nfs: [PATCH 27/31] enable swap on NFS

From: Suresh Jayaraman
Date: Thu Oct 01 2009 - 10:09:24 EST


From: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>

Implement all the new swapfile a_ops for NFS. 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.

(swapping continues over a server reset during heavy network traffic)

Signed-off-by: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Signed-off-by: Suresh Jayaraman <sjayaraman@xxxxxxx>
---
fs/nfs/Kconfig | 10 ++++++
fs/nfs/file.c | 18 +++++++++++
fs/nfs/write.c | 22 +++++++++++++
include/linux/nfs_fs.h | 2 +
include/linux/sunrpc/xprt.h | 5 ++-
net/sunrpc/Kconfig | 5 +++
net/sunrpc/sched.c | 9 ++++-
net/sunrpc/xprtsock.c | 70 ++++++++++++++++++++++++++++++++++++++++++++
8 files changed, 138 insertions(+), 3 deletions(-)

Index: mmotm/fs/nfs/file.c
===================================================================
--- mmotm.orig/fs/nfs/file.c
+++ mmotm/fs/nfs/file.c
@@ -468,6 +468,18 @@ static int nfs_launder_page(struct page
return nfs_wb_page(inode, page);
}

+#ifdef CONFIG_NFS_SWAP
+static int nfs_swapon(struct file *file)
+{
+ return xs_swapper(NFS_CLIENT(file->f_mapping->host)->cl_xprt, 1);
+}
+
+static int nfs_swapoff(struct file *file)
+{
+ return 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,
@@ -480,6 +492,12 @@ const struct address_space_operations nf
.releasepage = nfs_release_page,
.direct_IO = nfs_direct_IO,
.launder_page = nfs_launder_page,
+#ifdef CONFIG_NFS_SWAP
+ .swapon = nfs_swapon,
+ .swapoff = nfs_swapoff,
+ .swap_out = nfs_swap_out,
+ .swap_in = nfs_readpage,
+#endif
};

/*
Index: mmotm/fs/nfs/write.c
===================================================================
--- mmotm.orig/fs/nfs/write.c
+++ mmotm/fs/nfs/write.c
@@ -344,6 +344,28 @@ int nfs_writepage(struct page *page, str
return ret;
}

+static int nfs_writepage_setup(struct nfs_open_context *ctx, struct page *page,
+ unsigned int offset, unsigned int count);
+
+int nfs_swap_out(struct file *file, struct page *page,
+ struct writeback_control *wbc)
+{
+ struct nfs_open_context *ctx = nfs_file_open_context(file);
+ int status;
+
+ status = nfs_writepage_setup(ctx, page, 0, nfs_page_length(page));
+ if (status < 0) {
+ nfs_set_pageerror(page);
+ goto out;
+ }
+
+ status = nfs_writepage_locked(page, wbc);
+
+out:
+ unlock_page(page);
+ return status;
+}
+
static int nfs_writepages_callback(struct page *page, struct writeback_control *wbc, void *data)
{
int ret;
Index: mmotm/include/linux/nfs_fs.h
===================================================================
--- mmotm.orig/include/linux/nfs_fs.h
+++ mmotm/include/linux/nfs_fs.h
@@ -473,6 +473,8 @@ extern int nfs_writepages(struct addres
extern int nfs_flush_incompatible(struct file *file, struct page *page);
extern int nfs_updatepage(struct file *, struct page *, unsigned int, unsigned int);
extern int nfs_writeback_done(struct rpc_task *, struct nfs_write_data *);
+extern int nfs_swap_out(struct file *file, struct page *page,
+ struct writeback_control *wbc);

/*
* Try to write back everything synchronously (but check the
Index: mmotm/include/linux/sunrpc/xprt.h
===================================================================
--- mmotm.orig/include/linux/sunrpc/xprt.h
+++ mmotm/include/linux/sunrpc/xprt.h
@@ -153,7 +153,9 @@ struct rpc_xprt {
unsigned int max_reqs; /* total slots */
unsigned long state; /* transport state */
unsigned char shutdown : 1, /* being shut down */
- resvport : 1; /* use a reserved port */
+ resvport : 1, /* use a reserved port */
+ swapper : 1; /* we're swapping over this
+ transport */
unsigned int bind_index; /* bind function index */

/*
@@ -285,6 +287,7 @@ void xprt_release_rqst_cong(struct rpc
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
Index: mmotm/net/sunrpc/sched.c
===================================================================
--- mmotm.orig/net/sunrpc/sched.c
+++ mmotm/net/sunrpc/sched.c
@@ -735,7 +735,10 @@ struct rpc_buffer {
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)
@@ -806,6 +809,8 @@ static void rpc_init_task(struct rpc_tas
kref_get(&task->tk_client->cl_kref);
if (task->tk_client->cl_softrtry)
task->tk_flags |= RPC_TASK_SOFT;
+ if (task->tk_client->cl_xprt->swapper)
+ task->tk_flags |= RPC_TASK_SWAPPER;
}

if (task->tk_ops->rpc_call_prepare != NULL)
@@ -831,7 +836,7 @@ static void rpc_init_task(struct rpc_tas
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);
}

/*
Index: mmotm/net/sunrpc/xprtsock.c
===================================================================
--- mmotm.orig/net/sunrpc/xprtsock.c
+++ mmotm/net/sunrpc/xprtsock.c
@@ -1719,6 +1719,57 @@ static inline void xs_reclassify_socket6
}
#endif

+#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);
+}
+
+#define RPC_BUF_RESERVE_PAGES \
+ kmalloc_estimate_objs(sizeof(struct rpc_rqst), GFP_KERNEL, RPC_MAX_SLOT_TABLE)
+#define RPC_RESERVE_PAGES (RPC_BUF_RESERVE_PAGES + TX_RESERVE_PAGES)
+
+/**
+ * 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) {
+ /*
+ * keep one extra sock reference so the reserve won't dip
+ * when the socket gets reconnected.
+ */
+ err = sk_adjust_memalloc(1, RPC_RESERVE_PAGES);
+ if (!err) {
+ xprt->swapper = 1;
+ xs_set_memalloc(xprt);
+ }
+ } else if (xprt->swapper) {
+ xprt->swapper = 0;
+ sk_clear_memalloc(transport->inet);
+ sk_adjust_memalloc(-1, -RPC_RESERVE_PAGES);
+ }
+
+ 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);
@@ -1743,6 +1794,8 @@ static void xs_udp_finish_connecting(str
transport->sock = sock;
transport->inet = sk;

+ xs_set_memalloc(xprt);
+
write_unlock_bh(&sk->sk_callback_lock);
}
xs_udp_do_set_buffer_size(xprt);
@@ -1760,11 +1813,15 @@ static void xs_udp_connect_worker4(struc
container_of(work, struct sock_xprt, connect_worker.work);
struct rpc_xprt *xprt = &transport->xprt;
struct socket *sock = transport->sock;
+ unsigned long pflags = current->flags;
int err, status = -EIO;

if (xprt->shutdown)
goto out;

+ if (xprt->swapper)
+ current->flags |= PF_MEMALLOC;
+
/* Start by resetting any existing state */
xs_reset_transport(transport);

@@ -1788,6 +1845,7 @@ static void xs_udp_connect_worker4(struc
out:
xprt_clear_connecting(xprt);
xprt_wake_pending_tasks(xprt, status);
+ tsk_restore_flags(current, pflags, PF_MEMALLOC);
}

/**
@@ -1802,11 +1860,15 @@ static void xs_udp_connect_worker6(struc
container_of(work, struct sock_xprt, connect_worker.work);
struct rpc_xprt *xprt = &transport->xprt;
struct socket *sock = transport->sock;
+ unsigned long pflags = current->flags;
int err, status = -EIO;

if (xprt->shutdown)
goto out;

+ if (xprt->swapper)
+ current->flags |= PF_MEMALLOC;
+
/* Start by resetting any existing state */
xs_reset_transport(transport);

@@ -1830,6 +1892,7 @@ static void xs_udp_connect_worker6(struc
out:
xprt_clear_connecting(xprt);
xprt_wake_pending_tasks(xprt, status);
+ tsk_restore_flags(current, pflags, PF_MEMALLOC);
}

/*
@@ -1904,6 +1967,8 @@ static int xs_tcp_finish_connecting(stru
if (!xprt_bound(xprt))
return -ENOTCONN;

+ xs_set_memalloc(xprt);
+
/* Tell the socket layer to start connecting... */
xprt->stat.connect_count++;
xprt->stat.connect_start = jiffies;
@@ -1924,11 +1989,15 @@ static void xs_tcp_setup_socket(struct r
struct sock_xprt *))
{
struct socket *sock = transport->sock;
+ unsigned long pflags = current->flags;
int status = -EIO;

if (xprt->shutdown)
goto out;

+ if (xprt->swapper)
+ current->flags |= PF_MEMALLOC;
+
if (!sock) {
clear_bit(XPRT_CONNECTION_ABORT, &xprt->state);
sock = create_sock(xprt, transport);
@@ -1981,6 +2050,7 @@ out_eagain:
out:
xprt_clear_connecting(xprt);
xprt_wake_pending_tasks(xprt, status);
+ tsk_restore_flags(current, pflags, PF_MEMALLOC);
}

static struct socket *xs_create_tcp_sock4(struct rpc_xprt *xprt,
Index: mmotm/fs/nfs/Kconfig
===================================================================
--- mmotm.orig/fs/nfs/Kconfig
+++ mmotm/fs/nfs/Kconfig
@@ -74,6 +74,16 @@ config NFS_V4

If unsure, say N.

+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.
+
+ For more details, see Documentation/network-swap.txt
+
config NFS_V4_1
bool "NFS client support for NFSv4.1 (DEVELOPER ONLY)"
depends on NFS_V4 && EXPERIMENTAL
Index: mmotm/net/sunrpc/Kconfig
===================================================================
--- mmotm.orig/net/sunrpc/Kconfig
+++ mmotm/net/sunrpc/Kconfig
@@ -17,6 +17,11 @@ config SUNRPC_XPRT_RDMA

If unsure, say N.

+config SUNRPC_SWAP
+ def_bool n
+ depends on SUNRPC
+ select NETVM
+
config RPCSEC_GSS_KRB5
tristate "Secure RPC: Kerberos V mechanism (EXPERIMENTAL)"
depends on SUNRPC && EXPERIMENTAL
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/