Skip to content

K
Kernel

openeuler / Kernel
11 个月 前同步成功

通知 5
Star 0
Fork 0
K
Kernel

体验新版 GitCode，发现更多精彩内容 >>

提交 6f83e5bd 编写于 作者: L Linus Torvalds
浏览文件
操作

Merge tag 'nfs-for-3.20-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs 

Pull NFS client updates from Trond Myklebust:
 "Highlights incluse:

  Features:
   - Removing the forced serialisation of open()/close() calls in
     NFSv4.x (x>0) makes for a significant performance improvement in
     metadata intensive workloads.
   - Full support for the pNFS "flexible files" layout type
   - Further RPC/RDMA client improvements from Chuck

  Bugfixes:
   - Stable fix: NFSv4.1 backchannel calls blocking operations with !TASK_RUNNING
   - Stable fix: pnfs_generic_pg_init_read/write can be called with lseg == NULL
   - Stable fix: Fix an Oopsable condition when nsm_mon_unmon is called
     as part of the namespace cleanup,
   - Stable fix: Ensure we reference the inode for return-on-close in
     delegreturn
   - Use SO_REUSEPORT to ensure that NFSv3 TCP connections can rebind to
     the same source address/port combination during a disconnect/
     reconnect event.  This is a requirement imposed by most NFSv3
     server duplicate reply cache implementations.

  Optimisations:
   - Ask for no NFSv4.1 delegations on OPEN if using O_DIRECT

  Other:
   - Add Anna Schumaker as co-maintainer for the NFS client"

* tag 'nfs-for-3.20-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (119 commits)
  SUNRPC: Cleanup to remove xs_tcp_close()
  pnfs: delete an unintended goto
  pnfs/flexfiles: Do not dprintk after the free
  SUNRPC: Fix stupid typo in xs_sock_set_reuseport
  SUNRPC: Define xs_tcp_fin_timeout only if CONFIG_SUNRPC_DEBUG
  SUNRPC: Handle connection reset more efficiently.
  SUNRPC: Remove the redundant XPRT_CONNECTION_CLOSE flag
  SUNRPC: Make xs_tcp_close() do a socket shutdown rather than a sock_release
  SUNRPC: Ensure xs_tcp_shutdown() requests a full close of the connection
  SUNRPC: Cleanup to remove remaining uses of XPRT_CONNECTION_ABORT
  SUNRPC: Remove TCP socket linger code
  SUNRPC: Remove TCP client connection reset hack
  SUNRPC: TCP/UDP always close the old socket before reconnecting
  SUNRPC: Add helpers to prevent socket create from racing
  SUNRPC: Ensure xs_reset_transport() resets the close connection flags
  SUNRPC: Do not clear the source port in xs_reset_transport
  SUNRPC: Handle EADDRINUSE on connect
  SUNRPC: Set SO_REUSEPORT socket option for TCP connections
  NFSv4.1: Fix pnfs_put_lseg races
  NFSv4.1: pnfs_send_layoutreturn should use GFP_NOFS
  ...
上级 73b4f63a c627d31b
展开全部 隐藏空白更改
内联 并排
Showing with 5236 addition and 1729 deletion
Documentation/filesystems/nfs/pnfs.txt
浏览文件 @ 6f83e5bd
......@@ -57,15 +57,16 @@ bit is set, preventing any new lsegs from being added.
layout drivers
--------------
PNFS utilizes what is called layout drivers. The STD defines 3 basic
layout types: "files" "objects" and "blocks". For each of these types
there is a layout-driver with a common function-vectors table which
are called by the nfs-client pnfs-core to implement the different layout
types.
PNFS utilizes what is called layout drivers. The STD defines 4 basic
layout types: "files", "objects", "blocks", and "flexfiles". For each
of these types there is a layout-driver with a common function-vectors
table which are called by the nfs-client pnfs-core to implement the
different layout types.
Files-layout-driver code is in: fs/nfs/nfs4filelayout.c && nfs4filelayoutdev.c
Files-layout-driver code is in: fs/nfs/filelayout/.. directory
Objects-layout-deriver code is in: fs/nfs/objlayout/.. directory
Blocks-layout-deriver code is in: fs/nfs/blocklayout/.. directory
Flexfiles-layout-driver code is in: fs/nfs/flexfilelayout/.. directory
objects-layout setup
--------------------
......
MAINTAINERS
浏览文件 @ 6f83e5bd
......@@ -6777,6 +6777,7 @@ F: Documentation/devicetree/bindings/net/nfc/
NFS, SUNRPC, AND LOCKD CLIENTS
M: Trond Myklebust <trond.myklebust@primarydata.com>
M: Anna Schumaker <anna.schumaker@netapp.com>
L: linux-nfs@vger.kernel.org
W: http://client.linux-nfs.org
T: git git://git.linux-nfs.org/projects/trondmy/linux-nfs.git
......
fs/lockd/mon.c
浏览文件 @ 6f83e5bd
......@@ -65,7 +65,7 @@ static inline struct sockaddr *nsm_addr(const struct nsm_handle *nsm)
return (struct sockaddr *)&nsm->sm_addr;
}
static struct rpc_clnt *nsm_create(struct net *net)
static struct rpc_clnt *nsm_create(struct net *net, const char *nodename)
{
struct sockaddr_in sin = {
.sin_family = AF_INET,
......@@ -77,6 +77,7 @@ static struct rpc_clnt *nsm_create(struct net *net)
.address = (struct sockaddr *)&sin,
.addrsize = sizeof(sin),
.servername = "rpc.statd",
.nodename = nodename,
.program = &nsm_program,
.version = NSM_VERSION,
.authflavor = RPC_AUTH_NULL,
......@@ -102,7 +103,7 @@ static struct rpc_clnt *nsm_client_set(struct lockd_net *ln,
return clnt;
}
static struct rpc_clnt *nsm_client_get(struct net *net)
static struct rpc_clnt *nsm_client_get(struct net *net, const char *nodename)
{
struct rpc_clnt *clnt, *new;
struct lockd_net *ln = net_generic(net, lockd_net_id);
......@@ -111,7 +112,7 @@ static struct rpc_clnt *nsm_client_get(struct net *net)
if (clnt != NULL)
goto out;
clnt = new = nsm_create(net);
clnt = new = nsm_create(net, nodename);
if (IS_ERR(clnt))
goto out;
......@@ -190,19 +191,23 @@ int nsm_monitor(const struct nlm_host *host)
struct nsm_res res;
int status;
struct rpc_clnt *clnt;
const char *nodename = NULL;
dprintk("lockd: nsm_monitor(%s)\n", nsm->sm_name);
if (nsm->sm_monitored)
return 0;
if (host->h_rpcclnt)
nodename = host->h_rpcclnt->cl_nodename;
/*
* Choose whether to record the caller_name or IP address of
* this peer in the local rpc.statd's database.
*/
nsm->sm_mon_name = nsm_use_hostnames ? nsm->sm_name : nsm->sm_addrbuf;
clnt = nsm_client_get(host->net);
clnt = nsm_client_get(host->net, nodename);
if (IS_ERR(clnt)) {
status = PTR_ERR(clnt);
dprintk("lockd: failed to create NSM upcall transport, "
......
fs/nfs/Kconfig
浏览文件 @ 6f83e5bd
......@@ -128,6 +128,11 @@ config PNFS_OBJLAYOUT
depends on NFS_V4_1 && SCSI_OSD_ULD
default NFS_V4
config PNFS_FLEXFILE_LAYOUT
tristate
depends on NFS_V4_1 && NFS_V3
default m
config NFS_V4_1_IMPLEMENTATION_ID_DOMAIN
string "NFSv4.1 Implementation ID Domain"
depends on NFS_V4_1
......
fs/nfs/Makefile
浏览文件 @ 6f83e5bd
......@@ -27,9 +27,10 @@ nfsv4-y := nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o nfs4super.o nfs4file.o
dns_resolve.o nfs4trace.o
nfsv4-$(CONFIG_NFS_USE_LEGACY_DNS) += cache_lib.o
nfsv4-$(CONFIG_SYSCTL) += nfs4sysctl.o
nfsv4-$(CONFIG_NFS_V4_1) += pnfs.o pnfs_dev.o
nfsv4-$(CONFIG_NFS_V4_1) += pnfs.o pnfs_dev.o pnfs_nfs.o
nfsv4-$(CONFIG_NFS_V4_2) += nfs42proc.o
obj-$(CONFIG_PNFS_FILE_LAYOUT) += filelayout/
obj-$(CONFIG_PNFS_OBJLAYOUT) += objlayout/
obj-$(CONFIG_PNFS_BLOCK) += blocklayout/
obj-$(CONFIG_PNFS_FLEXFILE_LAYOUT) += flexfilelayout/
fs/nfs/blocklayout/blocklayout.c
浏览文件 @ 6f83e5bd
......@@ -860,12 +860,14 @@ static const struct nfs_pageio_ops bl_pg_read_ops = {
.pg_init = bl_pg_init_read,
.pg_test = bl_pg_test_read,
.pg_doio = pnfs_generic_pg_readpages,
.pg_cleanup = pnfs_generic_pg_cleanup,
};
static const struct nfs_pageio_ops bl_pg_write_ops = {
.pg_init = bl_pg_init_write,
.pg_test = bl_pg_test_write,
.pg_doio = pnfs_generic_pg_writepages,
.pg_cleanup = pnfs_generic_pg_cleanup,
};
static struct pnfs_layoutdriver_type blocklayout_type = {
......
fs/nfs/callback.c
浏览文件 @ 6f83e5bd
......@@ -128,22 +128,24 @@ nfs41_callback_svc(void *vrqstp)
if (try_to_freeze())
continue;
prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_INTERRUPTIBLE);
prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_UNINTERRUPTIBLE);
spin_lock_bh(&serv->sv_cb_lock);
if (!list_empty(&serv->sv_cb_list)) {
req = list_first_entry(&serv->sv_cb_list,
struct rpc_rqst, rq_bc_list);
list_del(&req->rq_bc_list);
spin_unlock_bh(&serv->sv_cb_lock);
finish_wait(&serv->sv_cb_waitq, &wq);
dprintk("Invoking bc_svc_process()\n");
error = bc_svc_process(serv, req, rqstp);
dprintk("bc_svc_process() returned w/ error code= %d\n",
error);
} else {
spin_unlock_bh(&serv->sv_cb_lock);
schedule();
/* schedule_timeout to game the hung task watchdog */
schedule_timeout(60 * HZ);
finish_wait(&serv->sv_cb_waitq, &wq);
}
finish_wait(&serv->sv_cb_waitq, &wq);
}
return 0;
}
......
fs/nfs/delegation.c
浏览文件 @ 6f83e5bd
......@@ -306,6 +306,17 @@ nfs_inode_detach_delegation(struct inode *inode)
return nfs_detach_delegation(nfsi, delegation, server);
}
static void
nfs_update_inplace_delegation(struct nfs_delegation *delegation,
const struct nfs_delegation *update)
{
if (nfs4_stateid_is_newer(&update->stateid, &delegation->stateid)) {
delegation->stateid.seqid = update->stateid.seqid;
smp_wmb();
delegation->type = update->type;
}
}
/**
* nfs_inode_set_delegation - set up a delegation on an inode
* @inode: inode to which delegation applies
......@@ -339,9 +350,12 @@ int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct
old_delegation = rcu_dereference_protected(nfsi->delegation,
lockdep_is_held(&clp->cl_lock));
if (old_delegation != NULL) {
if (nfs4_stateid_match(&delegation->stateid,
&old_delegation->stateid) &&
delegation->type == old_delegation->type) {
/* Is this an update of the existing delegation? */
if (nfs4_stateid_match_other(&old_delegation->stateid,
&delegation->stateid)) {
nfs_update_inplace_delegation(old_delegation,
delegation);
nfsi->delegation_state = old_delegation->type;
goto out;
}
/*
......
fs/nfs/direct.c
浏览文件 @ 6f83e5bd
......@@ -66,6 +66,10 @@ static struct kmem_cache *nfs_direct_cachep;
/*
* This represents a set of asynchronous requests that we're waiting on
*/
struct nfs_direct_mirror {
ssize_t count;
};
struct nfs_direct_req {
struct kref kref; /* release manager */
......@@ -78,8 +82,13 @@ struct nfs_direct_req {
/* completion state */
atomic_t io_count; /* i/os we're waiting for */
spinlock_t lock; /* protect completion state */
struct nfs_direct_mirror mirrors[NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX];
int mirror_count;
ssize_t count, /* bytes actually processed */
bytes_left, /* bytes left to be sent */
io_start, /* start of IO */
error; /* any reported error */
struct completion completion; /* wait for i/o completion */
......@@ -108,26 +117,56 @@ static inline int put_dreq(struct nfs_direct_req *dreq)
return atomic_dec_and_test(&dreq->io_count);
}
void nfs_direct_set_resched_writes(struct nfs_direct_req *dreq)
{
dreq->flags = NFS_ODIRECT_RESCHED_WRITES;
}
EXPORT_SYMBOL_GPL(nfs_direct_set_resched_writes);
static void
nfs_direct_good_bytes(struct nfs_direct_req *dreq, struct nfs_pgio_header *hdr)
{
int i;
ssize_t count;
WARN_ON_ONCE(hdr->pgio_mirror_idx >= dreq->mirror_count);
count = dreq->mirrors[hdr->pgio_mirror_idx].count;
if (count + dreq->io_start < hdr->io_start + hdr->good_bytes) {
count = hdr->io_start + hdr->good_bytes - dreq->io_start;
dreq->mirrors[hdr->pgio_mirror_idx].count = count;
}
/* update the dreq->count by finding the minimum agreed count from all
* mirrors */
count = dreq->mirrors[0].count;
for (i = 1; i < dreq->mirror_count; i++)
count = min(count, dreq->mirrors[i].count);
dreq->count = count;
}
/*
* nfs_direct_select_verf - select the right verifier
* @dreq - direct request possibly spanning multiple servers
* @ds_clp - nfs_client of data server or NULL if MDS / non-pnfs
* @ds_idx - index of data server in data server list, only valid if ds_clp set
* @commit_idx - commit bucket index for the DS
*
* returns the correct verifier to use given the role of the server
*/
static struct nfs_writeverf *
nfs_direct_select_verf(struct nfs_direct_req *dreq,
struct nfs_client *ds_clp,
int ds_idx)
int commit_idx)
{
struct nfs_writeverf *verfp = &dreq->verf;
#ifdef CONFIG_NFS_V4_1
if (ds_clp) {
/* pNFS is in use, use the DS verf */
if (ds_idx >= 0 && ds_idx < dreq->ds_cinfo.nbuckets)
verfp = &dreq->ds_cinfo.buckets[ds_idx].direct_verf;
if (commit_idx >= 0 && commit_idx < dreq->ds_cinfo.nbuckets)
verfp = &dreq->ds_cinfo.buckets[commit_idx].direct_verf;
else
WARN_ON_ONCE(1);
}
......@@ -148,8 +187,7 @@ static void nfs_direct_set_hdr_verf(struct nfs_direct_req *dreq,
{
struct nfs_writeverf *verfp;
verfp = nfs_direct_select_verf(dreq, hdr->ds_clp,
hdr->ds_idx);
verfp = nfs_direct_select_verf(dreq, hdr->ds_clp, hdr->ds_commit_idx);
WARN_ON_ONCE(verfp->committed >= 0);
memcpy(verfp, &hdr->verf, sizeof(struct nfs_writeverf));
WARN_ON_ONCE(verfp->committed < 0);
......@@ -169,8 +207,7 @@ static int nfs_direct_set_or_cmp_hdr_verf(struct nfs_direct_req *dreq,
{
struct nfs_writeverf *verfp;
verfp = nfs_direct_select_verf(dreq, hdr->ds_clp,
hdr->ds_idx);
verfp = nfs_direct_select_verf(dreq, hdr->ds_clp, hdr->ds_commit_idx);
if (verfp->committed < 0) {
nfs_direct_set_hdr_verf(dreq, hdr);
return 0;
......@@ -193,7 +230,11 @@ static int nfs_direct_cmp_commit_data_verf(struct nfs_direct_req *dreq,
verfp = nfs_direct_select_verf(dreq, data->ds_clp,
data->ds_commit_index);
WARN_ON_ONCE(verfp->committed < 0);
/* verifier not set so always fail */
if (verfp->committed < 0)
return 1;
return memcmp(verfp, &data->verf, sizeof(struct nfs_writeverf));
}
......@@ -249,6 +290,18 @@ void nfs_init_cinfo_from_dreq(struct nfs_commit_info *cinfo,
cinfo->completion_ops = &nfs_direct_commit_completion_ops;
}
static inline void nfs_direct_setup_mirroring(struct nfs_direct_req *dreq,
struct nfs_pageio_descriptor *pgio,
struct nfs_page *req)
{
int mirror_count = 1;
if (pgio->pg_ops->pg_get_mirror_count)
mirror_count = pgio->pg_ops->pg_get_mirror_count(pgio, req);
dreq->mirror_count = mirror_count;
}
static inline struct nfs_direct_req *nfs_direct_req_alloc(void)
{
struct nfs_direct_req *dreq;
......@@ -263,6 +316,7 @@ static inline struct nfs_direct_req *nfs_direct_req_alloc(void)
INIT_LIST_HEAD(&dreq->mds_cinfo.list);
dreq->verf.committed = NFS_INVALID_STABLE_HOW; /* not set yet */
INIT_WORK(&dreq->work, nfs_direct_write_schedule_work);
dreq->mirror_count = 1;
spin_lock_init(&dreq->lock);
return dreq;
......@@ -369,7 +423,8 @@ static void nfs_direct_read_completion(struct nfs_pgio_header *hdr)
if (test_bit(NFS_IOHDR_ERROR, &hdr->flags) && (hdr->good_bytes == 0))
dreq->error = hdr->error;
else
dreq->count += hdr->good_bytes;
nfs_direct_good_bytes(dreq, hdr);
spin_unlock(&dreq->lock);
while (!list_empty(&hdr->pages)) {
......@@ -547,6 +602,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter,
dreq->inode = inode;
dreq->bytes_left = count;
dreq->io_start = pos;
dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
l_ctx = nfs_get_lock_context(dreq->ctx);
if (IS_ERR(l_ctx)) {
......@@ -579,6 +635,20 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter,
return result;
}
static void
nfs_direct_write_scan_commit_list(struct inode *inode,
struct list_head *list,
struct nfs_commit_info *cinfo)
{
spin_lock(cinfo->lock);
#ifdef CONFIG_NFS_V4_1
if (cinfo->ds != NULL && cinfo->ds->nwritten != 0)
NFS_SERVER(inode)->pnfs_curr_ld->recover_commit_reqs(list, cinfo);
#endif
nfs_scan_commit_list(&cinfo->mds->list, list, cinfo, 0);
spin_unlock(cinfo->lock);
}
static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
{
struct nfs_pageio_descriptor desc;
......@@ -586,20 +656,23 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
LIST_HEAD(reqs);
struct nfs_commit_info cinfo;
LIST_HEAD(failed);
int i;
nfs_init_cinfo_from_dreq(&cinfo, dreq);
pnfs_recover_commit_reqs(dreq->inode, &reqs, &cinfo);
spin_lock(cinfo.lock);
nfs_scan_commit_list(&cinfo.mds->list, &reqs, &cinfo, 0);
spin_unlock(cinfo.lock);
nfs_direct_write_scan_commit_list(dreq->inode, &reqs, &cinfo);
dreq->count = 0;
for (i = 0; i < dreq->mirror_count; i++)
dreq->mirrors[i].count = 0;
get_dreq(dreq);
nfs_pageio_init_write(&desc, dreq->inode, FLUSH_STABLE, false,
&nfs_direct_write_completion_ops);
desc.pg_dreq = dreq;
req = nfs_list_entry(reqs.next);
nfs_direct_setup_mirroring(dreq, &desc, req);
list_for_each_entry_safe(req, tmp, &reqs, wb_list) {
if (!nfs_pageio_add_request(&desc, req)) {
nfs_list_remove_request(req);
......@@ -646,7 +719,7 @@ static void nfs_direct_commit_complete(struct nfs_commit_data *data)
nfs_list_remove_request(req);
if (dreq->flags == NFS_ODIRECT_RESCHED_WRITES) {
/* Note the rewrite will go through mds */
nfs_mark_request_commit(req, NULL, &cinfo);
nfs_mark_request_commit(req, NULL, &cinfo, 0);
} else
nfs_release_request(req);
nfs_unlock_and_release_request(req);
......@@ -721,7 +794,7 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
dreq->error = hdr->error;
}
if (dreq->error == 0) {
dreq->count += hdr->good_bytes;
nfs_direct_good_bytes(dreq, hdr);
if (nfs_write_need_commit(hdr)) {
if (dreq->flags == NFS_ODIRECT_RESCHED_WRITES)
request_commit = true;
......@@ -745,7 +818,8 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
nfs_list_remove_request(req);
if (request_commit) {
kref_get(&req->wb_kref);
nfs_mark_request_commit(req, hdr->lseg, &cinfo);
nfs_mark_request_commit(req, hdr->lseg, &cinfo,
hdr->ds_commit_idx);
}
nfs_unlock_and_release_request(req);
}
......@@ -826,6 +900,9 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
result = PTR_ERR(req);
break;
}
nfs_direct_setup_mirroring(dreq, &desc, req);
nfs_lock_request(req);
req->wb_index = pos >> PAGE_SHIFT;
req->wb_offset = pos & ~PAGE_MASK;
......@@ -934,6 +1011,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter,
dreq->inode = inode;
dreq->bytes_left = count;
dreq->io_start = pos;
dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
l_ctx = nfs_get_lock_context(dreq->ctx);
if (IS_ERR(l_ctx)) {
......
fs/nfs/filelayout/filelayout.c
浏览文件 @ 6f83e5bd
......@@ -118,13 +118,6 @@ static void filelayout_reset_read(struct nfs_pgio_header *hdr)
}
}
static void filelayout_fenceme(struct inode *inode, struct pnfs_layout_hdr *lo)
{
if (!test_and_clear_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
return;
pnfs_return_layout(inode);
}
static int filelayout_async_handle_error(struct rpc_task *task,
struct nfs4_state *state,
struct nfs_client *clp,
......@@ -207,7 +200,7 @@ static int filelayout_async_handle_error(struct rpc_task *task,
dprintk("%s DS connection error %d\n", __func__,
task->tk_status);
nfs4_mark_deviceid_unavailable(devid);
set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags);
pnfs_error_mark_layout_for_return(inode, lseg);
rpc_wake_up(&tbl->slot_tbl_waitq);
/* fall through */
default:
......@@ -339,16 +332,6 @@ static void filelayout_read_count_stats(struct rpc_task *task, void *data)
rpc_count_iostats(task, NFS_SERVER(hdr->inode)->client->cl_metrics);
}
static void filelayout_read_release(void *data)
{
struct nfs_pgio_header *hdr = data;
struct pnfs_layout_hdr *lo = hdr->lseg->pls_layout;
filelayout_fenceme(lo->plh_inode, lo);
nfs_put_client(hdr->ds_clp);
hdr->mds_ops->rpc_release(data);
}
static int filelayout_write_done_cb(struct rpc_task *task,
struct nfs_pgio_header *hdr)
{
......@@ -371,17 +354,6 @@ static int filelayout_write_done_cb(struct rpc_task *task,
return 0;
}
/* Fake up some data that will cause nfs_commit_release to retry the writes. */
static void prepare_to_resend_writes(struct nfs_commit_data *data)
{
struct nfs_page *first = nfs_list_entry(data->pages.next);
data->task.tk_status = 0;
memcpy(&data->verf.verifier, &first->wb_verf,
sizeof(data->verf.verifier));
data->verf.verifier.data[0]++; /* ensure verifier mismatch */
}
static int filelayout_commit_done_cb(struct rpc_task *task,
struct nfs_commit_data *data)
{
......@@ -393,7 +365,7 @@ static int filelayout_commit_done_cb(struct rpc_task *task,
switch (err) {
case -NFS4ERR_RESET_TO_MDS:
prepare_to_resend_writes(data);
pnfs_generic_prepare_to_resend_writes(data);
return -EAGAIN;
case -EAGAIN:
rpc_restart_call_prepare(task);
......@@ -451,16 +423,6 @@ static void filelayout_write_count_stats(struct rpc_task *task, void *data)
rpc_count_iostats(task, NFS_SERVER(hdr->inode)->client->cl_metrics);
}
static void filelayout_write_release(void *data)
{
struct nfs_pgio_header *hdr = data;
struct pnfs_layout_hdr *lo = hdr->lseg->pls_layout;
filelayout_fenceme(lo->plh_inode, lo);
nfs_put_client(hdr->ds_clp);
hdr->mds_ops->rpc_release(data);
}
static void filelayout_commit_prepare(struct rpc_task *task, void *data)
{
struct nfs_commit_data *wdata = data;
......@@ -471,14 +433,6 @@ static void filelayout_commit_prepare(struct rpc_task *task, void *data)
task);
}
static void filelayout_write_commit_done(struct rpc_task *task, void *data)
{
struct nfs_commit_data *wdata = data;
/* Note this may cause RPC to be resent */
wdata->mds_ops->rpc_call_done(task, data);
}
static void filelayout_commit_count_stats(struct rpc_task *task, void *data)
{
struct nfs_commit_data *cdata = data;
......@@ -486,35 +440,25 @@ static void filelayout_commit_count_stats(struct rpc_task *task, void *data)
rpc_count_iostats(task, NFS_SERVER(cdata->inode)->client->cl_metrics);
}
static void filelayout_commit_release(void *calldata)
{
struct nfs_commit_data *data = calldata;
data->completion_ops->completion(data);
pnfs_put_lseg(data->lseg);
nfs_put_client(data->ds_clp);
nfs_commitdata_release(data);
}
static const struct rpc_call_ops filelayout_read_call_ops = {
.rpc_call_prepare = filelayout_read_prepare,
.rpc_call_done = filelayout_read_call_done,
.rpc_count_stats = filelayout_read_count_stats,
.rpc_release = filelayout_read_release,
.rpc_release = pnfs_generic_rw_release,
};
static const struct rpc_call_ops filelayout_write_call_ops = {
.rpc_call_prepare = filelayout_write_prepare,
.rpc_call_done = filelayout_write_call_done,
.rpc_count_stats = filelayout_write_count_stats,
.rpc_release = filelayout_write_release,
.rpc_release = pnfs_generic_rw_release,
};
static const struct rpc_call_ops filelayout_commit_call_ops = {
.rpc_call_prepare = filelayout_commit_prepare,
.rpc_call_done = filelayout_write_commit_done,
.rpc_call_done = pnfs_generic_write_commit_done,
.rpc_count_stats = filelayout_commit_count_stats,
.rpc_release = filelayout_commit_release,
.rpc_release = pnfs_generic_commit_release,
};
static enum pnfs_try_status
......@@ -548,7 +492,7 @@ filelayout_read_pagelist(struct nfs_pgio_header *hdr)
/* No multipath support. Use first DS */
atomic_inc(&ds->ds_clp->cl_count);
hdr->ds_clp = ds->ds_clp;
hdr->ds_idx = idx;
hdr->ds_commit_idx = idx;
fh = nfs4_fl_select_ds_fh(lseg, j);
if (fh)
hdr->args.fh = fh;
......@@ -557,8 +501,9 @@ filelayout_read_pagelist(struct nfs_pgio_header *hdr)
hdr->mds_offset = offset;
/* Perform an asynchronous read to ds */
nfs_initiate_pgio(ds_clnt, hdr,
&filelayout_read_call_ops, 0, RPC_TASK_SOFTCONN);
nfs_initiate_pgio(ds_clnt, hdr, hdr->cred,
NFS_PROTO(hdr->inode), &filelayout_read_call_ops,
0, RPC_TASK_SOFTCONN);
return PNFS_ATTEMPTED;
}
......@@ -591,16 +536,16 @@ filelayout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
hdr->pgio_done_cb = filelayout_write_done_cb;
atomic_inc(&ds->ds_clp->cl_count);
hdr->ds_clp = ds->ds_clp;
hdr->ds_idx = idx;
hdr->ds_commit_idx = idx;
fh = nfs4_fl_select_ds_fh(lseg, j);
if (fh)
hdr->args.fh = fh;
hdr->args.offset = filelayout_get_dserver_offset(lseg, offset);
/* Perform an asynchronous write */
nfs_initiate_pgio(ds_clnt, hdr,
&filelayout_write_call_ops, sync,
RPC_TASK_SOFTCONN);
nfs_initiate_pgio(ds_clnt, hdr, hdr->cred,
NFS_PROTO(hdr->inode), &filelayout_write_call_ops,
sync, RPC_TASK_SOFTCONN);
return PNFS_ATTEMPTED;
}
......@@ -988,12 +933,14 @@ static const struct nfs_pageio_ops filelayout_pg_read_ops = {
.pg_init = filelayout_pg_init_read,
.pg_test = filelayout_pg_test,
.pg_doio = pnfs_generic_pg_readpages,
.pg_cleanup = pnfs_generic_pg_cleanup,
};
static const struct nfs_pageio_ops filelayout_pg_write_ops = {
.pg_init = filelayout_pg_init_write,
.pg_test = filelayout_pg_test,
.pg_doio = pnfs_generic_pg_writepages,
.pg_cleanup = pnfs_generic_pg_cleanup,
};
static u32 select_bucket_index(struct nfs4_filelayout_segment *fl, u32 j)
......@@ -1004,37 +951,11 @@ static u32 select_bucket_index(struct nfs4_filelayout_segment *fl, u32 j)
return j;
}
/* The generic layer is about to remove the req from the commit list.
* If this will make the bucket empty, it will need to put the lseg reference.
* Note this is must be called holding the inode (/cinfo) lock
*/
static void
filelayout_clear_request_commit(struct nfs_page *req,
struct nfs_commit_info *cinfo)
{
struct pnfs_layout_segment *freeme = NULL;
if (!test_and_clear_bit(PG_COMMIT_TO_DS, &req->wb_flags))
goto out;
cinfo->ds->nwritten--;
if (list_is_singular(&req->wb_list)) {
struct pnfs_commit_bucket *bucket;
bucket = list_first_entry(&req->wb_list,
struct pnfs_commit_bucket,
written);
freeme = bucket->wlseg;
bucket->wlseg = NULL;
}
out:
nfs_request_remove_commit_list(req, cinfo);
pnfs_put_lseg_locked(freeme);
}
static void
filelayout_mark_request_commit(struct nfs_page *req,
struct pnfs_layout_segment *lseg,
struct nfs_commit_info *cinfo)
struct nfs_commit_info *cinfo,
u32 ds_commit_idx)
{
struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg);
......@@ -1064,7 +985,7 @@ filelayout_mark_request_commit(struct nfs_page *req,
* is normally transferred to the COMMIT call and released
* there. It could also be released if the last req is pulled
* off due to a rewrite, in which case it will be done in
* filelayout_clear_request_commit
* pnfs_generic_clear_request_commit
*/
buckets[i].wlseg = pnfs_get_lseg(lseg);
}
......@@ -1138,101 +1059,15 @@ static int filelayout_initiate_commit(struct nfs_commit_data *data, int how)
fh = select_ds_fh_from_commit(lseg, data->ds_commit_index);
if (fh)
data->args.fh = fh;
return nfs_initiate_commit(ds_clnt, data,
return nfs_initiate_commit(ds_clnt, data, NFS_PROTO(data->inode),
&filelayout_commit_call_ops, how,
RPC_TASK_SOFTCONN);
out_err:
prepare_to_resend_writes(data);
filelayout_commit_release(data);
pnfs_generic_prepare_to_resend_writes(data);
pnfs_generic_commit_release(data);
return -EAGAIN;
}
static int
transfer_commit_list(struct list_head *src, struct list_head *dst,
struct nfs_commit_info *cinfo, int max)
{
struct nfs_page *req, *tmp;
int ret = 0;
list_for_each_entry_safe(req, tmp, src, wb_list) {
if (!nfs_lock_request(req))
continue;
kref_get(&req->wb_kref);
if (cond_resched_lock(cinfo->lock))
list_safe_reset_next(req, tmp, wb_list);
nfs_request_remove_commit_list(req, cinfo);
clear_bit(PG_COMMIT_TO_DS, &req->wb_flags);
nfs_list_add_request(req, dst);
ret++;
if ((ret == max) && !cinfo->dreq)
break;
}
return ret;
}
/* Note called with cinfo->lock held. */
static int
filelayout_scan_ds_commit_list(struct pnfs_commit_bucket *bucket,
struct nfs_commit_info *cinfo,
int max)
{
struct list_head *src = &bucket->written;
struct list_head *dst = &bucket->committing;
int ret;
ret = transfer_commit_list(src, dst, cinfo, max);
if (ret) {
cinfo->ds->nwritten -= ret;
cinfo->ds->ncommitting += ret;
bucket->clseg = bucket->wlseg;
if (list_empty(src))
bucket->wlseg = NULL;
else
pnfs_get_lseg(bucket->clseg);
}
return ret;
}
/* Move reqs from written to committing lists, returning count of number moved.
* Note called with cinfo->lock held.
*/
static int filelayout_scan_commit_lists(struct nfs_commit_info *cinfo,
int max)
{
int i, rv = 0, cnt;
for (i = 0; i < cinfo->ds->nbuckets && max != 0; i++) {
cnt = filelayout_scan_ds_commit_list(&cinfo->ds->buckets[i],
cinfo, max);
max -= cnt;
rv += cnt;
}
return rv;
}
/* Pull everything off the committing lists and dump into @dst */
static void filelayout_recover_commit_reqs(struct list_head *dst,
struct nfs_commit_info *cinfo)
{
struct pnfs_commit_bucket *b;
struct pnfs_layout_segment *freeme;
int i;
restart:
spin_lock(cinfo->lock);
for (i = 0, b = cinfo->ds->buckets; i < cinfo->ds->nbuckets; i++, b++) {
if (transfer_commit_list(&b->written, dst, cinfo, 0)) {
freeme = b->wlseg;
b->wlseg = NULL;
spin_unlock(cinfo->lock);
pnfs_put_lseg(freeme);
goto restart;
}
}
cinfo->ds->nwritten = 0;
spin_unlock(cinfo->lock);
}
/* filelayout_search_commit_reqs - Search lists in @cinfo for the head reqest
* for @page
* @cinfo - commit info for current inode
......@@ -1263,108 +1098,14 @@ filelayout_search_commit_reqs(struct nfs_commit_info *cinfo, struct page *page)
return NULL;
}
static void filelayout_retry_commit(struct nfs_commit_info *cinfo, int idx)
{
struct pnfs_ds_commit_info *fl_cinfo = cinfo->ds;
struct pnfs_commit_bucket *bucket;
struct pnfs_layout_segment *freeme;
int i;
for (i = idx; i < fl_cinfo->nbuckets; i++) {
bucket = &fl_cinfo->buckets[i];
if (list_empty(&bucket->committing))
continue;
nfs_retry_commit(&bucket->committing, bucket->clseg, cinfo);
spin_lock(cinfo->lock);
freeme = bucket->clseg;
bucket->clseg = NULL;
spin_unlock(cinfo->lock);
pnfs_put_lseg(freeme);
}
}
static unsigned int
alloc_ds_commits(struct nfs_commit_info *cinfo, struct list_head *list)
{
struct pnfs_ds_commit_info *fl_cinfo;
struct pnfs_commit_bucket *bucket;
struct nfs_commit_data *data;
int i;
unsigned int nreq = 0;
fl_cinfo = cinfo->ds;
bucket = fl_cinfo->buckets;
for (i = 0; i < fl_cinfo->nbuckets; i++, bucket++) {
if (list_empty(&bucket->committing))
continue;
data = nfs_commitdata_alloc();
if (!data)
break;
data->ds_commit_index = i;
spin_lock(cinfo->lock);
data->lseg = bucket->clseg;
bucket->clseg = NULL;
spin_unlock(cinfo->lock);
list_add(&data->pages, list);
nreq++;
}
/* Clean up on error */
filelayout_retry_commit(cinfo, i);
/* Caller will clean up entries put on list */
return nreq;
}
/* This follows nfs_commit_list pretty closely */
static int
filelayout_commit_pagelist(struct inode *inode, struct list_head *mds_pages,
int how, struct nfs_commit_info *cinfo)
{
struct nfs_commit_data *data, *tmp;
LIST_HEAD(list);
unsigned int nreq = 0;
if (!list_empty(mds_pages)) {
data = nfs_commitdata_alloc();
if (data != NULL) {
data->lseg = NULL;
list_add(&data->pages, &list);
nreq++;
} else {
nfs_retry_commit(mds_pages, NULL, cinfo);
filelayout_retry_commit(cinfo, 0);
cinfo->completion_ops->error_cleanup(NFS_I(inode));
return -ENOMEM;
}
}
nreq += alloc_ds_commits(cinfo, &list);
if (nreq == 0) {
cinfo->completion_ops->error_cleanup(NFS_I(inode));
goto out;
}
atomic_add(nreq, &cinfo->mds->rpcs_out);
list_for_each_entry_safe(data, tmp, &list, pages) {
list_del_init(&data->pages);
if (!data->lseg) {
nfs_init_commit(data, mds_pages, NULL, cinfo);
nfs_initiate_commit(NFS_CLIENT(inode), data,
data->mds_ops, how, 0);
} else {
struct pnfs_commit_bucket *buckets;
buckets = cinfo->ds->buckets;
nfs_init_commit(data, &buckets[data->ds_commit_index].committing, data->lseg, cinfo);
filelayout_initiate_commit(data, how);
}
}
out:
cinfo->ds->ncommitting = 0;
return PNFS_ATTEMPTED;
return pnfs_generic_commit_pagelist(inode, mds_pages, how, cinfo,
filelayout_initiate_commit);
}
static struct nfs4_deviceid_node *
filelayout_alloc_deviceid_node(struct nfs_server *server,
struct pnfs_device *pdev, gfp_t gfp_flags)
......@@ -1421,9 +1162,9 @@ static struct pnfs_layoutdriver_type filelayout_type = {
.pg_write_ops = &filelayout_pg_write_ops,
.get_ds_info = &filelayout_get_ds_info,
.mark_request_commit = filelayout_mark_request_commit,
.clear_request_commit = filelayout_clear_request_commit,
.scan_commit_lists = filelayout_scan_commit_lists,
.recover_commit_reqs = filelayout_recover_commit_reqs,
.clear_request_commit = pnfs_generic_clear_request_commit,
.scan_commit_lists = pnfs_generic_scan_commit_lists,
.recover_commit_reqs = pnfs_generic_recover_commit_reqs,
.search_commit_reqs = filelayout_search_commit_reqs,
.commit_pagelist = filelayout_commit_pagelist,
.read_pagelist = filelayout_read_pagelist,
......
fs/nfs/filelayout/filelayout.h
浏览文件 @ 6f83e5bd
......@@ -32,13 +32,6 @@
#include "../pnfs.h"
/*
* Default data server connection timeout and retrans vaules.
* Set by module paramters dataserver_timeo and dataserver_retrans.
*/
#define NFS4_DEF_DS_TIMEO 600 /* in tenths of a second */
#define NFS4_DEF_DS_RETRANS 5
/*
* Field testing shows we need to support up to 4096 stripe indices.
* We store each index as a u8 (u32 on the wire) to keep the memory footprint
......@@ -48,32 +41,11 @@
#define NFS4_PNFS_MAX_STRIPE_CNT 4096
#define NFS4_PNFS_MAX_MULTI_CNT 256 /* 256 fit into a u8 stripe_index */
/* error codes for internal use */
#define NFS4ERR_RESET_TO_MDS 12001
enum stripetype4 {
STRIPE_SPARSE = 1,
STRIPE_DENSE = 2
};
/* Individual ip address */
struct nfs4_pnfs_ds_addr {
struct sockaddr_storage da_addr;
size_t da_addrlen;
struct list_head da_node; /* nfs4_pnfs_dev_hlist dev_dslist */
char *da_remotestr; /* human readable addr+port */
};
struct nfs4_pnfs_ds {
struct list_head ds_node; /* nfs4_pnfs_dev_hlist dev_dslist */
char *ds_remotestr; /* comma sep list of addrs */
struct list_head ds_addrs;
struct nfs_client *ds_clp;
atomic_t ds_count;
unsigned long ds_state;
#define NFS4DS_CONNECTING 0 /* ds is establishing connection */
};
struct nfs4_file_layout_dsaddr {
struct nfs4_deviceid_node id_node;
u32 stripe_count;
......@@ -119,17 +91,6 @@ FILELAYOUT_DEVID_NODE(struct pnfs_layout_segment *lseg)
return &FILELAYOUT_LSEG(lseg)->dsaddr->id_node;
}
static inline void
filelayout_mark_devid_invalid(struct nfs4_deviceid_node *node)
{
u32 *p = (u32 *)&node->deviceid;
printk(KERN_WARNING "NFS: Deviceid [%x%x%x%x] marked out of use.\n",
p[0], p[1], p[2], p[3]);
set_bit(NFS_DEVICEID_INVALID, &node->flags);
}
static inline bool
filelayout_test_devid_invalid(struct nfs4_deviceid_node *node)
{
......@@ -142,7 +103,6 @@ filelayout_test_devid_unavailable(struct nfs4_deviceid_node *node);
extern struct nfs_fh *
nfs4_fl_select_ds_fh(struct pnfs_layout_segment *lseg, u32 j);
extern void print_ds(struct nfs4_pnfs_ds *ds);
u32 nfs4_fl_calc_j_index(struct pnfs_layout_segment *lseg, loff_t offset);
u32 nfs4_fl_calc_ds_index(struct pnfs_layout_segment *lseg, u32 j);
struct nfs4_pnfs_ds *nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg,
......
fs/nfs/filelayout/filelayoutdev.c
浏览文件 @ 6f83e5bd
......@@ -31,7 +31,6 @@
#include <linux/nfs_fs.h>
#include <linux/vmalloc.h>
#include <linux/module.h>
#include <linux/sunrpc/addr.h>
#include "../internal.h"
#include "../nfs4session.h"
......@@ -42,183 +41,6 @@
static unsigned int dataserver_timeo = NFS4_DEF_DS_TIMEO;
static unsigned int dataserver_retrans = NFS4_DEF_DS_RETRANS;
/*
* Data server cache
*
* Data servers can be mapped to different device ids.
* nfs4_pnfs_ds reference counting
* - set to 1 on allocation
* - incremented when a device id maps a data server already in the cache.
* - decremented when deviceid is removed from the cache.
*/
static DEFINE_SPINLOCK(nfs4_ds_cache_lock);
static LIST_HEAD(nfs4_data_server_cache);
/* Debug routines */
void
print_ds(struct nfs4_pnfs_ds *ds)
{
if (ds == NULL) {
printk("%s NULL device\n", __func__);
return;
}
printk(" ds %s\n"
" ref count %d\n"
" client %p\n"
" cl_exchange_flags %x\n",
ds->ds_remotestr,
atomic_read(&ds->ds_count), ds->ds_clp,
ds->ds_clp ? ds->ds_clp->cl_exchange_flags : 0);
}
static bool
same_sockaddr(struct sockaddr *addr1, struct sockaddr *addr2)
{
struct sockaddr_in *a, *b;
struct sockaddr_in6 *a6, *b6;
if (addr1->sa_family != addr2->sa_family)
return false;
switch (addr1->sa_family) {
case AF_INET:
a = (struct sockaddr_in *)addr1;
b = (struct sockaddr_in *)addr2;
if (a->sin_addr.s_addr == b->sin_addr.s_addr &&
a->sin_port == b->sin_port)
return true;
break;
case AF_INET6:
a6 = (struct sockaddr_in6 *)addr1;
b6 = (struct sockaddr_in6 *)addr2;
/* LINKLOCAL addresses must have matching scope_id */
if (ipv6_addr_src_scope(&a6->sin6_addr) ==
IPV6_ADDR_SCOPE_LINKLOCAL &&
a6->sin6_scope_id != b6->sin6_scope_id)
return false;
if (ipv6_addr_equal(&a6->sin6_addr, &b6->sin6_addr) &&
a6->sin6_port == b6->sin6_port)
return true;
break;
default:
dprintk("%s: unhandled address family: %u\n",
__func__, addr1->sa_family);
return false;
}
return false;
}
static bool
_same_data_server_addrs_locked(const struct list_head *dsaddrs1,
const struct list_head *dsaddrs2)
{
struct nfs4_pnfs_ds_addr *da1, *da2;
/* step through both lists, comparing as we go */
for (da1 = list_first_entry(dsaddrs1, typeof(*da1), da_node),
da2 = list_first_entry(dsaddrs2, typeof(*da2), da_node);
da1 != NULL && da2 != NULL;
da1 = list_entry(da1->da_node.next, typeof(*da1), da_node),
da2 = list_entry(da2->da_node.next, typeof(*da2), da_node)) {
if (!same_sockaddr((struct sockaddr *)&da1->da_addr,
(struct sockaddr *)&da2->da_addr))
return false;
}
if (da1 == NULL && da2 == NULL)
return true;
return false;
}
/*
* Lookup DS by addresses. nfs4_ds_cache_lock is held
*/
static struct nfs4_pnfs_ds *
_data_server_lookup_locked(const struct list_head *dsaddrs)
{
struct nfs4_pnfs_ds *ds;
list_for_each_entry(ds, &nfs4_data_server_cache, ds_node)
if (_same_data_server_addrs_locked(&ds->ds_addrs, dsaddrs))
return ds;
return NULL;
}
/*
* Create an rpc connection to the nfs4_pnfs_ds data server
* Currently only supports IPv4 and IPv6 addresses
*/
static int
nfs4_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds)
{
struct nfs_client *clp = ERR_PTR(-EIO);
struct nfs4_pnfs_ds_addr *da;
int status = 0;
dprintk("--> %s DS %s au_flavor %d\n", __func__, ds->ds_remotestr,
mds_srv->nfs_client->cl_rpcclient->cl_auth->au_flavor);
list_for_each_entry(da, &ds->ds_addrs, da_node) {
dprintk("%s: DS %s: trying address %s\n",
__func__, ds->ds_remotestr, da->da_remotestr);
clp = nfs4_set_ds_client(mds_srv->nfs_client,
(struct sockaddr *)&da->da_addr,
da->da_addrlen, IPPROTO_TCP,
dataserver_timeo, dataserver_retrans);
if (!IS_ERR(clp))
break;
}
if (IS_ERR(clp)) {
status = PTR_ERR(clp);
goto out;
}
status = nfs4_init_ds_session(clp, mds_srv->nfs_client->cl_lease_time);
if (status)
goto out_put;
smp_wmb();
ds->ds_clp = clp;
dprintk("%s [new] addr: %s\n", __func__, ds->ds_remotestr);
out:
return status;
out_put:
nfs_put_client(clp);
goto out;
}
static void
destroy_ds(struct nfs4_pnfs_ds *ds)
{
struct nfs4_pnfs_ds_addr *da;
dprintk("--> %s\n", __func__);
ifdebug(FACILITY)
print_ds(ds);
nfs_put_client(ds->ds_clp);
while (!list_empty(&ds->ds_addrs)) {
da = list_first_entry(&ds->ds_addrs,
struct nfs4_pnfs_ds_addr,
da_node);
list_del_init(&da->da_node);
kfree(da->da_remotestr);
kfree(da);
}
kfree(ds->ds_remotestr);
kfree(ds);
}
void
nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr)
{
......@@ -229,259 +51,13 @@ nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr)
for (i = 0; i < dsaddr->ds_num; i++) {
ds = dsaddr->ds_list[i];
if (ds != NULL) {
if (atomic_dec_and_lock(&ds->ds_count,
&nfs4_ds_cache_lock)) {
list_del_init(&ds->ds_node);
spin_unlock(&nfs4_ds_cache_lock);
destroy_ds(ds);
}
}
if (ds != NULL)
nfs4_pnfs_ds_put(ds);
}
kfree(dsaddr->stripe_indices);
kfree(dsaddr);
}
/*
* Create a string with a human readable address and port to avoid
* complicated setup around many dprinks.
*/
static char *
nfs4_pnfs_remotestr(struct list_head *dsaddrs, gfp_t gfp_flags)
{
struct nfs4_pnfs_ds_addr *da;
char *remotestr;
size_t len;
char *p;
len = 3; /* '{', '}' and eol */
list_for_each_entry(da, dsaddrs, da_node) {
len += strlen(da->da_remotestr) + 1; /* string plus comma */
}
remotestr = kzalloc(len, gfp_flags);
if (!remotestr)
return NULL;
p = remotestr;
*(p++) = '{';
len--;
list_for_each_entry(da, dsaddrs, da_node) {
size_t ll = strlen(da->da_remotestr);
if (ll > len)
goto out_err;
memcpy(p, da->da_remotestr, ll);
p += ll;
len -= ll;
if (len < 1)
goto out_err;
(*p++) = ',';
len--;
}
if (len < 2)
goto out_err;
*(p++) = '}';
*p = '\0';
return remotestr;
out_err:
kfree(remotestr);
return NULL;
}
static struct nfs4_pnfs_ds *
nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags)
{
struct nfs4_pnfs_ds *tmp_ds, *ds = NULL;
char *remotestr;
if (list_empty(dsaddrs)) {
dprintk("%s: no addresses defined\n", __func__);
goto out;
}
ds = kzalloc(sizeof(*ds), gfp_flags);
if (!ds)
goto out;
/* this is only used for debugging, so it's ok if its NULL */
remotestr = nfs4_pnfs_remotestr(dsaddrs, gfp_flags);
spin_lock(&nfs4_ds_cache_lock);
tmp_ds = _data_server_lookup_locked(dsaddrs);
if (tmp_ds == NULL) {
INIT_LIST_HEAD(&ds->ds_addrs);
list_splice_init(dsaddrs, &ds->ds_addrs);
ds->ds_remotestr = remotestr;
atomic_set(&ds->ds_count, 1);
INIT_LIST_HEAD(&ds->ds_node);
ds->ds_clp = NULL;
list_add(&ds->ds_node, &nfs4_data_server_cache);
dprintk("%s add new data server %s\n", __func__,
ds->ds_remotestr);
} else {
kfree(remotestr);
kfree(ds);
atomic_inc(&tmp_ds->ds_count);
dprintk("%s data server %s found, inc'ed ds_count to %d\n",
__func__, tmp_ds->ds_remotestr,
atomic_read(&tmp_ds->ds_count));
ds = tmp_ds;
}
spin_unlock(&nfs4_ds_cache_lock);
out:
return ds;
}
/*
* Currently only supports ipv4, ipv6 and one multi-path address.
*/
static struct nfs4_pnfs_ds_addr *
decode_ds_addr(struct net *net, struct xdr_stream *streamp, gfp_t gfp_flags)
{
struct nfs4_pnfs_ds_addr *da = NULL;
char *buf, *portstr;
__be16 port;
int nlen, rlen;
int tmp[2];
__be32 *p;
char *netid, *match_netid;
size_t len, match_netid_len;
char *startsep = "";
char *endsep = "";
/* r_netid */
p = xdr_inline_decode(streamp, 4);
if (unlikely(!p))
goto out_err;
nlen = be32_to_cpup(p++);
p = xdr_inline_decode(streamp, nlen);
if (unlikely(!p))
goto out_err;
netid = kmalloc(nlen+1, gfp_flags);
if (unlikely(!netid))
goto out_err;
netid[nlen] = '\0';
memcpy(netid, p, nlen);
/* r_addr: ip/ip6addr with port in dec octets - see RFC 5665 */
p = xdr_inline_decode(streamp, 4);
if (unlikely(!p))
goto out_free_netid;
rlen = be32_to_cpup(p);
p = xdr_inline_decode(streamp, rlen);
if (unlikely(!p))
goto out_free_netid;
/* port is ".ABC.DEF", 8 chars max */
if (rlen > INET6_ADDRSTRLEN + IPV6_SCOPE_ID_LEN + 8) {
dprintk("%s: Invalid address, length %d\n", __func__,
rlen);
goto out_free_netid;
}
buf = kmalloc(rlen + 1, gfp_flags);
if (!buf) {
dprintk("%s: Not enough memory\n", __func__);
goto out_free_netid;
}
buf[rlen] = '\0';
memcpy(buf, p, rlen);
/* replace port '.' with '-' */
portstr = strrchr(buf, '.');
if (!portstr) {
dprintk("%s: Failed finding expected dot in port\n",
__func__);
goto out_free_buf;
}
*portstr = '-';
/* find '.' between address and port */
portstr = strrchr(buf, '.');
if (!portstr) {
dprintk("%s: Failed finding expected dot between address and "
"port\n", __func__);
goto out_free_buf;
}
*portstr = '\0';
da = kzalloc(sizeof(*da), gfp_flags);
if (unlikely(!da))
goto out_free_buf;
INIT_LIST_HEAD(&da->da_node);
if (!rpc_pton(net, buf, portstr-buf, (struct sockaddr *)&da->da_addr,
sizeof(da->da_addr))) {
dprintk("%s: error parsing address %s\n", __func__, buf);
goto out_free_da;
}
portstr++;
sscanf(portstr, "%d-%d", &tmp[0], &tmp[1]);
port = htons((tmp[0] << 8) | (tmp[1]));
switch (da->da_addr.ss_family) {
case AF_INET:
((struct sockaddr_in *)&da->da_addr)->sin_port = port;
da->da_addrlen = sizeof(struct sockaddr_in);
match_netid = "tcp";
match_netid_len = 3;
break;
case AF_INET6:
((struct sockaddr_in6 *)&da->da_addr)->sin6_port = port;
da->da_addrlen = sizeof(struct sockaddr_in6);
match_netid = "tcp6";
match_netid_len = 4;
startsep = "[";
endsep = "]";
break;
default:
dprintk("%s: unsupported address family: %u\n",
__func__, da->da_addr.ss_family);
goto out_free_da;
}
if (nlen != match_netid_len || strncmp(netid, match_netid, nlen)) {
dprintk("%s: ERROR: r_netid \"%s\" != \"%s\"\n",
__func__, netid, match_netid);
goto out_free_da;
}
/* save human readable address */
len = strlen(startsep) + strlen(buf) + strlen(endsep) + 7;
da->da_remotestr = kzalloc(len, gfp_flags);
/* NULL is ok, only used for dprintk */
if (da->da_remotestr)
snprintf(da->da_remotestr, len, "%s%s%s:%u", startsep,
buf, endsep, ntohs(port));
dprintk("%s: Parsed DS addr %s\n", __func__, da->da_remotestr);
kfree(buf);
kfree(netid);
return da;
out_free_da:
kfree(da);
out_free_buf:
dprintk("%s: Error parsing DS addr: %s\n", __func__, buf);
kfree(buf);
out_free_netid:
kfree(netid);
out_err:
return NULL;
}
/* Decode opaque device data and return the result */
struct nfs4_file_layout_dsaddr *
nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
......@@ -584,8 +160,8 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
mp_count = be32_to_cpup(p); /* multipath count */
for (j = 0; j < mp_count; j++) {
da = decode_ds_addr(server->nfs_client->cl_net,
&stream, gfp_flags);
da = nfs4_decode_mp_ds_addr(server->nfs_client->cl_net,
&stream, gfp_flags);
if (da)
list_add_tail(&da->da_node, &dsaddrs);
}
......@@ -681,22 +257,7 @@ nfs4_fl_select_ds_fh(struct pnfs_layout_segment *lseg, u32 j)
return flseg->fh_array[i];
}
static void nfs4_wait_ds_connect(struct nfs4_pnfs_ds *ds)
{
might_sleep();
wait_on_bit_action(&ds->ds_state, NFS4DS_CONNECTING,
nfs_wait_bit_killable, TASK_KILLABLE);
}
static void nfs4_clear_ds_conn_bit(struct nfs4_pnfs_ds *ds)
{
smp_mb__before_atomic();
clear_bit(NFS4DS_CONNECTING, &ds->ds_state);
smp_mb__after_atomic();
wake_up_bit(&ds->ds_state, NFS4DS_CONNECTING);
}
/* Upon return, either ds is connected, or ds is NULL */
struct nfs4_pnfs_ds *
nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx)
{
......@@ -704,29 +265,23 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx)
struct nfs4_pnfs_ds *ds = dsaddr->ds_list[ds_idx];
struct nfs4_deviceid_node *devid = FILELAYOUT_DEVID_NODE(lseg);
struct nfs4_pnfs_ds *ret = ds;
struct nfs_server *s = NFS_SERVER(lseg->pls_layout->plh_inode);
if (ds == NULL) {
printk(KERN_ERR "NFS: %s: No data server for offset index %d\n",
__func__, ds_idx);
filelayout_mark_devid_invalid(devid);
pnfs_generic_mark_devid_invalid(devid);
goto out;
}
smp_rmb();
if (ds->ds_clp)
goto out_test_devid;
if (test_and_set_bit(NFS4DS_CONNECTING, &ds->ds_state) == 0) {
struct nfs_server *s = NFS_SERVER(lseg->pls_layout->plh_inode);
int err;
err = nfs4_ds_connect(s, ds);
if (err)
nfs4_mark_deviceid_unavailable(devid);
nfs4_clear_ds_conn_bit(ds);
} else {
/* Either ds is connected, or ds is NULL */
nfs4_wait_ds_connect(ds);
}
nfs4_pnfs_ds_connect(s, ds, devid, dataserver_timeo,
dataserver_retrans, 4,
s->nfs_client->cl_minorversion,
s->nfs_client->cl_rpcclient->cl_auth->au_flavor);
out_test_devid:
if (filelayout_test_devid_unavailable(devid))
ret = NULL;
......
fs/nfs/flexfilelayout/Makefile 0 → 100644
浏览文件 @ 6f83e5bd
#
# Makefile for the pNFS Flexfile Layout Driver kernel module
#
obj-$(CONFIG_PNFS_FLEXFILE_LAYOUT) += nfs_layout_flexfiles.o
nfs_layout_flexfiles-y := flexfilelayout.o flexfilelayoutdev.o
fs/nfs/flexfilelayout/flexfilelayout.c 0 → 100644
浏览文件 @ 6f83e5bd
此差异已折叠。
fs/nfs/flexfilelayout/flexfilelayout.h 0 → 100644
浏览文件 @ 6f83e5bd
/*
* NFSv4 flexfile layout driver data structures.
*
* Copyright (c) 2014, Primary Data, Inc. All rights reserved.
*
* Tao Peng <bergwolf@primarydata.com>
*/
#ifndef FS_NFS_NFS4FLEXFILELAYOUT_H
#define FS_NFS_NFS4FLEXFILELAYOUT_H
#include "../pnfs.h"
/* XXX: Let's filter out insanely large mirror count for now to avoid oom
* due to network error etc. */
#define NFS4_FLEXFILE_LAYOUT_MAX_MIRROR_CNT 4096
struct nfs4_ff_ds_version {
u32 version;
u32 minor_version;
u32 rsize;
u32 wsize;
bool tightly_coupled;
};
/* chained in global deviceid hlist */
struct nfs4_ff_layout_ds {
struct nfs4_deviceid_node id_node;
u32 ds_versions_cnt;
struct nfs4_ff_ds_version *ds_versions;
struct nfs4_pnfs_ds *ds;
};
struct nfs4_ff_layout_ds_err {
struct list_head list; /* linked in mirror error_list */
u64 offset;
u64 length;
int status;
enum nfs_opnum4 opnum;
nfs4_stateid stateid;
struct nfs4_deviceid deviceid;
};
struct nfs4_ff_layout_mirror {
u32 ds_count;
u32 efficiency;
struct nfs4_ff_layout_ds *mirror_ds;
u32 fh_versions_cnt;
struct nfs_fh *fh_versions;
nfs4_stateid stateid;
struct nfs4_string user_name;
struct nfs4_string group_name;
u32 uid;
u32 gid;
struct rpc_cred *cred;
spinlock_t lock;
};
struct nfs4_ff_layout_segment {
struct pnfs_layout_segment generic_hdr;
u64 stripe_unit;
u32 mirror_array_cnt;
struct nfs4_ff_layout_mirror **mirror_array;
};
struct nfs4_flexfile_layout {
struct pnfs_layout_hdr generic_hdr;
struct pnfs_ds_commit_info commit_info;
struct list_head error_list; /* nfs4_ff_layout_ds_err */
};
static inline struct nfs4_flexfile_layout *
FF_LAYOUT_FROM_HDR(struct pnfs_layout_hdr *lo)
{
return container_of(lo, struct nfs4_flexfile_layout, generic_hdr);
}
static inline struct nfs4_ff_layout_segment *
FF_LAYOUT_LSEG(struct pnfs_layout_segment *lseg)
{
return container_of(lseg,
struct nfs4_ff_layout_segment,
generic_hdr);
}
static inline struct nfs4_deviceid_node *
FF_LAYOUT_DEVID_NODE(struct pnfs_layout_segment *lseg, u32 idx)
{
if (idx >= FF_LAYOUT_LSEG(lseg)->mirror_array_cnt ||
FF_LAYOUT_LSEG(lseg)->mirror_array[idx] == NULL ||
FF_LAYOUT_LSEG(lseg)->mirror_array[idx]->mirror_ds == NULL)
return NULL;
return &FF_LAYOUT_LSEG(lseg)->mirror_array[idx]->mirror_ds->id_node;
}
static inline struct nfs4_ff_layout_ds *
FF_LAYOUT_MIRROR_DS(struct nfs4_deviceid_node *node)
{
return container_of(node, struct nfs4_ff_layout_ds, id_node);
}
static inline struct nfs4_ff_layout_mirror *
FF_LAYOUT_COMP(struct pnfs_layout_segment *lseg, u32 idx)
{
if (idx >= FF_LAYOUT_LSEG(lseg)->mirror_array_cnt)
return NULL;
return FF_LAYOUT_LSEG(lseg)->mirror_array[idx];
}
static inline u32
FF_LAYOUT_MIRROR_COUNT(struct pnfs_layout_segment *lseg)
{
return FF_LAYOUT_LSEG(lseg)->mirror_array_cnt;
}
static inline bool
ff_layout_test_devid_unavailable(struct nfs4_deviceid_node *node)
{
return nfs4_test_deviceid_unavailable(node);
}
static inline int
nfs4_ff_layout_ds_version(struct pnfs_layout_segment *lseg, u32 ds_idx)
{
return FF_LAYOUT_COMP(lseg, ds_idx)->mirror_ds->ds_versions[0].version;
}
struct nfs4_ff_layout_ds *
nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
gfp_t gfp_flags);
void nfs4_ff_layout_put_deviceid(struct nfs4_ff_layout_ds *mirror_ds);
void nfs4_ff_layout_free_deviceid(struct nfs4_ff_layout_ds *mirror_ds);
int ff_layout_track_ds_error(struct nfs4_flexfile_layout *flo,
struct nfs4_ff_layout_mirror *mirror, u64 offset,
u64 length, int status, enum nfs_opnum4 opnum,
gfp_t gfp_flags);
int ff_layout_encode_ds_ioerr(struct nfs4_flexfile_layout *flo,
struct xdr_stream *xdr, int *count,
const struct pnfs_layout_range *range);
struct nfs_fh *
nfs4_ff_layout_select_ds_fh(struct pnfs_layout_segment *lseg, u32 mirror_idx);
struct nfs4_pnfs_ds *
nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx,
bool fail_return);
struct rpc_clnt *
nfs4_ff_find_or_create_ds_client(struct pnfs_layout_segment *lseg,
u32 ds_idx,
struct nfs_client *ds_clp,
struct inode *inode);
struct rpc_cred *ff_layout_get_ds_cred(struct pnfs_layout_segment *lseg,
u32 ds_idx, struct rpc_cred *mdscred);
bool ff_layout_has_available_ds(struct pnfs_layout_segment *lseg);
#endif /* FS_NFS_NFS4FLEXFILELAYOUT_H */
fs/nfs/flexfilelayout/flexfilelayoutdev.c 0 → 100644
浏览文件 @ 6f83e5bd
/*
* Device operations for the pnfs nfs4 file layout driver.
*
* Copyright (c) 2014, Primary Data, Inc. All rights reserved.
*
* Tao Peng <bergwolf@primarydata.com>
*/
#include <linux/nfs_fs.h>
#include <linux/vmalloc.h>
#include <linux/module.h>
#include <linux/sunrpc/addr.h>
#include "../internal.h"
#include "../nfs4session.h"
#include "flexfilelayout.h"
#define NFSDBG_FACILITY NFSDBG_PNFS_LD
static unsigned int dataserver_timeo = NFS4_DEF_DS_TIMEO;
static unsigned int dataserver_retrans = NFS4_DEF_DS_RETRANS;
void nfs4_ff_layout_put_deviceid(struct nfs4_ff_layout_ds *mirror_ds)
{
if (mirror_ds)
nfs4_put_deviceid_node(&mirror_ds->id_node);
}
void nfs4_ff_layout_free_deviceid(struct nfs4_ff_layout_ds *mirror_ds)
{
nfs4_print_deviceid(&mirror_ds->id_node.deviceid);
nfs4_pnfs_ds_put(mirror_ds->ds);
kfree(mirror_ds);
}
/* Decode opaque device data and construct new_ds using it */
struct nfs4_ff_layout_ds *
nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
gfp_t gfp_flags)
{
struct xdr_stream stream;
struct xdr_buf buf;
struct page *scratch;
struct list_head dsaddrs;
struct nfs4_pnfs_ds_addr *da;
struct nfs4_ff_layout_ds *new_ds = NULL;
struct nfs4_ff_ds_version *ds_versions = NULL;
u32 mp_count;
u32 version_count;
__be32 *p;
int i, ret = -ENOMEM;
/* set up xdr stream */
scratch = alloc_page(gfp_flags);
if (!scratch)
goto out_err;
new_ds = kzalloc(sizeof(struct nfs4_ff_layout_ds), gfp_flags);
if (!new_ds)
goto out_scratch;
nfs4_init_deviceid_node(&new_ds->id_node,
server,
&pdev->dev_id);
INIT_LIST_HEAD(&dsaddrs);
xdr_init_decode_pages(&stream, &buf, pdev->pages, pdev->pglen);
xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
/* multipath count */
p = xdr_inline_decode(&stream, 4);
if (unlikely(!p))
goto out_err_drain_dsaddrs;
mp_count = be32_to_cpup(p);
dprintk("%s: multipath ds count %d\n", __func__, mp_count);
for (i = 0; i < mp_count; i++) {
/* multipath ds */
da = nfs4_decode_mp_ds_addr(server->nfs_client->cl_net,
&stream, gfp_flags);
if (da)
list_add_tail(&da->da_node, &dsaddrs);
}
if (list_empty(&dsaddrs)) {
dprintk("%s: no suitable DS addresses found\n",
__func__);
ret = -ENOMEDIUM;
goto out_err_drain_dsaddrs;
}
/* version count */
p = xdr_inline_decode(&stream, 4);
if (unlikely(!p))
goto out_err_drain_dsaddrs;
version_count = be32_to_cpup(p);
dprintk("%s: version count %d\n", __func__, version_count);
ds_versions = kzalloc(version_count * sizeof(struct nfs4_ff_ds_version),
gfp_flags);
if (!ds_versions)
goto out_scratch;
for (i = 0; i < version_count; i++) {
/* 20 = version(4) + minor_version(4) + rsize(4) + wsize(4) +
* tightly_coupled(4) */
p = xdr_inline_decode(&stream, 20);
if (unlikely(!p))
goto out_err_drain_dsaddrs;
ds_versions[i].version = be32_to_cpup(p++);
ds_versions[i].minor_version = be32_to_cpup(p++);
ds_versions[i].rsize = nfs_block_size(be32_to_cpup(p++), NULL);
ds_versions[i].wsize = nfs_block_size(be32_to_cpup(p++), NULL);
ds_versions[i].tightly_coupled = be32_to_cpup(p);
if (ds_versions[i].rsize > NFS_MAX_FILE_IO_SIZE)
ds_versions[i].rsize = NFS_MAX_FILE_IO_SIZE;
if (ds_versions[i].wsize > NFS_MAX_FILE_IO_SIZE)
ds_versions[i].wsize = NFS_MAX_FILE_IO_SIZE;
if (ds_versions[i].version != 3 || ds_versions[i].minor_version != 0) {
dprintk("%s: [%d] unsupported ds version %d-%d\n", __func__,
i, ds_versions[i].version,
ds_versions[i].minor_version);
ret = -EPROTONOSUPPORT;
goto out_err_drain_dsaddrs;
}
dprintk("%s: [%d] vers %u minor_ver %u rsize %u wsize %u coupled %d\n",
__func__, i, ds_versions[i].version,
ds_versions[i].minor_version,
ds_versions[i].rsize,
ds_versions[i].wsize,
ds_versions[i].tightly_coupled);
}
new_ds->ds_versions = ds_versions;
new_ds->ds_versions_cnt = version_count;
new_ds->ds = nfs4_pnfs_ds_add(&dsaddrs, gfp_flags);
if (!new_ds->ds)
goto out_err_drain_dsaddrs;
/* If DS was already in cache, free ds addrs */
while (!list_empty(&dsaddrs)) {
da = list_first_entry(&dsaddrs,
struct nfs4_pnfs_ds_addr,
da_node);
list_del_init(&da->da_node);
kfree(da->da_remotestr);
kfree(da);
}
__free_page(scratch);
return new_ds;
out_err_drain_dsaddrs:
while (!list_empty(&dsaddrs)) {
da = list_first_entry(&dsaddrs, struct nfs4_pnfs_ds_addr,
da_node);
list_del_init(&da->da_node);
kfree(da->da_remotestr);
kfree(da);
}
kfree(ds_versions);
out_scratch:
__free_page(scratch);
out_err:
kfree(new_ds);
dprintk("%s ERROR: returning %d\n", __func__, ret);
return NULL;
}
static u64
end_offset(u64 start, u64 len)
{
u64 end;
end = start + len;
return end >= start ? end : NFS4_MAX_UINT64;
}
static void extend_ds_error(struct nfs4_ff_layout_ds_err *err,
u64 offset, u64 length)
{
u64 end;
end = max_t(u64, end_offset(err->offset, err->length),
end_offset(offset, length));
err->offset = min_t(u64, err->offset, offset);
err->length = end - err->offset;
}
static bool ds_error_can_merge(struct nfs4_ff_layout_ds_err *err, u64 offset,
u64 length, int status, enum nfs_opnum4 opnum,
nfs4_stateid *stateid,
struct nfs4_deviceid *deviceid)
{
return err->status == status && err->opnum == opnum &&
nfs4_stateid_match(&err->stateid, stateid) &&
!memcmp(&err->deviceid, deviceid, sizeof(*deviceid)) &&
end_offset(err->offset, err->length) >= offset &&
err->offset <= end_offset(offset, length);
}
static bool merge_ds_error(struct nfs4_ff_layout_ds_err *old,
struct nfs4_ff_layout_ds_err *new)
{
if (!ds_error_can_merge(old, new->offset, new->length, new->status,
new->opnum, &new->stateid, &new->deviceid))
return false;
extend_ds_error(old, new->offset, new->length);
return true;
}
static bool
ff_layout_add_ds_error_locked(struct nfs4_flexfile_layout *flo,
struct nfs4_ff_layout_ds_err *dserr)
{
struct nfs4_ff_layout_ds_err *err;
list_for_each_entry(err, &flo->error_list, list) {
if (merge_ds_error(err, dserr)) {
return true;
}
}
list_add(&dserr->list, &flo->error_list);
return false;
}
static bool
ff_layout_update_ds_error(struct nfs4_flexfile_layout *flo, u64 offset,
u64 length, int status, enum nfs_opnum4 opnum,
nfs4_stateid *stateid, struct nfs4_deviceid *deviceid)
{
bool found = false;
struct nfs4_ff_layout_ds_err *err;
list_for_each_entry(err, &flo->error_list, list) {
if (ds_error_can_merge(err, offset, length, status, opnum,
stateid, deviceid)) {
found = true;
extend_ds_error(err, offset, length);
break;
}
}
return found;
}
int ff_layout_track_ds_error(struct nfs4_flexfile_layout *flo,
struct nfs4_ff_layout_mirror *mirror, u64 offset,
u64 length, int status, enum nfs_opnum4 opnum,
gfp_t gfp_flags)
{
struct nfs4_ff_layout_ds_err *dserr;
bool needfree;
if (status == 0)
return 0;
if (mirror->mirror_ds == NULL)
return -EINVAL;
spin_lock(&flo->generic_hdr.plh_inode->i_lock);
if (ff_layout_update_ds_error(flo, offset, length, status, opnum,
&mirror->stateid,
&mirror->mirror_ds->id_node.deviceid)) {
spin_unlock(&flo->generic_hdr.plh_inode->i_lock);
return 0;
}
spin_unlock(&flo->generic_hdr.plh_inode->i_lock);
dserr = kmalloc(sizeof(*dserr), gfp_flags);
if (!dserr)
return -ENOMEM;
INIT_LIST_HEAD(&dserr->list);
dserr->offset = offset;
dserr->length = length;
dserr->status = status;
dserr->opnum = opnum;
nfs4_stateid_copy(&dserr->stateid, &mirror->stateid);
memcpy(&dserr->deviceid, &mirror->mirror_ds->id_node.deviceid,
NFS4_DEVICEID4_SIZE);
spin_lock(&flo->generic_hdr.plh_inode->i_lock);
needfree = ff_layout_add_ds_error_locked(flo, dserr);
spin_unlock(&flo->generic_hdr.plh_inode->i_lock);
if (needfree)
kfree(dserr);
return 0;
}
/* currently we only support AUTH_NONE and AUTH_SYS */
static rpc_authflavor_t
nfs4_ff_layout_choose_authflavor(struct nfs4_ff_layout_mirror *mirror)
{
if (mirror->uid == (u32)-1)
return RPC_AUTH_NULL;
return RPC_AUTH_UNIX;
}
/* fetch cred for NFSv3 DS */
static int ff_layout_update_mirror_cred(struct nfs4_ff_layout_mirror *mirror,
struct nfs4_pnfs_ds *ds)
{
if (ds->ds_clp && !mirror->cred &&
mirror->mirror_ds->ds_versions[0].version == 3) {
struct rpc_auth *auth = ds->ds_clp->cl_rpcclient->cl_auth;
struct rpc_cred *cred;
struct auth_cred acred = {
.uid = make_kuid(&init_user_ns, mirror->uid),
.gid = make_kgid(&init_user_ns, mirror->gid),
};
/* AUTH_NULL ignores acred */
cred = auth->au_ops->lookup_cred(auth, &acred, 0);
if (IS_ERR(cred)) {
dprintk("%s: lookup_cred failed with %ld\n",
__func__, PTR_ERR(cred));
return PTR_ERR(cred);
} else {
mirror->cred = cred;
}
}
return 0;
}
struct nfs_fh *
nfs4_ff_layout_select_ds_fh(struct pnfs_layout_segment *lseg, u32 mirror_idx)
{
struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, mirror_idx);
struct nfs_fh *fh = NULL;
struct nfs4_deviceid_node *devid;
if (mirror == NULL || mirror->mirror_ds == NULL ||
mirror->mirror_ds->ds == NULL) {
printk(KERN_ERR "NFS: %s: No data server for mirror offset index %d\n",
__func__, mirror_idx);
if (mirror && mirror->mirror_ds) {
devid = &mirror->mirror_ds->id_node;
pnfs_generic_mark_devid_invalid(devid);
}
goto out;
}
/* FIXME: For now assume there is only 1 version available for the DS */
fh = &mirror->fh_versions[0];
out:
return fh;
}
/* Upon return, either ds is connected, or ds is NULL */
struct nfs4_pnfs_ds *
nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx,
bool fail_return)
{
struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, ds_idx);
struct nfs4_pnfs_ds *ds = NULL;
struct nfs4_deviceid_node *devid;
struct inode *ino = lseg->pls_layout->plh_inode;
struct nfs_server *s = NFS_SERVER(ino);
unsigned int max_payload;
rpc_authflavor_t flavor;
if (mirror == NULL || mirror->mirror_ds == NULL ||
mirror->mirror_ds->ds == NULL) {
printk(KERN_ERR "NFS: %s: No data server for offset index %d\n",
__func__, ds_idx);
if (mirror && mirror->mirror_ds) {
devid = &mirror->mirror_ds->id_node;
pnfs_generic_mark_devid_invalid(devid);
}
goto out;
}
devid = &mirror->mirror_ds->id_node;
if (ff_layout_test_devid_unavailable(devid))
goto out;
ds = mirror->mirror_ds->ds;
/* matching smp_wmb() in _nfs4_pnfs_v3/4_ds_connect */
smp_rmb();
if (ds->ds_clp)
goto out;
flavor = nfs4_ff_layout_choose_authflavor(mirror);
/* FIXME: For now we assume the server sent only one version of NFS
* to use for the DS.
*/
nfs4_pnfs_ds_connect(s, ds, devid, dataserver_timeo,
dataserver_retrans,
mirror->mirror_ds->ds_versions[0].version,
mirror->mirror_ds->ds_versions[0].minor_version,
flavor);
/* connect success, check rsize/wsize limit */
if (ds->ds_clp) {
max_payload =
nfs_block_size(rpc_max_payload(ds->ds_clp->cl_rpcclient),
NULL);
if (mirror->mirror_ds->ds_versions[0].rsize > max_payload)
mirror->mirror_ds->ds_versions[0].rsize = max_payload;
if (mirror->mirror_ds->ds_versions[0].wsize > max_payload)
mirror->mirror_ds->ds_versions[0].wsize = max_payload;
} else {
ff_layout_track_ds_error(FF_LAYOUT_FROM_HDR(lseg->pls_layout),
mirror, lseg->pls_range.offset,
lseg->pls_range.length, NFS4ERR_NXIO,
OP_ILLEGAL, GFP_NOIO);
if (fail_return) {
pnfs_error_mark_layout_for_return(ino, lseg);
if (ff_layout_has_available_ds(lseg))
pnfs_set_retry_layoutget(lseg->pls_layout);
else
pnfs_clear_retry_layoutget(lseg->pls_layout);
} else {
if (ff_layout_has_available_ds(lseg))
set_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE,
&lseg->pls_layout->plh_flags);
else {
pnfs_error_mark_layout_for_return(ino, lseg);
pnfs_clear_retry_layoutget(lseg->pls_layout);
}
}
}
if (ff_layout_update_mirror_cred(mirror, ds))
ds = NULL;
out:
return ds;
}
struct rpc_cred *
ff_layout_get_ds_cred(struct pnfs_layout_segment *lseg, u32 ds_idx,
struct rpc_cred *mdscred)
{
struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, ds_idx);
struct rpc_cred *cred = ERR_PTR(-EINVAL);
if (!nfs4_ff_layout_prepare_ds(lseg, ds_idx, true))
goto out;
if (mirror && mirror->cred)
cred = mirror->cred;
else
cred = mdscred;
out:
return cred;
}
/**
* Find or create a DS rpc client with th MDS server rpc client auth flavor
* in the nfs_client cl_ds_clients list.
*/
struct rpc_clnt *
nfs4_ff_find_or_create_ds_client(struct pnfs_layout_segment *lseg, u32 ds_idx,
struct nfs_client *ds_clp, struct inode *inode)
{
struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, ds_idx);
switch (mirror->mirror_ds->ds_versions[0].version) {
case 3:
/* For NFSv3 DS, flavor is set when creating DS connections */
return ds_clp->cl_rpcclient;
case 4:
return nfs4_find_or_create_ds_client(ds_clp, inode);
default:
BUG();
}
}
static bool is_range_intersecting(u64 offset1, u64 length1,
u64 offset2, u64 length2)
{
u64 end1 = end_offset(offset1, length1);
u64 end2 = end_offset(offset2, length2);
return (end1 == NFS4_MAX_UINT64 || end1 > offset2) &&
(end2 == NFS4_MAX_UINT64 || end2 > offset1);
}
/* called with inode i_lock held */
int ff_layout_encode_ds_ioerr(struct nfs4_flexfile_layout *flo,
struct xdr_stream *xdr, int *count,
const struct pnfs_layout_range *range)
{
struct nfs4_ff_layout_ds_err *err, *n;
__be32 *p;
list_for_each_entry_safe(err, n, &flo->error_list, list) {
if (!is_range_intersecting(err->offset, err->length,
range->offset, range->length))
continue;
/* offset(8) + length(8) + stateid(NFS4_STATEID_SIZE)
* + deviceid(NFS4_DEVICEID4_SIZE) + status(4) + opnum(4)
*/
p = xdr_reserve_space(xdr,
24 + NFS4_STATEID_SIZE + NFS4_DEVICEID4_SIZE);
if (unlikely(!p))
return -ENOBUFS;
p = xdr_encode_hyper(p, err->offset);
p = xdr_encode_hyper(p, err->length);
p = xdr_encode_opaque_fixed(p, &err->stateid,
NFS4_STATEID_SIZE);
p = xdr_encode_opaque_fixed(p, &err->deviceid,
NFS4_DEVICEID4_SIZE);
*p++ = cpu_to_be32(err->status);
*p++ = cpu_to_be32(err->opnum);
*count += 1;
list_del(&err->list);
dprintk("%s: offset %llu length %llu status %d op %d count %d\n",
__func__, err->offset, err->length, err->status,
err->opnum, *count);
kfree(err);
}
return 0;
}
bool ff_layout_has_available_ds(struct pnfs_layout_segment *lseg)
{
struct nfs4_ff_layout_mirror *mirror;
struct nfs4_deviceid_node *devid;
int idx;
for (idx = 0; idx < FF_LAYOUT_MIRROR_COUNT(lseg); idx++) {
mirror = FF_LAYOUT_COMP(lseg, idx);
if (mirror && mirror->mirror_ds) {
devid = &mirror->mirror_ds->id_node;
if (!ff_layout_test_devid_unavailable(devid))
return true;
}
}
return false;
}
module_param(dataserver_retrans, uint, 0644);
MODULE_PARM_DESC(dataserver_retrans, "The number of times the NFSv4.1 client "
"retries a request before it attempts further "
" recovery action.");
module_param(dataserver_timeo, uint, 0644);
MODULE_PARM_DESC(dataserver_timeo, "The time (in tenths of a second) the "
"NFSv4.1 client waits for a response from a "
" data server before it retries an NFS request.");
fs/nfs/idmap.c
浏览文件 @ 6f83e5bd
......@@ -152,7 +152,7 @@ void nfs_fattr_map_and_free_names(struct nfs_server *server, struct nfs_fattr *f
nfs_fattr_free_group_name(fattr);
}
static int nfs_map_string_to_numeric(const char *name, size_t namelen, __u32 *res)
int nfs_map_string_to_numeric(const char *name, size_t namelen, __u32 *res)
{
unsigned long val;
char buf[16];
......@@ -166,6 +166,7 @@ static int nfs_map_string_to_numeric(const char *name, size_t namelen, __u32 *re
*res = val;
return 1;
}
EXPORT_SYMBOL_GPL(nfs_map_string_to_numeric);
static int nfs_map_numeric_to_string(__u32 id, char *buf, size_t buflen)
{
......
fs/nfs/inode.c
浏览文件 @ 6f83e5bd
......@@ -507,10 +507,15 @@ nfs_setattr(struct dentry *dentry, struct iattr *attr)
attr->ia_valid &= ~ATTR_MODE;
if (attr->ia_valid & ATTR_SIZE) {
loff_t i_size;
BUG_ON(!S_ISREG(inode->i_mode));
if (attr->ia_size == i_size_read(inode))
i_size = i_size_read(inode);
if (attr->ia_size == i_size)
attr->ia_valid &= ~ATTR_SIZE;
else if (attr->ia_size < i_size && IS_SWAPFILE(inode))
return -ETXTBSY;
}
/* Optimization: if the end result is no change, don't RPC */
......
fs/nfs/internal.h
浏览文件 @ 6f83e5bd
......@@ -6,6 +6,7 @@
#include <linux/mount.h>
#include <linux/security.h>
#include <linux/crc32.h>
#include <linux/nfs_page.h>
#define NFS_MS_MASK (MS_RDONLY|MS_NOSUID|MS_NODEV|MS_NOEXEC|MS_SYNCHRONOUS)
......@@ -187,9 +188,15 @@ extern struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
const struct sockaddr *ds_addr,
int ds_addrlen, int ds_proto,
unsigned int ds_timeo,
unsigned int ds_retrans);
unsigned int ds_retrans,
u32 minor_version,
rpc_authflavor_t au_flavor);
extern struct rpc_clnt *nfs4_find_or_create_ds_client(struct nfs_client *,
struct inode *);
extern struct nfs_client *nfs3_set_ds_client(struct nfs_client *mds_clp,
const struct sockaddr *ds_addr, int ds_addrlen,
int ds_proto, unsigned int ds_timeo,
unsigned int ds_retrans, rpc_authflavor_t au_flavor);
#ifdef CONFIG_PROC_FS
extern int __init nfs_fs_proc_init(void);
extern void nfs_fs_proc_exit(void);
......@@ -242,9 +249,12 @@ struct nfs_pgio_header *nfs_pgio_header_alloc(const struct nfs_rw_ops *);
void nfs_pgio_header_free(struct nfs_pgio_header *);
void nfs_pgio_data_destroy(struct nfs_pgio_header *);
int nfs_generic_pgio(struct nfs_pageio_descriptor *, struct nfs_pgio_header *);
int nfs_initiate_pgio(struct rpc_clnt *, struct nfs_pgio_header *,
const struct rpc_call_ops *, int, int);
int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr,
struct rpc_cred *cred, const struct nfs_rpc_ops *rpc_ops,
const struct rpc_call_ops *call_ops, int how, int flags);
void nfs_free_request(struct nfs_page *req);
struct nfs_pgio_mirror *
nfs_pgio_current_mirror(struct nfs_pageio_descriptor *desc);
static inline void nfs_iocounter_init(struct nfs_io_counter *c)
{
......@@ -252,6 +262,12 @@ static inline void nfs_iocounter_init(struct nfs_io_counter *c)
atomic_set(&c->io_count, 0);
}
static inline bool nfs_pgio_has_mirroring(struct nfs_pageio_descriptor *desc)
{
WARN_ON_ONCE(desc->pg_mirror_count < 1);
return desc->pg_mirror_count > 1;
}
/* nfs2xdr.c */
extern struct rpc_procinfo nfs_procedures[];
extern int nfs2_decode_dirent(struct xdr_stream *,
......@@ -375,7 +391,7 @@ extern struct rpc_stat nfs_rpcstat;
extern int __init register_nfs_fs(void);
extern void __exit unregister_nfs_fs(void);
extern void nfs_sb_active(struct super_block *sb);
extern bool nfs_sb_active(struct super_block *sb);
extern void nfs_sb_deactive(struct super_block *sb);
/* namespace.c */
......@@ -427,6 +443,7 @@ extern void nfs_write_prepare(struct rpc_task *task, void *calldata);
extern void nfs_commit_prepare(struct rpc_task *task, void *calldata);
extern int nfs_initiate_commit(struct rpc_clnt *clnt,
struct nfs_commit_data *data,
const struct nfs_rpc_ops *nfs_ops,
const struct rpc_call_ops *call_ops,
int how, int flags);
extern void nfs_init_commit(struct nfs_commit_data *data,
......@@ -440,13 +457,15 @@ int nfs_scan_commit(struct inode *inode, struct list_head *dst,
struct nfs_commit_info *cinfo);
void nfs_mark_request_commit(struct nfs_page *req,
struct pnfs_layout_segment *lseg,
struct nfs_commit_info *cinfo);
struct nfs_commit_info *cinfo,
u32 ds_commit_idx);
int nfs_write_need_commit(struct nfs_pgio_header *);
int nfs_generic_commit_list(struct inode *inode, struct list_head *head,
int how, struct nfs_commit_info *cinfo);
void nfs_retry_commit(struct list_head *page_list,
struct pnfs_layout_segment *lseg,
struct nfs_commit_info *cinfo);
struct nfs_commit_info *cinfo,
u32 ds_commit_idx);
void nfs_commitdata_release(struct nfs_commit_data *data);
void nfs_request_add_commit_list(struct nfs_page *req, struct list_head *dst,
struct nfs_commit_info *cinfo);
......@@ -457,6 +476,7 @@ void nfs_init_cinfo(struct nfs_commit_info *cinfo,
struct nfs_direct_req *dreq);
int nfs_key_timeout_notify(struct file *filp, struct inode *inode);
bool nfs_ctx_key_to_expire(struct nfs_open_context *ctx);
void nfs_pageio_stop_mirroring(struct nfs_pageio_descriptor *pgio);
#ifdef CONFIG_MIGRATION
extern int nfs_migrate_page(struct address_space *,
......@@ -480,6 +500,7 @@ static inline void nfs_inode_dio_wait(struct inode *inode)
inode_dio_wait(inode);
}
extern ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq);
extern void nfs_direct_set_resched_writes(struct nfs_direct_req *dreq);
/* nfs4proc.c */
extern void __nfs4_read_done_cb(struct nfs_pgio_header *);
......@@ -493,6 +514,26 @@ extern int nfs41_walk_client_list(struct nfs_client *clp,
struct nfs_client **result,
struct rpc_cred *cred);
static inline struct inode *nfs_igrab_and_active(struct inode *inode)
{
inode = igrab(inode);
if (inode != NULL && !nfs_sb_active(inode->i_sb)) {
iput(inode);
inode = NULL;
}
return inode;
}
static inline void nfs_iput_and_deactive(struct inode *inode)
{
if (inode != NULL) {
struct super_block *sb = inode->i_sb;
iput(inode);
nfs_sb_deactive(sb);
}
}
/*
* Determine the device name as a string
*/
......
fs/nfs/nfs2xdr.c
浏览文件 @ 6f83e5bd
......@@ -481,7 +481,8 @@ static int decode_path(struct xdr_stream *xdr)
* void;
* };
*/
static int decode_attrstat(struct xdr_stream *xdr, struct nfs_fattr *result)
static int decode_attrstat(struct xdr_stream *xdr, struct nfs_fattr *result,
__u32 *op_status)
{
enum nfs_stat status;
int error;
......@@ -489,6 +490,8 @@ static int decode_attrstat(struct xdr_stream *xdr, struct nfs_fattr *result)
error = decode_stat(xdr, &status);
if (unlikely(error))
goto out;
if (op_status)
*op_status = status;
if (status != NFS_OK)
goto out_default;
error = decode_fattr(xdr, result);
......@@ -808,7 +811,7 @@ static int nfs2_xdr_dec_stat(struct rpc_rqst *req, struct xdr_stream *xdr,
static int nfs2_xdr_dec_attrstat(struct rpc_rqst *req, struct xdr_stream *xdr,
struct nfs_fattr *result)
{
return decode_attrstat(xdr, result);
return decode_attrstat(xdr, result, NULL);
}
static int nfs2_xdr_dec_diropres(struct rpc_rqst *req, struct xdr_stream *xdr,
......@@ -865,6 +868,7 @@ static int nfs2_xdr_dec_readres(struct rpc_rqst *req, struct xdr_stream *xdr,
error = decode_stat(xdr, &status);
if (unlikely(error))
goto out;
result->op_status = status;
if (status != NFS_OK)
goto out_default;
error = decode_fattr(xdr, result->fattr);
......@@ -882,7 +886,7 @@ static int nfs2_xdr_dec_writeres(struct rpc_rqst *req, struct xdr_stream *xdr,
{
/* All NFSv2 writes are "file sync" writes */
result->verf->committed = NFS_FILE_SYNC;
return decode_attrstat(xdr, result->fattr);
return decode_attrstat(xdr, result->fattr, &result->op_status);
}
/**
......
fs/nfs/nfs3_fs.h
浏览文件 @ 6f83e5bd
......@@ -30,5 +30,7 @@ struct nfs_server *nfs3_create_server(struct nfs_mount_info *, struct nfs_subver
struct nfs_server *nfs3_clone_server(struct nfs_server *, struct nfs_fh *,
struct nfs_fattr *, rpc_authflavor_t);
/* nfs3super.c */
extern struct nfs_subversion nfs_v3;
#endif /* __LINUX_FS_NFS_NFS3_FS_H */
fs/nfs/nfs3client.c
浏览文件 @ 6f83e5bd
#include <linux/nfs_fs.h>
#include <linux/nfs_mount.h>
#include <linux/sunrpc/addr.h>
#include "internal.h"
#include "nfs3_fs.h"
......@@ -64,3 +65,43 @@ struct nfs_server *nfs3_clone_server(struct nfs_server *source,
nfs_init_server_aclclient(server);
return server;
}
/*
* Set up a pNFS Data Server client over NFSv3.
*
* Return any existing nfs_client that matches server address,port,version
* and minorversion.
*
* For a new nfs_client, use a soft mount (default), a low retrans and a
* low timeout interval so that if a connection is lost, we retry through
* the MDS.
*/
struct nfs_client *nfs3_set_ds_client(struct nfs_client *mds_clp,
const struct sockaddr *ds_addr, int ds_addrlen,
int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans,
rpc_authflavor_t au_flavor)
{
struct nfs_client_initdata cl_init = {
.addr = ds_addr,
.addrlen = ds_addrlen,
.nfs_mod = &nfs_v3,
.proto = ds_proto,
.net = mds_clp->cl_net,
};
struct rpc_timeout ds_timeout;
struct nfs_client *clp;
char buf[INET6_ADDRSTRLEN + 1];
/* fake a hostname because lockd wants it */
if (rpc_ntop(ds_addr, buf, sizeof(buf)) <= 0)
return ERR_PTR(-EINVAL);
cl_init.hostname = buf;
/* Use the MDS nfs_client cl_ipaddr. */
nfs_init_timeout_values(&ds_timeout, ds_proto, ds_timeo, ds_retrans);
clp = nfs_get_client(&cl_init, &ds_timeout, mds_clp->cl_ipaddr,
au_flavor);
return clp;
}
EXPORT_SYMBOL_GPL(nfs3_set_ds_client);
fs/nfs/nfs3proc.c
浏览文件 @ 6f83e5bd
......@@ -800,6 +800,9 @@ static int nfs3_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
{
struct inode *inode = hdr->inode;
if (hdr->pgio_done_cb != NULL)
return hdr->pgio_done_cb(task, hdr);
if (nfs3_async_handle_jukebox(task, inode))
return -EAGAIN;
......@@ -825,6 +828,9 @@ static int nfs3_write_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
{
struct inode *inode = hdr->inode;
if (hdr->pgio_done_cb != NULL)
return hdr->pgio_done_cb(task, hdr);
if (nfs3_async_handle_jukebox(task, inode))
return -EAGAIN;
if (task->tk_status >= 0)
......@@ -845,6 +851,9 @@ static void nfs3_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commi
static int nfs3_commit_done(struct rpc_task *task, struct nfs_commit_data *data)
{
if (data->commit_done_cb != NULL)
return data->commit_done_cb(task, data);
if (nfs3_async_handle_jukebox(task, data->inode))
return -EAGAIN;
nfs_refresh_inode(data->inode, data->res.fattr);
......
fs/nfs/nfs3super.c
浏览文件 @ 6f83e5bd
......@@ -7,7 +7,7 @@
#include "nfs3_fs.h"
#include "nfs.h"
static struct nfs_subversion nfs_v3 = {
struct nfs_subversion nfs_v3 = {
.owner = THIS_MODULE,
.nfs_fs = &nfs_fs_type,
.rpc_vers = &nfs_version3,
......
fs/nfs/nfs3xdr.c
浏览文件 @ 6f83e5bd
......@@ -1636,6 +1636,7 @@ static int nfs3_xdr_dec_read3res(struct rpc_rqst *req, struct xdr_stream *xdr,
error = decode_post_op_attr(xdr, result->fattr);
if (unlikely(error))
goto out;
result->op_status = status;
if (status != NFS3_OK)
goto out_status;
error = decode_read3resok(xdr, result);
......@@ -1708,6 +1709,7 @@ static int nfs3_xdr_dec_write3res(struct rpc_rqst *req, struct xdr_stream *xdr,
error = decode_wcc_data(xdr, result->fattr);
if (unlikely(error))
goto out;
result->op_status = status;
if (status != NFS3_OK)
goto out_status;
error = decode_write3resok(xdr, result);
......@@ -2323,6 +2325,7 @@ static int nfs3_xdr_dec_commit3res(struct rpc_rqst *req,
error = decode_wcc_data(xdr, result->fattr);
if (unlikely(error))
goto out;
result->op_status = status;
if (status != NFS3_OK)
goto out_status;
error = decode_writeverf3(xdr, &result->verf->verifier);
......
fs/nfs/nfs4_fs.h
浏览文件 @ 6f83e5bd
......@@ -44,6 +44,7 @@ enum nfs4_client_state {
#define NFS4_RENEW_TIMEOUT 0x01
#define NFS4_RENEW_DELEGATION_CB 0x02
struct nfs_seqid_counter;
struct nfs4_minor_version_ops {
u32 minor_version;
unsigned init_caps;
......@@ -56,6 +57,8 @@ struct nfs4_minor_version_ops {
struct nfs_fsinfo *);
void (*free_lock_state)(struct nfs_server *,
struct nfs4_lock_state *);
struct nfs_seqid *
(*alloc_seqid)(struct nfs_seqid_counter *, gfp_t);
const struct rpc_call_ops *call_sync_ops;
const struct nfs4_state_recovery_ops *reboot_recovery_ops;
const struct nfs4_state_recovery_ops *nograce_recovery_ops;
......@@ -443,6 +446,12 @@ extern void nfs_increment_open_seqid(int status, struct nfs_seqid *seqid);
extern void nfs_increment_lock_seqid(int status, struct nfs_seqid *seqid);
extern void nfs_release_seqid(struct nfs_seqid *seqid);
extern void nfs_free_seqid(struct nfs_seqid *seqid);
extern int nfs40_setup_sequence(struct nfs4_slot_table *tbl,
struct nfs4_sequence_args *args,
struct nfs4_sequence_res *res,
struct rpc_task *task);
extern int nfs4_sequence_done(struct rpc_task *task,
struct nfs4_sequence_res *res);
extern void nfs4_free_lock_state(struct nfs_server *server, struct nfs4_lock_state *lsp);
......
fs/nfs/nfs4client.c
浏览文件 @ 6f83e5bd
......@@ -849,14 +849,15 @@ static int nfs4_set_client(struct nfs_server *server,
*/
struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
const struct sockaddr *ds_addr, int ds_addrlen,
int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans)
int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans,
u32 minor_version, rpc_authflavor_t au_flavor)
{
struct nfs_client_initdata cl_init = {
.addr = ds_addr,
.addrlen = ds_addrlen,
.nfs_mod = &nfs_v4,
.proto = ds_proto,
.minorversion = mds_clp->cl_minorversion,
.minorversion = minor_version,
.net = mds_clp->cl_net,
};
struct rpc_timeout ds_timeout;
......@@ -874,7 +875,7 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
*/
nfs_init_timeout_values(&ds_timeout, ds_proto, ds_timeo, ds_retrans);
clp = nfs_get_client(&cl_init, &ds_timeout, mds_clp->cl_ipaddr,
mds_clp->cl_rpcclient->cl_auth->au_flavor);
au_flavor);
dprintk("<-- %s %p\n", __func__, clp);
return clp;
......
fs/nfs/nfs4proc.c
浏览文件 @ 6f83e5bd
此差异已折叠。
fs/nfs/nfs4state.c
浏览文件 @ 6f83e5bd
......@@ -1003,11 +1003,11 @@ struct nfs_seqid *nfs_alloc_seqid(struct nfs_seqid_counter *counter, gfp_t gfp_m
struct nfs_seqid *new;
new = kmalloc(sizeof(*new), gfp_mask);
if (new != NULL) {
new->sequence = counter;
INIT_LIST_HEAD(&new->list);
new->task = NULL;
}
if (new == NULL)
return ERR_PTR(-ENOMEM);
new->sequence = counter;
INIT_LIST_HEAD(&new->list);
new->task = NULL;
return new;
}
......@@ -1015,7 +1015,7 @@ void nfs_release_seqid(struct nfs_seqid *seqid)
{
struct nfs_seqid_counter *sequence;
if (list_empty(&seqid->list))
if (seqid == NULL || list_empty(&seqid->list))
return;
sequence = seqid->sequence;
spin_lock(&sequence->lock);
......@@ -1071,13 +1071,15 @@ static void nfs_increment_seqid(int status, struct nfs_seqid *seqid)
void nfs_increment_open_seqid(int status, struct nfs_seqid *seqid)
{
struct nfs4_state_owner *sp = container_of(seqid->sequence,
struct nfs4_state_owner, so_seqid);
struct nfs_server *server = sp->so_server;
struct nfs4_state_owner *sp;
if (seqid == NULL)
return;
sp = container_of(seqid->sequence, struct nfs4_state_owner, so_seqid);
if (status == -NFS4ERR_BAD_SEQID)
nfs4_drop_state_owner(sp);
if (!nfs4_has_session(server->nfs_client))
if (!nfs4_has_session(sp->so_server->nfs_client))
nfs_increment_seqid(status, seqid);
}
......@@ -1088,14 +1090,18 @@ void nfs_increment_open_seqid(int status, struct nfs_seqid *seqid)
*/
void nfs_increment_lock_seqid(int status, struct nfs_seqid *seqid)
{
nfs_increment_seqid(status, seqid);
if (seqid != NULL)
nfs_increment_seqid(status, seqid);
}
int nfs_wait_on_sequence(struct nfs_seqid *seqid, struct rpc_task *task)
{
struct nfs_seqid_counter *sequence = seqid->sequence;
struct nfs_seqid_counter *sequence;
int status = 0;
if (seqid == NULL)
goto out;
sequence = seqid->sequence;
spin_lock(&sequence->lock);
seqid->task = task;
if (list_empty(&seqid->list))
......@@ -1106,6 +1112,7 @@ int nfs_wait_on_sequence(struct nfs_seqid *seqid, struct rpc_task *task)
status = -EAGAIN;
unlock:
spin_unlock(&sequence->lock);
out:
return status;
}
......
fs/nfs/nfs4super.c
浏览文件 @ 6f83e5bd
......@@ -346,6 +346,9 @@ static int __init init_nfs_v4(void)
static void __exit exit_nfs_v4(void)
{
/* Not called in the _init(), conditionally loaded */
nfs4_pnfs_v3_ds_connect_unload();
unregister_nfs_version(&nfs_v4);
nfs4_unregister_sysctl();
nfs_idmap_quit();
......
fs/nfs/nfs4xdr.c
浏览文件 @ 6f83e5bd
此差异已折叠。
fs/nfs/nfsroot.c
浏览文件 @ 6f83e5bd
......@@ -261,11 +261,11 @@ static int __init root_nfs_data(char *cmdline)
*/
len = snprintf(nfs_export_path, sizeof(nfs_export_path),
tmp, utsname()->nodename);
if (len > (int)sizeof(nfs_export_path))
if (len >= (int)sizeof(nfs_export_path))
goto out_devnametoolong;
len = snprintf(nfs_root_device, sizeof(nfs_root_device),
"%pI4:%s", &servaddr, nfs_export_path);
if (len > (int)sizeof(nfs_root_device))
if (len >= (int)sizeof(nfs_root_device))
goto out_devnametoolong;
retval = 0;
......
fs/nfs/objlayout/objio_osd.c
浏览文件 @ 6f83e5bd
......@@ -537,11 +537,12 @@ int objio_write_pagelist(struct nfs_pgio_header *hdr, int how)
static size_t objio_pg_test(struct nfs_pageio_descriptor *pgio,
struct nfs_page *prev, struct nfs_page *req)
{
struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(pgio);
unsigned int size;
size = pnfs_generic_pg_test(pgio, prev, req);
if (!size || pgio->pg_count + req->wb_bytes >
if (!size || mirror->pg_count + req->wb_bytes >
(unsigned long)pgio->pg_layout_private)
return 0;
......@@ -607,12 +608,14 @@ static const struct nfs_pageio_ops objio_pg_read_ops = {
.pg_init = objio_init_read,
.pg_test = objio_pg_test,
.pg_doio = pnfs_generic_pg_readpages,
.pg_cleanup = pnfs_generic_pg_cleanup,
};
static const struct nfs_pageio_ops objio_pg_write_ops = {
.pg_init = objio_init_write,
.pg_test = objio_pg_test,
.pg_doio = pnfs_generic_pg_writepages,
.pg_cleanup = pnfs_generic_pg_cleanup,
};
static struct pnfs_layoutdriver_type objlayout_type = {
......
fs/nfs/pagelist.c
浏览文件 @ 6f83e5bd
此差异已折叠。
fs/nfs/pnfs.c
浏览文件 @ 6f83e5bd
此差异已折叠。
fs/nfs/pnfs.h
浏览文件 @ 6f83e5bd
此差异已折叠。
fs/nfs/pnfs_nfs.c 0 → 100644
浏览文件 @ 6f83e5bd
此差异已折叠。
fs/nfs/read.c
浏览文件 @ 6f83e5bd
......@@ -70,8 +70,15 @@ EXPORT_SYMBOL_GPL(nfs_pageio_init_read);
void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio)
{
struct nfs_pgio_mirror *mirror;
pgio->pg_ops = &nfs_pgio_rw_ops;
pgio->pg_bsize = NFS_SERVER(pgio->pg_inode)->rsize;
/* read path should never have more than one mirror */
WARN_ON_ONCE(pgio->pg_mirror_count != 1);
mirror = &pgio->pg_mirrors[0];
mirror->pg_bsize = NFS_SERVER(pgio->pg_inode)->rsize;
}
EXPORT_SYMBOL_GPL(nfs_pageio_reset_read_mds);
......@@ -81,6 +88,7 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
struct nfs_page *new;
unsigned int len;
struct nfs_pageio_descriptor pgio;
struct nfs_pgio_mirror *pgm;
len = nfs_page_length(page);
if (len == 0)
......@@ -97,7 +105,13 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
&nfs_async_read_completion_ops);
nfs_pageio_add_request(&pgio, new);
nfs_pageio_complete(&pgio);
NFS_I(inode)->read_io += pgio.pg_bytes_written;
/* It doesn't make sense to do mirrored reads! */
WARN_ON_ONCE(pgio.pg_mirror_count != 1);
pgm = &pgio.pg_mirrors[0];
NFS_I(inode)->read_io += pgm->pg_bytes_written;
return 0;
}
......@@ -168,13 +182,14 @@ static void nfs_read_completion(struct nfs_pgio_header *hdr)
static void nfs_initiate_read(struct nfs_pgio_header *hdr,
struct rpc_message *msg,
const struct nfs_rpc_ops *rpc_ops,
struct rpc_task_setup *task_setup_data, int how)
{
struct inode *inode = hdr->inode;
int swap_flags = IS_SWAPFILE(inode) ? NFS_RPC_SWAPFLAGS : 0;
task_setup_data->flags |= swap_flags;
NFS_PROTO(inode)->read_setup(hdr, msg);
rpc_ops->read_setup(hdr, msg);
}
static void
......@@ -351,6 +366,7 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
struct list_head *pages, unsigned nr_pages)
{
struct nfs_pageio_descriptor pgio;
struct nfs_pgio_mirror *pgm;
struct nfs_readdesc desc = {
.pgio = &pgio,
};
......@@ -386,10 +402,15 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
&nfs_async_read_completion_ops);
ret = read_cache_pages(mapping, pages, readpage_async_filler, &desc);
nfs_pageio_complete(&pgio);
NFS_I(inode)->read_io += pgio.pg_bytes_written;
npages = (pgio.pg_bytes_written + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
/* It doesn't make sense to do mirrored reads! */
WARN_ON_ONCE(pgio.pg_mirror_count != 1);
pgm = &pgio.pg_mirrors[0];
NFS_I(inode)->read_io += pgm->pg_bytes_written;
npages = (pgm->pg_bytes_written + PAGE_CACHE_SIZE - 1) >>
PAGE_CACHE_SHIFT;
nfs_add_stats(inode, NFSIOS_READPAGES, npages);
read_complete:
put_nfs_open_context(desc.ctx);
......
fs/nfs/super.c
浏览文件 @ 6f83e5bd
......@@ -405,12 +405,15 @@ void __exit unregister_nfs_fs(void)
unregister_filesystem(&nfs_fs_type);
}
void nfs_sb_active(struct super_block *sb)
bool nfs_sb_active(struct super_block *sb)
{
struct nfs_server *server = NFS_SB(sb);
if (atomic_inc_return(&server->active) == 1)
atomic_inc(&sb->s_active);
if (!atomic_inc_not_zero(&sb->s_active))
return false;
if (atomic_inc_return(&server->active) != 1)
atomic_dec(&sb->s_active);
return true;
}
EXPORT_SYMBOL_GPL(nfs_sb_active);
......
fs/nfs/write.c
浏览文件 @ 6f83e5bd
此差异已折叠。
include/linux/nfs4.h
浏览文件 @ 6f83e5bd
......@@ -516,6 +516,7 @@ enum pnfs_layouttype {
LAYOUT_NFSV4_1_FILES = 1,
LAYOUT_OSD2_OBJECTS = 2,
LAYOUT_BLOCK_VOLUME = 3,
LAYOUT_FLEX_FILES = 4,
};
/* used for both layout return and recall */
......
include/linux/nfs_fs_sb.h
浏览文件 @ 6f83e5bd
......@@ -77,10 +77,6 @@ struct nfs_client {
/* Client owner identifier */
const char * cl_owner_id;
/* Our own IP address, as a null-terminated string.
* This is used to generate the mv0 callback address.
*/
char cl_ipaddr[48];
u32 cl_cb_ident; /* v4.0 callback identifier */
const struct nfs4_minor_version_ops *cl_mvops;
unsigned long cl_mig_gen;
......@@ -108,6 +104,11 @@ struct nfs_client {
#define NFS_SP4_MACH_CRED_COMMIT 6 /* COMMIT */
#endif /* CONFIG_NFS_V4 */
/* Our own IP address, as a null-terminated string.
* This is used to generate the mv0 callback address.
*/
char cl_ipaddr[48];
#ifdef CONFIG_NFS_FSCACHE
struct fscache_cookie *fscache; /* client index cache cookie */
#endif
......
include/linux/nfs_idmap.h
浏览文件 @ 6f83e5bd
此差异已折叠。
include/linux/nfs_page.h
浏览文件 @ 6f83e5bd
此差异已折叠。
include/linux/nfs_xdr.h
浏览文件 @ 6f83e5bd
此差异已折叠。
include/linux/sunrpc/clnt.h
浏览文件 @ 6f83e5bd
此差异已折叠。
include/linux/sunrpc/metrics.h
浏览文件 @ 6f83e5bd
此差异已折叠。
include/linux/sunrpc/rpc_rdma.h
浏览文件 @ 6f83e5bd
此差异已折叠。
include/linux/sunrpc/svc_rdma.h
浏览文件 @ 6f83e5bd
此差异已折叠。
include/linux/sunrpc/xprt.h
浏览文件 @ 6f83e5bd
此差异已折叠。
net/sunrpc/clnt.c
浏览文件 @ 6f83e5bd
此差异已折叠。
net/sunrpc/rpcb_clnt.c
浏览文件 @ 6f83e5bd
此差异已折叠。
net/sunrpc/sched.c
浏览文件 @ 6f83e5bd
此差异已折叠。
net/sunrpc/stats.c
浏览文件 @ 6f83e5bd
此差异已折叠。
net/sunrpc/xprt.c
浏览文件 @ 6f83e5bd
此差异已折叠。
net/sunrpc/xprtrdma/rpc_rdma.c
浏览文件 @ 6f83e5bd
此差异已折叠。
net/sunrpc/xprtrdma/transport.c
浏览文件 @ 6f83e5bd
此差异已折叠。
net/sunrpc/xprtrdma/verbs.c
浏览文件 @ 6f83e5bd
此差异已折叠。
net/sunrpc/xprtrdma/xprt_rdma.h
浏览文件 @ 6f83e5bd
此差异已折叠。
net/sunrpc/xprtsock.c
浏览文件 @ 6f83e5bd
此差异已折叠。
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或