@@ -13,6 +13,7 @@ nfs-y := client.o dir.o file.o getroot.o inode.o super.o \
nfs-$(CONFIG_ROOT_NFS) += nfsroot.o
nfs-$(CONFIG_SYSCTL) += sysctl.o
nfs-$(CONFIG_NFS_FSCACHE) += fscache.o
+nfs-$(CONFIG_NFS_LOCALIO) += localio.o
obj-$(CONFIG_NFS_V2) += nfsv2.o
nfsv2-y := nfs2super.o proc.o nfs2xdr.o
@@ -178,6 +178,10 @@ struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init)
clp->cl_max_connect = cl_init->max_connect ? cl_init->max_connect : 1;
clp->cl_net = get_net(cl_init->net);
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+ seqlock_init(&clp->cl_boot_lock);
+ ktime_get_real_ts64(&clp->cl_nfssvc_boot);
+#endif
clp->cl_principal = "*";
clp->cl_xprtsec = cl_init->xprtsec;
return clp;
@@ -233,6 +237,8 @@ static void pnfs_init_server(struct nfs_server *server)
*/
void nfs_free_client(struct nfs_client *clp)
{
+ nfs_local_disable(clp);
+
/* -EIO all pending I/O */
if (!IS_ERR(clp->cl_rpcclient))
rpc_shutdown_client(clp->cl_rpcclient);
@@ -424,6 +430,7 @@ struct nfs_client *nfs_get_client(const struct nfs_client_initdata *cl_init)
list_add_tail(&new->cl_share_link,
&nn->nfs_client_list);
spin_unlock(&nn->nfs_client_lock);
+ nfs_local_probe(new);
return rpc_ops->init_client(new, cl_init);
}
@@ -39,6 +39,7 @@
#include <linux/slab.h>
#include <linux/compat.h>
#include <linux/freezer.h>
+#include <linux/file.h>
#include <linux/uaccess.h>
#include <linux/iversion.h>
@@ -1053,6 +1054,7 @@ struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry,
ctx->lock_context.open_context = ctx;
INIT_LIST_HEAD(&ctx->list);
ctx->mdsthreshold = NULL;
+ ctx->local_filp = NULL;
return ctx;
}
EXPORT_SYMBOL_GPL(alloc_nfs_open_context);
@@ -1084,6 +1086,8 @@ static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync)
nfs_sb_deactive(sb);
put_rpccred(rcu_dereference_protected(ctx->ll_cred, 1));
kfree(ctx->mdsthreshold);
+ if (!IS_ERR_OR_NULL(ctx->local_filp))
+ fput(ctx->local_filp);
kfree_rcu(ctx, rcu_head);
}
@@ -2495,6 +2499,7 @@ static int __init init_nfs_fs(void)
if (err)
goto out1;
+ nfs_local_init();
err = register_nfs_fs();
if (err)
goto out0;
@@ -451,6 +451,59 @@ extern void nfs_set_cache_invalid(struct inode *inode, unsigned long flags);
extern bool nfs_check_cache_invalid(struct inode *, unsigned long);
extern int nfs_wait_bit_killable(struct wait_bit_key *key, int mode);
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+/* localio.c */
+extern void nfs_local_init(void);
+extern void nfs_local_disable(struct nfs_client *);
+extern void nfs_local_probe(struct nfs_client *);
+extern struct file *nfs_local_open_fh(struct nfs_client *, const struct cred *,
+ struct nfs_fh *, const fmode_t);
+extern struct file *nfs_local_file_open(struct nfs_client *clp,
+ const struct cred *cred,
+ struct nfs_fh *fh,
+ struct nfs_open_context *ctx);
+extern int nfs_local_doio(struct nfs_client *, struct file *,
+ struct nfs_pgio_header *,
+ const struct rpc_call_ops *);
+extern int nfs_local_commit(struct file *, struct nfs_commit_data *,
+ const struct rpc_call_ops *, int);
+extern bool nfs_server_is_local(const struct nfs_client *clp);
+
+#else
+static inline void nfs_local_init(void) {}
+static inline void nfs_local_disable(struct nfs_client *clp) {}
+static inline void nfs_local_probe(struct nfs_client *clp) {}
+static inline struct file *nfs_local_open_fh(struct nfs_client *clp,
+ const struct cred *cred,
+ struct nfs_fh *fh,
+ const fmode_t mode)
+{
+ return ERR_PTR(-EINVAL);
+}
+static inline struct file *nfs_local_file_open(struct nfs_client *clp,
+ const struct cred *cred,
+ struct nfs_fh *fh,
+ struct nfs_open_context *ctx)
+{
+ return NULL;
+}
+static inline int nfs_local_doio(struct nfs_client *clp, struct file *filep,
+ struct nfs_pgio_header *hdr,
+ const struct rpc_call_ops *call_ops)
+{
+ return -EINVAL;
+}
+static inline int nfs_local_commit(struct file *filep, struct nfs_commit_data *data,
+ const struct rpc_call_ops *call_ops, int how)
+{
+ return -EINVAL;
+}
+static inline bool nfs_server_is_local(const struct nfs_client *clp)
+{
+ return false;
+}
+#endif /* CONFIG_NFS_LOCALIO */
+
/* super.c */
extern const struct super_operations nfs_sops;
bool nfs_auth_info_match(const struct nfs_auth_info *, rpc_authflavor_t);
new file mode 100644
@@ -0,0 +1,797 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * NFS client support for local clients to bypass network stack
+ *
+ * Copyright (C) 2014 Weston Andros Adamson <dros@primarydata.com>
+ * Copyright (C) 2019 Trond Myklebust <trond.myklebust@hammerspace.com>
+ * Copyright (C) 2024 Mike Snitzer <snitzer@hammerspace.com>
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/vfs.h>
+#include <linux/file.h>
+#include <linux/inet.h>
+#include <linux/sunrpc/addr.h>
+#include <linux/inetdevice.h>
+#include <net/addrconf.h>
+#include <linux/module.h>
+#include <linux/bvec.h>
+
+#include <linux/nfs.h>
+#include <linux/nfs_fs.h>
+#include <linux/nfs_xdr.h>
+
+#include "internal.h"
+#include "pnfs.h"
+#include "nfstrace.h"
+
+#define NFSDBG_FACILITY NFSDBG_VFS
+
+extern int nfsd_open_local_fh(struct rpc_clnt *rpc_clnt,
+ const struct cred *cred,
+ const struct nfs_fh *nfs_fh, const fmode_t fmode,
+ struct file **pfilp);
+/*
+ * The localio code needs to call into nfsd to do the filehandle -> struct path
+ * mapping, but cannot be statically linked, because that will make the nfs
+ * module depend on the nfsd module.
+ *
+ * Instead, do dynamic linking to the nfsd module. This way the nfs module
+ * will only hold a reference on nfsd when it's actually in use. This also
+ * allows some sanity checking, like giving up on localio if nfsd isn't loaded.
+ */
+
+struct nfs_local_open_ctx {
+ spinlock_t lock;
+ nfs_to_nfsd_open_t open_f;
+ atomic_t refcount;
+};
+
+struct nfs_local_kiocb {
+ struct kiocb kiocb;
+ struct bio_vec *bvec;
+ struct nfs_pgio_header *hdr;
+ struct work_struct work;
+};
+
+struct nfs_local_fsync_ctx {
+ struct file *filp;
+ struct nfs_commit_data *data;
+ struct work_struct work;
+ struct kref kref;
+ struct completion *done;
+};
+static void nfs_local_fsync_work(struct work_struct *work);
+
+/*
+ * We need to translate between nfs status return values and
+ * the local errno values which may not be the same.
+ */
+static struct {
+ __u32 stat;
+ int errno;
+} nfs_errtbl[] = {
+ { NFS4_OK, 0 },
+ { NFS4ERR_PERM, -EPERM },
+ { NFS4ERR_NOENT, -ENOENT },
+ { NFS4ERR_IO, -EIO },
+ { NFS4ERR_NXIO, -ENXIO },
+ { NFS4ERR_FBIG, -E2BIG },
+ { NFS4ERR_STALE, -EBADF },
+ { NFS4ERR_ACCESS, -EACCES },
+ { NFS4ERR_EXIST, -EEXIST },
+ { NFS4ERR_XDEV, -EXDEV },
+ { NFS4ERR_MLINK, -EMLINK },
+ { NFS4ERR_NOTDIR, -ENOTDIR },
+ { NFS4ERR_ISDIR, -EISDIR },
+ { NFS4ERR_INVAL, -EINVAL },
+ { NFS4ERR_FBIG, -EFBIG },
+ { NFS4ERR_NOSPC, -ENOSPC },
+ { NFS4ERR_ROFS, -EROFS },
+ { NFS4ERR_NAMETOOLONG, -ENAMETOOLONG },
+ { NFS4ERR_NOTEMPTY, -ENOTEMPTY },
+ { NFS4ERR_DQUOT, -EDQUOT },
+ { NFS4ERR_STALE, -ESTALE },
+ { NFS4ERR_STALE, -EOPENSTALE },
+ { NFS4ERR_DELAY, -ETIMEDOUT },
+ { NFS4ERR_DELAY, -ERESTARTSYS },
+ { NFS4ERR_DELAY, -EAGAIN },
+ { NFS4ERR_DELAY, -ENOMEM },
+ { NFS4ERR_IO, -ETXTBSY },
+ { NFS4ERR_IO, -EBUSY },
+ { NFS4ERR_BADHANDLE, -EBADHANDLE },
+ { NFS4ERR_BAD_COOKIE, -EBADCOOKIE },
+ { NFS4ERR_NOTSUPP, -EOPNOTSUPP },
+ { NFS4ERR_TOOSMALL, -ETOOSMALL },
+ { NFS4ERR_SERVERFAULT, -ESERVERFAULT },
+ { NFS4ERR_SERVERFAULT, -ENFILE },
+ { NFS4ERR_IO, -EREMOTEIO },
+ { NFS4ERR_IO, -EUCLEAN },
+ { NFS4ERR_PERM, -ENOKEY },
+ { NFS4ERR_BADTYPE, -EBADTYPE },
+ { NFS4ERR_SYMLINK, -ELOOP },
+ { NFS4ERR_DEADLOCK, -EDEADLK },
+};
+
+/*
+ * Convert an NFS error code to a local one.
+ * This one is used jointly by NFSv2 and NFSv3.
+ */
+static __u32
+nfs4errno(int errno)
+{
+ unsigned int i;
+ for (i = 0; i < ARRAY_SIZE(nfs_errtbl); i++) {
+ if (nfs_errtbl[i].errno == errno)
+ return nfs_errtbl[i].stat;
+ }
+ /* If we cannot translate the error, the recovery routines should
+ * handle it.
+ * Note: remaining NFSv4 error codes have values > 10000, so should
+ * not conflict with native Linux error codes.
+ */
+ return NFS4ERR_SERVERFAULT;
+}
+
+static struct nfs_local_open_ctx __local_open_ctx __read_mostly;
+
+static bool localio_enabled __read_mostly = true;
+module_param(localio_enabled, bool, 0644);
+
+bool nfs_server_is_local(const struct nfs_client *clp)
+{
+ return test_bit(NFS_CS_LOCAL_IO, &clp->cl_flags) != 0 &&
+ localio_enabled;
+}
+EXPORT_SYMBOL_GPL(nfs_server_is_local);
+
+void
+nfs_local_init(void)
+{
+ struct nfs_local_open_ctx *ctx = &__local_open_ctx;
+
+ ctx->open_f = NULL;
+ spin_lock_init(&ctx->lock);
+ atomic_set(&ctx->refcount, 0);
+}
+
+static bool
+nfs_local_get_lookup_ctx(void)
+{
+ struct nfs_local_open_ctx *ctx = &__local_open_ctx;
+ nfs_to_nfsd_open_t fn = NULL;
+
+ spin_lock(&ctx->lock);
+ if (ctx->open_f == NULL) {
+ spin_unlock(&ctx->lock);
+
+ fn = symbol_request(nfsd_open_local_fh);
+ if (!fn)
+ return false;
+
+ spin_lock(&ctx->lock);
+ /* catch race */
+ if (ctx->open_f == NULL) {
+ ctx->open_f = fn;
+ fn = NULL;
+ }
+ }
+ atomic_inc(&ctx->refcount);
+ spin_unlock(&ctx->lock);
+ if (fn)
+ symbol_put(nfsd_open_local_fh);
+ return true;
+}
+
+static void
+nfs_local_put_lookup_ctx(void)
+{
+ struct nfs_local_open_ctx *ctx = &__local_open_ctx;
+ nfs_to_nfsd_open_t fn;
+
+ if (atomic_dec_and_lock(&ctx->refcount, &ctx->lock)) {
+ fn = ctx->open_f;
+ ctx->open_f = NULL;
+ spin_unlock(&ctx->lock);
+ if (fn)
+ symbol_put(nfsd_open_local_fh);
+ }
+}
+
+/*
+ * nfs_local_enable - attempt to enable local i/o for an nfs_client
+ */
+static void nfs_local_enable(struct nfs_client *clp)
+{
+ if (nfs_local_get_lookup_ctx()) {
+ set_bit(NFS_CS_LOCAL_IO, &clp->cl_flags);
+ trace_nfs_local_enable(clp);
+ }
+}
+
+/*
+ * nfs_local_disable - disable local i/o for an nfs_client
+ */
+void
+nfs_local_disable(struct nfs_client *clp)
+{
+ if (test_and_clear_bit(NFS_CS_LOCAL_IO, &clp->cl_flags)) {
+ trace_nfs_local_disable(clp);
+ nfs_local_put_lookup_ctx();
+ }
+}
+
+/*
+ * nfs_local_probe - probe local i/o support for an nfs_client
+ */
+void
+nfs_local_probe(struct nfs_client *clp)
+{
+ bool enable = false;
+
+ if (enable)
+ nfs_local_enable(clp);
+}
+EXPORT_SYMBOL_GPL(nfs_local_probe);
+
+/*
+ * nfs_local_open_fh - open a local filehandle
+ *
+ * Returns a pointer to a struct file or an ERR_PTR
+ */
+struct file *
+nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred,
+ struct nfs_fh *fh, const fmode_t mode)
+{
+ struct nfs_local_open_ctx *ctx = &__local_open_ctx;
+ struct file *filp;
+ int status;
+
+ if (mode & ~(FMODE_READ | FMODE_WRITE))
+ return ERR_PTR(-EINVAL);
+
+ status = ctx->open_f(clp->cl_rpcclient, cred, fh, mode, &filp);
+ if (status < 0) {
+ dprintk("%s: open local file failed error=%d\n",
+ __func__, status);
+ trace_nfs_local_open_fh(fh, mode, status);
+ switch (status) {
+ case -ENXIO:
+ nfs_local_disable(clp);
+ fallthrough;
+ case -ETIMEDOUT:
+ status = -EAGAIN;
+ }
+ filp = ERR_PTR(status);
+ }
+ return filp;
+}
+EXPORT_SYMBOL_GPL(nfs_local_open_fh);
+
+static struct bio_vec *
+nfs_bvec_alloc_and_import_pagevec(struct page **pagevec,
+ unsigned int npages, gfp_t flags)
+{
+ struct bio_vec *bvec, *p;
+
+ bvec = kmalloc_array(npages, sizeof(*bvec), flags);
+ if (bvec != NULL) {
+ for (p = bvec; npages > 0; p++, pagevec++, npages--) {
+ p->bv_page = *pagevec;
+ p->bv_len = PAGE_SIZE;
+ p->bv_offset = 0;
+ }
+ }
+ return bvec;
+}
+
+static void
+nfs_local_iocb_free(struct nfs_local_kiocb *iocb)
+{
+ kfree(iocb->bvec);
+ kfree(iocb);
+}
+
+static struct nfs_local_kiocb *
+nfs_local_iocb_alloc(struct nfs_pgio_header *hdr, struct file *filp,
+ gfp_t flags)
+{
+ struct nfs_local_kiocb *iocb;
+
+ iocb = kmalloc(sizeof(*iocb), flags);
+ if (iocb == NULL)
+ return NULL;
+ iocb->bvec = nfs_bvec_alloc_and_import_pagevec(hdr->page_array.pagevec,
+ hdr->page_array.npages, flags);
+ if (iocb->bvec == NULL) {
+ kfree(iocb);
+ return NULL;
+ }
+ init_sync_kiocb(&iocb->kiocb, filp);
+ iocb->kiocb.ki_pos = hdr->args.offset;
+ iocb->hdr = hdr;
+ /* FIXME: NFS_IOHDR_ODIRECT isn't ever set */
+ if (test_bit(NFS_IOHDR_ODIRECT, &hdr->flags))
+ iocb->kiocb.ki_flags |= IOCB_DIRECT|IOCB_DSYNC;
+ iocb->kiocb.ki_flags &= ~IOCB_APPEND;
+ return iocb;
+}
+
+static void
+nfs_local_iter_init(struct iov_iter *i, struct nfs_local_kiocb *iocb, int dir)
+{
+ struct nfs_pgio_header *hdr = iocb->hdr;
+
+ if (hdr->args.pgbase != 0) {
+ iov_iter_bvec(i, dir, iocb->bvec,
+ hdr->page_array.npages,
+ hdr->args.count + hdr->args.pgbase);
+ iov_iter_advance(i, hdr->args.pgbase);
+ } else
+ iov_iter_bvec(i, dir, iocb->bvec,
+ hdr->page_array.npages, hdr->args.count);
+}
+
+static void
+nfs_local_hdr_release(struct nfs_pgio_header *hdr,
+ const struct rpc_call_ops *call_ops)
+{
+ call_ops->rpc_call_done(&hdr->task, hdr);
+ call_ops->rpc_release(hdr);
+}
+
+static void
+nfs_local_pgio_init(struct nfs_pgio_header *hdr,
+ const struct rpc_call_ops *call_ops)
+{
+ hdr->task.tk_ops = call_ops;
+ if (!hdr->task.tk_start)
+ hdr->task.tk_start = ktime_get();
+}
+
+static void
+nfs_local_pgio_done(struct nfs_pgio_header *hdr, long status)
+{
+ if (status >= 0) {
+ hdr->res.count = status;
+ hdr->res.op_status = NFS4_OK;
+ hdr->task.tk_status = 0;
+ } else {
+ hdr->res.op_status = nfs4errno(status);
+ hdr->task.tk_status = status;
+ }
+}
+
+static void
+nfs_local_pgio_release(struct nfs_local_kiocb *iocb)
+{
+ struct nfs_pgio_header *hdr = iocb->hdr;
+
+ fput(iocb->kiocb.ki_filp);
+ nfs_local_iocb_free(iocb);
+ nfs_local_hdr_release(hdr, hdr->task.tk_ops);
+}
+
+static void
+nfs_local_read_aio_complete_work(struct work_struct *work)
+{
+ struct nfs_local_kiocb *iocb = container_of(work,
+ struct nfs_local_kiocb, work);
+
+ nfs_local_pgio_release(iocb);
+}
+
+/*
+ * Complete the I/O from iocb->kiocb.ki_complete()
+ *
+ * Note that this function can be called from a bottom half context,
+ * hence we need to queue the fput() etc to a workqueue
+ */
+static void
+nfs_local_pgio_complete(struct nfs_local_kiocb *iocb)
+{
+ queue_work(nfsiod_workqueue, &iocb->work);
+}
+
+static void
+nfs_local_read_done(struct nfs_local_kiocb *iocb, long status)
+{
+ struct nfs_pgio_header *hdr = iocb->hdr;
+ struct file *filp = iocb->kiocb.ki_filp;
+
+ nfs_local_pgio_done(hdr, status);
+
+ if (hdr->res.count != hdr->args.count ||
+ hdr->args.offset + hdr->res.count >= i_size_read(file_inode(filp)))
+ hdr->res.eof = true;
+
+ dprintk("%s: read %ld bytes eof %d.\n", __func__,
+ status > 0 ? status : 0, hdr->res.eof);
+}
+
+static void
+nfs_local_read_aio_complete(struct kiocb *kiocb, long ret)
+{
+ struct nfs_local_kiocb *iocb = container_of(kiocb,
+ struct nfs_local_kiocb, kiocb);
+
+ nfs_local_read_done(iocb, ret);
+ nfs_local_pgio_complete(iocb);
+}
+
+static int
+nfs_do_local_read(struct nfs_pgio_header *hdr, struct file *filp,
+ const struct rpc_call_ops *call_ops)
+{
+ struct nfs_local_kiocb *iocb;
+ struct iov_iter iter;
+ ssize_t status;
+
+ dprintk("%s: vfs_read count=%u pos=%llu\n",
+ __func__, hdr->args.count, hdr->args.offset);
+
+ iocb = nfs_local_iocb_alloc(hdr, filp, GFP_KERNEL);
+ if (iocb == NULL)
+ return -ENOMEM;
+ nfs_local_iter_init(&iter, iocb, READ);
+
+ nfs_local_pgio_init(hdr, call_ops);
+ hdr->res.eof = false;
+
+ if (iocb->kiocb.ki_flags & IOCB_DIRECT) {
+ INIT_WORK(&iocb->work, nfs_local_read_aio_complete_work);
+ iocb->kiocb.ki_complete = nfs_local_read_aio_complete;
+ }
+
+ status = filp->f_op->read_iter(&iocb->kiocb, &iter);
+ if (status != -EIOCBQUEUED) {
+ nfs_local_read_done(iocb, status);
+ nfs_local_pgio_release(iocb);
+ }
+ return 0;
+}
+
+static void
+nfs_copy_boot_verifier(struct nfs_write_verifier *verifier, struct inode *inode)
+{
+ struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
+ u32 *verf = (u32 *)verifier->data;
+ int seq = 0;
+
+ do {
+ read_seqbegin_or_lock(&clp->cl_boot_lock, &seq);
+ verf[0] = (u32)clp->cl_nfssvc_boot.tv_sec;
+ verf[1] = (u32)clp->cl_nfssvc_boot.tv_nsec;
+ } while (need_seqretry(&clp->cl_boot_lock, seq));
+ done_seqretry(&clp->cl_boot_lock, seq);
+}
+
+static void
+nfs_reset_boot_verifier(struct inode *inode)
+{
+ struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
+
+ write_seqlock(&clp->cl_boot_lock);
+ ktime_get_real_ts64(&clp->cl_nfssvc_boot);
+ write_sequnlock(&clp->cl_boot_lock);
+}
+
+static void
+nfs_set_local_verifier(struct inode *inode,
+ struct nfs_writeverf *verf,
+ enum nfs3_stable_how how)
+{
+
+ nfs_copy_boot_verifier(&verf->verifier, inode);
+ verf->committed = how;
+}
+
+static void
+nfs_get_vfs_attr(struct file *filp, struct nfs_fattr *fattr)
+{
+ struct kstat stat;
+
+ if (fattr != NULL && vfs_getattr(&filp->f_path, &stat,
+ STATX_INO |
+ STATX_ATIME |
+ STATX_MTIME |
+ STATX_CTIME |
+ STATX_SIZE |
+ STATX_BLOCKS,
+ AT_STATX_SYNC_AS_STAT) == 0) {
+ fattr->valid = NFS_ATTR_FATTR_FILEID |
+ NFS_ATTR_FATTR_CHANGE |
+ NFS_ATTR_FATTR_SIZE |
+ NFS_ATTR_FATTR_ATIME |
+ NFS_ATTR_FATTR_MTIME |
+ NFS_ATTR_FATTR_CTIME |
+ NFS_ATTR_FATTR_SPACE_USED;
+ fattr->fileid = stat.ino;
+ fattr->size = stat.size;
+ fattr->atime = stat.atime;
+ fattr->mtime = stat.mtime;
+ fattr->ctime = stat.ctime;
+ fattr->change_attr = nfs_timespec_to_change_attr(&fattr->ctime);
+ fattr->du.nfs3.used = stat.blocks << 9;
+ }
+}
+
+static void
+nfs_local_write_done(struct nfs_local_kiocb *iocb, long status)
+{
+ struct nfs_pgio_header *hdr = iocb->hdr;
+
+ dprintk("%s: wrote %ld bytes.\n", __func__, status > 0 ? status : 0);
+
+ /* Handle short writes as if they are ENOSPC */
+ if (status > 0 && status < hdr->args.count) {
+ hdr->mds_offset += status;
+ hdr->args.offset += status;
+ hdr->args.pgbase += status;
+ hdr->args.count -= status;
+ nfs_set_pgio_error(hdr, -ENOSPC, hdr->args.offset);
+ status = -ENOSPC;
+ }
+ if (status < 0)
+ nfs_reset_boot_verifier(hdr->inode);
+ nfs_local_pgio_done(hdr, status);
+}
+
+static void
+nfs_local_write_aio_complete_work(struct work_struct *work)
+{
+ struct nfs_local_kiocb *iocb = container_of(work,
+ struct nfs_local_kiocb, work);
+
+ nfs_get_vfs_attr(iocb->kiocb.ki_filp, iocb->hdr->res.fattr);
+ nfs_local_pgio_release(iocb);
+}
+
+static void
+nfs_local_write_aio_complete(struct kiocb *kiocb, long ret)
+{
+ struct nfs_local_kiocb *iocb = container_of(kiocb,
+ struct nfs_local_kiocb, kiocb);
+
+ nfs_local_write_done(iocb, ret);
+ nfs_local_pgio_complete(iocb);
+}
+
+static int
+nfs_do_local_write(struct nfs_pgio_header *hdr, struct file *filp,
+ const struct rpc_call_ops *call_ops)
+{
+ struct nfs_local_kiocb *iocb;
+ struct iov_iter iter;
+ ssize_t status;
+
+ dprintk("%s: vfs_write count=%u pos=%llu %s\n",
+ __func__, hdr->args.count, hdr->args.offset,
+ (hdr->args.stable == NFS_UNSTABLE) ? "unstable" : "stable");
+
+ iocb = nfs_local_iocb_alloc(hdr, filp, GFP_NOIO);
+ if (iocb == NULL)
+ return -ENOMEM;
+ nfs_local_iter_init(&iter, iocb, WRITE);
+
+ switch (hdr->args.stable) {
+ default:
+ break;
+ case NFS_DATA_SYNC:
+ iocb->kiocb.ki_flags |= IOCB_DSYNC;
+ break;
+ case NFS_FILE_SYNC:
+ iocb->kiocb.ki_flags |= IOCB_DSYNC|IOCB_SYNC;
+ }
+ nfs_local_pgio_init(hdr, call_ops);
+
+ if (iocb->kiocb.ki_flags & IOCB_DIRECT) {
+ INIT_WORK(&iocb->work, nfs_local_write_aio_complete_work);
+ iocb->kiocb.ki_complete = nfs_local_write_aio_complete;
+ }
+
+ nfs_set_local_verifier(hdr->inode, hdr->res.verf, hdr->args.stable);
+
+ file_start_write(filp);
+ status = filp->f_op->write_iter(&iocb->kiocb, &iter);
+ file_end_write(filp);
+ if (status != -EIOCBQUEUED) {
+ nfs_local_write_done(iocb, status);
+ nfs_get_vfs_attr(filp, hdr->res.fattr);
+ nfs_local_pgio_release(iocb);
+ }
+ return 0;
+}
+
+static struct file *
+nfs_local_file_open_cached(struct nfs_client *clp, const struct cred *cred,
+ struct nfs_fh *fh, struct nfs_open_context *ctx)
+{
+ struct file *filp = ctx->local_filp;
+
+ if (!filp) {
+ struct file *new = nfs_local_open_fh(clp, cred, fh, ctx->mode);
+ if (IS_ERR_OR_NULL(new))
+ return NULL;
+ /* try to put this one in the slot */
+ filp = cmpxchg(&ctx->local_filp, NULL, new);
+ if (filp != NULL)
+ fput(new);
+ else
+ filp = new;
+ }
+ return get_file(filp);
+}
+
+struct file *
+nfs_local_file_open(struct nfs_client *clp, const struct cred *cred,
+ struct nfs_fh *fh, struct nfs_open_context *ctx)
+{
+ if (!nfs_server_is_local(clp))
+ return NULL;
+ return nfs_local_file_open_cached(clp, cred, fh, ctx);
+}
+
+int
+nfs_local_doio(struct nfs_client *clp, struct file *filp,
+ struct nfs_pgio_header *hdr,
+ const struct rpc_call_ops *call_ops)
+{
+ int status = 0;
+
+ if (!hdr->args.count)
+ goto out_fput;
+ /* Don't support filesystems without read_iter/write_iter */
+ if (!filp->f_op->read_iter || !filp->f_op->write_iter) {
+ nfs_local_disable(clp);
+ status = -EAGAIN;
+ goto out_fput;
+ }
+
+ switch (hdr->rw_mode) {
+ case FMODE_READ:
+ status = nfs_do_local_read(hdr, filp, call_ops);
+ break;
+ case FMODE_WRITE:
+ status = nfs_do_local_write(hdr, filp, call_ops);
+ break;
+ default:
+ dprintk("%s: invalid mode: %d\n", __func__,
+ hdr->rw_mode);
+ status = -EINVAL;
+ }
+out_fput:
+ if (status != 0) {
+ fput(filp);
+ hdr->task.tk_status = status;
+ nfs_local_hdr_release(hdr, call_ops);
+ }
+ return status;
+}
+
+static void
+nfs_local_init_commit(struct nfs_commit_data *data,
+ const struct rpc_call_ops *call_ops)
+{
+ data->task.tk_ops = call_ops;
+}
+
+static int
+nfs_local_run_commit(struct file *filp, struct nfs_commit_data *data)
+{
+ loff_t start = data->args.offset;
+ loff_t end = LLONG_MAX;
+
+ if (data->args.count > 0) {
+ end = start + data->args.count - 1;
+ if (end < start)
+ end = LLONG_MAX;
+ }
+
+ dprintk("%s: commit %llu - %llu\n", __func__, start, end);
+ return vfs_fsync_range(filp, start, end, 0);
+}
+
+static void
+nfs_local_commit_done(struct nfs_commit_data *data, int status)
+{
+ if (status >= 0) {
+ nfs_set_local_verifier(data->inode,
+ data->res.verf,
+ NFS_FILE_SYNC);
+ data->res.op_status = NFS4_OK;
+ data->task.tk_status = 0;
+ } else {
+ nfs_reset_boot_verifier(data->inode);
+ data->res.op_status = nfs4errno(status);
+ data->task.tk_status = status;
+ }
+}
+
+static void
+nfs_local_release_commit_data(struct file *filp,
+ struct nfs_commit_data *data,
+ const struct rpc_call_ops *call_ops)
+{
+ fput(filp);
+ call_ops->rpc_call_done(&data->task, data);
+ call_ops->rpc_release(data);
+}
+
+static struct nfs_local_fsync_ctx *
+nfs_local_fsync_ctx_alloc(struct nfs_commit_data *data, struct file *filp,
+ gfp_t flags)
+{
+ struct nfs_local_fsync_ctx *ctx = kmalloc(sizeof(*ctx), flags);
+
+ if (ctx != NULL) {
+ ctx->filp = filp;
+ ctx->data = data;
+ INIT_WORK(&ctx->work, nfs_local_fsync_work);
+ kref_init(&ctx->kref);
+ ctx->done = NULL;
+ }
+ return ctx;
+}
+
+static void
+nfs_local_fsync_ctx_kref_free(struct kref *kref)
+{
+ kfree(container_of(kref, struct nfs_local_fsync_ctx, kref));
+}
+
+static void
+nfs_local_fsync_ctx_put(struct nfs_local_fsync_ctx *ctx)
+{
+ kref_put(&ctx->kref, nfs_local_fsync_ctx_kref_free);
+}
+
+static void
+nfs_local_fsync_ctx_free(struct nfs_local_fsync_ctx *ctx)
+{
+ nfs_local_release_commit_data(ctx->filp, ctx->data,
+ ctx->data->task.tk_ops);
+ nfs_local_fsync_ctx_put(ctx);
+}
+
+static void
+nfs_local_fsync_work(struct work_struct *work)
+{
+ struct nfs_local_fsync_ctx *ctx;
+ int status;
+
+ ctx = container_of(work, struct nfs_local_fsync_ctx, work);
+
+ status = nfs_local_run_commit(ctx->filp, ctx->data);
+ nfs_local_commit_done(ctx->data, status);
+ if (ctx->done != NULL)
+ complete(ctx->done);
+ nfs_local_fsync_ctx_free(ctx);
+}
+
+int
+nfs_local_commit(struct file *filp, struct nfs_commit_data *data,
+ const struct rpc_call_ops *call_ops, int how)
+{
+ struct nfs_local_fsync_ctx *ctx;
+
+ ctx = nfs_local_fsync_ctx_alloc(data, filp, GFP_KERNEL);
+ if (!ctx) {
+ nfs_local_commit_done(data, -ENOMEM);
+ nfs_local_release_commit_data(filp, data, call_ops);
+ return -ENOMEM;
+ }
+
+ nfs_local_init_commit(data, call_ops);
+ kref_get(&ctx->kref);
+ if (how & FLUSH_SYNC) {
+ DECLARE_COMPLETION_ONSTACK(done);
+ ctx->done = &done;
+ queue_work(nfsiod_workqueue, &ctx->work);
+ wait_for_completion(&done);
+ } else
+ queue_work(nfsiod_workqueue, &ctx->work);
+ nfs_local_fsync_ctx_put(ctx);
+ return 0;
+}
@@ -1681,6 +1681,67 @@ TRACE_EVENT(nfs_mount_path,
TP_printk("path='%s'", __get_str(path))
);
+TRACE_EVENT(nfs_local_open_fh,
+ TP_PROTO(
+ const struct nfs_fh *fh,
+ fmode_t fmode,
+ int error
+ ),
+
+ TP_ARGS(fh, fmode, error),
+
+ TP_STRUCT__entry(
+ __field(int, error)
+ __field(u32, fhandle)
+ __field(unsigned int, fmode)
+ ),
+
+ TP_fast_assign(
+ __entry->error = error;
+ __entry->fhandle = nfs_fhandle_hash(fh);
+ __entry->fmode = (__force unsigned int)fmode;
+ ),
+
+ TP_printk(
+ "error=%d fhandle=0x%08x mode=%s",
+ __entry->error,
+ __entry->fhandle,
+ show_fs_fmode_flags(__entry->fmode)
+ )
+);
+
+DECLARE_EVENT_CLASS(nfs_local_client_event,
+ TP_PROTO(
+ const struct nfs_client *clp
+ ),
+
+ TP_ARGS(clp),
+
+ TP_STRUCT__entry(
+ __field(unsigned int, protocol)
+ __string(server, clp->cl_hostname)
+ ),
+
+ TP_fast_assign(
+ __entry->protocol = clp->rpc_ops->version;
+ __assign_str(server);
+ ),
+
+ TP_printk(
+ "server=%s NFSv%u", __get_str(server), __entry->protocol
+ )
+);
+
+#define DEFINE_NFS_LOCAL_CLIENT_EVENT(name) \
+ DEFINE_EVENT(nfs_local_client_event, name, \
+ TP_PROTO( \
+ const struct nfs_client *clp \
+ ), \
+ TP_ARGS(clp))
+
+DEFINE_NFS_LOCAL_CLIENT_EVENT(nfs_local_enable);
+DEFINE_NFS_LOCAL_CLIENT_EVENT(nfs_local_disable);
+
DECLARE_EVENT_CLASS(nfs_xdr_event,
TP_PROTO(
const struct xdr_stream *xdr,
@@ -879,6 +879,9 @@ int nfs_initiate_pgio(struct nfs_pageio_descriptor *desc,
hdr->args.count,
(unsigned long long)hdr->args.offset);
+ if (localio)
+ return nfs_local_doio(clp, localio, hdr, call_ops);
+
task = rpc_run_task(&task_setup_data);
if (IS_ERR(task))
return PTR_ERR(task);
@@ -1700,6 +1700,9 @@ int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data,
dprintk("NFS: initiated commit call\n");
+ if (localio)
+ return nfs_local_commit(localio, data, call_ops, how);
+
task = rpc_run_task(&task_setup_data);
if (IS_ERR(task))
return PTR_ERR(task);
@@ -23,3 +23,4 @@ nfsd-$(CONFIG_NFSD_PNFS) += nfs4layouts.o
nfsd-$(CONFIG_NFSD_BLOCKLAYOUT) += blocklayout.o blocklayoutxdr.o
nfsd-$(CONFIG_NFSD_SCSILAYOUT) += blocklayout.o blocklayoutxdr.o
nfsd-$(CONFIG_NFSD_FLEXFILELAYOUT) += flexfilelayout.o flexfilelayoutxdr.o
+nfsd-$(CONFIG_NFSD_LOCALIO) += localio.o
@@ -52,7 +52,7 @@
#define NFSD_FILE_CACHE_UP (0)
/* We only care about NFSD_MAY_READ/WRITE for this cache */
-#define NFSD_FILE_MAY_MASK (NFSD_MAY_READ|NFSD_MAY_WRITE)
+#define NFSD_FILE_MAY_MASK (NFSD_MAY_READ|NFSD_MAY_WRITE|NFSD_MAY_LOCALIO)
static DEFINE_PER_CPU(unsigned long, nfsd_file_cache_hits);
static DEFINE_PER_CPU(unsigned long, nfsd_file_acquisitions);
new file mode 100644
@@ -0,0 +1,243 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * NFS server support for local clients to bypass network stack
+ *
+ * Copyright (C) 2014 Weston Andros Adamson <dros@primarydata.com>
+ * Copyright (C) 2019 Trond Myklebust <trond.myklebust@hammerspace.com>
+ * Copyright (C) 2024 Mike Snitzer <snitzer@hammerspace.com>
+ */
+
+#include <linux/exportfs.h>
+#include <linux/sunrpc/svcauth_gss.h>
+#include <linux/sunrpc/clnt.h>
+#include <linux/nfs.h>
+#include <linux/string.h>
+
+#include "nfsd.h"
+#include "vfs.h"
+#include "netns.h"
+#include "filecache.h"
+
+#define NFSDDBG_FACILITY NFSDDBG_FH
+
+/*
+ * We need to translate between nfs status return values and
+ * the local errno values which may not be the same.
+ * - duplicated from fs/nfs/nfs2xdr.c to avoid needless bloat of
+ * all compiled nfs objects if it were in include/linux/nfs.h
+ */
+static const struct {
+ int stat;
+ int errno;
+} nfs_common_errtbl[] = {
+ { NFS_OK, 0 },
+ { NFSERR_PERM, -EPERM },
+ { NFSERR_NOENT, -ENOENT },
+ { NFSERR_IO, -EIO },
+ { NFSERR_NXIO, -ENXIO },
+/* { NFSERR_EAGAIN, -EAGAIN }, */
+ { NFSERR_ACCES, -EACCES },
+ { NFSERR_EXIST, -EEXIST },
+ { NFSERR_XDEV, -EXDEV },
+ { NFSERR_NODEV, -ENODEV },
+ { NFSERR_NOTDIR, -ENOTDIR },
+ { NFSERR_ISDIR, -EISDIR },
+ { NFSERR_INVAL, -EINVAL },
+ { NFSERR_FBIG, -EFBIG },
+ { NFSERR_NOSPC, -ENOSPC },
+ { NFSERR_ROFS, -EROFS },
+ { NFSERR_MLINK, -EMLINK },
+ { NFSERR_NAMETOOLONG, -ENAMETOOLONG },
+ { NFSERR_NOTEMPTY, -ENOTEMPTY },
+ { NFSERR_DQUOT, -EDQUOT },
+ { NFSERR_STALE, -ESTALE },
+ { NFSERR_REMOTE, -EREMOTE },
+#ifdef EWFLUSH
+ { NFSERR_WFLUSH, -EWFLUSH },
+#endif
+ { NFSERR_BADHANDLE, -EBADHANDLE },
+ { NFSERR_NOT_SYNC, -ENOTSYNC },
+ { NFSERR_BAD_COOKIE, -EBADCOOKIE },
+ { NFSERR_NOTSUPP, -ENOTSUPP },
+ { NFSERR_TOOSMALL, -ETOOSMALL },
+ { NFSERR_SERVERFAULT, -EREMOTEIO },
+ { NFSERR_BADTYPE, -EBADTYPE },
+ { NFSERR_JUKEBOX, -EJUKEBOX },
+ { -1, -EIO }
+};
+
+/**
+ * nfs_stat_to_errno - convert an NFS status code to a local errno
+ * @status: NFS status code to convert
+ *
+ * Returns a local errno value, or -EIO if the NFS status code is
+ * not recognized. This function is used jointly by NFSv2 and NFSv3.
+ */
+static inline int nfs_stat_to_errno(enum nfs_stat status)
+{
+ int i;
+
+ for (i = 0; nfs_common_errtbl[i].stat != -1; i++) {
+ if (nfs_common_errtbl[i].stat == (int)status)
+ return nfs_common_errtbl[i].errno;
+ }
+ return nfs_common_errtbl[i].errno;
+}
+
+static void
+nfsd_local_fakerqst_destroy(struct svc_rqst *rqstp)
+{
+ if (rqstp->rq_client)
+ auth_domain_put(rqstp->rq_client);
+ if (rqstp->rq_cred.cr_group_info)
+ put_group_info(rqstp->rq_cred.cr_group_info);
+ /* rpcauth_map_to_svc_cred_local() clears cr_principal */
+ WARN_ON_ONCE(rqstp->rq_cred.cr_principal != NULL);
+ kfree(rqstp->rq_xprt);
+ kfree(rqstp);
+}
+
+static struct svc_rqst *
+nfsd_local_fakerqst_create(struct rpc_clnt *rpc_clnt, const struct cred *cred)
+{
+ struct svc_rqst *rqstp;
+ struct net *net = rpc_net_ns(rpc_clnt);
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ int status;
+
+ /* FIXME: not running in nfsd context, must get reference on nfsd_serv */
+ if (unlikely(!READ_ONCE(nn->nfsd_serv))) {
+ dprintk("%s: localio denied. Server not running\n", __func__);
+ return ERR_PTR(-ENXIO);
+ }
+
+ rqstp = kzalloc(sizeof(*rqstp), GFP_KERNEL);
+ if (!rqstp)
+ return ERR_PTR(-ENOMEM);
+
+ rqstp->rq_xprt = kzalloc(sizeof(*rqstp->rq_xprt), GFP_KERNEL);
+ if (!rqstp->rq_xprt) {
+ status = -ENOMEM;
+ goto out_err;
+ }
+
+ rqstp->rq_xprt->xpt_net = net;
+ __set_bit(RQ_SECURE, &rqstp->rq_flags);
+ rqstp->rq_proc = 1;
+ rqstp->rq_vers = 3;
+ rqstp->rq_prot = IPPROTO_TCP;
+ rqstp->rq_server = nn->nfsd_serv;
+
+ /* Note: we're connecting to ourself, so source addr == peer addr */
+ rqstp->rq_addrlen = rpc_peeraddr(rpc_clnt,
+ (struct sockaddr *)&rqstp->rq_addr,
+ sizeof(rqstp->rq_addr));
+
+ rpcauth_map_to_svc_cred_local(rpc_clnt->cl_auth, cred, &rqstp->rq_cred);
+
+ /*
+ * set up enough for svcauth_unix_set_client to be able to wait
+ * for the cache downcall. Note that we do _not_ want to allow the
+ * request to be deferred for later revisit since this rqst and xprt
+ * are not set up to run inside of the normal svc_rqst engine.
+ */
+ INIT_LIST_HEAD(&rqstp->rq_xprt->xpt_deferred);
+ kref_init(&rqstp->rq_xprt->xpt_ref);
+ spin_lock_init(&rqstp->rq_xprt->xpt_lock);
+ rqstp->rq_chandle.thread_wait = 5 * HZ;
+
+ status = svcauth_unix_set_client(rqstp);
+ switch (status) {
+ case SVC_OK:
+ break;
+ case SVC_DENIED:
+ status = -ENXIO;
+ dprintk("%s: client %pISpc denied localio access\n",
+ __func__, (struct sockaddr *)&rqstp->rq_addr);
+ goto out_err;
+ default:
+ status = -ETIMEDOUT;
+ dprintk("%s: client %pISpc temporarily denied localio access\n",
+ __func__, (struct sockaddr *)&rqstp->rq_addr);
+ goto out_err;
+ }
+
+ return rqstp;
+
+out_err:
+ nfsd_local_fakerqst_destroy(rqstp);
+ return ERR_PTR(status);
+}
+
+/*
+ * nfsd_open_local_fh - lookup a local filehandle @nfs_fh and map to @file
+ *
+ * This function maps a local fh to a path on a local filesystem.
+ * This is useful when the nfs client has the local server mounted - it can
+ * avoid all the NFS overhead with reads, writes and commits.
+ *
+ * on successful return, caller is responsible for calling path_put. Also
+ * note that this is called from nfs.ko via find_symbol() to avoid an explicit
+ * dependency on knfsd. So, there is no forward declaration in a header file
+ * for it.
+ */
+int nfsd_open_local_fh(struct rpc_clnt *rpc_clnt,
+ const struct cred *cred,
+ const struct nfs_fh *nfs_fh,
+ const fmode_t fmode,
+ struct file **pfilp)
+{
+ const struct cred *save_cred;
+ struct svc_rqst *rqstp;
+ struct svc_fh fh;
+ struct nfsd_file *nf;
+ int status = 0;
+ int mayflags = NFSD_MAY_LOCALIO;
+ __be32 beres;
+
+ /* Save creds before calling into nfsd */
+ save_cred = get_current_cred();
+
+ rqstp = nfsd_local_fakerqst_create(rpc_clnt, cred);
+ if (IS_ERR(rqstp)) {
+ status = PTR_ERR(rqstp);
+ goto out_revertcred;
+ }
+
+ /* nfs_fh -> svc_fh */
+ if (nfs_fh->size > NFS4_FHSIZE) {
+ status = -EINVAL;
+ goto out;
+ }
+ fh_init(&fh, NFS4_FHSIZE);
+ fh.fh_handle.fh_size = nfs_fh->size;
+ memcpy(fh.fh_handle.fh_raw, nfs_fh->data, nfs_fh->size);
+
+ if (fmode & FMODE_READ)
+ mayflags |= NFSD_MAY_READ;
+ if (fmode & FMODE_WRITE)
+ mayflags |= NFSD_MAY_WRITE;
+
+ beres = nfsd_file_acquire(rqstp, &fh, mayflags, &nf);
+ if (beres) {
+ status = nfs_stat_to_errno(be32_to_cpu(beres));
+ dprintk("%s: fh_verify failed %d\n", __func__, status);
+ goto out_fh_put;
+ }
+
+ *pfilp = get_file(nf->nf_file);
+
+ nfsd_file_put(nf);
+out_fh_put:
+ fh_put(&fh);
+
+out:
+ nfsd_local_fakerqst_destroy(rqstp);
+out_revertcred:
+ revert_creds(save_cred);
+ return status;
+}
+EXPORT_SYMBOL_GPL(nfsd_open_local_fh);
+
+/* Compile time type checking, not used by anything */
+static nfs_to_nfsd_open_t __maybe_unused nfsd_open_local_fh_typecheck = nfsd_open_local_fh;
@@ -86,7 +86,8 @@ DEFINE_NFSD_XDR_ERR_EVENT(cant_encode);
{ NFSD_MAY_NOT_BREAK_LEASE, "NOT_BREAK_LEASE" }, \
{ NFSD_MAY_BYPASS_GSS, "BYPASS_GSS" }, \
{ NFSD_MAY_READ_IF_EXEC, "READ_IF_EXEC" }, \
- { NFSD_MAY_64BIT_COOKIE, "64BIT_COOKIE" })
+ { NFSD_MAY_64BIT_COOKIE, "64BIT_COOKIE" }, \
+ { NFSD_MAY_LOCALIO, "LOCALIO" })
TRACE_EVENT(nfsd_compound,
TP_PROTO(
@@ -36,6 +36,8 @@
#define NFSD_MAY_CREATE (NFSD_MAY_EXEC|NFSD_MAY_WRITE)
#define NFSD_MAY_REMOVE (NFSD_MAY_EXEC|NFSD_MAY_WRITE|NFSD_MAY_TRUNC)
+#define NFSD_MAY_LOCALIO 0x800000
+
struct nfsd_file;
/*
@@ -158,6 +160,12 @@ __be32 nfsd_permission(struct svc_rqst *, struct svc_export *,
void nfsd_filp_close(struct file *fp);
+int nfsd_open_local_fh(struct rpc_clnt *rpc_clnt,
+ const struct cred *cred,
+ const struct nfs_fh *nfs_fh,
+ const fmode_t fmode,
+ struct file **pfilp);
+
static inline int fh_want_write(struct svc_fh *fh)
{
int ret;
@@ -8,6 +8,8 @@
#ifndef _LINUX_NFS_H
#define _LINUX_NFS_H
+#include <linux/cred.h>
+#include <linux/sunrpc/auth.h>
#include <linux/sunrpc/msg_prot.h>
#include <linux/string.h>
#include <linux/crc32.h>
@@ -46,6 +48,10 @@ enum nfs3_stable_how {
NFS_INVALID_STABLE_HOW = -1
};
+typedef int (*nfs_to_nfsd_open_t)(struct rpc_clnt *, const struct cred *,
+ const struct nfs_fh *, const fmode_t,
+ struct file **);
+
#ifdef CONFIG_CRC32
/**
* nfs_fhandle_hash - calculate the crc32 hash for the filehandle
@@ -96,6 +96,8 @@ struct nfs_open_context {
struct list_head list;
struct nfs4_threshold *mdsthreshold;
struct rcu_head rcu_head;
+
+ struct file *local_filp;
};
struct nfs_open_dir_context {
@@ -49,6 +49,7 @@ struct nfs_client {
#define NFS_CS_DS 7 /* - Server is a DS */
#define NFS_CS_REUSEPORT 8 /* - reuse src port on reconnect */
#define NFS_CS_PNFS 9 /* - Server used for pnfs */
+#define NFS_CS_LOCAL_IO 10 /* - client is local */
struct sockaddr_storage cl_addr; /* server identifier */
size_t cl_addrlen;
char * cl_hostname; /* hostname of server */
@@ -125,6 +126,10 @@ struct nfs_client {
struct net *cl_net;
struct list_head pending_cb_stateids;
struct rcu_head rcu;
+
+ /* localio */
+ struct timespec64 cl_nfssvc_boot;
+ seqlock_t cl_boot_lock;
};
/*
@@ -1605,6 +1605,7 @@ enum {
NFS_IOHDR_RESEND_PNFS,
NFS_IOHDR_RESEND_MDS,
NFS_IOHDR_UNSTABLE_WRITES,
+ NFS_IOHDR_ODIRECT,
};
struct nfs_io_completion;