diff options
51 files changed, 2580 insertions, 3378 deletions
diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c index daa8e7514eae..9106f42c472c 100644 --- a/fs/lockd/mon.c +++ b/fs/lockd/mon.c @@ -159,6 +159,12 @@ static int nsm_mon_unmon(struct nsm_handle *nsm, u32 proc, struct nsm_res *res, msg.rpc_proc = &clnt->cl_procinfo[proc]; status = rpc_call_sync(clnt, &msg, RPC_TASK_SOFTCONN); + if (status == -ECONNREFUSED) { + dprintk("lockd: NSM upcall RPC failed, status=%d, forcing rebind\n", + status); + rpc_force_rebind(clnt); + status = rpc_call_sync(clnt, &msg, RPC_TASK_SOFTCONN); + } if (status < 0) dprintk("lockd: NSM upcall RPC failed, status=%d\n", status); 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_re |