ((coe & FD_CLOEXEC) == 0)
    {
      puts ("socket(SOCK_CLOEXEC) does not set close-on-exec flag");
      return 1;
    }
  close (fd);

  int fds[2];
  if (socketpair (PF_UNIX, SOCK_STREAM, 0, fds) == -1)
    {
      puts ("socketpair(0) failed");
      return 1;
    }
  for (int i = 0; i < 2; ++i)
    {
      coe = fcntl (fds[i], F_GETFD);
      if (coe == -1)
        {
          puts ("fcntl failed");
          return 1;
        }
      if (coe & FD_CLOEXEC)
        {
          printf ("socketpair(0) set close-on-exec flag for fds[%d]\n", i);
          return 1;
        }
      close (fds[i]);
    }

  if (socketpair (PF_UNIX, SOCK_STREAM|SOCK_CLOEXEC, 0, fds) == -1)
    {
      puts ("socketpair(SOCK_CLOEXEC) failed");
      return 1;
    }
  for (int i = 0; i < 2; ++i)
    {
      coe = fcntl (fds[i], F_GETFD);
      if (coe == -1)
        {
          puts ("fcntl failed");
          return 1;
        }
      if ((coe & FD_CLOEXEC) == 0)
        {
          printf ("socketpair(SOCK_CLOEXEC) does not set close-on-exec flag for fds[%d]\n", i);
          return 1;
        }
      close (fds[i]);
    }

  puts ("OK");

  return 0;
}
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Signed-off-by: NUlrich Drepper <drepper@redhat.com>
Acked-by: NDavide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@googlemail.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      a677a039
  5. 24 7月, 2008 5 次提交
    • J
      pkt_sched: sch_sfq: dump a real number of flows · f867e6af
      由 Jarek Poplawski 提交于 
      Dump the "flows" number according to the number of active flows
instead of repeating the "limit".
Reported-by: NDenys Fedoryshchenko <denys@visp.net.lb>
Signed-off-by: NJarek Poplawski <jarkao2@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      f867e6af
    • P
      netfilter: make security table depend on NETFILTER_ADVANCED · 70eed75d
      由 Patrick McHardy 提交于 
      Signed-off-by: NPatrick McHardy <kaber@trash.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      70eed75d
    • D
      tcp: Clear probes_out more aggressively in tcp_ack(). · 4b53fb67
      由 David S. Miller 提交于 
      This is based upon an excellent bug report from Eric Dumazet.

tcp_ack() should clear ->icsk_probes_out even if there are packets
outstanding.  Otherwise if we get a sequence of ACKs while we do have
packets outstanding over and over again, we'll never clear the
probes_out value and eventually think the connection is too sick and
we'll reset it.

This appears to be some "optimization" added to tcp_ack() in the 2.4.x
timeframe.  In 2.2.x, probes_out is pretty much always cleared by
tcp_ack().

Here is Eric's original report:

----------------------------------------
Apparently, we can in some situations reset TCP connections in a couple of seconds when some frames are lost.

In order to reproduce the problem, please try the following program on linux-2.6.25.*

Setup some iptables rules to allow two frames per second sent on loopback interface to tcp destination port 12000

iptables -N SLOWLO
iptables -A SLOWLO -m hashlimit --hashlimit 2 --hashlimit-burst 1 --hashlimit-mode dstip --hashlimit-name slow2 -j ACCEPT
iptables -A SLOWLO -j DROP

iptables -A OUTPUT -o lo -p tcp --dport 12000 -j SLOWLO

Then run the attached program and see the output :

# ./loop
State      Recv-Q Send-Q                                  Local Address:Port                                    Peer Address:Port
ESTAB      0      40                                          127.0.0.1:54455                                      127.0.0.1:12000  timer:(persist,200ms,1)
State      Recv-Q Send-Q                                  Local Address:Port                                    Peer Address:Port
ESTAB      0      40                                          127.0.0.1:54455                                      127.0.0.1:12000  timer:(persist,200ms,3)
State      Recv-Q Send-Q                                  Local Address:Port                                    Peer Address:Port
ESTAB      0      40                                          127.0.0.1:54455                                      127.0.0.1:12000  timer:(persist,200ms,5)
State      Recv-Q Send-Q                                  Local Address:Port                                    Peer Address:Port
ESTAB      0      40                                          127.0.0.1:54455                                      127.0.0.1:12000  timer:(persist,200ms,7)
State      Recv-Q Send-Q                                  Local Address:Port                                    Peer Address:Port
ESTAB      0      40                                          127.0.0.1:54455                                      127.0.0.1:12000  timer:(persist,200ms,9)
State      Recv-Q Send-Q                                  Local Address:Port                                    Peer Address:Port
ESTAB      0      40                                          127.0.0.1:54455                                      127.0.0.1:12000  timer:(persist,200ms,11)
State      Recv-Q Send-Q                                  Local Address:Port                                    Peer Address:Port
ESTAB      0      40                                          127.0.0.1:54455                                      127.0.0.1:12000  timer:(persist,201ms,13)
State      Recv-Q Send-Q                                  Local Address:Port                                    Peer Address:Port
ESTAB      0      40                                          127.0.0.1:54455                                      127.0.0.1:12000  timer:(persist,188ms,15)
write(): Connection timed out
wrote 890 bytes but was interrupted after 9 seconds
ESTAB      0      0                 127.0.0.1:12000            127.0.0.1:54455
Exiting read() because no data available (4000 ms timeout).
read 860 bytes

While this tcp session makes progress (sending frames with 50 bytes of payload, every 500ms), linux tcp stack decides to reset it, when tcp_retries 2 is reached (default value : 15)

tcpdump :

15:30:28.856695 IP 127.0.0.1.56554 > 127.0.0.1.12000: S 33788768:33788768(0) win 32792 <mss 16396,nop,nop,sackOK,nop,wscale 7>
15:30:28.856711 IP 127.0.0.1.12000 > 127.0.0.1.56554: S 33899253:33899253(0) ack 33788769 win 32792 <mss 16396,nop,nop,sackOK,nop,wscale 7>
15:30:29.356947 IP 127.0.0.1.56554 > 127.0.0.1.12000: P 1:61(60) ack 1 win 257
15:30:29.356966 IP 127.0.0.1.12000 > 127.0.0.1.56554: . ack 61 win 257
15:30:29.866415 IP 127.0.0.1.56554 > 127.0.0.1.12000: P 61:111(50) ack 1 win 257
15:30:29.866427 IP 127.0.0.1.12000 > 127.0.0.1.56554: . ack 111 win 257
15:30:30.366516 IP 127.0.0.1.56554 > 127.0.0.1.12000: P 111:161(50) ack 1 win 257
15:30:30.366527 IP 127.0.0.1.12000 > 127.0.0.1.56554: . ack 161 win 257
15:30:30.876196 IP 127.0.0.1.56554 > 127.0.0.1.12000: P 161:211(50) ack 1 win 257
15:30:30.876207 IP 127.0.0.1.12000 > 127.0.0.1.56554: . ack 211 win 257
15:30:31.376282 IP 127.0.0.1.56554 > 127.0.0.1.12000: P 211:261(50) ack 1 win 257
15:30:31.376290 IP 127.0.0.1.12000 > 127.0.0.1.56554: . ack 261 win 257
15:30:31.885619 IP 127.0.0.1.56554 > 127.0.0.1.12000: P 261:311(50) ack 1 win 257
15:30:31.885631 IP 127.0.0.1.12000 > 127.0.0.1.56554: . ack 311 win 257
15:30:32.385705 IP 127.0.0.1.56554 > 127.0.0.1.12000: P 311:361(50) ack 1 win 257
15:30:32.385715 IP 127.0.0.1.12000 > 127.0.0.1.56554: . ack 361 win 257
15:30:32.895249 IP 127.0.0.1.56554 > 127.0.0.1.12000: P 361:411(50) ack 1 win 257
15:30:32.895266 IP 127.0.0.1.12000 > 127.0.0.1.56554: . ack 411 win 257
15:30:33.395341 IP 127.0.0.1.56554 > 127.0.0.1.12000: P 411:461(50) ack 1 win 257
15:30:33.395351 IP 127.0.0.1.12000 > 127.0.0.1.56554: . ack 461 win 257
15:30:33.918085 IP 127.0.0.1.56554 > 127.0.0.1.12000: P 461:511(50) ack 1 win 257
15:30:33.918096 IP 127.0.0.1.12000 > 127.0.0.1.56554: . ack 511 win 257
15:30:34.418163 IP 127.0.0.1.56554 > 127.0.0.1.12000: P 511:561(50) ack 1 win 257
15:30:34.418172 IP 127.0.0.1.12000 > 127.0.0.1.56554: . ack 561 win 257
15:30:34.927685 IP 127.0.0.1.56554 > 127.0.0.1.12000: P 561:611(50) ack 1 win 257
15:30:34.927698 IP 127.0.0.1.12000 > 127.0.0.1.56554: . ack 611 win 257
15:30:35.427757 IP 127.0.0.1.56554 > 127.0.0.1.12000: P 611:661(50) ack 1 win 257
15:30:35.427766 IP 127.0.0.1.12000 > 127.0.0.1.56554: . ack 661 win 257
15:30:35.937359 IP 127.0.0.1.56554 > 127.0.0.1.12000: P 661:711(50) ack 1 win 257
15:30:35.937376 IP 127.0.0.1.12000 > 127.0.0.1.56554: . ack 711 win 257
15:30:36.437451 IP 127.0.0.1.56554 > 127.0.0.1.12000: P 711:761(50) ack 1 win 257
15:30:36.437464 IP 127.0.0.1.12000 > 127.0.0.1.56554: . ack 761 win 257
15:30:36.947022 IP 127.0.0.1.56554 > 127.0.0.1.12000: P 761:811(50) ack 1 win 257
15:30:36.947039 IP 127.0.0.1.12000 > 127.0.0.1.56554: . ack 811 win 257
15:30:37.447135 IP 127.0.0.1.56554 > 127.0.0.1.12000: P 811:861(50) ack 1 win 257
15:30:37.447203 IP 127.0.0.1.12000 > 127.0.0.1.56554: . ack 861 win 257
15:30:41.448171 IP 127.0.0.1.12000 > 127.0.0.1.56554: F 1:1(0) ack 861 win 257
15:30:41.448189 IP 127.0.0.1.56554 > 127.0.0.1.12000: R 33789629:33789629(0) win 0

Source of program :

/*
 * small producer/consumer program.
 * setup a listener on 127.0.0.1:12000
 * Forks a child
 *   child connect to 127.0.0.1, and sends 10 bytes on this tcp socket every 100 ms
 * Father accepts connection, and read all data
 */
#include <sys/types.h>
#include <sys/socket.h>
#include <netinet/in.h>
#include <unistd.h>
#include <stdio.h>
#include <time.h>
#include <sys/poll.h>

int port = 12000;
char buffer[4096];
int main(int argc, char *argv[])
{
        int lfd = socket(AF_INET, SOCK_STREAM, 0);
        struct sockaddr_in socket_address;
        time_t t0, t1;
        int on = 1, sfd, res;
        unsigned long total = 0;
        socklen_t alen = sizeof(socket_address);
        pid_t pid;

        time(&t0);
        socket_address.sin_family = AF_INET;
        socket_address.sin_port = htons(port);
        socket_address.sin_addr.s_addr = htonl(INADDR_LOOPBACK);

        if (lfd == -1) {
                perror("socket()");
                return 1;
        }
        setsockopt(lfd, SOL_SOCKET, SO_REUSEADDR, &on, sizeof(int));
        if (bind(lfd, (struct sockaddr *)&socket_address, sizeof(socket_address)) == -1) {
                perror("bind");
                close(lfd);
                return 1;
        }
        if (listen(lfd, 1) == -1) {
                perror("listen()");
                close(lfd);
                return 1;
        }
        pid = fork();
        if (pid == 0) {
                int i, cfd = socket(AF_INET, SOCK_STREAM, 0);
                close(lfd);
                if (connect(cfd, (struct sockaddr *)&socket_address, sizeof(socket_address)) == -1) {
                        perror("connect()");
                        return 1;
                        }
                for (i = 0 ; ;) {
                        res = write(cfd, "blablabla\n", 10);
                        if (res > 0) total += res;
                        else if (res == -1) {
                                perror("write()");
                                break;
                        } else break;
                        usleep(100000);
                        if (++i == 10) {
                                system("ss -on dst 127.0.0.1:12000");
                                i = 0;
                        }
                }
                time(&t1);
                fprintf(stderr, "wrote %lu bytes but was interrupted after %g seconds\n", total, difftime(t1, t0));
                system("ss -on | grep 127.0.0.1:12000");
                close(cfd);
                return 0;
        }
        sfd = accept(lfd, (struct sockaddr *)&socket_address, &alen);
        if (sfd == -1) {
                perror("accept");
                return 1;
        }
        close(lfd);
        while (1) {
                struct pollfd pfd[1];
                pfd[0].fd = sfd;
                pfd[0].events = POLLIN;
                if (poll(pfd, 1, 4000) == 0) {
                        fprintf(stderr, "Exiting read() because no data available (4000 ms timeout).\n");
                        break;
                }
                res = read(sfd, buffer, sizeof(buffer));
                if (res > 0) total += res;
                else if (res == 0) break;
                else perror("read()");
        }
        fprintf(stderr, "read %lu bytes\n", total);
        close(sfd);
        return 0;
}
----------------------------------------
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      4b53fb67
    • O
      net: Update entry in af_family_clock_key_strings · b4942af6
      由 Oliver Hartkopp 提交于 
      In the merge phase of the CAN subsystem the 
af_family_clock_key_strings[] have been added to sock.c in commit 
443aef0e 
(lockdep: fixup sk_callback_lock annotation). This trivial patch adds 
the missing name for address family 29 (AF_CAN).
Signed-off-by: NOliver Hartkopp <oliver@hartkopp.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      b4942af6
    • D
      netdev: Remove warning from __netif_schedule(). · 5b3ab1db
      由 David S. Miller 提交于 
      It isn't helping anything and we aren't going to be able to change all
the drivers that do queue wakeups in strange situations.

Just letting a noop_qdisc get scheduled will work because when
qdisc_run() executes via net_tx_work() it will simply find no packets
pending when it makes the ->dequeue() call in qdisc_restart.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      5b3ab1db
  7. 23 7月, 2008 12 次提交
  9. 22 7月, 2008 12 次提交