1. 02 9月, 2009 3 次提交
    • S
      [CIFS] Fix checkpatch warnings · ca43e3be
      Steve French 提交于
      Also update version number to 1.61
      Signed-off-by: NSteve French <sfrench@us.ibm.com>
      ca43e3be
    • S
      PATCH] cifs: fix broken mounts when a SSH tunnel is used (try #4) · bdb97adc
      Suresh Jayaraman 提交于
      One more try..
      
      It seems there is a regression that got introduced while Jeff fixed
      all the mount/umount races. While attempting to find whether a tcp
      session is already existing, we were not checking whether the "port"
      used are the same. When a second mount is attempted with a different
      "port=" option, it is being ignored. Because of this the cifs mounts
      that uses a SSH tunnel appears to be broken.
      
      Steps to reproduce:
      
      1. create 2 shares
      # SSH Tunnel a SMB session
      2. ssh -f -L 6111:127.0.0.1:445 root@localhost "sleep 86400"
      3. ssh -f -L 6222:127.0.0.1:445 root@localhost "sleep 86400"
      4. tcpdump -i lo 6111 &
      5. mkdir -p /mnt/mnt1
      6. mkdir -p /mnt/mnt2
      7. mount.cifs //localhost/a /mnt/mnt1 -o username=guest,ip=127.0.0.1,port=6111
      #(shows tcpdump activity on port 6111)
      8. mount.cifs //localhost/b /mnt/mnt2 -o username=guest,ip=127.0.0.1,port=6222
      #(shows tcpdump activity only on port 6111 and not on 6222
      
      Fix by adding a check to compare the port _only_ if the user tries to
      override the tcp port with "port=" option, before deciding that an
      existing tcp session is found. Also, clean up a bit by replacing
      if-else if by a switch statment while at it as suggested by Jeff.
      Reviewed-by: NJeff Layton <jlayton@redhat.com>
      Reviewed-by: NShirish Pargaonkar <shirishp@us.ibm.com>
      Signed-off-by: NSuresh Jayaraman <sjayaraman@suse.de>
      Signed-off-by: NSteve French <sfrench@us.ibm.com>
      bdb97adc
    • A
      [CIFS] Memory leak in ntlmv2 hash calculation · 1b3859bc
      Alexander Strakh 提交于
       in function calc_ntlmv2_hash memory is not released.
      1. If in the line 333 we successfully allocate memory and assign it to
      pctxt variable:
             pctxt = kmalloc(sizeof(struct HMACMD5Context), GFP_KERNEL);
      then we go to line 376 and exit wihout releasing memory pointed to by pctxt
      variable.
      
      Add a memory  releasing for pctxt variable before exit from function
      calc_ntlmv2_hash.
      Signed-off-by: NAlexander Strakh <strakh@ispras.ru>
      Signed-off-by: NSteve French <sfrench@us.ibm.com>
      1b3859bc
  2. 31 8月, 2009 1 次提交
  3. 08 8月, 2009 36 次提交