diff options
Diffstat (limited to 'fs/nfsd')
54 files changed, 11745 insertions, 5723 deletions
diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig index 7c441f2bd444..0b5c1a0bf1cf 100644 --- a/fs/nfsd/Kconfig +++ b/fs/nfsd/Kconfig @@ -4,9 +4,13 @@ config NFSD depends on INET depends on FILE_LOCKING depends on FSNOTIFY + select CRC32 + select CRYPTO_LIB_MD5 if NFSD_LEGACY_CLIENT_TRACKING + select CRYPTO_LIB_SHA256 if NFSD_V4 select LOCKD select SUNRPC select EXPORTFS + select NFS_COMMON select NFS_ACL_SUPPORT if NFSD_V2_ACL select NFS_ACL_SUPPORT if NFSD_V3_ACL depends on MULTIUSER @@ -73,10 +77,8 @@ config NFSD_V4 bool "NFS server support for NFS version 4" depends on NFSD && PROC_FS select FS_POSIX_ACL - select SUNRPC_GSS - select CRYPTO - select CRYPTO_MD5 - select CRYPTO_SHA256 + select RPCSEC_GSS_KRB5 + select CRYPTO # required by RPCSEC_GSS_KRB5 select GRACE_PERIOD select NFS_V4_2_SSC_HELPER if NFS_V4_2 help @@ -158,3 +160,29 @@ config NFSD_V4_SECURITY_LABEL If you do not wish to enable fine-grained security labels SELinux or Smack policies on NFSv4 files, say N. + +config NFSD_LEGACY_CLIENT_TRACKING + bool "Support legacy NFSv4 client tracking methods (DEPRECATED)" + depends on NFSD_V4 + default n + help + The NFSv4 server needs to store a small amount of information on + stable storage in order to handle state recovery after reboot. Most + modern deployments upcall to a userland daemon for this (nfsdcld), + but older NFS servers may store information directly in a + recoverydir, or spawn a process directly using a usermodehelper + upcall. + + These legacy client tracking methods have proven to be problematic + and will be removed in the future. Say Y here if you need support + for them in the interim. + +config NFSD_V4_DELEG_TIMESTAMPS + bool "Support delegated timestamps" + depends on NFSD_V4 + default n + help + NFSD implements delegated timestamps according to + draft-ietf-nfsv4-delstid-08 "Extending the Opening of Files". This + is currently an experimental feature and is therefore left disabled + by default. diff --git a/fs/nfsd/Makefile b/fs/nfsd/Makefile index 6fffc8f03f74..55744bb786c9 100644 --- a/fs/nfsd/Makefile +++ b/fs/nfsd/Makefile @@ -12,13 +12,30 @@ nfsd-y += trace.o nfsd-y += nfssvc.o nfsctl.o nfsfh.o vfs.o \ export.o auth.o lockd.o nfscache.o \ - stats.o filecache.o nfs3proc.o nfs3xdr.o + stats.o filecache.o nfs3proc.o nfs3xdr.o \ + netlink.o nfsd-$(CONFIG_NFSD_V2) += nfsproc.o nfsxdr.o nfsd-$(CONFIG_NFSD_V2_ACL) += nfs2acl.o nfsd-$(CONFIG_NFSD_V3_ACL) += nfs3acl.o nfsd-$(CONFIG_NFSD_V4) += nfs4proc.o nfs4xdr.o nfs4state.o nfs4idmap.o \ - nfs4acl.o nfs4callback.o nfs4recover.o + nfs4acl.o nfs4callback.o nfs4recover.o nfs4xdr_gen.o 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-$(CONFIG_NFS_LOCALIO) += localio.o +nfsd-$(CONFIG_DEBUG_FS) += debugfs.o + + +.PHONY: xdrgen + +xdrgen: ../../include/linux/sunrpc/xdrgen/nfs4_1.h nfs4xdr_gen.h nfs4xdr_gen.c + +../../include/linux/sunrpc/xdrgen/nfs4_1.h: ../../Documentation/sunrpc/xdr/nfs4_1.x + ../../tools/net/sunrpc/xdrgen/xdrgen definitions $< > $@ + +nfs4xdr_gen.h: ../../Documentation/sunrpc/xdr/nfs4_1.x + ../../tools/net/sunrpc/xdrgen/xdrgen declarations $< > $@ + +nfs4xdr_gen.c: ../../Documentation/sunrpc/xdr/nfs4_1.x + ../../tools/net/sunrpc/xdrgen/xdrgen source $< > $@ diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c index fdf2aad73470..4dc327e02456 100644 --- a/fs/nfsd/auth.c +++ b/fs/nfsd/auth.c @@ -5,39 +5,37 @@ #include "nfsd.h" #include "auth.h" -int nfsexp_flags(struct svc_rqst *rqstp, struct svc_export *exp) +int nfsexp_flags(struct svc_cred *cred, struct svc_export *exp) { struct exp_flavor_info *f; struct exp_flavor_info *end = exp->ex_flavors + exp->ex_nflavors; for (f = exp->ex_flavors; f < end; f++) { - if (f->pseudoflavor == rqstp->rq_cred.cr_flavor) + if (f->pseudoflavor == cred->cr_flavor) return f->flags; } return exp->ex_flags; } -int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp) +int nfsd_setuser(struct svc_cred *cred, struct svc_export *exp) { struct group_info *rqgi; struct group_info *gi; struct cred *new; int i; - int flags = nfsexp_flags(rqstp, exp); - - validate_process_creds(); + int flags = nfsexp_flags(cred, exp); /* discard any old override before preparing the new set */ - revert_creds(get_cred(current_real_cred())); + put_cred(revert_creds(get_cred(current_real_cred()))); new = prepare_creds(); if (!new) return -ENOMEM; - new->fsuid = rqstp->rq_cred.cr_uid; - new->fsgid = rqstp->rq_cred.cr_gid; + new->fsuid = cred->cr_uid; + new->fsgid = cred->cr_gid; - rqgi = rqstp->rq_cred.cr_group_info; + rqgi = cred->cr_group_info; if (flags & NFSEXP_ALLSQUASH) { new->fsuid = exp->ex_anon_uid; @@ -81,10 +79,7 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp) else new->cap_effective = cap_raise_nfsd_set(new->cap_effective, new->cap_permitted); - validate_process_creds(); put_cred(override_creds(new)); - put_cred(new); - validate_process_creds(); return 0; oom: diff --git a/fs/nfsd/auth.h b/fs/nfsd/auth.h index dbd66424f600..8c5031bbbcee 100644 --- a/fs/nfsd/auth.h +++ b/fs/nfsd/auth.h @@ -12,6 +12,6 @@ * Set the current process's fsuid/fsgid etc to those of the NFS * client user */ -int nfsd_setuser(struct svc_rqst *, struct svc_export *); +int nfsd_setuser(struct svc_cred *cred, struct svc_export *exp); #endif /* LINUX_NFSD_AUTH_H */ diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c index 04697f8dc37d..afa16d7a8013 100644 --- a/fs/nfsd/blocklayout.c +++ b/fs/nfsd/blocklayout.c @@ -13,67 +13,49 @@ #include "pnfs.h" #include "filecache.h" #include "vfs.h" +#include "trace.h" #define NFSDDBG_FACILITY NFSDDBG_PNFS +/* + * Get an extent from the file system that starts at offset or below + * and may be shorter than the requested length. + */ static __be32 -nfsd4_block_proc_layoutget(struct inode *inode, const struct svc_fh *fhp, - struct nfsd4_layoutget *args) +nfsd4_block_map_extent(struct inode *inode, const struct svc_fh *fhp, + u64 offset, u64 length, u32 iomode, u64 minlength, + struct pnfs_block_extent *bex) { - struct nfsd4_layout_seg *seg = &args->lg_seg; struct super_block *sb = inode->i_sb; - u32 block_size = i_blocksize(inode); - struct pnfs_block_extent *bex; struct iomap iomap; u32 device_generation = 0; int error; - if (seg->offset & (block_size - 1)) { - dprintk("pnfsd: I/O misaligned\n"); - goto out_layoutunavailable; - } - - /* - * Some clients barf on non-zero block numbers for NONE or INVALID - * layouts, so make sure to zero the whole structure. - */ - error = -ENOMEM; - bex = kzalloc(sizeof(*bex), GFP_KERNEL); - if (!bex) - goto out_error; - args->lg_content = bex; - - error = sb->s_export_op->map_blocks(inode, seg->offset, seg->length, - &iomap, seg->iomode != IOMODE_READ, - &device_generation); + error = sb->s_export_op->map_blocks(inode, offset, length, &iomap, + iomode != IOMODE_READ, &device_generation); if (error) { if (error == -ENXIO) - goto out_layoutunavailable; - goto out_error; - } - - if (iomap.length < args->lg_minlength) { - dprintk("pnfsd: extent smaller than minlength\n"); - goto out_layoutunavailable; + return nfserr_layoutunavailable; + return nfserrno(error); } switch (iomap.type) { case IOMAP_MAPPED: - if (seg->iomode == IOMODE_READ) + if (iomode == IOMODE_READ) bex->es = PNFS_BLOCK_READ_DATA; else bex->es = PNFS_BLOCK_READWRITE_DATA; bex->soff = iomap.addr; break; case IOMAP_UNWRITTEN: - if (seg->iomode & IOMODE_RW) { + if (iomode & IOMODE_RW) { /* * Crack monkey special case from section 2.3.1. */ - if (args->lg_minlength == 0) { + if (minlength == 0) { dprintk("pnfsd: no soup for you!\n"); - goto out_layoutunavailable; + return nfserr_layoutunavailable; } bex->es = PNFS_BLOCK_INVALID_DATA; @@ -82,7 +64,7 @@ nfsd4_block_proc_layoutget(struct inode *inode, const struct svc_fh *fhp, } fallthrough; case IOMAP_HOLE: - if (seg->iomode == IOMODE_READ) { + if (iomode == IOMODE_READ) { bex->es = PNFS_BLOCK_NONE_DATA; break; } @@ -90,46 +72,126 @@ nfsd4_block_proc_layoutget(struct inode *inode, const struct svc_fh *fhp, case IOMAP_DELALLOC: default: WARN(1, "pnfsd: filesystem returned %d extent\n", iomap.type); - goto out_layoutunavailable; + return nfserr_layoutunavailable; } error = nfsd4_set_deviceid(&bex->vol_id, fhp, device_generation); if (error) - goto out_error; + return nfserrno(error); + bex->foff = iomap.offset; bex->len = iomap.length; + return nfs_ok; +} - seg->offset = iomap.offset; - seg->length = iomap.length; +static __be32 +nfsd4_block_proc_layoutget(struct svc_rqst *rqstp, struct inode *inode, + const struct svc_fh *fhp, struct nfsd4_layoutget *args) +{ + struct nfsd4_layout_seg *seg = &args->lg_seg; + struct pnfs_block_layout *bl; + struct pnfs_block_extent *first_bex, *last_bex; + u64 offset = seg->offset, length = seg->length; + u32 i, nr_extents_max, block_size = i_blocksize(inode); + __be32 nfserr; - dprintk("GET: 0x%llx:0x%llx %d\n", bex->foff, bex->len, bex->es); - return 0; + if (locks_in_grace(SVC_NET(rqstp))) + return nfserr_grace; + + nfserr = nfserr_layoutunavailable; + if (seg->offset & (block_size - 1)) { + dprintk("pnfsd: I/O misaligned\n"); + goto out_error; + } + + /* + * RFC 8881, section 3.3.17: + * The layout4 data type defines a layout for a file. + * + * RFC 8881, section 18.43.3: + * The loga_maxcount field specifies the maximum layout size + * (in bytes) that the client can handle. If the size of the + * layout structure exceeds the size specified by maxcount, + * the metadata server will return the NFS4ERR_TOOSMALL error. + */ + nfserr = nfserr_toosmall; + if (args->lg_maxcount < PNFS_BLOCK_LAYOUT4_SIZE + + PNFS_BLOCK_EXTENT_SIZE) + goto out_error; + + /* + * Limit the maximum layout size to avoid allocating + * a large buffer on the server for each layout request. + */ + nr_extents_max = (min(args->lg_maxcount, PAGE_SIZE) - + PNFS_BLOCK_LAYOUT4_SIZE) / PNFS_BLOCK_EXTENT_SIZE; + + /* + * Some clients barf on non-zero block numbers for NONE or INVALID + * layouts, so make sure to zero the whole structure. + */ + nfserr = nfserrno(-ENOMEM); + bl = kzalloc(struct_size(bl, extents, nr_extents_max), GFP_KERNEL); + if (!bl) + goto out_error; + bl->nr_extents = nr_extents_max; + args->lg_content = bl; + + for (i = 0; i < bl->nr_extents; i++) { + struct pnfs_block_extent *bex = bl->extents + i; + u64 bex_length; + + nfserr = nfsd4_block_map_extent(inode, fhp, offset, length, + seg->iomode, args->lg_minlength, bex); + if (nfserr != nfs_ok) + goto out_error; + + bex_length = bex->len - (offset - bex->foff); + if (bex_length >= length) { + bl->nr_extents = i + 1; + break; + } + + offset = bex->foff + bex->len; + length -= bex_length; + } + + first_bex = bl->extents; + last_bex = bl->extents + bl->nr_extents - 1; + + nfserr = nfserr_layoutunavailable; + length = last_bex->foff + last_bex->len - seg->offset; + if (length < args->lg_minlength) { + dprintk("pnfsd: extent smaller than minlength\n"); + goto out_error; + } + + seg->offset = first_bex->foff; + seg->length = last_bex->foff - first_bex->foff + last_bex->len; + return nfs_ok; out_error: seg->length = 0; - return nfserrno(error); -out_layoutunavailable: - seg->length = 0; - return nfserr_layoutunavailable; + return nfserr; } static __be32 nfsd4_block_commit_blocks(struct inode *inode, struct nfsd4_layoutcommit *lcp, struct iomap *iomaps, int nr_iomaps) { - loff_t new_size = lcp->lc_last_wr + 1; + struct timespec64 mtime = inode_get_mtime(inode); struct iattr iattr = { .ia_valid = 0 }; int error; if (lcp->lc_mtime.tv_nsec == UTIME_NOW || - timespec64_compare(&lcp->lc_mtime, &inode->i_mtime) < 0) + timespec64_compare(&lcp->lc_mtime, &mtime) < 0) lcp->lc_mtime = current_time(inode); iattr.ia_valid |= ATTR_ATIME | ATTR_CTIME | ATTR_MTIME; iattr.ia_atime = iattr.ia_ctime = iattr.ia_mtime = lcp->lc_mtime; - if (new_size > i_size_read(inode)) { + if (lcp->lc_size_chg) { iattr.ia_valid |= ATTR_SIZE; - iattr.ia_size = new_size; + iattr.ia_size = lcp->lc_newsize; } error = inode->i_sb->s_export_op->commit_blocks(inode, iomaps, @@ -146,8 +208,7 @@ nfsd4_block_get_device_info_simple(struct super_block *sb, struct pnfs_block_deviceaddr *dev; struct pnfs_block_volume *b; - dev = kzalloc(sizeof(struct pnfs_block_deviceaddr) + - sizeof(struct pnfs_block_volume), GFP_KERNEL); + dev = kzalloc(struct_size(dev, volumes, 1), GFP_KERNEL); if (!dev) return -ENOMEM; gdp->gd_device = dev; @@ -173,16 +234,20 @@ nfsd4_block_proc_getdeviceinfo(struct super_block *sb, } static __be32 -nfsd4_block_proc_layoutcommit(struct inode *inode, +nfsd4_block_proc_layoutcommit(struct inode *inode, struct svc_rqst *rqstp, struct nfsd4_layoutcommit *lcp) { struct iomap *iomaps; int nr_iomaps; + __be32 nfserr; + + rqstp->rq_arg = lcp->lc_up_layout; + svcxdr_init_decode(rqstp); - nr_iomaps = nfsd4_block_decode_layoutupdate(lcp->lc_up_layout, - lcp->lc_up_len, &iomaps, i_blocksize(inode)); - if (nr_iomaps < 0) - return nfserrno(nr_iomaps); + nfserr = nfsd4_block_decode_layoutupdate(&rqstp->rq_arg_stream, + &iomaps, &nr_iomaps, i_blocksize(inode)); + if (nfserr != nfs_ok) + return nfserr; return nfsd4_block_commit_blocks(inode, lcp, iomaps, nr_iomaps); } @@ -254,8 +319,7 @@ nfsd4_block_get_device_info_scsi(struct super_block *sb, const struct pr_ops *ops; int ret; - dev = kzalloc(sizeof(struct pnfs_block_deviceaddr) + - sizeof(struct pnfs_block_volume), GFP_KERNEL); + dev = kzalloc(struct_size(dev, volumes, 1), GFP_KERNEL); if (!dev) return -ENOMEM; gdp->gd_device = dev; @@ -297,6 +361,7 @@ nfsd4_block_get_device_info_scsi(struct super_block *sb, out_free_dev: kfree(dev); + gdp->gd_device = NULL; return ret; } @@ -311,28 +376,35 @@ nfsd4_scsi_proc_getdeviceinfo(struct super_block *sb, return nfserrno(nfsd4_block_get_device_info_scsi(sb, clp, gdp)); } static __be32 -nfsd4_scsi_proc_layoutcommit(struct inode *inode, +nfsd4_scsi_proc_layoutcommit(struct inode *inode, struct svc_rqst *rqstp, struct nfsd4_layoutcommit *lcp) { struct iomap *iomaps; int nr_iomaps; + __be32 nfserr; + + rqstp->rq_arg = lcp->lc_up_layout; + svcxdr_init_decode(rqstp); - nr_iomaps = nfsd4_scsi_decode_layoutupdate(lcp->lc_up_layout, - lcp->lc_up_len, &iomaps, i_blocksize(inode)); - if (nr_iomaps < 0) - return nfserrno(nr_iomaps); + nfserr = nfsd4_scsi_decode_layoutupdate(&rqstp->rq_arg_stream, + &iomaps, &nr_iomaps, i_blocksize(inode)); + if (nfserr != nfs_ok) + return nfserr; return nfsd4_block_commit_blocks(inode, lcp, iomaps, nr_iomaps); } static void -nfsd4_scsi_fence_client(struct nfs4_layout_stateid *ls) +nfsd4_scsi_fence_client(struct nfs4_layout_stateid *ls, struct nfsd_file *file) { struct nfs4_client *clp = ls->ls_stid.sc_client; - struct block_device *bdev = ls->ls_file->nf_file->f_path.mnt->mnt_sb->s_bdev; + struct block_device *bdev = file->nf_file->f_path.mnt->mnt_sb->s_bdev; + int status; - bdev->bd_disk->fops->pr_ops->pr_preempt(bdev, NFSD_MDS_PR_KEY, - nfsd4_scsi_pr_key(clp), 0, true); + status = bdev->bd_disk->fops->pr_ops->pr_preempt(bdev, NFSD_MDS_PR_KEY, + nfsd4_scsi_pr_key(clp), + PR_EXCLUSIVE_ACCESS_REG_ONLY, true); + trace_nfsd_pnfs_fence(clp, bdev->bd_disk->disk_name, status); } const struct nfsd4_layout_ops scsi_layout_ops = { diff --git a/fs/nfsd/blocklayoutxdr.c b/fs/nfsd/blocklayoutxdr.c index 8e9c1a0f8d38..196ef4245604 100644 --- a/fs/nfsd/blocklayoutxdr.c +++ b/fs/nfsd/blocklayoutxdr.c @@ -14,12 +14,25 @@ #define NFSDDBG_FACILITY NFSDDBG_PNFS +/** + * nfsd4_block_encode_layoutget - encode block/scsi layout extent array + * @xdr: stream for data encoding + * @lgp: layoutget content, actually an array of extents to encode + * + * Encode the opaque loc_body field in the layoutget response. Since the + * pnfs_block_layout4 and pnfs_scsi_layout4 structures on the wire are + * the same, this function is used by both layout drivers. + * + * Return values: + * %nfs_ok: Success, all extents encoded into @xdr + * %nfserr_toosmall: Not enough space in @xdr to encode all the data + */ __be32 nfsd4_block_encode_layoutget(struct xdr_stream *xdr, - struct nfsd4_layoutget *lgp) + const struct nfsd4_layoutget *lgp) { - struct pnfs_block_extent *b = lgp->lg_content; - int len = sizeof(__be32) + 5 * sizeof(__be64) + sizeof(__be32); + const struct pnfs_block_layout *bl = lgp->lg_content; + u32 i, len = sizeof(__be32) + bl->nr_extents * PNFS_BLOCK_EXTENT_SIZE; __be32 *p; p = xdr_reserve_space(xdr, sizeof(__be32) + len); @@ -27,15 +40,19 @@ nfsd4_block_encode_layoutget(struct xdr_stream *xdr, return nfserr_toosmall; *p++ = cpu_to_be32(len); - *p++ = cpu_to_be32(1); /* we always return a single extent */ - - p = xdr_encode_opaque_fixed(p, &b->vol_id, - sizeof(struct nfsd4_deviceid)); - p = xdr_encode_hyper(p, b->foff); - p = xdr_encode_hyper(p, b->len); - p = xdr_encode_hyper(p, b->soff); - *p++ = cpu_to_be32(b->es); - return 0; + *p++ = cpu_to_be32(bl->nr_extents); + + for (i = 0; i < bl->nr_extents; i++) { + const struct pnfs_block_extent *bex = bl->extents + i; + + p = svcxdr_encode_deviceid4(p, &bex->vol_id); + p = xdr_encode_hyper(p, bex->foff); + p = xdr_encode_hyper(p, bex->len); + p = xdr_encode_hyper(p, bex->soff); + *p++ = cpu_to_be32(bex->es); + } + + return nfs_ok; } static int @@ -77,12 +94,21 @@ nfsd4_block_encode_volume(struct xdr_stream *xdr, struct pnfs_block_volume *b) __be32 nfsd4_block_encode_getdeviceinfo(struct xdr_stream *xdr, - struct nfsd4_getdeviceinfo *gdp) + const struct nfsd4_getdeviceinfo *gdp) { struct pnfs_block_deviceaddr *dev = gdp->gd_device; int len = sizeof(__be32), ret, i; __be32 *p; + /* + * See paragraph 5 of RFC 8881 S18.40.3. + */ + if (!gdp->gd_maxcount) { + if (xdr_stream_encode_u32(xdr, 0) != XDR_UNIT) + return nfserr_resource; + return nfs_ok; + } + p = xdr_reserve_space(xdr, len + sizeof(__be32)); if (!p) return nfserr_resource; @@ -103,64 +129,86 @@ nfsd4_block_encode_getdeviceinfo(struct xdr_stream *xdr, return 0; } -int -nfsd4_block_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp, - u32 block_size) +/** + * nfsd4_block_decode_layoutupdate - decode the block layout extent array + * @xdr: subbuf set to the encoded array + * @iomapp: pointer to store the decoded extent array + * @nr_iomapsp: pointer to store the number of extents + * @block_size: alignment of extent offset and length + * + * This function decodes the opaque field of the layoutupdate4 structure + * in a layoutcommit request for the block layout driver. The field is + * actually an array of extents sent by the client. It also checks that + * the file offset, storage offset and length of each extent are aligned + * by @block_size. + * + * Return values: + * %nfs_ok: Successful decoding, @iomapp and @nr_iomapsp are valid + * %nfserr_bad_xdr: The encoded array in @xdr is invalid + * %nfserr_inval: An unaligned extent found + * %nfserr_delay: Failed to allocate memory for @iomapp + */ +__be32 +nfsd4_block_decode_layoutupdate(struct xdr_stream *xdr, struct iomap **iomapp, + int *nr_iomapsp, u32 block_size) { struct iomap *iomaps; - u32 nr_iomaps, i; + u32 nr_iomaps, expected, len, i; + __be32 nfserr; - if (len < sizeof(u32)) { - dprintk("%s: extent array too small: %u\n", __func__, len); - return -EINVAL; - } - len -= sizeof(u32); - if (len % PNFS_BLOCK_EXTENT_SIZE) { - dprintk("%s: extent array invalid: %u\n", __func__, len); - return -EINVAL; - } + if (xdr_stream_decode_u32(xdr, &nr_iomaps)) + return nfserr_bad_xdr; - nr_iomaps = be32_to_cpup(p++); - if (nr_iomaps != len / PNFS_BLOCK_EXTENT_SIZE) { - dprintk("%s: extent array size mismatch: %u/%u\n", - __func__, len, nr_iomaps); - return -EINVAL; - } + len = sizeof(__be32) + xdr_stream_remaining(xdr); + expected = sizeof(__be32) + nr_iomaps * PNFS_BLOCK_EXTENT_SIZE; + if (len != expected) + return nfserr_bad_xdr; iomaps = kcalloc(nr_iomaps, sizeof(*iomaps), GFP_KERNEL); - if (!iomaps) { - dprintk("%s: failed to allocate extent array\n", __func__); - return -ENOMEM; - } + if (!iomaps) + return nfserr_delay; for (i = 0; i < nr_iomaps; i++) { struct pnfs_block_extent bex; - memcpy(&bex.vol_id, p, sizeof(struct nfsd4_deviceid)); - p += XDR_QUADLEN(sizeof(struct nfsd4_deviceid)); + if (nfsd4_decode_deviceid4(xdr, &bex.vol_id)) { + nfserr = nfserr_bad_xdr; + goto fail; + } - p = xdr_decode_hyper(p, &bex.foff); + if (xdr_stream_decode_u64(xdr, &bex.foff)) { + nfserr = nfserr_bad_xdr; + goto fail; + } if (bex.foff & (block_size - 1)) { - dprintk("%s: unaligned offset 0x%llx\n", - __func__, bex.foff); + nfserr = nfserr_inval; + goto fail; + } + + if (xdr_stream_decode_u64(xdr, &bex.len)) { + nfserr = nfserr_bad_xdr; goto fail; } - p = xdr_decode_hyper(p, &bex.len); if (bex.len & (block_size - 1)) { - dprintk("%s: unaligned length 0x%llx\n", - __func__, bex.foff); + nfserr = nfserr_inval; + goto fail; + } + + if (xdr_stream_decode_u64(xdr, &bex.soff)) { + nfserr = nfserr_bad_xdr; goto fail; } - p = xdr_decode_hyper(p, &bex.soff); if (bex.soff & (block_size - 1)) { - dprintk("%s: unaligned disk offset 0x%llx\n", - __func__, bex.soff); + nfserr = nfserr_inval; + goto fail; + } + + if (xdr_stream_decode_u32(xdr, &bex.es)) { + nfserr = nfserr_bad_xdr; goto fail; } - bex.es = be32_to_cpup(p++); if (bex.es != PNFS_BLOCK_READWRITE_DATA) { - dprintk("%s: incorrect extent state %d\n", - __func__, bex.es); + nfserr = nfserr_inval; goto fail; } @@ -169,59 +217,79 @@ nfsd4_block_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp, } *iomapp = iomaps; - return nr_iomaps; + *nr_iomapsp = nr_iomaps; + return nfs_ok; fail: kfree(iomaps); - return -EINVAL; + return nfserr; } -int -nfsd4_scsi_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp, - u32 block_size) +/** + * nfsd4_scsi_decode_layoutupdate - decode the scsi layout extent array + * @xdr: subbuf set to the encoded array + * @iomapp: pointer to store the decoded extent array + * @nr_iomapsp: pointer to store the number of extents + * @block_size: alignment of extent offset and length + * + * This function decodes the opaque field of the layoutupdate4 structure + * in a layoutcommit request for the scsi layout driver. The field is + * actually an array of extents sent by the client. It also checks that + * the offset and length of each extent are aligned by @block_size. + * + * Return values: + * %nfs_ok: Successful decoding, @iomapp and @nr_iomapsp are valid + * %nfserr_bad_xdr: The encoded array in @xdr is invalid + * %nfserr_inval: An unaligned extent found + * %nfserr_delay: Failed to allocate memory for @iomapp + */ +__be32 +nfsd4_scsi_decode_layoutupdate(struct xdr_stream *xdr, struct iomap **iomapp, + int *nr_iomapsp, u32 block_size) { struct iomap *iomaps; - u32 nr_iomaps, expected, i; + u32 nr_iomaps, expected, len, i; + __be32 nfserr; - if (len < sizeof(u32)) { - dprintk("%s: extent array too small: %u\n", __func__, len); - return -EINVAL; - } + if (xdr_stream_decode_u32(xdr, &nr_iomaps)) + return nfserr_bad_xdr; - nr_iomaps = be32_to_cpup(p++); + len = sizeof(__be32) + xdr_stream_remaining(xdr); expected = sizeof(__be32) + nr_iomaps * PNFS_SCSI_RANGE_SIZE; - if (len != expected) { - dprintk("%s: extent array size mismatch: %u/%u\n", - __func__, len, expected); - return -EINVAL; - } + if (len != expected) + return nfserr_bad_xdr; iomaps = kcalloc(nr_iomaps, sizeof(*iomaps), GFP_KERNEL); - if (!iomaps) { - dprintk("%s: failed to allocate extent array\n", __func__); - return -ENOMEM; - } + if (!iomaps) + return nfserr_delay; for (i = 0; i < nr_iomaps; i++) { u64 val; - p = xdr_decode_hyper(p, &val); + if (xdr_stream_decode_u64(xdr, &val)) { + nfserr = nfserr_bad_xdr; + goto fail; + } if (val & (block_size - 1)) { - dprintk("%s: unaligned offset 0x%llx\n", __func__, val); + nfserr = nfserr_inval; goto fail; } iomaps[i].offset = val; - p = xdr_decode_hyper(p, &val); + if (xdr_stream_decode_u64(xdr, &val)) { + nfserr = nfserr_bad_xdr; + goto fail; + } if (val & (block_size - 1)) { - dprintk("%s: unaligned length 0x%llx\n", __func__, val); + nfserr = nfserr_inval; goto fail; } iomaps[i].length = val; } *iomapp = iomaps; - return nr_iomaps; + *nr_iomapsp = nr_iomaps; + return nfs_ok; fail: kfree(iomaps); - return -EINVAL; + return nfserr; } diff --git a/fs/nfsd/blocklayoutxdr.h b/fs/nfsd/blocklayoutxdr.h index bc5166bfe46b..2e0c6c7d2b42 100644 --- a/fs/nfsd/blocklayoutxdr.h +++ b/fs/nfsd/blocklayoutxdr.h @@ -8,6 +8,15 @@ struct iomap; struct xdr_stream; +/* On the wire size of the layout4 struct with zero number of extents */ +#define PNFS_BLOCK_LAYOUT4_SIZE \ + (sizeof(__be32) * 2 + /* offset4 */ \ + sizeof(__be32) * 2 + /* length4 */ \ + sizeof(__be32) + /* layoutiomode4 */ \ + sizeof(__be32) + /* layouttype4 */ \ + sizeof(__be32) + /* number of bytes */ \ + sizeof(__be32)) /* number of extents */ + struct pnfs_block_extent { struct nfsd4_deviceid vol_id; u64 foff; @@ -21,6 +30,11 @@ struct pnfs_block_range { u64 len; }; +struct pnfs_block_layout { + u32 nr_extents; + struct pnfs_block_extent extents[] __counted_by(nr_extents); +}; + /* * Random upper cap for the uuid length to avoid unbounded allocation. * Not actually limited by the protocol. @@ -47,16 +61,16 @@ struct pnfs_block_volume { struct pnfs_block_deviceaddr { u32 nr_volumes; - struct pnfs_block_volume volumes[]; + struct pnfs_block_volume volumes[] __counted_by(nr_volumes); }; __be32 nfsd4_block_encode_getdeviceinfo(struct xdr_stream *xdr, - struct nfsd4_getdeviceinfo *gdp); + const struct nfsd4_getdeviceinfo *gdp); __be32 nfsd4_block_encode_layoutget(struct xdr_stream *xdr, - struct nfsd4_layoutget *lgp); -int nfsd4_block_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp, - u32 block_size); -int nfsd4_scsi_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp, - u32 block_size); + const struct nfsd4_layoutget *lgp); +__be32 nfsd4_block_decode_layoutupdate(struct xdr_stream *xdr, + struct iomap **iomapp, int *nr_iomapsp, u32 block_size); +__be32 nfsd4_scsi_decode_layoutupdate(struct xdr_stream *xdr, + struct iomap **iomapp, int *nr_iomapsp, u32 block_size); #endif /* _NFSD_BLOCKLAYOUTXDR_H */ diff --git a/fs/nfsd/cache.h b/fs/nfsd/cache.h index f21259ead64b..bb7addef4a31 100644 --- a/fs/nfsd/cache.h +++ b/fs/nfsd/cache.h @@ -10,7 +10,7 @@ #define NFSCACHE_H #include <linux/sunrpc/svc.h> -#include "netns.h" +#include "nfsd.h" /* * Representation of a reply cache entry. @@ -19,7 +19,7 @@ * typical sockaddr_storage. This is for space reasons, since sockaddr_storage * is much larger than a sockaddr_in6. */ -struct svc_cacherep { +struct nfsd_cacherep { struct { /* Keep often-read xid, csum in the same cache line: */ __be32 k_xid; @@ -82,8 +82,10 @@ int nfsd_drc_slab_create(void); void nfsd_drc_slab_free(void); int nfsd_reply_cache_init(struct nfsd_net *); void nfsd_reply_cache_shutdown(struct nfsd_net *); -int nfsd_cache_lookup(struct svc_rqst *); -void nfsd_cache_update(struct svc_rqst *, int, __be32 *); +int nfsd_cache_lookup(struct svc_rqst *rqstp, unsigned int start, + unsigned int len, struct nfsd_cacherep **cacherep); +void nfsd_cache_update(struct svc_rqst *rqstp, struct nfsd_cacherep *rp, + int cachetype, __be32 *statp); int nfsd_reply_cache_stats_show(struct seq_file *m, void *v); #endif /* NFSCACHE_H */ diff --git a/fs/nfsd/debugfs.c b/fs/nfsd/debugfs.c new file mode 100644 index 000000000000..7f44689e0a53 --- /dev/null +++ b/fs/nfsd/debugfs.c @@ -0,0 +1,143 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/debugfs.h> + +#include "nfsd.h" + +static struct dentry *nfsd_top_dir __read_mostly; + +/* + * /sys/kernel/debug/nfsd/disable-splice-read + * + * Contents: + * %0: NFS READ is allowed to use page splicing + * %1: NFS READ uses only iov iter read + * + * The default value of this setting is zero (page splicing is + * allowed). This setting takes immediate effect for all NFS + * versions, all exports, and in all NFSD net namespaces. + */ + +static int nfsd_dsr_get(void *data, u64 *val) +{ + *val = nfsd_disable_splice_read ? 1 : 0; + return 0; +} + +static int nfsd_dsr_set(void *data, u64 val) +{ + nfsd_disable_splice_read = (val > 0); + if (!nfsd_disable_splice_read) { + /* + * Must use buffered I/O if splice_read is enabled. + */ + nfsd_io_cache_read = NFSD_IO_BUFFERED; + } + return 0; +} + +DEFINE_DEBUGFS_ATTRIBUTE(nfsd_dsr_fops, nfsd_dsr_get, nfsd_dsr_set, "%llu\n"); + +/* + * /sys/kernel/debug/nfsd/io_cache_read + * + * Contents: + * %0: NFS READ will use buffered IO + * %1: NFS READ will use dontcache (buffered IO w/ dropbehind) + * %2: NFS READ will use direct IO + * + * This setting takes immediate effect for all NFS versions, + * all exports, and in all NFSD net namespaces. + */ + +static int nfsd_io_cache_read_get(void *data, u64 *val) +{ + *val = nfsd_io_cache_read; + return 0; +} + +static int nfsd_io_cache_read_set(void *data, u64 val) +{ + int ret = 0; + + switch (val) { + case NFSD_IO_BUFFERED: + nfsd_io_cache_read = NFSD_IO_BUFFERED; + break; + case NFSD_IO_DONTCACHE: + case NFSD_IO_DIRECT: + /* + * Must disable splice_read when enabling + * NFSD_IO_DONTCACHE. + */ + nfsd_disable_splice_read = true; + nfsd_io_cache_read = val; + break; + default: + ret = -EINVAL; + break; + } + + return ret; +} + +DEFINE_DEBUGFS_ATTRIBUTE(nfsd_io_cache_read_fops, nfsd_io_cache_read_get, + nfsd_io_cache_read_set, "%llu\n"); + +/* + * /sys/kernel/debug/nfsd/io_cache_write + * + * Contents: + * %0: NFS WRITE will use buffered IO + * %1: NFS WRITE will use dontcache (buffered IO w/ dropbehind) + * + * This setting takes immediate effect for all NFS versions, + * all exports, and in all NFSD net namespaces. + */ + +static int nfsd_io_cache_write_get(void *data, u64 *val) +{ + *val = nfsd_io_cache_write; + return 0; +} + +static int nfsd_io_cache_write_set(void *data, u64 val) +{ + int ret = 0; + + switch (val) { + case NFSD_IO_BUFFERED: + case NFSD_IO_DONTCACHE: + case NFSD_IO_DIRECT: + nfsd_io_cache_write = val; + break; + default: + ret = -EINVAL; + break; + } + + return ret; +} + +DEFINE_DEBUGFS_ATTRIBUTE(nfsd_io_cache_write_fops, nfsd_io_cache_write_get, + nfsd_io_cache_write_set, "%llu\n"); + +void nfsd_debugfs_exit(void) +{ + debugfs_remove_recursive(nfsd_top_dir); + nfsd_top_dir = NULL; +} + +void nfsd_debugfs_init(void) +{ + nfsd_top_dir = debugfs_create_dir("nfsd", NULL); + + debugfs_create_file("disable-splice-read", S_IWUSR | S_IRUGO, + nfsd_top_dir, NULL, &nfsd_dsr_fops); + + debugfs_create_file("io_cache_read", 0644, nfsd_top_dir, NULL, + &nfsd_io_cache_read_fops); + + debugfs_create_file("io_cache_write", 0644, nfsd_top_dir, NULL, + &nfsd_io_cache_write_fops); +} diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index 668c7527b17e..9d55512d0cc9 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -82,8 +82,7 @@ static int expkey_parse(struct cache_detail *cd, char *mesg, int mlen) int len; struct auth_domain *dom = NULL; int err; - int fsidtype; - char *ep; + u8 fsidtype; struct svc_expkey key; struct svc_expkey *ek = NULL; @@ -97,7 +96,7 @@ static int expkey_parse(struct cache_detail *cd, char *mesg, int mlen) goto out; err = -EINVAL; - if ((len=qword_get(&mesg, buf, PAGE_SIZE)) <= 0) + if (qword_get(&mesg, buf, PAGE_SIZE) <= 0) goto out; err = -ENOENT; @@ -107,12 +106,11 @@ static int expkey_parse(struct cache_detail *cd, char *mesg, int mlen) dprintk("found domain %s\n", buf); err = -EINVAL; - if ((len=qword_get(&mesg, buf, PAGE_SIZE)) <= 0) + if (qword_get(&mesg, buf, PAGE_SIZE) <= 0) goto out; - fsidtype = simple_strtoul(buf, &ep, 10); - if (*ep) + if (kstrtou8(buf, 10, &fsidtype)) goto out; - dprintk("found fsidtype %d\n", fsidtype); + dprintk("found fsidtype %u\n", fsidtype); if (key_len(fsidtype)==0) /* invalid type */ goto out; if ((len=qword_get(&mesg, buf, PAGE_SIZE)) <= 0) @@ -123,11 +121,11 @@ static int expkey_parse(struct cache_detail *cd, char *mesg, int mlen) /* OK, we seem to have a valid key */ key.h.flags = 0; - key.h.expiry_time = get_expiry(&mesg); - if (key.h.expiry_time == 0) + err = get_expiry(&mesg, &key.h.expiry_time); + if (err) goto out; - key.ek_client = dom; + key.ek_client = dom; key.ek_fsidtype = fsidtype; memcpy(key.ek_fsid, buf, len); @@ -334,28 +332,46 @@ static void nfsd4_fslocs_free(struct nfsd4_fs_locations *fsloc) static int export_stats_init(struct export_stats *stats) { stats->start_time = ktime_get_seconds(); - return nfsd_percpu_counters_init(stats->counter, EXP_STATS_COUNTERS_NUM); + return percpu_counter_init_many(stats->counter, 0, GFP_KERNEL, + EXP_STATS_COUNTERS_NUM); } static void export_stats_reset(struct export_stats *stats) { - nfsd_percpu_counters_reset(stats->counter, EXP_STATS_COUNTERS_NUM); + if (stats) { + int i; + + for (i = 0; i < EXP_STATS_COUNTERS_NUM; i++) + percpu_counter_set(&stats->counter[i], 0); + } } static void export_stats_destroy(struct export_stats *stats) { - nfsd_percpu_counters_destroy(stats->counter, EXP_STATS_COUNTERS_NUM); + if (stats) + percpu_counter_destroy_many(stats->counter, + EXP_STATS_COUNTERS_NUM); +} + +static void svc_export_release(struct rcu_head *rcu_head) +{ + struct svc_export *exp = container_of(rcu_head, struct svc_export, + ex_rcu); + + nfsd4_fslocs_free(&exp->ex_fslocs); + export_stats_destroy(exp->ex_stats); + kfree(exp->ex_stats); + kfree(exp->ex_uuid); + kfree(exp); } static void svc_export_put(struct kref *ref) { struct svc_export *exp = container_of(ref, struct svc_export, h.ref); + path_put(&exp->ex_path); auth_domain_put(exp->ex_client); - nfsd4_fslocs_free(&exp->ex_fslocs); - export_stats_destroy(&exp->ex_stats); - kfree(exp->ex_uuid); - kfree_rcu(exp, ex_rcu); + call_rcu(&exp->ex_rcu, svc_export_release); } static int svc_export_upcall(struct cache_detail *cd, struct cache_head *h) @@ -386,7 +402,7 @@ static struct svc_export *svc_export_update(struct svc_export *new, struct svc_export *old); static struct svc_export *svc_export_lookup(struct svc_export *); -static int check_export(struct path *path, int *flags, unsigned char *uuid) +static int check_export(const struct path *path, int *flags, unsigned char *uuid) { struct inode *inode = d_inode(path->dentry); @@ -421,8 +437,7 @@ static int check_export(struct path *path, int *flags, unsigned char *uuid) return -EINVAL; } - if (!inode->i_sb->s_export_op || - !inode->i_sb->s_export_op->fh_to_dentry) { + if (!exportfs_can_decode_fh(inode->i_sb->s_export_op)) { dprintk("exp_export: export of invalid fs type.\n"); return -EINVAL; } @@ -439,7 +454,6 @@ static int check_export(struct path *path, int *flags, unsigned char *uuid) return -EINVAL; } return 0; - } #ifdef CONFIG_NFSD_V4 @@ -546,6 +560,29 @@ static inline int secinfo_parse(char **mesg, char *buf, struct svc_export *exp) { return 0; } #endif +static int xprtsec_parse(char **mesg, char *buf, struct svc_export *exp) +{ + unsigned int i, mode, listsize; + int err; + + err = get_uint(mesg, &listsize); + if (err) + return err; + if (listsize > NFSEXP_XPRTSEC_NUM) + return -EINVAL; + + exp->ex_xprtsec_modes = 0; + for (i = 0; i < listsize; i++) { + err = get_uint(mesg, &mode); + if (err) + return err; + if (mode > NFSEXP_XPRTSEC_MTLS) + return -EINVAL; + exp->ex_xprtsec_modes |= mode; + } + return 0; +} + static inline int nfsd_uuid_parse(char **mesg, char *buf, unsigned char **puuid) { @@ -571,7 +608,6 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) { /* client path expiry [flags anonuid anongid fsid] */ char *buf; - int len; int err; struct auth_domain *dom = NULL; struct svc_export exp = {}, *expp; @@ -587,8 +623,7 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) /* client */ err = -EINVAL; - len = qword_get(&mesg, buf, PAGE_SIZE); - if (len <= 0) + if (qword_get(&mesg, buf, PAGE_SIZE) <= 0) goto out; err = -ENOENT; @@ -598,7 +633,7 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) /* path */ err = -EINVAL; - if ((len = qword_get(&mesg, buf, PAGE_SIZE)) <= 0) + if (qword_get(&mesg, buf, PAGE_SIZE) <= 0) goto out1; err = kern_path(buf, 0, &exp.ex_path); @@ -608,11 +643,11 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) exp.ex_client = dom; exp.cd = cd; exp.ex_devid_map = NULL; + exp.ex_xprtsec_modes = NFSEXP_XPRTSEC_ALL; /* expiry */ - err = -EINVAL; - exp.h.expiry_time = get_expiry(&mesg); - if (exp.h.expiry_time == 0) + err = get_expiry(&mesg, &exp.h.expiry_time); + if (err) goto out3; /* flags */ @@ -624,7 +659,7 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) if (err || an_int < 0) goto out3; exp.ex_flags= an_int; - + /* anon uid */ err = get_int(&mesg, &an_int); if (err) @@ -643,13 +678,15 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) goto out3; exp.ex_fsid = an_int; - while ((len = qword_get(&mesg, buf, PAGE_SIZE)) > 0) { + while (qword_get(&mesg, buf, PAGE_SIZE) > 0) { if (strcmp(buf, "fsloc") == 0) err = fsloc_parse(&mesg, buf, &exp.ex_fslocs); else if (strcmp(buf, "uuid") == 0) err = nfsd_uuid_parse(&mesg, buf, &exp.ex_uuid); else if (strcmp(buf, "secinfo") == 0) err = secinfo_parse(&mesg, buf, &exp); + else if (strcmp(buf, "xprtsec") == 0) + err = xprtsec_parse(&mesg, buf, &exp); else /* quietly ignore unknown words and anything * following. Newer user-space can try to set @@ -663,6 +700,7 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) err = check_export(&exp.ex_path, &exp.ex_flags, exp.ex_uuid); if (err) goto out4; + /* * No point caching this if it would immediately expire. * Also, this protects exportfs's dummy export from the @@ -744,13 +782,15 @@ static int svc_export_show(struct seq_file *m, seq_putc(m, '\t'); seq_escape(m, exp->ex_client->name, " \t\n\\"); if (export_stats) { - seq_printf(m, "\t%lld\n", exp->ex_stats.start_time); + struct percpu_counter *counter = exp->ex_stats->counter; + + seq_printf(m, "\t%lld\n", exp->ex_stats->start_time); seq_printf(m, "\tfh_stale: %lld\n", - percpu_counter_sum_positive(&exp->ex_stats.counter[EXP_STATS_FH_STALE])); + percpu_counter_sum_positive(&counter[EXP_STATS_FH_STALE])); seq_printf(m, "\tio_read: %lld\n", - percpu_counter_sum_positive(&exp->ex_stats.counter[EXP_STATS_IO_READ])); + percpu_counter_sum_positive(&counter[EXP_STATS_IO_READ])); seq_printf(m, "\tio_write: %lld\n", - percpu_counter_sum_positive(&exp->ex_stats.counter[EXP_STATS_IO_WRITE])); + percpu_counter_sum_positive(&counter[EXP_STATS_IO_WRITE])); seq_putc(m, '\n'); return 0; } @@ -796,7 +836,7 @@ static void svc_export_init(struct cache_head *cnew, struct cache_head *citem) new->ex_layout_types = 0; new->ex_uuid = NULL; new->cd = item->cd; - export_stats_reset(&new->ex_stats); + export_stats_reset(new->ex_stats); } static void export_update(struct cache_head *cnew, struct cache_head *citem) @@ -824,6 +864,7 @@ static void export_update(struct cache_head *cnew, struct cache_head *citem) for (i = 0; i < MAX_SECINFO_LIST; i++) { new->ex_flavors[i] = item->ex_flavors[i]; } + new->ex_xprtsec_modes = item->ex_xprtsec_modes; } static struct cache_head *svc_export_alloc(void) @@ -832,7 +873,14 @@ static struct cache_head *svc_export_alloc(void) if (!i) return NULL; - if (export_stats_init(&i->ex_stats)) { + i->ex_stats = kmalloc(sizeof(*(i->ex_stats)), GFP_KERNEL); + if (!i->ex_stats) { + kfree(i); + return NULL; + } + + if (export_stats_init(i->ex_stats)) { + kfree(i->ex_stats); kfree(i); return NULL; } @@ -1033,24 +1081,76 @@ static struct svc_export *exp_find(struct cache_detail *cd, return exp; } -__be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp) +/** + * check_xprtsec_policy - check if access to export is allowed by the + * xprtsec policy + * @exp: svc_export that is being accessed. + * @rqstp: svc_rqst attempting to access @exp. + * + * Helper function for check_nfsd_access(). Note that callers should be + * using check_nfsd_access() instead of calling this function directly. The + * one exception is __fh_verify() since it has logic that may result in one + * or both of the helpers being skipped. + * + * Return values: + * %nfs_ok if access is granted, or + * %nfserr_wrongsec if access is denied + */ +__be32 check_xprtsec_policy(struct svc_export *exp, struct svc_rqst *rqstp) { - struct exp_flavor_info *f; - struct exp_flavor_info *end = exp->ex_flavors + exp->ex_nflavors; + struct svc_xprt *xprt = rqstp->rq_xprt; + + if (exp->ex_xprtsec_modes & NFSEXP_XPRTSEC_NONE) { + if (!test_bit(XPT_TLS_SESSION, &xprt->xpt_flags)) + return nfs_ok; + } + if (exp->ex_xprtsec_modes & NFSEXP_XPRTSEC_TLS) { + if (test_bit(XPT_TLS_SESSION, &xprt->xpt_flags) && + !test_bit(XPT_PEER_AUTH, &xprt->xpt_flags)) + return nfs_ok; + } + if (exp->ex_xprtsec_modes & NFSEXP_XPRTSEC_MTLS) { + if (test_bit(XPT_TLS_SESSION, &xprt->xpt_flags) && + test_bit(XPT_PEER_AUTH, &xprt->xpt_flags)) + return nfs_ok; + } + return nfserr_wrongsec; +} + +/** + * check_security_flavor - check if access to export is allowed by the + * security flavor + * @exp: svc_export that is being accessed. + * @rqstp: svc_rqst attempting to access @exp. + * @may_bypass_gss: reduce strictness of authorization check + * + * Helper function for check_nfsd_access(). Note that callers should be + * using check_nfsd_access() instead of calling this function directly. The + * one exception is __fh_verify() since it has logic that may result in one + * or both of the helpers being skipped. + * + * Return values: + * %nfs_ok if access is granted, or + * %nfserr_wrongsec if access is denied + */ +__be32 check_security_flavor(struct svc_export *exp, struct svc_rqst *rqstp, + bool may_bypass_gss) +{ + struct exp_flavor_info *f, *end = exp->ex_flavors + exp->ex_nflavors; /* legacy gss-only clients are always OK: */ if (exp->ex_client == rqstp->rq_gssclient) - return 0; + return nfs_ok; /* ip-address based client; check sec= export option: */ for (f = exp->ex_flavors; f < end; f++) { if (f->pseudoflavor == rqstp->rq_cred.cr_flavor) - return 0; + return nfs_ok; } /* defaults in absence of sec= options: */ if (exp->ex_nflavors == 0) { if (rqstp->rq_cred.cr_flavor == RPC_AUTH_NULL || rqstp->rq_cred.cr_flavor == RPC_AUTH_UNIX) - return 0; + return nfs_ok; } /* If the compound op contains a spo_must_allowed op, @@ -1060,9 +1160,47 @@ __be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp) */ if (nfsd4_spo_must_allow(rqstp)) - return 0; + return nfs_ok; + + /* Some calls may be processed without authentication + * on GSS exports. For example NFS2/3 calls on root + * directory, see section 2.3.2 of rfc 2623. + * For "may_bypass_gss" check that export has really + * enabled some flavor with authentication (GSS or any + * other) and also check that the used auth flavor is + * without authentication (none or sys). + */ + if (may_bypass_gss && ( + rqstp->rq_cred.cr_flavor == RPC_AUTH_NULL || + rqstp->rq_cred.cr_flavor == RPC_AUTH_UNIX)) { + for (f = exp->ex_flavors; f < end; f++) { + if (f->pseudoflavor >= RPC_AUTH_DES) + return 0; + } + } + + return nfserr_wrongsec; +} + +/** + * check_nfsd_access - check if access to export is allowed. + * @exp: svc_export that is being accessed. + * @rqstp: svc_rqst attempting to access @exp. + * @may_bypass_gss: reduce strictness of authorization check + * + * Return values: + * %nfs_ok if access is granted, or + * %nfserr_wrongsec if access is denied + */ +__be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp, + bool may_bypass_gss) +{ + __be32 status; - return rqstp->rq_vers < 4 ? nfserr_acces : nfserr_wrongsec; + status = check_xprtsec_policy(exp, rqstp); + if (status != nfs_ok) + return status; + return check_security_flavor(exp, rqstp, may_bypass_gss); } /* @@ -1075,7 +1213,7 @@ __be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp) * use exp_get_by_name() or exp_find(). */ struct svc_export * -rqst_exp_get_by_name(struct svc_rqst *rqstp, struct path *path) +rqst_exp_get_by_name(struct svc_rqst *rqstp, const struct path *path) { struct svc_export *gssexp, *exp = ERR_PTR(-ENOENT); struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); @@ -1105,19 +1243,35 @@ gss: return gssexp; } +/** + * rqst_exp_find - Find an svc_export in the context of a rqst or similar + * @reqp: The handle to be used to suspend the request if a cache-upcall is needed + * If NULL, missing in-cache information will result in failure. + * @net: The network namespace in which the request exists + * @cl: default auth_domain to use for looking up the export + * @gsscl: an alternate auth_domain defined using deprecated gss/krb5 format. + * @fsid_type: The type of fsid to look for + * @fsidv: The actual fsid to look up in the context of either client. + * + * Perform a lookup for @cl/@fsidv in the given @net for an export. If + * none found and @gsscl specified, repeat the lookup. + * + * Returns an export, or an error pointer. + */ struct svc_export * -rqst_exp_find(struct svc_rqst *rqstp, int fsid_type, u32 *fsidv) +rqst_exp_find(struct cache_req *reqp, struct net *net, + struct auth_domain *cl, struct auth_domain *gsscl, + int fsid_type, u32 *fsidv) { + struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct svc_export *gssexp, *exp = ERR_PTR(-ENOENT); - struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); struct cache_detail *cd = nn->svc_export_cache; - if (rqstp->rq_client == NULL) + if (!cl) goto gss; /* First try the auth_unix client: */ - exp = exp_find(cd, rqstp->rq_client, fsid_type, - fsidv, &rqstp->rq_chandle); + exp = exp_find(cd, cl, fsid_type, fsidv, reqp); if (PTR_ERR(exp) == -ENOENT) goto gss; if (IS_ERR(exp)) @@ -1127,10 +1281,9 @@ rqst_exp_find(struct svc_rqst *rqstp, int fsid_type, u32 *fsidv) return exp; gss: /* Otherwise, try falling back on gss client */ - if (rqstp->rq_gssclient == NULL) + if (!gsscl) return exp; - gssexp = exp_find(cd, rqstp->rq_gssclient, fsid_type, fsidv, - &rqstp->rq_chandle); + gssexp = exp_find(cd, gsscl, fsid_type, fsidv, reqp); if (PTR_ERR(gssexp) == -ENOENT) return exp; if (!IS_ERR(exp)) @@ -1161,7 +1314,9 @@ struct svc_export *rqst_find_fsidzero_export(struct svc_rqst *rqstp) mk_fsid(FSID_NUM, fsidv, 0, 0, 0, NULL); - return rqst_exp_find(rqstp, FSID_NUM, fsidv); + return rqst_exp_find(&rqstp->rq_chandle, SVC_NET(rqstp), + rqstp->rq_client, rqstp->rq_gssclient, + FSID_NUM, fsidv); } /* @@ -1310,10 +1465,9 @@ static int e_show(struct seq_file *m, void *p) return 0; } - exp_get(exp); - if (cache_check(cd, &exp->h, NULL)) + if (cache_check_rcu(cd, &exp->h, NULL)) return 0; - exp_put(exp); + return svc_export_show(m, cd, cp); } diff --git a/fs/nfsd/export.h b/fs/nfsd/export.h index d03f7f6a8642..d2b09cd76145 100644 --- a/fs/nfsd/export.h +++ b/fs/nfsd/export.h @@ -64,10 +64,10 @@ struct svc_export { struct cache_head h; struct auth_domain * ex_client; int ex_flags; + int ex_fsid; struct path ex_path; kuid_t ex_anon_uid; kgid_t ex_anon_gid; - int ex_fsid; unsigned char * ex_uuid; /* 16 byte fsid */ struct nfsd4_fs_locations ex_fslocs; uint32_t ex_nflavors; @@ -76,7 +76,8 @@ struct svc_export { struct nfsd4_deviceid_map *ex_devid_map; struct cache_detail *cd; struct rcu_head ex_rcu; - struct export_stats ex_stats; + unsigned long ex_xprtsec_modes; + struct export_stats *ex_stats; }; /* an "export key" (expkey) maps a filehandlefragement to an @@ -87,7 +88,7 @@ struct svc_expkey { struct cache_head h; struct auth_domain * ek_client; - int ek_fsidtype; + u8 ek_fsidtype; u32 ek_fsid[6]; struct path ek_path; @@ -98,8 +99,13 @@ struct svc_expkey { #define EX_NOHIDE(exp) ((exp)->ex_flags & NFSEXP_NOHIDE) #define EX_WGATHER(exp) ((exp)->ex_flags & NFSEXP_GATHERED_WRITES) -int nfsexp_flags(struct svc_rqst *rqstp, struct svc_export *exp); -__be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp); +struct svc_cred; +int nfsexp_flags(struct svc_cred *cred, struct svc_export *exp); +__be32 check_xprtsec_policy(struct svc_export *exp, struct svc_rqst *rqstp); +__be32 check_security_flavor(struct svc_export *exp, struct svc_rqst *rqstp, + bool may_bypass_gss); +__be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp, + bool may_bypass_gss); /* * Function declarations @@ -108,7 +114,7 @@ int nfsd_export_init(struct net *); void nfsd_export_shutdown(struct net *); void nfsd_export_flush(struct net *); struct svc_export * rqst_exp_get_by_name(struct svc_rqst *, - struct path *); + const struct path *); struct svc_export * rqst_exp_parent(struct svc_rqst *, struct path *); struct svc_export * rqst_find_fsidzero_export(struct svc_rqst *); @@ -126,6 +132,8 @@ static inline struct svc_export *exp_get(struct svc_export *exp) cache_get(&exp->h); return exp; } -struct svc_export * rqst_exp_find(struct svc_rqst *, int, u32 *); +struct svc_export *rqst_exp_find(struct cache_req *reqp, struct net *net, + struct auth_domain *cl, struct auth_domain *gsscl, + int fsid_type, u32 *fsidv); #endif /* NFSD_EXPORT_H */ diff --git a/fs/nfsd/fault_inject.c b/fs/nfsd/fault_inject.c deleted file mode 100644 index 76bee0a0d308..000000000000 --- a/fs/nfsd/fault_inject.c +++ /dev/null @@ -1,142 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (c) 2011 Bryan Schumaker <bjschuma@netapp.com> - * - * Uses debugfs to create fault injection points for client testing - */ - -#include <linux/types.h> -#include <linux/fs.h> -#include <linux/debugfs.h> -#include <linux/module.h> -#include <linux/nsproxy.h> -#include <linux/sunrpc/addr.h> -#include <linux/uaccess.h> -#include <linux/kernel.h> - -#include "state.h" -#include "netns.h" - -struct nfsd_fault_inject_op { - char *file; - u64 (*get)(void); - u64 (*set_val)(u64); - u64 (*set_clnt)(struct sockaddr_storage *, size_t); -}; - -static struct dentry *debug_dir; - -static ssize_t fault_inject_read(struct file *file, char __user *buf, - size_t len, loff_t *ppos) -{ - static u64 val; - char read_buf[25]; - size_t size; - loff_t pos = *ppos; - struct nfsd_fault_inject_op *op = file_inode(file)->i_private; - - if (!pos) - val = op->get(); - size = scnprintf(read_buf, sizeof(read_buf), "%llu\n", val); - - return simple_read_from_buffer(buf, len, ppos, read_buf, size); -} - -static ssize_t fault_inject_write(struct file *file, const char __user *buf, - size_t len, loff_t *ppos) -{ - char write_buf[INET6_ADDRSTRLEN]; - size_t size = min(sizeof(write_buf) - 1, len); - struct net *net = current->nsproxy->net_ns; - struct sockaddr_storage sa; - struct nfsd_fault_inject_op *op = file_inode(file)->i_private; - u64 val; - char *nl; - - if (copy_from_user(write_buf, buf, size)) - return -EFAULT; - write_buf[size] = '\0'; - - /* Deal with any embedded newlines in the string */ - nl = strchr(write_buf, '\n'); - if (nl) { - size = nl - write_buf; - *nl = '\0'; - } - - size = rpc_pton(net, write_buf, size, (struct sockaddr *)&sa, sizeof(sa)); - if (size > 0) { - val = op->set_clnt(&sa, size); - if (val) - pr_info("NFSD [%s]: Client %s had %llu state object(s)\n", - op->file, write_buf, val); - } else { - val = simple_strtoll(write_buf, NULL, 0); - if (val == 0) - pr_info("NFSD Fault Injection: %s (all)", op->file); - else - pr_info("NFSD Fault Injection: %s (n = %llu)", - op->file, val); - val = op->set_val(val); - pr_info("NFSD: %s: found %llu", op->file, val); - } - return len; /* on success, claim we got the whole input */ -} - -static const struct file_operations fops_nfsd = { - .owner = THIS_MODULE, - .read = fault_inject_read, - .write = fault_inject_write, -}; - -void nfsd_fault_inject_cleanup(void) -{ - debugfs_remove_recursive(debug_dir); -} - -static struct nfsd_fault_inject_op inject_ops[] = { - { - .file = "forget_clients", - .get = nfsd_inject_print_clients, - .set_val = nfsd_inject_forget_clients, - .set_clnt = nfsd_inject_forget_client, - }, - { - .file = "forget_locks", - .get = nfsd_inject_print_locks, - .set_val = nfsd_inject_forget_locks, - .set_clnt = nfsd_inject_forget_client_locks, - }, - { - .file = "forget_openowners", - .get = nfsd_inject_print_openowners, - .set_val = nfsd_inject_forget_openowners, - .set_clnt = nfsd_inject_forget_client_openowners, - }, - { - .file = "forget_delegations", - .get = nfsd_inject_print_delegations, - .set_val = nfsd_inject_forget_delegations, - .set_clnt = nfsd_inject_forget_client_delegations, - }, - { - .file = "recall_delegations", - .get = nfsd_inject_print_delegations, - .set_val = nfsd_inject_recall_delegations, - .set_clnt = nfsd_inject_recall_client_delegations, - }, -}; - -void nfsd_fault_inject_init(void) -{ - unsigned int i; - struct nfsd_fault_inject_op *op; - umode_t mode = S_IFREG | S_IRUSR | S_IWUSR; - - debug_dir = debugfs_create_dir("nfsd", NULL); - - for (i = 0; i < ARRAY_SIZE(inject_ops); i++) { - op = &inject_ops[i]; - debugfs_create_file(op->file, mode, debug_dir, op, &fops_nfsd); - } -} diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index c0950edb26b0..93798575b807 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -39,6 +39,7 @@ #include <linux/fsnotify.h> #include <linux/seq_file.h> #include <linux/rhashtable.h> +#include <linux/nfslocalio.h> #include "vfs.h" #include "nfsd.h" @@ -52,92 +53,29 @@ #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); +static DEFINE_PER_CPU(unsigned long, nfsd_file_allocations); static DEFINE_PER_CPU(unsigned long, nfsd_file_releases); static DEFINE_PER_CPU(unsigned long, nfsd_file_total_age); static DEFINE_PER_CPU(unsigned long, nfsd_file_evictions); struct nfsd_fcache_disposal { - struct work_struct work; spinlock_t lock; struct list_head freeme; }; -static struct workqueue_struct *nfsd_filecache_wq __read_mostly; - static struct kmem_cache *nfsd_file_slab; static struct kmem_cache *nfsd_file_mark_slab; static struct list_lru nfsd_file_lru; static unsigned long nfsd_file_flags; static struct fsnotify_group *nfsd_file_fsnotify_group; static struct delayed_work nfsd_filecache_laundrette; -static struct rhashtable nfsd_file_rhash_tbl +static struct rhltable nfsd_file_rhltable ____cacheline_aligned_in_smp; -enum nfsd_file_lookup_type { - NFSD_FILE_KEY_INODE, - NFSD_FILE_KEY_FULL, -}; - -struct nfsd_file_lookup_key { - struct inode *inode; - struct net *net; - const struct cred *cred; - unsigned char need; - bool gc; - enum nfsd_file_lookup_type type; -}; - -/* - * The returned hash value is based solely on the address of an in-code - * inode, a pointer to a slab-allocated object. The entropy in such a - * pointer is concentrated in its middle bits. - */ -static u32 nfsd_file_inode_hash(const struct inode *inode, u32 seed) -{ - unsigned long ptr = (unsigned long)inode; - u32 k; - - k = ptr >> L1_CACHE_SHIFT; - k &= 0x00ffffff; - return jhash2(&k, 1, seed); -} - -/** - * nfsd_file_key_hashfn - Compute the hash value of a lookup key - * @data: key on which to compute the hash value - * @len: rhash table's key_len parameter (unused) - * @seed: rhash table's random seed of the day - * - * Return value: - * Computed 32-bit hash value - */ -static u32 nfsd_file_key_hashfn(const void *data, u32 len, u32 seed) -{ - const struct nfsd_file_lookup_key *key = data; - - return nfsd_file_inode_hash(key->inode, seed); -} - -/** - * nfsd_file_obj_hashfn - Compute the hash value of an nfsd_file - * @data: object on which to compute the hash value - * @len: rhash table's key_len parameter (unused) - * @seed: rhash table's random seed of the day - * - * Return value: - * Computed 32-bit hash value - */ -static u32 nfsd_file_obj_hashfn(const void *data, u32 len, u32 seed) -{ - const struct nfsd_file *nf = data; - - return nfsd_file_inode_hash(nf->nf_inode, seed); -} - static bool nfsd_match_cred(const struct cred *c1, const struct cred *c2) { @@ -158,53 +96,16 @@ nfsd_match_cred(const struct cred *c1, const struct cred *c2) return true; } -/** - * nfsd_file_obj_cmpfn - Match a cache item against search criteria - * @arg: search criteria - * @ptr: cache item to check - * - * Return values: - * %0 - Item matches search criteria - * %1 - Item does not match search criteria - */ -static int nfsd_file_obj_cmpfn(struct rhashtable_compare_arg *arg, - const void *ptr) -{ - const struct nfsd_file_lookup_key *key = arg->key; - const struct nfsd_file *nf = ptr; - - switch (key->type) { - case NFSD_FILE_KEY_INODE: - if (nf->nf_inode != key->inode) - return 1; - break; - case NFSD_FILE_KEY_FULL: - if (nf->nf_inode != key->inode) - return 1; - if (nf->nf_may != key->need) - return 1; - if (nf->nf_net != key->net) - return 1; - if (!nfsd_match_cred(nf->nf_cred, key->cred)) - return 1; - if (!!test_bit(NFSD_FILE_GC, &nf->nf_flags) != key->gc) - return 1; - if (test_bit(NFSD_FILE_HASHED, &nf->nf_flags) == 0) - return 1; - break; - } - return 0; -} - static const struct rhashtable_params nfsd_file_rhash_params = { .key_len = sizeof_field(struct nfsd_file, nf_inode), .key_offset = offsetof(struct nfsd_file, nf_inode), - .head_offset = offsetof(struct nfsd_file, nf_rhash), - .hashfn = nfsd_file_key_hashfn, - .obj_hashfn = nfsd_file_obj_hashfn, - .obj_cmpfn = nfsd_file_obj_cmpfn, - /* Reduce resizing churn on light workloads */ - .min_size = 512, /* buckets */ + .head_offset = offsetof(struct nfsd_file, nf_rlist), + + /* + * Start with a single page hash table to reduce resizing churn + * on light workloads. + */ + .min_size = 256, .automatic_shrinking = true, }; @@ -212,7 +113,7 @@ static void nfsd_file_schedule_laundrette(void) { if (test_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags)) - queue_delayed_work(system_wq, &nfsd_filecache_laundrette, + queue_delayed_work(system_dfl_wq, &nfsd_filecache_laundrette, NFSD_LAUNDRETTE_DELAY); } @@ -252,7 +153,7 @@ nfsd_file_mark_put(struct nfsd_file_mark *nfm) } static struct nfsd_file_mark * -nfsd_file_mark_find_or_create(struct nfsd_file *nf, struct inode *inode) +nfsd_file_mark_find_or_create(struct inode *inode) { int err; struct fsnotify_mark *mark; @@ -260,8 +161,8 @@ nfsd_file_mark_find_or_create(struct nfsd_file *nf, struct inode *inode) do { fsnotify_group_lock(nfsd_file_fsnotify_group); - mark = fsnotify_find_mark(&inode->i_fsnotify_marks, - nfsd_file_fsnotify_group); + mark = fsnotify_find_inode_mark(inode, + nfsd_file_fsnotify_group); if (mark) { nfm = nfsd_file_mark_get(container_of(mark, struct nfsd_file_mark, @@ -307,63 +208,58 @@ nfsd_file_mark_find_or_create(struct nfsd_file *nf, struct inode *inode) } static struct nfsd_file * -nfsd_file_alloc(struct nfsd_file_lookup_key *key, unsigned int may) +nfsd_file_alloc(struct net *net, struct inode *inode, unsigned char need, + bool want_gc) { struct nfsd_file *nf; nf = kmem_cache_alloc(nfsd_file_slab, GFP_KERNEL); - if (nf) { - INIT_LIST_HEAD(&nf->nf_lru); - nf->nf_birthtime = ktime_get(); - nf->nf_file = NULL; - nf->nf_cred = get_current_cred(); - nf->nf_net = key->net; - nf->nf_flags = 0; - __set_bit(NFSD_FILE_HASHED, &nf->nf_flags); - __set_bit(NFSD_FILE_PENDING, &nf->nf_flags); - if (key->gc) - __set_bit(NFSD_FILE_GC, &nf->nf_flags); - nf->nf_inode = key->inode; - refcount_set(&nf->nf_ref, 1); - nf->nf_may = key->need; - nf->nf_mark = NULL; - } + if (unlikely(!nf)) + return NULL; + + this_cpu_inc(nfsd_file_allocations); + INIT_LIST_HEAD(&nf->nf_lru); + INIT_LIST_HEAD(&nf->nf_gc); + nf->nf_birthtime = ktime_get(); + nf->nf_file = NULL; + nf->nf_cred = get_current_cred(); + nf->nf_net = net; + nf->nf_flags = want_gc ? + BIT(NFSD_FILE_HASHED) | BIT(NFSD_FILE_PENDING) | BIT(NFSD_FILE_GC) : + BIT(NFSD_FILE_HASHED) | BIT(NFSD_FILE_PENDING); + nf->nf_inode = inode; + refcount_set(&nf->nf_ref, 1); + nf->nf_may = need; + nf->nf_mark = NULL; + nf->nf_dio_mem_align = 0; + nf->nf_dio_offset_align = 0; + nf->nf_dio_read_offset_align = 0; return nf; } +/** + * nfsd_file_check_write_error - check for writeback errors on a file + * @nf: nfsd_file to check for writeback errors + * + * Check whether a nfsd_file has an unseen error. Reset the write + * verifier if so. + */ static void -nfsd_file_fsync(struct nfsd_file *nf) -{ - struct file *file = nf->nf_file; - int ret; - - if (!file || !(file->f_mode & FMODE_WRITE)) - return; - ret = vfs_fsync(file, 1); - trace_nfsd_file_fsync(nf, ret); - if (ret) - nfsd_reset_write_verifier(net_generic(nf->nf_net, nfsd_net_id)); -} - -static int nfsd_file_check_write_error(struct nfsd_file *nf) { struct file *file = nf->nf_file; - if (!file || !(file->f_mode & FMODE_WRITE)) - return 0; - return filemap_check_wb_err(file->f_mapping, READ_ONCE(file->f_wb_err)); + if ((file->f_mode & FMODE_WRITE) && + filemap_check_wb_err(file->f_mapping, READ_ONCE(file->f_wb_err))) + nfsd_reset_write_verifier(net_generic(nf->nf_net, nfsd_net_id)); } static void nfsd_file_hash_remove(struct nfsd_file *nf) { trace_nfsd_file_unhash(nf); - - if (nfsd_file_check_write_error(nf)) - nfsd_reset_write_verifier(net_generic(nf->nf_net, nfsd_net_id)); - rhashtable_remove_fast(&nfsd_file_rhash_tbl, &nf->nf_rhash, - nfsd_file_rhash_params); + rhltable_remove(&nfsd_file_rhltable, &nf->nf_rlist, + nfsd_file_rhash_params); } static bool @@ -387,24 +283,11 @@ nfsd_file_free(struct nfsd_file *nf) this_cpu_add(nfsd_file_total_age, age); nfsd_file_unhash(nf); - - /* - * We call fsync here in order to catch writeback errors. It's not - * strictly required by the protocol, but an nfsd_file could get - * evicted from the cache before a COMMIT comes in. If another - * task were to open that file in the interim and scrape the error, - * then the client may never see it. By calling fsync here, we ensure - * that writeback happens before the entry is freed, and that any - * errors reported result in the write verifier changing. - */ - nfsd_file_fsync(nf); - if (nf->nf_mark) nfsd_file_mark_put(nf->nf_mark); if (nf->nf_file) { - get_file(nf->nf_file); - filp_close(nf->nf_file, NULL); - fput(nf->nf_file); + nfsd_file_check_write_error(nf); + nfsd_filp_close(nf->nf_file); } /* @@ -423,26 +306,35 @@ nfsd_file_check_writeback(struct nfsd_file *nf) struct file *file = nf->nf_file; struct address_space *mapping; - if (!file || !(file->f_mode & FMODE_WRITE)) + /* File not open for write? */ + if (!(file->f_mode & FMODE_WRITE)) + return false; + + /* + * Some filesystems (e.g. NFS) flush all dirty data on close. + * On others, there is no need to wait for writeback. + */ + if (!(file_inode(file)->i_sb->s_export_op->flags & EXPORT_OP_FLUSH_ON_CLOSE)) return false; + mapping = file->f_mapping; return mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) || mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK); } -static bool nfsd_file_lru_add(struct nfsd_file *nf) +static void nfsd_file_lru_add(struct nfsd_file *nf) { - set_bit(NFSD_FILE_REFERENCED, &nf->nf_flags); - if (list_lru_add(&nfsd_file_lru, &nf->nf_lru)) { + refcount_inc(&nf->nf_ref); + if (list_lru_add_obj(&nfsd_file_lru, &nf->nf_lru)) trace_nfsd_file_lru_add(nf); - return true; - } - return false; + else + WARN_ON(1); + nfsd_file_schedule_laundrette(); } static bool nfsd_file_lru_remove(struct nfsd_file *nf) { - if (list_lru_del(&nfsd_file_lru, &nf->nf_lru)) { + if (list_lru_del_obj(&nfsd_file_lru, &nf->nf_lru)) { trace_nfsd_file_lru_del(nf); return true; } @@ -452,7 +344,7 @@ static bool nfsd_file_lru_remove(struct nfsd_file *nf) struct nfsd_file * nfsd_file_get(struct nfsd_file *nf) { - if (likely(refcount_inc_not_zero(&nf->nf_ref))) + if (nf && refcount_inc_not_zero(&nf->nf_ref)) return nf; return NULL; } @@ -473,89 +365,118 @@ nfsd_file_put(struct nfsd_file *nf) if (test_bit(NFSD_FILE_GC, &nf->nf_flags) && test_bit(NFSD_FILE_HASHED, &nf->nf_flags)) { - /* - * If this is the last reference (nf_ref == 1), then try to - * transfer it to the LRU. - */ - if (refcount_dec_not_one(&nf->nf_ref)) - return; - - /* Try to add it to the LRU. If that fails, decrement. */ - if (nfsd_file_lru_add(nf)) { - /* If it's still hashed, we're done */ - if (test_bit(NFSD_FILE_HASHED, &nf->nf_flags)) { - nfsd_file_schedule_laundrette(); - return; - } - - /* - * We're racing with unhashing, so try to remove it from - * the LRU. If removal fails, then someone else already - * has our reference. - */ - if (!nfsd_file_lru_remove(nf)) - return; - } + set_bit(NFSD_FILE_REFERENCED, &nf->nf_flags); + set_bit(NFSD_FILE_RECENT, &nf->nf_flags); } + if (refcount_dec_and_test(&nf->nf_ref)) nfsd_file_free(nf); } -static void -nfsd_file_dispose_list(struct list_head *dispose) +/** + * nfsd_file_put_local - put nfsd_file reference and arm nfsd_net_put in caller + * @pnf: nfsd_file of which to put the reference + * + * First save the associated net to return to caller, then put + * the reference of the nfsd_file. + */ +struct net * +nfsd_file_put_local(struct nfsd_file __rcu **pnf) { struct nfsd_file *nf; + struct net *net = NULL; - while (!list_empty(dispose)) { - nf = list_first_entry(dispose, struct nfsd_file, nf_lru); - list_del_init(&nf->nf_lru); - nfsd_file_free(nf); + nf = unrcu_pointer(xchg(pnf, NULL)); + if (nf) { + net = nf->nf_net; + nfsd_file_put(nf); } + return net; } -static void -nfsd_file_list_remove_disposal(struct list_head *dst, - struct nfsd_fcache_disposal *l) +/** + * nfsd_file_file - get the backing file of an nfsd_file + * @nf: nfsd_file of which to access the backing file. + * + * Return backing file for @nf. + */ +struct file * +nfsd_file_file(struct nfsd_file *nf) { - spin_lock(&l->lock); - list_splice_init(&l->freeme, dst); - spin_unlock(&l->lock); + return nf->nf_file; } static void -nfsd_file_list_add_disposal(struct list_head *files, struct net *net) +nfsd_file_dispose_list(struct list_head *dispose) { - struct nfsd_net *nn = net_generic(net, nfsd_net_id); - struct nfsd_fcache_disposal *l = nn->fcache_disposal; + struct nfsd_file *nf; - spin_lock(&l->lock); - list_splice_tail_init(files, &l->freeme); - spin_unlock(&l->lock); - queue_work(nfsd_filecache_wq, &l->work); + while (!list_empty(dispose)) { + nf = list_first_entry(dispose, struct nfsd_file, nf_gc); + list_del_init(&nf->nf_gc); + nfsd_file_free(nf); + } } +/** + * nfsd_file_dispose_list_delayed - move list of dead files to net's freeme list + * @dispose: list of nfsd_files to be disposed + * + * Transfers each file to the "freeme" list for its nfsd_net, to eventually + * be disposed of by the per-net garbage collector. + */ static void -nfsd_file_list_add_pernet(struct list_head *dst, struct list_head *src, - struct net *net) +nfsd_file_dispose_list_delayed(struct list_head *dispose) { - struct nfsd_file *nf, *tmp; + while(!list_empty(dispose)) { + struct nfsd_file *nf = list_first_entry(dispose, + struct nfsd_file, nf_gc); + struct nfsd_net *nn = net_generic(nf->nf_net, nfsd_net_id); + struct nfsd_fcache_disposal *l = nn->fcache_disposal; + struct svc_serv *serv; + + spin_lock(&l->lock); + list_move_tail(&nf->nf_gc, &l->freeme); + spin_unlock(&l->lock); - list_for_each_entry_safe(nf, tmp, src, nf_lru) { - if (nf->nf_net == net) - list_move_tail(&nf->nf_lru, dst); + /* + * The filecache laundrette is shut down after the + * nn->nfsd_serv pointer is cleared, but before the + * svc_serv is freed. + */ + serv = nn->nfsd_serv; + if (serv) + svc_wake_up(serv); } } -static void -nfsd_file_dispose_list_delayed(struct list_head *dispose) +/** + * nfsd_file_net_dispose - deal with nfsd_files waiting to be disposed. + * @nn: nfsd_net in which to find files to be disposed. + * + * When files held open for nfsv3 are removed from the filecache, whether + * due to memory pressure or garbage collection, they are queued to + * a per-net-ns queue. This function completes the disposal, either + * directly or by waking another nfsd thread to help with the work. + */ +void nfsd_file_net_dispose(struct nfsd_net *nn) { - LIST_HEAD(list); - struct nfsd_file *nf; + struct nfsd_fcache_disposal *l = nn->fcache_disposal; - while(!list_empty(dispose)) { - nf = list_first_entry(dispose, struct nfsd_file, nf_lru); - nfsd_file_list_add_pernet(&list, dispose, nf->nf_net); - nfsd_file_list_add_disposal(&list, nf->nf_net); + if (!list_empty(&l->freeme)) { + LIST_HEAD(dispose); + int i; + + spin_lock(&l->lock); + for (i = 0; i < 8 && !list_empty(&l->freeme); i++) + list_move(l->freeme.next, &dispose); + spin_unlock(&l->lock); + if (!list_empty(&l->freeme)) + /* Wake up another thread to share the work + * *before* doing any actual disposing. + */ + svc_wake_up(nn->nfsd_serv); + nfsd_file_dispose_list(&dispose); } } @@ -563,7 +484,6 @@ nfsd_file_dispose_list_delayed(struct list_head *dispose) * nfsd_file_lru_cb - Examine an entry on the LRU list * @item: LRU entry to examine * @lru: controlling LRU - * @lock: LRU list lock (unused) * @arg: dispose list * * Return values: @@ -573,9 +493,7 @@ nfsd_file_dispose_list_delayed(struct list_head *dispose) */ static enum lru_status nfsd_file_lru_cb(struct list_head *item, struct list_lru_one *lru, - spinlock_t *lock, void *arg) - __releases(lock) - __acquires(lock) + void *arg) { struct list_head *head = arg; struct nfsd_file *nf = list_entry(item, struct nfsd_file, nf_lru); @@ -599,31 +517,71 @@ nfsd_file_lru_cb(struct list_head *item, struct list_lru_one *lru, } /* - * Put the reference held on behalf of the LRU. If it wasn't the last - * one, then just remove it from the LRU and ignore it. + * Put the reference held on behalf of the LRU if it is the last + * reference, else rotate. */ - if (!refcount_dec_and_test(&nf->nf_ref)) { + if (!refcount_dec_if_one(&nf->nf_ref)) { trace_nfsd_file_gc_in_use(nf); - list_lru_isolate(lru, &nf->nf_lru); - return LRU_REMOVED; + return LRU_ROTATE; } /* Refcount went to zero. Unhash it and queue it to the dispose list */ nfsd_file_unhash(nf); - list_lru_isolate_move(lru, &nf->nf_lru, head); + list_lru_isolate(lru, &nf->nf_lru); + list_add(&nf->nf_gc, head); this_cpu_inc(nfsd_file_evictions); trace_nfsd_file_gc_disposed(nf); return LRU_REMOVED; } +static enum lru_status +nfsd_file_gc_cb(struct list_head *item, struct list_lru_one *lru, + void *arg) +{ + struct nfsd_file *nf = list_entry(item, struct nfsd_file, nf_lru); + + if (test_and_clear_bit(NFSD_FILE_RECENT, &nf->nf_flags)) { + /* + * "REFERENCED" really means "should be at the end of the + * LRU. As we are putting it there we can clear the flag. + */ + clear_bit(NFSD_FILE_REFERENCED, &nf->nf_flags); + trace_nfsd_file_gc_aged(nf); + return LRU_ROTATE; + } + return nfsd_file_lru_cb(item, lru, arg); +} + +/* If the shrinker runs between calls to list_lru_walk_node() in + * nfsd_file_gc(), the "remaining" count will be wrong. This could + * result in premature freeing of some files. This may not matter much + * but is easy to fix with this spinlock which temporarily disables + * the shrinker. + */ +static DEFINE_SPINLOCK(nfsd_gc_lock); static void nfsd_file_gc(void) { + unsigned long ret = 0; LIST_HEAD(dispose); - unsigned long ret; + int nid; + + spin_lock(&nfsd_gc_lock); + for_each_node_state(nid, N_NORMAL_MEMORY) { + unsigned long remaining = list_lru_count_node(&nfsd_file_lru, nid); + + while (remaining > 0) { + unsigned long nr = min(remaining, NFSD_FILE_GC_BATCH); - ret = list_lru_walk(&nfsd_file_lru, nfsd_file_lru_cb, - &dispose, list_lru_count(&nfsd_file_lru)); + remaining -= nr; + ret += list_lru_walk_node(&nfsd_file_lru, nid, nfsd_file_gc_cb, + &dispose, &nr); + if (nr) + /* walk aborted early */ + remaining = 0; + } + } + spin_unlock(&nfsd_gc_lock); trace_nfsd_file_gc_removed(ret, list_lru_count(&nfsd_file_lru)); nfsd_file_dispose_list_delayed(&dispose); } @@ -631,9 +589,9 @@ nfsd_file_gc(void) static void nfsd_file_gc_worker(struct work_struct *work) { - nfsd_file_gc(); if (list_lru_count(&nfsd_file_lru)) - nfsd_file_schedule_laundrette(); + nfsd_file_gc(); + nfsd_file_schedule_laundrette(); } static unsigned long @@ -648,18 +606,18 @@ nfsd_file_lru_scan(struct shrinker *s, struct shrink_control *sc) LIST_HEAD(dispose); unsigned long ret; + if (!spin_trylock(&nfsd_gc_lock)) + return SHRINK_STOP; + ret = list_lru_shrink_walk(&nfsd_file_lru, sc, nfsd_file_lru_cb, &dispose); + spin_unlock(&nfsd_gc_lock); trace_nfsd_file_shrinker_removed(ret, list_lru_count(&nfsd_file_lru)); nfsd_file_dispose_list_delayed(&dispose); return ret; } -static struct shrinker nfsd_file_shrinker = { - .scan_objects = nfsd_file_lru_scan, - .count_objects = nfsd_file_lru_count, - .seeks = 1, -}; +static struct shrinker *nfsd_file_shrinker; /** * nfsd_file_cond_queue - conditionally unhash and queue a nfsd_file @@ -689,7 +647,7 @@ nfsd_file_cond_queue(struct nfsd_file *nf, struct list_head *dispose) /* If refcount goes to 0, then put on the dispose list */ if (refcount_sub_and_test(decrement, &nf->nf_ref)) { - list_add(&nf->nf_lru, dispose); + list_add(&nf->nf_gc, dispose); trace_nfsd_file_closing(nf); } } @@ -699,8 +657,8 @@ nfsd_file_cond_queue(struct nfsd_file *nf, struct list_head *dispose) * @inode: inode on which to close out nfsd_files * @dispose: list on which to gather nfsd_files to close out * - * An nfsd_file represents a struct file being held open on behalf of nfsd. An - * open file however can block other activity (such as leases), or cause + * An nfsd_file represents a struct file being held open on behalf of nfsd. + * An open file however can block other activity (such as leases), or cause * undesirable behavior (e.g. spurious silly-renames when reexporting NFS). * * This function is intended to find open nfsd_files when this sort of @@ -713,20 +671,17 @@ nfsd_file_cond_queue(struct nfsd_file *nf, struct list_head *dispose) static void nfsd_file_queue_for_close(struct inode *inode, struct list_head *dispose) { - struct nfsd_file_lookup_key key = { - .type = NFSD_FILE_KEY_INODE, - .inode = inode, - }; + struct rhlist_head *tmp, *list; struct nfsd_file *nf; rcu_read_lock(); - do { - nf = rhashtable_lookup(&nfsd_file_rhash_tbl, &key, - nfsd_file_rhash_params); - if (!nf) - break; + list = rhltable_lookup(&nfsd_file_rhltable, &inode, + nfsd_file_rhash_params); + rhl_for_each_entry_rcu(nf, tmp, list, nf_rlist) { + if (!test_bit(NFSD_FILE_GC, &nf->nf_flags)) + continue; nfsd_file_cond_queue(nf, dispose); - } while (1); + } rcu_read_unlock(); } @@ -761,47 +716,23 @@ nfsd_file_close_inode(struct inode *inode) void nfsd_file_close_inode_sync(struct inode *inode) { - struct nfsd_file *nf; LIST_HEAD(dispose); trace_nfsd_file_close(inode); nfsd_file_queue_for_close(inode, &dispose); - while (!list_empty(&dispose)) { - nf = list_first_entry(&dispose, struct nfsd_file, nf_lru); - list_del_init(&nf->nf_lru); - nfsd_file_free(nf); - } - flush_delayed_fput(); -} - -/** - * nfsd_file_delayed_close - close unused nfsd_files - * @work: dummy - * - * Walk the LRU list and destroy any entries that have not been used since - * the last scan. - */ -static void -nfsd_file_delayed_close(struct work_struct *work) -{ - LIST_HEAD(head); - struct nfsd_fcache_disposal *l = container_of(work, - struct nfsd_fcache_disposal, work); - - nfsd_file_list_remove_disposal(&head, l); - nfsd_file_dispose_list(&head); + nfsd_file_dispose_list(&dispose); } static int nfsd_file_lease_notifier_call(struct notifier_block *nb, unsigned long arg, void *data) { - struct file_lock *fl = data; + struct file_lease *fl = data; /* Only close files for F_SETLEASE leases */ - if (fl->fl_flags & FL_LEASE) - nfsd_file_close_inode(file_inode(fl->fl_file)); + if (fl->c.flc_flags & FL_LEASE) + nfsd_file_close_inode(file_inode(fl->c.flc_file)); return 0; } @@ -850,42 +781,42 @@ nfsd_file_cache_init(void) if (test_and_set_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags) == 1) return 0; - ret = rhashtable_init(&nfsd_file_rhash_tbl, &nfsd_file_rhash_params); + ret = rhltable_init(&nfsd_file_rhltable, &nfsd_file_rhash_params); if (ret) - return ret; - - ret = -ENOMEM; - nfsd_filecache_wq = alloc_workqueue("nfsd_filecache", 0, 0); - if (!nfsd_filecache_wq) goto out; - nfsd_file_slab = kmem_cache_create("nfsd_file", - sizeof(struct nfsd_file), 0, 0, NULL); + ret = -ENOMEM; + nfsd_file_slab = KMEM_CACHE(nfsd_file, 0); if (!nfsd_file_slab) { pr_err("nfsd: unable to create nfsd_file_slab\n"); goto out_err; } - nfsd_file_mark_slab = kmem_cache_create("nfsd_file_mark", - sizeof(struct nfsd_file_mark), 0, 0, NULL); + nfsd_file_mark_slab = KMEM_CACHE(nfsd_file_mark, 0); if (!nfsd_file_mark_slab) { pr_err("nfsd: unable to create nfsd_file_mark_slab\n"); goto out_err; } - ret = list_lru_init(&nfsd_file_lru); if (ret) { pr_err("nfsd: failed to init nfsd_file_lru: %d\n", ret); goto out_err; } - ret = register_shrinker(&nfsd_file_shrinker, "nfsd-filecache"); - if (ret) { - pr_err("nfsd: failed to register nfsd_file_shrinker: %d\n", ret); + nfsd_file_shrinker = shrinker_alloc(0, "nfsd-filecache"); + if (!nfsd_file_shrinker) { + ret = -ENOMEM; + pr_err("nfsd: failed to allocate nfsd_file_shrinker\n"); goto out_lru; } + nfsd_file_shrinker->count_objects = nfsd_file_lru_count; + nfsd_file_shrinker->scan_objects = nfsd_file_lru_scan; + nfsd_file_shrinker->seeks = 1; + + shrinker_register(nfsd_file_shrinker); + ret = lease_register_notifier(&nfsd_file_lease_notifier); if (ret) { pr_err("nfsd: unable to register lease notifier: %d\n", ret); @@ -893,7 +824,7 @@ nfsd_file_cache_init(void) } nfsd_file_fsnotify_group = fsnotify_alloc_group(&nfsd_file_fsnotify_ops, - FSNOTIFY_GROUP_NOFS); + 0); if (IS_ERR(nfsd_file_fsnotify_group)) { pr_err("nfsd: unable to create fsnotify group: %ld\n", PTR_ERR(nfsd_file_fsnotify_group)); @@ -904,11 +835,13 @@ nfsd_file_cache_init(void) INIT_DELAYED_WORK(&nfsd_filecache_laundrette, nfsd_file_gc_worker); out: + if (ret) + clear_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags); return ret; out_notifier: lease_unregister_notifier(&nfsd_file_lease_notifier); out_shrinker: - unregister_shrinker(&nfsd_file_shrinker); + shrinker_free(nfsd_file_shrinker); out_lru: list_lru_destroy(&nfsd_file_lru); out_err: @@ -916,9 +849,7 @@ out_err: nfsd_file_slab = NULL; kmem_cache_destroy(nfsd_file_mark_slab); nfsd_file_mark_slab = NULL; - destroy_workqueue(nfsd_filecache_wq); - nfsd_filecache_wq = NULL; - rhashtable_destroy(&nfsd_file_rhash_tbl); + rhltable_destroy(&nfsd_file_rhltable); goto out; } @@ -927,7 +858,8 @@ out_err: * @net: net-namespace to shut down the cache (may be NULL) * * Walk the nfsd_file cache and close out any that match @net. If @net is NULL, - * then close out everything. Called when an nfsd instance is being shut down. + * then close out everything. Called when an nfsd instance is being shut down, + * and when the exports table is flushed. */ static void __nfsd_file_cache_purge(struct net *net) @@ -936,7 +868,15 @@ __nfsd_file_cache_purge(struct net *net) struct nfsd_file *nf; LIST_HEAD(dispose); - rhashtable_walk_enter(&nfsd_file_rhash_tbl, &iter); +#if IS_ENABLED(CONFIG_NFS_LOCALIO) + if (net) { + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + nfs_localio_invalidate_clients(&nn->local_clients, + &nn->local_clients_lock); + } +#endif + + rhltable_walk_enter(&nfsd_file_rhltable, &iter); do { rhashtable_walk_start(&iter); @@ -962,7 +902,6 @@ nfsd_alloc_fcache_disposal(void) l = kmalloc(sizeof(*l), GFP_KERNEL); if (!l) return NULL; - INIT_WORK(&l->work, nfsd_file_delayed_close); spin_lock_init(&l->lock); INIT_LIST_HEAD(&l->freeme); return l; @@ -971,7 +910,6 @@ nfsd_alloc_fcache_disposal(void) static void nfsd_free_fcache_disposal(struct nfsd_fcache_disposal *l) { - cancel_work_sync(&l->work); nfsd_file_dispose_list(&l->freeme); kfree(l); } @@ -1024,7 +962,7 @@ nfsd_file_cache_shutdown(void) return; lease_unregister_notifier(&nfsd_file_lease_notifier); - unregister_shrinker(&nfsd_file_shrinker); + shrinker_free(nfsd_file_shrinker); /* * make sure all callers of nfsd_file_lru_cb are done before * calling nfsd_file_cache_purge @@ -1040,19 +978,47 @@ nfsd_file_cache_shutdown(void) fsnotify_wait_marks_destroyed(); kmem_cache_destroy(nfsd_file_mark_slab); nfsd_file_mark_slab = NULL; - destroy_workqueue(nfsd_filecache_wq); - nfsd_filecache_wq = NULL; - rhashtable_destroy(&nfsd_file_rhash_tbl); + rhltable_destroy(&nfsd_file_rhltable); for_each_possible_cpu(i) { per_cpu(nfsd_file_cache_hits, i) = 0; per_cpu(nfsd_file_acquisitions, i) = 0; + per_cpu(nfsd_file_allocations, i) = 0; per_cpu(nfsd_file_releases, i) = 0; per_cpu(nfsd_file_total_age, i) = 0; per_cpu(nfsd_file_evictions, i) = 0; } } +static struct nfsd_file * +nfsd_file_lookup_locked(const struct net *net, const struct cred *cred, + struct inode *inode, unsigned char need, + bool want_gc) +{ + struct rhlist_head *tmp, *list; + struct nfsd_file *nf; + + list = rhltable_lookup(&nfsd_file_rhltable, &inode, + nfsd_file_rhash_params); + rhl_for_each_entry_rcu(nf, tmp, list, nf_rlist) { + if (nf->nf_may != need) + continue; + if (nf->nf_net != net) + continue; + if (!nfsd_match_cred(nf->nf_cred, cred)) + continue; + if (test_bit(NFSD_FILE_GC, &nf->nf_flags) != want_gc) + continue; + if (test_bit(NFSD_FILE_HASHED, &nf->nf_flags) == 0) + continue; + + if (!nfsd_file_get(nf)) + continue; + return nf; + } + return NULL; +} + /** * nfsd_file_is_cached - are there any cached open files for this inode? * @inode: inode to check @@ -1067,123 +1033,176 @@ nfsd_file_cache_shutdown(void) bool nfsd_file_is_cached(struct inode *inode) { - struct nfsd_file_lookup_key key = { - .type = NFSD_FILE_KEY_INODE, - .inode = inode, - }; + struct rhlist_head *tmp, *list; + struct nfsd_file *nf; bool ret = false; - if (rhashtable_lookup_fast(&nfsd_file_rhash_tbl, &key, - nfsd_file_rhash_params) != NULL) - ret = true; + rcu_read_lock(); + list = rhltable_lookup(&nfsd_file_rhltable, &inode, + nfsd_file_rhash_params); + rhl_for_each_entry_rcu(nf, tmp, list, nf_rlist) + if (test_bit(NFSD_FILE_GC, &nf->nf_flags)) { + ret = true; + break; + } + rcu_read_unlock(); + trace_nfsd_file_is_cached(inode, (int)ret); return ret; } static __be32 -nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, +nfsd_file_get_dio_attrs(const struct svc_fh *fhp, struct nfsd_file *nf) +{ + struct inode *inode = file_inode(nf->nf_file); + struct kstat stat; + __be32 status; + + /* Currently only need to get DIO alignment info for regular files */ + if (!S_ISREG(inode->i_mode)) + return nfs_ok; + + status = fh_getattr(fhp, &stat); + if (status != nfs_ok) + return status; + + trace_nfsd_file_get_dio_attrs(inode, &stat); + + if (stat.result_mask & STATX_DIOALIGN) { + nf->nf_dio_mem_align = stat.dio_mem_align; + nf->nf_dio_offset_align = stat.dio_offset_align; + } + if (stat.result_mask & STATX_DIO_READ_ALIGN) + nf->nf_dio_read_offset_align = stat.dio_read_offset_align; + else + nf->nf_dio_read_offset_align = nf->nf_dio_offset_align; + + return nfs_ok; +} + +static __be32 +nfsd_file_do_acquire(struct svc_rqst *rqstp, struct net *net, + struct svc_cred *cred, + struct auth_domain *client, + struct svc_fh *fhp, unsigned int may_flags, struct file *file, - struct nfsd_file **pnf, bool want_gc) + umode_t type, bool want_gc, struct nfsd_file **pnf) { - struct nfsd_file_lookup_key key = { - .type = NFSD_FILE_KEY_FULL, - .need = may_flags & NFSD_FILE_MAY_MASK, - .net = SVC_NET(rqstp), - .gc = want_gc, - }; + unsigned char need = may_flags & NFSD_FILE_MAY_MASK; + struct nfsd_file *new, *nf; + bool stale_retry = true; bool open_retry = true; - struct nfsd_file *nf; + struct inode *inode; __be32 status; int ret; - status = fh_verify(rqstp, fhp, S_IFREG, - may_flags|NFSD_MAY_OWNER_OVERRIDE); +retry: + if (rqstp) + status = fh_verify(rqstp, fhp, type, + may_flags|NFSD_MAY_OWNER_OVERRIDE); + else + status = fh_verify_local(net, cred, client, fhp, type, + may_flags|NFSD_MAY_OWNER_OVERRIDE); + if (status != nfs_ok) return status; - key.inode = d_inode(fhp->fh_dentry); - key.cred = get_current_cred(); + inode = d_inode(fhp->fh_dentry); -retry: rcu_read_lock(); - nf = rhashtable_lookup(&nfsd_file_rhash_tbl, &key, - nfsd_file_rhash_params); - if (nf) - nf = nfsd_file_get(nf); + nf = nfsd_file_lookup_locked(net, current_cred(), inode, need, want_gc); rcu_read_unlock(); - if (nf) { - if (nfsd_file_lru_remove(nf)) - WARN_ON_ONCE(refcount_dec_and_test(&nf->nf_ref)); + if (nf) goto wait_for_construction; - } - nf = nfsd_file_alloc(&key, may_flags); - if (!nf) { + new = nfsd_file_alloc(net, inode, need, want_gc); + if (!new) { status = nfserr_jukebox; - goto out_status; + goto out; } - ret = rhashtable_lookup_insert_key(&nfsd_file_rhash_tbl, - &key, &nf->nf_rhash, - nfsd_file_rhash_params); + rcu_read_lock(); + spin_lock(&inode->i_lock); + nf = nfsd_file_lookup_locked(net, current_cred(), inode, need, want_gc); + if (unlikely(nf)) { + spin_unlock(&inode->i_lock); + rcu_read_unlock(); + nfsd_file_free(new); + goto wait_for_construction; + } + nf = new; + ret = rhltable_insert(&nfsd_file_rhltable, &nf->nf_rlist, + nfsd_file_rhash_params); + spin_unlock(&inode->i_lock); + rcu_read_unlock(); if (likely(ret == 0)) goto open_file; - nfsd_file_slab_free(&nf->nf_rcu); - nf = NULL; - if (ret == -EEXIST) - goto retry; - trace_nfsd_file_insert_err(rqstp, key.inode, may_flags, ret); + trace_nfsd_file_insert_err(rqstp, inode, may_flags, ret); status = nfserr_jukebox; - goto out_status; + goto construction_err; wait_for_construction: wait_on_bit(&nf->nf_flags, NFSD_FILE_PENDING, TASK_UNINTERRUPTIBLE); /* Did construction of this file fail? */ if (!test_bit(NFSD_FILE_HASHED, &nf->nf_flags)) { - trace_nfsd_file_cons_err(rqstp, key.inode, may_flags, nf); + trace_nfsd_file_cons_err(rqstp, inode, may_flags, nf); if (!open_retry) { status = nfserr_jukebox; - goto out; + goto construction_err; } + nfsd_file_put(nf); open_retry = false; - if (refcount_dec_and_test(&nf->nf_ref)) - nfsd_file_free(nf); + fh_put(fhp); goto retry; } - this_cpu_inc(nfsd_file_cache_hits); status = nfserrno(nfsd_open_break_lease(file_inode(nf->nf_file), may_flags)); + if (status != nfs_ok) { + nfsd_file_put(nf); + nf = NULL; + } + out: if (status == nfs_ok) { this_cpu_inc(nfsd_file_acquisitions); + nfsd_file_check_write_error(nf); *pnf = nf; - } else { - if (refcount_dec_and_test(&nf->nf_ref)) - nfsd_file_free(nf); - nf = NULL; } - -out_status: - put_cred(key.cred); - trace_nfsd_file_acquire(rqstp, key.inode, may_flags, nf, status); + trace_nfsd_file_acquire(rqstp, inode, may_flags, nf, status); return status; open_file: trace_nfsd_file_alloc(nf); - nf->nf_mark = nfsd_file_mark_find_or_create(nf, key.inode); - if (nf->nf_mark) { + + if (type == S_IFREG) + nf->nf_mark = nfsd_file_mark_find_or_create(inode); + + if (type != S_IFREG || nf->nf_mark) { if (file) { get_file(file); nf->nf_file = file; status = nfs_ok; trace_nfsd_file_opened(nf, status); } else { - status = nfsd_open_verified(rqstp, fhp, may_flags, - &nf->nf_file); + ret = nfsd_open_verified(fhp, type, may_flags, &nf->nf_file); + if (ret == -EOPENSTALE && stale_retry) { + stale_retry = false; + nfsd_file_unhash(nf); + clear_and_wake_up_bit(NFSD_FILE_PENDING, + &nf->nf_flags); + if (refcount_dec_and_test(&nf->nf_ref)) + nfsd_file_free(nf); + nf = NULL; + fh_put(fhp); + goto retry; + } + status = nfserrno(ret); trace_nfsd_file_open(nf, status); + if (status == nfs_ok) + status = nfsd_file_get_dio_attrs(fhp, nf); } } else status = nfserr_jukebox; @@ -1191,13 +1210,19 @@ open_file: * If construction failed, or we raced with a call to unlink() * then unhash. */ - if (status == nfs_ok && key.inode->i_nlink == 0) - status = nfserr_jukebox; - if (status != nfs_ok) + if (status != nfs_ok || inode->i_nlink == 0) nfsd_file_unhash(nf); - clear_bit_unlock(NFSD_FILE_PENDING, &nf->nf_flags); - smp_mb__after_atomic(); - wake_up_bit(&nf->nf_flags, NFSD_FILE_PENDING); + else if (want_gc) + nfsd_file_lru_add(nf); + + clear_and_wake_up_bit(NFSD_FILE_PENDING, &nf->nf_flags); + if (status == nfs_ok) + goto out; + +construction_err: + if (refcount_dec_and_test(&nf->nf_ref)) + nfsd_file_free(nf); + nf = NULL; goto out; } @@ -1213,14 +1238,18 @@ open_file: * seconds after the final nfsd_file_put() in case the caller * wants to re-use it. * - * Returns nfs_ok and sets @pnf on success; otherwise an nfsstat in - * network byte order is returned. + * Return values: + * %nfs_ok - @pnf points to an nfsd_file with its reference + * count boosted. + * + * On error, an nfsstat value in network byte order is returned. */ __be32 nfsd_file_acquire_gc(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned int may_flags, struct nfsd_file **pnf) { - return nfsd_file_do_acquire(rqstp, fhp, may_flags, NULL, pnf, true); + return nfsd_file_do_acquire(rqstp, SVC_NET(rqstp), NULL, NULL, + fhp, may_flags, NULL, S_IFREG, true, pnf); } /** @@ -1234,14 +1263,64 @@ nfsd_file_acquire_gc(struct svc_rqst *rqstp, struct svc_fh *fhp, * but not garbage-collected. The object is unhashed after the * final nfsd_file_put(). * - * Returns nfs_ok and sets @pnf on success; otherwise an nfsstat in - * network byte order is returned. + * Return values: + * %nfs_ok - @pnf points to an nfsd_file with its reference + * count boosted. + * + * On error, an nfsstat value in network byte order is returned. */ __be32 nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned int may_flags, struct nfsd_file **pnf) { - return nfsd_file_do_acquire(rqstp, fhp, may_flags, NULL, pnf, false); + return nfsd_file_do_acquire(rqstp, SVC_NET(rqstp), NULL, NULL, + fhp, may_flags, NULL, S_IFREG, false, pnf); +} + +/** + * nfsd_file_acquire_local - Get a struct nfsd_file with an open file for localio + * @net: The network namespace in which to perform a lookup + * @cred: the user credential with which to validate access + * @client: the auth_domain for LOCALIO lookup + * @fhp: the NFS filehandle of the file to be opened + * @may_flags: NFSD_MAY_ settings for the file + * @pnf: OUT: new or found "struct nfsd_file" object + * + * This file lookup interface provide access to a file given the + * filehandle and credential. No connection-based authorisation + * is performed and in that way it is quite different to other + * file access mediated by nfsd. It allows a kernel module such as the NFS + * client to reach across network and filesystem namespaces to access + * a file. The security implications of this should be carefully + * considered before use. + * + * The nfsd_file_object returned by this API is reference-counted + * but not garbage-collected. The object is unhashed after the + * final nfsd_file_put(). + * + * Return values: + * %nfs_ok - @pnf points to an nfsd_file with its reference + * count boosted. + * + * On error, an nfsstat value in network byte order is returned. + */ +__be32 +nfsd_file_acquire_local(struct net *net, struct svc_cred *cred, + struct auth_domain *client, struct svc_fh *fhp, + unsigned int may_flags, struct nfsd_file **pnf) +{ + /* + * Save creds before calling nfsd_file_do_acquire() (which calls + * nfsd_setuser). Important because caller (LOCALIO) is from + * client context. + */ + const struct cred *save_cred = get_current_cred(); + __be32 beres; + + beres = nfsd_file_do_acquire(NULL, net, cred, client, fhp, may_flags, + NULL, S_IFREG, false, pnf); + put_cred(revert_creds(save_cred)); + return beres; } /** @@ -1256,15 +1335,45 @@ nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, * and @file is non-NULL, use it to instantiate a new nfsd_file instead of * opening a new one. * - * Returns nfs_ok and sets @pnf on success; otherwise an nfsstat in - * network byte order is returned. + * Return values: + * %nfs_ok - @pnf points to an nfsd_file with its reference + * count boosted. + * + * On error, an nfsstat value in network byte order is returned. */ __be32 nfsd_file_acquire_opened(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned int may_flags, struct file *file, struct nfsd_file **pnf) { - return nfsd_file_do_acquire(rqstp, fhp, may_flags, file, pnf, false); + return nfsd_file_do_acquire(rqstp, SVC_NET(rqstp), NULL, NULL, + fhp, may_flags, file, S_IFREG, false, pnf); +} + +/** + * nfsd_file_acquire_dir - Get a struct nfsd_file with an open directory + * @rqstp: the RPC transaction being executed + * @fhp: the NFS filehandle of the file to be opened + * @pnf: OUT: new or found "struct nfsd_file" object + * + * The nfsd_file_object returned by this API is reference-counted + * but not garbage-collected. The object is unhashed after the + * final nfsd_file_put(). This opens directories only, and only + * in O_RDONLY mode. + * + * Return values: + * %nfs_ok - @pnf points to an nfsd_file with its reference + * count boosted. + * + * On error, an nfsstat value in network byte order is returned. + */ +__be32 +nfsd_file_acquire_dir(struct svc_rqst *rqstp, struct svc_fh *fhp, + struct nfsd_file **pnf) +{ + return nfsd_file_do_acquire(rqstp, SVC_NET(rqstp), NULL, NULL, fhp, + NFSD_MAY_READ|NFSD_MAY_64BIT_COOKIE, + NULL, S_IFDIR, false, pnf); } /* @@ -1274,7 +1383,7 @@ nfsd_file_acquire_opened(struct svc_rqst *rqstp, struct svc_fh *fhp, */ int nfsd_file_cache_stats_show(struct seq_file *m, void *v) { - unsigned long releases = 0, evictions = 0; + unsigned long allocations = 0, releases = 0, evictions = 0; unsigned long hits = 0, acquisitions = 0; unsigned int i, count = 0, buckets = 0; unsigned long lru = 0, total_age = 0; @@ -1288,7 +1397,7 @@ int nfsd_file_cache_stats_show(struct seq_file *m, void *v) lru = list_lru_count(&nfsd_file_lru); rcu_read_lock(); - ht = &nfsd_file_rhash_tbl; + ht = &nfsd_file_rhltable.ht; count = atomic_read(&ht->nelems); tbl = rht_dereference_rcu(ht->tbl, ht); buckets = tbl->size; @@ -1299,16 +1408,18 @@ int nfsd_file_cache_stats_show(struct seq_file *m, void *v) for_each_possible_cpu(i) { hits += per_cpu(nfsd_file_cache_hits, i); acquisitions += per_cpu(nfsd_file_acquisitions, i); + allocations += per_cpu(nfsd_file_allocations, i); releases += per_cpu(nfsd_file_releases, i); total_age += per_cpu(nfsd_file_total_age, i); evictions += per_cpu(nfsd_file_evictions, i); } - seq_printf(m, "total entries: %u\n", count); + seq_printf(m, "total inodes: %u\n", count); seq_printf(m, "hash buckets: %u\n", buckets); seq_printf(m, "lru entries: %lu\n", lru); seq_printf(m, "cache hits: %lu\n", hits); seq_printf(m, "acquisitions: %lu\n", acquisitions); + seq_printf(m, "allocations: %lu\n", allocations); seq_printf(m, "releases: %lu\n", releases); seq_printf(m, "evictions: %lu\n", evictions); if (releases) diff --git a/fs/nfsd/filecache.h b/fs/nfsd/filecache.h index 41516a4263ea..b383dbc5b921 100644 --- a/fs/nfsd/filecache.h +++ b/fs/nfsd/filecache.h @@ -4,6 +4,12 @@ #include <linux/fsnotify_backend.h> /* + * Limit the time that the list_lru_one lock is held during + * an LRU scan. + */ +#define NFSD_FILE_GC_BATCH (16UL) + +/* * This is the fsnotify_mark container that nfsd attaches to the files that it * is holding open. Note that we have a separate refcount here aside from the * one in the fsnotify_mark. We only want a single fsnotify_mark attached to @@ -29,9 +35,8 @@ struct nfsd_file_mark { * never be dereferenced, only used for comparison. */ struct nfsd_file { - struct rhash_head nf_rhash; - struct list_head nf_lru; - struct rcu_head nf_rcu; + struct rhlist_head nf_rlist; + void *nf_inode; struct file *nf_file; const struct cred *nf_cred; struct net *nf_net; @@ -39,12 +44,20 @@ struct nfsd_file { #define NFSD_FILE_PENDING (1) #define NFSD_FILE_REFERENCED (2) #define NFSD_FILE_GC (3) +#define NFSD_FILE_RECENT (4) unsigned long nf_flags; - struct inode *nf_inode; /* don't deref */ refcount_t nf_ref; unsigned char nf_may; + struct nfsd_file_mark *nf_mark; + struct list_head nf_lru; + struct list_head nf_gc; + struct rcu_head nf_rcu; ktime_t nf_birthtime; + + u32 nf_dio_mem_align; + u32 nf_dio_offset_align; + u32 nf_dio_read_offset_align; }; int nfsd_file_cache_init(void); @@ -53,8 +66,11 @@ void nfsd_file_cache_shutdown(void); int nfsd_file_cache_start_net(struct net *net); void nfsd_file_cache_shutdown_net(struct net *net); void nfsd_file_put(struct nfsd_file *nf); +struct net *nfsd_file_put_local(struct nfsd_file __rcu **nf); struct nfsd_file *nfsd_file_get(struct nfsd_file *nf); +struct file *nfsd_file_file(struct nfsd_file *nf); void nfsd_file_close_inode_sync(struct inode *inode); +void nfsd_file_net_dispose(struct nfsd_net *nn); bool nfsd_file_is_cached(struct inode *inode); __be32 nfsd_file_acquire_gc(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned int may_flags, struct nfsd_file **nfp); @@ -63,5 +79,10 @@ __be32 nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, __be32 nfsd_file_acquire_opened(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned int may_flags, struct file *file, struct nfsd_file **nfp); +__be32 nfsd_file_acquire_local(struct net *net, struct svc_cred *cred, + struct auth_domain *client, struct svc_fh *fhp, + unsigned int may_flags, struct nfsd_file **pnf); +__be32 nfsd_file_acquire_dir(struct svc_rqst *rqstp, struct svc_fh *fhp, + struct nfsd_file **pnf); int nfsd_file_cache_stats_show(struct seq_file *m, void *v); #endif /* _FS_NFSD_FILECACHE_H */ diff --git a/fs/nfsd/flexfilelayout.c b/fs/nfsd/flexfilelayout.c index 3ca5304440ff..0f1a35400cd5 100644 --- a/fs/nfsd/flexfilelayout.c +++ b/fs/nfsd/flexfilelayout.c @@ -20,8 +20,8 @@ #define NFSDDBG_FACILITY NFSDDBG_PNFS static __be32 -nfsd4_ff_proc_layoutget(struct inode *inode, const struct svc_fh *fhp, - struct nfsd4_layoutget *args) +nfsd4_ff_proc_layoutget(struct svc_rqst *rqstp, struct inode *inode, + const struct svc_fh *fhp, struct nfsd4_layoutget *args) { struct nfsd4_layout_seg *seg = &args->lg_seg; u32 device_generation = 0; @@ -125,6 +125,13 @@ nfsd4_ff_proc_getdeviceinfo(struct super_block *sb, struct svc_rqst *rqstp, return 0; } +static __be32 +nfsd4_ff_proc_layoutcommit(struct inode *inode, struct svc_rqst *rqstp, + struct nfsd4_layoutcommit *lcp) +{ + return nfs_ok; +} + const struct nfsd4_layout_ops ff_layout_ops = { .notify_types = NOTIFY_DEVICEID4_DELETE | NOTIFY_DEVICEID4_CHANGE, @@ -133,4 +140,5 @@ const struct nfsd4_layout_ops ff_layout_ops = { .encode_getdeviceinfo = nfsd4_ff_encode_getdeviceinfo, .proc_layoutget = nfsd4_ff_proc_layoutget, .encode_layoutget = nfsd4_ff_encode_layoutget, + .proc_layoutcommit = nfsd4_ff_proc_layoutcommit, }; diff --git a/fs/nfsd/flexfilelayoutxdr.c b/fs/nfsd/flexfilelayoutxdr.c index e81d2a5cf381..f9f7e38cba13 100644 --- a/fs/nfsd/flexfilelayoutxdr.c +++ b/fs/nfsd/flexfilelayoutxdr.c @@ -17,9 +17,9 @@ struct ff_idmap { __be32 nfsd4_ff_encode_layoutget(struct xdr_stream *xdr, - struct nfsd4_layoutget *lgp) + const struct nfsd4_layoutget *lgp) { - struct pnfs_ff_layout *fl = lgp->lg_content; + const struct pnfs_ff_layout *fl = lgp->lg_content; int len, mirror_len, ds_len, fh_len; __be32 *p; @@ -54,8 +54,7 @@ nfsd4_ff_encode_layoutget(struct xdr_stream *xdr, *p++ = cpu_to_be32(1); /* single mirror */ *p++ = cpu_to_be32(1); /* single data server */ - p = xdr_encode_opaque_fixed(p, &fl->deviceid, - sizeof(struct nfsd4_deviceid)); + p = svcxdr_encode_deviceid4(p, &fl->deviceid); *p++ = cpu_to_be32(1); /* efficiency */ @@ -77,7 +76,7 @@ nfsd4_ff_encode_layoutget(struct xdr_stream *xdr, __be32 nfsd4_ff_encode_getdeviceinfo(struct xdr_stream *xdr, - struct nfsd4_getdeviceinfo *gdp) + const struct nfsd4_getdeviceinfo *gdp) { struct pnfs_ff_device_addr *da = gdp->gd_device; int len; @@ -85,6 +84,15 @@ nfsd4_ff_encode_getdeviceinfo(struct xdr_stream *xdr, int addr_len; __be32 *p; + /* + * See paragraph 5 of RFC 8881 S18.40.3. + */ + if (!gdp->gd_maxcount) { + if (xdr_stream_encode_u32(xdr, 0) != XDR_UNIT) + return nfserr_resource; + return nfs_ok; + } + /* len + padding for two strings */ addr_len = 16 + da->netaddr.netid_len + da->netaddr.addr_len; ver_len = 20; diff --git a/fs/nfsd/flexfilelayoutxdr.h b/fs/nfsd/flexfilelayoutxdr.h index 8e195aeca023..6d5a1066a903 100644 --- a/fs/nfsd/flexfilelayoutxdr.h +++ b/fs/nfsd/flexfilelayoutxdr.h @@ -43,8 +43,8 @@ struct pnfs_ff_layout { }; __be32 nfsd4_ff_encode_getdeviceinfo(struct xdr_stream *xdr, - struct nfsd4_getdeviceinfo *gdp); + const struct nfsd4_getdeviceinfo *gdp); __be32 nfsd4_ff_encode_layoutget(struct xdr_stream *xdr, - struct nfsd4_layoutget *lgp); + const struct nfsd4_layoutget *lgp); #endif /* _NFSD_FLEXFILELAYOUTXDR_H */ diff --git a/fs/nfsd/localio.c b/fs/nfsd/localio.c new file mode 100644 index 000000000000..be710d809a3b --- /dev/null +++ b/fs/nfsd/localio.c @@ -0,0 +1,217 @@ +// 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> + * Copyright (C) 2024 NeilBrown <neilb@suse.de> + */ + +#include <linux/exportfs.h> +#include <linux/sunrpc/svcauth.h> +#include <linux/sunrpc/clnt.h> +#include <linux/nfs.h> +#include <linux/nfs_common.h> +#include <linux/nfslocalio.h> +#include <linux/nfs_fs.h> +#include <linux/nfs_xdr.h> +#include <linux/string.h> + +#include "nfsd.h" +#include "vfs.h" +#include "netns.h" +#include "filecache.h" +#include "cache.h" + +/** + * nfsd_open_local_fh - lookup a local filehandle @nfs_fh and map to nfsd_file + * + * @net: 'struct net' to get the proper nfsd_net required for LOCALIO access + * @dom: 'struct auth_domain' required for LOCALIO access + * @rpc_clnt: rpc_clnt that the client established + * @cred: cred that the client established + * @nfs_fh: filehandle to lookup + * @pnf: place to find the nfsd_file, or store it if it was non-NULL + * @fmode: fmode_t to use for open + * + * 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, returned nfsd_file will have its nf_net member + * set. Caller (NFS client) is responsible for calling nfsd_net_put and + * nfsd_file_put (via nfs_to_nfsd_file_put_local). + */ +static struct nfsd_file * +nfsd_open_local_fh(struct net *net, struct auth_domain *dom, + struct rpc_clnt *rpc_clnt, const struct cred *cred, + const struct nfs_fh *nfs_fh, struct nfsd_file __rcu **pnf, + const fmode_t fmode) +{ + int mayflags = NFSD_MAY_LOCALIO; + struct svc_cred rq_cred; + struct svc_fh fh; + struct nfsd_file *localio; + __be32 beres; + + if (nfs_fh->size > NFS4_FHSIZE) + return ERR_PTR(-EINVAL); + + if (!nfsd_net_try_get(net)) + return ERR_PTR(-ENXIO); + + rcu_read_lock(); + localio = nfsd_file_get(rcu_dereference(*pnf)); + rcu_read_unlock(); + if (localio) + return localio; + + /* nfs_fh -> svc_fh */ + 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; + + svcauth_map_clnt_to_svc_cred_local(rpc_clnt, cred, &rq_cred); + + beres = nfsd_file_acquire_local(net, &rq_cred, dom, + &fh, mayflags, &localio); + if (beres) + localio = ERR_PTR(nfs_stat_to_errno(be32_to_cpu(beres))); + + fh_put(&fh); + if (rq_cred.cr_group_info) + put_group_info(rq_cred.cr_group_info); + + if (!IS_ERR(localio)) { + struct nfsd_file *new; + if (!nfsd_net_try_get(net)) { + nfsd_file_put(localio); + nfsd_net_put(net); + return ERR_PTR(-ENXIO); + } + nfsd_file_get(localio); + again: + new = unrcu_pointer(cmpxchg(pnf, NULL, RCU_INITIALIZER(localio))); + if (new) { + /* Some other thread installed an nfsd_file */ + if (nfsd_file_get(new) == NULL) + goto again; + /* + * Drop the ref we were going to install (both file and + * net) and the one we were going to return (only file). + */ + nfsd_file_put(localio); + nfsd_net_put(net); + nfsd_file_put(localio); + localio = new; + } + } else + nfsd_net_put(net); + + return localio; +} + +static void nfsd_file_dio_alignment(struct nfsd_file *nf, + u32 *nf_dio_mem_align, + u32 *nf_dio_offset_align, + u32 *nf_dio_read_offset_align) +{ + *nf_dio_mem_align = nf->nf_dio_mem_align; + *nf_dio_offset_align = nf->nf_dio_offset_align; + *nf_dio_read_offset_align = nf->nf_dio_read_offset_align; +} + +static const struct nfsd_localio_operations nfsd_localio_ops = { + .nfsd_net_try_get = nfsd_net_try_get, + .nfsd_net_put = nfsd_net_put, + .nfsd_open_local_fh = nfsd_open_local_fh, + .nfsd_file_put_local = nfsd_file_put_local, + .nfsd_file_file = nfsd_file_file, + .nfsd_file_dio_alignment = nfsd_file_dio_alignment, +}; + +void nfsd_localio_ops_init(void) +{ + nfs_to = &nfsd_localio_ops; +} + +/* + * UUID_IS_LOCAL XDR functions + */ + +static __be32 localio_proc_null(struct svc_rqst *rqstp) +{ + return rpc_success; +} + +struct localio_uuidarg { + uuid_t uuid; +}; + +static __be32 localio_proc_uuid_is_local(struct svc_rqst *rqstp) +{ + struct localio_uuidarg *argp = rqstp->rq_argp; + struct net *net = SVC_NET(rqstp); + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + + nfs_uuid_is_local(&argp->uuid, &nn->local_clients, + &nn->local_clients_lock, + net, rqstp->rq_client, THIS_MODULE); + + return rpc_success; +} + +static bool localio_decode_uuidarg(struct svc_rqst *rqstp, + struct xdr_stream *xdr) +{ + struct localio_uuidarg *argp = rqstp->rq_argp; + u8 uuid[UUID_SIZE]; + + if (decode_opaque_fixed(xdr, uuid, UUID_SIZE)) + return false; + import_uuid(&argp->uuid, uuid); + + return true; +} + +static const struct svc_procedure localio_procedures1[] = { + [LOCALIOPROC_NULL] = { + .pc_func = localio_proc_null, + .pc_decode = nfssvc_decode_voidarg, + .pc_encode = nfssvc_encode_voidres, + .pc_argsize = sizeof(struct nfsd_voidargs), + .pc_ressize = sizeof(struct nfsd_voidres), + .pc_cachetype = RC_NOCACHE, + .pc_xdrressize = 0, + .pc_name = "NULL", + }, + [LOCALIOPROC_UUID_IS_LOCAL] = { + .pc_func = localio_proc_uuid_is_local, + .pc_decode = localio_decode_uuidarg, + .pc_encode = nfssvc_encode_voidres, + .pc_argsize = sizeof(struct localio_uuidarg), + .pc_argzero = sizeof(struct localio_uuidarg), + .pc_ressize = sizeof(struct nfsd_voidres), + .pc_cachetype = RC_NOCACHE, + .pc_name = "UUID_IS_LOCAL", + }, +}; + +#define LOCALIO_NR_PROCEDURES ARRAY_SIZE(localio_procedures1) +static DEFINE_PER_CPU_ALIGNED(unsigned long, + localio_count[LOCALIO_NR_PROCEDURES]); +const struct svc_version localio_version1 = { + .vs_vers = 1, + .vs_nproc = LOCALIO_NR_PROCEDURES, + .vs_proc = localio_procedures1, + .vs_dispatch = nfsd_dispatch, + .vs_count = localio_count, + .vs_xdrsize = XDR_QUADLEN(UUID_SIZE), + .vs_hidden = true, +}; diff --git a/fs/nfsd/lockd.c b/fs/nfsd/lockd.c index 46a7f9b813e5..c774ce9aa296 100644 --- a/fs/nfsd/lockd.c +++ b/fs/nfsd/lockd.c @@ -38,17 +38,39 @@ nlm_fopen(struct svc_rqst *rqstp, struct nfs_fh *f, struct file **filp, memcpy(&fh.fh_handle.fh_raw, f->data, f->size); fh.fh_export = NULL; + /* + * Allow BYPASS_GSS as some client implementations use AUTH_SYS + * for NLM even when GSS is used for NFS. + * Allow OWNER_OVERRIDE as permission might have been changed + * after the file was opened. + * Pass MAY_NLM so that authentication can be completely bypassed + * if NFSEXP_NOAUTHNLM is set. Some older clients use AUTH_NULL + * for NLM requests. + */ access = (mode == O_WRONLY) ? NFSD_MAY_WRITE : NFSD_MAY_READ; - access |= NFSD_MAY_LOCK; + access |= NFSD_MAY_NLM | NFSD_MAY_OWNER_OVERRIDE | NFSD_MAY_BYPASS_GSS; nfserr = nfsd_open(rqstp, &fh, S_IFREG, access, filp); fh_put(&fh); - /* We return nlm error codes as nlm doesn't know + /* We return nlm error codes as nlm doesn't know * about nfsd, but nfsd does know about nlm.. */ switch (nfserr) { case nfs_ok: return 0; - case nfserr_dropit: + case nfserr_jukebox: + /* this error can indicate a presence of a conflicting + * delegation to an NLM lock request. Options are: + * (1) For now, drop this request and make the client + * retry. When delegation is returned, client's lock retry + * will complete. + * (2) NLM4_DENIED as per "spec" signals to the client + * that the lock is unavailable now but client can retry. + * Linux client implementation does not. It treats + * NLM4_DENIED same as NLM4_FAILED and errors the request. + * (3) For the future, treat this as blocked lock and try + * to callback when the delegation is returned but might + * not have a proper lock request to block on. + */ return nlm_drop_reply; case nfserr_stale: return nlm_stale_fh; diff --git a/fs/nfsd/netlink.c b/fs/nfsd/netlink.c new file mode 100644 index 000000000000..ac51a44e1065 --- /dev/null +++ b/fs/nfsd/netlink.c @@ -0,0 +1,114 @@ +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/nfsd.yaml */ +/* YNL-GEN kernel source */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ + +#include <net/netlink.h> +#include <net/genetlink.h> + +#include "netlink.h" + +#include <uapi/linux/nfsd_netlink.h> + +/* Common nested types */ +const struct nla_policy nfsd_sock_nl_policy[NFSD_A_SOCK_TRANSPORT_NAME + 1] = { + [NFSD_A_SOCK_ADDR] = { .type = NLA_BINARY, }, + [NFSD_A_SOCK_TRANSPORT_NAME] = { .type = NLA_NUL_STRING, }, +}; + +const struct nla_policy nfsd_version_nl_policy[NFSD_A_VERSION_ENABLED + 1] = { + [NFSD_A_VERSION_MAJOR] = { .type = NLA_U32, }, + [NFSD_A_VERSION_MINOR] = { .type = NLA_U32, }, + [NFSD_A_VERSION_ENABLED] = { .type = NLA_FLAG, }, +}; + +/* NFSD_CMD_THREADS_SET - do */ +static const struct nla_policy nfsd_threads_set_nl_policy[NFSD_A_SERVER_SCOPE + 1] = { + [NFSD_A_SERVER_THREADS] = { .type = NLA_U32, }, + [NFSD_A_SERVER_GRACETIME] = { .type = NLA_U32, }, + [NFSD_A_SERVER_LEASETIME] = { .type = NLA_U32, }, + [NFSD_A_SERVER_SCOPE] = { .type = NLA_NUL_STRING, }, +}; + +/* NFSD_CMD_VERSION_SET - do */ +static const struct nla_policy nfsd_version_set_nl_policy[NFSD_A_SERVER_PROTO_VERSION + 1] = { + [NFSD_A_SERVER_PROTO_VERSION] = NLA_POLICY_NESTED(nfsd_version_nl_policy), +}; + +/* NFSD_CMD_LISTENER_SET - do */ +static const struct nla_policy nfsd_listener_set_nl_policy[NFSD_A_SERVER_SOCK_ADDR + 1] = { + [NFSD_A_SERVER_SOCK_ADDR] = NLA_POLICY_NESTED(nfsd_sock_nl_policy), +}; + +/* NFSD_CMD_POOL_MODE_SET - do */ +static const struct nla_policy nfsd_pool_mode_set_nl_policy[NFSD_A_POOL_MODE_MODE + 1] = { + [NFSD_A_POOL_MODE_MODE] = { .type = NLA_NUL_STRING, }, +}; + +/* Ops table for nfsd */ +static const struct genl_split_ops nfsd_nl_ops[] = { + { + .cmd = NFSD_CMD_RPC_STATUS_GET, + .dumpit = nfsd_nl_rpc_status_get_dumpit, + .flags = GENL_CMD_CAP_DUMP, + }, + { + .cmd = NFSD_CMD_THREADS_SET, + .doit = nfsd_nl_threads_set_doit, + .policy = nfsd_threads_set_nl_policy, + .maxattr = NFSD_A_SERVER_SCOPE, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = NFSD_CMD_THREADS_GET, + .doit = nfsd_nl_threads_get_doit, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = NFSD_CMD_VERSION_SET, + .doit = nfsd_nl_version_set_doit, + .policy = nfsd_version_set_nl_policy, + .maxattr = NFSD_A_SERVER_PROTO_VERSION, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = NFSD_CMD_VERSION_GET, + .doit = nfsd_nl_version_get_doit, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = NFSD_CMD_LISTENER_SET, + .doit = nfsd_nl_listener_set_doit, + .policy = nfsd_listener_set_nl_policy, + .maxattr = NFSD_A_SERVER_SOCK_ADDR, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = NFSD_CMD_LISTENER_GET, + .doit = nfsd_nl_listener_get_doit, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = NFSD_CMD_POOL_MODE_SET, + .doit = nfsd_nl_pool_mode_set_doit, + .policy = nfsd_pool_mode_set_nl_policy, + .maxattr = NFSD_A_POOL_MODE_MODE, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = NFSD_CMD_POOL_MODE_GET, + .doit = nfsd_nl_pool_mode_get_doit, + .flags = GENL_CMD_CAP_DO, + }, +}; + +struct genl_family nfsd_nl_family __ro_after_init = { + .name = NFSD_FAMILY_NAME, + .version = NFSD_FAMILY_VERSION, + .netnsok = true, + .parallel_ops = true, + .module = THIS_MODULE, + .split_ops = nfsd_nl_ops, + .n_split_ops = ARRAY_SIZE(nfsd_nl_ops), +}; diff --git a/fs/nfsd/netlink.h b/fs/nfsd/netlink.h new file mode 100644 index 000000000000..478117ff6b8c --- /dev/null +++ b/fs/nfsd/netlink.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/nfsd.yaml */ +/* YNL-GEN kernel header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ + +#ifndef _LINUX_NFSD_GEN_H +#define _LINUX_NFSD_GEN_H + +#include <net/netlink.h> +#include <net/genetlink.h> + +#include <uapi/linux/nfsd_netlink.h> + +/* Common nested types */ +extern const struct nla_policy nfsd_sock_nl_policy[NFSD_A_SOCK_TRANSPORT_NAME + 1]; +extern const struct nla_policy nfsd_version_nl_policy[NFSD_A_VERSION_ENABLED + 1]; + +int nfsd_nl_rpc_status_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); +int nfsd_nl_threads_set_doit(struct sk_buff *skb, struct genl_info *info); +int nfsd_nl_threads_get_doit(struct sk_buff *skb, struct genl_info *info); +int nfsd_nl_version_set_doit(struct sk_buff *skb, struct genl_info *info); +int nfsd_nl_version_get_doit(struct sk_buff *skb, struct genl_info *info); +int nfsd_nl_listener_set_doit(struct sk_buff *skb, struct genl_info *info); +int nfsd_nl_listener_get_doit(struct sk_buff *skb, struct genl_info *info); +int nfsd_nl_pool_mode_set_doit(struct sk_buff *skb, struct genl_info *info); +int nfsd_nl_pool_mode_get_doit(struct sk_buff *skb, struct genl_info *info); + +extern struct genl_family nfsd_nl_family; + +#endif /* _LINUX_NFSD_GEN_H */ diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index 51a4b7885cae..3e2d0fde80a7 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -10,8 +10,12 @@ #include <net/net_namespace.h> #include <net/netns/generic.h> +#include <linux/filelock.h> +#include <linux/nfs4.h> #include <linux/percpu_counter.h> +#include <linux/percpu-refcount.h> #include <linux/siphash.h> +#include <linux/sunrpc/stats.h> /* Hash tables for nfs4_clientid state */ #define CLIENT_HASH_BITS 4 @@ -25,10 +29,22 @@ struct nfsd4_client_tracking_ops; enum { /* cache misses due only to checksum comparison failures */ - NFSD_NET_PAYLOAD_MISSES, + NFSD_STATS_PAYLOAD_MISSES, /* amount of memory (in bytes) currently consumed by the DRC */ - NFSD_NET_DRC_MEM_USAGE, - NFSD_NET_COUNTERS_NUM + NFSD_STATS_DRC_MEM_USAGE, + NFSD_STATS_RC_HITS, /* repcache hits */ + NFSD_STATS_RC_MISSES, /* repcache misses */ + NFSD_STATS_RC_NOCACHE, /* uncached reqs */ + NFSD_STATS_FH_STALE, /* FH stale error */ + NFSD_STATS_IO_READ, /* bytes returned to read requests */ + NFSD_STATS_IO_WRITE, /* bytes passed in write requests */ +#ifdef CONFIG_NFSD_V4 + NFSD_STATS_FIRST_NFS4_OP, /* count of individual nfsv4 operations */ + NFSD_STATS_LAST_NFS4_OP = NFSD_STATS_FIRST_NFS4_OP + LAST_NFS4_OP, +#define NFSD_STATS_NFS4_OP(op) (NFSD_STATS_FIRST_NFS4_OP + (op)) + NFSD_STATS_WDELEG_GETATTR, /* count of getattr conflict with wdeleg */ +#endif + NFSD_STATS_COUNTERS_NUM }; /* @@ -112,24 +128,16 @@ struct nfsd_net { seqlock_t writeverf_lock; unsigned char writeverf[8]; - /* - * Max number of connections this nfsd container will allow. Defaults - * to '0' which is means that it bases this on the number of threads. - */ - unsigned int max_connections; - u32 clientid_base; u32 clientid_counter; u32 clverifier_counter; - struct svc_serv *nfsd_serv; - /* When a listening socket is added to nfsd, keep_active is set - * and this justifies a reference on nfsd_serv. This stops - * nfsd_serv from being freed. When the number of threads is - * set, keep_active is cleared and the reference is dropped. So - * when the last thread exits, the service will be destroyed. - */ - int keep_active; + struct svc_info nfsd_info; +#define nfsd_serv nfsd_info.serv + + struct percpu_ref nfsd_net_ref; + struct completion nfsd_net_confirm_done; + struct completion nfsd_net_free_done; /* * clientid and stateid data for construction of net unique COPY @@ -138,12 +146,13 @@ struct nfsd_net { u32 s2s_cp_cl_id; struct idr s2s_cp_stateids; spinlock_t s2s_cp_lock; + atomic_t pending_async_copies; /* * Version information */ - bool *nfsd_versions; - bool *nfsd4_minorversions; + bool nfsd_versions[NFSD_MAXVERS + 1]; + bool nfsd4_minorversions[NFSD_SUPPORTED_MINOR_VERSION + 1]; /* * Duplicate reply cache @@ -168,7 +177,10 @@ struct nfsd_net { atomic_t num_drc_entries; /* Per-netns stats counters */ - struct percpu_counter counter[NFSD_NET_COUNTERS_NUM]; + struct percpu_counter counter[NFSD_STATS_COUNTERS_NUM]; + + /* sunrpc svc stats */ + struct svc_stat nfsd_svcstats; /* longest hash chain seen */ unsigned int longest_chain; @@ -176,7 +188,7 @@ struct nfsd_net { /* size of cache when we saw the longest hash chain */ unsigned int longest_chain_cachesize; - struct shrinker nfsd_reply_cache_shrinker; + struct shrinker *nfsd_reply_cache_shrinker; /* tracking server-to-server copy mounts */ spinlock_t nfsd_ssc_lock; @@ -194,17 +206,28 @@ struct nfsd_net { int nfs4_max_clients; atomic_t nfsd_courtesy_clients; - struct shrinker nfsd_client_shrinker; + struct shrinker *nfsd_client_shrinker; struct work_struct nfsd_shrinker_work; + + /* last time an admin-revoke happened for NFSv4.0 */ + time64_t nfs40_last_revoke; + +#if IS_ENABLED(CONFIG_NFS_LOCALIO) + /* Local clients to be invalidated when net is shut down */ + spinlock_t local_clients_lock; + struct list_head local_clients; +#endif }; /* Simple check to find out if a given net was properly initialized */ #define nfsd_netns_ready(nn) ((nn)->sessionid_hashtbl) -extern void nfsd_netns_free_versions(struct nfsd_net *nn); - +extern bool nfsd_support_version(int vers); extern unsigned int nfsd_net_id; +bool nfsd_net_try_get(struct net *net); +void nfsd_net_put(struct net *net); + void nfsd_copy_write_verifier(__be32 verf[2], struct nfsd_net *nn); void nfsd_reset_write_verifier(struct nfsd_net *nn); #endif /* __NFSD_NETNS_H__ */ diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index 1457f59f447a..5fb202acb0fd 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -84,6 +84,8 @@ out: fail: posix_acl_release(resp->acl_access); posix_acl_release(resp->acl_default); + resp->acl_access = NULL; + resp->acl_default = NULL; goto out; } @@ -113,11 +115,11 @@ static __be32 nfsacld_proc_setacl(struct svc_rqst *rqstp) inode_lock(inode); - error = set_posix_acl(&init_user_ns, fh->fh_dentry, ACL_TYPE_ACCESS, + error = set_posix_acl(&nop_mnt_idmap, fh->fh_dentry, ACL_TYPE_ACCESS, argp->acl_access); if (error) goto out_drop_lock; - error = set_posix_acl(&init_user_ns, fh->fh_dentry, ACL_TYPE_DEFAULT, + error = set_posix_acl(&nop_mnt_idmap, fh->fh_dentry, ACL_TYPE_DEFAULT, argp->acl_default); if (error) goto out_drop_lock; @@ -308,8 +310,6 @@ static void nfsaclsvc_release_access(struct svc_rqst *rqstp) fh_put(&resp->fh); } -struct nfsd3_voidargs { int dummy; }; - #define ST 1 /* status*/ #define AT 21 /* attributes */ #define pAT (1+AT) /* post attributes - conditional */ @@ -377,10 +377,11 @@ static const struct svc_procedure nfsd_acl_procedures2[5] = { }, }; -static unsigned int nfsd_acl_count2[ARRAY_SIZE(nfsd_acl_procedures2)]; +static DEFINE_PER_CPU_ALIGNED(unsigned long, + nfsd_acl_count2[ARRAY_SIZE(nfsd_acl_procedures2)]); const struct svc_version nfsd_acl_version2 = { .vs_vers = 2, - .vs_nproc = 5, + .vs_nproc = ARRAY_SIZE(nfsd_acl_procedures2), .vs_proc = nfsd_acl_procedures2, .vs_count = nfsd_acl_count2, .vs_dispatch = nfsd_dispatch, diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index 647108138e8a..7b5433bd3019 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -76,6 +76,8 @@ out: fail: posix_acl_release(resp->acl_access); posix_acl_release(resp->acl_default); + resp->acl_access = NULL; + resp->acl_default = NULL; goto out; } @@ -103,11 +105,11 @@ static __be32 nfsd3_proc_setacl(struct svc_rqst *rqstp) inode_lock(inode); - error = set_posix_acl(&init_user_ns, fh->fh_dentry, ACL_TYPE_ACCESS, + error = set_posix_acl(&nop_mnt_idmap, fh->fh_dentry, ACL_TYPE_ACCESS, argp->acl_access); if (error) goto out_drop_lock; - error = set_posix_acl(&init_user_ns, fh->fh_dentry, ACL_TYPE_DEFAULT, + error = set_posix_acl(&nop_mnt_idmap, fh->fh_dentry, ACL_TYPE_DEFAULT, argp->acl_default); out_drop_lock: @@ -221,8 +223,6 @@ static void nfs3svc_release_getacl(struct svc_rqst *rqstp) posix_acl_release(resp->acl_default); } -struct nfsd3_voidargs { int dummy; }; - #define ST 1 /* status*/ #define AT 21 /* attributes */ #define pAT (1+AT) /* post attributes - conditional */ @@ -266,10 +266,11 @@ static const struct svc_procedure nfsd_acl_procedures3[3] = { }, }; -static unsigned int nfsd_acl_count3[ARRAY_SIZE(nfsd_acl_procedures3)]; +static DEFINE_PER_CPU_ALIGNED(unsigned long, + nfsd_acl_count3[ARRAY_SIZE(nfsd_acl_procedures3)]); const struct svc_version nfsd_acl_version3 = { .vs_vers = 3, - .vs_nproc = 3, + .vs_nproc = ARRAY_SIZE(nfsd_acl_procedures3), .vs_proc = nfsd_acl_procedures3, .vs_count = nfsd_acl_count3, .vs_dispatch = nfsd_dispatch, diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index d01b29aba662..42adc5461db0 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -14,6 +14,7 @@ #include "xdr3.h" #include "vfs.h" #include "filecache.h" +#include "trace.h" #define NFSDDBG_FACILITY NFSDDBG_PROC @@ -28,6 +29,29 @@ static int nfs3_ftypes[] = { S_IFIFO, /* NF3FIFO */ }; +static __be32 nfsd3_map_status(__be32 status) +{ + switch (status) { + case nfs_ok: + break; + case nfserr_nofilehandle: + status = nfserr_badhandle; + break; + case nfserr_wrongsec: + case nfserr_file_open: + status = nfserr_acces; + break; + case nfserr_symlink_not_dir: + status = nfserr_notdir; + break; + case nfserr_symlink: + case nfserr_wrong_type: + status = nfserr_inval; + break; + } + return status; +} + /* * NULL call. */ @@ -46,8 +70,7 @@ nfsd3_proc_getattr(struct svc_rqst *rqstp) struct nfsd_fhandle *argp = rqstp->rq_argp; struct nfsd3_attrstat *resp = rqstp->rq_resp; - dprintk("nfsd: GETATTR(3) %s\n", - SVCFH_fmt(&argp->fh)); + trace_nfsd_vfs_getattr(rqstp, &argp->fh); fh_copy(&resp->fh, &argp->fh); resp->status = fh_verify(rqstp, &resp->fh, 0, @@ -57,6 +80,7 @@ nfsd3_proc_getattr(struct svc_rqst *rqstp) resp->status = fh_getattr(&resp->fh, &resp->stat); out: + resp->status = nfsd3_map_status(resp->status); return rpc_success; } @@ -71,13 +95,16 @@ nfsd3_proc_setattr(struct svc_rqst *rqstp) struct nfsd_attrs attrs = { .na_iattr = &argp->attrs, }; + const struct timespec64 *guardtime = NULL; dprintk("nfsd: SETATTR(3) %s\n", SVCFH_fmt(&argp->fh)); fh_copy(&resp->fh, &argp->fh); - resp->status = nfsd_setattr(rqstp, &resp->fh, &attrs, - argp->check_guard, argp->guardtime); + if (argp->check_guard) + guardtime = &argp->guardtime; + resp->status = nfsd_setattr(rqstp, &resp->fh, &attrs, guardtime); + resp->status = nfsd3_map_status(resp->status); return rpc_success; } @@ -101,6 +128,7 @@ nfsd3_proc_lookup(struct svc_rqst *rqstp) resp->status = nfsd_lookup(rqstp, &resp->dirfh, argp->name, argp->len, &resp->fh); + resp->status = nfsd3_map_status(resp->status); return rpc_success; } @@ -120,6 +148,7 @@ nfsd3_proc_access(struct svc_rqst *rqstp) fh_copy(&resp->fh, &argp->fh); resp->access = argp->access; resp->status = nfsd_access(rqstp, &resp->fh, &resp->access, NULL); + resp->status = nfsd3_map_status(resp->status); return rpc_success; } @@ -140,6 +169,7 @@ nfsd3_proc_readlink(struct svc_rqst *rqstp) resp->pages = rqstp->rq_next_page++; resp->status = nfsd_readlink(rqstp, &resp->fh, page_address(*resp->pages), &resp->len); + resp->status = nfsd3_map_status(resp->status); return rpc_success; } @@ -151,8 +181,6 @@ nfsd3_proc_read(struct svc_rqst *rqstp) { struct nfsd3_readargs *argp = rqstp->rq_argp; struct nfsd3_readres *resp = rqstp->rq_resp; - unsigned int len; - int v; dprintk("nfsd: READ(3) %s %lu bytes at %Lu\n", SVCFH_fmt(&argp->fh), @@ -166,28 +194,20 @@ nfsd3_proc_read(struct svc_rqst *rqstp) if (argp->offset + argp->count > (u64)OFFSET_MAX) argp->count = (u64)OFFSET_MAX - argp->offset; - v = 0; - len = argp->count; resp->pages = rqstp->rq_next_page; - while (len > 0) { - struct page *page = *(rqstp->rq_next_page++); - - rqstp->rq_vec[v].iov_base = page_address(page); - rqstp->rq_vec[v].iov_len = min_t(unsigned int, len, PAGE_SIZE); - len -= rqstp->rq_vec[v].iov_len; - v++; - } /* Obtain buffer pointer for payload. * 1 (status) + 22 (post_op_attr) + 1 (count) + 1 (eof) * + 1 (xdr opaque byte count) = 26 */ resp->count = argp->count; - svc_reserve_auth(rqstp, ((1 + NFS3_POST_OP_ATTR_WORDS + 3)<<2) + resp->count +4); + svc_reserve_auth(rqstp, ((1 + NFS3_POST_OP_ATTR_WORDS + 3) << 2) + + resp->count + 4); fh_copy(&resp->fh, &argp->fh); resp->status = nfsd_read(rqstp, &resp->fh, argp->offset, - rqstp->rq_vec, v, &resp->count, &resp->eof); + &resp->count, &resp->eof); + resp->status = nfsd3_map_status(resp->status); return rpc_success; } @@ -200,13 +220,12 @@ nfsd3_proc_write(struct svc_rqst *rqstp) struct nfsd3_writeargs *argp = rqstp->rq_argp; struct nfsd3_writeres *resp = rqstp->rq_resp; unsigned long cnt = argp->len; - unsigned int nvecs; dprintk("nfsd: WRITE(3) %s %d bytes at %Lu%s\n", SVCFH_fmt(&argp->fh), argp->len, (unsigned long long) argp->offset, - argp->stable? " stable" : ""); + argp->stable ? " stable" : ""); resp->status = nfserr_fbig; if (argp->offset > (u64)OFFSET_MAX || @@ -215,12 +234,11 @@ nfsd3_proc_write(struct svc_rqst *rqstp) fh_copy(&resp->fh, &argp->fh); resp->committed = argp->stable; - nvecs = svc_fill_write_vector(rqstp, &argp->payload); - resp->status = nfsd_write(rqstp, &resp->fh, argp->offset, - rqstp->rq_vec, nvecs, &cnt, + &argp->payload, &cnt, resp->committed, resp->verf); resp->count = cnt; + resp->status = nfsd3_map_status(resp->status); return rpc_success; } @@ -245,6 +263,8 @@ nfsd3_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, __be32 status; int host_err; + trace_nfsd_vfs_create(rqstp, fhp, S_IFREG, argp->name, argp->len); + if (isdotent(argp->name, argp->len)) return nfserr_exist; if (!(iap->ia_valid & ATTR_MODE)) @@ -261,12 +281,11 @@ nfsd3_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, if (host_err) return nfserrno(host_err); - inode_lock_nested(inode, I_MUTEX_PARENT); - - child = lookup_one_len(argp->name, parent, argp->len); + child = start_creating(&nop_mnt_idmap, parent, + &QSTR_LEN(argp->name, argp->len)); if (IS_ERR(child)) { status = nfserrno(PTR_ERR(child)); - goto out; + goto out_write; } if (d_really_is_negative(child)) { @@ -306,8 +325,8 @@ nfsd3_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, status = nfserr_exist; break; case NFS3_CREATE_EXCLUSIVE: - if (d_inode(child)->i_mtime.tv_sec == v_mtime && - d_inode(child)->i_atime.tv_sec == v_atime && + if (inode_get_mtime_sec(d_inode(child)) == v_mtime && + inode_get_atime_sec(d_inode(child)) == v_atime && d_inode(child)->i_size == 0) { break; } @@ -319,8 +338,10 @@ nfsd3_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, if (!IS_POSIXACL(inode)) iap->ia_mode &= ~current_umask(); - fh_fill_pre_attrs(fhp); - host_err = vfs_create(&init_user_ns, inode, child, iap->ia_mode, true); + status = fh_fill_pre_attrs(fhp); + if (status != nfs_ok) + goto out; + host_err = vfs_create(&nop_mnt_idmap, child, iap->ia_mode, NULL); if (host_err < 0) { status = nfserrno(host_err); goto out; @@ -343,9 +364,8 @@ set_attr: status = nfsd_create_setattr(rqstp, fhp, resfhp, &attrs); out: - inode_unlock(inode); - if (child && !IS_ERR(child)) - dput(child); + end_creating(child); +out_write: fh_drop_write(fhp); return status; } @@ -357,15 +377,11 @@ nfsd3_proc_create(struct svc_rqst *rqstp) struct nfsd3_diropres *resp = rqstp->rq_resp; svc_fh *dirfhp, *newfhp; - dprintk("nfsd: CREATE(3) %s %.*s\n", - SVCFH_fmt(&argp->fh), - argp->len, - argp->name); - dirfhp = fh_copy(&resp->dirfh, &argp->fh); newfhp = fh_init(&resp->fh, NFS3_FHSIZE); resp->status = nfsd3_create_file(rqstp, dirfhp, newfhp, argp); + resp->status = nfsd3_map_status(resp->status); return rpc_success; } @@ -381,16 +397,12 @@ nfsd3_proc_mkdir(struct svc_rqst *rqstp) .na_iattr = &argp->attrs, }; - dprintk("nfsd: MKDIR(3) %s %.*s\n", - SVCFH_fmt(&argp->fh), - argp->len, - argp->name); - argp->attrs.ia_valid &= ~ATTR_SIZE; fh_copy(&resp->dirfh, &argp->fh); fh_init(&resp->fh, NFS3_FHSIZE); resp->status = nfsd_create(rqstp, &resp->dirfh, argp->name, argp->len, &attrs, S_IFDIR, 0, &resp->fh); + resp->status = nfsd3_map_status(resp->status); return rpc_success; } @@ -420,17 +432,13 @@ nfsd3_proc_symlink(struct svc_rqst *rqstp) goto out; } - dprintk("nfsd: SYMLINK(3) %s %.*s -> %.*s\n", - SVCFH_fmt(&argp->ffh), - argp->flen, argp->fname, - argp->tlen, argp->tname); - fh_copy(&resp->dirfh, &argp->ffh); fh_init(&resp->fh, NFS3_FHSIZE); resp->status = nfsd_symlink(rqstp, &resp->dirfh, argp->fname, argp->flen, argp->tname, &attrs, &resp->fh); kfree(argp->tname); out: + resp->status = nfsd3_map_status(resp->status); return rpc_success; } @@ -448,11 +456,6 @@ nfsd3_proc_mknod(struct svc_rqst *rqstp) int type; dev_t rdev = 0; - dprintk("nfsd: MKNOD(3) %s %.*s\n", - SVCFH_fmt(&argp->fh), - argp->len, - argp->name); - fh_copy(&resp->dirfh, &argp->fh); fh_init(&resp->fh, NFS3_FHSIZE); @@ -472,6 +475,7 @@ nfsd3_proc_mknod(struct svc_rqst *rqstp) resp->status = nfsd_create(rqstp, &resp->dirfh, argp->name, argp->len, &attrs, type, rdev, &resp->fh); out: + resp->status = nfsd3_map_status(resp->status); return rpc_success; } @@ -484,15 +488,11 @@ nfsd3_proc_remove(struct svc_rqst *rqstp) struct nfsd3_diropargs *argp = rqstp->rq_argp; struct nfsd3_attrstat *resp = rqstp->rq_resp; - dprintk("nfsd: REMOVE(3) %s %.*s\n", - SVCFH_fmt(&argp->fh), - argp->len, - argp->name); - /* Unlink. -S_IFDIR means file must not be a directory */ fh_copy(&resp->fh, &argp->fh); resp->status = nfsd_unlink(rqstp, &resp->fh, -S_IFDIR, argp->name, argp->len); + resp->status = nfsd3_map_status(resp->status); return rpc_success; } @@ -505,14 +505,10 @@ nfsd3_proc_rmdir(struct svc_rqst *rqstp) struct nfsd3_diropargs *argp = rqstp->rq_argp; struct nfsd3_attrstat *resp = rqstp->rq_resp; - dprintk("nfsd: RMDIR(3) %s %.*s\n", - SVCFH_fmt(&argp->fh), - argp->len, - argp->name); - fh_copy(&resp->fh, &argp->fh); resp->status = nfsd_unlink(rqstp, &resp->fh, S_IFDIR, argp->name, argp->len); + resp->status = nfsd3_map_status(resp->status); return rpc_success; } @@ -522,19 +518,11 @@ nfsd3_proc_rename(struct svc_rqst *rqstp) struct nfsd3_renameargs *argp = rqstp->rq_argp; struct nfsd3_renameres *resp = rqstp->rq_resp; - dprintk("nfsd: RENAME(3) %s %.*s ->\n", - SVCFH_fmt(&argp->ffh), - argp->flen, - argp->fname); - dprintk("nfsd: -> %s %.*s\n", - SVCFH_fmt(&argp->tfh), - argp->tlen, - argp->tname); - fh_copy(&resp->ffh, &argp->ffh); fh_copy(&resp->tfh, &argp->tfh); resp->status = nfsd_rename(rqstp, &resp->ffh, argp->fname, argp->flen, &resp->tfh, argp->tname, argp->tlen); + resp->status = nfsd3_map_status(resp->status); return rpc_success; } @@ -544,17 +532,11 @@ nfsd3_proc_link(struct svc_rqst *rqstp) struct nfsd3_linkargs *argp = rqstp->rq_argp; struct nfsd3_linkres *resp = rqstp->rq_resp; - dprintk("nfsd: LINK(3) %s ->\n", - SVCFH_fmt(&argp->ffh)); - dprintk("nfsd: -> %s %.*s\n", - SVCFH_fmt(&argp->tfh), - argp->tlen, - argp->tname); - fh_copy(&resp->fh, &argp->ffh); fh_copy(&resp->tfh, &argp->tfh); resp->status = nfsd_link(rqstp, &resp->tfh, argp->tname, argp->tlen, &resp->fh); + resp->status = nfsd3_map_status(resp->status); return rpc_success; } @@ -575,7 +557,7 @@ static void nfsd3_init_dirlist_pages(struct svc_rqst *rqstp, buf->pages = rqstp->rq_next_page; rqstp->rq_next_page += (buf->buflen + PAGE_SIZE - 1) >> PAGE_SHIFT; - xdr_init_encode_pages(xdr, buf, buf->pages, NULL); + xdr_init_encode_pages(xdr, buf); } /* @@ -588,9 +570,7 @@ nfsd3_proc_readdir(struct svc_rqst *rqstp) struct nfsd3_readdirres *resp = rqstp->rq_resp; loff_t offset; - dprintk("nfsd: READDIR(3) %s %d bytes at %d\n", - SVCFH_fmt(&argp->fh), - argp->count, (u32) argp->cookie); + trace_nfsd_vfs_readdir(rqstp, &argp->fh, argp->count, argp->cookie); nfsd3_init_dirlist_pages(rqstp, resp, argp->count); @@ -607,6 +587,7 @@ nfsd3_proc_readdir(struct svc_rqst *rqstp) /* Recycle only pages that were part of the reply */ rqstp->rq_next_page = resp->xdr.page_ptr + 1; + resp->status = nfsd3_map_status(resp->status); return rpc_success; } @@ -621,9 +602,7 @@ nfsd3_proc_readdirplus(struct svc_rqst *rqstp) struct nfsd3_readdirres *resp = rqstp->rq_resp; loff_t offset; - dprintk("nfsd: READDIR+(3) %s %d bytes at %d\n", - SVCFH_fmt(&argp->fh), - argp->count, (u32) argp->cookie); + trace_nfsd_vfs_readdir(rqstp, &argp->fh, argp->count, argp->cookie); nfsd3_init_dirlist_pages(rqstp, resp, argp->count); @@ -651,6 +630,7 @@ nfsd3_proc_readdirplus(struct svc_rqst *rqstp) rqstp->rq_next_page = resp->xdr.page_ptr + 1; out: + resp->status = nfsd3_map_status(resp->status); return rpc_success; } @@ -663,11 +643,9 @@ nfsd3_proc_fsstat(struct svc_rqst *rqstp) struct nfsd_fhandle *argp = rqstp->rq_argp; struct nfsd3_fsstatres *resp = rqstp->rq_resp; - dprintk("nfsd: FSSTAT(3) %s\n", - SVCFH_fmt(&argp->fh)); - resp->status = nfsd_statfs(rqstp, &argp->fh, &resp->stats, 0); fh_put(&argp->fh); + resp->status = nfsd3_map_status(resp->status); return rpc_success; } @@ -711,6 +689,7 @@ nfsd3_proc_fsinfo(struct svc_rqst *rqstp) } fh_put(&argp->fh); + resp->status = nfsd3_map_status(resp->status); return rpc_success; } @@ -753,6 +732,7 @@ nfsd3_proc_pathconf(struct svc_rqst *rqstp) } fh_put(&argp->fh); + resp->status = nfsd3_map_status(resp->status); return rpc_success; } @@ -780,6 +760,7 @@ nfsd3_proc_commit(struct svc_rqst *rqstp) argp->count, resp->verf); nfsd_file_put(nf); out: + resp->status = nfsd3_map_status(resp->status); return rpc_success; } @@ -1064,10 +1045,11 @@ static const struct svc_procedure nfsd_procedures3[22] = { }, }; -static unsigned int nfsd_count3[ARRAY_SIZE(nfsd_procedures3)]; +static DEFINE_PER_CPU_ALIGNED(unsigned long, + nfsd_count3[ARRAY_SIZE(nfsd_procedures3)]); const struct svc_version nfsd_version3 = { .vs_vers = 3, - .vs_nproc = 22, + .vs_nproc = ARRAY_SIZE(nfsd_procedures3), .vs_proc = nfsd_procedures3, .vs_dispatch = nfsd_dispatch, .vs_count = nfsd_count3, diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 3308dd671ef0..ef4971d71ac4 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -295,17 +295,14 @@ svcxdr_decode_sattr3(struct svc_rqst *rqstp, struct xdr_stream *xdr, static bool svcxdr_decode_sattrguard3(struct xdr_stream *xdr, struct nfsd3_sattrargs *args) { - __be32 *p; u32 check; if (xdr_stream_decode_bool(xdr, &check) < 0) return false; if (check) { - p = xdr_inline_decode(xdr, XDR_UNIT * 2); - if (!p) + if (!svcxdr_decode_nfstime3(xdr, &args->guardtime)) return false; args->check_guard = 1; - args->guardtime = be32_to_cpup(p); } else args->check_guard = 0; @@ -828,7 +825,8 @@ nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, struct xdr_stream *xdr) return false; if (xdr_stream_encode_u32(xdr, resp->len) < 0) return false; - xdr_write_pages(xdr, resp->pages, 0, resp->len); + svcxdr_encode_opaque_pages(rqstp, xdr, resp->pages, 0, + resp->len); if (svc_encode_result_payload(rqstp, head->iov_len, resp->len) < 0) return false; break; @@ -859,8 +857,9 @@ nfs3svc_encode_readres(struct svc_rqst *rqstp, struct xdr_stream *xdr) return false; if (xdr_stream_encode_u32(xdr, resp->count) < 0) return false; - xdr_write_pages(xdr, resp->pages, rqstp->rq_res.page_base, - resp->count); + svcxdr_encode_opaque_pages(rqstp, xdr, resp->pages, + rqstp->rq_res.page_base, + resp->count); if (svc_encode_result_payload(rqstp, head->iov_len, resp->count) < 0) return false; break; @@ -961,7 +960,8 @@ nfs3svc_encode_readdirres(struct svc_rqst *rqstp, struct xdr_stream *xdr) return false; if (!svcxdr_encode_cookieverf3(xdr, resp->verf)) return false; - xdr_write_pages(xdr, dirlist->pages, 0, dirlist->len); + svcxdr_encode_opaque_pages(rqstp, xdr, dirlist->pages, 0, + dirlist->len); /* no more entries */ if (xdr_stream_encode_item_absent(xdr) < 0) return false; @@ -1001,7 +1001,9 @@ compose_entry_fh(struct nfsd3_readdirres *cd, struct svc_fh *fhp, } else dchild = dget(dparent); } else - dchild = lookup_positive_unlocked(name, dparent, namlen); + dchild = lookup_one_positive_unlocked(&nop_mnt_idmap, + &QSTR_LEN(name, namlen), + dparent); if (IS_ERR(dchild)) return rv; if (d_mountpoint(dchild)) diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c index 518203821790..936ea1ad9586 100644 --- a/fs/nfsd/nfs4acl.c +++ b/fs/nfsd/nfs4acl.c @@ -198,8 +198,6 @@ summarize_posix_acl(struct posix_acl *acl, struct posix_acl_summary *pas) memset(pas, 0, sizeof(*pas)); pas->mask = 07; - pe = acl->a_entries + acl->a_count; - FOREACH_ACL_ENTRY(pa, acl, pe) { switch (pa->e_tag) { case ACL_USER_OBJ: @@ -441,7 +439,7 @@ struct posix_ace_state_array { * calculated so far: */ struct posix_acl_state { - int empty; + unsigned char valid; struct posix_ace_state owner; struct posix_ace_state group; struct posix_ace_state other; @@ -457,7 +455,6 @@ init_state(struct posix_acl_state *state, int cnt) int alloc; memset(state, 0, sizeof(struct posix_acl_state)); - state->empty = 1; /* * In the worst case, each individual acl could be for a distinct * named user or group, but we don't know which, so we allocate @@ -500,7 +497,7 @@ posix_state_to_acl(struct posix_acl_state *state, unsigned int flags) * and effective cases: when there are no inheritable ACEs, * calls ->set_acl with a NULL ACL structure. */ - if (state->empty && (flags & NFS4_ACL_TYPE_DEFAULT)) + if (!state->valid && (flags & NFS4_ACL_TYPE_DEFAULT)) return NULL; /* @@ -622,11 +619,12 @@ static void process_one_v4_ace(struct posix_acl_state *state, struct nfs4_ace *ace) { u32 mask = ace->access_mask; + short type = ace2type(ace); int i; - state->empty = 0; + state->valid |= type; - switch (ace2type(ace)) { + switch (type) { case ACL_USER_OBJ: if (ace->type == NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE) { allow_bits(&state->owner, mask); @@ -726,6 +724,30 @@ static int nfs4_acl_nfsv4_to_posix(struct nfs4_acl *acl, if (!(ace->flag & NFS4_ACE_INHERIT_ONLY_ACE)) process_one_v4_ace(&effective_acl_state, ace); } + + /* + * At this point, the default ACL may have zeroed-out entries for owner, + * group and other. That usually results in a non-sensical resulting ACL + * that denies all access except to any ACE that was explicitly added. + * + * The setfacl command solves a similar problem with this logic: + * + * "If a Default ACL entry is created, and the Default ACL contains + * no owner, owning group, or others entry, a copy of the ACL + * owner, owning group, or others entry is added to the Default ACL." + * + * Copy any missing ACEs from the effective set, if any ACEs were + * explicitly set. + */ + if (default_acl_state.valid) { + if (!(default_acl_state.valid & ACL_USER_OBJ)) + default_acl_state.owner = effective_acl_state.owner; + if (!(default_acl_state.valid & ACL_GROUP_OBJ)) + default_acl_state.group = effective_acl_state.group; + if (!(default_acl_state.valid & ACL_OTHER)) + default_acl_state.other = effective_acl_state.other; + } + *pacl = posix_state_to_acl(&effective_acl_state, flags); if (IS_ERR(*pacl)) { ret = PTR_ERR(*pacl); diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 2a815f5a52c4..e00b2aea8da2 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -31,6 +31,7 @@ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */ +#include <linux/nfs4.h> #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/xprt.h> #include <linux/sunrpc/svc_xprt.h> @@ -41,11 +42,10 @@ #include "trace.h" #include "xdr4cb.h" #include "xdr4.h" +#include "nfs4xdr_gen.h" #define NFSDDBG_FACILITY NFSDDBG_PROC -static void nfsd4_mark_cb_fault(struct nfs4_client *, int reason); - #define NFSPROC4_CB_NULL 0 #define NFSPROC4_CB_COMPOUND 1 @@ -84,33 +84,45 @@ static void encode_uint32(struct xdr_stream *xdr, u32 n) static void encode_bitmap4(struct xdr_stream *xdr, const __u32 *bitmap, size_t len) { - WARN_ON_ONCE(xdr_stream_encode_uint32_array(xdr, bitmap, len) < 0); + xdr_stream_encode_uint32_array(xdr, bitmap, len); } -/* - * nfs_cb_opnum4 - * - * enum nfs_cb_opnum4 { - * OP_CB_GETATTR = 3, - * ... - * }; - */ -enum nfs_cb_opnum4 { - OP_CB_GETATTR = 3, - OP_CB_RECALL = 4, - OP_CB_LAYOUTRECALL = 5, - OP_CB_NOTIFY = 6, - OP_CB_PUSH_DELEG = 7, - OP_CB_RECALL_ANY = 8, - OP_CB_RECALLABLE_OBJ_AVAIL = 9, - OP_CB_RECALL_SLOT = 10, - OP_CB_SEQUENCE = 11, - OP_CB_WANTS_CANCELLED = 12, - OP_CB_NOTIFY_LOCK = 13, - OP_CB_NOTIFY_DEVICEID = 14, - OP_CB_OFFLOAD = 15, - OP_CB_ILLEGAL = 10044 -}; +static int decode_cb_fattr4(struct xdr_stream *xdr, uint32_t *bitmap, + struct nfs4_cb_fattr *fattr) +{ + fattr->ncf_cb_change = 0; + fattr->ncf_cb_fsize = 0; + fattr->ncf_cb_atime.tv_sec = 0; + fattr->ncf_cb_atime.tv_nsec = 0; + fattr->ncf_cb_mtime.tv_sec = 0; + fattr->ncf_cb_mtime.tv_nsec = 0; + + if (bitmap[0] & FATTR4_WORD0_CHANGE) + if (xdr_stream_decode_u64(xdr, &fattr->ncf_cb_change) < 0) + return -EIO; + if (bitmap[0] & FATTR4_WORD0_SIZE) + if (xdr_stream_decode_u64(xdr, &fattr->ncf_cb_fsize) < 0) + return -EIO; + if (bitmap[2] & FATTR4_WORD2_TIME_DELEG_ACCESS) { + fattr4_time_deleg_access access; + + if (!xdrgen_decode_fattr4_time_deleg_access(xdr, &access)) + return -EIO; + fattr->ncf_cb_atime.tv_sec = access.seconds; + fattr->ncf_cb_atime.tv_nsec = access.nseconds; + + } + if (bitmap[2] & FATTR4_WORD2_TIME_DELEG_MODIFY) { + fattr4_time_deleg_modify modify; + + if (!xdrgen_decode_fattr4_time_deleg_modify(xdr, &modify)) + return -EIO; + fattr->ncf_cb_mtime.tv_sec = modify.seconds; + fattr->ncf_cb_mtime.tv_nsec = modify.nseconds; + + } + return 0; +} static void encode_nfs_cb_opnum4(struct xdr_stream *xdr, enum nfs_cb_opnum4 op) { @@ -297,17 +309,17 @@ static int decode_cb_compound4res(struct xdr_stream *xdr, u32 length; __be32 *p; - p = xdr_inline_decode(xdr, 4 + 4); + p = xdr_inline_decode(xdr, XDR_UNIT); if (unlikely(p == NULL)) goto out_overflow; - hdr->status = be32_to_cpup(p++); + hdr->status = be32_to_cpup(p); /* Ignore the tag */ - length = be32_to_cpup(p++); - p = xdr_inline_decode(xdr, length + 4); - if (unlikely(p == NULL)) + if (xdr_stream_decode_u32(xdr, &length) < 0) + goto out_overflow; + if (xdr_inline_decode(xdr, length) == NULL) + goto out_overflow; + if (xdr_stream_decode_u32(xdr, &hdr->nops) < 0) goto out_overflow; - p += XDR_QUADLEN(length); - hdr->nops = be32_to_cpup(p); return 0; out_overflow: return -EIO; @@ -358,6 +370,77 @@ encode_cb_recallany4args(struct xdr_stream *xdr, } /* + * CB_GETATTR4args + * struct CB_GETATTR4args { + * nfs_fh4 fh; + * bitmap4 attr_request; + * }; + * + * The size and change attributes are the only one + * guaranteed to be serviced by the client. + */ +static void +encode_cb_getattr4args(struct xdr_stream *xdr, struct nfs4_cb_compound_hdr *hdr, + struct nfs4_cb_fattr *fattr) +{ + struct nfs4_delegation *dp = container_of(fattr, struct nfs4_delegation, dl_cb_fattr); + struct knfsd_fh *fh = &dp->dl_stid.sc_file->fi_fhandle; + struct nfs4_cb_fattr *ncf = &dp->dl_cb_fattr; + u32 bmap_size = 1; + u32 bmap[3]; + + bmap[0] = FATTR4_WORD0_SIZE; + if (!ncf->ncf_file_modified) + bmap[0] |= FATTR4_WORD0_CHANGE; + + if (deleg_attrs_deleg(dp->dl_type)) { + bmap[1] = 0; + bmap[2] = FATTR4_WORD2_TIME_DELEG_ACCESS | FATTR4_WORD2_TIME_DELEG_MODIFY; + bmap_size = 3; + } + encode_nfs_cb_opnum4(xdr, OP_CB_GETATTR); + encode_nfs_fh4(xdr, fh); + encode_bitmap4(xdr, bmap, bmap_size); + hdr->nops++; +} + +static u32 highest_slotid(struct nfsd4_session *ses) +{ + u32 idx; + + spin_lock(&ses->se_lock); + idx = fls(~ses->se_cb_slot_avail); + if (idx > 0) + --idx; + idx = max(idx, ses->se_cb_highest_slot); + spin_unlock(&ses->se_lock); + return idx; +} + +static void +encode_referring_call4(struct xdr_stream *xdr, + const struct nfsd4_referring_call *rc) +{ + encode_uint32(xdr, rc->rc_sequenceid); + encode_uint32(xdr, rc->rc_slotid); +} + +static void +encode_referring_call_list4(struct xdr_stream *xdr, + const struct nfsd4_referring_call_list *rcl) +{ + struct nfsd4_referring_call *rc; + __be32 *p; + + p = xdr_reserve_space(xdr, NFS4_MAX_SESSIONID_LEN); + xdr_encode_opaque_fixed(p, rcl->rcl_sessionid.data, + NFS4_MAX_SESSIONID_LEN); + encode_uint32(xdr, rcl->__nr_referring_calls); + list_for_each_entry(rc, &rcl->rcl_referring_calls, __list) + encode_referring_call4(xdr, rc); +} + +/* * CB_SEQUENCE4args * * struct CB_SEQUENCE4args { @@ -374,6 +457,7 @@ static void encode_cb_sequence4args(struct xdr_stream *xdr, struct nfs4_cb_compound_hdr *hdr) { struct nfsd4_session *session = cb->cb_clp->cl_cb_session; + struct nfsd4_referring_call_list *rcl; __be32 *p; if (hdr->minorversion == 0) @@ -382,16 +466,45 @@ static void encode_cb_sequence4args(struct xdr_stream *xdr, encode_nfs_cb_opnum4(xdr, OP_CB_SEQUENCE); encode_sessionid4(xdr, session); - p = xdr_reserve_space(xdr, 4 + 4 + 4 + 4 + 4); - *p++ = cpu_to_be32(session->se_cb_seq_nr); /* csa_sequenceid */ - *p++ = xdr_zero; /* csa_slotid */ - *p++ = xdr_zero; /* csa_highest_slotid */ + p = xdr_reserve_space(xdr, XDR_UNIT * 4); + *p++ = cpu_to_be32(session->se_cb_seq_nr[cb->cb_held_slot]); /* csa_sequenceid */ + *p++ = cpu_to_be32(cb->cb_held_slot); /* csa_slotid */ + *p++ = cpu_to_be32(highest_slotid(session)); /* csa_highest_slotid */ *p++ = xdr_zero; /* csa_cachethis */ - xdr_encode_empty_array(p); /* csa_referring_call_lists */ + + /* csa_referring_call_lists */ + encode_uint32(xdr, cb->cb_nr_referring_call_list); + list_for_each_entry(rcl, &cb->cb_referring_call_list, __list) + encode_referring_call_list4(xdr, rcl); hdr->nops++; } +static void update_cb_slot_table(struct nfsd4_session *ses, u32 target) +{ + /* No need to do anything if nothing changed */ + if (likely(target == READ_ONCE(ses->se_cb_highest_slot))) + return; + + spin_lock(&ses->se_lock); + if (target > ses->se_cb_highest_slot) { + int i; + + target = min(target, NFSD_BC_SLOT_TABLE_SIZE - 1); + + /* + * Growing the slot table. Reset any new sequences to 1. + * + * NB: There is some debate about whether the RFC requires this, + * but the Linux client expects it. + */ + for (i = ses->se_cb_highest_slot + 1; i <= target; ++i) + ses->se_cb_seq_nr[i] = 1; + } + ses->se_cb_highest_slot = target; + spin_unlock(&ses->se_lock); +} + /* * CB_SEQUENCE4resok * @@ -419,7 +532,7 @@ static int decode_cb_sequence4resok(struct xdr_stream *xdr, struct nfsd4_session *session = cb->cb_clp->cl_cb_session; int status = -ESERVERFAULT; __be32 *p; - u32 dummy; + u32 seqid, slotid, target; /* * If the server returns different values for sessionID, slotID or @@ -435,21 +548,22 @@ static int decode_cb_sequence4resok(struct xdr_stream *xdr, } p += XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN); - dummy = be32_to_cpup(p++); - if (dummy != session->se_cb_seq_nr) { + seqid = be32_to_cpup(p++); + if (seqid != session->se_cb_seq_nr[cb->cb_held_slot]) { dprintk("NFS: %s Invalid sequence number\n", __func__); goto out; } - dummy = be32_to_cpup(p++); - if (dummy != 0) { + slotid = be32_to_cpup(p++); + if (slotid != cb->cb_held_slot) { dprintk("NFS: %s Invalid slotid\n", __func__); goto out; } - /* - * FIXME: process highest slotid and target highest slotid - */ + p++; // ignore current highest slot value + + target = be32_to_cpup(p++); + update_cb_slot_table(session, target); status = 0; out: cb->cb_seq_status = status; @@ -493,6 +607,26 @@ static void nfs4_xdr_enc_cb_null(struct rpc_rqst *req, struct xdr_stream *xdr, } /* + * 20.1. Operation 3: CB_GETATTR - Get Attributes + */ +static void nfs4_xdr_enc_cb_getattr(struct rpc_rqst *req, + struct xdr_stream *xdr, const void *data) +{ + const struct nfsd4_callback *cb = data; + struct nfs4_cb_fattr *ncf = + container_of(cb, struct nfs4_cb_fattr, ncf_getattr); + struct nfs4_cb_compound_hdr hdr = { + .ident = cb->cb_clp->cl_cb_ident, + .minorversion = cb->cb_clp->cl_minorversion, + }; + + encode_cb_compound4args(xdr, &hdr); + encode_cb_sequence4args(xdr, cb, &hdr); + encode_cb_getattr4args(xdr, &hdr, ncf); + encode_cb_nops(&hdr); +} + +/* * 20.2. Operation 4: CB_RECALL - Recall a Delegation */ static void nfs4_xdr_enc_cb_recall(struct rpc_rqst *req, struct xdr_stream *xdr, @@ -548,6 +682,46 @@ static int nfs4_xdr_dec_cb_null(struct rpc_rqst *req, struct xdr_stream *xdr, } /* + * 20.1. Operation 3: CB_GETATTR - Get Attributes + */ +static int nfs4_xdr_dec_cb_getattr(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + void *data) +{ + struct nfsd4_callback *cb = data; + struct nfs4_cb_compound_hdr hdr; + int status; + u32 bitmap[3] = {0}; + u32 attrlen, maxlen; + struct nfs4_cb_fattr *ncf = + container_of(cb, struct nfs4_cb_fattr, ncf_getattr); + + status = decode_cb_compound4res(xdr, &hdr); + if (unlikely(status)) + return status; + + status = decode_cb_sequence4res(xdr, cb); + if (unlikely(status || cb->cb_seq_status)) + return status; + + status = decode_cb_op_status(xdr, OP_CB_GETATTR, &cb->cb_status); + if (unlikely(status || cb->cb_status)) + return status; + if (xdr_stream_decode_uint32_array(xdr, bitmap, 3) < 0) + return -EIO; + if (xdr_stream_decode_u32(xdr, &attrlen) < 0) + return -EIO; + maxlen = sizeof(ncf->ncf_cb_change) + sizeof(ncf->ncf_cb_fsize); + if (bitmap[2] != 0) + maxlen += (sizeof(ncf->ncf_cb_mtime.tv_sec) + + sizeof(ncf->ncf_cb_mtime.tv_nsec)) * 2; + if (attrlen > maxlen) + return -EIO; + status = decode_cb_fattr4(xdr, bitmap, ncf); + return status; +} + +/* * 20.2. Operation 4: CB_RECALL - Recall a Delegation */ static int nfs4_xdr_dec_cb_recall(struct rpc_rqst *rqstp, @@ -698,7 +872,7 @@ static void nfs4_xdr_enc_cb_notify_lock(struct rpc_rqst *req, const struct nfsd4_callback *cb = data; const struct nfsd4_blocked_lock *nbl = container_of(cb, struct nfsd4_blocked_lock, nbl_cb); - struct nfs4_lockowner *lo = (struct nfs4_lockowner *)nbl->nbl_lock.fl_owner; + struct nfs4_lockowner *lo = (struct nfs4_lockowner *)nbl->nbl_lock.c.flc_owner; struct nfs4_cb_compound_hdr hdr = { .ident = 0, .minorversion = cb->cb_clp->cl_minorversion, @@ -855,6 +1029,7 @@ static const struct rpc_procinfo nfs4_cb_procedures[] = { PROC(CB_NOTIFY_LOCK, COMPOUND, cb_notify_lock, cb_notify_lock), PROC(CB_OFFLOAD, COMPOUND, cb_offload, cb_offload), PROC(CB_RECALL_ANY, COMPOUND, cb_recall_any, cb_recall_any), + PROC(CB_GETATTR, COMPOUND, cb_getattr, cb_getattr), }; static unsigned int nfs4_cb_counts[ARRAY_SIZE(nfs4_cb_procedures)]; @@ -907,11 +1082,23 @@ static int max_cb_time(struct net *net) return max(((u32)nn->nfsd4_lease)/10, 1u) * HZ; } -static struct workqueue_struct *callback_wq; - static bool nfsd4_queue_cb(struct nfsd4_callback *cb) { - return queue_work(callback_wq, &cb->cb_work); + struct nfs4_client *clp = cb->cb_clp; + + trace_nfsd_cb_queue(clp, cb); + return queue_work(clp->cl_callback_wq, &cb->cb_work); +} + +static void nfsd4_requeue_cb(struct rpc_task *task, struct nfsd4_callback *cb) +{ + struct nfs4_client *clp = cb->cb_clp; + + if (!test_bit(NFSD4_CLIENT_CB_KILL, &clp->cl_flags)) { + trace_nfsd_cb_restart(clp, cb); + task->tk_status = 0; + set_bit(NFSD4_CALLBACK_REQUEUE, &cb->cb_flags); + } } static void nfsd41_cb_inflight_begin(struct nfs4_client *clp) @@ -922,8 +1109,7 @@ static void nfsd41_cb_inflight_begin(struct nfs4_client *clp) static void nfsd41_cb_inflight_end(struct nfs4_client *clp) { - if (atomic_dec_and_test(&clp->cl_cb_inflight)) - wake_up_var(&clp->cl_cb_inflight); + atomic_dec_and_wake_up(&clp->cl_cb_inflight); } static void nfsd41_cb_inflight_wait_complete(struct nfs4_client *clp) @@ -946,8 +1132,8 @@ static const struct cred *get_backchannel_cred(struct nfs4_client *clp, struct r if (!kcred) return NULL; - kcred->uid = ses->se_cb_sec.uid; - kcred->gid = ses->se_cb_sec.gid; + kcred->fsuid = ses->se_cb_sec.uid; + kcred->fsgid = ses->se_cb_sec.gid; return kcred; } } @@ -986,7 +1172,7 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c args.authflavor = clp->cl_cred.cr_flavor; clp->cl_cb_ident = conn->cb_ident; } else { - if (!conn->cb_xprt) + if (!conn->cb_xprt || !ses) return -EINVAL; clp->cl_cb_session = ses; args.bc_xprt = conn->cb_xprt; @@ -1023,18 +1209,18 @@ static void nfsd4_mark_cb_state(struct nfs4_client *clp, int newstate) { if (clp->cl_cb_state != newstate) { clp->cl_cb_state = newstate; - trace_nfsd_cb_state(clp); + trace_nfsd_cb_new_state(clp); } } -static void nfsd4_mark_cb_down(struct nfs4_client *clp, int reason) +static void nfsd4_mark_cb_down(struct nfs4_client *clp) { if (test_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_flags)) return; nfsd4_mark_cb_state(clp, NFSD4_CB_DOWN); } -static void nfsd4_mark_cb_fault(struct nfs4_client *clp, int reason) +static void nfsd4_mark_cb_fault(struct nfs4_client *clp) { if (test_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_flags)) return; @@ -1046,7 +1232,7 @@ static void nfsd4_cb_probe_done(struct rpc_task *task, void *calldata) struct nfs4_client *clp = container_of(calldata, struct nfs4_client, cl_cb_null); if (task->tk_status) - nfsd4_mark_cb_down(clp, task->tk_status); + nfsd4_mark_cb_down(clp); else nfsd4_mark_cb_state(clp, NFSD4_CB_UP); } @@ -1081,7 +1267,7 @@ void nfsd4_probe_callback(struct nfs4_client *clp) void nfsd4_probe_callback_sync(struct nfs4_client *clp) { nfsd4_probe_callback(clp); - flush_workqueue(callback_wq); + flush_workqueue(clp->cl_callback_wq); } void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *conn) @@ -1092,6 +1278,22 @@ void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *conn) spin_unlock(&clp->cl_lock); } +static int grab_slot(struct nfsd4_session *ses) +{ + int idx; + + spin_lock(&ses->se_lock); + idx = ffs(ses->se_cb_slot_avail) - 1; + if (idx < 0 || idx > ses->se_cb_highest_slot) { + spin_unlock(&ses->se_lock); + return -1; + } + /* clear the bit for the slot */ + ses->se_cb_slot_avail &= ~BIT(idx); + spin_unlock(&ses->se_lock); + return idx; +} + /* * There's currently a single callback channel slot. * If the slot is available, then mark it busy. Otherwise, set the @@ -1100,28 +1302,32 @@ void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *conn) static bool nfsd41_cb_get_slot(struct nfsd4_callback *cb, struct rpc_task *task) { struct nfs4_client *clp = cb->cb_clp; + struct nfsd4_session *ses = clp->cl_cb_session; - if (!cb->cb_holds_slot && - test_and_set_bit(0, &clp->cl_cb_slot_busy) != 0) { + if (cb->cb_held_slot >= 0) + return true; + cb->cb_held_slot = grab_slot(ses); + if (cb->cb_held_slot < 0) { rpc_sleep_on(&clp->cl_cb_waitq, task, NULL); /* Race breaker */ - if (test_and_set_bit(0, &clp->cl_cb_slot_busy) != 0) { - dprintk("%s slot is busy\n", __func__); + cb->cb_held_slot = grab_slot(ses); + if (cb->cb_held_slot < 0) return false; - } rpc_wake_up_queued_task(&clp->cl_cb_waitq, task); } - cb->cb_holds_slot = true; return true; } static void nfsd41_cb_release_slot(struct nfsd4_callback *cb) { struct nfs4_client *clp = cb->cb_clp; + struct nfsd4_session *ses = clp->cl_cb_session; - if (cb->cb_holds_slot) { - cb->cb_holds_slot = false; - clear_bit(0, &clp->cl_cb_slot_busy); + if (cb->cb_held_slot >= 0) { + spin_lock(&ses->se_lock); + ses->se_cb_slot_avail |= BIT(cb->cb_held_slot); + spin_unlock(&ses->se_lock); + cb->cb_held_slot = -1; rpc_wake_up_next(&clp->cl_cb_waitq); } } @@ -1130,16 +1336,115 @@ static void nfsd41_destroy_cb(struct nfsd4_callback *cb) { struct nfs4_client *clp = cb->cb_clp; + trace_nfsd_cb_destroy(clp, cb); nfsd41_cb_release_slot(cb); + if (test_bit(NFSD4_CALLBACK_WAKE, &cb->cb_flags)) + clear_and_wake_up_bit(NFSD4_CALLBACK_RUNNING, &cb->cb_flags); + else + clear_bit(NFSD4_CALLBACK_RUNNING, &cb->cb_flags); + if (cb->cb_ops && cb->cb_ops->release) cb->cb_ops->release(cb); nfsd41_cb_inflight_end(clp); } -/* - * TODO: cb_sequence should support referring call lists, cachethis, multiple - * slots, and mark callback channel down on communication errors. +/** + * nfsd41_cb_referring_call - add a referring call to a callback operation + * @cb: context of callback to add the rc to + * @sessionid: referring call's session ID + * @slotid: referring call's session slot index + * @seqno: referring call's slot sequence number + * + * Caller serializes access to @cb. + * + * NB: If memory allocation fails, the referring call is not added. + */ +void nfsd41_cb_referring_call(struct nfsd4_callback *cb, + struct nfs4_sessionid *sessionid, + u32 slotid, u32 seqno) +{ + struct nfsd4_referring_call_list *rcl; + struct nfsd4_referring_call *rc; + bool found; + + might_sleep(); + + found = false; + list_for_each_entry(rcl, &cb->cb_referring_call_list, __list) { + if (!memcmp(rcl->rcl_sessionid.data, sessionid->data, + NFS4_MAX_SESSIONID_LEN)) { + found = true; + break; + } + } + if (!found) { + rcl = kmalloc(sizeof(*rcl), GFP_KERNEL); + if (!rcl) + return; + memcpy(rcl->rcl_sessionid.data, sessionid->data, + NFS4_MAX_SESSIONID_LEN); + rcl->__nr_referring_calls = 0; + INIT_LIST_HEAD(&rcl->rcl_referring_calls); + list_add(&rcl->__list, &cb->cb_referring_call_list); + cb->cb_nr_referring_call_list++; + } + + found = false; + list_for_each_entry(rc, &rcl->rcl_referring_calls, __list) { + if (rc->rc_sequenceid == seqno && rc->rc_slotid == slotid) { + found = true; + break; + } + } + if (!found) { + rc = kmalloc(sizeof(*rc), GFP_KERNEL); + if (!rc) + goto out; + rc->rc_sequenceid = seqno; + rc->rc_slotid = slotid; + rcl->__nr_referring_calls++; + list_add(&rc->__list, &rcl->rcl_referring_calls); + } + +out: + if (!rcl->__nr_referring_calls) { + cb->cb_nr_referring_call_list--; + list_del(&rcl->__list); + kfree(rcl); + } +} + +/** + * nfsd41_cb_destroy_referring_call_list - release referring call info + * @cb: context of a callback that has completed + * + * Callers who allocate referring calls using nfsd41_cb_referring_call() must + * release those resources by calling nfsd41_cb_destroy_referring_call_list. + * + * Caller serializes access to @cb. */ +void nfsd41_cb_destroy_referring_call_list(struct nfsd4_callback *cb) +{ + struct nfsd4_referring_call_list *rcl; + struct nfsd4_referring_call *rc; + + while (!list_empty(&cb->cb_referring_call_list)) { + rcl = list_first_entry(&cb->cb_referring_call_list, + struct nfsd4_referring_call_list, + __list); + + while (!list_empty(&rcl->rcl_referring_calls)) { + rc = list_first_entry(&rcl->rcl_referring_calls, + struct nfsd4_referring_call, + __list); + list_del(&rc->__list); + kfree(rc); + } + list_del(&rcl->__list); + kfree(rcl); + } +} + static void nfsd4_cb_prepare(struct rpc_task *task, void *calldata) { struct nfsd4_callback *cb = calldata; @@ -1150,6 +1455,7 @@ static void nfsd4_cb_prepare(struct rpc_task *task, void *calldata) * cb_seq_status is only set in decode_cb_sequence4res, * and so will remain 1 if an rpc level failure occurs. */ + trace_nfsd_cb_rpc_prepare(clp); cb->cb_seq_status = 1; cb->cb_status = 0; if (minorversion && !nfsd41_cb_get_slot(cb, task)) @@ -1157,31 +1463,17 @@ static void nfsd4_cb_prepare(struct rpc_task *task, void *calldata) rpc_call_start(task); } +/* Returns true if CB_COMPOUND processing should continue */ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback *cb) { - struct nfs4_client *clp = cb->cb_clp; - struct nfsd4_session *session = clp->cl_cb_session; - bool ret = true; - - if (!clp->cl_minorversion) { - /* - * If the backchannel connection was shut down while this - * task was queued, we need to resubmit it after setting up - * a new backchannel connection. - * - * Note that if we lost our callback connection permanently - * the submission code will error out, so we don't need to - * handle that case here. - */ - if (RPC_SIGNALLED(task)) - goto need_restart; - - return true; - } + struct nfsd4_session *session = cb->cb_clp->cl_cb_session; + bool ret = false; - if (!cb->cb_holds_slot) - goto need_restart; + if (cb->cb_held_slot < 0) + goto requeue; + /* This is the operation status code for CB_SEQUENCE */ + trace_nfsd_cb_seq_status(task, cb); switch (cb->cb_seq_status) { case 0: /* @@ -1191,53 +1483,64 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback * If CB_SEQUENCE returns an error, then the state of the slot * (sequence ID, cached reply) MUST NOT change. */ - ++session->se_cb_seq_nr; + ++session->se_cb_seq_nr[cb->cb_held_slot]; + ret = true; break; case -ESERVERFAULT: - ++session->se_cb_seq_nr; - fallthrough; + /* + * Call succeeded, but the session, slot index, or slot + * sequence number in the response do not match the same + * in the server's call. The sequence information is thus + * untrustworthy. + */ + nfsd4_mark_cb_fault(cb->cb_clp); + break; case 1: + /* + * cb_seq_status remains 1 if an RPC Reply was never + * received. NFSD can't know if the client processed + * the CB_SEQUENCE operation. Ask the client to send a + * DESTROY_SESSION to recover. + */ + fallthrough; case -NFS4ERR_BADSESSION: - nfsd4_mark_cb_fault(cb->cb_clp, cb->cb_seq_status); - ret = false; - break; + nfsd4_mark_cb_fault(cb->cb_clp); + goto requeue; case -NFS4ERR_DELAY: - if (!rpc_restart_call(task)) - goto out; - + cb->cb_seq_status = 1; + if (RPC_SIGNALLED(task) || !rpc_restart_call(task)) + goto requeue; rpc_delay(task, 2 * HZ); return false; + case -NFS4ERR_SEQ_MISORDERED: case -NFS4ERR_BADSLOT: + /* + * A SEQ_MISORDERED or BADSLOT error means that the client and + * server are out of sync as to the backchannel parameters. Mark + * the backchannel faulty and restart the RPC, but leak the slot + * so that it's no longer used. + */ + nfsd4_mark_cb_fault(cb->cb_clp); + cb->cb_held_slot = -1; goto retry_nowait; - case -NFS4ERR_SEQ_MISORDERED: - if (session->se_cb_seq_nr != 1) { - session->se_cb_seq_nr = 1; - goto retry_nowait; - } - break; default: - nfsd4_mark_cb_fault(cb->cb_clp, cb->cb_seq_status); - dprintk("%s: unprocessed error %d\n", __func__, - cb->cb_seq_status); + nfsd4_mark_cb_fault(cb->cb_clp); } - + trace_nfsd_cb_free_slot(task, cb); nfsd41_cb_release_slot(cb); - dprintk("%s: freed slot, new seqid=%d\n", __func__, - clp->cl_cb_session->se_cb_seq_nr); - - if (RPC_SIGNALLED(task)) - goto need_restart; -out: return ret; retry_nowait: - if (rpc_restart_call_prepare(task)) - ret = false; - goto out; -need_restart: - if (!test_bit(NFSD4_CLIENT_CB_KILL, &clp->cl_flags)) { - task->tk_status = 0; - cb->cb_need_restart = true; + /* + * RPC_SIGNALLED() means that the rpc_client is being torn down and + * (possibly) recreated. Requeue the call in that case. + */ + if (!RPC_SIGNALLED(task)) { + if (rpc_restart_call_prepare(task)) + return false; } +requeue: + nfsd41_cb_release_slot(cb); + nfsd4_requeue_cb(task, cb); return false; } @@ -1246,11 +1549,28 @@ static void nfsd4_cb_done(struct rpc_task *task, void *calldata) struct nfsd4_callback *cb = calldata; struct nfs4_client *clp = cb->cb_clp; - if (!nfsd4_cb_sequence_done(task, cb)) + trace_nfsd_cb_rpc_done(clp); + + if (!clp->cl_minorversion) { + /* + * If the backchannel connection was shut down while this + * task was queued, we need to resubmit it after setting up + * a new backchannel connection. + * + * Note that if we lost our callback connection permanently + * the submission code will error out, so we don't need to + * handle that case here. + */ + if (RPC_SIGNALLED(task)) + nfsd4_requeue_cb(task, cb); + } else if (!nfsd4_cb_sequence_done(task, cb)) { return; + } if (cb->cb_status) { - WARN_ON_ONCE(task->tk_status); + WARN_ONCE(task->tk_status, + "cb_status=%d tk_status=%d cb_opcode=%d", + cb->cb_status, task->tk_status, cb->cb_ops->opcode); task->tk_status = cb->cb_status; } @@ -1264,7 +1584,7 @@ static void nfsd4_cb_done(struct rpc_task *task, void *calldata) case -EIO: case -ETIMEDOUT: case -EACCES: - nfsd4_mark_cb_down(clp, task->tk_status); + nfsd4_mark_cb_down(clp); } break; default: @@ -1276,7 +1596,9 @@ static void nfsd4_cb_release(void *calldata) { struct nfsd4_callback *cb = calldata; - if (cb->cb_need_restart) + trace_nfsd_cb_rpc_release(cb->cb_clp); + + if (test_bit(NFSD4_CALLBACK_REQUEUE, &cb->cb_flags)) nfsd4_queue_cb(cb); else nfsd41_destroy_cb(cb); @@ -1289,19 +1611,6 @@ static const struct rpc_call_ops nfsd4_cb_ops = { .rpc_release = nfsd4_cb_release, }; -int nfsd4_create_callback_queue(void) -{ - callback_wq = alloc_ordered_workqueue("nfsd4_callbacks", 0); - if (!callback_wq) - return -ENOMEM; - return 0; -} - -void nfsd4_destroy_callback_queue(void) -{ - destroy_workqueue(callback_wq); -} - /* must be called under the state lock */ void nfsd4_shutdown_callback(struct nfs4_client *clp) { @@ -1315,16 +1624,17 @@ void nfsd4_shutdown_callback(struct nfs4_client *clp) * client, destroy the rpc client, and stop: */ nfsd4_run_cb(&clp->cl_cb_null); - flush_workqueue(callback_wq); + flush_workqueue(clp->cl_callback_wq); nfsd41_cb_inflight_wait_complete(clp); } -/* requires cl_lock: */ static struct nfsd4_conn * __nfsd4_find_backchannel(struct nfs4_client *clp) { struct nfsd4_session *s; struct nfsd4_conn *c; + lockdep_assert_held(&clp->cl_lock); + list_for_each_entry(s, &clp->cl_sessions, se_perclnt) { list_for_each_entry(c, &s->se_conns, cn_persession) { if (c->cn_flags & NFS4_CDFC4_BACK) @@ -1336,9 +1646,9 @@ static struct nfsd4_conn * __nfsd4_find_backchannel(struct nfs4_client *clp) /* * Note there isn't a lot of locking in this code; instead we depend on - * the fact that it is run from the callback_wq, which won't run two - * work items at once. So, for example, callback_wq handles all access - * of cl_cb_client and all calls to rpc_create or rpc_shutdown_client. + * the fact that it is run from clp->cl_callback_wq, which won't run two + * work items at once. So, for example, clp->cl_callback_wq handles all + * access of cl_cb_client and all calls to rpc_create or rpc_shutdown_client. */ static void nfsd4_process_cb_update(struct nfsd4_callback *cb) { @@ -1348,11 +1658,14 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb) struct nfsd4_conn *c; int err; + trace_nfsd_cb_bc_update(clp, cb); + /* * This is either an update, or the client dying; in either case, * kill the old client: */ if (clp->cl_cb_client) { + trace_nfsd_cb_bc_shutdown(clp, cb); rpc_shutdown_client(clp->cl_cb_client); clp->cl_cb_client = NULL; put_cred(clp->cl_cb_cred); @@ -1364,13 +1677,15 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb) } if (test_bit(NFSD4_CLIENT_CB_KILL, &clp->cl_flags)) return; + spin_lock(&clp->cl_lock); /* * Only serialized callback code is allowed to clear these * flags; main nfsd code can only set them: */ - BUG_ON(!(clp->cl_flags & NFSD4_CLIENT_CB_FLAG_MASK)); + WARN_ON(!(clp->cl_flags & NFSD4_CLIENT_CB_FLAG_MASK)); clear_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_flags); + memcpy(&conn, &cb->cb_clp->cl_cb_conn, sizeof(struct nfs4_cb_conn)); c = __nfsd4_find_backchannel(clp); if (c) { @@ -1382,7 +1697,7 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb) err = setup_callback_client(clp, &conn, ses); if (err) { - nfsd4_mark_cb_down(clp, err); + nfsd4_mark_cb_down(clp); if (c) svc_xprt_put(c->cn_xprt); return; @@ -1396,21 +1711,19 @@ nfsd4_run_cb_work(struct work_struct *work) container_of(work, struct nfsd4_callback, cb_work); struct nfs4_client *clp = cb->cb_clp; struct rpc_clnt *clnt; - int flags; + int flags, ret; - if (cb->cb_need_restart) { - cb->cb_need_restart = false; - } else { - if (cb->cb_ops && cb->cb_ops->prepare) - cb->cb_ops->prepare(cb); - } + trace_nfsd_cb_start(clp); if (clp->cl_flags & NFSD4_CLIENT_CB_FLAG_MASK) nfsd4_process_cb_update(cb); clnt = clp->cl_cb_client; - if (!clnt) { - /* Callback channel broken, or client killed; give up: */ + if (!clnt || clp->cl_state == NFSD4_COURTESY) { + /* + * Callback channel broken, client killed or + * nfs4_client in courtesy state; give up. + */ nfsd41_destroy_cb(cb); return; } @@ -1424,10 +1737,19 @@ nfsd4_run_cb_work(struct work_struct *work) return; } + if (!test_and_clear_bit(NFSD4_CALLBACK_REQUEUE, &cb->cb_flags)) { + if (cb->cb_ops && cb->cb_ops->prepare) + cb->cb_ops->prepare(cb); + } + cb->cb_msg.rpc_cred = clp->cl_cb_cred; flags = clp->cl_minorversion ? RPC_TASK_NOCONNECT : RPC_TASK_SOFTCONN; - rpc_call_async(clnt, &cb->cb_msg, RPC_TASK_SOFT | flags, - cb->cb_ops ? &nfsd4_cb_ops : &nfsd4_cb_probe_ops, cb); + ret = rpc_call_async(clnt, &cb->cb_msg, RPC_TASK_SOFT | flags, + cb->cb_ops ? &nfsd4_cb_ops : &nfsd4_cb_probe_ops, cb); + if (ret != 0) { + set_bit(NFSD4_CALLBACK_REQUEUE, &cb->cb_flags); + nfsd4_queue_cb(cb); + } } void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp, @@ -1437,12 +1759,13 @@ void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp, cb->cb_msg.rpc_proc = &nfs4_cb_procedures[op]; cb->cb_msg.rpc_argp = cb; cb->cb_msg.rpc_resp = cb; + cb->cb_flags = 0; cb->cb_ops = ops; INIT_WORK(&cb->cb_work, nfsd4_run_cb_work); - cb->cb_seq_status = 1; cb->cb_status = 0; - cb->cb_need_restart = false; - cb->cb_holds_slot = false; + cb->cb_held_slot = -1; + cb->cb_nr_referring_call_list = 0; + INIT_LIST_HEAD(&cb->cb_referring_call_list); } /** diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c index 5e9809aff37e..8cca1329f348 100644 --- a/fs/nfsd/nfs4idmap.c +++ b/fs/nfsd/nfs4idmap.c @@ -240,8 +240,8 @@ idtoname_parse(struct cache_detail *cd, char *buf, int buflen) goto out; /* expiry */ - ent.h.expiry_time = get_expiry(&buf); - if (ent.h.expiry_time == 0) + error = get_expiry(&buf, &ent.h.expiry_time); + if (error) goto out; error = -ENOMEM; @@ -408,8 +408,8 @@ nametoid_parse(struct cache_detail *cd, char *buf, int buflen) memcpy(ent.name, buf1, sizeof(ent.name)); /* expiry */ - ent.h.expiry_time = get_expiry(&buf); - if (ent.h.expiry_time == 0) + error = get_expiry(&buf, &ent.h.expiry_time); + if (error) goto out; /* ID */ @@ -581,6 +581,7 @@ static __be32 idmap_id_to_name(struct xdr_stream *xdr, .id = id, .type = type, }; + __be32 status = nfs_ok; __be32 *p; int ret; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); @@ -593,12 +594,16 @@ static __be32 idmap_id_to_name(struct xdr_stream *xdr, return nfserrno(ret); ret = strlen(item->name); WARN_ON_ONCE(ret > IDMAP_NAMESZ); + p = xdr_reserve_space(xdr, ret + 4); - if (!p) - return nfserr_resource; - p = xdr_encode_opaque(p, item->name, ret); + if (unlikely(!p)) { + status = nfserr_resource; + goto out_put; + } + xdr_encode_opaque(p, item->name, ret); +out_put: cache_put(&item->h, nn->idtoname_cache); - return 0; + return status; } static bool diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index 3564d1c6f610..683bd1130afe 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -25,7 +25,7 @@ static struct kmem_cache *nfs4_layout_cache; static struct kmem_cache *nfs4_layout_stateid_cache; static const struct nfsd4_callback_ops nfsd4_cb_layout_ops; -static const struct lock_manager_operations nfsd4_layouts_lm_ops; +static const struct lease_manager_operations nfsd4_layouts_lm_ops; const struct nfsd4_layout_ops *nfsd4_layout_ops[LAYOUT_TYPE_MAX] = { #ifdef CONFIG_NFSD_FLEXFILELAYOUT @@ -65,7 +65,7 @@ nfsd4_alloc_devid_map(const struct svc_fh *fhp) return; map->fsid_type = fh->fh_fsid_type; - memcpy(&map->fsid, fh->fh_fsid, fsid_len); + memcpy(&map->fsid, fh_fsid(fh), fsid_len); spin_lock(&nfsd_devid_lock); if (fhp->fh_export->ex_devid_map) @@ -75,7 +75,7 @@ nfsd4_alloc_devid_map(const struct svc_fh *fhp) list_for_each_entry(old, &nfsd_devid_hash[i], hash) { if (old->fsid_type != fh->fh_fsid_type) continue; - if (memcmp(old->fsid, fh->fh_fsid, + if (memcmp(old->fsid, fh_fsid(fh), key_len(old->fsid_type))) continue; @@ -120,7 +120,6 @@ nfsd4_set_deviceid(struct nfsd4_deviceid *id, const struct svc_fh *fhp, id->fsid_idx = fhp->fh_export->ex_devid_map->idx; id->generation = device_generation; - id->pad = 0; return 0; } @@ -152,6 +151,23 @@ void nfsd4_setup_layout_type(struct svc_export *exp) #endif } +void nfsd4_close_layout(struct nfs4_layout_stateid *ls) +{ + struct nfsd_file *fl; + + spin_lock(&ls->ls_stid.sc_file->fi_lock); + fl = ls->ls_file; + ls->ls_file = NULL; + spin_unlock(&ls->ls_stid.sc_file->fi_lock); + + if (fl) { + if (!nfsd4_layout_ops[ls->ls_layout_type]->disable_recalls) + kernel_setlease(fl->nf_file, F_UNLCK, NULL, + (void **)&ls); + nfsd_file_put(fl); + } +} + static void nfsd4_free_layout_stateid(struct nfs4_stid *stid) { @@ -169,9 +185,7 @@ nfsd4_free_layout_stateid(struct nfs4_stid *stid) list_del_init(&ls->ls_perfile); spin_unlock(&fp->fi_lock); - if (!nfsd4_layout_ops[ls->ls_layout_type]->disable_recalls) - vfs_setlease(ls->ls_file->nf_file, F_UNLCK, NULL, (void **)&ls); - nfsd_file_put(ls->ls_file); + nfsd4_close_layout(ls); if (ls->ls_recalled) atomic_dec(&ls->ls_stid.sc_file->fi_lo_recalls); @@ -182,27 +196,26 @@ nfsd4_free_layout_stateid(struct nfs4_stid *stid) static int nfsd4_layout_setlease(struct nfs4_layout_stateid *ls) { - struct file_lock *fl; + struct file_lease *fl; int status; if (nfsd4_layout_ops[ls->ls_layout_type]->disable_recalls) return 0; - fl = locks_alloc_lock(); + fl = locks_alloc_lease(); if (!fl) return -ENOMEM; - locks_init_lock(fl); + locks_init_lease(fl); fl->fl_lmops = &nfsd4_layouts_lm_ops; - fl->fl_flags = FL_LAYOUT; - fl->fl_type = F_RDLCK; - fl->fl_end = OFFSET_MAX; - fl->fl_owner = ls; - fl->fl_pid = current->tgid; - fl->fl_file = ls->ls_file->nf_file; - - status = vfs_setlease(fl->fl_file, fl->fl_type, &fl, NULL); + fl->c.flc_flags = FL_LAYOUT; + fl->c.flc_type = F_RDLCK; + fl->c.flc_owner = ls; + fl->c.flc_pid = current->tgid; + fl->c.flc_file = ls->ls_file->nf_file; + + status = kernel_setlease(fl->c.flc_file, fl->c.flc_type, &fl, NULL); if (status) { - locks_free_lock(fl); + locks_free_lease(fl); return status; } BUG_ON(fl != NULL); @@ -236,7 +249,7 @@ nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate, nfsd4_init_cb(&ls->ls_recall, clp, &nfsd4_cb_layout_ops, NFSPROC4_CLNT_CB_LAYOUT); - if (parent->sc_type == NFS4_DELEG_STID) + if (parent->sc_type == SC_TYPE_DELEG) ls->ls_file = nfsd_file_get(fp->fi_deleg_file); else ls->ls_file = find_any_file(fp); @@ -250,7 +263,7 @@ nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate, } spin_lock(&clp->cl_lock); - stp->sc_type = NFS4_LAYOUT_STID; + stp->sc_type = SC_TYPE_LAYOUT; list_add(&ls->ls_perclnt, &clp->cl_lo_states); spin_unlock(&clp->cl_lock); @@ -269,13 +282,13 @@ nfsd4_preprocess_layout_stateid(struct svc_rqst *rqstp, { struct nfs4_layout_stateid *ls; struct nfs4_stid *stid; - unsigned char typemask = NFS4_LAYOUT_STID; + unsigned short typemask = SC_TYPE_LAYOUT; __be32 status; if (create) - typemask |= (NFS4_OPEN_STID | NFS4_LOCK_STID | NFS4_DELEG_STID); + typemask |= (SC_TYPE_OPEN | SC_TYPE_LOCK | SC_TYPE_DELEG); - status = nfsd4_lookup_stateid(cstate, stateid, typemask, &stid, + status = nfsd4_lookup_stateid(cstate, stateid, typemask, 0, &stid, net_generic(SVC_NET(rqstp), nfsd_net_id)); if (status) goto out; @@ -286,7 +299,7 @@ nfsd4_preprocess_layout_stateid(struct svc_rqst *rqstp, goto out_put_stid; } - if (stid->sc_type != NFS4_LAYOUT_STID) { + if (stid->sc_type != SC_TYPE_LAYOUT) { ls = nfsd4_alloc_layout_stateid(cstate, stid, layout_type); nfs4_put_stid(stid); @@ -323,16 +336,17 @@ nfsd4_recall_file_layout(struct nfs4_layout_stateid *ls) if (ls->ls_recalled) goto out_unlock; - ls->ls_recalled = true; - atomic_inc(&ls->ls_stid.sc_file->fi_lo_recalls); if (list_empty(&ls->ls_layouts)) goto out_unlock; + ls->ls_recalled = true; + atomic_inc(&ls->ls_stid.sc_file->fi_lo_recalls); trace_nfsd_layout_recall(&ls->ls_stid.sc_stateid); - refcount_inc(&ls->ls_stid.sc_count); - nfsd4_run_cb(&ls->ls_recall); - + if (!test_and_set_bit(NFSD4_CALLBACK_RUNNING, &ls->ls_recall.cb_flags)) { + refcount_inc(&ls->ls_stid.sc_count); + nfsd4_run_cb(&ls->ls_recall); + } out_unlock: spin_unlock(&ls->ls_lock); } @@ -515,11 +529,11 @@ nfsd4_return_file_layouts(struct svc_rqst *rqstp, if (!list_empty(&ls->ls_layouts)) { if (found) nfs4_inc_and_copy_stateid(&lrp->lr_sid, &ls->ls_stid); - lrp->lrs_present = 1; + lrp->lrs_present = true; } else { trace_nfsd_layoutstate_unhash(&ls->ls_stid.sc_stateid); - nfs4_unhash_stid(&ls->ls_stid); - lrp->lrs_present = 0; + ls->ls_stid.sc_status |= SC_STATUS_CLOSED; + lrp->lrs_present = false; } spin_unlock(&ls->ls_lock); @@ -539,7 +553,7 @@ nfsd4_return_client_layouts(struct svc_rqst *rqstp, struct nfs4_layout *lp, *t; LIST_HEAD(reaplist); - lrp->lrs_present = 0; + lrp->lrs_present = false; spin_lock(&clp->cl_lock); list_for_each_entry_safe(ls, n, &clp->cl_lo_states, ls_perclnt) { @@ -605,7 +619,7 @@ nfsd4_return_all_file_layouts(struct nfs4_client *clp, struct nfs4_file *fp) } static void -nfsd4_cb_layout_fail(struct nfs4_layout_stateid *ls) +nfsd4_cb_layout_fail(struct nfs4_layout_stateid *ls, struct nfsd_file *file) { struct nfs4_client *clp = ls->ls_stid.sc_client; char addr_str[INET6_ADDRSTRLEN]; @@ -627,7 +641,7 @@ nfsd4_cb_layout_fail(struct nfs4_layout_stateid *ls) argv[0] = (char *)nfsd_recall_failed; argv[1] = addr_str; - argv[2] = ls->ls_file->nf_file->f_path.mnt->mnt_sb->s_id; + argv[2] = file->nf_file->f_path.mnt->mnt_sb->s_id; argv[3] = NULL; error = call_usermodehelper(nfsd_recall_failed, argv, envp, @@ -657,6 +671,7 @@ nfsd4_cb_layout_done(struct nfsd4_callback *cb, struct rpc_task *task) struct nfsd_net *nn; ktime_t now, cutoff; const struct nfsd4_layout_ops *ops; + struct nfsd_file *fl; trace_nfsd_cb_layout_done(&ls->ls_stid.sc_stateid, task); switch (task->tk_status) { @@ -688,12 +703,17 @@ nfsd4_cb_layout_done(struct nfsd4_callback *cb, struct rpc_task *task) * Unknown error or non-responding client, we'll need to fence. */ trace_nfsd_layout_recall_fail(&ls->ls_stid.sc_stateid); - - ops = nfsd4_layout_ops[ls->ls_layout_type]; - if (ops->fence_client) - ops->fence_client(ls); - else - nfsd4_cb_layout_fail(ls); + rcu_read_lock(); + fl = nfsd_file_get(ls->ls_file); + rcu_read_unlock(); + if (fl) { + ops = nfsd4_layout_ops[ls->ls_layout_type]; + if (ops->fence_client) + ops->fence_client(ls, fl); + else + nfsd4_cb_layout_fail(ls, fl); + nfsd_file_put(fl); + } return 1; case -NFS4ERR_NOMATCHING_LAYOUT: trace_nfsd_layout_recall_done(&ls->ls_stid.sc_stateid); @@ -720,10 +740,11 @@ static const struct nfsd4_callback_ops nfsd4_cb_layout_ops = { .prepare = nfsd4_cb_layout_prepare, .done = nfsd4_cb_layout_done, .release = nfsd4_cb_layout_release, + .opcode = OP_CB_LAYOUTRECALL, }; static bool -nfsd4_layout_lm_break(struct file_lock *fl) +nfsd4_layout_lm_break(struct file_lease *fl) { /* * We don't want the locks code to timeout the lease for us; @@ -731,19 +752,19 @@ nfsd4_layout_lm_break(struct file_lock *fl) * in time: */ fl->fl_break_time = 0; - nfsd4_recall_file_layout(fl->fl_owner); + nfsd4_recall_file_layout(fl->c.flc_owner); return false; } static int -nfsd4_layout_lm_change(struct file_lock *onlist, int arg, +nfsd4_layout_lm_change(struct file_lease *onlist, int arg, struct list_head *dispose) { BUG_ON(!(arg & F_UNLCK)); return lease_modify(onlist, arg, dispose); } -static const struct lock_manager_operations nfsd4_layouts_lm_ops = { +static const struct lease_manager_operations nfsd4_layouts_lm_ops = { .lm_break = nfsd4_layout_lm_break, .lm_change = nfsd4_layout_lm_change, }; @@ -756,13 +777,11 @@ nfsd4_init_pnfs(void) for (i = 0; i < DEVID_HASH_SIZE; i++) INIT_LIST_HEAD(&nfsd_devid_hash[i]); - nfs4_layout_cache = kmem_cache_create("nfs4_layout", - sizeof(struct nfs4_layout), 0, 0, NULL); + nfs4_layout_cache = KMEM_CACHE(nfs4_layout, 0); if (!nfs4_layout_cache) return -ENOMEM; - nfs4_layout_stateid_cache = kmem_cache_create("nfs4_layout_stateid", - sizeof(struct nfs4_layout_stateid), 0, 0, NULL); + nfs4_layout_stateid_cache = KMEM_CACHE(nfs4_layout_stateid, 0); if (!nfs4_layout_stateid_cache) { kmem_cache_destroy(nfs4_layout_cache); return -ENOMEM; diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index f189ba7995f5..b74800917583 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -57,6 +57,8 @@ module_param(inter_copy_offload_enable, bool, 0644); MODULE_PARM_DESC(inter_copy_offload_enable, "Enable inter server to server copy offload. Default: false"); +static void cleanup_async_copy(struct nfsd4_copy *copy); + #ifdef CONFIG_NFSD_V4_2_INTER_SSC static int nfsd4_ssc_umount_timeout = 900000; /* default to 15 mins */ module_param(nfsd4_ssc_umount_timeout, int, 0644); @@ -158,7 +160,7 @@ do_open_permission(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfs return fh_verify(rqstp, current_fh, S_IFREG, accmode); } -static __be32 nfsd_check_obj_isreg(struct svc_fh *fh) +static __be32 nfsd_check_obj_isreg(struct svc_fh *fh, u32 minor_version) { umode_t mode = d_inode(fh->fh_dentry)->i_mode; @@ -166,14 +168,15 @@ static __be32 nfsd_check_obj_isreg(struct svc_fh *fh) return nfs_ok; if (S_ISDIR(mode)) return nfserr_isdir; - /* - * Using err_symlink as our catch-all case may look odd; but - * there's no other obvious error for this case in 4.0, and we - * happen to know that it will cause the linux v4 client to do - * the right thing on attempts to open something other than a - * regular file. - */ - return nfserr_symlink; + if (S_ISLNK(mode)) + return nfserr_symlink; + + /* RFC 7530 - 16.16.6 */ + if (minor_version == 0) + return nfserr_symlink; + else + return nfserr_wrong_type; + } static void nfsd4_set_open_owner_reply_cache(struct nfsd4_compound_state *cstate, struct nfsd4_open *open, struct svc_fh *resfh) @@ -261,12 +264,11 @@ nfsd4_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, if (is_create_with_attrs(open)) nfsd4_acl_to_attr(NF4REG, open->op_acl, &attrs); - inode_lock_nested(inode, I_MUTEX_PARENT); - - child = lookup_one_len(open->op_fname, parent, open->op_fnamelen); + child = start_creating(&nop_mnt_idmap, parent, + &QSTR_LEN(open->op_fname, open->op_fnamelen)); if (IS_ERR(child)) { status = nfserrno(PTR_ERR(child)); - goto out; + goto out_write; } if (d_really_is_negative(child)) { @@ -297,12 +299,12 @@ nfsd4_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, } if (d_really_is_positive(child)) { - status = nfs_ok; - /* NFSv4 protocol requires change attributes even though * no change happened. */ - fh_fill_both_attrs(fhp); + status = fh_fill_both_attrs(fhp); + if (status != nfs_ok) + goto out; switch (open->op_createmode) { case NFS4_CREATE_UNCHECKED: @@ -322,8 +324,8 @@ nfsd4_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, status = nfserr_exist; break; case NFS4_CREATE_EXCLUSIVE: - if (d_inode(child)->i_mtime.tv_sec == v_mtime && - d_inode(child)->i_atime.tv_sec == v_atime && + if (inode_get_mtime_sec(d_inode(child)) == v_mtime && + inode_get_atime_sec(d_inode(child)) == v_atime && d_inode(child)->i_size == 0) { open->op_created = true; break; /* subtle */ @@ -331,8 +333,8 @@ nfsd4_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, status = nfserr_exist; break; case NFS4_CREATE_EXCLUSIVE4_1: - if (d_inode(child)->i_mtime.tv_sec == v_mtime && - d_inode(child)->i_atime.tv_sec == v_atime && + if (inode_get_mtime_sec(d_inode(child)) == v_mtime && + inode_get_atime_sec(d_inode(child)) == v_atime && d_inode(child)->i_size == 0) { open->op_created = true; goto set_attr; /* subtle */ @@ -345,7 +347,9 @@ nfsd4_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, if (!IS_POSIXACL(inode)) iap->ia_mode &= ~current_umask(); - fh_fill_pre_attrs(fhp); + status = fh_fill_pre_attrs(fhp); + if (status != nfs_ok) + goto out; status = nfsd4_vfs_create(fhp, child, open); if (status != nfs_ok) goto out; @@ -372,14 +376,45 @@ set_attr: if (attrs.na_aclerr) open->op_bmval[0] &= ~FATTR4_WORD0_ACL; out: - inode_unlock(inode); + end_creating(child); nfsd_attrs_free(&attrs); - if (child && !IS_ERR(child)) - dput(child); +out_write: fh_drop_write(fhp); return status; } +/** + * set_change_info - set up the change_info4 for a reply + * @cinfo: pointer to nfsd4_change_info to be populated + * @fhp: pointer to svc_fh to use as source + * + * Many operations in NFSv4 require change_info4 in the reply. This function + * populates that from the info that we (should!) have already collected. In + * the event that we didn't get any pre-attrs, just zero out both. + */ +static void +set_change_info(struct nfsd4_change_info *cinfo, struct svc_fh *fhp) +{ + cinfo->atomic = (u32)(fhp->fh_pre_saved && fhp->fh_post_saved && !fhp->fh_no_atomic_attr); + cinfo->before_change = fhp->fh_pre_change; + cinfo->after_change = fhp->fh_post_change; + + /* + * If fetching the pre-change attributes failed, then we should + * have already failed the whole operation. We could have still + * failed to fetch post-change attributes however. + * + * If we didn't get post-op attrs, just zero-out the after + * field since we don't know what it should be. If the pre_saved + * field isn't set for some reason, throw warning and just copy + * whatever is in the after field. + */ + if (WARN_ON_ONCE(!fhp->fh_pre_saved)) + cinfo->before_change = 0; + if (!fhp->fh_post_saved) + cinfo->after_change = cinfo->before_change + 1; +} + static __be32 do_open_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_open *open, struct svc_fh **resfh) { @@ -424,15 +459,15 @@ do_open_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, stru } else { status = nfsd_lookup(rqstp, current_fh, open->op_fname, open->op_fnamelen, *resfh); - if (!status) + if (status == nfs_ok) /* NFSv4 protocol requires change attributes even though * no change happened. */ - fh_fill_both_attrs(current_fh); + status = fh_fill_both_attrs(current_fh); } if (status) goto out; - status = nfsd_check_obj_isreg(*resfh); + status = nfsd_check_obj_isreg(*resfh, cstate->minorversion); if (status) goto out; @@ -717,15 +752,6 @@ nfsd4_access(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, &access->ac_supported); } -static void gen_boot_verifier(nfs4_verifier *verifier, struct net *net) -{ - __be32 *verf = (__be32 *)verifier->data; - - BUILD_BUG_ON(2*sizeof(*verf) != sizeof(verifier->data)); - - nfsd_copy_write_verifier(verf, net_generic(net, nfsd_net_id)); -} - static __be32 nfsd4_commit(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) @@ -848,6 +874,8 @@ nfsd4_getattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_getattr *getattr = &u->getattr; __be32 status; + trace_nfsd_vfs_getattr(rqstp, &cstate->current_fh); + status = fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_NOP); if (status) return status; @@ -936,8 +964,11 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, * To ensure proper ordering, we therefore turn off zero copy if * the client wants us to do more in this compound: */ - if (!nfsd4_last_compound_op(rqstp)) - clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags); + if (!nfsd4_last_compound_op(rqstp)) { + struct nfsd4_compoundargs *argp = rqstp->rq_argp; + + argp->splice_ok = false; + } /* check stateid */ status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, @@ -953,10 +984,11 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, static void nfsd4_read_release(union nfsd4_op_u *u) { - if (u->read.rd_nf) + if (u->read.rd_nf) { + trace_nfsd_read_done(u->read.rd_rqstp, u->read.rd_fhp, + u->read.rd_offset, u->read.rd_length); nfsd_file_put(u->read.rd_nf); - trace_nfsd_read_done(u->read.rd_rqstp, u->read.rd_fhp, - u->read.rd_offset, u->read.rd_length); + } } static __be32 @@ -967,6 +999,9 @@ nfsd4_readdir(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, u64 cookie = readdir->rd_cookie; static const nfs4_verifier zeroverf; + trace_nfsd_vfs_readdir(rqstp, &cstate->current_fh, + readdir->rd_maxcount, readdir->rd_cookie); + /* no need to check permission - this will be done in nfsd_readdir() */ if (readdir->rd_bmval[1] & NFSD_WRITEONLY_ATTRS_WORD1) @@ -1024,8 +1059,8 @@ nfsd4_rename(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, rename->rn_tname, rename->rn_tnamelen); if (status) return status; - set_change_info(&rename->rn_sinfo, &cstate->current_fh); - set_change_info(&rename->rn_tinfo, &cstate->save_fh); + set_change_info(&rename->rn_sinfo, &cstate->save_fh); + set_change_info(&rename->rn_tinfo, &cstate->current_fh); return nfs_ok; } @@ -1095,6 +1130,35 @@ nfsd4_secinfo_no_name_release(union nfsd4_op_u *u) exp_put(u->secinfo_no_name.sin_exp); } +/* + * Validate that the requested timestamps are within the acceptable range. If + * timestamp appears to be in the future, then it will be clamped to + * current_time(). + */ +static void +vet_deleg_attrs(struct nfsd4_setattr *setattr, struct nfs4_delegation *dp) +{ + struct timespec64 now = current_time(dp->dl_stid.sc_file->fi_inode); + struct iattr *iattr = &setattr->sa_iattr; + + if ((setattr->sa_bmval[2] & FATTR4_WORD2_TIME_DELEG_ACCESS) && + !nfsd4_vet_deleg_time(&iattr->ia_atime, &dp->dl_atime, &now)) + iattr->ia_valid &= ~(ATTR_ATIME | ATTR_ATIME_SET); + + if (setattr->sa_bmval[2] & FATTR4_WORD2_TIME_DELEG_MODIFY) { + if (nfsd4_vet_deleg_time(&iattr->ia_mtime, &dp->dl_mtime, &now)) { + iattr->ia_ctime = iattr->ia_mtime; + if (nfsd4_vet_deleg_time(&iattr->ia_ctime, &dp->dl_ctime, &now)) + dp->dl_setattr = true; + else + iattr->ia_valid &= ~(ATTR_CTIME | ATTR_CTIME_SET); + } else { + iattr->ia_valid &= ~(ATTR_CTIME | ATTR_CTIME_SET | + ATTR_MTIME | ATTR_MTIME_SET); + } + } +} + static __be32 nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) @@ -1104,17 +1168,45 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, .na_iattr = &setattr->sa_iattr, .na_seclabel = &setattr->sa_label, }; + bool save_no_wcc, deleg_attrs; + struct nfs4_stid *st = NULL; struct inode *inode; __be32 status = nfs_ok; int err; - if (setattr->sa_iattr.ia_valid & ATTR_SIZE) { + deleg_attrs = setattr->sa_bmval[2] & (FATTR4_WORD2_TIME_DELEG_ACCESS | + FATTR4_WORD2_TIME_DELEG_MODIFY); + + if (deleg_attrs || (setattr->sa_iattr.ia_valid & ATTR_SIZE)) { + int flags = WR_STATE; + + if (setattr->sa_bmval[2] & FATTR4_WORD2_TIME_DELEG_ACCESS) + flags |= RD_STATE; + status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, &setattr->sa_stateid, - WR_STATE, NULL, NULL); + flags, NULL, &st); if (status) return status; } + + if (deleg_attrs) { + status = nfserr_bad_stateid; + if (st->sc_type & SC_TYPE_DELEG) { + struct nfs4_delegation *dp = delegstateid(st); + + /* Only for *_ATTRS_DELEG flavors */ + if (deleg_attrs_deleg(dp->dl_type)) { + vet_deleg_attrs(setattr, dp); + status = nfs_ok; + } + } + } + if (st) + nfs4_put_stid(st); + if (status) + return status; + err = fh_want_write(&cstate->current_fh); if (err) return nfserrno(err); @@ -1131,8 +1223,10 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (status) goto out; - status = nfsd_setattr(rqstp, &cstate->current_fh, &attrs, - 0, (time64_t)0); + save_no_wcc = cstate->current_fh.fh_no_wcc; + cstate->current_fh.fh_no_wcc = true; + status = nfsd_setattr(rqstp, &cstate->current_fh, &attrs, NULL); + cstate->current_fh.fh_no_wcc = save_no_wcc; if (!status) status = nfserrno(attrs.na_labelerr); if (!status) @@ -1143,16 +1237,29 @@ out: return status; } +static void nfsd4_file_mark_deleg_written(struct nfs4_file *fi) +{ + spin_lock(&fi->fi_lock); + if (!list_empty(&fi->fi_delegations)) { + struct nfs4_delegation *dp = list_first_entry(&fi->fi_delegations, + struct nfs4_delegation, dl_perfile); + + if (dp->dl_type == OPEN_DELEGATE_WRITE_ATTRS_DELEG) + dp->dl_written = true; + } + spin_unlock(&fi->fi_lock); +} + static __be32 nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_write *write = &u->write; stateid_t *stateid = &write->wr_stateid; + struct nfs4_stid *stid = NULL; struct nfsd_file *nf = NULL; __be32 status = nfs_ok; unsigned long cnt; - int nvecs; if (write->wr_offset > (u64)OFFSET_MAX || write->wr_offset + write->wr_buflen > (u64)OFFSET_MAX) @@ -1162,18 +1269,19 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, trace_nfsd_write_start(rqstp, &cstate->current_fh, write->wr_offset, cnt); status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, - stateid, WR_STATE, &nf, NULL); + stateid, WR_STATE, &nf, &stid); if (status) return status; - write->wr_how_written = write->wr_stable_how; - - nvecs = svc_fill_write_vector(rqstp, &write->wr_payload); - WARN_ON_ONCE(nvecs > ARRAY_SIZE(rqstp->rq_vec)); + if (stid) { + nfsd4_file_mark_deleg_written(stid->sc_file); + nfs4_put_stid(stid); + } + write->wr_how_written = write->wr_stable_how; status = nfsd_vfs_write(rqstp, &cstate->current_fh, nf, - write->wr_offset, rqstp->rq_vec, nvecs, &cnt, - write->wr_how_written, + write->wr_offset, &write->wr_payload, + &cnt, write->wr_how_written, (__be32 *)write->wr_verifier.data); nfsd_file_put(nf); @@ -1214,8 +1322,10 @@ out: return status; out_put_dst: nfsd_file_put(*dst); + *dst = NULL; out_put_src: nfsd_file_put(*src); + *src = NULL; goto out; } @@ -1242,6 +1352,71 @@ out: return status; } +/** + * nfsd4_has_active_async_copies - Check for ongoing copy operations + * @clp: Client to be checked + * + * NFSD maintains state for async COPY operations after they complete, + * and this state remains in the nfs4_client's async_copies list. + * Ongoing copies should block the destruction of the nfs4_client, but + * completed copies should not. + * + * Return values: + * %true: At least one active async COPY is ongoing + * %false: No active async COPY operations were found + */ +bool nfsd4_has_active_async_copies(struct nfs4_client *clp) +{ + struct nfsd4_copy *copy; + bool result = false; + + spin_lock(&clp->async_lock); + list_for_each_entry(copy, &clp->async_copies, copies) { + if (!test_bit(NFSD4_COPY_F_COMPLETED, ©->cp_flags) && + !test_bit(NFSD4_COPY_F_STOPPED, ©->cp_flags)) { + result = true; + break; + } + } + spin_unlock(&clp->async_lock); + return result; +} + +/** + * nfsd4_async_copy_reaper - Purge completed copies + * @nn: Network namespace with possible active copy information + */ +void nfsd4_async_copy_reaper(struct nfsd_net *nn) +{ + struct nfs4_client *clp; + struct nfsd4_copy *copy; + LIST_HEAD(reaplist); + + spin_lock(&nn->client_lock); + list_for_each_entry(clp, &nn->client_lru, cl_lru) { + struct list_head *pos, *next; + + spin_lock(&clp->async_lock); + list_for_each_safe(pos, next, &clp->async_copies) { + copy = list_entry(pos, struct nfsd4_copy, copies); + if (test_bit(NFSD4_COPY_F_OFFLOAD_DONE, ©->cp_flags)) { + if (--copy->cp_ttl) { + list_del_init(©->copies); + list_add(©->copies, &reaplist); + } + } + } + spin_unlock(&clp->async_lock); + } + spin_unlock(&nn->client_lock); + + while (!list_empty(&reaplist)) { + copy = list_first_entry(&reaplist, struct nfsd4_copy, copies); + list_del_init(©->copies); + cleanup_async_copy(copy); + } +} + static void nfs4_put_copy(struct nfsd4_copy *copy) { if (!refcount_dec_and_test(©->refcount)) @@ -1252,12 +1427,16 @@ static void nfs4_put_copy(struct nfsd4_copy *copy) static void nfsd4_stop_copy(struct nfsd4_copy *copy) { - if (!test_and_set_bit(NFSD4_COPY_F_STOPPED, ©->cp_flags)) + trace_nfsd_copy_async_cancel(copy); + if (!test_and_set_bit(NFSD4_COPY_F_STOPPED, ©->cp_flags)) { kthread_stop(copy->copy_task); + copy->nfserr = nfs_ok; + set_bit(NFSD4_COPY_F_COMPLETED, ©->cp_flags); + } nfs4_put_copy(copy); } -static struct nfsd4_copy *nfsd4_get_copy(struct nfs4_client *clp) +static struct nfsd4_copy *nfsd4_unhash_copy(struct nfs4_client *clp) { struct nfsd4_copy *copy = NULL; @@ -1266,6 +1445,9 @@ static struct nfsd4_copy *nfsd4_get_copy(struct nfs4_client *clp) copy = list_first_entry(&clp->async_copies, struct nfsd4_copy, copies); refcount_inc(©->refcount); + copy->cp_clp = NULL; + if (!list_empty(©->copies)) + list_del_init(©->copies); } spin_unlock(&clp->async_lock); return copy; @@ -1275,7 +1457,7 @@ void nfsd4_shutdown_copy(struct nfs4_client *clp) { struct nfsd4_copy *copy; - while ((copy = nfsd4_get_copy(clp)) != NULL) + while ((copy = nfsd4_unhash_copy(clp)) != NULL) nfsd4_stop_copy(copy); } #ifdef CONFIG_NFSD_V4_2_INTER_SSC @@ -1293,15 +1475,16 @@ extern void nfs_sb_deactive(struct super_block *sb); * setup a work entry in the ssc delayed unmount list. */ static __be32 nfsd4_ssc_setup_dul(struct nfsd_net *nn, char *ipaddr, - struct nfsd4_ssc_umount_item **retwork, struct vfsmount **ss_mnt) + struct nfsd4_ssc_umount_item **nsui, + struct svc_rqst *rqstp) { struct nfsd4_ssc_umount_item *ni = NULL; struct nfsd4_ssc_umount_item *work = NULL; struct nfsd4_ssc_umount_item *tmp; DEFINE_WAIT(wait); + __be32 status = 0; - *ss_mnt = NULL; - *retwork = NULL; + *nsui = NULL; work = kzalloc(sizeof(*work), GFP_KERNEL); try_again: spin_lock(&nn->nfsd_ssc_lock); @@ -1311,12 +1494,11 @@ try_again: /* found a match */ if (ni->nsui_busy) { /* wait - and try again */ - prepare_to_wait(&nn->nfsd_ssc_waitq, &wait, - TASK_INTERRUPTIBLE); + prepare_to_wait(&nn->nfsd_ssc_waitq, &wait, TASK_IDLE); spin_unlock(&nn->nfsd_ssc_lock); /* allow 20secs for mount/unmount for now - revisit */ - if (signal_pending(current) || + if (svc_thread_should_stop(rqstp) || (schedule_timeout(20*HZ) == 0)) { finish_wait(&nn->nfsd_ssc_waitq, &wait); kfree(work); @@ -1325,44 +1507,45 @@ try_again: finish_wait(&nn->nfsd_ssc_waitq, &wait); goto try_again; } - *ss_mnt = ni->nsui_vfsmount; + *nsui = ni; refcount_inc(&ni->nsui_refcnt); spin_unlock(&nn->nfsd_ssc_lock); kfree(work); - /* return vfsmount in ss_mnt */ + /* return vfsmount in (*nsui)->nsui_vfsmount */ return 0; } if (work) { - strscpy(work->nsui_ipaddr, ipaddr, sizeof(work->nsui_ipaddr) - 1); + strscpy(work->nsui_ipaddr, ipaddr, sizeof(work->nsui_ipaddr)); refcount_set(&work->nsui_refcnt, 2); work->nsui_busy = true; list_add_tail(&work->nsui_list, &nn->nfsd_ssc_mount_list); - *retwork = work; - } + *nsui = work; + } else + status = nfserr_resource; spin_unlock(&nn->nfsd_ssc_lock); - return 0; + return status; } -static void nfsd4_ssc_update_dul_work(struct nfsd_net *nn, - struct nfsd4_ssc_umount_item *work, struct vfsmount *ss_mnt) +static void nfsd4_ssc_update_dul(struct nfsd_net *nn, + struct nfsd4_ssc_umount_item *nsui, + struct vfsmount *ss_mnt) { - /* set nsui_vfsmount, clear busy flag and wakeup waiters */ spin_lock(&nn->nfsd_ssc_lock); - work->nsui_vfsmount = ss_mnt; - work->nsui_busy = false; + nsui->nsui_vfsmount = ss_mnt; + nsui->nsui_busy = false; wake_up_all(&nn->nfsd_ssc_waitq); spin_unlock(&nn->nfsd_ssc_lock); } -static void nfsd4_ssc_cancel_dul_work(struct nfsd_net *nn, - struct nfsd4_ssc_umount_item *work) +static void nfsd4_ssc_cancel_dul(struct nfsd_net *nn, + struct nfsd4_ssc_umount_item *nsui) { spin_lock(&nn->nfsd_ssc_lock); - list_del(&work->nsui_list); + list_del(&nsui->nsui_list); wake_up_all(&nn->nfsd_ssc_waitq); spin_unlock(&nn->nfsd_ssc_lock); - kfree(work); + kfree(nsui); } /* @@ -1370,7 +1553,7 @@ static void nfsd4_ssc_cancel_dul_work(struct nfsd_net *nn, */ static __be32 nfsd4_interssc_connect(struct nl4_server *nss, struct svc_rqst *rqstp, - struct vfsmount **mount) + struct nfsd4_ssc_umount_item **nsui) { struct file_system_type *type; struct vfsmount *ss_mnt; @@ -1381,7 +1564,6 @@ nfsd4_interssc_connect(struct nl4_server *nss, struct svc_rqst *rqstp, char *ipaddr, *dev_name, *raw_data; int len, raw_len; __be32 status = nfserr_inval; - struct nfsd4_ssc_umount_item *work = NULL; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); naddr = &nss->u.nl4_addr; @@ -1389,6 +1571,7 @@ nfsd4_interssc_connect(struct nl4_server *nss, struct svc_rqst *rqstp, naddr->addr_len, (struct sockaddr *)&tmp_addr, sizeof(tmp_addr)); + *nsui = NULL; if (tmp_addrlen == 0) goto out_err; @@ -1431,10 +1614,10 @@ nfsd4_interssc_connect(struct nl4_server *nss, struct svc_rqst *rqstp, goto out_free_rawdata; snprintf(dev_name, len + 5, "%s%s%s:/", startsep, ipaddr, endsep); - status = nfsd4_ssc_setup_dul(nn, ipaddr, &work, &ss_mnt); + status = nfsd4_ssc_setup_dul(nn, ipaddr, nsui, rqstp); if (status) goto out_free_devname; - if (ss_mnt) + if ((*nsui)->nsui_vfsmount) goto out_done; /* Use an 'internal' mount: SB_KERNMOUNT -> MNT_INTERNAL */ @@ -1442,15 +1625,12 @@ nfsd4_interssc_connect(struct nl4_server *nss, struct svc_rqst *rqstp, module_put(type->owner); if (IS_ERR(ss_mnt)) { status = nfserr_nodev; - if (work) - nfsd4_ssc_cancel_dul_work(nn, work); + nfsd4_ssc_cancel_dul(nn, *nsui); goto out_free_devname; } - if (work) - nfsd4_ssc_update_dul_work(nn, work, ss_mnt); + nfsd4_ssc_update_dul(nn, *nsui, ss_mnt); out_done: status = 0; - *mount = ss_mnt; out_free_devname: kfree(dev_name); @@ -1474,7 +1654,7 @@ out_err: static __be32 nfsd4_setup_inter_ssc(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_copy *copy, struct vfsmount **mount) + struct nfsd4_copy *copy) { struct svc_fh *s_fh = NULL; stateid_t *s_stid = ©->cp_src_stateid; @@ -1487,7 +1667,7 @@ nfsd4_setup_inter_ssc(struct svc_rqst *rqstp, if (status) goto out; - status = nfsd4_interssc_connect(copy->cp_src, rqstp, mount); + status = nfsd4_interssc_connect(copy->cp_src, rqstp, ©->ss_nsui); if (status) goto out; @@ -1505,45 +1685,26 @@ out: } static void -nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct file *filp, +nfsd4_cleanup_inter_ssc(struct nfsd4_ssc_umount_item *nsui, struct file *filp, struct nfsd_file *dst) { - bool found = false; - long timeout; - struct nfsd4_ssc_umount_item *tmp; - struct nfsd4_ssc_umount_item *ni = NULL; struct nfsd_net *nn = net_generic(dst->nf_net, nfsd_net_id); + long timeout = msecs_to_jiffies(nfsd4_ssc_umount_timeout); nfs42_ssc_close(filp); - nfsd_file_put(dst); fput(filp); - if (!nn) { - mntput(ss_mnt); - return; - } spin_lock(&nn->nfsd_ssc_lock); - timeout = msecs_to_jiffies(nfsd4_ssc_umount_timeout); - list_for_each_entry_safe(ni, tmp, &nn->nfsd_ssc_mount_list, nsui_list) { - if (ni->nsui_vfsmount->mnt_sb == ss_mnt->mnt_sb) { - list_del(&ni->nsui_list); - /* - * vfsmount can be shared by multiple exports, - * decrement refcnt. If the count drops to 1 it - * will be unmounted when nsui_expire expires. - */ - refcount_dec(&ni->nsui_refcnt); - ni->nsui_expire = jiffies + timeout; - list_add_tail(&ni->nsui_list, &nn->nfsd_ssc_mount_list); - found = true; - break; - } - } + list_del(&nsui->nsui_list); + /* + * vfsmount can be shared by multiple exports, + * decrement refcnt. If the count drops to 1 it + * will be unmounted when nsui_expire expires. + */ + refcount_dec(&nsui->nsui_refcnt); + nsui->nsui_expire = jiffies + timeout; + list_add_tail(&nsui->nsui_list, &nn->nfsd_ssc_mount_list); spin_unlock(&nn->nfsd_ssc_lock); - if (!found) { - mntput(ss_mnt); - return; - } } #else /* CONFIG_NFSD_V4_2_INTER_SSC */ @@ -1551,15 +1712,13 @@ nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct file *filp, static __be32 nfsd4_setup_inter_ssc(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_copy *copy, - struct vfsmount **mount) + struct nfsd4_copy *copy) { - *mount = NULL; return nfserr_inval; } static void -nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct file *filp, +nfsd4_cleanup_inter_ssc(struct nfsd4_ssc_umount_item *nsui, struct file *filp, struct nfsd_file *dst) { } @@ -1582,19 +1741,14 @@ nfsd4_setup_intra_ssc(struct svc_rqst *rqstp, ©->nf_dst); } -static void -nfsd4_cleanup_intra_ssc(struct nfsd_file *src, struct nfsd_file *dst) -{ - nfsd_file_put(src); - nfsd_file_put(dst); -} - static void nfsd4_cb_offload_release(struct nfsd4_callback *cb) { struct nfsd4_cb_offload *cbo = container_of(cb, struct nfsd4_cb_offload, co_cb); + struct nfsd4_copy *copy = + container_of(cbo, struct nfsd4_copy, cp_cb_offload); - kfree(cbo); + set_bit(NFSD4_COPY_F_OFFLOAD_DONE, ©->cp_flags); } static int nfsd4_cb_offload_done(struct nfsd4_callback *cb, @@ -1604,12 +1758,21 @@ static int nfsd4_cb_offload_done(struct nfsd4_callback *cb, container_of(cb, struct nfsd4_cb_offload, co_cb); trace_nfsd_cb_offload_done(&cbo->co_res.cb_stateid, task); + switch (task->tk_status) { + case -NFS4ERR_DELAY: + if (cbo->co_retries--) { + rpc_delay(task, HZ / 5); + return 0; + } + } + nfsd41_cb_destroy_referring_call_list(cb); return 1; } static const struct nfsd4_callback_ops nfsd4_cb_offload_ops = { .release = nfsd4_cb_offload_release, - .done = nfsd4_cb_offload_done + .done = nfsd4_cb_offload_done, + .opcode = OP_CB_OFFLOAD, }; static void nfsd4_init_copy_res(struct nfsd4_copy *copy, bool sync) @@ -1618,7 +1781,6 @@ static void nfsd4_init_copy_res(struct nfsd4_copy *copy, bool sync) test_bit(NFSD4_COPY_F_COMMITTED, ©->cp_flags) ? NFS_FILE_SYNC : NFS_UNSTABLE; nfsd4_copy_set_sync(copy, sync); - gen_boot_verifier(©->cp_res.wr_verifier, copy->cp_clp->net); } static ssize_t _nfsd_copy_file_range(struct nfsd4_copy *copy, @@ -1637,6 +1799,7 @@ static ssize_t _nfsd_copy_file_range(struct nfsd4_copy *copy, if (bytes_total == 0) bytes_total = ULLONG_MAX; do { + /* Only async copies can be stopped here */ if (kthread_should_stop()) break; bytes_copied = nfsd_copy_file_range(src, src_pos, dst, dst_pos, @@ -1700,38 +1863,47 @@ static void dup_copy_fields(struct nfsd4_copy *src, struct nfsd4_copy *dst) memcpy(dst->cp_src, src->cp_src, sizeof(struct nl4_server)); memcpy(&dst->stateid, &src->stateid, sizeof(src->stateid)); memcpy(&dst->c_fh, &src->c_fh, sizeof(src->c_fh)); - dst->ss_mnt = src->ss_mnt; + dst->ss_nsui = src->ss_nsui; +} + +static void release_copy_files(struct nfsd4_copy *copy) +{ + if (copy->nf_src) + nfsd_file_put(copy->nf_src); + if (copy->nf_dst) + nfsd_file_put(copy->nf_dst); } static void cleanup_async_copy(struct nfsd4_copy *copy) { nfs4_free_copy_state(copy); - nfsd_file_put(copy->nf_dst); - if (!nfsd4_ssc_is_inter(copy)) - nfsd_file_put(copy->nf_src); - spin_lock(©->cp_clp->async_lock); - list_del(©->copies); - spin_unlock(©->cp_clp->async_lock); + release_copy_files(copy); + if (copy->cp_clp) { + spin_lock(©->cp_clp->async_lock); + if (!list_empty(©->copies)) + list_del_init(©->copies); + spin_unlock(©->cp_clp->async_lock); + } nfs4_put_copy(copy); } -static void nfsd4_send_cb_offload(struct nfsd4_copy *copy, __be32 nfserr) +static void nfsd4_send_cb_offload(struct nfsd4_copy *copy) { - struct nfsd4_cb_offload *cbo; - - cbo = kzalloc(sizeof(*cbo), GFP_KERNEL); - if (!cbo) - return; + struct nfsd4_cb_offload *cbo = ©->cp_cb_offload; memcpy(&cbo->co_res, ©->cp_res, sizeof(copy->cp_res)); memcpy(&cbo->co_fh, ©->fh, sizeof(copy->fh)); - cbo->co_nfserr = nfserr; + cbo->co_nfserr = copy->nfserr; + cbo->co_retries = 5; nfsd4_init_cb(&cbo->co_cb, copy->cp_clp, &nfsd4_cb_offload_ops, NFSPROC4_CLNT_CB_OFFLOAD); + nfsd41_cb_referring_call(&cbo->co_cb, &cbo->co_referring_sessionid, + cbo->co_referring_slotid, + cbo->co_referring_seqno); trace_nfsd_cb_offload(copy->cp_clp, &cbo->co_res.cb_stateid, - &cbo->co_fh, copy->cp_count, nfserr); - nfsd4_run_cb(&cbo->co_cb); + &cbo->co_fh, copy->cp_count, copy->nfserr); + nfsd4_try_run_cb(&cbo->co_cb); } /** @@ -1744,36 +1916,41 @@ static void nfsd4_send_cb_offload(struct nfsd4_copy *copy, __be32 nfserr) static int nfsd4_do_async_copy(void *data) { struct nfsd4_copy *copy = (struct nfsd4_copy *)data; - __be32 nfserr; + trace_nfsd_copy_async(copy); if (nfsd4_ssc_is_inter(copy)) { struct file *filp; - filp = nfs42_ssc_open(copy->ss_mnt, ©->c_fh, - ©->stateid); + filp = nfs42_ssc_open(copy->ss_nsui->nsui_vfsmount, + ©->c_fh, ©->stateid); if (IS_ERR(filp)) { switch (PTR_ERR(filp)) { case -EBADF: - nfserr = nfserr_wrong_type; + copy->nfserr = nfserr_wrong_type; break; default: - nfserr = nfserr_offload_denied; + copy->nfserr = nfserr_offload_denied; } /* ss_mnt will be unmounted by the laundromat */ goto do_callback; } - nfserr = nfsd4_do_copy(copy, filp, copy->nf_dst->nf_file, - false); - nfsd4_cleanup_inter_ssc(copy->ss_mnt, filp, copy->nf_dst); + copy->nfserr = nfsd4_do_copy(copy, filp, copy->nf_dst->nf_file, + false); + nfsd4_cleanup_inter_ssc(copy->ss_nsui, filp, copy->nf_dst); } else { - nfserr = nfsd4_do_copy(copy, copy->nf_src->nf_file, - copy->nf_dst->nf_file, false); - nfsd4_cleanup_intra_ssc(copy->nf_src, copy->nf_dst); + copy->nfserr = nfsd4_do_copy(copy, copy->nf_src->nf_file, + copy->nf_dst->nf_file, false); } do_callback: - nfsd4_send_cb_offload(copy, nfserr); - cleanup_async_copy(copy); + /* The kthread exits forthwith. Ensure that a subsequent + * OFFLOAD_CANCEL won't try to kill it again. */ + set_bit(NFSD4_COPY_F_STOPPED, ©->cp_flags); + + set_bit(NFSD4_COPY_F_COMPLETED, ©->cp_flags); + trace_nfsd_copy_async_done(copy); + nfsd4_send_cb_offload(copy); + atomic_dec(©->cp_nn->pending_async_copies); return 0; } @@ -1781,48 +1958,67 @@ static __be32 nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); + struct nfsd4_copy *async_copy = NULL; struct nfsd4_copy *copy = &u->copy; + struct nfsd42_write_res *result; __be32 status; - struct nfsd4_copy *async_copy = NULL; + result = ©->cp_res; + nfsd_copy_write_verifier((__be32 *)&result->wr_verifier.data, nn); + + copy->cp_clp = cstate->clp; if (nfsd4_ssc_is_inter(copy)) { + trace_nfsd_copy_inter(copy); if (!inter_copy_offload_enable || nfsd4_copy_is_sync(copy)) { status = nfserr_notsupp; goto out; } - status = nfsd4_setup_inter_ssc(rqstp, cstate, copy, - ©->ss_mnt); - if (status) + status = nfsd4_setup_inter_ssc(rqstp, cstate, copy); + if (status) { + trace_nfsd_copy_done(copy, status); return nfserr_offload_denied; + } } else { + trace_nfsd_copy_intra(copy); status = nfsd4_setup_intra_ssc(rqstp, cstate, copy); - if (status) + if (status) { + trace_nfsd_copy_done(copy, status); return status; + } } - copy->cp_clp = cstate->clp; memcpy(©->fh, &cstate->current_fh.fh_handle, sizeof(struct knfsd_fh)); if (nfsd4_copy_is_async(copy)) { - struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); - - status = nfserrno(-ENOMEM); async_copy = kzalloc(sizeof(struct nfsd4_copy), GFP_KERNEL); if (!async_copy) goto out_err; + async_copy->cp_nn = nn; + INIT_LIST_HEAD(&async_copy->copies); + refcount_set(&async_copy->refcount, 1); + async_copy->cp_ttl = NFSD_COPY_INITIAL_TTL; + /* Arbitrary cap on number of pending async copy operations */ + if (atomic_inc_return(&nn->pending_async_copies) > + (int)rqstp->rq_pool->sp_nrthreads) + goto out_dec_async_copy_err; async_copy->cp_src = kmalloc(sizeof(*async_copy->cp_src), GFP_KERNEL); if (!async_copy->cp_src) - goto out_err; + goto out_dec_async_copy_err; if (!nfs4_init_copy_state(nn, copy)) - goto out_err; - refcount_set(&async_copy->refcount, 1); - memcpy(©->cp_res.cb_stateid, ©->cp_stateid.cs_stid, - sizeof(copy->cp_res.cb_stateid)); + goto out_dec_async_copy_err; + memcpy(&result->cb_stateid, ©->cp_stateid.cs_stid, + sizeof(result->cb_stateid)); dup_copy_fields(copy, async_copy); + memcpy(async_copy->cp_cb_offload.co_referring_sessionid.data, + cstate->session->se_sessionid.data, + NFS4_MAX_SESSIONID_LEN); + async_copy->cp_cb_offload.co_referring_slotid = cstate->slot->sl_index; + async_copy->cp_cb_offload.co_referring_seqno = cstate->slot->sl_seqid; async_copy->copy_task = kthread_create(nfsd4_do_async_copy, async_copy, "%s", "copy thread"); if (IS_ERR(async_copy->copy_task)) - goto out_err; + goto out_dec_async_copy_err; spin_lock(&async_copy->cp_clp->async_lock); list_add(&async_copy->copies, &async_copy->cp_clp->async_copies); @@ -1832,38 +2028,57 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, } else { status = nfsd4_do_copy(copy, copy->nf_src->nf_file, copy->nf_dst->nf_file, true); - nfsd4_cleanup_intra_ssc(copy->nf_src, copy->nf_dst); } out: + trace_nfsd_copy_done(copy, status); + release_copy_files(copy); return status; +out_dec_async_copy_err: + if (async_copy) + atomic_dec(&nn->pending_async_copies); out_err: + if (nfsd4_ssc_is_inter(copy)) { + /* + * Source's vfsmount of inter-copy will be unmounted + * by the laundromat. Use copy instead of async_copy + * since async_copy->ss_nsui might not be set yet. + */ + refcount_dec(©->ss_nsui->nsui_refcnt); + } if (async_copy) cleanup_async_copy(async_copy); - status = nfserrno(-ENOMEM); - /* - * source's vfsmount of inter-copy will be unmounted - * by the laundromat - */ + status = nfserr_jukebox; goto out; } -struct nfsd4_copy * -find_async_copy(struct nfs4_client *clp, stateid_t *stateid) +static struct nfsd4_copy * +find_async_copy_locked(struct nfs4_client *clp, stateid_t *stateid) { struct nfsd4_copy *copy; - spin_lock(&clp->async_lock); + lockdep_assert_held(&clp->async_lock); + list_for_each_entry(copy, &clp->async_copies, copies) { if (memcmp(©->cp_stateid.cs_stid, stateid, NFS4_STATEID_SIZE)) continue; - refcount_inc(©->refcount); - spin_unlock(&clp->async_lock); return copy; } - spin_unlock(&clp->async_lock); return NULL; } +static struct nfsd4_copy * +find_async_copy(struct nfs4_client *clp, stateid_t *stateid) +{ + struct nfsd4_copy *copy; + + spin_lock(&clp->async_lock); + copy = find_async_copy_locked(clp, stateid); + if (copy) + refcount_inc(©->refcount); + spin_unlock(&clp->async_lock); + return copy; +} + static __be32 nfsd4_offload_cancel(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, @@ -1891,7 +2106,7 @@ nfsd4_copy_notify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_copy_notify *cn = &u->copy_notify; __be32 status; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); - struct nfs4_stid *stid; + struct nfs4_stid *stid = NULL; struct nfs4_cpntf_state *cps; struct nfs4_client *clp = cstate->clp; @@ -1900,9 +2115,11 @@ nfsd4_copy_notify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, &stid); if (status) return status; + if (!stid) + return nfserr_bad_stateid; - cn->cpn_sec = nn->nfsd4_lease; - cn->cpn_nsec = 0; + cn->cpn_lease_time.tv_sec = nn->nfsd4_lease; + cn->cpn_lease_time.tv_nsec = 0; status = nfserrno(-ENOMEM); cps = nfs4_alloc_init_cpntf_state(nn, stid); @@ -1948,22 +2165,29 @@ nfsd4_fallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, nfsd_file_put(nf); return status; } + static __be32 nfsd4_offload_status(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_offload_status *os = &u->offload_status; - __be32 status = 0; + __be32 status = nfs_ok; struct nfsd4_copy *copy; struct nfs4_client *clp = cstate->clp; - copy = find_async_copy(clp, &os->stateid); + os->completed = false; + spin_lock(&clp->async_lock); + copy = find_async_copy_locked(clp, &os->stateid); if (copy) { os->count = copy->cp_res.wr_bytes_written; - nfs4_put_copy(copy); + if (test_bit(NFSD4_COPY_F_COMPLETED, ©->cp_flags)) { + os->completed = true; + os->status = copy->nfserr; + } } else status = nfserr_bad_stateid; + spin_unlock(&clp->async_lock); return status; } @@ -2108,6 +2332,49 @@ nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, return status == nfserr_same ? nfs_ok : status; } +static __be32 +nfsd4_get_dir_delegation(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) +{ + struct nfsd4_get_dir_delegation *gdd = &u->get_dir_delegation; + struct nfs4_delegation *dd; + struct nfsd_file *nf; + __be32 status; + + status = nfsd_file_acquire_dir(rqstp, &cstate->current_fh, &nf); + if (status != nfs_ok) + return status; + + /* + * RFC 8881, section 18.39.3 says: + * + * "The server may refuse to grant the delegation. In that case, the + * server will return NFS4ERR_DIRDELEG_UNAVAIL." + * + * This is sub-optimal, since it means that the server would need to + * abort compound processing just because the delegation wasn't + * available. RFC8881bis should change this to allow the server to + * return NFS4_OK with a non-fatal status of GDD4_UNAVAIL in this + * situation. + */ + dd = nfsd_get_dir_deleg(cstate, gdd, nf); + nfsd_file_put(nf); + if (IS_ERR(dd)) { + int err = PTR_ERR(dd); + + if (err != -EAGAIN) + return nfserrno(err); + gdd->gddrnf_status = GDD4_UNAVAIL; + return nfs_ok; + } + + gdd->gddrnf_status = GDD4_OK; + memcpy(&gdd->gddr_stateid, &dd->dl_stid.sc_stateid, sizeof(gdd->gddr_stateid)); + nfs4_put_stid(&dd->dl_stid); + return nfs_ok; +} + #ifdef CONFIG_NFSD_PNFS static const struct nfsd4_layout_ops * nfsd4_layout_verify(struct svc_export *exp, unsigned int layout_type) @@ -2150,7 +2417,9 @@ nfsd4_getdeviceinfo(struct svc_rqst *rqstp, return nfserr_noent; } - exp = rqst_exp_find(rqstp, map->fsid_type, map->fsid); + exp = rqst_exp_find(&rqstp->rq_chandle, SVC_NET(rqstp), + rqstp->rq_client, rqstp->rq_gssclient, + map->fsid_type, map->fsid); if (IS_ERR(exp)) { dprintk("%s: could not find device id\n", __func__); return nfserr_noent; @@ -2188,7 +2457,7 @@ nfsd4_layoutget(struct svc_rqst *rqstp, const struct nfsd4_layout_ops *ops; struct nfs4_layout_stateid *ls; __be32 nfserr; - int accmode = NFSD_MAY_READ_IF_EXEC; + int accmode = NFSD_MAY_READ_IF_EXEC | NFSD_MAY_OWNER_OVERRIDE; switch (lgp->lg_seg.iomode) { case IOMODE_READ: @@ -2245,7 +2514,7 @@ nfsd4_layoutget(struct svc_rqst *rqstp, if (atomic_read(&ls->ls_stid.sc_file->fi_lo_recalls)) goto out_put_stid; - nfserr = ops->proc_layoutget(d_inode(current_fh->fh_dentry), + nfserr = ops->proc_layoutget(rqstp, d_inode(current_fh->fh_dentry), current_fh, lgp); if (nfserr) goto out_put_stid; @@ -2269,16 +2538,17 @@ static __be32 nfsd4_layoutcommit(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { + struct net *net = SVC_NET(rqstp); struct nfsd4_layoutcommit *lcp = &u->layoutcommit; const struct nfsd4_layout_seg *seg = &lcp->lc_seg; struct svc_fh *current_fh = &cstate->current_fh; const struct nfsd4_layout_ops *ops; - loff_t new_size = lcp->lc_last_wr + 1; struct inode *inode; struct nfs4_layout_stateid *ls; __be32 nfserr; - nfserr = fh_verify(rqstp, current_fh, 0, NFSD_MAY_WRITE); + nfserr = fh_verify(rqstp, current_fh, 0, + NFSD_MAY_WRITE | NFSD_MAY_OWNER_OVERRIDE); if (nfserr) goto out; @@ -2288,43 +2558,50 @@ nfsd4_layoutcommit(struct svc_rqst *rqstp, goto out; inode = d_inode(current_fh->fh_dentry); - nfserr = nfserr_inval; - if (new_size <= seg->offset) { - dprintk("pnfsd: last write before layout segment\n"); - goto out; + lcp->lc_size_chg = false; + if (lcp->lc_newoffset) { + loff_t new_size = lcp->lc_last_wr + 1; + + nfserr = nfserr_inval; + if (new_size <= seg->offset) + goto out; + if (new_size > seg->offset + seg->length) + goto out; + + if (new_size > i_size_read(inode)) { + lcp->lc_size_chg = true; + lcp->lc_newsize = new_size; + } } - if (new_size > seg->offset + seg->length) { - dprintk("pnfsd: last write beyond layout segment\n"); + + nfserr = nfserr_grace; + if (locks_in_grace(net) && !lcp->lc_reclaim) goto out; - } - if (!lcp->lc_newoffset && new_size > i_size_read(inode)) { - dprintk("pnfsd: layoutcommit beyond EOF\n"); + nfserr = nfserr_no_grace; + if (!locks_in_grace(net) && lcp->lc_reclaim) goto out; - } - nfserr = nfsd4_preprocess_layout_stateid(rqstp, cstate, &lcp->lc_sid, - false, lcp->lc_layout_type, - &ls); - if (nfserr) { - trace_nfsd_layout_commit_lookup_fail(&lcp->lc_sid); - /* fixup error code as per RFC5661 */ - if (nfserr == nfserr_bad_stateid) - nfserr = nfserr_badlayout; - goto out; + if (!lcp->lc_reclaim) { + nfserr = nfsd4_preprocess_layout_stateid(rqstp, cstate, + &lcp->lc_sid, false, lcp->lc_layout_type, &ls); + if (nfserr) { + trace_nfsd_layout_commit_lookup_fail(&lcp->lc_sid); + /* fixup error code as per RFC5661 */ + if (nfserr == nfserr_bad_stateid) + nfserr = nfserr_badlayout; + goto out; + } + + /* LAYOUTCOMMIT does not require any serialization */ + mutex_unlock(&ls->ls_mutex); } - /* LAYOUTCOMMIT does not require any serialization */ - mutex_unlock(&ls->ls_mutex); + nfserr = ops->proc_layoutcommit(inode, rqstp, lcp); - if (new_size > i_size_read(inode)) { - lcp->lc_size_chg = 1; - lcp->lc_newsize = new_size; - } else { - lcp->lc_size_chg = 0; + if (!lcp->lc_reclaim) { + nfsd4_file_mark_deleg_written(ls->ls_stid.sc_file); + nfs4_put_stid(&ls->ls_stid); } - - nfserr = ops->proc_layoutcommit(inode, lcp); - nfs4_put_stid(&ls->ls_stid); out: return nfserr; } @@ -2447,10 +2724,10 @@ nfsd4_proc_null(struct svc_rqst *rqstp) return rpc_success; } -static inline void nfsd4_increment_op_stats(u32 opnum) +static inline void nfsd4_increment_op_stats(struct nfsd_net *nn, u32 opnum) { if (opnum >= FIRST_NFS4_OP && opnum <= LAST_NFS4_OP) - percpu_counter_inc(&nfsdstats.counter[NFSD_STATS_NFS4_OP(opnum)]); + percpu_counter_inc(&nn->counter[NFSD_STATS_NFS4_OP(opnum)]); } static const struct nfsd4_operation nfsd4_ops[]; @@ -2693,6 +2970,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp) if (op->opdesc->op_get_currentstateid) op->opdesc->op_get_currentstateid(cstate, &op->u); op->status = op->opdesc->op_func(rqstp, cstate, &op->u); + trace_nfsd_compound_op_err(rqstp, op->opnum, op->status); /* Only from SEQUENCE */ if (cstate->status == nfserr_replay_cache) { @@ -2709,7 +2987,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp) if (current_fh->fh_export && need_wrongsec_check(rqstp)) - op->status = check_nfsd_access(current_fh->fh_export, rqstp); + op->status = check_nfsd_access(current_fh->fh_export, rqstp, false); } encode_op: if (op->status == nfserr_replay_me) { @@ -2725,7 +3003,7 @@ encode_op: status, nfsd4_op_name(op->opnum)); nfsd4_cstate_clear_replay(cstate); - nfsd4_increment_op_stats(op->opnum); + nfsd4_increment_op_stats(nn, op->opnum); } fh_put(current_fh); @@ -3036,6 +3314,18 @@ static u32 nfsd4_copy_notify_rsize(const struct svc_rqst *rqstp, * sizeof(__be32); } +static u32 nfsd4_get_dir_delegation_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) +{ + return (op_encode_hdr_size + + 1 /* gddr_status */ + + op_encode_verifier_maxsz + + op_encode_stateid_maxsz + + 2 /* gddr_notification */ + + 2 /* gddr_child_attributes */ + + 2 /* gddr_dir_attributes */); +} + #ifdef CONFIG_NFSD_PNFS static u32 nfsd4_getdeviceinfo_rsize(const struct svc_rqst *rqstp, const struct nfsd4_op *op) @@ -3170,6 +3460,7 @@ static const struct nfsd4_operation nfsd4_ops[] = { }, [OP_LOCK] = { .op_func = nfsd4_lock, + .op_release = nfsd4_lock_release, .op_flags = OP_MODIFIES_SOMETHING | OP_NONTRIVIAL_ERROR_ENCODE, .op_name = "OP_LOCK", @@ -3178,6 +3469,7 @@ static const struct nfsd4_operation nfsd4_ops[] = { }, [OP_LOCKT] = { .op_func = nfsd4_lockt, + .op_release = nfsd4_lockt_release, .op_flags = OP_NONTRIVIAL_ERROR_ENCODE, .op_name = "OP_LOCKT", .op_rsize_bop = nfsd4_lock_rsize, @@ -3351,6 +3643,7 @@ static const struct nfsd4_operation nfsd4_ops[] = { /* NFSv4.1 operations */ [OP_EXCHANGE_ID] = { .op_func = nfsd4_exchange_id, + .op_release = nfsd4_exchange_id_release, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP | OP_MODIFIES_SOMETHING, .op_name = "OP_EXCHANGE_ID", @@ -3422,6 +3715,12 @@ static const struct nfsd4_operation nfsd4_ops[] = { .op_get_currentstateid = nfsd4_get_freestateid, .op_rsize_bop = nfsd4_only_status_rsize, }, + [OP_GET_DIR_DELEGATION] = { + .op_func = nfsd4_get_dir_delegation, + .op_flags = OP_MODIFIES_SOMETHING, + .op_name = "OP_GET_DIR_DELEGATION", + .op_rsize_bop = nfsd4_get_dir_delegation_rsize, + }, #ifdef CONFIG_NFSD_PNFS [OP_GETDEVICEINFO] = { .op_func = nfsd4_getdeviceinfo, @@ -3548,7 +3847,8 @@ bool nfsd4_spo_must_allow(struct svc_rqst *rqstp) struct nfs4_op_map *allow = &cstate->clp->cl_spo_must_allow; u32 opiter; - if (!cstate->minorversion) + if (rqstp->rq_procinfo != &nfsd_version4.vs_proc[NFSPROC4_COMPOUND] || + cstate->minorversion == 0) return false; if (cstate->spo_must_allowed) @@ -3614,17 +3914,18 @@ static const struct svc_procedure nfsd_procedures4[2] = { .pc_ressize = sizeof(struct nfsd4_compoundres), .pc_release = nfsd4_release_compoundargs, .pc_cachetype = RC_NOCACHE, - .pc_xdrressize = NFSD_BUFSIZE/4, + .pc_xdrressize = 3+NFSSVC_MAXBLKSIZE/4, .pc_name = "COMPOUND", }, }; -static unsigned int nfsd_count3[ARRAY_SIZE(nfsd_procedures4)]; +static DEFINE_PER_CPU_ALIGNED(unsigned long, + nfsd_count4[ARRAY_SIZE(nfsd_procedures4)]); const struct svc_version nfsd_version4 = { .vs_vers = 4, - .vs_nproc = 2, + .vs_nproc = ARRAY_SIZE(nfsd_procedures4), .vs_proc = nfsd_procedures4, - .vs_count = nfsd_count3, + .vs_count = nfsd_count4, .vs_dispatch = nfsd_dispatch, .vs_xdrsize = NFS4_SVC_XDRSIZE, .vs_rpcb_optnl = true, diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index 78b8cd9651d5..441dfbfe2d2b 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -32,7 +32,8 @@ * */ -#include <crypto/hash.h> +#include <crypto/md5.h> +#include <crypto/sha2.h> #include <linux/file.h> #include <linux/slab.h> #include <linux/namei.h> @@ -66,6 +67,7 @@ struct nfsd4_client_tracking_ops { static const struct nfsd4_client_tracking_ops nfsd4_cld_tracking_ops; static const struct nfsd4_client_tracking_ops nfsd4_cld_tracking_ops_v2; +#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING /* Globals */ static char user_recovery_dirname[PATH_MAX] = "/var/lib/nfs/v4recovery"; @@ -81,110 +83,38 @@ nfs4_save_creds(const struct cred **original_creds) new->fsuid = GLOBAL_ROOT_UID; new->fsgid = GLOBAL_ROOT_GID; *original_creds = override_creds(new); - put_cred(new); return 0; } static void nfs4_reset_creds(const struct cred *original) { - revert_creds(original); + put_cred(revert_creds(original)); } static void -md5_to_hex(char *out, char *md5) +nfs4_make_rec_clidname(char dname[HEXDIR_LEN], const struct xdr_netobj *clname) { - int i; - - for (i=0; i<16; i++) { - unsigned char c = md5[i]; - - *out++ = '0' + ((c&0xf0)>>4) + (c>=0xa0)*('a'-'9'-1); - *out++ = '0' + (c&0x0f) + ((c&0x0f)>=0x0a)*('a'-'9'-1); - } - *out = '\0'; -} - -static int -nfs4_make_rec_clidname(char *dname, const struct xdr_netobj *clname) -{ - struct xdr_netobj cksum; - struct crypto_shash *tfm; - int status; + u8 digest[MD5_DIGEST_SIZE]; dprintk("NFSD: nfs4_make_rec_clidname for %.*s\n", clname->len, clname->data); - tfm = crypto_alloc_shash("md5", 0, 0); - if (IS_ERR(tfm)) { - status = PTR_ERR(tfm); - goto out_no_tfm; - } - - cksum.len = crypto_shash_digestsize(tfm); - cksum.data = kmalloc(cksum.len, GFP_KERNEL); - if (cksum.data == NULL) { - status = -ENOMEM; - goto out; - } - - status = crypto_shash_tfm_digest(tfm, clname->data, clname->len, - cksum.data); - if (status) - goto out; - md5_to_hex(dname, cksum.data); + md5(clname->data, clname->len, digest); - status = 0; -out: - kfree(cksum.data); - crypto_free_shash(tfm); -out_no_tfm: - return status; -} - -/* - * If we had an error generating the recdir name for the legacy tracker - * then warn the admin. If the error doesn't appear to be transient, - * then disable recovery tracking. - */ -static void -legacy_recdir_name_error(struct nfs4_client *clp, int error) -{ - printk(KERN_ERR "NFSD: unable to generate recoverydir " - "name (%d).\n", error); - - /* - * if the algorithm just doesn't exist, then disable the recovery - * tracker altogether. The crypto libs will generally return this if - * FIPS is enabled as well. - */ - if (error == -ENOENT) { - printk(KERN_ERR "NFSD: disabling legacy clientid tracking. " - "Reboot recovery will not function correctly!\n"); - nfsd4_client_tracking_exit(clp->net); - } + static_assert(HEXDIR_LEN == 2 * MD5_DIGEST_SIZE + 1); + sprintf(dname, "%*phN", MD5_DIGEST_SIZE, digest); } static void __nfsd4_create_reclaim_record_grace(struct nfs4_client *clp, - const char *dname, int len, struct nfsd_net *nn) + char *dname, struct nfsd_net *nn) { - struct xdr_netobj name; + struct xdr_netobj name = { .len = strlen(dname), .data = dname }; struct xdr_netobj princhash = { .len = 0, .data = NULL }; struct nfs4_client_reclaim *crp; - name.data = kmemdup(dname, len, GFP_KERNEL); - if (!name.data) { - dprintk("%s: failed to allocate memory for name.data!\n", - __func__); - return; - } - name.len = len; crp = nfs4_client_to_reclaim(name, princhash, nn); - if (!crp) { - kfree(name.data); - return; - } crp->cr_clp = clp; } @@ -202,9 +132,7 @@ nfsd4_create_clid_dir(struct nfs4_client *clp) if (!nn->rec_file) return; - status = nfs4_make_rec_clidname(dname, &clp->cl_name); - if (status) - return legacy_recdir_name_error(clp, status); + nfs4_make_rec_clidname(dname, &clp->cl_name); status = nfs4_save_creds(&original_cred); if (status < 0) @@ -215,13 +143,11 @@ nfsd4_create_clid_dir(struct nfs4_client *clp) goto out_creds; dir = nn->rec_file->f_path.dentry; - /* lock the parent */ - inode_lock(d_inode(dir)); - dentry = lookup_one_len(dname, dir, HEXDIR_LEN-1); + dentry = start_creating(&nop_mnt_idmap, dir, &QSTR(dname)); if (IS_ERR(dentry)) { status = PTR_ERR(dentry); - goto out_unlock; + goto out; } if (d_really_is_positive(dentry)) /* @@ -232,16 +158,16 @@ nfsd4_create_clid_dir(struct nfs4_client *clp) * In the 4.0 case, we should never get here; but we may * as well be forgiving and just succeed silently. */ - goto out_put; - status = vfs_mkdir(&init_user_ns, d_inode(dir), dentry, S_IRWXU); -out_put: - dput(dentry); -out_unlock: - inode_unlock(d_inode(dir)); + goto out_end; + dentry = vfs_mkdir(&nop_mnt_idmap, d_inode(dir), dentry, 0700, NULL); + if (IS_ERR(dentry)) + status = PTR_ERR(dentry); +out_end: + end_creating(dentry); +out: if (status == 0) { if (nn->in_grace) - __nfsd4_create_reclaim_record_grace(clp, dname, - HEXDIR_LEN, nn); + __nfsd4_create_reclaim_record_grace(clp, dname, nn); vfs_fsync(nn->rec_file, 0); } else { printk(KERN_ERR "NFSD: failed to write recovery record" @@ -254,7 +180,7 @@ out_creds: nfs4_reset_creds(original_cred); } -typedef int (recdir_func)(struct dentry *, struct dentry *, struct nfsd_net *); +typedef int (recdir_func)(struct dentry *, char *, struct nfsd_net *); struct name_list { char name[HEXDIR_LEN]; @@ -308,23 +234,14 @@ nfsd4_list_rec_dir(recdir_func *f, struct nfsd_net *nn) } status = iterate_dir(nn->rec_file, &ctx.ctx); - inode_lock_nested(d_inode(dir), I_MUTEX_PARENT); list_for_each_entry_safe(entry, tmp, &ctx.names, list) { - if (!status) { - struct dentry *dentry; - dentry = lookup_one_len(entry->name, dir, HEXDIR_LEN-1); - if (IS_ERR(dentry)) { - status = PTR_ERR(dentry); - break; - } - status = f(dir, dentry, nn); - dput(dentry); - } + if (!status) + status = f(dir, entry->name, nn); + list_del(&entry->list); kfree(entry); } - inode_unlock(d_inode(dir)); nfs4_reset_creds(original_cred); list_for_each_entry_safe(entry, tmp, &ctx.names, list) { @@ -336,28 +253,20 @@ nfsd4_list_rec_dir(recdir_func *f, struct nfsd_net *nn) } static int -nfsd4_unlink_clid_dir(char *name, int namlen, struct nfsd_net *nn) +nfsd4_unlink_clid_dir(char *name, struct nfsd_net *nn) { struct dentry *dir, *dentry; int status; - dprintk("NFSD: nfsd4_unlink_clid_dir. name %.*s\n", namlen, name); + dprintk("NFSD: nfsd4_unlink_clid_dir. name %s\n", name); dir = nn->rec_file->f_path.dentry; - inode_lock_nested(d_inode(dir), I_MUTEX_PARENT); - dentry = lookup_one_len(name, dir, namlen); - if (IS_ERR(dentry)) { - status = PTR_ERR(dentry); - goto out_unlock; - } - status = -ENOENT; - if (d_really_is_negative(dentry)) - goto out; - status = vfs_rmdir(&init_user_ns, d_inode(dir), dentry); -out: - dput(dentry); -out_unlock: - inode_unlock(d_inode(dir)); + dentry = start_removing(&nop_mnt_idmap, dir, &QSTR(name)); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); + + status = vfs_rmdir(&nop_mnt_idmap, d_inode(dir), dentry, NULL); + end_removing(dentry); return status; } @@ -392,9 +301,7 @@ nfsd4_remove_clid_dir(struct nfs4_client *clp) if (!nn->rec_file || !test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags)) return; - status = nfs4_make_rec_clidname(dname, &clp->cl_name); - if (status) - return legacy_recdir_name_error(clp, status); + nfs4_make_rec_clidname(dname, &clp->cl_name); status = mnt_want_write_file(nn->rec_file); if (status) @@ -405,7 +312,7 @@ nfsd4_remove_clid_dir(struct nfs4_client *clp) if (status < 0) goto out_drop_write; - status = nfsd4_unlink_clid_dir(dname, HEXDIR_LEN-1, nn); + status = nfsd4_unlink_clid_dir(dname, nn); nfs4_reset_creds(original_cred); if (status == 0) { vfs_fsync(nn->rec_file, 0); @@ -422,18 +329,19 @@ out: } static int -purge_old(struct dentry *parent, struct dentry *child, struct nfsd_net *nn) +purge_old(struct dentry *parent, char *cname, struct nfsd_net *nn) { int status; + struct dentry *child; struct xdr_netobj name; - if (child->d_name.len != HEXDIR_LEN - 1) { - printk("%s: illegal name %pd in recovery directory\n", - __func__, child); + if (strlen(cname) != HEXDIR_LEN - 1) { + printk("%s: illegal name %s in recovery directory\n", + __func__, cname); /* Keep trying; maybe the others are OK: */ return 0; } - name.data = kmemdup_nul(child->d_name.name, child->d_name.len, GFP_KERNEL); + name.data = kstrdup(cname, GFP_KERNEL); if (!name.data) { dprintk("%s: failed to allocate memory for name.data!\n", __func__); @@ -443,10 +351,17 @@ purge_old(struct dentry *parent, struct dentry *child, struct nfsd_net *nn) if (nfs4_has_reclaimed_state(name, nn)) goto out_free; - status = vfs_rmdir(&init_user_ns, d_inode(parent), child); - if (status) - printk("failed to remove client recovery directory %pd\n", - child); + inode_lock_nested(d_inode(parent), I_MUTEX_PARENT); + child = lookup_one(&nop_mnt_idmap, &QSTR(cname), parent); + if (!IS_ERR(child)) { + status = vfs_rmdir(&nop_mnt_idmap, d_inode(parent), child, NULL); + if (status) + printk("failed to remove client recovery directory %pd\n", + child); + dput(child); + } + inode_unlock(d_inode(parent)); + out_free: kfree(name.data); out: @@ -477,27 +392,18 @@ out: } static int -load_recdir(struct dentry *parent, struct dentry *child, struct nfsd_net *nn) +load_recdir(struct dentry *parent, char *cname, struct nfsd_net *nn) { - struct xdr_netobj name; + struct xdr_netobj name = { .len = HEXDIR_LEN, .data = cname }; struct xdr_netobj princhash = { .len = 0, .data = NULL }; - if (child->d_name.len != HEXDIR_LEN - 1) { - printk("%s: illegal name %pd in recovery directory\n", - __func__, child); + if (strlen(cname) != HEXDIR_LEN - 1) { + printk("%s: illegal name %s in recovery directory\n", + __func__, cname); /* Keep trying; maybe the others are OK: */ return 0; } - name.data = kmemdup_nul(child->d_name.name, child->d_name.len, GFP_KERNEL); - if (!name.data) { - dprintk("%s: failed to allocate memory for name.data!\n", - __func__); - goto out; - } - name.len = HEXDIR_LEN; - if (!nfs4_client_to_reclaim(name, princhash, nn)) - kfree(name.data); -out: + nfs4_client_to_reclaim(name, princhash, nn); return 0; } @@ -658,7 +564,8 @@ nfs4_reset_recoverydir(char *recdir) return status; status = -ENOTDIR; if (d_is_dir(path.dentry)) { - strcpy(user_recovery_dirname, recdir); + strscpy(user_recovery_dirname, recdir, + sizeof(user_recovery_dirname)); status = 0; } path_put(&path); @@ -674,7 +581,6 @@ nfs4_recoverydir(void) static int nfsd4_check_legacy_client(struct nfs4_client *clp) { - int status; char dname[HEXDIR_LEN]; struct nfs4_client_reclaim *crp; struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); @@ -684,11 +590,7 @@ nfsd4_check_legacy_client(struct nfs4_client *clp) if (test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags)) return 0; - status = nfs4_make_rec_clidname(dname, &clp->cl_name); - if (status) { - legacy_recdir_name_error(clp, status); - return status; - } + nfs4_make_rec_clidname(dname, &clp->cl_name); /* look for it in the reclaim hashtable otherwise */ name.data = kmemdup(dname, HEXDIR_LEN, GFP_KERNEL); @@ -720,6 +622,7 @@ static const struct nfsd4_client_tracking_ops nfsd4_legacy_tracking_ops = { .version = 1, .msglen = 0, }; +#endif /* CONFIG_NFSD_LEGACY_CLIENT_TRACKING */ /* Globals */ #define NFSD_PIPE_DIR "nfsd" @@ -731,8 +634,9 @@ struct cld_net { spinlock_t cn_lock; struct list_head cn_list; unsigned int cn_xid; +#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING bool cn_has_legacy; - struct crypto_shash *cn_tfm; +#endif }; struct cld_upcall { @@ -792,8 +696,9 @@ __cld_pipe_inprogress_downcall(const struct cld_msg_v2 __user *cmsg, { uint8_t cmd, princhashlen; struct xdr_netobj name, princhash = { .len = 0, .data = NULL }; + char *namecopy __free(kfree) = NULL; + char *princhashcopy __free(kfree) = NULL; uint16_t namelen; - struct cld_net *cn = nn->cld_net; if (get_user(cmd, &cmsg->cm_cmd)) { dprintk("%s: error when copying cmd from userspace", __func__); @@ -806,19 +711,23 @@ __cld_pipe_inprogress_downcall(const struct cld_msg_v2 __user *cmsg, ci = &cmsg->cm_u.cm_clntinfo; if (get_user(namelen, &ci->cc_name.cn_len)) return -EFAULT; - name.data = memdup_user(&ci->cc_name.cn_id, namelen); - if (IS_ERR(name.data)) - return PTR_ERR(name.data); + if (namelen == 0 || namelen > NFS4_OPAQUE_LIMIT) { + dprintk("%s: invalid namelen (%u)", __func__, namelen); + return -EINVAL; + } + namecopy = memdup_user(&ci->cc_name.cn_id, namelen); + if (IS_ERR(namecopy)) + return PTR_ERR(namecopy); + name.data = namecopy; name.len = namelen; get_user(princhashlen, &ci->cc_princhash.cp_len); if (princhashlen > 0) { - princhash.data = memdup_user( - &ci->cc_princhash.cp_data, - princhashlen); - if (IS_ERR(princhash.data)) { - kfree(name.data); - return PTR_ERR(princhash.data); - } + princhashcopy = memdup_user( + &ci->cc_princhash.cp_data, + princhashlen); + if (IS_ERR(princhashcopy)) + return PTR_ERR(princhashcopy); + princhash.data = princhashcopy; princhash.len = princhashlen; } else princhash.len = 0; @@ -828,21 +737,27 @@ __cld_pipe_inprogress_downcall(const struct cld_msg_v2 __user *cmsg, cnm = &cmsg->cm_u.cm_name; if (get_user(namelen, &cnm->cn_len)) return -EFAULT; - name.data = memdup_user(&cnm->cn_id, namelen); - if (IS_ERR(name.data)) - return PTR_ERR(name.data); + if (namelen == 0 || namelen > NFS4_OPAQUE_LIMIT) { + dprintk("%s: invalid namelen (%u)", __func__, namelen); + return -EINVAL; + } + namecopy = memdup_user(&cnm->cn_id, namelen); + if (IS_ERR(namecopy)) + return PTR_ERR(namecopy); + name.data = namecopy; name.len = namelen; } +#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING if (name.len > 5 && memcmp(name.data, "hash:", 5) == 0) { + struct cld_net *cn = nn->cld_net; + name.len = name.len - 5; - memmove(name.data, name.data + 5, name.len); + name.data = name.data + 5; cn->cn_has_legacy = true; } - if (!nfs4_client_to_reclaim(name, princhash, nn)) { - kfree(name.data); - kfree(princhash.data); +#endif + if (!nfs4_client_to_reclaim(name, princhash, nn)) return -EFAULT; - } return nn->client_tracking_ops->msglen; } return -EFAULT; @@ -931,38 +846,32 @@ static const struct rpc_pipe_ops cld_upcall_ops = { .destroy_msg = cld_pipe_destroy_msg, }; -static struct dentry * +static int nfsd4_cld_register_sb(struct super_block *sb, struct rpc_pipe *pipe) { - struct dentry *dir, *dentry; + struct dentry *dir; + int err; dir = rpc_d_lookup_sb(sb, NFSD_PIPE_DIR); if (dir == NULL) - return ERR_PTR(-ENOENT); - dentry = rpc_mkpipe_dentry(dir, NFSD_CLD_PIPE, NULL, pipe); + return -ENOENT; + err = rpc_mkpipe_dentry(dir, NFSD_CLD_PIPE, NULL, pipe); dput(dir); - return dentry; -} - -static void -nfsd4_cld_unregister_sb(struct rpc_pipe *pipe) -{ - if (pipe->dentry) - rpc_unlink(pipe->dentry); + return err; } -static struct dentry * +static int nfsd4_cld_register_net(struct net *net, struct rpc_pipe *pipe) { struct super_block *sb; - struct dentry *dentry; + int err; sb = rpc_get_sb_net(net); if (!sb) - return NULL; - dentry = nfsd4_cld_register_sb(sb, pipe); + return 0; + err = nfsd4_cld_register_sb(sb, pipe); rpc_put_sb_net(net); - return dentry; + return err; } static void @@ -972,7 +881,7 @@ nfsd4_cld_unregister_net(struct net *net, struct rpc_pipe *pipe) sb = rpc_get_sb_net(net); if (sb) { - nfsd4_cld_unregister_sb(pipe); + rpc_unlink(pipe); rpc_put_sb_net(net); } } @@ -982,7 +891,6 @@ static int __nfsd4_init_cld_pipe(struct net *net) { int ret; - struct dentry *dentry; struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct cld_net *cn; @@ -1003,14 +911,13 @@ __nfsd4_init_cld_pipe(struct net *net) spin_lock_init(&cn->cn_lock); INIT_LIST_HEAD(&cn->cn_list); - dentry = nfsd4_cld_register_net(net, cn->cn_pipe); - if (IS_ERR(dentry)) { - ret = PTR_ERR(dentry); + ret = nfsd4_cld_register_net(net, cn->cn_pipe); + if (unlikely(ret)) goto err_destroy_data; - } - cn->cn_pipe->dentry = dentry; +#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING cn->cn_has_legacy = false; +#endif nn->cld_net = cn; return 0; @@ -1042,8 +949,6 @@ nfsd4_remove_cld_pipe(struct net *net) nfsd4_cld_unregister_net(net, cn->cn_pipe); rpc_destroy_pipe_data(cn->cn_pipe); - if (cn->cn_tfm) - crypto_free_shash(cn->cn_tfm); kfree(nn->cld_net); nn->cld_net = NULL; } @@ -1137,8 +1042,6 @@ nfsd4_cld_create_v2(struct nfs4_client *clp) struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); struct cld_net *cn = nn->cld_net; struct cld_msg_v2 *cmsg; - struct crypto_shash *tfm = cn->cn_tfm; - struct xdr_netobj cksum; char *principal = NULL; /* Don't upcall if it's already stored */ @@ -1161,22 +1064,9 @@ nfsd4_cld_create_v2(struct nfs4_client *clp) else if (clp->cl_cred.cr_principal) principal = clp->cl_cred.cr_principal; if (principal) { - cksum.len = crypto_shash_digestsize(tfm); - cksum.data = kmalloc(cksum.len, GFP_KERNEL); - if (cksum.data == NULL) { - ret = -ENOMEM; - goto out; - } - ret = crypto_shash_tfm_digest(tfm, principal, strlen(principal), - cksum.data); - if (ret) { - kfree(cksum.data); - goto out; - } - cmsg->cm_u.cm_clntinfo.cc_princhash.cp_len = cksum.len; - memcpy(cmsg->cm_u.cm_clntinfo.cc_princhash.cp_data, - cksum.data, cksum.len); - kfree(cksum.data); + sha256(principal, strlen(principal), + cmsg->cm_u.cm_clntinfo.cc_princhash.cp_data); + cmsg->cm_u.cm_clntinfo.cc_princhash.cp_len = SHA256_DIGEST_SIZE; } else cmsg->cm_u.cm_clntinfo.cc_princhash.cp_len = 0; @@ -1186,7 +1076,6 @@ nfsd4_cld_create_v2(struct nfs4_client *clp) set_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags); } -out: free_cld_upcall(cup); out_err: if (ret) @@ -1282,10 +1171,6 @@ nfsd4_cld_check(struct nfs4_client *clp) { struct nfs4_client_reclaim *crp; struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); - struct cld_net *cn = nn->cld_net; - int status; - char dname[HEXDIR_LEN]; - struct xdr_netobj name; /* did we already find that this client is stable? */ if (test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags)) @@ -1296,10 +1181,12 @@ nfsd4_cld_check(struct nfs4_client *clp) if (crp) goto found; - if (cn->cn_has_legacy) { - status = nfs4_make_rec_clidname(dname, &clp->cl_name); - if (status) - return -ENOENT; +#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING + if (nn->cld_net->cn_has_legacy) { + char dname[HEXDIR_LEN]; + struct xdr_netobj name; + + nfs4_make_rec_clidname(dname, &clp->cl_name); name.data = kmemdup(dname, HEXDIR_LEN, GFP_KERNEL); if (!name.data) { @@ -1314,6 +1201,7 @@ nfsd4_cld_check(struct nfs4_client *clp) goto found; } +#endif return -ENOENT; found: crp->cr_clp = clp; @@ -1323,14 +1211,11 @@ found: static int nfsd4_cld_check_v2(struct nfs4_client *clp) { - struct nfs4_client_reclaim *crp; struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); +#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING struct cld_net *cn = nn->cld_net; - int status; - char dname[HEXDIR_LEN]; - struct xdr_netobj name; - struct crypto_shash *tfm = cn->cn_tfm; - struct xdr_netobj cksum; +#endif + struct nfs4_client_reclaim *crp; char *principal = NULL; /* did we already find that this client is stable? */ @@ -1342,10 +1227,12 @@ nfsd4_cld_check_v2(struct nfs4_client *clp) if (crp) goto found; +#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING if (cn->cn_has_legacy) { - status = nfs4_make_rec_clidname(dname, &clp->cl_name); - if (status) - return -ENOENT; + struct xdr_netobj name; + char dname[HEXDIR_LEN]; + + nfs4_make_rec_clidname(dname, &clp->cl_name); name.data = kmemdup(dname, HEXDIR_LEN, GFP_KERNEL); if (!name.data) { @@ -1360,31 +1247,22 @@ nfsd4_cld_check_v2(struct nfs4_client *clp) goto found; } +#endif return -ENOENT; found: if (crp->cr_princhash.len) { + u8 digest[SHA256_DIGEST_SIZE]; + if (clp->cl_cred.cr_raw_principal) principal = clp->cl_cred.cr_raw_principal; else if (clp->cl_cred.cr_principal) principal = clp->cl_cred.cr_principal; if (principal == NULL) return -ENOENT; - cksum.len = crypto_shash_digestsize(tfm); - cksum.data = kmalloc(cksum.len, GFP_KERNEL); - if (cksum.data == NULL) + sha256(principal, strlen(principal), digest); + if (memcmp(crp->cr_princhash.data, digest, + crp->cr_princhash.len)) return -ENOENT; - status = crypto_shash_tfm_digest(tfm, principal, - strlen(principal), cksum.data); - if (status) { - kfree(cksum.data); - return -ENOENT; - } - if (memcmp(crp->cr_princhash.data, cksum.data, - crp->cr_princhash.len)) { - kfree(cksum.data); - return -ENOENT; - } - kfree(cksum.data); } crp->cr_clp = clp; return 0; @@ -1564,7 +1442,6 @@ nfsd4_cld_tracking_init(struct net *net) struct nfsd_net *nn = net_generic(net, nfsd_net_id); bool running; int retries = 10; - struct crypto_shash *tfm; status = nfs4_cld_state_init(net); if (status) @@ -1589,12 +1466,6 @@ nfsd4_cld_tracking_init(struct net *net) status = -ETIMEDOUT; goto err_remove; } - tfm = crypto_alloc_shash("sha256", 0, 0); - if (IS_ERR(tfm)) { - status = PTR_ERR(tfm); - goto err_remove; - } - nn->cld_net->cn_tfm = tfm; status = nfsd4_cld_get_version(nn); if (status == -EOPNOTSUPP) @@ -1663,6 +1534,7 @@ static const struct nfsd4_client_tracking_ops nfsd4_cld_tracking_ops_v2 = { .msglen = sizeof(struct cld_msg_v2), }; +#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING /* upcall via usermodehelper */ static char cltrack_prog[PATH_MAX] = "/sbin/nfsdcltrack"; module_param_string(cltrack_prog, cltrack_prog, sizeof(cltrack_prog), @@ -1733,11 +1605,7 @@ nfsd4_cltrack_legacy_recdir(const struct xdr_netobj *name) return NULL; } - copied = nfs4_make_rec_clidname(result + copied, name); - if (copied) { - kfree(result); - return NULL; - } + nfs4_make_rec_clidname(result + copied, name); return result; } @@ -1880,10 +1748,7 @@ nfsd4_cltrack_upcall_lock(struct nfs4_client *clp) static void nfsd4_cltrack_upcall_unlock(struct nfs4_client *clp) { - smp_mb__before_atomic(); - clear_bit(NFSD4_CLIENT_UPCALL_LOCK, &clp->cl_flags); - smp_mb__after_atomic(); - wake_up_bit(&clp->cl_flags, NFSD4_CLIENT_UPCALL_LOCK); + clear_and_wake_up_bit(NFSD4_CLIENT_UPCALL_LOCK, &clp->cl_flags); } static void @@ -2007,28 +1872,10 @@ static const struct nfsd4_client_tracking_ops nfsd4_umh_tracking_ops = { .msglen = 0, }; -int -nfsd4_client_tracking_init(struct net *net) +static inline int check_for_legacy_methods(int status, struct net *net) { - int status; - struct path path; struct nfsd_net *nn = net_generic(net, nfsd_net_id); - - /* just run the init if it the method is already decided */ - if (nn->client_tracking_ops) - goto do_init; - - /* First, try to use nfsdcld */ - nn->client_tracking_ops = &nfsd4_cld_tracking_ops; - status = nn->client_tracking_ops->init(net); - if (!status) - return status; - if (status != -ETIMEDOUT) { - nn->client_tracking_ops = &nfsd4_cld_tracking_ops_v0; - status = nn->client_tracking_ops->init(net); - if (!status) - return status; - } + struct path path; /* * Next, try the UMH upcall. @@ -2045,20 +1892,51 @@ nfsd4_client_tracking_init(struct net *net) nn->client_tracking_ops = &nfsd4_legacy_tracking_ops; status = kern_path(nfs4_recoverydir(), LOOKUP_FOLLOW, &path); if (!status) { - status = d_is_dir(path.dentry); + status = !d_is_dir(path.dentry); path_put(&path); - if (!status) { - status = -EINVAL; - goto out; - } + if (status) + return -ENOTDIR; + } + return status; +} +#else +static inline int check_for_legacy_methods(int status, struct net *net) +{ + return status; +} +#endif /* CONFIG_LEGACY_NFSD_CLIENT_TRACKING */ + +int +nfsd4_client_tracking_init(struct net *net) +{ + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + int status; + + /* just run the init if it the method is already decided */ + if (nn->client_tracking_ops) + goto do_init; + + /* First, try to use nfsdcld */ + nn->client_tracking_ops = &nfsd4_cld_tracking_ops; + status = nn->client_tracking_ops->init(net); + if (!status) + return status; + if (status != -ETIMEDOUT) { + nn->client_tracking_ops = &nfsd4_cld_tracking_ops_v0; + status = nn->client_tracking_ops->init(net); + if (!status) + return status; } + status = check_for_legacy_methods(status, net); + if (status) + goto out; do_init: status = nn->client_tracking_ops->init(net); out: if (status) { - printk(KERN_WARNING "NFSD: Unable to initialize client " - "recovery tracking! (%d)\n", status); + pr_warn("NFSD: Unable to initialize client recovery tracking! (%d)\n", status); + pr_warn("NFSD: Is nfsdcld running? If not, enable CONFIG_NFSD_LEGACY_CLIENT_TRACKING.\n"); nn->client_tracking_ops = NULL; } return status; @@ -2119,7 +1997,6 @@ rpc_pipefs_event(struct notifier_block *nb, unsigned long event, void *ptr) struct net *net = sb->s_fs_info; struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct cld_net *cn = nn->cld_net; - struct dentry *dentry; int ret = 0; if (!try_module_get(THIS_MODULE)) @@ -2132,16 +2009,10 @@ rpc_pipefs_event(struct notifier_block *nb, unsigned long event, void *ptr) switch (event) { case RPC_PIPEFS_MOUNT: - dentry = nfsd4_cld_register_sb(sb, cn->cn_pipe); - if (IS_ERR(dentry)) { - ret = PTR_ERR(dentry); - break; - } - cn->cn_pipe->dentry = dentry; + ret = nfsd4_cld_register_sb(sb, cn->cn_pipe); break; case RPC_PIPEFS_UMOUNT: - if (cn->cn_pipe->dentry) - nfsd4_cld_unregister_sb(cn->cn_pipe); + rpc_unlink(cn->cn_pipe); break; default: ret = -ENOTSUPP; diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 4ef529379065..808c24fb5c9a 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -59,7 +59,7 @@ #define NFSDDBG_FACILITY NFSDDBG_PROC -#define all_ones {{~0,~0},~0} +#define all_ones {{ ~0, ~0}, ~0} static const stateid_t one_stateid = { .si_generation = ~0, .si_opaque = all_ones, @@ -87,6 +87,7 @@ static void nfs4_free_ol_stateid(struct nfs4_stid *stid); void nfsd4_end_grace(struct nfsd_net *nn); static void _free_cpntf_state_locked(struct nfsd_net *nn, struct nfs4_cpntf_state *cps); static void nfsd4_file_hash_remove(struct nfs4_file *fi); +static void deleg_reaper(struct nfsd_net *nn); /* Locking: */ @@ -127,6 +128,7 @@ static void free_session(struct nfsd4_session *); static const struct nfsd4_callback_ops nfsd4_cb_recall_ops; static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops; +static const struct nfsd4_callback_ops nfsd4_cb_getattr_ops; static struct workqueue_struct *laundry_wq; @@ -147,14 +149,14 @@ void nfsd4_destroy_laundry_wq(void) static bool is_session_dead(struct nfsd4_session *ses) { - return ses->se_flags & NFS4_SESSION_DEAD; + return ses->se_dead; } static __be32 mark_session_dead_locked(struct nfsd4_session *ses, int ref_held_by_me) { if (atomic_read(&ses->se_ref) > ref_held_by_me) return nfserr_jukebox; - ses->se_flags |= NFS4_SESSION_DEAD; + ses->se_dead = true; return nfs_ok; } @@ -297,7 +299,7 @@ find_or_allocate_block(struct nfs4_lockowner *lo, struct knfsd_fh *fh, nbl = find_blocked_lock(lo, fh, nn); if (!nbl) { - nbl= kmalloc(sizeof(*nbl), GFP_KERNEL); + nbl = kmalloc(sizeof(*nbl), GFP_KERNEL); if (nbl) { INIT_LIST_HEAD(&nbl->nbl_list); INIT_LIST_HEAD(&nbl->nbl_lru); @@ -318,6 +320,7 @@ free_nbl(struct kref *kref) struct nfsd4_blocked_lock *nbl; nbl = container_of(kref, struct nfsd4_blocked_lock, nbl_kref); + locks_release_private(&nbl->nbl_lock); kfree(nbl); } @@ -325,7 +328,6 @@ static void free_blocked_lock(struct nfsd4_blocked_lock *nbl) { locks_delete_block(&nbl->nbl_lock); - locks_release_private(&nbl->nbl_lock); kref_put(&nbl->nbl_kref, free_nbl); } @@ -398,6 +400,7 @@ static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops = { .prepare = nfsd4_cb_notify_lock_prepare, .done = nfsd4_cb_notify_lock_done, .release = nfsd4_cb_notify_lock_release, + .opcode = OP_CB_NOTIFY_LOCK, }; /* @@ -539,7 +542,7 @@ same_owner_str(struct nfs4_stateowner *sop, struct xdr_netobj *owner) } static struct nfs4_openowner * -find_openstateowner_str_locked(unsigned int hashval, struct nfsd4_open *open, +find_openstateowner_str(unsigned int hashval, struct nfsd4_open *open, struct nfs4_client *clp) { struct nfs4_stateowner *so; @@ -556,18 +559,6 @@ find_openstateowner_str_locked(unsigned int hashval, struct nfsd4_open *open, return NULL; } -static struct nfs4_openowner * -find_openstateowner_str(unsigned int hashval, struct nfsd4_open *open, - struct nfs4_client *clp) -{ - struct nfs4_openowner *oo; - - spin_lock(&clp->cl_lock); - oo = find_openstateowner_str_locked(hashval, open, clp); - spin_unlock(&clp->cl_lock); - return oo; -} - static inline u32 opaque_hashval(const void *ptr, int nbytes) { @@ -581,13 +572,6 @@ opaque_hashval(const void *ptr, int nbytes) return x; } -static void nfsd4_free_file_rcu(struct rcu_head *rcu) -{ - struct nfs4_file *fp = container_of(rcu, struct nfs4_file, fi_rcu); - - kmem_cache_free(file_slab, fp); -} - void put_nfs4_file(struct nfs4_file *fi) { @@ -595,28 +579,20 @@ put_nfs4_file(struct nfs4_file *fi) nfsd4_file_hash_remove(fi); WARN_ON_ONCE(!list_empty(&fi->fi_clnt_odstate)); WARN_ON_ONCE(!list_empty(&fi->fi_delegations)); - call_rcu(&fi->fi_rcu, nfsd4_free_file_rcu); + kfree_rcu(fi, fi_rcu); } } static struct nfsd_file * -__nfs4_get_fd(struct nfs4_file *f, int oflag) -{ - if (f->fi_fds[oflag]) - return nfsd_file_get(f->fi_fds[oflag]); - return NULL; -} - -static struct nfsd_file * find_writeable_file_locked(struct nfs4_file *f) { struct nfsd_file *ret; lockdep_assert_held(&f->fi_lock); - ret = __nfs4_get_fd(f, O_WRONLY); + ret = nfsd_file_get(f->fi_fds[O_WRONLY]); if (!ret) - ret = __nfs4_get_fd(f, O_RDWR); + ret = nfsd_file_get(f->fi_fds[O_RDWR]); return ret; } @@ -639,9 +615,9 @@ find_readable_file_locked(struct nfs4_file *f) lockdep_assert_held(&f->fi_lock); - ret = __nfs4_get_fd(f, O_RDONLY); + ret = nfsd_file_get(f->fi_fds[O_RDONLY]); if (!ret) - ret = __nfs4_get_fd(f, O_RDWR); + ret = nfsd_file_get(f->fi_fds[O_RDWR]); return ret; } @@ -665,11 +641,11 @@ find_any_file(struct nfs4_file *f) if (!f) return NULL; spin_lock(&f->fi_lock); - ret = __nfs4_get_fd(f, O_RDWR); + ret = nfsd_file_get(f->fi_fds[O_RDWR]); if (!ret) { - ret = __nfs4_get_fd(f, O_WRONLY); + ret = nfsd_file_get(f->fi_fds[O_WRONLY]); if (!ret) - ret = __nfs4_get_fd(f, O_RDONLY); + ret = nfsd_file_get(f->fi_fds[O_RDONLY]); } spin_unlock(&f->fi_lock); return ret; @@ -688,15 +664,6 @@ static struct nfsd_file *find_any_file_locked(struct nfs4_file *f) return NULL; } -static struct nfsd_file *find_deleg_file_locked(struct nfs4_file *f) -{ - lockdep_assert_held(&f->fi_lock); - - if (f->fi_deleg_file) - return f->fi_deleg_file; - return NULL; -} - static atomic_long_t num_delegations; unsigned long max_delegations; @@ -967,15 +934,6 @@ struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *sla spin_lock_init(&stid->sc_lock); INIT_LIST_HEAD(&stid->sc_cp_list); - /* - * It shouldn't be a problem to reuse an opaque stateid value. - * I don't think it is for 4.1. But with 4.0 I worry that, for - * example, a stray write retransmission could be accepted by - * the server when it should have been rejected. Therefore, - * adopt a trick from the sctp code to attempt to maximize the - * amount of time until an id is reused, by ensuring they always - * "increase" (mod INT_MAX): - */ return stid; out_free: kmem_cache_free(slab, stid); @@ -992,7 +950,6 @@ static int nfs4_init_cp_state(struct nfsd_net *nn, copy_stateid_t *stid, stid->cs_stid.si_opaque.so_clid.cl_boot = (u32)nn->boot_time; stid->cs_stid.si_opaque.so_clid.cl_id = nn->s2s_cp_cl_id; - stid->cs_type = cs_type; idr_preload(GFP_KERNEL); spin_lock(&nn->s2s_cp_lock); @@ -1003,6 +960,7 @@ static int nfs4_init_cp_state(struct nfsd_net *nn, copy_stateid_t *stid, idr_preload_end(); if (new_id < 0) return 0; + stid->cs_type = cs_type; return 1; } @@ -1036,7 +994,8 @@ void nfs4_free_copy_state(struct nfsd4_copy *copy) { struct nfsd_net *nn; - WARN_ON_ONCE(copy->cp_stateid.cs_type != NFS4_COPY_STID); + if (copy->cp_stateid.cs_type != NFS4_COPY_STID) + return; nn = net_generic(copy->cp_clp->net, nfsd_net_id); spin_lock(&nn->s2s_cp_lock); idr_remove(&nn->s2s_cp_stateids, @@ -1070,6 +1029,12 @@ static struct nfs4_ol_stateid * nfs4_alloc_open_stateid(struct nfs4_client *clp) return openlockstateid(stid); } +/* + * As the sc_free callback of deleg, this may be called by nfs4_put_stid + * in nfsd_break_one_deleg. + * Considering nfsd_break_one_deleg is called with the flc->flc_lock held, + * this function mustn't ever sleep. + */ static void nfs4_free_deleg(struct nfs4_stid *stid) { struct nfs4_delegation *dp = delegstateid(stid); @@ -1091,7 +1056,8 @@ static void nfs4_free_deleg(struct nfs4_stid *stid) * When a delegation is recalled, the filehandle is stored in the "new" * filter. * Every 30 seconds we swap the filters and clear the "new" one, - * unless both are empty of course. + * unless both are empty of course. This results in delegations for a + * given filehandle being blocked for between 30 and 60 seconds. * * Each filter is 256 bits. We hash the filehandle to 32bit and use the * low 3 bytes as hash-table indices. @@ -1120,9 +1086,9 @@ static int delegation_blocked(struct knfsd_fh *fh) if (ktime_get_seconds() - bd->swap_time > 30) { bd->entries -= bd->old_entries; bd->old_entries = bd->entries; + bd->new = 1-bd->new; memset(bd->set[bd->new], 0, sizeof(bd->set[0])); - bd->new = 1-bd->new; bd->swap_time = ktime_get_seconds(); } spin_unlock(&blocked_delegations_lock); @@ -1160,9 +1126,10 @@ static void block_delegations(struct knfsd_fh *fh) static struct nfs4_delegation * alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp, - struct nfs4_clnt_odstate *odstate) + struct nfs4_clnt_odstate *odstate, u32 dl_type) { struct nfs4_delegation *dp; + struct nfs4_stid *stid; long n; dprintk("NFSD alloc_init_deleg\n"); @@ -1171,9 +1138,10 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp, goto out_dec; if (delegation_blocked(&fp->fi_fhandle)) goto out_dec; - dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab, nfs4_free_deleg)); - if (dp == NULL) + stid = nfs4_alloc_stid(clp, deleg_slab, nfs4_free_deleg); + if (stid == NULL) goto out_dec; + dp = delegstateid(stid); /* * delegation seqid's are never incremented. The 4.1 special @@ -1186,11 +1154,14 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp, INIT_LIST_HEAD(&dp->dl_recall_lru); dp->dl_clnt_odstate = odstate; get_clnt_odstate(odstate); - dp->dl_type = NFS4_OPEN_DELEGATE_READ; + dp->dl_type = dl_type; dp->dl_retries = 1; dp->dl_recalled = false; nfsd4_init_cb(&dp->dl_recall, dp->dl_stid.sc_client, &nfsd4_cb_recall_ops, NFSPROC4_CLNT_CB_RECALL); + nfsd4_init_cb(&dp->dl_cb_fattr.ncf_getattr, dp->dl_stid.sc_client, + &nfsd4_cb_getattr_ops, NFSPROC4_CLNT_CB_GETATTR); + dp->dl_cb_fattr.ncf_file_modified = false; get_nfs4_file(fp); dp->dl_stid.sc_file = fp; return dp; @@ -1212,6 +1183,8 @@ nfs4_put_stid(struct nfs4_stid *s) return; } idr_remove(&clp->cl_stateids, s->sc_stateid.si_opaque.so_id); + if (s->sc_status & SC_STATUS_ADMIN_REVOKED) + atomic_dec(&s->sc_client->cl_admin_revoked); nfs4_free_cpntf_statelist(clp->net, s); spin_unlock(&clp->cl_lock); s->sc_free(s); @@ -1233,15 +1206,56 @@ nfs4_inc_and_copy_stateid(stateid_t *dst, struct nfs4_stid *stid) static void put_deleg_file(struct nfs4_file *fp) { + struct nfsd_file *rnf = NULL; struct nfsd_file *nf = NULL; spin_lock(&fp->fi_lock); - if (--fp->fi_delegees == 0) + if (--fp->fi_delegees == 0) { swap(nf, fp->fi_deleg_file); + swap(rnf, fp->fi_rdeleg_file); + } spin_unlock(&fp->fi_lock); if (nf) nfsd_file_put(nf); + if (rnf) + nfs4_file_put_access(fp, NFS4_SHARE_ACCESS_READ); +} + +static void nfsd4_finalize_deleg_timestamps(struct nfs4_delegation *dp, struct file *f) +{ + struct iattr ia = { .ia_valid = ATTR_ATIME | ATTR_CTIME | ATTR_MTIME }; + struct inode *inode = file_inode(f); + int ret; + + /* don't do anything if FMODE_NOCMTIME isn't set */ + if ((READ_ONCE(f->f_mode) & FMODE_NOCMTIME) == 0) + return; + + spin_lock(&f->f_lock); + f->f_mode &= ~FMODE_NOCMTIME; + spin_unlock(&f->f_lock); + + /* was it never written? */ + if (!dp->dl_written) + return; + + /* did it get a setattr for the timestamps at some point? */ + if (dp->dl_setattr) + return; + + /* Stamp everything to "now" */ + inode_lock(inode); + ret = notify_change(&nop_mnt_idmap, f->f_path.dentry, &ia, NULL); + inode_unlock(inode); + if (ret) { + struct inode *inode = file_inode(f); + + pr_notice_ratelimited("Unable to update timestamps on inode %02x:%02x:%lu: %d\n", + MAJOR(inode->i_sb->s_dev), + MINOR(inode->i_sb->s_dev), + inode->i_ino, ret); + } } static void nfs4_unlock_deleg_lease(struct nfs4_delegation *dp) @@ -1251,7 +1265,8 @@ static void nfs4_unlock_deleg_lease(struct nfs4_delegation *dp) WARN_ON_ONCE(!fp->fi_delegees); - vfs_setlease(nf->nf_file, F_UNLCK, NULL, (void **)&dp); + nfsd4_finalize_deleg_timestamps(dp, nf->nf_file); + kernel_setlease(nf->nf_file, F_UNLCK, NULL, (void **)&dp); put_deleg_file(fp); } @@ -1262,11 +1277,6 @@ static void destroy_unhashed_deleg(struct nfs4_delegation *dp) nfs4_put_stid(&dp->dl_stid); } -void nfs4_unhash_stid(struct nfs4_stid *s) -{ - s->sc_type = 0; -} - /** * nfs4_delegation_exists - Discover if this delegation already exists * @clp: a pointer to the nfs4_client we're granting a delegation to @@ -1314,11 +1324,12 @@ hash_delegation_locked(struct nfs4_delegation *dp, struct nfs4_file *fp) lockdep_assert_held(&state_lock); lockdep_assert_held(&fp->fi_lock); + lockdep_assert_held(&clp->cl_lock); if (nfs4_delegation_exists(clp, fp)) return -EAGAIN; refcount_inc(&dp->dl_stid.sc_count); - dp->dl_stid.sc_type = NFS4_DELEG_STID; + dp->dl_stid.sc_type = SC_TYPE_DELEG; list_add(&dp->dl_perfile, &fp->fi_delegations); list_add(&dp->dl_perclnt, &clp->cl_delegations); return 0; @@ -1330,7 +1341,7 @@ static bool delegation_hashed(struct nfs4_delegation *dp) } static bool -unhash_delegation_locked(struct nfs4_delegation *dp) +unhash_delegation_locked(struct nfs4_delegation *dp, unsigned short statusmask) { struct nfs4_file *fp = dp->dl_stid.sc_file; @@ -1339,7 +1350,13 @@ unhash_delegation_locked(struct nfs4_delegation *dp) if (!delegation_hashed(dp)) return false; - dp->dl_stid.sc_type = NFS4_CLOSED_DELEG_STID; + if (statusmask == SC_STATUS_REVOKED && + dp->dl_stid.sc_client->cl_minorversion == 0) + statusmask = SC_STATUS_CLOSED; + dp->dl_stid.sc_status |= statusmask; + if (statusmask & SC_STATUS_ADMIN_REVOKED) + atomic_inc(&dp->dl_stid.sc_client->cl_admin_revoked); + /* Ensure that deleg break won't try to requeue it */ ++dp->dl_time; spin_lock(&fp->fi_lock); @@ -1355,32 +1372,59 @@ static void destroy_delegation(struct nfs4_delegation *dp) bool unhashed; spin_lock(&state_lock); - unhashed = unhash_delegation_locked(dp); + unhashed = unhash_delegation_locked(dp, SC_STATUS_CLOSED); spin_unlock(&state_lock); if (unhashed) destroy_unhashed_deleg(dp); } +/** + * revoke_delegation - perform nfs4 delegation structure cleanup + * @dp: pointer to the delegation + * + * This function assumes that it's called either from the administrative + * interface (nfsd4_revoke_states()) that's revoking a specific delegation + * stateid or it's called from a laundromat thread (nfsd4_landromat()) that + * determined that this specific state has expired and needs to be revoked + * (both mark state with the appropriate stid sc_status mode). It is also + * assumed that a reference was taken on the @dp state. + * + * If this function finds that the @dp state is SC_STATUS_FREED it means + * that a FREE_STATEID operation for this stateid has been processed and + * we can proceed to removing it from recalled list. However, if @dp state + * isn't marked SC_STATUS_FREED, it means we need place it on the cl_revoked + * list and wait for the FREE_STATEID to arrive from the client. At the same + * time, we need to mark it as SC_STATUS_FREEABLE to indicate to the + * nfsd4_free_stateid() function that this stateid has already been added + * to the cl_revoked list and that nfsd4_free_stateid() is now responsible + * for removing it from the list. Inspection of where the delegation state + * in the revocation process is protected by the clp->cl_lock. + */ static void revoke_delegation(struct nfs4_delegation *dp) { struct nfs4_client *clp = dp->dl_stid.sc_client; WARN_ON(!list_empty(&dp->dl_recall_lru)); + WARN_ON_ONCE(dp->dl_stid.sc_client->cl_minorversion > 0 && + !(dp->dl_stid.sc_status & + (SC_STATUS_REVOKED | SC_STATUS_ADMIN_REVOKED))); trace_nfsd_stid_revoke(&dp->dl_stid); - if (clp->cl_minorversion) { - dp->dl_stid.sc_type = NFS4_REVOKED_DELEG_STID; - refcount_inc(&dp->dl_stid.sc_count); - spin_lock(&clp->cl_lock); - list_add(&dp->dl_recall_lru, &clp->cl_revoked); - spin_unlock(&clp->cl_lock); + spin_lock(&clp->cl_lock); + if (dp->dl_stid.sc_status & SC_STATUS_FREED) { + list_del_init(&dp->dl_recall_lru); + goto out; } + list_add(&dp->dl_recall_lru, &clp->cl_revoked); + dp->dl_stid.sc_status |= SC_STATUS_FREEABLE; +out: + spin_unlock(&clp->cl_lock); destroy_unhashed_deleg(dp); } -/* - * SETCLIENTID state +/* + * SETCLIENTID state */ static unsigned int clientid_hashval(u32 id) @@ -1401,11 +1445,16 @@ static void recalculate_deny_mode(struct nfs4_file *fp) { struct nfs4_ol_stateid *stp; + u32 old_deny; spin_lock(&fp->fi_lock); + old_deny = fp->fi_share_deny; fp->fi_share_deny = 0; - list_for_each_entry(stp, &fp->fi_stateids, st_perfile) + list_for_each_entry(stp, &fp->fi_stateids, st_perfile) { fp->fi_share_deny |= bmap_to_share_mode(stp->st_deny_bmap); + if (fp->fi_share_deny == old_deny) + break; + } spin_unlock(&fp->fi_lock); } @@ -1493,7 +1542,8 @@ static void nfs4_free_ol_stateid(struct nfs4_stid *stid) release_all_access(stp); if (stp->st_stateowner) nfs4_put_stateowner(stp->st_stateowner); - WARN_ON(!list_empty(&stid->sc_cp_list)); + if (!list_empty(&stid->sc_cp_list)) + nfs4_free_cpntf_statelist(stid->sc_client->net, stid); kmem_cache_free(stateid_slab, stid); } @@ -1533,6 +1583,8 @@ static void put_ol_stateid_locked(struct nfs4_ol_stateid *stp, } idr_remove(&clp->cl_stateids, s->sc_stateid.si_opaque.so_id); + if (s->sc_status & SC_STATUS_ADMIN_REVOKED) + atomic_dec(&s->sc_client->cl_admin_revoked); list_add(&stp->st_locks, reaplist); } @@ -1543,7 +1595,7 @@ static bool unhash_lock_stateid(struct nfs4_ol_stateid *stp) if (!unhash_ol_stateid(stp)) return false; list_del_init(&stp->st_locks); - nfs4_unhash_stid(&stp->st_stid); + stp->st_stid.sc_status |= SC_STATUS_CLOSED; return true; } @@ -1601,7 +1653,7 @@ static void release_open_stateid_locks(struct nfs4_ol_stateid *open_stp, while (!list_empty(&open_stp->st_locks)) { stp = list_entry(open_stp->st_locks.next, struct nfs4_ol_stateid, st_locks); - WARN_ON(!unhash_lock_stateid(stp)); + unhash_lock_stateid(stp); put_ol_stateid_locked(stp, reaplist); } } @@ -1622,12 +1674,21 @@ static void release_open_stateid(struct nfs4_ol_stateid *stp) LIST_HEAD(reaplist); spin_lock(&stp->st_stid.sc_client->cl_lock); + stp->st_stid.sc_status |= SC_STATUS_CLOSED; if (unhash_open_stateid(stp, &reaplist)) put_ol_stateid_locked(stp, &reaplist); spin_unlock(&stp->st_stid.sc_client->cl_lock); free_ol_stateid_reaplist(&reaplist); } +static bool nfs4_openowner_unhashed(struct nfs4_openowner *oo) +{ + lockdep_assert_held(&oo->oo_owner.so_client->cl_lock); + + return list_empty(&oo->oo_owner.so_strhash) && + list_empty(&oo->oo_perclient); +} + static void unhash_openowner_locked(struct nfs4_openowner *oo) { struct nfs4_client *clp = oo->oo_owner.so_client; @@ -1659,9 +1720,7 @@ static void release_openowner(struct nfs4_openowner *oo) { struct nfs4_ol_stateid *stp; struct nfs4_client *clp = oo->oo_owner.so_client; - struct list_head reaplist; - - INIT_LIST_HEAD(&reaplist); + LIST_HEAD(reaplist); spin_lock(&clp->cl_lock); unhash_openowner_locked(oo); @@ -1677,6 +1736,137 @@ static void release_openowner(struct nfs4_openowner *oo) nfs4_put_stateowner(&oo->oo_owner); } +static struct nfs4_stid *find_one_sb_stid(struct nfs4_client *clp, + struct super_block *sb, + unsigned int sc_types) +{ + unsigned long id, tmp; + struct nfs4_stid *stid; + + spin_lock(&clp->cl_lock); + idr_for_each_entry_ul(&clp->cl_stateids, stid, tmp, id) + if ((stid->sc_type & sc_types) && + stid->sc_status == 0 && + stid->sc_file->fi_inode->i_sb == sb) { + refcount_inc(&stid->sc_count); + break; + } + spin_unlock(&clp->cl_lock); + return stid; +} + +/** + * nfsd4_revoke_states - revoke all nfsv4 states associated with given filesystem + * @net: used to identify instance of nfsd (there is one per net namespace) + * @sb: super_block used to identify target filesystem + * + * All nfs4 states (open, lock, delegation, layout) held by the server instance + * and associated with a file on the given filesystem will be revoked resulting + * in any files being closed and so all references from nfsd to the filesystem + * being released. Thus nfsd will no longer prevent the filesystem from being + * unmounted. + * + * The clients which own the states will subsequently being notified that the + * states have been "admin-revoked". + */ +void nfsd4_revoke_states(struct net *net, struct super_block *sb) +{ + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + unsigned int idhashval; + unsigned int sc_types; + + sc_types = SC_TYPE_OPEN | SC_TYPE_LOCK | SC_TYPE_DELEG | SC_TYPE_LAYOUT; + + spin_lock(&nn->client_lock); + for (idhashval = 0; idhashval < CLIENT_HASH_MASK; idhashval++) { + struct list_head *head = &nn->conf_id_hashtbl[idhashval]; + struct nfs4_client *clp; + retry: + list_for_each_entry(clp, head, cl_idhash) { + struct nfs4_stid *stid = find_one_sb_stid(clp, sb, + sc_types); + if (stid) { + struct nfs4_ol_stateid *stp; + struct nfs4_delegation *dp; + struct nfs4_layout_stateid *ls; + + spin_unlock(&nn->client_lock); + switch (stid->sc_type) { + case SC_TYPE_OPEN: + stp = openlockstateid(stid); + mutex_lock_nested(&stp->st_mutex, + OPEN_STATEID_MUTEX); + + spin_lock(&clp->cl_lock); + if (stid->sc_status == 0) { + stid->sc_status |= + SC_STATUS_ADMIN_REVOKED; + atomic_inc(&clp->cl_admin_revoked); + spin_unlock(&clp->cl_lock); + release_all_access(stp); + } else + spin_unlock(&clp->cl_lock); + mutex_unlock(&stp->st_mutex); + break; + case SC_TYPE_LOCK: + stp = openlockstateid(stid); + mutex_lock_nested(&stp->st_mutex, + LOCK_STATEID_MUTEX); + spin_lock(&clp->cl_lock); + if (stid->sc_status == 0) { + struct nfs4_lockowner *lo = + lockowner(stp->st_stateowner); + struct nfsd_file *nf; + + stid->sc_status |= + SC_STATUS_ADMIN_REVOKED; + atomic_inc(&clp->cl_admin_revoked); + spin_unlock(&clp->cl_lock); + nf = find_any_file(stp->st_stid.sc_file); + if (nf) { + get_file(nf->nf_file); + filp_close(nf->nf_file, + (fl_owner_t)lo); + nfsd_file_put(nf); + } + release_all_access(stp); + } else + spin_unlock(&clp->cl_lock); + mutex_unlock(&stp->st_mutex); + break; + case SC_TYPE_DELEG: + refcount_inc(&stid->sc_count); + dp = delegstateid(stid); + spin_lock(&state_lock); + if (!unhash_delegation_locked( + dp, SC_STATUS_ADMIN_REVOKED)) + dp = NULL; + spin_unlock(&state_lock); + if (dp) + revoke_delegation(dp); + break; + case SC_TYPE_LAYOUT: + ls = layoutstateid(stid); + nfsd4_close_layout(ls); + break; + } + nfs4_put_stid(stid); + spin_lock(&nn->client_lock); + if (clp->cl_minorversion == 0) + /* Allow cleanup after a lease period. + * store_release ensures cleanup will + * see any newly revoked states if it + * sees the time updated. + */ + nn->nfs40_last_revoke = + ktime_get_boottime_seconds(); + goto retry; + } + } + } + spin_unlock(&nn->client_lock); +} + static inline int hash_sessionid(struct nfs4_sessionid *sessionid) { @@ -1748,113 +1938,145 @@ gen_sessionid(struct nfsd4_session *ses) */ #define NFSD_MIN_HDR_SEQ_SZ (24 + 12 + 44) +static struct shrinker *nfsd_slot_shrinker; +static DEFINE_SPINLOCK(nfsd_session_list_lock); +static LIST_HEAD(nfsd_session_list); +/* The sum of "target_slots-1" on every session. The shrinker can push this + * down, though it can take a little while for the memory to actually + * be freed. The "-1" is because we can never free slot 0 while the + * session is active. + */ +static atomic_t nfsd_total_target_slots = ATOMIC_INIT(0); + static void -free_session_slots(struct nfsd4_session *ses) +free_session_slots(struct nfsd4_session *ses, int from) { int i; - for (i = 0; i < ses->se_fchannel.maxreqs; i++) { - free_svc_cred(&ses->se_slots[i]->sl_cred); - kfree(ses->se_slots[i]); + if (from >= ses->se_fchannel.maxreqs) + return; + + for (i = from; i < ses->se_fchannel.maxreqs; i++) { + struct nfsd4_slot *slot = xa_load(&ses->se_slots, i); + + /* + * Save the seqid in case we reactivate this slot. + * This will never require a memory allocation so GFP + * flag is irrelevant + */ + xa_store(&ses->se_slots, i, xa_mk_value(slot->sl_seqid), 0); + free_svc_cred(&slot->sl_cred); + kfree(slot); + } + ses->se_fchannel.maxreqs = from; + if (ses->se_target_maxslots > from) { + int new_target = from ?: 1; + atomic_sub(ses->se_target_maxslots - new_target, &nfsd_total_target_slots); + ses->se_target_maxslots = new_target; } } -/* - * We don't actually need to cache the rpc and session headers, so we - * can allocate a little less for each slot: +/** + * reduce_session_slots - reduce the target max-slots of a session if possible + * @ses: The session to affect + * @dec: how much to decrease the target by + * + * This interface can be used by a shrinker to reduce the target max-slots + * for a session so that some slots can eventually be freed. + * It uses spin_trylock() as it may be called in a context where another + * spinlock is held that has a dependency on client_lock. As shrinkers are + * best-effort, skiping a session is client_lock is already held has no + * great coast + * + * Return value: + * The number of slots that the target was reduced by. */ -static inline u32 slot_bytes(struct nfsd4_channel_attrs *ca) +static int +reduce_session_slots(struct nfsd4_session *ses, int dec) { - u32 size; + struct nfsd_net *nn = net_generic(ses->se_client->net, + nfsd_net_id); + int ret = 0; - if (ca->maxresp_cached < NFSD_MIN_HDR_SEQ_SZ) - size = 0; - else - size = ca->maxresp_cached - NFSD_MIN_HDR_SEQ_SZ; - return size + sizeof(struct nfsd4_slot); + if (ses->se_target_maxslots <= 1) + return ret; + if (!spin_trylock(&nn->client_lock)) + return ret; + ret = min(dec, ses->se_target_maxslots-1); + ses->se_target_maxslots -= ret; + atomic_sub(ret, &nfsd_total_target_slots); + ses->se_slot_gen += 1; + if (ses->se_slot_gen == 0) { + int i; + ses->se_slot_gen = 1; + for (i = 0; i < ses->se_fchannel.maxreqs; i++) { + struct nfsd4_slot *slot = xa_load(&ses->se_slots, i); + slot->sl_generation = 0; + } + } + spin_unlock(&nn->client_lock); + return ret; } -/* - * XXX: If we run out of reserved DRC memory we could (up to a point) - * re-negotiate active sessions and reduce their slot usage to make - * room for new connections. For now we just fail the create session. - */ -static u32 nfsd4_get_drc_mem(struct nfsd4_channel_attrs *ca, struct nfsd_net *nn) +static struct nfsd4_slot *nfsd4_alloc_slot(struct nfsd4_channel_attrs *fattrs, + int index, gfp_t gfp) { - u32 slotsize = slot_bytes(ca); - u32 num = ca->maxreqs; - unsigned long avail, total_avail; - unsigned int scale_factor; + struct nfsd4_slot *slot; + size_t size; - spin_lock(&nfsd_drc_lock); - if (nfsd_drc_max_mem > nfsd_drc_mem_used) - total_avail = nfsd_drc_max_mem - nfsd_drc_mem_used; - else - /* We have handed out more space than we chose in - * set_max_drc() to allow. That isn't really a - * problem as long as that doesn't make us think we - * have lots more due to integer overflow. - */ - total_avail = 0; - avail = min((unsigned long)NFSD_MAX_MEM_PER_SESSION, total_avail); /* - * Never use more than a fraction of the remaining memory, - * unless it's the only way to give this client a slot. - * The chosen fraction is either 1/8 or 1/number of threads, - * whichever is smaller. This ensures there are adequate - * slots to support multiple clients per thread. - * Give the client one slot even if that would require - * over-allocation--it is better than failure. + * The RPC and NFS session headers are never saved in + * the slot reply cache buffer. */ - scale_factor = max_t(unsigned int, 8, nn->nfsd_serv->sv_nrthreads); - - avail = clamp_t(unsigned long, avail, slotsize, - total_avail/scale_factor); - num = min_t(int, num, avail / slotsize); - num = max_t(int, num, 1); - nfsd_drc_mem_used += num * slotsize; - spin_unlock(&nfsd_drc_lock); + size = fattrs->maxresp_cached < NFSD_MIN_HDR_SEQ_SZ ? + 0 : fattrs->maxresp_cached - NFSD_MIN_HDR_SEQ_SZ; - return num; -} - -static void nfsd4_put_drc_mem(struct nfsd4_channel_attrs *ca) -{ - int slotsize = slot_bytes(ca); - - spin_lock(&nfsd_drc_lock); - nfsd_drc_mem_used -= slotsize * ca->maxreqs; - spin_unlock(&nfsd_drc_lock); + slot = kzalloc(struct_size(slot, sl_data, size), gfp); + if (!slot) + return NULL; + slot->sl_index = index; + return slot; } static struct nfsd4_session *alloc_session(struct nfsd4_channel_attrs *fattrs, struct nfsd4_channel_attrs *battrs) { int numslots = fattrs->maxreqs; - int slotsize = slot_bytes(fattrs); struct nfsd4_session *new; + struct nfsd4_slot *slot; int i; - BUILD_BUG_ON(struct_size(new, se_slots, NFSD_MAX_SLOTS_PER_SESSION) - > PAGE_SIZE); - - new = kzalloc(struct_size(new, se_slots, numslots), GFP_KERNEL); + new = kzalloc(sizeof(*new), GFP_KERNEL); if (!new) return NULL; - /* allocate each struct nfsd4_slot and data cache in one piece */ - for (i = 0; i < numslots; i++) { - new->se_slots[i] = kzalloc(slotsize, GFP_KERNEL); - if (!new->se_slots[i]) - goto out_free; - } + xa_init(&new->se_slots); - memcpy(&new->se_fchannel, fattrs, sizeof(struct nfsd4_channel_attrs)); - memcpy(&new->se_bchannel, battrs, sizeof(struct nfsd4_channel_attrs)); + slot = nfsd4_alloc_slot(fattrs, 0, GFP_KERNEL); + if (!slot || xa_is_err(xa_store(&new->se_slots, 0, slot, GFP_KERNEL))) + goto out_free; + for (i = 1; i < numslots; i++) { + const gfp_t gfp = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN; + slot = nfsd4_alloc_slot(fattrs, i, gfp); + if (!slot) + break; + if (xa_is_err(xa_store(&new->se_slots, i, slot, gfp))) { + kfree(slot); + break; + } + } + fattrs->maxreqs = i; + memcpy(&new->se_fchannel, fattrs, sizeof(struct nfsd4_channel_attrs)); + new->se_target_maxslots = i; + atomic_add(i - 1, &nfsd_total_target_slots); + new->se_cb_slot_avail = ~0U; + new->se_cb_highest_slot = min(battrs->maxreqs - 1, + NFSD_BC_SLOT_TABLE_SIZE - 1); + spin_lock_init(&new->se_lock); return new; out_free: - while (i--) - kfree(new->se_slots[i]); + kfree(slot); + xa_destroy(&new->se_slots); kfree(new); return NULL; } @@ -1960,17 +2182,47 @@ static void nfsd4_del_conns(struct nfsd4_session *s) static void __free_session(struct nfsd4_session *ses) { - free_session_slots(ses); + free_session_slots(ses, 0); + xa_destroy(&ses->se_slots); kfree(ses); } static void free_session(struct nfsd4_session *ses) { nfsd4_del_conns(ses); - nfsd4_put_drc_mem(&ses->se_fchannel); __free_session(ses); } +static unsigned long +nfsd_slot_count(struct shrinker *s, struct shrink_control *sc) +{ + unsigned long cnt = atomic_read(&nfsd_total_target_slots); + + return cnt ? cnt : SHRINK_EMPTY; +} + +static unsigned long +nfsd_slot_scan(struct shrinker *s, struct shrink_control *sc) +{ + struct nfsd4_session *ses; + unsigned long scanned = 0; + unsigned long freed = 0; + + spin_lock(&nfsd_session_list_lock); + list_for_each_entry(ses, &nfsd_session_list, se_all_sessions) { + freed += reduce_session_slots(ses, 1); + scanned += 1; + if (scanned >= sc->nr_to_scan) { + /* Move starting point for next scan */ + list_move(&nfsd_session_list, &ses->se_all_sessions); + break; + } + } + spin_unlock(&nfsd_session_list_lock); + sc->nr_scanned = scanned; + return freed; +} + static void init_session(struct svc_rqst *rqstp, struct nfsd4_session *new, struct nfs4_client *clp, struct nfsd4_create_session *cses) { int idx; @@ -1981,17 +2233,24 @@ static void init_session(struct svc_rqst *rqstp, struct nfsd4_session *new, stru INIT_LIST_HEAD(&new->se_conns); - new->se_cb_seq_nr = 1; - new->se_flags = cses->flags; + atomic_set(&new->se_ref, 0); + new->se_dead = false; new->se_cb_prog = cses->callback_prog; new->se_cb_sec = cses->cb_sec; - atomic_set(&new->se_ref, 0); + + for (idx = 0; idx < NFSD_BC_SLOT_TABLE_SIZE; ++idx) + new->se_cb_seq_nr[idx] = 1; + idx = hash_sessionid(&new->se_sessionid); list_add(&new->se_hash, &nn->sessionid_hashtbl[idx]); spin_lock(&clp->cl_lock); list_add(&new->se_perclnt, &clp->cl_sessions); spin_unlock(&clp->cl_lock); + spin_lock(&nfsd_session_list_lock); + list_add_tail(&new->se_all_sessions, &nfsd_session_list); + spin_unlock(&nfsd_session_list_lock); + { struct sockaddr *sa = svc_addr(rqstp); /* @@ -2061,6 +2320,9 @@ unhash_session(struct nfsd4_session *ses) spin_lock(&ses->se_client->cl_lock); list_del(&ses->se_perclnt); spin_unlock(&ses->se_client->cl_lock); + spin_lock(&nfsd_session_list_lock); + list_del(&ses->se_all_sessions); + spin_unlock(&nfsd_session_list_lock); } /* SETCLIENTID and SETCLIENTID_CONFIRM Helper functions */ @@ -2078,21 +2340,16 @@ STALE_CLIENTID(clientid_t *clid, struct nfsd_net *nn) return 1; } -/* - * XXX Should we use a slab cache ? - * This type of memory management is somewhat inefficient, but we use it - * anyway since SETCLIENTID is not a common operation. - */ static struct nfs4_client *alloc_client(struct xdr_netobj name, struct nfsd_net *nn) { struct nfs4_client *clp; int i; - if (atomic_read(&nn->nfs4_client_count) >= nn->nfs4_max_clients) { + if (atomic_read(&nn->nfs4_client_count) >= nn->nfs4_max_clients && + atomic_read(&nn->nfsd_courtesy_clients) > 0) mod_delayed_work(laundry_wq, &nn->laundromat_work, 0); - return NULL; - } + clp = kmem_cache_zalloc(client_slab, GFP_KERNEL); if (clp == NULL) return NULL; @@ -2104,6 +2361,10 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name, GFP_KERNEL); if (!clp->cl_ownerstr_hashtbl) goto err_no_hashtbl; + clp->cl_callback_wq = alloc_ordered_workqueue("nfsd4_callbacks", 0); + if (!clp->cl_callback_wq) + goto err_no_callback_wq; + for (i = 0; i < OWNER_HASH_SIZE; i++) INIT_LIST_HEAD(&clp->cl_ownerstr_hashtbl[i]); INIT_LIST_HEAD(&clp->cl_sessions); @@ -2126,6 +2387,8 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name, spin_lock_init(&clp->cl_lock); rpc_init_wait_queue(&clp->cl_cb_waitq, "Backchannel slot table"); return clp; +err_no_callback_wq: + kfree(clp->cl_ownerstr_hashtbl); err_no_hashtbl: kfree(clp->cl_name.data); err_no_name: @@ -2139,6 +2402,7 @@ static void __free_client(struct kref *k) struct nfs4_client *clp = container_of(c, struct nfs4_client, cl_nfsdfs); free_svc_cred(&clp->cl_cred); + destroy_workqueue(clp->cl_callback_wq); kfree(clp->cl_ownerstr_hashtbl); kfree(clp->cl_name.data); kfree(clp->cl_nii_domain.data); @@ -2194,8 +2458,12 @@ unhash_client_locked(struct nfs4_client *clp) } list_del_init(&clp->cl_lru); spin_lock(&clp->cl_lock); - list_for_each_entry(ses, &clp->cl_sessions, se_perclnt) + spin_lock(&nfsd_session_list_lock); + list_for_each_entry(ses, &clp->cl_sessions, se_perclnt) { list_del_init(&ses->se_hash); + list_del_init(&ses->se_all_sessions); + } + spin_unlock(&nfsd_session_list_lock); spin_unlock(&clp->cl_lock); } @@ -2211,7 +2479,11 @@ unhash_client(struct nfs4_client *clp) static __be32 mark_client_expired_locked(struct nfs4_client *clp) { - if (atomic_read(&clp->cl_rpc_users)) + int users = atomic_read(&clp->cl_rpc_users); + + trace_nfsd_mark_client_expired(clp, users); + + if (users) return nfserr_jukebox; unhash_client_locked(clp); return nfs_ok; @@ -2224,13 +2496,12 @@ __destroy_client(struct nfs4_client *clp) int i; struct nfs4_openowner *oo; struct nfs4_delegation *dp; - struct list_head reaplist; + LIST_HEAD(reaplist); - INIT_LIST_HEAD(&reaplist); spin_lock(&state_lock); while (!list_empty(&clp->cl_delegations)) { dp = list_entry(clp->cl_delegations.next, struct nfs4_delegation, dl_perclnt); - WARN_ON(!unhash_delegation_locked(dp)); + unhash_delegation_locked(dp, SC_STATUS_CLOSED); list_add(&dp->dl_recall_lru, &reaplist); } spin_unlock(&state_lock); @@ -2462,14 +2733,16 @@ find_stateid_locked(struct nfs4_client *cl, stateid_t *t) } static struct nfs4_stid * -find_stateid_by_type(struct nfs4_client *cl, stateid_t *t, char typemask) +find_stateid_by_type(struct nfs4_client *cl, stateid_t *t, + unsigned short typemask, unsigned short ok_states) { struct nfs4_stid *s; spin_lock(&cl->cl_lock); s = find_stateid_locked(cl, t); if (s != NULL) { - if (typemask & s->sc_type) + if ((s->sc_status & ~ok_states) == 0 && + (typemask & s->sc_type)) refcount_inc(&s->sc_count); else s = NULL; @@ -2489,9 +2762,9 @@ static struct nfs4_client *get_nfsdfs_clp(struct inode *inode) static void seq_quote_mem(struct seq_file *m, char *data, int len) { - seq_printf(m, "\""); + seq_puts(m, "\""); seq_escape_mem(m, data, len, ESCAPE_HEX | ESCAPE_NAP | ESCAPE_APPEND, "\"\\"); - seq_printf(m, "\""); + seq_puts(m, "\""); } static const char *cb_state2str(int state) @@ -2512,6 +2785,7 @@ static const char *cb_state2str(int state) static int client_info_show(struct seq_file *m, void *v) { struct inode *inode = file_inode(m->file); + struct nfsd4_session *ses; struct nfs4_client *clp; u64 clid; @@ -2532,20 +2806,32 @@ static int client_info_show(struct seq_file *m, void *v) seq_puts(m, "status: unconfirmed\n"); seq_printf(m, "seconds from last renew: %lld\n", ktime_get_boottime_seconds() - clp->cl_time); - seq_printf(m, "name: "); + seq_puts(m, "name: "); seq_quote_mem(m, clp->cl_name.data, clp->cl_name.len); seq_printf(m, "\nminor version: %d\n", clp->cl_minorversion); if (clp->cl_nii_domain.data) { - seq_printf(m, "Implementation domain: "); + seq_puts(m, "Implementation domain: "); seq_quote_mem(m, clp->cl_nii_domain.data, clp->cl_nii_domain.len); - seq_printf(m, "\nImplementation name: "); + seq_puts(m, "\nImplementation name: "); seq_quote_mem(m, clp->cl_nii_name.data, clp->cl_nii_name.len); seq_printf(m, "\nImplementation time: [%lld, %ld]\n", clp->cl_nii_time.tv_sec, clp->cl_nii_time.tv_nsec); } seq_printf(m, "callback state: %s\n", cb_state2str(clp->cl_cb_state)); - seq_printf(m, "callback address: %pISpc\n", &clp->cl_cb_conn.cb_addr); + seq_printf(m, "callback address: \"%pISpc\"\n", &clp->cl_cb_conn.cb_addr); + seq_printf(m, "admin-revoked states: %d\n", + atomic_read(&clp->cl_admin_revoked)); + spin_lock(&clp->cl_lock); + seq_printf(m, "session slots:"); + list_for_each_entry(ses, &clp->cl_sessions, se_perclnt) + seq_printf(m, " %u", ses->se_fchannel.maxreqs); + seq_printf(m, "\nsession target slots:"); + list_for_each_entry(ses, &clp->cl_sessions, se_perclnt) + seq_printf(m, " %u", ses->se_target_maxslots); + spin_unlock(&clp->cl_lock); + seq_puts(m, "\n"); + drop_client(clp); return 0; @@ -2604,7 +2890,7 @@ static void nfs4_show_superblock(struct seq_file *s, struct nfsd_file *f) static void nfs4_show_owner(struct seq_file *s, struct nfs4_stateowner *oo) { - seq_printf(s, "owner: "); + seq_puts(s, "owner: "); seq_quote_mem(s, oo->so_owner.data, oo->so_owner.len); } @@ -2622,20 +2908,13 @@ static int nfs4_show_open(struct seq_file *s, struct nfs4_stid *st) struct nfs4_stateowner *oo; unsigned int access, deny; - if (st->sc_type != NFS4_OPEN_STID && st->sc_type != NFS4_LOCK_STID) - return 0; /* XXX: or SEQ_SKIP? */ ols = openlockstateid(st); oo = ols->st_stateowner; nf = st->sc_file; - spin_lock(&nf->fi_lock); - file = find_any_file_locked(nf); - if (!file) - goto out; - - seq_printf(s, "- "); + seq_puts(s, "- "); nfs4_show_stateid(s, &st->sc_stateid); - seq_printf(s, ": { type: open, "); + seq_puts(s, ": { type: open, "); access = bmap_to_share_mode(ols->st_access_bmap); deny = bmap_to_share_mode(ols->st_deny_bmap); @@ -2647,14 +2926,22 @@ static int nfs4_show_open(struct seq_file *s, struct nfs4_stid *st) deny & NFS4_SHARE_ACCESS_READ ? "r" : "-", deny & NFS4_SHARE_ACCESS_WRITE ? "w" : "-"); - nfs4_show_superblock(s, file); - seq_printf(s, ", "); - nfs4_show_fname(s, file); - seq_printf(s, ", "); + if (nf) { + spin_lock(&nf->fi_lock); + file = find_any_file_locked(nf); + if (file) { + nfs4_show_superblock(s, file); + seq_puts(s, ", "); + nfs4_show_fname(s, file); + seq_puts(s, ", "); + } + spin_unlock(&nf->fi_lock); + } else + seq_puts(s, "closed, "); nfs4_show_owner(s, oo); - seq_printf(s, " }\n"); -out: - spin_unlock(&nf->fi_lock); + if (st->sc_status & SC_STATUS_ADMIN_REVOKED) + seq_puts(s, ", admin-revoked"); + seq_puts(s, " }\n"); return 0; } @@ -2668,34 +2955,50 @@ static int nfs4_show_lock(struct seq_file *s, struct nfs4_stid *st) ols = openlockstateid(st); oo = ols->st_stateowner; nf = st->sc_file; - spin_lock(&nf->fi_lock); - file = find_any_file_locked(nf); - if (!file) - goto out; - seq_printf(s, "- "); + seq_puts(s, "- "); nfs4_show_stateid(s, &st->sc_stateid); - seq_printf(s, ": { type: lock, "); + seq_puts(s, ": { type: lock, "); - /* - * Note: a lock stateid isn't really the same thing as a lock, - * it's the locking state held by one owner on a file, and there - * may be multiple (or no) lock ranges associated with it. - * (Same for the matter is true of open stateids.) - */ + spin_lock(&nf->fi_lock); + file = find_any_file_locked(nf); + if (file) { + /* + * Note: a lock stateid isn't really the same thing as a lock, + * it's the locking state held by one owner on a file, and there + * may be multiple (or no) lock ranges associated with it. + * (Same for the matter is true of open stateids.) + */ - nfs4_show_superblock(s, file); - /* XXX: open stateid? */ - seq_printf(s, ", "); - nfs4_show_fname(s, file); - seq_printf(s, ", "); + nfs4_show_superblock(s, file); + /* XXX: open stateid? */ + seq_puts(s, ", "); + nfs4_show_fname(s, file); + seq_puts(s, ", "); + } nfs4_show_owner(s, oo); - seq_printf(s, " }\n"); -out: + if (st->sc_status & SC_STATUS_ADMIN_REVOKED) + seq_puts(s, ", admin-revoked"); + seq_puts(s, " }\n"); spin_unlock(&nf->fi_lock); return 0; } +static char *nfs4_show_deleg_type(u32 dl_type) +{ + switch (dl_type) { + case OPEN_DELEGATE_READ: + return "r"; + case OPEN_DELEGATE_WRITE: + return "w"; + case OPEN_DELEGATE_READ_ATTRS_DELEG: + return "ra"; + case OPEN_DELEGATE_WRITE_ATTRS_DELEG: + return "wa"; + } + return "?"; +} + static int nfs4_show_deleg(struct seq_file *s, struct nfs4_stid *st) { struct nfs4_delegation *ds; @@ -2704,27 +3007,27 @@ static int nfs4_show_deleg(struct seq_file *s, struct nfs4_stid *st) ds = delegstateid(st); nf = st->sc_file; - spin_lock(&nf->fi_lock); - file = find_deleg_file_locked(nf); - if (!file) - goto out; - seq_printf(s, "- "); + seq_puts(s, "- "); nfs4_show_stateid(s, &st->sc_stateid); - seq_printf(s, ": { type: deleg, "); + seq_puts(s, ": { type: deleg, "); - /* Kinda dead code as long as we only support read delegs: */ - seq_printf(s, "access: %s, ", - ds->dl_type == NFS4_OPEN_DELEGATE_READ ? "r" : "w"); + seq_printf(s, "access: %s", nfs4_show_deleg_type(ds->dl_type)); /* XXX: lease time, whether it's being recalled. */ - nfs4_show_superblock(s, file); - seq_printf(s, ", "); - nfs4_show_fname(s, file); - seq_printf(s, " }\n"); -out: + spin_lock(&nf->fi_lock); + file = nf->fi_deleg_file; + if (file) { + seq_puts(s, ", "); + nfs4_show_superblock(s, file); + seq_puts(s, ", "); + nfs4_show_fname(s, file); + } spin_unlock(&nf->fi_lock); + if (st->sc_status & SC_STATUS_ADMIN_REVOKED) + seq_puts(s, ", admin-revoked"); + seq_puts(s, " }\n"); return 0; } @@ -2734,18 +3037,25 @@ static int nfs4_show_layout(struct seq_file *s, struct nfs4_stid *st) struct nfsd_file *file; ls = container_of(st, struct nfs4_layout_stateid, ls_stid); - file = ls->ls_file; - seq_printf(s, "- "); + seq_puts(s, "- "); nfs4_show_stateid(s, &st->sc_stateid); - seq_printf(s, ": { type: layout, "); + seq_puts(s, ": { type: layout"); /* XXX: What else would be useful? */ - nfs4_show_superblock(s, file); - seq_printf(s, ", "); - nfs4_show_fname(s, file); - seq_printf(s, " }\n"); + spin_lock(&ls->ls_stid.sc_file->fi_lock); + file = ls->ls_file; + if (file) { + seq_puts(s, ", "); + nfs4_show_superblock(s, file); + seq_puts(s, ", "); + nfs4_show_fname(s, file); + } + spin_unlock(&ls->ls_stid.sc_file->fi_lock); + if (st->sc_status & SC_STATUS_ADMIN_REVOKED) + seq_puts(s, ", admin-revoked"); + seq_puts(s, " }\n"); return 0; } @@ -2755,13 +3065,13 @@ static int states_show(struct seq_file *s, void *v) struct nfs4_stid *st = v; switch (st->sc_type) { - case NFS4_OPEN_STID: + case SC_TYPE_OPEN: return nfs4_show_open(s, st); - case NFS4_LOCK_STID: + case SC_TYPE_LOCK: return nfs4_show_lock(s, st); - case NFS4_DELEG_STID: + case SC_TYPE_DELEG: return nfs4_show_deleg(s, st); - case NFS4_LAYOUT_STID: + case SC_TYPE_LAYOUT: return nfs4_show_layout(s, st); default: return 0; /* XXX: or SEQ_SKIP? */ @@ -2801,7 +3111,7 @@ static int client_opens_release(struct inode *inode, struct file *file) /* XXX: alternatively, we could get/drop in seq start/stop */ drop_client(clp); - return 0; + return seq_release(inode, file); } static const struct file_operations client_states_fops = { @@ -2890,19 +3200,70 @@ static void nfsd4_cb_recall_any_release(struct nfsd4_callback *cb) { struct nfs4_client *clp = cb->cb_clp; - struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); - spin_lock(&nn->client_lock); - clear_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags); - put_client_renew_locked(clp); - spin_unlock(&nn->client_lock); + drop_client(clp); +} + +static int +nfsd4_cb_getattr_done(struct nfsd4_callback *cb, struct rpc_task *task) +{ + struct nfs4_cb_fattr *ncf = + container_of(cb, struct nfs4_cb_fattr, ncf_getattr); + struct nfs4_delegation *dp = + container_of(ncf, struct nfs4_delegation, dl_cb_fattr); + + trace_nfsd_cb_getattr_done(&dp->dl_stid.sc_stateid, task); + ncf->ncf_cb_status = task->tk_status; + switch (task->tk_status) { + case -NFS4ERR_DELAY: + rpc_delay(task, 2 * HZ); + return 0; + default: + return 1; + } +} + +static void +nfsd4_cb_getattr_release(struct nfsd4_callback *cb) +{ + struct nfs4_cb_fattr *ncf = + container_of(cb, struct nfs4_cb_fattr, ncf_getattr); + struct nfs4_delegation *dp = + container_of(ncf, struct nfs4_delegation, dl_cb_fattr); + + nfs4_put_stid(&dp->dl_stid); } static const struct nfsd4_callback_ops nfsd4_cb_recall_any_ops = { .done = nfsd4_cb_recall_any_done, .release = nfsd4_cb_recall_any_release, + .opcode = OP_CB_RECALL_ANY, }; +static const struct nfsd4_callback_ops nfsd4_cb_getattr_ops = { + .done = nfsd4_cb_getattr_done, + .release = nfsd4_cb_getattr_release, + .opcode = OP_CB_GETATTR, +}; + +static void nfs4_cb_getattr(struct nfs4_cb_fattr *ncf) +{ + struct nfs4_delegation *dp = + container_of(ncf, struct nfs4_delegation, dl_cb_fattr); + + if (test_and_set_bit(NFSD4_CALLBACK_RUNNING, &ncf->ncf_getattr.cb_flags)) + return; + + /* set to proper status when nfsd4_cb_getattr_done runs */ + ncf->ncf_cb_status = NFS4ERR_IO; + + /* ensure that wake_bit is done when RUNNING is cleared */ + set_bit(NFSD4_CALLBACK_WAKE, &ncf->ncf_getattr.cb_flags); + + refcount_inc(&dp->dl_stid.sc_count); + nfsd4_run_cb(&ncf->ncf_getattr); +} + static struct nfs4_client *create_client(struct xdr_netobj name, struct svc_rqst *rqstp, nfs4_verifier *verf) { @@ -2926,7 +3287,6 @@ static struct nfs4_client *create_client(struct xdr_netobj name, kref_init(&clp->cl_nfsdfs.cl_ref); nfsd4_init_cb(&clp->cl_cb_null, clp, NULL, NFSPROC4_CLNT_CB_NULL); clp->cl_time = ktime_get_boottime_seconds(); - clear_bit(0, &clp->cl_cb_slot_busy); copy_verf(clp, verf); memcpy(&clp->cl_addr, sa, sizeof(struct sockaddr_storage)); clp->cl_cb_session = NULL; @@ -3127,7 +3487,20 @@ nfsd4_store_cache_entry(struct nfsd4_compoundres *resp) struct nfsd4_slot *slot = resp->cstate.slot; unsigned int base; - dprintk("--> %s slot %p\n", __func__, slot); + /* + * RFC 5661 Section 2.10.6.1.2: + * + * Any time SEQUENCE ... returns an error ... [t]he replier MUST NOT + * modify the reply cache entry for the slot whenever an error is + * returned from SEQUENCE ... + * + * Because nfsd4_store_cache_entry is called only by + * nfsd4_sequence_done(), nfsd4_store_cache_entry() is called only + * when a SEQUENCE operation was part of the COMPOUND. + * nfs41_check_op_ordering() ensures SEQUENCE is the first op. + */ + if (resp->opcnt == 1 && resp->cstate.status != nfs_ok) + return; slot->sl_flags |= NFSD4_SLOT_INITIALIZED; slot->sl_opcnt = resp->opcnt; @@ -3135,7 +3508,7 @@ nfsd4_store_cache_entry(struct nfsd4_compoundres *resp) free_svc_cred(&slot->sl_cred); copy_cred(&slot->sl_cred, &resp->rqstp->rq_cred); - if (!nfsd4_cache_this(resp)) { + if (!(resp->cstate.slot->sl_flags & NFSD4_SLOT_CACHETHIS)) { slot->sl_flags &= ~NFSD4_SLOT_CACHED; return; } @@ -3150,41 +3523,6 @@ nfsd4_store_cache_entry(struct nfsd4_compoundres *resp) } /* - * Encode the replay sequence operation from the slot values. - * If cachethis is FALSE encode the uncached rep error on the next - * operation which sets resp->p and increments resp->opcnt for - * nfs4svc_encode_compoundres. - * - */ -static __be32 -nfsd4_enc_sequence_replay(struct nfsd4_compoundargs *args, - struct nfsd4_compoundres *resp) -{ - struct nfsd4_op *op; - struct nfsd4_slot *slot = resp->cstate.slot; - - /* Encode the replayed sequence operation */ - op = &args->ops[resp->opcnt - 1]; - nfsd4_encode_operation(resp, op); - - if (slot->sl_flags & NFSD4_SLOT_CACHED) - return op->status; - if (args->opcnt == 1) { - /* - * The original operation wasn't a solo sequence--we - * always cache those--so this retry must not match the - * original: - */ - op->status = nfserr_seq_false_retry; - } else { - op = &args->ops[resp->opcnt++]; - op->status = nfserr_retry_uncached_rep; - nfsd4_encode_operation(resp, op); - } - return op->status; -} - -/* * The sequence operation is not cached because we can use the slot and * session values. */ @@ -3192,17 +3530,30 @@ static __be32 nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp, struct nfsd4_sequence *seq) { + struct nfsd4_compoundargs *args = resp->rqstp->rq_argp; struct nfsd4_slot *slot = resp->cstate.slot; struct xdr_stream *xdr = resp->xdr; __be32 *p; - __be32 status; dprintk("--> %s slot %p\n", __func__, slot); - status = nfsd4_enc_sequence_replay(resp->rqstp->rq_argp, resp); - if (status) - return status; + /* Always encode the SEQUENCE response. */ + nfsd4_encode_operation(resp, &args->ops[0]); + if (args->opcnt == 1) + /* A solo SEQUENCE - nothing was cached */ + return args->ops[0].status; + + if (!(slot->sl_flags & NFSD4_SLOT_CACHED)) { + /* We weren't asked to cache this. */ + struct nfsd4_op *op; + + op = &args->ops[resp->opcnt++]; + op->status = nfserr_retry_uncached_rep; + nfsd4_encode_operation(resp, op); + return op->status; + } + /* return reply from cache */ p = xdr_reserve_space(xdr, slot->sl_datalen); if (!p) { WARN_ON_ONCE(1); @@ -3253,7 +3604,7 @@ static bool client_has_state(struct nfs4_client *clp) #endif || !list_empty(&clp->cl_delegations) || !list_empty(&clp->cl_sessions) - || !list_empty(&clp->async_copies); + || nfsd4_has_active_async_copies(clp); } static __be32 copy_impl_id(struct nfs4_client *clp, @@ -3291,6 +3642,12 @@ nfsd4_exchange_id(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, __func__, rqstp, exid, exid->clname.len, exid->clname.data, addr_str, exid->flags, exid->spa_how); + exid->server_impl_name = kasprintf(GFP_KERNEL, "%s %s %s %s", + utsname()->sysname, utsname()->release, + utsname()->version, utsname()->machine); + if (!exid->server_impl_name) + return nfserr_jukebox; + if (exid->flags & ~EXCHGID4_FLAG_MASK_A) return nfserr_inval; @@ -3416,6 +3773,9 @@ out_new: new->cl_spo_must_allow.u.words[0] = exid->spo_must_allow[0]; new->cl_spo_must_allow.u.words[1] = exid->spo_must_allow[1]; + /* Contrived initial CREATE_SESSION response */ + new->cl_cs_slot.sl_status = nfserr_seq_misordered; + add_to_unconfirmed(new); swap(new, conf); out_copy: @@ -3425,6 +3785,23 @@ out_copy: exid->seqid = conf->cl_cs_slot.sl_seqid + 1; nfsd4_set_ex_flags(conf, exid); + exid->nii_domain.len = sizeof("kernel.org") - 1; + exid->nii_domain.data = "kernel.org"; + + /* + * Note that RFC 8881 places no length limit on + * nii_name, but this implementation permits no + * more than NFS4_OPAQUE_LIMIT bytes. + */ + exid->nii_name.len = strlen(exid->server_impl_name); + if (exid->nii_name.len > NFS4_OPAQUE_LIMIT) + exid->nii_name.len = NFS4_OPAQUE_LIMIT; + exid->nii_name.data = exid->server_impl_name; + + /* just send zeros - the date is in nii_name */ + exid->nii_time.tv_sec = 0; + exid->nii_time.tv_nsec = 0; + dprintk("nfsd4_exchange_id seqid %d flags %x\n", conf->cl_cs_slot.sl_seqid, conf->cl_exchange_flags); status = nfs_ok; @@ -3441,14 +3818,18 @@ out_nolock: return status; } -static __be32 -check_slot_seqid(u32 seqid, u32 slot_seqid, int slot_inuse) +void +nfsd4_exchange_id_release(union nfsd4_op_u *u) { - dprintk("%s enter. seqid %d slot_seqid %d\n", __func__, seqid, - slot_seqid); + struct nfsd4_exchange_id *exid = &u->exchange_id; + kfree(exid->server_impl_name); +} + +static __be32 check_slot_seqid(u32 seqid, u32 slot_seqid, u8 flags) +{ /* The slot is in use, and no response has been sent. */ - if (slot_inuse) { + if (flags & NFSD4_SLOT_INUSE) { if (seqid == slot_seqid) return nfserr_jukebox; else @@ -3457,6 +3838,8 @@ check_slot_seqid(u32 seqid, u32 slot_seqid, int slot_inuse) /* Note unsigned 32-bit arithmetic handles wraparound: */ if (likely(seqid == slot_seqid + 1)) return nfs_ok; + if ((flags & NFSD4_SLOT_REUSED) && seqid == 1) + return nfs_ok; if (seqid == slot_seqid) return nfserr_replay_cache; return nfserr_seq_misordered; @@ -3515,17 +3898,6 @@ static __be32 check_forechannel_attrs(struct nfsd4_channel_attrs *ca, struct nfs ca->maxresp_cached = min_t(u32, ca->maxresp_cached, NFSD_SLOT_CACHE_SIZE + NFSD_MIN_HDR_SEQ_SZ); ca->maxreqs = min_t(u32, ca->maxreqs, NFSD_MAX_SLOTS_PER_SESSION); - /* - * Note decreasing slot size below client's request may make it - * difficult for client to function correctly, whereas - * decreasing the number of slots will (just?) affect - * performance. When short on memory we therefore prefer to - * decrease number of slots instead of their size. Clients that - * request larger slots than they need will get poor results: - * Note that we always allow at least one slot, because our - * accounting is soft and provides no guarantees either way. - */ - ca->maxreqs = nfsd4_get_drc_mem(ca, nn); return nfs_ok; } @@ -3586,10 +3958,10 @@ nfsd4_create_session(struct svc_rqst *rqstp, struct nfsd4_create_session *cr_ses = &u->create_session; struct sockaddr *sa = svc_addr(rqstp); struct nfs4_client *conf, *unconf; + struct nfsd4_clid_slot *cs_slot; struct nfs4_client *old = NULL; struct nfsd4_session *new; struct nfsd4_conn *conn; - struct nfsd4_clid_slot *cs_slot = NULL; __be32 status = 0; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); @@ -3603,76 +3975,89 @@ nfsd4_create_session(struct svc_rqst *rqstp, return status; status = check_backchannel_attrs(&cr_ses->back_channel); if (status) - goto out_release_drc_mem; + goto out_err; status = nfserr_jukebox; new = alloc_session(&cr_ses->fore_channel, &cr_ses->back_channel); if (!new) - goto out_release_drc_mem; + goto out_err; conn = alloc_conn_from_crses(rqstp, cr_ses); if (!conn) goto out_free_session; spin_lock(&nn->client_lock); + + /* RFC 8881 Section 18.36.4 Phase 1: Client record look-up. */ unconf = find_unconfirmed_client(&cr_ses->clientid, true, nn); conf = find_confirmed_client(&cr_ses->clientid, true, nn); - WARN_ON_ONCE(conf && unconf); + if (!conf && !unconf) { + status = nfserr_stale_clientid; + goto out_free_conn; + } + /* RFC 8881 Section 18.36.4 Phase 2: Sequence ID processing. */ + if (conf) { + cs_slot = &conf->cl_cs_slot; + trace_nfsd_slot_seqid_conf(conf, cr_ses); + } else { + cs_slot = &unconf->cl_cs_slot; + trace_nfsd_slot_seqid_unconf(unconf, cr_ses); + } + status = check_slot_seqid(cr_ses->seqid, cs_slot->sl_seqid, 0); + switch (status) { + case nfs_ok: + cs_slot->sl_seqid++; + cr_ses->seqid = cs_slot->sl_seqid; + break; + case nfserr_replay_cache: + status = nfsd4_replay_create_session(cr_ses, cs_slot); + fallthrough; + case nfserr_jukebox: + /* The server MUST NOT cache NFS4ERR_DELAY */ + goto out_free_conn; + default: + goto out_cache_error; + } + + /* RFC 8881 Section 18.36.4 Phase 3: Client ID confirmation. */ if (conf) { status = nfserr_wrong_cred; if (!nfsd4_mach_creds_match(conf, rqstp)) - goto out_free_conn; - cs_slot = &conf->cl_cs_slot; - status = check_slot_seqid(cr_ses->seqid, cs_slot->sl_seqid, 0); - if (status) { - if (status == nfserr_replay_cache) - status = nfsd4_replay_create_session(cr_ses, cs_slot); - goto out_free_conn; - } - } else if (unconf) { + goto out_cache_error; + } else { status = nfserr_clid_inuse; if (!same_creds(&unconf->cl_cred, &rqstp->rq_cred) || !rpc_cmp_addr(sa, (struct sockaddr *) &unconf->cl_addr)) { trace_nfsd_clid_cred_mismatch(unconf, rqstp); - goto out_free_conn; + goto out_cache_error; } status = nfserr_wrong_cred; if (!nfsd4_mach_creds_match(unconf, rqstp)) - goto out_free_conn; - cs_slot = &unconf->cl_cs_slot; - status = check_slot_seqid(cr_ses->seqid, cs_slot->sl_seqid, 0); - if (status) { - /* an unconfirmed replay returns misordered */ - status = nfserr_seq_misordered; - goto out_free_conn; - } + goto out_cache_error; old = find_confirmed_client_by_name(&unconf->cl_name, nn); if (old) { status = mark_client_expired_locked(old); - if (status) { - old = NULL; - goto out_free_conn; - } + if (status) + goto out_expired_error; trace_nfsd_clid_replaced(&old->cl_clientid); } move_to_confirmed(unconf); conf = unconf; - } else { - status = nfserr_stale_clientid; - goto out_free_conn; } + + /* RFC 8881 Section 18.36.4 Phase 4: Session creation. */ status = nfs_ok; /* Persistent sessions are not supported */ cr_ses->flags &= ~SESSION4_PERSIST; /* Upshifting from TCP to RDMA is not supported */ cr_ses->flags &= ~SESSION4_RDMA; + /* Report the correct number of backchannel slots */ + cr_ses->back_channel.maxreqs = new->se_cb_highest_slot + 1; init_session(rqstp, new, conf, cr_ses); nfsd4_get_session_locked(new); memcpy(cr_ses->sessionid.data, new->se_sessionid.data, NFS4_MAX_SESSIONID_LEN); - cs_slot->sl_seqid++; - cr_ses->seqid = cs_slot->sl_seqid; /* cache solo and embedded create sessions under the client_lock */ nfsd4_cache_create_session(cr_ses, cs_slot, status); @@ -3685,15 +4070,25 @@ nfsd4_create_session(struct svc_rqst *rqstp, if (old) expire_client(old); return status; + +out_expired_error: + /* + * Revert the slot seq_nr change so the server will process + * the client's resend instead of returning a cached response. + */ + if (status == nfserr_jukebox) { + cs_slot->sl_seqid--; + cr_ses->seqid = cs_slot->sl_seqid; + goto out_free_conn; + } +out_cache_error: + nfsd4_cache_create_session(cr_ses, cs_slot, status); out_free_conn: spin_unlock(&nn->client_lock); free_conn(conn); - if (old) - expire_client(old); out_free_session: __free_session(new); -out_release_drc_mem: - nfsd4_put_drc_mem(&cr_ses->fore_channel); +out_err: return status; } @@ -3946,6 +4341,36 @@ static bool replay_matches_cache(struct svc_rqst *rqstp, return true; } +/* + * Note that the response is constructed here both for the case + * of a new SEQUENCE request and for a replayed SEQUENCE request. + * We do not cache SEQUENCE responses as SEQUENCE is idempotent. + */ +static void nfsd4_construct_sequence_response(struct nfsd4_session *session, + struct nfsd4_sequence *seq) +{ + struct nfs4_client *clp = session->se_client; + + seq->maxslots_response = max(session->se_target_maxslots, + seq->maxslots); + seq->target_maxslots = session->se_target_maxslots; + + switch (clp->cl_cb_state) { + case NFSD4_CB_DOWN: + seq->status_flags = SEQ4_STATUS_CB_PATH_DOWN; + break; + case NFSD4_CB_FAULT: + seq->status_flags = SEQ4_STATUS_BACKCHANNEL_FAULT; + break; + default: + seq->status_flags = 0; + } + if (!list_empty(&clp->cl_revoked)) + seq->status_flags |= SEQ4_STATUS_RECALLABLE_STATE_REVOKED; + if (atomic_read(&clp->cl_admin_revoked)) + seq->status_flags |= SEQ4_STATUS_ADMIN_STATE_REVOKED; +} + __be32 nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) @@ -3991,16 +4416,14 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (seq->slotid >= session->se_fchannel.maxreqs) goto out_put_session; - slot = session->se_slots[seq->slotid]; + slot = xa_load(&session->se_slots, seq->slotid); dprintk("%s: slotid %d\n", __func__, seq->slotid); - /* We do not negotiate the number of slots yet, so set the - * maxslots to the session maxreqs which is used to encode - * sr_highest_slotid and the sr_target_slot id to maxslots */ - seq->maxslots = session->se_fchannel.maxreqs; + trace_nfsd_slot_seqid_sequence(clp, seq, slot); + + nfsd4_construct_sequence_response(session, seq); - status = check_slot_seqid(seq->seqid, slot->sl_seqid, - slot->sl_flags & NFSD4_SLOT_INUSE); + status = check_slot_seqid(seq->seqid, slot->sl_seqid, slot->sl_flags); if (status == nfserr_replay_cache) { status = nfserr_seq_misordered; if (!(slot->sl_flags & NFSD4_SLOT_INITIALIZED)) @@ -4025,6 +4448,12 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (status) goto out_put_session; + if (session->se_target_maxslots < session->se_fchannel.maxreqs && + slot->sl_generation == session->se_slot_gen && + seq->maxslots <= session->se_target_maxslots) + /* Client acknowledged our reduce maxreqs */ + free_session_slots(session, session->se_target_maxslots); + buflen = (seq->cachethis) ? session->se_fchannel.maxresp_cached : session->se_fchannel.maxresp_sz; @@ -4032,12 +4461,14 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, nfserr_rep_too_big; if (xdr_restrict_buflen(xdr, buflen - rqstp->rq_auth_slack)) goto out_put_session; - svc_reserve(rqstp, buflen); + svc_reserve_auth(rqstp, buflen); status = nfs_ok; - /* Success! bump slot seqid */ + /* Success! accept new slot seqid */ slot->sl_seqid = seq->seqid; + slot->sl_flags &= ~NFSD4_SLOT_REUSED; slot->sl_flags |= NFSD4_SLOT_INUSE; + slot->sl_generation = session->se_slot_gen; if (seq->cachethis) slot->sl_flags |= NFSD4_SLOT_CACHETHIS; else @@ -4047,19 +4478,49 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, cstate->session = session; cstate->clp = clp; -out: - switch (clp->cl_cb_state) { - case NFSD4_CB_DOWN: - seq->status_flags = SEQ4_STATUS_CB_PATH_DOWN; - break; - case NFSD4_CB_FAULT: - seq->status_flags = SEQ4_STATUS_BACKCHANNEL_FAULT; - break; - default: - seq->status_flags = 0; + /* + * If the client ever uses the highest available slot, + * gently try to allocate another 20%. This allows + * fairly quick growth without grossly over-shooting what + * the client might use. + */ + if (seq->slotid == session->se_fchannel.maxreqs - 1 && + session->se_target_maxslots >= session->se_fchannel.maxreqs && + session->se_fchannel.maxreqs < NFSD_MAX_SLOTS_PER_SESSION) { + int s = session->se_fchannel.maxreqs; + int cnt = DIV_ROUND_UP(s, 5); + void *prev_slot; + + do { + /* + * GFP_NOWAIT both allows allocation under a + * spinlock, and only succeeds if there is + * plenty of memory. + */ + slot = nfsd4_alloc_slot(&session->se_fchannel, s, + GFP_NOWAIT); + prev_slot = xa_load(&session->se_slots, s); + if (xa_is_value(prev_slot) && slot) { + slot->sl_seqid = xa_to_value(prev_slot); + slot->sl_flags |= NFSD4_SLOT_REUSED; + } + if (slot && + !xa_is_err(xa_store(&session->se_slots, s, slot, + GFP_NOWAIT))) { + s += 1; + session->se_fchannel.maxreqs = s; + atomic_add(s - session->se_target_maxslots, + &nfsd_total_target_slots); + session->se_target_maxslots = s; + } else { + kfree(slot); + slot = NULL; + } + } while (slot && --cnt > 0); } - if (!list_empty(&clp->cl_revoked)) - seq->status_flags |= SEQ4_STATUS_RECALLABLE_STATE_REVOKED; + +out: + trace_nfsd_seq4_status(rqstp, seq); out_no_session: if (conn) free_conn(conn); @@ -4274,10 +4735,16 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp, } status = nfs_ok; if (conf) { - old = unconf; - unhash_client_locked(old); - nfsd4_change_callback(conf, &unconf->cl_cb_conn); - } else { + if (get_client_locked(conf) == nfs_ok) { + old = unconf; + unhash_client_locked(old); + nfsd4_change_callback(conf, &unconf->cl_cb_conn); + } else { + conf = NULL; + } + } + + if (!conf) { old = find_confirmed_client_by_name(&unconf->cl_name, nn); if (old) { status = nfserr_clid_inuse; @@ -4294,10 +4761,14 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp, } trace_nfsd_clid_replaced(&old->cl_clientid); } + status = get_client_locked(unconf); + if (status != nfs_ok) { + old = NULL; + goto out; + } move_to_confirmed(unconf); conf = unconf; } - get_client_locked(conf); spin_unlock(&nn->client_lock); if (conf == unconf) fsnotify_dentry(conf->cl_nfsd_info_dentry, FS_MODIFY); @@ -4327,6 +4798,7 @@ static void nfsd4_file_init(const struct svc_fh *fh, struct nfs4_file *fp) INIT_LIST_HEAD(&fp->fi_clnt_odstate); fh_copy_shallow(&fp->fi_fhandle, &fh->fh_handle); fp->fi_deleg_file = NULL; + fp->fi_rdeleg_file = NULL; fp->fi_had_conflict = false; fp->fi_share_deny = 0; memset(fp->fi_fds, 0, sizeof(fp->fi_fds)); @@ -4354,32 +4826,25 @@ nfsd4_free_slabs(void) int nfsd4_init_slabs(void) { - client_slab = kmem_cache_create("nfsd4_clients", - sizeof(struct nfs4_client), 0, 0, NULL); + client_slab = KMEM_CACHE(nfs4_client, 0); if (client_slab == NULL) goto out; - openowner_slab = kmem_cache_create("nfsd4_openowners", - sizeof(struct nfs4_openowner), 0, 0, NULL); + openowner_slab = KMEM_CACHE(nfs4_openowner, 0); if (openowner_slab == NULL) goto out_free_client_slab; - lockowner_slab = kmem_cache_create("nfsd4_lockowners", - sizeof(struct nfs4_lockowner), 0, 0, NULL); + lockowner_slab = KMEM_CACHE(nfs4_lockowner, 0); if (lockowner_slab == NULL) goto out_free_openowner_slab; - file_slab = kmem_cache_create("nfsd4_files", - sizeof(struct nfs4_file), 0, 0, NULL); + file_slab = KMEM_CACHE(nfs4_file, 0); if (file_slab == NULL) goto out_free_lockowner_slab; - stateid_slab = kmem_cache_create("nfsd4_stateids", - sizeof(struct nfs4_ol_stateid), 0, 0, NULL); + stateid_slab = KMEM_CACHE(nfs4_ol_stateid, 0); if (stateid_slab == NULL) goto out_free_file_slab; - deleg_slab = kmem_cache_create("nfsd4_delegations", - sizeof(struct nfs4_delegation), 0, 0, NULL); + deleg_slab = KMEM_CACHE(nfs4_delegation, 0); if (deleg_slab == NULL) goto out_free_stateid_slab; - odstate_slab = kmem_cache_create("nfsd4_odstate", - sizeof(struct nfs4_clnt_odstate), 0, 0, NULL); + odstate_slab = KMEM_CACHE(nfs4_clnt_odstate, 0); if (odstate_slab == NULL) goto out_free_deleg_slab; return 0; @@ -4403,9 +4868,8 @@ out: static unsigned long nfsd4_state_shrinker_count(struct shrinker *shrink, struct shrink_control *sc) { - int count; - struct nfsd_net *nn = container_of(shrink, - struct nfsd_net, nfsd_client_shrinker); + struct nfsd_net *nn = shrink->private_data; + long count; count = atomic_read(&nn->nfsd_courtesy_clients); if (!count) @@ -4445,21 +4909,32 @@ nfsd4_init_leases_net(struct nfsd_net *nn) atomic_set(&nn->nfsd_courtesy_clients, 0); } +enum rp_lock { + RP_UNLOCKED, + RP_LOCKED, + RP_UNHASHED, +}; + static void init_nfs4_replay(struct nfs4_replay *rp) { rp->rp_status = nfserr_serverfault; rp->rp_buflen = 0; rp->rp_buf = rp->rp_ibuf; - mutex_init(&rp->rp_mutex); + rp->rp_locked = RP_UNLOCKED; } -static void nfsd4_cstate_assign_replay(struct nfsd4_compound_state *cstate, - struct nfs4_stateowner *so) +static int nfsd4_cstate_assign_replay(struct nfsd4_compound_state *cstate, + struct nfs4_stateowner *so) { if (!nfsd4_has_session(cstate)) { - mutex_lock(&so->so_replay.rp_mutex); + wait_var_event(&so->so_replay.rp_locked, + cmpxchg(&so->so_replay.rp_locked, + RP_UNLOCKED, RP_LOCKED) != RP_LOCKED); + if (so->so_replay.rp_locked == RP_UNHASHED) + return -EAGAIN; cstate->replay_owner = nfs4_get_stateowner(so); } + return 0; } void nfsd4_cstate_clear_replay(struct nfsd4_compound_state *cstate) @@ -4468,7 +4943,7 @@ void nfsd4_cstate_clear_replay(struct nfsd4_compound_state *cstate) if (so != NULL) { cstate->replay_owner = NULL; - mutex_unlock(&so->so_replay.rp_mutex); + store_release_wake_up(&so->so_replay.rp_locked, RP_UNLOCKED); nfs4_put_stateowner(so); } } @@ -4534,7 +5009,8 @@ nfsd4_find_existing_open(struct nfs4_file *fp, struct nfsd4_open *open) continue; if (local->st_stateowner != &oo->oo_owner) continue; - if (local->st_stid.sc_type == NFS4_OPEN_STID) { + if (local->st_stid.sc_type == SC_TYPE_OPEN && + !local->st_stid.sc_status) { ret = local; refcount_inc(&ret->st_stid.sc_count); break; @@ -4543,22 +5019,75 @@ nfsd4_find_existing_open(struct nfs4_file *fp, struct nfsd4_open *open) return ret; } -static __be32 -nfsd4_verify_open_stid(struct nfs4_stid *s) +static void nfsd4_drop_revoked_stid(struct nfs4_stid *s) + __releases(&s->sc_client->cl_lock) { - __be32 ret = nfs_ok; + struct nfs4_client *cl = s->sc_client; + LIST_HEAD(reaplist); + struct nfs4_ol_stateid *stp; + struct nfs4_delegation *dp; + bool unhashed; switch (s->sc_type) { - default: + case SC_TYPE_OPEN: + stp = openlockstateid(s); + if (unhash_open_stateid(stp, &reaplist)) + put_ol_stateid_locked(stp, &reaplist); + spin_unlock(&cl->cl_lock); + free_ol_stateid_reaplist(&reaplist); break; - case 0: - case NFS4_CLOSED_STID: - case NFS4_CLOSED_DELEG_STID: - ret = nfserr_bad_stateid; + case SC_TYPE_LOCK: + stp = openlockstateid(s); + unhashed = unhash_lock_stateid(stp); + spin_unlock(&cl->cl_lock); + if (unhashed) + nfs4_put_stid(s); break; - case NFS4_REVOKED_DELEG_STID: - ret = nfserr_deleg_revoked; + case SC_TYPE_DELEG: + dp = delegstateid(s); + list_del_init(&dp->dl_recall_lru); + spin_unlock(&cl->cl_lock); + nfs4_put_stid(s); + break; + default: + spin_unlock(&cl->cl_lock); } +} + +static void nfsd40_drop_revoked_stid(struct nfs4_client *cl, + stateid_t *stid) +{ + /* NFSv4.0 has no way for the client to tell the server + * that it can forget an admin-revoked stateid. + * So we keep it around until the first time that the + * client uses it, and drop it the first time + * nfserr_admin_revoked is returned. + * For v4.1 and later we wait until explicitly told + * to free the stateid. + */ + if (cl->cl_minorversion == 0) { + struct nfs4_stid *st; + + spin_lock(&cl->cl_lock); + st = find_stateid_locked(cl, stid); + if (st) + nfsd4_drop_revoked_stid(st); + else + spin_unlock(&cl->cl_lock); + } +} + +static __be32 +nfsd4_verify_open_stid(struct nfs4_stid *s) +{ + __be32 ret = nfs_ok; + + if (s->sc_status & SC_STATUS_ADMIN_REVOKED) + ret = nfserr_admin_revoked; + else if (s->sc_status & SC_STATUS_REVOKED) + ret = nfserr_deleg_revoked; + else if (s->sc_status & SC_STATUS_CLOSED) + ret = nfserr_bad_stateid; return ret; } @@ -4570,6 +5099,10 @@ nfsd4_lock_ol_stateid(struct nfs4_ol_stateid *stp) mutex_lock_nested(&stp->st_mutex, LOCK_STATEID_MUTEX); ret = nfsd4_verify_open_stid(&stp->st_stid); + if (ret == nfserr_admin_revoked) + nfsd40_drop_revoked_stid(stp->st_stid.sc_client, + &stp->st_stid.sc_stateid); + if (ret != nfs_ok) mutex_unlock(&stp->st_mutex); return ret; @@ -4591,34 +5124,46 @@ nfsd4_find_and_lock_existing_open(struct nfs4_file *fp, struct nfsd4_open *open) } static struct nfs4_openowner * -alloc_init_open_stateowner(unsigned int strhashval, struct nfsd4_open *open, - struct nfsd4_compound_state *cstate) +find_or_alloc_open_stateowner(unsigned int strhashval, struct nfsd4_open *open, + struct nfsd4_compound_state *cstate) { struct nfs4_client *clp = cstate->clp; - struct nfs4_openowner *oo, *ret; + struct nfs4_openowner *oo, *new = NULL; - oo = alloc_stateowner(openowner_slab, &open->op_owner, clp); - if (!oo) - return NULL; - oo->oo_owner.so_ops = &openowner_ops; - oo->oo_owner.so_is_open_owner = 1; - oo->oo_owner.so_seqid = open->op_seqid; - oo->oo_flags = 0; - if (nfsd4_has_session(cstate)) - oo->oo_flags |= NFS4_OO_CONFIRMED; - oo->oo_time = 0; - oo->oo_last_closed_stid = NULL; - INIT_LIST_HEAD(&oo->oo_close_lru); +retry: spin_lock(&clp->cl_lock); - ret = find_openstateowner_str_locked(strhashval, open, clp); - if (ret == NULL) { - hash_openowner(oo, clp, strhashval); - ret = oo; - } else - nfs4_free_stateowner(&oo->oo_owner); - + oo = find_openstateowner_str(strhashval, open, clp); + if (!oo && new) { + hash_openowner(new, clp, strhashval); + spin_unlock(&clp->cl_lock); + return new; + } spin_unlock(&clp->cl_lock); - return ret; + + if (oo && !(oo->oo_flags & NFS4_OO_CONFIRMED)) { + /* Replace unconfirmed owners without checking for replay. */ + release_openowner(oo); + oo = NULL; + } + if (oo) { + if (new) + nfs4_free_stateowner(&new->oo_owner); + return oo; + } + + new = alloc_stateowner(openowner_slab, &open->op_owner, clp); + if (!new) + return NULL; + new->oo_owner.so_ops = &openowner_ops; + new->oo_owner.so_is_open_owner = 1; + new->oo_owner.so_seqid = open->op_seqid; + new->oo_flags = 0; + if (nfsd4_has_session(cstate)) + new->oo_flags |= NFS4_OO_CONFIRMED; + new->oo_time = 0; + new->oo_last_closed_stid = NULL; + INIT_LIST_HEAD(&new->oo_close_lru); + goto retry; } static struct nfs4_ol_stateid * @@ -4638,13 +5183,19 @@ retry: spin_lock(&oo->oo_owner.so_client->cl_lock); spin_lock(&fp->fi_lock); + if (nfs4_openowner_unhashed(oo)) { + mutex_unlock(&stp->st_mutex); + stp = NULL; + goto out_unlock; + } + retstp = nfsd4_find_existing_open(fp, open); if (retstp) goto out_unlock; open->op_stp = NULL; refcount_inc(&stp->st_stid.sc_count); - stp->st_stid.sc_type = NFS4_OPEN_STID; + stp->st_stid.sc_type = SC_TYPE_OPEN; INIT_LIST_HEAD(&stp->st_locks); stp->st_stateowner = nfs4_get_stateowner(&oo->oo_owner); get_nfs4_file(fp); @@ -4694,7 +5245,10 @@ move_to_close_lru(struct nfs4_ol_stateid *s, struct net *net) * Wait for the refcount to drop to 2. Since it has been unhashed, * there should be no danger of the refcount going back up again at * this point. + * Some threads with a reference might be waiting for rp_locked, + * so tell them to stop waiting. */ + store_release_wake_up(&oo->oo_owner.so_replay.rp_locked, RP_UNHASHED); wait_event(close_wq, refcount_read(&s->st_stid.sc_count) == 2); release_all_access(s); @@ -4871,9 +5425,9 @@ static int nfsd4_cb_recall_done(struct nfsd4_callback *cb, trace_nfsd_cb_recall_done(&dp->dl_stid.sc_stateid, task); - if (dp->dl_stid.sc_type == NFS4_CLOSED_DELEG_STID || - dp->dl_stid.sc_type == NFS4_REVOKED_DELEG_STID) - return 1; + if (dp->dl_stid.sc_status) + /* CLOSED or REVOKED */ + return 1; switch (task->tk_status) { case 0: @@ -4908,10 +5462,16 @@ static const struct nfsd4_callback_ops nfsd4_cb_recall_ops = { .prepare = nfsd4_cb_recall_prepare, .done = nfsd4_cb_recall_done, .release = nfsd4_cb_recall_release, + .opcode = OP_CB_RECALL, }; static void nfsd_break_one_deleg(struct nfs4_delegation *dp) { + bool queued; + + if (test_and_set_bit(NFSD4_CALLBACK_RUNNING, &dp->dl_recall.cb_flags)) + return; + /* * We're assuming the state code never drops its reference * without first removing the lease. Since we're in this lease @@ -4920,14 +5480,17 @@ static void nfsd_break_one_deleg(struct nfs4_delegation *dp) * we know it's safe to take a reference. */ refcount_inc(&dp->dl_stid.sc_count); - WARN_ON_ONCE(!nfsd4_run_cb(&dp->dl_recall)); + queued = nfsd4_run_cb(&dp->dl_recall); + WARN_ON_ONCE(!queued); + if (!queued) + refcount_dec(&dp->dl_stid.sc_count); } /* Called from break_lease() with flc_lock held. */ static bool -nfsd_break_deleg_cb(struct file_lock *fl) +nfsd_break_deleg_cb(struct file_lease *fl) { - struct nfs4_delegation *dp = (struct nfs4_delegation *)fl->fl_owner; + struct nfs4_delegation *dp = (struct nfs4_delegation *) fl->c.flc_owner; struct nfs4_file *fp = dp->dl_stid.sc_file; struct nfs4_client *clp = dp->dl_stid.sc_client; struct nfsd_net *nn; @@ -4948,10 +5511,8 @@ nfsd_break_deleg_cb(struct file_lock *fl) */ fl->fl_break_time = 0; - spin_lock(&fp->fi_lock); fp->fi_had_conflict = true; nfsd_break_one_deleg(dp); - spin_unlock(&fp->fi_lock); return false; } @@ -4963,27 +5524,24 @@ nfsd_break_deleg_cb(struct file_lock *fl) * %true: Lease conflict was resolved * %false: Lease conflict was not resolved. */ -static bool nfsd_breaker_owns_lease(struct file_lock *fl) +static bool nfsd_breaker_owns_lease(struct file_lease *fl) { - struct nfs4_delegation *dl = fl->fl_owner; + struct nfs4_delegation *dl = fl->c.flc_owner; struct svc_rqst *rqst; struct nfs4_client *clp; - if (!i_am_nfsd()) - return false; - rqst = kthread_data(current); - /* Note rq_prog == NFS_ACL_PROGRAM is also possible: */ - if (rqst->rq_prog != NFS_PROGRAM || rqst->rq_vers < 4) + rqst = nfsd_current_rqst(); + if (!nfsd_v4client(rqst)) return false; clp = *(rqst->rq_lease_breaker); return dl->dl_stid.sc_client == clp; } static int -nfsd_change_deleg_cb(struct file_lock *onlist, int arg, +nfsd_change_deleg_cb(struct file_lease *onlist, int arg, struct list_head *dispose) { - struct nfs4_delegation *dp = (struct nfs4_delegation *)onlist->fl_owner; + struct nfs4_delegation *dp = (struct nfs4_delegation *) onlist->c.flc_owner; struct nfs4_client *clp = dp->dl_stid.sc_client; if (arg & F_UNLCK) { @@ -4994,7 +5552,7 @@ nfsd_change_deleg_cb(struct file_lock *onlist, int arg, return -EAGAIN; } -static const struct lock_manager_operations nfsd_lease_mng_ops = { +static const struct lease_manager_operations nfsd_lease_mng_ops = { .lm_breaker_owns_lease = nfsd_breaker_owns_lease, .lm_break = nfsd_break_deleg_cb, .lm_change = nfsd_change_deleg_cb, @@ -5069,27 +5627,19 @@ nfsd4_process_open1(struct nfsd4_compound_state *cstate, clp = cstate->clp; strhashval = ownerstr_hashval(&open->op_owner); - oo = find_openstateowner_str(strhashval, open, clp); +retry: + oo = find_or_alloc_open_stateowner(strhashval, open, cstate); open->op_openowner = oo; - if (!oo) { - goto new_owner; - } - if (!(oo->oo_flags & NFS4_OO_CONFIRMED)) { - /* Replace unconfirmed owners without checking for replay. */ - release_openowner(oo); - open->op_openowner = NULL; - goto new_owner; + if (!oo) + return nfserr_jukebox; + if (nfsd4_cstate_assign_replay(cstate, &oo->oo_owner) == -EAGAIN) { + nfs4_put_stateowner(&oo->oo_owner); + goto retry; } status = nfsd4_check_seqid(cstate, &oo->oo_owner, open->op_seqid); if (status) return status; - goto alloc_stateid; -new_owner: - oo = alloc_init_open_stateowner(strhashval, open, cstate); - if (oo == NULL) - return nfserr_jukebox; - open->op_openowner = oo; -alloc_stateid: + open->op_stp = nfs4_alloc_open_stateid(clp); if (!open->op_stp) return nfserr_jukebox; @@ -5107,7 +5657,7 @@ alloc_stateid: static inline __be32 nfs4_check_delegmode(struct nfs4_delegation *dp, int flags) { - if ((flags & WR_STATE) && (dp->dl_type == NFS4_OPEN_DELEGATE_READ)) + if (!(flags & RD_STATE) && deleg_is_read(dp->dl_type)) return nfserr_openmode; else return nfs_ok; @@ -5118,12 +5668,12 @@ static int share_access_to_flags(u32 share_access) return share_access == NFS4_SHARE_ACCESS_READ ? RD_STATE : WR_STATE; } -static struct nfs4_delegation *find_deleg_stateid(struct nfs4_client *cl, stateid_t *s) +static struct nfs4_delegation *find_deleg_stateid(struct nfs4_client *cl, + stateid_t *s) { struct nfs4_stid *ret; - ret = find_stateid_by_type(cl, s, - NFS4_DELEG_STID|NFS4_REVOKED_DELEG_STID); + ret = find_stateid_by_type(cl, s, SC_TYPE_DELEG, SC_STATUS_REVOKED); if (!ret) return NULL; return delegstateid(ret); @@ -5146,10 +5696,15 @@ nfs4_check_deleg(struct nfs4_client *cl, struct nfsd4_open *open, deleg = find_deleg_stateid(cl, &open->op_delegate_stateid); if (deleg == NULL) goto out; - if (deleg->dl_stid.sc_type == NFS4_REVOKED_DELEG_STID) { + if (deleg->dl_stid.sc_status & SC_STATUS_ADMIN_REVOKED) { nfs4_put_stid(&deleg->dl_stid); - if (cl->cl_minorversion) - status = nfserr_deleg_revoked; + status = nfserr_admin_revoked; + goto out; + } + if (deleg->dl_stid.sc_status & SC_STATUS_REVOKED) { + nfs4_put_stid(&deleg->dl_stid); + nfsd40_drop_revoked_stid(cl, &open->op_delegate_stateid); + status = nfserr_deleg_revoked; goto out; } flags = share_access_to_flags(open->op_share_access); @@ -5194,7 +5749,7 @@ nfsd4_truncate(struct svc_rqst *rqstp, struct svc_fh *fh, return 0; if (!(open->op_share_access & NFS4_SHARE_ACCESS_WRITE)) return nfserr_inval; - return nfsd_setattr(rqstp, fh, &attrs, 0, (time64_t)0); + return nfsd_setattr(rqstp, fh, &attrs, NULL); } static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp, @@ -5298,16 +5853,17 @@ nfs4_upgrade_open(struct svc_rqst *rqstp, struct nfs4_file *fp, /* test and set deny mode */ spin_lock(&fp->fi_lock); status = nfs4_file_check_deny(fp, open->op_share_deny); - if (status == nfs_ok) { - if (status != nfserr_share_denied) { - set_deny(open->op_share_deny, stp); - fp->fi_share_deny |= - (open->op_share_deny & NFS4_SHARE_DENY_BOTH); - } else { - if (nfs4_resolve_deny_conflicts_locked(fp, false, - stp, open->op_share_deny, false)) - status = nfserr_jukebox; - } + switch (status) { + case nfs_ok: + set_deny(open->op_share_deny, stp); + fp->fi_share_deny |= + (open->op_share_deny & NFS4_SHARE_DENY_BOTH); + break; + case nfserr_share_denied: + if (nfs4_resolve_deny_conflicts_locked(fp, false, + stp, open->op_share_deny, false)) + status = nfserr_jukebox; + break; } spin_unlock(&fp->fi_lock); @@ -5333,21 +5889,19 @@ static bool nfsd4_cb_channel_good(struct nfs4_client *clp) return clp->cl_minorversion && clp->cl_cb_state == NFSD4_CB_UNKNOWN; } -static struct file_lock *nfs4_alloc_init_lease(struct nfs4_delegation *dp, - int flag) +static struct file_lease *nfs4_alloc_init_lease(struct nfs4_delegation *dp) { - struct file_lock *fl; + struct file_lease *fl; - fl = locks_alloc_lock(); + fl = locks_alloc_lease(); if (!fl) return NULL; fl->fl_lmops = &nfsd_lease_mng_ops; - fl->fl_flags = FL_DELEG; - fl->fl_type = flag == NFS4_OPEN_DELEGATE_READ? F_RDLCK: F_WRLCK; - fl->fl_end = OFFSET_MAX; - fl->fl_owner = (fl_owner_t)dp; - fl->fl_pid = current->tgid; - fl->fl_file = dp->dl_stid.sc_file->fi_deleg_file->nf_file; + fl->c.flc_flags = FL_DELEG; + fl->c.flc_type = deleg_is_read(dp->dl_type) ? F_RDLCK : F_WRLCK; + fl->c.flc_owner = (fl_owner_t)dp; + fl->c.flc_pid = current->tgid; + fl->c.flc_file = dp->dl_stid.sc_file->fi_deleg_file->nf_file; return fl; } @@ -5356,7 +5910,7 @@ static int nfsd4_check_conflicting_opens(struct nfs4_client *clp, { struct nfs4_ol_stateid *st; struct file *f = fp->fi_deleg_file->nf_file; - struct inode *ino = locks_inode(f); + struct inode *ino = file_inode(f); int writes; writes = atomic_read(&ino->i_writecount); @@ -5438,17 +5992,48 @@ nfsd4_verify_deleg_dentry(struct nfsd4_open *open, struct nfs4_file *fp, return 0; } +/* + * We avoid breaking delegations held by a client due to its own activity, but + * clearing setuid/setgid bits on a write is an implicit activity and the client + * may not notice and continue using the old mode. Avoid giving out a delegation + * on setuid/setgid files when the client is requesting an open for write. + */ +static int +nfsd4_verify_setuid_write(struct nfsd4_open *open, struct nfsd_file *nf) +{ + struct inode *inode = file_inode(nf->nf_file); + + if ((open->op_share_access & NFS4_SHARE_ACCESS_WRITE) && + (inode->i_mode & (S_ISUID|S_ISGID))) + return -EAGAIN; + return 0; +} + +#ifdef CONFIG_NFSD_V4_DELEG_TIMESTAMPS +static bool nfsd4_want_deleg_timestamps(const struct nfsd4_open *open) +{ + return open->op_deleg_want & OPEN4_SHARE_ACCESS_WANT_DELEG_TIMESTAMPS; +} +#else /* CONFIG_NFSD_V4_DELEG_TIMESTAMPS */ +static bool nfsd4_want_deleg_timestamps(const struct nfsd4_open *open) +{ + return false; +} +#endif /* CONFIG NFSD_V4_DELEG_TIMESTAMPS */ + static struct nfs4_delegation * nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, struct svc_fh *parent) { - int status = 0; + bool deleg_ts = nfsd4_want_deleg_timestamps(open); struct nfs4_client *clp = stp->st_stid.sc_client; struct nfs4_file *fp = stp->st_stid.sc_file; struct nfs4_clnt_odstate *odstate = stp->st_clnt_odstate; struct nfs4_delegation *dp; - struct nfsd_file *nf; - struct file_lock *fl; + struct nfsd_file *nf = NULL; + struct file_lease *fl; + int status = 0; + u32 dl_type; /* * The fi_had_conflict and nfs_get_existing_delegation checks @@ -5458,19 +6043,55 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, if (fp->fi_had_conflict) return ERR_PTR(-EAGAIN); - nf = find_readable_file(fp); - if (!nf) { - /* - * We probably could attempt another open and get a read - * delegation, but for now, don't bother until the - * client actually sends us one. - */ + /* + * Try for a write delegation first. RFC8881 section 10.4 says: + * + * "An OPEN_DELEGATE_WRITE delegation allows the client to handle, + * on its own, all opens." + * + * Furthermore, section 9.1.2 says: + * + * "In the case of READ, the server may perform the corresponding + * check on the access mode, or it may choose to allow READ for + * OPEN4_SHARE_ACCESS_WRITE, to accommodate clients whose WRITE + * implementation may unavoidably do reads (e.g., due to buffer + * cache constraints)." + * + * We choose to offer a write delegation for OPEN with the + * OPEN4_SHARE_ACCESS_WRITE access mode to accommodate such clients. + */ + if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE) { + nf = find_writeable_file(fp); + dl_type = deleg_ts ? OPEN_DELEGATE_WRITE_ATTRS_DELEG : OPEN_DELEGATE_WRITE; + } + + /* + * If the file is being opened O_RDONLY or we couldn't get a O_RDWR + * file for some reason, then try for a read delegation instead. + */ + if (!nf && (open->op_share_access & NFS4_SHARE_ACCESS_READ)) { + nf = find_readable_file(fp); + dl_type = deleg_ts ? OPEN_DELEGATE_READ_ATTRS_DELEG : OPEN_DELEGATE_READ; + } + + if (!nf) return ERR_PTR(-EAGAIN); + + /* + * File delegations and associated locks cannot be recovered if the + * export is from an NFS proxy server. + */ + if (exportfs_cannot_lock(nf->nf_file->f_path.mnt->mnt_sb->s_export_op)) { + nfsd_file_put(nf); + return ERR_PTR(-EOPNOTSUPP); } + spin_lock(&state_lock); spin_lock(&fp->fi_lock); if (nfs4_delegation_exists(clp, fp)) status = -EAGAIN; + else if (nfsd4_verify_setuid_write(open, nf)) + status = -EAGAIN; else if (!fp->fi_deleg_file) { fp->fi_deleg_file = nf; /* increment early to prevent fi_deleg_file from being @@ -5487,17 +6108,18 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, return ERR_PTR(status); status = -ENOMEM; - dp = alloc_init_deleg(clp, fp, odstate); + dp = alloc_init_deleg(clp, fp, odstate, dl_type); if (!dp) goto out_delegees; - fl = nfs4_alloc_init_lease(dp, NFS4_OPEN_DELEGATE_READ); + fl = nfs4_alloc_init_lease(dp); if (!fl) goto out_clnt_odstate; - status = vfs_setlease(fp->fi_deleg_file->nf_file, fl->fl_type, &fl, NULL); + status = kernel_setlease(fp->fi_deleg_file->nf_file, + fl->c.flc_type, &fl, NULL); if (fl) - locks_free_lock(fl); + locks_free_lease(fl); if (status) goto out_clnt_odstate; @@ -5511,13 +6133,24 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, if (status) goto out_unlock; + /* + * Now that the deleg is set, check again to ensure that nothing + * raced in and changed the mode while we weren't looking. + */ + status = nfsd4_verify_setuid_write(open, fp->fi_deleg_file); + if (status) + goto out_unlock; + + status = -EAGAIN; + if (fp->fi_had_conflict) + goto out_unlock; + spin_lock(&state_lock); + spin_lock(&clp->cl_lock); spin_lock(&fp->fi_lock); - if (fp->fi_had_conflict) - status = -EAGAIN; - else - status = hash_delegation_locked(dp, fp); + status = hash_delegation_locked(dp, fp); spin_unlock(&fp->fi_lock); + spin_unlock(&clp->cl_lock); spin_unlock(&state_lock); if (status) @@ -5525,7 +6158,7 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, return dp; out_unlock: - vfs_setlease(fp->fi_deleg_file->nf_file, F_UNLCK, NULL, (void **)&dp); + kernel_setlease(fp->fi_deleg_file->nf_file, F_UNLCK, NULL, (void **)&dp); out_clnt_odstate: put_clnt_odstate(dp->dl_clnt_odstate); nfs4_put_stid(&dp->dl_stid); @@ -5536,50 +6169,120 @@ out_delegees: static void nfsd4_open_deleg_none_ext(struct nfsd4_open *open, int status) { - open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT; + open->op_delegate_type = OPEN_DELEGATE_NONE_EXT; if (status == -EAGAIN) open->op_why_no_deleg = WND4_CONTENTION; else { open->op_why_no_deleg = WND4_RESOURCE; switch (open->op_deleg_want) { - case NFS4_SHARE_WANT_READ_DELEG: - case NFS4_SHARE_WANT_WRITE_DELEG: - case NFS4_SHARE_WANT_ANY_DELEG: + case OPEN4_SHARE_ACCESS_WANT_READ_DELEG: + case OPEN4_SHARE_ACCESS_WANT_WRITE_DELEG: + case OPEN4_SHARE_ACCESS_WANT_ANY_DELEG: break; - case NFS4_SHARE_WANT_CANCEL: + case OPEN4_SHARE_ACCESS_WANT_CANCEL: open->op_why_no_deleg = WND4_CANCELLED; break; - case NFS4_SHARE_WANT_NO_DELEG: + case OPEN4_SHARE_ACCESS_WANT_NO_DELEG: WARN_ON_ONCE(1); } } } +static bool +nfs4_delegation_stat(struct nfs4_delegation *dp, struct svc_fh *currentfh, + struct kstat *stat) +{ + struct nfsd_file *nf = find_writeable_file(dp->dl_stid.sc_file); + struct path path; + int rc; + + if (!nf) + return false; + + path.mnt = currentfh->fh_export->ex_path.mnt; + path.dentry = file_dentry(nf->nf_file); + + rc = vfs_getattr(&path, stat, + STATX_MODE | STATX_SIZE | STATX_ATIME | + STATX_MTIME | STATX_CTIME | STATX_CHANGE_COOKIE, + AT_STATX_SYNC_AS_STAT); + + nfsd_file_put(nf); + return rc == 0; +} + /* - * Attempt to hand out a delegation. + * Add NFS4_SHARE_ACCESS_READ to the write delegation granted on OPEN + * with NFS4_SHARE_ACCESS_WRITE by allocating separate nfsd_file and + * struct file to be used for read with delegation stateid. * - * Note we don't support write delegations, and won't until the vfs has - * proper support for them. + */ +static bool +nfsd4_add_rdaccess_to_wrdeleg(struct svc_rqst *rqstp, struct nfsd4_open *open, + struct svc_fh *fh, struct nfs4_ol_stateid *stp) +{ + struct nfs4_file *fp; + struct nfsd_file *nf = NULL; + + if ((open->op_share_access & NFS4_SHARE_ACCESS_BOTH) == + NFS4_SHARE_ACCESS_WRITE) { + if (nfsd_file_acquire_opened(rqstp, fh, NFSD_MAY_READ, NULL, &nf)) + return (false); + fp = stp->st_stid.sc_file; + spin_lock(&fp->fi_lock); + __nfs4_file_get_access(fp, NFS4_SHARE_ACCESS_READ); + fp = stp->st_stid.sc_file; + fp->fi_fds[O_RDONLY] = nf; + fp->fi_rdeleg_file = nf; + spin_unlock(&fp->fi_lock); + } + return true; +} + +/* + * The Linux NFS server does not offer write delegations to NFSv4.0 + * clients in order to avoid conflicts between write delegations and + * GETATTRs requesting CHANGE or SIZE attributes. + * + * With NFSv4.1 and later minorversions, the SEQUENCE operation that + * begins each COMPOUND contains a client ID. Delegation recall can + * be avoided when the server recognizes the client sending a + * GETATTR also holds write delegation it conflicts with. + * + * However, the NFSv4.0 protocol does not enable a server to + * determine that a GETATTR originated from the client holding the + * conflicting delegation versus coming from some other client. Per + * RFC 7530 Section 16.7.5, the server must recall or send a + * CB_GETATTR even when the GETATTR originates from the client that + * holds the conflicting delegation. + * + * An NFSv4.0 client can trigger a pathological situation if it + * always sends a DELEGRETURN preceded by a conflicting GETATTR in + * the same COMPOUND. COMPOUND execution will always stop at the + * GETATTR and the DELEGRETURN will never get executed. The server + * eventually revokes the delegation, which can result in loss of + * open or lock state. */ static void -nfs4_open_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, - struct svc_fh *currentfh) +nfs4_open_delegation(struct svc_rqst *rqstp, struct nfsd4_open *open, + struct nfs4_ol_stateid *stp, struct svc_fh *currentfh, + struct svc_fh *fh) { - struct nfs4_delegation *dp; struct nfs4_openowner *oo = openowner(stp->st_stateowner); + bool deleg_ts = nfsd4_want_deleg_timestamps(open); struct nfs4_client *clp = stp->st_stid.sc_client; struct svc_fh *parent = NULL; - int cb_up; + struct nfs4_delegation *dp; + struct kstat stat; int status = 0; + int cb_up; cb_up = nfsd4_cb_channel_good(oo->oo_owner.so_client); - open->op_recall = 0; + open->op_recall = false; switch (open->op_claim_type) { case NFS4_OPEN_CLAIM_PREVIOUS: if (!cb_up) - open->op_recall = 1; - if (open->op_delegate_type != NFS4_OPEN_DELEGATE_READ) - goto out_no_deleg; + open->op_recall = true; break; case NFS4_OPEN_CLAIM_NULL: parent = currentfh; @@ -5594,6 +6297,9 @@ nfs4_open_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, goto out_no_deleg; if (!cb_up || !(oo->oo_flags & NFS4_OO_CONFIRMED)) goto out_no_deleg; + if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE && + !clp->cl_minorversion) + goto out_no_deleg; break; default: goto out_no_deleg; @@ -5604,17 +6310,36 @@ nfs4_open_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, memcpy(&open->op_delegate_stateid, &dp->dl_stid.sc_stateid, sizeof(dp->dl_stid.sc_stateid)); - trace_nfsd_deleg_read(&dp->dl_stid.sc_stateid); - open->op_delegate_type = NFS4_OPEN_DELEGATE_READ; + if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE) { + struct file *f = dp->dl_stid.sc_file->fi_deleg_file->nf_file; + + if (!nfsd4_add_rdaccess_to_wrdeleg(rqstp, open, fh, stp) || + !nfs4_delegation_stat(dp, currentfh, &stat)) { + nfs4_put_stid(&dp->dl_stid); + destroy_delegation(dp); + goto out_no_deleg; + } + open->op_delegate_type = deleg_ts ? OPEN_DELEGATE_WRITE_ATTRS_DELEG : + OPEN_DELEGATE_WRITE; + dp->dl_cb_fattr.ncf_cur_fsize = stat.size; + dp->dl_cb_fattr.ncf_initial_cinfo = nfsd4_change_attribute(&stat); + dp->dl_atime = stat.atime; + dp->dl_ctime = stat.ctime; + dp->dl_mtime = stat.mtime; + spin_lock(&f->f_lock); + f->f_mode |= FMODE_NOCMTIME; + spin_unlock(&f->f_lock); + trace_nfsd_deleg_write(&dp->dl_stid.sc_stateid); + } else { + open->op_delegate_type = deleg_ts && nfs4_delegation_stat(dp, currentfh, &stat) ? + OPEN_DELEGATE_READ_ATTRS_DELEG : OPEN_DELEGATE_READ; + dp->dl_atime = stat.atime; + trace_nfsd_deleg_read(&dp->dl_stid.sc_stateid); + } nfs4_put_stid(&dp->dl_stid); return; out_no_deleg: - open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE; - if (open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS && - open->op_delegate_type != NFS4_OPEN_DELEGATE_NONE) { - dprintk("NFSD: WARNING: refusing delegation reclaim\n"); - open->op_recall = 1; - } + open->op_delegate_type = OPEN_DELEGATE_NONE; /* 4.1 client asking for a delegation? */ if (open->op_deleg_want) @@ -5625,21 +6350,32 @@ out_no_deleg: static void nfsd4_deleg_xgrade_none_ext(struct nfsd4_open *open, struct nfs4_delegation *dp) { - if (open->op_deleg_want == NFS4_SHARE_WANT_READ_DELEG && - dp->dl_type == NFS4_OPEN_DELEGATE_WRITE) { - open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT; - open->op_why_no_deleg = WND4_NOT_SUPP_DOWNGRADE; - } else if (open->op_deleg_want == NFS4_SHARE_WANT_WRITE_DELEG && - dp->dl_type == NFS4_OPEN_DELEGATE_WRITE) { - open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT; - open->op_why_no_deleg = WND4_NOT_SUPP_UPGRADE; + if (deleg_is_write(dp->dl_type)) { + if (open->op_deleg_want & OPEN4_SHARE_ACCESS_WANT_READ_DELEG) { + open->op_delegate_type = OPEN_DELEGATE_NONE_EXT; + open->op_why_no_deleg = WND4_NOT_SUPP_DOWNGRADE; + } else if (open->op_deleg_want & OPEN4_SHARE_ACCESS_WANT_WRITE_DELEG) { + open->op_delegate_type = OPEN_DELEGATE_NONE_EXT; + open->op_why_no_deleg = WND4_NOT_SUPP_UPGRADE; + } } /* Otherwise the client must be confused wanting a delegation * it already has, therefore we don't return - * NFS4_OPEN_DELEGATE_NONE_EXT and reason. + * OPEN_DELEGATE_NONE_EXT and reason. */ } +/* Are we returning only a delegation stateid? */ +static bool open_xor_delegation(struct nfsd4_open *open) +{ + if (!(open->op_deleg_want & OPEN4_SHARE_ACCESS_WANT_OPEN_XOR_DELEGATION)) + return false; + /* Did we actually get a delegation? */ + if (!deleg_is_read(open->op_delegate_type) && !deleg_is_write(open->op_delegate_type)) + return false; + return true; +} + /** * nfsd4_process_open2 - finish open processing * @rqstp: the RPC transaction being executed @@ -5675,6 +6411,20 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf status = nfs4_check_deleg(cl, open, &dp); if (status) goto out; + if (dp && nfsd4_is_deleg_cur(open) && + (dp->dl_stid.sc_file != fp)) { + /* + * RFC8881 section 8.2.4 mandates the server to return + * NFS4ERR_BAD_STATEID if the selected table entry does + * not match the current filehandle. However returning + * NFS4ERR_BAD_STATEID in the OPEN can cause the client + * to repeatedly retry the operation with the same + * stateid, since the stateid itself is valid. To avoid + * this situation NFSD returns NFS4ERR_INVAL instead. + */ + status = nfserr_inval; + goto out; + } stp = nfsd4_find_and_lock_existing_open(fp, open); } else { open->op_file = NULL; @@ -5685,6 +6435,11 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf if (!stp) { stp = init_open_stateid(fp, open); + if (!stp) { + status = nfserr_jukebox; + goto out; + } + if (!open->op_stp) new_stp = true; } @@ -5705,7 +6460,6 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf } else { status = nfs4_get_vfs_file(rqstp, fp, current_fh, stp, open, true); if (status) { - stp->st_stid.sc_type = NFS4_CLOSED_STID; release_open_stateid(stp); mutex_unlock(&stp->st_mutex); goto out; @@ -5721,8 +6475,8 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf mutex_unlock(&stp->st_mutex); if (nfsd4_has_session(&resp->cstate)) { - if (open->op_deleg_want & NFS4_SHARE_WANT_NO_DELEG) { - open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT; + if (open->op_deleg_want & OPEN4_SHARE_ACCESS_WANT_NO_DELEG) { + open->op_delegate_type = OPEN_DELEGATE_NONE_EXT; open->op_why_no_deleg = WND4_NOT_WANTED; goto nodeleg; } @@ -5732,13 +6486,25 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf * Attempt to hand out a delegation. No error return, because the * OPEN succeeds even if we fail. */ - nfs4_open_delegation(open, stp, &resp->cstate.current_fh); + nfs4_open_delegation(rqstp, open, stp, + &resp->cstate.current_fh, current_fh); + + /* + * If there is an existing open stateid, it must be updated and + * returned. Only respect WANT_OPEN_XOR_DELEGATION when a new + * open stateid would have to be created. + */ + if (new_stp && open_xor_delegation(open)) { + memcpy(&open->op_stateid, &zero_stateid, sizeof(open->op_stateid)); + open->op_rflags |= OPEN4_RESULT_NO_OPEN_STATEID; + release_open_stateid(stp); + } nodeleg: status = nfs_ok; trace_nfsd_open(&stp->st_stid.sc_stateid); out: /* 4.1 client trying to upgrade/downgrade delegation? */ - if (open->op_delegate_type == NFS4_OPEN_DELEGATE_NONE && dp && + if (open->op_delegate_type == OPEN_DELEGATE_NONE && dp && open->op_deleg_want) nfsd4_deleg_xgrade_none_ext(open, dp); @@ -5749,7 +6515,7 @@ out: /* * To finish the open response, we just need to set the rflags. */ - open->op_rflags = NFS4_OPEN_RESULT_LOCKTYPE_POSIX; + open->op_rflags |= NFS4_OPEN_RESULT_LOCKTYPE_POSIX; if (nfsd4_has_session(&resp->cstate)) open->op_rflags |= NFS4_OPEN_RESULT_MAY_NOTIFY_LOCK; else if (!(open->op_openowner->oo_flags & NFS4_OO_CONFIRMED)) @@ -5766,12 +6532,8 @@ out: void nfsd4_cleanup_open_state(struct nfsd4_compound_state *cstate, struct nfsd4_open *open) { - if (open->op_openowner) { - struct nfs4_stateowner *so = &open->op_openowner->oo_owner; - - nfsd4_cstate_assign_replay(cstate, so); - nfs4_put_stateowner(so); - } + if (open->op_openowner) + nfs4_put_stateowner(&open->op_openowner->oo_owner); if (open->op_file) kmem_cache_free(file_slab, open->op_file); if (open->op_stp) @@ -5881,7 +6643,6 @@ void nfsd4_ssc_init_umount_work(struct nfsd_net *nn) INIT_LIST_HEAD(&nn->nfsd_ssc_mount_list); init_waitqueue_head(&nn->nfsd_ssc_waitq); } -EXPORT_SYMBOL_GPL(nfsd4_ssc_init_umount_work); /* * This is called when nfsd is being shutdown, after all inter_ssc @@ -6059,6 +6820,43 @@ nfs4_process_client_reaplist(struct list_head *reaplist) } } +static void nfs40_clean_admin_revoked(struct nfsd_net *nn, + struct laundry_time *lt) +{ + struct nfs4_client *clp; + + spin_lock(&nn->client_lock); + if (nn->nfs40_last_revoke == 0 || + nn->nfs40_last_revoke > lt->cutoff) { + spin_unlock(&nn->client_lock); + return; + } + nn->nfs40_last_revoke = 0; + +retry: + list_for_each_entry(clp, &nn->client_lru, cl_lru) { + unsigned long id, tmp; + struct nfs4_stid *stid; + + if (atomic_read(&clp->cl_admin_revoked) == 0) + continue; + + spin_lock(&clp->cl_lock); + idr_for_each_entry_ul(&clp->cl_stateids, stid, tmp, id) + if (stid->sc_status & SC_STATUS_ADMIN_REVOKED) { + refcount_inc(&stid->sc_count); + spin_unlock(&nn->client_lock); + /* this function drops ->cl_lock */ + nfsd4_drop_revoked_stid(stid); + nfs4_put_stid(stid); + spin_lock(&nn->client_lock); + goto retry; + } + spin_unlock(&clp->cl_lock); + } + spin_unlock(&nn->client_lock); +} + static time64_t nfs4_laundromat(struct nfsd_net *nn) { @@ -6089,15 +6887,19 @@ nfs4_laundromat(struct nfsd_net *nn) _free_cpntf_state_locked(nn, cps); } spin_unlock(&nn->s2s_cp_lock); + nfsd4_async_copy_reaper(nn); nfs4_get_client_reaplist(nn, &reaplist, <); nfs4_process_client_reaplist(&reaplist); + nfs40_clean_admin_revoked(nn, <); + spin_lock(&state_lock); list_for_each_safe(pos, next, &nn->del_recall_lru) { dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru); if (!state_expired(<, dp->dl_time)) break; - WARN_ON(!unhash_delegation_locked(dp)); + refcount_inc(&dp->dl_stid.sc_count); + unhash_delegation_locked(dp, SC_STATUS_REVOKED); list_add(&dp->dl_recall_lru, &reaplist); } spin_unlock(&state_lock); @@ -6156,6 +6958,8 @@ nfs4_laundromat(struct nfsd_net *nn) /* service the server-to-server copy delayed unmount list */ nfsd4_ssc_expire_umount(nn); #endif + if (atomic_long_read(&num_delegations) >= max_delegations) + deleg_reaper(nn); out: return max_t(time64_t, lt.new_timeo, NFSD_LAUNDROMAT_MINTIMEOUT); } @@ -6188,38 +6992,34 @@ deleg_reaper(struct nfsd_net *nn) { struct list_head *pos, *next; struct nfs4_client *clp; - struct list_head cblist; - INIT_LIST_HEAD(&cblist); spin_lock(&nn->client_lock); list_for_each_safe(pos, next, &nn->client_lru) { clp = list_entry(pos, struct nfs4_client, cl_lru); - if (clp->cl_state != NFSD4_ACTIVE || - list_empty(&clp->cl_delegations) || - atomic_read(&clp->cl_delegs_in_recall) || - test_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags) || - (ktime_get_boottime_seconds() - - clp->cl_ra_time < 5)) { + + if (clp->cl_state != NFSD4_ACTIVE) + continue; + if (list_empty(&clp->cl_delegations)) + continue; + if (atomic_read(&clp->cl_delegs_in_recall)) + continue; + if (test_and_set_bit(NFSD4_CALLBACK_RUNNING, &clp->cl_ra->ra_cb.cb_flags)) + continue; + if (ktime_get_boottime_seconds() - clp->cl_ra_time < 5) + continue; + if (clp->cl_cb_state != NFSD4_CB_UP) continue; - } - list_add(&clp->cl_ra_cblist, &cblist); /* release in nfsd4_cb_recall_any_release */ - atomic_inc(&clp->cl_rpc_users); - set_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags); + kref_get(&clp->cl_nfsdfs.cl_ref); clp->cl_ra_time = ktime_get_boottime_seconds(); - } - spin_unlock(&nn->client_lock); - - while (!list_empty(&cblist)) { - clp = list_first_entry(&cblist, struct nfs4_client, - cl_ra_cblist); - list_del_init(&clp->cl_ra_cblist); clp->cl_ra->ra_keep = 0; - clp->cl_ra->ra_bmval[0] = BIT(RCA4_TYPE_MASK_RDATA_DLG); + clp->cl_ra->ra_bmval[0] = BIT(RCA4_TYPE_MASK_RDATA_DLG) | + BIT(RCA4_TYPE_MASK_WDATA_DLG); trace_nfsd_cb_recall_any(clp->cl_ra); nfsd4_run_cb(&clp->cl_ra->ra_cb); } + spin_unlock(&nn->client_lock); } static void @@ -6310,6 +7110,9 @@ static __be32 nfsd4_stid_check_stateid_generation(stateid_t *in, struct nfs4_sti if (ret == nfs_ok) ret = check_stateid_generation(in, &s->sc_stateid, has_session); spin_unlock(&s->sc_lock); + if (ret == nfserr_admin_revoked) + nfsd40_drop_revoked_stid(s->sc_client, + &s->sc_stateid); return ret; } @@ -6329,8 +7132,6 @@ static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid) if (ZERO_STATEID(stateid) || ONE_STATEID(stateid) || CLOSE_STATEID(stateid)) return status; - if (!same_clid(&stateid->si_opaque.so_clid, &cl->cl_clientid)) - return status; spin_lock(&cl->cl_lock); s = find_stateid_locked(cl, stateid); if (!s) @@ -6338,32 +7139,33 @@ static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid) status = nfsd4_stid_check_stateid_generation(stateid, s, 1); if (status) goto out_unlock; + status = nfsd4_verify_open_stid(s); + if (status) + goto out_unlock; + switch (s->sc_type) { - case NFS4_DELEG_STID: + case SC_TYPE_DELEG: status = nfs_ok; break; - case NFS4_REVOKED_DELEG_STID: - status = nfserr_deleg_revoked; - break; - case NFS4_OPEN_STID: - case NFS4_LOCK_STID: + case SC_TYPE_OPEN: + case SC_TYPE_LOCK: status = nfsd4_check_openowner_confirmed(openlockstateid(s)); break; default: printk("unknown stateid type %x\n", s->sc_type); - fallthrough; - case NFS4_CLOSED_STID: - case NFS4_CLOSED_DELEG_STID: status = nfserr_bad_stateid; } out_unlock: spin_unlock(&cl->cl_lock); + if (status == nfserr_admin_revoked) + nfsd40_drop_revoked_stid(cl, stateid); return status; } __be32 nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate, - stateid_t *stateid, unsigned char typemask, + stateid_t *stateid, + unsigned short typemask, unsigned short statusmask, struct nfs4_stid **s, struct nfsd_net *nn) { __be32 status; @@ -6374,10 +7176,15 @@ nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate, * only return revoked delegations if explicitly asked. * otherwise we report revoked or bad_stateid status. */ - if (typemask & NFS4_REVOKED_DELEG_STID) + if (statusmask & SC_STATUS_REVOKED) return_revoked = true; - else if (typemask & NFS4_DELEG_STID) - typemask |= NFS4_REVOKED_DELEG_STID; + if (typemask & SC_TYPE_DELEG) + /* Always allow REVOKED for DELEG so we can + * return the appropriate error. + */ + statusmask |= SC_STATUS_REVOKED; + + statusmask |= SC_STATUS_ADMIN_REVOKED | SC_STATUS_FREEABLE; if (ZERO_STATEID(stateid) || ONE_STATEID(stateid) || CLOSE_STATEID(stateid)) @@ -6390,14 +7197,17 @@ nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate, } if (status) return status; - stid = find_stateid_by_type(cstate->clp, stateid, typemask); + stid = find_stateid_by_type(cstate->clp, stateid, typemask, statusmask); if (!stid) return nfserr_bad_stateid; - if ((stid->sc_type == NFS4_REVOKED_DELEG_STID) && !return_revoked) { + if ((stid->sc_status & SC_STATUS_REVOKED) && !return_revoked) { nfs4_put_stid(stid); - if (cstate->minorversion) - return nfserr_deleg_revoked; - return nfserr_bad_stateid; + return nfserr_deleg_revoked; + } + if (stid->sc_status & SC_STATUS_ADMIN_REVOKED) { + nfsd40_drop_revoked_stid(cstate->clp, stateid); + nfs4_put_stid(stid); + return nfserr_admin_revoked; } *s = stid; return nfs_ok; @@ -6406,23 +7216,22 @@ nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate, static struct nfsd_file * nfs4_find_file(struct nfs4_stid *s, int flags) { - if (!s) + struct nfsd_file *ret = NULL; + + if (!s || s->sc_status) return NULL; switch (s->sc_type) { - case NFS4_DELEG_STID: - if (WARN_ON_ONCE(!s->sc_file->fi_deleg_file)) - return NULL; - return nfsd_file_get(s->sc_file->fi_deleg_file); - case NFS4_OPEN_STID: - case NFS4_LOCK_STID: + case SC_TYPE_DELEG: + case SC_TYPE_OPEN: + case SC_TYPE_LOCK: if (flags & RD_STATE) - return find_readable_file(s->sc_file); + ret = find_readable_file(s->sc_file); else - return find_writeable_file(s->sc_file); + ret = find_writeable_file(s->sc_file); } - return NULL; + return ret; } static __be32 @@ -6446,7 +7255,8 @@ nfs4_check_file(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfs4_stid *s, nf = nfs4_find_file(s, flags); if (nf) { - status = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry, + status = nfsd_permission(&rqstp->rq_cred, + fhp->fh_export, fhp->fh_dentry, acc | NFSD_MAY_OWNER_OVERRIDE); if (status) { nfsd_file_put(nf); @@ -6504,7 +7314,7 @@ unlock: spin_unlock(&nn->s2s_cp_lock); if (!state) return nfserr_bad_stateid; - if (!clp && state) + if (!clp) *cps = state; return 0; } @@ -6528,7 +7338,8 @@ static __be32 find_cpntf_state(struct nfsd_net *nn, stateid_t *st, goto out; *stid = find_stateid_by_type(found, &cps->cp_p_stateid, - NFS4_DELEG_STID|NFS4_OPEN_STID|NFS4_LOCK_STID); + SC_TYPE_DELEG|SC_TYPE_OPEN|SC_TYPE_LOCK, + 0); if (*stid) status = nfs_ok; else @@ -6547,8 +7358,19 @@ void nfs4_put_cpntf_state(struct nfsd_net *nn, struct nfs4_cpntf_state *cps) spin_unlock(&nn->s2s_cp_lock); } -/* - * Checks for stateid operations +/** + * nfs4_preprocess_stateid_op - find and prep stateid for an operation + * @rqstp: incoming request from client + * @cstate: current compound state + * @fhp: filehandle associated with requested stateid + * @stateid: stateid (provided by client) + * @flags: flags describing type of operation to be done + * @nfp: optional nfsd_file return pointer (may be NULL) + * @cstid: optional returned nfs4_stid pointer (may be NULL) + * + * Given info from the client, look up a nfs4_stid for the operation. On + * success, it returns a reference to the nfs4_stid and/or the nfsd_file + * associated with it. */ __be32 nfs4_preprocess_stateid_op(struct svc_rqst *rqstp, @@ -6565,17 +7387,13 @@ nfs4_preprocess_stateid_op(struct svc_rqst *rqstp, *nfp = NULL; if (ZERO_STATEID(stateid) || ONE_STATEID(stateid)) { - if (cstid) - status = nfserr_bad_stateid; - else - status = check_special_stateids(net, fhp, stateid, - flags); + status = check_special_stateids(net, fhp, stateid, flags); goto done; } status = nfsd4_lookup_stateid(cstate, stateid, - NFS4_DELEG_STID|NFS4_OPEN_STID|NFS4_LOCK_STID, - &s, nn); + SC_TYPE_DELEG|SC_TYPE_OPEN|SC_TYPE_LOCK, + 0, &s, nn); if (status == nfserr_bad_stateid) status = find_cpntf_state(nn, stateid, &s); if (status) @@ -6586,16 +7404,13 @@ nfs4_preprocess_stateid_op(struct svc_rqst *rqstp, goto out; switch (s->sc_type) { - case NFS4_DELEG_STID: + case SC_TYPE_DELEG: status = nfs4_check_delegmode(delegstateid(s), flags); break; - case NFS4_OPEN_STID: - case NFS4_LOCK_STID: + case SC_TYPE_OPEN: + case SC_TYPE_LOCK: status = nfs4_check_olstateid(openlockstateid(s), flags); break; - default: - status = nfserr_bad_stateid; - break; } if (status) goto out; @@ -6674,34 +7489,42 @@ nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, spin_lock(&cl->cl_lock); s = find_stateid_locked(cl, stateid); - if (!s) + if (!s || s->sc_status & SC_STATUS_CLOSED) goto out_unlock; + if (s->sc_status & SC_STATUS_ADMIN_REVOKED) { + nfsd4_drop_revoked_stid(s); + ret = nfs_ok; + goto out; + } spin_lock(&s->sc_lock); switch (s->sc_type) { - case NFS4_DELEG_STID: + case SC_TYPE_DELEG: + if (s->sc_status & SC_STATUS_REVOKED) { + s->sc_status |= SC_STATUS_CLOSED; + spin_unlock(&s->sc_lock); + dp = delegstateid(s); + if (s->sc_status & SC_STATUS_FREEABLE) + list_del_init(&dp->dl_recall_lru); + s->sc_status |= SC_STATUS_FREED; + spin_unlock(&cl->cl_lock); + nfs4_put_stid(s); + ret = nfs_ok; + goto out; + } ret = nfserr_locks_held; break; - case NFS4_OPEN_STID: + case SC_TYPE_OPEN: ret = check_stateid_generation(stateid, &s->sc_stateid, 1); if (ret) break; ret = nfserr_locks_held; break; - case NFS4_LOCK_STID: + case SC_TYPE_LOCK: spin_unlock(&s->sc_lock); refcount_inc(&s->sc_count); spin_unlock(&cl->cl_lock); ret = nfsd4_free_lock_stateid(stateid, s); goto out; - case NFS4_REVOKED_DELEG_STID: - spin_unlock(&s->sc_lock); - dp = delegstateid(s); - list_del_init(&dp->dl_recall_lru); - spin_unlock(&cl->cl_lock); - nfs4_put_stid(s); - ret = nfs_ok; - goto out; - /* Default falls through and returns nfserr_bad_stateid */ } spin_unlock(&s->sc_lock); out_unlock: @@ -6737,12 +7560,24 @@ static __be32 nfs4_seqid_op_checks(struct nfsd4_compound_state *cstate, stateid_ return status; } -/* - * Checks for sequence id mutating operations. +/** + * nfs4_preprocess_seqid_op - find and prep an ol_stateid for a seqid-morphing op + * @cstate: compund state + * @seqid: seqid (provided by client) + * @stateid: stateid (provided by client) + * @typemask: mask of allowable types for this operation + * @statusmask: mask of allowed states: 0 or STID_CLOSED + * @stpp: return pointer for the stateid found + * @nn: net namespace for request + * + * Given a stateid+seqid from a client, look up an nfs4_ol_stateid and + * return it in @stpp. On a nfs_ok return, the returned stateid will + * have its st_mutex locked. */ static __be32 nfs4_preprocess_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid, - stateid_t *stateid, char typemask, + stateid_t *stateid, + unsigned short typemask, unsigned short statusmask, struct nfs4_ol_stateid **stpp, struct nfsd_net *nn) { @@ -6753,11 +7588,16 @@ nfs4_preprocess_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid, trace_nfsd_preprocess(seqid, stateid); *stpp = NULL; - status = nfsd4_lookup_stateid(cstate, stateid, typemask, &s, nn); +retry: + status = nfsd4_lookup_stateid(cstate, stateid, + typemask, statusmask, &s, nn); if (status) return status; stp = openlockstateid(s); - nfsd4_cstate_assign_replay(cstate, stp->st_stateowner); + if (nfsd4_cstate_assign_replay(cstate, stp->st_stateowner) == -EAGAIN) { + nfs4_put_stateowner(stp->st_stateowner); + goto retry; + } status = nfs4_seqid_op_checks(cstate, stateid, seqid, stp); if (!status) @@ -6775,7 +7615,7 @@ static __be32 nfs4_preprocess_confirmed_seqid_op(struct nfsd4_compound_state *cs struct nfs4_ol_stateid *stp; status = nfs4_preprocess_seqid_op(cstate, seqid, stateid, - NFS4_OPEN_STID, &stp, nn); + SC_TYPE_OPEN, 0, &stp, nn); if (status) return status; oo = openowner(stp->st_stateowner); @@ -6806,8 +7646,8 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, return status; status = nfs4_preprocess_seqid_op(cstate, - oc->oc_seqid, &oc->oc_req_stateid, - NFS4_OPEN_STID, &stp, nn); + oc->oc_seqid, &oc->oc_req_stateid, + SC_TYPE_OPEN, 0, &stp, nn); if (status) goto out; oo = openowner(stp->st_stateowner); @@ -6899,7 +7739,7 @@ out: return status; } -static void nfsd4_close_open_stateid(struct nfs4_ol_stateid *s) +static bool nfsd4_close_open_stateid(struct nfs4_ol_stateid *s) { struct nfs4_client *clp = s->st_stid.sc_client; bool unhashed; @@ -6916,11 +7756,11 @@ static void nfsd4_close_open_stateid(struct nfs4_ol_stateid *s) list_for_each_entry(stp, &reaplist, st_locks) nfs4_free_cpntf_statelist(clp->net, &stp->st_stid); free_ol_stateid_reaplist(&reaplist); + return false; } else { spin_unlock(&clp->cl_lock); free_ol_stateid_reaplist(&reaplist); - if (unhashed) - move_to_close_lru(s, clp->net); + return unhashed; } } @@ -6936,19 +7776,22 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfs4_ol_stateid *stp; struct net *net = SVC_NET(rqstp); struct nfsd_net *nn = net_generic(net, nfsd_net_id); + bool need_move_to_close_list; - dprintk("NFSD: nfsd4_close on file %pd\n", + dprintk("NFSD: nfsd4_close on file %pd\n", cstate->current_fh.fh_dentry); status = nfs4_preprocess_seqid_op(cstate, close->cl_seqid, - &close->cl_stateid, - NFS4_OPEN_STID|NFS4_CLOSED_STID, - &stp, nn); + &close->cl_stateid, + SC_TYPE_OPEN, SC_STATUS_CLOSED, + &stp, nn); nfsd4_bump_seqid(cstate, status); if (status) - goto out; + goto out; - stp->st_stid.sc_type = NFS4_CLOSED_STID; + spin_lock(&stp->st_stid.sc_client->cl_lock); + stp->st_stid.sc_status |= SC_STATUS_CLOSED; + spin_unlock(&stp->st_stid.sc_client->cl_lock); /* * Technically we don't _really_ have to increment or copy it, since @@ -6958,8 +7801,10 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, */ nfs4_inc_and_copy_stateid(&close->cl_stateid, &stp->st_stid); - nfsd4_close_open_stateid(stp); + need_move_to_close_list = nfsd4_close_open_stateid(stp); mutex_unlock(&stp->st_mutex); + if (need_move_to_close_list) + move_to_close_lru(stp, net); /* v4.1+ suggests that we send a special stateid in here, since the * clients should just ignore this anyway. Since this is not useful @@ -6987,10 +7832,11 @@ nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, __be32 status; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); - if ((status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0))) + status = fh_verify(rqstp, &cstate->current_fh, 0, 0); + if (status) return status; - status = nfsd4_lookup_stateid(cstate, stateid, NFS4_DELEG_STID, &s, nn); + status = nfsd4_lookup_stateid(cstate, stateid, SC_TYPE_DELEG, SC_STATUS_REVOKED, &s, nn); if (status) goto out; dp = delegstateid(s); @@ -6999,8 +7845,9 @@ nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto put_stateid; trace_nfsd_deleg_return(stateid); - wake_up_var(d_inode(cstate->current_fh.fh_dentry)); destroy_delegation(dp); + smp_mb__after_atomic(); + wake_up_var(d_inode(cstate->current_fh.fh_dentry)); put_stateid: nfs4_put_stid(&dp->dl_stid); out: @@ -7057,7 +7904,7 @@ nfsd4_lm_put_owner(fl_owner_t owner) static bool nfsd4_lm_lock_expirable(struct file_lock *cfl) { - struct nfs4_lockowner *lo = (struct nfs4_lockowner *)cfl->fl_owner; + struct nfs4_lockowner *lo = (struct nfs4_lockowner *) cfl->c.flc_owner; struct nfs4_client *clp = lo->lo_owner.so_client; struct nfsd_net *nn; @@ -7079,7 +7926,7 @@ nfsd4_lm_expire_lock(void) static void nfsd4_lm_notify(struct file_lock *fl) { - struct nfs4_lockowner *lo = (struct nfs4_lockowner *)fl->fl_owner; + struct nfs4_lockowner *lo = (struct nfs4_lockowner *) fl->c.flc_owner; struct net *net = lo->lo_owner.so_client->net; struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct nfsd4_blocked_lock *nbl = container_of(fl, @@ -7097,7 +7944,7 @@ nfsd4_lm_notify(struct file_lock *fl) if (queue) { trace_nfsd_cb_notify_lock(lo, nbl); - nfsd4_run_cb(&nbl->nbl_cb); + nfsd4_try_run_cb(&nbl->nbl_cb); } } @@ -7116,7 +7963,7 @@ nfs4_set_lock_denied(struct file_lock *fl, struct nfsd4_lock_denied *deny) struct nfs4_lockowner *lo; if (fl->fl_lmops == &nfsd_posix_mng_ops) { - lo = (struct nfs4_lockowner *) fl->fl_owner; + lo = (struct nfs4_lockowner *) fl->c.flc_owner; xdr_netobj_dup(&deny->ld_owner, &lo->lo_owner.so_owner, GFP_KERNEL); if (!deny->ld_owner.data) @@ -7135,7 +7982,7 @@ nevermind: if (fl->fl_end != NFS4_MAX_UINT64) deny->ld_length = fl->fl_end - fl->fl_start + 1; deny->ld_type = NFS4_READ_LT; - if (fl->fl_type != F_RDLCK) + if (fl->c.flc_type != F_RDLCK) deny->ld_type = NFS4_WRITE_LT; } @@ -7257,7 +8104,7 @@ retry: if (retstp) goto out_found; refcount_inc(&stp->st_stid.sc_count); - stp->st_stid.sc_type = NFS4_LOCK_STID; + stp->st_stid.sc_type = SC_TYPE_LOCK; stp->st_stateowner = nfs4_get_stateowner(&lo->lo_owner); get_nfs4_file(fp); stp->st_stid.sc_file = fp; @@ -7400,8 +8247,8 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, int lkflg; int err; bool new = false; - unsigned char fl_type; - unsigned int fl_flags = FL_POSIX; + unsigned char type; + unsigned int flags = FL_POSIX; struct net *net = SVC_NET(rqstp); struct nfsd_net *nn = net_generic(net, nfsd_net_id); @@ -7412,10 +8259,12 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (check_lock_length(lock->lk_offset, lock->lk_length)) return nfserr_inval; - if ((status = fh_verify(rqstp, &cstate->current_fh, - S_IFREG, NFSD_MAY_LOCK))) { - dprintk("NFSD: nfsd4_lock: permission denied!\n"); + status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0); + if (status != nfs_ok) return status; + if (exportfs_cannot_lock(cstate->current_fh.fh_dentry->d_sb->s_export_op)) { + status = nfserr_notsupp; + goto out; } if (lock->lk_is_new) { @@ -7442,9 +8291,10 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, &lock_stp, &new); } else { status = nfs4_preprocess_seqid_op(cstate, - lock->lk_old_lock_seqid, - &lock->lk_old_lock_stateid, - NFS4_LOCK_STID, &lock_stp, nn); + lock->lk_old_lock_seqid, + &lock->lk_old_lock_stateid, + SC_TYPE_LOCK, 0, &lock_stp, + nn); } if (status) goto out; @@ -7463,13 +8313,11 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; if (lock->lk_reclaim) - fl_flags |= FL_RECLAIM; + flags |= FL_RECLAIM; fp = lock_stp->st_stid.sc_file; switch (lock->lk_type) { case NFS4_READW_LT: - if (nfsd4_has_session(cstate)) - fl_flags |= FL_SLEEP; fallthrough; case NFS4_READ_LT: spin_lock(&fp->fi_lock); @@ -7477,11 +8325,9 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (nf) get_lock_access(lock_stp, NFS4_SHARE_ACCESS_READ); spin_unlock(&fp->fi_lock); - fl_type = F_RDLCK; + type = F_RDLCK; break; case NFS4_WRITEW_LT: - if (nfsd4_has_session(cstate)) - fl_flags |= FL_SLEEP; fallthrough; case NFS4_WRITE_LT: spin_lock(&fp->fi_lock); @@ -7489,7 +8335,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (nf) get_lock_access(lock_stp, NFS4_SHARE_ACCESS_WRITE); spin_unlock(&fp->fi_lock); - fl_type = F_WRLCK; + type = F_WRLCK; break; default: status = nfserr_inval; @@ -7501,15 +8347,10 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; } - /* - * Most filesystems with their own ->lock operations will block - * the nfsd thread waiting to acquire the lock. That leads to - * deadlocks (we don't want every nfsd thread tied up waiting - * for file locks), so don't attempt blocking lock notifications - * on those filesystems: - */ - if (nf->nf_file->f_op->lock) - fl_flags &= ~FL_SLEEP; + if (lock->lk_type & (NFS4_READW_LT | NFS4_WRITEW_LT) && + nfsd4_has_session(cstate) && + locks_can_async_lock(nf->nf_file->f_op)) + flags |= FL_SLEEP; nbl = find_or_allocate_block(lock_sop, &fp->fi_fhandle, nn); if (!nbl) { @@ -7519,11 +8360,11 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, } file_lock = &nbl->nbl_lock; - file_lock->fl_type = fl_type; - file_lock->fl_owner = (fl_owner_t)lockowner(nfs4_get_stateowner(&lock_sop->lo_owner)); - file_lock->fl_pid = current->tgid; - file_lock->fl_file = nf->nf_file; - file_lock->fl_flags = fl_flags; + file_lock->c.flc_type = type; + file_lock->c.flc_owner = (fl_owner_t)lockowner(nfs4_get_stateowner(&lock_sop->lo_owner)); + file_lock->c.flc_pid = current->tgid; + file_lock->c.flc_file = nf->nf_file; + file_lock->c.flc_flags = flags; file_lock->fl_lmops = &nfsd_posix_mng_ops; file_lock->fl_start = lock->lk_offset; file_lock->fl_end = last_byte_offset(lock->lk_offset, lock->lk_length); @@ -7536,7 +8377,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; } - if (fl_flags & FL_SLEEP) { + if (flags & FL_SLEEP) { nbl->nbl_time = ktime_get_boottime_seconds(); spin_lock(&nn->blocked_locks_lock); list_add_tail(&nbl->nbl_list, &lock_sop->lo_blocked); @@ -7573,7 +8414,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, out: if (nbl) { /* dequeue it if we queued it before */ - if (fl_flags & FL_SLEEP) { + if (flags & FL_SLEEP) { spin_lock(&nn->blocked_locks_lock); if (!list_empty(&nbl->nbl_list) && !list_empty(&nbl->nbl_lru)) { @@ -7614,6 +8455,14 @@ out: return status; } +void nfsd4_lock_release(union nfsd4_op_u *u) +{ + struct nfsd4_lock *lock = &u->lock; + struct nfsd4_lock_denied *deny = &lock->lk_denied; + + kfree(deny->ld_owner.data); +} + /* * The NFSv4 spec allows a client to do a LOCKT without holding an OPEN, * so we do a temporary open here just to get an open file to pass to @@ -7633,9 +8482,9 @@ static __be32 nfsd_test_lock(struct svc_rqst *rqstp, struct svc_fh *fhp, struct err = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ)); if (err) goto out; - lock->fl_file = nf->nf_file; + lock->c.flc_file = nf->nf_file; err = nfserrno(vfs_test_lock(nf->nf_file, lock)); - lock->fl_file = NULL; + lock->c.flc_file = NULL; out: inode_unlock(inode); nfsd_file_put(nf); @@ -7680,11 +8529,11 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, switch (lockt->lt_type) { case NFS4_READ_LT: case NFS4_READW_LT: - file_lock->fl_type = F_RDLCK; + file_lock->c.flc_type = F_RDLCK; break; case NFS4_WRITE_LT: case NFS4_WRITEW_LT: - file_lock->fl_type = F_WRLCK; + file_lock->c.flc_type = F_WRLCK; break; default: dprintk("NFSD: nfs4_lockt: bad lock type!\n"); @@ -7694,9 +8543,9 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, lo = find_lockowner_str(cstate->clp, &lockt->lt_owner); if (lo) - file_lock->fl_owner = (fl_owner_t)lo; - file_lock->fl_pid = current->tgid; - file_lock->fl_flags = FL_POSIX; + file_lock->c.flc_owner = (fl_owner_t)lo; + file_lock->c.flc_pid = current->tgid; + file_lock->c.flc_flags = FL_POSIX; file_lock->fl_start = lockt->lt_offset; file_lock->fl_end = last_byte_offset(lockt->lt_offset, lockt->lt_length); @@ -7707,7 +8556,7 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (status) goto out; - if (file_lock->fl_type != F_UNLCK) { + if (file_lock->c.flc_type != F_UNLCK) { status = nfserr_denied; nfs4_set_lock_denied(file_lock, &lockt->lt_denied); } @@ -7719,6 +8568,14 @@ out: return status; } +void nfsd4_lockt_release(union nfsd4_op_u *u) +{ + struct nfsd4_lockt *lockt = &u->lockt; + struct nfsd4_lock_denied *deny = &lockt->lt_denied; + + kfree(deny->ld_owner.data); +} + __be32 nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) @@ -7739,8 +8596,8 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, return nfserr_inval; status = nfs4_preprocess_seqid_op(cstate, locku->lu_seqid, - &locku->lu_stateid, NFS4_LOCK_STID, - &stp, nn); + &locku->lu_stateid, SC_TYPE_LOCK, 0, + &stp, nn); if (status) goto out; nf = find_any_file(stp->st_stid.sc_file); @@ -7748,6 +8605,11 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = nfserr_lock_range; goto put_stateid; } + if (exportfs_cannot_lock(nf->nf_file->f_path.mnt->mnt_sb->s_export_op)) { + status = nfserr_notsupp; + goto put_file; + } + file_lock = locks_alloc_lock(); if (!file_lock) { dprintk("NFSD: %s: unable to allocate lock!\n", __func__); @@ -7755,11 +8617,11 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto put_file; } - file_lock->fl_type = F_UNLCK; - file_lock->fl_owner = (fl_owner_t)lockowner(nfs4_get_stateowner(stp->st_stateowner)); - file_lock->fl_pid = current->tgid; - file_lock->fl_file = nf->nf_file; - file_lock->fl_flags = FL_POSIX; + file_lock->c.flc_type = F_UNLCK; + file_lock->c.flc_owner = (fl_owner_t)lockowner(nfs4_get_stateowner(stp->st_stateowner)); + file_lock->c.flc_pid = current->tgid; + file_lock->c.flc_file = nf->nf_file; + file_lock->c.flc_flags = FL_POSIX; file_lock->fl_lmops = &nfsd_posix_mng_ops; file_lock->fl_start = locku->lu_offset; @@ -7799,30 +8661,33 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) { struct file_lock *fl; int status = false; - struct nfsd_file *nf = find_any_file(fp); + struct nfsd_file *nf; struct inode *inode; struct file_lock_context *flctx; + spin_lock(&fp->fi_lock); + nf = find_any_file_locked(fp); if (!nf) { /* Any valid lock stateid should have some sort of access */ WARN_ON_ONCE(1); - return status; + goto out; } - inode = locks_inode(nf->nf_file); + inode = file_inode(nf->nf_file); flctx = locks_inode_context(inode); if (flctx && !list_empty_careful(&flctx->flc_posix)) { spin_lock(&flctx->flc_lock); - list_for_each_entry(fl, &flctx->flc_posix, fl_list) { - if (fl->fl_owner == (fl_owner_t)lowner) { + for_each_file_lock(fl, &flctx->flc_posix) { + if (fl->c.flc_owner == (fl_owner_t)lowner) { status = true; break; } } spin_unlock(&flctx->flc_lock); } - nfsd_file_put(nf); +out: + spin_unlock(&fp->fi_lock); return status; } @@ -7832,10 +8697,8 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) * @cstate: NFSv4 COMPOUND state * @u: RELEASE_LOCKOWNER arguments * - * The lockowner's so_count is bumped when a lock record is added - * or when copying a conflicting lock. The latter case is brief, - * but can lead to fleeting false positives when looking for - * locks-in-use. + * Check if there are any locks still held and if not, free the lockowner + * and any lock state that is owned. * * Return values: * %nfs_ok: lockowner released or not found @@ -7871,17 +8734,20 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp, spin_unlock(&clp->cl_lock); return nfs_ok; } - if (atomic_read(&lo->lo_owner.so_count) != 2) { - spin_unlock(&clp->cl_lock); - nfs4_put_stateowner(&lo->lo_owner); - return nfserr_locks_held; + + list_for_each_entry(stp, &lo->lo_owner.so_stateids, st_perstateowner) { + if (check_for_locks(stp->st_stid.sc_file, lo)) { + spin_unlock(&clp->cl_lock); + nfs4_put_stateowner(&lo->lo_owner); + return nfserr_locks_held; + } } unhash_lockowner_locked(lo); while (!list_empty(&lo->lo_owner.so_stateids)) { stp = list_first_entry(&lo->lo_owner.so_stateids, struct nfs4_ol_stateid, st_perstateowner); - WARN_ON(!unhash_lock_stateid(stp)); + unhash_lock_stateid(stp); put_ol_stateid_locked(stp, &reaplist); } spin_unlock(&clp->cl_lock); @@ -7909,9 +8775,6 @@ nfs4_has_reclaimed_state(struct xdr_netobj name, struct nfsd_net *nn) /* * failure => all reset bets are off, nfserr_no_grace... - * - * The caller is responsible for freeing name.data if NULL is returned (it - * will be freed in nfs4_remove_reclaim_record in the normal case). */ struct nfs4_client_reclaim * nfs4_client_to_reclaim(struct xdr_netobj name, struct xdr_netobj princhash, @@ -7920,6 +8783,22 @@ nfs4_client_to_reclaim(struct xdr_netobj name, struct xdr_netobj princhash, unsigned int strhashval; struct nfs4_client_reclaim *crp; + name.data = kmemdup(name.data, name.len, GFP_KERNEL); + if (!name.data) { + dprintk("%s: failed to allocate memory for name.data!\n", + __func__); + return NULL; + } + if (princhash.len) { + princhash.data = kmemdup(princhash.data, princhash.len, GFP_KERNEL); + if (!princhash.data) { + dprintk("%s: failed to allocate memory for princhash.data!\n", + __func__); + kfree(name.data); + return NULL; + } + } else + princhash.data = NULL; crp = alloc_reclaim(); if (crp) { strhashval = clientstr_hashval(name); @@ -7931,6 +8810,9 @@ nfs4_client_to_reclaim(struct xdr_netobj name, struct xdr_netobj princhash, crp->cr_princhash.len = princhash.len; crp->cr_clp = NULL; nn->reclaim_str_hashtbl_size++; + } else { + kfree(name.data); + kfree(princhash.data); } return crp; } @@ -8050,6 +8932,7 @@ static int nfs4_state_create_net(struct net *net) spin_lock_init(&nn->client_lock); spin_lock_init(&nn->s2s_cp_lock); idr_init(&nn->s2s_cp_stateids); + atomic_set(&nn->pending_async_copies, 0); spin_lock_init(&nn->blocked_locks_lock); INIT_LIST_HEAD(&nn->blocked_locks_lru); @@ -8058,12 +8941,16 @@ static int nfs4_state_create_net(struct net *net) INIT_WORK(&nn->nfsd_shrinker_work, nfsd4_state_shrinker_worker); get_net(net); - nn->nfsd_client_shrinker.scan_objects = nfsd4_state_shrinker_scan; - nn->nfsd_client_shrinker.count_objects = nfsd4_state_shrinker_count; - nn->nfsd_client_shrinker.seeks = DEFAULT_SEEKS; - - if (register_shrinker(&nn->nfsd_client_shrinker, "nfsd-client")) + nn->nfsd_client_shrinker = shrinker_alloc(0, "nfsd-client"); + if (!nn->nfsd_client_shrinker) goto err_shrinker; + + nn->nfsd_client_shrinker->scan_objects = nfsd4_state_shrinker_scan; + nn->nfsd_client_shrinker->count_objects = nfsd4_state_shrinker_count; + nn->nfsd_client_shrinker->private_data = nn; + + shrinker_register(nn->nfsd_client_shrinker); + return 0; err_shrinker: @@ -8134,7 +9021,6 @@ skip_grace: } /* initialization to perform when the nfsd service is started: */ - int nfs4_state_start(void) { @@ -8144,11 +9030,14 @@ nfs4_state_start(void) if (ret) return ret; - ret = nfsd4_create_callback_queue(); - if (ret) { + nfsd_slot_shrinker = shrinker_alloc(0, "nfsd-DRC-slot"); + if (!nfsd_slot_shrinker) { rhltable_destroy(&nfs4_file_rhltable); - return ret; + return -ENOMEM; } + nfsd_slot_shrinker->count_objects = nfsd_slot_count; + nfsd_slot_shrinker->scan_objects = nfsd_slot_scan; + shrinker_register(nfsd_slot_shrinker); set_max_delegations(); return 0; @@ -8161,8 +9050,8 @@ nfs4_state_shutdown_net(struct net *net) struct list_head *pos, *next, reaplist; struct nfsd_net *nn = net_generic(net, nfsd_net_id); - unregister_shrinker(&nn->nfsd_client_shrinker); - cancel_work(&nn->nfsd_shrinker_work); + shrinker_free(nn->nfsd_client_shrinker); + cancel_work_sync(&nn->nfsd_shrinker_work); cancel_delayed_work_sync(&nn->laundromat_work); locks_end_grace(&nn->nfsd4_manager); @@ -8170,7 +9059,7 @@ nfs4_state_shutdown_net(struct net *net) spin_lock(&state_lock); list_for_each_safe(pos, next, &nn->del_recall_lru) { dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru); - WARN_ON(!unhash_delegation_locked(dp)); + unhash_delegation_locked(dp, SC_STATUS_CLOSED); list_add(&dp->dl_recall_lru, &reaplist); } spin_unlock(&state_lock); @@ -8182,7 +9071,6 @@ nfs4_state_shutdown_net(struct net *net) nfsd4_client_tracking_exit(net); nfs4_state_destroy_net(net); - rhltable_destroy(&nfs4_file_rhltable); #ifdef CONFIG_NFSD_V4_2_INTER_SSC nfsd4_ssc_shutdown_umount(nn); #endif @@ -8191,7 +9079,8 @@ nfs4_state_shutdown_net(struct net *net) void nfs4_state_shutdown(void) { - nfsd4_destroy_callback_queue(); + rhltable_destroy(&nfs4_file_rhltable); + shrinker_free(nfsd_slot_shrinker); } static void @@ -8307,3 +9196,274 @@ nfsd4_get_writestateid(struct nfsd4_compound_state *cstate, { get_stateid(cstate, &u->write.wr_stateid); } + +/** + * nfsd4_vet_deleg_time - vet and set the timespec for a delegated timestamp update + * @req: timestamp from the client + * @orig: original timestamp in the inode + * @now: current time + * + * Given a timestamp from the client response, check it against the + * current timestamp in the inode and the current time. Returns true + * if the inode's timestamp needs to be updated, and false otherwise. + * @req may also be changed if the timestamp needs to be clamped. + */ +bool nfsd4_vet_deleg_time(struct timespec64 *req, const struct timespec64 *orig, + const struct timespec64 *now) +{ + + /* + * "When the time presented is before the original time, then the + * update is ignored." Also no need to update if there is no change. + */ + if (timespec64_compare(req, orig) <= 0) + return false; + + /* + * "When the time presented is in the future, the server can either + * clamp the new time to the current time, or it may + * return NFS4ERR_DELAY to the client, allowing it to retry." + */ + if (timespec64_compare(req, now) > 0) + *req = *now; + + return true; +} + +static int cb_getattr_update_times(struct dentry *dentry, struct nfs4_delegation *dp) +{ + struct inode *inode = d_inode(dentry); + struct nfs4_cb_fattr *ncf = &dp->dl_cb_fattr; + struct iattr attrs = { }; + int ret; + + if (deleg_attrs_deleg(dp->dl_type)) { + struct timespec64 now = current_time(inode); + + attrs.ia_atime = ncf->ncf_cb_atime; + attrs.ia_mtime = ncf->ncf_cb_mtime; + + if (nfsd4_vet_deleg_time(&attrs.ia_atime, &dp->dl_atime, &now)) + attrs.ia_valid |= ATTR_ATIME | ATTR_ATIME_SET; + + if (nfsd4_vet_deleg_time(&attrs.ia_mtime, &dp->dl_mtime, &now)) { + attrs.ia_valid |= ATTR_MTIME | ATTR_MTIME_SET; + attrs.ia_ctime = attrs.ia_mtime; + if (nfsd4_vet_deleg_time(&attrs.ia_ctime, &dp->dl_ctime, &now)) + attrs.ia_valid |= ATTR_CTIME | ATTR_CTIME_SET; + } + } else { + attrs.ia_valid |= ATTR_MTIME | ATTR_CTIME; + } + + if (!attrs.ia_valid) + return 0; + + attrs.ia_valid |= ATTR_DELEG; + inode_lock(inode); + ret = notify_change(&nop_mnt_idmap, dentry, &attrs, NULL); + inode_unlock(inode); + return ret; +} + +/** + * nfsd4_deleg_getattr_conflict - Recall if GETATTR causes conflict + * @rqstp: RPC transaction context + * @dentry: dentry of inode to be checked for a conflict + * @pdp: returned WRITE delegation, if one was found + * + * This function is called when there is a conflict between a write + * delegation and a change/size GETATTR from another client. The server + * must either use the CB_GETATTR to get the current values of the + * attributes from the client that holds the delegation or recall the + * delegation before replying to the GETATTR. See RFC 8881 section + * 18.7.4. + * + * Returns 0 if there is no conflict; otherwise an nfs_stat + * code is returned. If @pdp is set to a non-NULL value, then the + * caller must put the reference. + */ +__be32 +nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct dentry *dentry, + struct nfs4_delegation **pdp) +{ + __be32 status; + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); + struct file_lock_context *ctx; + struct nfs4_delegation *dp = NULL; + struct file_lease *fl; + struct nfs4_cb_fattr *ncf; + struct inode *inode = d_inode(dentry); + + ctx = locks_inode_context(inode); + if (!ctx) + return nfs_ok; + +#define NON_NFSD_LEASE ((void *)1) + + spin_lock(&ctx->flc_lock); + for_each_file_lock(fl, &ctx->flc_lease) { + if (fl->c.flc_flags == FL_LAYOUT) + continue; + if (fl->c.flc_type == F_WRLCK) { + if (fl->fl_lmops == &nfsd_lease_mng_ops) + dp = fl->c.flc_owner; + else + dp = NON_NFSD_LEASE; + } + break; + } + if (dp == NULL || dp == NON_NFSD_LEASE || + dp->dl_recall.cb_clp == *(rqstp->rq_lease_breaker)) { + spin_unlock(&ctx->flc_lock); + if (dp == NON_NFSD_LEASE) { + status = nfserrno(nfsd_open_break_lease(inode, + NFSD_MAY_READ)); + if (status != nfserr_jukebox || + !nfsd_wait_for_delegreturn(rqstp, inode)) + return status; + } + return 0; + } + + nfsd_stats_wdeleg_getattr_inc(nn); + refcount_inc(&dp->dl_stid.sc_count); + ncf = &dp->dl_cb_fattr; + nfs4_cb_getattr(&dp->dl_cb_fattr); + spin_unlock(&ctx->flc_lock); + + wait_on_bit_timeout(&ncf->ncf_getattr.cb_flags, NFSD4_CALLBACK_RUNNING, + TASK_UNINTERRUPTIBLE, NFSD_CB_GETATTR_TIMEOUT); + if (ncf->ncf_cb_status) { + /* Recall delegation only if client didn't respond */ + status = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ)); + if (status != nfserr_jukebox || + !nfsd_wait_for_delegreturn(rqstp, inode)) + goto out_status; + } + if (!ncf->ncf_file_modified && + (ncf->ncf_initial_cinfo != ncf->ncf_cb_change || + ncf->ncf_cur_fsize != ncf->ncf_cb_fsize)) + ncf->ncf_file_modified = true; + if (ncf->ncf_file_modified) { + int err; + + /* + * Per section 10.4.3 of RFC 8881, the server would + * not update the file's metadata with the client's + * modified size + */ + err = cb_getattr_update_times(dentry, dp); + if (err) { + status = nfserrno(err); + goto out_status; + } + ncf->ncf_cur_fsize = ncf->ncf_cb_fsize; + *pdp = dp; + return nfs_ok; + } + status = nfs_ok; +out_status: + nfs4_put_stid(&dp->dl_stid); + return status; +} + +/** + * nfsd_get_dir_deleg - attempt to get a directory delegation + * @cstate: compound state + * @gdd: GET_DIR_DELEGATION arg/resp structure + * @nf: nfsd_file opened on the directory + * + * Given a GET_DIR_DELEGATION request @gdd, attempt to acquire a delegation + * on the directory to which @nf refers. Note that this does not set up any + * sort of async notifications for the delegation. + */ +struct nfs4_delegation * +nfsd_get_dir_deleg(struct nfsd4_compound_state *cstate, + struct nfsd4_get_dir_delegation *gdd, + struct nfsd_file *nf) +{ + struct nfs4_client *clp = cstate->clp; + struct nfs4_delegation *dp; + struct file_lease *fl; + struct nfs4_file *fp, *rfp; + int status = 0; + + fp = nfsd4_alloc_file(); + if (!fp) + return ERR_PTR(-ENOMEM); + + nfsd4_file_init(&cstate->current_fh, fp); + + rfp = nfsd4_file_hash_insert(fp, &cstate->current_fh); + if (unlikely(!rfp)) { + put_nfs4_file(fp); + return ERR_PTR(-ENOMEM); + } + + if (rfp != fp) { + put_nfs4_file(fp); + fp = rfp; + } + + /* if this client already has one, return that it's unavailable */ + spin_lock(&state_lock); + spin_lock(&fp->fi_lock); + /* existing delegation? */ + if (nfs4_delegation_exists(clp, fp)) { + status = -EAGAIN; + } else if (!fp->fi_deleg_file) { + fp->fi_deleg_file = nfsd_file_get(nf); + fp->fi_delegees = 1; + } else { + ++fp->fi_delegees; + } + spin_unlock(&fp->fi_lock); + spin_unlock(&state_lock); + + if (status) { + put_nfs4_file(fp); + return ERR_PTR(status); + } + + /* Try to set up the lease */ + status = -ENOMEM; + dp = alloc_init_deleg(clp, fp, NULL, NFS4_OPEN_DELEGATE_READ); + if (!dp) + goto out_delegees; + + fl = nfs4_alloc_init_lease(dp); + if (!fl) + goto out_put_stid; + + status = kernel_setlease(nf->nf_file, + fl->c.flc_type, &fl, NULL); + if (fl) + locks_free_lease(fl); + if (status) + goto out_put_stid; + + /* + * Now, try to hash it. This can fail if we race another nfsd task + * trying to set a delegation on the same file. If that happens, + * then just say UNAVAIL. + */ + spin_lock(&state_lock); + spin_lock(&clp->cl_lock); + spin_lock(&fp->fi_lock); + status = hash_delegation_locked(dp, fp); + spin_unlock(&fp->fi_lock); + spin_unlock(&clp->cl_lock); + spin_unlock(&state_lock); + + if (!status) + return dp; + + /* Something failed. Drop the lease and clean up the stid */ + kernel_setlease(fp->fi_deleg_file->nf_file, F_UNLCK, NULL, (void **)&dp); +out_put_stid: + nfs4_put_stid(&dp->dl_stid); +out_delegees: + put_deleg_file(fp); + return ERR_PTR(status); +} diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 97edb32be77f..30ce5851fe4c 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -55,6 +55,7 @@ #include "netns.h" #include "pnfs.h" #include "filecache.h" +#include "nfs4xdr_gen.h" #include "trace.h" @@ -118,11 +119,11 @@ static int zero_clientid(clientid_t *clid) * operation described in @argp finishes. */ static void * -svcxdr_tmpalloc(struct nfsd4_compoundargs *argp, u32 len) +svcxdr_tmpalloc(struct nfsd4_compoundargs *argp, size_t len) { struct svcxdr_tmpbuf *tb; - tb = kmalloc(sizeof(*tb) + len, GFP_KERNEL); + tb = kmalloc(struct_size(tb, buf, len), GFP_KERNEL); if (!tb) return NULL; tb->next = argp->to_free; @@ -138,9 +139,9 @@ svcxdr_tmpalloc(struct nfsd4_compoundargs *argp, u32 len) * buffer might end on a page boundary. */ static char * -svcxdr_dupstr(struct nfsd4_compoundargs *argp, void *buf, u32 len) +svcxdr_dupstr(struct nfsd4_compoundargs *argp, void *buf, size_t len) { - char *p = svcxdr_tmpalloc(argp, len + 1); + char *p = svcxdr_tmpalloc(argp, size_add(len, 1)); if (!p) return NULL; @@ -150,7 +151,7 @@ svcxdr_dupstr(struct nfsd4_compoundargs *argp, void *buf, u32 len) } static void * -svcxdr_savemem(struct nfsd4_compoundargs *argp, __be32 *p, u32 len) +svcxdr_savemem(struct nfsd4_compoundargs *argp, __be32 *p, size_t len) { __be32 *tmp; @@ -520,6 +521,27 @@ nfsd4_decode_fattr4(struct nfsd4_compoundargs *argp, u32 *bmval, u32 bmlen, *umask = mask & S_IRWXUGO; iattr->ia_valid |= ATTR_MODE; } + if (bmval[2] & FATTR4_WORD2_TIME_DELEG_ACCESS) { + fattr4_time_deleg_access access; + + if (!xdrgen_decode_fattr4_time_deleg_access(argp->xdr, &access)) + return nfserr_bad_xdr; + iattr->ia_atime.tv_sec = access.seconds; + iattr->ia_atime.tv_nsec = access.nseconds; + iattr->ia_valid |= ATTR_ATIME | ATTR_ATIME_SET | ATTR_DELEG; + } + if (bmval[2] & FATTR4_WORD2_TIME_DELEG_MODIFY) { + fattr4_time_deleg_modify modify; + + if (!xdrgen_decode_fattr4_time_deleg_modify(argp->xdr, &modify)) + return nfserr_bad_xdr; + iattr->ia_mtime.tv_sec = modify.seconds; + iattr->ia_mtime.tv_nsec = modify.nseconds; + iattr->ia_ctime.tv_sec = modify.seconds; + iattr->ia_ctime.tv_nsec = modify.nseconds; + iattr->ia_valid |= ATTR_CTIME | ATTR_CTIME_SET | + ATTR_MTIME | ATTR_MTIME_SET | ATTR_DELEG; + } /* request sanity: did attrlist4 contain the expected number of words? */ if (attrlist4_count != xdr_stream_pos(argp->xdr) - starting_pos) @@ -566,23 +588,13 @@ nfsd4_decode_state_owner4(struct nfsd4_compoundargs *argp, } #ifdef CONFIG_NFSD_PNFS -static __be32 -nfsd4_decode_deviceid4(struct nfsd4_compoundargs *argp, - struct nfsd4_deviceid *devid) -{ - __be32 *p; - - p = xdr_inline_decode(argp->xdr, NFS4_DEVICEID4_SIZE); - if (!p) - return nfserr_bad_xdr; - memcpy(devid, p, sizeof(*devid)); - return nfs_ok; -} static __be32 nfsd4_decode_layoutupdate4(struct nfsd4_compoundargs *argp, struct nfsd4_layoutcommit *lcp) { + u32 len; + if (xdr_stream_decode_u32(argp->xdr, &lcp->lc_layout_type) < 0) return nfserr_bad_xdr; if (lcp->lc_layout_type < LAYOUT_NFSV4_1_FILES) @@ -590,13 +602,10 @@ nfsd4_decode_layoutupdate4(struct nfsd4_compoundargs *argp, if (lcp->lc_layout_type >= LAYOUT_TYPE_MAX) return nfserr_bad_xdr; - if (xdr_stream_decode_u32(argp->xdr, &lcp->lc_up_len) < 0) + if (xdr_stream_decode_u32(argp->xdr, &len) < 0) + return nfserr_bad_xdr; + if (!xdr_stream_subsegment(argp->xdr, &lcp->lc_up_layout, len)) return nfserr_bad_xdr; - if (lcp->lc_up_len > 0) { - lcp->lc_up_layout = xdr_inline_decode(argp->xdr, lcp->lc_up_len); - if (!lcp->lc_up_layout) - return nfserr_bad_xdr; - } return nfs_ok; } @@ -1066,13 +1075,13 @@ static __be32 nfsd4_decode_share_access(struct nfsd4_compoundargs *argp, u32 *sh return nfs_ok; if (!argp->minorversion) return nfserr_bad_xdr; - switch (w & NFS4_SHARE_WANT_MASK) { - case NFS4_SHARE_WANT_NO_PREFERENCE: - case NFS4_SHARE_WANT_READ_DELEG: - case NFS4_SHARE_WANT_WRITE_DELEG: - case NFS4_SHARE_WANT_ANY_DELEG: - case NFS4_SHARE_WANT_NO_DELEG: - case NFS4_SHARE_WANT_CANCEL: + switch (w & NFS4_SHARE_WANT_TYPE_MASK) { + case OPEN4_SHARE_ACCESS_WANT_NO_PREFERENCE: + case OPEN4_SHARE_ACCESS_WANT_READ_DELEG: + case OPEN4_SHARE_ACCESS_WANT_WRITE_DELEG: + case OPEN4_SHARE_ACCESS_WANT_ANY_DELEG: + case OPEN4_SHARE_ACCESS_WANT_NO_DELEG: + case OPEN4_SHARE_ACCESS_WANT_CANCEL: break; default: return nfserr_bad_xdr; @@ -1246,14 +1255,6 @@ nfsd4_decode_putfh(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) } static __be32 -nfsd4_decode_putpubfh(struct nfsd4_compoundargs *argp, union nfsd4_op_u *p) -{ - if (argp->minorversion == 0) - return nfs_ok; - return nfserr_notsupp; -} - -static __be32 nfsd4_decode_read(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { struct nfsd4_read *read = &u->read; @@ -1732,6 +1733,35 @@ nfsd4_decode_free_stateid(struct nfsd4_compoundargs *argp, return nfsd4_decode_stateid4(argp, &free_stateid->fr_stateid); } +static __be32 +nfsd4_decode_get_dir_delegation(struct nfsd4_compoundargs *argp, + union nfsd4_op_u *u) +{ + struct nfsd4_get_dir_delegation *gdd = &u->get_dir_delegation; + __be32 status; + + memset(gdd, 0, sizeof(*gdd)); + + if (xdr_stream_decode_bool(argp->xdr, &gdd->gdda_signal_deleg_avail) < 0) + return nfserr_bad_xdr; + status = nfsd4_decode_bitmap4(argp, gdd->gdda_notification_types, + ARRAY_SIZE(gdd->gdda_notification_types)); + if (status) + return status; + status = nfsd4_decode_nfstime4(argp, &gdd->gdda_child_attr_delay); + if (status) + return status; + status = nfsd4_decode_nfstime4(argp, &gdd->gdda_dir_attr_delay); + if (status) + return status; + status = nfsd4_decode_bitmap4(argp, gdd->gdda_child_attributes, + ARRAY_SIZE(gdd->gdda_child_attributes)); + if (status) + return status; + return nfsd4_decode_bitmap4(argp, gdd->gdda_dir_attributes, + ARRAY_SIZE(gdd->gdda_dir_attributes)); +} + #ifdef CONFIG_NFSD_PNFS static __be32 nfsd4_decode_getdeviceinfo(struct nfsd4_compoundargs *argp, @@ -1741,7 +1771,7 @@ nfsd4_decode_getdeviceinfo(struct nfsd4_compoundargs *argp, __be32 status; memset(gdev, 0, sizeof(*gdev)); - status = nfsd4_decode_deviceid4(argp, &gdev->gd_devid); + status = nfsd4_decode_deviceid4(argp->xdr, &gdev->gd_devid); if (status) return status; if (xdr_stream_decode_u32(argp->xdr, &gdev->gd_layout_type) < 0) @@ -1772,7 +1802,7 @@ nfsd4_decode_layoutcommit(struct nfsd4_compoundargs *argp, status = nfsd4_decode_stateid4(argp, &lcp->lc_sid); if (status) return status; - if (xdr_stream_decode_u32(argp->xdr, &lcp->lc_newoffset) < 0) + if (xdr_stream_decode_bool(argp->xdr, &lcp->lc_newoffset) < 0) return nfserr_bad_xdr; if (lcp->lc_newoffset) { if (xdr_stream_decode_u64(argp->xdr, &lcp->lc_last_wr) < 0) @@ -1863,7 +1893,8 @@ nfsd4_decode_sequence(struct nfsd4_compoundargs *argp, return nfserr_bad_xdr; seq->seqid = be32_to_cpup(p++); seq->slotid = be32_to_cpup(p++); - seq->maxslots = be32_to_cpup(p++); + /* sa_highest_slotid counts from 0 but maxslots counts from 1 ... */ + seq->maxslots = be32_to_cpup(p++) + 1; seq->cachethis = be32_to_cpup(p); seq->status_flags = 0; @@ -2117,7 +2148,7 @@ nfsd4_decode_clone(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) */ static __be32 nfsd4_vbuf_from_vector(struct nfsd4_compoundargs *argp, struct xdr_buf *xdr, - char **bufp, u32 buflen) + char **bufp, size_t buflen) { struct page **pages = xdr->pages; struct kvec *head = xdr->head; @@ -2345,7 +2376,7 @@ static const nfsd4_dec nfsd4_dec_ops[] = { [OP_OPEN_CONFIRM] = nfsd4_decode_open_confirm, [OP_OPEN_DOWNGRADE] = nfsd4_decode_open_downgrade, [OP_PUTFH] = nfsd4_decode_putfh, - [OP_PUTPUBFH] = nfsd4_decode_putpubfh, + [OP_PUTPUBFH] = nfsd4_decode_noop, [OP_PUTROOTFH] = nfsd4_decode_noop, [OP_READ] = nfsd4_decode_read, [OP_READDIR] = nfsd4_decode_readdir, @@ -2370,7 +2401,7 @@ static const nfsd4_dec nfsd4_dec_ops[] = { [OP_CREATE_SESSION] = nfsd4_decode_create_session, [OP_DESTROY_SESSION] = nfsd4_decode_destroy_session, [OP_FREE_STATEID] = nfsd4_decode_free_stateid, - [OP_GET_DIR_DELEGATION] = nfsd4_decode_notsupp, + [OP_GET_DIR_DELEGATION] = nfsd4_decode_get_dir_delegation, #ifdef CONFIG_NFSD_PNFS [OP_GETDEVICEINFO] = nfsd4_decode_getdeviceinfo, [OP_GETDEVICELIST] = nfsd4_decode_notsupp, @@ -2476,10 +2507,12 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) for (i = 0; i < argp->opcnt; i++) { op = &argp->ops[i]; op->replay = NULL; + op->opdesc = NULL; if (xdr_stream_decode_u32(argp->xdr, &op->opnum) < 0) return false; if (nfsd4_opnum_in_range(argp, op)) { + op->opdesc = OPDESC(op); op->status = nfsd4_dec_ops[op->opnum](argp, &op->u); if (op->status != nfs_ok) trace_nfsd_compound_decode_err(argp->rqstp, @@ -2490,7 +2523,7 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) op->opnum = OP_ILLEGAL; op->status = nfserr_op_illegal; } - op->opdesc = OPDESC(op); + /* * We'll try to cache the result in the DRC if any one * op in the compound wants to be cached: @@ -2519,57 +2552,72 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) /* Sessions make the DRC unnecessary: */ if (argp->minorversion) cachethis = false; - svc_reserve(argp->rqstp, max_reply + readbytes); + svc_reserve_auth(argp->rqstp, max_reply + readbytes); argp->rqstp->rq_cachetype = cachethis ? RC_REPLBUFF : RC_NOCACHE; + argp->splice_ok = nfsd_read_splice_ok(argp->rqstp); if (readcount > 1 || max_reply > PAGE_SIZE - auth_slack) - clear_bit(RQ_SPLICE_OK, &argp->rqstp->rq_flags); + argp->splice_ok = false; return true; } -static __be32 *encode_change(__be32 *p, struct kstat *stat, struct inode *inode, - struct svc_export *exp) +static __be32 nfsd4_encode_nfs_fh4(struct xdr_stream *xdr, + struct knfsd_fh *fh_handle) { - if (exp->ex_flags & NFSEXP_V4ROOT) { - *p++ = cpu_to_be32(convert_to_wallclock(exp->cd->flush_time)); - *p++ = 0; - } else - p = xdr_encode_hyper(p, nfsd4_change_attribute(stat, inode)); - return p; + return nfsd4_encode_opaque(xdr, fh_handle->fh_raw, fh_handle->fh_size); } -/* - * ctime (in NFSv4, time_metadata) is not writeable, and the client - * doesn't really care what resolution could theoretically be stored by - * the filesystem. - * - * The client cares how close together changes can be while still - * guaranteeing ctime changes. For most filesystems (which have - * timestamps with nanosecond fields) that is limited by the resolution - * of the time returned from current_time() (which I'm assuming to be - * 1/HZ). - */ -static __be32 *encode_time_delta(__be32 *p, struct inode *inode) +/* This is a frequently-encoded type; open-coded for speed */ +static __be32 nfsd4_encode_nfstime4(struct xdr_stream *xdr, + const struct timespec64 *tv) +{ + __be32 *p; + + p = xdr_reserve_space(xdr, XDR_UNIT * 3); + if (!p) + return nfserr_resource; + p = xdr_encode_hyper(p, tv->tv_sec); + *p = cpu_to_be32(tv->tv_nsec); + return nfs_ok; +} + +static __be32 nfsd4_encode_specdata4(struct xdr_stream *xdr, + unsigned int major, unsigned int minor) { - struct timespec64 ts; - u32 ns; + __be32 status; - ns = max_t(u32, NSEC_PER_SEC/HZ, inode->i_sb->s_time_gran); - ts = ns_to_timespec64(ns); + status = nfsd4_encode_uint32_t(xdr, major); + if (status != nfs_ok) + return status; + return nfsd4_encode_uint32_t(xdr, minor); +} - p = xdr_encode_hyper(p, ts.tv_sec); - *p++ = cpu_to_be32(ts.tv_nsec); +static __be32 +nfsd4_encode_change_info4(struct xdr_stream *xdr, const struct nfsd4_change_info *c) +{ + __be32 status; - return p; + status = nfsd4_encode_bool(xdr, c->atomic); + if (status != nfs_ok) + return status; + status = nfsd4_encode_changeid4(xdr, c->before_change); + if (status != nfs_ok) + return status; + return nfsd4_encode_changeid4(xdr, c->after_change); } -static __be32 *encode_cinfo(__be32 *p, struct nfsd4_change_info *c) +static __be32 nfsd4_encode_netaddr4(struct xdr_stream *xdr, + const struct nfs42_netaddr *addr) { - *p++ = cpu_to_be32(c->atomic); - p = xdr_encode_hyper(p, c->before_change); - p = xdr_encode_hyper(p, c->after_change); - return p; + __be32 status; + + /* na_r_netid */ + status = nfsd4_encode_opaque(xdr, addr->netid, addr->netid_len); + if (status != nfs_ok) + return status; + /* na_r_addr */ + return nfsd4_encode_opaque(xdr, addr->addr, addr->addr_len); } /* Encode as an array of strings the string given with components @@ -2582,10 +2630,8 @@ static __be32 nfsd4_encode_components_esc(struct xdr_stream *xdr, char sep, __be32 *p; __be32 pathlen; int pathlen_offset; - int strlen, count=0; char *str, *end, *next; - - dprintk("nfsd4_encode_components(%s)\n", components); + int count = 0; pathlen_offset = xdr->buf->len; p = xdr_reserve_space(xdr, 4); @@ -2612,15 +2658,11 @@ static __be32 nfsd4_encode_components_esc(struct xdr_stream *xdr, char sep, for (; *end && (*end != sep); end++) /* find sep or end of string */; - strlen = end - str; - if (strlen) { - p = xdr_reserve_space(xdr, strlen + 4); - if (!p) + if (end > str) { + if (xdr_stream_encode_opaque(xdr, str, end - str) < 0) return nfserr_resource; - p = xdr_encode_opaque(p, str, strlen); count++; - } - else + } else end++; if (found_esc) end = next; @@ -2641,9 +2683,6 @@ static __be32 nfsd4_encode_components(struct xdr_stream *xdr, char sep, return nfsd4_encode_components_esc(xdr, sep, components, 0, 0); } -/* - * encode a location element of a fs_locations structure - */ static __be32 nfsd4_encode_fs_location4(struct xdr_stream *xdr, struct nfsd4_fs_location *location) { @@ -2656,18 +2695,14 @@ static __be32 nfsd4_encode_fs_location4(struct xdr_stream *xdr, status = nfsd4_encode_components(xdr, '/', location->path); if (status) return status; - return 0; + return nfs_ok; } -/* - * Encode a path in RFC3530 'pathname4' format - */ -static __be32 nfsd4_encode_path(struct xdr_stream *xdr, - const struct path *root, - const struct path *path) +static __be32 nfsd4_encode_pathname4(struct xdr_stream *xdr, + const struct path *root, + const struct path *path) { struct path cur = *path; - __be32 *p; struct dentry **components = NULL; unsigned int ncomponents = 0; __be32 err = nfserr_jukebox; @@ -2698,24 +2733,19 @@ static __be32 nfsd4_encode_path(struct xdr_stream *xdr, components[ncomponents++] = cur.dentry; cur.dentry = dget_parent(cur.dentry); } + err = nfserr_resource; - p = xdr_reserve_space(xdr, 4); - if (!p) + if (xdr_stream_encode_u32(xdr, ncomponents) != XDR_UNIT) goto out_free; - *p++ = cpu_to_be32(ncomponents); - while (ncomponents) { struct dentry *dentry = components[ncomponents - 1]; - unsigned int len; spin_lock(&dentry->d_lock); - len = dentry->d_name.len; - p = xdr_reserve_space(xdr, len + 4); - if (!p) { + if (xdr_stream_encode_opaque(xdr, dentry->d_name.name, + dentry->d_name.len) < 0) { spin_unlock(&dentry->d_lock); goto out_free; } - p = xdr_encode_opaque(p, dentry->d_name.name, len); dprintk("/%pd", dentry); spin_unlock(&dentry->d_lock); dput(dentry); @@ -2732,89 +2762,59 @@ out_free: return err; } -static __be32 nfsd4_encode_fsloc_fsroot(struct xdr_stream *xdr, - struct svc_rqst *rqstp, const struct path *path) +static __be32 nfsd4_encode_fs_locations4(struct xdr_stream *xdr, + struct svc_rqst *rqstp, + struct svc_export *exp) { + struct nfsd4_fs_locations *fslocs = &exp->ex_fslocs; struct svc_export *exp_ps; - __be32 res; + unsigned int i; + __be32 status; + /* fs_root */ exp_ps = rqst_find_fsidzero_export(rqstp); if (IS_ERR(exp_ps)) return nfserrno(PTR_ERR(exp_ps)); - res = nfsd4_encode_path(xdr, &exp_ps->ex_path, path); + status = nfsd4_encode_pathname4(xdr, &exp_ps->ex_path, &exp->ex_path); exp_put(exp_ps); - return res; -} - -/* - * encode a fs_locations structure - */ -static __be32 nfsd4_encode_fs_locations(struct xdr_stream *xdr, - struct svc_rqst *rqstp, struct svc_export *exp) -{ - __be32 status; - int i; - __be32 *p; - struct nfsd4_fs_locations *fslocs = &exp->ex_fslocs; - - status = nfsd4_encode_fsloc_fsroot(xdr, rqstp, &exp->ex_path); - if (status) + if (status != nfs_ok) return status; - p = xdr_reserve_space(xdr, 4); - if (!p) + + /* locations<> */ + if (xdr_stream_encode_u32(xdr, fslocs->locations_count) != XDR_UNIT) return nfserr_resource; - *p++ = cpu_to_be32(fslocs->locations_count); - for (i=0; i<fslocs->locations_count; i++) { + for (i = 0; i < fslocs->locations_count; i++) { status = nfsd4_encode_fs_location4(xdr, &fslocs->locations[i]); - if (status) + if (status != nfs_ok) return status; } - return 0; -} -static u32 nfs4_file_type(umode_t mode) -{ - switch (mode & S_IFMT) { - case S_IFIFO: return NF4FIFO; - case S_IFCHR: return NF4CHR; - case S_IFDIR: return NF4DIR; - case S_IFBLK: return NF4BLK; - case S_IFLNK: return NF4LNK; - case S_IFREG: return NF4REG; - case S_IFSOCK: return NF4SOCK; - default: return NF4BAD; - } + return nfs_ok; } -static inline __be32 -nfsd4_encode_aclname(struct xdr_stream *xdr, struct svc_rqst *rqstp, - struct nfs4_ace *ace) +static __be32 nfsd4_encode_nfsace4(struct xdr_stream *xdr, struct svc_rqst *rqstp, + struct nfs4_ace *ace) { + __be32 status; + + /* type */ + status = nfsd4_encode_acetype4(xdr, ace->type); + if (status != nfs_ok) + return nfserr_resource; + /* flag */ + status = nfsd4_encode_aceflag4(xdr, ace->flag); + if (status != nfs_ok) + return nfserr_resource; + /* access mask */ + status = nfsd4_encode_acemask4(xdr, ace->access_mask & NFS4_ACE_MASK_ALL); + if (status != nfs_ok) + return nfserr_resource; + /* who */ if (ace->whotype != NFS4_ACL_WHO_NAMED) return nfs4_acl_write_who(xdr, ace->whotype); - else if (ace->flag & NFS4_ACE_IDENTIFIER_GROUP) + if (ace->flag & NFS4_ACE_IDENTIFIER_GROUP) return nfsd4_encode_group(xdr, rqstp, ace->who_gid); - else - return nfsd4_encode_user(xdr, rqstp, ace->who_uid); -} - -static inline __be32 -nfsd4_encode_layout_types(struct xdr_stream *xdr, u32 layout_types) -{ - __be32 *p; - unsigned long i = hweight_long(layout_types); - - p = xdr_reserve_space(xdr, 4 + 4 * i); - if (!p) - return nfserr_resource; - - *p++ = cpu_to_be32(i); - - for (i = LAYOUT_NFSV4_1_FILES; i < LAYOUT_TYPE_MAX; ++i) - if (layout_types & (1 << i)) - *p++ = cpu_to_be32(i); - - return 0; + return nfsd4_encode_user(xdr, rqstp, ace->who_uid); } #define WORD0_ABSENT_FS_ATTRS (FATTR4_WORD0_FS_LOCATIONS | FATTR4_WORD0_FSID | \ @@ -2825,11 +2825,11 @@ nfsd4_encode_layout_types(struct xdr_stream *xdr, u32 layout_types) #ifdef CONFIG_NFSD_V4_SECURITY_LABEL static inline __be32 nfsd4_encode_security_label(struct xdr_stream *xdr, struct svc_rqst *rqstp, - void *context, int len) + const struct lsm_context *context) { __be32 *p; - p = xdr_reserve_space(xdr, len + 4 + 4 + 4); + p = xdr_reserve_space(xdr, context->len + 4 + 4 + 4); if (!p) return nfserr_resource; @@ -2839,13 +2839,13 @@ nfsd4_encode_security_label(struct xdr_stream *xdr, struct svc_rqst *rqstp, */ *p++ = cpu_to_be32(0); /* lfs */ *p++ = cpu_to_be32(0); /* pi */ - p = xdr_encode_opaque(p, context, len); + p = xdr_encode_opaque(p, context->context, context->len); return 0; } #else static inline __be32 nfsd4_encode_security_label(struct xdr_stream *xdr, struct svc_rqst *rqstp, - void *context, int len) + struct lsm_context *context) { return 0; } #endif @@ -2886,12 +2886,12 @@ static int nfsd4_get_mounted_on_ino(struct svc_export *exp, u64 *pino) } static __be32 -nfsd4_encode_bitmap(struct xdr_stream *xdr, u32 bmval0, u32 bmval1, u32 bmval2) +nfsd4_encode_bitmap4(struct xdr_stream *xdr, u32 bmval0, u32 bmval1, u32 bmval2) { __be32 *p; if (bmval2) { - p = xdr_reserve_space(xdr, 16); + p = xdr_reserve_space(xdr, XDR_UNIT * 4); if (!p) goto out_resource; *p++ = cpu_to_be32(3); @@ -2899,87 +2899,778 @@ nfsd4_encode_bitmap(struct xdr_stream *xdr, u32 bmval0, u32 bmval1, u32 bmval2) *p++ = cpu_to_be32(bmval1); *p++ = cpu_to_be32(bmval2); } else if (bmval1) { - p = xdr_reserve_space(xdr, 12); + p = xdr_reserve_space(xdr, XDR_UNIT * 3); if (!p) goto out_resource; *p++ = cpu_to_be32(2); *p++ = cpu_to_be32(bmval0); *p++ = cpu_to_be32(bmval1); } else { - p = xdr_reserve_space(xdr, 8); + p = xdr_reserve_space(xdr, XDR_UNIT * 2); if (!p) goto out_resource; *p++ = cpu_to_be32(1); *p++ = cpu_to_be32(bmval0); } - return 0; + return nfs_ok; out_resource: return nfserr_resource; } +struct nfsd4_fattr_args { + struct svc_rqst *rqstp; + struct svc_fh *fhp; + struct svc_export *exp; + struct dentry *dentry; + struct kstat stat; + struct kstatfs statfs; + struct nfs4_acl *acl; + u64 change_attr; +#ifdef CONFIG_NFSD_V4_SECURITY_LABEL + struct lsm_context context; +#endif + u32 rdattr_err; + bool contextsupport; + bool ignore_crossmnt; +}; + +typedef __be32(*nfsd4_enc_attr)(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args); + +static __be32 nfsd4_encode_fattr4__inval(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfserr_inval; +} + +static __be32 nfsd4_encode_fattr4__noop(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfs_ok; +} + +static __be32 nfsd4_encode_fattr4__true(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_bool(xdr, true); +} + +static __be32 nfsd4_encode_fattr4__false(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_bool(xdr, false); +} + +static __be32 nfsd4_encode_fattr4_supported_attrs(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + struct nfsd4_compoundres *resp = args->rqstp->rq_resp; + u32 minorversion = resp->cstate.minorversion; + u32 supp[3]; + + memcpy(supp, nfsd_suppattrs[minorversion], sizeof(supp)); + if (!IS_POSIXACL(d_inode(args->dentry))) + supp[0] &= ~FATTR4_WORD0_ACL; + if (!args->contextsupport) + supp[2] &= ~FATTR4_WORD2_SECURITY_LABEL; + + return nfsd4_encode_bitmap4(xdr, supp[0], supp[1], supp[2]); +} + +static __be32 nfsd4_encode_fattr4_type(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + __be32 *p; + + p = xdr_reserve_space(xdr, XDR_UNIT); + if (!p) + return nfserr_resource; + + switch (args->stat.mode & S_IFMT) { + case S_IFIFO: + *p = cpu_to_be32(NF4FIFO); + break; + case S_IFCHR: + *p = cpu_to_be32(NF4CHR); + break; + case S_IFDIR: + *p = cpu_to_be32(NF4DIR); + break; + case S_IFBLK: + *p = cpu_to_be32(NF4BLK); + break; + case S_IFLNK: + *p = cpu_to_be32(NF4LNK); + break; + case S_IFREG: + *p = cpu_to_be32(NF4REG); + break; + case S_IFSOCK: + *p = cpu_to_be32(NF4SOCK); + break; + default: + return nfserr_serverfault; + } + + return nfs_ok; +} + +static __be32 nfsd4_encode_fattr4_fh_expire_type(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + u32 mask; + + mask = NFS4_FH_PERSISTENT; + if (!(args->exp->ex_flags & NFSEXP_NOSUBTREECHECK)) + mask |= NFS4_FH_VOL_RENAME; + return nfsd4_encode_uint32_t(xdr, mask); +} + +static __be32 nfsd4_encode_fattr4_change(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + const struct svc_export *exp = args->exp; + + if (unlikely(exp->ex_flags & NFSEXP_V4ROOT)) { + u32 flush_time = convert_to_wallclock(exp->cd->flush_time); + + if (xdr_stream_encode_u32(xdr, flush_time) != XDR_UNIT) + return nfserr_resource; + if (xdr_stream_encode_u32(xdr, 0) != XDR_UNIT) + return nfserr_resource; + return nfs_ok; + } + return nfsd4_encode_changeid4(xdr, args->change_attr); +} + +static __be32 nfsd4_encode_fattr4_size(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_uint64_t(xdr, args->stat.size); +} + +static __be32 nfsd4_encode_fattr4_fsid(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + __be32 *p; + + p = xdr_reserve_space(xdr, XDR_UNIT * 2 + XDR_UNIT * 2); + if (!p) + return nfserr_resource; + + if (unlikely(args->exp->ex_fslocs.migrated)) { + p = xdr_encode_hyper(p, NFS4_REFERRAL_FSID_MAJOR); + xdr_encode_hyper(p, NFS4_REFERRAL_FSID_MINOR); + return nfs_ok; + } + switch (fsid_source(args->fhp)) { + case FSIDSOURCE_FSID: + p = xdr_encode_hyper(p, (u64)args->exp->ex_fsid); + xdr_encode_hyper(p, (u64)0); + break; + case FSIDSOURCE_DEV: + *p++ = xdr_zero; + *p++ = cpu_to_be32(MAJOR(args->stat.dev)); + *p++ = xdr_zero; + *p = cpu_to_be32(MINOR(args->stat.dev)); + break; + case FSIDSOURCE_UUID: + xdr_encode_opaque_fixed(p, args->exp->ex_uuid, EX_UUID_LEN); + break; + } + + return nfs_ok; +} + +static __be32 nfsd4_encode_fattr4_lease_time(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + struct nfsd_net *nn = net_generic(SVC_NET(args->rqstp), nfsd_net_id); + + return nfsd4_encode_nfs_lease4(xdr, nn->nfsd4_lease); +} + +static __be32 nfsd4_encode_fattr4_rdattr_error(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_uint32_t(xdr, args->rdattr_err); +} + +static __be32 nfsd4_encode_fattr4_aclsupport(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + u32 mask; + + mask = 0; + if (IS_POSIXACL(d_inode(args->dentry))) + mask = ACL4_SUPPORT_ALLOW_ACL | ACL4_SUPPORT_DENY_ACL; + return nfsd4_encode_uint32_t(xdr, mask); +} + +static __be32 nfsd4_encode_fattr4_acl(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + struct nfs4_acl *acl = args->acl; + struct nfs4_ace *ace; + __be32 status; + + /* nfsace4<> */ + if (!acl) { + if (xdr_stream_encode_u32(xdr, 0) != XDR_UNIT) + return nfserr_resource; + } else { + if (xdr_stream_encode_u32(xdr, acl->naces) != XDR_UNIT) + return nfserr_resource; + for (ace = acl->aces; ace < acl->aces + acl->naces; ace++) { + status = nfsd4_encode_nfsace4(xdr, args->rqstp, ace); + if (status != nfs_ok) + return status; + } + } + return nfs_ok; +} + +static __be32 nfsd4_encode_fattr4_filehandle(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_nfs_fh4(xdr, &args->fhp->fh_handle); +} + +static __be32 nfsd4_encode_fattr4_fileid(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_uint64_t(xdr, args->stat.ino); +} + +static __be32 nfsd4_encode_fattr4_files_avail(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_uint64_t(xdr, args->statfs.f_ffree); +} + +static __be32 nfsd4_encode_fattr4_files_free(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_uint64_t(xdr, args->statfs.f_ffree); +} + +static __be32 nfsd4_encode_fattr4_files_total(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_uint64_t(xdr, args->statfs.f_files); +} + +static __be32 nfsd4_encode_fattr4_fs_locations(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_fs_locations4(xdr, args->rqstp, args->exp); +} + +static __be32 nfsd4_encode_fattr4_maxfilesize(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + struct super_block *sb = args->exp->ex_path.mnt->mnt_sb; + + return nfsd4_encode_uint64_t(xdr, sb->s_maxbytes); +} + +static __be32 nfsd4_encode_fattr4_maxlink(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_uint32_t(xdr, 255); +} + +static __be32 nfsd4_encode_fattr4_maxname(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_uint32_t(xdr, args->statfs.f_namelen); +} + +static __be32 nfsd4_encode_fattr4_maxread(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_uint64_t(xdr, svc_max_payload(args->rqstp)); +} + +static __be32 nfsd4_encode_fattr4_maxwrite(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_uint64_t(xdr, svc_max_payload(args->rqstp)); +} + +static __be32 nfsd4_encode_fattr4_mode(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_mode4(xdr, args->stat.mode & S_IALLUGO); +} + +static __be32 nfsd4_encode_fattr4_numlinks(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_uint32_t(xdr, args->stat.nlink); +} + +static __be32 nfsd4_encode_fattr4_owner(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_user(xdr, args->rqstp, args->stat.uid); +} + +static __be32 nfsd4_encode_fattr4_owner_group(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_group(xdr, args->rqstp, args->stat.gid); +} + +static __be32 nfsd4_encode_fattr4_rawdev(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_specdata4(xdr, MAJOR(args->stat.rdev), + MINOR(args->stat.rdev)); +} + +static __be32 nfsd4_encode_fattr4_space_avail(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + u64 avail = (u64)args->statfs.f_bavail * (u64)args->statfs.f_bsize; + + return nfsd4_encode_uint64_t(xdr, avail); +} + +static __be32 nfsd4_encode_fattr4_space_free(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + u64 free = (u64)args->statfs.f_bfree * (u64)args->statfs.f_bsize; + + return nfsd4_encode_uint64_t(xdr, free); +} + +static __be32 nfsd4_encode_fattr4_space_total(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + u64 total = (u64)args->statfs.f_blocks * (u64)args->statfs.f_bsize; + + return nfsd4_encode_uint64_t(xdr, total); +} + +static __be32 nfsd4_encode_fattr4_space_used(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_uint64_t(xdr, (u64)args->stat.blocks << 9); +} + +static __be32 nfsd4_encode_fattr4_time_access(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_nfstime4(xdr, &args->stat.atime); +} + +static __be32 nfsd4_encode_fattr4_time_create(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_nfstime4(xdr, &args->stat.btime); +} + +/* + * ctime (in NFSv4, time_metadata) is not writeable, and the client + * doesn't really care what resolution could theoretically be stored by + * the filesystem. + * + * The client cares how close together changes can be while still + * guaranteeing ctime changes. For most filesystems (which have + * timestamps with nanosecond fields) that is limited by the resolution + * of the time returned from current_time() (which I'm assuming to be + * 1/HZ). + */ +static __be32 nfsd4_encode_fattr4_time_delta(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + const struct inode *inode = d_inode(args->dentry); + u32 ns = max_t(u32, NSEC_PER_SEC/HZ, inode->i_sb->s_time_gran); + struct timespec64 ts = ns_to_timespec64(ns); + + return nfsd4_encode_nfstime4(xdr, &ts); +} + +static __be32 nfsd4_encode_fattr4_time_metadata(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_nfstime4(xdr, &args->stat.ctime); +} + +static __be32 nfsd4_encode_fattr4_time_modify(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_nfstime4(xdr, &args->stat.mtime); +} + +static __be32 nfsd4_encode_fattr4_mounted_on_fileid(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + u64 ino; + int err; + + if (!args->ignore_crossmnt && + args->dentry == args->exp->ex_path.mnt->mnt_root) { + err = nfsd4_get_mounted_on_ino(args->exp, &ino); + if (err) + return nfserrno(err); + } else + ino = args->stat.ino; + + return nfsd4_encode_uint64_t(xdr, ino); +} + +#ifdef CONFIG_NFSD_PNFS + +static __be32 nfsd4_encode_fattr4_fs_layout_types(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + unsigned long mask = args->exp->ex_layout_types; + int i; + + /* Hamming weight of @mask is the number of layout types to return */ + if (xdr_stream_encode_u32(xdr, hweight_long(mask)) != XDR_UNIT) + return nfserr_resource; + for (i = LAYOUT_NFSV4_1_FILES; i < LAYOUT_TYPE_MAX; ++i) + if (mask & BIT(i)) { + /* layouttype4 */ + if (xdr_stream_encode_u32(xdr, i) != XDR_UNIT) + return nfserr_resource; + } + return nfs_ok; +} + +static __be32 nfsd4_encode_fattr4_layout_types(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + unsigned long mask = args->exp->ex_layout_types; + int i; + + /* Hamming weight of @mask is the number of layout types to return */ + if (xdr_stream_encode_u32(xdr, hweight_long(mask)) != XDR_UNIT) + return nfserr_resource; + for (i = LAYOUT_NFSV4_1_FILES; i < LAYOUT_TYPE_MAX; ++i) + if (mask & BIT(i)) { + /* layouttype4 */ + if (xdr_stream_encode_u32(xdr, i) != XDR_UNIT) + return nfserr_resource; + } + return nfs_ok; +} + +static __be32 nfsd4_encode_fattr4_layout_blksize(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_uint32_t(xdr, args->stat.blksize); +} + +#endif + +static __be32 nfsd4_encode_fattr4_suppattr_exclcreat(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + struct nfsd4_compoundres *resp = args->rqstp->rq_resp; + u32 supp[3]; + + memcpy(supp, nfsd_suppattrs[resp->cstate.minorversion], sizeof(supp)); + supp[0] &= NFSD_SUPPATTR_EXCLCREAT_WORD0; + supp[1] &= NFSD_SUPPATTR_EXCLCREAT_WORD1; + supp[2] &= NFSD_SUPPATTR_EXCLCREAT_WORD2; + + return nfsd4_encode_bitmap4(xdr, supp[0], supp[1], supp[2]); +} + +/* + * Copied from generic_remap_checks/generic_remap_file_range_prep. + * + * These generic functions use the file system's s_blocksize, but + * individual file systems aren't required to use + * generic_remap_file_range_prep. Until there is a mechanism for + * determining a particular file system's (or file's) clone block + * size, this is the best NFSD can do. + */ +static __be32 nfsd4_encode_fattr4_clone_blksize(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + struct inode *inode = d_inode(args->dentry); + + return nfsd4_encode_uint32_t(xdr, inode->i_sb->s_blocksize); +} + +#ifdef CONFIG_NFSD_V4_SECURITY_LABEL +static __be32 nfsd4_encode_fattr4_sec_label(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_security_label(xdr, args->rqstp, &args->context); +} +#endif + +static __be32 nfsd4_encode_fattr4_xattr_support(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + int err = xattr_supports_user_prefix(d_inode(args->dentry)); + + return nfsd4_encode_bool(xdr, err == 0); +} + +#define NFSD_OA_SHARE_ACCESS (BIT(OPEN_ARGS_SHARE_ACCESS_READ) | \ + BIT(OPEN_ARGS_SHARE_ACCESS_WRITE) | \ + BIT(OPEN_ARGS_SHARE_ACCESS_BOTH)) + +#define NFSD_OA_SHARE_DENY (BIT(OPEN_ARGS_SHARE_DENY_NONE) | \ + BIT(OPEN_ARGS_SHARE_DENY_READ) | \ + BIT(OPEN_ARGS_SHARE_DENY_WRITE) | \ + BIT(OPEN_ARGS_SHARE_DENY_BOTH)) + +#define NFSD_OA_SHARE_ACCESS_WANT (BIT(OPEN_ARGS_SHARE_ACCESS_WANT_ANY_DELEG) | \ + BIT(OPEN_ARGS_SHARE_ACCESS_WANT_NO_DELEG) | \ + BIT(OPEN_ARGS_SHARE_ACCESS_WANT_CANCEL) | \ + BIT(OPEN_ARGS_SHARE_ACCESS_WANT_DELEG_TIMESTAMPS) | \ + BIT(OPEN_ARGS_SHARE_ACCESS_WANT_OPEN_XOR_DELEGATION)) + +#define NFSD_OA_OPEN_CLAIM (BIT(OPEN_ARGS_OPEN_CLAIM_NULL) | \ + BIT(OPEN_ARGS_OPEN_CLAIM_PREVIOUS) | \ + BIT(OPEN_ARGS_OPEN_CLAIM_DELEGATE_CUR) | \ + BIT(OPEN_ARGS_OPEN_CLAIM_DELEGATE_PREV)| \ + BIT(OPEN_ARGS_OPEN_CLAIM_FH) | \ + BIT(OPEN_ARGS_OPEN_CLAIM_DELEG_CUR_FH) | \ + BIT(OPEN_ARGS_OPEN_CLAIM_DELEG_PREV_FH)) + +#define NFSD_OA_CREATE_MODE (BIT(OPEN_ARGS_CREATEMODE_UNCHECKED4) | \ + BIT(OPEN_ARGS_CREATE_MODE_GUARDED) | \ + BIT(OPEN_ARGS_CREATEMODE_EXCLUSIVE4) | \ + BIT(OPEN_ARGS_CREATE_MODE_EXCLUSIVE4_1)) + +static uint32_t oa_share_access = NFSD_OA_SHARE_ACCESS; +static uint32_t oa_share_deny = NFSD_OA_SHARE_DENY; +static uint32_t oa_share_access_want = NFSD_OA_SHARE_ACCESS_WANT; +static uint32_t oa_open_claim = NFSD_OA_OPEN_CLAIM; +static uint32_t oa_create_mode = NFSD_OA_CREATE_MODE; + +static const struct open_arguments4 nfsd_open_arguments = { + .oa_share_access = { .count = 1, .element = &oa_share_access }, + .oa_share_deny = { .count = 1, .element = &oa_share_deny }, + .oa_share_access_want = { .count = 1, .element = &oa_share_access_want }, + .oa_open_claim = { .count = 1, .element = &oa_open_claim }, + .oa_create_mode = { .count = 1, .element = &oa_create_mode }, +}; + +static __be32 nfsd4_encode_fattr4_open_arguments(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + if (!xdrgen_encode_fattr4_open_arguments(xdr, &nfsd_open_arguments)) + return nfserr_resource; + return nfs_ok; +} + +static const nfsd4_enc_attr nfsd4_enc_fattr4_encode_ops[] = { + [FATTR4_SUPPORTED_ATTRS] = nfsd4_encode_fattr4_supported_attrs, + [FATTR4_TYPE] = nfsd4_encode_fattr4_type, + [FATTR4_FH_EXPIRE_TYPE] = nfsd4_encode_fattr4_fh_expire_type, + [FATTR4_CHANGE] = nfsd4_encode_fattr4_change, + [FATTR4_SIZE] = nfsd4_encode_fattr4_size, + [FATTR4_LINK_SUPPORT] = nfsd4_encode_fattr4__true, + [FATTR4_SYMLINK_SUPPORT] = nfsd4_encode_fattr4__true, + [FATTR4_NAMED_ATTR] = nfsd4_encode_fattr4__false, + [FATTR4_FSID] = nfsd4_encode_fattr4_fsid, + [FATTR4_UNIQUE_HANDLES] = nfsd4_encode_fattr4__true, + [FATTR4_LEASE_TIME] = nfsd4_encode_fattr4_lease_time, + [FATTR4_RDATTR_ERROR] = nfsd4_encode_fattr4_rdattr_error, + [FATTR4_ACL] = nfsd4_encode_fattr4_acl, + [FATTR4_ACLSUPPORT] = nfsd4_encode_fattr4_aclsupport, + [FATTR4_ARCHIVE] = nfsd4_encode_fattr4__noop, + [FATTR4_CANSETTIME] = nfsd4_encode_fattr4__true, + [FATTR4_CASE_INSENSITIVE] = nfsd4_encode_fattr4__false, + [FATTR4_CASE_PRESERVING] = nfsd4_encode_fattr4__true, + [FATTR4_CHOWN_RESTRICTED] = nfsd4_encode_fattr4__true, + [FATTR4_FILEHANDLE] = nfsd4_encode_fattr4_filehandle, + [FATTR4_FILEID] = nfsd4_encode_fattr4_fileid, + [FATTR4_FILES_AVAIL] = nfsd4_encode_fattr4_files_avail, + [FATTR4_FILES_FREE] = nfsd4_encode_fattr4_files_free, + [FATTR4_FILES_TOTAL] = nfsd4_encode_fattr4_files_total, + [FATTR4_FS_LOCATIONS] = nfsd4_encode_fattr4_fs_locations, + [FATTR4_HIDDEN] = nfsd4_encode_fattr4__noop, + [FATTR4_HOMOGENEOUS] = nfsd4_encode_fattr4__true, + [FATTR4_MAXFILESIZE] = nfsd4_encode_fattr4_maxfilesize, + [FATTR4_MAXLINK] = nfsd4_encode_fattr4_maxlink, + [FATTR4_MAXNAME] = nfsd4_encode_fattr4_maxname, + [FATTR4_MAXREAD] = nfsd4_encode_fattr4_maxread, + [FATTR4_MAXWRITE] = nfsd4_encode_fattr4_maxwrite, + [FATTR4_MIMETYPE] = nfsd4_encode_fattr4__noop, + [FATTR4_MODE] = nfsd4_encode_fattr4_mode, + [FATTR4_NO_TRUNC] = nfsd4_encode_fattr4__true, + [FATTR4_NUMLINKS] = nfsd4_encode_fattr4_numlinks, + [FATTR4_OWNER] = nfsd4_encode_fattr4_owner, + [FATTR4_OWNER_GROUP] = nfsd4_encode_fattr4_owner_group, + [FATTR4_QUOTA_AVAIL_HARD] = nfsd4_encode_fattr4__noop, + [FATTR4_QUOTA_AVAIL_SOFT] = nfsd4_encode_fattr4__noop, + [FATTR4_QUOTA_USED] = nfsd4_encode_fattr4__noop, + [FATTR4_RAWDEV] = nfsd4_encode_fattr4_rawdev, + [FATTR4_SPACE_AVAIL] = nfsd4_encode_fattr4_space_avail, + [FATTR4_SPACE_FREE] = nfsd4_encode_fattr4_space_free, + [FATTR4_SPACE_TOTAL] = nfsd4_encode_fattr4_space_total, + [FATTR4_SPACE_USED] = nfsd4_encode_fattr4_space_used, + [FATTR4_SYSTEM] = nfsd4_encode_fattr4__noop, + [FATTR4_TIME_ACCESS] = nfsd4_encode_fattr4_time_access, + [FATTR4_TIME_ACCESS_SET] = nfsd4_encode_fattr4__noop, + [FATTR4_TIME_BACKUP] = nfsd4_encode_fattr4__noop, + [FATTR4_TIME_CREATE] = nfsd4_encode_fattr4_time_create, + [FATTR4_TIME_DELTA] = nfsd4_encode_fattr4_time_delta, + [FATTR4_TIME_METADATA] = nfsd4_encode_fattr4_time_metadata, + [FATTR4_TIME_MODIFY] = nfsd4_encode_fattr4_time_modify, + [FATTR4_TIME_MODIFY_SET] = nfsd4_encode_fattr4__noop, + [FATTR4_MOUNTED_ON_FILEID] = nfsd4_encode_fattr4_mounted_on_fileid, + [FATTR4_DIR_NOTIF_DELAY] = nfsd4_encode_fattr4__noop, + [FATTR4_DIRENT_NOTIF_DELAY] = nfsd4_encode_fattr4__noop, + [FATTR4_DACL] = nfsd4_encode_fattr4__noop, + [FATTR4_SACL] = nfsd4_encode_fattr4__noop, + [FATTR4_CHANGE_POLICY] = nfsd4_encode_fattr4__noop, + [FATTR4_FS_STATUS] = nfsd4_encode_fattr4__noop, + +#ifdef CONFIG_NFSD_PNFS + [FATTR4_FS_LAYOUT_TYPES] = nfsd4_encode_fattr4_fs_layout_types, + [FATTR4_LAYOUT_HINT] = nfsd4_encode_fattr4__noop, + [FATTR4_LAYOUT_TYPES] = nfsd4_encode_fattr4_layout_types, + [FATTR4_LAYOUT_BLKSIZE] = nfsd4_encode_fattr4_layout_blksize, + [FATTR4_LAYOUT_ALIGNMENT] = nfsd4_encode_fattr4__noop, +#else + [FATTR4_FS_LAYOUT_TYPES] = nfsd4_encode_fattr4__noop, + [FATTR4_LAYOUT_HINT] = nfsd4_encode_fattr4__noop, + [FATTR4_LAYOUT_TYPES] = nfsd4_encode_fattr4__noop, + [FATTR4_LAYOUT_BLKSIZE] = nfsd4_encode_fattr4__noop, + [FATTR4_LAYOUT_ALIGNMENT] = nfsd4_encode_fattr4__noop, +#endif + + [FATTR4_FS_LOCATIONS_INFO] = nfsd4_encode_fattr4__noop, + [FATTR4_MDSTHRESHOLD] = nfsd4_encode_fattr4__noop, + [FATTR4_RETENTION_GET] = nfsd4_encode_fattr4__noop, + [FATTR4_RETENTION_SET] = nfsd4_encode_fattr4__noop, + [FATTR4_RETENTEVT_GET] = nfsd4_encode_fattr4__noop, + [FATTR4_RETENTEVT_SET] = nfsd4_encode_fattr4__noop, + [FATTR4_RETENTION_HOLD] = nfsd4_encode_fattr4__noop, + [FATTR4_MODE_SET_MASKED] = nfsd4_encode_fattr4__noop, + [FATTR4_SUPPATTR_EXCLCREAT] = nfsd4_encode_fattr4_suppattr_exclcreat, + [FATTR4_FS_CHARSET_CAP] = nfsd4_encode_fattr4__noop, + [FATTR4_CLONE_BLKSIZE] = nfsd4_encode_fattr4_clone_blksize, + [FATTR4_SPACE_FREED] = nfsd4_encode_fattr4__noop, + [FATTR4_CHANGE_ATTR_TYPE] = nfsd4_encode_fattr4__noop, + +#ifdef CONFIG_NFSD_V4_SECURITY_LABEL + [FATTR4_SEC_LABEL] = nfsd4_encode_fattr4_sec_label, +#else + [FATTR4_SEC_LABEL] = nfsd4_encode_fattr4__noop, +#endif + + [FATTR4_MODE_UMASK] = nfsd4_encode_fattr4__noop, + [FATTR4_XATTR_SUPPORT] = nfsd4_encode_fattr4_xattr_support, + [FATTR4_TIME_DELEG_ACCESS] = nfsd4_encode_fattr4__inval, + [FATTR4_TIME_DELEG_MODIFY] = nfsd4_encode_fattr4__inval, + [FATTR4_OPEN_ARGUMENTS] = nfsd4_encode_fattr4_open_arguments, +}; + /* * Note: @fhp can be NULL; in this case, we might have to compose the filehandle * ourselves. */ static __be32 -nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp, - struct svc_export *exp, - struct dentry *dentry, u32 *bmval, - struct svc_rqst *rqstp, int ignore_crossmnt) +nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, + struct svc_fh *fhp, struct svc_export *exp, + struct dentry *dentry, const u32 *bmval, + int ignore_crossmnt) { - u32 bmval0 = bmval[0]; - u32 bmval1 = bmval[1]; - u32 bmval2 = bmval[2]; - struct kstat stat; + DECLARE_BITMAP(attr_bitmap, ARRAY_SIZE(nfsd4_enc_fattr4_encode_ops)); + struct nfs4_delegation *dp = NULL; + struct nfsd4_fattr_args args; struct svc_fh *tempfh = NULL; - struct kstatfs statfs; - __be32 *p, *attrlen_p; int starting_len = xdr->buf->len; - int attrlen_offset; - u32 dummy; - u64 dummy64; - u32 rdattr_err = 0; - __be32 status; + unsigned int attrlen_offset; + __be32 attrlen, status; + u32 attrmask[3]; int err; - struct nfs4_acl *acl = NULL; -#ifdef CONFIG_NFSD_V4_SECURITY_LABEL - void *context = NULL; - int contextlen; -#endif - bool contextsupport = false; struct nfsd4_compoundres *resp = rqstp->rq_resp; u32 minorversion = resp->cstate.minorversion; struct path path = { .mnt = exp->ex_path.mnt, .dentry = dentry, }; - struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); + unsigned long bit; + + WARN_ON_ONCE(bmval[1] & NFSD_WRITEONLY_ATTRS_WORD1); + WARN_ON_ONCE(!nfsd_attrs_supported(minorversion, bmval)); - BUG_ON(bmval1 & NFSD_WRITEONLY_ATTRS_WORD1); - BUG_ON(!nfsd_attrs_supported(minorversion, bmval)); + args.rqstp = rqstp; + args.exp = exp; + args.dentry = dentry; + args.ignore_crossmnt = (ignore_crossmnt != 0); + args.acl = NULL; +#ifdef CONFIG_NFSD_V4_SECURITY_LABEL + args.context.context = NULL; +#endif + + /* + * Make a local copy of the attribute bitmap that can be modified. + */ + attrmask[0] = bmval[0]; + attrmask[1] = bmval[1]; + attrmask[2] = bmval[2]; + args.rdattr_err = 0; if (exp->ex_fslocs.migrated) { - status = fattr_handle_absent_fs(&bmval0, &bmval1, &bmval2, &rdattr_err); + status = fattr_handle_absent_fs(&attrmask[0], &attrmask[1], + &attrmask[2], &args.rdattr_err); if (status) goto out; } + if ((attrmask[0] & (FATTR4_WORD0_CHANGE | + FATTR4_WORD0_SIZE)) || + (attrmask[1] & (FATTR4_WORD1_TIME_ACCESS | + FATTR4_WORD1_TIME_MODIFY | + FATTR4_WORD1_TIME_METADATA))) { + status = nfsd4_deleg_getattr_conflict(rqstp, dentry, &dp); + if (status) + goto out; + } + + err = vfs_getattr(&path, &args.stat, + STATX_BASIC_STATS | STATX_BTIME | STATX_CHANGE_COOKIE, + AT_STATX_SYNC_AS_STAT); + if (dp) { + struct nfs4_cb_fattr *ncf = &dp->dl_cb_fattr; + + if (ncf->ncf_file_modified) { + ++ncf->ncf_initial_cinfo; + args.stat.size = ncf->ncf_cur_fsize; + if (!timespec64_is_epoch(&ncf->ncf_cb_mtime)) + args.stat.mtime = ncf->ncf_cb_mtime; + } + args.change_attr = ncf->ncf_initial_cinfo; + + if (!timespec64_is_epoch(&ncf->ncf_cb_atime)) + args.stat.atime = ncf->ncf_cb_atime; + + nfs4_put_stid(&dp->dl_stid); + } else { + args.change_attr = nfsd4_change_attribute(&args.stat); + } - err = vfs_getattr(&path, &stat, STATX_BASIC_STATS, AT_STATX_SYNC_AS_STAT); if (err) goto out_nfserr; - if (!(stat.result_mask & STATX_BTIME)) + + if (!(args.stat.result_mask & STATX_BTIME)) /* underlying FS does not offer btime so we can't share it */ - bmval1 &= ~FATTR4_WORD1_TIME_CREATE; - if ((bmval0 & (FATTR4_WORD0_FILES_AVAIL | FATTR4_WORD0_FILES_FREE | + attrmask[1] &= ~FATTR4_WORD1_TIME_CREATE; + if ((attrmask[0] & (FATTR4_WORD0_FILES_AVAIL | FATTR4_WORD0_FILES_FREE | FATTR4_WORD0_FILES_TOTAL | FATTR4_WORD0_MAXNAME)) || - (bmval1 & (FATTR4_WORD1_SPACE_AVAIL | FATTR4_WORD1_SPACE_FREE | + (attrmask[1] & (FATTR4_WORD1_SPACE_AVAIL | FATTR4_WORD1_SPACE_FREE | FATTR4_WORD1_SPACE_TOTAL))) { - err = vfs_statfs(&path, &statfs); + err = vfs_statfs(&path, &args.statfs); if (err) goto out_nfserr; } - if ((bmval0 & (FATTR4_WORD0_FILEHANDLE | FATTR4_WORD0_FSID)) && !fhp) { + if ((attrmask[0] & (FATTR4_WORD0_FILEHANDLE | FATTR4_WORD0_FSID)) && + !fhp) { tempfh = kmalloc(sizeof(struct svc_fh), GFP_KERNEL); status = nfserr_jukebox; if (!tempfh) @@ -2988,12 +3679,14 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp, status = fh_compose(tempfh, exp, dentry, NULL); if (status) goto out; - fhp = tempfh; - } - if (bmval0 & FATTR4_WORD0_ACL) { - err = nfsd4_get_nfs4_acl(rqstp, dentry, &acl); + args.fhp = tempfh; + } else + args.fhp = fhp; + + if (attrmask[0] & FATTR4_WORD0_ACL) { + err = nfsd4_get_nfs4_acl(rqstp, dentry, &args.acl); if (err == -EOPNOTSUPP) - bmval0 &= ~FATTR4_WORD0_ACL; + attrmask[0] &= ~FATTR4_WORD0_ACL; else if (err == -EINVAL) { status = nfserr_attrnotsupp; goto out; @@ -3001,461 +3694,54 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp, goto out_nfserr; } + args.contextsupport = false; + #ifdef CONFIG_NFSD_V4_SECURITY_LABEL - if ((bmval2 & FATTR4_WORD2_SECURITY_LABEL) || - bmval0 & FATTR4_WORD0_SUPPORTED_ATTRS) { + if ((attrmask[2] & FATTR4_WORD2_SECURITY_LABEL) || + attrmask[0] & FATTR4_WORD0_SUPPORTED_ATTRS) { if (exp->ex_flags & NFSEXP_SECURITY_LABEL) err = security_inode_getsecctx(d_inode(dentry), - &context, &contextlen); + &args.context); else err = -EOPNOTSUPP; - contextsupport = (err == 0); - if (bmval2 & FATTR4_WORD2_SECURITY_LABEL) { + args.contextsupport = (err == 0); + if (attrmask[2] & FATTR4_WORD2_SECURITY_LABEL) { if (err == -EOPNOTSUPP) - bmval2 &= ~FATTR4_WORD2_SECURITY_LABEL; + attrmask[2] &= ~FATTR4_WORD2_SECURITY_LABEL; else if (err) goto out_nfserr; } } #endif /* CONFIG_NFSD_V4_SECURITY_LABEL */ - status = nfsd4_encode_bitmap(xdr, bmval0, bmval1, bmval2); + /* attrmask */ + status = nfsd4_encode_bitmap4(xdr, attrmask[0], attrmask[1], + attrmask[2]); if (status) goto out; + /* attr_vals */ attrlen_offset = xdr->buf->len; - attrlen_p = xdr_reserve_space(xdr, XDR_UNIT); - if (!attrlen_p) + if (unlikely(!xdr_reserve_space(xdr, XDR_UNIT))) goto out_resource; - - if (bmval0 & FATTR4_WORD0_SUPPORTED_ATTRS) { - u32 supp[3]; - - memcpy(supp, nfsd_suppattrs[minorversion], sizeof(supp)); - - if (!IS_POSIXACL(dentry->d_inode)) - supp[0] &= ~FATTR4_WORD0_ACL; - if (!contextsupport) - supp[2] &= ~FATTR4_WORD2_SECURITY_LABEL; - if (!supp[2]) { - p = xdr_reserve_space(xdr, 12); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(2); - *p++ = cpu_to_be32(supp[0]); - *p++ = cpu_to_be32(supp[1]); - } else { - p = xdr_reserve_space(xdr, 16); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(3); - *p++ = cpu_to_be32(supp[0]); - *p++ = cpu_to_be32(supp[1]); - *p++ = cpu_to_be32(supp[2]); - } - } - if (bmval0 & FATTR4_WORD0_TYPE) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - dummy = nfs4_file_type(stat.mode); - if (dummy == NF4BAD) { - status = nfserr_serverfault; + bitmap_from_arr32(attr_bitmap, attrmask, + ARRAY_SIZE(nfsd4_enc_fattr4_encode_ops)); + for_each_set_bit(bit, attr_bitmap, + ARRAY_SIZE(nfsd4_enc_fattr4_encode_ops)) { + status = nfsd4_enc_fattr4_encode_ops[bit](xdr, &args); + if (status != nfs_ok) goto out; - } - *p++ = cpu_to_be32(dummy); - } - if (bmval0 & FATTR4_WORD0_FH_EXPIRE_TYPE) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - if (exp->ex_flags & NFSEXP_NOSUBTREECHECK) - *p++ = cpu_to_be32(NFS4_FH_PERSISTENT); - else - *p++ = cpu_to_be32(NFS4_FH_PERSISTENT| - NFS4_FH_VOL_RENAME); - } - if (bmval0 & FATTR4_WORD0_CHANGE) { - p = xdr_reserve_space(xdr, 8); - if (!p) - goto out_resource; - p = encode_change(p, &stat, d_inode(dentry), exp); - } - if (bmval0 & FATTR4_WORD0_SIZE) { - p = xdr_reserve_space(xdr, 8); - if (!p) - goto out_resource; - p = xdr_encode_hyper(p, stat.size); - } - if (bmval0 & FATTR4_WORD0_LINK_SUPPORT) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(1); - } - if (bmval0 & FATTR4_WORD0_SYMLINK_SUPPORT) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(1); - } - if (bmval0 & FATTR4_WORD0_NAMED_ATTR) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(0); - } - if (bmval0 & FATTR4_WORD0_FSID) { - p = xdr_reserve_space(xdr, 16); - if (!p) - goto out_resource; - if (exp->ex_fslocs.migrated) { - p = xdr_encode_hyper(p, NFS4_REFERRAL_FSID_MAJOR); - p = xdr_encode_hyper(p, NFS4_REFERRAL_FSID_MINOR); - } else switch(fsid_source(fhp)) { - case FSIDSOURCE_FSID: - p = xdr_encode_hyper(p, (u64)exp->ex_fsid); - p = xdr_encode_hyper(p, (u64)0); - break; - case FSIDSOURCE_DEV: - *p++ = cpu_to_be32(0); - *p++ = cpu_to_be32(MAJOR(stat.dev)); - *p++ = cpu_to_be32(0); - *p++ = cpu_to_be32(MINOR(stat.dev)); - break; - case FSIDSOURCE_UUID: - p = xdr_encode_opaque_fixed(p, exp->ex_uuid, - EX_UUID_LEN); - break; - } - } - if (bmval0 & FATTR4_WORD0_UNIQUE_HANDLES) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(0); - } - if (bmval0 & FATTR4_WORD0_LEASE_TIME) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(nn->nfsd4_lease); - } - if (bmval0 & FATTR4_WORD0_RDATTR_ERROR) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(rdattr_err); - } - if (bmval0 & FATTR4_WORD0_ACL) { - struct nfs4_ace *ace; - - if (acl == NULL) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - - *p++ = cpu_to_be32(0); - goto out_acl; - } - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(acl->naces); - - for (ace = acl->aces; ace < acl->aces + acl->naces; ace++) { - p = xdr_reserve_space(xdr, 4*3); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(ace->type); - *p++ = cpu_to_be32(ace->flag); - *p++ = cpu_to_be32(ace->access_mask & - NFS4_ACE_MASK_ALL); - status = nfsd4_encode_aclname(xdr, rqstp, ace); - if (status) - goto out; - } - } -out_acl: - if (bmval0 & FATTR4_WORD0_ACLSUPPORT) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(IS_POSIXACL(dentry->d_inode) ? - ACL4_SUPPORT_ALLOW_ACL|ACL4_SUPPORT_DENY_ACL : 0); - } - if (bmval0 & FATTR4_WORD0_CANSETTIME) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(1); - } - if (bmval0 & FATTR4_WORD0_CASE_INSENSITIVE) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(0); - } - if (bmval0 & FATTR4_WORD0_CASE_PRESERVING) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(1); - } - if (bmval0 & FATTR4_WORD0_CHOWN_RESTRICTED) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(1); - } - if (bmval0 & FATTR4_WORD0_FILEHANDLE) { - p = xdr_reserve_space(xdr, fhp->fh_handle.fh_size + 4); - if (!p) - goto out_resource; - p = xdr_encode_opaque(p, &fhp->fh_handle.fh_raw, - fhp->fh_handle.fh_size); - } - if (bmval0 & FATTR4_WORD0_FILEID) { - p = xdr_reserve_space(xdr, 8); - if (!p) - goto out_resource; - p = xdr_encode_hyper(p, stat.ino); } - if (bmval0 & FATTR4_WORD0_FILES_AVAIL) { - p = xdr_reserve_space(xdr, 8); - if (!p) - goto out_resource; - p = xdr_encode_hyper(p, (u64) statfs.f_ffree); - } - if (bmval0 & FATTR4_WORD0_FILES_FREE) { - p = xdr_reserve_space(xdr, 8); - if (!p) - goto out_resource; - p = xdr_encode_hyper(p, (u64) statfs.f_ffree); - } - if (bmval0 & FATTR4_WORD0_FILES_TOTAL) { - p = xdr_reserve_space(xdr, 8); - if (!p) - goto out_resource; - p = xdr_encode_hyper(p, (u64) statfs.f_files); - } - if (bmval0 & FATTR4_WORD0_FS_LOCATIONS) { - status = nfsd4_encode_fs_locations(xdr, rqstp, exp); - if (status) - goto out; - } - if (bmval0 & FATTR4_WORD0_HOMOGENEOUS) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(1); - } - if (bmval0 & FATTR4_WORD0_MAXFILESIZE) { - p = xdr_reserve_space(xdr, 8); - if (!p) - goto out_resource; - p = xdr_encode_hyper(p, exp->ex_path.mnt->mnt_sb->s_maxbytes); - } - if (bmval0 & FATTR4_WORD0_MAXLINK) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(255); - } - if (bmval0 & FATTR4_WORD0_MAXNAME) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(statfs.f_namelen); - } - if (bmval0 & FATTR4_WORD0_MAXREAD) { - p = xdr_reserve_space(xdr, 8); - if (!p) - goto out_resource; - p = xdr_encode_hyper(p, (u64) svc_max_payload(rqstp)); - } - if (bmval0 & FATTR4_WORD0_MAXWRITE) { - p = xdr_reserve_space(xdr, 8); - if (!p) - goto out_resource; - p = xdr_encode_hyper(p, (u64) svc_max_payload(rqstp)); - } - if (bmval1 & FATTR4_WORD1_MODE) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(stat.mode & S_IALLUGO); - } - if (bmval1 & FATTR4_WORD1_NO_TRUNC) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(1); - } - if (bmval1 & FATTR4_WORD1_NUMLINKS) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(stat.nlink); - } - if (bmval1 & FATTR4_WORD1_OWNER) { - status = nfsd4_encode_user(xdr, rqstp, stat.uid); - if (status) - goto out; - } - if (bmval1 & FATTR4_WORD1_OWNER_GROUP) { - status = nfsd4_encode_group(xdr, rqstp, stat.gid); - if (status) - goto out; - } - if (bmval1 & FATTR4_WORD1_RAWDEV) { - p = xdr_reserve_space(xdr, 8); - if (!p) - goto out_resource; - *p++ = cpu_to_be32((u32) MAJOR(stat.rdev)); - *p++ = cpu_to_be32((u32) MINOR(stat.rdev)); - } - if (bmval1 & FATTR4_WORD1_SPACE_AVAIL) { - p = xdr_reserve_space(xdr, 8); - if (!p) - goto out_resource; - dummy64 = (u64)statfs.f_bavail * (u64)statfs.f_bsize; - p = xdr_encode_hyper(p, dummy64); - } - if (bmval1 & FATTR4_WORD1_SPACE_FREE) { - p = xdr_reserve_space(xdr, 8); - if (!p) - goto out_resource; - dummy64 = (u64)statfs.f_bfree * (u64)statfs.f_bsize; - p = xdr_encode_hyper(p, dummy64); - } - if (bmval1 & FATTR4_WORD1_SPACE_TOTAL) { - p = xdr_reserve_space(xdr, 8); - if (!p) - goto out_resource; - dummy64 = (u64)statfs.f_blocks * (u64)statfs.f_bsize; - p = xdr_encode_hyper(p, dummy64); - } - if (bmval1 & FATTR4_WORD1_SPACE_USED) { - p = xdr_reserve_space(xdr, 8); - if (!p) - goto out_resource; - dummy64 = (u64)stat.blocks << 9; - p = xdr_encode_hyper(p, dummy64); - } - if (bmval1 & FATTR4_WORD1_TIME_ACCESS) { - p = xdr_reserve_space(xdr, 12); - if (!p) - goto out_resource; - p = xdr_encode_hyper(p, (s64)stat.atime.tv_sec); - *p++ = cpu_to_be32(stat.atime.tv_nsec); - } - if (bmval1 & FATTR4_WORD1_TIME_DELTA) { - p = xdr_reserve_space(xdr, 12); - if (!p) - goto out_resource; - p = encode_time_delta(p, d_inode(dentry)); - } - if (bmval1 & FATTR4_WORD1_TIME_METADATA) { - p = xdr_reserve_space(xdr, 12); - if (!p) - goto out_resource; - p = xdr_encode_hyper(p, (s64)stat.ctime.tv_sec); - *p++ = cpu_to_be32(stat.ctime.tv_nsec); - } - if (bmval1 & FATTR4_WORD1_TIME_MODIFY) { - p = xdr_reserve_space(xdr, 12); - if (!p) - goto out_resource; - p = xdr_encode_hyper(p, (s64)stat.mtime.tv_sec); - *p++ = cpu_to_be32(stat.mtime.tv_nsec); - } - if (bmval1 & FATTR4_WORD1_TIME_CREATE) { - p = xdr_reserve_space(xdr, 12); - if (!p) - goto out_resource; - p = xdr_encode_hyper(p, (s64)stat.btime.tv_sec); - *p++ = cpu_to_be32(stat.btime.tv_nsec); - } - if (bmval1 & FATTR4_WORD1_MOUNTED_ON_FILEID) { - u64 ino = stat.ino; - - p = xdr_reserve_space(xdr, 8); - if (!p) - goto out_resource; - /* - * Get ino of mountpoint in parent filesystem, if not ignoring - * crossmount and this is the root of a cross-mounted - * filesystem. - */ - if (ignore_crossmnt == 0 && - dentry == exp->ex_path.mnt->mnt_root) { - err = nfsd4_get_mounted_on_ino(exp, &ino); - if (err) - goto out_nfserr; - } - p = xdr_encode_hyper(p, ino); - } -#ifdef CONFIG_NFSD_PNFS - if (bmval1 & FATTR4_WORD1_FS_LAYOUT_TYPES) { - status = nfsd4_encode_layout_types(xdr, exp->ex_layout_types); - if (status) - goto out; - } - - if (bmval2 & FATTR4_WORD2_LAYOUT_TYPES) { - status = nfsd4_encode_layout_types(xdr, exp->ex_layout_types); - if (status) - goto out; - } - - if (bmval2 & FATTR4_WORD2_LAYOUT_BLKSIZE) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(stat.blksize); - } -#endif /* CONFIG_NFSD_PNFS */ - if (bmval2 & FATTR4_WORD2_SUPPATTR_EXCLCREAT) { - u32 supp[3]; - - memcpy(supp, nfsd_suppattrs[minorversion], sizeof(supp)); - supp[0] &= NFSD_SUPPATTR_EXCLCREAT_WORD0; - supp[1] &= NFSD_SUPPATTR_EXCLCREAT_WORD1; - supp[2] &= NFSD_SUPPATTR_EXCLCREAT_WORD2; - - status = nfsd4_encode_bitmap(xdr, supp[0], supp[1], supp[2]); - if (status) - goto out; - } - -#ifdef CONFIG_NFSD_V4_SECURITY_LABEL - if (bmval2 & FATTR4_WORD2_SECURITY_LABEL) { - status = nfsd4_encode_security_label(xdr, rqstp, context, - contextlen); - if (status) - goto out; - } -#endif - - if (bmval2 & FATTR4_WORD2_XATTR_SUPPORT) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - err = xattr_supported_namespace(d_inode(dentry), - XATTR_USER_PREFIX); - *p++ = cpu_to_be32(err == 0); - } - - *attrlen_p = cpu_to_be32(xdr->buf->len - attrlen_offset - XDR_UNIT); + attrlen = cpu_to_be32(xdr->buf->len - attrlen_offset - XDR_UNIT); + write_bytes_to_xdr_buf(xdr->buf, attrlen_offset, &attrlen, XDR_UNIT); status = nfs_ok; out: #ifdef CONFIG_NFSD_V4_SECURITY_LABEL - if (context) - security_release_secctx(context, contextlen); + if (args.context.context) + security_release_secctx(&args.context); #endif /* CONFIG_NFSD_V4_SECURITY_LABEL */ - kfree(acl); + kfree(args.acl); if (tempfh) { fh_put(tempfh); kfree(tempfh); @@ -3496,12 +3782,28 @@ __be32 nfsd4_encode_fattr_to_buf(__be32 **p, int words, __be32 ret; svcxdr_init_encode_from_buffer(&xdr, &dummy, *p, words << 2); - ret = nfsd4_encode_fattr(&xdr, fhp, exp, dentry, bmval, rqstp, - ignore_crossmnt); + ret = nfsd4_encode_fattr4(rqstp, &xdr, fhp, exp, dentry, bmval, + ignore_crossmnt); *p = xdr.p; return ret; } +/* + * The buffer space for this field was reserved during a previous + * call to nfsd4_encode_entry4(). + */ +static void nfsd4_encode_entry4_nfs_cookie4(const struct nfsd4_readdir *readdir, + u64 offset) +{ + __be64 cookie = cpu_to_be64(offset); + struct xdr_stream *xdr = readdir->xdr; + + if (!readdir->cookie_offset) + return; + write_bytes_to_xdr_buf(xdr->buf, readdir->cookie_offset, &cookie, + sizeof(cookie)); +} + static inline int attributes_need_mount(u32 *bmval) { if (bmval[0] & ~(FATTR4_WORD0_RDATTR_ERROR | FATTR4_WORD0_LEASE_TIME)) @@ -3512,15 +3814,17 @@ static inline int attributes_need_mount(u32 *bmval) } static __be32 -nfsd4_encode_dirent_fattr(struct xdr_stream *xdr, struct nfsd4_readdir *cd, - const char *name, int namlen) +nfsd4_encode_entry4_fattr(struct nfsd4_readdir *cd, const char *name, + int namlen) { struct svc_export *exp = cd->rd_fhp->fh_export; struct dentry *dentry; __be32 nfserr; int ignore_crossmnt = 0; - dentry = lookup_positive_unlocked(name, cd->rd_fhp->fh_dentry, namlen); + dentry = lookup_one_positive_unlocked(&nop_mnt_idmap, + &QSTR_LEN(name, namlen), + cd->rd_fhp->fh_dentry); if (IS_ERR(dentry)) return nfserrno(PTR_ERR(dentry)); @@ -3550,39 +3854,40 @@ nfsd4_encode_dirent_fattr(struct xdr_stream *xdr, struct nfsd4_readdir *cd, nfserr = nfserrno(err); goto out_put; } - nfserr = check_nfsd_access(exp, cd->rd_rqstp); + nfserr = check_nfsd_access(exp, cd->rd_rqstp, false); if (nfserr) goto out_put; } out_encode: - nfserr = nfsd4_encode_fattr(xdr, NULL, exp, dentry, cd->rd_bmval, - cd->rd_rqstp, ignore_crossmnt); + nfserr = nfsd4_encode_fattr4(cd->rd_rqstp, cd->xdr, NULL, exp, dentry, + cd->rd_bmval, ignore_crossmnt); out_put: dput(dentry); exp_put(exp); return nfserr; } -static __be32 * -nfsd4_encode_rdattr_error(struct xdr_stream *xdr, __be32 nfserr) +static __be32 +nfsd4_encode_entry4_rdattr_error(struct xdr_stream *xdr, __be32 nfserr) { - __be32 *p; - - p = xdr_reserve_space(xdr, 20); - if (!p) - return NULL; - *p++ = htonl(2); - *p++ = htonl(FATTR4_WORD0_RDATTR_ERROR); /* bmval0 */ - *p++ = htonl(0); /* bmval1 */ + __be32 status; - *p++ = htonl(4); /* attribute length */ - *p++ = nfserr; /* no htonl */ - return p; + /* attrmask */ + status = nfsd4_encode_bitmap4(xdr, FATTR4_WORD0_RDATTR_ERROR, 0, 0); + if (status != nfs_ok) + return status; + /* attr_vals */ + if (xdr_stream_encode_u32(xdr, XDR_UNIT) != XDR_UNIT) + return nfserr_resource; + /* rdattr_error */ + if (xdr_stream_encode_be32(xdr, nfserr) != XDR_UNIT) + return nfserr_resource; + return nfs_ok; } static int -nfsd4_encode_dirent(void *ccdv, const char *name, int namlen, +nfsd4_encode_entry4(void *ccdv, const char *name, int namlen, loff_t offset, u64 ino, unsigned int d_type) { struct readdir_cd *ccd = ccdv; @@ -3593,8 +3898,6 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen, u32 name_and_cookie; int entry_bytes; __be32 nfserr = nfserr_toosmall; - __be64 wire_offset; - __be32 *p; /* In nfsv4, "." and ".." never make it onto the wire.. */ if (name && isdotent(name, namlen)) { @@ -3602,24 +3905,19 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen, return 0; } - if (cd->cookie_offset) { - wire_offset = cpu_to_be64(offset); - write_bytes_to_xdr_buf(xdr->buf, cd->cookie_offset, - &wire_offset, 8); - } + /* Encode the previous entry's cookie value */ + nfsd4_encode_entry4_nfs_cookie4(cd, offset); - p = xdr_reserve_space(xdr, 4); - if (!p) + if (xdr_stream_encode_item_present(xdr) != XDR_UNIT) goto fail; - *p++ = xdr_one; /* mark entry present */ + + /* Reserve send buffer space for this entry's cookie value. */ cookie_offset = xdr->buf->len; - p = xdr_reserve_space(xdr, 3*4 + namlen); - if (!p) + if (nfsd4_encode_nfs_cookie4(xdr, OFFSET_MAX) != nfs_ok) goto fail; - p = xdr_encode_hyper(p, OFFSET_MAX); /* offset of next entry */ - p = xdr_encode_array(p, name, namlen); /* name length & name */ - - nfserr = nfsd4_encode_dirent_fattr(xdr, cd, name, namlen); + if (nfsd4_encode_component4(xdr, name, namlen) != nfs_ok) + goto fail; + nfserr = nfsd4_encode_entry4_fattr(cd, name, namlen); switch (nfserr) { case nfs_ok: break; @@ -3650,8 +3948,7 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen, */ if (!(cd->rd_bmval[0] & FATTR4_WORD0_RDATTR_ERROR)) goto fail; - p = nfsd4_encode_rdattr_error(xdr, nfserr); - if (p == NULL) { + if (nfsd4_encode_entry4_rdattr_error(xdr, nfserr)) { nfserr = nfserr_toosmall; goto fail; } @@ -3686,17 +3983,49 @@ fail: } static __be32 -nfsd4_encode_stateid(struct xdr_stream *xdr, stateid_t *sid) +nfsd4_encode_verifier4(struct xdr_stream *xdr, const nfs4_verifier *verf) +{ + __be32 *p; + + p = xdr_reserve_space(xdr, NFS4_VERIFIER_SIZE); + if (!p) + return nfserr_resource; + memcpy(p, verf->data, sizeof(verf->data)); + return nfs_ok; +} + +static __be32 +nfsd4_encode_clientid4(struct xdr_stream *xdr, const clientid_t *clientid) { __be32 *p; - p = xdr_reserve_space(xdr, sizeof(stateid_t)); + p = xdr_reserve_space(xdr, sizeof(__be64)); + if (!p) + return nfserr_resource; + memcpy(p, clientid, sizeof(*clientid)); + return nfs_ok; +} + +/* This is a frequently-encoded item; open-coded for speed */ +static __be32 +nfsd4_encode_stateid4(struct xdr_stream *xdr, const stateid_t *sid) +{ + __be32 *p; + + p = xdr_reserve_space(xdr, NFS4_STATEID_SIZE); if (!p) return nfserr_resource; *p++ = cpu_to_be32(sid->si_generation); - p = xdr_encode_opaque_fixed(p, &sid->si_opaque, - sizeof(stateid_opaque_t)); - return 0; + memcpy(p, &sid->si_opaque, sizeof(sid->si_opaque)); + return nfs_ok; +} + +static __be32 +nfsd4_encode_sessionid4(struct xdr_stream *xdr, + const struct nfs4_sessionid *sessionid) +{ + return nfsd4_encode_opaque_fixed(xdr, sessionid->data, + NFS4_MAX_SESSIONID_LEN); } static __be32 @@ -3705,14 +4034,14 @@ nfsd4_encode_access(struct nfsd4_compoundres *resp, __be32 nfserr, { struct nfsd4_access *access = &u->access; struct xdr_stream *xdr = resp->xdr; - __be32 *p; + __be32 status; - p = xdr_reserve_space(xdr, 8); - if (!p) - return nfserr_resource; - *p++ = cpu_to_be32(access->ac_supported); - *p++ = cpu_to_be32(access->ac_resp_access); - return 0; + /* supported */ + status = nfsd4_encode_uint32_t(xdr, access->ac_supported); + if (status != nfs_ok) + return status; + /* access */ + return nfsd4_encode_uint32_t(xdr, access->ac_resp_access); } static __be32 nfsd4_encode_bind_conn_to_session(struct nfsd4_compoundres *resp, __be32 nfserr, @@ -3720,17 +4049,16 @@ static __be32 nfsd4_encode_bind_conn_to_session(struct nfsd4_compoundres *resp, { struct nfsd4_bind_conn_to_session *bcts = &u->bind_conn_to_session; struct xdr_stream *xdr = resp->xdr; - __be32 *p; - p = xdr_reserve_space(xdr, NFS4_MAX_SESSIONID_LEN + 8); - if (!p) + /* bctsr_sessid */ + nfserr = nfsd4_encode_sessionid4(xdr, &bcts->sessionid); + if (nfserr != nfs_ok) + return nfserr; + /* bctsr_dir */ + if (xdr_stream_encode_u32(xdr, bcts->dir) != XDR_UNIT) return nfserr_resource; - p = xdr_encode_opaque_fixed(p, bcts->sessionid.data, - NFS4_MAX_SESSIONID_LEN); - *p++ = cpu_to_be32(bcts->dir); - /* Upshifting from TCP to RDMA is not supported */ - *p++ = cpu_to_be32(0); - return 0; + /* bctsr_use_conn_in_rdma_mode */ + return nfsd4_encode_bool(xdr, false); } static __be32 @@ -3740,7 +4068,8 @@ nfsd4_encode_close(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_close *close = &u->close; struct xdr_stream *xdr = resp->xdr; - return nfsd4_encode_stateid(xdr, &close->cl_stateid); + /* open_stateid */ + return nfsd4_encode_stateid4(xdr, &close->cl_stateid); } @@ -3749,15 +4078,8 @@ nfsd4_encode_commit(struct nfsd4_compoundres *resp, __be32 nfserr, union nfsd4_op_u *u) { struct nfsd4_commit *commit = &u->commit; - struct xdr_stream *xdr = resp->xdr; - __be32 *p; - p = xdr_reserve_space(xdr, NFS4_VERIFIER_SIZE); - if (!p) - return nfserr_resource; - p = xdr_encode_opaque_fixed(p, commit->co_verf.data, - NFS4_VERIFIER_SIZE); - return 0; + return nfsd4_encode_verifier4(resp->xdr, &commit->co_verf); } static __be32 @@ -3766,14 +4088,14 @@ nfsd4_encode_create(struct nfsd4_compoundres *resp, __be32 nfserr, { struct nfsd4_create *create = &u->create; struct xdr_stream *xdr = resp->xdr; - __be32 *p; - p = xdr_reserve_space(xdr, 20); - if (!p) - return nfserr_resource; - encode_cinfo(p, &create->cr_cinfo); - return nfsd4_encode_bitmap(xdr, create->cr_bmval[0], - create->cr_bmval[1], create->cr_bmval[2]); + /* cinfo */ + nfserr = nfsd4_encode_change_info4(xdr, &create->cr_cinfo); + if (nfserr) + return nfserr; + /* attrset */ + return nfsd4_encode_bitmap4(xdr, create->cr_bmval[0], + create->cr_bmval[1], create->cr_bmval[2]); } static __be32 @@ -3784,65 +4106,56 @@ nfsd4_encode_getattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct svc_fh *fhp = getattr->ga_fhp; struct xdr_stream *xdr = resp->xdr; - return nfsd4_encode_fattr(xdr, fhp, fhp->fh_export, fhp->fh_dentry, - getattr->ga_bmval, resp->rqstp, 0); + /* obj_attributes */ + return nfsd4_encode_fattr4(resp->rqstp, xdr, fhp, fhp->fh_export, + fhp->fh_dentry, getattr->ga_bmval, 0); } static __be32 nfsd4_encode_getfh(struct nfsd4_compoundres *resp, __be32 nfserr, union nfsd4_op_u *u) { - struct svc_fh **fhpp = &u->getfh; struct xdr_stream *xdr = resp->xdr; - struct svc_fh *fhp = *fhpp; - unsigned int len; - __be32 *p; + struct svc_fh *fhp = u->getfh; - len = fhp->fh_handle.fh_size; - p = xdr_reserve_space(xdr, len + 4); - if (!p) - return nfserr_resource; - p = xdr_encode_opaque(p, &fhp->fh_handle.fh_raw, len); - return 0; + /* object */ + return nfsd4_encode_nfs_fh4(xdr, &fhp->fh_handle); } -/* -* Including all fields other than the name, a LOCK4denied structure requires -* 8(clientid) + 4(namelen) + 8(offset) + 8(length) + 4(type) = 32 bytes. -*/ static __be32 -nfsd4_encode_lock_denied(struct xdr_stream *xdr, struct nfsd4_lock_denied *ld) +nfsd4_encode_lock_owner4(struct xdr_stream *xdr, const clientid_t *clientid, + const struct xdr_netobj *owner) { - struct xdr_netobj *conf = &ld->ld_owner; - __be32 *p; + __be32 status; -again: - p = xdr_reserve_space(xdr, 32 + XDR_LEN(conf->len)); - if (!p) { - /* - * Don't fail to return the result just because we can't - * return the conflicting open: - */ - if (conf->len) { - kfree(conf->data); - conf->len = 0; - conf->data = NULL; - goto again; - } + /* clientid */ + status = nfsd4_encode_clientid4(xdr, clientid); + if (status != nfs_ok) + return status; + /* owner */ + return nfsd4_encode_opaque(xdr, owner->data, owner->len); +} + +static __be32 +nfsd4_encode_lock4denied(struct xdr_stream *xdr, + const struct nfsd4_lock_denied *ld) +{ + __be32 status; + + /* offset */ + status = nfsd4_encode_offset4(xdr, ld->ld_start); + if (status != nfs_ok) + return status; + /* length */ + status = nfsd4_encode_length4(xdr, ld->ld_length); + if (status != nfs_ok) + return status; + /* locktype */ + if (xdr_stream_encode_u32(xdr, ld->ld_type) != XDR_UNIT) return nfserr_resource; - } - p = xdr_encode_hyper(p, ld->ld_start); - p = xdr_encode_hyper(p, ld->ld_length); - *p++ = cpu_to_be32(ld->ld_type); - if (conf->len) { - p = xdr_encode_opaque_fixed(p, &ld->ld_clientid, 8); - p = xdr_encode_opaque(p, conf->data, conf->len); - kfree(conf->data); - } else { /* non - nfsv4 lock in conflict, no clientid nor owner */ - p = xdr_encode_hyper(p, (u64)0); /* clientid */ - *p++ = cpu_to_be32(0); /* length of owner name */ - } - return nfserr_denied; + /* owner */ + return nfsd4_encode_lock_owner4(xdr, &ld->ld_clientid, + &ld->ld_owner); } static __be32 @@ -3851,13 +4164,21 @@ nfsd4_encode_lock(struct nfsd4_compoundres *resp, __be32 nfserr, { struct nfsd4_lock *lock = &u->lock; struct xdr_stream *xdr = resp->xdr; + __be32 status; - if (!nfserr) - nfserr = nfsd4_encode_stateid(xdr, &lock->lk_resp_stateid); - else if (nfserr == nfserr_denied) - nfserr = nfsd4_encode_lock_denied(xdr, &lock->lk_denied); - - return nfserr; + switch (nfserr) { + case nfs_ok: + /* resok4 */ + status = nfsd4_encode_stateid4(xdr, &lock->lk_resp_stateid); + break; + case nfserr_denied: + /* denied */ + status = nfsd4_encode_lock4denied(xdr, &lock->lk_denied); + break; + default: + return nfserr; + } + return status != nfs_ok ? status : nfserr; } static __be32 @@ -3866,9 +4187,14 @@ nfsd4_encode_lockt(struct nfsd4_compoundres *resp, __be32 nfserr, { struct nfsd4_lockt *lockt = &u->lockt; struct xdr_stream *xdr = resp->xdr; + __be32 status; - if (nfserr == nfserr_denied) - nfsd4_encode_lock_denied(xdr, &lockt->lt_denied); + if (nfserr == nfserr_denied) { + /* denied */ + status = nfsd4_encode_lock4denied(xdr, &lockt->lt_denied); + if (status != nfs_ok) + return status; + } return nfserr; } @@ -3879,7 +4205,8 @@ nfsd4_encode_locku(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_locku *locku = &u->locku; struct xdr_stream *xdr = resp->xdr; - return nfsd4_encode_stateid(xdr, &locku->lu_stateid); + /* lock_stateid */ + return nfsd4_encode_stateid4(xdr, &locku->lu_stateid); } @@ -3889,110 +4216,165 @@ nfsd4_encode_link(struct nfsd4_compoundres *resp, __be32 nfserr, { struct nfsd4_link *link = &u->link; struct xdr_stream *xdr = resp->xdr; - __be32 *p; - p = xdr_reserve_space(xdr, 20); - if (!p) - return nfserr_resource; - p = encode_cinfo(p, &link->li_cinfo); - return 0; + return nfsd4_encode_change_info4(xdr, &link->li_cinfo); } - +/* + * This implementation does not yet support returning an ACE in an + * OPEN that offers a delegation. + */ static __be32 -nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, - union nfsd4_op_u *u) +nfsd4_encode_open_nfsace4(struct xdr_stream *xdr) { - struct nfsd4_open *open = &u->open; - struct xdr_stream *xdr = resp->xdr; - __be32 *p; + __be32 status; - nfserr = nfsd4_encode_stateid(xdr, &open->op_stateid); - if (nfserr) - return nfserr; - p = xdr_reserve_space(xdr, 24); - if (!p) + /* type */ + status = nfsd4_encode_acetype4(xdr, NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE); + if (status != nfs_ok) + return nfserr_resource; + /* flag */ + status = nfsd4_encode_aceflag4(xdr, 0); + if (status != nfs_ok) return nfserr_resource; - p = encode_cinfo(p, &open->op_cinfo); - *p++ = cpu_to_be32(open->op_rflags); + /* access mask */ + status = nfsd4_encode_acemask4(xdr, 0); + if (status != nfs_ok) + return nfserr_resource; + /* who - empty for now */ + if (xdr_stream_encode_u32(xdr, 0) != XDR_UNIT) + return nfserr_resource; + return nfs_ok; +} - nfserr = nfsd4_encode_bitmap(xdr, open->op_bmval[0], open->op_bmval[1], - open->op_bmval[2]); - if (nfserr) - return nfserr; +static __be32 +nfsd4_encode_open_read_delegation4(struct xdr_stream *xdr, struct nfsd4_open *open) +{ + __be32 status; - p = xdr_reserve_space(xdr, 4); - if (!p) + /* stateid */ + status = nfsd4_encode_stateid4(xdr, &open->op_delegate_stateid); + if (status != nfs_ok) + return status; + /* recall */ + status = nfsd4_encode_bool(xdr, open->op_recall); + if (status != nfs_ok) + return status; + /* permissions */ + return nfsd4_encode_open_nfsace4(xdr); +} + +static __be32 +nfsd4_encode_nfs_space_limit4(struct xdr_stream *xdr, u64 filesize) +{ + /* limitby */ + if (xdr_stream_encode_u32(xdr, NFS4_LIMIT_SIZE) != XDR_UNIT) return nfserr_resource; + /* filesize */ + return nfsd4_encode_uint64_t(xdr, filesize); +} - *p++ = cpu_to_be32(open->op_delegate_type); - switch (open->op_delegate_type) { - case NFS4_OPEN_DELEGATE_NONE: - break; - case NFS4_OPEN_DELEGATE_READ: - nfserr = nfsd4_encode_stateid(xdr, &open->op_delegate_stateid); - if (nfserr) - return nfserr; - p = xdr_reserve_space(xdr, 20); - if (!p) - return nfserr_resource; - *p++ = cpu_to_be32(open->op_recall); +static __be32 +nfsd4_encode_open_write_delegation4(struct xdr_stream *xdr, + struct nfsd4_open *open) +{ + __be32 status; - /* - * TODO: ACE's in delegations - */ - *p++ = cpu_to_be32(NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE); - *p++ = cpu_to_be32(0); - *p++ = cpu_to_be32(0); - *p++ = cpu_to_be32(0); /* XXX: is NULL principal ok? */ + /* stateid */ + status = nfsd4_encode_stateid4(xdr, &open->op_delegate_stateid); + if (status != nfs_ok) + return status; + /* recall */ + status = nfsd4_encode_bool(xdr, open->op_recall); + if (status != nfs_ok) + return status; + /* space_limit */ + status = nfsd4_encode_nfs_space_limit4(xdr, 0); + if (status != nfs_ok) + return status; + return nfsd4_encode_open_nfsace4(xdr); +} + +static __be32 +nfsd4_encode_open_none_delegation4(struct xdr_stream *xdr, + struct nfsd4_open *open) +{ + __be32 status = nfs_ok; + + /* ond_why */ + if (xdr_stream_encode_u32(xdr, open->op_why_no_deleg) != XDR_UNIT) + return nfserr_resource; + switch (open->op_why_no_deleg) { + case WND4_CONTENTION: + /* ond_server_will_push_deleg */ + status = nfsd4_encode_bool(xdr, false); break; - case NFS4_OPEN_DELEGATE_WRITE: - nfserr = nfsd4_encode_stateid(xdr, &open->op_delegate_stateid); - if (nfserr) - return nfserr; - p = xdr_reserve_space(xdr, 32); - if (!p) - return nfserr_resource; - *p++ = cpu_to_be32(0); + case WND4_RESOURCE: + /* ond_server_will_signal_avail */ + status = nfsd4_encode_bool(xdr, false); + } + return status; +} - /* - * TODO: space_limit's in delegations - */ - *p++ = cpu_to_be32(NFS4_LIMIT_SIZE); - *p++ = cpu_to_be32(~(u32)0); - *p++ = cpu_to_be32(~(u32)0); +static __be32 +nfsd4_encode_open_delegation4(struct xdr_stream *xdr, struct nfsd4_open *open) +{ + __be32 status; - /* - * TODO: ACE's in delegations - */ - *p++ = cpu_to_be32(NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE); - *p++ = cpu_to_be32(0); - *p++ = cpu_to_be32(0); - *p++ = cpu_to_be32(0); /* XXX: is NULL principal ok? */ + /* delegation_type */ + if (xdr_stream_encode_u32(xdr, open->op_delegate_type) != XDR_UNIT) + return nfserr_resource; + switch (open->op_delegate_type) { + case OPEN_DELEGATE_NONE: + status = nfs_ok; break; - case NFS4_OPEN_DELEGATE_NONE_EXT: /* 4.1 */ - switch (open->op_why_no_deleg) { - case WND4_CONTENTION: - case WND4_RESOURCE: - p = xdr_reserve_space(xdr, 8); - if (!p) - return nfserr_resource; - *p++ = cpu_to_be32(open->op_why_no_deleg); - /* deleg signaling not supported yet: */ - *p++ = cpu_to_be32(0); - break; - default: - p = xdr_reserve_space(xdr, 4); - if (!p) - return nfserr_resource; - *p++ = cpu_to_be32(open->op_why_no_deleg); - } + case OPEN_DELEGATE_READ: + case OPEN_DELEGATE_READ_ATTRS_DELEG: + /* read */ + status = nfsd4_encode_open_read_delegation4(xdr, open); + break; + case OPEN_DELEGATE_WRITE: + case OPEN_DELEGATE_WRITE_ATTRS_DELEG: + /* write */ + status = nfsd4_encode_open_write_delegation4(xdr, open); + break; + case OPEN_DELEGATE_NONE_EXT: + /* od_whynone */ + status = nfsd4_encode_open_none_delegation4(xdr, open); break; default: - BUG(); + status = nfserr_serverfault; } - /* XXX save filehandle here */ - return 0; + + return status; +} + +static __be32 +nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) +{ + struct nfsd4_open *open = &u->open; + struct xdr_stream *xdr = resp->xdr; + + /* stateid */ + nfserr = nfsd4_encode_stateid4(xdr, &open->op_stateid); + if (nfserr != nfs_ok) + return nfserr; + /* cinfo */ + nfserr = nfsd4_encode_change_info4(xdr, &open->op_cinfo); + if (nfserr != nfs_ok) + return nfserr; + /* rflags */ + nfserr = nfsd4_encode_uint32_t(xdr, open->op_rflags); + if (nfserr != nfs_ok) + return nfserr; + /* attrset */ + nfserr = nfsd4_encode_bitmap4(xdr, open->op_bmval[0], + open->op_bmval[1], open->op_bmval[2]); + if (nfserr != nfs_ok) + return nfserr; + /* delegation */ + return nfsd4_encode_open_delegation4(xdr, open); } static __be32 @@ -4002,7 +4384,8 @@ nfsd4_encode_open_confirm(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open_confirm *oc = &u->open_confirm; struct xdr_stream *xdr = resp->xdr; - return nfsd4_encode_stateid(xdr, &oc->oc_resp_stateid); + /* open_stateid */ + return nfsd4_encode_stateid4(xdr, &oc->oc_resp_stateid); } static __be32 @@ -4012,9 +4395,15 @@ nfsd4_encode_open_downgrade(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open_downgrade *od = &u->open_downgrade; struct xdr_stream *xdr = resp->xdr; - return nfsd4_encode_stateid(xdr, &od->od_stateid); + /* open_stateid */ + return nfsd4_encode_stateid4(xdr, &od->od_stateid); } +/* + * The operation of this function assumes that this is the only + * READ operation in the COMPOUND. If there are multiple READs, + * we use nfsd4_encode_readv(). + */ static __be32 nfsd4_encode_splice_read( struct nfsd4_compoundres *resp, struct nfsd4_read *read, @@ -4025,8 +4414,21 @@ static __be32 nfsd4_encode_splice_read( int status, space_left; __be32 nfserr; - /* Make sure there will be room for padding if needed */ - if (xdr->end - xdr->p < 1) + /* + * Splice read doesn't work if encoding has already wandered + * into the XDR buf's page array. + */ + if (unlikely(xdr->buf->page_len)) { + WARN_ON_ONCE(1); + return nfserr_serverfault; + } + + /* + * Make sure there is room at the end of buf->head for + * svcxdr_encode_opaque_pages() to create a tail buffer + * to XDR-pad the payload. + */ + if (xdr->iov != xdr->buf->head || xdr->end - xdr->p < 1) return nfserr_resource; nfserr = nfsd_splice_read(read->rd_rqstp, read->rd_fhp, @@ -4035,6 +4437,8 @@ static __be32 nfsd4_encode_splice_read( read->rd_length = maxcount; if (nfserr) goto out_err; + svcxdr_encode_opaque_pages(read->rd_rqstp, xdr, buf->pages, + buf->page_base, maxcount); status = svc_encode_result_payload(read->rd_rqstp, buf->head[0].iov_len, maxcount); if (status) { @@ -4042,31 +4446,19 @@ static __be32 nfsd4_encode_splice_read( goto out_err; } - buf->page_len = maxcount; - buf->len += maxcount; - xdr->page_ptr += (buf->page_base + maxcount + PAGE_SIZE - 1) - / PAGE_SIZE; - - /* Use rest of head for padding and remaining ops: */ - buf->tail[0].iov_base = xdr->p; - buf->tail[0].iov_len = 0; - xdr->iov = buf->tail; - if (maxcount&3) { - int pad = 4 - (maxcount&3); - - *(xdr->p++) = 0; - - buf->tail[0].iov_base += maxcount&3; - buf->tail[0].iov_len = pad; - buf->len += pad; - } - + /* + * Prepare to encode subsequent operations. + * + * xdr_truncate_encode() is not safe to use after a successful + * splice read has been done, so the following stream + * manipulations are open-coded. + */ space_left = min_t(int, (void *)xdr->end - (void *)xdr->p, buf->buflen - buf->len); buf->buflen = buf->len + space_left; xdr->end = (__be32 *)((void *)xdr->end + space_left); - return 0; + return nfs_ok; out_err: /* @@ -4080,26 +4472,38 @@ out_err: static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp, struct nfsd4_read *read, - struct file *file, unsigned long maxcount) + unsigned long maxcount) { struct xdr_stream *xdr = resp->xdr; + unsigned int base = xdr->buf->page_len & ~PAGE_MASK; unsigned int starting_len = xdr->buf->len; __be32 zero = xdr_zero; __be32 nfserr; - read->rd_vlen = xdr_reserve_space_vec(xdr, resp->rqstp->rq_vec, maxcount); - if (read->rd_vlen < 0) - return nfserr_resource; - - nfserr = nfsd_readv(resp->rqstp, read->rd_fhp, file, read->rd_offset, - resp->rqstp->rq_vec, read->rd_vlen, &maxcount, - &read->rd_eof); + nfserr = nfsd_iter_read(resp->rqstp, read->rd_fhp, read->rd_nf, + read->rd_offset, &maxcount, base, + &read->rd_eof); read->rd_length = maxcount; if (nfserr) return nfserr; + + /* + * svcxdr_encode_opaque_pages() is not used here because + * we don't want to encode subsequent results in this + * COMPOUND into the xdr->buf's tail, but rather those + * results should follow the NFS READ payload in the + * buf's pages. + */ + if (xdr_reserve_space_vec(xdr, maxcount) < 0) + return nfserr_resource; + + /* + * Mark the buffer location of the NFS READ payload so that + * direct placement-capable transports send only the + * payload bytes out-of-band. + */ if (svc_encode_result_payload(resp->rqstp, starting_len, maxcount)) return nfserr_io; - xdr_truncate_encode(xdr, starting_len + xdr_align_size(maxcount)); write_bytes_to_xdr_buf(xdr->buf, starting_len + maxcount, &zero, xdr_pad_size(maxcount)); @@ -4110,27 +4514,26 @@ static __be32 nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr, union nfsd4_op_u *u) { + struct nfsd4_compoundargs *argp = resp->rqstp->rq_argp; struct nfsd4_read *read = &u->read; - bool splice_ok = test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags); - unsigned long maxcount; struct xdr_stream *xdr = resp->xdr; + bool splice_ok = argp->splice_ok; + unsigned int eof_offset; + unsigned long maxcount; + __be32 wire_data[2]; struct file *file; - int starting_len = xdr->buf->len; - __be32 *p; if (nfserr) return nfserr; + + eof_offset = xdr->buf->len; file = read->rd_nf->nf_file; - p = xdr_reserve_space(xdr, 8); /* eof flag and byte count */ - if (!p) { + /* Reserve space for the eof flag and byte count */ + if (unlikely(!xdr_reserve_space(xdr, XDR_UNIT * 2))) { WARN_ON_ONCE(splice_ok); return nfserr_resource; } - if (resp->xdr->buf->page_len && splice_ok) { - WARN_ON_ONCE(1); - return nfserr_serverfault; - } xdr_commit_encode(xdr); maxcount = min_t(unsigned long, read->rd_length, @@ -4139,14 +4542,15 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr, if (file->f_op->splice_read && splice_ok) nfserr = nfsd4_encode_splice_read(resp, read, file, maxcount); else - nfserr = nfsd4_encode_readv(resp, read, file, maxcount); + nfserr = nfsd4_encode_readv(resp, read, maxcount); if (nfserr) { - xdr_truncate_encode(xdr, starting_len); + xdr_truncate_encode(xdr, eof_offset); return nfserr; } - p = xdr_encode_bool(p, read->rd_eof); - *p = cpu_to_be32(read->rd_length); + wire_data[0] = read->rd_eof ? xdr_one : xdr_zero; + wire_data[1] = cpu_to_be32(read->rd_length); + write_bytes_to_xdr_buf(xdr->buf, eof_offset, &wire_data, XDR_UNIT * 2); return nfs_ok; } @@ -4155,25 +4559,21 @@ nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, union nfsd4_op_u *u) { struct nfsd4_readlink *readlink = &u->readlink; - __be32 *p, *maxcount_p, zero = xdr_zero; + __be32 *p, wire_count, zero = xdr_zero; struct xdr_stream *xdr = resp->xdr; - int length_offset = xdr->buf->len; + unsigned int length_offset; int maxcount, status; - maxcount_p = xdr_reserve_space(xdr, XDR_UNIT); - if (!maxcount_p) + /* linktext4.count */ + length_offset = xdr->buf->len; + if (unlikely(!xdr_reserve_space(xdr, XDR_UNIT))) return nfserr_resource; - maxcount = PAGE_SIZE; + /* linktext4.data */ + maxcount = PAGE_SIZE; p = xdr_reserve_space(xdr, maxcount); if (!p) return nfserr_resource; - /* - * XXX: By default, vfs_readlink() will truncate symlinks if they - * would overflow the buffer. Is this kosher in NFSv4? If not, one - * easy fix is: if vfs_readlink() precisely fills the buffer, assume - * that truncation occurred, and return NFS4ERR_RESOURCE. - */ nfserr = nfsd_readlink(readlink->rl_rqstp, readlink->rl_fhp, (char *)p, &maxcount); if (nfserr == nfserr_isdir) @@ -4186,7 +4586,9 @@ nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, nfserr = nfserrno(status); goto out_err; } - *maxcount_p = cpu_to_be32(maxcount); + + wire_count = cpu_to_be32(maxcount); + write_bytes_to_xdr_buf(xdr->buf, length_offset, &wire_count, XDR_UNIT); xdr_truncate_encode(xdr, length_offset + 4 + xdr_align_size(maxcount)); write_bytes_to_xdr_buf(xdr->buf, length_offset + 4 + maxcount, &zero, xdr_pad_size(maxcount)); @@ -4197,96 +4599,83 @@ out_err: return nfserr; } -static __be32 -nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, - union nfsd4_op_u *u) +static __be32 nfsd4_encode_dirlist4(struct xdr_stream *xdr, + struct nfsd4_readdir *readdir, + u32 max_payload) { - struct nfsd4_readdir *readdir = &u->readdir; - int maxcount; - int bytes_left; + int bytes_left, maxcount, starting_len = xdr->buf->len; loff_t offset; - __be64 wire_offset; - struct xdr_stream *xdr = resp->xdr; - int starting_len = xdr->buf->len; - __be32 *p; - - p = xdr_reserve_space(xdr, NFS4_VERIFIER_SIZE); - if (!p) - return nfserr_resource; - - /* XXX: Following NFSv3, we ignore the READDIR verifier for now. */ - *p++ = cpu_to_be32(0); - *p++ = cpu_to_be32(0); - xdr->buf->head[0].iov_len = (char *)xdr->p - - (char *)xdr->buf->head[0].iov_base; + __be32 status; /* * Number of bytes left for directory entries allowing for the - * final 8 bytes of the readdir and a following failed op: + * final 8 bytes of the readdir and a following failed op. */ - bytes_left = xdr->buf->buflen - xdr->buf->len - - COMPOUND_ERR_SLACK_SPACE - 8; - if (bytes_left < 0) { - nfserr = nfserr_resource; - goto err_no_verf; - } - maxcount = svc_max_payload(resp->rqstp); - maxcount = min_t(u32, readdir->rd_maxcount, maxcount); + bytes_left = xdr->buf->buflen - xdr->buf->len - + COMPOUND_ERR_SLACK_SPACE - XDR_UNIT * 2; + if (bytes_left < 0) + return nfserr_resource; + maxcount = min_t(u32, readdir->rd_maxcount, max_payload); + /* - * Note the rfc defines rd_maxcount as the size of the - * READDIR4resok structure, which includes the verifier above - * and the 8 bytes encoded at the end of this function: + * The RFC defines rd_maxcount as the size of the + * READDIR4resok structure, which includes the verifier + * and the 8 bytes encoded at the end of this function. */ - if (maxcount < 16) { - nfserr = nfserr_toosmall; - goto err_no_verf; - } - maxcount = min_t(int, maxcount-16, bytes_left); + if (maxcount < XDR_UNIT * 4) + return nfserr_toosmall; + maxcount = min_t(int, maxcount - XDR_UNIT * 4, bytes_left); - /* RFC 3530 14.2.24 allows us to ignore dircount when it's 0: */ + /* RFC 3530 14.2.24 allows us to ignore dircount when it's 0 */ if (!readdir->rd_dircount) - readdir->rd_dircount = svc_max_payload(resp->rqstp); + readdir->rd_dircount = max_payload; + /* *entries */ readdir->xdr = xdr; readdir->rd_maxcount = maxcount; readdir->common.err = 0; readdir->cookie_offset = 0; - offset = readdir->rd_cookie; - nfserr = nfsd_readdir(readdir->rd_rqstp, readdir->rd_fhp, - &offset, - &readdir->common, nfsd4_encode_dirent); - if (nfserr == nfs_ok && - readdir->common.err == nfserr_toosmall && - xdr->buf->len == starting_len + 8) { - /* nothing encoded; which limit did we hit?: */ - if (maxcount - 16 < bytes_left) - /* It was the fault of rd_maxcount: */ - nfserr = nfserr_toosmall; - else - /* We ran out of buffer space: */ - nfserr = nfserr_resource; + status = nfsd_readdir(readdir->rd_rqstp, readdir->rd_fhp, &offset, + &readdir->common, nfsd4_encode_entry4); + if (status) + return status; + if (readdir->common.err == nfserr_toosmall && + xdr->buf->len == starting_len) { + /* No entries were encoded. Which limit did we hit? */ + if (maxcount - XDR_UNIT * 4 < bytes_left) + /* It was the fault of rd_maxcount */ + return nfserr_toosmall; + /* We ran out of buffer space */ + return nfserr_resource; } - if (nfserr) - goto err_no_verf; + /* Encode the final entry's cookie value */ + nfsd4_encode_entry4_nfs_cookie4(readdir, offset); + /* No entries follow */ + if (xdr_stream_encode_item_absent(xdr) != XDR_UNIT) + return nfserr_resource; - if (readdir->cookie_offset) { - wire_offset = cpu_to_be64(offset); - write_bytes_to_xdr_buf(xdr->buf, readdir->cookie_offset, - &wire_offset, 8); - } + /* eof */ + return nfsd4_encode_bool(xdr, readdir->common.err == nfserr_eof); +} - p = xdr_reserve_space(xdr, 8); - if (!p) { - WARN_ON_ONCE(1); - goto err_no_verf; - } - *p++ = 0; /* no more entries */ - *p++ = htonl(readdir->common.err == nfserr_eof); +static __be32 +nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) +{ + struct nfsd4_readdir *readdir = &u->readdir; + struct xdr_stream *xdr = resp->xdr; + int starting_len = xdr->buf->len; - return 0; -err_no_verf: - xdr_truncate_encode(xdr, starting_len); + /* cookieverf */ + nfserr = nfsd4_encode_verifier4(xdr, &readdir->rd_verf); + if (nfserr != nfs_ok) + return nfserr; + + /* reply */ + nfserr = nfsd4_encode_dirlist4(xdr, readdir, svc_max_payload(resp->rqstp)); + if (nfserr != nfs_ok) + xdr_truncate_encode(xdr, starting_len); return nfserr; } @@ -4296,13 +4685,8 @@ nfsd4_encode_remove(struct nfsd4_compoundres *resp, __be32 nfserr, { struct nfsd4_remove *remove = &u->remove; struct xdr_stream *xdr = resp->xdr; - __be32 *p; - p = xdr_reserve_space(xdr, 20); - if (!p) - return nfserr_resource; - p = encode_cinfo(p, &remove->rm_cinfo); - return 0; + return nfsd4_encode_change_info4(xdr, &remove->rm_cinfo); } static __be32 @@ -4311,24 +4695,70 @@ nfsd4_encode_rename(struct nfsd4_compoundres *resp, __be32 nfserr, { struct nfsd4_rename *rename = &u->rename; struct xdr_stream *xdr = resp->xdr; - __be32 *p; - p = xdr_reserve_space(xdr, 40); - if (!p) + nfserr = nfsd4_encode_change_info4(xdr, &rename->rn_sinfo); + if (nfserr) + return nfserr; + return nfsd4_encode_change_info4(xdr, &rename->rn_tinfo); +} + +static __be32 +nfsd4_encode_rpcsec_gss_info(struct xdr_stream *xdr, + struct rpcsec_gss_info *info) +{ + __be32 status; + + /* oid */ + if (xdr_stream_encode_opaque(xdr, info->oid.data, info->oid.len) < 0) return nfserr_resource; - p = encode_cinfo(p, &rename->rn_sinfo); - p = encode_cinfo(p, &rename->rn_tinfo); - return 0; + /* qop */ + status = nfsd4_encode_qop4(xdr, info->qop); + if (status != nfs_ok) + return status; + /* service */ + if (xdr_stream_encode_u32(xdr, info->service) != XDR_UNIT) + return nfserr_resource; + + return nfs_ok; } static __be32 -nfsd4_do_encode_secinfo(struct xdr_stream *xdr, struct svc_export *exp) +nfsd4_encode_secinfo4(struct xdr_stream *xdr, rpc_authflavor_t pf, + u32 *supported) +{ + struct rpcsec_gss_info info; + __be32 status; + + if (rpcauth_get_gssinfo(pf, &info) == 0) { + (*supported)++; + + /* flavor */ + status = nfsd4_encode_uint32_t(xdr, RPC_AUTH_GSS); + if (status != nfs_ok) + return status; + /* flavor_info */ + status = nfsd4_encode_rpcsec_gss_info(xdr, &info); + if (status != nfs_ok) + return status; + } else if (pf < RPC_AUTH_MAXFLAVOR) { + (*supported)++; + + /* flavor */ + status = nfsd4_encode_uint32_t(xdr, pf); + if (status != nfs_ok) + return status; + } + return nfs_ok; +} + +static __be32 +nfsd4_encode_SECINFO4resok(struct xdr_stream *xdr, struct svc_export *exp) { u32 i, nflavs, supported; struct exp_flavor_info *flavs; struct exp_flavor_info def_flavs[2]; - __be32 *p, *flavorsp; - static bool report = true; + unsigned int count_offset; + __be32 status, wire_count; if (exp->ex_nflavors) { flavs = exp->ex_flavors; @@ -4350,42 +4780,20 @@ nfsd4_do_encode_secinfo(struct xdr_stream *xdr, struct svc_export *exp) } } - supported = 0; - p = xdr_reserve_space(xdr, 4); - if (!p) + count_offset = xdr->buf->len; + if (unlikely(!xdr_reserve_space(xdr, XDR_UNIT))) return nfserr_resource; - flavorsp = p++; /* to be backfilled later */ - - for (i = 0; i < nflavs; i++) { - rpc_authflavor_t pf = flavs[i].pseudoflavor; - struct rpcsec_gss_info info; - if (rpcauth_get_gssinfo(pf, &info) == 0) { - supported++; - p = xdr_reserve_space(xdr, 4 + 4 + - XDR_LEN(info.oid.len) + 4 + 4); - if (!p) - return nfserr_resource; - *p++ = cpu_to_be32(RPC_AUTH_GSS); - p = xdr_encode_opaque(p, info.oid.data, info.oid.len); - *p++ = cpu_to_be32(info.qop); - *p++ = cpu_to_be32(info.service); - } else if (pf < RPC_AUTH_MAXFLAVOR) { - supported++; - p = xdr_reserve_space(xdr, 4); - if (!p) - return nfserr_resource; - *p++ = cpu_to_be32(pf); - } else { - if (report) - pr_warn("NFS: SECINFO: security flavor %u " - "is not supported\n", pf); - } + for (i = 0, supported = 0; i < nflavs; i++) { + status = nfsd4_encode_secinfo4(xdr, flavs[i].pseudoflavor, + &supported); + if (status != nfs_ok) + return status; } - if (nflavs != supported) - report = false; - *flavorsp = htonl(supported); + wire_count = cpu_to_be32(supported); + write_bytes_to_xdr_buf(xdr->buf, count_offset, &wire_count, + XDR_UNIT); return 0; } @@ -4396,7 +4804,7 @@ nfsd4_encode_secinfo(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_secinfo *secinfo = &u->secinfo; struct xdr_stream *xdr = resp->xdr; - return nfsd4_do_encode_secinfo(xdr, secinfo->si_exp); + return nfsd4_encode_SECINFO4resok(xdr, secinfo->si_exp); } static __be32 @@ -4406,37 +4814,28 @@ nfsd4_encode_secinfo_no_name(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_secinfo_no_name *secinfo = &u->secinfo_no_name; struct xdr_stream *xdr = resp->xdr; - return nfsd4_do_encode_secinfo(xdr, secinfo->sin_exp); + return nfsd4_encode_SECINFO4resok(xdr, secinfo->sin_exp); } -/* - * The SETATTR encode routine is special -- it always encodes a bitmap, - * regardless of the error status. - */ static __be32 nfsd4_encode_setattr(struct nfsd4_compoundres *resp, __be32 nfserr, union nfsd4_op_u *u) { struct nfsd4_setattr *setattr = &u->setattr; - struct xdr_stream *xdr = resp->xdr; - __be32 *p; + __be32 status; - p = xdr_reserve_space(xdr, 16); - if (!p) - return nfserr_resource; - if (nfserr) { - *p++ = cpu_to_be32(3); - *p++ = cpu_to_be32(0); - *p++ = cpu_to_be32(0); - *p++ = cpu_to_be32(0); - } - else { - *p++ = cpu_to_be32(3); - *p++ = cpu_to_be32(setattr->sa_bmval[0]); - *p++ = cpu_to_be32(setattr->sa_bmval[1]); - *p++ = cpu_to_be32(setattr->sa_bmval[2]); + switch (nfserr) { + case nfs_ok: + /* attrsset */ + status = nfsd4_encode_bitmap4(resp->xdr, setattr->sa_bmval[0], + setattr->sa_bmval[1], + setattr->sa_bmval[2]); + break; + default: + /* attrsset */ + status = nfsd4_encode_bitmap4(resp->xdr, 0, 0, 0); } - return nfserr; + return status != nfs_ok ? status : nfserr; } static __be32 @@ -4445,23 +4844,25 @@ nfsd4_encode_setclientid(struct nfsd4_compoundres *resp, __be32 nfserr, { struct nfsd4_setclientid *scd = &u->setclientid; struct xdr_stream *xdr = resp->xdr; - __be32 *p; if (!nfserr) { - p = xdr_reserve_space(xdr, 8 + NFS4_VERIFIER_SIZE); - if (!p) - return nfserr_resource; - p = xdr_encode_opaque_fixed(p, &scd->se_clientid, 8); - p = xdr_encode_opaque_fixed(p, &scd->se_confirm, - NFS4_VERIFIER_SIZE); - } - else if (nfserr == nfserr_clid_inuse) { - p = xdr_reserve_space(xdr, 8); - if (!p) - return nfserr_resource; - *p++ = cpu_to_be32(0); - *p++ = cpu_to_be32(0); + nfserr = nfsd4_encode_clientid4(xdr, &scd->se_clientid); + if (nfserr != nfs_ok) + goto out; + nfserr = nfsd4_encode_verifier4(xdr, &scd->se_confirm); + } else if (nfserr == nfserr_clid_inuse) { + /* empty network id */ + if (xdr_stream_encode_u32(xdr, 0) < 0) { + nfserr = nfserr_resource; + goto out; + } + /* empty universal address */ + if (xdr_stream_encode_u32(xdr, 0) < 0) { + nfserr = nfserr_resource; + goto out; + } } +out: return nfserr; } @@ -4471,149 +4872,196 @@ nfsd4_encode_write(struct nfsd4_compoundres *resp, __be32 nfserr, { struct nfsd4_write *write = &u->write; struct xdr_stream *xdr = resp->xdr; - __be32 *p; - p = xdr_reserve_space(xdr, 16); - if (!p) + /* count */ + nfserr = nfsd4_encode_count4(xdr, write->wr_bytes_written); + if (nfserr) + return nfserr; + /* committed */ + if (xdr_stream_encode_u32(xdr, write->wr_how_written) != XDR_UNIT) return nfserr_resource; - *p++ = cpu_to_be32(write->wr_bytes_written); - *p++ = cpu_to_be32(write->wr_how_written); - p = xdr_encode_opaque_fixed(p, write->wr_verifier.data, - NFS4_VERIFIER_SIZE); - return 0; + /* writeverf */ + return nfsd4_encode_verifier4(xdr, &write->wr_verifier); } static __be32 -nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr, - union nfsd4_op_u *u) +nfsd4_encode_state_protect_ops4(struct xdr_stream *xdr, + struct nfsd4_exchange_id *exid) { - struct nfsd4_exchange_id *exid = &u->exchange_id; - struct xdr_stream *xdr = resp->xdr; - __be32 *p; - char *major_id; - char *server_scope; - int major_id_sz; - int server_scope_sz; - uint64_t minor_id = 0; - struct nfsd_net *nn = net_generic(SVC_NET(resp->rqstp), nfsd_net_id); - - major_id = nn->nfsd_name; - major_id_sz = strlen(nn->nfsd_name); - server_scope = nn->nfsd_name; - server_scope_sz = strlen(nn->nfsd_name); - - p = xdr_reserve_space(xdr, - 8 /* eir_clientid */ + - 4 /* eir_sequenceid */ + - 4 /* eir_flags */ + - 4 /* spr_how */); - if (!p) - return nfserr_resource; + __be32 status; - p = xdr_encode_opaque_fixed(p, &exid->clientid, 8); - *p++ = cpu_to_be32(exid->seqid); - *p++ = cpu_to_be32(exid->flags); + /* spo_must_enforce */ + status = nfsd4_encode_bitmap4(xdr, exid->spo_must_enforce[0], + exid->spo_must_enforce[1], + exid->spo_must_enforce[2]); + if (status != nfs_ok) + return status; + /* spo_must_allow */ + return nfsd4_encode_bitmap4(xdr, exid->spo_must_allow[0], + exid->spo_must_allow[1], + exid->spo_must_allow[2]); +} - *p++ = cpu_to_be32(exid->spa_how); +static __be32 +nfsd4_encode_state_protect4_r(struct xdr_stream *xdr, struct nfsd4_exchange_id *exid) +{ + __be32 status; + if (xdr_stream_encode_u32(xdr, exid->spa_how) != XDR_UNIT) + return nfserr_resource; switch (exid->spa_how) { case SP4_NONE: + status = nfs_ok; break; case SP4_MACH_CRED: - /* spo_must_enforce bitmap: */ - nfserr = nfsd4_encode_bitmap(xdr, - exid->spo_must_enforce[0], - exid->spo_must_enforce[1], - exid->spo_must_enforce[2]); - if (nfserr) - return nfserr; - /* spo_must_allow bitmap: */ - nfserr = nfsd4_encode_bitmap(xdr, - exid->spo_must_allow[0], - exid->spo_must_allow[1], - exid->spo_must_allow[2]); - if (nfserr) - return nfserr; + /* spr_mach_ops */ + status = nfsd4_encode_state_protect_ops4(xdr, exid); break; default: - WARN_ON_ONCE(1); + status = nfserr_serverfault; } + return status; +} - p = xdr_reserve_space(xdr, - 8 /* so_minor_id */ + - 4 /* so_major_id.len */ + - (XDR_QUADLEN(major_id_sz) * 4) + - 4 /* eir_server_scope.len */ + - (XDR_QUADLEN(server_scope_sz) * 4) + - 4 /* eir_server_impl_id.count (0) */); - if (!p) - return nfserr_resource; +static __be32 +nfsd4_encode_server_owner4(struct xdr_stream *xdr, struct svc_rqst *rqstp) +{ + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); + __be32 status; - /* The server_owner struct */ - p = xdr_encode_hyper(p, minor_id); /* Minor id */ - /* major id */ - p = xdr_encode_opaque(p, major_id, major_id_sz); + /* so_minor_id */ + status = nfsd4_encode_uint64_t(xdr, 0); + if (status != nfs_ok) + return status; + /* so_major_id */ + return nfsd4_encode_opaque(xdr, nn->nfsd_name, strlen(nn->nfsd_name)); +} - /* Server scope */ - p = xdr_encode_opaque(p, server_scope, server_scope_sz); +static __be32 +nfsd4_encode_nfs_impl_id4(struct xdr_stream *xdr, struct nfsd4_exchange_id *exid) +{ + __be32 status; - /* Implementation id */ - *p++ = cpu_to_be32(0); /* zero length nfs_impl_id4 array */ - return 0; + /* nii_domain */ + status = nfsd4_encode_opaque(xdr, exid->nii_domain.data, + exid->nii_domain.len); + if (status != nfs_ok) + return status; + /* nii_name */ + status = nfsd4_encode_opaque(xdr, exid->nii_name.data, + exid->nii_name.len); + if (status != nfs_ok) + return status; + /* nii_time */ + return nfsd4_encode_nfstime4(xdr, &exid->nii_time); } static __be32 -nfsd4_encode_create_session(struct nfsd4_compoundres *resp, __be32 nfserr, - union nfsd4_op_u *u) +nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { - struct nfsd4_create_session *sess = &u->create_session; + struct nfsd_net *nn = net_generic(SVC_NET(resp->rqstp), nfsd_net_id); + struct nfsd4_exchange_id *exid = &u->exchange_id; struct xdr_stream *xdr = resp->xdr; - __be32 *p; - p = xdr_reserve_space(xdr, 24); - if (!p) + /* eir_clientid */ + nfserr = nfsd4_encode_clientid4(xdr, &exid->clientid); + if (nfserr != nfs_ok) + return nfserr; + /* eir_sequenceid */ + nfserr = nfsd4_encode_sequenceid4(xdr, exid->seqid); + if (nfserr != nfs_ok) + return nfserr; + /* eir_flags */ + nfserr = nfsd4_encode_uint32_t(xdr, exid->flags); + if (nfserr != nfs_ok) + return nfserr; + /* eir_state_protect */ + nfserr = nfsd4_encode_state_protect4_r(xdr, exid); + if (nfserr != nfs_ok) + return nfserr; + /* eir_server_owner */ + nfserr = nfsd4_encode_server_owner4(xdr, resp->rqstp); + if (nfserr != nfs_ok) + return nfserr; + /* eir_server_scope */ + nfserr = nfsd4_encode_opaque(xdr, nn->nfsd_name, + strlen(nn->nfsd_name)); + if (nfserr != nfs_ok) + return nfserr; + /* eir_server_impl_id<1> */ + if (xdr_stream_encode_u32(xdr, 1) != XDR_UNIT) return nfserr_resource; - p = xdr_encode_opaque_fixed(p, sess->sessionid.data, - NFS4_MAX_SESSIONID_LEN); - *p++ = cpu_to_be32(sess->seqid); - *p++ = cpu_to_be32(sess->flags); + nfserr = nfsd4_encode_nfs_impl_id4(xdr, exid); + if (nfserr != nfs_ok) + return nfserr; - p = xdr_reserve_space(xdr, 28); - if (!p) - return nfserr_resource; - *p++ = cpu_to_be32(0); /* headerpadsz */ - *p++ = cpu_to_be32(sess->fore_channel.maxreq_sz); - *p++ = cpu_to_be32(sess->fore_channel.maxresp_sz); - *p++ = cpu_to_be32(sess->fore_channel.maxresp_cached); - *p++ = cpu_to_be32(sess->fore_channel.maxops); - *p++ = cpu_to_be32(sess->fore_channel.maxreqs); - *p++ = cpu_to_be32(sess->fore_channel.nr_rdma_attrs); - - if (sess->fore_channel.nr_rdma_attrs) { - p = xdr_reserve_space(xdr, 4); - if (!p) - return nfserr_resource; - *p++ = cpu_to_be32(sess->fore_channel.rdma_attrs); - } + return nfs_ok; +} - p = xdr_reserve_space(xdr, 28); - if (!p) +static __be32 +nfsd4_encode_channel_attrs4(struct xdr_stream *xdr, + const struct nfsd4_channel_attrs *attrs) +{ + __be32 status; + + /* ca_headerpadsize */ + status = nfsd4_encode_count4(xdr, 0); + if (status != nfs_ok) + return status; + /* ca_maxrequestsize */ + status = nfsd4_encode_count4(xdr, attrs->maxreq_sz); + if (status != nfs_ok) + return status; + /* ca_maxresponsesize */ + status = nfsd4_encode_count4(xdr, attrs->maxresp_sz); + if (status != nfs_ok) + return status; + /* ca_maxresponsesize_cached */ + status = nfsd4_encode_count4(xdr, attrs->maxresp_cached); + if (status != nfs_ok) + return status; + /* ca_maxoperations */ + status = nfsd4_encode_count4(xdr, attrs->maxops); + if (status != nfs_ok) + return status; + /* ca_maxrequests */ + status = nfsd4_encode_count4(xdr, attrs->maxreqs); + if (status != nfs_ok) + return status; + /* ca_rdma_ird<1> */ + if (xdr_stream_encode_u32(xdr, attrs->nr_rdma_attrs) != XDR_UNIT) return nfserr_resource; - *p++ = cpu_to_be32(0); /* headerpadsz */ - *p++ = cpu_to_be32(sess->back_channel.maxreq_sz); - *p++ = cpu_to_be32(sess->back_channel.maxresp_sz); - *p++ = cpu_to_be32(sess->back_channel.maxresp_cached); - *p++ = cpu_to_be32(sess->back_channel.maxops); - *p++ = cpu_to_be32(sess->back_channel.maxreqs); - *p++ = cpu_to_be32(sess->back_channel.nr_rdma_attrs); - - if (sess->back_channel.nr_rdma_attrs) { - p = xdr_reserve_space(xdr, 4); - if (!p) - return nfserr_resource; - *p++ = cpu_to_be32(sess->back_channel.rdma_attrs); - } - return 0; + if (attrs->nr_rdma_attrs) + return nfsd4_encode_uint32_t(xdr, attrs->rdma_attrs); + return nfs_ok; +} + +static __be32 +nfsd4_encode_create_session(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) +{ + struct nfsd4_create_session *sess = &u->create_session; + struct xdr_stream *xdr = resp->xdr; + + /* csr_sessionid */ + nfserr = nfsd4_encode_sessionid4(xdr, &sess->sessionid); + if (nfserr != nfs_ok) + return nfserr; + /* csr_sequence */ + nfserr = nfsd4_encode_sequenceid4(xdr, sess->seqid); + if (nfserr != nfs_ok) + return nfserr; + /* csr_flags */ + nfserr = nfsd4_encode_uint32_t(xdr, sess->flags); + if (nfserr != nfs_ok) + return nfserr; + /* csr_fore_chan_attrs */ + nfserr = nfsd4_encode_channel_attrs4(xdr, &sess->fore_channel); + if (nfserr != nfs_ok) + return nfserr; + /* csr_back_chan_attrs */ + return nfsd4_encode_channel_attrs4(xdr, &sess->back_channel); } static __be32 @@ -4622,22 +5070,35 @@ nfsd4_encode_sequence(struct nfsd4_compoundres *resp, __be32 nfserr, { struct nfsd4_sequence *seq = &u->sequence; struct xdr_stream *xdr = resp->xdr; - __be32 *p; - p = xdr_reserve_space(xdr, NFS4_MAX_SESSIONID_LEN + 20); - if (!p) - return nfserr_resource; - p = xdr_encode_opaque_fixed(p, seq->sessionid.data, - NFS4_MAX_SESSIONID_LEN); - *p++ = cpu_to_be32(seq->seqid); - *p++ = cpu_to_be32(seq->slotid); + /* sr_sessionid */ + nfserr = nfsd4_encode_sessionid4(xdr, &seq->sessionid); + if (nfserr != nfs_ok) + return nfserr; + /* sr_sequenceid */ + nfserr = nfsd4_encode_sequenceid4(xdr, seq->seqid); + if (nfserr != nfs_ok) + return nfserr; + /* sr_slotid */ + nfserr = nfsd4_encode_slotid4(xdr, seq->slotid); + if (nfserr != nfs_ok) + return nfserr; /* Note slotid's are numbered from zero: */ - *p++ = cpu_to_be32(seq->maxslots - 1); /* sr_highest_slotid */ - *p++ = cpu_to_be32(seq->maxslots - 1); /* sr_target_highest_slotid */ - *p++ = cpu_to_be32(seq->status_flags); + /* sr_highest_slotid */ + nfserr = nfsd4_encode_slotid4(xdr, seq->maxslots_response - 1); + if (nfserr != nfs_ok) + return nfserr; + /* sr_target_highest_slotid */ + nfserr = nfsd4_encode_slotid4(xdr, seq->target_maxslots - 1); + if (nfserr != nfs_ok) + return nfserr; + /* sr_status_flags */ + nfserr = nfsd4_encode_uint32_t(xdr, seq->status_flags); + if (nfserr != nfs_ok) + return nfserr; resp->cstate.data_offset = xdr->buf->len; /* DRC cache data pointer */ - return 0; + return nfs_ok; } static __be32 @@ -4645,128 +5106,175 @@ nfsd4_encode_test_stateid(struct nfsd4_compoundres *resp, __be32 nfserr, union nfsd4_op_u *u) { struct nfsd4_test_stateid *test_stateid = &u->test_stateid; - struct xdr_stream *xdr = resp->xdr; struct nfsd4_test_stateid_id *stateid, *next; - __be32 *p; + struct xdr_stream *xdr = resp->xdr; - p = xdr_reserve_space(xdr, 4 + (4 * test_stateid->ts_num_ids)); - if (!p) + /* tsr_status_codes<> */ + if (xdr_stream_encode_u32(xdr, test_stateid->ts_num_ids) != XDR_UNIT) return nfserr_resource; - *p++ = htonl(test_stateid->ts_num_ids); - - list_for_each_entry_safe(stateid, next, &test_stateid->ts_stateid_list, ts_id_list) { - *p++ = stateid->ts_id_status; + list_for_each_entry_safe(stateid, next, + &test_stateid->ts_stateid_list, ts_id_list) { + if (xdr_stream_encode_be32(xdr, stateid->ts_id_status) != XDR_UNIT) + return nfserr_resource; } + return nfs_ok; +} - return 0; +static __be32 +nfsd4_encode_get_dir_delegation(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) +{ + struct nfsd4_get_dir_delegation *gdd = &u->get_dir_delegation; + struct xdr_stream *xdr = resp->xdr; + __be32 status = nfserr_resource; + + switch(gdd->gddrnf_status) { + case GDD4_OK: + if (xdr_stream_encode_u32(xdr, GDD4_OK) != XDR_UNIT) + break; + status = nfsd4_encode_verifier4(xdr, &gdd->gddr_cookieverf); + if (status) + break; + status = nfsd4_encode_stateid4(xdr, &gdd->gddr_stateid); + if (status) + break; + status = nfsd4_encode_bitmap4(xdr, gdd->gddr_notification[0], 0, 0); + if (status) + break; + status = nfsd4_encode_bitmap4(xdr, gdd->gddr_child_attributes[0], + gdd->gddr_child_attributes[1], + gdd->gddr_child_attributes[2]); + if (status) + break; + status = nfsd4_encode_bitmap4(xdr, gdd->gddr_dir_attributes[0], + gdd->gddr_dir_attributes[1], + gdd->gddr_dir_attributes[2]); + break; + default: + pr_warn("nfsd: bad gddrnf_status (%u)\n", gdd->gddrnf_status); + gdd->gddrnf_will_signal_deleg_avail = 0; + fallthrough; + case GDD4_UNAVAIL: + if (xdr_stream_encode_u32(xdr, GDD4_UNAVAIL) != XDR_UNIT) + break; + status = nfsd4_encode_bool(xdr, gdd->gddrnf_will_signal_deleg_avail); + break; + } + return status; } #ifdef CONFIG_NFSD_PNFS static __be32 -nfsd4_encode_getdeviceinfo(struct nfsd4_compoundres *resp, __be32 nfserr, - union nfsd4_op_u *u) +nfsd4_encode_device_addr4(struct xdr_stream *xdr, + const struct nfsd4_getdeviceinfo *gdev) { - struct nfsd4_getdeviceinfo *gdev = &u->getdeviceinfo; - struct xdr_stream *xdr = resp->xdr; + u32 needed_len, starting_len = xdr->buf->len; const struct nfsd4_layout_ops *ops; - u32 starting_len = xdr->buf->len, needed_len; - __be32 *p; + __be32 status; - p = xdr_reserve_space(xdr, 4); - if (!p) + /* da_layout_type */ + if (xdr_stream_encode_u32(xdr, gdev->gd_layout_type) != XDR_UNIT) return nfserr_resource; - - *p++ = cpu_to_be32(gdev->gd_layout_type); - - /* If maxcount is 0 then just update notifications */ - if (gdev->gd_maxcount != 0) { - ops = nfsd4_layout_ops[gdev->gd_layout_type]; - nfserr = ops->encode_getdeviceinfo(xdr, gdev); - if (nfserr) { - /* - * We don't bother to burden the layout drivers with - * enforcing gd_maxcount, just tell the client to - * come back with a bigger buffer if it's not enough. - */ - if (xdr->buf->len + 4 > gdev->gd_maxcount) - goto toosmall; - return nfserr; - } + /* da_addr_body */ + ops = nfsd4_layout_ops[gdev->gd_layout_type]; + status = ops->encode_getdeviceinfo(xdr, gdev); + if (status != nfs_ok) { + /* + * Don't burden the layout drivers with enforcing + * gd_maxcount. Just tell the client to come back + * with a bigger buffer if it's not enough. + */ + if (xdr->buf->len + XDR_UNIT > gdev->gd_maxcount) + goto toosmall; + return status; } - if (gdev->gd_notify_types) { - p = xdr_reserve_space(xdr, 4 + 4); - if (!p) - return nfserr_resource; - *p++ = cpu_to_be32(1); /* bitmap length */ - *p++ = cpu_to_be32(gdev->gd_notify_types); - } else { - p = xdr_reserve_space(xdr, 4); - if (!p) - return nfserr_resource; - *p++ = 0; - } + return nfs_ok; - return 0; toosmall: - dprintk("%s: maxcount too small\n", __func__); - needed_len = xdr->buf->len + 4 /* notifications */; + needed_len = xdr->buf->len + XDR_UNIT; /* notifications */ xdr_truncate_encode(xdr, starting_len); - p = xdr_reserve_space(xdr, 4); - if (!p) - return nfserr_resource; - *p++ = cpu_to_be32(needed_len); + + status = nfsd4_encode_count4(xdr, needed_len); + if (status != nfs_ok) + return status; return nfserr_toosmall; } static __be32 -nfsd4_encode_layoutget(struct nfsd4_compoundres *resp, __be32 nfserr, +nfsd4_encode_getdeviceinfo(struct nfsd4_compoundres *resp, __be32 nfserr, union nfsd4_op_u *u) { - struct nfsd4_layoutget *lgp = &u->layoutget; + struct nfsd4_getdeviceinfo *gdev = &u->getdeviceinfo; struct xdr_stream *xdr = resp->xdr; - const struct nfsd4_layout_ops *ops; - __be32 *p; - p = xdr_reserve_space(xdr, 36 + sizeof(stateid_opaque_t)); - if (!p) - return nfserr_resource; - - *p++ = cpu_to_be32(1); /* we always set return-on-close */ - *p++ = cpu_to_be32(lgp->lg_sid.si_generation); - p = xdr_encode_opaque_fixed(p, &lgp->lg_sid.si_opaque, - sizeof(stateid_opaque_t)); + /* gdir_device_addr */ + nfserr = nfsd4_encode_device_addr4(xdr, gdev); + if (nfserr) + return nfserr; + /* gdir_notification */ + return nfsd4_encode_bitmap4(xdr, gdev->gd_notify_types, 0, 0); +} - *p++ = cpu_to_be32(1); /* we always return a single layout */ - p = xdr_encode_hyper(p, lgp->lg_seg.offset); - p = xdr_encode_hyper(p, lgp->lg_seg.length); - *p++ = cpu_to_be32(lgp->lg_seg.iomode); - *p++ = cpu_to_be32(lgp->lg_layout_type); +static __be32 +nfsd4_encode_layout4(struct xdr_stream *xdr, const struct nfsd4_layoutget *lgp) +{ + const struct nfsd4_layout_ops *ops = nfsd4_layout_ops[lgp->lg_layout_type]; + __be32 status; - ops = nfsd4_layout_ops[lgp->lg_layout_type]; + /* lo_offset */ + status = nfsd4_encode_offset4(xdr, lgp->lg_seg.offset); + if (status != nfs_ok) + return status; + /* lo_length */ + status = nfsd4_encode_length4(xdr, lgp->lg_seg.length); + if (status != nfs_ok) + return status; + /* lo_iomode */ + if (xdr_stream_encode_u32(xdr, lgp->lg_seg.iomode) != XDR_UNIT) + return nfserr_resource; + /* lo_content */ + if (xdr_stream_encode_u32(xdr, lgp->lg_layout_type) != XDR_UNIT) + return nfserr_resource; return ops->encode_layoutget(xdr, lgp); } static __be32 +nfsd4_encode_layoutget(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) +{ + struct nfsd4_layoutget *lgp = &u->layoutget; + struct xdr_stream *xdr = resp->xdr; + + /* logr_return_on_close */ + nfserr = nfsd4_encode_bool(xdr, true); + if (nfserr != nfs_ok) + return nfserr; + /* logr_stateid */ + nfserr = nfsd4_encode_stateid4(xdr, &lgp->lg_sid); + if (nfserr != nfs_ok) + return nfserr; + /* logr_layout<> */ + if (xdr_stream_encode_u32(xdr, 1) != XDR_UNIT) + return nfserr_resource; + return nfsd4_encode_layout4(xdr, lgp); +} + +static __be32 nfsd4_encode_layoutcommit(struct nfsd4_compoundres *resp, __be32 nfserr, union nfsd4_op_u *u) { struct nfsd4_layoutcommit *lcp = &u->layoutcommit; struct xdr_stream *xdr = resp->xdr; - __be32 *p; - - p = xdr_reserve_space(xdr, 4); - if (!p) - return nfserr_resource; - *p++ = cpu_to_be32(lcp->lc_size_chg); - if (lcp->lc_size_chg) { - p = xdr_reserve_space(xdr, 8); - if (!p) - return nfserr_resource; - p = xdr_encode_hyper(p, lcp->lc_newsize); - } - return 0; + /* ns_sizechanged */ + nfserr = nfsd4_encode_bool(xdr, lcp->lc_size_chg); + if (nfserr != nfs_ok) + return nfserr; + if (lcp->lc_size_chg) + /* ns_size */ + return nfsd4_encode_length4(xdr, lcp->lc_newsize); + return nfs_ok; } static __be32 @@ -4775,103 +5283,108 @@ nfsd4_encode_layoutreturn(struct nfsd4_compoundres *resp, __be32 nfserr, { struct nfsd4_layoutreturn *lrp = &u->layoutreturn; struct xdr_stream *xdr = resp->xdr; - __be32 *p; - p = xdr_reserve_space(xdr, 4); - if (!p) - return nfserr_resource; - *p++ = cpu_to_be32(lrp->lrs_present); + /* lrs_present */ + nfserr = nfsd4_encode_bool(xdr, lrp->lrs_present); + if (nfserr != nfs_ok) + return nfserr; if (lrp->lrs_present) - return nfsd4_encode_stateid(xdr, &lrp->lr_sid); - return 0; + /* lrs_stateid */ + return nfsd4_encode_stateid4(xdr, &lrp->lr_sid); + return nfs_ok; } #endif /* CONFIG_NFSD_PNFS */ static __be32 -nfsd42_encode_write_res(struct nfsd4_compoundres *resp, - struct nfsd42_write_res *write, bool sync) +nfsd4_encode_write_response4(struct xdr_stream *xdr, + const struct nfsd4_copy *copy) { - __be32 *p; - p = xdr_reserve_space(resp->xdr, 4); - if (!p) - return nfserr_resource; + const struct nfsd42_write_res *write = ©->cp_res; + u32 count = nfsd4_copy_is_sync(copy) ? 0 : 1; + __be32 status; - if (sync) - *p++ = cpu_to_be32(0); - else { - __be32 nfserr; - *p++ = cpu_to_be32(1); - nfserr = nfsd4_encode_stateid(resp->xdr, &write->cb_stateid); - if (nfserr) - return nfserr; + /* wr_callback_id<1> */ + if (xdr_stream_encode_u32(xdr, count) != XDR_UNIT) + return nfserr_resource; + if (count) { + status = nfsd4_encode_stateid4(xdr, &write->cb_stateid); + if (status != nfs_ok) + return status; } - p = xdr_reserve_space(resp->xdr, 8 + 4 + NFS4_VERIFIER_SIZE); - if (!p) + + /* wr_count */ + status = nfsd4_encode_length4(xdr, write->wr_bytes_written); + if (status != nfs_ok) + return status; + /* wr_committed */ + if (xdr_stream_encode_u32(xdr, write->wr_stable_how) != XDR_UNIT) return nfserr_resource; + /* wr_writeverf */ + return nfsd4_encode_verifier4(xdr, &write->wr_verifier); +} - p = xdr_encode_hyper(p, write->wr_bytes_written); - *p++ = cpu_to_be32(write->wr_stable_how); - p = xdr_encode_opaque_fixed(p, write->wr_verifier.data, - NFS4_VERIFIER_SIZE); - return nfs_ok; +static __be32 nfsd4_encode_copy_requirements4(struct xdr_stream *xdr, + const struct nfsd4_copy *copy) +{ + __be32 status; + + /* cr_consecutive */ + status = nfsd4_encode_bool(xdr, true); + if (status != nfs_ok) + return status; + /* cr_synchronous */ + return nfsd4_encode_bool(xdr, nfsd4_copy_is_sync(copy)); } static __be32 -nfsd42_encode_nl4_server(struct nfsd4_compoundres *resp, struct nl4_server *ns) +nfsd4_encode_copy(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { - struct xdr_stream *xdr = resp->xdr; - struct nfs42_netaddr *addr; - __be32 *p; + struct nfsd4_copy *copy = &u->copy; - p = xdr_reserve_space(xdr, 4); - *p++ = cpu_to_be32(ns->nl4_type); + nfserr = nfsd4_encode_write_response4(resp->xdr, copy); + if (nfserr != nfs_ok) + return nfserr; + return nfsd4_encode_copy_requirements4(resp->xdr, copy); +} + +static __be32 +nfsd4_encode_netloc4(struct xdr_stream *xdr, const struct nl4_server *ns) +{ + __be32 status; + if (xdr_stream_encode_u32(xdr, ns->nl4_type) != XDR_UNIT) + return nfserr_resource; switch (ns->nl4_type) { case NL4_NETADDR: - addr = &ns->u.nl4_addr; - - /* netid_len, netid, uaddr_len, uaddr (port included - * in RPCBIND_MAXUADDRLEN) - */ - p = xdr_reserve_space(xdr, - 4 /* netid len */ + - (XDR_QUADLEN(addr->netid_len) * 4) + - 4 /* uaddr len */ + - (XDR_QUADLEN(addr->addr_len) * 4)); - if (!p) - return nfserr_resource; - - *p++ = cpu_to_be32(addr->netid_len); - p = xdr_encode_opaque_fixed(p, addr->netid, - addr->netid_len); - *p++ = cpu_to_be32(addr->addr_len); - p = xdr_encode_opaque_fixed(p, addr->addr, - addr->addr_len); + /* nl_addr */ + status = nfsd4_encode_netaddr4(xdr, &ns->u.nl4_addr); break; default: - WARN_ON_ONCE(ns->nl4_type != NL4_NETADDR); - return nfserr_inval; + status = nfserr_serverfault; } - - return 0; + return status; } static __be32 -nfsd4_encode_copy(struct nfsd4_compoundres *resp, __be32 nfserr, - union nfsd4_op_u *u) +nfsd4_encode_copy_notify(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { - struct nfsd4_copy *copy = &u->copy; - __be32 *p; + struct nfsd4_copy_notify *cn = &u->copy_notify; + struct xdr_stream *xdr = resp->xdr; - nfserr = nfsd42_encode_write_res(resp, ©->cp_res, - nfsd4_copy_is_sync(copy)); + /* cnr_lease_time */ + nfserr = nfsd4_encode_nfstime4(xdr, &cn->cpn_lease_time); if (nfserr) return nfserr; - - p = xdr_reserve_space(resp->xdr, 4 + 4); - *p++ = xdr_one; /* cr_consecutive */ - *p = nfsd4_copy_is_sync(copy) ? xdr_one : xdr_zero; - return 0; + /* cnr_stateid */ + nfserr = nfsd4_encode_stateid4(xdr, &cn->cpn_cnr_stateid); + if (nfserr) + return nfserr; + /* cnr_source_server<> */ + if (xdr_stream_encode_u32(xdr, 1) != XDR_UNIT) + return nfserr_resource; + return nfsd4_encode_netloc4(xdr, cn->cpn_src); } static __be32 @@ -4880,34 +5393,44 @@ nfsd4_encode_offload_status(struct nfsd4_compoundres *resp, __be32 nfserr, { struct nfsd4_offload_status *os = &u->offload_status; struct xdr_stream *xdr = resp->xdr; - __be32 *p; - p = xdr_reserve_space(xdr, 8 + 4); - if (!p) + /* osr_count */ + nfserr = nfsd4_encode_length4(xdr, os->count); + if (nfserr != nfs_ok) + return nfserr; + /* osr_complete<1> */ + if (os->completed) { + if (xdr_stream_encode_u32(xdr, 1) != XDR_UNIT) + return nfserr_resource; + if (xdr_stream_encode_be32(xdr, os->status) != XDR_UNIT) + return nfserr_resource; + } else if (xdr_stream_encode_u32(xdr, 0) != XDR_UNIT) return nfserr_resource; - p = xdr_encode_hyper(p, os->count); - *p++ = cpu_to_be32(0); - return nfserr; + return nfs_ok; } static __be32 nfsd4_encode_read_plus_data(struct nfsd4_compoundres *resp, struct nfsd4_read *read) { - bool splice_ok = test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags); + struct nfsd4_compoundargs *argp = resp->rqstp->rq_argp; struct file *file = read->rd_nf->nf_file; struct xdr_stream *xdr = resp->xdr; + bool splice_ok = argp->splice_ok; + unsigned int offset_offset; + __be32 nfserr, wire_count; unsigned long maxcount; - __be32 nfserr, *p; + __be64 wire_offset; - /* Content type, offset, byte count */ - p = xdr_reserve_space(xdr, 4 + 8 + 4); - if (!p) + if (xdr_stream_encode_u32(xdr, NFS4_CONTENT_DATA) != XDR_UNIT) return nfserr_io; - if (resp->xdr->buf->page_len && splice_ok) { - WARN_ON_ONCE(splice_ok); - return nfserr_serverfault; - } + + offset_offset = xdr->buf->len; + + /* Reserve space for the byte offset and count */ + if (unlikely(!xdr_reserve_space(xdr, XDR_UNIT * 3))) + return nfserr_io; + xdr_commit_encode(xdr); maxcount = min_t(unsigned long, read->rd_length, (xdr->buf->buflen - xdr->buf->len)); @@ -4915,14 +5438,16 @@ nfsd4_encode_read_plus_data(struct nfsd4_compoundres *resp, if (file->f_op->splice_read && splice_ok) nfserr = nfsd4_encode_splice_read(resp, read, file, maxcount); else - nfserr = nfsd4_encode_readv(resp, read, file, maxcount); + nfserr = nfsd4_encode_readv(resp, read, maxcount); if (nfserr) return nfserr; - *p++ = cpu_to_be32(NFS4_CONTENT_DATA); - p = xdr_encode_hyper(p, read->rd_offset); - *p = cpu_to_be32(read->rd_length); - + wire_offset = cpu_to_be64(read->rd_offset); + write_bytes_to_xdr_buf(xdr->buf, offset_offset, &wire_offset, + XDR_UNIT * 2); + wire_count = cpu_to_be32(read->rd_length); + write_bytes_to_xdr_buf(xdr->buf, offset_offset + XDR_UNIT * 2, + &wire_count, XDR_UNIT); return nfs_ok; } @@ -4933,16 +5458,17 @@ nfsd4_encode_read_plus(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_read *read = &u->read; struct file *file = read->rd_nf->nf_file; struct xdr_stream *xdr = resp->xdr; - int starting_len = xdr->buf->len; + unsigned int eof_offset; + __be32 wire_data[2]; u32 segments = 0; - __be32 *p; if (nfserr) return nfserr; - /* eof flag, segment count */ - p = xdr_reserve_space(xdr, 4 + 4); - if (!p) + eof_offset = xdr->buf->len; + + /* Reserve space for the eof flag and segment count */ + if (unlikely(!xdr_reserve_space(xdr, XDR_UNIT * 2))) return nfserr_io; xdr_commit_encode(xdr); @@ -4952,51 +5478,16 @@ nfsd4_encode_read_plus(struct nfsd4_compoundres *resp, __be32 nfserr, nfserr = nfsd4_encode_read_plus_data(resp, read); if (nfserr) { - xdr_truncate_encode(xdr, starting_len); + xdr_truncate_encode(xdr, eof_offset); return nfserr; } segments++; out: - p = xdr_encode_bool(p, read->rd_eof); - *p = cpu_to_be32(segments); - return nfserr; -} - -static __be32 -nfsd4_encode_copy_notify(struct nfsd4_compoundres *resp, __be32 nfserr, - union nfsd4_op_u *u) -{ - struct nfsd4_copy_notify *cn = &u->copy_notify; - struct xdr_stream *xdr = resp->xdr; - __be32 *p; - - if (nfserr) - return nfserr; - - /* 8 sec, 4 nsec */ - p = xdr_reserve_space(xdr, 12); - if (!p) - return nfserr_resource; - - /* cnr_lease_time */ - p = xdr_encode_hyper(p, cn->cpn_sec); - *p++ = cpu_to_be32(cn->cpn_nsec); - - /* cnr_stateid */ - nfserr = nfsd4_encode_stateid(xdr, &cn->cpn_cnr_stateid); - if (nfserr) - return nfserr; - - /* cnr_src.nl_nsvr */ - p = xdr_reserve_space(xdr, 4); - if (!p) - return nfserr_resource; - - *p++ = cpu_to_be32(1); - - nfserr = nfsd42_encode_nl4_server(resp, cn->cpn_src); + wire_data[0] = read->rd_eof ? xdr_one : xdr_zero; + wire_data[1] = cpu_to_be32(segments); + write_bytes_to_xdr_buf(xdr->buf, eof_offset, &wire_data, XDR_UNIT * 2); return nfserr; } @@ -5005,13 +5496,14 @@ nfsd4_encode_seek(struct nfsd4_compoundres *resp, __be32 nfserr, union nfsd4_op_u *u) { struct nfsd4_seek *seek = &u->seek; - __be32 *p; - - p = xdr_reserve_space(resp->xdr, 4 + 8); - *p++ = cpu_to_be32(seek->seek_eof); - p = xdr_encode_hyper(p, seek->seek_pos); + struct xdr_stream *xdr = resp->xdr; - return 0; + /* sr_eof */ + nfserr = nfsd4_encode_bool(xdr, seek->seek_eof); + if (nfserr != nfs_ok) + return nfserr; + /* sr_offset */ + return nfsd4_encode_offset4(xdr, seek->seek_pos); } static __be32 @@ -5096,15 +5588,8 @@ nfsd4_encode_setxattr(struct nfsd4_compoundres *resp, __be32 nfserr, { struct nfsd4_setxattr *setxattr = &u->setxattr; struct xdr_stream *xdr = resp->xdr; - __be32 *p; - - p = xdr_reserve_space(xdr, 20); - if (!p) - return nfserr_resource; - - encode_cinfo(p, &setxattr->setxa_cinfo); - return 0; + return nfsd4_encode_change_info4(xdr, &setxattr->setxa_cinfo); } /* @@ -5118,16 +5603,11 @@ nfsd4_listxattr_validate_cookie(struct nfsd4_listxattrs *listxattrs, /* * If the cookie is larger than the maximum number we can fit - * in either the buffer we just got back from vfs_listxattr, or, - * XDR-encoded, in the return buffer, it's invalid. + * in the buffer we just got back from vfs_listxattr, it's invalid. */ if (cookie > (listxattrs->lsxa_len) / (XATTR_USER_PREFIX_LEN + 2)) return nfserr_badcookie; - if (cookie > (listxattrs->lsxa_maxcount / - (XDR_QUADLEN(XATTR_USER_PREFIX_LEN + 2) + 4))) - return nfserr_badcookie; - *offsetp = (u32)cookie; return 0; } @@ -5144,6 +5624,7 @@ nfsd4_encode_listxattrs(struct nfsd4_compoundres *resp, __be32 nfserr, u64 cookie; char *sp; __be32 status, tmp; + __be64 wire_cookie; __be32 *p; u32 nuser; @@ -5159,7 +5640,7 @@ nfsd4_encode_listxattrs(struct nfsd4_compoundres *resp, __be32 nfserr, */ cookie_offset = xdr->buf->len; count_offset = cookie_offset + 8; - p = xdr_reserve_space(xdr, 12); + p = xdr_reserve_space(xdr, XDR_UNIT * 3); if (!p) { status = nfserr_resource; goto out; @@ -5170,7 +5651,8 @@ nfsd4_encode_listxattrs(struct nfsd4_compoundres *resp, __be32 nfserr, sp = listxattrs->lsxa_buf; nuser = 0; - xdrleft = listxattrs->lsxa_maxcount; + /* Bytes left is maxcount - 8 (cookie) - 4 (array count) */ + xdrleft = listxattrs->lsxa_maxcount - XDR_UNIT * 3; while (left > 0 && xdrleft > 0) { slen = strlen(sp); @@ -5183,7 +5665,8 @@ nfsd4_encode_listxattrs(struct nfsd4_compoundres *resp, __be32 nfserr, slen -= XATTR_USER_PREFIX_LEN; xdrlen = 4 + ((slen + 3) & ~3); - if (xdrlen > xdrleft) { + /* Check if both entry and eof can fit in the XDR buffer */ + if (xdrlen + XDR_UNIT > xdrleft) { if (count == 0) { /* * Can't even fit the first attribute name. @@ -5235,7 +5718,8 @@ wreof: cookie = offset + count; - write_bytes_to_xdr_buf(xdr->buf, cookie_offset, &cookie, 8); + wire_cookie = cpu_to_be64(cookie); + write_bytes_to_xdr_buf(xdr->buf, cookie_offset, &wire_cookie, 8); tmp = cpu_to_be32(count); write_bytes_to_xdr_buf(xdr->buf, count_offset, &tmp, 4); out: @@ -5250,14 +5734,8 @@ nfsd4_encode_removexattr(struct nfsd4_compoundres *resp, __be32 nfserr, { struct nfsd4_removexattr *removexattr = &u->removexattr; struct xdr_stream *xdr = resp->xdr; - __be32 *p; - - p = xdr_reserve_space(xdr, 20); - if (!p) - return nfserr_resource; - p = encode_cinfo(p, &removexattr->rmxa_cinfo); - return 0; + return nfsd4_encode_change_info4(xdr, &removexattr->rmxa_cinfo); } typedef __be32(*nfsd4_enc)(struct nfsd4_compoundres *, __be32, union nfsd4_op_u *u); @@ -5313,7 +5791,7 @@ static const nfsd4_enc nfsd4_enc_ops[] = { [OP_CREATE_SESSION] = nfsd4_encode_create_session, [OP_DESTROY_SESSION] = nfsd4_encode_noop, [OP_FREE_STATEID] = nfsd4_encode_noop, - [OP_GET_DIR_DELEGATION] = nfsd4_encode_noop, + [OP_GET_DIR_DELEGATION] = nfsd4_encode_get_dir_delegation, #ifdef CONFIG_NFSD_PNFS [OP_GETDEVICEINFO] = nfsd4_encode_getdeviceinfo, [OP_GETDEVICELIST] = nfsd4_encode_noop, @@ -5386,6 +5864,23 @@ __be32 nfsd4_check_resp_size(struct nfsd4_compoundres *resp, u32 respsize) return nfserr_rep_too_big; } +static __be32 nfsd4_map_status(__be32 status, u32 minor) +{ + switch (status) { + case nfs_ok: + break; + case nfserr_wrong_type: + /* RFC 8881 - 15.1.2.9 */ + if (minor == 0) + status = nfserr_inval; + break; + case nfserr_symlink_not_dir: + status = nfserr_symlink; + break; + } + return status; +} + void nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op) { @@ -5393,17 +5888,14 @@ nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op) struct nfs4_stateowner *so = resp->cstate.replay_owner; struct svc_rqst *rqstp = resp->rqstp; const struct nfsd4_operation *opdesc = op->opdesc; - int post_err_offset; + unsigned int op_status_offset; nfsd4_enc encoder; - __be32 *p; - p = xdr_reserve_space(xdr, 8); - if (!p) { - WARN_ON_ONCE(1); - return; - } - *p++ = cpu_to_be32(op->opnum); - post_err_offset = xdr->buf->len; + if (xdr_stream_encode_u32(xdr, op->opnum) != XDR_UNIT) + goto release; + op_status_offset = xdr->buf->len; + if (!xdr_reserve_space(xdr, XDR_UNIT)) + goto release; if (op->opnum == OP_ILLEGAL) goto status; @@ -5416,8 +5908,6 @@ nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op) op->status = encoder(resp, op->status, &op->u); if (op->status) trace_nfsd_compound_encode_err(rqstp, op->opnum, op->status); - if (opdesc && opdesc->op_release) - opdesc->op_release(&op->u); xdr_commit_encode(xdr); /* nfsd4_check_resp_size guarantees enough room for error status */ @@ -5446,41 +5936,49 @@ nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op) * bug if we had to do this on a non-idempotent op: */ warn_on_nonidempotent_op(op); - xdr_truncate_encode(xdr, post_err_offset); - } - if (so) { - int len = xdr->buf->len - post_err_offset; + xdr_truncate_encode(xdr, op_status_offset + XDR_UNIT); + } else if (so) { + int len = xdr->buf->len - (op_status_offset + XDR_UNIT); so->so_replay.rp_status = op->status; so->so_replay.rp_buflen = len; - read_bytes_from_xdr_buf(xdr->buf, post_err_offset, + read_bytes_from_xdr_buf(xdr->buf, op_status_offset + XDR_UNIT, so->so_replay.rp_buf, len); } status: - *p = op->status; + op->status = nfsd4_map_status(op->status, + resp->cstate.minorversion); + write_bytes_to_xdr_buf(xdr->buf, op_status_offset, + &op->status, XDR_UNIT); +release: + if (opdesc && opdesc->op_release) + opdesc->op_release(&op->u); + + /* + * Account for pages consumed while encoding this operation. + * The xdr_stream primitives don't manage rq_next_page. + */ + rqstp->rq_next_page = xdr->page_ptr + 1; } -/* - * Encode the reply stored in the stateowner reply cache - * - * XDR note: do not encode rp->rp_buflen: the buffer contains the - * previously sent already encoded operation. +/** + * nfsd4_encode_replay - encode a result stored in the stateowner reply cache + * @xdr: send buffer's XDR stream + * @op: operation being replayed + * + * @op->replay->rp_buf contains the previously-sent already-encoded result. */ -void -nfsd4_encode_replay(struct xdr_stream *xdr, struct nfsd4_op *op) +void nfsd4_encode_replay(struct xdr_stream *xdr, struct nfsd4_op *op) { - __be32 *p; struct nfs4_replay *rp = op->replay; - p = xdr_reserve_space(xdr, 8 + rp->rp_buflen); - if (!p) { - WARN_ON_ONCE(1); - return; - } - *p++ = cpu_to_be32(op->opnum); - *p++ = rp->rp_status; /* already xdr'ed */ + trace_nfsd_stateowner_replay(op->opnum, rp); - p = xdr_encode_opaque_fixed(p, rp->rp_buf, rp->rp_buflen); + if (xdr_stream_encode_u32(xdr, op->opnum) != XDR_UNIT) + return; + if (xdr_stream_encode_be32(xdr, rp->rp_status) != XDR_UNIT) + return; + xdr_stream_encode_opaque_fixed(xdr, rp->rp_buf, rp->rp_buflen); } void nfsd4_release_compoundargs(struct svc_rqst *rqstp) @@ -5526,9 +6024,6 @@ nfs4svc_encode_compoundres(struct svc_rqst *rqstp, struct xdr_stream *xdr) p = resp->statusp; *p++ = resp->cstate.status; - - rqstp->rq_next_page = xdr->page_ptr + 1; - *p++ = htonl(resp->taglen); memcpy(p, resp->tag, resp->taglen); p += XDR_QUADLEN(resp->taglen); diff --git a/fs/nfsd/nfs4xdr_gen.c b/fs/nfsd/nfs4xdr_gen.c new file mode 100644 index 000000000000..a17b5d8e60b3 --- /dev/null +++ b/fs/nfsd/nfs4xdr_gen.c @@ -0,0 +1,256 @@ +// SPDX-License-Identifier: GPL-2.0 +// Generated by xdrgen. Manual edits will be lost. +// XDR specification file: ../../Documentation/sunrpc/xdr/nfs4_1.x +// XDR specification modification time: Mon Oct 14 09:10:13 2024 + +#include <linux/sunrpc/svc.h> + +#include "nfs4xdr_gen.h" + +static bool __maybe_unused +xdrgen_decode_int64_t(struct xdr_stream *xdr, int64_t *ptr) +{ + return xdrgen_decode_hyper(xdr, ptr); +}; + +static bool __maybe_unused +xdrgen_decode_uint32_t(struct xdr_stream *xdr, uint32_t *ptr) +{ + return xdrgen_decode_unsigned_int(xdr, ptr); +}; + +static bool __maybe_unused +xdrgen_decode_bitmap4(struct xdr_stream *xdr, bitmap4 *ptr) +{ + if (xdr_stream_decode_u32(xdr, &ptr->count) < 0) + return false; + for (u32 i = 0; i < ptr->count; i++) + if (!xdrgen_decode_uint32_t(xdr, &ptr->element[i])) + return false; + return true; +}; + +static bool __maybe_unused +xdrgen_decode_nfstime4(struct xdr_stream *xdr, struct nfstime4 *ptr) +{ + if (!xdrgen_decode_int64_t(xdr, &ptr->seconds)) + return false; + if (!xdrgen_decode_uint32_t(xdr, &ptr->nseconds)) + return false; + return true; +}; + +static bool __maybe_unused +xdrgen_decode_fattr4_offline(struct xdr_stream *xdr, fattr4_offline *ptr) +{ + return xdrgen_decode_bool(xdr, ptr); +}; + +static bool __maybe_unused +xdrgen_decode_open_arguments4(struct xdr_stream *xdr, struct open_arguments4 *ptr) +{ + if (!xdrgen_decode_bitmap4(xdr, &ptr->oa_share_access)) + return false; + if (!xdrgen_decode_bitmap4(xdr, &ptr->oa_share_deny)) + return false; + if (!xdrgen_decode_bitmap4(xdr, &ptr->oa_share_access_want)) + return false; + if (!xdrgen_decode_bitmap4(xdr, &ptr->oa_open_claim)) + return false; + if (!xdrgen_decode_bitmap4(xdr, &ptr->oa_create_mode)) + return false; + return true; +}; + +static bool __maybe_unused +xdrgen_decode_open_args_share_access4(struct xdr_stream *xdr, open_args_share_access4 *ptr) +{ + u32 val; + + if (xdr_stream_decode_u32(xdr, &val) < 0) + return false; + *ptr = val; + return true; +} + +static bool __maybe_unused +xdrgen_decode_open_args_share_deny4(struct xdr_stream *xdr, open_args_share_deny4 *ptr) +{ + u32 val; + + if (xdr_stream_decode_u32(xdr, &val) < 0) + return false; + *ptr = val; + return true; +} + +static bool __maybe_unused +xdrgen_decode_open_args_share_access_want4(struct xdr_stream *xdr, open_args_share_access_want4 *ptr) +{ + u32 val; + + if (xdr_stream_decode_u32(xdr, &val) < 0) + return false; + *ptr = val; + return true; +} + +static bool __maybe_unused +xdrgen_decode_open_args_open_claim4(struct xdr_stream *xdr, open_args_open_claim4 *ptr) +{ + u32 val; + + if (xdr_stream_decode_u32(xdr, &val) < 0) + return false; + *ptr = val; + return true; +} + +static bool __maybe_unused +xdrgen_decode_open_args_createmode4(struct xdr_stream *xdr, open_args_createmode4 *ptr) +{ + u32 val; + + if (xdr_stream_decode_u32(xdr, &val) < 0) + return false; + *ptr = val; + return true; +} + +bool +xdrgen_decode_fattr4_open_arguments(struct xdr_stream *xdr, fattr4_open_arguments *ptr) +{ + return xdrgen_decode_open_arguments4(xdr, ptr); +}; + +bool +xdrgen_decode_fattr4_time_deleg_access(struct xdr_stream *xdr, fattr4_time_deleg_access *ptr) +{ + return xdrgen_decode_nfstime4(xdr, ptr); +}; + +bool +xdrgen_decode_fattr4_time_deleg_modify(struct xdr_stream *xdr, fattr4_time_deleg_modify *ptr) +{ + return xdrgen_decode_nfstime4(xdr, ptr); +}; + +static bool __maybe_unused +xdrgen_decode_open_delegation_type4(struct xdr_stream *xdr, open_delegation_type4 *ptr) +{ + u32 val; + + if (xdr_stream_decode_u32(xdr, &val) < 0) + return false; + *ptr = val; + return true; +} + +static bool __maybe_unused +xdrgen_encode_int64_t(struct xdr_stream *xdr, const int64_t value) +{ + return xdrgen_encode_hyper(xdr, value); +}; + +static bool __maybe_unused +xdrgen_encode_uint32_t(struct xdr_stream *xdr, const uint32_t value) +{ + return xdrgen_encode_unsigned_int(xdr, value); +}; + +static bool __maybe_unused +xdrgen_encode_bitmap4(struct xdr_stream *xdr, const bitmap4 value) +{ + if (xdr_stream_encode_u32(xdr, value.count) != XDR_UNIT) + return false; + for (u32 i = 0; i < value.count; i++) + if (!xdrgen_encode_uint32_t(xdr, value.element[i])) + return false; + return true; +}; + +static bool __maybe_unused +xdrgen_encode_nfstime4(struct xdr_stream *xdr, const struct nfstime4 *value) +{ + if (!xdrgen_encode_int64_t(xdr, value->seconds)) + return false; + if (!xdrgen_encode_uint32_t(xdr, value->nseconds)) + return false; + return true; +}; + +static bool __maybe_unused +xdrgen_encode_fattr4_offline(struct xdr_stream *xdr, const fattr4_offline value) +{ + return xdrgen_encode_bool(xdr, value); +}; + +static bool __maybe_unused +xdrgen_encode_open_arguments4(struct xdr_stream *xdr, const struct open_arguments4 *value) +{ + if (!xdrgen_encode_bitmap4(xdr, value->oa_share_access)) + return false; + if (!xdrgen_encode_bitmap4(xdr, value->oa_share_deny)) + return false; + if (!xdrgen_encode_bitmap4(xdr, value->oa_share_access_want)) + return false; + if (!xdrgen_encode_bitmap4(xdr, value->oa_open_claim)) + return false; + if (!xdrgen_encode_bitmap4(xdr, value->oa_create_mode)) + return false; + return true; +}; + +static bool __maybe_unused +xdrgen_encode_open_args_share_access4(struct xdr_stream *xdr, open_args_share_access4 value) +{ + return xdr_stream_encode_u32(xdr, value) == XDR_UNIT; +} + +static bool __maybe_unused +xdrgen_encode_open_args_share_deny4(struct xdr_stream *xdr, open_args_share_deny4 value) +{ + return xdr_stream_encode_u32(xdr, value) == XDR_UNIT; +} + +static bool __maybe_unused +xdrgen_encode_open_args_share_access_want4(struct xdr_stream *xdr, open_args_share_access_want4 value) +{ + return xdr_stream_encode_u32(xdr, value) == XDR_UNIT; +} + +static bool __maybe_unused +xdrgen_encode_open_args_open_claim4(struct xdr_stream *xdr, open_args_open_claim4 value) +{ + return xdr_stream_encode_u32(xdr, value) == XDR_UNIT; +} + +static bool __maybe_unused +xdrgen_encode_open_args_createmode4(struct xdr_stream *xdr, open_args_createmode4 value) +{ + return xdr_stream_encode_u32(xdr, value) == XDR_UNIT; +} + +bool +xdrgen_encode_fattr4_open_arguments(struct xdr_stream *xdr, const fattr4_open_arguments *value) +{ + return xdrgen_encode_open_arguments4(xdr, value); +}; + +bool +xdrgen_encode_fattr4_time_deleg_access(struct xdr_stream *xdr, const fattr4_time_deleg_access *value) +{ + return xdrgen_encode_nfstime4(xdr, value); +}; + +bool +xdrgen_encode_fattr4_time_deleg_modify(struct xdr_stream *xdr, const fattr4_time_deleg_modify *value) +{ + return xdrgen_encode_nfstime4(xdr, value); +}; + +static bool __maybe_unused +xdrgen_encode_open_delegation_type4(struct xdr_stream *xdr, open_delegation_type4 value) +{ + return xdr_stream_encode_u32(xdr, value) == XDR_UNIT; +} diff --git a/fs/nfsd/nfs4xdr_gen.h b/fs/nfsd/nfs4xdr_gen.h new file mode 100644 index 000000000000..41a0033b7256 --- /dev/null +++ b/fs/nfsd/nfs4xdr_gen.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Generated by xdrgen. Manual edits will be lost. */ +/* XDR specification file: ../../Documentation/sunrpc/xdr/nfs4_1.x */ +/* XDR specification modification time: Mon Oct 14 09:10:13 2024 */ + +#ifndef _LINUX_XDRGEN_NFS4_1_DECL_H +#define _LINUX_XDRGEN_NFS4_1_DECL_H + +#include <linux/types.h> + +#include <linux/sunrpc/xdr.h> +#include <linux/sunrpc/xdrgen/_defs.h> +#include <linux/sunrpc/xdrgen/_builtins.h> +#include <linux/sunrpc/xdrgen/nfs4_1.h> + +bool xdrgen_decode_fattr4_open_arguments(struct xdr_stream *xdr, fattr4_open_arguments *ptr); +bool xdrgen_encode_fattr4_open_arguments(struct xdr_stream *xdr, const fattr4_open_arguments *value); + +bool xdrgen_decode_fattr4_time_deleg_access(struct xdr_stream *xdr, fattr4_time_deleg_access *ptr); +bool xdrgen_encode_fattr4_time_deleg_access(struct xdr_stream *xdr, const fattr4_time_deleg_access *value); + +bool xdrgen_decode_fattr4_time_deleg_modify(struct xdr_stream *xdr, fattr4_time_deleg_modify *ptr); +bool xdrgen_encode_fattr4_time_deleg_modify(struct xdr_stream *xdr, const fattr4_time_deleg_modify *value); + +#endif /* _LINUX_XDRGEN_NFS4_1_DECL_H */ diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index 3e64a3d50a1c..ab13ee9c7fd8 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -27,7 +27,7 @@ * cache size, the idea being that when the cache is at its maximum number * of entries, then this should be the average number of entries per bucket. */ -#define TARGET_BUCKET_SIZE 64 +#define TARGET_BUCKET_SIZE 8 struct nfsd_drc_bucket { struct rb_root rb_head; @@ -84,11 +84,11 @@ nfsd_hashsize(unsigned int limit) return roundup_pow_of_two(limit / TARGET_BUCKET_SIZE); } -static struct svc_cacherep * -nfsd_reply_cache_alloc(struct svc_rqst *rqstp, __wsum csum, - struct nfsd_net *nn) +static struct nfsd_cacherep * +nfsd_cacherep_alloc(struct svc_rqst *rqstp, __wsum csum, + struct nfsd_net *nn) { - struct svc_cacherep *rp; + struct nfsd_cacherep *rp; rp = kmem_cache_alloc(drc_slab, GFP_KERNEL); if (rp) { @@ -110,36 +110,63 @@ nfsd_reply_cache_alloc(struct svc_rqst *rqstp, __wsum csum, return rp; } -static void -nfsd_reply_cache_free_locked(struct nfsd_drc_bucket *b, struct svc_cacherep *rp, - struct nfsd_net *nn) +static void nfsd_cacherep_free(struct nfsd_cacherep *rp) { - if (rp->c_type == RC_REPLBUFF && rp->c_replvec.iov_base) { - nfsd_stats_drc_mem_usage_sub(nn, rp->c_replvec.iov_len); + if (rp->c_type == RC_REPLBUFF) kfree(rp->c_replvec.iov_base); + kmem_cache_free(drc_slab, rp); +} + +static unsigned long +nfsd_cacherep_dispose(struct list_head *dispose) +{ + struct nfsd_cacherep *rp; + unsigned long freed = 0; + + while (!list_empty(dispose)) { + rp = list_first_entry(dispose, struct nfsd_cacherep, c_lru); + list_del(&rp->c_lru); + nfsd_cacherep_free(rp); + freed++; } + return freed; +} + +static void +nfsd_cacherep_unlink_locked(struct nfsd_net *nn, struct nfsd_drc_bucket *b, + struct nfsd_cacherep *rp) +{ + if (rp->c_type == RC_REPLBUFF && rp->c_replvec.iov_base) + nfsd_stats_drc_mem_usage_sub(nn, rp->c_replvec.iov_len); if (rp->c_state != RC_UNUSED) { rb_erase(&rp->c_node, &b->rb_head); list_del(&rp->c_lru); atomic_dec(&nn->num_drc_entries); nfsd_stats_drc_mem_usage_sub(nn, sizeof(*rp)); } - kmem_cache_free(drc_slab, rp); } static void -nfsd_reply_cache_free(struct nfsd_drc_bucket *b, struct svc_cacherep *rp, +nfsd_reply_cache_free_locked(struct nfsd_drc_bucket *b, struct nfsd_cacherep *rp, + struct nfsd_net *nn) +{ + nfsd_cacherep_unlink_locked(nn, b, rp); + nfsd_cacherep_free(rp); +} + +static void +nfsd_reply_cache_free(struct nfsd_drc_bucket *b, struct nfsd_cacherep *rp, struct nfsd_net *nn) { spin_lock(&b->cache_lock); - nfsd_reply_cache_free_locked(b, rp, nn); + nfsd_cacherep_unlink_locked(nn, b, rp); spin_unlock(&b->cache_lock); + nfsd_cacherep_free(rp); } int nfsd_drc_slab_create(void) { - drc_slab = kmem_cache_create("nfsd_drc", - sizeof(struct svc_cacherep), 0, 0, NULL); + drc_slab = KMEM_CACHE(nfsd_cacherep, 0); return drc_slab ? 0: -ENOMEM; } @@ -148,44 +175,33 @@ void nfsd_drc_slab_free(void) kmem_cache_destroy(drc_slab); } -static int nfsd_reply_cache_stats_init(struct nfsd_net *nn) -{ - return nfsd_percpu_counters_init(nn->counter, NFSD_NET_COUNTERS_NUM); -} - -static void nfsd_reply_cache_stats_destroy(struct nfsd_net *nn) -{ - nfsd_percpu_counters_destroy(nn->counter, NFSD_NET_COUNTERS_NUM); -} - int nfsd_reply_cache_init(struct nfsd_net *nn) { unsigned int hashsize; unsigned int i; - int status = 0; nn->max_drc_entries = nfsd_cache_size_limit(); atomic_set(&nn->num_drc_entries, 0); hashsize = nfsd_hashsize(nn->max_drc_entries); nn->maskbits = ilog2(hashsize); - status = nfsd_reply_cache_stats_init(nn); - if (status) - goto out_nomem; - - nn->nfsd_reply_cache_shrinker.scan_objects = nfsd_reply_cache_scan; - nn->nfsd_reply_cache_shrinker.count_objects = nfsd_reply_cache_count; - nn->nfsd_reply_cache_shrinker.seeks = 1; - status = register_shrinker(&nn->nfsd_reply_cache_shrinker, - "nfsd-reply:%s", nn->nfsd_name); - if (status) - goto out_stats_destroy; - nn->drc_hashtbl = kvzalloc(array_size(hashsize, sizeof(*nn->drc_hashtbl)), GFP_KERNEL); if (!nn->drc_hashtbl) + return -ENOMEM; + + nn->nfsd_reply_cache_shrinker = shrinker_alloc(0, "nfsd-reply:%s", + nn->nfsd_name); + if (!nn->nfsd_reply_cache_shrinker) goto out_shrinker; + nn->nfsd_reply_cache_shrinker->scan_objects = nfsd_reply_cache_scan; + nn->nfsd_reply_cache_shrinker->count_objects = nfsd_reply_cache_count; + nn->nfsd_reply_cache_shrinker->seeks = 1; + nn->nfsd_reply_cache_shrinker->private_data = nn; + + shrinker_register(nn->nfsd_reply_cache_shrinker); + for (i = 0; i < hashsize; i++) { INIT_LIST_HEAD(&nn->drc_hashtbl[i].lru_head); spin_lock_init(&nn->drc_hashtbl[i].cache_lock); @@ -194,30 +210,26 @@ int nfsd_reply_cache_init(struct nfsd_net *nn) return 0; out_shrinker: - unregister_shrinker(&nn->nfsd_reply_cache_shrinker); -out_stats_destroy: - nfsd_reply_cache_stats_destroy(nn); -out_nomem: + kvfree(nn->drc_hashtbl); printk(KERN_ERR "nfsd: failed to allocate reply cache\n"); return -ENOMEM; } void nfsd_reply_cache_shutdown(struct nfsd_net *nn) { - struct svc_cacherep *rp; + struct nfsd_cacherep *rp; unsigned int i; - unregister_shrinker(&nn->nfsd_reply_cache_shrinker); + shrinker_free(nn->nfsd_reply_cache_shrinker); for (i = 0; i < nn->drc_hashsize; i++) { struct list_head *head = &nn->drc_hashtbl[i].lru_head; while (!list_empty(head)) { - rp = list_first_entry(head, struct svc_cacherep, c_lru); + rp = list_first_entry(head, struct nfsd_cacherep, c_lru); nfsd_reply_cache_free_locked(&nn->drc_hashtbl[i], rp, nn); } } - nfsd_reply_cache_stats_destroy(nn); kvfree(nn->drc_hashtbl); nn->drc_hashtbl = NULL; @@ -225,12 +237,8 @@ void nfsd_reply_cache_shutdown(struct nfsd_net *nn) } -/* - * Move cache entry to end of LRU list, and queue the cleaner to run if it's - * not already scheduled. - */ static void -lru_put_end(struct nfsd_drc_bucket *b, struct svc_cacherep *rp) +lru_put_end(struct nfsd_drc_bucket *b, struct nfsd_cacherep *rp) { rp->c_timestamp = jiffies; list_move_tail(&rp->c_lru, &b->lru_head); @@ -244,100 +252,134 @@ nfsd_cache_bucket_find(__be32 xid, struct nfsd_net *nn) return &nn->drc_hashtbl[hash]; } -static long prune_bucket(struct nfsd_drc_bucket *b, struct nfsd_net *nn, - unsigned int max) +/* + * Remove and return no more than @max expired entries in bucket @b. + * If @max is zero, do not limit the number of removed entries. + */ +static void +nfsd_prune_bucket_locked(struct nfsd_net *nn, struct nfsd_drc_bucket *b, + unsigned int max, struct list_head *dispose) { - struct svc_cacherep *rp, *tmp; - long freed = 0; + unsigned long expiry = jiffies - RC_EXPIRE; + struct nfsd_cacherep *rp, *tmp; + unsigned int freed = 0; + lockdep_assert_held(&b->cache_lock); + + /* The bucket LRU is ordered oldest-first. */ list_for_each_entry_safe(rp, tmp, &b->lru_head, c_lru) { - /* - * Don't free entries attached to calls that are still - * in-progress, but do keep scanning the list. - */ - if (rp->c_state == RC_INPROG) - continue; if (atomic_read(&nn->num_drc_entries) <= nn->max_drc_entries && - time_before(jiffies, rp->c_timestamp + RC_EXPIRE)) + time_before(expiry, rp->c_timestamp)) break; - nfsd_reply_cache_free_locked(b, rp, nn); - if (max && freed++ > max) + + nfsd_cacherep_unlink_locked(nn, b, rp); + list_add(&rp->c_lru, dispose); + + if (max && ++freed > max) break; } - return freed; } -static long nfsd_prune_bucket(struct nfsd_drc_bucket *b, struct nfsd_net *nn) +/** + * nfsd_reply_cache_count - count_objects method for the DRC shrinker + * @shrink: our registered shrinker context + * @sc: garbage collection parameters + * + * Returns the total number of entries in the duplicate reply cache. To + * keep things simple and quick, this is not the number of expired entries + * in the cache (ie, the number that would be removed by a call to + * nfsd_reply_cache_scan). + */ +static unsigned long +nfsd_reply_cache_count(struct shrinker *shrink, struct shrink_control *sc) { - return prune_bucket(b, nn, 3); + struct nfsd_net *nn = shrink->private_data; + + return atomic_read(&nn->num_drc_entries); } -/* - * Walk the LRU list and prune off entries that are older than RC_EXPIRE. - * Also prune the oldest ones when the total exceeds the max number of entries. +/** + * nfsd_reply_cache_scan - scan_objects method for the DRC shrinker + * @shrink: our registered shrinker context + * @sc: garbage collection parameters + * + * Free expired entries on each bucket's LRU list until we've released + * nr_to_scan freed objects. Nothing will be released if the cache + * has not exceeded it's max_drc_entries limit. + * + * Returns the number of entries released by this call. */ -static long -prune_cache_entries(struct nfsd_net *nn) +static unsigned long +nfsd_reply_cache_scan(struct shrinker *shrink, struct shrink_control *sc) { + struct nfsd_net *nn = shrink->private_data; + unsigned long freed = 0; + LIST_HEAD(dispose); unsigned int i; - long freed = 0; for (i = 0; i < nn->drc_hashsize; i++) { struct nfsd_drc_bucket *b = &nn->drc_hashtbl[i]; if (list_empty(&b->lru_head)) continue; + spin_lock(&b->cache_lock); - freed += prune_bucket(b, nn, 0); + nfsd_prune_bucket_locked(nn, b, 0, &dispose); spin_unlock(&b->cache_lock); + + freed += nfsd_cacherep_dispose(&dispose); + if (freed > sc->nr_to_scan) + break; } return freed; } -static unsigned long -nfsd_reply_cache_count(struct shrinker *shrink, struct shrink_control *sc) -{ - struct nfsd_net *nn = container_of(shrink, - struct nfsd_net, nfsd_reply_cache_shrinker); - - return atomic_read(&nn->num_drc_entries); -} - -static unsigned long -nfsd_reply_cache_scan(struct shrinker *shrink, struct shrink_control *sc) -{ - struct nfsd_net *nn = container_of(shrink, - struct nfsd_net, nfsd_reply_cache_shrinker); - - return prune_cache_entries(nn); -} -/* - * Walk an xdr_buf and get a CRC for at most the first RC_CSUMLEN bytes +/** + * nfsd_cache_csum - Checksum incoming NFS Call arguments + * @buf: buffer containing a whole RPC Call message + * @start: starting byte of the NFS Call header + * @remaining: size of the NFS Call header, in bytes + * + * Compute a weak checksum of the leading bytes of an NFS procedure + * call header to help verify that a retransmitted Call matches an + * entry in the duplicate reply cache. + * + * To avoid assumptions about how the RPC message is laid out in + * @buf and what else it might contain (eg, a GSS MIC suffix), the + * caller passes us the exact location and length of the NFS Call + * header. + * + * Returns a 32-bit checksum value, as defined in RFC 793. */ -static __wsum -nfsd_cache_csum(struct svc_rqst *rqstp) +static __wsum nfsd_cache_csum(struct xdr_buf *buf, unsigned int start, + unsigned int remaining) { + unsigned int base, len; + struct xdr_buf subbuf; + __wsum csum = 0; + void *p; int idx; - unsigned int base; - __wsum csum; - struct xdr_buf *buf = &rqstp->rq_arg; - const unsigned char *p = buf->head[0].iov_base; - size_t csum_len = min_t(size_t, buf->head[0].iov_len + buf->page_len, - RC_CSUMLEN); - size_t len = min(buf->head[0].iov_len, csum_len); + + if (remaining > RC_CSUMLEN) + remaining = RC_CSUMLEN; + if (xdr_buf_subsegment(buf, &subbuf, start, remaining)) + return csum; /* rq_arg.head first */ - csum = csum_partial(p, len, 0); - csum_len -= len; + if (subbuf.head[0].iov_len) { + len = min_t(unsigned int, subbuf.head[0].iov_len, remaining); + csum = csum_partial(subbuf.head[0].iov_base, len, csum); + remaining -= len; + } /* Continue into page array */ - idx = buf->page_base / PAGE_SIZE; - base = buf->page_base & ~PAGE_MASK; - while (csum_len) { - p = page_address(buf->pages[idx]) + base; - len = min_t(size_t, PAGE_SIZE - base, csum_len); + idx = subbuf.page_base / PAGE_SIZE; + base = subbuf.page_base & ~PAGE_MASK; + while (remaining) { + p = page_address(subbuf.pages[idx]) + base; + len = min_t(unsigned int, PAGE_SIZE - base, remaining); csum = csum_partial(p, len, csum); - csum_len -= len; + remaining -= len; base = 0; ++idx; } @@ -345,8 +387,8 @@ nfsd_cache_csum(struct svc_rqst *rqstp) } static int -nfsd_cache_key_cmp(const struct svc_cacherep *key, - const struct svc_cacherep *rp, struct nfsd_net *nn) +nfsd_cache_key_cmp(const struct nfsd_cacherep *key, + const struct nfsd_cacherep *rp, struct nfsd_net *nn) { if (key->c_key.k_xid == rp->c_key.k_xid && key->c_key.k_csum != rp->c_key.k_csum) { @@ -362,11 +404,11 @@ nfsd_cache_key_cmp(const struct svc_cacherep *key, * Must be called with cache_lock held. Returns the found entry or * inserts an empty key on failure. */ -static struct svc_cacherep * -nfsd_cache_insert(struct nfsd_drc_bucket *b, struct svc_cacherep *key, +static struct nfsd_cacherep * +nfsd_cache_insert(struct nfsd_drc_bucket *b, struct nfsd_cacherep *key, struct nfsd_net *nn) { - struct svc_cacherep *rp, *ret = key; + struct nfsd_cacherep *rp, *ret = key; struct rb_node **p = &b->rb_head.rb_node, *parent = NULL; unsigned int entries = 0; @@ -375,7 +417,7 @@ nfsd_cache_insert(struct nfsd_drc_bucket *b, struct svc_cacherep *key, while (*p != NULL) { ++entries; parent = *p; - rp = rb_entry(parent, struct svc_cacherep, c_node); + rp = rb_entry(parent, struct nfsd_cacherep, c_node); cmp = nfsd_cache_key_cmp(key, rp, nn); if (cmp < 0) @@ -400,14 +442,15 @@ out: nn->longest_chain_cachesize, atomic_read(&nn->num_drc_entries)); } - - lru_put_end(b, ret); return ret; } /** * nfsd_cache_lookup - Find an entry in the duplicate reply cache * @rqstp: Incoming Call to find + * @start: starting byte in @rqstp->rq_arg of the NFS Call header + * @len: size of the NFS Call header, in bytes + * @cacherep: OUT: DRC entry for this request * * Try to find an entry matching the current call in the cache. When none * is found, we try to grab the oldest expired entry off the LRU list. If @@ -420,29 +463,29 @@ out: * %RC_REPLY: Reply from cache * %RC_DROPIT: Do not process the request further */ -int nfsd_cache_lookup(struct svc_rqst *rqstp) +int nfsd_cache_lookup(struct svc_rqst *rqstp, unsigned int start, + unsigned int len, struct nfsd_cacherep **cacherep) { - struct nfsd_net *nn; - struct svc_cacherep *rp, *found; + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); + struct nfsd_cacherep *rp, *found; __wsum csum; struct nfsd_drc_bucket *b; int type = rqstp->rq_cachetype; + LIST_HEAD(dispose); int rtn = RC_DOIT; - rqstp->rq_cacherep = NULL; if (type == RC_NOCACHE) { - nfsd_stats_rc_nocache_inc(); + nfsd_stats_rc_nocache_inc(nn); goto out; } - csum = nfsd_cache_csum(rqstp); + csum = nfsd_cache_csum(&rqstp->rq_arg, start, len); /* * Since the common case is a cache miss followed by an insert, * preallocate an entry. */ - nn = net_generic(SVC_NET(rqstp), nfsd_net_id); - rp = nfsd_reply_cache_alloc(rqstp, csum, nn); + rp = nfsd_cacherep_alloc(rqstp, csum, nn); if (!rp) goto out; @@ -451,25 +494,22 @@ int nfsd_cache_lookup(struct svc_rqst *rqstp) found = nfsd_cache_insert(b, rp, nn); if (found != rp) goto found_entry; - - nfsd_stats_rc_misses_inc(); - rqstp->rq_cacherep = rp; + *cacherep = rp; rp->c_state = RC_INPROG; + nfsd_prune_bucket_locked(nn, b, 3, &dispose); + spin_unlock(&b->cache_lock); + nfsd_cacherep_dispose(&dispose); + + nfsd_stats_rc_misses_inc(nn); atomic_inc(&nn->num_drc_entries); nfsd_stats_drc_mem_usage_add(nn, sizeof(*rp)); - - nfsd_prune_bucket(b, nn); - -out_unlock: - spin_unlock(&b->cache_lock); -out: - return rtn; + goto out; found_entry: /* We found a matching entry which is either in progress or done. */ nfsd_reply_cache_free_locked(NULL, rp, nn); - nfsd_stats_rc_hits_inc(); + nfsd_stats_rc_hits_inc(nn); rtn = RC_DROPIT; rp = found; @@ -488,7 +528,7 @@ found_entry: case RC_NOCACHE: break; case RC_REPLSTAT: - svc_putu32(&rqstp->rq_res.head[0], rp->c_replstat); + xdr_stream_encode_be32(&rqstp->rq_res_stream, rp->c_replstat); rtn = RC_REPLY; break; case RC_REPLBUFF: @@ -502,14 +542,18 @@ found_entry: out_trace: trace_nfsd_drc_found(nn, rqstp, rtn); - goto out_unlock; +out_unlock: + spin_unlock(&b->cache_lock); +out: + return rtn; } /** * nfsd_cache_update - Update an entry in the duplicate reply cache. * @rqstp: svc_rqst with a finished Reply + * @rp: IN: DRC entry for this request * @cachetype: which cache to update - * @statp: Reply's status code + * @statp: pointer to Reply's NFS status code, or NULL * * This is called from nfsd_dispatch when the procedure has been * executed and the complete reply is in rqstp->rq_res. @@ -525,10 +569,10 @@ out_trace: * nfsd failed to encode a reply that otherwise would have been cached. * In this case, nfsd_cache_update is called with statp == NULL. */ -void nfsd_cache_update(struct svc_rqst *rqstp, int cachetype, __be32 *statp) +void nfsd_cache_update(struct svc_rqst *rqstp, struct nfsd_cacherep *rp, + int cachetype, __be32 *statp) { struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); - struct svc_cacherep *rp = rqstp->rq_cacherep; struct kvec *resv = &rqstp->rq_res.head[0], *cachv; struct nfsd_drc_bucket *b; int len; @@ -579,24 +623,17 @@ void nfsd_cache_update(struct svc_rqst *rqstp, int cachetype, __be32 *statp) return; } -/* - * Copy cached reply to current reply buffer. Should always fit. - * FIXME as reply is in a page, we should just attach the page, and - * keep a refcount.... - */ static int nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *data) { - struct kvec *vec = &rqstp->rq_res.head[0]; - - if (vec->iov_len + data->iov_len > PAGE_SIZE) { - printk(KERN_WARNING "nfsd: cached reply too large (%zd).\n", - data->iov_len); - return 0; - } - memcpy((char*)vec->iov_base + vec->iov_len, data->iov_base, data->iov_len); - vec->iov_len += data->iov_len; - return 1; + __be32 *p; + + p = xdr_reserve_space(&rqstp->rq_res_stream, data->iov_len); + if (unlikely(!p)) + return false; + memcpy(p, data->iov_base, data->iov_len); + xdr_commit_encode(&rqstp->rq_res_stream); + return true; } /* @@ -614,15 +651,15 @@ int nfsd_reply_cache_stats_show(struct seq_file *m, void *v) atomic_read(&nn->num_drc_entries)); seq_printf(m, "hash buckets: %u\n", 1 << nn->maskbits); seq_printf(m, "mem usage: %lld\n", - percpu_counter_sum_positive(&nn->counter[NFSD_NET_DRC_MEM_USAGE])); + percpu_counter_sum_positive(&nn->counter[NFSD_STATS_DRC_MEM_USAGE])); seq_printf(m, "cache hits: %lld\n", - percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_RC_HITS])); + percpu_counter_sum_positive(&nn->counter[NFSD_STATS_RC_HITS])); seq_printf(m, "cache misses: %lld\n", - percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_RC_MISSES])); + percpu_counter_sum_positive(&nn->counter[NFSD_STATS_RC_MISSES])); seq_printf(m, "not cached: %lld\n", - percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_RC_NOCACHE])); + percpu_counter_sum_positive(&nn->counter[NFSD_STATS_RC_NOCACHE])); seq_printf(m, "payload misses: %lld\n", - percpu_counter_sum_positive(&nn->counter[NFSD_NET_PAYLOAD_MISSES])); + percpu_counter_sum_positive(&nn->counter[NFSD_STATS_PAYLOAD_MISSES])); seq_printf(m, "longest chain len: %u\n", nn->longest_chain); seq_printf(m, "cachesize at longest: %u\n", nn->longest_chain_cachesize); return 0; diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index c2577ee7ffb2..5ce9a49e76ba 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -14,10 +14,11 @@ #include <linux/lockd/lockd.h> #include <linux/sunrpc/addr.h> #include <linux/sunrpc/gss_api.h> -#include <linux/sunrpc/gss_krb5_enctypes.h> #include <linux/sunrpc/rpc_pipe_fs.h> +#include <linux/sunrpc/svc.h> #include <linux/module.h> #include <linux/fsnotify.h> +#include <linux/nfslocalio.h> #include "idmap.h" #include "nfsd.h" @@ -26,6 +27,8 @@ #include "netns.h" #include "pnfs.h" #include "filecache.h" +#include "trace.h" +#include "netlink.h" /* * We have a single directory with several nodes in it. @@ -45,19 +48,11 @@ enum { NFSD_Versions, NFSD_Ports, NFSD_MaxBlkSize, - NFSD_MaxConnections, NFSD_Filecache, - NFSD_SupportedEnctypes, - /* - * The below MUST come last. Otherwise we leave a hole in nfsd_files[] - * with !CONFIG_NFSD_V4 and simple_fill_super() goes oops - */ -#ifdef CONFIG_NFSD_V4 NFSD_Leasetime, NFSD_Gracetime, NFSD_RecoveryDir, NFSD_V4EndGrace, -#endif NFSD_MaxReserved }; @@ -72,11 +67,12 @@ static ssize_t write_pool_threads(struct file *file, char *buf, size_t size); static ssize_t write_versions(struct file *file, char *buf, size_t size); static ssize_t write_ports(struct file *file, char *buf, size_t size); static ssize_t write_maxblksize(struct file *file, char *buf, size_t size); -static ssize_t write_maxconn(struct file *file, char *buf, size_t size); #ifdef CONFIG_NFSD_V4 static ssize_t write_leasetime(struct file *file, char *buf, size_t size); static ssize_t write_gracetime(struct file *file, char *buf, size_t size); +#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING static ssize_t write_recoverydir(struct file *file, char *buf, size_t size); +#endif static ssize_t write_v4_end_grace(struct file *file, char *buf, size_t size); #endif @@ -89,11 +85,12 @@ static ssize_t (*const write_op[])(struct file *, char *, size_t) = { [NFSD_Versions] = write_versions, [NFSD_Ports] = write_ports, [NFSD_MaxBlkSize] = write_maxblksize, - [NFSD_MaxConnections] = write_maxconn, #ifdef CONFIG_NFSD_V4 [NFSD_Leasetime] = write_leasetime, [NFSD_Gracetime] = write_gracetime, +#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING [NFSD_RecoveryDir] = write_recoverydir, +#endif [NFSD_V4EndGrace] = write_v4_end_grace, #endif }; @@ -111,12 +108,12 @@ static ssize_t nfsctl_transaction_write(struct file *file, const char __user *bu if (IS_ERR(data)) return PTR_ERR(data); - rv = write_op[ino](file, data, size); - if (rv >= 0) { - simple_transaction_set(file, rv); - rv = size; - } - return rv; + rv = write_op[ino](file, data, size); + if (rv < 0) + return rv; + + simple_transaction_set(file, rv); + return size; } static ssize_t nfsctl_transaction_read(struct file *file, char __user *buf, size_t size, loff_t *pos) @@ -155,18 +152,6 @@ static int exports_net_open(struct net *net, struct file *file) return 0; } -static int exports_proc_open(struct inode *inode, struct file *file) -{ - return exports_net_open(current->nsproxy->net_ns, file); -} - -static const struct proc_ops exports_proc_ops = { - .proc_open = exports_proc_open, - .proc_read = seq_read, - .proc_lseek = seq_lseek, - .proc_release = seq_release, -}; - static int exports_nfsd_open(struct inode *inode, struct file *file) { return exports_net_open(inode->i_sb->s_fs_info, file); @@ -187,21 +172,18 @@ static int export_features_show(struct seq_file *m, void *v) DEFINE_SHOW_ATTRIBUTE(export_features); -#if defined(CONFIG_SUNRPC_GSS) || defined(CONFIG_SUNRPC_GSS_MODULE) -static int supported_enctypes_show(struct seq_file *m, void *v) +static int nfsd_pool_stats_open(struct inode *inode, struct file *file) { - seq_printf(m, KRB5_SUPPORTED_ENCTYPES); - return 0; -} + struct nfsd_net *nn = net_generic(inode->i_sb->s_fs_info, nfsd_net_id); -DEFINE_SHOW_ATTRIBUTE(supported_enctypes); -#endif /* CONFIG_SUNRPC_GSS or CONFIG_SUNRPC_GSS_MODULE */ + return svc_pool_stats_open(&nn->nfsd_info, file); +} static const struct file_operations pool_stats_operations = { .open = nfsd_pool_stats_open, .read = seq_read, .llseek = seq_lseek, - .release = nfsd_pool_stats_release, + .release = seq_release, }; DEFINE_SHOW_ATTRIBUTE(nfsd_reply_cache_stats); @@ -254,6 +236,7 @@ static ssize_t write_unlock_ip(struct file *file, char *buf, size_t size) if (rpc_pton(net, fo_path, size, sap, salen) == 0) return -EINVAL; + trace_nfsd_ctl_unlock_ip(net, buf); return nlmsvc_unlock_all_by_ip(sap); } @@ -287,7 +270,7 @@ static ssize_t write_unlock_fs(struct file *file, char *buf, size_t size) fo_path = buf; if (qword_get(&buf, fo_path, size) < 0) return -EINVAL; - + trace_nfsd_ctl_unlock_fs(netns(file), fo_path); error = kern_path(fo_path, 0, &path); if (error) return error; @@ -302,6 +285,7 @@ static ssize_t write_unlock_fs(struct file *file, char *buf, size_t size) * 3. Is that directory the root of an exported file system? */ error = nlmsvc_unlock_all_by_sb(path.dentry->d_sb); + nfsd4_revoke_states(netns(file), path.dentry->d_sb); path_put(&path); return error; @@ -348,7 +332,7 @@ static ssize_t write_filehandle(struct file *file, char *buf, size_t size) len = qword_get(&mesg, dname, size); if (len <= 0) return -EINVAL; - + path = dname+len+1; len = qword_get(&mesg, path, size); if (len <= 0) @@ -362,15 +346,17 @@ static ssize_t write_filehandle(struct file *file, char *buf, size_t size) return -EINVAL; maxsize = min(maxsize, NFS3_FHSIZE); - if (qword_get(&mesg, mesg, size)>0) + if (qword_get(&mesg, mesg, size) > 0) return -EINVAL; + trace_nfsd_ctl_filehandle(netns(file), dname, path, maxsize); + /* we have all the words, they are in buf.. */ dom = unix_domain_find(dname); if (!dom) return -ENOMEM; - len = exp_rootfh(netns(file), dom, path, &fh, maxsize); + len = exp_rootfh(netns(file), dom, path, &fh, maxsize); auth_domain_put(dom); if (len) return len; @@ -423,7 +409,10 @@ static ssize_t write_threads(struct file *file, char *buf, size_t size) return rv; if (newthreads < 0) return -EINVAL; - rv = nfsd_svc(newthreads, net, file->f_cred); + trace_nfsd_ctl_threads(net, newthreads); + mutex_lock(&nfsd_mutex); + rv = nfsd_svc(1, &newthreads, net, file->f_cred, NULL); + mutex_unlock(&nfsd_mutex); if (rv < 0) return rv; } else @@ -442,8 +431,8 @@ static ssize_t write_threads(struct file *file, char *buf, size_t size) * OR * * Input: - * buf: C string containing whitespace- - * separated unsigned integer values + * buf: C string containing whitespace- + * separated unsigned integer values * representing the number of NFSD * threads to start in each pool * size: non-zero length of C string in @buf @@ -495,7 +484,16 @@ static ssize_t write_pool_threads(struct file *file, char *buf, size_t size) rv = -EINVAL; if (nthreads[i] < 0) goto out_free; + trace_nfsd_ctl_pool_threads(net, i, nthreads[i]); } + + /* + * There must always be a thread in pool 0; the admin + * can't shut down NFS completely using pool_threads. + */ + if (nthreads[0] == 0) + nthreads[0] = 1; + rv = nfsd_set_nrthreads(i, nthreads, net); if (rv) goto out_free; @@ -550,7 +548,7 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size) char *sep; struct nfsd_net *nn = net_generic(netns(file), nfsd_net_id); - if (size>0) { + if (size > 0) { if (nn->nfsd_serv) /* Cannot change versions without updating * nn->nfsd_serv->sv_xdrsize, and reallocing @@ -560,6 +558,7 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size) if (buf[size-1] != '\n') return -EINVAL; buf[size-1] = 0; + trace_nfsd_ctl_version(netns(file), buf); vers = mesg; len = qword_get(&mesg, vers, size); @@ -661,11 +660,11 @@ out: * OR * * Input: - * buf: C string containing whitespace- - * separated positive or negative - * integer values representing NFS - * protocol versions to enable ("+n") - * or disable ("-n") + * buf: C string containing whitespace- + * separated positive or negative + * integer values representing NFS + * protocol versions to enable ("+n") + * or disable ("-n") * size: non-zero length of C string in @buf * Output: * On success: status of zero or more protocol versions has @@ -709,32 +708,28 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net, const struct cred char *mesg = buf; int fd, err; struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct svc_serv *serv; err = get_int(&mesg, &fd); if (err != 0 || fd < 0) return -EINVAL; - - if (svc_alien_sock(net, fd)) { - printk(KERN_ERR "%s: socket net is different to NFSd's one\n", __func__); - return -EINVAL; - } + trace_nfsd_ctl_ports_addfd(net, fd); err = nfsd_create_serv(net); if (err != 0) return err; - err = svc_addsock(nn->nfsd_serv, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred); + serv = nn->nfsd_serv; + err = svc_addsock(serv, net, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred); - if (err >= 0 && - !nn->nfsd_serv->sv_nrthreads && !xchg(&nn->keep_active, 1)) - svc_get(nn->nfsd_serv); + if (!serv->sv_nrthreads && list_empty(&nn->nfsd_serv->sv_permsocks)) + nfsd_destroy_serv(net); - nfsd_put(net); return err; } /* - * A transport listener is added by writing it's transport name and + * A transport listener is added by writing its transport name and * a port number. */ static ssize_t __write_ports_addxprt(char *buf, struct net *net, const struct cred *cred) @@ -743,40 +738,41 @@ static ssize_t __write_ports_addxprt(char *buf, struct net *net, const struct cr struct svc_xprt *xprt; int port, err; struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct svc_serv *serv; if (sscanf(buf, "%15s %5u", transport, &port) != 2) return -EINVAL; if (port < 1 || port > USHRT_MAX) return -EINVAL; + trace_nfsd_ctl_ports_addxprt(net, transport, port); err = nfsd_create_serv(net); if (err != 0) return err; - err = svc_xprt_create(nn->nfsd_serv, transport, net, + serv = nn->nfsd_serv; + err = svc_xprt_create(serv, transport, net, PF_INET, port, SVC_SOCK_ANONYMOUS, cred); if (err < 0) goto out_err; - err = svc_xprt_create(nn->nfsd_serv, transport, net, + err = svc_xprt_create(serv, transport, net, PF_INET6, port, SVC_SOCK_ANONYMOUS, cred); if (err < 0 && err != -EAFNOSUPPORT) goto out_close; - if (!nn->nfsd_serv->sv_nrthreads && !xchg(&nn->keep_active, 1)) - svc_get(nn->nfsd_serv); - - nfsd_put(net); return 0; out_close: - xprt = svc_find_xprt(nn->nfsd_serv, transport, net, PF_INET, port); + xprt = svc_find_xprt(serv, transport, net, PF_INET, port); if (xprt != NULL) { svc_xprt_close(xprt); svc_xprt_put(xprt); } out_err: - nfsd_put(net); + if (!serv->sv_nrthreads && list_empty(&nn->nfsd_serv->sv_permsocks)) + nfsd_destroy_serv(net); + return err; } @@ -861,9 +857,9 @@ int nfsd_max_blksize; * OR * * Input: - * buf: C string containing an unsigned - * integer value representing the new - * NFS blksize + * buf: C string containing an unsigned + * integer value representing the new + * NFS blksize * size: non-zero length of C string in @buf * Output: * On success: passed-in buffer filled with '\n'-terminated C string @@ -882,6 +878,8 @@ static ssize_t write_maxblksize(struct file *file, char *buf, size_t size) int rv = get_int(&mesg, &bsize); if (rv) return rv; + trace_nfsd_ctl_maxblksize(netns(file), bsize); + /* force bsize into allowed range and * required alignment. */ @@ -901,47 +899,11 @@ static ssize_t write_maxblksize(struct file *file, char *buf, size_t size) nfsd_max_blksize); } -/* - * write_maxconn - Set or report the current max number of connections - * - * Input: - * buf: ignored - * size: zero - * OR - * - * Input: - * buf: C string containing an unsigned - * integer value representing the new - * number of max connections - * size: non-zero length of C string in @buf - * Output: - * On success: passed-in buffer filled with '\n'-terminated C string - * containing numeric value of max_connections setting - * for this net namespace; - * return code is the size in bytes of the string - * On error: return code is zero or a negative errno value - */ -static ssize_t write_maxconn(struct file *file, char *buf, size_t size) -{ - char *mesg = buf; - struct nfsd_net *nn = net_generic(netns(file), nfsd_net_id); - unsigned int maxconn = nn->max_connections; - - if (size > 0) { - int rv = get_uint(&mesg, &maxconn); - - if (rv) - return rv; - nn->max_connections = maxconn; - } - - return scnprintf(buf, SIMPLE_TRANSACTION_LIMIT, "%u\n", maxconn); -} - #ifdef CONFIG_NFSD_V4 static ssize_t __nfsd4_write_time(struct file *file, char *buf, size_t size, time64_t *time, struct nfsd_net *nn) { + struct dentry *dentry = file_dentry(file); char *mesg = buf; int rv, i; @@ -951,6 +913,9 @@ static ssize_t __nfsd4_write_time(struct file *file, char *buf, size_t size, rv = get_int(&mesg, &i); if (rv) return rv; + trace_nfsd_ctl_time(netns(file), dentry->d_name.name, + dentry->d_name.len, i); + /* * Some sanity checking. We don't have a reason for * these particular numbers, but problems with the @@ -1025,6 +990,7 @@ static ssize_t write_gracetime(struct file *file, char *buf, size_t size) return nfsd4_write_time(file, buf, size, &nn->nfsd4_grace, nn); } +#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING static ssize_t __write_recoverydir(struct file *file, char *buf, size_t size, struct nfsd_net *nn) { @@ -1043,6 +1009,7 @@ static ssize_t __write_recoverydir(struct file *file, char *buf, size_t size, len = qword_get(&mesg, recdir, size); if (len <= 0) return -EINVAL; + trace_nfsd_ctl_recoverydir(netns(file), recdir); status = nfs4_reset_recoverydir(recdir); if (status) @@ -1084,6 +1051,7 @@ static ssize_t write_recoverydir(struct file *file, char *buf, size_t size) mutex_unlock(&nfsd_mutex); return rv; } +#endif /* * write_v4_end_grace - release grace period for nfsd's v4.x lock manager @@ -1094,7 +1062,7 @@ static ssize_t write_recoverydir(struct file *file, char *buf, size_t size) * OR * * Input: - * buf: any value + * buf: any value * size: non-zero length of C string in @buf * Output: * passed-in buffer filled with "Y" or "N" with a newline @@ -1116,6 +1084,7 @@ static ssize_t write_v4_end_grace(struct file *file, char *buf, size_t size) case '1': if (!nn->nfsd_serv) return -EBUSY; + trace_nfsd_end_grace(netns(file)); nfsd4_end_grace(nn); break; default: @@ -1134,155 +1103,138 @@ static ssize_t write_v4_end_grace(struct file *file, char *buf, size_t size) * populating the filesystem. */ -/* Basically copying rpc_get_inode. */ static struct inode *nfsd_get_inode(struct super_block *sb, umode_t mode) { struct inode *inode = new_inode(sb); - if (!inode) - return NULL; - /* Following advice from simple_fill_super documentation: */ - inode->i_ino = iunique(sb, NFSD_MaxReserved); - inode->i_mode = mode; - inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode); - switch (mode & S_IFMT) { - case S_IFDIR: - inode->i_fop = &simple_dir_operations; - inode->i_op = &simple_dir_inode_operations; - inc_nlink(inode); - break; - default: - break; + if (inode) { + /* Following advice from simple_fill_super documentation: */ + inode->i_ino = iunique(sb, NFSD_MaxReserved); + inode->i_mode = mode; + simple_inode_init_ts(inode); } return inode; } -static int __nfsd_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode, struct nfsdfs_client *ncl) +static struct dentry *nfsd_mkdir(struct dentry *parent, struct nfsdfs_client *ncl, char *name) { + struct inode *dir = parent->d_inode; + struct dentry *dentry; struct inode *inode; - inode = nfsd_get_inode(dir->i_sb, mode); + inode = nfsd_get_inode(parent->d_sb, S_IFDIR | 0600); if (!inode) - return -ENOMEM; + return ERR_PTR(-ENOMEM); + + dentry = simple_start_creating(parent, name); + if (IS_ERR(dentry)) { + iput(inode); + return dentry; + } + inode->i_fop = &simple_dir_operations; + inode->i_op = &simple_dir_inode_operations; + inc_nlink(inode); if (ncl) { inode->i_private = ncl; kref_get(&ncl->cl_ref); } - d_add(dentry, inode); + d_make_persistent(dentry, inode); inc_nlink(dir); fsnotify_mkdir(dir, dentry); - return 0; + simple_done_creating(dentry); + return dentry; // borrowed } -static struct dentry *nfsd_mkdir(struct dentry *parent, struct nfsdfs_client *ncl, char *name) +#if IS_ENABLED(CONFIG_SUNRPC_GSS) +/* + * @content is assumed to be a NUL-terminated string that lives + * longer than the symlink itself. + */ +static void _nfsd_symlink(struct dentry *parent, const char *name, + const char *content) { struct inode *dir = parent->d_inode; + struct inode *inode; struct dentry *dentry; - int ret = -ENOMEM; - inode_lock(dir); - dentry = d_alloc_name(parent, name); - if (!dentry) - goto out_err; - ret = __nfsd_mkdir(d_inode(parent), dentry, S_IFDIR | 0600, ncl); - if (ret) - goto out_err; -out: - inode_unlock(dir); - return dentry; -out_err: - dput(dentry); - dentry = ERR_PTR(ret); - goto out; + inode = nfsd_get_inode(dir->i_sb, S_IFLNK | 0777); + if (!inode) + return; + + dentry = simple_start_creating(parent, name); + if (IS_ERR(dentry)) { + iput(inode); + return; + } + + inode->i_op = &simple_symlink_inode_operations; + inode->i_link = (char *)content; + inode->i_size = strlen(content); + + d_make_persistent(dentry, inode); + fsnotify_create(dir, dentry); + simple_done_creating(dentry); +} +#else +static inline void _nfsd_symlink(struct dentry *parent, const char *name, + const char *content) +{ } -static void clear_ncl(struct inode *inode) +#endif + +static void clear_ncl(struct dentry *dentry) { + struct inode *inode = d_inode(dentry); struct nfsdfs_client *ncl = inode->i_private; + spin_lock(&inode->i_lock); inode->i_private = NULL; + spin_unlock(&inode->i_lock); kref_put(&ncl->cl_ref, ncl->cl_release); } -static struct nfsdfs_client *__get_nfsdfs_client(struct inode *inode) -{ - struct nfsdfs_client *nc = inode->i_private; - - if (nc) - kref_get(&nc->cl_ref); - return nc; -} - struct nfsdfs_client *get_nfsdfs_client(struct inode *inode) { struct nfsdfs_client *nc; - inode_lock_shared(inode); - nc = __get_nfsdfs_client(inode); - inode_unlock_shared(inode); + spin_lock(&inode->i_lock); + nc = inode->i_private; + if (nc) + kref_get(&nc->cl_ref); + spin_unlock(&inode->i_lock); return nc; } -/* from __rpc_unlink */ -static void nfsdfs_remove_file(struct inode *dir, struct dentry *dentry) -{ - int ret; - - clear_ncl(d_inode(dentry)); - dget(dentry); - ret = simple_unlink(dir, dentry); - d_drop(dentry); - fsnotify_unlink(dir, dentry); - dput(dentry); - WARN_ON_ONCE(ret); -} - -static void nfsdfs_remove_files(struct dentry *root) -{ - struct dentry *dentry, *tmp; - - list_for_each_entry_safe(dentry, tmp, &root->d_subdirs, d_child) { - if (!simple_positive(dentry)) { - WARN_ON_ONCE(1); /* I think this can't happen? */ - continue; - } - nfsdfs_remove_file(d_inode(root), dentry); - } -} /* XXX: cut'n'paste from simple_fill_super; figure out if we could share * code instead. */ -static int nfsdfs_create_files(struct dentry *root, +static int nfsdfs_create_files(struct dentry *root, const struct tree_descr *files, + struct nfsdfs_client *ncl, struct dentry **fdentries) { struct inode *dir = d_inode(root); - struct inode *inode; struct dentry *dentry; - int i; - inode_lock(dir); - for (i = 0; files->name && files->name[0]; i++, files++) { - dentry = d_alloc_name(root, files->name); - if (!dentry) - goto out; - inode = nfsd_get_inode(d_inode(root)->i_sb, - S_IFREG | files->mode); - if (!inode) { - dput(dentry); - goto out; + for (int i = 0; files->name && files->name[0]; i++, files++) { + struct inode *inode = nfsd_get_inode(root->d_sb, + S_IFREG | files->mode); + if (!inode) + return -ENOMEM; + dentry = simple_start_creating(root, files->name); + if (IS_ERR(dentry)) { + iput(inode); + return PTR_ERR(dentry); } + kref_get(&ncl->cl_ref); inode->i_fop = files->ops; - inode->i_private = __get_nfsdfs_client(dir); - d_add(dentry, inode); + inode->i_private = ncl; + d_make_persistent(dentry, inode); fsnotify_create(dir, dentry); if (fdentries) - fdentries[i] = dentry; + fdentries[i] = dentry; // borrowed + simple_done_creating(dentry); } - inode_unlock(dir); return 0; -out: - nfsdfs_remove_files(root); - inode_unlock(dir); - return -ENOMEM; } /* on success, returns positive number unique to that client. */ @@ -1300,7 +1252,7 @@ struct dentry *nfsd_client_mkdir(struct nfsd_net *nn, dentry = nfsd_mkdir(nn->nfsd_client_dir, ncl, name); if (IS_ERR(dentry)) /* XXX: tossing errors? */ return NULL; - ret = nfsdfs_create_files(dentry, files, fdentries); + ret = nfsdfs_create_files(dentry, files, ncl, fdentries); if (ret) { nfsd_client_rmdir(dentry); return NULL; @@ -1311,20 +1263,7 @@ struct dentry *nfsd_client_mkdir(struct nfsd_net *nn, /* Taken from __rpc_rmdir: */ void nfsd_client_rmdir(struct dentry *dentry) { - struct inode *dir = d_inode(dentry->d_parent); - struct inode *inode = d_inode(dentry); - int ret; - - inode_lock(dir); - nfsdfs_remove_files(dentry); - clear_ncl(inode); - dget(dentry); - ret = simple_rmdir(dir, dentry); - WARN_ON_ONCE(ret); - d_drop(dentry); - fsnotify_rmdir(dir, dentry); - dput(dentry); - inode_unlock(dir); + simple_recursive_removal(dentry, clear_ncl); } static int nfsd_fill_super(struct super_block *sb, struct fs_context *fc) @@ -1353,16 +1292,13 @@ static int nfsd_fill_super(struct super_block *sb, struct fs_context *fc) [NFSD_Versions] = {"versions", &transaction_ops, S_IWUSR|S_IRUSR}, [NFSD_Ports] = {"portlist", &transaction_ops, S_IWUSR|S_IRUGO}, [NFSD_MaxBlkSize] = {"max_block_size", &transaction_ops, S_IWUSR|S_IRUGO}, - [NFSD_MaxConnections] = {"max_connections", &transaction_ops, S_IWUSR|S_IRUGO}, [NFSD_Filecache] = {"filecache", &nfsd_file_cache_stats_fops, S_IRUGO}, -#if defined(CONFIG_SUNRPC_GSS) || defined(CONFIG_SUNRPC_GSS_MODULE) - [NFSD_SupportedEnctypes] = {"supported_krb5_enctypes", - &supported_enctypes_fops, S_IRUGO}, -#endif /* CONFIG_SUNRPC_GSS or CONFIG_SUNRPC_GSS_MODULE */ #ifdef CONFIG_NFSD_V4 [NFSD_Leasetime] = {"nfsv4leasetime", &transaction_ops, S_IWUSR|S_IRUSR}, [NFSD_Gracetime] = {"nfsv4gracetime", &transaction_ops, S_IWUSR|S_IRUSR}, +#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING [NFSD_RecoveryDir] = {"nfsv4recoverydir", &transaction_ops, S_IWUSR|S_IRUSR}, +#endif [NFSD_V4EndGrace] = {"v4_end_grace", &transaction_ops, S_IWUSR|S_IRUGO}, #endif /* last one */ {""} @@ -1371,6 +1307,8 @@ static int nfsd_fill_super(struct super_block *sb, struct fs_context *fc) ret = simple_fill_super(sb, 0x6e667364, nfsd_files); if (ret) return ret; + _nfsd_symlink(sb->s_root, "supported_krb5_enctypes", + "/proc/net/rpc/gss_krb5_enctypes"); dentry = nfsd_mkdir(sb->s_root, NULL, "clients"); if (IS_ERR(dentry)) return PTR_ERR(dentry); @@ -1408,7 +1346,7 @@ static void nfsd_umount(struct super_block *sb) nfsd_shutdown_threads(net); - kill_litter_super(sb); + kill_anon_super(sb); put_net(net); } @@ -1421,6 +1359,19 @@ static struct file_system_type nfsd_fs_type = { MODULE_ALIAS_FS("nfsd"); #ifdef CONFIG_PROC_FS + +static int exports_proc_open(struct inode *inode, struct file *file) +{ + return exports_net_open(current->nsproxy->net_ns, file); +} + +static const struct proc_ops exports_proc_ops = { + .proc_open = exports_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = seq_release, +}; + static int create_proc_exports_entry(void) { struct proc_dir_entry *entry; @@ -1444,10 +1395,755 @@ static int create_proc_exports_entry(void) unsigned int nfsd_net_id; -static __net_init int nfsd_init_net(struct net *net) +static int nfsd_genl_rpc_status_compose_msg(struct sk_buff *skb, + struct netlink_callback *cb, + struct nfsd_genl_rqstp *genl_rqstp) { - int retval; + void *hdr; + u32 i; + + hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + &nfsd_nl_family, 0, NFSD_CMD_RPC_STATUS_GET); + if (!hdr) + return -ENOBUFS; + + if (nla_put_be32(skb, NFSD_A_RPC_STATUS_XID, genl_rqstp->rq_xid) || + nla_put_u32(skb, NFSD_A_RPC_STATUS_FLAGS, genl_rqstp->rq_flags) || + nla_put_u32(skb, NFSD_A_RPC_STATUS_PROG, genl_rqstp->rq_prog) || + nla_put_u32(skb, NFSD_A_RPC_STATUS_PROC, genl_rqstp->rq_proc) || + nla_put_u8(skb, NFSD_A_RPC_STATUS_VERSION, genl_rqstp->rq_vers) || + nla_put_s64(skb, NFSD_A_RPC_STATUS_SERVICE_TIME, + ktime_to_us(genl_rqstp->rq_stime), + NFSD_A_RPC_STATUS_PAD)) + return -ENOBUFS; + + switch (genl_rqstp->rq_saddr.sa_family) { + case AF_INET: { + const struct sockaddr_in *s_in, *d_in; + + s_in = (const struct sockaddr_in *)&genl_rqstp->rq_saddr; + d_in = (const struct sockaddr_in *)&genl_rqstp->rq_daddr; + if (nla_put_in_addr(skb, NFSD_A_RPC_STATUS_SADDR4, + s_in->sin_addr.s_addr) || + nla_put_in_addr(skb, NFSD_A_RPC_STATUS_DADDR4, + d_in->sin_addr.s_addr) || + nla_put_be16(skb, NFSD_A_RPC_STATUS_SPORT, + s_in->sin_port) || + nla_put_be16(skb, NFSD_A_RPC_STATUS_DPORT, + d_in->sin_port)) + return -ENOBUFS; + break; + } + case AF_INET6: { + const struct sockaddr_in6 *s_in, *d_in; + + s_in = (const struct sockaddr_in6 *)&genl_rqstp->rq_saddr; + d_in = (const struct sockaddr_in6 *)&genl_rqstp->rq_daddr; + if (nla_put_in6_addr(skb, NFSD_A_RPC_STATUS_SADDR6, + &s_in->sin6_addr) || + nla_put_in6_addr(skb, NFSD_A_RPC_STATUS_DADDR6, + &d_in->sin6_addr) || + nla_put_be16(skb, NFSD_A_RPC_STATUS_SPORT, + s_in->sin6_port) || + nla_put_be16(skb, NFSD_A_RPC_STATUS_DPORT, + d_in->sin6_port)) + return -ENOBUFS; + break; + } + } + + for (i = 0; i < genl_rqstp->rq_opcnt; i++) + if (nla_put_u32(skb, NFSD_A_RPC_STATUS_COMPOUND_OPS, + genl_rqstp->rq_opnum[i])) + return -ENOBUFS; + + genlmsg_end(skb, hdr); + return 0; +} + +/** + * nfsd_nl_rpc_status_get_dumpit - Handle rpc_status_get dumpit + * @skb: reply buffer + * @cb: netlink metadata and command arguments + * + * Returns the size of the reply or a negative errno. + */ +int nfsd_nl_rpc_status_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) +{ + int i, ret, rqstp_index = 0; + struct nfsd_net *nn; + + mutex_lock(&nfsd_mutex); + + nn = net_generic(sock_net(skb->sk), nfsd_net_id); + if (!nn->nfsd_serv) { + ret = -ENODEV; + goto out_unlock; + } + + rcu_read_lock(); + + for (i = 0; i < nn->nfsd_serv->sv_nrpools; i++) { + struct svc_rqst *rqstp; + + if (i < cb->args[0]) /* already consumed */ + continue; + + rqstp_index = 0; + list_for_each_entry_rcu(rqstp, + &nn->nfsd_serv->sv_pools[i].sp_all_threads, + rq_all) { + struct nfsd_genl_rqstp genl_rqstp; + unsigned int status_counter; + + if (rqstp_index++ < cb->args[1]) /* already consumed */ + continue; + /* + * Acquire rq_status_counter before parsing the rqst + * fields. rq_status_counter is set to an odd value in + * order to notify the consumers the rqstp fields are + * meaningful. + */ + status_counter = + smp_load_acquire(&rqstp->rq_status_counter); + if (!(status_counter & 1)) + continue; + + genl_rqstp.rq_xid = rqstp->rq_xid; + genl_rqstp.rq_flags = rqstp->rq_flags; + genl_rqstp.rq_vers = rqstp->rq_vers; + genl_rqstp.rq_prog = rqstp->rq_prog; + genl_rqstp.rq_proc = rqstp->rq_proc; + genl_rqstp.rq_stime = rqstp->rq_stime; + genl_rqstp.rq_opcnt = 0; + memcpy(&genl_rqstp.rq_daddr, svc_daddr(rqstp), + sizeof(struct sockaddr)); + memcpy(&genl_rqstp.rq_saddr, svc_addr(rqstp), + sizeof(struct sockaddr)); + +#ifdef CONFIG_NFSD_V4 + if (rqstp->rq_vers == NFS4_VERSION && + rqstp->rq_proc == NFSPROC4_COMPOUND) { + /* NFSv4 compound */ + struct nfsd4_compoundargs *args; + int j; + + args = rqstp->rq_argp; + genl_rqstp.rq_opcnt = min_t(u32, args->opcnt, + ARRAY_SIZE(genl_rqstp.rq_opnum)); + for (j = 0; j < genl_rqstp.rq_opcnt; j++) + genl_rqstp.rq_opnum[j] = + args->ops[j].opnum; + } +#endif /* CONFIG_NFSD_V4 */ + + /* + * Acquire rq_status_counter before reporting the rqst + * fields to the user. + */ + if (smp_load_acquire(&rqstp->rq_status_counter) != + status_counter) + continue; + + ret = nfsd_genl_rpc_status_compose_msg(skb, cb, + &genl_rqstp); + if (ret) + goto out; + } + } + + cb->args[0] = i; + cb->args[1] = rqstp_index; + ret = skb->len; +out: + rcu_read_unlock(); +out_unlock: + mutex_unlock(&nfsd_mutex); + + return ret; +} + +/** + * nfsd_nl_threads_set_doit - set the number of running threads + * @skb: reply buffer + * @info: netlink metadata and command arguments + * + * Return 0 on success or a negative errno. + */ +int nfsd_nl_threads_set_doit(struct sk_buff *skb, struct genl_info *info) +{ + int *nthreads, nrpools = 0, i, ret = -EOPNOTSUPP, rem; + struct net *net = genl_info_net(info); + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + const struct nlattr *attr; + const char *scope = NULL; + + if (GENL_REQ_ATTR_CHECK(info, NFSD_A_SERVER_THREADS)) + return -EINVAL; + + /* count number of SERVER_THREADS values */ + nlmsg_for_each_attr_type(attr, NFSD_A_SERVER_THREADS, info->nlhdr, + GENL_HDRLEN, rem) + nrpools++; + + mutex_lock(&nfsd_mutex); + + nthreads = kcalloc(nrpools, sizeof(int), GFP_KERNEL); + if (!nthreads) { + ret = -ENOMEM; + goto out_unlock; + } + + i = 0; + nlmsg_for_each_attr_type(attr, NFSD_A_SERVER_THREADS, info->nlhdr, + GENL_HDRLEN, rem) { + nthreads[i++] = nla_get_u32(attr); + if (i >= nrpools) + break; + } + + if (info->attrs[NFSD_A_SERVER_GRACETIME] || + info->attrs[NFSD_A_SERVER_LEASETIME] || + info->attrs[NFSD_A_SERVER_SCOPE]) { + ret = -EBUSY; + if (nn->nfsd_serv && nn->nfsd_serv->sv_nrthreads) + goto out_unlock; + + ret = -EINVAL; + attr = info->attrs[NFSD_A_SERVER_GRACETIME]; + if (attr) { + u32 gracetime = nla_get_u32(attr); + + if (gracetime < 10 || gracetime > 3600) + goto out_unlock; + + nn->nfsd4_grace = gracetime; + } + + attr = info->attrs[NFSD_A_SERVER_LEASETIME]; + if (attr) { + u32 leasetime = nla_get_u32(attr); + + if (leasetime < 10 || leasetime > 3600) + goto out_unlock; + + nn->nfsd4_lease = leasetime; + } + + attr = info->attrs[NFSD_A_SERVER_SCOPE]; + if (attr) + scope = nla_data(attr); + } + + ret = nfsd_svc(nrpools, nthreads, net, get_current_cred(), scope); + if (ret > 0) + ret = 0; +out_unlock: + mutex_unlock(&nfsd_mutex); + kfree(nthreads); + return ret; +} + +/** + * nfsd_nl_threads_get_doit - get the number of running threads + * @skb: reply buffer + * @info: netlink metadata and command arguments + * + * Return 0 on success or a negative errno. + */ +int nfsd_nl_threads_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct net *net = genl_info_net(info); struct nfsd_net *nn = net_generic(net, nfsd_net_id); + void *hdr; + int err; + + skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!skb) + return -ENOMEM; + + hdr = genlmsg_iput(skb, info); + if (!hdr) { + err = -EMSGSIZE; + goto err_free_msg; + } + + mutex_lock(&nfsd_mutex); + + err = nla_put_u32(skb, NFSD_A_SERVER_GRACETIME, + nn->nfsd4_grace) || + nla_put_u32(skb, NFSD_A_SERVER_LEASETIME, + nn->nfsd4_lease) || + nla_put_string(skb, NFSD_A_SERVER_SCOPE, + nn->nfsd_name); + if (err) + goto err_unlock; + + if (nn->nfsd_serv) { + int i; + + for (i = 0; i < nfsd_nrpools(net); ++i) { + struct svc_pool *sp = &nn->nfsd_serv->sv_pools[i]; + + err = nla_put_u32(skb, NFSD_A_SERVER_THREADS, + sp->sp_nrthreads); + if (err) + goto err_unlock; + } + } else { + err = nla_put_u32(skb, NFSD_A_SERVER_THREADS, 0); + if (err) + goto err_unlock; + } + + mutex_unlock(&nfsd_mutex); + + genlmsg_end(skb, hdr); + + return genlmsg_reply(skb, info); + +err_unlock: + mutex_unlock(&nfsd_mutex); +err_free_msg: + nlmsg_free(skb); + + return err; +} + +/** + * nfsd_nl_version_set_doit - set the nfs enabled versions + * @skb: reply buffer + * @info: netlink metadata and command arguments + * + * Return 0 on success or a negative errno. + */ +int nfsd_nl_version_set_doit(struct sk_buff *skb, struct genl_info *info) +{ + const struct nlattr *attr; + struct nfsd_net *nn; + int i, rem; + + if (GENL_REQ_ATTR_CHECK(info, NFSD_A_SERVER_PROTO_VERSION)) + return -EINVAL; + + mutex_lock(&nfsd_mutex); + + nn = net_generic(genl_info_net(info), nfsd_net_id); + if (nn->nfsd_serv) { + mutex_unlock(&nfsd_mutex); + return -EBUSY; + } + + /* clear current supported versions. */ + nfsd_vers(nn, 2, NFSD_CLEAR); + nfsd_vers(nn, 3, NFSD_CLEAR); + for (i = 0; i <= NFSD_SUPPORTED_MINOR_VERSION; i++) + nfsd_minorversion(nn, i, NFSD_CLEAR); + + nlmsg_for_each_attr_type(attr, NFSD_A_SERVER_PROTO_VERSION, info->nlhdr, + GENL_HDRLEN, rem) { + struct nlattr *tb[NFSD_A_VERSION_MAX + 1]; + u32 major, minor = 0; + bool enabled; + + if (nla_parse_nested(tb, NFSD_A_VERSION_MAX, attr, + nfsd_version_nl_policy, info->extack) < 0) + continue; + + if (!tb[NFSD_A_VERSION_MAJOR]) + continue; + + major = nla_get_u32(tb[NFSD_A_VERSION_MAJOR]); + if (tb[NFSD_A_VERSION_MINOR]) + minor = nla_get_u32(tb[NFSD_A_VERSION_MINOR]); + + enabled = nla_get_flag(tb[NFSD_A_VERSION_ENABLED]); + + switch (major) { + case 4: + nfsd_minorversion(nn, minor, enabled ? NFSD_SET : NFSD_CLEAR); + break; + case 3: + case 2: + if (!minor) + nfsd_vers(nn, major, enabled ? NFSD_SET : NFSD_CLEAR); + break; + default: + break; + } + } + + mutex_unlock(&nfsd_mutex); + + return 0; +} + +/** + * nfsd_nl_version_get_doit - get the enabled status for all supported nfs versions + * @skb: reply buffer + * @info: netlink metadata and command arguments + * + * Return 0 on success or a negative errno. + */ +int nfsd_nl_version_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct nfsd_net *nn; + int i, err; + void *hdr; + + skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!skb) + return -ENOMEM; + + hdr = genlmsg_iput(skb, info); + if (!hdr) { + err = -EMSGSIZE; + goto err_free_msg; + } + + mutex_lock(&nfsd_mutex); + nn = net_generic(genl_info_net(info), nfsd_net_id); + + for (i = 2; i <= 4; i++) { + int j; + + for (j = 0; j <= NFSD_SUPPORTED_MINOR_VERSION; j++) { + struct nlattr *attr; + + /* Don't record any versions the kernel doesn't have + * compiled in + */ + if (!nfsd_support_version(i)) + continue; + + /* NFSv{2,3} does not support minor numbers */ + if (i < 4 && j) + continue; + + attr = nla_nest_start(skb, + NFSD_A_SERVER_PROTO_VERSION); + if (!attr) { + err = -EINVAL; + goto err_nfsd_unlock; + } + + if (nla_put_u32(skb, NFSD_A_VERSION_MAJOR, i) || + nla_put_u32(skb, NFSD_A_VERSION_MINOR, j)) { + err = -EINVAL; + goto err_nfsd_unlock; + } + + /* Set the enabled flag if the version is enabled */ + if (nfsd_vers(nn, i, NFSD_TEST) && + (i < 4 || nfsd_minorversion(nn, j, NFSD_TEST)) && + nla_put_flag(skb, NFSD_A_VERSION_ENABLED)) { + err = -EINVAL; + goto err_nfsd_unlock; + } + + nla_nest_end(skb, attr); + } + } + + mutex_unlock(&nfsd_mutex); + genlmsg_end(skb, hdr); + + return genlmsg_reply(skb, info); + +err_nfsd_unlock: + mutex_unlock(&nfsd_mutex); +err_free_msg: + nlmsg_free(skb); + + return err; +} + +/** + * nfsd_nl_listener_set_doit - set the nfs running sockets + * @skb: reply buffer + * @info: netlink metadata and command arguments + * + * Return 0 on success or a negative errno. + */ +int nfsd_nl_listener_set_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct net *net = genl_info_net(info); + struct svc_xprt *xprt, *tmp; + const struct nlattr *attr; + struct svc_serv *serv; + LIST_HEAD(permsocks); + struct nfsd_net *nn; + bool delete = false; + int err, rem; + + mutex_lock(&nfsd_mutex); + + err = nfsd_create_serv(net); + if (err) { + mutex_unlock(&nfsd_mutex); + return err; + } + + nn = net_generic(net, nfsd_net_id); + serv = nn->nfsd_serv; + + spin_lock_bh(&serv->sv_lock); + + /* Move all of the old listener sockets to a temp list */ + list_splice_init(&serv->sv_permsocks, &permsocks); + + /* + * Walk the list of server_socks from userland and move any that match + * back to sv_permsocks + */ + nlmsg_for_each_attr_type(attr, NFSD_A_SERVER_SOCK_ADDR, info->nlhdr, + GENL_HDRLEN, rem) { + struct nlattr *tb[NFSD_A_SOCK_MAX + 1]; + const char *xcl_name; + struct sockaddr *sa; + + if (nla_parse_nested(tb, NFSD_A_SOCK_MAX, attr, + nfsd_sock_nl_policy, info->extack) < 0) + continue; + + if (!tb[NFSD_A_SOCK_ADDR] || !tb[NFSD_A_SOCK_TRANSPORT_NAME]) + continue; + + if (nla_len(tb[NFSD_A_SOCK_ADDR]) < sizeof(*sa)) + continue; + + xcl_name = nla_data(tb[NFSD_A_SOCK_TRANSPORT_NAME]); + sa = nla_data(tb[NFSD_A_SOCK_ADDR]); + + /* Put back any matching sockets */ + list_for_each_entry_safe(xprt, tmp, &permsocks, xpt_list) { + /* This shouldn't be possible */ + if (WARN_ON_ONCE(xprt->xpt_net != net)) { + list_move(&xprt->xpt_list, &serv->sv_permsocks); + continue; + } + + /* If everything matches, put it back */ + if (!strcmp(xprt->xpt_class->xcl_name, xcl_name) && + rpc_cmp_addr_port(sa, (struct sockaddr *)&xprt->xpt_local)) { + list_move(&xprt->xpt_list, &serv->sv_permsocks); + break; + } + } + } + + /* + * If there are listener transports remaining on the permsocks list, + * it means we were asked to remove a listener. + */ + if (!list_empty(&permsocks)) { + list_splice_init(&permsocks, &serv->sv_permsocks); + delete = true; + } + spin_unlock_bh(&serv->sv_lock); + + /* Do not remove listeners while there are active threads. */ + if (serv->sv_nrthreads) { + err = -EBUSY; + goto out_unlock_mtx; + } + + /* + * Since we can't delete an arbitrary llist entry, destroy the + * remaining listeners and recreate the list. + */ + if (delete) + svc_xprt_destroy_all(serv, net, false); + + /* walk list of addrs again, open any that still don't exist */ + nlmsg_for_each_attr_type(attr, NFSD_A_SERVER_SOCK_ADDR, info->nlhdr, + GENL_HDRLEN, rem) { + struct nlattr *tb[NFSD_A_SOCK_MAX + 1]; + const char *xcl_name; + struct sockaddr *sa; + int ret; + + if (nla_parse_nested(tb, NFSD_A_SOCK_MAX, attr, + nfsd_sock_nl_policy, info->extack) < 0) + continue; + + if (!tb[NFSD_A_SOCK_ADDR] || !tb[NFSD_A_SOCK_TRANSPORT_NAME]) + continue; + + if (nla_len(tb[NFSD_A_SOCK_ADDR]) < sizeof(*sa)) + continue; + + xcl_name = nla_data(tb[NFSD_A_SOCK_TRANSPORT_NAME]); + sa = nla_data(tb[NFSD_A_SOCK_ADDR]); + + xprt = svc_find_listener(serv, xcl_name, net, sa); + if (xprt) { + if (delete) + WARN_ONCE(1, "Transport type=%s already exists\n", + xcl_name); + svc_xprt_put(xprt); + continue; + } + + ret = svc_xprt_create_from_sa(serv, xcl_name, net, sa, 0, + get_current_cred()); + /* always save the latest error */ + if (ret < 0) + err = ret; + } + + if (!serv->sv_nrthreads && list_empty(&nn->nfsd_serv->sv_permsocks)) + nfsd_destroy_serv(net); + +out_unlock_mtx: + mutex_unlock(&nfsd_mutex); + + return err; +} + +/** + * nfsd_nl_listener_get_doit - get the nfs running listeners + * @skb: reply buffer + * @info: netlink metadata and command arguments + * + * Return 0 on success or a negative errno. + */ +int nfsd_nl_listener_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct svc_xprt *xprt; + struct svc_serv *serv; + struct nfsd_net *nn; + void *hdr; + int err; + + skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!skb) + return -ENOMEM; + + hdr = genlmsg_iput(skb, info); + if (!hdr) { + err = -EMSGSIZE; + goto err_free_msg; + } + + mutex_lock(&nfsd_mutex); + nn = net_generic(genl_info_net(info), nfsd_net_id); + + /* no nfs server? Just send empty socket list */ + if (!nn->nfsd_serv) + goto out_unlock_mtx; + + serv = nn->nfsd_serv; + spin_lock_bh(&serv->sv_lock); + list_for_each_entry(xprt, &serv->sv_permsocks, xpt_list) { + struct nlattr *attr; + + attr = nla_nest_start(skb, NFSD_A_SERVER_SOCK_ADDR); + if (!attr) { + err = -EINVAL; + goto err_serv_unlock; + } + + if (nla_put_string(skb, NFSD_A_SOCK_TRANSPORT_NAME, + xprt->xpt_class->xcl_name) || + nla_put(skb, NFSD_A_SOCK_ADDR, + sizeof(struct sockaddr_storage), + &xprt->xpt_local)) { + err = -EINVAL; + goto err_serv_unlock; + } + + nla_nest_end(skb, attr); + } + spin_unlock_bh(&serv->sv_lock); +out_unlock_mtx: + mutex_unlock(&nfsd_mutex); + genlmsg_end(skb, hdr); + + return genlmsg_reply(skb, info); + +err_serv_unlock: + spin_unlock_bh(&serv->sv_lock); + mutex_unlock(&nfsd_mutex); +err_free_msg: + nlmsg_free(skb); + + return err; +} + +/** + * nfsd_nl_pool_mode_set_doit - set the number of running threads + * @skb: reply buffer + * @info: netlink metadata and command arguments + * + * Return 0 on success or a negative errno. + */ +int nfsd_nl_pool_mode_set_doit(struct sk_buff *skb, struct genl_info *info) +{ + const struct nlattr *attr; + + if (GENL_REQ_ATTR_CHECK(info, NFSD_A_POOL_MODE_MODE)) + return -EINVAL; + + attr = info->attrs[NFSD_A_POOL_MODE_MODE]; + return sunrpc_set_pool_mode(nla_data(attr)); +} + +/** + * nfsd_nl_pool_mode_get_doit - get info about pool_mode + * @skb: reply buffer + * @info: netlink metadata and command arguments + * + * Return 0 on success or a negative errno. + */ +int nfsd_nl_pool_mode_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct net *net = genl_info_net(info); + char buf[16]; + void *hdr; + int err; + + if (sunrpc_get_pool_mode(buf, ARRAY_SIZE(buf)) >= ARRAY_SIZE(buf)) + return -ERANGE; + + skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!skb) + return -ENOMEM; + + err = -EMSGSIZE; + hdr = genlmsg_iput(skb, info); + if (!hdr) + goto err_free_msg; + + err = nla_put_string(skb, NFSD_A_POOL_MODE_MODE, buf) | + nla_put_u32(skb, NFSD_A_POOL_MODE_NPOOLS, nfsd_nrpools(net)); + if (err) + goto err_free_msg; + + genlmsg_end(skb, hdr); + return genlmsg_reply(skb, info); + +err_free_msg: + nlmsg_free(skb); + return err; +} + +/** + * nfsd_net_init - Prepare the nfsd_net portion of a new net namespace + * @net: a freshly-created network namespace + * + * This information stays around as long as the network namespace is + * alive whether or not there is an NFSD instance running in the + * namespace. + * + * Returns zero on success, or a negative errno otherwise. + */ +static __net_init int nfsd_net_init(struct net *net) +{ + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + int retval; + int i; retval = nfsd_export_init(net); if (retval) @@ -1455,18 +2151,36 @@ static __net_init int nfsd_init_net(struct net *net) retval = nfsd_idmap_init(net); if (retval) goto out_idmap_error; - nn->nfsd_versions = NULL; - nn->nfsd4_minorversions = NULL; - nfsd4_init_leases_net(nn); - retval = nfsd_reply_cache_init(nn); + retval = percpu_counter_init_many(nn->counter, 0, GFP_KERNEL, + NFSD_STATS_COUNTERS_NUM); if (retval) - goto out_cache_error; + goto out_repcache_error; + + memset(&nn->nfsd_svcstats, 0, sizeof(nn->nfsd_svcstats)); + nn->nfsd_svcstats.program = &nfsd_programs[0]; + if (!nfsd_proc_stat_init(net)) { + retval = -ENOMEM; + goto out_proc_error; + } + + for (i = 0; i < sizeof(nn->nfsd_versions); i++) + nn->nfsd_versions[i] = nfsd_support_version(i); + for (i = 0; i < sizeof(nn->nfsd4_minorversions); i++) + nn->nfsd4_minorversions[i] = nfsd_support_version(4); + nn->nfsd_info.mutex = &nfsd_mutex; + nn->nfsd_serv = NULL; + nfsd4_init_leases_net(nn); get_random_bytes(&nn->siphash_key, sizeof(nn->siphash_key)); seqlock_init(&nn->writeverf_lock); - +#if IS_ENABLED(CONFIG_NFS_LOCALIO) + spin_lock_init(&nn->local_clients_lock); + INIT_LIST_HEAD(&nn->local_clients); +#endif return 0; -out_cache_error: +out_proc_error: + percpu_counter_destroy_many(nn->counter, NFSD_STATS_COUNTERS_NUM); +out_repcache_error: nfsd_idmap_shutdown(net); out_idmap_error: nfsd_export_shutdown(net); @@ -1474,19 +2188,44 @@ out_export_error: return retval; } -static __net_exit void nfsd_exit_net(struct net *net) +#if IS_ENABLED(CONFIG_NFS_LOCALIO) +/** + * nfsd_net_pre_exit - Disconnect localio clients from net namespace + * @net: a network namespace that is about to be destroyed + * + * This invalidates ->net pointers held by localio clients + * while they can still safely access nn->counter. + */ +static __net_exit void nfsd_net_pre_exit(struct net *net) +{ + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + + nfs_localio_invalidate_clients(&nn->local_clients, + &nn->local_clients_lock); +} +#endif + +/** + * nfsd_net_exit - Release the nfsd_net portion of a net namespace + * @net: a network namespace that is about to be destroyed + * + */ +static __net_exit void nfsd_net_exit(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); - nfsd_reply_cache_shutdown(nn); + nfsd_proc_stat_shutdown(net); + percpu_counter_destroy_many(nn->counter, NFSD_STATS_COUNTERS_NUM); nfsd_idmap_shutdown(net); nfsd_export_shutdown(net); - nfsd_netns_free_versions(net_generic(net, nfsd_net_id)); } static struct pernet_operations nfsd_net_ops = { - .init = nfsd_init_net, - .exit = nfsd_exit_net, + .init = nfsd_net_init, +#if IS_ENABLED(CONFIG_NFS_LOCALIO) + .pre_exit = nfsd_net_pre_exit, +#endif + .exit = nfsd_net_exit, .id = &nfsd_net_id, .size = sizeof(struct nfsd_net), }; @@ -1495,25 +2234,21 @@ static int __init init_nfsd(void) { int retval; + nfsd_debugfs_init(); + retval = nfsd4_init_slabs(); if (retval) return retval; retval = nfsd4_init_pnfs(); if (retval) goto out_free_slabs; - retval = nfsd_stat_init(); /* Statistics */ - if (retval) - goto out_free_pnfs; retval = nfsd_drc_slab_create(); if (retval) - goto out_free_stat; + goto out_free_pnfs; nfsd_lockd_init(); /* lockd->nfsd callbacks */ - retval = create_proc_exports_entry(); - if (retval) - goto out_free_lockd; retval = register_pernet_subsys(&nfsd_net_ops); if (retval < 0) - goto out_free_exports; + goto out_free_lockd; retval = register_cld_notifier(); if (retval) goto out_free_subsys; @@ -1522,45 +2257,55 @@ static int __init init_nfsd(void) goto out_free_cld; retval = register_filesystem(&nfsd_fs_type); if (retval) + goto out_free_nfsd4; + retval = genl_register_family(&nfsd_nl_family); + if (retval) + goto out_free_filesystem; + retval = create_proc_exports_entry(); + if (retval) goto out_free_all; + nfsd_localio_ops_init(); + return 0; out_free_all: + genl_unregister_family(&nfsd_nl_family); +out_free_filesystem: + unregister_filesystem(&nfsd_fs_type); +out_free_nfsd4: nfsd4_destroy_laundry_wq(); out_free_cld: unregister_cld_notifier(); out_free_subsys: unregister_pernet_subsys(&nfsd_net_ops); -out_free_exports: - remove_proc_entry("fs/nfs/exports", NULL); - remove_proc_entry("fs/nfs", NULL); out_free_lockd: nfsd_lockd_shutdown(); nfsd_drc_slab_free(); -out_free_stat: - nfsd_stat_shutdown(); out_free_pnfs: nfsd4_exit_pnfs(); out_free_slabs: nfsd4_free_slabs(); + nfsd_debugfs_exit(); return retval; } static void __exit exit_nfsd(void) { + remove_proc_entry("fs/nfs/exports", NULL); + remove_proc_entry("fs/nfs", NULL); + genl_unregister_family(&nfsd_nl_family); unregister_filesystem(&nfsd_fs_type); nfsd4_destroy_laundry_wq(); unregister_cld_notifier(); unregister_pernet_subsys(&nfsd_net_ops); nfsd_drc_slab_free(); - remove_proc_entry("fs/nfs/exports", NULL); - remove_proc_entry("fs/nfs", NULL); - nfsd_stat_shutdown(); nfsd_lockd_shutdown(); nfsd4_free_slabs(); nfsd4_exit_pnfs(); + nfsd_debugfs_exit(); } MODULE_AUTHOR("Olaf Kirch <okir@monad.swb.de>"); +MODULE_DESCRIPTION("In-kernel NFS server"); MODULE_LICENSE("GPL"); module_init(init_nfsd) module_exit(exit_nfsd) diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index fa0144a74267..e4263326ca4a 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -23,9 +23,7 @@ #include <uapi/linux/nfsd/debug.h> -#include "netns.h" #include "export.h" -#include "stats.h" #undef ifdebug #ifdef CONFIG_SUNRPC_DEBUG @@ -37,38 +35,50 @@ /* * nfsd version */ +#define NFSD_MINVERS 2 +#define NFSD_MAXVERS 4 #define NFSD_SUPPORTED_MINOR_VERSION 2 -/* - * Maximum blocksizes supported by daemon under various circumstances. - */ -#define NFSSVC_MAXBLKSIZE RPCSVC_MAXPAYLOAD -/* NFSv2 is limited by the protocol specification, see RFC 1094 */ -#define NFSSVC_MAXBLKSIZE_V2 (8*1024) +bool nfsd_support_version(int vers); +#include "netns.h" +#include "stats.h" /* - * Largest number of bytes we need to allocate for an NFS - * call or reply. Used to control buffer sizes. We use - * the length of v3 WRITE, READDIR and READDIR replies - * which are an RPC header, up to 26 XDR units of reply - * data, and some page data. - * - * Note that accuracy here doesn't matter too much as the - * size is rounded up to a page size when allocating space. + * Default and maximum payload size (NFS READ or WRITE), in bytes. + * The default is historical, and the maximum is an implementation + * limit. */ -#define NFSD_BUFSIZE ((RPC_MAX_HEADER_WITH_AUTH+26)*XDR_UNIT + NFSSVC_MAXBLKSIZE) +enum { + NFSSVC_DEFBLKSIZE = 1 * 1024 * 1024, + NFSSVC_MAXBLKSIZE = RPCSVC_MAXPAYLOAD, +}; struct readdir_cd { __be32 err; /* 0, nfserr, or nfserr_eof */ }; +/* Maximum number of operations per session compound */ +#define NFSD_MAX_OPS_PER_COMPOUND 200 + +struct nfsd_genl_rqstp { + struct sockaddr rq_daddr; + struct sockaddr rq_saddr; + unsigned long rq_flags; + ktime_t rq_stime; + __be32 rq_xid; + u32 rq_vers; + u32 rq_prog; + u32 rq_proc; + + /* NFSv4 compound */ + u32 rq_opcnt; + u32 rq_opnum[16]; +}; -extern struct svc_program nfsd_program; +extern struct svc_program nfsd_programs[]; extern const struct svc_version nfsd_version2, nfsd_version3, nfsd_version4; extern struct mutex nfsd_mutex; -extern spinlock_t nfsd_drc_lock; -extern unsigned long nfsd_drc_max_mem; -extern unsigned long nfsd_drc_mem_used; +extern atomic_t nfsd_th_cnt; /* number of available threads */ extern const struct seq_operations nfs_exports_op; @@ -85,20 +95,17 @@ bool nfssvc_encode_voidres(struct svc_rqst *rqstp, /* * Function prototypes. */ -int nfsd_svc(int nrservs, struct net *net, const struct cred *cred); -int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp); +int nfsd_svc(int n, int *nservers, struct net *net, + const struct cred *cred, const char *scope); +int nfsd_dispatch(struct svc_rqst *rqstp); int nfsd_nrthreads(struct net *); int nfsd_nrpools(struct net *); int nfsd_get_nrthreads(int n, int *, struct net *); int nfsd_set_nrthreads(int n, int *, struct net *); -int nfsd_pool_stats_open(struct inode *, struct file *); -int nfsd_pool_stats_release(struct inode *, struct file *); void nfsd_shutdown_threads(struct net *net); -void nfsd_put(struct net *net); - -bool i_am_nfsd(void); +struct svc_rqst *nfsd_current_rqst(void); struct nfsdfs_client { struct kref cl_ref; @@ -126,6 +133,10 @@ extern const struct svc_version nfsd_acl_version3; #endif #endif +#if IS_ENABLED(CONFIG_NFS_LOCALIO) +extern const struct svc_version localio_version1; +#endif + struct nfsd_net; enum vers_op {NFSD_SET, NFSD_CLEAR, NFSD_TEST, NFSD_AVAIL }; @@ -133,12 +144,33 @@ int nfsd_vers(struct nfsd_net *nn, int vers, enum vers_op change); int nfsd_minorversion(struct nfsd_net *nn, u32 minorversion, enum vers_op change); void nfsd_reset_versions(struct nfsd_net *nn); int nfsd_create_serv(struct net *net); +void nfsd_destroy_serv(struct net *net); + +#ifdef CONFIG_DEBUG_FS +void nfsd_debugfs_init(void); +void nfsd_debugfs_exit(void); +#else +static inline void nfsd_debugfs_init(void) {} +static inline void nfsd_debugfs_exit(void) {} +#endif + +extern bool nfsd_disable_splice_read __read_mostly; + +enum { + /* Any new NFSD_IO enum value must be added at the end */ + NFSD_IO_BUFFERED, + NFSD_IO_DONTCACHE, + NFSD_IO_DIRECT, +}; + +extern u64 nfsd_io_cache_read __read_mostly; +extern u64 nfsd_io_cache_write __read_mostly; extern int nfsd_max_blksize; static inline int nfsd_v4client(struct svc_rqst *rq) { - return rq->rq_prog == NFS_PROGRAM && rq->rq_vers == 4; + return rq && rq->rq_prog == NFS_PROGRAM && rq->rq_vers == 4; } static inline struct user_namespace * nfsd_user_namespace(const struct svc_rqst *rqstp) @@ -213,7 +245,6 @@ void nfsd_lockd_shutdown(void); #define nfserr_nospc cpu_to_be32(NFSERR_NOSPC) #define nfserr_rofs cpu_to_be32(NFSERR_ROFS) #define nfserr_mlink cpu_to_be32(NFSERR_MLINK) -#define nfserr_opnotsupp cpu_to_be32(NFSERR_OPNOTSUPP) #define nfserr_nametoolong cpu_to_be32(NFSERR_NAMETOOLONG) #define nfserr_notempty cpu_to_be32(NFSERR_NOTEMPTY) #define nfserr_dquot cpu_to_be32(NFSERR_DQUOT) @@ -258,9 +289,11 @@ void nfsd_lockd_shutdown(void); #define nfserr_no_grace cpu_to_be32(NFSERR_NO_GRACE) #define nfserr_reclaim_bad cpu_to_be32(NFSERR_RECLAIM_BAD) #define nfserr_badname cpu_to_be32(NFSERR_BADNAME) +#define nfserr_admin_revoked cpu_to_be32(NFS4ERR_ADMIN_REVOKED) #define nfserr_cb_path_down cpu_to_be32(NFSERR_CB_PATH_DOWN) #define nfserr_locked cpu_to_be32(NFSERR_LOCKED) #define nfserr_wrongsec cpu_to_be32(NFSERR_WRONGSEC) +#define nfserr_delay cpu_to_be32(NFS4ERR_DELAY) #define nfserr_badiomode cpu_to_be32(NFS4ERR_BADIOMODE) #define nfserr_badlayout cpu_to_be32(NFS4ERR_BADLAYOUT) #define nfserr_bad_session_digest cpu_to_be32(NFS4ERR_BAD_SESSION_DIGEST) @@ -309,17 +342,30 @@ void nfsd_lockd_shutdown(void); #define nfserr_xattr2big cpu_to_be32(NFS4ERR_XATTR2BIG) #define nfserr_noxattr cpu_to_be32(NFS4ERR_NOXATTR) -/* error codes for internal use */ -/* if a request fails due to kmalloc failure, it gets dropped. - * Client should resend eventually +/* + * Error codes for internal use. We use enum to choose numbers that are + * not already assigned, then covert to be32 resulting in a number that + * cannot conflict with any existing be32 nfserr value. */ -#define nfserr_dropit cpu_to_be32(30000) +enum { /* end-of-file indicator in readdir */ -#define nfserr_eof cpu_to_be32(30001) + NFSERR_EOF = NFS4ERR_FIRST_FREE, +#define nfserr_eof cpu_to_be32(NFSERR_EOF) + /* replay detected */ -#define nfserr_replay_me cpu_to_be32(11001) + NFSERR_REPLAY_ME, +#define nfserr_replay_me cpu_to_be32(NFSERR_REPLAY_ME) + /* nfs41 replay detected */ -#define nfserr_replay_cache cpu_to_be32(11002) + NFSERR_REPLAY_CACHE, +#define nfserr_replay_cache cpu_to_be32(NFSERR_REPLAY_CACHE) + +/* symlink found where dir expected - handled differently to + * other symlink found errors by NFSv3. + */ + NFSERR_SYMLINK_NOT_DIR, +#define nfserr_symlink_not_dir cpu_to_be32(NFSERR_SYMLINK_NOT_DIR) +}; /* Check for dir entries '.' and '..' */ #define isdotent(n, l) (l < 3 && n[0] == '.' && (l == 1 || n[1] == '.')) @@ -349,16 +395,16 @@ void nfsd_lockd_shutdown(void); #define NFSD_CLIENT_MAX_TRIM_PER_RUN 128 #define NFS4_CLIENTS_PER_GB 1024 #define NFSD_DELEGRETURN_TIMEOUT (HZ / 34) /* 30ms */ +#define NFSD_CB_GETATTR_TIMEOUT NFSD_DELEGRETURN_TIMEOUT /* - * The following attributes are currently not supported by the NFSv4 server: + * The following attributes are not implemented by NFSD: * ARCHIVE (deprecated anyway) * HIDDEN (unlikely to be supported any time soon) * MIMETYPE (unlikely to be supported any time soon) * QUOTA_* (will be supported in a forthcoming patch) * SYSTEM (unlikely to be supported any time soon) * TIME_BACKUP (unlikely to be supported any time soon) - * TIME_CREATE (unlikely to be supported any time soon) */ #define NFSD4_SUPPORTED_ATTRS_WORD0 \ (FATTR4_WORD0_SUPPORTED_ATTRS | FATTR4_WORD0_TYPE | FATTR4_WORD0_FH_EXPIRE_TYPE \ @@ -412,8 +458,12 @@ void nfsd_lockd_shutdown(void); #define NFSD4_2_SUPPORTED_ATTRS_WORD2 \ (NFSD4_1_SUPPORTED_ATTRS_WORD2 | \ FATTR4_WORD2_MODE_UMASK | \ + FATTR4_WORD2_CLONE_BLKSIZE | \ NFSD4_2_SECURITY_ATTRS | \ - FATTR4_WORD2_XATTR_SUPPORT) + FATTR4_WORD2_XATTR_SUPPORT | \ + FATTR4_WORD2_TIME_DELEG_ACCESS | \ + FATTR4_WORD2_TIME_DELEG_MODIFY | \ + FATTR4_WORD2_OPEN_ARGUMENTS) extern const u32 nfsd_suppattrs[3][3]; @@ -483,7 +533,10 @@ static inline bool nfsd_attrs_supported(u32 minorversion, const u32 *bmval) #endif #define NFSD_WRITEABLE_ATTRS_WORD2 \ (FATTR4_WORD2_MODE_UMASK \ - | MAYBE_FATTR4_WORD2_SECURITY_LABEL) + | MAYBE_FATTR4_WORD2_SECURITY_LABEL \ + | FATTR4_WORD2_TIME_DELEG_ACCESS \ + | FATTR4_WORD2_TIME_DELEG_MODIFY \ + ) #define NFSD_SUPPATTR_EXCLCREAT_WORD0 \ NFSD_WRITEABLE_ATTRS_WORD0 diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index 8c52b6c9d31a..ed85dd43da18 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -40,7 +40,7 @@ static int nfsd_acceptable(void *expv, struct dentry *dentry) /* make sure parents give x permission to user */ int err; parent = dget_parent(tdentry); - err = inode_permission(&init_user_ns, + err = inode_permission(&nop_mnt_idmap, d_inode(parent), MAY_EXEC); if (err < 0) { dput(parent); @@ -62,8 +62,7 @@ static int nfsd_acceptable(void *expv, struct dentry *dentry) * the write call). */ static inline __be32 -nfsd_mode_check(struct svc_rqst *rqstp, struct dentry *dentry, - umode_t requested) +nfsd_mode_check(struct dentry *dentry, umode_t requested) { umode_t mode = d_inode(dentry)->i_mode & S_IFMT; @@ -76,36 +75,36 @@ nfsd_mode_check(struct svc_rqst *rqstp, struct dentry *dentry, } return nfs_ok; } - /* - * v4 has an error more specific than err_notdir which we should - * return in preference to err_notdir: - */ - if (rqstp->rq_vers == 4 && mode == S_IFLNK) + if (mode == S_IFLNK) { + if (requested == S_IFDIR) + return nfserr_symlink_not_dir; return nfserr_symlink; + } if (requested == S_IFDIR) return nfserr_notdir; if (mode == S_IFDIR) return nfserr_isdir; - return nfserr_inval; + return nfserr_wrong_type; } -static bool nfsd_originating_port_ok(struct svc_rqst *rqstp, int flags) +static bool nfsd_originating_port_ok(struct svc_rqst *rqstp, + struct svc_cred *cred, + struct svc_export *exp) { - if (flags & NFSEXP_INSECURE_PORT) + if (nfsexp_flags(cred, exp) & NFSEXP_INSECURE_PORT) return true; /* We don't require gss requests to use low ports: */ - if (rqstp->rq_cred.cr_flavor >= RPC_AUTH_GSS) + if (cred->cr_flavor >= RPC_AUTH_GSS) return true; return test_bit(RQ_SECURE, &rqstp->rq_flags); } static __be32 nfsd_setuser_and_check_port(struct svc_rqst *rqstp, + struct svc_cred *cred, struct svc_export *exp) { - int flags = nfsexp_flags(rqstp, exp); - /* Check if the request originated from a secure port. */ - if (!nfsd_originating_port_ok(rqstp, flags)) { + if (rqstp && !nfsd_originating_port_ok(rqstp, cred, exp)) { RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]); dprintk("nfsd: request from insecure port %s!\n", svc_print_addr(rqstp, buf, sizeof(buf))); @@ -113,23 +112,15 @@ static __be32 nfsd_setuser_and_check_port(struct svc_rqst *rqstp, } /* Set user creds for this exportpoint */ - return nfserrno(nfsd_setuser(rqstp, exp)); + return nfserrno(nfsd_setuser(cred, exp)); } -static inline __be32 check_pseudo_root(struct svc_rqst *rqstp, - struct dentry *dentry, struct svc_export *exp) +static inline __be32 check_pseudo_root(struct dentry *dentry, + struct svc_export *exp) { if (!(exp->ex_flags & NFSEXP_V4ROOT)) return nfs_ok; /* - * v2/v3 clients have no need for the V4ROOT export--they use - * the mount protocl instead; also, further V4ROOT checks may be - * in v4-specific code, in which case v2/v3 clients could bypass - * them. - */ - if (!nfsd_v4client(rqstp)) - return nfserr_stale; - /* * We're exposing only the directories and symlinks that have to be * traversed on the way to real exports: */ @@ -151,7 +142,11 @@ static inline __be32 check_pseudo_root(struct svc_rqst *rqstp, * dentry. On success, the results are used to set fh_export and * fh_dentry. */ -static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp) +static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct net *net, + struct svc_cred *cred, + struct auth_domain *client, + struct auth_domain *gssclient, + struct svc_fh *fhp) { struct knfsd_fh *fh = &fhp->fh_handle; struct fid *fid = NULL; @@ -162,10 +157,8 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp) int len; __be32 error; - error = nfserr_stale; - if (rqstp->rq_vers > 2) - error = nfserr_badhandle; - if (rqstp->rq_vers == 4 && fh->fh_size == 0) + error = nfserr_badhandle; + if (fh->fh_size == 0) return nfserr_nofilehandle; if (fh->fh_version != 1) @@ -179,6 +172,8 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp) if (len == 0) return error; if (fh->fh_fsid_type == FSID_MAJOR_MINOR) { + u32 *fsid = fh_fsid(fh); + /* deprecated, convert to type 3 */ len = key_len(FSID_ENCODE_DEV)/4; fh->fh_fsid_type = FSID_ENCODE_DEV; @@ -188,15 +183,17 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp) * confuses sparse, so we must use __force here to * keep it from complaining. */ - fh->fh_fsid[0] = new_encode_dev(MKDEV(ntohl((__force __be32)fh->fh_fsid[0]), - ntohl((__force __be32)fh->fh_fsid[1]))); - fh->fh_fsid[1] = fh->fh_fsid[2]; + fsid[0] = new_encode_dev(MKDEV(ntohl((__force __be32)fsid[0]), + ntohl((__force __be32)fsid[1]))); + fsid[1] = fsid[2]; } data_left -= len; if (data_left < 0) return error; - exp = rqst_exp_find(rqstp, fh->fh_fsid_type, fh->fh_fsid); - fid = (struct fid *)(fh->fh_fsid + len); + exp = rqst_exp_find(rqstp ? &rqstp->rq_chandle : NULL, + net, client, gssclient, + fh->fh_fsid_type, fh_fsid(fh)); + fid = (struct fid *)(fh_fsid(fh) + len); error = nfserr_stale; if (IS_ERR(exp)) { @@ -227,9 +224,8 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp) cap_raise_nfsd_set(new->cap_effective, new->cap_permitted); put_cred(override_creds(new)); - put_cred(new); } else { - error = nfsd_setuser_and_check_port(rqstp, exp); + error = nfsd_setuser_and_check_port(rqstp, cred, exp); if (error) goto out; } @@ -237,9 +233,7 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp) /* * Look up the dentry using the NFS file handle. */ - error = nfserr_stale; - if (rqstp->rq_vers > 2) - error = nfserr_badhandle; + error = nfserr_badhandle; fileid_type = fh->fh_fileid_type; @@ -247,7 +241,7 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp) dentry = dget(exp->ex_path.dentry); else { dentry = exportfs_decode_fh_raw(exp->ex_path.mnt, fid, - data_left, fileid_type, + data_left, fileid_type, 0, nfsd_acceptable, exp); if (IS_ERR_OR_NULL(dentry)) { trace_nfsd_set_fh_dentry_badhandle(rqstp, fhp, @@ -275,22 +269,30 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp) dentry); } - fhp->fh_dentry = dentry; - fhp->fh_export = exp; - - switch (rqstp->rq_vers) { - case 4: + switch (fhp->fh_maxsize) { + case NFS4_FHSIZE: if (dentry->d_sb->s_export_op->flags & EXPORT_OP_NOATOMIC_ATTR) fhp->fh_no_atomic_attr = true; + fhp->fh_64bit_cookies = true; break; - case 3: + case NFS3_FHSIZE: if (dentry->d_sb->s_export_op->flags & EXPORT_OP_NOWCC) fhp->fh_no_wcc = true; + fhp->fh_64bit_cookies = true; + if (exp->ex_flags & NFSEXP_V4ROOT) + goto out; break; - case 2: + case NFS_FHSIZE: fhp->fh_no_wcc = true; + if (EX_WGATHER(exp)) + fhp->fh_use_wgather = true; + if (exp->ex_flags & NFSEXP_V4ROOT) + goto out; } + fhp->fh_dentry = dentry; + fhp->fh_export = exp; + return 0; out: exp_put(exp); @@ -298,41 +300,34 @@ out: } /** - * fh_verify - filehandle lookup and access checking - * @rqstp: pointer to current rpc request + * __fh_verify - filehandle lookup and access checking + * @rqstp: RPC transaction context, or NULL + * @net: net namespace in which to perform the export lookup + * @cred: RPC user credential + * @client: RPC auth domain + * @gssclient: RPC GSS auth domain, or NULL * @fhp: filehandle to be verified * @type: expected type of object pointed to by filehandle * @access: type of access needed to object * - * Look up a dentry from the on-the-wire filehandle, check the client's - * access to the export, and set the current task's credentials. - * - * Regardless of success or failure of fh_verify(), fh_put() should be - * called on @fhp when the caller is finished with the filehandle. - * - * fh_verify() may be called multiple times on a given filehandle, for - * example, when processing an NFSv4 compound. The first call will look - * up a dentry using the on-the-wire filehandle. Subsequent calls will - * skip the lookup and just perform the other checks and possibly change - * the current task's credentials. - * - * @type specifies the type of object expected using one of the S_IF* - * constants defined in include/linux/stat.h. The caller may use zero - * to indicate that it doesn't care, or a negative integer to indicate - * that it expects something not of the given type. - * - * @access is formed from the NFSD_MAY_* constants defined in - * fs/nfsd/vfs.h. + * See fh_verify() for further descriptions of @fhp, @type, and @access. */ -__be32 -fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int access) +static __be32 +__fh_verify(struct svc_rqst *rqstp, + struct net *net, struct svc_cred *cred, + struct auth_domain *client, + struct auth_domain *gssclient, + struct svc_fh *fhp, umode_t type, int access) { + struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct svc_export *exp = NULL; + bool may_bypass_gss = false; struct dentry *dentry; __be32 error; if (!fhp->fh_dentry) { - error = nfsd_set_fh_dentry(rqstp, fhp); + error = nfsd_set_fh_dentry(rqstp, net, cred, client, + gssclient, fhp); if (error) goto out; } @@ -357,25 +352,44 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int access) * (for example, if different id-squashing options are in * effect on the new filesystem). */ - error = check_pseudo_root(rqstp, dentry, exp); + error = check_pseudo_root(dentry, exp); if (error) goto out; - error = nfsd_setuser_and_check_port(rqstp, exp); + error = nfsd_setuser_and_check_port(rqstp, cred, exp); if (error) goto out; - error = nfsd_mode_check(rqstp, dentry, type); + error = nfsd_mode_check(dentry, type); if (error) goto out; /* - * pseudoflavor restrictions are not enforced on NLM, - * which clients virtually always use auth_sys for, - * even while using RPCSEC_GSS for NFS. + * If rqstp is NULL, this is a LOCALIO request which will only + * ever use a filehandle/credential pair for which access has + * been affirmed (by ACCESS or OPEN NFS requests) over the + * wire. Skip both the xprtsec policy and the security flavor + * checks. + */ + if (!rqstp) + goto check_permissions; + + if ((access & NFSD_MAY_NLM) && (exp->ex_flags & NFSEXP_NOAUTHNLM)) + /* NLM is allowed to fully bypass authentication */ + goto out; + + /* + * NLM is allowed to bypass the xprtsec policy check because lockd + * doesn't support xprtsec. */ - if (access & NFSD_MAY_LOCK || access & NFSD_MAY_BYPASS_GSS) - goto skip_pseudoflavor_check; + if (!(access & NFSD_MAY_NLM)) { + error = check_xprtsec_policy(exp, rqstp); + if (error) + goto out; + } + + if (access & NFSD_MAY_BYPASS_GSS) + may_bypass_gss = true; /* * Clients may expect to be able to use auth_sys during mount, * even if they use gss for everything else; see section 2.3.2 @@ -383,22 +397,81 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int access) */ if (access & NFSD_MAY_BYPASS_GSS_ON_ROOT && exp->ex_path.dentry == dentry) - goto skip_pseudoflavor_check; + may_bypass_gss = true; - error = check_nfsd_access(exp, rqstp); + error = check_security_flavor(exp, rqstp, may_bypass_gss); if (error) goto out; -skip_pseudoflavor_check: + svc_xprt_set_valid(rqstp->rq_xprt); + +check_permissions: /* Finally, check access permissions. */ - error = nfsd_permission(rqstp, exp, dentry, access); + error = nfsd_permission(cred, exp, dentry, access); out: trace_nfsd_fh_verify_err(rqstp, fhp, type, access, error); if (error == nfserr_stale) - nfsd_stats_fh_stale_inc(exp); + nfsd_stats_fh_stale_inc(nn, exp); return error; } +/** + * fh_verify_local - filehandle lookup and access checking + * @net: net namespace in which to perform the export lookup + * @cred: RPC user credential + * @client: RPC auth domain + * @fhp: filehandle to be verified + * @type: expected type of object pointed to by filehandle + * @access: type of access needed to object + * + * This API can be used by callers who do not have an RPC + * transaction context (ie are not running in an nfsd thread). + * + * See fh_verify() for further descriptions of @fhp, @type, and @access. + */ +__be32 +fh_verify_local(struct net *net, struct svc_cred *cred, + struct auth_domain *client, struct svc_fh *fhp, + umode_t type, int access) +{ + return __fh_verify(NULL, net, cred, client, NULL, + fhp, type, access); +} + +/** + * fh_verify - filehandle lookup and access checking + * @rqstp: pointer to current rpc request + * @fhp: filehandle to be verified + * @type: expected type of object pointed to by filehandle + * @access: type of access needed to object + * + * Look up a dentry from the on-the-wire filehandle, check the client's + * access to the export, and set the current task's credentials. + * + * Regardless of success or failure of fh_verify(), fh_put() should be + * called on @fhp when the caller is finished with the filehandle. + * + * fh_verify() may be called multiple times on a given filehandle, for + * example, when processing an NFSv4 compound. The first call will look + * up a dentry using the on-the-wire filehandle. Subsequent calls will + * skip the lookup and just perform the other checks and possibly change + * the current task's credentials. + * + * @type specifies the type of object expected using one of the S_IF* + * constants defined in include/linux/stat.h. The caller may use zero + * to indicate that it doesn't care, or a negative integer to indicate + * that it expects something not of the given type. + * + * @access is formed from the NFSD_MAY_* constants defined in + * fs/nfsd/vfs.h. + */ +__be32 +fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int access) +{ + return __fh_verify(rqstp, SVC_NET(rqstp), &rqstp->rq_cred, + rqstp->rq_client, rqstp->rq_gssclient, + fhp, type, access); +} /* * Compose a file handle for an NFS reply. @@ -412,12 +485,15 @@ static void _fh_update(struct svc_fh *fhp, struct svc_export *exp, { if (dentry != exp->ex_path.dentry) { struct fid *fid = (struct fid *) - (fhp->fh_handle.fh_fsid + fhp->fh_handle.fh_size/4 - 1); + (fh_fsid(&fhp->fh_handle) + fhp->fh_handle.fh_size/4 - 1); int maxsize = (fhp->fh_maxsize - fhp->fh_handle.fh_size)/4; - int subtreecheck = !(exp->ex_flags & NFSEXP_NOSUBTREECHECK); + int fh_flags = (exp->ex_flags & NFSEXP_NOSUBTREECHECK) ? 0 : + EXPORT_FH_CONNECTABLE; + int fileid_type = + exportfs_encode_fh(dentry, fid, &maxsize, fh_flags); fhp->fh_handle.fh_fileid_type = - exportfs_encode_fh(dentry, fid, &maxsize, subtreecheck); + fileid_type > 0 ? fileid_type : FILEID_INVALID; fhp->fh_handle.fh_size += maxsize * 4; } else { fhp->fh_handle.fh_fileid_type = FILEID_ROOT; @@ -560,7 +636,7 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry, fhp->fh_handle.fh_auth_type = 0; mk_fsid(fhp->fh_handle.fh_fsid_type, - fhp->fh_handle.fh_fsid, + fh_fsid(&fhp->fh_handle), ex_dev, d_inode(exp->ex_path.dentry)->i_ino, exp->ex_fsid, exp->ex_uuid); @@ -569,7 +645,7 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry, _fh_update(fhp, exp, dentry); if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID) { fh_put(fhp); - return nfserr_opnotsupp; + return nfserr_stale; } return 0; @@ -595,7 +671,7 @@ fh_update(struct svc_fh *fhp) _fh_update(fhp, fhp->fh_export, dentry); if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID) - return nfserr_opnotsupp; + return nfserr_stale; return 0; out_bad: printk(KERN_ERR "fh_update: fh not verified!\n"); @@ -607,35 +683,58 @@ out_negative: } /** + * fh_getattr - Retrieve attributes on a local file + * @fhp: File handle of target file + * @stat: Caller-supplied kstat buffer to be filled in + * + * Returns nfs_ok on success, otherwise an NFS status code is + * returned. + */ +__be32 fh_getattr(const struct svc_fh *fhp, struct kstat *stat) +{ + struct path p = { + .mnt = fhp->fh_export->ex_path.mnt, + .dentry = fhp->fh_dentry, + }; + struct inode *inode = d_inode(p.dentry); + u32 request_mask = STATX_BASIC_STATS; + + if (S_ISREG(inode->i_mode)) + request_mask |= (STATX_DIOALIGN | STATX_DIO_READ_ALIGN); + + if (fhp->fh_maxsize == NFS4_FHSIZE) + request_mask |= (STATX_BTIME | STATX_CHANGE_COOKIE); + + return nfserrno(vfs_getattr(&p, stat, request_mask, + AT_STATX_SYNC_AS_STAT)); +} + +/** * fh_fill_pre_attrs - Fill in pre-op attributes * @fhp: file handle to be updated * */ -void fh_fill_pre_attrs(struct svc_fh *fhp) +__be32 __must_check fh_fill_pre_attrs(struct svc_fh *fhp) { bool v4 = (fhp->fh_maxsize == NFS4_FHSIZE); - struct inode *inode; struct kstat stat; __be32 err; if (fhp->fh_no_wcc || fhp->fh_pre_saved) - return; + return nfs_ok; - inode = d_inode(fhp->fh_dentry); err = fh_getattr(fhp, &stat); - if (err) { - /* Grab the times from inode anyway */ - stat.mtime = inode->i_mtime; - stat.ctime = inode->i_ctime; - stat.size = inode->i_size; - } + if (err) + return err; + if (v4) - fhp->fh_pre_change = nfsd4_change_attribute(&stat, inode); + fhp->fh_pre_change = nfsd4_change_attribute(&stat); fhp->fh_pre_mtime = stat.mtime; fhp->fh_pre_ctime = stat.ctime; fhp->fh_pre_size = stat.size; fhp->fh_pre_saved = true; + return nfs_ok; } /** @@ -643,27 +742,26 @@ void fh_fill_pre_attrs(struct svc_fh *fhp) * @fhp: file handle to be updated * */ -void fh_fill_post_attrs(struct svc_fh *fhp) +__be32 fh_fill_post_attrs(struct svc_fh *fhp) { bool v4 = (fhp->fh_maxsize == NFS4_FHSIZE); - struct inode *inode = d_inode(fhp->fh_dentry); __be32 err; if (fhp->fh_no_wcc) - return; + return nfs_ok; if (fhp->fh_post_saved) printk("nfsd: inode locked twice during operation.\n"); err = fh_getattr(fhp, &fhp->fh_post_attr); - if (err) { - fhp->fh_post_saved = false; - fhp->fh_post_attr.ctime = inode->i_ctime; - } else - fhp->fh_post_saved = true; + if (err) + return err; + + fhp->fh_post_saved = true; if (v4) fhp->fh_post_change = - nfsd4_change_attribute(&fhp->fh_post_attr, inode); + nfsd4_change_attribute(&fhp->fh_post_attr); + return nfs_ok; } /** @@ -673,16 +771,20 @@ void fh_fill_post_attrs(struct svc_fh *fhp) * This is used when the directory wasn't changed, but wcc attributes * are needed anyway. */ -void fh_fill_both_attrs(struct svc_fh *fhp) +__be32 __must_check fh_fill_both_attrs(struct svc_fh *fhp) { - fh_fill_post_attrs(fhp); - if (!fhp->fh_post_saved) - return; + __be32 err; + + err = fh_fill_post_attrs(fhp); + if (err) + return err; + fhp->fh_pre_change = fhp->fh_post_change; fhp->fh_pre_mtime = fhp->fh_post_attr.mtime; fhp->fh_pre_ctime = fhp->fh_post_attr.ctime; fhp->fh_pre_size = fhp->fh_post_attr.size; fhp->fh_pre_saved = true; + return nfs_ok; } /* @@ -715,7 +817,7 @@ char * SVCFH_fmt(struct svc_fh *fhp) struct knfsd_fh *fh = &fhp->fh_handle; static char buf[2+1+1+64*3+1]; - if (fh->fh_size < 0 || fh->fh_size> 64) + if (fh->fh_size > 64) return "bad-fh"; sprintf(buf, "%d: %*ph", fh->fh_size, fh->fh_size, fh->fh_raw); return buf; @@ -748,3 +850,44 @@ enum fsid_source fsid_source(const struct svc_fh *fhp) return FSIDSOURCE_UUID; return FSIDSOURCE_DEV; } + +/** + * nfsd4_change_attribute - Generate an NFSv4 change_attribute value + * @stat: inode attributes + * + * Caller must fill in @stat before calling, typically by invoking + * vfs_getattr() with STATX_MODE, STATX_CTIME, and STATX_CHANGE_COOKIE. + * Returns an unsigned 64-bit changeid4 value (RFC 8881 Section 3.2). + * + * We could use i_version alone as the change attribute. However, i_version + * can go backwards on a regular file after an unclean shutdown. On its own + * that doesn't necessarily cause a problem, but if i_version goes backwards + * and then is incremented again it could reuse a value that was previously + * used before boot, and a client who queried the two values might incorrectly + * assume nothing changed. + * + * By using both ctime and the i_version counter we guarantee that as long as + * time doesn't go backwards we never reuse an old value. If the filesystem + * advertises STATX_ATTR_CHANGE_MONOTONIC, then this mitigation is not + * needed. + * + * We only need to do this for regular files as well. For directories, we + * assume that the new change attr is always logged to stable storage in some + * fashion before the results can be seen. + */ +u64 nfsd4_change_attribute(const struct kstat *stat) +{ + u64 chattr; + + if (stat->result_mask & STATX_CHANGE_COOKIE) { + chattr = stat->change_cookie; + if (S_ISREG(stat->mode) && + !(stat->attributes & STATX_ATTR_CHANGE_MONOTONIC)) { + chattr += (u64)stat->ctime.tv_sec << 30; + chattr += stat->ctime.tv_nsec; + } + } else { + chattr = time_to_chattr(&stat->ctime); + } + return chattr; +} diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h index 513e028b0bbe..5ef7191f8ad8 100644 --- a/fs/nfsd/nfsfh.h +++ b/fs/nfsd/nfsfh.h @@ -14,6 +14,8 @@ #include <linux/exportfs.h> #include <linux/nfs4.h> +#include "export.h" + /* * The file handle starts with a sequence of four-byte words. * The first word contains a version number (1) and three descriptor bytes @@ -49,18 +51,19 @@ struct knfsd_fh { * Points to the current size while * building a new file handle. */ - union { - char fh_raw[NFS4_FHSIZE]; - struct { - u8 fh_version; /* == 1 */ - u8 fh_auth_type; /* deprecated */ - u8 fh_fsid_type; - u8 fh_fileid_type; - u32 fh_fsid[]; /* flexible-array member */ - }; - }; + u8 fh_raw[NFS4_FHSIZE]; }; +#define fh_version fh_raw[0] +#define fh_auth_type fh_raw[1] +#define fh_fsid_type fh_raw[2] +#define fh_fileid_type fh_raw[3] + +static inline u32 *fh_fsid(const struct knfsd_fh *fh) +{ + return (u32 *)&fh->fh_raw[4]; +} + static inline __u32 ino_t_to_u32(ino_t ino) { return (__u32) ino; @@ -88,6 +91,8 @@ typedef struct svc_fh { * wcc data is not atomic with * operation */ + bool fh_use_wgather; /* NFSv2 wgather option */ + bool fh_64bit_cookies;/* readdir cookie size */ int fh_flags; /* FH flags */ bool fh_post_saved; /* post-op attrs saved */ bool fh_pre_saved; /* pre-op attrs saved */ @@ -215,6 +220,9 @@ extern char * SVCFH_fmt(struct svc_fh *fhp); * Function prototypes */ __be32 fh_verify(struct svc_rqst *, struct svc_fh *, umode_t, int); +__be32 fh_verify_local(struct net *, struct svc_cred *, struct auth_domain *, + struct svc_fh *, umode_t, int); +__be32 fh_getattr(const struct svc_fh *fhp, struct kstat *stat); __be32 fh_compose(struct svc_fh *, struct svc_export *, struct dentry *, struct svc_fh *); __be32 fh_update(struct svc_fh *); void fh_put(struct svc_fh *); @@ -256,14 +264,51 @@ static inline bool fh_match(const struct knfsd_fh *fh1, static inline bool fh_fsid_match(const struct knfsd_fh *fh1, const struct knfsd_fh *fh2) { + u32 *fsid1 = fh_fsid(fh1); + u32 *fsid2 = fh_fsid(fh2); + if (fh1->fh_fsid_type != fh2->fh_fsid_type) return false; - if (memcmp(fh1->fh_fsid, fh2->fh_fsid, key_len(fh1->fh_fsid_type)) != 0) + if (memcmp(fsid1, fsid2, key_len(fh1->fh_fsid_type)) != 0) return false; return true; } -#ifdef CONFIG_CRC32 +/** + * fh_want_write - Get write access to an export + * @fhp: File handle of file to be written + * + * Caller must invoke fh_drop_write() when its write operation + * is complete. + * + * Returns 0 if the file handle's export can be written to. Otherwise + * the export is not prepared for updates, and the returned negative + * errno value reflects the reason for the failure. + */ +static inline int fh_want_write(struct svc_fh *fhp) +{ + int ret; + + if (fhp->fh_want_write) + return 0; + ret = mnt_want_write(fhp->fh_export->ex_path.mnt); + if (!ret) + fhp->fh_want_write = true; + return ret; +} + +/** + * fh_drop_write - Release write access on an export + * @fhp: File handle of file on which fh_want_write() was previously called + */ +static inline void fh_drop_write(struct svc_fh *fhp) +{ + if (fhp->fh_want_write) { + fhp->fh_want_write = false; + mnt_drop_write(fhp->fh_export->ex_path.mnt); + } +} + /** * knfsd_fh_hash - calculate the crc32 hash for the filehandle * @fh - pointer to filehandle @@ -275,12 +320,6 @@ static inline u32 knfsd_fh_hash(const struct knfsd_fh *fh) { return ~crc32_le(0xFFFFFFFF, fh->fh_raw, fh->fh_size); } -#else -static inline u32 knfsd_fh_hash(const struct knfsd_fh *fh) -{ - return 0; -} -#endif /** * fh_clear_pre_post_attrs - Reset pre/post attributes @@ -293,35 +332,8 @@ static inline void fh_clear_pre_post_attrs(struct svc_fh *fhp) fhp->fh_pre_saved = false; } -/* - * We could use i_version alone as the change attribute. However, - * i_version can go backwards after a reboot. On its own that doesn't - * necessarily cause a problem, but if i_version goes backwards and then - * is incremented again it could reuse a value that was previously used - * before boot, and a client who queried the two values might - * incorrectly assume nothing changed. - * - * By using both ctime and the i_version counter we guarantee that as - * long as time doesn't go backwards we never reuse an old value. - */ -static inline u64 nfsd4_change_attribute(struct kstat *stat, - struct inode *inode) -{ - if (inode->i_sb->s_export_op->fetch_iversion) - return inode->i_sb->s_export_op->fetch_iversion(inode); - else if (IS_I_VERSION(inode)) { - u64 chattr; - - chattr = stat->ctime.tv_sec; - chattr <<= 30; - chattr += stat->ctime.tv_nsec; - chattr += inode_query_iversion(inode); - return chattr; - } else - return time_to_chattr(&stat->ctime); -} - -extern void fh_fill_pre_attrs(struct svc_fh *fhp); -extern void fh_fill_post_attrs(struct svc_fh *fhp); -extern void fh_fill_both_attrs(struct svc_fh *fhp); +u64 nfsd4_change_attribute(const struct kstat *stat); +__be32 __must_check fh_fill_pre_attrs(struct svc_fh *fhp); +__be32 fh_fill_post_attrs(struct svc_fh *fhp); +__be32 __must_check fh_fill_both_attrs(struct svc_fh *fhp); #endif /* _LINUX_NFSD_NFSFH_H */ diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index 9744443c3965..481e789a7697 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -10,9 +10,35 @@ #include "cache.h" #include "xdr.h" #include "vfs.h" +#include "trace.h" #define NFSDDBG_FACILITY NFSDDBG_PROC +static __be32 nfsd_map_status(__be32 status) +{ + switch (status) { + case nfs_ok: + break; + case nfserr_nofilehandle: + case nfserr_badhandle: + status = nfserr_stale; + break; + case nfserr_wrongsec: + case nfserr_xdev: + case nfserr_file_open: + status = nfserr_acces; + break; + case nfserr_symlink_not_dir: + status = nfserr_notdir; + break; + case nfserr_symlink: + case nfserr_wrong_type: + status = nfserr_inval; + break; + } + return status; +} + static __be32 nfsd_proc_null(struct svc_rqst *rqstp) { @@ -29,7 +55,7 @@ nfsd_proc_getattr(struct svc_rqst *rqstp) struct nfsd_fhandle *argp = rqstp->rq_argp; struct nfsd_attrstat *resp = rqstp->rq_resp; - dprintk("nfsd: GETATTR %s\n", SVCFH_fmt(&argp->fh)); + trace_nfsd_vfs_getattr(rqstp, &argp->fh); fh_copy(&resp->fh, &argp->fh); resp->status = fh_verify(rqstp, &resp->fh, 0, @@ -38,6 +64,7 @@ nfsd_proc_getattr(struct svc_rqst *rqstp) goto out; resp->status = fh_getattr(&resp->fh, &resp->stat); out: + resp->status = nfsd_map_status(resp->status); return rpc_success; } @@ -93,7 +120,7 @@ nfsd_proc_setattr(struct svc_rqst *rqstp) if (delta < 0) delta = -delta; if (delta < MAX_TOUCH_TIME_ERROR && - setattr_prepare(&init_user_ns, fhp->fh_dentry, iap) != 0) { + setattr_prepare(&nop_mnt_idmap, fhp->fh_dentry, iap) != 0) { /* * Turn off ATTR_[AM]TIME_SET but leave ATTR_[AM]TIME. * This will cause notify_change to set these times @@ -103,12 +130,13 @@ nfsd_proc_setattr(struct svc_rqst *rqstp) } } - resp->status = nfsd_setattr(rqstp, fhp, &attrs, 0, (time64_t)0); + resp->status = nfsd_setattr(rqstp, fhp, &attrs, NULL); if (resp->status != nfs_ok) goto out; resp->status = fh_getattr(&resp->fh, &resp->stat); out: + resp->status = nfsd_map_status(resp->status); return rpc_success; } @@ -143,6 +171,7 @@ nfsd_proc_lookup(struct svc_rqst *rqstp) resp->status = fh_getattr(&resp->fh, &resp->stat); out: + resp->status = nfsd_map_status(resp->status); return rpc_success; } @@ -164,6 +193,7 @@ nfsd_proc_readlink(struct svc_rqst *rqstp) page_address(resp->page), &resp->len); fh_put(&argp->fh); + resp->status = nfsd_map_status(resp->status); return rpc_success; } @@ -176,28 +206,16 @@ nfsd_proc_read(struct svc_rqst *rqstp) { struct nfsd_readargs *argp = rqstp->rq_argp; struct nfsd_readres *resp = rqstp->rq_resp; - unsigned int len; u32 eof; - int v; dprintk("nfsd: READ %s %d bytes at %d\n", SVCFH_fmt(&argp->fh), argp->count, argp->offset); - argp->count = min_t(u32, argp->count, NFSSVC_MAXBLKSIZE_V2); + argp->count = min_t(u32, argp->count, NFS_MAXDATA); argp->count = min_t(u32, argp->count, rqstp->rq_res.buflen); - v = 0; - len = argp->count; resp->pages = rqstp->rq_next_page; - while (len > 0) { - struct page *page = *(rqstp->rq_next_page++); - - rqstp->rq_vec[v].iov_base = page_address(page); - rqstp->rq_vec[v].iov_len = min_t(unsigned int, len, PAGE_SIZE); - len -= rqstp->rq_vec[v].iov_len; - v++; - } /* Obtain buffer pointer for payload. 19 is 1 word for * status, 17 words for fattr, and 1 word for the byte count. @@ -207,11 +225,12 @@ nfsd_proc_read(struct svc_rqst *rqstp) resp->count = argp->count; fh_copy(&resp->fh, &argp->fh); resp->status = nfsd_read(rqstp, &resp->fh, argp->offset, - rqstp->rq_vec, v, &resp->count, &eof); + &resp->count, &eof); if (resp->status == nfs_ok) resp->status = fh_getattr(&resp->fh, &resp->stat); else if (resp->status == nfserr_jukebox) set_bit(RQ_DROPME, &rqstp->rq_flags); + resp->status = nfsd_map_status(resp->status); return rpc_success; } @@ -232,21 +251,19 @@ nfsd_proc_write(struct svc_rqst *rqstp) struct nfsd_writeargs *argp = rqstp->rq_argp; struct nfsd_attrstat *resp = rqstp->rq_resp; unsigned long cnt = argp->len; - unsigned int nvecs; dprintk("nfsd: WRITE %s %u bytes at %d\n", SVCFH_fmt(&argp->fh), argp->len, argp->offset); - nvecs = svc_fill_write_vector(rqstp, &argp->payload); - - resp->status = nfsd_write(rqstp, fh_copy(&resp->fh, &argp->fh), - argp->offset, rqstp->rq_vec, nvecs, - &cnt, NFS_DATA_SYNC, NULL); + fh_copy(&resp->fh, &argp->fh); + resp->status = nfsd_write(rqstp, &resp->fh, argp->offset, + &argp->payload, &cnt, NFS_DATA_SYNC, NULL); if (resp->status == nfs_ok) resp->status = fh_getattr(&resp->fh, &resp->stat); else if (resp->status == nfserr_jukebox) set_bit(RQ_DROPME, &rqstp->rq_flags); + resp->status = nfsd_map_status(resp->status); return rpc_success; } @@ -273,9 +290,6 @@ nfsd_proc_create(struct svc_rqst *rqstp) int hosterr; dev_t rdev = 0, wanted = new_decode_dev(attr->ia_size); - dprintk("nfsd: CREATE %s %.*s\n", - SVCFH_fmt(dirfhp), argp->len, argp->name); - /* First verify the parent file handle */ resp->status = fh_verify(rqstp, dirfhp, S_IFDIR, NFSD_MAY_EXEC); if (resp->status != nfs_ok) @@ -292,17 +306,16 @@ nfsd_proc_create(struct svc_rqst *rqstp) goto done; } - inode_lock_nested(dirfhp->fh_dentry->d_inode, I_MUTEX_PARENT); - dchild = lookup_one_len(argp->name, dirfhp->fh_dentry, argp->len); + dchild = start_creating(&nop_mnt_idmap, dirfhp->fh_dentry, + &QSTR_LEN(argp->name, argp->len)); if (IS_ERR(dchild)) { resp->status = nfserrno(PTR_ERR(dchild)); - goto out_unlock; + goto out_write; } fh_init(newfhp, NFS_FHSIZE); resp->status = fh_compose(newfhp, dirfhp->fh_export, dchild, dirfhp); if (!resp->status && d_really_is_negative(dchild)) resp->status = nfserr_noent; - dput(dchild); if (resp->status) { if (resp->status != nfserr_noent) goto out_unlock; @@ -312,7 +325,7 @@ nfsd_proc_create(struct svc_rqst *rqstp) */ resp->status = nfserr_acces; if (!newfhp->fh_dentry) { - printk(KERN_WARNING + printk(KERN_WARNING "nfsd_proc_create: file handle not verified\n"); goto out_unlock; } @@ -343,10 +356,11 @@ nfsd_proc_create(struct svc_rqst *rqstp) * echo thing > device-special-file-or-pipe * by doing a CREATE with type==0 */ - resp->status = nfsd_permission(rqstp, - newfhp->fh_export, - newfhp->fh_dentry, - NFSD_MAY_WRITE|NFSD_MAY_LOCAL_ACCESS); + resp->status = nfsd_permission( + &rqstp->rq_cred, + newfhp->fh_export, + newfhp->fh_dentry, + NFSD_MAY_WRITE|NFSD_MAY_LOCAL_ACCESS); if (resp->status && resp->status != nfserr_rofs) goto out_unlock; } @@ -393,6 +407,9 @@ nfsd_proc_create(struct svc_rqst *rqstp) /* File doesn't exist. Create it and set attrs */ resp->status = nfsd_create_locked(rqstp, dirfhp, &attrs, type, rdev, newfhp); + /* nfsd_create_locked() unlocked the parent */ + dput(dchild); + goto out_write; } else if (type == S_IFREG) { dprintk("nfsd: existing %s, valid=%x, size=%ld\n", argp->name, attr->ia_valid, (long) attr->ia_size); @@ -402,12 +419,13 @@ nfsd_proc_create(struct svc_rqst *rqstp) */ attr->ia_valid &= ATTR_SIZE; if (attr->ia_valid) - resp->status = nfsd_setattr(rqstp, newfhp, &attrs, 0, - (time64_t)0); + resp->status = nfsd_setattr(rqstp, newfhp, &attrs, + NULL); } out_unlock: - inode_unlock(dirfhp->fh_dentry->d_inode); + end_creating(dchild); +out_write: fh_drop_write(dirfhp); done: fh_put(dirfhp); @@ -415,6 +433,7 @@ done: goto out; resp->status = fh_getattr(&resp->fh, &resp->stat); out: + resp->status = nfsd_map_status(resp->status); return rpc_success; } @@ -424,13 +443,11 @@ nfsd_proc_remove(struct svc_rqst *rqstp) struct nfsd_diropargs *argp = rqstp->rq_argp; struct nfsd_stat *resp = rqstp->rq_resp; - dprintk("nfsd: REMOVE %s %.*s\n", SVCFH_fmt(&argp->fh), - argp->len, argp->name); - /* Unlink. -SIFDIR means file must not be a directory */ resp->status = nfsd_unlink(rqstp, &argp->fh, -S_IFDIR, argp->name, argp->len); fh_put(&argp->fh); + resp->status = nfsd_map_status(resp->status); return rpc_success; } @@ -440,15 +457,11 @@ nfsd_proc_rename(struct svc_rqst *rqstp) struct nfsd_renameargs *argp = rqstp->rq_argp; struct nfsd_stat *resp = rqstp->rq_resp; - dprintk("nfsd: RENAME %s %.*s -> \n", - SVCFH_fmt(&argp->ffh), argp->flen, argp->fname); - dprintk("nfsd: -> %s %.*s\n", - SVCFH_fmt(&argp->tfh), argp->tlen, argp->tname); - resp->status = nfsd_rename(rqstp, &argp->ffh, argp->fname, argp->flen, &argp->tfh, argp->tname, argp->tlen); fh_put(&argp->ffh); fh_put(&argp->tfh); + resp->status = nfsd_map_status(resp->status); return rpc_success; } @@ -458,17 +471,11 @@ nfsd_proc_link(struct svc_rqst *rqstp) struct nfsd_linkargs *argp = rqstp->rq_argp; struct nfsd_stat *resp = rqstp->rq_resp; - dprintk("nfsd: LINK %s ->\n", - SVCFH_fmt(&argp->ffh)); - dprintk("nfsd: %s %.*s\n", - SVCFH_fmt(&argp->tfh), - argp->tlen, - argp->tname); - resp->status = nfsd_link(rqstp, &argp->tfh, argp->tname, argp->tlen, &argp->ffh); fh_put(&argp->ffh); fh_put(&argp->tfh); + resp->status = nfsd_map_status(resp->status); return rpc_success; } @@ -495,10 +502,6 @@ nfsd_proc_symlink(struct svc_rqst *rqstp) goto out; } - dprintk("nfsd: SYMLINK %s %.*s -> %.*s\n", - SVCFH_fmt(&argp->ffh), argp->flen, argp->fname, - argp->tlen, argp->tname); - fh_init(&newfh, NFS_FHSIZE); resp->status = nfsd_symlink(rqstp, &argp->ffh, argp->fname, argp->flen, argp->tname, &attrs, &newfh); @@ -507,6 +510,7 @@ nfsd_proc_symlink(struct svc_rqst *rqstp) fh_put(&argp->ffh); fh_put(&newfh); out: + resp->status = nfsd_map_status(resp->status); return rpc_success; } @@ -523,8 +527,6 @@ nfsd_proc_mkdir(struct svc_rqst *rqstp) .na_iattr = &argp->attrs, }; - dprintk("nfsd: MKDIR %s %.*s\n", SVCFH_fmt(&argp->fh), argp->len, argp->name); - if (resp->fh.fh_dentry) { printk(KERN_WARNING "nfsd_proc_mkdir: response already verified??\n"); @@ -540,6 +542,7 @@ nfsd_proc_mkdir(struct svc_rqst *rqstp) resp->status = fh_getattr(&resp->fh, &resp->stat); out: + resp->status = nfsd_map_status(resp->status); return rpc_success; } @@ -552,11 +555,10 @@ nfsd_proc_rmdir(struct svc_rqst *rqstp) struct nfsd_diropargs *argp = rqstp->rq_argp; struct nfsd_stat *resp = rqstp->rq_resp; - dprintk("nfsd: RMDIR %s %.*s\n", SVCFH_fmt(&argp->fh), argp->len, argp->name); - resp->status = nfsd_unlink(rqstp, &argp->fh, S_IFDIR, argp->name, argp->len); fh_put(&argp->fh); + resp->status = nfsd_map_status(resp->status); return rpc_success; } @@ -575,7 +577,7 @@ static void nfsd_init_dirlist_pages(struct svc_rqst *rqstp, buf->pages = rqstp->rq_next_page; rqstp->rq_next_page++; - xdr_init_encode_pages(xdr, buf, buf->pages, NULL); + xdr_init_encode_pages(xdr, buf); } /* @@ -588,9 +590,7 @@ nfsd_proc_readdir(struct svc_rqst *rqstp) struct nfsd_readdirres *resp = rqstp->rq_resp; loff_t offset; - dprintk("nfsd: READDIR %s %d bytes at %d\n", - SVCFH_fmt(&argp->fh), - argp->count, argp->cookie); + trace_nfsd_vfs_readdir(rqstp, &argp->fh, argp->count, argp->cookie); nfsd_init_dirlist_pages(rqstp, resp, argp->count); @@ -602,6 +602,7 @@ nfsd_proc_readdir(struct svc_rqst *rqstp) nfssvc_encode_nfscookie(resp, offset); fh_put(&argp->fh); + resp->status = nfsd_map_status(resp->status); return rpc_success; } @@ -614,11 +615,10 @@ nfsd_proc_statfs(struct svc_rqst *rqstp) struct nfsd_fhandle *argp = rqstp->rq_argp; struct nfsd_statfsres *resp = rqstp->rq_resp; - dprintk("nfsd: STATFS %s\n", SVCFH_fmt(&argp->fh)); - resp->status = nfsd_statfs(rqstp, &argp->fh, &resp->stats, NFSD_MAY_BYPASS_GSS_ON_ROOT); fh_put(&argp->fh); + resp->status = nfsd_map_status(resp->status); return rpc_success; } @@ -710,7 +710,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_argzero = sizeof(struct nfsd_readargs), .pc_ressize = sizeof(struct nfsd_readres), .pc_cachetype = RC_NOCACHE, - .pc_xdrressize = ST+AT+1+NFSSVC_MAXBLKSIZE_V2/4, + .pc_xdrressize = ST+AT+1+NFS_MAXDATA/4, .pc_name = "READ", }, [NFSPROC_WRITECACHE] = { @@ -838,11 +838,11 @@ static const struct svc_procedure nfsd_procedures2[18] = { }, }; - -static unsigned int nfsd_count2[ARRAY_SIZE(nfsd_procedures2)]; +static DEFINE_PER_CPU_ALIGNED(unsigned long, + nfsd_count2[ARRAY_SIZE(nfsd_procedures2)]); const struct svc_version nfsd_version2 = { .vs_vers = 2, - .vs_nproc = 18, + .vs_nproc = ARRAY_SIZE(nfsd_procedures2), .vs_proc = nfsd_procedures2, .vs_count = nfsd_count2, .vs_dispatch = nfsd_dispatch, diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 325d3d3f1211..b08ae85d53ef 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -19,6 +19,7 @@ #include <linux/sunrpc/svc_xprt.h> #include <linux/lockd/bind.h> #include <linux/nfsacl.h> +#include <linux/nfslocalio.h> #include <linux/seq_file.h> #include <linux/inetdevice.h> #include <net/addrconf.h> @@ -34,7 +35,7 @@ #define NFSDDBG_FACILITY NFSDDBG_SVC -extern struct svc_program nfsd_program; +atomic_t nfsd_th_cnt = ATOMIC_INIT(0); static int nfsd(void *vrqstp); #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) static int nfsd_acl_rpcbind_set(struct net *, @@ -59,15 +60,6 @@ static __be32 nfsd_init_request(struct svc_rqst *, * nfsd_mutex protects nn->nfsd_serv -- both the pointer itself and some members * of the svc_serv struct such as ->sv_temp_socks and ->sv_permsocks. * - * If (out side the lock) nn->nfsd_serv is non-NULL, then it must point to a - * properly initialised 'struct svc_serv' with ->sv_nrthreads > 0 (unless - * nn->keep_active is set). That number of nfsd threads must - * exist and each must be listed in ->sp_all_threads in some entry of - * ->sv_pools[]. - * - * Each active thread holds a counted reference on nn->nfsd_serv, as does - * the nn->keep_active flag and various transient calls to svc_get(). - * * Finally, the nfsd_mutex also protects some of the global variables that are * accessed when nfsd starts and that are settable via the write_* routines in * nfsctl.c. In particular: @@ -78,18 +70,16 @@ static __be32 nfsd_init_request(struct svc_rqst *, */ DEFINE_MUTEX(nfsd_mutex); -/* - * nfsd_drc_lock protects nfsd_drc_max_pages and nfsd_drc_pages_used. - * nfsd_drc_max_pages limits the total amount of memory available for - * version 4.1 DRC caches. - * nfsd_drc_pages_used tracks the current version 4.1 DRC memory usage. - */ -DEFINE_SPINLOCK(nfsd_drc_lock); -unsigned long nfsd_drc_max_mem; -unsigned long nfsd_drc_mem_used; +#if IS_ENABLED(CONFIG_NFS_LOCALIO) +static const struct svc_version *localio_versions[] = { + [1] = &localio_version1, +}; + +#define NFSD_LOCALIO_NRVERS ARRAY_SIZE(localio_versions) + +#endif /* CONFIG_NFS_LOCALIO */ #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) -static struct svc_stat nfsd_acl_svcstats; static const struct svc_version *nfsd_acl_version[] = { # if defined(CONFIG_NFSD_V2_ACL) [2] = &nfsd_acl_version2, @@ -99,27 +89,12 @@ static const struct svc_version *nfsd_acl_version[] = { # endif }; -#define NFSD_ACL_MINVERS 2 +#define NFSD_ACL_MINVERS 2 #define NFSD_ACL_NRVERS ARRAY_SIZE(nfsd_acl_version) -static struct svc_program nfsd_acl_program = { - .pg_prog = NFS_ACL_PROGRAM, - .pg_nvers = NFSD_ACL_NRVERS, - .pg_vers = nfsd_acl_version, - .pg_name = "nfsacl", - .pg_class = "nfsd", - .pg_stats = &nfsd_acl_svcstats, - .pg_authenticate = &svc_set_client, - .pg_init_request = nfsd_acl_init_request, - .pg_rpcbind_set = nfsd_acl_rpcbind_set, -}; - -static struct svc_stat nfsd_acl_svcstats = { - .program = &nfsd_acl_program, -}; #endif /* defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) */ -static const struct svc_version *nfsd_version[] = { +static const struct svc_version *nfsd_version[NFSD_MAXVERS+1] = { #if defined(CONFIG_NFSD_V2) [2] = &nfsd_version2, #endif @@ -129,99 +104,63 @@ static const struct svc_version *nfsd_version[] = { #endif }; -#define NFSD_MINVERS 2 -#define NFSD_NRVERS ARRAY_SIZE(nfsd_version) - -struct svc_program nfsd_program = { -#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) - .pg_next = &nfsd_acl_program, -#endif +struct svc_program nfsd_programs[] = { + { .pg_prog = NFS_PROGRAM, /* program number */ - .pg_nvers = NFSD_NRVERS, /* nr of entries in nfsd_version */ + .pg_nvers = NFSD_MAXVERS+1, /* nr of entries in nfsd_version */ .pg_vers = nfsd_version, /* version table */ .pg_name = "nfsd", /* program name */ .pg_class = "nfsd", /* authentication class */ - .pg_stats = &nfsd_svcstats, /* version table */ - .pg_authenticate = &svc_set_client, /* export authentication */ + .pg_authenticate = svc_set_client, /* export authentication */ .pg_init_request = nfsd_init_request, .pg_rpcbind_set = nfsd_rpcbind_set, + }, +#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) + { + .pg_prog = NFS_ACL_PROGRAM, + .pg_nvers = NFSD_ACL_NRVERS, + .pg_vers = nfsd_acl_version, + .pg_name = "nfsacl", + .pg_class = "nfsd", + .pg_authenticate = svc_set_client, + .pg_init_request = nfsd_acl_init_request, + .pg_rpcbind_set = nfsd_acl_rpcbind_set, + }, +#endif /* defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) */ +#if IS_ENABLED(CONFIG_NFS_LOCALIO) + { + .pg_prog = NFS_LOCALIO_PROGRAM, + .pg_nvers = NFSD_LOCALIO_NRVERS, + .pg_vers = localio_versions, + .pg_name = "nfslocalio", + .pg_class = "nfsd", + .pg_authenticate = svc_set_client, + .pg_init_request = svc_generic_init_request, + .pg_rpcbind_set = svc_generic_rpcbind_set, + } +#endif /* CONFIG_NFS_LOCALIO */ }; -static bool -nfsd_support_version(int vers) +bool nfsd_support_version(int vers) { - if (vers >= NFSD_MINVERS && vers < NFSD_NRVERS) + if (vers >= NFSD_MINVERS && vers <= NFSD_MAXVERS) return nfsd_version[vers] != NULL; return false; } -static bool * -nfsd_alloc_versions(void) -{ - bool *vers = kmalloc_array(NFSD_NRVERS, sizeof(bool), GFP_KERNEL); - unsigned i; - - if (vers) { - /* All compiled versions are enabled by default */ - for (i = 0; i < NFSD_NRVERS; i++) - vers[i] = nfsd_support_version(i); - } - return vers; -} - -static bool * -nfsd_alloc_minorversions(void) -{ - bool *vers = kmalloc_array(NFSD_SUPPORTED_MINOR_VERSION + 1, - sizeof(bool), GFP_KERNEL); - unsigned i; - - if (vers) { - /* All minor versions are enabled by default */ - for (i = 0; i <= NFSD_SUPPORTED_MINOR_VERSION; i++) - vers[i] = nfsd_support_version(4); - } - return vers; -} - -void -nfsd_netns_free_versions(struct nfsd_net *nn) -{ - kfree(nn->nfsd_versions); - kfree(nn->nfsd4_minorversions); - nn->nfsd_versions = NULL; - nn->nfsd4_minorversions = NULL; -} - -static void -nfsd_netns_init_versions(struct nfsd_net *nn) -{ - if (!nn->nfsd_versions) { - nn->nfsd_versions = nfsd_alloc_versions(); - nn->nfsd4_minorversions = nfsd_alloc_minorversions(); - if (!nn->nfsd_versions || !nn->nfsd4_minorversions) - nfsd_netns_free_versions(nn); - } -} - int nfsd_vers(struct nfsd_net *nn, int vers, enum vers_op change) { - if (vers < NFSD_MINVERS || vers >= NFSD_NRVERS) + if (vers < NFSD_MINVERS || vers > NFSD_MAXVERS) return 0; switch(change) { case NFSD_SET: - if (nn->nfsd_versions) - nn->nfsd_versions[vers] = nfsd_support_version(vers); + nn->nfsd_versions[vers] = nfsd_support_version(vers); break; case NFSD_CLEAR: - nfsd_netns_init_versions(nn); - if (nn->nfsd_versions) - nn->nfsd_versions[vers] = false; + nn->nfsd_versions[vers] = false; break; case NFSD_TEST: - if (nn->nfsd_versions) - return nn->nfsd_versions[vers]; - fallthrough; + return nn->nfsd_versions[vers]; case NFSD_AVAIL: return nfsd_support_version(vers); } @@ -248,23 +187,16 @@ int nfsd_minorversion(struct nfsd_net *nn, u32 minorversion, enum vers_op change switch(change) { case NFSD_SET: - if (nn->nfsd4_minorversions) { - nfsd_vers(nn, 4, NFSD_SET); - nn->nfsd4_minorversions[minorversion] = - nfsd_vers(nn, 4, NFSD_TEST); - } + nfsd_vers(nn, 4, NFSD_SET); + nn->nfsd4_minorversions[minorversion] = + nfsd_vers(nn, 4, NFSD_TEST); break; case NFSD_CLEAR: - nfsd_netns_init_versions(nn); - if (nn->nfsd4_minorversions) { - nn->nfsd4_minorversions[minorversion] = false; - nfsd_adjust_nfsd_versions4(nn); - } + nn->nfsd4_minorversions[minorversion] = false; + nfsd_adjust_nfsd_versions4(nn); break; case NFSD_TEST: - if (nn->nfsd4_minorversions) - return nn->nfsd4_minorversions[minorversion]; - return nfsd_vers(nn, 4, NFSD_TEST); + return nn->nfsd4_minorversions[minorversion]; case NFSD_AVAIL: return minorversion <= NFSD_SUPPORTED_MINOR_VERSION && nfsd_vers(nn, 4, NFSD_AVAIL); @@ -272,6 +204,34 @@ int nfsd_minorversion(struct nfsd_net *nn, u32 minorversion, enum vers_op change return 0; } +bool nfsd_net_try_get(struct net *net) __must_hold(rcu) +{ + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + + return (nn && percpu_ref_tryget_live(&nn->nfsd_net_ref)); +} + +void nfsd_net_put(struct net *net) __must_hold(rcu) +{ + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + + percpu_ref_put(&nn->nfsd_net_ref); +} + +static void nfsd_net_done(struct percpu_ref *ref) +{ + struct nfsd_net *nn = container_of(ref, struct nfsd_net, nfsd_net_ref); + + complete(&nn->nfsd_net_confirm_done); +} + +static void nfsd_net_free(struct percpu_ref *ref) +{ + struct nfsd_net *nn = container_of(ref, struct nfsd_net, nfsd_net_ref); + + complete(&nn->nfsd_net_free_done); +} + /* * Maximum number of nfsd processes */ @@ -289,27 +249,6 @@ int nfsd_nrthreads(struct net *net) return rv; } -static int nfsd_init_socks(struct net *net, const struct cred *cred) -{ - int error; - struct nfsd_net *nn = net_generic(net, nfsd_net_id); - - if (!list_empty(&nn->nfsd_serv->sv_permsocks)) - return 0; - - error = svc_xprt_create(nn->nfsd_serv, "udp", net, PF_INET, NFS_PORT, - SVC_SOCK_DEFAULTS, cred); - if (error < 0) - return error; - - error = svc_xprt_create(nn->nfsd_serv, "tcp", net, PF_INET, NFS_PORT, - SVC_SOCK_DEFAULTS, cred); - if (error < 0) - return error; - - return 0; -} - static int nfsd_users = 0; static int nfsd_startup_generic(void) @@ -359,13 +298,12 @@ static bool nfsd_needs_lockd(struct nfsd_net *nn) */ void nfsd_copy_write_verifier(__be32 verf[2], struct nfsd_net *nn) { - int seq = 0; + unsigned int seq; do { - read_seqbegin_or_lock(&nn->writeverf_lock, &seq); - memcpy(verf, nn->writeverf, sizeof(*verf)); - } while (need_seqretry(&nn->writeverf_lock, seq)); - done_seqretry(&nn->writeverf_lock, seq); + seq = read_seqbegin(&nn->writeverf_lock); + memcpy(verf, nn->writeverf, sizeof(nn->writeverf)); + } while (read_seqretry(&nn->writeverf_lock, seq)); } static void nfsd_reset_write_verifier_locked(struct nfsd_net *nn) @@ -402,6 +340,11 @@ void nfsd_reset_write_verifier(struct nfsd_net *nn) write_sequnlock(&nn->writeverf_lock); } +/* + * Crank up a set of per-namespace resources for a new NFSD instance, + * including lockd, a duplicate reply cache, an open file cache + * instance, and a cache of NFSv4 state objects. + */ static int nfsd_startup_net(struct net *net, const struct cred *cred) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); @@ -413,9 +356,12 @@ static int nfsd_startup_net(struct net *net, const struct cred *cred) ret = nfsd_startup_generic(); if (ret) return ret; - ret = nfsd_init_socks(net, cred); - if (ret) + + if (list_empty(&nn->nfsd_serv->sv_permsocks)) { + pr_warn("NFSD: Failed to start, no listeners configured.\n"); + ret = -EIO; goto out_socks; + } if (nfsd_needs_lockd(nn) && !nn->lockd_up) { ret = lockd_up(net, cred); @@ -427,16 +373,23 @@ static int nfsd_startup_net(struct net *net, const struct cred *cred) ret = nfsd_file_cache_start_net(net); if (ret) goto out_lockd; - ret = nfs4_state_start_net(net); + + ret = nfsd_reply_cache_init(nn); if (ret) goto out_filecache; #ifdef CONFIG_NFSD_V4_2_INTER_SSC nfsd4_ssc_init_umount_work(nn); #endif + ret = nfs4_state_start_net(net); + if (ret) + goto out_reply_cache; + nn->nfsd_net_up = true; return 0; +out_reply_cache: + nfsd_reply_cache_shutdown(nn); out_filecache: nfsd_file_cache_shutdown_net(net); out_lockd: @@ -453,12 +406,24 @@ static void nfsd_shutdown_net(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); + if (!nn->nfsd_net_up) + return; + + percpu_ref_kill_and_confirm(&nn->nfsd_net_ref, nfsd_net_done); + wait_for_completion(&nn->nfsd_net_confirm_done); + + nfsd_export_flush(net); nfs4_state_shutdown_net(net); + nfsd_reply_cache_shutdown(nn); nfsd_file_cache_shutdown_net(net); if (nn->lockd_up) { lockd_down(net); nn->lockd_up = false; } + + wait_for_completion(&nn->nfsd_net_free_done); + percpu_ref_exit(&nn->nfsd_net_ref); + nn->nfsd_net_up = false; nfsd_shutdown_generic(); } @@ -529,9 +494,20 @@ static struct notifier_block nfsd_inet6addr_notifier = { /* Only used under nfsd_mutex, so this atomic may be overkill: */ static atomic_t nfsd_notifier_refcount = ATOMIC_INIT(0); -static void nfsd_last_thread(struct svc_serv *serv, struct net *net) +/** + * nfsd_destroy_serv - tear down NFSD's svc_serv for a namespace + * @net: network namespace the NFS service is associated with + */ +void nfsd_destroy_serv(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct svc_serv *serv = nn->nfsd_serv; + + lockdep_assert_held(&nfsd_mutex); + + spin_lock(&nfsd_notifier_lock); + nn->nfsd_serv = NULL; + spin_unlock(&nfsd_notifier_lock); /* check if the notifier still has clients */ if (atomic_dec_return(&nfsd_notifier_refcount) == 0) { @@ -543,28 +519,24 @@ static void nfsd_last_thread(struct svc_serv *serv, struct net *net) /* * write_ports can create the server without actually starting - * any threads--if we get shut down before any threads are - * started, then nfsd_last_thread will be run before any of this + * any threads. If we get shut down before any threads are + * started, then nfsd_destroy_serv will be run before any of this * other initialization has been done except the rpcb information. */ - svc_rpcb_cleanup(serv, net); - if (!nn->nfsd_net_up) - return; - + svc_xprt_destroy_all(serv, net, true); nfsd_shutdown_net(net); - pr_info("nfsd: last server has exited, flushing export cache\n"); - nfsd_export_flush(net); + svc_destroy(&serv); } void nfsd_reset_versions(struct nfsd_net *nn) { int i; - for (i = 0; i < NFSD_NRVERS; i++) + for (i = 0; i <= NFSD_MAXVERS; i++) if (nfsd_vers(nn, i, NFSD_TEST)) return; - for (i = 0; i < NFSD_NRVERS; i++) + for (i = 0; i <= NFSD_MAXVERS; i++) if (i != 4) nfsd_vers(nn, i, NFSD_SET); else { @@ -574,27 +546,6 @@ void nfsd_reset_versions(struct nfsd_net *nn) } } -/* - * Each session guarantees a negotiated per slot memory cache for replies - * which in turn consumes memory beyond the v2/v3/v4.0 server. A dedicated - * NFSv4.1 server might want to use more memory for a DRC than a machine - * with mutiple services. - * - * Impose a hard limit on the number of pages for the DRC which varies - * according to the machines free pages. This is of course only a default. - * - * For now this is a #defined shift which could be under admin control - * in the future. - */ -static void set_max_drc(void) -{ - #define NFSD_DRC_SIZE_SHIFT 7 - nfsd_drc_max_mem = (nr_free_buffer_pages() - >> NFSD_DRC_SIZE_SHIFT) * PAGE_SIZE; - nfsd_drc_mem_used = 0; - dprintk("%s nfsd_drc_max_mem %lu \n", __func__, nfsd_drc_max_mem); -} - static int nfsd_get_default_max_blksize(void) { struct sysinfo i; @@ -610,7 +561,7 @@ static int nfsd_get_default_max_blksize(void) */ target >>= 12; - ret = NFSSVC_MAXBLKSIZE; + ret = NFSSVC_DEFBLKSIZE; while (ret > target && ret >= 8*1024*2) ret /= 2; return ret; @@ -628,16 +579,17 @@ void nfsd_shutdown_threads(struct net *net) return; } - svc_get(serv); /* Kill outstanding nfsd threads */ svc_set_num_threads(serv, NULL, 0); - nfsd_put(net); + nfsd_destroy_serv(net); mutex_unlock(&nfsd_mutex); } -bool i_am_nfsd(void) +struct svc_rqst *nfsd_current_rqst(void) { - return kthread_func(current) == nfsd; + if (kthread_func(current) == nfsd) + return kthread_data(current); + return NULL; } int nfsd_create_serv(struct net *net) @@ -647,31 +599,34 @@ int nfsd_create_serv(struct net *net) struct svc_serv *serv; WARN_ON(!mutex_is_locked(&nfsd_mutex)); - if (nn->nfsd_serv) { - svc_get(nn->nfsd_serv); + if (nn->nfsd_serv) return 0; - } + + error = percpu_ref_init(&nn->nfsd_net_ref, nfsd_net_free, + 0, GFP_KERNEL); + if (error) + return error; + init_completion(&nn->nfsd_net_free_done); + init_completion(&nn->nfsd_net_confirm_done); + if (nfsd_max_blksize == 0) nfsd_max_blksize = nfsd_get_default_max_blksize(); nfsd_reset_versions(nn); - serv = svc_create_pooled(&nfsd_program, nfsd_max_blksize, nfsd); + serv = svc_create_pooled(nfsd_programs, ARRAY_SIZE(nfsd_programs), + &nn->nfsd_svcstats, + nfsd_max_blksize, nfsd); if (serv == NULL) return -ENOMEM; - serv->sv_maxconn = nn->max_connections; error = svc_bind(serv, net); if (error < 0) { - /* NOT nfsd_put() as notifiers (see below) haven't - * been set up yet. - */ - svc_put(serv); + svc_destroy(&serv); return error; } spin_lock(&nfsd_notifier_lock); nn->nfsd_serv = serv; spin_unlock(&nfsd_notifier_lock); - set_max_drc(); /* check if the notifier is already set */ if (atomic_inc_return(&nfsd_notifier_refcount) == 1) { register_inetaddr_notifier(&nfsd_inetaddr_notifier); @@ -695,40 +650,29 @@ int nfsd_nrpools(struct net *net) int nfsd_get_nrthreads(int n, int *nthreads, struct net *net) { - int i = 0; struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct svc_serv *serv = nn->nfsd_serv; + int i; - if (nn->nfsd_serv != NULL) { - for (i = 0; i < nn->nfsd_serv->sv_nrpools && i < n; i++) - nthreads[i] = nn->nfsd_serv->sv_pools[i].sp_nrthreads; - } - + if (serv) + for (i = 0; i < serv->sv_nrpools && i < n; i++) + nthreads[i] = serv->sv_pools[i].sp_nrthreads; return 0; } -/* This is the callback for kref_put() below. - * There is no code here as the first thing to be done is - * call svc_shutdown_net(), but we cannot get the 'net' from - * the kref. So do all the work when kref_put returns true. +/** + * nfsd_set_nrthreads - set the number of running threads in the net's service + * @n: number of array members in @nthreads + * @nthreads: array of thread counts for each pool + * @net: network namespace to operate within + * + * This function alters the number of running threads for the given network + * namespace in each pool. If passed an array longer then the number of pools + * the extra pool settings are ignored. If passed an array shorter than the + * number of pools, the missing values are interpreted as 0's. + * + * Returns 0 on success or a negative errno on error. */ -static void nfsd_noop(struct kref *ref) -{ -} - -void nfsd_put(struct net *net) -{ - struct nfsd_net *nn = net_generic(net, nfsd_net_id); - - if (kref_put(&nn->nfsd_serv->sv_refcnt, nfsd_noop)) { - svc_xprt_destroy_all(nn->nfsd_serv, net); - nfsd_last_thread(nn->nfsd_serv, net); - svc_destroy(&nn->nfsd_serv->sv_refcnt); - spin_lock(&nfsd_notifier_lock); - nn->nfsd_serv = NULL; - spin_unlock(&nfsd_notifier_lock); - } -} - int nfsd_set_nrthreads(int n, int *nthreads, struct net *net) { int i = 0; @@ -736,11 +680,18 @@ int nfsd_set_nrthreads(int n, int *nthreads, struct net *net) int err = 0; struct nfsd_net *nn = net_generic(net, nfsd_net_id); - WARN_ON(!mutex_is_locked(&nfsd_mutex)); + lockdep_assert_held(&nfsd_mutex); if (nn->nfsd_serv == NULL || n <= 0) return 0; + /* + * Special case: When n == 1, pass in NULL for the pool, so that the + * change is distributed equally among them. + */ + if (n == 1) + return svc_set_num_threads(nn->nfsd_serv, NULL, nthreads[0]); + if (n > nn->nfsd_serv->sv_nrpools) n = nn->nfsd_serv->sv_nrpools; @@ -763,74 +714,68 @@ int nfsd_set_nrthreads(int n, int *nthreads, struct net *net) } } - /* - * There must always be a thread in pool 0; the admin - * can't shut down NFS completely using pool_threads. - */ - if (nthreads[0] == 0) - nthreads[0] = 1; - /* apply the new numbers */ - svc_get(nn->nfsd_serv); for (i = 0; i < n; i++) { err = svc_set_num_threads(nn->nfsd_serv, &nn->nfsd_serv->sv_pools[i], nthreads[i]); if (err) - break; + goto out; + } + + /* Anything undefined in array is considered to be 0 */ + for (i = n; i < nn->nfsd_serv->sv_nrpools; ++i) { + err = svc_set_num_threads(nn->nfsd_serv, + &nn->nfsd_serv->sv_pools[i], + 0); + if (err) + goto out; } - nfsd_put(net); +out: return err; } -/* - * Adjust the number of threads and return the new number of threads. - * This is also the function that starts the server if necessary, if - * this is the first time nrservs is nonzero. +/** + * nfsd_svc: start up or shut down the nfsd server + * @n: number of array members in @nthreads + * @nthreads: array of thread counts for each pool + * @net: network namespace to operate within + * @cred: credentials to use for xprt creation + * @scope: server scope value (defaults to nodename) + * + * Adjust the number of threads in each pool and return the new + * total number of threads in the service. */ int -nfsd_svc(int nrservs, struct net *net, const struct cred *cred) +nfsd_svc(int n, int *nthreads, struct net *net, const struct cred *cred, const char *scope) { int error; - bool nfsd_up_before; struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct svc_serv *serv; - mutex_lock(&nfsd_mutex); - dprintk("nfsd: creating service\n"); - - nrservs = max(nrservs, 0); - nrservs = min(nrservs, NFSD_MAXSERVS); - error = 0; + lockdep_assert_held(&nfsd_mutex); - if (nrservs == 0 && nn->nfsd_serv == NULL) - goto out; + dprintk("nfsd: creating service\n"); - strscpy(nn->nfsd_name, utsname()->nodename, + strscpy(nn->nfsd_name, scope ? scope : utsname()->nodename, sizeof(nn->nfsd_name)); error = nfsd_create_serv(net); if (error) goto out; - - nfsd_up_before = nn->nfsd_net_up; + serv = nn->nfsd_serv; error = nfsd_startup_net(net, cred); if (error) goto out_put; - error = svc_set_num_threads(nn->nfsd_serv, NULL, nrservs); + error = nfsd_set_nrthreads(n, nthreads, net); if (error) - goto out_shutdown; - error = nn->nfsd_serv->sv_nrthreads; -out_shutdown: - if (error < 0 && !nfsd_up_before) - nfsd_shutdown_net(net); + goto out_put; + error = serv->sv_nrthreads; out_put: - /* Threads now hold service active */ - if (xchg(&nn->keep_active, 0)) - nfsd_put(net); - nfsd_put(net); + if (serv->sv_nrthreads == 0) + nfsd_destroy_serv(net); out: - mutex_unlock(&nfsd_mutex); return error; } @@ -911,17 +856,17 @@ nfsd_init_request(struct svc_rqst *rqstp, if (likely(nfsd_vers(nn, rqstp->rq_vers, NFSD_TEST))) return svc_generic_init_request(rqstp, progp, ret); - ret->mismatch.lovers = NFSD_NRVERS; - for (i = NFSD_MINVERS; i < NFSD_NRVERS; i++) { + ret->mismatch.lovers = NFSD_MAXVERS + 1; + for (i = NFSD_MINVERS; i <= NFSD_MAXVERS; i++) { if (nfsd_vers(nn, i, NFSD_TEST)) { ret->mismatch.lovers = i; break; } } - if (ret->mismatch.lovers == NFSD_NRVERS) + if (ret->mismatch.lovers > NFSD_MAXVERS) return rpc_prog_unavail; ret->mismatch.hivers = NFSD_MINVERS; - for (i = NFSD_NRVERS - 1; i >= NFSD_MINVERS; i--) { + for (i = NFSD_MAXVERS; i >= NFSD_MINVERS; i--) { if (nfsd_vers(nn, i, NFSD_TEST)) { ret->mismatch.hivers = i; break; @@ -940,89 +885,37 @@ nfsd(void *vrqstp) struct svc_xprt *perm_sock = list_entry(rqstp->rq_server->sv_permsocks.next, typeof(struct svc_xprt), xpt_list); struct net *net = perm_sock->xpt_net; struct nfsd_net *nn = net_generic(net, nfsd_net_id); - int err; /* At this point, the thread shares current->fs * with the init process. We need to create files with the - * umask as defined by the client instead of init's umask. */ - if (unshare_fs_struct() < 0) { - printk("Unable to start nfsd thread: out of memory\n"); - goto out; - } + * umask as defined by the client instead of init's umask. + */ + svc_thread_init_status(rqstp, unshare_fs_struct()); current->fs->umask = 0; - /* - * thread is spawned with all signals set to SIG_IGN, re-enable - * the ones that will bring down the thread - */ - allow_signal(SIGKILL); - allow_signal(SIGHUP); - allow_signal(SIGINT); - allow_signal(SIGQUIT); - - atomic_inc(&nfsdstats.th_cnt); + atomic_inc(&nfsd_th_cnt); set_freezable(); /* * The main request loop */ - for (;;) { - /* Update sv_maxconn if it has changed */ - rqstp->rq_server->sv_maxconn = nn->max_connections; - - /* - * Find a socket with data available and call its - * recvfrom routine. - */ - while ((err = svc_recv(rqstp, 60*60*HZ)) == -EAGAIN) - ; - if (err == -EINTR) - break; - validate_process_creds(); - svc_process(rqstp); - validate_process_creds(); + while (!svc_thread_should_stop(rqstp)) { + svc_recv(rqstp); + nfsd_file_net_dispose(nn); } - /* Clear signals before calling svc_exit_thread() */ - flush_signals(current); - - atomic_dec(&nfsdstats.th_cnt); - -out: - /* Take an extra ref so that the svc_put in svc_exit_thread() - * doesn't call svc_destroy() - */ - svc_get(nn->nfsd_serv); + atomic_dec(&nfsd_th_cnt); /* Release the thread */ svc_exit_thread(rqstp); - - /* We need to drop a ref, but may not drop the last reference - * without holding nfsd_mutex, and we cannot wait for nfsd_mutex as that - * could deadlock with nfsd_shutdown_threads() waiting for us. - * So three options are: - * - drop a non-final reference, - * - get the mutex without waiting - * - sleep briefly andd try the above again - */ - while (!svc_put_not_last(nn->nfsd_serv)) { - if (mutex_trylock(&nfsd_mutex)) { - nfsd_put(net); - mutex_unlock(&nfsd_mutex); - break; - } - msleep(20); - } - return 0; } /** - * nfsd_dispatch - Process an NFS or NFSACL Request + * nfsd_dispatch - Process an NFS or NFSACL or LOCALIO Request * @rqstp: incoming request - * @statp: pointer to location of accept_stat field in RPC Reply buffer * * This RPC dispatcher integrates the NFS server's duplicate reply cache. * @@ -1030,9 +923,13 @@ out: * %0: Processing complete; do not send a Reply * %1: Processing complete; send Reply in rqstp->rq_res */ -int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) +int nfsd_dispatch(struct svc_rqst *rqstp) { const struct svc_procedure *proc = rqstp->rq_procinfo; + __be32 *statp = rqstp->rq_accept_statp; + struct nfsd_cacherep *rp; + unsigned int start, len; + __be32 *nfs_reply; /* * Give the xdr decoder a chance to change this if it wants @@ -1040,11 +937,27 @@ int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) */ rqstp->rq_cachetype = proc->pc_cachetype; - svcxdr_init_decode(rqstp); + /* + * ->pc_decode advances the argument stream past the NFS + * Call header, so grab the header's starting location and + * size now for the call to nfsd_cache_lookup(). + */ + start = xdr_stream_pos(&rqstp->rq_arg_stream); + len = xdr_stream_remaining(&rqstp->rq_arg_stream); if (!proc->pc_decode(rqstp, &rqstp->rq_arg_stream)) goto out_decode_err; - switch (nfsd_cache_lookup(rqstp)) { + /* + * Release rq_status_counter setting it to an odd value after the rpc + * request has been properly parsed. rq_status_counter is used to + * notify the consumers if the rqstp fields are stable + * (rq_status_counter is odd) or not meaningful (rq_status_counter + * is even). + */ + smp_store_release(&rqstp->rq_status_counter, rqstp->rq_status_counter | 1); + + rp = NULL; + switch (nfsd_cache_lookup(rqstp, start, len, &rp)) { case RC_DOIT: break; case RC_REPLY: @@ -1053,12 +966,7 @@ int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) goto out_dropit; } - /* - * Need to grab the location to store the status, as - * NFSv4 does some encoding while processing - */ - svcxdr_init_encode(rqstp); - + nfs_reply = xdr_inline_decode(&rqstp->rq_res_stream, 0); *statp = proc->pc_func(rqstp); if (test_bit(RQ_DROPME, &rqstp->rq_flags)) goto out_update_drop; @@ -1066,7 +974,13 @@ int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) if (!proc->pc_encode(rqstp, &rqstp->rq_res_stream)) goto out_encode_err; - nfsd_cache_update(rqstp, rqstp->rq_cachetype, statp + 1); + /* + * Release rq_status_counter setting it to an even value after the rpc + * request has been properly processed. + */ + smp_store_release(&rqstp->rq_status_counter, rqstp->rq_status_counter + 1); + + nfsd_cache_update(rqstp, rp, rqstp->rq_cachetype, nfs_reply); out_cached_reply: return 1; @@ -1076,13 +990,13 @@ out_decode_err: return 1; out_update_drop: - nfsd_cache_update(rqstp, RC_NOCACHE, NULL); + nfsd_cache_update(rqstp, rp, RC_NOCACHE, NULL); out_dropit: return 0; out_encode_err: trace_nfsd_cant_encode_err(rqstp); - nfsd_cache_update(rqstp, RC_NOCACHE, NULL); + nfsd_cache_update(rqstp, rp, RC_NOCACHE, NULL); *statp = rpc_system_err; return 1; } @@ -1114,30 +1028,3 @@ bool nfssvc_encode_voidres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { return true; } - -int nfsd_pool_stats_open(struct inode *inode, struct file *file) -{ - int ret; - struct nfsd_net *nn = net_generic(inode->i_sb->s_fs_info, nfsd_net_id); - - mutex_lock(&nfsd_mutex); - if (nn->nfsd_serv == NULL) { - mutex_unlock(&nfsd_mutex); - return -ENODEV; - } - svc_get(nn->nfsd_serv); - ret = svc_pool_stats_open(nn->nfsd_serv, file); - mutex_unlock(&nfsd_mutex); - return ret; -} - -int nfsd_pool_stats_release(struct inode *inode, struct file *file) -{ - int ret = seq_release(inode, file); - struct net *net = inode->i_sb->s_fs_info; - - mutex_lock(&nfsd_mutex); - nfsd_put(net); - mutex_unlock(&nfsd_mutex); - return ret; -} diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index caf6355b18fa..fc262ceafca9 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -336,7 +336,7 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) /* opaque data */ if (xdr_stream_decode_u32(xdr, &args->len) < 0) return false; - if (args->len > NFSSVC_MAXBLKSIZE_V2) + if (args->len > NFS_MAXDATA) return false; return xdr_stream_subsegment(xdr, &args->payload, args->len); @@ -468,7 +468,8 @@ nfssvc_encode_readlinkres(struct svc_rqst *rqstp, struct xdr_stream *xdr) case nfs_ok: if (xdr_stream_encode_u32(xdr, resp->len) < 0) return false; - xdr_write_pages(xdr, &resp->page, 0, resp->len); + svcxdr_encode_opaque_pages(rqstp, xdr, &resp->page, 0, + resp->len); if (svc_encode_result_payload(rqstp, head->iov_len, resp->len) < 0) return false; break; @@ -491,8 +492,9 @@ nfssvc_encode_readres(struct svc_rqst *rqstp, struct xdr_stream *xdr) return false; if (xdr_stream_encode_u32(xdr, resp->count) < 0) return false; - xdr_write_pages(xdr, resp->pages, rqstp->rq_res.page_base, - resp->count); + svcxdr_encode_opaque_pages(rqstp, xdr, resp->pages, + rqstp->rq_res.page_base, + resp->count); if (svc_encode_result_payload(rqstp, head->iov_len, resp->count) < 0) return false; break; @@ -511,7 +513,8 @@ nfssvc_encode_readdirres(struct svc_rqst *rqstp, struct xdr_stream *xdr) return false; switch (resp->status) { case nfs_ok: - xdr_write_pages(xdr, dirlist->pages, 0, dirlist->len); + svcxdr_encode_opaque_pages(rqstp, xdr, dirlist->pages, 0, + dirlist->len); /* no more entries */ if (xdr_stream_encode_item_absent(xdr) < 0) return false; @@ -537,7 +540,7 @@ nfssvc_encode_statfsres(struct svc_rqst *rqstp, struct xdr_stream *xdr) p = xdr_reserve_space(xdr, XDR_UNIT * 5); if (!p) return false; - *p++ = cpu_to_be32(NFSSVC_MAXBLKSIZE_V2); + *p++ = cpu_to_be32(NFS_MAXDATA); *p++ = cpu_to_be32(stat->f_bsize); *p++ = cpu_to_be32(stat->f_blocks); *p++ = cpu_to_be32(stat->f_bfree); diff --git a/fs/nfsd/pnfs.h b/fs/nfsd/pnfs.h index 4f4282d4eeca..db9af780438b 100644 --- a/fs/nfsd/pnfs.h +++ b/fs/nfsd/pnfs.h @@ -27,17 +27,19 @@ struct nfsd4_layout_ops { struct nfs4_client *clp, struct nfsd4_getdeviceinfo *gdevp); __be32 (*encode_getdeviceinfo)(struct xdr_stream *xdr, - struct nfsd4_getdeviceinfo *gdevp); + const struct nfsd4_getdeviceinfo *gdevp); - __be32 (*proc_layoutget)(struct inode *, const struct svc_fh *fhp, - struct nfsd4_layoutget *lgp); - __be32 (*encode_layoutget)(struct xdr_stream *, - struct nfsd4_layoutget *lgp); + __be32 (*proc_layoutget)(struct svc_rqst *rqstp, struct inode *inode, + const struct svc_fh *fhp, struct nfsd4_layoutget *lgp); + __be32 (*encode_layoutget)(struct xdr_stream *xdr, + const struct nfsd4_layoutget *lgp); __be32 (*proc_layoutcommit)(struct inode *inode, + struct svc_rqst *rqstp, struct nfsd4_layoutcommit *lcp); - void (*fence_client)(struct nfs4_layout_stateid *ls); + void (*fence_client)(struct nfs4_layout_stateid *ls, + struct nfsd_file *file); }; extern const struct nfsd4_layout_ops *nfsd4_layout_ops[]; @@ -72,11 +74,13 @@ void nfsd4_setup_layout_type(struct svc_export *exp); void nfsd4_return_all_client_layouts(struct nfs4_client *); void nfsd4_return_all_file_layouts(struct nfs4_client *clp, struct nfs4_file *fp); +void nfsd4_close_layout(struct nfs4_layout_stateid *ls); int nfsd4_init_pnfs(void); void nfsd4_exit_pnfs(void); #else struct nfs4_client; struct nfs4_file; +struct nfs4_layout_stateid; static inline void nfsd4_setup_layout_type(struct svc_export *exp) { @@ -89,6 +93,9 @@ static inline void nfsd4_return_all_file_layouts(struct nfs4_client *clp, struct nfs4_file *fp) { } +static inline void nfsd4_close_layout(struct nfs4_layout_stateid *ls) +{ +} static inline void nfsd4_exit_pnfs(void) { } diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index e94634d30591..b052c1effdc5 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -35,6 +35,7 @@ #ifndef _NFSD4_STATE_H #define _NFSD4_STATE_H +#include <crypto/md5.h> #include <linux/idr.h> #include <linux/refcount.h> #include <linux/sunrpc/svc_xprt.h> @@ -64,21 +65,43 @@ typedef struct { refcount_t cs_count; } copy_stateid_t; +struct nfsd4_referring_call { + struct list_head __list; + + u32 rc_sequenceid; + u32 rc_slotid; +}; + +struct nfsd4_referring_call_list { + struct list_head __list; + + struct nfs4_sessionid rcl_sessionid; + int __nr_referring_calls; + struct list_head rcl_referring_calls; +}; + struct nfsd4_callback { struct nfs4_client *cb_clp; struct rpc_message cb_msg; +#define NFSD4_CALLBACK_RUNNING (0) +#define NFSD4_CALLBACK_WAKE (1) +#define NFSD4_CALLBACK_REQUEUE (2) + unsigned long cb_flags; const struct nfsd4_callback_ops *cb_ops; struct work_struct cb_work; int cb_seq_status; int cb_status; - bool cb_need_restart; - bool cb_holds_slot; + int cb_held_slot; + + int cb_nr_referring_call_list; + struct list_head cb_referring_call_list; }; struct nfsd4_callback_ops { void (*prepare)(struct nfsd4_callback *); int (*done)(struct nfsd4_callback *, struct rpc_task *); void (*release)(struct nfsd4_callback *); + uint32_t opcode; }; /* @@ -88,17 +111,36 @@ struct nfsd4_callback_ops { */ struct nfs4_stid { refcount_t sc_count; -#define NFS4_OPEN_STID 1 -#define NFS4_LOCK_STID 2 -#define NFS4_DELEG_STID 4 -/* For an open stateid kept around *only* to process close replays: */ -#define NFS4_CLOSED_STID 8 + + /* A new stateid is added to the cl_stateids idr early before it + * is fully initialised. Its sc_type is then zero. After + * initialisation the sc_type it set under cl_lock, and then + * never changes. + */ +#define SC_TYPE_OPEN BIT(0) +#define SC_TYPE_LOCK BIT(1) +#define SC_TYPE_DELEG BIT(2) +#define SC_TYPE_LAYOUT BIT(3) + unsigned short sc_type; + +/* state_lock protects sc_status for delegation stateids. + * ->cl_lock protects sc_status for open and lock stateids. + * ->st_mutex also protect sc_status for open stateids. + * ->ls_lock protects sc_status for layout stateids. + */ +/* + * For an open stateid kept around *only* to process close replays. + * For deleg stateid, kept in idr until last reference is dropped. + */ +#define SC_STATUS_CLOSED BIT(0) /* For a deleg stateid kept around only to process free_stateid's: */ -#define NFS4_REVOKED_DELEG_STID 16 -#define NFS4_CLOSED_DELEG_STID 32 -#define NFS4_LAYOUT_STID 64 +#define SC_STATUS_REVOKED BIT(1) +#define SC_STATUS_ADMIN_REVOKED BIT(2) +#define SC_STATUS_FREEABLE BIT(3) +#define SC_STATUS_FREED BIT(4) + unsigned short sc_status; + struct list_head sc_cp_list; - unsigned char sc_type; stateid_t sc_stateid; spinlock_t sc_lock; struct nfs4_client *sc_client; @@ -118,6 +160,36 @@ struct nfs4_cpntf_state { }; /* + * RFC 7862 Section 4.8 states: + * + * | A copy offload stateid will be valid until either (A) the client + * | or server restarts or (B) the client returns the resource by + * | issuing an OFFLOAD_CANCEL operation or the client replies to a + * | CB_OFFLOAD operation. + * + * Because a client might not reply to a CB_OFFLOAD, or a reply + * might get lost due to connection loss, NFSD purges async copy + * state after a short period to prevent it from accumulating + * over time. + */ +#define NFSD_COPY_INITIAL_TTL 10 + +struct nfs4_cb_fattr { + struct nfsd4_callback ncf_getattr; + u32 ncf_cb_status; + + /* from CB_GETATTR reply */ + u64 ncf_cb_change; + u64 ncf_cb_fsize; + struct timespec64 ncf_cb_mtime; + struct timespec64 ncf_cb_atime; + + bool ncf_file_modified; + u64 ncf_initial_cinfo; + u64 ncf_cur_fsize; +}; + +/* * Represents a delegation stateid. The nfs4_client holds references to these * and they are put when it is being destroyed or when the delegation is * returned by the client: @@ -144,14 +216,43 @@ struct nfs4_delegation { struct list_head dl_perclnt; struct list_head dl_recall_lru; /* delegation recalled */ struct nfs4_clnt_odstate *dl_clnt_odstate; - u32 dl_type; time64_t dl_time; -/* For recall: */ + u32 dl_type; + /* For recall: */ int dl_retries; struct nfsd4_callback dl_recall; bool dl_recalled; + bool dl_written; + bool dl_setattr; + + /* for CB_GETATTR */ + struct nfs4_cb_fattr dl_cb_fattr; + + /* For delegated timestamps */ + struct timespec64 dl_atime; + struct timespec64 dl_mtime; + struct timespec64 dl_ctime; }; +static inline bool deleg_is_read(u32 dl_type) +{ + return (dl_type == OPEN_DELEGATE_READ || dl_type == OPEN_DELEGATE_READ_ATTRS_DELEG); +} + +static inline bool deleg_is_write(u32 dl_type) +{ + return (dl_type == OPEN_DELEGATE_WRITE || dl_type == OPEN_DELEGATE_WRITE_ATTRS_DELEG); +} + +static inline bool deleg_attrs_deleg(u32 dl_type) +{ + return dl_type == OPEN_DELEGATE_READ_ATTRS_DELEG || + dl_type == OPEN_DELEGATE_WRITE_ATTRS_DELEG; +} + +bool nfsd4_vet_deleg_time(struct timespec64 *cb, const struct timespec64 *orig, + const struct timespec64 *now); + #define cb_to_delegation(cb) \ container_of(cb, struct nfs4_delegation, dl_recall) @@ -172,10 +273,11 @@ static inline struct nfs4_delegation *delegstateid(struct nfs4_stid *s) return container_of(s, struct nfs4_delegation, dl_stid); } -/* Maximum number of slots per session. 160 is useful for long haul TCP */ -#define NFSD_MAX_SLOTS_PER_SESSION 160 -/* Maximum number of operations per session compound */ -#define NFSD_MAX_OPS_PER_COMPOUND 50 +/* Maximum number of slots per session. This is for sanity-check only. + * It could be increased if we had a mechanism to shutdown misbehaving clients. + * A large number can be needed to get good throughput on high-latency servers. + */ +#define NFSD_MAX_SLOTS_PER_SESSION 2048 /* Maximum session per slot cache size */ #define NFSD_SLOT_CACHE_SIZE 2048 /* Maximum number of NFSD_SLOT_CACHE_SIZE slots per session */ @@ -187,12 +289,15 @@ struct nfsd4_slot { u32 sl_seqid; __be32 sl_status; struct svc_cred sl_cred; + u32 sl_index; u32 sl_datalen; u16 sl_opcnt; + u16 sl_generation; #define NFSD4_SLOT_INUSE (1 << 0) #define NFSD4_SLOT_CACHETHIS (1 << 1) #define NFSD4_SLOT_INITIALIZED (1 << 2) #define NFSD4_SLOT_CACHED (1 << 3) +#define NFSD4_SLOT_REUSED (1 << 4) u8 sl_flags; char sl_data[]; }; @@ -251,6 +356,9 @@ struct nfsd4_conn { unsigned char cn_flags; }; +/* Maximum number of slots that nfsd will use in the backchannel */ +#define NFSD_BC_SLOT_TABLE_SIZE (sizeof(u32) * 8) + /* * Representation of a v4.1+ session. These are refcounted in a similar fashion * to the nfs4_client. References are only taken when the server is actively @@ -258,20 +366,23 @@ struct nfsd4_conn { */ struct nfsd4_session { atomic_t se_ref; + spinlock_t se_lock; + u32 se_cb_slot_avail; /* bitmap of available slots */ + u32 se_cb_highest_slot; /* highest slot client wants */ + u32 se_cb_prog; struct list_head se_hash; /* hash by sessionid */ struct list_head se_perclnt; -/* See SESSION4_PERSIST, etc. for standard flags; this is internal-only: */ -#define NFS4_SESSION_DEAD 0x010 - u32 se_flags; + struct list_head se_all_sessions;/* global list of sessions */ struct nfs4_client *se_client; struct nfs4_sessionid se_sessionid; struct nfsd4_channel_attrs se_fchannel; - struct nfsd4_channel_attrs se_bchannel; struct nfsd4_cb_sec se_cb_sec; struct list_head se_conns; - u32 se_cb_prog; - u32 se_cb_seq_nr; - struct nfsd4_slot *se_slots[]; /* forward channel slots */ + u32 se_cb_seq_nr[NFSD_BC_SLOT_TABLE_SIZE]; + struct xarray se_slots; /* forward channel slots */ + u16 se_slot_gen; + bool se_dead; + u32 se_target_maxslots; }; /* formatted contents of nfs4_sessionid */ @@ -281,7 +392,8 @@ struct nfsd4_sessionid { u32 reserved; }; -#define HEXDIR_LEN 33 /* hex version of 16 byte md5 of cl_name plus '\0' */ +/* Length of MD5 digest as hex, plus terminating '\0' */ +#define HEXDIR_LEN (2 * MD5_DIGEST_SIZE + 1) /* * State Meaning Where set @@ -319,8 +431,9 @@ enum { * 0. If they are not renewed within a lease period, they become eligible for * destruction by the laundromat. * - * These objects can also be destroyed prematurely by the fault injection code, - * or if the client sends certain forms of SETCLIENTID or EXCHANGE_ID updates. + * These objects can also be destroyed if the client sends certain forms of + * SETCLIENTID or EXCHANGE_ID operations. + * * Care is taken *not* to do this however when the objects have an elevated * refcount. * @@ -328,7 +441,7 @@ enum { * * o Each nfs4_clients is also hashed by name (the opaque quantity initially * sent by the client to identify itself). - * + * * o cl_perclient list is used to ensure no dangling stateowner references * when we expire the nfs4_client */ @@ -353,6 +466,7 @@ struct nfs4_client { clientid_t cl_clientid; /* generated by server */ nfs4_verifier cl_confirm; /* generated by server */ u32 cl_minorversion; + atomic_t cl_admin_revoked; /* count of admin-revoked states */ /* NFSv4.1 client implementation id: */ struct xdr_netobj cl_nii_domain; struct xdr_netobj cl_nii_name; @@ -368,8 +482,9 @@ struct nfs4_client { #define NFSD4_CLIENT_UPCALL_LOCK (5) /* upcall serialization */ #define NFSD4_CLIENT_CB_FLAG_MASK (1 << NFSD4_CLIENT_CB_UPDATE | \ 1 << NFSD4_CLIENT_CB_KILL) -#define NFSD4_CLIENT_CB_RECALL_ANY (6) unsigned long cl_flags; + + struct workqueue_struct *cl_callback_wq; const struct cred *cl_cb_cred; struct rpc_clnt *cl_cb_client; u32 cl_cb_ident; @@ -400,9 +515,6 @@ struct nfs4_client { */ struct dentry *cl_nfsd_info_dentry; - /* for nfs41 callbacks */ - /* We currently support a single back channel with a single slot */ - unsigned long cl_cb_slot_busy; struct rpc_wait_queue cl_cb_waitq; /* backchannel callers may */ /* wait here for slots */ struct net *net; @@ -415,7 +527,6 @@ struct nfs4_client { struct nfsd4_cb_recall_any *cl_ra; time64_t cl_ra_time; - struct list_head cl_ra_cblist; }; /* struct nfs4_client_reset @@ -448,7 +559,7 @@ struct nfs4_replay { unsigned int rp_buflen; char *rp_buf; struct knfsd_fh rp_openfh; - struct mutex rp_mutex; + int rp_locked; char rp_ibuf[NFSD4_REPLAY_ISIZE]; }; @@ -566,6 +677,7 @@ struct nfs4_file { atomic_t fi_access[2]; u32 fi_share_deny; struct nfsd_file *fi_deleg_file; + struct nfsd_file *fi_rdeleg_file; int fi_delegees; struct knfsd_fh fi_fhandle; bool fi_had_conflict; @@ -642,6 +754,7 @@ enum nfsd4_cb_op { NFSPROC4_CLNT_CB_SEQUENCE, NFSPROC4_CLNT_CB_NOTIFY_LOCK, NFSPROC4_CLNT_CB_RECALL_ANY, + NFSPROC4_CLNT_CB_GETATTR, }; /* Returns true iff a is later than b: */ @@ -674,15 +787,15 @@ extern __be32 nfs4_preprocess_stateid_op(struct svc_rqst *rqstp, stateid_t *stateid, int flags, struct nfsd_file **filp, struct nfs4_stid **cstid); __be32 nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate, - stateid_t *stateid, unsigned char typemask, - struct nfs4_stid **s, struct nfsd_net *nn); + stateid_t *stateid, unsigned short typemask, + unsigned short statusmask, + struct nfs4_stid **s, struct nfsd_net *nn); struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *slab, void (*sc_free)(struct nfs4_stid *)); int nfs4_init_copy_state(struct nfsd_net *nn, struct nfsd4_copy *copy); void nfs4_free_copy_state(struct nfsd4_copy *copy); struct nfs4_cpntf_state *nfs4_alloc_init_cpntf_state(struct nfsd_net *nn, struct nfs4_stid *p_stid); -void nfs4_unhash_stid(struct nfs4_stid *s); void nfs4_put_stid(struct nfs4_stid *s); void nfs4_inc_and_copy_stateid(stateid_t *dst, struct nfs4_stid *stid); void nfs4_remove_reclaim_record(struct nfs4_client_reclaim *, struct nfsd_net *); @@ -693,20 +806,29 @@ extern __be32 nfs4_check_open_reclaim(struct nfs4_client *); extern void nfsd4_probe_callback(struct nfs4_client *clp); extern void nfsd4_probe_callback_sync(struct nfs4_client *clp); extern void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *); +extern void nfsd41_cb_referring_call(struct nfsd4_callback *cb, + struct nfs4_sessionid *sessionid, + u32 slotid, u32 seqno); +extern void nfsd41_cb_destroy_referring_call_list(struct nfsd4_callback *cb); extern void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp, const struct nfsd4_callback_ops *ops, enum nfsd4_cb_op op); extern bool nfsd4_run_cb(struct nfsd4_callback *cb); -extern int nfsd4_create_callback_queue(void); -extern void nfsd4_destroy_callback_queue(void); + +static inline void nfsd4_try_run_cb(struct nfsd4_callback *cb) +{ + if (!test_and_set_bit(NFSD4_CALLBACK_RUNNING, &cb->cb_flags)) + WARN_ON_ONCE(!nfsd4_run_cb(cb)); +} + extern void nfsd4_shutdown_callback(struct nfs4_client *); extern void nfsd4_shutdown_copy(struct nfs4_client *clp); +void nfsd4_async_copy_reaper(struct nfsd_net *nn); +bool nfsd4_has_active_async_copies(struct nfs4_client *clp); extern struct nfs4_client_reclaim *nfs4_client_to_reclaim(struct xdr_netobj name, struct xdr_netobj princhash, struct nfsd_net *nn); extern bool nfs4_has_reclaimed_state(struct xdr_netobj name, struct nfsd_net *nn); void put_nfs4_file(struct nfs4_file *fi); -extern struct nfsd4_copy * -find_async_copy(struct nfs4_client *clp, stateid_t *staetid); extern void nfs4_put_cpntf_state(struct nfsd_net *nn, struct nfs4_cpntf_state *cps); extern __be32 manage_cpntf_state(struct nfsd_net *nn, stateid_t *st, @@ -718,6 +840,14 @@ static inline void get_nfs4_file(struct nfs4_file *fi) } struct nfsd_file *find_any_file(struct nfs4_file *f); +#ifdef CONFIG_NFSD_V4 +void nfsd4_revoke_states(struct net *net, struct super_block *sb); +#else +static inline void nfsd4_revoke_states(struct net *net, struct super_block *sb) +{ +} +#endif + /* grace period management */ void nfsd4_end_grace(struct nfsd_net *nn); @@ -734,4 +864,12 @@ static inline bool try_to_expire_client(struct nfs4_client *clp) cmpxchg(&clp->cl_state, NFSD4_COURTESY, NFSD4_EXPIRABLE); return clp->cl_state == NFSD4_EXPIRABLE; } + +extern __be32 nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, + struct dentry *dentry, struct nfs4_delegation **pdp); + +struct nfsd4_get_dir_delegation; +struct nfs4_delegation *nfsd_get_dir_deleg(struct nfsd4_compound_state *cstate, + struct nfsd4_get_dir_delegation *gdd, + struct nfsd_file *nf); #endif /* NFSD4_STATE_H */ diff --git a/fs/nfsd/stats.c b/fs/nfsd/stats.c index 777e24e5da33..f7eaf95e20fc 100644 --- a/fs/nfsd/stats.c +++ b/fs/nfsd/stats.c @@ -27,25 +27,22 @@ #include "nfsd.h" -struct nfsd_stats nfsdstats; -struct svc_stat nfsd_svcstats = { - .program = &nfsd_program, -}; - static int nfsd_show(struct seq_file *seq, void *v) { + struct net *net = pde_data(file_inode(seq->file)); + struct nfsd_net *nn = net_generic(net, nfsd_net_id); int i; seq_printf(seq, "rc %lld %lld %lld\nfh %lld 0 0 0 0\nio %lld %lld\n", - percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_RC_HITS]), - percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_RC_MISSES]), - percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_RC_NOCACHE]), - percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_FH_STALE]), - percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_IO_READ]), - percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_IO_WRITE])); + percpu_counter_sum_positive(&nn->counter[NFSD_STATS_RC_HITS]), + percpu_counter_sum_positive(&nn->counter[NFSD_STATS_RC_MISSES]), + percpu_counter_sum_positive(&nn->counter[NFSD_STATS_RC_NOCACHE]), + percpu_counter_sum_positive(&nn->counter[NFSD_STATS_FH_STALE]), + percpu_counter_sum_positive(&nn->counter[NFSD_STATS_IO_READ]), + percpu_counter_sum_positive(&nn->counter[NFSD_STATS_IO_WRITE])); /* thread usage: */ - seq_printf(seq, "th %u 0", atomic_read(&nfsdstats.th_cnt)); + seq_printf(seq, "th %u 0", atomic_read(&nfsd_th_cnt)); /* deprecated thread usage histogram stats */ for (i = 0; i < 10; i++) @@ -55,16 +52,18 @@ static int nfsd_show(struct seq_file *seq, void *v) seq_puts(seq, "\nra 0 0 0 0 0 0 0 0 0 0 0 0\n"); /* show my rpc info */ - svc_seq_show(seq, &nfsd_svcstats); + svc_seq_show(seq, &nn->nfsd_svcstats); #ifdef CONFIG_NFSD_V4 /* Show count for individual nfsv4 operations */ /* Writing operation numbers 0 1 2 also for maintaining uniformity */ - seq_printf(seq,"proc4ops %u", LAST_NFS4_OP + 1); + seq_printf(seq, "proc4ops %u", LAST_NFS4_OP + 1); for (i = 0; i <= LAST_NFS4_OP; i++) { seq_printf(seq, " %lld", - percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_NFS4_OP(i)])); + percpu_counter_sum_positive(&nn->counter[NFSD_STATS_NFS4_OP(i)])); } + seq_printf(seq, "\nwdeleg_getattr %lld", + percpu_counter_sum_positive(&nn->counter[NFSD_STATS_WDELEG_GETATTR])); seq_putc(seq, '\n'); #endif @@ -74,63 +73,14 @@ static int nfsd_show(struct seq_file *seq, void *v) DEFINE_PROC_SHOW_ATTRIBUTE(nfsd); -int nfsd_percpu_counters_init(struct percpu_counter counters[], int num) -{ - int i, err = 0; - - for (i = 0; !err && i < num; i++) - err = percpu_counter_init(&counters[i], 0, GFP_KERNEL); - - if (!err) - return 0; - - for (; i > 0; i--) - percpu_counter_destroy(&counters[i-1]); - - return err; -} - -void nfsd_percpu_counters_reset(struct percpu_counter counters[], int num) +struct proc_dir_entry *nfsd_proc_stat_init(struct net *net) { - int i; - - for (i = 0; i < num; i++) - percpu_counter_set(&counters[i], 0); -} - -void nfsd_percpu_counters_destroy(struct percpu_counter counters[], int num) -{ - int i; + struct nfsd_net *nn = net_generic(net, nfsd_net_id); - for (i = 0; i < num; i++) - percpu_counter_destroy(&counters[i]); -} - -static int nfsd_stat_counters_init(void) -{ - return nfsd_percpu_counters_init(nfsdstats.counter, NFSD_STATS_COUNTERS_NUM); -} - -static void nfsd_stat_counters_destroy(void) -{ - nfsd_percpu_counters_destroy(nfsdstats.counter, NFSD_STATS_COUNTERS_NUM); -} - -int nfsd_stat_init(void) -{ - int err; - - err = nfsd_stat_counters_init(); - if (err) - return err; - - svc_proc_register(&init_net, &nfsd_svcstats, &nfsd_proc_ops); - - return 0; + return svc_proc_register(net, &nn->nfsd_svcstats, &nfsd_proc_ops); } -void nfsd_stat_shutdown(void) +void nfsd_proc_stat_shutdown(struct net *net) { - nfsd_stat_counters_destroy(); - svc_proc_unregister(&init_net, "nfsd"); + svc_proc_unregister(net, "nfsd"); } diff --git a/fs/nfsd/stats.h b/fs/nfsd/stats.h index 9b43dc3d9991..e4efb0e4e56d 100644 --- a/fs/nfsd/stats.h +++ b/fs/nfsd/stats.h @@ -10,87 +10,67 @@ #include <uapi/linux/nfsd/stats.h> #include <linux/percpu_counter.h> +struct proc_dir_entry *nfsd_proc_stat_init(struct net *net); +void nfsd_proc_stat_shutdown(struct net *net); -enum { - NFSD_STATS_RC_HITS, /* repcache hits */ - NFSD_STATS_RC_MISSES, /* repcache misses */ - NFSD_STATS_RC_NOCACHE, /* uncached reqs */ - NFSD_STATS_FH_STALE, /* FH stale error */ - NFSD_STATS_IO_READ, /* bytes returned to read requests */ - NFSD_STATS_IO_WRITE, /* bytes passed in write requests */ -#ifdef CONFIG_NFSD_V4 - NFSD_STATS_FIRST_NFS4_OP, /* count of individual nfsv4 operations */ - NFSD_STATS_LAST_NFS4_OP = NFSD_STATS_FIRST_NFS4_OP + LAST_NFS4_OP, -#define NFSD_STATS_NFS4_OP(op) (NFSD_STATS_FIRST_NFS4_OP + (op)) -#endif - NFSD_STATS_COUNTERS_NUM -}; - -struct nfsd_stats { - struct percpu_counter counter[NFSD_STATS_COUNTERS_NUM]; - - atomic_t th_cnt; /* number of available threads */ -}; - -extern struct nfsd_stats nfsdstats; - -extern struct svc_stat nfsd_svcstats; - -int nfsd_percpu_counters_init(struct percpu_counter counters[], int num); -void nfsd_percpu_counters_reset(struct percpu_counter counters[], int num); -void nfsd_percpu_counters_destroy(struct percpu_counter counters[], int num); -int nfsd_stat_init(void); -void nfsd_stat_shutdown(void); - -static inline void nfsd_stats_rc_hits_inc(void) +static inline void nfsd_stats_rc_hits_inc(struct nfsd_net *nn) { - percpu_counter_inc(&nfsdstats.counter[NFSD_STATS_RC_HITS]); + percpu_counter_inc(&nn->counter[NFSD_STATS_RC_HITS]); } -static inline void nfsd_stats_rc_misses_inc(void) +static inline void nfsd_stats_rc_misses_inc(struct nfsd_net *nn) { - percpu_counter_inc(&nfsdstats.counter[NFSD_STATS_RC_MISSES]); + percpu_counter_inc(&nn->counter[NFSD_STATS_RC_MISSES]); } -static inline void nfsd_stats_rc_nocache_inc(void) +static inline void nfsd_stats_rc_nocache_inc(struct nfsd_net *nn) { - percpu_counter_inc(&nfsdstats.counter[NFSD_STATS_RC_NOCACHE]); + percpu_counter_inc(&nn->counter[NFSD_STATS_RC_NOCACHE]); } -static inline void nfsd_stats_fh_stale_inc(struct svc_export *exp) +static inline void nfsd_stats_fh_stale_inc(struct nfsd_net *nn, + struct svc_export *exp) { - percpu_counter_inc(&nfsdstats.counter[NFSD_STATS_FH_STALE]); - if (exp) - percpu_counter_inc(&exp->ex_stats.counter[EXP_STATS_FH_STALE]); + percpu_counter_inc(&nn->counter[NFSD_STATS_FH_STALE]); + if (exp && exp->ex_stats) + percpu_counter_inc(&exp->ex_stats->counter[EXP_STATS_FH_STALE]); } -static inline void nfsd_stats_io_read_add(struct svc_export *exp, s64 amount) +static inline void nfsd_stats_io_read_add(struct nfsd_net *nn, + struct svc_export *exp, s64 amount) { - percpu_counter_add(&nfsdstats.counter[NFSD_STATS_IO_READ], amount); - if (exp) - percpu_counter_add(&exp->ex_stats.counter[EXP_STATS_IO_READ], amount); + percpu_counter_add(&nn->counter[NFSD_STATS_IO_READ], amount); + if (exp && exp->ex_stats) + percpu_counter_add(&exp->ex_stats->counter[EXP_STATS_IO_READ], amount); } -static inline void nfsd_stats_io_write_add(struct svc_export *exp, s64 amount) +static inline void nfsd_stats_io_write_add(struct nfsd_net *nn, + struct svc_export *exp, s64 amount) { - percpu_counter_add(&nfsdstats.counter[NFSD_STATS_IO_WRITE], amount); - if (exp) - percpu_counter_add(&exp->ex_stats.counter[EXP_STATS_IO_WRITE], amount); + percpu_counter_add(&nn->counter[NFSD_STATS_IO_WRITE], amount); + if (exp && exp->ex_stats) + percpu_counter_add(&exp->ex_stats->counter[EXP_STATS_IO_WRITE], amount); } static inline void nfsd_stats_payload_misses_inc(struct nfsd_net *nn) { - percpu_counter_inc(&nn->counter[NFSD_NET_PAYLOAD_MISSES]); + percpu_counter_inc(&nn->counter[NFSD_STATS_PAYLOAD_MISSES]); } static inline void nfsd_stats_drc_mem_usage_add(struct nfsd_net *nn, s64 amount) { - percpu_counter_add(&nn->counter[NFSD_NET_DRC_MEM_USAGE], amount); + percpu_counter_add(&nn->counter[NFSD_STATS_DRC_MEM_USAGE], amount); } static inline void nfsd_stats_drc_mem_usage_sub(struct nfsd_net *nn, s64 amount) { - percpu_counter_sub(&nn->counter[NFSD_NET_DRC_MEM_USAGE], amount); + percpu_counter_sub(&nn->counter[NFSD_STATS_DRC_MEM_USAGE], amount); } +#ifdef CONFIG_NFSD_V4 +static inline void nfsd_stats_wdeleg_getattr_inc(struct nfsd_net *nn) +{ + percpu_counter_inc(&nn->counter[NFSD_STATS_WDELEG_GETATTR]); +} +#endif #endif /* _NFSD_STATS_H */ diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index 8f9c82d9e075..5ae2a611e57f 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -9,29 +9,50 @@ #define _NFSD_TRACE_H #include <linux/tracepoint.h> +#include <linux/sunrpc/clnt.h> #include <linux/sunrpc/xprt.h> +#include <trace/misc/fs.h> #include <trace/misc/nfs.h> +#include <trace/misc/sunrpc.h> #include "export.h" #include "nfsfh.h" #include "xdr4.h" -#define NFSD_TRACE_PROC_RES_FIELDS \ +#define NFSD_TRACE_PROC_CALL_FIELDS(r) \ + __field(unsigned int, netns_ino) \ + __field(u32, xid) \ + __sockaddr(server, (r)->rq_xprt->xpt_locallen) \ + __sockaddr(client, (r)->rq_xprt->xpt_remotelen) + +#define NFSD_TRACE_PROC_CALL_ASSIGNMENTS(r) \ + do { \ + struct svc_xprt *xprt = (r)->rq_xprt; \ + __entry->netns_ino = SVC_NET(r)->ns.inum; \ + __entry->xid = be32_to_cpu((r)->rq_xid); \ + __assign_sockaddr(server, &xprt->xpt_local, \ + xprt->xpt_locallen); \ + __assign_sockaddr(client, &xprt->xpt_remote, \ + xprt->xpt_remotelen); \ + } while (0) + +#define NFSD_TRACE_PROC_RES_FIELDS(r) \ __field(unsigned int, netns_ino) \ __field(u32, xid) \ __field(unsigned long, status) \ - __array(unsigned char, server, sizeof(struct sockaddr_in6)) \ - __array(unsigned char, client, sizeof(struct sockaddr_in6)) + __sockaddr(server, (r)->rq_xprt->xpt_locallen) \ + __sockaddr(client, (r)->rq_xprt->xpt_remotelen) -#define NFSD_TRACE_PROC_RES_ASSIGNMENTS(error) \ +#define NFSD_TRACE_PROC_RES_ASSIGNMENTS(r, error) \ do { \ - __entry->netns_ino = SVC_NET(rqstp)->ns.inum; \ - __entry->xid = be32_to_cpu(rqstp->rq_xid); \ + struct svc_xprt *xprt = (r)->rq_xprt; \ + __entry->netns_ino = SVC_NET(r)->ns.inum; \ + __entry->xid = be32_to_cpu((r)->rq_xid); \ __entry->status = be32_to_cpu(error); \ - memcpy(__entry->server, &rqstp->rq_xprt->xpt_local, \ - rqstp->rq_xprt->xpt_locallen); \ - memcpy(__entry->client, &rqstp->rq_xprt->xpt_remote, \ - rqstp->rq_xprt->xpt_remotelen); \ + __assign_sockaddr(server, &xprt->xpt_local, \ + xprt->xpt_locallen); \ + __assign_sockaddr(client, &xprt->xpt_remote, \ + xprt->xpt_remotelen); \ } while (0); DECLARE_EVENT_CLASS(nfsd_xdr_err_class, @@ -77,14 +98,15 @@ DEFINE_NFSD_XDR_ERR_EVENT(cant_encode); { NFSD_MAY_READ, "READ" }, \ { NFSD_MAY_SATTR, "SATTR" }, \ { NFSD_MAY_TRUNC, "TRUNC" }, \ - { NFSD_MAY_LOCK, "LOCK" }, \ + { NFSD_MAY_NLM, "NLM" }, \ { NFSD_MAY_OWNER_OVERRIDE, "OWNER_OVERRIDE" }, \ { NFSD_MAY_LOCAL_ACCESS, "LOCAL_ACCESS" }, \ { NFSD_MAY_BYPASS_GSS_ON_ROOT, "BYPASS_GSS_ON_ROOT" }, \ { 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( @@ -102,7 +124,7 @@ TRACE_EVENT(nfsd_compound, TP_fast_assign( __entry->xid = be32_to_cpu(rqst->rq_xid); __entry->opcnt = opcnt; - __assign_str_len(tag, tag, taglen); + __assign_str(tag); ), TP_printk("xid=0x%08x opcnt=%u tag=%s", __entry->xid, __entry->opcnt, __get_str(tag) @@ -125,7 +147,7 @@ TRACE_EVENT(nfsd_compound_status, __entry->args_opcnt = args_opcnt; __entry->resp_opcnt = resp_opcnt; __entry->status = be32_to_cpu(status); - __assign_str(name, name); + __assign_str(name); ), TP_printk("op=%u/%u %s status=%d", __entry->resp_opcnt, __entry->args_opcnt, @@ -142,14 +164,14 @@ TRACE_EVENT(nfsd_compound_decode_err, ), TP_ARGS(rqstp, args_opcnt, resp_opcnt, opnum, status), TP_STRUCT__entry( - NFSD_TRACE_PROC_RES_FIELDS + NFSD_TRACE_PROC_RES_FIELDS(rqstp) __field(u32, args_opcnt) __field(u32, resp_opcnt) __field(u32, opnum) ), TP_fast_assign( - NFSD_TRACE_PROC_RES_ASSIGNMENTS(status) + NFSD_TRACE_PROC_RES_ASSIGNMENTS(rqstp, status) __entry->args_opcnt = args_opcnt; __entry->resp_opcnt = resp_opcnt; @@ -160,7 +182,7 @@ TRACE_EVENT(nfsd_compound_decode_err, __entry->opnum, __entry->status) ); -TRACE_EVENT(nfsd_compound_encode_err, +DECLARE_EVENT_CLASS(nfsd_compound_err_class, TP_PROTO( const struct svc_rqst *rqstp, u32 opnum, @@ -168,12 +190,12 @@ TRACE_EVENT(nfsd_compound_encode_err, ), TP_ARGS(rqstp, opnum, status), TP_STRUCT__entry( - NFSD_TRACE_PROC_RES_FIELDS + NFSD_TRACE_PROC_RES_FIELDS(rqstp) __field(u32, opnum) ), TP_fast_assign( - NFSD_TRACE_PROC_RES_ASSIGNMENTS(status) + NFSD_TRACE_PROC_RES_ASSIGNMENTS(rqstp, status) __entry->opnum = opnum; ), @@ -181,6 +203,18 @@ TRACE_EVENT(nfsd_compound_encode_err, __entry->opnum, __entry->status) ); +#define DEFINE_NFSD_COMPOUND_ERR_EVENT(name) \ +DEFINE_EVENT(nfsd_compound_err_class, nfsd_compound_##name##_err, \ + TP_PROTO( \ + const struct svc_rqst *rqstp, \ + u32 opnum, \ + __be32 status \ + ), \ + TP_ARGS(rqstp, opnum, status)) + +DEFINE_NFSD_COMPOUND_ERR_EVENT(op); +DEFINE_NFSD_COMPOUND_ERR_EVENT(encode); + #define show_fs_file_type(x) \ __print_symbolic(x, \ { S_IFLNK, "LNK" }, \ @@ -191,7 +225,7 @@ TRACE_EVENT(nfsd_compound_encode_err, { S_IFIFO, "FIFO" }, \ { S_IFSOCK, "SOCK" }) -TRACE_EVENT(nfsd_fh_verify, +TRACE_EVENT_CONDITION(nfsd_fh_verify, TP_PROTO( const struct svc_rqst *rqstp, const struct svc_fh *fhp, @@ -199,6 +233,7 @@ TRACE_EVENT(nfsd_fh_verify, int access ), TP_ARGS(rqstp, fhp, type, access), + TP_CONDITION(rqstp != NULL), TP_STRUCT__entry( __field(unsigned int, netns_ino) __sockaddr(server, rqstp->rq_xprt->xpt_remotelen) @@ -237,7 +272,7 @@ TRACE_EVENT_CONDITION(nfsd_fh_verify_err, __be32 error ), TP_ARGS(rqstp, fhp, type, access, error), - TP_CONDITION(error), + TP_CONDITION(rqstp != NULL && error), TP_STRUCT__entry( __field(unsigned int, netns_ino) __sockaddr(server, rqstp->rq_xprt->xpt_remotelen) @@ -293,12 +328,13 @@ DECLARE_EVENT_CLASS(nfsd_fh_err_class, __entry->status) ) -#define DEFINE_NFSD_FH_ERR_EVENT(name) \ -DEFINE_EVENT(nfsd_fh_err_class, nfsd_##name, \ - TP_PROTO(struct svc_rqst *rqstp, \ - struct svc_fh *fhp, \ - int status), \ - TP_ARGS(rqstp, fhp, status)) +#define DEFINE_NFSD_FH_ERR_EVENT(name) \ +DEFINE_EVENT_CONDITION(nfsd_fh_err_class, nfsd_##name, \ + TP_PROTO(struct svc_rqst *rqstp, \ + struct svc_fh *fhp, \ + int status), \ + TP_ARGS(rqstp, fhp, status), \ + TP_CONDITION(rqstp != NULL)) DEFINE_NFSD_FH_ERR_EVENT(set_fh_dentry_badexport); DEFINE_NFSD_FH_ERR_EVENT(set_fh_dentry_badhandle); @@ -308,7 +344,7 @@ TRACE_EVENT(nfsd_exp_find_key, int status), TP_ARGS(key, status), TP_STRUCT__entry( - __field(int, fsidtype) + __field(u8, fsidtype) __array(u32, fsid, 6) __string(auth_domain, key->ek_client->name) __field(int, status) @@ -316,7 +352,7 @@ TRACE_EVENT(nfsd_exp_find_key, TP_fast_assign( __entry->fsidtype = key->ek_fsidtype; memcpy(__entry->fsid, key->ek_fsid, 4*6); - __assign_str(auth_domain, key->ek_client->name); + __assign_str(auth_domain); __entry->status = status; ), TP_printk("fsid=%x::%s domain=%s status=%d", @@ -331,7 +367,7 @@ TRACE_EVENT(nfsd_expkey_update, TP_PROTO(const struct svc_expkey *key, const char *exp_path), TP_ARGS(key, exp_path), TP_STRUCT__entry( - __field(int, fsidtype) + __field(u8, fsidtype) __array(u32, fsid, 6) __string(auth_domain, key->ek_client->name) __string(path, exp_path) @@ -340,8 +376,8 @@ TRACE_EVENT(nfsd_expkey_update, TP_fast_assign( __entry->fsidtype = key->ek_fsidtype; memcpy(__entry->fsid, key->ek_fsid, 4*6); - __assign_str(auth_domain, key->ek_client->name); - __assign_str(path, exp_path); + __assign_str(auth_domain); + __assign_str(path); __entry->cache = !test_bit(CACHE_NEGATIVE, &key->h.flags); ), TP_printk("fsid=%x::%s domain=%s path=%s cache=%s", @@ -363,8 +399,8 @@ TRACE_EVENT(nfsd_exp_get_by_name, __field(int, status) ), TP_fast_assign( - __assign_str(path, key->ex_path.dentry->d_name.name); - __assign_str(auth_domain, key->ex_client->name); + __assign_str(path); + __assign_str(auth_domain); __entry->status = status; ), TP_printk("path=%s domain=%s status=%d", @@ -383,8 +419,8 @@ TRACE_EVENT(nfsd_export_update, __field(bool, cache) ), TP_fast_assign( - __assign_str(path, key->ex_path.dentry->d_name.name); - __assign_str(auth_domain, key->ex_client->name); + __assign_str(path); + __assign_str(auth_domain); __entry->cache = !test_bit(CACHE_NEGATIVE, &key->h.flags); ), TP_printk("path=%s domain=%s cache=%s", @@ -428,12 +464,17 @@ DEFINE_EVENT(nfsd_io_class, nfsd_##name, \ DEFINE_NFSD_IO_EVENT(read_start); DEFINE_NFSD_IO_EVENT(read_splice); DEFINE_NFSD_IO_EVENT(read_vector); +DEFINE_NFSD_IO_EVENT(read_direct); DEFINE_NFSD_IO_EVENT(read_io_done); DEFINE_NFSD_IO_EVENT(read_done); DEFINE_NFSD_IO_EVENT(write_start); DEFINE_NFSD_IO_EVENT(write_opened); +DEFINE_NFSD_IO_EVENT(write_direct); +DEFINE_NFSD_IO_EVENT(write_vector); DEFINE_NFSD_IO_EVENT(write_io_done); DEFINE_NFSD_IO_EVENT(write_done); +DEFINE_NFSD_IO_EVENT(commit_start); +DEFINE_NFSD_IO_EVENT(commit_done); DECLARE_EVENT_CLASS(nfsd_err_class, TP_PROTO(struct svc_rqst *rqstp, @@ -483,7 +524,7 @@ TRACE_EVENT(nfsd_dirent, TP_fast_assign( __entry->fh_hash = fhp ? knfsd_fh_hash(&fhp->fh_handle) : 0; __entry->ino = ino; - __assign_str_len(name, name, namlen) + __assign_str(name); ), TP_printk("fh_hash=0x%08x ino=%llu name=%s", __entry->fh_hash, __entry->ino, __get_str(name) @@ -607,8 +648,8 @@ DEFINE_STATEID_EVENT(layout_recall_release); DEFINE_STATEID_EVENT(open); DEFINE_STATEID_EVENT(deleg_read); +DEFINE_STATEID_EVENT(deleg_write); DEFINE_STATEID_EVENT(deleg_return); -DEFINE_STATEID_EVENT(deleg_recall); DECLARE_EVENT_CLASS(nfsd_stateseqid_class, TP_PROTO(u32 seqid, const stateid_t *stp), @@ -640,23 +681,18 @@ DEFINE_EVENT(nfsd_stateseqid_class, nfsd_##name, \ DEFINE_STATESEQID_EVENT(preprocess); DEFINE_STATESEQID_EVENT(open_confirm); -TRACE_DEFINE_ENUM(NFS4_OPEN_STID); -TRACE_DEFINE_ENUM(NFS4_LOCK_STID); -TRACE_DEFINE_ENUM(NFS4_DELEG_STID); -TRACE_DEFINE_ENUM(NFS4_CLOSED_STID); -TRACE_DEFINE_ENUM(NFS4_REVOKED_DELEG_STID); -TRACE_DEFINE_ENUM(NFS4_CLOSED_DELEG_STID); -TRACE_DEFINE_ENUM(NFS4_LAYOUT_STID); - #define show_stid_type(x) \ __print_flags(x, "|", \ - { NFS4_OPEN_STID, "OPEN" }, \ - { NFS4_LOCK_STID, "LOCK" }, \ - { NFS4_DELEG_STID, "DELEG" }, \ - { NFS4_CLOSED_STID, "CLOSED" }, \ - { NFS4_REVOKED_DELEG_STID, "REVOKED" }, \ - { NFS4_CLOSED_DELEG_STID, "CLOSED_DELEG" }, \ - { NFS4_LAYOUT_STID, "LAYOUT" }) + { SC_TYPE_OPEN, "OPEN" }, \ + { SC_TYPE_LOCK, "LOCK" }, \ + { SC_TYPE_DELEG, "DELEG" }, \ + { SC_TYPE_LAYOUT, "LAYOUT" }) + +#define show_stid_status(x) \ + __print_flags(x, "|", \ + { SC_STATUS_CLOSED, "CLOSED" }, \ + { SC_STATUS_REVOKED, "REVOKED" }, \ + { SC_STATUS_ADMIN_REVOKED, "ADMIN_REVOKED" }) DECLARE_EVENT_CLASS(nfsd_stid_class, TP_PROTO( @@ -665,6 +701,7 @@ DECLARE_EVENT_CLASS(nfsd_stid_class, TP_ARGS(stid), TP_STRUCT__entry( __field(unsigned long, sc_type) + __field(unsigned long, sc_status) __field(int, sc_count) __field(u32, cl_boot) __field(u32, cl_id) @@ -675,16 +712,18 @@ DECLARE_EVENT_CLASS(nfsd_stid_class, const stateid_t *stp = &stid->sc_stateid; __entry->sc_type = stid->sc_type; + __entry->sc_status = stid->sc_status; __entry->sc_count = refcount_read(&stid->sc_count); __entry->cl_boot = stp->si_opaque.so_clid.cl_boot; __entry->cl_id = stp->si_opaque.so_clid.cl_id; __entry->si_id = stp->si_opaque.so_id; __entry->si_generation = stp->si_generation; ), - TP_printk("client %08x:%08x stateid %08x:%08x ref=%d type=%s", + TP_printk("client %08x:%08x stateid %08x:%08x ref=%d type=%s state=%s", __entry->cl_boot, __entry->cl_id, __entry->si_id, __entry->si_generation, - __entry->sc_count, show_stid_type(__entry->sc_type) + __entry->sc_count, show_stid_type(__entry->sc_type), + show_stid_status(__entry->sc_status) ) ); @@ -695,6 +734,140 @@ DEFINE_EVENT(nfsd_stid_class, nfsd_stid_##name, \ DEFINE_STID_EVENT(revoke); +TRACE_EVENT(nfsd_stateowner_replay, + TP_PROTO( + u32 opnum, + const struct nfs4_replay *rp + ), + TP_ARGS(opnum, rp), + TP_STRUCT__entry( + __field(unsigned long, status) + __field(u32, opnum) + ), + TP_fast_assign( + __entry->status = be32_to_cpu(rp->rp_status); + __entry->opnum = opnum; + ), + TP_printk("opnum=%u status=%lu", + __entry->opnum, __entry->status) +); + +TRACE_EVENT_CONDITION(nfsd_seq4_status, + TP_PROTO( + const struct svc_rqst *rqstp, + const struct nfsd4_sequence *sequence + ), + TP_ARGS(rqstp, sequence), + TP_CONDITION(sequence->status_flags), + TP_STRUCT__entry( + __field(unsigned int, netns_ino) + __field(u32, xid) + __field(u32, cl_boot) + __field(u32, cl_id) + __field(u32, seqno) + __field(u32, reserved) + __field(unsigned long, status_flags) + ), + TP_fast_assign( + const struct nfsd4_sessionid *sid = + (struct nfsd4_sessionid *)&sequence->sessionid; + + __entry->netns_ino = SVC_NET(rqstp)->ns.inum; + __entry->xid = be32_to_cpu(rqstp->rq_xid); + __entry->cl_boot = sid->clientid.cl_boot; + __entry->cl_id = sid->clientid.cl_id; + __entry->seqno = sid->sequence; + __entry->reserved = sid->reserved; + __entry->status_flags = sequence->status_flags; + ), + TP_printk("xid=0x%08x sessionid=%08x:%08x:%08x:%08x status_flags=%s", + __entry->xid, __entry->cl_boot, __entry->cl_id, + __entry->seqno, __entry->reserved, + show_nfs4_seq4_status(__entry->status_flags) + ) +); + +DECLARE_EVENT_CLASS(nfsd_cs_slot_class, + TP_PROTO( + const struct nfs4_client *clp, + const struct nfsd4_create_session *cs + ), + TP_ARGS(clp, cs), + TP_STRUCT__entry( + __field(u32, seqid) + __field(u32, slot_seqid) + __field(u32, cl_boot) + __field(u32, cl_id) + __sockaddr(addr, clp->cl_cb_conn.cb_addrlen) + ), + TP_fast_assign( + const struct nfsd4_clid_slot *slot = &clp->cl_cs_slot; + + __entry->cl_boot = clp->cl_clientid.cl_boot; + __entry->cl_id = clp->cl_clientid.cl_id; + __assign_sockaddr(addr, &clp->cl_cb_conn.cb_addr, + clp->cl_cb_conn.cb_addrlen); + __entry->seqid = cs->seqid; + __entry->slot_seqid = slot->sl_seqid; + ), + TP_printk("addr=%pISpc client %08x:%08x seqid=%u slot_seqid=%u", + __get_sockaddr(addr), __entry->cl_boot, __entry->cl_id, + __entry->seqid, __entry->slot_seqid + ) +); + +#define DEFINE_CS_SLOT_EVENT(name) \ +DEFINE_EVENT(nfsd_cs_slot_class, nfsd_##name, \ + TP_PROTO( \ + const struct nfs4_client *clp, \ + const struct nfsd4_create_session *cs \ + ), \ + TP_ARGS(clp, cs)) + +DEFINE_CS_SLOT_EVENT(slot_seqid_conf); +DEFINE_CS_SLOT_EVENT(slot_seqid_unconf); + +#define show_nfs_slot_flags(val) \ + __print_flags(val, "|", \ + { NFSD4_SLOT_INUSE, "INUSE" }, \ + { NFSD4_SLOT_CACHETHIS, "CACHETHIS" }, \ + { NFSD4_SLOT_INITIALIZED, "INITIALIZED" }, \ + { NFSD4_SLOT_CACHED, "CACHED" }, \ + { NFSD4_SLOT_REUSED, "REUSED" }) + +TRACE_EVENT(nfsd_slot_seqid_sequence, + TP_PROTO( + const struct nfs4_client *clp, + const struct nfsd4_sequence *seq, + const struct nfsd4_slot *slot + ), + TP_ARGS(clp, seq, slot), + TP_STRUCT__entry( + __field(u32, seqid) + __field(u32, slot_seqid) + __field(u32, slot_index) + __field(unsigned long, slot_flags) + __field(u32, cl_boot) + __field(u32, cl_id) + __sockaddr(addr, clp->cl_cb_conn.cb_addrlen) + ), + TP_fast_assign( + __entry->cl_boot = clp->cl_clientid.cl_boot; + __entry->cl_id = clp->cl_clientid.cl_id; + __assign_sockaddr(addr, &clp->cl_cb_conn.cb_addr, + clp->cl_cb_conn.cb_addrlen); + __entry->seqid = seq->seqid; + __entry->slot_seqid = slot->sl_seqid; + __entry->slot_index = seq->slotid; + __entry->slot_flags = slot->sl_flags; + ), + TP_printk("addr=%pISpc client %08x:%08x idx=%u seqid=%u slot_seqid=%u flags=%s", + __get_sockaddr(addr), __entry->cl_boot, __entry->cl_id, + __entry->slot_index, __entry->seqid, __entry->slot_seqid, + show_nfs_slot_flags(__entry->slot_flags) + ) +); + DECLARE_EVENT_CLASS(nfsd_clientid_class, TP_PROTO(const clientid_t *clid), TP_ARGS(clid), @@ -724,6 +897,30 @@ DEFINE_CLIENTID_EVENT(purged); DEFINE_CLIENTID_EVENT(renew); DEFINE_CLIENTID_EVENT(stale); +TRACE_EVENT(nfsd_mark_client_expired, + TP_PROTO( + const struct nfs4_client *clp, + int cl_rpc_users + ), + TP_ARGS(clp, cl_rpc_users), + TP_STRUCT__entry( + __field(int, cl_rpc_users) + __field(u32, cl_boot) + __field(u32, cl_id) + __sockaddr(addr, clp->cl_cb_conn.cb_addrlen) + ), + TP_fast_assign( + __entry->cl_rpc_users = cl_rpc_users; + __entry->cl_boot = clp->cl_clientid.cl_boot; + __entry->cl_id = clp->cl_clientid.cl_id; + __assign_sockaddr(addr, &clp->cl_cb_conn.cb_addr, + clp->cl_cb_conn.cb_addrlen) + ), + TP_printk("addr=%pISpc client %08x:%08x cl_rpc_users=%d", + __get_sockaddr(addr), __entry->cl_boot, __entry->cl_id, + __entry->cl_rpc_users) +); + DECLARE_EVENT_CLASS(nfsd_net_class, TP_PROTO(const struct nfsd_net *nn), TP_ARGS(nn), @@ -842,7 +1039,7 @@ DECLARE_EVENT_CLASS(nfsd_clid_class, __array(unsigned char, addr, sizeof(struct sockaddr_in6)) __field(unsigned long, flavor) __array(unsigned char, verifier, NFS4_VERIFIER_SIZE) - __string_len(name, name, clp->cl_name.len) + __string_len(name, clp->cl_name.data, clp->cl_name.len) ), TP_fast_assign( __entry->cl_boot = clp->cl_clientid.cl_boot; @@ -852,7 +1049,7 @@ DECLARE_EVENT_CLASS(nfsd_clid_class, __entry->flavor = clp->cl_cred.cr_flavor; memcpy(__entry->verifier, (void *)&clp->cl_verifier, NFS4_VERIFIER_SIZE); - __assign_str_len(name, clp->cl_name.data, clp->cl_name.len); + __assign_str(name); ), TP_printk("addr=%pISpc name='%s' verifier=0x%s flavor=%s client=%08x:%08x", __entry->addr, __get_str(name), @@ -877,6 +1074,7 @@ DEFINE_CLID_EVENT(confirmed_r); { 1 << NFSD_FILE_HASHED, "HASHED" }, \ { 1 << NFSD_FILE_PENDING, "PENDING" }, \ { 1 << NFSD_FILE_REFERENCED, "REFERENCED" }, \ + { 1 << NFSD_FILE_RECENT, "RECENT" }, \ { 1 << NFSD_FILE_GC, "GC" }) DECLARE_EVENT_CLASS(nfsd_file_class, @@ -913,7 +1111,6 @@ DEFINE_NFSD_FILE_EVENT(nfsd_file_free); DEFINE_NFSD_FILE_EVENT(nfsd_file_unhash); DEFINE_NFSD_FILE_EVENT(nfsd_file_put); DEFINE_NFSD_FILE_EVENT(nfsd_file_closing); -DEFINE_NFSD_FILE_EVENT(nfsd_file_unhash_and_queue); TRACE_EVENT(nfsd_file_alloc, TP_PROTO( @@ -939,6 +1136,33 @@ TRACE_EVENT(nfsd_file_alloc, ) ); +TRACE_EVENT(nfsd_file_get_dio_attrs, + TP_PROTO( + const struct inode *inode, + const struct kstat *stat + ), + TP_ARGS(inode, stat), + TP_STRUCT__entry( + __field(const void *, inode) + __field(unsigned long, mask) + __field(u32, mem_align) + __field(u32, offset_align) + __field(u32, read_offset_align) + ), + TP_fast_assign( + __entry->inode = inode; + __entry->mask = stat->result_mask; + __entry->mem_align = stat->dio_mem_align; + __entry->offset_align = stat->dio_offset_align; + __entry->read_offset_align = stat->dio_read_offset_align; + ), + TP_printk("inode=%p flags=%s mem_align=%u offset_align=%u read_offset_align=%u", + __entry->inode, show_statx_mask(__entry->mask), + __entry->mem_align, __entry->offset_align, + __entry->read_offset_align + ) +); + TRACE_EVENT(nfsd_file_acquire, TP_PROTO( const struct svc_rqst *rqstp, @@ -962,7 +1186,7 @@ TRACE_EVENT(nfsd_file_acquire, ), TP_fast_assign( - __entry->xid = be32_to_cpu(rqstp->rq_xid); + __entry->xid = rqstp ? be32_to_cpu(rqstp->rq_xid) : 0; __entry->inode = inode; __entry->may_flags = may_flags; __entry->nf_ref = nf ? refcount_read(&nf->nf_ref) : 0; @@ -996,7 +1220,7 @@ TRACE_EVENT(nfsd_file_insert_err, __field(long, error) ), TP_fast_assign( - __entry->xid = be32_to_cpu(rqstp->rq_xid); + __entry->xid = rqstp ? be32_to_cpu(rqstp->rq_xid) : 0; __entry->inode = inode; __entry->may_flags = may_flags; __entry->error = error; @@ -1026,7 +1250,7 @@ TRACE_EVENT(nfsd_file_cons_err, __field(const void *, nf_file) ), TP_fast_assign( - __entry->xid = be32_to_cpu(rqstp->rq_xid); + __entry->xid = rqstp ? be32_to_cpu(rqstp->rq_xid) : 0; __entry->inode = inode; __entry->may_flags = may_flags; __entry->nf_ref = refcount_read(&nf->nf_ref); @@ -1149,12 +1373,11 @@ DEFINE_EVENT(nfsd_file_gc_class, name, \ TP_ARGS(nf)) DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_lru_add); -DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_lru_add_disposed); DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_lru_del); -DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_lru_del_disposed); DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_gc_in_use); DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_gc_writeback); DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_gc_referenced); +DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_gc_aged); DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_gc_disposed); DECLARE_EVENT_CLASS(nfsd_file_lruwalk_class, @@ -1202,37 +1425,6 @@ TRACE_EVENT(nfsd_file_close, ) ); -TRACE_EVENT(nfsd_file_fsync, - TP_PROTO( - const struct nfsd_file *nf, - int ret - ), - TP_ARGS(nf, ret), - TP_STRUCT__entry( - __field(void *, nf_inode) - __field(int, nf_ref) - __field(int, ret) - __field(unsigned long, nf_flags) - __field(unsigned char, nf_may) - __field(struct file *, nf_file) - ), - TP_fast_assign( - __entry->nf_inode = nf->nf_inode; - __entry->nf_ref = refcount_read(&nf->nf_ref); - __entry->ret = ret; - __entry->nf_flags = nf->nf_flags; - __entry->nf_may = nf->nf_may; - __entry->nf_file = nf->nf_file; - ), - TP_printk("inode=%p ref=%d flags=%s may=%s nf_file=%p ret=%d", - __entry->nf_inode, - __entry->nf_ref, - show_nf_flags(__entry->nf_flags), - show_nfsd_may_flags(__entry->nf_may), - __entry->nf_file, __entry->ret - ) -); - #include "cache.h" TRACE_DEFINE_ENUM(RC_DROPIT); @@ -1271,8 +1463,8 @@ TRACE_EVENT(nfsd_drc_found, TRACE_EVENT(nfsd_drc_mismatch, TP_PROTO( const struct nfsd_net *nn, - const struct svc_cacherep *key, - const struct svc_cacherep *rp + const struct nfsd_cacherep *key, + const struct nfsd_cacherep *rp ), TP_ARGS(nn, key, rp), TP_STRUCT__entry( @@ -1364,10 +1556,14 @@ DEFINE_EVENT(nfsd_cb_class, nfsd_cb_##name, \ TP_PROTO(const struct nfs4_client *clp), \ TP_ARGS(clp)) -DEFINE_NFSD_CB_EVENT(state); +DEFINE_NFSD_CB_EVENT(start); +DEFINE_NFSD_CB_EVENT(new_state); DEFINE_NFSD_CB_EVENT(probe); DEFINE_NFSD_CB_EVENT(lost); DEFINE_NFSD_CB_EVENT(shutdown); +DEFINE_NFSD_CB_EVENT(rpc_prepare); +DEFINE_NFSD_CB_EVENT(rpc_done); +DEFINE_NFSD_CB_EVENT(rpc_release); TRACE_DEFINE_ENUM(RPC_AUTH_NULL); TRACE_DEFINE_ENUM(RPC_AUTH_UNIX); @@ -1396,19 +1592,19 @@ TRACE_EVENT(nfsd_cb_setup, __field(u32, cl_id) __field(unsigned long, authflavor) __sockaddr(addr, clp->cl_cb_conn.cb_addrlen) - __array(unsigned char, netid, 8) + __string(netid, netid) ), TP_fast_assign( __entry->cl_boot = clp->cl_clientid.cl_boot; __entry->cl_id = clp->cl_clientid.cl_id; - strlcpy(__entry->netid, netid, sizeof(__entry->netid)); + __assign_str(netid); __entry->authflavor = authflavor; __assign_sockaddr(addr, &clp->cl_cb_conn.cb_addr, clp->cl_cb_conn.cb_addrlen) ), TP_printk("addr=%pISpc client %08x:%08x proto=%s flavor=%s", __get_sockaddr(addr), __entry->cl_boot, __entry->cl_id, - __entry->netid, show_nfsd_authflavor(__entry->authflavor)) + __get_str(netid), show_nfsd_authflavor(__entry->authflavor)) ); TRACE_EVENT(nfsd_cb_setup_err, @@ -1435,6 +1631,143 @@ TRACE_EVENT(nfsd_cb_setup_err, __entry->error) ); +/* Not a real opcode, but there is no 0 operation. */ +#define _CB_NULL 0 + +#define show_nfsd_cb_opcode(val) \ + __print_symbolic(val, \ + { _CB_NULL, "CB_NULL" }, \ + { OP_CB_GETATTR, "CB_GETATTR" }, \ + { OP_CB_RECALL, "CB_RECALL" }, \ + { OP_CB_LAYOUTRECALL, "CB_LAYOUTRECALL" }, \ + { OP_CB_RECALL_ANY, "CB_RECALL_ANY" }, \ + { OP_CB_NOTIFY_LOCK, "CB_NOTIFY_LOCK" }, \ + { OP_CB_OFFLOAD, "CB_OFFLOAD" }) + +DECLARE_EVENT_CLASS(nfsd_cb_lifetime_class, + TP_PROTO( + const struct nfs4_client *clp, + const struct nfsd4_callback *cb + ), + TP_ARGS(clp, cb), + TP_STRUCT__entry( + __field(u32, cl_boot) + __field(u32, cl_id) + __field(const void *, cb) + __field(unsigned long, opcode) + __field(bool, need_restart) + __sockaddr(addr, clp->cl_cb_conn.cb_addrlen) + ), + TP_fast_assign( + __entry->cl_boot = clp->cl_clientid.cl_boot; + __entry->cl_id = clp->cl_clientid.cl_id; + __entry->cb = cb; + __entry->opcode = cb->cb_ops ? cb->cb_ops->opcode : _CB_NULL; + __entry->need_restart = test_bit(NFSD4_CALLBACK_REQUEUE, &cb->cb_flags); + __assign_sockaddr(addr, &clp->cl_cb_conn.cb_addr, + clp->cl_cb_conn.cb_addrlen) + ), + TP_printk("addr=%pISpc client %08x:%08x cb=%p%s opcode=%s", + __get_sockaddr(addr), __entry->cl_boot, __entry->cl_id, __entry->cb, + __entry->need_restart ? " (need restart)" : " (first try)", + show_nfsd_cb_opcode(__entry->opcode) + ) +); + +#define DEFINE_NFSD_CB_LIFETIME_EVENT(name) \ +DEFINE_EVENT(nfsd_cb_lifetime_class, nfsd_cb_##name, \ + TP_PROTO( \ + const struct nfs4_client *clp, \ + const struct nfsd4_callback *cb \ + ), \ + TP_ARGS(clp, cb)) + +DEFINE_NFSD_CB_LIFETIME_EVENT(queue); +DEFINE_NFSD_CB_LIFETIME_EVENT(destroy); +DEFINE_NFSD_CB_LIFETIME_EVENT(restart); +DEFINE_NFSD_CB_LIFETIME_EVENT(bc_update); +DEFINE_NFSD_CB_LIFETIME_EVENT(bc_shutdown); + +TRACE_EVENT(nfsd_cb_seq_status, + TP_PROTO( + const struct rpc_task *task, + const struct nfsd4_callback *cb + ), + TP_ARGS(task, cb), + TP_STRUCT__entry( + __field(unsigned int, task_id) + __field(unsigned int, client_id) + __field(u32, cl_boot) + __field(u32, cl_id) + __field(u32, seqno) + __field(u32, reserved) + __field(int, tk_status) + __field(int, seq_status) + ), + TP_fast_assign( + const struct nfs4_client *clp = cb->cb_clp; + const struct nfsd4_session *session = clp->cl_cb_session; + const struct nfsd4_sessionid *sid = + (struct nfsd4_sessionid *)&session->se_sessionid; + + __entry->task_id = task->tk_pid; + __entry->client_id = task->tk_client ? + task->tk_client->cl_clid : -1; + __entry->cl_boot = sid->clientid.cl_boot; + __entry->cl_id = sid->clientid.cl_id; + __entry->seqno = sid->sequence; + __entry->reserved = sid->reserved; + __entry->tk_status = task->tk_status; + __entry->seq_status = cb->cb_seq_status; + ), + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " sessionid=%08x:%08x:%08x:%08x tk_status=%d seq_status=%d", + __entry->task_id, __entry->client_id, + __entry->cl_boot, __entry->cl_id, + __entry->seqno, __entry->reserved, + __entry->tk_status, __entry->seq_status + ) +); + +TRACE_EVENT(nfsd_cb_free_slot, + TP_PROTO( + const struct rpc_task *task, + const struct nfsd4_callback *cb + ), + TP_ARGS(task, cb), + TP_STRUCT__entry( + __field(unsigned int, task_id) + __field(unsigned int, client_id) + __field(u32, cl_boot) + __field(u32, cl_id) + __field(u32, seqno) + __field(u32, reserved) + __field(u32, slot_seqno) + ), + TP_fast_assign( + const struct nfs4_client *clp = cb->cb_clp; + const struct nfsd4_session *session = clp->cl_cb_session; + const struct nfsd4_sessionid *sid = + (struct nfsd4_sessionid *)&session->se_sessionid; + + __entry->task_id = task->tk_pid; + __entry->client_id = task->tk_client ? + task->tk_client->cl_clid : -1; + __entry->cl_boot = sid->clientid.cl_boot; + __entry->cl_id = sid->clientid.cl_id; + __entry->seqno = sid->sequence; + __entry->reserved = sid->reserved; + __entry->slot_seqno = session->se_cb_seq_nr[cb->cb_held_slot]; + ), + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " sessionid=%08x:%08x:%08x:%08x new slot seqno=%u", + __entry->task_id, __entry->client_id, + __entry->cl_boot, __entry->cl_id, + __entry->seqno, __entry->reserved, + __entry->slot_seqno + ) +); + TRACE_EVENT_CONDITION(nfsd_cb_recall, TP_PROTO( const struct nfs4_stid *stid @@ -1590,6 +1923,7 @@ DEFINE_NFSD_CB_DONE_EVENT(nfsd_cb_recall_done); DEFINE_NFSD_CB_DONE_EVENT(nfsd_cb_notify_lock_done); DEFINE_NFSD_CB_DONE_EVENT(nfsd_cb_layout_done); DEFINE_NFSD_CB_DONE_EVENT(nfsd_cb_offload_done); +DEFINE_NFSD_CB_DONE_EVENT(nfsd_cb_getattr_done); TRACE_EVENT(nfsd_cb_recall_any_done, TP_PROTO( @@ -1612,6 +1946,714 @@ TRACE_EVENT(nfsd_cb_recall_any_done, ) ); +TRACE_EVENT(nfsd_ctl_unlock_ip, + TP_PROTO( + const struct net *net, + const char *address + ), + TP_ARGS(net, address), + TP_STRUCT__entry( + __field(unsigned int, netns_ino) + __string(address, address) + ), + TP_fast_assign( + __entry->netns_ino = net->ns.inum; + __assign_str(address); + ), + TP_printk("address=%s", + __get_str(address) + ) +); + +TRACE_EVENT(nfsd_ctl_unlock_fs, + TP_PROTO( + const struct net *net, + const char *path + ), + TP_ARGS(net, path), + TP_STRUCT__entry( + __field(unsigned int, netns_ino) + __string(path, path) + ), + TP_fast_assign( + __entry->netns_ino = net->ns.inum; + __assign_str(path); + ), + TP_printk("path=%s", + __get_str(path) + ) +); + +TRACE_EVENT(nfsd_ctl_filehandle, + TP_PROTO( + const struct net *net, + const char *domain, + const char *path, + int maxsize + ), + TP_ARGS(net, domain, path, maxsize), + TP_STRUCT__entry( + __field(unsigned int, netns_ino) + __field(int, maxsize) + __string(domain, domain) + __string(path, path) + ), + TP_fast_assign( + __entry->netns_ino = net->ns.inum; + __entry->maxsize = maxsize; + __assign_str(domain); + __assign_str(path); + ), + TP_printk("domain=%s path=%s maxsize=%d", + __get_str(domain), __get_str(path), __entry->maxsize + ) +); + +TRACE_EVENT(nfsd_ctl_threads, + TP_PROTO( + const struct net *net, + int newthreads + ), + TP_ARGS(net, newthreads), + TP_STRUCT__entry( + __field(unsigned int, netns_ino) + __field(int, newthreads) + ), + TP_fast_assign( + __entry->netns_ino = net->ns.inum; + __entry->newthreads = newthreads; + ), + TP_printk("newthreads=%d", + __entry->newthreads + ) +); + +TRACE_EVENT(nfsd_ctl_pool_threads, + TP_PROTO( + const struct net *net, + int pool, + int nrthreads + ), + TP_ARGS(net, pool, nrthreads), + TP_STRUCT__entry( + __field(unsigned int, netns_ino) + __field(int, pool) + __field(int, nrthreads) + ), + TP_fast_assign( + __entry->netns_ino = net->ns.inum; + __entry->pool = pool; + __entry->nrthreads = nrthreads; + ), + TP_printk("pool=%d nrthreads=%d", + __entry->pool, __entry->nrthreads + ) +); + +TRACE_EVENT(nfsd_ctl_version, + TP_PROTO( + const struct net *net, + const char *mesg + ), + TP_ARGS(net, mesg), + TP_STRUCT__entry( + __field(unsigned int, netns_ino) + __string(mesg, mesg) + ), + TP_fast_assign( + __entry->netns_ino = net->ns.inum; + __assign_str(mesg); + ), + TP_printk("%s", + __get_str(mesg) + ) +); + +TRACE_EVENT(nfsd_ctl_ports_addfd, + TP_PROTO( + const struct net *net, + int fd + ), + TP_ARGS(net, fd), + TP_STRUCT__entry( + __field(unsigned int, netns_ino) + __field(int, fd) + ), + TP_fast_assign( + __entry->netns_ino = net->ns.inum; + __entry->fd = fd; + ), + TP_printk("fd=%d", + __entry->fd + ) +); + +TRACE_EVENT(nfsd_ctl_ports_addxprt, + TP_PROTO( + const struct net *net, + const char *transport, + int port + ), + TP_ARGS(net, transport, port), + TP_STRUCT__entry( + __field(unsigned int, netns_ino) + __field(int, port) + __string(transport, transport) + ), + TP_fast_assign( + __entry->netns_ino = net->ns.inum; + __entry->port = port; + __assign_str(transport); + ), + TP_printk("transport=%s port=%d", + __get_str(transport), __entry->port + ) +); + +TRACE_EVENT(nfsd_ctl_maxblksize, + TP_PROTO( + const struct net *net, + int bsize + ), + TP_ARGS(net, bsize), + TP_STRUCT__entry( + __field(unsigned int, netns_ino) + __field(int, bsize) + ), + TP_fast_assign( + __entry->netns_ino = net->ns.inum; + __entry->bsize = bsize; + ), + TP_printk("bsize=%d", + __entry->bsize + ) +); + +TRACE_EVENT(nfsd_ctl_time, + TP_PROTO( + const struct net *net, + const char *name, + size_t namelen, + int time + ), + TP_ARGS(net, name, namelen, time), + TP_STRUCT__entry( + __field(unsigned int, netns_ino) + __field(int, time) + __string_len(name, name, namelen) + ), + TP_fast_assign( + __entry->netns_ino = net->ns.inum; + __entry->time = time; + __assign_str(name); + ), + TP_printk("file=%s time=%d", + __get_str(name), __entry->time + ) +); + +TRACE_EVENT(nfsd_ctl_recoverydir, + TP_PROTO( + const struct net *net, + const char *recdir + ), + TP_ARGS(net, recdir), + TP_STRUCT__entry( + __field(unsigned int, netns_ino) + __string(recdir, recdir) + ), + TP_fast_assign( + __entry->netns_ino = net->ns.inum; + __assign_str(recdir); + ), + TP_printk("recdir=%s", + __get_str(recdir) + ) +); + +TRACE_EVENT(nfsd_end_grace, + TP_PROTO( + const struct net *net + ), + TP_ARGS(net), + TP_STRUCT__entry( + __field(unsigned int, netns_ino) + ), + TP_fast_assign( + __entry->netns_ino = net->ns.inum; + ), + TP_printk("nn=%d", __entry->netns_ino + ) +); + +DECLARE_EVENT_CLASS(nfsd_copy_class, + TP_PROTO( + const struct nfsd4_copy *copy + ), + TP_ARGS(copy), + TP_STRUCT__entry( + __field(bool, intra) + __field(bool, async) + __field(u32, src_cl_boot) + __field(u32, src_cl_id) + __field(u32, src_so_id) + __field(u32, src_si_generation) + __field(u32, dst_cl_boot) + __field(u32, dst_cl_id) + __field(u32, dst_so_id) + __field(u32, dst_si_generation) + __field(u32, cb_cl_boot) + __field(u32, cb_cl_id) + __field(u32, cb_so_id) + __field(u32, cb_si_generation) + __field(u64, src_cp_pos) + __field(u64, dst_cp_pos) + __field(u64, cp_count) + __sockaddr(addr, sizeof(struct sockaddr_in6)) + ), + TP_fast_assign( + const stateid_t *src_stp = ©->cp_src_stateid; + const stateid_t *dst_stp = ©->cp_dst_stateid; + const stateid_t *cb_stp = ©->cp_res.cb_stateid; + + __entry->intra = test_bit(NFSD4_COPY_F_INTRA, ©->cp_flags); + __entry->async = !test_bit(NFSD4_COPY_F_SYNCHRONOUS, ©->cp_flags); + __entry->src_cl_boot = src_stp->si_opaque.so_clid.cl_boot; + __entry->src_cl_id = src_stp->si_opaque.so_clid.cl_id; + __entry->src_so_id = src_stp->si_opaque.so_id; + __entry->src_si_generation = src_stp->si_generation; + __entry->dst_cl_boot = dst_stp->si_opaque.so_clid.cl_boot; + __entry->dst_cl_id = dst_stp->si_opaque.so_clid.cl_id; + __entry->dst_so_id = dst_stp->si_opaque.so_id; + __entry->dst_si_generation = dst_stp->si_generation; + __entry->cb_cl_boot = cb_stp->si_opaque.so_clid.cl_boot; + __entry->cb_cl_id = cb_stp->si_opaque.so_clid.cl_id; + __entry->cb_so_id = cb_stp->si_opaque.so_id; + __entry->cb_si_generation = cb_stp->si_generation; + __entry->src_cp_pos = copy->cp_src_pos; + __entry->dst_cp_pos = copy->cp_dst_pos; + __entry->cp_count = copy->cp_count; + __assign_sockaddr(addr, ©->cp_clp->cl_addr, + sizeof(struct sockaddr_in6)); + ), + TP_printk("client=%pISpc intra=%d async=%d " + "src_client %08x:%08x src_stateid %08x:%08x " + "dst_client %08x:%08x dst_stateid %08x:%08x " + "cb_client %08x:%08x cb_stateid %08x:%08x " + "cp_src_pos=%llu cp_dst_pos=%llu cp_count=%llu", + __get_sockaddr(addr), __entry->intra, __entry->async, + __entry->src_cl_boot, __entry->src_cl_id, + __entry->src_so_id, __entry->src_si_generation, + __entry->dst_cl_boot, __entry->dst_cl_id, + __entry->dst_so_id, __entry->dst_si_generation, + __entry->cb_cl_boot, __entry->cb_cl_id, + __entry->cb_so_id, __entry->cb_si_generation, + __entry->src_cp_pos, __entry->dst_cp_pos, __entry->cp_count + ) +); + +#define DEFINE_COPY_EVENT(name) \ +DEFINE_EVENT(nfsd_copy_class, nfsd_copy_##name, \ + TP_PROTO(const struct nfsd4_copy *copy), \ + TP_ARGS(copy)) + +DEFINE_COPY_EVENT(inter); +DEFINE_COPY_EVENT(intra); +DEFINE_COPY_EVENT(async); + +TRACE_EVENT(nfsd_copy_done, + TP_PROTO( + const struct nfsd4_copy *copy, + __be32 status + ), + TP_ARGS(copy, status), + TP_STRUCT__entry( + __field(int, status) + __field(bool, intra) + __field(bool, async) + __sockaddr(addr, sizeof(struct sockaddr_in6)) + ), + TP_fast_assign( + __entry->status = be32_to_cpu(status); + __entry->intra = test_bit(NFSD4_COPY_F_INTRA, ©->cp_flags); + __entry->async = !test_bit(NFSD4_COPY_F_SYNCHRONOUS, ©->cp_flags); + __assign_sockaddr(addr, ©->cp_clp->cl_addr, + sizeof(struct sockaddr_in6)); + ), + TP_printk("addr=%pISpc status=%d intra=%d async=%d", + __get_sockaddr(addr), __entry->status, __entry->intra, __entry->async + ) +); + +DECLARE_EVENT_CLASS(nfsd_copy_async_done_class, + TP_PROTO( + const struct nfsd4_copy *copy + ), + TP_ARGS(copy), + TP_STRUCT__entry( + __field(int, status) + __field(bool, intra) + __field(bool, async) + __field(u32, src_cl_boot) + __field(u32, src_cl_id) + __field(u32, src_so_id) + __field(u32, src_si_generation) + __field(u32, dst_cl_boot) + __field(u32, dst_cl_id) + __field(u32, dst_so_id) + __field(u32, dst_si_generation) + __field(u32, cb_cl_boot) + __field(u32, cb_cl_id) + __field(u32, cb_so_id) + __field(u32, cb_si_generation) + __field(u64, src_cp_pos) + __field(u64, dst_cp_pos) + __field(u64, cp_count) + __sockaddr(addr, sizeof(struct sockaddr_in6)) + ), + TP_fast_assign( + const stateid_t *src_stp = ©->cp_src_stateid; + const stateid_t *dst_stp = ©->cp_dst_stateid; + const stateid_t *cb_stp = ©->cp_res.cb_stateid; + + __entry->status = be32_to_cpu(copy->nfserr); + __entry->intra = test_bit(NFSD4_COPY_F_INTRA, ©->cp_flags); + __entry->async = !test_bit(NFSD4_COPY_F_SYNCHRONOUS, ©->cp_flags); + __entry->src_cl_boot = src_stp->si_opaque.so_clid.cl_boot; + __entry->src_cl_id = src_stp->si_opaque.so_clid.cl_id; + __entry->src_so_id = src_stp->si_opaque.so_id; + __entry->src_si_generation = src_stp->si_generation; + __entry->dst_cl_boot = dst_stp->si_opaque.so_clid.cl_boot; + __entry->dst_cl_id = dst_stp->si_opaque.so_clid.cl_id; + __entry->dst_so_id = dst_stp->si_opaque.so_id; + __entry->dst_si_generation = dst_stp->si_generation; + __entry->cb_cl_boot = cb_stp->si_opaque.so_clid.cl_boot; + __entry->cb_cl_id = cb_stp->si_opaque.so_clid.cl_id; + __entry->cb_so_id = cb_stp->si_opaque.so_id; + __entry->cb_si_generation = cb_stp->si_generation; + __entry->src_cp_pos = copy->cp_src_pos; + __entry->dst_cp_pos = copy->cp_dst_pos; + __entry->cp_count = copy->cp_count; + __assign_sockaddr(addr, ©->cp_clp->cl_addr, + sizeof(struct sockaddr_in6)); + ), + TP_printk("client=%pISpc status=%d intra=%d async=%d " + "src_client %08x:%08x src_stateid %08x:%08x " + "dst_client %08x:%08x dst_stateid %08x:%08x " + "cb_client %08x:%08x cb_stateid %08x:%08x " + "cp_src_pos=%llu cp_dst_pos=%llu cp_count=%llu", + __get_sockaddr(addr), + __entry->status, __entry->intra, __entry->async, + __entry->src_cl_boot, __entry->src_cl_id, + __entry->src_so_id, __entry->src_si_generation, + __entry->dst_cl_boot, __entry->dst_cl_id, + __entry->dst_so_id, __entry->dst_si_generation, + __entry->cb_cl_boot, __entry->cb_cl_id, + __entry->cb_so_id, __entry->cb_si_generation, + __entry->src_cp_pos, __entry->dst_cp_pos, __entry->cp_count + ) +); + +#define DEFINE_COPY_ASYNC_DONE_EVENT(name) \ +DEFINE_EVENT(nfsd_copy_async_done_class, \ + nfsd_copy_async_##name, \ + TP_PROTO(const struct nfsd4_copy *copy), \ + TP_ARGS(copy)) + +DEFINE_COPY_ASYNC_DONE_EVENT(done); +DEFINE_COPY_ASYNC_DONE_EVENT(cancel); + +TRACE_EVENT(nfsd_vfs_setattr, + TP_PROTO( + const struct svc_rqst *rqstp, + const struct svc_fh *fhp, + const struct iattr *iap, + const struct timespec64 *guardtime + ), + TP_ARGS(rqstp, fhp, iap, guardtime), + TP_STRUCT__entry( + NFSD_TRACE_PROC_CALL_FIELDS(rqstp) + __field(u32, fh_hash) + __field(s64, gtime_tv_sec) + __field(u32, gtime_tv_nsec) + __field(unsigned int, ia_valid) + __field(loff_t, ia_size) + __field(uid_t, ia_uid) + __field(gid_t, ia_gid) + __field(umode_t, ia_mode) + ), + TP_fast_assign( + NFSD_TRACE_PROC_CALL_ASSIGNMENTS(rqstp); + __entry->fh_hash = knfsd_fh_hash(&fhp->fh_handle); + __entry->gtime_tv_sec = guardtime ? guardtime->tv_sec : 0; + __entry->gtime_tv_nsec = guardtime ? guardtime->tv_nsec : 0; + __entry->ia_valid = iap->ia_valid; + __entry->ia_size = iap->ia_size; + __entry->ia_uid = __kuid_val(iap->ia_uid); + __entry->ia_gid = __kgid_val(iap->ia_gid); + __entry->ia_mode = iap->ia_mode; + ), + TP_printk( + "xid=0x%08x fh_hash=0x%08x ia_valid=%s ia_size=%llu ia_mode=0%o ia_uid=%u ia_gid=%u guard_time=%lld.%u", + __entry->xid, __entry->fh_hash, show_ia_valid_flags(__entry->ia_valid), + __entry->ia_size, __entry->ia_mode, __entry->ia_uid, __entry->ia_gid, + __entry->gtime_tv_sec, __entry->gtime_tv_nsec + ) +) + +TRACE_EVENT(nfsd_vfs_lookup, + TP_PROTO( + const struct svc_rqst *rqstp, + const struct svc_fh *fhp, + const char *name, + unsigned int len + ), + TP_ARGS(rqstp, fhp, name, len), + TP_STRUCT__entry( + NFSD_TRACE_PROC_CALL_FIELDS(rqstp) + __field(u32, fh_hash) + __string_len(name, name, len) + ), + TP_fast_assign( + NFSD_TRACE_PROC_CALL_ASSIGNMENTS(rqstp); + __entry->fh_hash = knfsd_fh_hash(&fhp->fh_handle); + __assign_str(name); + ), + TP_printk("xid=0x%08x fh_hash=0x%08x name=%s", + __entry->xid, __entry->fh_hash, __get_str(name) + ) +); + +TRACE_EVENT(nfsd_vfs_create, + TP_PROTO( + const struct svc_rqst *rqstp, + const struct svc_fh *fhp, + umode_t type, + const char *name, + unsigned int len + ), + TP_ARGS(rqstp, fhp, type, name, len), + TP_STRUCT__entry( + NFSD_TRACE_PROC_CALL_FIELDS(rqstp) + __field(u32, fh_hash) + __field(umode_t, type) + __string_len(name, name, len) + ), + TP_fast_assign( + NFSD_TRACE_PROC_CALL_ASSIGNMENTS(rqstp); + __entry->fh_hash = knfsd_fh_hash(&fhp->fh_handle); + __entry->type = type; + __assign_str(name); + ), + TP_printk("xid=0x%08x fh_hash=0x%08x type=%s name=%s", + __entry->xid, __entry->fh_hash, + show_fs_file_type(__entry->type), __get_str(name) + ) +); + +TRACE_EVENT(nfsd_vfs_symlink, + TP_PROTO( + const struct svc_rqst *rqstp, + const struct svc_fh *fhp, + const char *name, + unsigned int namelen, + const char *target + ), + TP_ARGS(rqstp, fhp, name, namelen, target), + TP_STRUCT__entry( + NFSD_TRACE_PROC_CALL_FIELDS(rqstp) + __field(u32, fh_hash) + __string_len(name, name, namelen) + __string(target, target) + ), + TP_fast_assign( + NFSD_TRACE_PROC_CALL_ASSIGNMENTS(rqstp); + __entry->fh_hash = knfsd_fh_hash(&fhp->fh_handle); + __assign_str(name); + __assign_str(target); + ), + TP_printk("xid=0x%08x fh_hash=0x%08x name=%s target=%s", + __entry->xid, __entry->fh_hash, + __get_str(name), __get_str(target) + ) +); + +TRACE_EVENT(nfsd_vfs_link, + TP_PROTO( + const struct svc_rqst *rqstp, + const struct svc_fh *sfhp, + const struct svc_fh *tfhp, + const char *name, + unsigned int namelen + ), + TP_ARGS(rqstp, sfhp, tfhp, name, namelen), + TP_STRUCT__entry( + NFSD_TRACE_PROC_CALL_FIELDS(rqstp) + __field(u32, sfh_hash) + __field(u32, tfh_hash) + __string_len(name, name, namelen) + ), + TP_fast_assign( + NFSD_TRACE_PROC_CALL_ASSIGNMENTS(rqstp); + __entry->sfh_hash = knfsd_fh_hash(&sfhp->fh_handle); + __entry->tfh_hash = knfsd_fh_hash(&tfhp->fh_handle); + __assign_str(name); + ), + TP_printk("xid=0x%08x src_fh=0x%08x tgt_fh=0x%08x name=%s", + __entry->xid, __entry->sfh_hash, __entry->tfh_hash, + __get_str(name) + ) +); + +TRACE_EVENT(nfsd_vfs_unlink, + TP_PROTO( + const struct svc_rqst *rqstp, + const struct svc_fh *fhp, + const char *name, + unsigned int len + ), + TP_ARGS(rqstp, fhp, name, len), + TP_STRUCT__entry( + NFSD_TRACE_PROC_CALL_FIELDS(rqstp) + __field(u32, fh_hash) + __string_len(name, name, len) + ), + TP_fast_assign( + NFSD_TRACE_PROC_CALL_ASSIGNMENTS(rqstp); + __entry->fh_hash = knfsd_fh_hash(&fhp->fh_handle); + __assign_str(name); + ), + TP_printk("xid=0x%08x fh_hash=0x%08x name=%s", + __entry->xid, __entry->fh_hash, + __get_str(name) + ) +); + +TRACE_EVENT(nfsd_vfs_rename, + TP_PROTO( + const struct svc_rqst *rqstp, + const struct svc_fh *sfhp, + const struct svc_fh *tfhp, + const char *source, + unsigned int sourcelen, + const char *target, + unsigned int targetlen + ), + TP_ARGS(rqstp, sfhp, tfhp, source, sourcelen, target, targetlen), + TP_STRUCT__entry( + NFSD_TRACE_PROC_CALL_FIELDS(rqstp) + __field(u32, sfh_hash) + __field(u32, tfh_hash) + __string_len(source, source, sourcelen) + __string_len(target, target, targetlen) + ), + TP_fast_assign( + NFSD_TRACE_PROC_CALL_ASSIGNMENTS(rqstp); + __entry->sfh_hash = knfsd_fh_hash(&sfhp->fh_handle); + __entry->tfh_hash = knfsd_fh_hash(&tfhp->fh_handle); + __assign_str(source); + __assign_str(target); + ), + TP_printk("xid=0x%08x sfh_hash=0x%08x tfh_hash=0x%08x source=%s target=%s", + __entry->xid, __entry->sfh_hash, __entry->tfh_hash, + __get_str(source), __get_str(target) + ) +); + +TRACE_EVENT(nfsd_vfs_readdir, + TP_PROTO( + const struct svc_rqst *rqstp, + const struct svc_fh *fhp, + u32 count, + u64 offset + ), + TP_ARGS(rqstp, fhp, count, offset), + TP_STRUCT__entry( + NFSD_TRACE_PROC_CALL_FIELDS(rqstp) + __field(u32, fh_hash) + __field(u32, count) + __field(u64, offset) + ), + TP_fast_assign( + NFSD_TRACE_PROC_CALL_ASSIGNMENTS(rqstp); + __entry->fh_hash = knfsd_fh_hash(&fhp->fh_handle); + __entry->count = count; + __entry->offset = offset; + ), + TP_printk("xid=0x%08x fh_hash=0x%08x offset=%llu count=%u", + __entry->xid, __entry->fh_hash, + __entry->offset, __entry->count + ) +); + +DECLARE_EVENT_CLASS(nfsd_vfs_getattr_class, + TP_PROTO( + const struct svc_rqst *rqstp, + const struct svc_fh *fhp + ), + TP_ARGS(rqstp, fhp), + TP_STRUCT__entry( + NFSD_TRACE_PROC_CALL_FIELDS(rqstp) + __field(u32, fh_hash) + ), + TP_fast_assign( + NFSD_TRACE_PROC_CALL_ASSIGNMENTS(rqstp); + __entry->fh_hash = knfsd_fh_hash(&fhp->fh_handle); + ), + TP_printk("xid=0x%08x fh_hash=0x%08x", + __entry->xid, __entry->fh_hash + ) +); + +#define DEFINE_NFSD_VFS_GETATTR_EVENT(__name) \ +DEFINE_EVENT(nfsd_vfs_getattr_class, __name, \ + TP_PROTO( \ + const struct svc_rqst *rqstp, \ + const struct svc_fh *fhp \ + ), \ + TP_ARGS(rqstp, fhp)) + +DEFINE_NFSD_VFS_GETATTR_EVENT(nfsd_vfs_getattr); +DEFINE_NFSD_VFS_GETATTR_EVENT(nfsd_vfs_statfs); + +DECLARE_EVENT_CLASS(nfsd_pnfs_class, + TP_PROTO( + const struct nfs4_client *clp, + const char *dev, + int error + ), + TP_ARGS(clp, dev, error), + TP_STRUCT__entry( + __sockaddr(addr, sizeof(struct sockaddr_in6)) + __field(unsigned int, netns_ino) + __string(dev, dev) + __field(int, error) + ), + TP_fast_assign( + __assign_sockaddr(addr, &clp->cl_addr, + sizeof(struct sockaddr_in6)); + __entry->netns_ino = clp->net->ns.inum; + __assign_str(dev); + __entry->error = error; + ), + TP_printk("client=%pISpc nn=%d dev=%s error=%d", + __get_sockaddr(addr), + __entry->netns_ino, + __get_str(dev), + __entry->error + ) +); + +#define DEFINE_NFSD_PNFS_ERR_EVENT(name) \ +DEFINE_EVENT(nfsd_pnfs_class, nfsd_pnfs_##name, \ + TP_PROTO( \ + const struct nfs4_client *clp, \ + const char *dev, \ + int error \ + ), \ + TP_ARGS(clp, dev, error)) + +DEFINE_NFSD_PNFS_ERR_EVENT(fence); #endif /* _NFSD_TRACE_H */ #undef TRACE_INCLUDE_PATH diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 4c3a0d84043c..964cf922ad83 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -25,18 +25,17 @@ #include <linux/posix_acl_xattr.h> #include <linux/xattr.h> #include <linux/jhash.h> -#include <linux/ima.h> #include <linux/pagemap.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/exportfs.h> #include <linux/writeback.h> #include <linux/security.h> +#include <linux/sunrpc/xdr.h> #include "xdr3.h" #ifdef CONFIG_NFSD_V4 -#include "../internal.h" #include "acl.h" #include "idmap.h" #include "xdr4.h" @@ -49,6 +48,10 @@ #define NFSDDBG_FACILITY NFSDDBG_FILEOP +bool nfsd_disable_splice_read __read_mostly; +u64 nfsd_io_cache_read __read_mostly = NFSD_IO_BUFFERED; +u64 nfsd_io_cache_write __read_mostly = NFSD_IO_BUFFERED; + /** * nfserrno - Map Linux errnos to NFS errnos * @errno: POSIX(-ish) error code to be mapped @@ -73,7 +76,6 @@ nfserrno (int errno) { nfserr_acces, -EACCES }, { nfserr_exist, -EEXIST }, { nfserr_xdev, -EXDEV }, - { nfserr_mlink, -EMLINK }, { nfserr_nodev, -ENODEV }, { nfserr_notdir, -ENOTDIR }, { nfserr_isdir, -EISDIR }, @@ -101,6 +103,7 @@ nfserrno (int errno) { nfserr_io, -EUCLEAN }, { nfserr_perm, -ENOKEY }, { nfserr_no_grace, -ENOGRACE}, + { nfserr_io, -EBADMSG }, }; int i; @@ -126,9 +129,13 @@ nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp, struct dentry *dentry = *dpp; struct path path = {.mnt = mntget(exp->ex_path.mnt), .dentry = dget(dentry)}; + unsigned int follow_flags = 0; int err = 0; - err = follow_down(&path); + if (exp->ex_flags & NFSEXP_CROSSMOUNT) + follow_flags = LOOKUP_AUTOMOUNT; + + err = follow_down(&path, follow_flags); if (err < 0) goto out; if (path.mnt == exp->ex_path.mnt && path.dentry == dentry && @@ -223,7 +230,7 @@ int nfsd_mountpoint(struct dentry *dentry, struct svc_export *exp) return 1; if (nfsd4_is_junction(dentry)) return 1; - if (d_mountpoint(dentry)) + if (d_managed(dentry)) /* * Might only be a mountpoint in a different namespace, * but we need to check. @@ -242,7 +249,7 @@ nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp, struct dentry *dentry; int host_err; - dprintk("nfsd: nfsd_lookup(fh %s, %.*s)\n", SVCFH_fmt(fhp), len,name); + trace_nfsd_vfs_lookup(rqstp, fhp, name, len); dparent = fhp->fh_dentry; exp = exp_get(fhp->fh_export); @@ -262,7 +269,8 @@ nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp, goto out_nfserr; } } else { - dentry = lookup_one_len_unlocked(name, dparent, len); + dentry = lookup_one_unlocked(&nop_mnt_idmap, + &QSTR_LEN(name, len), dparent); host_err = PTR_ERR(dentry); if (IS_ERR(dentry)) goto out_nfserr; @@ -317,7 +325,7 @@ nfsd_lookup(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name, err = nfsd_lookup_dentry(rqstp, fhp, name, len, &exp, &dentry); if (err) return err; - err = check_nfsd_access(exp, rqstp); + err = check_nfsd_access(exp, rqstp, false); if (err) goto out; /* @@ -333,6 +341,24 @@ out: return err; } +static void +commit_reset_write_verifier(struct nfsd_net *nn, struct svc_rqst *rqstp, + int err) +{ + switch (err) { + case -EAGAIN: + case -ESTALE: + /* + * Neither of these are the result of a problem with + * durable storage, so avoid a write verifier reset. + */ + break; + default: + nfsd_reset_write_verifier(nn); + trace_nfsd_writeverf_reset(nn, rqstp, err); + } +} + /* * Commit metadata changes to stable storage. */ @@ -384,7 +410,9 @@ nfsd_sanitize_attrs(struct inode *inode, struct iattr *iap) iap->ia_mode &= ~S_ISGID; } else { /* set ATTR_KILL_* bits and let VFS handle it */ - iap->ia_valid |= (ATTR_KILL_SUID | ATTR_KILL_SGID); + iap->ia_valid |= ATTR_KILL_SUID; + iap->ia_valid |= + setattr_should_drop_sgid(&nop_mnt_idmap, inode); } } } @@ -398,8 +426,9 @@ nfsd_get_write_access(struct svc_rqst *rqstp, struct svc_fh *fhp, if (iap->ia_size < inode->i_size) { __be32 err; - err = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry, - NFSD_MAY_TRUNC | NFSD_MAY_OWNER_OVERRIDE); + err = nfsd_permission(&rqstp->rq_cred, + fhp->fh_export, fhp->fh_dentry, + NFSD_MAY_TRUNC | NFSD_MAY_OWNER_OVERRIDE); if (err) return err; } @@ -426,7 +455,7 @@ static int __nfsd_setattr(struct dentry *dentry, struct iattr *iap) if (iap->ia_size < 0) return -EFBIG; - host_err = notify_change(&init_user_ns, dentry, &size_attr, NULL); + host_err = notify_change(&nop_mnt_idmap, dentry, &size_attr, NULL); if (host_err) return host_err; iap->ia_valid &= ~ATTR_SIZE; @@ -440,11 +469,19 @@ static int __nfsd_setattr(struct dentry *dentry, struct iattr *iap) return 0; } - if (!iap->ia_valid) + if ((iap->ia_valid & ~ATTR_DELEG) == 0) return 0; - iap->ia_valid |= ATTR_CTIME; - return notify_change(&init_user_ns, dentry, iap, NULL); + /* + * If ATTR_DELEG is set, then this is an update from a client that + * holds a delegation. If this is an update for only the atime, the + * ctime should not be changed. If the update contains the mtime + * too, then ATTR_CTIME should already be set. + */ + if (!(iap->ia_valid & ATTR_DELEG)) + iap->ia_valid |= ATTR_CTIME; + + return notify_change(&nop_mnt_idmap, dentry, iap, NULL); } /** @@ -452,7 +489,6 @@ static int __nfsd_setattr(struct dentry *dentry, struct iattr *iap) * @rqstp: controlling RPC transaction * @fhp: filehandle of target * @attr: attributes to set - * @check_guard: set to 1 if guardtime is a valid timestamp * @guardtime: do not act if ctime.tv_sec does not match this timestamp * * This call may adjust the contents of @attr (in particular, this @@ -464,8 +500,7 @@ static int __nfsd_setattr(struct dentry *dentry, struct iattr *iap) */ __be32 nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, - struct nfsd_attrs *attr, - int check_guard, time64_t guardtime) + struct nfsd_attrs *attr, const struct timespec64 *guardtime) { struct dentry *dentry; struct inode *inode; @@ -473,11 +508,13 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, int accmode = NFSD_MAY_SATTR; umode_t ftype = 0; __be32 err; - int host_err; + int host_err = 0; bool get_write_count; bool size_change = (iap->ia_valid & ATTR_SIZE); int retries; + trace_nfsd_vfs_setattr(rqstp, fhp, iap, guardtime); + if (iap->ia_valid & ATTR_SIZE) { accmode |= NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE; ftype = S_IFREG; @@ -514,9 +551,6 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, nfsd_sanitize_attrs(inode, iap); - if (check_guard && guardtime != inode->i_ctime.tv_sec) - return nfserr_notsync; - /* * The size case is special, it changes the file in addition to the * attributes, and file systems don't expect it to be mixed with @@ -531,8 +565,29 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, } inode_lock(inode); + err = fh_fill_pre_attrs(fhp); + if (err) + goto out_unlock; + + if (guardtime) { + struct timespec64 ctime = inode_get_ctime(inode); + if ((u32)guardtime->tv_sec != (u32)ctime.tv_sec || + guardtime->tv_nsec != ctime.tv_nsec) { + err = nfserr_notsync; + goto out_fill_attrs; + } + } + for (retries = 1;;) { - host_err = __nfsd_setattr(dentry, iap); + struct iattr attrs; + + /* + * notify_change() can alter its iattr argument, making + * @iap unsuitable for submission multiple times. Make a + * copy for every loop iteration. + */ + attrs = *iap; + host_err = __nfsd_setattr(dentry, &attrs); if (host_err != -EAGAIN || !retries--) break; if (!nfsd_wait_for_delegreturn(rqstp, inode)) @@ -542,21 +597,31 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, attr->na_labelerr = security_inode_setsecctx(dentry, attr->na_seclabel->data, attr->na_seclabel->len); if (IS_ENABLED(CONFIG_FS_POSIX_ACL) && attr->na_pacl) - attr->na_aclerr = set_posix_acl(&init_user_ns, + attr->na_aclerr = set_posix_acl(&nop_mnt_idmap, dentry, ACL_TYPE_ACCESS, attr->na_pacl); if (IS_ENABLED(CONFIG_FS_POSIX_ACL) && !attr->na_aclerr && attr->na_dpacl && S_ISDIR(inode->i_mode)) - attr->na_aclerr = set_posix_acl(&init_user_ns, + attr->na_aclerr = set_posix_acl(&nop_mnt_idmap, dentry, ACL_TYPE_DEFAULT, attr->na_dpacl); +out_fill_attrs: + /* + * RFC 1813 Section 3.3.2 does not mandate that an NFS server + * returns wcc_data for SETATTR. Some client implementations + * depend on receiving wcc_data, however, to sort out partial + * updates (eg., the client requested that size and mode be + * modified, but the server changed only the file mode). + */ + fh_fill_post_attrs(fhp); +out_unlock: inode_unlock(inode); if (size_change) put_write_access(inode); out: if (!host_err) host_err = commit_metadata(fhp); - return nfserrno(host_err); + return err != 0 ? err : nfserrno(host_err); } #if defined(CONFIG_NFSD_V4) @@ -583,7 +648,7 @@ int nfsd4_is_junction(struct dentry *dentry) return 0; if (!(inode->i_mode & S_ISVTX)) return 0; - if (vfs_getxattr(&init_user_ns, dentry, NFSD_JUNCTION_XATTR_NAME, + if (vfs_getxattr(&nop_mnt_idmap, dentry, NFSD_JUNCTION_XATTR_NAME, NULL, 0) <= 0) return 0; return 1; @@ -633,8 +698,7 @@ __be32 nfsd4_clone_file_range(struct svc_rqst *rqstp, &nfsd4_get_cstate(rqstp)->current_fh, dst_pos, count, status); - nfsd_reset_write_verifier(nn); - trace_nfsd_writeverf_reset(nn, rqstp, status); + commit_reset_write_verifier(nn, rqstp, status); ret = nfserrno(status); } } @@ -766,7 +830,8 @@ nfsd_access(struct svc_rqst *rqstp, struct svc_fh *fhp, u32 *access, u32 *suppor sresult |= map->access; - err2 = nfsd_permission(rqstp, export, dentry, map->how); + err2 = nfsd_permission(&rqstp->rq_cred, export, + dentry, map->how); switch (err2) { case nfs_ok: result |= map->access; @@ -809,22 +874,19 @@ int nfsd_open_break_lease(struct inode *inode, int access) * and additional flags. * N.B. After this call fhp needs an fh_put */ -static __be32 -__nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, - int may_flags, struct file **filp) +static int +__nfsd_open(struct svc_fh *fhp, umode_t type, int may_flags, struct file **filp) { struct path path; struct inode *inode; struct file *file; int flags = O_RDONLY|O_LARGEFILE; - __be32 err; - int host_err = 0; + int host_err = -EPERM; path.mnt = fhp->fh_export->ex_path.mnt; path.dentry = fhp->fh_dentry; inode = d_inode(path.dentry); - err = nfserr_perm; if (IS_APPEND(inode) && (may_flags & NFSD_MAY_WRITE)) goto out; @@ -833,7 +895,7 @@ __nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, host_err = nfsd_open_break_lease(inode, may_flags); if (host_err) /* NOMEM or WOULDBLOCK */ - goto out_nfserr; + goto out; if (may_flags & NFSD_MAY_WRITE) { if (may_flags & NFSD_MAY_READ) @@ -845,25 +907,18 @@ __nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, file = dentry_open(&path, flags, current_cred()); if (IS_ERR(file)) { host_err = PTR_ERR(file); - goto out_nfserr; + goto out; } - host_err = ima_file_check(file, may_flags); + host_err = security_file_post_open(file, may_flags); if (host_err) { fput(file); - goto out_nfserr; + goto out; } - if (may_flags & NFSD_MAY_64BIT_COOKIE) - file->f_mode |= FMODE_64BITHASH; - else - file->f_mode |= FMODE_32BITHASH; - *filp = file; -out_nfserr: - err = nfserrno(host_err); out: - return err; + return host_err; } __be32 @@ -871,9 +926,9 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int may_flags, struct file **filp) { __be32 err; + int host_err; bool retried = false; - validate_process_creds(); /* * If we get here, then the client has already done an "open", * and (hopefully) checked permission - so allow OWNER_OVERRIDE @@ -883,49 +938,46 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, * directories, but we never have and it doesn't seem to have * caused anyone a problem. If we were to change this, note * also that our filldir callbacks would need a variant of - * lookup_one_len that doesn't check permissions. + * lookup_one_positive_unlocked() that doesn't check permissions. */ if (type == S_IFREG) may_flags |= NFSD_MAY_OWNER_OVERRIDE; retry: err = fh_verify(rqstp, fhp, type, may_flags); if (!err) { - err = __nfsd_open(rqstp, fhp, type, may_flags, filp); - if (err == nfserr_stale && !retried) { + host_err = __nfsd_open(fhp, type, may_flags, filp); + if (host_err == -EOPENSTALE && !retried) { retried = true; fh_put(fhp); goto retry; } + err = nfserrno(host_err); } - validate_process_creds(); return err; } /** * nfsd_open_verified - Open a regular file for the filecache - * @rqstp: RPC request * @fhp: NFS filehandle of the file to open + * @type: S_IFMT inode type allowed (0 means any type is allowed) * @may_flags: internal permission flags * @filp: OUT: open "struct file *" * - * Returns an nfsstat value in network byte order. + * Returns zero on success, or a negative errno value. */ -__be32 -nfsd_open_verified(struct svc_rqst *rqstp, struct svc_fh *fhp, int may_flags, - struct file **filp) +int +nfsd_open_verified(struct svc_fh *fhp, umode_t type, int may_flags, struct file **filp) { - __be32 err; - - validate_process_creds(); - err = __nfsd_open(rqstp, fhp, S_IFREG, may_flags, filp); - validate_process_creds(); - return err; + return __nfsd_open(fhp, type, may_flags, filp); } /* * Grab and keep cached pages associated with a file in the svc_rqst - * so that they can be passed to the network sendmsg/sendpage routines + * so that they can be passed to the network sendmsg routines * directly. They will be released after the sending has completed. + * + * Return values: Number of bytes consumed, or -EIO if there are no + * remaining pages in rqstp->rq_pages. */ static int nfsd_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf, @@ -937,8 +989,19 @@ nfsd_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf, struct page *last_page; last_page = page + (offset + sd->len - 1) / PAGE_SIZE; - for (page += offset / PAGE_SIZE; page <= last_page; page++) - svc_rqst_replace_page(rqstp, page); + for (page += offset / PAGE_SIZE; page <= last_page; page++) { + /* + * Skip page replacement when extending the contents of the + * current page. But note that we may get two zero_pages in a + * row from shmem. + */ + if (page == *(rqstp->rq_next_page - 1) && + offset_in_page(rqstp->rq_res.page_base + + rqstp->rq_res.page_len)) + continue; + if (unlikely(!svc_rqst_replace_page(rqstp, page))) + return -EIO; + } if (rqstp->rq_res.page_len == 0) // first call rqstp->rq_res.page_base = offset % PAGE_SIZE; rqstp->rq_res.page_len += sd->len; @@ -966,7 +1029,9 @@ static __be32 nfsd_finish_read(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned long *count, u32 *eof, ssize_t host_err) { if (host_err >= 0) { - nfsd_stats_io_read_add(fhp->fh_export, host_err); + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); + + nfsd_stats_io_read_add(nn, fhp->fh_export, host_err); *eof = nfsd_eof_on_read(file, offset, host_err, *count); *count = host_err; fsnotify_access(file); @@ -978,6 +1043,18 @@ static __be32 nfsd_finish_read(struct svc_rqst *rqstp, struct svc_fh *fhp, } } +/** + * nfsd_splice_read - Perform a VFS read using a splice pipe + * @rqstp: RPC transaction context + * @fhp: file handle of file to be read + * @file: opened struct file of file to be read + * @offset: starting byte offset + * @count: IN: requested number of bytes; OUT: number of bytes read + * @eof: OUT: set non-zero if operation reached the end of the file + * + * Returns nfs_ok on success, otherwise an nfserr stat value is + * returned. + */ __be32 nfsd_splice_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, loff_t offset, unsigned long *count, u32 *eof) @@ -991,23 +1068,153 @@ __be32 nfsd_splice_read(struct svc_rqst *rqstp, struct svc_fh *fhp, ssize_t host_err; trace_nfsd_read_splice(rqstp, fhp, offset, *count); - rqstp->rq_next_page = rqstp->rq_respages + 1; - host_err = splice_direct_to_actor(file, &sd, nfsd_direct_splice_actor); + host_err = rw_verify_area(READ, file, &offset, *count); + if (!host_err) + host_err = splice_direct_to_actor(file, &sd, + nfsd_direct_splice_actor); return nfsd_finish_read(rqstp, fhp, file, offset, count, eof, host_err); } -__be32 nfsd_readv(struct svc_rqst *rqstp, struct svc_fh *fhp, - struct file *file, loff_t offset, - struct kvec *vec, int vlen, unsigned long *count, - u32 *eof) +/* + * The byte range of the client's READ request is expanded on both ends + * until it meets the underlying file system's direct I/O alignment + * requirements. After the internal read is complete, the byte range of + * the NFS READ payload is reduced to the byte range that was originally + * requested. + * + * Note that a direct read can be done only when the xdr_buf containing + * the NFS READ reply does not already have contents in its .pages array. + * This is due to potentially restrictive alignment requirements on the + * read buffer. When .page_len and @base are zero, the .pages array is + * guaranteed to be page-aligned. + */ +static noinline_for_stack __be32 +nfsd_direct_read(struct svc_rqst *rqstp, struct svc_fh *fhp, + struct nfsd_file *nf, loff_t offset, unsigned long *count, + u32 *eof) +{ + u64 dio_start, dio_end; + unsigned long v, total; + struct iov_iter iter; + struct kiocb kiocb; + ssize_t host_err; + size_t len; + + init_sync_kiocb(&kiocb, nf->nf_file); + kiocb.ki_flags |= IOCB_DIRECT; + + /* Read a properly-aligned region of bytes into rq_bvec */ + dio_start = round_down(offset, nf->nf_dio_read_offset_align); + dio_end = round_up((u64)offset + *count, nf->nf_dio_read_offset_align); + + kiocb.ki_pos = dio_start; + + v = 0; + total = dio_end - dio_start; + while (total && v < rqstp->rq_maxpages && + rqstp->rq_next_page < rqstp->rq_page_end) { + len = min_t(size_t, total, PAGE_SIZE); + bvec_set_page(&rqstp->rq_bvec[v], *rqstp->rq_next_page, + len, 0); + + total -= len; + ++rqstp->rq_next_page; + ++v; + } + + trace_nfsd_read_direct(rqstp, fhp, offset, *count - total); + iov_iter_bvec(&iter, ITER_DEST, rqstp->rq_bvec, v, + dio_end - dio_start - total); + + host_err = vfs_iocb_iter_read(nf->nf_file, &kiocb, &iter); + if (host_err >= 0) { + unsigned int pad = offset - dio_start; + + /* The returned payload starts after the pad */ + rqstp->rq_res.page_base = pad; + + /* Compute the count of bytes to be returned */ + if (host_err > pad + *count) + host_err = *count; + else if (host_err > pad) + host_err -= pad; + else + host_err = 0; + } else if (unlikely(host_err == -EINVAL)) { + struct inode *inode = d_inode(fhp->fh_dentry); + + pr_info_ratelimited("nfsd: Direct I/O alignment failure on %s/%ld\n", + inode->i_sb->s_id, inode->i_ino); + host_err = -ESERVERFAULT; + } + + return nfsd_finish_read(rqstp, fhp, nf->nf_file, offset, count, + eof, host_err); +} + +/** + * nfsd_iter_read - Perform a VFS read using an iterator + * @rqstp: RPC transaction context + * @fhp: file handle of file to be read + * @nf: opened struct nfsd_file of file to be read + * @offset: starting byte offset + * @count: IN: requested number of bytes; OUT: number of bytes read + * @base: offset in first page of read buffer + * @eof: OUT: set non-zero if operation reached the end of the file + * + * Some filesystems or situations cannot use nfsd_splice_read. This + * function is the slightly less-performant fallback for those cases. + * + * Returns nfs_ok on success, otherwise an nfserr stat value is + * returned. + */ +__be32 nfsd_iter_read(struct svc_rqst *rqstp, struct svc_fh *fhp, + struct nfsd_file *nf, loff_t offset, unsigned long *count, + unsigned int base, u32 *eof) { + struct file *file = nf->nf_file; + unsigned long v, total; struct iov_iter iter; - loff_t ppos = offset; + struct kiocb kiocb; ssize_t host_err; + size_t len; + + init_sync_kiocb(&kiocb, file); + + switch (nfsd_io_cache_read) { + case NFSD_IO_BUFFERED: + break; + case NFSD_IO_DIRECT: + /* When dio_read_offset_align is zero, dio is not supported */ + if (nf->nf_dio_read_offset_align && !rqstp->rq_res.page_len) + return nfsd_direct_read(rqstp, fhp, nf, offset, + count, eof); + fallthrough; + case NFSD_IO_DONTCACHE: + if (file->f_op->fop_flags & FOP_DONTCACHE) + kiocb.ki_flags = IOCB_DONTCACHE; + break; + } - trace_nfsd_read_vector(rqstp, fhp, offset, *count); - iov_iter_kvec(&iter, ITER_DEST, vec, vlen, *count); - host_err = vfs_iter_read(file, &iter, &ppos, 0); + kiocb.ki_pos = offset; + + v = 0; + total = *count; + while (total && v < rqstp->rq_maxpages && + rqstp->rq_next_page < rqstp->rq_page_end) { + len = min_t(size_t, total, PAGE_SIZE - base); + bvec_set_page(&rqstp->rq_bvec[v], *rqstp->rq_next_page, + len, base); + + total -= len; + ++rqstp->rq_next_page; + ++v; + base = 0; + } + + trace_nfsd_read_vector(rqstp, fhp, offset, *count - total); + iov_iter_bvec(&iter, ITER_DEST, rqstp->rq_bvec, v, *count - total); + host_err = vfs_iocb_iter_read(file, &kiocb, &iter); return nfsd_finish_read(rqstp, fhp, file, offset, count, eof, host_err); } @@ -1039,7 +1246,7 @@ static int wait_for_concurrent_writes(struct file *file) dprintk("nfsd: write resume %d\n", task_pid_nr(current)); } - if (inode->i_state & I_DIRTY) { + if (inode_state_read_once(inode) & I_DIRTY) { dprintk("nfsd: write sync %d\n", task_pid_nr(current)); err = vfs_fsync(file, 0); } @@ -1048,26 +1255,171 @@ static int wait_for_concurrent_writes(struct file *file) return err; } +struct nfsd_write_dio_seg { + struct iov_iter iter; + int flags; +}; + +static unsigned long +iov_iter_bvec_offset(const struct iov_iter *iter) +{ + return (unsigned long)(iter->bvec->bv_offset + iter->iov_offset); +} + +static void +nfsd_write_dio_seg_init(struct nfsd_write_dio_seg *segment, + struct bio_vec *bvec, unsigned int nvecs, + unsigned long total, size_t start, size_t len, + struct kiocb *iocb) +{ + iov_iter_bvec(&segment->iter, ITER_SOURCE, bvec, nvecs, total); + if (start) + iov_iter_advance(&segment->iter, start); + iov_iter_truncate(&segment->iter, len); + segment->flags = iocb->ki_flags; +} + +static unsigned int +nfsd_write_dio_iters_init(struct nfsd_file *nf, struct bio_vec *bvec, + unsigned int nvecs, struct kiocb *iocb, + unsigned long total, + struct nfsd_write_dio_seg segments[3]) +{ + u32 offset_align = nf->nf_dio_offset_align; + loff_t prefix_end, orig_end, middle_end; + u32 mem_align = nf->nf_dio_mem_align; + size_t prefix, middle, suffix; + loff_t offset = iocb->ki_pos; + unsigned int nsegs = 0; + + /* + * Check if direct I/O is feasible for this write request. + * If alignments are not available, the write is too small, + * or no alignment can be found, fall back to buffered I/O. + */ + if (unlikely(!mem_align || !offset_align) || + unlikely(total < max(offset_align, mem_align))) + goto no_dio; + + prefix_end = round_up(offset, offset_align); + orig_end = offset + total; + middle_end = round_down(orig_end, offset_align); + + prefix = prefix_end - offset; + middle = middle_end - prefix_end; + suffix = orig_end - middle_end; + + if (!middle) + goto no_dio; + + if (prefix) + nfsd_write_dio_seg_init(&segments[nsegs++], bvec, + nvecs, total, 0, prefix, iocb); + + nfsd_write_dio_seg_init(&segments[nsegs], bvec, nvecs, + total, prefix, middle, iocb); + + /* + * Check if the bvec iterator is aligned for direct I/O. + * + * bvecs generated from RPC receive buffers are contiguous: After + * the first bvec, all subsequent bvecs start at bv_offset zero + * (page-aligned). Therefore, only the first bvec is checked. + */ + if (iov_iter_bvec_offset(&segments[nsegs].iter) & (mem_align - 1)) + goto no_dio; + segments[nsegs].flags |= IOCB_DIRECT; + nsegs++; + + if (suffix) + nfsd_write_dio_seg_init(&segments[nsegs++], bvec, nvecs, total, + prefix + middle, suffix, iocb); + + return nsegs; + +no_dio: + /* No DIO alignment possible - pack into single non-DIO segment. */ + nfsd_write_dio_seg_init(&segments[0], bvec, nvecs, total, 0, + total, iocb); + return 1; +} + +static noinline_for_stack int +nfsd_direct_write(struct svc_rqst *rqstp, struct svc_fh *fhp, + struct nfsd_file *nf, unsigned int nvecs, + unsigned long *cnt, struct kiocb *kiocb) +{ + struct nfsd_write_dio_seg segments[3]; + struct file *file = nf->nf_file; + unsigned int nsegs, i; + ssize_t host_err; + + nsegs = nfsd_write_dio_iters_init(nf, rqstp->rq_bvec, nvecs, + kiocb, *cnt, segments); + + *cnt = 0; + for (i = 0; i < nsegs; i++) { + kiocb->ki_flags = segments[i].flags; + if (kiocb->ki_flags & IOCB_DIRECT) + trace_nfsd_write_direct(rqstp, fhp, kiocb->ki_pos, + segments[i].iter.count); + else { + trace_nfsd_write_vector(rqstp, fhp, kiocb->ki_pos, + segments[i].iter.count); + /* + * Mark the I/O buffer as evict-able to reduce + * memory contention. + */ + if (nf->nf_file->f_op->fop_flags & FOP_DONTCACHE) + kiocb->ki_flags |= IOCB_DONTCACHE; + } + + host_err = vfs_iocb_iter_write(file, kiocb, &segments[i].iter); + if (host_err < 0) + return host_err; + *cnt += host_err; + if (host_err < segments[i].iter.count) + break; /* partial write */ + } + + return 0; +} + +/** + * nfsd_vfs_write - write data to an already-open file + * @rqstp: RPC execution context + * @fhp: File handle of file to write into + * @nf: An open file matching @fhp + * @offset: Byte offset of start + * @payload: xdr_buf containing the write payload + * @cnt: IN: number of bytes to write, OUT: number of bytes actually written + * @stable: An NFS stable_how value + * @verf: NFS WRITE verifier + * + * Upon return, caller must invoke fh_put on @fhp. + * + * Return values: + * An nfsstat value in network byte order. + */ __be32 -nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf, - loff_t offset, struct kvec *vec, int vlen, - unsigned long *cnt, int stable, - __be32 *verf) +nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, + struct nfsd_file *nf, loff_t offset, + const struct xdr_buf *payload, unsigned long *cnt, + int stable, __be32 *verf) { struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); struct file *file = nf->nf_file; struct super_block *sb = file_inode(file)->i_sb; + struct kiocb kiocb; struct svc_export *exp; struct iov_iter iter; errseq_t since; __be32 nfserr; int host_err; - int use_wgather; - loff_t pos = offset; unsigned long exp_op_flags = 0; unsigned int pflags = current->flags; - rwf_t flags = 0; bool restore_flags = false; + unsigned int nvecs; trace_nfsd_write_opened(rqstp, fhp, offset, *cnt); @@ -1088,37 +1440,61 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf, } exp = fhp->fh_export; - use_wgather = (rqstp->rq_vers == 2) && EX_WGATHER(exp); if (!EX_ISSYNC(exp)) stable = NFS_UNSTABLE; + init_sync_kiocb(&kiocb, file); + kiocb.ki_pos = offset; + if (likely(!fhp->fh_use_wgather)) { + switch (stable) { + case NFS_FILE_SYNC: + /* persist data and timestamps */ + kiocb.ki_flags |= IOCB_DSYNC | IOCB_SYNC; + break; + case NFS_DATA_SYNC: + /* persist data only */ + kiocb.ki_flags |= IOCB_DSYNC; + break; + } + } - if (stable && !use_wgather) - flags |= RWF_SYNC; + nvecs = xdr_buf_to_bvec(rqstp->rq_bvec, rqstp->rq_maxpages, payload); - iov_iter_kvec(&iter, ITER_SOURCE, vec, vlen, *cnt); since = READ_ONCE(file->f_wb_err); if (verf) nfsd_copy_write_verifier(verf, nn); - host_err = vfs_iter_write(file, &iter, &pos, flags); + + switch (nfsd_io_cache_write) { + case NFSD_IO_DIRECT: + host_err = nfsd_direct_write(rqstp, fhp, nf, nvecs, + cnt, &kiocb); + break; + case NFSD_IO_DONTCACHE: + if (file->f_op->fop_flags & FOP_DONTCACHE) + kiocb.ki_flags |= IOCB_DONTCACHE; + fallthrough; + case NFSD_IO_BUFFERED: + iov_iter_bvec(&iter, ITER_SOURCE, rqstp->rq_bvec, nvecs, *cnt); + host_err = vfs_iocb_iter_write(file, &kiocb, &iter); + if (host_err < 0) + break; + *cnt = host_err; + break; + } if (host_err < 0) { - nfsd_reset_write_verifier(nn); - trace_nfsd_writeverf_reset(nn, rqstp, host_err); + commit_reset_write_verifier(nn, rqstp, host_err); goto out_nfserr; } - *cnt = host_err; - nfsd_stats_io_write_add(exp, *cnt); + nfsd_stats_io_write_add(nn, exp, *cnt); fsnotify_modify(file); host_err = filemap_check_wb_err(file->f_mapping, since); if (host_err < 0) goto out_nfserr; - if (stable && use_wgather) { + if (stable && fhp->fh_use_wgather) { host_err = wait_for_concurrent_writes(file); - if (host_err < 0) { - nfsd_reset_write_verifier(nn); - trace_nfsd_writeverf_reset(nn, rqstp, host_err); - } + if (host_err < 0) + commit_reset_write_verifier(nn, rqstp, host_err); } out_nfserr: @@ -1134,14 +1510,50 @@ out_nfserr: return nfserr; } -/* - * Read data from a file. count must contain the requested read count - * on entry. On return, *count contains the number of bytes actually read. +/** + * nfsd_read_splice_ok - check if spliced reading is supported + * @rqstp: RPC transaction context + * + * Return values: + * %true: nfsd_splice_read() may be used + * %false: nfsd_splice_read() must not be used + * + * NFS READ normally uses splice to send data in-place. However the + * data in cache can change after the reply's MIC is computed but + * before the RPC reply is sent. To prevent the client from + * rejecting the server-computed MIC in this somewhat rare case, do + * not use splice with the GSS integrity and privacy services. + */ +bool nfsd_read_splice_ok(struct svc_rqst *rqstp) +{ + if (nfsd_disable_splice_read) + return false; + switch (svc_auth_flavor(rqstp)) { + case RPC_AUTH_GSS_KRB5I: + case RPC_AUTH_GSS_KRB5P: + return false; + } + return true; +} + +/** + * nfsd_read - Read data from a file + * @rqstp: RPC transaction context + * @fhp: file handle of file to be read + * @offset: starting byte offset + * @count: IN: requested number of bytes; OUT: number of bytes read + * @eof: OUT: set non-zero if operation reached the end of the file + * + * The caller must verify that there is enough space in @rqstp.rq_res + * to perform this operation. + * * N.B. After this call fhp needs an fh_put + * + * Returns nfs_ok on success, otherwise an nfserr stat value is + * returned. */ __be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp, - loff_t offset, struct kvec *vec, int vlen, unsigned long *count, - u32 *eof) + loff_t offset, unsigned long *count, u32 *eof) { struct nfsd_file *nf; struct file *file; @@ -1153,26 +1565,34 @@ __be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp, return err; file = nf->nf_file; - if (file->f_op->splice_read && test_bit(RQ_SPLICE_OK, &rqstp->rq_flags)) + if (file->f_op->splice_read && nfsd_read_splice_ok(rqstp)) err = nfsd_splice_read(rqstp, fhp, file, offset, count, eof); else - err = nfsd_readv(rqstp, fhp, file, offset, vec, vlen, count, eof); + err = nfsd_iter_read(rqstp, fhp, nf, offset, count, 0, eof); nfsd_file_put(nf); - trace_nfsd_read_done(rqstp, fhp, offset, *count); - return err; } -/* - * Write data to a file. - * The stable flag requests synchronous writes. - * N.B. After this call fhp needs an fh_put +/** + * nfsd_write - open a file and write data to it + * @rqstp: RPC execution context + * @fhp: File handle of file to write into; nfsd_write() may modify it + * @offset: Byte offset of start + * @payload: xdr_buf containing the write payload + * @cnt: IN: number of bytes to write, OUT: number of bytes actually written + * @stable: An NFS stable_how value + * @verf: NFS WRITE verifier + * + * Upon return, caller must invoke fh_put on @fhp. + * + * Return values: + * An nfsstat value in network byte order. */ __be32 nfsd_write(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t offset, - struct kvec *vec, int vlen, unsigned long *cnt, int stable, + const struct xdr_buf *payload, unsigned long *cnt, int stable, __be32 *verf) { struct nfsd_file *nf; @@ -1184,8 +1604,8 @@ nfsd_write(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t offset, if (err) goto out; - err = nfsd_vfs_write(rqstp, fhp, nf, offset, vec, - vlen, cnt, stable, verf); + err = nfsd_vfs_write(rqstp, fhp, nf, offset, payload, cnt, + stable, verf); nfsd_file_put(nf); out: trace_nfsd_write_done(rqstp, fhp, offset, *cnt); @@ -1221,6 +1641,8 @@ nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf, loff_t start, end; struct nfsd_net *nn; + trace_nfsd_commit_start(rqstp, fhp, offset, count); + /* * Convert the client-provided (offset, count) range to a * (start, end) range. If the client-provided range falls @@ -1253,13 +1675,13 @@ nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf, err = nfserr_notsupp; break; default: - nfsd_reset_write_verifier(nn); - trace_nfsd_writeverf_reset(nn, rqstp, err2); + commit_reset_write_verifier(nn, rqstp, err2); err = nfserrno(err2); } } else nfsd_copy_write_verifier(verf, nn); + trace_nfsd_commit_done(rqstp, fhp, offset, count); return err; } @@ -1296,8 +1718,8 @@ nfsd_create_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, * Callers expect new file metadata to be committed even * if the attributes have not changed. */ - if (iap->ia_valid) - status = nfsd_setattr(rqstp, resfhp, attrs, 0, (time64_t)0); + if (nfsd_attrs_valid(attrs)) + status = nfsd_setattr(rqstp, resfhp, attrs, NULL); else status = nfserrno(commit_metadata(resfhp)); @@ -1333,7 +1755,7 @@ nfsd_check_ignore_resizing(struct iattr *iap) iap->ia_valid &= ~ATTR_SIZE; } -/* The parent directory should already be locked: */ +/* The parent directory should already be locked - we will unlock */ __be32 nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_attrs *attrs, @@ -1343,13 +1765,14 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp, struct inode *dirp; struct iattr *iap = attrs->na_iattr; __be32 err; - int host_err; + int host_err = 0; dentry = fhp->fh_dentry; dirp = d_inode(dentry); dchild = dget(resfhp->fh_dentry); - err = nfsd_permission(rqstp, fhp->fh_export, dentry, NFSD_MAY_CREATE); + err = nfsd_permission(&rqstp->rq_cred, fhp->fh_export, dentry, + NFSD_MAY_CREATE); if (err) goto out; @@ -1363,41 +1786,28 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp, err = 0; switch (type) { case S_IFREG: - host_err = vfs_create(&init_user_ns, dirp, dchild, iap->ia_mode, true); + host_err = vfs_create(&nop_mnt_idmap, dchild, iap->ia_mode, NULL); if (!host_err) nfsd_check_ignore_resizing(iap); break; case S_IFDIR: - host_err = vfs_mkdir(&init_user_ns, dirp, dchild, iap->ia_mode); - if (!host_err && unlikely(d_unhashed(dchild))) { - struct dentry *d; - d = lookup_one_len(dchild->d_name.name, - dchild->d_parent, - dchild->d_name.len); - if (IS_ERR(d)) { - host_err = PTR_ERR(d); - break; - } - if (unlikely(d_is_negative(d))) { - dput(d); - err = nfserr_serverfault; - goto out; - } + dchild = vfs_mkdir(&nop_mnt_idmap, dirp, dchild, iap->ia_mode, NULL); + if (IS_ERR(dchild)) { + host_err = PTR_ERR(dchild); + } else if (d_is_negative(dchild)) { + err = nfserr_serverfault; + goto out; + } else if (unlikely(dchild != resfhp->fh_dentry)) { dput(resfhp->fh_dentry); - resfhp->fh_dentry = dget(d); - err = fh_update(resfhp); - dput(dchild); - dchild = d; - if (err) - goto out; + resfhp->fh_dentry = dget(dchild); } break; case S_IFCHR: case S_IFBLK: case S_IFIFO: case S_IFSOCK: - host_err = vfs_mknod(&init_user_ns, dirp, dchild, - iap->ia_mode, rdev); + host_err = vfs_mknod(&nop_mnt_idmap, dirp, dchild, + iap->ia_mode, rdev, NULL); break; default: printk(KERN_WARNING "nfsd: bad file type %o in nfsd_create\n", @@ -1410,7 +1820,9 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp, err = nfsd_create_setattr(rqstp, fhp, resfhp, attrs); out: - dput(dchild); + if (!err) + fh_fill_post_attrs(fhp); + end_creating(dchild); return err; out_nfserr: @@ -1433,6 +1845,8 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, __be32 err; int host_err; + trace_nfsd_vfs_create(rqstp, fhp, type, fname, flen); + if (isdotent(fname, flen)) return nfserr_exist; @@ -1446,26 +1860,24 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, if (host_err) return nfserrno(host_err); - inode_lock_nested(dentry->d_inode, I_MUTEX_PARENT); - dchild = lookup_one_len(fname, dentry, flen); + dchild = start_creating(&nop_mnt_idmap, dentry, &QSTR_LEN(fname, flen)); host_err = PTR_ERR(dchild); - if (IS_ERR(dchild)) { - err = nfserrno(host_err); - goto out_unlock; - } + if (IS_ERR(dchild)) + return nfserrno(host_err); + err = fh_compose(resfhp, fhp->fh_export, dchild, fhp); - /* - * We unconditionally drop our ref to dchild as fh_compose will have - * already grabbed its own ref for it. - */ - dput(dchild); if (err) goto out_unlock; - fh_fill_pre_attrs(fhp); + err = fh_fill_pre_attrs(fhp); + if (err != nfs_ok) + goto out_unlock; err = nfsd_create_locked(rqstp, fhp, attrs, type, rdev, resfhp); - fh_fill_post_attrs(fhp); + /* nfsd_create_locked() unlocked the parent */ + dput(dchild); + return err; + out_unlock: - inode_unlock(dentry->d_inode); + end_creating(dchild); return err; } @@ -1531,6 +1943,8 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp, __be32 err, cerr; int host_err; + trace_nfsd_vfs_symlink(rqstp, fhp, fname, flen, path); + err = nfserr_noent; if (!flen || path[0] == '\0') goto out; @@ -1549,34 +1963,43 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp, } dentry = fhp->fh_dentry; - inode_lock_nested(dentry->d_inode, I_MUTEX_PARENT); - dnew = lookup_one_len(fname, dentry, flen); + dnew = start_creating(&nop_mnt_idmap, dentry, &QSTR_LEN(fname, flen)); if (IS_ERR(dnew)) { err = nfserrno(PTR_ERR(dnew)); - inode_unlock(dentry->d_inode); goto out_drop_write; } - fh_fill_pre_attrs(fhp); - host_err = vfs_symlink(&init_user_ns, d_inode(dentry), dnew, path); + err = fh_fill_pre_attrs(fhp); + if (err != nfs_ok) + goto out_unlock; + host_err = vfs_symlink(&nop_mnt_idmap, d_inode(dentry), dnew, path, NULL); err = nfserrno(host_err); cerr = fh_compose(resfhp, fhp->fh_export, dnew, fhp); if (!err) nfsd_create_setattr(rqstp, fhp, resfhp, attrs); fh_fill_post_attrs(fhp); - inode_unlock(dentry->d_inode); +out_unlock: + end_creating(dnew); if (!err) err = nfserrno(commit_metadata(fhp)); - dput(dnew); - if (err==0) err = cerr; + if (!err) + err = cerr; out_drop_write: fh_drop_write(fhp); out: return err; } -/* - * Create a hardlink - * N.B. After this call _both_ ffhp and tfhp need an fh_put +/** + * nfsd_link - create a link + * @rqstp: RPC transaction context + * @ffhp: the file handle of the directory where the new link is to be created + * @name: the filename of the new link + * @len: the length of @name in octets + * @tfhp: the file handle of an existing file object + * + * After this call _both_ ffhp and tfhp need an fh_put. + * + * Returns a generic NFS status code in network byte-order. */ __be32 nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp, @@ -1584,9 +2007,12 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp, { struct dentry *ddir, *dnew, *dold; struct inode *dirp; + int type; __be32 err; int host_err; + trace_nfsd_vfs_link(rqstp, ffhp, tfhp, name, len); + err = fh_verify(rqstp, ffhp, S_IFDIR, NFSD_MAY_CREATE); if (err) goto out; @@ -1603,52 +2029,53 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp, if (isdotent(name, len)) goto out; + err = nfs_ok; + type = d_inode(tfhp->fh_dentry)->i_mode & S_IFMT; host_err = fh_want_write(tfhp); - if (host_err) { - err = nfserrno(host_err); + if (host_err) goto out; - } ddir = ffhp->fh_dentry; dirp = d_inode(ddir); - inode_lock_nested(dirp, I_MUTEX_PARENT); + dnew = start_creating(&nop_mnt_idmap, ddir, &QSTR_LEN(name, len)); - dnew = lookup_one_len(name, ddir, len); if (IS_ERR(dnew)) { - err = nfserrno(PTR_ERR(dnew)); - goto out_unlock; + host_err = PTR_ERR(dnew); + goto out_drop_write; } dold = tfhp->fh_dentry; err = nfserr_noent; if (d_really_is_negative(dold)) - goto out_dput; - fh_fill_pre_attrs(ffhp); - host_err = vfs_link(dold, &init_user_ns, dirp, dnew, NULL); + goto out_unlock; + err = fh_fill_pre_attrs(ffhp); + if (err != nfs_ok) + goto out_unlock; + host_err = vfs_link(dold, &nop_mnt_idmap, dirp, dnew, NULL); fh_fill_post_attrs(ffhp); - inode_unlock(dirp); +out_unlock: + end_creating(dnew); if (!host_err) { - err = nfserrno(commit_metadata(ffhp)); - if (!err) - err = nfserrno(commit_metadata(tfhp)); - } else { - if (host_err == -EXDEV && rqstp->rq_vers == 2) - err = nfserr_acces; - else - err = nfserrno(host_err); + host_err = commit_metadata(ffhp); + if (!host_err) + host_err = commit_metadata(tfhp); } - dput(dnew); + out_drop_write: fh_drop_write(tfhp); + if (host_err == -EBUSY) { + /* + * See RFC 8881 Section 18.9.4 para 1-2: NFSv4 LINK + * wants a status unique to the object type. + */ + if (type != S_IFDIR) + err = nfserr_file_open; + else + err = nfserr_acces; + } out: - return err; - -out_dput: - dput(dnew); -out_unlock: - inode_unlock(dirp); - goto out_drop_write; + return err != nfs_ok ? err : nfserrno(host_err); } static void @@ -1671,19 +2098,32 @@ nfsd_has_cached_files(struct dentry *dentry) return ret; } -/* - * Rename a file - * N.B. After this call _both_ ffhp and tfhp need an fh_put +/** + * nfsd_rename - rename a directory entry + * @rqstp: RPC transaction context + * @ffhp: the file handle of parent directory containing the entry to be renamed + * @fname: the filename of directory entry to be renamed + * @flen: the length of @fname in octets + * @tfhp: the file handle of parent directory to contain the renamed entry + * @tname: the filename of the new entry + * @tlen: the length of @tlen in octets + * + * After this call _both_ ffhp and tfhp need an fh_put. + * + * Returns a generic NFS status code in network byte-order. */ __be32 nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen, struct svc_fh *tfhp, char *tname, int tlen) { - struct dentry *fdentry, *tdentry, *odentry, *ndentry, *trap; - struct inode *fdir, *tdir; + struct dentry *fdentry, *tdentry; + int type = S_IFDIR; + struct renamedata rd = {}; __be32 err; int host_err; - bool close_cached = false; + struct dentry *close_cached; + + trace_nfsd_vfs_rename(rqstp, ffhp, tfhp, fname, flen, tname, tlen); err = fh_verify(rqstp, ffhp, S_IFDIR, NFSD_MAY_REMOVE); if (err) @@ -1693,72 +2133,62 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen, goto out; fdentry = ffhp->fh_dentry; - fdir = d_inode(fdentry); tdentry = tfhp->fh_dentry; - tdir = d_inode(tdentry); err = nfserr_perm; if (!flen || isdotent(fname, flen) || !tlen || isdotent(tname, tlen)) goto out; + err = nfserr_xdev; + if (ffhp->fh_export->ex_path.mnt != tfhp->fh_export->ex_path.mnt) + goto out; + if (ffhp->fh_export->ex_path.dentry != tfhp->fh_export->ex_path.dentry) + goto out; + retry: + close_cached = NULL; host_err = fh_want_write(ffhp); if (host_err) { err = nfserrno(host_err); goto out; } - trap = lock_rename(tdentry, fdentry); - fh_fill_pre_attrs(ffhp); - fh_fill_pre_attrs(tfhp); + rd.mnt_idmap = &nop_mnt_idmap; + rd.old_parent = fdentry; + rd.new_parent = tdentry; - odentry = lookup_one_len(fname, fdentry, flen); - host_err = PTR_ERR(odentry); - if (IS_ERR(odentry)) - goto out_nfserr; + host_err = start_renaming(&rd, 0, &QSTR_LEN(fname, flen), + &QSTR_LEN(tname, tlen)); - host_err = -ENOENT; - if (d_really_is_negative(odentry)) - goto out_dput_old; - host_err = -EINVAL; - if (odentry == trap) - goto out_dput_old; - - ndentry = lookup_one_len(tname, tdentry, tlen); - host_err = PTR_ERR(ndentry); - if (IS_ERR(ndentry)) - goto out_dput_old; - host_err = -ENOTEMPTY; - if (ndentry == trap) - goto out_dput_new; - - host_err = -EXDEV; - if (ffhp->fh_export->ex_path.mnt != tfhp->fh_export->ex_path.mnt) - goto out_dput_new; - if (ffhp->fh_export->ex_path.dentry != tfhp->fh_export->ex_path.dentry) - goto out_dput_new; + if (host_err) { + err = nfserrno(host_err); + goto out_want_write; + } + err = fh_fill_pre_attrs(ffhp); + if (err != nfs_ok) + goto out_unlock; + err = fh_fill_pre_attrs(tfhp); + if (err != nfs_ok) + goto out_unlock; + + type = d_inode(rd.old_dentry)->i_mode & S_IFMT; + + if (d_inode(rd.new_dentry)) + type = d_inode(rd.new_dentry)->i_mode & S_IFMT; - if ((ndentry->d_sb->s_export_op->flags & EXPORT_OP_CLOSE_BEFORE_UNLINK) && - nfsd_has_cached_files(ndentry)) { - close_cached = true; - goto out_dput_old; + if ((rd.new_dentry->d_sb->s_export_op->flags & EXPORT_OP_CLOSE_BEFORE_UNLINK) && + nfsd_has_cached_files(rd.new_dentry)) { + close_cached = dget(rd.new_dentry); + goto out_unlock; } else { - struct renamedata rd = { - .old_mnt_userns = &init_user_ns, - .old_dir = fdir, - .old_dentry = odentry, - .new_mnt_userns = &init_user_ns, - .new_dir = tdir, - .new_dentry = ndentry, - }; int retries; for (retries = 1;;) { host_err = vfs_rename(&rd); if (host_err != -EAGAIN || !retries--) break; - if (!nfsd_wait_for_delegreturn(rqstp, d_inode(odentry))) + if (!nfsd_wait_for_delegreturn(rqstp, d_inode(rd.old_dentry))) break; } if (!host_err) { @@ -1767,39 +2197,54 @@ retry: host_err = commit_metadata(ffhp); } } - out_dput_new: - dput(ndentry); - out_dput_old: - dput(odentry); - out_nfserr: - err = nfserrno(host_err); + if (host_err == -EBUSY) { + /* + * See RFC 8881 Section 18.26.4 para 1-3: NFSv4 RENAME + * wants a status unique to the object type. + */ + if (type != S_IFDIR) + err = nfserr_file_open; + else + err = nfserr_acces; + } else { + err = nfserrno(host_err); + } if (!close_cached) { fh_fill_post_attrs(ffhp); fh_fill_post_attrs(tfhp); } - unlock_rename(tdentry, fdentry); +out_unlock: + end_renaming(&rd); +out_want_write: fh_drop_write(ffhp); /* - * If the target dentry has cached open files, then we need to try to - * close them prior to doing the rename. Flushing delayed fput - * shouldn't be done with locks held however, so we delay it until this - * point and then reattempt the whole shebang. + * If the target dentry has cached open files, then we need to + * try to close them prior to doing the rename. Final fput + * shouldn't be done with locks held however, so we delay it + * until this point and then reattempt the whole shebang. */ if (close_cached) { - close_cached = false; - nfsd_close_cached_files(ndentry); - dput(ndentry); + nfsd_close_cached_files(close_cached); + dput(close_cached); goto retry; } out: return err; } -/* - * Unlink a file or directory - * N.B. After this call fhp needs an fh_put +/** + * nfsd_unlink - remove a directory entry + * @rqstp: RPC transaction context + * @fhp: the file handle of the parent directory to be modified + * @type: enforced file type of the object to be removed + * @fname: the name of directory entry to be removed + * @flen: length of @fname in octets + * + * After this call fhp needs an fh_put. + * + * Returns a generic NFS status code in network byte-order. */ __be32 nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, @@ -1807,10 +2252,12 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, { struct dentry *dentry, *rdentry; struct inode *dirp; - struct inode *rinode; + struct inode *rinode = NULL; __be32 err; int host_err; + trace_nfsd_vfs_unlink(rqstp, fhp, fname, flen); + err = nfserr_acces; if (!flen || isdotent(fname, flen)) goto out; @@ -1824,25 +2271,24 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, dentry = fhp->fh_dentry; dirp = d_inode(dentry); - inode_lock_nested(dirp, I_MUTEX_PARENT); - rdentry = lookup_one_len(fname, dentry, flen); + rdentry = start_removing(&nop_mnt_idmap, dentry, &QSTR_LEN(fname, flen)); + host_err = PTR_ERR(rdentry); if (IS_ERR(rdentry)) - goto out_unlock; + goto out_drop_write; - if (d_really_is_negative(rdentry)) { - dput(rdentry); - host_err = -ENOENT; + err = fh_fill_pre_attrs(fhp); + if (err != nfs_ok) goto out_unlock; - } + rinode = d_inode(rdentry); + /* Prevent truncation until after locks dropped */ ihold(rinode); if (!type) type = d_inode(rdentry)->i_mode & S_IFMT; - fh_fill_pre_attrs(fhp); if (type != S_IFDIR) { int retries; @@ -1850,42 +2296,38 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, nfsd_close_cached_files(rdentry); for (retries = 1;;) { - host_err = vfs_unlink(&init_user_ns, dirp, rdentry, NULL); + host_err = vfs_unlink(&nop_mnt_idmap, dirp, rdentry, NULL); if (host_err != -EAGAIN || !retries--) break; if (!nfsd_wait_for_delegreturn(rqstp, rinode)) break; } } else { - host_err = vfs_rmdir(&init_user_ns, dirp, rdentry); + host_err = vfs_rmdir(&nop_mnt_idmap, dirp, rdentry, NULL); } fh_fill_post_attrs(fhp); - inode_unlock(dirp); - if (!host_err) +out_unlock: + end_removing(rdentry); + if (!err && !host_err) host_err = commit_metadata(fhp); - dput(rdentry); iput(rinode); /* truncate the inode here */ out_drop_write: fh_drop_write(fhp); out_nfserr: if (host_err == -EBUSY) { - /* name is mounted-on. There is no perfect - * error status. + /* + * See RFC 8881 Section 18.25.4 para 4: NFSv4 REMOVE + * wants a status unique to the object type. */ - if (nfsd_v4client(rqstp)) + if (type != S_IFDIR) err = nfserr_file_open; else err = nfserr_acces; - } else { - err = nfserrno(host_err); } out: - return err; -out_unlock: - inode_unlock(dirp); - goto out_drop_write; + return err != nfs_ok ? err : nfserrno(host_err); } /* @@ -2005,9 +2447,23 @@ static __be32 nfsd_buffered_readdir(struct file *file, struct svc_fh *fhp, return cdp->err; } -/* - * Read entries from a directory. - * The NFSv3/4 verifier we ignore for now. +/** + * nfsd_readdir - Read entries from a directory + * @rqstp: RPC transaction context + * @fhp: NFS file handle of directory to be read + * @offsetp: OUT: seek offset of final entry that was read + * @cdp: OUT: an eof error value + * @func: entry filler actor + * + * This implementation ignores the NFSv3/4 verifier cookie. + * + * NB: normal system calls hold file->f_pos_lock when calling + * ->iterate_shared and ->llseek, but nfsd_readdir() does not. + * Because the struct file acquired here is not visible to other + * threads, it's internal state does not need mutex protection. + * + * Returns nfs_ok on success, otherwise an nfsstat code is + * returned. */ __be32 nfsd_readdir(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t *offsetp, @@ -2018,14 +2474,15 @@ nfsd_readdir(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t *offsetp, loff_t offset = *offsetp; int may_flags = NFSD_MAY_READ; - /* NFSv2 only supports 32 bit cookies */ - if (rqstp->rq_vers > 2) - may_flags |= NFSD_MAY_64BIT_COOKIE; - err = nfsd_open(rqstp, fhp, S_IFDIR, may_flags, &file); if (err) goto out; + if (fhp->fh_64bit_cookies) + file->f_mode |= FMODE_64BITHASH; + else + file->f_mode |= FMODE_32BITHASH; + offset = vfs_llseek(file, offset, SEEK_SET); if (offset < 0) { err = nfserrno((int)offset); @@ -2037,11 +2494,43 @@ nfsd_readdir(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t *offsetp, if (err == nfserr_eof || err == nfserr_toosmall) err = nfs_ok; /* can still be found in ->err */ out_close: - fput(file); + nfsd_filp_close(file); out: return err; } +/** + * nfsd_filp_close: close a file synchronously + * @fp: the file to close + * + * nfsd_filp_close() is similar in behaviour to filp_close(). + * The difference is that if this is the final close on the + * file, the that finalisation happens immediately, rather then + * being handed over to a work_queue, as it the case for + * filp_close(). + * When a user-space process closes a file (even when using + * filp_close() the finalisation happens before returning to + * userspace, so it is effectively synchronous. When a kernel thread + * uses file_close(), on the other hand, the handling is completely + * asynchronous. This means that any cost imposed by that finalisation + * is not imposed on the nfsd thread, and nfsd could potentually + * close files more quickly than the work queue finalises the close, + * which would lead to unbounded growth in the queue. + * + * In some contexts is it not safe to synchronously wait for + * close finalisation (see comment for __fput_sync()), but nfsd + * does not match those contexts. In partcilarly it does not, at the + * time that this function is called, hold and locks and no finalisation + * of any file, socket, or device driver would have any cause to wait + * for nfsd to make progress. + */ +void nfsd_filp_close(struct file *fp) +{ + get_file(fp); + filp_close(fp, NULL); + __fput_sync(fp); +} + /* * Get file system stats * N.B. After this call fhp needs an fh_put @@ -2051,6 +2540,8 @@ nfsd_statfs(struct svc_rqst *rqstp, struct svc_fh *fhp, struct kstatfs *stat, in { __be32 err; + trace_nfsd_vfs_statfs(rqstp, fhp); + err = fh_verify(rqstp, fhp, 0, NFSD_MAY_NOP | access); if (!err) { struct path path = { @@ -2063,9 +2554,9 @@ nfsd_statfs(struct svc_rqst *rqstp, struct svc_fh *fhp, struct kstatfs *stat, in return err; } -static int exp_rdonly(struct svc_rqst *rqstp, struct svc_export *exp) +static int exp_rdonly(struct svc_cred *cred, struct svc_export *exp) { - return nfsexp_flags(rqstp, exp) & NFSEXP_READONLY; + return nfsexp_flags(cred, exp) & NFSEXP_READONLY; } #ifdef CONFIG_NFSD_V4 @@ -2129,7 +2620,7 @@ nfsd_getxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name, inode_lock_shared(inode); - len = vfs_getxattr(&init_user_ns, dentry, name, NULL, 0); + len = vfs_getxattr(&nop_mnt_idmap, dentry, name, NULL, 0); /* * Zero-length attribute, just return. @@ -2150,13 +2641,13 @@ nfsd_getxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name, goto out; } - buf = kvmalloc(len, GFP_KERNEL | GFP_NOFS); + buf = kvmalloc(len, GFP_KERNEL); if (buf == NULL) { err = nfserr_jukebox; goto out; } - len = vfs_getxattr(&init_user_ns, dentry, name, buf, len); + len = vfs_getxattr(&nop_mnt_idmap, dentry, name, buf, len); if (len <= 0) { kvfree(buf); buf = NULL; @@ -2213,10 +2704,7 @@ nfsd_listxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char **bufp, goto out; } - /* - * We're holding i_rwsem - use GFP_NOFS. - */ - buf = kvmalloc(len, GFP_KERNEL | GFP_NOFS); + buf = kvmalloc(len, GFP_KERNEL); if (buf == NULL) { err = nfserr_jukebox; goto out; @@ -2265,16 +2753,18 @@ nfsd_removexattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name) return nfserrno(ret); inode_lock(fhp->fh_dentry->d_inode); - fh_fill_pre_attrs(fhp); - - ret = __vfs_removexattr_locked(&init_user_ns, fhp->fh_dentry, + err = fh_fill_pre_attrs(fhp); + if (err != nfs_ok) + goto out_unlock; + ret = __vfs_removexattr_locked(&nop_mnt_idmap, fhp->fh_dentry, name, NULL); - + err = nfsd_xattr_errno(ret); fh_fill_post_attrs(fhp); +out_unlock: inode_unlock(fhp->fh_dentry->d_inode); fh_drop_write(fhp); - return nfsd_xattr_errno(ret); + return err; } __be32 @@ -2292,15 +2782,17 @@ nfsd_setxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name, if (ret) return nfserrno(ret); inode_lock(fhp->fh_dentry->d_inode); - fh_fill_pre_attrs(fhp); - - ret = __vfs_setxattr_locked(&init_user_ns, fhp->fh_dentry, name, buf, - len, flags, NULL); + err = fh_fill_pre_attrs(fhp); + if (err != nfs_ok) + goto out_unlock; + ret = __vfs_setxattr_locked(&nop_mnt_idmap, fhp->fh_dentry, + name, buf, len, flags, NULL); fh_fill_post_attrs(fhp); + err = nfsd_xattr_errno(ret); +out_unlock: inode_unlock(fhp->fh_dentry->d_inode); fh_drop_write(fhp); - - return nfsd_xattr_errno(ret); + return err; } #endif @@ -2308,8 +2800,8 @@ nfsd_setxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name, * Check for a user's access permissions to this inode. */ __be32 -nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp, - struct dentry *dentry, int acc) +nfsd_permission(struct svc_cred *cred, struct svc_export *exp, + struct dentry *dentry, int acc) { struct inode *inode = d_inode(dentry); int err; @@ -2324,7 +2816,7 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp, (acc & NFSD_MAY_EXEC)? " exec" : "", (acc & NFSD_MAY_SATTR)? " sattr" : "", (acc & NFSD_MAY_TRUNC)? " trunc" : "", - (acc & NFSD_MAY_LOCK)? " lock" : "", + (acc & NFSD_MAY_NLM)? " nlm" : "", (acc & NFSD_MAY_OWNER_OVERRIDE)? " owneroverride" : "", inode->i_mode, IS_IMMUTABLE(inode)? " immut" : "", @@ -2340,7 +2832,7 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp, */ if (!(acc & NFSD_MAY_LOCAL_ACCESS)) if (acc & (NFSD_MAY_WRITE | NFSD_MAY_SATTR | NFSD_MAY_TRUNC)) { - if (exp_rdonly(rqstp, exp) || + if (exp_rdonly(cred, exp) || __mnt_is_readonly(exp->ex_path.mnt)) return nfserr_rofs; if (/* (acc & NFSD_MAY_WRITE) && */ IS_IMMUTABLE(inode)) @@ -2349,16 +2841,6 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp, if ((acc & NFSD_MAY_TRUNC) && IS_APPEND(inode)) return nfserr_perm; - if (acc & NFSD_MAY_LOCK) { - /* If we cannot rely on authentication in NLM requests, - * just allow locks, otherwise require read permission, or - * ownership - */ - if (exp->ex_flags & NFSEXP_NOAUTHNLM) - return 0; - else - acc = NFSD_MAY_READ | NFSD_MAY_OWNER_OVERRIDE; - } /* * The file owner always gets access permission for accesses that * would normally be checked at open time. This is to make @@ -2378,14 +2860,14 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp, return 0; /* This assumes NFSD_MAY_{READ,WRITE,EXEC} == MAY_{READ,WRITE,EXEC} */ - err = inode_permission(&init_user_ns, inode, + err = inode_permission(&nop_mnt_idmap, inode, acc & (MAY_READ | MAY_WRITE | MAY_EXEC)); /* Allow read access to binaries even when mode 111 */ if (err == -EACCES && S_ISREG(inode->i_mode) && (acc == (NFSD_MAY_READ | NFSD_MAY_OWNER_OVERRIDE) || acc == (NFSD_MAY_READ | NFSD_MAY_READ_IF_EXEC))) - err = inode_permission(&init_user_ns, inode, MAY_EXEC); + err = inode_permission(&nop_mnt_idmap, inode, MAY_EXEC); return err? nfserrno(err) : 0; } diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h index dbdfef7ae85b..ded2900d423f 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -20,7 +20,7 @@ #define NFSD_MAY_READ 0x004 /* == MAY_READ */ #define NFSD_MAY_SATTR 0x008 #define NFSD_MAY_TRUNC 0x010 -#define NFSD_MAY_LOCK 0x020 +#define NFSD_MAY_NLM 0x020 /* request is from lockd */ #define NFSD_MAY_MASK 0x03f /* extra hints to permission and open routines: */ @@ -33,6 +33,8 @@ #define NFSD_MAY_64BIT_COOKIE 0x1000 /* 64 bit readdir cookies for >= NFSv3 */ +#define NFSD_MAY_LOCALIO 0x2000 /* for tracing, reflects when localio used */ + #define NFSD_MAY_CREATE (NFSD_MAY_EXEC|NFSD_MAY_WRITE) #define NFSD_MAY_REMOVE (NFSD_MAY_EXEC|NFSD_MAY_WRITE|NFSD_MAY_TRUNC) @@ -60,6 +62,14 @@ static inline void nfsd_attrs_free(struct nfsd_attrs *attrs) posix_acl_release(attrs->na_dpacl); } +static inline bool nfsd_attrs_valid(struct nfsd_attrs *attrs) +{ + struct iattr *iap = attrs->na_iattr; + + return (iap->ia_valid || (attrs->na_seclabel && + attrs->na_seclabel->len)); +} + __be32 nfserrno (int errno); int nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp, struct svc_export **expp); @@ -69,7 +79,7 @@ __be32 nfsd_lookup_dentry(struct svc_rqst *, struct svc_fh *, const char *, unsigned int, struct svc_export **, struct dentry **); __be32 nfsd_setattr(struct svc_rqst *, struct svc_fh *, - struct nfsd_attrs *, int, time64_t); + struct nfsd_attrs *, const struct timespec64 *); int nfsd_mountpoint(struct dentry *, struct svc_export *); #ifdef CONFIG_NFSD_V4 __be32 nfsd4_vfs_fallocate(struct svc_rqst *, struct svc_fh *, @@ -104,27 +114,27 @@ __be32 nfsd_setxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, int nfsd_open_break_lease(struct inode *, int); __be32 nfsd_open(struct svc_rqst *, struct svc_fh *, umode_t, int, struct file **); -__be32 nfsd_open_verified(struct svc_rqst *, struct svc_fh *, - int, struct file **); +int nfsd_open_verified(struct svc_fh *fhp, umode_t type, int may_flags, + struct file **filp); __be32 nfsd_splice_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, loff_t offset, unsigned long *count, u32 *eof); -__be32 nfsd_readv(struct svc_rqst *rqstp, struct svc_fh *fhp, - struct file *file, loff_t offset, - struct kvec *vec, int vlen, - unsigned long *count, +__be32 nfsd_iter_read(struct svc_rqst *rqstp, struct svc_fh *fhp, + struct nfsd_file *nf, loff_t offset, + unsigned long *count, unsigned int base, u32 *eof); -__be32 nfsd_read(struct svc_rqst *, struct svc_fh *, - loff_t, struct kvec *, int, unsigned long *, +bool nfsd_read_splice_ok(struct svc_rqst *rqstp); +__be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp, + loff_t offset, unsigned long *count, u32 *eof); -__be32 nfsd_write(struct svc_rqst *, struct svc_fh *, loff_t, - struct kvec *, int, unsigned long *, - int stable, __be32 *verf); +__be32 nfsd_write(struct svc_rqst *rqstp, struct svc_fh *fhp, + loff_t offset, const struct xdr_buf *payload, + unsigned long *cnt, int stable, __be32 *verf); __be32 nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf, loff_t offset, - struct kvec *vec, int vlen, unsigned long *cnt, - int stable, __be32 *verf); + const struct xdr_buf *payload, + unsigned long *cnt, int stable, __be32 *verf); __be32 nfsd_readlink(struct svc_rqst *, struct svc_fh *, char *, int *); __be32 nfsd_symlink(struct svc_rqst *, struct svc_fh *, @@ -145,35 +155,9 @@ __be32 nfsd_readdir(struct svc_rqst *, struct svc_fh *, __be32 nfsd_statfs(struct svc_rqst *, struct svc_fh *, struct kstatfs *, int access); -__be32 nfsd_permission(struct svc_rqst *, struct svc_export *, - struct dentry *, int); +__be32 nfsd_permission(struct svc_cred *cred, struct svc_export *exp, + struct dentry *dentry, int acc); -static inline int fh_want_write(struct svc_fh *fh) -{ - int ret; - - if (fh->fh_want_write) - return 0; - ret = mnt_want_write(fh->fh_export->ex_path.mnt); - if (!ret) - fh->fh_want_write = true; - return ret; -} - -static inline void fh_drop_write(struct svc_fh *fh) -{ - if (fh->fh_want_write) { - fh->fh_want_write = false; - mnt_drop_write(fh->fh_export->ex_path.mnt); - } -} - -static inline __be32 fh_getattr(const struct svc_fh *fh, struct kstat *stat) -{ - struct path p = {.mnt = fh->fh_export->ex_path.mnt, - .dentry = fh->fh_dentry}; - return nfserrno(vfs_getattr(&p, stat, STATX_BASIC_STATS, - AT_STATX_SYNC_AS_STAT)); -} +void nfsd_filp_close(struct file *fp); #endif /* LINUX_NFSD_VFS_H */ diff --git a/fs/nfsd/xdr3.h b/fs/nfsd/xdr3.h index 03fe4e21306c..522067b7fd75 100644 --- a/fs/nfsd/xdr3.h +++ b/fs/nfsd/xdr3.h @@ -14,7 +14,7 @@ struct nfsd3_sattrargs { struct svc_fh fh; struct iattr attrs; int check_guard; - time64_t guardtime; + struct timespec64 guardtime; }; struct nfsd3_diropargs { diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index 4fd2cf6d1d2d..ae75846b3cd7 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -50,6 +50,134 @@ #define HAS_CSTATE_FLAG(c, f) ((c)->sid_flags & (f)) #define CLEAR_CSTATE_FLAG(c, f) ((c)->sid_flags &= ~(f)) +/** + * nfsd4_encode_bool - Encode an XDR bool type result + * @xdr: target XDR stream + * @val: boolean value to encode + * + * Return values: + * %nfs_ok: @val encoded; @xdr advanced to next position + * %nfserr_resource: stream buffer space exhausted + */ +static __always_inline __be32 +nfsd4_encode_bool(struct xdr_stream *xdr, bool val) +{ + __be32 *p = xdr_reserve_space(xdr, XDR_UNIT); + + if (unlikely(p == NULL)) + return nfserr_resource; + *p = val ? xdr_one : xdr_zero; + return nfs_ok; +} + +/** + * nfsd4_encode_uint32_t - Encode an XDR uint32_t type result + * @xdr: target XDR stream + * @val: integer value to encode + * + * Return values: + * %nfs_ok: @val encoded; @xdr advanced to next position + * %nfserr_resource: stream buffer space exhausted + */ +static __always_inline __be32 +nfsd4_encode_uint32_t(struct xdr_stream *xdr, u32 val) +{ + __be32 *p = xdr_reserve_space(xdr, XDR_UNIT); + + if (unlikely(p == NULL)) + return nfserr_resource; + *p = cpu_to_be32(val); + return nfs_ok; +} + +#define nfsd4_encode_aceflag4(x, v) nfsd4_encode_uint32_t(x, v) +#define nfsd4_encode_acemask4(x, v) nfsd4_encode_uint32_t(x, v) +#define nfsd4_encode_acetype4(x, v) nfsd4_encode_uint32_t(x, v) +#define nfsd4_encode_count4(x, v) nfsd4_encode_uint32_t(x, v) +#define nfsd4_encode_mode4(x, v) nfsd4_encode_uint32_t(x, v) +#define nfsd4_encode_nfs_lease4(x, v) nfsd4_encode_uint32_t(x, v) +#define nfsd4_encode_qop4(x, v) nfsd4_encode_uint32_t(x, v) +#define nfsd4_encode_sequenceid4(x, v) nfsd4_encode_uint32_t(x, v) +#define nfsd4_encode_slotid4(x, v) nfsd4_encode_uint32_t(x, v) + +/** + * nfsd4_encode_uint64_t - Encode an XDR uint64_t type result + * @xdr: target XDR stream + * @val: integer value to encode + * + * Return values: + * %nfs_ok: @val encoded; @xdr advanced to next position + * %nfserr_resource: stream buffer space exhausted + */ +static __always_inline __be32 +nfsd4_encode_uint64_t(struct xdr_stream *xdr, u64 val) +{ + __be32 *p = xdr_reserve_space(xdr, XDR_UNIT * 2); + + if (unlikely(p == NULL)) + return nfserr_resource; + put_unaligned_be64(val, p); + return nfs_ok; +} + +#define nfsd4_encode_changeid4(x, v) nfsd4_encode_uint64_t(x, v) +#define nfsd4_encode_nfs_cookie4(x, v) nfsd4_encode_uint64_t(x, v) +#define nfsd4_encode_length4(x, v) nfsd4_encode_uint64_t(x, v) +#define nfsd4_encode_offset4(x, v) nfsd4_encode_uint64_t(x, v) + +/** + * nfsd4_encode_opaque_fixed - Encode a fixed-length XDR opaque type result + * @xdr: target XDR stream + * @data: pointer to data + * @size: length of data in bytes + * + * Return values: + * %nfs_ok: @data encoded; @xdr advanced to next position + * %nfserr_resource: stream buffer space exhausted + */ +static __always_inline __be32 +nfsd4_encode_opaque_fixed(struct xdr_stream *xdr, const void *data, + size_t size) +{ + __be32 *p = xdr_reserve_space(xdr, xdr_align_size(size)); + size_t pad = xdr_pad_size(size); + + if (unlikely(p == NULL)) + return nfserr_resource; + memcpy(p, data, size); + if (pad) + memset((char *)p + size, 0, pad); + return nfs_ok; +} + +/** + * nfsd4_encode_opaque - Encode a variable-length XDR opaque type result + * @xdr: target XDR stream + * @data: pointer to data + * @size: length of data in bytes + * + * Return values: + * %nfs_ok: @data encoded; @xdr advanced to next position + * %nfserr_resource: stream buffer space exhausted + */ +static __always_inline __be32 +nfsd4_encode_opaque(struct xdr_stream *xdr, const void *data, size_t size) +{ + size_t pad = xdr_pad_size(size); + __be32 *p; + + p = xdr_reserve_space(xdr, XDR_UNIT + xdr_align_size(size)); + if (unlikely(p == NULL)) + return nfserr_resource; + *p++ = cpu_to_be32(size); + memcpy(p, data, size); + if (pad) + memset((char *)p + size, 0, pad); + return nfs_ok; +} + +#define nfsd4_encode_component4(x, d, s) nfsd4_encode_opaque(x, d, s) + struct nfsd4_compound_state { struct svc_fh current_fh; struct svc_fh save_fh; @@ -170,12 +298,8 @@ struct nfsd4_lock { } v; /* response */ - union { - struct { - stateid_t stateid; - } ok; - struct nfsd4_lock_denied denied; - } u; + stateid_t lk_resp_stateid; + struct nfsd4_lock_denied lk_denied; }; #define lk_new_open_seqid v.new.open_seqid #define lk_new_open_stateid v.new.open_stateid @@ -185,20 +309,15 @@ struct nfsd4_lock { #define lk_old_lock_stateid v.old.lock_stateid #define lk_old_lock_seqid v.old.lock_seqid -#define lk_resp_stateid u.ok.stateid -#define lk_denied u.denied - - struct nfsd4_lockt { u32 lt_type; clientid_t lt_clientid; struct xdr_netobj lt_owner; u64 lt_offset; u64 lt_length; - struct nfsd4_lock_denied lt_denied; + struct nfsd4_lock_denied lt_denied; }; - struct nfsd4_locku { u32 lu_type; u32 lu_seqid; @@ -267,9 +386,9 @@ struct nfsd4_open { u32 op_deleg_want; /* request */ stateid_t op_stateid; /* response */ __be32 op_xdr_error; /* see nfsd4_open_omfg() */ - u32 op_recall; /* recall */ struct nfsd4_change_info op_cinfo; /* response */ u32 op_rflags; /* response */ + bool op_recall; /* response */ bool op_truncate; /* used during processing */ bool op_created; /* used during processing */ struct nfs4_openowner *op_openowner; /* used during processing */ @@ -399,6 +518,24 @@ struct nfsd4_free_stateid { stateid_t fr_stateid; /* request */ }; +struct nfsd4_get_dir_delegation { + /* request */ + u32 gdda_signal_deleg_avail; + u32 gdda_notification_types[1]; + struct timespec64 gdda_child_attr_delay; + struct timespec64 gdda_dir_attr_delay; + u32 gdda_child_attributes[3]; + u32 gdda_dir_attributes[3]; + /* response */ + u32 gddrnf_status; + nfs4_verifier gddr_cookieverf; + stateid_t gddr_stateid; + u32 gddr_notification[1]; + u32 gddr_child_attributes[3]; + u32 gddr_dir_attributes[3]; + bool gddrnf_will_signal_deleg_avail; +}; + /* also used for NVERIFY */ struct nfsd4_verify { u32 ve_bmval[3]; /* request */ @@ -430,17 +567,17 @@ struct nfsd4_exchange_id { struct xdr_netobj nii_domain; struct xdr_netobj nii_name; struct timespec64 nii_time; + char *server_impl_name; }; struct nfsd4_sequence { struct nfs4_sessionid sessionid; /* request/response */ u32 seqid; /* request/response */ u32 slotid; /* request/response */ - u32 maxslots; /* request/response */ + u32 maxslots; /* request */ u32 cachethis; /* request */ -#if 0 + u32 maxslots_response; /* response */ u32 target_maxslots; /* response */ -#endif /* not yet */ u32 status_flags; /* response */ }; @@ -459,9 +596,43 @@ struct nfsd4_reclaim_complete { struct nfsd4_deviceid { u64 fsid_idx; u32 generation; - u32 pad; }; +static inline __be32 * +svcxdr_encode_deviceid4(__be32 *p, const struct nfsd4_deviceid *devid) +{ + __be64 *q = (__be64 *)p; + + *q = (__force __be64)devid->fsid_idx; + p += 2; + *p++ = (__force __be32)devid->generation; + *p++ = xdr_zero; + return p; +} + +static inline __be32 * +svcxdr_decode_deviceid4(__be32 *p, struct nfsd4_deviceid *devid) +{ + __be64 *q = (__be64 *)p; + + devid->fsid_idx = (__force u64)(*q); + p += 2; + devid->generation = (__force u32)(*p++); + p++; /* NFSD does not use the remaining octets */ + return p; +} + +static inline __be32 +nfsd4_decode_deviceid4(struct xdr_stream *xdr, struct nfsd4_deviceid *devid) +{ + __be32 *p = xdr_inline_decode(xdr, NFS4_DEVICEID4_SIZE); + + if (unlikely(!p)) + return nfserr_bad_xdr; + svcxdr_decode_deviceid4(p, devid); + return nfs_ok; +} + struct nfsd4_layout_seg { u32 iomode; u64 offset; @@ -494,9 +665,8 @@ struct nfsd4_layoutcommit { u64 lc_last_wr; /* request */ struct timespec64 lc_mtime; /* request */ u32 lc_layout_type; /* request */ - u32 lc_up_len; /* layout length */ - void *lc_up_layout; /* decoded by callback */ - u32 lc_size_chg; /* boolean for response */ + struct xdr_buf lc_up_layout; /* decoded by callback */ + bool lc_size_chg; /* response */ u64 lc_newsize; /* response */ }; @@ -508,7 +678,7 @@ struct nfsd4_layoutreturn { u32 lrf_body_len; /* request */ void *lrf_body; /* request */ stateid_t lr_sid; /* request/response */ - u32 lrs_present; /* response */ + bool lrs_present; /* response */ }; struct nfsd4_fallocate { @@ -538,7 +708,12 @@ struct nfsd4_cb_offload { struct nfsd4_callback co_cb; struct nfsd42_write_res co_res; __be32 co_nfserr; + unsigned int co_retries; struct knfsd_fh co_fh; + + struct nfs4_sessionid co_referring_sessionid; + u32 co_referring_slotid; + u32 co_referring_seqno; }; struct nfsd4_copy { @@ -555,11 +730,17 @@ struct nfsd4_copy { #define NFSD4_COPY_F_INTRA (1) #define NFSD4_COPY_F_SYNCHRONOUS (2) #define NFSD4_COPY_F_COMMITTED (3) +#define NFSD4_COPY_F_COMPLETED (4) +#define NFSD4_COPY_F_OFFLOAD_DONE (5) /* response */ + __be32 nfserr; struct nfsd42_write_res cp_res; struct knfsd_fh fh; + /* offload callback */ + struct nfsd4_cb_offload cp_cb_offload; + struct nfs4_client *cp_clp; struct nfsd_file *nf_src; @@ -570,10 +751,12 @@ struct nfsd4_copy { struct list_head copies; struct task_struct *copy_task; refcount_t refcount; + unsigned int cp_ttl; - struct vfsmount *ss_mnt; + struct nfsd4_ssc_umount_item *ss_nsui; struct nfs_fh c_fh; nfs4_stateid stateid; + struct nfsd_net *cp_nn; }; static inline void nfsd4_copy_set_sync(struct nfsd4_copy *copy, bool sync) @@ -616,7 +799,8 @@ struct nfsd4_offload_status { /* response */ u64 count; - u32 status; + __be32 status; + bool completed; }; struct nfsd4_copy_notify { @@ -626,8 +810,7 @@ struct nfsd4_copy_notify { /* response */ stateid_t cpn_cnr_stateid; - u64 cpn_sec; - u32 cpn_nsec; + struct timespec64 cpn_lease_time; struct nl4_server *cpn_src; }; @@ -679,6 +862,7 @@ struct nfsd4_op { struct nfsd4_reclaim_complete reclaim_complete; struct nfsd4_test_stateid test_stateid; struct nfsd4_free_stateid free_stateid; + struct nfsd4_get_dir_delegation get_dir_delegation; struct nfsd4_getdeviceinfo getdeviceinfo; struct nfsd4_layoutget layoutget; struct nfsd4_layoutcommit layoutcommit; @@ -722,6 +906,7 @@ struct nfsd4_compoundargs { u32 minorversion; u32 client_opcnt; u32 opcnt; + bool splice_ok; struct nfsd4_op *ops; struct nfsd4_op iops[8]; }; @@ -739,27 +924,6 @@ struct nfsd4_compoundres { struct nfsd4_compound_state cstate; }; -static inline bool nfsd4_is_solo_sequence(struct nfsd4_compoundres *resp) -{ - struct nfsd4_compoundargs *args = resp->rqstp->rq_argp; - return resp->opcnt == 1 && args->ops[0].opnum == OP_SEQUENCE; -} - -/* - * The session reply cache only needs to cache replies that the client - * actually asked us to. But it's almost free for us to cache compounds - * consisting of only a SEQUENCE op, so we may as well cache those too. - * Also, the protocol doesn't give us a convenient response in the case - * of a replay of a solo SEQUENCE op that wasn't cached - * (RETRY_UNCACHED_REP can only be returned in the second op of a - * compound). - */ -static inline bool nfsd4_cache_this(struct nfsd4_compoundres *resp) -{ - return (resp->cstate.slot->sl_flags & NFSD4_SLOT_CACHETHIS) - || nfsd4_is_solo_sequence(resp); -} - static inline bool nfsd4_last_compound_op(struct svc_rqst *rqstp) { struct nfsd4_compoundres *resp = rqstp->rq_resp; @@ -774,17 +938,6 @@ void warn_on_nonidempotent_op(struct nfsd4_op *op); #define NFS4_SVC_XDRSIZE sizeof(struct nfsd4_compoundargs) -static inline void -set_change_info(struct nfsd4_change_info *cinfo, struct svc_fh *fhp) -{ - BUG_ON(!fhp->fh_pre_saved); - cinfo->atomic = (u32)(fhp->fh_post_saved && !fhp->fh_no_atomic_attr); - - cinfo->before_change = fhp->fh_pre_change; - cinfo->after_change = fhp->fh_post_change; -} - - bool nfsd4_mach_creds_match(struct nfs4_client *cl, struct svc_rqst *rqstp); bool nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); bool nfs4svc_encode_compoundres(struct svc_rqst *rqstp, struct xdr_stream *xdr); @@ -799,6 +952,7 @@ extern __be32 nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *, union nfsd4_op_u *u); extern __be32 nfsd4_setclientid_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *, union nfsd4_op_u *u); +void nfsd4_exchange_id_release(union nfsd4_op_u *u); extern __be32 nfsd4_exchange_id(struct svc_rqst *rqstp, struct nfsd4_compound_state *, union nfsd4_op_u *u); extern __be32 nfsd4_backchannel_ctl(struct svc_rqst *, @@ -831,8 +985,10 @@ extern __be32 nfsd4_open_downgrade(struct svc_rqst *rqstp, struct nfsd4_compound_state *, union nfsd4_op_u *u); extern __be32 nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *, union nfsd4_op_u *u); +extern void nfsd4_lock_release(union nfsd4_op_u *u); extern __be32 nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *, union nfsd4_op_u *u); +extern void nfsd4_lockt_release(union nfsd4_op_u *u); extern __be32 nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *, union nfsd4_op_u *u); extern __be32 diff --git a/fs/nfsd/xdr4cb.h b/fs/nfsd/xdr4cb.h index 0d39af1b00a0..f4e29c0c701c 100644 --- a/fs/nfsd/xdr4cb.h +++ b/fs/nfsd/xdr4cb.h @@ -6,8 +6,11 @@ #define cb_compound_enc_hdr_sz 4 #define cb_compound_dec_hdr_sz (3 + (NFS4_MAXTAGLEN >> 2)) #define sessionid_sz (NFS4_MAX_SESSIONID_LEN >> 2) +#define enc_referring_call4_sz (1 + 1) +#define enc_referring_call_list4_sz (sessionid_sz + 1 + \ + enc_referring_call4_sz) #define cb_sequence_enc_sz (sessionid_sz + 4 + \ - 1 /* no referring calls list yet */) + enc_referring_call_list4_sz) #define cb_sequence_dec_sz (op_dec_sz + sessionid_sz + 4) #define op_enc_sz 1 @@ -54,3 +57,25 @@ #define NFS4_dec_cb_recall_any_sz (cb_compound_dec_hdr_sz + \ cb_sequence_dec_sz + \ op_dec_sz) + +/* + * 1: CB_GETATTR opcode (32-bit) + * N: file_handle + * 1: number of entry in attribute array (32-bit) + * 3: entry 0-2 in attribute array (32-bit * 3) + */ +#define NFS4_enc_cb_getattr_sz (cb_compound_enc_hdr_sz + \ + cb_sequence_enc_sz + \ + 1 + enc_nfs4_fh_sz + 1 + 3) +/* + * 4: fattr_bitmap_maxsz + * 1: attribute array len + * 2: change attr (64-bit) + * 2: size (64-bit) + * 2: atime.seconds (64-bit) + * 1: atime.nanoseconds (32-bit) + * 2: mtime.seconds (64-bit) + * 1: mtime.nanoseconds (32-bit) + */ +#define NFS4_dec_cb_getattr_sz (cb_compound_dec_hdr_sz + \ + cb_sequence_dec_sz + 4 + 1 + 2 + 2 + 2 + 1 + 2 + 1 + op_dec_sz) |