From 0b7c01533aa9f4a228d07d2768d084acb3a387bc Mon Sep 17 00:00:00 2001 From: Fred Isaman Date: Fri, 20 Apr 2012 14:47:39 -0400 Subject: NFS: add a struct nfs_commit_data to replace nfs_write_data in commits Commits don't need the vectors of pages, etc. that writes do. Split out a separate structure for the commit operation. Signed-off-by: Fred Isaman Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 4 ++-- include/linux/nfs_xdr.h | 45 ++++++++++++++++++++++++++++++++++++++++++--- 2 files changed, 44 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 52a1bdb4ee2b..d5d68f322bf0 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -552,8 +552,8 @@ extern int nfs_wb_page(struct inode *inode, struct page* page); extern int nfs_wb_page_cancel(struct inode *inode, struct page* page); #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4) extern int nfs_commit_inode(struct inode *, int); -extern struct nfs_write_data *nfs_commitdata_alloc(void); -extern void nfs_commit_free(struct nfs_write_data *wdata); +extern struct nfs_commit_data *nfs_commitdata_alloc(void); +extern void nfs_commit_free(struct nfs_commit_data *data); #else static inline int nfs_commit_inode(struct inode *inode, int how) diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 7ba3551a0414..8fb036a0d489 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -518,6 +518,24 @@ struct nfs_writeres { struct nfs4_sequence_res seq_res; }; +/* + * Arguments to the commit call. + */ +struct nfs_commitargs { + struct nfs_fh *fh; + __u64 offset; + __u32 count; + const u32 *bitmask; + struct nfs4_sequence_args seq_args; +}; + +struct nfs_commitres { + struct nfs_fattr *fattr; + struct nfs_writeverf *verf; + const struct nfs_server *server; + struct nfs4_sequence_res seq_res; +}; + /* * Common arguments to the unlink call */ @@ -1171,6 +1189,8 @@ struct nfs_read_data { struct page *page_array[NFS_PAGEVEC_SIZE]; }; +struct nfs_direct_req; + struct nfs_write_data { struct rpc_task task; struct inode *inode; @@ -1186,7 +1206,6 @@ struct nfs_write_data { struct nfs_writeres res; /* result struct */ struct pnfs_layout_segment *lseg; struct nfs_client *ds_clp; /* pNFS data server */ - int ds_commit_index; const struct rpc_call_ops *mds_ops; int (*write_done_cb) (struct rpc_task *task, struct nfs_write_data *data); #ifdef CONFIG_NFS_V4 @@ -1197,6 +1216,25 @@ struct nfs_write_data { struct page *page_array[NFS_PAGEVEC_SIZE]; }; +struct nfs_commit_data { + struct rpc_task task; + struct inode *inode; + struct rpc_cred *cred; + struct nfs_fattr fattr; + struct nfs_writeverf verf; + struct list_head pages; /* Coalesced requests we wish to flush */ + struct list_head list; /* lists of struct nfs_write_data */ + struct nfs_direct_req *dreq; /* O_DIRECT request */ + struct nfs_commitargs args; /* argument struct */ + struct nfs_commitres res; /* result struct */ + struct nfs_open_context *context; + struct pnfs_layout_segment *lseg; + struct nfs_client *ds_clp; /* pNFS data server */ + int ds_commit_index; + const struct rpc_call_ops *mds_ops; + int (*commit_done_cb) (struct rpc_task *task, struct nfs_commit_data *data); +}; + struct nfs_unlinkdata { struct hlist_node list; struct nfs_removeargs args; @@ -1277,8 +1315,9 @@ struct nfs_rpc_ops { void (*write_setup) (struct nfs_write_data *, struct rpc_message *); void (*write_rpc_prepare)(struct rpc_task *, struct nfs_write_data *); int (*write_done) (struct rpc_task *, struct nfs_write_data *); - void (*commit_setup) (struct nfs_write_data *, struct rpc_message *); - int (*commit_done) (struct rpc_task *, struct nfs_write_data *); + void (*commit_setup) (struct nfs_commit_data *, struct rpc_message *); + void (*commit_rpc_prepare)(struct rpc_task *, struct nfs_commit_data *); + int (*commit_done) (struct rpc_task *, struct nfs_commit_data *); int (*lock)(struct file *, int, struct file_lock *); int (*lock_check_bounds)(const struct file_lock *); void (*clear_acl_cache)(struct inode *); -- cgit v1.2.3 From cd841605f7a721878d8a2d1362484723d8abf569 Mon Sep 17 00:00:00 2001 From: Fred Isaman Date: Fri, 20 Apr 2012 14:47:44 -0400 Subject: NFS: create common nfs_pgio_header for both read and write In order to avoid duplicating all the data in nfs_read_data whenever we split it up into multiple RPC calls (either due to a short read result or due to rsize < PAGE_SIZE), we split out the bits that are the same per RPC call into a separate "header" structure. The goal this patch moves towards is to have a single header refcounted by several rpc_data structures. Thus, want to always refer from rpc_data to the header, and not the other way. This patch comes close to that ideal, but the directio code currently needs some special casing, isolated in the nfs_direct_[read_write]hdr_release() functions. This will be dealt with in a future patch. Signed-off-by: Fred Isaman Signed-off-by: Trond Myklebust --- fs/nfs/blocklayout/blocklayout.c | 79 +++++++++++++++-------------- fs/nfs/direct.c | 73 ++++++++++++++++++--------- fs/nfs/internal.h | 4 ++ fs/nfs/nfs3proc.c | 14 ++++-- fs/nfs/nfs4filelayout.c | 40 ++++++++------- fs/nfs/nfs4proc.c | 44 ++++++++++------- fs/nfs/objlayout/objio_osd.c | 16 +++--- fs/nfs/objlayout/objlayout.c | 19 ++++--- fs/nfs/pnfs.c | 102 ++++++++++++++++++++++---------------- fs/nfs/proc.c | 10 ++-- fs/nfs/read.c | 89 +++++++++++++++++++-------------- fs/nfs/write.c | 104 ++++++++++++++++++++++----------------- include/linux/nfs_fs.h | 12 ----- include/linux/nfs_xdr.h | 48 ++++++++++-------- 14 files changed, 376 insertions(+), 278 deletions(-) (limited to 'include') diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index 7f6a23f0244e..7a482517f4c6 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -187,7 +187,6 @@ static void bl_end_io_read(struct bio *bio, int err) struct parallel_io *par = bio->bi_private; const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1; - struct nfs_read_data *rdata = (struct nfs_read_data *)par->data; do { struct page *page = bvec->bv_page; @@ -198,9 +197,12 @@ static void bl_end_io_read(struct bio *bio, int err) SetPageUptodate(page); } while (bvec >= bio->bi_io_vec); if (!uptodate) { - if (!rdata->pnfs_error) - rdata->pnfs_error = -EIO; - pnfs_set_lo_fail(rdata->lseg); + struct nfs_read_data *rdata = par->data; + struct nfs_pgio_header *header = rdata->header; + + if (!header->pnfs_error) + header->pnfs_error = -EIO; + pnfs_set_lo_fail(header->lseg); } bio_put(bio); put_parallel(par); @@ -221,7 +223,7 @@ bl_end_par_io_read(void *data, int unused) { struct nfs_read_data *rdata = data; - rdata->task.tk_status = rdata->pnfs_error; + rdata->task.tk_status = rdata->header->pnfs_error; INIT_WORK(&rdata->task.u.tk_work, bl_read_cleanup); schedule_work(&rdata->task.u.tk_work); } @@ -229,6 +231,7 @@ bl_end_par_io_read(void *data, int unused) static enum pnfs_try_status bl_read_pagelist(struct nfs_read_data *rdata) { + struct nfs_pgio_header *header = rdata->header; int i, hole; struct bio *bio = NULL; struct pnfs_block_extent *be = NULL, *cow_read = NULL; @@ -256,10 +259,10 @@ bl_read_pagelist(struct nfs_read_data *rdata) bl_put_extent(cow_read); bio = bl_submit_bio(READ, bio); /* Get the next one */ - be = bl_find_get_extent(BLK_LSEG2EXT(rdata->lseg), + be = bl_find_get_extent(BLK_LSEG2EXT(header->lseg), isect, &cow_read); if (!be) { - rdata->pnfs_error = -EIO; + header->pnfs_error = -EIO; goto out; } extent_length = be->be_length - @@ -286,7 +289,7 @@ bl_read_pagelist(struct nfs_read_data *rdata) isect, pages[i], be_read, bl_end_io_read, par); if (IS_ERR(bio)) { - rdata->pnfs_error = PTR_ERR(bio); + header->pnfs_error = PTR_ERR(bio); bio = NULL; goto out; } @@ -294,9 +297,9 @@ bl_read_pagelist(struct nfs_read_data *rdata) isect += PAGE_CACHE_SECTORS; extent_length -= PAGE_CACHE_SECTORS; } - if ((isect << SECTOR_SHIFT) >= rdata->inode->i_size) { + if ((isect << SECTOR_SHIFT) >= header->inode->i_size) { rdata->res.eof = 1; - rdata->res.count = rdata->inode->i_size - f_offset; + rdata->res.count = header->inode->i_size - f_offset; } else { rdata->res.count = (isect << SECTOR_SHIFT) - f_offset; } @@ -345,7 +348,6 @@ static void bl_end_io_write_zero(struct bio *bio, int err) struct parallel_io *par = bio->bi_private; const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1; - struct nfs_write_data *wdata = (struct nfs_write_data *)par->data; do { struct page *page = bvec->bv_page; @@ -358,9 +360,12 @@ static void bl_end_io_write_zero(struct bio *bio, int err) } while (bvec >= bio->bi_io_vec); if (unlikely(!uptodate)) { - if (!wdata->pnfs_error) - wdata->pnfs_error = -EIO; - pnfs_set_lo_fail(wdata->lseg); + struct nfs_write_data *data = par->data; + struct nfs_pgio_header *header = data->header; + + if (!header->pnfs_error) + header->pnfs_error = -EIO; + pnfs_set_lo_fail(header->lseg); } bio_put(bio); put_parallel(par); @@ -370,12 +375,13 @@ 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 *wdata = (struct nfs_write_data *)par->data; + struct nfs_write_data *data = par->data; + struct nfs_pgio_header *header = data->header; if (!uptodate) { - if (!wdata->pnfs_error) - wdata->pnfs_error = -EIO; - pnfs_set_lo_fail(wdata->lseg); + if (!header->pnfs_error) + header->pnfs_error = -EIO; + pnfs_set_lo_fail(header->lseg); } bio_put(bio); put_parallel(par); @@ -391,9 +397,9 @@ static void bl_write_cleanup(struct work_struct *work) dprintk("%s enter\n", __func__); task = container_of(work, struct rpc_task, u.tk_work); wdata = container_of(task, struct nfs_write_data, task); - if (likely(!wdata->pnfs_error)) { + if (likely(!wdata->header->pnfs_error)) { /* Marks for LAYOUTCOMMIT */ - mark_extents_written(BLK_LSEG2EXT(wdata->lseg), + mark_extents_written(BLK_LSEG2EXT(wdata->header->lseg), wdata->args.offset, wdata->args.count); } pnfs_ld_write_done(wdata); @@ -404,12 +410,12 @@ static void bl_end_par_io_write(void *data, int num_se) { struct nfs_write_data *wdata = data; - if (unlikely(wdata->pnfs_error)) { - bl_free_short_extents(&BLK_LSEG2EXT(wdata->lseg)->bl_inval, + if (unlikely(wdata->header->pnfs_error)) { + bl_free_short_extents(&BLK_LSEG2EXT(wdata->header->lseg)->bl_inval, num_se); } - wdata->task.tk_status = wdata->pnfs_error; + wdata->task.tk_status = wdata->header->pnfs_error; wdata->verf.committed = NFS_FILE_SYNC; INIT_WORK(&wdata->task.u.tk_work, bl_write_cleanup); schedule_work(&wdata->task.u.tk_work); @@ -540,6 +546,7 @@ check_page: static enum pnfs_try_status bl_write_pagelist(struct nfs_write_data *wdata, int sync) { + struct nfs_pgio_header *header = wdata->header; int i, ret, npg_zero, pg_index, last = 0; struct bio *bio = NULL; struct pnfs_block_extent *be = NULL, *cow_read = NULL; @@ -552,7 +559,7 @@ bl_write_pagelist(struct nfs_write_data *wdata, int sync) pgoff_t index; u64 temp; int npg_per_block = - NFS_SERVER(wdata->inode)->pnfs_blksize >> PAGE_CACHE_SHIFT; + NFS_SERVER(header->inode)->pnfs_blksize >> PAGE_CACHE_SHIFT; dprintk("%s enter, %Zu@%lld\n", __func__, count, offset); /* At this point, wdata->pages is a (sequential) list of nfs_pages. @@ -566,7 +573,7 @@ bl_write_pagelist(struct nfs_write_data *wdata, int sync) /* At this point, have to be more careful with error handling */ isect = (sector_t) ((offset & (long)PAGE_CACHE_MASK) >> SECTOR_SHIFT); - be = bl_find_get_extent(BLK_LSEG2EXT(wdata->lseg), isect, &cow_read); + be = bl_find_get_extent(BLK_LSEG2EXT(header->lseg), isect, &cow_read); if (!be || !is_writable(be, isect)) { dprintk("%s no matching extents!\n", __func__); goto out_mds; @@ -597,10 +604,10 @@ fill_invalid_ext: dprintk("%s zero %dth page: index %lu isect %llu\n", __func__, npg_zero, index, (unsigned long long)isect); - page = bl_find_get_zeroing_page(wdata->inode, index, + page = bl_find_get_zeroing_page(header->inode, index, cow_read); if (unlikely(IS_ERR(page))) { - wdata->pnfs_error = PTR_ERR(page); + header->pnfs_error = PTR_ERR(page); goto out; } else if (page == NULL) goto next_page; @@ -612,7 +619,7 @@ fill_invalid_ext: __func__, ret); end_page_writeback(page); page_cache_release(page); - wdata->pnfs_error = ret; + header->pnfs_error = ret; goto out; } if (likely(!bl_push_one_short_extent(be->be_inval))) @@ -620,11 +627,11 @@ fill_invalid_ext: else { end_page_writeback(page); page_cache_release(page); - wdata->pnfs_error = -ENOMEM; + header->pnfs_error = -ENOMEM; goto out; } /* FIXME: This should be done in bi_end_io */ - mark_extents_written(BLK_LSEG2EXT(wdata->lseg), + mark_extents_written(BLK_LSEG2EXT(header->lseg), page->index << PAGE_CACHE_SHIFT, PAGE_CACHE_SIZE); @@ -632,7 +639,7 @@ fill_invalid_ext: isect, page, be, bl_end_io_write_zero, par); if (IS_ERR(bio)) { - wdata->pnfs_error = PTR_ERR(bio); + header->pnfs_error = PTR_ERR(bio); bio = NULL; goto out; } @@ -653,10 +660,10 @@ next_page: bl_put_extent(be); bio = bl_submit_bio(WRITE, bio); /* Get the next one */ - be = bl_find_get_extent(BLK_LSEG2EXT(wdata->lseg), + be = bl_find_get_extent(BLK_LSEG2EXT(header->lseg), isect, NULL); if (!be || !is_writable(be, isect)) { - wdata->pnfs_error = -EINVAL; + header->pnfs_error = -EINVAL; goto out; } if (be->be_state == PNFS_BLOCK_INVALID_DATA) { @@ -664,7 +671,7 @@ next_page: be->be_inval))) par->bse_count++; else { - wdata->pnfs_error = -ENOMEM; + header->pnfs_error = -ENOMEM; goto out; } } @@ -677,7 +684,7 @@ next_page: if (unlikely(ret)) { dprintk("%s bl_mark_sectors_init fail %d\n", __func__, ret); - wdata->pnfs_error = ret; + header->pnfs_error = ret; goto out; } } @@ -685,7 +692,7 @@ next_page: isect, pages[i], be, bl_end_io_write, par); if (IS_ERR(bio)) { - wdata->pnfs_error = PTR_ERR(bio); + header->pnfs_error = PTR_ERR(bio); bio = NULL; goto out; } diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index fb7fbaa79c20..56176af1436f 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -242,7 +242,7 @@ static void nfs_direct_read_release(void *calldata) { struct nfs_read_data *data = calldata; - struct nfs_direct_req *dreq = (struct nfs_direct_req *) data->req; + struct nfs_direct_req *dreq = (struct nfs_direct_req *)data->header->req; int status = data->task.tk_status; spin_lock(&dreq->lock); @@ -269,6 +269,15 @@ static const struct rpc_call_ops nfs_read_direct_ops = { .rpc_release = nfs_direct_read_release, }; +static void nfs_direct_readhdr_release(struct nfs_read_header *rhdr) +{ + struct nfs_read_data *data = &rhdr->rpc_data; + + if (data->pagevec != data->page_array) + kfree(data->pagevec); + nfs_readhdr_free(&rhdr->header); +} + /* * For each rsize'd chunk of the user's buffer, dispatch an NFS READ * operation. If nfs_readdata_alloc() or get_user_pages() fails, @@ -301,6 +310,7 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_direct_req *dreq, ssize_t started = 0; do { + struct nfs_read_header *rhdr; struct nfs_read_data *data; size_t bytes; @@ -308,23 +318,24 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_direct_req *dreq, bytes = min(rsize,count); result = -ENOMEM; - data = nfs_readdata_alloc(nfs_page_array_len(pgbase, bytes)); - if (unlikely(!data)) + rhdr = nfs_readhdr_alloc(nfs_page_array_len(pgbase, bytes)); + if (unlikely(!rhdr)) break; + data = &rhdr->rpc_data; down_read(¤t->mm->mmap_sem); result = get_user_pages(current, current->mm, user_addr, data->npages, 1, 0, data->pagevec, NULL); up_read(¤t->mm->mmap_sem); if (result < 0) { - nfs_readdata_free(data); + nfs_direct_readhdr_release(rhdr); break; } if ((unsigned)result < data->npages) { bytes = result * PAGE_SIZE; if (bytes <= pgbase) { nfs_direct_release_pages(data->pagevec, result); - nfs_readdata_free(data); + nfs_direct_readhdr_release(rhdr); break; } bytes -= pgbase; @@ -333,9 +344,9 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_direct_req *dreq, get_dreq(dreq); - data->req = (struct nfs_page *) dreq; - data->inode = inode; - data->cred = msg.rpc_cred; + rhdr->header.req = (struct nfs_page *) dreq; + rhdr->header.inode = inode; + rhdr->header.cred = msg.rpc_cred; data->args.fh = NFS_FH(inode); data->args.context = get_nfs_open_context(ctx); data->args.lock_context = dreq->l_ctx; @@ -447,13 +458,23 @@ out: return result; } +static void nfs_direct_writehdr_release(struct nfs_write_header *whdr) +{ + struct nfs_write_data *data = &whdr->rpc_data; + + if (data->pagevec != data->page_array) + kfree(data->pagevec); + nfs_writehdr_free(&whdr->header); +} + static void nfs_direct_free_writedata(struct nfs_direct_req *dreq) { while (!list_empty(&dreq->rewrite_list)) { - struct nfs_write_data *data = list_entry(dreq->rewrite_list.next, struct nfs_write_data, pages); - list_del(&data->pages); - nfs_direct_release_pages(data->pagevec, data->npages); - nfs_writedata_free(data); + struct nfs_pgio_header *hdr = list_entry(dreq->rewrite_list.next, struct nfs_pgio_header, pages); + struct nfs_write_header *whdr = container_of(hdr, struct nfs_write_header, header); + list_del(&hdr->pages); + nfs_direct_release_pages(whdr->rpc_data.pagevec, whdr->rpc_data.npages); + nfs_direct_writehdr_release(whdr); } } @@ -463,6 +484,7 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) struct inode *inode = dreq->inode; struct list_head *p; struct nfs_write_data *data; + struct nfs_pgio_header *hdr; struct rpc_task *task; struct rpc_message msg = { .rpc_cred = dreq->ctx->cred, @@ -479,7 +501,8 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) get_dreq(dreq); list_for_each(p, &dreq->rewrite_list) { - data = list_entry(p, struct nfs_write_data, pages); + hdr = list_entry(p, struct nfs_pgio_header, pages); + data = &(container_of(hdr, struct nfs_write_header, header))->rpc_data; get_dreq(dreq); @@ -652,7 +675,8 @@ static void nfs_direct_write_result(struct rpc_task *task, void *calldata) static void nfs_direct_write_release(void *calldata) { struct nfs_write_data *data = calldata; - struct nfs_direct_req *dreq = (struct nfs_direct_req *) data->req; + struct nfs_pgio_header *hdr = data->header; + struct nfs_direct_req *dreq = (struct nfs_direct_req *) hdr->req; int status = data->task.tk_status; spin_lock(&dreq->lock); @@ -684,7 +708,7 @@ out_unlock: spin_unlock(&dreq->lock); if (put_dreq(dreq)) - nfs_direct_write_complete(dreq, data->inode); + nfs_direct_write_complete(dreq, hdr->inode); } static const struct rpc_call_ops nfs_write_direct_ops = { @@ -725,6 +749,7 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_direct_req *dreq, ssize_t started = 0; do { + struct nfs_write_header *whdr; struct nfs_write_data *data; size_t bytes; @@ -732,23 +757,25 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_direct_req *dreq, bytes = min(wsize,count); result = -ENOMEM; - data = nfs_writedata_alloc(nfs_page_array_len(pgbase, bytes)); - if (unlikely(!data)) + whdr = nfs_writehdr_alloc(nfs_page_array_len(pgbase, bytes)); + if (unlikely(!whdr)) break; + data = &whdr->rpc_data; + down_read(¤t->mm->mmap_sem); result = get_user_pages(current, current->mm, user_addr, data->npages, 0, 0, data->pagevec, NULL); up_read(¤t->mm->mmap_sem); if (result < 0) { - nfs_writedata_free(data); + nfs_direct_writehdr_release(whdr); break; } if ((unsigned)result < data->npages) { bytes = result * PAGE_SIZE; if (bytes <= pgbase) { nfs_direct_release_pages(data->pagevec, result); - nfs_writedata_free(data); + nfs_direct_writehdr_release(whdr); break; } bytes -= pgbase; @@ -757,11 +784,11 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_direct_req *dreq, get_dreq(dreq); - list_move_tail(&data->pages, &dreq->rewrite_list); + list_move_tail(&whdr->header.pages, &dreq->rewrite_list); - data->req = (struct nfs_page *) dreq; - data->inode = inode; - data->cred = msg.rpc_cred; + whdr->header.req = (struct nfs_page *) dreq; + whdr->header.inode = inode; + whdr->header.cred = msg.rpc_cred; data->args.fh = NFS_FH(inode); data->args.context = ctx; data->args.lock_context = dreq->l_ctx; diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 650127fd24bb..7dc9be1a6e1a 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -296,6 +296,8 @@ extern int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh); struct nfs_pageio_descriptor; /* read.c */ +extern struct nfs_read_header *nfs_readhdr_alloc(unsigned int npages); +extern void nfs_readhdr_free(struct nfs_pgio_header *hdr); extern int nfs_initiate_read(struct rpc_clnt *clnt, struct nfs_read_data *data, const struct rpc_call_ops *call_ops); @@ -309,6 +311,8 @@ extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio); extern void nfs_readdata_release(struct nfs_read_data *rdata); /* write.c */ +extern struct nfs_write_header *nfs_writehdr_alloc(unsigned int npages); +extern void nfs_writehdr_free(struct nfs_pgio_header *hdr); extern int nfs_generic_flush(struct nfs_pageio_descriptor *desc, struct list_head *head); extern void nfs_pageio_init_write_mds(struct nfs_pageio_descriptor *pgio, diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index b1daca7f0f7b..56dcefc2f3f7 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -811,11 +811,13 @@ nfs3_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle, static int nfs3_read_done(struct rpc_task *task, struct nfs_read_data *data) { - if (nfs3_async_handle_jukebox(task, data->inode)) + struct inode *inode = data->header->inode; + + if (nfs3_async_handle_jukebox(task, inode)) return -EAGAIN; - nfs_invalidate_atime(data->inode); - nfs_refresh_inode(data->inode, &data->fattr); + nfs_invalidate_atime(inode); + nfs_refresh_inode(inode, &data->fattr); return 0; } @@ -831,10 +833,12 @@ static void nfs3_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_da static int nfs3_write_done(struct rpc_task *task, struct nfs_write_data *data) { - if (nfs3_async_handle_jukebox(task, data->inode)) + struct inode *inode = data->header->inode; + + if (nfs3_async_handle_jukebox(task, inode)) return -EAGAIN; if (task->tk_status >= 0) - nfs_post_op_update_inode_force_wcc(data->inode, data->res.fattr); + nfs_post_op_update_inode_force_wcc(inode, data->res.fattr); return 0; } diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c index c536328557cb..ad1d68013a5b 100644 --- a/fs/nfs/nfs4filelayout.c +++ b/fs/nfs/nfs4filelayout.c @@ -148,6 +148,7 @@ wait_on_recovery: static int filelayout_read_done_cb(struct rpc_task *task, struct nfs_read_data *data) { + struct nfs_pgio_header *hdr = data->header; int reset = 0; dprintk("%s DS read\n", __func__); @@ -157,7 +158,7 @@ static int filelayout_read_done_cb(struct rpc_task *task, dprintk("%s calling restart ds_clp %p ds_clp->cl_session %p\n", __func__, data->ds_clp, data->ds_clp->cl_session); if (reset) { - pnfs_set_lo_fail(data->lseg); + pnfs_set_lo_fail(hdr->lseg); nfs4_reset_read(task, data); } rpc_restart_call_prepare(task); @@ -175,13 +176,15 @@ static int filelayout_read_done_cb(struct rpc_task *task, static void filelayout_set_layoutcommit(struct nfs_write_data *wdata) { - if (FILELAYOUT_LSEG(wdata->lseg)->commit_through_mds || + struct nfs_pgio_header *hdr = wdata->header; + + if (FILELAYOUT_LSEG(hdr->lseg)->commit_through_mds || wdata->res.verf->committed == NFS_FILE_SYNC) return; pnfs_set_layoutcommit(wdata); - dprintk("%s ionde %lu pls_end_pos %lu\n", __func__, wdata->inode->i_ino, - (unsigned long) NFS_I(wdata->inode)->layout->plh_lwb); + dprintk("%s ionde %lu pls_end_pos %lu\n", __func__, hdr->inode->i_ino, + (unsigned long) NFS_I(hdr->inode)->layout->plh_lwb); } /* @@ -210,27 +213,28 @@ static void filelayout_read_call_done(struct rpc_task *task, void *data) dprintk("--> %s task->tk_status %d\n", __func__, task->tk_status); /* Note this may cause RPC to be resent */ - rdata->mds_ops->rpc_call_done(task, data); + rdata->header->mds_ops->rpc_call_done(task, data); } static void filelayout_read_count_stats(struct rpc_task *task, void *data) { struct nfs_read_data *rdata = data; - rpc_count_iostats(task, NFS_SERVER(rdata->inode)->client->cl_metrics); + 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; - put_lseg(rdata->lseg); - rdata->mds_ops->rpc_release(data); + put_lseg(rdata->header->lseg); + rdata->header->mds_ops->rpc_release(data); } static int filelayout_write_done_cb(struct rpc_task *task, struct nfs_write_data *data) { + struct nfs_pgio_header *hdr = data->header; int reset = 0; if (filelayout_async_handle_error(task, data->args.context->state, @@ -238,7 +242,7 @@ static int filelayout_write_done_cb(struct rpc_task *task, dprintk("%s calling restart ds_clp %p ds_clp->cl_session %p\n", __func__, data->ds_clp, data->ds_clp->cl_session); if (reset) { - pnfs_set_lo_fail(data->lseg); + pnfs_set_lo_fail(hdr->lseg); nfs4_reset_write(task, data); } rpc_restart_call_prepare(task); @@ -297,22 +301,22 @@ static void filelayout_write_call_done(struct rpc_task *task, void *data) struct nfs_write_data *wdata = data; /* Note this may cause RPC to be resent */ - wdata->mds_ops->rpc_call_done(task, data); + wdata->header->mds_ops->rpc_call_done(task, data); } static void filelayout_write_count_stats(struct rpc_task *task, void *data) { struct nfs_write_data *wdata = data; - rpc_count_iostats(task, NFS_SERVER(wdata->inode)->client->cl_metrics); + 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; - put_lseg(wdata->lseg); - wdata->mds_ops->rpc_release(data); + put_lseg(wdata->header->lseg); + wdata->header->mds_ops->rpc_release(data); } static void filelayout_commit_prepare(struct rpc_task *task, void *data) @@ -377,7 +381,8 @@ static const struct rpc_call_ops filelayout_commit_call_ops = { static enum pnfs_try_status filelayout_read_pagelist(struct nfs_read_data *data) { - struct pnfs_layout_segment *lseg = data->lseg; + struct nfs_pgio_header *hdr = data->header; + struct pnfs_layout_segment *lseg = hdr->lseg; struct nfs4_pnfs_ds *ds; loff_t offset = data->args.offset; u32 j, idx; @@ -385,7 +390,7 @@ filelayout_read_pagelist(struct nfs_read_data *data) int status; dprintk("--> %s ino %lu pgbase %u req %Zu@%llu\n", - __func__, data->inode->i_ino, + __func__, hdr->inode->i_ino, data->args.pgbase, (size_t)data->args.count, offset); if (test_bit(NFS_DEVICEID_INVALID, &FILELAYOUT_DEVID_NODE(lseg)->flags)) @@ -423,7 +428,8 @@ filelayout_read_pagelist(struct nfs_read_data *data) static enum pnfs_try_status filelayout_write_pagelist(struct nfs_write_data *data, int sync) { - struct pnfs_layout_segment *lseg = data->lseg; + struct nfs_pgio_header *hdr = data->header; + struct pnfs_layout_segment *lseg = hdr->lseg; struct nfs4_pnfs_ds *ds; loff_t offset = data->args.offset; u32 j, idx; @@ -445,7 +451,7 @@ filelayout_write_pagelist(struct nfs_write_data *data, int sync) return PNFS_NOT_ATTEMPTED; } dprintk("%s ino %lu sync %d req %Zu@%llu DS: %s\n", __func__, - data->inode->i_ino, sync, (size_t) data->args.count, offset, + hdr->inode->i_ino, sync, (size_t) data->args.count, offset, ds->ds_remotestr); data->write_done_cb = filelayout_write_done_cb; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index cc04b6e409ed..5375862075de 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3336,12 +3336,12 @@ static int nfs4_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle, void __nfs4_read_done_cb(struct nfs_read_data *data) { - nfs_invalidate_atime(data->inode); + nfs_invalidate_atime(data->header->inode); } static int nfs4_read_done_cb(struct rpc_task *task, struct nfs_read_data *data) { - struct nfs_server *server = NFS_SERVER(data->inode); + struct nfs_server *server = NFS_SERVER(data->header->inode); if (nfs4_async_handle_error(task, server, data->args.context->state) == -EAGAIN) { rpc_restart_call_prepare(task); @@ -3376,7 +3376,7 @@ static void nfs4_proc_read_setup(struct nfs_read_data *data, struct rpc_message static void nfs4_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_data *data) { - if (nfs4_setup_sequence(NFS_SERVER(data->inode), + if (nfs4_setup_sequence(NFS_SERVER(data->header->inode), &data->args.seq_args, &data->res.seq_res, task)) @@ -3387,22 +3387,25 @@ static void nfs4_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_da /* Reset the the nfs_read_data to send the read to the MDS. */ void nfs4_reset_read(struct rpc_task *task, struct nfs_read_data *data) { + struct nfs_pgio_header *hdr = data->header; + struct inode *inode = hdr->inode; + dprintk("%s Reset task for i/o through\n", __func__); - put_lseg(data->lseg); - data->lseg = NULL; + put_lseg(hdr->lseg); + hdr->lseg = NULL; + data->ds_clp = NULL; /* offsets will differ in the dense stripe case */ data->args.offset = data->mds_offset; - data->ds_clp = NULL; - data->args.fh = NFS_FH(data->inode); + data->args.fh = NFS_FH(inode); data->read_done_cb = nfs4_read_done_cb; - task->tk_ops = data->mds_ops; - rpc_task_reset_client(task, NFS_CLIENT(data->inode)); + task->tk_ops = hdr->mds_ops; + rpc_task_reset_client(task, NFS_CLIENT(inode)); } EXPORT_SYMBOL_GPL(nfs4_reset_read); static int nfs4_write_done_cb(struct rpc_task *task, struct nfs_write_data *data) { - struct inode *inode = data->inode; + struct inode *inode = data->header->inode; if (nfs4_async_handle_error(task, NFS_SERVER(inode), data->args.context->state) == -EAGAIN) { rpc_restart_call_prepare(task); @@ -3426,25 +3429,28 @@ static int nfs4_write_done(struct rpc_task *task, struct nfs_write_data *data) /* Reset the the nfs_write_data to send the write to the MDS. */ void nfs4_reset_write(struct rpc_task *task, struct nfs_write_data *data) { + struct nfs_pgio_header *hdr = data->header; + struct inode *inode = hdr->inode; + dprintk("%s Reset task for i/o through\n", __func__); - put_lseg(data->lseg); - data->lseg = NULL; - data->ds_clp = NULL; + put_lseg(hdr->lseg); + hdr->lseg = NULL; + data->ds_clp = NULL; data->write_done_cb = nfs4_write_done_cb; - data->args.fh = NFS_FH(data->inode); + data->args.fh = NFS_FH(inode); data->args.bitmask = data->res.server->cache_consistency_bitmask; data->args.offset = data->mds_offset; data->res.fattr = &data->fattr; - task->tk_ops = data->mds_ops; - rpc_task_reset_client(task, NFS_CLIENT(data->inode)); + task->tk_ops = hdr->mds_ops; + rpc_task_reset_client(task, NFS_CLIENT(inode)); } EXPORT_SYMBOL_GPL(nfs4_reset_write); static void nfs4_proc_write_setup(struct nfs_write_data *data, struct rpc_message *msg) { - struct nfs_server *server = NFS_SERVER(data->inode); + struct nfs_server *server = NFS_SERVER(data->header->inode); - if (data->lseg) { + if (data->header->lseg) { data->args.bitmask = NULL; data->res.fattr = NULL; } else @@ -3460,7 +3466,7 @@ static void nfs4_proc_write_setup(struct nfs_write_data *data, struct rpc_messag static void nfs4_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_data *data) { - if (nfs4_setup_sequence(NFS_SERVER(data->inode), + if (nfs4_setup_sequence(NFS_SERVER(data->header->inode), &data->args.seq_args, &data->res.seq_res, task)) diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c index 4bff4a3dab46..fbf4874ec252 100644 --- a/fs/nfs/objlayout/objio_osd.c +++ b/fs/nfs/objlayout/objio_osd.c @@ -440,11 +440,12 @@ static void _read_done(struct ore_io_state *ios, void *private) int objio_read_pagelist(struct nfs_read_data *rdata) { + struct nfs_pgio_header *hdr = rdata->header; struct objio_state *objios; int ret; - ret = objio_alloc_io_state(NFS_I(rdata->inode)->layout, true, - rdata->lseg, rdata->args.pages, rdata->args.pgbase, + ret = objio_alloc_io_state(NFS_I(hdr->inode)->layout, true, + hdr->lseg, rdata->args.pages, rdata->args.pgbase, rdata->args.offset, rdata->args.count, rdata, GFP_KERNEL, &objios); if (unlikely(ret)) @@ -483,12 +484,12 @@ 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 address_space *mapping = wdata->header->inode->i_mapping; pgoff_t index = offset / PAGE_SIZE; - struct page *page = find_get_page(wdata->inode->i_mapping, index); + struct page *page = find_get_page(mapping, index); if (!page) { - page = find_or_create_page(wdata->inode->i_mapping, - index, GFP_NOFS); + page = find_or_create_page(mapping, index, GFP_NOFS); if (unlikely(!page)) { dprintk("%s: grab_cache_page Failed index=0x%lx\n", __func__, index); @@ -518,11 +519,12 @@ static const struct _ore_r4w_op _r4w_op = { int objio_write_pagelist(struct nfs_write_data *wdata, int how) { + struct nfs_pgio_header *hdr = wdata->header; struct objio_state *objios; int ret; - ret = objio_alloc_io_state(NFS_I(wdata->inode)->layout, false, - wdata->lseg, wdata->args.pages, wdata->args.pgbase, + ret = objio_alloc_io_state(NFS_I(hdr->inode)->layout, false, + hdr->lseg, wdata->args.pages, wdata->args.pgbase, wdata->args.offset, wdata->args.count, wdata, GFP_NOFS, &objios); if (unlikely(ret)) diff --git a/fs/nfs/objlayout/objlayout.c b/fs/nfs/objlayout/objlayout.c index 595c5fc21a19..874613545301 100644 --- a/fs/nfs/objlayout/objlayout.c +++ b/fs/nfs/objlayout/objlayout.c @@ -258,7 +258,7 @@ objlayout_read_done(struct objlayout_io_res *oir, ssize_t status, bool sync) if (status >= 0) rdata->res.count = status; else - rdata->pnfs_error = status; + rdata->header->pnfs_error = status; objlayout_iodone(oir); /* must not use oir after this point */ @@ -279,12 +279,14 @@ objlayout_read_done(struct objlayout_io_res *oir, ssize_t status, bool sync) enum pnfs_try_status objlayout_read_pagelist(struct nfs_read_data *rdata) { + struct nfs_pgio_header *hdr = rdata->header; + struct inode *inode = hdr->inode; loff_t offset = rdata->args.offset; size_t count = rdata->args.count; int err; loff_t eof; - eof = i_size_read(rdata->inode); + eof = i_size_read(inode); if (unlikely(offset + count > eof)) { if (offset >= eof) { err = 0; @@ -297,17 +299,17 @@ objlayout_read_pagelist(struct nfs_read_data *rdata) } rdata->res.eof = (offset + count) >= eof; - _fix_verify_io_params(rdata->lseg, &rdata->args.pages, + _fix_verify_io_params(hdr->lseg, &rdata->args.pages, &rdata->args.pgbase, rdata->args.offset, rdata->args.count); dprintk("%s: inode(%lx) offset 0x%llx count 0x%Zx eof=%d\n", - __func__, rdata->inode->i_ino, offset, count, rdata->res.eof); + __func__, inode->i_ino, offset, count, rdata->res.eof); err = objio_read_pagelist(rdata); out: if (unlikely(err)) { - rdata->pnfs_error = err; + hdr->pnfs_error = err; dprintk("%s: Returned Error %d\n", __func__, err); return PNFS_NOT_ATTEMPTED; } @@ -340,7 +342,7 @@ objlayout_write_done(struct objlayout_io_res *oir, ssize_t status, bool sync) wdata->res.count = status; wdata->verf.committed = oir->committed; } else { - wdata->pnfs_error = status; + wdata->header->pnfs_error = status; } objlayout_iodone(oir); /* must not use oir after this point */ @@ -363,15 +365,16 @@ enum pnfs_try_status objlayout_write_pagelist(struct nfs_write_data *wdata, int how) { + struct nfs_pgio_header *hdr = wdata->header; int err; - _fix_verify_io_params(wdata->lseg, &wdata->args.pages, + _fix_verify_io_params(hdr->lseg, &wdata->args.pages, &wdata->args.pgbase, wdata->args.offset, wdata->args.count); err = objio_write_pagelist(wdata, how); if (unlikely(err)) { - wdata->pnfs_error = err; + hdr->pnfs_error = err; dprintk("%s: Returned Error %d\n", __func__, err); return PNFS_NOT_ATTEMPTED; } diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 9c4d14a17d49..d705da427e6d 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1191,13 +1191,15 @@ static int pnfs_write_done_resend_to_mds(struct inode *inode, struct list_head * static void pnfs_ld_handle_write_error(struct nfs_write_data *data) { - dprintk("pnfs write error = %d\n", data->pnfs_error); - if (NFS_SERVER(data->inode)->pnfs_curr_ld->flags & + struct nfs_pgio_header *hdr = data->header; + + dprintk("pnfs write error = %d\n", hdr->pnfs_error); + if (NFS_SERVER(hdr->inode)->pnfs_curr_ld->flags & PNFS_LAYOUTRET_ON_ERROR) { - clear_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(data->inode)->flags); - pnfs_return_layout(data->inode); + clear_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(hdr->inode)->flags); + pnfs_return_layout(hdr->inode); } - data->task.tk_status = pnfs_write_done_resend_to_mds(data->inode, &data->pages); + data->task.tk_status = pnfs_write_done_resend_to_mds(hdr->inode, &hdr->pages); } /* @@ -1205,13 +1207,15 @@ static void pnfs_ld_handle_write_error(struct nfs_write_data *data) */ void pnfs_ld_write_done(struct nfs_write_data *data) { - if (likely(!data->pnfs_error)) { + struct nfs_pgio_header *hdr = data->header; + + if (!hdr->pnfs_error) { pnfs_set_layoutcommit(data); - data->mds_ops->rpc_call_done(&data->task, data); + hdr->mds_ops->rpc_call_done(&data->task, data); } else pnfs_ld_handle_write_error(data); - put_lseg(data->lseg); - data->mds_ops->rpc_release(data); + put_lseg(hdr->lseg); + hdr->mds_ops->rpc_release(data); } EXPORT_SYMBOL_GPL(pnfs_ld_write_done); @@ -1219,12 +1223,14 @@ static void pnfs_write_through_mds(struct nfs_pageio_descriptor *desc, struct nfs_write_data *data) { - list_splice_tail_init(&data->pages, &desc->pg_list); - if (data->req && list_empty(&data->req->wb_list)) - nfs_list_add_request(data->req, &desc->pg_list); + struct nfs_pgio_header *hdr = data->header; + + list_splice_tail_init(&hdr->pages, &desc->pg_list); + if (hdr->req && list_empty(&hdr->req->wb_list)) + nfs_list_add_request(hdr->req, &desc->pg_list); nfs_pageio_reset_write_mds(desc); desc->pg_recoalesce = 1; - put_lseg(data->lseg); + put_lseg(hdr->lseg); nfs_writedata_release(data); } @@ -1234,20 +1240,21 @@ pnfs_try_to_write_data(struct nfs_write_data *wdata, struct pnfs_layout_segment *lseg, int how) { - struct inode *inode = wdata->inode; + struct nfs_pgio_header *hdr = wdata->header; + struct inode *inode = hdr->inode; enum pnfs_try_status trypnfs; struct nfs_server *nfss = NFS_SERVER(inode); - wdata->mds_ops = call_ops; - wdata->lseg = get_lseg(lseg); + hdr->mds_ops = call_ops; + hdr->lseg = get_lseg(lseg); dprintk("%s: Writing ino:%lu %u@%llu (how %d)\n", __func__, inode->i_ino, wdata->args.count, wdata->args.offset, how); trypnfs = nfss->pnfs_curr_ld->write_pagelist(wdata, how); if (trypnfs == PNFS_NOT_ATTEMPTED) { - put_lseg(wdata->lseg); - wdata->lseg = NULL; + put_lseg(hdr->lseg); + hdr->lseg = NULL; } else nfs_inc_stats(inode, NFSIOS_PNFS_WRITE); @@ -1318,13 +1325,15 @@ static int pnfs_read_done_resend_to_mds(struct inode *inode, struct list_head *h static void pnfs_ld_handle_read_error(struct nfs_read_data *data) { - dprintk("pnfs read error = %d\n", data->pnfs_error); - if (NFS_SERVER(data->inode)->pnfs_curr_ld->flags & + struct nfs_pgio_header *hdr = data->header; + + dprintk("pnfs read error = %d\n", hdr->pnfs_error); + if (NFS_SERVER(hdr->inode)->pnfs_curr_ld->flags & PNFS_LAYOUTRET_ON_ERROR) { - clear_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(data->inode)->flags); - pnfs_return_layout(data->inode); + clear_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(hdr->inode)->flags); + pnfs_return_layout(hdr->inode); } - data->task.tk_status = pnfs_read_done_resend_to_mds(data->inode, &data->pages); + data->task.tk_status = pnfs_read_done_resend_to_mds(hdr->inode, &hdr->pages); } /* @@ -1332,13 +1341,15 @@ static void pnfs_ld_handle_read_error(struct nfs_read_data *data) */ void pnfs_ld_read_done(struct nfs_read_data *data) { - if (likely(!data->pnfs_error)) { + struct nfs_pgio_header *hdr = data->header; + + if (likely(!hdr->pnfs_error)) { __nfs4_read_done_cb(data); - data->mds_ops->rpc_call_done(&data->task, data); + hdr->mds_ops->rpc_call_done(&data->task, data); } else pnfs_ld_handle_read_error(data); - put_lseg(data->lseg); - data->mds_ops->rpc_release(data); + put_lseg(hdr->lseg); + hdr->mds_ops->rpc_release(data); } EXPORT_SYMBOL_GPL(pnfs_ld_read_done); @@ -1346,9 +1357,11 @@ static void pnfs_read_through_mds(struct nfs_pageio_descriptor *desc, struct nfs_read_data *data) { - list_splice_tail_init(&data->pages, &desc->pg_list); - if (data->req && list_empty(&data->req->wb_list)) - nfs_list_add_request(data->req, &desc->pg_list); + struct nfs_pgio_header *hdr = data->header; + + list_splice_tail_init(&hdr->pages, &desc->pg_list); + if (hdr->req && list_empty(&hdr->req->wb_list)) + nfs_list_add_request(hdr->req, &desc->pg_list); nfs_pageio_reset_read_mds(desc); desc->pg_recoalesce = 1; nfs_readdata_release(data); @@ -1362,20 +1375,21 @@ pnfs_try_to_read_data(struct nfs_read_data *rdata, const struct rpc_call_ops *call_ops, struct pnfs_layout_segment *lseg) { - struct inode *inode = rdata->inode; + struct nfs_pgio_header *hdr = rdata->header; + struct inode *inode = hdr->inode; struct nfs_server *nfss = NFS_SERVER(inode); enum pnfs_try_status trypnfs; - rdata->mds_ops = call_ops; - rdata->lseg = get_lseg(lseg); + hdr->mds_ops = call_ops; + hdr->lseg = get_lseg(lseg); dprintk("%s: Reading ino:%lu %u@%llu\n", __func__, inode->i_ino, rdata->args.count, rdata->args.offset); trypnfs = nfss->pnfs_curr_ld->read_pagelist(rdata); if (trypnfs == PNFS_NOT_ATTEMPTED) { - put_lseg(rdata->lseg); - rdata->lseg = NULL; + put_lseg(hdr->lseg); + hdr->lseg = NULL; } else { nfs_inc_stats(inode, NFSIOS_PNFS_READ); } @@ -1450,30 +1464,32 @@ EXPORT_SYMBOL_GPL(pnfs_set_lo_fail); void pnfs_set_layoutcommit(struct nfs_write_data *wdata) { - struct nfs_inode *nfsi = NFS_I(wdata->inode); + struct nfs_pgio_header *hdr = wdata->header; + struct inode *inode = hdr->inode; + struct nfs_inode *nfsi = NFS_I(inode); loff_t end_pos = wdata->mds_offset + wdata->res.count; bool mark_as_dirty = false; - spin_lock(&nfsi->vfs_inode.i_lock); + spin_lock(&inode->i_lock); if (!test_and_set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) { mark_as_dirty = true; dprintk("%s: Set layoutcommit for inode %lu ", - __func__, wdata->inode->i_ino); + __func__, inode->i_ino); } - if (!test_and_set_bit(NFS_LSEG_LAYOUTCOMMIT, &wdata->lseg->pls_flags)) { + if (!test_and_set_bit(NFS_LSEG_LAYOUTCOMMIT, &hdr->lseg->pls_flags)) { /* references matched in nfs4_layoutcommit_release */ - get_lseg(wdata->lseg); + get_lseg(hdr->lseg); } if (end_pos > nfsi->layout->plh_lwb) nfsi->layout->plh_lwb = end_pos; - spin_unlock(&nfsi->vfs_inode.i_lock); + spin_unlock(&inode->i_lock); dprintk("%s: lseg %p end_pos %llu\n", - __func__, wdata->lseg, nfsi->layout->plh_lwb); + __func__, hdr->lseg, nfsi->layout->plh_lwb); /* if pnfs_layoutcommit_inode() runs between inode locks, the next one * will be a noop because NFS_INO_LAYOUTCOMMIT will not be set */ if (mark_as_dirty) - mark_inode_dirty_sync(wdata->inode); + mark_inode_dirty_sync(inode); } EXPORT_SYMBOL_GPL(pnfs_set_layoutcommit); diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c index bf80503200f5..22ee70586875 100644 --- a/fs/nfs/proc.c +++ b/fs/nfs/proc.c @@ -641,12 +641,14 @@ nfs_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle, static int nfs_read_done(struct rpc_task *task, struct nfs_read_data *data) { + struct inode *inode = data->header->inode; + if (nfs_async_handle_expired_key(task)) return -EAGAIN; - nfs_invalidate_atime(data->inode); + nfs_invalidate_atime(inode); if (task->tk_status >= 0) { - nfs_refresh_inode(data->inode, data->res.fattr); + nfs_refresh_inode(inode, data->res.fattr); /* Emulate the eof flag, which isn't normally needed in NFSv2 * as it is guaranteed to always return the file attributes */ @@ -668,11 +670,13 @@ static void nfs_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_dat static int nfs_write_done(struct rpc_task *task, struct nfs_write_data *data) { + struct inode *inode = data->header->inode; + if (nfs_async_handle_expired_key(task)) return -EAGAIN; if (task->tk_status >= 0) - nfs_post_op_update_inode_force_wcc(data->inode, data->res.fattr); + nfs_post_op_update_inode_force_wcc(inode, data->res.fattr); return 0; } diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 4ddba6706347..d6d46823d9e4 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -35,19 +35,24 @@ static const struct rpc_call_ops nfs_read_full_ops; static struct kmem_cache *nfs_rdata_cachep; -struct nfs_read_data *nfs_readdata_alloc(unsigned int pagecount) +struct nfs_read_header *nfs_readhdr_alloc(unsigned int pagecount) { - struct nfs_read_data *p; + struct nfs_read_header *p; p = kmem_cache_zalloc(nfs_rdata_cachep, GFP_KERNEL); if (p) { - INIT_LIST_HEAD(&p->pages); - p->npages = pagecount; - if (pagecount <= ARRAY_SIZE(p->page_array)) - p->pagevec = p->page_array; + struct nfs_pgio_header *hdr = &p->header; + struct nfs_read_data *data = &p->rpc_data; + + INIT_LIST_HEAD(&hdr->pages); + INIT_LIST_HEAD(&data->list); + data->npages = pagecount; + data->header = hdr; + if (pagecount <= ARRAY_SIZE(data->page_array)) + data->pagevec = data->page_array; else { - p->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_KERNEL); - if (!p->pagevec) { + data->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_KERNEL); + if (!data->pagevec) { kmem_cache_free(nfs_rdata_cachep, p); p = NULL; } @@ -56,17 +61,19 @@ struct nfs_read_data *nfs_readdata_alloc(unsigned int pagecount) return p; } -void nfs_readdata_free(struct nfs_read_data *p) +void nfs_readhdr_free(struct nfs_pgio_header *hdr) { - if (p && (p->pagevec != &p->page_array[0])) - kfree(p->pagevec); - kmem_cache_free(nfs_rdata_cachep, p); + struct nfs_read_header *rhdr = container_of(hdr, struct nfs_read_header, header); + + kmem_cache_free(nfs_rdata_cachep, rhdr); } void nfs_readdata_release(struct nfs_read_data *rdata) { put_nfs_open_context(rdata->args.context); - nfs_readdata_free(rdata); + if (rdata->pagevec != rdata->page_array) + kfree(rdata->pagevec); + nfs_readhdr_free(rdata->header); } static @@ -173,13 +180,13 @@ int nfs_initiate_read(struct rpc_clnt *clnt, struct nfs_read_data *data, const struct rpc_call_ops *call_ops) { - struct inode *inode = data->inode; + 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->cred, + .rpc_cred = data->header->cred, }; struct rpc_task_setup task_setup_data = { .task = &data->task, @@ -216,11 +223,11 @@ EXPORT_SYMBOL_GPL(nfs_initiate_read); static void nfs_read_rpcsetup(struct nfs_page *req, struct nfs_read_data *data, unsigned int count, unsigned int offset) { - struct inode *inode = req->wb_context->dentry->d_inode; + struct inode *inode = data->header->inode; - data->req = req; - data->inode = inode; - data->cred = req->wb_context->cred; + data->header->req = req; + data->header->inode = inode; + data->header->cred = req->wb_context->cred; data->args.fh = NFS_FH(inode); data->args.offset = req_offset(req) + offset; @@ -239,7 +246,7 @@ static void nfs_read_rpcsetup(struct nfs_page *req, struct nfs_read_data *data, static int nfs_do_read(struct nfs_read_data *data, const struct rpc_call_ops *call_ops) { - struct inode *inode = data->args.context->dentry->d_inode; + struct inode *inode = data->header->inode; return nfs_initiate_read(NFS_CLIENT(inode), data, call_ops); } @@ -293,6 +300,7 @@ static int nfs_pagein_multi(struct nfs_pageio_descriptor *desc, struct list_head { struct nfs_page *req = nfs_list_entry(desc->pg_list.next); struct page *page = req->wb_page; + struct nfs_read_header *rhdr; struct nfs_read_data *data; size_t rsize = desc->pg_bsize, nbytes; unsigned int offset; @@ -306,9 +314,10 @@ static int nfs_pagein_multi(struct nfs_pageio_descriptor *desc, struct list_head do { size_t len = min(nbytes,rsize); - data = nfs_readdata_alloc(1); - if (!data) + rhdr = nfs_readhdr_alloc(1); + if (!rhdr) goto out_bad; + data = &rhdr->rpc_data; data->pagevec[0] = page; nfs_read_rpcsetup(req, data, len, offset); list_add(&data->list, res); @@ -333,26 +342,28 @@ static int nfs_pagein_one(struct nfs_pageio_descriptor *desc, struct list_head * { struct nfs_page *req; struct page **pages; + struct nfs_read_header *rhdr; struct nfs_read_data *data; struct list_head *head = &desc->pg_list; int ret = 0; - data = nfs_readdata_alloc(nfs_page_array_len(desc->pg_base, - desc->pg_count)); - if (!data) { + rhdr = nfs_readhdr_alloc(nfs_page_array_len(desc->pg_base, + desc->pg_count)); + if (!rhdr) { nfs_async_read_error(head); ret = -ENOMEM; goto out; } + data = &rhdr->rpc_data; pages = data->pagevec; while (!list_empty(head)) { req = nfs_list_entry(head->next); nfs_list_remove_request(req); - nfs_list_add_request(req, &data->pages); + nfs_list_add_request(req, &rhdr->header.pages); *pages++ = req->wb_page; } - req = nfs_list_entry(data->pages.next); + req = nfs_list_entry(rhdr->header.pages.next); nfs_read_rpcsetup(req, data, desc->pg_count, 0); list_add(&data->list, res); @@ -390,20 +401,21 @@ static const struct nfs_pageio_ops nfs_pageio_read_ops = { */ int nfs_readpage_result(struct rpc_task *task, struct nfs_read_data *data) { + 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(data->inode)->read_done(task, data); + status = NFS_PROTO(inode)->read_done(task, data); if (status != 0) return status; - nfs_add_stats(data->inode, NFSIOS_SERVERREADBYTES, data->res.count); + nfs_add_stats(inode, NFSIOS_SERVERREADBYTES, data->res.count); if (task->tk_status == -ESTALE) { - set_bit(NFS_INO_STALE, &NFS_I(data->inode)->flags); - nfs_mark_for_revalidate(data->inode); + set_bit(NFS_INO_STALE, &NFS_I(inode)->flags); + nfs_mark_for_revalidate(inode); } return 0; } @@ -417,7 +429,7 @@ static void nfs_readpage_retry(struct rpc_task *task, struct nfs_read_data *data return; /* This is a short read! */ - nfs_inc_stats(data->inode, NFSIOS_SHORTREAD); + nfs_inc_stats(data->header->inode, NFSIOS_SHORTREAD); /* Has the server at least made some progress? */ if (resp->count == 0) return; @@ -449,7 +461,7 @@ static void nfs_readpage_result_partial(struct rpc_task *task, void *calldata) static void nfs_readpage_release_partial(void *calldata) { struct nfs_read_data *data = calldata; - struct nfs_page *req = data->req; + struct nfs_page *req = data->header->req; struct page *page = req->wb_page; int status = data->task.tk_status; @@ -461,13 +473,13 @@ static void nfs_readpage_release_partial(void *calldata) SetPageUptodate(page); nfs_readpage_release(req); } - nfs_readdata_release(calldata); + nfs_readdata_release(data); } void nfs_read_prepare(struct rpc_task *task, void *calldata) { struct nfs_read_data *data = calldata; - NFS_PROTO(data->inode)->read_rpc_prepare(task, data); + NFS_PROTO(data->header->inode)->read_rpc_prepare(task, data); } static const struct rpc_call_ops nfs_read_partial_ops = { @@ -524,9 +536,10 @@ static void nfs_readpage_result_full(struct rpc_task *task, void *calldata) static void nfs_readpage_release_full(void *calldata) { struct nfs_read_data *data = calldata; + struct nfs_pgio_header *hdr = data->header; - while (!list_empty(&data->pages)) { - struct nfs_page *req = nfs_list_entry(data->pages.next); + while (!list_empty(&hdr->pages)) { + struct nfs_page *req = nfs_list_entry(hdr->pages.next); nfs_list_remove_request(req); nfs_readpage_release(req); @@ -685,7 +698,7 @@ out: int __init nfs_init_readpagecache(void) { nfs_rdata_cachep = kmem_cache_create("nfs_read_data", - sizeof(struct nfs_read_data), + sizeof(struct nfs_read_header), 0, SLAB_HWCACHE_ALIGN, NULL); if (nfs_rdata_cachep == NULL) diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 76735dd8c9a7..dbb5c0a613b8 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -69,19 +69,24 @@ void nfs_commit_free(struct nfs_commit_data *p) } EXPORT_SYMBOL_GPL(nfs_commit_free); -struct nfs_write_data *nfs_writedata_alloc(unsigned int pagecount) +struct nfs_write_header *nfs_writehdr_alloc(unsigned int pagecount) { - struct nfs_write_data *p = mempool_alloc(nfs_wdata_mempool, GFP_NOFS); + struct nfs_write_header *p = mempool_alloc(nfs_wdata_mempool, GFP_NOFS); if (p) { + struct nfs_pgio_header *hdr = &p->header; + struct nfs_write_data *data = &p->rpc_data; + memset(p, 0, sizeof(*p)); - INIT_LIST_HEAD(&p->pages); - p->npages = pagecount; - if (pagecount <= ARRAY_SIZE(p->page_array)) - p->pagevec = p->page_array; + INIT_LIST_HEAD(&hdr->pages); + INIT_LIST_HEAD(&data->list); + data->npages = pagecount; + data->header = hdr; + if (pagecount <= ARRAY_SIZE(data->page_array)) + data->pagevec = data->page_array; else { - p->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_NOFS); - if (!p->pagevec) { + data->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_NOFS); + if (!data->pagevec) { mempool_free(p, nfs_wdata_mempool); p = NULL; } @@ -90,17 +95,18 @@ struct nfs_write_data *nfs_writedata_alloc(unsigned int pagecount) return p; } -void nfs_writedata_free(struct nfs_write_data *p) +void nfs_writehdr_free(struct nfs_pgio_header *hdr) { - if (p && (p->pagevec != &p->page_array[0])) - kfree(p->pagevec); - mempool_free(p, nfs_wdata_mempool); + struct nfs_write_header *whdr = container_of(hdr, struct nfs_write_header, header); + mempool_free(whdr, nfs_wdata_mempool); } void nfs_writedata_release(struct nfs_write_data *wdata) { put_nfs_open_context(wdata->args.context); - nfs_writedata_free(wdata); + if (wdata->pagevec != wdata->page_array) + kfree(wdata->pagevec); + nfs_writehdr_free(wdata->header); } static void nfs_context_set_write_error(struct nfs_open_context *ctx, int error) @@ -507,9 +513,8 @@ static inline int nfs_write_need_commit(struct nfs_write_data *data) { if (data->verf.committed == NFS_DATA_SYNC) - return data->lseg == NULL; - else - return data->verf.committed != NFS_FILE_SYNC; + return data->header->lseg == NULL; + return data->verf.committed != NFS_FILE_SYNC; } static inline @@ -517,7 +522,7 @@ int nfs_reschedule_unstable_write(struct nfs_page *req, struct nfs_write_data *data) { if (test_and_clear_bit(PG_NEED_COMMIT, &req->wb_flags)) { - nfs_mark_request_commit(req, data->lseg); + nfs_mark_request_commit(req, data->header->lseg); return 1; } if (test_and_clear_bit(PG_NEED_RESCHED, &req->wb_flags)) { @@ -841,13 +846,13 @@ int nfs_initiate_write(struct rpc_clnt *clnt, const struct rpc_call_ops *call_ops, int how) { - struct inode *inode = data->inode; + 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->cred, + .rpc_cred = data->header->cred, }; struct rpc_task_setup task_setup_data = { .rpc_client = clnt, @@ -896,14 +901,15 @@ static void nfs_write_rpcsetup(struct nfs_page *req, unsigned int count, unsigned int offset, int how) { + struct nfs_pgio_header *hdr = data->header; struct inode *inode = req->wb_context->dentry->d_inode; /* Set up the RPC argument and reply structs * NB: take care not to mess about with data->commit et al. */ - data->req = req; - data->inode = inode = req->wb_context->dentry->d_inode; - data->cred = req->wb_context->cred; + hdr->req = req; + hdr->inode = inode = req->wb_context->dentry->d_inode; + hdr->cred = req->wb_context->cred; data->args.fh = NFS_FH(inode); data->args.offset = req_offset(req) + offset; @@ -935,7 +941,7 @@ static int nfs_do_write(struct nfs_write_data *data, const struct rpc_call_ops *call_ops, int how) { - struct inode *inode = data->args.context->dentry->d_inode; + struct inode *inode = data->header->inode; return nfs_initiate_write(NFS_CLIENT(inode), data, call_ops, how); } @@ -981,6 +987,7 @@ static int nfs_flush_multi(struct nfs_pageio_descriptor *desc, struct list_head { struct nfs_page *req = nfs_list_entry(desc->pg_list.next); struct page *page = req->wb_page; + struct nfs_write_header *whdr; struct nfs_write_data *data; size_t wsize = desc->pg_bsize, nbytes; unsigned int offset; @@ -1000,9 +1007,10 @@ static int nfs_flush_multi(struct nfs_pageio_descriptor *desc, struct list_head do { size_t len = min(nbytes, wsize); - data = nfs_writedata_alloc(1); - if (!data) + whdr = nfs_writehdr_alloc(1); + if (!whdr) goto out_bad; + data = &whdr->rpc_data; data->pagevec[0] = page; nfs_write_rpcsetup(req, data, len, offset, desc->pg_ioflags); list_add(&data->list, res); @@ -1036,13 +1044,14 @@ static int nfs_flush_one(struct nfs_pageio_descriptor *desc, struct list_head *r { struct nfs_page *req; struct page **pages; + struct nfs_write_header *whdr; struct nfs_write_data *data; struct list_head *head = &desc->pg_list; int ret = 0; - data = nfs_writedata_alloc(nfs_page_array_len(desc->pg_base, - desc->pg_count)); - if (!data) { + whdr = nfs_writehdr_alloc(nfs_page_array_len(desc->pg_base, + desc->pg_count)); + if (!whdr) { while (!list_empty(head)) { req = nfs_list_entry(head->next); nfs_list_remove_request(req); @@ -1051,14 +1060,15 @@ static int nfs_flush_one(struct nfs_pageio_descriptor *desc, struct list_head *r ret = -ENOMEM; goto out; } + data = &whdr->rpc_data; pages = data->pagevec; while (!list_empty(head)) { req = nfs_list_entry(head->next); nfs_list_remove_request(req); - nfs_list_add_request(req, &data->pages); + nfs_list_add_request(req, &whdr->header.pages); *pages++ = req->wb_page; } - req = nfs_list_entry(data->pages.next); + req = nfs_list_entry(whdr->header.pages.next); if ((desc->pg_ioflags & FLUSH_COND_STABLE) && (desc->pg_moreio || NFS_I(desc->pg_inode)->ncommit)) @@ -1126,10 +1136,11 @@ static void nfs_writeback_done_partial(struct rpc_task *task, void *calldata) dprintk("NFS: %5u write(%s/%lld %d@%lld)", task->tk_pid, - data->req->wb_context->dentry->d_inode->i_sb->s_id, + data->header->inode->i_sb->s_id, (long long) - NFS_FILEID(data->req->wb_context->dentry->d_inode), - data->req->wb_bytes, (long long)req_offset(data->req)); + NFS_FILEID(data->header->inode), + data->header->req->wb_bytes, + (long long)req_offset(data->header->req)); nfs_writeback_done(task, data); } @@ -1137,7 +1148,7 @@ static void nfs_writeback_done_partial(struct rpc_task *task, void *calldata) static void nfs_writeback_release_partial(void *calldata) { struct nfs_write_data *data = calldata; - struct nfs_page *req = data->req; + struct nfs_page *req = data->header->req; struct page *page = req->wb_page; int status = data->task.tk_status; @@ -1169,13 +1180,13 @@ static void nfs_writeback_release_partial(void *calldata) out: if (atomic_dec_and_test(&req->wb_complete)) nfs_writepage_release(req, data); - nfs_writedata_release(calldata); + nfs_writedata_release(data); } void nfs_write_prepare(struct rpc_task *task, void *calldata) { struct nfs_write_data *data = calldata; - NFS_PROTO(data->inode)->write_rpc_prepare(task, data); + NFS_PROTO(data->header->inode)->write_rpc_prepare(task, data); } void nfs_commit_prepare(struct rpc_task *task, void *calldata) @@ -1208,11 +1219,12 @@ static void nfs_writeback_done_full(struct rpc_task *task, void *calldata) static void nfs_writeback_release_full(void *calldata) { struct nfs_write_data *data = calldata; + struct nfs_pgio_header *hdr = data->header; int status = data->task.tk_status; /* Update attributes as result of writeback. */ - while (!list_empty(&data->pages)) { - struct nfs_page *req = nfs_list_entry(data->pages.next); + while (!list_empty(&hdr->pages)) { + struct nfs_page *req = nfs_list_entry(hdr->pages.next); struct page *page = req->wb_page; nfs_list_remove_request(req); @@ -1233,7 +1245,7 @@ static void nfs_writeback_release_full(void *calldata) if (nfs_write_need_commit(data)) { memcpy(&req->wb_verf, &data->verf, sizeof(req->wb_verf)); - nfs_mark_request_commit(req, data->lseg); + nfs_mark_request_commit(req, hdr->lseg); dprintk(" marked for commit\n"); goto next; } @@ -1244,7 +1256,7 @@ remove_request: nfs_unlock_request(req); nfs_end_page_writeback(page); } - nfs_writedata_release(calldata); + nfs_writedata_release(data); } static const struct rpc_call_ops nfs_write_full_ops = { @@ -1261,6 +1273,7 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data) { 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", @@ -1273,10 +1286,10 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data) * another writer had changed the file, but some applications * depend on tighter cache coherency when writing. */ - status = NFS_PROTO(data->inode)->write_done(task, data); + status = NFS_PROTO(inode)->write_done(task, data); if (status != 0) return; - nfs_add_stats(data->inode, NFSIOS_SERVERWRITTENBYTES, resp->count); + nfs_add_stats(inode, NFSIOS_SERVERWRITTENBYTES, resp->count); #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4) if (resp->verf->committed < argp->stable && task->tk_status >= 0) { @@ -1294,7 +1307,7 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data) if (time_before(complain, jiffies)) { dprintk("NFS: faulty NFS server %s:" " (committed = %d) != (stable = %d)\n", - NFS_SERVER(data->inode)->nfs_client->cl_hostname, + NFS_SERVER(inode)->nfs_client->cl_hostname, resp->verf->committed, argp->stable); complain = jiffies + 300 * HZ; } @@ -1304,7 +1317,7 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data) if (task->tk_status >= 0 && resp->count < argp->count) { static unsigned long complain; - nfs_inc_stats(data->inode, NFSIOS_SHORTWRITE); + nfs_inc_stats(inode, NFSIOS_SHORTWRITE); /* Has the server at least made some progress? */ if (resp->count != 0) { @@ -1333,7 +1346,6 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data) /* Can't do anything about it except throw an error. */ task->tk_status = -EIO; } - return; } @@ -1745,7 +1757,7 @@ 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_data), + sizeof(struct nfs_write_header), 0, SLAB_HWCACHE_ALIGN, NULL); if (nfs_wdata_cachep == NULL) diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index d5d68f322bf0..8d3a2b804201 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -568,12 +568,6 @@ nfs_have_writebacks(struct inode *inode) return NFS_I(inode)->npages != 0; } -/* - * Allocate nfs_write_data structures - */ -extern struct nfs_write_data *nfs_writedata_alloc(unsigned int npages); -extern void nfs_writedata_free(struct nfs_write_data *); - /* * linux/fs/nfs/read.c */ @@ -584,12 +578,6 @@ extern int nfs_readpage_result(struct rpc_task *, struct nfs_read_data *); extern int nfs_readpage_async(struct nfs_open_context *, struct inode *, struct page *); -/* - * Allocate nfs_read_data structures - */ -extern struct nfs_read_data *nfs_readdata_alloc(unsigned int npages); -extern void nfs_readdata_free(struct nfs_read_data *); - /* * linux/fs/nfs3proc.c */ diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 8fb036a0d489..fee324175391 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1168,52 +1168,58 @@ struct nfs_page; #define NFS_PAGEVEC_SIZE (8U) struct nfs_read_data { + struct nfs_pgio_header *header; + struct list_head list; struct rpc_task task; - struct inode *inode; - struct rpc_cred *cred; struct nfs_fattr fattr; /* fattr storage */ - struct list_head pages; /* Coalesced read requests */ - struct list_head list; /* lists of struct nfs_read_data */ - struct nfs_page *req; /* multi ops per nfs_page */ struct page **pagevec; unsigned int npages; /* Max length of pagevec */ struct nfs_readargs args; struct nfs_readres res; unsigned long timestamp; /* For lease renewal */ - struct pnfs_layout_segment *lseg; - struct nfs_client *ds_clp; /* pNFS data server */ - const struct rpc_call_ops *mds_ops; int (*read_done_cb) (struct rpc_task *task, struct nfs_read_data *data); __u64 mds_offset; - int pnfs_error; struct page *page_array[NFS_PAGEVEC_SIZE]; + struct nfs_client *ds_clp; /* pNFS data server */ +}; + +struct nfs_pgio_header { + struct inode *inode; + struct rpc_cred *cred; + struct list_head pages; + struct nfs_page *req; + struct pnfs_layout_segment *lseg; + const struct rpc_call_ops *mds_ops; + int pnfs_error; +}; + +struct nfs_read_header { + struct nfs_pgio_header header; + struct nfs_read_data rpc_data; }; struct nfs_direct_req; struct nfs_write_data { + struct nfs_pgio_header *header; + struct list_head list; struct rpc_task task; - struct inode *inode; - struct rpc_cred *cred; struct nfs_fattr fattr; struct nfs_writeverf verf; - struct list_head pages; /* Coalesced requests we wish to flush */ - struct list_head list; /* lists of struct nfs_write_data */ - struct nfs_page *req; /* multi ops per nfs_page */ struct page **pagevec; unsigned int npages; /* Max length of pagevec */ struct nfs_writeargs args; /* argument struct */ struct nfs_writeres res; /* result struct */ - struct pnfs_layout_segment *lseg; - struct nfs_client *ds_clp; /* pNFS data server */ - const struct rpc_call_ops *mds_ops; - int (*write_done_cb) (struct rpc_task *task, struct nfs_write_data *data); -#ifdef CONFIG_NFS_V4 unsigned long timestamp; /* For lease renewal */ -#endif + int (*write_done_cb) (struct rpc_task *task, struct nfs_write_data *data); __u64 mds_offset; /* Filelayout dense stripe */ - int pnfs_error; struct page *page_array[NFS_PAGEVEC_SIZE]; + struct nfs_client *ds_clp; /* pNFS data server */ +}; + +struct nfs_write_header { + struct nfs_pgio_header header; + struct nfs_write_data rpc_data; }; struct nfs_commit_data { -- cgit v1.2.3 From 30dd374f6fc1b202db3a1b57b61afff1326bad92 Mon Sep 17 00:00:00 2001 From: Fred Isaman Date: Fri, 20 Apr 2012 14:47:45 -0400 Subject: NFS: create struct nfs_page_array Both nfs_read_data and nfs_write_data devote several fields which can be combined into a single shared struct. Signed-off-by: Fred Isaman Signed-off-by: Trond Myklebust --- fs/nfs/blocklayout/blocklayout.c | 11 ++++++----- fs/nfs/direct.c | 40 +++++++++++++++++++++++----------------- fs/nfs/internal.h | 1 + fs/nfs/pagelist.c | 13 +++++++++++++ fs/nfs/read.c | 22 ++++++++-------------- fs/nfs/write.c | 22 ++++++++-------------- include/linux/nfs_xdr.h | 14 ++++++++------ 7 files changed, 67 insertions(+), 56 deletions(-) (limited to 'include') diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index 7a482517f4c6..7ae8a608956f 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -242,7 +242,7 @@ bl_read_pagelist(struct nfs_read_data *rdata) int pg_index = rdata->args.pgbase >> PAGE_CACHE_SHIFT; dprintk("%s enter nr_pages %u offset %lld count %u\n", __func__, - rdata->npages, f_offset, (unsigned int)rdata->args.count); + rdata->pages.npages, f_offset, (unsigned int)rdata->args.count); par = alloc_parallel(rdata); if (!par) @@ -252,7 +252,7 @@ bl_read_pagelist(struct nfs_read_data *rdata) isect = (sector_t) (f_offset >> SECTOR_SHIFT); /* Code assumes extents are page-aligned */ - for (i = pg_index; i < rdata->npages; i++) { + for (i = pg_index; i < rdata->pages.npages; i++) { if (!extent_length) { /* We've used up the previous extent */ bl_put_extent(be); @@ -285,7 +285,8 @@ bl_read_pagelist(struct nfs_read_data *rdata) struct pnfs_block_extent *be_read; be_read = (hole && cow_read) ? cow_read : be; - bio = bl_add_page_to_bio(bio, rdata->npages - i, READ, + bio = bl_add_page_to_bio(bio, rdata->pages.npages - i, + READ, isect, pages[i], be_read, bl_end_io_read, par); if (IS_ERR(bio)) { @@ -654,7 +655,7 @@ next_page: /* Middle pages */ pg_index = wdata->args.pgbase >> PAGE_CACHE_SHIFT; - for (i = pg_index; i < wdata->npages; i++) { + for (i = pg_index; i < wdata->pages.npages; i++) { if (!extent_length) { /* We've used up the previous extent */ bl_put_extent(be); @@ -688,7 +689,7 @@ next_page: goto out; } } - bio = bl_add_page_to_bio(bio, wdata->npages - i, WRITE, + bio = bl_add_page_to_bio(bio, wdata->pages.npages - i, WRITE, isect, pages[i], be, bl_end_io_write, par); if (IS_ERR(bio)) { diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 56176af1436f..0faba4cb531d 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -252,11 +252,11 @@ static void nfs_direct_read_release(void *calldata) } else { dreq->count += data->res.count; spin_unlock(&dreq->lock); - nfs_direct_dirty_pages(data->pagevec, + nfs_direct_dirty_pages(data->pages.pagevec, data->args.pgbase, data->res.count); } - nfs_direct_release_pages(data->pagevec, data->npages); + nfs_direct_release_pages(data->pages.pagevec, data->pages.npages); if (put_dreq(dreq)) nfs_direct_complete(dreq); @@ -273,8 +273,8 @@ static void nfs_direct_readhdr_release(struct nfs_read_header *rhdr) { struct nfs_read_data *data = &rhdr->rpc_data; - if (data->pagevec != data->page_array) - kfree(data->pagevec); + if (data->pages.pagevec != data->pages.page_array) + kfree(data->pages.pagevec); nfs_readhdr_free(&rhdr->header); } @@ -312,6 +312,7 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_direct_req *dreq, do { struct nfs_read_header *rhdr; struct nfs_read_data *data; + struct nfs_page_array *pages; size_t bytes; pgbase = user_addr & ~PAGE_MASK; @@ -322,24 +323,25 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_direct_req *dreq, if (unlikely(!rhdr)) break; data = &rhdr->rpc_data; + pages = &data->pages; down_read(¤t->mm->mmap_sem); result = get_user_pages(current, current->mm, user_addr, - data->npages, 1, 0, data->pagevec, NULL); + pages->npages, 1, 0, pages->pagevec, NULL); up_read(¤t->mm->mmap_sem); if (result < 0) { nfs_direct_readhdr_release(rhdr); break; } - if ((unsigned)result < data->npages) { + if ((unsigned)result < pages->npages) { bytes = result * PAGE_SIZE; if (bytes <= pgbase) { - nfs_direct_release_pages(data->pagevec, result); + nfs_direct_release_pages(pages->pagevec, result); nfs_direct_readhdr_release(rhdr); break; } bytes -= pgbase; - data->npages = result; + pages->npages = result; } get_dreq(dreq); @@ -352,7 +354,7 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_direct_req *dreq, data->args.lock_context = dreq->l_ctx; data->args.offset = pos; data->args.pgbase = pgbase; - data->args.pages = data->pagevec; + data->args.pages = pages->pagevec; data->args.count = bytes; data->res.fattr = &data->fattr; data->res.eof = 0; @@ -462,8 +464,8 @@ static void nfs_direct_writehdr_release(struct nfs_write_header *whdr) { struct nfs_write_data *data = &whdr->rpc_data; - if (data->pagevec != data->page_array) - kfree(data->pagevec); + if (data->pages.pagevec != data->pages.page_array) + kfree(data->pages.pagevec); nfs_writehdr_free(&whdr->header); } @@ -472,8 +474,10 @@ static void nfs_direct_free_writedata(struct nfs_direct_req *dreq) while (!list_empty(&dreq->rewrite_list)) { struct nfs_pgio_header *hdr = list_entry(dreq->rewrite_list.next, struct nfs_pgio_header, pages); struct nfs_write_header *whdr = container_of(hdr, struct nfs_write_header, header); + struct nfs_page_array *p = &whdr->rpc_data.pages; + list_del(&hdr->pages); - nfs_direct_release_pages(whdr->rpc_data.pagevec, whdr->rpc_data.npages); + nfs_direct_release_pages(p->pagevec, p->npages); nfs_direct_writehdr_release(whdr); } } @@ -751,6 +755,7 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_direct_req *dreq, do { struct nfs_write_header *whdr; struct nfs_write_data *data; + struct nfs_page_array *pages; size_t bytes; pgbase = user_addr & ~PAGE_MASK; @@ -762,24 +767,25 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_direct_req *dreq, break; data = &whdr->rpc_data; + pages = &data->pages; down_read(¤t->mm->mmap_sem); result = get_user_pages(current, current->mm, user_addr, - data->npages, 0, 0, data->pagevec, NULL); + pages->npages, 0, 0, pages->pagevec, NULL); up_read(¤t->mm->mmap_sem); if (result < 0) { nfs_direct_writehdr_release(whdr); break; } - if ((unsigned)result < data->npages) { + if ((unsigned)result < pages->npages) { bytes = result * PAGE_SIZE; if (bytes <= pgbase) { - nfs_direct_release_pages(data->pagevec, result); + nfs_direct_release_pages(pages->pagevec, result); nfs_direct_writehdr_release(whdr); break; } bytes -= pgbase; - data->npages = result; + pages->npages = result; } get_dreq(dreq); @@ -794,7 +800,7 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_direct_req *dreq, data->args.lock_context = dreq->l_ctx; data->args.offset = pos; data->args.pgbase = pgbase; - data->args.pages = data->pagevec; + data->args.pages = pages->pagevec; data->args.count = bytes; data->args.stable = sync; data->res.fattr = &data->fattr; diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 7dc9be1a6e1a..5c3d77fda560 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -210,6 +210,7 @@ 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); /* nfs2xdr.c */ extern int nfs_stat_to_errno(enum nfs_stat); diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index d21fceaa9f62..d349bd4c48db 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -26,6 +26,19 @@ static struct kmem_cache *nfs_page_cachep; +bool nfs_pgarray_set(struct nfs_page_array *p, unsigned int pagecount) +{ + p->npages = pagecount; + if (pagecount <= ARRAY_SIZE(p->page_array)) + p->pagevec = p->page_array; + else { + p->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_KERNEL); + if (!p->pagevec) + p->npages = 0; + } + return p->pagevec != NULL; +} + static inline struct nfs_page * nfs_page_alloc(void) { diff --git a/fs/nfs/read.c b/fs/nfs/read.c index d6d46823d9e4..f6ab30b5a462 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -46,16 +46,10 @@ struct nfs_read_header *nfs_readhdr_alloc(unsigned int pagecount) INIT_LIST_HEAD(&hdr->pages); INIT_LIST_HEAD(&data->list); - data->npages = pagecount; data->header = hdr; - if (pagecount <= ARRAY_SIZE(data->page_array)) - data->pagevec = data->page_array; - else { - data->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_KERNEL); - if (!data->pagevec) { - kmem_cache_free(nfs_rdata_cachep, p); - p = NULL; - } + if (!nfs_pgarray_set(&data->pages, pagecount)) { + kmem_cache_free(nfs_rdata_cachep, p); + p = NULL; } } return p; @@ -71,8 +65,8 @@ void nfs_readhdr_free(struct nfs_pgio_header *hdr) void nfs_readdata_release(struct nfs_read_data *rdata) { put_nfs_open_context(rdata->args.context); - if (rdata->pagevec != rdata->page_array) - kfree(rdata->pagevec); + if (rdata->pages.pagevec != rdata->pages.page_array) + kfree(rdata->pages.pagevec); nfs_readhdr_free(rdata->header); } @@ -232,7 +226,7 @@ static void nfs_read_rpcsetup(struct nfs_page *req, struct nfs_read_data *data, data->args.fh = NFS_FH(inode); data->args.offset = req_offset(req) + offset; data->args.pgbase = req->wb_pgbase + offset; - data->args.pages = data->pagevec; + 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; @@ -318,7 +312,7 @@ static int nfs_pagein_multi(struct nfs_pageio_descriptor *desc, struct list_head if (!rhdr) goto out_bad; data = &rhdr->rpc_data; - data->pagevec[0] = page; + data->pages.pagevec[0] = page; nfs_read_rpcsetup(req, data, len, offset); list_add(&data->list, res); requests++; @@ -356,7 +350,7 @@ static int nfs_pagein_one(struct nfs_pageio_descriptor *desc, struct list_head * } data = &rhdr->rpc_data; - pages = data->pagevec; + pages = data->pages.pagevec; while (!list_empty(head)) { req = nfs_list_entry(head->next); nfs_list_remove_request(req); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index dbb5c0a613b8..2efae049b4f0 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -80,16 +80,10 @@ struct nfs_write_header *nfs_writehdr_alloc(unsigned int pagecount) memset(p, 0, sizeof(*p)); INIT_LIST_HEAD(&hdr->pages); INIT_LIST_HEAD(&data->list); - data->npages = pagecount; data->header = hdr; - if (pagecount <= ARRAY_SIZE(data->page_array)) - data->pagevec = data->page_array; - else { - data->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_NOFS); - if (!data->pagevec) { - mempool_free(p, nfs_wdata_mempool); - p = NULL; - } + if (!nfs_pgarray_set(&data->pages, pagecount)) { + mempool_free(p, nfs_wdata_mempool); + p = NULL; } } return p; @@ -104,8 +98,8 @@ void nfs_writehdr_free(struct nfs_pgio_header *hdr) void nfs_writedata_release(struct nfs_write_data *wdata) { put_nfs_open_context(wdata->args.context); - if (wdata->pagevec != wdata->page_array) - kfree(wdata->pagevec); + if (wdata->pages.pagevec != wdata->pages.page_array) + kfree(wdata->pages.pagevec); nfs_writehdr_free(wdata->header); } @@ -916,7 +910,7 @@ static void nfs_write_rpcsetup(struct nfs_page *req, /* pnfs_set_layoutcommit needs this */ data->mds_offset = data->args.offset; data->args.pgbase = req->wb_pgbase + offset; - data->args.pages = data->pagevec; + 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; @@ -1011,7 +1005,7 @@ static int nfs_flush_multi(struct nfs_pageio_descriptor *desc, struct list_head if (!whdr) goto out_bad; data = &whdr->rpc_data; - data->pagevec[0] = page; + data->pages.pagevec[0] = page; nfs_write_rpcsetup(req, data, len, offset, desc->pg_ioflags); list_add(&data->list, res); requests++; @@ -1061,7 +1055,7 @@ static int nfs_flush_one(struct nfs_pageio_descriptor *desc, struct list_head *r goto out; } data = &whdr->rpc_data; - pages = data->pagevec; + pages = data->pages.pagevec; while (!list_empty(head)) { req = nfs_list_entry(head->next); nfs_list_remove_request(req); diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index fee324175391..e34beaf86e9c 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1167,19 +1167,23 @@ struct nfs_page; #define NFS_PAGEVEC_SIZE (8U) +struct nfs_page_array { + struct page **pagevec; + unsigned int npages; /* Max length of pagevec */ + struct page *page_array[NFS_PAGEVEC_SIZE]; +}; + struct nfs_read_data { struct nfs_pgio_header *header; struct list_head list; struct rpc_task task; struct nfs_fattr fattr; /* fattr storage */ - struct page **pagevec; - unsigned int npages; /* Max length of pagevec */ struct nfs_readargs args; struct nfs_readres res; unsigned long timestamp; /* For lease renewal */ int (*read_done_cb) (struct rpc_task *task, struct nfs_read_data *data); __u64 mds_offset; - struct page *page_array[NFS_PAGEVEC_SIZE]; + struct nfs_page_array pages; struct nfs_client *ds_clp; /* pNFS data server */ }; @@ -1206,14 +1210,12 @@ struct nfs_write_data { struct rpc_task task; struct nfs_fattr fattr; struct nfs_writeverf verf; - struct page **pagevec; - unsigned int npages; /* Max length of pagevec */ struct nfs_writeargs args; /* argument struct */ struct nfs_writeres res; /* result struct */ unsigned long timestamp; /* For lease renewal */ int (*write_done_cb) (struct rpc_task *task, struct nfs_write_data *data); __u64 mds_offset; /* Filelayout dense stripe */ - struct page *page_array[NFS_PAGEVEC_SIZE]; + struct nfs_page_array pages; struct nfs_client *ds_clp; /* pNFS data server */ }; -- cgit v1.2.3 From 4db6e0b74c0f6dfc2f9c0690e8df512e3b635983 Mon Sep 17 00:00:00 2001 From: Fred Isaman Date: Fri, 20 Apr 2012 14:47:46 -0400 Subject: NFS: merge _full and _partial read rpc_ops Decouple nfs_pgio_header and nfs_read_data, and have (possibly multiple) nfs_read_datas each take a refcount on nfs_pgio_header. For the moment keeps nfs_read_header as a way to preallocate a single nfs_read_data with the nfs_pgio_header. The code doesn't need this, and would be prettier without, but given the amount of churn I am already introducing I didn't want to play with tuning new mempools. This also fixes bug in pnfs_ld_handle_read_error. In the case of desc->pg_bsize < PAGE_CACHE_SIZE, the pages list was empty, causing replay attempt to do nothing. Signed-off-by: Fred Isaman Signed-off-by: Trond Myklebust --- fs/nfs/direct.c | 10 +- fs/nfs/internal.h | 15 ++- fs/nfs/nfs4filelayout.c | 1 - fs/nfs/nfs4proc.c | 2 - fs/nfs/pagelist.c | 24 ++++ fs/nfs/pnfs.c | 55 +++++--- fs/nfs/read.c | 338 ++++++++++++++++++++++------------------------- include/linux/nfs_page.h | 1 - include/linux/nfs_xdr.h | 16 +++ 9 files changed, 252 insertions(+), 210 deletions(-) (limited to 'include') diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 0faba4cb531d..90b00ce42cbe 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -319,10 +319,16 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_direct_req *dreq, bytes = min(rsize,count); result = -ENOMEM; - rhdr = nfs_readhdr_alloc(nfs_page_array_len(pgbase, bytes)); + rhdr = nfs_readhdr_alloc(); if (unlikely(!rhdr)) break; - data = &rhdr->rpc_data; + data = nfs_readdata_alloc(&rhdr->header, nfs_page_array_len(pgbase, bytes)); + if (!data) { + nfs_readhdr_free(&rhdr->header); + break; + } + data->header = &rhdr->header; + atomic_inc(&data->header->refcnt); pages = &data->pages; down_read(¤t->mm->mmap_sem); diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 5c3d77fda560..33af5e51c0bb 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -200,6 +200,7 @@ struct vfsmount *nfs_do_refmount(struct rpc_clnt *client, struct dentry *dentry) extern struct svc_version nfs4_callback_version1; extern struct svc_version nfs4_callback_version4; +struct nfs_pageio_descriptor; /* pagelist.c */ extern int __init nfs_init_nfspagecache(void); extern void nfs_destroy_nfspagecache(void); @@ -211,6 +212,10 @@ 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); /* nfs2xdr.c */ extern int nfs_stat_to_errno(enum nfs_stat); @@ -295,17 +300,19 @@ extern struct dentry *nfs4_get_root(struct super_block *, struct nfs_fh *, extern int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh); #endif -struct nfs_pageio_descriptor; /* read.c */ -extern struct nfs_read_header *nfs_readhdr_alloc(unsigned int npages); +extern void nfs_async_read_error(struct list_head *head); +extern struct nfs_read_header *nfs_readhdr_alloc(void); extern void nfs_readhdr_free(struct nfs_pgio_header *hdr); +extern void nfs_read_completion(struct nfs_pgio_header *hdr); +extern struct nfs_read_data *nfs_readdata_alloc(struct nfs_pgio_header *hdr, + unsigned int pagecount); extern int nfs_initiate_read(struct rpc_clnt *clnt, struct nfs_read_data *data, const struct rpc_call_ops *call_ops); extern void nfs_read_prepare(struct rpc_task *task, void *calldata); extern int nfs_generic_pagein(struct nfs_pageio_descriptor *desc, - struct list_head *head); - + struct nfs_pgio_header *hdr); extern void nfs_pageio_init_read_mds(struct nfs_pageio_descriptor *pgio, struct inode *inode); extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio); diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c index ad1d68013a5b..333e765f3ac2 100644 --- a/fs/nfs/nfs4filelayout.c +++ b/fs/nfs/nfs4filelayout.c @@ -227,7 +227,6 @@ static void filelayout_read_release(void *data) { struct nfs_read_data *rdata = data; - put_lseg(rdata->header->lseg); rdata->header->mds_ops->rpc_release(data); } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 5375862075de..ce31ab22bc55 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3391,8 +3391,6 @@ void nfs4_reset_read(struct rpc_task *task, struct nfs_read_data *data) struct inode *inode = hdr->inode; dprintk("%s Reset task for i/o through\n", __func__); - put_lseg(hdr->lseg); - hdr->lseg = NULL; data->ds_clp = NULL; /* offsets will differ in the dense stripe case */ data->args.offset = data->mds_offset; diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index d349bd4c48db..cd4c038135a7 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -39,6 +39,30 @@ bool nfs_pgarray_set(struct nfs_page_array *p, unsigned int pagecount) return p->pagevec != NULL; } +void nfs_pgheader_init(struct nfs_pageio_descriptor *desc, + struct nfs_pgio_header *hdr, + void (*release)(struct nfs_pgio_header *hdr)) +{ + hdr->req = nfs_list_entry(desc->pg_list.next); + hdr->inode = desc->pg_inode; + hdr->cred = hdr->req->wb_context->cred; + hdr->io_start = req_offset(hdr->req); + hdr->good_bytes = desc->pg_count; + hdr->release = release; +} + +void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos) +{ + spin_lock(&hdr->lock); + if (pos < hdr->io_start + hdr->good_bytes) { + set_bit(NFS_IOHDR_ERROR, &hdr->flags); + clear_bit(NFS_IOHDR_EOF, &hdr->flags); + hdr->good_bytes = pos - hdr->io_start; + hdr->error = error; + } + spin_unlock(&hdr->lock); +} + static inline struct nfs_page * nfs_page_alloc(void) { diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index d705da427e6d..d1a91dbe7654 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1333,7 +1333,9 @@ static void pnfs_ld_handle_read_error(struct nfs_read_data *data) clear_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(hdr->inode)->flags); pnfs_return_layout(hdr->inode); } - data->task.tk_status = pnfs_read_done_resend_to_mds(hdr->inode, &hdr->pages); + if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) + data->task.tk_status = pnfs_read_done_resend_to_mds(hdr->inode, + &hdr->pages); } /* @@ -1348,7 +1350,6 @@ void pnfs_ld_read_done(struct nfs_read_data *data) hdr->mds_ops->rpc_call_done(&data->task, data); } else pnfs_ld_handle_read_error(data); - put_lseg(hdr->lseg); hdr->mds_ops->rpc_release(data); } EXPORT_SYMBOL_GPL(pnfs_ld_read_done); @@ -1359,11 +1360,11 @@ pnfs_read_through_mds(struct nfs_pageio_descriptor *desc, { struct nfs_pgio_header *hdr = data->header; - list_splice_tail_init(&hdr->pages, &desc->pg_list); - if (hdr->req && list_empty(&hdr->req->wb_list)) - nfs_list_add_request(hdr->req, &desc->pg_list); - nfs_pageio_reset_read_mds(desc); - desc->pg_recoalesce = 1; + if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) { + list_splice_tail_init(&hdr->pages, &desc->pg_list); + nfs_pageio_reset_read_mds(desc); + desc->pg_recoalesce = 1; + } nfs_readdata_release(data); } @@ -1381,18 +1382,13 @@ pnfs_try_to_read_data(struct nfs_read_data *rdata, enum pnfs_try_status trypnfs; hdr->mds_ops = call_ops; - hdr->lseg = get_lseg(lseg); dprintk("%s: Reading ino:%lu %u@%llu\n", __func__, inode->i_ino, rdata->args.count, rdata->args.offset); trypnfs = nfss->pnfs_curr_ld->read_pagelist(rdata); - if (trypnfs == PNFS_NOT_ATTEMPTED) { - put_lseg(hdr->lseg); - hdr->lseg = NULL; - } else { + if (trypnfs != PNFS_NOT_ATTEMPTED) nfs_inc_stats(inode, NFSIOS_PNFS_READ); - } dprintk("%s End (trypnfs:%d)\n", __func__, trypnfs); return trypnfs; } @@ -1408,7 +1404,7 @@ pnfs_do_multiple_reads(struct nfs_pageio_descriptor *desc, struct list_head *hea while (!list_empty(head)) { enum pnfs_try_status trypnfs; - data = list_entry(head->next, struct nfs_read_data, list); + 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); @@ -1418,20 +1414,41 @@ pnfs_do_multiple_reads(struct nfs_pageio_descriptor *desc, struct list_head *hea put_lseg(lseg); } +static void pnfs_readhdr_free(struct nfs_pgio_header *hdr) +{ + put_lseg(hdr->lseg); + nfs_readhdr_free(hdr); +} + int pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc) { - LIST_HEAD(head); + struct nfs_read_header *rhdr; + struct nfs_pgio_header *hdr; int ret; - ret = nfs_generic_pagein(desc, &head); - if (ret != 0) { + rhdr = nfs_readhdr_alloc(); + if (!rhdr) { + nfs_async_read_error(&desc->pg_list); + ret = -ENOMEM; put_lseg(desc->pg_lseg); desc->pg_lseg = NULL; return ret; } - pnfs_do_multiple_reads(desc, &head); - return 0; + hdr = &rhdr->header; + nfs_pgheader_init(desc, hdr, pnfs_readhdr_free); + hdr->lseg = get_lseg(desc->pg_lseg); + atomic_inc(&hdr->refcnt); + ret = nfs_generic_pagein(desc, hdr); + if (ret != 0) { + put_lseg(desc->pg_lseg); + desc->pg_lseg = NULL; + set_bit(NFS_IOHDR_REDO, &hdr->flags); + } else + pnfs_do_multiple_reads(desc, &hdr->rpc_list); + if (atomic_dec_and_test(&hdr->refcnt)) + nfs_read_completion(hdr); + return ret; } EXPORT_SYMBOL_GPL(pnfs_generic_pg_readpages); diff --git a/fs/nfs/read.c b/fs/nfs/read.c index f6ab30b5a462..c9633b2501bd 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -30,29 +30,49 @@ #define NFSDBG_FACILITY NFSDBG_PAGECACHE static const struct nfs_pageio_ops nfs_pageio_read_ops; -static const struct rpc_call_ops nfs_read_partial_ops; -static const struct rpc_call_ops nfs_read_full_ops; +static const struct rpc_call_ops nfs_read_common_ops; static struct kmem_cache *nfs_rdata_cachep; -struct nfs_read_header *nfs_readhdr_alloc(unsigned int pagecount) +struct nfs_read_header *nfs_readhdr_alloc() { - struct nfs_read_header *p; + struct nfs_read_header *rhdr; - p = kmem_cache_zalloc(nfs_rdata_cachep, GFP_KERNEL); - if (p) { - struct nfs_pgio_header *hdr = &p->header; - struct nfs_read_data *data = &p->rpc_data; + 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(&data->list); + INIT_LIST_HEAD(&hdr->rpc_list); + spin_lock_init(&hdr->lock); + atomic_set(&hdr->refcnt, 0); + } + return rhdr; +} + +struct nfs_read_data *nfs_readdata_alloc(struct nfs_pgio_header *hdr, + unsigned int pagecount) +{ + 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; - if (!nfs_pgarray_set(&data->pages, pagecount)) { - kmem_cache_free(nfs_rdata_cachep, p); - p = NULL; - } + atomic_inc(&hdr->refcnt); + } else { + if (data != prealloc) + kfree(data); + data = NULL; } - return p; +out: + return data; } void nfs_readhdr_free(struct nfs_pgio_header *hdr) @@ -64,10 +84,18 @@ void nfs_readhdr_free(struct nfs_pgio_header *hdr) 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); - nfs_readhdr_free(rdata->header); + if (rdata != &read_header->rpc_data) + kfree(rdata); + else + rdata->header = NULL; + if (atomic_dec_and_test(&hdr->refcnt)) + nfs_read_completion(hdr); } static @@ -79,35 +107,6 @@ int nfs_return_empty_page(struct page *page) return 0; } -static void nfs_readpage_truncate_uninitialised_page(struct nfs_read_data *data) -{ - unsigned int remainder = data->args.count - data->res.count; - unsigned int base = data->args.pgbase + data->res.count; - unsigned int pglen; - struct page **pages; - - if (data->res.eof == 0 || remainder == 0) - return; - /* - * Note: "remainder" can never be negative, since we check for - * this in the XDR code. - */ - pages = &data->args.pages[base >> PAGE_CACHE_SHIFT]; - base &= ~PAGE_CACHE_MASK; - pglen = PAGE_CACHE_SIZE - base; - for (;;) { - if (remainder <= pglen) { - zero_user(*pages, base, remainder); - break; - } - zero_user(*pages, base, pglen); - pages++; - remainder -= pglen; - pglen = PAGE_CACHE_SIZE; - base = 0; - } -} - void nfs_pageio_init_read_mds(struct nfs_pageio_descriptor *pgio, struct inode *inode) { @@ -170,6 +169,46 @@ static void nfs_readpage_release(struct nfs_page *req) nfs_release_request(req); } +/* Note io was page aligned */ +void nfs_read_completion(struct nfs_pgio_header *hdr) +{ + unsigned long bytes = 0; + + if (test_bit(NFS_IOHDR_REDO, &hdr->flags)) + goto out; + if (!test_bit(NFS_IOHDR_ERROR, &hdr->flags)) { + while (!list_empty(&hdr->pages)) { + struct nfs_page *req = nfs_list_entry(hdr->pages.next); + struct page *page = req->wb_page; + + 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); + } + SetPageUptodate(page); + nfs_list_remove_request(req); + nfs_readpage_release(req); + bytes += PAGE_SIZE; + } + } else { + while (!list_empty(&hdr->pages)) { + struct nfs_page *req = nfs_list_entry(hdr->pages.next); + + bytes += req->wb_bytes; + if (bytes <= hdr->good_bytes) + SetPageUptodate(req->wb_page); + nfs_list_remove_request(req); + nfs_readpage_release(req); + } + } +out: + hdr->release(hdr); +} + int nfs_initiate_read(struct rpc_clnt *clnt, struct nfs_read_data *data, const struct rpc_call_ops *call_ops) @@ -214,16 +253,12 @@ EXPORT_SYMBOL_GPL(nfs_initiate_read); /* * Set up the NFS read request struct */ -static void nfs_read_rpcsetup(struct nfs_page *req, struct nfs_read_data *data, +static void nfs_read_rpcsetup(struct nfs_read_data *data, unsigned int count, unsigned int offset) { - struct inode *inode = data->header->inode; - - data->header->req = req; - data->header->inode = inode; - data->header->cred = req->wb_context->cred; + struct nfs_page *req = data->header->req; - data->args.fh = NFS_FH(inode); + 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; @@ -255,7 +290,7 @@ nfs_do_multiple_reads(struct list_head *head, while (!list_empty(head)) { int ret2; - data = list_entry(head->next, struct nfs_read_data, list); + data = list_first_entry(head, struct nfs_read_data, list); list_del_init(&data->list); ret2 = nfs_do_read(data, call_ops); @@ -265,7 +300,7 @@ nfs_do_multiple_reads(struct list_head *head, return ret; } -static void +void nfs_async_read_error(struct list_head *head) { struct nfs_page *req; @@ -290,11 +325,11 @@ nfs_async_read_error(struct list_head *head) * 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 list_head *res) +static int nfs_pagein_multi(struct nfs_pageio_descriptor *desc, + struct nfs_pgio_header *hdr) { - struct nfs_page *req = nfs_list_entry(desc->pg_list.next); + struct nfs_page *req = hdr->req; struct page *page = req->wb_page; - struct nfs_read_header *rhdr; struct nfs_read_data *data; size_t rsize = desc->pg_bsize, nbytes; unsigned int offset; @@ -302,85 +337,97 @@ static int nfs_pagein_multi(struct nfs_pageio_descriptor *desc, struct list_head int ret = 0; nfs_list_remove_request(req); + nfs_list_add_request(req, &hdr->pages); offset = 0; nbytes = desc->pg_count; do { size_t len = min(nbytes,rsize); - rhdr = nfs_readhdr_alloc(1); - if (!rhdr) + data = nfs_readdata_alloc(hdr, 1); + if (!data) goto out_bad; - data = &rhdr->rpc_data; data->pages.pagevec[0] = page; - nfs_read_rpcsetup(req, data, len, offset); - list_add(&data->list, res); + nfs_read_rpcsetup(data, len, offset); + list_add(&data->list, &hdr->rpc_list); requests++; nbytes -= len; offset += len; } while(nbytes != 0); - atomic_set(&req->wb_complete, requests); - desc->pg_rpc_callops = &nfs_read_partial_ops; + desc->pg_rpc_callops = &nfs_read_common_ops; return ret; out_bad: - while (!list_empty(res)) { - data = list_entry(res->next, struct nfs_read_data, list); + while (!list_empty(&hdr->rpc_list)) { + data = list_first_entry(&hdr->rpc_list, struct nfs_read_data, list); list_del(&data->list); nfs_readdata_release(data); } - nfs_readpage_release(req); + nfs_async_read_error(&hdr->pages); return -ENOMEM; } -static int nfs_pagein_one(struct nfs_pageio_descriptor *desc, struct list_head *res) +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_header *rhdr; - struct nfs_read_data *data; + struct nfs_read_data *data; struct list_head *head = &desc->pg_list; int ret = 0; - rhdr = nfs_readhdr_alloc(nfs_page_array_len(desc->pg_base, - desc->pg_count)); - if (!rhdr) { + data = nfs_readdata_alloc(hdr, nfs_page_array_len(desc->pg_base, + desc->pg_count)); + if (!data) { nfs_async_read_error(head); ret = -ENOMEM; goto out; } - data = &rhdr->rpc_data; pages = data->pages.pagevec; while (!list_empty(head)) { req = nfs_list_entry(head->next); nfs_list_remove_request(req); - nfs_list_add_request(req, &rhdr->header.pages); + nfs_list_add_request(req, &hdr->pages); *pages++ = req->wb_page; } - req = nfs_list_entry(rhdr->header.pages.next); - nfs_read_rpcsetup(req, data, desc->pg_count, 0); - list_add(&data->list, res); - desc->pg_rpc_callops = &nfs_read_full_ops; + nfs_read_rpcsetup(data, desc->pg_count, 0); + list_add(&data->list, &hdr->rpc_list); + desc->pg_rpc_callops = &nfs_read_common_ops; out: return ret; } -int nfs_generic_pagein(struct nfs_pageio_descriptor *desc, struct list_head *head) +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, head); - return nfs_pagein_one(desc, head); + return nfs_pagein_multi(desc, hdr); + return nfs_pagein_one(desc, hdr); } static int nfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc) { - LIST_HEAD(head); + struct nfs_read_header *rhdr; + struct nfs_pgio_header *hdr; int ret; - ret = nfs_generic_pagein(desc, &head); + rhdr = nfs_readhdr_alloc(); + if (!rhdr) { + nfs_async_read_error(&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(&head, desc->pg_rpc_callops); + ret = nfs_do_multiple_reads(&hdr->rpc_list, + desc->pg_rpc_callops); + else + set_bit(NFS_IOHDR_REDO, &hdr->flags); + if (atomic_dec_and_test(&hdr->refcnt)) + nfs_read_completion(hdr); return ret; } @@ -419,15 +466,13 @@ static void nfs_readpage_retry(struct rpc_task *task, struct nfs_read_data *data struct nfs_readargs *argp = &data->args; struct nfs_readres *resp = &data->res; - if (resp->eof || resp->count == argp->count) - return; - /* This is a short read! */ nfs_inc_stats(data->header->inode, NFSIOS_SHORTREAD); /* Has the server at least made some progress? */ - if (resp->count == 0) + if (resp->count == 0) { + nfs_set_pgio_error(data->header, -EIO, argp->offset); return; - + } /* Yes, so retry the read at the end of the data */ data->mds_offset += resp->count; argp->offset += resp->count; @@ -436,38 +481,34 @@ static void nfs_readpage_retry(struct rpc_task *task, struct nfs_read_data *data rpc_restart_call_prepare(task); } -/* - * Handle a read reply that fills part of a page. - */ -static void nfs_readpage_result_partial(struct rpc_task *task, void *calldata) +static void nfs_readpage_result_common(struct rpc_task *task, void *calldata) { 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) - return; - - nfs_readpage_truncate_uninitialised_page(data); - nfs_readpage_retry(task, data); + nfs_set_pgio_error(hdr, task->tk_status, data->args.offset); + else if (data->res.eof) { + loff_t bound; + + bound = data->args.offset + data->res.count; + spin_lock(&hdr->lock); + if (bound < hdr->io_start + hdr->good_bytes) { + set_bit(NFS_IOHDR_EOF, &hdr->flags); + clear_bit(NFS_IOHDR_ERROR, &hdr->flags); + hdr->good_bytes = bound - hdr->io_start; + } + spin_unlock(&hdr->lock); + } else if (data->res.count != data->args.count) + nfs_readpage_retry(task, data); } -static void nfs_readpage_release_partial(void *calldata) +static void nfs_readpage_release_common(void *calldata) { - struct nfs_read_data *data = calldata; - struct nfs_page *req = data->header->req; - struct page *page = req->wb_page; - int status = data->task.tk_status; - - if (status < 0) - set_bit(PG_PARTIAL_READ_FAILED, &req->wb_flags); - - if (atomic_dec_and_test(&req->wb_complete)) { - if (!test_bit(PG_PARTIAL_READ_FAILED, &req->wb_flags)) - SetPageUptodate(page); - nfs_readpage_release(req); - } - nfs_readdata_release(data); + nfs_readdata_release(calldata); } void nfs_read_prepare(struct rpc_task *task, void *calldata) @@ -476,75 +517,10 @@ void nfs_read_prepare(struct rpc_task *task, void *calldata) NFS_PROTO(data->header->inode)->read_rpc_prepare(task, data); } -static const struct rpc_call_ops nfs_read_partial_ops = { - .rpc_call_prepare = nfs_read_prepare, - .rpc_call_done = nfs_readpage_result_partial, - .rpc_release = nfs_readpage_release_partial, -}; - -static void nfs_readpage_set_pages_uptodate(struct nfs_read_data *data) -{ - unsigned int count = data->res.count; - unsigned int base = data->args.pgbase; - struct page **pages; - - if (data->res.eof) - count = data->args.count; - if (unlikely(count == 0)) - return; - pages = &data->args.pages[base >> PAGE_CACHE_SHIFT]; - base &= ~PAGE_CACHE_MASK; - count += base; - for (;count >= PAGE_CACHE_SIZE; count -= PAGE_CACHE_SIZE, pages++) - SetPageUptodate(*pages); - if (count == 0) - return; - /* Was this a short read? */ - if (data->res.eof || data->res.count == data->args.count) - SetPageUptodate(*pages); -} - -/* - * This is the callback from RPC telling us whether a reply was - * received or some error occurred (timeout or socket shutdown). - */ -static void nfs_readpage_result_full(struct rpc_task *task, void *calldata) -{ - struct nfs_read_data *data = calldata; - - if (nfs_readpage_result(task, data) != 0) - return; - if (task->tk_status < 0) - return; - /* - * Note: nfs_readpage_retry may change the values of - * data->args. In the multi-page case, we therefore need - * to ensure that we call nfs_readpage_set_pages_uptodate() - * first. - */ - nfs_readpage_truncate_uninitialised_page(data); - nfs_readpage_set_pages_uptodate(data); - nfs_readpage_retry(task, data); -} - -static void nfs_readpage_release_full(void *calldata) -{ - struct nfs_read_data *data = calldata; - struct nfs_pgio_header *hdr = data->header; - - while (!list_empty(&hdr->pages)) { - struct nfs_page *req = nfs_list_entry(hdr->pages.next); - - nfs_list_remove_request(req); - nfs_readpage_release(req); - } - nfs_readdata_release(calldata); -} - -static const struct rpc_call_ops nfs_read_full_ops = { +static const struct rpc_call_ops nfs_read_common_ops = { .rpc_call_prepare = nfs_read_prepare, - .rpc_call_done = nfs_readpage_result_full, - .rpc_release = nfs_readpage_release_full, + .rpc_call_done = nfs_readpage_result_common, + .rpc_release = nfs_readpage_release_common, }; /* diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index eac30d6bec17..5c520344d8ad 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -27,7 +27,6 @@ enum { PG_CLEAN, PG_NEED_COMMIT, PG_NEED_RESCHED, - PG_PARTIAL_READ_FAILED, PG_COMMIT_TO_DS, }; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index e34beaf86e9c..164862148ba0 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1187,14 +1187,30 @@ struct nfs_read_data { struct nfs_client *ds_clp; /* pNFS data server */ }; +/* used as flag bits in nfs_pgio_header */ +enum { + NFS_IOHDR_ERROR = 0, + NFS_IOHDR_EOF, + NFS_IOHDR_REDO, +}; + struct nfs_pgio_header { struct inode *inode; struct rpc_cred *cred; struct list_head pages; + struct list_head rpc_list; + atomic_t refcnt; struct nfs_page *req; struct pnfs_layout_segment *lseg; + loff_t io_start; const struct rpc_call_ops *mds_ops; + void (*release) (struct nfs_pgio_header *hdr); + spinlock_t lock; + /* fields protected by lock */ int pnfs_error; + int error; /* merge with pnfs_error */ + unsigned long good_bytes; /* boundary of good data */ + unsigned long flags; }; struct nfs_read_header { -- cgit v1.2.3 From 6c75dc0d498caa402fb17b1bf769835a9db875c8 Mon Sep 17 00:00:00 2001 From: Fred Isaman Date: Fri, 20 Apr 2012 14:47:47 -0400 Subject: NFS: merge _full and _partial write rpc_ops Decouple nfs_pgio_header and nfs_write_data, and have (possibly multiple) nfs_write_datas each take a refcount on nfs_pgio_header. For the moment keeps nfs_write_header as a way to preallocate a single nfs_write_data with the nfs_pgio_header. The code doesn't need this, and would be prettier without, but given the amount of churn I am already introducing I didn't want to play with tuning new mempools. This also fixes bug in pnfs_ld_handle_write_error. In the case of desc->pg_bsize < PAGE_CACHE_SIZE, the pages list was empty, causing replay attempt to do nothing. Signed-off-by: Fred Isaman Signed-off-by: Trond Myklebust --- fs/nfs/direct.c | 10 +- fs/nfs/internal.h | 8 +- fs/nfs/nfs4filelayout.c | 1 - fs/nfs/nfs4proc.c | 4 +- fs/nfs/pnfs.c | 58 +++++--- fs/nfs/write.c | 383 ++++++++++++++++++++++-------------------------- include/linux/nfs_xdr.h | 2 + 7 files changed, 227 insertions(+), 239 deletions(-) (limited to 'include') diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 90b00ce42cbe..22a40c408449 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -768,11 +768,17 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_direct_req *dreq, bytes = min(wsize,count); result = -ENOMEM; - whdr = nfs_writehdr_alloc(nfs_page_array_len(pgbase, bytes)); + whdr = nfs_writehdr_alloc(); if (unlikely(!whdr)) break; - data = &whdr->rpc_data; + data = nfs_writedata_alloc(&whdr->header, nfs_page_array_len(pgbase, bytes)); + if (!data) { + nfs_writehdr_free(&whdr->header); + break; + } + data->header = &whdr->header; + atomic_inc(&data->header->refcnt); pages = &data->pages; down_read(¤t->mm->mmap_sem); diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 33af5e51c0bb..16bc9c47c83e 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -319,10 +319,14 @@ extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio); extern void nfs_readdata_release(struct nfs_read_data *rdata); /* write.c */ -extern struct nfs_write_header *nfs_writehdr_alloc(unsigned int npages); +extern void nfs_async_write_error(struct list_head *head); +extern struct nfs_write_header *nfs_writehdr_alloc(void); extern void nfs_writehdr_free(struct nfs_pgio_header *hdr); +extern struct nfs_write_data *nfs_writedata_alloc(struct nfs_pgio_header *hdr, + unsigned int pagecount); +extern void nfs_write_completion(struct nfs_pgio_header *hdr); extern int nfs_generic_flush(struct nfs_pageio_descriptor *desc, - struct list_head *head); + struct nfs_pgio_header *hdr); extern void nfs_pageio_init_write_mds(struct nfs_pageio_descriptor *pgio, struct inode *inode, int ioflags); extern void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio); diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c index 333e765f3ac2..02d8170ce0f3 100644 --- a/fs/nfs/nfs4filelayout.c +++ b/fs/nfs/nfs4filelayout.c @@ -314,7 +314,6 @@ static void filelayout_write_release(void *data) { struct nfs_write_data *wdata = data; - put_lseg(wdata->header->lseg); wdata->header->mds_ops->rpc_release(data); } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index ce31ab22bc55..87af80d28a82 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3431,8 +3431,6 @@ void nfs4_reset_write(struct rpc_task *task, struct nfs_write_data *data) struct inode *inode = hdr->inode; dprintk("%s Reset task for i/o through\n", __func__); - put_lseg(hdr->lseg); - hdr->lseg = NULL; data->ds_clp = NULL; data->write_done_cb = nfs4_write_done_cb; data->args.fh = NFS_FH(inode); @@ -3448,7 +3446,7 @@ static void nfs4_proc_write_setup(struct nfs_write_data *data, struct rpc_messag { struct nfs_server *server = NFS_SERVER(data->header->inode); - if (data->header->lseg) { + if (data->ds_clp) { data->args.bitmask = NULL; data->res.fattr = NULL; } else diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index d1a91dbe7654..d515f00614cd 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1199,7 +1199,9 @@ static void pnfs_ld_handle_write_error(struct nfs_write_data *data) clear_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(hdr->inode)->flags); pnfs_return_layout(hdr->inode); } - data->task.tk_status = pnfs_write_done_resend_to_mds(hdr->inode, &hdr->pages); + if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) + data->task.tk_status = pnfs_write_done_resend_to_mds(hdr->inode, + &hdr->pages); } /* @@ -1214,7 +1216,6 @@ void pnfs_ld_write_done(struct nfs_write_data *data) hdr->mds_ops->rpc_call_done(&data->task, data); } else pnfs_ld_handle_write_error(data); - put_lseg(hdr->lseg); hdr->mds_ops->rpc_release(data); } EXPORT_SYMBOL_GPL(pnfs_ld_write_done); @@ -1225,12 +1226,11 @@ pnfs_write_through_mds(struct nfs_pageio_descriptor *desc, { struct nfs_pgio_header *hdr = data->header; - list_splice_tail_init(&hdr->pages, &desc->pg_list); - if (hdr->req && list_empty(&hdr->req->wb_list)) - nfs_list_add_request(hdr->req, &desc->pg_list); - nfs_pageio_reset_write_mds(desc); - desc->pg_recoalesce = 1; - put_lseg(hdr->lseg); + if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) { + list_splice_tail_init(&hdr->pages, &desc->pg_list); + nfs_pageio_reset_write_mds(desc); + desc->pg_recoalesce = 1; + } nfs_writedata_release(data); } @@ -1246,18 +1246,12 @@ pnfs_try_to_write_data(struct nfs_write_data *wdata, struct nfs_server *nfss = NFS_SERVER(inode); hdr->mds_ops = call_ops; - hdr->lseg = get_lseg(lseg); dprintk("%s: Writing ino:%lu %u@%llu (how %d)\n", __func__, inode->i_ino, wdata->args.count, wdata->args.offset, how); - trypnfs = nfss->pnfs_curr_ld->write_pagelist(wdata, how); - if (trypnfs == PNFS_NOT_ATTEMPTED) { - put_lseg(hdr->lseg); - hdr->lseg = NULL; - } else + if (trypnfs != PNFS_NOT_ATTEMPTED) nfs_inc_stats(inode, NFSIOS_PNFS_WRITE); - dprintk("%s End (trypnfs:%d)\n", __func__, trypnfs); return trypnfs; } @@ -1273,7 +1267,7 @@ pnfs_do_multiple_writes(struct nfs_pageio_descriptor *desc, struct list_head *he while (!list_empty(head)) { enum pnfs_try_status trypnfs; - data = list_entry(head->next, struct nfs_write_data, list); + 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); @@ -1283,20 +1277,40 @@ pnfs_do_multiple_writes(struct nfs_pageio_descriptor *desc, struct list_head *he put_lseg(lseg); } +static void pnfs_writehdr_free(struct nfs_pgio_header *hdr) +{ + put_lseg(hdr->lseg); + nfs_writehdr_free(hdr); +} + int pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc) { - LIST_HEAD(head); + struct nfs_write_header *whdr; + struct nfs_pgio_header *hdr; int ret; - ret = nfs_generic_flush(desc, &head); - if (ret != 0) { + whdr = nfs_writehdr_alloc(); + if (!whdr) { + nfs_async_write_error(&desc->pg_list); put_lseg(desc->pg_lseg); desc->pg_lseg = NULL; - return ret; + return -ENOMEM; } - pnfs_do_multiple_writes(desc, &head, desc->pg_ioflags); - return 0; + hdr = &whdr->header; + nfs_pgheader_init(desc, hdr, pnfs_writehdr_free); + hdr->lseg = get_lseg(desc->pg_lseg); + atomic_inc(&hdr->refcnt); + ret = nfs_generic_flush(desc, hdr); + if (ret != 0) { + put_lseg(desc->pg_lseg); + desc->pg_lseg = NULL; + set_bit(NFS_IOHDR_REDO, &hdr->flags); + } else + pnfs_do_multiple_writes(desc, &hdr->rpc_list, desc->pg_ioflags); + if (atomic_dec_and_test(&hdr->refcnt)) + nfs_write_completion(hdr); + return ret; } EXPORT_SYMBOL_GPL(pnfs_generic_pg_writepages); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 2efae049b4f0..076075eb676c 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -42,8 +42,7 @@ static void nfs_pageio_init_write(struct nfs_pageio_descriptor *desc, struct inode *inode, int ioflags); static void nfs_redirty_request(struct nfs_page *req); -static const struct rpc_call_ops nfs_write_partial_ops; -static const struct rpc_call_ops nfs_write_full_ops; +static const struct rpc_call_ops nfs_write_common_ops; static const struct rpc_call_ops nfs_commit_ops; static struct kmem_cache *nfs_wdata_cachep; @@ -69,26 +68,47 @@ void nfs_commit_free(struct nfs_commit_data *p) } EXPORT_SYMBOL_GPL(nfs_commit_free); -struct nfs_write_header *nfs_writehdr_alloc(unsigned int pagecount) +struct nfs_write_header *nfs_writehdr_alloc(void) { struct nfs_write_header *p = mempool_alloc(nfs_wdata_mempool, GFP_NOFS); if (p) { struct nfs_pgio_header *hdr = &p->header; - struct nfs_write_data *data = &p->rpc_data; memset(p, 0, sizeof(*p)); INIT_LIST_HEAD(&hdr->pages); - INIT_LIST_HEAD(&data->list); - data->header = hdr; - if (!nfs_pgarray_set(&data->pages, pagecount)) { - mempool_free(p, nfs_wdata_mempool); - p = NULL; - } + INIT_LIST_HEAD(&hdr->rpc_list); + spin_lock_init(&hdr->lock); + atomic_set(&hdr->refcnt, 0); } return p; } +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) { struct nfs_write_header *whdr = container_of(hdr, struct nfs_write_header, header); @@ -97,10 +117,18 @@ void nfs_writehdr_free(struct nfs_pgio_header *hdr) 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); - nfs_writehdr_free(wdata->header); + if (wdata != &write_header->rpc_data) + kfree(wdata); + else + wdata->header = NULL; + if (atomic_dec_and_test(&hdr->refcnt)) + nfs_write_completion(hdr); } static void nfs_context_set_write_error(struct nfs_open_context *ctx, int error) @@ -511,20 +539,6 @@ int nfs_write_need_commit(struct nfs_write_data *data) return data->verf.committed != NFS_FILE_SYNC; } -static inline -int nfs_reschedule_unstable_write(struct nfs_page *req, - struct nfs_write_data *data) -{ - if (test_and_clear_bit(PG_NEED_COMMIT, &req->wb_flags)) { - nfs_mark_request_commit(req, data->header->lseg); - return 1; - } - if (test_and_clear_bit(PG_NEED_RESCHED, &req->wb_flags)) { - nfs_mark_request_dirty(req); - return 1; - } - return 0; -} #else static void nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg) @@ -542,13 +556,43 @@ int nfs_write_need_commit(struct nfs_write_data *data) return 0; } -static inline -int nfs_reschedule_unstable_write(struct nfs_page *req, - struct nfs_write_data *data) +#endif + +void nfs_write_completion(struct nfs_pgio_header *hdr) { - return 0; + unsigned long bytes = 0; + + if (test_bit(NFS_IOHDR_REDO, &hdr->flags)) + goto out; + while (!list_empty(&hdr->pages)) { + struct nfs_page *req = nfs_list_entry(hdr->pages.next); + struct page *page = req->wb_page; + + bytes += req->wb_bytes; + nfs_list_remove_request(req); + if (test_bit(NFS_IOHDR_ERROR, &hdr->flags) && + (hdr->good_bytes < bytes)) { + nfs_set_pageerror(page); + nfs_context_set_write_error(req->wb_context, hdr->error); + goto remove_req; + } + if (test_bit(NFS_IOHDR_NEED_RESCHED, &hdr->flags)) { + nfs_mark_request_dirty(req); + goto next; + } + if (test_bit(NFS_IOHDR_NEED_COMMIT, &hdr->flags)) { + nfs_mark_request_commit(req, hdr->lseg); + goto next; + } +remove_req: + nfs_inode_remove_request(req); +next: + nfs_unlock_request(req); + nfs_end_page_writeback(page); + } +out: + hdr->release(hdr); } -#endif #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4) static int @@ -813,17 +857,6 @@ int nfs_updatepage(struct file *file, struct page *page, return status; } -static void nfs_writepage_release(struct nfs_page *req, - struct nfs_write_data *data) -{ - struct page *page = req->wb_page; - - if (PageError(req->wb_page) || !nfs_reschedule_unstable_write(req, data)) - nfs_inode_remove_request(req); - nfs_unlock_request(req); - nfs_end_page_writeback(page); -} - static int flush_task_priority(int how) { switch (how & (FLUSH_HIGHPRI|FLUSH_LOWPRI)) { @@ -890,22 +923,16 @@ EXPORT_SYMBOL_GPL(nfs_initiate_write); /* * Set up the argument/result storage required for the RPC call. */ -static void nfs_write_rpcsetup(struct nfs_page *req, - struct nfs_write_data *data, +static void nfs_write_rpcsetup(struct nfs_write_data *data, unsigned int count, unsigned int offset, int how) { - struct nfs_pgio_header *hdr = data->header; - struct inode *inode = req->wb_context->dentry->d_inode; + 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. */ - hdr->req = req; - hdr->inode = inode = req->wb_context->dentry->d_inode; - hdr->cred = req->wb_context->cred; - - data->args.fh = NFS_FH(inode); + 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; @@ -919,7 +946,7 @@ static void nfs_write_rpcsetup(struct nfs_page *req, case 0: break; case FLUSH_COND_STABLE: - if (nfs_need_commit(NFS_I(inode))) + if (nfs_need_commit(NFS_I(data->header->inode))) break; default: data->args.stable = NFS_FILE_SYNC; @@ -950,7 +977,7 @@ static int nfs_do_multiple_writes(struct list_head *head, while (!list_empty(head)) { int ret2; - data = list_entry(head->next, struct nfs_write_data, list); + data = list_first_entry(head, struct nfs_write_data, list); list_del_init(&data->list); ret2 = nfs_do_write(data, call_ops, how); @@ -973,15 +1000,26 @@ static void nfs_redirty_request(struct nfs_page *req) nfs_end_page_writeback(page); } +void nfs_async_write_error(struct list_head *head) +{ + struct nfs_page *req; + + while (!list_empty(head)) { + req = nfs_list_entry(head->next); + nfs_list_remove_request(req); + nfs_redirty_request(req); + } +} + /* * 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 list_head *res) +static int nfs_flush_multi(struct nfs_pageio_descriptor *desc, + struct nfs_pgio_header *hdr) { - struct nfs_page *req = nfs_list_entry(desc->pg_list.next); + struct nfs_page *req = hdr->req; struct page *page = req->wb_page; - struct nfs_write_header *whdr; struct nfs_write_data *data; size_t wsize = desc->pg_bsize, nbytes; unsigned int offset; @@ -989,6 +1027,7 @@ static int nfs_flush_multi(struct nfs_pageio_descriptor *desc, struct list_head int ret = 0; nfs_list_remove_request(req); + nfs_list_add_request(req, &hdr->pages); if ((desc->pg_ioflags & FLUSH_COND_STABLE) && (desc->pg_moreio || NFS_I(desc->pg_inode)->ncommit || @@ -1001,28 +1040,27 @@ static int nfs_flush_multi(struct nfs_pageio_descriptor *desc, struct list_head do { size_t len = min(nbytes, wsize); - whdr = nfs_writehdr_alloc(1); - if (!whdr) + data = nfs_writedata_alloc(hdr, 1); + if (!data) goto out_bad; - data = &whdr->rpc_data; data->pages.pagevec[0] = page; - nfs_write_rpcsetup(req, data, len, offset, desc->pg_ioflags); - list_add(&data->list, res); + nfs_write_rpcsetup(data, len, offset, desc->pg_ioflags); + list_add(&data->list, &hdr->rpc_list); requests++; nbytes -= len; offset += len; } while (nbytes != 0); atomic_set(&req->wb_complete, requests); - desc->pg_rpc_callops = &nfs_write_partial_ops; + desc->pg_rpc_callops = &nfs_write_common_ops; return ret; out_bad: - while (!list_empty(res)) { - data = list_entry(res->next, struct nfs_write_data, list); + while (!list_empty(&hdr->rpc_list)) { + data = list_first_entry(&hdr->rpc_list, struct nfs_write_data, list); list_del(&data->list); nfs_writedata_release(data); } - nfs_redirty_request(req); + nfs_async_write_error(&hdr->pages); return -ENOMEM; } @@ -1034,64 +1072,74 @@ out_bad: * 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 list_head *res) +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_header *whdr; struct nfs_write_data *data; struct list_head *head = &desc->pg_list; int ret = 0; - whdr = nfs_writehdr_alloc(nfs_page_array_len(desc->pg_base, - desc->pg_count)); - if (!whdr) { - while (!list_empty(head)) { - req = nfs_list_entry(head->next); - nfs_list_remove_request(req); - nfs_redirty_request(req); - } + data = nfs_writedata_alloc(hdr, nfs_page_array_len(desc->pg_base, + desc->pg_count)); + if (!data) { + nfs_async_write_error(head); ret = -ENOMEM; goto out; } - data = &whdr->rpc_data; + pages = data->pages.pagevec; while (!list_empty(head)) { req = nfs_list_entry(head->next); nfs_list_remove_request(req); - nfs_list_add_request(req, &whdr->header.pages); + nfs_list_add_request(req, &hdr->pages); *pages++ = req->wb_page; } - req = nfs_list_entry(whdr->header.pages.next); if ((desc->pg_ioflags & FLUSH_COND_STABLE) && (desc->pg_moreio || NFS_I(desc->pg_inode)->ncommit)) desc->pg_ioflags &= ~FLUSH_COND_STABLE; /* Set up the argument struct */ - nfs_write_rpcsetup(req, data, desc->pg_count, 0, desc->pg_ioflags); - list_add(&data->list, res); - desc->pg_rpc_callops = &nfs_write_full_ops; + nfs_write_rpcsetup(data, desc->pg_count, 0, desc->pg_ioflags); + list_add(&data->list, &hdr->rpc_list); + desc->pg_rpc_callops = &nfs_write_common_ops; out: return ret; } -int nfs_generic_flush(struct nfs_pageio_descriptor *desc, struct list_head *head) +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, head); - return nfs_flush_one(desc, head); + return nfs_flush_multi(desc, hdr); + return nfs_flush_one(desc, hdr); } static int nfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc) { - LIST_HEAD(head); + struct nfs_write_header *whdr; + struct nfs_pgio_header *hdr; int ret; - ret = nfs_generic_flush(desc, &head); + whdr = nfs_writehdr_alloc(); + if (!whdr) { + nfs_async_write_error(&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(&head, desc->pg_rpc_callops, - desc->pg_ioflags); + ret = nfs_do_multiple_writes(&hdr->rpc_list, + desc->pg_rpc_callops, + desc->pg_ioflags); + else + set_bit(NFS_IOHDR_REDO, &hdr->flags); + if (atomic_dec_and_test(&hdr->refcnt)) + nfs_write_completion(hdr); return ret; } @@ -1121,62 +1169,6 @@ static void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, nfs_pageio_init_write_mds(pgio, inode, ioflags); } -/* - * Handle a write reply that flushed part of a page. - */ -static void nfs_writeback_done_partial(struct rpc_task *task, void *calldata) -{ - struct nfs_write_data *data = calldata; - - dprintk("NFS: %5u write(%s/%lld %d@%lld)", - task->tk_pid, - data->header->inode->i_sb->s_id, - (long long) - NFS_FILEID(data->header->inode), - data->header->req->wb_bytes, - (long long)req_offset(data->header->req)); - - nfs_writeback_done(task, data); -} - -static void nfs_writeback_release_partial(void *calldata) -{ - struct nfs_write_data *data = calldata; - struct nfs_page *req = data->header->req; - struct page *page = req->wb_page; - int status = data->task.tk_status; - - if (status < 0) { - nfs_set_pageerror(page); - nfs_context_set_write_error(req->wb_context, status); - dprintk(", error = %d\n", status); - goto out; - } - - if (nfs_write_need_commit(data)) { - struct inode *inode = page->mapping->host; - - spin_lock(&inode->i_lock); - if (test_bit(PG_NEED_RESCHED, &req->wb_flags)) { - /* Do nothing we need to resend the writes */ - } else if (!test_and_set_bit(PG_NEED_COMMIT, &req->wb_flags)) { - memcpy(&req->wb_verf, &data->verf, sizeof(req->wb_verf)); - dprintk(" defer commit\n"); - } else if (memcmp(&req->wb_verf, &data->verf, sizeof(req->wb_verf))) { - set_bit(PG_NEED_RESCHED, &req->wb_flags); - clear_bit(PG_NEED_COMMIT, &req->wb_flags); - dprintk(" server reboot detected\n"); - } - spin_unlock(&inode->i_lock); - } else - dprintk(" OK\n"); - -out: - if (atomic_dec_and_test(&req->wb_complete)) - nfs_writepage_release(req, data); - nfs_writedata_release(data); -} - void nfs_write_prepare(struct rpc_task *task, void *calldata) { struct nfs_write_data *data = calldata; @@ -1190,12 +1182,6 @@ void nfs_commit_prepare(struct rpc_task *task, void *calldata) NFS_PROTO(data->inode)->commit_rpc_prepare(task, data); } -static const struct rpc_call_ops nfs_write_partial_ops = { - .rpc_call_prepare = nfs_write_prepare, - .rpc_call_done = nfs_writeback_done_partial, - .rpc_release = nfs_writeback_release_partial, -}; - /* * Handle a write reply that flushes a whole page. * @@ -1203,60 +1189,37 @@ static const struct rpc_call_ops nfs_write_partial_ops = { * writebacks since the page->count is kept > 1 for as long * as the page has a write request pending. */ -static void nfs_writeback_done_full(struct rpc_task *task, void *calldata) +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_full(void *calldata) +static void nfs_writeback_release_common(void *calldata) { struct nfs_write_data *data = calldata; struct nfs_pgio_header *hdr = data->header; int status = data->task.tk_status; + struct nfs_page *req = hdr->req; - /* Update attributes as result of writeback. */ - while (!list_empty(&hdr->pages)) { - struct nfs_page *req = nfs_list_entry(hdr->pages.next); - struct page *page = req->wb_page; - - nfs_list_remove_request(req); - - dprintk("NFS: %5u write (%s/%lld %d@%lld)", - data->task.tk_pid, - req->wb_context->dentry->d_inode->i_sb->s_id, - (long long)NFS_FILEID(req->wb_context->dentry->d_inode), - req->wb_bytes, - (long long)req_offset(req)); - - if (status < 0) { - nfs_set_pageerror(page); - nfs_context_set_write_error(req->wb_context, status); - dprintk(", error = %d\n", status); - goto remove_request; - } - - if (nfs_write_need_commit(data)) { + if ((status >= 0) && nfs_write_need_commit(data)) { + spin_lock(&hdr->lock); + if (test_bit(NFS_IOHDR_NEED_RESCHED, &hdr->flags)) + ; /* Do nothing */ + else if (!test_and_set_bit(NFS_IOHDR_NEED_COMMIT, &hdr->flags)) memcpy(&req->wb_verf, &data->verf, sizeof(req->wb_verf)); - nfs_mark_request_commit(req, hdr->lseg); - dprintk(" marked for commit\n"); - goto next; - } - dprintk(" OK\n"); -remove_request: - nfs_inode_remove_request(req); - next: - nfs_unlock_request(req); - nfs_end_page_writeback(page); + else if (memcmp(&req->wb_verf, &data->verf, sizeof(req->wb_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_full_ops = { +static const struct rpc_call_ops nfs_write_common_ops = { .rpc_call_prepare = nfs_write_prepare, - .rpc_call_done = nfs_writeback_done_full, - .rpc_release = nfs_writeback_release_full, + .rpc_call_done = nfs_writeback_done_common, + .rpc_release = nfs_writeback_release_common, }; @@ -1307,38 +1270,40 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data) } } #endif - /* Is this a short write? */ - if (task->tk_status >= 0 && resp->count < argp->count) { + if (task->tk_status < 0) + nfs_set_pgio_error(data->header, task->tk_status, argp->offset); + else if (resp->count < argp->count) { static unsigned long complain; + /* This a short write! */ nfs_inc_stats(inode, NFSIOS_SHORTWRITE); /* Has the server at least made some progress? */ - if (resp->count != 0) { - /* Was this an NFSv2 write or an NFSv3 stable write? */ - if (resp->verf->committed != NFS_UNSTABLE) { - /* Resend from where the server left off */ - data->mds_offset += resp->count; - argp->offset += resp->count; - argp->pgbase += resp->count; - argp->count -= resp->count; - } else { - /* Resend as a stable write in order to avoid - * headaches in the case of a server crash. - */ - argp->stable = NFS_FILE_SYNC; + if (resp->count == 0) { + if (time_before(complain, jiffies)) { + printk(KERN_WARNING + "NFS: Server wrote zero bytes, expected %u.\n", + argp->count); + complain = jiffies + 300 * HZ; } - rpc_restart_call_prepare(task); + nfs_set_pgio_error(data->header, -EIO, argp->offset); + task->tk_status = -EIO; return; } - if (time_before(complain, jiffies)) { - printk(KERN_WARNING - "NFS: Server wrote zero bytes, expected %u.\n", - argp->count); - complain = jiffies + 300 * HZ; + /* Was this an NFSv2 write or an NFSv3 stable write? */ + if (resp->verf->committed != NFS_UNSTABLE) { + /* Resend from where the server left off */ + data->mds_offset += resp->count; + argp->offset += resp->count; + argp->pgbase += resp->count; + argp->count -= resp->count; + } else { + /* Resend as a stable write in order to avoid + * headaches in the case of a server crash. + */ + argp->stable = NFS_FILE_SYNC; } - /* Can't do anything about it except throw an error. */ - task->tk_status = -EIO; + rpc_restart_call_prepare(task); } } diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 164862148ba0..0d17db7973de 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1192,6 +1192,8 @@ enum { NFS_IOHDR_ERROR = 0, NFS_IOHDR_EOF, NFS_IOHDR_REDO, + NFS_IOHDR_NEED_COMMIT, + NFS_IOHDR_NEED_RESCHED, }; struct nfs_pgio_header { -- cgit v1.2.3 From 061ae2edb7375ab6776468b075da71008a098b55 Mon Sep 17 00:00:00 2001 From: Fred Isaman Date: Fri, 20 Apr 2012 14:47:48 -0400 Subject: NFS: create completion structure to pass into page_init functions Factors out the code that will need to change when directio starts using these code paths. This will allow directio to use the generic pagein and flush routines Signed-off-by: Fred Isaman Signed-off-by: Trond Myklebust --- fs/nfs/internal.h | 11 +++++------ fs/nfs/pagelist.c | 3 +++ fs/nfs/pnfs.c | 39 +++++++++++++++++++++++++-------------- fs/nfs/pnfs.h | 6 ++++-- fs/nfs/read.c | 36 ++++++++++++++++++++++-------------- fs/nfs/write.c | 41 ++++++++++++++++++++++++++--------------- include/linux/nfs_page.h | 2 ++ include/linux/nfs_xdr.h | 6 ++++++ 8 files changed, 93 insertions(+), 51 deletions(-) (limited to 'include') diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 16bc9c47c83e..3ef8fcda1a5f 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -300,11 +300,10 @@ extern struct dentry *nfs4_get_root(struct super_block *, struct nfs_fh *, extern int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh); #endif +struct nfs_pgio_completion_ops; /* read.c */ -extern void nfs_async_read_error(struct list_head *head); extern struct nfs_read_header *nfs_readhdr_alloc(void); extern void nfs_readhdr_free(struct nfs_pgio_header *hdr); -extern void nfs_read_completion(struct nfs_pgio_header *hdr); extern struct nfs_read_data *nfs_readdata_alloc(struct nfs_pgio_header *hdr, unsigned int pagecount); extern int nfs_initiate_read(struct rpc_clnt *clnt, @@ -314,21 +313,21 @@ 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_init_read_mds(struct nfs_pageio_descriptor *pgio, - struct inode *inode); + struct inode *inode, + const struct nfs_pgio_completion_ops *compl_ops); extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio); extern void nfs_readdata_release(struct nfs_read_data *rdata); /* write.c */ -extern void nfs_async_write_error(struct list_head *head); extern struct nfs_write_header *nfs_writehdr_alloc(void); extern void nfs_writehdr_free(struct nfs_pgio_header *hdr); extern struct nfs_write_data *nfs_writedata_alloc(struct nfs_pgio_header *hdr, unsigned int pagecount); -extern void nfs_write_completion(struct nfs_pgio_header *hdr); extern int nfs_generic_flush(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr); extern void nfs_pageio_init_write_mds(struct nfs_pageio_descriptor *pgio, - struct inode *inode, int ioflags); + struct inode *inode, int ioflags, + const struct nfs_pgio_completion_ops *compl_ops); 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); diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index cd4c038135a7..4cf2a68493e0 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -49,6 +49,7 @@ void nfs_pgheader_init(struct nfs_pageio_descriptor *desc, hdr->io_start = req_offset(hdr->req); hdr->good_bytes = desc->pg_count; hdr->release = release; + hdr->completion_ops = desc->pg_completion_ops; } void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos) @@ -240,6 +241,7 @@ EXPORT_SYMBOL_GPL(nfs_generic_pg_test); 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, size_t bsize, int io_flags) { @@ -252,6 +254,7 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc, desc->pg_recoalesce = 0; desc->pg_inode = inode; desc->pg_ops = pg_ops; + desc->pg_completion_ops = compl_ops; desc->pg_ioflags = io_flags; desc->pg_error = 0; desc->pg_lseg = NULL; diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index d515f00614cd..b3a0c01718af 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1113,26 +1113,31 @@ pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page * EXPORT_SYMBOL_GPL(pnfs_generic_pg_init_write); bool -pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode) +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) return false; - nfs_pageio_init(pgio, inode, ld->pg_read_ops, server->rsize, 0); + nfs_pageio_init(pgio, inode, ld->pg_read_ops, compl_ops, + server->rsize, 0); return true; } bool -pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode, int ioflags) +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) return false; - nfs_pageio_init(pgio, inode, ld->pg_write_ops, server->wsize, ioflags); + nfs_pageio_init(pgio, inode, ld->pg_write_ops, compl_ops, + server->wsize, ioflags); return true; } @@ -1162,13 +1167,15 @@ pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, } EXPORT_SYMBOL_GPL(pnfs_generic_pg_test); -static int pnfs_write_done_resend_to_mds(struct inode *inode, struct list_head *head) +static int pnfs_write_done_resend_to_mds(struct inode *inode, + struct list_head *head, + const struct nfs_pgio_completion_ops *compl_ops) { struct nfs_pageio_descriptor pgio; LIST_HEAD(failed); /* Resend all requests through the MDS */ - nfs_pageio_init_write_mds(&pgio, inode, FLUSH_STABLE); + nfs_pageio_init_write_mds(&pgio, inode, FLUSH_STABLE, compl_ops); while (!list_empty(head)) { struct nfs_page *req = nfs_list_entry(head->next); @@ -1201,7 +1208,8 @@ static void pnfs_ld_handle_write_error(struct nfs_write_data *data) } if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) data->task.tk_status = pnfs_write_done_resend_to_mds(hdr->inode, - &hdr->pages); + &hdr->pages, + hdr->completion_ops); } /* @@ -1292,7 +1300,7 @@ pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc) whdr = nfs_writehdr_alloc(); if (!whdr) { - nfs_async_write_error(&desc->pg_list); + desc->pg_completion_ops->error_cleanup(&hdr->pages); put_lseg(desc->pg_lseg); desc->pg_lseg = NULL; return -ENOMEM; @@ -1309,18 +1317,20 @@ pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc) } else pnfs_do_multiple_writes(desc, &hdr->rpc_list, desc->pg_ioflags); if (atomic_dec_and_test(&hdr->refcnt)) - nfs_write_completion(hdr); + hdr->completion_ops->completion(hdr); return ret; } EXPORT_SYMBOL_GPL(pnfs_generic_pg_writepages); -static int pnfs_read_done_resend_to_mds(struct inode *inode, struct list_head *head) +static int pnfs_read_done_resend_to_mds(struct inode *inode, + struct list_head *head, + const struct nfs_pgio_completion_ops *compl_ops) { struct nfs_pageio_descriptor pgio; LIST_HEAD(failed); /* Resend all requests through the MDS */ - nfs_pageio_init_read_mds(&pgio, inode); + nfs_pageio_init_read_mds(&pgio, inode, compl_ops); while (!list_empty(head)) { struct nfs_page *req = nfs_list_entry(head->next); @@ -1349,7 +1359,8 @@ static void pnfs_ld_handle_read_error(struct nfs_read_data *data) } if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) data->task.tk_status = pnfs_read_done_resend_to_mds(hdr->inode, - &hdr->pages); + &hdr->pages, + hdr->completion_ops); } /* @@ -1443,7 +1454,7 @@ pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc) rhdr = nfs_readhdr_alloc(); if (!rhdr) { - nfs_async_read_error(&desc->pg_list); + desc->pg_completion_ops->error_cleanup(&desc->pg_list); ret = -ENOMEM; put_lseg(desc->pg_lseg); desc->pg_lseg = NULL; @@ -1461,7 +1472,7 @@ pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc) } else pnfs_do_multiple_reads(desc, &hdr->rpc_list); if (atomic_dec_and_test(&hdr->refcnt)) - nfs_read_completion(hdr); + hdr->completion_ops->completion(hdr); return ret; } EXPORT_SYMBOL_GPL(pnfs_generic_pg_readpages); diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 442ebf68eeec..734e4eff7fb0 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -168,8 +168,10 @@ extern int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp); void get_layout_hdr(struct pnfs_layout_hdr *lo); void put_lseg(struct pnfs_layout_segment *lseg); -bool pnfs_pageio_init_read(struct nfs_pageio_descriptor *, struct inode *); -bool pnfs_pageio_init_write(struct nfs_pageio_descriptor *, struct inode *, int); +bool pnfs_pageio_init_read(struct nfs_pageio_descriptor *, struct inode *, + const struct nfs_pgio_completion_ops *); +bool 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 *); diff --git a/fs/nfs/read.c b/fs/nfs/read.c index c9633b2501bd..5e78af162039 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -31,6 +31,7 @@ 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 struct kmem_cache *nfs_rdata_cachep; @@ -95,7 +96,7 @@ void nfs_readdata_release(struct nfs_read_data *rdata) else rdata->header = NULL; if (atomic_dec_and_test(&hdr->refcnt)) - nfs_read_completion(hdr); + hdr->completion_ops->completion(hdr); } static @@ -108,9 +109,10 @@ int nfs_return_empty_page(struct page *page) } void nfs_pageio_init_read_mds(struct nfs_pageio_descriptor *pgio, - struct inode *inode) + struct inode *inode, + const struct nfs_pgio_completion_ops *compl_ops) { - nfs_pageio_init(pgio, inode, &nfs_pageio_read_ops, + nfs_pageio_init(pgio, inode, &nfs_pageio_read_ops, compl_ops, NFS_SERVER(inode)->rsize, 0); } @@ -122,10 +124,11 @@ void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio) EXPORT_SYMBOL_GPL(nfs_pageio_reset_read_mds); static void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, - struct inode *inode) + struct inode *inode, + const struct nfs_pgio_completion_ops *compl_ops) { - if (!pnfs_pageio_init_read(pgio, inode)) - nfs_pageio_init_read_mds(pgio, inode); + if (!pnfs_pageio_init_read(pgio, inode, compl_ops)) + nfs_pageio_init_read_mds(pgio, inode, compl_ops); } int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode, @@ -146,7 +149,7 @@ 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_pageio_init_read(&pgio, inode); + nfs_pageio_init_read(&pgio, inode, &nfs_async_read_completion_ops); nfs_pageio_add_request(&pgio, new); nfs_pageio_complete(&pgio); return 0; @@ -170,7 +173,7 @@ static void nfs_readpage_release(struct nfs_page *req) } /* Note io was page aligned */ -void nfs_read_completion(struct nfs_pgio_header *hdr) +static void nfs_read_completion(struct nfs_pgio_header *hdr) { unsigned long bytes = 0; @@ -300,7 +303,7 @@ nfs_do_multiple_reads(struct list_head *head, return ret; } -void +static void nfs_async_read_error(struct list_head *head) { struct nfs_page *req; @@ -312,6 +315,11 @@ nfs_async_read_error(struct list_head *head) } } +static const struct nfs_pgio_completion_ops nfs_async_read_completion_ops = { + .error_cleanup = nfs_async_read_error, + .completion = nfs_read_completion, +}; + /* * Generate multiple requests to fill a single page. * @@ -362,7 +370,7 @@ out_bad: list_del(&data->list); nfs_readdata_release(data); } - nfs_async_read_error(&hdr->pages); + desc->pg_completion_ops->error_cleanup(&hdr->pages); return -ENOMEM; } @@ -378,7 +386,7 @@ static int nfs_pagein_one(struct nfs_pageio_descriptor *desc, data = nfs_readdata_alloc(hdr, nfs_page_array_len(desc->pg_base, desc->pg_count)); if (!data) { - nfs_async_read_error(head); + desc->pg_completion_ops->error_cleanup(head); ret = -ENOMEM; goto out; } @@ -414,7 +422,7 @@ static int nfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc) rhdr = nfs_readhdr_alloc(); if (!rhdr) { - nfs_async_read_error(&desc->pg_list); + desc->pg_completion_ops->error_cleanup(&desc->pg_list); return -ENOMEM; } hdr = &rhdr->header; @@ -427,7 +435,7 @@ static int nfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc) else set_bit(NFS_IOHDR_REDO, &hdr->flags); if (atomic_dec_and_test(&hdr->refcnt)) - nfs_read_completion(hdr); + hdr->completion_ops->completion(hdr); return ret; } @@ -652,7 +660,7 @@ int nfs_readpages(struct file *filp, struct address_space *mapping, if (ret == 0) goto read_complete; /* all pages were read */ - nfs_pageio_init_read(&pgio, inode); + nfs_pageio_init_read(&pgio, inode, &nfs_async_read_completion_ops); ret = read_cache_pages(mapping, pages, readpage_async_filler, &desc); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 076075eb676c..150397279b8d 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -40,10 +40,12 @@ * Local function declarations */ static void nfs_pageio_init_write(struct nfs_pageio_descriptor *desc, - struct inode *inode, int ioflags); + struct inode *inode, int ioflags, + const struct nfs_pgio_completion_ops *compl_ops); 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 struct kmem_cache *nfs_wdata_cachep; static mempool_t *nfs_wdata_mempool; @@ -128,7 +130,7 @@ void nfs_writedata_release(struct nfs_write_data *wdata) else wdata->header = NULL; if (atomic_dec_and_test(&hdr->refcnt)) - nfs_write_completion(hdr); + hdr->completion_ops->completion(hdr); } static void nfs_context_set_write_error(struct nfs_open_context *ctx, int error) @@ -337,7 +339,8 @@ static int nfs_writepage_locked(struct page *page, struct writeback_control *wbc struct nfs_pageio_descriptor pgio; int err; - nfs_pageio_init_write(&pgio, page->mapping->host, wb_priority(wbc)); + nfs_pageio_init_write(&pgio, page->mapping->host, wb_priority(wbc), + &nfs_async_write_completion_ops); err = nfs_do_writepage(page, wbc, &pgio); nfs_pageio_complete(&pgio); if (err < 0) @@ -380,7 +383,8 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc) nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGES); - nfs_pageio_init_write(&pgio, inode, wb_priority(wbc)); + nfs_pageio_init_write(&pgio, inode, wb_priority(wbc), + &nfs_async_write_completion_ops); err = write_cache_pages(mapping, wbc, nfs_writepages_callback, &pgio); nfs_pageio_complete(&pgio); @@ -558,7 +562,7 @@ int nfs_write_need_commit(struct nfs_write_data *data) #endif -void nfs_write_completion(struct nfs_pgio_header *hdr) +static void nfs_write_completion(struct nfs_pgio_header *hdr) { unsigned long bytes = 0; @@ -1000,7 +1004,7 @@ static void nfs_redirty_request(struct nfs_page *req) nfs_end_page_writeback(page); } -void nfs_async_write_error(struct list_head *head) +static void nfs_async_write_error(struct list_head *head) { struct nfs_page *req; @@ -1011,6 +1015,11 @@ void nfs_async_write_error(struct list_head *head) } } +static const struct nfs_pgio_completion_ops nfs_async_write_completion_ops = { + .error_cleanup = nfs_async_write_error, + .completion = nfs_write_completion, +}; + /* * Generate multiple small requests to write out a single * contiguous dirty area on one page. @@ -1060,7 +1069,7 @@ out_bad: list_del(&data->list); nfs_writedata_release(data); } - nfs_async_write_error(&hdr->pages); + desc->pg_completion_ops->error_cleanup(&hdr->pages); return -ENOMEM; } @@ -1084,7 +1093,7 @@ static int nfs_flush_one(struct nfs_pageio_descriptor *desc, data = nfs_writedata_alloc(hdr, nfs_page_array_len(desc->pg_base, desc->pg_count)); if (!data) { - nfs_async_write_error(head); + desc->pg_completion_ops->error_cleanup(head); ret = -ENOMEM; goto out; } @@ -1125,7 +1134,7 @@ static int nfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc) whdr = nfs_writehdr_alloc(); if (!whdr) { - nfs_async_write_error(&desc->pg_list); + desc->pg_completion_ops->error_cleanup(&hdr->pages); return -ENOMEM; } hdr = &whdr->header; @@ -1139,7 +1148,7 @@ static int nfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc) else set_bit(NFS_IOHDR_REDO, &hdr->flags); if (atomic_dec_and_test(&hdr->refcnt)) - nfs_write_completion(hdr); + hdr->completion_ops->completion(hdr); return ret; } @@ -1149,9 +1158,10 @@ static const struct nfs_pageio_ops nfs_pageio_write_ops = { }; void nfs_pageio_init_write_mds(struct nfs_pageio_descriptor *pgio, - struct inode *inode, int ioflags) + struct inode *inode, int ioflags, + const struct nfs_pgio_completion_ops *compl_ops) { - nfs_pageio_init(pgio, inode, &nfs_pageio_write_ops, + nfs_pageio_init(pgio, inode, &nfs_pageio_write_ops, compl_ops, NFS_SERVER(inode)->wsize, ioflags); } @@ -1163,10 +1173,11 @@ void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio) EXPORT_SYMBOL_GPL(nfs_pageio_reset_write_mds); static void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, - struct inode *inode, int ioflags) + struct inode *inode, int ioflags, + const struct nfs_pgio_completion_ops *compl_ops) { - if (!pnfs_pageio_init_write(pgio, inode, ioflags)) - nfs_pageio_init_write_mds(pgio, inode, ioflags); + if (!pnfs_pageio_init_write(pgio, inode, ioflags, compl_ops)) + nfs_pageio_init_write_mds(pgio, inode, ioflags, compl_ops); } void nfs_write_prepare(struct rpc_task *task, void *calldata) diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 5c520344d8ad..bc5b7a5e787e 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -67,6 +67,7 @@ struct nfs_pageio_descriptor { int pg_ioflags; int pg_error; const struct rpc_call_ops *pg_rpc_callops; + const struct nfs_pgio_completion_ops *pg_completion_ops; struct pnfs_layout_segment *pg_lseg; }; @@ -83,6 +84,7 @@ extern void nfs_release_request(struct nfs_page *req); extern 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, size_t bsize, int how); extern int nfs_pageio_add_request(struct nfs_pageio_descriptor *, diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 0d17db7973de..6fa1d2278c9d 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1207,6 +1207,7 @@ struct nfs_pgio_header { loff_t io_start; const struct rpc_call_ops *mds_ops; void (*release) (struct nfs_pgio_header *hdr); + const struct nfs_pgio_completion_ops *completion_ops; spinlock_t lock; /* fields protected by lock */ int pnfs_error; @@ -1261,6 +1262,11 @@ struct nfs_commit_data { int (*commit_done_cb) (struct rpc_task *task, struct nfs_commit_data *data); }; +struct nfs_pgio_completion_ops { + void (*error_cleanup)(struct list_head *head); + void (*completion)(struct nfs_pgio_header *hdr); +}; + struct nfs_unlinkdata { struct hlist_node list; struct nfs_removeargs args; -- cgit v1.2.3 From 9533da2979757258d3fd5429d830a297013d69ed Mon Sep 17 00:00:00 2001 From: Fred Isaman Date: Fri, 20 Apr 2012 14:47:49 -0400 Subject: NFS: remove unused wb_complete field from struct nfs_page Signed-off-by: Fred Isaman Signed-off-by: Trond Myklebust --- fs/nfs/pagelist.c | 1 - fs/nfs/write.c | 1 - include/linux/nfs_page.h | 1 - 3 files changed, 3 deletions(-) (limited to 'include') diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 4cf2a68493e0..5d01a1651084 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -114,7 +114,6 @@ nfs_create_request(struct nfs_open_context *ctx, struct inode *inode, * long write-back delay. This will be adjusted in * update_nfs_request below if the region is not locked. */ req->wb_page = page; - atomic_set(&req->wb_complete, 0); req->wb_index = page->index; page_cache_get(page); BUG_ON(PagePrivate(page)); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 150397279b8d..705bf01cfbba 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1059,7 +1059,6 @@ static int nfs_flush_multi(struct nfs_pageio_descriptor *desc, nbytes -= len; offset += len; } while (nbytes != 0); - atomic_set(&req->wb_complete, requests); desc->pg_rpc_callops = &nfs_write_common_ops; return ret; diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index bc5b7a5e787e..0a5b63f16116 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -36,7 +36,6 @@ struct nfs_page { struct page *wb_page; /* page to read in/write out */ struct nfs_open_context *wb_context; /* File state context info */ struct nfs_lock_context *wb_lock_context; /* lock context info */ - atomic_t wb_complete; /* i/os we're waiting for */ pgoff_t wb_index; /* Offset >> PAGE_CACHE_SHIFT */ unsigned int wb_offset, /* Offset & ~PAGE_CACHE_MASK */ wb_pgbase, /* Start of page data */ -- cgit v1.2.3 From 584aa810b6240d88c28113a90c5029449814a3b5 Mon Sep 17 00:00:00 2001 From: Fred Isaman Date: Fri, 20 Apr 2012 14:47:51 -0400 Subject: NFS: rewrite directio read to use async coalesce code This also has the advantage that it allows directio to use pnfs. Signed-off-by: Fred Isaman Signed-off-by: Trond Myklebust --- fs/nfs/direct.c | 255 +++++++++++++++++++++++------------------------ fs/nfs/internal.h | 5 +- fs/nfs/pagelist.c | 7 +- fs/nfs/read.c | 10 +- include/linux/nfs_page.h | 1 + include/linux/nfs_xdr.h | 4 +- 6 files changed, 138 insertions(+), 144 deletions(-) (limited to 'include') diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 22a40c408449..4ba9a2c839bb 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -124,22 +124,6 @@ ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, loff_ return -EINVAL; } -static void nfs_direct_dirty_pages(struct page **pages, unsigned int pgbase, size_t count) -{ - unsigned int npages; - unsigned int i; - - if (count == 0) - return; - pages += (pgbase >> PAGE_SHIFT); - npages = (count + (pgbase & ~PAGE_MASK) + PAGE_SIZE - 1) >> PAGE_SHIFT; - for (i = 0; i < npages; i++) { - struct page *page = pages[i]; - if (!PageCompound(page)) - set_page_dirty(page); - } -} - static void nfs_direct_release_pages(struct page **pages, unsigned int npages) { unsigned int i; @@ -226,58 +210,92 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq) nfs_direct_req_release(dreq); } -/* - * We must hold a reference to all the pages in this direct read request - * until the RPCs complete. This could be long *after* we are woken up in - * nfs_direct_wait (for instance, if someone hits ^C on a slow server). - */ -static void nfs_direct_read_result(struct rpc_task *task, void *calldata) +void nfs_direct_readpage_release(struct nfs_page *req) { - struct nfs_read_data *data = calldata; - - nfs_readpage_result(task, data); + dprintk("NFS: direct read done (%s/%lld %d@%lld)\n", + req->wb_context->dentry->d_inode->i_sb->s_id, + (long long)NFS_FILEID(req->wb_context->dentry->d_inode), + req->wb_bytes, + (long long)req_offset(req)); + nfs_release_request(req); } -static void nfs_direct_read_release(void *calldata) +static void nfs_direct_read_completion(struct nfs_pgio_header *hdr) { + unsigned long bytes = 0; + struct nfs_direct_req *dreq = hdr->dreq; - struct nfs_read_data *data = calldata; - struct nfs_direct_req *dreq = (struct nfs_direct_req *)data->header->req; - int status = data->task.tk_status; + if (test_bit(NFS_IOHDR_REDO, &hdr->flags)) + goto out_put; spin_lock(&dreq->lock); - if (unlikely(status < 0)) { - dreq->error = status; - spin_unlock(&dreq->lock); + if (test_bit(NFS_IOHDR_ERROR, &hdr->flags) && (hdr->good_bytes == 0)) + dreq->error = hdr->error; + else + dreq->count += hdr->good_bytes; + spin_unlock(&dreq->lock); + + if (!test_bit(NFS_IOHDR_ERROR, &hdr->flags)) { + while (!list_empty(&hdr->pages)) { + struct nfs_page *req = nfs_list_entry(hdr->pages.next); + struct page *page = req->wb_page; + + 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); + } + bytes += req->wb_bytes; + nfs_list_remove_request(req); + nfs_direct_readpage_release(req); + if (!PageCompound(page)) + set_page_dirty(page); + page_cache_release(page); + } } else { - dreq->count += data->res.count; - spin_unlock(&dreq->lock); - nfs_direct_dirty_pages(data->pages.pagevec, - data->args.pgbase, - data->res.count); + while (!list_empty(&hdr->pages)) { + struct nfs_page *req = nfs_list_entry(hdr->pages.next); + + if (bytes < hdr->good_bytes) + if (!PageCompound(req->wb_page)) + set_page_dirty(req->wb_page); + bytes += req->wb_bytes; + page_cache_release(req->wb_page); + nfs_list_remove_request(req); + nfs_direct_readpage_release(req); + } } - nfs_direct_release_pages(data->pages.pagevec, data->pages.npages); - +out_put: if (put_dreq(dreq)) nfs_direct_complete(dreq); - nfs_readdata_release(data); + hdr->release(hdr); } -static const struct rpc_call_ops nfs_read_direct_ops = { - .rpc_call_prepare = nfs_read_prepare, - .rpc_call_done = nfs_direct_read_result, - .rpc_release = nfs_direct_read_release, -}; - -static void nfs_direct_readhdr_release(struct nfs_read_header *rhdr) +static void nfs_sync_pgio_error(struct list_head *head) { - struct nfs_read_data *data = &rhdr->rpc_data; + struct nfs_page *req; - if (data->pages.pagevec != data->pages.page_array) - kfree(data->pages.pagevec); - nfs_readhdr_free(&rhdr->header); + while (!list_empty(head)) { + req = nfs_list_entry(head->next); + nfs_list_remove_request(req); + nfs_release_request(req); + } } +static void nfs_direct_pgio_init(struct nfs_pgio_header *hdr) +{ + get_dreq(hdr->dreq); +} + +static const struct nfs_pgio_completion_ops nfs_direct_read_completion_ops = { + .error_cleanup = nfs_sync_pgio_error, + .init_hdr = nfs_direct_pgio_init, + .completion = nfs_direct_read_completion, +}; + /* * For each rsize'd chunk of the user's buffer, dispatch an NFS READ * operation. If nfs_readdata_alloc() or get_user_pages() fails, @@ -285,118 +303,85 @@ static void nfs_direct_readhdr_release(struct nfs_read_header *rhdr) * handled automatically by nfs_direct_read_result(). Otherwise, if * no requests have been sent, just return an error. */ -static ssize_t nfs_direct_read_schedule_segment(struct nfs_direct_req *dreq, +static ssize_t nfs_direct_read_schedule_segment(struct nfs_pageio_descriptor *desc, const struct iovec *iov, loff_t pos) { + struct nfs_direct_req *dreq = desc->pg_dreq; struct nfs_open_context *ctx = dreq->ctx; struct inode *inode = ctx->dentry->d_inode; unsigned long user_addr = (unsigned long)iov->iov_base; size_t count = iov->iov_len; size_t rsize = NFS_SERVER(inode)->rsize; - struct rpc_task *task; - struct rpc_message msg = { - .rpc_cred = ctx->cred, - }; - struct rpc_task_setup task_setup_data = { - .rpc_client = NFS_CLIENT(inode), - .rpc_message = &msg, - .callback_ops = &nfs_read_direct_ops, - .workqueue = nfsiod_workqueue, - .flags = RPC_TASK_ASYNC, - }; unsigned int pgbase; int result; ssize_t started = 0; + struct page **pagevec = NULL; + unsigned int npages; do { - struct nfs_read_header *rhdr; - struct nfs_read_data *data; - struct nfs_page_array *pages; size_t bytes; + int i; pgbase = user_addr & ~PAGE_MASK; - bytes = min(rsize,count); + bytes = min(max(rsize, PAGE_SIZE), count); result = -ENOMEM; - rhdr = nfs_readhdr_alloc(); - if (unlikely(!rhdr)) - break; - data = nfs_readdata_alloc(&rhdr->header, nfs_page_array_len(pgbase, bytes)); - if (!data) { - nfs_readhdr_free(&rhdr->header); + npages = nfs_page_array_len(pgbase, bytes); + if (!pagevec) + pagevec = kmalloc(npages * sizeof(struct page *), + GFP_KERNEL); + if (!pagevec) break; - } - data->header = &rhdr->header; - atomic_inc(&data->header->refcnt); - pages = &data->pages; - down_read(¤t->mm->mmap_sem); result = get_user_pages(current, current->mm, user_addr, - pages->npages, 1, 0, pages->pagevec, NULL); + npages, 1, 0, pagevec, NULL); up_read(¤t->mm->mmap_sem); - if (result < 0) { - nfs_direct_readhdr_release(rhdr); + if (result < 0) break; - } - if ((unsigned)result < pages->npages) { + if ((unsigned)result < npages) { bytes = result * PAGE_SIZE; if (bytes <= pgbase) { - nfs_direct_release_pages(pages->pagevec, result); - nfs_direct_readhdr_release(rhdr); + nfs_direct_release_pages(pagevec, result); break; } bytes -= pgbase; - pages->npages = result; + npages = result; } - get_dreq(dreq); - - rhdr->header.req = (struct nfs_page *) dreq; - rhdr->header.inode = inode; - rhdr->header.cred = msg.rpc_cred; - data->args.fh = NFS_FH(inode); - data->args.context = get_nfs_open_context(ctx); - data->args.lock_context = dreq->l_ctx; - data->args.offset = pos; - data->args.pgbase = pgbase; - data->args.pages = pages->pagevec; - data->args.count = bytes; - data->res.fattr = &data->fattr; - data->res.eof = 0; - data->res.count = bytes; - nfs_fattr_init(&data->fattr); - msg.rpc_argp = &data->args; - msg.rpc_resp = &data->res; - - task_setup_data.task = &data->task; - task_setup_data.callback_data = data; - NFS_PROTO(inode)->read_setup(data, &msg); - - task = rpc_run_task(&task_setup_data); - if (IS_ERR(task)) - break; - - dprintk("NFS: %5u initiated direct read call " - "(req %s/%Ld, %zu bytes @ offset %Lu)\n", - task->tk_pid, - inode->i_sb->s_id, - (long long)NFS_FILEID(inode), - bytes, - (unsigned long long)data->args.offset); - rpc_put_task(task); - - started += bytes; - user_addr += bytes; - pos += bytes; - /* FIXME: Remove this unnecessary math from final patch */ - pgbase += bytes; - pgbase &= ~PAGE_MASK; - BUG_ON(pgbase != (user_addr & ~PAGE_MASK)); - - count -= bytes; + for (i = 0; i < npages; i++) { + struct nfs_page *req; + unsigned int req_len = min(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], + pgbase, req_len); + if (IS_ERR(req)) { + nfs_direct_release_pages(pagevec + i, + npages - i); + result = PTR_ERR(req); + break; + } + req->wb_index = pos >> PAGE_SHIFT; + req->wb_offset = pos & ~PAGE_MASK; + if (!nfs_pageio_add_request(desc, req)) { + result = desc->pg_error; + nfs_release_request(req); + nfs_direct_release_pages(pagevec + i, + npages - i); + break; + } + pgbase = 0; + bytes -= req_len; + started += req_len; + user_addr += req_len; + pos += req_len; + count -= req_len; + } } while (count != 0); + kfree(pagevec); + if (started) return started; return result < 0 ? (ssize_t) result : -EFAULT; @@ -407,15 +392,19 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, unsigned long nr_segs, loff_t pos) { + struct nfs_pageio_descriptor desc; ssize_t result = -EINVAL; size_t requested_bytes = 0; unsigned long seg; + nfs_pageio_init_read(&desc, dreq->inode, + &nfs_direct_read_completion_ops); get_dreq(dreq); + desc.pg_dreq = dreq; for (seg = 0; seg < nr_segs; seg++) { const struct iovec *vec = &iov[seg]; - result = nfs_direct_read_schedule_segment(dreq, vec, pos); + result = nfs_direct_read_schedule_segment(&desc, vec, pos); if (result < 0) break; requested_bytes += result; @@ -424,6 +413,8 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, pos += vec->iov_len; } + nfs_pageio_complete(&desc); + /* * If no bytes were started, return the error, and let the * generic layer handle the completion. diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 3ef8fcda1a5f..cd5d4a300bc9 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -304,8 +304,9 @@ 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 struct nfs_read_data *nfs_readdata_alloc(struct nfs_pgio_header *hdr, - unsigned int pagecount); +extern void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, + struct inode *inode, + 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); diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 638ca7f5a1e4..33a21ca9b84b 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -48,8 +48,11 @@ void nfs_pgheader_init(struct nfs_pageio_descriptor *desc, hdr->cred = hdr->req->wb_context->cred; hdr->io_start = req_offset(hdr->req); hdr->good_bytes = desc->pg_count; + hdr->dreq = desc->pg_dreq; hdr->release = release; hdr->completion_ops = desc->pg_completion_ops; + if (hdr->completion_ops->init_hdr) + hdr->completion_ops->init_hdr(hdr); } void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos) @@ -116,9 +119,6 @@ nfs_create_request(struct nfs_open_context *ctx, struct inode *inode, req->wb_page = page; req->wb_index = page->index; page_cache_get(page); - BUG_ON(PagePrivate(page)); - BUG_ON(!PageLocked(page)); - BUG_ON(page->mapping->host != inode); req->wb_offset = offset; req->wb_pgbase = offset; req->wb_bytes = count; @@ -257,6 +257,7 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc, desc->pg_ioflags = io_flags; desc->pg_error = 0; desc->pg_lseg = NULL; + desc->pg_dreq = NULL; } /** diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 5e78af162039..35e2dcebffe6 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -51,8 +51,8 @@ struct nfs_read_header *nfs_readhdr_alloc() return rhdr; } -struct nfs_read_data *nfs_readdata_alloc(struct nfs_pgio_header *hdr, - unsigned int pagecount) +static struct nfs_read_data *nfs_readdata_alloc(struct nfs_pgio_header *hdr, + unsigned int pagecount) { struct nfs_read_data *data, *prealloc; @@ -123,9 +123,9 @@ void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio) } EXPORT_SYMBOL_GPL(nfs_pageio_reset_read_mds); -static void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, - struct inode *inode, - const struct nfs_pgio_completion_ops *compl_ops) +void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, + struct inode *inode, + const struct nfs_pgio_completion_ops *compl_ops) { if (!pnfs_pageio_init_read(pgio, inode, compl_ops)) nfs_pageio_init_read_mds(pgio, inode, compl_ops); diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 0a5b63f16116..f9ee9eba7f88 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -68,6 +68,7 @@ struct nfs_pageio_descriptor { const struct rpc_call_ops *pg_rpc_callops; const struct nfs_pgio_completion_ops *pg_completion_ops; struct pnfs_layout_segment *pg_lseg; + struct nfs_direct_req *pg_dreq; }; #define NFS_WBACK_BUSY(req) (test_bit(PG_BUSY,&(req)->wb_flags)) diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 6fa1d2278c9d..38687b87ca9b 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1208,6 +1208,7 @@ struct nfs_pgio_header { const struct rpc_call_ops *mds_ops; void (*release) (struct nfs_pgio_header *hdr); const struct nfs_pgio_completion_ops *completion_ops; + struct nfs_direct_req *dreq; spinlock_t lock; /* fields protected by lock */ int pnfs_error; @@ -1221,8 +1222,6 @@ struct nfs_read_header { struct nfs_read_data rpc_data; }; -struct nfs_direct_req; - struct nfs_write_data { struct nfs_pgio_header *header; struct list_head list; @@ -1264,6 +1263,7 @@ struct nfs_commit_data { struct nfs_pgio_completion_ops { void (*error_cleanup)(struct list_head *head); + void (*init_hdr)(struct nfs_pgio_header *hdr); void (*completion)(struct nfs_pgio_header *hdr); }; -- cgit v1.2.3 From ea2cf2282b4278461266013e9c002ee1c66700ff Mon Sep 17 00:00:00 2001 From: Fred Isaman Date: Fri, 20 Apr 2012 14:47:53 -0400 Subject: NFS: create struct nfs_commit_info It is COMMIT that is handled the most differently between the paged and direct paths. Create a structure that encapsulates everything either path needs to know about the commit state. We could use void to hide some of the layout driver stuff, but Trond suggests pulling it out to ensure type checking, given the huge changes being made, and the fact that it doesn't interfere with other drivers. Signed-off-by: Fred Isaman Signed-off-by: Trond Myklebust --- fs/nfs/inode.c | 6 +- fs/nfs/internal.h | 12 +++- fs/nfs/nfs4filelayout.c | 119 ++++++++++++++++++++---------------- fs/nfs/nfs4filelayout.h | 14 +---- fs/nfs/pnfs.h | 72 ++++++++++++++-------- fs/nfs/write.c | 158 ++++++++++++++++++++++++++++-------------------- include/linux/nfs_fs.h | 5 +- include/linux/nfs_xdr.h | 27 +++++++++ 8 files changed, 248 insertions(+), 165 deletions(-) (limited to 'include') diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index e8bbfa5b3500..59a12c6a8df6 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -1547,7 +1547,7 @@ static inline void nfs4_init_once(struct nfs_inode *nfsi) nfsi->delegation_state = 0; init_rwsem(&nfsi->rwsem); nfsi->layout = NULL; - atomic_set(&nfsi->commits_outstanding, 0); + atomic_set(&nfsi->commit_info.rpcs_out, 0); #endif } @@ -1559,9 +1559,9 @@ static void init_once(void *foo) INIT_LIST_HEAD(&nfsi->open_files); INIT_LIST_HEAD(&nfsi->access_cache_entry_lru); INIT_LIST_HEAD(&nfsi->access_cache_inode_lru); - INIT_LIST_HEAD(&nfsi->commit_list); + INIT_LIST_HEAD(&nfsi->commit_info.list); nfsi->npages = 0; - nfsi->ncommit = 0; + nfsi->commit_info.ncommit = 0; atomic_set(&nfsi->silly_count, 1); INIT_HLIST_HEAD(&nfsi->silly_list); init_waitqueue_head(&nfsi->waitqueue); diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index cd5d4a300bc9..145e9e7dc8ce 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -346,12 +346,18 @@ extern void nfs_init_commit(struct nfs_commit_data *data, struct list_head *head, struct pnfs_layout_segment *lseg); void nfs_retry_commit(struct list_head *page_list, - struct pnfs_layout_segment *lseg); + struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo); void nfs_commit_clear_lock(struct nfs_inode *nfsi); void nfs_commitdata_release(struct nfs_commit_data *data); void nfs_commit_release_pages(struct nfs_commit_data *data); -void nfs_request_add_commit_list(struct nfs_page *req, struct list_head *head); -void nfs_request_remove_commit_list(struct nfs_page *req); +void nfs_request_add_commit_list(struct nfs_page *req, struct list_head *dst, + struct nfs_commit_info *cinfo); +void nfs_request_remove_commit_list(struct nfs_page *req, + struct nfs_commit_info *cinfo); +void nfs_init_cinfo(struct nfs_commit_info *cinfo, + struct inode *inode, + struct nfs_direct_req *dreq); #ifdef CONFIG_MIGRATION extern int nfs_migrate_page(struct address_space *, diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c index e40523f2fe26..fe2cb55ca6b1 100644 --- a/fs/nfs/nfs4filelayout.c +++ b/fs/nfs/nfs4filelayout.c @@ -347,9 +347,11 @@ static void filelayout_commit_count_stats(struct rpc_task *task, void *data) static void filelayout_commit_release(void *calldata) { struct nfs_commit_data *data = calldata; + struct nfs_commit_info cinfo; nfs_commit_release_pages(data); - if (atomic_dec_and_test(&NFS_I(data->inode)->commits_outstanding)) + nfs_init_cinfo(&cinfo, data->inode, data->dreq); + if (atomic_dec_and_test(&cinfo.mds->rpcs_out)) nfs_commit_clear_lock(NFS_I(data->inode)); put_lseg(data->lseg); nfs_commitdata_release(data); @@ -695,17 +697,16 @@ filelayout_free_lseg(struct pnfs_layout_segment *lseg) static int filelayout_alloc_commit_info(struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo, gfp_t gfp_flags) { struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg); - struct nfs4_filelayout *flo = FILELAYOUT_FROM_HDR(lseg->pls_layout); - - struct nfs4_fl_commit_bucket *buckets; + struct pnfs_commit_bucket *buckets; int size; if (fl->commit_through_mds) return 0; - if (flo->commit_info.nbuckets != 0) { + if (cinfo->ds->nbuckets != 0) { /* This assumes there is only one IOMODE_RW lseg. What * we really want to do is have a layout_hdr level * dictionary of keys, each @@ -718,25 +719,25 @@ filelayout_alloc_commit_info(struct pnfs_layout_segment *lseg, size = (fl->stripe_type == STRIPE_SPARSE) ? fl->dsaddr->ds_num : fl->dsaddr->stripe_count; - buckets = kcalloc(size, sizeof(struct nfs4_fl_commit_bucket), + buckets = kcalloc(size, sizeof(struct pnfs_commit_bucket), gfp_flags); if (!buckets) return -ENOMEM; else { int i; - spin_lock(&lseg->pls_layout->plh_inode->i_lock); - if (flo->commit_info.nbuckets != 0) + spin_lock(cinfo->lock); + if (cinfo->ds->nbuckets != 0) kfree(buckets); else { - flo->commit_info.buckets = buckets; - flo->commit_info.nbuckets = size; + 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(&lseg->pls_layout->plh_inode->i_lock); + spin_unlock(cinfo->lock); return 0; } } @@ -821,6 +822,7 @@ static void filelayout_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) { + struct nfs_commit_info cinfo; int status; BUG_ON(pgio->pg_lseg != NULL); @@ -836,7 +838,8 @@ filelayout_pg_init_write(struct nfs_pageio_descriptor *pgio, /* If no lseg, fall back to write through mds */ if (pgio->pg_lseg == NULL) goto out_mds; - status = filelayout_alloc_commit_info(pgio->pg_lseg, GFP_NOFS); + nfs_init_cinfo(&cinfo, pgio->pg_inode, pgio->pg_dreq); + status = filelayout_alloc_commit_info(pgio->pg_lseg, &cinfo, GFP_NOFS); if (status < 0) { put_lseg(pgio->pg_lseg); pgio->pg_lseg = NULL; @@ -871,40 +874,42 @@ static u32 select_bucket_index(struct nfs4_filelayout_segment *fl, u32 j) * If this will make the bucket empty, it will need to put the lseg reference. */ static void -filelayout_clear_request_commit(struct nfs_page *req) +filelayout_clear_request_commit(struct nfs_page *req, + struct nfs_commit_info *cinfo) { struct pnfs_layout_segment *freeme = NULL; - struct inode *inode = req->wb_context->dentry->d_inode; - spin_lock(&inode->i_lock); + spin_lock(cinfo->lock); if (!test_and_clear_bit(PG_COMMIT_TO_DS, &req->wb_flags)) goto out; + cinfo->ds->nwritten--; if (list_is_singular(&req->wb_list)) { - struct nfs4_fl_commit_bucket *bucket; + struct pnfs_commit_bucket *bucket; bucket = list_first_entry(&req->wb_list, - struct nfs4_fl_commit_bucket, + struct pnfs_commit_bucket, written); freeme = bucket->wlseg; bucket->wlseg = NULL; } out: - nfs_request_remove_commit_list(req); - spin_unlock(&inode->i_lock); + nfs_request_remove_commit_list(req, cinfo); + spin_unlock(cinfo->lock); put_lseg(freeme); } static struct list_head * filelayout_choose_commit_list(struct nfs_page *req, - struct pnfs_layout_segment *lseg) + struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo) { struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg); u32 i, j; struct list_head *list; - struct nfs4_fl_commit_bucket *buckets; + struct pnfs_commit_bucket *buckets; if (fl->commit_through_mds) - return &NFS_I(req->wb_context->dentry->d_inode)->commit_list; + return &cinfo->mds->list; /* Note that we are calling nfs4_fl_calc_j_index on each page * that ends up being committed to a data server. An attractive @@ -914,7 +919,7 @@ filelayout_choose_commit_list(struct nfs_page *req, */ j = nfs4_fl_calc_j_index(lseg, req_offset(req)); i = select_bucket_index(fl, j); - buckets = FILELAYOUT_FROM_HDR(lseg->pls_layout)->commit_info.buckets; + buckets = cinfo->ds->buckets; list = &buckets[i].written; if (list_empty(list)) { /* Non-empty buckets hold a reference on the lseg. That ref @@ -926,17 +931,19 @@ filelayout_choose_commit_list(struct nfs_page *req, buckets[i].wlseg = get_lseg(lseg); } set_bit(PG_COMMIT_TO_DS, &req->wb_flags); + cinfo->ds->nwritten++; return list; } static void filelayout_mark_request_commit(struct nfs_page *req, - struct pnfs_layout_segment *lseg) + struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo) { struct list_head *list; - list = filelayout_choose_commit_list(req, lseg); - nfs_request_add_commit_list(req, list); + list = filelayout_choose_commit_list(req, lseg, cinfo); + nfs_request_add_commit_list(req, list, cinfo); } static u32 calc_ds_index_from_commit(struct pnfs_layout_segment *lseg, u32 i) @@ -993,8 +1000,9 @@ static int filelayout_initiate_commit(struct nfs_commit_data *data, int how) } static int -filelayout_scan_ds_commit_list(struct nfs4_fl_commit_bucket *bucket, int max, - spinlock_t *lock) +filelayout_scan_ds_commit_list(struct pnfs_commit_bucket *bucket, + struct nfs_commit_info *cinfo, + int max) { struct list_head *src = &bucket->written; struct list_head *dst = &bucket->committing; @@ -1004,9 +1012,9 @@ filelayout_scan_ds_commit_list(struct nfs4_fl_commit_bucket *bucket, int max, list_for_each_entry_safe(req, tmp, src, wb_list) { if (!nfs_lock_request(req)) continue; - if (cond_resched_lock(lock)) + if (cond_resched_lock(cinfo->lock)) list_safe_reset_next(req, tmp, wb_list); - nfs_request_remove_commit_list(req); + nfs_request_remove_commit_list(req, cinfo); clear_bit(PG_COMMIT_TO_DS, &req->wb_flags); nfs_list_add_request(req, dst); ret++; @@ -1014,6 +1022,8 @@ filelayout_scan_ds_commit_list(struct nfs4_fl_commit_bucket *bucket, int max, break; } if (ret) { + cinfo->ds->nwritten -= ret; + cinfo->ds->ncommitting += ret; bucket->clseg = bucket->wlseg; if (list_empty(src)) bucket->wlseg = NULL; @@ -1024,37 +1034,32 @@ filelayout_scan_ds_commit_list(struct nfs4_fl_commit_bucket *bucket, int max, } /* Move reqs from written to committing lists, returning count of number moved. - * Note called with i_lock held. + * Note called with cinfo->lock held. */ -static int filelayout_scan_commit_lists(struct inode *inode, int max, - spinlock_t *lock) +static int filelayout_scan_commit_lists(struct nfs_commit_info *cinfo, + int max) { - struct nfs4_fl_commit_info *fl_cinfo; int i, rv = 0, cnt; - fl_cinfo = &FILELAYOUT_FROM_HDR(NFS_I(inode)->layout)->commit_info; - if (fl_cinfo->nbuckets == 0) - goto out_done; - for (i = 0; i < fl_cinfo->nbuckets && max != 0; i++) { - cnt = filelayout_scan_ds_commit_list(&fl_cinfo->buckets[i], - max, lock); + for (i = 0; i < cinfo->ds->nbuckets && max != 0; i++) { + cnt = filelayout_scan_ds_commit_list(&cinfo->ds->buckets[i], + cinfo, max); max -= cnt; rv += cnt; } -out_done: return rv; } static unsigned int -alloc_ds_commits(struct inode *inode, struct list_head *list) +alloc_ds_commits(struct nfs_commit_info *cinfo, struct list_head *list) { - struct nfs4_fl_commit_info *fl_cinfo; - struct nfs4_fl_commit_bucket *bucket; + struct pnfs_ds_commit_info *fl_cinfo; + struct pnfs_commit_bucket *bucket; struct nfs_commit_data *data; int i, j; unsigned int nreq = 0; - fl_cinfo = &FILELAYOUT_FROM_HDR(NFS_I(inode)->layout)->commit_info; + fl_cinfo = cinfo->ds; bucket = fl_cinfo->buckets; for (i = 0; i < fl_cinfo->nbuckets; i++, bucket++) { if (list_empty(&bucket->committing)) @@ -1073,7 +1078,7 @@ alloc_ds_commits(struct inode *inode, struct list_head *list) for (j = i; j < fl_cinfo->nbuckets; j++, bucket++) { if (list_empty(&bucket->committing)) continue; - nfs_retry_commit(&bucket->committing, bucket->clseg); + nfs_retry_commit(&bucket->committing, bucket->clseg, cinfo); put_lseg(bucket->clseg); bucket->clseg = NULL; } @@ -1084,7 +1089,7 @@ alloc_ds_commits(struct inode *inode, struct list_head *list) /* This follows nfs_commit_list pretty closely */ static int filelayout_commit_pagelist(struct inode *inode, struct list_head *mds_pages, - int how) + int how, struct nfs_commit_info *cinfo) { struct nfs_commit_data *data, *tmp; LIST_HEAD(list); @@ -1097,17 +1102,17 @@ filelayout_commit_pagelist(struct inode *inode, struct list_head *mds_pages, list_add(&data->pages, &list); nreq++; } else - nfs_retry_commit(mds_pages, NULL); + nfs_retry_commit(mds_pages, NULL, cinfo); } - nreq += alloc_ds_commits(inode, &list); + nreq += alloc_ds_commits(cinfo, &list); if (nreq == 0) { nfs_commit_clear_lock(NFS_I(inode)); goto out; } - atomic_add(nreq, &NFS_I(inode)->commits_outstanding); + atomic_add(nreq, &cinfo->mds->rpcs_out); list_for_each_entry_safe(data, tmp, &list, pages) { list_del_init(&data->pages); @@ -1116,14 +1121,15 @@ filelayout_commit_pagelist(struct inode *inode, struct list_head *mds_pages, nfs_initiate_commit(NFS_CLIENT(inode), data, data->mds_ops, how); } else { - struct nfs4_fl_commit_info *fl_cinfo; + struct pnfs_commit_bucket *buckets; - fl_cinfo = &FILELAYOUT_FROM_HDR(data->lseg->pls_layout)->commit_info; - nfs_init_commit(data, &fl_cinfo->buckets[data->ds_commit_index].committing, data->lseg); + buckets = cinfo->ds->buckets; + nfs_init_commit(data, &buckets[data->ds_commit_index].committing, data->lseg); filelayout_initiate_commit(data, how); } } out: + cinfo->ds->ncommitting = 0; return PNFS_ATTEMPTED; } @@ -1148,6 +1154,12 @@ filelayout_free_layout_hdr(struct pnfs_layout_hdr *lo) kfree(FILELAYOUT_FROM_HDR(lo)); } +static struct pnfs_ds_commit_info * +filelayout_get_ds_info(struct inode *inode) +{ + return &FILELAYOUT_FROM_HDR(NFS_I(inode)->layout)->commit_info; +} + static struct pnfs_layoutdriver_type filelayout_type = { .id = LAYOUT_NFSV4_1_FILES, .name = "LAYOUT_NFSV4_1_FILES", @@ -1158,6 +1170,7 @@ static struct pnfs_layoutdriver_type filelayout_type = { .free_lseg = filelayout_free_lseg, .pg_read_ops = &filelayout_pg_read_ops, .pg_write_ops = &filelayout_pg_write_ops, + .get_ds_info = &filelayout_get_ds_info, .mark_request_commit = filelayout_mark_request_commit, .clear_request_commit = filelayout_clear_request_commit, .scan_commit_lists = filelayout_scan_commit_lists, diff --git a/fs/nfs/nfs4filelayout.h b/fs/nfs/nfs4filelayout.h index 333a3ac97606..96b89bbddf4f 100644 --- a/fs/nfs/nfs4filelayout.h +++ b/fs/nfs/nfs4filelayout.h @@ -74,18 +74,6 @@ struct nfs4_file_layout_dsaddr { struct nfs4_pnfs_ds *ds_list[1]; }; -struct nfs4_fl_commit_bucket { - struct list_head written; - struct list_head committing; - struct pnfs_layout_segment *wlseg; - struct pnfs_layout_segment *clseg; -}; - -struct nfs4_fl_commit_info { - int nbuckets; - struct nfs4_fl_commit_bucket *buckets; -}; - struct nfs4_filelayout_segment { struct pnfs_layout_segment generic_hdr; u32 stripe_type; @@ -100,7 +88,7 @@ struct nfs4_filelayout_segment { struct nfs4_filelayout { struct pnfs_layout_hdr generic_hdr; - struct nfs4_fl_commit_info commit_info; + struct pnfs_ds_commit_info commit_info; }; static inline struct nfs4_filelayout * diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 734e4eff7fb0..4cd8760c2f89 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -94,11 +94,18 @@ struct pnfs_layoutdriver_type { const struct nfs_pageio_ops *pg_read_ops; const struct nfs_pageio_ops *pg_write_ops; + struct pnfs_ds_commit_info *(*get_ds_info) (struct inode *inode); void (*mark_request_commit) (struct nfs_page *req, - struct pnfs_layout_segment *lseg); - void (*clear_request_commit) (struct nfs_page *req); - int (*scan_commit_lists) (struct inode *inode, int max, spinlock_t *lock); - int (*commit_pagelist)(struct inode *inode, struct list_head *mds_pages, int how); + struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo); + void (*clear_request_commit) (struct nfs_page *req, + struct nfs_commit_info *cinfo); + int (*scan_commit_lists) (struct nfs_commit_info *cinfo, + int max); + int (*commit_pagelist)(struct inode *inode, + struct list_head *mds_pages, + int how, + struct nfs_commit_info *cinfo); /* * Return PNFS_ATTEMPTED to indicate the layout code has attempted @@ -263,49 +270,57 @@ static inline int pnfs_enabled_sb(struct nfs_server *nfss) } static inline int -pnfs_commit_list(struct inode *inode, struct list_head *mds_pages, int how) +pnfs_commit_list(struct inode *inode, struct list_head *mds_pages, int how, + struct nfs_commit_info *cinfo) { - if (!test_and_clear_bit(NFS_INO_PNFS_COMMIT, &NFS_I(inode)->flags)) + if (cinfo->ds == NULL || cinfo->ds->ncommitting == 0) return PNFS_NOT_ATTEMPTED; - return NFS_SERVER(inode)->pnfs_curr_ld->commit_pagelist(inode, mds_pages, how); + return NFS_SERVER(inode)->pnfs_curr_ld->commit_pagelist(inode, mds_pages, how, cinfo); +} + +static inline struct pnfs_ds_commit_info * +pnfs_get_ds_info(struct inode *inode) +{ + struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld; + + if (ld == NULL || ld->get_ds_info == NULL) + return NULL; + return ld->get_ds_info(inode); } static inline bool -pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg) +pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo) { struct inode *inode = req->wb_context->dentry->d_inode; struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld; if (lseg == NULL || ld->mark_request_commit == NULL) return false; - ld->mark_request_commit(req, lseg); + ld->mark_request_commit(req, lseg, cinfo); return true; } static inline bool -pnfs_clear_request_commit(struct nfs_page *req) +pnfs_clear_request_commit(struct nfs_page *req, struct nfs_commit_info *cinfo) { struct inode *inode = req->wb_context->dentry->d_inode; struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld; if (ld == NULL || ld->clear_request_commit == NULL) return false; - ld->clear_request_commit(req); + ld->clear_request_commit(req, cinfo); return true; } static inline int -pnfs_scan_commit_lists(struct inode *inode, int max, spinlock_t *lock) +pnfs_scan_commit_lists(struct inode *inode, struct nfs_commit_info *cinfo, + int max) { - struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld; - int ret; - - if (ld == NULL || ld->scan_commit_lists == NULL) + if (cinfo->ds == NULL || cinfo->ds->nwritten == 0) return 0; - ret = ld->scan_commit_lists(inode, max, lock); - if (ret != 0) - set_bit(NFS_INO_PNFS_COMMIT, &NFS_I(inode)->flags); - return ret; + else + return NFS_SERVER(inode)->pnfs_curr_ld->scan_commit_lists(cinfo, max); } /* Should the pNFS client commit and return the layout upon a setattr */ @@ -409,25 +424,34 @@ static inline bool pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, st } static inline int -pnfs_commit_list(struct inode *inode, struct list_head *mds_pages, int how) +pnfs_commit_list(struct inode *inode, struct list_head *mds_pages, int how, + struct nfs_commit_info *cinfo) { return PNFS_NOT_ATTEMPTED; } +static inline struct pnfs_ds_commit_info * +pnfs_get_ds_info(struct inode *inode) +{ + return NULL; +} + static inline bool -pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg) +pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo) { return false; } static inline bool -pnfs_clear_request_commit(struct nfs_page *req) +pnfs_clear_request_commit(struct nfs_page *req, struct nfs_commit_info *cinfo) { return false; } static inline int -pnfs_scan_commit_lists(struct inode *inode, int max, spinlock_t *lock) +pnfs_scan_commit_lists(struct inode *inode, struct nfs_commit_info *cinfo, + int max) { return 0; } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 2500f1cf1996..18bf70055272 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -452,65 +452,79 @@ nfs_mark_request_dirty(struct nfs_page *req) /** * nfs_request_add_commit_list - add request to a commit list * @req: pointer to a struct nfs_page - * @head: commit list head + * @dst: commit list head + * @cinfo: holds list lock and accounting info * - * This sets the PG_CLEAN bit, updates the inode global count of + * This sets the PG_CLEAN bit, updates the cinfo count of * number of outstanding requests requiring a commit as well as * the MM page stats. * - * The caller must _not_ hold the inode->i_lock, but must be + * The caller must _not_ hold the cinfo->lock, but must be * holding the nfs_page lock. */ void -nfs_request_add_commit_list(struct nfs_page *req, struct list_head *head) +nfs_request_add_commit_list(struct nfs_page *req, struct list_head *dst, + struct nfs_commit_info *cinfo) { - struct inode *inode = req->wb_context->dentry->d_inode; - set_bit(PG_CLEAN, &(req)->wb_flags); - spin_lock(&inode->i_lock); - nfs_list_add_request(req, head); - NFS_I(inode)->ncommit++; - spin_unlock(&inode->i_lock); + spin_lock(cinfo->lock); + nfs_list_add_request(req, dst); + cinfo->mds->ncommit++; + spin_unlock(cinfo->lock); inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS); inc_bdi_stat(req->wb_page->mapping->backing_dev_info, BDI_RECLAIMABLE); - __mark_inode_dirty(inode, I_DIRTY_DATASYNC); + __mark_inode_dirty(req->wb_context->dentry->d_inode, I_DIRTY_DATASYNC); } EXPORT_SYMBOL_GPL(nfs_request_add_commit_list); /** * nfs_request_remove_commit_list - Remove request from a commit list * @req: pointer to a nfs_page + * @cinfo: holds list lock and accounting info * - * This clears the PG_CLEAN bit, and updates the inode global count of + * This clears the PG_CLEAN bit, and updates the cinfo's count of * number of outstanding requests requiring a commit * It does not update the MM page stats. * - * The caller _must_ hold the inode->i_lock and the nfs_page lock. + * The caller _must_ hold the cinfo->lock and the nfs_page lock. */ void -nfs_request_remove_commit_list(struct nfs_page *req) +nfs_request_remove_commit_list(struct nfs_page *req, + struct nfs_commit_info *cinfo) { - struct inode *inode = req->wb_context->dentry->d_inode; - if (!test_and_clear_bit(PG_CLEAN, &(req)->wb_flags)) return; nfs_list_remove_request(req); - NFS_I(inode)->ncommit--; + cinfo->mds->ncommit--; } EXPORT_SYMBOL_GPL(nfs_request_remove_commit_list); +static void nfs_init_cinfo_from_inode(struct nfs_commit_info *cinfo, + struct inode *inode) +{ + cinfo->lock = &inode->i_lock; + cinfo->mds = &NFS_I(inode)->commit_info; + cinfo->ds = pnfs_get_ds_info(inode); +} + +void nfs_init_cinfo(struct nfs_commit_info *cinfo, + struct inode *inode, + struct nfs_direct_req *dreq) +{ + nfs_init_cinfo_from_inode(cinfo, inode); +} +EXPORT_SYMBOL_GPL(nfs_init_cinfo); /* * Add a request to the inode's commit list. */ static void -nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg) +nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo) { - struct inode *inode = req->wb_context->dentry->d_inode; - - if (pnfs_mark_request_commit(req, lseg)) + if (pnfs_mark_request_commit(req, lseg, cinfo)) return; - nfs_request_add_commit_list(req, &NFS_I(inode)->commit_list); + nfs_request_add_commit_list(req, &cinfo->mds->list, cinfo); } static void @@ -525,11 +539,13 @@ nfs_clear_request_commit(struct nfs_page *req) { if (test_bit(PG_CLEAN, &req->wb_flags)) { struct inode *inode = req->wb_context->dentry->d_inode; + struct nfs_commit_info cinfo; - if (!pnfs_clear_request_commit(req)) { - spin_lock(&inode->i_lock); - nfs_request_remove_commit_list(req); - spin_unlock(&inode->i_lock); + nfs_init_cinfo_from_inode(&cinfo, inode); + if (!pnfs_clear_request_commit(req, &cinfo)) { + spin_lock(cinfo.lock); + nfs_request_remove_commit_list(req, &cinfo); + spin_unlock(cinfo.lock); } nfs_clear_page_commit(req->wb_page); } @@ -545,7 +561,8 @@ int nfs_write_need_commit(struct nfs_write_data *data) #else static void -nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg) +nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo) { } @@ -564,10 +581,12 @@ int nfs_write_need_commit(struct nfs_write_data *data) static void nfs_write_completion(struct nfs_pgio_header *hdr) { + struct nfs_commit_info cinfo; unsigned long bytes = 0; if (test_bit(NFS_IOHDR_REDO, &hdr->flags)) goto out; + nfs_init_cinfo_from_inode(&cinfo, hdr->inode); while (!list_empty(&hdr->pages)) { struct nfs_page *req = nfs_list_entry(hdr->pages.next); struct page *page = req->wb_page; @@ -585,7 +604,7 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr) goto next; } if (test_bit(NFS_IOHDR_NEED_COMMIT, &hdr->flags)) { - nfs_mark_request_commit(req, hdr->lseg); + nfs_mark_request_commit(req, hdr->lseg, &cinfo); goto next; } remove_req: @@ -599,16 +618,16 @@ out: } #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4) -static int -nfs_need_commit(struct nfs_inode *nfsi) +static unsigned long +nfs_reqs_to_commit(struct nfs_commit_info *cinfo) { - return nfsi->ncommit > 0; + return cinfo->mds->ncommit; } -/* i_lock held by caller */ +/* cinfo->lock held by caller */ static int -nfs_scan_commit_list(struct list_head *src, struct list_head *dst, int max, - spinlock_t *lock) +nfs_scan_commit_list(struct list_head *src, struct list_head *dst, + struct nfs_commit_info *cinfo, int max) { struct nfs_page *req, *tmp; int ret = 0; @@ -616,9 +635,9 @@ nfs_scan_commit_list(struct list_head *src, struct list_head *dst, int max, list_for_each_entry_safe(req, tmp, src, wb_list) { if (!nfs_lock_request(req)) continue; - if (cond_resched_lock(lock)) + if (cond_resched_lock(cinfo->lock)) list_safe_reset_next(req, tmp, wb_list); - nfs_request_remove_commit_list(req); + nfs_request_remove_commit_list(req, cinfo); nfs_list_add_request(req, dst); ret++; if (ret == max) @@ -630,37 +649,38 @@ nfs_scan_commit_list(struct list_head *src, struct list_head *dst, int max, /* * nfs_scan_commit - Scan an inode for commit requests * @inode: NFS inode to scan - * @dst: destination list + * @dst: mds destination list + * @cinfo: mds and ds lists of reqs ready to commit * * Moves requests from the inode's 'commit' request list. * The requests are *not* checked to ensure that they form a contiguous set. */ static int -nfs_scan_commit(struct inode *inode, struct list_head *dst) +nfs_scan_commit(struct inode *inode, struct list_head *dst, + struct nfs_commit_info *cinfo) { - struct nfs_inode *nfsi = NFS_I(inode); int ret = 0; - spin_lock(&inode->i_lock); - if (nfsi->ncommit > 0) { + spin_lock(cinfo->lock); + if (cinfo->mds->ncommit > 0) { const int max = INT_MAX; - ret = nfs_scan_commit_list(&nfsi->commit_list, dst, max, - &inode->i_lock); - ret += pnfs_scan_commit_lists(inode, max - ret, - &inode->i_lock); + ret = nfs_scan_commit_list(&cinfo->mds->list, dst, + cinfo, max); + ret += pnfs_scan_commit_lists(inode, cinfo, max - ret); } - spin_unlock(&inode->i_lock); + spin_unlock(cinfo->lock); return ret; } #else -static inline int nfs_need_commit(struct nfs_inode *nfsi) +static unsigned long nfs_reqs_to_commit(struct nfs_commit_info *cinfo) { return 0; } -static inline int nfs_scan_commit(struct inode *inode, struct list_head *dst) +static inline int nfs_scan_commit(struct inode *inode, struct list_head *dst, + struct nfs_commit_info *cinfo) { return 0; } @@ -929,7 +949,7 @@ EXPORT_SYMBOL_GPL(nfs_initiate_write); */ static void nfs_write_rpcsetup(struct nfs_write_data *data, unsigned int count, unsigned int offset, - int how) + int how, struct nfs_commit_info *cinfo) { struct nfs_page *req = data->header->req; @@ -950,7 +970,7 @@ static void nfs_write_rpcsetup(struct nfs_write_data *data, case 0: break; case FLUSH_COND_STABLE: - if (nfs_need_commit(NFS_I(data->header->inode))) + if (nfs_reqs_to_commit(cinfo)) break; default: data->args.stable = NFS_FILE_SYNC; @@ -1034,12 +1054,14 @@ static int nfs_flush_multi(struct nfs_pageio_descriptor *desc, unsigned int offset; int requests = 0; int ret = 0; + struct nfs_commit_info cinfo; + nfs_init_cinfo(&cinfo, desc->pg_inode, desc->pg_dreq); nfs_list_remove_request(req); nfs_list_add_request(req, &hdr->pages); if ((desc->pg_ioflags & FLUSH_COND_STABLE) && - (desc->pg_moreio || NFS_I(desc->pg_inode)->ncommit || + (desc->pg_moreio || nfs_reqs_to_commit(&cinfo) || desc->pg_count > wsize)) desc->pg_ioflags &= ~FLUSH_COND_STABLE; @@ -1053,7 +1075,7 @@ static int nfs_flush_multi(struct nfs_pageio_descriptor *desc, if (!data) goto out_bad; data->pages.pagevec[0] = page; - nfs_write_rpcsetup(data, len, offset, desc->pg_ioflags); + nfs_write_rpcsetup(data, len, offset, desc->pg_ioflags, &cinfo); list_add(&data->list, &hdr->rpc_list); requests++; nbytes -= len; @@ -1088,6 +1110,7 @@ static int nfs_flush_one(struct nfs_pageio_descriptor *desc, struct nfs_write_data *data; struct list_head *head = &desc->pg_list; int ret = 0; + struct nfs_commit_info cinfo; data = nfs_writedata_alloc(hdr, nfs_page_array_len(desc->pg_base, desc->pg_count)); @@ -1097,6 +1120,7 @@ static int nfs_flush_one(struct nfs_pageio_descriptor *desc, goto out; } + nfs_init_cinfo(&cinfo, desc->pg_inode, desc->pg_dreq); pages = data->pages.pagevec; while (!list_empty(head)) { req = nfs_list_entry(head->next); @@ -1106,11 +1130,11 @@ static int nfs_flush_one(struct nfs_pageio_descriptor *desc, } if ((desc->pg_ioflags & FLUSH_COND_STABLE) && - (desc->pg_moreio || NFS_I(desc->pg_inode)->ncommit)) + (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); + 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; out: @@ -1417,14 +1441,15 @@ void nfs_init_commit(struct nfs_commit_data *data, EXPORT_SYMBOL_GPL(nfs_init_commit); void nfs_retry_commit(struct list_head *page_list, - struct pnfs_layout_segment *lseg) + struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo) { struct nfs_page *req; while (!list_empty(page_list)) { req = nfs_list_entry(page_list->next); nfs_list_remove_request(req); - nfs_mark_request_commit(req, lseg); + nfs_mark_request_commit(req, lseg, cinfo); dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS); dec_bdi_stat(req->wb_page->mapping->backing_dev_info, BDI_RECLAIMABLE); @@ -1437,7 +1462,8 @@ EXPORT_SYMBOL_GPL(nfs_retry_commit); * Commit dirty pages */ static int -nfs_commit_list(struct inode *inode, struct list_head *head, int how) +nfs_commit_list(struct inode *inode, struct list_head *head, int how, + struct nfs_commit_info *cinfo) { struct nfs_commit_data *data; @@ -1450,7 +1476,7 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how) nfs_init_commit(data, head, NULL); return nfs_initiate_commit(NFS_CLIENT(inode), data, data->mds_ops, how); out_bad: - nfs_retry_commit(head, NULL); + nfs_retry_commit(head, NULL, cinfo); nfs_commit_clear_lock(NFS_I(inode)); return -ENOMEM; } @@ -1524,30 +1550,32 @@ static const struct rpc_call_ops nfs_commit_ops = { }; static int nfs_generic_commit_list(struct inode *inode, struct list_head *head, - int how) + int how, struct nfs_commit_info *cinfo) { int status; - status = pnfs_commit_list(inode, head, how); + status = pnfs_commit_list(inode, head, how, cinfo); if (status == PNFS_NOT_ATTEMPTED) - status = nfs_commit_list(inode, head, how); + status = nfs_commit_list(inode, head, how, cinfo); return status; } int nfs_commit_inode(struct inode *inode, int how) { LIST_HEAD(head); + struct nfs_commit_info cinfo; int may_wait = how & FLUSH_SYNC; int res; res = nfs_commit_set_lock(NFS_I(inode), may_wait); if (res <= 0) goto out_mark_dirty; - res = nfs_scan_commit(inode, &head); + nfs_init_cinfo_from_inode(&cinfo, inode); + res = nfs_scan_commit(inode, &head, &cinfo); if (res) { int error; - error = nfs_generic_commit_list(inode, &head, how); + error = nfs_generic_commit_list(inode, &head, how, &cinfo); if (error < 0) return error; if (!may_wait) @@ -1578,14 +1606,14 @@ static int nfs_commit_unstable_pages(struct inode *inode, struct writeback_contr int ret = 0; /* no commits means nothing needs to be done */ - if (!nfsi->ncommit) + if (!nfsi->commit_info.ncommit) return ret; if (wbc->sync_mode == WB_SYNC_NONE) { /* Don't commit yet if this is a non-blocking flush and there * are a lot of outstanding writes for this mapping. */ - if (nfsi->ncommit <= (nfsi->npages >> 1)) + if (nfsi->commit_info.ncommit <= (nfsi->npages >> 1)) goto out_mark_dirty; /* don't wait for the COMMIT response */ diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 8d3a2b804201..8a88c16662c5 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -179,8 +179,7 @@ struct nfs_inode { __be32 cookieverf[2]; unsigned long npages; - unsigned long ncommit; - struct list_head commit_list; + struct nfs_mds_commit_info commit_info; /* Open contexts for shared mmap writes */ struct list_head open_files; @@ -201,7 +200,6 @@ struct nfs_inode { /* pNFS layout information */ struct pnfs_layout_hdr *layout; - atomic_t commits_outstanding; #endif /* CONFIG_NFS_V4*/ #ifdef CONFIG_NFS_FSCACHE struct fscache_cookie *fscache; @@ -230,7 +228,6 @@ struct nfs_inode { #define NFS_INO_FSCACHE (5) /* inode can be cached by FS-Cache */ #define NFS_INO_FSCACHE_LOCK (6) /* FS-Cache cookie management lock */ #define NFS_INO_COMMIT (7) /* inode is committing unstable writes */ -#define NFS_INO_PNFS_COMMIT (8) /* use pnfs code for commit */ #define NFS_INO_LAYOUTCOMMIT (9) /* layoutcommit required */ #define NFS_INO_LAYOUTCOMMITTING (10) /* layoutcommit inflight */ diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 38687b87ca9b..224e1e82670c 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1079,6 +1079,21 @@ struct nfstime4 { }; #ifdef CONFIG_NFS_V4_1 + +struct pnfs_commit_bucket { + struct list_head written; + struct list_head committing; + struct pnfs_layout_segment *wlseg; + struct pnfs_layout_segment *clseg; +}; + +struct pnfs_ds_commit_info { + int nwritten; + int ncommitting; + int nbuckets; + struct pnfs_commit_bucket *buckets; +}; + #define NFS4_EXCHANGE_ID_LEN (48) struct nfs41_exchange_id_args { struct nfs_client *client; @@ -1242,6 +1257,18 @@ struct nfs_write_header { struct nfs_write_data rpc_data; }; +struct nfs_mds_commit_info { + atomic_t rpcs_out; + unsigned long ncommit; + struct list_head list; +}; + +struct nfs_commit_info { + spinlock_t *lock; + struct nfs_mds_commit_info *mds; + struct pnfs_ds_commit_info *ds; +}; + struct nfs_commit_data { struct rpc_task task; struct inode *inode; -- cgit v1.2.3 From f453a54a01c7c0453ad9550906e3d2663dd486ac Mon Sep 17 00:00:00 2001 From: Fred Isaman Date: Fri, 20 Apr 2012 14:47:54 -0400 Subject: NFS: create nfs_commit_completion_ops Factors out the code that needs to change when directio starts using these code paths. Signed-off-by: Fred Isaman Signed-off-by: Trond Myklebust --- fs/nfs/internal.h | 5 ++--- fs/nfs/nfs4filelayout.c | 12 ++++-------- fs/nfs/write.c | 31 +++++++++++++++++++++---------- include/linux/nfs_xdr.h | 9 +++++++++ 4 files changed, 36 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 145e9e7dc8ce..137f5cd71433 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -344,13 +344,12 @@ extern int nfs_initiate_commit(struct rpc_clnt *clnt, int how); extern void nfs_init_commit(struct nfs_commit_data *data, struct list_head *head, - struct pnfs_layout_segment *lseg); + struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo); void nfs_retry_commit(struct list_head *page_list, struct pnfs_layout_segment *lseg, struct nfs_commit_info *cinfo); -void nfs_commit_clear_lock(struct nfs_inode *nfsi); void nfs_commitdata_release(struct nfs_commit_data *data); -void nfs_commit_release_pages(struct nfs_commit_data *data); void nfs_request_add_commit_list(struct nfs_page *req, struct list_head *dst, struct nfs_commit_info *cinfo); void nfs_request_remove_commit_list(struct nfs_page *req, diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c index fe2cb55ca6b1..26d1da486761 100644 --- a/fs/nfs/nfs4filelayout.c +++ b/fs/nfs/nfs4filelayout.c @@ -347,12 +347,8 @@ static void filelayout_commit_count_stats(struct rpc_task *task, void *data) static void filelayout_commit_release(void *calldata) { struct nfs_commit_data *data = calldata; - struct nfs_commit_info cinfo; - nfs_commit_release_pages(data); - nfs_init_cinfo(&cinfo, data->inode, data->dreq); - if (atomic_dec_and_test(&cinfo.mds->rpcs_out)) - nfs_commit_clear_lock(NFS_I(data->inode)); + data->completion_ops->completion(data); put_lseg(data->lseg); nfs_commitdata_release(data); } @@ -1108,7 +1104,7 @@ filelayout_commit_pagelist(struct inode *inode, struct list_head *mds_pages, nreq += alloc_ds_commits(cinfo, &list); if (nreq == 0) { - nfs_commit_clear_lock(NFS_I(inode)); + cinfo->completion_ops->error_cleanup(NFS_I(inode)); goto out; } @@ -1117,14 +1113,14 @@ filelayout_commit_pagelist(struct inode *inode, struct list_head *mds_pages, list_for_each_entry_safe(data, tmp, &list, pages) { list_del_init(&data->pages); if (!data->lseg) { - nfs_init_commit(data, mds_pages, NULL); + nfs_init_commit(data, mds_pages, NULL, cinfo); nfs_initiate_commit(NFS_CLIENT(inode), data, data->mds_ops, how); } else { struct pnfs_commit_bucket *buckets; buckets = cinfo->ds->buckets; - nfs_init_commit(data, &buckets[data->ds_commit_index].committing, data->lseg); + nfs_init_commit(data, &buckets[data->ds_commit_index].committing, data->lseg, cinfo); filelayout_initiate_commit(data, how); } } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 18bf70055272..333d01d26292 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -46,6 +46,7 @@ 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 struct kmem_cache *nfs_wdata_cachep; static mempool_t *nfs_wdata_mempool; @@ -505,6 +506,7 @@ static void nfs_init_cinfo_from_inode(struct nfs_commit_info *cinfo, cinfo->lock = &inode->i_lock; cinfo->mds = &NFS_I(inode)->commit_info; cinfo->ds = pnfs_get_ds_info(inode); + cinfo->completion_ops = &nfs_commit_completion_ops; } void nfs_init_cinfo(struct nfs_commit_info *cinfo, @@ -1358,13 +1360,12 @@ static int nfs_commit_set_lock(struct nfs_inode *nfsi, int may_wait) return (ret < 0) ? ret : 1; } -void nfs_commit_clear_lock(struct nfs_inode *nfsi) +static void nfs_commit_clear_lock(struct nfs_inode *nfsi) { clear_bit(NFS_INO_COMMIT, &nfsi->flags); smp_mb__after_clear_bit(); wake_up_bit(&nfsi->flags, NFS_INO_COMMIT); } -EXPORT_SYMBOL_GPL(nfs_commit_clear_lock); void nfs_commitdata_release(struct nfs_commit_data *data) { @@ -1413,8 +1414,9 @@ EXPORT_SYMBOL_GPL(nfs_initiate_commit); * Set up the argument/result storage required for the RPC call. */ void nfs_init_commit(struct nfs_commit_data *data, - struct list_head *head, - struct pnfs_layout_segment *lseg) + struct list_head *head, + struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo) { struct nfs_page *first = nfs_list_entry(head->next); struct inode *inode = first->wb_context->dentry->d_inode; @@ -1428,6 +1430,7 @@ void nfs_init_commit(struct nfs_commit_data *data, data->cred = first->wb_context->cred; data->lseg = lseg; /* reference transferred */ data->mds_ops = &nfs_commit_ops; + data->completion_ops = cinfo->completion_ops; data->args.fh = NFS_FH(data->inode); /* Note: we always request a commit of the entire inode */ @@ -1473,11 +1476,12 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how, goto out_bad; /* Set up the argument struct */ - nfs_init_commit(data, head, NULL); + nfs_init_commit(data, head, NULL, cinfo); + atomic_inc(&cinfo->mds->rpcs_out); return nfs_initiate_commit(NFS_CLIENT(inode), data, data->mds_ops, how); out_bad: nfs_retry_commit(head, NULL, cinfo); - nfs_commit_clear_lock(NFS_I(inode)); + cinfo->completion_ops->error_cleanup(NFS_I(inode)); return -ENOMEM; } @@ -1495,10 +1499,11 @@ static void nfs_commit_done(struct rpc_task *task, void *calldata) NFS_PROTO(data->inode)->commit_done(task, data); } -void nfs_commit_release_pages(struct nfs_commit_data *data) +static void nfs_commit_release_pages(struct nfs_commit_data *data) { struct nfs_page *req; int status = data->task.tk_status; + struct nfs_commit_info cinfo; while (!list_empty(&data->pages)) { req = nfs_list_entry(data->pages.next); @@ -1531,15 +1536,16 @@ void nfs_commit_release_pages(struct nfs_commit_data *data) next: nfs_unlock_request(req); } + nfs_init_cinfo(&cinfo, data->inode, data->dreq); + if (atomic_dec_and_test(&cinfo.mds->rpcs_out)) + nfs_commit_clear_lock(NFS_I(data->inode)); } -EXPORT_SYMBOL_GPL(nfs_commit_release_pages); static void nfs_commit_release(void *calldata) { struct nfs_commit_data *data = calldata; - nfs_commit_release_pages(data); - nfs_commit_clear_lock(NFS_I(data->inode)); + data->completion_ops->completion(data); nfs_commitdata_release(calldata); } @@ -1549,6 +1555,11 @@ static const struct rpc_call_ops nfs_commit_ops = { .rpc_release = nfs_commit_release, }; +static const struct nfs_commit_completion_ops nfs_commit_completion_ops = { + .completion = nfs_commit_release_pages, + .error_cleanup = nfs_commit_clear_lock, +}; + static int nfs_generic_commit_list(struct inode *inode, struct list_head *head, int how, struct nfs_commit_info *cinfo) { diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 224e1e82670c..0e8b88ad9ae2 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1263,10 +1263,18 @@ struct nfs_mds_commit_info { struct list_head list; }; +struct nfs_commit_data; +struct nfs_inode; +struct nfs_commit_completion_ops { + void (*error_cleanup) (struct nfs_inode *nfsi); + void (*completion) (struct nfs_commit_data *data); +}; + struct nfs_commit_info { spinlock_t *lock; struct nfs_mds_commit_info *mds; struct pnfs_ds_commit_info *ds; + const struct nfs_commit_completion_ops *completion_ops; }; struct nfs_commit_data { @@ -1285,6 +1293,7 @@ struct nfs_commit_data { struct nfs_client *ds_clp; /* pNFS data server */ int ds_commit_index; const struct rpc_call_ops *mds_ops; + const struct nfs_commit_completion_ops *completion_ops; int (*commit_done_cb) (struct rpc_task *task, struct nfs_commit_data *data); }; -- cgit v1.2.3 From b359f9d09bcbaede09243cfe844172ba055d89fd Mon Sep 17 00:00:00 2001 From: Fred Isaman Date: Fri, 20 Apr 2012 14:47:55 -0400 Subject: NFS: add dreq to nfs_commit_info Need this to pass into nfs_commitdata_init, in order to keep data->dreq accurate. Signed-off-by: Fred Isaman Signed-off-by: Trond Myklebust --- fs/nfs/write.c | 2 ++ include/linux/nfs_xdr.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include') diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 333d01d26292..44a93d8c7b52 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -506,6 +506,7 @@ static void nfs_init_cinfo_from_inode(struct nfs_commit_info *cinfo, cinfo->lock = &inode->i_lock; cinfo->mds = &NFS_I(inode)->commit_info; cinfo->ds = pnfs_get_ds_info(inode); + cinfo->dreq = NULL; cinfo->completion_ops = &nfs_commit_completion_ops; } @@ -1431,6 +1432,7 @@ void nfs_init_commit(struct nfs_commit_data *data, data->lseg = lseg; /* reference transferred */ data->mds_ops = &nfs_commit_ops; data->completion_ops = cinfo->completion_ops; + data->dreq = cinfo->dreq; data->args.fh = NFS_FH(data->inode); /* Note: we always request a commit of the entire inode */ diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 0e8b88ad9ae2..5f563bd113e8 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1274,6 +1274,7 @@ struct nfs_commit_info { spinlock_t *lock; struct nfs_mds_commit_info *mds; struct pnfs_ds_commit_info *ds; + struct nfs_direct_req *dreq; /* O_DIRECT request */ const struct nfs_commit_completion_ops *completion_ops; }; -- cgit v1.2.3 From 2671bfc3beb44e70636bd0208274426db57f73b5 Mon Sep 17 00:00:00 2001 From: Bryan Schumaker Date: Fri, 27 Apr 2012 13:27:44 -0400 Subject: NFS: Remove secinfo knowledge out of the generic client And also remove the unneeded rpc_op. Signed-off-by: Bryan Schumaker Signed-off-by: Trond Myklebust --- fs/nfs/internal.h | 3 --- fs/nfs/namespace.c | 29 ----------------------------- fs/nfs/nfs4_fs.h | 1 + fs/nfs/nfs4namespace.c | 29 +++++++++++++++++++++++++++++ fs/nfs/nfs4proc.c | 1 - include/linux/nfs_xdr.h | 1 - 6 files changed, 30 insertions(+), 34 deletions(-) (limited to 'include') diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index d68810f61869..d6994443f285 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -286,9 +286,6 @@ extern void nfs_sb_deactive(struct super_block *sb); extern char *nfs_path(char **p, struct dentry *dentry, char *buffer, ssize_t buflen); extern struct vfsmount *nfs_d_automount(struct path *path); -#ifdef CONFIG_NFS_V4 -rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *); -#endif /* getroot.c */ extern struct dentry *nfs_get_root(struct super_block *, struct nfs_fh *, diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index d51868e5683c..2a9591b0b150 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -119,35 +119,6 @@ Elong: } #ifdef CONFIG_NFS_V4 -rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *flavors) -{ - struct gss_api_mech *mech; - struct xdr_netobj oid; - int i; - rpc_authflavor_t pseudoflavor = RPC_AUTH_UNIX; - - for (i = 0; i < flavors->num_flavors; i++) { - struct nfs4_secinfo_flavor *flavor; - flavor = &flavors->flavors[i]; - - if (flavor->flavor == RPC_AUTH_NULL || flavor->flavor == RPC_AUTH_UNIX) { - pseudoflavor = flavor->flavor; - break; - } else if (flavor->flavor == RPC_AUTH_GSS) { - oid.len = flavor->gss.sec_oid4.len; - oid.data = flavor->gss.sec_oid4.data; - mech = gss_mech_get_by_OID(&oid); - if (!mech) - continue; - pseudoflavor = gss_svc_to_pseudoflavor(mech, flavor->gss.service); - gss_mech_put(mech); - break; - } - } - - return pseudoflavor; -} - static struct rpc_clnt *nfs_lookup_mountpoint(struct inode *dir, struct qstr *name, struct nfs_fh *fh, diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 8d75021020b3..53a487ee9867 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -206,6 +206,7 @@ extern const struct dentry_operations nfs4_dentry_operations; extern const struct inode_operations nfs4_dir_inode_operations; /* nfs4namespace.c */ +rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *); struct rpc_clnt *nfs4_create_sec_client(struct rpc_clnt *, struct inode *, struct qstr *); /* nfs4proc.c */ diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c index a7f3dedc4ec7..a69ee3952bbe 100644 --- a/fs/nfs/nfs4namespace.c +++ b/fs/nfs/nfs4namespace.c @@ -132,6 +132,35 @@ static size_t nfs_parse_server_name(char *string, size_t len, return ret; } +rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *flavors) +{ + struct gss_api_mech *mech; + struct xdr_netobj oid; + int i; + rpc_authflavor_t pseudoflavor = RPC_AUTH_UNIX; + + for (i = 0; i < flavors->num_flavors; i++) { + struct nfs4_secinfo_flavor *flavor; + flavor = &flavors->flavors[i]; + + if (flavor->flavor == RPC_AUTH_NULL || flavor->flavor == RPC_AUTH_UNIX) { + pseudoflavor = flavor->flavor; + break; + } else if (flavor->flavor == RPC_AUTH_GSS) { + oid.len = flavor->gss.sec_oid4.len; + oid.data = flavor->gss.sec_oid4.data; + mech = gss_mech_get_by_OID(&oid); + if (!mech) + continue; + pseudoflavor = gss_svc_to_pseudoflavor(mech, flavor->gss.service); + gss_mech_put(mech); + break; + } + } + + return pseudoflavor; +} + static rpc_authflavor_t nfs4_negotiate_security(struct inode *inode, struct qstr *name) { struct page *page; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 87af80d28a82..fa661b91e57c 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -6610,7 +6610,6 @@ const struct nfs_rpc_ops nfs_v4_clientops = { .close_context = nfs4_close_context, .open_context = nfs4_atomic_open, .init_client = nfs4_init_client, - .secinfo = nfs4_proc_secinfo, }; static const struct xattr_handler nfs4_xattr_nfs4_acl_handler = { diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 5f563bd113e8..eb1f143042f4 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1397,7 +1397,6 @@ struct nfs_rpc_ops { struct iattr *iattr); int (*init_client) (struct nfs_client *, const struct rpc_timeout *, const char *, rpc_authflavor_t, int); - int (*secinfo)(struct inode *, const struct qstr *, struct nfs4_secinfo_flavors *); }; /* -- cgit v1.2.3 From 281cad46b34db4dbb1d1e603f7b9cfe25d1ae7c9 Mon Sep 17 00:00:00 2001 From: Bryan Schumaker Date: Fri, 27 Apr 2012 13:27:45 -0400 Subject: NFS: Create a submount rpc_op This simplifies the code for v2 and v3 and gives v4 a chance to decide on referrals without needing to modify the generic client. Signed-off-by: Bryan Schumaker Signed-off-by: Trond Myklebust --- fs/nfs/internal.h | 15 +++------- fs/nfs/namespace.c | 75 +++++++++++++------------------------------------ fs/nfs/nfs3proc.c | 1 + fs/nfs/nfs4_fs.h | 2 ++ fs/nfs/nfs4namespace.c | 24 +++++++++++++++- fs/nfs/nfs4proc.c | 1 + fs/nfs/proc.c | 1 + include/linux/nfs_xdr.h | 2 ++ 8 files changed, 54 insertions(+), 67 deletions(-) (limited to 'include') diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index d6994443f285..0fd1efaf1cff 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -185,17 +185,6 @@ static inline void nfs_fs_proc_exit(void) } #endif -/* nfs4namespace.c */ -#ifdef CONFIG_NFS_V4 -extern struct vfsmount *nfs_do_refmount(struct rpc_clnt *client, struct dentry *dentry); -#else -static inline -struct vfsmount *nfs_do_refmount(struct rpc_clnt *client, struct dentry *dentry) -{ - return ERR_PTR(-ENOENT); -} -#endif - /* callback_xdr.c */ extern struct svc_version nfs4_callback_version1; extern struct svc_version nfs4_callback_version4; @@ -286,6 +275,10 @@ extern void nfs_sb_deactive(struct super_block *sb); extern char *nfs_path(char **p, struct dentry *dentry, char *buffer, ssize_t buflen); extern struct vfsmount *nfs_d_automount(struct path *path); +struct vfsmount *nfs_submount(struct nfs_server *, struct dentry *, + struct nfs_fh *, struct nfs_fattr *); +struct vfsmount *nfs_do_submount(struct dentry *, struct nfs_fh *, + struct nfs_fattr *, rpc_authflavor_t); /* getroot.c */ extern struct dentry *nfs_get_root(struct super_block *, struct nfs_fh *, diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index 2a9591b0b150..e36fd8a51819 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -26,11 +26,6 @@ static LIST_HEAD(nfs_automount_list); static DECLARE_DELAYED_WORK(nfs_automount_task, nfs_expire_automounts); int nfs_mountpoint_expiry_timeout = 500 * HZ; -static struct vfsmount *nfs_do_submount(struct dentry *dentry, - struct nfs_fh *fh, - struct nfs_fattr *fattr, - rpc_authflavor_t authflavor); - /* * nfs_path - reconstruct the path given an arbitrary dentry * @base - used to return pointer to the end of devname part of path @@ -118,35 +113,6 @@ Elong: return ERR_PTR(-ENAMETOOLONG); } -#ifdef CONFIG_NFS_V4 -static struct rpc_clnt *nfs_lookup_mountpoint(struct inode *dir, - struct qstr *name, - struct nfs_fh *fh, - struct nfs_fattr *fattr) -{ - int err; - - if (NFS_PROTO(dir)->version == 4) - return nfs4_proc_lookup_mountpoint(dir, name, fh, fattr); - - err = NFS_PROTO(dir)->lookup(NFS_SERVER(dir)->client, dir, name, fh, fattr); - if (err) - return ERR_PTR(err); - return rpc_clone_client(NFS_SERVER(dir)->client); -} -#else /* CONFIG_NFS_V4 */ -static inline struct rpc_clnt *nfs_lookup_mountpoint(struct inode *dir, - struct qstr *name, - struct nfs_fh *fh, - struct nfs_fattr *fattr) -{ - int err = NFS_PROTO(dir)->lookup(NFS_SERVER(dir)->client, dir, name, fh, fattr); - if (err) - return ERR_PTR(err); - return rpc_clone_client(NFS_SERVER(dir)->client); -} -#endif /* CONFIG_NFS_V4 */ - /* * nfs_d_automount - Handle crossing a mountpoint on the server * @path - The mountpoint @@ -162,10 +128,9 @@ static inline struct rpc_clnt *nfs_lookup_mountpoint(struct inode *dir, struct vfsmount *nfs_d_automount(struct path *path) { struct vfsmount *mnt; - struct dentry *parent; + struct nfs_server *server = NFS_SERVER(path->dentry->d_inode); struct nfs_fh *fh = NULL; struct nfs_fattr *fattr = NULL; - struct rpc_clnt *client; dprintk("--> nfs_d_automount()\n"); @@ -181,21 +146,7 @@ struct vfsmount *nfs_d_automount(struct path *path) dprintk("%s: enter\n", __func__); - /* Look it up again to get its attributes */ - parent = dget_parent(path->dentry); - client = nfs_lookup_mountpoint(parent->d_inode, &path->dentry->d_name, fh, fattr); - dput(parent); - if (IS_ERR(client)) { - mnt = ERR_CAST(client); - goto out; - } - - if (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) - mnt = nfs_do_refmount(client, path->dentry); - else - mnt = nfs_do_submount(path->dentry, fh, fattr, client->cl_auth->au_flavor); - rpc_shutdown_client(client); - + mnt = server->nfs_client->rpc_ops->submount(server, path->dentry, fh, fattr); if (IS_ERR(mnt)) goto out; @@ -268,10 +219,8 @@ static struct vfsmount *nfs_do_clone_mount(struct nfs_server *server, * @authflavor - security flavor to use when performing the mount * */ -static struct vfsmount *nfs_do_submount(struct dentry *dentry, - struct nfs_fh *fh, - struct nfs_fattr *fattr, - rpc_authflavor_t authflavor) +struct vfsmount *nfs_do_submount(struct dentry *dentry, struct nfs_fh *fh, + struct nfs_fattr *fattr, rpc_authflavor_t authflavor) { struct nfs_clone_mount mountdata = { .sb = dentry->d_sb, @@ -304,3 +253,19 @@ out: dprintk("<-- nfs_do_submount() = %p\n", mnt); return mnt; } + +struct vfsmount *nfs_submount(struct nfs_server *server, struct dentry *dentry, + struct nfs_fh *fh, struct nfs_fattr *fattr) +{ + int err; + struct dentry *parent = dget_parent(dentry); + + /* Look it up again to get its attributes */ + err = server->nfs_client->rpc_ops->lookup(server->client, parent->d_inode, + &dentry->d_name, fh, fattr); + dput(parent); + if (err != 0) + return ERR_PTR(err); + + return nfs_do_submount(dentry, fh, fattr, server->client->cl_auth->au_flavor); +} diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index 56dcefc2f3f7..c23214d55ecf 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -885,6 +885,7 @@ const struct nfs_rpc_ops nfs_v3_clientops = { .file_inode_ops = &nfs3_file_inode_operations, .file_ops = &nfs_file_operations, .getroot = nfs3_proc_get_root, + .submount = nfs_submount, .getattr = nfs3_proc_getattr, .setattr = nfs3_proc_setattr, .lookup = nfs3_proc_lookup, diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 53a487ee9867..97365b0f9d3f 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -208,6 +208,8 @@ extern const struct inode_operations nfs4_dir_inode_operations; /* nfs4namespace.c */ rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *); struct rpc_clnt *nfs4_create_sec_client(struct rpc_clnt *, struct inode *, struct qstr *); +struct vfsmount *nfs4_submount(struct nfs_server *, struct dentry *, + struct nfs_fh *, struct nfs_fattr *); /* nfs4proc.c */ extern int nfs4_proc_setclientid(struct nfs_client *, u32, unsigned short, struct rpc_cred *, struct nfs4_setclientid_res *); diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c index a69ee3952bbe..80fc0fe7095e 100644 --- a/fs/nfs/nfs4namespace.c +++ b/fs/nfs/nfs4namespace.c @@ -329,7 +329,7 @@ out: * @dentry - dentry of referral * */ -struct vfsmount *nfs_do_refmount(struct rpc_clnt *client, struct dentry *dentry) +static struct vfsmount *nfs_do_refmount(struct rpc_clnt *client, struct dentry *dentry) { struct vfsmount *mnt = ERR_PTR(-ENOMEM); struct dentry *parent; @@ -370,3 +370,25 @@ out: dprintk("%s: done\n", __func__); return mnt; } + +struct vfsmount *nfs4_submount(struct nfs_server *server, struct dentry *dentry, + struct nfs_fh *fh, struct nfs_fattr *fattr) +{ + struct dentry *parent = dget_parent(dentry); + struct rpc_clnt *client; + struct vfsmount *mnt; + + /* Look it up again to get its attributes and sec flavor */ + client = nfs4_proc_lookup_mountpoint(parent->d_inode, &dentry->d_name, fh, fattr); + dput(parent); + if (IS_ERR(client)) + return ERR_CAST(client); + + if (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) + mnt = nfs_do_refmount(client, dentry); + else + mnt = nfs_do_submount(dentry, fh, fattr, client->cl_auth->au_flavor); + + rpc_shutdown_client(client); + return mnt; +} diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index fa661b91e57c..2091af294c61 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -6571,6 +6571,7 @@ const struct nfs_rpc_ops nfs_v4_clientops = { .file_inode_ops = &nfs4_file_inode_operations, .file_ops = &nfs4_file_operations, .getroot = nfs4_proc_get_root, + .submount = nfs4_submount, .getattr = nfs4_proc_getattr, .setattr = nfs4_proc_setattr, .lookup = nfs4_proc_lookup, diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c index 22ee70586875..76b3229fc527 100644 --- a/fs/nfs/proc.c +++ b/fs/nfs/proc.c @@ -742,6 +742,7 @@ const struct nfs_rpc_ops nfs_v2_clientops = { .file_inode_ops = &nfs_file_inode_operations, .file_ops = &nfs_file_operations, .getroot = nfs_proc_get_root, + .submount = nfs_submount, .getattr = nfs_proc_getattr, .setattr = nfs_proc_setattr, .lookup = nfs_proc_lookup, diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index eb1f143042f4..4dada94eba7d 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1341,6 +1341,8 @@ struct nfs_rpc_ops { int (*getroot) (struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *); + struct vfsmount *(*submount) (struct nfs_server *, struct dentry *, + struct nfs_fh *, struct nfs_fattr *); int (*getattr) (struct nfs_server *, struct nfs_fh *, struct nfs_fattr *); int (*setattr) (struct dentry *, struct nfs_fattr *, -- cgit v1.2.3 From 80a16b21a81eb639f0b726549f4c46c0e9aff92e Mon Sep 17 00:00:00 2001 From: Bryan Schumaker Date: Fri, 27 Apr 2012 13:27:46 -0400 Subject: NFS: Remove extra rpc_clnt argument to proc_lookup Now that I'm doing secinfo automatically in the v4 code this extra argument isn't needed. Signed-off-by: Bryan Schumaker Signed-off-by: Trond Myklebust --- fs/nfs/dir.c | 6 +++--- fs/nfs/namespace.c | 3 +-- fs/nfs/nfs3proc.c | 2 +- fs/nfs/nfs4proc.c | 2 +- fs/nfs/proc.c | 2 +- include/linux/nfs_xdr.h | 2 +- 6 files changed, 8 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 8789210c6905..82b42e2ea65c 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1143,7 +1143,7 @@ static int nfs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd) if (fhandle == NULL || fattr == NULL) goto out_error; - error = NFS_PROTO(dir)->lookup(NFS_SERVER(dir)->client, dir, &dentry->d_name, fhandle, fattr); + error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr); if (error) goto out_bad; if (nfs_compare_fh(NFS_FH(inode), fhandle)) @@ -1299,7 +1299,7 @@ static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, stru parent = dentry->d_parent; /* Protect against concurrent sillydeletes */ nfs_block_sillyrename(parent); - error = NFS_PROTO(dir)->lookup(NFS_SERVER(dir)->client, dir, &dentry->d_name, fhandle, fattr); + error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr); if (error == -ENOENT) goto no_entry; if (error < 0) { @@ -1646,7 +1646,7 @@ int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fhandle, if (dentry->d_inode) goto out; if (fhandle->size == 0) { - error = NFS_PROTO(dir)->lookup(NFS_SERVER(dir)->client, dir, &dentry->d_name, fhandle, fattr); + error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr); if (error) goto out_error; } diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index e36fd8a51819..08b9c93675da 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -261,8 +261,7 @@ struct vfsmount *nfs_submount(struct nfs_server *server, struct dentry *dentry, struct dentry *parent = dget_parent(dentry); /* Look it up again to get its attributes */ - err = server->nfs_client->rpc_ops->lookup(server->client, parent->d_inode, - &dentry->d_name, fh, fattr); + err = server->nfs_client->rpc_ops->lookup(parent->d_inode, &dentry->d_name, fh, fattr); dput(parent); if (err != 0) return ERR_PTR(err); diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index c23214d55ecf..48bcad294161 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -142,7 +142,7 @@ nfs3_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr, } static int -nfs3_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, struct qstr *name, +nfs3_proc_lookup(struct inode *dir, struct qstr *name, struct nfs_fh *fhandle, struct nfs_fattr *fattr) { struct nfs3_diropargs arg = { diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 2091af294c61..1780391a2c4c 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2578,7 +2578,7 @@ out: return err; } -static int nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, struct qstr *name, +static int nfs4_proc_lookup(struct inode *dir, struct qstr *name, struct nfs_fh *fhandle, struct nfs_fattr *fattr) { int status; diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c index 76b3229fc527..fea9163d6f8e 100644 --- a/fs/nfs/proc.c +++ b/fs/nfs/proc.c @@ -178,7 +178,7 @@ nfs_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr, } static int -nfs_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, struct qstr *name, +nfs_proc_lookup(struct inode *dir, struct qstr *name, struct nfs_fh *fhandle, struct nfs_fattr *fattr) { struct nfs_diropargs arg = { diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 4dada94eba7d..c940d46eb423 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1347,7 +1347,7 @@ struct nfs_rpc_ops { struct nfs_fattr *); int (*setattr) (struct dentry *, struct nfs_fattr *, struct iattr *); - int (*lookup) (struct rpc_clnt *clnt, struct inode *, struct qstr *, + int (*lookup) (struct inode *, struct qstr *, struct nfs_fh *, struct nfs_fattr *); int (*access) (struct inode *, struct nfs_access_entry *); int (*readlink)(struct inode *, struct page *, unsigned int, -- cgit v1.2.3 From 4f97615d19c370d1d907ef37f8bcd9c3672851ca Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 30 Apr 2012 18:39:20 -0400 Subject: NFS: Fix a compile issue when CONFIG_NFS_V4_1 is undefined struct nfs_direct_req can't compile when struct pnfs_ds_commit_info is undefined. Reported-by: Bryan Schumaker Signed-off-by: Trond Myklebust Cc: Fred Isaman --- include/linux/nfs_xdr.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index c940d46eb423..6deb8f097c42 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1176,6 +1176,11 @@ struct nfs41_free_stateid_res { struct nfs4_sequence_res seq_res; }; +#else + +struct pnfs_ds_commit_info { +}; + #endif /* CONFIG_NFS_V4_1 */ struct nfs_page; -- cgit v1.2.3 From 3a1556e8662cc425c433b463fcdae138908ca467 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 27 Apr 2012 13:48:18 -0400 Subject: NFSv2/v3: Simulate the change attribute Use the ctime to simulate a change attribute for NFSv2 and NFSv3. Signed-off-by: Trond Myklebust --- fs/nfs/client.c | 2 +- fs/nfs/internal.h | 12 ++++++++++++ fs/nfs/nfs2xdr.c | 2 ++ fs/nfs/nfs3xdr.c | 3 +++ include/linux/nfs_xdr.h | 6 +++--- 5 files changed, 21 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 60f7e4ec842c..a8f8de618d73 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -880,7 +880,7 @@ static int nfs_init_server(struct nfs_server *server, server->options = data->options; server->caps |= NFS_CAP_HARDLINKS|NFS_CAP_SYMLINKS|NFS_CAP_FILEID| NFS_CAP_MODE|NFS_CAP_NLINK|NFS_CAP_OWNER|NFS_CAP_OWNER_GROUP| - NFS_CAP_ATIME|NFS_CAP_CTIME|NFS_CAP_MTIME; + NFS_CAP_ATIME|NFS_CAP_CTIME|NFS_CAP_MTIME|NFS_CAP_CHANGE_ATTR; if (data->rsize) server->rsize = nfs_block_size(data->rsize, NULL); diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 0fd1efaf1cff..1855e8fea423 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -493,3 +493,15 @@ unsigned int nfs_page_array_len(unsigned int base, size_t len) PAGE_SIZE - 1) >> PAGE_SHIFT; } +/* + * Convert a struct timespec into a 64-bit change attribute + * + * This does approximately the same thing as timespec_to_ns(), + * but for calculation efficiency, we multiply the seconds by + * 1024*1024*1024. + */ +static inline +u64 nfs_timespec_to_change_attr(const struct timespec *ts) +{ + return ((u64)ts->tv_sec << 30) + ts->tv_nsec; +} diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c index 1f56000fabbd..c99008e9d8a4 100644 --- a/fs/nfs/nfs2xdr.c +++ b/fs/nfs/nfs2xdr.c @@ -313,6 +313,8 @@ static int decode_fattr(struct xdr_stream *xdr, struct nfs_fattr *fattr) p = xdr_decode_time(p, &fattr->atime); p = xdr_decode_time(p, &fattr->mtime); xdr_decode_time(p, &fattr->ctime); + fattr->change_attr = nfs_timespec_to_change_attr(&fattr->ctime); + return 0; out_overflow: print_overflow_msg(__func__, xdr); diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index 01e53e94f53d..ee284c2b2757 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -675,6 +675,7 @@ static int decode_fattr3(struct xdr_stream *xdr, struct nfs_fattr *fattr) p = xdr_decode_nfstime3(p, &fattr->atime); p = xdr_decode_nfstime3(p, &fattr->mtime); xdr_decode_nfstime3(p, &fattr->ctime); + fattr->change_attr = nfs_timespec_to_change_attr(&fattr->ctime); fattr->valid |= NFS_ATTR_FATTR_V3; return 0; @@ -725,12 +726,14 @@ static int decode_wcc_attr(struct xdr_stream *xdr, struct nfs_fattr *fattr) goto out_overflow; fattr->valid |= NFS_ATTR_FATTR_PRESIZE + | NFS_ATTR_FATTR_PRECHANGE | NFS_ATTR_FATTR_PREMTIME | NFS_ATTR_FATTR_PRECTIME; p = xdr_decode_size3(p, &fattr->pre_size); p = xdr_decode_nfstime3(p, &fattr->pre_mtime); xdr_decode_nfstime3(p, &fattr->pre_ctime); + fattr->pre_change_attr = nfs_timespec_to_change_attr(&fattr->pre_ctime); return 0; out_overflow: diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 6deb8f097c42..bc3680885428 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -106,14 +106,14 @@ struct nfs_fattr { | NFS_ATTR_FATTR_FILEID \ | NFS_ATTR_FATTR_ATIME \ | NFS_ATTR_FATTR_MTIME \ - | NFS_ATTR_FATTR_CTIME) + | NFS_ATTR_FATTR_CTIME \ + | NFS_ATTR_FATTR_CHANGE) #define NFS_ATTR_FATTR_V2 (NFS_ATTR_FATTR \ | NFS_ATTR_FATTR_BLOCKS_USED) #define NFS_ATTR_FATTR_V3 (NFS_ATTR_FATTR \ | NFS_ATTR_FATTR_SPACE_USED) #define NFS_ATTR_FATTR_V4 (NFS_ATTR_FATTR \ - | NFS_ATTR_FATTR_SPACE_USED \ - | NFS_ATTR_FATTR_CHANGE) + | NFS_ATTR_FATTR_SPACE_USED) /* * Info on the file system -- cgit v1.2.3 From 90ff0c548d1220d31f80e498b587393895705e6c Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 27 Apr 2012 13:48:18 -0400 Subject: NFSv4: Simplify the NFSv4 OPEN compound Get rid of the post-op GETATTR on the directory in order to reduce the amount of processing done on the server. The cost is that if we later need to stat() the directory, then we know that the ctime and mtime are likely to be invalid. Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 11 +---------- fs/nfs/nfs4xdr.c | 18 +----------------- include/linux/nfs_xdr.h | 2 -- 3 files changed, 2 insertions(+), 29 deletions(-) (limited to 'include') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 2e0fbff37d1f..f01c3d1b54b7 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -788,7 +788,6 @@ struct nfs4_opendata { struct nfs4_string owner_name; struct nfs4_string group_name; struct nfs_fattr f_attr; - struct nfs_fattr dir_attr; struct dentry *dir; struct dentry *dentry; struct nfs4_state_owner *owner; @@ -804,12 +803,10 @@ struct nfs4_opendata { static void nfs4_init_opendata_res(struct nfs4_opendata *p) { p->o_res.f_attr = &p->f_attr; - p->o_res.dir_attr = &p->dir_attr; p->o_res.seqid = p->o_arg.seqid; p->c_res.seqid = p->c_arg.seqid; p->o_res.server = p->o_arg.server; nfs_fattr_init(&p->f_attr); - nfs_fattr_init(&p->dir_attr); nfs_fattr_init_names(&p->f_attr, &p->owner_name, &p->group_name); } @@ -843,7 +840,6 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, p->o_arg.name = &dentry->d_name; p->o_arg.server = server; p->o_arg.bitmask = server->attr_bitmask; - p->o_arg.dir_bitmask = server->cache_consistency_bitmask; p->o_arg.claim = NFS4_OPEN_CLAIM_NULL; if (attrs != NULL && attrs->ia_valid != 0) { __be32 verf[2]; @@ -1611,8 +1607,6 @@ static int _nfs4_recover_proc_open(struct nfs4_opendata *data) nfs_fattr_map_and_free_names(NFS_SERVER(dir), &data->f_attr); - nfs_refresh_inode(dir, o_res->dir_attr); - if (o_res->rflags & NFS4_OPEN_RESULT_CONFIRM) { status = _nfs4_proc_open_confirm(data); if (status != 0) @@ -1645,11 +1639,8 @@ static int _nfs4_proc_open(struct nfs4_opendata *data) nfs_fattr_map_and_free_names(server, &data->f_attr); - if (o_arg->open_flags & O_CREAT) { + if (o_arg->open_flags & O_CREAT) update_changeattr(dir, &o_res->cinfo); - nfs_post_op_update_inode(dir, o_res->dir_attr); - } else - nfs_refresh_inode(dir, o_res->dir_attr); if ((o_res->rflags & NFS4_OPEN_RESULT_LOCKTYPE_POSIX) == 0) server->caps &= ~NFS_CAP_POSIX_LOCK; if(o_res->rflags & NFS4_OPEN_RESULT_CONFIRM) { diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index ac7a3b014d99..6e878dcc0d2d 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -431,20 +431,14 @@ static int nfs4_stat_to_errno(int); #define NFS4_enc_open_sz (compound_encode_hdr_maxsz + \ encode_sequence_maxsz + \ encode_putfh_maxsz + \ - encode_savefh_maxsz + \ encode_open_maxsz + \ encode_getfh_maxsz + \ - encode_getattr_maxsz + \ - encode_restorefh_maxsz + \ encode_getattr_maxsz) #define NFS4_dec_open_sz (compound_decode_hdr_maxsz + \ decode_sequence_maxsz + \ decode_putfh_maxsz + \ - decode_savefh_maxsz + \ decode_open_maxsz + \ decode_getfh_maxsz + \ - decode_getattr_maxsz + \ - decode_restorefh_maxsz + \ decode_getattr_maxsz) #define NFS4_enc_open_confirm_sz \ (compound_encode_hdr_maxsz + \ @@ -2191,12 +2185,9 @@ static void nfs4_xdr_enc_open(struct rpc_rqst *req, struct xdr_stream *xdr, encode_compound_hdr(xdr, req, &hdr); encode_sequence(xdr, &args->seq_args, &hdr); encode_putfh(xdr, args->fh, &hdr); - encode_savefh(xdr, &hdr); encode_open(xdr, args, &hdr); encode_getfh(xdr, &hdr); encode_getfattr(xdr, args->bitmask, &hdr); - encode_restorefh(xdr, &hdr); - encode_getfattr(xdr, args->dir_bitmask, &hdr); encode_nops(&hdr); } @@ -6073,9 +6064,6 @@ static int nfs4_xdr_dec_open(struct rpc_rqst *rqstp, struct xdr_stream *xdr, if (status) goto out; status = decode_putfh(xdr); - if (status) - goto out; - status = decode_savefh(xdr); if (status) goto out; status = decode_open(xdr, res); @@ -6083,11 +6071,7 @@ static int nfs4_xdr_dec_open(struct rpc_rqst *rqstp, struct xdr_stream *xdr, goto out; if (decode_getfh(xdr, &res->fh) != 0) goto out; - if (decode_getfattr(xdr, res->f_attr, res->server) != 0) - goto out; - if (decode_restorefh(xdr) != 0) - goto out; - decode_getfattr(xdr, res->dir_attr, res->server); + decode_getfattr(xdr, res->f_attr, res->server); out: return status; } diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index bc3680885428..92a929fc97c8 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -338,7 +338,6 @@ struct nfs_openargs { const struct qstr * name; const struct nfs_server *server; /* Needed for ID mapping */ const u32 * bitmask; - const u32 * dir_bitmask; __u32 claim; struct nfs4_sequence_args seq_args; }; @@ -349,7 +348,6 @@ struct nfs_openres { struct nfs4_change_info cinfo; __u32 rflags; struct nfs_fattr * f_attr; - struct nfs_fattr * dir_attr; struct nfs_seqid * seqid; const struct nfs_server *server; fmode_t delegation_type; -- cgit v1.2.3 From 7c317fcfbae773e493ecee1c53738db774b1d0ca Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 27 Apr 2012 13:48:18 -0400 Subject: NFSv4: Simplify the NFSv4 CREATE compound Get rid of the post-op GETATTR on the directory in order to reduce the amount of processing done on the server. Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 4 ---- fs/nfs/nfs4xdr.c | 19 +------------------ include/linux/nfs_xdr.h | 1 - 3 files changed, 1 insertion(+), 23 deletions(-) (limited to 'include') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index f01c3d1b54b7..619bc1eb157b 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2994,7 +2994,6 @@ struct nfs4_createdata { struct nfs4_create_res res; struct nfs_fh fh; struct nfs_fattr fattr; - struct nfs_fattr dir_fattr; }; static struct nfs4_createdata *nfs4_alloc_createdata(struct inode *dir, @@ -3018,9 +3017,7 @@ static struct nfs4_createdata *nfs4_alloc_createdata(struct inode *dir, data->res.server = server; data->res.fh = &data->fh; data->res.fattr = &data->fattr; - data->res.dir_fattr = &data->dir_fattr; nfs_fattr_init(data->res.fattr); - nfs_fattr_init(data->res.dir_fattr); } return data; } @@ -3031,7 +3028,6 @@ static int nfs4_do_create(struct inode *dir, struct dentry *dentry, struct nfs4_ &data->arg.seq_args, &data->res.seq_res, 1); if (status == 0) { update_changeattr(dir, &data->res.dir_cinfo); - nfs_post_op_update_inode(dir, data->res.dir_fattr); status = nfs_instantiate(dentry, data->res.fh, data->res.fattr); } return status; diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 6e878dcc0d2d..1a70097a8dc7 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -647,20 +647,14 @@ static int nfs4_stat_to_errno(int); #define NFS4_enc_create_sz (compound_encode_hdr_maxsz + \ encode_sequence_maxsz + \ encode_putfh_maxsz + \ - encode_savefh_maxsz + \ encode_create_maxsz + \ encode_getfh_maxsz + \ - encode_getattr_maxsz + \ - encode_restorefh_maxsz + \ encode_getattr_maxsz) #define NFS4_dec_create_sz (compound_decode_hdr_maxsz + \ decode_sequence_maxsz + \ decode_putfh_maxsz + \ - decode_savefh_maxsz + \ decode_create_maxsz + \ decode_getfh_maxsz + \ - decode_getattr_maxsz + \ - decode_restorefh_maxsz + \ decode_getattr_maxsz) #define NFS4_enc_pathconf_sz (compound_encode_hdr_maxsz + \ encode_sequence_maxsz + \ @@ -2119,12 +2113,9 @@ static void nfs4_xdr_enc_create(struct rpc_rqst *req, struct xdr_stream *xdr, encode_compound_hdr(xdr, req, &hdr); encode_sequence(xdr, &args->seq_args, &hdr); encode_putfh(xdr, args->dir_fh, &hdr); - encode_savefh(xdr, &hdr); encode_create(xdr, args, &hdr); encode_getfh(xdr, &hdr); encode_getfattr(xdr, args->bitmask, &hdr); - encode_restorefh(xdr, &hdr); - encode_getfattr(xdr, args->bitmask, &hdr); encode_nops(&hdr); } @@ -5893,9 +5884,6 @@ static int nfs4_xdr_dec_create(struct rpc_rqst *rqstp, struct xdr_stream *xdr, if (status) goto out; status = decode_putfh(xdr); - if (status) - goto out; - status = decode_savefh(xdr); if (status) goto out; status = decode_create(xdr, &res->dir_cinfo); @@ -5904,12 +5892,7 @@ static int nfs4_xdr_dec_create(struct rpc_rqst *rqstp, struct xdr_stream *xdr, status = decode_getfh(xdr, res->fh); if (status) goto out; - if (decode_getfattr(xdr, res->fattr, res->server)) - goto out; - status = decode_restorefh(xdr); - if (status) - goto out; - decode_getfattr(xdr, res->dir_fattr, res->server); + decode_getfattr(xdr, res->fattr, res->server); out: return status; } diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 92a929fc97c8..696a17e047be 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -855,7 +855,6 @@ struct nfs4_create_res { struct nfs_fh * fh; struct nfs_fattr * fattr; struct nfs4_change_info dir_cinfo; - struct nfs_fattr * dir_fattr; struct nfs4_sequence_res seq_res; }; -- cgit v1.2.3 From 778d28172f710184855bcfeadcdd6b46997c4de2 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 27 Apr 2012 13:48:19 -0400 Subject: NFSv4: Simplify the NFSv4 REMOVE, LINK and RENAME compounds Get rid of the post-op GETATTR on the directory in order to reduce the amount of processing done on the server. Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 34 +++------------------------------- fs/nfs/nfs4xdr.c | 37 ++++--------------------------------- include/linux/nfs_xdr.h | 2 -- 3 files changed, 7 insertions(+), 66 deletions(-) (limited to 'include') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 619bc1eb157b..c746b0cab499 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2775,7 +2775,6 @@ static int _nfs4_proc_remove(struct inode *dir, struct qstr *name) .fh = NFS_FH(dir), .name.len = name->len, .name.name = name->name, - .bitmask = server->attr_bitmask, }; struct nfs_removeres res = { .server = server, @@ -2785,19 +2784,11 @@ static int _nfs4_proc_remove(struct inode *dir, struct qstr *name) .rpc_argp = &args, .rpc_resp = &res, }; - int status = -ENOMEM; - - res.dir_attr = nfs_alloc_fattr(); - if (res.dir_attr == NULL) - goto out; + int status; status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 1); - if (status == 0) { + if (status == 0) update_changeattr(dir, &res.cinfo); - nfs_post_op_update_inode(dir, res.dir_attr); - } - nfs_free_fattr(res.dir_attr); -out: return status; } @@ -2819,7 +2810,6 @@ static void nfs4_proc_unlink_setup(struct rpc_message *msg, struct inode *dir) struct nfs_removeargs *args = msg->rpc_argp; struct nfs_removeres *res = msg->rpc_resp; - args->bitmask = server->cache_consistency_bitmask; res->server = server; msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_REMOVE]; nfs41_init_sequence(&args->seq_args, &res->seq_res, 1); @@ -2844,7 +2834,6 @@ static int nfs4_proc_unlink_done(struct rpc_task *task, struct inode *dir) if (nfs4_async_handle_error(task, res->server, NULL) == -EAGAIN) return 0; update_changeattr(dir, &res->cinfo); - nfs_post_op_update_inode(dir, res->dir_attr); return 1; } @@ -2855,7 +2844,6 @@ static void nfs4_proc_rename_setup(struct rpc_message *msg, struct inode *dir) struct nfs_renameres *res = msg->rpc_resp; msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_RENAME]; - arg->bitmask = server->attr_bitmask; res->server = server; nfs41_init_sequence(&arg->seq_args, &res->seq_res, 1); } @@ -2881,9 +2869,7 @@ static int nfs4_proc_rename_done(struct rpc_task *task, struct inode *old_dir, return 0; update_changeattr(old_dir, &res->old_cinfo); - nfs_post_op_update_inode(old_dir, res->old_fattr); update_changeattr(new_dir, &res->new_cinfo); - nfs_post_op_update_inode(new_dir, res->new_fattr); return 1; } @@ -2896,7 +2882,6 @@ static int _nfs4_proc_rename(struct inode *old_dir, struct qstr *old_name, .new_dir = NFS_FH(new_dir), .old_name = old_name, .new_name = new_name, - .bitmask = server->attr_bitmask, }; struct nfs_renameres res = { .server = server, @@ -2908,21 +2893,11 @@ static int _nfs4_proc_rename(struct inode *old_dir, struct qstr *old_name, }; int status = -ENOMEM; - res.old_fattr = nfs_alloc_fattr(); - res.new_fattr = nfs_alloc_fattr(); - if (res.old_fattr == NULL || res.new_fattr == NULL) - goto out; - status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1); if (!status) { update_changeattr(old_dir, &res.old_cinfo); - nfs_post_op_update_inode(old_dir, res.old_fattr); update_changeattr(new_dir, &res.new_cinfo); - nfs_post_op_update_inode(new_dir, res.new_fattr); } -out: - nfs_free_fattr(res.new_fattr); - nfs_free_fattr(res.old_fattr); return status; } @@ -2960,18 +2935,15 @@ static int _nfs4_proc_link(struct inode *inode, struct inode *dir, struct qstr * int status = -ENOMEM; res.fattr = nfs_alloc_fattr(); - res.dir_attr = nfs_alloc_fattr(); - if (res.fattr == NULL || res.dir_attr == NULL) + if (res.fattr == NULL) goto out; status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1); if (!status) { update_changeattr(dir, &res.cinfo); - nfs_post_op_update_inode(dir, res.dir_attr); nfs_post_op_update_inode(inode, res.fattr); } out: - nfs_free_fattr(res.dir_attr); nfs_free_fattr(res.fattr); return status; } diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 1a70097a8dc7..49483f19c5d3 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -589,38 +589,29 @@ static int nfs4_stat_to_errno(int); #define NFS4_enc_remove_sz (compound_encode_hdr_maxsz + \ encode_sequence_maxsz + \ encode_putfh_maxsz + \ - encode_remove_maxsz + \ - encode_getattr_maxsz) + encode_remove_maxsz) #define NFS4_dec_remove_sz (compound_decode_hdr_maxsz + \ decode_sequence_maxsz + \ decode_putfh_maxsz + \ - decode_remove_maxsz + \ - decode_getattr_maxsz) + decode_remove_maxsz) #define NFS4_enc_rename_sz (compound_encode_hdr_maxsz + \ encode_sequence_maxsz + \ encode_putfh_maxsz + \ encode_savefh_maxsz + \ encode_putfh_maxsz + \ - encode_rename_maxsz + \ - encode_getattr_maxsz + \ - encode_restorefh_maxsz + \ - encode_getattr_maxsz) + encode_rename_maxsz) #define NFS4_dec_rename_sz (compound_decode_hdr_maxsz + \ decode_sequence_maxsz + \ decode_putfh_maxsz + \ decode_savefh_maxsz + \ decode_putfh_maxsz + \ - decode_rename_maxsz + \ - decode_getattr_maxsz + \ - decode_restorefh_maxsz + \ - decode_getattr_maxsz) + decode_rename_maxsz) #define NFS4_enc_link_sz (compound_encode_hdr_maxsz + \ encode_sequence_maxsz + \ encode_putfh_maxsz + \ encode_savefh_maxsz + \ encode_putfh_maxsz + \ encode_link_maxsz + \ - encode_getattr_maxsz + \ encode_restorefh_maxsz + \ encode_getattr_maxsz) #define NFS4_dec_link_sz (compound_decode_hdr_maxsz + \ @@ -629,7 +620,6 @@ static int nfs4_stat_to_errno(int); decode_savefh_maxsz + \ decode_putfh_maxsz + \ decode_link_maxsz + \ - decode_getattr_maxsz + \ decode_restorefh_maxsz + \ decode_getattr_maxsz) #define NFS4_enc_symlink_sz (compound_encode_hdr_maxsz + \ @@ -2052,7 +2042,6 @@ static void nfs4_xdr_enc_remove(struct rpc_rqst *req, struct xdr_stream *xdr, encode_sequence(xdr, &args->seq_args, &hdr); encode_putfh(xdr, args->fh, &hdr); encode_remove(xdr, &args->name, &hdr); - encode_getfattr(xdr, args->bitmask, &hdr); encode_nops(&hdr); } @@ -2072,9 +2061,6 @@ static void nfs4_xdr_enc_rename(struct rpc_rqst *req, struct xdr_stream *xdr, encode_savefh(xdr, &hdr); encode_putfh(xdr, args->new_dir, &hdr); encode_rename(xdr, args->old_name, args->new_name, &hdr); - encode_getfattr(xdr, args->bitmask, &hdr); - encode_restorefh(xdr, &hdr); - encode_getfattr(xdr, args->bitmask, &hdr); encode_nops(&hdr); } @@ -2094,7 +2080,6 @@ static void nfs4_xdr_enc_link(struct rpc_rqst *req, struct xdr_stream *xdr, encode_savefh(xdr, &hdr); encode_putfh(xdr, args->dir_fh, &hdr); encode_link(xdr, args->name, &hdr); - encode_getfattr(xdr, args->bitmask, &hdr); encode_restorefh(xdr, &hdr); encode_getfattr(xdr, args->bitmask, &hdr); encode_nops(&hdr); @@ -5782,9 +5767,6 @@ static int nfs4_xdr_dec_remove(struct rpc_rqst *rqstp, struct xdr_stream *xdr, if (status) goto out; status = decode_remove(xdr, &res->cinfo); - if (status) - goto out; - decode_getfattr(xdr, res->dir_attr, res->server); out: return status; } @@ -5814,15 +5796,6 @@ static int nfs4_xdr_dec_rename(struct rpc_rqst *rqstp, struct xdr_stream *xdr, if (status) goto out; status = decode_rename(xdr, &res->old_cinfo, &res->new_cinfo); - if (status) - goto out; - /* Current FH is target directory */ - if (decode_getfattr(xdr, res->new_fattr, res->server)) - goto out; - status = decode_restorefh(xdr); - if (status) - goto out; - decode_getfattr(xdr, res->old_fattr, res->server); out: return status; } @@ -5858,8 +5831,6 @@ static int nfs4_xdr_dec_link(struct rpc_rqst *rqstp, struct xdr_stream *xdr, * Note order: OP_LINK leaves the directory as the current * filehandle. */ - if (decode_getfattr(xdr, res->dir_attr, res->server)) - goto out; status = decode_restorefh(xdr); if (status) goto out; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 696a17e047be..2e53a3f1d2ff 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -540,7 +540,6 @@ struct nfs_commitres { struct nfs_removeargs { const struct nfs_fh *fh; struct qstr name; - const u32 * bitmask; struct nfs4_sequence_args seq_args; }; @@ -559,7 +558,6 @@ struct nfs_renameargs { const struct nfs_fh *new_dir; const struct qstr *old_name; const struct qstr *new_name; - const u32 *bitmask; struct nfs4_sequence_args seq_args; }; -- cgit v1.2.3 From d69ee9b85541a69a1092f5da675bd23256dc62af Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 1 May 2012 17:37:59 -0400 Subject: NFS: Adapt readdirplus to application usage patterns While the use of READDIRPLUS is significantly more efficient than READDIR followed by many LOOKUP calls, it is still less efficient than just READDIR if the attributes are not required. This patch tracks when lookups are attempted on the directory, and uses that information to selectively disable READDIRPLUS on that directory. The first 'readdir' call is always served using READDIRPLUS. Subsequent calls only use READDIRPLUS if there was a successful lookup or revalidation on a child in the mean time. Credit for the original idea should go to Neil Brown. See: http://www.spinics.net/lists/linux-nfs/msg19996.html However, the implementation in this patch differs from Neil's in that it focuses on tracking lookups rather than calls to stat(). Signed-off-by: Trond Myklebust Cc: Neil Brown --- fs/nfs/dir.c | 33 +++++++++++++++++++++++++++++++-- fs/nfs/inode.c | 2 -- include/linux/nfs_fs.h | 5 ----- 3 files changed, 31 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 82b42e2ea65c..d0884c0d9464 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -474,6 +474,29 @@ different: return 0; } +static +bool nfs_use_readdirplus(struct inode *dir, struct file *filp) +{ + if (!nfs_server_capable(dir, NFS_CAP_READDIRPLUS)) + return false; + if (test_and_clear_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(dir)->flags)) + return true; + if (filp->f_pos == 0) + return true; + return false; +} + +/* + * This function is called by the lookup code to request the use of + * readdirplus to accelerate any future lookups in the same + * directory. + */ +static +void nfs_advise_use_readdirplus(struct inode *dir) +{ + set_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(dir)->flags); +} + static void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry) { @@ -874,7 +897,7 @@ static int nfs_readdir(struct file *filp, void *dirent, filldir_t filldir) desc->file = filp; desc->dir_cookie = &dir_ctx->dir_cookie; desc->decode = NFS_PROTO(inode)->decode_dirent; - desc->plus = NFS_USE_READDIRPLUS(inode); + desc->plus = nfs_use_readdirplus(inode, filp) ? 1 : 0; nfs_block_sillyrename(dentry); res = nfs_revalidate_mapping(inode, filp->f_mapping); @@ -1114,7 +1137,7 @@ static int nfs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd) if (!inode) { if (nfs_neg_need_reval(dir, dentry, nd)) goto out_bad; - goto out_valid; + goto out_valid_noent; } if (is_bad_inode(inode)) { @@ -1156,6 +1179,9 @@ static int nfs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd) out_set_verifier: nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); out_valid: + /* Success: notify readdir to use READDIRPLUS */ + nfs_advise_use_readdirplus(dir); + out_valid_noent: dput(parent); dfprintk(LOOKUPCACHE, "NFS: %s(%s/%s) is valid\n", __func__, dentry->d_parent->d_name.name, @@ -1311,6 +1337,9 @@ static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, stru if (IS_ERR(res)) goto out_unblock_sillyrename; + /* Success: notify readdir to use READDIRPLUS */ + nfs_advise_use_readdirplus(dir); + no_entry: res = d_materialise_unique(dentry, inode); if (res != NULL) { diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 0d53113207e5..9f17cd19e710 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -298,8 +298,6 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->dir_inode_ops; inode->i_fop = &nfs_dir_operations; inode->i_data.a_ops = &nfs_dir_aops; - if (nfs_server_capable(inode, NFS_CAP_READDIRPLUS)) - set_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags); /* Deal with crossing mountpoints */ if (fattr->valid & NFS_ATTR_FATTR_MOUNTPOINT || fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) { diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 8a88c16662c5..6cc7dbaf0695 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -314,11 +314,6 @@ static inline int nfs_server_capable(struct inode *inode, int cap) return NFS_SERVER(inode)->caps & cap; } -static inline int NFS_USE_READDIRPLUS(struct inode *inode) -{ - return test_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags); -} - static inline void nfs_set_verifier(struct dentry * dentry, unsigned long verf) { dentry->d_time = verf; -- cgit v1.2.3 From 3aff4ebb95b20ad8db2c1447e8c52097d89af5a7 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 9 May 2012 14:30:35 -0400 Subject: NFS: Prevent a deadlock in the new writeback code We have to unlock the nfs_page before we call nfs_end_page_writeback to avoid races with functions that expect the page to be unlocked when PG_locked and PG_writeback are not set. The problem is that nfs_unlock_request also releases the nfs_page, causing a deadlock if the release of the nfs_open_context triggers an iput() while the PG_writeback flag is still set... The solution is to separate the unlocking and release of the nfs_page, so that we can do the former before nfs_end_page_writeback and the latter after. Signed-off-by: Trond Myklebust Cc: Fred Isaman --- fs/nfs/pagelist.c | 12 ++++++++++-- fs/nfs/write.c | 6 ++++-- include/linux/nfs_page.h | 1 + 3 files changed, 15 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 33a21ca9b84b..69146f386989 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -128,10 +128,10 @@ nfs_create_request(struct nfs_open_context *ctx, struct inode *inode, } /** - * nfs_unlock_request - Unlock request and wake up sleepers. + * nfs_unlock_request_dont_release - Unlock request and wake up sleepers. * @req: */ -void nfs_unlock_request(struct nfs_page *req) +void nfs_unlock_request_dont_release(struct nfs_page *req) { if (!NFS_WBACK_BUSY(req)) { printk(KERN_ERR "NFS: Invalid unlock attempted\n"); @@ -141,6 +141,14 @@ void nfs_unlock_request(struct nfs_page *req) clear_bit(PG_BUSY, &req->wb_flags); smp_mb__after_clear_bit(); wake_up_bit(&req->wb_flags, PG_BUSY); +} + +/** + * nfs_unlock_request - Unlock request and release the nfs_page + */ +void nfs_unlock_request(struct nfs_page *req) +{ + nfs_unlock_request_dont_release(req); nfs_release_request(req); } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 6f263daac748..fd36b31ee72e 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -628,8 +628,9 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr) remove_req: nfs_inode_remove_request(req); next: - nfs_unlock_request(req); + nfs_unlock_request_dont_release(req); nfs_end_page_writeback(page); + nfs_release_request(req); } out: hdr->release(hdr); @@ -1042,8 +1043,9 @@ static void nfs_redirty_request(struct nfs_page *req) struct page *page = req->wb_page; nfs_mark_request_dirty(req); - nfs_unlock_request(req); + nfs_unlock_request_dont_release(req); nfs_end_page_writeback(page); + nfs_release_request(req); } static void nfs_async_write_error(struct list_head *head) diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index f9ee9eba7f88..ef7504215446 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -96,6 +96,7 @@ extern bool nfs_generic_pg_test(struct nfs_pageio_descriptor *desc, struct nfs_page *req); extern int nfs_wait_on_request(struct nfs_page *); extern void nfs_unlock_request(struct nfs_page *req); +extern void nfs_unlock_request_dont_release(struct nfs_page *req); /* * Lock the page of an asynchronous request without getting a new reference -- cgit v1.2.3 From 7ad84aa9448571678c243f0c5ef383fbe5b50f4f Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 9 May 2012 13:19:15 -0400 Subject: NFS: Clean up - simplify nfs_lock_request() We only have two places where we need to grab a reference when trying to lock the nfs_page. We're better off making that explicit. Signed-off-by: Trond Myklebust Cc: Fred Isaman --- fs/nfs/direct.c | 1 + fs/nfs/write.c | 11 ++++++----- include/linux/nfs_page.h | 14 ++------------ 3 files changed, 9 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 257d0091148b..465ea84a2874 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -657,6 +657,7 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_pageio_descriptor *d break; } nfs_lock_request(req); + kref_get(&req->wb_kref); req->wb_index = pos >> PAGE_SHIFT; req->wb_offset = pos & ~PAGE_MASK; if (!nfs_pageio_add_request(desc, req)) { diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 83823294ffd2..553f7ef1079b 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -260,10 +260,10 @@ static struct nfs_page *nfs_find_and_lock_request(struct page *page, bool nonblo req = nfs_page_find_request_locked(page); if (req == NULL) break; - if (nfs_lock_request_dontget(req)) + if (nfs_lock_request(req)) break; /* Note: If we hold the page lock, as is the case in nfs_writepage, - * then the call to nfs_lock_request_dontget() will always + * then the call to nfs_lock_request() will always * succeed provided that someone hasn't already marked the * request as dirty (in which case we don't care). */ @@ -406,7 +406,7 @@ static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req) struct nfs_inode *nfsi = NFS_I(inode); /* Lock the request! */ - nfs_lock_request_dontget(req); + nfs_lock_request(req); spin_lock(&inode->i_lock); if (!nfsi->npages && nfs_have_delegation(inode, FMODE_WRITE)) @@ -651,6 +651,7 @@ nfs_scan_commit_list(struct list_head *src, struct list_head *dst, list_for_each_entry_safe(req, tmp, src, wb_list) { if (!nfs_lock_request(req)) continue; + kref_get(&req->wb_kref); if (cond_resched_lock(cinfo->lock)) list_safe_reset_next(req, tmp, wb_list); nfs_request_remove_commit_list(req, cinfo); @@ -741,7 +742,7 @@ static struct nfs_page *nfs_try_to_update_request(struct inode *inode, || end < req->wb_offset) goto out_flushme; - if (nfs_lock_request_dontget(req)) + if (nfs_lock_request(req)) break; /* The request is locked, so wait and then retry */ @@ -1717,7 +1718,7 @@ int nfs_wb_page_cancel(struct inode *inode, struct page *page) req = nfs_page_find_request(page); if (req == NULL) break; - if (nfs_lock_request_dontget(req)) { + if (nfs_lock_request(req)) { nfs_clear_request_commit(req); nfs_inode_remove_request(req); /* diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index ef7504215446..263f30a5e10d 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -99,24 +99,14 @@ extern void nfs_unlock_request(struct nfs_page *req); extern void nfs_unlock_request_dont_release(struct nfs_page *req); /* - * Lock the page of an asynchronous request without getting a new reference + * Lock the page of an asynchronous request */ -static inline int -nfs_lock_request_dontget(struct nfs_page *req) -{ - return !test_and_set_bit(PG_BUSY, &req->wb_flags); -} - static inline int nfs_lock_request(struct nfs_page *req) { - if (test_and_set_bit(PG_BUSY, &req->wb_flags)) - return 0; - kref_get(&req->wb_kref); - return 1; + return !test_and_set_bit(PG_BUSY, &req->wb_flags); } - /** * nfs_list_add_request - Insert a request into a list * @req: request -- cgit v1.2.3 From 1d1afcbc294cc7c788eb5c7b6b98e8d63caf002c Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 9 May 2012 14:04:55 -0400 Subject: NFS: Clean up - Rename nfs_unlock_request and nfs_unlock_request_dont_release Function rename to ensure that the functionality of nfs_unlock_request() mirrors that of nfs_lock_request(). Then let nfs_unlock_and_release_request() do the work of what used to be called nfs_unlock_request()... Signed-off-by: Trond Myklebust Cc: Fred Isaman --- fs/nfs/direct.c | 10 +++++----- fs/nfs/pagelist.c | 11 ++++++----- fs/nfs/write.c | 12 ++++++------ include/linux/nfs_page.h | 2 +- 4 files changed, 18 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 465ea84a2874..845e20196803 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -488,7 +488,7 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) while (!list_empty(&failed)) { nfs_release_request(req); - nfs_unlock_request(req); + nfs_unlock_and_release_request(req); } if (put_dreq(dreq)) @@ -521,7 +521,7 @@ static void nfs_direct_commit_complete(struct nfs_commit_data *data) nfs_mark_request_commit(req, NULL, &cinfo); } else nfs_release_request(req); - nfs_unlock_request(req); + nfs_unlock_and_release_request(req); } if (atomic_dec_and_test(&cinfo.mds->rpcs_out)) @@ -662,7 +662,7 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_pageio_descriptor *d req->wb_offset = pos & ~PAGE_MASK; if (!nfs_pageio_add_request(desc, req)) { result = desc->pg_error; - nfs_unlock_request(req); + nfs_unlock_and_release_request(req); nfs_release_request(req); break; } @@ -739,7 +739,7 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr) default: nfs_release_request(req); } - nfs_unlock_request(req); + nfs_unlock_and_release_request(req); } out_put: @@ -756,7 +756,7 @@ static void nfs_write_sync_pgio_error(struct list_head *head) req = nfs_list_entry(head->next); nfs_list_remove_request(req); nfs_release_request(req); - nfs_unlock_request(req); + nfs_unlock_and_release_request(req); } } diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 69146f386989..aed913c833f4 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -128,10 +128,10 @@ nfs_create_request(struct nfs_open_context *ctx, struct inode *inode, } /** - * nfs_unlock_request_dont_release - Unlock request and wake up sleepers. + * nfs_unlock_request - Unlock request and wake up sleepers. * @req: */ -void nfs_unlock_request_dont_release(struct nfs_page *req) +void nfs_unlock_request(struct nfs_page *req) { if (!NFS_WBACK_BUSY(req)) { printk(KERN_ERR "NFS: Invalid unlock attempted\n"); @@ -144,11 +144,12 @@ void nfs_unlock_request_dont_release(struct nfs_page *req) } /** - * nfs_unlock_request - Unlock request and release the nfs_page + * nfs_unlock_and_release_request - Unlock request and release the nfs_page + * @req: */ -void nfs_unlock_request(struct nfs_page *req) +void nfs_unlock_and_release_request(struct nfs_page *req) { - nfs_unlock_request_dont_release(req); + nfs_unlock_request(req); nfs_release_request(req); } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 553f7ef1079b..8ffd7d5ed58b 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -625,7 +625,7 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr) remove_req: nfs_inode_remove_request(req); next: - nfs_unlock_request_dont_release(req); + nfs_unlock_request(req); nfs_end_page_writeback(req->wb_page); nfs_release_request(req); } @@ -812,7 +812,7 @@ static int nfs_writepage_setup(struct nfs_open_context *ctx, struct page *page, nfs_grow_file(page, offset, count); nfs_mark_uptodate(page, req->wb_pgbase, req->wb_bytes); nfs_mark_request_dirty(req); - nfs_unlock_request(req); + nfs_unlock_and_release_request(req); return 0; } @@ -1039,7 +1039,7 @@ static int nfs_do_multiple_writes(struct list_head *head, static void nfs_redirty_request(struct nfs_page *req) { nfs_mark_request_dirty(req); - nfs_unlock_request_dont_release(req); + nfs_unlock_request(req); nfs_end_page_writeback(req->wb_page); nfs_release_request(req); } @@ -1477,7 +1477,7 @@ void nfs_retry_commit(struct list_head *page_list, dec_bdi_stat(req->wb_page->mapping->backing_dev_info, BDI_RECLAIMABLE); } - nfs_unlock_request(req); + nfs_unlock_and_release_request(req); } } EXPORT_SYMBOL_GPL(nfs_retry_commit); @@ -1555,7 +1555,7 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data) dprintk(" mismatch\n"); nfs_mark_request_dirty(req); next: - nfs_unlock_request(req); + nfs_unlock_and_release_request(req); } nfs_init_cinfo(&cinfo, data->inode, data->dreq); if (atomic_dec_and_test(&cinfo.mds->rpcs_out)) @@ -1726,7 +1726,7 @@ int nfs_wb_page_cancel(struct inode *inode, struct page *page) * page as being dirty */ cancel_dirty_page(page, PAGE_CACHE_SIZE); - nfs_unlock_request(req); + nfs_unlock_and_release_request(req); break; } ret = nfs_wait_on_request(req); diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 263f30a5e10d..88d166b555e8 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -96,7 +96,7 @@ extern bool nfs_generic_pg_test(struct nfs_pageio_descriptor *desc, struct nfs_page *req); extern int nfs_wait_on_request(struct nfs_page *); extern void nfs_unlock_request(struct nfs_page *req); -extern void nfs_unlock_request_dont_release(struct nfs_page *req); +extern void nfs_unlock_and_release_request(struct nfs_page *req); /* * Lock the page of an asynchronous request -- cgit v1.2.3 From e3c0fb7ef515852619932b0da993baa2d107684d Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 21 May 2012 22:45:24 -0400 Subject: NFS: Add NFSDBG_STATE fs/nfs/nfs4state.c does not yet have any dprintk() call sites, and I'm about to introduce some. We will need a new flag for enabling them. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- fs/nfs/nfs4renewd.c | 2 +- fs/nfs/nfs4state.c | 2 ++ include/linux/nfs_fs.h | 1 + 3 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/fs/nfs/nfs4renewd.c b/fs/nfs/nfs4renewd.c index dc484c0eae7f..6930bec91bca 100644 --- a/fs/nfs/nfs4renewd.c +++ b/fs/nfs/nfs4renewd.c @@ -49,7 +49,7 @@ #include "nfs4_fs.h" #include "delegation.h" -#define NFSDBG_FACILITY NFSDBG_PROC +#define NFSDBG_FACILITY NFSDBG_STATE void nfs4_renew_state(struct work_struct *work) diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 7f0fcfc1fe9d..f8c06dec6563 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -57,6 +57,8 @@ #include "internal.h" #include "pnfs.h" +#define NFSDBG_FACILITY NFSDBG_STATE + #define OPENOWNER_POOL_SIZE 8 const nfs4_stateid zero_stateid; diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 6cc7dbaf0695..80a9385b88ab 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -634,6 +634,7 @@ nfs_fileid_to_ino_t(u64 fileid) #define NFSDBG_FSCACHE 0x0800 #define NFSDBG_PNFS 0x1000 #define NFSDBG_PNFS_LD 0x2000 +#define NFSDBG_STATE 0x4000 #define NFSDBG_ALL 0xFFFF #ifdef __KERNEL__ -- cgit v1.2.3 From 722baafc9e638714a69aa66e9ed24ef961ff350c Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 21 May 2012 22:44:22 -0400 Subject: NFS: Fix comment misspelling in struct nfs_client definition Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 7073fc74481c..5498e9d9ba84 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -79,7 +79,7 @@ struct nfs_client { u32 cl_seqid; /* The flags used for obtaining the clientid during EXCHANGE_ID */ u32 cl_exchange_flags; - struct nfs4_session *cl_session; /* sharred session */ + struct nfs4_session *cl_session; /* shared session */ #endif /* CONFIG_NFS_V4 */ #ifdef CONFIG_NFS_FSCACHE -- cgit v1.2.3 From 79d4e1f0d8910f0214a57832ca6d589640d572c0 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 21 May 2012 22:44:31 -0400 Subject: NFS: Use proper naming conventions for NFSv4.1 server scope fields Clean up: When naming fields and data types, follow established conventions to facilitate accurate grep/cscope searches. Additionally, for consistency, move the scope field into the NFSv4- specific part of the nfs_client, and free that memory in the logic that shuts down NFSv4 nfs_clients. Introduced by commit 99fe60d0 "nfs41: exchange_id operation", April 1 2009. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- fs/nfs/client.c | 2 +- fs/nfs/nfs4_fs.h | 2 +- fs/nfs/nfs4proc.c | 18 ++++++++++-------- include/linux/nfs_fs_sb.h | 4 ++-- include/linux/nfs_xdr.h | 4 ++-- 5 files changed, 16 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/fs/nfs/client.c b/fs/nfs/client.c index b4e2199c32b3..471fc9b927a9 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -237,6 +237,7 @@ static void nfs4_shutdown_client(struct nfs_client *clp) nfs_idmap_delete(clp); rpc_destroy_wait_queue(&clp->cl_rpcwaitq); + kfree(clp->cl_serverscope); } /* idr_remove_all is not needed as all id's are removed by nfs_put_client */ @@ -305,7 +306,6 @@ static void nfs_free_client(struct nfs_client *clp) put_net(clp->net); kfree(clp->cl_hostname); - kfree(clp->server_scope); kfree(clp->impl_id); kfree(clp); diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index edeef71f957a..b14bcc3c132d 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -338,7 +338,7 @@ extern void nfs4_schedule_stateid_recovery(const struct nfs_server *, struct nfs extern void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags); extern void nfs41_handle_recall_slot(struct nfs_client *clp); extern void nfs41_handle_server_scope(struct nfs_client *, - struct server_scope **); + struct nfs41_server_scope **); extern void nfs4_put_lock_state(struct nfs4_lock_state *lsp); extern int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl); extern void nfs4_select_rw_stateid(nfs4_stateid *, struct nfs4_state *, diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 0f4e54033abf..94494f24bb12 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5052,7 +5052,8 @@ out_inval: } static bool -nfs41_same_server_scope(struct server_scope *a, struct server_scope *b) +nfs41_same_server_scope(struct nfs41_server_scope *a, + struct nfs41_server_scope *b) { if (a->server_scope_sz == b->server_scope_sz && memcmp(a->server_scope, b->server_scope, a->server_scope_sz) == 0) @@ -5099,7 +5100,8 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred) clp->cl_rpcclient->cl_nodename, clp->cl_rpcclient->cl_auth->au_flavor); - res.server_scope = kzalloc(sizeof(struct server_scope), GFP_KERNEL); + res.server_scope = kzalloc(sizeof(struct nfs41_server_scope), + GFP_KERNEL); if (unlikely(!res.server_scope)) { status = -ENOMEM; goto out; @@ -5123,18 +5125,18 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred) kfree(res.impl_id); if (!status) { - if (clp->server_scope && - !nfs41_same_server_scope(clp->server_scope, + if (clp->cl_serverscope && + !nfs41_same_server_scope(clp->cl_serverscope, res.server_scope)) { dprintk("%s: server_scope mismatch detected\n", __func__); set_bit(NFS4CLNT_SERVER_SCOPE_MISMATCH, &clp->cl_state); - kfree(clp->server_scope); - clp->server_scope = NULL; + kfree(clp->cl_serverscope); + clp->cl_serverscope = NULL; } - if (!clp->server_scope) { - clp->server_scope = res.server_scope; + if (!clp->cl_serverscope) { + clp->cl_serverscope = res.server_scope; goto out; } } diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 5498e9d9ba84..900d733668eb 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -17,7 +17,7 @@ struct nfs4_sequence_args; struct nfs4_sequence_res; struct nfs_server; struct nfs4_minor_version_ops; -struct server_scope; +struct nfs41_server_scope; struct nfs41_impl_id; /* @@ -80,13 +80,13 @@ struct nfs_client { /* The flags used for obtaining the clientid during EXCHANGE_ID */ u32 cl_exchange_flags; struct nfs4_session *cl_session; /* shared session */ + struct nfs41_server_scope *cl_serverscope; #endif /* CONFIG_NFS_V4 */ #ifdef CONFIG_NFS_FSCACHE struct fscache_cookie *fscache; /* client index cache cookie */ #endif - struct server_scope *server_scope; /* from exchange_id */ struct nfs41_impl_id *impl_id; /* from exchange_id */ struct net *net; }; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 2e53a3f1d2ff..c420b8d60a55 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1104,7 +1104,7 @@ struct server_owner { char major_id[NFS4_OPAQUE_LIMIT]; }; -struct server_scope { +struct nfs41_server_scope { uint32_t server_scope_sz; char server_scope[NFS4_OPAQUE_LIMIT]; }; @@ -1118,7 +1118,7 @@ struct nfs41_impl_id { struct nfs41_exchange_id_res { struct nfs_client *client; u32 flags; - struct server_scope *server_scope; + struct nfs41_server_scope *server_scope; struct nfs41_impl_id *impl_id; }; -- cgit v1.2.3 From 591555465ec513c42416392d392fd56866cb220c Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 21 May 2012 22:44:41 -0400 Subject: NFS: Use proper naming conventions for nfs_client.impl_id field Clean up: When naming fields and data types, follow established conventions to facilitate accurate grep/cscope searches. Additionally, for consistency, move the impl_id field into the NFSv4- specific part of the nfs_client, and free that memory in the logic that shuts down NFSv4 nfs_clients. Introduced by commit 7d2ed9ac "NFSv4: parse and display server implementation ids," Fri Feb 17, 2012. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- fs/nfs/client.c | 2 +- fs/nfs/nfs4proc.c | 12 ++++++------ fs/nfs/super.c | 4 ++-- include/linux/nfs_fs_sb.h | 2 +- 4 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 471fc9b927a9..39db1beb92f8 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -238,6 +238,7 @@ static void nfs4_shutdown_client(struct nfs_client *clp) rpc_destroy_wait_queue(&clp->cl_rpcwaitq); kfree(clp->cl_serverscope); + kfree(clp->cl_implid); } /* idr_remove_all is not needed as all id's are removed by nfs_put_client */ @@ -306,7 +307,6 @@ static void nfs_free_client(struct nfs_client *clp) put_net(clp->net); kfree(clp->cl_hostname); - kfree(clp->impl_id); kfree(clp); dprintk("<-- nfs_free_client()\n"); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 94494f24bb12..daa4e1b17313 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5119,8 +5119,8 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred) if (!status) { /* use the most recent implementation id */ - kfree(clp->impl_id); - clp->impl_id = res.impl_id; + kfree(clp->cl_implid); + clp->cl_implid = res.impl_id; } else kfree(res.impl_id); @@ -5144,12 +5144,12 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred) out_server_scope: kfree(res.server_scope); out: - if (clp->impl_id) + if (clp->cl_implid) dprintk("%s: Server Implementation ID: " "domain: %s, name: %s, date: %llu,%u\n", - __func__, clp->impl_id->domain, clp->impl_id->name, - clp->impl_id->date.seconds, - clp->impl_id->date.nseconds); + __func__, clp->cl_implid->domain, clp->cl_implid->name, + clp->cl_implid->date.seconds, + clp->cl_implid->date.nseconds); dprintk("<-- %s status= %d\n", __func__, status); return status; } diff --git a/fs/nfs/super.c b/fs/nfs/super.c index a973eb101a92..ff656c022684 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -796,8 +796,8 @@ static void show_pnfs(struct seq_file *m, struct nfs_server *server) static void show_implementation_id(struct seq_file *m, struct nfs_server *nfss) { - if (nfss->nfs_client && nfss->nfs_client->impl_id) { - struct nfs41_impl_id *impl_id = nfss->nfs_client->impl_id; + if (nfss->nfs_client && nfss->nfs_client->cl_implid) { + struct nfs41_impl_id *impl_id = nfss->nfs_client->cl_implid; seq_printf(m, "\n\timpl_id:\tname='%s',domain='%s'," "date='%llu,%u'", impl_id->name, impl_id->domain, diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 900d733668eb..773e02135903 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -81,13 +81,13 @@ struct nfs_client { u32 cl_exchange_flags; struct nfs4_session *cl_session; /* shared session */ struct nfs41_server_scope *cl_serverscope; + struct nfs41_impl_id *cl_implid; #endif /* CONFIG_NFS_V4 */ #ifdef CONFIG_NFS_FSCACHE struct fscache_cookie *fscache; /* client index cache cookie */ #endif - struct nfs41_impl_id *impl_id; /* from exchange_id */ struct net *net; }; -- cgit v1.2.3 From 73ea666c2bb536f2862cefdb3e014ed62b262ba5 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 21 May 2012 22:44:50 -0400 Subject: NFS: Use proper naming conventions for the nfs_client.net field Clean up: When naming fields and data types, follow established conventions to facilitate accurate grep/cscope searches. Introduced by commit e50a7a1a "NFS: make NFS client allocated per network namespace context," Tue Jan 10, 2012. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- fs/nfs/blocklayout/blocklayoutdev.c | 2 +- fs/nfs/client.c | 22 +++++++++++----------- fs/nfs/idmap.c | 4 ++-- fs/nfs/nfs4filelayoutdev.c | 2 +- include/linux/nfs_fs_sb.h | 2 +- 5 files changed, 16 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/fs/nfs/blocklayout/blocklayoutdev.c b/fs/nfs/blocklayout/blocklayoutdev.c index a5c88a554d92..c96554245ccf 100644 --- a/fs/nfs/blocklayout/blocklayoutdev.c +++ b/fs/nfs/blocklayout/blocklayoutdev.c @@ -123,7 +123,7 @@ nfs4_blk_decode_device(struct nfs_server *server, uint8_t *dataptr; DECLARE_WAITQUEUE(wq, current); int offset, len, i, rc; - struct net *net = server->nfs_client->net; + struct net *net = server->nfs_client->cl_net; struct nfs_net *nn = net_generic(net, nfs_net_id); struct bl_dev_msg *reply = &nn->bl_mount_reply; diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 39db1beb92f8..9b9df71df09a 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -65,7 +65,7 @@ static DECLARE_WAIT_QUEUE_HEAD(nfs_client_active_wq); static int nfs_get_cb_ident_idr(struct nfs_client *clp, int minorversion) { int ret = 0; - struct nfs_net *nn = net_generic(clp->net, nfs_net_id); + struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id); if (clp->rpc_ops->version != 4 || minorversion != 0) return ret; @@ -174,7 +174,7 @@ static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_ clp->cl_rpcclient = ERR_PTR(-EINVAL); clp->cl_proto = cl_init->proto; - clp->net = get_net(cl_init->net); + clp->cl_net = get_net(cl_init->net); #ifdef CONFIG_NFS_V4 err = nfs_get_cb_ident_idr(clp, cl_init->minorversion); @@ -252,7 +252,7 @@ void nfs_cleanup_cb_ident_idr(struct net *net) /* nfs_client_lock held */ static void nfs_cb_idr_remove_locked(struct nfs_client *clp) { - struct nfs_net *nn = net_generic(clp->net, nfs_net_id); + struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id); if (clp->cl_cb_ident) idr_remove(&nn->cb_ident_idr, clp->cl_cb_ident); @@ -305,7 +305,7 @@ static void nfs_free_client(struct nfs_client *clp) if (clp->cl_machine_cred != NULL) put_rpccred(clp->cl_machine_cred); - put_net(clp->net); + put_net(clp->cl_net); kfree(clp->cl_hostname); kfree(clp); @@ -323,7 +323,7 @@ void nfs_put_client(struct nfs_client *clp) return; dprintk("--> nfs_put_client({%d})\n", atomic_read(&clp->cl_count)); - nn = net_generic(clp->net, nfs_net_id); + nn = net_generic(clp->cl_net, nfs_net_id); if (atomic_dec_and_lock(&clp->cl_count, &nn->nfs_client_lock)) { list_del(&clp->cl_share_link); @@ -661,7 +661,7 @@ static int nfs_create_rpc_client(struct nfs_client *clp, { struct rpc_clnt *clnt = NULL; struct rpc_create_args args = { - .net = clp->net, + .net = clp->cl_net, .protocol = clp->cl_proto, .address = (struct sockaddr *)&clp->cl_addr, .addrsize = clp->cl_addrlen, @@ -715,7 +715,7 @@ static int nfs_start_lockd(struct nfs_server *server) .nfs_version = clp->rpc_ops->version, .noresvport = server->flags & NFS_MOUNT_NORESVPORT ? 1 : 0, - .net = clp->net, + .net = clp->cl_net, }; if (nlm_init.nfs_version > 3) @@ -1060,7 +1060,7 @@ static void nfs_server_copy_userdata(struct nfs_server *target, struct nfs_serve static void nfs_server_insert_lists(struct nfs_server *server) { struct nfs_client *clp = server->nfs_client; - struct nfs_net *nn = net_generic(clp->net, nfs_net_id); + struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id); spin_lock(&nn->nfs_client_lock); list_add_tail_rcu(&server->client_link, &clp->cl_superblocks); @@ -1077,7 +1077,7 @@ static void nfs_server_remove_lists(struct nfs_server *server) if (clp == NULL) return; - nn = net_generic(clp->net, nfs_net_id); + nn = net_generic(clp->cl_net, nfs_net_id); spin_lock(&nn->nfs_client_lock); list_del_rcu(&server->client_link); if (list_empty(&clp->cl_superblocks)) @@ -1486,7 +1486,7 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp, .rpc_ops = &nfs_v4_clientops, .proto = ds_proto, .minorversion = mds_clp->cl_minorversion, - .net = mds_clp->net, + .net = mds_clp->cl_net, }; struct rpc_timeout ds_timeout; struct nfs_client *clp; @@ -1709,7 +1709,7 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data, rpc_protocol(parent_server->client), parent_server->client->cl_timeout, parent_client->cl_mvops->minor_version, - parent_client->net); + parent_client->cl_net); if (error < 0) goto error; diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c index 3e8edbe71ec6..2eaecf9d8db7 100644 --- a/fs/nfs/idmap.c +++ b/fs/nfs/idmap.c @@ -415,7 +415,7 @@ static int __nfs_idmap_register(struct dentry *dir, static void nfs_idmap_unregister(struct nfs_client *clp, struct rpc_pipe *pipe) { - struct net *net = clp->net; + struct net *net = clp->cl_net; struct super_block *pipefs_sb; pipefs_sb = rpc_get_sb_net(net); @@ -429,7 +429,7 @@ static int nfs_idmap_register(struct nfs_client *clp, struct idmap *idmap, struct rpc_pipe *pipe) { - struct net *net = clp->net; + struct net *net = clp->cl_net; struct super_block *pipefs_sb; int err = 0; diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c index bf49b78db1b3..c610f84ff030 100644 --- a/fs/nfs/nfs4filelayoutdev.c +++ b/fs/nfs/nfs4filelayoutdev.c @@ -629,7 +629,7 @@ decode_device(struct inode *ino, struct pnfs_device *pdev, gfp_t gfp_flags) mp_count = be32_to_cpup(p); /* multipath count */ for (j = 0; j < mp_count; j++) { - da = decode_ds_addr(NFS_SERVER(ino)->nfs_client->net, + da = decode_ds_addr(NFS_SERVER(ino)->nfs_client->cl_net, &stream, gfp_flags); if (da) list_add_tail(&da->da_node, &dsaddrs); diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 773e02135903..59410b365ba4 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -88,7 +88,7 @@ struct nfs_client { struct fscache_cookie *fscache; /* client index cache cookie */ #endif - struct net *net; + struct net *cl_net; }; /* -- cgit v1.2.3 From f092075dd33ea04000590e8ffea65c2e7d03d764 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 21 May 2012 22:45:41 -0400 Subject: NFS: Always use the same SETCLIENTID boot verifier Currently our NFS client assigns a unique SETCLIENTID boot verifier for each server IP address it knows about. It's set to CURRENT_TIME when the struct nfs_client for that server IP is created. During the SETCLIENTID operation, our client also presents an nfs_client_id4 string to servers, as an identifier on which the server can hang all of this client's NFSv4 state. Our client's nfs_client_id4 string is unique for each server IP address. An NFSv4 server is obligated to wipe all NFSv4 state associated with an nfs_client_id4 string when the client presents the same nfs_client_id4 string along with a changed SETCLIENTID boot verifier. When our client unmounts the last of a server's shares, it destroys that server's struct nfs_client. The next time the client mounts that NFS server, it creates a fresh struct nfs_client with a fresh boot verifier. On seeing the fresh verifer, the server wipes any previous NFSv4 state associated with that nfs_client_id4. However, NFSv4.1 clients are supposed to present the same nfs_client_id4 string to all servers. And, to support Transparent State Migration, the same nfs_client_id4 string should be presented to all NFSv4.0 servers so they recognize that migrated state for this client belongs with state a server may already have for this client. (This is known as the Uniform Client String model). If the nfs_client_id4 string is the same but the boot verifier changes for each server IP address, SETCLIENTID and EXCHANGE_ID operations from such a client could unintentionally result in a server wiping a client's previously obtained lease. Thus, if our NFS client is going to use a fixed nfs_client_id4 string, either for NFSv4.0 or NFSv4.1 mounts, our NFS client should use a boot verifier that does not change depending on server IP address. Replace our current per-nfs_client boot verifier with a per-nfs_net boot verifier. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- fs/nfs/client.c | 2 +- fs/nfs/netns.h | 5 +++++ fs/nfs/nfs4proc.c | 14 ++++++++------ fs/nfs/nfs4xdr.c | 5 ++++- include/linux/nfs_fs_sb.h | 3 --- 5 files changed, 18 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 9b9df71df09a..af9b7e4b9df2 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -184,7 +184,6 @@ static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_ spin_lock_init(&clp->cl_lock); INIT_DELAYED_WORK(&clp->cl_renewd, nfs4_renew_state); rpc_init_wait_queue(&clp->cl_rpcwaitq, "NFS client"); - clp->cl_boot_time = CURRENT_TIME; clp->cl_state = 1 << NFS4CLNT_LEASE_EXPIRED; clp->cl_minorversion = cl_init->minorversion; clp->cl_mvops = nfs_v4_minor_ops[cl_init->minorversion]; @@ -1813,6 +1812,7 @@ void nfs_clients_init(struct net *net) idr_init(&nn->cb_ident_idr); #endif spin_lock_init(&nn->nfs_client_lock); + nn->boot_time = CURRENT_TIME; } #ifdef CONFIG_PROC_FS diff --git a/fs/nfs/netns.h b/fs/nfs/netns.h index aa14ec303e94..8a6394edb8b0 100644 --- a/fs/nfs/netns.h +++ b/fs/nfs/netns.h @@ -1,3 +1,7 @@ +/* + * NFS-private data for each "struct net". Accessed with net_generic(). + */ + #ifndef __NFS_NETNS_H__ #define __NFS_NETNS_H__ @@ -20,6 +24,7 @@ struct nfs_net { struct idr cb_ident_idr; /* Protected by nfs_client_lock */ #endif spinlock_t nfs_client_lock; + struct timespec boot_time; }; extern int nfs_net_id; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 81ccdbbb43e8..9e9334a172cf 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -64,6 +64,7 @@ #include "iostat.h" #include "callback.h" #include "pnfs.h" +#include "netns.h" #define NFSDBG_FACILITY NFSDBG_PROC @@ -3903,8 +3904,8 @@ wait_on_recovery: return -EAGAIN; } -static void nfs4_construct_boot_verifier(struct nfs_client *clp, - nfs4_verifier *bootverf) +static void nfs4_init_boot_verifier(const struct nfs_client *clp, + nfs4_verifier *bootverf) { __be32 verf[2]; @@ -3914,8 +3915,9 @@ static void nfs4_construct_boot_verifier(struct nfs_client *clp, verf[0] = 0; verf[1] = (__be32)(NSEC_PER_SEC + 1); } else { - verf[0] = (__be32)clp->cl_boot_time.tv_sec; - verf[1] = (__be32)clp->cl_boot_time.tv_nsec; + struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id); + verf[0] = (__be32)nn->boot_time.tv_sec; + verf[1] = (__be32)nn->boot_time.tv_nsec; } memcpy(bootverf->data, verf, sizeof(bootverf->data)); } @@ -3939,7 +3941,7 @@ int nfs4_proc_setclientid(struct nfs_client *clp, u32 program, int loop = 0; int status; - nfs4_construct_boot_verifier(clp, &sc_verifier); + nfs4_init_boot_verifier(clp, &sc_verifier); for(;;) { rcu_read_lock(); @@ -5099,7 +5101,7 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred) dprintk("--> %s\n", __func__); BUG_ON(clp == NULL); - nfs4_construct_boot_verifier(clp, &verifier); + nfs4_init_boot_verifier(clp, &verifier); args.id_len = scnprintf(args.id, sizeof(args.id), "%s/%s/%u", diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index db040e971932..12b99825a1c1 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -53,9 +53,11 @@ #include #include #include + #include "nfs4_fs.h" #include "internal.h" #include "pnfs.h" +#include "netns.h" #define NFSDBG_FACILITY NFSDBG_XDR @@ -1702,6 +1704,7 @@ static void encode_create_session(struct xdr_stream *xdr, char machine_name[NFS4_MAX_MACHINE_NAME_LEN]; uint32_t len; struct nfs_client *clp = args->client; + struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id); u32 max_resp_sz_cached; /* @@ -1743,7 +1746,7 @@ static void encode_create_session(struct xdr_stream *xdr, *p++ = cpu_to_be32(RPC_AUTH_UNIX); /* auth_sys */ /* authsys_parms rfc1831 */ - *p++ = cpu_to_be32((u32)clp->cl_boot_time.tv_nsec); /* stamp */ + *p++ = (__be32)nn->boot_time.tv_nsec; /* stamp */ p = xdr_encode_opaque(p, machine_name, len); *p++ = cpu_to_be32(0); /* UID */ *p++ = cpu_to_be32(0); /* GID */ diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 59410b365ba4..fbec57d6dc0a 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -61,9 +61,6 @@ struct nfs_client { struct rpc_wait_queue cl_rpcwaitq; - /* used for the setclientid verifier */ - struct timespec cl_boot_time; - /* idmapper */ struct idmap * cl_idmap; -- cgit v1.2.3 From 8cab4c390b43fe34c07bd33799c1bc24be648122 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 21 May 2012 22:45:59 -0400 Subject: NFS: Refactor nfs_get_client(): initialize nfs_client Clean up: Continue to rationalize the locking in nfs_get_client() by moving the logic that handles the case where a matching server IP address is not found. When we support server trunking detection, client initialization may return a different nfs_client struct than was passed to it. Change the synopsis of the init_client methods to return an nfs_client. The client initialization logic in nfs_get_client() is not much more than a wrapper around ->init_client. It's simpler to keep the little bits of error handling in the version-specific init_client methods. No behavior change is expected. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- fs/nfs/client.c | 76 +++++++++++++++++++++++++++---------------------- fs/nfs/internal.h | 4 +-- include/linux/nfs_xdr.h | 3 +- 3 files changed, 46 insertions(+), 37 deletions(-) (limited to 'include') diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 5f19f9577730..8a4b3c2c5a2b 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -546,7 +546,6 @@ nfs_get_client(const struct nfs_client_initdata *cl_init, int noresvport) { struct nfs_client *clp, *new = NULL; - int error; struct nfs_net *nn = net_generic(cl_init->net, nfs_net_id); dprintk("--> nfs_get_client(%s,v%u)\n", @@ -563,8 +562,13 @@ nfs_get_client(const struct nfs_client_initdata *cl_init, nfs_free_client(new); return nfs_found_client(cl_init, clp); } - if (new) - goto install_client; + if (new) { + list_add(&new->cl_share_link, &nn->nfs_client_list); + spin_unlock(&nn->nfs_client_lock); + return cl_init->rpc_ops->init_client(new, + timeparms, ip_addr, + authflavour, noresvport); + } spin_unlock(&nn->nfs_client_lock); @@ -574,21 +578,6 @@ nfs_get_client(const struct nfs_client_initdata *cl_init, dprintk("<-- nfs_get_client() Failed to find %s (%ld)\n", cl_init->hostname ?: "", PTR_ERR(new)); return new; - - /* install a new client and return with it unready */ -install_client: - clp = new; - list_add(&clp->cl_share_link, &nn->nfs_client_list); - spin_unlock(&nn->nfs_client_lock); - - error = cl_init->rpc_ops->init_client(clp, timeparms, ip_addr, - authflavour, noresvport); - if (error < 0) { - nfs_put_client(clp); - return ERR_PTR(error); - } - dprintk("--> nfs_get_client() = %p [new]\n", clp); - return clp; } /* @@ -813,10 +802,19 @@ static int nfs_init_server_rpcclient(struct nfs_server *server, return 0; } -/* - * Initialise an NFS2 or NFS3 client +/** + * nfs_init_client - Initialise an NFS2 or NFS3 client + * + * @clp: nfs_client to initialise + * @timeparms: timeout parameters for underlying RPC transport + * @ip_addr: IP presentation address (not used) + * @authflavor: authentication flavor for underlying RPC transport + * @noresvport: set if RPC transport can use an ephemeral source port + * + * Returns pointer to an NFS client, or an ERR_PTR value. */ -int nfs_init_client(struct nfs_client *clp, const struct rpc_timeout *timeparms, +struct nfs_client *nfs_init_client(struct nfs_client *clp, + const struct rpc_timeout *timeparms, const char *ip_addr, rpc_authflavor_t authflavour, int noresvport) { @@ -825,7 +823,7 @@ int nfs_init_client(struct nfs_client *clp, const struct rpc_timeout *timeparms, if (clp->cl_cons_state == NFS_CS_READY) { /* the client is already initialised */ dprintk("<-- nfs_init_client() = 0 [already %p]\n", clp); - return 0; + return clp; } /* @@ -837,12 +835,13 @@ int nfs_init_client(struct nfs_client *clp, const struct rpc_timeout *timeparms, if (error < 0) goto error; nfs_mark_client_ready(clp, NFS_CS_READY); - return 0; + return clp; error: nfs_mark_client_ready(clp, error); + nfs_put_client(clp); dprintk("<-- nfs_init_client() = xerror %d\n", error); - return error; + return ERR_PTR(error); } /* @@ -1358,14 +1357,22 @@ static int nfs4_init_client_minor_version(struct nfs_client *clp) return nfs4_init_callback(clp); } -/* - * Initialise an NFS4 client record +/** + * nfs4_init_client - Initialise an NFS4 client record + * + * @clp: nfs_client to initialise + * @timeparms: timeout parameters for underlying RPC transport + * @ip_addr: callback IP address in presentation format + * @authflavor: authentication flavor for underlying RPC transport + * @noresvport: set if RPC transport can use an ephemeral source port + * + * Returns pointer to an NFS client, or an ERR_PTR value. */ -int nfs4_init_client(struct nfs_client *clp, - const struct rpc_timeout *timeparms, - const char *ip_addr, - rpc_authflavor_t authflavour, - int noresvport) +struct nfs_client *nfs4_init_client(struct nfs_client *clp, + const struct rpc_timeout *timeparms, + const char *ip_addr, + rpc_authflavor_t authflavour, + int noresvport) { char buf[INET6_ADDRSTRLEN + 1]; int error; @@ -1373,7 +1380,7 @@ int nfs4_init_client(struct nfs_client *clp, if (clp->cl_cons_state == NFS_CS_READY) { /* the client is initialised already */ dprintk("<-- nfs4_init_client() = 0 [already %p]\n", clp); - return 0; + return clp; } /* Check NFS protocol revision and initialize RPC op vector */ @@ -1413,12 +1420,13 @@ int nfs4_init_client(struct nfs_client *clp, if (!nfs4_has_session(clp)) nfs_mark_client_ready(clp, NFS_CS_READY); - return 0; + return clp; error: nfs_mark_client_ready(clp, error); + nfs_put_client(clp); dprintk("<-- nfs4_init_client() = xerror %d\n", error); - return error; + return ERR_PTR(error); } /* diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 989959a59f07..3a9e80c9524b 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -238,7 +238,7 @@ extern int nfs4_init_ds_session(struct nfs_client *clp); /* proc.c */ void nfs_close_context(struct nfs_open_context *ctx, int is_sync); -extern int nfs_init_client(struct nfs_client *clp, +extern struct nfs_client *nfs_init_client(struct nfs_client *clp, const struct rpc_timeout *timeparms, const char *ip_addr, rpc_authflavor_t authflavour, int noresvport); @@ -373,7 +373,7 @@ void nfs_init_cinfo_from_dreq(struct nfs_commit_info *cinfo, /* nfs4proc.c */ extern void __nfs4_read_done_cb(struct nfs_read_data *); -extern int nfs4_init_client(struct nfs_client *clp, +extern struct nfs_client *nfs4_init_client(struct nfs_client *clp, const struct rpc_timeout *timeparms, const char *ip_addr, rpc_authflavor_t authflavour, diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index c420b8d60a55..0c521cd496a7 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1397,7 +1397,8 @@ struct nfs_rpc_ops { struct nfs_open_context *ctx, int open_flags, struct iattr *iattr); - int (*init_client) (struct nfs_client *, const struct rpc_timeout *, + struct nfs_client * + (*init_client) (struct nfs_client *, const struct rpc_timeout *, const char *, rpc_authflavor_t, int); }; -- cgit v1.2.3 From 4bf590e08f6db3395c181618a4c14f1c39b7c4af Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 21 May 2012 22:46:07 -0400 Subject: NFS: Add nfs_client behavior flags "noresvport" and "discrtry" can be passed to nfs_create_rpc_client() by setting flags in the passed-in nfs_client. This change makes it easy to add new flags. Note that these settings are now "sticky" over the lifetime of a struct nfs_client, and may even be copied when an nfs_client is cloned. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- fs/nfs/client.c | 42 ++++++++++++++++++++---------------------- fs/nfs/internal.h | 6 ++---- include/linux/nfs_fs_sb.h | 3 +++ include/linux/nfs_xdr.h | 2 +- 4 files changed, 26 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 8a4b3c2c5a2b..34b2e68c5249 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -131,6 +131,7 @@ const struct rpc_program nfsacl_program = { #endif /* CONFIG_NFS_V3_ACL */ struct nfs_client_initdata { + unsigned long init_flags; const char *hostname; const struct sockaddr *addr; size_t addrlen; @@ -542,8 +543,7 @@ static struct nfs_client * nfs_get_client(const struct nfs_client_initdata *cl_init, const struct rpc_timeout *timeparms, const char *ip_addr, - rpc_authflavor_t authflavour, - int noresvport) + rpc_authflavor_t authflavour) { struct nfs_client *clp, *new = NULL; struct nfs_net *nn = net_generic(cl_init->net, nfs_net_id); @@ -565,9 +565,10 @@ nfs_get_client(const struct nfs_client_initdata *cl_init, if (new) { list_add(&new->cl_share_link, &nn->nfs_client_list); spin_unlock(&nn->nfs_client_lock); + new->cl_flags = cl_init->init_flags; return cl_init->rpc_ops->init_client(new, timeparms, ip_addr, - authflavour, noresvport); + authflavour); } spin_unlock(&nn->nfs_client_lock); @@ -651,8 +652,7 @@ static void nfs_init_timeout_values(struct rpc_timeout *to, int proto, */ static int nfs_create_rpc_client(struct nfs_client *clp, const struct rpc_timeout *timeparms, - rpc_authflavor_t flavor, - int discrtry, int noresvport) + rpc_authflavor_t flavor) { struct rpc_clnt *clnt = NULL; struct rpc_create_args args = { @@ -667,9 +667,9 @@ static int nfs_create_rpc_client(struct nfs_client *clp, .authflavor = flavor, }; - if (discrtry) + if (test_bit(NFS_CS_DISCRTRY, &clp->cl_flags)) args.flags |= RPC_CLNT_CREATE_DISCRTRY; - if (noresvport) + if (test_bit(NFS_CS_NORESVPORT, &clp->cl_flags)) args.flags |= RPC_CLNT_CREATE_NONPRIVPORT; if (!IS_ERR(clp->cl_rpcclient)) @@ -809,14 +809,12 @@ static int nfs_init_server_rpcclient(struct nfs_server *server, * @timeparms: timeout parameters for underlying RPC transport * @ip_addr: IP presentation address (not used) * @authflavor: authentication flavor for underlying RPC transport - * @noresvport: set if RPC transport can use an ephemeral source port * * Returns pointer to an NFS client, or an ERR_PTR value. */ struct nfs_client *nfs_init_client(struct nfs_client *clp, const struct rpc_timeout *timeparms, - const char *ip_addr, rpc_authflavor_t authflavour, - int noresvport) + const char *ip_addr, rpc_authflavor_t authflavour) { int error; @@ -830,8 +828,7 @@ struct nfs_client *nfs_init_client(struct nfs_client *clp, * Create a client RPC handle for doing FSSTAT with UNIX auth only * - RFC 2623, sec 2.3.2 */ - error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_UNIX, - 0, noresvport); + error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_UNIX); if (error < 0) goto error; nfs_mark_client_ready(clp, NFS_CS_READY); @@ -881,10 +878,11 @@ static int nfs_init_server(struct nfs_server *server, nfs_init_timeout_values(&timeparms, data->nfs_server.protocol, data->timeo, data->retrans); + if (data->flags & NFS_MOUNT_NORESVPORT) + set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags); /* Allocate or find a client reference we can use */ - clp = nfs_get_client(&cl_init, &timeparms, NULL, RPC_AUTH_UNIX, - data->flags & NFS_MOUNT_NORESVPORT); + clp = nfs_get_client(&cl_init, &timeparms, NULL, RPC_AUTH_UNIX); if (IS_ERR(clp)) { dprintk("<-- nfs_init_server() = error %ld\n", PTR_ERR(clp)); return PTR_ERR(clp); @@ -1364,15 +1362,13 @@ static int nfs4_init_client_minor_version(struct nfs_client *clp) * @timeparms: timeout parameters for underlying RPC transport * @ip_addr: callback IP address in presentation format * @authflavor: authentication flavor for underlying RPC transport - * @noresvport: set if RPC transport can use an ephemeral source port * * Returns pointer to an NFS client, or an ERR_PTR value. */ struct nfs_client *nfs4_init_client(struct nfs_client *clp, const struct rpc_timeout *timeparms, const char *ip_addr, - rpc_authflavor_t authflavour, - int noresvport) + rpc_authflavor_t authflavour) { char buf[INET6_ADDRSTRLEN + 1]; int error; @@ -1386,8 +1382,8 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp, /* Check NFS protocol revision and initialize RPC op vector */ clp->rpc_ops = &nfs_v4_clientops; - error = nfs_create_rpc_client(clp, timeparms, authflavour, - 1, noresvport); + __set_bit(NFS_CS_DISCRTRY, &clp->cl_flags); + error = nfs_create_rpc_client(clp, timeparms, authflavour); if (error < 0) goto error; @@ -1455,9 +1451,11 @@ static int nfs4_set_client(struct nfs_server *server, dprintk("--> nfs4_set_client()\n"); + if (server->flags & NFS_MOUNT_NORESVPORT) + set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags); + /* Allocate or find a client reference we can use */ - clp = nfs_get_client(&cl_init, timeparms, ip_addr, authflavour, - server->flags & NFS_MOUNT_NORESVPORT); + clp = nfs_get_client(&cl_init, timeparms, ip_addr, authflavour); if (IS_ERR(clp)) { error = PTR_ERR(clp); goto error; @@ -1512,7 +1510,7 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp, */ nfs_init_timeout_values(&ds_timeout, ds_proto, ds_timeo, ds_retrans); clp = nfs_get_client(&cl_init, &ds_timeout, mds_clp->cl_ipaddr, - mds_clp->cl_rpcclient->cl_auth->au_flavor, 0); + mds_clp->cl_rpcclient->cl_auth->au_flavor); dprintk("<-- %s %p\n", __func__, clp); return clp; diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 3a9e80c9524b..547f24f17d16 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -240,8 +240,7 @@ extern int nfs4_init_ds_session(struct nfs_client *clp); void nfs_close_context(struct nfs_open_context *ctx, int is_sync); extern struct nfs_client *nfs_init_client(struct nfs_client *clp, const struct rpc_timeout *timeparms, - const char *ip_addr, rpc_authflavor_t authflavour, - int noresvport); + const char *ip_addr, rpc_authflavor_t authflavour); /* dir.c */ extern int nfs_access_cache_shrinker(struct shrinker *shrink, @@ -376,8 +375,7 @@ extern void __nfs4_read_done_cb(struct nfs_read_data *); extern struct nfs_client *nfs4_init_client(struct nfs_client *clp, const struct rpc_timeout *timeparms, const char *ip_addr, - rpc_authflavor_t authflavour, - int noresvport); + rpc_authflavor_t authflavour); extern int _nfs4_call_sync(struct rpc_clnt *clnt, struct nfs_server *server, struct rpc_message *msg, diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index fbec57d6dc0a..3a99f5252340 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -35,6 +35,9 @@ struct nfs_client { #define NFS_CS_RENEWD 3 /* - renewd started */ #define NFS_CS_STOP_RENEW 4 /* no more state to renew */ #define NFS_CS_CHECK_LEASE_TIME 5 /* need to check lease time */ + unsigned long cl_flags; /* behavior switches */ +#define NFS_CS_NORESVPORT 0 /* - use ephemeral src port */ +#define NFS_CS_DISCRTRY 1 /* - disconnect on RPC retry */ struct sockaddr_storage cl_addr; /* server identifier */ size_t cl_addrlen; char * cl_hostname; /* hostname of server */ diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 0c521cd496a7..07048c012dec 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1399,7 +1399,7 @@ struct nfs_rpc_ops { struct iattr *iattr); struct nfs_client * (*init_client) (struct nfs_client *, const struct rpc_timeout *, - const char *, rpc_authflavor_t, int); + const char *, rpc_authflavor_t); }; /* -- cgit v1.2.3 From acdeb69d9c5934a678a732b4e24770326bf9471e Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 21 May 2012 22:46:16 -0400 Subject: NFS: EXCHANGE_ID should save the server major and minor ID Save the server major and minor ID results from EXCHANGE_ID, as they are needed for detecting server trunking. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- fs/nfs/client.c | 1 + fs/nfs/nfs4proc.c | 17 ++++++++++++++++- fs/nfs/nfs4xdr.c | 13 ++++++++----- include/linux/nfs_fs_sb.h | 1 + include/linux/nfs_xdr.h | 3 ++- 5 files changed, 28 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 34b2e68c5249..3c144689f9e4 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -237,6 +237,7 @@ static void nfs4_shutdown_client(struct nfs_client *clp) nfs_idmap_delete(clp); rpc_destroy_wait_queue(&clp->cl_rpcwaitq); + kfree(clp->cl_serverowner); kfree(clp->cl_serverscope); kfree(clp->cl_implid); } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 9e9334a172cf..0d46fe449f0b 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5109,11 +5109,18 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred) clp->cl_rpcclient->cl_nodename, clp->cl_rpcclient->cl_auth->au_flavor); + res.server_owner = kzalloc(sizeof(struct nfs41_server_owner), + GFP_KERNEL); + if (unlikely(res.server_owner == NULL)) { + status = -ENOMEM; + goto out; + } + res.server_scope = kzalloc(sizeof(struct nfs41_server_scope), GFP_KERNEL); if (unlikely(res.server_scope == NULL)) { status = -ENOMEM; - goto out; + goto out_server_owner; } res.impl_id = kzalloc(sizeof(struct nfs41_impl_id), GFP_KERNEL); @@ -5126,6 +5133,12 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred) if (status == 0) status = nfs4_check_cl_exchange_flags(clp->cl_exchange_flags); + if (status == 0) { + kfree(clp->cl_serverowner); + clp->cl_serverowner = res.server_owner; + res.server_owner = NULL; + } + if (status == 0) { /* use the most recent implementation id */ kfree(clp->cl_implid); @@ -5150,6 +5163,8 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred) } } +out_server_owner: + kfree(res.server_owner); out_server_scope: kfree(res.server_scope); out: diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 12b99825a1c1..5ad2b2c2aecb 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -5144,24 +5144,27 @@ static int decode_exchange_id(struct xdr_stream *xdr, if (dummy != SP4_NONE) return -EIO; - /* Throw away minor_id */ + /* server_owner4.so_minor_id */ p = xdr_inline_decode(xdr, 8); if (unlikely(!p)) goto out_overflow; + p = xdr_decode_hyper(p, &res->server_owner->minor_id); - /* Throw away Major id */ + /* server_owner4.so_major_id */ status = decode_opaque_inline(xdr, &dummy, &dummy_str); if (unlikely(status)) return status; + if (unlikely(dummy > NFS4_OPAQUE_LIMIT)) + return -EIO; + memcpy(res->server_owner->major_id, dummy_str, dummy); + res->server_owner->major_id_sz = dummy; - /* Save server_scope */ + /* server_scope4 */ status = decode_opaque_inline(xdr, &dummy, &dummy_str); if (unlikely(status)) return status; - if (unlikely(dummy > NFS4_OPAQUE_LIMIT)) return -EIO; - memcpy(res->server_scope->server_scope, dummy_str, dummy); res->server_scope->server_scope_sz = dummy; diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 3a99f5252340..fbb78fb09bd2 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -80,6 +80,7 @@ struct nfs_client { /* The flags used for obtaining the clientid during EXCHANGE_ID */ u32 cl_exchange_flags; struct nfs4_session *cl_session; /* shared session */ + struct nfs41_server_owner *cl_serverowner; struct nfs41_server_scope *cl_serverscope; struct nfs41_impl_id *cl_implid; #endif /* CONFIG_NFS_V4 */ diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 07048c012dec..0872f32c8eef 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1098,7 +1098,7 @@ struct nfs41_exchange_id_args { u32 flags; }; -struct server_owner { +struct nfs41_server_owner { uint64_t minor_id; uint32_t major_id_sz; char major_id[NFS4_OPAQUE_LIMIT]; @@ -1118,6 +1118,7 @@ struct nfs41_impl_id { struct nfs41_exchange_id_res { struct nfs_client *client; u32 flags; + struct nfs41_server_owner *server_owner; struct nfs41_server_scope *server_scope; struct nfs41_impl_id *impl_id; }; -- cgit v1.2.3 From 88034c3d88c2c48b215f2cc5eb22e564aa817f9c Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Wed, 23 May 2012 05:02:34 -0400 Subject: NFSv4.1 mdsthreshold attribute xdr We only support one layout type per file system, so one threshold_item4 per mdsthreshold4. Signed-off-by: Andy Adamson Signed-off-by: Trond Myklebust --- fs/nfs/nfs4xdr.c | 125 +++++++++++++++++++++++++++++++++++++++++++++++- include/linux/nfs4.h | 7 +++ include/linux/nfs_xdr.h | 10 ++++ 3 files changed, 140 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 5ad2b2c2aecb..edb8ac7fce0e 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -101,9 +101,12 @@ static int nfs4_stat_to_errno(int); #define nfs4_path_maxsz (1 + ((3 + NFS4_MAXPATHLEN) >> 2)) #define nfs4_owner_maxsz (1 + XDR_QUADLEN(IDMAP_NAMESZ)) #define nfs4_group_maxsz (1 + XDR_QUADLEN(IDMAP_NAMESZ)) +/* We support only one layout type per file system */ +#define decode_mdsthreshold_maxsz (1 + 1 + nfs4_fattr_bitmap_maxsz + 1 + 8) /* This is based on getfattr, which uses the most attributes: */ #define nfs4_fattr_value_maxsz (1 + (1 + 2 + 2 + 4 + 2 + 1 + 1 + 2 + 2 + \ - 3 + 3 + 3 + nfs4_owner_maxsz + nfs4_group_maxsz)) + 3 + 3 + 3 + nfs4_owner_maxsz + \ + nfs4_group_maxsz + decode_mdsthreshold_maxsz)) #define nfs4_fattr_maxsz (nfs4_fattr_bitmap_maxsz + \ nfs4_fattr_value_maxsz) #define decode_getattr_maxsz (op_decode_hdr_maxsz + nfs4_fattr_maxsz) @@ -1172,6 +1175,16 @@ static void encode_getfattr(struct xdr_stream *xdr, const u32* bitmask, struct c bitmask[1] & nfs4_fattr_bitmap[1], hdr); } +static void encode_getfattr_open(struct xdr_stream *xdr, const u32 *bitmask, + struct compound_hdr *hdr) +{ + encode_getattr_three(xdr, + bitmask[0] & nfs4_fattr_bitmap[0], + bitmask[1] & nfs4_fattr_bitmap[1], + bitmask[2] & FATTR4_WORD2_MDSTHRESHOLD, + hdr); +} + static void encode_fsinfo(struct xdr_stream *xdr, const u32* bitmask, struct compound_hdr *hdr) { encode_getattr_three(xdr, @@ -2164,7 +2177,7 @@ static void nfs4_xdr_enc_open(struct rpc_rqst *req, struct xdr_stream *xdr, encode_putfh(xdr, args->fh, &hdr); encode_open(xdr, args, &hdr); encode_getfh(xdr, &hdr); - encode_getfattr(xdr, args->bitmask, &hdr); + encode_getfattr_open(xdr, args->bitmask, &hdr); encode_nops(&hdr); } @@ -4186,6 +4199,110 @@ xdr_error: return status; } +static int decode_threshold_hint(struct xdr_stream *xdr, + uint32_t *bitmap, + uint64_t *res, + uint32_t hint_bit) +{ + __be32 *p; + + *res = 0; + if (likely(bitmap[0] & hint_bit)) { + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + xdr_decode_hyper(p, res); + } + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_first_threshold_item4(struct xdr_stream *xdr, + struct nfs4_threshold *res) +{ + __be32 *p, *savep; + uint32_t bitmap[3] = {0,}, attrlen; + int status; + + /* layout type */ + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) { + print_overflow_msg(__func__, xdr); + return -EIO; + } + res->l_type = be32_to_cpup(p); + + /* thi_hintset bitmap */ + status = decode_attr_bitmap(xdr, bitmap); + if (status < 0) + goto xdr_error; + + /* thi_hintlist length */ + status = decode_attr_length(xdr, &attrlen, &savep); + if (status < 0) + goto xdr_error; + /* thi_hintlist */ + status = decode_threshold_hint(xdr, bitmap, &res->rd_sz, THRESHOLD_RD); + if (status < 0) + goto xdr_error; + status = decode_threshold_hint(xdr, bitmap, &res->wr_sz, THRESHOLD_WR); + if (status < 0) + goto xdr_error; + status = decode_threshold_hint(xdr, bitmap, &res->rd_io_sz, + THRESHOLD_RD_IO); + if (status < 0) + goto xdr_error; + status = decode_threshold_hint(xdr, bitmap, &res->wr_io_sz, + THRESHOLD_WR_IO); + if (status < 0) + goto xdr_error; + + status = verify_attr_len(xdr, savep, attrlen); + res->bm = bitmap[0]; + + dprintk("%s bm=0x%x rd_sz=%llu wr_sz=%llu rd_io=%llu wr_io=%llu\n", + __func__, res->bm, res->rd_sz, res->wr_sz, res->rd_io_sz, + res->wr_io_sz); +xdr_error: + dprintk("%s ret=%d!\n", __func__, status); + return status; +} + +/* + * Thresholds on pNFS direct I/O vrs MDS I/O + */ +static int decode_attr_mdsthreshold(struct xdr_stream *xdr, + uint32_t *bitmap, + struct nfs4_threshold *res) +{ + __be32 *p; + int status = 0; + uint32_t num; + + if (unlikely(bitmap[2] & (FATTR4_WORD2_MDSTHRESHOLD - 1U))) + return -EIO; + if (likely(bitmap[2] & FATTR4_WORD2_MDSTHRESHOLD)) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + num = be32_to_cpup(p); + if (num == 0) + return 0; + if (num > 1) + printk(KERN_INFO "%s: Warning: Multiple pNFS layout " + "drivers per filesystem not supported\n", + __func__); + + status = decode_first_threshold_item4(xdr, res); + } + return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_fattr *fattr, struct nfs_fh *fh, struct nfs4_fs_locations *fs_loc, @@ -4292,6 +4409,10 @@ static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap, goto xdr_error; fattr->valid |= status; + status = decode_attr_mdsthreshold(xdr, bitmap, fattr->mdsthreshold); + if (status < 0) + goto xdr_error; + xdr_error: dprintk("%s: xdr returned %d\n", __func__, -status); return status; diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 0987146b0637..72b6bada0d79 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -526,6 +526,13 @@ enum lock_type4 { #define FATTR4_WORD1_MOUNTED_ON_FILEID (1UL << 23) #define FATTR4_WORD1_FS_LAYOUT_TYPES (1UL << 30) #define FATTR4_WORD2_LAYOUT_BLKSIZE (1UL << 1) +#define FATTR4_WORD2_MDSTHRESHOLD (1UL << 4) + +/* MDS threshold bitmap bits */ +#define THRESHOLD_RD (1UL << 0) +#define THRESHOLD_WR (1UL << 1) +#define THRESHOLD_RD_IO (1UL << 2) +#define THRESHOLD_WR_IO (1UL << 3) #define NFSPROC4_NULL 0 #define NFSPROC4_COMPOUND 1 diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 0872f32c8eef..201c312152fb 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -35,6 +35,15 @@ static inline int nfs_fsid_equal(const struct nfs_fsid *a, const struct nfs_fsid return a->major == b->major && a->minor == b->minor; } +struct nfs4_threshold { + __u32 bm; + __u32 l_type; + __u64 rd_sz; + __u64 wr_sz; + __u64 rd_io_sz; + __u64 wr_io_sz; +}; + struct nfs_fattr { unsigned int valid; /* which fields are valid */ umode_t mode; @@ -67,6 +76,7 @@ struct nfs_fattr { unsigned long gencount; struct nfs4_string *owner_name; struct nfs4_string *group_name; + struct nfs4_threshold *mdsthreshold; /* pNFS threshold hints */ }; #define NFS_ATTR_FATTR_TYPE (1U << 0) -- cgit v1.2.3 From 82be417aa37c05116e310b0f2171187ea389f89b Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Wed, 23 May 2012 05:02:35 -0400 Subject: NFSv4.1 cache mdsthreshold values on OPEN Signed-off-by: Andy Adamson Signed-off-by: Trond Myklebust --- fs/nfs/inode.c | 2 ++ fs/nfs/nfs4proc.c | 38 +++++++++++++++++++++++++++++++++----- fs/nfs/pnfs.c | 12 ++++++++++++ fs/nfs/pnfs.h | 21 +++++++++++++++++++++ include/linux/nfs_fs.h | 1 + 5 files changed, 69 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 9ad81ce0c40f..889f7e5e92e1 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -641,6 +641,7 @@ struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry, fmode_t f nfs_init_lock_context(&ctx->lock_context); ctx->lock_context.open_context = ctx; INIT_LIST_HEAD(&ctx->list); + ctx->mdsthreshold = NULL; return ctx; } @@ -669,6 +670,7 @@ static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync) put_rpccred(ctx->cred); dput(ctx->dentry); nfs_sb_deactive(sb); + kfree(ctx->mdsthreshold); kfree(ctx); } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 8f39bb3ca1b3..e725736ff288 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1782,7 +1782,14 @@ static inline void nfs4_exclusive_attrset(struct nfs4_opendata *opendata, struct /* * Returns a referenced nfs4_state */ -static int _nfs4_do_open(struct inode *dir, struct dentry *dentry, fmode_t fmode, int flags, struct iattr *sattr, struct rpc_cred *cred, struct nfs4_state **res) +static int _nfs4_do_open(struct inode *dir, + struct dentry *dentry, + fmode_t fmode, + int flags, + struct iattr *sattr, + struct rpc_cred *cred, + struct nfs4_state **res, + struct nfs4_threshold **ctx_th) { struct nfs4_state_owner *sp; struct nfs4_state *state = NULL; @@ -1807,6 +1814,11 @@ static int _nfs4_do_open(struct inode *dir, struct dentry *dentry, fmode_t fmode if (opendata == NULL) goto err_put_state_owner; + if (ctx_th && server->attr_bitmask[2] & FATTR4_WORD2_MDSTHRESHOLD) { + opendata->f_attr.mdsthreshold = pnfs_mdsthreshold_alloc(); + if (!opendata->f_attr.mdsthreshold) + goto err_opendata_put; + } if (dentry->d_inode != NULL) opendata->state = nfs4_get_open_state(dentry->d_inode, sp); @@ -1832,11 +1844,19 @@ static int _nfs4_do_open(struct inode *dir, struct dentry *dentry, fmode_t fmode nfs_setattr_update_inode(state->inode, sattr); nfs_post_op_update_inode(state->inode, opendata->o_res.f_attr); } + + if (pnfs_use_threshold(ctx_th, opendata->f_attr.mdsthreshold, server)) + *ctx_th = opendata->f_attr.mdsthreshold; + else + kfree(opendata->f_attr.mdsthreshold); + opendata->f_attr.mdsthreshold = NULL; + nfs4_opendata_put(opendata); nfs4_put_state_owner(sp); *res = state; return 0; err_opendata_put: + kfree(opendata->f_attr.mdsthreshold); nfs4_opendata_put(opendata); err_put_state_owner: nfs4_put_state_owner(sp); @@ -1846,14 +1866,21 @@ out_err: } -static struct nfs4_state *nfs4_do_open(struct inode *dir, struct dentry *dentry, fmode_t fmode, int flags, struct iattr *sattr, struct rpc_cred *cred) +static struct nfs4_state *nfs4_do_open(struct inode *dir, + struct dentry *dentry, + fmode_t fmode, + int flags, + struct iattr *sattr, + struct rpc_cred *cred, + struct nfs4_threshold **ctx_th) { struct nfs4_exception exception = { }; struct nfs4_state *res; int status; do { - status = _nfs4_do_open(dir, dentry, fmode, flags, sattr, cred, &res); + status = _nfs4_do_open(dir, dentry, fmode, flags, sattr, cred, + &res, ctx_th); if (status == 0) break; /* NOTE: BAD_SEQID means the server and client disagree about the @@ -2177,7 +2204,8 @@ nfs4_atomic_open(struct inode *dir, struct nfs_open_context *ctx, int open_flags struct nfs4_state *state; /* Protect against concurrent sillydeletes */ - state = nfs4_do_open(dir, ctx->dentry, ctx->mode, open_flags, attr, ctx->cred); + state = nfs4_do_open(dir, ctx->dentry, ctx->mode, open_flags, attr, + ctx->cred, &ctx->mdsthreshold); if (IS_ERR(state)) return ERR_CAST(state); ctx->state = state; @@ -2779,7 +2807,7 @@ nfs4_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, fmode = ctx->mode; } sattr->ia_mode &= ~current_umask(); - state = nfs4_do_open(dir, de, fmode, flags, sattr, cred); + state = nfs4_do_open(dir, de, fmode, flags, sattr, cred, NULL); d_drop(dentry); if (IS_ERR(state)) { status = PTR_ERR(state); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 5d09a36b2cd8..cbcb6aea58a3 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1630,3 +1630,15 @@ out_free: kfree(data); goto out; } + +struct nfs4_threshold *pnfs_mdsthreshold_alloc(void) +{ + struct nfs4_threshold *thp; + + thp = kzalloc(sizeof(*thp), GFP_NOFS); + if (!thp) { + dprintk("%s mdsthreshold allocation failed\n", __func__); + return NULL; + } + return thp; +} diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 7980756b2f57..29fd23c0efdc 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -227,6 +227,7 @@ int pnfs_read_done_resend_to_mds(struct inode *inode, struct list_head *head, const struct nfs_pgio_completion_ops *compl_ops); int pnfs_write_done_resend_to_mds(struct inode *inode, struct list_head *head, const struct nfs_pgio_completion_ops *compl_ops); +struct nfs4_threshold *pnfs_mdsthreshold_alloc(void); /* nfs4_deviceid_flags */ enum { @@ -360,6 +361,14 @@ static inline int pnfs_return_layout(struct inode *ino) return 0; } +static inline bool +pnfs_use_threshold(struct nfs4_threshold **dst, struct nfs4_threshold *src, + struct nfs_server *nfss) +{ + return (dst && src && src->bm != 0 && + nfss->pnfs_curr_ld->id == src->l_type); +} + #ifdef NFS_DEBUG void nfs4_print_deviceid(const struct nfs4_deviceid *dev_id); #else @@ -485,6 +494,18 @@ static inline int pnfs_layoutcommit_inode(struct inode *inode, bool sync) return 0; } +static inline bool +pnfs_use_threshold(struct nfs4_threshold **dst, struct nfs4_threshold *src, + struct nfs_server *nfss) +{ + return false; +} + +static inline struct nfs4_threshold *pnfs_mdsthreshold_alloc(void) +{ + return NULL; +} + #endif /* CONFIG_NFS_V4_1 */ #endif /* FS_NFS_PNFS_H */ diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 80a9385b88ab..ce910cb7d761 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -102,6 +102,7 @@ struct nfs_open_context { int error; struct list_head list; + struct nfs4_threshold *mdsthreshold; }; struct nfs_open_dir_context { -- cgit v1.2.3 From 2701d086dbfca03b2d28b25c6dc11dd78d0e26ad Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Thu, 24 May 2012 13:13:24 -0400 Subject: NFSv4.1 add nfs_inode book keeping for mdsthreshold Keep track of the number of bytes read or written via buffered, direct, and mem-mapped i/o for use by mdsthreshold size_io hints. Signed-off-by: Andy Adamson Signed-off-by: Trond Myklebust --- fs/nfs/direct.c | 2 ++ fs/nfs/file.c | 1 + fs/nfs/inode.c | 2 ++ fs/nfs/pnfs.c | 3 +++ fs/nfs/read.c | 2 ++ include/linux/nfs_fs.h | 3 +++ 6 files changed, 13 insertions(+) (limited to 'include') diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index c47a46eaf905..23d170bc44f4 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -447,6 +447,7 @@ static ssize_t nfs_direct_read(struct kiocb *iocb, const struct iovec *iov, result = nfs_direct_read_schedule_iovec(dreq, iov, nr_segs, pos); if (!result) result = nfs_direct_wait(dreq); + NFS_I(inode)->read_io += result; out_release: nfs_direct_req_release(dreq); out: @@ -785,6 +786,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, pos += vec->iov_len; } nfs_pageio_complete(&desc); + NFS_I(dreq->inode)->write_io += desc.pg_bytes_written; /* * If no bytes were started, return the error, and let the diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 8eda8a6644c3..56311ca5f9f8 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -424,6 +424,7 @@ static int nfs_write_end(struct file *file, struct address_space *mapping, if (status < 0) return status; + NFS_I(mapping->host)->write_io += copied; return copied; } diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 889f7e5e92e1..a6f5fbbe9b9c 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -323,6 +323,8 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) inode->i_gid = -2; inode->i_blocks = 0; memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf)); + nfsi->write_io = 0; + nfsi->read_io = 0; nfsi->read_cache_jiffies = fattr->time_start; nfsi->attr_gencount = fattr->gencount; diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index cbcb6aea58a3..6620606f2687 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -395,6 +395,9 @@ mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo, dprintk("%s:Begin lo %p\n", __func__, lo); if (list_empty(&lo->plh_segs)) { + /* Reset MDS Threshold I/O counters */ + NFS_I(lo->plh_inode)->write_io = 0; + NFS_I(lo->plh_inode)->read_io = 0; if (!test_and_set_bit(NFS_LAYOUT_DESTROYED, &lo->plh_flags)) put_layout_hdr_locked(lo); return 0; diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 2cfdd7785411..86ced7836214 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -152,6 +152,7 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode, nfs_pageio_init_read(&pgio, inode, &nfs_async_read_completion_ops); nfs_pageio_add_request(&pgio, new); nfs_pageio_complete(&pgio); + NFS_I(inode)->read_io += pgio.pg_bytes_written; return 0; } @@ -656,6 +657,7 @@ int nfs_readpages(struct file *filp, struct address_space *mapping, ret = read_cache_pages(mapping, pages, readpage_async_filler, &desc); nfs_pageio_complete(&pgio); + NFS_I(inode)->read_io += pgio.pg_bytes_written; npages = (pgio.pg_bytes_written + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; nfs_add_stats(inode, NFSIOS_READPAGES, npages); read_complete: diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index ce910cb7d761..b23cfc120edb 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -202,6 +202,9 @@ struct nfs_inode { /* pNFS layout information */ struct pnfs_layout_hdr *layout; #endif /* CONFIG_NFS_V4*/ + /* how many bytes have been written/read and how many bytes queued up */ + __u64 write_io; + __u64 read_io; #ifdef CONFIG_NFS_FSCACHE struct fscache_cookie *fscache; #endif -- cgit v1.2.3 From 7c44f1ae4a21458a1ea3d6482ffb3136f1df6d2b Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Thu, 24 May 2012 13:22:50 -0400 Subject: nfs4.1: add BIND_CONN_TO_SESSION operation This patch adds the BIND_CONN_TO_SESSION operation which is needed for upcoming SP4_MACH_CRED work and useful for recovering from broken connections without destroying the session. Signed-off-by: Weston Andros Adamson Signed-off-by: Trond Myklebust --- fs/nfs/nfs4_fs.h | 1 + fs/nfs/nfs4proc.c | 54 ++++++++++++++++++++++++++++ fs/nfs/nfs4xdr.c | 95 +++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/nfs4.h | 5 +++ include/linux/nfs_xdr.h | 6 ++++ 5 files changed, 161 insertions(+) (limited to 'include') diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index e6da02124c4e..2c7f1cf85b8f 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -211,6 +211,7 @@ struct vfsmount *nfs4_submount(struct nfs_server *, struct dentry *, extern int nfs4_proc_setclientid(struct nfs_client *, u32, unsigned short, struct rpc_cred *, struct nfs4_setclientid_res *); extern int nfs4_proc_setclientid_confirm(struct nfs_client *, struct nfs4_setclientid_res *arg, struct rpc_cred *); extern int nfs4_proc_get_rootfh(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *); +extern int nfs4_proc_bind_conn_to_session(struct nfs_client *); extern int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred); extern int nfs4_init_clientid(struct nfs_client *, struct rpc_cred *); extern int nfs41_init_clientid(struct nfs_client *, struct rpc_cred *); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index e725736ff288..e8988c000e7f 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5099,6 +5099,60 @@ nfs41_same_server_scope(struct nfs41_server_scope *a, return false; } +/* + * nfs4_proc_bind_conn_to_session() + * + * The 4.1 client currently uses the same TCP connection for the + * fore and backchannel. + */ +int nfs4_proc_bind_conn_to_session(struct nfs_client *clp) +{ + int status; + struct nfs41_bind_conn_to_session_res res; + struct rpc_message msg = { + .rpc_proc = + &nfs4_procedures[NFSPROC4_CLNT_BIND_CONN_TO_SESSION], + .rpc_argp = clp, + .rpc_resp = &res, + }; + + dprintk("--> %s\n", __func__); + BUG_ON(clp == NULL); + + res.session = kzalloc(sizeof(struct nfs4_session), GFP_NOFS); + if (unlikely(res.session == NULL)) { + status = -ENOMEM; + goto out; + } + + status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT); + if (status == 0) { + if (memcmp(res.session->sess_id.data, + clp->cl_session->sess_id.data, NFS4_MAX_SESSIONID_LEN)) { + dprintk("NFS: %s: Session ID mismatch\n", __func__); + status = -EIO; + goto out_session; + } + if (res.dir != NFS4_CDFS4_BOTH) { + dprintk("NFS: %s: Unexpected direction from server\n", + __func__); + status = -EIO; + goto out_session; + } + if (res.use_conn_in_rdma_mode) { + dprintk("NFS: %s: Server returned RDMA mode = true\n", + __func__); + status = -EIO; + goto out_session; + } + } +out_session: + kfree(res.session); +out: + dprintk("<-- %s status= %d\n", __func__, status); + return status; +} + /* * nfs4_proc_exchange_id() * diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index edb8ac7fce0e..a6b95b766220 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -326,6 +326,16 @@ static int nfs4_stat_to_errno(int); 1 /* csr_flags */ + \ decode_channel_attrs_maxsz + \ decode_channel_attrs_maxsz) +#define encode_bind_conn_to_session_maxsz (op_encode_hdr_maxsz + \ + /* bctsa_sessid */ \ + XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + \ + 1 /* bctsa_dir */ + \ + 1 /* bctsa_use_conn_in_rdma_mode */) +#define decode_bind_conn_to_session_maxsz (op_decode_hdr_maxsz + \ + /* bctsr_sessid */ \ + XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + \ + 1 /* bctsr_dir */ + \ + 1 /* bctsr_use_conn_in_rdma_mode */) #define encode_destroy_session_maxsz (op_encode_hdr_maxsz + 4) #define decode_destroy_session_maxsz (op_decode_hdr_maxsz) #define encode_sequence_maxsz (op_encode_hdr_maxsz + \ @@ -719,6 +729,12 @@ static int nfs4_stat_to_errno(int); decode_putfh_maxsz + \ decode_secinfo_maxsz) #if defined(CONFIG_NFS_V4_1) +#define NFS4_enc_bind_conn_to_session_sz \ + (compound_encode_hdr_maxsz + \ + encode_bind_conn_to_session_maxsz) +#define NFS4_dec_bind_conn_to_session_sz \ + (compound_decode_hdr_maxsz + \ + decode_bind_conn_to_session_maxsz) #define NFS4_enc_exchange_id_sz \ (compound_encode_hdr_maxsz + \ encode_exchange_id_maxsz) @@ -1669,6 +1685,20 @@ static void encode_secinfo(struct xdr_stream *xdr, const struct qstr *name, stru #if defined(CONFIG_NFS_V4_1) /* NFSv4.1 operations */ +static void encode_bind_conn_to_session(struct xdr_stream *xdr, + struct nfs4_session *session, + struct compound_hdr *hdr) +{ + __be32 *p; + + encode_op_hdr(xdr, OP_BIND_CONN_TO_SESSION, + decode_bind_conn_to_session_maxsz, hdr); + encode_opaque_fixed(xdr, session->sess_id.data, NFS4_MAX_SESSIONID_LEN); + p = xdr_reserve_space(xdr, 8); + *p++ = cpu_to_be32(NFS4_CDFC4_BACK_OR_BOTH); + *p = 0; /* use_conn_in_rdma_mode = False */ +} + static void encode_exchange_id(struct xdr_stream *xdr, struct nfs41_exchange_id_args *args, struct compound_hdr *hdr) @@ -2629,6 +2659,22 @@ static void nfs4_xdr_enc_secinfo(struct rpc_rqst *req, } #if defined(CONFIG_NFS_V4_1) +/* + * BIND_CONN_TO_SESSION request + */ +static void nfs4_xdr_enc_bind_conn_to_session(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs_client *clp) +{ + struct compound_hdr hdr = { + .minorversion = clp->cl_mvops->minor_version, + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_bind_conn_to_session(xdr, clp->cl_session, &hdr); + encode_nops(&hdr); +} + /* * EXCHANGE_ID request */ @@ -5366,6 +5412,37 @@ static int decode_sessionid(struct xdr_stream *xdr, struct nfs4_sessionid *sid) return decode_opaque_fixed(xdr, sid->data, NFS4_MAX_SESSIONID_LEN); } +static int decode_bind_conn_to_session(struct xdr_stream *xdr, + struct nfs41_bind_conn_to_session_res *res) +{ + __be32 *p; + int status; + + status = decode_op_hdr(xdr, OP_BIND_CONN_TO_SESSION); + if (!status) + status = decode_sessionid(xdr, &res->session->sess_id); + if (unlikely(status)) + return status; + + /* dir flags, rdma mode bool */ + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + + res->dir = be32_to_cpup(p++); + if (res->dir == 0 || res->dir > NFS4_CDFS4_BOTH) + return -EIO; + if (be32_to_cpup(p) == 0) + res->use_conn_in_rdma_mode = false; + else + res->use_conn_in_rdma_mode = true; + + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + static int decode_create_session(struct xdr_stream *xdr, struct nfs41_create_session_res *res) { @@ -6647,6 +6724,22 @@ out: } #if defined(CONFIG_NFS_V4_1) +/* + * Decode BIND_CONN_TO_SESSION response + */ +static int nfs4_xdr_dec_bind_conn_to_session(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + void *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (!status) + status = decode_bind_conn_to_session(xdr, res); + return status; +} + /* * Decode EXCHANGE_ID response */ @@ -7128,6 +7221,8 @@ struct rpc_procinfo nfs4_procedures[] = { PROC(RELEASE_LOCKOWNER, enc_release_lockowner, dec_release_lockowner), PROC(SECINFO, enc_secinfo, dec_secinfo), #if defined(CONFIG_NFS_V4_1) + PROC(BIND_CONN_TO_SESSION, + enc_bind_conn_to_session, dec_bind_conn_to_session), PROC(EXCHANGE_ID, enc_exchange_id, dec_exchange_id), PROC(CREATE_SESSION, enc_create_session, dec_create_session), PROC(DESTROY_SESSION, enc_destroy_session, dec_destroy_session), diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 72b6bada0d79..a2b71cbfc44a 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -69,6 +69,10 @@ #define NFS4_CDFC4_FORE_OR_BOTH 0x3 #define NFS4_CDFC4_BACK_OR_BOTH 0x7 +#define NFS4_CDFS4_FORE 0x1 +#define NFS4_CDFS4_BACK 0x2 +#define NFS4_CDFS4_BOTH 0x3 + #define NFS4_SET_TO_SERVER_TIME 0 #define NFS4_SET_TO_CLIENT_TIME 1 @@ -589,6 +593,7 @@ enum { NFSPROC4_CLNT_SECINFO, /* nfs41 */ + NFSPROC4_CLNT_BIND_CONN_TO_SESSION, NFSPROC4_CLNT_EXCHANGE_ID, NFSPROC4_CLNT_CREATE_SESSION, NFSPROC4_CLNT_DESTROY_SESSION, diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 201c312152fb..6387fc0097fe 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1125,6 +1125,12 @@ struct nfs41_impl_id { struct nfstime4 date; }; +struct nfs41_bind_conn_to_session_res { + struct nfs4_session *session; + u32 dir; + bool use_conn_in_rdma_mode; +}; + struct nfs41_exchange_id_res { struct nfs_client *client; u32 flags; -- cgit v1.2.3 From ad24ecfbcddfa88541bccc980e753aeda8bf4031 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 25 May 2012 17:11:42 -0400 Subject: NFSv4.1: Move NFSPROC4_CLNT_BIND_CONN_TO_SESSION to the end of the operations For backward compatibility with nfs-utils. Signed-off-by: Trond Myklebust Cc: Weston Andros Adamson --- fs/nfs/nfs4xdr.c | 4 ++-- include/linux/nfs4.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index a6b95b766220..1d4d259c5b3c 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -7221,8 +7221,6 @@ struct rpc_procinfo nfs4_procedures[] = { PROC(RELEASE_LOCKOWNER, enc_release_lockowner, dec_release_lockowner), PROC(SECINFO, enc_secinfo, dec_secinfo), #if defined(CONFIG_NFS_V4_1) - PROC(BIND_CONN_TO_SESSION, - enc_bind_conn_to_session, dec_bind_conn_to_session), PROC(EXCHANGE_ID, enc_exchange_id, dec_exchange_id), PROC(CREATE_SESSION, enc_create_session, dec_create_session), PROC(DESTROY_SESSION, enc_destroy_session, dec_destroy_session), @@ -7237,6 +7235,8 @@ struct rpc_procinfo nfs4_procedures[] = { PROC(TEST_STATEID, enc_test_stateid, dec_test_stateid), PROC(FREE_STATEID, enc_free_stateid, dec_free_stateid), PROC(GETDEVICELIST, enc_getdevicelist, dec_getdevicelist), + PROC(BIND_CONN_TO_SESSION, + enc_bind_conn_to_session, dec_bind_conn_to_session), #endif /* CONFIG_NFS_V4_1 */ }; diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index a2b71cbfc44a..54006a997dd0 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -593,7 +593,6 @@ enum { NFSPROC4_CLNT_SECINFO, /* nfs41 */ - NFSPROC4_CLNT_BIND_CONN_TO_SESSION, NFSPROC4_CLNT_EXCHANGE_ID, NFSPROC4_CLNT_CREATE_SESSION, NFSPROC4_CLNT_DESTROY_SESSION, @@ -608,6 +607,7 @@ enum { NFSPROC4_CLNT_TEST_STATEID, NFSPROC4_CLNT_FREE_STATEID, NFSPROC4_CLNT_GETDEVICELIST, + NFSPROC4_CLNT_BIND_CONN_TO_SESSION, }; /* nfs41 types */ -- cgit v1.2.3 From 662455391040a783b89d0232e743c27c23617dbd Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 25 May 2012 17:18:09 -0400 Subject: NFSv4.1: Add DESTROY_CLIENTID Ensure that we destroy our lease on last unmount Signed-off-by: Trond Myklebust --- fs/nfs/client.c | 1 + fs/nfs/nfs4_fs.h | 1 + fs/nfs/nfs4proc.c | 59 ++++++++++++++++++++++++++++++++++++++++++++++++++++ fs/nfs/nfs4xdr.c | 52 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/nfs4.h | 1 + 5 files changed, 114 insertions(+) (limited to 'include') diff --git a/fs/nfs/client.c b/fs/nfs/client.c index a50bdfbbc429..7d108753af81 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -209,6 +209,7 @@ static void nfs4_shutdown_session(struct nfs_client *clp) if (nfs4_has_session(clp)) { nfs4_deviceid_purge_client(clp); nfs4_destroy_session(clp->cl_session); + nfs4_destroy_clientid(clp); } } diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index f7307304320a..b20b5164f70a 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -214,6 +214,7 @@ extern int nfs4_proc_setclientid_confirm(struct nfs_client *, struct nfs4_setcli extern int nfs4_proc_get_rootfh(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *); extern int nfs4_proc_bind_conn_to_session(struct nfs_client *, struct rpc_cred *cred); extern int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred); +extern int nfs4_destroy_clientid(struct nfs_client *clp); extern int nfs4_init_clientid(struct nfs_client *, struct rpc_cred *); extern int nfs41_init_clientid(struct nfs_client *, struct rpc_cred *); extern int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait, bool roc); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 3fdff0cd558d..485a6c0cdc40 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5261,6 +5261,65 @@ out: return status; } +static int _nfs4_proc_destroy_clientid(struct nfs_client *clp, + struct rpc_cred *cred) +{ + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_DESTROY_CLIENTID], + .rpc_argp = clp, + .rpc_cred = cred, + }; + int status; + + status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT); + if (status) + pr_warn("NFS: Got error %d from the server %s on " + "DESTROY_CLIENTID.", status, clp->cl_hostname); + return status; +} + +static int nfs4_proc_destroy_clientid(struct nfs_client *clp, + struct rpc_cred *cred) +{ + unsigned int loop; + int ret; + + for (loop = NFS4_MAX_LOOP_ON_RECOVER; loop != 0; loop--) { + ret = _nfs4_proc_destroy_clientid(clp, cred); + switch (ret) { + case -NFS4ERR_DELAY: + case -NFS4ERR_CLIENTID_BUSY: + ssleep(1); + break; + default: + return ret; + } + } + return 0; +} + +int nfs4_destroy_clientid(struct nfs_client *clp) +{ + struct rpc_cred *cred; + int ret = 0; + + if (clp->cl_mvops->minor_version < 1) + goto out; + if (clp->cl_exchange_flags == 0) + goto out; + cred = nfs4_get_exchange_id_cred(clp); + ret = nfs4_proc_destroy_clientid(clp, cred); + if (cred) + put_rpccred(cred); + switch (ret) { + case 0: + case -NFS4ERR_STALE_CLIENTID: + clp->cl_exchange_flags = 0; + } +out: + return ret; +} + struct nfs4_get_lease_time_data { struct nfs4_get_lease_time_args *args; struct nfs4_get_lease_time_res *res; diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 1d4d259c5b3c..b9ce3fdb862a 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -338,6 +338,8 @@ static int nfs4_stat_to_errno(int); 1 /* bctsr_use_conn_in_rdma_mode */) #define encode_destroy_session_maxsz (op_encode_hdr_maxsz + 4) #define decode_destroy_session_maxsz (op_decode_hdr_maxsz) +#define encode_destroy_clientid_maxsz (op_encode_hdr_maxsz + 2) +#define decode_destroy_clientid_maxsz (op_decode_hdr_maxsz) #define encode_sequence_maxsz (op_encode_hdr_maxsz + \ XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + 4) #define decode_sequence_maxsz (op_decode_hdr_maxsz + \ @@ -751,6 +753,10 @@ static int nfs4_stat_to_errno(int); encode_destroy_session_maxsz) #define NFS4_dec_destroy_session_sz (compound_decode_hdr_maxsz + \ decode_destroy_session_maxsz) +#define NFS4_enc_destroy_clientid_sz (compound_encode_hdr_maxsz + \ + encode_destroy_clientid_maxsz) +#define NFS4_dec_destroy_clientid_sz (compound_decode_hdr_maxsz + \ + decode_destroy_clientid_maxsz) #define NFS4_enc_sequence_sz \ (compound_decode_hdr_maxsz + \ encode_sequence_maxsz) @@ -1804,6 +1810,14 @@ static void encode_destroy_session(struct xdr_stream *xdr, encode_opaque_fixed(xdr, session->sess_id.data, NFS4_MAX_SESSIONID_LEN); } +static void encode_destroy_clientid(struct xdr_stream *xdr, + uint64_t clientid, + struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_DESTROY_CLIENTID, decode_destroy_clientid_maxsz, hdr); + encode_uint64(xdr, clientid); +} + static void encode_reclaim_complete(struct xdr_stream *xdr, struct nfs41_reclaim_complete_args *args, struct compound_hdr *hdr) @@ -2723,6 +2737,22 @@ static void nfs4_xdr_enc_destroy_session(struct rpc_rqst *req, encode_nops(&hdr); } +/* + * a DESTROY_CLIENTID request + */ +static void nfs4_xdr_enc_destroy_clientid(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs_client *clp) +{ + struct compound_hdr hdr = { + .minorversion = clp->cl_mvops->minor_version, + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_destroy_clientid(xdr, clp->cl_clientid, &hdr); + encode_nops(&hdr); +} + /* * a SEQUENCE request */ @@ -5479,6 +5509,11 @@ static int decode_destroy_session(struct xdr_stream *xdr, void *dummy) return decode_op_hdr(xdr, OP_DESTROY_SESSION); } +static int decode_destroy_clientid(struct xdr_stream *xdr, void *dummy) +{ + return decode_op_hdr(xdr, OP_DESTROY_CLIENTID); +} + static int decode_reclaim_complete(struct xdr_stream *xdr, void *dummy) { return decode_op_hdr(xdr, OP_RECLAIM_COMPLETE); @@ -6788,6 +6823,22 @@ static int nfs4_xdr_dec_destroy_session(struct rpc_rqst *rqstp, return status; } +/* + * Decode DESTROY_CLIENTID response + */ +static int nfs4_xdr_dec_destroy_clientid(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + void *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (!status) + status = decode_destroy_clientid(xdr, res); + return status; +} + /* * Decode SEQUENCE response */ @@ -7237,6 +7288,7 @@ struct rpc_procinfo nfs4_procedures[] = { PROC(GETDEVICELIST, enc_getdevicelist, dec_getdevicelist), PROC(BIND_CONN_TO_SESSION, enc_bind_conn_to_session, dec_bind_conn_to_session), + PROC(DESTROY_CLIENTID, enc_destroy_clientid, dec_destroy_clientid), #endif /* CONFIG_NFS_V4_1 */ }; diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 54006a997dd0..af2d2fa30eee 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -608,6 +608,7 @@ enum { NFSPROC4_CLNT_FREE_STATEID, NFSPROC4_CLNT_GETDEVICELIST, NFSPROC4_CLNT_BIND_CONN_TO_SESSION, + NFSPROC4_CLNT_DESTROY_CLIENTID, }; /* nfs41 types */ -- cgit v1.2.3 From 32b0131069c5bebf52368a9fe170f8d58b78fa8d Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 26 May 2012 13:41:04 -0400 Subject: NFSv4.1: Don't clobber the seqid if exchange_id returns a confirmed clientid If the EXCHGID4_FLAG_CONFIRMED_R flag is set, the client is in theory supposed to already know the correct value of the seqid, in which case RFC5661 states that it should ignore the value returned. Also ensure that if the sanity check in nfs4_check_cl_exchange_flags fails, then we must not change the nfs_client fields. Finally, clean up the code: we don't need to retest the value of 'status' unless it can change. Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 17 +++++++++-------- fs/nfs/nfs4xdr.c | 7 +++---- include/linux/nfs_xdr.h | 3 ++- 3 files changed, 14 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 485a6c0cdc40..9f0a96fe6212 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5171,7 +5171,7 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred) .flags = EXCHGID4_FLAG_SUPP_MOVED_REFER, }; struct nfs41_exchange_id_res res = { - .client = clp, + 0 }; int status; struct rpc_message msg = { @@ -5214,22 +5214,22 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred) status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT); if (status == 0) - status = nfs4_check_cl_exchange_flags(clp->cl_exchange_flags); + status = nfs4_check_cl_exchange_flags(res.flags); if (status == 0) { + clp->cl_clientid = res.clientid; + clp->cl_exchange_flags = (res.flags & ~EXCHGID4_FLAG_CONFIRMED_R); + if (!(res.flags & EXCHGID4_FLAG_CONFIRMED_R)) + clp->cl_seqid = res.seqid; + kfree(clp->cl_serverowner); clp->cl_serverowner = res.server_owner; res.server_owner = NULL; - } - if (status == 0) { /* use the most recent implementation id */ kfree(clp->cl_implid); clp->cl_implid = res.impl_id; - } else - kfree(res.impl_id); - if (status == 0) { if (clp->cl_serverscope != NULL && !nfs41_same_server_scope(clp->cl_serverscope, res.server_scope)) { @@ -5244,7 +5244,8 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred) clp->cl_serverscope = res.server_scope; goto out; } - } + } else + kfree(res.impl_id); out_server_owner: kfree(res.server_owner); diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index b9ce3fdb862a..ee4a74db95d0 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -5319,7 +5319,6 @@ static int decode_exchange_id(struct xdr_stream *xdr, uint32_t dummy; char *dummy_str; int status; - struct nfs_client *clp = res->client; uint32_t impl_id_count; status = decode_op_hdr(xdr, OP_EXCHANGE_ID); @@ -5329,12 +5328,12 @@ static int decode_exchange_id(struct xdr_stream *xdr, p = xdr_inline_decode(xdr, 8); if (unlikely(!p)) goto out_overflow; - xdr_decode_hyper(p, &clp->cl_clientid); + xdr_decode_hyper(p, &res->clientid); p = xdr_inline_decode(xdr, 12); if (unlikely(!p)) goto out_overflow; - clp->cl_seqid = be32_to_cpup(p++); - clp->cl_exchange_flags = be32_to_cpup(p++); + res->seqid = be32_to_cpup(p++); + res->flags = be32_to_cpup(p++); /* We ask for SP4_NONE */ dummy = be32_to_cpup(p); diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 6387fc0097fe..d1a7bf51c326 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1132,7 +1132,8 @@ struct nfs41_bind_conn_to_session_res { }; struct nfs41_exchange_id_res { - struct nfs_client *client; + u64 clientid; + u32 seqid; u32 flags; struct nfs41_server_owner *server_owner; struct nfs41_server_scope *server_scope; -- cgit v1.2.3