Merge branch 'for-3.4' of git://linux-nfs.org/~bfields/linux

Pull nfsd changes from Bruce Fields:

Highlights:
 - Benny Halevy and Tigran Mkrtchyan implemented some more 4.1 features,
   moving us closer to a complete 4.1 implementation.
 - Bernd Schubert fixed a long-standing problem with readdir cookies on
   ext2/3/4.
 - Jeff Layton performed a long-overdue overhaul of the server reboot
   recovery code which will allow us to deprecate the current code (a
   rather unusual user of the vfs), and give us some needed flexibility
   for further improvements.
 - Like the client, we now support numeric uid's and gid's in the
   auth_sys case, allowing easier upgrades from NFSv2/v3 to v4.x.

Plus miscellaneous bugfixes and cleanup.

Thanks to everyone!

There are also some delegation fixes waiting on vfs review that I
suppose will have to wait for 3.5.  With that done I think we'll finally
turn off the "EXPERIMENTAL" dependency for v4 (though that's mostly
symbolic as it's been on by default in distro's for a while).

And the list of 4.1 todo's should be achievable for 3.5 as well:

   http://wiki.linux-nfs.org/wiki/index.php/Server_4.0_and_4.1_issues

though we may still want a bit more experience with it before turning it
on by default.

* 'for-3.4' of git://linux-nfs.org/~bfields/linux: (55 commits)
  nfsd: only register cld pipe notifier when CONFIG_NFSD_V4 is enabled
  nfsd4: use auth_unix unconditionally on backchannel
  nfsd: fix NULL pointer dereference in cld_pipe_downcall
  nfsd4: memory corruption in numeric_name_to_id()
  sunrpc: skip portmap calls on sessions backchannel
  nfsd4: allow numeric idmapping
  nfsd: don't allow legacy client tracker init for anything but init_net
  nfsd: add notifier to handle mount/unmount of rpc_pipefs sb
  nfsd: add the infrastructure to handle the cld upcall
  nfsd: add a header describing upcall to nfsdcld
  nfsd: add a per-net-namespace struct for nfsd
  sunrpc: create nfsd dir in rpc_pipefs
  nfsd: add nfsd4_client_tracking_ops struct and a way to set it
  nfsd: convert nfs4_client->cl_cb_flags to a generic flags field
  NFSD: Fix nfs4_verifier memory alignment
  NFSD: Fix warnings when NFSD_DEBUG is not defined
  nfsd: vfs_llseek() with 32 or 64 bit offsets (hashes)
  nfsd: rename 'int access' to 'int may_flags' in nfsd_open()
  ext4: return 32/64-bit dir name hash according to usage type
  fs: add new FMODE flags: FMODE_32bithash and FMODE_64bithash
  ...

11 files changed, 59 insertions, 83 deletions

diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index f21ece088764..de0b0f39d9d8 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -830,6 +830,8 @@ static ssize_t cache_do_downcall(char *kaddr, const char __user *buf,
 {
         ssize_t ret;
 
+        if (count == 0)
+                return -EINVAL;
         if (copy_from_user(kaddr, buf, count))
                 return -EFAULT;
         kaddr[count] = '\0';
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index c84c0e0c41cb..0af37fc46818 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -1014,6 +1014,7 @@ enum {
         RPCAUTH_statd,
         RPCAUTH_nfsd4_cb,
         RPCAUTH_cache,
+        RPCAUTH_nfsd,
         RPCAUTH_RootEOF
 };
 
@@ -1046,6 +1047,10 @@ static const struct rpc_filelist files[] = {
                 .name = "cache",
                 .mode = S_IFDIR | S_IRUGO | S_IXUGO,
         },
+        [RPCAUTH_nfsd] = {
+                .name = "nfsd",
+                .mode = S_IFDIR | S_IRUGO | S_IXUGO,
+        },
 };
 
 /*
diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c
index bcd574f2ac56..521d8f7dc833 100644
--- a/net/sunrpc/svcauth_unix.c
+++ b/net/sunrpc/svcauth_unix.c
@@ -507,7 +507,7 @@ static int unix_gid_parse(struct cache_detail *cd,
         time_t expiry;
         struct unix_gid ug, *ugp;
 
-        if (mlen <= 0 || mesg[mlen-1] != '\n')
+        if (mesg[mlen - 1] != '\n')
                 return -EINVAL;
         mesg[mlen-1] = 0;
 
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 40ae884db865..824d32fb3121 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1381,8 +1381,6 @@ void svc_sock_update_bufs(struct svc_serv *serv)
         spin_lock_bh(&serv->sv_lock);
         list_for_each_entry(svsk, &serv->sv_permsocks, sk_xprt.xpt_list)
                 set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags);
-        list_for_each_entry(svsk, &serv->sv_tempsocks, sk_xprt.xpt_list)
-                set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags);
         spin_unlock_bh(&serv->sv_lock);
 }
 EXPORT_SYMBOL_GPL(svc_sock_update_bufs);
diff --git a/net/sunrpc/xprtrdma/svc_rdma.c b/net/sunrpc/xprtrdma/svc_rdma.c
index 09af4fab1a45..8343737e85f4 100644
--- a/net/sunrpc/xprtrdma/svc_rdma.c
+++ b/net/sunrpc/xprtrdma/svc_rdma.c
@@ -47,6 +47,7 @@
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/sched.h>
 #include <linux/sunrpc/svc_rdma.h>
+#include "xprt_rdma.h"
 
 #define RPCDBG_FACILITY RPCDBG_SVCXPRT
 
diff --git a/net/sunrpc/xprtrdma/svc_rdma_marshal.c b/net/sunrpc/xprtrdma/svc_rdma_marshal.c
index 9530ef2d40dc..8d2edddf48cf 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_marshal.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_marshal.c
@@ -60,21 +60,11 @@ static u32 *decode_read_list(u32 *va, u32 *vaend)
         struct rpcrdma_read_chunk *ch = (struct rpcrdma_read_chunk *)va;
 
         while (ch->rc_discrim != xdr_zero) {
-                u64 ch_offset;
-
                 if (((unsigned long)ch + sizeof(struct rpcrdma_read_chunk)) >
                     (unsigned long)vaend) {
                         dprintk("svcrdma: vaend=%p, ch=%p\n", vaend, ch);
                         return NULL;
                 }
-
-                ch->rc_discrim = ntohl(ch->rc_discrim);
-                ch->rc_position = ntohl(ch->rc_position);
-                ch->rc_target.rs_handle = ntohl(ch->rc_target.rs_handle);
-                ch->rc_target.rs_length = ntohl(ch->rc_target.rs_length);
-                va = (u32 *)&ch->rc_target.rs_offset;
-                xdr_decode_hyper(va, &ch_offset);
-                put_unaligned(ch_offset, (u64 *)va);
                 ch++;
         }
         return (u32 *)&ch->rc_position;
@@ -91,7 +81,7 @@ void svc_rdma_rcl_chunk_counts(struct rpcrdma_read_chunk *ch,
         *byte_count = 0;
         *ch_count = 0;
         for (; ch->rc_discrim != 0; ch++) {
-                *byte_count = *byte_count + ch->rc_target.rs_length;
+                *byte_count = *byte_count + ntohl(ch->rc_target.rs_length);
                 *ch_count = *ch_count + 1;
         }
 }
@@ -108,7 +98,8 @@ void svc_rdma_rcl_chunk_counts(struct rpcrdma_read_chunk *ch,
  */
 static u32 *decode_write_list(u32 *va, u32 *vaend)
 {
-        int ch_no;
+        int nchunks;
+
         struct rpcrdma_write_array *ary =
                 (struct rpcrdma_write_array *)va;
 
@@ -121,37 +112,24 @@ static u32 *decode_write_list(u32 *va, u32 *vaend)
                 dprintk("svcrdma: ary=%p, vaend=%p\n", ary, vaend);
                 return NULL;
         }
-        ary->wc_discrim = ntohl(ary->wc_discrim);
-        ary->wc_nchunks = ntohl(ary->wc_nchunks);
+        nchunks = ntohl(ary->wc_nchunks);
         if (((unsigned long)&ary->wc_array[0] +
-             (sizeof(struct rpcrdma_write_chunk) * ary->wc_nchunks)) >
+             (sizeof(struct rpcrdma_write_chunk) * nchunks)) >
             (unsigned long)vaend) {
                 dprintk("svcrdma: ary=%p, wc_nchunks=%d, vaend=%p\n",
-                        ary, ary->wc_nchunks, vaend);
+                        ary, nchunks, vaend);
                 return NULL;
         }
-        for (ch_no = 0; ch_no < ary->wc_nchunks; ch_no++) {
-                u64 ch_offset;
-
-                ary->wc_array[ch_no].wc_target.rs_handle =
-                        ntohl(ary->wc_array[ch_no].wc_target.rs_handle);
-                ary->wc_array[ch_no].wc_target.rs_length =
-                        ntohl(ary->wc_array[ch_no].wc_target.rs_length);
-                va = (u32 *)&ary->wc_array[ch_no].wc_target.rs_offset;
-                xdr_decode_hyper(va, &ch_offset);
-                put_unaligned(ch_offset, (u64 *)va);
-        }
-
         /*
          * rs_length is the 2nd 4B field in wc_target and taking its
          * address skips the list terminator
          */
-        return (u32 *)&ary->wc_array[ch_no].wc_target.rs_length;
+        return (u32 *)&ary->wc_array[nchunks].wc_target.rs_length;
 }
 
 static u32 *decode_reply_array(u32 *va, u32 *vaend)
 {
-        int ch_no;
+        int nchunks;
         struct rpcrdma_write_array *ary =
                 (struct rpcrdma_write_array *)va;
 
@@ -164,28 +142,15 @@ static u32 *decode_reply_array(u32 *va, u32 *vaend)
                 dprintk("svcrdma: ary=%p, vaend=%p\n", ary, vaend);
                 return NULL;
         }
-        ary->wc_discrim = ntohl(ary->wc_discrim);
-        ary->wc_nchunks = ntohl(ary->wc_nchunks);
+        nchunks = ntohl(ary->wc_nchunks);
         if (((unsigned long)&ary->wc_array[0] +
-             (sizeof(struct rpcrdma_write_chunk) * ary->wc_nchunks)) >
+             (sizeof(struct rpcrdma_write_chunk) * nchunks)) >
             (unsigned long)vaend) {
                 dprintk("svcrdma: ary=%p, wc_nchunks=%d, vaend=%p\n",
-                        ary, ary->wc_nchunks, vaend);
+                        ary, nchunks, vaend);
                 return NULL;
         }
-        for (ch_no = 0; ch_no < ary->wc_nchunks; ch_no++) {
-                u64 ch_offset;
-
-                ary->wc_array[ch_no].wc_target.rs_handle =
-                        ntohl(ary->wc_array[ch_no].wc_target.rs_handle);
-                ary->wc_array[ch_no].wc_target.rs_length =
-                        ntohl(ary->wc_array[ch_no].wc_target.rs_length);
-                va = (u32 *)&ary->wc_array[ch_no].wc_target.rs_offset;
-                xdr_decode_hyper(va, &ch_offset);
-                put_unaligned(ch_offset, (u64 *)va);
-        }
-
-        return (u32 *)&ary->wc_array[ch_no];
+        return (u32 *)&ary->wc_array[nchunks];
 }
 
 int svc_rdma_xdr_decode_req(struct rpcrdma_msg **rdma_req,
@@ -386,13 +351,14 @@ void svc_rdma_xdr_encode_reply_array(struct rpcrdma_write_array *ary,
 
 void svc_rdma_xdr_encode_array_chunk(struct rpcrdma_write_array *ary,
                                      int chunk_no,
-                                     u32 rs_handle, u64 rs_offset,
+                                     __be32 rs_handle,
+                                     __be64 rs_offset,
                                      u32 write_len)
 {
         struct rpcrdma_segment *seg = &ary->wc_array[chunk_no].wc_target;
-        seg->rs_handle = htonl(rs_handle);
+        seg->rs_handle = rs_handle;
+        seg->rs_offset = rs_offset;
         seg->rs_length = htonl(write_len);
-        xdr_encode_hyper((u32 *) &seg->rs_offset, rs_offset);
 }
 
 void svc_rdma_xdr_encode_reply_header(struct svcxprt_rdma *xprt,
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index df67211c4baf..41cb63b623df 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -147,7 +147,7 @@ static int map_read_chunks(struct svcxprt_rdma *xprt,
         page_off = 0;
         ch = (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0];
         ch_no = 0;
-        ch_bytes = ch->rc_target.rs_length;
+        ch_bytes = ntohl(ch->rc_target.rs_length);
         head->arg.head[0] = rqstp->rq_arg.head[0];
         head->arg.tail[0] = rqstp->rq_arg.tail[0];
         head->arg.pages = &head->pages[head->count];
@@ -183,7 +183,7 @@ static int map_read_chunks(struct svcxprt_rdma *xprt,
                         ch_no++;
                         ch++;
                         chl_map->ch[ch_no].start = sge_no;
-                        ch_bytes = ch->rc_target.rs_length;
+                        ch_bytes = ntohl(ch->rc_target.rs_length);
                         /* If bytes remaining account for next chunk */
                         if (byte_count) {
                                 head->arg.page_len += ch_bytes;
@@ -281,11 +281,12 @@ static int fast_reg_read_chunks(struct svcxprt_rdma *xprt,
         offset = 0;
         ch = (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0];
         for (ch_no = 0; ch_no < ch_count; ch_no++) {
+                int len = ntohl(ch->rc_target.rs_length);
                 rpl_map->sge[ch_no].iov_base = frmr->kva + offset;
-                rpl_map->sge[ch_no].iov_len = ch->rc_target.rs_length;
+                rpl_map->sge[ch_no].iov_len = len;
                 chl_map->ch[ch_no].count = 1;
                 chl_map->ch[ch_no].start = ch_no;
-                offset += ch->rc_target.rs_length;
+                offset += len;
                 ch++;
         }
 
@@ -316,7 +317,7 @@ static int rdma_set_ctxt_sge(struct svcxprt_rdma *xprt,
         for (i = 0; i < count; i++) {
                 ctxt->sge[i].length = 0; /* in case map fails */
                 if (!frmr) {
-                        BUG_ON(0 == virt_to_page(vec[i].iov_base));
+                        BUG_ON(!virt_to_page(vec[i].iov_base));
                         off = (unsigned long)vec[i].iov_base & ~PAGE_MASK;
                         ctxt->sge[i].addr =
                                 ib_dma_map_page(xprt->sc_cm_id->device,
@@ -426,6 +427,7 @@ static int rdma_read_xdr(struct svcxprt_rdma *xprt,
 
         for (ch = (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0];
              ch->rc_discrim != 0; ch++, ch_no++) {
+                u64 rs_offset;
 next_sge:
                 ctxt = svc_rdma_get_context(xprt);
                 ctxt->direction = DMA_FROM_DEVICE;
@@ -440,10 +442,10 @@ next_sge:
                 read_wr.opcode = IB_WR_RDMA_READ;
                 ctxt->wr_op = read_wr.opcode;
                 read_wr.send_flags = IB_SEND_SIGNALED;
-                read_wr.wr.rdma.rkey = ch->rc_target.rs_handle;
-                read_wr.wr.rdma.remote_addr =
-                        get_unaligned(&(ch->rc_target.rs_offset)) +
-                        sgl_offset;
+                read_wr.wr.rdma.rkey = ntohl(ch->rc_target.rs_handle);
+                xdr_decode_hyper((__be32 *)&ch->rc_target.rs_offset,
+                                 &rs_offset);
+                read_wr.wr.rdma.remote_addr = rs_offset + sgl_offset;
                 read_wr.sg_list = ctxt->sge;
                 read_wr.num_sge =
                         rdma_read_max_sge(xprt, chl_map->ch[ch_no].count);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index 249a835b703f..42eb7ba0b903 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -409,21 +409,21 @@ static int send_write_chunks(struct svcxprt_rdma *xprt,
                 u64 rs_offset;
 
                 arg_ch = &arg_ary->wc_array[chunk_no].wc_target;
-                write_len = min(xfer_len, arg_ch->rs_length);
+                write_len = min(xfer_len, ntohl(arg_ch->rs_length));
 
                 /* Prepare the response chunk given the length actually
                  * written */
-                rs_offset = get_unaligned(&(arg_ch->rs_offset));
+                xdr_decode_hyper((__be32 *)&arg_ch->rs_offset, &rs_offset);
                 svc_rdma_xdr_encode_array_chunk(res_ary, chunk_no,
-                                            arg_ch->rs_handle,
-                                            rs_offset,
-                                            write_len);
+                                                arg_ch->rs_handle,
+                                                arg_ch->rs_offset,
+                                                write_len);
                 chunk_off = 0;
                 while (write_len) {
                         int this_write;
                         this_write = min(write_len, max_write);
                         ret = send_write(xprt, rqstp,
-                                         arg_ch->rs_handle,
+                                         ntohl(arg_ch->rs_handle),
                                          rs_offset + chunk_off,
                                          xdr_off,
                                          this_write,
@@ -457,6 +457,7 @@ static int send_reply_chunks(struct svcxprt_rdma *xprt,
         u32 xdr_off;
         int chunk_no;
         int chunk_off;
+        int nchunks;
         struct rpcrdma_segment *ch;
         struct rpcrdma_write_array *arg_ary;
         struct rpcrdma_write_array *res_ary;
@@ -476,26 +477,27 @@ static int send_reply_chunks(struct svcxprt_rdma *xprt,
                 max_write = xprt->sc_max_sge * PAGE_SIZE;
 
         /* xdr offset starts at RPC message */
+        nchunks = ntohl(arg_ary->wc_nchunks);
         for (xdr_off = 0, chunk_no = 0;
-             xfer_len && chunk_no < arg_ary->wc_nchunks;
+             xfer_len && chunk_no < nchunks;
              chunk_no++) {
                 u64 rs_offset;
                 ch = &arg_ary->wc_array[chunk_no].wc_target;
-                write_len = min(xfer_len, ch->rs_length);
+                write_len = min(xfer_len, htonl(ch->rs_length));
 
                 /* Prepare the reply chunk given the length actually
                  * written */
-                rs_offset = get_unaligned(&(ch->rs_offset));
+                xdr_decode_hyper((__be32 *)&ch->rs_offset, &rs_offset);
                 svc_rdma_xdr_encode_array_chunk(res_ary, chunk_no,
-                                            ch->rs_handle, rs_offset,
-                                            write_len);
+                                                ch->rs_handle, ch->rs_offset,
+                                                write_len);
                 chunk_off = 0;
                 while (write_len) {
                         int this_write;
 
                         this_write = min(write_len, max_write);
                         ret = send_write(xprt, rqstp,
-                                         ch->rs_handle,
+                                         ntohl(ch->rs_handle),
                                          rs_offset + chunk_off,
                                          xdr_off,
                                          this_write,
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 894cb42db91d..73b428bef598 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -51,6 +51,7 @@
 #include <rdma/rdma_cm.h>
 #include <linux/sunrpc/svc_rdma.h>
 #include <linux/export.h>
+#include "xprt_rdma.h"
 
 #define RPCDBG_FACILITY RPCDBG_SVCXPRT
 
@@ -90,12 +91,6 @@ struct svc_xprt_class svc_rdma_class = {
         .xcl_max_payload = RPCSVC_MAXPAYLOAD_TCP,
 };
 
-/* WR context cache. Created in svc_rdma.c  */
-extern struct kmem_cache *svc_rdma_ctxt_cachep;
-
-/* Workqueue created in svc_rdma.c */
-extern struct workqueue_struct *svc_rdma_wq;
-
 struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *xprt)
 {
         struct svc_rdma_op_ctxt *ctxt;
@@ -150,9 +145,6 @@ void svc_rdma_put_context(struct svc_rdma_op_ctxt *ctxt, int free_pages)
         atomic_dec(&xprt->sc_ctxt_used);
 }
 
-/* Temporary NFS request map cache. Created in svc_rdma.c  */
-extern struct kmem_cache *svc_rdma_map_cachep;
-
 /*
  * Temporary NFS req mappings are shared across all transport
  * instances. These are short lived and should be bounded by the number
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index 08c5d5a128fc..9a66c95b5837 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -343,4 +343,11 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *);
  */
 int rpcrdma_marshal_req(struct rpc_rqst *);
 
+/* Temporary NFS request map cache. Created in svc_rdma.c  */
+extern struct kmem_cache *svc_rdma_map_cachep;
+/* WR context cache. Created in svc_rdma.c  */
+extern struct kmem_cache *svc_rdma_ctxt_cachep;
+/* Workqueue created in svc_rdma.c */
+extern struct workqueue_struct *svc_rdma_wq;
+
 #endif                          /* _LINUX_SUNRPC_XPRT_RDMA_H */
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 92bc5181dbeb..890b03f8d877 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -2475,6 +2475,7 @@ static struct rpc_xprt_ops xs_tcp_ops = {
 static struct rpc_xprt_ops bc_tcp_ops = {
         .reserve_xprt           = xprt_reserve_xprt,
         .release_xprt           = xprt_release_xprt,
+        .rpcbind                = xs_local_rpcbind,
         .buf_alloc              = bc_malloc,
         .buf_free               = bc_free,
         .send_request           = bc_send_request,