diff options
Diffstat (limited to 'fs')
65 files changed, 3174 insertions, 2473 deletions
diff --git a/fs/attr.c b/fs/attr.c index 5d4e59d56e85..6530ced19697 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -50,14 +50,14 @@ int inode_change_ok(const struct inode *inode, struct iattr *attr) if ((ia_valid & ATTR_UID) && (!uid_eq(current_fsuid(), inode->i_uid) || !uid_eq(attr->ia_uid, inode->i_uid)) && - !inode_capable(inode, CAP_CHOWN)) + !capable_wrt_inode_uidgid(inode, CAP_CHOWN)) return -EPERM; /* Make sure caller can chgrp. */ if ((ia_valid & ATTR_GID) && (!uid_eq(current_fsuid(), inode->i_uid) || (!in_group_p(attr->ia_gid) && !gid_eq(attr->ia_gid, inode->i_gid))) && - !inode_capable(inode, CAP_CHOWN)) + !capable_wrt_inode_uidgid(inode, CAP_CHOWN)) return -EPERM; /* Make sure a caller can chmod. */ @@ -67,7 +67,7 @@ int inode_change_ok(const struct inode *inode, struct iattr *attr) /* Also check the setgid bit! */ if (!in_group_p((ia_valid & ATTR_GID) ? attr->ia_gid : inode->i_gid) && - !inode_capable(inode, CAP_FSETID)) + !capable_wrt_inode_uidgid(inode, CAP_FSETID)) attr->ia_mode &= ~S_ISGID; } @@ -160,7 +160,7 @@ void setattr_copy(struct inode *inode, const struct iattr *attr) umode_t mode = attr->ia_mode; if (!in_group_p(inode->i_gid) && - !inode_capable(inode, CAP_FSETID)) + !capable_wrt_inode_uidgid(inode, CAP_FSETID)) mode &= ~S_ISGID; inode->i_mode = mode; } diff --git a/fs/inode.c b/fs/inode.c index 2feb9b69f1be..6eecb7ff0b9a 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1839,14 +1839,18 @@ EXPORT_SYMBOL(inode_init_owner); * inode_owner_or_capable - check current task permissions to inode * @inode: inode being checked * - * Return true if current either has CAP_FOWNER to the inode, or - * owns the file. + * Return true if current either has CAP_FOWNER in a namespace with the + * inode owner uid mapped, or owns the file. */ bool inode_owner_or_capable(const struct inode *inode) { + struct user_namespace *ns; + if (uid_eq(current_fsuid(), inode->i_uid)) return true; - if (inode_capable(inode, CAP_FOWNER)) + + ns = current_user_ns(); + if (ns_capable(ns, CAP_FOWNER) && kuid_has_mapping(ns, inode->i_uid)) return true; return false; } diff --git a/fs/lockd/clnt4xdr.c b/fs/lockd/clnt4xdr.c index 00ec0b9c94d1..d3e40db28930 100644 --- a/fs/lockd/clnt4xdr.c +++ b/fs/lockd/clnt4xdr.c @@ -14,6 +14,8 @@ #include <linux/sunrpc/stats.h> #include <linux/lockd/lockd.h> +#include <uapi/linux/nfs3.h> + #define NLMDBG_FACILITY NLMDBG_XDR #if (NLMCLNT_OHSIZE > XDR_MAX_NETOBJ) diff --git a/fs/lockd/clntxdr.c b/fs/lockd/clntxdr.c index 9a55797a1cd4..3e9f7874b975 100644 --- a/fs/lockd/clntxdr.c +++ b/fs/lockd/clntxdr.c @@ -15,6 +15,8 @@ #include <linux/sunrpc/stats.h> #include <linux/lockd/lockd.h> +#include <uapi/linux/nfs2.h> + #define NLMDBG_FACILITY NLMDBG_XDR #if (NLMCLNT_OHSIZE > XDR_MAX_NETOBJ) diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index de051cb1f553..8f27c93f8d2e 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -622,8 +622,8 @@ static int __init init_nlm(void) err_pernet: #ifdef CONFIG_SYSCTL unregister_sysctl_table(nlm_sysctl_table); -#endif err_sysctl: +#endif return err; } diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c index dc5c75930f0f..b6f3b84b6e99 100644 --- a/fs/lockd/svcsubs.c +++ b/fs/lockd/svcsubs.c @@ -14,12 +14,11 @@ #include <linux/mutex.h> #include <linux/sunrpc/svc.h> #include <linux/sunrpc/addr.h> -#include <linux/nfsd/nfsfh.h> -#include <linux/nfsd/export.h> #include <linux/lockd/lockd.h> #include <linux/lockd/share.h> #include <linux/module.h> #include <linux/mount.h> +#include <uapi/linux/nfs2.h> #define NLMDBG_FACILITY NLMDBG_SVCSUBS diff --git a/fs/lockd/xdr.c b/fs/lockd/xdr.c index 964666c68a86..9340e7e10ef6 100644 --- a/fs/lockd/xdr.c +++ b/fs/lockd/xdr.c @@ -16,6 +16,8 @@ #include <linux/sunrpc/stats.h> #include <linux/lockd/lockd.h> +#include <uapi/linux/nfs2.h> + #define NLMDBG_FACILITY NLMDBG_XDR diff --git a/fs/namei.c b/fs/namei.c index 80168273396b..985c6f368485 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -332,10 +332,11 @@ int generic_permission(struct inode *inode, int mask) if (S_ISDIR(inode->i_mode)) { /* DACs are overridable for directories */ - if (inode_capable(inode, CAP_DAC_OVERRIDE)) + if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE)) return 0; if (!(mask & MAY_WRITE)) - if (inode_capable(inode, CAP_DAC_READ_SEARCH)) + if (capable_wrt_inode_uidgid(inode, + CAP_DAC_READ_SEARCH)) return 0; return -EACCES; } @@ -345,7 +346,7 @@ int generic_permission(struct inode *inode, int mask) * at least one exec bit set. */ if (!(mask & MAY_EXEC) || (inode->i_mode & S_IXUGO)) - if (inode_capable(inode, CAP_DAC_OVERRIDE)) + if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE)) return 0; /* @@ -353,7 +354,7 @@ int generic_permission(struct inode *inode, int mask) */ mask &= MAY_READ | MAY_WRITE | MAY_EXEC; if (mask == MAY_READ) - if (inode_capable(inode, CAP_DAC_READ_SEARCH)) + if (capable_wrt_inode_uidgid(inode, CAP_DAC_READ_SEARCH)) return 0; return -EACCES; @@ -2379,7 +2380,7 @@ static inline int check_sticky(struct inode *dir, struct inode *inode) return 0; if (uid_eq(dir->i_uid, fsuid)) return 0; - return !inode_capable(inode, CAP_FOWNER); + return !capable_wrt_inode_uidgid(inode, CAP_FOWNER); } /* diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile index 03192a66c143..4782e0840dcc 100644 --- a/fs/nfs/Makefile +++ b/fs/nfs/Makefile @@ -29,8 +29,6 @@ nfsv4-$(CONFIG_NFS_USE_LEGACY_DNS) += cache_lib.o nfsv4-$(CONFIG_SYSCTL) += nfs4sysctl.o nfsv4-$(CONFIG_NFS_V4_1) += pnfs.o pnfs_dev.o -obj-$(CONFIG_PNFS_FILE_LAYOUT) += nfs_layout_nfsv41_files.o -nfs_layout_nfsv41_files-y := nfs4filelayout.o nfs4filelayoutdev.o - +obj-$(CONFIG_PNFS_FILE_LAYOUT) += filelayout/ obj-$(CONFIG_PNFS_OBJLAYOUT) += objlayout/ obj-$(CONFIG_PNFS_BLOCK) += blocklayout/ diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index 65d849bdf77a..9b431f44fad9 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -210,7 +210,7 @@ static void bl_end_io_read(struct bio *bio, int err) SetPageUptodate(bvec->bv_page); if (err) { - struct nfs_read_data *rdata = par->data; + struct nfs_pgio_data *rdata = par->data; struct nfs_pgio_header *header = rdata->header; if (!header->pnfs_error) @@ -224,17 +224,17 @@ static void bl_end_io_read(struct bio *bio, int err) static void bl_read_cleanup(struct work_struct *work) { struct rpc_task *task; - struct nfs_read_data *rdata; + struct nfs_pgio_data *rdata; dprintk("%s enter\n", __func__); task = container_of(work, struct rpc_task, u.tk_work); - rdata = container_of(task, struct nfs_read_data, task); + rdata = container_of(task, struct nfs_pgio_data, task); pnfs_ld_read_done(rdata); } static void bl_end_par_io_read(void *data, int unused) { - struct nfs_read_data *rdata = data; + struct nfs_pgio_data *rdata = data; rdata->task.tk_status = rdata->header->pnfs_error; INIT_WORK(&rdata->task.u.tk_work, bl_read_cleanup); @@ -242,7 +242,7 @@ bl_end_par_io_read(void *data, int unused) } static enum pnfs_try_status -bl_read_pagelist(struct nfs_read_data *rdata) +bl_read_pagelist(struct nfs_pgio_data *rdata) { struct nfs_pgio_header *header = rdata->header; int i, hole; @@ -390,7 +390,7 @@ static void bl_end_io_write_zero(struct bio *bio, int err) } if (unlikely(err)) { - struct nfs_write_data *data = par->data; + struct nfs_pgio_data *data = par->data; struct nfs_pgio_header *header = data->header; if (!header->pnfs_error) @@ -405,7 +405,7 @@ static void bl_end_io_write(struct bio *bio, int err) { struct parallel_io *par = bio->bi_private; const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); - struct nfs_write_data *data = par->data; + struct nfs_pgio_data *data = par->data; struct nfs_pgio_header *header = data->header; if (!uptodate) { @@ -423,10 +423,10 @@ static void bl_end_io_write(struct bio *bio, int err) static void bl_write_cleanup(struct work_struct *work) { struct rpc_task *task; - struct nfs_write_data *wdata; + struct nfs_pgio_data *wdata; dprintk("%s enter\n", __func__); task = container_of(work, struct rpc_task, u.tk_work); - wdata = container_of(task, struct nfs_write_data, task); + wdata = container_of(task, struct nfs_pgio_data, task); if (likely(!wdata->header->pnfs_error)) { /* Marks for LAYOUTCOMMIT */ mark_extents_written(BLK_LSEG2EXT(wdata->header->lseg), @@ -438,7 +438,7 @@ static void bl_write_cleanup(struct work_struct *work) /* Called when last of bios associated with a bl_write_pagelist call finishes */ static void bl_end_par_io_write(void *data, int num_se) { - struct nfs_write_data *wdata = data; + struct nfs_pgio_data *wdata = data; if (unlikely(wdata->header->pnfs_error)) { bl_free_short_extents(&BLK_LSEG2EXT(wdata->header->lseg)->bl_inval, @@ -673,7 +673,7 @@ check_page: } static enum pnfs_try_status -bl_write_pagelist(struct nfs_write_data *wdata, int sync) +bl_write_pagelist(struct nfs_pgio_data *wdata, int sync) { struct nfs_pgio_header *header = wdata->header; int i, ret, npg_zero, pg_index, last = 0; @@ -1189,13 +1189,17 @@ bl_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) pnfs_generic_pg_init_read(pgio, req); } -static bool +/* + * Return 0 if @req cannot be coalesced into @pgio, otherwise return the number + * of bytes (maximum @req->wb_bytes) that can be coalesced. + */ +static size_t bl_pg_test_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, struct nfs_page *req) { if (pgio->pg_dreq != NULL && !is_aligned_req(req, SECTOR_SIZE)) - return false; + return 0; return pnfs_generic_pg_test(pgio, prev, req); } @@ -1241,13 +1245,17 @@ bl_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) } } -static bool +/* + * Return 0 if @req cannot be coalesced into @pgio, otherwise return the number + * of bytes (maximum @req->wb_bytes) that can be coalesced. + */ +static size_t bl_pg_test_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, struct nfs_page *req) { if (pgio->pg_dreq != NULL && !is_aligned_req(req, PAGE_CACHE_SIZE)) - return false; + return 0; return pnfs_generic_pg_test(pgio, prev, req); } diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index b8797ae6831f..4ad7bc388679 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -108,6 +108,97 @@ static inline int put_dreq(struct nfs_direct_req *dreq) return atomic_dec_and_test(&dreq->io_count); } +/* + * nfs_direct_select_verf - select the right verifier + * @dreq - direct request possibly spanning multiple servers + * @ds_clp - nfs_client of data server or NULL if MDS / non-pnfs + * @ds_idx - index of data server in data server list, only valid if ds_clp set + * + * returns the correct verifier to use given the role of the server + */ +static struct nfs_writeverf * +nfs_direct_select_verf(struct nfs_direct_req *dreq, + struct nfs_client *ds_clp, + int ds_idx) +{ + struct nfs_writeverf *verfp = &dreq->verf; + +#ifdef CONFIG_NFS_V4_1 + if (ds_clp) { + /* pNFS is in use, use the DS verf */ + if (ds_idx >= 0 && ds_idx < dreq->ds_cinfo.nbuckets) + verfp = &dreq->ds_cinfo.buckets[ds_idx].direct_verf; + else + WARN_ON_ONCE(1); + } +#endif + return verfp; +} + + +/* + * nfs_direct_set_hdr_verf - set the write/commit verifier + * @dreq - direct request possibly spanning multiple servers + * @hdr - pageio header to validate against previously seen verfs + * + * Set the server's (MDS or DS) "seen" verifier + */ +static void nfs_direct_set_hdr_verf(struct nfs_direct_req *dreq, + struct nfs_pgio_header *hdr) +{ + struct nfs_writeverf *verfp; + + verfp = nfs_direct_select_verf(dreq, hdr->data->ds_clp, + hdr->data->ds_idx); + WARN_ON_ONCE(verfp->committed >= 0); + memcpy(verfp, &hdr->verf, sizeof(struct nfs_writeverf)); + WARN_ON_ONCE(verfp->committed < 0); +} + +/* + * nfs_direct_cmp_hdr_verf - compare verifier for pgio header + * @dreq - direct request possibly spanning multiple servers + * @hdr - pageio header to validate against previously seen verf + * + * set the server's "seen" verf if not initialized. + * returns result of comparison between @hdr->verf and the "seen" + * verf of the server used by @hdr (DS or MDS) + */ +static int nfs_direct_set_or_cmp_hdr_verf(struct nfs_direct_req *dreq, + struct nfs_pgio_header *hdr) +{ + struct nfs_writeverf *verfp; + + verfp = nfs_direct_select_verf(dreq, hdr->data->ds_clp, + hdr->data->ds_idx); + if (verfp->committed < 0) { + nfs_direct_set_hdr_verf(dreq, hdr); + return 0; + } + return memcmp(verfp, &hdr->verf, sizeof(struct nfs_writeverf)); +} + +#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4) +/* + * nfs_direct_cmp_commit_data_verf - compare verifier for commit data + * @dreq - direct request possibly spanning multiple servers + * @data - commit data to validate against previously seen verf + * + * returns result of comparison between @data->verf and the verf of + * the server used by @data (DS or MDS) + */ +static int nfs_direct_cmp_commit_data_verf(struct nfs_direct_req *dreq, + struct nfs_commit_data *data) +{ + struct nfs_writeverf *verfp; + + verfp = nfs_direct_select_verf(dreq, data->ds_clp, + data->ds_commit_index); + WARN_ON_ONCE(verfp->committed < 0); + return memcmp(verfp, &data->verf, sizeof(struct nfs_writeverf)); +} +#endif + /** * nfs_direct_IO - NFS address space operation for direct I/O * @rw: direction (read or write) @@ -168,6 +259,7 @@ static inline struct nfs_direct_req *nfs_direct_req_alloc(void) kref_get(&dreq->kref); init_completion(&dreq->completion); INIT_LIST_HEAD(&dreq->mds_cinfo.list); + dreq->verf.committed = NFS_INVALID_STABLE_HOW; /* not set yet */ INIT_WORK(&dreq->work, nfs_direct_write_schedule_work); spin_lock_init(&dreq->lock); @@ -380,8 +472,7 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_pageio_descriptor *de struct nfs_page *req; unsigned int req_len = min_t(size_t, bytes, PAGE_SIZE - pgbase); /* XXX do we need to do the eof zeroing found in async_filler? */ - req = nfs_create_request(dreq->ctx, dreq->inode, - pagevec[i], + req = nfs_create_request(dreq->ctx, pagevec[i], NULL, pgbase, req_len); if (IS_ERR(req)) { result = PTR_ERR(req); @@ -424,7 +515,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, size_t requested_bytes = 0; unsigned long seg; - NFS_PROTO(dreq->inode)->read_pageio_init(&desc, dreq->inode, + nfs_pageio_init_read(&desc, dreq->inode, false, &nfs_direct_read_completion_ops); get_dreq(dreq); desc.pg_dreq = dreq; @@ -564,7 +655,7 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) dreq->count = 0; get_dreq(dreq); - NFS_PROTO(dreq->inode)->write_pageio_init(&desc, dreq->inode, FLUSH_STABLE, + nfs_pageio_init_write(&desc, dreq->inode, FLUSH_STABLE, false, &nfs_direct_write_completion_ops); desc.pg_dreq = dreq; @@ -603,7 +694,7 @@ static void nfs_direct_commit_complete(struct nfs_commit_data *data) dprintk("NFS: %5u commit failed with error %d.\n", data->task.tk_pid, status); dreq->flags = NFS_ODIRECT_RESCHED_WRITES; - } else if (memcmp(&dreq->verf, &data->verf, sizeof(data->verf))) { + } else if (nfs_direct_cmp_commit_data_verf(dreq, data)) { dprintk("NFS: %5u commit verify failed\n", data->task.tk_pid); dreq->flags = NFS_ODIRECT_RESCHED_WRITES; } @@ -750,8 +841,7 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_pageio_descriptor *d struct nfs_page *req; unsigned int req_len = min_t(size_t, bytes, PAGE_SIZE - pgbase); - req = nfs_create_request(dreq->ctx, dreq->inode, - pagevec[i], + req = nfs_create_request(dreq->ctx, pagevec[i], NULL, pgbase, req_len); if (IS_ERR(req)) { result = PTR_ERR(req); @@ -813,13 +903,13 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr) if (dreq->flags == NFS_ODIRECT_RESCHED_WRITES) bit = NFS_IOHDR_NEED_RESCHED; else if (dreq->flags == 0) { - memcpy(&dreq->verf, hdr->verf, - sizeof(dreq->verf)); + nfs_direct_set_hdr_verf(dreq, hdr); bit = NFS_IOHDR_NEED_COMMIT; dreq->flags = NFS_ODIRECT_DO_COMMIT; } else if (dreq->flags == NFS_ODIRECT_DO_COMMIT) { - if (memcmp(&dreq->verf, hdr->verf, sizeof(dreq->verf))) { - dreq->flags = NFS_ODIRECT_RESCHED_WRITES; + if (nfs_direct_set_or_cmp_hdr_verf(dreq, hdr)) { + dreq->flags = + NFS_ODIRECT_RESCHED_WRITES; bit = NFS_IOHDR_NEED_RESCHED; } else bit = NFS_IOHDR_NEED_COMMIT; @@ -829,6 +919,8 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr) spin_unlock(&dreq->lock); while (!list_empty(&hdr->pages)) { + bool do_destroy = true; + req = nfs_list_entry(hdr->pages.next); nfs_list_remove_request(req); switch (bit) { @@ -836,6 +928,7 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr) case NFS_IOHDR_NEED_COMMIT: kref_get(&req->wb_kref); nfs_mark_request_commit(req, hdr->lseg, &cinfo); + do_destroy = false; } nfs_unlock_and_release_request(req); } @@ -874,7 +967,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, size_t requested_bytes = 0; unsigned long seg; - NFS_PROTO(inode)->write_pageio_init(&desc, inode, FLUSH_COND_STABLE, + nfs_pageio_init_write(&desc, inode, FLUSH_COND_STABLE, false, &nfs_direct_write_completion_ops); desc.pg_dreq = dreq; get_dreq(dreq); diff --git a/fs/nfs/filelayout/Makefile b/fs/nfs/filelayout/Makefile new file mode 100644 index 000000000000..8516cdffb9e9 --- /dev/null +++ b/fs/nfs/filelayout/Makefile @@ -0,0 +1,5 @@ +# +# Makefile for the pNFS Files Layout Driver kernel module +# +obj-$(CONFIG_PNFS_FILE_LAYOUT) += nfs_layout_nfsv41_files.o +nfs_layout_nfsv41_files-y := filelayout.o filelayoutdev.o diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/filelayout/filelayout.c index b9a35c05b60f..d2eba1c13b7e 100644 --- a/fs/nfs/nfs4filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -35,11 +35,11 @@ #include <linux/sunrpc/metrics.h> -#include "nfs4session.h" -#include "internal.h" -#include "delegation.h" -#include "nfs4filelayout.h" -#include "nfs4trace.h" +#include "../nfs4session.h" +#include "../internal.h" +#include "../delegation.h" +#include "filelayout.h" +#include "../nfs4trace.h" #define NFSDBG_FACILITY NFSDBG_PNFS_LD @@ -84,7 +84,7 @@ filelayout_get_dserver_offset(struct pnfs_layout_segment *lseg, loff_t offset) BUG(); } -static void filelayout_reset_write(struct nfs_write_data *data) +static void filelayout_reset_write(struct nfs_pgio_data *data) { struct nfs_pgio_header *hdr = data->header; struct rpc_task *task = &data->task; @@ -105,7 +105,7 @@ static void filelayout_reset_write(struct nfs_write_data *data) } } -static void filelayout_reset_read(struct nfs_read_data *data) +static void filelayout_reset_read(struct nfs_pgio_data *data) { struct nfs_pgio_header *hdr = data->header; struct rpc_task *task = &data->task; @@ -243,7 +243,7 @@ wait_on_recovery: /* NFS_PROTO call done callback routines */ static int filelayout_read_done_cb(struct rpc_task *task, - struct nfs_read_data *data) + struct nfs_pgio_data *data) { struct nfs_pgio_header *hdr = data->header; int err; @@ -270,7 +270,7 @@ static int filelayout_read_done_cb(struct rpc_task *task, * rfc5661 is not clear about which credential should be used. */ static void -filelayout_set_layoutcommit(struct nfs_write_data *wdata) +filelayout_set_layoutcommit(struct nfs_pgio_data *wdata) { struct nfs_pgio_header *hdr = wdata->header; @@ -279,7 +279,7 @@ filelayout_set_layoutcommit(struct nfs_write_data *wdata) return; pnfs_set_layoutcommit(wdata); - dprintk("%s ionde %lu pls_end_pos %lu\n", __func__, hdr->inode->i_ino, + dprintk("%s inode %lu pls_end_pos %lu\n", __func__, hdr->inode->i_ino, (unsigned long) NFS_I(hdr->inode)->layout->plh_lwb); } @@ -305,7 +305,7 @@ filelayout_reset_to_mds(struct pnfs_layout_segment *lseg) */ static void filelayout_read_prepare(struct rpc_task *task, void *data) { - struct nfs_read_data *rdata = data; + struct nfs_pgio_data *rdata = data; if (unlikely(test_bit(NFS_CONTEXT_BAD, &rdata->args.context->flags))) { rpc_exit(task, -EIO); @@ -317,7 +317,7 @@ static void filelayout_read_prepare(struct rpc_task *task, void *data) rpc_exit(task, 0); return; } - rdata->read_done_cb = filelayout_read_done_cb; + rdata->pgio_done_cb = filelayout_read_done_cb; if (nfs41_setup_sequence(rdata->ds_clp->cl_session, &rdata->args.seq_args, @@ -331,7 +331,7 @@ static void filelayout_read_prepare(struct rpc_task *task, void *data) static void filelayout_read_call_done(struct rpc_task *task, void *data) { - struct nfs_read_data *rdata = data; + struct nfs_pgio_data *rdata = data; dprintk("--> %s task->tk_status %d\n", __func__, task->tk_status); @@ -347,14 +347,14 @@ static void filelayout_read_call_done(struct rpc_task *task, void *data) static void filelayout_read_count_stats(struct rpc_task *task, void *data) { - struct nfs_read_data *rdata = data; + struct nfs_pgio_data *rdata = data; rpc_count_iostats(task, NFS_SERVER(rdata->header->inode)->client->cl_metrics); } static void filelayout_read_release(void *data) { - struct nfs_read_data *rdata = data; + struct nfs_pgio_data *rdata = data; struct pnfs_layout_hdr *lo = rdata->header->lseg->pls_layout; filelayout_fenceme(lo->plh_inode, lo); @@ -363,7 +363,7 @@ static void filelayout_read_release(void *data) } static int filelayout_write_done_cb(struct rpc_task *task, - struct nfs_write_data *data) + struct nfs_pgio_data *data) { struct nfs_pgio_header *hdr = data->header; int err; @@ -419,7 +419,7 @@ static int filelayout_commit_done_cb(struct rpc_task *task, static void filelayout_write_prepare(struct rpc_task *task, void *data) { - struct nfs_write_data *wdata = data; + struct nfs_pgio_data *wdata = data; if (unlikely(test_bit(NFS_CONTEXT_BAD, &wdata->args.context->flags))) { rpc_exit(task, -EIO); @@ -443,7 +443,7 @@ static void filelayout_write_prepare(struct rpc_task *task, void *data) static void filelayout_write_call_done(struct rpc_task *task, void *data) { - struct nfs_write_data *wdata = data; + struct nfs_pgio_data *wdata = data; if (test_bit(NFS_IOHDR_REDO, &wdata->header->flags) && task->tk_status == 0) { @@ -457,14 +457,14 @@ static void filelayout_write_call_done(struct rpc_task *task, void *data) static void filelayout_write_count_stats(struct rpc_task *task, void *data) { - struct nfs_write_data *wdata = data; + struct nfs_pgio_data *wdata = data; rpc_count_iostats(task, NFS_SERVER(wdata->header->inode)->client->cl_metrics); } static void filelayout_write_release(void *data) { - struct nfs_write_data *wdata = data; + struct nfs_pgio_data *wdata = data; struct pnfs_layout_hdr *lo = wdata->header->lseg->pls_layout; filelayout_fenceme(lo->plh_inode, lo); @@ -529,7 +529,7 @@ static const struct rpc_call_ops filelayout_commit_call_ops = { }; static enum pnfs_try_status -filelayout_read_pagelist(struct nfs_read_data *data) +filelayout_read_pagelist(struct nfs_pgio_data *data) { struct nfs_pgio_header *hdr = data->header; struct pnfs_layout_segment *lseg = hdr->lseg; @@ -560,6 +560,7 @@ filelayout_read_pagelist(struct nfs_read_data *data) /* No multipath support. Use first DS */ atomic_inc(&ds->ds_clp->cl_count); data->ds_clp = ds->ds_clp; + data->ds_idx = idx; fh = nfs4_fl_select_ds_fh(lseg, j); if (fh) data->args.fh = fh; @@ -568,14 +569,14 @@ filelayout_read_pagelist(struct nfs_read_data *data) data->mds_offset = offset; /* Perform an asynchronous read to ds */ - nfs_initiate_read(ds_clnt, data, - &filelayout_read_call_ops, RPC_TASK_SOFTCONN); + nfs_initiate_pgio(ds_clnt, data, + &filelayout_read_call_ops, 0, RPC_TASK_SOFTCONN); return PNFS_ATTEMPTED; } /* Perform async writes. */ static enum pnfs_try_status -filelayout_write_pagelist(struct nfs_write_data *data, int sync) +filelayout_write_pagelist(struct nfs_pgio_data *data, int sync) { struct nfs_pgio_header *hdr = data->header; struct pnfs_layout_segment *lseg = hdr->lseg; @@ -600,20 +601,18 @@ filelayout_write_pagelist(struct nfs_write_data *data, int sync) __func__, hdr->inode->i_ino, sync, (size_t) data->args.count, offset, ds->ds_remotestr, atomic_read(&ds->ds_clp->cl_count)); - data->write_done_cb = filelayout_write_done_cb; + data->pgio_done_cb = filelayout_write_done_cb; atomic_inc(&ds->ds_clp->cl_count); data->ds_clp = ds->ds_clp; + data->ds_idx = idx; fh = nfs4_fl_select_ds_fh(lseg, j); if (fh) data->args.fh = fh; - /* - * Get the file offset on the dserver. Set the write offset to - * this offset and save the original offset. - */ + data->args.offset = filelayout_get_dserver_offset(lseg, offset); /* Perform an asynchronous write */ - nfs_initiate_write(ds_clnt, data, + nfs_initiate_pgio(ds_clnt, data, &filelayout_write_call_ops, sync, RPC_TASK_SOFTCONN); return PNFS_ATTEMPTED; @@ -637,7 +636,6 @@ filelayout_check_layout(struct pnfs_layout_hdr *lo, struct nfs4_deviceid_node *d; struct nfs4_file_layout_dsaddr *dsaddr; int status = -EINVAL; - struct nfs_server *nfss = NFS_SERVER(lo->plh_inode); dprintk("--> %s\n", __func__); @@ -655,7 +653,7 @@ filelayout_check_layout(struct pnfs_layout_hdr *lo, goto out; } - if (!fl->stripe_unit || fl->stripe_unit % PAGE_SIZE) { + if (!fl->stripe_unit) { dprintk("%s Invalid stripe unit (%u)\n", __func__, fl->stripe_unit); goto out; @@ -692,12 +690,6 @@ filelayout_check_layout(struct pnfs_layout_hdr *lo, goto out_put; } - if (fl->stripe_unit % nfss->rsize || fl->stripe_unit % nfss->wsize) { - dprintk("%s Stripe unit (%u) not aligned with rsize %u " - "wsize %u\n", __func__, fl->stripe_unit, nfss->rsize, - nfss->wsize); - } - status = 0; out: dprintk("--> %s returns %d\n", __func__, status); @@ -850,11 +842,15 @@ filelayout_alloc_commit_info(struct pnfs_layout_segment *lseg, { struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg); struct pnfs_commit_bucket *buckets; - int size; + int size, i; if (fl->commit_through_mds) return 0; - if (cinfo->ds->nbuckets != 0) { + + size = (fl->stripe_type == STRIPE_SPARSE) ? + fl->dsaddr->ds_num : fl->dsaddr->stripe_count; + + if (cinfo->ds->nbuckets >= size) { /* This assumes there is only one IOMODE_RW lseg. What * we really want to do is have a layout_hdr level * dictionary of <multipath_list4, fh> keys, each @@ -864,30 +860,36 @@ filelayout_alloc_commit_info(struct pnfs_layout_segment *lseg, return 0; } - size = (fl->stripe_type == STRIPE_SPARSE) ? - fl->dsaddr->ds_num : fl->dsaddr->stripe_count; - buckets = kcalloc(size, sizeof(struct pnfs_commit_bucket), gfp_flags); if (!buckets) return -ENOMEM; - else { - int i; + for (i = 0; i < size; i++) { + INIT_LIST_HEAD(&buckets[i].written); + INIT_LIST_HEAD(&buckets[i].committing); + /* mark direct verifier as unset */ + buckets[i].direct_verf.committed = NFS_INVALID_STABLE_HOW; + } - spin_lock(cinfo->lock); - if (cinfo->ds->nbuckets != 0) - kfree(buckets); - else { - cinfo->ds->buckets = buckets; - cinfo->ds->nbuckets = size; - for (i = 0; i < size; i++) { - INIT_LIST_HEAD(&buckets[i].written); - INIT_LIST_HEAD(&buckets[i].committing); - } - } - spin_unlock(cinfo->lock); - return 0; + spin_lock(cinfo->lock); + if (cinfo->ds->nbuckets >= size) + goto out; + for (i = 0; i < cinfo->ds->nbuckets; i++) { + list_splice(&cinfo->ds->buckets[i].written, + &buckets[i].written); + list_splice(&cinfo->ds->buckets[i].committing, + &buckets[i].committing); + buckets[i].direct_verf.committed = + cinfo->ds->buckets[i].direct_verf.committed; + buckets[i].wlseg = cinfo->ds->buckets[i].wlseg; + buckets[i].clseg = cinfo->ds->buckets[i].clseg; } + swap(cinfo->ds->buckets, buckets); + cinfo->ds->nbuckets = size; +out: + spin_unlock(cinfo->lock); + kfree(buckets); + return 0; } static struct pnfs_layout_segment * @@ -915,47 +917,51 @@ filelayout_alloc_lseg(struct pnfs_layout_hdr *layoutid, /* * filelayout_pg_test(). Called by nfs_can_coalesce_requests() * - * return true : coalesce page - * return false : don't coalesce page + * Return 0 if @req cannot be coalesced into @pgio, otherwise return the number + * of bytes (maximum @req->wb_bytes) that can be coalesced. */ -static bool +static size_t filelayout_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, struct nfs_page *req) { + unsigned int size; u64 p_stripe, r_stripe; - u32 stripe_unit; + u32 stripe_offset; + u64 segment_offset = pgio->pg_lseg->pls_range.offset; + u32 stripe_unit = FILELAYOUT_LSEG(pgio->pg_lseg)->stripe_unit; - if (!pnfs_generic_pg_test(pgio, prev, req) || - !nfs_generic_pg_test(pgio, prev, req)) - return false; + /* calls nfs_generic_pg_test */ + size = pnfs_generic_pg_test(pgio, prev, req); + if (!size) + return 0; - p_stripe = (u64)req_offset(prev); - r_stripe = (u64)req_offset(req); - stripe_unit = FILELAYOUT_LSEG(pgio->pg_lseg)->stripe_unit; + /* see if req and prev are in the same stripe */ + if (prev) { + p_stripe = (u64)req_offset(prev) - segment_offset; + r_stripe = (u64)req_offset(req) - segment_offset; + do_div(p_stripe, stripe_unit); + do_div(r_stripe, stripe_unit); - do_div(p_stripe, stripe_unit); - do_div(r_stripe, stripe_unit); + if (p_stripe != r_stripe) + return 0; + } - return (p_stripe == r_stripe); + /* calculate remaining bytes in the current stripe */ + div_u64_rem((u64)req_offset(req) - segment_offset, + stripe_unit, + &stripe_offset); + WARN_ON_ONCE(stripe_offset > stripe_unit); + if (stripe_offset >= stripe_unit) + return 0; + return min(stripe_unit - (unsigned int)stripe_offset, size); } static void filelayout_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) { - WARN_ON_ONCE(pgio->pg_lseg != NULL); - - if (req->wb_offset != req->wb_pgbase) { - /* - * Handling unaligned pages is difficult, because have to - * somehow split a req in two in certain cases in the - * pg.test code. Avoid this by just not using pnfs - * in this case. - */ - nfs_pageio_reset_read_mds(pgio); - return; - } - pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, + if (!pgio->pg_lseg) + pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, req->wb_context, 0, NFS4_MAX_UINT64, @@ -973,11 +979,8 @@ filelayout_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_commit_info cinfo; int status; - WARN_ON_ONCE(pgio->pg_lseg != NULL); - - if (req->wb_offset != req->wb_pgbase) - goto out_mds; - pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, + if (!pgio->pg_lseg) + pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, req->wb_context, 0, NFS4_MAX_UINT64, @@ -1067,6 +1070,7 @@ filelayout_choose_commit_list(struct nfs_page *req, */ j = nfs4_fl_calc_j_index(lseg, req_offset(req)); i = select_bucket_index(fl, j); + spin_lock(cinfo->lock); buckets = cinfo->ds->buckets; list = &buckets[i].written; if (list_empty(list)) { @@ -1080,6 +1084,7 @@ filelayout_choose_commit_list(struct nfs_page *req, } set_bit(PG_COMMIT_TO_DS, &req->wb_flags); cinfo->ds->nwritten++; + spin_unlock(cinfo->lock); return list; } @@ -1176,6 +1181,7 @@ transfer_commit_list(struct list_head *src, struct list_head *dst, return ret; } +/* Note called with cinfo->lock held. */ static int filelayout_scan_ds_commit_list(struct pnfs_commit_bucket *bucket, struct nfs_commit_info *cinfo, @@ -1220,15 +1226,18 @@ static void filelayout_recover_commit_reqs(struct list_head *dst, struct nfs_commit_info *cinfo) { struct pnfs_commit_bucket *b; + struct pnfs_layout_segment *freeme; int i; +restart: spin_lock(cinfo->lock); for (i = 0, b = cinfo->ds->buckets; i < cinfo->ds->nbuckets; i++, b++) { if (transfer_commit_list(&b->written, dst, cinfo, 0)) { - spin_unlock(cinfo->lock); - pnfs_put_lseg(b->wlseg); + freeme = b->wlseg; b->wlseg = NULL; - spin_lock(cinfo->lock); + spin_unlock(cinfo->lock); + pnfs_put_lseg(freeme); + goto restart; } } cinfo->ds->nwritten = 0; @@ -1243,6 +1252,7 @@ alloc_ds_commits(struct nfs_commit_info *cinfo, struct list_head *list) struct nfs_commit_data *data; int i, j; unsigned int nreq = 0; + struct pnfs_layout_segment *freeme; fl_cinfo = cinfo->ds; bucket = fl_cinfo->buckets; @@ -1253,8 +1263,10 @@ alloc_ds_commits(struct nfs_commit_info *cinfo, struct list_head *list) if (!data) break; data->ds_commit_index = i; + spin_lock(cinfo->lock); data->lseg = bucket->clseg; bucket->clseg = NULL; + spin_unlock(cinfo->lock); list_add(&data->pages, list); nreq++; } @@ -1264,8 +1276,11 @@ alloc_ds_commits(struct nfs_commit_info *cinfo, struct list_head *list) if (list_empty(&bucket->committing)) continue; nfs_retry_commit(&bucket->committing, bucket->clseg, cinfo); - pnfs_put_lseg(bucket->clseg); + spin_lock(cinfo->lock); + freeme = bucket->clseg; bucket->clseg = NULL; + spin_unlock(cinfo->lock); + pnfs_put_lseg(freeme); } /* Caller will clean up entries put on list */ return nreq; @@ -1330,7 +1345,7 @@ filelayout_alloc_layout_hdr(struct inode *inode, gfp_t gfp_flags) struct nfs4_filelayout *flo; flo = kzalloc(sizeof(*flo), gfp_flags); - return &flo->generic_hdr; + return flo != NULL ? &flo->generic_hdr : NULL; } static void diff --git a/fs/nfs/nfs4filelayout.h b/fs/nfs/filelayout/filelayout.h index cebd20e7e923..ffbddf2219ea 100644 --- a/fs/nfs/nfs4filelayout.h +++ b/fs/nfs/filelayout/filelayout.h @@ -30,7 +30,7 @@ #ifndef FS_NFS_NFS4FILELAYOUT_H #define FS_NFS_NFS4FILELAYOUT_H -#include "pnfs.h" +#include "../pnfs.h" /* * Default data server connection timeout and retrans vaules. diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c index b9c61efe9660..44bf0140a4c7 100644 --- a/fs/nfs/nfs4filelayoutdev.c +++ b/fs/nfs/filelayout/filelayoutdev.c @@ -33,9 +33,9 @@ #include <linux/module.h> #include <linux/sunrpc/addr.h> -#include "internal.h" -#include "nfs4session.h" -#include "nfs4filelayout.h" +#include "../internal.h" +#include "../nfs4session.h" +#include "filelayout.h" #define NFSDBG_FACILITY NFSDBG_PNFS_LD diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c index 66984a9aafaa..b94f80420a58 100644 --- a/fs/nfs/getroot.c +++ b/fs/nfs/getroot.c @@ -120,7 +120,8 @@ struct dentry *nfs_get_root(struct super_block *sb, struct nfs_fh *mntfh, security_d_instantiate(ret, inode); spin_lock(&ret->d_lock); - if (IS_ROOT(ret) && !(ret->d_flags & DCACHE_NFSFS_RENAMED)) { + if (IS_ROOT(ret) && !ret->d_fsdata && + !(ret->d_flags & DCACHE_NFSFS_RENAMED)) { ret->d_fsdata = name; name = NULL; } diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index e6f7398d2b3c..c496f8a74639 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -1575,18 +1575,20 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) inode->i_version = fattr->change_attr; } } else if (server->caps & NFS_CAP_CHANGE_ATTR) - invalid |= save_cache_validity; + nfsi->cache_validity |= save_cache_validity; if (fattr->valid & NFS_ATTR_FATTR_MTIME) { memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime)); } else if (server->caps & NFS_CAP_MTIME) - invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR + nfsi->cache_validity |= save_cache_validity & + (NFS_INO_INVALID_ATTR | NFS_INO_REVAL_FORCED); if (fattr->valid & NFS_ATTR_FATTR_CTIME) { memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime)); } else if (server->caps & NFS_CAP_CTIME) - invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR + nfsi->cache_validity |= save_cache_validity & + (NFS_INO_INVALID_ATTR | NFS_INO_REVAL_FORCED); /* Check if our cached file size is stale */ @@ -1608,7 +1610,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) (long long)new_isize); } } else - invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR + nfsi->cache_validity |= save_cache_validity & + (NFS_INO_INVALID_ATTR | NFS_INO_REVAL_PAGECACHE | NFS_INO_REVAL_FORCED); @@ -1616,7 +1619,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) if (fattr->valid & NFS_ATTR_FATTR_ATIME) memcpy(&inode->i_atime, &fattr->atime, sizeof(inode->i_atime)); else if (server->caps & NFS_CAP_ATIME) - invalid |= save_cache_validity & (NFS_INO_INVALID_ATIME + nfsi->cache_validity |= save_cache_validity & + (NFS_INO_INVALID_ATIME | NFS_INO_REVAL_FORCED); if (fattr->valid & NFS_ATTR_FATTR_MODE) { @@ -1627,7 +1631,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL; } } else if (server->caps & NFS_CAP_MODE) - invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR + nfsi->cache_validity |= save_cache_validity & + (NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_REVAL_FORCED); @@ -1638,7 +1643,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) inode->i_uid = fattr->uid; } } else if (server->caps & NFS_CAP_OWNER) - invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR + nfsi->cache_validity |= save_cache_validity & + (NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_REVAL_FORCED); @@ -1649,7 +1655,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) inode->i_gid = fattr->gid; } } else if (server->caps & NFS_CAP_OWNER_GROUP) - invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR + nfsi->cache_validity |= save_cache_validity & + (NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_REVAL_FORCED); @@ -1662,7 +1669,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) set_nlink(inode, fattr->nlink); } } else if (server->caps & NFS_CAP_NLINK) - invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR + nfsi->cache_validity |= save_cache_validity & + (NFS_INO_INVALID_ATTR | NFS_INO_REVAL_FORCED); if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) { diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index dd8bfc2e2464..8b69cba1bb04 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -231,13 +231,20 @@ extern void nfs_destroy_writepagecache(void); extern int __init nfs_init_directcache(void); extern void nfs_destroy_directcache(void); -extern bool nfs_pgarray_set(struct nfs_page_array *p, unsigned int pagecount); extern void nfs_pgheader_init(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr, void (*release)(struct nfs_pgio_header *hdr)); void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos); int nfs_iocounter_wait(struct nfs_io_counter *c); +extern const struct nfs_pageio_ops nfs_pgio_rw_ops; +struct nfs_rw_header *nfs_rw_header_alloc(const struct nfs_rw_ops *); +void nfs_rw_header_free(struct nfs_pgio_header *); +void nfs_pgio_data_release(struct nfs_pgio_data *); +int nfs_generic_pgio(struct nfs_pageio_descriptor *, struct nfs_pgio_header *); +int nfs_initiate_pgio(struct rpc_clnt *, struct nfs_pgio_data *, + const struct rpc_call_ops *, int, int); + static inline void nfs_iocounter_init(struct nfs_io_counter *c) { c->flags = 0; @@ -395,19 +402,11 @@ extern int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh, bool struct nfs_pgio_completion_ops; /* read.c */ -extern struct nfs_read_header *nfs_readhdr_alloc(void); -extern void nfs_readhdr_free(struct nfs_pgio_header *hdr); extern void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, - struct inode *inode, + struct inode *inode, bool force_mds, const struct nfs_pgio_completion_ops *compl_ops); -extern int nfs_initiate_read(struct rpc_clnt *clnt, - struct nfs_read_data *data, - const struct rpc_call_ops *call_ops, int flags); extern void nfs_read_prepare(struct rpc_task *task, void *calldata); -extern int nfs_generic_pagein(struct nfs_pageio_descriptor *desc, - struct nfs_pgio_header *hdr); extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio); -extern void nfs_readdata_release(struct nfs_read_data *rdata); /* super.c */ void nfs_clone_super(struct super_block *, struct nfs_mount_info *); @@ -422,19 +421,10 @@ int nfs_remount(struct super_block *sb, int *flags, char *raw_data); /* write.c */ extern void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, - struct inode *inode, int ioflags, + struct inode *inode, int ioflags, bool force_mds, const struct nfs_pgio_completion_ops *compl_ops); -extern struct nfs_write_header *nfs_writehdr_alloc(void); -extern void nfs_writehdr_free(struct nfs_pgio_header *hdr); -extern int nfs_generic_flush(struct nfs_pageio_descriptor *desc, - struct nfs_pgio_header *hdr); extern void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio); -extern void nfs_writedata_release(struct nfs_write_data *wdata); extern void nfs_commit_free(struct nfs_commit_data *p); -extern int nfs_initiate_write(struct rpc_clnt *clnt, - struct nfs_write_data *data, - const struct rpc_call_ops *call_ops, - int how, int flags); 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, @@ -447,6 +437,7 @@ extern void nfs_init_commit(struct nfs_commit_data *data, struct nfs_commit_info *cinfo); int nfs_scan_commit_list(struct list_head *src, struct list_head *dst, struct nfs_commit_info *cinfo, int max); +unsigned long nfs_reqs_to_commit(struct nfs_commit_info *); int nfs_scan_commit(struct inode *inode, struct list_head *dst, struct nfs_commit_info *cinfo); void nfs_mark_request_commit(struct nfs_page *req, @@ -492,7 +483,7 @@ static inline void nfs_inode_dio_wait(struct inode *inode) extern ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq); /* nfs4proc.c */ -extern void __nfs4_read_done_cb(struct nfs_read_data *); +extern void __nfs4_read_done_cb(struct nfs_pgio_data *); extern struct nfs_client *nfs4_init_client(struct nfs_client *clp, const struct rpc_timeout *timeparms, const char *ip_addr); diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c index 62db136339ea..5f61b83f4a1c 100644 --- a/fs/nfs/nfs2xdr.c +++ b/fs/nfs/nfs2xdr.c @@ -103,7 +103,7 @@ static void print_overflow_msg(const char *func, const struct xdr_stream *xdr) /* * typedef opaque nfsdata<>; */ -static int decode_nfsdata(struct xdr_stream *xdr, struct nfs_readres *result) +static int decode_nfsdata(struct xdr_stream *xdr, struct nfs_pgio_res *result) { u32 recvd, count; __be32 *p; @@ -613,7 +613,7 @@ static void nfs2_xdr_enc_readlinkargs(struct rpc_rqst *req, * }; */ static void encode_readargs(struct xdr_stream *xdr, - const struct nfs_readargs *args) + const struct nfs_pgio_args *args) { u32 offset = args->offset; u32 count = args->count; @@ -629,7 +629,7 @@ static void encode_readargs(struct xdr_stream *xdr, static void nfs2_xdr_enc_readargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_readargs *args) + const struct nfs_pgio_args *args) { encode_readargs(xdr, args); prepare_reply_buffer(req, args->pages, args->pgbase, @@ -649,7 +649,7 @@ static void nfs2_xdr_enc_readargs(struct rpc_rqst *req, * }; */ static void encode_writeargs(struct xdr_stream *xdr, - const struct nfs_writeargs *args) + const struct nfs_pgio_args *args) { u32 offset = args->offset; u32 count = args->count; @@ -669,7 +669,7 @@ static void encode_writeargs(struct xdr_stream *xdr, static void nfs2_xdr_enc_writeargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_writeargs *args) + const struct nfs_pgio_args *args) { encode_writeargs(xdr, args); xdr->buf->flags |= XDRBUF_WRITE; @@ -857,7 +857,7 @@ out_default: * }; */ static int nfs2_xdr_dec_readres(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_readres *result) + struct nfs_pgio_res *result) { enum nfs_stat status; int error; @@ -878,7 +878,7 @@ out_default: } static int nfs2_xdr_dec_writeres(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_writeres *result) + struct nfs_pgio_res *result) { /* All NFSv2 writes are "file sync" writes */ result->verf->committed = NFS_FILE_SYNC; diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index db60149c4579..e7daa42bbc86 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -795,7 +795,7 @@ nfs3_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle, return status; } -static int nfs3_read_done(struct rpc_task *task, struct nfs_read_data *data) +static int nfs3_read_done(struct rpc_task *task, struct nfs_pgio_data *data) { struct inode *inode = data->header->inode; @@ -807,18 +807,18 @@ static int nfs3_read_done(struct rpc_task *task, struct nfs_read_data *data) return 0; } -static void nfs3_proc_read_setup(struct nfs_read_data *data, struct rpc_message *msg) +static void nfs3_proc_read_setup(struct nfs_pgio_data *data, struct rpc_message *msg) { msg->rpc_proc = &nfs3_procedures[NFS3PROC_READ]; } -static int nfs3_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_data *data) +static int nfs3_proc_pgio_rpc_prepare(struct rpc_task *task, struct nfs_pgio_data *data) { rpc_call_start(task); return 0; } -static int nfs3_write_done(struct rpc_task *task, struct nfs_write_data *data) +static int nfs3_write_done(struct rpc_task *task, struct nfs_pgio_data *data) { struct inode *inode = data->header->inode; @@ -829,17 +829,11 @@ static int nfs3_write_done(struct rpc_task *task, struct nfs_write_data *data) return 0; } -static void nfs3_proc_write_setup(struct nfs_write_data *data, struct rpc_message *msg) +static void nfs3_proc_write_setup(struct nfs_pgio_data *data, struct rpc_message *msg) { msg->rpc_proc = &nfs3_procedures[NFS3PROC_WRITE]; } -static int nfs3_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_data *data) -{ - rpc_call_start(task); - return 0; -} - static void nfs3_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commit_data *data) { rpc_call_start(task); @@ -946,13 +940,10 @@ const struct nfs_rpc_ops nfs_v3_clientops = { .fsinfo = nfs3_proc_fsinfo, .pathconf = nfs3_proc_pathconf, .decode_dirent = nfs3_decode_dirent, + .pgio_rpc_prepare = nfs3_proc_pgio_rpc_prepare, .read_setup = nfs3_proc_read_setup, - .read_pageio_init = nfs_pageio_init_read, - .read_rpc_prepare = nfs3_proc_read_rpc_prepare, .read_done = nfs3_read_done, .write_setup = nfs3_proc_write_setup, - .write_pageio_init = nfs_pageio_init_write, - .write_rpc_prepare = nfs3_proc_write_rpc_prepare, .write_done = nfs3_write_done, .commit_setup = nfs3_proc_commit_setup, .commit_rpc_prepare = nfs3_proc_commit_rpc_prepare, diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index fa6d72131c19..8f4cbe7f4aa8 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -953,7 +953,7 @@ static void nfs3_xdr_enc_readlink3args(struct rpc_rqst *req, * }; */ static void encode_read3args(struct xdr_stream *xdr, - const struct nfs_readargs *args) + const struct nfs_pgio_args *args) { __be32 *p; @@ -966,7 +966,7 @@ static void encode_read3args(struct xdr_stream *xdr, static void nfs3_xdr_enc_read3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_readargs *args) + const struct nfs_pgio_args *args) { encode_read3args(xdr, args); prepare_reply_buffer(req, args->pages, args->pgbase, @@ -992,7 +992,7 @@ static void nfs3_xdr_enc_read3args(struct rpc_rqst *req, * }; */ static void encode_write3args(struct xdr_stream *xdr, - const struct nfs_writeargs *args) + const struct nfs_pgio_args *args) { __be32 *p; @@ -1008,7 +1008,7 @@ static void encode_write3args(struct xdr_stream *xdr, static void nfs3_xdr_enc_write3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_writeargs *args) + const struct nfs_pgio_args *args) { encode_write3args(xdr, args); xdr->buf->flags |= XDRBUF_WRITE; @@ -1589,7 +1589,7 @@ out_default: * }; */ static int decode_read3resok(struct xdr_stream *xdr, - struct nfs_readres *result) + struct nfs_pgio_res *result) { u32 eof, count, ocount, recvd; __be32 *p; @@ -1625,7 +1625,7 @@ out_overflow: } static int nfs3_xdr_dec_read3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_readres *result) + struct nfs_pgio_res *result) { enum nfs_stat status; int error; @@ -1673,7 +1673,7 @@ out_status: * }; */ static int decode_write3resok(struct xdr_stream *xdr, - struct nfs_writeres *result) + struct nfs_pgio_res *result) { __be32 *p; @@ -1697,7 +1697,7 @@ out_eio: } static int nfs3_xdr_dec_write3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_writeres *result) + struct nfs_pgio_res *result) { enum nfs_stat status; int error; diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index e1d1badbe53c..f63cb87cd730 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -337,7 +337,7 @@ nfs4_state_protect(struct nfs_client *clp, unsigned long sp4_mode, */ static inline void nfs4_state_protect_write(struct nfs_client *clp, struct rpc_clnt **clntp, - struct rpc_message *msg, struct nfs_write_data *wdata) + struct rpc_message *msg, struct nfs_pgio_data *wdata) { if (_nfs4_state_protect(clp, NFS_SP4_MACH_CRED_WRITE, clntp, msg) && !test_bit(NFS_SP4_MACH_CRED_COMMIT, &clp->cl_sp4_flags)) @@ -369,7 +369,7 @@ nfs4_state_protect(struct nfs_client *clp, unsigned long sp4_flags, static inline void nfs4_state_protect_write(struct nfs_client *clp, struct rpc_clnt **clntp, - struct rpc_message *msg, struct nfs_write_data *wdata) + struct rpc_message *msg, struct nfs_pgio_data *wdata) { } #endif /* CONFIG_NFS_V4_1 */ diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 8de3407e0360..464db9dd6318 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -100,8 +100,7 @@ nfs4_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) break; mutex_lock(&inode->i_mutex); ret = nfs_file_fsync_commit(file, start, end, datasync); - if (!ret && !datasync) - /* application has asked for meta-data sync */ + if (!ret) ret = pnfs_layoutcommit_inode(inode, true); mutex_unlock(&inode->i_mutex); /* diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 397be39c6dc8..285ad5334018 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2027,7 +2027,7 @@ static int _nfs4_proc_open(struct nfs4_opendata *data) return status; } if (!(o_res->f_attr->valid & NFS_ATTR_FATTR)) - _nfs4_proc_getattr(server, &o_res->fh, o_res->f_attr, o_res->f_label); + nfs4_proc_getattr(server, &o_res->fh, o_res->f_attr, o_res->f_label); return 0; } @@ -2750,7 +2750,7 @@ static void nfs4_close_context(struct nfs_open_context *ctx, int is_sync) #define FATTR4_WORD1_NFS40_MASK (2*FATTR4_WORD1_MOUNTED_ON_FILEID - 1UL) #define FATTR4_WORD2_NFS41_MASK (2*FATTR4_WORD2_SUPPATTR_EXCLCREAT - 1UL) -#define FATTR4_WORD2_NFS42_MASK (2*FATTR4_WORD2_CHANGE_SECURITY_LABEL - 1UL) +#define FATTR4_WORD2_NFS42_MASK (2*FATTR4_WORD2_SECURITY_LABEL - 1UL) static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle) { @@ -4033,12 +4033,12 @@ static bool nfs4_error_stateid_expired(int err) return false; } -void __nfs4_read_done_cb(struct nfs_read_data *data) +void __nfs4_read_done_cb(struct nfs_pgio_data *data) { nfs_invalidate_atime(data->header->inode); } -static int nfs4_read_done_cb(struct rpc_task *task, struct nfs_read_data *data) +static int nfs4_read_done_cb(struct rpc_task *task, struct nfs_pgio_data *data) { struct nfs_server *server = NFS_SERVER(data->header->inode); @@ -4055,7 +4055,7 @@ static int nfs4_read_done_cb(struct rpc_task *task, struct nfs_read_data *data) } static bool nfs4_read_stateid_changed(struct rpc_task *task, - struct nfs_readargs *args) + struct nfs_pgio_args *args) { if (!nfs4_error_stateid_expired(task->tk_status) || @@ -4068,7 +4068,7 @@ static bool nfs4_read_stateid_changed(struct rpc_task *task, return true; } -static int nfs4_read_done(struct rpc_task *task, struct nfs_read_data *data) +static int nfs4_read_done(struct rpc_task *task, struct nfs_pgio_data *data) { dprintk("--> %s\n", __func__); @@ -4077,19 +4077,19 @@ static int nfs4_read_done(struct rpc_task *task, struct nfs_read_data *data) return -EAGAIN; if (nfs4_read_stateid_changed(task, &data->args)) return -EAGAIN; - return data->read_done_cb ? data->read_done_cb(task, data) : + return data->pgio_done_cb ? data->pgio_done_cb(task, data) : nfs4_read_done_cb(task, data); } -static void nfs4_proc_read_setup(struct nfs_read_data *data, struct rpc_message *msg) +static void nfs4_proc_read_setup(struct nfs_pgio_data *data, struct rpc_message *msg) { data->timestamp = jiffies; - data->read_done_cb = nfs4_read_done_cb; + data->pgio_done_cb = nfs4_read_done_cb; msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ]; nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 0); } -static int nfs4_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_data *data) +static int nfs4_proc_pgio_rpc_prepare(struct rpc_task *task, struct nfs_pgio_data *data) { if (nfs4_setup_sequence(NFS_SERVER(data->header->inode), &data->args.seq_args, @@ -4097,14 +4097,14 @@ static int nfs4_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_dat task)) return 0; if (nfs4_set_rw_stateid(&data->args.stateid, data->args.context, - data->args.lock_context, FMODE_READ) == -EIO) + data->args.lock_context, data->header->rw_ops->rw_mode) == -EIO) return -EIO; if (unlikely(test_bit(NFS_CONTEXT_BAD, &data->args.context->flags))) return -EIO; return 0; } -static int nfs4_write_done_cb(struct rpc_task *task, struct nfs_write_data *data) +static int nfs4_write_done_cb(struct rpc_task *task, struct nfs_pgio_data *data) { struct inode *inode = data->header->inode; @@ -4121,7 +4121,7 @@ static int nfs4_write_done_cb(struct rpc_task *task, struct nfs_write_data *data } static bool nfs4_write_stateid_changed(struct rpc_task *task, - struct nfs_writeargs *args) + struct nfs_pgio_args *args) { if (!nfs4_error_stateid_expired(task->tk_status) || @@ -4134,18 +4134,18 @@ static bool nfs4_write_stateid_changed(struct rpc_task *task, return true; } -static int nfs4_write_done(struct rpc_task *task, struct nfs_write_data *data) +static int nfs4_write_done(struct rpc_task *task, struct nfs_pgio_data *data) { if (!nfs4_sequence_done(task, &data->res.seq_res)) return -EAGAIN; if (nfs4_write_stateid_changed(task, &data->args)) return -EAGAIN; - return data->write_done_cb ? data->write_done_cb(task, data) : + return data->pgio_done_cb ? data->pgio_done_cb(task, data) : nfs4_write_done_cb(task, data); } static -bool nfs4_write_need_cache_consistency_data(const struct nfs_write_data *data) +bool nfs4_write_need_cache_consistency_data(const struct nfs_pgio_data *data) { const struct nfs_pgio_header *hdr = data->header; @@ -4158,7 +4158,7 @@ bool nfs4_write_need_cache_consistency_data(const struct nfs_write_data *data) return nfs4_have_delegation(hdr->inode, FMODE_READ) == 0; } -static void nfs4_proc_write_setup(struct nfs_write_data *data, struct rpc_message *msg) +static void nfs4_proc_write_setup(struct nfs_pgio_data *data, struct rpc_message *msg) { struct nfs_server *server = NFS_SERVER(data->header->inode); @@ -4168,8 +4168,8 @@ static void nfs4_proc_write_setup(struct nfs_write_data *data, struct rpc_messag } else data->args.bitmask = server->cache_consistency_bitmask; - if (!data->write_done_cb) - data->write_done_cb = nfs4_write_done_cb; + if (!data->pgio_done_cb) + data->pgio_done_cb = nfs4_write_done_cb; data->res.server = server; data->timestamp = jiffies; @@ -4177,21 +4177,6 @@ static void nfs4_proc_write_setup(struct nfs_write_data *data, struct rpc_messag nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1); } -static int nfs4_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_data *data) -{ - if (nfs4_setup_sequence(NFS_SERVER(data->header->inode), - &data->args.seq_args, - &data->res.seq_res, - task)) - return 0; - if (nfs4_set_rw_stateid(&data->args.stateid, data->args.context, - data->args.lock_context, FMODE_WRITE) == -EIO) - return -EIO; - if (unlikely(test_bit(NFS_CONTEXT_BAD, &data->args.context->flags))) - return -EIO; - return 0; -} - static void nfs4_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commit_data *data) { nfs4_setup_sequence(NFS_SERVER(data->inode), @@ -8432,13 +8417,10 @@ const struct nfs_rpc_ops nfs_v4_clientops = { .pathconf = nfs4_proc_pathconf, .set_capabilities = nfs4_server_capabilities, .decode_dirent = nfs4_decode_dirent, + .pgio_rpc_prepare = nfs4_proc_pgio_rpc_prepare, .read_setup = nfs4_proc_read_setup, - .read_pageio_init = pnfs_pageio_init_read, - .read_rpc_prepare = nfs4_proc_read_rpc_prepare, .read_done = nfs4_read_done, .write_setup = nfs4_proc_write_setup, - .write_pageio_init = pnfs_pageio_init_write, - .write_rpc_prepare = nfs4_proc_write_rpc_prepare, .write_done = nfs4_write_done, .commit_setup = nfs4_proc_commit_setup, .commit_rpc_prepare = nfs4_proc_commit_rpc_prepare, diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index c0583b9bef71..848f6853c59e 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1456,7 +1456,7 @@ static int nfs4_reclaim_open_state(struct nfs4_state_owner *sp, const struct nfs * server that doesn't support a grace period. */ spin_lock(&sp->so_lock); - write_seqcount_begin(&sp->so_reclaim_seqcount); + raw_write_seqcount_begin(&sp->so_reclaim_seqcount); restart: list_for_each_entry(state, &sp->so_states, open_states) { if (!test_and_clear_bit(ops->state_flag_bit, &state->flags)) @@ -1519,13 +1519,13 @@ restart: spin_lock(&sp->so_lock); goto restart; } - write_seqcount_end(&sp->so_reclaim_seqcount); + raw_write_seqcount_end(&sp->so_reclaim_seqcount); spin_unlock(&sp->so_lock); return 0; out_err: nfs4_put_open_state(state); spin_lock(&sp->so_lock); - write_seqcount_end(&sp->so_reclaim_seqcount); + raw_write_seqcount_end(&sp->so_reclaim_seqcount); spin_unlock(&sp->so_lock); return status; } diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h index 849cf146db30..0a744f3a86f6 100644 --- a/fs/nfs/nfs4trace.h +++ b/fs/nfs/nfs4trace.h @@ -932,7 +932,7 @@ DEFINE_NFS4_IDMAP_EVENT(nfs4_map_gid_to_group); DECLARE_EVENT_CLASS(nfs4_read_event, TP_PROTO( - const struct nfs_read_data *data, + const struct nfs_pgio_data *data, int error ), @@ -972,7 +972,7 @@ DECLARE_EVENT_CLASS(nfs4_read_event, #define DEFINE_NFS4_READ_EVENT(name) \ DEFINE_EVENT(nfs4_read_event, name, \ TP_PROTO( \ - const struct nfs_read_data *data, \ + const struct nfs_pgio_data *data, \ int error \ ), \ TP_ARGS(data, error)) @@ -983,7 +983,7 @@ DEFINE_NFS4_READ_EVENT(nfs4_pnfs_read); DECLARE_EVENT_CLASS(nfs4_write_event, TP_PROTO( - const struct nfs_write_data *data, + const struct nfs_pgio_data *data, int error ), @@ -1024,7 +1024,7 @@ DECLARE_EVENT_CLASS(nfs4_write_event, #define DEFINE_NFS4_WRITE_EVENT(name) \ DEFINE_EVENT(nfs4_write_event, name, \ TP_PROTO( \ - const struct nfs_write_data *data, \ + const struct nfs_pgio_data *data, \ int error \ ), \ TP_ARGS(data, error)) diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 73ce8d4fe2c8..939ae606cfa4 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -1556,7 +1556,8 @@ static void encode_putrootfh(struct xdr_stream *xdr, struct compound_hdr *hdr) encode_op_hdr(xdr, OP_PUTROOTFH, decode_putrootfh_maxsz, hdr); } -static void encode_read(struct xdr_stream *xdr, const struct nfs_readargs *args, struct compound_hdr *hdr) +static void encode_read(struct xdr_stream *xdr, const struct nfs_pgio_args *args, + struct compound_hdr *hdr) { __be32 *p; @@ -1701,7 +1702,8 @@ static void encode_setclientid_confirm(struct xdr_stream *xdr, const struct nfs4 encode_nfs4_verifier(xdr, &arg->confirm); } -static void encode_write(struct xdr_stream *xdr, const struct nfs_writeargs *args, struct compound_hdr *hdr) +static void encode_write(struct xdr_stream *xdr, const struct nfs_pgio_args *args, + struct compound_hdr *hdr) { __be32 *p; @@ -2451,7 +2453,7 @@ static void nfs4_xdr_enc_readdir(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode a READ request */ static void nfs4_xdr_enc_read(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_readargs *args) + struct nfs_pgio_args *args) { struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), @@ -2513,7 +2515,7 @@ static void nfs4_xdr_enc_getacl(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode a WRITE request */ static void nfs4_xdr_enc_write(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_writeargs *args) + struct nfs_pgio_args *args) { struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), @@ -5085,7 +5087,8 @@ static int decode_putrootfh(struct xdr_stream *xdr) return decode_op_hdr(xdr, OP_PUTROOTFH); } -static int decode_read(struct xdr_stream *xdr, struct rpc_rqst *req, struct nfs_readres *res) +static int decode_read(struct xdr_stream *xdr, struct rpc_rqst *req, + struct nfs_pgio_res *res) { __be32 *p; uint32_t count, eof, recvd; @@ -5339,7 +5342,7 @@ static int decode_setclientid_confirm(struct xdr_stream *xdr) return decode_op_hdr(xdr, OP_SETCLIENTID_CONFIRM); } -static int decode_write(struct xdr_stream *xdr, struct nfs_writeres *res) +static int decode_write(struct xdr_stream *xdr, struct nfs_pgio_res *res) { __be32 *p; int status; @@ -6636,7 +6639,7 @@ out: * Decode Read response */ static int nfs4_xdr_dec_read(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_readres *res) + struct nfs_pgio_res *res) { struct compound_hdr hdr; int status; @@ -6661,7 +6664,7 @@ out: * Decode WRITE response */ static int nfs4_xdr_dec_write(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_writeres *res) + struct nfs_pgio_res *res) { struct compound_hdr hdr; int status; diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c index 5457745dd4f1..611320753db2 100644 --- a/fs/nfs/objlayout/objio_osd.c +++ b/fs/nfs/objlayout/objio_osd.c @@ -439,7 +439,7 @@ static void _read_done(struct ore_io_state *ios, void *private) objlayout_read_done(&objios->oir, status, objios->sync); } -int objio_read_pagelist(struct nfs_read_data *rdata) +int objio_read_pagelist(struct nfs_pgio_data *rdata) { struct nfs_pgio_header *hdr = rdata->header; struct objio_state *objios; @@ -487,7 +487,7 @@ static void _write_done(struct ore_io_state *ios, void *private) static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate) { struct objio_state *objios = priv; - struct nfs_write_data *wdata = objios->oir.rpcdata; + struct nfs_pgio_data *wdata = objios->oir.rpcdata; struct address_space *mapping = wdata->header->inode->i_mapping; pgoff_t index = offset / PAGE_SIZE; struct page *page; @@ -531,7 +531,7 @@ static const struct _ore_r4w_op _r4w_op = { .put_page = &__r4w_put_page, }; -int objio_write_pagelist(struct nfs_write_data *wdata, int how) +int objio_write_pagelist(struct nfs_pgio_data *wdata, int how) { struct nfs_pgio_header *hdr = wdata->header; struct objio_state *objios; @@ -564,14 +564,22 @@ int objio_write_pagelist(struct nfs_write_data *wdata, int how) return 0; } -static bool objio_pg_test(struct nfs_pageio_descriptor *pgio, +/* + * Return 0 if @req cannot be coalesced into @pgio, otherwise return the number + * of bytes (maximum @req->wb_bytes) that can be coalesced. + */ +static size_t objio_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, struct nfs_page *req) { - if (!pnfs_generic_pg_test(pgio, prev, req)) - return false; + unsigned int size; + + size = pnfs_generic_pg_test(pgio, prev, req); + + if (!size || pgio->pg_count + req->wb_bytes > + (unsigned long)pgio->pg_layout_private) + return 0; - return pgio->pg_count + req->wb_bytes <= - (unsigned long)pgio->pg_layout_private; + return min(size, req->wb_bytes); } static void objio_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) diff --git a/fs/nfs/objlayout/objlayout.c b/fs/nfs/objlayout/objlayout.c index e4f9cbfec67b..765d3f54e986 100644 --- a/fs/nfs/objlayout/objlayout.c +++ b/fs/nfs/objlayout/objlayout.c @@ -53,10 +53,10 @@ objlayout_alloc_layout_hdr(struct inode *inode, gfp_t gfp_flags) struct objlayout *objlay; objlay = kzalloc(sizeof(struct objlayout), gfp_flags); - if (objlay) { - spin_lock_init(&objlay->lock); - INIT_LIST_HEAD(&objlay->err_list); - } + if (!objlay) + return NULL; + spin_lock_init(&objlay->lock); + INIT_LIST_HEAD(&objlay->err_list); dprintk("%s: Return %p\n", __func__, objlay); return &objlay->pnfs_layout; } @@ -229,11 +229,11 @@ objlayout_io_set_result(struct objlayout_io_res *oir, unsigned index, static void _rpc_read_complete(struct work_struct *work) { struct rpc_task *task; - struct nfs_read_data *rdata; + struct nfs_pgio_data *rdata; dprintk("%s enter\n", __func__); task = container_of(work, struct rpc_task, u.tk_work); - rdata = container_of(task, struct nfs_read_data, task); + rdata = container_of(task, struct nfs_pgio_data, task); pnfs_ld_read_done(rdata); } @@ -241,7 +241,7 @@ static void _rpc_read_complete(struct work_struct *work) void objlayout_read_done(struct objlayout_io_res *oir, ssize_t status, bool sync) { - struct nfs_read_data *rdata = oir->rpcdata; + struct nfs_pgio_data *rdata = oir->rpcdata; oir->status = rdata->task.tk_status = status; if (status >= 0) @@ -266,7 +266,7 @@ objlayout_read_done(struct objlayout_io_res *oir, ssize_t status, bool sync) * Perform sync or async reads. */ enum pnfs_try_status -objlayout_read_pagelist(struct nfs_read_data *rdata) +objlayout_read_pagelist(struct nfs_pgio_data *rdata) { struct nfs_pgio_header *hdr = rdata->header; struct inode *inode = hdr->inode; @@ -312,11 +312,11 @@ objlayout_read_pagelist(struct nfs_read_data *rdata) static void _rpc_write_complete(struct work_struct *work) { struct rpc_task *task; - struct nfs_write_data *wdata; + struct nfs_pgio_data *wdata; dprintk("%s enter\n", __func__); task = container_of(work, struct rpc_task, u.tk_work); - wdata = container_of(task, struct nfs_write_data, task); + wdata = container_of(task, struct nfs_pgio_data, task); pnfs_ld_write_done(wdata); } @@ -324,7 +324,7 @@ static void _rpc_write_complete(struct work_struct *work) void objlayout_write_done(struct objlayout_io_res *oir, ssize_t status, bool sync) { - struct nfs_write_data *wdata = oir->rpcdata; + struct nfs_pgio_data *wdata = oir->rpcdata; oir->status = wdata->task.tk_status = status; if (status >= 0) { @@ -351,7 +351,7 @@ objlayout_write_done(struct objlayout_io_res *oir, ssize_t status, bool sync) * Perform sync or async writes. */ enum pnfs_try_status -objlayout_write_pagelist(struct nfs_write_data *wdata, +objlayout_write_pagelist(struct nfs_pgio_data *wdata, int how) { struct nfs_pgio_header *hdr = wdata->header; diff --git a/fs/nfs/objlayout/objlayout.h b/fs/nfs/objlayout/objlayout.h index 87aa1dec6120..01e041029a6c 100644 --- a/fs/nfs/objlayout/objlayout.h +++ b/fs/nfs/objlayout/objlayout.h @@ -119,8 +119,8 @@ extern void objio_free_lseg(struct pnfs_layout_segment *lseg); */ extern void objio_free_result(struct objlayout_io_res *oir); -extern int objio_read_pagelist(struct nfs_read_data *rdata); -extern int objio_write_pagelist(struct nfs_write_data *wdata, int how); +extern int objio_read_pagelist(struct nfs_pgio_data *rdata); +extern int objio_write_pagelist(struct nfs_pgio_data *wdata, int how); /* * callback API @@ -168,10 +168,10 @@ extern struct pnfs_layout_segment *objlayout_alloc_lseg( extern void objlayout_free_lseg(struct pnfs_layout_segment *); extern enum pnfs_try_status objlayout_read_pagelist( - struct nfs_read_data *); + struct nfs_pgio_data *); extern enum pnfs_try_status objlayout_write_pagelist( - struct nfs_write_data *, + struct nfs_pgio_data *, int how); extern void objlayout_encode_layoutcommit( diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 03ed984ab4d8..b6ee3a6ee96d 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -24,9 +24,14 @@ #include "internal.h" #include "pnfs.h" +#define NFSDBG_FACILITY NFSDBG_PAGECACHE + static struct kmem_cache *nfs_page_cachep; +static const struct rpc_call_ops nfs_pgio_common_ops; + +static void nfs_free_request(struct nfs_page *); -bool nfs_pgarray_set(struct nfs_page_array *p, unsigned int pagecount) +static bool nfs_pgarray_set(struct nfs_page_array *p, unsigned int pagecount) { p->npages = pagecount; if (pagecount <= ARRAY_SIZE(p->page_array)) @@ -133,11 +138,156 @@ nfs_iocounter_wait(struct nfs_io_counter *c) return __nfs_iocounter_wait(c); } +static int nfs_wait_bit_uninterruptible(void *word) +{ + io_schedule(); + return 0; +} + +/* + * nfs_page_group_lock - lock the head of the page group + * @req - request in group that is to be locked + * + * this lock must be held if modifying the page group list + */ +void +nfs_page_group_lock(struct nfs_page *req) +{ + struct nfs_page *head = req->wb_head; + + WARN_ON_ONCE(head != head->wb_head); + + wait_on_bit_lock(&head->wb_flags, PG_HEADLOCK, + nfs_wait_bit_uninterruptible, + TASK_UNINTERRUPTIBLE); +} + +/* + * nfs_page_group_unlock - unlock the head of the page group + * @req - request in group that is to be unlocked + */ +void +nfs_page_group_unlock(struct nfs_page *req) +{ + struct nfs_page *head = req->wb_head; + + WARN_ON_ONCE(head != head->wb_head); + + smp_mb__before_atomic(); + clear_bit(PG_HEADLOCK, &head->wb_flags); + smp_mb__after_atomic(); + wake_up_bit(&head->wb_flags, PG_HEADLOCK); +} + +/* + * nfs_page_group_sync_on_bit_locked + * + * must be called with page group lock held + */ +static bool +nfs_page_group_sync_on_bit_locked(struct nfs_page *req, unsigned int bit) +{ + struct nfs_page *head = req->wb_head; + struct nfs_page *tmp; + + WARN_ON_ONCE(!test_bit(PG_HEADLOCK, &head->wb_flags)); + WARN_ON_ONCE(test_and_set_bit(bit, &req->wb_flags)); + + tmp = req->wb_this_page; + while (tmp != req) { + if (!test_bit(bit, &tmp->wb_flags)) + return false; + tmp = tmp->wb_this_page; + } + + /* true! reset all bits */ + tmp = req; + do { + clear_bit(bit, &tmp->wb_flags); + tmp = tmp->wb_this_page; + } while (tmp != req); + + return true; +} + +/* + * nfs_page_group_sync_on_bit - set bit on current request, but only + * return true if the bit is set for all requests in page group + * @req - request in page group + * @bit - PG_* bit that is used to sync page group + */ +bool nfs_page_group_sync_on_bit(struct nfs_page *req, unsigned int bit) +{ + bool ret; + + nfs_page_group_lock(req); + ret = nfs_page_group_sync_on_bit_locked(req, bit); + nfs_page_group_unlock(req); + + return ret; +} + +/* + * nfs_page_group_init - Initialize the page group linkage for @req + * @req - a new nfs request + * @prev - the previous request in page group, or NULL if @req is the first + * or only request in the group (the head). + */ +static inline void +nfs_page_group_init(struct nfs_page *req, struct nfs_page *prev) +{ + WARN_ON_ONCE(prev == req); + + if (!prev) { + req->wb_head = req; + req->wb_this_page = req; + } else { + WARN_ON_ONCE(prev->wb_this_page != prev->wb_head); + WARN_ON_ONCE(!test_bit(PG_HEADLOCK, &prev->wb_head->wb_flags)); + req->wb_head = prev->wb_head; + req->wb_this_page = prev->wb_this_page; + prev->wb_this_page = req; + + /* grab extra ref if head request has extra ref from + * the write/commit path to handle handoff between write + * and commit lists */ + if (test_bit(PG_INODE_REF, &prev->wb_head->wb_flags)) + kref_get(&req->wb_kref); + } +} + +/* + * nfs_page_group_destroy - sync the destruction of page groups + * @req - request that no longer needs the page group + * + * releases the page group reference from each member once all + * members have called this function. + */ +static void +nfs_page_group_destroy(struct kref *kref) +{ + struct nfs_page *req = container_of(kref, struct nfs_page, wb_kref); + struct nfs_page *tmp, *next; + + if (!nfs_page_group_sync_on_bit(req, PG_TEARDOWN)) + return; + + tmp = req; + do { + next = tmp->wb_this_page; + /* unlink and free */ + tmp->wb_this_page = tmp; + tmp->wb_head = tmp; + nfs_free_request(tmp); + tmp = next; + } while (tmp != req); +} + /** * nfs_create_request - Create an NFS read/write request. * @ctx: open context to use - * @inode: inode to which the request is attached * @page: page to write + * @last: last nfs request created for this page group or NULL if head * @offset: starting offset within the page for the write * @count: number of bytes to read/write * @@ -146,9 +296,9 @@ nfs_iocounter_wait(struct nfs_io_counter *c) * User should ensure it is safe to sleep in this function. */ struct nfs_page * -nfs_create_request(struct nfs_open_context *ctx, struct inode *inode, - struct page *page, - unsigned int offset, unsigned int count) +nfs_create_request(struct nfs_open_context *ctx, struct page *page, + struct nfs_page *last, unsigned int offset, + unsigned int count) { struct nfs_page *req; struct nfs_lock_context *l_ctx; @@ -180,6 +330,7 @@ nfs_create_request(struct nfs_open_context *ctx, struct inode *inode, req->wb_bytes = count; req->wb_context = get_nfs_open_context(ctx); kref_init(&req->wb_kref); + nfs_page_group_init(req, last); return req; } @@ -237,16 +388,22 @@ static void nfs_clear_request(struct nfs_page *req) } } - /** * nfs_release_request - Release the count on an NFS read/write request * @req: request to release * * Note: Should never be called with the spinlock held! */ -static void nfs_free_request(struct kref *kref) +static void nfs_free_request(struct nfs_page *req) { - struct nfs_page *req = container_of(kref, struct nfs_page, wb_kref); + WARN_ON_ONCE(req->wb_this_page != req); + + /* extra debug: make sure no sync bits are still set */ + WARN_ON_ONCE(test_bit(PG_TEARDOWN, &req->wb_flags)); + WARN_ON_ONCE(test_bit(PG_UNLOCKPAGE, &req->wb_flags)); + WARN_ON_ONCE(test_bit(PG_UPTODATE, &req->wb_flags)); + WARN_ON_ONCE(test_bit(PG_WB_END, &req->wb_flags)); + WARN_ON_ONCE(test_bit(PG_REMOVE, &req->wb_flags)); /* Release struct file and open context */ nfs_clear_request(req); @@ -255,13 +412,7 @@ static void nfs_free_request(struct kref *kref) void nfs_release_request(struct nfs_page *req) { - kref_put(&req->wb_kref, nfs_free_request); -} - -static int nfs_wait_bit_uninterruptible(void *word) -{ - io_schedule(); - return 0; + kref_put(&req->wb_kref, nfs_page_group_destroy); } /** @@ -279,22 +430,249 @@ nfs_wait_on_request(struct nfs_page *req) TASK_UNINTERRUPTIBLE); } -bool nfs_generic_pg_test(struct nfs_pageio_descriptor *desc, struct nfs_page *prev, struct nfs_page *req) +/* + * nfs_generic_pg_test - determine if requests can be coalesced + * @desc: pointer to descriptor + * @prev: previous request in desc, or NULL + * @req: this request + * + * Returns zero if @req can be coalesced into @desc, otherwise it returns + * the size of the request. + */ +size_t nfs_generic_pg_test(struct nfs_pageio_descriptor *desc, + struct nfs_page *prev, struct nfs_page *req) { - /* - * FIXME: ideally we should be able to coalesce all requests - * that are not block boundary aligned, but currently this - * is problematic for the case of bsize < PAGE_CACHE_SIZE, - * since nfs_flush_multi and nfs_pagein_multi assume you - * can have only one struct nfs_page. - */ - if (desc->pg_bsize < PAGE_SIZE) + if (desc->pg_count > desc->pg_bsize) { + /* should never happen */ + WARN_ON_ONCE(1); return 0; + } - return desc->pg_count + req->wb_bytes <= desc->pg_bsize; + return min(desc->pg_bsize - desc->pg_count, (size_t)req->wb_bytes); } EXPORT_SYMBOL_GPL(nfs_generic_pg_test); +static inline struct nfs_rw_header *NFS_RW_HEADER(struct nfs_pgio_header *hdr) +{ + return container_of(hdr, struct nfs_rw_header, header); +} + +/** + * nfs_rw_header_alloc - Allocate a header for a read or write + * @ops: Read or write function vector + */ +struct nfs_rw_header *nfs_rw_header_alloc(const struct nfs_rw_ops *ops) +{ + struct nfs_rw_header *header = ops->rw_alloc_header(); + + if (header) { + struct nfs_pgio_header *hdr = &header->header; + + INIT_LIST_HEAD(&hdr->pages); + spin_lock_init(&hdr->lock); + atomic_set(&hdr->refcnt, 0); + hdr->rw_ops = ops; + } + return header; +} +EXPORT_SYMBOL_GPL(nfs_rw_header_alloc); + +/* + * nfs_rw_header_free - Free a read or write header + * @hdr: The header to free + */ +void nfs_rw_header_free(struct nfs_pgio_header *hdr) +{ + hdr->rw_ops->rw_free_header(NFS_RW_HEADER(hdr)); +} +EXPORT_SYMBOL_GPL(nfs_rw_header_free); + +/** + * nfs_pgio_data_alloc - Allocate pageio data + * @hdr: The header making a request + * @pagecount: Number of pages to create + */ +static struct nfs_pgio_data *nfs_pgio_data_alloc(struct nfs_pgio_header *hdr, + unsigned int pagecount) +{ + struct nfs_pgio_data *data, *prealloc; + + prealloc = &NFS_RW_HEADER(hdr)->rpc_data; + if (prealloc->header == NULL) + data = prealloc; + else + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + goto out; + + if (nfs_pgarray_set(&data->pages, pagecount)) { + data->header = hdr; + atomic_inc(&hdr->refcnt); + } else { + if (data != prealloc) + kfree(data); + data = NULL; + } +out: + return data; +} + +/** + * nfs_pgio_data_release - Properly free pageio data + * @data: The data to release + */ +void nfs_pgio_data_release(struct nfs_pgio_data *data) +{ + struct nfs_pgio_header *hdr = data->header; + struct nfs_rw_header *pageio_header = NFS_RW_HEADER(hdr); + + put_nfs_open_context(data->args.context); + if (data->pages.pagevec != data->pages.page_array) + kfree(data->pages.pagevec); + if (data == &pageio_header->rpc_data) { + data->header = NULL; + data = NULL; + } + if (atomic_dec_and_test(&hdr->refcnt)) + hdr->completion_ops->completion(hdr); + /* Note: we only free the rpc_task after callbacks are done. + * See the comment in rpc_free_task() for why + */ + kfree(data); +} +EXPORT_SYMBOL_GPL(nfs_pgio_data_release); + +/** + * nfs_pgio_rpcsetup - Set up arguments for a pageio call + * @data: The pageio data + * @count: Number of bytes to read + * @offset: Initial offset + * @how: How to commit data (writes only) + * @cinfo: Commit information for the call (writes only) + */ +static void nfs_pgio_rpcsetup(struct nfs_pgio_data *data, + unsigned int count, unsigned int offset, + int how, struct nfs_commit_info *cinfo) +{ + struct nfs_page *req = data->header->req; + + /* Set up the RPC argument and reply structs + * NB: take care not to mess about with data->commit et al. */ + + data->args.fh = NFS_FH(data->header->inode); + data->args.offset = req_offset(req) + offset; + /* pnfs_set_layoutcommit needs this */ + data->mds_offset = data->args.offset; + data->args.pgbase = req->wb_pgbase + offset; + data->args.pages = data->pages.pagevec; + data->args.count = count; + data->args.context = get_nfs_open_context(req->wb_context); + data->args.lock_context = req->wb_lock_context; + data->args.stable = NFS_UNSTABLE; + switch (how & (FLUSH_STABLE | FLUSH_COND_STABLE)) { + case 0: + break; + case FLUSH_COND_STABLE: + if (nfs_reqs_to_commit(cinfo)) + break; + default: + data->args.stable = NFS_FILE_SYNC; + } + + data->res.fattr = &data->fattr; + data->res.count = count; + data->res.eof = 0; + data->res.verf = &data->verf; + nfs_fattr_init(&data->fattr); +} + +/** + * nfs_pgio_prepare - Prepare pageio data to go over the wire + * @task: The current task + * @calldata: pageio data to prepare + */ +static void nfs_pgio_prepare(struct rpc_task *task, void *calldata) +{ + struct nfs_pgio_data *data = calldata; + int err; + err = NFS_PROTO(data->header->inode)->pgio_rpc_prepare(task, data); + if (err) + rpc_exit(task, err); +} + +int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_data *data, + const struct rpc_call_ops *call_ops, int how, int flags) +{ + struct rpc_task *task; + struct rpc_message msg = { + .rpc_argp = &data->args, + .rpc_resp = &data->res, + .rpc_cred = data->header->cred, + }; + struct rpc_task_setup task_setup_data = { + .rpc_client = clnt, + .task = &data->task, + .rpc_message = &msg, + .callback_ops = call_ops, + .callback_data = data, + .workqueue = nfsiod_workqueue, + .flags = RPC_TASK_ASYNC | flags, + }; + int ret = 0; + + data->header->rw_ops->rw_initiate(data, &msg, &task_setup_data, how); + + dprintk("NFS: %5u initiated pgio call " + "(req %s/%llu, %u bytes @ offset %llu)\n", + data->task.tk_pid, + data->header->inode->i_sb->s_id, + (unsigned long long)NFS_FILEID(data->header->inode), + data->args.count, + (unsigned long long)data->args.offset); + + task = rpc_run_task(&task_setup_data); + if (IS_ERR(task)) { + ret = PTR_ERR(task); + goto out; + } + if (how & FLUSH_SYNC) { + ret = rpc_wait_for_completion_task(task); + if (ret == 0) + ret = task->tk_status; + } + rpc_put_task(task); +out: + return ret; +} +EXPORT_SYMBOL_GPL(nfs_initiate_pgio); + +/** + * nfs_pgio_error - Clean up from a pageio error + * @desc: IO descriptor + * @hdr: pageio header + */ +static int nfs_pgio_error(struct nfs_pageio_descriptor *desc, + struct nfs_pgio_header *hdr) +{ + set_bit(NFS_IOHDR_REDO, &hdr->flags); + nfs_pgio_data_release(hdr->data); + hdr->data = NULL; + desc->pg_completion_ops->error_cleanup(&desc->pg_list); + return -ENOMEM; +} + +/** + * nfs_pgio_release - Release pageio data + * @calldata: The pageio data to release + */ +static void nfs_pgio_release(void *calldata) +{ + struct nfs_pgio_data *data = calldata; + if (data->header->rw_ops->rw_release) + data->header->rw_ops->rw_release(data); + nfs_pgio_data_release(data); +} + /** * nfs_pageio_init - initialise a page io descriptor * @desc: pointer to descriptor @@ -307,6 +685,7 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc, struct inode *inode, const struct nfs_pageio_ops *pg_ops, const struct nfs_pgio_completion_ops *compl_ops, + const struct nfs_rw_ops *rw_ops, size_t bsize, int io_flags) { @@ -320,6 +699,7 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc, desc->pg_inode = inode; desc->pg_ops = pg_ops; desc->pg_completion_ops = compl_ops; + desc->pg_rw_ops = rw_ops; desc->pg_ioflags = io_flags; desc->pg_error = 0; desc->pg_lseg = NULL; @@ -328,6 +708,94 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc, } EXPORT_SYMBOL_GPL(nfs_pageio_init); +/** + * nfs_pgio_result - Basic pageio error handling + * @task: The task that ran + * @calldata: Pageio data to check + */ +static void nfs_pgio_result(struct rpc_task *task, void *calldata) +{ + struct nfs_pgio_data *data = calldata; + struct inode *inode = data->header->inode; + + dprintk("NFS: %s: %5u, (status %d)\n", __func__, + task->tk_pid, task->tk_status); + + if (data->header->rw_ops->rw_done(task, data, inode) != 0) + return; + if (task->tk_status < 0) + nfs_set_pgio_error(data->header, task->tk_status, data->args.offset); + else + data->header->rw_ops->rw_result(task, data); +} + +/* + * Create an RPC task for the given read or write request and kick it. + * The page must have been locked by the caller. + * + * It may happen that the page we're passed is not marked dirty. + * This is the case if nfs_updatepage detects a conflicting request + * that has been written but not committed. + */ +int nfs_generic_pgio(struct nfs_pageio_descriptor *desc, + struct nfs_pgio_header *hdr) +{ + struct nfs_page *req; + struct page **pages; + struct nfs_pgio_data *data; + struct list_head *head = &desc->pg_list; + struct nfs_commit_info cinfo; + + data = nfs_pgio_data_alloc(hdr, nfs_page_array_len(desc->pg_base, + desc->pg_count)); + if (!data) + return nfs_pgio_error(desc, hdr); + + nfs_init_cinfo(&cinfo, desc->pg_inode, desc->pg_dreq); + pages = data->pages.pagevec; + while (!list_empty(head)) { + req = nfs_list_entry(head->next); + nfs_list_remove_request(req); + nfs_list_add_request(req, &hdr->pages); + *pages++ = req->wb_page; + } + + if ((desc->pg_ioflags & FLUSH_COND_STABLE) && + (desc->pg_moreio || nfs_reqs_to_commit(&cinfo))) + desc->pg_ioflags &= ~FLUSH_COND_STABLE; + + /* Set up the argument struct */ + nfs_pgio_rpcsetup(data, desc->pg_count, 0, desc->pg_ioflags, &cinfo); + hdr->data = data; + desc->pg_rpc_callops = &nfs_pgio_common_ops; + return 0; +} +EXPORT_SYMBOL_GPL(nfs_generic_pgio); + +static int nfs_generic_pg_pgios(struct nfs_pageio_descriptor *desc) +{ + struct nfs_rw_header *rw_hdr; + struct nfs_pgio_header *hdr; + int ret; + + rw_hdr = nfs_rw_header_alloc(desc->pg_rw_ops); + if (!rw_hdr) { + desc->pg_completion_ops->error_cleanup(&desc->pg_list); + return -ENOMEM; + } + hdr = &rw_hdr->header; + nfs_pgheader_init(desc, hdr, nfs_rw_header_free); + atomic_inc(&hdr->refcnt); + ret = nfs_generic_pgio(desc, hdr); + if (ret == 0) + ret = nfs_initiate_pgio(NFS_CLIENT(hdr->inode), + hdr->data, desc->pg_rpc_callops, + desc->pg_ioflags, 0); + if (atomic_dec_and_test(&hdr->refcnt)) + hdr->completion_ops->completion(hdr); + return ret; +} + static bool nfs_match_open_context(const struct nfs_open_context *ctx1, const struct nfs_open_context *ctx2) { @@ -356,18 +824,23 @@ static bool nfs_can_coalesce_requests(struct nfs_page *prev, struct nfs_page *req, struct nfs_pageio_descriptor *pgio) { - if (!nfs_match_open_context(req->wb_context, prev->wb_context)) - return false; - if (req->wb_context->dentry->d_inode->i_flock != NULL && - !nfs_match_lock_context(req->wb_lock_context, prev->wb_lock_context)) - return false; - if (req->wb_pgbase != 0) - return false; - if (prev->wb_pgbase + prev->wb_bytes != PAGE_CACHE_SIZE) - return false; - if (req_offset(req) != req_offset(prev) + prev->wb_bytes) - return false; - return pgio->pg_ops->pg_test(pgio, prev, req); + size_t size; + + if (prev) { + if (!nfs_match_open_context(req->wb_context, prev->wb_context)) + return false; + if (req->wb_context->dentry->d_inode->i_flock != NULL && + !nfs_match_lock_context(req->wb_lock_context, + prev->wb_lock_context)) + return false; + if (req_offset(req) != req_offset(prev) + prev->wb_bytes) + return false; + } + size = pgio->pg_ops->pg_test(pgio, prev, req); + WARN_ON_ONCE(size > req->wb_bytes); + if (size && size < req->wb_bytes) + req->wb_bytes = size; + return size > 0; } /** @@ -381,17 +854,16 @@ static bool nfs_can_coalesce_requests(struct nfs_page *prev, static int nfs_pageio_do_add_request(struct nfs_pageio_descriptor *desc, struct nfs_page *req) { + struct nfs_page *prev = NULL; if (desc->pg_count != 0) { - struct nfs_page *prev; - prev = nfs_list_entry(desc->pg_list.prev); - if (!nfs_can_coalesce_requests(prev, req, desc)) - return 0; } else { if (desc->pg_ops->pg_init) desc->pg_ops->pg_init(desc, req); desc->pg_base = req->wb_pgbase; } + if (!nfs_can_coalesce_requests(prev, req, desc)) + return 0; nfs_list_remove_request(req); nfs_list_add_request(req, &desc->pg_list); desc->pg_count += req->wb_bytes; @@ -421,22 +893,73 @@ static void nfs_pageio_doio(struct nfs_pageio_descriptor *desc) * @desc: destination io descriptor * @req: request * + * This may split a request into subrequests which are all part of the + * same page group. + * * Returns true if the request 'req' was successfully coalesced into the * existing list of pages 'desc'. */ static int __nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, struct nfs_page *req) { - while (!nfs_pageio_do_add_request(desc, req)) { - desc->pg_moreio = 1; - nfs_pageio_doio(desc); - if (desc->pg_error < 0) - return 0; - desc->pg_moreio = 0; - if (desc->pg_recoalesce) - return 0; - } + struct nfs_page *subreq; + unsigned int bytes_left = 0; + unsigned int offset, pgbase; + + nfs_page_group_lock(req); + + subreq = req; + bytes_left = subreq->wb_bytes; + offset = subreq->wb_offset; + pgbase = subreq->wb_pgbase; + + do { + if (!nfs_pageio_do_add_request(desc, subreq)) { + /* make sure pg_test call(s) did nothing */ + WARN_ON_ONCE(subreq->wb_bytes != bytes_left); + WARN_ON_ONCE(subreq->wb_offset != offset); + WARN_ON_ONCE(subreq->wb_pgbase != pgbase); + + nfs_page_group_unlock(req); + desc->pg_moreio = 1; + nfs_pageio_doio(desc); + if (desc->pg_error < 0) + return 0; + desc->pg_moreio = 0; + if (desc->pg_recoalesce) + return 0; + /* retry add_request for this subreq */ + nfs_page_group_lock(req); + continue; + } + + /* check for buggy pg_test call(s) */ + WARN_ON_ONCE(subreq->wb_bytes + subreq->wb_pgbase > PAGE_SIZE); + WARN_ON_ONCE(subreq->wb_bytes > bytes_left); + WARN_ON_ONCE(subreq->wb_bytes == 0); + + bytes_left -= subreq->wb_bytes; + offset += subreq->wb_bytes; + pgbase += subreq->wb_bytes; + + if (bytes_left) { + subreq = nfs_create_request(req->wb_context, + req->wb_page, + subreq, pgbase, bytes_left); + if (IS_ERR(subreq)) + goto err_ptr; + nfs_lock_request(subreq); + subreq->wb_offset = offset; + subreq->wb_index = req->wb_index; + } + } while (bytes_left > 0); + + nfs_page_group_unlock(req); return 1; +err_ptr: + desc->pg_error = PTR_ERR(subreq); + nfs_page_group_unlock(req); + return 0; } static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc) @@ -535,3 +1058,13 @@ void nfs_destroy_nfspagecache(void) kmem_cache_destroy(nfs_page_cachep); } +static const struct rpc_call_ops nfs_pgio_common_ops = { + .rpc_call_prepare = nfs_pgio_prepare, + .rpc_call_done = nfs_pgio_result, + .rpc_release = nfs_pgio_release, +}; + +const struct nfs_pageio_ops nfs_pgio_rw_ops = { + .pg_test = nfs_generic_pg_test, + .pg_doio = nfs_generic_pg_pgios, +}; diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index fd9536e494bc..6fdcd233d6f7 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1388,11 +1388,6 @@ pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *r WARN_ON_ONCE(pgio->pg_lseg != NULL); - if (req->wb_offset != req->wb_pgbase) { - nfs_pageio_reset_read_mds(pgio); - return; - } - if (pgio->pg_dreq == NULL) rd_size = i_size_read(pgio->pg_inode) - req_offset(req); else @@ -1417,11 +1412,6 @@ pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio, { WARN_ON_ONCE(pgio->pg_lseg != NULL); - if (req->wb_offset != req->wb_pgbase) { - nfs_pageio_reset_write_mds(pgio); - return; - } - pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, req->wb_context, req_offset(req), @@ -1434,56 +1424,49 @@ pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio, } EXPORT_SYMBOL_GPL(pnfs_generic_pg_init_write); -void -pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode, - const struct nfs_pgio_completion_ops *compl_ops) -{ - struct nfs_server *server = NFS_SERVER(inode); - struct pnfs_layoutdriver_type *ld = server->pnfs_curr_ld; - - if (ld == NULL) - nfs_pageio_init_read(pgio, inode, compl_ops); - else - nfs_pageio_init(pgio, inode, ld->pg_read_ops, compl_ops, server->rsize, 0); -} - -void -pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode, - int ioflags, - const struct nfs_pgio_completion_ops *compl_ops) -{ - struct nfs_server *server = NFS_SERVER(inode); - struct pnfs_layoutdriver_type *ld = server->pnfs_curr_ld; - - if (ld == NULL) - nfs_pageio_init_write(pgio, inode, ioflags, compl_ops); - else - nfs_pageio_init(pgio, inode, ld->pg_write_ops, compl_ops, server->wsize, ioflags); -} - -bool +/* + * Return 0 if @req cannot be coalesced into @pgio, otherwise return the number + * of bytes (maximum @req->wb_bytes) that can be coalesced. + */ +size_t pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, struct nfs_page *req) { - if (pgio->pg_lseg == NULL) - return nfs_generic_pg_test(pgio, prev, req); + unsigned int size; + u64 seg_end, req_start, seg_left; + + size = nfs_generic_pg_test(pgio, prev, req); + if (!size) + return 0; /* - * Test if a nfs_page is fully contained in the pnfs_layout_range. - * Note that this test makes several assumptions: - * - that the previous nfs_page in the struct nfs_pageio_descriptor - * is known to lie within the range. - * - that the nfs_page being tested is known to be contiguous with the - * previous nfs_page. - * - Layout ranges are page aligned, so we only have to test the - * start offset of the request. + * 'size' contains the number of bytes left in the current page (up + * to the original size asked for in @req->wb_bytes). + * + * Calculate how many bytes are left in the layout segment + * and if there are less bytes than 'size', return that instead. * * Please also note that 'end_offset' is actually the offset of the * first byte that lies outside the pnfs_layout_range. FIXME? * */ - return req_offset(req) < end_offset(pgio->pg_lseg->pls_range.offset, - pgio->pg_lseg->pls_range.length); + if (pgio->pg_lseg) { + seg_end = end_offset(pgio->pg_lseg->pls_range.offset, + pgio->pg_lseg->pls_range.length); + req_start = req_offset(req); + WARN_ON_ONCE(req_start > seg_end); + /* start of request is past the last byte of this segment */ + if (req_start >= seg_end) + return 0; + + /* adjust 'size' iff there are fewer bytes left in the + * segment than what nfs_generic_pg_test returned */ + seg_left = seg_end - req_start; + if (seg_left < size) + size = (unsigned int)seg_left; + } + + return size; } EXPORT_SYMBOL_GPL(pnfs_generic_pg_test); @@ -1496,7 +1479,7 @@ int pnfs_write_done_resend_to_mds(struct inode *inode, LIST_HEAD(failed); /* Resend all requests through the MDS */ - nfs_pageio_init_write(&pgio, inode, FLUSH_STABLE, compl_ops); + nfs_pageio_init_write(&pgio, inode, FLUSH_STABLE, true, compl_ops); pgio.pg_dreq = dreq; while (!list_empty(head)) { struct nfs_page *req = nfs_list_entry(head->next); @@ -1519,7 +1502,7 @@ int pnfs_write_done_resend_to_mds(struct inode *inode, } EXPORT_SYMBOL_GPL(pnfs_write_done_resend_to_mds); -static void pnfs_ld_handle_write_error(struct nfs_write_data *data) +static void pnfs_ld_handle_write_error(struct nfs_pgio_data *data) { struct nfs_pgio_header *hdr = data->header; @@ -1538,7 +1521,7 @@ static void pnfs_ld_handle_write_error(struct nfs_write_data *data) /* * Called by non rpc-based layout drivers */ -void pnfs_ld_write_done(struct nfs_write_data *data) +void pnfs_ld_write_done(struct nfs_pgio_data *data) { struct nfs_pgio_header *hdr = data->header; @@ -1554,7 +1537,7 @@ EXPORT_SYMBOL_GPL(pnfs_ld_write_done); static void pnfs_write_through_mds(struct nfs_pageio_descriptor *desc, - struct nfs_write_data *data) + struct nfs_pgio_data *data) { struct nfs_pgio_header *hdr = data->header; @@ -1563,11 +1546,11 @@ pnfs_write_through_mds(struct nfs_pageio_descriptor *desc, nfs_pageio_reset_write_mds(desc); desc->pg_recoalesce = 1; } - nfs_writedata_release(data); + nfs_pgio_data_release(data); } static enum pnfs_try_status -pnfs_try_to_write_data(struct nfs_write_data *wdata, +pnfs_try_to_write_data(struct nfs_pgio_data *wdata, const struct rpc_call_ops *call_ops, struct pnfs_layout_segment *lseg, int how) @@ -1589,41 +1572,36 @@ pnfs_try_to_write_data(struct nfs_write_data *wdata, } static void -pnfs_do_multiple_writes(struct nfs_pageio_descriptor *desc, struct list_head *head, int how) +pnfs_do_write(struct nfs_pageio_descriptor *desc, + struct nfs_pgio_header *hdr, int how) { - struct nfs_write_data *data; + struct nfs_pgio_data *data = hdr->data; const struct rpc_call_ops *call_ops = desc->pg_rpc_callops; struct pnfs_layout_segment *lseg = desc->pg_lseg; + enum pnfs_try_status trypnfs; desc->pg_lseg = NULL; - while (!list_empty(head)) { - enum pnfs_try_status trypnfs; - - data = list_first_entry(head, struct nfs_write_data, list); - list_del_init(&data->list); - - trypnfs = pnfs_try_to_write_data(data, call_ops, lseg, how); - if (trypnfs == PNFS_NOT_ATTEMPTED) - pnfs_write_through_mds(desc, data); - } + trypnfs = pnfs_try_to_write_data(data, call_ops, lseg, how); + if (trypnfs == PNFS_NOT_ATTEMPTED) + pnfs_write_through_mds(desc, data); pnfs_put_lseg(lseg); } static void pnfs_writehdr_free(struct nfs_pgio_header *hdr) { pnfs_put_lseg(hdr->lseg); - nfs_writehdr_free(hdr); + nfs_rw_header_free(hdr); } EXPORT_SYMBOL_GPL(pnfs_writehdr_free); int pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc) { - struct nfs_write_header *whdr; + struct nfs_rw_header *whdr; struct nfs_pgio_header *hdr; int ret; - whdr = nfs_writehdr_alloc(); + whdr = nfs_rw_header_alloc(desc->pg_rw_ops); if (!whdr) { desc->pg_completion_ops->error_cleanup(&desc->pg_list); pnfs_put_lseg(desc->pg_lseg); @@ -1634,12 +1612,12 @@ pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc) nfs_pgheader_init(desc, hdr, pnfs_writehdr_free); hdr->lseg = pnfs_get_lseg(desc->pg_lseg); atomic_inc(&hdr->refcnt); - ret = nfs_generic_flush(desc, hdr); + ret = nfs_generic_pgio(desc, hdr); if (ret != 0) { pnfs_put_lseg(desc->pg_lseg); desc->pg_lseg = NULL; } else - pnfs_do_multiple_writes(desc, &hdr->rpc_list, desc->pg_ioflags); + pnfs_do_write(desc, hdr, desc->pg_ioflags); if (atomic_dec_and_test(&hdr->refcnt)) hdr->completion_ops->completion(hdr); return ret; @@ -1655,7 +1633,7 @@ int pnfs_read_done_resend_to_mds(struct inode *inode, LIST_HEAD(failed); /* Resend all requests through the MDS */ - nfs_pageio_init_read(&pgio, inode, compl_ops); + nfs_pageio_init_read(&pgio, inode, true, compl_ops); pgio.pg_dreq = dreq; while (!list_empty(head)) { struct nfs_page *req = nfs_list_entry(head->next); @@ -1674,7 +1652,7 @@ int pnfs_read_done_resend_to_mds(struct inode *inode, } EXPORT_SYMBOL_GPL(pnfs_read_done_resend_to_mds); -static void pnfs_ld_handle_read_error(struct nfs_read_data *data) +static void pnfs_ld_handle_read_error(struct nfs_pgio_data *data) { struct nfs_pgio_header *hdr = data->header; @@ -1693,7 +1671,7 @@ static void pnfs_ld_handle_read_error(struct nfs_read_data *data) /* * Called by non rpc-based layout drivers */ -void pnfs_ld_read_done(struct nfs_read_data *data) +void pnfs_ld_read_done(struct nfs_pgio_data *data) { struct nfs_pgio_header *hdr = data->header; @@ -1709,7 +1687,7 @@ EXPORT_SYMBOL_GPL(pnfs_ld_read_done); static void pnfs_read_through_mds(struct nfs_pageio_descriptor *desc, - struct nfs_read_data *data) + struct nfs_pgio_data *data) { struct nfs_pgio_header *hdr = data->header; @@ -1718,14 +1696,14 @@ pnfs_read_through_mds(struct nfs_pageio_descriptor *desc, nfs_pageio_reset_read_mds(desc); desc->pg_recoalesce = 1; } - nfs_readdata_release(data); + nfs_pgio_data_release(data); } /* * Call the appropriate parallel I/O subsystem read function. */ static enum pnfs_try_status -pnfs_try_to_read_data(struct nfs_read_data *rdata, +pnfs_try_to_read_data(struct nfs_pgio_data *rdata, const struct rpc_call_ops *call_ops, struct pnfs_layout_segment *lseg) { @@ -1747,41 +1725,35 @@ pnfs_try_to_read_data(struct nfs_read_data *rdata, } static void -pnfs_do_multiple_reads(struct nfs_pageio_descriptor *desc, struct list_head *head) +pnfs_do_read(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr) { - struct nfs_read_data *data; + struct nfs_pgio_data *data = hdr->data; const struct rpc_call_ops *call_ops = desc->pg_rpc_callops; struct pnfs_layout_segment *lseg = desc->pg_lseg; + enum pnfs_try_status trypnfs; desc->pg_lseg = NULL; - while (!list_empty(head)) { - enum pnfs_try_status trypnfs; - - data = list_first_entry(head, struct nfs_read_data, list); - list_del_init(&data->list); - - trypnfs = pnfs_try_to_read_data(data, call_ops, lseg); - if (trypnfs == PNFS_NOT_ATTEMPTED) - pnfs_read_through_mds(desc, data); - } + trypnfs = pnfs_try_to_read_data(data, call_ops, lseg); + if (trypnfs == PNFS_NOT_ATTEMPTED) + pnfs_read_through_mds(desc, data); pnfs_put_lseg(lseg); } static void pnfs_readhdr_free(struct nfs_pgio_header *hdr) { pnfs_put_lseg(hdr->lseg); - nfs_readhdr_free(hdr); + nfs_rw_header_free(hdr); } EXPORT_SYMBOL_GPL(pnfs_readhdr_free); int pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc) { - struct nfs_read_header *rhdr; + struct nfs_rw_header *rhdr; struct nfs_pgio_header *hdr; int ret; - rhdr = nfs_readhdr_alloc(); + rhdr = nfs_rw_header_alloc(desc->pg_rw_ops); if (!rhdr) { desc->pg_completion_ops->error_cleanup(&desc->pg_list); ret = -ENOMEM; @@ -1793,12 +1765,12 @@ pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc) nfs_pgheader_init(desc, hdr, pnfs_readhdr_free); hdr->lseg = pnfs_get_lseg(desc->pg_lseg); atomic_inc(&hdr->refcnt); - ret = nfs_generic_pagein(desc, hdr); + ret = nfs_generic_pgio(desc, hdr); if (ret != 0) { pnfs_put_lseg(desc->pg_lseg); desc->pg_lseg = NULL; } else - pnfs_do_multiple_reads(desc, &hdr->rpc_list); + pnfs_do_read(desc, hdr); if (atomic_dec_and_test(&hdr->refcnt)) hdr->completion_ops->completion(hdr); return ret; @@ -1848,7 +1820,7 @@ void pnfs_set_lo_fail(struct pnfs_layout_segment *lseg) EXPORT_SYMBOL_GPL(pnfs_set_lo_fail); void -pnfs_set_layoutcommit(struct nfs_write_data *wdata) +pnfs_set_layoutcommit(struct nfs_pgio_data *wdata) { struct nfs_pgio_header *hdr = wdata->header; struct inode *inode = hdr->inode; diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index c3058a076596..4fb309a2b4c4 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -113,8 +113,8 @@ struct pnfs_layoutdriver_type { * Return PNFS_ATTEMPTED to indicate the layout code has attempted * I/O, else return PNFS_NOT_ATTEMPTED to fall back to normal NFS */ - enum pnfs_try_status (*read_pagelist) (struct nfs_read_data *nfs_data); - enum pnfs_try_status (*write_pagelist) (struct nfs_write_data *nfs_data, int how); + enum pnfs_try_status (*read_pagelist) (struct nfs_pgio_data *nfs_data); + enum pnfs_try_status (*write_pagelist) (struct nfs_pgio_data *nfs_data, int how); void (*free_deviceid_node) (struct nfs4_deviceid_node *); @@ -180,11 +180,6 @@ extern int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp); void pnfs_get_layout_hdr(struct pnfs_layout_hdr *lo); void pnfs_put_lseg(struct pnfs_layout_segment *lseg); -void pnfs_pageio_init_read(struct nfs_pageio_descriptor *, struct inode *, - const struct nfs_pgio_completion_ops *); -void pnfs_pageio_init_write(struct nfs_pageio_descriptor *, struct inode *, - int, const struct nfs_pgio_completion_ops *); - void set_pnfs_layoutdriver(struct nfs_server *, const struct nfs_fh *, u32); void unset_pnfs_layoutdriver(struct nfs_server *); void pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *, struct nfs_page *); @@ -192,7 +187,8 @@ int pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc); void pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req, u64 wb_size); int pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc); -bool pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, struct nfs_page *req); +size_t pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, + struct nfs_page *prev, struct nfs_page *req); void pnfs_set_lo_fail(struct pnfs_layout_segment *lseg); struct pnfs_layout_segment *pnfs_layout_process(struct nfs4_layoutget *lgp); void pnfs_free_lseg_list(struct list_head *tmp_list); @@ -217,13 +213,13 @@ bool pnfs_roc(struct inode *ino); void pnfs_roc_release(struct inode *ino); void pnfs_roc_set_barrier(struct inode *ino, u32 barrier); bool pnfs_roc_drain(struct inode *ino, u32 *barrier, struct rpc_task *task); -void pnfs_set_layoutcommit(struct nfs_write_data *wdata); +void pnfs_set_layoutcommit(struct nfs_pgio_data *wdata); void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data); int pnfs_layoutcommit_inode(struct inode *inode, bool sync); int _pnfs_return_layout(struct inode *); int pnfs_commit_and_return_layout(struct inode *); -void pnfs_ld_write_done(struct nfs_write_data *); -void pnfs_ld_read_done(struct nfs_read_data *); +void pnfs_ld_write_done(struct nfs_pgio_data *); +void pnfs_ld_read_done(struct nfs_pgio_data *); struct pnfs_layout_segment *pnfs_update_layout(struct inode *ino, struct nfs_open_context *ctx, loff_t pos, @@ -461,18 +457,6 @@ static inline void unset_pnfs_layoutdriver(struct nfs_server *s) { } -static inline void pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode, - const struct nfs_pgio_completion_ops *compl_ops) -{ - nfs_pageio_init_read(pgio, inode, compl_ops); -} - -static inline void pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode, int ioflags, - const struct nfs_pgio_completion_ops *compl_ops) -{ - nfs_pageio_init_write(pgio, inode, ioflags, compl_ops); -} - static inline int pnfs_commit_list(struct inode *inode, struct list_head *mds_pages, int how, struct nfs_commit_info *cinfo) diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c index e55ce9e8b034..c171ce1a8a30 100644 --- a/fs/nfs/proc.c +++ b/fs/nfs/proc.c @@ -578,7 +578,7 @@ nfs_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle, return 0; } -static int nfs_read_done(struct rpc_task *task, struct nfs_read_data *data) +static int nfs_read_done(struct rpc_task *task, struct nfs_pgio_data *data) { struct inode *inode = data->header->inode; @@ -594,18 +594,18 @@ static int nfs_read_done(struct rpc_task *task, struct nfs_read_data *data) return 0; } -static void nfs_proc_read_setup(struct nfs_read_data *data, struct rpc_message *msg) +static void nfs_proc_read_setup(struct nfs_pgio_data *data, struct rpc_message *msg) { msg->rpc_proc = &nfs_procedures[NFSPROC_READ]; } -static int nfs_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_data *data) +static int nfs_proc_pgio_rpc_prepare(struct rpc_task *task, struct nfs_pgio_data *data) { rpc_call_start(task); return 0; } -static int nfs_write_done(struct rpc_task *task, struct nfs_write_data *data) +static int nfs_write_done(struct rpc_task *task, struct nfs_pgio_data *data) { struct inode *inode = data->header->inode; @@ -614,19 +614,13 @@ static int nfs_write_done(struct rpc_task *task, struct nfs_write_data *data) return 0; } -static void nfs_proc_write_setup(struct nfs_write_data *data, struct rpc_message *msg) +static void nfs_proc_write_setup(struct nfs_pgio_data *data, struct rpc_message *msg) { /* Note: NFSv2 ignores @stable and always uses NFS_FILE_SYNC */ data->args.stable = NFS_FILE_SYNC; msg->rpc_proc = &nfs_procedures[NFSPROC_WRITE]; } -static int nfs_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_data *data) -{ - rpc_call_start(task); - return 0; -} - static void nfs_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commit_data *data) { BUG(); @@ -734,13 +728,10 @@ const struct nfs_rpc_ops nfs_v2_clientops = { .fsinfo = nfs_proc_fsinfo, .pathconf = nfs_proc_pathconf, .decode_dirent = nfs2_decode_dirent, + .pgio_rpc_prepare = nfs_proc_pgio_rpc_prepare, .read_setup = nfs_proc_read_setup, - .read_pageio_init = nfs_pageio_init_read, - .read_rpc_prepare = nfs_proc_read_rpc_prepare, .read_done = nfs_read_done, .write_setup = nfs_proc_write_setup, - .write_pageio_init = nfs_pageio_init_write, - .write_rpc_prepare = nfs_proc_write_rpc_prepare, .write_done = nfs_write_done, .commit_setup = nfs_proc_commit_setup, .commit_rpc_prepare = nfs_proc_commit_rpc_prepare, diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 411aedda14bb..e818a475ca64 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -24,85 +24,24 @@ #include "internal.h" #include "iostat.h" #include "fscache.h" +#include "pnfs.h" #define NFSDBG_FACILITY NFSDBG_PAGECACHE -static const struct nfs_pageio_ops nfs_pageio_read_ops; -static const struct rpc_call_ops nfs_read_common_ops; static const struct nfs_pgio_completion_ops nfs_async_read_completion_ops; +static const struct nfs_rw_ops nfs_rw_read_ops; static struct kmem_cache *nfs_rdata_cachep; -struct nfs_read_header *nfs_readhdr_alloc(void) +static struct nfs_rw_header *nfs_readhdr_alloc(void) { - struct nfs_read_header *rhdr; - - rhdr = kmem_cache_zalloc(nfs_rdata_cachep, GFP_KERNEL); - if (rhdr) { - struct nfs_pgio_header *hdr = &rhdr->header; - - INIT_LIST_HEAD(&hdr->pages); - INIT_LIST_HEAD(&hdr->rpc_list); - spin_lock_init(&hdr->lock); - atomic_set(&hdr->refcnt, 0); - } - return rhdr; + return kmem_cache_zalloc(nfs_rdata_cachep, GFP_KERNEL); } -EXPORT_SYMBOL_GPL(nfs_readhdr_alloc); -static struct nfs_read_data *nfs_readdata_alloc(struct nfs_pgio_header *hdr, - unsigned int pagecount) +static void nfs_readhdr_free(struct nfs_rw_header *rhdr) { - struct nfs_read_data *data, *prealloc; - - prealloc = &container_of(hdr, struct nfs_read_header, header)->rpc_data; - if (prealloc->header == NULL) - data = prealloc; - else - data = kzalloc(sizeof(*data), GFP_KERNEL); - if (!data) - goto out; - - if (nfs_pgarray_set(&data->pages, pagecount)) { - data->header = hdr; - atomic_inc(&hdr->refcnt); - } else { - if (data != prealloc) - kfree(data); - data = NULL; - } -out: - return data; -} - -void nfs_readhdr_free(struct nfs_pgio_header *hdr) -{ - struct nfs_read_header *rhdr = container_of(hdr, struct nfs_read_header, header); - kmem_cache_free(nfs_rdata_cachep, rhdr); } -EXPORT_SYMBOL_GPL(nfs_readhdr_free); - -void nfs_readdata_release(struct nfs_read_data *rdata) -{ - struct nfs_pgio_header *hdr = rdata->header; - struct nfs_read_header *read_header = container_of(hdr, struct nfs_read_header, header); - - put_nfs_open_context(rdata->args.context); - if (rdata->pages.pagevec != rdata->pages.page_array) - kfree(rdata->pages.pagevec); - if (rdata == &read_header->rpc_data) { - rdata->header = NULL; - rdata = NULL; - } - if (atomic_dec_and_test(&hdr->refcnt)) - hdr->completion_ops->completion(hdr); - /* Note: we only free the rpc_task after callbacks are done. - * See the comment in rpc_free_task() for why - */ - kfree(rdata); -} -EXPORT_SYMBOL_GPL(nfs_readdata_release); static int nfs_return_empty_page(struct page *page) @@ -114,17 +53,24 @@ int nfs_return_empty_page(struct page *page) } void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, - struct inode *inode, + struct inode *inode, bool force_mds, const struct nfs_pgio_completion_ops *compl_ops) { - nfs_pageio_init(pgio, inode, &nfs_pageio_read_ops, compl_ops, - NFS_SERVER(inode)->rsize, 0); + struct nfs_server *server = NFS_SERVER(inode); + const struct nfs_pageio_ops *pg_ops = &nfs_pgio_rw_ops; + +#ifdef CONFIG_NFS_V4_1 + if (server->pnfs_curr_ld && !force_mds) + pg_ops = server->pnfs_curr_ld->pg_read_ops; +#endif + nfs_pageio_init(pgio, inode, pg_ops, compl_ops, &nfs_rw_read_ops, + server->rsize, 0); } EXPORT_SYMBOL_GPL(nfs_pageio_init_read); void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio) { - pgio->pg_ops = &nfs_pageio_read_ops; + pgio->pg_ops = &nfs_pgio_rw_ops; pgio->pg_bsize = NFS_SERVER(pgio->pg_inode)->rsize; } EXPORT_SYMBOL_GPL(nfs_pageio_reset_read_mds); @@ -139,7 +85,7 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode, len = nfs_page_length(page); if (len == 0) return nfs_return_empty_page(page); - new = nfs_create_request(ctx, inode, page, 0, len); + new = nfs_create_request(ctx, page, NULL, 0, len); if (IS_ERR(new)) { unlock_page(page); return PTR_ERR(new); @@ -147,7 +93,8 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode, if (len < PAGE_CACHE_SIZE) zero_user_segment(page, len, PAGE_CACHE_SIZE); - NFS_PROTO(inode)->read_pageio_init(&pgio, inode, &nfs_async_read_completion_ops); + nfs_pageio_init_read(&pgio, inode, false, + &nfs_async_read_completion_ops); nfs_pageio_add_request(&pgio, new); nfs_pageio_complete(&pgio); NFS_I(inode)->read_io += pgio.pg_bytes_written; @@ -158,10 +105,16 @@ static void nfs_readpage_release(struct nfs_page *req) { struct inode *d_inode = req->wb_context->dentry->d_inode; - if (PageUptodate(req->wb_page)) - nfs_readpage_to_fscache(d_inode, req->wb_page, 0); + dprintk("NFS: read done (%s/%llu %d@%lld)\n", d_inode->i_sb->s_id, + (unsigned long long)NFS_FILEID(d_inode), req->wb_bytes, + (long long)req_offset(req)); - unlock_page(req->wb_page); + if (nfs_page_group_sync_on_bit(req, PG_UNLOCKPAGE)) { + if (PageUptodate(req->wb_page)) + nfs_readpage_to_fscache(d_inode, req->wb_page, 0); + + unlock_page(req->wb_page); + } dprintk("NFS: read done (%s/%Lu %d@%Ld)\n", req->wb_context->dentry->d_inode->i_sb->s_id, @@ -171,7 +124,12 @@ static void nfs_readpage_release(struct nfs_page *req) nfs_release_request(req); } -/* Note io was page aligned */ +static void nfs_page_group_set_uptodate(struct nfs_page *req) +{ + if (nfs_page_group_sync_on_bit(req, PG_UPTODATE)) + SetPageUptodate(req->wb_page); +} + static void nfs_read_completion(struct nfs_pgio_header *hdr) { unsigned long bytes = 0; @@ -181,21 +139,32 @@ static void nfs_read_completion(struct nfs_pgio_header *hdr) while (!list_empty(&hdr->pages)) { struct nfs_page *req = nfs_list_entry(hdr->pages.next); struct page *page = req->wb_page; + unsigned long start = req->wb_pgbase; + unsigned long end = req->wb_pgbase + req->wb_bytes; if (test_bit(NFS_IOHDR_EOF, &hdr->flags)) { - if (bytes > hdr->good_bytes) - zero_user(page, 0, PAGE_SIZE); - else if (hdr->good_bytes - bytes < PAGE_SIZE) - zero_user_segment(page, - hdr->good_bytes & ~PAGE_MASK, - PAGE_SIZE); + /* note: regions of the page not covered by a + * request are zeroed in nfs_readpage_async / + * readpage_async_filler */ + if (bytes > hdr->good_bytes) { + /* nothing in this request was good, so zero + * the full extent of the request */ + zero_user_segment(page, start, end); + + } else if (hdr->good_bytes - bytes < req->wb_bytes) { + /* part of this request has good bytes, but + * not all. zero the bad bytes */ + start += hdr->good_bytes - bytes; + WARN_ON(start < req->wb_pgbase); + zero_user_segment(page, start, end); + } } bytes += req->wb_bytes; if (test_bit(NFS_IOHDR_ERROR, &hdr->flags)) { if (bytes <= hdr->good_bytes) - SetPageUptodate(page); + nfs_page_group_set_uptodate(req); } else - SetPageUptodate(page); + nfs_page_group_set_uptodate(req); nfs_list_remove_request(req); nfs_readpage_release(req); } @@ -203,95 +172,14 @@ out: hdr->release(hdr); } -int nfs_initiate_read(struct rpc_clnt *clnt, - struct nfs_read_data *data, - const struct rpc_call_ops *call_ops, int flags) +static void nfs_initiate_read(struct nfs_pgio_data *data, struct rpc_message *msg, + struct rpc_task_setup *task_setup_data, int how) { struct inode *inode = data->header->inode; int swap_flags = IS_SWAPFILE(inode) ? NFS_RPC_SWAPFLAGS : 0; - struct rpc_task *task; - struct rpc_message msg = { - .rpc_argp = &data->args, - .rpc_resp = &data->res, - .rpc_cred = data->header->cred, - }; - struct rpc_task_setup task_setup_data = { - .task = &data->task, - .rpc_client = clnt, - .rpc_message = &msg, - .callback_ops = call_ops, - .callback_data = data, - .workqueue = nfsiod_workqueue, - .flags = RPC_TASK_ASYNC | swap_flags | flags, - }; - /* Set up the initial task struct. */ - NFS_PROTO(inode)->read_setup(data, &msg); - - dprintk("NFS: %5u initiated read call (req %s/%llu, %u bytes @ " - "offset %llu)\n", - data->task.tk_pid, - inode->i_sb->s_id, - (unsigned long long)NFS_FILEID(inode), - data->args.count, - (unsigned long long)data->args.offset); - - task = rpc_run_task(&task_setup_data); - if (IS_ERR(task)) - return PTR_ERR(task); - rpc_put_task(task); - return 0; -} -EXPORT_SYMBOL_GPL(nfs_initiate_read); - -/* - * Set up the NFS read request struct - */ -static void nfs_read_rpcsetup(struct nfs_read_data *data, - unsigned int count, unsigned int offset) -{ - struct nfs_page *req = data->header->req; - - data->args.fh = NFS_FH(data->header->inode); - data->args.offset = req_offset(req) + offset; - data->args.pgbase = req->wb_pgbase + offset; - data->args.pages = data->pages.pagevec; - data->args.count = count; - data->args.context = get_nfs_open_context(req->wb_context); - data->args.lock_context = req->wb_lock_context; - - data->res.fattr = &data->fattr; - data->res.count = count; - data->res.eof = 0; - nfs_fattr_init(&data->fattr); -} - -static int nfs_do_read(struct nfs_read_data *data, - const struct rpc_call_ops *call_ops) -{ - struct inode *inode = data->header->inode; - - return nfs_initiate_read(NFS_CLIENT(inode), data, call_ops, 0); -} - -static int -nfs_do_multiple_reads(struct list_head *head, - const struct rpc_call_ops *call_ops) -{ - struct nfs_read_data *data; - int ret = 0; - - while (!list_empty(head)) { - int ret2; - - data = list_first_entry(head, struct nfs_read_data, list); - list_del_init(&data->list); - - ret2 = nfs_do_read(data, call_ops); - if (ret == 0) - ret = ret2; - } - return ret; + task_setup_data->flags |= swap_flags; + NFS_PROTO(inode)->read_setup(data, msg); } static void @@ -311,143 +199,14 @@ static const struct nfs_pgio_completion_ops nfs_async_read_completion_ops = { .completion = nfs_read_completion, }; -static void nfs_pagein_error(struct nfs_pageio_descriptor *desc, - struct nfs_pgio_header *hdr) -{ - set_bit(NFS_IOHDR_REDO, &hdr->flags); - while (!list_empty(&hdr->rpc_list)) { - struct nfs_read_data *data = list_first_entry(&hdr->rpc_list, - struct nfs_read_data, list); - list_del(&data->list); - nfs_readdata_release(data); - } - desc->pg_completion_ops->error_cleanup(&desc->pg_list); -} - -/* - * Generate multiple requests to fill a single page. - * - * We optimize to reduce the number of read operations on the wire. If we - * detect that we're reading a page, or an area of a page, that is past the - * end of file, we do not generate NFS read operations but just clear the - * parts of the page that would have come back zero from the server anyway. - * - * We rely on the cached value of i_size to make this determination; another - * client can fill pages on the server past our cached end-of-file, but we - * won't see the new data until our attribute cache is updated. This is more - * or less conventional NFS client behavior. - */ -static int nfs_pagein_multi(struct nfs_pageio_descriptor *desc, - struct nfs_pgio_header *hdr) -{ - struct nfs_page *req = hdr->req; - struct page *page = req->wb_page; - struct nfs_read_data *data; - size_t rsize = desc->pg_bsize, nbytes; - unsigned int offset; - - offset = 0; - nbytes = desc->pg_count; - do { - size_t len = min(nbytes,rsize); - - data = nfs_readdata_alloc(hdr, 1); - if (!data) { - nfs_pagein_error(desc, hdr); - return -ENOMEM; - } - data->pages.pagevec[0] = page; - nfs_read_rpcsetup(data, len, offset); - list_add(&data->list, &hdr->rpc_list); - nbytes -= len; - offset += len; - } while (nbytes != 0); - - nfs_list_remove_request(req); - nfs_list_add_request(req, &hdr->pages); - desc->pg_rpc_callops = &nfs_read_common_ops; - return 0; -} - -static int nfs_pagein_one(struct nfs_pageio_descriptor *desc, - struct nfs_pgio_header *hdr) -{ - struct nfs_page *req; - struct page **pages; - struct nfs_read_data *data; - struct list_head *head = &desc->pg_list; - - data = nfs_readdata_alloc(hdr, nfs_page_array_len(desc->pg_base, - desc->pg_count)); - if (!data) { - nfs_pagein_error(desc, hdr); - return -ENOMEM; - } - - pages = data->pages.pagevec; - while (!list_empty(head)) { - req = nfs_list_entry(head->next); - nfs_list_remove_request(req); - nfs_list_add_request(req, &hdr->pages); - *pages++ = req->wb_page; - } - - nfs_read_rpcsetup(data, desc->pg_count, 0); - list_add(&data->list, &hdr->rpc_list); - desc->pg_rpc_callops = &nfs_read_common_ops; - return 0; -} - -int nfs_generic_pagein(struct nfs_pageio_descriptor *desc, - struct nfs_pgio_header *hdr) -{ - if (desc->pg_bsize < PAGE_CACHE_SIZE) - return nfs_pagein_multi(desc, hdr); - return nfs_pagein_one(desc, hdr); -} -EXPORT_SYMBOL_GPL(nfs_generic_pagein); - -static int nfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc) -{ - struct nfs_read_header *rhdr; - struct nfs_pgio_header *hdr; - int ret; - - rhdr = nfs_readhdr_alloc(); - if (!rhdr) { - desc->pg_completion_ops->error_cleanup(&desc->pg_list); - return -ENOMEM; - } - hdr = &rhdr->header; - nfs_pgheader_init(desc, hdr, nfs_readhdr_free); - atomic_inc(&hdr->refcnt); - ret = nfs_generic_pagein(desc, hdr); - if (ret == 0) - ret = nfs_do_multiple_reads(&hdr->rpc_list, - desc->pg_rpc_callops); - if (atomic_dec_and_test(&hdr->refcnt)) - hdr->completion_ops->completion(hdr); - return ret; -} - -static const struct nfs_pageio_ops nfs_pageio_read_ops = { - .pg_test = nfs_generic_pg_test, - .pg_doio = nfs_generic_pg_readpages, -}; - /* * This is the callback from RPC telling us whether a reply was * received or some error occurred (timeout or socket shutdown). */ -int nfs_readpage_result(struct rpc_task *task, struct nfs_read_data *data) +static int nfs_readpage_done(struct rpc_task *task, struct nfs_pgio_data *data, + struct inode *inode) { - struct inode *inode = data->header->inode; - int status; - - dprintk("NFS: %s: %5u, (status %d)\n", __func__, task->tk_pid, - task->tk_status); - - status = NFS_PROTO(inode)->read_done(task, data); + int status = NFS_PROTO(inode)->read_done(task, data); if (status != 0) return status; @@ -460,10 +219,10 @@ int nfs_readpage_result(struct rpc_task *task, struct nfs_read_data *data) return 0; } -static void nfs_readpage_retry(struct rpc_task *task, struct nfs_read_data *data) +static void nfs_readpage_retry(struct rpc_task *task, struct nfs_pgio_data *data) { - struct nfs_readargs *argp = &data->args; - struct nfs_readres *resp = &data->res; + struct nfs_pgio_args *argp = &data->args; + struct nfs_pgio_res *resp = &data->res; /* This is a short read! */ nfs_inc_stats(data->header->inode, NFSIOS_SHORTREAD); @@ -480,17 +239,11 @@ static void nfs_readpage_retry(struct rpc_task *task, struct nfs_read_data *data rpc_restart_call_prepare(task); } -static void nfs_readpage_result_common(struct rpc_task *task, void *calldata) +static void nfs_readpage_result(struct rpc_task *task, struct nfs_pgio_data *data) { - struct nfs_read_data *data = calldata; struct nfs_pgio_header *hdr = data->header; - /* Note the only returns of nfs_readpage_result are 0 and -EAGAIN */ - if (nfs_readpage_result(task, data) != 0) - return; - if (task->tk_status < 0) - nfs_set_pgio_error(hdr, task->tk_status, data->args.offset); - else if (data->res.eof) { + if (data->res.eof) { loff_t bound; bound = data->args.offset + data->res.count; @@ -505,26 +258,6 @@ static void nfs_readpage_result_common(struct rpc_task *task, void *calldata) nfs_readpage_retry(task, data); } -static void nfs_readpage_release_common(void *calldata) -{ - nfs_readdata_release(calldata); -} - -void nfs_read_prepare(struct rpc_task *task, void *calldata) -{ - struct nfs_read_data *data = calldata; - int err; - err = NFS_PROTO(data->header->inode)->read_rpc_prepare(task, data); - if (err) - rpc_exit(task, err); -} - -static const struct rpc_call_ops nfs_read_common_ops = { - .rpc_call_prepare = nfs_read_prepare, - .rpc_call_done = nfs_readpage_result_common, - .rpc_release = nfs_readpage_release_common, -}; - /* * Read a page over NFS. * We read the page synchronously in the following case: @@ -592,7 +325,6 @@ static int readpage_async_filler(void *data, struct page *page) { struct nfs_readdesc *desc = (struct nfs_readdesc *)data; - struct inode *inode = page_file_mapping(page)->host; struct nfs_page *new; unsigned int len; int error; @@ -601,7 +333,7 @@ readpage_async_filler(void *data, struct page *page) if (len == 0) return nfs_return_empty_page(page); - new = nfs_create_request(desc->ctx, inode, page, 0, len); + new = nfs_create_request(desc->ctx, page, NULL, 0, len); if (IS_ERR(new)) goto out_error; @@ -654,7 +386,8 @@ int nfs_readpages(struct file *filp, struct address_space *mapping, if (ret == 0) goto read_complete; /* all pages were read */ - NFS_PROTO(inode)->read_pageio_init(&pgio, inode, &nfs_async_read_completion_ops); + nfs_pageio_init_read(&pgio, inode, false, + &nfs_async_read_completion_ops); ret = read_cache_pages(mapping, pages, readpage_async_filler, &desc); @@ -671,7 +404,7 @@ out: int __init nfs_init_readpagecache(void) { nfs_rdata_cachep = kmem_cache_create("nfs_read_data", - sizeof(struct nfs_read_header), + sizeof(struct nfs_rw_header), 0, SLAB_HWCACHE_ALIGN, NULL); if (nfs_rdata_cachep == NULL) @@ -684,3 +417,12 @@ void nfs_destroy_readpagecache(void) { kmem_cache_destroy(nfs_rdata_cachep); } + +static const struct nfs_rw_ops nfs_rw_read_ops = { + .rw_mode = FMODE_READ, + .rw_alloc_header = nfs_readhdr_alloc, + .rw_free_header = nfs_readhdr_free, + .rw_done = nfs_readpage_done, + .rw_result = nfs_readpage_result, + .rw_initiate = nfs_initiate_read, +}; diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 2cb56943e232..084af1060d79 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -2180,11 +2180,23 @@ out_no_address: return -EINVAL; } +#define NFS_MOUNT_CMP_FLAGMASK ~(NFS_MOUNT_INTR \ + | NFS_MOUNT_SECURE \ + | NFS_MOUNT_TCP \ + | NFS_MOUNT_VER3 \ + | NFS_MOUNT_KERBEROS \ + | NFS_MOUNT_NONLM \ + | NFS_MOUNT_BROKEN_SUID \ + | NFS_MOUNT_STRICTLOCK \ + | NFS_MOUNT_UNSHARED \ + | NFS_MOUNT_NORESVPORT \ + | NFS_MOUNT_LEGACY_INTERFACE) + static int nfs_compare_remount_data(struct nfs_server *nfss, struct nfs_parsed_mount_data *data) { - if (data->flags != nfss->flags || + if ((data->flags ^ nfss->flags) & NFS_MOUNT_CMP_FLAGMASK || data->rsize != nfss->rsize || data->wsize != nfss->wsize || data->version != nfss->nfs_client->rpc_ops->version || @@ -2248,6 +2260,7 @@ nfs_remount(struct super_block *sb, int *flags, char *raw_data) data->nfs_server.addrlen = nfss->nfs_client->cl_addrlen; data->version = nfsvers; data->minorversion = nfss->nfs_client->cl_minorversion; + data->net = current->nsproxy->net_ns; memcpy(&data->nfs_server.address, &nfss->nfs_client->cl_addr, data->nfs_server.addrlen); @@ -2347,18 +2360,6 @@ void nfs_clone_super(struct super_block *sb, struct nfs_mount_info *mount_info) nfs_initialise_sb(sb); } -#define NFS_MOUNT_CMP_FLAGMASK ~(NFS_MOUNT_INTR \ - | NFS_MOUNT_SECURE \ - | NFS_MOUNT_TCP \ - | NFS_MOUNT_VER3 \ - | NFS_MOUNT_KERBEROS \ - | NFS_MOUNT_NONLM \ - | NFS_MOUNT_BROKEN_SUID \ - | NFS_MOUNT_STRICTLOCK \ - | NFS_MOUNT_UNSHARED \ - | NFS_MOUNT_NORESVPORT \ - | NFS_MOUNT_LEGACY_INTERFACE) - static int nfs_compare_mount_options(const struct super_block *s, const struct nfs_server *b, int flags) { const struct nfs_server *a = s->s_fs_info; diff --git a/fs/nfs/write.c b/fs/nfs/write.c index ffb9459f180b..3ee5af4e738e 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -42,10 +42,10 @@ * Local function declarations */ static void nfs_redirty_request(struct nfs_page *req); -static const struct rpc_call_ops nfs_write_common_ops; static const struct rpc_call_ops nfs_commit_ops; static const struct nfs_pgio_completion_ops nfs_async_write_completion_ops; static const struct nfs_commit_completion_ops nfs_commit_completion_ops; +static const struct nfs_rw_ops nfs_rw_write_ops; static struct kmem_cache *nfs_wdata_cachep; static mempool_t *nfs_wdata_mempool; @@ -70,76 +70,19 @@ void nfs_commit_free(struct nfs_commit_data *p) } EXPORT_SYMBOL_GPL(nfs_commit_free); -struct nfs_write_header *nfs_writehdr_alloc(void) +static struct nfs_rw_header *nfs_writehdr_alloc(void) { - struct nfs_write_header *p = mempool_alloc(nfs_wdata_mempool, GFP_NOIO); - - if (p) { - struct nfs_pgio_header *hdr = &p->header; + struct nfs_rw_header *p = mempool_alloc(nfs_wdata_mempool, GFP_NOIO); + if (p) memset(p, 0, sizeof(*p)); - INIT_LIST_HEAD(&hdr->pages); - INIT_LIST_HEAD(&hdr->rpc_list); - spin_lock_init(&hdr->lock); - atomic_set(&hdr->refcnt, 0); - hdr->verf = &p->verf; - } return p; } -EXPORT_SYMBOL_GPL(nfs_writehdr_alloc); - -static struct nfs_write_data *nfs_writedata_alloc(struct nfs_pgio_header *hdr, - unsigned int pagecount) -{ - struct nfs_write_data *data, *prealloc; - - prealloc = &container_of(hdr, struct nfs_write_header, header)->rpc_data; - if (prealloc->header == NULL) - data = prealloc; - else - data = kzalloc(sizeof(*data), GFP_KERNEL); - if (!data) - goto out; - - if (nfs_pgarray_set(&data->pages, pagecount)) { - data->header = hdr; - atomic_inc(&hdr->refcnt); - } else { - if (data != prealloc) - kfree(data); - data = NULL; - } -out: - return data; -} -void nfs_writehdr_free(struct nfs_pgio_header *hdr) +static void nfs_writehdr_free(struct nfs_rw_header *whdr) { - struct nfs_write_header *whdr = container_of(hdr, struct nfs_write_header, header); mempool_free(whdr, nfs_wdata_mempool); } -EXPORT_SYMBOL_GPL(nfs_writehdr_free); - -void nfs_writedata_release(struct nfs_write_data *wdata) -{ - struct nfs_pgio_header *hdr = wdata->header; - struct nfs_write_header *write_header = container_of(hdr, struct nfs_write_header, header); - - put_nfs_open_context(wdata->args.context); - if (wdata->pages.pagevec != wdata->pages.page_array) - kfree(wdata->pages.pagevec); - if (wdata == &write_header->rpc_data) { - wdata->header = NULL; - wdata = NULL; - } - if (atomic_dec_and_test(&hdr->refcnt)) - hdr->completion_ops->completion(hdr); - /* Note: we only free the rpc_task after callbacks are done. - * See the comment in rpc_free_task() for why - */ - kfree(wdata); -} -EXPORT_SYMBOL_GPL(nfs_writedata_release); static void nfs_context_set_write_error(struct nfs_open_context *ctx, int error) { @@ -211,18 +154,78 @@ static void nfs_set_pageerror(struct page *page) nfs_zap_mapping(page_file_mapping(page)->host, page_file_mapping(page)); } +/* + * nfs_page_group_search_locked + * @head - head request of page group + * @page_offset - offset into page + * + * Search page group with head @head to find a request that contains the + * page offset @page_offset. + * + * Returns a pointer to the first matching nfs request, or NULL if no + * match is found. + * + * Must be called with the page group lock held + */ +static struct nfs_page * +nfs_page_group_search_locked(struct nfs_page *head, unsigned int page_offset) +{ + struct nfs_page *req; + + WARN_ON_ONCE(head != head->wb_head); + WARN_ON_ONCE(!test_bit(PG_HEADLOCK, &head->wb_head->wb_flags)); + + req = head; + do { + if (page_offset >= req->wb_pgbase && + page_offset < (req->wb_pgbase + req->wb_bytes)) + return req; + + req = req->wb_this_page; + } while (req != head); + + return NULL; +} + +/* + * nfs_page_group_covers_page + * @head - head request of page group + * + * Return true if the page group with head @head covers the whole page, + * returns false otherwise + */ +static bool nfs_page_group_covers_page(struct nfs_page *req) +{ + struct nfs_page *tmp; + unsigned int pos = 0; + unsigned int len = nfs_page_length(req->wb_page); + + nfs_page_group_lock(req); + + do { + tmp = nfs_page_group_search_locked(req->wb_head, pos); + if (tmp) { + /* no way this should happen */ + WARN_ON_ONCE(tmp->wb_pgbase != pos); + pos += tmp->wb_bytes - (pos - tmp->wb_pgbase); + } + } while (tmp && pos < len); + + nfs_page_group_unlock(req); + WARN_ON_ONCE(pos > len); + return pos == len; +} + /* We can set the PG_uptodate flag if we see that a write request * covers the full page. */ -static void nfs_mark_uptodate(struct page *page, unsigned int base, unsigned int count) +static void nfs_mark_uptodate(struct nfs_page *req) { - if (PageUptodate(page)) - return; - if (base != 0) + if (PageUptodate(req->wb_page)) return; - if (count != nfs_page_length(page)) + if (!nfs_page_group_covers_page(req)) return; - SetPageUptodate(page); + SetPageUptodate(req->wb_page); } static int wb_priority(struct writeback_control *wbc) @@ -258,12 +261,15 @@ static void nfs_set_page_writeback(struct page *page) } } -static void nfs_end_page_writeback(struct page *page) +static void nfs_end_page_writeback(struct nfs_page *req) { - struct inode *inode = page_file_mapping(page)->host; + struct inode *inode = page_file_mapping(req->wb_page)->host; struct nfs_server *nfss = NFS_SERVER(inode); - end_page_writeback(page); + if (!nfs_page_group_sync_on_bit(req, PG_WB_END)) + return; + + end_page_writeback(req->wb_page); if (atomic_long_dec_return(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH) clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC); } @@ -354,10 +360,8 @@ static int nfs_writepage_locked(struct page *page, struct writeback_control *wbc struct nfs_pageio_descriptor pgio; int err; - NFS_PROTO(page_file_mapping(page)->host)->write_pageio_init(&pgio, - page->mapping->host, - wb_priority(wbc), - &nfs_async_write_completion_ops); + nfs_pageio_init_write(&pgio, page->mapping->host, wb_priority(wbc), + false, &nfs_async_write_completion_ops); err = nfs_do_writepage(page, wbc, &pgio); nfs_pageio_complete(&pgio); if (err < 0) @@ -400,7 +404,8 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc) nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGES); - NFS_PROTO(inode)->write_pageio_init(&pgio, inode, wb_priority(wbc), &nfs_async_write_completion_ops); + nfs_pageio_init_write(&pgio, inode, wb_priority(wbc), false, + &nfs_async_write_completion_ops); err = write_cache_pages(mapping, wbc, nfs_writepages_callback, &pgio); nfs_pageio_complete(&pgio); @@ -425,6 +430,8 @@ static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req) { struct nfs_inode *nfsi = NFS_I(inode); + WARN_ON_ONCE(req->wb_this_page != req); + /* Lock the request! */ nfs_lock_request(req); @@ -441,6 +448,7 @@ static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req) set_page_private(req->wb_page, (unsigned long)req); } nfsi->npages++; + set_bit(PG_INODE_REF, &req->wb_flags); kref_get(&req->wb_kref); spin_unlock(&inode->i_lock); } @@ -452,15 +460,20 @@ static void nfs_inode_remove_request(struct nfs_page *req) { struct inode *inode = req->wb_context->dentry->d_inode; struct nfs_inode *nfsi = NFS_I(inode); + struct nfs_page *head; - spin_lock(&inode->i_lock); - if (likely(!PageSwapCache(req->wb_page))) { - set_page_private(req->wb_page, 0); - ClearPagePrivate(req->wb_page); - clear_bit(PG_MAPPED, &req->wb_flags); + if (nfs_page_group_sync_on_bit(req, PG_REMOVE)) { + head = req->wb_head; + + spin_lock(&inode->i_lock); + if (likely(!PageSwapCache(head->wb_page))) { + set_page_private(head->wb_page, 0); + ClearPagePrivate(head->wb_page); + clear_bit(PG_MAPPED, &head->wb_flags); + } + nfsi->npages--; + spin_unlock(&inode->i_lock); } - nfsi->npages--; - spin_unlock(&inode->i_lock); nfs_release_request(req); } @@ -583,7 +596,7 @@ nfs_clear_request_commit(struct nfs_page *req) } static inline -int nfs_write_need_commit(struct nfs_write_data *data) +int nfs_write_need_commit(struct nfs_pgio_data *data) { if (data->verf.committed == NFS_DATA_SYNC) return data->header->lseg == NULL; @@ -614,7 +627,7 @@ nfs_clear_request_commit(struct nfs_page *req) } static inline -int nfs_write_need_commit(struct nfs_write_data *data) +int nfs_write_need_commit(struct nfs_pgio_data *data) { return 0; } @@ -625,6 +638,7 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr) { struct nfs_commit_info cinfo; unsigned long bytes = 0; + bool do_destroy; if (test_bit(NFS_IOHDR_REDO, &hdr->flags)) goto out; @@ -645,7 +659,7 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr) goto next; } if (test_bit(NFS_IOHDR_NEED_COMMIT, &hdr->flags)) { - memcpy(&req->wb_verf, &hdr->verf->verifier, sizeof(req->wb_verf)); + memcpy(&req->wb_verf, &hdr->verf.verifier, sizeof(req->wb_verf)); nfs_mark_request_commit(req, hdr->lseg, &cinfo); goto next; } @@ -653,7 +667,8 @@ remove_req: nfs_inode_remove_request(req); next: nfs_unlock_request(req); - nfs_end_page_writeback(req->wb_page); + nfs_end_page_writeback(req); + do_destroy = !test_bit(NFS_IOHDR_NEED_COMMIT, &hdr->flags); nfs_release_request(req); } out: @@ -661,7 +676,7 @@ out: } #if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4) -static unsigned long +unsigned long nfs_reqs_to_commit(struct nfs_commit_info *cinfo) { return cinfo->mds->ncommit; @@ -718,7 +733,7 @@ nfs_scan_commit(struct inode *inode, struct list_head *dst, } #else -static unsigned long nfs_reqs_to_commit(struct nfs_commit_info *cinfo) +unsigned long nfs_reqs_to_commit(struct nfs_commit_info *cinfo) { return 0; } @@ -758,6 +773,10 @@ static struct nfs_page *nfs_try_to_update_request(struct inode *inode, if (req == NULL) goto out_unlock; + /* should be handled by nfs_flush_incompatible */ + WARN_ON_ONCE(req->wb_head != req); + WARN_ON_ONCE(req->wb_this_page != req); + rqend = req->wb_offset + req->wb_bytes; /* * Tell the caller to flush out the request if @@ -819,7 +838,7 @@ static struct nfs_page * nfs_setup_write_request(struct nfs_open_context* ctx, req = nfs_try_to_update_request(inode, page, offset, bytes); if (req != NULL) goto out; - req = nfs_create_request(ctx, inode, page, offset, bytes); + req = nfs_create_request(ctx, page, NULL, offset, bytes); if (IS_ERR(req)) goto out; nfs_inode_add_request(inode, req); @@ -837,7 +856,7 @@ static int nfs_writepage_setup(struct nfs_open_context *ctx, struct page *page, return PTR_ERR(req); /* Update file length */ nfs_grow_file(page, offset, count); - nfs_mark_uptodate(page, req->wb_pgbase, req->wb_bytes); + nfs_mark_uptodate(req); nfs_mark_request_dirty(req); nfs_unlock_and_release_request(req); return 0; @@ -863,6 +882,8 @@ int nfs_flush_incompatible(struct file *file, struct page *page) return 0; l_ctx = req->wb_lock_context; do_flush = req->wb_page != page || req->wb_context != ctx; + /* for now, flush if more than 1 request in page_group */ + do_flush |= req->wb_this_page != req; if (l_ctx && ctx->dentry->d_inode->i_flock != NULL) { do_flush |= l_ctx->lockowner.l_owner != current->files || l_ctx->lockowner.l_pid != current->tgid; @@ -990,126 +1011,17 @@ static int flush_task_priority(int how) return RPC_PRIORITY_NORMAL; } -int nfs_initiate_write(struct rpc_clnt *clnt, - struct nfs_write_data *data, - const struct rpc_call_ops *call_ops, - int how, int flags) +static void nfs_initiate_write(struct nfs_pgio_data *data, struct rpc_message *msg, + struct rpc_task_setup *task_setup_data, int how) { struct inode *inode = data->header->inode; int priority = flush_task_priority(how); - struct rpc_task *task; - struct rpc_message msg = { - .rpc_argp = &data->args, - .rpc_resp = &data->res, - .rpc_cred = data->header->cred, - }; - struct rpc_task_setup task_setup_data = { - .rpc_client = clnt, - .task = &data->task, - .rpc_message = &msg, - .callback_ops = call_ops, - .callback_data = data, - .workqueue = nfsiod_workqueue, - .flags = RPC_TASK_ASYNC | flags, - .priority = priority, - }; - int ret = 0; - - /* Set up the initial task struct. */ - NFS_PROTO(inode)->write_setup(data, &msg); - dprintk("NFS: %5u initiated write call " - "(req %s/%llu, %u bytes @ offset %llu)\n", - data->task.tk_pid, - inode->i_sb->s_id, - (unsigned long long)NFS_FILEID(inode), - data->args.count, - (unsigned long long)data->args.offset); + task_setup_data->priority = priority; + NFS_PROTO(inode)->write_setup(data, msg); nfs4_state_protect_write(NFS_SERVER(inode)->nfs_client, - &task_setup_data.rpc_client, &msg, data); - - task = rpc_run_task(&task_setup_data); - if (IS_ERR(task)) { - ret = PTR_ERR(task); - goto out; - } - if (how & FLUSH_SYNC) { - ret = rpc_wait_for_completion_task(task); - if (ret == 0) - ret = task->tk_status; - } - rpc_put_task(task); -out: - return ret; -} -EXPORT_SYMBOL_GPL(nfs_initiate_write); - -/* - * Set up the argument/result storage required for the RPC call. - */ -static void nfs_write_rpcsetup(struct nfs_write_data *data, - unsigned int count, unsigned int offset, - int how, struct nfs_commit_info *cinfo) -{ - struct nfs_page *req = data->header->req; - - /* Set up the RPC argument and reply structs - * NB: take care not to mess about with data->commit et al. */ - - data->args.fh = NFS_FH(data->header->inode); - data->args.offset = req_offset(req) + offset; - /* pnfs_set_layoutcommit needs this */ - data->mds_offset = data->args.offset; - data->args.pgbase = req->wb_pgbase + offset; - data->args.pages = data->pages.pagevec; - data->args.count = count; - data->args.context = get_nfs_open_context(req->wb_context); - data->args.lock_context = req->wb_lock_context; - data->args.stable = NFS_UNSTABLE; - switch (how & (FLUSH_STABLE | FLUSH_COND_STABLE)) { - case 0: - break; - case FLUSH_COND_STABLE: - if (nfs_reqs_to_commit(cinfo)) - break; - default: - data->args.stable = NFS_FILE_SYNC; - } - - data->res.fattr = &data->fattr; - data->res.count = count; - data->res.verf = &data->verf; - nfs_fattr_init(&data->fattr); -} - -static int nfs_do_write(struct nfs_write_data *data, - const struct rpc_call_ops *call_ops, - int how) -{ - struct inode *inode = data->header->inode; - - return nfs_initiate_write(NFS_CLIENT(inode), data, call_ops, how, 0); -} - -static int nfs_do_multiple_writes(struct list_head *head, - const struct rpc_call_ops *call_ops, - int how) -{ - struct nfs_write_data *data; - int ret = 0; - - while (!list_empty(head)) { - int ret2; - - data = list_first_entry(head, struct nfs_write_data, list); - list_del_init(&data->list); - - ret2 = nfs_do_write(data, call_ops, how); - if (ret == 0) - ret = ret2; - } - return ret; + &task_setup_data->rpc_client, msg, data); } /* If a nfs_flush_* function fails, it should remove reqs from @head and @@ -1120,7 +1032,7 @@ static void nfs_redirty_request(struct nfs_page *req) { nfs_mark_request_dirty(req); nfs_unlock_request(req); - nfs_end_page_writeback(req->wb_page); + nfs_end_page_writeback(req); nfs_release_request(req); } @@ -1140,173 +1052,30 @@ static const struct nfs_pgio_completion_ops nfs_async_write_completion_ops = { .completion = nfs_write_completion, }; -static void nfs_flush_error(struct nfs_pageio_descriptor *desc, - struct nfs_pgio_header *hdr) -{ - set_bit(NFS_IOHDR_REDO, &hdr->flags); - while (!list_empty(&hdr->rpc_list)) { - struct nfs_write_data *data = list_first_entry(&hdr->rpc_list, - struct nfs_write_data, list); - list_del(&data->list); - nfs_writedata_release(data); - } - desc->pg_completion_ops->error_cleanup(&desc->pg_list); -} - -/* - * Generate multiple small requests to write out a single - * contiguous dirty area on one page. - */ -static int nfs_flush_multi(struct nfs_pageio_descriptor *desc, - struct nfs_pgio_header *hdr) -{ - struct nfs_page *req = hdr->req; - struct page *page = req->wb_page; - struct nfs_write_data *data; - size_t wsize = desc->pg_bsize, nbytes; - unsigned int offset; - int requests = 0; - struct nfs_commit_info cinfo; - - nfs_init_cinfo(&cinfo, desc->pg_inode, desc->pg_dreq); - - if ((desc->pg_ioflags & FLUSH_COND_STABLE) && - (desc->pg_moreio || nfs_reqs_to_commit(&cinfo) || - desc->pg_count > wsize)) - desc->pg_ioflags &= ~FLUSH_COND_STABLE; - - - offset = 0; - nbytes = desc->pg_count; - do { - size_t len = min(nbytes, wsize); - - data = nfs_writedata_alloc(hdr, 1); - if (!data) { - nfs_flush_error(desc, hdr); - return -ENOMEM; - } - data->pages.pagevec[0] = page; - nfs_write_rpcsetup(data, len, offset, desc->pg_ioflags, &cinfo); - list_add(&data->list, &hdr->rpc_list); - requests++; - nbytes -= len; - offset += len; - } while (nbytes != 0); - nfs_list_remove_request(req); - nfs_list_add_request(req, &hdr->pages); - desc->pg_rpc_callops = &nfs_write_common_ops; - return 0; -} - -/* - * Create an RPC task for the given write request and kick it. - * The page must have been locked by the caller. - * - * It may happen that the page we're passed is not marked dirty. - * This is the case if nfs_updatepage detects a conflicting request - * that has been written but not committed. - */ -static int nfs_flush_one(struct nfs_pageio_descriptor *desc, - struct nfs_pgio_header *hdr) -{ - struct nfs_page *req; - struct page **pages; - struct nfs_write_data *data; - struct list_head *head = &desc->pg_list; - struct nfs_commit_info cinfo; - - data = nfs_writedata_alloc(hdr, nfs_page_array_len(desc->pg_base, - desc->pg_count)); - if (!data) { - nfs_flush_error(desc, hdr); - return -ENOMEM; - } - - nfs_init_cinfo(&cinfo, desc->pg_inode, desc->pg_dreq); - pages = data->pages.pagevec; - while (!list_empty(head)) { - req = nfs_list_entry(head->next); - nfs_list_remove_request(req); - nfs_list_add_request(req, &hdr->pages); - *pages++ = req->wb_page; - } - - if ((desc->pg_ioflags & FLUSH_COND_STABLE) && - (desc->pg_moreio || nfs_reqs_to_commit(&cinfo))) - desc->pg_ioflags &= ~FLUSH_COND_STABLE; - - /* Set up the argument struct */ - nfs_write_rpcsetup(data, desc->pg_count, 0, desc->pg_ioflags, &cinfo); - list_add(&data->list, &hdr->rpc_list); - desc->pg_rpc_callops = &nfs_write_common_ops; - return 0; -} - -int nfs_generic_flush(struct nfs_pageio_descriptor *desc, - struct nfs_pgio_header *hdr) -{ - if (desc->pg_bsize < PAGE_CACHE_SIZE) - return nfs_flush_multi(desc, hdr); - return nfs_flush_one(desc, hdr); -} -EXPORT_SYMBOL_GPL(nfs_generic_flush); - -static int nfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc) -{ - struct nfs_write_header *whdr; - struct nfs_pgio_header *hdr; - int ret; - - whdr = nfs_writehdr_alloc(); - if (!whdr) { - desc->pg_completion_ops->error_cleanup(&desc->pg_list); - return -ENOMEM; - } - hdr = &whdr->header; - nfs_pgheader_init(desc, hdr, nfs_writehdr_free); - atomic_inc(&hdr->refcnt); - ret = nfs_generic_flush(desc, hdr); - if (ret == 0) - ret = nfs_do_multiple_writes(&hdr->rpc_list, - desc->pg_rpc_callops, - desc->pg_ioflags); - if (atomic_dec_and_test(&hdr->refcnt)) - hdr->completion_ops->completion(hdr); - return ret; -} - -static const struct nfs_pageio_ops nfs_pageio_write_ops = { - .pg_test = nfs_generic_pg_test, - .pg_doio = nfs_generic_pg_writepages, -}; - void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, - struct inode *inode, int ioflags, + struct inode *inode, int ioflags, bool force_mds, const struct nfs_pgio_completion_ops *compl_ops) { - nfs_pageio_init(pgio, inode, &nfs_pageio_write_ops, compl_ops, - NFS_SERVER(inode)->wsize, ioflags); + struct nfs_server *server = NFS_SERVER(inode); + const struct nfs_pageio_ops *pg_ops = &nfs_pgio_rw_ops; + +#ifdef CONFIG_NFS_V4_1 + if (server->pnfs_curr_ld && !force_mds) + pg_ops = server->pnfs_curr_ld->pg_write_ops; +#endif + nfs_pageio_init(pgio, inode, pg_ops, compl_ops, &nfs_rw_write_ops, + server->wsize, ioflags); } EXPORT_SYMBOL_GPL(nfs_pageio_init_write); void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio) { - pgio->pg_ops = &nfs_pageio_write_ops; + pgio->pg_ops = &nfs_pgio_rw_ops; pgio->pg_bsize = NFS_SERVER(pgio->pg_inode)->wsize; } EXPORT_SYMBOL_GPL(nfs_pageio_reset_write_mds); -void nfs_write_prepare(struct rpc_task *task, void *calldata) -{ - struct nfs_write_data *data = calldata; - int err; - err = NFS_PROTO(data->header->inode)->write_rpc_prepare(task, data); - if (err) - rpc_exit(task, err); -} - void nfs_commit_prepare(struct rpc_task *task, void *calldata) { struct nfs_commit_data *data = calldata; @@ -1314,23 +1083,8 @@ void nfs_commit_prepare(struct rpc_task *task, void *calldata) NFS_PROTO(data->inode)->commit_rpc_prepare(task, data); } -/* - * Handle a write reply that flushes a whole page. - * - * FIXME: There is an inherent race with invalidate_inode_pages and - * writebacks since the page->count is kept > 1 for as long - * as the page has a write request pending. - */ -static void nfs_writeback_done_common(struct rpc_task *task, void *calldata) -{ - struct nfs_write_data *data = calldata; - - nfs_writeback_done(task, data); -} - -static void nfs_writeback_release_common(void *calldata) +static void nfs_writeback_release_common(struct nfs_pgio_data *data) { - struct nfs_write_data *data = calldata; struct nfs_pgio_header *hdr = data->header; int status = data->task.tk_status; @@ -1339,34 +1093,46 @@ static void nfs_writeback_release_common(void *calldata) if (test_bit(NFS_IOHDR_NEED_RESCHED, &hdr->flags)) ; /* Do nothing */ else if (!test_and_set_bit(NFS_IOHDR_NEED_COMMIT, &hdr->flags)) - memcpy(hdr->verf, &data->verf, sizeof(*hdr->verf)); - else if (memcmp(hdr->verf, &data->verf, sizeof(*hdr->verf))) + memcpy(&hdr->verf, &data->verf, sizeof(hdr->verf)); + else if (memcmp(&hdr->verf, &data->verf, sizeof(hdr->verf))) set_bit(NFS_IOHDR_NEED_RESCHED, &hdr->flags); spin_unlock(&hdr->lock); } - nfs_writedata_release(data); } -static const struct rpc_call_ops nfs_write_common_ops = { - .rpc_call_prepare = nfs_write_prepare, - .rpc_call_done = nfs_writeback_done_common, - .rpc_release = nfs_writeback_release_common, -}; +/* + * 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; +} /* * This function is called when the WRITE call is complete. */ -void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data) +static int nfs_writeback_done(struct rpc_task *task, struct nfs_pgio_data *data, + struct inode *inode) { - struct nfs_writeargs *argp = &data->args; - struct nfs_writeres *resp = &data->res; - struct inode *inode = data->header->inode; int status; - dprintk("NFS: %5u nfs_writeback_done (status %d)\n", - task->tk_pid, task->tk_status); - /* * ->write_done will attempt to use post-op attributes to detect * conflicting writes by other clients. A strict interpretation @@ -1376,11 +1142,11 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data) */ status = NFS_PROTO(inode)->write_done(task, data); if (status != 0) - return; - nfs_add_stats(inode, NFSIOS_SERVERWRITTENBYTES, resp->count); + return status; + nfs_add_stats(inode, NFSIOS_SERVERWRITTENBYTES, data->res.count); #if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4) - if (resp->verf->committed < argp->stable && task->tk_status >= 0) { + if (data->res.verf->committed < data->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. @@ -1396,18 +1162,31 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data) dprintk("NFS: faulty NFS server %s:" " (committed = %d) != (stable = %d)\n", NFS_SERVER(inode)->nfs_client->cl_hostname, - resp->verf->committed, argp->stable); + data->res.verf->committed, data->args.stable); complain = jiffies + 300 * HZ; } } #endif - if (task->tk_status < 0) - nfs_set_pgio_error(data->header, task->tk_status, argp->offset); - else if (resp->count < argp->count) { + + /* Deal with the suid/sgid bit corner case */ + if (nfs_should_remove_suid(inode)) + nfs_mark_for_revalidate(inode); + return 0; +} + +/* + * This function is called when the WRITE call is complete. + */ +static void nfs_writeback_result(struct rpc_task *task, struct nfs_pgio_data *data) +{ + struct nfs_pgio_args *argp = &data->args; + struct nfs_pgio_res *resp = &data->res; + + if (resp->count < argp->count) { static unsigned long complain; /* This a short write! */ - nfs_inc_stats(inode, NFSIOS_SHORTWRITE); + nfs_inc_stats(data->header->inode, NFSIOS_SHORTWRITE); /* Has the server at least made some progress? */ if (resp->count == 0) { @@ -1874,7 +1653,7 @@ int nfs_migrate_page(struct address_space *mapping, struct page *newpage, int __init nfs_init_writepagecache(void) { nfs_wdata_cachep = kmem_cache_create("nfs_write_data", - sizeof(struct nfs_write_header), + sizeof(struct nfs_rw_header), 0, SLAB_HWCACHE_ALIGN, NULL); if (nfs_wdata_cachep == NULL) @@ -1936,3 +1715,12 @@ void nfs_destroy_writepagecache(void) kmem_cache_destroy(nfs_wdata_cachep); } +static const struct nfs_rw_ops nfs_rw_write_ops = { + .rw_mode = FMODE_WRITE, + .rw_alloc_header = nfs_writehdr_alloc, + .rw_free_header = nfs_writehdr_free, + .rw_release = nfs_writeback_release_common, + .rw_done = nfs_writeback_done, + .rw_result = nfs_writeback_result, + .rw_initiate = nfs_initiate_write, +}; diff --git a/fs/nfsd/acl.h b/fs/nfsd/acl.h index b481e1f5eecc..a986ceb6fd0d 100644 --- a/fs/nfsd/acl.h +++ b/fs/nfsd/acl.h @@ -49,7 +49,7 @@ struct svc_rqst; struct nfs4_acl *nfs4_acl_new(int); int nfs4_acl_get_whotype(char *, u32); -__be32 nfs4_acl_write_who(int who, __be32 **p, int *len); +__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); diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c index 2645be435e75..72f44823adbb 100644 --- a/fs/nfsd/auth.c +++ b/fs/nfsd/auth.c @@ -1,7 +1,6 @@ /* Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de> */ #include <linux/sched.h> -#include <linux/user_namespace.h> #include "nfsd.h" #include "auth.h" @@ -25,7 +24,6 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp) struct cred *new; int i; int flags = nfsexp_flags(rqstp, exp); - int ret; validate_process_creds(); @@ -86,8 +84,7 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp) return 0; oom: - ret = -ENOMEM; abort_creds(new); - return ret; + return -ENOMEM; } diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index 8513c598fabf..13b85f94d9e2 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -17,17 +17,12 @@ #include <linux/exportfs.h> #include <linux/sunrpc/svc_xprt.h> -#include <net/ipv6.h> - #include "nfsd.h" #include "nfsfh.h" #include "netns.h" #define NFSDDBG_FACILITY NFSDDBG_EXPORT -typedef struct auth_domain svc_client; -typedef struct svc_export svc_export; - /* * We have two caches. * One maps client+vfsmnt+dentry to export options - the export map @@ -73,7 +68,7 @@ static struct svc_expkey *svc_expkey_lookup(struct cache_detail *cd, struct svc_ static int expkey_parse(struct cache_detail *cd, char *mesg, int mlen) { - /* client fsidtype fsid [path] */ + /* client fsidtype fsid expiry [path] */ char *buf; int len; struct auth_domain *dom = NULL; @@ -295,13 +290,19 @@ svc_expkey_update(struct cache_detail *cd, struct svc_expkey *new, static void nfsd4_fslocs_free(struct nfsd4_fs_locations *fsloc) { + struct nfsd4_fs_location *locations = fsloc->locations; int i; + if (!locations) + return; + for (i = 0; i < fsloc->locations_count; i++) { - kfree(fsloc->locations[i].path); - kfree(fsloc->locations[i].hosts); + kfree(locations[i].path); + kfree(locations[i].hosts); } - kfree(fsloc->locations); + + kfree(locations); + fsloc->locations = NULL; } static void svc_export_put(struct kref *ref) @@ -388,6 +389,10 @@ fsloc_parse(char **mesg, char *buf, struct nfsd4_fs_locations *fsloc) int len; int migrated, i, err; + /* more than one fsloc */ + if (fsloc->locations) + return -EINVAL; + /* listsize */ err = get_uint(mesg, &fsloc->locations_count); if (err) @@ -437,13 +442,18 @@ out_free_all: static int secinfo_parse(char **mesg, char *buf, struct svc_export *exp) { - int listsize, err; struct exp_flavor_info *f; + u32 listsize; + int err; + + /* more than one secinfo */ + if (exp->ex_nflavors) + return -EINVAL; - err = get_int(mesg, &listsize); + err = get_uint(mesg, &listsize); if (err) return err; - if (listsize < 0 || listsize > MAX_SECINFO_LIST) + if (listsize > MAX_SECINFO_LIST) return -EINVAL; for (f = exp->ex_flavors; f < exp->ex_flavors + listsize; f++) { @@ -474,6 +484,27 @@ static inline int secinfo_parse(char **mesg, char *buf, struct svc_export *exp) { return 0; } #endif +static inline int +uuid_parse(char **mesg, char *buf, unsigned char **puuid) +{ + int len; + + /* more than one uuid */ + if (*puuid) + return -EINVAL; + + /* expect a 16 byte uuid encoded as \xXXXX... */ + len = qword_get(mesg, buf, PAGE_SIZE); + if (len != EX_UUID_LEN) + return -EINVAL; + + *puuid = kmemdup(buf, EX_UUID_LEN, GFP_KERNEL); + if (*puuid == NULL) + return -ENOMEM; + + return 0; +} + static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) { /* client path expiry [flags anonuid anongid fsid] */ @@ -552,18 +583,9 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) while ((len = qword_get(&mesg, buf, PAGE_SIZE)) > 0) { if (strcmp(buf, "fsloc") == 0) err = fsloc_parse(&mesg, buf, &exp.ex_fslocs); - else if (strcmp(buf, "uuid") == 0) { - /* expect a 16 byte uuid encoded as \xXXXX... */ - len = qword_get(&mesg, buf, PAGE_SIZE); - if (len != 16) - err = -EINVAL; - else { - exp.ex_uuid = - kmemdup(buf, 16, GFP_KERNEL); - if (exp.ex_uuid == NULL) - err = -ENOMEM; - } - } else if (strcmp(buf, "secinfo") == 0) + else if (strcmp(buf, "uuid") == 0) + err = uuid_parse(&mesg, buf, &exp.ex_uuid); + else if (strcmp(buf, "secinfo") == 0) err = secinfo_parse(&mesg, buf, &exp); else /* quietly ignore unknown words and anything @@ -649,7 +671,7 @@ static int svc_export_show(struct seq_file *m, if (exp->ex_uuid) { int i; seq_puts(m, ",uuid="); - for (i=0; i<16; i++) { + for (i = 0; i < EX_UUID_LEN; i++) { if ((i&3) == 0 && i) seq_putc(m, ':'); seq_printf(m, "%02x", exp->ex_uuid[i]); @@ -771,7 +793,7 @@ svc_export_update(struct svc_export *new, struct svc_export *old) static struct svc_expkey * -exp_find_key(struct cache_detail *cd, svc_client *clp, int fsid_type, +exp_find_key(struct cache_detail *cd, struct auth_domain *clp, int fsid_type, u32 *fsidv, struct cache_req *reqp) { struct svc_expkey key, *ek; @@ -793,9 +815,9 @@ exp_find_key(struct cache_detail *cd, svc_client *clp, int fsid_type, return ek; } - -static svc_export *exp_get_by_name(struct cache_detail *cd, svc_client *clp, - const struct path *path, struct cache_req *reqp) +static struct svc_export * +exp_get_by_name(struct cache_detail *cd, struct auth_domain *clp, + const struct path *path, struct cache_req *reqp) { struct svc_export *exp, key; int err; @@ -819,11 +841,11 @@ static svc_export *exp_get_by_name(struct cache_detail *cd, svc_client *clp, /* * Find the export entry for a given dentry. */ -static struct svc_export *exp_parent(struct cache_detail *cd, svc_client *clp, - struct path *path) +static struct svc_export * +exp_parent(struct cache_detail *cd, struct auth_domain *clp, struct path *path) { struct dentry *saved = dget(path->dentry); - svc_export *exp = exp_get_by_name(cd, clp, path, NULL); + struct svc_export *exp = exp_get_by_name(cd, clp, path, NULL); while (PTR_ERR(exp) == -ENOENT && !IS_ROOT(path->dentry)) { struct dentry *parent = dget_parent(path->dentry); @@ -844,7 +866,7 @@ static struct svc_export *exp_parent(struct cache_detail *cd, svc_client *clp, * since its harder to fool a kernel module than a user space program. */ int -exp_rootfh(struct net *net, svc_client *clp, char *name, +exp_rootfh(struct net *net, struct auth_domain *clp, char *name, struct knfsd_fh *f, int maxsize) { struct svc_export *exp; diff --git a/fs/nfsd/export.h b/fs/nfsd/export.h new file mode 100644 index 000000000000..cfeea85c5bed --- /dev/null +++ b/fs/nfsd/export.h @@ -0,0 +1,110 @@ +/* + * Copyright (C) 1995-1997 Olaf Kirch <okir@monad.swb.de> + */ +#ifndef NFSD_EXPORT_H +#define NFSD_EXPORT_H + +#include <linux/sunrpc/cache.h> +#include <uapi/linux/nfsd/export.h> + +struct knfsd_fh; +struct svc_fh; +struct svc_rqst; + +/* + * FS Locations + */ + +#define MAX_FS_LOCATIONS 128 + +struct nfsd4_fs_location { + char *hosts; /* colon separated list of hosts */ + char *path; /* slash separated list of path components */ +}; + +struct nfsd4_fs_locations { + uint32_t locations_count; + struct nfsd4_fs_location *locations; +/* If we're not actually serving this data ourselves (only providing a + * list of replicas that do serve it) then we set "migrated": */ + int migrated; +}; + +/* + * We keep an array of pseudoflavors with the export, in order from most + * to least preferred. For the foreseeable future, we don't expect more + * than the eight pseudoflavors null, unix, krb5, krb5i, krb5p, skpm3, + * spkm3i, and spkm3p (and using all 8 at once should be rare). + */ +#define MAX_SECINFO_LIST 8 +#define EX_UUID_LEN 16 + +struct exp_flavor_info { + u32 pseudoflavor; + u32 flags; +}; + +struct svc_export { + struct cache_head h; + struct auth_domain * ex_client; + int ex_flags; + struct path ex_path; + kuid_t ex_anon_uid; + kgid_t ex_anon_gid; + int ex_fsid; + unsigned char * ex_uuid; /* 16 byte fsid */ + struct nfsd4_fs_locations ex_fslocs; + uint32_t ex_nflavors; + struct exp_flavor_info ex_flavors[MAX_SECINFO_LIST]; + struct cache_detail *cd; +}; + +/* an "export key" (expkey) maps a filehandlefragement to an + * svc_export for a given client. There can be several per export, + * for the different fsid types. + */ +struct svc_expkey { + struct cache_head h; + + struct auth_domain * ek_client; + int ek_fsidtype; + u32 ek_fsid[6]; + + struct path ek_path; +}; + +#define EX_ISSYNC(exp) (!((exp)->ex_flags & NFSEXP_ASYNC)) +#define EX_NOHIDE(exp) ((exp)->ex_flags & NFSEXP_NOHIDE) +#define EX_WGATHER(exp) ((exp)->ex_flags & NFSEXP_GATHERED_WRITES) + +int nfsexp_flags(struct svc_rqst *rqstp, struct svc_export *exp); +__be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp); + +/* + * Function declarations + */ +int nfsd_export_init(struct net *); +void nfsd_export_shutdown(struct net *); +void nfsd_export_flush(struct net *); +struct svc_export * rqst_exp_get_by_name(struct svc_rqst *, + struct path *); +struct svc_export * rqst_exp_parent(struct svc_rqst *, + struct path *); +struct svc_export * rqst_find_fsidzero_export(struct svc_rqst *); +int exp_rootfh(struct net *, struct auth_domain *, + char *path, struct knfsd_fh *, int maxsize); +__be32 exp_pseudoroot(struct svc_rqst *, struct svc_fh *); +__be32 nfserrno(int errno); + +static inline void exp_put(struct svc_export *exp) +{ + cache_put(&exp->h, exp->cd); +} + +static inline void exp_get(struct svc_export *exp) +{ + cache_get(&exp->h); +} +struct svc_export * rqst_exp_find(struct svc_rqst *, int, u32 *); + +#endif /* NFSD_EXPORT_H */ diff --git a/fs/nfsd/fault_inject.c b/fs/nfsd/fault_inject.c index d620e7f81429..2ed05c3cd43d 100644 --- a/fs/nfsd/fault_inject.c +++ b/fs/nfsd/fault_inject.c @@ -97,25 +97,14 @@ static ssize_t fault_inject_read(struct file *file, char __user *buf, { static u64 val; char read_buf[25]; - size_t size, ret; + size_t size; loff_t pos = *ppos; if (!pos) nfsd_inject_get(file_inode(file)->i_private, &val); size = scnprintf(read_buf, sizeof(read_buf), "%llu\n", val); - if (pos < 0) - return -EINVAL; - if (pos >= size || !len) - return 0; - if (len > size - pos) - len = size - pos; - ret = copy_to_user(buf, read_buf + pos, len); - if (ret == len) - return -EFAULT; - len -= ret; - *ppos = pos + len; - return len; + return simple_read_from_buffer(buf, len, ppos, read_buf, size); } static ssize_t fault_inject_write(struct file *file, const char __user *buf, diff --git a/fs/nfsd/idmap.h b/fs/nfsd/idmap.h index 66e58db01936..a3f34900091f 100644 --- a/fs/nfsd/idmap.h +++ b/fs/nfsd/idmap.h @@ -56,7 +56,7 @@ static inline void nfsd_idmap_shutdown(struct net *net) __be32 nfsd_map_name_to_uid(struct svc_rqst *, const char *, size_t, kuid_t *); __be32 nfsd_map_name_to_gid(struct svc_rqst *, const char *, size_t, kgid_t *); -__be32 nfsd4_encode_user(struct svc_rqst *, kuid_t, __be32 **, int *); -__be32 nfsd4_encode_group(struct svc_rqst *, kgid_t, __be32 **, int *); +__be32 nfsd4_encode_user(struct xdr_stream *, struct svc_rqst *, kuid_t); +__be32 nfsd4_encode_group(struct xdr_stream *, struct svc_rqst *, kgid_t); #endif /* LINUX_NFSD_IDMAP_H */ diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index 11c1fba29312..12b023a7ab7d 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -182,7 +182,8 @@ static __be32 nfsacld_proc_access(struct svc_rqst *rqstp, struct nfsd3_accessarg static int nfsaclsvc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd3_getaclargs *argp) { - if (!(p = nfs2svc_decode_fh(p, &argp->fh))) + p = nfs2svc_decode_fh(p, &argp->fh); + if (!p) return 0; argp->mask = ntohl(*p); p++; @@ -197,7 +198,8 @@ static int nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p, unsigned int base; int n; - if (!(p = nfs2svc_decode_fh(p, &argp->fh))) + p = nfs2svc_decode_fh(p, &argp->fh); + if (!p) return 0; argp->mask = ntohl(*p++); if (argp->mask & ~(NFS_ACL|NFS_ACLCNT|NFS_DFACL|NFS_DFACLCNT) || @@ -218,7 +220,8 @@ static int nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p, static int nfsaclsvc_decode_fhandleargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd_fhandle *argp) { - if (!(p = nfs2svc_decode_fh(p, &argp->fh))) + p = nfs2svc_decode_fh(p, &argp->fh); + if (!p) return 0; return xdr_argsize_check(rqstp, p); } @@ -226,7 +229,8 @@ static int nfsaclsvc_decode_fhandleargs(struct svc_rqst *rqstp, __be32 *p, static int nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd3_accessargs *argp) { - if (!(p = nfs2svc_decode_fh(p, &argp->fh))) + p = nfs2svc_decode_fh(p, &argp->fh); + if (!p) return 0; argp->access = ntohl(*p++); diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index adc5f1b1dc26..2a514e21dc74 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -128,7 +128,8 @@ out: static int nfs3svc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd3_getaclargs *args) { - if (!(p = nfs3svc_decode_fh(p, &args->fh))) + p = nfs3svc_decode_fh(p, &args->fh); + if (!p) return 0; args->mask = ntohl(*p); p++; @@ -143,7 +144,8 @@ static int nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p, unsigned int base; int n; - if (!(p = nfs3svc_decode_fh(p, &args->fh))) + p = nfs3svc_decode_fh(p, &args->fh); + if (!p) return 0; args->mask = ntohl(*p++); if (args->mask & ~(NFS_ACL|NFS_ACLCNT|NFS_DFACL|NFS_DFACLCNT) || diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index de6e39e12cb3..e6c01e80325e 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -278,7 +278,8 @@ void fill_post_wcc(struct svc_fh *fhp) int nfs3svc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p, struct nfsd_fhandle *args) { - if (!(p = decode_fh(p, &args->fh))) + p = decode_fh(p, &args->fh); + if (!p) return 0; return xdr_argsize_check(rqstp, p); } @@ -287,7 +288,8 @@ int nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd3_sattrargs *args) { - if (!(p = decode_fh(p, &args->fh))) + p = decode_fh(p, &args->fh); + if (!p) return 0; p = decode_sattr3(p, &args->attrs); @@ -315,7 +317,8 @@ int nfs3svc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd3_accessargs *args) { - if (!(p = decode_fh(p, &args->fh))) + p = decode_fh(p, &args->fh); + if (!p) return 0; args->access = ntohl(*p++); @@ -330,7 +333,8 @@ nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p, int v; u32 max_blocksize = svc_max_payload(rqstp); - if (!(p = decode_fh(p, &args->fh))) + p = decode_fh(p, &args->fh); + if (!p) return 0; p = xdr_decode_hyper(p, &args->offset); @@ -360,7 +364,8 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, unsigned int len, v, hdr, dlen; u32 max_blocksize = svc_max_payload(rqstp); - if (!(p = decode_fh(p, &args->fh))) + p = decode_fh(p, &args->fh); + if (!p) return 0; p = xdr_decode_hyper(p, &args->offset); @@ -535,7 +540,8 @@ int nfs3svc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd3_readlinkargs *args) { - if (!(p = decode_fh(p, &args->fh))) + p = decode_fh(p, &args->fh); + if (!p) return 0; args->buffer = page_address(*(rqstp->rq_next_page++)); @@ -558,7 +564,8 @@ int nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd3_readdirargs *args) { - if (!(p = decode_fh(p, &args->fh))) + p = decode_fh(p, &args->fh); + if (!p) return 0; p = xdr_decode_hyper(p, &args->cookie); args->verf = p; p += 2; @@ -580,7 +587,8 @@ nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p, int len; u32 max_blocksize = svc_max_payload(rqstp); - if (!(p = decode_fh(p, &args->fh))) + p = decode_fh(p, &args->fh); + if (!p) return 0; p = xdr_decode_hyper(p, &args->cookie); args->verf = p; p += 2; @@ -605,7 +613,8 @@ int nfs3svc_decode_commitargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd3_commitargs *args) { - if (!(p = decode_fh(p, &args->fh))) + p = decode_fh(p, &args->fh); + if (!p) return 0; p = xdr_decode_hyper(p, &args->offset); args->count = ntohl(*p++); diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c index f66c66b9f182..d714156a19fd 100644 --- a/fs/nfsd/nfs4acl.c +++ b/fs/nfsd/nfs4acl.c @@ -36,7 +36,6 @@ #include <linux/slab.h> #include <linux/nfs_fs.h> -#include <linux/export.h> #include "nfsfh.h" #include "nfsd.h" #include "acl.h" @@ -920,20 +919,19 @@ nfs4_acl_get_whotype(char *p, u32 len) return NFS4_ACL_WHO_NAMED; } -__be32 nfs4_acl_write_who(int who, __be32 **p, int *len) +__be32 nfs4_acl_write_who(struct xdr_stream *xdr, int who) { + __be32 *p; int i; - int bytes; for (i = 0; i < ARRAY_SIZE(s2t_map); i++) { if (s2t_map[i].type != who) continue; - bytes = 4 + (XDR_QUADLEN(s2t_map[i].stringlen) << 2); - if (bytes > *len) + p = xdr_reserve_space(xdr, s2t_map[i].stringlen + 4); + if (!p) return nfserr_resource; - *p = xdr_encode_opaque(*p, s2t_map[i].string, + p = xdr_encode_opaque(p, s2t_map[i].string, s2t_map[i].stringlen); - *len -= bytes; return 0; } WARN_ON_ONCE(1); diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c index c0dfde68742e..a0ab0a847d69 100644 --- a/fs/nfsd/nfs4idmap.c +++ b/fs/nfsd/nfs4idmap.c @@ -551,44 +551,43 @@ idmap_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen return 0; } -static __be32 encode_ascii_id(u32 id, __be32 **p, int *buflen) +static __be32 encode_ascii_id(struct xdr_stream *xdr, u32 id) { char buf[11]; int len; - int bytes; + __be32 *p; len = sprintf(buf, "%u", id); - bytes = 4 + (XDR_QUADLEN(len) << 2); - if (bytes > *buflen) + p = xdr_reserve_space(xdr, len + 4); + if (!p) return nfserr_resource; - *p = xdr_encode_opaque(*p, buf, len); - *buflen -= bytes; + p = xdr_encode_opaque(p, buf, len); return 0; } -static __be32 idmap_id_to_name(struct svc_rqst *rqstp, int type, u32 id, __be32 **p, int *buflen) +static __be32 idmap_id_to_name(struct xdr_stream *xdr, + struct svc_rqst *rqstp, int type, u32 id) { struct ent *item, key = { .id = id, .type = type, }; + __be32 *p; int ret; - int bytes; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); strlcpy(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(id, p, buflen); + return encode_ascii_id(xdr, id); if (ret) return nfserrno(ret); ret = strlen(item->name); WARN_ON_ONCE(ret > IDMAP_NAMESZ); - bytes = 4 + (XDR_QUADLEN(ret) << 2); - if (bytes > *buflen) + p = xdr_reserve_space(xdr, ret + 4); + if (!p) return nfserr_resource; - *p = xdr_encode_opaque(*p, item->name, ret); - *buflen -= bytes; + p = xdr_encode_opaque(p, item->name, ret); cache_put(&item->h, nn->idtoname_cache); return 0; } @@ -622,11 +621,12 @@ do_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen, u return idmap_name_to_id(rqstp, type, name, namelen, id); } -static __be32 encode_name_from_id(struct svc_rqst *rqstp, int type, u32 id, __be32 **p, int *buflen) +static __be32 encode_name_from_id(struct xdr_stream *xdr, + struct svc_rqst *rqstp, int type, u32 id) { if (nfs4_disable_idmapping && rqstp->rq_cred.cr_flavor < RPC_AUTH_GSS) - return encode_ascii_id(id, p, buflen); - return idmap_id_to_name(rqstp, type, id, p, buflen); + return encode_ascii_id(xdr, id); + return idmap_id_to_name(xdr, rqstp, type, id); } __be32 @@ -655,14 +655,16 @@ nfsd_map_name_to_gid(struct svc_rqst *rqstp, const char *name, size_t namelen, return status; } -__be32 nfsd4_encode_user(struct svc_rqst *rqstp, kuid_t uid, __be32 **p, int *buflen) +__be32 nfsd4_encode_user(struct xdr_stream *xdr, struct svc_rqst *rqstp, + kuid_t uid) { u32 id = from_kuid(&init_user_ns, uid); - return encode_name_from_id(rqstp, IDMAP_TYPE_USER, id, p, buflen); + return encode_name_from_id(xdr, rqstp, IDMAP_TYPE_USER, id); } -__be32 nfsd4_encode_group(struct svc_rqst *rqstp, kgid_t gid, __be32 **p, int *buflen) +__be32 nfsd4_encode_group(struct xdr_stream *xdr, struct svc_rqst *rqstp, + kgid_t gid) { u32 id = from_kgid(&init_user_ns, gid); - return encode_name_from_id(rqstp, IDMAP_TYPE_GROUP, id, p, buflen); + return encode_name_from_id(xdr, rqstp, IDMAP_TYPE_GROUP, id); } diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index d543222babf3..6851b003f2a4 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -430,12 +430,12 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; break; case NFS4_OPEN_CLAIM_PREVIOUS: - open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED; status = nfs4_check_open_reclaim(&open->op_clientid, cstate->minorversion, nn); if (status) goto out; + open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED; case NFS4_OPEN_CLAIM_FH: case NFS4_OPEN_CLAIM_DELEG_CUR_FH: status = do_open_fhandle(rqstp, cstate, open); @@ -445,7 +445,6 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, break; case NFS4_OPEN_CLAIM_DELEG_PREV_FH: case NFS4_OPEN_CLAIM_DELEGATE_PREV: - open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED; dprintk("NFSD: unsupported OPEN claim type %d\n", open->op_claim_type); status = nfserr_notsupp; @@ -786,7 +785,6 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (!nfsd4_last_compound_op(rqstp)) rqstp->rq_splice_ok = false; - nfs4_lock_state(); /* check stateid */ if ((status = nfs4_preprocess_stateid_op(SVC_NET(rqstp), cstate, &read->rd_stateid, @@ -794,11 +792,8 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, dprintk("NFSD: nfsd4_read: couldn't process stateid!\n"); goto out; } - if (read->rd_filp) - get_file(read->rd_filp); status = nfs_ok; out: - nfs4_unlock_state(); read->rd_rqstp = rqstp; read->rd_fhp = &cstate->current_fh; return status; @@ -937,10 +932,8 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, int err; if (setattr->sa_iattr.ia_valid & ATTR_SIZE) { - nfs4_lock_state(); status = nfs4_preprocess_stateid_op(SVC_NET(rqstp), cstate, &setattr->sa_stateid, WR_STATE, NULL); - nfs4_unlock_state(); if (status) { dprintk("NFSD: nfsd4_setattr: couldn't process stateid!\n"); return status; @@ -1006,17 +999,12 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (write->wr_offset >= OFFSET_MAX) return nfserr_inval; - nfs4_lock_state(); status = nfs4_preprocess_stateid_op(SVC_NET(rqstp), cstate, stateid, WR_STATE, &filp); if (status) { - nfs4_unlock_state(); dprintk("NFSD: nfsd4_write: couldn't process stateid!\n"); return status; } - if (filp) - get_file(filp); - nfs4_unlock_state(); cnt = write->wr_buflen; write->wr_how_written = write->wr_stable_how; @@ -1072,10 +1060,10 @@ _nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, return nfserr_jukebox; p = buf; - status = nfsd4_encode_fattr(&cstate->current_fh, + status = nfsd4_encode_fattr_to_buf(&p, count, &cstate->current_fh, cstate->current_fh.fh_export, - cstate->current_fh.fh_dentry, &p, - count, verify->ve_bmval, + cstate->current_fh.fh_dentry, + verify->ve_bmval, rqstp, 0); /* * If nfsd4_encode_fattr() ran out of space, assume that's because @@ -1182,9 +1170,7 @@ struct nfsd4_operation { static struct nfsd4_operation nfsd4_ops[]; -#ifdef NFSD_DEBUG static const char *nfsd4_op_name(unsigned opnum); -#endif /* * Enforce NFSv4.1 COMPOUND ordering rules: @@ -1226,6 +1212,8 @@ static inline struct nfsd4_operation *OPDESC(struct nfsd4_op *op) bool nfsd4_cache_this_op(struct nfsd4_op *op) { + if (op->opnum == OP_ILLEGAL) + return false; return OPDESC(op)->op_flags & OP_CACHEME; } @@ -1262,6 +1250,25 @@ static bool need_wrongsec_check(struct svc_rqst *rqstp) return !(nextd->op_flags & OP_HANDLES_WRONGSEC); } +static void svcxdr_init_encode(struct svc_rqst *rqstp, + struct nfsd4_compoundres *resp) +{ + struct xdr_stream *xdr = &resp->xdr; + struct xdr_buf *buf = &rqstp->rq_res; + struct kvec *head = buf->head; + + xdr->buf = buf; + xdr->iov = head; + xdr->p = head->iov_base + head->iov_len; + xdr->end = head->iov_base + PAGE_SIZE - rqstp->rq_auth_slack; + /* Tail and page_len should be zero at this point: */ + buf->len = buf->head[0].iov_len; + xdr->scratch.iov_len = 0; + xdr->page_ptr = buf->pages - 1; + buf->buflen = PAGE_SIZE * (1 + rqstp->rq_page_end - buf->pages) + - rqstp->rq_auth_slack; +} + /* * COMPOUND call. */ @@ -1275,24 +1282,16 @@ nfsd4_proc_compound(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate = &resp->cstate; struct svc_fh *current_fh = &cstate->current_fh; struct svc_fh *save_fh = &cstate->save_fh; - int slack_bytes; - u32 plen = 0; __be32 status; - resp->xbuf = &rqstp->rq_res; - resp->p = rqstp->rq_res.head[0].iov_base + - rqstp->rq_res.head[0].iov_len; - resp->tagp = resp->p; + svcxdr_init_encode(rqstp, resp); + resp->tagp = resp->xdr.p; /* reserve space for: taglen, tag, and opcnt */ - resp->p += 2 + XDR_QUADLEN(args->taglen); - resp->end = rqstp->rq_res.head[0].iov_base + PAGE_SIZE; + xdr_reserve_space(&resp->xdr, 8 + args->taglen); resp->taglen = args->taglen; resp->tag = args->tag; - resp->opcnt = 0; resp->rqstp = rqstp; cstate->minorversion = args->minorversion; - cstate->replay_owner = NULL; - cstate->session = NULL; fh_init(current_fh, NFS4_FHSIZE); fh_init(save_fh, NFS4_FHSIZE); /* @@ -1332,19 +1331,6 @@ nfsd4_proc_compound(struct svc_rqst *rqstp, goto encode_op; } - /* We must be able to encode a successful response to - * this operation, with enough room left over to encode a - * failed response to the next operation. If we don't - * have enough room, fail with ERR_RESOURCE. - */ - slack_bytes = (char *)resp->end - (char *)resp->p; - if (slack_bytes < COMPOUND_SLACK_SPACE - + COMPOUND_ERR_SLACK_SPACE) { - BUG_ON(slack_bytes < COMPOUND_ERR_SLACK_SPACE); - op->status = nfserr_resource; - goto encode_op; - } - opdesc = OPDESC(op); if (!current_fh->fh_dentry) { @@ -1362,9 +1348,13 @@ nfsd4_proc_compound(struct svc_rqst *rqstp, /* If op is non-idempotent */ if (opdesc->op_flags & OP_MODIFIES_SOMETHING) { - plen = opdesc->op_rsize_bop(rqstp, op); /* - * If there's still another operation, make sure + * Don't execute this op if we couldn't encode a + * succesful reply: + */ + u32 plen = opdesc->op_rsize_bop(rqstp, op); + /* + * Plus if there's another operation, make sure * we'll have space to at least encode an error: */ if (resp->opcnt < args->opcnt) @@ -1399,7 +1389,7 @@ encode_op: } if (op->status == nfserr_replay_me) { op->replay = &cstate->replay_owner->so_replay; - nfsd4_encode_replay(resp, op); + nfsd4_encode_replay(&resp->xdr, op); status = op->status = op->replay->rp_status; } else { nfsd4_encode_operation(resp, op); @@ -1438,7 +1428,8 @@ out: #define op_encode_change_info_maxsz (5) #define nfs4_fattr_bitmap_maxsz (4) -#define op_encode_lockowner_maxsz (1 + XDR_QUADLEN(IDMAP_NAMESZ)) +/* We'll fall back on returning no lockowner if run out of space: */ +#define op_encode_lockowner_maxsz (0) #define op_encode_lock_denied_maxsz (8 + op_encode_lockowner_maxsz) #define nfs4_owner_maxsz (1 + XDR_QUADLEN(IDMAP_NAMESZ)) @@ -1470,6 +1461,49 @@ static inline u32 nfsd4_create_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op + nfs4_fattr_bitmap_maxsz) * sizeof(__be32); } +/* + * Note since this is an idempotent operation we won't insist on failing + * 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) +{ + 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); + if (bmap0 & FATTR4_WORD0_FS_LOCATIONS) + return svc_max_payload(rqstp); + + if (bmap1 & FATTR4_WORD1_OWNER) { + ret += IDMAP_NAMESZ + 4; + bmap1 &= ~FATTR4_WORD1_OWNER; + } + if (bmap1 & FATTR4_WORD1_OWNER_GROUP) { + ret += IDMAP_NAMESZ + 4; + bmap1 &= ~FATTR4_WORD1_OWNER_GROUP; + } + if (bmap0 & FATTR4_WORD0_FILEHANDLE) { + ret += NFS4_FHSIZE + 4; + bmap0 &= ~FATTR4_WORD0_FILEHANDLE; + } + if (bmap2 & FATTR4_WORD2_SECURITY_LABEL) { + ret += NFSD4_MAX_SEC_LABEL_LEN + 12; + bmap2 &= ~FATTR4_WORD2_SECURITY_LABEL; + } + /* + * Largest of remaining attributes are 16 bytes (e.g., + * supported_attributes) + */ + ret += 16 * (hweight32(bmap0) + hweight32(bmap1) + hweight32(bmap2)); + /* bitmask, length */ + ret += 20; + return ret; +} + static inline u32 nfsd4_link_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) { return (op_encode_hdr_size + op_encode_change_info_maxsz) @@ -1500,18 +1534,19 @@ static inline u32 nfsd4_read_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) if (rlen > maxcount) rlen = maxcount; - return (op_encode_hdr_size + 2) * sizeof(__be32) + rlen; + return (op_encode_hdr_size + 2 + XDR_QUADLEN(rlen)) * sizeof(__be32); } static inline u32 nfsd4_readdir_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) { + u32 maxcount = svc_max_payload(rqstp); u32 rlen = op->u.readdir.rd_maxcount; - if (rlen > PAGE_SIZE) - rlen = PAGE_SIZE; + if (rlen > maxcount) + rlen = maxcount; - return (op_encode_hdr_size + op_encode_verifier_maxsz) - * sizeof(__be32) + rlen; + return (op_encode_hdr_size + op_encode_verifier_maxsz + + XDR_QUADLEN(rlen)) * sizeof(__be32); } static inline u32 nfsd4_remove_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) @@ -1526,6 +1561,12 @@ static inline u32 nfsd4_rename_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op + op_encode_change_info_maxsz) * sizeof(__be32); } +static inline u32 nfsd4_sequence_rsize(struct svc_rqst *rqstp, + struct nfsd4_op *op) +{ + return NFS4_MAX_SESSIONID_LEN + 20; +} + static inline u32 nfsd4_setattr_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) { return (op_encode_hdr_size + nfs4_fattr_bitmap_maxsz) * sizeof(__be32); @@ -1539,7 +1580,7 @@ static inline u32 nfsd4_setclientid_rsize(struct svc_rqst *rqstp, struct nfsd4_o static inline u32 nfsd4_write_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) { - return (op_encode_hdr_size + op_encode_verifier_maxsz) * sizeof(__be32); + 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) @@ -1607,6 +1648,7 @@ static struct nfsd4_operation nfsd4_ops[] = { [OP_GETATTR] = { .op_func = (nfsd4op_func)nfsd4_getattr, .op_flags = ALLOWED_ON_ABSENT_FS, + .op_rsize_bop = nfsd4_getattr_rsize, .op_name = "OP_GETATTR", }, [OP_GETFH] = { @@ -1676,37 +1718,32 @@ static struct nfsd4_operation nfsd4_ops[] = { [OP_PUTFH] = { .op_func = (nfsd4op_func)nfsd4_putfh, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS - | OP_IS_PUTFH_LIKE | OP_MODIFIES_SOMETHING - | OP_CLEAR_STATEID, + | OP_IS_PUTFH_LIKE | OP_CLEAR_STATEID, .op_name = "OP_PUTFH", .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, }, [OP_PUTPUBFH] = { .op_func = (nfsd4op_func)nfsd4_putrootfh, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS - | OP_IS_PUTFH_LIKE | OP_MODIFIES_SOMETHING - | OP_CLEAR_STATEID, + | OP_IS_PUTFH_LIKE | OP_CLEAR_STATEID, .op_name = "OP_PUTPUBFH", .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, }, [OP_PUTROOTFH] = { .op_func = (nfsd4op_func)nfsd4_putrootfh, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS - | OP_IS_PUTFH_LIKE | OP_MODIFIES_SOMETHING - | OP_CLEAR_STATEID, + | OP_IS_PUTFH_LIKE | OP_CLEAR_STATEID, .op_name = "OP_PUTROOTFH", .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, }, [OP_READ] = { .op_func = (nfsd4op_func)nfsd4_read, - .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_READ", .op_rsize_bop = (nfsd4op_rsize)nfsd4_read_rsize, .op_get_currentstateid = (stateid_getter)nfsd4_get_readstateid, }, [OP_READDIR] = { .op_func = (nfsd4op_func)nfsd4_readdir, - .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_READDIR", .op_rsize_bop = (nfsd4op_rsize)nfsd4_readdir_rsize, }, @@ -1864,14 +1901,33 @@ static struct nfsd4_operation nfsd4_ops[] = { }, }; -#ifdef NFSD_DEBUG +int nfsd4_max_reply(struct svc_rqst *rqstp, struct nfsd4_op *op) +{ + struct nfsd4_operation *opdesc; + nfsd4op_rsize estimator; + + if (op->opnum == OP_ILLEGAL) + return op_encode_hdr_size * sizeof(__be32); + opdesc = OPDESC(op); + estimator = opdesc->op_rsize_bop; + return estimator ? estimator(rqstp, op) : PAGE_SIZE; +} + +void warn_on_nonidempotent_op(struct nfsd4_op *op) +{ + if (OPDESC(op)->op_flags & OP_MODIFIES_SOMETHING) { + pr_err("unable to encode reply to nonidempotent op %d (%s)\n", + op->opnum, nfsd4_op_name(op->opnum)); + WARN_ON_ONCE(1); + } +} + static const char *nfsd4_op_name(unsigned opnum) { if (opnum < ARRAY_SIZE(nfsd4_ops)) return nfsd4_ops[opnum].op_name; return "unknown_operation"; } -#endif #define nfsd4_voidres nfsd4_voidargs struct nfsd4_voidargs { int dummy; }; diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 9a77a5a21557..c0d45cec9958 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -81,13 +81,13 @@ static DEFINE_MUTEX(client_mutex); * effort to decrease the scope of the client_mutex, this spinlock may * eventually cover more: */ -static DEFINE_SPINLOCK(recall_lock); +static DEFINE_SPINLOCK(state_lock); -static struct kmem_cache *openowner_slab = NULL; -static struct kmem_cache *lockowner_slab = NULL; -static struct kmem_cache *file_slab = NULL; -static struct kmem_cache *stateid_slab = NULL; -static struct kmem_cache *deleg_slab = NULL; +static struct kmem_cache *openowner_slab; +static struct kmem_cache *lockowner_slab; +static struct kmem_cache *file_slab; +static struct kmem_cache *stateid_slab; +static struct kmem_cache *deleg_slab; void nfs4_lock_state(void) @@ -235,9 +235,9 @@ static void nfsd4_free_file(struct nfs4_file *f) static inline void put_nfs4_file(struct nfs4_file *fi) { - if (atomic_dec_and_lock(&fi->fi_ref, &recall_lock)) { + if (atomic_dec_and_lock(&fi->fi_ref, &state_lock)) { hlist_del(&fi->fi_hash); - spin_unlock(&recall_lock); + spin_unlock(&state_lock); iput(fi->fi_inode); nfsd4_free_file(fi); } @@ -375,7 +375,6 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_ol_stateid *stp, struct sv dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab)); if (dp == NULL) return dp; - dp->dl_stid.sc_type = NFS4_DELEG_STID; /* * delegation seqid's are never incremented. The 4.1 special * meaning of seqid 0 isn't meaningful, really, but let's avoid @@ -418,6 +417,8 @@ nfs4_put_delegation(struct nfs4_delegation *dp) static void nfs4_put_deleg_lease(struct nfs4_file *fp) { + if (!fp->fi_lease) + return; if (atomic_dec_and_test(&fp->fi_delegees)) { vfs_setlease(fp->fi_deleg_file, F_UNLCK, &fp->fi_lease); fp->fi_lease = NULL; @@ -431,18 +432,30 @@ static void unhash_stid(struct nfs4_stid *s) s->sc_type = 0; } +static void +hash_delegation_locked(struct nfs4_delegation *dp, struct nfs4_file *fp) +{ + lockdep_assert_held(&state_lock); + + dp->dl_stid.sc_type = NFS4_DELEG_STID; + list_add(&dp->dl_perfile, &fp->fi_delegations); + list_add(&dp->dl_perclnt, &dp->dl_stid.sc_client->cl_delegations); +} + /* Called under the state lock. */ static void unhash_delegation(struct nfs4_delegation *dp) { + spin_lock(&state_lock); list_del_init(&dp->dl_perclnt); - spin_lock(&recall_lock); list_del_init(&dp->dl_perfile); list_del_init(&dp->dl_recall_lru); - spin_unlock(&recall_lock); - nfs4_put_deleg_lease(dp->dl_file); - put_nfs4_file(dp->dl_file); - dp->dl_file = NULL; + spin_unlock(&state_lock); + if (dp->dl_file) { + nfs4_put_deleg_lease(dp->dl_file); + put_nfs4_file(dp->dl_file); + dp->dl_file = NULL; + } } @@ -645,6 +658,12 @@ static void unhash_lockowner(struct nfs4_lockowner *lo) } } +static void nfs4_free_lockowner(struct nfs4_lockowner *lo) +{ + kfree(lo->lo_owner.so_owner.data); + kmem_cache_free(lockowner_slab, lo); +} + static void release_lockowner(struct nfs4_lockowner *lo) { unhash_lockowner(lo); @@ -699,6 +718,12 @@ static void release_last_closed_stateid(struct nfs4_openowner *oo) } } +static void nfs4_free_openowner(struct nfs4_openowner *oo) +{ + kfree(oo->oo_owner.so_owner.data); + kmem_cache_free(openowner_slab, oo); +} + static void release_openowner(struct nfs4_openowner *oo) { unhash_openowner(oo); @@ -1093,7 +1118,7 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name) return clp; } -static inline void +static void free_client(struct nfs4_client *clp) { struct nfsd_net __maybe_unused *nn = net_generic(clp->net, nfsd_net_id); @@ -1136,13 +1161,13 @@ destroy_client(struct nfs4_client *clp) struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); INIT_LIST_HEAD(&reaplist); - spin_lock(&recall_lock); + spin_lock(&state_lock); while (!list_empty(&clp->cl_delegations)) { dp = list_entry(clp->cl_delegations.next, struct nfs4_delegation, dl_perclnt); list_del_init(&dp->dl_perclnt); list_move(&dp->dl_recall_lru, &reaplist); } - spin_unlock(&recall_lock); + spin_unlock(&state_lock); while (!list_empty(&reaplist)) { dp = list_entry(reaplist.next, struct nfs4_delegation, dl_recall_lru); destroy_delegation(dp); @@ -1544,6 +1569,7 @@ out_err: void nfsd4_store_cache_entry(struct nfsd4_compoundres *resp) { + struct xdr_buf *buf = resp->xdr.buf; struct nfsd4_slot *slot = resp->cstate.slot; unsigned int base; @@ -1557,11 +1583,9 @@ nfsd4_store_cache_entry(struct nfsd4_compoundres *resp) slot->sl_datalen = 0; return; } - slot->sl_datalen = (char *)resp->p - (char *)resp->cstate.datap; - base = (char *)resp->cstate.datap - - (char *)resp->xbuf->head[0].iov_base; - if (read_bytes_from_xdr_buf(resp->xbuf, base, slot->sl_data, - slot->sl_datalen)) + base = resp->cstate.data_offset; + slot->sl_datalen = buf->len - base; + if (read_bytes_from_xdr_buf(buf, base, slot->sl_data, slot->sl_datalen)) WARN("%s: sessions DRC could not cache compound\n", __func__); return; } @@ -1602,6 +1626,8 @@ nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp, struct nfsd4_sequence *seq) { struct nfsd4_slot *slot = resp->cstate.slot; + struct xdr_stream *xdr = &resp->xdr; + __be32 *p; __be32 status; dprintk("--> %s slot %p\n", __func__, slot); @@ -1610,14 +1636,16 @@ nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp, if (status) return status; - /* The sequence operation has been encoded, cstate->datap set. */ - memcpy(resp->cstate.datap, slot->sl_data, slot->sl_datalen); + p = xdr_reserve_space(xdr, slot->sl_datalen); + if (!p) { + WARN_ON_ONCE(1); + return nfserr_serverfault; + } + xdr_encode_opaque_fixed(p, slot->sl_data, slot->sl_datalen); + xdr_commit_encode(xdr); resp->opcnt = slot->sl_opcnt; - resp->p = resp->cstate.datap + XDR_QUADLEN(slot->sl_datalen); - status = slot->sl_status; - - return status; + return slot->sl_status; } /* @@ -2189,11 +2217,13 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_sequence *seq) { struct nfsd4_compoundres *resp = rqstp->rq_resp; + struct xdr_stream *xdr = &resp->xdr; struct nfsd4_session *session; struct nfs4_client *clp; struct nfsd4_slot *slot; struct nfsd4_conn *conn; __be32 status; + int buflen; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); if (resp->opcnt != 1) @@ -2262,6 +2292,16 @@ nfsd4_sequence(struct svc_rqst *rqstp, if (status) goto out_put_session; + buflen = (seq->cachethis) ? + session->se_fchannel.maxresp_cached : + session->se_fchannel.maxresp_sz; + status = (seq->cachethis) ? nfserr_rep_too_big_to_cache : + nfserr_rep_too_big; + if (xdr_restrict_buflen(xdr, buflen - rqstp->rq_auth_slack)) + goto out_put_session; + svc_reserve(rqstp, buflen); + + status = nfs_ok; /* Success! bump slot seqid */ slot->sl_seqid = seq->seqid; slot->sl_flags |= NFSD4_SLOT_INUSE; @@ -2499,28 +2539,19 @@ static void nfsd4_init_file(struct nfs4_file *fp, struct inode *ino) fp->fi_lease = NULL; memset(fp->fi_fds, 0, sizeof(fp->fi_fds)); memset(fp->fi_access, 0, sizeof(fp->fi_access)); - spin_lock(&recall_lock); + spin_lock(&state_lock); hlist_add_head(&fp->fi_hash, &file_hashtbl[hashval]); - spin_unlock(&recall_lock); -} - -static void -nfsd4_free_slab(struct kmem_cache **slab) -{ - if (*slab == NULL) - return; - kmem_cache_destroy(*slab); - *slab = NULL; + spin_unlock(&state_lock); } void nfsd4_free_slabs(void) { - nfsd4_free_slab(&openowner_slab); - nfsd4_free_slab(&lockowner_slab); - nfsd4_free_slab(&file_slab); - nfsd4_free_slab(&stateid_slab); - nfsd4_free_slab(&deleg_slab); + kmem_cache_destroy(openowner_slab); + kmem_cache_destroy(lockowner_slab); + kmem_cache_destroy(file_slab); + kmem_cache_destroy(stateid_slab); + kmem_cache_destroy(deleg_slab); } int @@ -2529,42 +2560,38 @@ nfsd4_init_slabs(void) openowner_slab = kmem_cache_create("nfsd4_openowners", sizeof(struct nfs4_openowner), 0, 0, NULL); if (openowner_slab == NULL) - goto out_nomem; + goto out; lockowner_slab = kmem_cache_create("nfsd4_lockowners", sizeof(struct nfs4_lockowner), 0, 0, NULL); if (lockowner_slab == NULL) - goto out_nomem; + goto out_free_openowner_slab; file_slab = kmem_cache_create("nfsd4_files", sizeof(struct nfs4_file), 0, 0, NULL); if (file_slab == NULL) - goto out_nomem; + goto out_free_lockowner_slab; stateid_slab = kmem_cache_create("nfsd4_stateids", sizeof(struct nfs4_ol_stateid), 0, 0, NULL); if (stateid_slab == NULL) - goto out_nomem; + goto out_free_file_slab; deleg_slab = kmem_cache_create("nfsd4_delegations", sizeof(struct nfs4_delegation), 0, 0, NULL); if (deleg_slab == NULL) - goto out_nomem; + goto out_free_stateid_slab; return 0; -out_nomem: - nfsd4_free_slabs(); + +out_free_stateid_slab: + kmem_cache_destroy(stateid_slab); +out_free_file_slab: + kmem_cache_destroy(file_slab); +out_free_lockowner_slab: + kmem_cache_destroy(lockowner_slab); +out_free_openowner_slab: + kmem_cache_destroy(openowner_slab); +out: dprintk("nfsd4: out of memory while initializing nfsv4\n"); return -ENOMEM; } -void nfs4_free_openowner(struct nfs4_openowner *oo) -{ - kfree(oo->oo_owner.so_owner.data); - kmem_cache_free(openowner_slab, oo); -} - -void nfs4_free_lockowner(struct nfs4_lockowner *lo) -{ - kfree(lo->lo_owner.so_owner.data); - kmem_cache_free(lockowner_slab, lo); -} - static void init_nfs4_replay(struct nfs4_replay *rp) { rp->rp_status = nfserr_serverfault; @@ -2685,15 +2712,15 @@ find_file(struct inode *ino) unsigned int hashval = file_hashval(ino); struct nfs4_file *fp; - spin_lock(&recall_lock); + spin_lock(&state_lock); hlist_for_each_entry(fp, &file_hashtbl[hashval], fi_hash) { if (fp->fi_inode == ino) { get_nfs4_file(fp); - spin_unlock(&recall_lock); + spin_unlock(&state_lock); return fp; } } - spin_unlock(&recall_lock); + spin_unlock(&state_lock); return NULL; } @@ -2730,6 +2757,7 @@ static void nfsd_break_one_deleg(struct nfs4_delegation *dp) struct nfs4_client *clp = dp->dl_stid.sc_client; struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); + lockdep_assert_held(&state_lock); /* 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 kernel @@ -2766,11 +2794,11 @@ static void nfsd_break_deleg_cb(struct file_lock *fl) */ fl->fl_break_time = 0; - spin_lock(&recall_lock); + spin_lock(&state_lock); fp->fi_had_conflict = true; list_for_each_entry(dp, &fp->fi_delegations, dl_perfile) nfsd_break_one_deleg(dp); - spin_unlock(&recall_lock); + spin_unlock(&state_lock); } static @@ -3047,11 +3075,12 @@ static int nfs4_setlease(struct nfs4_delegation *dp) status = vfs_setlease(fl->fl_file, fl->fl_type, &fl); if (status) goto out_free; - list_add(&dp->dl_perclnt, &dp->dl_stid.sc_client->cl_delegations); fp->fi_lease = fl; fp->fi_deleg_file = get_file(fl->fl_file); atomic_set(&fp->fi_delegees, 1); - list_add(&dp->dl_perfile, &fp->fi_delegations); + spin_lock(&state_lock); + hash_delegation_locked(dp, fp); + spin_unlock(&state_lock); return 0; out_free: locks_free_lock(fl); @@ -3060,33 +3089,21 @@ out_free: static int nfs4_set_delegation(struct nfs4_delegation *dp, struct nfs4_file *fp) { - int status; - if (fp->fi_had_conflict) return -EAGAIN; get_nfs4_file(fp); dp->dl_file = fp; - if (!fp->fi_lease) { - status = nfs4_setlease(dp); - if (status) - goto out_free; - return 0; - } - spin_lock(&recall_lock); + if (!fp->fi_lease) + return nfs4_setlease(dp); + spin_lock(&state_lock); + atomic_inc(&fp->fi_delegees); if (fp->fi_had_conflict) { - spin_unlock(&recall_lock); - status = -EAGAIN; - goto out_free; + spin_unlock(&state_lock); + return -EAGAIN; } - atomic_inc(&fp->fi_delegees); - list_add(&dp->dl_perfile, &fp->fi_delegations); - spin_unlock(&recall_lock); - list_add(&dp->dl_perclnt, &dp->dl_stid.sc_client->cl_delegations); + hash_delegation_locked(dp, fp); + spin_unlock(&state_lock); return 0; -out_free: - put_nfs4_file(fp); - dp->dl_file = fp; - return status; } static void nfsd4_open_deleg_none_ext(struct nfsd4_open *open, int status) @@ -3173,8 +3190,7 @@ nfs4_open_delegation(struct net *net, struct svc_fh *fh, open->op_delegate_type = NFS4_OPEN_DELEGATE_READ; return; out_free: - remove_stid(&dp->dl_stid); - nfs4_put_delegation(dp); + destroy_delegation(dp); out_no_deleg: open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE; if (open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS && @@ -3391,8 +3407,7 @@ nfs4_laundromat(struct nfsd_net *nn) struct nfs4_delegation *dp; struct list_head *pos, *next, reaplist; time_t cutoff = get_seconds() - nn->nfsd4_lease; - time_t t, clientid_val = nn->nfsd4_lease; - time_t u, test_val = nn->nfsd4_lease; + time_t t, new_timeo = nn->nfsd4_lease; nfs4_lock_state(); @@ -3404,8 +3419,7 @@ nfs4_laundromat(struct nfsd_net *nn) clp = list_entry(pos, struct nfs4_client, cl_lru); if (time_after((unsigned long)clp->cl_time, (unsigned long)cutoff)) { t = clp->cl_time - cutoff; - if (clientid_val > t) - clientid_val = t; + new_timeo = min(new_timeo, t); break; } if (mark_client_expired_locked(clp)) { @@ -3422,39 +3436,35 @@ nfs4_laundromat(struct nfsd_net *nn) clp->cl_clientid.cl_id); expire_client(clp); } - spin_lock(&recall_lock); + spin_lock(&state_lock); list_for_each_safe(pos, next, &nn->del_recall_lru) { dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru); if (net_generic(dp->dl_stid.sc_client->net, nfsd_net_id) != nn) continue; if (time_after((unsigned long)dp->dl_time, (unsigned long)cutoff)) { - u = dp->dl_time - cutoff; - if (test_val > u) - test_val = u; + t = dp->dl_time - cutoff; + new_timeo = min(new_timeo, t); break; } list_move(&dp->dl_recall_lru, &reaplist); } - spin_unlock(&recall_lock); + spin_unlock(&state_lock); list_for_each_safe(pos, next, &reaplist) { dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru); revoke_delegation(dp); } - test_val = nn->nfsd4_lease; list_for_each_safe(pos, next, &nn->close_lru) { oo = container_of(pos, struct nfs4_openowner, oo_close_lru); if (time_after((unsigned long)oo->oo_time, (unsigned long)cutoff)) { - u = oo->oo_time - cutoff; - if (test_val > u) - test_val = u; + t = oo->oo_time - cutoff; + new_timeo = min(new_timeo, t); break; } release_openowner(oo); } - if (clientid_val < NFSD_LAUNDROMAT_MINTIMEOUT) - clientid_val = NFSD_LAUNDROMAT_MINTIMEOUT; + new_timeo = max_t(time_t, new_timeo, NFSD_LAUNDROMAT_MINTIMEOUT); nfs4_unlock_state(); - return clientid_val; + return new_timeo; } static struct workqueue_struct *laundry_wq; @@ -3654,6 +3664,7 @@ nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate, struct svc_fh *current_fh = &cstate->current_fh; struct inode *ino = current_fh->fh_dentry->d_inode; struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct file *file = NULL; __be32 status; if (filpp) @@ -3665,10 +3676,12 @@ nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate, if (ZERO_STATEID(stateid) || ONE_STATEID(stateid)) return check_special_stateids(net, current_fh, stateid, flags); + nfs4_lock_state(); + status = nfsd4_lookup_stateid(stateid, NFS4_DELEG_STID|NFS4_OPEN_STID|NFS4_LOCK_STID, &s, cstate->minorversion, nn); if (status) - return status; + goto out; status = check_stateid_generation(stateid, &s->sc_stateid, nfsd4_has_session(cstate)); if (status) goto out; @@ -3679,8 +3692,8 @@ nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate, if (status) goto out; if (filpp) { - *filpp = dp->dl_file->fi_deleg_file; - if (!*filpp) { + file = dp->dl_file->fi_deleg_file; + if (!file) { WARN_ON_ONCE(1); status = nfserr_serverfault; goto out; @@ -3701,16 +3714,20 @@ nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate, goto out; if (filpp) { if (flags & RD_STATE) - *filpp = find_readable_file(stp->st_file); + file = find_readable_file(stp->st_file); else - *filpp = find_writeable_file(stp->st_file); + file = find_writeable_file(stp->st_file); } break; default: - return nfserr_bad_stateid; + status = nfserr_bad_stateid; + goto out; } status = nfs_ok; + if (file) + *filpp = get_file(file); out: + nfs4_unlock_state(); return status; } @@ -3726,7 +3743,7 @@ nfsd4_free_lock_stateid(struct nfs4_ol_stateid *stp) * correspondance, and we have to delete the lockowner when we * delete the lock stateid: */ - unhash_lockowner(lo); + release_lockowner(lo); return nfs_ok; } @@ -4896,6 +4913,7 @@ static u64 nfsd_find_all_delegations(struct nfs4_client *clp, u64 max, struct nfs4_delegation *dp, *next; u64 count = 0; + lockdep_assert_held(&state_lock); list_for_each_entry_safe(dp, next, &clp->cl_delegations, dl_perclnt) { if (victims) list_move(&dp->dl_recall_lru, victims); @@ -4911,9 +4929,9 @@ u64 nfsd_forget_client_delegations(struct nfs4_client *clp, u64 max) LIST_HEAD(victims); u64 count; - spin_lock(&recall_lock); + spin_lock(&state_lock); count = nfsd_find_all_delegations(clp, max, &victims); - spin_unlock(&recall_lock); + spin_unlock(&state_lock); list_for_each_entry_safe(dp, next, &victims, dl_recall_lru) revoke_delegation(dp); @@ -4927,11 +4945,11 @@ u64 nfsd_recall_client_delegations(struct nfs4_client *clp, u64 max) LIST_HEAD(victims); u64 count; - spin_lock(&recall_lock); + spin_lock(&state_lock); count = nfsd_find_all_delegations(clp, max, &victims); list_for_each_entry_safe(dp, next, &victims, dl_recall_lru) nfsd_break_one_deleg(dp); - spin_unlock(&recall_lock); + spin_unlock(&state_lock); return count; } @@ -4940,9 +4958,9 @@ u64 nfsd_print_client_delegations(struct nfs4_client *clp, u64 max) { u64 count = 0; - spin_lock(&recall_lock); + spin_lock(&state_lock); count = nfsd_find_all_delegations(clp, max, NULL); - spin_unlock(&recall_lock); + spin_unlock(&state_lock); nfsd_print_count(clp, count, "delegations"); return count; @@ -4983,13 +5001,6 @@ struct nfs4_client *nfsd_find_client(struct sockaddr_storage *addr, size_t addr_ #endif /* CONFIG_NFSD_FAULT_INJECTION */ -/* initialization to perform at module load time: */ - -void -nfs4_state_init(void) -{ -} - /* * Since the lifetime of a delegation isn't limited to that of an open, a * client may quite reasonably hang on to a delegation as long as it has @@ -5160,12 +5171,12 @@ nfs4_state_shutdown_net(struct net *net) nfs4_lock_state(); INIT_LIST_HEAD(&reaplist); - spin_lock(&recall_lock); + spin_lock(&state_lock); list_for_each_safe(pos, next, &nn->del_recall_lru) { dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru); list_move(&dp->dl_recall_lru, &reaplist); } - spin_unlock(&recall_lock); + spin_unlock(&state_lock); list_for_each_safe(pos, next, &reaplist) { dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru); destroy_delegation(dp); diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 18881f34737a..2d305a121f37 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -98,11 +98,6 @@ xdr_error: \ status = nfserr_bad_xdr; \ goto out -#define READ32(x) (x) = ntohl(*p++) -#define READ64(x) do { \ - (x) = (u64)ntohl(*p++) << 32; \ - (x) |= ntohl(*p++); \ -} while (0) #define READMEM(x,nbytes) do { \ x = (char *)p; \ p += XDR_QUADLEN(nbytes); \ @@ -248,17 +243,17 @@ nfsd4_decode_bitmap(struct nfsd4_compoundargs *argp, u32 *bmval) bmval[2] = 0; READ_BUF(4); - READ32(bmlen); + bmlen = be32_to_cpup(p++); if (bmlen > 1000) goto xdr_error; READ_BUF(bmlen << 2); if (bmlen > 0) - READ32(bmval[0]); + bmval[0] = be32_to_cpup(p++); if (bmlen > 1) - READ32(bmval[1]); + bmval[1] = be32_to_cpup(p++); if (bmlen > 2) - READ32(bmval[2]); + bmval[2] = be32_to_cpup(p++); DECODE_TAIL; } @@ -270,6 +265,7 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, { int expected_len, len = 0; u32 dummy32; + u64 sec; char *buf; DECODE_HEAD; @@ -278,12 +274,12 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, return status; READ_BUF(4); - READ32(expected_len); + expected_len = be32_to_cpup(p++); if (bmval[0] & FATTR4_WORD0_SIZE) { READ_BUF(8); len += 8; - READ64(iattr->ia_size); + p = xdr_decode_hyper(p, &iattr->ia_size); iattr->ia_valid |= ATTR_SIZE; } if (bmval[0] & FATTR4_WORD0_ACL) { @@ -291,7 +287,7 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, struct nfs4_ace *ace; READ_BUF(4); len += 4; - READ32(nace); + nace = be32_to_cpup(p++); if (nace > NFS4_ACL_MAX) return nfserr_fbig; @@ -305,10 +301,10 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, (*acl)->naces = nace; for (ace = (*acl)->aces; ace < (*acl)->aces + nace; ace++) { READ_BUF(16); len += 16; - READ32(ace->type); - READ32(ace->flag); - READ32(ace->access_mask); - READ32(dummy32); + ace->type = be32_to_cpup(p++); + ace->flag = be32_to_cpup(p++); + ace->access_mask = be32_to_cpup(p++); + dummy32 = be32_to_cpup(p++); READ_BUF(dummy32); len += XDR_QUADLEN(dummy32) << 2; READMEM(buf, dummy32); @@ -330,14 +326,14 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, if (bmval[1] & FATTR4_WORD1_MODE) { READ_BUF(4); len += 4; - READ32(iattr->ia_mode); + iattr->ia_mode = be32_to_cpup(p++); iattr->ia_mode &= (S_IFMT | S_IALLUGO); iattr->ia_valid |= ATTR_MODE; } if (bmval[1] & FATTR4_WORD1_OWNER) { READ_BUF(4); len += 4; - READ32(dummy32); + dummy32 = be32_to_cpup(p++); READ_BUF(dummy32); len += (XDR_QUADLEN(dummy32) << 2); READMEM(buf, dummy32); @@ -348,7 +344,7 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, if (bmval[1] & FATTR4_WORD1_OWNER_GROUP) { READ_BUF(4); len += 4; - READ32(dummy32); + dummy32 = be32_to_cpup(p++); READ_BUF(dummy32); len += (XDR_QUADLEN(dummy32) << 2); READMEM(buf, dummy32); @@ -359,15 +355,16 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, if (bmval[1] & FATTR4_WORD1_TIME_ACCESS_SET) { READ_BUF(4); len += 4; - READ32(dummy32); + dummy32 = be32_to_cpup(p++); switch (dummy32) { case NFS4_SET_TO_CLIENT_TIME: /* We require the high 32 bits of 'seconds' to be 0, and we ignore all 32 bits of 'nseconds'. */ READ_BUF(12); len += 12; - READ64(iattr->ia_atime.tv_sec); - READ32(iattr->ia_atime.tv_nsec); + p = xdr_decode_hyper(p, &sec); + iattr->ia_atime.tv_sec = (time_t)sec; + iattr->ia_atime.tv_nsec = be32_to_cpup(p++); if (iattr->ia_atime.tv_nsec >= (u32)1000000000) return nfserr_inval; iattr->ia_valid |= (ATTR_ATIME | ATTR_ATIME_SET); @@ -382,15 +379,16 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, if (bmval[1] & FATTR4_WORD1_TIME_MODIFY_SET) { READ_BUF(4); len += 4; - READ32(dummy32); + dummy32 = be32_to_cpup(p++); switch (dummy32) { case NFS4_SET_TO_CLIENT_TIME: /* We require the high 32 bits of 'seconds' to be 0, and we ignore all 32 bits of 'nseconds'. */ READ_BUF(12); len += 12; - READ64(iattr->ia_mtime.tv_sec); - READ32(iattr->ia_mtime.tv_nsec); + p = xdr_decode_hyper(p, &sec); + iattr->ia_mtime.tv_sec = sec; + iattr->ia_mtime.tv_nsec = be32_to_cpup(p++); if (iattr->ia_mtime.tv_nsec >= (u32)1000000000) return nfserr_inval; iattr->ia_valid |= (ATTR_MTIME | ATTR_MTIME_SET); @@ -408,13 +406,13 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, if (bmval[2] & FATTR4_WORD2_SECURITY_LABEL) { READ_BUF(4); len += 4; - READ32(dummy32); /* lfs: we don't use it */ + dummy32 = be32_to_cpup(p++); /* lfs: we don't use it */ READ_BUF(4); len += 4; - READ32(dummy32); /* pi: we don't use it either */ + dummy32 = be32_to_cpup(p++); /* pi: we don't use it either */ READ_BUF(4); len += 4; - READ32(dummy32); + dummy32 = be32_to_cpup(p++); READ_BUF(dummy32); if (dummy32 > NFSD4_MAX_SEC_LABEL_LEN) return nfserr_badlabel; @@ -445,7 +443,7 @@ nfsd4_decode_stateid(struct nfsd4_compoundargs *argp, stateid_t *sid) DECODE_HEAD; READ_BUF(sizeof(stateid_t)); - READ32(sid->si_generation); + sid->si_generation = be32_to_cpup(p++); COPYMEM(&sid->si_opaque, sizeof(stateid_opaque_t)); DECODE_TAIL; @@ -457,7 +455,7 @@ nfsd4_decode_access(struct nfsd4_compoundargs *argp, struct nfsd4_access *access DECODE_HEAD; READ_BUF(4); - READ32(access->ac_req_access); + access->ac_req_access = be32_to_cpup(p++); DECODE_TAIL; } @@ -472,7 +470,7 @@ static __be32 nfsd4_decode_cb_sec(struct nfsd4_compoundargs *argp, struct nfsd4_ /* callback_sec_params4 */ READ_BUF(4); - READ32(nr_secflavs); + nr_secflavs = be32_to_cpup(p++); if (nr_secflavs) cbs->flavor = (u32)(-1); else @@ -480,7 +478,7 @@ static __be32 nfsd4_decode_cb_sec(struct nfsd4_compoundargs *argp, struct nfsd4_ cbs->flavor = 0; for (i = 0; i < nr_secflavs; ++i) { READ_BUF(4); - READ32(dummy); + dummy = be32_to_cpup(p++); switch (dummy) { case RPC_AUTH_NULL: /* Nothing to read */ @@ -490,21 +488,21 @@ static __be32 nfsd4_decode_cb_sec(struct nfsd4_compoundargs *argp, struct nfsd4_ case RPC_AUTH_UNIX: READ_BUF(8); /* stamp */ - READ32(dummy); + dummy = be32_to_cpup(p++); /* machine name */ - READ32(dummy); + dummy = be32_to_cpup(p++); READ_BUF(dummy); SAVEMEM(machine_name, dummy); /* uid, gid */ READ_BUF(8); - READ32(uid); - READ32(gid); + uid = be32_to_cpup(p++); + gid = be32_to_cpup(p++); /* more gids */ READ_BUF(4); - READ32(dummy); + dummy = be32_to_cpup(p++); READ_BUF(dummy * 4); if (cbs->flavor == (u32)(-1)) { kuid_t kuid = make_kuid(&init_user_ns, uid); @@ -524,14 +522,14 @@ static __be32 nfsd4_decode_cb_sec(struct nfsd4_compoundargs *argp, struct nfsd4_ "not supported!\n"); READ_BUF(8); /* gcbp_service */ - READ32(dummy); + dummy = be32_to_cpup(p++); /* gcbp_handle_from_server */ - READ32(dummy); + dummy = be32_to_cpup(p++); READ_BUF(dummy); p += XDR_QUADLEN(dummy); /* gcbp_handle_from_client */ READ_BUF(4); - READ32(dummy); + dummy = be32_to_cpup(p++); READ_BUF(dummy); break; default: @@ -547,7 +545,7 @@ static __be32 nfsd4_decode_backchannel_ctl(struct nfsd4_compoundargs *argp, stru DECODE_HEAD; READ_BUF(4); - READ32(bc->bc_cb_program); + bc->bc_cb_program = be32_to_cpup(p++); nfsd4_decode_cb_sec(argp, &bc->bc_cb_sec); DECODE_TAIL; @@ -559,7 +557,7 @@ static __be32 nfsd4_decode_bind_conn_to_session(struct nfsd4_compoundargs *argp, READ_BUF(NFS4_MAX_SESSIONID_LEN + 8); COPYMEM(bcts->sessionid.data, NFS4_MAX_SESSIONID_LEN); - READ32(bcts->dir); + bcts->dir = be32_to_cpup(p++); /* XXX: skipping ctsa_use_conn_in_rdma_mode. Perhaps Tom Tucker * could help us figure out we should be using it. */ DECODE_TAIL; @@ -571,7 +569,7 @@ nfsd4_decode_close(struct nfsd4_compoundargs *argp, struct nfsd4_close *close) DECODE_HEAD; READ_BUF(4); - READ32(close->cl_seqid); + close->cl_seqid = be32_to_cpup(p++); return nfsd4_decode_stateid(argp, &close->cl_stateid); DECODE_TAIL; @@ -584,8 +582,8 @@ nfsd4_decode_commit(struct nfsd4_compoundargs *argp, struct nfsd4_commit *commit DECODE_HEAD; READ_BUF(12); - READ64(commit->co_offset); - READ32(commit->co_count); + p = xdr_decode_hyper(p, &commit->co_offset); + commit->co_count = be32_to_cpup(p++); DECODE_TAIL; } @@ -596,19 +594,19 @@ nfsd4_decode_create(struct nfsd4_compoundargs *argp, struct nfsd4_create *create DECODE_HEAD; READ_BUF(4); - READ32(create->cr_type); + create->cr_type = be32_to_cpup(p++); switch (create->cr_type) { case NF4LNK: READ_BUF(4); - READ32(create->cr_linklen); + create->cr_linklen = be32_to_cpup(p++); READ_BUF(create->cr_linklen); SAVEMEM(create->cr_linkname, create->cr_linklen); break; case NF4BLK: case NF4CHR: READ_BUF(8); - READ32(create->cr_specdata1); - READ32(create->cr_specdata2); + create->cr_specdata1 = be32_to_cpup(p++); + create->cr_specdata2 = be32_to_cpup(p++); break; case NF4SOCK: case NF4FIFO: @@ -618,7 +616,7 @@ nfsd4_decode_create(struct nfsd4_compoundargs *argp, struct nfsd4_create *create } READ_BUF(4); - READ32(create->cr_namelen); + create->cr_namelen = be32_to_cpup(p++); READ_BUF(create->cr_namelen); SAVEMEM(create->cr_name, create->cr_namelen); if ((status = check_filename(create->cr_name, create->cr_namelen))) @@ -650,7 +648,7 @@ nfsd4_decode_link(struct nfsd4_compoundargs *argp, struct nfsd4_link *link) DECODE_HEAD; READ_BUF(4); - READ32(link->li_namelen); + link->li_namelen = be32_to_cpup(p++); READ_BUF(link->li_namelen); SAVEMEM(link->li_name, link->li_namelen); if ((status = check_filename(link->li_name, link->li_namelen))) @@ -668,24 +666,24 @@ nfsd4_decode_lock(struct nfsd4_compoundargs *argp, struct nfsd4_lock *lock) * type, reclaim(boolean), offset, length, new_lock_owner(boolean) */ READ_BUF(28); - READ32(lock->lk_type); + lock->lk_type = be32_to_cpup(p++); if ((lock->lk_type < NFS4_READ_LT) || (lock->lk_type > NFS4_WRITEW_LT)) goto xdr_error; - READ32(lock->lk_reclaim); - READ64(lock->lk_offset); - READ64(lock->lk_length); - READ32(lock->lk_is_new); + lock->lk_reclaim = be32_to_cpup(p++); + p = xdr_decode_hyper(p, &lock->lk_offset); + p = xdr_decode_hyper(p, &lock->lk_length); + lock->lk_is_new = be32_to_cpup(p++); if (lock->lk_is_new) { READ_BUF(4); - READ32(lock->lk_new_open_seqid); + lock->lk_new_open_seqid = be32_to_cpup(p++); status = nfsd4_decode_stateid(argp, &lock->lk_new_open_stateid); if (status) return status; READ_BUF(8 + sizeof(clientid_t)); - READ32(lock->lk_new_lock_seqid); + lock->lk_new_lock_seqid = be32_to_cpup(p++); COPYMEM(&lock->lk_new_clientid, sizeof(clientid_t)); - READ32(lock->lk_new_owner.len); + lock->lk_new_owner.len = be32_to_cpup(p++); READ_BUF(lock->lk_new_owner.len); READMEM(lock->lk_new_owner.data, lock->lk_new_owner.len); } else { @@ -693,7 +691,7 @@ nfsd4_decode_lock(struct nfsd4_compoundargs *argp, struct nfsd4_lock *lock) if (status) return status; READ_BUF(4); - READ32(lock->lk_old_lock_seqid); + lock->lk_old_lock_seqid = be32_to_cpup(p++); } DECODE_TAIL; @@ -705,13 +703,13 @@ nfsd4_decode_lockt(struct nfsd4_compoundargs *argp, struct nfsd4_lockt *lockt) DECODE_HEAD; READ_BUF(32); - READ32(lockt->lt_type); + lockt->lt_type = be32_to_cpup(p++); if((lockt->lt_type < NFS4_READ_LT) || (lockt->lt_type > NFS4_WRITEW_LT)) goto xdr_error; - READ64(lockt->lt_offset); - READ64(lockt->lt_length); + p = xdr_decode_hyper(p, &lockt->lt_offset); + p = xdr_decode_hyper(p, &lockt->lt_length); COPYMEM(&lockt->lt_clientid, 8); - READ32(lockt->lt_owner.len); + lockt->lt_owner.len = be32_to_cpup(p++); READ_BUF(lockt->lt_owner.len); READMEM(lockt->lt_owner.data, lockt->lt_owner.len); @@ -724,16 +722,16 @@ nfsd4_decode_locku(struct nfsd4_compoundargs *argp, struct nfsd4_locku *locku) DECODE_HEAD; READ_BUF(8); - READ32(locku->lu_type); + locku->lu_type = be32_to_cpup(p++); if ((locku->lu_type < NFS4_READ_LT) || (locku->lu_type > NFS4_WRITEW_LT)) goto xdr_error; - READ32(locku->lu_seqid); + locku->lu_seqid = be32_to_cpup(p++); status = nfsd4_decode_stateid(argp, &locku->lu_stateid); if (status) return status; READ_BUF(16); - READ64(locku->lu_offset); - READ64(locku->lu_length); + p = xdr_decode_hyper(p, &locku->lu_offset); + p = xdr_decode_hyper(p, &locku->lu_length); DECODE_TAIL; } @@ -744,7 +742,7 @@ nfsd4_decode_lookup(struct nfsd4_compoundargs *argp, struct nfsd4_lookup *lookup DECODE_HEAD; READ_BUF(4); - READ32(lookup->lo_len); + lookup->lo_len = be32_to_cpup(p++); READ_BUF(lookup->lo_len); SAVEMEM(lookup->lo_name, lookup->lo_len); if ((status = check_filename(lookup->lo_name, lookup->lo_len))) @@ -759,7 +757,7 @@ static __be32 nfsd4_decode_share_access(struct nfsd4_compoundargs *argp, u32 *sh u32 w; READ_BUF(4); - READ32(w); + w = be32_to_cpup(p++); *share_access = w & NFS4_SHARE_ACCESS_MASK; *deleg_want = w & NFS4_SHARE_WANT_MASK; if (deleg_when) @@ -811,7 +809,7 @@ static __be32 nfsd4_decode_share_deny(struct nfsd4_compoundargs *argp, u32 *x) __be32 *p; READ_BUF(4); - READ32(*x); + *x = be32_to_cpup(p++); /* Note: unlinke access bits, deny bits may be zero. */ if (*x & ~NFS4_SHARE_DENY_BOTH) return nfserr_bad_xdr; @@ -825,7 +823,7 @@ static __be32 nfsd4_decode_opaque(struct nfsd4_compoundargs *argp, struct xdr_ne __be32 *p; READ_BUF(4); - READ32(o->len); + o->len = be32_to_cpup(p++); if (o->len == 0 || o->len > NFS4_OPAQUE_LIMIT) return nfserr_bad_xdr; @@ -850,7 +848,7 @@ nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open) open->op_xdr_error = 0; /* seqid, share_access, share_deny, clientid, ownerlen */ READ_BUF(4); - READ32(open->op_seqid); + open->op_seqid = be32_to_cpup(p++); /* decode, yet ignore deleg_when until supported */ status = nfsd4_decode_share_access(argp, &open->op_share_access, &open->op_deleg_want, &dummy); @@ -865,13 +863,13 @@ nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open) if (status) goto xdr_error; READ_BUF(4); - READ32(open->op_create); + open->op_create = be32_to_cpup(p++); switch (open->op_create) { case NFS4_OPEN_NOCREATE: break; case NFS4_OPEN_CREATE: READ_BUF(4); - READ32(open->op_createmode); + open->op_createmode = be32_to_cpup(p++); switch (open->op_createmode) { case NFS4_CREATE_UNCHECKED: case NFS4_CREATE_GUARDED: @@ -904,12 +902,12 @@ nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open) /* open_claim */ READ_BUF(4); - READ32(open->op_claim_type); + open->op_claim_type = be32_to_cpup(p++); switch (open->op_claim_type) { case NFS4_OPEN_CLAIM_NULL: case NFS4_OPEN_CLAIM_DELEGATE_PREV: READ_BUF(4); - READ32(open->op_fname.len); + open->op_fname.len = be32_to_cpup(p++); READ_BUF(open->op_fname.len); SAVEMEM(open->op_fname.data, open->op_fname.len); if ((status = check_filename(open->op_fname.data, open->op_fname.len))) @@ -917,14 +915,14 @@ nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open) break; case NFS4_OPEN_CLAIM_PREVIOUS: READ_BUF(4); - READ32(open->op_delegate_type); + open->op_delegate_type = be32_to_cpup(p++); break; case NFS4_OPEN_CLAIM_DELEGATE_CUR: status = nfsd4_decode_stateid(argp, &open->op_delegate_stateid); if (status) return status; READ_BUF(4); - READ32(open->op_fname.len); + open->op_fname.len = be32_to_cpup(p++); READ_BUF(open->op_fname.len); SAVEMEM(open->op_fname.data, open->op_fname.len); if ((status = check_filename(open->op_fname.data, open->op_fname.len))) @@ -962,7 +960,7 @@ nfsd4_decode_open_confirm(struct nfsd4_compoundargs *argp, struct nfsd4_open_con if (status) return status; READ_BUF(4); - READ32(open_conf->oc_seqid); + open_conf->oc_seqid = be32_to_cpup(p++); DECODE_TAIL; } @@ -976,7 +974,7 @@ nfsd4_decode_open_downgrade(struct nfsd4_compoundargs *argp, struct nfsd4_open_d if (status) return status; READ_BUF(4); - READ32(open_down->od_seqid); + open_down->od_seqid = be32_to_cpup(p++); status = nfsd4_decode_share_access(argp, &open_down->od_share_access, &open_down->od_deleg_want, NULL); if (status) @@ -993,7 +991,7 @@ nfsd4_decode_putfh(struct nfsd4_compoundargs *argp, struct nfsd4_putfh *putfh) DECODE_HEAD; READ_BUF(4); - READ32(putfh->pf_fhlen); + putfh->pf_fhlen = be32_to_cpup(p++); if (putfh->pf_fhlen > NFS4_FHSIZE) goto xdr_error; READ_BUF(putfh->pf_fhlen); @@ -1019,8 +1017,8 @@ nfsd4_decode_read(struct nfsd4_compoundargs *argp, struct nfsd4_read *read) if (status) return status; READ_BUF(12); - READ64(read->rd_offset); - READ32(read->rd_length); + p = xdr_decode_hyper(p, &read->rd_offset); + read->rd_length = be32_to_cpup(p++); DECODE_TAIL; } @@ -1031,10 +1029,10 @@ nfsd4_decode_readdir(struct nfsd4_compoundargs *argp, struct nfsd4_readdir *read DECODE_HEAD; READ_BUF(24); - READ64(readdir->rd_cookie); + p = xdr_decode_hyper(p, &readdir->rd_cookie); COPYMEM(readdir->rd_verf.data, sizeof(readdir->rd_verf.data)); - READ32(readdir->rd_dircount); /* just in case you needed a useless field... */ - READ32(readdir->rd_maxcount); + readdir->rd_dircount = be32_to_cpup(p++); + readdir->rd_maxcount = be32_to_cpup(p++); if ((status = nfsd4_decode_bitmap(argp, readdir->rd_bmval))) goto out; @@ -1047,7 +1045,7 @@ nfsd4_decode_remove(struct nfsd4_compoundargs *argp, struct nfsd4_remove *remove DECODE_HEAD; READ_BUF(4); - READ32(remove->rm_namelen); + remove->rm_namelen = be32_to_cpup(p++); READ_BUF(remove->rm_namelen); SAVEMEM(remove->rm_name, remove->rm_namelen); if ((status = check_filename(remove->rm_name, remove->rm_namelen))) @@ -1062,10 +1060,10 @@ nfsd4_decode_rename(struct nfsd4_compoundargs *argp, struct nfsd4_rename *rename DECODE_HEAD; READ_BUF(4); - READ32(rename->rn_snamelen); + rename->rn_snamelen = be32_to_cpup(p++); READ_BUF(rename->rn_snamelen + 4); SAVEMEM(rename->rn_sname, rename->rn_snamelen); - READ32(rename->rn_tnamelen); + rename->rn_tnamelen = be32_to_cpup(p++); READ_BUF(rename->rn_tnamelen); SAVEMEM(rename->rn_tname, rename->rn_tnamelen); if ((status = check_filename(rename->rn_sname, rename->rn_snamelen))) @@ -1097,7 +1095,7 @@ nfsd4_decode_secinfo(struct nfsd4_compoundargs *argp, DECODE_HEAD; READ_BUF(4); - READ32(secinfo->si_namelen); + secinfo->si_namelen = be32_to_cpup(p++); READ_BUF(secinfo->si_namelen); SAVEMEM(secinfo->si_name, secinfo->si_namelen); status = check_filename(secinfo->si_name, secinfo->si_namelen); @@ -1113,7 +1111,7 @@ nfsd4_decode_secinfo_no_name(struct nfsd4_compoundargs *argp, DECODE_HEAD; READ_BUF(4); - READ32(sin->sin_style); + sin->sin_style = be32_to_cpup(p++); DECODE_TAIL; } @@ -1144,16 +1142,16 @@ nfsd4_decode_setclientid(struct nfsd4_compoundargs *argp, struct nfsd4_setclient if (status) return nfserr_bad_xdr; READ_BUF(8); - READ32(setclientid->se_callback_prog); - READ32(setclientid->se_callback_netid_len); + setclientid->se_callback_prog = be32_to_cpup(p++); + setclientid->se_callback_netid_len = be32_to_cpup(p++); READ_BUF(setclientid->se_callback_netid_len + 4); SAVEMEM(setclientid->se_callback_netid_val, setclientid->se_callback_netid_len); - READ32(setclientid->se_callback_addr_len); + setclientid->se_callback_addr_len = be32_to_cpup(p++); READ_BUF(setclientid->se_callback_addr_len + 4); SAVEMEM(setclientid->se_callback_addr_val, setclientid->se_callback_addr_len); - READ32(setclientid->se_callback_ident); + setclientid->se_callback_ident = be32_to_cpup(p++); DECODE_TAIL; } @@ -1186,7 +1184,7 @@ nfsd4_decode_verify(struct nfsd4_compoundargs *argp, struct nfsd4_verify *verify * nfsd4_proc_verify */ READ_BUF(4); - READ32(verify->ve_attrlen); + verify->ve_attrlen = be32_to_cpup(p++); READ_BUF(verify->ve_attrlen); SAVEMEM(verify->ve_attrval, verify->ve_attrlen); @@ -1204,11 +1202,11 @@ nfsd4_decode_write(struct nfsd4_compoundargs *argp, struct nfsd4_write *write) if (status) return status; READ_BUF(16); - READ64(write->wr_offset); - READ32(write->wr_stable_how); + p = xdr_decode_hyper(p, &write->wr_offset); + write->wr_stable_how = be32_to_cpup(p++); if (write->wr_stable_how > 2) goto xdr_error; - READ32(write->wr_buflen); + write->wr_buflen = be32_to_cpup(p++); /* Sorry .. no magic macros for this.. * * READ_BUF(write->wr_buflen); @@ -1254,7 +1252,7 @@ nfsd4_decode_release_lockowner(struct nfsd4_compoundargs *argp, struct nfsd4_rel READ_BUF(12); COPYMEM(&rlockowner->rl_clientid, sizeof(clientid_t)); - READ32(rlockowner->rl_owner.len); + rlockowner->rl_owner.len = be32_to_cpup(p++); READ_BUF(rlockowner->rl_owner.len); READMEM(rlockowner->rl_owner.data, rlockowner->rl_owner.len); @@ -1278,63 +1276,63 @@ nfsd4_decode_exchange_id(struct nfsd4_compoundargs *argp, return nfserr_bad_xdr; READ_BUF(4); - READ32(exid->flags); + exid->flags = be32_to_cpup(p++); /* Ignore state_protect4_a */ READ_BUF(4); - READ32(exid->spa_how); + exid->spa_how = be32_to_cpup(p++); switch (exid->spa_how) { case SP4_NONE: break; case SP4_MACH_CRED: /* spo_must_enforce */ READ_BUF(4); - READ32(dummy); + dummy = be32_to_cpup(p++); READ_BUF(dummy * 4); p += dummy; /* spo_must_allow */ READ_BUF(4); - READ32(dummy); + dummy = be32_to_cpup(p++); READ_BUF(dummy * 4); p += dummy; break; case SP4_SSV: /* ssp_ops */ READ_BUF(4); - READ32(dummy); + dummy = be32_to_cpup(p++); READ_BUF(dummy * 4); p += dummy; READ_BUF(4); - READ32(dummy); + dummy = be32_to_cpup(p++); READ_BUF(dummy * 4); p += dummy; /* ssp_hash_algs<> */ READ_BUF(4); - READ32(tmp); + tmp = be32_to_cpup(p++); while (tmp--) { READ_BUF(4); - READ32(dummy); + dummy = be32_to_cpup(p++); READ_BUF(dummy); p += XDR_QUADLEN(dummy); } /* ssp_encr_algs<> */ READ_BUF(4); - READ32(tmp); + tmp = be32_to_cpup(p++); while (tmp--) { READ_BUF(4); - READ32(dummy); + dummy = be32_to_cpup(p++); READ_BUF(dummy); p += XDR_QUADLEN(dummy); } /* ssp_window and ssp_num_gss_handles */ READ_BUF(8); - READ32(dummy); - READ32(dummy); + dummy = be32_to_cpup(p++); + dummy = be32_to_cpup(p++); break; default: goto xdr_error; @@ -1342,7 +1340,7 @@ nfsd4_decode_exchange_id(struct nfsd4_compoundargs *argp, /* Ignore Implementation ID */ READ_BUF(4); /* nfs_impl_id4 array length */ - READ32(dummy); + dummy = be32_to_cpup(p++); if (dummy > 1) goto xdr_error; @@ -1350,13 +1348,13 @@ nfsd4_decode_exchange_id(struct nfsd4_compoundargs *argp, if (dummy == 1) { /* nii_domain */ READ_BUF(4); - READ32(dummy); + dummy = be32_to_cpup(p++); READ_BUF(dummy); p += XDR_QUADLEN(dummy); /* nii_name */ READ_BUF(4); - READ32(dummy); + dummy = be32_to_cpup(p++); READ_BUF(dummy); p += XDR_QUADLEN(dummy); @@ -1376,21 +1374,21 @@ nfsd4_decode_create_session(struct nfsd4_compoundargs *argp, READ_BUF(16); COPYMEM(&sess->clientid, 8); - READ32(sess->seqid); - READ32(sess->flags); + sess->seqid = be32_to_cpup(p++); + sess->flags = be32_to_cpup(p++); /* Fore channel attrs */ READ_BUF(28); - READ32(dummy); /* headerpadsz is always 0 */ - READ32(sess->fore_channel.maxreq_sz); - READ32(sess->fore_channel.maxresp_sz); - READ32(sess->fore_channel.maxresp_cached); - READ32(sess->fore_channel.maxops); - READ32(sess->fore_channel.maxreqs); - READ32(sess->fore_channel.nr_rdma_attrs); + dummy = be32_to_cpup(p++); /* headerpadsz is always 0 */ + sess->fore_channel.maxreq_sz = be32_to_cpup(p++); + sess->fore_channel.maxresp_sz = be32_to_cpup(p++); + sess->fore_channel.maxresp_cached = be32_to_cpup(p++); + sess->fore_channel.maxops = be32_to_cpup(p++); + sess->fore_channel.maxreqs = be32_to_cpup(p++); + sess->fore_channel.nr_rdma_attrs = be32_to_cpup(p++); if (sess->fore_channel.nr_rdma_attrs == 1) { READ_BUF(4); - READ32(sess->fore_channel.rdma_attrs); + sess->fore_channel.rdma_attrs = be32_to_cpup(p++); } else if (sess->fore_channel.nr_rdma_attrs > 1) { dprintk("Too many fore channel attr bitmaps!\n"); goto xdr_error; @@ -1398,23 +1396,23 @@ nfsd4_decode_create_session(struct nfsd4_compoundargs *argp, /* Back channel attrs */ READ_BUF(28); - READ32(dummy); /* headerpadsz is always 0 */ - READ32(sess->back_channel.maxreq_sz); - READ32(sess->back_channel.maxresp_sz); - READ32(sess->back_channel.maxresp_cached); - READ32(sess->back_channel.maxops); - READ32(sess->back_channel.maxreqs); - READ32(sess->back_channel.nr_rdma_attrs); + dummy = be32_to_cpup(p++); /* headerpadsz is always 0 */ + sess->back_channel.maxreq_sz = be32_to_cpup(p++); + sess->back_channel.maxresp_sz = be32_to_cpup(p++); + sess->back_channel.maxresp_cached = be32_to_cpup(p++); + sess->back_channel.maxops = be32_to_cpup(p++); + sess->back_channel.maxreqs = be32_to_cpup(p++); + sess->back_channel.nr_rdma_attrs = be32_to_cpup(p++); if (sess->back_channel.nr_rdma_attrs == 1) { READ_BUF(4); - READ32(sess->back_channel.rdma_attrs); + sess->back_channel.rdma_attrs = be32_to_cpup(p++); } else if (sess->back_channel.nr_rdma_attrs > 1) { dprintk("Too many back channel attr bitmaps!\n"); goto xdr_error; } READ_BUF(4); - READ32(sess->callback_prog); + sess->callback_prog = be32_to_cpup(p++); nfsd4_decode_cb_sec(argp, &sess->cb_sec); DECODE_TAIL; } @@ -1437,7 +1435,7 @@ nfsd4_decode_free_stateid(struct nfsd4_compoundargs *argp, DECODE_HEAD; READ_BUF(sizeof(stateid_t)); - READ32(free_stateid->fr_stateid.si_generation); + free_stateid->fr_stateid.si_generation = be32_to_cpup(p++); COPYMEM(&free_stateid->fr_stateid.si_opaque, sizeof(stateid_opaque_t)); DECODE_TAIL; @@ -1451,10 +1449,10 @@ nfsd4_decode_sequence(struct nfsd4_compoundargs *argp, READ_BUF(NFS4_MAX_SESSIONID_LEN + 16); COPYMEM(seq->sessionid.data, NFS4_MAX_SESSIONID_LEN); - READ32(seq->seqid); - READ32(seq->slotid); - READ32(seq->maxslots); - READ32(seq->cachethis); + seq->seqid = be32_to_cpup(p++); + seq->slotid = be32_to_cpup(p++); + seq->maxslots = be32_to_cpup(p++); + seq->cachethis = be32_to_cpup(p++); DECODE_TAIL; } @@ -1511,7 +1509,7 @@ static __be32 nfsd4_decode_reclaim_complete(struct nfsd4_compoundargs *argp, str DECODE_HEAD; READ_BUF(4); - READ32(rc->rca_one_fs); + rc->rca_one_fs = be32_to_cpup(p++); DECODE_TAIL; } @@ -1605,47 +1603,25 @@ nfsd4_opnum_in_range(struct nfsd4_compoundargs *argp, struct nfsd4_op *op) return true; } -/* - * Return a rough estimate of the maximum possible reply size. Note the - * estimate includes rpc headers so is meant to be passed to - * svc_reserve, not svc_reserve_auth. - * - * Also note the current compound encoding permits only one operation to - * use pages beyond the first one, so the maximum possible length is the - * maximum over these values, not the sum. - */ -static int nfsd4_max_reply(u32 opnum) -{ - switch (opnum) { - case OP_READLINK: - case OP_READDIR: - /* - * Both of these ops take a single page for data and put - * the head and tail in another page: - */ - return 2 * PAGE_SIZE; - case OP_READ: - return INT_MAX; - default: - return PAGE_SIZE; - } -} - static __be32 nfsd4_decode_compound(struct nfsd4_compoundargs *argp) { DECODE_HEAD; struct nfsd4_op *op; bool cachethis = false; - int max_reply = PAGE_SIZE; + int auth_slack= argp->rqstp->rq_auth_slack; + int max_reply = auth_slack + 8; /* opcnt, status */ + int readcount = 0; + int readbytes = 0; int i; READ_BUF(4); - READ32(argp->taglen); + argp->taglen = be32_to_cpup(p++); READ_BUF(argp->taglen + 8); SAVEMEM(argp->tag, argp->taglen); - READ32(argp->minorversion); - READ32(argp->opcnt); + argp->minorversion = be32_to_cpup(p++); + argp->opcnt = be32_to_cpup(p++); + max_reply += 4 + (XDR_QUADLEN(argp->taglen) << 2); if (argp->taglen > NFSD4_MAX_TAGLEN) goto xdr_error; @@ -1669,7 +1645,7 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) op->replay = NULL; READ_BUF(4); - READ32(op->opnum); + op->opnum = be32_to_cpup(p++); if (nfsd4_opnum_in_range(argp, op)) op->status = nfsd4_dec_ops[op->opnum](argp, &op->u); @@ -1677,97 +1653,82 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) op->opnum = OP_ILLEGAL; op->status = nfserr_op_illegal; } - - if (op->status) { - argp->opcnt = i+1; - break; - } /* * We'll try to cache the result in the DRC if any one * op in the compound wants to be cached: */ cachethis |= nfsd4_cache_this_op(op); - max_reply = max(max_reply, nfsd4_max_reply(op->opnum)); + if (op->opnum == OP_READ) { + readcount++; + readbytes += nfsd4_max_reply(argp->rqstp, op); + } else + max_reply += nfsd4_max_reply(argp->rqstp, op); + + if (op->status) { + argp->opcnt = i+1; + break; + } } /* Sessions make the DRC unnecessary: */ if (argp->minorversion) cachethis = false; - if (max_reply != INT_MAX) - svc_reserve(argp->rqstp, max_reply); + svc_reserve(argp->rqstp, max_reply + readbytes); argp->rqstp->rq_cachetype = cachethis ? RC_REPLBUFF : RC_NOCACHE; - DECODE_TAIL; -} - -#define WRITE32(n) *p++ = htonl(n) -#define WRITE64(n) do { \ - *p++ = htonl((u32)((n) >> 32)); \ - *p++ = htonl((u32)(n)); \ -} while (0) -#define WRITEMEM(ptr,nbytes) do { if (nbytes > 0) { \ - *(p + XDR_QUADLEN(nbytes) -1) = 0; \ - memcpy(p, ptr, nbytes); \ - p += XDR_QUADLEN(nbytes); \ -}} while (0) - -static void write32(__be32 **p, u32 n) -{ - *(*p)++ = htonl(n); -} + if (readcount > 1 || max_reply > PAGE_SIZE - auth_slack) + argp->rqstp->rq_splice_ok = false; -static void write64(__be32 **p, u64 n) -{ - write32(p, (n >> 32)); - write32(p, (u32)n); + DECODE_TAIL; } -static void write_change(__be32 **p, struct kstat *stat, struct inode *inode) +static __be32 *encode_change(__be32 *p, struct kstat *stat, struct inode *inode) { if (IS_I_VERSION(inode)) { - write64(p, inode->i_version); + p = xdr_encode_hyper(p, inode->i_version); } else { - write32(p, stat->ctime.tv_sec); - write32(p, stat->ctime.tv_nsec); + *p++ = cpu_to_be32(stat->ctime.tv_sec); + *p++ = cpu_to_be32(stat->ctime.tv_nsec); } + return p; } -static void write_cinfo(__be32 **p, struct nfsd4_change_info *c) +static __be32 *encode_cinfo(__be32 *p, struct nfsd4_change_info *c) { - write32(p, c->atomic); + *p++ = cpu_to_be32(c->atomic); if (c->change_supported) { - write64(p, c->before_change); - write64(p, c->after_change); + p = xdr_encode_hyper(p, c->before_change); + p = xdr_encode_hyper(p, c->after_change); } else { - write32(p, c->before_ctime_sec); - write32(p, c->before_ctime_nsec); - write32(p, c->after_ctime_sec); - write32(p, c->after_ctime_nsec); + *p++ = cpu_to_be32(c->before_ctime_sec); + *p++ = cpu_to_be32(c->before_ctime_nsec); + *p++ = cpu_to_be32(c->after_ctime_sec); + *p++ = cpu_to_be32(c->after_ctime_nsec); } + return p; } -#define RESERVE_SPACE(nbytes) do { \ - p = resp->p; \ - BUG_ON(p + XDR_QUADLEN(nbytes) > resp->end); \ -} while (0) -#define ADJUST_ARGS() resp->p = p - /* Encode as an array of strings the string given with components * separated @sep, escaped with esc_enter and esc_exit. */ -static __be32 nfsd4_encode_components_esc(char sep, char *components, - __be32 **pp, int *buflen, - char esc_enter, char esc_exit) +static __be32 nfsd4_encode_components_esc(struct xdr_stream *xdr, char sep, + char *components, char esc_enter, + char esc_exit) { - __be32 *p = *pp; - __be32 *countp = p; + __be32 *p; + __be32 pathlen; + int pathlen_offset; int strlen, count=0; char *str, *end, *next; dprintk("nfsd4_encode_components(%s)\n", components); - if ((*buflen -= 4) < 0) + + pathlen_offset = xdr->buf->len; + p = xdr_reserve_space(xdr, 4); + if (!p) return nfserr_resource; - WRITE32(0); /* We will fill this in with @count later */ + p++; /* We will fill this in with @count later */ + end = str = components; while (*end) { bool found_esc = false; @@ -1789,59 +1750,57 @@ static __be32 nfsd4_encode_components_esc(char sep, char *components, strlen = end - str; if (strlen) { - if ((*buflen -= ((XDR_QUADLEN(strlen) << 2) + 4)) < 0) + p = xdr_reserve_space(xdr, strlen + 4); + if (!p) return nfserr_resource; - WRITE32(strlen); - WRITEMEM(str, strlen); + p = xdr_encode_opaque(p, str, strlen); count++; } else end++; str = end; } - *pp = p; - p = countp; - WRITE32(count); + pathlen = htonl(xdr->buf->len - pathlen_offset); + write_bytes_to_xdr_buf(xdr->buf, pathlen_offset, &pathlen, 4); return 0; } /* Encode as an array of strings the string given with components * separated @sep. */ -static __be32 nfsd4_encode_components(char sep, char *components, - __be32 **pp, int *buflen) +static __be32 nfsd4_encode_components(struct xdr_stream *xdr, char sep, + char *components) { - return nfsd4_encode_components_esc(sep, components, pp, buflen, 0, 0); + return nfsd4_encode_components_esc(xdr, sep, components, 0, 0); } /* * encode a location element of a fs_locations structure */ -static __be32 nfsd4_encode_fs_location4(struct nfsd4_fs_location *location, - __be32 **pp, int *buflen) +static __be32 nfsd4_encode_fs_location4(struct xdr_stream *xdr, + struct nfsd4_fs_location *location) { __be32 status; - __be32 *p = *pp; - status = nfsd4_encode_components_esc(':', location->hosts, &p, buflen, + status = nfsd4_encode_components_esc(xdr, ':', location->hosts, '[', ']'); if (status) return status; - status = nfsd4_encode_components('/', location->path, &p, buflen); + status = nfsd4_encode_components(xdr, '/', location->path); if (status) return status; - *pp = p; return 0; } /* * Encode a path in RFC3530 'pathname4' format */ -static __be32 nfsd4_encode_path(const struct path *root, - const struct path *path, __be32 **pp, int *buflen) +static __be32 nfsd4_encode_path(struct xdr_stream *xdr, + const struct path *root, + const struct path *path) { struct path cur = *path; - __be32 *p = *pp; + __be32 *p; struct dentry **components = NULL; unsigned int ncomponents = 0; __be32 err = nfserr_jukebox; @@ -1872,11 +1831,11 @@ static __be32 nfsd4_encode_path(const struct path *root, components[ncomponents++] = cur.dentry; cur.dentry = dget_parent(cur.dentry); } - - *buflen -= 4; - if (*buflen < 0) + err = nfserr_resource; + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_free; - WRITE32(ncomponents); + *p++ = cpu_to_be32(ncomponents); while (ncomponents) { struct dentry *dentry = components[ncomponents - 1]; @@ -1884,20 +1843,18 @@ static __be32 nfsd4_encode_path(const struct path *root, spin_lock(&dentry->d_lock); len = dentry->d_name.len; - *buflen -= 4 + (XDR_QUADLEN(len) << 2); - if (*buflen < 0) { + p = xdr_reserve_space(xdr, len + 4); + if (!p) { spin_unlock(&dentry->d_lock); goto out_free; } - WRITE32(len); - WRITEMEM(dentry->d_name.name, len); + p = xdr_encode_opaque(p, dentry->d_name.name, len); dprintk("/%s", dentry->d_name.name); spin_unlock(&dentry->d_lock); dput(dentry); ncomponents--; } - *pp = p; err = 0; out_free: dprintk(")\n"); @@ -1908,8 +1865,8 @@ out_free: return err; } -static __be32 nfsd4_encode_fsloc_fsroot(struct svc_rqst *rqstp, - const struct path *path, __be32 **pp, int *buflen) +static __be32 nfsd4_encode_fsloc_fsroot(struct xdr_stream *xdr, + struct svc_rqst *rqstp, const struct path *path) { struct svc_export *exp_ps; __be32 res; @@ -1917,7 +1874,7 @@ static __be32 nfsd4_encode_fsloc_fsroot(struct svc_rqst *rqstp, exp_ps = rqst_find_fsidzero_export(rqstp); if (IS_ERR(exp_ps)) return nfserrno(PTR_ERR(exp_ps)); - res = nfsd4_encode_path(&exp_ps->ex_path, path, pp, buflen); + res = nfsd4_encode_path(xdr, &exp_ps->ex_path, path); exp_put(exp_ps); return res; } @@ -1925,28 +1882,26 @@ static __be32 nfsd4_encode_fsloc_fsroot(struct svc_rqst *rqstp, /* * encode a fs_locations structure */ -static __be32 nfsd4_encode_fs_locations(struct svc_rqst *rqstp, - struct svc_export *exp, - __be32 **pp, int *buflen) +static __be32 nfsd4_encode_fs_locations(struct xdr_stream *xdr, + struct svc_rqst *rqstp, struct svc_export *exp) { __be32 status; int i; - __be32 *p = *pp; + __be32 *p; struct nfsd4_fs_locations *fslocs = &exp->ex_fslocs; - status = nfsd4_encode_fsloc_fsroot(rqstp, &exp->ex_path, &p, buflen); + status = nfsd4_encode_fsloc_fsroot(xdr, rqstp, &exp->ex_path); if (status) return status; - if ((*buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) return nfserr_resource; - WRITE32(fslocs->locations_count); + *p++ = cpu_to_be32(fslocs->locations_count); for (i=0; i<fslocs->locations_count; i++) { - status = nfsd4_encode_fs_location4(&fslocs->locations[i], - &p, buflen); + status = nfsd4_encode_fs_location4(xdr, &fslocs->locations[i]); if (status) return status; } - *pp = p; return 0; } @@ -1965,15 +1920,15 @@ static u32 nfs4_file_type(umode_t mode) } static inline __be32 -nfsd4_encode_aclname(struct svc_rqst *rqstp, struct nfs4_ace *ace, - __be32 **p, int *buflen) +nfsd4_encode_aclname(struct xdr_stream *xdr, struct svc_rqst *rqstp, + struct nfs4_ace *ace) { if (ace->whotype != NFS4_ACL_WHO_NAMED) - return nfs4_acl_write_who(ace->whotype, p, buflen); + return nfs4_acl_write_who(xdr, ace->whotype); else if (ace->flag & NFS4_ACE_IDENTIFIER_GROUP) - return nfsd4_encode_group(rqstp, ace->who_gid, p, buflen); + return nfsd4_encode_group(xdr, rqstp, ace->who_gid); else - return nfsd4_encode_user(rqstp, ace->who_uid, p, buflen); + return nfsd4_encode_user(xdr, rqstp, ace->who_uid); } #define WORD0_ABSENT_FS_ATTRS (FATTR4_WORD0_FS_LOCATIONS | FATTR4_WORD0_FSID | \ @@ -1982,31 +1937,28 @@ nfsd4_encode_aclname(struct svc_rqst *rqstp, struct nfs4_ace *ace, #ifdef CONFIG_NFSD_V4_SECURITY_LABEL static inline __be32 -nfsd4_encode_security_label(struct svc_rqst *rqstp, void *context, int len, __be32 **pp, int *buflen) +nfsd4_encode_security_label(struct xdr_stream *xdr, struct svc_rqst *rqstp, + void *context, int len) { - __be32 *p = *pp; + __be32 *p; - if (*buflen < ((XDR_QUADLEN(len) << 2) + 4 + 4 + 4)) + p = xdr_reserve_space(xdr, len + 4 + 4 + 4); + if (!p) return nfserr_resource; /* * For now we use a 0 here to indicate the null translation; in * the future we may place a call to translation code here. */ - if ((*buflen -= 8) < 0) - return nfserr_resource; - - WRITE32(0); /* lfs */ - WRITE32(0); /* pi */ + *p++ = cpu_to_be32(0); /* lfs */ + *p++ = cpu_to_be32(0); /* pi */ p = xdr_encode_opaque(p, context, len); - *buflen -= (XDR_QUADLEN(len) << 2) + 4; - - *pp = p; return 0; } #else static inline __be32 -nfsd4_encode_security_label(struct svc_rqst *rqstp, void *context, int len, __be32 **pp, int *buflen) +nfsd4_encode_security_label(struct xdr_stream *xdr, struct svc_rqst *rqstp, + void *context, int len) { return 0; } #endif @@ -2045,12 +1997,11 @@ static int get_parent_attributes(struct svc_export *exp, struct kstat *stat) /* * Note: @fhp can be NULL; in this case, we might have to compose the filehandle * ourselves. - * - * countp is the buffer size in _words_ */ -__be32 -nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp, - struct dentry *dentry, __be32 **buffer, int count, u32 *bmval, +static __be32 +nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp, + struct svc_export *exp, + struct dentry *dentry, u32 *bmval, struct svc_rqst *rqstp, int ignore_crossmnt) { u32 bmval0 = bmval[0]; @@ -2059,12 +2010,13 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp, struct kstat stat; struct svc_fh *tempfh = NULL; struct kstatfs statfs; - int buflen = count << 2; - __be32 *attrlenp; + __be32 *p; + int starting_len = xdr->buf->len; + int attrlen_offset; + __be32 attrlen; u32 dummy; u64 dummy64; u32 rdattr_err = 0; - __be32 *p = *buffer; __be32 status; int err; int aclsupport = 0; @@ -2095,8 +2047,8 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp, err = vfs_getattr(&path, &stat); if (err) goto out_nfserr; - if ((bmval0 & (FATTR4_WORD0_FILES_FREE | FATTR4_WORD0_FILES_TOTAL | - FATTR4_WORD0_MAXNAME)) || + 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 | FATTR4_WORD1_SPACE_TOTAL))) { err = vfs_statfs(&path, &statfs); @@ -2145,25 +2097,33 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp, #endif /* CONFIG_NFSD_V4_SECURITY_LABEL */ if (bmval2) { - if ((buflen -= 16) < 0) + p = xdr_reserve_space(xdr, 16); + if (!p) goto out_resource; - WRITE32(3); - WRITE32(bmval0); - WRITE32(bmval1); - WRITE32(bmval2); + *p++ = cpu_to_be32(3); + *p++ = cpu_to_be32(bmval0); + *p++ = cpu_to_be32(bmval1); + *p++ = cpu_to_be32(bmval2); } else if (bmval1) { - if ((buflen -= 12) < 0) + p = xdr_reserve_space(xdr, 12); + if (!p) goto out_resource; - WRITE32(2); - WRITE32(bmval0); - WRITE32(bmval1); + *p++ = cpu_to_be32(2); + *p++ = cpu_to_be32(bmval0); + *p++ = cpu_to_be32(bmval1); } else { - if ((buflen -= 8) < 0) + p = xdr_reserve_space(xdr, 8); + if (!p) goto out_resource; - WRITE32(1); - WRITE32(bmval0); + *p++ = cpu_to_be32(1); + *p++ = cpu_to_be32(bmval0); } - attrlenp = p++; /* to be backfilled later */ + + attrlen_offset = xdr->buf->len; + p = xdr_reserve_space(xdr, 4); + if (!p) + goto out_resource; + p++; /* to be backfilled later */ if (bmval0 & FATTR4_WORD0_SUPPORTED_ATTRS) { u32 word0 = nfsd_suppattrs0(minorversion); @@ -2175,296 +2135,343 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp, if (!contextsupport) word2 &= ~FATTR4_WORD2_SECURITY_LABEL; if (!word2) { - if ((buflen -= 12) < 0) + p = xdr_reserve_space(xdr, 12); + if (!p) goto out_resource; - WRITE32(2); - WRITE32(word0); - WRITE32(word1); + *p++ = cpu_to_be32(2); + *p++ = cpu_to_be32(word0); + *p++ = cpu_to_be32(word1); } else { - if ((buflen -= 16) < 0) + p = xdr_reserve_space(xdr, 16); + if (!p) goto out_resource; - WRITE32(3); - WRITE32(word0); - WRITE32(word1); - WRITE32(word2); + *p++ = cpu_to_be32(3); + *p++ = cpu_to_be32(word0); + *p++ = cpu_to_be32(word1); + *p++ = cpu_to_be32(word2); } } if (bmval0 & FATTR4_WORD0_TYPE) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; dummy = nfs4_file_type(stat.mode); if (dummy == NF4BAD) { status = nfserr_serverfault; goto out; } - WRITE32(dummy); + *p++ = cpu_to_be32(dummy); } if (bmval0 & FATTR4_WORD0_FH_EXPIRE_TYPE) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; if (exp->ex_flags & NFSEXP_NOSUBTREECHECK) - WRITE32(NFS4_FH_PERSISTENT); + *p++ = cpu_to_be32(NFS4_FH_PERSISTENT); else - WRITE32(NFS4_FH_PERSISTENT|NFS4_FH_VOL_RENAME); + *p++ = cpu_to_be32(NFS4_FH_PERSISTENT| + NFS4_FH_VOL_RENAME); } if (bmval0 & FATTR4_WORD0_CHANGE) { - if ((buflen -= 8) < 0) + p = xdr_reserve_space(xdr, 8); + if (!p) goto out_resource; - write_change(&p, &stat, dentry->d_inode); + p = encode_change(p, &stat, dentry->d_inode); } if (bmval0 & FATTR4_WORD0_SIZE) { - if ((buflen -= 8) < 0) + p = xdr_reserve_space(xdr, 8); + if (!p) goto out_resource; - WRITE64(stat.size); + p = xdr_encode_hyper(p, stat.size); } if (bmval0 & FATTR4_WORD0_LINK_SUPPORT) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; - WRITE32(1); + *p++ = cpu_to_be32(1); } if (bmval0 & FATTR4_WORD0_SYMLINK_SUPPORT) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; - WRITE32(1); + *p++ = cpu_to_be32(1); } if (bmval0 & FATTR4_WORD0_NAMED_ATTR) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; - WRITE32(0); + *p++ = cpu_to_be32(0); } if (bmval0 & FATTR4_WORD0_FSID) { - if ((buflen -= 16) < 0) + p = xdr_reserve_space(xdr, 16); + if (!p) goto out_resource; if (exp->ex_fslocs.migrated) { - WRITE64(NFS4_REFERRAL_FSID_MAJOR); - WRITE64(NFS4_REFERRAL_FSID_MINOR); + p = xdr_encode_hyper(p, NFS4_REFERRAL_FSID_MAJOR); + p = xdr_encode_hyper(p, NFS4_REFERRAL_FSID_MINOR); } else switch(fsid_source(fhp)) { case FSIDSOURCE_FSID: - WRITE64((u64)exp->ex_fsid); - WRITE64((u64)0); + p = xdr_encode_hyper(p, (u64)exp->ex_fsid); + p = xdr_encode_hyper(p, (u64)0); break; case FSIDSOURCE_DEV: - WRITE32(0); - WRITE32(MAJOR(stat.dev)); - WRITE32(0); - WRITE32(MINOR(stat.dev)); + *p++ = cpu_to_be32(0); + *p++ = cpu_to_be32(MAJOR(stat.dev)); + *p++ = cpu_to_be32(0); + *p++ = cpu_to_be32(MINOR(stat.dev)); break; case FSIDSOURCE_UUID: - WRITEMEM(exp->ex_uuid, 16); + p = xdr_encode_opaque_fixed(p, exp->ex_uuid, + EX_UUID_LEN); break; } } if (bmval0 & FATTR4_WORD0_UNIQUE_HANDLES) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; - WRITE32(0); + *p++ = cpu_to_be32(0); } if (bmval0 & FATTR4_WORD0_LEASE_TIME) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; - WRITE32(nn->nfsd4_lease); + *p++ = cpu_to_be32(nn->nfsd4_lease); } if (bmval0 & FATTR4_WORD0_RDATTR_ERROR) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; - WRITE32(rdattr_err); + *p++ = cpu_to_be32(rdattr_err); } if (bmval0 & FATTR4_WORD0_ACL) { struct nfs4_ace *ace; if (acl == NULL) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; - WRITE32(0); + *p++ = cpu_to_be32(0); goto out_acl; } - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; - WRITE32(acl->naces); + *p++ = cpu_to_be32(acl->naces); for (ace = acl->aces; ace < acl->aces + acl->naces; ace++) { - if ((buflen -= 4*3) < 0) + p = xdr_reserve_space(xdr, 4*3); + if (!p) goto out_resource; - WRITE32(ace->type); - WRITE32(ace->flag); - WRITE32(ace->access_mask & NFS4_ACE_MASK_ALL); - status = nfsd4_encode_aclname(rqstp, ace, &p, &buflen); + *p++ = cpu_to_be32(ace->type); + *p++ = cpu_to_be32(ace->flag); + *p++ = cpu_to_be32(ace->access_mask & + NFS4_ACE_MASK_ALL); + status = nfsd4_encode_aclname(xdr, rqstp, ace); if (status) goto out; } } out_acl: if (bmval0 & FATTR4_WORD0_ACLSUPPORT) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; - WRITE32(aclsupport ? + *p++ = cpu_to_be32(aclsupport ? ACL4_SUPPORT_ALLOW_ACL|ACL4_SUPPORT_DENY_ACL : 0); } if (bmval0 & FATTR4_WORD0_CANSETTIME) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; - WRITE32(1); + *p++ = cpu_to_be32(1); } if (bmval0 & FATTR4_WORD0_CASE_INSENSITIVE) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; - WRITE32(0); + *p++ = cpu_to_be32(0); } if (bmval0 & FATTR4_WORD0_CASE_PRESERVING) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; - WRITE32(1); + *p++ = cpu_to_be32(1); } if (bmval0 & FATTR4_WORD0_CHOWN_RESTRICTED) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; - WRITE32(1); + *p++ = cpu_to_be32(1); } if (bmval0 & FATTR4_WORD0_FILEHANDLE) { - buflen -= (XDR_QUADLEN(fhp->fh_handle.fh_size) << 2) + 4; - if (buflen < 0) + p = xdr_reserve_space(xdr, fhp->fh_handle.fh_size + 4); + if (!p) goto out_resource; - WRITE32(fhp->fh_handle.fh_size); - WRITEMEM(&fhp->fh_handle.fh_base, fhp->fh_handle.fh_size); + p = xdr_encode_opaque(p, &fhp->fh_handle.fh_base, + fhp->fh_handle.fh_size); } if (bmval0 & FATTR4_WORD0_FILEID) { - if ((buflen -= 8) < 0) + p = xdr_reserve_space(xdr, 8); + if (!p) goto out_resource; - WRITE64(stat.ino); + p = xdr_encode_hyper(p, stat.ino); } if (bmval0 & FATTR4_WORD0_FILES_AVAIL) { - if ((buflen -= 8) < 0) + p = xdr_reserve_space(xdr, 8); + if (!p) goto out_resource; - WRITE64((u64) statfs.f_ffree); + p = xdr_encode_hyper(p, (u64) statfs.f_ffree); } if (bmval0 & FATTR4_WORD0_FILES_FREE) { - if ((buflen -= 8) < 0) + p = xdr_reserve_space(xdr, 8); + if (!p) goto out_resource; - WRITE64((u64) statfs.f_ffree); + p = xdr_encode_hyper(p, (u64) statfs.f_ffree); } if (bmval0 & FATTR4_WORD0_FILES_TOTAL) { - if ((buflen -= 8) < 0) + p = xdr_reserve_space(xdr, 8); + if (!p) goto out_resource; - WRITE64((u64) statfs.f_files); + p = xdr_encode_hyper(p, (u64) statfs.f_files); } if (bmval0 & FATTR4_WORD0_FS_LOCATIONS) { - status = nfsd4_encode_fs_locations(rqstp, exp, &p, &buflen); + status = nfsd4_encode_fs_locations(xdr, rqstp, exp); if (status) goto out; } if (bmval0 & FATTR4_WORD0_HOMOGENEOUS) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; - WRITE32(1); + *p++ = cpu_to_be32(1); } if (bmval0 & FATTR4_WORD0_MAXFILESIZE) { - if ((buflen -= 8) < 0) + p = xdr_reserve_space(xdr, 8); + if (!p) goto out_resource; - WRITE64(exp->ex_path.mnt->mnt_sb->s_maxbytes); + p = xdr_encode_hyper(p, exp->ex_path.mnt->mnt_sb->s_maxbytes); } if (bmval0 & FATTR4_WORD0_MAXLINK) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; - WRITE32(255); + *p++ = cpu_to_be32(255); } if (bmval0 & FATTR4_WORD0_MAXNAME) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; - WRITE32(statfs.f_namelen); + *p++ = cpu_to_be32(statfs.f_namelen); } if (bmval0 & FATTR4_WORD0_MAXREAD) { - if ((buflen -= 8) < 0) + p = xdr_reserve_space(xdr, 8); + if (!p) goto out_resource; - WRITE64((u64) svc_max_payload(rqstp)); + p = xdr_encode_hyper(p, (u64) svc_max_payload(rqstp)); } if (bmval0 & FATTR4_WORD0_MAXWRITE) { - if ((buflen -= 8) < 0) + p = xdr_reserve_space(xdr, 8); + if (!p) goto out_resource; - WRITE64((u64) svc_max_payload(rqstp)); + p = xdr_encode_hyper(p, (u64) svc_max_payload(rqstp)); } if (bmval1 & FATTR4_WORD1_MODE) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; - WRITE32(stat.mode & S_IALLUGO); + *p++ = cpu_to_be32(stat.mode & S_IALLUGO); } if (bmval1 & FATTR4_WORD1_NO_TRUNC) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; - WRITE32(1); + *p++ = cpu_to_be32(1); } if (bmval1 & FATTR4_WORD1_NUMLINKS) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; - WRITE32(stat.nlink); + *p++ = cpu_to_be32(stat.nlink); } if (bmval1 & FATTR4_WORD1_OWNER) { - status = nfsd4_encode_user(rqstp, stat.uid, &p, &buflen); + status = nfsd4_encode_user(xdr, rqstp, stat.uid); if (status) goto out; } if (bmval1 & FATTR4_WORD1_OWNER_GROUP) { - status = nfsd4_encode_group(rqstp, stat.gid, &p, &buflen); + status = nfsd4_encode_group(xdr, rqstp, stat.gid); if (status) goto out; } if (bmval1 & FATTR4_WORD1_RAWDEV) { - if ((buflen -= 8) < 0) + p = xdr_reserve_space(xdr, 8); + if (!p) goto out_resource; - WRITE32((u32) MAJOR(stat.rdev)); - WRITE32((u32) MINOR(stat.rdev)); + *p++ = cpu_to_be32((u32) MAJOR(stat.rdev)); + *p++ = cpu_to_be32((u32) MINOR(stat.rdev)); } if (bmval1 & FATTR4_WORD1_SPACE_AVAIL) { - if ((buflen -= 8) < 0) + p = xdr_reserve_space(xdr, 8); + if (!p) goto out_resource; dummy64 = (u64)statfs.f_bavail * (u64)statfs.f_bsize; - WRITE64(dummy64); + p = xdr_encode_hyper(p, dummy64); } if (bmval1 & FATTR4_WORD1_SPACE_FREE) { - if ((buflen -= 8) < 0) + p = xdr_reserve_space(xdr, 8); + if (!p) goto out_resource; dummy64 = (u64)statfs.f_bfree * (u64)statfs.f_bsize; - WRITE64(dummy64); + p = xdr_encode_hyper(p, dummy64); } if (bmval1 & FATTR4_WORD1_SPACE_TOTAL) { - if ((buflen -= 8) < 0) + p = xdr_reserve_space(xdr, 8); + if (!p) goto out_resource; dummy64 = (u64)statfs.f_blocks * (u64)statfs.f_bsize; - WRITE64(dummy64); + p = xdr_encode_hyper(p, dummy64); } if (bmval1 & FATTR4_WORD1_SPACE_USED) { - if ((buflen -= 8) < 0) + p = xdr_reserve_space(xdr, 8); + if (!p) goto out_resource; dummy64 = (u64)stat.blocks << 9; - WRITE64(dummy64); + p = xdr_encode_hyper(p, dummy64); } if (bmval1 & FATTR4_WORD1_TIME_ACCESS) { - if ((buflen -= 12) < 0) + p = xdr_reserve_space(xdr, 12); + if (!p) goto out_resource; - WRITE64((s64)stat.atime.tv_sec); - WRITE32(stat.atime.tv_nsec); + p = xdr_encode_hyper(p, (s64)stat.atime.tv_sec); + *p++ = cpu_to_be32(stat.atime.tv_nsec); } if (bmval1 & FATTR4_WORD1_TIME_DELTA) { - if ((buflen -= 12) < 0) + p = xdr_reserve_space(xdr, 12); + if (!p) goto out_resource; - WRITE32(0); - WRITE32(1); - WRITE32(0); + *p++ = cpu_to_be32(0); + *p++ = cpu_to_be32(1); + *p++ = cpu_to_be32(0); } if (bmval1 & FATTR4_WORD1_TIME_METADATA) { - if ((buflen -= 12) < 0) + p = xdr_reserve_space(xdr, 12); + if (!p) goto out_resource; - WRITE64((s64)stat.ctime.tv_sec); - WRITE32(stat.ctime.tv_nsec); + p = xdr_encode_hyper(p, (s64)stat.ctime.tv_sec); + *p++ = cpu_to_be32(stat.ctime.tv_nsec); } if (bmval1 & FATTR4_WORD1_TIME_MODIFY) { - if ((buflen -= 12) < 0) + p = xdr_reserve_space(xdr, 12); + if (!p) goto out_resource; - WRITE64((s64)stat.mtime.tv_sec); - WRITE32(stat.mtime.tv_nsec); + p = xdr_encode_hyper(p, (s64)stat.mtime.tv_sec); + *p++ = cpu_to_be32(stat.mtime.tv_nsec); } if (bmval1 & FATTR4_WORD1_MOUNTED_ON_FILEID) { - if ((buflen -= 8) < 0) + p = xdr_reserve_space(xdr, 8); + if (!p) goto out_resource; /* * Get parent's attributes if not ignoring crossmount @@ -2473,25 +2480,26 @@ out_acl: if (ignore_crossmnt == 0 && dentry == exp->ex_path.mnt->mnt_root) get_parent_attributes(exp, &stat); - WRITE64(stat.ino); + p = xdr_encode_hyper(p, stat.ino); } if (bmval2 & FATTR4_WORD2_SECURITY_LABEL) { - status = nfsd4_encode_security_label(rqstp, context, - contextlen, &p, &buflen); + status = nfsd4_encode_security_label(xdr, rqstp, context, + contextlen); if (status) goto out; } if (bmval2 & FATTR4_WORD2_SUPPATTR_EXCLCREAT) { - if ((buflen -= 16) < 0) + p = xdr_reserve_space(xdr, 16); + if (!p) goto out_resource; - WRITE32(3); - WRITE32(NFSD_SUPPATTR_EXCLCREAT_WORD0); - WRITE32(NFSD_SUPPATTR_EXCLCREAT_WORD1); - WRITE32(NFSD_SUPPATTR_EXCLCREAT_WORD2); + *p++ = cpu_to_be32(3); + *p++ = cpu_to_be32(NFSD_SUPPATTR_EXCLCREAT_WORD0); + *p++ = cpu_to_be32(NFSD_SUPPATTR_EXCLCREAT_WORD1); + *p++ = cpu_to_be32(NFSD_SUPPATTR_EXCLCREAT_WORD2); } - *attrlenp = htonl((char *)p - (char *)attrlenp - 4); - *buffer = p; + attrlen = htonl(xdr->buf->len - attrlen_offset - 4); + write_bytes_to_xdr_buf(xdr->buf, attrlen_offset, &attrlen, 4); status = nfs_ok; out: @@ -2504,6 +2512,8 @@ out: fh_put(tempfh); kfree(tempfh); } + if (status) + xdr_truncate_encode(xdr, starting_len); return status; out_nfserr: status = nfserrno(err); @@ -2513,6 +2523,37 @@ out_resource: goto out; } +static void svcxdr_init_encode_from_buffer(struct xdr_stream *xdr, + struct xdr_buf *buf, __be32 *p, int bytes) +{ + xdr->scratch.iov_len = 0; + memset(buf, 0, sizeof(struct xdr_buf)); + buf->head[0].iov_base = p; + buf->head[0].iov_len = 0; + buf->len = 0; + xdr->buf = buf; + xdr->iov = buf->head; + xdr->p = p; + xdr->end = (void *)p + bytes; + buf->buflen = bytes; +} + +__be32 nfsd4_encode_fattr_to_buf(__be32 **p, int words, + struct svc_fh *fhp, struct svc_export *exp, + struct dentry *dentry, u32 *bmval, + struct svc_rqst *rqstp, int ignore_crossmnt) +{ + struct xdr_buf dummy; + struct xdr_stream xdr; + __be32 ret; + + svcxdr_init_encode_from_buffer(&xdr, &dummy, *p, words << 2); + ret = nfsd4_encode_fattr(&xdr, fhp, exp, dentry, bmval, rqstp, + ignore_crossmnt); + *p = xdr.p; + return ret; +} + static inline int attributes_need_mount(u32 *bmval) { if (bmval[0] & ~(FATTR4_WORD0_RDATTR_ERROR | FATTR4_WORD0_LEASE_TIME)) @@ -2523,8 +2564,8 @@ static inline int attributes_need_mount(u32 *bmval) } static __be32 -nfsd4_encode_dirent_fattr(struct nfsd4_readdir *cd, - const char *name, int namlen, __be32 **p, int buflen) +nfsd4_encode_dirent_fattr(struct xdr_stream *xdr, struct nfsd4_readdir *cd, + const char *name, int namlen) { struct svc_export *exp = cd->rd_fhp->fh_export; struct dentry *dentry; @@ -2576,7 +2617,7 @@ nfsd4_encode_dirent_fattr(struct nfsd4_readdir *cd, } out_encode: - nfserr = nfsd4_encode_fattr(NULL, exp, dentry, p, buflen, cd->rd_bmval, + nfserr = nfsd4_encode_fattr(xdr, NULL, exp, dentry, cd->rd_bmval, cd->rd_rqstp, ignore_crossmnt); out_put: dput(dentry); @@ -2585,9 +2626,12 @@ out_put: } static __be32 * -nfsd4_encode_rdattr_error(__be32 *p, int buflen, __be32 nfserr) +nfsd4_encode_rdattr_error(struct xdr_stream *xdr, __be32 nfserr) { - if (buflen < 6) + __be32 *p; + + p = xdr_reserve_space(xdr, 6); + if (!p) return NULL; *p++ = htonl(2); *p++ = htonl(FATTR4_WORD0_RDATTR_ERROR); /* bmval0 */ @@ -2604,10 +2648,13 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen, { struct readdir_cd *ccd = ccdv; struct nfsd4_readdir *cd = container_of(ccd, struct nfsd4_readdir, common); - int buflen; - __be32 *p = cd->buffer; - __be32 *cookiep; + struct xdr_stream *xdr = cd->xdr; + int start_offset = xdr->buf->len; + int cookie_offset; + int entry_bytes; __be32 nfserr = nfserr_toosmall; + __be64 wire_offset; + __be32 *p; /* In nfsv4, "." and ".." never make it onto the wire.. */ if (name && isdotent(name, namlen)) { @@ -2615,19 +2662,24 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen, return 0; } - if (cd->offset) - xdr_encode_hyper(cd->offset, (u64) offset); + if (cd->cookie_offset) { + wire_offset = cpu_to_be64(offset); + write_bytes_to_xdr_buf(xdr->buf, cd->cookie_offset, + &wire_offset, 8); + } - buflen = cd->buflen - 4 - XDR_QUADLEN(namlen); - if (buflen < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto fail; - *p++ = xdr_one; /* mark entry present */ - cookiep = p; + cookie_offset = xdr->buf->len; + 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_array(p, name, namlen); /* name length & name */ - nfserr = nfsd4_encode_dirent_fattr(cd, name, namlen, &p, buflen); + nfserr = nfsd4_encode_dirent_fattr(xdr, cd, name, namlen); switch (nfserr) { case nfs_ok: break; @@ -2646,59 +2698,74 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen, */ if (!(cd->rd_bmval[0] & FATTR4_WORD0_RDATTR_ERROR)) goto fail; - p = nfsd4_encode_rdattr_error(p, buflen, nfserr); + p = nfsd4_encode_rdattr_error(xdr, nfserr); if (p == NULL) { nfserr = nfserr_toosmall; goto fail; } } - cd->buflen -= (p - cd->buffer); - cd->buffer = p; - cd->offset = cookiep; + nfserr = nfserr_toosmall; + entry_bytes = xdr->buf->len - start_offset; + if (entry_bytes > cd->rd_maxcount) + goto fail; + cd->rd_maxcount -= entry_bytes; + if (!cd->rd_dircount) + goto fail; + cd->rd_dircount--; + cd->cookie_offset = cookie_offset; skip_entry: cd->common.err = nfs_ok; return 0; fail: + xdr_truncate_encode(xdr, start_offset); cd->common.err = nfserr; return -EINVAL; } -static void -nfsd4_encode_stateid(struct nfsd4_compoundres *resp, stateid_t *sid) +static __be32 +nfsd4_encode_stateid(struct xdr_stream *xdr, stateid_t *sid) { __be32 *p; - RESERVE_SPACE(sizeof(stateid_t)); - WRITE32(sid->si_generation); - WRITEMEM(&sid->si_opaque, sizeof(stateid_opaque_t)); - ADJUST_ARGS(); + p = xdr_reserve_space(xdr, sizeof(stateid_t)); + if (!p) + return nfserr_resource; + *p++ = cpu_to_be32(sid->si_generation); + p = xdr_encode_opaque_fixed(p, &sid->si_opaque, + sizeof(stateid_opaque_t)); + return 0; } static __be32 nfsd4_encode_access(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_access *access) { + struct xdr_stream *xdr = &resp->xdr; __be32 *p; if (!nfserr) { - RESERVE_SPACE(8); - WRITE32(access->ac_supported); - WRITE32(access->ac_resp_access); - ADJUST_ARGS(); + p = xdr_reserve_space(xdr, 8); + if (!p) + return nfserr_resource; + *p++ = cpu_to_be32(access->ac_supported); + *p++ = cpu_to_be32(access->ac_resp_access); } return nfserr; } static __be32 nfsd4_encode_bind_conn_to_session(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_bind_conn_to_session *bcts) { + struct xdr_stream *xdr = &resp->xdr; __be32 *p; if (!nfserr) { - RESERVE_SPACE(NFS4_MAX_SESSIONID_LEN + 8); - WRITEMEM(bcts->sessionid.data, NFS4_MAX_SESSIONID_LEN); - WRITE32(bcts->dir); + p = xdr_reserve_space(xdr, NFS4_MAX_SESSIONID_LEN + 8); + if (!p) + return nfserr_resource; + p = xdr_encode_opaque_fixed(p, bcts->sessionid.data, + NFS4_MAX_SESSIONID_LEN); + *p++ = cpu_to_be32(bcts->dir); /* Sorry, we do not yet support RDMA over 4.1: */ - WRITE32(0); - ADJUST_ARGS(); + *p++ = cpu_to_be32(0); } return nfserr; } @@ -2706,8 +2773,10 @@ static __be32 nfsd4_encode_bind_conn_to_session(struct nfsd4_compoundres *resp, static __be32 nfsd4_encode_close(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_close *close) { + struct xdr_stream *xdr = &resp->xdr; + if (!nfserr) - nfsd4_encode_stateid(resp, &close->cl_stateid); + nfserr = nfsd4_encode_stateid(xdr, &close->cl_stateid); return nfserr; } @@ -2716,12 +2785,15 @@ nfsd4_encode_close(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_c static __be32 nfsd4_encode_commit(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_commit *commit) { + struct xdr_stream *xdr = &resp->xdr; __be32 *p; if (!nfserr) { - RESERVE_SPACE(NFS4_VERIFIER_SIZE); - WRITEMEM(commit->co_verf.data, NFS4_VERIFIER_SIZE); - ADJUST_ARGS(); + p = xdr_reserve_space(xdr, NFS4_VERIFIER_SIZE); + if (!p) + return nfserr_resource; + p = xdr_encode_opaque_fixed(p, commit->co_verf.data, + NFS4_VERIFIER_SIZE); } return nfserr; } @@ -2729,15 +2801,17 @@ nfsd4_encode_commit(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_ static __be32 nfsd4_encode_create(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_create *create) { + struct xdr_stream *xdr = &resp->xdr; __be32 *p; if (!nfserr) { - RESERVE_SPACE(32); - write_cinfo(&p, &create->cr_cinfo); - WRITE32(2); - WRITE32(create->cr_bmval[0]); - WRITE32(create->cr_bmval[1]); - ADJUST_ARGS(); + p = xdr_reserve_space(xdr, 32); + if (!p) + return nfserr_resource; + p = encode_cinfo(p, &create->cr_cinfo); + *p++ = cpu_to_be32(2); + *p++ = cpu_to_be32(create->cr_bmval[0]); + *p++ = cpu_to_be32(create->cr_bmval[1]); } return nfserr; } @@ -2746,14 +2820,13 @@ static __be32 nfsd4_encode_getattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_getattr *getattr) { struct svc_fh *fhp = getattr->ga_fhp; - int buflen; + struct xdr_stream *xdr = &resp->xdr; if (nfserr) return nfserr; - buflen = resp->end - resp->p - (COMPOUND_ERR_SLACK_SPACE >> 2); - nfserr = nfsd4_encode_fattr(fhp, fhp->fh_export, fhp->fh_dentry, - &resp->p, buflen, getattr->ga_bmval, + nfserr = nfsd4_encode_fattr(xdr, fhp, fhp->fh_export, fhp->fh_dentry, + getattr->ga_bmval, resp->rqstp, 0); return nfserr; } @@ -2761,16 +2834,17 @@ nfsd4_encode_getattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4 static __be32 nfsd4_encode_getfh(struct nfsd4_compoundres *resp, __be32 nfserr, struct svc_fh **fhpp) { + struct xdr_stream *xdr = &resp->xdr; struct svc_fh *fhp = *fhpp; unsigned int len; __be32 *p; if (!nfserr) { len = fhp->fh_handle.fh_size; - RESERVE_SPACE(len + 4); - WRITE32(len); - WRITEMEM(&fhp->fh_handle.fh_base, len); - ADJUST_ARGS(); + p = xdr_reserve_space(xdr, len + 4); + if (!p) + return nfserr_resource; + p = xdr_encode_opaque(p, &fhp->fh_handle.fh_base, len); } return nfserr; } @@ -2779,52 +2853,69 @@ nfsd4_encode_getfh(struct nfsd4_compoundres *resp, __be32 nfserr, struct svc_fh * Including all fields other than the name, a LOCK4denied structure requires * 8(clientid) + 4(namelen) + 8(offset) + 8(length) + 4(type) = 32 bytes. */ -static void -nfsd4_encode_lock_denied(struct nfsd4_compoundres *resp, struct nfsd4_lock_denied *ld) +static __be32 +nfsd4_encode_lock_denied(struct xdr_stream *xdr, struct nfsd4_lock_denied *ld) { struct xdr_netobj *conf = &ld->ld_owner; __be32 *p; - RESERVE_SPACE(32 + XDR_LEN(conf->len)); - WRITE64(ld->ld_start); - WRITE64(ld->ld_length); - WRITE32(ld->ld_type); +again: + p = xdr_reserve_space(xdr, 32 + XDR_LEN(conf->len)); + if (!p) { + /* + * Don't fail to return the result just because we can't + * return the conflicting open: + */ + if (conf->len) { + conf->len = 0; + conf->data = NULL; + goto again; + } + return nfserr_resource; + } + p = xdr_encode_hyper(p, ld->ld_start); + p = xdr_encode_hyper(p, ld->ld_length); + *p++ = cpu_to_be32(ld->ld_type); if (conf->len) { - WRITEMEM(&ld->ld_clientid, 8); - WRITE32(conf->len); - WRITEMEM(conf->data, conf->len); - kfree(conf->data); + p = xdr_encode_opaque_fixed(p, &ld->ld_clientid, 8); + p = xdr_encode_opaque(p, conf->data, conf->len); } else { /* non - nfsv4 lock in conflict, no clientid nor owner */ - WRITE64((u64)0); /* clientid */ - WRITE32(0); /* length of owner name */ + p = xdr_encode_hyper(p, (u64)0); /* clientid */ + *p++ = cpu_to_be32(0); /* length of owner name */ } - ADJUST_ARGS(); + return nfserr_denied; } static __be32 nfsd4_encode_lock(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_lock *lock) { + struct xdr_stream *xdr = &resp->xdr; + if (!nfserr) - nfsd4_encode_stateid(resp, &lock->lk_resp_stateid); + nfserr = nfsd4_encode_stateid(xdr, &lock->lk_resp_stateid); else if (nfserr == nfserr_denied) - nfsd4_encode_lock_denied(resp, &lock->lk_denied); - + nfserr = nfsd4_encode_lock_denied(xdr, &lock->lk_denied); + kfree(lock->lk_denied.ld_owner.data); return nfserr; } static __be32 nfsd4_encode_lockt(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_lockt *lockt) { + struct xdr_stream *xdr = &resp->xdr; + if (nfserr == nfserr_denied) - nfsd4_encode_lock_denied(resp, &lockt->lt_denied); + nfsd4_encode_lock_denied(xdr, &lockt->lt_denied); return nfserr; } static __be32 nfsd4_encode_locku(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_locku *locku) { + struct xdr_stream *xdr = &resp->xdr; + if (!nfserr) - nfsd4_encode_stateid(resp, &locku->lu_stateid); + nfserr = nfsd4_encode_stateid(xdr, &locku->lu_stateid); return nfserr; } @@ -2833,12 +2924,14 @@ nfsd4_encode_locku(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_l static __be32 nfsd4_encode_link(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_link *link) { + struct xdr_stream *xdr = &resp->xdr; __be32 *p; if (!nfserr) { - RESERVE_SPACE(20); - write_cinfo(&p, &link->li_cinfo); - ADJUST_ARGS(); + p = xdr_reserve_space(xdr, 20); + if (!p) + return nfserr_resource; + p = encode_cinfo(p, &link->li_cinfo); } return nfserr; } @@ -2847,72 +2940,86 @@ nfsd4_encode_link(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_li static __be32 nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open *open) { + struct xdr_stream *xdr = &resp->xdr; __be32 *p; if (nfserr) goto out; - nfsd4_encode_stateid(resp, &open->op_stateid); - RESERVE_SPACE(40); - write_cinfo(&p, &open->op_cinfo); - WRITE32(open->op_rflags); - WRITE32(2); - WRITE32(open->op_bmval[0]); - WRITE32(open->op_bmval[1]); - WRITE32(open->op_delegate_type); - ADJUST_ARGS(); + nfserr = nfsd4_encode_stateid(xdr, &open->op_stateid); + if (nfserr) + goto out; + p = xdr_reserve_space(xdr, 40); + if (!p) + return nfserr_resource; + p = encode_cinfo(p, &open->op_cinfo); + *p++ = cpu_to_be32(open->op_rflags); + *p++ = cpu_to_be32(2); + *p++ = cpu_to_be32(open->op_bmval[0]); + *p++ = cpu_to_be32(open->op_bmval[1]); + *p++ = cpu_to_be32(open->op_delegate_type); switch (open->op_delegate_type) { case NFS4_OPEN_DELEGATE_NONE: break; case NFS4_OPEN_DELEGATE_READ: - nfsd4_encode_stateid(resp, &open->op_delegate_stateid); - RESERVE_SPACE(20); - WRITE32(open->op_recall); + nfserr = nfsd4_encode_stateid(xdr, &open->op_delegate_stateid); + if (nfserr) + return nfserr; + p = xdr_reserve_space(xdr, 20); + if (!p) + return nfserr_resource; + *p++ = cpu_to_be32(open->op_recall); /* * TODO: ACE's in delegations */ - WRITE32(NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE); - WRITE32(0); - WRITE32(0); - WRITE32(0); /* XXX: is NULL principal ok? */ - ADJUST_ARGS(); + *p++ = cpu_to_be32(NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE); + *p++ = cpu_to_be32(0); + *p++ = cpu_to_be32(0); + *p++ = cpu_to_be32(0); /* XXX: is NULL principal ok? */ break; case NFS4_OPEN_DELEGATE_WRITE: - nfsd4_encode_stateid(resp, &open->op_delegate_stateid); - RESERVE_SPACE(32); - WRITE32(0); + nfserr = nfsd4_encode_stateid(xdr, &open->op_delegate_stateid); + if (nfserr) + return nfserr; + p = xdr_reserve_space(xdr, 32); + if (!p) + return nfserr_resource; + *p++ = cpu_to_be32(0); /* * TODO: space_limit's in delegations */ - WRITE32(NFS4_LIMIT_SIZE); - WRITE32(~(u32)0); - WRITE32(~(u32)0); + *p++ = cpu_to_be32(NFS4_LIMIT_SIZE); + *p++ = cpu_to_be32(~(u32)0); + *p++ = cpu_to_be32(~(u32)0); /* * TODO: ACE's in delegations */ - WRITE32(NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE); - WRITE32(0); - WRITE32(0); - WRITE32(0); /* XXX: is NULL principal ok? */ - ADJUST_ARGS(); + *p++ = cpu_to_be32(NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE); + *p++ = cpu_to_be32(0); + *p++ = cpu_to_be32(0); + *p++ = cpu_to_be32(0); /* XXX: is NULL principal ok? */ break; case NFS4_OPEN_DELEGATE_NONE_EXT: /* 4.1 */ switch (open->op_why_no_deleg) { case WND4_CONTENTION: case WND4_RESOURCE: - RESERVE_SPACE(8); - WRITE32(open->op_why_no_deleg); - WRITE32(0); /* deleg signaling not supported yet */ + p = xdr_reserve_space(xdr, 8); + if (!p) + return nfserr_resource; + *p++ = cpu_to_be32(open->op_why_no_deleg); + /* deleg signaling not supported yet: */ + *p++ = cpu_to_be32(0); break; default: - RESERVE_SPACE(4); - WRITE32(open->op_why_no_deleg); + p = xdr_reserve_space(xdr, 4); + if (!p) + return nfserr_resource; + *p++ = cpu_to_be32(open->op_why_no_deleg); } - ADJUST_ARGS(); break; default: BUG(); @@ -2925,8 +3032,10 @@ out: static __be32 nfsd4_encode_open_confirm(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open_confirm *oc) { + struct xdr_stream *xdr = &resp->xdr; + if (!nfserr) - nfsd4_encode_stateid(resp, &oc->oc_resp_stateid); + nfserr = nfsd4_encode_stateid(xdr, &oc->oc_resp_stateid); return nfserr; } @@ -2934,127 +3043,233 @@ nfsd4_encode_open_confirm(struct nfsd4_compoundres *resp, __be32 nfserr, struct static __be32 nfsd4_encode_open_downgrade(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open_downgrade *od) { + struct xdr_stream *xdr = &resp->xdr; + if (!nfserr) - nfsd4_encode_stateid(resp, &od->od_stateid); + nfserr = nfsd4_encode_stateid(xdr, &od->od_stateid); return nfserr; } -static __be32 -nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_read *read) +static __be32 nfsd4_encode_splice_read( + struct nfsd4_compoundres *resp, + struct nfsd4_read *read, + struct file *file, unsigned long maxcount) { + struct xdr_stream *xdr = &resp->xdr; + struct xdr_buf *buf = xdr->buf; u32 eof; - int v; - struct page *page; - unsigned long maxcount; - long len; - __be32 *p; + int space_left; + __be32 nfserr; + __be32 *p = xdr->p - 2; - if (nfserr) - return nfserr; - if (resp->xbuf->page_len) + /* + * Don't inline pages unless we know there's room for eof, + * count, and possible padding: + */ + if (xdr->end - xdr->p < 3) return nfserr_resource; - RESERVE_SPACE(8); /* eof flag and byte count */ + nfserr = nfsd_splice_read(read->rd_rqstp, file, + read->rd_offset, &maxcount); + if (nfserr) { + /* + * nfsd_splice_actor may have already messed with the + * page length; reset it so as not to confuse + * xdr_truncate_encode: + */ + buf->page_len = 0; + return nfserr; + } - maxcount = svc_max_payload(resp->rqstp); - if (maxcount > read->rd_length) - maxcount = read->rd_length; + eof = (read->rd_offset + maxcount >= + read->rd_fhp->fh_dentry->d_inode->i_size); + + *(p++) = htonl(eof); + *(p++) = htonl(maxcount); + + buf->page_len = maxcount; + buf->len += maxcount; + xdr->page_ptr += (maxcount + PAGE_SIZE - 1) / PAGE_SIZE; + + /* Use rest of head for padding and remaining ops: */ + buf->tail[0].iov_base = xdr->p; + buf->tail[0].iov_len = 0; + xdr->iov = buf->tail; + if (maxcount&3) { + int pad = 4 - (maxcount&3); + + *(xdr->p++) = 0; + + buf->tail[0].iov_base += maxcount&3; + buf->tail[0].iov_len = pad; + buf->len += pad; + } + + space_left = min_t(int, (void *)xdr->end - (void *)xdr->p, + buf->buflen - buf->len); + buf->buflen = buf->len + space_left; + xdr->end = (__be32 *)((void *)xdr->end + space_left); + + return 0; +} + +static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp, + struct nfsd4_read *read, + struct file *file, unsigned long maxcount) +{ + struct xdr_stream *xdr = &resp->xdr; + u32 eof; + int v; + int starting_len = xdr->buf->len - 8; + long len; + int thislen; + __be32 nfserr; + __be32 tmp; + __be32 *p; + u32 zzz = 0; + int pad; len = maxcount; v = 0; - while (len > 0) { - page = *(resp->rqstp->rq_next_page); - if (!page) { /* ran out of pages */ - maxcount -= len; - break; - } - resp->rqstp->rq_vec[v].iov_base = page_address(page); - resp->rqstp->rq_vec[v].iov_len = - len < PAGE_SIZE ? len : PAGE_SIZE; - resp->rqstp->rq_next_page++; + + thislen = (void *)xdr->end - (void *)xdr->p; + if (len < thislen) + thislen = len; + p = xdr_reserve_space(xdr, (thislen+3)&~3); + WARN_ON_ONCE(!p); + resp->rqstp->rq_vec[v].iov_base = p; + resp->rqstp->rq_vec[v].iov_len = thislen; + v++; + len -= thislen; + + while (len) { + thislen = min_t(long, len, PAGE_SIZE); + p = xdr_reserve_space(xdr, (thislen+3)&~3); + WARN_ON_ONCE(!p); + resp->rqstp->rq_vec[v].iov_base = p; + resp->rqstp->rq_vec[v].iov_len = thislen; v++; - len -= PAGE_SIZE; + len -= thislen; } read->rd_vlen = v; - nfserr = nfsd_read_file(read->rd_rqstp, read->rd_fhp, read->rd_filp, - read->rd_offset, resp->rqstp->rq_vec, read->rd_vlen, - &maxcount); - + nfserr = nfsd_readv(file, read->rd_offset, resp->rqstp->rq_vec, + read->rd_vlen, &maxcount); if (nfserr) return nfserr; + xdr_truncate_encode(xdr, starting_len + 8 + ((maxcount+3)&~3)); + eof = (read->rd_offset + maxcount >= read->rd_fhp->fh_dentry->d_inode->i_size); - WRITE32(eof); - WRITE32(maxcount); - ADJUST_ARGS(); - resp->xbuf->head[0].iov_len = (char*)p - - (char*)resp->xbuf->head[0].iov_base; - resp->xbuf->page_len = 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); - /* Use rest of head for padding and remaining ops: */ - resp->xbuf->tail[0].iov_base = p; - resp->xbuf->tail[0].iov_len = 0; - if (maxcount&3) { - RESERVE_SPACE(4); - WRITE32(0); - resp->xbuf->tail[0].iov_base += maxcount&3; - resp->xbuf->tail[0].iov_len = 4 - (maxcount&3); - ADJUST_ARGS(); - } + pad = (maxcount&3) ? 4 - (maxcount&3) : 0; + write_bytes_to_xdr_buf(xdr->buf, starting_len + 8 + maxcount, + &zzz, pad); return 0; + } static __be32 -nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_readlink *readlink) +nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr, + struct nfsd4_read *read) { - int maxcount; - char *page; + unsigned long maxcount; + struct xdr_stream *xdr = &resp->xdr; + struct file *file = read->rd_filp; + int starting_len = xdr->buf->len; + struct raparms *ra; __be32 *p; + __be32 err; if (nfserr) return nfserr; - if (resp->xbuf->page_len) + + p = xdr_reserve_space(xdr, 8); /* eof flag and byte count */ + if (!p) { + WARN_ON_ONCE(resp->rqstp->rq_splice_ok); return nfserr_resource; - if (!*resp->rqstp->rq_next_page) + } + if (resp->xdr.buf->page_len && resp->rqstp->rq_splice_ok) { + WARN_ON_ONCE(1); return nfserr_resource; + } + xdr_commit_encode(xdr); + + maxcount = svc_max_payload(resp->rqstp); + if (maxcount > xdr->buf->buflen - xdr->buf->len) + maxcount = xdr->buf->buflen - xdr->buf->len; + if (maxcount > read->rd_length) + maxcount = read->rd_length; + + if (!read->rd_filp) { + err = nfsd_get_tmp_read_open(resp->rqstp, read->rd_fhp, + &file, &ra); + if (err) + goto err_truncate; + } + + if (file->f_op->splice_read && resp->rqstp->rq_splice_ok) + err = nfsd4_encode_splice_read(resp, read, file, maxcount); + else + err = nfsd4_encode_readv(resp, read, file, maxcount); + + if (!read->rd_filp) + nfsd_put_tmp_read_open(file, ra); + +err_truncate: + if (err) + xdr_truncate_encode(xdr, starting_len); + return err; +} + +static __be32 +nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_readlink *readlink) +{ + int maxcount; + __be32 wire_count; + int zero = 0; + struct xdr_stream *xdr = &resp->xdr; + int length_offset = xdr->buf->len; + __be32 *p; - page = page_address(*(resp->rqstp->rq_next_page++)); + if (nfserr) + return nfserr; + p = xdr_reserve_space(xdr, 4); + if (!p) + return nfserr_resource; maxcount = PAGE_SIZE; - RESERVE_SPACE(4); + p = xdr_reserve_space(xdr, maxcount); + if (!p) + return nfserr_resource; /* * XXX: By default, the ->readlink() VFS op will truncate symlinks * if they would overflow the buffer. Is this kosher in NFSv4? If * not, one easy fix is: if ->readlink() precisely fills the buffer, * assume that truncation occurred, and return NFS4ERR_RESOURCE. */ - nfserr = nfsd_readlink(readlink->rl_rqstp, readlink->rl_fhp, page, &maxcount); + nfserr = nfsd_readlink(readlink->rl_rqstp, readlink->rl_fhp, + (char *)p, &maxcount); if (nfserr == nfserr_isdir) - return nfserr_inval; - if (nfserr) + nfserr = nfserr_inval; + if (nfserr) { + xdr_truncate_encode(xdr, length_offset); return nfserr; - - WRITE32(maxcount); - ADJUST_ARGS(); - resp->xbuf->head[0].iov_len = (char*)p - - (char*)resp->xbuf->head[0].iov_base; - resp->xbuf->page_len = maxcount; - - /* Use rest of head for padding and remaining ops: */ - resp->xbuf->tail[0].iov_base = p; - resp->xbuf->tail[0].iov_len = 0; - if (maxcount&3) { - RESERVE_SPACE(4); - WRITE32(0); - resp->xbuf->tail[0].iov_base += maxcount&3; - resp->xbuf->tail[0].iov_len = 4 - (maxcount&3); - ADJUST_ARGS(); } + + wire_count = htonl(maxcount); + write_bytes_to_xdr_buf(xdr->buf, length_offset, &wire_count, 4); + xdr_truncate_encode(xdr, length_offset + 4 + maxcount); + if (maxcount & 3) + write_bytes_to_xdr_buf(xdr->buf, length_offset + 4 + maxcount, + &zero, 4 - (maxcount&3)); return 0; } @@ -3062,47 +3277,52 @@ static __be32 nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_readdir *readdir) { int maxcount; + int bytes_left; loff_t offset; - __be32 *page, *savep, *tailbase; + __be64 wire_offset; + struct xdr_stream *xdr = &resp->xdr; + int starting_len = xdr->buf->len; __be32 *p; if (nfserr) return nfserr; - if (resp->xbuf->page_len) - return nfserr_resource; - if (!*resp->rqstp->rq_next_page) - return nfserr_resource; - RESERVE_SPACE(NFS4_VERIFIER_SIZE); - savep = p; + p = xdr_reserve_space(xdr, NFS4_VERIFIER_SIZE); + if (!p) + return nfserr_resource; /* XXX: Following NFSv3, we ignore the READDIR verifier for now. */ - WRITE32(0); - WRITE32(0); - ADJUST_ARGS(); - resp->xbuf->head[0].iov_len = ((char*)resp->p) - (char*)resp->xbuf->head[0].iov_base; - tailbase = p; - - maxcount = PAGE_SIZE; - if (maxcount > readdir->rd_maxcount) - maxcount = readdir->rd_maxcount; + *p++ = cpu_to_be32(0); + *p++ = cpu_to_be32(0); + resp->xdr.buf->head[0].iov_len = ((char *)resp->xdr.p) + - (char *)resp->xdr.buf->head[0].iov_base; /* - * Convert from bytes to words, account for the two words already - * written, make sure to leave two words at the end for the next - * pointer and eof field. + * Number of bytes left for directory entries allowing for the + * final 8 bytes of the readdir and a following failed op: + */ + bytes_left = xdr->buf->buflen - xdr->buf->len + - COMPOUND_ERR_SLACK_SPACE - 8; + if (bytes_left < 0) { + nfserr = nfserr_resource; + goto err_no_verf; + } + maxcount = min_t(u32, readdir->rd_maxcount, INT_MAX); + /* + * Note the rfc defines rd_maxcount as the size of the + * READDIR4resok structure, which includes the verifier above + * and the 8 bytes encoded at the end of this function: */ - maxcount = (maxcount >> 2) - 4; - if (maxcount < 0) { - nfserr = nfserr_toosmall; + if (maxcount < 16) { + nfserr = nfserr_toosmall; goto err_no_verf; } + maxcount = min_t(int, maxcount-16, bytes_left); - page = page_address(*(resp->rqstp->rq_next_page++)); + readdir->xdr = xdr; + readdir->rd_maxcount = maxcount; readdir->common.err = 0; - readdir->buflen = maxcount; - readdir->buffer = page; - readdir->offset = NULL; + readdir->cookie_offset = 0; offset = readdir->rd_cookie; nfserr = nfsd_readdir(readdir->rd_rqstp, readdir->rd_fhp, @@ -3110,42 +3330,49 @@ nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4 &readdir->common, nfsd4_encode_dirent); if (nfserr == nfs_ok && readdir->common.err == nfserr_toosmall && - readdir->buffer == page) - nfserr = nfserr_toosmall; + xdr->buf->len == starting_len + 8) { + /* nothing encoded; which limit did we hit?: */ + if (maxcount - 16 < bytes_left) + /* It was the fault of rd_maxcount: */ + nfserr = nfserr_toosmall; + else + /* We ran out of buffer space: */ + nfserr = nfserr_resource; + } if (nfserr) goto err_no_verf; - if (readdir->offset) - xdr_encode_hyper(readdir->offset, offset); + if (readdir->cookie_offset) { + wire_offset = cpu_to_be64(offset); + write_bytes_to_xdr_buf(xdr->buf, readdir->cookie_offset, + &wire_offset, 8); + } - p = readdir->buffer; + p = xdr_reserve_space(xdr, 8); + if (!p) { + WARN_ON_ONCE(1); + goto err_no_verf; + } *p++ = 0; /* no more entries */ *p++ = htonl(readdir->common.err == nfserr_eof); - resp->xbuf->page_len = ((char*)p) - - (char*)page_address(*(resp->rqstp->rq_next_page-1)); - - /* Use rest of head for padding and remaining ops: */ - resp->xbuf->tail[0].iov_base = tailbase; - resp->xbuf->tail[0].iov_len = 0; - resp->p = resp->xbuf->tail[0].iov_base; - resp->end = resp->p + (PAGE_SIZE - resp->xbuf->head[0].iov_len)/4; return 0; err_no_verf: - p = savep; - ADJUST_ARGS(); + xdr_truncate_encode(xdr, starting_len); return nfserr; } static __be32 nfsd4_encode_remove(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_remove *remove) { + struct xdr_stream *xdr = &resp->xdr; __be32 *p; if (!nfserr) { - RESERVE_SPACE(20); - write_cinfo(&p, &remove->rm_cinfo); - ADJUST_ARGS(); + p = xdr_reserve_space(xdr, 20); + if (!p) + return nfserr_resource; + p = encode_cinfo(p, &remove->rm_cinfo); } return nfserr; } @@ -3153,19 +3380,21 @@ nfsd4_encode_remove(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_ static __be32 nfsd4_encode_rename(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_rename *rename) { + struct xdr_stream *xdr = &resp->xdr; __be32 *p; if (!nfserr) { - RESERVE_SPACE(40); - write_cinfo(&p, &rename->rn_sinfo); - write_cinfo(&p, &rename->rn_tinfo); - ADJUST_ARGS(); + p = xdr_reserve_space(xdr, 40); + if (!p) + return nfserr_resource; + p = encode_cinfo(p, &rename->rn_sinfo); + p = encode_cinfo(p, &rename->rn_tinfo); } return nfserr; } static __be32 -nfsd4_do_encode_secinfo(struct nfsd4_compoundres *resp, +nfsd4_do_encode_secinfo(struct xdr_stream *xdr, __be32 nfserr, struct svc_export *exp) { u32 i, nflavs, supported; @@ -3176,6 +3405,7 @@ nfsd4_do_encode_secinfo(struct nfsd4_compoundres *resp, if (nfserr) goto out; + nfserr = nfserr_resource; if (exp->ex_nflavors) { flavs = exp->ex_flavors; nflavs = exp->ex_nflavors; @@ -3197,9 +3427,10 @@ nfsd4_do_encode_secinfo(struct nfsd4_compoundres *resp, } supported = 0; - RESERVE_SPACE(4); + p = xdr_reserve_space(xdr, 4); + if (!p) + goto out; flavorsp = p++; /* to be backfilled later */ - ADJUST_ARGS(); for (i = 0; i < nflavs; i++) { rpc_authflavor_t pf = flavs[i].pseudoflavor; @@ -3207,18 +3438,20 @@ nfsd4_do_encode_secinfo(struct nfsd4_compoundres *resp, if (rpcauth_get_gssinfo(pf, &info) == 0) { supported++; - RESERVE_SPACE(4 + 4 + XDR_LEN(info.oid.len) + 4 + 4); - WRITE32(RPC_AUTH_GSS); - WRITE32(info.oid.len); - WRITEMEM(info.oid.data, info.oid.len); - WRITE32(info.qop); - WRITE32(info.service); - ADJUST_ARGS(); + p = xdr_reserve_space(xdr, 4 + 4 + + XDR_LEN(info.oid.len) + 4 + 4); + if (!p) + goto out; + *p++ = cpu_to_be32(RPC_AUTH_GSS); + p = xdr_encode_opaque(p, info.oid.data, info.oid.len); + *p++ = cpu_to_be32(info.qop); + *p++ = cpu_to_be32(info.service); } else if (pf < RPC_AUTH_MAXFLAVOR) { supported++; - RESERVE_SPACE(4); - WRITE32(pf); - ADJUST_ARGS(); + p = xdr_reserve_space(xdr, 4); + if (!p) + goto out; + *p++ = cpu_to_be32(pf); } else { if (report) pr_warn("NFS: SECINFO: security flavor %u " @@ -3229,7 +3462,7 @@ nfsd4_do_encode_secinfo(struct nfsd4_compoundres *resp, if (nflavs != supported) report = false; *flavorsp = htonl(supported); - + nfserr = 0; out: if (exp) exp_put(exp); @@ -3240,14 +3473,18 @@ static __be32 nfsd4_encode_secinfo(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_secinfo *secinfo) { - return nfsd4_do_encode_secinfo(resp, nfserr, secinfo->si_exp); + struct xdr_stream *xdr = &resp->xdr; + + return nfsd4_do_encode_secinfo(xdr, nfserr, secinfo->si_exp); } static __be32 nfsd4_encode_secinfo_no_name(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_secinfo_no_name *secinfo) { - return nfsd4_do_encode_secinfo(resp, nfserr, secinfo->sin_exp); + struct xdr_stream *xdr = &resp->xdr; + + return nfsd4_do_encode_secinfo(xdr, nfserr, secinfo->sin_exp); } /* @@ -3257,41 +3494,47 @@ nfsd4_encode_secinfo_no_name(struct nfsd4_compoundres *resp, __be32 nfserr, static __be32 nfsd4_encode_setattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_setattr *setattr) { + struct xdr_stream *xdr = &resp->xdr; __be32 *p; - RESERVE_SPACE(16); + p = xdr_reserve_space(xdr, 16); + if (!p) + return nfserr_resource; if (nfserr) { - WRITE32(3); - WRITE32(0); - WRITE32(0); - WRITE32(0); + *p++ = cpu_to_be32(3); + *p++ = cpu_to_be32(0); + *p++ = cpu_to_be32(0); + *p++ = cpu_to_be32(0); } else { - WRITE32(3); - WRITE32(setattr->sa_bmval[0]); - WRITE32(setattr->sa_bmval[1]); - WRITE32(setattr->sa_bmval[2]); + *p++ = cpu_to_be32(3); + *p++ = cpu_to_be32(setattr->sa_bmval[0]); + *p++ = cpu_to_be32(setattr->sa_bmval[1]); + *p++ = cpu_to_be32(setattr->sa_bmval[2]); } - ADJUST_ARGS(); return nfserr; } static __be32 nfsd4_encode_setclientid(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_setclientid *scd) { + struct xdr_stream *xdr = &resp->xdr; __be32 *p; if (!nfserr) { - RESERVE_SPACE(8 + NFS4_VERIFIER_SIZE); - WRITEMEM(&scd->se_clientid, 8); - WRITEMEM(&scd->se_confirm, NFS4_VERIFIER_SIZE); - ADJUST_ARGS(); + p = xdr_reserve_space(xdr, 8 + NFS4_VERIFIER_SIZE); + if (!p) + return nfserr_resource; + p = xdr_encode_opaque_fixed(p, &scd->se_clientid, 8); + p = xdr_encode_opaque_fixed(p, &scd->se_confirm, + NFS4_VERIFIER_SIZE); } else if (nfserr == nfserr_clid_inuse) { - RESERVE_SPACE(8); - WRITE32(0); - WRITE32(0); - ADJUST_ARGS(); + p = xdr_reserve_space(xdr, 8); + if (!p) + return nfserr_resource; + *p++ = cpu_to_be32(0); + *p++ = cpu_to_be32(0); } return nfserr; } @@ -3299,14 +3542,17 @@ nfsd4_encode_setclientid(struct nfsd4_compoundres *resp, __be32 nfserr, struct n static __be32 nfsd4_encode_write(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_write *write) { + struct xdr_stream *xdr = &resp->xdr; __be32 *p; if (!nfserr) { - RESERVE_SPACE(16); - WRITE32(write->wr_bytes_written); - WRITE32(write->wr_how_written); - WRITEMEM(write->wr_verifier.data, NFS4_VERIFIER_SIZE); - ADJUST_ARGS(); + p = xdr_reserve_space(xdr, 16); + if (!p) + return nfserr_resource; + *p++ = cpu_to_be32(write->wr_bytes_written); + *p++ = cpu_to_be32(write->wr_how_written); + p = xdr_encode_opaque_fixed(p, write->wr_verifier.data, + NFS4_VERIFIER_SIZE); } return nfserr; } @@ -3323,6 +3569,7 @@ static __be32 nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_exchange_id *exid) { + struct xdr_stream *xdr = &resp->xdr; __be32 *p; char *major_id; char *server_scope; @@ -3338,60 +3585,61 @@ nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr, server_scope = utsname()->nodename; server_scope_sz = strlen(server_scope); - RESERVE_SPACE( + p = xdr_reserve_space(xdr, 8 /* eir_clientid */ + 4 /* eir_sequenceid */ + 4 /* eir_flags */ + 4 /* spr_how */); + if (!p) + return nfserr_resource; - WRITEMEM(&exid->clientid, 8); - WRITE32(exid->seqid); - WRITE32(exid->flags); + p = xdr_encode_opaque_fixed(p, &exid->clientid, 8); + *p++ = cpu_to_be32(exid->seqid); + *p++ = cpu_to_be32(exid->flags); - WRITE32(exid->spa_how); - ADJUST_ARGS(); + *p++ = cpu_to_be32(exid->spa_how); switch (exid->spa_how) { case SP4_NONE: break; case SP4_MACH_CRED: /* spo_must_enforce, spo_must_allow */ - RESERVE_SPACE(16); + p = xdr_reserve_space(xdr, 16); + if (!p) + return nfserr_resource; /* spo_must_enforce bitmap: */ - WRITE32(2); - WRITE32(nfs4_minimal_spo_must_enforce[0]); - WRITE32(nfs4_minimal_spo_must_enforce[1]); + *p++ = cpu_to_be32(2); + *p++ = cpu_to_be32(nfs4_minimal_spo_must_enforce[0]); + *p++ = cpu_to_be32(nfs4_minimal_spo_must_enforce[1]); /* empty spo_must_allow bitmap: */ - WRITE32(0); + *p++ = cpu_to_be32(0); - ADJUST_ARGS(); break; default: WARN_ON_ONCE(1); } - RESERVE_SPACE( + p = xdr_reserve_space(xdr, 8 /* so_minor_id */ + 4 /* so_major_id.len */ + (XDR_QUADLEN(major_id_sz) * 4) + 4 /* eir_server_scope.len */ + (XDR_QUADLEN(server_scope_sz) * 4) + 4 /* eir_server_impl_id.count (0) */); + if (!p) + return nfserr_resource; /* The server_owner struct */ - WRITE64(minor_id); /* Minor id */ + p = xdr_encode_hyper(p, minor_id); /* Minor id */ /* major id */ - WRITE32(major_id_sz); - WRITEMEM(major_id, major_id_sz); + p = xdr_encode_opaque(p, major_id, major_id_sz); /* Server scope */ - WRITE32(server_scope_sz); - WRITEMEM(server_scope, server_scope_sz); + p = xdr_encode_opaque(p, server_scope, server_scope_sz); /* Implementation id */ - WRITE32(0); /* zero length nfs_impl_id4 array */ - ADJUST_ARGS(); + *p++ = cpu_to_be32(0); /* zero length nfs_impl_id4 array */ return 0; } @@ -3399,47 +3647,54 @@ static __be32 nfsd4_encode_create_session(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_create_session *sess) { + struct xdr_stream *xdr = &resp->xdr; __be32 *p; if (nfserr) return nfserr; - RESERVE_SPACE(24); - WRITEMEM(sess->sessionid.data, NFS4_MAX_SESSIONID_LEN); - WRITE32(sess->seqid); - WRITE32(sess->flags); - ADJUST_ARGS(); - - RESERVE_SPACE(28); - WRITE32(0); /* headerpadsz */ - WRITE32(sess->fore_channel.maxreq_sz); - WRITE32(sess->fore_channel.maxresp_sz); - WRITE32(sess->fore_channel.maxresp_cached); - WRITE32(sess->fore_channel.maxops); - WRITE32(sess->fore_channel.maxreqs); - WRITE32(sess->fore_channel.nr_rdma_attrs); - ADJUST_ARGS(); + p = xdr_reserve_space(xdr, 24); + if (!p) + return nfserr_resource; + p = xdr_encode_opaque_fixed(p, sess->sessionid.data, + NFS4_MAX_SESSIONID_LEN); + *p++ = cpu_to_be32(sess->seqid); + *p++ = cpu_to_be32(sess->flags); + + p = xdr_reserve_space(xdr, 28); + if (!p) + return nfserr_resource; + *p++ = cpu_to_be32(0); /* headerpadsz */ + *p++ = cpu_to_be32(sess->fore_channel.maxreq_sz); + *p++ = cpu_to_be32(sess->fore_channel.maxresp_sz); + *p++ = cpu_to_be32(sess->fore_channel.maxresp_cached); + *p++ = cpu_to_be32(sess->fore_channel.maxops); + *p++ = cpu_to_be32(sess->fore_channel.maxreqs); + *p++ = cpu_to_be32(sess->fore_channel.nr_rdma_attrs); if (sess->fore_channel.nr_rdma_attrs) { - RESERVE_SPACE(4); - WRITE32(sess->fore_channel.rdma_attrs); - ADJUST_ARGS(); + p = xdr_reserve_space(xdr, 4); + if (!p) + return nfserr_resource; + *p++ = cpu_to_be32(sess->fore_channel.rdma_attrs); } - RESERVE_SPACE(28); - WRITE32(0); /* headerpadsz */ - WRITE32(sess->back_channel.maxreq_sz); - WRITE32(sess->back_channel.maxresp_sz); - WRITE32(sess->back_channel.maxresp_cached); - WRITE32(sess->back_channel.maxops); - WRITE32(sess->back_channel.maxreqs); - WRITE32(sess->back_channel.nr_rdma_attrs); - ADJUST_ARGS(); + p = xdr_reserve_space(xdr, 28); + if (!p) + return nfserr_resource; + *p++ = cpu_to_be32(0); /* headerpadsz */ + *p++ = cpu_to_be32(sess->back_channel.maxreq_sz); + *p++ = cpu_to_be32(sess->back_channel.maxresp_sz); + *p++ = cpu_to_be32(sess->back_channel.maxresp_cached); + *p++ = cpu_to_be32(sess->back_channel.maxops); + *p++ = cpu_to_be32(sess->back_channel.maxreqs); + *p++ = cpu_to_be32(sess->back_channel.nr_rdma_attrs); if (sess->back_channel.nr_rdma_attrs) { - RESERVE_SPACE(4); - WRITE32(sess->back_channel.rdma_attrs); - ADJUST_ARGS(); + p = xdr_reserve_space(xdr, 4); + if (!p) + return nfserr_resource; + *p++ = cpu_to_be32(sess->back_channel.rdma_attrs); } return 0; } @@ -3448,22 +3703,25 @@ static __be32 nfsd4_encode_sequence(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_sequence *seq) { + struct xdr_stream *xdr = &resp->xdr; __be32 *p; if (nfserr) return nfserr; - RESERVE_SPACE(NFS4_MAX_SESSIONID_LEN + 20); - WRITEMEM(seq->sessionid.data, NFS4_MAX_SESSIONID_LEN); - WRITE32(seq->seqid); - WRITE32(seq->slotid); + p = xdr_reserve_space(xdr, NFS4_MAX_SESSIONID_LEN + 20); + if (!p) + return nfserr_resource; + p = xdr_encode_opaque_fixed(p, seq->sessionid.data, + NFS4_MAX_SESSIONID_LEN); + *p++ = cpu_to_be32(seq->seqid); + *p++ = cpu_to_be32(seq->slotid); /* Note slotid's are numbered from zero: */ - WRITE32(seq->maxslots - 1); /* sr_highest_slotid */ - WRITE32(seq->maxslots - 1); /* sr_target_highest_slotid */ - WRITE32(seq->status_flags); + *p++ = cpu_to_be32(seq->maxslots - 1); /* sr_highest_slotid */ + *p++ = cpu_to_be32(seq->maxslots - 1); /* sr_target_highest_slotid */ + *p++ = cpu_to_be32(seq->status_flags); - ADJUST_ARGS(); - resp->cstate.datap = p; /* DRC cache data pointer */ + resp->cstate.data_offset = xdr->buf->len; /* DRC cache data pointer */ return 0; } @@ -3471,20 +3729,22 @@ static __be32 nfsd4_encode_test_stateid(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_test_stateid *test_stateid) { + struct xdr_stream *xdr = &resp->xdr; struct nfsd4_test_stateid_id *stateid, *next; __be32 *p; if (nfserr) return nfserr; - RESERVE_SPACE(4 + (4 * test_stateid->ts_num_ids)); + p = xdr_reserve_space(xdr, 4 + (4 * test_stateid->ts_num_ids)); + if (!p) + return nfserr_resource; *p++ = htonl(test_stateid->ts_num_ids); list_for_each_entry_safe(stateid, next, &test_stateid->ts_stateid_list, ts_id_list) { *p++ = stateid->ts_id_status; } - ADJUST_ARGS(); return nfserr; } @@ -3563,81 +3823,99 @@ static nfsd4_enc nfsd4_enc_ops[] = { }; /* - * Calculate the total amount of memory that the compound response has taken - * after encoding the current operation with pad. - * - * pad: if operation is non-idempotent, pad was calculate by op_rsize_bop() - * which was specified at nfsd4_operation, else pad is zero. - * - * Compare this length to the session se_fmaxresp_sz and se_fmaxresp_cached. + * Calculate whether we still have space to encode repsize bytes. + * There are two considerations: + * - For NFS versions >=4.1, the size of the reply must stay within + * session limits + * - For all NFS versions, we must stay within limited preallocated + * buffer space. * - * Our se_fmaxresp_cached will always be a multiple of PAGE_SIZE, and so - * will be at least a page and will therefore hold the xdr_buf head. + * This is called before the operation is processed, so can only provide + * an upper estimate. For some nonidempotent operations (such as + * getattr), it's not necessarily a problem if that estimate is wrong, + * as we can fail it after processing without significant side effects. */ -__be32 nfsd4_check_resp_size(struct nfsd4_compoundres *resp, u32 pad) +__be32 nfsd4_check_resp_size(struct nfsd4_compoundres *resp, u32 respsize) { - struct xdr_buf *xb = &resp->rqstp->rq_res; - struct nfsd4_session *session = NULL; + struct xdr_buf *buf = &resp->rqstp->rq_res; struct nfsd4_slot *slot = resp->cstate.slot; - u32 length, tlen = 0; + if (buf->len + respsize <= buf->buflen) + return nfs_ok; if (!nfsd4_has_session(&resp->cstate)) - return 0; - - session = resp->cstate.session; - - if (xb->page_len == 0) { - length = (char *)resp->p - (char *)xb->head[0].iov_base + pad; - } else { - if (xb->tail[0].iov_base && xb->tail[0].iov_len > 0) - tlen = (char *)resp->p - (char *)xb->tail[0].iov_base; - - length = xb->head[0].iov_len + xb->page_len + tlen + pad; - } - dprintk("%s length %u, xb->page_len %u tlen %u pad %u\n", __func__, - length, xb->page_len, tlen, pad); - - if (length > session->se_fchannel.maxresp_sz) - return nfserr_rep_too_big; - - if ((slot->sl_flags & NFSD4_SLOT_CACHETHIS) && - length > session->se_fchannel.maxresp_cached) + return nfserr_resource; + if (slot->sl_flags & NFSD4_SLOT_CACHETHIS) { + WARN_ON_ONCE(1); return nfserr_rep_too_big_to_cache; - - return 0; + } + return nfserr_rep_too_big; } void nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op) { + struct xdr_stream *xdr = &resp->xdr; struct nfs4_stateowner *so = resp->cstate.replay_owner; - __be32 *statp; + struct svc_rqst *rqstp = resp->rqstp; + int post_err_offset; + nfsd4_enc encoder; __be32 *p; - RESERVE_SPACE(8); - WRITE32(op->opnum); - statp = p++; /* to be backfilled at the end */ - ADJUST_ARGS(); + p = xdr_reserve_space(xdr, 8); + if (!p) { + WARN_ON_ONCE(1); + return; + } + *p++ = cpu_to_be32(op->opnum); + post_err_offset = xdr->buf->len; if (op->opnum == OP_ILLEGAL) goto status; BUG_ON(op->opnum < 0 || op->opnum >= ARRAY_SIZE(nfsd4_enc_ops) || !nfsd4_enc_ops[op->opnum]); - op->status = nfsd4_enc_ops[op->opnum](resp, op->status, &op->u); + encoder = nfsd4_enc_ops[op->opnum]; + op->status = encoder(resp, op->status, &op->u); + xdr_commit_encode(xdr); + /* nfsd4_check_resp_size guarantees enough room for error status */ - if (!op->status) - op->status = nfsd4_check_resp_size(resp, 0); + if (!op->status) { + int space_needed = 0; + if (!nfsd4_last_compound_op(rqstp)) + space_needed = COMPOUND_ERR_SLACK_SPACE; + op->status = nfsd4_check_resp_size(resp, space_needed); + } + if (op->status == nfserr_resource && nfsd4_has_session(&resp->cstate)) { + struct nfsd4_slot *slot = resp->cstate.slot; + + if (slot->sl_flags & NFSD4_SLOT_CACHETHIS) + op->status = nfserr_rep_too_big_to_cache; + else + op->status = nfserr_rep_too_big; + } + if (op->status == nfserr_resource || + op->status == nfserr_rep_too_big || + op->status == nfserr_rep_too_big_to_cache) { + /* + * The operation may have already been encoded or + * partially encoded. No op returns anything additional + * in the case of one of these three errors, so we can + * just truncate back to after the status. But it's a + * bug if we had to do this on a non-idempotent op: + */ + warn_on_nonidempotent_op(op); + xdr_truncate_encode(xdr, post_err_offset); + } if (so) { + int len = xdr->buf->len - post_err_offset; + so->so_replay.rp_status = op->status; - so->so_replay.rp_buflen = (char *)resp->p - (char *)(statp+1); - memcpy(so->so_replay.rp_buf, statp+1, so->so_replay.rp_buflen); + so->so_replay.rp_buflen = len; + read_bytes_from_xdr_buf(xdr->buf, post_err_offset, + so->so_replay.rp_buf, len); } status: - /* - * Note: We write the status directly, instead of using WRITE32(), - * since it is already in network byte order. - */ - *statp = op->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); } /* @@ -3649,21 +3927,22 @@ status: * called with nfs4_lock_state() held */ void -nfsd4_encode_replay(struct nfsd4_compoundres *resp, struct nfsd4_op *op) +nfsd4_encode_replay(struct xdr_stream *xdr, struct nfsd4_op *op) { __be32 *p; struct nfs4_replay *rp = op->replay; BUG_ON(!rp); - RESERVE_SPACE(8); - WRITE32(op->opnum); + p = xdr_reserve_space(xdr, 8 + rp->rp_buflen); + if (!p) { + WARN_ON_ONCE(1); + return; + } + *p++ = cpu_to_be32(op->opnum); *p++ = rp->rp_status; /* already xdr'ed */ - ADJUST_ARGS(); - RESERVE_SPACE(rp->rp_buflen); - WRITEMEM(rp->rp_buf, rp->rp_buflen); - ADJUST_ARGS(); + p = xdr_encode_opaque_fixed(p, rp->rp_buf, rp->rp_buflen); } int @@ -3720,19 +3999,19 @@ nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_compo * All that remains is to write the tag and operation count... */ struct nfsd4_compound_state *cs = &resp->cstate; - struct kvec *iov; + struct xdr_buf *buf = resp->xdr.buf; + + WARN_ON_ONCE(buf->len != buf->head[0].iov_len + buf->page_len + + buf->tail[0].iov_len); + + rqstp->rq_next_page = resp->xdr.page_ptr + 1; + p = resp->tagp; *p++ = htonl(resp->taglen); memcpy(p, resp->tag, resp->taglen); p += XDR_QUADLEN(resp->taglen); *p++ = htonl(resp->opcnt); - if (rqstp->rq_res.page_len) - iov = &rqstp->rq_res.tail[0]; - else - iov = &rqstp->rq_res.head[0]; - iov->iov_len = ((char*)resp->p) - (char*)iov->iov_base; - BUG_ON(iov->iov_len > PAGE_SIZE); if (nfsd4_has_session(cs)) { struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); struct nfs4_client *clp = cs->session->se_client; diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index f8f060ffbf4f..6040da8830ff 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -224,13 +224,6 @@ hash_refile(struct svc_cacherep *rp) hlist_add_head(&rp->c_hash, cache_hash + hash_32(rp->c_xid, maskbits)); } -static inline bool -nfsd_cache_entry_expired(struct svc_cacherep *rp) -{ - return rp->c_state != RC_INPROG && - time_after(jiffies, rp->c_timestamp + RC_EXPIRE); -} - /* * Walk the LRU list and prune off entries that are older than RC_EXPIRE. * Also prune the oldest ones when the total exceeds the max number of entries. @@ -242,8 +235,14 @@ prune_cache_entries(void) long freed = 0; list_for_each_entry_safe(rp, tmp, &lru_head, c_lru) { - if (!nfsd_cache_entry_expired(rp) && - num_drc_entries <= max_drc_entries) + /* + * Don't free entries attached to calls that are still + * in-progress, but do keep scanning the list. + */ + if (rp->c_state == RC_INPROG) + continue; + if (num_drc_entries <= max_drc_entries && + time_before(jiffies, rp->c_timestamp + RC_EXPIRE)) break; nfsd_reply_cache_free_locked(rp); freed++; diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index f34d9de802ab..51844048937f 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -1179,7 +1179,6 @@ static int __init init_nfsd(void) retval = nfsd4_init_slabs(); if (retval) goto out_unregister_pernet; - nfs4_state_init(); retval = nfsd_fault_inject_init(); /* nfsd fault injection controls */ if (retval) goto out_free_slabs; diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 479eb681c27c..847daf37e566 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -15,11 +15,20 @@ #include <linux/nfs2.h> #include <linux/nfs3.h> #include <linux/nfs4.h> +#include <linux/sunrpc/svc.h> #include <linux/sunrpc/msg_prot.h> -#include <linux/nfsd/debug.h> -#include <linux/nfsd/export.h> -#include <linux/nfsd/stats.h> +#include <uapi/linux/nfsd/debug.h> + +#include "stats.h" +#include "export.h" + +#undef ifdebug +#ifdef NFSD_DEBUG +# define ifdebug(flag) if (nfsd_debug & NFSDDBG_##flag) +#else +# define ifdebug(flag) if (0) +#endif /* * nfsd version @@ -106,7 +115,6 @@ static inline int nfsd_v4client(struct svc_rqst *rq) */ #ifdef CONFIG_NFSD_V4 extern unsigned long max_delegations; -void nfs4_state_init(void); int nfsd4_init_slabs(void); void nfsd4_free_slabs(void); int nfs4_state_start(void); @@ -117,7 +125,6 @@ void nfs4_reset_lease(time_t leasetime); int nfs4_reset_recoverydir(char *recdir); char * nfs4_recoverydir(void); #else -static inline void nfs4_state_init(void) { } static inline int nfsd4_init_slabs(void) { return 0; } static inline void nfsd4_free_slabs(void) { } static inline int nfs4_state_start(void) { return 0; } diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index 3c37b160dcad..ec8393418154 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -88,9 +88,8 @@ static __be32 nfsd_setuser_and_check_port(struct svc_rqst *rqstp, /* Check if the request originated from a secure port. */ if (!rqstp->rq_secure && !(flags & NFSEXP_INSECURE_PORT)) { RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]); - dprintk(KERN_WARNING - "nfsd: request from insecure port %s!\n", - svc_print_addr(rqstp, buf, sizeof(buf))); + dprintk("nfsd: request from insecure port %s!\n", + svc_print_addr(rqstp, buf, sizeof(buf))); return nfserr_perm; } @@ -169,8 +168,8 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp) data_left -= len; if (data_left < 0) return error; - exp = rqst_exp_find(rqstp, fh->fh_fsid_type, fh->fh_auth); - fid = (struct fid *)(fh->fh_auth + len); + exp = rqst_exp_find(rqstp, fh->fh_fsid_type, fh->fh_fsid); + fid = (struct fid *)(fh->fh_fsid + len); } else { __u32 tfh[2]; dev_t xdev; @@ -385,7 +384,7 @@ static void _fh_update(struct svc_fh *fhp, struct svc_export *exp, { if (dentry != exp->ex_path.dentry) { struct fid *fid = (struct fid *) - (fhp->fh_handle.fh_auth + fhp->fh_handle.fh_size/4 - 1); + (fhp->fh_handle.fh_fsid + fhp->fh_handle.fh_size/4 - 1); int maxsize = (fhp->fh_maxsize - fhp->fh_handle.fh_size)/4; int subtreecheck = !(exp->ex_flags & NFSEXP_NOSUBTREECHECK); @@ -513,7 +512,6 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry, */ struct inode * inode = dentry->d_inode; - __u32 *datap; dev_t ex_dev = exp_sb(exp)->s_dev; dprintk("nfsd: fh_compose(exp %02x:%02x/%ld %pd2, ino=%ld)\n", @@ -557,17 +555,16 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry, if (inode) _fh_update_old(dentry, exp, &fhp->fh_handle); } else { - int len; + fhp->fh_handle.fh_size = + key_len(fhp->fh_handle.fh_fsid_type) + 4; fhp->fh_handle.fh_auth_type = 0; - datap = fhp->fh_handle.fh_auth+0; - mk_fsid(fhp->fh_handle.fh_fsid_type, datap, ex_dev, + + mk_fsid(fhp->fh_handle.fh_fsid_type, + fhp->fh_handle.fh_fsid, + ex_dev, exp->ex_path.dentry->d_inode->i_ino, exp->ex_fsid, exp->ex_uuid); - len = key_len(fhp->fh_handle.fh_fsid_type); - datap += len/4; - fhp->fh_handle.fh_size = 4 + len; - if (inode) _fh_update(fhp, exp, dentry); if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID) { diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h index ad67964d0bb1..2e89e70ac15c 100644 --- a/fs/nfsd/nfsfh.h +++ b/fs/nfsd/nfsfh.h @@ -1,9 +1,58 @@ -/* Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de> */ +/* + * Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de> + * + * This file describes the layout of the file handles as passed + * over the wire. + */ +#ifndef _LINUX_NFSD_NFSFH_H +#define _LINUX_NFSD_NFSFH_H + +#include <linux/sunrpc/svc.h> +#include <uapi/linux/nfsd/nfsfh.h> + +static inline __u32 ino_t_to_u32(ino_t ino) +{ + return (__u32) ino; +} + +static inline ino_t u32_to_ino_t(__u32 uino) +{ + return (ino_t) uino; +} -#ifndef _LINUX_NFSD_FH_INT_H -#define _LINUX_NFSD_FH_INT_H +/* + * This is the internal representation of an NFS handle used in knfsd. + * pre_mtime/post_version will be used to support wcc_attr's in NFSv3. + */ +typedef struct svc_fh { + struct knfsd_fh fh_handle; /* FH data */ + struct dentry * fh_dentry; /* validated dentry */ + struct svc_export * fh_export; /* export pointer */ + int fh_maxsize; /* max size for fh_handle */ + + unsigned char fh_locked; /* inode locked by us */ + unsigned char fh_want_write; /* remount protection taken */ + +#ifdef CONFIG_NFSD_V3 + unsigned char fh_post_saved; /* post-op attrs saved */ + unsigned char fh_pre_saved; /* pre-op attrs saved */ + + /* Pre-op attributes saved during fh_lock */ + __u64 fh_pre_size; /* size before operation */ + struct timespec fh_pre_mtime; /* mtime before oper */ + struct timespec fh_pre_ctime; /* ctime before oper */ + /* + * pre-op nfsv4 change attr: note must check IS_I_VERSION(inode) + * to find out if it is valid. + */ + u64 fh_pre_change; + + /* Post-op attributes saved in fh_unlock */ + struct kstat fh_post_attr; /* full attrs after operation */ + u64 fh_post_change; /* nfsv4 change; see above */ +#endif /* CONFIG_NFSD_V3 */ -#include <linux/nfsd/nfsfh.h> +} svc_fh; enum nfsd_fsid { FSID_DEV = 0, @@ -215,4 +264,4 @@ fh_unlock(struct svc_fh *fhp) } } -#endif /* _LINUX_NFSD_FH_INT_H */ +#endif /* _LINUX_NFSD_NFSFH_H */ diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 9a4a5f9e7468..1879e43f2868 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -591,12 +591,6 @@ nfsd(void *vrqstp) nfsdstats.th_cnt++; mutex_unlock(&nfsd_mutex); - /* - * We want less throttling in balance_dirty_pages() so that nfs to - * localhost doesn't cause nfsd to lock up due to all the client's - * dirty pages. - */ - current->flags |= PF_LESS_THROTTLE; set_freezable(); /* diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index 9c769a47ac5a..1ac306b769df 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -214,7 +214,8 @@ nfssvc_decode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy) int nfssvc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p, struct nfsd_fhandle *args) { - if (!(p = decode_fh(p, &args->fh))) + p = decode_fh(p, &args->fh); + if (!p) return 0; return xdr_argsize_check(rqstp, p); } @@ -248,7 +249,8 @@ nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p, { unsigned int len; int v; - if (!(p = decode_fh(p, &args->fh))) + p = decode_fh(p, &args->fh); + if (!p) return 0; args->offset = ntohl(*p++); @@ -281,7 +283,8 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, unsigned int len, hdr, dlen; int v; - if (!(p = decode_fh(p, &args->fh))) + p = decode_fh(p, &args->fh); + if (!p) return 0; p++; /* beginoffset */ @@ -355,7 +358,8 @@ nfssvc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p, int nfssvc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd_readlinkargs *args) { - if (!(p = decode_fh(p, &args->fh))) + p = decode_fh(p, &args->fh); + if (!p) return 0; args->buffer = page_address(*(rqstp->rq_next_page++)); @@ -391,7 +395,8 @@ int nfssvc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd_readdirargs *args) { - if (!(p = decode_fh(p, &args->fh))) + p = decode_fh(p, &args->fh); + if (!p) return 0; args->cookie = ntohl(*p++); args->count = ntohl(*p++); diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 424d8f5f2317..374c66283ac5 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -37,7 +37,6 @@ #include <linux/idr.h> #include <linux/sunrpc/svc_xprt.h> -#include <linux/nfsd/nfsfh.h> #include "nfsfh.h" typedef struct { @@ -123,7 +122,7 @@ static inline struct nfs4_delegation *delegstateid(struct nfs4_stid *s) /* Maximum number of operations per session compound */ #define NFSD_MAX_OPS_PER_COMPOUND 16 /* Maximum session per slot cache size */ -#define NFSD_SLOT_CACHE_SIZE 1024 +#define NFSD_SLOT_CACHE_SIZE 2048 /* Maximum number of NFSD_SLOT_CACHE_SIZE slots per session */ #define NFSD_CACHE_SIZE_SLOTS_PER_SESSION 32 #define NFSD_MAX_MEM_PER_SESSION \ @@ -464,8 +463,6 @@ extern void nfs4_release_reclaim(struct nfsd_net *); extern struct nfs4_client_reclaim *nfsd4_find_reclaim_client(const char *recdir, struct nfsd_net *nn); extern __be32 nfs4_check_open_reclaim(clientid_t *clid, bool sessions, struct nfsd_net *nn); -extern void nfs4_free_openowner(struct nfs4_openowner *); -extern void nfs4_free_lockowner(struct nfs4_lockowner *); extern int set_callback_cred(void); extern void nfsd4_init_callback(struct nfsd4_callback *); extern void nfsd4_probe_callback(struct nfs4_client *clp); diff --git a/fs/nfsd/stats.c b/fs/nfsd/stats.c index 6d4521feb6e3..cd90878a76aa 100644 --- a/fs/nfsd/stats.c +++ b/fs/nfsd/stats.c @@ -24,7 +24,6 @@ #include <linux/seq_file.h> #include <linux/module.h> #include <linux/sunrpc/stats.h> -#include <linux/nfsd/stats.h> #include <net/net_namespace.h> #include "nfsd.h" diff --git a/fs/nfsd/stats.h b/fs/nfsd/stats.h new file mode 100644 index 000000000000..a5c944b771c6 --- /dev/null +++ b/fs/nfsd/stats.h @@ -0,0 +1,43 @@ +/* + * Statistics for NFS server. + * + * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de> + */ +#ifndef _NFSD_STATS_H +#define _NFSD_STATS_H + +#include <uapi/linux/nfsd/stats.h> + + +struct nfsd_stats { + unsigned int rchits; /* repcache hits */ + unsigned int rcmisses; /* repcache hits */ + unsigned int rcnocache; /* uncached reqs */ + unsigned int fh_stale; /* FH stale error */ + unsigned int fh_lookup; /* dentry cached */ + unsigned int fh_anon; /* anon file dentry returned */ + unsigned int fh_nocache_dir; /* filehandle not found in dcache */ + unsigned int fh_nocache_nondir; /* filehandle not found in dcache */ + unsigned int io_read; /* bytes returned to read requests */ + unsigned int io_write; /* bytes passed in write requests */ + unsigned int th_cnt; /* number of available threads */ + unsigned int th_usage[10]; /* number of ticks during which n perdeciles + * of available threads were in use */ + unsigned int th_fullcnt; /* number of times last free thread was used */ + unsigned int ra_size; /* size of ra cache */ + unsigned int ra_depth[11]; /* number of times ra entry was found that deep + * in the cache (10percentiles). [10] = not found */ +#ifdef CONFIG_NFSD_V4 + unsigned int nfs4_opcount[LAST_NFS4_OP + 1]; /* count of individual nfsv4 operations */ +#endif + +}; + + +extern struct nfsd_stats nfsdstats; +extern struct svc_stat nfsd_svcstats; + +void nfsd_stat_init(void); +void nfsd_stat_shutdown(void); + +#endif /* _NFSD_STATS_H */ diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 16f0673a423c..140c496f612c 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -820,55 +820,54 @@ static int nfsd_direct_splice_actor(struct pipe_inode_info *pipe, return __splice_from_pipe(pipe, sd, nfsd_splice_actor); } -static __be32 -nfsd_vfs_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, - loff_t offset, struct kvec *vec, int vlen, unsigned long *count) +__be32 nfsd_finish_read(struct file *file, unsigned long *count, int host_err) { - mm_segment_t oldfs; - __be32 err; - int host_err; - - err = nfserr_perm; - - if (file->f_op->splice_read && rqstp->rq_splice_ok) { - struct splice_desc sd = { - .len = 0, - .total_len = *count, - .pos = offset, - .u.data = rqstp, - }; - - rqstp->rq_next_page = rqstp->rq_respages + 1; - host_err = splice_direct_to_actor(file, &sd, nfsd_direct_splice_actor); - } else { - oldfs = get_fs(); - set_fs(KERNEL_DS); - host_err = vfs_readv(file, (struct iovec __user *)vec, vlen, &offset); - set_fs(oldfs); - } - if (host_err >= 0) { nfsdstats.io_read += host_err; *count = host_err; - err = 0; fsnotify_access(file); + return 0; } else - err = nfserrno(host_err); - return err; + return nfserrno(host_err); +} + +int nfsd_splice_read(struct svc_rqst *rqstp, + struct file *file, loff_t offset, unsigned long *count) +{ + struct splice_desc sd = { + .len = 0, + .total_len = *count, + .pos = offset, + .u.data = rqstp, + }; + int host_err; + + rqstp->rq_next_page = rqstp->rq_respages + 1; + host_err = splice_direct_to_actor(file, &sd, nfsd_direct_splice_actor); + return nfsd_finish_read(file, count, host_err); } -static void kill_suid(struct dentry *dentry) +int nfsd_readv(struct file *file, loff_t offset, struct kvec *vec, int vlen, + unsigned long *count) { - struct iattr ia; - ia.ia_valid = ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_KILL_PRIV; + mm_segment_t oldfs; + int host_err; - mutex_lock(&dentry->d_inode->i_mutex); - /* - * Note we call this on write, so notify_change will not - * encounter any conflicting delegations: - */ - notify_change(dentry, &ia, NULL); - mutex_unlock(&dentry->d_inode->i_mutex); + oldfs = get_fs(); + set_fs(KERNEL_DS); + host_err = vfs_readv(file, (struct iovec __user *)vec, vlen, &offset); + set_fs(oldfs); + return nfsd_finish_read(file, count, host_err); +} + +static __be32 +nfsd_vfs_read(struct svc_rqst *rqstp, struct file *file, + loff_t offset, struct kvec *vec, int vlen, unsigned long *count) +{ + if (file->f_op->splice_read && rqstp->rq_splice_ok) + return nfsd_splice_read(rqstp, file, offset, count); + else + return nfsd_readv(file, offset, vec, vlen, count); } /* @@ -922,6 +921,16 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, int stable = *stablep; int use_wgather; loff_t pos = offset; + unsigned int pflags = current->flags; + + if (rqstp->rq_local) + /* + * We want less throttling in balance_dirty_pages() + * and shrink_inactive_list() so that nfs to + * localhost doesn't cause nfsd to lock up due to all + * the client's dirty pages or its congested queue. + */ + current->flags |= PF_LESS_THROTTLE; dentry = file->f_path.dentry; inode = dentry->d_inode; @@ -942,10 +951,6 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, nfsdstats.io_write += host_err; fsnotify_modify(file); - /* clear setuid/setgid flag after write */ - if (inode->i_mode & (S_ISUID | S_ISGID)) - kill_suid(dentry); - if (stable) { if (use_wgather) host_err = wait_for_concurrent_writes(file); @@ -959,36 +964,33 @@ out_nfserr: err = 0; else err = nfserrno(host_err); + if (rqstp->rq_local) + tsk_restore_flags(current, pflags, PF_LESS_THROTTLE); return err; } -/* - * Read data from a file. count must contain the requested read count - * on entry. On return, *count contains the number of bytes actually read. - * N.B. After this call fhp needs an fh_put - */ -__be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp, - loff_t offset, struct kvec *vec, int vlen, unsigned long *count) +__be32 nfsd_get_tmp_read_open(struct svc_rqst *rqstp, struct svc_fh *fhp, + struct file **file, struct raparms **ra) { - struct file *file; struct inode *inode; - struct raparms *ra; __be32 err; - err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_READ, &file); + err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_READ, file); if (err) return err; - inode = file_inode(file); + inode = file_inode(*file); /* Get readahead parameters */ - ra = nfsd_get_raparms(inode->i_sb->s_dev, inode->i_ino); + *ra = nfsd_get_raparms(inode->i_sb->s_dev, inode->i_ino); - if (ra && ra->p_set) - file->f_ra = ra->p_ra; - - err = nfsd_vfs_read(rqstp, fhp, file, offset, vec, vlen, count); + if (*ra && (*ra)->p_set) + (*file)->f_ra = (*ra)->p_ra; + return nfs_ok; +} +void nfsd_put_tmp_read_open(struct file *file, struct raparms *ra) +{ /* Write back readahead params */ if (ra) { struct raparm_hbucket *rab = &raparm_hash[ra->p_hindex]; @@ -998,28 +1000,29 @@ __be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp, ra->p_count--; spin_unlock(&rab->pb_lock); } - nfsd_close(file); - return err; } -/* As above, but use the provided file descriptor. */ -__be32 -nfsd_read_file(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, - loff_t offset, struct kvec *vec, int vlen, - unsigned long *count) +/* + * Read data from a file. count must contain the requested read count + * on entry. On return, *count contains the number of bytes actually read. + * N.B. After this call fhp needs an fh_put + */ +__be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp, + loff_t offset, struct kvec *vec, int vlen, unsigned long *count) { - __be32 err; + struct file *file; + struct raparms *ra; + __be32 err; + + err = nfsd_get_tmp_read_open(rqstp, fhp, &file, &ra); + if (err) + return err; + + err = nfsd_vfs_read(rqstp, file, offset, vec, vlen, count); + + nfsd_put_tmp_read_open(file, ra); - if (file) { - err = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry, - NFSD_MAY_READ|NFSD_MAY_OWNER_OVERRIDE); - if (err) - goto out; - err = nfsd_vfs_read(rqstp, fhp, file, offset, vec, vlen, count); - } else /* Note file may still be NULL in NFSv4 special stateid case: */ - err = nfsd_read(rqstp, fhp, offset, vec, vlen, count); -out: return err; } diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h index fbe90bdb2214..91b6ae3f658b 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -70,10 +70,16 @@ __be32 nfsd_commit(struct svc_rqst *, struct svc_fh *, __be32 nfsd_open(struct svc_rqst *, struct svc_fh *, umode_t, int, struct file **); void nfsd_close(struct file *); +struct raparms; +__be32 nfsd_get_tmp_read_open(struct svc_rqst *, struct svc_fh *, + struct file **, struct raparms **); +void nfsd_put_tmp_read_open(struct file *, struct raparms *); +int nfsd_splice_read(struct svc_rqst *, + struct file *, loff_t, unsigned long *); +int nfsd_readv(struct file *, loff_t, struct kvec *, int, + unsigned long *); __be32 nfsd_read(struct svc_rqst *, struct svc_fh *, loff_t, struct kvec *, int, unsigned long *); -__be32 nfsd_read_file(struct svc_rqst *, struct svc_fh *, struct file *, - loff_t, struct kvec *, int, unsigned long *); __be32 nfsd_write(struct svc_rqst *, struct svc_fh *,struct file *, loff_t, struct kvec *,int, unsigned long *, int *); __be32 nfsd_readlink(struct svc_rqst *, struct svc_fh *, diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index 5ea7df305083..18cbb6d9c8a9 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -58,7 +58,7 @@ struct nfsd4_compound_state { /* For sessions DRC */ struct nfsd4_session *session; struct nfsd4_slot *slot; - __be32 *datap; + int data_offset; size_t iovlen; u32 minorversion; __be32 status; @@ -287,9 +287,8 @@ struct nfsd4_readdir { struct svc_fh * rd_fhp; /* response */ struct readdir_cd common; - __be32 * buffer; - int buflen; - __be32 * offset; + struct xdr_stream *xdr; + int cookie_offset; }; struct nfsd4_release_lockowner { @@ -506,9 +505,7 @@ struct nfsd4_compoundargs { struct nfsd4_compoundres { /* scratch variables for XDR encode */ - __be32 * p; - __be32 * end; - struct xdr_buf * xbuf; + struct xdr_stream xdr; struct svc_rqst * rqstp; u32 taglen; @@ -538,6 +535,9 @@ static inline bool nfsd4_last_compound_op(struct svc_rqst *rqstp) return argp->opcnt == resp->opcnt; } +int nfsd4_max_reply(struct svc_rqst *rqstp, struct nfsd4_op *op); +void warn_on_nonidempotent_op(struct nfsd4_op *op); + #define NFS4_SVC_XDRSIZE sizeof(struct nfsd4_compoundargs) static inline void @@ -563,10 +563,11 @@ int nfs4svc_encode_compoundres(struct svc_rqst *, __be32 *, struct nfsd4_compoundres *); __be32 nfsd4_check_resp_size(struct nfsd4_compoundres *, u32); void nfsd4_encode_operation(struct nfsd4_compoundres *, struct nfsd4_op *); -void nfsd4_encode_replay(struct nfsd4_compoundres *resp, struct nfsd4_op *op); -__be32 nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp, - struct dentry *dentry, __be32 **buffer, int countp, - u32 *bmval, struct svc_rqst *, int ignore_crossmnt); +void nfsd4_encode_replay(struct xdr_stream *xdr, struct nfsd4_op *op); +__be32 nfsd4_encode_fattr_to_buf(__be32 **p, int words, + struct svc_fh *fhp, struct svc_export *exp, + struct dentry *dentry, + u32 *bmval, struct svc_rqst *, int ignore_crossmnt); extern __be32 nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *, struct nfsd4_setclientid *setclid); diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 0b18776b075e..6152cbe353e8 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1215,7 +1215,7 @@ xfs_ioctl_setattr( * cleared upon successful return from chown() */ if ((ip->i_d.di_mode & (S_ISUID|S_ISGID)) && - !inode_capable(VFS_I(ip), CAP_FSETID)) + !capable_wrt_inode_uidgid(VFS_I(ip), CAP_FSETID)) ip->i_d.di_mode &= ~(S_ISUID|S_ISGID); /* |