linux-nfs.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: bfields@fieldses.org (J. Bruce Fields)
To: "J. Bruce Fields" <bfields@redhat.com>
Cc: Olga Kornievskaia <olga.kornievskaia@gmail.com>,
	Dan Carpenter <dan.carpenter@oracle.com>,
	linux-nfs <linux-nfs@vger.kernel.org>
Subject: Re: [bug report] NFSD: allow inter server COPY to have a STALE source server fh
Date: Fri, 6 Dec 2019 16:14:42 -0500	[thread overview]
Message-ID: <20191206211442.GB17524@fieldses.org> (raw)
In-Reply-To: <20191205023826.GA43279@pick.fieldses.org>

On Wed, Dec 04, 2019 at 09:38:26PM -0500, J. Bruce Fields wrote:
> So, stuff we could do:
> 
> 	- add an extra check of fh_export or something here.

So, I'm applying the following for now.

--b.

commit a0a906b965b0
Author: J. Bruce Fields <bfields@redhat.com>
Date:   Fri Dec 6 16:07:32 2019 -0500

    nfsd4: avoid NULL deference on strange COPY compounds
    
    With cross-server COPY we've introduced the possibility that the current
    or saved filehandle might not have fh_dentry/fh_export filled in, but we
    missed a place that assumed it was.  I think this could be triggered by
    a compound like:
    
            PUTFH(foreign filehandle)
            GETATTR
            SAVEFH
            COPY
    
    First, check_if_stalefh_allowed sets no_verify on the first (PUTFH) op.
    Then op_func = nfsd4_putfh runs and leaves current_fh->fh_export NULL.
    need_wrongsec_check returns true, since this PUTFH has OP_IS_PUTFH_LIKE
    set and GETATTR does not have OP_HANDLES_WRONGSEC set.
    
    We should probably also consider tightening the checks in
    check_if_stalefh_allowed and double-checking that we don't assume the
    filehandle is verified elsewhere in the compound.  But I think this
    fixes the immediate issue.
    
    Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
    Fixes: 4e48f1cccab3 "NFSD: allow inter server COPY to have... "
    Signed-off-by: J. Bruce Fields <bfields@redhat.com>

diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index d33c39c18cdd..5c7f622fed29 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -2368,7 +2368,8 @@ nfsd4_proc_compound(struct svc_rqst *rqstp)
 			if (op->opdesc->op_flags & OP_CLEAR_STATEID)
 				clear_current_stateid(cstate);
 
-			if (need_wrongsec_check(rqstp))
+			if (current->fh->fh_export &&
+					need_wrongsec_check(rqstp))
 				op->status = check_nfsd_access(current_fh->fh_export, rqstp);
 		}
 encode_op:

  reply	other threads:[~2019-12-06 21:14 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-12-04  8:00 [bug report] NFSD: allow inter server COPY to have a STALE source server fh Dan Carpenter
2019-12-04 20:11 ` Olga Kornievskaia
2019-12-04 22:04   ` J. Bruce Fields
2019-12-05  2:38     ` J. Bruce Fields
2019-12-06 21:14       ` J. Bruce Fields [this message]
2019-12-06 21:15         ` J. Bruce Fields
2019-12-06 21:27           ` Olga Kornievskaia

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20191206211442.GB17524@fieldses.org \
    --to=bfields@fieldses.org \
    --cc=bfields@redhat.com \
    --cc=dan.carpenter@oracle.com \
    --cc=linux-nfs@vger.kernel.org \
    --cc=olga.kornievskaia@gmail.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).