Merge tag 'nfs-for-3.6-2' of git://git.linux-nfs.org/projects/trondmy…

…/linux-nfs

Pull second wave of NFS client updates from Trond Myklebust:

 - Patches from Bryan to allow splitting of the NFSv2/v3/v4 code into
   separate modules.

 - Fix Oopses in the NFSv4 idmapper

 - Fix a deadlock whereby rpciod tries to allocate a new socket and ends
   up recursing into the NFS code due to memory reclaim.

 - Increase the number of permitted callback connections.

* tag 'nfs-for-3.6-2' of git://git.linux-nfs.org/projects/trondmy/linux-nfs:
  nfs: explicitly reject LOCK_MAND flock() requests
  nfs: increase number of permitted callback connections.
  SUNRPC: return negative value in case rpcbind client creation error
  NFS: Convert v4 into a module
  NFS: Convert v3 into a module
  NFS: Convert v2 into a module
  NFS: Keep module parameters in the generic NFS client
  NFS: Split out remaining NFS v4 inode functions
  NFS: Pass super operations and xattr handlers in the nfs_subversion
  NFS: Only initialize the ACL client in the v3 case
  NFS: Create a try_mount rpc op
  NFS: Remove the NFS v4 xdev mount function
  NFS: Add version registering framework
  NFS: Fix a number of bugs in the idmapper
  nfs: skip commit in releasepage if we're freeing memory for fs-related reasons
  sunrpc: clarify comments on rpc_make_runnable
  pnfsblock: bail out partial page IO

fs/nfs/Kconfig

@@ -30,7 +30,7 @@ config NFS_FS
 	  If unsure, say N.
 
 config NFS_V2
-	bool "NFS client support for NFS version 2"
+	tristate "NFS client support for NFS version 2"
 	depends on NFS_FS
 	default y
 	help
@@ -40,7 +40,7 @@ config NFS_V2
 	  If unsure, say Y.
 
 config NFS_V3
-	bool "NFS client support for NFS version 3"
+	tristate "NFS client support for NFS version 3"
 	depends on NFS_FS
 	default y
 	help
@@ -72,7 +72,7 @@ config NFS_V3_ACL
 	  If unsure, say N.
 
 config NFS_V4
-	bool "NFS client support for NFS version 4"
+	tristate "NFS client support for NFS version 4"
 	depends on NFS_FS
 	select SUNRPC_GSS
 	select KEYS

fs/nfs/Makefile

@@ -9,21 +9,22 @@ nfs-y 			:= client.o dir.o file.o getroot.o inode.o super.o \
 			   write.o namespace.o mount_clnt.o \
 			   dns_resolve.o cache_lib.o
 nfs-$(CONFIG_ROOT_NFS)	+= nfsroot.o
-nfs-$(CONFIG_NFS_V2)	+= proc.o nfs2xdr.o
-nfs-$(CONFIG_NFS_V3)	+= nfs3proc.o nfs3xdr.o
-nfs-$(CONFIG_NFS_V3_ACL)	+= nfs3acl.o
-nfs-$(CONFIG_NFS_V4)	+= nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o \
-			   nfs4super.o nfs4file.o delegation.o idmap.o \
-			   callback.o callback_xdr.o callback_proc.o \
-			   nfs4namespace.o nfs4getroot.o nfs4client.o
-nfs-$(CONFIG_NFS_V4_1)	+= pnfs.o pnfs_dev.o
+nfs-$(CONFIG_SYSCTL)	+= sysctl.o
+nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o
 
-ifeq ($(CONFIG_SYSCTL), y)
-nfs-y += sysctl.o
-nfs-$(CONFIG_NFS_V4) += nfs4sysctl.o
-endif
+obj-$(CONFIG_NFS_V2) += nfs2.o
+nfs2-y := nfs2super.o proc.o nfs2xdr.o
 
-nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o
+obj-$(CONFIG_NFS_V3) += nfs3.o
+nfs3-y := nfs3super.o nfs3client.o nfs3proc.o nfs3xdr.o
+nfs3-$(CONFIG_NFS_V3_ACL) += nfs3acl.o
+
+obj-$(CONFIG_NFS_V4) += nfs4.o
+nfs4-y := nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o nfs4super.o nfs4file.o \
+	  delegation.o idmap.o callback.o callback_xdr.o callback_proc.o \
+	  nfs4namespace.o nfs4getroot.o nfs4client.o
+nfs4-$(CONFIG_SYSCTL)	+= nfs4sysctl.o
+nfs4-$(CONFIG_NFS_V4_1)	+= pnfs.o pnfs_dev.o
 
 obj-$(CONFIG_PNFS_FILE_LAYOUT) += nfs_layout_nfsv41_files.o
 nfs_layout_nfsv41_files-y := nfs4filelayout.o nfs4filelayoutdev.o

fs/nfs/blocklayout/blocklayout.c

@@ -228,6 +228,14 @@ bl_end_par_io_read(void *data, int unused)
 	schedule_work(&rdata->task.u.tk_work);
 }
 
+static bool
+bl_check_alignment(u64 offset, u32 len, unsigned long blkmask)
+{
+	if ((offset & blkmask) || (len & blkmask))
+		return false;
+	return true;
+}
+
 static enum pnfs_try_status
 bl_read_pagelist(struct nfs_read_data *rdata)
 {
@@ -244,6 +252,9 @@ bl_read_pagelist(struct nfs_read_data *rdata)
 	dprintk("%s enter nr_pages %u offset %lld count %u\n", __func__,
 	       rdata->pages.npages, f_offset, (unsigned int)rdata->args.count);
 
+	if (!bl_check_alignment(f_offset, rdata->args.count, PAGE_CACHE_MASK))
+		goto use_mds;
+
 	par = alloc_parallel(rdata);
 	if (!par)
 		goto use_mds;
@@ -552,7 +563,7 @@ bl_write_pagelist(struct nfs_write_data *wdata, int sync)
 	struct bio *bio = NULL;
 	struct pnfs_block_extent *be = NULL, *cow_read = NULL;
 	sector_t isect, last_isect = 0, extent_length = 0;
-	struct parallel_io *par;
+	struct parallel_io *par = NULL;
 	loff_t offset = wdata->args.offset;
 	size_t count = wdata->args.count;
 	struct page **pages = wdata->args.pages;
@@ -563,6 +574,10 @@ bl_write_pagelist(struct nfs_write_data *wdata, int sync)
 	    NFS_SERVER(header->inode)->pnfs_blksize >> PAGE_CACHE_SHIFT;
 
 	dprintk("%s enter, %Zu@%lld\n", __func__, count, offset);
+	/* Check for alignment first */
+	if (!bl_check_alignment(offset, count, PAGE_CACHE_MASK))
+		goto out_mds;
+
 	/* At this point, wdata->pages is a (sequential) list of nfs_pages.
 	 * We want to write each, and if there is an error set pnfs_error
 	 * to have it redone using nfs.
@@ -996,14 +1011,32 @@ bl_clear_layoutdriver(struct nfs_server *server)
 	return 0;
 }
 
+static void
+bl_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
+{
+	if (!bl_check_alignment(req->wb_offset, req->wb_bytes, PAGE_CACHE_MASK))
+		nfs_pageio_reset_read_mds(pgio);
+	else
+		pnfs_generic_pg_init_read(pgio, req);
+}
+
+static void
+bl_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
+{
+	if (!bl_check_alignment(req->wb_offset, req->wb_bytes, PAGE_CACHE_MASK))
+		nfs_pageio_reset_write_mds(pgio);
+	else
+		pnfs_generic_pg_init_write(pgio, req);
+}
+
 static const struct nfs_pageio_ops bl_pg_read_ops = {
-	.pg_init = pnfs_generic_pg_init_read,
+	.pg_init = bl_pg_init_read,
 	.pg_test = pnfs_generic_pg_test,
 	.pg_doio = pnfs_generic_pg_readpages,
 };
 
 static const struct nfs_pageio_ops bl_pg_write_ops = {
-	.pg_init = pnfs_generic_pg_init_write,
+	.pg_init = bl_pg_init_write,
 	.pg_test = pnfs_generic_pg_test,
 	.pg_doio = pnfs_generic_pg_writepages,
 };

fs/nfs/callback.c

@@ -37,31 +37,7 @@ static struct nfs_callback_data nfs_callback_info[NFS4_MAX_MINOR_VERSION + 1];
 static DEFINE_MUTEX(nfs_callback_mutex);
 static struct svc_program nfs4_callback_program;
 
-unsigned int nfs_callback_set_tcpport;
-unsigned short nfs_callback_tcpport;
 unsigned short nfs_callback_tcpport6;
-#define NFS_CALLBACK_MAXPORTNR (65535U)
-
-static int param_set_portnr(const char *val, const struct kernel_param *kp)
-{
-	unsigned long num;
-	int ret;
-
-	if (!val)
-		return -EINVAL;
-	ret = strict_strtoul(val, 0, &num);
-	if (ret == -EINVAL || num > NFS_CALLBACK_MAXPORTNR)
-		return -EINVAL;
-	*((unsigned int *)kp->arg) = num;
-	return 0;
-}
-static struct kernel_param_ops param_ops_portnr = {
-	.set = param_set_portnr,
-	.get = param_get_uint,
-};
-#define param_check_portnr(name, p) __param_check(name, p, unsigned int);
-
-module_param_named(callback_tcpport, nfs_callback_set_tcpport, portnr, 0644);
 
 /*
  * This is the NFSv4 callback kernel thread.
@@ -265,6 +241,10 @@ int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt)
 		ret = -ENOMEM;
 		goto out_err;
 	}
+	/* As there is only one thread we need to over-ride the
+	 * default maximum of 80 connections
+	 */
+	serv->sv_maxconn = 1024;
 
 	ret = svc_bind(serv, net);
 	if (ret < 0) {

fs/nfs/callback.h

@@ -192,7 +192,7 @@ extern __be32 nfs4_callback_getattr(struct cb_getattrargs *args,
 				    struct cb_process_state *cps);
 extern __be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy,
 				   struct cb_process_state *cps);
-#ifdef CONFIG_NFS_V4
+#if IS_ENABLED(CONFIG_NFS_V4)
 extern int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt);
 extern void nfs_callback_down(int minorversion);
 extern int nfs4_validate_delegation_stateid(struct nfs_delegation *delegation,