diff options
Diffstat (limited to '')
95 files changed, 6590 insertions, 4384 deletions
diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile index 22d11fdc6deb..5f6db37f461e 100644 --- a/fs/nfs/Makefile +++ b/fs/nfs/Makefile @@ -12,7 +12,7 @@ nfs-y := client.o dir.o file.o getroot.o inode.o super.o \ export.o sysfs.o fs_context.o nfs-$(CONFIG_ROOT_NFS) += nfsroot.o nfs-$(CONFIG_SYSCTL) += sysctl.o -nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o +nfs-$(CONFIG_NFS_FSCACHE) += fscache.o obj-$(CONFIG_NFS_V2) += nfsv2.o nfsv2-y := nfs2super.o proc.o nfs2xdr.o diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index fe860c538747..943aeea1eb16 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -115,30 +115,13 @@ bl_submit_bio(struct bio *bio) return NULL; } -static struct bio *bl_alloc_init_bio(unsigned int npg, - struct block_device *bdev, sector_t disk_sector, - bio_end_io_t end_io, struct parallel_io *par) -{ - struct bio *bio; - - npg = bio_max_segs(npg); - bio = bio_alloc(GFP_NOIO, npg); - if (bio) { - bio->bi_iter.bi_sector = disk_sector; - bio_set_dev(bio, bdev); - bio->bi_end_io = end_io; - bio->bi_private = par; - } - return bio; -} - static bool offset_in_map(u64 offset, struct pnfs_block_dev_map *map) { return offset >= map->start && offset < map->start + map->len; } static struct bio * -do_add_page_to_bio(struct bio *bio, int npg, int rw, sector_t isect, +do_add_page_to_bio(struct bio *bio, int npg, enum req_op op, sector_t isect, struct page *page, struct pnfs_block_dev_map *map, struct pnfs_block_extent *be, bio_end_io_t end_io, struct parallel_io *par, unsigned int offset, int *len) @@ -148,7 +131,7 @@ do_add_page_to_bio(struct bio *bio, int npg, int rw, sector_t isect, u64 disk_addr, end; dprintk("%s: npg %d rw %d isect %llu offset %u len %d\n", __func__, - npg, rw, (unsigned long long)isect, offset, *len); + npg, (__force u32)op, (unsigned long long)isect, offset, *len); /* translate to device offset */ isect += be->be_v_offset; @@ -171,11 +154,10 @@ do_add_page_to_bio(struct bio *bio, int npg, int rw, sector_t isect, retry: if (!bio) { - bio = bl_alloc_init_bio(npg, map->bdev, - disk_addr >> SECTOR_SHIFT, end_io, par); - if (!bio) - return ERR_PTR(-ENOMEM); - bio_set_op_attrs(bio, rw, 0); + bio = bio_alloc(map->bdev, bio_max_segs(npg), op, GFP_NOIO); + bio->bi_iter.bi_sector = disk_addr >> SECTOR_SHIFT; + bio->bi_end_io = end_io; + bio->bi_private = par; } if (bio_add_page(bio, page, *len, offset) < *len) { bio = bl_submit_bio(bio); @@ -309,7 +291,7 @@ bl_read_pagelist(struct nfs_pgio_header *header) } else { bio = do_add_page_to_bio(bio, header->page_array.npages - i, - READ, + REQ_OP_READ, isect, pages[i], &map, &be, bl_end_io_read, par, pg_offset, &pg_len); @@ -438,9 +420,8 @@ bl_write_pagelist(struct nfs_pgio_header *header, int sync) pg_len = PAGE_SIZE; bio = do_add_page_to_bio(bio, header->page_array.npages - i, - WRITE, isect, pages[i], &map, &be, - bl_end_io_write, par, - 0, &pg_len); + REQ_OP_WRITE, isect, pages[i], &map, + &be, bl_end_io_write, par, 0, &pg_len); if (IS_ERR(bio)) { header->pnfs_error = PTR_ERR(bio); bio = NULL; diff --git a/fs/nfs/blocklayout/dev.c b/fs/nfs/blocklayout/dev.c index 5e56da748b2a..fea5f8821da5 100644 --- a/fs/nfs/blocklayout/dev.c +++ b/fs/nfs/blocklayout/dev.c @@ -301,18 +301,14 @@ bl_validate_designator(struct pnfs_block_volume *v) } } -/* - * Try to open the udev path for the WWN. At least on Debian the udev - * by-id path will always point to the dm-multipath device if one exists. - */ static struct block_device * -bl_open_udev_path(struct pnfs_block_volume *v) +bl_open_path(struct pnfs_block_volume *v, const char *prefix) { struct block_device *bdev; const char *devname; - devname = kasprintf(GFP_KERNEL, "/dev/disk/by-id/wwn-0x%*phN", - v->scsi.designator_len, v->scsi.designator); + devname = kasprintf(GFP_KERNEL, "/dev/disk/by-id/%s%*phN", + prefix, v->scsi.designator_len, v->scsi.designator); if (!devname) return ERR_PTR(-ENOMEM); @@ -326,28 +322,6 @@ bl_open_udev_path(struct pnfs_block_volume *v) return bdev; } -/* - * Try to open the RH/Fedora specific dm-mpath udev path for this WWN, as the - * wwn- links will only point to the first discovered SCSI device there. - */ -static struct block_device * -bl_open_dm_mpath_udev_path(struct pnfs_block_volume *v) -{ - struct block_device *bdev; - const char *devname; - - devname = kasprintf(GFP_KERNEL, - "/dev/disk/by-id/dm-uuid-mpath-%d%*phN", - v->scsi.designator_type, - v->scsi.designator_len, v->scsi.designator); - if (!devname) - return ERR_PTR(-ENOMEM); - - bdev = blkdev_get_by_path(devname, FMODE_READ | FMODE_WRITE, NULL); - kfree(devname); - return bdev; -} - static int bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d, struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask) @@ -360,9 +334,15 @@ bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d, if (!bl_validate_designator(v)) return -EINVAL; - bdev = bl_open_dm_mpath_udev_path(v); + /* + * Try to open the RH/Fedora specific dm-mpath udev path first, as the + * wwn- links will only point to the first discovered SCSI device there. + * On other distributions like Debian, the default SCSI by-id path will + * point to the dm-multipath device if one exists. + */ + bdev = bl_open_path(v, "dm-uuid-mpath-0x"); if (IS_ERR(bdev)) - bdev = bl_open_udev_path(v); + bdev = bl_open_path(v, "wwn-0x"); if (IS_ERR(bdev)) return PTR_ERR(bdev); d->bdev = bdev; diff --git a/fs/nfs/blocklayout/rpc_pipefs.c b/fs/nfs/blocklayout/rpc_pipefs.c index ef9db135c649..6c977288cc28 100644 --- a/fs/nfs/blocklayout/rpc_pipefs.c +++ b/fs/nfs/blocklayout/rpc_pipefs.c @@ -27,7 +27,6 @@ */ #include <linux/module.h> -#include <linux/genhd.h> #include <linux/blkdev.h> #include "blocklayout.h" diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index 86d856de1389..456af7d230cf 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -17,7 +17,6 @@ #include <linux/errno.h> #include <linux/mutex.h> #include <linux/freezer.h> -#include <linux/kthread.h> #include <linux/sunrpc/svcauth_gss.h> #include <linux/sunrpc/bc_xprt.h> @@ -45,18 +44,18 @@ static int nfs4_callback_up_net(struct svc_serv *serv, struct net *net) int ret; struct nfs_net *nn = net_generic(net, nfs_net_id); - ret = svc_create_xprt(serv, "tcp", net, PF_INET, - nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS, - cred); + ret = svc_xprt_create(serv, "tcp", net, PF_INET, + nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS, + cred); if (ret <= 0) goto out_err; nn->nfs_callback_tcpport = ret; dprintk("NFS: Callback listener port = %u (af %u, net %x)\n", nn->nfs_callback_tcpport, PF_INET, net->ns.inum); - ret = svc_create_xprt(serv, "tcp", net, PF_INET6, - nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS, - cred); + ret = svc_xprt_create(serv, "tcp", net, PF_INET6, + nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS, + cred); if (ret > 0) { nn->nfs_callback_tcpport6 = ret; dprintk("NFS: Callback listener port = %u (af %u, net %x)\n", @@ -92,8 +91,8 @@ nfs4_callback_svc(void *vrqstp) continue; svc_process(rqstp); } + svc_exit_thread(rqstp); - module_put_and_exit(0); return 0; } @@ -136,8 +135,8 @@ nfs41_callback_svc(void *vrqstp) finish_wait(&serv->sv_cb_waitq, &wq); } } + svc_exit_thread(rqstp); - module_put_and_exit(0); return 0; } @@ -169,12 +168,12 @@ static int nfs_callback_start_svc(int minorversion, struct rpc_xprt *xprt, if (nrservs < NFS4_MIN_NR_CALLBACK_THREADS) nrservs = NFS4_MIN_NR_CALLBACK_THREADS; - if (serv->sv_nrthreads-1 == nrservs) + if (serv->sv_nrthreads == nrservs) return 0; - ret = serv->sv_ops->svo_setup(serv, NULL, nrservs); + ret = svc_set_num_threads(serv, NULL, nrservs); if (ret) { - serv->sv_ops->svo_setup(serv, NULL, 0); + svc_set_num_threads(serv, NULL, 0); return ret; } dprintk("nfs_callback_up: service started\n"); @@ -189,7 +188,7 @@ static void nfs_callback_down_net(u32 minorversion, struct svc_serv *serv, struc return; dprintk("NFS: destroy per-net callback data; net=%x\n", net->ns.inum); - svc_shutdown_net(serv, net); + svc_xprt_destroy_all(serv, net); } static int nfs_callback_up_net(int minorversion, struct svc_serv *serv, @@ -232,59 +231,17 @@ err_bind: return ret; } -static const struct svc_serv_ops nfs40_cb_sv_ops = { - .svo_function = nfs4_callback_svc, - .svo_enqueue_xprt = svc_xprt_do_enqueue, - .svo_setup = svc_set_num_threads_sync, - .svo_module = THIS_MODULE, -}; -#if defined(CONFIG_NFS_V4_1) -static const struct svc_serv_ops nfs41_cb_sv_ops = { - .svo_function = nfs41_callback_svc, - .svo_enqueue_xprt = svc_xprt_do_enqueue, - .svo_setup = svc_set_num_threads_sync, - .svo_module = THIS_MODULE, -}; - -static const struct svc_serv_ops *nfs4_cb_sv_ops[] = { - [0] = &nfs40_cb_sv_ops, - [1] = &nfs41_cb_sv_ops, -}; -#else -static const struct svc_serv_ops *nfs4_cb_sv_ops[] = { - [0] = &nfs40_cb_sv_ops, - [1] = NULL, -}; -#endif - static struct svc_serv *nfs_callback_create_svc(int minorversion) { struct nfs_callback_data *cb_info = &nfs_callback_info[minorversion]; - const struct svc_serv_ops *sv_ops; + int (*threadfn)(void *data); struct svc_serv *serv; /* * Check whether we're already up and running. */ - if (cb_info->serv) { - /* - * Note: increase service usage, because later in case of error - * svc_destroy() will be called. - */ - svc_get(cb_info->serv); - return cb_info->serv; - } - - switch (minorversion) { - case 0: - sv_ops = nfs4_cb_sv_ops[0]; - break; - default: - sv_ops = nfs4_cb_sv_ops[1]; - } - - if (sv_ops == NULL) - return ERR_PTR(-ENOTSUPP); + if (cb_info->serv) + return svc_get(cb_info->serv); /* * Sanity check: if there's no task, @@ -294,7 +251,16 @@ static struct svc_serv *nfs_callback_create_svc(int minorversion) printk(KERN_WARNING "nfs_callback_create_svc: no kthread, %d users??\n", cb_info->users); - serv = svc_create_pooled(&nfs4_callback_program, NFS4_CALLBACK_BUFSIZE, sv_ops); + threadfn = nfs4_callback_svc; +#if defined(CONFIG_NFS_V4_1) + if (minorversion) + threadfn = nfs41_callback_svc; +#else + if (minorversion) + return ERR_PTR(-ENOTSUPP); +#endif + serv = svc_create(&nfs4_callback_program, NFS4_CALLBACK_BUFSIZE, + threadfn); if (!serv) { printk(KERN_ERR "nfs_callback_create_svc: create service failed\n"); return ERR_PTR(-ENOMEM); @@ -335,16 +301,10 @@ int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt) goto err_start; cb_info->users++; - /* - * svc_create creates the svc_serv with sv_nrthreads == 1, and then - * svc_prepare_thread increments that. So we need to call svc_destroy - * on both success and failure so that the refcount is 1 when the - * thread exits. - */ err_net: if (!cb_info->users) cb_info->serv = NULL; - svc_destroy(serv); + svc_put(serv); err_create: mutex_unlock(&nfs_callback_mutex); return ret; @@ -369,8 +329,8 @@ void nfs_callback_down(int minorversion, struct net *net) cb_info->users--; if (cb_info->users == 0) { svc_get(serv); - serv->sv_ops->svo_setup(serv, NULL, 0); - svc_destroy(serv); + svc_set_num_threads(serv, NULL, 0); + svc_put(serv); dprintk("nfs_callback_down: service destroyed\n"); cb_info->serv = NULL; } diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h index 6a2033131c06..ccd4f245cae2 100644 --- a/fs/nfs/callback.h +++ b/fs/nfs/callback.h @@ -170,7 +170,7 @@ struct cb_devicenotifyitem { }; struct cb_devicenotifyargs { - int ndevs; + uint32_t ndevs; struct cb_devicenotifyitem *devs; }; diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c index 09c5b1cb3e07..c1eda73254e1 100644 --- a/fs/nfs/callback_proc.c +++ b/fs/nfs/callback_proc.c @@ -288,6 +288,7 @@ static u32 initiate_file_draining(struct nfs_client *clp, rv = NFS4_OK; break; case -ENOENT: + set_bit(NFS_LAYOUT_DRAIN, &lo->plh_flags); /* Embrace your forgetfulness! */ rv = NFS4ERR_NOMATCHING_LAYOUT; @@ -358,12 +359,11 @@ __be32 nfs4_callback_devicenotify(void *argp, void *resp, struct cb_process_state *cps) { struct cb_devicenotifyargs *args = argp; - int i; + const struct pnfs_layoutdriver_type *ld = NULL; + uint32_t i; __be32 res = 0; - struct nfs_client *clp = cps->clp; - struct nfs_server *server = NULL; - if (!clp) { + if (!cps->clp) { res = cpu_to_be32(NFS4ERR_OP_NOT_IN_SESSION); goto out; } @@ -371,23 +371,15 @@ __be32 nfs4_callback_devicenotify(void *argp, void *resp, for (i = 0; i < args->ndevs; i++) { struct cb_devicenotifyitem *dev = &args->devs[i]; - if (!server || - server->pnfs_curr_ld->id != dev->cbd_layout_type) { - rcu_read_lock(); - list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) - if (server->pnfs_curr_ld && - server->pnfs_curr_ld->id == dev->cbd_layout_type) { - rcu_read_unlock(); - goto found; - } - rcu_read_unlock(); - continue; + if (!ld || ld->id != dev->cbd_layout_type) { + pnfs_put_layoutdriver(ld); + ld = pnfs_find_layoutdriver(dev->cbd_layout_type); + if (!ld) + continue; } - - found: - nfs4_delete_deviceid(server->pnfs_curr_ld, clp, &dev->cbd_dev_id); + nfs4_delete_deviceid(ld, cps->clp, &dev->cbd_dev_id); } - + pnfs_put_layoutdriver(ld); out: kfree(args->devs); return res; @@ -710,7 +702,7 @@ __be32 nfs4_callback_offload(void *data, void *dummy, struct nfs4_copy_state *copy, *tmp_copy; bool found = false; - copy = kzalloc(sizeof(struct nfs4_copy_state), GFP_NOFS); + copy = kzalloc(sizeof(struct nfs4_copy_state), GFP_KERNEL); if (!copy) return htonl(NFS4ERR_SERVERFAULT); diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index a67c41ec545f..d0cccddb7d08 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -258,11 +258,9 @@ __be32 decode_devicenotify_args(struct svc_rqst *rqstp, void *argp) { struct cb_devicenotifyargs *args = argp; + uint32_t tmp, n, i; __be32 *p; __be32 status = 0; - u32 tmp; - int n, i; - args->ndevs = 0; /* Num of device notifications */ p = xdr_inline_decode(xdr, sizeof(uint32_t)); @@ -271,12 +269,8 @@ __be32 decode_devicenotify_args(struct svc_rqst *rqstp, goto out; } n = ntohl(*p++); - if (n <= 0) - goto out; - if (n > ULONG_MAX / sizeof(*args->devs)) { - status = htonl(NFS4ERR_BADXDR); + if (n == 0) goto out; - } args->devs = kmalloc_array(n, sizeof(*args->devs), GFP_KERNEL); if (!args->devs) { @@ -330,19 +324,21 @@ __be32 decode_devicenotify_args(struct svc_rqst *rqstp, dev->cbd_immediate = 0; } - args->ndevs++; - dprintk("%s: type %d layout 0x%x immediate %d\n", __func__, dev->cbd_notify_type, dev->cbd_layout_type, dev->cbd_immediate); } + args->ndevs = n; + dprintk("%s: ndevs %d\n", __func__, args->ndevs); + return 0; +err: + kfree(args->devs); out: + args->devs = NULL; + args->ndevs = 0; dprintk("%s: status %d ndevs %d\n", __func__, ntohl(status), args->ndevs); return status; -err: - kfree(args->devs); - goto out; } static __be32 decode_sessionid(struct xdr_stream *xdr, @@ -1069,6 +1065,7 @@ static const struct svc_procedure nfs4_callback_procedures1[] = { .pc_func = nfs4_callback_compound, .pc_encode = nfs4_encode_void, .pc_argsize = 256, + .pc_argzero = 256, .pc_ressize = 256, .pc_xdrressize = NFS4_CALLBACK_BUFSIZE, .pc_name = "COMPOUND", diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 1e4dc1ab9312..f50e025ae406 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -177,14 +177,13 @@ struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init) INIT_LIST_HEAD(&clp->cl_superblocks); clp->cl_rpcclient = ERR_PTR(-EINVAL); + clp->cl_flags = cl_init->init_flags; clp->cl_proto = cl_init->proto; clp->cl_nconnect = cl_init->nconnect; clp->cl_max_connect = cl_init->max_connect ? cl_init->max_connect : 1; clp->cl_net = get_net(cl_init->net); clp->cl_principal = "*"; - nfs_fscache_get_client_cookie(clp); - return clp; error_cleanup: @@ -238,8 +237,6 @@ static void pnfs_init_server(struct nfs_server *server) */ void nfs_free_client(struct nfs_client *clp) { - nfs_fscache_release_client_cookie(clp); - /* -EIO all pending I/O */ if (!IS_ERR(clp->cl_rpcclient)) rpc_shutdown_client(clp->cl_rpcclient); @@ -283,7 +280,7 @@ EXPORT_SYMBOL_GPL(nfs_put_client); static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *data) { struct nfs_client *clp; - const struct sockaddr *sap = data->addr; + const struct sockaddr *sap = (struct sockaddr *)data->addr; struct nfs_net *nn = net_generic(data->net, nfs_net_id); int error; @@ -427,7 +424,6 @@ struct nfs_client *nfs_get_client(const struct nfs_client_initdata *cl_init) list_add_tail(&new->cl_share_link, &nn->nfs_client_list); spin_unlock(&nn->nfs_client_lock); - new->cl_flags = cl_init->init_flags; return rpc_ops->init_client(new, cl_init); } @@ -670,7 +666,7 @@ static int nfs_init_server(struct nfs_server *server, struct rpc_timeout timeparms; struct nfs_client_initdata cl_init = { .hostname = ctx->nfs_server.hostname, - .addr = (const struct sockaddr *)&ctx->nfs_server.address, + .addr = &ctx->nfs_server._address, .addrlen = ctx->nfs_server.addrlen, .nfs_mod = ctx->nfs_mod, .proto = ctx->nfs_server.protocol, @@ -712,9 +708,9 @@ static int nfs_init_server(struct nfs_server *server, } if (ctx->rsize) - server->rsize = nfs_block_size(ctx->rsize, NULL); + server->rsize = nfs_io_size(ctx->rsize, clp->cl_proto); if (ctx->wsize) - server->wsize = nfs_block_size(ctx->wsize, NULL); + server->wsize = nfs_io_size(ctx->wsize, clp->cl_proto); server->acregmin = ctx->acregmin * HZ; server->acregmax = ctx->acregmax * HZ; @@ -759,18 +755,19 @@ error: static void nfs_server_set_fsinfo(struct nfs_server *server, struct nfs_fsinfo *fsinfo) { + struct nfs_client *clp = server->nfs_client; unsigned long max_rpc_payload, raw_max_rpc_payload; /* Work out a lot of parameters */ if (server->rsize == 0) - server->rsize = nfs_block_size(fsinfo->rtpref, NULL); + server->rsize = nfs_io_size(fsinfo->rtpref, clp->cl_proto); if (server->wsize == 0) - server->wsize = nfs_block_size(fsinfo->wtpref, NULL); + server->wsize = nfs_io_size(fsinfo->wtpref, clp->cl_proto); if (fsinfo->rtmax >= 512 && server->rsize > fsinfo->rtmax) - server->rsize = nfs_block_size(fsinfo->rtmax, NULL); + server->rsize = nfs_io_size(fsinfo->rtmax, clp->cl_proto); if (fsinfo->wtmax >= 512 && server->wsize > fsinfo->wtmax) - server->wsize = nfs_block_size(fsinfo->wtmax, NULL); + server->wsize = nfs_io_size(fsinfo->wtmax, clp->cl_proto); raw_max_rpc_payload = rpc_max_payload(server->client); max_rpc_payload = nfs_block_size(raw_max_rpc_payload, NULL); @@ -860,6 +857,14 @@ static int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *mntfh, str server->namelen = pathinfo.max_namelen; } + if (clp->rpc_ops->discover_trunking != NULL && + (server->caps & NFS_CAP_FS_LOCATIONS && + (server->flags & NFS_MOUNT_TRUNK_DISCOVERY))) { + error = clp->rpc_ops->discover_trunking(server, mntfh); + if (error < 0) + return error; + } + return 0; } diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 7c9eb679dbdb..ead8a0e06abf 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -228,8 +228,7 @@ again: * */ void nfs_inode_reclaim_delegation(struct inode *inode, const struct cred *cred, - fmode_t type, - const nfs4_stateid *stateid, + fmode_t type, const nfs4_stateid *stateid, unsigned long pagemod_limit) { struct nfs_delegation *delegation; @@ -239,25 +238,24 @@ void nfs_inode_reclaim_delegation(struct inode *inode, const struct cred *cred, delegation = rcu_dereference(NFS_I(inode)->delegation); if (delegation != NULL) { spin_lock(&delegation->lock); - if (nfs4_is_valid_delegation(delegation, 0)) { - nfs4_stateid_copy(&delegation->stateid, stateid); - delegation->type = type; - delegation->pagemod_limit = pagemod_limit; - oldcred = delegation->cred; - delegation->cred = get_cred(cred); - clear_bit(NFS_DELEGATION_NEED_RECLAIM, - &delegation->flags); - spin_unlock(&delegation->lock); - rcu_read_unlock(); - put_cred(oldcred); - trace_nfs4_reclaim_delegation(inode, type); - return; - } - /* We appear to have raced with a delegation return. */ + nfs4_stateid_copy(&delegation->stateid, stateid); + delegation->type = type; + delegation->pagemod_limit = pagemod_limit; + oldcred = delegation->cred; + delegation->cred = get_cred(cred); + clear_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags); + if (test_and_clear_bit(NFS_DELEGATION_REVOKED, + &delegation->flags)) + atomic_long_inc(&nfs_active_delegations); spin_unlock(&delegation->lock); + rcu_read_unlock(); + put_cred(oldcred); + trace_nfs4_reclaim_delegation(inode, type); + } else { + rcu_read_unlock(); + nfs_inode_set_delegation(inode, cred, type, stateid, + pagemod_limit); } - rcu_read_unlock(); - nfs_inode_set_delegation(inode, cred, type, stateid, pagemod_limit); } static int nfs_do_return_delegation(struct inode *inode, struct nfs_delegation *delegation, int issync) @@ -439,7 +437,7 @@ int nfs_inode_set_delegation(struct inode *inode, const struct cred *cred, struct nfs_delegation *freeme = NULL; int status = 0; - delegation = kmalloc(sizeof(*delegation), GFP_NOFS); + delegation = kmalloc(sizeof(*delegation), GFP_KERNEL_ACCOUNT); if (delegation == NULL) return -ENOMEM; nfs4_stateid_copy(&delegation->stateid, stateid); diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 347793626f19..f594dac436a7 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -39,6 +39,7 @@ #include <linux/sched.h> #include <linux/kmemleak.h> #include <linux/xattr.h> +#include <linux/hash.h> #include "delegation.h" #include "iostat.h" @@ -54,7 +55,7 @@ static int nfs_closedir(struct inode *, struct file *); static int nfs_readdir(struct file *, struct dir_context *); static int nfs_fsync_dir(struct file *, loff_t, loff_t, int); static loff_t nfs_llseek_dir(struct file *, loff_t, int); -static void nfs_readdir_clear_array(struct page*); +static void nfs_readdir_free_folio(struct folio *); const struct file_operations nfs_dir_operations = { .llseek = nfs_llseek_dir, @@ -66,28 +67,29 @@ const struct file_operations nfs_dir_operations = { }; const struct address_space_operations nfs_dir_aops = { - .freepage = nfs_readdir_clear_array, + .free_folio = nfs_readdir_free_folio, }; -static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir) +#define NFS_INIT_DTSIZE PAGE_SIZE + +static struct nfs_open_dir_context * +alloc_nfs_open_dir_context(struct inode *dir) { struct nfs_inode *nfsi = NFS_I(dir); struct nfs_open_dir_context *ctx; - ctx = kmalloc(sizeof(*ctx), GFP_KERNEL); + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL_ACCOUNT); if (ctx != NULL) { - ctx->duped = 0; ctx->attr_gencount = nfsi->attr_gencount; - ctx->dir_cookie = 0; - ctx->dup_cookie = 0; - ctx->page_index = 0; + ctx->dtsize = NFS_INIT_DTSIZE; spin_lock(&dir->i_lock); if (list_empty(&nfsi->open_files) && (nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER)) nfs_set_cache_invalid(dir, NFS_INO_INVALID_DATA | NFS_INO_REVAL_FORCED); - list_add(&ctx->list, &nfsi->open_files); - clear_bit(NFS_INO_FORCE_READDIR, &nfsi->flags); + list_add_tail_rcu(&ctx->list, &nfsi->open_files); + memcpy(ctx->verf, nfsi->cookieverf, sizeof(ctx->verf)); spin_unlock(&dir->i_lock); return ctx; } @@ -97,9 +99,9 @@ static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir static void put_nfs_open_dir_context(struct inode *dir, struct nfs_open_dir_context *ctx) { spin_lock(&dir->i_lock); - list_del(&ctx->list); + list_del_rcu(&ctx->list); spin_unlock(&dir->i_lock); - kfree(ctx); + kfree_rcu(ctx, rcu_head); } /* @@ -141,6 +143,7 @@ struct nfs_cache_array_entry { }; struct nfs_cache_array { + u64 change_attr; u64 last_cookie; unsigned int size; unsigned char page_full : 1, @@ -154,11 +157,10 @@ struct nfs_readdir_descriptor { struct page *page; struct dir_context *ctx; pgoff_t page_index; + pgoff_t page_index_max; u64 dir_cookie; u64 last_cookie; - u64 dup_cookie; loff_t current_index; - loff_t prev_index; __be32 verf[NFS_DIR_VERIFIER_SIZE]; unsigned long dir_verifier; @@ -166,23 +168,47 @@ struct nfs_readdir_descriptor { unsigned long gencount; unsigned long attr_gencount; unsigned int cache_entry_index; - signed char duped; + unsigned int buffer_fills; + unsigned int dtsize; + bool clear_cache; bool plus; + bool eob; bool eof; }; -static void nfs_readdir_array_init(struct nfs_cache_array *array) +static void nfs_set_dtsize(struct nfs_readdir_descriptor *desc, unsigned int sz) +{ + struct nfs_server *server = NFS_SERVER(file_inode(desc->file)); + unsigned int maxsize = server->dtsize; + + if (sz > maxsize) + sz = maxsize; + if (sz < NFS_MIN_FILE_IO_SIZE) + sz = NFS_MIN_FILE_IO_SIZE; + desc->dtsize = sz; +} + +static void nfs_shrink_dtsize(struct nfs_readdir_descriptor *desc) +{ + nfs_set_dtsize(desc, desc->dtsize >> 1); +} + +static void nfs_grow_dtsize(struct nfs_readdir_descriptor *desc) { - memset(array, 0, sizeof(struct nfs_cache_array)); + nfs_set_dtsize(desc, desc->dtsize << 1); } -static void nfs_readdir_page_init_array(struct page *page, u64 last_cookie) +static void nfs_readdir_page_init_array(struct page *page, u64 last_cookie, + u64 change_attr) { struct nfs_cache_array *array; array = kmap_atomic(page); - nfs_readdir_array_init(array); + array->change_attr = change_attr; array->last_cookie = last_cookie; + array->size = 0; + array->page_full = 0; + array->page_is_eof = 0; array->cookies_are_ordered = 1; kunmap_atomic(array); } @@ -190,25 +216,36 @@ static void nfs_readdir_page_init_array(struct page *page, u64 last_cookie) /* * we are freeing strings created by nfs_add_to_readdir_array() */ -static -void nfs_readdir_clear_array(struct page *page) +static void nfs_readdir_clear_array(struct page *page) { struct nfs_cache_array *array; - int i; + unsigned int i; array = kmap_atomic(page); for (i = 0; i < array->size; i++) kfree(array->array[i].name); - nfs_readdir_array_init(array); + array->size = 0; kunmap_atomic(array); } +static void nfs_readdir_free_folio(struct folio *folio) +{ + nfs_readdir_clear_array(&folio->page); +} + +static void nfs_readdir_page_reinit_array(struct page *page, u64 last_cookie, + u64 change_attr) +{ + nfs_readdir_clear_array(page); + nfs_readdir_page_init_array(page, last_cookie, change_attr); +} + static struct page * nfs_readdir_page_array_alloc(u64 last_cookie, gfp_t gfp_flags) { struct page *page = alloc_page(gfp_flags); if (page) - nfs_readdir_page_init_array(page, last_cookie); + nfs_readdir_page_init_array(page, last_cookie, 0); return page; } @@ -220,6 +257,11 @@ static void nfs_readdir_page_array_free(struct page *page) } } +static u64 nfs_readdir_array_index_cookie(struct nfs_cache_array *array) +{ + return array->size == 0 ? array->last_cookie : array->array[0].cookie; +} + static void nfs_readdir_array_set_eof(struct nfs_cache_array *array) { array->page_is_eof = 1; @@ -249,36 +291,40 @@ static const char *nfs_readdir_copy_name(const char *name, unsigned int len) return ret; } +static size_t nfs_readdir_array_maxentries(void) +{ + return (PAGE_SIZE - sizeof(struct nfs_cache_array)) / + sizeof(struct nfs_cache_array_entry); +} + /* * Check that the next array entry lies entirely within the page bounds */ static int nfs_readdir_array_can_expand(struct nfs_cache_array *array) { - struct nfs_cache_array_entry *cache_entry; - if (array->page_full) return -ENOSPC; - cache_entry = &array->array[array->size + 1]; - if ((char *)cache_entry - (char *)array > PAGE_SIZE) { + if (array->size == nfs_readdir_array_maxentries()) { array->page_full = 1; return -ENOSPC; } return 0; } -static -int nfs_readdir_add_to_array(struct nfs_entry *entry, struct page *page) +static int nfs_readdir_page_array_append(struct page *page, + const struct nfs_entry *entry, + u64 *cookie) { struct nfs_cache_array *array; struct nfs_cache_array_entry *cache_entry; const char *name; - int ret; + int ret = -ENOMEM; name = nfs_readdir_copy_name(entry->name, entry->len); - if (!name) - return -ENOMEM; array = kmap_atomic(page); + if (!name) + goto out; ret = nfs_readdir_array_can_expand(array); if (ret) { kfree(name); @@ -286,7 +332,7 @@ int nfs_readdir_add_to_array(struct nfs_entry *entry, struct page *page) } cache_entry = &array->array[array->size]; - cache_entry->cookie = entry->prev_cookie; + cache_entry->cookie = array->last_cookie; cache_entry->ino = entry->ino; cache_entry->d_type = entry->d_type; cache_entry->name_len = entry->len; @@ -298,23 +344,72 @@ int nfs_readdir_add_to_array(struct nfs_entry *entry, struct page *page) if (entry->eof != 0) nfs_readdir_array_set_eof(array); out: + *cookie = array->last_cookie; + kunmap_atomic(array); + return ret; +} + +#define NFS_READDIR_COOKIE_MASK (U32_MAX >> 14) +/* + * Hash algorithm allowing content addressible access to sequences + * of directory cookies. Content is addressed by the value of the + * cookie index of the first readdir entry in a page. + * + * We select only the first 18 bits to avoid issues with excessive + * memory use for the page cache XArray. 18 bits should allow the caching + * of 262144 pages of sequences of readdir entries. Since each page holds + * 127 readdir entries for a typical 64-bit system, that works out to a + * cache of ~ 33 million entries per directory. + */ +static pgoff_t nfs_readdir_page_cookie_hash(u64 cookie) +{ + if (cookie == 0) + return 0; + return hash_64(cookie, 18); +} + +static bool nfs_readdir_page_validate(struct page *page, u64 last_cookie, + u64 change_attr) +{ + struct nfs_cache_array *array = kmap_atomic(page); + int ret = true; + + if (array->change_attr != change_attr) + ret = false; + if (nfs_readdir_array_index_cookie(array) != last_cookie) + ret = false; kunmap_atomic(array); return ret; } +static void nfs_readdir_page_unlock_and_put(struct page *page) +{ + unlock_page(page); + put_page(page); +} + +static void nfs_readdir_page_init_and_validate(struct page *page, u64 cookie, + u64 change_attr) +{ + if (PageUptodate(page)) { + if (nfs_readdir_page_validate(page, cookie, change_attr)) + return; + nfs_readdir_clear_array(page); + } + nfs_readdir_page_init_array(page, cookie, change_attr); + SetPageUptodate(page); +} + static struct page *nfs_readdir_page_get_locked(struct address_space *mapping, - pgoff_t index, u64 last_cookie) + u64 cookie, u64 change_attr) { + pgoff_t index = nfs_readdir_page_cookie_hash(cookie); struct page *page; page = grab_cache_page(mapping, index); - if (page && !PageUptodate(page)) { - nfs_readdir_page_init_array(page, last_cookie); - if (invalidate_inode_pages2_range(mapping, index + 1, -1) < 0) - nfs_zap_mapping(mapping->host, mapping); - SetPageUptodate(page); - } - + if (!page) + return NULL; + nfs_readdir_page_init_and_validate(page, cookie, change_attr); return page; } @@ -349,24 +444,19 @@ static void nfs_readdir_page_set_eof(struct page *page) kunmap_atomic(array); } -static void nfs_readdir_page_unlock_and_put(struct page *page) -{ - unlock_page(page); - put_page(page); -} - static struct page *nfs_readdir_page_get_next(struct address_space *mapping, - pgoff_t index, u64 cookie) + u64 cookie, u64 change_attr) { + pgoff_t index = nfs_readdir_page_cookie_hash(cookie); struct page *page; - page = nfs_readdir_page_get_locked(mapping, index, cookie); - if (page) { - if (nfs_readdir_page_last_cookie(page) == cookie) - return page; - nfs_readdir_page_unlock_and_put(page); - } - return NULL; + page = grab_cache_page_nowait(mapping, index); + if (!page) + return NULL; + nfs_readdir_page_init_and_validate(page, cookie, change_attr); + if (nfs_readdir_page_last_cookie(page) != cookie) + nfs_readdir_page_reinit_array(page, cookie, change_attr); + return page; } static inline @@ -388,6 +478,25 @@ bool nfs_readdir_use_cookie(const struct file *filp) return true; } +static void nfs_readdir_seek_next_array(struct nfs_cache_array *array, + struct nfs_readdir_descriptor *desc) +{ + if (array->page_full) { + desc->last_cookie = array->last_cookie; + desc->current_index += array->size; + desc->cache_entry_index = 0; + desc->page_index++; + } else + desc->last_cookie = nfs_readdir_array_index_cookie(array); +} + +static void nfs_readdir_rewind_search(struct nfs_readdir_descriptor *desc) +{ + desc->current_index = 0; + desc->last_cookie = 0; + desc->page_index = 0; +} + static int nfs_readdir_search_for_pos(struct nfs_cache_array *array, struct nfs_readdir_descriptor *desc) { @@ -399,6 +508,7 @@ static int nfs_readdir_search_for_pos(struct nfs_cache_array *array, if (diff >= array->size) { if (array->page_is_eof) goto out_eof; + nfs_readdir_seek_next_array(array, desc); return -EAGAIN; } @@ -411,16 +521,6 @@ out_eof: return -EBADCOOKIE; } -static bool -nfs_readdir_inode_mapping_valid(struct nfs_inode *nfsi) -{ - if (nfsi->cache_validity & (NFS_INO_INVALID_CHANGE | - NFS_INO_INVALID_DATA)) - return false; - smp_rmb(); - return !test_bit(NFS_INO_INVALIDATING, &nfsi->flags); -} - static bool nfs_readdir_array_cookie_in_range(struct nfs_cache_array *array, u64 cookie) { @@ -437,8 +537,7 @@ static bool nfs_readdir_array_cookie_in_range(struct nfs_cache_array *array, static int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, struct nfs_readdir_descriptor *desc) { - int i; - loff_t new_pos; + unsigned int i; int status = -EAGAIN; if (!nfs_readdir_array_cookie_in_range(array, desc->dir_cookie)) @@ -446,33 +545,10 @@ static int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, for (i = 0; i < array->size; i++) { if (array->array[i].cookie == desc->dir_cookie) { - struct nfs_inode *nfsi = NFS_I(file_inode(desc->file)); - - new_pos = desc->current_index + i; - if (desc->attr_gencount != nfsi->attr_gencount || - !nfs_readdir_inode_mapping_valid(nfsi)) { - desc->duped = 0; - desc->attr_gencount = nfsi->attr_gencount; - } else if (new_pos < desc->prev_index) { - if (desc->duped > 0 - && desc->dup_cookie == desc->dir_cookie) { - if (printk_ratelimit()) { - pr_notice("NFS: directory %pD2 contains a readdir loop." - "Please contact your server vendor. " - "The file: %s has duplicate cookie %llu\n", - desc->file, array->array[i].name, desc->dir_cookie); - } - status = -ELOOP; - goto out; - } - desc->dup_cookie = desc->dir_cookie; - desc->duped = -1; - } if (nfs_readdir_use_cookie(desc->file)) desc->ctx->pos = desc->dir_cookie; else - desc->ctx->pos = new_pos; - desc->prev_index = new_pos; + desc->ctx->pos = desc->current_index + i; desc->cache_entry_index = i; return 0; } @@ -482,8 +558,8 @@ check_eof: status = -EBADCOOKIE; if (desc->dir_cookie == array->last_cookie) desc->eof = true; - } -out: + } else + nfs_readdir_seek_next_array(array, desc); return status; } @@ -499,11 +575,6 @@ static int nfs_readdir_search_array(struct nfs_readdir_descriptor *desc) else status = nfs_readdir_search_for_cookie(array, desc); - if (status == -EAGAIN) { - desc->last_cookie = array->last_cookie; - desc->current_index += array->size; - desc->page_index++; - } kunmap_atomic(array); return status; } @@ -539,7 +610,6 @@ static int nfs_readdir_xdr_filler(struct nfs_readdir_descriptor *desc, /* We requested READDIRPLUS, but the server doesn't grok it */ if (error == -ENOTSUPP && desc->plus) { NFS_SERVER(inode)->caps &= ~NFS_CAP_READDIRPLUS; - clear_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags); desc->plus = arg.plus = false; goto again; } @@ -589,51 +659,68 @@ int nfs_same_file(struct dentry *dentry, struct nfs_entry *entry) return 1; } -static -bool nfs_use_readdirplus(struct inode *dir, struct dir_context *ctx) +#define NFS_READDIR_CACHE_USAGE_THRESHOLD (8UL) + +static bool nfs_use_readdirplus(struct inode *dir, struct dir_context *ctx, + unsigned int cache_hits, + unsigned int cache_misses) { if (!nfs_server_capable(dir, NFS_CAP_READDIRPLUS)) return false; - if (test_and_clear_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(dir)->flags)) - return true; - if (ctx->pos == 0) + if (ctx->pos == 0 || + cache_hits + cache_misses > NFS_READDIR_CACHE_USAGE_THRESHOLD) return true; return false; } /* - * This function is called by the lookup and getattr code to request the + * This function is called by the getattr code to request the * use of readdirplus to accelerate any future lookups in the same * directory. */ -void nfs_advise_use_readdirplus(struct inode *dir) +void nfs_readdir_record_entry_cache_hit(struct inode *dir) { struct nfs_inode *nfsi = NFS_I(dir); + struct nfs_open_dir_context *ctx; if (nfs_server_capable(dir, NFS_CAP_READDIRPLUS) && - !list_empty(&nfsi->open_files)) - set_bit(NFS_INO_ADVISE_RDPLUS, &nfsi->flags); + S_ISDIR(dir->i_mode)) { + rcu_read_lock(); + list_for_each_entry_rcu (ctx, &nfsi->open_files, list) + atomic_inc(&ctx->cache_hits); + rcu_read_unlock(); + } } /* * This function is mainly for use by nfs_getattr(). * * If this is an 'ls -l', we want to force use of readdirplus. - * Do this by checking if there is an active file descriptor - * and calling nfs_advise_use_readdirplus, then forcing a - * cache flush. */ -void nfs_force_use_readdirplus(struct inode *dir) +void nfs_readdir_record_entry_cache_miss(struct inode *dir) { struct nfs_inode *nfsi = NFS_I(dir); + struct nfs_open_dir_context *ctx; if (nfs_server_capable(dir, NFS_CAP_READDIRPLUS) && - !list_empty(&nfsi->open_files)) { - set_bit(NFS_INO_ADVISE_RDPLUS, &nfsi->flags); - set_bit(NFS_INO_FORCE_READDIR, &nfsi->flags); + S_ISDIR(dir->i_mode)) { + rcu_read_lock(); + list_for_each_entry_rcu (ctx, &nfsi->open_files, list) + atomic_inc(&ctx->cache_misses); + rcu_read_unlock(); } } +static void nfs_lookup_advise_force_readdirplus(struct inode *dir, + unsigned int flags) +{ + if (nfs_server_capable(dir, NFS_CAP_CASE_INSENSITIVE)) + return; + if (flags & (LOOKUP_EXCL | LOOKUP_PARENT | LOOKUP_REVAL)) + return; + nfs_readdir_record_entry_cache_miss(dir); +} + static void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry, unsigned long dir_verifier) @@ -684,8 +771,12 @@ again: status = nfs_refresh_inode(d_inode(dentry), entry->fattr); if (!status) nfs_setsecurity(d_inode(dentry), entry->fattr); + trace_nfs_readdir_lookup_revalidate(d_inode(parent), + dentry, 0, status); goto out; } else { + trace_nfs_readdir_lookup_revalidate_failed( + d_inode(parent), dentry, 0); d_invalidate(dentry); dput(dentry); dentry = NULL; @@ -707,22 +798,38 @@ again: dentry = alias; } nfs_set_verifier(dentry, dir_verifier); + trace_nfs_readdir_lookup(d_inode(parent), dentry, 0); out: dput(dentry); } +static int nfs_readdir_entry_decode(struct nfs_readdir_descriptor *desc, + struct nfs_entry *entry, + struct xdr_stream *stream) +{ + int ret; + + if (entry->fattr->label) + entry->fattr->label->len = NFS4_MAXLABELLEN; + ret = xdr_decode(desc, entry, stream); + if (ret || !desc->plus) + return ret; + nfs_prime_dcache(file_dentry(desc->file), entry, desc->dir_verifier); + return 0; +} + /* Perform conversion from xdr to cache array */ static int nfs_readdir_page_filler(struct nfs_readdir_descriptor *desc, struct nfs_entry *entry, - struct page **xdr_pages, - unsigned int buflen, - struct page **arrays, - size_t narrays) + struct page **xdr_pages, unsigned int buflen, + struct page **arrays, size_t narrays, + u64 change_attr) { struct address_space *mapping = desc->file->f_mapping; struct xdr_stream stream; struct xdr_buf buf; struct page *scratch, *new, *page = *arrays; + u64 cookie; int status; scratch = alloc_page(GFP_KERNEL); @@ -733,54 +840,50 @@ static int nfs_readdir_page_filler(struct nfs_readdir_descriptor *desc, xdr_set_scratch_page(&stream, scratch); do { - if (entry->fattr->label) - entry->fattr->label->len = NFS4_MAXLABELLEN; - - status = xdr_decode(desc, entry, &stream); + status = nfs_readdir_entry_decode(desc, entry, &stream); if (status != 0) break; - if (desc->plus) - nfs_prime_dcache(file_dentry(desc->file), entry, - desc->dir_verifier); - - status = nfs_readdir_add_to_array(entry, page); + status = nfs_readdir_page_array_append(page, entry, &cookie); if (status != -ENOSPC) continue; if (page->mapping != mapping) { if (!--narrays) break; - new = nfs_readdir_page_array_alloc(entry->prev_cookie, - GFP_KERNEL); + new = nfs_readdir_page_array_alloc(cookie, GFP_KERNEL); if (!new) break; arrays++; *arrays = page = new; } else { - new = nfs_readdir_page_get_next(mapping, - page->index + 1, - entry->prev_cookie); + new = nfs_readdir_page_get_next(mapping, cookie, + change_attr); if (!new) break; if (page != *arrays) nfs_readdir_page_unlock_and_put(page); page = new; } - status = nfs_readdir_add_to_array(entry, page); + desc->page_index_max++; + status = nfs_readdir_page_array_append(page, entry, &cookie); } while (!status && !entry->eof); switch (status) { case -EBADCOOKIE: - if (entry->eof) { - nfs_readdir_page_set_eof(page); - status = 0; - } - break; - case -ENOSPC: + if (!entry->eof) + break; + nfs_readdir_page_set_eof(page); + fallthrough; case -EAGAIN: status = 0; break; + case -ENOSPC: + status = 0; + if (!desc->plus) + break; + while (!nfs_readdir_entry_decode(desc, entry, &stream)) + ; } if (page != *arrays) @@ -826,12 +929,14 @@ static int nfs_readdir_xdr_to_array(struct nfs_readdir_descriptor *desc, __be32 *verf_arg, __be32 *verf_res, struct page **arrays, size_t narrays) { + u64 change_attr; struct page **pages; struct page *page = *arrays; struct nfs_entry *entry; size_t array_size; struct inode *inode = file_inode(desc->file); - size_t dtsize = NFS_SERVER(inode)->dtsize; + unsigned int dtsize = desc->dtsize; + unsigned int pglen; int status = -ENOMEM; entry = kzalloc(sizeof(*entry), GFP_KERNEL); @@ -849,26 +954,21 @@ static int nfs_readdir_xdr_to_array(struct nfs_readdir_descriptor *desc, if (!pages) goto out; - do { - unsigned int pglen; - status = nfs_readdir_xdr_filler(desc, verf_arg, entry->cookie, - pages, dtsize, - verf_res); - if (status < 0) - break; - - pglen = status; - if (pglen == 0) { - nfs_readdir_page_set_eof(page); - break; - } - - verf_arg = verf_res; + change_attr = inode_peek_iversion_raw(inode); + status = nfs_readdir_xdr_filler(desc, verf_arg, entry->cookie, pages, + dtsize, verf_res); + if (status < 0) + goto free_pages; + pglen = status; + if (pglen != 0) status = nfs_readdir_page_filler(desc, entry, pages, pglen, - arrays, narrays); - } while (!status && nfs_readdir_page_needs_filling(page)); + arrays, narrays, change_attr); + else + nfs_readdir_page_set_eof(page); + desc->buffer_fills++; +free_pages: nfs_readdir_free_pages(pages, array_size); out: nfs_free_fattr(entry->fattr); @@ -893,9 +993,17 @@ nfs_readdir_page_unlock_and_put_cached(struct nfs_readdir_descriptor *desc) static struct page * nfs_readdir_page_get_cached(struct nfs_readdir_descriptor *desc) { - return nfs_readdir_page_get_locked(desc->file->f_mapping, - desc->page_index, - desc->last_cookie); + struct address_space *mapping = desc->file->f_mapping; + u64 change_attr = inode_peek_iversion_raw(mapping->host); + u64 cookie = desc->last_cookie; + struct page *page; + + page = nfs_readdir_page_get_locked(mapping, cookie, change_attr); + if (!page) + return NULL; + if (desc->clear_cache && !nfs_readdir_page_needs_filling(page)) + nfs_readdir_page_reinit_array(page, cookie, change_attr); + return page; } /* @@ -913,13 +1021,23 @@ static int find_and_lock_cache_page(struct nfs_readdir_descriptor *desc) if (!desc->page) return -ENOMEM; if (nfs_readdir_page_needs_filling(desc->page)) { + /* Grow the dtsize if we had to go back for more pages */ + if (desc->page_index == desc->page_index_max) + nfs_grow_dtsize(desc); + desc->page_index_max = desc->page_index; + trace_nfs_readdir_cache_fill(desc->file, nfsi->cookieverf, + desc->last_cookie, + desc->page->index, desc->dtsize); res = nfs_readdir_xdr_to_array(desc, nfsi->cookieverf, verf, &desc->page, 1); if (res < 0) { nfs_readdir_page_unlock_and_put_cached(desc); + trace_nfs_readdir_cache_fill_done(inode, res); if (res == -EBADCOOKIE || res == -ENOTSYNC) { invalidate_inode_pages2(desc->file->f_mapping); - desc->page_index = 0; + nfs_readdir_rewind_search(desc); + trace_nfs_readdir_invalidate_cache_range( + inode, 0, MAX_LFS_FILESIZE); return -EAGAIN; } return res; @@ -927,9 +1045,16 @@ static int find_and_lock_cache_page(struct nfs_readdir_descriptor *desc) /* * Set the cookie verifier if the page cache was empty */ - if (desc->page_index == 0) + if (desc->last_cookie == 0 && + memcmp(nfsi->cookieverf, verf, sizeof(nfsi->cookieverf))) { memcpy(nfsi->cookieverf, verf, sizeof(nfsi->cookieverf)); + invalidate_inode_pages2_range(desc->file->f_mapping, 1, + -1); + trace_nfs_readdir_invalidate_cache_range( + inode, 1, MAX_LFS_FILESIZE); + } + desc->clear_cache = false; } res = nfs_readdir_search_array(desc); if (res == 0) @@ -938,34 +1063,12 @@ static int find_and_lock_cache_page(struct nfs_readdir_descriptor *desc) return res; } -static bool nfs_readdir_dont_search_cache(struct nfs_readdir_descriptor *desc) -{ - struct address_space *mapping = desc->file->f_mapping; - struct inode *dir = file_inode(desc->file); - unsigned int dtsize = NFS_SERVER(dir)->dtsize; - loff_t size = i_size_read(dir); - - /* - * Default to uncached readdir if the page cache is empty, and - * we're looking for a non-zero cookie in a large directory. - */ - return desc->dir_cookie != 0 && mapping->nrpages == 0 && size > dtsize; -} - /* Search for desc->dir_cookie from the beginning of the page cache */ static int readdir_search_pagecache(struct nfs_readdir_descriptor *desc) { int res; - if (nfs_readdir_dont_search_cache(desc)) - return -EBADCOOKIE; - do { - if (desc->page_index == 0) { - desc->current_index = 0; - desc->prev_index = 0; - desc->last_cookie = 0; - } res = find_and_lock_cache_page(desc); } while (res == -EAGAIN); return res; @@ -979,34 +1082,35 @@ static void nfs_do_filldir(struct nfs_readdir_descriptor *desc, { struct file *file = desc->file; struct nfs_cache_array *array; - unsigned int i = 0; + unsigned int i; - array = kmap(desc->page); + array = kmap_local_page(desc->page); for (i = desc->cache_entry_index; i < array->size; i++) { struct nfs_cache_array_entry *ent; ent = &array->array[i]; if (!dir_emit(desc->ctx, ent->name, ent->name_len, nfs_compat_user_ino64(ent->ino), ent->d_type)) { - desc->eof = true; + desc->eob = true; break; } memcpy(desc->verf, verf, sizeof(desc->verf)); - if (i < (array->size-1)) - desc->dir_cookie = array->array[i+1].cookie; - else + if (i == array->size - 1) { desc->dir_cookie = array->last_cookie; + nfs_readdir_seek_next_array(array, desc); + } else { + desc->dir_cookie = array->array[i + 1].cookie; + desc->last_cookie = array->array[0].cookie; + } if (nfs_readdir_use_cookie(file)) desc->ctx->pos = desc->dir_cookie; else desc->ctx->pos++; - if (desc->duped != 0) - desc->duped = 1; } if (array->page_is_eof) - desc->eof = true; + desc->eof = !desc->eob; - kunmap(desc->page); + kunmap_local(array); dfprintk(DIRCACHE, "NFS: nfs_do_filldir() filling ended @ cookie %llu\n", (unsigned long long)desc->dir_cookie); } @@ -1041,26 +1145,63 @@ static int uncached_readdir(struct nfs_readdir_descriptor *desc) goto out; desc->page_index = 0; + desc->cache_entry_index = 0; desc->last_cookie = desc->dir_cookie; - desc->duped = 0; + desc->page_index_max = 0; + + trace_nfs_readdir_uncached(desc->file, desc->verf, desc->last_cookie, + -1, desc->dtsize); status = nfs_readdir_xdr_to_array(desc, desc->verf, verf, arrays, sz); + if (status < 0) { + trace_nfs_readdir_uncached_done(file_inode(desc->file), status); + goto out_free; + } - for (i = 0; !desc->eof && i < sz && arrays[i]; i++) { + for (i = 0; !desc->eob && i < sz && arrays[i]; i++) { desc->page = arrays[i]; nfs_do_filldir(desc, verf); } desc->page = NULL; - + /* + * Grow the dtsize if we have to go back for more pages, + * or shrink it if we're reading too many. + */ + if (!desc->eof) { + if (!desc->eob) + nfs_grow_dtsize(desc); + else if (desc->buffer_fills == 1 && + i < (desc->page_index_max >> 1)) + nfs_shrink_dtsize(desc); + } +out_free: for (i = 0; i < sz && arrays[i]; i++) nfs_readdir_page_array_free(arrays[i]); out: + if (!nfs_readdir_use_cookie(desc->file)) + nfs_readdir_rewind_search(desc); + desc->page_index_max = -1; kfree(arrays); dfprintk(DIRCACHE, "NFS: %s: returns %d\n", __func__, status); return status; } +#define NFS_READDIR_CACHE_MISS_THRESHOLD (16UL) + +static bool nfs_readdir_handle_cache_misses(struct inode *inode, + struct nfs_readdir_descriptor *desc, + unsigned int cache_misses, + bool force_clear) +{ + if (desc->ctx->pos == 0 || !desc->plus) + return false; + if (cache_misses <= NFS_READDIR_CACHE_MISS_THRESHOLD && !force_clear) + return false; + trace_nfs_readdir_force_readdirplus(inode); + return true; +} + /* The file offset position represents the dirent entry number. A last cookie cache takes care of the common case of reading the whole directory. @@ -1072,7 +1213,8 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) struct nfs_inode *nfsi = NFS_I(inode); struct nfs_open_dir_context *dir_ctx = file->private_data; struct nfs_readdir_descriptor *desc; - pgoff_t page_index; + unsigned int cache_hits, cache_misses; + bool force_clear; int res; dfprintk(FILE, "NFS: readdir(%pD2) starting at cookie %llu\n", @@ -1085,11 +1227,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) * to either find the entry with the appropriate number or * revalidate the cookie. */ - if (ctx->pos == 0 || nfs_attribute_cache_expired(inode)) { - res = nfs_revalidate_mapping(inode, file->f_mapping); - if (res < 0) - goto out; - } + nfs_revalidate_mapping(inode, file->f_mapping); res = -ENOMEM; desc = kzalloc(sizeof(*desc), GFP_KERNEL); @@ -1097,20 +1235,30 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) goto out; desc->file = file; desc->ctx = ctx; - desc->plus = nfs_use_readdirplus(inode, ctx); + desc->page_index_max = -1; spin_lock(&file->f_lock); desc->dir_cookie = dir_ctx->dir_cookie; - desc->dup_cookie = dir_ctx->dup_cookie; - desc->duped = dir_ctx->duped; - page_index = dir_ctx->page_index; + desc->page_index = dir_ctx->page_index; + desc->last_cookie = dir_ctx->last_cookie; desc->attr_gencount = dir_ctx->attr_gencount; + desc->eof = dir_ctx->eof; + nfs_set_dtsize(desc, dir_ctx->dtsize); memcpy(desc->verf, dir_ctx->verf, sizeof(desc->verf)); + cache_hits = atomic_xchg(&dir_ctx->cache_hits, 0); + cache_misses = atomic_xchg(&dir_ctx->cache_misses, 0); + force_clear = dir_ctx->force_clear; spin_unlock(&file->f_lock); - if (test_and_clear_bit(NFS_INO_FORCE_READDIR, &nfsi->flags) && - list_is_singular(&nfsi->open_files)) - invalidate_mapping_pages(inode->i_mapping, page_index + 1, -1); + if (desc->eof) { + res = 0; + goto out_free; + } + + desc->plus = nfs_use_readdirplus(inode, ctx, cache_hits, cache_misses); + force_clear = nfs_readdir_handle_cache_misses(inode, desc, cache_misses, + force_clear); + desc->clear_cache = force_clear; do { res = readdir_search_pagecache(desc); @@ -1129,9 +1277,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) break; } if (res == -ETOOSMALL && desc->plus) { - clear_bit(NFS_INO_ADVISE_RDPLUS, &nfsi->flags); nfs_zap_caches(inode); - desc->page_index = 0; desc->plus = false; desc->eof = false; continue; @@ -1141,17 +1287,21 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) nfs_do_filldir(desc, nfsi->cookieverf); nfs_readdir_page_unlock_and_put_cached(desc); - } while (!desc->eof); + if (desc->page_index == desc->page_index_max) + desc->clear_cache = force_clear; + } while (!desc->eob && !desc->eof); spin_lock(&file->f_lock); dir_ctx->dir_cookie = desc->dir_cookie; - dir_ctx->dup_cookie = desc->dup_cookie; - dir_ctx->duped = desc->duped; + dir_ctx->last_cookie = desc->last_cookie; dir_ctx->attr_gencount = desc->attr_gencount; dir_ctx->page_index = desc->page_index; + dir_ctx->force_clear = force_clear; + dir_ctx->eof = desc->eof; + dir_ctx->dtsize = desc->dtsize; memcpy(dir_ctx->verf, desc->verf, sizeof(dir_ctx->verf)); spin_unlock(&file->f_lock); - +out_free: kfree(desc); out: @@ -1186,13 +1336,15 @@ static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence) } if (offset != filp->f_pos) { filp->f_pos = offset; - if (nfs_readdir_use_cookie(filp)) - dir_ctx->dir_cookie = offset; - else + dir_ctx->page_index = 0; + if (!nfs_readdir_use_cookie(filp)) { dir_ctx->dir_cookie = 0; - if (offset == 0) - memset(dir_ctx->verf, 0, sizeof(dir_ctx->verf)); - dir_ctx->duped = 0; + dir_ctx->last_cookie = 0; + } else { + dir_ctx->dir_cookie = offset; + dir_ctx->last_cookie = offset; + } + dir_ctx->eof = false; } spin_unlock(&filp->f_lock); return offset; @@ -1325,6 +1477,14 @@ void nfs_clear_verifier_delegated(struct inode *inode) EXPORT_SYMBOL_GPL(nfs_clear_verifier_delegated); #endif /* IS_ENABLED(CONFIG_NFS_V4) */ +static int nfs_dentry_verify_change(struct inode *dir, struct dentry *dentry) +{ + if (nfs_server_capable(dir, NFS_CAP_CASE_INSENSITIVE) && + d_really_is_negative(dentry)) + return dentry->d_time == inode_peek_iversion_raw(dir); + return nfs_verify_change_attribute(dir, dentry->d_time); +} + /* * A check for whether or not the parent directory has changed. * In the case it has, we assume that the dentries are untrustworthy @@ -1338,7 +1498,7 @@ static int nfs_check_verifier(struct inode *dir, struct dentry *dentry, return 1; if (NFS_SERVER(dir)->flags & NFS_MOUNT_LOOKUP_CACHE_NONE) return 0; - if (!nfs_verify_change_attribute(dir, dentry->d_time)) + if (!nfs_dentry_verify_change(dir, dentry)) return 0; /* Revalidate nfsi->cache_change_attribute before we declare a match */ if (nfs_mapping_need_revalidate_inode(dir)) { @@ -1347,7 +1507,7 @@ static int nfs_check_verifier(struct inode *dir, struct dentry *dentry, if (__nfs_revalidate_inode(NFS_SERVER(dir), dir) < 0) return 0; } - if (!nfs_verify_change_attribute(dir, dentry->d_time)) + if (!nfs_dentry_verify_change(dir, dentry)) return 0; return 1; } @@ -1399,7 +1559,12 @@ int nfs_lookup_verify_inode(struct inode *inode, unsigned int flags) if (flags & LOOKUP_REVAL) goto out_force; out: - return (inode->i_nlink == 0) ? -ESTALE : 0; + if (inode->i_nlink > 0 || + (inode->i_nlink == 0 && + test_bit(NFS_INO_PRESERVE_UNLINKED, &NFS_I(inode)->flags))) + return 0; + else + return -ESTALE; out_force: if (flags & LOOKUP_RCU) return -ECHILD; @@ -1437,6 +1602,9 @@ int nfs_neg_need_reval(struct inode *dir, struct dentry *dentry, return 0; if (NFS_SERVER(dir)->flags & NFS_MOUNT_LOOKUP_CACHE_NONEG) return 1; + /* Case insensitive server? Revalidate negative dentries */ + if (nfs_server_capable(dir, NFS_CAP_CASE_INSENSITIVE)) + return 1; return !nfs_check_verifier(dir, dentry, flags & LOOKUP_RCU); } @@ -1446,9 +1614,7 @@ nfs_lookup_revalidate_done(struct inode *dir, struct dentry *dentry, { switch (error) { case 1: - dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) is valid\n", - __func__, dentry); - return 1; + break; case 0: /* * We can't d_drop the root of a disconnected tree: @@ -1457,13 +1623,10 @@ nfs_lookup_revalidate_done(struct inode *dir, struct dentry *dentry, * inodes on unmount and further oopses. */ if (inode && IS_ROOT(dentry)) - return 1; - dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) is invalid\n", - __func__, dentry); - return 0; + error = 1; + break; } - dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) lookup returned error %d\n", - __func__, dentry, error); + trace_nfs_lookup_revalidate_exit(dir, dentry, 0, error); return error; } @@ -1488,15 +1651,17 @@ nfs_lookup_revalidate_delegated(struct inode *dir, struct dentry *dentry, return nfs_lookup_revalidate_done(dir, dentry, inode, 1); } -static int -nfs_lookup_revalidate_dentry(struct inode *dir, struct dentry *dentry, - struct inode *inode) +static int nfs_lookup_revalidate_dentry(struct inode *dir, + struct dentry *dentry, + struct inode *inode, unsigned int flags) { struct nfs_fh *fhandle; struct nfs_fattr *fattr; unsigned long dir_verifier; int ret; + trace_nfs_lookup_revalidate_enter(dir, dentry, flags); + ret = -ENOMEM; fhandle = nfs_alloc_fhandle(); fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode)); @@ -1517,6 +1682,10 @@ nfs_lookup_revalidate_dentry(struct inode *dir, struct dentry *dentry, } goto out; } + + /* Request help from readdirplus */ + nfs_lookup_advise_force_readdirplus(dir, flags); + ret = 0; if (nfs_compare_fh(NFS_FH(inode), fhandle)) goto out; @@ -1526,8 +1695,6 @@ nfs_lookup_revalidate_dentry(struct inode *dir, struct dentry *dentry, nfs_setsecurity(inode, fattr); nfs_set_verifier(dentry, dir_verifier); - /* set a readdirplus hint that we had a cache miss */ - nfs_force_use_readdirplus(dir); ret = 1; out: nfs_free_fattr(fattr); @@ -1537,7 +1704,7 @@ out: * If the lookup failed despite the dentry change attribute being * a match, then we should revalidate the directory cache. */ - if (!ret && nfs_verify_change_attribute(dir, dentry->d_time)) + if (!ret && nfs_dentry_verify_change(dir, dentry)) nfs_mark_dir_for_revalidate(dir); return nfs_lookup_revalidate_done(dir, dentry, inode, ret); } @@ -1572,6 +1739,10 @@ nfs_do_lookup_revalidate(struct inode *dir, struct dentry *dentry, goto out_bad; } + if ((flags & LOOKUP_RENAME_TARGET) && d_count(dentry) < 2 && + nfs_server_capable(dir, NFS_CAP_CASE_INSENSITIVE)) + goto out_bad; + if (nfs_verifier_is_delegated(dentry)) return nfs_lookup_revalidate_delegated(dir, dentry, inode); @@ -1584,7 +1755,6 @@ nfs_do_lookup_revalidate(struct inode *dir, struct dentry *dentry, nfs_mark_dir_for_revalidate(dir); goto out_bad; } - nfs_advise_use_readdirplus(dir); goto out_valid; } @@ -1594,10 +1764,7 @@ nfs_do_lookup_revalidate(struct inode *dir, struct dentry *dentry, if (NFS_STALE(inode)) goto out_bad; - trace_nfs_lookup_revalidate_enter(dir, dentry, flags); - error = nfs_lookup_revalidate_dentry(dir, dentry, inode); - trace_nfs_lookup_revalidate_exit(dir, dentry, flags, error); - return error; + return nfs_lookup_revalidate_dentry(dir, dentry, inode, flags); out_valid: return nfs_lookup_revalidate_done(dir, dentry, inode, 1); out_bad: @@ -1615,6 +1782,8 @@ __nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags, int ret; if (flags & LOOKUP_RCU) { + if (dentry->d_fsdata == NFS_FSDATA_BLOCKED) + return -ECHILD; parent = READ_ONCE(dentry->d_parent); dir = d_inode_rcu(parent); if (!dir) @@ -1623,6 +1792,9 @@ __nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags, if (parent != READ_ONCE(dentry->d_parent)) return -ECHILD; } else { + /* Wait for unlink to complete */ + wait_var_event(&dentry->d_fsdata, + dentry->d_fsdata != NFS_FSDATA_BLOCKED); parent = dget_parent(dentry); ret = reval(d_inode(parent), dentry, flags); dput(parent); @@ -1776,8 +1948,11 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in dir_verifier = nfs_save_change_attribute(dir); trace_nfs_lookup_enter(dir, dentry, flags); error = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr); - if (error == -ENOENT) + if (error == -ENOENT) { + if (nfs_server_capable(dir, NFS_CAP_CASE_INSENSITIVE)) + dir_verifier = inode_peek_iversion_raw(dir); goto no_entry; + } if (error < 0) { res = ERR_PTR(error); goto out; @@ -1788,7 +1963,7 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in goto out; /* Notify readdir to use READDIRPLUS */ - nfs_force_use_readdirplus(dir); + nfs_lookup_advise_force_readdirplus(dir, flags); no_entry: res = d_splice_alias(inode, dentry); @@ -1806,6 +1981,14 @@ out: } EXPORT_SYMBOL_GPL(nfs_lookup); +void nfs_d_prune_case_insensitive_aliases(struct inode *inode) +{ + /* Case insensitive server? Revalidate dentries */ + if (inode && nfs_server_capable(inode, NFS_CAP_CASE_INSENSITIVE)) + d_prune_aliases(inode); +} +EXPORT_SYMBOL_GPL(nfs_d_prune_case_insensitive_aliases); + #if IS_ENABLED(CONFIG_NFS_V4) static int nfs4_lookup_revalidate(struct dentry *, unsigned int); @@ -1819,16 +2002,6 @@ const struct dentry_operations nfs4_dentry_operations = { }; EXPORT_SYMBOL_GPL(nfs4_dentry_operations); -static fmode_t flags_to_mode(int flags) -{ - fmode_t res = (__force fmode_t)flags & FMODE_EXEC; - if ((flags & O_ACCMODE) != O_WRONLY) - res |= FMODE_READ; - if ((flags & O_ACCMODE) != O_RDONLY) - res |= FMODE_WRITE; - return res; -} - static struct nfs_open_context *create_nfs_open_context(struct dentry *dentry, int open_flags, struct file *filp) { return alloc_nfs_open_context(dentry, flags_to_mode(open_flags), filp); @@ -1849,7 +2022,7 @@ static int nfs_finish_open(struct nfs_open_context *ctx, err = finish_open(file, dentry, do_open); if (err) goto out; - if (S_ISREG(file->f_path.dentry->d_inode->i_mode)) + if (S_ISREG(file_inode(file)->i_mode)) nfs_file_set_open_context(file, ctx); else err = -EOPENSTALE; @@ -1867,6 +2040,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry, struct iattr attr = { .ia_valid = ATTR_OPEN }; struct inode *inode; unsigned int lookup_flags = 0; + unsigned long dir_verifier; bool switched = false; int created = 0; int err; @@ -1940,7 +2114,11 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry, switch (err) { case -ENOENT: d_splice_alias(NULL, dentry); - nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); + if (nfs_server_capable(dir, NFS_CAP_CASE_INSENSITIVE)) + dir_verifier = inode_peek_iversion_raw(dir); + else + dir_verifier = nfs_save_change_attribute(dir); + nfs_set_verifier(dentry, dir_verifier); break; case -EISDIR: case -ENOTDIR: @@ -1955,6 +2133,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry, } goto out; } + file->f_mode |= FMODE_CAN_ODIRECT; err = nfs_finish_open(ctx, ctx->dentry, file, open_flags); trace_nfs_atomic_open_exit(dir, ctx, open_flags, err); @@ -1968,6 +2147,24 @@ out: no_open: res = nfs_lookup(dir, dentry, lookup_flags); + if (!res) { + inode = d_inode(dentry); + if ((lookup_flags & LOOKUP_DIRECTORY) && inode && + !(S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))) + res = ERR_PTR(-ENOTDIR); + else if (inode && S_ISREG(inode->i_mode)) + res = ERR_PTR(-EOPENSTALE); + } else if (!IS_ERR(res)) { + inode = d_inode(res); + if ((lookup_flags & LOOKUP_DIRECTORY) && inode && + !(S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))) { + dput(res); + res = ERR_PTR(-ENOTDIR); + } else if (inode && S_ISREG(inode->i_mode)) { + dput(res); + res = ERR_PTR(-EOPENSTALE); + } + } if (switched) { d_lookup_done(dentry); if (!res) @@ -2020,7 +2217,7 @@ nfs4_do_lookup_revalidate(struct inode *dir, struct dentry *dentry, reval_dentry: if (flags & LOOKUP_RCU) return -ECHILD; - return nfs_lookup_revalidate_dentry(dir, dentry, inode); + return nfs_lookup_revalidate_dentry(dir, dentry, inode, flags); full_reval: return nfs_do_lookup_revalidate(dir, dentry, flags); @@ -2185,9 +2382,12 @@ static void nfs_dentry_remove_handle_error(struct inode *dir, { switch (error) { case -ENOENT: - d_delete(dentry); - fallthrough; + if (d_really_is_positive(dentry)) + d_delete(dentry); + nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); + break; case 0: + nfs_d_prune_case_insensitive_aliases(d_inode(dentry)); nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); } } @@ -2264,29 +2464,40 @@ out: int nfs_unlink(struct inode *dir, struct dentry *dentry) { int error; - int need_rehash = 0; dfprintk(VFS, "NFS: unlink(%s/%lu, %pd)\n", dir->i_sb->s_id, dir->i_ino, dentry); trace_nfs_unlink_enter(dir, dentry); spin_lock(&dentry->d_lock); - if (d_count(dentry) > 1) { + if (d_count(dentry) > 1 && !test_bit(NFS_INO_PRESERVE_UNLINKED, + &NFS_I(d_inode(dentry))->flags)) { spin_unlock(&dentry->d_lock); /* Start asynchronous writeout of the inode */ write_inode_now(d_inode(dentry), 0); error = nfs_sillyrename(dir, dentry); goto out; } - if (!d_unhashed(dentry)) { - __d_drop(dentry); - need_rehash = 1; + /* We must prevent any concurrent open until the unlink + * completes. ->d_revalidate will wait for ->d_fsdata + * to clear. We set it here to ensure no lookup succeeds until + * the unlink is complete on the server. + */ + error = -ETXTBSY; + if (WARN_ON(dentry->d_flags & DCACHE_NFSFS_RENAMED) || + WARN_ON(dentry->d_fsdata == NFS_FSDATA_BLOCKED)) { + spin_unlock(&dentry->d_lock); + goto out; } + /* old devname */ + kfree(dentry->d_fsdata); + dentry->d_fsdata = NFS_FSDATA_BLOCKED; + spin_unlock(&dentry->d_lock); error = nfs_safe_remove(dentry); nfs_dentry_remove_handle_error(dir, dentry, error); - if (need_rehash) - d_rehash(dentry); + dentry->d_fsdata = NULL; + wake_up_var(&dentry->d_fsdata); out: trace_nfs_unlink_exit(dir, dentry, error); return error; @@ -2380,6 +2591,8 @@ nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) trace_nfs_link_enter(inode, dir, dentry); d_drop(dentry); + if (S_ISREG(inode->i_mode)) + nfs_sync_inode(inode); error = NFS_PROTO(dir)->link(inode, dir, &dentry->d_name); if (error == 0) { nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); @@ -2391,6 +2604,15 @@ nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) } EXPORT_SYMBOL_GPL(nfs_link); +static void +nfs_unblock_rename(struct rpc_task *task, struct nfs_renamedata *data) +{ + struct dentry *new_dentry = data->new_dentry; + + new_dentry->d_fsdata = NULL; + wake_up_var(&new_dentry->d_fsdata); +} + /* * RENAME * FIXME: Some nfsds, like the Linux user space nfsd, may generate a @@ -2421,8 +2643,9 @@ int nfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, { struct inode *old_inode = d_inode(old_dentry); struct inode *new_inode = d_inode(new_dentry); - struct dentry *dentry = NULL, *rehash = NULL; + struct dentry *dentry = NULL; struct rpc_task *task; + bool must_unblock = false; int error = -EBUSY; if (flags) @@ -2440,18 +2663,27 @@ int nfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, * the new target. */ if (new_inode && !S_ISDIR(new_inode->i_mode)) { - /* - * To prevent any new references to the target during the - * rename, we unhash the dentry in advance. + /* We must prevent any concurrent open until the unlink + * completes. ->d_revalidate will wait for ->d_fsdata + * to clear. We set it here to ensure no lookup succeeds until + * the unlink is complete on the server. */ - if (!d_unhashed(new_dentry)) { - d_drop(new_dentry); - rehash = new_dentry; + error = -ETXTBSY; + if (WARN_ON(new_dentry->d_flags & DCACHE_NFSFS_RENAMED) || + WARN_ON(new_dentry->d_fsdata == NFS_FSDATA_BLOCKED)) + goto out; + if (new_dentry->d_fsdata) { + /* old devname */ + kfree(new_dentry->d_fsdata); + new_dentry->d_fsdata = NULL; } + spin_lock(&new_dentry->d_lock); if (d_count(new_dentry) > 2) { int err; + spin_unlock(&new_dentry->d_lock); + /* copy the target dentry's name */ dentry = d_alloc(new_dentry->d_parent, &new_dentry->d_name); @@ -2464,12 +2696,19 @@ int nfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, goto out; new_dentry = dentry; - rehash = NULL; new_inode = NULL; + } else { + new_dentry->d_fsdata = NFS_FSDATA_BLOCKED; + must_unblock = true; + spin_unlock(&new_dentry->d_lock); } + } - task = nfs_async_rename(old_dir, new_dir, old_dentry, new_dentry, NULL); + if (S_ISREG(old_inode->i_mode)) + nfs_sync_inode(old_inode); + task = nfs_async_rename(old_dir, new_dir, old_dentry, new_dentry, + must_unblock ? nfs_unblock_rename : NULL); if (IS_ERR(task)) { error = PTR_ERR(task); goto out; @@ -2493,8 +2732,6 @@ int nfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, spin_unlock(&old_inode->i_lock); } out: - if (rehash) - d_rehash(rehash); trace_nfs_rename_exit(old_dir, old_dentry, new_dir, new_dentry, error); if (!error) { @@ -2529,7 +2766,7 @@ MODULE_PARM_DESC(nfs_access_max_cachesize, "NFS access maximum total cache lengt static void nfs_access_free_entry(struct nfs_access_entry *entry) { - put_cred(entry->cred); + put_group_info(entry->group_info); kfree_rcu(entry, rcu_head); smp_mb__before_atomic(); atomic_long_dec(&nfs_access_nr_entries); @@ -2655,6 +2892,43 @@ void nfs_access_zap_cache(struct inode *inode) } EXPORT_SYMBOL_GPL(nfs_access_zap_cache); +static int access_cmp(const struct cred *a, const struct nfs_access_entry *b) +{ + struct group_info *ga, *gb; + int g; + + if (uid_lt(a->fsuid, b->fsuid)) + return -1; + if (uid_gt(a->fsuid, b->fsuid)) + return 1; + + if (gid_lt(a->fsgid, b->fsgid)) + return -1; + if (gid_gt(a->fsgid, b->fsgid)) + return 1; + + ga = a->group_info; + gb = b->group_info; + if (ga == gb) + return 0; + if (ga == NULL) + return -1; + if (gb == NULL) + return 1; + if (ga->ngroups < gb->ngroups) + return -1; + if (ga->ngroups > gb->ngroups) + return 1; + + for (g = 0; g < ga->ngroups; g++) { + if (gid_lt(ga->gid[g], gb->gid[g])) + return -1; + if (gid_gt(ga->gid[g], gb->gid[g])) + return 1; + } + return 0; +} + static struct nfs_access_entry *nfs_access_search_rbtree(struct inode *inode, const struct cred *cred) { struct rb_node *n = NFS_I(inode)->access_cache.rb_node; @@ -2662,7 +2936,7 @@ static struct nfs_access_entry *nfs_access_search_rbtree(struct inode *inode, co while (n != NULL) { struct nfs_access_entry *entry = rb_entry(n, struct nfs_access_entry, rb_node); - int cmp = cred_fscmp(cred, entry->cred); + int cmp = access_cmp(cred, entry); if (cmp < 0) n = n->rb_left; @@ -2674,7 +2948,7 @@ static struct nfs_access_entry *nfs_access_search_rbtree(struct inode *inode, co return NULL; } -static int nfs_access_get_cached_locked(struct inode *inode, const struct cred *cred, struct nfs_access_entry *res, bool may_block) +static int nfs_access_get_cached_locked(struct inode *inode, const struct cred *cred, u32 *mask, bool may_block) { struct nfs_inode *nfsi = NFS_I(inode); struct nfs_access_entry *cache; @@ -2704,8 +2978,7 @@ static int nfs_access_get_cached_locked(struct inode *inode, const struct cred * spin_lock(&inode->i_lock); retry = false; } - res->cred = cache->cred; - res->mask = cache->mask; + *mask = cache->mask; list_move_tail(&cache->lru, &nfsi->access_cache_entry_lru); err = 0; out: @@ -2717,7 +2990,7 @@ out_zap: return -ENOENT; } -static int nfs_access_get_cached_rcu(struct inode *inode, const struct cred *cred, struct nfs_access_entry *res) +static int nfs_access_get_cached_rcu(struct inode *inode, const struct cred *cred, u32 *mask) { /* Only check the most recently returned cache entry, * but do it without locking. @@ -2733,35 +3006,36 @@ static int nfs_access_get_cached_rcu(struct inode *inode, const struct cred *cre lh = rcu_dereference(list_tail_rcu(&nfsi->access_cache_entry_lru)); cache = list_entry(lh, struct nfs_access_entry, lru); if (lh == &nfsi->access_cache_entry_lru || - cred_fscmp(cred, cache->cred) != 0) + access_cmp(cred, cache) != 0) cache = NULL; if (cache == NULL) goto out; if (nfs_check_cache_invalid(inode, NFS_INO_INVALID_ACCESS)) goto out; - res->cred = cache->cred; - res->mask = cache->mask; + *mask = cache->mask; err = 0; out: rcu_read_unlock(); return err; } -int nfs_access_get_cached(struct inode *inode, const struct cred *cred, struct -nfs_access_entry *res, bool may_block) +int nfs_access_get_cached(struct inode *inode, const struct cred *cred, + u32 *mask, bool may_block) { int status; - status = nfs_access_get_cached_rcu(inode, cred, res); + status = nfs_access_get_cached_rcu(inode, cred, mask); if (status != 0) - status = nfs_access_get_cached_locked(inode, cred, res, + status = nfs_access_get_cached_locked(inode, cred, mask, may_block); return status; } EXPORT_SYMBOL_GPL(nfs_access_get_cached); -static void nfs_access_add_rbtree(struct inode *inode, struct nfs_access_entry *set) +static void nfs_access_add_rbtree(struct inode *inode, + struct nfs_access_entry *set, + const struct cred *cred) { struct nfs_inode *nfsi = NFS_I(inode); struct rb_root *root_node = &nfsi->access_cache; @@ -2774,7 +3048,7 @@ static void nfs_access_add_rbtree(struct inode *inode, struct nfs_access_entry * while (*p != NULL) { parent = *p; entry = rb_entry(parent, struct nfs_access_entry, rb_node); - cmp = cred_fscmp(set->cred, entry->cred); + cmp = access_cmp(cred, entry); if (cmp < 0) p = &parent->rb_left; @@ -2796,13 +3070,16 @@ found: nfs_access_free_entry(entry); } -void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set) +void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set, + const struct cred *cred) { struct nfs_access_entry *cache = kmalloc(sizeof(*cache), GFP_KERNEL); if (cache == NULL) return; RB_CLEAR_NODE(&cache->rb_node); - cache->cred = get_cred(set->cred); + cache->fsuid = cred->fsuid; + cache->fsgid = cred->fsgid; + cache->group_info = get_group_info(cred->group_info); cache->mask = set->mask; /* The above field assignments must be visible @@ -2810,7 +3087,7 @@ void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set) * use rcu_assign_pointer, so just force the memory barrier. */ smp_wmb(); - nfs_access_add_rbtree(inode, cache); + nfs_access_add_rbtree(inode, cache, cred); /* Update accounting */ smp_mb__before_atomic(); @@ -2875,7 +3152,7 @@ static int nfs_do_access(struct inode *inode, const struct cred *cred, int mask) trace_nfs_access_enter(inode); - status = nfs_access_get_cached(inode, cred, &cache, may_block); + status = nfs_access_get_cached(inode, cred, &cache.mask, may_block); if (status == 0) goto out_cached; @@ -2886,17 +3163,13 @@ static int nfs_do_access(struct inode *inode, const struct cred *cred, int mask) /* * Determine which access bits we want to ask for... */ - cache.mask = NFS_ACCESS_READ | NFS_ACCESS_MODIFY | NFS_ACCESS_EXTEND; - if (nfs_server_capable(inode, NFS_CAP_XATTR)) { - cache.mask |= NFS_ACCESS_XAREAD | NFS_ACCESS_XAWRITE | - NFS_ACCESS_XALIST; - } + cache.mask = NFS_ACCESS_READ | NFS_ACCESS_MODIFY | NFS_ACCESS_EXTEND | + nfs_access_xattr_mask(NFS_SERVER(inode)); if (S_ISDIR(inode->i_mode)) cache.mask |= NFS_ACCESS_DELETE | NFS_ACCESS_LOOKUP; else cache.mask |= NFS_ACCESS_EXECUTE; - cache.cred = cred; - status = NFS_PROTO(inode)->access(inode, &cache); + status = NFS_PROTO(inode)->access(inode, &cache, cred); if (status != 0) { if (status == -ESTALE) { if (!S_ISDIR(inode->i_mode)) @@ -2906,7 +3179,7 @@ static int nfs_do_access(struct inode *inode, const struct cred *cred, int mask) } goto out; } - nfs_access_add_cache(inode, &cache); + nfs_access_add_cache(inode, &cache, cred); out_cached: cache_mask = nfs_access_calc_mask(cache.mask, inode->i_mode); if ((mask & ~cache_mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) != 0) diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 9cff8709c80a..1707f46b1335 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -59,44 +59,13 @@ #include "internal.h" #include "iostat.h" #include "pnfs.h" +#include "fscache.h" +#include "nfstrace.h" #define NFSDBG_FACILITY NFSDBG_VFS static struct kmem_cache *nfs_direct_cachep; -struct nfs_direct_req { - struct kref kref; /* release manager */ - - /* I/O parameters */ - struct nfs_open_context *ctx; /* file open context info */ - struct nfs_lock_context *l_ctx; /* Lock context info */ - struct kiocb * iocb; /* controlling i/o request */ - struct inode * inode; /* target file of i/o */ - - /* completion state */ - atomic_t io_count; /* i/os we're waiting for */ - spinlock_t lock; /* protect completion state */ - - loff_t io_start; /* Start offset for I/O */ - ssize_t count, /* bytes actually processed */ - max_count, /* max expected count */ - bytes_left, /* bytes left to be sent */ - error; /* any reported error */ - struct completion completion; /* wait for i/o completion */ - - /* commit state */ - struct nfs_mds_commit_info mds_cinfo; /* Storage for cinfo */ - struct pnfs_ds_commit_info ds_cinfo; /* Storage for cinfo */ - struct work_struct work; - int flags; - /* for write */ -#define NFS_ODIRECT_DO_COMMIT (1) /* an unstable reply was received */ -#define NFS_ODIRECT_RESCHED_WRITES (2) /* write verification failed */ - /* for read */ -#define NFS_ODIRECT_SHOULD_DIRTY (3) /* dirty user-space page after read */ -#define NFS_ODIRECT_DONE INT_MAX /* write verification failed */ -}; - static const struct nfs_pgio_completion_ops nfs_direct_write_completion_ops; static const struct nfs_commit_completion_ops nfs_direct_commit_completion_ops; static void nfs_direct_write_complete(struct nfs_direct_req *dreq); @@ -152,28 +121,25 @@ nfs_direct_count_bytes(struct nfs_direct_req *dreq, } /** - * nfs_direct_IO - NFS address space operation for direct I/O + * nfs_swap_rw - NFS address space operation for swap I/O * @iocb: target I/O control block * @iter: I/O buffer * - * The presence of this routine in the address space ops vector means - * the NFS client supports direct I/O. However, for most direct IO, we - * shunt off direct read and write requests before the VFS gets them, - * so this method is only ever called for swap. + * Perform IO to the swap-file. This is much like direct IO. */ -ssize_t nfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) +int nfs_swap_rw(struct kiocb *iocb, struct iov_iter *iter) { - struct inode *inode = iocb->ki_filp->f_mapping->host; - - /* we only support swap file calling nfs_direct_IO */ - if (!IS_SWAPFILE(inode)) - return 0; + ssize_t ret; VM_BUG_ON(iov_iter_count(iter) != PAGE_SIZE); if (iov_iter_rw(iter) == READ) - return nfs_file_direct_read(iocb, iter); - return nfs_file_direct_write(iocb, iter); + ret = nfs_file_direct_read(iocb, iter, true); + else + ret = nfs_file_direct_write(iocb, iter, true); + if (ret < 0) + return ret; + return 0; } static void nfs_direct_release_pages(struct page **pages, unsigned int npages) @@ -366,13 +332,12 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, size_t pgbase; unsigned npages, i; - result = iov_iter_get_pages_alloc(iter, &pagevec, + result = iov_iter_get_pages_alloc2(iter, &pagevec, rsize, &pgbase); if (result < 0) break; bytes = result; - iov_iter_advance(iter, bytes); npages = (result + pgbase + PAGE_SIZE - 1) / PAGE_SIZE; for (i = 0; i < npages; i++) { struct nfs_page *req; @@ -424,6 +389,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, * nfs_file_direct_read - file direct read operation for NFS files * @iocb: target I/O control block * @iter: vector of user buffers into which to read data + * @swap: flag indicating this is swap IO, not O_DIRECT IO * * We use this function for direct reads instead of calling * generic_file_aio_read() in order to avoid gfar's check to see if @@ -439,7 +405,8 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, * client must read the updated atime from the server back into its * cache. */ -ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter) +ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter, + bool swap) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; @@ -478,15 +445,17 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter) if (!is_sync_kiocb(iocb)) dreq->iocb = iocb; - if (iter_is_iovec(iter)) + if (user_backed_iter(iter)) dreq->flags = NFS_ODIRECT_SHOULD_DIRTY; - nfs_start_io_direct(inode); + if (!swap) + nfs_start_io_direct(inode); NFS_I(inode)->read_io += count; requested = nfs_direct_read_schedule_iovec(dreq, iter, iocb->ki_pos); - nfs_end_io_direct(inode); + if (!swap) + nfs_end_io_direct(inode); if (requested > 0) { result = nfs_direct_wait(dreq); @@ -593,14 +562,17 @@ static void nfs_direct_commit_complete(struct nfs_commit_data *data) struct nfs_page *req; int status = data->task.tk_status; + trace_nfs_direct_commit_complete(dreq); + if (status < 0) { /* Errors in commit are fatal */ dreq->error = status; dreq->max_count = 0; dreq->count = 0; dreq->flags = NFS_ODIRECT_DONE; - } else if (dreq->flags == NFS_ODIRECT_DONE) + } else { status = dreq->error; + } nfs_init_cinfo_from_dreq(&cinfo, dreq); @@ -629,6 +601,8 @@ static void nfs_direct_resched_write(struct nfs_commit_info *cinfo, { struct nfs_direct_req *dreq = cinfo->dreq; + trace_nfs_direct_resched_write(dreq); + spin_lock(&dreq->lock); if (dreq->flags != NFS_ODIRECT_DONE) dreq->flags = NFS_ODIRECT_RESCHED_WRITES; @@ -693,6 +667,7 @@ static void nfs_direct_write_schedule_work(struct work_struct *work) static void nfs_direct_write_complete(struct nfs_direct_req *dreq) { + trace_nfs_direct_write_complete(dreq); queue_work(nfsiod_workqueue, &dreq->work); /* Calls nfs_direct_write_schedule_work */ } @@ -703,6 +678,8 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr) struct nfs_page *req = nfs_list_entry(hdr->pages.next); int flags = NFS_ODIRECT_DONE; + trace_nfs_direct_write_completion(dreq); + nfs_init_cinfo_from_dreq(&cinfo, dreq); spin_lock(&dreq->lock); @@ -712,7 +689,7 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr) } nfs_direct_count_bytes(dreq, hdr); - if (hdr->good_bytes != 0 && nfs_write_need_commit(hdr)) { + if (test_bit(NFS_IOHDR_UNSTABLE_WRITES, &hdr->flags)) { if (!dreq->flags) dreq->flags = NFS_ODIRECT_DO_COMMIT; flags = dreq->flags; @@ -757,6 +734,8 @@ static void nfs_direct_write_reschedule_io(struct nfs_pgio_header *hdr) { struct nfs_direct_req *dreq = hdr->dreq; + trace_nfs_direct_write_reschedule_io(dreq); + spin_lock(&dreq->lock); if (dreq->error == 0) { dreq->flags = NFS_ODIRECT_RESCHED_WRITES; @@ -789,7 +768,7 @@ static const struct nfs_pgio_completion_ops nfs_direct_write_completion_ops = { */ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, struct iov_iter *iter, - loff_t pos) + loff_t pos, int ioflags) { struct nfs_pageio_descriptor desc; struct inode *inode = dreq->inode; @@ -797,7 +776,9 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, size_t requested_bytes = 0; size_t wsize = max_t(size_t, NFS_SERVER(inode)->wsize, PAGE_SIZE); - nfs_pageio_init_write(&desc, inode, FLUSH_COND_STABLE, false, + trace_nfs_direct_write_schedule_iovec(dreq); + + nfs_pageio_init_write(&desc, inode, ioflags, false, &nfs_direct_write_completion_ops); desc.pg_dreq = dreq; get_dreq(dreq); @@ -810,13 +791,12 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, size_t pgbase; unsigned npages, i; - result = iov_iter_get_pages_alloc(iter, &pagevec, + result = iov_iter_get_pages_alloc2(iter, &pagevec, wsize, &pgbase); if (result < 0) break; bytes = result; - iov_iter_advance(iter, bytes); npages = (result + pgbase + PAGE_SIZE - 1) / PAGE_SIZE; for (i = 0; i < npages; i++) { struct nfs_page *req; @@ -875,6 +855,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, * nfs_file_direct_write - file direct write operation for NFS files * @iocb: target I/O control block * @iter: vector of user buffers from which to write data + * @swap: flag indicating this is swap IO, not O_DIRECT IO * * We use this function for direct writes instead of calling * generic_file_aio_write() in order to avoid taking the inode @@ -891,7 +872,8 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, * Note that O_APPEND is not supported for NFS direct writes, as there * is no atomic O_APPEND write facility in the NFS protocol. */ -ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter) +ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter, + bool swap) { ssize_t result, requested; size_t count; @@ -905,7 +887,11 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter) dfprintk(FILE, "NFS: direct write(%pD2, %zd@%Ld)\n", file, iov_iter_count(iter), (long long) iocb->ki_pos); - result = generic_write_checks(iocb, iter); + if (swap) + /* bypass generic checks */ + result = iov_iter_count(iter); + else + result = generic_write_checks(iocb, iter); if (result <= 0) return result; count = result; @@ -936,16 +922,22 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter) dreq->iocb = iocb; pnfs_init_ds_commit_info_ops(&dreq->ds_cinfo, inode); - nfs_start_io_direct(inode); + if (swap) { + requested = nfs_direct_write_schedule_iovec(dreq, iter, pos, + FLUSH_STABLE); + } else { + nfs_start_io_direct(inode); - requested = nfs_direct_write_schedule_iovec(dreq, iter, pos); + requested = nfs_direct_write_schedule_iovec(dreq, iter, pos, + FLUSH_COND_STABLE); - if (mapping->nrpages) { - invalidate_inode_pages2_range(mapping, - pos >> PAGE_SHIFT, end); - } + if (mapping->nrpages) { + invalidate_inode_pages2_range(mapping, + pos >> PAGE_SHIFT, end); + } - nfs_end_io_direct(inode); + nfs_end_io_direct(inode); + } if (requested > 0) { result = nfs_direct_wait(dreq); @@ -959,6 +951,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter) } else { result = requested; } + nfs_fscache_invalidate(inode, FSCACHE_INVAL_DIO_WRITE); out_release: nfs_direct_req_release(dreq); out: diff --git a/fs/nfs/dns_resolve.c b/fs/nfs/dns_resolve.c index e87d500ad95a..6603b5cee029 100644 --- a/fs/nfs/dns_resolve.c +++ b/fs/nfs/dns_resolve.c @@ -16,8 +16,9 @@ #include "dns_resolve.h" ssize_t nfs_dns_resolve_name(struct net *net, char *name, size_t namelen, - struct sockaddr *sa, size_t salen) + struct sockaddr_storage *ss, size_t salen) { + struct sockaddr *sa = (struct sockaddr *)ss; ssize_t ret; char *ip_addr = NULL; int ip_len; @@ -341,7 +342,7 @@ out: } ssize_t nfs_dns_resolve_name(struct net *net, char *name, - size_t namelen, struct sockaddr *sa, size_t salen) + size_t namelen, struct sockaddr_storage *ss, size_t salen) { struct nfs_dns_ent key = { .hostname = name, @@ -354,7 +355,7 @@ ssize_t nfs_dns_resolve_name(struct net *net, char *name, ret = do_cache_lookup_wait(nn->nfs_dns_resolve, &key, &item); if (ret == 0) { if (salen >= item->addrlen) { - memcpy(sa, &item->addr, item->addrlen); + memcpy(ss, &item->addr, item->addrlen); ret = item->addrlen; } else ret = -EOVERFLOW; diff --git a/fs/nfs/dns_resolve.h b/fs/nfs/dns_resolve.h index 576ff4b54c82..fe3b172c4de1 100644 --- a/fs/nfs/dns_resolve.h +++ b/fs/nfs/dns_resolve.h @@ -32,6 +32,6 @@ extern void nfs_dns_resolver_cache_destroy(struct net *net); #endif extern ssize_t nfs_dns_resolve_name(struct net *net, char *name, - size_t namelen, struct sockaddr *sa, size_t salen); + size_t namelen, struct sockaddr_storage *sa, size_t salen); #endif diff --git a/fs/nfs/export.c b/fs/nfs/export.c index 171c424cb6d5..01596f2d0a1e 100644 --- a/fs/nfs/export.c +++ b/fs/nfs/export.c @@ -158,5 +158,5 @@ const struct export_operations nfs_export_ops = { .fetch_iversion = nfs_fetch_iversion, .flags = EXPORT_OP_NOWCC|EXPORT_OP_NOSUBTREECHK| EXPORT_OP_CLOSE_BEFORE_UNLINK|EXPORT_OP_REMOTE_FS| - EXPORT_OP_NOATOMIC_ATTR|EXPORT_OP_SYNC_LOCKS, + EXPORT_OP_NOATOMIC_ATTR, }; diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 24e7dccce355..d8ec889a4b3f 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -44,11 +44,6 @@ static const struct vm_operations_struct nfs_file_vm_ops; -/* Hack for future NFS swap support */ -#ifndef IS_SWAPFILE -# define IS_SWAPFILE(inode) (0) -#endif - int nfs_check_flags(int flags) { if ((flags & (O_APPEND | O_DIRECT)) == (O_APPEND | O_DIRECT)) @@ -74,6 +69,8 @@ nfs_file_open(struct inode *inode, struct file *filp) return res; res = nfs_open(inode, filp); + if (res == 0) + filp->f_mode |= FMODE_CAN_ODIRECT; return res; } @@ -84,6 +81,7 @@ nfs_file_release(struct inode *inode, struct file *filp) nfs_inc_stats(inode, NFSIOS_VFSRELEASE); nfs_file_clear_open_context(filp); + nfs_fscache_release_file(inode, filp); return 0; } EXPORT_SYMBOL_GPL(nfs_file_release); @@ -161,7 +159,7 @@ nfs_file_read(struct kiocb *iocb, struct iov_iter *to) ssize_t result; if (iocb->ki_flags & IOCB_DIRECT) - return nfs_file_direct_read(iocb, to); + return nfs_file_direct_read(iocb, to, false); dprintk("NFS: read(%pD2, %zu@%lu)\n", iocb->ki_filp, @@ -208,22 +206,25 @@ static int nfs_file_fsync_commit(struct file *file, int datasync) { struct inode *inode = file_inode(file); - int ret; + int ret, ret2; dprintk("NFS: fsync file(%pD2) datasync %d\n", file, datasync); nfs_inc_stats(inode, NFSIOS_VFSFSYNC); ret = nfs_commit_inode(inode, FLUSH_SYNC); - if (ret < 0) - return ret; - return file_check_and_advance_wb_err(file); + ret2 = file_check_and_advance_wb_err(file); + if (ret2 < 0) + return ret2; + return ret; } int nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) { - struct nfs_open_context *ctx = nfs_file_open_context(file); struct inode *inode = file_inode(file); + struct nfs_inode *nfsi = NFS_I(inode); + long save_nredirtied = atomic_long_read(&nfsi->redirtied_pages); + long nredirtied; int ret; trace_nfs_fsync_enter(inode); @@ -238,15 +239,10 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) ret = pnfs_sync_inode(inode, !!datasync); if (ret != 0) break; - if (!test_and_clear_bit(NFS_CONTEXT_RESEND_WRITES, &ctx->flags)) + nredirtied = atomic_long_read(&nfsi->redirtied_pages); + if (nredirtied == save_nredirtied) break; - /* - * If nfs_file_fsync_commit detected a server reboot, then - * resend all dirty pages that might have been covered by - * the NFS_CONTEXT_RESEND_WRITES flag - */ - start = 0; - end = LLONG_MAX; + save_nredirtied = nredirtied; } trace_nfs_fsync_exit(inode, ret); @@ -317,7 +313,7 @@ static bool nfs_want_read_modify_write(struct file *file, struct page *page, * increment the page use counts until he is done with the page. */ static int nfs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata) { int ret; @@ -329,7 +325,7 @@ static int nfs_write_begin(struct file *file, struct address_space *mapping, file, mapping->host->i_ino, len, (long long) pos); start: - page = grab_cache_page_write_begin(mapping, index, flags); + page = grab_cache_page_write_begin(mapping, index); if (!page) return -ENOMEM; *pagep = page; @@ -341,7 +337,7 @@ start: } else if (!once_thru && nfs_want_read_modify_write(file, page, pos, len)) { once_thru = 1; - ret = nfs_readpage(file, page); + ret = nfs_read_folio(file, page_folio(page)); put_page(page); if (!ret) goto start; @@ -389,11 +385,8 @@ static int nfs_write_end(struct file *file, struct address_space *mapping, return status; NFS_I(mapping->host)->write_io += copied; - if (nfs_ctx_key_to_expire(ctx, mapping->host)) { - status = nfs_wb_all(mapping->host); - if (status < 0) - return status; - } + if (nfs_ctx_key_to_expire(ctx, mapping->host)) + nfs_wb_all(mapping->host); return copied; } @@ -405,49 +398,45 @@ static int nfs_write_end(struct file *file, struct address_space *mapping, * - Called if either PG_private or PG_fscache is set on the page * - Caller holds page lock */ -static void nfs_invalidate_page(struct page *page, unsigned int offset, - unsigned int length) +static void nfs_invalidate_folio(struct folio *folio, size_t offset, + size_t length) { - dfprintk(PAGECACHE, "NFS: invalidate_page(%p, %u, %u)\n", - page, offset, length); + dfprintk(PAGECACHE, "NFS: invalidate_folio(%lu, %zu, %zu)\n", + folio->index, offset, length); - if (offset != 0 || length < PAGE_SIZE) + if (offset != 0 || length < folio_size(folio)) return; /* Cancel any unstarted writes on this page */ - nfs_wb_page_cancel(page_file_mapping(page)->host, page); - - nfs_fscache_invalidate_page(page, page->mapping->host); + nfs_wb_folio_cancel(folio->mapping->host, folio); + folio_wait_fscache(folio); } /* - * Attempt to release the private state associated with a page - * - Called if either PG_private or PG_fscache is set on the page - * - Caller holds page lock - * - Return true (may release page) or false (may not) + * Attempt to release the private state associated with a folio + * - Called if either private or fscache flags are set on the folio + * - Caller holds folio lock + * - Return true (may release folio) or false (may not) */ -static int nfs_release_page(struct page *page, gfp_t gfp) +static bool nfs_release_folio(struct folio *folio, gfp_t gfp) { - dfprintk(PAGECACHE, "NFS: release_page(%p)\n", page); + dfprintk(PAGECACHE, "NFS: release_folio(%p)\n", folio); - /* If PagePrivate() is set, then the page is not freeable */ - if (PagePrivate(page)) - return 0; - return nfs_fscache_release_page(page, gfp); + /* If the private flag is set, then the folio is not freeable */ + if (folio_test_private(folio)) + return false; + return nfs_fscache_release_folio(folio, gfp); } -static void nfs_check_dirty_writeback(struct page *page, +static void nfs_check_dirty_writeback(struct folio *folio, bool *dirty, bool *writeback) { struct nfs_inode *nfsi; - struct address_space *mapping = page_file_mapping(page); - - if (!mapping || PageSwapCache(page)) - return; + struct address_space *mapping = folio->mapping; /* - * Check if an unstable page is currently being committed and - * if so, have the VM treat it as if the page is under writeback - * so it will not block due to pages that will shortly be freeable. + * Check if an unstable folio is currently being committed and + * if so, have the VM treat it as if the folio is under writeback + * so it will not block due to folios that will shortly be freeable. */ nfsi = NFS_I(mapping->host); if (atomic_read(&nfsi->commit_info.rpcs_out)) { @@ -456,11 +445,11 @@ static void nfs_check_dirty_writeback(struct page *page, } /* - * If PagePrivate() is set, then the page is not freeable and as the - * inode is not being committed, it's not going to be cleaned in the - * near future so treat it as dirty + * If the private flag is set, then the folio is not freeable + * and as the inode is not being committed, it's not going to + * be cleaned in the near future so treat it as dirty */ - if (PagePrivate(page)) + if (folio_test_private(folio)) *dirty = true; } @@ -472,16 +461,15 @@ static void nfs_check_dirty_writeback(struct page *page, * - Caller holds page lock * - Return 0 if successful, -error otherwise */ -static int nfs_launder_page(struct page *page) +static int nfs_launder_folio(struct folio *folio) { - struct inode *inode = page_file_mapping(page)->host; - struct nfs_inode *nfsi = NFS_I(inode); + struct inode *inode = folio->mapping->host; - dfprintk(PAGECACHE, "NFS: launder_page(%ld, %llu)\n", - inode->i_ino, (long long)page_offset(page)); + dfprintk(PAGECACHE, "NFS: launder_folio(%ld, %llu)\n", + inode->i_ino, folio_pos(folio)); - nfs_fscache_wait_on_page_write(nfsi, page); - return nfs_wb_page(inode, page); + folio_wait_fscache(folio); + return nfs_wb_page(inode, &folio->page); } static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file, @@ -489,8 +477,10 @@ static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file, { unsigned long blocks; long long isize; - struct rpc_clnt *clnt = NFS_CLIENT(file->f_mapping->host); - struct inode *inode = file->f_mapping->host; + int ret; + struct inode *inode = file_inode(file); + struct rpc_clnt *clnt = NFS_CLIENT(inode); + struct nfs_client *cl = NFS_SERVER(inode)->nfs_client; spin_lock(&inode->i_lock); blocks = inode->i_blocks; @@ -501,37 +491,52 @@ static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file, return -EINVAL; } + ret = rpc_clnt_swap_activate(clnt); + if (ret) + return ret; + ret = add_swap_extent(sis, 0, sis->max, 0); + if (ret < 0) { + rpc_clnt_swap_deactivate(clnt); + return ret; + } + *span = sis->pages; - return rpc_clnt_swap_activate(clnt); + if (cl->rpc_ops->enable_swap) + cl->rpc_ops->enable_swap(inode); + + sis->flags |= SWP_FS_OPS; + return ret; } static void nfs_swap_deactivate(struct file *file) { - struct rpc_clnt *clnt = NFS_CLIENT(file->f_mapping->host); + struct inode *inode = file_inode(file); + struct rpc_clnt *clnt = NFS_CLIENT(inode); + struct nfs_client *cl = NFS_SERVER(inode)->nfs_client; rpc_clnt_swap_deactivate(clnt); + if (cl->rpc_ops->disable_swap) + cl->rpc_ops->disable_swap(file_inode(file)); } const struct address_space_operations nfs_file_aops = { - .readpage = nfs_readpage, - .readpages = nfs_readpages, - .set_page_dirty = __set_page_dirty_nobuffers, + .read_folio = nfs_read_folio, + .readahead = nfs_readahead, + .dirty_folio = filemap_dirty_folio, .writepage = nfs_writepage, .writepages = nfs_writepages, .write_begin = nfs_write_begin, .write_end = nfs_write_end, - .invalidatepage = nfs_invalidate_page, - .releasepage = nfs_release_page, - .direct_IO = nfs_direct_IO, -#ifdef CONFIG_MIGRATION - .migratepage = nfs_migrate_page, -#endif - .launder_page = nfs_launder_page, + .invalidate_folio = nfs_invalidate_folio, + .release_folio = nfs_release_folio, + .migrate_folio = nfs_migrate_folio, + .launder_folio = nfs_launder_folio, .is_dirty_writeback = nfs_check_dirty_writeback, .error_remove_page = generic_error_remove_page, .swap_activate = nfs_swap_activate, .swap_deactivate = nfs_swap_deactivate, + .swap_rw = nfs_swap_rw, }; /* @@ -555,10 +560,15 @@ static vm_fault_t nfs_vm_page_mkwrite(struct vm_fault *vmf) sb_start_pagefault(inode->i_sb); /* make sure the cache has finished storing the page */ - nfs_fscache_wait_on_page_write(NFS_I(inode), page); + if (PageFsCache(page) && + wait_on_page_fscache_killable(vmf->page) < 0) { + ret = VM_FAULT_RETRY; + goto out; + } wait_on_bit_action(&NFS_I(inode)->flags, NFS_INO_INVALIDATING, - nfs_wait_bit_killable, TASK_KILLABLE); + nfs_wait_bit_killable, + TASK_KILLABLE|TASK_FREEZABLE_UNSAFE); lock_page(page); mapping = page_file_mapping(page); @@ -590,18 +600,6 @@ static const struct vm_operations_struct nfs_file_vm_ops = { .page_mkwrite = nfs_vm_page_mkwrite, }; -static int nfs_need_check_write(struct file *filp, struct inode *inode, - int error) -{ - struct nfs_open_context *ctx; - - ctx = nfs_file_open_context(filp); - if (nfs_error_is_fatal_on_server(error) || - nfs_ctx_key_to_expire(ctx, inode)) - return 1; - return 0; -} - ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; @@ -616,7 +614,7 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from) return result; if (iocb->ki_flags & IOCB_DIRECT) - return nfs_file_direct_write(iocb, from); + return nfs_file_direct_write(iocb, from, false); dprintk("NFS: write(%pD2, %zu@%Ld)\n", file, iov_iter_count(from), (long long) iocb->ki_pos); @@ -629,7 +627,7 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from) if (iocb->ki_flags & IOCB_APPEND || iocb->ki_pos > i_size_read(inode)) { result = nfs_revalidate_file_size(inode, file); if (result) - goto out; + return result; } nfs_clear_invalid_mapping(file->f_mapping); @@ -639,7 +637,7 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from) result = generic_write_checks(iocb, from); if (result > 0) { current->backing_dev_info = inode_to_bdi(inode); - result = generic_perform_write(file, from, iocb->ki_pos); + result = generic_perform_write(iocb, from); current->backing_dev_info = NULL; } nfs_end_io_write(inode); @@ -648,6 +646,7 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from) written = result; iocb->ki_pos += written; + nfs_add_stats(inode, NFSIOS_NORMALWRITTENBYTES, written); if (mntflags & NFS_MOUNT_WRITE_EAGER) { result = filemap_fdatawrite_range(file->f_mapping, @@ -657,25 +656,28 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from) goto out; } if (mntflags & NFS_MOUNT_WRITE_WAIT) { - result = filemap_fdatawait_range(file->f_mapping, - iocb->ki_pos - written, - iocb->ki_pos - 1); - if (result < 0) - goto out; + filemap_fdatawait_range(file->f_mapping, + iocb->ki_pos - written, + iocb->ki_pos - 1); } result = generic_write_sync(iocb, written); if (result < 0) - goto out; + return result; +out: /* Return error values */ error = filemap_check_wb_err(file->f_mapping, since); - if (nfs_need_check_write(file, inode, error)) { - int err = nfs_wb_all(inode); - if (err < 0) - result = err; + switch (error) { + default: + break; + case -EDQUOT: + case -EFBIG: + case -ENOSPC: + nfs_wb_all(inode); + error = file_check_and_advance_wb_err(file); + if (error < 0) + result = error; } - nfs_add_stats(inode, NFSIOS_NORMALWRITTENBYTES, written); -out: return result; out_swapfile: diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index 9c96e3e5ed35..ad34a33b0737 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -181,6 +181,8 @@ static int filelayout_async_handle_error(struct rpc_task *task, case -EIO: case -ETIMEDOUT: case -EPIPE: + case -EPROTO: + case -ENODEV: dprintk("%s DS connection error %d\n", __func__, task->tk_status); nfs4_mark_deviceid_unavailable(devid); @@ -839,7 +841,12 @@ fl_pnfs_update_layout(struct inode *ino, lseg = pnfs_update_layout(ino, ctx, pos, count, iomode, strict_iomode, gfp_flags); - if (IS_ERR_OR_NULL(lseg)) + if (IS_ERR(lseg)) { + /* Fall back to MDS on recoverable errors */ + if (!nfs_error_is_fatal_on_server(PTR_ERR(lseg))) + lseg = NULL; + goto out; + } else if (!lseg) goto out; lo = NFS_I(ino)->layout; @@ -1075,7 +1082,7 @@ filelayout_setup_ds_info(struct pnfs_ds_commit_info *fl_cinfo, unsigned int size = (fl->stripe_type == STRIPE_SPARSE) ? fl->dsaddr->ds_num : fl->dsaddr->stripe_count; - new = pnfs_alloc_commit_array(size, GFP_NOIO); + new = pnfs_alloc_commit_array(size, nfs_io_gfp_mask()); if (new) { spin_lock(&inode->i_lock); array = pnfs_add_commit_array(fl_cinfo, new, lseg); diff --git a/fs/nfs/filelayout/filelayout.h b/fs/nfs/filelayout/filelayout.h index 79323b5dab0c..aed0748fd6ec 100644 --- a/fs/nfs/filelayout/filelayout.h +++ b/fs/nfs/filelayout/filelayout.h @@ -51,7 +51,7 @@ struct nfs4_file_layout_dsaddr { u32 stripe_count; u8 *stripe_indices; u32 ds_num; - struct nfs4_pnfs_ds *ds_list[1]; + struct nfs4_pnfs_ds *ds_list[]; }; struct nfs4_filelayout_segment { diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c index 86c3f7e69ec4..acf4b88889dc 100644 --- a/fs/nfs/filelayout/filelayoutdev.c +++ b/fs/nfs/filelayout/filelayoutdev.c @@ -136,9 +136,7 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, goto out_err_free_stripe_indices; } - dsaddr = kzalloc(sizeof(*dsaddr) + - (sizeof(struct nfs4_pnfs_ds *) * (num - 1)), - gfp_flags); + dsaddr = kzalloc(struct_size(dsaddr, ds_list, num), gfp_flags); if (!dsaddr) goto out_err_free_stripe_indices; diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index a553d59afa8b..1ec79ccf89ad 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -30,14 +30,20 @@ #define FF_LAYOUT_POLL_RETRY_MAX (15*HZ) #define FF_LAYOUTRETURN_MAXERR 20 +enum nfs4_ff_op_type { + NFS4_FF_OP_LAYOUTSTATS, + NFS4_FF_OP_LAYOUTRETURN, +}; + static unsigned short io_maxretrans; static const struct pnfs_commit_ops ff_layout_commit_ops; static void ff_layout_read_record_layoutstats_done(struct rpc_task *task, struct nfs_pgio_header *hdr); -static int ff_layout_mirror_prepare_stats(struct pnfs_layout_hdr *lo, +static int +ff_layout_mirror_prepare_stats(struct pnfs_layout_hdr *lo, struct nfs42_layoutstat_devinfo *devinfo, - int dev_limit); + int dev_limit, enum nfs4_ff_op_type type); static void ff_layout_encode_ff_layoutupdate(struct xdr_stream *xdr, const struct nfs42_layoutstat_devinfo *devinfo, struct nfs4_ff_layout_mirror *mirror); @@ -663,7 +669,7 @@ nfs4_ff_layout_stat_io_start_read(struct inode *inode, spin_unlock(&mirror->lock); if (report) - pnfs_report_layoutstat(inode, GFP_KERNEL); + pnfs_report_layoutstat(inode, nfs_io_gfp_mask()); } static void @@ -694,7 +700,7 @@ nfs4_ff_layout_stat_io_start_write(struct inode *inode, spin_unlock(&mirror->lock); if (report) - pnfs_report_layoutstat(inode, GFP_NOIO); + pnfs_report_layoutstat(inode, nfs_io_gfp_mask()); } static void @@ -806,13 +812,10 @@ ff_layout_pg_get_read(struct nfs_pageio_descriptor *pgio, bool strict_iomode) { pnfs_put_lseg(pgio->pg_lseg); - pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, - nfs_req_openctx(req), - req_offset(req), - req->wb_bytes, - IOMODE_READ, - strict_iomode, - GFP_KERNEL); + pgio->pg_lseg = + pnfs_update_layout(pgio->pg_inode, nfs_req_openctx(req), + req_offset(req), req->wb_bytes, IOMODE_READ, + strict_iomode, nfs_io_gfp_mask()); if (IS_ERR(pgio->pg_lseg)) { pgio->pg_error = PTR_ERR(pgio->pg_lseg); pgio->pg_lseg = NULL; @@ -894,13 +897,10 @@ ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio, retry: ff_layout_pg_check_layout(pgio, req); if (!pgio->pg_lseg) { - pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, - nfs_req_openctx(req), - req_offset(req), - req->wb_bytes, - IOMODE_RW, - false, - GFP_NOFS); + pgio->pg_lseg = + pnfs_update_layout(pgio->pg_inode, nfs_req_openctx(req), + req_offset(req), req->wb_bytes, + IOMODE_RW, false, nfs_io_gfp_mask()); if (IS_ERR(pgio->pg_lseg)) { pgio->pg_error = PTR_ERR(pgio->pg_lseg); pgio->pg_lseg = NULL; @@ -953,13 +953,10 @@ ff_layout_pg_get_mirror_count_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) { if (!pgio->pg_lseg) { - pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, - nfs_req_openctx(req), - req_offset(req), - req->wb_bytes, - IOMODE_RW, - false, - GFP_NOFS); + pgio->pg_lseg = + pnfs_update_layout(pgio->pg_inode, nfs_req_openctx(req), + req_offset(req), req->wb_bytes, + IOMODE_RW, false, nfs_io_gfp_mask()); if (IS_ERR(pgio->pg_lseg)) { pgio->pg_error = PTR_ERR(pgio->pg_lseg); pgio->pg_lseg = NULL; @@ -1140,6 +1137,8 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task, case -EIO: case -ETIMEDOUT: case -EPIPE: + case -EPROTO: + case -ENODEV: dprintk("%s DS connection error %d\n", __func__, task->tk_status); nfs4_delete_deviceid(devid->ld, devid->nfs_client, @@ -1245,6 +1244,8 @@ static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg, case -ENOBUFS: case -EPIPE: case -EPERM: + case -EPROTO: + case -ENODEV: *op_status = status = NFS4ERR_NXIO; break; case -EACCES: @@ -1258,7 +1259,7 @@ static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg, mirror = FF_LAYOUT_COMP(lseg, idx); err = ff_layout_track_ds_error(FF_LAYOUT_FROM_HDR(lseg->pls_layout), mirror, offset, length, status, opnum, - GFP_NOIO); + nfs_io_gfp_mask()); switch (status) { case NFS4ERR_DELAY: @@ -1378,6 +1379,11 @@ static int ff_layout_read_prepare_common(struct rpc_task *task, return -EIO; } + if (!pnfs_is_valid_lseg(hdr->lseg)) { + rpc_exit(task, -EAGAIN); + return -EAGAIN; + } + ff_layout_read_record_layoutstats_start(task, hdr); return 0; } @@ -1558,6 +1564,11 @@ static int ff_layout_write_prepare_common(struct rpc_task *task, return -EIO; } + if (!pnfs_is_valid_lseg(hdr->lseg)) { + rpc_exit(task, -EAGAIN); + return -EAGAIN; + } + ff_layout_write_record_layoutstats_start(task, hdr); return 0; } @@ -1650,15 +1661,23 @@ static void ff_layout_commit_record_layoutstats_done(struct rpc_task *task, set_bit(NFS_LSEG_LAYOUTRETURN, &cdata->lseg->pls_flags); } -static void ff_layout_commit_prepare_common(struct rpc_task *task, - struct nfs_commit_data *cdata) +static int ff_layout_commit_prepare_common(struct rpc_task *task, + struct nfs_commit_data *cdata) { + if (!pnfs_is_valid_lseg(cdata->lseg)) { + rpc_exit(task, -EAGAIN); + return -EAGAIN; + } + ff_layout_commit_record_layoutstats_start(task, cdata); + return 0; } static void ff_layout_commit_prepare_v3(struct rpc_task *task, void *data) { - ff_layout_commit_prepare_common(task, data); + if (ff_layout_commit_prepare_common(task, data)) + return; + rpc_call_start(task); } @@ -1954,6 +1973,65 @@ ff_layout_commit_pagelist(struct inode *inode, struct list_head *mds_pages, ff_layout_initiate_commit); } +static bool ff_layout_match_rw(const struct rpc_task *task, + const struct nfs_pgio_header *hdr, + const struct pnfs_layout_segment *lseg) +{ + return hdr->lseg == lseg; +} + +static bool ff_layout_match_commit(const struct rpc_task *task, + const struct nfs_commit_data *cdata, + const struct pnfs_layout_segment *lseg) +{ + return cdata->lseg == lseg; +} + +static bool ff_layout_match_io(const struct rpc_task *task, const void *data) +{ + const struct rpc_call_ops *ops = task->tk_ops; + + if (ops == &ff_layout_read_call_ops_v3 || + ops == &ff_layout_read_call_ops_v4 || + ops == &ff_layout_write_call_ops_v3 || + ops == &ff_layout_write_call_ops_v4) + return ff_layout_match_rw(task, task->tk_calldata, data); + if (ops == &ff_layout_commit_call_ops_v3 || + ops == &ff_layout_commit_call_ops_v4) + return ff_layout_match_commit(task, task->tk_calldata, data); + return false; +} + +static void ff_layout_cancel_io(struct pnfs_layout_segment *lseg) +{ + struct nfs4_ff_layout_segment *flseg = FF_LAYOUT_LSEG(lseg); + struct nfs4_ff_layout_mirror *mirror; + struct nfs4_ff_layout_ds *mirror_ds; + struct nfs4_pnfs_ds *ds; + struct nfs_client *ds_clp; + struct rpc_clnt *clnt; + u32 idx; + + for (idx = 0; idx < flseg->mirror_array_cnt; idx++) { + mirror = flseg->mirror_array[idx]; + mirror_ds = mirror->mirror_ds; + if (!mirror_ds) + continue; + ds = mirror->mirror_ds->ds; + if (!ds) + continue; + ds_clp = ds->ds_clp; + if (!ds_clp) + continue; + clnt = ds_clp->cl_rpcclient; + if (!clnt) + continue; + if (!rpc_cancel_tasks(clnt, -EAGAIN, ff_layout_match_io, lseg)) + continue; + rpc_clnt_disconnect(clnt); + } +} + static struct pnfs_ds_commit_info * ff_layout_get_ds_info(struct inode *inode) { @@ -1973,7 +2051,8 @@ ff_layout_setup_ds_info(struct pnfs_ds_commit_info *fl_cinfo, struct inode *inode = lseg->pls_layout->plh_inode; struct pnfs_commit_array *array, *new; - new = pnfs_alloc_commit_array(flseg->mirror_array_cnt, GFP_NOIO); + new = pnfs_alloc_commit_array(flseg->mirror_array_cnt, + nfs_io_gfp_mask()); if (new) { spin_lock(&inode->i_lock); array = pnfs_add_commit_array(fl_cinfo, new, lseg); @@ -2152,10 +2231,10 @@ ff_layout_prepare_layoutreturn(struct nfs4_layoutreturn_args *args) struct nfs4_flexfile_layoutreturn_args *ff_args; struct nfs4_flexfile_layout *ff_layout = FF_LAYOUT_FROM_HDR(args->layout); - ff_args = kmalloc(sizeof(*ff_args), GFP_KERNEL); + ff_args = kmalloc(sizeof(*ff_args), nfs_io_gfp_mask()); if (!ff_args) goto out_nomem; - ff_args->pages[0] = alloc_page(GFP_KERNEL); + ff_args->pages[0] = alloc_page(nfs_io_gfp_mask()); if (!ff_args->pages[0]) goto out_nomem_free; @@ -2165,8 +2244,9 @@ ff_layout_prepare_layoutreturn(struct nfs4_layoutreturn_args *args) FF_LAYOUTRETURN_MAXERR); spin_lock(&args->inode->i_lock); - ff_args->num_dev = ff_layout_mirror_prepare_stats(&ff_layout->generic_hdr, - &ff_args->devinfo[0], ARRAY_SIZE(ff_args->devinfo)); + ff_args->num_dev = ff_layout_mirror_prepare_stats( + &ff_layout->generic_hdr, &ff_args->devinfo[0], + ARRAY_SIZE(ff_args->devinfo), NFS4_FF_OP_LAYOUTRETURN); spin_unlock(&args->inode->i_lock); args->ld_private->ops = &layoutreturn_ops; @@ -2192,8 +2272,8 @@ ff_layout_send_layouterror(struct pnfs_layout_segment *lseg) if (list_empty(&head)) return; - errors = kmalloc_array(NFS42_LAYOUTERROR_MAX, - sizeof(*errors), GFP_NOFS); + errors = kmalloc_array(NFS42_LAYOUTERROR_MAX, sizeof(*errors), + nfs_io_gfp_mask()); if (errors != NULL) { const struct nfs4_ff_layout_ds_err *pos; size_t n = 0; @@ -2400,7 +2480,7 @@ static const struct nfs4_xdr_opaque_ops layoutstat_ops = { static int ff_layout_mirror_prepare_stats(struct pnfs_layout_hdr *lo, struct nfs42_layoutstat_devinfo *devinfo, - int dev_limit) + int dev_limit, enum nfs4_ff_op_type type) { struct nfs4_flexfile_layout *ff_layout = FF_LAYOUT_FROM_HDR(lo); struct nfs4_ff_layout_mirror *mirror; @@ -2412,7 +2492,9 @@ ff_layout_mirror_prepare_stats(struct pnfs_layout_hdr *lo, break; if (IS_ERR_OR_NULL(mirror->mirror_ds)) continue; - if (!test_and_clear_bit(NFS4_FF_MIRROR_STAT_AVAIL, &mirror->flags)) + if (!test_and_clear_bit(NFS4_FF_MIRROR_STAT_AVAIL, + &mirror->flags) && + type != NFS4_FF_OP_LAYOUTRETURN) continue; /* mirror refcount put in cleanup_layoutstats */ if (!refcount_inc_not_zero(&mirror->ref)) @@ -2444,14 +2526,17 @@ ff_layout_prepare_layoutstats(struct nfs42_layoutstat_args *args) const int dev_count = PNFS_LAYOUTSTATS_MAXDEV; /* For now, send at most PNFS_LAYOUTSTATS_MAXDEV statistics */ - args->devinfo = kmalloc_array(dev_count, sizeof(*args->devinfo), GFP_NOIO); + args->devinfo = kmalloc_array(dev_count, sizeof(*args->devinfo), + nfs_io_gfp_mask()); if (!args->devinfo) return -ENOMEM; spin_lock(&args->inode->i_lock); ff_layout = FF_LAYOUT_FROM_HDR(NFS_I(args->inode)->layout); args->num_dev = ff_layout_mirror_prepare_stats(&ff_layout->generic_hdr, - &args->devinfo[0], dev_count); + &args->devinfo[0], + dev_count, + NFS4_FF_OP_LAYOUTSTATS); spin_unlock(&args->inode->i_lock); if (!args->num_dev) { kfree(args->devinfo); @@ -2504,6 +2589,7 @@ static struct pnfs_layoutdriver_type flexfilelayout_type = { .prepare_layoutreturn = ff_layout_prepare_layoutreturn, .sync = pnfs_nfs_generic_sync, .prepare_layoutstats = ff_layout_prepare_layoutstats, + .cancel_io = ff_layout_cancel_io, }; static int __init nfs4flexfilelayout_init(void) diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c index bfa7202ca7be..e028f5a0ef5f 100644 --- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -113,8 +113,10 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, goto out_err_drain_dsaddrs; ds_versions[i].version = be32_to_cpup(p++); ds_versions[i].minor_version = be32_to_cpup(p++); - ds_versions[i].rsize = nfs_block_size(be32_to_cpup(p++), NULL); - ds_versions[i].wsize = nfs_block_size(be32_to_cpup(p++), NULL); + ds_versions[i].rsize = nfs_io_size(be32_to_cpup(p++), + server->nfs_client->cl_proto); + ds_versions[i].wsize = nfs_io_size(be32_to_cpup(p++), + server->nfs_client->cl_proto); ds_versions[i].tightly_coupled = be32_to_cpup(p); if (ds_versions[i].rsize > NFS_MAX_FILE_IO_SIZE) diff --git a/fs/nfs/fs_context.c b/fs/nfs/fs_context.c index ea17fa1f31ec..09833ec102fc 100644 --- a/fs/nfs/fs_context.c +++ b/fs/nfs/fs_context.c @@ -21,6 +21,8 @@ #include "nfs.h" #include "internal.h" +#include "nfstrace.h" + #define NFSDBG_FACILITY NFSDBG_MOUNT #if IS_ENABLED(CONFIG_NFS_V3) @@ -80,6 +82,7 @@ enum nfs_param { Opt_source, Opt_tcp, Opt_timeo, + Opt_trunkdiscovery, Opt_udp, Opt_v, Opt_vers, @@ -180,6 +183,7 @@ static const struct fs_parameter_spec nfs_fs_parameters[] = { fsparam_string("source", Opt_source), fsparam_flag ("tcp", Opt_tcp), fsparam_u32 ("timeo", Opt_timeo), + fsparam_flag_no("trunkdiscovery", Opt_trunkdiscovery), fsparam_flag ("udp", Opt_udp), fsparam_flag ("v2", Opt_v), fsparam_flag ("v3", Opt_v), @@ -269,9 +273,9 @@ static const struct constant_table nfs_secflavor_tokens[] = { * Address family must be initialized, and address must not be * the ANY address for that family. */ -static int nfs_verify_server_address(struct sockaddr *addr) +static int nfs_verify_server_address(struct sockaddr_storage *addr) { - switch (addr->sa_family) { + switch (addr->ss_family) { case AF_INET: { struct sockaddr_in *sa = (struct sockaddr_in *)addr; return sa->sin_addr.s_addr != htonl(INADDR_ANY); @@ -282,7 +286,6 @@ static int nfs_verify_server_address(struct sockaddr *addr) } } - dfprintk(MOUNT, "NFS: Invalid IP address specified\n"); return 0; } @@ -376,7 +379,7 @@ static int nfs_parse_security_flavors(struct fs_context *fc, char *string = param->string, *p; int ret; - dfprintk(MOUNT, "NFS: parsing %s=%s option\n", param->key, param->string); + trace_nfs_mount_assign(param->key, string); while ((p = strsep(&string, ":")) != NULL) { if (!*p) @@ -478,11 +481,11 @@ static int nfs_fs_context_parse_param(struct fs_context *fc, unsigned int len; int ret, opt; - dfprintk(MOUNT, "NFS: parsing nfs mount option '%s'\n", param->key); + trace_nfs_mount_option(param); opt = fs_parse(fc, nfs_fs_parameters, param, &result); if (opt < 0) - return ctx->sloppy ? 1 : opt; + return (opt == -ENOPARAM && ctx->sloppy) ? 1 : opt; if (fc->security) ctx->has_sec_mnt_opts = 1; @@ -515,7 +518,7 @@ static int nfs_fs_context_parse_param(struct fs_context *fc, if (result.negated) ctx->flags &= ~NFS_MOUNT_SOFTREVAL; else - ctx->flags &= NFS_MOUNT_SOFTREVAL; + ctx->flags |= NFS_MOUNT_SOFTREVAL; break; case Opt_posix: if (result.negated) @@ -529,6 +532,12 @@ static int nfs_fs_context_parse_param(struct fs_context *fc, else ctx->flags &= ~NFS_MOUNT_NOCTO; break; + case Opt_trunkdiscovery: + if (result.negated) + ctx->flags &= ~NFS_MOUNT_TRUNK_DISCOVERY; + else + ctx->flags |= NFS_MOUNT_TRUNK_DISCOVERY; + break; case Opt_ac: if (result.negated) ctx->flags |= NFS_MOUNT_NOAC; @@ -675,6 +684,7 @@ static int nfs_fs_context_parse_param(struct fs_context *fc, return ret; break; case Opt_vers: + trace_nfs_mount_assign(param->key, param->string); ret = nfs_parse_version_string(fc, param->string); if (ret < 0) return ret; @@ -686,6 +696,7 @@ static int nfs_fs_context_parse_param(struct fs_context *fc, break; case Opt_proto: + trace_nfs_mount_assign(param->key, param->string); protofamily = AF_INET; switch (lookup_constant(nfs_xprt_protocol_tokens, param->string, -1)) { case Opt_xprt_udp6: @@ -721,6 +732,7 @@ static int nfs_fs_context_parse_param(struct fs_context *fc, break; case Opt_mountproto: + trace_nfs_mount_assign(param->key, param->string); mountfamily = AF_INET; switch (lookup_constant(nfs_xprt_protocol_tokens, param->string, -1)) { case Opt_xprt_udp6: @@ -743,6 +755,7 @@ static int nfs_fs_context_parse_param(struct fs_context *fc, break; case Opt_addr: + trace_nfs_mount_assign(param->key, param->string); len = rpc_pton(fc->net_ns, param->string, param->size, &ctx->nfs_server.address, sizeof(ctx->nfs_server._address)); @@ -751,16 +764,19 @@ static int nfs_fs_context_parse_param(struct fs_context *fc, ctx->nfs_server.addrlen = len; break; case Opt_clientaddr: + trace_nfs_mount_assign(param->key, param->string); kfree(ctx->client_address); ctx->client_address = param->string; param->string = NULL; break; case Opt_mounthost: + trace_nfs_mount_assign(param->key, param->string); kfree(ctx->mount_server.hostname); ctx->mount_server.hostname = param->string; param->string = NULL; break; case Opt_mountaddr: + trace_nfs_mount_assign(param->key, param->string); len = rpc_pton(fc->net_ns, param->string, param->size, &ctx->mount_server.address, sizeof(ctx->mount_server._address)); @@ -838,7 +854,6 @@ static int nfs_fs_context_parse_param(struct fs_context *fc, */ case Opt_sloppy: ctx->sloppy = true; - dfprintk(MOUNT, "NFS: relaxing parsing rules\n"); break; } @@ -871,10 +886,8 @@ static int nfs_parse_source(struct fs_context *fc, size_t len; const char *end; - if (unlikely(!dev_name || !*dev_name)) { - dfprintk(MOUNT, "NFS: device name not specified\n"); + if (unlikely(!dev_name || !*dev_name)) return -EINVAL; - } /* Is the host name protected with square brakcets? */ if (*dev_name == '[') { @@ -914,7 +927,7 @@ static int nfs_parse_source(struct fs_context *fc, if (!ctx->nfs_server.export_path) goto out_nomem; - dfprintk(MOUNT, "NFS: MNTPATH: '%s'\n", ctx->nfs_server.export_path); + trace_nfs_mount_path(ctx->nfs_server.export_path); return 0; out_bad_devname: @@ -956,7 +969,7 @@ static int nfs23_parse_monolithic(struct fs_context *fc, { struct nfs_fs_context *ctx = nfs_fc2context(fc); struct nfs_fh *mntfh = ctx->mntfh; - struct sockaddr *sap = (struct sockaddr *)&ctx->nfs_server.address; + struct sockaddr_storage *sap = &ctx->nfs_server._address; int extra_flags = NFS_MOUNT_LEGACY_INTERFACE; int ret; @@ -1031,7 +1044,7 @@ static int nfs23_parse_monolithic(struct fs_context *fc, memcpy(sap, &data->addr, sizeof(data->addr)); ctx->nfs_server.addrlen = sizeof(data->addr); ctx->nfs_server.port = ntohs(data->addr.sin_port); - if (sap->sa_family != AF_INET || + if (sap->ss_family != AF_INET || !nfs_verify_server_address(sap)) goto out_no_address; @@ -1108,7 +1121,6 @@ out_no_sec: return nfs_invalf(fc, "NFS: nfs_mount_data version supports only AUTH_SYS"); out_nomem: - dfprintk(MOUNT, "NFS: not enough memory to handle mount options"); return -ENOMEM; out_no_address: @@ -1188,7 +1200,7 @@ static int nfs4_parse_monolithic(struct fs_context *fc, struct nfs4_mount_data *data) { struct nfs_fs_context *ctx = nfs_fc2context(fc); - struct sockaddr *sap = (struct sockaddr *)&ctx->nfs_server.address; + struct sockaddr_storage *sap = &ctx->nfs_server._address; int ret; char *c; @@ -1240,7 +1252,7 @@ static int nfs4_parse_monolithic(struct fs_context *fc, if (IS_ERR(c)) return PTR_ERR(c); ctx->nfs_server.export_path = c; - dfprintk(MOUNT, "NFS: MNTPATH: '%s'\n", c); + trace_nfs_mount_path(c); c = strndup_user(data->client_addr.data, 16); if (IS_ERR(c)) @@ -1302,7 +1314,7 @@ static int nfs_fs_context_validate(struct fs_context *fc) { struct nfs_fs_context *ctx = nfs_fc2context(fc); struct nfs_subversion *nfs_mod; - struct sockaddr *sap = (struct sockaddr *)&ctx->nfs_server.address; + struct sockaddr_storage *sap = &ctx->nfs_server._address; int max_namelen = PAGE_SIZE; int max_pathlen = NFS_MAXPATHLEN; int port = 0; @@ -1528,7 +1540,7 @@ static int nfs_init_fs_context(struct fs_context *fc) ctx->version = nfss->nfs_client->rpc_ops->version; ctx->minorversion = nfss->nfs_client->cl_minorversion; - memcpy(&ctx->nfs_server.address, &nfss->nfs_client->cl_addr, + memcpy(&ctx->nfs_server._address, &nfss->nfs_client->cl_addr, ctx->nfs_server.addrlen); if (fc->net_ns != net) { diff --git a/fs/nfs/fscache-index.c b/fs/nfs/fscache-index.c deleted file mode 100644 index 573b1da9342c..000000000000 --- a/fs/nfs/fscache-index.c +++ /dev/null @@ -1,140 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* NFS FS-Cache index structure definition - * - * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - */ - -#include <linux/init.h> -#include <linux/kernel.h> -#include <linux/sched.h> -#include <linux/mm.h> -#include <linux/nfs_fs.h> -#include <linux/nfs_fs_sb.h> -#include <linux/in6.h> -#include <linux/iversion.h> - -#include "internal.h" -#include "fscache.h" - -#define NFSDBG_FACILITY NFSDBG_FSCACHE - -/* - * Define the NFS filesystem for FS-Cache. Upon registration FS-Cache sticks - * the cookie for the top-level index object for NFS into here. The top-level - * index can than have other cache objects inserted into it. - */ -struct fscache_netfs nfs_fscache_netfs = { - .name = "nfs", - .version = 0, -}; - -/* - * Register NFS for caching - */ -int nfs_fscache_register(void) -{ - return fscache_register_netfs(&nfs_fscache_netfs); -} - -/* - * Unregister NFS for caching - */ -void nfs_fscache_unregister(void) -{ - fscache_unregister_netfs(&nfs_fscache_netfs); -} - -/* - * Define the server object for FS-Cache. This is used to describe a server - * object to fscache_acquire_cookie(). It is keyed by the NFS protocol and - * server address parameters. - */ -const struct fscache_cookie_def nfs_fscache_server_index_def = { - .name = "NFS.server", - .type = FSCACHE_COOKIE_TYPE_INDEX, -}; - -/* - * Define the superblock object for FS-Cache. This is used to describe a - * superblock object to fscache_acquire_cookie(). It is keyed by all the NFS - * parameters that might cause a separate superblock. - */ -const struct fscache_cookie_def nfs_fscache_super_index_def = { - .name = "NFS.super", - .type = FSCACHE_COOKIE_TYPE_INDEX, -}; - -/* - * Consult the netfs about the state of an object - * - This function can be absent if the index carries no state data - * - The netfs data from the cookie being used as the target is - * presented, as is the auxiliary data - */ -static -enum fscache_checkaux nfs_fscache_inode_check_aux(void *cookie_netfs_data, - const void *data, - uint16_t datalen, - loff_t object_size) -{ - struct nfs_fscache_inode_auxdata auxdata; - struct nfs_inode *nfsi = cookie_netfs_data; - - if (datalen != sizeof(auxdata)) - return FSCACHE_CHECKAUX_OBSOLETE; - - memset(&auxdata, 0, sizeof(auxdata)); - auxdata.mtime_sec = nfsi->vfs_inode.i_mtime.tv_sec; - auxdata.mtime_nsec = nfsi->vfs_inode.i_mtime.tv_nsec; - auxdata.ctime_sec = nfsi->vfs_inode.i_ctime.tv_sec; - auxdata.ctime_nsec = nfsi->vfs_inode.i_ctime.tv_nsec; - - if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4) - auxdata.change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode); - - if (memcmp(data, &auxdata, datalen) != 0) - return FSCACHE_CHECKAUX_OBSOLETE; - - return FSCACHE_CHECKAUX_OKAY; -} - -/* - * Get an extra reference on a read context. - * - This function can be absent if the completion function doesn't require a - * context. - * - The read context is passed back to NFS in the event that a data read on the - * cache fails with EIO - in which case the server must be contacted to - * retrieve the data, which requires the read context for security. - */ -static void nfs_fh_get_context(void *cookie_netfs_data, void *context) -{ - get_nfs_open_context(context); -} - -/* - * Release an extra reference on a read context. - * - This function can be absent if the completion function doesn't require a - * context. - */ -static void nfs_fh_put_context(void *cookie_netfs_data, void *context) -{ - if (context) - put_nfs_open_context(context); -} - -/* - * Define the inode object for FS-Cache. This is used to describe an inode - * object to fscache_acquire_cookie(). It is keyed by the NFS file handle for - * an inode. - * - * Coherency is managed by comparing the copies of i_size, i_mtime and i_ctime - * held in the cache auxiliary data for the data storage object with those in - * the inode struct in memory. - */ -const struct fscache_cookie_def nfs_fscache_inode_object_def = { - .name = "NFS.fh", - .type = FSCACHE_COOKIE_TYPE_DATAFILE, - .check_aux = nfs_fscache_inode_check_aux, - .get_context = nfs_fh_get_context, - .put_context = nfs_fh_put_context, -}; diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index d743629e05e1..e861d7bae305 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -19,27 +19,20 @@ #include "internal.h" #include "iostat.h" #include "fscache.h" +#include "nfstrace.h" -#define NFSDBG_FACILITY NFSDBG_FSCACHE +#define NFS_MAX_KEY_LEN 1000 -static struct rb_root nfs_fscache_keys = RB_ROOT; -static DEFINE_SPINLOCK(nfs_fscache_keys_lock); - -/* - * Layout of the key for an NFS server cache object. - */ -struct nfs_server_key { - struct { - uint16_t nfsversion; /* NFS protocol version */ - uint32_t minorversion; /* NFSv4 minor version */ - uint16_t family; /* address family */ - __be16 port; /* IP port */ - } hdr; - union { - struct in_addr ipv4_addr; /* IPv4 address */ - struct in6_addr ipv6_addr; /* IPv6 address */ - }; -} __packed; +static bool nfs_append_int(char *key, int *_len, unsigned long long x) +{ + if (*_len > NFS_MAX_KEY_LEN) + return false; + if (x == 0) + key[(*_len)++] = ','; + else + *_len += sprintf(key + *_len, ",%llx", x); + return true; +} /* * Get the per-client index cookie for an NFS client if the appropriate mount @@ -47,160 +40,106 @@ struct nfs_server_key { * - We always try and get an index cookie for the client, but get filehandle * cookies on a per-superblock basis, depending on the mount flags */ -void nfs_fscache_get_client_cookie(struct nfs_client *clp) +static bool nfs_fscache_get_client_key(struct nfs_client *clp, + char *key, int *_len) { const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) &clp->cl_addr; const struct sockaddr_in *sin = (struct sockaddr_in *) &clp->cl_addr; - struct nfs_server_key key; - uint16_t len = sizeof(key.hdr); - memset(&key, 0, sizeof(key)); - key.hdr.nfsversion = clp->rpc_ops->version; - key.hdr.minorversion = clp->cl_minorversion; - key.hdr.family = clp->cl_addr.ss_family; + *_len += snprintf(key + *_len, NFS_MAX_KEY_LEN - *_len, + ",%u.%u,%x", + clp->rpc_ops->version, + clp->cl_minorversion, + clp->cl_addr.ss_family); switch (clp->cl_addr.ss_family) { case AF_INET: - key.hdr.port = sin->sin_port; - key.ipv4_addr = sin->sin_addr; - len += sizeof(key.ipv4_addr); - break; + if (!nfs_append_int(key, _len, sin->sin_port) || + !nfs_append_int(key, _len, sin->sin_addr.s_addr)) + return false; + return true; case AF_INET6: - key.hdr.port = sin6->sin6_port; - key.ipv6_addr = sin6->sin6_addr; - len += sizeof(key.ipv6_addr); - break; + if (!nfs_append_int(key, _len, sin6->sin6_port) || + !nfs_append_int(key, _len, sin6->sin6_addr.s6_addr32[0]) || + !nfs_append_int(key, _len, sin6->sin6_addr.s6_addr32[1]) || + !nfs_append_int(key, _len, sin6->sin6_addr.s6_addr32[2]) || + !nfs_append_int(key, _len, sin6->sin6_addr.s6_addr32[3])) + return false; + return true; default: printk(KERN_WARNING "NFS: Unknown network family '%d'\n", clp->cl_addr.ss_family); - clp->fscache = NULL; - return; + return false; } - - /* create a cache index for looking up filehandles */ - clp->fscache = fscache_acquire_cookie(nfs_fscache_netfs.primary_index, - &nfs_fscache_server_index_def, - &key, len, - NULL, 0, - clp, 0, true); - dfprintk(FSCACHE, "NFS: get client cookie (0x%p/0x%p)\n", - clp, clp->fscache); -} - -/* - * Dispose of a per-client cookie - */ -void nfs_fscache_release_client_cookie(struct nfs_client *clp) -{ - dfprintk(FSCACHE, "NFS: releasing client cookie (0x%p/0x%p)\n", - clp, clp->fscache); - - fscache_relinquish_cookie(clp->fscache, NULL, false); - clp->fscache = NULL; } /* - * Get the cache cookie for an NFS superblock. We have to handle - * uniquification here because the cache doesn't do it for us. + * Get the cache cookie for an NFS superblock. * * The default uniquifier is just an empty string, but it may be overridden * either by the 'fsc=xxx' option to mount, or by inheriting it from the parent * superblock across an automount point of some nature. */ -void nfs_fscache_get_super_cookie(struct super_block *sb, const char *uniq, int ulen) +int nfs_fscache_get_super_cookie(struct super_block *sb, const char *uniq, int ulen) { - struct nfs_fscache_key *key, *xkey; + struct fscache_volume *vcookie; struct nfs_server *nfss = NFS_SB(sb); - struct rb_node **p, *parent; - int diff; + unsigned int len = 3; + char *key; - nfss->fscache_key = NULL; - nfss->fscache = NULL; - if (!uniq) { - uniq = ""; - ulen = 1; + if (uniq) { + nfss->fscache_uniq = kmemdup_nul(uniq, ulen, GFP_KERNEL); + if (!nfss->fscache_uniq) + return -ENOMEM; } - key = kzalloc(sizeof(*key) + ulen, GFP_KERNEL); + key = kmalloc(NFS_MAX_KEY_LEN + 24, GFP_KERNEL); if (!key) - return; - - key->nfs_client = nfss->nfs_client; - key->key.super.s_flags = sb->s_flags & NFS_SB_MASK; - key->key.nfs_server.flags = nfss->flags; - key->key.nfs_server.rsize = nfss->rsize; - key->key.nfs_server.wsize = nfss->wsize; - key->key.nfs_server.acregmin = nfss->acregmin; - key->key.nfs_server.acregmax = nfss->acregmax; - key->key.nfs_server.acdirmin = nfss->acdirmin; - key->key.nfs_server.acdirmax = nfss->acdirmax; - key->key.nfs_server.fsid = nfss->fsid; - key->key.rpc_auth.au_flavor = nfss->client->cl_auth->au_flavor; - - key->key.uniq_len = ulen; - memcpy(key->key.uniquifier, uniq, ulen); - - spin_lock(&nfs_fscache_keys_lock); - p = &nfs_fscache_keys.rb_node; - parent = NULL; - while (*p) { - parent = *p; - xkey = rb_entry(parent, struct nfs_fscache_key, node); - - if (key->nfs_client < xkey->nfs_client) - goto go_left; - if (key->nfs_client > xkey->nfs_client) - goto go_right; - - diff = memcmp(&key->key, &xkey->key, sizeof(key->key)); - if (diff < 0) - goto go_left; - if (diff > 0) - goto go_right; - - if (key->key.uniq_len == 0) - goto non_unique; - diff = memcmp(key->key.uniquifier, - xkey->key.uniquifier, - key->key.uniq_len); - if (diff < 0) - goto go_left; - if (diff > 0) - goto go_right; - goto non_unique; - - go_left: - p = &(*p)->rb_left; - continue; - go_right: - p = &(*p)->rb_right; + return -ENOMEM; + + memcpy(key, "nfs", 3); + if (!nfs_fscache_get_client_key(nfss->nfs_client, key, &len) || + !nfs_append_int(key, &len, nfss->fsid.major) || + !nfs_append_int(key, &len, nfss->fsid.minor) || + !nfs_append_int(key, &len, sb->s_flags & NFS_SB_MASK) || + !nfs_append_int(key, &len, nfss->flags) || + !nfs_append_int(key, &len, nfss->rsize) || + !nfs_append_int(key, &len, nfss->wsize) || + !nfs_append_int(key, &len, nfss->acregmin) || + !nfs_append_int(key, &len, nfss->acregmax) || + !nfs_append_int(key, &len, nfss->acdirmin) || + !nfs_append_int(key, &len, nfss->acdirmax) || + !nfs_append_int(key, &len, nfss->client->cl_auth->au_flavor)) + goto out; + + if (ulen > 0) { + if (ulen > NFS_MAX_KEY_LEN - len) + goto out; + key[len++] = ','; + memcpy(key + len, uniq, ulen); + len += ulen; } - - rb_link_node(&key->node, parent, p); - rb_insert_color(&key->node, &nfs_fscache_keys); - spin_unlock(&nfs_fscache_keys_lock); - nfss->fscache_key = key; + key[len] = 0; /* create a cache index for looking up filehandles */ - nfss->fscache = fscache_acquire_cookie(nfss->nfs_client->fscache, - &nfs_fscache_super_index_def, - &key->key, - sizeof(key->key) + ulen, - NULL, 0, - nfss, 0, true); - dfprintk(FSCACHE, "NFS: get superblock cookie (0x%p/0x%p)\n", - nfss, nfss->fscache); - return; - -non_unique: - spin_unlock(&nfs_fscache_keys_lock); + vcookie = fscache_acquire_volume(key, + NULL, /* preferred_cache */ + NULL, 0 /* coherency_data */); + if (IS_ERR(vcookie)) { + if (vcookie != ERR_PTR(-EBUSY)) { + kfree(key); + return PTR_ERR(vcookie); + } + pr_err("NFS: Cache volume key already in use (%s)\n", key); + vcookie = NULL; + } + nfss->fscache = vcookie; + +out: kfree(key); - nfss->fscache_key = NULL; - nfss->fscache = NULL; - printk(KERN_WARNING "NFS:" - " Cache request denied due to non-unique superblock keys\n"); + return 0; } /* @@ -210,32 +149,9 @@ void nfs_fscache_release_super_cookie(struct super_block *sb) { struct nfs_server *nfss = NFS_SB(sb); - dfprintk(FSCACHE, "NFS: releasing superblock cookie (0x%p/0x%p)\n", - nfss, nfss->fscache); - - fscache_relinquish_cookie(nfss->fscache, NULL, false); + fscache_relinquish_volume(nfss->fscache, NULL, false); nfss->fscache = NULL; - - if (nfss->fscache_key) { - spin_lock(&nfs_fscache_keys_lock); - rb_erase(&nfss->fscache_key->node, &nfs_fscache_keys); - spin_unlock(&nfs_fscache_keys_lock); - kfree(nfss->fscache_key); - nfss->fscache_key = NULL; - } -} - -static void nfs_fscache_update_auxdata(struct nfs_fscache_inode_auxdata *auxdata, - struct nfs_inode *nfsi) -{ - memset(auxdata, 0, sizeof(*auxdata)); - auxdata->mtime_sec = nfsi->vfs_inode.i_mtime.tv_sec; - auxdata->mtime_nsec = nfsi->vfs_inode.i_mtime.tv_nsec; - auxdata->ctime_sec = nfsi->vfs_inode.i_ctime.tv_sec; - auxdata->ctime_nsec = nfsi->vfs_inode.i_ctime.tv_nsec; - - if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4) - auxdata->change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode); + kfree(nfss->fscache_uniq); } /* @@ -251,13 +167,15 @@ void nfs_fscache_init_inode(struct inode *inode) if (!(nfss->fscache && S_ISREG(inode->i_mode))) return; - nfs_fscache_update_auxdata(&auxdata, nfsi); + nfs_fscache_update_auxdata(&auxdata, inode); nfsi->fscache = fscache_acquire_cookie(NFS_SB(inode->i_sb)->fscache, - &nfs_fscache_inode_object_def, - nfsi->fh.data, nfsi->fh.size, - &auxdata, sizeof(auxdata), - nfsi, nfsi->vfs_inode.i_size, false); + 0, + nfsi->fh.data, /* index_key */ + nfsi->fh.size, + &auxdata, /* aux_data */ + sizeof(auxdata), + i_size_read(inode)); } /* @@ -265,24 +183,13 @@ void nfs_fscache_init_inode(struct inode *inode) */ void nfs_fscache_clear_inode(struct inode *inode) { - struct nfs_fscache_inode_auxdata auxdata; struct nfs_inode *nfsi = NFS_I(inode); struct fscache_cookie *cookie = nfs_i_fscache(inode); - dfprintk(FSCACHE, "NFS: clear cookie (0x%p/0x%p)\n", nfsi, cookie); - - nfs_fscache_update_auxdata(&auxdata, nfsi); - fscache_relinquish_cookie(cookie, &auxdata, false); + fscache_relinquish_cookie(cookie, false); nfsi->fscache = NULL; } -static bool nfs_fscache_can_enable(void *data) -{ - struct inode *inode = data; - - return !inode_is_open_for_write(inode); -} - /* * Enable or disable caching for a file that is being opened as appropriate. * The cookie is allocated when the inode is initialised, but is not enabled at @@ -305,216 +212,137 @@ static bool nfs_fscache_can_enable(void *data) void nfs_fscache_open_file(struct inode *inode, struct file *filp) { struct nfs_fscache_inode_auxdata auxdata; - struct nfs_inode *nfsi = NFS_I(inode); struct fscache_cookie *cookie = nfs_i_fscache(inode); + bool open_for_write = inode_is_open_for_write(inode); if (!fscache_cookie_valid(cookie)) return; - nfs_fscache_update_auxdata(&auxdata, nfsi); - - if (inode_is_open_for_write(inode)) { - dfprintk(FSCACHE, "NFS: nfsi 0x%p disabling cache\n", nfsi); - clear_bit(NFS_INO_FSCACHE, &nfsi->flags); - fscache_disable_cookie(cookie, &auxdata, true); - fscache_uncache_all_inode_pages(cookie, inode); - } else { - dfprintk(FSCACHE, "NFS: nfsi 0x%p enabling cache\n", nfsi); - fscache_enable_cookie(cookie, &auxdata, nfsi->vfs_inode.i_size, - nfs_fscache_can_enable, inode); - if (fscache_cookie_enabled(cookie)) - set_bit(NFS_INO_FSCACHE, &NFS_I(inode)->flags); + fscache_use_cookie(cookie, open_for_write); + if (open_for_write) { + nfs_fscache_update_auxdata(&auxdata, inode); + fscache_invalidate(cookie, &auxdata, i_size_read(inode), + FSCACHE_INVAL_DIO_WRITE); } } EXPORT_SYMBOL_GPL(nfs_fscache_open_file); -/* - * Release the caching state associated with a page, if the page isn't busy - * interacting with the cache. - * - Returns true (can release page) or false (page busy). - */ -int nfs_fscache_release_page(struct page *page, gfp_t gfp) +void nfs_fscache_release_file(struct inode *inode, struct file *filp) { - if (PageFsCache(page)) { - struct fscache_cookie *cookie = nfs_i_fscache(page->mapping->host); - - BUG_ON(!cookie); - dfprintk(FSCACHE, "NFS: fscache releasepage (0x%p/0x%p/0x%p)\n", - cookie, page, NFS_I(page->mapping->host)); - - if (!fscache_maybe_release_page(cookie, page, gfp)) - return 0; - - nfs_inc_fscache_stats(page->mapping->host, - NFSIOS_FSCACHE_PAGES_UNCACHED); - } + struct nfs_fscache_inode_auxdata auxdata; + struct fscache_cookie *cookie = nfs_i_fscache(inode); + loff_t i_size = i_size_read(inode); - return 1; + nfs_fscache_update_auxdata(&auxdata, inode); + fscache_unuse_cookie(cookie, &auxdata, &i_size); } /* - * Release the caching state associated with a page if undergoing complete page - * invalidation. + * Fallback page reading interface. */ -void __nfs_fscache_invalidate_page(struct page *page, struct inode *inode) +static int fscache_fallback_read_page(struct inode *inode, struct page *page) { + struct netfs_cache_resources cres; struct fscache_cookie *cookie = nfs_i_fscache(inode); + struct iov_iter iter; + struct bio_vec bvec[1]; + int ret; - BUG_ON(!cookie); - - dfprintk(FSCACHE, "NFS: fscache invalidatepage (0x%p/0x%p/0x%p)\n", - cookie, page, NFS_I(inode)); - - fscache_wait_on_page_write(cookie, page); + memset(&cres, 0, sizeof(cres)); + bvec[0].bv_page = page; + bvec[0].bv_offset = 0; + bvec[0].bv_len = PAGE_SIZE; + iov_iter_bvec(&iter, READ, bvec, ARRAY_SIZE(bvec), PAGE_SIZE); - BUG_ON(!PageLocked(page)); - fscache_uncache_page(cookie, page); - nfs_inc_fscache_stats(page->mapping->host, - NFSIOS_FSCACHE_PAGES_UNCACHED); -} + ret = fscache_begin_read_operation(&cres, cookie); + if (ret < 0) + return ret; -/* - * Handle completion of a page being read from the cache. - * - Called in process (keventd) context. - */ -static void nfs_readpage_from_fscache_complete(struct page *page, - void *context, - int error) -{ - dfprintk(FSCACHE, - "NFS: readpage_from_fscache_complete (0x%p/0x%p/%d)\n", - page, context, error); - - /* - * If the read completes with an error, mark the page with PG_checked, - * unlock the page, and let the VM reissue the readpage. - */ - if (!error) - SetPageUptodate(page); - else - SetPageChecked(page); - unlock_page(page); + ret = fscache_read(&cres, page_offset(page), &iter, NETFS_READ_HOLE_FAIL, + NULL, NULL); + fscache_end_operation(&cres); + return ret; } /* - * Retrieve a page from fscache + * Fallback page writing interface. */ -int __nfs_readpage_from_fscache(struct nfs_open_context *ctx, - struct inode *inode, struct page *page) +static int fscache_fallback_write_page(struct inode *inode, struct page *page, + bool no_space_allocated_yet) { + struct netfs_cache_resources cres; + struct fscache_cookie *cookie = nfs_i_fscache(inode); + struct iov_iter iter; + struct bio_vec bvec[1]; + loff_t start = page_offset(page); + size_t len = PAGE_SIZE; int ret; - dfprintk(FSCACHE, - "NFS: readpage_from_fscache(fsc:%p/p:%p(i:%lx f:%lx)/0x%p)\n", - nfs_i_fscache(inode), page, page->index, page->flags, inode); + memset(&cres, 0, sizeof(cres)); + bvec[0].bv_page = page; + bvec[0].bv_offset = 0; + bvec[0].bv_len = PAGE_SIZE; + iov_iter_bvec(&iter, WRITE, bvec, ARRAY_SIZE(bvec), PAGE_SIZE); - if (PageChecked(page)) { - ClearPageChecked(page); - return 1; - } - - ret = fscache_read_or_alloc_page(nfs_i_fscache(inode), - page, - nfs_readpage_from_fscache_complete, - ctx, - GFP_KERNEL); - - switch (ret) { - case 0: /* read BIO submitted (page in fscache) */ - dfprintk(FSCACHE, - "NFS: readpage_from_fscache: BIO submitted\n"); - nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_OK); + ret = fscache_begin_write_operation(&cres, cookie); + if (ret < 0) return ret; - case -ENOBUFS: /* inode not in cache */ - case -ENODATA: /* page not in cache */ - nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL); - dfprintk(FSCACHE, - "NFS: readpage_from_fscache %d\n", ret); - return 1; - - default: - dfprintk(FSCACHE, "NFS: readpage_from_fscache %d\n", ret); - nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL); - } + ret = cres.ops->prepare_write(&cres, &start, &len, i_size_read(inode), + no_space_allocated_yet); + if (ret == 0) + ret = fscache_write(&cres, page_offset(page), &iter, NULL, NULL); + fscache_end_operation(&cres); return ret; } /* - * Retrieve a set of pages from fscache + * Retrieve a page from fscache */ -int __nfs_readpages_from_fscache(struct nfs_open_context *ctx, - struct inode *inode, - struct address_space *mapping, - struct list_head *pages, - unsigned *nr_pages) +int __nfs_fscache_read_page(struct inode *inode, struct page *page) { - unsigned npages = *nr_pages; int ret; - dfprintk(FSCACHE, "NFS: nfs_getpages_from_fscache (0x%p/%u/0x%p)\n", - nfs_i_fscache(inode), npages, inode); - - ret = fscache_read_or_alloc_pages(nfs_i_fscache(inode), - mapping, pages, nr_pages, - nfs_readpage_from_fscache_complete, - ctx, - mapping_gfp_mask(mapping)); - if (*nr_pages < npages) - nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_OK, - npages); - if (*nr_pages > 0) - nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL, - *nr_pages); - - switch (ret) { - case 0: /* read submitted to the cache for all pages */ - BUG_ON(!list_empty(pages)); - BUG_ON(*nr_pages != 0); - dfprintk(FSCACHE, - "NFS: nfs_getpages_from_fscache: submitted\n"); - - return ret; - - case -ENOBUFS: /* some pages aren't cached and can't be */ - case -ENODATA: /* some pages aren't cached */ - dfprintk(FSCACHE, - "NFS: nfs_getpages_from_fscache: no page: %d\n", ret); - return 1; + trace_nfs_fscache_read_page(inode, page); + if (PageChecked(page)) { + ClearPageChecked(page); + ret = 1; + goto out; + } - default: - dfprintk(FSCACHE, - "NFS: nfs_getpages_from_fscache: ret %d\n", ret); + ret = fscache_fallback_read_page(inode, page); + if (ret < 0) { + nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL); + SetPageChecked(page); + goto out; } + /* Read completed synchronously */ + nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_OK); + SetPageUptodate(page); + ret = 0; +out: + trace_nfs_fscache_read_page_exit(inode, page, ret); return ret; } /* - * Store a newly fetched page in fscache - * - PG_fscache must be set on the page + * Store a newly fetched page in fscache. We can be certain there's no page + * stored in the cache as yet otherwise we would've read it from there. */ -void __nfs_readpage_to_fscache(struct inode *inode, struct page *page, int sync) +void __nfs_fscache_write_page(struct inode *inode, struct page *page) { int ret; - dfprintk(FSCACHE, - "NFS: readpage_to_fscache(fsc:%p/p:%p(i:%lx f:%lx)/%d)\n", - nfs_i_fscache(inode), page, page->index, page->flags, sync); + trace_nfs_fscache_write_page(inode, page); - ret = fscache_write_page(nfs_i_fscache(inode), page, - inode->i_size, GFP_KERNEL); - dfprintk(FSCACHE, - "NFS: readpage_to_fscache: p:%p(i:%lu f:%lx) ret %d\n", - page, page->index, page->flags, ret); + ret = fscache_fallback_write_page(inode, page, true); if (ret != 0) { - fscache_uncache_page(nfs_i_fscache(inode), page); - nfs_inc_fscache_stats(inode, - NFSIOS_FSCACHE_PAGES_WRITTEN_FAIL); + nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_WRITTEN_FAIL); nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_UNCACHED); } else { - nfs_inc_fscache_stats(inode, - NFSIOS_FSCACHE_PAGES_WRITTEN_OK); + nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_WRITTEN_OK); } + trace_nfs_fscache_write_page_exit(inode, page, ret); } diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h index 6754c8607230..2a37af880978 100644 --- a/fs/nfs/fscache.h +++ b/fs/nfs/fscache.h @@ -8,51 +8,16 @@ #ifndef _NFS_FSCACHE_H #define _NFS_FSCACHE_H +#include <linux/swap.h> #include <linux/nfs_fs.h> #include <linux/nfs_mount.h> #include <linux/nfs4_mount.h> #include <linux/fscache.h> +#include <linux/iversion.h> #ifdef CONFIG_NFS_FSCACHE /* - * set of NFS FS-Cache objects that form a superblock key - */ -struct nfs_fscache_key { - struct rb_node node; - struct nfs_client *nfs_client; /* the server */ - - /* the elements of the unique key - as used by nfs_compare_super() and - * nfs_compare_mount_options() to distinguish superblocks */ - struct { - struct { - unsigned long s_flags; /* various flags - * (& NFS_MS_MASK) */ - } super; - - struct { - struct nfs_fsid fsid; - int flags; - unsigned int rsize; /* read size */ - unsigned int wsize; /* write size */ - unsigned int acregmin; /* attr cache timeouts */ - unsigned int acregmax; - unsigned int acdirmin; - unsigned int acdirmax; - } nfs_server; - - struct { - rpc_authflavor_t au_flavor; - } rpc_auth; - - /* uniquifier - can be used if nfs_server.flags includes - * NFS_MOUNT_UNSHARED */ - u8 uniq_len; - char uniquifier[0]; - } key; -}; - -/* * Definition of the auxiliary data attached to NFS inode storage objects * within the cache. * @@ -70,84 +35,39 @@ struct nfs_fscache_inode_auxdata { }; /* - * fscache-index.c - */ -extern struct fscache_netfs nfs_fscache_netfs; -extern const struct fscache_cookie_def nfs_fscache_server_index_def; -extern const struct fscache_cookie_def nfs_fscache_super_index_def; -extern const struct fscache_cookie_def nfs_fscache_inode_object_def; - -extern int nfs_fscache_register(void); -extern void nfs_fscache_unregister(void); - -/* * fscache.c */ -extern void nfs_fscache_get_client_cookie(struct nfs_client *); -extern void nfs_fscache_release_client_cookie(struct nfs_client *); - -extern void nfs_fscache_get_super_cookie(struct super_block *, const char *, int); +extern int nfs_fscache_get_super_cookie(struct super_block *, const char *, int); extern void nfs_fscache_release_super_cookie(struct super_block *); extern void nfs_fscache_init_inode(struct inode *); extern void nfs_fscache_clear_inode(struct inode *); extern void nfs_fscache_open_file(struct inode *, struct file *); +extern void nfs_fscache_release_file(struct inode *, struct file *); -extern void __nfs_fscache_invalidate_page(struct page *, struct inode *); -extern int nfs_fscache_release_page(struct page *, gfp_t); +extern int __nfs_fscache_read_page(struct inode *, struct page *); +extern void __nfs_fscache_write_page(struct inode *, struct page *); -extern int __nfs_readpage_from_fscache(struct nfs_open_context *, - struct inode *, struct page *); -extern int __nfs_readpages_from_fscache(struct nfs_open_context *, - struct inode *, struct address_space *, - struct list_head *, unsigned *); -extern void __nfs_readpage_to_fscache(struct inode *, struct page *, int); - -/* - * wait for a page to complete writing to the cache - */ -static inline void nfs_fscache_wait_on_page_write(struct nfs_inode *nfsi, - struct page *page) -{ - if (PageFsCache(page)) - fscache_wait_on_page_write(nfsi->fscache, page); -} - -/* - * release the caching state associated with a page if undergoing complete page - * invalidation - */ -static inline void nfs_fscache_invalidate_page(struct page *page, - struct inode *inode) +static inline bool nfs_fscache_release_folio(struct folio *folio, gfp_t gfp) { - if (PageFsCache(page)) - __nfs_fscache_invalidate_page(page, inode); + if (folio_test_fscache(folio)) { + if (current_is_kswapd() || !(gfp & __GFP_FS)) + return false; + folio_wait_fscache(folio); + fscache_note_page_release(nfs_i_fscache(folio->mapping->host)); + nfs_inc_fscache_stats(folio->mapping->host, + NFSIOS_FSCACHE_PAGES_UNCACHED); + } + return true; } /* * Retrieve a page from an inode data storage object. */ -static inline int nfs_readpage_from_fscache(struct nfs_open_context *ctx, - struct inode *inode, - struct page *page) +static inline int nfs_fscache_read_page(struct inode *inode, struct page *page) { - if (NFS_I(inode)->fscache) - return __nfs_readpage_from_fscache(ctx, inode, page); - return -ENOBUFS; -} - -/* - * Retrieve a set of pages from an inode data storage object. - */ -static inline int nfs_readpages_from_fscache(struct nfs_open_context *ctx, - struct inode *inode, - struct address_space *mapping, - struct list_head *pages, - unsigned *nr_pages) -{ - if (NFS_I(inode)->fscache) - return __nfs_readpages_from_fscache(ctx, inode, mapping, pages, - nr_pages); + if (nfs_i_fscache(inode)) + return __nfs_fscache_read_page(inode, page); return -ENOBUFS; } @@ -155,28 +75,39 @@ static inline int nfs_readpages_from_fscache(struct nfs_open_context *ctx, * Store a page newly fetched from the server in an inode data storage object * in the cache. */ -static inline void nfs_readpage_to_fscache(struct inode *inode, - struct page *page, - int sync) +static inline void nfs_fscache_write_page(struct inode *inode, + struct page *page) { - if (PageFsCache(page)) - __nfs_readpage_to_fscache(inode, page, sync); + if (nfs_i_fscache(inode)) + __nfs_fscache_write_page(inode, page); } -/* - * Invalidate the contents of fscache for this inode. This will not sleep. - */ -static inline void nfs_fscache_invalidate(struct inode *inode) +static inline void nfs_fscache_update_auxdata(struct nfs_fscache_inode_auxdata *auxdata, + struct inode *inode) { - fscache_invalidate(NFS_I(inode)->fscache); + memset(auxdata, 0, sizeof(*auxdata)); + auxdata->mtime_sec = inode->i_mtime.tv_sec; + auxdata->mtime_nsec = inode->i_mtime.tv_nsec; + auxdata->ctime_sec = inode->i_ctime.tv_sec; + auxdata->ctime_nsec = inode->i_ctime.tv_nsec; + + if (NFS_SERVER(inode)->nfs_client->rpc_ops->version == 4) + auxdata->change_attr = inode_peek_iversion_raw(inode); } /* - * Wait for an object to finish being invalidated. + * Invalidate the contents of fscache for this inode. This will not sleep. */ -static inline void nfs_fscache_wait_on_invalidate(struct inode *inode) +static inline void nfs_fscache_invalidate(struct inode *inode, int flags) { - fscache_wait_on_invalidate(NFS_I(inode)->fscache); + struct nfs_fscache_inode_auxdata auxdata; + struct nfs_inode *nfsi = NFS_I(inode); + + if (nfsi->fscache) { + nfs_fscache_update_auxdata(&auxdata, inode); + fscache_invalidate(nfsi->fscache, &auxdata, + i_size_read(inode), flags); + } } /* @@ -190,48 +121,24 @@ static inline const char *nfs_server_fscache_state(struct nfs_server *server) } #else /* CONFIG_NFS_FSCACHE */ -static inline int nfs_fscache_register(void) { return 0; } -static inline void nfs_fscache_unregister(void) {} - -static inline void nfs_fscache_get_client_cookie(struct nfs_client *clp) {} -static inline void nfs_fscache_release_client_cookie(struct nfs_client *clp) {} - static inline void nfs_fscache_release_super_cookie(struct super_block *sb) {} static inline void nfs_fscache_init_inode(struct inode *inode) {} static inline void nfs_fscache_clear_inode(struct inode *inode) {} static inline void nfs_fscache_open_file(struct inode *inode, struct file *filp) {} +static inline void nfs_fscache_release_file(struct inode *inode, struct file *file) {} -static inline int nfs_fscache_release_page(struct page *page, gfp_t gfp) -{ - return 1; /* True: may release page */ -} -static inline void nfs_fscache_invalidate_page(struct page *page, - struct inode *inode) {} -static inline void nfs_fscache_wait_on_page_write(struct nfs_inode *nfsi, - struct page *page) {} - -static inline int nfs_readpage_from_fscache(struct nfs_open_context *ctx, - struct inode *inode, - struct page *page) +static inline bool nfs_fscache_release_folio(struct folio *folio, gfp_t gfp) { - return -ENOBUFS; + return true; /* may release folio */ } -static inline int nfs_readpages_from_fscache(struct nfs_open_context *ctx, - struct inode *inode, - struct address_space *mapping, - struct list_head *pages, - unsigned *nr_pages) +static inline int nfs_fscache_read_page(struct inode *inode, struct page *page) { return -ENOBUFS; } -static inline void nfs_readpage_to_fscache(struct inode *inode, - struct page *page, int sync) {} - - -static inline void nfs_fscache_invalidate(struct inode *inode) {} -static inline void nfs_fscache_wait_on_invalidate(struct inode *inode) {} +static inline void nfs_fscache_write_page(struct inode *inode, struct page *page) {} +static inline void nfs_fscache_invalidate(struct inode *inode, int flags) {} static inline const char *nfs_server_fscache_state(struct nfs_server *server) { diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index fda530d5e764..6b2cfa59a1a2 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -72,18 +72,13 @@ nfs_fattr_to_ino_t(struct nfs_fattr *fattr) return nfs_fileid_to_ino_t(fattr->fileid); } -static int nfs_wait_killable(int mode) +int nfs_wait_bit_killable(struct wait_bit_key *key, int mode) { - freezable_schedule_unsafe(); + schedule(); if (signal_pending_state(mode, current)) return -ERESTARTSYS; return 0; } - -int nfs_wait_bit_killable(struct wait_bit_key *key, int mode) -{ - return nfs_wait_killable(mode); -} EXPORT_SYMBOL_GPL(nfs_wait_bit_killable); /** @@ -203,14 +198,13 @@ void nfs_set_cache_invalid(struct inode *inode, unsigned long flags) NFS_INO_INVALID_OTHER | NFS_INO_INVALID_XATTR); flags &= ~(NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_SIZE); - } else if (flags & NFS_INO_REVAL_PAGECACHE) - flags |= NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_SIZE; + } if (!nfs_has_xattr_cache(nfsi)) flags &= ~NFS_INO_INVALID_XATTR; if (flags & NFS_INO_INVALID_DATA) - nfs_fscache_invalidate(inode); - flags &= ~(NFS_INO_REVAL_PAGECACHE | NFS_INO_REVAL_FORCED); + nfs_fscache_invalidate(inode, 0); + flags &= ~NFS_INO_REVAL_FORCED; nfsi->cache_validity |= flags; @@ -236,19 +230,17 @@ static void nfs_zap_caches_locked(struct inode *inode) nfsi->attrtimeo = NFS_MINATTRTIMEO(inode); nfsi->attrtimeo_timestamp = jiffies; - if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) { - nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR - | NFS_INO_INVALID_DATA - | NFS_INO_INVALID_ACCESS - | NFS_INO_INVALID_ACL - | NFS_INO_INVALID_XATTR - | NFS_INO_REVAL_PAGECACHE); - } else - nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR - | NFS_INO_INVALID_ACCESS - | NFS_INO_INVALID_ACL - | NFS_INO_INVALID_XATTR - | NFS_INO_REVAL_PAGECACHE); + if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) + nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR | + NFS_INO_INVALID_DATA | + NFS_INO_INVALID_ACCESS | + NFS_INO_INVALID_ACL | + NFS_INO_INVALID_XATTR); + else + nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR | + NFS_INO_INVALID_ACCESS | + NFS_INO_INVALID_ACL | + NFS_INO_INVALID_XATTR); nfs_zap_label_cache_locked(nfsi); } @@ -321,7 +313,7 @@ struct nfs_find_desc { static int nfs_find_actor(struct inode *inode, void *opaque) { - struct nfs_find_desc *desc = (struct nfs_find_desc *)opaque; + struct nfs_find_desc *desc = opaque; struct nfs_fh *fh = desc->fh; struct nfs_fattr *fattr = desc->fattr; @@ -339,7 +331,7 @@ nfs_find_actor(struct inode *inode, void *opaque) static int nfs_init_locked(struct inode *inode, void *opaque) { - struct nfs_find_desc *desc = (struct nfs_find_desc *)opaque; + struct nfs_find_desc *desc = opaque; struct nfs_fattr *fattr = desc->fattr; set_nfs_fileid(inode, fattr->fileid); @@ -429,6 +421,7 @@ nfs_ilookup(struct super_block *sb, struct nfs_fattr *fattr, struct nfs_fh *fh) static void nfs_inode_init_regular(struct nfs_inode *nfsi) { atomic_long_set(&nfsi->nrequests, 0); + atomic_long_set(&nfsi->redirtied_pages, 0); INIT_LIST_HEAD(&nfsi->commit_info.list); atomic_long_set(&nfsi->commit_info.ncommit, 0); atomic_set(&nfsi->commit_info.rpcs_out, 0); @@ -564,8 +557,6 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) inode->i_gid = fattr->gid; else if (fattr_supported & NFS_ATTR_FATTR_GROUP) nfs_set_cache_invalid(inode, NFS_INO_INVALID_OTHER); - if (nfs_server_capable(inode, NFS_CAP_XATTR)) - nfs_set_cache_invalid(inode, NFS_INO_INVALID_XATTR); if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED) inode->i_blocks = fattr->du.nfs2.blocks; else if (fattr_supported & NFS_ATTR_FATTR_BLOCKS_USED && @@ -785,26 +776,32 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, } EXPORT_SYMBOL_GPL(nfs_setattr_update_inode); -static void nfs_readdirplus_parent_cache_miss(struct dentry *dentry) +/* + * Don't request help from readdirplus if the file is being written to, + * or if attribute caching is turned off + */ +static bool nfs_getattr_readdirplus_enable(const struct inode *inode) { - struct dentry *parent; + return nfs_server_capable(inode, NFS_CAP_READDIRPLUS) && + !nfs_have_writebacks(inode) && NFS_MAXATTRTIMEO(inode) > 5 * HZ; +} - if (!nfs_server_capable(d_inode(dentry), NFS_CAP_READDIRPLUS)) - return; - parent = dget_parent(dentry); - nfs_force_use_readdirplus(d_inode(parent)); - dput(parent); +static void nfs_readdirplus_parent_cache_miss(struct dentry *dentry) +{ + if (!IS_ROOT(dentry)) { + struct dentry *parent = dget_parent(dentry); + nfs_readdir_record_entry_cache_miss(d_inode(parent)); + dput(parent); + } } static void nfs_readdirplus_parent_cache_hit(struct dentry *dentry) { - struct dentry *parent; - - if (!nfs_server_capable(d_inode(dentry), NFS_CAP_READDIRPLUS)) - return; - parent = dget_parent(dentry); - nfs_advise_use_readdirplus(d_inode(parent)); - dput(parent); + if (!IS_ROOT(dentry)) { + struct dentry *parent = dget_parent(dentry); + nfs_readdir_record_entry_cache_hit(d_inode(parent)); + dput(parent); + } } static u32 nfs_get_valid_attrmask(struct inode *inode) @@ -840,6 +837,7 @@ int nfs_getattr(struct user_namespace *mnt_userns, const struct path *path, int err = 0; bool force_sync = query_flags & AT_STATX_FORCE_SYNC; bool do_update = false; + bool readdirplus_enabled = nfs_getattr_readdirplus_enable(inode); trace_nfs_getattr_enter(inode); @@ -848,17 +846,15 @@ int nfs_getattr(struct user_namespace *mnt_userns, const struct path *path, STATX_INO | STATX_SIZE | STATX_BLOCKS; if ((query_flags & AT_STATX_DONT_SYNC) && !force_sync) { - nfs_readdirplus_parent_cache_hit(path->dentry); + if (readdirplus_enabled) + nfs_readdirplus_parent_cache_hit(path->dentry); goto out_no_revalidate; } /* Flush out writes to the server in order to update c/mtime. */ - if ((request_mask & (STATX_CTIME|STATX_MTIME)) && - S_ISREG(inode->i_mode)) { - err = filemap_write_and_wait(inode->i_mapping); - if (err) - goto out; - } + if ((request_mask & (STATX_CTIME | STATX_MTIME)) && + S_ISREG(inode->i_mode)) + filemap_write_and_wait(inode->i_mapping); /* * We may force a getattr if the user cares about atime. @@ -901,15 +897,12 @@ int nfs_getattr(struct user_namespace *mnt_userns, const struct path *path, do_update |= cache_validity & NFS_INO_INVALID_BLOCKS; if (do_update) { - /* Update the attribute cache */ - if (!(server->flags & NFS_MOUNT_NOAC)) + if (readdirplus_enabled) nfs_readdirplus_parent_cache_miss(path->dentry); - else - nfs_readdirplus_parent_cache_hit(path->dentry); err = __nfs_revalidate_inode(server, inode); if (err) goto out; - } else + } else if (readdirplus_enabled) nfs_readdirplus_parent_cache_hit(path->dentry); out_no_revalidate: /* Only return attributes that were revalidated. */ @@ -955,7 +948,7 @@ struct nfs_lock_context *nfs_get_lock_context(struct nfs_open_context *ctx) res = __nfs_find_lock_context(ctx); rcu_read_unlock(); if (res == NULL) { - new = kmalloc(sizeof(*new), GFP_KERNEL); + new = kmalloc(sizeof(*new), GFP_KERNEL_ACCOUNT); if (new == NULL) return ERR_PTR(-ENOMEM); nfs_init_lock_context(new); @@ -1033,7 +1026,7 @@ struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry, { struct nfs_open_context *ctx; - ctx = kmalloc(sizeof(*ctx), GFP_KERNEL); + ctx = kmalloc(sizeof(*ctx), GFP_KERNEL_ACCOUNT); if (!ctx) return ERR_PTR(-ENOMEM); nfs_sb_active(dentry->d_sb); @@ -1183,7 +1176,6 @@ int nfs_open(struct inode *inode, struct file *filp) nfs_fscache_open_file(inode, filp); return 0; } -EXPORT_SYMBOL_GPL(nfs_open); /* * This function is called whenever some part of NFS notices that @@ -1289,6 +1281,7 @@ static int nfs_invalidate_mapping(struct inode *inode, struct address_space *map { int ret; + nfs_fscache_invalidate(inode, 0); if (mapping->nrpages != 0) { if (S_ISREG(inode->i_mode)) { ret = nfs_sync_mapping(mapping); @@ -1300,7 +1293,6 @@ static int nfs_invalidate_mapping(struct inode *inode, struct address_space *map return ret; } nfs_inc_stats(inode, NFSIOS_DATAINVALIDATE); - nfs_fscache_wait_on_invalidate(inode); dfprintk(PAGECACHE, "NFS: (%s/%Lu) data cache invalidated\n", inode->i_sb->s_id, @@ -1335,7 +1327,8 @@ int nfs_clear_invalid_mapping(struct address_space *mapping) */ for (;;) { ret = wait_on_bit_action(bitlock, NFS_INO_INVALIDATING, - nfs_wait_bit_killable, TASK_KILLABLE); + nfs_wait_bit_killable, + TASK_KILLABLE|TASK_FREEZABLE_UNSAFE); if (ret) goto out; spin_lock(&inode->i_lock); @@ -1586,7 +1579,7 @@ struct nfs_fattr *nfs_alloc_fattr(void) { struct nfs_fattr *fattr; - fattr = kmalloc(sizeof(*fattr), GFP_NOFS); + fattr = kmalloc(sizeof(*fattr), GFP_KERNEL); if (fattr != NULL) { nfs_fattr_init(fattr); fattr->label = NULL; @@ -1602,7 +1595,7 @@ struct nfs_fattr *nfs_alloc_fattr_with_label(struct nfs_server *server) if (!fattr) return NULL; - fattr->label = nfs4_label_alloc(server, GFP_NOFS); + fattr->label = nfs4_label_alloc(server, GFP_KERNEL); if (IS_ERR(fattr->label)) { kfree(fattr); return NULL; @@ -1616,7 +1609,7 @@ struct nfs_fh *nfs_alloc_fhandle(void) { struct nfs_fh *fh; - fh = kmalloc(sizeof(struct nfs_fh), GFP_NOFS); + fh = kmalloc(sizeof(struct nfs_fh), GFP_KERNEL); if (fh != NULL) fh->size = 0; return fh; @@ -2241,7 +2234,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) struct inode *nfs_alloc_inode(struct super_block *sb) { struct nfs_inode *nfsi; - nfsi = kmem_cache_alloc(nfs_inode_cachep, GFP_KERNEL); + nfsi = alloc_inode_sb(sb, nfs_inode_cachep, GFP_KERNEL); if (!nfsi) return NULL; nfsi->flags = 0UL; @@ -2274,7 +2267,7 @@ static inline void nfs4_init_once(struct nfs_inode *nfsi) static void init_once(void *foo) { - struct nfs_inode *nfsi = (struct nfs_inode *) foo; + struct nfs_inode *nfsi = foo; inode_init_once(&nfsi->vfs_inode); INIT_LIST_HEAD(&nfsi->open_files); @@ -2374,10 +2367,6 @@ static int __init init_nfs_fs(void) if (err < 0) goto out9; - err = nfs_fscache_register(); - if (err < 0) - goto out8; - err = nfsiod_start(); if (err) goto out7; @@ -2429,8 +2418,6 @@ out5: out6: nfsiod_stop(); out7: - nfs_fscache_unregister(); -out8: unregister_pernet_subsys(&nfs_net_ops); out9: nfs_sysfs_exit(); @@ -2445,7 +2432,6 @@ static void __exit exit_nfs_fs(void) nfs_destroy_readpagecache(); nfs_destroy_inodecache(); nfs_destroy_nfspagecache(); - nfs_fscache_unregister(); unregister_pernet_subsys(&nfs_net_ops); rpc_proc_unregister(&init_net, "nfs"); unregister_nfs_fs(); diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 12f6acb483bb..647fc3f547cb 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -42,6 +42,16 @@ static inline bool nfs_lookup_is_soft_revalidate(const struct dentry *dentry) return true; } +static inline fmode_t flags_to_mode(int flags) +{ + fmode_t res = (__force fmode_t)flags & FMODE_EXEC; + if ((flags & O_ACCMODE) != O_WRONLY) + res |= FMODE_READ; + if ((flags & O_ACCMODE) != O_RDONLY) + res |= FMODE_WRITE; + return res; +} + /* * Note: RFC 1813 doesn't limit the number of auth flavors that * a server can return, so make something up. @@ -59,7 +69,7 @@ static inline bool nfs_lookup_is_soft_revalidate(const struct dentry *dentry) struct nfs_client_initdata { unsigned long init_flags; const char *hostname; /* Hostname of the server */ - const struct sockaddr *addr; /* Address of the server */ + const struct sockaddr_storage *addr; /* Address of the server */ const char *nodename; /* Hostname of the client */ const char *ip_addr; /* IP address of the client */ size_t addrlen; @@ -170,7 +180,7 @@ static inline struct nfs_fs_context *nfs_fc2context(const struct fs_context *fc) /* mount_clnt.c */ struct nfs_mount_request { - struct sockaddr *sap; + struct sockaddr_storage *sap; size_t salen; char *hostname; char *dirpath; @@ -213,7 +223,7 @@ extern void nfs4_server_set_init_caps(struct nfs_server *); extern struct nfs_server *nfs4_create_server(struct fs_context *); extern struct nfs_server *nfs4_create_referral_server(struct fs_context *); extern int nfs4_update_server(struct nfs_server *server, const char *hostname, - struct sockaddr *sap, size_t salen, + struct sockaddr_storage *sap, size_t salen, struct net *net); extern void nfs_free_server(struct nfs_server *server); extern struct nfs_server *nfs_clone_server(struct nfs_server *, @@ -225,7 +235,7 @@ extern int nfs_client_init_status(const struct nfs_client *clp); extern int nfs_wait_client_init_complete(const struct nfs_client *clp); extern void nfs_mark_client_ready(struct nfs_client *clp, int state); extern struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv, - const struct sockaddr *ds_addr, + const struct sockaddr_storage *ds_addr, int ds_addrlen, int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans, @@ -233,7 +243,7 @@ extern struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv, extern struct rpc_clnt *nfs4_find_or_create_ds_client(struct nfs_client *, struct inode *); extern struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv, - const struct sockaddr *ds_addr, int ds_addrlen, + const struct sockaddr_storage *ds_addr, int ds_addrlen, int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans); #ifdef CONFIG_PROC_FS @@ -366,13 +376,14 @@ extern struct nfs_client *nfs_init_client(struct nfs_client *clp, const struct nfs_client_initdata *); /* dir.c */ -extern void nfs_advise_use_readdirplus(struct inode *dir); -extern void nfs_force_use_readdirplus(struct inode *dir); +extern void nfs_readdir_record_entry_cache_hit(struct inode *dir); +extern void nfs_readdir_record_entry_cache_miss(struct inode *dir); extern unsigned long nfs_access_cache_count(struct shrinker *shrink, struct shrink_control *sc); extern unsigned long nfs_access_cache_scan(struct shrinker *shrink, struct shrink_control *sc); struct dentry *nfs_lookup(struct inode *, struct dentry *, unsigned int); +void nfs_d_prune_case_insensitive_aliases(struct inode *inode); int nfs_create(struct user_namespace *, struct inode *, struct dentry *, umode_t, bool); int nfs_mkdir(struct user_namespace *, struct inode *, struct dentry *, @@ -387,6 +398,20 @@ int nfs_mknod(struct user_namespace *, struct inode *, struct dentry *, umode_t, int nfs_rename(struct user_namespace *, struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); +#ifdef CONFIG_NFS_V4_2 +static inline __u32 nfs_access_xattr_mask(const struct nfs_server *server) +{ + if (!(server->caps & NFS_CAP_XATTR)) + return 0; + return NFS4_ACCESS_XAREAD | NFS4_ACCESS_XAWRITE | NFS4_ACCESS_XALIST; +} +#else +static inline __u32 nfs_access_xattr_mask(const struct nfs_server *server) +{ + return 0; +} +#endif + /* file.c */ int nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync); loff_t nfs_file_llseek(struct file *, loff_t, int); @@ -410,7 +435,6 @@ extern void nfs_zap_acl_cache(struct inode *inode); extern void nfs_set_cache_invalid(struct inode *inode, unsigned long flags); extern bool nfs_check_cache_invalid(struct inode *, unsigned long); extern int nfs_wait_bit_killable(struct wait_bit_key *key, int mode); -extern int nfs_wait_atomic_killable(atomic_t *p, unsigned int mode); /* super.c */ extern const struct super_operations nfs_sops; @@ -478,7 +502,6 @@ extern void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, const struct nfs_pgio_completion_ops *compl_ops); extern void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio); extern void nfs_commit_free(struct nfs_commit_data *p); -extern void nfs_write_prepare(struct rpc_task *task, void *calldata); extern void nfs_commit_prepare(struct rpc_task *task, void *calldata); extern int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data, @@ -553,8 +576,10 @@ void nfs_clear_pnfs_ds_commit_verifiers(struct pnfs_ds_commit_info *cinfo) #endif #ifdef CONFIG_MIGRATION -extern int nfs_migrate_page(struct address_space *, - struct page *, struct page *, enum migrate_mode); +int nfs_migrate_folio(struct address_space *, struct folio *dst, + struct folio *src, enum migrate_mode); +#else +#define nfs_migrate_folio NULL #endif static inline int @@ -572,6 +597,38 @@ nfs_write_match_verf(const struct nfs_writeverf *verf, !nfs_write_verifier_cmp(&req->wb_verf, &verf->verifier); } +static inline gfp_t nfs_io_gfp_mask(void) +{ + if (current->flags & PF_WQ_WORKER) + return GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN; + return GFP_KERNEL; +} + +/* + * Special version of should_remove_suid() that ignores capabilities. + */ +static inline int nfs_should_remove_suid(const struct inode *inode) +{ + umode_t mode = inode->i_mode; + int kill = 0; + + /* suid always must be killed */ + if (unlikely(mode & S_ISUID)) + kill = ATTR_KILL_SUID; + + /* + * sgid without any exec bits is just a mandatory locking mark; leave + * it alone. If some exec bits are set, it's a real sgid; kill it. + */ + if (unlikely((mode & S_ISGID) && (mode & S_IXGRP))) + kill |= ATTR_KILL_SGID; + + if (unlikely(kill && S_ISREG(mode))) + return kill; + + return 0; +} + /* unlink.c */ extern struct rpc_task * nfs_async_rename(struct inode *old_dir, struct inode *new_dir, @@ -673,6 +730,24 @@ unsigned long nfs_block_size(unsigned long bsize, unsigned char *nrbitsp) } /* + * Compute and set NFS server rsize / wsize + */ +static inline +unsigned long nfs_io_size(unsigned long iosize, enum xprt_transports proto) +{ + if (iosize < NFS_MIN_FILE_IO_SIZE) + iosize = NFS_DEF_FILE_IO_SIZE; + else if (iosize >= NFS_MAX_FILE_IO_SIZE) + iosize = NFS_MAX_FILE_IO_SIZE; + else + iosize = iosize & PAGE_MASK; + + if (proto == XPRT_TRANSPORT_UDP) + return nfs_block_bits(iosize, NULL); + return iosize; +} + +/* * Determine the maximum file size for a superblock */ static inline @@ -809,6 +884,7 @@ static inline bool nfs_error_is_fatal_on_server(int err) case 0: case -ERESTARTSYS: case -EINTR: + case -ENOMEM: return false; } return nfs_error_is_fatal(err); @@ -818,11 +894,44 @@ static inline bool nfs_error_is_fatal_on_server(int err) * Select between a default port value and a user-specified port value. * If a zero value is set, then autobind will be used. */ -static inline void nfs_set_port(struct sockaddr *sap, int *port, +static inline void nfs_set_port(struct sockaddr_storage *sap, int *port, const unsigned short default_port) { if (*port == NFS_UNSPEC_PORT) *port = default_port; - rpc_set_port(sap, *port); -} + rpc_set_port((struct sockaddr *)sap, *port); +} + +struct nfs_direct_req { + struct kref kref; /* release manager */ + + /* I/O parameters */ + struct nfs_open_context *ctx; /* file open context info */ + struct nfs_lock_context *l_ctx; /* Lock context info */ + struct kiocb * iocb; /* controlling i/o request */ + struct inode * inode; /* target file of i/o */ + + /* completion state */ + atomic_t io_count; /* i/os we're waiting for */ + spinlock_t lock; /* protect completion state */ + + loff_t io_start; /* Start offset for I/O */ + ssize_t count, /* bytes actually processed */ + max_count, /* max expected count */ + bytes_left, /* bytes left to be sent */ + error; /* any reported error */ + struct completion completion; /* wait for i/o completion */ + + /* commit state */ + struct nfs_mds_commit_info mds_cinfo; /* Storage for cinfo */ + struct pnfs_ds_commit_info ds_cinfo; /* Storage for cinfo */ + struct work_struct work; + int flags; + /* for write */ +#define NFS_ODIRECT_DO_COMMIT (1) /* an unstable reply was received */ +#define NFS_ODIRECT_RESCHED_WRITES (2) /* write verification failed */ + /* for read */ +#define NFS_ODIRECT_SHOULD_DIRTY (3) /* dirty user-space page after read */ +#define NFS_ODIRECT_DONE INT_MAX /* write verification failed */ +}; diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c index c5e3b6b3366a..68e76b626371 100644 --- a/fs/nfs/mount_clnt.c +++ b/fs/nfs/mount_clnt.c @@ -158,7 +158,7 @@ int nfs_mount(struct nfs_mount_request *info, int timeo, int retrans) struct rpc_create_args args = { .net = info->net, .protocol = info->protocol, - .address = info->sap, + .address = (struct sockaddr *)info->sap, .addrsize = info->salen, .timeout = &mnt_timeout, .servername = info->hostname, @@ -245,7 +245,7 @@ void nfs_umount(const struct nfs_mount_request *info) struct rpc_create_args args = { .net = info->net, .protocol = IPPROTO_UDP, - .address = info->sap, + .address = (struct sockaddr *)info->sap, .addrsize = info->salen, .timeout = &nfs_umnt_timeout, .servername = info->hostname, diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index 3295af4110f1..2f336ace7555 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -175,7 +175,7 @@ struct vfsmount *nfs_d_automount(struct path *path) } /* for submounts we want the same server; referrals will reassign */ - memcpy(&ctx->nfs_server.address, &client->cl_addr, client->cl_addrlen); + memcpy(&ctx->nfs_server._address, &client->cl_addr, client->cl_addrlen); ctx->nfs_server.addrlen = client->cl_addrlen; ctx->nfs_server.port = server->port; diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c index 7fba7711e6b3..05c3b4b2b3dd 100644 --- a/fs/nfs/nfs2xdr.c +++ b/fs/nfs/nfs2xdr.c @@ -949,13 +949,12 @@ int nfs2_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, error = decode_filename_inline(xdr, &entry->name, &entry->len); if (unlikely(error)) - return error; + return -EAGAIN; /* * The type (size and byte order) of nfscookie isn't defined in * RFC 1094. This implementation assumes that it's an XDR uint32. */ - entry->prev_cookie = entry->cookie; p = xdr_inline_decode(xdr, 4); if (unlikely(!p)) return -EAGAIN; diff --git a/fs/nfs/nfs3client.c b/fs/nfs/nfs3client.c index 5601e47360c2..669cda757a5c 100644 --- a/fs/nfs/nfs3client.c +++ b/fs/nfs/nfs3client.c @@ -78,7 +78,7 @@ struct nfs_server *nfs3_clone_server(struct nfs_server *source, * the MDS. */ struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv, - const struct sockaddr *ds_addr, int ds_addrlen, + const struct sockaddr_storage *ds_addr, int ds_addrlen, int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans) { struct rpc_timeout ds_timeout; @@ -98,7 +98,7 @@ struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv, char buf[INET6_ADDRSTRLEN + 1]; /* fake a hostname because lockd wants it */ - if (rpc_ntop(ds_addr, buf, sizeof(buf)) <= 0) + if (rpc_ntop((struct sockaddr *)ds_addr, buf, sizeof(buf)) <= 0) return ERR_PTR(-EINVAL); cl_init.hostname = buf; @@ -108,7 +108,6 @@ struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv, if (mds_srv->flags & NFS_MOUNT_NORESVPORT) __set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags); - __set_bit(NFS_CS_NOPING, &cl_init.init_flags); __set_bit(NFS_CS_DS, &cl_init.init_flags); /* Use the MDS nfs_client cl_ipaddr. */ diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index 7100514d306b..2e7579626cf0 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -36,7 +36,8 @@ nfs3_rpc_wrapper(struct rpc_clnt *clnt, struct rpc_message *msg, int flags) res = rpc_call_sync(clnt, msg, flags); if (res != -EJUKEBOX) break; - freezable_schedule_timeout_killable_unsafe(NFS_JUKEBOX_RETRY_TIME); + __set_current_state(TASK_KILLABLE|TASK_FREEZABLE_UNSAFE); + schedule_timeout(NFS_JUKEBOX_RETRY_TIME); res = -ERESTARTSYS; } while (!fatal_signal_pending(current)); return res; @@ -220,7 +221,8 @@ static int nfs3_proc_lookupp(struct inode *inode, struct nfs_fh *fhandle, task_flags); } -static int nfs3_proc_access(struct inode *inode, struct nfs_access_entry *entry) +static int nfs3_proc_access(struct inode *inode, struct nfs_access_entry *entry, + const struct cred *cred) { struct nfs3_accessargs arg = { .fh = NFS_FH(inode), @@ -231,7 +233,7 @@ static int nfs3_proc_access(struct inode *inode, struct nfs_access_entry *entry) .rpc_proc = &nfs3_procedures[NFS3PROC_ACCESS], .rpc_argp = &arg, .rpc_resp = &res, - .rpc_cred = entry->cred, + .rpc_cred = cred, }; int status = -ENOMEM; diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index 9274c9c5efea..3b0b650c9c5a 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -1261,6 +1261,8 @@ static void nfs3_xdr_enc_readdir3args(struct rpc_rqst *req, static void encode_readdirplus3args(struct xdr_stream *xdr, const struct nfs3_readdirargs *args) { + uint32_t dircount = args->count; + uint32_t maxcount = args->count; __be32 *p; encode_nfs_fh3(xdr, args->fh); @@ -1273,9 +1275,8 @@ static void encode_readdirplus3args(struct xdr_stream *xdr, * readdirplus: need dircount + buffer size. * We just make sure we make dircount big enough */ - *p++ = cpu_to_be32(args->count >> 3); - - *p = cpu_to_be32(args->count); + *p++ = cpu_to_be32(dircount); + *p = cpu_to_be32(maxcount); } static void nfs3_xdr_enc_readdirplus3args(struct rpc_rqst *req, @@ -1967,7 +1968,6 @@ int nfs3_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, bool plus) { struct user_namespace *userns = rpc_userns(entry->server->client); - struct nfs_entry old = *entry; __be32 *p; int error; u64 new_cookie; @@ -1987,15 +1987,15 @@ int nfs3_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, error = decode_fileid3(xdr, &entry->ino); if (unlikely(error)) - return error; + return -EAGAIN; error = decode_inline_filename3(xdr, &entry->name, &entry->len); if (unlikely(error)) - return error; + return -EAGAIN; error = decode_cookie3(xdr, &new_cookie); if (unlikely(error)) - return error; + return -EAGAIN; entry->d_type = DT_UNKNOWN; @@ -2003,7 +2003,7 @@ int nfs3_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, entry->fattr->valid = 0; error = decode_post_op_attr(xdr, entry->fattr, userns); if (unlikely(error)) - return error; + return -EAGAIN; if (entry->fattr->valid & NFS_ATTR_FATTR_V3) entry->d_type = nfs_umode_to_dtype(entry->fattr->mode); @@ -2018,24 +2018,15 @@ int nfs3_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, return -EAGAIN; if (*p != xdr_zero) { error = decode_nfs_fh3(xdr, entry->fh); - if (unlikely(error)) { - if (error == -E2BIG) - goto out_truncated; - return error; - } + if (unlikely(error)) + return -EAGAIN; } else zero_nfs_fh3(entry->fh); } - entry->prev_cookie = entry->cookie; entry->cookie = new_cookie; return 0; - -out_truncated: - dprintk("NFS: directory entry contains invalid file handle\n"); - *entry = old; - return -EAGAIN; } /* @@ -2228,6 +2219,7 @@ static int decode_fsinfo3resok(struct xdr_stream *xdr, /* ignore properties */ result->lease_time = 0; result->change_attr_type = NFS4_CHANGE_TYPE_IS_UNDEFINED; + result->xattr_support = 0; return 0; } diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 8b21ff1be717..ecb428512fe1 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -46,7 +46,7 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, { struct inode *inode = file_inode(filep); struct nfs_server *server = NFS_SERVER(inode); - u32 bitmask[3]; + u32 bitmask[NFS_BITMASK_SZ]; struct nfs42_falloc_args args = { .falloc_fh = NFS_FH(inode), .falloc_offset = offset, @@ -69,9 +69,8 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, return status; } - memcpy(bitmask, server->cache_consistency_bitmask, sizeof(bitmask)); - if (server->attr_bitmask[1] & FATTR4_WORD1_SPACE_USED) - bitmask[1] |= FATTR4_WORD1_SPACE_USED; + nfs4_bitmask_set(bitmask, server->cache_consistency_bitmask, inode, + NFS_INO_INVALID_BLOCKS); res.falloc_fattr = nfs_alloc_fattr(); if (!res.falloc_fattr) @@ -79,10 +78,15 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, status = nfs4_call_sync(server->client, server, msg, &args.seq_args, &res.seq_res, 0); - if (status == 0) + if (status == 0) { + if (nfs_should_remove_suid(inode)) { + spin_lock(&inode->i_lock); + nfs_set_cache_invalid(inode, NFS_INO_INVALID_MODE); + spin_unlock(&inode->i_lock); + } status = nfs_post_op_update_inode_force_wcc(inode, res.falloc_fattr); - + } if (msg->rpc_proc == &nfs4_procedures[NFSPROC4_CLNT_ALLOCATE]) trace_nfs4_fallocate(inode, &args, status); else @@ -176,28 +180,27 @@ static int handle_async_copy(struct nfs42_copy_res *res, nfs4_stateid *src_stateid, bool *restart) { - struct nfs4_copy_state *copy, *tmp_copy; + struct nfs4_copy_state *copy, *tmp_copy = NULL, *iter; int status = NFS4_OK; - bool found_pending = false; struct nfs_open_context *dst_ctx = nfs_file_open_context(dst); struct nfs_open_context *src_ctx = nfs_file_open_context(src); - copy = kzalloc(sizeof(struct nfs4_copy_state), GFP_NOFS); + copy = kzalloc(sizeof(struct nfs4_copy_state), GFP_KERNEL); if (!copy) return -ENOMEM; spin_lock(&dst_server->nfs_client->cl_lock); - list_for_each_entry(tmp_copy, + list_for_each_entry(iter, &dst_server->nfs_client->pending_cb_stateids, copies) { - if (memcmp(&res->write_res.stateid, &tmp_copy->stateid, + if (memcmp(&res->write_res.stateid, &iter->stateid, NFS4_STATEID_SIZE)) continue; - found_pending = true; - list_del(&tmp_copy->copies); + tmp_copy = iter; + list_del(&iter->copies); break; } - if (found_pending) { + if (tmp_copy) { spin_unlock(&dst_server->nfs_client->cl_lock); kfree(copy); copy = tmp_copy; @@ -255,7 +258,7 @@ static int process_copy_commit(struct file *dst, loff_t pos_dst, struct nfs_commitres cres; int status = -ENOMEM; - cres.verf = kzalloc(sizeof(struct nfs_writeverf), GFP_NOFS); + cres.verf = kzalloc(sizeof(struct nfs_writeverf), GFP_KERNEL); if (!cres.verf) goto out; @@ -338,7 +341,7 @@ static ssize_t _nfs42_proc_copy(struct file *src, return status; } } - status = nfs_filemap_write_and_wait_range(file_inode(src)->i_mapping, + status = nfs_filemap_write_and_wait_range(src->f_mapping, pos_src, pos_src + (loff_t)count - 1); if (status) return status; @@ -358,7 +361,7 @@ static ssize_t _nfs42_proc_copy(struct file *src, res->commit_res.verf = NULL; if (args->sync) { res->commit_res.verf = - kzalloc(sizeof(struct nfs_writeverf), GFP_NOFS); + kzalloc(sizeof(struct nfs_writeverf), GFP_KERNEL); if (!res->commit_res.verf) return -ENOMEM; } @@ -553,7 +556,7 @@ static int nfs42_do_offload_cancel_async(struct file *dst, if (!(dst_server->caps & NFS_CAP_OFFLOAD_CANCEL)) return -EOPNOTSUPP; - data = kzalloc(sizeof(struct nfs42_offloadcancel_data), GFP_NOFS); + data = kzalloc(sizeof(struct nfs42_offloadcancel_data), GFP_KERNEL); if (data == NULL) return -ENOMEM; @@ -592,8 +595,10 @@ static int _nfs42_proc_copy_notify(struct file *src, struct file *dst, ctx = get_nfs_open_context(nfs_file_open_context(src)); l_ctx = nfs_get_lock_context(ctx); - if (IS_ERR(l_ctx)) - return PTR_ERR(l_ctx); + if (IS_ERR(l_ctx)) { + status = PTR_ERR(l_ctx); + goto out; + } status = nfs4_set_rw_stateid(&args->cna_src_stateid, ctx, l_ctx, FMODE_READ); @@ -601,7 +606,7 @@ static int _nfs42_proc_copy_notify(struct file *src, struct file *dst, if (status) { if (status == -EAGAIN) status = -NFS4ERR_BAD_STATEID; - return status; + goto out; } status = nfs4_call_sync(src_server->client, src_server, &msg, @@ -610,6 +615,7 @@ static int _nfs42_proc_copy_notify(struct file *src, struct file *dst, if (status == -ENOTSUPP) src_server->caps &= ~NFS_CAP_COPY_NOTIFY; +out: put_nfs_open_context(nfs_file_open_context(src)); return status; } @@ -627,7 +633,7 @@ int nfs42_proc_copy_notify(struct file *src, struct file *dst, if (!(src_server->caps & NFS_CAP_COPY_NOTIFY)) return -EOPNOTSUPP; - args = kzalloc(sizeof(struct nfs42_copy_notify_args), GFP_NOFS); + args = kzalloc(sizeof(struct nfs42_copy_notify_args), GFP_KERNEL); if (args == NULL) return -ENOMEM; @@ -1015,7 +1021,7 @@ int nfs42_proc_layouterror(struct pnfs_layout_segment *lseg, return -EOPNOTSUPP; if (n > NFS42_LAYOUTERROR_MAX) return -EINVAL; - data = nfs42_alloc_layouterror_data(lseg, GFP_NOFS); + data = nfs42_alloc_layouterror_data(lseg, nfs_io_gfp_mask()); if (!data) return -ENOMEM; for (i = 0; i < n; i++) { @@ -1044,13 +1050,14 @@ static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f, struct inode *src_inode = file_inode(src_f); struct inode *dst_inode = file_inode(dst_f); struct nfs_server *server = NFS_SERVER(dst_inode); + __u32 dst_bitmask[NFS_BITMASK_SZ]; struct nfs42_clone_args args = { .src_fh = NFS_FH(src_inode), .dst_fh = NFS_FH(dst_inode), .src_offset = src_offset, .dst_offset = dst_offset, .count = count, - .dst_bitmask = server->cache_consistency_bitmask, + .dst_bitmask = dst_bitmask, }; struct nfs42_clone_res res = { .server = server, @@ -1079,10 +1086,16 @@ static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f, if (!res.dst_fattr) return -ENOMEM; + nfs4_bitmask_set(dst_bitmask, server->cache_consistency_bitmask, + dst_inode, NFS_INO_INVALID_BLOCKS); + status = nfs4_call_sync(server->client, server, msg, &args.seq_args, &res.seq_res, 0); trace_nfs4_clone(src_inode, dst_inode, &args, status); if (status == 0) { + /* a zero-length count means clone to EOF in src */ + if (count == 0 && res.dst_fattr->valid & NFS_ATTR_FATTR_SIZE) + count = nfs_size_to_loff_t(res.dst_fattr->size) - dst_offset; nfs42_copy_dest_done(dst_inode, dst_offset, count); status = nfs_post_op_update_inode(dst_inode, res.dst_fattr); } @@ -1165,6 +1178,7 @@ static int _nfs42_proc_removexattr(struct inode *inode, const char *name) ret = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 1); + trace_nfs4_removexattr(inode, name, ret); if (!ret) nfs4_update_changeattr(inode, &res.cinfo, timestamp, 0); @@ -1204,6 +1218,7 @@ static int _nfs42_proc_setxattr(struct inode *inode, const char *name, ret = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1); + trace_nfs4_setxattr(inode, name, ret); for (; np > 0; np--) put_page(pages[np - 1]); @@ -1236,6 +1251,7 @@ static ssize_t _nfs42_proc_getxattr(struct inode *inode, const char *name, ret = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 0); + trace_nfs4_getxattr(inode, name, ret); if (ret < 0) return ret; @@ -1307,6 +1323,7 @@ static ssize_t _nfs42_proc_listxattrs(struct inode *inode, void *buf, ret = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 0); + trace_nfs4_listxattr(inode, ret); if (ret >= 0) { ret = res.copied; diff --git a/fs/nfs/nfs42xattr.c b/fs/nfs/nfs42xattr.c index 1c4d2a05b401..76ae11834206 100644 --- a/fs/nfs/nfs42xattr.c +++ b/fs/nfs/nfs42xattr.c @@ -199,7 +199,7 @@ nfs4_xattr_alloc_entry(const char *name, const void *value, flags = NFS4_XATTR_ENTRY_EXTVAL; } - buf = kmalloc(alloclen, GFP_KERNEL_ACCOUNT | GFP_NOFS); + buf = kmalloc(alloclen, GFP_KERNEL); if (buf == NULL) return NULL; entry = (struct nfs4_xattr_entry *)buf; @@ -213,7 +213,7 @@ nfs4_xattr_alloc_entry(const char *name, const void *value, if (flags & NFS4_XATTR_ENTRY_EXTVAL) { - valp = kvmalloc(len, GFP_KERNEL_ACCOUNT | GFP_NOFS); + valp = kvmalloc(len, GFP_KERNEL); if (valp == NULL) { kfree(buf); return NULL; @@ -289,8 +289,7 @@ nfs4_xattr_alloc_cache(void) { struct nfs4_xattr_cache *cache; - cache = kmem_cache_alloc(nfs4_xattr_cache_cachep, - GFP_KERNEL_ACCOUNT | GFP_NOFS); + cache = kmem_cache_alloc(nfs4_xattr_cache_cachep, GFP_KERNEL); if (cache == NULL) return NULL; @@ -982,7 +981,7 @@ nfs4_xattr_entry_count(struct shrinker *shrink, struct shrink_control *sc) static void nfs4_xattr_cache_init_once(void *p) { - struct nfs4_xattr_cache *cache = (struct nfs4_xattr_cache *)p; + struct nfs4_xattr_cache *cache = p; spin_lock_init(&cache->listxattr_lock); atomic_long_set(&cache->nent, 0); @@ -998,7 +997,7 @@ int __init nfs4_xattr_cache_init(void) nfs4_xattr_cache_cachep = kmem_cache_create("nfs4_xattr_cache_cache", sizeof(struct nfs4_xattr_cache), 0, - (SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|SLAB_ACCOUNT), + (SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD), nfs4_xattr_cache_init_once); if (nfs4_xattr_cache_cachep == NULL) return -ENOMEM; @@ -1018,15 +1017,16 @@ int __init nfs4_xattr_cache_init(void) if (ret) goto out2; - ret = register_shrinker(&nfs4_xattr_cache_shrinker); + ret = register_shrinker(&nfs4_xattr_cache_shrinker, "nfs-xattr_cache"); if (ret) goto out1; - ret = register_shrinker(&nfs4_xattr_entry_shrinker); + ret = register_shrinker(&nfs4_xattr_entry_shrinker, "nfs-xattr_entry"); if (ret) goto out; - ret = register_shrinker(&nfs4_xattr_large_entry_shrinker); + ret = register_shrinker(&nfs4_xattr_large_entry_shrinker, + "nfs-xattr_large_entry"); if (!ret) return 0; diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c index 271e5f92ed01..fe1aeb0f048f 100644 --- a/fs/nfs/nfs42xdr.c +++ b/fs/nfs/nfs42xdr.c @@ -569,6 +569,14 @@ static int decode_listxattrs(struct xdr_stream *xdr, */ if (status == -ETOOSMALL) status = -ERANGE; + /* + * Special case: for LISTXATTRS, NFS4ERR_NOXATTR + * should be translated to success with zero-length reply. + */ + if (status == -ENODATA) { + res->eof = true; + status = 0; + } goto out; } @@ -1025,82 +1033,95 @@ static int decode_deallocate(struct xdr_stream *xdr, struct nfs42_falloc_res *re return decode_op_hdr(xdr, OP_DEALLOCATE); } -static int decode_read_plus_data(struct xdr_stream *xdr, - struct nfs_pgio_args *args, - struct nfs_pgio_res *res) -{ - uint32_t count, recvd; +struct read_plus_segment { + enum data_content4 type; uint64_t offset; - __be32 *p; - - p = xdr_inline_decode(xdr, 8 + 4); - if (!p) - return 1; + union { + struct { + uint64_t length; + } hole; + + struct { + uint32_t length; + unsigned int from; + } data; + }; +}; - p = xdr_decode_hyper(p, &offset); - count = be32_to_cpup(p); - recvd = xdr_align_data(xdr, res->count, xdr_align_size(count)); - if (recvd > count) - recvd = count; - if (res->count + recvd > args->count) { - if (args->count > res->count) - res->count += args->count - res->count; - return 1; - } - res->count += recvd; - if (count > recvd) - return 1; - return 0; +static inline uint64_t read_plus_segment_length(struct read_plus_segment *seg) +{ + return seg->type == NFS4_CONTENT_DATA ? seg->data.length : seg->hole.length; } -static int decode_read_plus_hole(struct xdr_stream *xdr, - struct nfs_pgio_args *args, - struct nfs_pgio_res *res, uint32_t *eof) +static int decode_read_plus_segment(struct xdr_stream *xdr, + struct read_plus_segment *seg) { - uint64_t offset, length, recvd; __be32 *p; - p = xdr_inline_decode(xdr, 8 + 8); + p = xdr_inline_decode(xdr, 4); if (!p) - return 1; - - p = xdr_decode_hyper(p, &offset); - p = xdr_decode_hyper(p, &length); - if (offset != args->offset + res->count) { - /* Server returned an out-of-sequence extent */ - if (offset > args->offset + res->count || - offset + length < args->offset + res->count) { - dprintk("NFS: server returned out of sequence extent: " - "offset/size = %llu/%llu != expected %llu\n", - (unsigned long long)offset, - (unsigned long long)length, - (unsigned long long)(args->offset + - res->count)); - return 1; - } - length -= args->offset + res->count - offset; - } - if (length + res->count > args->count) { - *eof = 0; - if (unlikely(res->count >= args->count)) - return 1; - length = args->count - res->count; - } - recvd = xdr_expand_hole(xdr, res->count, length); - res->count += recvd; + return -EIO; + seg->type = be32_to_cpup(p++); + + p = xdr_inline_decode(xdr, seg->type == NFS4_CONTENT_DATA ? 12 : 16); + if (!p) + return -EIO; + p = xdr_decode_hyper(p, &seg->offset); - if (recvd < length) - return 1; + if (seg->type == NFS4_CONTENT_DATA) { + struct xdr_buf buf; + uint32_t len = be32_to_cpup(p); + + seg->data.length = len; + seg->data.from = xdr_stream_pos(xdr); + + if (!xdr_stream_subsegment(xdr, &buf, xdr_align_size(len))) + return -EIO; + } else if (seg->type == NFS4_CONTENT_HOLE) { + xdr_decode_hyper(p, &seg->hole.length); + } else + return -EINVAL; return 0; } +static int process_read_plus_segment(struct xdr_stream *xdr, + struct nfs_pgio_args *args, + struct nfs_pgio_res *res, + struct read_plus_segment *seg) +{ + unsigned long offset = seg->offset; + unsigned long length = read_plus_segment_length(seg); + unsigned int bufpos; + + if (offset + length < args->offset) + return 0; + else if (offset > args->offset + args->count) { + res->eof = 0; + return 0; + } else if (offset < args->offset) { + length -= (args->offset - offset); + offset = args->offset; + } else if (offset + length > args->offset + args->count) { + length = (args->offset + args->count) - offset; + res->eof = 0; + } + + bufpos = xdr->buf->head[0].iov_len + (offset - args->offset); + if (seg->type == NFS4_CONTENT_HOLE) + return xdr_stream_zero(xdr, bufpos, length); + else + return xdr_stream_move_subsegment(xdr, seg->data.from, bufpos, length); +} + static int decode_read_plus(struct xdr_stream *xdr, struct nfs_pgio_res *res) { struct nfs_pgio_header *hdr = container_of(res, struct nfs_pgio_header, res); struct nfs_pgio_args *args = &hdr->args; - uint32_t eof, segments, type; + uint32_t segments; + struct read_plus_segment *segs; int status, i; + char scratch_buf[16]; __be32 *p; status = decode_op_hdr(xdr, OP_READ_PLUS); @@ -1112,38 +1133,31 @@ static int decode_read_plus(struct xdr_stream *xdr, struct nfs_pgio_res *res) return -EIO; res->count = 0; - eof = be32_to_cpup(p++); + res->eof = be32_to_cpup(p++); segments = be32_to_cpup(p++); if (segments == 0) - goto out; - - for (i = 0; i < segments; i++) { - p = xdr_inline_decode(xdr, 4); - if (!p) - goto early_out; + return status; - type = be32_to_cpup(p++); - if (type == NFS4_CONTENT_DATA) - status = decode_read_plus_data(xdr, args, res); - else if (type == NFS4_CONTENT_HOLE) - status = decode_read_plus_hole(xdr, args, res, &eof); - else - return -EINVAL; + segs = kmalloc_array(segments, sizeof(*segs), GFP_KERNEL); + if (!segs) + return -ENOMEM; + xdr_set_scratch_buffer(xdr, &scratch_buf, 32); + status = -EIO; + for (i = 0; i < segments; i++) { + status = decode_read_plus_segment(xdr, &segs[i]); if (status < 0) - return status; - if (status > 0) - goto early_out; + goto out; } + xdr_set_pagelen(xdr, xdr_align_size(args->count)); + for (i = segments; i > 0; i--) + res->count += process_read_plus_segment(xdr, args, res, &segs[i-1]); + status = 0; + out: - res->eof = eof; - return 0; -early_out: - if (unlikely(!i)) - return -EIO; - res->eof = 0; - return 0; + kfree(segs); + return status; } static int decode_seek(struct xdr_stream *xdr, struct nfs42_seek_res *res) diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index ed5eaca6801e..cfef738d765e 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -42,6 +42,7 @@ enum nfs4_client_state { NFS4CLNT_LEASE_MOVED, NFS4CLNT_DELEGATION_EXPIRED, NFS4CLNT_RUN_MANAGER, + NFS4CLNT_MANAGER_AVAILABLE, NFS4CLNT_RECALL_RUNNING, NFS4CLNT_RECALL_ANY_LAYOUT_READ, NFS4CLNT_RECALL_ANY_LAYOUT_RW, @@ -260,8 +261,8 @@ struct nfs4_state_maintenance_ops { }; struct nfs4_mig_recovery_ops { - int (*get_locations)(struct inode *, struct nfs4_fs_locations *, - struct page *, const struct cred *); + int (*get_locations)(struct nfs_server *, struct nfs_fh *, + struct nfs4_fs_locations *, struct page *, const struct cred *); int (*fsid_present)(struct inode *, const struct cred *); }; @@ -280,7 +281,8 @@ struct rpc_clnt *nfs4_negotiate_security(struct rpc_clnt *, struct inode *, int nfs4_submount(struct fs_context *, struct nfs_server *); int nfs4_replace_transport(struct nfs_server *server, const struct nfs4_fs_locations *locations); - +size_t nfs_parse_server_name(char *string, size_t len, struct sockaddr_storage *ss, + size_t salen, struct net *net, int port); /* nfs4proc.c */ extern int nfs4_handle_exception(struct nfs_server *, int, struct nfs4_exception *); extern int nfs4_async_handle_error(struct rpc_task *task, @@ -302,8 +304,9 @@ extern int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait); extern int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle); extern int nfs4_proc_fs_locations(struct rpc_clnt *, struct inode *, const struct qstr *, struct nfs4_fs_locations *, struct page *); -extern int nfs4_proc_get_locations(struct inode *, struct nfs4_fs_locations *, - struct page *page, const struct cred *); +extern int nfs4_proc_get_locations(struct nfs_server *, struct nfs_fh *, + struct nfs4_fs_locations *, + struct page *page, const struct cred *); extern int nfs4_proc_fsid_present(struct inode *, const struct cred *); extern struct rpc_clnt *nfs4_proc_lookup_mountpoint(struct inode *, struct dentry *, @@ -315,6 +318,8 @@ extern int nfs4_set_rw_stateid(nfs4_stateid *stateid, const struct nfs_open_context *ctx, const struct nfs_lock_context *l_ctx, fmode_t fmode); +extern void nfs4_bitmask_set(__u32 bitmask[], const __u32 src[], + struct inode *inode, unsigned long cache_validity); extern int nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fattr *fattr, struct inode *inode); extern int update_open_stateid(struct nfs4_state *state, @@ -454,7 +459,6 @@ struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *); /* nfs4renewd.c */ extern void nfs4_schedule_state_renewal(struct nfs_client *); -extern void nfs4_renewd_prepare_shutdown(struct nfs_server *); extern void nfs4_kill_renewd(struct nfs_client *); extern void nfs4_renew_state(struct work_struct *); extern void nfs4_set_lease_period(struct nfs_client *clp, unsigned long lease); diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index d8b5a250ca05..d3051b051a56 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -254,7 +254,7 @@ struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *cl_init) goto error; ip_addr = (const char *)buf; } - strlcpy(clp->cl_ipaddr, ip_addr, sizeof(clp->cl_ipaddr)); + strscpy(clp->cl_ipaddr, ip_addr, sizeof(clp->cl_ipaddr)); err = nfs_idmap_new(clp); if (err < 0) { @@ -346,6 +346,7 @@ int nfs40_init_client(struct nfs_client *clp) ret = nfs4_setup_slot_table(tbl, NFS4_MAX_SLOT_TABLE, "NFSv4.0 transport Slot table"); if (ret) { + nfs4_shutdown_slot_table(tbl); kfree(tbl); return ret; } @@ -889,7 +890,7 @@ nfs4_find_client_sessionid(struct net *net, const struct sockaddr *addr, */ static int nfs4_set_client(struct nfs_server *server, const char *hostname, - const struct sockaddr *addr, + const struct sockaddr_storage *addr, const size_t addrlen, const char *ip_addr, int proto, const struct rpc_timeout *timeparms, @@ -924,7 +925,7 @@ static int nfs4_set_client(struct nfs_server *server, __set_bit(NFS_CS_MIGRATION, &cl_init.init_flags); if (test_bit(NFS_MIG_TSM_POSSIBLE, &server->mig_status)) __set_bit(NFS_CS_TSM_POSSIBLE, &cl_init.init_flags); - server->port = rpc_get_port(addr); + server->port = rpc_get_port((struct sockaddr *)addr); /* Allocate or find a client reference we can use */ clp = nfs_get_client(&cl_init); @@ -960,7 +961,7 @@ static int nfs4_set_client(struct nfs_server *server, * the MDS. */ struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv, - const struct sockaddr *ds_addr, int ds_addrlen, + const struct sockaddr_storage *ds_addr, int ds_addrlen, int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans, u32 minor_version) { @@ -980,7 +981,7 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv, }; char buf[INET6_ADDRSTRLEN + 1]; - if (rpc_ntop(ds_addr, buf, sizeof(buf)) <= 0) + if (rpc_ntop((struct sockaddr *)ds_addr, buf, sizeof(buf)) <= 0) return ERR_PTR(-EINVAL); cl_init.hostname = buf; @@ -1148,7 +1149,7 @@ static int nfs4_init_server(struct nfs_server *server, struct fs_context *fc) /* Get a client record */ error = nfs4_set_client(server, ctx->nfs_server.hostname, - &ctx->nfs_server.address, + &ctx->nfs_server._address, ctx->nfs_server.addrlen, ctx->client_address, ctx->nfs_server.protocol, @@ -1161,9 +1162,9 @@ static int nfs4_init_server(struct nfs_server *server, struct fs_context *fc) return error; if (ctx->rsize) - server->rsize = nfs_block_size(ctx->rsize, NULL); + server->rsize = nfs_io_size(ctx->rsize, server->nfs_client->cl_proto); if (ctx->wsize) - server->wsize = nfs_block_size(ctx->wsize, NULL); + server->wsize = nfs_io_size(ctx->wsize, server->nfs_client->cl_proto); server->acregmin = ctx->acregmin * HZ; server->acregmax = ctx->acregmax * HZ; @@ -1238,7 +1239,7 @@ struct nfs_server *nfs4_create_referral_server(struct fs_context *fc) rpc_set_port(&ctx->nfs_server.address, NFS_RDMA_PORT); error = nfs4_set_client(server, ctx->nfs_server.hostname, - &ctx->nfs_server.address, + &ctx->nfs_server._address, ctx->nfs_server.addrlen, parent_client->cl_ipaddr, XPRT_TRANSPORT_RDMA, @@ -1254,7 +1255,7 @@ struct nfs_server *nfs4_create_referral_server(struct fs_context *fc) rpc_set_port(&ctx->nfs_server.address, NFS_PORT); error = nfs4_set_client(server, ctx->nfs_server.hostname, - &ctx->nfs_server.address, + &ctx->nfs_server._address, ctx->nfs_server.addrlen, parent_client->cl_ipaddr, XPRT_TRANSPORT_TCP, @@ -1303,14 +1304,14 @@ error: * Returns zero on success, or a negative errno value. */ int nfs4_update_server(struct nfs_server *server, const char *hostname, - struct sockaddr *sap, size_t salen, struct net *net) + struct sockaddr_storage *sap, size_t salen, struct net *net) { struct nfs_client *clp = server->nfs_client; struct rpc_clnt *clnt = server->client; struct xprt_create xargs = { .ident = clp->cl_proto, .net = net, - .dstaddr = sap, + .dstaddr = (struct sockaddr *)sap, .addrlen = salen, .servername = hostname, }; @@ -1343,8 +1344,11 @@ int nfs4_update_server(struct nfs_server *server, const char *hostname, } nfs_put_client(clp); - if (server->nfs_client->cl_hostname == NULL) + if (server->nfs_client->cl_hostname == NULL) { server->nfs_client->cl_hostname = kstrdup(hostname, GFP_KERNEL); + if (server->nfs_client->cl_hostname == NULL) + return -ENOMEM; + } nfs_server_insert_lists(server); return nfs_probe_server(server, NFS_FH(d_inode(server->super->s_root))); diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index e79ae4cbc395..9eb181287879 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -32,6 +32,7 @@ nfs4_file_open(struct inode *inode, struct file *filp) struct dentry *parent = NULL; struct inode *dir; unsigned openflags = filp->f_flags; + fmode_t f_mode; struct iattr attr; int err; @@ -50,8 +51,9 @@ nfs4_file_open(struct inode *inode, struct file *filp) if (err) return err; + f_mode = filp->f_mode; if ((openflags & O_ACCMODE) == 3) - return nfs_open(inode, filp); + f_mode |= flags_to_mode(openflags); /* We can't create new files here */ openflags &= ~(O_CREAT|O_EXCL); @@ -59,7 +61,7 @@ nfs4_file_open(struct inode *inode, struct file *filp) parent = dget_parent(dentry); dir = d_inode(parent); - ctx = alloc_nfs_open_context(file_dentry(filp), filp->f_mode, filp); + ctx = alloc_nfs_open_context(file_dentry(filp), f_mode, filp); err = PTR_ERR(ctx); if (IS_ERR(ctx)) goto out; @@ -91,6 +93,7 @@ nfs4_file_open(struct inode *inode, struct file *filp) nfs_file_set_open_context(filp, ctx); nfs_fscache_open_file(inode, filp); err = 0; + filp->f_mode |= FMODE_CAN_ODIRECT; out_put_ctx: put_nfs_open_context(ctx); @@ -165,7 +168,7 @@ retry: if (sync) return -EOPNOTSUPP; cn_resp = kzalloc(sizeof(struct nfs42_copy_notify_res), - GFP_NOFS); + GFP_KERNEL); if (unlikely(cn_resp == NULL)) return -ENOMEM; @@ -180,8 +183,8 @@ retry: ret = nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count, nss, cnrs, sync); out: - if (!nfs42_files_from_same_server(file_in, file_out)) - kfree(cn_resp); + kfree(cn_resp); + if (ret == -EAGAIN) goto retry; return ret; @@ -326,7 +329,7 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt, char *read_name = NULL; int len, status = 0; - server = NFS_SERVER(ss_mnt->mnt_root->d_inode); + server = NFS_SB(ss_mnt->mnt_sb); if (!fattr) return ERR_PTR(-ENOMEM); @@ -337,14 +340,19 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt, goto out; } + if (!S_ISREG(fattr->mode)) { + res = ERR_PTR(-EBADF); + goto out; + } + res = ERR_PTR(-ENOMEM); len = strlen(SSC_READ_NAME_BODY) + 16; - read_name = kzalloc(len, GFP_NOFS); + read_name = kzalloc(len, GFP_KERNEL); if (read_name == NULL) goto out; snprintf(read_name, len, SSC_READ_NAME_BODY, read_name_gen++); - r_ino = nfs_fhget(ss_mnt->mnt_root->d_inode->i_sb, src_fh, fattr); + r_ino = nfs_fhget(ss_mnt->mnt_sb, src_fh, fattr); if (IS_ERR(r_ino)) { res = ERR_CAST(r_ino); goto out_free_name; @@ -354,6 +362,7 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt, r_ino->i_fop); if (IS_ERR(filep)) { res = ERR_CAST(filep); + iput(r_ino); goto out_free_name; } diff --git a/fs/nfs/nfs4idmap.c b/fs/nfs/nfs4idmap.c index f331866dd418..e3fdd2f45b01 100644 --- a/fs/nfs/nfs4idmap.c +++ b/fs/nfs/nfs4idmap.c @@ -561,22 +561,20 @@ nfs_idmap_prepare_pipe_upcall(struct idmap *idmap, return true; } -static void -nfs_idmap_complete_pipe_upcall_locked(struct idmap *idmap, int ret) +static void nfs_idmap_complete_pipe_upcall(struct idmap_legacy_upcalldata *data, + int ret) { - struct key *authkey = idmap->idmap_upcall_data->authkey; - - kfree(idmap->idmap_upcall_data); - idmap->idmap_upcall_data = NULL; - complete_request_key(authkey, ret); - key_put(authkey); + complete_request_key(data->authkey, ret); + key_put(data->authkey); + kfree(data); } -static void -nfs_idmap_abort_pipe_upcall(struct idmap *idmap, int ret) +static void nfs_idmap_abort_pipe_upcall(struct idmap *idmap, + struct idmap_legacy_upcalldata *data, + int ret) { - if (idmap->idmap_upcall_data != NULL) - nfs_idmap_complete_pipe_upcall_locked(idmap, ret); + if (cmpxchg(&idmap->idmap_upcall_data, data, NULL) == data) + nfs_idmap_complete_pipe_upcall(data, ret); } static int nfs_idmap_legacy_upcall(struct key *authkey, void *aux) @@ -585,7 +583,7 @@ static int nfs_idmap_legacy_upcall(struct key *authkey, void *aux) struct request_key_auth *rka = get_request_key_auth(authkey); struct rpc_pipe_msg *msg; struct idmap_msg *im; - struct idmap *idmap = (struct idmap *)aux; + struct idmap *idmap = aux; struct key *key = rka->target_key; int ret = -ENOKEY; @@ -613,7 +611,7 @@ static int nfs_idmap_legacy_upcall(struct key *authkey, void *aux) ret = rpc_queue_upcall(idmap->idmap_pipe, msg); if (ret < 0) - nfs_idmap_abort_pipe_upcall(idmap, ret); + nfs_idmap_abort_pipe_upcall(idmap, data, ret); return ret; out2: @@ -669,6 +667,7 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) struct request_key_auth *rka; struct rpc_inode *rpci = RPC_I(file_inode(filp)); struct idmap *idmap = (struct idmap *)rpci->private; + struct idmap_legacy_upcalldata *data; struct key *authkey; struct idmap_msg im; size_t namelen_in; @@ -678,10 +677,11 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) * will have been woken up and someone else may now have used * idmap_key_cons - so after this point we may no longer touch it. */ - if (idmap->idmap_upcall_data == NULL) + data = xchg(&idmap->idmap_upcall_data, NULL); + if (data == NULL) goto out_noupcall; - authkey = idmap->idmap_upcall_data->authkey; + authkey = data->authkey; rka = get_request_key_auth(authkey); if (mlen != sizeof(im)) { @@ -703,18 +703,17 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) if (namelen_in == 0 || namelen_in == IDMAP_NAMESZ) { ret = -EINVAL; goto out; -} + } - ret = nfs_idmap_read_and_verify_message(&im, - &idmap->idmap_upcall_data->idmap_msg, - rka->target_key, authkey); + ret = nfs_idmap_read_and_verify_message(&im, &data->idmap_msg, + rka->target_key, authkey); if (ret >= 0) { key_set_timeout(rka->target_key, nfs_idmap_cache_timeout); ret = mlen; } out: - nfs_idmap_complete_pipe_upcall_locked(idmap, ret); + nfs_idmap_complete_pipe_upcall(data, ret); out_noupcall: return ret; } @@ -728,7 +727,7 @@ idmap_pipe_destroy_msg(struct rpc_pipe_msg *msg) struct idmap *idmap = data->idmap; if (msg->errno) - nfs_idmap_abort_pipe_upcall(idmap, msg->errno); + nfs_idmap_abort_pipe_upcall(idmap, data, msg->errno); } static void @@ -736,8 +735,11 @@ idmap_release_pipe(struct inode *inode) { struct rpc_inode *rpci = RPC_I(inode); struct idmap *idmap = (struct idmap *)rpci->private; + struct idmap_legacy_upcalldata *data; - nfs_idmap_abort_pipe_upcall(idmap, -EPIPE); + data = xchg(&idmap->idmap_upcall_data, NULL); + if (data) + nfs_idmap_complete_pipe_upcall(data, -EPIPE); } int nfs_map_name_to_uid(const struct nfs_server *server, const char *name, size_t namelen, kuid_t *uid) diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c index 873342308dc0..9a98595bb160 100644 --- a/fs/nfs/nfs4namespace.c +++ b/fs/nfs/nfs4namespace.c @@ -164,16 +164,22 @@ static int nfs4_validate_fspath(struct dentry *dentry, return 0; } -static size_t nfs_parse_server_name(char *string, size_t len, - struct sockaddr *sa, size_t salen, struct net *net) +size_t nfs_parse_server_name(char *string, size_t len, struct sockaddr_storage *ss, + size_t salen, struct net *net, int port) { + struct sockaddr *sa = (struct sockaddr *)ss; ssize_t ret; ret = rpc_pton(net, string, len, sa, salen); if (ret == 0) { - ret = nfs_dns_resolve_name(net, string, len, sa, salen); - if (ret < 0) - ret = 0; + ret = rpc_uaddr2sockaddr(net, string, len, sa, salen); + if (ret == 0) { + ret = nfs_dns_resolve_name(net, string, len, ss, salen); + if (ret < 0) + ret = 0; + } + } else if (port) { + rpc_set_port(sa, port); } return ret; } @@ -326,9 +332,9 @@ static int try_location(struct fs_context *fc, ctx->nfs_server.addrlen = nfs_parse_server_name(buf->data, buf->len, - &ctx->nfs_server.address, + &ctx->nfs_server._address, sizeof(ctx->nfs_server._address), - fc->net_ns); + fc->net_ns, 0); if (ctx->nfs_server.addrlen == 0) continue; @@ -412,6 +418,9 @@ static int nfs_do_refmount(struct fs_context *fc, struct rpc_clnt *client) fs_locations = kmalloc(sizeof(struct nfs4_fs_locations), GFP_KERNEL); if (!fs_locations) goto out_free; + fs_locations->fattr = nfs_alloc_fattr(); + if (!fs_locations->fattr) + goto out_free_2; /* Get locations */ dentry = ctx->clone_data.dentry; @@ -422,14 +431,16 @@ static int nfs_do_refmount(struct fs_context *fc, struct rpc_clnt *client) err = nfs4_proc_fs_locations(client, d_inode(parent), &dentry->d_name, fs_locations, page); dput(parent); if (err != 0) - goto out_free_2; + goto out_free_3; err = -ENOENT; if (fs_locations->nlocations <= 0 || fs_locations->fs_path.ncomponents <= 0) - goto out_free_2; + goto out_free_3; err = nfs_follow_referral(fc, fs_locations); +out_free_3: + kfree(fs_locations->fattr); out_free_2: kfree(fs_locations); out_free: @@ -473,14 +484,13 @@ static int nfs4_try_replacing_one_location(struct nfs_server *server, char *page, char *page2, const struct nfs4_fs_location *location) { - const size_t addr_bufsize = sizeof(struct sockaddr_storage); struct net *net = rpc_net_ns(server->client); - struct sockaddr *sap; + struct sockaddr_storage *sap; unsigned int s; size_t salen; int error; - sap = kmalloc(addr_bufsize, GFP_KERNEL); + sap = kmalloc(sizeof(*sap), GFP_KERNEL); if (sap == NULL) return -ENOMEM; @@ -496,10 +506,10 @@ static int nfs4_try_replacing_one_location(struct nfs_server *server, continue; salen = nfs_parse_server_name(buf->data, buf->len, - sap, addr_bufsize, net); + sap, sizeof(*sap), net, 0); if (salen == 0) continue; - rpc_set_port(sap, NFS_PORT); + rpc_set_port((struct sockaddr *)sap, NFS_PORT); error = -ENOMEM; hostname = kmemdup_nul(buf->data, buf->len, GFP_KERNEL); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index ee3bc79f6ca3..86ed5c0142c3 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -108,10 +108,6 @@ static int nfs41_test_stateid(struct nfs_server *, nfs4_stateid *, static int nfs41_free_stateid(struct nfs_server *, const nfs4_stateid *, const struct cred *, bool); #endif -static void nfs4_bitmask_set(__u32 bitmask[NFS4_BITMASK_SZ], - const __u32 *src, struct inode *inode, - struct nfs_server *server, - struct nfs4_label *label); #ifdef CONFIG_NFS_V4_SECURITY_LABEL static inline struct nfs4_label * @@ -367,6 +363,14 @@ static void nfs4_setup_readdir(u64 cookie, __be32 *verifier, struct dentry *dent kunmap_atomic(start); } +static void nfs4_fattr_set_prechange(struct nfs_fattr *fattr, u64 version) +{ + if (!(fattr->valid & NFS_ATTR_FATTR_PRECHANGE)) { + fattr->pre_change_attr = version; + fattr->valid |= NFS_ATTR_FATTR_PRECHANGE; + } +} + static void nfs4_test_and_free_stateid(struct nfs_server *server, nfs4_stateid *stateid, const struct cred *cred) @@ -412,8 +416,8 @@ static int nfs4_delay_killable(long *timeout) { might_sleep(); - freezable_schedule_timeout_killable_unsafe( - nfs4_update_delay(timeout)); + __set_current_state(TASK_KILLABLE|TASK_FREEZABLE_UNSAFE); + schedule_timeout(nfs4_update_delay(timeout)); if (!__fatal_signal_pending(current)) return 0; return -EINTR; @@ -423,7 +427,8 @@ static int nfs4_delay_interruptible(long *timeout) { might_sleep(); - freezable_schedule_timeout_interruptible_unsafe(nfs4_update_delay(timeout)); + __set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE_UNSAFE); + schedule_timeout(nfs4_update_delay(timeout)); if (!signal_pending(current)) return 0; return __fatal_signal_pending(current) ? -EINTR :-ERESTARTSYS; @@ -780,10 +785,9 @@ static void nfs4_slot_sequence_record_sent(struct nfs4_slot *slot, if ((s32)(seqnr - slot->seq_nr_highest_sent) > 0) slot->seq_nr_highest_sent = seqnr; } -static void nfs4_slot_sequence_acked(struct nfs4_slot *slot, - u32 seqnr) +static void nfs4_slot_sequence_acked(struct nfs4_slot *slot, u32 seqnr) { - slot->seq_nr_highest_sent = seqnr; + nfs4_slot_sequence_record_sent(slot, seqnr); slot->seq_nr_last_acked = seqnr; } @@ -850,7 +854,6 @@ static int nfs41_sequence_process(struct rpc_task *task, __func__, slot->slot_nr, slot->seq_nr); - nfs4_slot_sequence_acked(slot, slot->seq_nr); goto out_retry; case -NFS4ERR_RETRY_UNCACHED_REP: case -NFS4ERR_SEQ_FALSE_RETRY: @@ -1158,7 +1161,7 @@ static int nfs4_call_sync_sequence(struct rpc_clnt *clnt, { unsigned short task_flags = 0; - if (server->nfs_client->cl_minorversion) + if (server->caps & NFS_CAP_MOVEABLE) task_flags = RPC_TASK_MOVEABLE; return nfs4_do_call_sync(clnt, server, msg, args, res, task_flags); } @@ -1233,8 +1236,7 @@ nfs4_update_changeattr_locked(struct inode *inode, NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_INVALID_SIZE | NFS_INO_INVALID_OTHER | NFS_INO_INVALID_BLOCKS | NFS_INO_INVALID_NLINK | - NFS_INO_INVALID_MODE | NFS_INO_INVALID_XATTR | - NFS_INO_REVAL_PAGECACHE; + NFS_INO_INVALID_MODE | NFS_INO_INVALID_XATTR; nfsi->attrtimeo = NFS_MINATTRTIMEO(inode); } nfsi->attrtimeo_timestamp = jiffies; @@ -1397,13 +1399,8 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, case NFS4_OPEN_CLAIM_FH: p->o_arg.access = NFS4_ACCESS_READ | NFS4_ACCESS_MODIFY | NFS4_ACCESS_EXTEND | NFS4_ACCESS_DELETE | - NFS4_ACCESS_EXECUTE; -#ifdef CONFIG_NFS_V4_2 - if (!(server->caps & NFS_CAP_XATTR)) - break; - p->o_arg.access |= NFS4_ACCESS_XAREAD | NFS4_ACCESS_XAWRITE | - NFS4_ACCESS_XALIST; -#endif + NFS4_ACCESS_EXECUTE | + nfs_access_xattr_mask(server); } p->o_arg.clientid = server->nfs_client->cl_clientid; p->o_arg.id.create_time = ktime_to_ns(sp->so_seqid.create_time); @@ -2570,7 +2567,7 @@ static int nfs4_run_open_task(struct nfs4_opendata *data, }; int status; - if (server->nfs_client->cl_minorversion) + if (nfs_server_capable(dir, NFS_CAP_MOVEABLE)) task_setup_data.flags |= RPC_TASK_MOVEABLE; kref_get(&data->kref); @@ -2653,9 +2650,8 @@ static int nfs4_opendata_access(const struct cred *cred, } else if ((fmode & FMODE_READ) && !opendata->file_created) mask = NFS4_ACCESS_READ; - cache.cred = cred; nfs_access_set_mask(&cache, opendata->o_res.access_result); - nfs_access_add_cache(state->inode, &cache); + nfs_access_add_cache(state->inode, &cache, cred); flags = NFS4_ACCESS_READ | NFS4_ACCESS_EXECUTE | NFS4_ACCESS_LOOKUP; if ((mask & ~cache.mask & flags) == 0) @@ -3056,6 +3052,8 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata, set_bit(NFS_STATE_POSIX_LOCKS, &state->flags); if (opendata->o_res.rflags & NFS4_OPEN_RESULT_MAY_NOTIFY_LOCK) set_bit(NFS_STATE_MAY_NOTIFY_LOCK, &state->flags); + if (opendata->o_res.rflags & NFS4_OPEN_RESULT_PRESERVE_UNLINKED) + set_bit(NFS_INO_PRESERVE_UNLINKED, &NFS_I(state->inode)->flags); dentry = opendata->dentry; if (d_really_is_negative(dentry)) { @@ -3099,8 +3097,13 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata, } out: - if (!opendata->cancelled) + if (!opendata->cancelled) { + if (opendata->lgp) { + nfs4_lgopen_release(opendata->lgp); + opendata->lgp = NULL; + } nfs4_sequence_free_slot(&opendata->o_res.seq_res); + } return ret; } @@ -3670,7 +3673,7 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data) if (!nfs4_have_delegation(inode, FMODE_READ)) { nfs4_bitmask_set(calldata->arg.bitmask_store, server->cache_consistency_bitmask, - inode, server, NULL); + inode, 0); calldata->arg.bitmask = calldata->arg.bitmask_store; } else calldata->arg.bitmask = NULL; @@ -3734,7 +3737,7 @@ int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait) }; int status = -ENOMEM; - if (server->nfs_client->cl_minorversion) + if (nfs_server_capable(state->inode, NFS_CAP_MOVEABLE)) task_setup_data.flags |= RPC_TASK_MOVEABLE; nfs4_state_protect(server->nfs_client, NFS_SP4_MACH_CRED_CLEANUP, @@ -3841,7 +3844,9 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f FATTR4_WORD0_FH_EXPIRE_TYPE | FATTR4_WORD0_LINK_SUPPORT | FATTR4_WORD0_SYMLINK_SUPPORT | - FATTR4_WORD0_ACLSUPPORT; + FATTR4_WORD0_ACLSUPPORT | + FATTR4_WORD0_CASE_INSENSITIVE | + FATTR4_WORD0_CASE_PRESERVING; if (minorversion) bitmask[2] = FATTR4_WORD2_SUPPATTR_EXCLCREAT; @@ -3870,10 +3875,16 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f server->caps |= NFS_CAP_HARDLINKS; if (res.has_symlinks != 0) server->caps |= NFS_CAP_SYMLINKS; + if (res.case_insensitive) + server->caps |= NFS_CAP_CASE_INSENSITIVE; + if (res.case_preserving) + server->caps |= NFS_CAP_CASE_PRESERVING; #ifdef CONFIG_NFS_V4_SECURITY_LABEL if (res.attr_bitmask[2] & FATTR4_WORD2_SECURITY_LABEL) server->caps |= NFS_CAP_SECURITY_LABEL; #endif + if (res.attr_bitmask[0] & FATTR4_WORD0_FS_LOCATIONS) + server->caps |= NFS_CAP_FS_LOCATIONS; if (!(res.attr_bitmask[0] & FATTR4_WORD0_FILEID)) server->fattr_valid &= ~NFS_ATTR_FATTR_FILEID; if (!(res.attr_bitmask[1] & FATTR4_WORD1_MODE)) @@ -3932,6 +3943,121 @@ int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle) return err; } +static void test_fs_location_for_trunking(struct nfs4_fs_location *location, + struct nfs_client *clp, + struct nfs_server *server) +{ + int i; + + for (i = 0; i < location->nservers; i++) { + struct nfs4_string *srv_loc = &location->servers[i]; + struct sockaddr_storage addr; + size_t addrlen; + struct xprt_create xprt_args = { + .ident = 0, + .net = clp->cl_net, + }; + struct nfs4_add_xprt_data xprtdata = { + .clp = clp, + }; + struct rpc_add_xprt_test rpcdata = { + .add_xprt_test = clp->cl_mvops->session_trunk, + .data = &xprtdata, + }; + char *servername = NULL; + + if (!srv_loc->len) + continue; + + addrlen = nfs_parse_server_name(srv_loc->data, srv_loc->len, + &addr, sizeof(addr), + clp->cl_net, server->port); + if (!addrlen) + return; + xprt_args.dstaddr = (struct sockaddr *)&addr; + xprt_args.addrlen = addrlen; + servername = kmalloc(srv_loc->len + 1, GFP_KERNEL); + if (!servername) + return; + memcpy(servername, srv_loc->data, srv_loc->len); + servername[srv_loc->len] = '\0'; + xprt_args.servername = servername; + + xprtdata.cred = nfs4_get_clid_cred(clp); + rpc_clnt_add_xprt(clp->cl_rpcclient, &xprt_args, + rpc_clnt_setup_test_and_add_xprt, + &rpcdata); + if (xprtdata.cred) + put_cred(xprtdata.cred); + kfree(servername); + } +} + +static int _nfs4_discover_trunking(struct nfs_server *server, + struct nfs_fh *fhandle) +{ + struct nfs4_fs_locations *locations = NULL; + struct page *page; + const struct cred *cred; + struct nfs_client *clp = server->nfs_client; + const struct nfs4_state_maintenance_ops *ops = + clp->cl_mvops->state_renewal_ops; + int status = -ENOMEM, i; + + cred = ops->get_state_renewal_cred(clp); + if (cred == NULL) { + cred = nfs4_get_clid_cred(clp); + if (cred == NULL) + return -ENOKEY; + } + + page = alloc_page(GFP_KERNEL); + if (!page) + return -ENOMEM; + locations = kmalloc(sizeof(struct nfs4_fs_locations), GFP_KERNEL); + if (!locations) + goto out_free; + locations->fattr = nfs_alloc_fattr(); + if (!locations->fattr) + goto out_free_2; + + status = nfs4_proc_get_locations(server, fhandle, locations, page, + cred); + if (status) + goto out_free_3; + + for (i = 0; i < locations->nlocations; i++) + test_fs_location_for_trunking(&locations->locations[i], clp, + server); +out_free_3: + kfree(locations->fattr); +out_free_2: + kfree(locations); +out_free: + __free_page(page); + return status; +} + +static int nfs4_discover_trunking(struct nfs_server *server, + struct nfs_fh *fhandle) +{ + struct nfs4_exception exception = { + .interruptible = true, + }; + struct nfs_client *clp = server->nfs_client; + int err = 0; + + if (!nfs4_has_session(clp)) + goto out; + do { + err = nfs4_handle_exception(server, + _nfs4_discover_trunking(server, fhandle), + &exception); + } while (exception.retry); +out: + return err; +} + static int _nfs4_lookup_root(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fsinfo *info) { @@ -4128,6 +4254,8 @@ static int nfs4_get_referral(struct rpc_clnt *client, struct inode *dir, if (locations == NULL) goto out; + locations->fattr = fattr; + status = nfs4_proc_fs_locations(client, dir, name, locations, page); if (status != 0) goto out; @@ -4137,17 +4265,14 @@ static int nfs4_get_referral(struct rpc_clnt *client, struct inode *dir, * referral. Cause us to drop into the exception handler, which * will kick off migration recovery. */ - if (nfs_fsid_equal(&NFS_SERVER(dir)->fsid, &locations->fattr.fsid)) { + if (nfs_fsid_equal(&NFS_SERVER(dir)->fsid, &fattr->fsid)) { dprintk("%s: server did not return a different fsid for" " a referral at %s\n", __func__, name->name); status = -NFS4ERR_MOVED; goto out; } /* Fixup attributes for the nfs_lookup() call to nfs_fhget() */ - nfs_fixup_referral_attributes(&locations->fattr); - - /* replace the lookup nfs_fattr with the locations nfs_fattr */ - memcpy(fattr, &locations->fattr, sizeof(struct nfs_fattr)); + nfs_fixup_referral_attributes(fattr); memset(fhandle, 0, sizeof(struct nfs_fh)); out: if (page) @@ -4289,7 +4414,7 @@ static int _nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, }; unsigned short task_flags = 0; - if (server->nfs_client->cl_minorversion) + if (nfs_server_capable(dir, NFS_CAP_MOVEABLE)) task_flags = RPC_TASK_MOVEABLE; /* Is this is an attribute revalidation, subject to softreval? */ @@ -4441,7 +4566,8 @@ static int nfs4_proc_lookupp(struct inode *inode, struct nfs_fh *fhandle, return err; } -static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry) +static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry, + const struct cred *cred) { struct nfs_server *server = NFS_SERVER(inode); struct nfs4_accessargs args = { @@ -4455,7 +4581,7 @@ static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_ACCESS], .rpc_argp = &args, .rpc_resp = &res, - .rpc_cred = entry->cred, + .rpc_cred = cred, }; int status = 0; @@ -4475,14 +4601,15 @@ static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry return status; } -static int nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry) +static int nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry, + const struct cred *cred) { struct nfs4_exception exception = { .interruptible = true, }; int err; do { - err = _nfs4_proc_access(inode, entry); + err = _nfs4_proc_access(inode, entry, cred); trace_nfs4_access(inode, err); err = nfs4_handle_exception(NFS_SERVER(inode), err, &exception); @@ -4663,8 +4790,10 @@ static void nfs4_proc_unlink_setup(struct rpc_message *msg, nfs_fattr_init(res->dir_attr); - if (inode) + if (inode) { nfs4_inode_return_delegation(inode); + nfs_d_prune_case_insensitive_aliases(inode); + } } static void nfs4_proc_unlink_rpc_prepare(struct rpc_task *task, struct nfs_unlinkdata *data) @@ -4730,6 +4859,7 @@ static int nfs4_proc_rename_done(struct rpc_task *task, struct inode *old_dir, return 0; if (task->tk_status == 0) { + nfs_d_prune_case_insensitive_aliases(d_inode(data->old_dentry)); if (new_dir != old_dir) { /* Note: If we moved a directory, nlink will change */ nfs4_update_changeattr(old_dir, &res->old_cinfo, @@ -5422,14 +5552,14 @@ bool nfs4_write_need_cache_consistency_data(struct nfs_pgio_header *hdr) return nfs4_have_delegation(hdr->inode, FMODE_READ) == 0; } -static void nfs4_bitmask_set(__u32 bitmask[NFS4_BITMASK_SZ], const __u32 *src, - struct inode *inode, struct nfs_server *server, - struct nfs4_label *label) +void nfs4_bitmask_set(__u32 bitmask[], const __u32 src[], + struct inode *inode, unsigned long cache_validity) { - unsigned long cache_validity = READ_ONCE(NFS_I(inode)->cache_validity); + struct nfs_server *server = NFS_SERVER(inode); unsigned int i; memcpy(bitmask, src, sizeof(*bitmask) * NFS4_BITMASK_SZ); + cache_validity |= READ_ONCE(NFS_I(inode)->cache_validity); if (cache_validity & NFS_INO_INVALID_CHANGE) bitmask[0] |= FATTR4_WORD0_CHANGE; @@ -5441,8 +5571,6 @@ static void nfs4_bitmask_set(__u32 bitmask[NFS4_BITMASK_SZ], const __u32 *src, bitmask[1] |= FATTR4_WORD1_OWNER | FATTR4_WORD1_OWNER_GROUP; if (cache_validity & NFS_INO_INVALID_NLINK) bitmask[1] |= FATTR4_WORD1_NUMLINKS; - if (label && label->len && cache_validity & NFS_INO_INVALID_LABEL) - bitmask[2] |= FATTR4_WORD2_SECURITY_LABEL; if (cache_validity & NFS_INO_INVALID_CTIME) bitmask[1] |= FATTR4_WORD1_TIME_METADATA; if (cache_validity & NFS_INO_INVALID_MTIME) @@ -5469,7 +5597,7 @@ static void nfs4_proc_write_setup(struct nfs_pgio_header *hdr, } else { nfs4_bitmask_set(hdr->args.bitmask_store, server->cache_consistency_bitmask, - hdr->inode, server, NULL); + hdr->inode, NFS_INO_INVALID_BLOCKS); hdr->args.bitmask = hdr->args.bitmask_store; } @@ -5650,9 +5778,17 @@ static int nfs4_proc_renew(struct nfs_client *clp, const struct cred *cred) return 0; } -static inline int nfs4_server_supports_acls(struct nfs_server *server) +static bool nfs4_server_supports_acls(const struct nfs_server *server, + enum nfs4_acl_type type) { - return server->caps & NFS_CAP_ACLS; + switch (type) { + default: + return server->attr_bitmask[0] & FATTR4_WORD0_ACL; + case NFS4ACL_DACL: + return server->attr_bitmask[1] & FATTR4_WORD1_DACL; + case NFS4ACL_SACL: + return server->attr_bitmask[1] & FATTR4_WORD1_SACL; + } } /* Assuming that XATTR_SIZE_MAX is a multiple of PAGE_SIZE, and that @@ -5691,6 +5827,7 @@ unwind: } struct nfs4_cached_acl { + enum nfs4_acl_type type; int cached; size_t len; char data[]; @@ -5711,7 +5848,8 @@ static void nfs4_zap_acl_attr(struct inode *inode) nfs4_set_cached_acl(inode, NULL); } -static inline ssize_t nfs4_read_cached_acl(struct inode *inode, char *buf, size_t buflen) +static ssize_t nfs4_read_cached_acl(struct inode *inode, char *buf, + size_t buflen, enum nfs4_acl_type type) { struct nfs_inode *nfsi = NFS_I(inode); struct nfs4_cached_acl *acl; @@ -5721,6 +5859,8 @@ static inline ssize_t nfs4_read_cached_acl(struct inode *inode, char *buf, size_ acl = nfsi->nfs4_acl; if (acl == NULL) goto out; + if (acl->type != type) + goto out; if (buf == NULL) /* user is just asking for length */ goto out_len; if (acl->cached == 0) @@ -5736,7 +5876,9 @@ out: return ret; } -static void nfs4_write_cached_acl(struct inode *inode, struct page **pages, size_t pgbase, size_t acl_len) +static void nfs4_write_cached_acl(struct inode *inode, struct page **pages, + size_t pgbase, size_t acl_len, + enum nfs4_acl_type type) { struct nfs4_cached_acl *acl; size_t buflen = sizeof(*acl) + acl_len; @@ -5753,6 +5895,7 @@ static void nfs4_write_cached_acl(struct inode *inode, struct page **pages, size goto out; acl->cached = 0; } + acl->type = type; acl->len = acl_len; out: nfs4_set_cached_acl(inode, acl); @@ -5768,14 +5911,17 @@ out: * length. The next getxattr call will then produce another round trip to * the server, this time with the input buf of the required size. */ -static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t buflen) +static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, + size_t buflen, enum nfs4_acl_type type) { struct page **pages; struct nfs_getaclargs args = { .fh = NFS_FH(inode), + .acl_type = type, .acl_len = buflen, }; struct nfs_getaclres res = { + .acl_type = type, .acl_len = buflen, }; struct rpc_message msg = { @@ -5791,7 +5937,7 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu buflen = server->rsize; npages = DIV_ROUND_UP(buflen, PAGE_SIZE) + 1; - pages = kmalloc_array(npages, sizeof(struct page *), GFP_NOFS); + pages = kmalloc_array(npages, sizeof(struct page *), GFP_KERNEL); if (!pages) return -ENOMEM; @@ -5825,7 +5971,8 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu ret = -ERANGE; goto out_free; } - nfs4_write_cached_acl(inode, pages, res.acl_data_offset, res.acl_len); + nfs4_write_cached_acl(inode, pages, res.acl_data_offset, res.acl_len, + type); if (buf) { if (res.acl_len > buflen) { ret = -ERANGE; @@ -5845,14 +5992,15 @@ out_free: return ret; } -static ssize_t nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t buflen) +static ssize_t nfs4_get_acl_uncached(struct inode *inode, void *buf, + size_t buflen, enum nfs4_acl_type type) { struct nfs4_exception exception = { .interruptible = true, }; ssize_t ret; do { - ret = __nfs4_get_acl_uncached(inode, buf, buflen); + ret = __nfs4_get_acl_uncached(inode, buf, buflen, type); trace_nfs4_get_acl(inode, ret); if (ret >= 0) break; @@ -5861,34 +6009,37 @@ static ssize_t nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bufl return ret; } -static ssize_t nfs4_proc_get_acl(struct inode *inode, void *buf, size_t buflen) +static ssize_t nfs4_proc_get_acl(struct inode *inode, void *buf, size_t buflen, + enum nfs4_acl_type type) { struct nfs_server *server = NFS_SERVER(inode); int ret; - if (!nfs4_server_supports_acls(server)) + if (!nfs4_server_supports_acls(server, type)) return -EOPNOTSUPP; ret = nfs_revalidate_inode(inode, NFS_INO_INVALID_CHANGE); if (ret < 0) return ret; if (NFS_I(inode)->cache_validity & NFS_INO_INVALID_ACL) nfs_zap_acl_cache(inode); - ret = nfs4_read_cached_acl(inode, buf, buflen); + ret = nfs4_read_cached_acl(inode, buf, buflen, type); if (ret != -ENOENT) /* -ENOENT is returned if there is no ACL or if there is an ACL * but no cached acl data, just the acl length */ return ret; - return nfs4_get_acl_uncached(inode, buf, buflen); + return nfs4_get_acl_uncached(inode, buf, buflen, type); } -static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t buflen) +static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, + size_t buflen, enum nfs4_acl_type type) { struct nfs_server *server = NFS_SERVER(inode); struct page *pages[NFS4ACL_MAXPAGES]; struct nfs_setaclargs arg = { - .fh = NFS_FH(inode), - .acl_pages = pages, - .acl_len = buflen, + .fh = NFS_FH(inode), + .acl_type = type, + .acl_len = buflen, + .acl_pages = pages, }; struct nfs_setaclres res; struct rpc_message msg = { @@ -5902,7 +6053,7 @@ static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t bufl /* You can't remove system.nfs4_acl: */ if (buflen == 0) return -EINVAL; - if (!nfs4_server_supports_acls(server)) + if (!nfs4_server_supports_acls(server, type)) return -EOPNOTSUPP; if (npages > ARRAY_SIZE(pages)) return -ERANGE; @@ -5933,12 +6084,13 @@ static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t bufl return ret; } -static int nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t buflen) +static int nfs4_proc_set_acl(struct inode *inode, const void *buf, + size_t buflen, enum nfs4_acl_type type) { struct nfs4_exception exception = { }; int err; do { - err = __nfs4_proc_set_acl(inode, buf, buflen); + err = __nfs4_proc_set_acl(inode, buf, buflen, type); trace_nfs4_set_acl(inode, err); if (err == -NFS4ERR_BADOWNER || err == -NFS4ERR_BADNAME) { /* @@ -6443,7 +6595,9 @@ static void nfs4_delegreturn_release(void *calldata) pnfs_roc_release(&data->lr.arg, &data->lr.res, data->res.lr_ret); if (inode) { - nfs_post_op_update_inode_force_wcc(inode, &data->fattr); + nfs4_fattr_set_prechange(&data->fattr, + inode_peek_iversion_raw(inode)); + nfs_refresh_inode(inode, &data->fattr); nfs_iput_and_deactive(inode); } kfree(calldata); @@ -6454,7 +6608,7 @@ static void nfs4_delegreturn_prepare(struct rpc_task *task, void *data) struct nfs4_delegreturndata *d_data; struct pnfs_layout_hdr *lo; - d_data = (struct nfs4_delegreturndata *)data; + d_data = data; if (!d_data->lr.roc && nfs4_wait_on_layoutreturn(d_data->inode, task)) { nfs4_sequence_done(task, &d_data->res.seq_res); @@ -6492,11 +6646,14 @@ static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred, .rpc_client = server->client, .rpc_message = &msg, .callback_ops = &nfs4_delegreturn_ops, - .flags = RPC_TASK_ASYNC | RPC_TASK_TIMEOUT | RPC_TASK_MOVEABLE, + .flags = RPC_TASK_ASYNC | RPC_TASK_TIMEOUT, }; int status = 0; - data = kzalloc(sizeof(*data), GFP_NOFS); + if (nfs_server_capable(inode, NFS_CAP_MOVEABLE)) + task_setup_data.flags |= RPC_TASK_MOVEABLE; + + data = kzalloc(sizeof(*data), GFP_KERNEL); if (data == NULL) return -ENOMEM; @@ -6507,8 +6664,7 @@ static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred, data->args.fhandle = &data->fh; data->args.stateid = &data->stateid; nfs4_bitmask_set(data->args.bitmask_store, - server->cache_consistency_bitmask, inode, server, - NULL); + server->cache_consistency_bitmask, inode, 0); data->args.bitmask = data->args.bitmask_store; nfs_copy_fh(&data->fh, NFS_FH(inode)); nfs4_stateid_copy(&data->stateid, stateid); @@ -6685,7 +6841,7 @@ static struct nfs4_unlockdata *nfs4_alloc_unlockdata(struct file_lock *fl, struct nfs4_state *state = lsp->ls_state; struct inode *inode = state->inode; - p = kzalloc(sizeof(*p), GFP_NOFS); + p = kzalloc(sizeof(*p), GFP_KERNEL); if (p == NULL) return NULL; p->arg.fh = NFS_FH(inode); @@ -6810,10 +6966,8 @@ static struct rpc_task *nfs4_do_unlck(struct file_lock *fl, .workqueue = nfsiod_workqueue, .flags = RPC_TASK_ASYNC, }; - struct nfs_client *client = - NFS_SERVER(lsp->ls_state->inode)->nfs_client; - if (client->cl_minorversion) + if (nfs_server_capable(lsp->ls_state->inode, NFS_CAP_MOVEABLE)) task_setup_data.flags |= RPC_TASK_MOVEABLE; nfs4_state_protect(NFS_SERVER(lsp->ls_state->inode)->nfs_client, @@ -6984,6 +7138,7 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata) { struct nfs4_lockdata *data = calldata; struct nfs4_lock_state *lsp = data->lsp; + struct nfs_server *server = NFS_SERVER(d_inode(data->ctx->dentry)); if (!nfs4_sequence_done(task, &data->res.seq_res)) return; @@ -6991,8 +7146,7 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata) data->rpc_status = task->tk_status; switch (task->tk_status) { case 0: - renew_lease(NFS_SERVER(d_inode(data->ctx->dentry)), - data->timestamp); + renew_lease(server, data->timestamp); if (data->arg.new_lock && !data->cancelled) { data->fl.fl_flags &= ~(FL_SLEEP | FL_ACCESS); if (locks_lock_inode_wait(lsp->ls_state->inode, &data->fl) < 0) @@ -7013,6 +7167,8 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata) if (!nfs4_stateid_match(&data->arg.open_stateid, &lsp->ls_state->open_stateid)) goto out_restart; + else if (nfs4_async_handle_error(task, server, lsp->ls_state, NULL) == -EAGAIN) + goto out_restart; } else if (!nfs4_stateid_match(&data->arg.lock_stateid, &lsp->ls_stateid)) goto out_restart; @@ -7084,14 +7240,12 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f .flags = RPC_TASK_ASYNC | RPC_TASK_CRED_NOREF, }; int ret; - struct nfs_client *client = NFS_SERVER(state->inode)->nfs_client; - if (client->cl_minorversion) + if (nfs_server_capable(state->inode, NFS_CAP_MOVEABLE)) task_setup_data.flags |= RPC_TASK_MOVEABLE; data = nfs4_alloc_lockdata(fl, nfs_file_open_context(fl->fl_file), - fl->fl_u.nfs4_fl.owner, - recovery_type == NFS_LOCK_NEW ? GFP_KERNEL : GFP_NOFS); + fl->fl_u.nfs4_fl.owner, GFP_KERNEL); if (data == NULL) return -ENOMEM; if (IS_SETLKW(cmd)) @@ -7255,7 +7409,8 @@ nfs4_retry_setlk_simple(struct nfs4_state *state, int cmd, status = nfs4_proc_setlk(state, cmd, request); if ((status != -EAGAIN) || IS_SETLK(cmd)) break; - freezable_schedule_timeout_interruptible(timeout); + __set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE); + schedule_timeout(timeout); timeout *= 2; timeout = min_t(unsigned long, NFS4_LOCK_MAXTIMEOUT, timeout); status = -ERESTARTSYS; @@ -7323,10 +7478,8 @@ nfs4_retry_setlk(struct nfs4_state *state, int cmd, struct file_lock *request) break; status = -ERESTARTSYS; - freezer_do_not_count(); - wait_woken(&waiter.wait, TASK_INTERRUPTIBLE, + wait_woken(&waiter.wait, TASK_INTERRUPTIBLE|TASK_FREEZABLE, NFS4_LOCK_MAXTIMEOUT); - freezer_count(); } while (!signalled()); remove_wait_queue(q, &waiter.wait); @@ -7514,7 +7667,7 @@ nfs4_release_lockowner(struct nfs_server *server, struct nfs4_lock_state *lsp) if (server->nfs_client->cl_mvops->minor_version != 0) return; - data = kmalloc(sizeof(*data), GFP_NOFS); + data = kmalloc(sizeof(*data), GFP_KERNEL); if (!data) return; data->lsp = lsp; @@ -7537,21 +7690,70 @@ static int nfs4_xattr_set_nfs4_acl(const struct xattr_handler *handler, const char *key, const void *buf, size_t buflen, int flags) { - return nfs4_proc_set_acl(inode, buf, buflen); + return nfs4_proc_set_acl(inode, buf, buflen, NFS4ACL_ACL); } static int nfs4_xattr_get_nfs4_acl(const struct xattr_handler *handler, struct dentry *unused, struct inode *inode, const char *key, void *buf, size_t buflen) { - return nfs4_proc_get_acl(inode, buf, buflen); + return nfs4_proc_get_acl(inode, buf, buflen, NFS4ACL_ACL); } static bool nfs4_xattr_list_nfs4_acl(struct dentry *dentry) { - return nfs4_server_supports_acls(NFS_SERVER(d_inode(dentry))); + return nfs4_server_supports_acls(NFS_SB(dentry->d_sb), NFS4ACL_ACL); } +#if defined(CONFIG_NFS_V4_1) +#define XATTR_NAME_NFSV4_DACL "system.nfs4_dacl" + +static int nfs4_xattr_set_nfs4_dacl(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, + struct dentry *unused, struct inode *inode, + const char *key, const void *buf, + size_t buflen, int flags) +{ + return nfs4_proc_set_acl(inode, buf, buflen, NFS4ACL_DACL); +} + +static int nfs4_xattr_get_nfs4_dacl(const struct xattr_handler *handler, + struct dentry *unused, struct inode *inode, + const char *key, void *buf, size_t buflen) +{ + return nfs4_proc_get_acl(inode, buf, buflen, NFS4ACL_DACL); +} + +static bool nfs4_xattr_list_nfs4_dacl(struct dentry *dentry) +{ + return nfs4_server_supports_acls(NFS_SB(dentry->d_sb), NFS4ACL_DACL); +} + +#define XATTR_NAME_NFSV4_SACL "system.nfs4_sacl" + +static int nfs4_xattr_set_nfs4_sacl(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, + struct dentry *unused, struct inode *inode, + const char *key, const void *buf, + size_t buflen, int flags) +{ + return nfs4_proc_set_acl(inode, buf, buflen, NFS4ACL_SACL); +} + +static int nfs4_xattr_get_nfs4_sacl(const struct xattr_handler *handler, + struct dentry *unused, struct inode *inode, + const char *key, void *buf, size_t buflen) +{ + return nfs4_proc_get_acl(inode, buf, buflen, NFS4ACL_SACL); +} + +static bool nfs4_xattr_list_nfs4_sacl(struct dentry *dentry) +{ + return nfs4_server_supports_acls(NFS_SB(dentry->d_sb), NFS4ACL_SACL); +} + +#endif + #ifdef CONFIG_NFS_V4_SECURITY_LABEL static int nfs4_xattr_set_nfs4_label(const struct xattr_handler *handler, @@ -7611,7 +7813,7 @@ static int nfs4_xattr_set_nfs4_user(const struct xattr_handler *handler, const char *key, const void *buf, size_t buflen, int flags) { - struct nfs_access_entry cache; + u32 mask; int ret; if (!nfs_server_capable(inode, NFS_CAP_XATTR)) @@ -7626,8 +7828,8 @@ static int nfs4_xattr_set_nfs4_user(const struct xattr_handler *handler, * do a cached access check for the XA* flags to possibly avoid * doing an RPC and getting EACCES back. */ - if (!nfs_access_get_cached(inode, current_cred(), &cache, true)) { - if (!(cache.mask & NFS_ACCESS_XAWRITE)) + if (!nfs_access_get_cached(inode, current_cred(), &mask, true)) { + if (!(mask & NFS_ACCESS_XAWRITE)) return -EACCES; } @@ -7648,14 +7850,14 @@ static int nfs4_xattr_get_nfs4_user(const struct xattr_handler *handler, struct dentry *unused, struct inode *inode, const char *key, void *buf, size_t buflen) { - struct nfs_access_entry cache; + u32 mask; ssize_t ret; if (!nfs_server_capable(inode, NFS_CAP_XATTR)) return -EOPNOTSUPP; - if (!nfs_access_get_cached(inode, current_cred(), &cache, true)) { - if (!(cache.mask & NFS_ACCESS_XAREAD)) + if (!nfs_access_get_cached(inode, current_cred(), &mask, true)) { + if (!(mask & NFS_ACCESS_XAREAD)) return -EACCES; } @@ -7680,13 +7882,13 @@ nfs4_listxattr_nfs4_user(struct inode *inode, char *list, size_t list_len) ssize_t ret, size; char *buf; size_t buflen; - struct nfs_access_entry cache; + u32 mask; if (!nfs_server_capable(inode, NFS_CAP_XATTR)) return 0; - if (!nfs_access_get_cached(inode, current_cred(), &cache, true)) { - if (!(cache.mask & NFS_ACCESS_XALIST)) + if (!nfs_access_get_cached(inode, current_cred(), &mask, true)) { + if (!(mask & NFS_ACCESS_XALIST)) return 0; } @@ -7784,7 +7986,7 @@ static int _nfs4_proc_fs_locations(struct rpc_clnt *client, struct inode *dir, else bitmask[1] &= ~FATTR4_WORD1_MOUNTED_ON_FILEID; - nfs_fattr_init(&fs_locations->fattr); + nfs_fattr_init(fs_locations->fattr); fs_locations->server = server; fs_locations->nlocations = 0; status = nfs4_call_sync(client, server, &msg, &args.seq_args, &res.seq_res, 0); @@ -7818,18 +8020,18 @@ int nfs4_proc_fs_locations(struct rpc_clnt *client, struct inode *dir, * appended to this compound to identify the client ID which is * performing recovery. */ -static int _nfs40_proc_get_locations(struct inode *inode, +static int _nfs40_proc_get_locations(struct nfs_server *server, + struct nfs_fh *fhandle, struct nfs4_fs_locations *locations, struct page *page, const struct cred *cred) { - struct nfs_server *server = NFS_SERVER(inode); struct rpc_clnt *clnt = server->client; u32 bitmask[2] = { [0] = FATTR4_WORD0_FSID | FATTR4_WORD0_FS_LOCATIONS, }; struct nfs4_fs_locations_arg args = { .clientid = server->nfs_client->cl_clientid, - .fh = NFS_FH(inode), + .fh = fhandle, .page = page, .bitmask = bitmask, .migration = 1, /* skip LOOKUP */ @@ -7849,7 +8051,7 @@ static int _nfs40_proc_get_locations(struct inode *inode, unsigned long now = jiffies; int status; - nfs_fattr_init(&locations->fattr); + nfs_fattr_init(locations->fattr); locations->server = server; locations->nlocations = 0; @@ -7875,17 +8077,17 @@ static int _nfs40_proc_get_locations(struct inode *inode, * When the client supports GETATTR(fs_locations_info), it can * be plumbed in here. */ -static int _nfs41_proc_get_locations(struct inode *inode, +static int _nfs41_proc_get_locations(struct nfs_server *server, + struct nfs_fh *fhandle, struct nfs4_fs_locations *locations, struct page *page, const struct cred *cred) { - struct nfs_server *server = NFS_SERVER(inode); struct rpc_clnt *clnt = server->client; u32 bitmask[2] = { [0] = FATTR4_WORD0_FSID | FATTR4_WORD0_FS_LOCATIONS, }; struct nfs4_fs_locations_arg args = { - .fh = NFS_FH(inode), + .fh = fhandle, .page = page, .bitmask = bitmask, .migration = 1, /* skip LOOKUP */ @@ -7900,15 +8102,26 @@ static int _nfs41_proc_get_locations(struct inode *inode, .rpc_resp = &res, .rpc_cred = cred, }; + struct nfs4_call_sync_data data = { + .seq_server = server, + .seq_args = &args.seq_args, + .seq_res = &res.seq_res, + }; + struct rpc_task_setup task_setup_data = { + .rpc_client = clnt, + .rpc_message = &msg, + .callback_ops = server->nfs_client->cl_mvops->call_sync_ops, + .callback_data = &data, + .flags = RPC_TASK_NO_ROUND_ROBIN, + }; int status; - nfs_fattr_init(&locations->fattr); + nfs_fattr_init(locations->fattr); locations->server = server; locations->nlocations = 0; nfs4_init_sequence(&args.seq_args, &res.seq_res, 0, 1); - status = nfs4_call_sync_sequence(clnt, server, &msg, - &args.seq_args, &res.seq_res); + status = nfs4_call_sync_custom(&task_setup_data); if (status == NFS4_OK && res.seq_res.sr_status_flags & SEQ4_STATUS_LEASE_MOVED) status = -NFS4ERR_LEASE_MOVED; @@ -7919,7 +8132,8 @@ static int _nfs41_proc_get_locations(struct inode *inode, /** * nfs4_proc_get_locations - discover locations for a migrated FSID - * @inode: inode on FSID that is migrating + * @server: pointer to nfs_server to process + * @fhandle: pointer to the kernel NFS client file handle * @locations: result of query * @page: buffer * @cred: credential to use for this operation @@ -7934,11 +8148,11 @@ static int _nfs41_proc_get_locations(struct inode *inode, * -NFS4ERR_LEASE_MOVED is returned if the server still has leases * from this client that require migration recovery. */ -int nfs4_proc_get_locations(struct inode *inode, +int nfs4_proc_get_locations(struct nfs_server *server, + struct nfs_fh *fhandle, struct nfs4_fs_locations *locations, struct page *page, const struct cred *cred) { - struct nfs_server *server = NFS_SERVER(inode); struct nfs_client *clp = server->nfs_client; const struct nfs4_mig_recovery_ops *ops = clp->cl_mvops->mig_recovery_ops; @@ -7951,10 +8165,11 @@ int nfs4_proc_get_locations(struct inode *inode, (unsigned long long)server->fsid.major, (unsigned long long)server->fsid.minor, clp->cl_hostname); - nfs_display_fhandle(NFS_FH(inode), __func__); + nfs_display_fhandle(fhandle, __func__); do { - status = ops->get_locations(inode, locations, page, cred); + status = ops->get_locations(server, fhandle, locations, page, + cred); if (status != -NFS4ERR_DELAY) break; nfs4_handle_exception(server, status, &exception); @@ -8219,6 +8434,7 @@ nfs4_bind_one_conn_to_session_done(struct rpc_task *task, void *calldata) case -NFS4ERR_DEADSESSION: nfs4_schedule_session_recovery(clp->cl_session, task->tk_status); + return; } if (args->dir == NFS4_CDFC4_FORE_OR_BOTH && res->dir != NFS4_CDFS4_BOTH) { @@ -8686,7 +8902,7 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, const struct cred *cred) void nfs4_test_session_trunk(struct rpc_clnt *clnt, struct rpc_xprt *xprt, void *data) { - struct nfs4_add_xprt_data *adata = (struct nfs4_add_xprt_data *)data; + struct nfs4_add_xprt_data *adata = data; struct rpc_task *task; int status; @@ -8709,6 +8925,9 @@ void nfs4_test_session_trunk(struct rpc_clnt *clnt, struct rpc_xprt *xprt, if (status == 0) rpc_clnt_xprt_switch_add_xprt(clnt, xprt); + else if (rpc_clnt_xprt_switch_has_addr(clnt, + (struct sockaddr *)&xprt->addr)) + rpc_clnt_xprt_switch_remove_xprt(clnt, xprt); rpc_put_task(task); } @@ -9033,6 +9252,13 @@ int nfs4_proc_create_session(struct nfs_client *clp, const struct cred *cred) int status; unsigned *ptr; struct nfs4_session *session = clp->cl_session; + struct nfs4_add_xprt_data xprtdata = { + .clp = clp, + }; + struct rpc_add_xprt_test rpcdata = { + .add_xprt_test = clp->cl_mvops->session_trunk, + .data = &xprtdata, + }; dprintk("--> %s clp=%p session=%p\n", __func__, clp, session); @@ -9049,6 +9275,7 @@ int nfs4_proc_create_session(struct nfs_client *clp, const struct cred *cred) ptr = (unsigned *)&session->sess_id.data[0]; dprintk("%s client>seqid %d sessionid %u:%u:%u:%u\n", __func__, clp->cl_seqid, ptr[0], ptr[1], ptr[2], ptr[3]); + rpc_clnt_probe_trunked_xprts(clp->cl_rpcclient, &rpcdata); out: return status; } @@ -9078,6 +9305,7 @@ int nfs4_proc_destroy_session(struct nfs4_session *session, if (status) dprintk("NFS: Got error %d from the server on DESTROY_SESSION. " "Session has been destroyed regardless...\n", status); + rpc_clnt_manage_trunked_xprts(session->clp->cl_rpcclient); return status; } @@ -9177,7 +9405,7 @@ static struct rpc_task *_nfs41_proc_sequence(struct nfs_client *clp, goto out_err; ret = ERR_PTR(-ENOMEM); - calldata = kzalloc(sizeof(*calldata), GFP_NOFS); + calldata = kzalloc(sizeof(*calldata), GFP_KERNEL); if (calldata == NULL) goto out_put_clp; nfs4_init_sequence(&calldata->args, &calldata->res, 0, is_privileged); @@ -9262,6 +9490,9 @@ static int nfs41_reclaim_complete_handle_errors(struct rpc_task *task, struct nf rpc_delay(task, NFS4_POLL_RETRY_MAX); fallthrough; case -NFS4ERR_RETRY_UNCACHED_REP: + case -EACCES: + dprintk("%s: failed to reclaim complete error %d for server %s, retrying\n", + __func__, task->tk_status, clp->cl_hostname); return -EAGAIN; case -NFS4ERR_BADSESSION: case -NFS4ERR_DEADSESSION: @@ -9493,6 +9724,8 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, long *timeout) nfs4_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0, 0); task = rpc_run_task(&task_setup_data); + if (IS_ERR(task)) + return ERR_CAST(task); status = rpc_wait_for_completion_task(task); if (status != 0) @@ -10108,7 +10341,7 @@ static int nfs41_free_stateid(struct nfs_server *server, &task_setup.rpc_client, &msg); dprintk("NFS call free_stateid %p\n", stateid); - data = kmalloc(sizeof(*data), GFP_NOFS); + data = kmalloc(sizeof(*data), GFP_KERNEL); if (!data) return -ENOMEM; data->server = server; @@ -10257,7 +10490,8 @@ static const struct nfs4_minor_version_ops nfs_v4_1_minor_ops = { | NFS_CAP_POSIX_LOCK | NFS_CAP_STATEID_NFSV41 | NFS_CAP_ATOMIC_OPEN_V1 - | NFS_CAP_LGOPEN, + | NFS_CAP_LGOPEN + | NFS_CAP_MOVEABLE, .init_client = nfs41_init_client, .shutdown_client = nfs41_shutdown_client, .match_stateid = nfs41_match_stateid, @@ -10292,7 +10526,8 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = { | NFS_CAP_LAYOUTSTATS | NFS_CAP_CLONE | NFS_CAP_LAYOUTERROR - | NFS_CAP_READ_PLUS, + | NFS_CAP_READ_PLUS + | NFS_CAP_MOVEABLE, .init_client = nfs41_init_client, .shutdown_client = nfs41_shutdown_client, .match_stateid = nfs41_match_stateid, @@ -10347,6 +10582,24 @@ static ssize_t nfs4_listxattr(struct dentry *dentry, char *list, size_t size) return error + error2 + error3; } +static void nfs4_enable_swap(struct inode *inode) +{ + /* The state manager thread must always be running. + * It will notice the client is a swapper, and stay put. + */ + struct nfs_client *clp = NFS_SERVER(inode)->nfs_client; + + nfs4_schedule_state_manager(clp); +} + +static void nfs4_disable_swap(struct inode *inode) +{ + /* The state manager thread will now exit once it is + * woken. + */ + wake_up_var(&NFS_SERVER(inode)->nfs_client->cl_state); +} + static const struct inode_operations nfs4_dir_inode_operations = { .create = nfs_create, .lookup = nfs_lookup, @@ -10423,6 +10676,9 @@ const struct nfs_rpc_ops nfs_v4_clientops = { .free_client = nfs4_free_client, .create_server = nfs4_create_server, .clone_server = nfs_clone_server, + .discover_trunking = nfs4_discover_trunking, + .enable_swap = nfs4_enable_swap, + .disable_swap = nfs4_disable_swap, }; static const struct xattr_handler nfs4_xattr_nfs4_acl_handler = { @@ -10432,6 +10688,22 @@ static const struct xattr_handler nfs4_xattr_nfs4_acl_handler = { .set = nfs4_xattr_set_nfs4_acl, }; +#if defined(CONFIG_NFS_V4_1) +static const struct xattr_handler nfs4_xattr_nfs4_dacl_handler = { + .name = XATTR_NAME_NFSV4_DACL, + .list = nfs4_xattr_list_nfs4_dacl, + .get = nfs4_xattr_get_nfs4_dacl, + .set = nfs4_xattr_set_nfs4_dacl, +}; + +static const struct xattr_handler nfs4_xattr_nfs4_sacl_handler = { + .name = XATTR_NAME_NFSV4_SACL, + .list = nfs4_xattr_list_nfs4_sacl, + .get = nfs4_xattr_get_nfs4_sacl, + .set = nfs4_xattr_set_nfs4_sacl, +}; +#endif + #ifdef CONFIG_NFS_V4_2 static const struct xattr_handler nfs4_xattr_nfs4_user_handler = { .prefix = XATTR_USER_PREFIX, @@ -10442,6 +10714,10 @@ static const struct xattr_handler nfs4_xattr_nfs4_user_handler = { const struct xattr_handler *nfs4_xattr_handlers[] = { &nfs4_xattr_nfs4_acl_handler, +#if defined(CONFIG_NFS_V4_1) + &nfs4_xattr_nfs4_dacl_handler, + &nfs4_xattr_nfs4_sacl_handler, +#endif #ifdef CONFIG_NFS_V4_SECURITY_LABEL &nfs4_xattr_nfs4_label_handler, #endif diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index f63dfa01001c..a2d2d5d1b088 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -49,6 +49,7 @@ #include <linux/workqueue.h> #include <linux/bitops.h> #include <linux/jiffies.h> +#include <linux/sched/mm.h> #include <linux/sunrpc/clnt.h> @@ -496,8 +497,7 @@ nfs4_alloc_state_owner(struct nfs_server *server, sp = kzalloc(sizeof(*sp), gfp_flags); if (!sp) return NULL; - sp->so_seqid.owner_id = ida_simple_get(&server->openowner_id, 0, 0, - gfp_flags); + sp->so_seqid.owner_id = ida_alloc(&server->openowner_id, gfp_flags); if (sp->so_seqid.owner_id < 0) { kfree(sp); return NULL; @@ -533,7 +533,7 @@ static void nfs4_free_state_owner(struct nfs4_state_owner *sp) { nfs4_destroy_seqid_counter(&sp->so_seqid); put_cred(sp->so_cred); - ida_simple_remove(&sp->so_server->openowner_id, sp->so_seqid.owner_id); + ida_free(&sp->so_server->openowner_id, sp->so_seqid.owner_id); kfree(sp); } @@ -666,7 +666,7 @@ nfs4_alloc_open_state(void) { struct nfs4_state *state; - state = kzalloc(sizeof(*state), GFP_NOFS); + state = kzalloc(sizeof(*state), GFP_KERNEL_ACCOUNT); if (!state) return NULL; refcount_set(&state->count, 1); @@ -820,7 +820,7 @@ static void __nfs4_close(struct nfs4_state *state, void nfs4_close_state(struct nfs4_state *state, fmode_t fmode) { - __nfs4_close(state, fmode, GFP_NOFS, 0); + __nfs4_close(state, fmode, GFP_KERNEL, 0); } void nfs4_close_sync(struct nfs4_state *state, fmode_t fmode) @@ -869,14 +869,14 @@ static struct nfs4_lock_state *nfs4_alloc_lock_state(struct nfs4_state *state, f struct nfs4_lock_state *lsp; struct nfs_server *server = state->owner->so_server; - lsp = kzalloc(sizeof(*lsp), GFP_NOFS); + lsp = kzalloc(sizeof(*lsp), GFP_KERNEL_ACCOUNT); if (lsp == NULL) return NULL; nfs4_init_seqid_counter(&lsp->ls_seqid); refcount_set(&lsp->ls_count, 1); lsp->ls_state = state; lsp->ls_owner = fl_owner; - lsp->ls_seqid.owner_id = ida_simple_get(&server->lockowner_id, 0, 0, GFP_NOFS); + lsp->ls_seqid.owner_id = ida_alloc(&server->lockowner_id, GFP_KERNEL_ACCOUNT); if (lsp->ls_seqid.owner_id < 0) goto out_free; INIT_LIST_HEAD(&lsp->ls_locks); @@ -888,7 +888,7 @@ out_free: void nfs4_free_lock_state(struct nfs_server *server, struct nfs4_lock_state *lsp) { - ida_simple_remove(&server->lockowner_id, lsp->ls_seqid.owner_id); + ida_free(&server->lockowner_id, lsp->ls_seqid.owner_id); nfs4_destroy_seqid_counter(&lsp->ls_seqid); kfree(lsp); } @@ -1205,10 +1205,17 @@ void nfs4_schedule_state_manager(struct nfs_client *clp) { struct task_struct *task; char buf[INET6_ADDRSTRLEN + sizeof("-manager") + 1]; + struct rpc_clnt *cl = clp->cl_rpcclient; + + while (cl != cl->cl_parent) + cl = cl->cl_parent; set_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state); - if (test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) != 0) + if (test_and_set_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state) != 0) { + wake_up_var(&clp->cl_state); return; + } + set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state); __module_get(THIS_MODULE); refcount_inc(&clp->cl_count); @@ -1224,6 +1231,7 @@ void nfs4_schedule_state_manager(struct nfs_client *clp) printk(KERN_ERR "%s: kthread_run: %ld\n", __func__, PTR_ERR(task)); nfs4_clear_state_manager_bit(clp); + clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); nfs_put_client(clp); module_put(THIS_MODULE); } @@ -1304,7 +1312,8 @@ int nfs4_wait_clnt_recover(struct nfs_client *clp) refcount_inc(&clp->cl_count); res = wait_on_bit_action(&clp->cl_state, NFS4CLNT_MANAGER_RUNNING, - nfs_wait_bit_killable, TASK_KILLABLE); + nfs_wait_bit_killable, + TASK_KILLABLE|TASK_FREEZABLE_UNSAFE); if (res) goto out; if (clp->cl_cons_state < 0) @@ -1592,7 +1601,8 @@ static inline void nfs42_complete_copies(struct nfs4_state_owner *sp, #endif /* CONFIG_NFS_V4_2 */ static int __nfs4_reclaim_open_state(struct nfs4_state_owner *sp, struct nfs4_state *state, - const struct nfs4_state_recovery_ops *ops) + const struct nfs4_state_recovery_ops *ops, + int *lost_locks) { struct nfs4_lock_state *lock; int status; @@ -1610,7 +1620,7 @@ static int __nfs4_reclaim_open_state(struct nfs4_state_owner *sp, struct nfs4_st list_for_each_entry(lock, &state->lock_states, ls_locks) { trace_nfs4_state_lock_reclaim(state, lock); if (!test_bit(NFS_LOCK_INITIALIZED, &lock->ls_flags)) - pr_warn_ratelimited("NFS: %s: Lock reclaim failed!\n", __func__); + *lost_locks += 1; } spin_unlock(&state->state_lock); } @@ -1620,7 +1630,9 @@ static int __nfs4_reclaim_open_state(struct nfs4_state_owner *sp, struct nfs4_st return status; } -static int nfs4_reclaim_open_state(struct nfs4_state_owner *sp, const struct nfs4_state_recovery_ops *ops) +static int nfs4_reclaim_open_state(struct nfs4_state_owner *sp, + const struct nfs4_state_recovery_ops *ops, + int *lost_locks) { struct nfs4_state *state; unsigned int loop = 0; @@ -1656,7 +1668,7 @@ restart: #endif /* CONFIG_NFS_V4_2 */ refcount_inc(&state->count); spin_unlock(&sp->so_lock); - status = __nfs4_reclaim_open_state(sp, state, ops); + status = __nfs4_reclaim_open_state(sp, state, ops, lost_locks); switch (status) { default: @@ -1774,6 +1786,7 @@ static void nfs4_state_mark_reclaim_helper(struct nfs_client *clp, static void nfs4_state_start_reclaim_reboot(struct nfs_client *clp) { + set_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state); /* Mark all delegations for reclaim */ nfs_delegation_mark_reclaim(clp); nfs4_state_mark_reclaim_helper(clp, nfs4_state_mark_reclaim_reboot); @@ -1899,6 +1912,7 @@ static int nfs4_do_reclaim(struct nfs_client *clp, const struct nfs4_state_recov struct rb_node *pos; LIST_HEAD(freeme); int status = 0; + int lost_locks = 0; restart: rcu_read_lock(); @@ -1918,8 +1932,11 @@ restart: spin_unlock(&clp->cl_lock); rcu_read_unlock(); - status = nfs4_reclaim_open_state(sp, ops); + status = nfs4_reclaim_open_state(sp, ops, &lost_locks); if (status < 0) { + if (lost_locks) + pr_warn("NFS: %s: lost %d locks\n", + clp->cl_hostname, lost_locks); set_bit(ops->owner_flag_bit, &sp->so_flags); nfs4_put_state_owner(sp); status = nfs4_recovery_handle_error(clp, status); @@ -1933,6 +1950,9 @@ restart: } rcu_read_unlock(); nfs4_free_state_owners(&freeme); + if (lost_locks) + pr_warn("NFS: %s: lost %d locks\n", + clp->cl_hostname, lost_locks); return 0; } @@ -2096,9 +2116,15 @@ static int nfs4_try_migration(struct nfs_server *server, const struct cred *cred dprintk("<-- %s: no memory\n", __func__); goto out; } + locations->fattr = nfs_alloc_fattr(); + if (locations->fattr == NULL) { + dprintk("<-- %s: no memory\n", __func__); + goto out; + } inode = d_inode(server->super->s_root); - result = nfs4_proc_get_locations(inode, locations, page, cred); + result = nfs4_proc_get_locations(server, NFS_FH(inode), locations, + page, cred); if (result) { dprintk("<-- %s: failed to retrieve fs_locations: %d\n", __func__, result); @@ -2106,7 +2132,10 @@ static int nfs4_try_migration(struct nfs_server *server, const struct cred *cred } result = -NFS4ERR_NXIO; - if (!(locations->fattr.valid & NFS_ATTR_FATTR_V4_LOCATIONS)) { + if (!locations->nlocations) + goto out; + + if (!(locations->fattr->valid & NFS_ATTR_FATTR_V4_LOCATIONS)) { dprintk("<-- %s: No fs_locations data, migration skipped\n", __func__); goto out; @@ -2131,6 +2160,8 @@ static int nfs4_try_migration(struct nfs_server *server, const struct cred *cred out: if (page != NULL) __free_page(page); + if (locations != NULL) + kfree(locations->fattr); kfree(locations); if (result) { pr_err("NFS: migration recovery failed (server %s)\n", @@ -2556,9 +2587,17 @@ static void nfs4_layoutreturn_any_run(struct nfs_client *clp) static void nfs4_state_manager(struct nfs_client *clp) { + unsigned int memflags; int status = 0; const char *section = "", *section_sep = ""; + /* + * State recovery can deadlock if the direct reclaim code tries + * start NFS writeback. So ensure memory allocations are all + * GFP_NOFS. + */ + memflags = memalloc_nofs_save(); + /* Ensure exclusive access to NFSv4 state */ do { trace_nfs4_state_mgr(clp); @@ -2632,6 +2671,7 @@ static void nfs4_state_manager(struct nfs_client *clp) if (status < 0) goto out_error; nfs4_state_end_reclaim_reboot(clp); + continue; } /* Detect expired delegations... */ @@ -2653,6 +2693,7 @@ static void nfs4_state_manager(struct nfs_client *clp) clear_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state); } + memalloc_nofs_restore(memflags); nfs4_end_drain_session(clp); nfs4_clear_state_manager_bit(clp); @@ -2665,11 +2706,8 @@ static void nfs4_state_manager(struct nfs_client *clp) clear_bit(NFS4CLNT_RECALL_RUNNING, &clp->cl_state); } - /* Did we race with an attempt to give us more work? */ - if (!test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state)) - return; - if (test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) != 0) - return; + return; + } while (refcount_read(&clp->cl_count) > 1 && !signalled()); goto out_drain; @@ -2682,6 +2720,7 @@ out_error: clp->cl_hostname, -status); ssleep(1); out_drain: + memalloc_nofs_restore(memflags); nfs4_end_drain_session(clp); nfs4_clear_state_manager_bit(clp); } @@ -2689,10 +2728,32 @@ out_drain: static int nfs4_run_state_manager(void *ptr) { struct nfs_client *clp = ptr; + struct rpc_clnt *cl = clp->cl_rpcclient; + + while (cl != cl->cl_parent) + cl = cl->cl_parent; allow_signal(SIGKILL); +again: + set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state); nfs4_state_manager(clp); + if (atomic_read(&cl->cl_swapper)) { + wait_var_event_interruptible(&clp->cl_state, + test_bit(NFS4CLNT_RUN_MANAGER, + &clp->cl_state)); + if (atomic_read(&cl->cl_swapper) && + test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state)) + goto again; + /* Either no longer a swapper, or were signalled */ + } + clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); + + if (refcount_read(&clp->cl_count) > 1 && !signalled() && + test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state) && + !test_and_set_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state)) + goto again; + nfs_put_client(clp); - module_put_and_exit(0); + module_put_and_kthread_exit(0); return 0; } diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h index 6ee6ad3674a2..2cff5901c689 100644 --- a/fs/nfs/nfs4trace.h +++ b/fs/nfs/nfs4trace.h @@ -2097,6 +2097,7 @@ TRACE_EVENT(ff_layout_commit_error, ) ); +#ifdef CONFIG_NFS_V4_2 TRACE_DEFINE_ENUM(NFS4_CONTENT_DATA); TRACE_DEFINE_ENUM(NFS4_CONTENT_HOLE); @@ -2105,7 +2106,6 @@ TRACE_DEFINE_ENUM(NFS4_CONTENT_HOLE); { NFS4_CONTENT_DATA, "DATA" }, \ { NFS4_CONTENT_HOLE, "HOLE" }) -#ifdef CONFIG_NFS_V4_2 TRACE_EVENT(nfs4_llseek, TP_PROTO( const struct inode *inode, @@ -2496,6 +2496,54 @@ TRACE_EVENT(nfs4_offload_cancel, __entry->stateid_seq, __entry->stateid_hash ) ); + +DECLARE_EVENT_CLASS(nfs4_xattr_event, + TP_PROTO( + const struct inode *inode, + const char *name, + int error + ), + + TP_ARGS(inode, name, error), + + TP_STRUCT__entry( + __field(unsigned long, error) + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __string(name, name) + ), + + TP_fast_assign( + __entry->error = error < 0 ? -error : 0; + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = NFS_FILEID(inode); + __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); + __assign_str(name, name); + ), + + TP_printk( + "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " + "name=%s", + -__entry->error, show_nfs4_status(__entry->error), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, __get_str(name) + ) +); +#define DEFINE_NFS4_XATTR_EVENT(name) \ + DEFINE_EVENT(nfs4_xattr_event, name, \ + TP_PROTO( \ + const struct inode *inode, \ + const char *name, \ + int error \ + ), \ + TP_ARGS(inode, name, error)) +DEFINE_NFS4_XATTR_EVENT(nfs4_getxattr); +DEFINE_NFS4_XATTR_EVENT(nfs4_setxattr); +DEFINE_NFS4_XATTR_EVENT(nfs4_removexattr); + +DEFINE_NFS4_INODE_EVENT(nfs4_listxattr); #endif /* CONFIG_NFS_V4_2 */ #endif /* CONFIG_NFS_V4_1 */ diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 69862bf6db00..acfe5f4bda48 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -1605,7 +1605,8 @@ static void encode_readdir(struct xdr_stream *xdr, const struct nfs4_readdir_arg FATTR4_WORD0_RDATTR_ERROR, FATTR4_WORD1_MOUNTED_ON_FILEID, }; - uint32_t dircount = readdir->count >> 1; + uint32_t dircount = readdir->count; + uint32_t maxcount = readdir->count; __be32 *p, verf[2]; uint32_t attrlen = 0; unsigned int i; @@ -1618,7 +1619,6 @@ static void encode_readdir(struct xdr_stream *xdr, const struct nfs4_readdir_arg FATTR4_WORD1_SPACE_USED|FATTR4_WORD1_TIME_ACCESS| FATTR4_WORD1_TIME_METADATA|FATTR4_WORD1_TIME_MODIFY; attrs[2] |= FATTR4_WORD2_SECURITY_LABEL; - dircount >>= 1; } /* Use mounted_on_fileid only if the server supports it */ if (!(readdir->bitmask[1] & FATTR4_WORD1_MOUNTED_ON_FILEID)) @@ -1634,7 +1634,7 @@ static void encode_readdir(struct xdr_stream *xdr, const struct nfs4_readdir_arg encode_nfs4_verifier(xdr, &readdir->verifier); p = reserve_space(xdr, 12 + (attrlen << 2)); *p++ = cpu_to_be32(dircount); - *p++ = cpu_to_be32(readdir->count); + *p++ = cpu_to_be32(maxcount); *p++ = cpu_to_be32(attrlen); for (i = 0; i < attrlen; i++) *p++ = cpu_to_be32(attrs[i]); @@ -1680,19 +1680,35 @@ encode_restorefh(struct xdr_stream *xdr, struct compound_hdr *hdr) encode_op_hdr(xdr, OP_RESTOREFH, decode_restorefh_maxsz, hdr); } -static void -encode_setacl(struct xdr_stream *xdr, const struct nfs_setaclargs *arg, - struct compound_hdr *hdr) +static void nfs4_acltype_to_bitmap(enum nfs4_acl_type type, __u32 bitmap[2]) { - __be32 *p; + switch (type) { + default: + bitmap[0] = FATTR4_WORD0_ACL; + bitmap[1] = 0; + break; + case NFS4ACL_DACL: + bitmap[0] = 0; + bitmap[1] = FATTR4_WORD1_DACL; + break; + case NFS4ACL_SACL: + bitmap[0] = 0; + bitmap[1] = FATTR4_WORD1_SACL; + } +} + +static void encode_setacl(struct xdr_stream *xdr, + const struct nfs_setaclargs *arg, + struct compound_hdr *hdr) +{ + __u32 bitmap[2]; + + nfs4_acltype_to_bitmap(arg->acl_type, bitmap); encode_op_hdr(xdr, OP_SETATTR, decode_setacl_maxsz, hdr); encode_nfs4_stateid(xdr, &zero_stateid); - p = reserve_space(xdr, 2*4); - *p++ = cpu_to_be32(1); - *p = cpu_to_be32(FATTR4_WORD0_ACL); - p = reserve_space(xdr, 4); - *p = cpu_to_be32(arg->acl_len); + xdr_encode_bitmap4(xdr, bitmap, ARRAY_SIZE(bitmap)); + encode_uint32(xdr, arg->acl_len); xdr_write_pages(xdr, arg->acl_pages, 0, arg->acl_len); } @@ -2587,11 +2603,11 @@ static void nfs4_xdr_enc_getacl(struct rpc_rqst *req, struct xdr_stream *xdr, struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; - const __u32 nfs4_acl_bitmap[1] = { - [0] = FATTR4_WORD0_ACL, - }; + __u32 nfs4_acl_bitmap[2]; uint32_t replen; + nfs4_acltype_to_bitmap(args->acl_type, nfs4_acl_bitmap); + encode_compound_hdr(xdr, req, &hdr); encode_sequence(xdr, &args->seq_args, &hdr); encode_putfh(xdr, args->fh, &hdr); @@ -3533,6 +3549,42 @@ static int decode_attr_aclsupport(struct xdr_stream *xdr, uint32_t *bitmap, uint return 0; } +static int decode_attr_case_insensitive(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res) +{ + __be32 *p; + + *res = 0; + if (unlikely(bitmap[0] & (FATTR4_WORD0_CASE_INSENSITIVE - 1U))) + return -EIO; + if (likely(bitmap[0] & FATTR4_WORD0_CASE_INSENSITIVE)) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + return -EIO; + *res = be32_to_cpup(p); + bitmap[0] &= ~FATTR4_WORD0_CASE_INSENSITIVE; + } + dprintk("%s: case_insensitive=%s\n", __func__, *res == 0 ? "false" : "true"); + return 0; +} + +static int decode_attr_case_preserving(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res) +{ + __be32 *p; + + *res = 0; + if (unlikely(bitmap[0] & (FATTR4_WORD0_CASE_PRESERVING - 1U))) + return -EIO; + if (likely(bitmap[0] & FATTR4_WORD0_CASE_PRESERVING)) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + return -EIO; + *res = be32_to_cpup(p); + bitmap[0] &= ~FATTR4_WORD0_CASE_PRESERVING; + } + dprintk("%s: case_preserving=%s\n", __func__, *res == 0 ? "false" : "true"); + return 0; +} + static int decode_attr_fileid(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *fileid) { __be32 *p; @@ -3696,8 +3748,6 @@ static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, st if (unlikely(!p)) goto out_eio; n = be32_to_cpup(p); - if (n <= 0) - goto out_eio; for (res->nlocations = 0; res->nlocations < n; res->nlocations++) { u32 m; struct nfs4_fs_location *loc; @@ -4200,10 +4250,11 @@ static int decode_attr_security_label(struct xdr_stream *xdr, uint32_t *bitmap, } else printk(KERN_WARNING "%s: label too long (%u)!\n", __func__, len); + if (label && label->label) + dprintk("%s: label=%.*s, len=%d, PI=%d, LFS=%d\n", + __func__, label->len, (char *)label->label, + label->len, label->pi, label->lfs); } - if (label && label->label) - dprintk("%s: label=%s, len=%d, PI=%d, LFS=%d\n", __func__, - (char *)label->label, label->len, label->pi, label->lfs); return status; } @@ -4412,6 +4463,10 @@ static int decode_server_caps(struct xdr_stream *xdr, struct nfs4_server_caps_re goto xdr_error; if ((status = decode_attr_aclsupport(xdr, bitmap, &res->acl_bitmask)) != 0) goto xdr_error; + if ((status = decode_attr_case_insensitive(xdr, bitmap, &res->case_insensitive)) != 0) + goto xdr_error; + if ((status = decode_attr_case_preserving(xdr, bitmap, &res->case_preserving)) != 0) + goto xdr_error; if ((status = decode_attr_exclcreat_supported(xdr, bitmap, res->exclcreat_bitmask)) != 0) goto xdr_error; @@ -5347,7 +5402,7 @@ decode_restorefh(struct xdr_stream *xdr) } static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req, - struct nfs_getaclres *res) + struct nfs_getaclres *res, enum nfs4_acl_type type) { unsigned int savep; uint32_t attrlen, @@ -5365,26 +5420,39 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req, if ((status = decode_attr_length(xdr, &attrlen, &savep)) != 0) goto out; - if (unlikely(bitmap[0] & (FATTR4_WORD0_ACL - 1U))) - return -EIO; - if (likely(bitmap[0] & FATTR4_WORD0_ACL)) { - - /* The bitmap (xdr len + bitmaps) and the attr xdr len words - * are stored with the acl data to handle the problem of - * variable length bitmaps.*/ - res->acl_data_offset = xdr_page_pos(xdr); - res->acl_len = attrlen; - - /* Check for receive buffer overflow */ - if (res->acl_len > xdr_stream_remaining(xdr) || - res->acl_len + res->acl_data_offset > xdr->buf->page_len) { - res->acl_flags |= NFS4_ACL_TRUNC; - dprintk("NFS: acl reply: attrlen %u > page_len %zu\n", - attrlen, xdr_stream_remaining(xdr)); - } - } else - status = -EOPNOTSUPP; + switch (type) { + default: + if (unlikely(bitmap[0] & (FATTR4_WORD0_ACL - 1U))) + return -EIO; + if (!(bitmap[0] & FATTR4_WORD0_ACL)) + return -EOPNOTSUPP; + break; + case NFS4ACL_DACL: + if (unlikely(bitmap[0] || bitmap[1] & (FATTR4_WORD1_DACL - 1U))) + return -EIO; + if (!(bitmap[1] & FATTR4_WORD1_DACL)) + return -EOPNOTSUPP; + break; + case NFS4ACL_SACL: + if (unlikely(bitmap[0] || bitmap[1] & (FATTR4_WORD1_SACL - 1U))) + return -EIO; + if (!(bitmap[1] & FATTR4_WORD1_SACL)) + return -EOPNOTSUPP; + } + /* The bitmap (xdr len + bitmaps) and the attr xdr len words + * are stored with the acl data to handle the problem of + * variable length bitmaps.*/ + res->acl_data_offset = xdr_page_pos(xdr); + res->acl_len = attrlen; + + /* Check for receive buffer overflow */ + if (res->acl_len > xdr_stream_remaining(xdr) || + res->acl_len + res->acl_data_offset > xdr->buf->page_len) { + res->acl_flags |= NFS4_ACL_TRUNC; + dprintk("NFS: acl reply: attrlen %u > page_len %zu\n", + attrlen, xdr_stream_remaining(xdr)); + } out: return status; } @@ -6447,7 +6515,7 @@ nfs4_xdr_dec_getacl(struct rpc_rqst *rqstp, struct xdr_stream *xdr, status = decode_putfh(xdr); if (status) goto out; - status = decode_getacl(xdr, rqstp, res); + status = decode_getacl(xdr, rqstp, res, res->acl_type); out: return status; @@ -7012,7 +7080,7 @@ static int nfs4_xdr_dec_fs_locations(struct rpc_rqst *req, if (res->migration) { xdr_enter_page(xdr, PAGE_SIZE); status = decode_getfattr_generic(xdr, - &res->fs_locations->fattr, + res->fs_locations->fattr, NULL, res->fs_locations, res->fs_locations->server); if (status) @@ -7025,7 +7093,7 @@ static int nfs4_xdr_dec_fs_locations(struct rpc_rqst *req, goto out; xdr_enter_page(xdr, PAGE_SIZE); status = decode_getfattr_generic(xdr, - &res->fs_locations->fattr, + res->fs_locations->fattr, NULL, res->fs_locations, res->fs_locations->server); } @@ -7469,7 +7537,6 @@ int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, if (entry->fattr->valid & NFS_ATTR_FATTR_TYPE) entry->d_type = nfs_umode_to_dtype(entry->fattr->mode); - entry->prev_cookie = entry->cookie; entry->cookie = new_cookie; return 0; diff --git a/fs/nfs/nfsroot.c b/fs/nfs/nfsroot.c index fa148308822c..620329b7e6ae 100644 --- a/fs/nfs/nfsroot.c +++ b/fs/nfs/nfsroot.c @@ -139,7 +139,7 @@ static int __init nfs_root_setup(char *line) ROOT_DEV = Root_NFS; if (line[0] == '/' || line[0] == ',' || (line[0] >= '0' && line[0] <= '9')) { - strlcpy(nfs_root_parms, line, sizeof(nfs_root_parms)); + strscpy(nfs_root_parms, line, sizeof(nfs_root_parms)); } else { size_t n = strlen(line) + sizeof(NFS_ROOT) - 1; if (n >= sizeof(nfs_root_parms)) diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index b3aee261801e..8c6cc58679ff 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -21,7 +21,6 @@ { NFS_INO_INVALID_ATIME, "INVALID_ATIME" }, \ { NFS_INO_INVALID_ACCESS, "INVALID_ACCESS" }, \ { NFS_INO_INVALID_ACL, "INVALID_ACL" }, \ - { NFS_INO_REVAL_PAGECACHE, "REVAL_PAGECACHE" }, \ { NFS_INO_REVAL_FORCED, "REVAL_FORCED" }, \ { NFS_INO_INVALID_LABEL, "INVALID_LABEL" }, \ { NFS_INO_INVALID_CHANGE, "INVALID_CHANGE" }, \ @@ -37,12 +36,10 @@ #define nfs_show_nfsi_flags(v) \ __print_flags(v, "|", \ - { BIT(NFS_INO_ADVISE_RDPLUS), "ADVISE_RDPLUS" }, \ { BIT(NFS_INO_STALE), "STALE" }, \ { BIT(NFS_INO_ACL_LRU_SET), "ACL_LRU_SET" }, \ { BIT(NFS_INO_INVALIDATING), "INVALIDATING" }, \ { BIT(NFS_INO_FSCACHE), "FSCACHE" }, \ - { BIT(NFS_INO_FSCACHE_LOCK), "FSCACHE_LOCK" }, \ { BIT(NFS_INO_LAYOUTCOMMIT), "NEED_LAYOUTCOMMIT" }, \ { BIT(NFS_INO_LAYOUTCOMMITTING), "LAYOUTCOMMIT" }, \ { BIT(NFS_INO_LAYOUTSTATS), "LAYOUTSTATS" }, \ @@ -163,6 +160,9 @@ DEFINE_NFS_INODE_EVENT(nfs_fsync_enter); DEFINE_NFS_INODE_EVENT_DONE(nfs_fsync_exit); DEFINE_NFS_INODE_EVENT(nfs_access_enter); DEFINE_NFS_INODE_EVENT_DONE(nfs_set_cache_invalid); +DEFINE_NFS_INODE_EVENT(nfs_readdir_force_readdirplus); +DEFINE_NFS_INODE_EVENT_DONE(nfs_readdir_cache_fill_done); +DEFINE_NFS_INODE_EVENT_DONE(nfs_readdir_uncached_done); TRACE_EVENT(nfs_access_exit, TP_PROTO( @@ -274,6 +274,122 @@ DEFINE_NFS_UPDATE_SIZE_EVENT(wcc); DEFINE_NFS_UPDATE_SIZE_EVENT(update); DEFINE_NFS_UPDATE_SIZE_EVENT(grow); +DECLARE_EVENT_CLASS(nfs_inode_range_event, + TP_PROTO( + const struct inode *inode, + loff_t range_start, + loff_t range_end + ), + + TP_ARGS(inode, range_start, range_end), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(u64, version) + __field(loff_t, range_start) + __field(loff_t, range_end) + ), + + TP_fast_assign( + const struct nfs_inode *nfsi = NFS_I(inode); + + __entry->dev = inode->i_sb->s_dev; + __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); + __entry->fileid = nfsi->fileid; + __entry->version = inode_peek_iversion_raw(inode); + __entry->range_start = range_start; + __entry->range_end = range_end; + ), + + TP_printk( + "fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu " + "range=[%lld, %lld]", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, __entry->version, + __entry->range_start, __entry->range_end + ) +); + +#define DEFINE_NFS_INODE_RANGE_EVENT(name) \ + DEFINE_EVENT(nfs_inode_range_event, name, \ + TP_PROTO( \ + const struct inode *inode, \ + loff_t range_start, \ + loff_t range_end \ + ), \ + TP_ARGS(inode, range_start, range_end)) + +DEFINE_NFS_INODE_RANGE_EVENT(nfs_readdir_invalidate_cache_range); + +DECLARE_EVENT_CLASS(nfs_readdir_event, + TP_PROTO( + const struct file *file, + const __be32 *verifier, + u64 cookie, + pgoff_t page_index, + unsigned int dtsize + ), + + TP_ARGS(file, verifier, cookie, page_index, dtsize), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(u64, version) + __array(char, verifier, NFS4_VERIFIER_SIZE) + __field(u64, cookie) + __field(pgoff_t, index) + __field(unsigned int, dtsize) + ), + + TP_fast_assign( + const struct inode *dir = file_inode(file); + const struct nfs_inode *nfsi = NFS_I(dir); + + __entry->dev = dir->i_sb->s_dev; + __entry->fileid = nfsi->fileid; + __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); + __entry->version = inode_peek_iversion_raw(dir); + if (cookie != 0) + memcpy(__entry->verifier, verifier, + NFS4_VERIFIER_SIZE); + else + memset(__entry->verifier, 0, + NFS4_VERIFIER_SIZE); + __entry->cookie = cookie; + __entry->index = page_index; + __entry->dtsize = dtsize; + ), + + TP_printk( + "fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu " + "cookie=%s:0x%llx cache_index=%lu dtsize=%u", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, __entry->fhandle, + __entry->version, show_nfs4_verifier(__entry->verifier), + (unsigned long long)__entry->cookie, __entry->index, + __entry->dtsize + ) +); + +#define DEFINE_NFS_READDIR_EVENT(name) \ + DEFINE_EVENT(nfs_readdir_event, name, \ + TP_PROTO( \ + const struct file *file, \ + const __be32 *verifier, \ + u64 cookie, \ + pgoff_t page_index, \ + unsigned int dtsize \ + ), \ + TP_ARGS(file, verifier, cookie, page_index, dtsize)) + +DEFINE_NFS_READDIR_EVENT(nfs_readdir_cache_fill); +DEFINE_NFS_READDIR_EVENT(nfs_readdir_uncached); + DECLARE_EVENT_CLASS(nfs_lookup_event, TP_PROTO( const struct inode *dir, @@ -367,6 +483,9 @@ DEFINE_NFS_LOOKUP_EVENT(nfs_lookup_enter); DEFINE_NFS_LOOKUP_EVENT_DONE(nfs_lookup_exit); DEFINE_NFS_LOOKUP_EVENT(nfs_lookup_revalidate_enter); DEFINE_NFS_LOOKUP_EVENT_DONE(nfs_lookup_revalidate_exit); +DEFINE_NFS_LOOKUP_EVENT(nfs_readdir_lookup); +DEFINE_NFS_LOOKUP_EVENT(nfs_readdir_lookup_revalidate_failed); +DEFINE_NFS_LOOKUP_EVENT_DONE(nfs_readdir_lookup_revalidate); TRACE_EVENT(nfs_atomic_open_enter, TP_PROTO( @@ -890,11 +1009,11 @@ TRACE_EVENT(nfs_aop_readpage_done, TRACE_EVENT(nfs_aop_readahead, TP_PROTO( const struct inode *inode, - struct page *page, + loff_t pos, unsigned int nr_pages ), - TP_ARGS(inode, page, nr_pages), + TP_ARGS(inode, pos, nr_pages), TP_STRUCT__entry( __field(dev_t, dev) @@ -912,7 +1031,7 @@ TRACE_EVENT(nfs_aop_readahead, __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); __entry->version = inode_peek_iversion_raw(inode); - __entry->offset = page_index(page) << PAGE_SHIFT; + __entry->offset = pos; __entry->nr_pages = nr_pages; ), @@ -1018,7 +1137,7 @@ TRACE_EVENT(nfs_readpage_done, __field(u32, arg_count) __field(u32, res_count) __field(bool, eof) - __field(int, status) + __field(int, error) ), TP_fast_assign( @@ -1027,7 +1146,7 @@ TRACE_EVENT(nfs_readpage_done, const struct nfs_fh *fh = hdr->args.fh ? hdr->args.fh : &nfsi->fh; - __entry->status = task->tk_status; + __entry->error = task->tk_status; __entry->offset = hdr->args.offset; __entry->arg_count = hdr->args.count; __entry->res_count = hdr->res.count; @@ -1038,14 +1157,13 @@ TRACE_EVENT(nfs_readpage_done, ), TP_printk( - "fileid=%02x:%02x:%llu fhandle=0x%08x " - "offset=%lld count=%u res=%u status=%d%s", + "error=%d fileid=%02x:%02x:%llu fhandle=0x%08x " + "offset=%lld count=%u res=%u%s", __entry->error, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, (long long)__entry->offset, __entry->arg_count, - __entry->res_count, __entry->status, - __entry->eof ? " eof" : "" + __entry->res_count, __entry->eof ? " eof" : "" ) ); @@ -1065,7 +1183,7 @@ TRACE_EVENT(nfs_readpage_short, __field(u32, arg_count) __field(u32, res_count) __field(bool, eof) - __field(int, status) + __field(int, error) ), TP_fast_assign( @@ -1074,7 +1192,7 @@ TRACE_EVENT(nfs_readpage_short, const struct nfs_fh *fh = hdr->args.fh ? hdr->args.fh : &nfsi->fh; - __entry->status = task->tk_status; + __entry->error = task->tk_status; __entry->offset = hdr->args.offset; __entry->arg_count = hdr->args.count; __entry->res_count = hdr->res.count; @@ -1085,17 +1203,107 @@ TRACE_EVENT(nfs_readpage_short, ), TP_printk( - "fileid=%02x:%02x:%llu fhandle=0x%08x " - "offset=%lld count=%u res=%u status=%d%s", + "error=%d fileid=%02x:%02x:%llu fhandle=0x%08x " + "offset=%lld count=%u res=%u%s", __entry->error, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, (long long)__entry->offset, __entry->arg_count, - __entry->res_count, __entry->status, - __entry->eof ? " eof" : "" + __entry->res_count, __entry->eof ? " eof" : "" ) ); +DECLARE_EVENT_CLASS(nfs_fscache_page_event, + TP_PROTO( + const struct inode *inode, + struct page *page + ), + + TP_ARGS(inode, page), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(loff_t, offset) + ), + + TP_fast_assign( + const struct nfs_inode *nfsi = NFS_I(inode); + const struct nfs_fh *fh = &nfsi->fh; + + __entry->offset = page_index(page) << PAGE_SHIFT; + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = nfsi->fileid; + __entry->fhandle = nfs_fhandle_hash(fh); + ), + + TP_printk( + "fileid=%02x:%02x:%llu fhandle=0x%08x " + "offset=%lld", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + (long long)__entry->offset + ) +); +DECLARE_EVENT_CLASS(nfs_fscache_page_event_done, + TP_PROTO( + const struct inode *inode, + struct page *page, + int error + ), + + TP_ARGS(inode, page, error), + + TP_STRUCT__entry( + __field(int, error) + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(loff_t, offset) + ), + + TP_fast_assign( + const struct nfs_inode *nfsi = NFS_I(inode); + const struct nfs_fh *fh = &nfsi->fh; + + __entry->offset = page_index(page) << PAGE_SHIFT; + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = nfsi->fileid; + __entry->fhandle = nfs_fhandle_hash(fh); + __entry->error = error; + ), + + TP_printk( + "fileid=%02x:%02x:%llu fhandle=0x%08x " + "offset=%lld error=%d", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + (long long)__entry->offset, __entry->error + ) +); +#define DEFINE_NFS_FSCACHE_PAGE_EVENT(name) \ + DEFINE_EVENT(nfs_fscache_page_event, name, \ + TP_PROTO( \ + const struct inode *inode, \ + struct page *page \ + ), \ + TP_ARGS(inode, page)) +#define DEFINE_NFS_FSCACHE_PAGE_EVENT_DONE(name) \ + DEFINE_EVENT(nfs_fscache_page_event_done, name, \ + TP_PROTO( \ + const struct inode *inode, \ + struct page *page, \ + int error \ + ), \ + TP_ARGS(inode, page, error)) +DEFINE_NFS_FSCACHE_PAGE_EVENT(nfs_fscache_read_page); +DEFINE_NFS_FSCACHE_PAGE_EVENT_DONE(nfs_fscache_read_page_exit); +DEFINE_NFS_FSCACHE_PAGE_EVENT(nfs_fscache_write_page); +DEFINE_NFS_FSCACHE_PAGE_EVENT_DONE(nfs_fscache_write_page_exit); + TRACE_EVENT(nfs_pgio_error, TP_PROTO( const struct nfs_pgio_header *hdr, @@ -1113,7 +1321,7 @@ TRACE_EVENT(nfs_pgio_error, __field(u32, arg_count) __field(u32, res_count) __field(loff_t, pos) - __field(int, status) + __field(int, error) ), TP_fast_assign( @@ -1122,7 +1330,7 @@ TRACE_EVENT(nfs_pgio_error, const struct nfs_fh *fh = hdr->args.fh ? hdr->args.fh : &nfsi->fh; - __entry->status = error; + __entry->error = error; __entry->offset = hdr->args.offset; __entry->arg_count = hdr->args.count; __entry->res_count = hdr->res.count; @@ -1131,12 +1339,12 @@ TRACE_EVENT(nfs_pgio_error, __entry->fhandle = nfs_fhandle_hash(fh); ), - TP_printk("fileid=%02x:%02x:%llu fhandle=0x%08x " - "offset=%lld count=%u res=%u pos=%llu status=%d", + TP_printk("error=%d fileid=%02x:%02x:%llu fhandle=0x%08x " + "offset=%lld count=%u res=%u pos=%llu", __entry->error, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, (long long)__entry->offset, __entry->arg_count, __entry->res_count, - __entry->pos, __entry->status + __entry->pos ) ); @@ -1196,7 +1404,7 @@ TRACE_EVENT(nfs_writeback_done, __field(loff_t, offset) __field(u32, arg_count) __field(u32, res_count) - __field(int, status) + __field(int, error) __field(unsigned long, stable) __array(char, verifier, NFS4_VERIFIER_SIZE) ), @@ -1208,7 +1416,7 @@ TRACE_EVENT(nfs_writeback_done, hdr->args.fh : &nfsi->fh; const struct nfs_writeverf *verf = hdr->res.verf; - __entry->status = task->tk_status; + __entry->error = task->tk_status; __entry->offset = hdr->args.offset; __entry->arg_count = hdr->args.count; __entry->res_count = hdr->res.count; @@ -1222,14 +1430,14 @@ TRACE_EVENT(nfs_writeback_done, ), TP_printk( - "fileid=%02x:%02x:%llu fhandle=0x%08x " - "offset=%lld count=%u res=%u status=%d stable=%s " - "verifier=%s", + "error=%d fileid=%02x:%02x:%llu fhandle=0x%08x " + "offset=%lld count=%u res=%u stable=%s " + "verifier=%s", __entry->error, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, (long long)__entry->offset, __entry->arg_count, - __entry->res_count, __entry->status, + __entry->res_count, show_nfs_stable_how(__entry->stable), show_nfs4_verifier(__entry->verifier) ) @@ -1237,44 +1445,50 @@ TRACE_EVENT(nfs_writeback_done, DECLARE_EVENT_CLASS(nfs_page_error_class, TP_PROTO( + const struct inode *inode, const struct nfs_page *req, int error ), - TP_ARGS(req, error), + TP_ARGS(inode, req, error), TP_STRUCT__entry( - __field(const void *, req) - __field(pgoff_t, index) - __field(unsigned int, offset) - __field(unsigned int, pgbase) - __field(unsigned int, bytes) + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(loff_t, offset) + __field(unsigned int, count) __field(int, error) ), TP_fast_assign( - __entry->req = req; - __entry->index = req->wb_index; - __entry->offset = req->wb_offset; - __entry->pgbase = req->wb_pgbase; - __entry->bytes = req->wb_bytes; + const struct nfs_inode *nfsi = NFS_I(inode); + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = nfsi->fileid; + __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); + __entry->offset = req_offset(req); + __entry->count = req->wb_bytes; __entry->error = error; ), TP_printk( - "req=%p index=%lu offset=%u pgbase=%u bytes=%u error=%d", - __entry->req, __entry->index, __entry->offset, - __entry->pgbase, __entry->bytes, __entry->error + "error=%d fileid=%02x:%02x:%llu fhandle=0x%08x " + "offset=%lld count=%u", __entry->error, + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, __entry->offset, + __entry->count ) ); #define DEFINE_NFS_PAGEERR_EVENT(name) \ DEFINE_EVENT(nfs_page_error_class, name, \ TP_PROTO( \ + const struct inode *inode, \ const struct nfs_page *req, \ int error \ ), \ - TP_ARGS(req, error)) + TP_ARGS(inode, req, error)) DEFINE_NFS_PAGEERR_EVENT(nfs_write_error); DEFINE_NFS_PAGEERR_EVENT(nfs_comp_error); @@ -1331,7 +1545,7 @@ TRACE_EVENT(nfs_commit_done, __field(u32, fhandle) __field(u64, fileid) __field(loff_t, offset) - __field(int, status) + __field(int, error) __field(unsigned long, stable) __array(char, verifier, NFS4_VERIFIER_SIZE) ), @@ -1343,7 +1557,7 @@ TRACE_EVENT(nfs_commit_done, data->args.fh : &nfsi->fh; const struct nfs_writeverf *verf = data->res.verf; - __entry->status = task->tk_status; + __entry->error = task->tk_status; __entry->offset = data->args.offset; __entry->stable = verf->committed; memcpy(__entry->verifier, @@ -1355,17 +1569,83 @@ TRACE_EVENT(nfs_commit_done, ), TP_printk( - "fileid=%02x:%02x:%llu fhandle=0x%08x " - "offset=%lld status=%d stable=%s verifier=%s", + "error=%d fileid=%02x:%02x:%llu fhandle=0x%08x " + "offset=%lld stable=%s verifier=%s", __entry->error, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, - (long long)__entry->offset, __entry->status, + (long long)__entry->offset, show_nfs_stable_how(__entry->stable), show_nfs4_verifier(__entry->verifier) ) ); +#define nfs_show_direct_req_flags(v) \ + __print_flags(v, "|", \ + { NFS_ODIRECT_DO_COMMIT, "DO_COMMIT" }, \ + { NFS_ODIRECT_RESCHED_WRITES, "RESCHED_WRITES" }, \ + { NFS_ODIRECT_SHOULD_DIRTY, "SHOULD DIRTY" }, \ + { NFS_ODIRECT_DONE, "DONE" } ) + +DECLARE_EVENT_CLASS(nfs_direct_req_class, + TP_PROTO( + const struct nfs_direct_req *dreq + ), + + TP_ARGS(dreq), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u64, fileid) + __field(u32, fhandle) + __field(loff_t, offset) + __field(ssize_t, count) + __field(ssize_t, bytes_left) + __field(ssize_t, error) + __field(int, flags) + ), + + TP_fast_assign( + const struct inode *inode = dreq->inode; + const struct nfs_inode *nfsi = NFS_I(inode); + const struct nfs_fh *fh = &nfsi->fh; + + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = nfsi->fileid; + __entry->fhandle = nfs_fhandle_hash(fh); + __entry->offset = dreq->io_start; + __entry->count = dreq->count; + __entry->bytes_left = dreq->bytes_left; + __entry->error = dreq->error; + __entry->flags = dreq->flags; + ), + + TP_printk( + "error=%zd fileid=%02x:%02x:%llu fhandle=0x%08x " + "offset=%lld count=%zd bytes_left=%zd flags=%s", + __entry->error, MAJOR(__entry->dev), + MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, __entry->offset, + __entry->count, __entry->bytes_left, + nfs_show_direct_req_flags(__entry->flags) + ) +); + +#define DEFINE_NFS_DIRECT_REQ_EVENT(name) \ + DEFINE_EVENT(nfs_direct_req_class, name, \ + TP_PROTO( \ + const struct nfs_direct_req *dreq \ + ), \ + TP_ARGS(dreq)) + +DEFINE_NFS_DIRECT_REQ_EVENT(nfs_direct_commit_complete); +DEFINE_NFS_DIRECT_REQ_EVENT(nfs_direct_resched_write); +DEFINE_NFS_DIRECT_REQ_EVENT(nfs_direct_write_complete); +DEFINE_NFS_DIRECT_REQ_EVENT(nfs_direct_write_completion); +DEFINE_NFS_DIRECT_REQ_EVENT(nfs_direct_write_schedule_iovec); +DEFINE_NFS_DIRECT_REQ_EVENT(nfs_direct_write_reschedule_io); + TRACE_EVENT(nfs_fh_to_dentry, TP_PROTO( const struct super_block *sb, @@ -1399,6 +1679,65 @@ TRACE_EVENT(nfs_fh_to_dentry, ) ); +TRACE_EVENT(nfs_mount_assign, + TP_PROTO( + const char *option, + const char *value + ), + + TP_ARGS(option, value), + + TP_STRUCT__entry( + __string(option, option) + __string(value, value) + ), + + TP_fast_assign( + __assign_str(option, option); + __assign_str(value, value); + ), + + TP_printk("option %s=%s", + __get_str(option), __get_str(value) + ) +); + +TRACE_EVENT(nfs_mount_option, + TP_PROTO( + const struct fs_parameter *param + ), + + TP_ARGS(param), + + TP_STRUCT__entry( + __string(option, param->key) + ), + + TP_fast_assign( + __assign_str(option, param->key); + ), + + TP_printk("option %s", __get_str(option)) +); + +TRACE_EVENT(nfs_mount_path, + TP_PROTO( + const char *path + ), + + TP_ARGS(path), + + TP_STRUCT__entry( + __string(path, path) + ), + + TP_fast_assign( + __assign_str(path, path); + ), + + TP_printk("path='%s'", __get_str(path)) +); + DECLARE_EVENT_CLASS(nfs_xdr_event, TP_PROTO( const struct xdr_stream *xdr, diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index ad7f83dc9a2d..317cedfa52bf 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -90,10 +90,10 @@ void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos) } } -static inline struct nfs_page * -nfs_page_alloc(void) +static inline struct nfs_page *nfs_page_alloc(void) { - struct nfs_page *p = kmem_cache_zalloc(nfs_page_cachep, GFP_KERNEL); + struct nfs_page *p = + kmem_cache_zalloc(nfs_page_cachep, nfs_io_gfp_mask()); if (p) INIT_LIST_HEAD(&p->wb_list); return p; @@ -767,6 +767,9 @@ int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr, .flags = RPC_TASK_ASYNC | flags, }; + if (nfs_server_capable(hdr->inode, NFS_CAP_MOVEABLE)) + task_setup_data.flags |= RPC_TASK_MOVEABLE; + hdr->rw_ops->rw_initiate(hdr, &msg, rpc_ops, &task_setup_data, how); dprintk("NFS: initiated pgio call " @@ -892,7 +895,7 @@ int nfs_generic_pgio(struct nfs_pageio_descriptor *desc, struct nfs_commit_info cinfo; struct nfs_page_array *pg_array = &hdr->page_array; unsigned int pagecount, pageused; - gfp_t gfp_flags = GFP_KERNEL; + gfp_t gfp_flags = nfs_io_gfp_mask(); pagecount = nfs_page_array_len(mirror->pg_base, mirror->pg_count); pg_array->npages = pagecount; @@ -979,7 +982,7 @@ nfs_pageio_alloc_mirrors(struct nfs_pageio_descriptor *desc, desc->pg_mirrors_dynamic = NULL; if (mirror_count == 1) return desc->pg_mirrors_static; - ret = kmalloc_array(mirror_count, sizeof(*ret), GFP_KERNEL); + ret = kmalloc_array(mirror_count, sizeof(*ret), nfs_io_gfp_mask()); if (ret != NULL) { for (i = 0; i < mirror_count; i++) nfs_pageio_mirror_init(&ret[i], desc->pg_bsize); @@ -1218,6 +1221,7 @@ static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc) do { list_splice_init(&mirror->pg_list, &head); + mirror->pg_recoalesce = 0; while (!list_empty(&head)) { struct nfs_page *req; diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 7c9090a28e5c..a5db5158c634 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -92,6 +92,17 @@ find_pnfs_driver(u32 id) return local; } +const struct pnfs_layoutdriver_type *pnfs_find_layoutdriver(u32 id) +{ + return find_pnfs_driver(id); +} + +void pnfs_put_layoutdriver(const struct pnfs_layoutdriver_type *ld) +{ + if (ld) + module_put(ld->owner); +} + void unset_pnfs_layoutdriver(struct nfs_server *nfss) { @@ -458,6 +469,7 @@ pnfs_mark_layout_stateid_invalid(struct pnfs_layout_hdr *lo, pnfs_clear_lseg_state(lseg, lseg_list); pnfs_clear_layoutreturn_info(lo); pnfs_free_returned_lsegs(lo, lseg_list, &range, 0); + set_bit(NFS_LAYOUT_DRAIN, &lo->plh_flags); if (test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags) && !test_and_set_bit(NFS_LAYOUT_RETURN_LOCK, &lo->plh_flags)) pnfs_clear_layoutreturn_waitbit(lo); @@ -698,6 +710,7 @@ pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo, u32 seq) { struct pnfs_layout_segment *lseg, *next; + struct nfs_server *server = NFS_SERVER(lo->plh_inode); int remaining = 0; dprintk("%s:Begin lo %p\n", __func__, lo); @@ -710,8 +723,10 @@ pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo, "offset %llu length %llu\n", __func__, lseg, lseg->pls_range.iomode, lseg->pls_seq, lseg->pls_range.offset, lseg->pls_range.length); - if (!mark_lseg_invalid(lseg, tmp_list)) - remaining++; + if (mark_lseg_invalid(lseg, tmp_list)) + continue; + remaining++; + pnfs_lseg_cancel_io(server, lseg); } dprintk("%s:Return %i\n", __func__, remaining); return remaining; @@ -1233,7 +1248,7 @@ pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, int status = 0; *pcred = NULL; - lrp = kzalloc(sizeof(*lrp), GFP_NOFS); + lrp = kzalloc(sizeof(*lrp), nfs_io_gfp_mask()); if (unlikely(lrp == NULL)) { status = -ENOMEM; spin_lock(&ino->i_lock); @@ -1896,7 +1911,7 @@ static int pnfs_prepare_to_retry_layoutget(struct pnfs_layout_hdr *lo) pnfs_layoutcommit_inode(lo->plh_inode, false); return wait_on_bit_action(&lo->plh_flags, NFS_LAYOUT_RETURN, nfs_wait_bit_killable, - TASK_KILLABLE); + TASK_KILLABLE|TASK_FREEZABLE_UNSAFE); } static void nfs_layoutget_begin(struct pnfs_layout_hdr *lo) @@ -1906,8 +1921,9 @@ static void nfs_layoutget_begin(struct pnfs_layout_hdr *lo) static void nfs_layoutget_end(struct pnfs_layout_hdr *lo) { - if (atomic_dec_and_test(&lo->plh_outstanding)) - wake_up_var(&lo->plh_outstanding); + if (atomic_dec_and_test(&lo->plh_outstanding) && + test_and_clear_bit(NFS_LAYOUT_DRAIN, &lo->plh_flags)) + wake_up_bit(&lo->plh_flags, NFS_LAYOUT_DRAIN); } static bool pnfs_is_first_layoutget(struct pnfs_layout_hdr *lo) @@ -1989,6 +2005,7 @@ lookup_again: lo = pnfs_find_alloc_layout(ino, ctx, gfp_flags); if (lo == NULL) { spin_unlock(&ino->i_lock); + lseg = ERR_PTR(-ENOMEM); trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg, PNFS_UPDATE_LAYOUT_NOMEM); goto out; @@ -2013,11 +2030,11 @@ lookup_again: * If the layout segment list is empty, but there are outstanding * layoutget calls, then they might be subject to a layoutrecall. */ - if ((list_empty(&lo->plh_segs) || !pnfs_layout_is_valid(lo)) && + if (test_bit(NFS_LAYOUT_DRAIN, &lo->plh_flags) && atomic_read(&lo->plh_outstanding) != 0) { spin_unlock(&ino->i_lock); - lseg = ERR_PTR(wait_var_event_killable(&lo->plh_outstanding, - !atomic_read(&lo->plh_outstanding))); + lseg = ERR_PTR(wait_on_bit(&lo->plh_flags, NFS_LAYOUT_DRAIN, + TASK_KILLABLE)); if (IS_ERR(lseg)) goto out_put_layout_hdr; pnfs_put_layout_hdr(lo); @@ -2117,6 +2134,7 @@ lookup_again: lgp = pnfs_alloc_init_layoutget_args(ino, ctx, &stateid, &arg, gfp_flags); if (!lgp) { + lseg = ERR_PTR(-ENOMEM); trace_pnfs_update_layout(ino, pos, count, iomode, lo, NULL, PNFS_UPDATE_LAYOUT_NOMEM); nfs_layoutget_end(lo); @@ -2139,6 +2157,12 @@ lookup_again: case -ERECALLCONFLICT: case -EAGAIN: break; + case -ENODATA: + /* The server returned NFS4ERR_LAYOUTUNAVAILABLE */ + pnfs_layout_set_fail_bit( + lo, pnfs_iomode_to_fail_bit(iomode)); + lseg = NULL; + goto out_put_layout_hdr; default: if (!nfs_error_is_fatal(PTR_ERR(lseg))) { pnfs_layout_clear_fail_bit(lo, pnfs_iomode_to_fail_bit(iomode)); @@ -2206,7 +2230,7 @@ _pnfs_grab_empty_layout(struct inode *ino, struct nfs_open_context *ctx) struct pnfs_layout_hdr *lo; spin_lock(&ino->i_lock); - lo = pnfs_find_alloc_layout(ino, ctx, GFP_KERNEL); + lo = pnfs_find_alloc_layout(ino, ctx, nfs_io_gfp_mask()); if (!lo) goto out_unlock; if (!test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags)) @@ -2249,8 +2273,8 @@ static void _lgopen_prepare_attached(struct nfs4_opendata *data, lo = _pnfs_grab_empty_layout(ino, ctx); if (!lo) return; - lgp = pnfs_alloc_init_layoutget_args(ino, ctx, ¤t_stateid, - &rng, GFP_KERNEL); + lgp = pnfs_alloc_init_layoutget_args(ino, ctx, ¤t_stateid, &rng, + nfs_io_gfp_mask()); if (!lgp) { pnfs_clear_first_layoutget(lo); nfs_layoutget_end(lo); @@ -2275,8 +2299,8 @@ static void _lgopen_prepare_floating(struct nfs4_opendata *data, }; struct nfs4_layoutget *lgp; - lgp = pnfs_alloc_init_layoutget_args(ino, ctx, ¤t_stateid, - &rng, GFP_KERNEL); + lgp = pnfs_alloc_init_layoutget_args(ino, ctx, ¤t_stateid, &rng, + nfs_io_gfp_mask()); if (!lgp) return; data->lgp = lgp; @@ -2394,7 +2418,8 @@ pnfs_layout_process(struct nfs4_layoutget *lgp) goto out_forget; } - if (!pnfs_layout_is_valid(lo) && !pnfs_is_first_layoutget(lo)) + if (test_bit(NFS_LAYOUT_DRAIN, &lo->plh_flags) && + !pnfs_is_first_layoutget(lo)) goto out_forget; if (nfs4_stateid_match_other(&lo->plh_stateid, &res->stateid)) { @@ -2463,6 +2488,7 @@ pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo, u32 seq) { struct pnfs_layout_segment *lseg, *next; + struct nfs_server *server = NFS_SERVER(lo->plh_inode); int remaining = 0; dprintk("%s:Begin lo %p\n", __func__, lo); @@ -2485,6 +2511,7 @@ pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo, continue; remaining++; set_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags); + pnfs_lseg_cancel_io(server, lseg); } if (remaining) { @@ -2691,13 +2718,11 @@ pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *r else rd_size = nfs_dreq_bytes_left(pgio->pg_dreq); - pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, - nfs_req_openctx(req), - req_offset(req), - rd_size, - IOMODE_READ, - false, - GFP_KERNEL); + pgio->pg_lseg = + pnfs_update_layout(pgio->pg_inode, nfs_req_openctx(req), + req_offset(req), rd_size, + IOMODE_READ, false, + nfs_io_gfp_mask()); if (IS_ERR(pgio->pg_lseg)) { pgio->pg_error = PTR_ERR(pgio->pg_lseg); pgio->pg_lseg = NULL; @@ -2718,13 +2743,10 @@ pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio, pnfs_generic_pg_check_layout(pgio); pnfs_generic_pg_check_range(pgio, req); if (pgio->pg_lseg == NULL) { - pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, - nfs_req_openctx(req), - req_offset(req), - wb_size, - IOMODE_RW, - false, - GFP_KERNEL); + pgio->pg_lseg = + pnfs_update_layout(pgio->pg_inode, nfs_req_openctx(req), + req_offset(req), wb_size, IOMODE_RW, + false, nfs_io_gfp_mask()); if (IS_ERR(pgio->pg_lseg)) { pgio->pg_error = PTR_ERR(pgio->pg_lseg); pgio->pg_lseg = NULL; @@ -2800,7 +2822,6 @@ int pnfs_write_done_resend_to_mds(struct nfs_pgio_header *hdr) /* Resend all requests through the MDS */ nfs_pageio_init_write(&pgio, hdr->inode, FLUSH_STABLE, true, hdr->completion_ops); - set_bit(NFS_CONTEXT_RESEND_WRITES, &hdr->args.context->flags); return nfs_pageio_resend(&pgio, hdr); } EXPORT_SYMBOL_GPL(pnfs_write_done_resend_to_mds); @@ -3176,14 +3197,14 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync) status = wait_on_bit_lock_action(&nfsi->flags, NFS_INO_LAYOUTCOMMITTING, nfs_wait_bit_killable, - TASK_KILLABLE); + TASK_KILLABLE|TASK_FREEZABLE_UNSAFE); if (status) goto out; } status = -ENOMEM; /* Note kzalloc ensures data->res.seq_res.sr_slot == NULL */ - data = kzalloc(sizeof(*data), GFP_NOFS); + data = kzalloc(sizeof(*data), nfs_io_gfp_mask()); if (!data) goto clear_layoutcommitting; @@ -3250,7 +3271,7 @@ struct nfs4_threshold *pnfs_mdsthreshold_alloc(void) { struct nfs4_threshold *thp; - thp = kzalloc(sizeof(*thp), GFP_NOFS); + thp = kzalloc(sizeof(*thp), nfs_io_gfp_mask()); if (!thp) { dprintk("%s mdsthreshold allocation failed\n", __func__); return NULL; diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index f4d7548d67b2..e3e6a41f19de 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -105,6 +105,7 @@ enum { NFS_LAYOUT_FIRST_LAYOUTGET, /* Serialize first layoutget */ NFS_LAYOUT_INODE_FREEING, /* The inode is being freed */ NFS_LAYOUT_HASHED, /* The layout visible */ + NFS_LAYOUT_DRAIN, }; enum layoutdriver_policy_flags { @@ -168,6 +169,8 @@ struct pnfs_layoutdriver_type { void (*cleanup_layoutcommit) (struct nfs4_layoutcommit_data *data); int (*prepare_layoutcommit) (struct nfs4_layoutcommit_args *args); int (*prepare_layoutstats) (struct nfs42_layoutstat_args *args); + + void (*cancel_io)(struct pnfs_layout_segment *lseg); }; struct pnfs_commit_ops { @@ -234,6 +237,8 @@ struct pnfs_devicelist { extern int pnfs_register_layoutdriver(struct pnfs_layoutdriver_type *); extern void pnfs_unregister_layoutdriver(struct pnfs_layoutdriver_type *); +extern const struct pnfs_layoutdriver_type *pnfs_find_layoutdriver(u32 id); +extern void pnfs_put_layoutdriver(const struct pnfs_layoutdriver_type *ld); /* nfs4proc.c */ extern size_t max_response_pages(struct nfs_server *server); @@ -682,6 +687,13 @@ pnfs_lseg_request_intersecting(struct pnfs_layout_segment *lseg, struct nfs_page req_offset(req), req_last); } +static inline void pnfs_lseg_cancel_io(struct nfs_server *server, + struct pnfs_layout_segment *lseg) +{ + if (server->pnfs_curr_ld->cancel_io) + server->pnfs_curr_ld->cancel_io(lseg); +} + extern unsigned int layoutstats_timer; #ifdef NFS_DEBUG diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index 316f68f96e57..5d035dd2d7bf 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -374,12 +374,12 @@ pnfs_bucket_search_commit_reqs(struct pnfs_commit_bucket *buckets, return NULL; } -/* pnfs_generic_search_commit_reqs - Search lists in @cinfo for the head reqest +/* pnfs_generic_search_commit_reqs - Search lists in @cinfo for the head request * for @page * @cinfo - commit info for current inode * @page - page to search for matching head request * - * Returns a the head request if one is found, otherwise returns NULL. + * Return: the head request if one is found, otherwise %NULL. */ struct nfs_page * pnfs_generic_search_commit_reqs(struct nfs_commit_info *cinfo, struct page *page) @@ -419,7 +419,7 @@ static struct nfs_commit_data * pnfs_bucket_fetch_commitdata(struct pnfs_commit_bucket *bucket, struct nfs_commit_info *cinfo) { - struct nfs_commit_data *data = nfs_commitdata_alloc(false); + struct nfs_commit_data *data = nfs_commitdata_alloc(); if (!data) return NULL; @@ -515,7 +515,11 @@ pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages, unsigned int nreq = 0; if (!list_empty(mds_pages)) { - data = nfs_commitdata_alloc(true); + data = nfs_commitdata_alloc(); + if (!data) { + nfs_retry_commit(mds_pages, NULL, cinfo, -1); + return -ENOMEM; + } data->ds_commit_index = -1; list_splice_init(mds_pages, &data->pages); list_add_tail(&data->list, &list); @@ -817,7 +821,7 @@ static void nfs4_clear_ds_conn_bit(struct nfs4_pnfs_ds *ds) static struct nfs_client *(*get_v3_ds_connect)( struct nfs_server *mds_srv, - const struct sockaddr *ds_addr, + const struct sockaddr_storage *ds_addr, int ds_addrlen, int ds_proto, unsigned int ds_timeo, @@ -878,7 +882,7 @@ static int _nfs4_pnfs_v3_ds_connect(struct nfs_server *mds_srv, continue; } clp = get_v3_ds_connect(mds_srv, - (struct sockaddr *)&da->da_addr, + &da->da_addr, da->da_addrlen, da->da_transport, timeo, retrans); if (IS_ERR(clp)) @@ -947,7 +951,7 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv, put_cred(xprtdata.cred); } else { clp = nfs4_set_ds_client(mds_srv, - (struct sockaddr *)&da->da_addr, + &da->da_addr, da->da_addrlen, da->da_transport, timeo, retrans, minor_version); diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c index 73dcaa99fa9b..e3570c656b0f 100644 --- a/fs/nfs/proc.c +++ b/fs/nfs/proc.c @@ -92,6 +92,7 @@ nfs_proc_get_root(struct nfs_server *server, struct nfs_fh *fhandle, info->maxfilesize = 0x7FFFFFFF; info->lease_time = 0; info->change_attr_type = NFS4_CHANGE_TYPE_IS_UNDEFINED; + info->xattr_support = 0; return 0; } diff --git a/fs/nfs/read.c b/fs/nfs/read.c index d11af2a9299c..8ae2c8d1219d 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -120,12 +120,8 @@ static void nfs_readpage_release(struct nfs_page *req, int error) if (nfs_error_is_fatal_on_server(error) && error != -ETIMEDOUT) SetPageError(page); if (nfs_page_group_sync_on_bit(req, PG_UNLOCKPAGE)) { - struct address_space *mapping = page_file_mapping(page); - if (PageUptodate(page)) - nfs_readpage_to_fscache(inode, page, 0); - else if (!PageError(page) && !PagePrivate(page)) - generic_error_remove_page(mapping, page); + nfs_fscache_write_page(inode, page); unlock_page(page); } nfs_release_request(req); @@ -194,10 +190,6 @@ static void nfs_initiate_read(struct nfs_pgio_header *hdr, const struct nfs_rpc_ops *rpc_ops, struct rpc_task_setup *task_setup_data, int how) { - struct inode *inode = hdr->inode; - int swap_flags = IS_SWAPFILE(inode) ? NFS_RPC_SWAPFLAGS : 0; - - task_setup_data->flags |= swap_flags; rpc_ops->read_setup(hdr, msg); trace_nfs_initiate_read(hdr); } @@ -290,9 +282,8 @@ static void nfs_readpage_result(struct rpc_task *task, } static int -readpage_async_filler(void *data, struct page *page) +readpage_async_filler(struct nfs_readdesc *desc, struct page *page) { - struct nfs_readdesc *desc = data; struct inode *inode = page_file_mapping(page)->host; unsigned int rsize = NFS_SERVER(inode)->rsize; struct nfs_page *new; @@ -305,6 +296,12 @@ readpage_async_filler(void *data, struct page *page) aligned_len = min_t(unsigned int, ALIGN(len, rsize), PAGE_SIZE); + if (!IS_SYNC(page->mapping->host)) { + error = nfs_fscache_read_page(page->mapping->host, page); + if (error == 0) + goto out_unlock; + } + new = nfs_create_request(desc->ctx, page, 0, aligned_len); if (IS_ERR(new)) goto out_error; @@ -320,6 +317,7 @@ readpage_async_filler(void *data, struct page *page) return 0; out_error: error = PTR_ERR(new); +out_unlock: unlock_page(page); out: return error; @@ -331,8 +329,9 @@ out: * - The error flag is set for this page. This happens only when a * previous async read operation failed. */ -int nfs_readpage(struct file *file, struct page *page) +int nfs_read_folio(struct file *file, struct folio *folio) { + struct page *page = &folio->page; struct nfs_readdesc desc; struct inode *inode = page_file_mapping(page)->host; int ret; @@ -366,12 +365,6 @@ int nfs_readpage(struct file *file, struct page *page) desc.ctx = get_nfs_open_context(nfs_file_open_context(file)); xchg(&desc.ctx->error, 0); - if (!IS_SYNC(inode)) { - ret = nfs_readpage_from_fscache(desc.ctx, inode, page); - if (ret == 0) - goto out_wait; - } - nfs_pageio_init_read(&desc.pgio, inode, false, &nfs_async_read_completion_ops); @@ -381,7 +374,6 @@ int nfs_readpage(struct file *file, struct page *page) nfs_pageio_complete_read(&desc.pgio); ret = desc.pgio.pg_error < 0 ? desc.pgio.pg_error : 0; -out_wait: if (!ret) { ret = wait_on_page_locked_killable(page); if (!PageUptodate(page) && !ret) @@ -397,14 +389,16 @@ out_unlock: return ret; } -int nfs_readpages(struct file *file, struct address_space *mapping, - struct list_head *pages, unsigned nr_pages) +void nfs_readahead(struct readahead_control *ractl) { + unsigned int nr_pages = readahead_count(ractl); + struct file *file = ractl->file; struct nfs_readdesc desc; - struct inode *inode = mapping->host; + struct inode *inode = ractl->mapping->host; + struct page *page; int ret; - trace_nfs_aop_readahead(inode, lru_to_page(pages), nr_pages); + trace_nfs_aop_readahead(inode, readahead_pos(ractl), nr_pages); nfs_inc_stats(inode, NFSIOS_VFSREADPAGES); ret = -ESTALE; @@ -419,26 +413,21 @@ int nfs_readpages(struct file *file, struct address_space *mapping, } else desc.ctx = get_nfs_open_context(nfs_file_open_context(file)); - /* attempt to read as many of the pages as possible from the cache - * - this returns -ENOBUFS immediately if the cookie is negative - */ - ret = nfs_readpages_from_fscache(desc.ctx, inode, mapping, - pages, &nr_pages); - if (ret == 0) - goto read_complete; /* all pages were read */ - nfs_pageio_init_read(&desc.pgio, inode, false, &nfs_async_read_completion_ops); - ret = read_cache_pages(mapping, pages, readpage_async_filler, &desc); + while ((page = readahead_page(ractl)) != NULL) { + ret = readpage_async_filler(&desc, page); + put_page(page); + if (ret) + break; + } nfs_pageio_complete_read(&desc.pgio); -read_complete: put_nfs_open_context(desc.ctx); out: trace_nfs_aop_readahead_done(inode, nr_pages, ret); - return ret; } int __init nfs_init_readpagecache(void) diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 3aced401735c..05ae23657527 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -149,7 +149,7 @@ int __init register_nfs_fs(void) ret = nfs_register_sysctl(); if (ret < 0) goto error_2; - ret = register_shrinker(&acl_shrinker); + ret = register_shrinker(&acl_shrinker, "nfs-acl"); if (ret < 0) goto error_3; #ifdef CONFIG_NFS_V4_2 @@ -822,8 +822,7 @@ static int nfs_request_mount(struct fs_context *fc, { struct nfs_fs_context *ctx = nfs_fc2context(fc); struct nfs_mount_request request = { - .sap = (struct sockaddr *) - &ctx->mount_server.address, + .sap = &ctx->mount_server._address, .dirpath = ctx->nfs_server.export_path, .protocol = ctx->mount_server.protocol, .fh = root_fh, @@ -854,7 +853,7 @@ static int nfs_request_mount(struct fs_context *fc, * Construct the mount server's address. */ if (ctx->mount_server.address.sa_family == AF_UNSPEC) { - memcpy(request.sap, &ctx->nfs_server.address, + memcpy(request.sap, &ctx->nfs_server._address, ctx->nfs_server.addrlen); ctx->mount_server.addrlen = ctx->nfs_server.addrlen; } @@ -1051,22 +1050,31 @@ static void nfs_fill_super(struct super_block *sb, struct nfs_fs_context *ctx) if (ctx->bsize) sb->s_blocksize = nfs_block_size(ctx->bsize, &sb->s_blocksize_bits); - if (server->nfs_client->rpc_ops->version != 2) { - /* The VFS shouldn't apply the umask to mode bits. We will do - * so ourselves when necessary. + switch (server->nfs_client->rpc_ops->version) { + case 2: + sb->s_time_gran = 1000; + sb->s_time_min = 0; + sb->s_time_max = U32_MAX; + break; + case 3: + /* + * The VFS shouldn't apply the umask to mode bits. + * We will do so ourselves when necessary. */ sb->s_flags |= SB_POSIXACL; sb->s_time_gran = 1; - sb->s_export_op = &nfs_export_ops; - } else - sb->s_time_gran = 1000; - - if (server->nfs_client->rpc_ops->version != 4) { sb->s_time_min = 0; sb->s_time_max = U32_MAX; - } else { + sb->s_export_op = &nfs_export_ops; + break; + case 4: + sb->s_flags |= SB_POSIXACL; + sb->s_time_gran = 1; sb->s_time_min = S64_MIN; sb->s_time_max = S64_MAX; + if (server->caps & NFS_CAP_ATOMIC_OPEN_V1) + sb->s_export_op = &nfs_export_ops; + break; } sb->s_magic = NFS_SUPER_MAGIC; @@ -1204,42 +1212,42 @@ static int nfs_compare_super(struct super_block *sb, struct fs_context *fc) } #ifdef CONFIG_NFS_FSCACHE -static void nfs_get_cache_cookie(struct super_block *sb, - struct nfs_fs_context *ctx) +static int nfs_get_cache_cookie(struct super_block *sb, + struct nfs_fs_context *ctx) { struct nfs_server *nfss = NFS_SB(sb); char *uniq = NULL; int ulen = 0; - nfss->fscache_key = NULL; nfss->fscache = NULL; if (!ctx) - return; + return 0; if (ctx->clone_data.sb) { struct nfs_server *mnt_s = NFS_SB(ctx->clone_data.sb); if (!(mnt_s->options & NFS_OPTION_FSCACHE)) - return; - if (mnt_s->fscache_key) { - uniq = mnt_s->fscache_key->key.uniquifier; - ulen = mnt_s->fscache_key->key.uniq_len; + return 0; + if (mnt_s->fscache_uniq) { + uniq = mnt_s->fscache_uniq; + ulen = strlen(uniq); } } else { if (!(ctx->options & NFS_OPTION_FSCACHE)) - return; + return 0; if (ctx->fscache_uniq) { uniq = ctx->fscache_uniq; ulen = strlen(ctx->fscache_uniq); } } - nfs_fscache_get_super_cookie(sb, uniq, ulen); + return nfs_fscache_get_super_cookie(sb, uniq, ulen); } #else -static void nfs_get_cache_cookie(struct super_block *sb, - struct nfs_fs_context *ctx) +static int nfs_get_cache_cookie(struct super_block *sb, + struct nfs_fs_context *ctx) { + return 0; } #endif @@ -1299,7 +1307,9 @@ int nfs_get_tree_common(struct fs_context *fc) s->s_blocksize_bits = bsize; s->s_blocksize = 1U << bsize; } - nfs_get_cache_cookie(s, ctx); + error = nfs_get_cache_cookie(s, ctx); + if (error < 0) + goto error_splat_super; } error = nfs_get_root(s, fc); diff --git a/fs/nfs/symlink.c b/fs/nfs/symlink.c index 25ba299fdac2..0e27a2e4e68b 100644 --- a/fs/nfs/symlink.c +++ b/fs/nfs/symlink.c @@ -26,21 +26,21 @@ * and straight-forward than readdir caching. */ -static int nfs_symlink_filler(void *data, struct page *page) +static int nfs_symlink_filler(struct file *file, struct folio *folio) { - struct inode *inode = data; + struct inode *inode = folio->mapping->host; int error; - error = NFS_PROTO(inode)->readlink(inode, page, 0, PAGE_SIZE); + error = NFS_PROTO(inode)->readlink(inode, &folio->page, 0, PAGE_SIZE); if (error < 0) goto error; - SetPageUptodate(page); - unlock_page(page); + folio_mark_uptodate(folio); + folio_unlock(folio); return 0; error: - SetPageError(page); - unlock_page(page); + folio_set_error(folio); + folio_unlock(folio); return -EIO; } @@ -67,7 +67,7 @@ static const char *nfs_get_link(struct dentry *dentry, if (err) return err; page = read_cache_page(&inode->i_data, 0, nfs_symlink_filler, - inode); + NULL); if (IS_ERR(page)) return ERR_CAST(page); } diff --git a/fs/nfs/sysfs.c b/fs/nfs/sysfs.c index 8cb70755e3c9..a6f740366963 100644 --- a/fs/nfs/sysfs.c +++ b/fs/nfs/sysfs.c @@ -142,10 +142,11 @@ static struct attribute *nfs_netns_client_attrs[] = { &nfs_netns_client_id.attr, NULL, }; +ATTRIBUTE_GROUPS(nfs_netns_client); static struct kobj_type nfs_netns_client_type = { .release = nfs_netns_client_release, - .default_attrs = nfs_netns_client_attrs, + .default_groups = nfs_netns_client_groups, .sysfs_ops = &kobj_sysfs_ops, .namespace = nfs_netns_client_namespace, }; diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c index 5fa11e1aca4c..9697cd5d2561 100644 --- a/fs/nfs/unlink.c +++ b/fs/nfs/unlink.c @@ -102,6 +102,10 @@ static void nfs_do_call_unlink(struct inode *inode, struct nfs_unlinkdata *data) }; struct rpc_task *task; struct inode *dir = d_inode(data->dentry->d_parent); + + if (nfs_server_capable(inode, NFS_CAP_MOVEABLE)) + task_setup_data.flags |= RPC_TASK_MOVEABLE; + nfs_sb_active(dir->i_sb); data->args.fh = NFS_FH(dir); nfs_fattr_init(data->res.dir_attr); @@ -344,9 +348,14 @@ nfs_async_rename(struct inode *old_dir, struct inode *new_dir, .flags = RPC_TASK_ASYNC | RPC_TASK_CRED_NOREF, }; + if (nfs_server_capable(old_dir, NFS_CAP_MOVEABLE) && + nfs_server_capable(new_dir, NFS_CAP_MOVEABLE)) + task_setup_data.flags |= RPC_TASK_MOVEABLE; + data = kzalloc(sizeof(*data), GFP_KERNEL); if (data == NULL) return ERR_PTR(-ENOMEM); + task_setup_data.task = &data->task; task_setup_data.callback_data = data; data->cred = get_current_cred(); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 9b7619ce17a7..f41d24b54fd1 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -70,27 +70,17 @@ static mempool_t *nfs_wdata_mempool; static struct kmem_cache *nfs_cdata_cachep; static mempool_t *nfs_commit_mempool; -struct nfs_commit_data *nfs_commitdata_alloc(bool never_fail) +struct nfs_commit_data *nfs_commitdata_alloc(void) { struct nfs_commit_data *p; - if (never_fail) - p = mempool_alloc(nfs_commit_mempool, GFP_NOIO); - else { - /* It is OK to do some reclaim, not no safe to wait - * for anything to be returned to the pool. - * mempool_alloc() cannot handle that particular combination, - * so we need two separate attempts. - */ + p = kmem_cache_zalloc(nfs_cdata_cachep, nfs_io_gfp_mask()); + if (!p) { p = mempool_alloc(nfs_commit_mempool, GFP_NOWAIT); if (!p) - p = kmem_cache_alloc(nfs_cdata_cachep, GFP_NOIO | - __GFP_NOWARN | __GFP_NORETRY); - if (!p) return NULL; + memset(p, 0, sizeof(*p)); } - - memset(p, 0, sizeof(*p)); INIT_LIST_HEAD(&p->pages); return p; } @@ -104,9 +94,15 @@ EXPORT_SYMBOL_GPL(nfs_commit_free); static struct nfs_pgio_header *nfs_writehdr_alloc(void) { - struct nfs_pgio_header *p = mempool_alloc(nfs_wdata_mempool, GFP_KERNEL); + struct nfs_pgio_header *p; - memset(p, 0, sizeof(*p)); + p = kmem_cache_zalloc(nfs_wdata_cachep, nfs_io_gfp_mask()); + if (!p) { + p = mempool_alloc(nfs_wdata_mempool, GFP_NOWAIT); + if (!p) + return NULL; + memset(p, 0, sizeof(*p)); + } p->rw_mode = FMODE_WRITE; return p; } @@ -294,6 +290,7 @@ static void nfs_grow_file(struct page *page, unsigned int offset, unsigned int c nfs_inc_stats(inode, NFSIOS_EXTENDWRITE); out: spin_unlock(&inode->i_lock); + nfs_fscache_invalidate(inode, 0); } /* A writeback failed: mark the page as bad, and invalidate the page cache */ @@ -305,7 +302,7 @@ static void nfs_set_pageerror(struct address_space *mapping) /* Force file size revalidation */ spin_lock(&inode->i_lock); nfs_set_cache_invalid(inode, NFS_INO_REVAL_FORCED | - NFS_INO_REVAL_PAGECACHE | + NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_SIZE); spin_unlock(&inode->i_lock); } @@ -315,7 +312,10 @@ static void nfs_mapping_set_error(struct page *page, int error) struct address_space *mapping = page_file_mapping(page); SetPageError(page); - mapping_set_error(mapping, error); + filemap_set_wb_err(mapping, error); + if (mapping->host) + errseq_set(&mapping->host->i_sb->s_wb_err, + error == -ENOSPC ? -ENOSPC : -EIO); nfs_set_pageerror(mapping); } @@ -416,7 +416,7 @@ static void nfs_set_page_writeback(struct page *page) if (atomic_long_inc_return(&nfss->writeback) > NFS_CONGESTION_ON_THRESH) - set_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC); + nfss->write_congested = 1; } static void nfs_end_page_writeback(struct nfs_page *req) @@ -432,7 +432,7 @@ static void nfs_end_page_writeback(struct nfs_page *req) end_page_writeback(req->wb_page); if (atomic_long_dec_return(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH) - clear_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC); + nfss->write_congested = 0; } /* @@ -592,7 +592,8 @@ nfs_lock_and_join_requests(struct page *page) static void nfs_write_error(struct nfs_page *req, int error) { - trace_nfs_write_error(req, error); + trace_nfs_write_error(page_file_mapping(req->wb_page)->host, req, + error); nfs_mapping_set_error(req->wb_page, error); nfs_inode_remove_request(req); nfs_end_page_writeback(req); @@ -603,8 +604,9 @@ static void nfs_write_error(struct nfs_page *req, int error) * Find an associated nfs write request, and prepare to flush it out * May return an error if the user signalled nfs_wait_on_request(). */ -static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio, - struct page *page) +static int nfs_page_async_flush(struct page *page, + struct writeback_control *wbc, + struct nfs_pageio_descriptor *pgio) { struct nfs_page *req; int ret = 0; @@ -630,11 +632,11 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio, /* * Remove the problematic req upon fatal errors on the server */ - if (nfs_error_is_fatal(ret)) { - if (nfs_error_is_fatal_on_server(ret)) - goto out_launder; - } else - ret = -EAGAIN; + if (nfs_error_is_fatal_on_server(ret)) + goto out_launder; + if (wbc->sync_mode == WB_SYNC_NONE) + ret = AOP_WRITEPAGE_ACTIVATE; + redirty_page_for_writepage(wbc, page); nfs_redirty_request(req); pgio->pg_error = 0; } else @@ -650,15 +652,8 @@ out_launder: static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, struct nfs_pageio_descriptor *pgio) { - int ret; - nfs_pageio_cond_complete(pgio, page_index(page)); - ret = nfs_page_async_flush(pgio, page); - if (ret == -EAGAIN) { - redirty_page_for_writepage(wbc, page); - ret = AOP_WRITEPAGE_ACTIVATE; - } - return ret; + return nfs_page_async_flush(page, wbc, pgio); } /* @@ -671,17 +666,17 @@ static int nfs_writepage_locked(struct page *page, struct inode *inode = page_file_mapping(page)->host; int err; + if (wbc->sync_mode == WB_SYNC_NONE && + NFS_SERVER(inode)->write_congested) + return AOP_WRITEPAGE_ACTIVATE; + nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE); nfs_pageio_init_write(&pgio, inode, 0, false, &nfs_async_write_completion_ops); err = nfs_do_writepage(page, wbc, &pgio); pgio.pg_error = 0; nfs_pageio_complete(&pgio); - if (err < 0) - return err; - if (nfs_error_is_fatal(pgio.pg_error)) - return pgio.pg_error; - return 0; + return err; } int nfs_writepage(struct page *page, struct writeback_control *wbc) @@ -718,6 +713,10 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc) int priority = 0; int err; + if (wbc->sync_mode == WB_SYNC_NONE && + NFS_SERVER(inode)->write_congested) + return 0; + nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGES); if (!(mntflags & NFS_MOUNT_WRITE_EAGER) || wbc->for_kupdate || @@ -729,19 +728,19 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc) priority = wb_priority(wbc); } - nfs_pageio_init_write(&pgio, inode, priority, false, - &nfs_async_write_completion_ops); - pgio.pg_io_completion = ioc; - err = write_cache_pages(mapping, wbc, nfs_writepages_callback, &pgio); - pgio.pg_error = 0; - nfs_pageio_complete(&pgio); + do { + nfs_pageio_init_write(&pgio, inode, priority, false, + &nfs_async_write_completion_ops); + pgio.pg_io_completion = ioc; + err = write_cache_pages(mapping, wbc, nfs_writepages_callback, + &pgio); + pgio.pg_error = 0; + nfs_pageio_complete(&pgio); + } while (err < 0 && !nfs_error_is_fatal(err)); nfs_io_completion_put(ioc); if (err < 0) goto out_err; - err = pgio.pg_error; - if (nfs_error_is_fatal(err)) - goto out_err; return 0; out_err: return err; @@ -1002,7 +1001,7 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr) nfs_list_remove_request(req); if (test_bit(NFS_IOHDR_ERROR, &hdr->flags) && (hdr->good_bytes < bytes)) { - trace_nfs_comp_error(req, hdr->error); + trace_nfs_comp_error(hdr->inode, req, hdr->error); nfs_mapping_set_error(req->wb_page, hdr->error); goto remove_req; } @@ -1408,6 +1407,8 @@ static void nfs_initiate_write(struct nfs_pgio_header *hdr, { int priority = flush_task_priority(how); + if (IS_SWAPFILE(hdr->inode)) + task_setup_data->flags |= RPC_TASK_SWAPPER; task_setup_data->priority = priority; rpc_ops->write_setup(hdr, msg, &task_setup_data->rpc_client); trace_nfs_initiate_write(hdr); @@ -1419,10 +1420,12 @@ static void nfs_initiate_write(struct nfs_pgio_header *hdr, */ static void nfs_redirty_request(struct nfs_page *req) { + struct nfs_inode *nfsi = NFS_I(page_file_mapping(req->wb_page)->host); + /* Bump the transmission count */ req->wb_nio++; nfs_mark_request_dirty(req); - set_bit(NFS_CONTEXT_RESEND_WRITES, &nfs_req_openctx(req)->flags); + atomic_long_inc(&nfsi->redirtied_pages); nfs_end_page_writeback(req); nfs_release_request(req); } @@ -1434,7 +1437,7 @@ static void nfs_async_write_error(struct list_head *head, int error) while (!list_empty(head)) { req = nfs_list_entry(head->next); nfs_list_remove_request(req); - if (nfs_error_is_fatal(error)) + if (nfs_error_is_fatal_on_server(error)) nfs_write_error(req, error); else nfs_redirty_request(req); @@ -1444,8 +1447,6 @@ static void nfs_async_write_error(struct list_head *head, int error) static void nfs_async_write_reschedule_io(struct nfs_pgio_header *hdr) { nfs_async_write_error(&hdr->pages, 0); - filemap_fdatawrite_range(hdr->inode->i_mapping, hdr->args.offset, - hdr->args.offset + hdr->args.count - 1); } static const struct nfs_pgio_completion_ops nfs_async_write_completion_ops = { @@ -1495,31 +1496,6 @@ void nfs_commit_prepare(struct rpc_task *task, void *calldata) NFS_PROTO(data->inode)->commit_rpc_prepare(task, data); } -/* - * Special version of should_remove_suid() that ignores capabilities. - */ -static int nfs_should_remove_suid(const struct inode *inode) -{ - umode_t mode = inode->i_mode; - int kill = 0; - - /* suid always must be killed */ - if (unlikely(mode & S_ISUID)) - kill = ATTR_KILL_SUID; - - /* - * sgid without any exec bits is just a mandatory locking mark; leave - * it alone. If some exec bits are set, it's a real sgid; kill it. - */ - if (unlikely((mode & S_ISGID) && (mode & S_IXGRP))) - kill |= ATTR_KILL_SGID; - - if (unlikely(kill && S_ISREG(mode))) - return kill; - - return 0; -} - static void nfs_writeback_check_extend(struct nfs_pgio_header *hdr, struct nfs_fattr *fattr) { @@ -1576,25 +1552,37 @@ static int nfs_writeback_done(struct rpc_task *task, nfs_add_stats(inode, NFSIOS_SERVERWRITTENBYTES, hdr->res.count); trace_nfs_writeback_done(task, hdr); - if (hdr->res.verf->committed < hdr->args.stable && - task->tk_status >= 0) { - /* We tried a write call, but the server did not - * commit data to stable storage even though we - * requested it. - * Note: There is a known bug in Tru64 < 5.0 in which - * the server reports NFS_DATA_SYNC, but performs - * NFS_FILE_SYNC. We therefore implement this checking - * as a dprintk() in order to avoid filling syslog. - */ - static unsigned long complain; + if (task->tk_status >= 0) { + enum nfs3_stable_how committed = hdr->res.verf->committed; + + if (committed == NFS_UNSTABLE) { + /* + * We have some uncommitted data on the server at + * this point, so ensure that we keep track of that + * fact irrespective of what later writes do. + */ + set_bit(NFS_IOHDR_UNSTABLE_WRITES, &hdr->flags); + } + + if (committed < hdr->args.stable) { + /* We tried a write call, but the server did not + * commit data to stable storage even though we + * requested it. + * Note: There is a known bug in Tru64 < 5.0 in which + * the server reports NFS_DATA_SYNC, but performs + * NFS_FILE_SYNC. We therefore implement this checking + * as a dprintk() in order to avoid filling syslog. + */ + static unsigned long complain; - /* Note this will print the MDS for a DS write */ - if (time_before(complain, jiffies)) { - dprintk("NFS: faulty NFS server %s:" - " (committed = %d) != (stable = %d)\n", - NFS_SERVER(inode)->nfs_client->cl_hostname, - hdr->res.verf->committed, hdr->args.stable); - complain = jiffies + 300 * HZ; + /* Note this will print the MDS for a DS write */ + if (time_before(complain, jiffies)) { + dprintk("NFS: faulty NFS server %s:" + " (committed = %d) != (stable = %d)\n", + NFS_SERVER(inode)->nfs_client->cl_hostname, + committed, hdr->args.stable); + complain = jiffies + 300 * HZ; + } } } @@ -1709,6 +1697,10 @@ int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data, .flags = RPC_TASK_ASYNC | flags, .priority = priority, }; + + if (nfs_server_capable(data->inode, NFS_CAP_MOVEABLE)) + task_setup_data.flags |= RPC_TASK_MOVEABLE; + /* Set up the initial task struct. */ nfs_ops->commit_setup(data, &msg, &task_setup_data.rpc_client); trace_nfs_initiate_commit(data); @@ -1820,7 +1812,11 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how, if (list_empty(head)) return 0; - data = nfs_commitdata_alloc(true); + data = nfs_commitdata_alloc(); + if (!data) { + nfs_retry_commit(head, NULL, cinfo, -1); + return -ENOMEM; + } /* Set up the argument struct */ nfs_init_commit(data, head, NULL, cinfo); @@ -1864,7 +1860,8 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data) (long long)req_offset(req)); if (status < 0) { if (req->wb_page) { - trace_nfs_commit_error(req, status); + trace_nfs_commit_error(data->inode, req, + status); nfs_mapping_set_error(req->wb_page, status); nfs_inode_remove_request(req); } @@ -1884,7 +1881,7 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data) /* We have a mismatch. Write the page again */ dprintk_cont(" mismatch\n"); nfs_mark_request_dirty(req); - set_bit(NFS_CONTEXT_RESEND_WRITES, &nfs_req_openctx(req)->flags); + atomic_long_inc(&NFS_I(data->inode)->redirtied_pages); next: nfs_unlock_and_release_request(req); /* Latency breaker */ @@ -1892,7 +1889,7 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data) } nfss = NFS_SERVER(data->inode); if (atomic_long_read(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH) - clear_bdi_congested(inode_to_bdi(data->inode), BLK_RW_ASYNC); + nfss->write_congested = 0; nfs_init_cinfo(&cinfo, data->inode, data->dreq); nfs_commit_end(cinfo.mds); @@ -2048,21 +2045,21 @@ out: } EXPORT_SYMBOL_GPL(nfs_wb_all); -int nfs_wb_page_cancel(struct inode *inode, struct page *page) +int nfs_wb_folio_cancel(struct inode *inode, struct folio *folio) { struct nfs_page *req; int ret = 0; - wait_on_page_writeback(page); + folio_wait_writeback(folio); /* blocking call to cancel all requests and join to a single (head) * request */ - req = nfs_lock_and_join_requests(page); + req = nfs_lock_and_join_requests(&folio->page); if (IS_ERR(req)) { ret = PTR_ERR(req); } else if (req) { - /* all requests from this page have been cancelled by + /* all requests from this folio have been cancelled by * nfs_lock_and_join_requests, so just remove the head * request from the inode / page_private pointer and * release it */ @@ -2111,24 +2108,27 @@ out_error: } #ifdef CONFIG_MIGRATION -int nfs_migrate_page(struct address_space *mapping, struct page *newpage, - struct page *page, enum migrate_mode mode) +int nfs_migrate_folio(struct address_space *mapping, struct folio *dst, + struct folio *src, enum migrate_mode mode) { /* - * If PagePrivate is set, then the page is currently associated with + * If the private flag is set, the folio is currently associated with * an in-progress read or write request. Don't try to migrate it. * * FIXME: we could do this in principle, but we'll need a way to ensure * that we can safely release the inode reference while holding - * the page lock. + * the folio lock. */ - if (PagePrivate(page)) + if (folio_test_private(src)) return -EBUSY; - if (!nfs_fscache_release_page(page, GFP_KERNEL)) - return -EBUSY; + if (folio_test_fscache(src)) { + if (mode == MIGRATE_ASYNC) + return -EBUSY; + folio_wait_fscache(src); + } - return migrate_page(mapping, newpage, page, mode); + return migrate_folio(mapping, dst, src, mode); } #endif diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig index 3d1d17256a91..f6a2fd3015e7 100644 --- a/fs/nfsd/Kconfig +++ b/fs/nfsd/Kconfig @@ -35,18 +35,9 @@ config NFSD_V2_ACL bool depends on NFSD -config NFSD_V3 - bool "NFS server support for NFS version 3" - depends on NFSD - help - This option enables support in your system's NFS server for - version 3 of the NFS protocol (RFC 1813). - - If unsure, say Y. - config NFSD_V3_ACL bool "NFS server support for the NFSv3 ACL protocol extension" - depends on NFSD_V3 + depends on NFSD select NFSD_V2_ACL help Solaris NFS servers support an auxiliary NFSv3 ACL protocol that @@ -70,7 +61,6 @@ config NFSD_V3_ACL config NFSD_V4 bool "NFS server support for NFS version 4" depends on NFSD && PROC_FS - select NFSD_V3 select FS_POSIX_ACL select SUNRPC_GSS select CRYPTO diff --git a/fs/nfsd/Makefile b/fs/nfsd/Makefile index 3f0983e93a99..805c06d5f1b4 100644 --- a/fs/nfsd/Makefile +++ b/fs/nfsd/Makefile @@ -12,9 +12,8 @@ nfsd-y += trace.o nfsd-y += nfssvc.o nfsctl.o nfsproc.o nfsfh.o vfs.o \ export.o auth.o lockd.o nfscache.o nfsxdr.o \ - stats.o filecache.o + stats.o filecache.o nfs3proc.o nfs3xdr.o nfsd-$(CONFIG_NFSD_V2_ACL) += nfs2acl.o -nfsd-$(CONFIG_NFSD_V3) += nfs3proc.o nfs3xdr.o nfsd-$(CONFIG_NFSD_V3_ACL) += nfs3acl.o nfsd-$(CONFIG_NFSD_V4) += nfs4proc.o nfs4xdr.o nfs4state.o nfs4idmap.o \ nfs4acl.o nfs4callback.o nfs4recover.o diff --git a/fs/nfsd/acl.h b/fs/nfsd/acl.h index ba14d2f4b64f..4b7324458a94 100644 --- a/fs/nfsd/acl.h +++ b/fs/nfsd/acl.h @@ -38,6 +38,8 @@ struct nfs4_acl; struct svc_fh; struct svc_rqst; +struct nfsd_attrs; +enum nfs_ftype4; int nfs4_acl_bytes(int entries); int nfs4_acl_get_whotype(char *, u32); @@ -45,7 +47,7 @@ __be32 nfs4_acl_write_who(struct xdr_stream *xdr, int who); int nfsd4_get_nfs4_acl(struct svc_rqst *rqstp, struct dentry *dentry, struct nfs4_acl **acl); -__be32 nfsd4_set_nfs4_acl(struct svc_rqst *rqstp, struct svc_fh *fhp, - struct nfs4_acl *acl); +__be32 nfsd4_acl_to_attr(enum nfs_ftype4 type, struct nfs4_acl *acl, + struct nfsd_attrs *attr); #endif /* LINUX_NFS4_ACL_H */ diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c index e5c0982a381d..b6d01d51a746 100644 --- a/fs/nfsd/blocklayout.c +++ b/fs/nfsd/blocklayout.c @@ -4,7 +4,6 @@ */ #include <linux/exportfs.h> #include <linux/iomap.h> -#include <linux/genhd.h> #include <linux/slab.h> #include <linux/pr.h> diff --git a/fs/nfsd/cache.h b/fs/nfsd/cache.h index 65c331f75e9c..f21259ead64b 100644 --- a/fs/nfsd/cache.h +++ b/fs/nfsd/cache.h @@ -84,6 +84,6 @@ 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_reply_cache_stats_open(struct inode *, struct file *); +int nfsd_reply_cache_stats_show(struct seq_file *m, void *v); #endif /* NFSCACHE_H */ diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index fdf89fcf1a0c..ec3fceb92236 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -7,11 +7,13 @@ #include <linux/hash.h> #include <linux/slab.h> #include <linux/file.h> +#include <linux/pagemap.h> #include <linux/sched.h> #include <linux/list_lru.h> #include <linux/fsnotify_backend.h> #include <linux/fsnotify.h> #include <linux/seq_file.h> +#include <linux/rhashtable.h> #include "vfs.h" #include "nfsd.h" @@ -20,59 +22,170 @@ #include "filecache.h" #include "trace.h" -#define NFSDDBG_FACILITY NFSDDBG_FH - -/* FIXME: dynamically size this for the machine somehow? */ -#define NFSD_FILE_HASH_BITS 12 -#define NFSD_FILE_HASH_SIZE (1 << NFSD_FILE_HASH_BITS) #define NFSD_LAUNDRETTE_DELAY (2 * HZ) -#define NFSD_FILE_SHUTDOWN (1) -#define NFSD_FILE_LRU_THRESHOLD (4096UL) -#define NFSD_FILE_LRU_LIMIT (NFSD_FILE_LRU_THRESHOLD << 2) +#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) -struct nfsd_fcache_bucket { - struct hlist_head nfb_head; - spinlock_t nfb_lock; - unsigned int nfb_count; - unsigned int nfb_maxcount; -}; - 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_releases); +static DEFINE_PER_CPU(unsigned long, nfsd_file_total_age); +static DEFINE_PER_CPU(unsigned long, nfsd_file_pages_flushed); +static DEFINE_PER_CPU(unsigned long, nfsd_file_evictions); struct nfsd_fcache_disposal { - struct list_head list; struct work_struct work; - struct net *net; spinlock_t lock; struct list_head freeme; - struct rcu_head rcu; }; 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 nfsd_fcache_bucket *nfsd_file_hashtbl; static struct list_lru nfsd_file_lru; -static long nfsd_file_lru_flags; +static unsigned long nfsd_file_flags; static struct fsnotify_group *nfsd_file_fsnotify_group; -static atomic_long_t nfsd_filecache_count; static struct delayed_work nfsd_filecache_laundrette; -static DEFINE_SPINLOCK(laundrette_lock); -static LIST_HEAD(laundrettes); +static struct rhashtable nfsd_file_rhash_tbl + ____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; + 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) +{ + int i; + + if (!uid_eq(c1->fsuid, c2->fsuid)) + return false; + if (!gid_eq(c1->fsgid, c2->fsgid)) + return false; + if (c1->group_info == NULL || c2->group_info == NULL) + return c1->group_info == c2->group_info; + if (c1->group_info->ngroups != c2->group_info->ngroups) + return false; + for (i = 0; i < c1->group_info->ngroups; i++) { + if (!gid_eq(c1->group_info->gid[i], c2->group_info->gid[i])) + return false; + } + return true; +} -static void nfsd_file_gc(void); +/** + * 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_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 */ + .automatic_shrinking = true, +}; static void nfsd_file_schedule_laundrette(void) { - long count = atomic_long_read(&nfsd_filecache_count); - - if (count == 0 || test_bit(NFSD_FILE_SHUTDOWN, &nfsd_file_lru_flags)) + if ((atomic_read(&nfsd_file_rhash_tbl.nelems) == 0) || + test_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags) == 0) return; queue_delayed_work(system_wq, &nfsd_filecache_laundrette, @@ -115,22 +228,21 @@ nfsd_file_mark_put(struct nfsd_file_mark *nfm) } static struct nfsd_file_mark * -nfsd_file_mark_find_or_create(struct nfsd_file *nf) +nfsd_file_mark_find_or_create(struct nfsd_file *nf, struct inode *inode) { int err; struct fsnotify_mark *mark; struct nfsd_file_mark *nfm = NULL, *new; - struct inode *inode = nf->nf_inode; do { - mutex_lock(&nfsd_file_fsnotify_group->mark_mutex); + fsnotify_group_lock(nfsd_file_fsnotify_group); mark = fsnotify_find_mark(&inode->i_fsnotify_marks, - nfsd_file_fsnotify_group); + nfsd_file_fsnotify_group); if (mark) { nfm = nfsd_file_mark_get(container_of(mark, struct nfsd_file_mark, nfm_mark)); - mutex_unlock(&nfsd_file_fsnotify_group->mark_mutex); + fsnotify_group_unlock(nfsd_file_fsnotify_group); if (nfm) { fsnotify_put_mark(mark); break; @@ -138,8 +250,9 @@ nfsd_file_mark_find_or_create(struct nfsd_file *nf) /* Avoid soft lockup race with nfsd_file_mark_put() */ fsnotify_destroy_mark(mark, nfsd_file_fsnotify_group); fsnotify_put_mark(mark); - } else - mutex_unlock(&nfsd_file_fsnotify_group->mark_mutex); + } else { + fsnotify_group_unlock(nfsd_file_fsnotify_group); + } /* allocate a new nfm */ new = kmem_cache_alloc(nfsd_file_mark_slab, GFP_KERNEL); @@ -170,32 +283,25 @@ nfsd_file_mark_find_or_create(struct nfsd_file *nf) } static struct nfsd_file * -nfsd_file_alloc(struct inode *inode, unsigned int may, unsigned int hashval, - struct net *net) +nfsd_file_alloc(struct nfsd_file_lookup_key *key, unsigned int may) { struct nfsd_file *nf; nf = kmem_cache_alloc(nfsd_file_slab, GFP_KERNEL); if (nf) { - INIT_HLIST_NODE(&nf->nf_node); INIT_LIST_HEAD(&nf->nf_lru); + nf->nf_birthtime = ktime_get(); nf->nf_file = NULL; nf->nf_cred = get_current_cred(); - nf->nf_net = net; + nf->nf_net = key->net; nf->nf_flags = 0; - nf->nf_inode = inode; - nf->nf_hashval = hashval; - refcount_set(&nf->nf_ref, 1); - nf->nf_may = may & NFSD_FILE_MAY_MASK; - if (may & NFSD_MAY_NOT_BREAK_LEASE) { - if (may & NFSD_MAY_WRITE) - __set_bit(NFSD_FILE_BREAK_WRITE, &nf->nf_flags); - if (may & NFSD_MAY_READ) - __set_bit(NFSD_FILE_BREAK_READ, &nf->nf_flags); - } + __set_bit(NFSD_FILE_HASHED, &nf->nf_flags); + __set_bit(NFSD_FILE_PENDING, &nf->nf_flags); + nf->nf_inode = key->inode; + /* nf_ref is pre-incremented for hash table */ + refcount_set(&nf->nf_ref, 2); + nf->nf_may = key->need; nf->nf_mark = NULL; - init_rwsem(&nf->nf_rwsem); - trace_nfsd_file_alloc(nf); } return nf; } @@ -203,8 +309,12 @@ nfsd_file_alloc(struct inode *inode, unsigned int may, unsigned int hashval, static bool nfsd_file_free(struct nfsd_file *nf) { + s64 age = ktime_to_ms(ktime_sub(ktime_get(), nf->nf_birthtime)); bool flush = false; + this_cpu_inc(nfsd_file_releases); + this_cpu_add(nfsd_file_total_age, age); + trace_nfsd_file_put_final(nf); if (nf->nf_mark) nfsd_file_mark_put(nf->nf_mark); @@ -214,6 +324,14 @@ nfsd_file_free(struct nfsd_file *nf) fput(nf->nf_file); flush = true; } + + /* + * If this item is still linked via nf_lru, that's a bug. + * WARN and leak it to preserve system stability. + */ + if (WARN_ON_ONCE(!list_empty(&nf->nf_lru))) + return flush; + call_rcu(&nf->nf_rcu, nfsd_file_slab_free); return flush; } @@ -242,48 +360,60 @@ nfsd_file_check_write_error(struct nfsd_file *nf) } static void -nfsd_file_do_unhash(struct nfsd_file *nf) +nfsd_file_flush(struct nfsd_file *nf) +{ + struct file *file = nf->nf_file; + + if (!file || !(file->f_mode & FMODE_WRITE)) + return; + this_cpu_add(nfsd_file_pages_flushed, file->f_mapping->nrpages); + if (vfs_fsync(file, 1) != 0) + nfsd_reset_write_verifier(net_generic(nf->nf_net, nfsd_net_id)); +} + +static void nfsd_file_lru_add(struct nfsd_file *nf) { - lockdep_assert_held(&nfsd_file_hashtbl[nf->nf_hashval].nfb_lock); + set_bit(NFSD_FILE_REFERENCED, &nf->nf_flags); + if (list_lru_add(&nfsd_file_lru, &nf->nf_lru)) + trace_nfsd_file_lru_add(nf); +} +static void nfsd_file_lru_remove(struct nfsd_file *nf) +{ + if (list_lru_del(&nfsd_file_lru, &nf->nf_lru)) + trace_nfsd_file_lru_del(nf); +} + +static void +nfsd_file_hash_remove(struct nfsd_file *nf) +{ trace_nfsd_file_unhash(nf); if (nfsd_file_check_write_error(nf)) - nfsd_reset_boot_verifier(net_generic(nf->nf_net, nfsd_net_id)); - --nfsd_file_hashtbl[nf->nf_hashval].nfb_count; - hlist_del_rcu(&nf->nf_node); - atomic_long_dec(&nfsd_filecache_count); + 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); } static bool nfsd_file_unhash(struct nfsd_file *nf) { if (test_and_clear_bit(NFSD_FILE_HASHED, &nf->nf_flags)) { - nfsd_file_do_unhash(nf); - if (!list_empty(&nf->nf_lru)) - list_lru_del(&nfsd_file_lru, &nf->nf_lru); + nfsd_file_hash_remove(nf); return true; } return false; } -/* - * Return true if the file was unhashed. - */ -static bool -nfsd_file_unhash_and_release_locked(struct nfsd_file *nf, struct list_head *dispose) +static void +nfsd_file_unhash_and_dispose(struct nfsd_file *nf, struct list_head *dispose) { - lockdep_assert_held(&nfsd_file_hashtbl[nf->nf_hashval].nfb_lock); - - trace_nfsd_file_unhash_and_release_locked(nf); - if (!nfsd_file_unhash(nf)) - return false; - /* keep final reference for nfsd_file_lru_dispose */ - if (refcount_dec_not_one(&nf->nf_ref)) - return true; - - list_add(&nf->nf_lru, dispose); - return true; + trace_nfsd_file_unhash_and_dispose(nf); + if (nfsd_file_unhash(nf)) { + /* caller must call nfsd_file_dispose_list() later */ + nfsd_file_lru_remove(nf); + list_add(&nf->nf_lru, dispose); + } } static void @@ -293,6 +423,7 @@ nfsd_file_put_noref(struct nfsd_file *nf) if (refcount_dec_and_test(&nf->nf_ref)) { WARN_ON(test_bit(NFSD_FILE_HASHED, &nf->nf_flags)); + nfsd_file_lru_remove(nf); nfsd_file_free(nf); } } @@ -300,21 +431,35 @@ nfsd_file_put_noref(struct nfsd_file *nf) void nfsd_file_put(struct nfsd_file *nf) { - bool is_hashed; + might_sleep(); - set_bit(NFSD_FILE_REFERENCED, &nf->nf_flags); - if (refcount_read(&nf->nf_ref) > 2 || !nf->nf_file) { + nfsd_file_lru_add(nf); + if (test_bit(NFSD_FILE_HASHED, &nf->nf_flags) == 0) { + nfsd_file_flush(nf); + nfsd_file_put_noref(nf); + } else if (nf->nf_file) { nfsd_file_put_noref(nf); - return; - } - - filemap_flush(nf->nf_file->f_mapping); - is_hashed = test_bit(NFSD_FILE_HASHED, &nf->nf_flags) != 0; - nfsd_file_put_noref(nf); - if (is_hashed) nfsd_file_schedule_laundrette(); - if (atomic_long_read(&nfsd_filecache_count) >= NFSD_FILE_LRU_LIMIT) - nfsd_file_gc(); + } else + nfsd_file_put_noref(nf); +} + +/** + * nfsd_file_close - Close an nfsd_file + * @nf: nfsd_file to close + * + * If this is the final reference for @nf, free it immediately. + * This reflects an on-the-wire CLOSE or DELEGRETURN into the + * VFS and exported filesystem. + */ +void nfsd_file_close(struct nfsd_file *nf) +{ + nfsd_file_put(nf); + if (refcount_dec_if_one(&nf->nf_ref)) { + nfsd_file_unhash(nf); + nfsd_file_lru_remove(nf); + nfsd_file_free(nf); + } } struct nfsd_file * @@ -332,7 +477,8 @@ nfsd_file_dispose_list(struct list_head *dispose) while(!list_empty(dispose)) { nf = list_first_entry(dispose, struct nfsd_file, nf_lru); - list_del(&nf->nf_lru); + list_del_init(&nf->nf_lru); + nfsd_file_flush(nf); nfsd_file_put_noref(nf); } } @@ -345,7 +491,8 @@ nfsd_file_dispose_list_sync(struct list_head *dispose) while(!list_empty(dispose)) { nf = list_first_entry(dispose, struct nfsd_file, nf_lru); - list_del(&nf->nf_lru); + list_del_init(&nf->nf_lru); + nfsd_file_flush(nf); if (!refcount_dec_and_test(&nf->nf_ref)) continue; if (nfsd_file_free(nf)) @@ -367,19 +514,13 @@ nfsd_file_list_remove_disposal(struct list_head *dst, static void nfsd_file_list_add_disposal(struct list_head *files, struct net *net) { - struct nfsd_fcache_disposal *l; + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct nfsd_fcache_disposal *l = nn->fcache_disposal; - rcu_read_lock(); - list_for_each_entry_rcu(l, &laundrettes, list) { - if (l->net == net) { - spin_lock(&l->lock); - list_splice_tail_init(files, &l->freeme); - spin_unlock(&l->lock); - queue_work(nfsd_filecache_wq, &l->work); - break; - } - } - rcu_read_unlock(); + spin_lock(&l->lock); + list_splice_tail_init(files, &l->freeme); + spin_unlock(&l->lock); + queue_work(nfsd_filecache_wq, &l->work); } static void @@ -407,8 +548,17 @@ nfsd_file_dispose_list_delayed(struct list_head *dispose) } } -/* - * Note this can deadlock with nfsd_file_cache_purge. +/** + * 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: + * %LRU_REMOVED: @item was removed from the LRU + * %LRU_ROTATE: @item is to be moved to the LRU tail + * %LRU_SKIP: @item cannot be evicted */ static enum lru_status nfsd_file_lru_cb(struct list_head *item, struct list_lru_one *lru, @@ -429,55 +579,65 @@ nfsd_file_lru_cb(struct list_head *item, struct list_lru_one *lru, * counter. Here we check the counter and then test and clear the flag. * That order is deliberate to ensure that we can do this locklessly. */ - if (refcount_read(&nf->nf_ref) > 1) - goto out_skip; + if (refcount_read(&nf->nf_ref) > 1) { + list_lru_isolate(lru, &nf->nf_lru); + trace_nfsd_file_gc_in_use(nf); + return LRU_REMOVED; + } /* * Don't throw out files that are still undergoing I/O or * that have uncleared errors pending. */ - if (nfsd_file_check_writeback(nf)) - goto out_skip; + if (nfsd_file_check_writeback(nf)) { + trace_nfsd_file_gc_writeback(nf); + return LRU_SKIP; + } - if (test_and_clear_bit(NFSD_FILE_REFERENCED, &nf->nf_flags)) - goto out_skip; + if (test_and_clear_bit(NFSD_FILE_REFERENCED, &nf->nf_flags)) { + trace_nfsd_file_gc_referenced(nf); + return LRU_ROTATE; + } - if (!test_and_clear_bit(NFSD_FILE_HASHED, &nf->nf_flags)) - goto out_skip; + if (!test_and_clear_bit(NFSD_FILE_HASHED, &nf->nf_flags)) { + trace_nfsd_file_gc_hashed(nf); + return LRU_SKIP; + } list_lru_isolate_move(lru, &nf->nf_lru, head); + this_cpu_inc(nfsd_file_evictions); + trace_nfsd_file_gc_disposed(nf); return LRU_REMOVED; -out_skip: - return LRU_SKIP; } -static unsigned long -nfsd_file_lru_walk_list(struct shrink_control *sc) +/* + * Unhash items on @dispose immediately, then queue them on the + * disposal workqueue to finish releasing them in the background. + * + * cel: Note that between the time list_lru_shrink_walk runs and + * now, these items are in the hash table but marked unhashed. + * Why release these outside of lru_cb ? There's no lock ordering + * problem since lru_cb currently takes no lock. + */ +static void nfsd_file_gc_dispose_list(struct list_head *dispose) { - LIST_HEAD(head); struct nfsd_file *nf; - unsigned long ret; - if (sc) - ret = list_lru_shrink_walk(&nfsd_file_lru, sc, - nfsd_file_lru_cb, &head); - else - ret = list_lru_walk(&nfsd_file_lru, - nfsd_file_lru_cb, - &head, LONG_MAX); - list_for_each_entry(nf, &head, nf_lru) { - spin_lock(&nfsd_file_hashtbl[nf->nf_hashval].nfb_lock); - nfsd_file_do_unhash(nf); - spin_unlock(&nfsd_file_hashtbl[nf->nf_hashval].nfb_lock); - } - nfsd_file_dispose_list_delayed(&head); - return ret; + list_for_each_entry(nf, dispose, nf_lru) + nfsd_file_hash_remove(nf); + nfsd_file_dispose_list_delayed(dispose); } static void nfsd_file_gc(void) { - nfsd_file_lru_walk_list(NULL); + LIST_HEAD(dispose); + unsigned long ret; + + ret = list_lru_walk(&nfsd_file_lru, nfsd_file_lru_cb, + &dispose, list_lru_count(&nfsd_file_lru)); + trace_nfsd_file_gc_removed(ret, list_lru_count(&nfsd_file_lru)); + nfsd_file_gc_dispose_list(&dispose); } static void @@ -496,7 +656,14 @@ nfsd_file_lru_count(struct shrinker *s, struct shrink_control *sc) static unsigned long nfsd_file_lru_scan(struct shrinker *s, struct shrink_control *sc) { - return nfsd_file_lru_walk_list(sc); + LIST_HEAD(dispose); + unsigned long ret; + + ret = list_lru_shrink_walk(&nfsd_file_lru, sc, + nfsd_file_lru_cb, &dispose); + trace_nfsd_file_shrinker_removed(ret, list_lru_count(&nfsd_file_lru)); + nfsd_file_gc_dispose_list(&dispose); + return ret; } static struct shrinker nfsd_file_shrinker = { @@ -505,39 +672,47 @@ static struct shrinker nfsd_file_shrinker = { .seeks = 1, }; -static void -__nfsd_file_close_inode(struct inode *inode, unsigned int hashval, - struct list_head *dispose) +/* + * Find all cache items across all net namespaces that match @inode and + * move them to @dispose. The lookup is atomic wrt nfsd_file_acquire(). + */ +static unsigned int +__nfsd_file_close_inode(struct inode *inode, struct list_head *dispose) { - struct nfsd_file *nf; - struct hlist_node *tmp; + struct nfsd_file_lookup_key key = { + .type = NFSD_FILE_KEY_INODE, + .inode = inode, + }; + unsigned int count = 0; + struct nfsd_file *nf; - spin_lock(&nfsd_file_hashtbl[hashval].nfb_lock); - hlist_for_each_entry_safe(nf, tmp, &nfsd_file_hashtbl[hashval].nfb_head, nf_node) { - if (inode == nf->nf_inode) - nfsd_file_unhash_and_release_locked(nf, dispose); - } - spin_unlock(&nfsd_file_hashtbl[hashval].nfb_lock); + rcu_read_lock(); + do { + nf = rhashtable_lookup(&nfsd_file_rhash_tbl, &key, + nfsd_file_rhash_params); + if (!nf) + break; + nfsd_file_unhash_and_dispose(nf, dispose); + count++; + } while (1); + rcu_read_unlock(); + return count; } /** * nfsd_file_close_inode_sync - attempt to forcibly close a nfsd_file * @inode: inode of the file to attempt to remove * - * Walk the whole hash bucket, looking for any files that correspond to "inode". - * If any do, then unhash them and put the hashtable reference to them and - * destroy any that had their last reference put. Also ensure that any of the - * fputs also have their final __fput done as well. + * Unhash and put, then flush and fput all cache items associated with @inode. */ void nfsd_file_close_inode_sync(struct inode *inode) { - unsigned int hashval = (unsigned int)hash_long(inode->i_ino, - NFSD_FILE_HASH_BITS); LIST_HEAD(dispose); + unsigned int count; - __nfsd_file_close_inode(inode, hashval, &dispose); - trace_nfsd_file_close_inode_sync(inode, hashval, !list_empty(&dispose)); + count = __nfsd_file_close_inode(inode, &dispose); + trace_nfsd_file_close_inode_sync(inode, count); nfsd_file_dispose_list_sync(&dispose); } @@ -545,19 +720,16 @@ nfsd_file_close_inode_sync(struct inode *inode) * nfsd_file_close_inode - attempt a delayed close of a nfsd_file * @inode: inode of the file to attempt to remove * - * Walk the whole hash bucket, looking for any files that correspond to "inode". - * If any do, then unhash them and put the hashtable reference to them and - * destroy any that had their last reference put. + * Unhash and put all cache item associated with @inode. */ static void nfsd_file_close_inode(struct inode *inode) { - unsigned int hashval = (unsigned int)hash_long(inode->i_ino, - NFSD_FILE_HASH_BITS); LIST_HEAD(dispose); + unsigned int count; - __nfsd_file_close_inode(inode, hashval, &dispose); - trace_nfsd_file_close_inode(inode, hashval, !list_empty(&dispose)); + count = __nfsd_file_close_inode(inode, &dispose); + trace_nfsd_file_close_inode(inode, count); nfsd_file_dispose_list_delayed(&dispose); } @@ -567,8 +739,6 @@ nfsd_file_close_inode(struct inode *inode) * * Walk the LRU list and close any entries that have not been used since * the last scan. - * - * Note this can deadlock with nfsd_file_cache_purge. */ static void nfsd_file_delayed_close(struct work_struct *work) @@ -632,25 +802,21 @@ static const struct fsnotify_ops nfsd_file_fsnotify_ops = { int nfsd_file_cache_init(void) { - int ret = -ENOMEM; - unsigned int i; + int ret; - clear_bit(NFSD_FILE_SHUTDOWN, &nfsd_file_lru_flags); - - if (nfsd_file_hashtbl) + lockdep_assert_held(&nfsd_mutex); + 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); + if (ret) + return ret; + + ret = -ENOMEM; nfsd_filecache_wq = alloc_workqueue("nfsd_filecache", 0, 0); if (!nfsd_filecache_wq) goto out; - nfsd_file_hashtbl = kcalloc(NFSD_FILE_HASH_SIZE, - sizeof(*nfsd_file_hashtbl), GFP_KERNEL); - if (!nfsd_file_hashtbl) { - pr_err("nfsd: unable to allocate nfsd_file_hashtbl\n"); - goto out_err; - } - nfsd_file_slab = kmem_cache_create("nfsd_file", sizeof(struct nfsd_file), 0, 0, NULL); if (!nfsd_file_slab) { @@ -672,7 +838,7 @@ nfsd_file_cache_init(void) goto out_err; } - ret = register_shrinker(&nfsd_file_shrinker); + ret = register_shrinker(&nfsd_file_shrinker, "nfsd-filecache"); if (ret) { pr_err("nfsd: failed to register nfsd_file_shrinker: %d\n", ret); goto out_lru; @@ -684,7 +850,8 @@ nfsd_file_cache_init(void) goto out_shrinker; } - nfsd_file_fsnotify_group = fsnotify_alloc_group(&nfsd_file_fsnotify_ops); + nfsd_file_fsnotify_group = fsnotify_alloc_group(&nfsd_file_fsnotify_ops, + FSNOTIFY_GROUP_NOFS); if (IS_ERR(nfsd_file_fsnotify_group)) { pr_err("nfsd: unable to create fsnotify group: %ld\n", PTR_ERR(nfsd_file_fsnotify_group)); @@ -693,11 +860,6 @@ nfsd_file_cache_init(void) goto out_notifier; } - for (i = 0; i < NFSD_FILE_HASH_SIZE; i++) { - INIT_HLIST_HEAD(&nfsd_file_hashtbl[i].nfb_head); - spin_lock_init(&nfsd_file_hashtbl[i].nfb_lock); - } - INIT_DELAYED_WORK(&nfsd_filecache_laundrette, nfsd_file_gc_worker); out: return ret; @@ -712,50 +874,39 @@ out_err: nfsd_file_slab = NULL; kmem_cache_destroy(nfsd_file_mark_slab); nfsd_file_mark_slab = NULL; - kfree(nfsd_file_hashtbl); - nfsd_file_hashtbl = NULL; destroy_workqueue(nfsd_filecache_wq); nfsd_filecache_wq = NULL; + rhashtable_destroy(&nfsd_file_rhash_tbl); goto out; } -/* - * Note this can deadlock with nfsd_file_lru_cb. - */ -void -nfsd_file_cache_purge(struct net *net) +static void +__nfsd_file_cache_purge(struct net *net) { - unsigned int i; - struct nfsd_file *nf; - struct hlist_node *next; + struct rhashtable_iter iter; + struct nfsd_file *nf; LIST_HEAD(dispose); - bool del; - if (!nfsd_file_hashtbl) - return; + rhashtable_walk_enter(&nfsd_file_rhash_tbl, &iter); + do { + rhashtable_walk_start(&iter); - for (i = 0; i < NFSD_FILE_HASH_SIZE; i++) { - struct nfsd_fcache_bucket *nfb = &nfsd_file_hashtbl[i]; + nf = rhashtable_walk_next(&iter); + while (!IS_ERR_OR_NULL(nf)) { + if (!net || nf->nf_net == net) + nfsd_file_unhash_and_dispose(nf, &dispose); + nf = rhashtable_walk_next(&iter); + } - spin_lock(&nfb->nfb_lock); - hlist_for_each_entry_safe(nf, next, &nfb->nfb_head, nf_node) { - if (net && nf->nf_net != net) - continue; - del = nfsd_file_unhash_and_release_locked(nf, &dispose); + rhashtable_walk_stop(&iter); + } while (nf == ERR_PTR(-EAGAIN)); + rhashtable_walk_exit(&iter); - /* - * Deadlock detected! Something marked this entry as - * unhased, but hasn't removed it from the hash list. - */ - WARN_ON_ONCE(!del); - } - spin_unlock(&nfb->nfb_lock); - nfsd_file_dispose_list(&dispose); - } + nfsd_file_dispose_list(&dispose); } static struct nfsd_fcache_disposal * -nfsd_alloc_fcache_disposal(struct net *net) +nfsd_alloc_fcache_disposal(void) { struct nfsd_fcache_disposal *l; @@ -763,7 +914,6 @@ nfsd_alloc_fcache_disposal(struct net *net) if (!l) return NULL; INIT_WORK(&l->work, nfsd_file_delayed_close); - l->net = net; spin_lock_init(&l->lock); INIT_LIST_HEAD(&l->freeme); return l; @@ -772,61 +922,40 @@ nfsd_alloc_fcache_disposal(struct net *net) static void nfsd_free_fcache_disposal(struct nfsd_fcache_disposal *l) { - rcu_assign_pointer(l->net, NULL); cancel_work_sync(&l->work); nfsd_file_dispose_list(&l->freeme); - kfree_rcu(l, rcu); -} - -static void -nfsd_add_fcache_disposal(struct nfsd_fcache_disposal *l) -{ - spin_lock(&laundrette_lock); - list_add_tail_rcu(&l->list, &laundrettes); - spin_unlock(&laundrette_lock); + kfree(l); } static void -nfsd_del_fcache_disposal(struct nfsd_fcache_disposal *l) -{ - spin_lock(&laundrette_lock); - list_del_rcu(&l->list); - spin_unlock(&laundrette_lock); -} - -static int -nfsd_alloc_fcache_disposal_net(struct net *net) +nfsd_free_fcache_disposal_net(struct net *net) { - struct nfsd_fcache_disposal *l; + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct nfsd_fcache_disposal *l = nn->fcache_disposal; - l = nfsd_alloc_fcache_disposal(net); - if (!l) - return -ENOMEM; - nfsd_add_fcache_disposal(l); - return 0; + nfsd_free_fcache_disposal(l); } -static void -nfsd_free_fcache_disposal_net(struct net *net) +int +nfsd_file_cache_start_net(struct net *net) { - struct nfsd_fcache_disposal *l; + struct nfsd_net *nn = net_generic(net, nfsd_net_id); - rcu_read_lock(); - list_for_each_entry_rcu(l, &laundrettes, list) { - if (l->net != net) - continue; - nfsd_del_fcache_disposal(l); - rcu_read_unlock(); - nfsd_free_fcache_disposal(l); - return; - } - rcu_read_unlock(); + nn->fcache_disposal = nfsd_alloc_fcache_disposal(); + return nn->fcache_disposal ? 0 : -ENOMEM; } -int -nfsd_file_cache_start_net(struct net *net) +/** + * nfsd_file_cache_purge - Remove all cache items associated with @net + * @net: target net namespace + * + */ +void +nfsd_file_cache_purge(struct net *net) { - return nfsd_alloc_fcache_disposal_net(net); + lockdep_assert_held(&nfsd_mutex); + if (test_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags) == 1) + __nfsd_file_cache_purge(net); } void @@ -839,7 +968,11 @@ nfsd_file_cache_shutdown_net(struct net *net) void nfsd_file_cache_shutdown(void) { - set_bit(NFSD_FILE_SHUTDOWN, &nfsd_file_lru_flags); + int i; + + lockdep_assert_held(&nfsd_mutex); + if (test_and_clear_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags) == 0) + return; lease_unregister_notifier(&nfsd_file_lease_notifier); unregister_shrinker(&nfsd_file_shrinker); @@ -848,7 +981,7 @@ nfsd_file_cache_shutdown(void) * calling nfsd_file_cache_purge */ cancel_delayed_work_sync(&nfsd_filecache_laundrette); - nfsd_file_cache_purge(NULL); + __nfsd_file_cache_purge(NULL); list_lru_destroy(&nfsd_file_lru); rcu_barrier(); fsnotify_put_group(nfsd_file_fsnotify_group); @@ -858,240 +991,241 @@ nfsd_file_cache_shutdown(void) fsnotify_wait_marks_destroyed(); kmem_cache_destroy(nfsd_file_mark_slab); nfsd_file_mark_slab = NULL; - kfree(nfsd_file_hashtbl); - nfsd_file_hashtbl = NULL; destroy_workqueue(nfsd_filecache_wq); nfsd_filecache_wq = NULL; -} - -static bool -nfsd_match_cred(const struct cred *c1, const struct cred *c2) -{ - int i; - - if (!uid_eq(c1->fsuid, c2->fsuid)) - return false; - if (!gid_eq(c1->fsgid, c2->fsgid)) - return false; - if (c1->group_info == NULL || c2->group_info == NULL) - return c1->group_info == c2->group_info; - if (c1->group_info->ngroups != c2->group_info->ngroups) - return false; - for (i = 0; i < c1->group_info->ngroups; i++) { - if (!gid_eq(c1->group_info->gid[i], c2->group_info->gid[i])) - return false; - } - return true; -} - -static struct nfsd_file * -nfsd_file_find_locked(struct inode *inode, unsigned int may_flags, - unsigned int hashval, struct net *net) -{ - struct nfsd_file *nf; - unsigned char need = may_flags & NFSD_FILE_MAY_MASK; - - hlist_for_each_entry_rcu(nf, &nfsd_file_hashtbl[hashval].nfb_head, - nf_node, lockdep_is_held(&nfsd_file_hashtbl[hashval].nfb_lock)) { - if (nf->nf_may != need) - continue; - if (nf->nf_inode != inode) - continue; - if (nf->nf_net != net) - continue; - if (!nfsd_match_cred(nf->nf_cred, current_cred())) - continue; - if (!test_bit(NFSD_FILE_HASHED, &nf->nf_flags)) - continue; - if (nfsd_file_get(nf) != NULL) - return nf; + rhashtable_destroy(&nfsd_file_rhash_tbl); + + for_each_possible_cpu(i) { + per_cpu(nfsd_file_cache_hits, i) = 0; + per_cpu(nfsd_file_acquisitions, i) = 0; + per_cpu(nfsd_file_releases, i) = 0; + per_cpu(nfsd_file_total_age, i) = 0; + per_cpu(nfsd_file_pages_flushed, i) = 0; + per_cpu(nfsd_file_evictions, i) = 0; } - return NULL; } /** - * nfsd_file_is_cached - are there any cached open files for this fh? - * @inode: inode of the file to check + * nfsd_file_is_cached - are there any cached open files for this inode? + * @inode: inode to check * - * Scan the hashtable for open files that match this fh. Returns true if there - * are any, and false if not. + * The lookup matches inodes in all net namespaces and is atomic wrt + * nfsd_file_acquire(). + * + * Return values: + * %true: filecache contains at least one file matching this inode + * %false: filecache contains no files matching this inode */ bool nfsd_file_is_cached(struct inode *inode) { - bool ret = false; - struct nfsd_file *nf; - unsigned int hashval; - - hashval = (unsigned int)hash_long(inode->i_ino, NFSD_FILE_HASH_BITS); - - rcu_read_lock(); - hlist_for_each_entry_rcu(nf, &nfsd_file_hashtbl[hashval].nfb_head, - nf_node) { - if (inode == nf->nf_inode) { - ret = true; - break; - } - } - rcu_read_unlock(); - trace_nfsd_file_is_cached(inode, hashval, (int)ret); + struct nfsd_file_lookup_key key = { + .type = NFSD_FILE_KEY_INODE, + .inode = inode, + }; + bool ret = false; + + if (rhashtable_lookup_fast(&nfsd_file_rhash_tbl, &key, + nfsd_file_rhash_params) != NULL) + ret = true; + trace_nfsd_file_is_cached(inode, (int)ret); return ret; } -__be32 -nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, - unsigned int may_flags, struct nfsd_file **pnf) +static __be32 +nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, + unsigned int may_flags, struct nfsd_file **pnf, bool open) { - __be32 status; - struct net *net = SVC_NET(rqstp); - struct nfsd_file *nf, *new; - struct inode *inode; - unsigned int hashval; - bool retry = true; - - /* FIXME: skip this if fh_dentry is already set? */ + struct nfsd_file_lookup_key key = { + .type = NFSD_FILE_KEY_FULL, + .need = may_flags & NFSD_FILE_MAY_MASK, + .net = SVC_NET(rqstp), + }; + bool open_retry = true; + struct nfsd_file *nf; + __be32 status; + int ret; + status = fh_verify(rqstp, fhp, S_IFREG, 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); - hashval = (unsigned int)hash_long(inode->i_ino, NFSD_FILE_HASH_BITS); retry: rcu_read_lock(); - nf = nfsd_file_find_locked(inode, may_flags, hashval, net); + nf = rhashtable_lookup(&nfsd_file_rhash_tbl, &key, + nfsd_file_rhash_params); + if (nf) + nf = nfsd_file_get(nf); rcu_read_unlock(); if (nf) goto wait_for_construction; - new = nfsd_file_alloc(inode, may_flags, hashval, net); - if (!new) { - trace_nfsd_file_acquire(rqstp, hashval, inode, may_flags, - NULL, nfserr_jukebox); - return nfserr_jukebox; + nf = nfsd_file_alloc(&key, may_flags); + if (!nf) { + status = nfserr_jukebox; + goto out_status; } - spin_lock(&nfsd_file_hashtbl[hashval].nfb_lock); - nf = nfsd_file_find_locked(inode, may_flags, hashval, net); - if (nf == NULL) + ret = rhashtable_lookup_insert_key(&nfsd_file_rhash_tbl, + &key, &nf->nf_rhash, + nfsd_file_rhash_params); + if (likely(ret == 0)) goto open_file; - spin_unlock(&nfsd_file_hashtbl[hashval].nfb_lock); - nfsd_file_slab_free(&new->nf_rcu); + + 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); + status = nfserr_jukebox; + goto out_status; 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)) { - if (!retry) { + trace_nfsd_file_cons_err(rqstp, key.inode, may_flags, nf); + if (!open_retry) { status = nfserr_jukebox; goto out; } - retry = false; + open_retry = false; nfsd_file_put_noref(nf); goto retry; } + nfsd_file_lru_remove(nf); this_cpu_inc(nfsd_file_cache_hits); - if (!(may_flags & NFSD_MAY_NOT_BREAK_LEASE)) { - bool write = (may_flags & NFSD_MAY_WRITE); - - if (test_bit(NFSD_FILE_BREAK_READ, &nf->nf_flags) || - (test_bit(NFSD_FILE_BREAK_WRITE, &nf->nf_flags) && write)) { - status = nfserrno(nfsd_open_break_lease( - file_inode(nf->nf_file), may_flags)); - if (status == nfs_ok) { - clear_bit(NFSD_FILE_BREAK_READ, &nf->nf_flags); - if (write) - clear_bit(NFSD_FILE_BREAK_WRITE, - &nf->nf_flags); - } - } - } + status = nfserrno(nfsd_open_break_lease(file_inode(nf->nf_file), may_flags)); out: if (status == nfs_ok) { + if (open) + this_cpu_inc(nfsd_file_acquisitions); *pnf = nf; } else { nfsd_file_put(nf); nf = NULL; } - trace_nfsd_file_acquire(rqstp, hashval, inode, may_flags, nf, status); +out_status: + put_cred(key.cred); + if (open) + trace_nfsd_file_acquire(rqstp, key.inode, may_flags, nf, status); return status; + open_file: - nf = new; - /* Take reference for the hashtable */ - refcount_inc(&nf->nf_ref); - __set_bit(NFSD_FILE_HASHED, &nf->nf_flags); - __set_bit(NFSD_FILE_PENDING, &nf->nf_flags); - list_lru_add(&nfsd_file_lru, &nf->nf_lru); - hlist_add_head_rcu(&nf->nf_node, &nfsd_file_hashtbl[hashval].nfb_head); - ++nfsd_file_hashtbl[hashval].nfb_count; - nfsd_file_hashtbl[hashval].nfb_maxcount = max(nfsd_file_hashtbl[hashval].nfb_maxcount, - nfsd_file_hashtbl[hashval].nfb_count); - spin_unlock(&nfsd_file_hashtbl[hashval].nfb_lock); - if (atomic_long_inc_return(&nfsd_filecache_count) >= NFSD_FILE_LRU_THRESHOLD) - nfsd_file_gc(); - - nf->nf_mark = nfsd_file_mark_find_or_create(nf); - if (nf->nf_mark) - status = nfsd_open_verified(rqstp, fhp, S_IFREG, - may_flags, &nf->nf_file); - else + trace_nfsd_file_alloc(nf); + nf->nf_mark = nfsd_file_mark_find_or_create(nf, key.inode); + if (nf->nf_mark) { + if (open) { + status = nfsd_open_verified(rqstp, fhp, may_flags, + &nf->nf_file); + trace_nfsd_file_open(nf, status); + } else + status = nfs_ok; + } else status = nfserr_jukebox; /* * If construction failed, or we raced with a call to unlink() * then unhash. */ - if (status != nfs_ok || inode->i_nlink == 0) { - bool do_free; - spin_lock(&nfsd_file_hashtbl[hashval].nfb_lock); - do_free = nfsd_file_unhash(nf); - spin_unlock(&nfsd_file_hashtbl[hashval].nfb_lock); - if (do_free) + if (status != nfs_ok || key.inode->i_nlink == 0) + if (nfsd_file_unhash(nf)) nfsd_file_put_noref(nf); - } clear_bit_unlock(NFSD_FILE_PENDING, &nf->nf_flags); smp_mb__after_atomic(); wake_up_bit(&nf->nf_flags, NFSD_FILE_PENDING); goto out; } +/** + * nfsd_file_acquire - Get a struct nfsd_file with an open file + * @rqstp: the RPC transaction being executed + * @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 + * + * Returns nfs_ok and sets @pnf on success; otherwise an nfsstat 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, pnf, true); +} + +/** + * nfsd_file_create - Get a struct nfsd_file, do not open + * @rqstp: the RPC transaction being executed + * @fhp: the NFS filehandle of the file just created + * @may_flags: NFSD_MAY_ settings for the file + * @pnf: OUT: new or found "struct nfsd_file" object + * + * Returns nfs_ok and sets @pnf on success; otherwise an nfsstat in + * network byte order is returned. + */ +__be32 +nfsd_file_create(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, pnf, false); +} + /* * Note that fields may be added, removed or reordered in the future. Programs * scraping this file for info should test the labels to ensure they're * getting the correct field. */ -static int nfsd_file_cache_stats_show(struct seq_file *m, void *v) +int nfsd_file_cache_stats_show(struct seq_file *m, void *v) { - unsigned int i, count = 0, longest = 0; - unsigned long hits = 0; + unsigned long releases = 0, pages_flushed = 0, evictions = 0; + unsigned long hits = 0, acquisitions = 0; + unsigned int i, count = 0, buckets = 0; + unsigned long lru = 0, total_age = 0; - /* - * No need for spinlocks here since we're not terribly interested in - * accuracy. We do take the nfsd_mutex simply to ensure that we - * don't end up racing with server shutdown - */ + /* Serialize with server shutdown */ mutex_lock(&nfsd_mutex); - if (nfsd_file_hashtbl) { - for (i = 0; i < NFSD_FILE_HASH_SIZE; i++) { - count += nfsd_file_hashtbl[i].nfb_count; - longest = max(longest, nfsd_file_hashtbl[i].nfb_count); - } + if (test_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags) == 1) { + struct bucket_table *tbl; + struct rhashtable *ht; + + lru = list_lru_count(&nfsd_file_lru); + + rcu_read_lock(); + ht = &nfsd_file_rhash_tbl; + count = atomic_read(&ht->nelems); + tbl = rht_dereference_rcu(ht->tbl, ht); + buckets = tbl->size; + rcu_read_unlock(); } mutex_unlock(&nfsd_mutex); - for_each_possible_cpu(i) + for_each_possible_cpu(i) { hits += per_cpu(nfsd_file_cache_hits, i); + acquisitions += per_cpu(nfsd_file_acquisitions, i); + releases += per_cpu(nfsd_file_releases, i); + total_age += per_cpu(nfsd_file_total_age, i); + evictions += per_cpu(nfsd_file_evictions, i); + pages_flushed += per_cpu(nfsd_file_pages_flushed, i); + } seq_printf(m, "total entries: %u\n", count); - seq_printf(m, "longest chain: %u\n", longest); + 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, "releases: %lu\n", releases); + seq_printf(m, "evictions: %lu\n", evictions); + if (releases) + seq_printf(m, "mean age (ms): %ld\n", total_age / releases); + else + seq_printf(m, "mean age (ms): -\n"); + seq_printf(m, "pages flushed: %lu\n", pages_flushed); return 0; } - -int nfsd_file_cache_stats_open(struct inode *inode, struct file *file) -{ - return single_open(file, nfsd_file_cache_stats_show, NULL); -} diff --git a/fs/nfsd/filecache.h b/fs/nfsd/filecache.h index 7872df5a0fe3..357832bac736 100644 --- a/fs/nfsd/filecache.h +++ b/fs/nfsd/filecache.h @@ -29,7 +29,7 @@ struct nfsd_file_mark { * never be dereferenced, only used for comparison. */ struct nfsd_file { - struct hlist_node nf_node; + struct rhash_head nf_rhash; struct list_head nf_lru; struct rcu_head nf_rcu; struct file *nf_file; @@ -37,16 +37,13 @@ struct nfsd_file { struct net *nf_net; #define NFSD_FILE_HASHED (0) #define NFSD_FILE_PENDING (1) -#define NFSD_FILE_BREAK_READ (2) -#define NFSD_FILE_BREAK_WRITE (3) -#define NFSD_FILE_REFERENCED (4) +#define NFSD_FILE_REFERENCED (2) unsigned long nf_flags; - struct inode *nf_inode; - unsigned int nf_hashval; + struct inode *nf_inode; /* don't deref */ refcount_t nf_ref; unsigned char nf_may; struct nfsd_file_mark *nf_mark; - struct rw_semaphore nf_rwsem; + ktime_t nf_birthtime; }; int nfsd_file_cache_init(void); @@ -55,10 +52,13 @@ 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); +void nfsd_file_close(struct nfsd_file *nf); struct nfsd_file *nfsd_file_get(struct nfsd_file *nf); void nfsd_file_close_inode_sync(struct inode *inode); bool nfsd_file_is_cached(struct inode *inode); __be32 nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned int may_flags, struct nfsd_file **nfp); -int nfsd_file_cache_stats_open(struct inode *, struct file *); +__be32 nfsd_file_create(struct svc_rqst *rqstp, struct svc_fh *fhp, + unsigned int may_flags, struct nfsd_file **nfp); +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 2e2f1d5e9f62..070f90ed09b6 100644 --- a/fs/nfsd/flexfilelayout.c +++ b/fs/nfsd/flexfilelayout.c @@ -117,7 +117,7 @@ nfsd4_ff_proc_getdeviceinfo(struct super_block *sb, struct svc_rqst *rqstp, da->netaddr.addr_len = snprintf(da->netaddr.addr, FF_ADDR_LEN + 1, - "%s.%hhu.%hhu", addr, port >> 8, port & 0xff); + "%s.%d.%d", addr, port >> 8, port & 0xff); da->tightly_coupled = false; diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index 935c1028c217..8c854ba3285b 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -11,6 +11,7 @@ #include <net/net_namespace.h> #include <net/netns/generic.h> #include <linux/percpu_counter.h> +#include <linux/siphash.h> /* Hash tables for nfs4_clientid state */ #define CLIENT_HASH_BITS 4 @@ -108,9 +109,8 @@ struct nfsd_net { bool nfsd_net_up; bool lockd_up; - /* Time of server startup */ - struct timespec64 nfssvc_boot; - seqlock_t boot_lock; + seqlock_t writeverf_lock; + unsigned char writeverf[8]; /* * Max number of connections this nfsd container will allow. Defaults @@ -123,12 +123,13 @@ struct nfsd_net { u32 clverifier_counter; struct svc_serv *nfsd_serv; - - wait_queue_head_t ntf_wq; - atomic_t ntf_refcnt; - - /* Allow umount to wait for nfsd state cleanup */ - struct completion nfsd_shutdown_complete; + /* 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; /* * clientid and stateid data for construction of net unique COPY @@ -184,6 +185,17 @@ struct nfsd_net { /* utsname taken from the process that starts the server */ char nfsd_name[UNX_MAXNODENAME+1]; + + struct nfsd_fcache_disposal *fcache_disposal; + + siphash_key_t siphash_key; + + atomic_t nfs4_client_count; + int nfs4_max_clients; + + atomic_t nfsd_courtesy_clients; + struct shrinker nfsd_client_shrinker; + struct delayed_work nfsd_shrinker_work; }; /* Simple check to find out if a given net was properly initialized */ @@ -193,6 +205,6 @@ extern void nfsd_netns_free_versions(struct nfsd_net *nn); extern unsigned int nfsd_net_id; -void nfsd_copy_boot_verifier(__be32 verf[2], struct nfsd_net *nn); -void nfsd_reset_boot_verifier(struct nfsd_net *nn); +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 367551bddfc6..13e6e6897f6c 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -111,7 +111,7 @@ static __be32 nfsacld_proc_setacl(struct svc_rqst *rqstp) if (error) goto out_errno; - fh_lock(fh); + inode_lock(inode); error = set_posix_acl(&init_user_ns, inode, ACL_TYPE_ACCESS, argp->acl_access); @@ -122,7 +122,7 @@ static __be32 nfsacld_proc_setacl(struct svc_rqst *rqstp) if (error) goto out_drop_lock; - fh_unlock(fh); + inode_unlock(inode); fh_drop_write(fh); @@ -136,7 +136,7 @@ out: return rpc_success; out_drop_lock: - fh_unlock(fh); + inode_unlock(inode); fh_drop_write(fh); out_errno: resp->status = nfserrno(error); @@ -249,34 +249,34 @@ nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, struct xdr_stream *xdr) int w; if (!svcxdr_encode_stat(xdr, resp->status)) - return 0; + return false; if (dentry == NULL || d_really_is_negative(dentry)) - return 1; + return true; inode = d_inode(dentry); if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat)) - return 0; + return false; if (xdr_stream_encode_u32(xdr, resp->mask) < 0) - return 0; + return false; rqstp->rq_res.page_len = w = nfsacl_size( (resp->mask & NFS_ACL) ? resp->acl_access : NULL, (resp->mask & NFS_DFACL) ? resp->acl_default : NULL); while (w > 0) { if (!*(rqstp->rq_next_page++)) - return 1; + return true; w -= PAGE_SIZE; } if (!nfs_stream_encode_acl(xdr, inode, resp->acl_access, resp->mask & NFS_ACL, 0)) - return 0; + return false; if (!nfs_stream_encode_acl(xdr, inode, resp->acl_default, resp->mask & NFS_DFACL, NFS_ACL_DEFAULT)) - return 0; + return false; - return 1; + return true; } /* ACCESS */ @@ -286,17 +286,17 @@ nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, struct xdr_stream *xdr) struct nfsd3_accessres *resp = rqstp->rq_resp; if (!svcxdr_encode_stat(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat)) - return 0; + return false; if (xdr_stream_encode_u32(xdr, resp->access) < 0) - return 0; + return false; break; } - return 1; + return true; } /* @@ -331,6 +331,7 @@ static const struct svc_procedure nfsd_acl_procedures2[5] = { .pc_decode = nfssvc_decode_voidarg, .pc_encode = nfssvc_encode_voidres, .pc_argsize = sizeof(struct nfsd_voidargs), + .pc_argzero = sizeof(struct nfsd_voidargs), .pc_ressize = sizeof(struct nfsd_voidres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST, @@ -342,6 +343,7 @@ static const struct svc_procedure nfsd_acl_procedures2[5] = { .pc_encode = nfsaclsvc_encode_getaclres, .pc_release = nfsaclsvc_release_getacl, .pc_argsize = sizeof(struct nfsd3_getaclargs), + .pc_argzero = sizeof(struct nfsd3_getaclargs), .pc_ressize = sizeof(struct nfsd3_getaclres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+1+2*(1+ACL), @@ -353,6 +355,7 @@ static const struct svc_procedure nfsd_acl_procedures2[5] = { .pc_encode = nfssvc_encode_attrstatres, .pc_release = nfssvc_release_attrstat, .pc_argsize = sizeof(struct nfsd3_setaclargs), + .pc_argzero = sizeof(struct nfsd3_setaclargs), .pc_ressize = sizeof(struct nfsd_attrstat), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+AT, @@ -364,6 +367,7 @@ static const struct svc_procedure nfsd_acl_procedures2[5] = { .pc_encode = nfssvc_encode_attrstatres, .pc_release = nfssvc_release_attrstat, .pc_argsize = sizeof(struct nfsd_fhandle), + .pc_argzero = sizeof(struct nfsd_fhandle), .pc_ressize = sizeof(struct nfsd_attrstat), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+AT, @@ -375,6 +379,7 @@ static const struct svc_procedure nfsd_acl_procedures2[5] = { .pc_encode = nfsaclsvc_encode_accessres, .pc_release = nfsaclsvc_release_access, .pc_argsize = sizeof(struct nfsd3_accessargs), + .pc_argzero = sizeof(struct nfsd3_accessargs), .pc_ressize = sizeof(struct nfsd3_accessres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+AT+1, diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index 35b2ebda14da..2fb9ee356455 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -101,7 +101,7 @@ static __be32 nfsd3_proc_setacl(struct svc_rqst *rqstp) if (error) goto out_errno; - fh_lock(fh); + inode_lock(inode); error = set_posix_acl(&init_user_ns, inode, ACL_TYPE_ACCESS, argp->acl_access); @@ -111,7 +111,7 @@ static __be32 nfsd3_proc_setacl(struct svc_rqst *rqstp) argp->acl_default); out_drop_lock: - fh_unlock(fh); + inode_unlock(inode); fh_drop_write(fh); out_errno: resp->status = nfserrno(error); @@ -252,6 +252,7 @@ static const struct svc_procedure nfsd_acl_procedures3[3] = { .pc_decode = nfssvc_decode_voidarg, .pc_encode = nfssvc_encode_voidres, .pc_argsize = sizeof(struct nfsd_voidargs), + .pc_argzero = sizeof(struct nfsd_voidargs), .pc_ressize = sizeof(struct nfsd_voidres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST, @@ -263,6 +264,7 @@ static const struct svc_procedure nfsd_acl_procedures3[3] = { .pc_encode = nfs3svc_encode_getaclres, .pc_release = nfs3svc_release_getacl, .pc_argsize = sizeof(struct nfsd3_getaclargs), + .pc_argzero = sizeof(struct nfsd3_getaclargs), .pc_ressize = sizeof(struct nfsd3_getaclres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+1+2*(1+ACL), @@ -274,6 +276,7 @@ static const struct svc_procedure nfsd_acl_procedures3[3] = { .pc_encode = nfs3svc_encode_setaclres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_setaclargs), + .pc_argzero = sizeof(struct nfsd3_setaclargs), .pc_ressize = sizeof(struct nfsd3_attrstat), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+pAT, diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index 15dac36ca852..923d9a80df92 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -8,6 +8,7 @@ #include <linux/fs.h> #include <linux/ext2_fs.h> #include <linux/magic.h> +#include <linux/namei.h> #include "cache.h" #include "xdr3.h" @@ -66,12 +67,15 @@ nfsd3_proc_setattr(struct svc_rqst *rqstp) { struct nfsd3_sattrargs *argp = rqstp->rq_argp; struct nfsd3_attrstat *resp = rqstp->rq_resp; + struct nfsd_attrs attrs = { + .na_iattr = &argp->attrs, + }; dprintk("nfsd: SETATTR(3) %s\n", SVCFH_fmt(&argp->fh)); fh_copy(&resp->fh, &argp->fh); - resp->status = nfsd_setattr(rqstp, &resp->fh, &argp->attrs, + resp->status = nfsd_setattr(rqstp, &resp->fh, &attrs, argp->check_guard, argp->guardtime); return rpc_success; } @@ -146,17 +150,21 @@ nfsd3_proc_read(struct svc_rqst *rqstp) { struct nfsd3_readargs *argp = rqstp->rq_argp; struct nfsd3_readres *resp = rqstp->rq_resp; - u32 max_blocksize = svc_max_payload(rqstp); unsigned int len; int v; - argp->count = min_t(u32, argp->count, max_blocksize); - dprintk("nfsd: READ(3) %s %lu bytes at %Lu\n", SVCFH_fmt(&argp->fh), (unsigned long) argp->count, (unsigned long long) argp->offset); + argp->count = min_t(u32, argp->count, svc_max_payload(rqstp)); + argp->count = min_t(u32, argp->count, rqstp->rq_res.buflen); + if (argp->offset > (u64)OFFSET_MAX) + argp->offset = (u64)OFFSET_MAX; + 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; @@ -199,33 +207,154 @@ nfsd3_proc_write(struct svc_rqst *rqstp) (unsigned long long) argp->offset, argp->stable? " stable" : ""); + resp->status = nfserr_fbig; + if (argp->offset > (u64)OFFSET_MAX || + argp->offset + argp->len > (u64)OFFSET_MAX) + return rpc_success; + fh_copy(&resp->fh, &argp->fh); resp->committed = argp->stable; nvecs = svc_fill_write_vector(rqstp, &argp->payload); - if (!nvecs) { - resp->status = nfserr_io; - goto out; - } + resp->status = nfsd_write(rqstp, &resp->fh, argp->offset, rqstp->rq_vec, nvecs, &cnt, resp->committed, resp->verf); resp->count = cnt; -out: return rpc_success; } /* - * With NFSv3, CREATE processing is a lot easier than with NFSv2. - * At least in theory; we'll see how it fares in practice when the - * first reports about SunOS compatibility problems start to pour in... + * Implement NFSv3's unchecked, guarded, and exclusive CREATE + * semantics for regular files. Except for the created file, + * this operation is stateless on the server. + * + * Upon return, caller must release @fhp and @resfhp. */ static __be32 +nfsd3_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, + struct svc_fh *resfhp, struct nfsd3_createargs *argp) +{ + struct iattr *iap = &argp->attrs; + struct dentry *parent, *child; + struct nfsd_attrs attrs = { + .na_iattr = iap, + }; + __u32 v_mtime, v_atime; + struct inode *inode; + __be32 status; + int host_err; + + if (isdotent(argp->name, argp->len)) + return nfserr_exist; + if (!(iap->ia_valid & ATTR_MODE)) + iap->ia_mode = 0; + + status = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_EXEC); + if (status != nfs_ok) + return status; + + parent = fhp->fh_dentry; + inode = d_inode(parent); + + host_err = fh_want_write(fhp); + if (host_err) + return nfserrno(host_err); + + inode_lock_nested(inode, I_MUTEX_PARENT); + + child = lookup_one_len(argp->name, parent, argp->len); + if (IS_ERR(child)) { + status = nfserrno(PTR_ERR(child)); + goto out; + } + + if (d_really_is_negative(child)) { + status = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_CREATE); + if (status != nfs_ok) + goto out; + } + + status = fh_compose(resfhp, fhp->fh_export, child, fhp); + if (status != nfs_ok) + goto out; + + v_mtime = 0; + v_atime = 0; + if (argp->createmode == NFS3_CREATE_EXCLUSIVE) { + u32 *verifier = (u32 *)argp->verf; + + /* + * Solaris 7 gets confused (bugid 4218508) if these have + * the high bit set, as do xfs filesystems without the + * "bigtime" feature. So just clear the high bits. + */ + v_mtime = verifier[0] & 0x7fffffff; + v_atime = verifier[1] & 0x7fffffff; + } + + if (d_really_is_positive(child)) { + status = nfs_ok; + + switch (argp->createmode) { + case NFS3_CREATE_UNCHECKED: + if (!d_is_reg(child)) + break; + iap->ia_valid &= ATTR_SIZE; + goto set_attr; + case NFS3_CREATE_GUARDED: + 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 && + d_inode(child)->i_size == 0) { + break; + } + status = nfserr_exist; + } + goto out; + } + + 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); + if (host_err < 0) { + status = nfserrno(host_err); + goto out; + } + fh_fill_post_attrs(fhp); + + /* A newly created file already has a file size of zero. */ + if ((iap->ia_valid & ATTR_SIZE) && (iap->ia_size == 0)) + iap->ia_valid &= ~ATTR_SIZE; + if (argp->createmode == NFS3_CREATE_EXCLUSIVE) { + iap->ia_valid = ATTR_MTIME | ATTR_ATIME | + ATTR_MTIME_SET | ATTR_ATIME_SET; + iap->ia_mtime.tv_sec = v_mtime; + iap->ia_atime.tv_sec = v_atime; + iap->ia_mtime.tv_nsec = 0; + iap->ia_atime.tv_nsec = 0; + } + +set_attr: + status = nfsd_create_setattr(rqstp, fhp, resfhp, &attrs); + +out: + inode_unlock(inode); + if (child && !IS_ERR(child)) + dput(child); + fh_drop_write(fhp); + return status; +} + +static __be32 nfsd3_proc_create(struct svc_rqst *rqstp) { struct nfsd3_createargs *argp = rqstp->rq_argp; struct nfsd3_diropres *resp = rqstp->rq_resp; - svc_fh *dirfhp, *newfhp = NULL; - struct iattr *attr; + svc_fh *dirfhp, *newfhp; dprintk("nfsd: CREATE(3) %s %.*s\n", SVCFH_fmt(&argp->fh), @@ -234,21 +363,8 @@ nfsd3_proc_create(struct svc_rqst *rqstp) dirfhp = fh_copy(&resp->dirfh, &argp->fh); newfhp = fh_init(&resp->fh, NFS3_FHSIZE); - attr = &argp->attrs; - - /* Unfudge the mode bits */ - attr->ia_mode &= ~S_IFMT; - if (!(attr->ia_valid & ATTR_MODE)) { - attr->ia_valid |= ATTR_MODE; - attr->ia_mode = S_IFREG; - } else { - attr->ia_mode = (attr->ia_mode & ~S_IFMT) | S_IFREG; - } - /* Now create the file and set attributes */ - resp->status = do_nfsd_create(rqstp, dirfhp, argp->name, argp->len, - attr, newfhp, argp->createmode, - (u32 *)argp->verf, NULL, NULL); + resp->status = nfsd3_create_file(rqstp, dirfhp, newfhp, argp); return rpc_success; } @@ -260,6 +376,9 @@ nfsd3_proc_mkdir(struct svc_rqst *rqstp) { struct nfsd3_createargs *argp = rqstp->rq_argp; struct nfsd3_diropres *resp = rqstp->rq_resp; + struct nfsd_attrs attrs = { + .na_iattr = &argp->attrs, + }; dprintk("nfsd: MKDIR(3) %s %.*s\n", SVCFH_fmt(&argp->fh), @@ -270,8 +389,7 @@ nfsd3_proc_mkdir(struct svc_rqst *rqstp) fh_copy(&resp->dirfh, &argp->fh); fh_init(&resp->fh, NFS3_FHSIZE); resp->status = nfsd_create(rqstp, &resp->dirfh, argp->name, argp->len, - &argp->attrs, S_IFDIR, 0, &resp->fh); - fh_unlock(&resp->dirfh); + &attrs, S_IFDIR, 0, &resp->fh); return rpc_success; } @@ -280,6 +398,9 @@ nfsd3_proc_symlink(struct svc_rqst *rqstp) { struct nfsd3_symlinkargs *argp = rqstp->rq_argp; struct nfsd3_diropres *resp = rqstp->rq_resp; + struct nfsd_attrs attrs = { + .na_iattr = &argp->attrs, + }; if (argp->tlen == 0) { resp->status = nfserr_inval; @@ -306,7 +427,7 @@ nfsd3_proc_symlink(struct svc_rqst *rqstp) 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, &resp->fh); + argp->flen, argp->tname, &attrs, &resp->fh); kfree(argp->tname); out: return rpc_success; @@ -320,6 +441,9 @@ nfsd3_proc_mknod(struct svc_rqst *rqstp) { struct nfsd3_mknodargs *argp = rqstp->rq_argp; struct nfsd3_diropres *resp = rqstp->rq_resp; + struct nfsd_attrs attrs = { + .na_iattr = &argp->attrs, + }; int type; dev_t rdev = 0; @@ -345,8 +469,7 @@ nfsd3_proc_mknod(struct svc_rqst *rqstp) type = nfs3_ftypes[argp->ftype]; resp->status = nfsd_create(rqstp, &resp->dirfh, argp->name, argp->len, - &argp->attrs, type, rdev, &resp->fh); - fh_unlock(&resp->dirfh); + &attrs, type, rdev, &resp->fh); out: return rpc_success; } @@ -369,7 +492,6 @@ nfsd3_proc_remove(struct svc_rqst *rqstp) fh_copy(&resp->fh, &argp->fh); resp->status = nfsd_unlink(rqstp, &resp->fh, -S_IFDIR, argp->name, argp->len); - fh_unlock(&resp->fh); return rpc_success; } @@ -390,7 +512,6 @@ nfsd3_proc_rmdir(struct svc_rqst *rqstp) fh_copy(&resp->fh, &argp->fh); resp->status = nfsd_unlink(rqstp, &resp->fh, S_IFDIR, argp->name, argp->len); - fh_unlock(&resp->fh); return rpc_success; } @@ -442,25 +563,18 @@ static void nfsd3_init_dirlist_pages(struct svc_rqst *rqstp, { struct xdr_buf *buf = &resp->dirlist; struct xdr_stream *xdr = &resp->xdr; - - count = clamp(count, (u32)(XDR_UNIT * 2), svc_max_payload(rqstp)); + unsigned int sendbuf = min_t(unsigned int, rqstp->rq_res.buflen, + svc_max_payload(rqstp)); memset(buf, 0, sizeof(*buf)); /* Reserve room for the NULL ptr & eof flag (-2 words) */ - buf->buflen = count - XDR_UNIT * 2; + buf->buflen = clamp(count, (u32)(XDR_UNIT * 2), sendbuf); + buf->buflen -= XDR_UNIT * 2; buf->pages = rqstp->rq_next_page; rqstp->rq_next_page += (buf->buflen + PAGE_SIZE - 1) >> PAGE_SHIFT; - /* This is xdr_init_encode(), but it assumes that - * the head kvec has already been consumed. */ - xdr_set_scratch_buffer(xdr, NULL, 0); - xdr->buf = buf; - xdr->page_ptr = buf->pages; - xdr->iov = NULL; - xdr->p = page_address(*buf->pages); - xdr->end = (void *)xdr->p + min_t(u32, buf->buflen, PAGE_SIZE); - xdr->rqst = NULL; + xdr_init_encode_pages(xdr, buf, buf->pages, NULL); } /* @@ -655,15 +769,9 @@ nfsd3_proc_commit(struct svc_rqst *rqstp) argp->count, (unsigned long long) argp->offset); - if (argp->offset > NFS_OFFSET_MAX) { - resp->status = nfserr_inval; - goto out; - } - fh_copy(&resp->fh, &argp->fh); resp->status = nfsd_commit(rqstp, &resp->fh, argp->offset, argp->count, resp->verf); -out: return rpc_success; } @@ -693,6 +801,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_decode = nfssvc_decode_voidarg, .pc_encode = nfssvc_encode_voidres, .pc_argsize = sizeof(struct nfsd_voidargs), + .pc_argzero = sizeof(struct nfsd_voidargs), .pc_ressize = sizeof(struct nfsd_voidres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST, @@ -704,6 +813,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_encode = nfs3svc_encode_getattrres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd_fhandle), + .pc_argzero = sizeof(struct nfsd_fhandle), .pc_ressize = sizeof(struct nfsd3_attrstatres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+AT, @@ -715,6 +825,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_encode = nfs3svc_encode_wccstatres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_sattrargs), + .pc_argzero = sizeof(struct nfsd3_sattrargs), .pc_ressize = sizeof(struct nfsd3_wccstatres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+WC, @@ -726,6 +837,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_encode = nfs3svc_encode_lookupres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_diropargs), + .pc_argzero = sizeof(struct nfsd3_diropargs), .pc_ressize = sizeof(struct nfsd3_diropres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+FH+pAT+pAT, @@ -737,6 +849,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_encode = nfs3svc_encode_accessres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_accessargs), + .pc_argzero = sizeof(struct nfsd3_accessargs), .pc_ressize = sizeof(struct nfsd3_accessres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+pAT+1, @@ -748,6 +861,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_encode = nfs3svc_encode_readlinkres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd_fhandle), + .pc_argzero = sizeof(struct nfsd_fhandle), .pc_ressize = sizeof(struct nfsd3_readlinkres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+pAT+1+NFS3_MAXPATHLEN/4, @@ -759,6 +873,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_encode = nfs3svc_encode_readres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_readargs), + .pc_argzero = sizeof(struct nfsd3_readargs), .pc_ressize = sizeof(struct nfsd3_readres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+pAT+4+NFSSVC_MAXBLKSIZE/4, @@ -770,6 +885,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_encode = nfs3svc_encode_writeres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_writeargs), + .pc_argzero = sizeof(struct nfsd3_writeargs), .pc_ressize = sizeof(struct nfsd3_writeres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+WC+4, @@ -781,6 +897,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_encode = nfs3svc_encode_createres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_createargs), + .pc_argzero = sizeof(struct nfsd3_createargs), .pc_ressize = sizeof(struct nfsd3_createres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+(1+FH+pAT)+WC, @@ -792,6 +909,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_encode = nfs3svc_encode_createres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_mkdirargs), + .pc_argzero = sizeof(struct nfsd3_mkdirargs), .pc_ressize = sizeof(struct nfsd3_createres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+(1+FH+pAT)+WC, @@ -803,6 +921,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_encode = nfs3svc_encode_createres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_symlinkargs), + .pc_argzero = sizeof(struct nfsd3_symlinkargs), .pc_ressize = sizeof(struct nfsd3_createres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+(1+FH+pAT)+WC, @@ -814,6 +933,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_encode = nfs3svc_encode_createres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_mknodargs), + .pc_argzero = sizeof(struct nfsd3_mknodargs), .pc_ressize = sizeof(struct nfsd3_createres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+(1+FH+pAT)+WC, @@ -825,6 +945,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_encode = nfs3svc_encode_wccstatres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_diropargs), + .pc_argzero = sizeof(struct nfsd3_diropargs), .pc_ressize = sizeof(struct nfsd3_wccstatres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+WC, @@ -836,6 +957,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_encode = nfs3svc_encode_wccstatres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_diropargs), + .pc_argzero = sizeof(struct nfsd3_diropargs), .pc_ressize = sizeof(struct nfsd3_wccstatres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+WC, @@ -847,6 +969,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_encode = nfs3svc_encode_renameres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_renameargs), + .pc_argzero = sizeof(struct nfsd3_renameargs), .pc_ressize = sizeof(struct nfsd3_renameres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+WC+WC, @@ -858,6 +981,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_encode = nfs3svc_encode_linkres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_linkargs), + .pc_argzero = sizeof(struct nfsd3_linkargs), .pc_ressize = sizeof(struct nfsd3_linkres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+pAT+WC, @@ -869,6 +993,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_encode = nfs3svc_encode_readdirres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_readdirargs), + .pc_argzero = sizeof(struct nfsd3_readdirargs), .pc_ressize = sizeof(struct nfsd3_readdirres), .pc_cachetype = RC_NOCACHE, .pc_name = "READDIR", @@ -879,6 +1004,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_encode = nfs3svc_encode_readdirres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_readdirplusargs), + .pc_argzero = sizeof(struct nfsd3_readdirplusargs), .pc_ressize = sizeof(struct nfsd3_readdirres), .pc_cachetype = RC_NOCACHE, .pc_name = "READDIRPLUS", @@ -888,6 +1014,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_decode = nfs3svc_decode_fhandleargs, .pc_encode = nfs3svc_encode_fsstatres, .pc_argsize = sizeof(struct nfsd3_fhandleargs), + .pc_argzero = sizeof(struct nfsd3_fhandleargs), .pc_ressize = sizeof(struct nfsd3_fsstatres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+pAT+2*6+1, @@ -898,6 +1025,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_decode = nfs3svc_decode_fhandleargs, .pc_encode = nfs3svc_encode_fsinfores, .pc_argsize = sizeof(struct nfsd3_fhandleargs), + .pc_argzero = sizeof(struct nfsd3_fhandleargs), .pc_ressize = sizeof(struct nfsd3_fsinfores), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+pAT+12, @@ -908,6 +1036,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_decode = nfs3svc_decode_fhandleargs, .pc_encode = nfs3svc_encode_pathconfres, .pc_argsize = sizeof(struct nfsd3_fhandleargs), + .pc_argzero = sizeof(struct nfsd3_fhandleargs), .pc_ressize = sizeof(struct nfsd3_pathconfres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+pAT+6, @@ -919,6 +1048,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_encode = nfs3svc_encode_commitres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_commitargs), + .pc_argzero = sizeof(struct nfsd3_commitargs), .pc_ressize = sizeof(struct nfsd3_commitres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+WC+2, diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index c3ac1b6aa3aa..3308dd671ef0 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -254,7 +254,7 @@ svcxdr_decode_sattr3(struct svc_rqst *rqstp, struct xdr_stream *xdr, if (xdr_stream_decode_u64(xdr, &newsize) < 0) return false; iap->ia_valid |= ATTR_SIZE; - iap->ia_size = min_t(u64, newsize, NFS_OFFSET_MAX); + iap->ia_size = newsize; } if (xdr_stream_decode_u32(xdr, &set_it) < 0) return false; @@ -487,71 +487,6 @@ neither: return true; } -static bool fs_supports_change_attribute(struct super_block *sb) -{ - return sb->s_flags & SB_I_VERSION || sb->s_export_op->fetch_iversion; -} - -/* - * Fill in the pre_op attr for the wcc data - */ -void fill_pre_wcc(struct svc_fh *fhp) -{ - struct inode *inode; - struct kstat stat; - bool v4 = (fhp->fh_maxsize == NFS4_FHSIZE); - - if (fhp->fh_no_wcc || fhp->fh_pre_saved) - return; - inode = d_inode(fhp->fh_dentry); - if (fs_supports_change_attribute(inode->i_sb) || !v4) { - __be32 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; - } - fhp->fh_pre_mtime = stat.mtime; - fhp->fh_pre_ctime = stat.ctime; - fhp->fh_pre_size = stat.size; - } - if (v4) - fhp->fh_pre_change = nfsd4_change_attribute(&stat, inode); - - fhp->fh_pre_saved = true; -} - -/* - * Fill in the post_op attr for the wcc data - */ -void fill_post_wcc(struct svc_fh *fhp) -{ - bool v4 = (fhp->fh_maxsize == NFS4_FHSIZE); - struct inode *inode = d_inode(fhp->fh_dentry); - - if (fhp->fh_no_wcc) - return; - - if (fhp->fh_post_saved) - printk("nfsd: inode locked twice during operation.\n"); - - fhp->fh_post_saved = true; - - if (fs_supports_change_attribute(inode->i_sb) || !v4) { - __be32 err = fh_getattr(fhp, &fhp->fh_post_attr); - - if (err) { - fhp->fh_post_saved = false; - fhp->fh_post_attr.ctime = inode->i_ctime; - } - } - if (v4) - fhp->fh_post_change = - nfsd4_change_attribute(&fhp->fh_post_attr, inode); -} - /* * XDR decode functions */ @@ -636,10 +571,8 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) args->count = max_blocksize; args->len = max_blocksize; } - if (!xdr_stream_subsegment(xdr, &args->payload, args->count)) - return false; - return true; + return xdr_stream_subsegment(xdr, &args->payload, args->count); } bool @@ -681,8 +614,6 @@ nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd3_symlinkargs *args = rqstp->rq_argp; struct kvec *head = rqstp->rq_arg.head; - struct kvec *tail = rqstp->rq_arg.tail; - size_t remaining; if (!svcxdr_decode_diropargs3(xdr, &args->ffh, &args->fname, &args->flen)) return false; @@ -691,16 +622,10 @@ nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) if (xdr_stream_decode_u32(xdr, &args->tlen) < 0) return false; - /* request sanity */ - remaining = head->iov_len + rqstp->rq_arg.page_len + tail->iov_len; - remaining -= xdr_stream_pos(xdr); - if (remaining < xdr_align_size(args->tlen)) - return false; - - args->first.iov_base = xdr->p; + /* symlink_data */ args->first.iov_len = head->iov_len - xdr_stream_pos(xdr); - - return true; + args->first.iov_base = xdr_inline_decode(xdr, args->tlen); + return args->first.iov_base != NULL; } bool @@ -1125,7 +1050,7 @@ svcxdr_encode_entry3_common(struct nfsd3_readdirres *resp, const char *name, return false; /* cookie */ resp->cookie_offset = dirlist->len; - if (xdr_stream_encode_u64(xdr, NFS_OFFSET_MAX) < 0) + if (xdr_stream_encode_u64(xdr, OFFSET_MAX) < 0) return false; return true; diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c index eaa3a0cf38f1..bb8e2f6d7d03 100644 --- a/fs/nfsd/nfs4acl.c +++ b/fs/nfsd/nfs4acl.c @@ -751,58 +751,26 @@ out_estate: return ret; } -__be32 -nfsd4_set_nfs4_acl(struct svc_rqst *rqstp, struct svc_fh *fhp, - struct nfs4_acl *acl) +__be32 nfsd4_acl_to_attr(enum nfs_ftype4 type, struct nfs4_acl *acl, + struct nfsd_attrs *attr) { - __be32 error; int host_error; - struct dentry *dentry; - struct inode *inode; - struct posix_acl *pacl = NULL, *dpacl = NULL; unsigned int flags = 0; - /* Get inode */ - error = fh_verify(rqstp, fhp, 0, NFSD_MAY_SATTR); - if (error) - return error; - - dentry = fhp->fh_dentry; - inode = d_inode(dentry); + if (!acl) + return nfs_ok; - if (S_ISDIR(inode->i_mode)) + if (type == NF4DIR) flags = NFS4_ACL_DIR; - host_error = nfs4_acl_nfsv4_to_posix(acl, &pacl, &dpacl, flags); + host_error = nfs4_acl_nfsv4_to_posix(acl, &attr->na_pacl, + &attr->na_dpacl, flags); if (host_error == -EINVAL) return nfserr_attrnotsupp; - if (host_error < 0) - goto out_nfserr; - - fh_lock(fhp); - - host_error = set_posix_acl(&init_user_ns, inode, ACL_TYPE_ACCESS, pacl); - if (host_error < 0) - goto out_drop_lock; - - if (S_ISDIR(inode->i_mode)) { - host_error = set_posix_acl(&init_user_ns, inode, - ACL_TYPE_DEFAULT, dpacl); - } - -out_drop_lock: - fh_unlock(fhp); - - posix_acl_release(pacl); - posix_acl_release(dpacl); -out_nfserr: - if (host_error == -EOPNOTSUPP) - return nfserr_attrnotsupp; else return nfserrno(host_error); } - static short ace2type(struct nfs4_ace *ace) { diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 11f8715d92d6..f0e69edf5f0f 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -679,7 +679,7 @@ static int nfs4_xdr_dec_cb_notify_lock(struct rpc_rqst *rqstp, * case NFS4_OK: * write_response4 coa_resok4; * default: - * length4 coa_bytes_copied; + * length4 coa_bytes_copied; * }; * struct CB_OFFLOAD4args { * nfs_fh4 coa_fh; @@ -688,21 +688,22 @@ static int nfs4_xdr_dec_cb_notify_lock(struct rpc_rqst *rqstp, * }; */ static void encode_offload_info4(struct xdr_stream *xdr, - __be32 nfserr, - const struct nfsd4_copy *cp) + const struct nfsd4_cb_offload *cbo) { __be32 *p; p = xdr_reserve_space(xdr, 4); - *p++ = nfserr; - if (!nfserr) { + *p = cbo->co_nfserr; + switch (cbo->co_nfserr) { + case nfs_ok: p = xdr_reserve_space(xdr, 4 + 8 + 4 + NFS4_VERIFIER_SIZE); p = xdr_encode_empty_array(p); - p = xdr_encode_hyper(p, cp->cp_res.wr_bytes_written); - *p++ = cpu_to_be32(cp->cp_res.wr_stable_how); - p = xdr_encode_opaque_fixed(p, cp->cp_res.wr_verifier.data, + p = xdr_encode_hyper(p, cbo->co_res.wr_bytes_written); + *p++ = cpu_to_be32(cbo->co_res.wr_stable_how); + p = xdr_encode_opaque_fixed(p, cbo->co_res.wr_verifier.data, NFS4_VERIFIER_SIZE); - } else { + break; + default: p = xdr_reserve_space(xdr, 8); /* We always return success if bytes were written */ p = xdr_encode_hyper(p, 0); @@ -710,18 +711,16 @@ static void encode_offload_info4(struct xdr_stream *xdr, } static void encode_cb_offload4args(struct xdr_stream *xdr, - __be32 nfserr, - const struct knfsd_fh *fh, - const struct nfsd4_copy *cp, + const struct nfsd4_cb_offload *cbo, struct nfs4_cb_compound_hdr *hdr) { __be32 *p; p = xdr_reserve_space(xdr, 4); - *p++ = cpu_to_be32(OP_CB_OFFLOAD); - encode_nfs_fh4(xdr, fh); - encode_stateid4(xdr, &cp->cp_res.cb_stateid); - encode_offload_info4(xdr, nfserr, cp); + *p = cpu_to_be32(OP_CB_OFFLOAD); + encode_nfs_fh4(xdr, &cbo->co_fh); + encode_stateid4(xdr, &cbo->co_res.cb_stateid); + encode_offload_info4(xdr, cbo); hdr->nops++; } @@ -731,8 +730,8 @@ static void nfs4_xdr_enc_cb_offload(struct rpc_rqst *req, const void *data) { const struct nfsd4_callback *cb = data; - const struct nfsd4_copy *cp = - container_of(cb, struct nfsd4_copy, cp_cb); + const struct nfsd4_cb_offload *cbo = + container_of(cb, struct nfsd4_cb_offload, co_cb); struct nfs4_cb_compound_hdr hdr = { .ident = 0, .minorversion = cb->cb_clp->cl_minorversion, @@ -740,7 +739,7 @@ static void nfs4_xdr_enc_cb_offload(struct rpc_rqst *req, encode_cb_compound4args(xdr, &hdr); encode_cb_sequence4args(xdr, cb, &hdr); - encode_cb_offload4args(xdr, cp->nfserr, &cp->fh, cp, &hdr); + encode_cb_offload4args(xdr, cbo, &hdr); encode_cb_nops(&hdr); } @@ -1372,11 +1371,21 @@ void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp, cb->cb_holds_slot = false; } -void nfsd4_run_cb(struct nfsd4_callback *cb) +/** + * nfsd4_run_cb - queue up a callback job to run + * @cb: callback to queue + * + * Kick off a callback to do its thing. Returns false if it was already + * on a queue, true otherwise. + */ +bool nfsd4_run_cb(struct nfsd4_callback *cb) { struct nfs4_client *clp = cb->cb_clp; + bool queued; nfsd41_cb_inflight_begin(clp); - if (!nfsd4_queue_cb(cb)) + queued = nfsd4_queue_cb(cb); + if (!queued) nfsd41_cb_inflight_end(clp); + return queued; } diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c index f92161ce1f97..e70a1a2999b7 100644 --- a/fs/nfsd/nfs4idmap.c +++ b/fs/nfsd/nfs4idmap.c @@ -82,8 +82,8 @@ ent_init(struct cache_head *cnew, struct cache_head *citm) new->id = itm->id; new->type = itm->type; - strlcpy(new->name, itm->name, sizeof(new->name)); - strlcpy(new->authname, itm->authname, sizeof(new->authname)); + strscpy(new->name, itm->name, sizeof(new->name)); + strscpy(new->authname, itm->authname, sizeof(new->authname)); } static void @@ -548,7 +548,7 @@ idmap_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen return nfserr_badowner; memcpy(key.name, name, namelen); key.name[namelen] = '\0'; - strlcpy(key.authname, rqst_authname(rqstp), sizeof(key.authname)); + strscpy(key.authname, rqst_authname(rqstp), sizeof(key.authname)); ret = idmap_lookup(rqstp, nametoid_lookup, &key, nn->nametoid_cache, &item); if (ret == -ENOENT) return nfserr_badowner; @@ -584,7 +584,7 @@ static __be32 idmap_id_to_name(struct xdr_stream *xdr, int ret; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); - strlcpy(key.authname, rqst_authname(rqstp), sizeof(key.authname)); + strscpy(key.authname, rqst_authname(rqstp), sizeof(key.authname)); ret = idmap_lookup(rqstp, idtoname_lookup, &key, nn->idtoname_cache, &item); if (ret == -ENOENT) return encode_ascii_id(xdr, id); diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index 6d1b5bb051c5..3564d1c6f610 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -422,7 +422,7 @@ nfsd4_insert_layout(struct nfsd4_layoutget *lgp, struct nfs4_layout_stateid *ls) new = kmem_cache_alloc(nfs4_layout_cache, GFP_KERNEL); if (!new) return nfserr_jukebox; - memcpy(&new->lo_seg, seg, sizeof(lp->lo_seg)); + memcpy(&new->lo_seg, seg, sizeof(new->lo_seg)); new->lo_state = ls; spin_lock(&fp->fi_lock); @@ -658,7 +658,7 @@ nfsd4_cb_layout_done(struct nfsd4_callback *cb, struct rpc_task *task) ktime_t now, cutoff; const struct nfsd4_layout_ops *ops; - + trace_nfsd_cb_layout_done(&ls->ls_stid.sc_stateid, task); switch (task->tk_status) { case 0: case -NFS4ERR_DELAY: diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index a36261f89bdf..8beb2bc4c328 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -37,6 +37,8 @@ #include <linux/falloc.h> #include <linux/slab.h> #include <linux/kthread.h> +#include <linux/namei.h> + #include <linux/sunrpc/addr.h> #include <linux/nfs_ssc.h> @@ -62,36 +64,6 @@ MODULE_PARM_DESC(nfsd4_ssc_umount_timeout, "idle msecs before unmount export from source server"); #endif -#ifdef CONFIG_NFSD_V4_SECURITY_LABEL -#include <linux/security.h> - -static inline void -nfsd4_security_inode_setsecctx(struct svc_fh *resfh, struct xdr_netobj *label, u32 *bmval) -{ - struct inode *inode = d_inode(resfh->fh_dentry); - int status; - - inode_lock(inode); - status = security_inode_setsecctx(resfh->fh_dentry, - label->data, label->len); - inode_unlock(inode); - - if (status) - /* - * XXX: We should really fail the whole open, but we may - * already have created a new file, so it may be too - * late. For now this seems the least of evils: - */ - bmval[2] &= ~FATTR4_WORD2_SECURITY_LABEL; - - return; -} -#else -static inline void -nfsd4_security_inode_setsecctx(struct svc_fh *resfh, struct xdr_netobj *label, u32 *bmval) -{ } -#endif - #define NFSDDBG_FACILITY NFSDDBG_PROC static u32 nfsd_attrmask[] = { @@ -156,26 +128,6 @@ is_create_with_attrs(struct nfsd4_open *open) || open->op_createmode == NFS4_CREATE_EXCLUSIVE4_1); } -/* - * if error occurs when setting the acl, just clear the acl bit - * in the returned attr bitmap. - */ -static void -do_set_nfs4_acl(struct svc_rqst *rqstp, struct svc_fh *fhp, - struct nfs4_acl *acl, u32 *bmval) -{ - __be32 status; - - status = nfsd4_set_nfs4_acl(rqstp, fhp, acl); - if (status) - /* - * We should probably fail the whole open at this point, - * but we've already created the file, so it's too late; - * So this seems the least of evils: - */ - bmval[0] &= ~FATTR4_WORD0_ACL; -} - static inline void fh_dup2(struct svc_fh *dst, struct svc_fh *src) { @@ -189,7 +141,6 @@ fh_dup2(struct svc_fh *dst, struct svc_fh *src) static __be32 do_open_permission(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open, int accmode) { - __be32 status; if (open->op_truncate && !(open->op_share_access & NFS4_SHARE_ACCESS_WRITE)) @@ -204,9 +155,7 @@ do_open_permission(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfs if (open->op_share_deny & NFS4_SHARE_DENY_READ) accmode |= NFSD_MAY_WRITE; - status = fh_verify(rqstp, current_fh, S_IFREG, accmode); - - return status; + return fh_verify(rqstp, current_fh, S_IFREG, accmode); } static __be32 nfsd_check_obj_isreg(struct svc_fh *fh) @@ -235,6 +184,202 @@ static void nfsd4_set_open_owner_reply_cache(struct nfsd4_compound_state *cstate &resfh->fh_handle); } +static inline bool nfsd4_create_is_exclusive(int createmode) +{ + return createmode == NFS4_CREATE_EXCLUSIVE || + createmode == NFS4_CREATE_EXCLUSIVE4_1; +} + +static __be32 +nfsd4_vfs_create(struct svc_fh *fhp, struct dentry *child, + struct nfsd4_open *open) +{ + struct file *filp; + struct path path; + int oflags; + + oflags = O_CREAT | O_LARGEFILE; + switch (open->op_share_access & NFS4_SHARE_ACCESS_BOTH) { + case NFS4_SHARE_ACCESS_WRITE: + oflags |= O_WRONLY; + break; + case NFS4_SHARE_ACCESS_BOTH: + oflags |= O_RDWR; + break; + default: + oflags |= O_RDONLY; + } + + path.mnt = fhp->fh_export->ex_path.mnt; + path.dentry = child; + filp = dentry_create(&path, oflags, open->op_iattr.ia_mode, + current_cred()); + if (IS_ERR(filp)) + return nfserrno(PTR_ERR(filp)); + + open->op_filp = filp; + return nfs_ok; +} + +/* + * Implement NFSv4's unchecked, guarded, and exclusive create + * semantics for regular files. Open state for this new file is + * subsequently fabricated in nfsd4_process_open2(). + * + * Upon return, caller must release @fhp and @resfhp. + */ +static __be32 +nfsd4_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, + struct svc_fh *resfhp, struct nfsd4_open *open) +{ + struct iattr *iap = &open->op_iattr; + struct nfsd_attrs attrs = { + .na_iattr = iap, + .na_seclabel = &open->op_label, + }; + struct dentry *parent, *child; + __u32 v_mtime, v_atime; + struct inode *inode; + __be32 status; + int host_err; + + if (isdotent(open->op_fname, open->op_fnamelen)) + return nfserr_exist; + if (!(iap->ia_valid & ATTR_MODE)) + iap->ia_mode = 0; + + status = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_EXEC); + if (status != nfs_ok) + return status; + parent = fhp->fh_dentry; + inode = d_inode(parent); + + host_err = fh_want_write(fhp); + if (host_err) + return nfserrno(host_err); + + 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); + if (IS_ERR(child)) { + status = nfserrno(PTR_ERR(child)); + goto out; + } + + if (d_really_is_negative(child)) { + status = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_CREATE); + if (status != nfs_ok) + goto out; + } + + status = fh_compose(resfhp, fhp->fh_export, child, fhp); + if (status != nfs_ok) + goto out; + + v_mtime = 0; + v_atime = 0; + if (nfsd4_create_is_exclusive(open->op_createmode)) { + u32 *verifier = (u32 *)open->op_verf.data; + + /* + * Solaris 7 gets confused (bugid 4218508) if these have + * the high bit set, as do xfs filesystems without the + * "bigtime" feature. So just clear the high bits. If this + * is ever changed to use different attrs for storing the + * verifier, then do_open_lookup() will also need to be + * fixed accordingly. + */ + v_mtime = verifier[0] & 0x7fffffff; + v_atime = verifier[1] & 0x7fffffff; + } + + if (d_really_is_positive(child)) { + status = nfs_ok; + + /* NFSv4 protocol requires change attributes even though + * no change happened. + */ + fh_fill_both_attrs(fhp); + + switch (open->op_createmode) { + case NFS4_CREATE_UNCHECKED: + if (!d_is_reg(child)) + break; + + /* + * In NFSv4, we don't want to truncate the file + * now. This would be wrong if the OPEN fails for + * some other reason. Furthermore, if the size is + * nonzero, we should ignore it according to spec! + */ + open->op_truncate = (iap->ia_valid & ATTR_SIZE) && + !iap->ia_size; + break; + case NFS4_CREATE_GUARDED: + 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 && + d_inode(child)->i_size == 0) { + open->op_created = true; + break; /* subtle */ + } + 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 && + d_inode(child)->i_size == 0) { + open->op_created = true; + goto set_attr; /* subtle */ + } + status = nfserr_exist; + } + goto out; + } + + if (!IS_POSIXACL(inode)) + iap->ia_mode &= ~current_umask(); + + fh_fill_pre_attrs(fhp); + status = nfsd4_vfs_create(fhp, child, open); + if (status != nfs_ok) + goto out; + open->op_created = true; + fh_fill_post_attrs(fhp); + + /* A newly created file already has a file size of zero. */ + if ((iap->ia_valid & ATTR_SIZE) && (iap->ia_size == 0)) + iap->ia_valid &= ~ATTR_SIZE; + if (nfsd4_create_is_exclusive(open->op_createmode)) { + iap->ia_valid = ATTR_MTIME | ATTR_ATIME | + ATTR_MTIME_SET|ATTR_ATIME_SET; + iap->ia_mtime.tv_sec = v_mtime; + iap->ia_atime.tv_sec = v_atime; + iap->ia_mtime.tv_nsec = 0; + iap->ia_atime.tv_nsec = 0; + } + +set_attr: + status = nfsd_create_setattr(rqstp, fhp, resfhp, &attrs); + + if (attrs.na_labelerr) + open->op_bmval[2] &= ~FATTR4_WORD2_SECURITY_LABEL; + if (attrs.na_aclerr) + open->op_bmval[0] &= ~FATTR4_WORD0_ACL; +out: + inode_unlock(inode); + nfsd_attrs_free(&attrs); + if (child && !IS_ERR(child)) + dput(child); + fh_drop_write(fhp); + return status; +} + static __be32 do_open_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_open *open, struct svc_fh **resfh) { @@ -264,47 +409,33 @@ do_open_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, stru * yes | yes | GUARDED4 | GUARDED4 */ - /* - * Note: create modes (UNCHECKED,GUARDED...) are the same - * in NFSv4 as in v3 except EXCLUSIVE4_1. - */ current->fs->umask = open->op_umask; - status = do_nfsd_create(rqstp, current_fh, open->op_fname, - open->op_fnamelen, &open->op_iattr, - *resfh, open->op_createmode, - (u32 *)open->op_verf.data, - &open->op_truncate, &open->op_created); + status = nfsd4_create_file(rqstp, current_fh, *resfh, open); current->fs->umask = 0; - if (!status && open->op_label.len) - nfsd4_security_inode_setsecctx(*resfh, &open->op_label, open->op_bmval); - /* * Following rfc 3530 14.2.16, and rfc 5661 18.16.4 * use the returned bitmask to indicate which attributes * we used to store the verifier: */ - if (nfsd_create_is_exclusive(open->op_createmode) && status == 0) + if (nfsd4_create_is_exclusive(open->op_createmode) && status == 0) open->op_bmval[1] |= (FATTR4_WORD1_TIME_ACCESS | FATTR4_WORD1_TIME_MODIFY); - } else - /* - * Note this may exit with the parent still locked. - * We will hold the lock until nfsd4_open's final - * lookup, to prevent renames or unlinks until we've had - * a chance to an acquire a delegation if appropriate. - */ + } else { status = nfsd_lookup(rqstp, current_fh, open->op_fname, open->op_fnamelen, *resfh); + if (!status) + /* NFSv4 protocol requires change attributes even though + * no change happened. + */ + fh_fill_both_attrs(current_fh); + } if (status) goto out; status = nfsd_check_obj_isreg(*resfh); if (status) goto out; - if (is_create_with_attrs(open) && open->op_acl != NULL) - do_set_nfs4_acl(rqstp, *resfh, open->op_acl, open->op_bmval); - nfsd4_set_open_owner_reply_cache(cstate, open, *resfh); accmode = NFSD_MAY_NOP; if (open->op_created || @@ -320,7 +451,6 @@ static __be32 do_open_fhandle(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_open *open) { struct svc_fh *current_fh = &cstate->current_fh; - __be32 status; int accmode = 0; /* We don't know the target directory, and therefore can not @@ -345,9 +475,7 @@ do_open_fhandle(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, str if (open->op_claim_type == NFS4_OPEN_CLAIM_DELEG_CUR_FH) accmode = NFSD_MAY_OWNER_OVERRIDE; - status = do_open_permission(rqstp, current_fh, open, accmode); - - return status; + return do_open_permission(rqstp, current_fh, open, accmode); } static void @@ -375,6 +503,9 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, (int)open->op_fnamelen, open->op_fname, open->op_openowner); + open->op_filp = NULL; + open->op_rqstp = rqstp; + /* This check required by spec. */ if (open->op_create && open->op_claim_type != NFS4_OPEN_CLAIM_NULL) return nfserr_inval; @@ -427,50 +558,46 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; switch (open->op_claim_type) { - case NFS4_OPEN_CLAIM_DELEGATE_CUR: - case NFS4_OPEN_CLAIM_NULL: - status = do_open_lookup(rqstp, cstate, open, &resfh); - if (status) - goto out; - break; - case NFS4_OPEN_CLAIM_PREVIOUS: - status = nfs4_check_open_reclaim(cstate->clp); - if (status) - goto out; - open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED; - reclaim = true; - fallthrough; - case NFS4_OPEN_CLAIM_FH: - case NFS4_OPEN_CLAIM_DELEG_CUR_FH: - status = do_open_fhandle(rqstp, cstate, open); - if (status) - goto out; - resfh = &cstate->current_fh; - break; - case NFS4_OPEN_CLAIM_DELEG_PREV_FH: - case NFS4_OPEN_CLAIM_DELEGATE_PREV: - dprintk("NFSD: unsupported OPEN claim type %d\n", - open->op_claim_type); - status = nfserr_notsupp; + case NFS4_OPEN_CLAIM_DELEGATE_CUR: + case NFS4_OPEN_CLAIM_NULL: + status = do_open_lookup(rqstp, cstate, open, &resfh); + if (status) + goto out; + break; + case NFS4_OPEN_CLAIM_PREVIOUS: + status = nfs4_check_open_reclaim(cstate->clp); + if (status) goto out; - default: - dprintk("NFSD: Invalid OPEN claim type %d\n", - open->op_claim_type); - status = nfserr_inval; + open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED; + reclaim = true; + fallthrough; + case NFS4_OPEN_CLAIM_FH: + case NFS4_OPEN_CLAIM_DELEG_CUR_FH: + status = do_open_fhandle(rqstp, cstate, open); + if (status) goto out; + resfh = &cstate->current_fh; + break; + case NFS4_OPEN_CLAIM_DELEG_PREV_FH: + case NFS4_OPEN_CLAIM_DELEGATE_PREV: + status = nfserr_notsupp; + goto out; + default: + status = nfserr_inval; + goto out; } - /* - * nfsd4_process_open2() does the actual opening of the file. If - * successful, it (1) truncates the file if open->op_truncate was - * set, (2) sets open->op_stateid, (3) sets open->op_delegation. - */ + status = nfsd4_process_open2(rqstp, resfh, open); - WARN(status && open->op_created, - "nfsd4_process_open2 failed to open newly-created file! status=%u\n", - be32_to_cpu(status)); + if (status && open->op_created) + pr_warn("nfsd4_process_open2 failed to open newly-created file: status=%u\n", + be32_to_cpu(status)); if (reclaim && !status) nn->somebody_reclaimed = true; out: + if (open->op_filp) { + fput(open->op_filp); + open->op_filp = NULL; + } if (resfh && resfh != &cstate->current_fh) { fh_dup2(&cstate->current_fh, resfh); fh_put(resfh); @@ -535,11 +662,9 @@ static __be32 nfsd4_putrootfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { - __be32 status; - fh_put(&cstate->current_fh); - status = exp_pseudoroot(rqstp, &cstate->current_fh); - return status; + + return exp_pseudoroot(rqstp, &cstate->current_fh); } static __be32 @@ -598,7 +723,7 @@ static void gen_boot_verifier(nfs4_verifier *verifier, struct net *net) BUILD_BUG_ON(2*sizeof(*verf) != sizeof(verifier->data)); - nfsd_copy_boot_verifier(verf, net_generic(net, nfsd_net_id)); + nfsd_copy_write_verifier(verf, net_generic(net, nfsd_net_id)); } static __be32 @@ -617,6 +742,10 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_create *create = &u->create; + struct nfsd_attrs attrs = { + .na_iattr = &create->cr_iattr, + .na_seclabel = &create->cr_label, + }; struct svc_fh resfh; __be32 status; dev_t rdev; @@ -632,12 +761,13 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (status) return status; + status = nfsd4_acl_to_attr(create->cr_type, create->cr_acl, &attrs); current->fs->umask = create->cr_umask; switch (create->cr_type) { case NF4LNK: status = nfsd_symlink(rqstp, &cstate->current_fh, create->cr_name, create->cr_namelen, - create->cr_data, &resfh); + create->cr_data, &attrs, &resfh); break; case NF4BLK: @@ -648,7 +778,7 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out_umask; status = nfsd_create(rqstp, &cstate->current_fh, create->cr_name, create->cr_namelen, - &create->cr_iattr, S_IFBLK, rdev, &resfh); + &attrs, S_IFBLK, rdev, &resfh); break; case NF4CHR: @@ -659,26 +789,26 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out_umask; status = nfsd_create(rqstp, &cstate->current_fh, create->cr_name, create->cr_namelen, - &create->cr_iattr,S_IFCHR, rdev, &resfh); + &attrs, S_IFCHR, rdev, &resfh); break; case NF4SOCK: status = nfsd_create(rqstp, &cstate->current_fh, create->cr_name, create->cr_namelen, - &create->cr_iattr, S_IFSOCK, 0, &resfh); + &attrs, S_IFSOCK, 0, &resfh); break; case NF4FIFO: status = nfsd_create(rqstp, &cstate->current_fh, create->cr_name, create->cr_namelen, - &create->cr_iattr, S_IFIFO, 0, &resfh); + &attrs, S_IFIFO, 0, &resfh); break; case NF4DIR: create->cr_iattr.ia_valid &= ~ATTR_SIZE; status = nfsd_create(rqstp, &cstate->current_fh, create->cr_name, create->cr_namelen, - &create->cr_iattr, S_IFDIR, 0, &resfh); + &attrs, S_IFDIR, 0, &resfh); break; default: @@ -688,20 +818,17 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (status) goto out; - if (create->cr_label.len) - nfsd4_security_inode_setsecctx(&resfh, &create->cr_label, create->cr_bmval); - - if (create->cr_acl != NULL) - do_set_nfs4_acl(rqstp, &resfh, create->cr_acl, - create->cr_bmval); - - fh_unlock(&cstate->current_fh); + if (attrs.na_labelerr) + create->cr_bmval[2] &= ~FATTR4_WORD2_SECURITY_LABEL; + if (attrs.na_aclerr) + create->cr_bmval[0] &= ~FATTR4_WORD0_ACL; set_change_info(&create->cr_cinfo, &cstate->current_fh); fh_dup2(&cstate->current_fh, &resfh); out: fh_put(&resfh); out_umask: current->fs->umask = 0; + nfsd_attrs_free(&attrs); return status; } @@ -782,12 +909,16 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, __be32 status; read->rd_nf = NULL; - if (read->rd_offset >= OFFSET_MAX) - return nfserr_inval; trace_nfsd_read_start(rqstp, &cstate->current_fh, read->rd_offset, read->rd_length); + read->rd_length = min_t(u32, read->rd_length, svc_max_payload(rqstp)); + if (read->rd_offset > (u64)OFFSET_MAX) + read->rd_offset = (u64)OFFSET_MAX; + if (read->rd_offset + read->rd_length > (u64)OFFSET_MAX) + read->rd_length = (u64)OFFSET_MAX - read->rd_offset; + /* * If we do a zero copy read, then a client will see read data * that reflects the state of the file *after* performing the @@ -797,7 +928,7 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, * the client wants us to do more in this compound: */ if (!nfsd4_last_compound_op(rqstp)) - clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags); + __clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags); /* check stateid */ status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, @@ -870,10 +1001,8 @@ nfsd4_remove(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, return nfserr_grace; status = nfsd_unlink(rqstp, &cstate->current_fh, 0, remove->rm_name, remove->rm_namelen); - if (!status) { - fh_unlock(&cstate->current_fh); + if (!status) set_change_info(&remove->rm_cinfo, &cstate->current_fh); - } return status; } @@ -913,7 +1042,6 @@ nfsd4_secinfo(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, &exp, &dentry); if (err) return err; - fh_unlock(&cstate->current_fh); if (d_really_is_negative(dentry)) { exp_put(exp); err = nfserr_noent; @@ -968,6 +1096,11 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_setattr *setattr = &u->setattr; + struct nfsd_attrs attrs = { + .na_iattr = &setattr->sa_iattr, + .na_seclabel = &setattr->sa_label, + }; + struct inode *inode; __be32 status = nfs_ok; int err; @@ -990,19 +1123,18 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (status) goto out; - if (setattr->sa_acl != NULL) - status = nfsd4_set_nfs4_acl(rqstp, &cstate->current_fh, - setattr->sa_acl); - if (status) - goto out; - if (setattr->sa_label.len) - status = nfsd4_set_nfs4_label(rqstp, &cstate->current_fh, - &setattr->sa_label); + inode = cstate->current_fh.fh_dentry->d_inode; + status = nfsd4_acl_to_attr(S_ISDIR(inode->i_mode) ? NF4DIR : NF4REG, + setattr->sa_acl, &attrs); + if (status) goto out; - status = nfsd_setattr(rqstp, &cstate->current_fh, &setattr->sa_iattr, + status = nfsd_setattr(rqstp, &cstate->current_fh, &attrs, 0, (time64_t)0); + if (!status) + status = nfserrno(attrs.na_labelerr); out: + nfsd_attrs_free(&attrs); fh_drop_write(&cstate->current_fh); return status; } @@ -1018,8 +1150,9 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, unsigned long cnt; int nvecs; - if (write->wr_offset >= OFFSET_MAX) - return nfserr_inval; + if (write->wr_offset > (u64)OFFSET_MAX || + write->wr_offset + write->wr_buflen > (u64)OFFSET_MAX) + return nfserr_fbig; cnt = write->wr_buflen; trace_nfsd_write_start(rqstp, &cstate->current_fh, @@ -1101,7 +1234,7 @@ nfsd4_clone(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (status) goto out; - status = nfsd4_clone_file_range(src, clone->cl_src_pos, + status = nfsd4_clone_file_range(rqstp, src, clone->cl_src_pos, dst, clone->cl_dst_pos, clone->cl_count, EX_ISSYNC(cstate->current_fh.fh_export)); @@ -1111,30 +1244,17 @@ out: return status; } -void nfs4_put_copy(struct nfsd4_copy *copy) +static void nfs4_put_copy(struct nfsd4_copy *copy) { if (!refcount_dec_and_test(©->refcount)) return; + kfree(copy->cp_src); kfree(copy); } -static bool -check_and_set_stop_copy(struct nfsd4_copy *copy) -{ - bool value; - - spin_lock(©->cp_clp->async_lock); - value = copy->stopped; - if (!copy->stopped) - copy->stopped = true; - spin_unlock(©->cp_clp->async_lock); - return value; -} - static void nfsd4_stop_copy(struct nfsd4_copy *copy) { - /* only 1 thread should stop the copy */ - if (!check_and_set_stop_copy(copy)) + if (!test_and_set_bit(NFSD4_COPY_F_STOPPED, ©->cp_flags)) kthread_stop(copy->copy_task); nfs4_put_copy(copy); } @@ -1215,7 +1335,7 @@ try_again: return 0; } if (work) { - strncpy(work->nsui_ipaddr, ipaddr, sizeof(work->nsui_ipaddr)); + strscpy(work->nsui_ipaddr, ipaddr, sizeof(work->nsui_ipaddr) - 1); refcount_set(&work->nsui_refcnt, 2); work->nsui_busy = true; list_add_tail(&work->nsui_list, &nn->nfsd_ssc_mount_list); @@ -1375,7 +1495,7 @@ nfsd4_setup_inter_ssc(struct svc_rqst *rqstp, if (status) goto out; - status = nfsd4_interssc_connect(©->cp_src, rqstp, mount); + status = nfsd4_interssc_connect(copy->cp_src, rqstp, mount); if (status) goto out; @@ -1393,7 +1513,7 @@ out: } static void -nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct nfsd_file *src, +nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct file *filp, struct nfsd_file *dst) { bool found = false; @@ -1402,9 +1522,9 @@ nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct nfsd_file *src, struct nfsd4_ssc_umount_item *ni = NULL; struct nfsd_net *nn = net_generic(dst->nf_net, nfsd_net_id); - nfs42_ssc_close(src->nf_file); + nfs42_ssc_close(filp); nfsd_file_put(dst); - fput(src->nf_file); + fput(filp); if (!nn) { mntput(ss_mnt); @@ -1447,7 +1567,7 @@ nfsd4_setup_inter_ssc(struct svc_rqst *rqstp, } static void -nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct nfsd_file *src, +nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct file *filp, struct nfsd_file *dst) { } @@ -1484,14 +1604,19 @@ nfsd4_cleanup_intra_ssc(struct nfsd_file *src, struct nfsd_file *dst) static void nfsd4_cb_offload_release(struct nfsd4_callback *cb) { - struct nfsd4_copy *copy = container_of(cb, struct nfsd4_copy, cp_cb); + struct nfsd4_cb_offload *cbo = + container_of(cb, struct nfsd4_cb_offload, co_cb); - nfs4_put_copy(copy); + kfree(cbo); } static int nfsd4_cb_offload_done(struct nfsd4_callback *cb, struct rpc_task *task) { + struct nfsd4_cb_offload *cbo = + container_of(cb, struct nfsd4_cb_offload, co_cb); + + trace_nfsd_cb_offload_done(&cbo->co_res.cb_stateid, task); return 1; } @@ -1503,18 +1628,22 @@ static const struct nfsd4_callback_ops nfsd4_cb_offload_ops = { static void nfsd4_init_copy_res(struct nfsd4_copy *copy, bool sync) { copy->cp_res.wr_stable_how = - copy->committed ? NFS_FILE_SYNC : NFS_UNSTABLE; - copy->cp_synchronous = 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) +static ssize_t _nfsd_copy_file_range(struct nfsd4_copy *copy, + struct file *dst, + struct file *src) { + errseq_t since; ssize_t bytes_copied = 0; u64 bytes_total = copy->cp_count; u64 src_pos = copy->cp_src_pos; u64 dst_pos = copy->cp_dst_pos; - __be32 status; + int status; /* See RFC 7862 p.67: */ if (bytes_total == 0) @@ -1522,35 +1651,37 @@ static ssize_t _nfsd_copy_file_range(struct nfsd4_copy *copy) do { if (kthread_should_stop()) break; - bytes_copied = nfsd_copy_file_range(copy->nf_src->nf_file, - src_pos, copy->nf_dst->nf_file, dst_pos, - bytes_total); + bytes_copied = nfsd_copy_file_range(src, src_pos, dst, dst_pos, + bytes_total); if (bytes_copied <= 0) break; bytes_total -= bytes_copied; copy->cp_res.wr_bytes_written += bytes_copied; src_pos += bytes_copied; dst_pos += bytes_copied; - } while (bytes_total > 0 && !copy->cp_synchronous); + } while (bytes_total > 0 && nfsd4_copy_is_async(copy)); /* for a non-zero asynchronous copy do a commit of data */ - if (!copy->cp_synchronous && copy->cp_res.wr_bytes_written > 0) { - down_write(©->nf_dst->nf_rwsem); - status = vfs_fsync_range(copy->nf_dst->nf_file, - copy->cp_dst_pos, + if (nfsd4_copy_is_async(copy) && copy->cp_res.wr_bytes_written > 0) { + since = READ_ONCE(dst->f_wb_err); + status = vfs_fsync_range(dst, copy->cp_dst_pos, copy->cp_res.wr_bytes_written, 0); - up_write(©->nf_dst->nf_rwsem); if (!status) - copy->committed = true; + status = filemap_check_wb_err(dst->f_mapping, since); + if (!status) + set_bit(NFSD4_COPY_F_COMMITTED, ©->cp_flags); } return bytes_copied; } -static __be32 nfsd4_do_copy(struct nfsd4_copy *copy, bool sync) +static __be32 nfsd4_do_copy(struct nfsd4_copy *copy, + struct file *src, struct file *dst, + bool sync) { __be32 status; ssize_t bytes; - bytes = _nfsd_copy_file_range(copy); + bytes = _nfsd_copy_file_range(copy, dst, src); + /* for async copy, we ignore the error, client can always retry * to get the error */ @@ -1560,13 +1691,6 @@ static __be32 nfsd4_do_copy(struct nfsd4_copy *copy, bool sync) nfsd4_init_copy_res(copy, sync); status = nfs_ok; } - - if (!copy->cp_intra) /* Inter server SSC */ - nfsd4_cleanup_inter_ssc(copy->ss_mnt, copy->nf_src, - copy->nf_dst); - else - nfsd4_cleanup_intra_ssc(copy->nf_src, copy->nf_dst); - return status; } @@ -1575,17 +1699,17 @@ static void dup_copy_fields(struct nfsd4_copy *src, struct nfsd4_copy *dst) dst->cp_src_pos = src->cp_src_pos; dst->cp_dst_pos = src->cp_dst_pos; dst->cp_count = src->cp_count; - dst->cp_synchronous = src->cp_synchronous; + dst->cp_flags = src->cp_flags; memcpy(&dst->cp_res, &src->cp_res, sizeof(src->cp_res)); memcpy(&dst->fh, &src->fh, sizeof(src->fh)); dst->cp_clp = src->cp_clp; dst->nf_dst = nfsd_file_get(src->nf_dst); - dst->cp_intra = src->cp_intra; - if (src->cp_intra) /* for inter, file_src doesn't exist yet */ + /* for inter, nf_src doesn't exist yet */ + if (!nfsd4_ssc_is_inter(src)) dst->nf_src = nfsd_file_get(src->nf_src); memcpy(&dst->cp_stateid, &src->cp_stateid, sizeof(src->cp_stateid)); - memcpy(&dst->cp_src, &src->cp_src, sizeof(struct nl4_server)); + 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; @@ -1595,7 +1719,7 @@ static void cleanup_async_copy(struct nfsd4_copy *copy) { nfs4_free_copy_state(copy); nfsd_file_put(copy->nf_dst); - if (copy->cp_intra) + if (!nfsd4_ssc_is_inter(copy)) nfsd_file_put(copy->nf_src); spin_lock(©->cp_clp->async_lock); list_del(©->copies); @@ -1603,45 +1727,64 @@ static void cleanup_async_copy(struct nfsd4_copy *copy) nfs4_put_copy(copy); } +static void nfsd4_send_cb_offload(struct nfsd4_copy *copy, __be32 nfserr) +{ + struct nfsd4_cb_offload *cbo; + + cbo = kzalloc(sizeof(*cbo), GFP_KERNEL); + if (!cbo) + return; + + memcpy(&cbo->co_res, ©->cp_res, sizeof(copy->cp_res)); + memcpy(&cbo->co_fh, ©->fh, sizeof(copy->fh)); + cbo->co_nfserr = nfserr; + + nfsd4_init_cb(&cbo->co_cb, copy->cp_clp, &nfsd4_cb_offload_ops, + NFSPROC4_CLNT_CB_OFFLOAD); + 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); +} + +/** + * nfsd4_do_async_copy - kthread function for background server-side COPY + * @data: arguments for COPY operation + * + * Return values: + * %0: Copy operation is done. + */ static int nfsd4_do_async_copy(void *data) { struct nfsd4_copy *copy = (struct nfsd4_copy *)data; - struct nfsd4_copy *cb_copy; + __be32 nfserr; - if (!copy->cp_intra) { /* Inter server SSC */ - copy->nf_src = kzalloc(sizeof(struct nfsd_file), GFP_KERNEL); - if (!copy->nf_src) { - copy->nfserr = nfserr_serverfault; - nfsd4_interssc_disconnect(copy->ss_mnt); - goto do_callback; - } - copy->nf_src->nf_file = nfs42_ssc_open(copy->ss_mnt, ©->c_fh, - ©->stateid); - if (IS_ERR(copy->nf_src->nf_file)) { - copy->nfserr = nfserr_offload_denied; + if (nfsd4_ssc_is_inter(copy)) { + struct file *filp; + + filp = nfs42_ssc_open(copy->ss_mnt, ©->c_fh, + ©->stateid); + if (IS_ERR(filp)) { + switch (PTR_ERR(filp)) { + case -EBADF: + nfserr = nfserr_wrong_type; + break; + default: + nfserr = nfserr_offload_denied; + } nfsd4_interssc_disconnect(copy->ss_mnt); 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); + } 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, 0); do_callback: - cb_copy = kzalloc(sizeof(struct nfsd4_copy), GFP_KERNEL); - if (!cb_copy) - goto out; - refcount_set(&cb_copy->refcount, 1); - memcpy(&cb_copy->cp_res, ©->cp_res, sizeof(copy->cp_res)); - cb_copy->cp_clp = copy->cp_clp; - cb_copy->nfserr = copy->nfserr; - memcpy(&cb_copy->fh, ©->fh, sizeof(copy->fh)); - nfsd4_init_cb(&cb_copy->cp_cb, cb_copy->cp_clp, - &nfsd4_cb_offload_ops, NFSPROC4_CLNT_CB_OFFLOAD); - trace_nfsd_cb_offload(copy->cp_clp, ©->cp_res.cb_stateid, - ©->fh, copy->cp_count, copy->nfserr); - nfsd4_run_cb(&cb_copy->cp_cb); -out: - if (!copy->cp_intra) - kfree(copy->nf_src); + nfsd4_send_cb_offload(copy, nfserr); cleanup_async_copy(copy); return 0; } @@ -1654,8 +1797,8 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, __be32 status; struct nfsd4_copy *async_copy = NULL; - if (!copy->cp_intra) { /* Inter server SSC */ - if (!inter_copy_offload_enable || copy->cp_synchronous) { + if (nfsd4_ssc_is_inter(copy)) { + if (!inter_copy_offload_enable || nfsd4_copy_is_sync(copy)) { status = nfserr_notsupp; goto out; } @@ -1672,17 +1815,20 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, copy->cp_clp = cstate->clp; memcpy(©->fh, &cstate->current_fh.fh_handle, sizeof(struct knfsd_fh)); - if (!copy->cp_synchronous) { + 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_src = kmalloc(sizeof(*async_copy->cp_src), GFP_KERNEL); + if (!async_copy->cp_src) + goto out_err; if (!nfs4_init_copy_state(nn, copy)) goto out_err; refcount_set(&async_copy->refcount, 1); - memcpy(©->cp_res.cb_stateid, ©->cp_stateid.stid, + memcpy(©->cp_res.cb_stateid, ©->cp_stateid.cs_stid, sizeof(copy->cp_res.cb_stateid)); dup_copy_fields(copy, async_copy); async_copy->copy_task = kthread_create(nfsd4_do_async_copy, @@ -1696,7 +1842,9 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, wake_up_process(async_copy->copy_task); status = nfs_ok; } else { - status = nfsd4_do_copy(copy, 1); + 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: return status; @@ -1704,7 +1852,7 @@ out_err: if (async_copy) cleanup_async_copy(async_copy); status = nfserrno(-ENOMEM); - if (!copy->cp_intra) + if (nfsd4_ssc_is_inter(copy)) nfsd4_interssc_disconnect(copy->ss_mnt); goto out; } @@ -1716,7 +1864,7 @@ find_async_copy(struct nfs4_client *clp, stateid_t *stateid) spin_lock(&clp->async_lock); list_for_each_entry(copy, &clp->async_copies, copies) { - if (memcmp(©->cp_stateid.stid, stateid, NFS4_STATEID_SIZE)) + if (memcmp(©->cp_stateid.cs_stid, stateid, NFS4_STATEID_SIZE)) continue; refcount_inc(©->refcount); spin_unlock(&clp->async_lock); @@ -1770,16 +1918,16 @@ nfsd4_copy_notify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, cps = nfs4_alloc_init_cpntf_state(nn, stid); if (!cps) goto out; - memcpy(&cn->cpn_cnr_stateid, &cps->cp_stateid.stid, sizeof(stateid_t)); + memcpy(&cn->cpn_cnr_stateid, &cps->cp_stateid.cs_stid, sizeof(stateid_t)); memcpy(&cps->cp_p_stateid, &stid->sc_stateid, sizeof(stateid_t)); memcpy(&cps->cp_p_clid, &clp->cl_clientid, sizeof(clientid_t)); /* For now, only return one server address in cpn_src, the * address used by the client to connect to this server. */ - cn->cpn_src.nl4_type = NL4_NETADDR; + cn->cpn_src->nl4_type = NL4_NETADDR; status = nfsd4_set_netaddr((struct sockaddr *)&rqstp->rq_daddr, - &cn->cpn_src.u.nl4_addr); + &cn->cpn_src->u.nl4_addr); WARN_ON_ONCE(status); if (status) { nfs4_put_cpntf_state(nn, cps); @@ -2433,7 +2581,7 @@ check_if_stalefh_allowed(struct nfsd4_compoundargs *args) return; } putfh = (struct nfsd4_putfh *)&saved_op->u; - if (!copy->cp_intra) + if (nfsd4_ssc_is_inter(copy)) putfh->no_verify = true; } } @@ -2474,11 +2622,12 @@ nfsd4_proc_compound(struct svc_rqst *rqstp) cstate->minorversion = args->minorversion; fh_init(current_fh, NFS4_FHSIZE); fh_init(save_fh, NFS4_FHSIZE); + /* * Don't use the deferral mechanism for NFSv4; compounds make it * too hard to avoid non-idempotency problems. */ - clear_bit(RQ_USEDEFERRAL, &rqstp->rq_flags); + __clear_bit(RQ_USEDEFERRAL, &rqstp->rq_flags); /* * According to RFC3010, this takes precedence over all other errors. @@ -2486,9 +2635,6 @@ nfsd4_proc_compound(struct svc_rqst *rqstp) status = nfserr_minor_vers_mismatch; if (nfsd_minorversion(nn, args->minorversion, NFSD_TEST) <= 0) goto out; - status = nfserr_resource; - if (args->opcnt > NFSD_MAX_OPS_PER_COMPOUND) - goto out; status = nfs41_check_op_ordering(args); if (status) { @@ -2501,10 +2647,20 @@ nfsd4_proc_compound(struct svc_rqst *rqstp) rqstp->rq_lease_breaker = (void **)&cstate->clp; - trace_nfsd_compound(rqstp, args->opcnt); + trace_nfsd_compound(rqstp, args->tag, args->taglen, args->client_opcnt); while (!status && resp->opcnt < args->opcnt) { op = &args->ops[resp->opcnt++]; + if (unlikely(resp->opcnt == NFSD_MAX_OPS_PER_COMPOUND)) { + /* If there are still more operations to process, + * stop here and report NFS4ERR_RESOURCE. */ + if (cstate->minorversion == 0 && + args->client_opcnt > resp->opcnt) { + op->status = nfserr_resource; + goto encode_op; + } + } + /* * The XDR decode routines may have pre-set op->status; * for example, if there is a miscellaneous XDR error @@ -2528,13 +2684,13 @@ nfsd4_proc_compound(struct svc_rqst *rqstp) goto encode_op; } - fh_clear_wcc(current_fh); + fh_clear_pre_post_attrs(current_fh); /* If op is non-idempotent */ if (op->opdesc->op_flags & OP_MODIFIES_SOMETHING) { /* * Don't execute this op if we couldn't encode a - * succesful reply: + * successful reply: */ u32 plen = op->opdesc->op_rsize_bop(rqstp, op); /* @@ -2580,8 +2736,8 @@ encode_op: status = op->status; } - trace_nfsd_compound_status(args->opcnt, resp->opcnt, status, - nfsd4_op_name(op->opnum)); + trace_nfsd_compound_status(args->client_opcnt, resp->opcnt, + status, nfsd4_op_name(op->opnum)); nfsd4_cstate_clear_replay(cstate); nfsd4_increment_op_stats(op->opnum); @@ -2593,7 +2749,7 @@ encode_op: out: cstate->status = status; /* Reset deferral mechanism for RPC deferrals */ - set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags); + __set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags); return rpc_success; } @@ -2615,28 +2771,49 @@ out: #define op_encode_channel_attrs_maxsz (6 + 1 + 1) -static inline u32 nfsd4_only_status_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +/* + * The _rsize() helpers are invoked by the NFSv4 COMPOUND decoder, which + * is called before sunrpc sets rq_res.buflen. Thus we have to compute + * the maximum payload size here, based on transport limits and the size + * of the remaining space in the rq_pages array. + */ +static u32 nfsd4_max_payload(const struct svc_rqst *rqstp) +{ + u32 buflen; + + buflen = (rqstp->rq_page_end - rqstp->rq_next_page) * PAGE_SIZE; + buflen -= rqstp->rq_auth_slack; + buflen -= rqstp->rq_res.head[0].iov_len; + return min_t(u32, buflen, svc_max_payload(rqstp)); +} + +static u32 nfsd4_only_status_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size) * sizeof(__be32); } -static inline u32 nfsd4_status_stateid_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_status_stateid_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + op_encode_stateid_maxsz)* sizeof(__be32); } -static inline u32 nfsd4_access_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_access_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { /* ac_supported, ac_resp_access */ return (op_encode_hdr_size + 2)* sizeof(__be32); } -static inline u32 nfsd4_commit_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_commit_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + op_encode_verifier_maxsz) * sizeof(__be32); } -static inline u32 nfsd4_create_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_create_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + op_encode_change_info_maxsz + nfs4_fattr_bitmap_maxsz) * sizeof(__be32); @@ -2647,17 +2824,17 @@ static inline u32 nfsd4_create_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op * the op prematurely if the estimate is too large. We may turn off splice * reads unnecessarily. */ -static inline u32 nfsd4_getattr_rsize(struct svc_rqst *rqstp, - struct nfsd4_op *op) +static u32 nfsd4_getattr_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { - u32 *bmap = op->u.getattr.ga_bmval; + const u32 *bmap = op->u.getattr.ga_bmval; u32 bmap0 = bmap[0], bmap1 = bmap[1], bmap2 = bmap[2]; u32 ret = 0; if (bmap0 & FATTR4_WORD0_ACL) - return svc_max_payload(rqstp); + return nfsd4_max_payload(rqstp); if (bmap0 & FATTR4_WORD0_FS_LOCATIONS) - return svc_max_payload(rqstp); + return nfsd4_max_payload(rqstp); if (bmap1 & FATTR4_WORD1_OWNER) { ret += IDMAP_NAMESZ + 4; @@ -2685,24 +2862,28 @@ static inline u32 nfsd4_getattr_rsize(struct svc_rqst *rqstp, return ret; } -static inline u32 nfsd4_getfh_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_getfh_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + 1) * sizeof(__be32) + NFS4_FHSIZE; } -static inline u32 nfsd4_link_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_link_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + op_encode_change_info_maxsz) * sizeof(__be32); } -static inline u32 nfsd4_lock_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_lock_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + op_encode_lock_denied_maxsz) * sizeof(__be32); } -static inline u32 nfsd4_open_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_open_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + op_encode_stateid_maxsz + op_encode_change_info_maxsz + 1 @@ -2710,20 +2891,18 @@ static inline u32 nfsd4_open_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) + op_encode_delegation_maxsz) * sizeof(__be32); } -static inline u32 nfsd4_read_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_read_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { - u32 maxcount = 0, rlen = 0; - - maxcount = svc_max_payload(rqstp); - rlen = min(op->u.read.rd_length, maxcount); + u32 rlen = min(op->u.read.rd_length, nfsd4_max_payload(rqstp)); return (op_encode_hdr_size + 2 + XDR_QUADLEN(rlen)) * sizeof(__be32); } -static inline u32 nfsd4_read_plus_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_read_plus_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { - u32 maxcount = svc_max_payload(rqstp); - u32 rlen = min(op->u.read.rd_length, maxcount); + u32 rlen = min(op->u.read.rd_length, nfsd4_max_payload(rqstp)); /* * If we detect that the file changed during hole encoding, then we * recover by encoding the remaining reply as data. This means we need @@ -2734,70 +2913,77 @@ static inline u32 nfsd4_read_plus_rsize(struct svc_rqst *rqstp, struct nfsd4_op return (op_encode_hdr_size + 2 + seg_len + XDR_QUADLEN(rlen)) * sizeof(__be32); } -static inline u32 nfsd4_readdir_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_readdir_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { - u32 maxcount = 0, rlen = 0; - - maxcount = svc_max_payload(rqstp); - rlen = min(op->u.readdir.rd_maxcount, maxcount); + u32 rlen = min(op->u.readdir.rd_maxcount, nfsd4_max_payload(rqstp)); return (op_encode_hdr_size + op_encode_verifier_maxsz + XDR_QUADLEN(rlen)) * sizeof(__be32); } -static inline u32 nfsd4_readlink_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_readlink_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + 1) * sizeof(__be32) + PAGE_SIZE; } -static inline u32 nfsd4_remove_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_remove_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + op_encode_change_info_maxsz) * sizeof(__be32); } -static inline u32 nfsd4_rename_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_rename_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + op_encode_change_info_maxsz + op_encode_change_info_maxsz) * sizeof(__be32); } -static inline u32 nfsd4_sequence_rsize(struct svc_rqst *rqstp, - struct nfsd4_op *op) +static u32 nfsd4_sequence_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + 5) * sizeof(__be32); } -static inline u32 nfsd4_test_stateid_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_test_stateid_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + 1 + op->u.test_stateid.ts_num_ids) * sizeof(__be32); } -static inline u32 nfsd4_setattr_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_setattr_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + nfs4_fattr_bitmap_maxsz) * sizeof(__be32); } -static inline u32 nfsd4_secinfo_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_secinfo_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + RPC_AUTH_MAXFLAVOR * (4 + XDR_QUADLEN(GSS_OID_MAX_LEN))) * sizeof(__be32); } -static inline u32 nfsd4_setclientid_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_setclientid_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + 2 + XDR_QUADLEN(NFS4_VERIFIER_SIZE)) * sizeof(__be32); } -static inline u32 nfsd4_write_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_write_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + 2 + op_encode_verifier_maxsz) * sizeof(__be32); } -static inline u32 nfsd4_exchange_id_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_exchange_id_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + 2 + 1 + /* eir_clientid, eir_sequenceid */\ 1 + 1 + /* eir_flags, spr_how */\ @@ -2811,14 +2997,16 @@ static inline u32 nfsd4_exchange_id_rsize(struct svc_rqst *rqstp, struct nfsd4_o 0 /* ignored eir_server_impl_id contents */) * sizeof(__be32); } -static inline u32 nfsd4_bind_conn_to_session_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_bind_conn_to_session_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + \ XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + /* bctsr_sessid */\ 2 /* bctsr_dir, use_conn_in_rdma_mode */) * sizeof(__be32); } -static inline u32 nfsd4_create_session_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_create_session_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + \ XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + /* sessionid */\ @@ -2827,7 +3015,8 @@ static inline u32 nfsd4_create_session_rsize(struct svc_rqst *rqstp, struct nfsd op_encode_channel_attrs_maxsz) * sizeof(__be32); } -static inline u32 nfsd4_copy_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_copy_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + 1 /* wr_callback */ + @@ -2839,16 +3028,16 @@ static inline u32 nfsd4_copy_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) 1 /* cr_synchronous */) * sizeof(__be32); } -static inline u32 nfsd4_offload_status_rsize(struct svc_rqst *rqstp, - struct nfsd4_op *op) +static u32 nfsd4_offload_status_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + 2 /* osr_count */ + 1 /* osr_complete<1> optional 0 for now */) * sizeof(__be32); } -static inline u32 nfsd4_copy_notify_rsize(struct svc_rqst *rqstp, - struct nfsd4_op *op) +static u32 nfsd4_copy_notify_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + 3 /* cnr_lease_time */ + @@ -2863,12 +3052,10 @@ static inline u32 nfsd4_copy_notify_rsize(struct svc_rqst *rqstp, } #ifdef CONFIG_NFSD_PNFS -static inline u32 nfsd4_getdeviceinfo_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_getdeviceinfo_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { - u32 maxcount = 0, rlen = 0; - - maxcount = svc_max_payload(rqstp); - rlen = min(op->u.getdeviceinfo.gd_maxcount, maxcount); + u32 rlen = min(op->u.getdeviceinfo.gd_maxcount, nfsd4_max_payload(rqstp)); return (op_encode_hdr_size + 1 /* gd_layout_type*/ + @@ -2881,7 +3068,8 @@ static inline u32 nfsd4_getdeviceinfo_rsize(struct svc_rqst *rqstp, struct nfsd4 * so we need to define an arbitrary upper bound here. */ #define MAX_LAYOUT_SIZE 128 -static inline u32 nfsd4_layoutget_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_layoutget_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + 1 /* logr_return_on_close */ + @@ -2890,14 +3078,16 @@ static inline u32 nfsd4_layoutget_rsize(struct svc_rqst *rqstp, struct nfsd4_op MAX_LAYOUT_SIZE) * sizeof(__be32); } -static inline u32 nfsd4_layoutcommit_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_layoutcommit_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + 1 /* locr_newsize */ + 2 /* ns_size */) * sizeof(__be32); } -static inline u32 nfsd4_layoutreturn_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_layoutreturn_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + 1 /* lrs_stateid */ + @@ -2906,41 +3096,36 @@ static inline u32 nfsd4_layoutreturn_rsize(struct svc_rqst *rqstp, struct nfsd4_ #endif /* CONFIG_NFSD_PNFS */ -static inline u32 nfsd4_seek_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_seek_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + 3) * sizeof(__be32); } -static inline u32 nfsd4_getxattr_rsize(struct svc_rqst *rqstp, - struct nfsd4_op *op) +static u32 nfsd4_getxattr_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { - u32 maxcount, rlen; - - maxcount = svc_max_payload(rqstp); - rlen = min_t(u32, XATTR_SIZE_MAX, maxcount); + u32 rlen = min_t(u32, XATTR_SIZE_MAX, nfsd4_max_payload(rqstp)); return (op_encode_hdr_size + 1 + XDR_QUADLEN(rlen)) * sizeof(__be32); } -static inline u32 nfsd4_setxattr_rsize(struct svc_rqst *rqstp, - struct nfsd4_op *op) +static u32 nfsd4_setxattr_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + op_encode_change_info_maxsz) * sizeof(__be32); } -static inline u32 nfsd4_listxattrs_rsize(struct svc_rqst *rqstp, - struct nfsd4_op *op) +static u32 nfsd4_listxattrs_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { - u32 maxcount, rlen; - - maxcount = svc_max_payload(rqstp); - rlen = min(op->u.listxattrs.lsxa_maxcount, maxcount); + u32 rlen = min(op->u.listxattrs.lsxa_maxcount, nfsd4_max_payload(rqstp)); return (op_encode_hdr_size + 4 + XDR_QUADLEN(rlen)) * sizeof(__be32); } -static inline u32 nfsd4_removexattr_rsize(struct svc_rqst *rqstp, - struct nfsd4_op *op) +static u32 nfsd4_removexattr_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + op_encode_change_info_maxsz) * sizeof(__be32); @@ -3429,6 +3614,7 @@ static const struct svc_procedure nfsd_procedures4[2] = { .pc_decode = nfssvc_decode_voidarg, .pc_encode = nfssvc_encode_voidres, .pc_argsize = sizeof(struct nfsd_voidargs), + .pc_argzero = sizeof(struct nfsd_voidargs), .pc_ressize = sizeof(struct nfsd_voidres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = 1, @@ -3439,6 +3625,7 @@ static const struct svc_procedure nfsd_procedures4[2] = { .pc_decode = nfs4svc_decode_compoundargs, .pc_encode = nfs4svc_encode_compoundres, .pc_argsize = sizeof(struct nfsd4_compoundargs), + .pc_argzero = offsetof(struct nfsd4_compoundargs, iops), .pc_ressize = sizeof(struct nfsd4_compoundres), .pc_release = nfsd4_release_compoundargs, .pc_cachetype = RC_NOCACHE, diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index c634483d85d2..78b8cd9651d5 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -266,7 +266,7 @@ struct nfs4_dir_ctx { struct list_head names; }; -static int +static bool nfsd4_build_namelist(struct dir_context *__ctx, const char *name, int namlen, loff_t offset, u64 ino, unsigned int d_type) { @@ -275,14 +275,14 @@ nfsd4_build_namelist(struct dir_context *__ctx, const char *name, int namlen, struct name_list *entry; if (namlen != HEXDIR_LEN - 1) - return 0; + return true; entry = kmalloc(sizeof(struct name_list), GFP_KERNEL); if (entry == NULL) - return -ENOMEM; + return false; memcpy(entry->name, name, HEXDIR_LEN - 1); entry->name[HEXDIR_LEN - 1] = '\0'; list_add(&entry->list, &ctx->names); - return 0; + return true; } static int @@ -807,16 +807,18 @@ __cld_pipe_inprogress_downcall(const struct cld_msg_v2 __user *cmsg, if (get_user(namelen, &ci->cc_name.cn_len)) return -EFAULT; name.data = memdup_user(&ci->cc_name.cn_id, namelen); - if (IS_ERR_OR_NULL(name.data)) - return -EFAULT; + if (IS_ERR(name.data)) + return PTR_ERR(name.data); 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_OR_NULL(princhash.data)) - return -EFAULT; + if (IS_ERR(princhash.data)) { + kfree(name.data); + return PTR_ERR(princhash.data); + } princhash.len = princhashlen; } else princhash.len = 0; @@ -827,8 +829,8 @@ __cld_pipe_inprogress_downcall(const struct cld_msg_v2 __user *cmsg, if (get_user(namelen, &cnm->cn_len)) return -EFAULT; name.data = memdup_user(&cnm->cn_id, namelen); - if (IS_ERR_OR_NULL(name.data)) - return -EFAULT; + if (IS_ERR(name.data)) + return PTR_ERR(name.data); name.len = namelen; } if (name.len > 5 && memcmp(name.data, "hash:", 5) == 0) { diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 1956d377d1a6..836bd825ca4a 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -125,6 +125,23 @@ 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 struct workqueue_struct *laundry_wq; + +int nfsd4_create_laundry_wq(void) +{ + int rc = 0; + + laundry_wq = alloc_workqueue("%s", WQ_UNBOUND, 0, "nfsd4"); + if (laundry_wq == NULL) + rc = -ENOMEM; + return rc; +} + +void nfsd4_destroy_laundry_wq(void) +{ + destroy_workqueue(laundry_wq); +} + static bool is_session_dead(struct nfsd4_session *ses) { return ses->se_flags & NFS4_SESSION_DEAD; @@ -143,6 +160,13 @@ static bool is_client_expired(struct nfs4_client *clp) return clp->cl_time == 0; } +static void nfsd4_dec_courtesy_client_count(struct nfsd_net *nn, + struct nfs4_client *clp) +{ + if (clp->cl_state != NFSD4_ACTIVE) + atomic_add_unless(&nn->nfsd_courtesy_clients, -1, 0); +} + static __be32 get_client_locked(struct nfs4_client *clp) { struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); @@ -152,6 +176,8 @@ static __be32 get_client_locked(struct nfs4_client *clp) if (is_client_expired(clp)) return nfserr_expired; atomic_inc(&clp->cl_rpc_users); + nfsd4_dec_courtesy_client_count(nn, clp); + clp->cl_state = NFSD4_ACTIVE; return nfs_ok; } @@ -172,6 +198,8 @@ renew_client_locked(struct nfs4_client *clp) list_move_tail(&clp->cl_lru, &nn->client_lru); clp->cl_time = ktime_get_boottime_seconds(); + nfsd4_dec_courtesy_client_count(nn, clp); + clp->cl_state = NFSD4_ACTIVE; } static void put_client_renew_locked(struct nfs4_client *clp) @@ -246,6 +274,7 @@ find_blocked_lock(struct nfs4_lockowner *lo, struct knfsd_fh *fh, list_for_each_entry(cur, &lo->lo_blocked, nbl_list) { if (fh_match(fh, &cur->nbl_fh)) { list_del_init(&cur->nbl_list); + WARN_ON(list_empty(&cur->nbl_lru)); list_del_init(&cur->nbl_lru); found = cur; break; @@ -271,6 +300,7 @@ find_or_allocate_block(struct nfs4_lockowner *lo, struct knfsd_fh *fh, INIT_LIST_HEAD(&nbl->nbl_lru); fh_copy_shallow(&nbl->nbl_fh, fh); locks_init_lock(&nbl->nbl_lock); + kref_init(&nbl->nbl_kref); nfsd4_init_cb(&nbl->nbl_cb, lo->lo_owner.so_client, &nfsd4_cb_notify_lock_ops, NFSPROC4_CLNT_CB_NOTIFY_LOCK); @@ -280,11 +310,20 @@ find_or_allocate_block(struct nfs4_lockowner *lo, struct knfsd_fh *fh, } static void +free_nbl(struct kref *kref) +{ + struct nfsd4_blocked_lock *nbl; + + nbl = container_of(kref, struct nfsd4_blocked_lock, nbl_kref); + kfree(nbl); +} + +static void free_blocked_lock(struct nfsd4_blocked_lock *nbl) { locks_delete_block(&nbl->nbl_lock); locks_release_private(&nbl->nbl_lock); - kfree(nbl); + kref_put(&nbl->nbl_kref, free_nbl); } static void @@ -302,6 +341,7 @@ remove_blocked_locks(struct nfs4_lockowner *lo) struct nfsd4_blocked_lock, nbl_list); list_del_init(&nbl->nbl_list); + WARN_ON(list_empty(&nbl->nbl_lru)); list_move(&nbl->nbl_lru, &reaplist); } spin_unlock(&nn->blocked_locks_lock); @@ -326,6 +366,8 @@ nfsd4_cb_notify_lock_prepare(struct nfsd4_callback *cb) static int nfsd4_cb_notify_lock_done(struct nfsd4_callback *cb, struct rpc_task *task) { + trace_nfsd_cb_notify_lock_done(&zero_stateid, task); + /* * Since this is just an optimization, we don't try very hard if it * turns out not to succeed. We'll requeue it on NFS4ERR_DELAY, and @@ -360,11 +402,13 @@ static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops = { * st_{access,deny}_bmap field of the stateid, in order to track not * only what share bits are currently in force, but also what * combinations of share bits previous opens have used. This allows us - * to enforce the recommendation of rfc 3530 14.2.19 that the server - * return an error if the client attempt to downgrade to a combination - * of share bits not explicable by closing some of its previous opens. + * to enforce the recommendation in + * https://datatracker.ietf.org/doc/html/rfc7530#section-16.19.4 that + * the server return an error if the client attempt to downgrade to a + * combination of share bits not explicable by closing some of its + * previous opens. * - * XXX: This enforcement is actually incomplete, since we don't keep + * This enforcement is arguably incomplete, since we don't keep * track of access/deny bit combinations; so, e.g., we allow: * * OPEN allow read, deny write @@ -372,6 +416,10 @@ static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops = { * DOWNGRADE allow read, deny none * * which we should reject. + * + * But you could also argue that our current code is already overkill, + * since it only exists to return NFS4ERR_INVAL on incorrect client + * behavior. */ static unsigned int bmap_to_share_mode(unsigned long bmap) @@ -672,6 +720,57 @@ static unsigned int file_hashval(struct svc_fh *fh) static struct hlist_head file_hashtbl[FILE_HASH_SIZE]; +/* + * Check if courtesy clients have conflicting access and resolve it if possible + * + * access: is op_share_access if share_access is true. + * Check if access mode, op_share_access, would conflict with + * the current deny mode of the file 'fp'. + * access: is op_share_deny if share_access is false. + * Check if the deny mode, op_share_deny, would conflict with + * current access of the file 'fp'. + * stp: skip checking this entry. + * new_stp: normal open, not open upgrade. + * + * Function returns: + * false - access/deny mode conflict with normal client. + * true - no conflict or conflict with courtesy client(s) is resolved. + */ +static bool +nfs4_resolve_deny_conflicts_locked(struct nfs4_file *fp, bool new_stp, + struct nfs4_ol_stateid *stp, u32 access, bool share_access) +{ + struct nfs4_ol_stateid *st; + bool resolvable = true; + unsigned char bmap; + struct nfsd_net *nn; + struct nfs4_client *clp; + + lockdep_assert_held(&fp->fi_lock); + list_for_each_entry(st, &fp->fi_stateids, st_perfile) { + /* ignore lock stateid */ + if (st->st_openstp) + continue; + if (st == stp && new_stp) + continue; + /* check file access against deny mode or vice versa */ + bmap = share_access ? st->st_deny_bmap : st->st_access_bmap; + if (!(access & bmap_to_share_mode(bmap))) + continue; + clp = st->st_stid.sc_client; + if (try_to_expire_client(clp)) + continue; + resolvable = false; + break; + } + if (resolvable) { + clp = stp->st_stid.sc_client; + nn = net_generic(clp->net, nfsd_net_id); + mod_delayed_work(laundry_wq, &nn->laundromat_work, 0); + } + return resolvable; +} + static void __nfs4_file_get_access(struct nfs4_file *fp, u32 access) { @@ -732,9 +831,9 @@ static void __nfs4_file_put_access(struct nfs4_file *fp, int oflag) swap(f2, fp->fi_fds[O_RDWR]); spin_unlock(&fp->fi_lock); if (f1) - nfsd_file_put(f1); + nfsd_file_close(f1); if (f2) - nfsd_file_put(f2); + nfsd_file_close(f2); } } @@ -875,19 +974,19 @@ out_free: * Create a unique stateid_t to represent each COPY. */ static int nfs4_init_cp_state(struct nfsd_net *nn, copy_stateid_t *stid, - unsigned char sc_type) + unsigned char cs_type) { int new_id; - stid->stid.si_opaque.so_clid.cl_boot = (u32)nn->boot_time; - stid->stid.si_opaque.so_clid.cl_id = nn->s2s_cp_cl_id; - stid->sc_type = sc_type; + 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); new_id = idr_alloc_cyclic(&nn->s2s_cp_stateids, stid, 0, 0, GFP_NOWAIT); - stid->stid.si_opaque.so_id = new_id; - stid->stid.si_generation = 1; + stid->cs_stid.si_opaque.so_id = new_id; + stid->cs_stid.si_generation = 1; spin_unlock(&nn->s2s_cp_lock); idr_preload_end(); if (new_id < 0) @@ -909,7 +1008,7 @@ struct nfs4_cpntf_state *nfs4_alloc_init_cpntf_state(struct nfsd_net *nn, if (!cps) return NULL; cps->cpntf_time = ktime_get_boottime_seconds(); - refcount_set(&cps->cp_stateid.sc_count, 1); + refcount_set(&cps->cp_stateid.cs_count, 1); if (!nfs4_init_cp_state(nn, &cps->cp_stateid, NFS4_COPYNOTIFY_STID)) goto out_free; spin_lock(&nn->s2s_cp_lock); @@ -925,11 +1024,11 @@ void nfs4_free_copy_state(struct nfsd4_copy *copy) { struct nfsd_net *nn; - WARN_ON_ONCE(copy->cp_stateid.sc_type != NFS4_COPY_STID); + WARN_ON_ONCE(copy->cp_stateid.cs_type != NFS4_COPY_STID); nn = net_generic(copy->cp_clp->net, nfsd_net_id); spin_lock(&nn->s2s_cp_lock); idr_remove(&nn->s2s_cp_stateids, - copy->cp_stateid.stid.si_opaque.so_id); + copy->cp_stateid.cs_stid.si_opaque.so_id); spin_unlock(&nn->s2s_cp_lock); } @@ -961,6 +1060,12 @@ static struct nfs4_ol_stateid * nfs4_alloc_open_stateid(struct nfs4_client *clp) static void nfs4_free_deleg(struct nfs4_stid *stid) { + struct nfs4_delegation *dp = delegstateid(stid); + + WARN_ON_ONCE(!list_empty(&stid->sc_cp_list)); + WARN_ON_ONCE(!list_empty(&dp->dl_perfile)); + WARN_ON_ONCE(!list_empty(&dp->dl_perclnt)); + WARN_ON_ONCE(!list_empty(&dp->dl_recall_lru)); kmem_cache_free(deleg_slab, stid); atomic_long_dec(&num_delegations); } @@ -1043,7 +1148,6 @@ static void block_delegations(struct knfsd_fh *fh) static struct nfs4_delegation * alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp, - struct svc_fh *current_fh, struct nfs4_clnt_odstate *odstate) { struct nfs4_delegation *dp; @@ -1053,7 +1157,7 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp, n = atomic_long_inc_return(&num_delegations); if (n < 0 || n > max_delegations) goto out_dec; - if (delegation_blocked(¤t_fh->fh_handle)) + if (delegation_blocked(&fp->fi_fhandle)) goto out_dec; dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab, nfs4_free_deleg)); if (dp == NULL) @@ -1072,6 +1176,7 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp, get_clnt_odstate(odstate); dp->dl_type = NFS4_OPEN_DELEGATE_READ; 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); get_nfs4_file(fp); @@ -1374,6 +1479,7 @@ 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)); kmem_cache_free(stateid_slab, stid); } @@ -1964,11 +2070,16 @@ STALE_CLIENTID(clientid_t *clid, struct nfsd_net *nn) * 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) +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) { + mod_delayed_work(laundry_wq, &nn->laundromat_work, 0); + return NULL; + } clp = kmem_cache_zalloc(client_slab, GFP_KERNEL); if (clp == NULL) return NULL; @@ -1986,6 +2097,9 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name) idr_init(&clp->cl_stateids); atomic_set(&clp->cl_rpc_users, 0); clp->cl_cb_state = NFSD4_CB_UNKNOWN; + clp->cl_state = NFSD4_ACTIVE; + atomic_inc(&nn->nfs4_client_count); + atomic_set(&clp->cl_delegs_in_recall, 0); INIT_LIST_HEAD(&clp->cl_idhash); INIT_LIST_HEAD(&clp->cl_openowners); INIT_LIST_HEAD(&clp->cl_delegations); @@ -2092,6 +2206,7 @@ static __be32 mark_client_expired_locked(struct nfs4_client *clp) static void __destroy_client(struct nfs4_client *clp) { + struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); int i; struct nfs4_openowner *oo; struct nfs4_delegation *dp; @@ -2135,6 +2250,8 @@ __destroy_client(struct nfs4_client *clp) nfsd4_shutdown_callback(clp); if (clp->cl_cb_conn.cb_xprt) svc_xprt_put(clp->cl_cb_conn.cb_xprt); + atomic_add_unless(&nn->nfs4_client_count, -1, 0); + nfsd4_dec_courtesy_client_count(nn, clp); free_client(clp); wake_up_all(&expiry_wq); } @@ -2380,7 +2497,7 @@ static const char *cb_state2str(int state) static int client_info_show(struct seq_file *m, void *v) { - struct inode *inode = m->private; + struct inode *inode = file_inode(m->file); struct nfs4_client *clp; u64 clid; @@ -2390,10 +2507,17 @@ static int client_info_show(struct seq_file *m, void *v) memcpy(&clid, &clp->cl_clientid, sizeof(clid)); seq_printf(m, "clientid: 0x%llx\n", clid); seq_printf(m, "address: \"%pISpc\"\n", (struct sockaddr *)&clp->cl_addr); - if (test_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags)) + + if (clp->cl_state == NFSD4_COURTESY) + seq_puts(m, "status: courtesy\n"); + else if (clp->cl_state == NFSD4_EXPIRABLE) + seq_puts(m, "status: expirable\n"); + else if (test_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags)) seq_puts(m, "status: confirmed\n"); else 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_quote_mem(m, clp->cl_name.data, clp->cl_name.len); seq_printf(m, "\nminor version: %d\n", clp->cl_minorversion); @@ -2413,17 +2537,7 @@ static int client_info_show(struct seq_file *m, void *v) return 0; } -static int client_info_open(struct inode *inode, struct file *file) -{ - return single_open(file, client_info_show, inode); -} - -static const struct file_operations client_info_fops = { - .open = client_info_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(client_info); static void *states_start(struct seq_file *s, loff_t *pos) __acquires(&clp->cl_lock) @@ -2466,7 +2580,7 @@ static void nfs4_show_fname(struct seq_file *s, struct nfsd_file *f) static void nfs4_show_superblock(struct seq_file *s, struct nfsd_file *f) { - struct inode *inode = f->nf_inode; + struct inode *inode = file_inode(f->nf_file); seq_printf(s, "superblock: \"%02x:%02x:%ld\"", MAJOR(inode->i_sb->s_dev), @@ -2750,7 +2864,7 @@ static struct nfs4_client *create_client(struct xdr_netobj name, struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct dentry *dentries[ARRAY_SIZE(client_files)]; - clp = alloc_client(name); + clp = alloc_client(name, nn); if (clp == NULL) return NULL; @@ -4112,8 +4226,10 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp, status = nfserr_clid_inuse; if (client_has_state(old) && !same_creds(&unconf->cl_cred, - &old->cl_cred)) + &old->cl_cred)) { + old = NULL; goto out; + } status = mark_client_expired_locked(old); if (status) { old = NULL; @@ -4230,6 +4346,59 @@ out: return -ENOMEM; } +static unsigned long +nfsd_courtesy_client_count(struct shrinker *shrink, struct shrink_control *sc) +{ + int cnt; + struct nfsd_net *nn = container_of(shrink, + struct nfsd_net, nfsd_client_shrinker); + + cnt = atomic_read(&nn->nfsd_courtesy_clients); + if (cnt > 0) + mod_delayed_work(laundry_wq, &nn->nfsd_shrinker_work, 0); + return (unsigned long)cnt; +} + +static unsigned long +nfsd_courtesy_client_scan(struct shrinker *shrink, struct shrink_control *sc) +{ + return SHRINK_STOP; +} + +int +nfsd4_init_leases_net(struct nfsd_net *nn) +{ + struct sysinfo si; + u64 max_clients; + + nn->nfsd4_lease = 90; /* default lease time */ + nn->nfsd4_grace = 90; + nn->somebody_reclaimed = false; + nn->track_reclaim_completes = false; + nn->clverifier_counter = get_random_u32(); + nn->clientid_base = get_random_u32(); + nn->clientid_counter = nn->clientid_base + 1; + nn->s2s_cp_cl_id = nn->clientid_counter++; + + atomic_set(&nn->nfs4_client_count, 0); + si_meminfo(&si); + max_clients = (u64)si.totalram * si.mem_unit / (1024 * 1024 * 1024); + max_clients *= NFS4_CLIENTS_PER_GB; + nn->nfs4_max_clients = max_t(int, max_clients, NFS4_CLIENTS_PER_GB); + + atomic_set(&nn->nfsd_courtesy_clients, 0); + nn->nfsd_client_shrinker.scan_objects = nfsd_courtesy_client_scan; + nn->nfsd_client_shrinker.count_objects = nfsd_courtesy_client_count; + nn->nfsd_client_shrinker.seeks = DEFAULT_SEEKS; + return register_shrinker(&nn->nfsd_client_shrinker, "nfsd-client"); +} + +void +nfsd4_leases_net_shutdown(struct nfsd_net *nn) +{ + unregister_shrinker(&nn->nfsd_client_shrinker); +} + static void init_nfs4_replay(struct nfs4_replay *rp) { rp->rp_status = nfserr_serverfault; @@ -4587,6 +4756,35 @@ nfs4_share_conflict(struct svc_fh *current_fh, unsigned int deny_type) return ret; } +static bool nfsd4_deleg_present(const struct inode *inode) +{ + struct file_lock_context *ctx = smp_load_acquire(&inode->i_flctx); + + return ctx && !list_empty_careful(&ctx->flc_lease); +} + +/** + * nfsd_wait_for_delegreturn - wait for delegations to be returned + * @rqstp: the RPC transaction being executed + * @inode: in-core inode of the file being waited for + * + * The timeout prevents deadlock if all nfsd threads happen to be + * tied up waiting for returning delegations. + * + * Return values: + * %true: delegation was returned + * %false: timed out waiting for delegreturn + */ +bool nfsd_wait_for_delegreturn(struct svc_rqst *rqstp, struct inode *inode) +{ + long __maybe_unused timeo; + + timeo = wait_var_event_timeout(inode, !nfsd4_deleg_present(inode), + NFSD_DELEGRETURN_TIMEOUT); + trace_nfsd_delegret_wakeup(rqstp, inode, timeo); + return timeo > 0; +} + static void nfsd4_cb_recall_prepare(struct nfsd4_callback *cb) { struct nfs4_delegation *dp = cb_to_delegation(cb); @@ -4615,6 +4813,8 @@ static int nfsd4_cb_recall_done(struct nfsd4_callback *cb, { struct nfs4_delegation *dp = cb_to_delegation(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; @@ -4660,23 +4860,31 @@ static void nfsd_break_one_deleg(struct nfs4_delegation *dp) * We're assuming the state code never drops its reference * without first removing the lease. Since we're in this lease * callback (and since the lease code is serialized by the - * i_lock) we know the server hasn't removed the lease yet, and + * flc_lock) we know the server hasn't removed the lease yet, and * we know it's safe to take a reference. */ refcount_inc(&dp->dl_stid.sc_count); - nfsd4_run_cb(&dp->dl_recall); + WARN_ON_ONCE(!nfsd4_run_cb(&dp->dl_recall)); } -/* Called from break_lease() with i_lock held. */ +/* Called from break_lease() with flc_lock held. */ static bool nfsd_break_deleg_cb(struct file_lock *fl) { - bool ret = false; struct nfs4_delegation *dp = (struct nfs4_delegation *)fl->fl_owner; struct nfs4_file *fp = dp->dl_stid.sc_file; + struct nfs4_client *clp = dp->dl_stid.sc_client; + struct nfsd_net *nn; trace_nfsd_cb_recall(&dp->dl_stid); + dp->dl_recalled = true; + atomic_inc(&clp->cl_delegs_in_recall); + if (try_to_expire_client(clp)) { + nn = net_generic(clp->net, nfsd_net_id); + mod_delayed_work(laundry_wq, &nn->laundromat_work, 0); + } + /* * We don't want the locks code to timeout the lease for us; * we'll remove it ourself if a delegation isn't returned @@ -4688,9 +4896,17 @@ nfsd_break_deleg_cb(struct file_lock *fl) fp->fi_had_conflict = true; nfsd_break_one_deleg(dp); spin_unlock(&fp->fi_lock); - return ret; + return false; } +/** + * nfsd_breaker_owns_lease - Check if lease conflict was resolved + * @fl: Lock state to check + * + * Return values: + * %true: Lease conflict was resolved + * %false: Lease conflict was not resolved. + */ static bool nfsd_breaker_owns_lease(struct file_lock *fl) { struct nfs4_delegation *dl = fl->fl_owner; @@ -4698,11 +4914,11 @@ static bool nfsd_breaker_owns_lease(struct file_lock *fl) struct nfs4_client *clp; if (!i_am_nfsd()) - return NULL; + 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) - return NULL; + return false; clp = *(rqst->rq_lease_breaker); return dl->dl_stid.sc_client == clp; } @@ -4711,9 +4927,14 @@ static int nfsd_change_deleg_cb(struct file_lock *onlist, int arg, struct list_head *dispose) { - if (arg & F_UNLCK) + struct nfs4_delegation *dp = (struct nfs4_delegation *)onlist->fl_owner; + struct nfs4_client *clp = dp->dl_stid.sc_client; + + if (arg & F_UNLCK) { + if (dp->dl_recalled) + atomic_dec(&clp->cl_delegs_in_recall); return lease_modify(onlist, arg, dispose); - else + } else return -EAGAIN; } @@ -4910,16 +5131,19 @@ nfsd4_truncate(struct svc_rqst *rqstp, struct svc_fh *fh, .ia_valid = ATTR_SIZE, .ia_size = 0, }; + struct nfsd_attrs attrs = { + .na_iattr = &iattr, + }; if (!open->op_truncate) return 0; if (!(open->op_share_access & NFS4_SHARE_ACCESS_WRITE)) return nfserr_inval; - return nfsd_setattr(rqstp, fh, &iattr, 0, (time64_t)0); + return nfsd_setattr(rqstp, fh, &attrs, 0, (time64_t)0); } static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp, struct svc_fh *cur_fh, struct nfs4_ol_stateid *stp, - struct nfsd4_open *open) + struct nfsd4_open *open, bool new_stp) { struct nfsd_file *nf = NULL; __be32 status; @@ -4935,6 +5159,13 @@ static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp, */ status = nfs4_file_check_deny(fp, open->op_share_deny); if (status != nfs_ok) { + if (status != nfserr_share_denied) { + spin_unlock(&fp->fi_lock); + goto out; + } + if (nfs4_resolve_deny_conflicts_locked(fp, new_stp, + stp, open->op_share_deny, false)) + status = nfserr_jukebox; spin_unlock(&fp->fi_lock); goto out; } @@ -4942,6 +5173,13 @@ static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp, /* set access to the file */ status = nfs4_file_get_access(fp, open->op_share_access); if (status != nfs_ok) { + if (status != nfserr_share_denied) { + spin_unlock(&fp->fi_lock); + goto out; + } + if (nfs4_resolve_deny_conflicts_locked(fp, new_stp, + stp, open->op_share_access, true)) + status = nfserr_jukebox; spin_unlock(&fp->fi_lock); goto out; } @@ -4957,9 +5195,20 @@ static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp, if (!fp->fi_fds[oflag]) { spin_unlock(&fp->fi_lock); - status = nfsd_file_acquire(rqstp, cur_fh, access, &nf); - if (status) - goto out_put_access; + + if (!open->op_filp) { + status = nfsd_file_acquire(rqstp, cur_fh, access, &nf); + if (status != nfs_ok) + goto out_put_access; + } else { + status = nfsd_file_create(rqstp, cur_fh, access, &nf); + if (status != nfs_ok) + goto out_put_access; + nf->nf_file = open->op_filp; + open->op_filp = NULL; + trace_nfsd_file_create(rqstp, access, nf); + } + spin_lock(&fp->fi_lock); if (!fp->fi_fds[oflag]) { fp->fi_fds[oflag] = nf; @@ -4988,21 +5237,29 @@ out_put_access: } static __be32 -nfs4_upgrade_open(struct svc_rqst *rqstp, struct nfs4_file *fp, struct svc_fh *cur_fh, struct nfs4_ol_stateid *stp, struct nfsd4_open *open) +nfs4_upgrade_open(struct svc_rqst *rqstp, struct nfs4_file *fp, + struct svc_fh *cur_fh, struct nfs4_ol_stateid *stp, + struct nfsd4_open *open) { __be32 status; unsigned char old_deny_bmap = stp->st_deny_bmap; if (!test_access(open->op_share_access, stp)) - return nfs4_get_vfs_file(rqstp, fp, cur_fh, stp, open); + return nfs4_get_vfs_file(rqstp, fp, cur_fh, stp, open, false); /* test and set deny mode */ spin_lock(&fp->fi_lock); status = nfs4_file_check_deny(fp, open->op_share_deny); if (status == nfs_ok) { - set_deny(open->op_share_deny, stp); - fp->fi_share_deny |= + 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; + } } spin_unlock(&fp->fi_lock); @@ -5105,11 +5362,42 @@ static int nfsd4_check_conflicting_opens(struct nfs4_client *clp, return 0; } +/* + * It's possible that between opening the dentry and setting the delegation, + * that it has been renamed or unlinked. Redo the lookup to verify that this + * hasn't happened. + */ +static int +nfsd4_verify_deleg_dentry(struct nfsd4_open *open, struct nfs4_file *fp, + struct svc_fh *parent) +{ + struct svc_export *exp; + struct dentry *child; + __be32 err; + + err = nfsd_lookup_dentry(open->op_rqstp, parent, + open->op_fname, open->op_fnamelen, + &exp, &child); + + if (err) + return -EAGAIN; + + exp_put(exp); + dput(child); + if (child != file_dentry(fp->fi_deleg_file->nf_file)) + return -EAGAIN; + + return 0; +} + static struct nfs4_delegation * -nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh, - struct nfs4_file *fp, struct nfs4_clnt_odstate *odstate) +nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, + struct svc_fh *parent) { int status = 0; + 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; @@ -5151,7 +5439,7 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh, return ERR_PTR(status); status = -ENOMEM; - dp = alloc_init_deleg(clp, fp, fh, odstate); + dp = alloc_init_deleg(clp, fp, odstate); if (!dp) goto out_delegees; @@ -5164,6 +5452,13 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh, locks_free_lock(fl); if (status) goto out_clnt_odstate; + + if (parent) { + status = nfsd4_verify_deleg_dentry(open, fp, parent); + if (status) + goto out_unlock; + } + status = nfsd4_check_conflicting_opens(clp, fp); if (status) goto out_unlock; @@ -5219,12 +5514,13 @@ static void nfsd4_open_deleg_none_ext(struct nfsd4_open *open, int status) * proper support for them. */ static void -nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open, - struct nfs4_ol_stateid *stp) +nfs4_open_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, + struct svc_fh *currentfh) { struct nfs4_delegation *dp; struct nfs4_openowner *oo = openowner(stp->st_stateowner); struct nfs4_client *clp = stp->st_stid.sc_client; + struct svc_fh *parent = NULL; int cb_up; int status = 0; @@ -5238,6 +5534,8 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open, goto out_no_deleg; break; case NFS4_OPEN_CLAIM_NULL: + parent = currentfh; + fallthrough; case NFS4_OPEN_CLAIM_FH: /* * Let's not give out any delegations till everyone's @@ -5252,7 +5550,7 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open, default: goto out_no_deleg; } - dp = nfs4_set_delegation(clp, fh, stp->st_stid.sc_file, stp->st_clnt_odstate); + dp = nfs4_set_delegation(open, stp, parent); if (IS_ERR(dp)) goto out_no_deleg; @@ -5294,6 +5592,18 @@ static void nfsd4_deleg_xgrade_none_ext(struct nfsd4_open *open, */ } +/** + * nfsd4_process_open2 - finish open processing + * @rqstp: the RPC transaction being executed + * @current_fh: NFSv4 COMPOUND's current filehandle + * @open: OPEN arguments + * + * If successful, (1) truncate the file if open->op_truncate was + * set, (2) set open->op_stateid, (3) set open->op_delegation. + * + * Returns %nfs_ok on success; otherwise an nfs4stat value in + * network byte order is returned. + */ __be32 nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open) { @@ -5343,7 +5653,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf goto out; } } else { - status = nfs4_get_vfs_file(rqstp, fp, current_fh, stp, open); + 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); @@ -5372,7 +5682,7 @@ 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(current_fh, open, stp); + nfs4_open_delegation(open, stp, &resp->cstate.current_fh); nodeleg: status = nfs_ok; trace_nfsd_open(&stp->st_stid.sc_stateid); @@ -5577,10 +5887,131 @@ static void nfsd4_ssc_expire_umount(struct nfsd_net *nn) } #endif +/* Check if any lock belonging to this lockowner has any blockers */ +static bool +nfs4_lockowner_has_blockers(struct nfs4_lockowner *lo) +{ + struct file_lock_context *ctx; + struct nfs4_ol_stateid *stp; + struct nfs4_file *nf; + + list_for_each_entry(stp, &lo->lo_owner.so_stateids, st_perstateowner) { + nf = stp->st_stid.sc_file; + ctx = nf->fi_inode->i_flctx; + if (!ctx) + continue; + if (locks_owner_has_blockers(ctx, lo)) + return true; + } + return false; +} + +static bool +nfs4_anylock_blockers(struct nfs4_client *clp) +{ + int i; + struct nfs4_stateowner *so; + struct nfs4_lockowner *lo; + + if (atomic_read(&clp->cl_delegs_in_recall)) + return true; + spin_lock(&clp->cl_lock); + for (i = 0; i < OWNER_HASH_SIZE; i++) { + list_for_each_entry(so, &clp->cl_ownerstr_hashtbl[i], + so_strhash) { + if (so->so_is_open_owner) + continue; + lo = lockowner(so); + if (nfs4_lockowner_has_blockers(lo)) { + spin_unlock(&clp->cl_lock); + return true; + } + } + } + spin_unlock(&clp->cl_lock); + return false; +} + +static void +nfs4_get_client_reaplist(struct nfsd_net *nn, struct list_head *reaplist, + struct laundry_time *lt) +{ + unsigned int maxreap, reapcnt = 0; + struct list_head *pos, *next; + struct nfs4_client *clp; + + maxreap = (atomic_read(&nn->nfs4_client_count) >= nn->nfs4_max_clients) ? + NFSD_CLIENT_MAX_TRIM_PER_RUN : 0; + INIT_LIST_HEAD(reaplist); + 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_EXPIRABLE) + goto exp_client; + if (!state_expired(lt, clp->cl_time)) + break; + if (!atomic_read(&clp->cl_rpc_users)) { + if (clp->cl_state == NFSD4_ACTIVE) + atomic_inc(&nn->nfsd_courtesy_clients); + clp->cl_state = NFSD4_COURTESY; + } + if (!client_has_state(clp)) + goto exp_client; + if (!nfs4_anylock_blockers(clp)) + if (reapcnt >= maxreap) + continue; +exp_client: + if (!mark_client_expired_locked(clp)) { + list_add(&clp->cl_lru, reaplist); + reapcnt++; + } + } + spin_unlock(&nn->client_lock); +} + +static void +nfs4_get_courtesy_client_reaplist(struct nfsd_net *nn, + struct list_head *reaplist) +{ + unsigned int maxreap = 0, reapcnt = 0; + struct list_head *pos, *next; + struct nfs4_client *clp; + + maxreap = NFSD_CLIENT_MAX_TRIM_PER_RUN; + INIT_LIST_HEAD(reaplist); + + 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) + break; + if (reapcnt >= maxreap) + break; + if (!mark_client_expired_locked(clp)) { + list_add(&clp->cl_lru, reaplist); + reapcnt++; + } + } + spin_unlock(&nn->client_lock); +} + +static void +nfs4_process_client_reaplist(struct list_head *reaplist) +{ + struct list_head *pos, *next; + struct nfs4_client *clp; + + list_for_each_safe(pos, next, reaplist) { + clp = list_entry(pos, struct nfs4_client, cl_lru); + trace_nfsd_clid_purged(&clp->cl_clientid); + list_del_init(&clp->cl_lru); + expire_client(clp); + } +} + static time64_t nfs4_laundromat(struct nfsd_net *nn) { - struct nfs4_client *clp; struct nfs4_openowner *oo; struct nfs4_delegation *dp; struct nfs4_ol_stateid *stp; @@ -5599,33 +6030,18 @@ nfs4_laundromat(struct nfsd_net *nn) goto out; } nfsd4_end_grace(nn); - INIT_LIST_HEAD(&reaplist); spin_lock(&nn->s2s_cp_lock); idr_for_each_entry(&nn->s2s_cp_stateids, cps_t, i) { cps = container_of(cps_t, struct nfs4_cpntf_state, cp_stateid); - if (cps->cp_stateid.sc_type == NFS4_COPYNOTIFY_STID && + if (cps->cp_stateid.cs_type == NFS4_COPYNOTIFY_STID && state_expired(<, cps->cpntf_time)) _free_cpntf_state_locked(nn, cps); } spin_unlock(&nn->s2s_cp_lock); + nfs4_get_client_reaplist(nn, &reaplist, <); + nfs4_process_client_reaplist(&reaplist); - spin_lock(&nn->client_lock); - list_for_each_safe(pos, next, &nn->client_lru) { - clp = list_entry(pos, struct nfs4_client, cl_lru); - if (!state_expired(<, clp->cl_time)) - break; - if (mark_client_expired_locked(clp)) - continue; - list_add(&clp->cl_lru, &reaplist); - } - spin_unlock(&nn->client_lock); - list_for_each_safe(pos, next, &reaplist) { - clp = list_entry(pos, struct nfs4_client, cl_lru); - trace_nfsd_clid_purged(&clp->cl_clientid); - list_del_init(&clp->cl_lru); - expire_client(clp); - } spin_lock(&state_lock); list_for_each_safe(pos, next, &nn->del_recall_lru) { dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru); @@ -5694,7 +6110,6 @@ out: return max_t(time64_t, lt.new_timeo, NFSD_LAUNDROMAT_MINTIMEOUT); } -static struct workqueue_struct *laundry_wq; static void laundromat_main(struct work_struct *); static void @@ -5709,6 +6124,18 @@ laundromat_main(struct work_struct *laundry) queue_delayed_work(laundry_wq, &nn->laundromat_work, t*HZ); } +static void +courtesy_client_reaper(struct work_struct *reaper) +{ + struct list_head reaplist; + struct delayed_work *dwork = to_delayed_work(reaper); + struct nfsd_net *nn = container_of(dwork, struct nfsd_net, + nfsd_shrinker_work); + + nfs4_get_courtesy_client_reaplist(nn, &reaplist); + nfs4_process_client_reaplist(&reaplist); +} + static inline __be32 nfs4_check_fh(struct svc_fh *fhp, struct nfs4_stid *stp) { if (!fh_match(&fhp->fh_handle, &stp->sc_file->fi_fhandle)) @@ -5844,6 +6271,7 @@ nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate, struct nfs4_stid **s, struct nfsd_net *nn) { __be32 status; + struct nfs4_stid *stid; bool return_revoked = false; /* @@ -5866,15 +6294,16 @@ nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate, } if (status) return status; - *s = find_stateid_by_type(cstate->clp, stateid, typemask); - if (!*s) + stid = find_stateid_by_type(cstate->clp, stateid, typemask); + if (!stid) return nfserr_bad_stateid; - if (((*s)->sc_type == NFS4_REVOKED_DELEG_STID) && !return_revoked) { - nfs4_put_stid(*s); + if ((stid->sc_type == NFS4_REVOKED_DELEG_STID) && !return_revoked) { + nfs4_put_stid(stid); if (cstate->minorversion) return nfserr_deleg_revoked; return nfserr_bad_stateid; } + *s = stid; return nfs_ok; } @@ -5939,12 +6368,12 @@ out: static void _free_cpntf_state_locked(struct nfsd_net *nn, struct nfs4_cpntf_state *cps) { - WARN_ON_ONCE(cps->cp_stateid.sc_type != NFS4_COPYNOTIFY_STID); - if (!refcount_dec_and_test(&cps->cp_stateid.sc_count)) + WARN_ON_ONCE(cps->cp_stateid.cs_type != NFS4_COPYNOTIFY_STID); + if (!refcount_dec_and_test(&cps->cp_stateid.cs_count)) return; list_del(&cps->cp_list); idr_remove(&nn->s2s_cp_stateids, - cps->cp_stateid.stid.si_opaque.so_id); + cps->cp_stateid.cs_stid.si_opaque.so_id); kfree(cps); } /* @@ -5966,12 +6395,12 @@ __be32 manage_cpntf_state(struct nfsd_net *nn, stateid_t *st, if (cps_t) { state = container_of(cps_t, struct nfs4_cpntf_state, cp_stateid); - if (state->cp_stateid.sc_type != NFS4_COPYNOTIFY_STID) { + if (state->cp_stateid.cs_type != NFS4_COPYNOTIFY_STID) { state = NULL; goto unlock; } if (!clp) - refcount_inc(&state->cp_stateid.sc_count); + refcount_inc(&state->cp_stateid.cs_count); else _free_cpntf_state_locked(nn, state); } @@ -6040,7 +6469,11 @@ nfs4_preprocess_stateid_op(struct svc_rqst *rqstp, *nfp = NULL; if (ZERO_STATEID(stateid) || ONE_STATEID(stateid)) { - status = check_special_stateids(net, fhp, stateid, flags); + if (cstid) + status = nfserr_bad_stateid; + else + status = check_special_stateids(net, fhp, stateid, + flags); goto done; } @@ -6375,6 +6808,7 @@ static void nfsd4_close_open_stateid(struct nfs4_ol_stateid *s) struct nfs4_client *clp = s->st_stid.sc_client; bool unhashed; LIST_HEAD(reaplist); + struct nfs4_ol_stateid *stp; spin_lock(&clp->cl_lock); unhashed = unhash_open_stateid(s, &reaplist); @@ -6383,6 +6817,8 @@ static void nfsd4_close_open_stateid(struct nfs4_ol_stateid *s) if (unhashed) put_ol_stateid_locked(s, &reaplist); spin_unlock(&clp->cl_lock); + list_for_each_entry(stp, &reaplist, st_locks) + nfs4_free_cpntf_statelist(clp->net, &stp->st_stid); free_ol_stateid_reaplist(&reaplist); } else { spin_unlock(&clp->cl_lock); @@ -6466,6 +6902,7 @@ nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (status) goto put_stateid; + wake_up_var(d_inode(cstate->current_fh.fh_dentry)); destroy_delegation(dp); put_stateid: nfs4_put_stid(&dp->dl_stid); @@ -6502,7 +6939,7 @@ nfs4_transform_lock_offset(struct file_lock *lock) } static fl_owner_t -nfsd4_fl_get_owner(fl_owner_t owner) +nfsd4_lm_get_owner(fl_owner_t owner) { struct nfs4_lockowner *lo = (struct nfs4_lockowner *)owner; @@ -6511,7 +6948,7 @@ nfsd4_fl_get_owner(fl_owner_t owner) } static void -nfsd4_fl_put_owner(fl_owner_t owner) +nfsd4_lm_put_owner(fl_owner_t owner) { struct nfs4_lockowner *lo = (struct nfs4_lockowner *)owner; @@ -6519,6 +6956,29 @@ nfsd4_fl_put_owner(fl_owner_t owner) nfs4_put_stateowner(&lo->lo_owner); } +/* return pointer to struct nfs4_client if client is expirable */ +static bool +nfsd4_lm_lock_expirable(struct file_lock *cfl) +{ + struct nfs4_lockowner *lo = (struct nfs4_lockowner *)cfl->fl_owner; + struct nfs4_client *clp = lo->lo_owner.so_client; + struct nfsd_net *nn; + + if (try_to_expire_client(clp)) { + nn = net_generic(clp->net, nfsd_net_id); + mod_delayed_work(laundry_wq, &nn->laundromat_work, 0); + return true; + } + return false; +} + +/* schedule laundromat to run immediately and wait for it to complete */ +static void +nfsd4_lm_expire_lock(void) +{ + flush_workqueue(laundry_wq); +} + static void nfsd4_lm_notify(struct file_lock *fl) { @@ -6545,9 +7005,12 @@ nfsd4_lm_notify(struct file_lock *fl) } static const struct lock_manager_operations nfsd_posix_mng_ops = { + .lm_mod_owner = THIS_MODULE, .lm_notify = nfsd4_lm_notify, - .lm_get_owner = nfsd4_fl_get_owner, - .lm_put_owner = nfsd4_fl_put_owner, + .lm_get_owner = nfsd4_lm_get_owner, + .lm_put_owner = nfsd4_lm_put_owner, + .lm_lock_expirable = nfsd4_lm_lock_expirable, + .lm_expire_lock = nfsd4_lm_expire_lock, }; static inline void @@ -6836,7 +7299,6 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_blocked_lock *nbl = NULL; struct file_lock *file_lock = NULL; struct file_lock *conflock = NULL; - struct super_block *sb; __be32 status = 0; int lkflg; int err; @@ -6858,7 +7320,6 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, dprintk("NFSD: nfsd4_lock: permission denied!\n"); return status; } - sb = cstate->current_fh.fh_dentry->d_sb; if (lock->lk_is_new) { if (nfsd4_has_session(cstate)) @@ -6910,8 +7371,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, fp = lock_stp->st_stid.sc_file; switch (lock->lk_type) { case NFS4_READW_LT: - if (nfsd4_has_session(cstate) && - !(sb->s_export_op->flags & EXPORT_OP_SYNC_LOCKS)) + if (nfsd4_has_session(cstate)) fl_flags |= FL_SLEEP; fallthrough; case NFS4_READ_LT: @@ -6923,8 +7383,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, fl_type = F_RDLCK; break; case NFS4_WRITEW_LT: - if (nfsd4_has_session(cstate) && - !(sb->s_export_op->flags & EXPORT_OP_SYNC_LOCKS)) + if (nfsd4_has_session(cstate)) fl_flags |= FL_SLEEP; fallthrough; case NFS4_WRITE_LT: @@ -6945,6 +7404,16 @@ 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; + nbl = find_or_allocate_block(lock_sop, &fp->fi_fhandle, nn); if (!nbl) { dprintk("NFSD: %s: unable to allocate block!\n", __func__); @@ -6975,6 +7444,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, spin_lock(&nn->blocked_locks_lock); list_add_tail(&nbl->nbl_list, &lock_sop->lo_blocked); list_add_tail(&nbl->nbl_lru, &nn->blocked_locks_lru); + kref_get(&nbl->nbl_kref); spin_unlock(&nn->blocked_locks_lock); } @@ -6987,6 +7457,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, nn->somebody_reclaimed = true; break; case FILE_LOCK_DEFERRED: + kref_put(&nbl->nbl_kref, free_nbl); nbl = NULL; fallthrough; case -EAGAIN: /* conflock holds conflicting lock */ @@ -7007,8 +7478,13 @@ out: /* dequeue it if we queued it before */ if (fl_flags & FL_SLEEP) { spin_lock(&nn->blocked_locks_lock); - list_del_init(&nbl->nbl_list); - list_del_init(&nbl->nbl_lru); + if (!list_empty(&nbl->nbl_list) && + !list_empty(&nbl->nbl_lru)) { + list_del_init(&nbl->nbl_list); + list_del_init(&nbl->nbl_lru); + kref_put(&nbl->nbl_kref, free_nbl); + } + /* nbl can use one of lists to be linked to reaplist */ spin_unlock(&nn->blocked_locks_lock); } free_blocked_lock(nbl); @@ -7049,21 +7525,22 @@ out: static __be32 nfsd_test_lock(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file_lock *lock) { struct nfsd_file *nf; + struct inode *inode; __be32 err; err = nfsd_file_acquire(rqstp, fhp, NFSD_MAY_READ, &nf); if (err) return err; - fh_lock(fhp); /* to block new leases till after test_lock: */ - err = nfserrno(nfsd_open_break_lease(fhp->fh_dentry->d_inode, - NFSD_MAY_READ)); + inode = fhp->fh_dentry->d_inode; + inode_lock(inode); /* to block new leases till after test_lock: */ + err = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ)); if (err) goto out; lock->fl_file = nf->nf_file; err = nfserrno(vfs_test_lock(nf->nf_file, lock)); lock->fl_file = NULL; out: - fh_unlock(fhp); + inode_unlock(inode); nfsd_file_put(nf); return err; } @@ -7252,22 +7729,36 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) return status; } +/** + * nfsd4_release_lockowner - process NFSv4.0 RELEASE_LOCKOWNER operations + * @rqstp: RPC transaction + * @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. + * + * Return values: + * %nfs_ok: lockowner released or not found + * %nfserr_locks_held: lockowner still in use + * %nfserr_stale_clientid: clientid no longer active + * %nfserr_expired: clientid not recognized + */ __be32 nfsd4_release_lockowner(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_release_lockowner *rlockowner = &u->release_lockowner; + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); clientid_t *clid = &rlockowner->rl_clientid; - struct nfs4_stateowner *sop; - struct nfs4_lockowner *lo = NULL; struct nfs4_ol_stateid *stp; - struct xdr_netobj *owner = &rlockowner->rl_owner; - unsigned int hashval = ownerstr_hashval(owner); - __be32 status; - struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); + struct nfs4_lockowner *lo; struct nfs4_client *clp; - LIST_HEAD (reaplist); + LIST_HEAD(reaplist); + __be32 status; dprintk("nfsd4_release_lockowner clientid: (%08x/%08x):\n", clid->cl_boot, clid->cl_id); @@ -7275,34 +7766,19 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp, status = set_client(clid, cstate, nn); if (status) return status; - clp = cstate->clp; - /* Find the matching lock stateowner */ - spin_lock(&clp->cl_lock); - list_for_each_entry(sop, &clp->cl_ownerstr_hashtbl[hashval], - so_strhash) { - if (sop->so_is_open_owner || !same_owner_str(sop, owner)) - continue; - - /* see if there are still any locks associated with it */ - lo = lockowner(sop); - list_for_each_entry(stp, &sop->so_stateids, st_perstateowner) { - if (check_for_locks(stp->st_stid.sc_file, lo)) { - status = nfserr_locks_held; - spin_unlock(&clp->cl_lock); - return status; - } - } - - nfs4_get_stateowner(sop); - break; - } + spin_lock(&clp->cl_lock); + lo = find_lockowner_str_locked(clp, &rlockowner->rl_owner); if (!lo) { spin_unlock(&clp->cl_lock); - return status; + 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; } - unhash_lockowner_locked(lo); while (!list_empty(&lo->lo_owner.so_stateids)) { stp = list_first_entry(&lo->lo_owner.so_stateids, @@ -7312,11 +7788,11 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp, put_ol_stateid_locked(stp, &reaplist); } spin_unlock(&clp->cl_lock); + free_ol_stateid_reaplist(&reaplist); remove_blocked_locks(lo); nfs4_put_stateowner(&lo->lo_owner); - - return status; + return nfs_ok; } static inline struct nfs4_client_reclaim * @@ -7482,6 +7958,7 @@ static int nfs4_state_create_net(struct net *net) INIT_LIST_HEAD(&nn->blocked_locks_lru); INIT_DELAYED_WORK(&nn->laundromat_work, laundromat_main); + INIT_DELAYED_WORK(&nn->nfsd_shrinker_work, courtesy_client_reaper); get_net(net); return 0; @@ -7557,22 +8034,12 @@ nfs4_state_start(void) { int ret; - laundry_wq = alloc_workqueue("%s", WQ_UNBOUND, 0, "nfsd4"); - if (laundry_wq == NULL) { - ret = -ENOMEM; - goto out; - } ret = nfsd4_create_callback_queue(); if (ret) - goto out_free_laundry; + return ret; set_max_delegations(); return 0; - -out_free_laundry: - destroy_workqueue(laundry_wq); -out: - return ret; } void @@ -7609,7 +8076,6 @@ nfs4_state_shutdown_net(struct net *net) void nfs4_state_shutdown(void) { - destroy_workqueue(laundry_wq); nfsd4_destroy_callback_queue(); } diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 5a93a5db4fb0..bcfeb1a922c0 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -42,6 +42,8 @@ #include <linux/sunrpc/svcauth_gss.h> #include <linux/sunrpc/addr.h> #include <linux/xattr.h> +#include <linux/vmalloc.h> + #include <uapi/linux/xattr.h> #include "idmap.h" @@ -277,21 +279,10 @@ nfsd4_decode_verifier4(struct nfsd4_compoundargs *argp, nfs4_verifier *verf) static __be32 nfsd4_decode_bitmap4(struct nfsd4_compoundargs *argp, u32 *bmval, u32 bmlen) { - u32 i, count; - __be32 *p; + ssize_t status; - if (xdr_stream_decode_u32(argp->xdr, &count) < 0) - return nfserr_bad_xdr; - /* request sanity */ - if (count > 1000) - return nfserr_bad_xdr; - p = xdr_inline_decode(argp->xdr, count << 2); - if (!p) - return nfserr_bad_xdr; - for (i = 0; i < bmlen; i++) - bmval[i] = (i < count) ? be32_to_cpup(p++) : 0; - - return nfs_ok; + status = xdr_stream_decode_uint32_array(argp->xdr, bmval, bmlen); + return status == -EBADMSG ? nfserr_bad_xdr : nfs_ok; } static __be32 @@ -481,6 +472,15 @@ nfsd4_decode_fattr4(struct nfsd4_compoundargs *argp, u32 *bmval, u32 bmlen, return nfserr_bad_xdr; } } + if (bmval[1] & FATTR4_WORD1_TIME_CREATE) { + struct timespec64 ts; + + /* No Linux filesystem supports setting this attribute. */ + bmval[1] &= ~FATTR4_WORD1_TIME_CREATE; + status = nfsd4_decode_nfstime4(argp, &ts); + if (status) + return status; + } if (bmval[1] & FATTR4_WORD1_TIME_MODIFY_SET) { u32 set_it; @@ -793,6 +793,7 @@ nfsd4_decode_commit(struct nfsd4_compoundargs *argp, struct nfsd4_commit *commit return nfserr_bad_xdr; if (xdr_stream_decode_u32(argp->xdr, &commit->co_count) < 0) return nfserr_bad_xdr; + memset(&commit->co_verf, 0, sizeof(commit->co_verf)); return nfs_ok; } @@ -801,6 +802,7 @@ nfsd4_decode_create(struct nfsd4_compoundargs *argp, struct nfsd4_create *create { __be32 *p, status; + memset(create, 0, sizeof(*create)); if (xdr_stream_decode_u32(argp->xdr, &create->cr_type) < 0) return nfserr_bad_xdr; switch (create->cr_type) { @@ -850,6 +852,7 @@ nfsd4_decode_delegreturn(struct nfsd4_compoundargs *argp, struct nfsd4_delegretu static inline __be32 nfsd4_decode_getattr(struct nfsd4_compoundargs *argp, struct nfsd4_getattr *getattr) { + memset(getattr, 0, sizeof(*getattr)); return nfsd4_decode_bitmap4(argp, getattr->ga_bmval, ARRAY_SIZE(getattr->ga_bmval)); } @@ -857,6 +860,7 @@ nfsd4_decode_getattr(struct nfsd4_compoundargs *argp, struct nfsd4_getattr *geta static __be32 nfsd4_decode_link(struct nfsd4_compoundargs *argp, struct nfsd4_link *link) { + memset(link, 0, sizeof(*link)); return nfsd4_decode_component4(argp, &link->li_name, &link->li_namelen); } @@ -905,6 +909,7 @@ nfsd4_decode_locker4(struct nfsd4_compoundargs *argp, struct nfsd4_lock *lock) static __be32 nfsd4_decode_lock(struct nfsd4_compoundargs *argp, struct nfsd4_lock *lock) { + memset(lock, 0, sizeof(*lock)); if (xdr_stream_decode_u32(argp->xdr, &lock->lk_type) < 0) return nfserr_bad_xdr; if ((lock->lk_type < NFS4_READ_LT) || (lock->lk_type > NFS4_WRITEW_LT)) @@ -921,6 +926,7 @@ nfsd4_decode_lock(struct nfsd4_compoundargs *argp, struct nfsd4_lock *lock) static __be32 nfsd4_decode_lockt(struct nfsd4_compoundargs *argp, struct nfsd4_lockt *lockt) { + memset(lockt, 0, sizeof(*lockt)); if (xdr_stream_decode_u32(argp->xdr, &lockt->lt_type) < 0) return nfserr_bad_xdr; if ((lockt->lt_type < NFS4_READ_LT) || (lockt->lt_type > NFS4_WRITEW_LT)) @@ -1142,11 +1148,8 @@ nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open) __be32 status; u32 dummy; - memset(open->op_bmval, 0, sizeof(open->op_bmval)); - open->op_iattr.ia_valid = 0; - open->op_openowner = NULL; + memset(open, 0, sizeof(*open)); - open->op_xdr_error = 0; if (xdr_stream_decode_u32(argp->xdr, &open->op_seqid) < 0) return nfserr_bad_xdr; /* deleg_want is ignored */ @@ -1181,6 +1184,8 @@ nfsd4_decode_open_confirm(struct nfsd4_compoundargs *argp, struct nfsd4_open_con if (xdr_stream_decode_u32(argp->xdr, &open_conf->oc_seqid) < 0) return nfserr_bad_xdr; + memset(&open_conf->oc_resp_stateid, 0, + sizeof(open_conf->oc_resp_stateid)); return nfs_ok; } @@ -1189,6 +1194,7 @@ nfsd4_decode_open_downgrade(struct nfsd4_compoundargs *argp, struct nfsd4_open_d { __be32 status; + memset(open_down, 0, sizeof(*open_down)); status = nfsd4_decode_stateid4(argp, &open_down->od_stateid); if (status) return status; @@ -1218,6 +1224,7 @@ nfsd4_decode_putfh(struct nfsd4_compoundargs *argp, struct nfsd4_putfh *putfh) if (!putfh->pf_fhval) return nfserr_jukebox; + putfh->no_verify = false; return nfs_ok; } @@ -1234,6 +1241,7 @@ nfsd4_decode_read(struct nfsd4_compoundargs *argp, struct nfsd4_read *read) { __be32 status; + memset(read, 0, sizeof(*read)); status = nfsd4_decode_stateid4(argp, &read->rd_stateid); if (status) return status; @@ -1250,6 +1258,7 @@ nfsd4_decode_readdir(struct nfsd4_compoundargs *argp, struct nfsd4_readdir *read { __be32 status; + memset(readdir, 0, sizeof(*readdir)); if (xdr_stream_decode_u64(argp->xdr, &readdir->rd_cookie) < 0) return nfserr_bad_xdr; status = nfsd4_decode_verifier4(argp, &readdir->rd_verf); @@ -1269,6 +1278,7 @@ nfsd4_decode_readdir(struct nfsd4_compoundargs *argp, struct nfsd4_readdir *read static __be32 nfsd4_decode_remove(struct nfsd4_compoundargs *argp, struct nfsd4_remove *remove) { + memset(&remove->rm_cinfo, 0, sizeof(remove->rm_cinfo)); return nfsd4_decode_component4(argp, &remove->rm_name, &remove->rm_namelen); } @@ -1277,6 +1287,7 @@ nfsd4_decode_rename(struct nfsd4_compoundargs *argp, struct nfsd4_rename *rename { __be32 status; + memset(rename, 0, sizeof(*rename)); status = nfsd4_decode_component4(argp, &rename->rn_sname, &rename->rn_snamelen); if (status) return status; @@ -1293,6 +1304,7 @@ static __be32 nfsd4_decode_secinfo(struct nfsd4_compoundargs *argp, struct nfsd4_secinfo *secinfo) { + secinfo->si_exp = NULL; return nfsd4_decode_component4(argp, &secinfo->si_name, &secinfo->si_namelen); } @@ -1301,6 +1313,7 @@ nfsd4_decode_setattr(struct nfsd4_compoundargs *argp, struct nfsd4_setattr *seta { __be32 status; + memset(setattr, 0, sizeof(*setattr)); status = nfsd4_decode_stateid4(argp, &setattr->sa_stateid); if (status) return status; @@ -1315,6 +1328,8 @@ nfsd4_decode_setclientid(struct nfsd4_compoundargs *argp, struct nfsd4_setclient { __be32 *p, status; + memset(setclientid, 0, sizeof(*setclientid)); + if (argp->minorversion >= 1) return nfserr_notsupp; @@ -1371,6 +1386,8 @@ nfsd4_decode_verify(struct nfsd4_compoundargs *argp, struct nfsd4_verify *verify { __be32 *p, status; + memset(verify, 0, sizeof(*verify)); + status = nfsd4_decode_bitmap4(argp, verify->ve_bmval, ARRAY_SIZE(verify->ve_bmval)); if (status) @@ -1410,6 +1427,9 @@ nfsd4_decode_write(struct nfsd4_compoundargs *argp, struct nfsd4_write *write) if (!xdr_stream_subsegment(argp->xdr, &write->wr_payload, write->wr_buflen)) return nfserr_bad_xdr; + write->wr_bytes_written = 0; + write->wr_how_written = 0; + memset(&write->wr_verifier, 0, sizeof(write->wr_verifier)); return nfs_ok; } @@ -1434,6 +1454,7 @@ nfsd4_decode_release_lockowner(struct nfsd4_compoundargs *argp, struct nfsd4_rel static __be32 nfsd4_decode_backchannel_ctl(struct nfsd4_compoundargs *argp, struct nfsd4_backchannel_ctl *bc) { + memset(bc, 0, sizeof(*bc)); if (xdr_stream_decode_u32(argp->xdr, &bc->bc_cb_program) < 0) return nfserr_bad_xdr; return nfsd4_decode_cb_sec(argp, &bc->bc_cb_sec); @@ -1444,6 +1465,7 @@ static __be32 nfsd4_decode_bind_conn_to_session(struct nfsd4_compoundargs *argp, u32 use_conn_in_rdma_mode; __be32 status; + memset(bcts, 0, sizeof(*bcts)); status = nfsd4_decode_sessionid4(argp, &bcts->sessionid); if (status) return status; @@ -1585,6 +1607,7 @@ nfsd4_decode_exchange_id(struct nfsd4_compoundargs *argp, { __be32 status; + memset(exid, 0, sizeof(*exid)); status = nfsd4_decode_verifier4(argp, &exid->verifier); if (status) return status; @@ -1637,6 +1660,7 @@ nfsd4_decode_create_session(struct nfsd4_compoundargs *argp, { __be32 status; + memset(sess, 0, sizeof(*sess)); status = nfsd4_decode_clientid4(argp, &sess->clientid); if (status) return status; @@ -1652,11 +1676,7 @@ nfsd4_decode_create_session(struct nfsd4_compoundargs *argp, return status; if (xdr_stream_decode_u32(argp->xdr, &sess->callback_prog) < 0) return nfserr_bad_xdr; - status = nfsd4_decode_cb_sec(argp, &sess->cb_sec); - if (status) - return status; - - return nfs_ok; + return nfsd4_decode_cb_sec(argp, &sess->cb_sec); } static __be32 @@ -1680,6 +1700,7 @@ nfsd4_decode_getdeviceinfo(struct nfsd4_compoundargs *argp, { __be32 status; + memset(gdev, 0, sizeof(*gdev)); status = nfsd4_decode_deviceid4(argp, &gdev->gd_devid); if (status) return status; @@ -1700,6 +1721,7 @@ nfsd4_decode_layoutcommit(struct nfsd4_compoundargs *argp, { __be32 *p, status; + memset(lcp, 0, sizeof(*lcp)); if (xdr_stream_decode_u64(argp->xdr, &lcp->lc_seg.offset) < 0) return nfserr_bad_xdr; if (xdr_stream_decode_u64(argp->xdr, &lcp->lc_seg.length) < 0) @@ -1735,6 +1757,7 @@ nfsd4_decode_layoutget(struct nfsd4_compoundargs *argp, { __be32 status; + memset(lgp, 0, sizeof(*lgp)); if (xdr_stream_decode_u32(argp->xdr, &lgp->lg_signal) < 0) return nfserr_bad_xdr; if (xdr_stream_decode_u32(argp->xdr, &lgp->lg_layout_type) < 0) @@ -1760,6 +1783,7 @@ static __be32 nfsd4_decode_layoutreturn(struct nfsd4_compoundargs *argp, struct nfsd4_layoutreturn *lrp) { + memset(lrp, 0, sizeof(*lrp)); if (xdr_stream_decode_bool(argp->xdr, &lrp->lr_reclaim) < 0) return nfserr_bad_xdr; if (xdr_stream_decode_u32(argp->xdr, &lrp->lr_layout_type) < 0) @@ -1775,6 +1799,8 @@ static __be32 nfsd4_decode_secinfo_no_name(struct nfsd4_compoundargs *argp, { if (xdr_stream_decode_u32(argp->xdr, &sin->sin_style) < 0) return nfserr_bad_xdr; + + sin->sin_exp = NULL; return nfs_ok; } @@ -1795,6 +1821,7 @@ nfsd4_decode_sequence(struct nfsd4_compoundargs *argp, seq->maxslots = be32_to_cpup(p++); seq->cachethis = be32_to_cpup(p); + seq->status_flags = 0; return nfs_ok; } @@ -1805,6 +1832,7 @@ nfsd4_decode_test_stateid(struct nfsd4_compoundargs *argp, struct nfsd4_test_sta __be32 status; u32 i; + memset(test_stateid, 0, sizeof(*test_stateid)); if (xdr_stream_decode_u32(argp->xdr, &test_stateid->ts_num_ids) < 0) return nfserr_bad_xdr; @@ -1812,7 +1840,7 @@ nfsd4_decode_test_stateid(struct nfsd4_compoundargs *argp, struct nfsd4_test_sta for (i = 0; i < test_stateid->ts_num_ids; i++) { stateid = svcxdr_tmpalloc(argp, sizeof(*stateid)); if (!stateid) - return nfserrno(-ENOMEM); /* XXX: not jukebox? */ + return nfserr_jukebox; INIT_LIST_HEAD(&stateid->ts_id_list); list_add_tail(&stateid->ts_id_list, &test_stateid->ts_stateid_list); status = nfsd4_decode_stateid4(argp, &stateid->ts_id_stateid); @@ -1898,10 +1926,11 @@ static __be32 nfsd4_decode_nl4_server(struct nfsd4_compoundargs *argp, static __be32 nfsd4_decode_copy(struct nfsd4_compoundargs *argp, struct nfsd4_copy *copy) { + u32 consecutive, i, count, sync; struct nl4_server *ns_dummy; - u32 consecutive, i, count; __be32 status; + memset(copy, 0, sizeof(*copy)); status = nfsd4_decode_stateid4(argp, ©->cp_src_stateid); if (status) return status; @@ -1917,25 +1946,28 @@ nfsd4_decode_copy(struct nfsd4_compoundargs *argp, struct nfsd4_copy *copy) /* ca_consecutive: we always do consecutive copies */ if (xdr_stream_decode_u32(argp->xdr, &consecutive) < 0) return nfserr_bad_xdr; - if (xdr_stream_decode_u32(argp->xdr, ©->cp_synchronous) < 0) + if (xdr_stream_decode_bool(argp->xdr, &sync) < 0) return nfserr_bad_xdr; + nfsd4_copy_set_sync(copy, sync); if (xdr_stream_decode_u32(argp->xdr, &count) < 0) return nfserr_bad_xdr; - copy->cp_intra = false; + copy->cp_src = svcxdr_tmpalloc(argp, sizeof(*copy->cp_src)); + if (copy->cp_src == NULL) + return nfserr_jukebox; if (count == 0) { /* intra-server copy */ - copy->cp_intra = true; + __set_bit(NFSD4_COPY_F_INTRA, ©->cp_flags); return nfs_ok; } /* decode all the supplied server addresses but use only the first */ - status = nfsd4_decode_nl4_server(argp, ©->cp_src); + status = nfsd4_decode_nl4_server(argp, copy->cp_src); if (status) return status; ns_dummy = kmalloc(sizeof(struct nl4_server), GFP_KERNEL); if (ns_dummy == NULL) - return nfserrno(-ENOMEM); /* XXX: jukebox? */ + return nfserr_jukebox; for (i = 0; i < count - 1; i++) { status = nfsd4_decode_nl4_server(argp, ns_dummy); if (status) { @@ -1954,16 +1986,26 @@ nfsd4_decode_copy_notify(struct nfsd4_compoundargs *argp, { __be32 status; + memset(cn, 0, sizeof(*cn)); + cn->cpn_src = svcxdr_tmpalloc(argp, sizeof(*cn->cpn_src)); + if (cn->cpn_src == NULL) + return nfserr_jukebox; + cn->cpn_dst = svcxdr_tmpalloc(argp, sizeof(*cn->cpn_dst)); + if (cn->cpn_dst == NULL) + return nfserr_jukebox; + status = nfsd4_decode_stateid4(argp, &cn->cpn_src_stateid); if (status) return status; - return nfsd4_decode_nl4_server(argp, &cn->cpn_dst); + return nfsd4_decode_nl4_server(argp, cn->cpn_dst); } static __be32 nfsd4_decode_offload_status(struct nfsd4_compoundargs *argp, struct nfsd4_offload_status *os) { + os->count = 0; + os->status = 0; return nfsd4_decode_stateid4(argp, &os->stateid); } @@ -1980,6 +2022,8 @@ nfsd4_decode_seek(struct nfsd4_compoundargs *argp, struct nfsd4_seek *seek) if (xdr_stream_decode_u32(argp->xdr, &seek->seek_whence) < 0) return nfserr_bad_xdr; + seek->seek_eof = 0; + seek->seek_pos = 0; return nfs_ok; } @@ -2115,6 +2159,7 @@ nfsd4_decode_getxattr(struct nfsd4_compoundargs *argp, __be32 status; u32 maxcount; + memset(getxattr, 0, sizeof(*getxattr)); status = nfsd4_decode_xattr_name(argp, &getxattr->getxa_name); if (status) return status; @@ -2123,8 +2168,7 @@ nfsd4_decode_getxattr(struct nfsd4_compoundargs *argp, maxcount = min_t(u32, XATTR_SIZE_MAX, maxcount); getxattr->getxa_len = maxcount; - - return status; + return nfs_ok; } static __be32 @@ -2134,6 +2178,8 @@ nfsd4_decode_setxattr(struct nfsd4_compoundargs *argp, u32 flags, maxcount, size; __be32 status; + memset(setxattr, 0, sizeof(*setxattr)); + if (xdr_stream_decode_u32(argp->xdr, &flags) < 0) return nfserr_bad_xdr; @@ -2172,6 +2218,8 @@ nfsd4_decode_listxattrs(struct nfsd4_compoundargs *argp, { u32 maxcount; + memset(listxattrs, 0, sizeof(*listxattrs)); + if (xdr_stream_decode_u64(argp->xdr, &listxattrs->lsxa_cookie) < 0) return nfserr_bad_xdr; @@ -2199,6 +2247,7 @@ static __be32 nfsd4_decode_removexattr(struct nfsd4_compoundargs *argp, struct nfsd4_removexattr *removexattr) { + memset(removexattr, 0, sizeof(*removexattr)); return nfsd4_decode_xattr_name(argp, &removexattr->rmxa_name); } @@ -2349,22 +2398,15 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) if (xdr_stream_decode_u32(argp->xdr, &argp->minorversion) < 0) return false; - if (xdr_stream_decode_u32(argp->xdr, &argp->opcnt) < 0) + if (xdr_stream_decode_u32(argp->xdr, &argp->client_opcnt) < 0) return false; - - /* - * NFS4ERR_RESOURCE is a more helpful error than GARBAGE_ARGS - * here, so we return success at the xdr level so that - * nfsd4_proc can handle this is an NFS-level error. - */ - if (argp->opcnt > NFSD_MAX_OPS_PER_COMPOUND) - return true; + argp->opcnt = min_t(u32, argp->client_opcnt, + NFSD_MAX_OPS_PER_COMPOUND); if (argp->opcnt > ARRAY_SIZE(argp->iops)) { - argp->ops = kzalloc(argp->opcnt * sizeof(*argp->ops), GFP_KERNEL); + argp->ops = vcalloc(argp->opcnt, sizeof(*argp->ops)); if (!argp->ops) { argp->ops = argp->iops; - dprintk("nfsd: couldn't allocate room for COMPOUND\n"); return false; } } @@ -2422,7 +2464,7 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) argp->rqstp->rq_cachetype = cachethis ? RC_REPLBUFF : RC_NOCACHE; if (readcount > 1 || max_reply > PAGE_SIZE - auth_slack) - clear_bit(RQ_SPLICE_OK, &argp->rqstp->rq_flags); + __clear_bit(RQ_SPLICE_OK, &argp->rqstp->rq_flags); return true; } @@ -2766,9 +2808,10 @@ static __be32 fattr_handle_absent_fs(u32 *bmval0, u32 *bmval1, u32 *bmval2, u32 } -static int get_parent_attributes(struct svc_export *exp, struct kstat *stat) +static int nfsd4_get_mounted_on_ino(struct svc_export *exp, u64 *pino) { struct path path = exp->ex_path; + struct kstat stat; int err; path_get(&path); @@ -2776,8 +2819,10 @@ static int get_parent_attributes(struct svc_export *exp, struct kstat *stat) if (path.dentry != path.mnt->mnt_root) break; } - err = vfs_getattr(&path, stat, STATX_BASIC_STATS, AT_STATX_SYNC_AS_STAT); + err = vfs_getattr(&path, &stat, STATX_INO, AT_STATX_SYNC_AS_STAT); path_put(&path); + if (!err) + *pino = stat.ino; return err; } @@ -2830,10 +2875,9 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp, struct kstat stat; struct svc_fh *tempfh = NULL; struct kstatfs statfs; - __be32 *p; + __be32 *p, *attrlen_p; int starting_len = xdr->buf->len; int attrlen_offset; - __be32 attrlen; u32 dummy; u64 dummy64; u32 rdattr_err = 0; @@ -2865,6 +2909,9 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp, err = vfs_getattr(&path, &stat, STATX_BASIC_STATS, AT_STATX_SYNC_AS_STAT); if (err) goto out_nfserr; + if (!(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 | FATTR4_WORD0_FILES_TOTAL | FATTR4_WORD0_MAXNAME)) || (bmval1 & (FATTR4_WORD1_SPACE_AVAIL | FATTR4_WORD1_SPACE_FREE | @@ -2918,10 +2965,9 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp, goto out; attrlen_offset = xdr->buf->len; - p = xdr_reserve_space(xdr, 4); - if (!p) + attrlen_p = xdr_reserve_space(xdr, XDR_UNIT); + if (!attrlen_p) goto out_resource; - p++; /* to be backfilled later */ if (bmval0 & FATTR4_WORD0_SUPPORTED_ATTRS) { u32 supp[3]; @@ -3265,23 +3311,29 @@ out_acl: 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) { - struct kstat parent_stat; u64 ino = stat.ino; p = xdr_reserve_space(xdr, 8); if (!p) goto out_resource; /* - * Get parent's attributes if not ignoring crossmount - * and this is the root of a cross-mounted filesystem. + * 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 = get_parent_attributes(exp, &parent_stat); + err = nfsd4_get_mounted_on_ino(exp, &ino); if (err) goto out_nfserr; - ino = parent_stat.ino; } p = xdr_encode_hyper(p, ino); } @@ -3336,8 +3388,7 @@ out_acl: *p++ = cpu_to_be32(err == 0); } - attrlen = htonl(xdr->buf->len - attrlen_offset - 4); - write_bytes_to_xdr_buf(xdr->buf, attrlen_offset, &attrlen, 4); + *attrlen_p = cpu_to_be32(xdr->buf->len - attrlen_offset - XDR_UNIT); status = nfs_ok; out: @@ -3506,7 +3557,7 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen, p = xdr_reserve_space(xdr, 3*4 + namlen); if (!p) goto fail; - p = xdr_encode_hyper(p, NFS_OFFSET_MAX); /* offset of next entry */ + 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); @@ -3874,16 +3925,15 @@ static __be32 nfsd4_encode_splice_read( struct xdr_stream *xdr = resp->xdr; struct xdr_buf *buf = xdr->buf; int status, space_left; - u32 eof; __be32 nfserr; - __be32 *p = xdr->p - 2; /* Make sure there will be room for padding if needed */ if (xdr->end - xdr->p < 1) return nfserr_resource; nfserr = nfsd_splice_read(read->rd_rqstp, read->rd_fhp, - file, read->rd_offset, &maxcount, &eof); + file, read->rd_offset, &maxcount, + &read->rd_eof); read->rd_length = maxcount; if (nfserr) goto out_err; @@ -3894,9 +3944,6 @@ static __be32 nfsd4_encode_splice_read( goto out_err; } - *(p++) = htonl(eof); - *(p++) = htonl(maxcount); - buf->page_len = maxcount; buf->len += maxcount; xdr->page_ptr += (buf->page_base + maxcount + PAGE_SIZE - 1) @@ -3938,11 +3985,9 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp, struct file *file, unsigned long maxcount) { struct xdr_stream *xdr = resp->xdr; - u32 eof; - int starting_len = xdr->buf->len - 8; + unsigned int starting_len = xdr->buf->len; + __be32 zero = xdr_zero; __be32 nfserr; - __be32 tmp; - int pad; read->rd_vlen = xdr_reserve_space_vec(xdr, resp->rqstp->rq_vec, maxcount); if (read->rd_vlen < 0) @@ -3950,31 +3995,24 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp, nfserr = nfsd_readv(resp->rqstp, read->rd_fhp, file, read->rd_offset, resp->rqstp->rq_vec, read->rd_vlen, &maxcount, - &eof); + &read->rd_eof); read->rd_length = maxcount; if (nfserr) return nfserr; - if (svc_encode_result_payload(resp->rqstp, starting_len + 8, maxcount)) + if (svc_encode_result_payload(resp->rqstp, starting_len, maxcount)) return nfserr_io; - xdr_truncate_encode(xdr, starting_len + 8 + xdr_align_size(maxcount)); - - tmp = htonl(eof); - write_bytes_to_xdr_buf(xdr->buf, starting_len , &tmp, 4); - tmp = htonl(maxcount); - write_bytes_to_xdr_buf(xdr->buf, starting_len + 4, &tmp, 4); - - tmp = xdr_zero; - pad = (maxcount&3) ? 4 - (maxcount&3) : 0; - write_bytes_to_xdr_buf(xdr->buf, starting_len + 8 + maxcount, - &tmp, pad); - return 0; + 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)); + return nfs_ok; } static __be32 nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_read *read) { + bool splice_ok = test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags); unsigned long maxcount; struct xdr_stream *xdr = resp->xdr; struct file *file; @@ -3987,46 +4025,42 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr, p = xdr_reserve_space(xdr, 8); /* eof flag and byte count */ if (!p) { - WARN_ON_ONCE(test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags)); + WARN_ON_ONCE(splice_ok); return nfserr_resource; } - if (resp->xdr->buf->page_len && - test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags)) { + if (resp->xdr->buf->page_len && splice_ok) { WARN_ON_ONCE(1); - return nfserr_resource; + return nfserr_serverfault; } xdr_commit_encode(xdr); - maxcount = svc_max_payload(resp->rqstp); - maxcount = min_t(unsigned long, maxcount, + maxcount = min_t(unsigned long, read->rd_length, (xdr->buf->buflen - xdr->buf->len)); - maxcount = min_t(unsigned long, maxcount, read->rd_length); - if (file->f_op->splice_read && - test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags)) + 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); - - if (nfserr) + if (nfserr) { xdr_truncate_encode(xdr, starting_len); + return nfserr; + } - return nfserr; + p = xdr_encode_bool(p, read->rd_eof); + *p = cpu_to_be32(read->rd_length); + return nfs_ok; } static __be32 nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_readlink *readlink) { - int maxcount; - __be32 wire_count; - int zero = 0; + __be32 *p, *maxcount_p, zero = xdr_zero; struct xdr_stream *xdr = resp->xdr; int length_offset = xdr->buf->len; - int status; - __be32 *p; + int maxcount, status; - p = xdr_reserve_space(xdr, 4); - if (!p) + maxcount_p = xdr_reserve_space(xdr, XDR_UNIT); + if (!maxcount_p) return nfserr_resource; maxcount = PAGE_SIZE; @@ -4051,14 +4085,11 @@ nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd nfserr = nfserrno(status); goto out_err; } - - wire_count = htonl(maxcount); - write_bytes_to_xdr_buf(xdr->buf, length_offset, &wire_count, 4); - xdr_truncate_encode(xdr, length_offset + 4 + ALIGN(maxcount, 4)); - if (maxcount & 3) - write_bytes_to_xdr_buf(xdr->buf, length_offset + 4 + maxcount, - &zero, 4 - (maxcount&3)); - return 0; + *maxcount_p = cpu_to_be32(maxcount); + 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)); + return nfs_ok; out_err: xdr_truncate_encode(xdr, length_offset); @@ -4709,13 +4740,13 @@ nfsd4_encode_copy(struct nfsd4_compoundres *resp, __be32 nfserr, __be32 *p; nfserr = nfsd42_encode_write_res(resp, ©->cp_res, - !!copy->cp_synchronous); + nfsd4_copy_is_sync(copy)); if (nfserr) return nfserr; p = xdr_reserve_space(resp->xdr, 4 + 4); *p++ = xdr_one; /* cr_consecutive */ - *p++ = cpu_to_be32(copy->cp_synchronous); + *p = nfsd4_copy_is_sync(copy) ? xdr_one : xdr_zero; return 0; } @@ -4804,8 +4835,8 @@ nfsd4_encode_read_plus_hole(struct nfsd4_compoundres *resp, return nfserr_resource; *p++ = htonl(NFS4_CONTENT_HOLE); - p = xdr_encode_hyper(p, read->rd_offset); - p = xdr_encode_hyper(p, count); + p = xdr_encode_hyper(p, read->rd_offset); + p = xdr_encode_hyper(p, count); *eof = (read->rd_offset + count) >= f_size; *maxcount = min_t(unsigned long, count, *maxcount); @@ -4837,10 +4868,8 @@ nfsd4_encode_read_plus(struct nfsd4_compoundres *resp, __be32 nfserr, return nfserr_resource; xdr_commit_encode(xdr); - maxcount = svc_max_payload(resp->rqstp); - maxcount = min_t(unsigned long, maxcount, + maxcount = min_t(unsigned long, read->rd_length, (xdr->buf->buflen - xdr->buf->len)); - maxcount = min_t(unsigned long, maxcount, read->rd_length); count = maxcount; eof = read->rd_offset >= i_size_read(file_inode(file)); @@ -4915,7 +4944,8 @@ nfsd4_encode_copy_notify(struct nfsd4_compoundres *resp, __be32 nfserr, *p++ = cpu_to_be32(1); - return nfsd42_encode_nl4_server(resp, &cn->cpn_src); + nfserr = nfsd42_encode_nl4_server(resp, cn->cpn_src); + return nfserr; } static __be32 @@ -5369,8 +5399,7 @@ nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op) so->so_replay.rp_buf, len); } status: - /* Note that op->status is already in network byte order: */ - write_bytes_to_xdr_buf(xdr->buf, post_err_offset - 4, &op->status, 4); + *p = op->status; } /* @@ -5401,7 +5430,7 @@ void nfsd4_release_compoundargs(struct svc_rqst *rqstp) struct nfsd4_compoundargs *args = rqstp->rq_argp; if (args->ops != args->iops) { - kfree(args->ops); + vfree(args->ops); args->ops = args->iops; } while (args->to_free) { @@ -5430,12 +5459,8 @@ bool nfs4svc_encode_compoundres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd4_compoundres *resp = rqstp->rq_resp; - struct xdr_buf *buf = xdr->buf; __be32 *p; - WARN_ON_ONCE(buf->len != buf->head[0].iov_len + buf->page_len + - buf->tail[0].iov_len); - /* * Send buffer space for the following items is reserved * at the top of nfsd4_proc_compound(). diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index 6e0b6f3148dc..3e64a3d50a1c 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -84,12 +84,6 @@ nfsd_hashsize(unsigned int limit) return roundup_pow_of_two(limit / TARGET_BUCKET_SIZE); } -static u32 -nfsd_cache_hash(__be32 xid, struct nfsd_net *nn) -{ - return hash_32(be32_to_cpu(xid), nn->maskbits); -} - static struct svc_cacherep * nfsd_reply_cache_alloc(struct svc_rqst *rqstp, __wsum csum, struct nfsd_net *nn) @@ -182,7 +176,8 @@ int nfsd_reply_cache_init(struct nfsd_net *nn) 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); + status = register_shrinker(&nn->nfsd_reply_cache_shrinker, + "nfsd-reply:%s", nn->nfsd_name); if (status) goto out_stats_destroy; @@ -212,7 +207,6 @@ void nfsd_reply_cache_shutdown(struct nfsd_net *nn) struct svc_cacherep *rp; unsigned int i; - nfsd_reply_cache_stats_destroy(nn); unregister_shrinker(&nn->nfsd_reply_cache_shrinker); for (i = 0; i < nn->drc_hashsize; i++) { @@ -223,6 +217,7 @@ void nfsd_reply_cache_shutdown(struct nfsd_net *nn) rp, nn); } } + nfsd_reply_cache_stats_destroy(nn); kvfree(nn->drc_hashtbl); nn->drc_hashtbl = NULL; @@ -241,6 +236,14 @@ lru_put_end(struct nfsd_drc_bucket *b, struct svc_cacherep *rp) list_move_tail(&rp->c_lru, &b->lru_head); } +static noinline struct nfsd_drc_bucket * +nfsd_cache_bucket_find(__be32 xid, struct nfsd_net *nn) +{ + unsigned int hash = hash_32((__force u32)xid, nn->maskbits); + + return &nn->drc_hashtbl[hash]; +} + static long prune_bucket(struct nfsd_drc_bucket *b, struct nfsd_net *nn, unsigned int max) { @@ -419,12 +422,10 @@ out: */ int nfsd_cache_lookup(struct svc_rqst *rqstp) { - struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); + struct nfsd_net *nn; struct svc_cacherep *rp, *found; - __be32 xid = rqstp->rq_xid; __wsum csum; - u32 hash = nfsd_cache_hash(xid, nn); - struct nfsd_drc_bucket *b = &nn->drc_hashtbl[hash]; + struct nfsd_drc_bucket *b; int type = rqstp->rq_cachetype; int rtn = RC_DOIT; @@ -440,17 +441,16 @@ int nfsd_cache_lookup(struct svc_rqst *rqstp) * 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); if (!rp) goto out; + b = nfsd_cache_bucket_find(rqstp->rq_xid, nn); spin_lock(&b->cache_lock); found = nfsd_cache_insert(b, rp, nn); - if (found != rp) { - nfsd_reply_cache_free_locked(NULL, rp, nn); - rp = found; + if (found != rp) goto found_entry; - } nfsd_stats_rc_misses_inc(); rqstp->rq_cacherep = rp; @@ -468,8 +468,10 @@ 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(); rtn = RC_DROPIT; + rp = found; /* Request being processed */ if (rp->c_state == RC_INPROG) @@ -528,7 +530,6 @@ void nfsd_cache_update(struct svc_rqst *rqstp, 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; - u32 hash; struct nfsd_drc_bucket *b; int len; size_t bufsize = 0; @@ -536,8 +537,7 @@ void nfsd_cache_update(struct svc_rqst *rqstp, int cachetype, __be32 *statp) if (!rp) return; - hash = nfsd_cache_hash(rp->c_key.k_xid, nn); - b = &nn->drc_hashtbl[hash]; + b = nfsd_cache_bucket_find(rp->c_key.k_xid, nn); len = resv->iov_len - ((char*)statp - (char*)resv->iov_base); len >>= 2; @@ -604,9 +604,10 @@ nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *data) * scraping this file for info should test the labels to ensure they're * getting the correct field. */ -static int nfsd_reply_cache_stats_show(struct seq_file *m, void *v) +int nfsd_reply_cache_stats_show(struct seq_file *m, void *v) { - struct nfsd_net *nn = m->private; + struct nfsd_net *nn = net_generic(file_inode(m->file)->i_sb->s_fs_info, + nfsd_net_id); seq_printf(m, "max entries: %u\n", nn->max_drc_entries); seq_printf(m, "num entries: %u\n", @@ -626,11 +627,3 @@ static int nfsd_reply_cache_stats_show(struct seq_file *m, void *v) seq_printf(m, "cachesize at longest: %u\n", nn->longest_chain_cachesize); return 0; } - -int nfsd_reply_cache_stats_open(struct inode *inode, struct file *file) -{ - struct nfsd_net *nn = net_generic(file_inode(file)->i_sb->s_fs_info, - nfsd_net_id); - - return single_open(file, nfsd_reply_cache_stats_show, nn); -} diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 51a49e0cfe37..dc74a947a440 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -25,6 +25,7 @@ #include "state.h" #include "netns.h" #include "pnfs.h" +#include "filecache.h" /* * We have a single directory with several nodes in it. @@ -45,6 +46,7 @@ enum { NFSD_Ports, NFSD_MaxBlkSize, NFSD_MaxConnections, + NFSD_Filecache, NFSD_SupportedEnctypes, /* * The below MUST come last. Otherwise we leave a hole in nfsd_files[] @@ -183,17 +185,7 @@ static int export_features_show(struct seq_file *m, void *v) return 0; } -static int export_features_open(struct inode *inode, struct file *file) -{ - return single_open(file, export_features_show, NULL); -} - -static const struct file_operations export_features_operations = { - .open = export_features_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +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) @@ -202,17 +194,7 @@ static int supported_enctypes_show(struct seq_file *m, void *v) return 0; } -static int supported_enctypes_open(struct inode *inode, struct file *file) -{ - return single_open(file, supported_enctypes_show, NULL); -} - -static const struct file_operations supported_enctypes_ops = { - .open = supported_enctypes_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(supported_enctypes); #endif /* CONFIG_SUNRPC_GSS or CONFIG_SUNRPC_GSS_MODULE */ static const struct file_operations pool_stats_operations = { @@ -222,12 +204,9 @@ static const struct file_operations pool_stats_operations = { .release = nfsd_pool_stats_release, }; -static const struct file_operations reply_cache_stats_operations = { - .open = nfsd_reply_cache_stats_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(nfsd_reply_cache_stats); + +DEFINE_SHOW_ATTRIBUTE(nfsd_file_cache_stats); /*----------------------------------------------------------------------------*/ /* @@ -633,7 +612,6 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size) } /* Now write current state into reply buffer */ - len = 0; sep = ""; remaining = SIMPLE_TRANSACTION_LIMIT; for (num=2 ; num <= 4 ; num++) { @@ -742,13 +720,12 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net, const struct cred return err; err = svc_addsock(nn->nfsd_serv, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred); - if (err < 0) { - nfsd_destroy(net); - return err; - } - /* Decrease the count, but don't shut down the service */ - nn->nfsd_serv->sv_nrthreads--; + if (err >= 0 && + !nn->nfsd_serv->sv_nrthreads && !xchg(&nn->keep_active, 1)) + svc_get(nn->nfsd_serv); + + nfsd_put(net); return err; } @@ -773,30 +750,29 @@ static ssize_t __write_ports_addxprt(char *buf, struct net *net, const struct cr if (err != 0) return err; - err = svc_create_xprt(nn->nfsd_serv, transport, net, - PF_INET, port, SVC_SOCK_ANONYMOUS, cred); + err = svc_xprt_create(nn->nfsd_serv, transport, net, + PF_INET, port, SVC_SOCK_ANONYMOUS, cred); if (err < 0) goto out_err; - err = svc_create_xprt(nn->nfsd_serv, transport, net, - PF_INET6, port, SVC_SOCK_ANONYMOUS, cred); + err = svc_xprt_create(nn->nfsd_serv, transport, net, + PF_INET6, port, SVC_SOCK_ANONYMOUS, cred); if (err < 0 && err != -EAFNOSUPPORT) goto out_close; - /* Decrease the count, but don't shut down the service */ - nn->nfsd_serv->sv_nrthreads--; + 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); if (xprt != NULL) { - svc_close_xprt(xprt); + svc_xprt_close(xprt); svc_xprt_put(xprt); } out_err: - if (!list_empty(&nn->nfsd_serv->sv_permsocks)) - nn->nfsd_serv->sv_nrthreads--; - else - nfsd_destroy(net); + nfsd_put(net); return err; } @@ -1249,7 +1225,8 @@ static void nfsdfs_remove_file(struct inode *dir, struct dentry *dentry) clear_ncl(d_inode(dentry)); dget(dentry); ret = simple_unlink(dir, dentry); - d_delete(dentry); + d_drop(dentry); + fsnotify_unlink(dir, dentry); dput(dentry); WARN_ON_ONCE(ret); } @@ -1340,8 +1317,8 @@ void nfsd_client_rmdir(struct dentry *dentry) dget(dentry); ret = simple_rmdir(dir, dentry); WARN_ON_ONCE(ret); + d_drop(dentry); fsnotify_rmdir(dir, dentry); - d_delete(dentry); dput(dentry); inode_unlock(dir); } @@ -1358,7 +1335,7 @@ static int nfsd_fill_super(struct super_block *sb, struct fs_context *fc) /* Per-export io stats use same ops as exports file */ [NFSD_Export_Stats] = {"export_stats", &exports_nfsd_operations, S_IRUGO}, [NFSD_Export_features] = {"export_features", - &export_features_operations, S_IRUGO}, + &export_features_fops, S_IRUGO}, [NFSD_FO_UnlockIP] = {"unlock_ip", &transaction_ops, S_IWUSR|S_IRUSR}, [NFSD_FO_UnlockFS] = {"unlock_filesystem", @@ -1367,13 +1344,16 @@ static int nfsd_fill_super(struct super_block *sb, struct fs_context *fc) [NFSD_Threads] = {"threads", &transaction_ops, S_IWUSR|S_IRUSR}, [NFSD_Pool_Threads] = {"pool_threads", &transaction_ops, S_IWUSR|S_IRUSR}, [NFSD_Pool_Stats] = {"pool_stats", &pool_stats_operations, S_IRUGO}, - [NFSD_Reply_Cache_Stats] = {"reply_cache_stats", &reply_cache_stats_operations, S_IRUGO}, + [NFSD_Reply_Cache_Stats] = {"reply_cache_stats", + &nfsd_reply_cache_stats_fops, S_IRUGO}, [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_ops, S_IRUGO}, + [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}, @@ -1473,24 +1453,19 @@ static __net_init int nfsd_init_net(struct net *net) goto out_idmap_error; nn->nfsd_versions = NULL; nn->nfsd4_minorversions = NULL; - retval = nfsd_reply_cache_init(nn); + retval = nfsd4_init_leases_net(nn); if (retval) goto out_drc_error; - nn->nfsd4_lease = 90; /* default lease time */ - nn->nfsd4_grace = 90; - nn->somebody_reclaimed = false; - nn->track_reclaim_completes = false; - nn->clverifier_counter = prandom_u32(); - nn->clientid_base = prandom_u32(); - nn->clientid_counter = nn->clientid_base + 1; - nn->s2s_cp_cl_id = nn->clientid_counter++; - - atomic_set(&nn->ntf_refcnt, 0); - init_waitqueue_head(&nn->ntf_wq); - seqlock_init(&nn->boot_lock); + retval = nfsd_reply_cache_init(nn); + if (retval) + goto out_cache_error; + get_random_bytes(&nn->siphash_key, sizeof(nn->siphash_key)); + seqlock_init(&nn->writeverf_lock); return 0; +out_cache_error: + nfsd4_leases_net_shutdown(nn); out_drc_error: nfsd_idmap_shutdown(net); out_idmap_error: @@ -1507,6 +1482,7 @@ static __net_exit void nfsd_exit_net(struct net *net) nfsd_idmap_shutdown(net); nfsd_export_shutdown(net); nfsd_netns_free_versions(net_generic(net, nfsd_net_id)); + nfsd4_leases_net_shutdown(nn); } static struct pernet_operations nfsd_net_ops = { @@ -1519,7 +1495,6 @@ static struct pernet_operations nfsd_net_ops = { static int __init init_nfsd(void) { int retval; - printk(KERN_INFO "Installing knfsd (copyright (C) 1996 okir@monad.swb.de).\n"); retval = nfsd4_init_slabs(); if (retval) @@ -1537,20 +1512,25 @@ static int __init init_nfsd(void) retval = create_proc_exports_entry(); if (retval) goto out_free_lockd; - retval = register_filesystem(&nfsd_fs_type); - if (retval) - goto out_free_exports; retval = register_pernet_subsys(&nfsd_net_ops); if (retval < 0) - goto out_free_filesystem; + goto out_free_exports; retval = register_cld_notifier(); if (retval) + goto out_free_subsys; + retval = nfsd4_create_laundry_wq(); + if (retval) + goto out_free_cld; + retval = register_filesystem(&nfsd_fs_type); + if (retval) goto out_free_all; return 0; out_free_all: + nfsd4_destroy_laundry_wq(); +out_free_cld: + unregister_cld_notifier(); +out_free_subsys: unregister_pernet_subsys(&nfsd_net_ops); -out_free_filesystem: - unregister_filesystem(&nfsd_fs_type); out_free_exports: remove_proc_entry("fs/nfs/exports", NULL); remove_proc_entry("fs/nfs", NULL); @@ -1568,6 +1548,8 @@ out_free_slabs: static void __exit exit_nfsd(void) { + unregister_filesystem(&nfsd_fs_type); + nfsd4_destroy_laundry_wq(); unregister_cld_notifier(); unregister_pernet_subsys(&nfsd_net_ops); nfsd_drc_slab_free(); @@ -1577,7 +1559,6 @@ static void __exit exit_nfsd(void) nfsd_lockd_shutdown(); nfsd4_free_slabs(); nfsd4_exit_pnfs(); - unregister_filesystem(&nfsd_fs_type); } MODULE_AUTHOR("Olaf Kirch <okir@monad.swb.de>"); diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 498e5a489826..09726c5b9a31 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -97,7 +97,7 @@ 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_destroy(struct net *net); +void nfsd_put(struct net *net); bool i_am_nfsd(void); @@ -162,6 +162,9 @@ void nfs4_state_shutdown_net(struct net *net); int nfs4_reset_recoverydir(char *recdir); char * nfs4_recoverydir(void); bool nfsd4_spo_must_allow(struct svc_rqst *rqstp); +int nfsd4_create_laundry_wq(void); +void nfsd4_destroy_laundry_wq(void); +bool nfsd_wait_for_delegreturn(struct svc_rqst *rqstp, struct inode *inode); #else static inline int nfsd4_init_slabs(void) { return 0; } static inline void nfsd4_free_slabs(void) { } @@ -175,6 +178,13 @@ static inline bool nfsd4_spo_must_allow(struct svc_rqst *rqstp) { return false; } +static inline int nfsd4_create_laundry_wq(void) { return 0; }; +static inline void nfsd4_destroy_laundry_wq(void) {}; +static inline bool nfsd_wait_for_delegreturn(struct svc_rqst *rqstp, + struct inode *inode) +{ + return false; +} #endif /* @@ -336,6 +346,10 @@ void nfsd_lockd_shutdown(void); #define COMPOUND_ERR_SLACK_SPACE 16 /* OP_SETATTR */ #define NFSD_LAUNDROMAT_MINTIMEOUT 1 /* seconds */ +#define NFSD_COURTESY_CLIENT_TIMEOUT (24 * 60 * 60) /* seconds */ +#define NFSD_CLIENT_MAX_TRIM_PER_RUN 128 +#define NFS4_CLIENTS_PER_GB 1024 +#define NFSD_DELEGRETURN_TIMEOUT (HZ / 34) /* 30ms */ /* * The following attributes are currently not supported by the NFSv4 server: @@ -364,7 +378,7 @@ void nfsd_lockd_shutdown(void); | FATTR4_WORD1_OWNER | FATTR4_WORD1_OWNER_GROUP | FATTR4_WORD1_RAWDEV \ | FATTR4_WORD1_SPACE_AVAIL | FATTR4_WORD1_SPACE_FREE | FATTR4_WORD1_SPACE_TOTAL \ | FATTR4_WORD1_SPACE_USED | FATTR4_WORD1_TIME_ACCESS | FATTR4_WORD1_TIME_ACCESS_SET \ - | FATTR4_WORD1_TIME_DELTA | FATTR4_WORD1_TIME_METADATA \ + | FATTR4_WORD1_TIME_DELTA | FATTR4_WORD1_TIME_METADATA | FATTR4_WORD1_TIME_CREATE \ | FATTR4_WORD1_TIME_MODIFY | FATTR4_WORD1_TIME_MODIFY_SET | FATTR4_WORD1_MOUNTED_ON_FILEID) #define NFSD4_SUPPORTED_ATTRS_WORD2 0 @@ -460,7 +474,8 @@ static inline bool nfsd_attrs_supported(u32 minorversion, const u32 *bmval) (FATTR4_WORD0_SIZE | FATTR4_WORD0_ACL) #define NFSD_WRITEABLE_ATTRS_WORD1 \ (FATTR4_WORD1_MODE | FATTR4_WORD1_OWNER | FATTR4_WORD1_OWNER_GROUP \ - | FATTR4_WORD1_TIME_ACCESS_SET | FATTR4_WORD1_TIME_MODIFY_SET) + | FATTR4_WORD1_TIME_ACCESS_SET | FATTR4_WORD1_TIME_CREATE \ + | FATTR4_WORD1_TIME_MODIFY_SET) #ifdef CONFIG_NFSD_V4_SECURITY_LABEL #define MAYBE_FATTR4_WORD2_SECURITY_LABEL \ FATTR4_WORD2_SECURITY_LABEL @@ -490,12 +505,18 @@ extern void unregister_cld_notifier(void); extern void nfsd4_ssc_init_umount_work(struct nfsd_net *nn); #endif +extern int nfsd4_init_leases_net(struct nfsd_net *nn); +extern void nfsd4_leases_net_shutdown(struct nfsd_net *nn); + #else /* CONFIG_NFSD_V4 */ static inline int nfsd4_is_junction(struct dentry *dentry) { return 0; } +static inline int nfsd4_init_leases_net(struct nfsd_net *nn) { return 0; }; +static inline void nfsd4_leases_net_shutdown(struct nfsd_net *nn) {}; + #define register_cld_notifier() 0 #define unregister_cld_notifier() do { } while(0) diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index f3779fa72c89..8c52b6c9d31a 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -331,8 +331,6 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int access) struct dentry *dentry; __be32 error; - dprintk("nfsd: fh_verify(%s)\n", SVCFH_fmt(fhp)); - if (!fhp->fh_dentry) { error = nfsd_set_fh_dentry(rqstp, fhp); if (error) @@ -340,6 +338,9 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int access) } dentry = fhp->fh_dentry; exp = fhp->fh_export; + + trace_nfsd_fh_verify(rqstp, fhp, type, access); + /* * We still have to do all these permission checks, even when * fh_dentry is already set: @@ -391,14 +392,8 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int access) skip_pseudoflavor_check: /* Finally, check access permissions. */ error = nfsd_permission(rqstp, exp, dentry, access); - - if (error) { - dprintk("fh_verify: %pd2 permission failure, " - "acc=%x, error=%d\n", - dentry, - access, ntohl(error)); - } out: + trace_nfsd_fh_verify_err(rqstp, fhp, type, access, error); if (error == nfserr_stale) nfsd_stats_fh_stale_inc(exp); return error; @@ -548,7 +543,7 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry, if (ref_fh == fhp) fh_put(ref_fh); - if (fhp->fh_locked || fhp->fh_dentry) { + if (fhp->fh_dentry) { printk(KERN_ERR "fh_compose: fh %pd2 not initialized!\n", dentry); } @@ -611,6 +606,85 @@ out_negative: return nfserr_serverfault; } +/** + * fh_fill_pre_attrs - Fill in pre-op attributes + * @fhp: file handle to be updated + * + */ +void 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; + + 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 (v4) + fhp->fh_pre_change = nfsd4_change_attribute(&stat, inode); + + fhp->fh_pre_mtime = stat.mtime; + fhp->fh_pre_ctime = stat.ctime; + fhp->fh_pre_size = stat.size; + fhp->fh_pre_saved = true; +} + +/** + * fh_fill_post_attrs - Fill in post-op attributes + * @fhp: file handle to be updated + * + */ +void 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; + + 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 (v4) + fhp->fh_post_change = + nfsd4_change_attribute(&fhp->fh_post_attr, inode); +} + +/** + * fh_fill_both_attrs - Fill pre-op and post-op attributes + * @fhp: file handle to be updated + * + * This is used when the directory wasn't changed, but wcc attributes + * are needed anyway. + */ +void fh_fill_both_attrs(struct svc_fh *fhp) +{ + fh_fill_post_attrs(fhp); + if (!fhp->fh_post_saved) + return; + 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; +} + /* * Release a file handle. */ @@ -620,10 +694,9 @@ fh_put(struct svc_fh *fhp) struct dentry * dentry = fhp->fh_dentry; struct svc_export * exp = fhp->fh_export; if (dentry) { - fh_unlock(fhp); fhp->fh_dentry = NULL; dput(dentry); - fh_clear_wcc(fhp); + fh_clear_pre_post_attrs(fhp); } fh_drop_write(fhp); if (exp) { diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h index d11e4b6870d6..c3ae6414fc5c 100644 --- a/fs/nfsd/nfsfh.h +++ b/fs/nfsd/nfsfh.h @@ -81,7 +81,6 @@ typedef struct svc_fh { struct dentry * fh_dentry; /* validated dentry */ struct svc_export * fh_export; /* export pointer */ - bool fh_locked; /* inode locked by us */ bool fh_want_write; /* remount protection taken */ bool fh_no_wcc; /* no wcc data needed */ bool fh_no_atomic_attr; @@ -90,11 +89,10 @@ typedef struct svc_fh { * operation */ int fh_flags; /* FH flags */ -#ifdef CONFIG_NFSD_V3 bool fh_post_saved; /* post-op attrs saved */ bool fh_pre_saved; /* pre-op attrs saved */ - /* Pre-op attributes saved during fh_lock */ + /* Pre-op attributes saved when inode is locked */ __u64 fh_pre_size; /* size before operation */ struct timespec64 fh_pre_mtime; /* mtime before oper */ struct timespec64 fh_pre_ctime; /* ctime before oper */ @@ -104,10 +102,9 @@ typedef struct svc_fh { */ u64 fh_pre_change; - /* Post-op attributes saved in fh_unlock */ + /* Post-op attributes saved in fh_fill_post_attrs() */ struct kstat fh_post_attr; /* full attrs after operation */ u64 fh_post_change; /* nfsv4 change; see above */ -#endif /* CONFIG_NFSD_V3 */ } svc_fh; #define NFSD4_FH_FOREIGN (1<<0) #define SET_FH_FLAG(c, f) ((c)->fh_flags |= (f)) @@ -225,8 +222,8 @@ void fh_put(struct svc_fh *); static __inline__ struct svc_fh * fh_copy(struct svc_fh *dst, struct svc_fh *src) { - WARN_ON(src->fh_dentry || src->fh_locked); - + WARN_ON(src->fh_dentry); + *dst = *src; return dst; } @@ -283,13 +280,12 @@ static inline u32 knfsd_fh_hash(const struct knfsd_fh *fh) } #endif -#ifdef CONFIG_NFSD_V3 -/* - * The wcc data stored in current_fh should be cleared - * between compound ops. +/** + * fh_clear_pre_post_attrs - Reset pre/post attributes + * @fhp: file handle to be updated + * */ -static inline void -fh_clear_wcc(struct svc_fh *fhp) +static inline void fh_clear_pre_post_attrs(struct svc_fh *fhp) { fhp->fh_post_saved = false; fhp->fh_pre_saved = false; @@ -323,59 +319,7 @@ static inline u64 nfsd4_change_attribute(struct kstat *stat, return time_to_chattr(&stat->ctime); } -extern void fill_pre_wcc(struct svc_fh *fhp); -extern void fill_post_wcc(struct svc_fh *fhp); -#else -#define fh_clear_wcc(ignored) -#define fill_pre_wcc(ignored) -#define fill_post_wcc(notused) -#endif /* CONFIG_NFSD_V3 */ - - -/* - * Lock a file handle/inode - * NOTE: both fh_lock and fh_unlock are done "by hand" in - * vfs.c:nfsd_rename as it needs to grab 2 i_mutex's at once - * so, any changes here should be reflected there. - */ - -static inline void -fh_lock_nested(struct svc_fh *fhp, unsigned int subclass) -{ - struct dentry *dentry = fhp->fh_dentry; - struct inode *inode; - - BUG_ON(!dentry); - - if (fhp->fh_locked) { - printk(KERN_WARNING "fh_lock: %pd2 already locked!\n", - dentry); - return; - } - - inode = d_inode(dentry); - inode_lock_nested(inode, subclass); - fill_pre_wcc(fhp); - fhp->fh_locked = true; -} - -static inline void -fh_lock(struct svc_fh *fhp) -{ - fh_lock_nested(fhp, I_MUTEX_NORMAL); -} - -/* - * Unlock a file handle/inode - */ -static inline void -fh_unlock(struct svc_fh *fhp) -{ - if (fhp->fh_locked) { - fill_post_wcc(fhp); - inode_unlock(d_inode(fhp->fh_dentry)); - fhp->fh_locked = false; - } -} - +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); #endif /* _LINUX_NFSD_NFSFH_H */ diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index de282f3273c5..82b3ddeacc33 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -51,6 +51,9 @@ nfsd_proc_setattr(struct svc_rqst *rqstp) struct nfsd_sattrargs *argp = rqstp->rq_argp; struct nfsd_attrstat *resp = rqstp->rq_resp; struct iattr *iap = &argp->attrs; + struct nfsd_attrs attrs = { + .na_iattr = iap, + }; struct svc_fh *fhp; dprintk("nfsd: SETATTR %s, valid=%x, size=%ld\n", @@ -100,7 +103,7 @@ nfsd_proc_setattr(struct svc_rqst *rqstp) } } - resp->status = nfsd_setattr(rqstp, fhp, iap, 0, (time64_t)0); + resp->status = nfsd_setattr(rqstp, fhp, &attrs, 0, (time64_t)0); if (resp->status != nfs_ok) goto out; @@ -182,6 +185,7 @@ nfsd_proc_read(struct svc_rqst *rqstp) argp->count, argp->offset); argp->count = min_t(u32, argp->count, NFSSVC_MAXBLKSIZE_V2); + argp->count = min_t(u32, argp->count, rqstp->rq_res.buflen); v = 0; len = argp->count; @@ -230,15 +234,11 @@ nfsd_proc_write(struct svc_rqst *rqstp) unsigned long cnt = argp->len; unsigned int nvecs; - dprintk("nfsd: WRITE %s %d bytes at %d\n", + 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); - if (!nvecs) { - resp->status = nfserr_io; - goto out; - } resp->status = nfsd_write(rqstp, fh_copy(&resp->fh, &argp->fh), argp->offset, rqstp->rq_vec, nvecs, @@ -247,7 +247,6 @@ nfsd_proc_write(struct svc_rqst *rqstp) resp->status = fh_getattr(&resp->fh, &resp->stat); else if (resp->status == nfserr_jukebox) return rpc_drop_reply; -out: return rpc_success; } @@ -265,6 +264,9 @@ nfsd_proc_create(struct svc_rqst *rqstp) svc_fh *dirfhp = &argp->fh; svc_fh *newfhp = &resp->fh; struct iattr *attr = &argp->attrs; + struct nfsd_attrs attrs = { + .na_iattr = attr, + }; struct inode *inode; struct dentry *dchild; int type, mode; @@ -290,7 +292,7 @@ nfsd_proc_create(struct svc_rqst *rqstp) goto done; } - fh_lock_nested(dirfhp, I_MUTEX_PARENT); + inode_lock_nested(dirfhp->fh_dentry->d_inode, I_MUTEX_PARENT); dchild = lookup_one_len(argp->name, dirfhp->fh_dentry, argp->len); if (IS_ERR(dchild)) { resp->status = nfserrno(PTR_ERR(dchild)); @@ -389,9 +391,8 @@ nfsd_proc_create(struct svc_rqst *rqstp) resp->status = nfs_ok; if (!inode) { /* File doesn't exist. Create it and set attrs */ - resp->status = nfsd_create_locked(rqstp, dirfhp, argp->name, - argp->len, attr, type, rdev, - newfhp); + resp->status = nfsd_create_locked(rqstp, dirfhp, &attrs, type, + rdev, newfhp); } else if (type == S_IFREG) { dprintk("nfsd: existing %s, valid=%x, size=%ld\n", argp->name, attr->ia_valid, (long) attr->ia_size); @@ -401,13 +402,12 @@ nfsd_proc_create(struct svc_rqst *rqstp) */ attr->ia_valid &= ATTR_SIZE; if (attr->ia_valid) - resp->status = nfsd_setattr(rqstp, newfhp, attr, 0, + resp->status = nfsd_setattr(rqstp, newfhp, &attrs, 0, (time64_t)0); } out_unlock: - /* We don't really need to unlock, as fh_put does it. */ - fh_unlock(dirfhp); + inode_unlock(dirfhp->fh_dentry->d_inode); fh_drop_write(dirfhp); done: fh_put(dirfhp); @@ -477,6 +477,9 @@ nfsd_proc_symlink(struct svc_rqst *rqstp) { struct nfsd_symlinkargs *argp = rqstp->rq_argp; struct nfsd_stat *resp = rqstp->rq_resp; + struct nfsd_attrs attrs = { + .na_iattr = &argp->attrs, + }; struct svc_fh newfh; if (argp->tlen > NFS_MAXPATHLEN) { @@ -498,7 +501,7 @@ nfsd_proc_symlink(struct svc_rqst *rqstp) fh_init(&newfh, NFS_FHSIZE); resp->status = nfsd_symlink(rqstp, &argp->ffh, argp->fname, argp->flen, - argp->tname, &newfh); + argp->tname, &attrs, &newfh); kfree(argp->tname); fh_put(&argp->ffh); @@ -516,6 +519,9 @@ nfsd_proc_mkdir(struct svc_rqst *rqstp) { struct nfsd_createargs *argp = rqstp->rq_argp; struct nfsd_diropres *resp = rqstp->rq_resp; + struct nfsd_attrs attrs = { + .na_iattr = &argp->attrs, + }; dprintk("nfsd: MKDIR %s %.*s\n", SVCFH_fmt(&argp->fh), argp->len, argp->name); @@ -527,7 +533,7 @@ nfsd_proc_mkdir(struct svc_rqst *rqstp) argp->attrs.ia_valid &= ~ATTR_SIZE; fh_init(&resp->fh, NFS_FHSIZE); resp->status = nfsd_create(rqstp, &argp->fh, argp->name, argp->len, - &argp->attrs, S_IFDIR, 0, &resp->fh); + &attrs, S_IFDIR, 0, &resp->fh); fh_put(&argp->fh); if (resp->status != nfs_ok) goto out; @@ -561,24 +567,15 @@ static void nfsd_init_dirlist_pages(struct svc_rqst *rqstp, struct xdr_buf *buf = &resp->dirlist; struct xdr_stream *xdr = &resp->xdr; - count = clamp(count, (u32)(XDR_UNIT * 2), svc_max_payload(rqstp)); - memset(buf, 0, sizeof(*buf)); /* Reserve room for the NULL ptr & eof flag (-2 words) */ - buf->buflen = count - XDR_UNIT * 2; + buf->buflen = clamp(count, (u32)(XDR_UNIT * 2), (u32)PAGE_SIZE); + buf->buflen -= XDR_UNIT * 2; buf->pages = rqstp->rq_next_page; rqstp->rq_next_page++; - /* This is xdr_init_encode(), but it assumes that - * the head kvec has already been consumed. */ - xdr_set_scratch_buffer(xdr, NULL, 0); - xdr->buf = buf; - xdr->page_ptr = buf->pages; - xdr->iov = NULL; - xdr->p = page_address(*buf->pages); - xdr->end = (void *)xdr->p + min_t(u32, buf->buflen, PAGE_SIZE); - xdr->rqst = NULL; + xdr_init_encode_pages(xdr, buf, buf->pages, NULL); } /* @@ -640,6 +637,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_decode = nfssvc_decode_voidarg, .pc_encode = nfssvc_encode_voidres, .pc_argsize = sizeof(struct nfsd_voidargs), + .pc_argzero = sizeof(struct nfsd_voidargs), .pc_ressize = sizeof(struct nfsd_voidres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = 0, @@ -651,6 +649,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_encode = nfssvc_encode_attrstatres, .pc_release = nfssvc_release_attrstat, .pc_argsize = sizeof(struct nfsd_fhandle), + .pc_argzero = sizeof(struct nfsd_fhandle), .pc_ressize = sizeof(struct nfsd_attrstat), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+AT, @@ -662,6 +661,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_encode = nfssvc_encode_attrstatres, .pc_release = nfssvc_release_attrstat, .pc_argsize = sizeof(struct nfsd_sattrargs), + .pc_argzero = sizeof(struct nfsd_sattrargs), .pc_ressize = sizeof(struct nfsd_attrstat), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+AT, @@ -672,6 +672,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_decode = nfssvc_decode_voidarg, .pc_encode = nfssvc_encode_voidres, .pc_argsize = sizeof(struct nfsd_voidargs), + .pc_argzero = sizeof(struct nfsd_voidargs), .pc_ressize = sizeof(struct nfsd_voidres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = 0, @@ -683,6 +684,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_encode = nfssvc_encode_diropres, .pc_release = nfssvc_release_diropres, .pc_argsize = sizeof(struct nfsd_diropargs), + .pc_argzero = sizeof(struct nfsd_diropargs), .pc_ressize = sizeof(struct nfsd_diropres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+FH+AT, @@ -693,6 +695,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_decode = nfssvc_decode_fhandleargs, .pc_encode = nfssvc_encode_readlinkres, .pc_argsize = sizeof(struct nfsd_fhandle), + .pc_argzero = sizeof(struct nfsd_fhandle), .pc_ressize = sizeof(struct nfsd_readlinkres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+1+NFS_MAXPATHLEN/4, @@ -704,6 +707,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_encode = nfssvc_encode_readres, .pc_release = nfssvc_release_readres, .pc_argsize = sizeof(struct nfsd_readargs), + .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, @@ -714,6 +718,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_decode = nfssvc_decode_voidarg, .pc_encode = nfssvc_encode_voidres, .pc_argsize = sizeof(struct nfsd_voidargs), + .pc_argzero = sizeof(struct nfsd_voidargs), .pc_ressize = sizeof(struct nfsd_voidres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = 0, @@ -725,6 +730,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_encode = nfssvc_encode_attrstatres, .pc_release = nfssvc_release_attrstat, .pc_argsize = sizeof(struct nfsd_writeargs), + .pc_argzero = sizeof(struct nfsd_writeargs), .pc_ressize = sizeof(struct nfsd_attrstat), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+AT, @@ -736,6 +742,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_encode = nfssvc_encode_diropres, .pc_release = nfssvc_release_diropres, .pc_argsize = sizeof(struct nfsd_createargs), + .pc_argzero = sizeof(struct nfsd_createargs), .pc_ressize = sizeof(struct nfsd_diropres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+FH+AT, @@ -746,6 +753,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_decode = nfssvc_decode_diropargs, .pc_encode = nfssvc_encode_statres, .pc_argsize = sizeof(struct nfsd_diropargs), + .pc_argzero = sizeof(struct nfsd_diropargs), .pc_ressize = sizeof(struct nfsd_stat), .pc_cachetype = RC_REPLSTAT, .pc_xdrressize = ST, @@ -756,6 +764,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_decode = nfssvc_decode_renameargs, .pc_encode = nfssvc_encode_statres, .pc_argsize = sizeof(struct nfsd_renameargs), + .pc_argzero = sizeof(struct nfsd_renameargs), .pc_ressize = sizeof(struct nfsd_stat), .pc_cachetype = RC_REPLSTAT, .pc_xdrressize = ST, @@ -766,6 +775,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_decode = nfssvc_decode_linkargs, .pc_encode = nfssvc_encode_statres, .pc_argsize = sizeof(struct nfsd_linkargs), + .pc_argzero = sizeof(struct nfsd_linkargs), .pc_ressize = sizeof(struct nfsd_stat), .pc_cachetype = RC_REPLSTAT, .pc_xdrressize = ST, @@ -776,6 +786,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_decode = nfssvc_decode_symlinkargs, .pc_encode = nfssvc_encode_statres, .pc_argsize = sizeof(struct nfsd_symlinkargs), + .pc_argzero = sizeof(struct nfsd_symlinkargs), .pc_ressize = sizeof(struct nfsd_stat), .pc_cachetype = RC_REPLSTAT, .pc_xdrressize = ST, @@ -787,6 +798,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_encode = nfssvc_encode_diropres, .pc_release = nfssvc_release_diropres, .pc_argsize = sizeof(struct nfsd_createargs), + .pc_argzero = sizeof(struct nfsd_createargs), .pc_ressize = sizeof(struct nfsd_diropres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+FH+AT, @@ -797,6 +809,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_decode = nfssvc_decode_diropargs, .pc_encode = nfssvc_encode_statres, .pc_argsize = sizeof(struct nfsd_diropargs), + .pc_argzero = sizeof(struct nfsd_diropargs), .pc_ressize = sizeof(struct nfsd_stat), .pc_cachetype = RC_REPLSTAT, .pc_xdrressize = ST, @@ -807,6 +820,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_decode = nfssvc_decode_readdirargs, .pc_encode = nfssvc_encode_readdirres, .pc_argsize = sizeof(struct nfsd_readdirargs), + .pc_argzero = sizeof(struct nfsd_readdirargs), .pc_ressize = sizeof(struct nfsd_readdirres), .pc_cachetype = RC_NOCACHE, .pc_name = "READDIR", @@ -816,6 +830,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_decode = nfssvc_decode_fhandleargs, .pc_encode = nfssvc_encode_statfsres, .pc_argsize = sizeof(struct nfsd_fhandle), + .pc_argzero = sizeof(struct nfsd_fhandle), .pc_ressize = sizeof(struct nfsd_statfsres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+5, @@ -850,6 +865,7 @@ nfserrno (int errno) { nfserr_io, -EIO }, { nfserr_nxio, -ENXIO }, { nfserr_fbig, -E2BIG }, + { nfserr_stale, -EBADF }, { nfserr_acces, -EACCES }, { nfserr_exist, -EEXIST }, { nfserr_xdev, -EXDEV }, @@ -878,6 +894,8 @@ nfserrno (int errno) { nfserr_toosmall, -ETOOSMALL }, { nfserr_serverfault, -ESERVERFAULT }, { nfserr_serverfault, -ENFILE }, + { nfserr_io, -EREMOTEIO }, + { nfserr_stale, -EOPENSTALE }, { nfserr_io, -EUCLEAN }, { nfserr_perm, -ENOKEY }, { nfserr_no_grace, -ENOGRACE}, diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 80431921e5d7..bfbd9f672f59 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -12,6 +12,7 @@ #include <linux/module.h> #include <linux/fs_struct.h> #include <linux/swap.h> +#include <linux/siphash.h> #include <linux/sunrpc/stats.h> #include <linux/sunrpc/svcsock.h> @@ -55,18 +56,17 @@ static __be32 nfsd_init_request(struct svc_rqst *, struct svc_process_info *); /* - * nfsd_mutex protects nn->nfsd_serv -- both the pointer itself and the members - * of the svc_serv struct. In particular, ->sv_nrthreads but also to some - * extent ->sv_temp_socks and ->sv_permsocks. It also protects nfsdstats.th_cnt + * 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. That number - * of nfsd threads must exist and each must listed in ->sp_all_threads in each - * entry of ->sv_pools[]. + * 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[]. * - * Transitions of the thread count between zero and non-zero are of particular - * interest since the svc_serv needs to be created and initialized at that - * point, or freed. + * 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 @@ -117,9 +117,7 @@ static struct svc_stat nfsd_acl_svcstats = { static const struct svc_version *nfsd_version[] = { [2] = &nfsd_version2, -#if defined(CONFIG_NFSD_V3) [3] = &nfsd_version3, -#endif #if defined(CONFIG_NFSD_V4) [4] = &nfsd_version4, #endif @@ -293,13 +291,13 @@ static int nfsd_init_socks(struct net *net, const struct cred *cred) if (!list_empty(&nn->nfsd_serv->sv_permsocks)) return 0; - error = svc_create_xprt(nn->nfsd_serv, "udp", net, PF_INET, NFS_PORT, - SVC_SOCK_DEFAULTS, cred); + error = svc_xprt_create(nn->nfsd_serv, "udp", net, PF_INET, NFS_PORT, + SVC_SOCK_DEFAULTS, cred); if (error < 0) return error; - error = svc_create_xprt(nn->nfsd_serv, "tcp", net, PF_INET, NFS_PORT, - SVC_SOCK_DEFAULTS, cred); + error = svc_xprt_create(nn->nfsd_serv, "tcp", net, PF_INET, NFS_PORT, + SVC_SOCK_DEFAULTS, cred); if (error < 0) return error; @@ -345,33 +343,57 @@ static bool nfsd_needs_lockd(struct nfsd_net *nn) return nfsd_vers(nn, 2, NFSD_TEST) || nfsd_vers(nn, 3, NFSD_TEST); } -void nfsd_copy_boot_verifier(__be32 verf[2], struct nfsd_net *nn) +/** + * nfsd_copy_write_verifier - Atomically copy a write verifier + * @verf: buffer in which to receive the verifier cookie + * @nn: NFS net namespace + * + * This function provides a wait-free mechanism for copying the + * namespace's write verifier without tearing it. + */ +void nfsd_copy_write_verifier(__be32 verf[2], struct nfsd_net *nn) { int seq = 0; do { - read_seqbegin_or_lock(&nn->boot_lock, &seq); - /* - * This is opaque to client, so no need to byte-swap. Use - * __force to keep sparse happy. y2038 time_t overflow is - * irrelevant in this usage - */ - verf[0] = (__force __be32)nn->nfssvc_boot.tv_sec; - verf[1] = (__force __be32)nn->nfssvc_boot.tv_nsec; - } while (need_seqretry(&nn->boot_lock, seq)); - done_seqretry(&nn->boot_lock, seq); + 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); } -static void nfsd_reset_boot_verifier_locked(struct nfsd_net *nn) +static void nfsd_reset_write_verifier_locked(struct nfsd_net *nn) { - ktime_get_real_ts64(&nn->nfssvc_boot); + struct timespec64 now; + u64 verf; + + /* + * Because the time value is hashed, y2038 time_t overflow + * is irrelevant in this usage. + */ + ktime_get_raw_ts64(&now); + verf = siphash_2u64(now.tv_sec, now.tv_nsec, &nn->siphash_key); + memcpy(nn->writeverf, &verf, sizeof(nn->writeverf)); } -void nfsd_reset_boot_verifier(struct nfsd_net *nn) +/** + * nfsd_reset_write_verifier - Generate a new write verifier + * @nn: NFS net namespace + * + * This function updates the ->writeverf field of @nn. This field + * contains an opaque cookie that, according to Section 18.32.3 of + * RFC 8881, "the client can use to determine whether a server has + * changed instance state (e.g., server restart) between a call to + * WRITE and a subsequent call to either WRITE or COMMIT. This + * cookie MUST be unchanged during a single instance of the NFSv4.1 + * server and MUST be unique between instances of the NFSv4.1 + * server." + */ +void nfsd_reset_write_verifier(struct nfsd_net *nn) { - write_seqlock(&nn->boot_lock); - nfsd_reset_boot_verifier_locked(nn); - write_sequnlock(&nn->boot_lock); + write_seqlock(&nn->writeverf_lock); + nfsd_reset_write_verifier_locked(nn); + write_sequnlock(&nn->writeverf_lock); } static int nfsd_startup_net(struct net *net, const struct cred *cred) @@ -435,6 +457,7 @@ static void nfsd_shutdown_net(struct net *net) nfsd_shutdown_generic(); } +static DEFINE_SPINLOCK(nfsd_notifier_lock); static int nfsd_inetaddr_event(struct notifier_block *this, unsigned long event, void *ptr) { @@ -444,18 +467,17 @@ static int nfsd_inetaddr_event(struct notifier_block *this, unsigned long event, struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct sockaddr_in sin; - if ((event != NETDEV_DOWN) || - !atomic_inc_not_zero(&nn->ntf_refcnt)) + if (event != NETDEV_DOWN || !nn->nfsd_serv) goto out; + spin_lock(&nfsd_notifier_lock); if (nn->nfsd_serv) { dprintk("nfsd_inetaddr_event: removed %pI4\n", &ifa->ifa_local); sin.sin_family = AF_INET; sin.sin_addr.s_addr = ifa->ifa_local; svc_age_temp_xprts_now(nn->nfsd_serv, (struct sockaddr *)&sin); } - atomic_dec(&nn->ntf_refcnt); - wake_up(&nn->ntf_wq); + spin_unlock(&nfsd_notifier_lock); out: return NOTIFY_DONE; @@ -475,10 +497,10 @@ static int nfsd_inet6addr_event(struct notifier_block *this, struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct sockaddr_in6 sin6; - if ((event != NETDEV_DOWN) || - !atomic_inc_not_zero(&nn->ntf_refcnt)) + if (event != NETDEV_DOWN || !nn->nfsd_serv) goto out; + spin_lock(&nfsd_notifier_lock); if (nn->nfsd_serv) { dprintk("nfsd_inet6addr_event: removed %pI6\n", &ifa->addr); sin6.sin6_family = AF_INET6; @@ -487,8 +509,8 @@ static int nfsd_inet6addr_event(struct notifier_block *this, sin6.sin6_scope_id = ifa->idev->dev->ifindex; svc_age_temp_xprts_now(nn->nfsd_serv, (struct sockaddr *)&sin6); } - atomic_dec(&nn->ntf_refcnt); - wake_up(&nn->ntf_wq); + spin_unlock(&nfsd_notifier_lock); + out: return NOTIFY_DONE; } @@ -505,7 +527,6 @@ static void nfsd_last_thread(struct svc_serv *serv, struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); - atomic_dec(&nn->ntf_refcnt); /* check if the notifier still has clients */ if (atomic_dec_return(&nfsd_notifier_refcount) == 0) { unregister_inetaddr_notifier(&nfsd_inetaddr_notifier); @@ -513,7 +534,6 @@ static void nfsd_last_thread(struct svc_serv *serv, struct net *net) unregister_inet6addr_notifier(&nfsd_inet6addr_notifier); #endif } - wait_event(nn->ntf_wq, atomic_read(&nn->ntf_refcnt) == 0); /* * write_ports can create the server without actually starting @@ -590,24 +610,6 @@ static int nfsd_get_default_max_blksize(void) return ret; } -static const struct svc_serv_ops nfsd_thread_sv_ops = { - .svo_shutdown = nfsd_last_thread, - .svo_function = nfsd, - .svo_enqueue_xprt = svc_xprt_do_enqueue, - .svo_setup = svc_set_num_threads, - .svo_module = THIS_MODULE, -}; - -static void nfsd_complete_shutdown(struct net *net) -{ - struct nfsd_net *nn = net_generic(net, nfsd_net_id); - - WARN_ON(!mutex_is_locked(&nfsd_mutex)); - - nn->nfsd_serv = NULL; - complete(&nn->nfsd_shutdown_complete); -} - void nfsd_shutdown_threads(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); @@ -622,11 +624,9 @@ void nfsd_shutdown_threads(struct net *net) svc_get(serv); /* Kill outstanding nfsd threads */ - serv->sv_ops->svo_setup(serv, NULL, 0); - nfsd_destroy(net); + svc_set_num_threads(serv, NULL, 0); + nfsd_put(net); mutex_unlock(&nfsd_mutex); - /* Wait for shutdown of nfsd_serv to complete */ - wait_for_completion(&nn->nfsd_shutdown_complete); } bool i_am_nfsd(void) @@ -638,6 +638,7 @@ int nfsd_create_serv(struct net *net) { int error; struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct svc_serv *serv; WARN_ON(!mutex_is_locked(&nfsd_mutex)); if (nn->nfsd_serv) { @@ -647,19 +648,22 @@ int nfsd_create_serv(struct net *net) if (nfsd_max_blksize == 0) nfsd_max_blksize = nfsd_get_default_max_blksize(); nfsd_reset_versions(nn); - nn->nfsd_serv = svc_create_pooled(&nfsd_program, nfsd_max_blksize, - &nfsd_thread_sv_ops); - if (nn->nfsd_serv == NULL) + serv = svc_create_pooled(&nfsd_program, nfsd_max_blksize, nfsd); + if (serv == NULL) return -ENOMEM; - init_completion(&nn->nfsd_shutdown_complete); - nn->nfsd_serv->sv_maxconn = nn->max_connections; - error = svc_bind(nn->nfsd_serv, net); + serv->sv_maxconn = nn->max_connections; + error = svc_bind(serv, net); if (error < 0) { - svc_destroy(nn->nfsd_serv); - nfsd_complete_shutdown(net); + /* NOT nfsd_put() as notifiers (see below) haven't + * been set up yet. + */ + svc_put(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 */ @@ -669,8 +673,7 @@ int nfsd_create_serv(struct net *net) register_inet6addr_notifier(&nfsd_inet6addr_notifier); #endif } - atomic_inc(&nn->ntf_refcnt); - nfsd_reset_boot_verifier(nn); + nfsd_reset_write_verifier(nn); return 0; } @@ -697,16 +700,27 @@ int nfsd_get_nrthreads(int n, int *nthreads, struct net *net) return 0; } -void nfsd_destroy(struct net *net) +/* 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. + */ +static void nfsd_noop(struct kref *ref) +{ +} + +void nfsd_put(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); - int destroy = (nn->nfsd_serv->sv_nrthreads == 1); - if (destroy) - svc_shutdown_net(nn->nfsd_serv, net); - svc_destroy(nn->nfsd_serv); - if (destroy) - nfsd_complete_shutdown(net); + 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) @@ -733,7 +747,7 @@ int nfsd_set_nrthreads(int n, int *nthreads, struct net *net) if (tot > NFSD_MAXSERVS) { /* total too large: scale down requested numbers */ for (i = 0; i < n && tot > 0; i++) { - int new = nthreads[i] * NFSD_MAXSERVS / tot; + int new = nthreads[i] * NFSD_MAXSERVS / tot; tot -= (nthreads[i] - new); nthreads[i] = new; } @@ -753,12 +767,13 @@ int nfsd_set_nrthreads(int n, int *nthreads, struct net *net) /* apply the new numbers */ svc_get(nn->nfsd_serv); for (i = 0; i < n; i++) { - err = nn->nfsd_serv->sv_ops->svo_setup(nn->nfsd_serv, - &nn->nfsd_serv->sv_pools[i], nthreads[i]); + err = svc_set_num_threads(nn->nfsd_serv, + &nn->nfsd_serv->sv_pools[i], + nthreads[i]); if (err) break; } - nfsd_destroy(net); + nfsd_put(net); return err; } @@ -784,7 +799,7 @@ nfsd_svc(int nrservs, struct net *net, const struct cred *cred) if (nrservs == 0 && nn->nfsd_serv == NULL) goto out; - strlcpy(nn->nfsd_name, utsname()->nodename, + strscpy(nn->nfsd_name, utsname()->nodename, sizeof(nn->nfsd_name)); error = nfsd_create_serv(net); @@ -795,21 +810,19 @@ nfsd_svc(int nrservs, struct net *net, const struct cred *cred) error = nfsd_startup_net(net, cred); if (error) - goto out_destroy; - error = nn->nfsd_serv->sv_ops->svo_setup(nn->nfsd_serv, - NULL, nrservs); + goto out_put; + error = svc_set_num_threads(nn->nfsd_serv, NULL, nrservs); if (error) goto out_shutdown; - /* We are holding a reference to nn->nfsd_serv which - * we don't want to count in the return value, - * so subtract 1 - */ - error = nn->nfsd_serv->sv_nrthreads - 1; + error = nn->nfsd_serv->sv_nrthreads; out_shutdown: if (error < 0 && !nfsd_up_before) nfsd_shutdown_net(net); -out_destroy: - nfsd_destroy(net); /* Release server */ +out_put: + /* Threads now hold service active */ + if (xchg(&nn->keep_active, 0)) + nfsd_put(net); + nfsd_put(net); out: mutex_unlock(&nfsd_mutex); return error; @@ -923,9 +936,6 @@ nfsd(void *vrqstp) struct nfsd_net *nn = net_generic(net, nfsd_net_id); int err; - /* Lock module and set up kernel thread */ - mutex_lock(&nfsd_mutex); - /* 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. */ @@ -945,8 +955,7 @@ nfsd(void *vrqstp) allow_signal(SIGINT); allow_signal(SIGQUIT); - nfsdstats.th_cnt++; - mutex_unlock(&nfsd_mutex); + atomic_inc(&nfsdstats.th_cnt); set_freezable(); @@ -973,20 +982,34 @@ nfsd(void *vrqstp) /* Clear signals before calling svc_exit_thread() */ flush_signals(current); - mutex_lock(&nfsd_mutex); - nfsdstats.th_cnt --; + atomic_dec(&nfsdstats.th_cnt); out: - rqstp->rq_server = NULL; + /* Take an extra ref so that the svc_put in svc_exit_thread() + * doesn't call svc_destroy() + */ + svc_get(nn->nfsd_serv); /* Release the thread */ svc_exit_thread(rqstp); - nfsd_destroy(net); + /* 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); + } - /* Release module */ - mutex_unlock(&nfsd_mutex); - module_put_and_exit(0); return 0; } @@ -1096,7 +1119,6 @@ int nfsd_pool_stats_open(struct inode *inode, struct file *file) mutex_unlock(&nfsd_mutex); return -ENODEV; } - /* bump up the psudo refcount while traversing */ svc_get(nn->nfsd_serv); ret = svc_pool_stats_open(nn->nfsd_serv, file); mutex_unlock(&nfsd_mutex); @@ -1109,8 +1131,7 @@ int nfsd_pool_stats_release(struct inode *inode, struct file *file) struct net *net = inode->i_sb->s_fs_info; mutex_lock(&nfsd_mutex); - /* this function really, really should have been called svc_put() */ - nfsd_destroy(net); + nfsd_put(net); mutex_unlock(&nfsd_mutex); return ret; } diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index aba8520b4b8b..caf6355b18fa 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -338,10 +338,8 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) return false; if (args->len > NFSSVC_MAXBLKSIZE_V2) return false; - if (!xdr_stream_subsegment(xdr, &args->payload, args->len)) - return false; - return true; + return xdr_stream_subsegment(xdr, &args->payload, args->len); } bool diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index e73bdbb1634a..e2daef3cc003 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -57,11 +57,11 @@ typedef struct { } stateid_t; typedef struct { - stateid_t stid; + stateid_t cs_stid; #define NFS4_COPY_STID 1 #define NFS4_COPYNOTIFY_STID 2 - unsigned char sc_type; - refcount_t sc_count; + unsigned char cs_type; + refcount_t cs_count; } copy_stateid_t; struct nfsd4_callback { @@ -149,6 +149,7 @@ struct nfs4_delegation { /* For recall: */ int dl_retries; struct nfsd4_callback dl_recall; + bool dl_recalled; }; #define cb_to_delegation(cb) \ @@ -174,7 +175,7 @@ static inline struct nfs4_delegation *delegstateid(struct nfs4_stid *s) /* 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 16 +#define NFSD_MAX_OPS_PER_COMPOUND 50 /* Maximum session per slot cache size */ #define NFSD_SLOT_CACHE_SIZE 2048 /* Maximum number of NFSD_SLOT_CACHE_SIZE slots per session */ @@ -283,6 +284,28 @@ struct nfsd4_sessionid { #define HEXDIR_LEN 33 /* hex version of 16 byte md5 of cl_name plus '\0' */ /* + * State Meaning Where set + * -------------------------------------------------------------------------- + * | NFSD4_ACTIVE | Confirmed, active | Default | + * |------------------- ----------------------------------------------------| + * | NFSD4_COURTESY | Courtesy state. | nfs4_get_client_reaplist | + * | | Lease/lock/share | | + * | | reservation conflict | | + * | | can cause Courtesy | | + * | | client to be expired | | + * |------------------------------------------------------------------------| + * | NFSD4_EXPIRABLE | Courtesy client to be| nfs4_laundromat | + * | | expired by Laundromat| try_to_expire_client | + * | | due to conflict | | + * |------------------------------------------------------------------------| + */ +enum { + NFSD4_ACTIVE = 0, + NFSD4_COURTESY, + NFSD4_EXPIRABLE, +}; + +/* * struct nfs4_client - one per client. Clientids live here. * * The initial object created by an NFS client using SETCLIENTID (for NFSv4.0) @@ -385,6 +408,9 @@ struct nfs4_client { struct list_head async_copies; /* list of async copies */ spinlock_t async_lock; /* lock for async copies */ atomic_t cl_cb_inflight; /* Outstanding callbacks */ + + unsigned int cl_state; + atomic_t cl_delegs_in_recall; }; /* struct nfs4_client_reset @@ -568,6 +594,10 @@ struct nfs4_ol_stateid { struct list_head st_locks; struct nfs4_stateowner *st_stateowner; struct nfs4_clnt_odstate *st_clnt_odstate; +/* + * These bitmasks use 3 separate bits for READ, ALLOW, and BOTH; see the + * comment above bmap_to_share_mode() for explanation: + */ unsigned char st_access_bmap; unsigned char st_deny_bmap; struct nfs4_ol_stateid *st_openstp; @@ -629,6 +659,7 @@ struct nfsd4_blocked_lock { struct file_lock nbl_lock; struct knfsd_fh nbl_fh; struct nfsd4_callback nbl_cb; + struct kref nbl_kref; }; struct nfsd4_compound_state; @@ -661,18 +692,16 @@ 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 nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp, const struct nfsd4_callback_ops *ops, enum nfsd4_cb_op op); -extern void nfsd4_run_cb(struct nfsd4_callback *cb); +extern bool nfsd4_run_cb(struct nfsd4_callback *cb); extern int nfsd4_create_callback_queue(void); extern void nfsd4_destroy_callback_queue(void); extern void nfsd4_shutdown_callback(struct nfs4_client *); extern void nfsd4_shutdown_copy(struct nfs4_client *clp); -extern void nfsd4_prepare_cb_recall(struct nfs4_delegation *dp); 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 void nfs4_put_copy(struct nfsd4_copy *copy); extern struct nfsd4_copy * find_async_copy(struct nfs4_client *clp, stateid_t *staetid); extern void nfs4_put_cpntf_state(struct nfsd_net *nn, @@ -697,4 +726,9 @@ extern void nfsd4_client_record_remove(struct nfs4_client *clp); extern int nfsd4_client_record_check(struct nfs4_client *clp); extern void nfsd4_record_grace_done(struct nfsd_net *nn); +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; +} #endif /* NFSD4_STATE_H */ diff --git a/fs/nfsd/stats.c b/fs/nfsd/stats.c index 1d3b881e7382..777e24e5da33 100644 --- a/fs/nfsd/stats.c +++ b/fs/nfsd/stats.c @@ -32,7 +32,7 @@ struct svc_stat nfsd_svcstats = { .program = &nfsd_program, }; -static int nfsd_proc_show(struct seq_file *seq, void *v) +static int nfsd_show(struct seq_file *seq, void *v) { int i; @@ -45,7 +45,7 @@ static int nfsd_proc_show(struct seq_file *seq, void *v) percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_IO_WRITE])); /* thread usage: */ - seq_printf(seq, "th %u 0", nfsdstats.th_cnt); + seq_printf(seq, "th %u 0", atomic_read(&nfsdstats.th_cnt)); /* deprecated thread usage histogram stats */ for (i = 0; i < 10; i++) @@ -72,17 +72,7 @@ static int nfsd_proc_show(struct seq_file *seq, void *v) return 0; } -static int nfsd_proc_open(struct inode *inode, struct file *file) -{ - return single_open(file, nfsd_proc_show, NULL); -} - -static const struct proc_ops nfsd_proc_ops = { - .proc_open = nfsd_proc_open, - .proc_read = seq_read, - .proc_lseek = seq_lseek, - .proc_release = single_release, -}; +DEFINE_PROC_SHOW_ATTRIBUTE(nfsd); int nfsd_percpu_counters_init(struct percpu_counter counters[], int num) { diff --git a/fs/nfsd/stats.h b/fs/nfsd/stats.h index 51ecda852e23..9b43dc3d9991 100644 --- a/fs/nfsd/stats.h +++ b/fs/nfsd/stats.h @@ -29,11 +29,9 @@ enum { struct nfsd_stats { struct percpu_counter counter[NFSD_STATS_COUNTERS_NUM]; - /* Protected by nfsd_mutex */ - unsigned int th_cnt; /* number of available threads */ + atomic_t th_cnt; /* number of available threads */ }; - extern struct nfsd_stats nfsdstats; extern struct svc_stat nfsd_svcstats; diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index f1e0d3c51bc2..06a96e955bd0 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -13,22 +13,6 @@ #include "export.h" #include "nfsfh.h" -#define NFSD_TRACE_PROC_ARG_FIELDS \ - __field(unsigned int, netns_ino) \ - __field(u32, xid) \ - __array(unsigned char, server, sizeof(struct sockaddr_in6)) \ - __array(unsigned char, client, sizeof(struct sockaddr_in6)) - -#define NFSD_TRACE_PROC_ARG_ASSIGNMENTS \ - do { \ - __entry->netns_ino = SVC_NET(rqstp)->ns.inum; \ - __entry->xid = be32_to_cpu(rqstp->rq_xid); \ - 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); \ - } while (0); - #define NFSD_TRACE_PROC_RES_FIELDS \ __field(unsigned int, netns_ino) \ __field(u32, xid) \ @@ -47,49 +31,41 @@ rqstp->rq_xprt->xpt_remotelen); \ } while (0); -TRACE_EVENT(nfsd_garbage_args_err, +DECLARE_EVENT_CLASS(nfsd_xdr_err_class, TP_PROTO( const struct svc_rqst *rqstp ), TP_ARGS(rqstp), TP_STRUCT__entry( - NFSD_TRACE_PROC_ARG_FIELDS - + __field(unsigned int, netns_ino) + __field(u32, xid) __field(u32, vers) __field(u32, proc) + __sockaddr(server, rqstp->rq_xprt->xpt_locallen) + __sockaddr(client, rqstp->rq_xprt->xpt_remotelen) ), TP_fast_assign( - NFSD_TRACE_PROC_ARG_ASSIGNMENTS + const struct svc_xprt *xprt = rqstp->rq_xprt; + __entry->netns_ino = xprt->xpt_net->ns.inum; + __entry->xid = be32_to_cpu(rqstp->rq_xid); __entry->vers = rqstp->rq_vers; __entry->proc = rqstp->rq_proc; + __assign_sockaddr(server, &xprt->xpt_local, xprt->xpt_locallen); + __assign_sockaddr(client, &xprt->xpt_remote, xprt->xpt_remotelen); ), TP_printk("xid=0x%08x vers=%u proc=%u", __entry->xid, __entry->vers, __entry->proc ) ); -TRACE_EVENT(nfsd_cant_encode_err, - TP_PROTO( - const struct svc_rqst *rqstp - ), - TP_ARGS(rqstp), - TP_STRUCT__entry( - NFSD_TRACE_PROC_ARG_FIELDS +#define DEFINE_NFSD_XDR_ERR_EVENT(name) \ +DEFINE_EVENT(nfsd_xdr_err_class, nfsd_##name##_err, \ + TP_PROTO(const struct svc_rqst *rqstp), \ + TP_ARGS(rqstp)) - __field(u32, vers) - __field(u32, proc) - ), - TP_fast_assign( - NFSD_TRACE_PROC_ARG_ASSIGNMENTS - - __entry->vers = rqstp->rq_vers; - __entry->proc = rqstp->rq_proc; - ), - TP_printk("xid=0x%08x vers=%u proc=%u", - __entry->xid, __entry->vers, __entry->proc - ) -); +DEFINE_NFSD_XDR_ERR_EVENT(garbage_args); +DEFINE_NFSD_XDR_ERR_EVENT(cant_encode); #define show_nfsd_may_flags(x) \ __print_flags(x, "|", \ @@ -108,19 +84,26 @@ TRACE_EVENT(nfsd_cant_encode_err, { NFSD_MAY_64BIT_COOKIE, "64BIT_COOKIE" }) TRACE_EVENT(nfsd_compound, - TP_PROTO(const struct svc_rqst *rqst, - u32 args_opcnt), - TP_ARGS(rqst, args_opcnt), + TP_PROTO( + const struct svc_rqst *rqst, + const char *tag, + u32 taglen, + u32 opcnt + ), + TP_ARGS(rqst, tag, taglen, opcnt), TP_STRUCT__entry( __field(u32, xid) - __field(u32, args_opcnt) + __field(u32, opcnt) + __string_len(tag, tag, taglen) ), TP_fast_assign( __entry->xid = be32_to_cpu(rqst->rq_xid); - __entry->args_opcnt = args_opcnt; + __entry->opcnt = opcnt; + __assign_str_len(tag, tag, taglen); ), - TP_printk("xid=0x%08x opcnt=%u", - __entry->xid, __entry->args_opcnt) + TP_printk("xid=0x%08x opcnt=%u tag=%s", + __entry->xid, __entry->opcnt, __get_str(tag) + ) ) TRACE_EVENT(nfsd_compound_status, @@ -195,6 +178,94 @@ TRACE_EVENT(nfsd_compound_encode_err, __entry->opnum, __entry->status) ); +#define show_fs_file_type(x) \ + __print_symbolic(x, \ + { S_IFLNK, "LNK" }, \ + { S_IFREG, "REG" }, \ + { S_IFDIR, "DIR" }, \ + { S_IFCHR, "CHR" }, \ + { S_IFBLK, "BLK" }, \ + { S_IFIFO, "FIFO" }, \ + { S_IFSOCK, "SOCK" }) + +TRACE_EVENT(nfsd_fh_verify, + TP_PROTO( + const struct svc_rqst *rqstp, + const struct svc_fh *fhp, + umode_t type, + int access + ), + TP_ARGS(rqstp, fhp, type, access), + TP_STRUCT__entry( + __field(unsigned int, netns_ino) + __sockaddr(server, rqstp->rq_xprt->xpt_remotelen) + __sockaddr(client, rqstp->rq_xprt->xpt_remotelen) + __field(u32, xid) + __field(u32, fh_hash) + __field(const void *, inode) + __field(unsigned long, type) + __field(unsigned long, access) + ), + TP_fast_assign( + __entry->netns_ino = SVC_NET(rqstp)->ns.inum; + __assign_sockaddr(server, &rqstp->rq_xprt->xpt_local, + rqstp->rq_xprt->xpt_locallen); + __assign_sockaddr(client, &rqstp->rq_xprt->xpt_remote, + rqstp->rq_xprt->xpt_remotelen); + __entry->xid = be32_to_cpu(rqstp->rq_xid); + __entry->fh_hash = knfsd_fh_hash(&fhp->fh_handle); + __entry->inode = d_inode(fhp->fh_dentry); + __entry->type = type; + __entry->access = access; + ), + TP_printk("xid=0x%08x fh_hash=0x%08x type=%s access=%s", + __entry->xid, __entry->fh_hash, + show_fs_file_type(__entry->type), + show_nfsd_may_flags(__entry->access) + ) +); + +TRACE_EVENT_CONDITION(nfsd_fh_verify_err, + TP_PROTO( + const struct svc_rqst *rqstp, + const struct svc_fh *fhp, + umode_t type, + int access, + __be32 error + ), + TP_ARGS(rqstp, fhp, type, access, error), + TP_CONDITION(error), + TP_STRUCT__entry( + __field(unsigned int, netns_ino) + __sockaddr(server, rqstp->rq_xprt->xpt_remotelen) + __sockaddr(client, rqstp->rq_xprt->xpt_remotelen) + __field(u32, xid) + __field(u32, fh_hash) + __field(const void *, inode) + __field(unsigned long, type) + __field(unsigned long, access) + __field(int, error) + ), + TP_fast_assign( + __entry->netns_ino = SVC_NET(rqstp)->ns.inum; + __assign_sockaddr(server, &rqstp->rq_xprt->xpt_local, + rqstp->rq_xprt->xpt_locallen); + __assign_sockaddr(client, &rqstp->rq_xprt->xpt_remote, + rqstp->rq_xprt->xpt_remotelen); + __entry->xid = be32_to_cpu(rqstp->rq_xid); + __entry->fh_hash = knfsd_fh_hash(&fhp->fh_handle); + __entry->inode = d_inode(fhp->fh_dentry); + __entry->type = type; + __entry->access = access; + __entry->error = be32_to_cpu(error); + ), + TP_printk("xid=0x%08x fh_hash=0x%08x type=%s access=%s error=%d", + __entry->xid, __entry->fh_hash, + show_fs_file_type(__entry->type), + show_nfsd_may_flags(__entry->access), + __entry->error + ) +); DECLARE_EVENT_CLASS(nfsd_fh_err_class, TP_PROTO(struct svc_rqst *rqstp, @@ -320,14 +391,14 @@ TRACE_EVENT(nfsd_export_update, DECLARE_EVENT_CLASS(nfsd_io_class, TP_PROTO(struct svc_rqst *rqstp, struct svc_fh *fhp, - loff_t offset, - unsigned long len), + u64 offset, + u32 len), TP_ARGS(rqstp, fhp, offset, len), TP_STRUCT__entry( __field(u32, xid) __field(u32, fh_hash) - __field(loff_t, offset) - __field(unsigned long, len) + __field(u64, offset) + __field(u32, len) ), TP_fast_assign( __entry->xid = be32_to_cpu(rqstp->rq_xid); @@ -335,7 +406,7 @@ DECLARE_EVENT_CLASS(nfsd_io_class, __entry->offset = offset; __entry->len = len; ), - TP_printk("xid=0x%08x fh_hash=0x%08x offset=%lld len=%lu", + TP_printk("xid=0x%08x fh_hash=0x%08x offset=%llu len=%u", __entry->xid, __entry->fh_hash, __entry->offset, __entry->len) ) @@ -344,8 +415,8 @@ DECLARE_EVENT_CLASS(nfsd_io_class, DEFINE_EVENT(nfsd_io_class, nfsd_##name, \ TP_PROTO(struct svc_rqst *rqstp, \ struct svc_fh *fhp, \ - loff_t offset, \ - unsigned long len), \ + u64 offset, \ + u32 len), \ TP_ARGS(rqstp, fhp, offset, len)) DEFINE_NFSD_IO_EVENT(read_start); @@ -413,10 +484,83 @@ TRACE_EVENT(nfsd_dirent, ) ) +DECLARE_EVENT_CLASS(nfsd_copy_err_class, + TP_PROTO(struct svc_rqst *rqstp, + struct svc_fh *src_fhp, + loff_t src_offset, + struct svc_fh *dst_fhp, + loff_t dst_offset, + u64 count, + int status), + TP_ARGS(rqstp, src_fhp, src_offset, dst_fhp, dst_offset, count, status), + TP_STRUCT__entry( + __field(u32, xid) + __field(u32, src_fh_hash) + __field(loff_t, src_offset) + __field(u32, dst_fh_hash) + __field(loff_t, dst_offset) + __field(u64, count) + __field(int, status) + ), + TP_fast_assign( + __entry->xid = be32_to_cpu(rqstp->rq_xid); + __entry->src_fh_hash = knfsd_fh_hash(&src_fhp->fh_handle); + __entry->src_offset = src_offset; + __entry->dst_fh_hash = knfsd_fh_hash(&dst_fhp->fh_handle); + __entry->dst_offset = dst_offset; + __entry->count = count; + __entry->status = status; + ), + TP_printk("xid=0x%08x src_fh_hash=0x%08x src_offset=%lld " + "dst_fh_hash=0x%08x dst_offset=%lld " + "count=%llu status=%d", + __entry->xid, __entry->src_fh_hash, __entry->src_offset, + __entry->dst_fh_hash, __entry->dst_offset, + (unsigned long long)__entry->count, + __entry->status) +) + +#define DEFINE_NFSD_COPY_ERR_EVENT(name) \ +DEFINE_EVENT(nfsd_copy_err_class, nfsd_##name, \ + TP_PROTO(struct svc_rqst *rqstp, \ + struct svc_fh *src_fhp, \ + loff_t src_offset, \ + struct svc_fh *dst_fhp, \ + loff_t dst_offset, \ + u64 count, \ + int status), \ + TP_ARGS(rqstp, src_fhp, src_offset, dst_fhp, dst_offset, \ + count, status)) + +DEFINE_NFSD_COPY_ERR_EVENT(clone_file_range_err); + #include "state.h" #include "filecache.h" #include "vfs.h" +TRACE_EVENT(nfsd_delegret_wakeup, + TP_PROTO( + const struct svc_rqst *rqstp, + const struct inode *inode, + long timeo + ), + TP_ARGS(rqstp, inode, timeo), + TP_STRUCT__entry( + __field(u32, xid) + __field(const void *, inode) + __field(long, timeo) + ), + TP_fast_assign( + __entry->xid = be32_to_cpu(rqstp->rq_xid); + __entry->inode = inode; + __entry->timeo = timeo; + ), + TP_printk("xid=0x%08x inode=%p%s", + __entry->xid, __entry->inode, + __entry->timeo == 0 ? " (timed out)" : "" + ) +); + DECLARE_EVENT_CLASS(nfsd_stateid_class, TP_PROTO(stateid_t *stp), TP_ARGS(stp), @@ -538,6 +682,34 @@ DEFINE_EVENT(nfsd_net_class, nfsd_##name, \ DEFINE_NET_EVENT(grace_start); DEFINE_NET_EVENT(grace_complete); +TRACE_EVENT(nfsd_writeverf_reset, + TP_PROTO( + const struct nfsd_net *nn, + const struct svc_rqst *rqstp, + int error + ), + TP_ARGS(nn, rqstp, error), + TP_STRUCT__entry( + __field(unsigned long long, boot_time) + __field(u32, xid) + __field(int, error) + __array(unsigned char, verifier, NFS4_VERIFIER_SIZE) + ), + TP_fast_assign( + __entry->boot_time = nn->boot_time; + __entry->xid = be32_to_cpu(rqstp->rq_xid); + __entry->error = error; + + /* avoid seqlock inside TP_fast_assign */ + memcpy(__entry->verifier, nn->writeverf, + NFS4_VERIFIER_SIZE); + ), + TP_printk("boot_time=%16llx xid=0x%08x error=%d new verifier=0x%s", + __entry->boot_time, __entry->xid, __entry->error, + __print_hex_str(__entry->verifier, NFS4_VERIFIER_SIZE) + ) +); + TRACE_EVENT(nfsd_clid_cred_mismatch, TP_PROTO( const struct nfs4_client *clp, @@ -549,20 +721,21 @@ TRACE_EVENT(nfsd_clid_cred_mismatch, __field(u32, cl_id) __field(unsigned long, cl_flavor) __field(unsigned long, new_flavor) - __array(unsigned char, addr, sizeof(struct sockaddr_in6)) + __sockaddr(addr, rqstp->rq_xprt->xpt_remotelen) ), TP_fast_assign( __entry->cl_boot = clp->cl_clientid.cl_boot; __entry->cl_id = clp->cl_clientid.cl_id; __entry->cl_flavor = clp->cl_cred.cr_flavor; __entry->new_flavor = rqstp->rq_cred.cr_flavor; - memcpy(__entry->addr, &rqstp->rq_xprt->xpt_remote, - sizeof(struct sockaddr_in6)); + __assign_sockaddr(addr, &rqstp->rq_xprt->xpt_remote, + rqstp->rq_xprt->xpt_remotelen); ), TP_printk("client %08x:%08x flavor=%s, conflict=%s from addr=%pISpc", __entry->cl_boot, __entry->cl_id, show_nfsd_authflavor(__entry->cl_flavor), - show_nfsd_authflavor(__entry->new_flavor), __entry->addr + show_nfsd_authflavor(__entry->new_flavor), + __get_sockaddr(addr) ) ) @@ -578,7 +751,7 @@ TRACE_EVENT(nfsd_clid_verf_mismatch, __field(u32, cl_id) __array(unsigned char, cl_verifier, NFS4_VERIFIER_SIZE) __array(unsigned char, new_verifier, NFS4_VERIFIER_SIZE) - __array(unsigned char, addr, sizeof(struct sockaddr_in6)) + __sockaddr(addr, rqstp->rq_xprt->xpt_remotelen) ), TP_fast_assign( __entry->cl_boot = clp->cl_clientid.cl_boot; @@ -587,14 +760,14 @@ TRACE_EVENT(nfsd_clid_verf_mismatch, NFS4_VERIFIER_SIZE); memcpy(__entry->new_verifier, (void *)verf, NFS4_VERIFIER_SIZE); - memcpy(__entry->addr, &rqstp->rq_xprt->xpt_remote, - sizeof(struct sockaddr_in6)); + __assign_sockaddr(addr, &rqstp->rq_xprt->xpt_remote, + rqstp->rq_xprt->xpt_remotelen); ), TP_printk("client %08x:%08x verf=0x%s, updated=0x%s from addr=%pISpc", __entry->cl_boot, __entry->cl_id, __print_hex_str(__entry->cl_verifier, NFS4_VERIFIER_SIZE), __print_hex_str(__entry->new_verifier, NFS4_VERIFIER_SIZE), - __entry->addr + __get_sockaddr(addr) ) ); @@ -637,25 +810,16 @@ DEFINE_CLID_EVENT(confirmed_r); /* * from fs/nfsd/filecache.h */ -TRACE_DEFINE_ENUM(NFSD_FILE_HASHED); -TRACE_DEFINE_ENUM(NFSD_FILE_PENDING); -TRACE_DEFINE_ENUM(NFSD_FILE_BREAK_READ); -TRACE_DEFINE_ENUM(NFSD_FILE_BREAK_WRITE); -TRACE_DEFINE_ENUM(NFSD_FILE_REFERENCED); - #define show_nf_flags(val) \ __print_flags(val, "|", \ { 1 << NFSD_FILE_HASHED, "HASHED" }, \ { 1 << NFSD_FILE_PENDING, "PENDING" }, \ - { 1 << NFSD_FILE_BREAK_READ, "BREAK_READ" }, \ - { 1 << NFSD_FILE_BREAK_WRITE, "BREAK_WRITE" }, \ { 1 << NFSD_FILE_REFERENCED, "REFERENCED"}) DECLARE_EVENT_CLASS(nfsd_file_class, TP_PROTO(struct nfsd_file *nf), TP_ARGS(nf), TP_STRUCT__entry( - __field(unsigned int, nf_hashval) __field(void *, nf_inode) __field(int, nf_ref) __field(unsigned long, nf_flags) @@ -663,15 +827,13 @@ DECLARE_EVENT_CLASS(nfsd_file_class, __field(struct file *, nf_file) ), TP_fast_assign( - __entry->nf_hashval = nf->nf_hashval; __entry->nf_inode = nf->nf_inode; __entry->nf_ref = refcount_read(&nf->nf_ref); __entry->nf_flags = nf->nf_flags; __entry->nf_may = nf->nf_may; __entry->nf_file = nf->nf_file; ), - TP_printk("hash=0x%x inode=%p ref=%d flags=%s may=%s file=%p", - __entry->nf_hashval, + TP_printk("inode=%p ref=%d flags=%s may=%s nf_file=%p", __entry->nf_inode, __entry->nf_ref, show_nf_flags(__entry->nf_flags), @@ -684,34 +846,59 @@ DEFINE_EVENT(nfsd_file_class, name, \ TP_PROTO(struct nfsd_file *nf), \ TP_ARGS(nf)) -DEFINE_NFSD_FILE_EVENT(nfsd_file_alloc); DEFINE_NFSD_FILE_EVENT(nfsd_file_put_final); DEFINE_NFSD_FILE_EVENT(nfsd_file_unhash); DEFINE_NFSD_FILE_EVENT(nfsd_file_put); -DEFINE_NFSD_FILE_EVENT(nfsd_file_unhash_and_release_locked); +DEFINE_NFSD_FILE_EVENT(nfsd_file_unhash_and_dispose); + +TRACE_EVENT(nfsd_file_alloc, + TP_PROTO( + const struct nfsd_file *nf + ), + TP_ARGS(nf), + TP_STRUCT__entry( + __field(const void *, nf_inode) + __field(unsigned long, nf_flags) + __field(unsigned long, nf_may) + __field(unsigned int, nf_ref) + ), + TP_fast_assign( + __entry->nf_inode = nf->nf_inode; + __entry->nf_flags = nf->nf_flags; + __entry->nf_ref = refcount_read(&nf->nf_ref); + __entry->nf_may = nf->nf_may; + ), + TP_printk("inode=%p ref=%u flags=%s may=%s", + __entry->nf_inode, __entry->nf_ref, + show_nf_flags(__entry->nf_flags), + show_nfsd_may_flags(__entry->nf_may) + ) +); TRACE_EVENT(nfsd_file_acquire, - TP_PROTO(struct svc_rqst *rqstp, unsigned int hash, - struct inode *inode, unsigned int may_flags, - struct nfsd_file *nf, __be32 status), + TP_PROTO( + const struct svc_rqst *rqstp, + const struct inode *inode, + unsigned int may_flags, + const struct nfsd_file *nf, + __be32 status + ), - TP_ARGS(rqstp, hash, inode, may_flags, nf, status), + TP_ARGS(rqstp, inode, may_flags, nf, status), TP_STRUCT__entry( __field(u32, xid) - __field(unsigned int, hash) - __field(void *, inode) + __field(const void *, inode) __field(unsigned long, may_flags) - __field(int, nf_ref) + __field(unsigned int, nf_ref) __field(unsigned long, nf_flags) __field(unsigned long, nf_may) - __field(struct file *, nf_file) + __field(const void *, nf_file) __field(u32, status) ), TP_fast_assign( __entry->xid = be32_to_cpu(rqstp->rq_xid); - __entry->hash = hash; __entry->inode = inode; __entry->may_flags = may_flags; __entry->nf_ref = nf ? refcount_read(&nf->nf_ref) : 0; @@ -721,39 +908,186 @@ TRACE_EVENT(nfsd_file_acquire, __entry->status = be32_to_cpu(status); ), - TP_printk("xid=0x%x hash=0x%x inode=%p may_flags=%s ref=%d nf_flags=%s nf_may=%s nf_file=%p status=%u", - __entry->xid, __entry->hash, __entry->inode, + TP_printk("xid=0x%x inode=%p may_flags=%s ref=%u nf_flags=%s nf_may=%s nf_file=%p status=%u", + __entry->xid, __entry->inode, show_nfsd_may_flags(__entry->may_flags), __entry->nf_ref, show_nf_flags(__entry->nf_flags), show_nfsd_may_flags(__entry->nf_may), - __entry->nf_file, __entry->status) + __entry->nf_file, __entry->status + ) +); + +TRACE_EVENT(nfsd_file_create, + TP_PROTO( + const struct svc_rqst *rqstp, + unsigned int may_flags, + const struct nfsd_file *nf + ), + + TP_ARGS(rqstp, may_flags, nf), + + TP_STRUCT__entry( + __field(const void *, nf_inode) + __field(const void *, nf_file) + __field(unsigned long, may_flags) + __field(unsigned long, nf_flags) + __field(unsigned long, nf_may) + __field(unsigned int, nf_ref) + __field(u32, xid) + ), + + TP_fast_assign( + __entry->nf_inode = nf->nf_inode; + __entry->nf_file = nf->nf_file; + __entry->may_flags = may_flags; + __entry->nf_flags = nf->nf_flags; + __entry->nf_may = nf->nf_may; + __entry->nf_ref = refcount_read(&nf->nf_ref); + __entry->xid = be32_to_cpu(rqstp->rq_xid); + ), + + TP_printk("xid=0x%x inode=%p may_flags=%s ref=%u nf_flags=%s nf_may=%s nf_file=%p", + __entry->xid, __entry->nf_inode, + show_nfsd_may_flags(__entry->may_flags), + __entry->nf_ref, show_nf_flags(__entry->nf_flags), + show_nfsd_may_flags(__entry->nf_may), __entry->nf_file + ) +); + +TRACE_EVENT(nfsd_file_insert_err, + TP_PROTO( + const struct svc_rqst *rqstp, + const struct inode *inode, + unsigned int may_flags, + long error + ), + TP_ARGS(rqstp, inode, may_flags, error), + TP_STRUCT__entry( + __field(u32, xid) + __field(const void *, inode) + __field(unsigned long, may_flags) + __field(long, error) + ), + TP_fast_assign( + __entry->xid = be32_to_cpu(rqstp->rq_xid); + __entry->inode = inode; + __entry->may_flags = may_flags; + __entry->error = error; + ), + TP_printk("xid=0x%x inode=%p may_flags=%s error=%ld", + __entry->xid, __entry->inode, + show_nfsd_may_flags(__entry->may_flags), + __entry->error + ) +); + +TRACE_EVENT(nfsd_file_cons_err, + TP_PROTO( + const struct svc_rqst *rqstp, + const struct inode *inode, + unsigned int may_flags, + const struct nfsd_file *nf + ), + TP_ARGS(rqstp, inode, may_flags, nf), + TP_STRUCT__entry( + __field(u32, xid) + __field(const void *, inode) + __field(unsigned long, may_flags) + __field(unsigned int, nf_ref) + __field(unsigned long, nf_flags) + __field(unsigned long, nf_may) + __field(const void *, nf_file) + ), + TP_fast_assign( + __entry->xid = be32_to_cpu(rqstp->rq_xid); + __entry->inode = inode; + __entry->may_flags = may_flags; + __entry->nf_ref = refcount_read(&nf->nf_ref); + __entry->nf_flags = nf->nf_flags; + __entry->nf_may = nf->nf_may; + __entry->nf_file = nf->nf_file; + ), + TP_printk("xid=0x%x inode=%p may_flags=%s ref=%u nf_flags=%s nf_may=%s nf_file=%p", + __entry->xid, __entry->inode, + show_nfsd_may_flags(__entry->may_flags), __entry->nf_ref, + show_nf_flags(__entry->nf_flags), + show_nfsd_may_flags(__entry->nf_may), __entry->nf_file + ) ); +TRACE_EVENT(nfsd_file_open, + TP_PROTO(struct nfsd_file *nf, __be32 status), + TP_ARGS(nf, status), + TP_STRUCT__entry( + __field(void *, nf_inode) /* cannot be dereferenced */ + __field(int, nf_ref) + __field(unsigned long, nf_flags) + __field(unsigned long, nf_may) + __field(void *, nf_file) /* cannot be dereferenced */ + ), + TP_fast_assign( + __entry->nf_inode = nf->nf_inode; + __entry->nf_ref = refcount_read(&nf->nf_ref); + __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 file=%p", + __entry->nf_inode, + __entry->nf_ref, + show_nf_flags(__entry->nf_flags), + show_nfsd_may_flags(__entry->nf_may), + __entry->nf_file) +) + DECLARE_EVENT_CLASS(nfsd_file_search_class, - TP_PROTO(struct inode *inode, unsigned int hash, int found), - TP_ARGS(inode, hash, found), + TP_PROTO( + const struct inode *inode, + unsigned int count + ), + TP_ARGS(inode, count), TP_STRUCT__entry( - __field(struct inode *, inode) - __field(unsigned int, hash) - __field(int, found) + __field(const struct inode *, inode) + __field(unsigned int, count) ), TP_fast_assign( __entry->inode = inode; - __entry->hash = hash; - __entry->found = found; + __entry->count = count; ), - TP_printk("hash=0x%x inode=%p found=%d", __entry->hash, - __entry->inode, __entry->found) + TP_printk("inode=%p count=%u", + __entry->inode, __entry->count) ); #define DEFINE_NFSD_FILE_SEARCH_EVENT(name) \ DEFINE_EVENT(nfsd_file_search_class, name, \ - TP_PROTO(struct inode *inode, unsigned int hash, int found), \ - TP_ARGS(inode, hash, found)) + TP_PROTO( \ + const struct inode *inode, \ + unsigned int count \ + ), \ + TP_ARGS(inode, count)) DEFINE_NFSD_FILE_SEARCH_EVENT(nfsd_file_close_inode_sync); DEFINE_NFSD_FILE_SEARCH_EVENT(nfsd_file_close_inode); -DEFINE_NFSD_FILE_SEARCH_EVENT(nfsd_file_is_cached); + +TRACE_EVENT(nfsd_file_is_cached, + TP_PROTO( + const struct inode *inode, + int found + ), + TP_ARGS(inode, found), + TP_STRUCT__entry( + __field(const struct inode *, inode) + __field(int, found) + ), + TP_fast_assign( + __entry->inode = inode; + __entry->found = found; + ), + TP_printk("inode=%p is %scached", + __entry->inode, + __entry->found ? "" : "not " + ) +); TRACE_EVENT(nfsd_file_fsnotify_handle_event, TP_PROTO(struct inode *inode, u32 mask), @@ -774,6 +1108,76 @@ TRACE_EVENT(nfsd_file_fsnotify_handle_event, __entry->nlink, __entry->mode, __entry->mask) ); +DECLARE_EVENT_CLASS(nfsd_file_gc_class, + TP_PROTO( + const struct nfsd_file *nf + ), + TP_ARGS(nf), + TP_STRUCT__entry( + __field(void *, nf_inode) + __field(void *, nf_file) + __field(int, nf_ref) + __field(unsigned long, nf_flags) + ), + TP_fast_assign( + __entry->nf_inode = nf->nf_inode; + __entry->nf_file = nf->nf_file; + __entry->nf_ref = refcount_read(&nf->nf_ref); + __entry->nf_flags = nf->nf_flags; + ), + TP_printk("inode=%p ref=%d nf_flags=%s nf_file=%p", + __entry->nf_inode, __entry->nf_ref, + show_nf_flags(__entry->nf_flags), + __entry->nf_file + ) +); + +#define DEFINE_NFSD_FILE_GC_EVENT(name) \ +DEFINE_EVENT(nfsd_file_gc_class, name, \ + TP_PROTO( \ + const struct nfsd_file *nf \ + ), \ + 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_hashed); +DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_gc_disposed); + +DECLARE_EVENT_CLASS(nfsd_file_lruwalk_class, + TP_PROTO( + unsigned long removed, + unsigned long remaining + ), + TP_ARGS(removed, remaining), + TP_STRUCT__entry( + __field(unsigned long, removed) + __field(unsigned long, remaining) + ), + TP_fast_assign( + __entry->removed = removed; + __entry->remaining = remaining; + ), + TP_printk("%lu entries removed, %lu remaining", + __entry->removed, __entry->remaining) +); + +#define DEFINE_NFSD_FILE_LRUWALK_EVENT(name) \ +DEFINE_EVENT(nfsd_file_lruwalk_class, name, \ + TP_PROTO( \ + unsigned long removed, \ + unsigned long remaining \ + ), \ + TP_ARGS(removed, remaining)) + +DEFINE_NFSD_FILE_LRUWALK_EVENT(nfsd_file_gc_removed); +DEFINE_NFSD_FILE_LRUWALK_EVENT(nfsd_file_shrinker_removed); + #include "cache.h" TRACE_DEFINE_ENUM(RC_DROPIT); @@ -844,18 +1248,17 @@ TRACE_EVENT(nfsd_cb_args, __field(u32, cl_id) __field(u32, prog) __field(u32, ident) - __array(unsigned char, addr, sizeof(struct sockaddr_in6)) + __sockaddr(addr, conn->cb_addrlen) ), TP_fast_assign( __entry->cl_boot = clp->cl_clientid.cl_boot; __entry->cl_id = clp->cl_clientid.cl_id; __entry->prog = conn->cb_prog; __entry->ident = conn->cb_ident; - memcpy(__entry->addr, &conn->cb_addr, - sizeof(struct sockaddr_in6)); + __assign_sockaddr(addr, &conn->cb_addr, conn->cb_addrlen); ), TP_printk("addr=%pISpc client %08x:%08x prog=%u ident=%u", - __entry->addr, __entry->cl_boot, __entry->cl_id, + __get_sockaddr(addr), __entry->cl_boot, __entry->cl_id, __entry->prog, __entry->ident) ); @@ -887,17 +1290,17 @@ DECLARE_EVENT_CLASS(nfsd_cb_class, __field(unsigned long, state) __field(u32, cl_boot) __field(u32, cl_id) - __array(unsigned char, addr, sizeof(struct sockaddr_in6)) + __sockaddr(addr, clp->cl_cb_conn.cb_addrlen) ), TP_fast_assign( __entry->state = clp->cl_cb_state; __entry->cl_boot = clp->cl_clientid.cl_boot; __entry->cl_id = clp->cl_clientid.cl_id; - memcpy(__entry->addr, &clp->cl_cb_conn.cb_addr, - sizeof(struct sockaddr_in6)); + __assign_sockaddr(addr, &clp->cl_cb_conn.cb_addr, + clp->cl_cb_conn.cb_addrlen) ), TP_printk("addr=%pISpc client %08x:%08x state=%s", - __entry->addr, __entry->cl_boot, __entry->cl_id, + __get_sockaddr(addr), __entry->cl_boot, __entry->cl_id, show_cb_state(__entry->state)) ); @@ -937,7 +1340,7 @@ TRACE_EVENT(nfsd_cb_setup, __field(u32, cl_boot) __field(u32, cl_id) __field(unsigned long, authflavor) - __array(unsigned char, addr, sizeof(struct sockaddr_in6)) + __sockaddr(addr, clp->cl_cb_conn.cb_addrlen) __array(unsigned char, netid, 8) ), TP_fast_assign( @@ -945,11 +1348,11 @@ TRACE_EVENT(nfsd_cb_setup, __entry->cl_id = clp->cl_clientid.cl_id; strlcpy(__entry->netid, netid, sizeof(__entry->netid)); __entry->authflavor = authflavor; - memcpy(__entry->addr, &clp->cl_cb_conn.cb_addr, - sizeof(struct sockaddr_in6)); + __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", - __entry->addr, __entry->cl_boot, __entry->cl_id, + __get_sockaddr(addr), __entry->cl_boot, __entry->cl_id, __entry->netid, show_nfsd_authflavor(__entry->authflavor)) ); @@ -963,30 +1366,32 @@ TRACE_EVENT(nfsd_cb_setup_err, __field(long, error) __field(u32, cl_boot) __field(u32, cl_id) - __array(unsigned char, addr, sizeof(struct sockaddr_in6)) + __sockaddr(addr, clp->cl_cb_conn.cb_addrlen) ), TP_fast_assign( __entry->error = error; __entry->cl_boot = clp->cl_clientid.cl_boot; __entry->cl_id = clp->cl_clientid.cl_id; - memcpy(__entry->addr, &clp->cl_cb_conn.cb_addr, - sizeof(struct sockaddr_in6)); + __assign_sockaddr(addr, &clp->cl_cb_conn.cb_addr, + clp->cl_cb_conn.cb_addrlen) ), TP_printk("addr=%pISpc client %08x:%08x error=%ld", - __entry->addr, __entry->cl_boot, __entry->cl_id, __entry->error) + __get_sockaddr(addr), __entry->cl_boot, __entry->cl_id, + __entry->error) ); -TRACE_EVENT(nfsd_cb_recall, +TRACE_EVENT_CONDITION(nfsd_cb_recall, TP_PROTO( const struct nfs4_stid *stid ), TP_ARGS(stid), + TP_CONDITION(stid->sc_client), TP_STRUCT__entry( __field(u32, cl_boot) __field(u32, cl_id) __field(u32, si_id) __field(u32, si_generation) - __array(unsigned char, addr, sizeof(struct sockaddr_in6)) + __sockaddr(addr, stid->sc_client->cl_cb_conn.cb_addrlen) ), TP_fast_assign( const stateid_t *stp = &stid->sc_stateid; @@ -996,14 +1401,11 @@ TRACE_EVENT(nfsd_cb_recall, __entry->cl_id = stp->si_opaque.so_clid.cl_id; __entry->si_id = stp->si_opaque.so_id; __entry->si_generation = stp->si_generation; - if (clp) - memcpy(__entry->addr, &clp->cl_cb_conn.cb_addr, - sizeof(struct sockaddr_in6)); - else - memset(__entry->addr, 0, sizeof(struct sockaddr_in6)); + __assign_sockaddr(addr, &clp->cl_cb_conn.cb_addr, + clp->cl_cb_conn.cb_addrlen) ), TP_printk("addr=%pISpc client %08x:%08x stateid %08x:%08x", - __entry->addr, __entry->cl_boot, __entry->cl_id, + __get_sockaddr(addr), __entry->cl_boot, __entry->cl_id, __entry->si_id, __entry->si_generation) ); @@ -1017,7 +1419,7 @@ TRACE_EVENT(nfsd_cb_notify_lock, __field(u32, cl_boot) __field(u32, cl_id) __field(u32, fh_hash) - __array(unsigned char, addr, sizeof(struct sockaddr_in6)) + __sockaddr(addr, lo->lo_owner.so_client->cl_cb_conn.cb_addrlen) ), TP_fast_assign( const struct nfs4_client *clp = lo->lo_owner.so_client; @@ -1025,11 +1427,11 @@ TRACE_EVENT(nfsd_cb_notify_lock, __entry->cl_boot = clp->cl_clientid.cl_boot; __entry->cl_id = clp->cl_clientid.cl_id; __entry->fh_hash = knfsd_fh_hash(&nbl->nbl_fh); - memcpy(__entry->addr, &clp->cl_cb_conn.cb_addr, - sizeof(struct sockaddr_in6)); + __assign_sockaddr(addr, &clp->cl_cb_conn.cb_addr, + clp->cl_cb_conn.cb_addrlen) ), TP_printk("addr=%pISpc client %08x:%08x fh_hash=0x%08x", - __entry->addr, __entry->cl_boot, __entry->cl_id, + __get_sockaddr(addr), __entry->cl_boot, __entry->cl_id, __entry->fh_hash) ); @@ -1050,7 +1452,7 @@ TRACE_EVENT(nfsd_cb_offload, __field(u32, fh_hash) __field(int, status) __field(u64, count) - __array(unsigned char, addr, sizeof(struct sockaddr_in6)) + __sockaddr(addr, clp->cl_cb_conn.cb_addrlen) ), TP_fast_assign( __entry->cl_boot = stp->si_opaque.so_clid.cl_boot; @@ -1060,15 +1462,54 @@ TRACE_EVENT(nfsd_cb_offload, __entry->fh_hash = knfsd_fh_hash(fh); __entry->status = be32_to_cpu(status); __entry->count = count; - memcpy(__entry->addr, &clp->cl_cb_conn.cb_addr, - sizeof(struct sockaddr_in6)); + __assign_sockaddr(addr, &clp->cl_cb_conn.cb_addr, + clp->cl_cb_conn.cb_addrlen) ), TP_printk("addr=%pISpc client %08x:%08x stateid %08x:%08x fh_hash=0x%08x count=%llu status=%d", - __entry->addr, __entry->cl_boot, __entry->cl_id, + __get_sockaddr(addr), __entry->cl_boot, __entry->cl_id, __entry->si_id, __entry->si_generation, __entry->fh_hash, __entry->count, __entry->status) ); +DECLARE_EVENT_CLASS(nfsd_cb_done_class, + TP_PROTO( + const stateid_t *stp, + const struct rpc_task *task + ), + TP_ARGS(stp, task), + TP_STRUCT__entry( + __field(u32, cl_boot) + __field(u32, cl_id) + __field(u32, si_id) + __field(u32, si_generation) + __field(int, status) + ), + TP_fast_assign( + __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; + __entry->status = task->tk_status; + ), + TP_printk("client %08x:%08x stateid %08x:%08x status=%d", + __entry->cl_boot, __entry->cl_id, __entry->si_id, + __entry->si_generation, __entry->status + ) +); + +#define DEFINE_NFSD_CB_DONE_EVENT(name) \ +DEFINE_EVENT(nfsd_cb_done_class, name, \ + TP_PROTO( \ + const stateid_t *stp, \ + const struct rpc_task *task \ + ), \ + TP_ARGS(stp, task)) + +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); + #endif /* _NFSD_TRACE_H */ #undef TRACE_INCLUDE_PATH diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index c99857689e2c..f650afedd67f 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -26,20 +26,20 @@ #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> -#ifdef CONFIG_NFSD_V3 #include "xdr3.h" -#endif /* CONFIG_NFSD_V3 */ #ifdef CONFIG_NFSD_V4 #include "../internal.h" #include "acl.h" #include "idmap.h" +#include "xdr4.h" #endif /* CONFIG_NFSD_V4 */ #include "nfsd.h" @@ -199,27 +199,13 @@ nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp, goto out_nfserr; } } else { - /* - * In the nfsd4_open() case, this may be held across - * subsequent open and delegation acquisition which may - * need to take the child's i_mutex: - */ - fh_lock_nested(fhp, I_MUTEX_PARENT); - dentry = lookup_one_len(name, dparent, len); + dentry = lookup_one_len_unlocked(name, dparent, len); host_err = PTR_ERR(dentry); if (IS_ERR(dentry)) goto out_nfserr; if (nfsd_mountpoint(dentry, exp)) { - /* - * We don't need the i_mutex after all. It's - * still possible we could open this (regular - * files can be mountpoints too), but the - * i_mutex is just there to prevent renames of - * something that we might be about to delegate, - * and a mountpoint won't be renamed: - */ - fh_unlock(fhp); - if ((host_err = nfsd_cross_mnt(rqstp, &dentry, &exp))) { + host_err = nfsd_cross_mnt(rqstp, &dentry, &exp); + if (host_err) { dput(dentry); goto out_nfserr; } @@ -234,7 +220,15 @@ out_nfserr: return nfserrno(host_err); } -/* +/** + * nfsd_lookup - look up a single path component for nfsd + * + * @rqstp: the request context + * @fhp: the file handle of the directory + * @name: the component name, or %NULL to look up parent + * @len: length of name to examine + * @resfh: pointer to pre-initialised filehandle to hold result. + * * Look up one component of a pathname. * N.B. After this call _both_ fhp and resfh need an fh_put * @@ -244,11 +238,11 @@ out_nfserr: * returned. Otherwise the covered directory is returned. * NOTE: this mountpoint crossing is not supported properly by all * clients and is explicitly disallowed for NFSv3 - * NeilBrown <neilb@cse.unsw.edu.au> + * */ __be32 nfsd_lookup(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name, - unsigned int len, struct svc_fh *resfh) + unsigned int len, struct svc_fh *resfh) { struct svc_export *exp; struct dentry *dentry; @@ -306,6 +300,10 @@ commit_metadata(struct svc_fh *fhp) static void nfsd_sanitize_attrs(struct inode *inode, struct iattr *iap) { + /* Ignore mode updates on symlinks */ + if (S_ISLNK(inode->i_mode)) + iap->ia_valid &= ~ATTR_MODE; + /* sanitize the mode change */ if (iap->ia_valid & ATTR_MODE) { iap->ia_mode &= S_IALLUGO; @@ -345,21 +343,77 @@ nfsd_get_write_access(struct svc_rqst *rqstp, struct svc_fh *fhp, return nfserrno(get_write_access(inode)); } -/* - * Set various file attributes. After this call fhp needs an fh_put. +static int __nfsd_setattr(struct dentry *dentry, struct iattr *iap) +{ + int host_err; + + if (iap->ia_valid & ATTR_SIZE) { + /* + * RFC5661, Section 18.30.4: + * Changing the size of a file with SETATTR indirectly + * changes the time_modify and change attributes. + * + * (and similar for the older RFCs) + */ + struct iattr size_attr = { + .ia_valid = ATTR_SIZE | ATTR_CTIME | ATTR_MTIME, + .ia_size = iap->ia_size, + }; + + if (iap->ia_size < 0) + return -EFBIG; + + host_err = notify_change(&init_user_ns, dentry, &size_attr, NULL); + if (host_err) + return host_err; + iap->ia_valid &= ~ATTR_SIZE; + + /* + * Avoid the additional setattr call below if the only other + * attribute that the client sends is the mtime, as we update + * it as part of the size change above. + */ + if ((iap->ia_valid & ~ATTR_MTIME) == 0) + return 0; + } + + if (!iap->ia_valid) + return 0; + + iap->ia_valid |= ATTR_CTIME; + return notify_change(&init_user_ns, dentry, iap, NULL); +} + +/** + * nfsd_setattr - Set various file attributes. + * @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 + * call may change the bits in the na_iattr.ia_valid field). + * + * Returns nfs_ok on success, otherwise an NFS status code is + * returned. Caller must release @fhp by calling fh_put in either + * case. */ __be32 -nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, +nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, + struct nfsd_attrs *attr, int check_guard, time64_t guardtime) { struct dentry *dentry; struct inode *inode; + struct iattr *iap = attr->na_iattr; int accmode = NFSD_MAY_SATTR; umode_t ftype = 0; __be32 err; int host_err; bool get_write_count; bool size_change = (iap->ia_valid & ATTR_SIZE); + int retries; if (iap->ia_valid & ATTR_SIZE) { accmode |= NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE; @@ -395,13 +449,6 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, dentry = fhp->fh_dentry; inode = d_inode(dentry); - /* Ignore any mode updates on symlinks */ - if (S_ISLNK(inode->i_mode)) - iap->ia_valid &= ~ATTR_MODE; - - if (!iap->ia_valid) - return 0; - nfsd_sanitize_attrs(inode, iap); if (check_guard && guardtime != inode->i_ctime.tv_sec) @@ -420,39 +467,27 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, return err; } - fh_lock(fhp); - if (size_change) { - /* - * RFC5661, Section 18.30.4: - * Changing the size of a file with SETATTR indirectly - * changes the time_modify and change attributes. - * - * (and similar for the older RFCs) - */ - struct iattr size_attr = { - .ia_valid = ATTR_SIZE | ATTR_CTIME | ATTR_MTIME, - .ia_size = iap->ia_size, - }; - - host_err = notify_change(&init_user_ns, dentry, &size_attr, NULL); - if (host_err) - goto out_unlock; - iap->ia_valid &= ~ATTR_SIZE; - - /* - * Avoid the additional setattr call below if the only other - * attribute that the client sends is the mtime, as we update - * it as part of the size change above. - */ - if ((iap->ia_valid & ~ATTR_MTIME) == 0) - goto out_unlock; + inode_lock(inode); + for (retries = 1;;) { + host_err = __nfsd_setattr(dentry, iap); + if (host_err != -EAGAIN || !retries--) + break; + if (!nfsd_wait_for_delegreturn(rqstp, inode)) + break; } - - iap->ia_valid |= ATTR_CTIME; - host_err = notify_change(&init_user_ns, dentry, iap, NULL); - -out_unlock: - fh_unlock(fhp); + if (attr->na_seclabel && attr->na_seclabel->len) + 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, + inode, 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, + inode, ACL_TYPE_DEFAULT, + attr->na_dpacl); + inode_unlock(inode); if (size_change) put_write_access(inode); out: @@ -490,42 +525,24 @@ int nfsd4_is_junction(struct dentry *dentry) return 0; return 1; } -#ifdef CONFIG_NFSD_V4_SECURITY_LABEL -__be32 nfsd4_set_nfs4_label(struct svc_rqst *rqstp, struct svc_fh *fhp, - struct xdr_netobj *label) -{ - __be32 error; - int host_error; - struct dentry *dentry; - error = fh_verify(rqstp, fhp, 0 /* S_IFREG */, NFSD_MAY_SATTR); - if (error) - return error; - - dentry = fhp->fh_dentry; - - inode_lock(d_inode(dentry)); - host_error = security_inode_setsecctx(dentry, label->data, label->len); - inode_unlock(d_inode(dentry)); - return nfserrno(host_error); -} -#else -__be32 nfsd4_set_nfs4_label(struct svc_rqst *rqstp, struct svc_fh *fhp, - struct xdr_netobj *label) +static struct nfsd4_compound_state *nfsd4_get_cstate(struct svc_rqst *rqstp) { - return nfserr_notsupp; + return &((struct nfsd4_compoundres *)rqstp->rq_resp)->cstate; } -#endif -__be32 nfsd4_clone_file_range(struct nfsd_file *nf_src, u64 src_pos, - struct nfsd_file *nf_dst, u64 dst_pos, u64 count, bool sync) +__be32 nfsd4_clone_file_range(struct svc_rqst *rqstp, + struct nfsd_file *nf_src, u64 src_pos, + struct nfsd_file *nf_dst, u64 dst_pos, + u64 count, bool sync) { struct file *src = nf_src->nf_file; struct file *dst = nf_dst->nf_file; + errseq_t since; loff_t cloned; __be32 ret = 0; - down_write(&nf_dst->nf_rwsem); + since = READ_ONCE(dst->f_wb_err); cloned = vfs_clone_file_range(src, src_pos, dst, dst_pos, count, 0); if (cloned < 0) { ret = nfserrno(cloned); @@ -540,21 +557,32 @@ __be32 nfsd4_clone_file_range(struct nfsd_file *nf_src, u64 src_pos, int status = vfs_fsync_range(dst, dst_pos, dst_end, 0); if (!status) + status = filemap_check_wb_err(dst->f_mapping, since); + if (!status) status = commit_inode_metadata(file_inode(src)); if (status < 0) { - nfsd_reset_boot_verifier(net_generic(nf_dst->nf_net, - nfsd_net_id)); + struct nfsd_net *nn = net_generic(nf_dst->nf_net, + nfsd_net_id); + + trace_nfsd_clone_file_range_err(rqstp, + &nfsd4_get_cstate(rqstp)->save_fh, + src_pos, + &nfsd4_get_cstate(rqstp)->current_fh, + dst_pos, + count, status); + nfsd_reset_write_verifier(nn); + trace_nfsd_writeverf_reset(nn, rqstp, status); ret = nfserrno(status); } } out_err: - up_write(&nf_dst->nf_rwsem); return ret; } ssize_t nfsd_copy_file_range(struct file *src, u64 src_pos, struct file *dst, u64 dst_pos, u64 count) { + ssize_t ret; /* * Limit copy to 4MB to prevent indefinitely blocking an nfsd @@ -565,7 +593,12 @@ ssize_t nfsd_copy_file_range(struct file *src, u64 src_pos, struct file *dst, * limit like this and pipeline multiple COPY requests. */ count = min_t(u64, count, 1 << 22); - return vfs_copy_file_range(src, src_pos, dst, dst_pos, count, 0); + ret = vfs_copy_file_range(src, src_pos, dst, dst_pos, count, 0); + + if (ret == -EOPNOTSUPP || ret == -EXDEV) + ret = generic_copy_file_range(src, src_pos, dst, dst_pos, + count, 0); + return ret; } __be32 nfsd4_vfs_fallocate(struct svc_rqst *rqstp, struct svc_fh *fhp, @@ -585,7 +618,6 @@ __be32 nfsd4_vfs_fallocate(struct svc_rqst *rqstp, struct svc_fh *fhp, } #endif /* defined(CONFIG_NFSD_V4) */ -#ifdef CONFIG_NFSD_V3 /* * Check server access rights to a file system object */ @@ -697,7 +729,6 @@ nfsd_access(struct svc_rqst *rqstp, struct svc_fh *fhp, u32 *access, u32 *suppor out: return error; } -#endif /* CONFIG_NFSD_V3 */ int nfsd_open_break_lease(struct inode *inode, int access) { @@ -777,6 +808,7 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int may_flags, struct file **filp) { __be32 err; + bool retried = false; validate_process_creds(); /* @@ -792,21 +824,37 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, */ if (type == S_IFREG) may_flags |= NFSD_MAY_OWNER_OVERRIDE; +retry: err = fh_verify(rqstp, fhp, type, may_flags); - if (!err) + if (!err) { err = __nfsd_open(rqstp, fhp, type, may_flags, filp); + if (err == nfserr_stale && !retried) { + retried = true; + fh_put(fhp); + goto retry; + } + } 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 + * @may_flags: internal permission flags + * @filp: OUT: open "struct file *" + * + * Returns an nfsstat value in network byte order. + */ __be32 -nfsd_open_verified(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, - int may_flags, struct file **filp) +nfsd_open_verified(struct svc_rqst *rqstp, struct svc_fh *fhp, int may_flags, + struct file **filp) { __be32 err; validate_process_creds(); - err = __nfsd_open(rqstp, fhp, type, may_flags, filp); + err = __nfsd_open(rqstp, fhp, S_IFREG, may_flags, filp); validate_process_creds(); return err; } @@ -821,17 +869,15 @@ nfsd_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf, struct splice_desc *sd) { struct svc_rqst *rqstp = sd->u.data; - struct page **pp = rqstp->rq_next_page; - struct page *page = buf->page; - - if (rqstp->rq_res.page_len == 0) { - svc_rqst_replace_page(rqstp, page); - rqstp->rq_res.page_base = buf->offset; - } else if (page != pp[-1]) { - svc_rqst_replace_page(rqstp, page); - } + struct page *page = buf->page; // may be a compound one + unsigned offset = buf->offset; + + page += offset / PAGE_SIZE; + for (int i = sd->len; i > 0; i -= PAGE_SIZE) + svc_rqst_replace_page(rqstp, page++); + if (rqstp->rq_res.page_len == 0) // first call + rqstp->rq_res.page_base = offset % PAGE_SIZE; rqstp->rq_res.page_len += sd->len; - return sd->len; } @@ -944,10 +990,12 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf, 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 svc_export *exp; struct iov_iter iter; + errseq_t since; __be32 nfserr; int host_err; int use_wgather; @@ -985,36 +1033,28 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf, flags |= RWF_SYNC; iov_iter_kvec(&iter, WRITE, vec, vlen, *cnt); - if (flags & RWF_SYNC) { - down_write(&nf->nf_rwsem); - host_err = vfs_iter_write(file, &iter, &pos, flags); - if (host_err < 0) - nfsd_reset_boot_verifier(net_generic(SVC_NET(rqstp), - nfsd_net_id)); - up_write(&nf->nf_rwsem); - } else { - down_read(&nf->nf_rwsem); - if (verf) - nfsd_copy_boot_verifier(verf, - net_generic(SVC_NET(rqstp), - nfsd_net_id)); - host_err = vfs_iter_write(file, &iter, &pos, flags); - up_read(&nf->nf_rwsem); - } + since = READ_ONCE(file->f_wb_err); + if (verf) + nfsd_copy_write_verifier(verf, nn); + host_err = vfs_iter_write(file, &iter, &pos, flags); if (host_err < 0) { - nfsd_reset_boot_verifier(net_generic(SVC_NET(rqstp), - nfsd_net_id)); + nfsd_reset_write_verifier(nn); + trace_nfsd_writeverf_reset(nn, rqstp, host_err); goto out_nfserr; } *cnt = host_err; nfsd_stats_io_write_add(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) { host_err = wait_for_concurrent_writes(file); - if (host_err < 0) - nfsd_reset_boot_verifier(net_generic(SVC_NET(rqstp), - nfsd_net_id)); + if (host_err < 0) { + nfsd_reset_write_verifier(nn); + trace_nfsd_writeverf_reset(nn, rqstp, host_err); + } } out_nfserr: @@ -1088,87 +1128,105 @@ out: return err; } -#ifdef CONFIG_NFSD_V3 -static int -nfsd_filemap_write_and_wait_range(struct nfsd_file *nf, loff_t offset, - loff_t end) -{ - struct address_space *mapping = nf->nf_file->f_mapping; - int ret = filemap_fdatawrite_range(mapping, offset, end); - - if (ret) - return ret; - filemap_fdatawait_range_keep_errors(mapping, offset, end); - return 0; -} - -/* - * Commit all pending writes to stable storage. +/** + * nfsd_commit - Commit pending writes to stable storage + * @rqstp: RPC request being processed + * @fhp: NFS filehandle + * @offset: raw offset from beginning of file + * @count: raw count of bytes to sync + * @verf: filled in with the server's current write verifier * - * Note: we only guarantee that data that lies within the range specified - * by the 'offset' and 'count' parameters will be synced. + * Note: we guarantee that data that lies within the range specified + * by the 'offset' and 'count' parameters will be synced. The server + * is permitted to sync data that lies outside this range at the + * same time. * * Unfortunately we cannot lock the file to make sure we return full WCC * data to the client, as locking happens lower down in the filesystem. + * + * Return values: + * An nfsstat value in network byte order. */ __be32 -nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp, - loff_t offset, unsigned long count, __be32 *verf) +nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp, u64 offset, + u32 count, __be32 *verf) { + u64 maxbytes; + loff_t start, end; + struct nfsd_net *nn; struct nfsd_file *nf; - loff_t end = LLONG_MAX; - __be32 err = nfserr_inval; - - if (offset < 0) - goto out; - if (count != 0) { - end = offset + (loff_t)count - 1; - if (end < offset) - goto out; - } + __be32 err; err = nfsd_file_acquire(rqstp, fhp, NFSD_MAY_WRITE|NFSD_MAY_NOT_BREAK_LEASE, &nf); if (err) goto out; + + /* + * Convert the client-provided (offset, count) range to a + * (start, end) range. If the client-provided range falls + * outside the maximum file size of the underlying FS, + * clamp the sync range appropriately. + */ + start = 0; + end = LLONG_MAX; + maxbytes = (u64)fhp->fh_dentry->d_sb->s_maxbytes; + if (offset < maxbytes) { + start = offset; + if (count && (offset + count - 1 < maxbytes)) + end = offset + count - 1; + } + + nn = net_generic(nf->nf_net, nfsd_net_id); if (EX_ISSYNC(fhp->fh_export)) { - int err2 = nfsd_filemap_write_and_wait_range(nf, offset, end); + errseq_t since = READ_ONCE(nf->nf_file->f_wb_err); + int err2; - down_write(&nf->nf_rwsem); - if (!err2) - err2 = vfs_fsync_range(nf->nf_file, offset, end, 0); + err2 = vfs_fsync_range(nf->nf_file, start, end, 0); switch (err2) { case 0: - nfsd_copy_boot_verifier(verf, net_generic(nf->nf_net, - nfsd_net_id)); + nfsd_copy_write_verifier(verf, nn); + err2 = filemap_check_wb_err(nf->nf_file->f_mapping, + since); + err = nfserrno(err2); break; case -EINVAL: err = nfserr_notsupp; break; default: + nfsd_reset_write_verifier(nn); + trace_nfsd_writeverf_reset(nn, rqstp, err2); err = nfserrno(err2); - nfsd_reset_boot_verifier(net_generic(nf->nf_net, - nfsd_net_id)); } - up_write(&nf->nf_rwsem); } else - nfsd_copy_boot_verifier(verf, net_generic(nf->nf_net, - nfsd_net_id)); + nfsd_copy_write_verifier(verf, nn); nfsd_file_put(nf); out: return err; } -#endif /* CONFIG_NFSD_V3 */ -static __be32 -nfsd_create_setattr(struct svc_rqst *rqstp, struct svc_fh *resfhp, - struct iattr *iap) +/** + * nfsd_create_setattr - Set a created file's attributes + * @rqstp: RPC transaction being executed + * @fhp: NFS filehandle of parent directory + * @resfhp: NFS filehandle of new object + * @attrs: requested attributes of new object + * + * Returns nfs_ok on success, or an nfsstat in network byte order. + */ +__be32 +nfsd_create_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, + struct svc_fh *resfhp, struct nfsd_attrs *attrs) { + struct iattr *iap = attrs->na_iattr; + __be32 status; + /* - * Mode has already been set earlier in create: + * Mode has already been set by file creation. */ iap->ia_valid &= ~ATTR_MODE; + /* * Setting uid/gid works only for root. Irix appears to * send along the gid on create when it tries to implement @@ -1176,10 +1234,31 @@ nfsd_create_setattr(struct svc_rqst *rqstp, struct svc_fh *resfhp, */ if (!uid_eq(current_fsuid(), GLOBAL_ROOT_UID)) iap->ia_valid &= ~(ATTR_UID|ATTR_GID); + + /* + * Callers expect new file metadata to be committed even + * if the attributes have not changed. + */ if (iap->ia_valid) - return nfsd_setattr(rqstp, resfhp, iap, 0, (time64_t)0); - /* Callers expect file metadata to be committed here */ - return nfserrno(commit_metadata(resfhp)); + status = nfsd_setattr(rqstp, resfhp, attrs, 0, (time64_t)0); + else + status = nfserrno(commit_metadata(resfhp)); + + /* + * Transactional filesystems had a chance to commit changes + * for both parent and child simultaneously making the + * following commit_metadata a noop in many cases. + */ + if (!status) + status = nfserrno(commit_metadata(fhp)); + + /* + * Update the new filehandle to pick up the new attributes. + */ + if (!status) + status = fh_update(resfhp); + + return status; } /* HPUX client sometimes creates a file in mode 000, and sets size to 0. @@ -1200,26 +1279,19 @@ nfsd_check_ignore_resizing(struct iattr *iap) /* The parent directory should already be locked: */ __be32 nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp, - char *fname, int flen, struct iattr *iap, - int type, dev_t rdev, struct svc_fh *resfhp) + struct nfsd_attrs *attrs, + int type, dev_t rdev, struct svc_fh *resfhp) { struct dentry *dentry, *dchild; struct inode *dirp; + struct iattr *iap = attrs->na_iattr; __be32 err; - __be32 err2; int host_err; dentry = fhp->fh_dentry; dirp = d_inode(dentry); dchild = dget(resfhp->fh_dentry); - if (!fhp->fh_locked) { - WARN_ONCE(1, "nfsd_create: parent %pd2 not locked!\n", - dentry); - err = nfserr_io; - goto out; - } - err = nfsd_permission(rqstp, fhp->fh_export, dentry, NFSD_MAY_CREATE); if (err) goto out; @@ -1279,22 +1351,8 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp, if (host_err < 0) goto out_nfserr; - err = nfsd_create_setattr(rqstp, resfhp, iap); + err = nfsd_create_setattr(rqstp, fhp, resfhp, attrs); - /* - * nfsd_create_setattr already committed the child. Transactional - * filesystems had a chance to commit changes for both parent and - * child simultaneously making the following commit_metadata a - * noop. - */ - err2 = nfserrno(commit_metadata(fhp)); - if (err2) - err = err2; - /* - * Update the file handle to get the new inode info. - */ - if (!err) - err = fh_update(resfhp); out: dput(dchild); return err; @@ -1312,8 +1370,8 @@ out_nfserr: */ __be32 nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, - char *fname, int flen, struct iattr *iap, - int type, dev_t rdev, struct svc_fh *resfhp) + char *fname, int flen, struct nfsd_attrs *attrs, + int type, dev_t rdev, struct svc_fh *resfhp) { struct dentry *dentry, *dchild = NULL; __be32 err; @@ -1332,11 +1390,13 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, if (host_err) return nfserrno(host_err); - fh_lock_nested(fhp, I_MUTEX_PARENT); + inode_lock_nested(dentry->d_inode, I_MUTEX_PARENT); dchild = lookup_one_len(fname, dentry, flen); host_err = PTR_ERR(dchild); - if (IS_ERR(dchild)) - return nfserrno(host_err); + if (IS_ERR(dchild)) { + err = nfserrno(host_err); + goto out_unlock; + } err = fh_compose(resfhp, fhp->fh_export, dchild, fhp); /* * We unconditionally drop our ref to dchild as fh_compose will have @@ -1344,179 +1404,14 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, */ dput(dchild); if (err) - return err; - return nfsd_create_locked(rqstp, fhp, fname, flen, iap, type, - rdev, resfhp); -} - -#ifdef CONFIG_NFSD_V3 - -/* - * NFSv3 and NFSv4 version of nfsd_create - */ -__be32 -do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, - char *fname, int flen, struct iattr *iap, - struct svc_fh *resfhp, int createmode, u32 *verifier, - bool *truncp, bool *created) -{ - struct dentry *dentry, *dchild = NULL; - struct inode *dirp; - __be32 err; - int host_err; - __u32 v_mtime=0, v_atime=0; - - err = nfserr_perm; - if (!flen) - goto out; - err = nfserr_exist; - if (isdotent(fname, flen)) - goto out; - if (!(iap->ia_valid & ATTR_MODE)) - iap->ia_mode = 0; - err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_EXEC); - if (err) - goto out; - - dentry = fhp->fh_dentry; - dirp = d_inode(dentry); - - host_err = fh_want_write(fhp); - if (host_err) - goto out_nfserr; - - fh_lock_nested(fhp, I_MUTEX_PARENT); - - /* - * Compose the response file handle. - */ - dchild = lookup_one_len(fname, dentry, flen); - host_err = PTR_ERR(dchild); - if (IS_ERR(dchild)) - goto out_nfserr; - - /* If file doesn't exist, check for permissions to create one */ - if (d_really_is_negative(dchild)) { - err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_CREATE); - if (err) - goto out; - } - - err = fh_compose(resfhp, fhp->fh_export, dchild, fhp); - if (err) - goto out; - - if (nfsd_create_is_exclusive(createmode)) { - /* solaris7 gets confused (bugid 4218508) if these have - * the high bit set, as do xfs filesystems without the - * "bigtime" feature. So just clear the high bits. If this is - * ever changed to use different attrs for storing the - * verifier, then do_open_lookup() will also need to be fixed - * accordingly. - */ - v_mtime = verifier[0]&0x7fffffff; - v_atime = verifier[1]&0x7fffffff; - } - - if (d_really_is_positive(dchild)) { - err = 0; - - switch (createmode) { - case NFS3_CREATE_UNCHECKED: - if (! d_is_reg(dchild)) - goto out; - else if (truncp) { - /* in nfsv4, we need to treat this case a little - * differently. we don't want to truncate the - * file now; this would be wrong if the OPEN - * fails for some other reason. furthermore, - * if the size is nonzero, we should ignore it - * according to spec! - */ - *truncp = (iap->ia_valid & ATTR_SIZE) && !iap->ia_size; - } - else { - iap->ia_valid &= ATTR_SIZE; - goto set_attr; - } - break; - case NFS3_CREATE_EXCLUSIVE: - if ( d_inode(dchild)->i_mtime.tv_sec == v_mtime - && d_inode(dchild)->i_atime.tv_sec == v_atime - && d_inode(dchild)->i_size == 0 ) { - if (created) - *created = true; - break; - } - fallthrough; - case NFS4_CREATE_EXCLUSIVE4_1: - if ( d_inode(dchild)->i_mtime.tv_sec == v_mtime - && d_inode(dchild)->i_atime.tv_sec == v_atime - && d_inode(dchild)->i_size == 0 ) { - if (created) - *created = true; - goto set_attr; - } - fallthrough; - case NFS3_CREATE_GUARDED: - err = nfserr_exist; - } - fh_drop_write(fhp); - goto out; - } - - if (!IS_POSIXACL(dirp)) - iap->ia_mode &= ~current_umask(); - - host_err = vfs_create(&init_user_ns, dirp, dchild, iap->ia_mode, true); - if (host_err < 0) { - fh_drop_write(fhp); - goto out_nfserr; - } - if (created) - *created = true; - - nfsd_check_ignore_resizing(iap); - - if (nfsd_create_is_exclusive(createmode)) { - /* Cram the verifier into atime/mtime */ - iap->ia_valid = ATTR_MTIME|ATTR_ATIME - | ATTR_MTIME_SET|ATTR_ATIME_SET; - /* XXX someone who knows this better please fix it for nsec */ - iap->ia_mtime.tv_sec = v_mtime; - iap->ia_atime.tv_sec = v_atime; - iap->ia_mtime.tv_nsec = 0; - iap->ia_atime.tv_nsec = 0; - } - - set_attr: - err = nfsd_create_setattr(rqstp, resfhp, iap); - - /* - * nfsd_create_setattr already committed the child - * (and possibly also the parent). - */ - if (!err) - err = nfserrno(commit_metadata(fhp)); - - /* - * Update the filehandle to get the new inode info. - */ - if (!err) - err = fh_update(resfhp); - - out: - fh_unlock(fhp); - if (dchild && !IS_ERR(dchild)) - dput(dchild); - fh_drop_write(fhp); - return err; - - out_nfserr: - err = nfserrno(host_err); - goto out; + goto out_unlock; + fh_fill_pre_attrs(fhp); + err = nfsd_create_locked(rqstp, fhp, attrs, type, rdev, resfhp); + fh_fill_post_attrs(fhp); +out_unlock: + inode_unlock(dentry->d_inode); + return err; } -#endif /* CONFIG_NFSD_V3 */ /* * Read a symlink. On entry, *lenp must contain the maximum path length that @@ -1556,15 +1451,25 @@ nfsd_readlink(struct svc_rqst *rqstp, struct svc_fh *fhp, char *buf, int *lenp) return 0; } -/* - * Create a symlink and look up its inode +/** + * nfsd_symlink - Create a symlink and look up its inode + * @rqstp: RPC transaction being executed + * @fhp: NFS filehandle of parent directory + * @fname: filename of the new symlink + * @flen: length of @fname + * @path: content of the new symlink (NUL-terminated) + * @attrs: requested attributes of new object + * @resfhp: NFS filehandle of new object + * * N.B. After this call _both_ fhp and resfhp need an fh_put + * + * Returns nfs_ok on success, or an nfsstat in network byte order. */ __be32 nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp, - char *fname, int flen, - char *path, - struct svc_fh *resfhp) + char *fname, int flen, + char *path, struct nfsd_attrs *attrs, + struct svc_fh *resfhp) { struct dentry *dentry, *dnew; __be32 err, cerr; @@ -1582,33 +1487,35 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp, goto out; host_err = fh_want_write(fhp); - if (host_err) - goto out_nfserr; + if (host_err) { + err = nfserrno(host_err); + goto out; + } - fh_lock(fhp); dentry = fhp->fh_dentry; + inode_lock_nested(dentry->d_inode, I_MUTEX_PARENT); dnew = lookup_one_len(fname, dentry, flen); - host_err = PTR_ERR(dnew); - if (IS_ERR(dnew)) - goto out_nfserr; - + 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 = nfserrno(host_err); - fh_unlock(fhp); + 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); if (!err) err = nfserrno(commit_metadata(fhp)); - - fh_drop_write(fhp); - - cerr = fh_compose(resfhp, fhp->fh_export, dnew, fhp); dput(dnew); if (err==0) err = cerr; +out_drop_write: + fh_drop_write(fhp); out: return err; - -out_nfserr: - err = nfserrno(host_err); - goto out; } /* @@ -1646,22 +1553,25 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp, goto out; } - fh_lock_nested(ffhp, I_MUTEX_PARENT); ddir = ffhp->fh_dentry; dirp = d_inode(ddir); + inode_lock_nested(dirp, I_MUTEX_PARENT); dnew = lookup_one_len(name, ddir, len); - host_err = PTR_ERR(dnew); - if (IS_ERR(dnew)) - goto out_nfserr; + if (IS_ERR(dnew)) { + err = nfserrno(PTR_ERR(dnew)); + goto out_unlock; + } 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); - fh_unlock(ffhp); + fh_fill_post_attrs(ffhp); + inode_unlock(dirp); if (!host_err) { err = nfserrno(commit_metadata(ffhp)); if (!err) @@ -1672,17 +1582,17 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp, else err = nfserrno(host_err); } -out_dput: dput(dnew); -out_unlock: - fh_unlock(ffhp); +out_drop_write: fh_drop_write(tfhp); out: return err; -out_nfserr: - err = nfserrno(host_err); - goto out_unlock; +out_dput: + dput(dnew); +out_unlock: + inode_unlock(dirp); + goto out_drop_write; } static void @@ -1743,12 +1653,9 @@ retry: goto out; } - /* cannot use fh_lock as we need deadlock protective ordering - * so do it by hand */ trap = lock_rename(tdentry, fdentry); - ffhp->fh_locked = tfhp->fh_locked = true; - fill_pre_wcc(ffhp); - fill_pre_wcc(tfhp); + fh_fill_pre_attrs(ffhp); + fh_fill_pre_attrs(tfhp); odentry = lookup_one_len(fname, fdentry, flen); host_err = PTR_ERR(odentry); @@ -1789,7 +1696,15 @@ retry: .new_dir = tdir, .new_dentry = ndentry, }; - host_err = vfs_rename(&rd); + 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))) + break; + } if (!host_err) { host_err = commit_metadata(tfhp); if (!host_err) @@ -1802,17 +1717,12 @@ retry: dput(odentry); out_nfserr: err = nfserrno(host_err); - /* - * We cannot rely on fh_unlock on the two filehandles, - * as that would do the wrong thing if the two directories - * were the same, so again we do it by hand. - */ + if (!close_cached) { - fill_post_wcc(ffhp); - fill_post_wcc(tfhp); + fh_fill_post_attrs(ffhp); + fh_fill_post_attrs(tfhp); } unlock_rename(tdentry, fdentry); - ffhp->fh_locked = tfhp->fh_locked = false; fh_drop_write(ffhp); /* @@ -1856,19 +1766,19 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, if (host_err) goto out_nfserr; - fh_lock_nested(fhp, I_MUTEX_PARENT); dentry = fhp->fh_dentry; dirp = d_inode(dentry); + inode_lock_nested(dirp, I_MUTEX_PARENT); rdentry = lookup_one_len(fname, dentry, flen); host_err = PTR_ERR(rdentry); if (IS_ERR(rdentry)) - goto out_drop_write; + goto out_unlock; if (d_really_is_negative(rdentry)) { dput(rdentry); host_err = -ENOENT; - goto out_drop_write; + goto out_unlock; } rinode = d_inode(rdentry); ihold(rinode); @@ -1876,15 +1786,26 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, if (!type) type = d_inode(rdentry)->i_mode & S_IFMT; + fh_fill_pre_attrs(fhp); if (type != S_IFDIR) { + int retries; + if (rdentry->d_sb->s_export_op->flags & EXPORT_OP_CLOSE_BEFORE_UNLINK) nfsd_close_cached_files(rdentry); - host_err = vfs_unlink(&init_user_ns, dirp, rdentry, NULL); + + for (retries = 1;;) { + host_err = vfs_unlink(&init_user_ns, 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); } + fh_fill_post_attrs(fhp); - fh_unlock(fhp); + inode_unlock(dirp); if (!host_err) host_err = commit_metadata(fhp); dput(rdentry); @@ -1906,6 +1827,9 @@ out_nfserr: } out: return err; +out_unlock: + inode_unlock(dirp); + goto out_drop_write; } /* @@ -1930,7 +1854,7 @@ struct readdir_data { int full; }; -static int nfsd_buffered_filldir(struct dir_context *ctx, const char *name, +static bool nfsd_buffered_filldir(struct dir_context *ctx, const char *name, int namlen, loff_t offset, u64 ino, unsigned int d_type) { @@ -1942,7 +1866,7 @@ static int nfsd_buffered_filldir(struct dir_context *ctx, const char *name, reclen = ALIGN(sizeof(struct buffered_dirent) + namlen, sizeof(u64)); if (buf->used + reclen > PAGE_SIZE) { buf->full = 1; - return -EINVAL; + return false; } de->namlen = namlen; @@ -1952,7 +1876,7 @@ static int nfsd_buffered_filldir(struct dir_context *ctx, const char *name, memcpy(de->name, name, namlen); buf->used += reclen; - return 0; + return true; } static __be32 nfsd_buffered_readdir(struct file *file, struct svc_fh *fhp, @@ -2259,13 +2183,16 @@ out: return err; } -/* - * Removexattr and setxattr need to call fh_lock to both lock the inode - * and set the change attribute. Since the top-level vfs_removexattr - * and vfs_setxattr calls already do their own inode_lock calls, call - * the _locked variant. Pass in a NULL pointer for delegated_inode, - * and let the client deal with NFS4ERR_DELAY (same as with e.g. - * setattr and remove). +/** + * nfsd_removexattr - Remove an extended attribute + * @rqstp: RPC transaction being executed + * @fhp: NFS filehandle of object with xattr to remove + * @name: name of xattr to remove (NUL-terminate) + * + * Pass in a NULL pointer for delegated_inode, and let the client deal + * with NFS4ERR_DELAY (same as with e.g. setattr and remove). + * + * Returns nfs_ok on success, or an nfsstat in network byte order. */ __be32 nfsd_removexattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name) @@ -2281,12 +2208,14 @@ nfsd_removexattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name) if (ret) return nfserrno(ret); - fh_lock(fhp); + inode_lock(fhp->fh_dentry->d_inode); + fh_fill_pre_attrs(fhp); ret = __vfs_removexattr_locked(&init_user_ns, fhp->fh_dentry, name, NULL); - fh_unlock(fhp); + fh_fill_post_attrs(fhp); + inode_unlock(fhp->fh_dentry->d_inode); fh_drop_write(fhp); return nfsd_xattr_errno(ret); @@ -2306,12 +2235,13 @@ nfsd_setxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name, ret = fh_want_write(fhp); if (ret) return nfserrno(ret); - fh_lock(fhp); + 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); - - fh_unlock(fhp); + fh_fill_post_attrs(fhp); + inode_unlock(fhp->fh_dentry->d_inode); fh_drop_write(fhp); return nfsd_xattr_errno(ret); diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h index b21b76e6b9a8..120521bc7b24 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -6,6 +6,8 @@ #ifndef LINUX_NFSD_VFS_H #define LINUX_NFSD_VFS_H +#include <linux/fs.h> +#include <linux/posix_acl.h> #include "nfsfh.h" #include "nfsd.h" @@ -42,6 +44,22 @@ struct nfsd_file; typedef int (*nfsd_filldir_t)(void *, const char *, int, loff_t, u64, unsigned); /* nfsd/vfs.c */ +struct nfsd_attrs { + struct iattr *na_iattr; /* input */ + struct xdr_netobj *na_seclabel; /* input */ + struct posix_acl *na_pacl; /* input */ + struct posix_acl *na_dpacl; /* input */ + + int na_labelerr; /* output */ + int na_aclerr; /* output */ +}; + +static inline void nfsd_attrs_free(struct nfsd_attrs *attrs) +{ + posix_acl_release(attrs->na_pacl); + posix_acl_release(attrs->na_dpacl); +} + int nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp, struct svc_export **expp); __be32 nfsd_lookup(struct svc_rqst *, struct svc_fh *, @@ -50,32 +68,27 @@ __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 iattr *, int, time64_t); + struct nfsd_attrs *, int, time64_t); int nfsd_mountpoint(struct dentry *, struct svc_export *); #ifdef CONFIG_NFSD_V4 -__be32 nfsd4_set_nfs4_label(struct svc_rqst *, struct svc_fh *, - struct xdr_netobj *); __be32 nfsd4_vfs_fallocate(struct svc_rqst *, struct svc_fh *, struct file *, loff_t, loff_t, int); -__be32 nfsd4_clone_file_range(struct nfsd_file *nf_src, u64 src_pos, +__be32 nfsd4_clone_file_range(struct svc_rqst *rqstp, + struct nfsd_file *nf_src, u64 src_pos, struct nfsd_file *nf_dst, u64 dst_pos, u64 count, bool sync); #endif /* CONFIG_NFSD_V4 */ __be32 nfsd_create_locked(struct svc_rqst *, struct svc_fh *, - char *name, int len, struct iattr *attrs, - int type, dev_t rdev, struct svc_fh *res); + struct nfsd_attrs *attrs, int type, dev_t rdev, + struct svc_fh *res); __be32 nfsd_create(struct svc_rqst *, struct svc_fh *, - char *name, int len, struct iattr *attrs, + char *name, int len, struct nfsd_attrs *attrs, int type, dev_t rdev, struct svc_fh *res); -#ifdef CONFIG_NFSD_V3 __be32 nfsd_access(struct svc_rqst *, struct svc_fh *, u32 *, u32 *); -__be32 do_nfsd_create(struct svc_rqst *, struct svc_fh *, - char *name, int len, struct iattr *attrs, - struct svc_fh *res, int createmode, - u32 *verifier, bool *truncp, bool *created); -__be32 nfsd_commit(struct svc_rqst *, struct svc_fh *, - loff_t, unsigned long, __be32 *verf); -#endif /* CONFIG_NFSD_V3 */ +__be32 nfsd_create_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, + struct svc_fh *resfhp, struct nfsd_attrs *iap); +__be32 nfsd_commit(struct svc_rqst *rqst, struct svc_fh *fhp, + u64 offset, u32 count, __be32 *verf); #ifdef CONFIG_NFSD_V4 __be32 nfsd_getxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name, void **bufp, int *lenp); @@ -89,7 +102,7 @@ __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 *, umode_t, +__be32 nfsd_open_verified(struct svc_rqst *, struct svc_fh *, int, struct file **); __be32 nfsd_splice_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, loff_t offset, @@ -113,8 +126,9 @@ __be32 nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, __be32 nfsd_readlink(struct svc_rqst *, struct svc_fh *, char *, int *); __be32 nfsd_symlink(struct svc_rqst *, struct svc_fh *, - char *name, int len, char *path, - struct svc_fh *res); + char *name, int len, char *path, + struct nfsd_attrs *attrs, + struct svc_fh *res); __be32 nfsd_link(struct svc_rqst *, struct svc_fh *, char *, int, struct svc_fh *); ssize_t nfsd_copy_file_range(struct file *, u64, @@ -160,10 +174,4 @@ static inline __be32 fh_getattr(const struct svc_fh *fh, struct kstat *stat) AT_STATX_SYNC_AS_STAT)); } -static inline int nfsd_create_is_exclusive(int createmode) -{ - return createmode == NFS3_CREATE_EXCLUSIVE - || createmode == NFS4_CREATE_EXCLUSIVE4_1; -} - #endif /* LINUX_NFSD_VFS_H */ diff --git a/fs/nfsd/xdr.h b/fs/nfsd/xdr.h index 528fb299430e..852f71580bd0 100644 --- a/fs/nfsd/xdr.h +++ b/fs/nfsd/xdr.h @@ -32,7 +32,7 @@ struct nfsd_readargs { struct nfsd_writeargs { svc_fh fh; __u32 offset; - int len; + __u32 len; struct xdr_buf payload; }; diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index 846ab6df9d48..0eb00105d845 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -273,11 +273,13 @@ struct nfsd4_open { bool op_truncate; /* used during processing */ bool op_created; /* used during processing */ struct nfs4_openowner *op_openowner; /* used during processing */ + struct file *op_filp; /* used during processing */ struct nfs4_file *op_file; /* used during processing */ struct nfs4_ol_stateid *op_stp; /* used during processing */ struct nfs4_clnt_odstate *op_odstate; /* used during processing */ struct nfs4_acl *op_acl; struct xdr_netobj op_label; + struct svc_rqst *op_rqstp; }; struct nfsd4_open_confirm { @@ -301,9 +303,10 @@ struct nfsd4_read { u32 rd_length; /* request */ int rd_vlen; struct nfsd_file *rd_nf; - + struct svc_rqst *rd_rqstp; /* response */ - struct svc_fh *rd_fhp; /* response */ + struct svc_fh *rd_fhp; /* response */ + u32 rd_eof; /* response */ }; struct nfsd4_readdir { @@ -531,6 +534,13 @@ struct nfsd42_write_res { stateid_t cb_stateid; }; +struct nfsd4_cb_offload { + struct nfsd4_callback co_cb; + struct nfsd42_write_res co_res; + __be32 co_nfserr; + struct knfsd_fh co_fh; +}; + struct nfsd4_copy { /* request */ stateid_t cp_src_stateid; @@ -538,18 +548,16 @@ struct nfsd4_copy { u64 cp_src_pos; u64 cp_dst_pos; u64 cp_count; - struct nl4_server cp_src; - bool cp_intra; + struct nl4_server *cp_src; - /* both */ - u32 cp_synchronous; + unsigned long cp_flags; +#define NFSD4_COPY_F_STOPPED (0) +#define NFSD4_COPY_F_INTRA (1) +#define NFSD4_COPY_F_SYNCHRONOUS (2) +#define NFSD4_COPY_F_COMMITTED (3) /* response */ struct nfsd42_write_res cp_res; - - /* for cb_offload */ - struct nfsd4_callback cp_cb; - __be32 nfserr; struct knfsd_fh fh; struct nfs4_client *cp_clp; @@ -562,14 +570,35 @@ struct nfsd4_copy { struct list_head copies; struct task_struct *copy_task; refcount_t refcount; - bool stopped; struct vfsmount *ss_mnt; struct nfs_fh c_fh; nfs4_stateid stateid; - bool committed; }; +static inline void nfsd4_copy_set_sync(struct nfsd4_copy *copy, bool sync) +{ + if (sync) + set_bit(NFSD4_COPY_F_SYNCHRONOUS, ©->cp_flags); + else + clear_bit(NFSD4_COPY_F_SYNCHRONOUS, ©->cp_flags); +} + +static inline bool nfsd4_copy_is_sync(const struct nfsd4_copy *copy) +{ + return test_bit(NFSD4_COPY_F_SYNCHRONOUS, ©->cp_flags); +} + +static inline bool nfsd4_copy_is_async(const struct nfsd4_copy *copy) +{ + return !test_bit(NFSD4_COPY_F_SYNCHRONOUS, ©->cp_flags); +} + +static inline bool nfsd4_ssc_is_inter(const struct nfsd4_copy *copy) +{ + return !test_bit(NFSD4_COPY_F_INTRA, ©->cp_flags); +} + struct nfsd4_seek { /* request */ stateid_t seek_stateid; @@ -593,19 +622,20 @@ struct nfsd4_offload_status { struct nfsd4_copy_notify { /* request */ stateid_t cpn_src_stateid; - struct nl4_server cpn_dst; + struct nl4_server *cpn_dst; /* response */ stateid_t cpn_cnr_stateid; u64 cpn_sec; u32 cpn_nsec; - struct nl4_server cpn_src; + struct nl4_server *cpn_src; }; struct nfsd4_op { u32 opnum; - const struct nfsd4_operation * opdesc; __be32 status; + const struct nfsd4_operation *opdesc; + struct nfs4_replay *replay; union nfsd4_op_u { struct nfsd4_access access; struct nfsd4_close close; @@ -669,7 +699,6 @@ struct nfsd4_op { struct nfsd4_listxattrs listxattrs; struct nfsd4_removexattr removexattr; } u; - struct nfs4_replay * replay; }; bool nfsd4_cache_this_op(struct nfsd4_op *); @@ -688,13 +717,13 @@ struct nfsd4_compoundargs { struct svcxdr_tmpbuf *to_free; struct svc_rqst *rqstp; - u32 taglen; char * tag; + u32 taglen; u32 minorversion; + u32 client_opcnt; u32 opcnt; struct nfsd4_op *ops; struct nfsd4_op iops[8]; - int cachetype; }; struct nfsd4_compoundres { @@ -703,8 +732,8 @@ struct nfsd4_compoundres { struct svc_rqst * rqstp; __be32 *statusp; - u32 taglen; char * tag; + u32 taglen; u32 opcnt; struct nfsd4_compound_state cstate; @@ -859,7 +888,8 @@ struct nfsd4_operation { u32 op_flags; char *op_name; /* Try to get response size before operation */ - u32 (*op_rsize_bop)(struct svc_rqst *, struct nfsd4_op *); + u32 (*op_rsize_bop)(const struct svc_rqst *rqstp, + const struct nfsd4_op *op); void (*op_get_currentstateid)(struct nfsd4_compound_state *, union nfsd4_op_u *); void (*op_set_currentstateid)(struct nfsd4_compound_state *, |