I have been investigating a module reference count leak on the server for
rpcsec_gss_krb5.ko. It turns out the problem is a reference count leak for
the security context in net/sunrpc/auth_gss/svcauth_gss.c.
The problem is that gss_write_init_verf() calls gss_svc_searchbyctx() which
does a rsc_lookup() but never releases the reference to the context. There is
another issue that rpc.svcgssd sets an "end of time" expiration for the
context
By adding a cache_put() call in gss_svc_searchbyctx(), and setting an
expiration timeout in the downcall, cache_clean() does clean up the context
and the module reference count now goes to zero after unmount.
I also verified that if the context expires and then the client makes a new
request, a new context is established.
Here is the patch to fix the kernel, I will start a separate thread to discuss
what expiration time should be set by rpc.svcgssd.
Acked-by: "J. Bruce Fields" <bfields@citi.umich.edu>
Signed-off-by: Frank Filz <ffilzlnx@us.ibm.com>
Signed-off-by: Neil Brown <neilb@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
gss_write_init_verf(struct svc_rqst *rqstp, struct rsi *rsip)
{
struct rsc *rsci;
+ int rc;
if (rsip->major_status != GSS_S_COMPLETE)
return gss_write_null_verf(rqstp);
rsip->major_status = GSS_S_NO_CONTEXT;
return gss_write_null_verf(rqstp);
}
- return gss_write_verf(rqstp, rsci->mechctx, GSS_SEQ_WIN);
+ rc = gss_write_verf(rqstp, rsci->mechctx, GSS_SEQ_WIN);
+ cache_put(&rsci->h, &rsc_cache);
+ return rc;
}
/*