diff options
| author | Stefan Metzmacher <metze@samba.org> | 2012-06-13 12:13:01 +0200 |
|---|---|---|
| committer | Stefan Metzmacher <metze@samba.org> | 2012-06-14 22:04:10 +0200 |
| commit | 3f110e50bfdbaf6958c12098e06ef599341d7e3b (patch) | |
| tree | 7c036e9a07bf555559418269de9e49dc1273f0c1 /source3/smbd/files.c | |
| parent | 47f837c105ee7b70b7e80e41772b7c9470bbe153 (diff) | |
| download | samba-3f110e50bfdbaf6958c12098e06ef599341d7e3b.tar.gz samba-3f110e50bfdbaf6958c12098e06ef599341d7e3b.tar.bz2 samba-3f110e50bfdbaf6958c12098e06ef599341d7e3b.zip | |
s3:smbd: use fsp_persistent_id() as persistent_file_id part for SMB2 (bug #8995)
It seems to be important to have unique persistent file ids,
because windows clients seem to index files by server_guid + persistent_file_id.
Which may break, if we just have a 16-bit range per connection
and the client connects multiple times.
Based on code from Ira Cooper. Use fsp->fh->gen_id as the persistent
fileid in SMB2.
metze
Autobuild-User(master): Stefan Metzmacher <metze@samba.org>
Autobuild-Date(master): Thu Jun 14 22:04:13 CEST 2012 on sn-devel-104
Diffstat (limited to 'source3/smbd/files.c')
| -rw-r--r-- | source3/smbd/files.c | 10 |
1 files changed, 6 insertions, 4 deletions
diff --git a/source3/smbd/files.c b/source3/smbd/files.c index 18330805d8..d410083009 100644 --- a/source3/smbd/files.c +++ b/source3/smbd/files.c @@ -626,15 +626,12 @@ struct files_struct *file_fsp_smb2(struct smbd_smb2_request *smb2req, uint64_t volatile_id) { struct files_struct *fsp; + uint64_t fsp_persistent; if (smb2req->compat_chain_fsp != NULL) { return smb2req->compat_chain_fsp; } - if (persistent_id != volatile_id) { - return NULL; - } - if (volatile_id > UINT16_MAX) { return NULL; } @@ -643,6 +640,11 @@ struct files_struct *file_fsp_smb2(struct smbd_smb2_request *smb2req, if (fsp == NULL) { return NULL; } + fsp_persistent = fsp_persistent_id(fsp); + + if (persistent_id != fsp_persistent) { + return NULL; + } if (smb2req->tcon == NULL) { return NULL; |