1. 07 Dec, 2007 2 commits
  2. 09 Nov, 2007 1 commit
  3. 07 Nov, 2007 2 commits
  4. 14 Oct, 2007 1 commit
  5. 11 Oct, 2007 2 commits
  6. 10 Oct, 2007 3 commits
  7. 16 Sep, 2007 2 commits
  8. 30 Aug, 2007 2 commits
  9. 01 Aug, 2007 5 commits
  10. 19 Jul, 2007 1 commit
  11. 06 Jul, 2007 2 commits
  12. 26 Jun, 2007 1 commit
    • Zach Brown's avatar
      SCTP: lock_sock_nested in sctp_sock_migrate · 5131a184
      Zach Brown authored
      
      
      sctp_sock_migrate() grabs the socket lock on a newly allocated socket while
      holding the socket lock on an old socket.  lockdep worries that this might
      be a recursive lock attempt.
      
       task/3026 is trying to acquire lock:
        (sk_lock-AF_INET){--..}, at: [<ffffffff88105b8c>] sctp_sock_migrate+0x2e3/0x327 [sctp]
       but task is already holding lock:
        (sk_lock-AF_INET){--..}, at: [<ffffffff8810891f>] sctp_accept+0xdf/0x1e3 [sctp]
      
      This patch tells lockdep that this locking is safe by using
      lock_sock_nested().
      Signed-off-by: default avatarZach Brown <zach.brown@oracle.com>
      Signed-off-by: default avatarVlad Yasevich <vladislav.yasevich@hp.com>
      5131a184
  13. 19 Jun, 2007 2 commits
    • Neil Horman's avatar
      SCTP: Fix sctp_getsockopt_get_peer_addrs · 186e2343
      Neil Horman authored
      
      
      	This is the split out of the patch that we agreed I should split
      out from my last patch.  It changes space_left to be computed in the same
      way the to variable is.  I know we talked about changing space_left to an
      int, but I think size_t is more appropriate, since we should never have
      negative space in our buffer, and computing using offsetof means space_left
      should now never drop below zero.
      Signed-off-by: default avatarNeil Horman <nhorman@tuxdriver.com>
      Acked-by: default avatarSridhar Samudrala <sri@us.ibm.com>
      Signed-off-by: default avatarVlad Yasevich <vladislav.yasevich@hp.com>
      186e2343
    • Neil Horman's avatar
      SCTP: update sctp_getsockopt helpers to allow oversized buffers · 408f22e8
      Neil Horman authored
      
      
      	I noted the other day while looking at a bug that was ostensibly
      in some perl networking library, that we strictly avoid allowing getsockopt
      operations to complete if we pass in oversized buffers.  This seems to make
      libraries like Perl::NET malfunction since it seems to allocate oversized
      buffers for use in several operations.  It also seems to be out of line with
      the way udp, tcp and ip getsockopt routines handle buffer input (since the
      *optlen pointer in both an input and an output and gets set to the length
      of the data that we copy into the buffer).  This patch brings our getsockopt
      helpers into line with other protocols, and allows us to accept oversized
      buffers for our getsockopt operations.  Tested by me with good results.
      Signed-off-by: default avatarNeil Horman <nhorman@tuxdriver.com>
      Acked-by: default avatarSridhar Samudrala <sri@us.ibm.com>
      Signed-off-by: default avatarVlad Yasevich <vladislav.yasevich@hp.com>
      408f22e8
  14. 13 Jun, 2007 4 commits
  15. 11 May, 2007 2 commits
  16. 09 May, 2007 1 commit
  17. 04 May, 2007 2 commits
  18. 29 Apr, 2007 1 commit
  19. 26 Apr, 2007 4 commits