diff options
Diffstat (limited to 'fs/nfs/blocklayout')
| -rw-r--r-- | fs/nfs/blocklayout/Makefile | 3 | ||||
| -rw-r--r-- | fs/nfs/blocklayout/blocklayout.c | 1386 | ||||
| -rw-r--r-- | fs/nfs/blocklayout/blocklayout.h | 213 | ||||
| -rw-r--r-- | fs/nfs/blocklayout/blocklayoutdev.c | 384 | ||||
| -rw-r--r-- | fs/nfs/blocklayout/blocklayoutdm.c | 108 | ||||
| -rw-r--r-- | fs/nfs/blocklayout/dev.c | 363 | ||||
| -rw-r--r-- | fs/nfs/blocklayout/extent_tree.c | 602 | ||||
| -rw-r--r-- | fs/nfs/blocklayout/extents.c | 908 | ||||
| -rw-r--r-- | fs/nfs/blocklayout/rpc_pipefs.c | 285 |
9 files changed, 1782 insertions, 2470 deletions
diff --git a/fs/nfs/blocklayout/Makefile b/fs/nfs/blocklayout/Makefile index d5815505c020..3ca14c36d08b 100644 --- a/fs/nfs/blocklayout/Makefile +++ b/fs/nfs/blocklayout/Makefile @@ -2,4 +2,5 @@ # Makefile for the pNFS block layout driver kernel module # obj-$(CONFIG_PNFS_BLOCK) += blocklayoutdriver.o -blocklayoutdriver-objs := blocklayout.o extents.o blocklayoutdev.o blocklayoutdm.o + +blocklayoutdriver-y += blocklayout.o dev.o extent_tree.o rpc_pipefs.o diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index cbb1797149d5..5228f201d3d5 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -35,7 +35,6 @@ #include <linux/mount.h> #include <linux/namei.h> #include <linux/bio.h> /* struct bio */ -#include <linux/buffer_head.h> /* various write calls */ #include <linux/prefetch.h> #include <linux/pagevec.h> @@ -50,40 +49,16 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Andy Adamson <andros@citi.umich.edu>"); MODULE_DESCRIPTION("The NFSv4.1 pNFS Block layout driver"); -static void print_page(struct page *page) +static bool is_hole(struct pnfs_block_extent *be) { - dprintk("PRINTPAGE page %p\n", page); - dprintk(" PagePrivate %d\n", PagePrivate(page)); - dprintk(" PageUptodate %d\n", PageUptodate(page)); - dprintk(" PageError %d\n", PageError(page)); - dprintk(" PageDirty %d\n", PageDirty(page)); - dprintk(" PageReferenced %d\n", PageReferenced(page)); - dprintk(" PageLocked %d\n", PageLocked(page)); - dprintk(" PageWriteback %d\n", PageWriteback(page)); - dprintk(" PageMappedToDisk %d\n", PageMappedToDisk(page)); - dprintk("\n"); -} - -/* Given the be associated with isect, determine if page data needs to be - * initialized. - */ -static int is_hole(struct pnfs_block_extent *be, sector_t isect) -{ - if (be->be_state == PNFS_BLOCK_NONE_DATA) - return 1; - else if (be->be_state != PNFS_BLOCK_INVALID_DATA) - return 0; - else - return !bl_is_sector_init(be->be_inval, isect); -} - -/* Given the be associated with isect, determine if page data can be - * written to disk. - */ -static int is_writable(struct pnfs_block_extent *be, sector_t isect) -{ - return (be->be_state == PNFS_BLOCK_READWRITE_DATA || - be->be_state == PNFS_BLOCK_INVALID_DATA); + switch (be->be_state) { + case PNFS_BLOCK_NONE_DATA: + return true; + case PNFS_BLOCK_INVALID_DATA: + return be->be_tag ? false : true; + default: + return false; + } } /* The data we are handed might be spread across several bios. We need @@ -91,9 +66,8 @@ static int is_writable(struct pnfs_block_extent *be, sector_t isect) */ struct parallel_io { struct kref refcnt; - void (*pnfs_callback) (void *data, int num_se); + void (*pnfs_callback) (void *data); void *data; - int bse_count; }; static inline struct parallel_io *alloc_parallel(void *data) @@ -104,7 +78,6 @@ static inline struct parallel_io *alloc_parallel(void *data) if (rv) { rv->data = data; kref_init(&rv->refcnt); - rv->bse_count = 0; } return rv; } @@ -119,7 +92,7 @@ static void destroy_parallel(struct kref *kref) struct parallel_io *p = container_of(kref, struct parallel_io, refcnt); dprintk("%s enter\n", __func__); - p->pnfs_callback(p->data, p->bse_count); + p->pnfs_callback(p->data); kfree(p); } @@ -141,10 +114,9 @@ bl_submit_bio(int rw, struct bio *bio) return NULL; } -static struct bio *bl_alloc_init_bio(int npg, sector_t isect, - struct pnfs_block_extent *be, - void (*end_io)(struct bio *, int err), - struct parallel_io *par) +static struct bio * +bl_alloc_init_bio(int npg, struct block_device *bdev, sector_t disk_sector, + void (*end_io)(struct bio *, int err), struct parallel_io *par) { struct bio *bio; @@ -156,58 +128,64 @@ static struct bio *bl_alloc_init_bio(int npg, sector_t isect, } if (bio) { - bio->bi_iter.bi_sector = isect - be->be_f_offset + - be->be_v_offset; - bio->bi_bdev = be->be_mdev; + bio->bi_iter.bi_sector = disk_sector; + bio->bi_bdev = bdev; bio->bi_end_io = end_io; bio->bi_private = par; } return bio; } -static struct bio *do_add_page_to_bio(struct bio *bio, int npg, int rw, - sector_t isect, struct page *page, - struct pnfs_block_extent *be, - void (*end_io)(struct bio *, int err), - struct parallel_io *par, - unsigned int offset, int len) +static struct bio * +do_add_page_to_bio(struct bio *bio, int npg, int rw, sector_t isect, + struct page *page, struct pnfs_block_dev_map *map, + struct pnfs_block_extent *be, + void (*end_io)(struct bio *, int err), + struct parallel_io *par, unsigned int offset, int *len) { - isect = isect + (offset >> SECTOR_SHIFT); + struct pnfs_block_dev *dev = + container_of(be->be_device, struct pnfs_block_dev, node); + u64 disk_addr, end; + dprintk("%s: npg %d rw %d isect %llu offset %u len %d\n", __func__, - npg, rw, (unsigned long long)isect, offset, len); + npg, rw, (unsigned long long)isect, offset, *len); + + /* translate to device offset */ + isect += be->be_v_offset; + isect -= be->be_f_offset; + + /* translate to physical disk offset */ + disk_addr = (u64)isect << SECTOR_SHIFT; + if (disk_addr < map->start || disk_addr >= map->start + map->len) { + if (!dev->map(dev, disk_addr, map)) + return ERR_PTR(-EIO); + bio = bl_submit_bio(rw, bio); + } + disk_addr += map->disk_offset; + disk_addr -= map->start; + + /* limit length to what the device mapping allows */ + end = disk_addr + *len; + if (end >= map->start + map->len) + *len = map->start + map->len - disk_addr; + retry: if (!bio) { - bio = bl_alloc_init_bio(npg, isect, be, end_io, par); + bio = bl_alloc_init_bio(npg, map->bdev, + disk_addr >> SECTOR_SHIFT, end_io, par); if (!bio) return ERR_PTR(-ENOMEM); } - if (bio_add_page(bio, page, len, offset) < len) { + if (bio_add_page(bio, page, *len, offset) < *len) { bio = bl_submit_bio(rw, bio); goto retry; } return bio; } -static struct bio *bl_add_page_to_bio(struct bio *bio, int npg, int rw, - sector_t isect, struct page *page, - struct pnfs_block_extent *be, - void (*end_io)(struct bio *, int err), - struct parallel_io *par) -{ - return do_add_page_to_bio(bio, npg, rw, isect, page, be, - end_io, par, 0, PAGE_CACHE_SIZE); -} - -/* This is basically copied from mpage_end_io_read */ static void bl_end_io_read(struct bio *bio, int err) { struct parallel_io *par = bio->bi_private; - struct bio_vec *bvec; - int i; - - if (!err) - bio_for_each_segment_all(bvec, bio, i) - SetPageUptodate(bvec->bv_page); if (err) { struct nfs_pgio_header *header = par->data; @@ -216,6 +194,7 @@ static void bl_end_io_read(struct bio *bio, int err) header->pnfs_error = -EIO; pnfs_set_lo_fail(header->lseg); } + bio_put(bio); put_parallel(par); } @@ -231,7 +210,7 @@ static void bl_read_cleanup(struct work_struct *work) } static void -bl_end_par_io_read(void *data, int unused) +bl_end_par_io_read(void *data) { struct nfs_pgio_header *hdr = data; @@ -241,88 +220,78 @@ bl_end_par_io_read(void *data, int unused) } static enum pnfs_try_status -bl_read_pagelist(struct nfs_pgio_header *hdr) +bl_read_pagelist(struct nfs_pgio_header *header) { - struct nfs_pgio_header *header = hdr; - int i, hole; + struct pnfs_block_layout *bl = BLK_LSEG2EXT(header->lseg); + struct pnfs_block_dev_map map = { .start = NFS4_MAX_UINT64 }; struct bio *bio = NULL; - struct pnfs_block_extent *be = NULL, *cow_read = NULL; + struct pnfs_block_extent be; sector_t isect, extent_length = 0; struct parallel_io *par; - loff_t f_offset = hdr->args.offset; - size_t bytes_left = hdr->args.count; + loff_t f_offset = header->args.offset; + size_t bytes_left = header->args.count; unsigned int pg_offset, pg_len; - struct page **pages = hdr->args.pages; - int pg_index = hdr->args.pgbase >> PAGE_CACHE_SHIFT; + struct page **pages = header->args.pages; + int pg_index = header->args.pgbase >> PAGE_CACHE_SHIFT; const bool is_dio = (header->dreq != NULL); + struct blk_plug plug; + int i; dprintk("%s enter nr_pages %u offset %lld count %u\n", __func__, - hdr->page_array.npages, f_offset, - (unsigned int)hdr->args.count); + header->page_array.npages, f_offset, + (unsigned int)header->args.count); - par = alloc_parallel(hdr); + par = alloc_parallel(header); if (!par) - goto use_mds; + return PNFS_NOT_ATTEMPTED; par->pnfs_callback = bl_end_par_io_read; - /* At this point, we can no longer jump to use_mds */ + + blk_start_plug(&plug); isect = (sector_t) (f_offset >> SECTOR_SHIFT); /* Code assumes extents are page-aligned */ - for (i = pg_index; i < hdr->page_array.npages; i++) { - if (!extent_length) { + for (i = pg_index; i < header->page_array.npages; i++) { + if (extent_length <= 0) { /* We've used up the previous extent */ - bl_put_extent(be); - bl_put_extent(cow_read); bio = bl_submit_bio(READ, bio); + /* Get the next one */ - be = bl_find_get_extent(BLK_LSEG2EXT(header->lseg), - isect, &cow_read); - if (!be) { + if (!ext_tree_lookup(bl, isect, &be, false)) { header->pnfs_error = -EIO; goto out; } - extent_length = be->be_length - - (isect - be->be_f_offset); - if (cow_read) { - sector_t cow_length = cow_read->be_length - - (isect - cow_read->be_f_offset); - extent_length = min(extent_length, cow_length); - } + extent_length = be.be_length - (isect - be.be_f_offset); } + pg_offset = f_offset & ~PAGE_CACHE_MASK; if (is_dio) { - pg_offset = f_offset & ~PAGE_CACHE_MASK; if (pg_offset + bytes_left > PAGE_CACHE_SIZE) pg_len = PAGE_CACHE_SIZE - pg_offset; else pg_len = bytes_left; - - f_offset += pg_len; - bytes_left -= pg_len; - isect += (pg_offset >> SECTOR_SHIFT); } else { - pg_offset = 0; + BUG_ON(pg_offset != 0); pg_len = PAGE_CACHE_SIZE; } - hole = is_hole(be, isect); - if (hole && !cow_read) { + isect += (pg_offset >> SECTOR_SHIFT); + extent_length -= (pg_offset >> SECTOR_SHIFT); + + if (is_hole(&be)) { bio = bl_submit_bio(READ, bio); /* Fill hole w/ zeroes w/o accessing device */ dprintk("%s Zeroing page for hole\n", __func__); zero_user_segment(pages[i], pg_offset, pg_len); - print_page(pages[i]); - SetPageUptodate(pages[i]); - } else { - struct pnfs_block_extent *be_read; - be_read = (hole && cow_read) ? cow_read : be; + /* invalidate map */ + map.start = NFS4_MAX_UINT64; + } else { bio = do_add_page_to_bio(bio, - hdr->page_array.npages - i, + header->page_array.npages - i, READ, - isect, pages[i], be_read, + isect, pages[i], &map, &be, bl_end_io_read, par, - pg_offset, pg_len); + pg_offset, &pg_len); if (IS_ERR(bio)) { header->pnfs_error = PTR_ERR(bio); bio = NULL; @@ -330,75 +299,21 @@ bl_read_pagelist(struct nfs_pgio_header *hdr) } } isect += (pg_len >> SECTOR_SHIFT); - extent_length -= PAGE_CACHE_SECTORS; + extent_length -= (pg_len >> SECTOR_SHIFT); + f_offset += pg_len; + bytes_left -= pg_len; } if ((isect << SECTOR_SHIFT) >= header->inode->i_size) { - hdr->res.eof = 1; - hdr->res.count = header->inode->i_size - hdr->args.offset; + header->res.eof = 1; + header->res.count = header->inode->i_size - header->args.offset; } else { - hdr->res.count = (isect << SECTOR_SHIFT) - hdr->args.offset; + header->res.count = (isect << SECTOR_SHIFT) - header->args.offset; } out: - bl_put_extent(be); - bl_put_extent(cow_read); bl_submit_bio(READ, bio); + blk_finish_plug(&plug); put_parallel(par); return PNFS_ATTEMPTED; - - use_mds: - dprintk("Giving up and using normal NFS\n"); - return PNFS_NOT_ATTEMPTED; -} - -static void mark_extents_written(struct pnfs_block_layout *bl, - __u64 offset, __u32 count) -{ - sector_t isect, end; - struct pnfs_block_extent *be; - struct pnfs_block_short_extent *se; - - dprintk("%s(%llu, %u)\n", __func__, offset, count); - if (count == 0) - return; - isect = (offset & (long)(PAGE_CACHE_MASK)) >> SECTOR_SHIFT; - end = (offset + count + PAGE_CACHE_SIZE - 1) & (long)(PAGE_CACHE_MASK); - end >>= SECTOR_SHIFT; - while (isect < end) { - sector_t len; - be = bl_find_get_extent(bl, isect, NULL); - BUG_ON(!be); /* FIXME */ - len = min(end, be->be_f_offset + be->be_length) - isect; - if (be->be_state == PNFS_BLOCK_INVALID_DATA) { - se = bl_pop_one_short_extent(be->be_inval); - BUG_ON(!se); - bl_mark_for_commit(be, isect, len, se); - } - isect += len; - bl_put_extent(be); - } -} - -static void bl_end_io_write_zero(struct bio *bio, int err) -{ - struct parallel_io *par = bio->bi_private; - struct bio_vec *bvec; - int i; - - bio_for_each_segment_all(bvec, bio, i) { - /* This is the zeroing page we added */ - end_page_writeback(bvec->bv_page); - page_cache_release(bvec->bv_page); - } - - if (unlikely(err)) { - struct nfs_pgio_header *header = par->data; - - if (!header->pnfs_error) - header->pnfs_error = -EIO; - pnfs_set_lo_fail(header->lseg); - } - bio_put(bio); - put_parallel(par); } static void bl_end_io_write(struct bio *bio, int err) @@ -421,533 +336,118 @@ static void bl_end_io_write(struct bio *bio, int err) */ static void bl_write_cleanup(struct work_struct *work) { - struct rpc_task *task; - struct nfs_pgio_header *hdr; + struct rpc_task *task = container_of(work, struct rpc_task, u.tk_work); + struct nfs_pgio_header *hdr = + container_of(task, struct nfs_pgio_header, task); + dprintk("%s enter\n", __func__); - task = container_of(work, struct rpc_task, u.tk_work); - hdr = container_of(task, struct nfs_pgio_header, task); + if (likely(!hdr->pnfs_error)) { - /* Marks for LAYOUTCOMMIT */ - mark_extents_written(BLK_LSEG2EXT(hdr->lseg), - hdr->args.offset, hdr->args.count); + struct pnfs_block_layout *bl = BLK_LSEG2EXT(hdr->lseg); + u64 start = hdr->args.offset & (loff_t)PAGE_CACHE_MASK; + u64 end = (hdr->args.offset + hdr->args.count + + PAGE_CACHE_SIZE - 1) & (loff_t)PAGE_CACHE_MASK; + + ext_tree_mark_written(bl, start >> SECTOR_SHIFT, + (end - start) >> SECTOR_SHIFT); } + pnfs_ld_write_done(hdr); } /* Called when last of bios associated with a bl_write_pagelist call finishes */ -static void bl_end_par_io_write(void *data, int num_se) +static void bl_end_par_io_write(void *data) { struct nfs_pgio_header *hdr = data; - if (unlikely(hdr->pnfs_error)) { - bl_free_short_extents(&BLK_LSEG2EXT(hdr->lseg)->bl_inval, - num_se); - } - hdr->task.tk_status = hdr->pnfs_error; hdr->verf.committed = NFS_FILE_SYNC; INIT_WORK(&hdr->task.u.tk_work, bl_write_cleanup); schedule_work(&hdr->task.u.tk_work); } -/* FIXME STUB - mark intersection of layout and page as bad, so is not - * used again. - */ -static void mark_bad_read(void) -{ - return; -} - -/* - * map_block: map a requested I/0 block (isect) into an offset in the LVM - * block_device - */ -static void -map_block(struct buffer_head *bh, sector_t isect, struct pnfs_block_extent *be) -{ - dprintk("%s enter be=%p\n", __func__, be); - - set_buffer_mapped(bh); - bh->b_bdev = be->be_mdev; - bh->b_blocknr = (isect - be->be_f_offset + be->be_v_offset) >> - (be->be_mdev->bd_inode->i_blkbits - SECTOR_SHIFT); - - dprintk("%s isect %llu, bh->b_blocknr %ld, using bsize %Zd\n", - __func__, (unsigned long long)isect, (long)bh->b_blocknr, - bh->b_size); - return; -} - -static void -bl_read_single_end_io(struct bio *bio, int error) -{ - struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1; - struct page *page = bvec->bv_page; - - /* Only one page in bvec */ - unlock_page(page); -} - -static int -bl_do_readpage_sync(struct page *page, struct pnfs_block_extent *be, - unsigned int offset, unsigned int len) -{ - struct bio *bio; - struct page *shadow_page; - sector_t isect; - char *kaddr, *kshadow_addr; - int ret = 0; - - dprintk("%s: offset %u len %u\n", __func__, offset, len); - - shadow_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM); - if (shadow_page == NULL) - return -ENOMEM; - - bio = bio_alloc(GFP_NOIO, 1); - if (bio == NULL) - return -ENOMEM; - - isect = (page->index << PAGE_CACHE_SECTOR_SHIFT) + - (offset / SECTOR_SIZE); - - bio->bi_iter.bi_sector = isect - be->be_f_offset + be->be_v_offset; - bio->bi_bdev = be->be_mdev; - bio->bi_end_io = bl_read_single_end_io; - - lock_page(shadow_page); - if (bio_add_page(bio, shadow_page, - SECTOR_SIZE, round_down(offset, SECTOR_SIZE)) == 0) { - unlock_page(shadow_page); - bio_put(bio); - return -EIO; - } - - submit_bio(READ, bio); - wait_on_page_locked(shadow_page); - if (unlikely(!test_bit(BIO_UPTODATE, &bio->bi_flags))) { - ret = -EIO; - } else { - kaddr = kmap_atomic(page); - kshadow_addr = kmap_atomic(shadow_page); - memcpy(kaddr + offset, kshadow_addr + offset, len); - kunmap_atomic(kshadow_addr); - kunmap_atomic(kaddr); - } - __free_page(shadow_page); - bio_put(bio); - - return ret; -} - -static int -bl_read_partial_page_sync(struct page *page, struct pnfs_block_extent *be, - unsigned int dirty_offset, unsigned int dirty_len, - bool full_page) -{ - int ret = 0; - unsigned int start, end; - - if (full_page) { - start = 0; - end = PAGE_CACHE_SIZE; - } else { - start = round_down(dirty_offset, SECTOR_SIZE); - end = round_up(dirty_offset + dirty_len, SECTOR_SIZE); - } - - dprintk("%s: offset %u len %d\n", __func__, dirty_offset, dirty_len); - if (!be) { - zero_user_segments(page, start, dirty_offset, - dirty_offset + dirty_len, end); - if (start == 0 && end == PAGE_CACHE_SIZE && - trylock_page(page)) { - SetPageUptodate(page); - unlock_page(page); - } - return ret; - } - - if (start != dirty_offset) - ret = bl_do_readpage_sync(page, be, start, dirty_offset - start); - - if (!ret && (dirty_offset + dirty_len < end)) - ret = bl_do_readpage_sync(page, be, dirty_offset + dirty_len, - end - dirty_offset - dirty_len); - - return ret; -} - -/* Given an unmapped page, zero it or read in page for COW, page is locked - * by caller. - */ -static int -init_page_for_write(struct page *page, struct pnfs_block_extent *cow_read) -{ - struct buffer_head *bh = NULL; - int ret = 0; - sector_t isect; - - dprintk("%s enter, %p\n", __func__, page); - BUG_ON(PageUptodate(page)); - if (!cow_read) { - zero_user_segment(page, 0, PAGE_SIZE); - SetPageUptodate(page); - goto cleanup; - } - - bh = alloc_page_buffers(page, PAGE_CACHE_SIZE, 0); - if (!bh) { - ret = -ENOMEM; - goto cleanup; - } - - isect = (sector_t) page->index << PAGE_CACHE_SECTOR_SHIFT; - map_block(bh, isect, cow_read); - if (!bh_uptodate_or_lock(bh)) - ret = bh_submit_read(bh); - if (ret) - goto cleanup; - SetPageUptodate(page); - -cleanup: - if (bh) - free_buffer_head(bh); - if (ret) { - /* Need to mark layout with bad read...should now - * just use nfs4 for reads and writes. - */ - mark_bad_read(); - } - return ret; -} - -/* Find or create a zeroing page marked being writeback. - * Return ERR_PTR on error, NULL to indicate skip this page and page itself - * to indicate write out. - */ -static struct page * -bl_find_get_zeroing_page(struct inode *inode, pgoff_t index, - struct pnfs_block_extent *cow_read) -{ - struct page *page; - int locked = 0; - page = find_get_page(inode->i_mapping, index); - if (page) - goto check_page; - - page = find_or_create_page(inode->i_mapping, index, GFP_NOFS); - if (unlikely(!page)) { - dprintk("%s oom\n", __func__); - return ERR_PTR(-ENOMEM); - } - locked = 1; - -check_page: - /* PageDirty: Other will write this out - * PageWriteback: Other is writing this out - * PageUptodate: It was read before - */ - if (PageDirty(page) || PageWriteback(page)) { - print_page(page); - if (locked) - unlock_page(page); - page_cache_release(page); - return NULL; - } - - if (!locked) { - lock_page(page); - locked = 1; - goto check_page; - } - if (!PageUptodate(page)) { - /* New page, readin or zero it */ - init_page_for_write(page, cow_read); - } - set_page_writeback(page); - unlock_page(page); - - return page; -} - static enum pnfs_try_status bl_write_pagelist(struct nfs_pgio_header *header, int sync) { - int i, ret, npg_zero, pg_index, last = 0; + struct pnfs_block_layout *bl = BLK_LSEG2EXT(header->lseg); + struct pnfs_block_dev_map map = { .start = NFS4_MAX_UINT64 }; struct bio *bio = NULL; - struct pnfs_block_extent *be = NULL, *cow_read = NULL; - sector_t isect, last_isect = 0, extent_length = 0; + struct pnfs_block_extent be; + sector_t isect, extent_length = 0; struct parallel_io *par = NULL; loff_t offset = header->args.offset; size_t count = header->args.count; - unsigned int pg_offset, pg_len, saved_len; struct page **pages = header->args.pages; - struct page *page; - pgoff_t index; - u64 temp; - int npg_per_block = - NFS_SERVER(header->inode)->pnfs_blksize >> PAGE_CACHE_SHIFT; + int pg_index = pg_index = header->args.pgbase >> PAGE_CACHE_SHIFT; + unsigned int pg_len; + struct blk_plug plug; + int i; dprintk("%s enter, %Zu@%lld\n", __func__, count, offset); - if (header->dreq != NULL && - (!IS_ALIGNED(offset, NFS_SERVER(header->inode)->pnfs_blksize) || - !IS_ALIGNED(count, NFS_SERVER(header->inode)->pnfs_blksize))) { - dprintk("pnfsblock nonblock aligned DIO writes. Resend MDS\n"); - goto out_mds; - } /* At this point, header->page_aray is a (sequential) list of nfs_pages. * We want to write each, and if there is an error set pnfs_error * to have it redone using nfs. */ par = alloc_parallel(header); if (!par) - goto out_mds; + return PNFS_NOT_ATTEMPTED; par->pnfs_callback = bl_end_par_io_write; - /* 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(header->lseg), isect, &cow_read); - if (!be || !is_writable(be, isect)) { - dprintk("%s no matching extents!\n", __func__); - goto out_mds; - } + blk_start_plug(&plug); - /* First page inside INVALID extent */ - if (be->be_state == PNFS_BLOCK_INVALID_DATA) { - if (likely(!bl_push_one_short_extent(be->be_inval))) - par->bse_count++; - else - goto out_mds; - temp = offset >> PAGE_CACHE_SHIFT; - npg_zero = do_div(temp, npg_per_block); - isect = (sector_t) (((offset - npg_zero * PAGE_CACHE_SIZE) & - (long)PAGE_CACHE_MASK) >> SECTOR_SHIFT); - extent_length = be->be_length - (isect - be->be_f_offset); - -fill_invalid_ext: - dprintk("%s need to zero %d pages\n", __func__, npg_zero); - for (;npg_zero > 0; npg_zero--) { - if (bl_is_sector_init(be->be_inval, isect)) { - dprintk("isect %llu already init\n", - (unsigned long long)isect); - goto next_page; - } - /* page ref released in bl_end_io_write_zero */ - index = isect >> PAGE_CACHE_SECTOR_SHIFT; - dprintk("%s zero %dth page: index %lu isect %llu\n", - __func__, npg_zero, index, - (unsigned long long)isect); - page = bl_find_get_zeroing_page(header->inode, index, - cow_read); - if (unlikely(IS_ERR(page))) { - header->pnfs_error = PTR_ERR(page); - goto out; - } else if (page == NULL) - goto next_page; - - ret = bl_mark_sectors_init(be->be_inval, isect, - PAGE_CACHE_SECTORS); - if (unlikely(ret)) { - dprintk("%s bl_mark_sectors_init fail %d\n", - __func__, ret); - end_page_writeback(page); - page_cache_release(page); - header->pnfs_error = ret; - goto out; - } - if (likely(!bl_push_one_short_extent(be->be_inval))) - par->bse_count++; - else { - end_page_writeback(page); - page_cache_release(page); - header->pnfs_error = -ENOMEM; - goto out; - } - /* FIXME: This should be done in bi_end_io */ - mark_extents_written(BLK_LSEG2EXT(header->lseg), - page->index << PAGE_CACHE_SHIFT, - PAGE_CACHE_SIZE); - - bio = bl_add_page_to_bio(bio, npg_zero, WRITE, - isect, page, be, - bl_end_io_write_zero, par); - if (IS_ERR(bio)) { - header->pnfs_error = PTR_ERR(bio); - bio = NULL; - goto out; - } -next_page: - isect += PAGE_CACHE_SECTORS; - extent_length -= PAGE_CACHE_SECTORS; - } - if (last) - goto write_done; - } - bio = bl_submit_bio(WRITE, bio); + /* we always write out the whole page */ + offset = offset & (loff_t)PAGE_CACHE_MASK; + isect = offset >> SECTOR_SHIFT; - /* Middle pages */ - pg_index = header->args.pgbase >> PAGE_CACHE_SHIFT; for (i = pg_index; i < header->page_array.npages; i++) { - if (!extent_length) { + if (extent_length <= 0) { /* We've used up the previous extent */ - bl_put_extent(be); - bl_put_extent(cow_read); bio = bl_submit_bio(WRITE, bio); /* Get the next one */ - be = bl_find_get_extent(BLK_LSEG2EXT(header->lseg), - isect, &cow_read); - if (!be || !is_writable(be, isect)) { + if (!ext_tree_lookup(bl, isect, &be, true)) { header->pnfs_error = -EINVAL; goto out; } - if (be->be_state == PNFS_BLOCK_INVALID_DATA) { - if (likely(!bl_push_one_short_extent( - be->be_inval))) - par->bse_count++; - else { - header->pnfs_error = -ENOMEM; - goto out; - } - } - extent_length = be->be_length - - (isect - be->be_f_offset); - } - - dprintk("%s offset %lld count %Zu\n", __func__, offset, count); - pg_offset = offset & ~PAGE_CACHE_MASK; - if (pg_offset + count > PAGE_CACHE_SIZE) - pg_len = PAGE_CACHE_SIZE - pg_offset; - else - pg_len = count; - - saved_len = pg_len; - if (be->be_state == PNFS_BLOCK_INVALID_DATA && - !bl_is_sector_init(be->be_inval, isect)) { - ret = bl_read_partial_page_sync(pages[i], cow_read, - pg_offset, pg_len, true); - if (ret) { - dprintk("%s bl_read_partial_page_sync fail %d\n", - __func__, ret); - header->pnfs_error = ret; - goto out; - } - - ret = bl_mark_sectors_init(be->be_inval, isect, - PAGE_CACHE_SECTORS); - if (unlikely(ret)) { - dprintk("%s bl_mark_sectors_init fail %d\n", - __func__, ret); - header->pnfs_error = ret; - goto out; - } - /* Expand to full page write */ - pg_offset = 0; - pg_len = PAGE_CACHE_SIZE; - } else if ((pg_offset & (SECTOR_SIZE - 1)) || - (pg_len & (SECTOR_SIZE - 1))){ - /* ahh, nasty case. We have to do sync full sector - * read-modify-write cycles. - */ - unsigned int saved_offset = pg_offset; - ret = bl_read_partial_page_sync(pages[i], be, pg_offset, - pg_len, false); - pg_offset = round_down(pg_offset, SECTOR_SIZE); - pg_len = round_up(saved_offset + pg_len, SECTOR_SIZE) - - pg_offset; + extent_length = be.be_length - (isect - be.be_f_offset); } - + pg_len = PAGE_CACHE_SIZE; bio = do_add_page_to_bio(bio, header->page_array.npages - i, - WRITE, - isect, pages[i], be, + WRITE, isect, pages[i], &map, &be, bl_end_io_write, par, - pg_offset, pg_len); + 0, &pg_len); if (IS_ERR(bio)) { header->pnfs_error = PTR_ERR(bio); bio = NULL; goto out; } - offset += saved_len; - count -= saved_len; - isect += PAGE_CACHE_SECTORS; - last_isect = isect; - extent_length -= PAGE_CACHE_SECTORS; - } - /* Last page inside INVALID extent */ - if (be->be_state == PNFS_BLOCK_INVALID_DATA) { - bio = bl_submit_bio(WRITE, bio); - temp = last_isect >> PAGE_CACHE_SECTOR_SHIFT; - npg_zero = npg_per_block - do_div(temp, npg_per_block); - if (npg_zero < npg_per_block) { - last = 1; - goto fill_invalid_ext; - } + offset += pg_len; + count -= pg_len; + isect += (pg_len >> SECTOR_SHIFT); + extent_length -= (pg_len >> SECTOR_SHIFT); } -write_done: header->res.count = header->args.count; out: - bl_put_extent(be); - bl_put_extent(cow_read); bl_submit_bio(WRITE, bio); + blk_finish_plug(&plug); put_parallel(par); return PNFS_ATTEMPTED; -out_mds: - bl_put_extent(be); - bl_put_extent(cow_read); - kfree(par); - return PNFS_NOT_ATTEMPTED; -} - -/* FIXME - range ignored */ -static void -release_extents(struct pnfs_block_layout *bl, struct pnfs_layout_range *range) -{ - int i; - struct pnfs_block_extent *be; - - spin_lock(&bl->bl_ext_lock); - for (i = 0; i < EXTENT_LISTS; i++) { - while (!list_empty(&bl->bl_extents[i])) { - be = list_first_entry(&bl->bl_extents[i], - struct pnfs_block_extent, - be_node); - list_del(&be->be_node); - bl_put_extent(be); - } - } - spin_unlock(&bl->bl_ext_lock); -} - -static void -release_inval_marks(struct pnfs_inval_markings *marks) -{ - struct pnfs_inval_tracking *pos, *temp; - struct pnfs_block_short_extent *se, *stemp; - - list_for_each_entry_safe(pos, temp, &marks->im_tree.mtt_stub, it_link) { - list_del(&pos->it_link); - kfree(pos); - } - - list_for_each_entry_safe(se, stemp, &marks->im_extents, bse_node) { - list_del(&se->bse_node); - kfree(se); - } - return; } static void bl_free_layout_hdr(struct pnfs_layout_hdr *lo) { struct pnfs_block_layout *bl = BLK_LO2EXT(lo); + int err; dprintk("%s enter\n", __func__); - release_extents(bl, NULL); - release_inval_marks(&bl->bl_inval); + + err = ext_tree_remove(bl, true, 0, LLONG_MAX); + WARN_ON(err); + kfree(bl); } @@ -960,14 +460,11 @@ static struct pnfs_layout_hdr *bl_alloc_layout_hdr(struct inode *inode, bl = kzalloc(sizeof(*bl), gfp_flags); if (!bl) return NULL; + + bl->bl_ext_rw = RB_ROOT; + bl->bl_ext_ro = RB_ROOT; spin_lock_init(&bl->bl_ext_lock); - INIT_LIST_HEAD(&bl->bl_extents[0]); - INIT_LIST_HEAD(&bl->bl_extents[1]); - INIT_LIST_HEAD(&bl->bl_commit); - INIT_LIST_HEAD(&bl->bl_committing); - bl->bl_count = 0; - bl->bl_blocksize = NFS_SERVER(inode)->pnfs_blksize >> SECTOR_SHIFT; - BL_INIT_INVAL_MARKS(&bl->bl_inval, bl->bl_blocksize); + return &bl->bl_layout; } @@ -977,215 +474,318 @@ static void bl_free_lseg(struct pnfs_layout_segment *lseg) kfree(lseg); } -/* We pretty much ignore lseg, and store all data layout wide, so we - * can correctly merge. - */ -static struct pnfs_layout_segment *bl_alloc_lseg(struct pnfs_layout_hdr *lo, - struct nfs4_layoutget_res *lgr, - gfp_t gfp_flags) -{ - struct pnfs_layout_segment *lseg; - int status; +/* Tracks info needed to ensure extents in layout obey constraints of spec */ +struct layout_verification { + u32 mode; /* R or RW */ + u64 start; /* Expected start of next non-COW extent */ + u64 inval; /* Start of INVAL coverage */ + u64 cowread; /* End of COW read coverage */ +}; - dprintk("%s enter\n", __func__); - lseg = kzalloc(sizeof(*lseg), gfp_flags); - if (!lseg) - return ERR_PTR(-ENOMEM); - status = nfs4_blk_process_layoutget(lo, lgr, gfp_flags); - if (status) { - /* We don't want to call the full-blown bl_free_lseg, - * since on error extents were not touched. - */ - kfree(lseg); - return ERR_PTR(status); +/* Verify the extent meets the layout requirements of the pnfs-block draft, + * section 2.3.1. + */ +static int verify_extent(struct pnfs_block_extent *be, + struct layout_verification *lv) +{ + if (lv->mode == IOMODE_READ) { + if (be->be_state == PNFS_BLOCK_READWRITE_DATA || + be->be_state == PNFS_BLOCK_INVALID_DATA) + return -EIO; + if (be->be_f_offset != lv->start) + return -EIO; + lv->start += be->be_length; + return 0; } - return lseg; + /* lv->mode == IOMODE_RW */ + if (be->be_state == PNFS_BLOCK_READWRITE_DATA) { + if (be->be_f_offset != lv->start) + return -EIO; + if (lv->cowread > lv->start) + return -EIO; + lv->start += be->be_length; + lv->inval = lv->start; + return 0; + } else if (be->be_state == PNFS_BLOCK_INVALID_DATA) { + if (be->be_f_offset != lv->start) + return -EIO; + lv->start += be->be_length; + return 0; + } else if (be->be_state == PNFS_BLOCK_READ_DATA) { + if (be->be_f_offset > lv->start) + return -EIO; + if (be->be_f_offset < lv->inval) + return -EIO; + if (be->be_f_offset < lv->cowread) + return -EIO; + /* It looks like you might want to min this with lv->start, + * but you really don't. + */ + lv->inval = lv->inval + be->be_length; + lv->cowread = be->be_f_offset + be->be_length; + return 0; + } else + return -EIO; } -static void -bl_encode_layoutcommit(struct pnfs_layout_hdr *lo, struct xdr_stream *xdr, - const struct nfs4_layoutcommit_args *arg) +static int decode_sector_number(__be32 **rp, sector_t *sp) { - dprintk("%s enter\n", __func__); - encode_pnfs_block_layoutupdate(BLK_LO2EXT(lo), xdr, arg); + uint64_t s; + + *rp = xdr_decode_hyper(*rp, &s); + if (s & 0x1ff) { + printk(KERN_WARNING "NFS: %s: sector not aligned\n", __func__); + return -1; + } + *sp = s >> SECTOR_SHIFT; + return 0; } -static void -bl_cleanup_layoutcommit(struct nfs4_layoutcommit_data *lcdata) +static int +bl_alloc_extent(struct xdr_stream *xdr, struct pnfs_layout_hdr *lo, + struct layout_verification *lv, struct list_head *extents, + gfp_t gfp_mask) { - struct pnfs_layout_hdr *lo = NFS_I(lcdata->args.inode)->layout; + struct pnfs_block_extent *be; + struct nfs4_deviceid id; + int error; + __be32 *p; - dprintk("%s enter\n", __func__); - clean_pnfs_block_layoutupdate(BLK_LO2EXT(lo), &lcdata->args, lcdata->res.status); -} + p = xdr_inline_decode(xdr, 28 + NFS4_DEVICEID4_SIZE); + if (!p) + return -EIO; -static void free_blk_mountid(struct block_mount_id *mid) -{ - if (mid) { - struct pnfs_block_dev *dev, *tmp; + be = kzalloc(sizeof(*be), GFP_NOFS); + if (!be) + return -ENOMEM; - /* No need to take bm_lock as we are last user freeing bm_devlist */ - list_for_each_entry_safe(dev, tmp, &mid->bm_devlist, bm_node) { - list_del(&dev->bm_node); - bl_free_block_dev(dev); - } - kfree(mid); + memcpy(&id, p, NFS4_DEVICEID4_SIZE); + p += XDR_QUADLEN(NFS4_DEVICEID4_SIZE); + + error = -EIO; + be->be_device = nfs4_find_get_deviceid(NFS_SERVER(lo->plh_inode), &id, + lo->plh_lc_cred, gfp_mask); + if (!be->be_device) + goto out_free_be; + + /* + * The next three values are read in as bytes, but stored in the + * extent structure in 512-byte granularity. + */ + if (decode_sector_number(&p, &be->be_f_offset) < 0) + goto out_put_deviceid; + if (decode_sector_number(&p, &be->be_length) < 0) + goto out_put_deviceid; + if (decode_sector_number(&p, &be->be_v_offset) < 0) + goto out_put_deviceid; + be->be_state = be32_to_cpup(p++); + + error = verify_extent(be, lv); + if (error) { + dprintk("%s: extent verification failed\n", __func__); + goto out_put_deviceid; } + + list_add_tail(&be->be_list, extents); + return 0; + +out_put_deviceid: + nfs4_put_deviceid_node(be->be_device); +out_free_be: + kfree(be); + return error; } -/* This is mostly copied from the filelayout_get_device_info function. - * It seems much of this should be at the generic pnfs level. - */ -static struct pnfs_block_dev * -nfs4_blk_get_deviceinfo(struct nfs_server *server, const struct nfs_fh *fh, - struct nfs4_deviceid *d_id) +static struct pnfs_layout_segment * +bl_alloc_lseg(struct pnfs_layout_hdr *lo, struct nfs4_layoutget_res *lgr, + gfp_t gfp_mask) { - struct pnfs_device *dev; - struct pnfs_block_dev *rv; - u32 max_resp_sz; - int max_pages; - struct page **pages = NULL; - int i, rc; + struct layout_verification lv = { + .mode = lgr->range.iomode, + .start = lgr->range.offset >> SECTOR_SHIFT, + .inval = lgr->range.offset >> SECTOR_SHIFT, + .cowread = lgr->range.offset >> SECTOR_SHIFT, + }; + struct pnfs_block_layout *bl = BLK_LO2EXT(lo); + struct pnfs_layout_segment *lseg; + struct xdr_buf buf; + struct xdr_stream xdr; + struct page *scratch; + int status, i; + uint32_t count; + __be32 *p; + LIST_HEAD(extents); + + dprintk("---> %s\n", __func__); + + lseg = kzalloc(sizeof(*lseg), gfp_mask); + if (!lseg) + return ERR_PTR(-ENOMEM); + + status = -ENOMEM; + scratch = alloc_page(gfp_mask); + if (!scratch) + goto out; + + xdr_init_decode_pages(&xdr, &buf, + lgr->layoutp->pages, lgr->layoutp->len); + xdr_set_scratch_buffer(&xdr, page_address(scratch), PAGE_SIZE); + + status = -EIO; + p = xdr_inline_decode(&xdr, 4); + if (unlikely(!p)) + goto out_free_scratch; + + count = be32_to_cpup(p++); + dprintk("%s: number of extents %d\n", __func__, count); /* - * Use the session max response size as the basis for setting - * GETDEVICEINFO's maxcount + * Decode individual extents, putting them in temporary staging area + * until whole layout is decoded to make error recovery easier. */ - max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz; - max_pages = nfs_page_array_len(0, max_resp_sz); - dprintk("%s max_resp_sz %u max_pages %d\n", - __func__, max_resp_sz, max_pages); - - dev = kmalloc(sizeof(*dev), GFP_NOFS); - if (!dev) { - dprintk("%s kmalloc failed\n", __func__); - return ERR_PTR(-ENOMEM); + for (i = 0; i < count; i++) { + status = bl_alloc_extent(&xdr, lo, &lv, &extents, gfp_mask); + if (status) + goto process_extents; } - pages = kcalloc(max_pages, sizeof(struct page *), GFP_NOFS); - if (pages == NULL) { - kfree(dev); - return ERR_PTR(-ENOMEM); + if (lgr->range.offset + lgr->range.length != + lv.start << SECTOR_SHIFT) { + dprintk("%s Final length mismatch\n", __func__); + status = -EIO; + goto process_extents; } - for (i = 0; i < max_pages; i++) { - pages[i] = alloc_page(GFP_NOFS); - if (!pages[i]) { - rv = ERR_PTR(-ENOMEM); - goto out_free; - } + + if (lv.start < lv.cowread) { + dprintk("%s Final uncovered COW extent\n", __func__); + status = -EIO; } - memcpy(&dev->dev_id, d_id, sizeof(*d_id)); - dev->layout_type = LAYOUT_BLOCK_VOLUME; - dev->pages = pages; - dev->pgbase = 0; - dev->pglen = PAGE_SIZE * max_pages; - dev->mincount = 0; - dev->maxcount = max_resp_sz - nfs41_maxgetdevinfo_overhead; - - dprintk("%s: dev_id: %s\n", __func__, dev->dev_id.data); - rc = nfs4_proc_getdeviceinfo(server, dev, NULL); - dprintk("%s getdevice info returns %d\n", __func__, rc); - if (rc) { - rv = ERR_PTR(rc); - goto out_free; +process_extents: + while (!list_empty(&extents)) { + struct pnfs_block_extent *be = + list_first_entry(&extents, struct pnfs_block_extent, + be_list); + list_del(&be->be_list); + + if (!status) + status = ext_tree_insert(bl, be); + + if (status) { + nfs4_put_deviceid_node(be->be_device); + kfree(be); + } } - rv = nfs4_blk_decode_device(server, dev); - out_free: - for (i = 0; i < max_pages; i++) - __free_page(pages[i]); - kfree(pages); - kfree(dev); - return rv; +out_free_scratch: + __free_page(scratch); +out: + dprintk("%s returns %d\n", __func__, status); + if (status) { + kfree(lseg); + return ERR_PTR(status); + } + return lseg; } -static int -bl_set_layoutdriver(struct nfs_server *server, const struct nfs_fh *fh) +static void +bl_return_range(struct pnfs_layout_hdr *lo, + struct pnfs_layout_range *range) { - struct block_mount_id *b_mt_id = NULL; - struct pnfs_devicelist *dlist = NULL; - struct pnfs_block_dev *bdev; - LIST_HEAD(block_disklist); - int status, i; - - dprintk("%s enter\n", __func__); + struct pnfs_block_layout *bl = BLK_LO2EXT(lo); + sector_t offset = range->offset >> SECTOR_SHIFT, end; - if (server->pnfs_blksize == 0) { - dprintk("%s Server did not return blksize\n", __func__); - return -EINVAL; - } - b_mt_id = kzalloc(sizeof(struct block_mount_id), GFP_NOFS); - if (!b_mt_id) { - status = -ENOMEM; - goto out_error; - } - /* Initialize nfs4 block layout mount id */ - spin_lock_init(&b_mt_id->bm_lock); - INIT_LIST_HEAD(&b_mt_id->bm_devlist); - - dlist = kmalloc(sizeof(struct pnfs_devicelist), GFP_NOFS); - if (!dlist) { - status = -ENOMEM; - goto out_error; + if (range->offset % 8) { + dprintk("%s: offset %lld not block size aligned\n", + __func__, range->offset); + return; } - dlist->eof = 0; - while (!dlist->eof) { - status = nfs4_proc_getdevicelist(server, fh, dlist); - if (status) - goto out_error; - dprintk("%s GETDEVICELIST numdevs=%i, eof=%i\n", - __func__, dlist->num_devs, dlist->eof); - for (i = 0; i < dlist->num_devs; i++) { - bdev = nfs4_blk_get_deviceinfo(server, fh, - &dlist->dev_id[i]); - if (IS_ERR(bdev)) { - status = PTR_ERR(bdev); - goto out_error; - } - spin_lock(&b_mt_id->bm_lock); - list_add(&bdev->bm_node, &b_mt_id->bm_devlist); - spin_unlock(&b_mt_id->bm_lock); + + if (range->length != NFS4_MAX_UINT64) { + if (range->length % 8) { + dprintk("%s: length %lld not block size aligned\n", + __func__, range->length); + return; } - } - dprintk("%s SUCCESS\n", __func__); - server->pnfs_ld_data = b_mt_id; - out_return: - kfree(dlist); - return status; + end = offset + (range->length >> SECTOR_SHIFT); + } else { + end = round_down(NFS4_MAX_UINT64, PAGE_SIZE); + } - out_error: - free_blk_mountid(b_mt_id); - goto out_return; + ext_tree_remove(bl, range->iomode & IOMODE_RW, offset, end); } static int -bl_clear_layoutdriver(struct nfs_server *server) +bl_prepare_layoutcommit(struct nfs4_layoutcommit_args *arg) +{ + return ext_tree_prepare_commit(arg); +} + +static void +bl_cleanup_layoutcommit(struct nfs4_layoutcommit_data *lcdata) { - struct block_mount_id *b_mt_id = server->pnfs_ld_data; + ext_tree_mark_committed(&lcdata->args, lcdata->res.status); +} +static int +bl_set_layoutdriver(struct nfs_server *server, const struct nfs_fh *fh) +{ dprintk("%s enter\n", __func__); - free_blk_mountid(b_mt_id); - dprintk("%s RETURNS\n", __func__); + + if (server->pnfs_blksize == 0) { + dprintk("%s Server did not return blksize\n", __func__); + return -EINVAL; + } + if (server->pnfs_blksize > PAGE_SIZE) { + printk(KERN_ERR "%s: pNFS blksize %d not supported.\n", + __func__, server->pnfs_blksize); + return -EINVAL; + } + return 0; } static bool -is_aligned_req(struct nfs_page *req, unsigned int alignment) +is_aligned_req(struct nfs_pageio_descriptor *pgio, + struct nfs_page *req, unsigned int alignment) { - return IS_ALIGNED(req->wb_offset, alignment) && - IS_ALIGNED(req->wb_bytes, alignment); + /* + * Always accept buffered writes, higher layers take care of the + * right alignment. + */ + if (pgio->pg_dreq == NULL) + return true; + + if (!IS_ALIGNED(req->wb_offset, alignment)) + return false; + + if (IS_ALIGNED(req->wb_bytes, alignment)) + return true; + + if (req_offset(req) + req->wb_bytes == i_size_read(pgio->pg_inode)) { + /* + * If the write goes up to the inode size, just write + * the full page. Data past the inode size is + * guaranteed to be zeroed by the higher level client + * code, and this behaviour is mandated by RFC 5663 + * section 2.3.2. + */ + return true; + } + + return false; } static void bl_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) { - if (pgio->pg_dreq != NULL && - !is_aligned_req(req, SECTOR_SIZE)) + if (!is_aligned_req(pgio, req, SECTOR_SIZE)) { nfs_pageio_reset_read_mds(pgio); - else - pnfs_generic_pg_init_read(pgio, req); + return; + } + + pnfs_generic_pg_init_read(pgio, req); } /* @@ -1196,10 +796,8 @@ static size_t bl_pg_test_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, struct nfs_page *req) { - if (pgio->pg_dreq != NULL && - !is_aligned_req(req, SECTOR_SIZE)) + if (!is_aligned_req(pgio, req, SECTOR_SIZE)) return 0; - return pnfs_generic_pg_test(pgio, prev, req); } @@ -1229,19 +827,20 @@ static u64 pnfs_num_cont_bytes(struct inode *inode, pgoff_t idx) static void bl_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) { - if (pgio->pg_dreq != NULL && - !is_aligned_req(req, PAGE_CACHE_SIZE)) { + u64 wb_size; + + if (!is_aligned_req(pgio, req, PAGE_SIZE)) { nfs_pageio_reset_write_mds(pgio); - } else { - u64 wb_size; - if (pgio->pg_dreq == NULL) - wb_size = pnfs_num_cont_bytes(pgio->pg_inode, - req->wb_index); - else - wb_size = nfs_dreq_bytes_left(pgio->pg_dreq); - - pnfs_generic_pg_init_write(pgio, req, wb_size); + return; } + + if (pgio->pg_dreq == NULL) + wb_size = pnfs_num_cont_bytes(pgio->pg_inode, + req->wb_index); + else + wb_size = nfs_dreq_bytes_left(pgio->pg_dreq); + + pnfs_generic_pg_init_write(pgio, req, wb_size); } /* @@ -1252,10 +851,8 @@ static size_t bl_pg_test_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, struct nfs_page *req) { - if (pgio->pg_dreq != NULL && - !is_aligned_req(req, PAGE_CACHE_SIZE)) + if (!is_aligned_req(pgio, req, PAGE_SIZE)) return 0; - return pnfs_generic_pg_test(pgio, prev, req); } @@ -1275,146 +872,24 @@ static struct pnfs_layoutdriver_type blocklayout_type = { .id = LAYOUT_BLOCK_VOLUME, .name = "LAYOUT_BLOCK_VOLUME", .owner = THIS_MODULE, + .flags = PNFS_LAYOUTRET_ON_SETATTR | + PNFS_READ_WHOLE_PAGE, .read_pagelist = bl_read_pagelist, .write_pagelist = bl_write_pagelist, .alloc_layout_hdr = bl_alloc_layout_hdr, .free_layout_hdr = bl_free_layout_hdr, .alloc_lseg = bl_alloc_lseg, .free_lseg = bl_free_lseg, - .encode_layoutcommit = bl_encode_layoutcommit, + .return_range = bl_return_range, + .prepare_layoutcommit = bl_prepare_layoutcommit, .cleanup_layoutcommit = bl_cleanup_layoutcommit, .set_layoutdriver = bl_set_layoutdriver, - .clear_layoutdriver = bl_clear_layoutdriver, + .alloc_deviceid_node = bl_alloc_deviceid_node, + .free_deviceid_node = bl_free_deviceid_node, .pg_read_ops = &bl_pg_read_ops, .pg_write_ops = &bl_pg_write_ops, }; -static const struct rpc_pipe_ops bl_upcall_ops = { - .upcall = rpc_pipe_generic_upcall, - .downcall = bl_pipe_downcall, - .destroy_msg = bl_pipe_destroy_msg, -}; - -static struct dentry *nfs4blocklayout_register_sb(struct super_block *sb, - struct rpc_pipe *pipe) -{ - struct dentry *dir, *dentry; - - dir = rpc_d_lookup_sb(sb, NFS_PIPE_DIRNAME); - if (dir == NULL) - return ERR_PTR(-ENOENT); - dentry = rpc_mkpipe_dentry(dir, "blocklayout", NULL, pipe); - dput(dir); - return dentry; -} - -static void nfs4blocklayout_unregister_sb(struct super_block *sb, - struct rpc_pipe *pipe) -{ - if (pipe->dentry) - rpc_unlink(pipe->dentry); -} - -static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event, - void *ptr) -{ - struct super_block *sb = ptr; - struct net *net = sb->s_fs_info; - struct nfs_net *nn = net_generic(net, nfs_net_id); - struct dentry *dentry; - int ret = 0; - - if (!try_module_get(THIS_MODULE)) - return 0; - - if (nn->bl_device_pipe == NULL) { - module_put(THIS_MODULE); - return 0; - } - - switch (event) { - case RPC_PIPEFS_MOUNT: - dentry = nfs4blocklayout_register_sb(sb, nn->bl_device_pipe); - if (IS_ERR(dentry)) { - ret = PTR_ERR(dentry); - break; - } - nn->bl_device_pipe->dentry = dentry; - break; - case RPC_PIPEFS_UMOUNT: - if (nn->bl_device_pipe->dentry) - nfs4blocklayout_unregister_sb(sb, nn->bl_device_pipe); - break; - default: - ret = -ENOTSUPP; - break; - } - module_put(THIS_MODULE); - return ret; -} - -static struct notifier_block nfs4blocklayout_block = { - .notifier_call = rpc_pipefs_event, -}; - -static struct dentry *nfs4blocklayout_register_net(struct net *net, - struct rpc_pipe *pipe) -{ - struct super_block *pipefs_sb; - struct dentry *dentry; - - pipefs_sb = rpc_get_sb_net(net); - if (!pipefs_sb) - return NULL; - dentry = nfs4blocklayout_register_sb(pipefs_sb, pipe); - rpc_put_sb_net(net); - return dentry; -} - -static void nfs4blocklayout_unregister_net(struct net *net, - struct rpc_pipe *pipe) -{ - struct super_block *pipefs_sb; - - pipefs_sb = rpc_get_sb_net(net); - if (pipefs_sb) { - nfs4blocklayout_unregister_sb(pipefs_sb, pipe); - rpc_put_sb_net(net); - } -} - -static int nfs4blocklayout_net_init(struct net *net) -{ - struct nfs_net *nn = net_generic(net, nfs_net_id); - struct dentry *dentry; - - init_waitqueue_head(&nn->bl_wq); - nn->bl_device_pipe = rpc_mkpipe_data(&bl_upcall_ops, 0); - if (IS_ERR(nn->bl_device_pipe)) - return PTR_ERR(nn->bl_device_pipe); - dentry = nfs4blocklayout_register_net(net, nn->bl_device_pipe); - if (IS_ERR(dentry)) { - rpc_destroy_pipe_data(nn->bl_device_pipe); - return PTR_ERR(dentry); - } - nn->bl_device_pipe->dentry = dentry; - return 0; -} - -static void nfs4blocklayout_net_exit(struct net *net) -{ - struct nfs_net *nn = net_generic(net, nfs_net_id); - - nfs4blocklayout_unregister_net(net, nn->bl_device_pipe); - rpc_destroy_pipe_data(nn->bl_device_pipe); - nn->bl_device_pipe = NULL; -} - -static struct pernet_operations nfs4blocklayout_net_ops = { - .init = nfs4blocklayout_net_init, - .exit = nfs4blocklayout_net_exit, -}; - static int __init nfs4blocklayout_init(void) { int ret; @@ -1424,20 +899,14 @@ static int __init nfs4blocklayout_init(void) ret = pnfs_register_layoutdriver(&blocklayout_type); if (ret) goto out; - - ret = rpc_pipefs_notifier_register(&nfs4blocklayout_block); + ret = bl_init_pipefs(); if (ret) - goto out_remove; - ret = register_pernet_subsys(&nfs4blocklayout_net_ops); - if (ret) - goto out_notifier; -out: - return ret; + goto out_unregister; + return 0; -out_notifier: - rpc_pipefs_notifier_unregister(&nfs4blocklayout_block); -out_remove: +out_unregister: pnfs_unregister_layoutdriver(&blocklayout_type); +out: return ret; } @@ -1446,8 +915,7 @@ static void __exit nfs4blocklayout_exit(void) dprintk("%s: NFSv4 Block Layout Driver Unregistering...\n", __func__); - rpc_pipefs_notifier_unregister(&nfs4blocklayout_block); - unregister_pernet_subsys(&nfs4blocklayout_net_ops); + bl_cleanup_pipefs(); pnfs_unregister_layoutdriver(&blocklayout_type); } diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h index 9838fb020473..92dca9e90d8d 100644 --- a/fs/nfs/blocklayout/blocklayout.h +++ b/fs/nfs/blocklayout/blocklayout.h @@ -44,105 +44,112 @@ #define PAGE_CACHE_SECTOR_SHIFT (PAGE_CACHE_SHIFT - SECTOR_SHIFT) #define SECTOR_SIZE (1 << SECTOR_SHIFT) -struct block_mount_id { - spinlock_t bm_lock; /* protects list */ - struct list_head bm_devlist; /* holds pnfs_block_dev */ -}; +struct pnfs_block_dev; -struct pnfs_block_dev { - struct list_head bm_node; - struct nfs4_deviceid bm_mdevid; /* associated devid */ - struct block_device *bm_mdev; /* meta device itself */ - struct net *net; +enum pnfs_block_volume_type { + PNFS_BLOCK_VOLUME_SIMPLE = 0, + PNFS_BLOCK_VOLUME_SLICE = 1, + PNFS_BLOCK_VOLUME_CONCAT = 2, + PNFS_BLOCK_VOLUME_STRIPE = 3, }; -enum exstate4 { - PNFS_BLOCK_READWRITE_DATA = 0, - PNFS_BLOCK_READ_DATA = 1, - PNFS_BLOCK_INVALID_DATA = 2, /* mapped, but data is invalid */ - PNFS_BLOCK_NONE_DATA = 3 /* unmapped, it's a hole */ +#define PNFS_BLOCK_MAX_UUIDS 4 +#define PNFS_BLOCK_MAX_DEVICES 64 + +/* + * Random upper cap for the uuid length to avoid unbounded allocation. + * Not actually limited by the protocol. + */ +#define PNFS_BLOCK_UUID_LEN 128 + + +struct pnfs_block_volume { + enum pnfs_block_volume_type type; + union { + struct { + int len; + int nr_sigs; + struct { + u64 offset; + u32 sig_len; + u8 sig[PNFS_BLOCK_UUID_LEN]; + } sigs[PNFS_BLOCK_MAX_UUIDS]; + } simple; + struct { + u64 start; + u64 len; + u32 volume; + } slice; + struct { + u32 volumes_count; + u32 volumes[PNFS_BLOCK_MAX_DEVICES]; + } concat; + struct { + u64 chunk_size; + u32 volumes_count; + u32 volumes[PNFS_BLOCK_MAX_DEVICES]; + } stripe; + }; }; -#define MY_MAX_TAGS (15) /* tag bitnums used must be less than this */ +struct pnfs_block_dev_map { + sector_t start; + sector_t len; -struct my_tree { - sector_t mtt_step_size; /* Internal sector alignment */ - struct list_head mtt_stub; /* Should be a radix tree */ + sector_t disk_offset; + struct block_device *bdev; }; -struct pnfs_inval_markings { - spinlock_t im_lock; - struct my_tree im_tree; /* Sectors that need LAYOUTCOMMIT */ - sector_t im_block_size; /* Server blocksize in sectors */ - struct list_head im_extents; /* Short extents for INVAL->RW conversion */ +struct pnfs_block_dev { + struct nfs4_deviceid_node node; + + u64 start; + u64 len; + + u32 nr_children; + struct pnfs_block_dev *children; + u64 chunk_size; + + struct block_device *bdev; + u64 disk_offset; + + bool (*map)(struct pnfs_block_dev *dev, u64 offset, + struct pnfs_block_dev_map *map); }; -struct pnfs_inval_tracking { - struct list_head it_link; - int it_sector; - int it_tags; +enum exstate4 { + PNFS_BLOCK_READWRITE_DATA = 0, + PNFS_BLOCK_READ_DATA = 1, + PNFS_BLOCK_INVALID_DATA = 2, /* mapped, but data is invalid */ + PNFS_BLOCK_NONE_DATA = 3 /* unmapped, it's a hole */ }; /* sector_t fields are all in 512-byte sectors */ struct pnfs_block_extent { - struct kref be_refcnt; - struct list_head be_node; /* link into lseg list */ - struct nfs4_deviceid be_devid; /* FIXME: could use device cache instead */ - struct block_device *be_mdev; + union { + struct rb_node be_node; + struct list_head be_list; + }; + struct nfs4_deviceid_node *be_device; sector_t be_f_offset; /* the starting offset in the file */ sector_t be_length; /* the size of the extent */ sector_t be_v_offset; /* the starting offset in the volume */ enum exstate4 be_state; /* the state of this extent */ - struct pnfs_inval_markings *be_inval; /* tracks INVAL->RW transition */ +#define EXTENT_WRITTEN 1 +#define EXTENT_COMMITTING 2 + unsigned int be_tag; }; -/* Shortened extent used by LAYOUTCOMMIT */ -struct pnfs_block_short_extent { - struct list_head bse_node; - struct nfs4_deviceid bse_devid; - struct block_device *bse_mdev; - sector_t bse_f_offset; /* the starting offset in the file */ - sector_t bse_length; /* the size of the extent */ -}; - -static inline void -BL_INIT_INVAL_MARKS(struct pnfs_inval_markings *marks, sector_t blocksize) -{ - spin_lock_init(&marks->im_lock); - INIT_LIST_HEAD(&marks->im_tree.mtt_stub); - INIT_LIST_HEAD(&marks->im_extents); - marks->im_block_size = blocksize; - marks->im_tree.mtt_step_size = min((sector_t)PAGE_CACHE_SECTORS, - blocksize); -} - -enum extentclass4 { - RW_EXTENT = 0, /* READWRTE and INVAL */ - RO_EXTENT = 1, /* READ and NONE */ - EXTENT_LISTS = 2, -}; - -static inline int bl_choose_list(enum exstate4 state) -{ - if (state == PNFS_BLOCK_READ_DATA || state == PNFS_BLOCK_NONE_DATA) - return RO_EXTENT; - else - return RW_EXTENT; -} +/* on the wire size of the extent */ +#define BL_EXTENT_SIZE (7 * sizeof(__be32) + NFS4_DEVICEID4_SIZE) struct pnfs_block_layout { - struct pnfs_layout_hdr bl_layout; - struct pnfs_inval_markings bl_inval; /* tracks INVAL->RW transition */ + struct pnfs_layout_hdr bl_layout; + struct rb_root bl_ext_rw; + struct rb_root bl_ext_ro; spinlock_t bl_ext_lock; /* Protects list manipulation */ - struct list_head bl_extents[EXTENT_LISTS]; /* R and RW extents */ - struct list_head bl_commit; /* Needs layout commit */ - struct list_head bl_committing; /* Layout committing */ - unsigned int bl_count; /* entries in bl_commit */ - sector_t bl_blocksize; /* Server blocksize in sectors */ }; -#define BLK_ID(lo) ((struct block_mount_id *)(NFS_SERVER(lo->plh_inode)->pnfs_ld_data)) - static inline struct pnfs_block_layout * BLK_LO2EXT(struct pnfs_layout_hdr *lo) { @@ -171,41 +178,27 @@ struct bl_msg_hdr { #define BL_DEVICE_REQUEST_PROC 0x1 /* User level process succeeds */ #define BL_DEVICE_REQUEST_ERR 0x2 /* User level process fails */ -/* blocklayoutdev.c */ -ssize_t bl_pipe_downcall(struct file *, const char __user *, size_t); -void bl_pipe_destroy_msg(struct rpc_pipe_msg *); -void nfs4_blkdev_put(struct block_device *bdev); -struct pnfs_block_dev *nfs4_blk_decode_device(struct nfs_server *server, - struct pnfs_device *dev); -int nfs4_blk_process_layoutget(struct pnfs_layout_hdr *lo, - struct nfs4_layoutget_res *lgr, gfp_t gfp_flags); - -/* blocklayoutdm.c */ -void bl_free_block_dev(struct pnfs_block_dev *bdev); - -/* extents.c */ -struct pnfs_block_extent * -bl_find_get_extent(struct pnfs_block_layout *bl, sector_t isect, - struct pnfs_block_extent **cow_read); -int bl_mark_sectors_init(struct pnfs_inval_markings *marks, - sector_t offset, sector_t length); -void bl_put_extent(struct pnfs_block_extent *be); -struct pnfs_block_extent *bl_alloc_extent(void); -int bl_is_sector_init(struct pnfs_inval_markings *marks, sector_t isect); -int encode_pnfs_block_layoutupdate(struct pnfs_block_layout *bl, - struct xdr_stream *xdr, - const struct nfs4_layoutcommit_args *arg); -void clean_pnfs_block_layoutupdate(struct pnfs_block_layout *bl, - const struct nfs4_layoutcommit_args *arg, - int status); -int bl_add_merge_extent(struct pnfs_block_layout *bl, - struct pnfs_block_extent *new); -int bl_mark_for_commit(struct pnfs_block_extent *be, - sector_t offset, sector_t length, - struct pnfs_block_short_extent *new); -int bl_push_one_short_extent(struct pnfs_inval_markings *marks); -struct pnfs_block_short_extent * -bl_pop_one_short_extent(struct pnfs_inval_markings *marks); -void bl_free_short_extents(struct pnfs_inval_markings *marks, int num_to_free); +/* dev.c */ +struct nfs4_deviceid_node *bl_alloc_deviceid_node(struct nfs_server *server, + struct pnfs_device *pdev, gfp_t gfp_mask); +void bl_free_deviceid_node(struct nfs4_deviceid_node *d); + +/* extent_tree.c */ +int ext_tree_insert(struct pnfs_block_layout *bl, + struct pnfs_block_extent *new); +int ext_tree_remove(struct pnfs_block_layout *bl, bool rw, sector_t start, + sector_t end); +int ext_tree_mark_written(struct pnfs_block_layout *bl, sector_t start, + sector_t len); +bool ext_tree_lookup(struct pnfs_block_layout *bl, sector_t isect, + struct pnfs_block_extent *ret, bool rw); +int ext_tree_prepare_commit(struct nfs4_layoutcommit_args *arg); +void ext_tree_mark_committed(struct nfs4_layoutcommit_args *arg, int status); + +/* rpc_pipefs.c */ +dev_t bl_resolve_deviceid(struct nfs_server *server, + struct pnfs_block_volume *b, gfp_t gfp_mask); +int __init bl_init_pipefs(void); +void __exit bl_cleanup_pipefs(void); #endif /* FS_NFS_NFS4BLOCKLAYOUT_H */ diff --git a/fs/nfs/blocklayout/blocklayoutdev.c b/fs/nfs/blocklayout/blocklayoutdev.c deleted file mode 100644 index 04303b5c9361..000000000000 --- a/fs/nfs/blocklayout/blocklayoutdev.c +++ /dev/null @@ -1,384 +0,0 @@ -/* - * linux/fs/nfs/blocklayout/blocklayoutdev.c - * - * Device operations for the pnfs nfs4 file layout driver. - * - * Copyright (c) 2006 The Regents of the University of Michigan. - * All rights reserved. - * - * Andy Adamson <andros@citi.umich.edu> - * Fred Isaman <iisaman@umich.edu> - * - * permission is granted to use, copy, create derivative works and - * redistribute this software and such derivative works for any purpose, - * so long as the name of the university of michigan is not used in - * any advertising or publicity pertaining to the use or distribution - * of this software without specific, written prior authorization. if - * the above copyright notice or any other identification of the - * university of michigan is included in any copy of any portion of - * this software, then the disclaimer below must also be included. - * - * this software is provided as is, without representation from the - * university of michigan as to its fitness for any purpose, and without - * warranty by the university of michigan of any kind, either express - * or implied, including without limitation the implied warranties of - * merchantability and fitness for a particular purpose. the regents - * of the university of michigan shall not be liable for any damages, - * including special, indirect, incidental, or consequential damages, - * with respect to any claim arising out or in connection with the use - * of the software, even if it has been or is hereafter advised of the - * possibility of such damages. - */ -#include <linux/module.h> -#include <linux/buffer_head.h> /* __bread */ - -#include <linux/genhd.h> -#include <linux/blkdev.h> -#include <linux/hash.h> - -#include "blocklayout.h" - -#define NFSDBG_FACILITY NFSDBG_PNFS_LD - -static int decode_sector_number(__be32 **rp, sector_t *sp) -{ - uint64_t s; - - *rp = xdr_decode_hyper(*rp, &s); - if (s & 0x1ff) { - printk(KERN_WARNING "NFS: %s: sector not aligned\n", __func__); - return -1; - } - *sp = s >> SECTOR_SHIFT; - return 0; -} - -/* - * Release the block device - */ -void nfs4_blkdev_put(struct block_device *bdev) -{ - dprintk("%s for device %d:%d\n", __func__, MAJOR(bdev->bd_dev), - MINOR(bdev->bd_dev)); - blkdev_put(bdev, FMODE_READ); -} - -ssize_t bl_pipe_downcall(struct file *filp, const char __user *src, - size_t mlen) -{ - struct nfs_net *nn = net_generic(filp->f_dentry->d_sb->s_fs_info, - nfs_net_id); - - if (mlen != sizeof (struct bl_dev_msg)) - return -EINVAL; - - if (copy_from_user(&nn->bl_mount_reply, src, mlen) != 0) - return -EFAULT; - - wake_up(&nn->bl_wq); - - return mlen; -} - -void bl_pipe_destroy_msg(struct rpc_pipe_msg *msg) -{ - struct bl_pipe_msg *bl_pipe_msg = container_of(msg, struct bl_pipe_msg, msg); - - if (msg->errno >= 0) - return; - wake_up(bl_pipe_msg->bl_wq); -} - -/* - * Decodes pnfs_block_deviceaddr4 which is XDR encoded in dev->dev_addr_buf. - */ -struct pnfs_block_dev * -nfs4_blk_decode_device(struct nfs_server *server, - struct pnfs_device *dev) -{ - struct pnfs_block_dev *rv; - struct block_device *bd = NULL; - struct bl_pipe_msg bl_pipe_msg; - struct rpc_pipe_msg *msg = &bl_pipe_msg.msg; - struct bl_msg_hdr bl_msg = { - .type = BL_DEVICE_MOUNT, - .totallen = dev->mincount, - }; - uint8_t *dataptr; - DECLARE_WAITQUEUE(wq, current); - int offset, len, i, rc; - 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; - - dprintk("%s CREATING PIPEFS MESSAGE\n", __func__); - dprintk("%s: deviceid: %s, mincount: %d\n", __func__, dev->dev_id.data, - dev->mincount); - - bl_pipe_msg.bl_wq = &nn->bl_wq; - memset(msg, 0, sizeof(*msg)); - msg->data = kzalloc(sizeof(bl_msg) + dev->mincount, GFP_NOFS); - if (!msg->data) { - rv = ERR_PTR(-ENOMEM); - goto out; - } - - memcpy(msg->data, &bl_msg, sizeof(bl_msg)); - dataptr = (uint8_t *) msg->data; - len = dev->mincount; - offset = sizeof(bl_msg); - for (i = 0; len > 0; i++) { - memcpy(&dataptr[offset], page_address(dev->pages[i]), - len < PAGE_CACHE_SIZE ? len : PAGE_CACHE_SIZE); - len -= PAGE_CACHE_SIZE; - offset += PAGE_CACHE_SIZE; - } - msg->len = sizeof(bl_msg) + dev->mincount; - - dprintk("%s CALLING USERSPACE DAEMON\n", __func__); - add_wait_queue(&nn->bl_wq, &wq); - rc = rpc_queue_upcall(nn->bl_device_pipe, msg); - if (rc < 0) { - remove_wait_queue(&nn->bl_wq, &wq); - rv = ERR_PTR(rc); - goto out; - } - - set_current_state(TASK_UNINTERRUPTIBLE); - schedule(); - __set_current_state(TASK_RUNNING); - remove_wait_queue(&nn->bl_wq, &wq); - - if (reply->status != BL_DEVICE_REQUEST_PROC) { - dprintk("%s failed to open device: %d\n", - __func__, reply->status); - rv = ERR_PTR(-EINVAL); - goto out; - } - - bd = blkdev_get_by_dev(MKDEV(reply->major, reply->minor), - FMODE_READ, NULL); - if (IS_ERR(bd)) { - dprintk("%s failed to open device : %ld\n", __func__, - PTR_ERR(bd)); - rv = ERR_CAST(bd); - goto out; - } - - rv = kzalloc(sizeof(*rv), GFP_NOFS); - if (!rv) { - rv = ERR_PTR(-ENOMEM); - goto out; - } - - rv->bm_mdev = bd; - memcpy(&rv->bm_mdevid, &dev->dev_id, sizeof(struct nfs4_deviceid)); - rv->net = net; - dprintk("%s Created device %s with bd_block_size %u\n", - __func__, - bd->bd_disk->disk_name, - bd->bd_block_size); - -out: - kfree(msg->data); - return rv; -} - -/* Map deviceid returned by the server to constructed block_device */ -static struct block_device *translate_devid(struct pnfs_layout_hdr *lo, - struct nfs4_deviceid *id) -{ - struct block_device *rv = NULL; - struct block_mount_id *mid; - struct pnfs_block_dev *dev; - - dprintk("%s enter, lo=%p, id=%p\n", __func__, lo, id); - mid = BLK_ID(lo); - spin_lock(&mid->bm_lock); - list_for_each_entry(dev, &mid->bm_devlist, bm_node) { - if (memcmp(id->data, dev->bm_mdevid.data, - NFS4_DEVICEID4_SIZE) == 0) { - rv = dev->bm_mdev; - goto out; - } - } - out: - spin_unlock(&mid->bm_lock); - dprintk("%s returning %p\n", __func__, rv); - return rv; -} - -/* Tracks info needed to ensure extents in layout obey constraints of spec */ -struct layout_verification { - u32 mode; /* R or RW */ - u64 start; /* Expected start of next non-COW extent */ - u64 inval; /* Start of INVAL coverage */ - u64 cowread; /* End of COW read coverage */ -}; - -/* Verify the extent meets the layout requirements of the pnfs-block draft, - * section 2.3.1. - */ -static int verify_extent(struct pnfs_block_extent *be, - struct layout_verification *lv) -{ - if (lv->mode == IOMODE_READ) { - if (be->be_state == PNFS_BLOCK_READWRITE_DATA || - be->be_state == PNFS_BLOCK_INVALID_DATA) - return -EIO; - if (be->be_f_offset != lv->start) - return -EIO; - lv->start += be->be_length; - return 0; - } - /* lv->mode == IOMODE_RW */ - if (be->be_state == PNFS_BLOCK_READWRITE_DATA) { - if (be->be_f_offset != lv->start) - return -EIO; - if (lv->cowread > lv->start) - return -EIO; - lv->start += be->be_length; - lv->inval = lv->start; - return 0; - } else if (be->be_state == PNFS_BLOCK_INVALID_DATA) { - if (be->be_f_offset != lv->start) - return -EIO; - lv->start += be->be_length; - return 0; - } else if (be->be_state == PNFS_BLOCK_READ_DATA) { - if (be->be_f_offset > lv->start) - return -EIO; - if (be->be_f_offset < lv->inval) - return -EIO; - if (be->be_f_offset < lv->cowread) - return -EIO; - /* It looks like you might want to min this with lv->start, - * but you really don't. - */ - lv->inval = lv->inval + be->be_length; - lv->cowread = be->be_f_offset + be->be_length; - return 0; - } else - return -EIO; -} - -/* XDR decode pnfs_block_layout4 structure */ -int -nfs4_blk_process_layoutget(struct pnfs_layout_hdr *lo, - struct nfs4_layoutget_res *lgr, gfp_t gfp_flags) -{ - struct pnfs_block_layout *bl = BLK_LO2EXT(lo); - int i, status = -EIO; - uint32_t count; - struct pnfs_block_extent *be = NULL, *save; - struct xdr_stream stream; - struct xdr_buf buf; - struct page *scratch; - __be32 *p; - struct layout_verification lv = { - .mode = lgr->range.iomode, - .start = lgr->range.offset >> SECTOR_SHIFT, - .inval = lgr->range.offset >> SECTOR_SHIFT, - .cowread = lgr->range.offset >> SECTOR_SHIFT, - }; - LIST_HEAD(extents); - - dprintk("---> %s\n", __func__); - - scratch = alloc_page(gfp_flags); - if (!scratch) - return -ENOMEM; - - xdr_init_decode_pages(&stream, &buf, lgr->layoutp->pages, lgr->layoutp->len); - xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE); - - p = xdr_inline_decode(&stream, 4); - if (unlikely(!p)) - goto out_err; - - count = be32_to_cpup(p++); - - dprintk("%s enter, number of extents %i\n", __func__, count); - p = xdr_inline_decode(&stream, (28 + NFS4_DEVICEID4_SIZE) * count); - if (unlikely(!p)) - goto out_err; - - /* Decode individual extents, putting them in temporary - * staging area until whole layout is decoded to make error - * recovery easier. - */ - for (i = 0; i < count; i++) { - be = bl_alloc_extent(); - if (!be) { - status = -ENOMEM; - goto out_err; - } - memcpy(&be->be_devid, p, NFS4_DEVICEID4_SIZE); - p += XDR_QUADLEN(NFS4_DEVICEID4_SIZE); - be->be_mdev = translate_devid(lo, &be->be_devid); - if (!be->be_mdev) - goto out_err; - - /* The next three values are read in as bytes, - * but stored as 512-byte sector lengths - */ - if (decode_sector_number(&p, &be->be_f_offset) < 0) - goto out_err; - if (decode_sector_number(&p, &be->be_length) < 0) - goto out_err; - if (decode_sector_number(&p, &be->be_v_offset) < 0) - goto out_err; - be->be_state = be32_to_cpup(p++); - if (be->be_state == PNFS_BLOCK_INVALID_DATA) - be->be_inval = &bl->bl_inval; - if (verify_extent(be, &lv)) { - dprintk("%s verify failed\n", __func__); - goto out_err; - } - list_add_tail(&be->be_node, &extents); - } - if (lgr->range.offset + lgr->range.length != - lv.start << SECTOR_SHIFT) { - dprintk("%s Final length mismatch\n", __func__); - be = NULL; - goto out_err; - } - if (lv.start < lv.cowread) { - dprintk("%s Final uncovered COW extent\n", __func__); - be = NULL; - goto out_err; - } - /* Extents decoded properly, now try to merge them in to - * existing layout extents. - */ - spin_lock(&bl->bl_ext_lock); - list_for_each_entry_safe(be, save, &extents, be_node) { - list_del(&be->be_node); - status = bl_add_merge_extent(bl, be); - if (status) { - spin_unlock(&bl->bl_ext_lock); - /* This is a fairly catastrophic error, as the - * entire layout extent lists are now corrupted. - * We should have some way to distinguish this. - */ - be = NULL; - goto out_err; - } - } - spin_unlock(&bl->bl_ext_lock); - status = 0; - out: - __free_page(scratch); - dprintk("%s returns %i\n", __func__, status); - return status; - - out_err: - bl_put_extent(be); - while (!list_empty(&extents)) { - be = list_first_entry(&extents, struct pnfs_block_extent, - be_node); - list_del(&be->be_node); - bl_put_extent(be); - } - goto out; -} diff --git a/fs/nfs/blocklayout/blocklayoutdm.c b/fs/nfs/blocklayout/blocklayoutdm.c deleted file mode 100644 index 8999cfddd866..000000000000 --- a/fs/nfs/blocklayout/blocklayoutdm.c +++ /dev/null @@ -1,108 +0,0 @@ -/* - * linux/fs/nfs/blocklayout/blocklayoutdm.c - * - * Module for the NFSv4.1 pNFS block layout driver. - * - * Copyright (c) 2007 The Regents of the University of Michigan. - * All rights reserved. - * - * Fred Isaman <iisaman@umich.edu> - * Andy Adamson <andros@citi.umich.edu> - * - * permission is granted to use, copy, create derivative works and - * redistribute this software and such derivative works for any purpose, - * so long as the name of the university of michigan is not used in - * any advertising or publicity pertaining to the use or distribution - * of this software without specific, written prior authorization. if - * the above copyright notice or any other identification of the - * university of michigan is included in any copy of any portion of - * this software, then the disclaimer below must also be included. - * - * this software is provided as is, without representation from the - * university of michigan as to its fitness for any purpose, and without - * warranty by the university of michigan of any kind, either express - * or implied, including without limitation the implied warranties of - * merchantability and fitness for a particular purpose. the regents - * of the university of michigan shall not be liable for any damages, - * including special, indirect, incidental, or consequential damages, - * with respect to any claim arising out or in connection with the use - * of the software, even if it has been or is hereafter advised of the - * possibility of such damages. - */ - -#include <linux/genhd.h> /* gendisk - used in a dprintk*/ -#include <linux/sched.h> -#include <linux/hash.h> - -#include "blocklayout.h" - -#define NFSDBG_FACILITY NFSDBG_PNFS_LD - -static void dev_remove(struct net *net, dev_t dev) -{ - struct bl_pipe_msg bl_pipe_msg; - struct rpc_pipe_msg *msg = &bl_pipe_msg.msg; - struct bl_dev_msg bl_umount_request; - struct bl_msg_hdr bl_msg = { - .type = BL_DEVICE_UMOUNT, - .totallen = sizeof(bl_umount_request), - }; - uint8_t *dataptr; - DECLARE_WAITQUEUE(wq, current); - struct nfs_net *nn = net_generic(net, nfs_net_id); - - dprintk("Entering %s\n", __func__); - - bl_pipe_msg.bl_wq = &nn->bl_wq; - memset(msg, 0, sizeof(*msg)); - msg->len = sizeof(bl_msg) + bl_msg.totallen; - msg->data = kzalloc(msg->len, GFP_NOFS); - if (!msg->data) - goto out; - - memset(&bl_umount_request, 0, sizeof(bl_umount_request)); - bl_umount_request.major = MAJOR(dev); - bl_umount_request.minor = MINOR(dev); - - memcpy(msg->data, &bl_msg, sizeof(bl_msg)); - dataptr = (uint8_t *) msg->data; - memcpy(&dataptr[sizeof(bl_msg)], &bl_umount_request, sizeof(bl_umount_request)); - - add_wait_queue(&nn->bl_wq, &wq); - if (rpc_queue_upcall(nn->bl_device_pipe, msg) < 0) { - remove_wait_queue(&nn->bl_wq, &wq); - goto out; - } - - set_current_state(TASK_UNINTERRUPTIBLE); - schedule(); - __set_current_state(TASK_RUNNING); - remove_wait_queue(&nn->bl_wq, &wq); - -out: - kfree(msg->data); -} - -/* - * Release meta device - */ -static void nfs4_blk_metadev_release(struct pnfs_block_dev *bdev) -{ - dprintk("%s Releasing\n", __func__); - nfs4_blkdev_put(bdev->bm_mdev); - dev_remove(bdev->net, bdev->bm_mdev->bd_dev); -} - -void bl_free_block_dev(struct pnfs_block_dev *bdev) -{ - if (bdev) { - if (bdev->bm_mdev) { - dprintk("%s Removing DM device: %d:%d\n", - __func__, - MAJOR(bdev->bm_mdev->bd_dev), - MINOR(bdev->bm_mdev->bd_dev)); - nfs4_blk_metadev_release(bdev); - } - kfree(bdev); - } -} diff --git a/fs/nfs/blocklayout/dev.c b/fs/nfs/blocklayout/dev.c new file mode 100644 index 000000000000..5aed4f98df41 --- /dev/null +++ b/fs/nfs/blocklayout/dev.c @@ -0,0 +1,363 @@ +/* + * Copyright (c) 2014 Christoph Hellwig. + */ +#include <linux/sunrpc/svc.h> +#include <linux/blkdev.h> +#include <linux/nfs4.h> +#include <linux/nfs_fs.h> +#include <linux/nfs_xdr.h> + +#include "blocklayout.h" + +#define NFSDBG_FACILITY NFSDBG_PNFS_LD + +static void +bl_free_device(struct pnfs_block_dev *dev) +{ + if (dev->nr_children) { + int i; + + for (i = 0; i < dev->nr_children; i++) + bl_free_device(&dev->children[i]); + kfree(dev->children); + } else { + if (dev->bdev) + blkdev_put(dev->bdev, FMODE_READ); + } +} + +void +bl_free_deviceid_node(struct nfs4_deviceid_node *d) +{ + struct pnfs_block_dev *dev = + container_of(d, struct pnfs_block_dev, node); + + bl_free_device(dev); + kfree(dev); +} + +static int +nfs4_block_decode_volume(struct xdr_stream *xdr, struct pnfs_block_volume *b) +{ + __be32 *p; + int i; + + p = xdr_inline_decode(xdr, 4); + if (!p) + return -EIO; + b->type = be32_to_cpup(p++); + + switch (b->type) { + case PNFS_BLOCK_VOLUME_SIMPLE: + p = xdr_inline_decode(xdr, 4); + if (!p) + return -EIO; + b->simple.nr_sigs = be32_to_cpup(p++); + if (!b->simple.nr_sigs) { + dprintk("no signature\n"); + return -EIO; + } + + b->simple.len = 4 + 4; + for (i = 0; i < b->simple.nr_sigs; i++) { + p = xdr_inline_decode(xdr, 8 + 4); + if (!p) + return -EIO; + p = xdr_decode_hyper(p, &b->simple.sigs[i].offset); + b->simple.sigs[i].sig_len = be32_to_cpup(p++); + + p = xdr_inline_decode(xdr, b->simple.sigs[i].sig_len); + if (!p) + return -EIO; + memcpy(&b->simple.sigs[i].sig, p, + b->simple.sigs[i].sig_len); + + b->simple.len += 8 + 4 + b->simple.sigs[i].sig_len; + } + break; + case PNFS_BLOCK_VOLUME_SLICE: + p = xdr_inline_decode(xdr, 8 + 8 + 4); + if (!p) + return -EIO; + p = xdr_decode_hyper(p, &b->slice.start); + p = xdr_decode_hyper(p, &b->slice.len); + b->slice.volume = be32_to_cpup(p++); + break; + case PNFS_BLOCK_VOLUME_CONCAT: + p = xdr_inline_decode(xdr, 4); + if (!p) + return -EIO; + b->concat.volumes_count = be32_to_cpup(p++); + + p = xdr_inline_decode(xdr, b->concat.volumes_count * 4); + if (!p) + return -EIO; + for (i = 0; i < b->concat.volumes_count; i++) + b->concat.volumes[i] = be32_to_cpup(p++); + break; + case PNFS_BLOCK_VOLUME_STRIPE: + p = xdr_inline_decode(xdr, 8 + 4); + if (!p) + return -EIO; + p = xdr_decode_hyper(p, &b->stripe.chunk_size); + b->stripe.volumes_count = be32_to_cpup(p++); + + p = xdr_inline_decode(xdr, b->stripe.volumes_count * 4); + if (!p) + return -EIO; + for (i = 0; i < b->stripe.volumes_count; i++) + b->stripe.volumes[i] = be32_to_cpup(p++); + break; + default: + dprintk("unknown volume type!\n"); + return -EIO; + } + + return 0; +} + +static bool bl_map_simple(struct pnfs_block_dev *dev, u64 offset, + struct pnfs_block_dev_map *map) +{ + map->start = dev->start; + map->len = dev->len; + map->disk_offset = dev->disk_offset; + map->bdev = dev->bdev; + return true; +} + +static bool bl_map_concat(struct pnfs_block_dev *dev, u64 offset, + struct pnfs_block_dev_map *map) +{ + int i; + + for (i = 0; i < dev->nr_children; i++) { + struct pnfs_block_dev *child = &dev->children[i]; + + if (child->start > offset || + child->start + child->len <= offset) + continue; + + child->map(child, offset - child->start, map); + return true; + } + + dprintk("%s: ran off loop!\n", __func__); + return false; +} + +static bool bl_map_stripe(struct pnfs_block_dev *dev, u64 offset, + struct pnfs_block_dev_map *map) +{ + struct pnfs_block_dev *child; + u64 chunk; + u32 chunk_idx; + u64 disk_offset; + + chunk = div_u64(offset, dev->chunk_size); + div_u64_rem(chunk, dev->nr_children, &chunk_idx); + + if (chunk_idx > dev->nr_children) { + dprintk("%s: invalid chunk idx %d (%lld/%lld)\n", + __func__, chunk_idx, offset, dev->chunk_size); + /* error, should not happen */ + return false; + } + + /* truncate offset to the beginning of the stripe */ + offset = chunk * dev->chunk_size; + + /* disk offset of the stripe */ + disk_offset = div_u64(offset, dev->nr_children); + + child = &dev->children[chunk_idx]; + child->map(child, disk_offset, map); + + map->start += offset; + map->disk_offset += disk_offset; + map->len = dev->chunk_size; + return true; +} + +static int +bl_parse_deviceid(struct nfs_server *server, struct pnfs_block_dev *d, + struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask); + + +static int +bl_parse_simple(struct nfs_server *server, struct pnfs_block_dev *d, + struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask) +{ + struct pnfs_block_volume *v = &volumes[idx]; + dev_t dev; + + dev = bl_resolve_deviceid(server, v, gfp_mask); + if (!dev) + return -EIO; + + d->bdev = blkdev_get_by_dev(dev, FMODE_READ, NULL); + if (IS_ERR(d->bdev)) { + printk(KERN_WARNING "pNFS: failed to open device %d:%d (%ld)\n", + MAJOR(dev), MINOR(dev), PTR_ERR(d->bdev)); + return PTR_ERR(d->bdev); + } + + + d->len = i_size_read(d->bdev->bd_inode); + d->map = bl_map_simple; + + printk(KERN_INFO "pNFS: using block device %s\n", + d->bdev->bd_disk->disk_name); + return 0; +} + +static int +bl_parse_slice(struct nfs_server *server, struct pnfs_block_dev *d, + struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask) +{ + struct pnfs_block_volume *v = &volumes[idx]; + int ret; + + ret = bl_parse_deviceid(server, d, volumes, v->slice.volume, gfp_mask); + if (ret) + return ret; + + d->disk_offset = v->slice.start; + d->len = v->slice.len; + return 0; +} + +static int +bl_parse_concat(struct nfs_server *server, struct pnfs_block_dev *d, + struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask) +{ + struct pnfs_block_volume *v = &volumes[idx]; + u64 len = 0; + int ret, i; + + d->children = kcalloc(v->concat.volumes_count, + sizeof(struct pnfs_block_dev), GFP_KERNEL); + if (!d->children) + return -ENOMEM; + + for (i = 0; i < v->concat.volumes_count; i++) { + ret = bl_parse_deviceid(server, &d->children[i], + volumes, v->concat.volumes[i], gfp_mask); + if (ret) + return ret; + + d->nr_children++; + d->children[i].start += len; + len += d->children[i].len; + } + + d->len = len; + d->map = bl_map_concat; + return 0; +} + +static int +bl_parse_stripe(struct nfs_server *server, struct pnfs_block_dev *d, + struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask) +{ + struct pnfs_block_volume *v = &volumes[idx]; + u64 len = 0; + int ret, i; + + d->children = kcalloc(v->stripe.volumes_count, + sizeof(struct pnfs_block_dev), GFP_KERNEL); + if (!d->children) + return -ENOMEM; + + for (i = 0; i < v->stripe.volumes_count; i++) { + ret = bl_parse_deviceid(server, &d->children[i], + volumes, v->stripe.volumes[i], gfp_mask); + if (ret) + return ret; + + d->nr_children++; + len += d->children[i].len; + } + + d->len = len; + d->chunk_size = v->stripe.chunk_size; + d->map = bl_map_stripe; + return 0; +} + +static int +bl_parse_deviceid(struct nfs_server *server, struct pnfs_block_dev *d, + struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask) +{ + switch (volumes[idx].type) { + case PNFS_BLOCK_VOLUME_SIMPLE: + return bl_parse_simple(server, d, volumes, idx, gfp_mask); + case PNFS_BLOCK_VOLUME_SLICE: + return bl_parse_slice(server, d, volumes, idx, gfp_mask); + case PNFS_BLOCK_VOLUME_CONCAT: + return bl_parse_concat(server, d, volumes, idx, gfp_mask); + case PNFS_BLOCK_VOLUME_STRIPE: + return bl_parse_stripe(server, d, volumes, idx, gfp_mask); + default: + dprintk("unsupported volume type: %d\n", volumes[idx].type); + return -EIO; + } +} + +struct nfs4_deviceid_node * +bl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, + gfp_t gfp_mask) +{ + struct nfs4_deviceid_node *node = NULL; + struct pnfs_block_volume *volumes; + struct pnfs_block_dev *top; + struct xdr_stream xdr; + struct xdr_buf buf; + struct page *scratch; + int nr_volumes, ret, i; + __be32 *p; + + scratch = alloc_page(gfp_mask); + if (!scratch) + goto out; + + xdr_init_decode_pages(&xdr, &buf, pdev->pages, pdev->pglen); + xdr_set_scratch_buffer(&xdr, page_address(scratch), PAGE_SIZE); + + p = xdr_inline_decode(&xdr, sizeof(__be32)); + if (!p) + goto out_free_scratch; + nr_volumes = be32_to_cpup(p++); + + volumes = kcalloc(nr_volumes, sizeof(struct pnfs_block_volume), + gfp_mask); + if (!volumes) + goto out_free_scratch; + + for (i = 0; i < nr_volumes; i++) { + ret = nfs4_block_decode_volume(&xdr, &volumes[i]); + if (ret < 0) + goto out_free_volumes; + } + + top = kzalloc(sizeof(*top), gfp_mask); + if (!top) + goto out_free_volumes; + + ret = bl_parse_deviceid(server, top, volumes, nr_volumes - 1, gfp_mask); + if (ret) { + bl_free_device(top); + kfree(top); + goto out_free_volumes; + } + + node = &top->node; + nfs4_init_deviceid_node(node, server, &pdev->dev_id); + +out_free_volumes: + kfree(volumes); +out_free_scratch: + __free_page(scratch); +out: + return node; +} diff --git a/fs/nfs/blocklayout/extent_tree.c b/fs/nfs/blocklayout/extent_tree.c new file mode 100644 index 000000000000..31d0b5e53dfd --- /dev/null +++ b/fs/nfs/blocklayout/extent_tree.c @@ -0,0 +1,602 @@ +/* + * Copyright (c) 2014 Christoph Hellwig. + */ + +#include <linux/vmalloc.h> + +#include "blocklayout.h" + +#define NFSDBG_FACILITY NFSDBG_PNFS_LD + +static inline struct pnfs_block_extent * +ext_node(struct rb_node *node) +{ + return rb_entry(node, struct pnfs_block_extent, be_node); +} + +static struct pnfs_block_extent * +ext_tree_first(struct rb_root *root) +{ + struct rb_node *node = rb_first(root); + return node ? ext_node(node) : NULL; +} + +static struct pnfs_block_extent * +ext_tree_prev(struct pnfs_block_extent *be) +{ + struct rb_node *node = rb_prev(&be->be_node); + return node ? ext_node(node) : NULL; +} + +static struct pnfs_block_extent * +ext_tree_next(struct pnfs_block_extent *be) +{ + struct rb_node *node = rb_next(&be->be_node); + return node ? ext_node(node) : NULL; +} + +static inline sector_t +ext_f_end(struct pnfs_block_extent *be) +{ + return be->be_f_offset + be->be_length; +} + +static struct pnfs_block_extent * +__ext_tree_search(struct rb_root *root, sector_t start) +{ + struct rb_node *node = root->rb_node; + struct pnfs_block_extent *be = NULL; + + while (node) { + be = ext_node(node); + if (start < be->be_f_offset) + node = node->rb_left; + else if (start >= ext_f_end(be)) + node = node->rb_right; + else + return be; + } + + if (be) { + if (start < be->be_f_offset) + return be; + + if (start >= ext_f_end(be)) + return ext_tree_next(be); + } + + return NULL; +} + +static bool +ext_can_merge(struct pnfs_block_extent *be1, struct pnfs_block_extent *be2) +{ + if (be1->be_state != be2->be_state) + return false; + if (be1->be_device != be2->be_device) + return false; + + if (be1->be_f_offset + be1->be_length != be2->be_f_offset) + return false; + + if (be1->be_state != PNFS_BLOCK_NONE_DATA && + (be1->be_v_offset + be1->be_length != be2->be_v_offset)) + return false; + + if (be1->be_state == PNFS_BLOCK_INVALID_DATA && + be1->be_tag != be2->be_tag) + return false; + + return true; +} + +static struct pnfs_block_extent * +ext_try_to_merge_left(struct rb_root *root, struct pnfs_block_extent *be) +{ + struct pnfs_block_extent *left = ext_tree_prev(be); + + if (left && ext_can_merge(left, be)) { + left->be_length += be->be_length; + rb_erase(&be->be_node, root); + nfs4_put_deviceid_node(be->be_device); + kfree(be); + return left; + } + + return be; +} + +static struct pnfs_block_extent * +ext_try_to_merge_right(struct rb_root *root, struct pnfs_block_extent *be) +{ + struct pnfs_block_extent *right = ext_tree_next(be); + + if (right && ext_can_merge(be, right)) { + be->be_length += right->be_length; + rb_erase(&right->be_node, root); + nfs4_put_deviceid_node(right->be_device); + kfree(right); + } + + return be; +} + +static void +__ext_tree_insert(struct rb_root *root, + struct pnfs_block_extent *new, bool merge_ok) +{ + struct rb_node **p = &root->rb_node, *parent = NULL; + struct pnfs_block_extent *be; + + while (*p) { + parent = *p; + be = ext_node(parent); + + if (new->be_f_offset < be->be_f_offset) { + if (merge_ok && ext_can_merge(new, be)) { + be->be_f_offset = new->be_f_offset; + if (be->be_state != PNFS_BLOCK_NONE_DATA) + be->be_v_offset = new->be_v_offset; + be->be_length += new->be_length; + be = ext_try_to_merge_left(root, be); + goto free_new; + } + p = &(*p)->rb_left; + } else if (new->be_f_offset >= ext_f_end(be)) { + if (merge_ok && ext_can_merge(be, new)) { + be->be_length += new->be_length; + be = ext_try_to_merge_right(root, be); + goto free_new; + } + p = &(*p)->rb_right; + } else { + BUG(); + } + } + + rb_link_node(&new->be_node, parent, p); + rb_insert_color(&new->be_node, root); + return; +free_new: + nfs4_put_deviceid_node(new->be_device); + kfree(new); +} + +static int +__ext_tree_remove(struct rb_root *root, sector_t start, sector_t end) +{ + struct pnfs_block_extent *be; + sector_t len1 = 0, len2 = 0; + sector_t orig_v_offset; + sector_t orig_len; + + be = __ext_tree_search(root, start); + if (!be) + return 0; + if (be->be_f_offset >= end) + return 0; + + orig_v_offset = be->be_v_offset; + orig_len = be->be_length; + + if (start > be->be_f_offset) + len1 = start - be->be_f_offset; + if (ext_f_end(be) > end) + len2 = ext_f_end(be) - end; + + if (len2 > 0) { + if (len1 > 0) { + struct pnfs_block_extent *new; + + new = kzalloc(sizeof(*new), GFP_ATOMIC); + if (!new) + return -ENOMEM; + + be->be_length = len1; + + new->be_f_offset = end; + if (be->be_state != PNFS_BLOCK_NONE_DATA) { + new->be_v_offset = + orig_v_offset + orig_len - len2; + } + new->be_length = len2; + new->be_state = be->be_state; + new->be_tag = be->be_tag; + new->be_device = nfs4_get_deviceid(be->be_device); + + __ext_tree_insert(root, new, true); + } else { + be->be_f_offset = end; + if (be->be_state != PNFS_BLOCK_NONE_DATA) { + be->be_v_offset = + orig_v_offset + orig_len - len2; + } + be->be_length = len2; + } + } else { + if (len1 > 0) { + be->be_length = len1; + be = ext_tree_next(be); + } + + while (be && ext_f_end(be) <= end) { + struct pnfs_block_extent *next = ext_tree_next(be); + + rb_erase(&be->be_node, root); + nfs4_put_deviceid_node(be->be_device); + kfree(be); + be = next; + } + + if (be && be->be_f_offset < end) { + len1 = ext_f_end(be) - end; + be->be_f_offset = end; + if (be->be_state != PNFS_BLOCK_NONE_DATA) + be->be_v_offset += be->be_length - len1; + be->be_length = len1; + } + } + + return 0; +} + +int +ext_tree_insert(struct pnfs_block_layout *bl, struct pnfs_block_extent *new) +{ + struct pnfs_block_extent *be; + struct rb_root *root; + int err = 0; + + switch (new->be_state) { + case PNFS_BLOCK_READWRITE_DATA: + case PNFS_BLOCK_INVALID_DATA: + root = &bl->bl_ext_rw; + break; + case PNFS_BLOCK_READ_DATA: + case PNFS_BLOCK_NONE_DATA: + root = &bl->bl_ext_ro; + break; + default: + dprintk("invalid extent type\n"); + return -EINVAL; + } + + spin_lock(&bl->bl_ext_lock); +retry: + be = __ext_tree_search(root, new->be_f_offset); + if (!be || be->be_f_offset >= ext_f_end(new)) { + __ext_tree_insert(root, new, true); + } else if (new->be_f_offset >= be->be_f_offset) { + if (ext_f_end(new) <= ext_f_end(be)) { + nfs4_put_deviceid_node(new->be_device); + kfree(new); + } else { + sector_t new_len = ext_f_end(new) - ext_f_end(be); + sector_t diff = new->be_length - new_len; + + new->be_f_offset += diff; + new->be_v_offset += diff; + new->be_length = new_len; + goto retry; + } + } else if (ext_f_end(new) <= ext_f_end(be)) { + new->be_length = be->be_f_offset - new->be_f_offset; + __ext_tree_insert(root, new, true); + } else { + struct pnfs_block_extent *split; + sector_t new_len = ext_f_end(new) - ext_f_end(be); + sector_t diff = new->be_length - new_len; + + split = kmemdup(new, sizeof(*new), GFP_ATOMIC); + if (!split) { + err = -EINVAL; + goto out; + } + + split->be_length = be->be_f_offset - split->be_f_offset; + split->be_device = nfs4_get_deviceid(new->be_device); + __ext_tree_insert(root, split, true); + + new->be_f_offset += diff; + new->be_v_offset += diff; + new->be_length = new_len; + goto retry; + } +out: + spin_unlock(&bl->bl_ext_lock); + return err; +} + +static bool +__ext_tree_lookup(struct rb_root *root, sector_t isect, + struct pnfs_block_extent *ret) +{ + struct rb_node *node; + struct pnfs_block_extent *be; + + node = root->rb_node; + while (node) { + be = ext_node(node); + if (isect < be->be_f_offset) + node = node->rb_left; + else if (isect >= ext_f_end(be)) + node = node->rb_right; + else { + *ret = *be; + return true; + } + } + + return false; +} + +bool +ext_tree_lookup(struct pnfs_block_layout *bl, sector_t isect, + struct pnfs_block_extent *ret, bool rw) +{ + bool found = false; + + spin_lock(&bl->bl_ext_lock); + if (!rw) + found = __ext_tree_lookup(&bl->bl_ext_ro, isect, ret); + if (!found) + found = __ext_tree_lookup(&bl->bl_ext_rw, isect, ret); + spin_unlock(&bl->bl_ext_lock); + + return found; +} + +int ext_tree_remove(struct pnfs_block_layout *bl, bool rw, + sector_t start, sector_t end) +{ + int err, err2; + + spin_lock(&bl->bl_ext_lock); + err = __ext_tree_remove(&bl->bl_ext_ro, start, end); + if (rw) { + err2 = __ext_tree_remove(&bl->bl_ext_rw, start, end); + if (!err) + err = err2; + } + spin_unlock(&bl->bl_ext_lock); + + return err; +} + +static int +ext_tree_split(struct rb_root *root, struct pnfs_block_extent *be, + sector_t split) +{ + struct pnfs_block_extent *new; + sector_t orig_len = be->be_length; + + new = kzalloc(sizeof(*new), GFP_ATOMIC); + if (!new) + return -ENOMEM; + + be->be_length = split - be->be_f_offset; + + new->be_f_offset = split; + if (be->be_state != PNFS_BLOCK_NONE_DATA) + new->be_v_offset = be->be_v_offset + be->be_length; + new->be_length = orig_len - be->be_length; + new->be_state = be->be_state; + new->be_tag = be->be_tag; + new->be_device = nfs4_get_deviceid(be->be_device); + + __ext_tree_insert(root, new, false); + return 0; +} + +int +ext_tree_mark_written(struct pnfs_block_layout *bl, sector_t start, + sector_t len) +{ + struct rb_root *root = &bl->bl_ext_rw; + sector_t end = start + len; + struct pnfs_block_extent *be; + int err = 0; + + spin_lock(&bl->bl_ext_lock); + /* + * First remove all COW extents or holes from written to range. + */ + err = __ext_tree_remove(&bl->bl_ext_ro, start, end); + if (err) + goto out; + + /* + * Then mark all invalid extents in the range as written to. + */ + for (be = __ext_tree_search(root, start); be; be = ext_tree_next(be)) { + if (be->be_f_offset >= end) + break; + + if (be->be_state != PNFS_BLOCK_INVALID_DATA || be->be_tag) + continue; + + if (be->be_f_offset < start) { + struct pnfs_block_extent *left = ext_tree_prev(be); + + if (left && ext_can_merge(left, be)) { + sector_t diff = start - be->be_f_offset; + + left->be_length += diff; + + be->be_f_offset += diff; + be->be_v_offset += diff; + be->be_length -= diff; + } else { + err = ext_tree_split(root, be, start); + if (err) + goto out; + } + } + + if (ext_f_end(be) > end) { + struct pnfs_block_extent *right = ext_tree_next(be); + + if (right && ext_can_merge(be, right)) { + sector_t diff = end - be->be_f_offset; + + be->be_length -= diff; + + right->be_f_offset -= diff; + right->be_v_offset -= diff; + right->be_length += diff; + } else { + err = ext_tree_split(root, be, end); + if (err) + goto out; + } + } + + if (be->be_f_offset >= start && ext_f_end(be) <= end) { + be->be_tag = EXTENT_WRITTEN; + be = ext_try_to_merge_left(root, be); + be = ext_try_to_merge_right(root, be); + } + } +out: + spin_unlock(&bl->bl_ext_lock); + return err; +} + +static void ext_tree_free_commitdata(struct nfs4_layoutcommit_args *arg, + size_t buffer_size) +{ + if (arg->layoutupdate_pages != &arg->layoutupdate_page) { + int nr_pages = DIV_ROUND_UP(buffer_size, PAGE_SIZE), i; + + for (i = 0; i < nr_pages; i++) + put_page(arg->layoutupdate_pages[i]); + kfree(arg->layoutupdate_pages); + } else { + put_page(arg->layoutupdate_page); + } +} + +static int ext_tree_encode_commit(struct pnfs_block_layout *bl, __be32 *p, + size_t buffer_size, size_t *count) +{ + struct pnfs_block_extent *be; + int ret = 0; + + spin_lock(&bl->bl_ext_lock); + for (be = ext_tree_first(&bl->bl_ext_rw); be; be = ext_tree_next(be)) { + if (be->be_state != PNFS_BLOCK_INVALID_DATA || + be->be_tag != EXTENT_WRITTEN) + continue; + + (*count)++; + if (*count * BL_EXTENT_SIZE > buffer_size) { + /* keep counting.. */ + ret = -ENOSPC; + continue; + } + + p = xdr_encode_opaque_fixed(p, be->be_device->deviceid.data, + NFS4_DEVICEID4_SIZE); + p = xdr_encode_hyper(p, be->be_f_offset << SECTOR_SHIFT); + p = xdr_encode_hyper(p, be->be_length << SECTOR_SHIFT); + p = xdr_encode_hyper(p, 0LL); + *p++ = cpu_to_be32(PNFS_BLOCK_READWRITE_DATA); + + be->be_tag = EXTENT_COMMITTING; + } + spin_unlock(&bl->bl_ext_lock); + + return ret; +} + +int +ext_tree_prepare_commit(struct nfs4_layoutcommit_args *arg) +{ + struct pnfs_block_layout *bl = BLK_LO2EXT(NFS_I(arg->inode)->layout); + size_t count = 0, buffer_size = PAGE_SIZE; + __be32 *start_p; + int ret; + + dprintk("%s enter\n", __func__); + + arg->layoutupdate_page = alloc_page(GFP_NOFS); + if (!arg->layoutupdate_page) + return -ENOMEM; + start_p = page_address(arg->layoutupdate_page); + arg->layoutupdate_pages = &arg->layoutupdate_page; + +retry: + ret = ext_tree_encode_commit(bl, start_p + 1, buffer_size, &count); + if (unlikely(ret)) { + ext_tree_free_commitdata(arg, buffer_size); + + buffer_size = sizeof(__be32) + BL_EXTENT_SIZE * count; + count = 0; + + arg->layoutupdate_pages = + kcalloc(DIV_ROUND_UP(buffer_size, PAGE_SIZE), + sizeof(struct page *), GFP_NOFS); + if (!arg->layoutupdate_pages) + return -ENOMEM; + + start_p = __vmalloc(buffer_size, GFP_NOFS, PAGE_KERNEL); + if (!start_p) { + kfree(arg->layoutupdate_pages); + return -ENOMEM; + } + + goto retry; + } + + *start_p = cpu_to_be32(count); + arg->layoutupdate_len = sizeof(__be32) + BL_EXTENT_SIZE * count; + + if (unlikely(arg->layoutupdate_pages != &arg->layoutupdate_page)) { + __be32 *p = start_p; + int i = 0; + + for (p = start_p; + p < start_p + arg->layoutupdate_len; + p += PAGE_SIZE) { + arg->layoutupdate_pages[i++] = vmalloc_to_page(p); + } + } + + dprintk("%s found %zu ranges\n", __func__, count); + return 0; +} + +void +ext_tree_mark_committed(struct nfs4_layoutcommit_args *arg, int status) +{ + struct pnfs_block_layout *bl = BLK_LO2EXT(NFS_I(arg->inode)->layout); + struct rb_root *root = &bl->bl_ext_rw; + struct pnfs_block_extent *be; + + dprintk("%s status %d\n", __func__, status); + + ext_tree_free_commitdata(arg, arg->layoutupdate_len); + + spin_lock(&bl->bl_ext_lock); + for (be = ext_tree_first(root); be; be = ext_tree_next(be)) { + if (be->be_state != PNFS_BLOCK_INVALID_DATA || + be->be_tag != EXTENT_COMMITTING) + continue; + + if (status) { + /* + * Mark as written and try again. + * + * XXX: some real error handling here wouldn't hurt.. + */ + be->be_tag = EXTENT_WRITTEN; + } else { + be->be_state = PNFS_BLOCK_READWRITE_DATA; + be->be_tag = 0; + } + + be = ext_try_to_merge_left(root, be); + be = ext_try_to_merge_right(root, be); + } + spin_unlock(&bl->bl_ext_lock); +} diff --git a/fs/nfs/blocklayout/extents.c b/fs/nfs/blocklayout/extents.c deleted file mode 100644 index 4d0161442565..000000000000 --- a/fs/nfs/blocklayout/extents.c +++ /dev/null @@ -1,908 +0,0 @@ -/* - * linux/fs/nfs/blocklayout/blocklayout.h - * - * Module for the NFSv4.1 pNFS block layout driver. - * - * Copyright (c) 2006 The Regents of the University of Michigan. - * All rights reserved. - * - * Andy Adamson <andros@citi.umich.edu> - * Fred Isaman <iisaman@umich.edu> - * - * permission is granted to use, copy, create derivative works and - * redistribute this software and such derivative works for any purpose, - * so long as the name of the university of michigan is not used in - * any advertising or publicity pertaining to the use or distribution - * of this software without specific, written prior authorization. if - * the above copyright notice or any other identification of the - * university of michigan is included in any copy of any portion of - * this software, then the disclaimer below must also be included. - * - * this software is provided as is, without representation from the - * university of michigan as to its fitness for any purpose, and without - * warranty by the university of michigan of any kind, either express - * or implied, including without limitation the implied warranties of - * merchantability and fitness for a particular purpose. the regents - * of the university of michigan shall not be liable for any damages, - * including special, indirect, incidental, or consequential damages, - * with respect to any claim arising out or in connection with the use - * of the software, even if it has been or is hereafter advised of the - * possibility of such damages. - */ - -#include "blocklayout.h" -#define NFSDBG_FACILITY NFSDBG_PNFS_LD - -/* Bit numbers */ -#define EXTENT_INITIALIZED 0 -#define EXTENT_WRITTEN 1 -#define EXTENT_IN_COMMIT 2 -#define INTERNAL_EXISTS MY_MAX_TAGS -#define INTERNAL_MASK ((1 << INTERNAL_EXISTS) - 1) - -/* Returns largest t<=s s.t. t%base==0 */ -static inline sector_t normalize(sector_t s, int base) -{ - sector_t tmp = s; /* Since do_div modifies its argument */ - return s - sector_div(tmp, base); -} - -static inline sector_t normalize_up(sector_t s, int base) -{ - return normalize(s + base - 1, base); -} - -/* Complete stub using list while determine API wanted */ - -/* Returns tags, or negative */ -static int32_t _find_entry(struct my_tree *tree, u64 s) -{ - struct pnfs_inval_tracking *pos; - - dprintk("%s(%llu) enter\n", __func__, s); - list_for_each_entry_reverse(pos, &tree->mtt_stub, it_link) { - if (pos->it_sector > s) - continue; - else if (pos->it_sector == s) - return pos->it_tags & INTERNAL_MASK; - else - break; - } - return -ENOENT; -} - -static inline -int _has_tag(struct my_tree *tree, u64 s, int32_t tag) -{ - int32_t tags; - - dprintk("%s(%llu, %i) enter\n", __func__, s, tag); - s = normalize(s, tree->mtt_step_size); - tags = _find_entry(tree, s); - if ((tags < 0) || !(tags & (1 << tag))) - return 0; - else - return 1; -} - -/* Creates entry with tag, or if entry already exists, unions tag to it. - * If storage is not NULL, newly created entry will use it. - * Returns number of entries added, or negative on error. - */ -static int _add_entry(struct my_tree *tree, u64 s, int32_t tag, - struct pnfs_inval_tracking *storage) -{ - int found = 0; - struct pnfs_inval_tracking *pos; - - dprintk("%s(%llu, %i, %p) enter\n", __func__, s, tag, storage); - list_for_each_entry_reverse(pos, &tree->mtt_stub, it_link) { - if (pos->it_sector > s) - continue; - else if (pos->it_sector == s) { - found = 1; - break; - } else - break; - } - if (found) { - pos->it_tags |= (1 << tag); - return 0; - } else { - struct pnfs_inval_tracking *new; - new = storage; - new->it_sector = s; - new->it_tags = (1 << tag); - list_add(&new->it_link, &pos->it_link); - return 1; - } -} - -/* XXXX Really want option to not create */ -/* Over range, unions tag with existing entries, else creates entry with tag */ -static int _set_range(struct my_tree *tree, int32_t tag, u64 s, u64 length) -{ - u64 i; - - dprintk("%s(%i, %llu, %llu) enter\n", __func__, tag, s, length); - for (i = normalize(s, tree->mtt_step_size); i < s + length; - i += tree->mtt_step_size) - if (_add_entry(tree, i, tag, NULL)) - return -ENOMEM; - return 0; -} - -/* Ensure that future operations on given range of tree will not malloc */ -static int _preload_range(struct pnfs_inval_markings *marks, - u64 offset, u64 length) -{ - u64 start, end, s; - int count, i, used = 0, status = -ENOMEM; - struct pnfs_inval_tracking **storage; - struct my_tree *tree = &marks->im_tree; - - dprintk("%s(%llu, %llu) enter\n", __func__, offset, length); - start = normalize(offset, tree->mtt_step_size); - end = normalize_up(offset + length, tree->mtt_step_size); - count = (int)(end - start) / (int)tree->mtt_step_size; - - /* Pre-malloc what memory we might need */ - storage = kcalloc(count, sizeof(*storage), GFP_NOFS); - if (!storage) - return -ENOMEM; - for (i = 0; i < count; i++) { - storage[i] = kmalloc(sizeof(struct pnfs_inval_tracking), - GFP_NOFS); - if (!storage[i]) - goto out_cleanup; - } - - spin_lock_bh(&marks->im_lock); - for (s = start; s < end; s += tree->mtt_step_size) - used += _add_entry(tree, s, INTERNAL_EXISTS, storage[used]); - spin_unlock_bh(&marks->im_lock); - - status = 0; - - out_cleanup: - for (i = used; i < count; i++) { - if (!storage[i]) - break; - kfree(storage[i]); - } - kfree(storage); - return status; -} - -/* We are relying on page lock to serialize this */ -int bl_is_sector_init(struct pnfs_inval_markings *marks, sector_t isect) -{ - int rv; - - spin_lock_bh(&marks->im_lock); - rv = _has_tag(&marks->im_tree, isect, EXTENT_INITIALIZED); - spin_unlock_bh(&marks->im_lock); - return rv; -} - -/* Assume start, end already sector aligned */ -static int -_range_has_tag(struct my_tree *tree, u64 start, u64 end, int32_t tag) -{ - struct pnfs_inval_tracking *pos; - u64 expect = 0; - - dprintk("%s(%llu, %llu, %i) enter\n", __func__, start, end, tag); - list_for_each_entry_reverse(pos, &tree->mtt_stub, it_link) { - if (pos->it_sector >= end) - continue; - if (!expect) { - if ((pos->it_sector == end - tree->mtt_step_size) && - (pos->it_tags & (1 << tag))) { - expect = pos->it_sector - tree->mtt_step_size; - if (pos->it_sector < tree->mtt_step_size || expect < start) - return 1; - continue; - } else { - return 0; - } - } - if (pos->it_sector != expect || !(pos->it_tags & (1 << tag))) - return 0; - expect -= tree->mtt_step_size; - if (expect < start) - return 1; - } - return 0; -} - -static int is_range_written(struct pnfs_inval_markings *marks, - sector_t start, sector_t end) -{ - int rv; - - spin_lock_bh(&marks->im_lock); - rv = _range_has_tag(&marks->im_tree, start, end, EXTENT_WRITTEN); - spin_unlock_bh(&marks->im_lock); - return rv; -} - -/* Marks sectors in [offest, offset_length) as having been initialized. - * All lengths are step-aligned, where step is min(pagesize, blocksize). - * Currently assumes offset is page-aligned - */ -int bl_mark_sectors_init(struct pnfs_inval_markings *marks, - sector_t offset, sector_t length) -{ - sector_t start, end; - - dprintk("%s(offset=%llu,len=%llu) enter\n", - __func__, (u64)offset, (u64)length); - - start = normalize(offset, marks->im_block_size); - end = normalize_up(offset + length, marks->im_block_size); - if (_preload_range(marks, start, end - start)) - goto outerr; - - spin_lock_bh(&marks->im_lock); - if (_set_range(&marks->im_tree, EXTENT_INITIALIZED, offset, length)) - goto out_unlock; - spin_unlock_bh(&marks->im_lock); - - return 0; - -out_unlock: - spin_unlock_bh(&marks->im_lock); -outerr: - return -ENOMEM; -} - -/* Marks sectors in [offest, offset+length) as having been written to disk. - * All lengths should be block aligned. - */ -static int mark_written_sectors(struct pnfs_inval_markings *marks, - sector_t offset, sector_t length) -{ - int status; - - dprintk("%s(offset=%llu,len=%llu) enter\n", __func__, - (u64)offset, (u64)length); - spin_lock_bh(&marks->im_lock); - status = _set_range(&marks->im_tree, EXTENT_WRITTEN, offset, length); - spin_unlock_bh(&marks->im_lock); - return status; -} - -static void print_short_extent(struct pnfs_block_short_extent *be) -{ - dprintk("PRINT SHORT EXTENT extent %p\n", be); - if (be) { - dprintk(" be_f_offset %llu\n", (u64)be->bse_f_offset); - dprintk(" be_length %llu\n", (u64)be->bse_length); - } -} - -static void print_clist(struct list_head *list, unsigned int count) -{ - struct pnfs_block_short_extent *be; - unsigned int i = 0; - - ifdebug(FACILITY) { - printk(KERN_DEBUG "****************\n"); - printk(KERN_DEBUG "Extent list looks like:\n"); - list_for_each_entry(be, list, bse_node) { - i++; - print_short_extent(be); - } - if (i != count) - printk(KERN_DEBUG "\n\nExpected %u entries\n\n\n", count); - printk(KERN_DEBUG "****************\n"); - } -} - -/* Note: In theory, we should do more checking that devid's match between - * old and new, but if they don't, the lists are too corrupt to salvage anyway. - */ -/* Note this is very similar to bl_add_merge_extent */ -static void add_to_commitlist(struct pnfs_block_layout *bl, - struct pnfs_block_short_extent *new) -{ - struct list_head *clist = &bl->bl_commit; - struct pnfs_block_short_extent *old, *save; - sector_t end = new->bse_f_offset + new->bse_length; - - dprintk("%s enter\n", __func__); - print_short_extent(new); - print_clist(clist, bl->bl_count); - bl->bl_count++; - /* Scan for proper place to insert, extending new to the left - * as much as possible. - */ - list_for_each_entry_safe(old, save, clist, bse_node) { - if (new->bse_f_offset < old->bse_f_offset) - break; - if (end <= old->bse_f_offset + old->bse_length) { - /* Range is already in list */ - bl->bl_count--; - kfree(new); - return; - } else if (new->bse_f_offset <= - old->bse_f_offset + old->bse_length) { - /* new overlaps or abuts existing be */ - if (new->bse_mdev == old->bse_mdev) { - /* extend new to fully replace old */ - new->bse_length += new->bse_f_offset - - old->bse_f_offset; - new->bse_f_offset = old->bse_f_offset; - list_del(&old->bse_node); - bl->bl_count--; - kfree(old); - } - } - } - /* Note that if we never hit the above break, old will not point to a - * valid extent. However, in that case &old->bse_node==list. - */ - list_add_tail(&new->bse_node, &old->bse_node); - /* Scan forward for overlaps. If we find any, extend new and - * remove the overlapped extent. - */ - old = list_prepare_entry(new, clist, bse_node); - list_for_each_entry_safe_continue(old, save, clist, bse_node) { - if (end < old->bse_f_offset) - break; - /* new overlaps or abuts old */ - if (new->bse_mdev == old->bse_mdev) { - if (end < old->bse_f_offset + old->bse_length) { - /* extend new to fully cover old */ - end = old->bse_f_offset + old->bse_length; - new->bse_length = end - new->bse_f_offset; - } - list_del(&old->bse_node); - bl->bl_count--; - kfree(old); - } - } - dprintk("%s: after merging\n", __func__); - print_clist(clist, bl->bl_count); -} - -/* Note the range described by offset, length is guaranteed to be contained - * within be. - * new will be freed, either by this function or add_to_commitlist if they - * decide not to use it, or after LAYOUTCOMMIT uses it in the commitlist. - */ -int bl_mark_for_commit(struct pnfs_block_extent *be, - sector_t offset, sector_t length, - struct pnfs_block_short_extent *new) -{ - sector_t new_end, end = offset + length; - struct pnfs_block_layout *bl = container_of(be->be_inval, - struct pnfs_block_layout, - bl_inval); - - mark_written_sectors(be->be_inval, offset, length); - /* We want to add the range to commit list, but it must be - * block-normalized, and verified that the normalized range has - * been entirely written to disk. - */ - new->bse_f_offset = offset; - offset = normalize(offset, bl->bl_blocksize); - if (offset < new->bse_f_offset) { - if (is_range_written(be->be_inval, offset, new->bse_f_offset)) - new->bse_f_offset = offset; - else - new->bse_f_offset = offset + bl->bl_blocksize; - } - new_end = normalize_up(end, bl->bl_blocksize); - if (end < new_end) { - if (is_range_written(be->be_inval, end, new_end)) - end = new_end; - else - end = new_end - bl->bl_blocksize; - } - if (end <= new->bse_f_offset) { - kfree(new); - return 0; - } - new->bse_length = end - new->bse_f_offset; - new->bse_devid = be->be_devid; - new->bse_mdev = be->be_mdev; - - spin_lock(&bl->bl_ext_lock); - add_to_commitlist(bl, new); - spin_unlock(&bl->bl_ext_lock); - return 0; -} - -static void print_bl_extent(struct pnfs_block_extent *be) -{ - dprintk("PRINT EXTENT extent %p\n", be); - if (be) { - dprintk(" be_f_offset %llu\n", (u64)be->be_f_offset); - dprintk(" be_length %llu\n", (u64)be->be_length); - dprintk(" be_v_offset %llu\n", (u64)be->be_v_offset); - dprintk(" be_state %d\n", be->be_state); - } -} - -static void -destroy_extent(struct kref *kref) -{ - struct pnfs_block_extent *be; - - be = container_of(kref, struct pnfs_block_extent, be_refcnt); - dprintk("%s be=%p\n", __func__, be); - kfree(be); -} - -void -bl_put_extent(struct pnfs_block_extent *be) -{ - if (be) { - dprintk("%s enter %p (%i)\n", __func__, be, - atomic_read(&be->be_refcnt.refcount)); - kref_put(&be->be_refcnt, destroy_extent); - } -} - -struct pnfs_block_extent *bl_alloc_extent(void) -{ - struct pnfs_block_extent *be; - - be = kmalloc(sizeof(struct pnfs_block_extent), GFP_NOFS); - if (!be) - return NULL; - INIT_LIST_HEAD(&be->be_node); - kref_init(&be->be_refcnt); - be->be_inval = NULL; - return be; -} - -static void print_elist(struct list_head *list) -{ - struct pnfs_block_extent *be; - dprintk("****************\n"); - dprintk("Extent list looks like:\n"); - list_for_each_entry(be, list, be_node) { - print_bl_extent(be); - } - dprintk("****************\n"); -} - -static inline int -extents_consistent(struct pnfs_block_extent *old, struct pnfs_block_extent *new) -{ - /* Note this assumes new->be_f_offset >= old->be_f_offset */ - return (new->be_state == old->be_state) && - ((new->be_state == PNFS_BLOCK_NONE_DATA) || - ((new->be_v_offset - old->be_v_offset == - new->be_f_offset - old->be_f_offset) && - new->be_mdev == old->be_mdev)); -} - -/* Adds new to appropriate list in bl, modifying new and removing existing - * extents as appropriate to deal with overlaps. - * - * See bl_find_get_extent for list constraints. - * - * Refcount on new is already set. If end up not using it, or error out, - * need to put the reference. - * - * bl->bl_ext_lock is held by caller. - */ -int -bl_add_merge_extent(struct pnfs_block_layout *bl, - struct pnfs_block_extent *new) -{ - struct pnfs_block_extent *be, *tmp; - sector_t end = new->be_f_offset + new->be_length; - struct list_head *list; - - dprintk("%s enter with be=%p\n", __func__, new); - print_bl_extent(new); - list = &bl->bl_extents[bl_choose_list(new->be_state)]; - print_elist(list); - - /* Scan for proper place to insert, extending new to the left - * as much as possible. - */ - list_for_each_entry_safe_reverse(be, tmp, list, be_node) { - if (new->be_f_offset >= be->be_f_offset + be->be_length) - break; - if (new->be_f_offset >= be->be_f_offset) { - if (end <= be->be_f_offset + be->be_length) { - /* new is a subset of existing be*/ - if (extents_consistent(be, new)) { - dprintk("%s: new is subset, ignoring\n", - __func__); - bl_put_extent(new); - return 0; - } else { - goto out_err; - } - } else { - /* |<-- be -->| - * |<-- new -->| */ - if (extents_consistent(be, new)) { - /* extend new to fully replace be */ - new->be_length += new->be_f_offset - - be->be_f_offset; - new->be_f_offset = be->be_f_offset; - new->be_v_offset = be->be_v_offset; - dprintk("%s: removing %p\n", __func__, be); - list_del(&be->be_node); - bl_put_extent(be); - } else { - goto out_err; - } - } - } else if (end >= be->be_f_offset + be->be_length) { - /* new extent overlap existing be */ - if (extents_consistent(be, new)) { - /* extend new to fully replace be */ - dprintk("%s: removing %p\n", __func__, be); - list_del(&be->be_node); - bl_put_extent(be); - } else { - goto out_err; - } - } else if (end > be->be_f_offset) { - /* |<-- be -->| - *|<-- new -->| */ - if (extents_consistent(new, be)) { - /* extend new to fully replace be */ - new->be_length += be->be_f_offset + be->be_length - - new->be_f_offset - new->be_length; - dprintk("%s: removing %p\n", __func__, be); - list_del(&be->be_node); - bl_put_extent(be); - } else { - goto out_err; - } - } - } - /* Note that if we never hit the above break, be will not point to a - * valid extent. However, in that case &be->be_node==list. - */ - list_add(&new->be_node, &be->be_node); - dprintk("%s: inserting new\n", __func__); - print_elist(list); - /* FIXME - The per-list consistency checks have all been done, - * should now check cross-list consistency. - */ - return 0; - - out_err: - bl_put_extent(new); - return -EIO; -} - -/* Returns extent, or NULL. If a second READ extent exists, it is returned - * in cow_read, if given. - * - * The extents are kept in two seperate ordered lists, one for READ and NONE, - * one for READWRITE and INVALID. Within each list, we assume: - * 1. Extents are ordered by file offset. - * 2. For any given isect, there is at most one extents that matches. - */ -struct pnfs_block_extent * -bl_find_get_extent(struct pnfs_block_layout *bl, sector_t isect, - struct pnfs_block_extent **cow_read) -{ - struct pnfs_block_extent *be, *cow, *ret; - int i; - - dprintk("%s enter with isect %llu\n", __func__, (u64)isect); - cow = ret = NULL; - spin_lock(&bl->bl_ext_lock); - for (i = 0; i < EXTENT_LISTS; i++) { - list_for_each_entry_reverse(be, &bl->bl_extents[i], be_node) { - if (isect >= be->be_f_offset + be->be_length) - break; - if (isect >= be->be_f_offset) { - /* We have found an extent */ - dprintk("%s Get %p (%i)\n", __func__, be, - atomic_read(&be->be_refcnt.refcount)); - kref_get(&be->be_refcnt); - if (!ret) - ret = be; - else if (be->be_state != PNFS_BLOCK_READ_DATA) - bl_put_extent(be); - else - cow = be; - break; - } - } - if (ret && - (!cow_read || ret->be_state != PNFS_BLOCK_INVALID_DATA)) - break; - } - spin_unlock(&bl->bl_ext_lock); - if (cow_read) - *cow_read = cow; - print_bl_extent(ret); - return ret; -} - -/* Similar to bl_find_get_extent, but called with lock held, and ignores cow */ -static struct pnfs_block_extent * -bl_find_get_extent_locked(struct pnfs_block_layout *bl, sector_t isect) -{ - struct pnfs_block_extent *be, *ret = NULL; - int i; - - dprintk("%s enter with isect %llu\n", __func__, (u64)isect); - for (i = 0; i < EXTENT_LISTS; i++) { - if (ret) - break; - list_for_each_entry_reverse(be, &bl->bl_extents[i], be_node) { - if (isect >= be->be_f_offset + be->be_length) - break; - if (isect >= be->be_f_offset) { - /* We have found an extent */ - dprintk("%s Get %p (%i)\n", __func__, be, - atomic_read(&be->be_refcnt.refcount)); - kref_get(&be->be_refcnt); - ret = be; - break; - } - } - } - print_bl_extent(ret); - return ret; -} - -int -encode_pnfs_block_layoutupdate(struct pnfs_block_layout *bl, - struct xdr_stream *xdr, - const struct nfs4_layoutcommit_args *arg) -{ - struct pnfs_block_short_extent *lce, *save; - unsigned int count = 0; - __be32 *p, *xdr_start; - - dprintk("%s enter\n", __func__); - /* BUG - creation of bl_commit is buggy - need to wait for - * entire block to be marked WRITTEN before it can be added. - */ - spin_lock(&bl->bl_ext_lock); - /* Want to adjust for possible truncate */ - /* We now want to adjust argument range */ - - /* XDR encode the ranges found */ - xdr_start = xdr_reserve_space(xdr, 8); - if (!xdr_start) - goto out; - list_for_each_entry_safe(lce, save, &bl->bl_commit, bse_node) { - p = xdr_reserve_space(xdr, 7 * 4 + sizeof(lce->bse_devid.data)); - if (!p) - break; - p = xdr_encode_opaque_fixed(p, lce->bse_devid.data, NFS4_DEVICEID4_SIZE); - p = xdr_encode_hyper(p, lce->bse_f_offset << SECTOR_SHIFT); - p = xdr_encode_hyper(p, lce->bse_length << SECTOR_SHIFT); - p = xdr_encode_hyper(p, 0LL); - *p++ = cpu_to_be32(PNFS_BLOCK_READWRITE_DATA); - list_move_tail(&lce->bse_node, &bl->bl_committing); - bl->bl_count--; - count++; - } - xdr_start[0] = cpu_to_be32((xdr->p - xdr_start - 1) * 4); - xdr_start[1] = cpu_to_be32(count); -out: - spin_unlock(&bl->bl_ext_lock); - dprintk("%s found %i ranges\n", __func__, count); - return 0; -} - -/* Helper function to set_to_rw that initialize a new extent */ -static void -_prep_new_extent(struct pnfs_block_extent *new, - struct pnfs_block_extent *orig, - sector_t offset, sector_t length, int state) -{ - kref_init(&new->be_refcnt); - /* don't need to INIT_LIST_HEAD(&new->be_node) */ - memcpy(&new->be_devid, &orig->be_devid, sizeof(struct nfs4_deviceid)); - new->be_mdev = orig->be_mdev; - new->be_f_offset = offset; - new->be_length = length; - new->be_v_offset = orig->be_v_offset - orig->be_f_offset + offset; - new->be_state = state; - new->be_inval = orig->be_inval; -} - -/* Tries to merge be with extent in front of it in list. - * Frees storage if not used. - */ -static struct pnfs_block_extent * -_front_merge(struct pnfs_block_extent *be, struct list_head *head, - struct pnfs_block_extent *storage) -{ - struct pnfs_block_extent *prev; - - if (!storage) - goto no_merge; - if (&be->be_node == head || be->be_node.prev == head) - goto no_merge; - prev = list_entry(be->be_node.prev, struct pnfs_block_extent, be_node); - if ((prev->be_f_offset + prev->be_length != be->be_f_offset) || - !extents_consistent(prev, be)) - goto no_merge; - _prep_new_extent(storage, prev, prev->be_f_offset, - prev->be_length + be->be_length, prev->be_state); - list_replace(&prev->be_node, &storage->be_node); - bl_put_extent(prev); - list_del(&be->be_node); - bl_put_extent(be); - return storage; - - no_merge: - kfree(storage); - return be; -} - -static u64 -set_to_rw(struct pnfs_block_layout *bl, u64 offset, u64 length) -{ - u64 rv = offset + length; - struct pnfs_block_extent *be, *e1, *e2, *e3, *new, *old; - struct pnfs_block_extent *children[3]; - struct pnfs_block_extent *merge1 = NULL, *merge2 = NULL; - int i = 0, j; - - dprintk("%s(%llu, %llu)\n", __func__, offset, length); - /* Create storage for up to three new extents e1, e2, e3 */ - e1 = kmalloc(sizeof(*e1), GFP_ATOMIC); - e2 = kmalloc(sizeof(*e2), GFP_ATOMIC); - e3 = kmalloc(sizeof(*e3), GFP_ATOMIC); - /* BUG - we are ignoring any failure */ - if (!e1 || !e2 || !e3) - goto out_nosplit; - - spin_lock(&bl->bl_ext_lock); - be = bl_find_get_extent_locked(bl, offset); - rv = be->be_f_offset + be->be_length; - if (be->be_state != PNFS_BLOCK_INVALID_DATA) { - spin_unlock(&bl->bl_ext_lock); - goto out_nosplit; - } - /* Add e* to children, bumping e*'s krefs */ - if (be->be_f_offset != offset) { - _prep_new_extent(e1, be, be->be_f_offset, - offset - be->be_f_offset, - PNFS_BLOCK_INVALID_DATA); - children[i++] = e1; - print_bl_extent(e1); - } else - merge1 = e1; - _prep_new_extent(e2, be, offset, - min(length, be->be_f_offset + be->be_length - offset), - PNFS_BLOCK_READWRITE_DATA); - children[i++] = e2; - print_bl_extent(e2); - if (offset + length < be->be_f_offset + be->be_length) { - _prep_new_extent(e3, be, e2->be_f_offset + e2->be_length, - be->be_f_offset + be->be_length - - offset - length, - PNFS_BLOCK_INVALID_DATA); - children[i++] = e3; - print_bl_extent(e3); - } else - merge2 = e3; - - /* Remove be from list, and insert the e* */ - /* We don't get refs on e*, since this list is the base reference - * set when init'ed. - */ - if (i < 3) - children[i] = NULL; - new = children[0]; - list_replace(&be->be_node, &new->be_node); - bl_put_extent(be); - new = _front_merge(new, &bl->bl_extents[RW_EXTENT], merge1); - for (j = 1; j < i; j++) { - old = new; - new = children[j]; - list_add(&new->be_node, &old->be_node); - } - if (merge2) { - /* This is a HACK, should just create a _back_merge function */ - new = list_entry(new->be_node.next, - struct pnfs_block_extent, be_node); - new = _front_merge(new, &bl->bl_extents[RW_EXTENT], merge2); - } - spin_unlock(&bl->bl_ext_lock); - - /* Since we removed the base reference above, be is now scheduled for - * destruction. - */ - bl_put_extent(be); - dprintk("%s returns %llu after split\n", __func__, rv); - return rv; - - out_nosplit: - kfree(e1); - kfree(e2); - kfree(e3); - dprintk("%s returns %llu without splitting\n", __func__, rv); - return rv; -} - -void -clean_pnfs_block_layoutupdate(struct pnfs_block_layout *bl, - const struct nfs4_layoutcommit_args *arg, - int status) -{ - struct pnfs_block_short_extent *lce, *save; - - dprintk("%s status %d\n", __func__, status); - list_for_each_entry_safe(lce, save, &bl->bl_committing, bse_node) { - if (likely(!status)) { - u64 offset = lce->bse_f_offset; - u64 end = offset + lce->bse_length; - - do { - offset = set_to_rw(bl, offset, end - offset); - } while (offset < end); - list_del(&lce->bse_node); - - kfree(lce); - } else { - list_del(&lce->bse_node); - spin_lock(&bl->bl_ext_lock); - add_to_commitlist(bl, lce); - spin_unlock(&bl->bl_ext_lock); - } - } -} - -int bl_push_one_short_extent(struct pnfs_inval_markings *marks) -{ - struct pnfs_block_short_extent *new; - - new = kmalloc(sizeof(*new), GFP_NOFS); - if (unlikely(!new)) - return -ENOMEM; - - spin_lock_bh(&marks->im_lock); - list_add(&new->bse_node, &marks->im_extents); - spin_unlock_bh(&marks->im_lock); - - return 0; -} - -struct pnfs_block_short_extent * -bl_pop_one_short_extent(struct pnfs_inval_markings *marks) -{ - struct pnfs_block_short_extent *rv = NULL; - - spin_lock_bh(&marks->im_lock); - if (!list_empty(&marks->im_extents)) { - rv = list_entry((&marks->im_extents)->next, - struct pnfs_block_short_extent, bse_node); - list_del_init(&rv->bse_node); - } - spin_unlock_bh(&marks->im_lock); - - return rv; -} - -void bl_free_short_extents(struct pnfs_inval_markings *marks, int num_to_free) -{ - struct pnfs_block_short_extent *se = NULL, *tmp; - - if (num_to_free <= 0) - return; - - spin_lock(&marks->im_lock); - list_for_each_entry_safe(se, tmp, &marks->im_extents, bse_node) { - list_del(&se->bse_node); - kfree(se); - if (--num_to_free == 0) - break; - } - spin_unlock(&marks->im_lock); - - BUG_ON(num_to_free > 0); -} diff --git a/fs/nfs/blocklayout/rpc_pipefs.c b/fs/nfs/blocklayout/rpc_pipefs.c new file mode 100644 index 000000000000..8d04bda2bd2e --- /dev/null +++ b/fs/nfs/blocklayout/rpc_pipefs.c @@ -0,0 +1,285 @@ +/* + * Copyright (c) 2006,2007 The Regents of the University of Michigan. + * All rights reserved. + * + * Andy Adamson <andros@citi.umich.edu> + * Fred Isaman <iisaman@umich.edu> + * + * permission is granted to use, copy, create derivative works and + * redistribute this software and such derivative works for any purpose, + * so long as the name of the university of michigan is not used in + * any advertising or publicity pertaining to the use or distribution + * of this software without specific, written prior authorization. if + * the above copyright notice or any other identification of the + * university of michigan is included in any copy of any portion of + * this software, then the disclaimer below must also be included. + * + * this software is provided as is, without representation from the + * university of michigan as to its fitness for any purpose, and without + * warranty by the university of michigan of any kind, either express + * or implied, including without limitation the implied warranties of + * merchantability and fitness for a particular purpose. the regents + * of the university of michigan shall not be liable for any damages, + * including special, indirect, incidental, or consequential damages, + * with respect to any claim arising out or in connection with the use + * of the software, even if it has been or is hereafter advised of the + * possibility of such damages. + */ + +#include <linux/module.h> +#include <linux/genhd.h> +#include <linux/blkdev.h> + +#include "blocklayout.h" + +#define NFSDBG_FACILITY NFSDBG_PNFS_LD + +static void +nfs4_encode_simple(__be32 *p, struct pnfs_block_volume *b) +{ + int i; + + *p++ = cpu_to_be32(1); + *p++ = cpu_to_be32(b->type); + *p++ = cpu_to_be32(b->simple.nr_sigs); + for (i = 0; i < b->simple.nr_sigs; i++) { + p = xdr_encode_hyper(p, b->simple.sigs[i].offset); + p = xdr_encode_opaque(p, b->simple.sigs[i].sig, + b->simple.sigs[i].sig_len); + } +} + +dev_t +bl_resolve_deviceid(struct nfs_server *server, struct pnfs_block_volume *b, + gfp_t gfp_mask) +{ + 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; + struct bl_pipe_msg bl_pipe_msg; + struct rpc_pipe_msg *msg = &bl_pipe_msg.msg; + struct bl_msg_hdr *bl_msg; + DECLARE_WAITQUEUE(wq, current); + dev_t dev = 0; + int rc; + + dprintk("%s CREATING PIPEFS MESSAGE\n", __func__); + + bl_pipe_msg.bl_wq = &nn->bl_wq; + + b->simple.len += 4; /* single volume */ + if (b->simple.len > PAGE_SIZE) + return -EIO; + + memset(msg, 0, sizeof(*msg)); + msg->len = sizeof(*bl_msg) + b->simple.len; + msg->data = kzalloc(msg->len, gfp_mask); + if (!msg->data) + goto out; + + bl_msg = msg->data; + bl_msg->type = BL_DEVICE_MOUNT, + bl_msg->totallen = b->simple.len; + nfs4_encode_simple(msg->data + sizeof(*bl_msg), b); + + dprintk("%s CALLING USERSPACE DAEMON\n", __func__); + add_wait_queue(&nn->bl_wq, &wq); + rc = rpc_queue_upcall(nn->bl_device_pipe, msg); + if (rc < 0) { + remove_wait_queue(&nn->bl_wq, &wq); + goto out; + } + + set_current_state(TASK_UNINTERRUPTIBLE); + schedule(); + __set_current_state(TASK_RUNNING); + remove_wait_queue(&nn->bl_wq, &wq); + + if (reply->status != BL_DEVICE_REQUEST_PROC) { + printk(KERN_WARNING "%s failed to decode device: %d\n", + __func__, reply->status); + goto out; + } + + dev = MKDEV(reply->major, reply->minor); +out: + kfree(msg->data); + return dev; +} + +static ssize_t bl_pipe_downcall(struct file *filp, const char __user *src, + size_t mlen) +{ + struct nfs_net *nn = net_generic(filp->f_dentry->d_sb->s_fs_info, + nfs_net_id); + + if (mlen != sizeof (struct bl_dev_msg)) + return -EINVAL; + + if (copy_from_user(&nn->bl_mount_reply, src, mlen) != 0) + return -EFAULT; + + wake_up(&nn->bl_wq); + + return mlen; +} + +static void bl_pipe_destroy_msg(struct rpc_pipe_msg *msg) +{ + struct bl_pipe_msg *bl_pipe_msg = + container_of(msg, struct bl_pipe_msg, msg); + + if (msg->errno >= 0) + return; + wake_up(bl_pipe_msg->bl_wq); +} + +static const struct rpc_pipe_ops bl_upcall_ops = { + .upcall = rpc_pipe_generic_upcall, + .downcall = bl_pipe_downcall, + .destroy_msg = bl_pipe_destroy_msg, +}; + +static struct dentry *nfs4blocklayout_register_sb(struct super_block *sb, + struct rpc_pipe *pipe) +{ + struct dentry *dir, *dentry; + + dir = rpc_d_lookup_sb(sb, NFS_PIPE_DIRNAME); + if (dir == NULL) + return ERR_PTR(-ENOENT); + dentry = rpc_mkpipe_dentry(dir, "blocklayout", NULL, pipe); + dput(dir); + return dentry; +} + +static void nfs4blocklayout_unregister_sb(struct super_block *sb, + struct rpc_pipe *pipe) +{ + if (pipe->dentry) + rpc_unlink(pipe->dentry); +} + +static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event, + void *ptr) +{ + struct super_block *sb = ptr; + struct net *net = sb->s_fs_info; + struct nfs_net *nn = net_generic(net, nfs_net_id); + struct dentry *dentry; + int ret = 0; + + if (!try_module_get(THIS_MODULE)) + return 0; + + if (nn->bl_device_pipe == NULL) { + module_put(THIS_MODULE); + return 0; + } + + switch (event) { + case RPC_PIPEFS_MOUNT: + dentry = nfs4blocklayout_register_sb(sb, nn->bl_device_pipe); + if (IS_ERR(dentry)) { + ret = PTR_ERR(dentry); + break; + } + nn->bl_device_pipe->dentry = dentry; + break; + case RPC_PIPEFS_UMOUNT: + if (nn->bl_device_pipe->dentry) + nfs4blocklayout_unregister_sb(sb, nn->bl_device_pipe); + break; + default: + ret = -ENOTSUPP; + break; + } + module_put(THIS_MODULE); + return ret; +} + +static struct notifier_block nfs4blocklayout_block = { + .notifier_call = rpc_pipefs_event, +}; + +static struct dentry *nfs4blocklayout_register_net(struct net *net, + struct rpc_pipe *pipe) +{ + struct super_block *pipefs_sb; + struct dentry *dentry; + + pipefs_sb = rpc_get_sb_net(net); + if (!pipefs_sb) + return NULL; + dentry = nfs4blocklayout_register_sb(pipefs_sb, pipe); + rpc_put_sb_net(net); + return dentry; +} + +static void nfs4blocklayout_unregister_net(struct net *net, + struct rpc_pipe *pipe) +{ + struct super_block *pipefs_sb; + + pipefs_sb = rpc_get_sb_net(net); + if (pipefs_sb) { + nfs4blocklayout_unregister_sb(pipefs_sb, pipe); + rpc_put_sb_net(net); + } +} + +static int nfs4blocklayout_net_init(struct net *net) +{ + struct nfs_net *nn = net_generic(net, nfs_net_id); + struct dentry *dentry; + + init_waitqueue_head(&nn->bl_wq); + nn->bl_device_pipe = rpc_mkpipe_data(&bl_upcall_ops, 0); + if (IS_ERR(nn->bl_device_pipe)) + return PTR_ERR(nn->bl_device_pipe); + dentry = nfs4blocklayout_register_net(net, nn->bl_device_pipe); + if (IS_ERR(dentry)) { + rpc_destroy_pipe_data(nn->bl_device_pipe); + return PTR_ERR(dentry); + } + nn->bl_device_pipe->dentry = dentry; + return 0; +} + +static void nfs4blocklayout_net_exit(struct net *net) +{ + struct nfs_net *nn = net_generic(net, nfs_net_id); + + nfs4blocklayout_unregister_net(net, nn->bl_device_pipe); + rpc_destroy_pipe_data(nn->bl_device_pipe); + nn->bl_device_pipe = NULL; +} + +static struct pernet_operations nfs4blocklayout_net_ops = { + .init = nfs4blocklayout_net_init, + .exit = nfs4blocklayout_net_exit, +}; + +int __init bl_init_pipefs(void) +{ + int ret; + + ret = rpc_pipefs_notifier_register(&nfs4blocklayout_block); + if (ret) + goto out; + ret = register_pernet_subsys(&nfs4blocklayout_net_ops); + if (ret) + goto out_unregister_notifier; + return 0; + +out_unregister_notifier: + rpc_pipefs_notifier_unregister(&nfs4blocklayout_block); +out: + return ret; +} + +void __exit bl_cleanup_pipefs(void) +{ + rpc_pipefs_notifier_unregister(&nfs4blocklayout_block); + unregister_pernet_subsys(&nfs4blocklayout_net_ops); +} |