nfs: enable swap on NFS

Implement the new swapfile a_ops for NFS and hook up ->direct_IO.  This
will set the NFS socket to SOCK_MEMALLOC and run socket reconnect under
PF_MEMALLOC as well as reset SOCK_MEMALLOC before engaging the protocol
->connect() method.

PF_MEMALLOC should allow the allocation of struct socket and related
objects and the early (re)setting of SOCK_MEMALLOC should allow us to
receive the packets required for the TCP connection buildup.

[jlayton@redhat.com: Restore PF_MEMALLOC task flags in all cases]
[dfeng@redhat.com: Fix handling of multiple swap files]
[a.p.zijlstra@chello.nl: Original patch]
Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: David S. Miller <davem@davemloft.net>
Cc: Eric B Munson <emunson@mgebm.net>
Cc: Eric Paris <eparis@redhat.com>
Cc: James Morris <jmorris@namei.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Mike Christie <michaelc@cs.wisc.edu>
Cc: Neil Brown <neilb@suse.de>
Cc: Sebastian Andrzej Siewior <sebastian@breakpoint.cc>
Cc: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: Xiaotian Feng <dfeng@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index 404c6a8ac394423da4079aa965fd987e80a0e0cc..6fd5f2cdcd1e804cd5ddeaacbab56809317a739a 100644 (file)
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -86,6 +86,14 @@ config NFS_V4
 
          If unsure, say Y.
 
+config NFS_SWAP
+       bool "Provide swap over NFS support"
+       default n
+       depends on NFS_FS
+       select SUNRPC_SWAP
+       help
+         This option enables swapon to work on files located on NFS mounts.
+
 config NFS_V4_1
        bool "NFS client support for NFSv4.1 (EXPERIMENTAL)"
        depends on NFS_V4 && EXPERIMENTAL

diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 42dce909ec70073509c33eabdf8b9784eda68faf..bf9c8d0ec16a7a8b65921c24b8d24ae04f6654dd 100644 (file)
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -115,17 +115,28 @@ static inline int put_dreq(struct nfs_direct_req *dreq)
  * @nr_segs: size of iovec array
  *
  * The presence of this routine in the address space ops vector means
- * the NFS client supports direct I/O.  However, we shunt off direct
- * read and write requests before the VFS gets them, so this method
- * should never be called.
+ * the NFS client supports direct I/O. However, for most direct IO, we
+ * shunt off direct read and write requests before the VFS gets them,
+ * so this method is only ever called for swap.
  */
 ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, loff_t pos, unsigned long nr_segs)
 {
+#ifndef CONFIG_NFS_SWAP
        dprintk("NFS: nfs_direct_IO (%s) off/no(%Ld/%lu) EINVAL\n",
                        iocb->ki_filp->f_path.dentry->d_name.name,
                        (long long) pos, nr_segs);
 
        return -EINVAL;
+#else
+       VM_BUG_ON(iocb->ki_left != PAGE_SIZE);
+       VM_BUG_ON(iocb->ki_nbytes != PAGE_SIZE);
+
+       if (rw == READ || rw == KERNEL_READ)
+               return nfs_file_direct_read(iocb, iov, nr_segs, pos,
+                               rw == READ ? true : false);
+       return nfs_file_direct_write(iocb, iov, nr_segs, pos,
+                               rw == WRITE ? true : false);
+#endif /* CONFIG_NFS_SWAP */
 }
 
 static void nfs_direct_release_pages(struct page **pages, unsigned int npages)
@@ -303,7 +314,7 @@ static const struct nfs_pgio_completion_ops nfs_direct_read_completion_ops = {
  */
 static ssize_t nfs_direct_read_schedule_segment(struct nfs_pageio_descriptor *desc,
                                                const struct iovec *iov,
-                                               loff_t pos)
+                                               loff_t pos, bool uio)
 {
        struct nfs_direct_req *dreq = desc->pg_dreq;
        struct nfs_open_context *ctx = dreq->ctx;
@@ -331,12 +342,20 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_pageio_descriptor *de
                                          GFP_KERNEL);
                if (!pagevec)
                        break;
-               down_read(&current->mm->mmap_sem);
-               result = get_user_pages(current, current->mm, user_addr,
+               if (uio) {
+                       down_read(&current->mm->mmap_sem);
+                       result = get_user_pages(current, current->mm, user_addr,
                                        npages, 1, 0, pagevec, NULL);
-               up_read(&current->mm->mmap_sem);
-               if (result < 0)
-                       break;
+                       up_read(&current->mm->mmap_sem);
+                       if (result < 0)
+                               break;
+               } else {
+                       WARN_ON(npages != 1);
+                       result = get_kernel_page(user_addr, 1, pagevec);
+                       if (WARN_ON(result != 1))
+                               break;
+               }
+
                if ((unsigned)result < npages) {
                        bytes = result * PAGE_SIZE;
                        if (bytes <= pgbase) {
@@ -386,7 +405,7 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_pageio_descriptor *de
 static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
                                              const struct iovec *iov,
                                              unsigned long nr_segs,
-                                             loff_t pos)
+                                             loff_t pos, bool uio)
 {
        struct nfs_pageio_descriptor desc;
        ssize_t result = -EINVAL;
@@ -400,7 +419,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
 
        for (seg = 0; seg < nr_segs; seg++) {
                const struct iovec *vec = &iov[seg];
-               result = nfs_direct_read_schedule_segment(&desc, vec, pos);
+               result = nfs_direct_read_schedule_segment(&desc, vec, pos, uio);
                if (result < 0)
                        break;
                requested_bytes += result;
@@ -426,7 +445,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
 }
 
 static ssize_t nfs_direct_read(struct kiocb *iocb, const struct iovec *iov,
-                              unsigned long nr_segs, loff_t pos)
+                              unsigned long nr_segs, loff_t pos, bool uio)
 {
        ssize_t result = -ENOMEM;
        struct inode *inode = iocb->ki_filp->f_mapping->host;
@@ -444,7 +463,7 @@ static ssize_t nfs_direct_read(struct kiocb *iocb, const struct iovec *iov,
        if (!is_sync_kiocb(iocb))
                dreq->iocb = iocb;
 
-       result = nfs_direct_read_schedule_iovec(dreq, iov, nr_segs, pos);
+       result = nfs_direct_read_schedule_iovec(dreq, iov, nr_segs, pos, uio);
        if (!result)
                result = nfs_direct_wait(dreq);
        NFS_I(inode)->read_io += result;
@@ -610,7 +629,7 @@ static void nfs_direct_write_complete(struct nfs_direct_req *dreq, struct inode
  */
 static ssize_t nfs_direct_write_schedule_segment(struct nfs_pageio_descriptor *desc,
                                                 const struct iovec *iov,
-                                                loff_t pos)
+                                                loff_t pos, bool uio)
 {
        struct nfs_direct_req *dreq = desc->pg_dreq;
        struct nfs_open_context *ctx = dreq->ctx;
@@ -638,12 +657,19 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_pageio_descriptor *d
                if (!pagevec)
                        break;
 
-               down_read(&current->mm->mmap_sem);
-               result = get_user_pages(current, current->mm, user_addr,
-                                       npages, 0, 0, pagevec, NULL);
-               up_read(&current->mm->mmap_sem);
-               if (result < 0)
-                       break;
+               if (uio) {
+                       down_read(&current->mm->mmap_sem);
+                       result = get_user_pages(current, current->mm, user_addr,
+                                               npages, 0, 0, pagevec, NULL);
+                       up_read(&current->mm->mmap_sem);
+                       if (result < 0)
+                               break;
+               } else {
+                       WARN_ON(npages != 1);
+                       result = get_kernel_page(user_addr, 0, pagevec);
+                       if (WARN_ON(result != 1))
+                               break;
+               }
 
                if ((unsigned)result < npages) {
                        bytes = result * PAGE_SIZE;
@@ -774,7 +800,7 @@ static const struct nfs_pgio_completion_ops nfs_direct_write_completion_ops = {
 static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
                                               const struct iovec *iov,
                                               unsigned long nr_segs,
-                                              loff_t pos)
+                                              loff_t pos, bool uio)
 {
        struct nfs_pageio_descriptor desc;
        struct inode *inode = dreq->inode;
@@ -790,7 +816,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 
        for (seg = 0; seg < nr_segs; seg++) {
                const struct iovec *vec = &iov[seg];
-               result = nfs_direct_write_schedule_segment(&desc, vec, pos);
+               result = nfs_direct_write_schedule_segment(&desc, vec, pos, uio);
                if (result < 0)
                        break;
                requested_bytes += result;
@@ -818,7 +844,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 
 static ssize_t nfs_direct_write(struct kiocb *iocb, const struct iovec *iov,
                                unsigned long nr_segs, loff_t pos,
-                               size_t count)
+                               size_t count, bool uio)
 {
        ssize_t result = -ENOMEM;
        struct inode *inode = iocb->ki_filp->f_mapping->host;
@@ -836,7 +862,7 @@ static ssize_t nfs_direct_write(struct kiocb *iocb, const struct iovec *iov,
        if (!is_sync_kiocb(iocb))
                dreq->iocb = iocb;
 
-       result = nfs_direct_write_schedule_iovec(dreq, iov, nr_segs, pos);
+       result = nfs_direct_write_schedule_iovec(dreq, iov, nr_segs, pos, uio);
        if (!result)
                result = nfs_direct_wait(dreq);
 out_release:
@@ -867,7 +893,7 @@ out:
  * cache.
  */
 ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov,
-                               unsigned long nr_segs, loff_t pos)
+                               unsigned long nr_segs, loff_t pos, bool uio)
 {
        ssize_t retval = -EINVAL;
        struct file *file = iocb->ki_filp;
@@ -892,7 +918,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov,
 
        task_io_account_read(count);
 
-       retval = nfs_direct_read(iocb, iov, nr_segs, pos);
+       retval = nfs_direct_read(iocb, iov, nr_segs, pos, uio);
        if (retval > 0)
                iocb->ki_pos = pos + retval;
 
@@ -923,7 +949,7 @@ out:
  * is no atomic O_APPEND write facility in the NFS protocol.
  */
 ssize_t nfs_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
-                               unsigned long nr_segs, loff_t pos)
+                               unsigned long nr_segs, loff_t pos, bool uio)
 {
        ssize_t retval = -EINVAL;
        struct file *file = iocb->ki_filp;
@@ -955,7 +981,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
 
        task_io_account_write(count);
 
-       retval = nfs_direct_write(iocb, iov, nr_segs, pos, count);
+       retval = nfs_direct_write(iocb, iov, nr_segs, pos, count, uio);
        if (retval > 0) {
                struct inode *inode = mapping->host;
 

diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index acd4e4cd29065a7b4fb7dc33ade6f8af6719c1ee..50fb83a88b1b4fb2ac4d1d18b0a3c01c8299151b 100644 (file)
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -175,7 +175,7 @@ nfs_file_read(struct kiocb *iocb, const struct iovec *iov,
        ssize_t result;
 
        if (iocb->ki_filp->f_flags & O_DIRECT)
-               return nfs_file_direct_read(iocb, iov, nr_segs, pos);
+               return nfs_file_direct_read(iocb, iov, nr_segs, pos, true);
 
        dprintk("NFS: read(%s/%s, %lu@%lu)\n",
                dentry->d_parent->d_name.name, dentry->d_name.name,
@@ -482,6 +482,20 @@ static int nfs_launder_page(struct page *page)
        return nfs_wb_page(inode, page);
 }
 
+#ifdef CONFIG_NFS_SWAP
+static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file,
+                                               sector_t *span)
+{
+       *span = sis->pages;
+       return xs_swapper(NFS_CLIENT(file->f_mapping->host)->cl_xprt, 1);
+}
+
+static void nfs_swap_deactivate(struct file *file)
+{
+       xs_swapper(NFS_CLIENT(file->f_mapping->host)->cl_xprt, 0);
+}
+#endif
+
 const struct address_space_operations nfs_file_aops = {
        .readpage = nfs_readpage,
        .readpages = nfs_readpages,
@@ -496,6 +510,10 @@ const struct address_space_operations nfs_file_aops = {
        .migratepage = nfs_migrate_page,
        .launder_page = nfs_launder_page,
        .error_remove_page = generic_error_remove_page,
+#ifdef CONFIG_NFS_SWAP
+       .swap_activate = nfs_swap_activate,
+       .swap_deactivate = nfs_swap_deactivate,
+#endif
 };
 
 /*
@@ -570,7 +588,7 @@ ssize_t nfs_file_write(struct kiocb *iocb, const struct iovec *iov,
        size_t count = iov_length(iov, nr_segs);
 
        if (iocb->ki_filp->f_flags & O_DIRECT)
-               return nfs_file_direct_write(iocb, iov, nr_segs, pos);
+               return nfs_file_direct_write(iocb, iov, nr_segs, pos, true);
 
        dprintk("NFS: write(%s/%s, %lu@%Ld)\n",
                dentry->d_parent->d_name.name, dentry->d_name.name,

diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 4b6043c20f7745be854b6fd95ba3fbd8fc450ec3..35994f975a7ff90351ab02d2403eec17d52c5341 100644 (file)
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -473,10 +473,10 @@ extern ssize_t nfs_direct_IO(int, struct kiocb *, const struct iovec *, loff_t,
                        unsigned long);
 extern ssize_t nfs_file_direct_read(struct kiocb *iocb,
                        const struct iovec *iov, unsigned long nr_segs,
-                       loff_t pos);
+                       loff_t pos, bool uio);
 extern ssize_t nfs_file_direct_write(struct kiocb *iocb,
                        const struct iovec *iov, unsigned long nr_segs,
-                       loff_t pos);
+                       loff_t pos, bool uio);
 
 /*
  * linux/fs/nfs/dir.c

diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index 77d278defa70667011b5a8b08ba70394b23d1d84..cff40aa7db625bbb9dafd6b5842d3dc70276c682 100644 (file)
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -174,6 +174,8 @@ struct rpc_xprt {
        unsigned long           state;          /* transport state */
        unsigned char           shutdown   : 1, /* being shut down */
                                resvport   : 1; /* use a reserved port */
+       unsigned int            swapper;        /* we're swapping over this
+                                                  transport */
        unsigned int            bind_index;     /* bind function index */
 
        /*
@@ -316,6 +318,7 @@ void                        xprt_release_rqst_cong(struct rpc_task *task);
 void                   xprt_disconnect_done(struct rpc_xprt *xprt);
 void                   xprt_force_disconnect(struct rpc_xprt *xprt);
 void                   xprt_conditional_disconnect(struct rpc_xprt *xprt, unsigned int cookie);
+int                    xs_swapper(struct rpc_xprt *xprt, int enable);
 
 /*
  * Reserved bit positions in xprt->state

diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig
index 9fe8857d8d596e5eb59146416396b834b195b2c1..03d03e37a7d56e8fc3a1505cffc0002baf7726d3 100644 (file)
--- a/net/sunrpc/Kconfig
+++ b/net/sunrpc/Kconfig
@@ -21,6 +21,11 @@ config SUNRPC_XPRT_RDMA
 
          If unsure, say N.
 
+config SUNRPC_SWAP
+       bool
+       depends on SUNRPC
+       select NETVM
+
 config RPCSEC_GSS_KRB5
        tristate "Secure RPC: Kerberos V mechanism"
        depends on SUNRPC && CRYPTO

diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index b05df36692ff0aec2e370c96fc4a74dfb2f50ff0..fa48c60aef2305430956ef9735b20f6a0f62c073 100644 (file)
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -717,6 +717,15 @@ void rpc_task_set_client(struct rpc_task *task, struct rpc_clnt *clnt)
                atomic_inc(&clnt->cl_count);
                if (clnt->cl_softrtry)
                        task->tk_flags |= RPC_TASK_SOFT;
+               if (sk_memalloc_socks()) {
+                       struct rpc_xprt *xprt;
+
+                       rcu_read_lock();
+                       xprt = rcu_dereference(clnt->cl_xprt);
+                       if (xprt->swapper)
+                               task->tk_flags |= RPC_TASK_SWAPPER;
+                       rcu_read_unlock();
+               }
                /* Add to the client's list of all tasks */
                spin_lock(&clnt->cl_lock);
                list_add_tail(&task->tk_task, &clnt->cl_tasks);

diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index 994cfea2bad66f814432c2fcbb1227d0a321d34f..83a4c43cee7f254559206dd326ce1c7e2038d164 100644 (file)
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -812,7 +812,10 @@ static void rpc_async_schedule(struct work_struct *work)
 void *rpc_malloc(struct rpc_task *task, size_t size)
 {
        struct rpc_buffer *buf;
-       gfp_t gfp = RPC_IS_SWAPPER(task) ? GFP_ATOMIC : GFP_NOWAIT;
+       gfp_t gfp = GFP_NOWAIT;
+
+       if (RPC_IS_SWAPPER(task))
+               gfp |= __GFP_MEMALLOC;
 
        size += sizeof(struct rpc_buffer);
        if (size <= RPC_BUFFER_MAXSIZE)
@@ -886,7 +889,7 @@ static void rpc_init_task(struct rpc_task *task, const struct rpc_task_setup *ta
 static struct rpc_task *
 rpc_alloc_task(void)
 {
-       return (struct rpc_task *)mempool_alloc(rpc_task_mempool, GFP_NOFS);
+       return (struct rpc_task *)mempool_alloc(rpc_task_mempool, GFP_NOIO);
 }
 
 /*

diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 62d0dac8f7807f9fbfbe3fbc10315e5386197b89..bd59d01f035b04a403d63e2e1073997fec5bd759 100644 (file)
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -1927,6 +1927,45 @@ out:
        xprt_wake_pending_tasks(xprt, status);
 }
 
+#ifdef CONFIG_SUNRPC_SWAP
+static void xs_set_memalloc(struct rpc_xprt *xprt)
+{
+       struct sock_xprt *transport = container_of(xprt, struct sock_xprt,
+                       xprt);
+
+       if (xprt->swapper)
+               sk_set_memalloc(transport->inet);
+}
+
+/**
+ * xs_swapper - Tag this transport as being used for swap.
+ * @xprt: transport to tag
+ * @enable: enable/disable
+ *
+ */
+int xs_swapper(struct rpc_xprt *xprt, int enable)
+{
+       struct sock_xprt *transport = container_of(xprt, struct sock_xprt,
+                       xprt);
+       int err = 0;
+
+       if (enable) {
+               xprt->swapper++;
+               xs_set_memalloc(xprt);
+       } else if (xprt->swapper) {
+               xprt->swapper--;
+               sk_clear_memalloc(transport->inet);
+       }
+
+       return err;
+}
+EXPORT_SYMBOL_GPL(xs_swapper);
+#else
+static void xs_set_memalloc(struct rpc_xprt *xprt)
+{
+}
+#endif
+
 static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
 {
        struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
@@ -1951,6 +1990,8 @@ static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
                transport->sock = sock;
                transport->inet = sk;
 
+               xs_set_memalloc(xprt);
+
                write_unlock_bh(&sk->sk_callback_lock);
        }
        xs_udp_do_set_buffer_size(xprt);
@@ -2075,6 +2116,8 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
        if (!xprt_bound(xprt))
                goto out;
 
+       xs_set_memalloc(xprt);
+
        /* Tell the socket layer to start connecting... */
        xprt->stat.connect_count++;
        xprt->stat.connect_start = jiffies;