path: root/fs/cifs/cifs_spnego.c
diff options
authorSuresh Jayaraman <sjayaraman@suse.de>2009-08-20 13:03:34 +0530
committerSteve French <sfrench@us.ibm.com>2009-09-01 17:08:48 +0000
commitbdb97adcdf0993adbd2eef44b4533620d43792de (patch)
tree5d2a120233c93d6a372d26d5ce3fc6cb6525fa6e /fs/cifs/cifs_spnego.c
parent1b3859bc9e20d764316346665fc93ecea2d2b176 (diff)
PATCH] cifs: fix broken mounts when a SSH tunnel is used (try #4)
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: root@localhost "sleep 86400" 3. ssh -f -L 6222: 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=,port=6111 #(shows tcpdump activity on port 6111) 8. mount.cifs //localhost/b /mnt/mnt2 -o username=guest,ip=,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: Jeff Layton <jlayton@redhat.com> Reviewed-by: Shirish Pargaonkar <shirishp@us.ibm.com> Signed-off-by: Suresh Jayaraman <sjayaraman@suse.de> Signed-off-by: Steve French <sfrench@us.ibm.com>
Diffstat (limited to 'fs/cifs/cifs_spnego.c')
0 files changed, 0 insertions, 0 deletions