zte's code,first commit
Change-Id: I9a04da59e459a9bc0d67f101f700d9d7dc8d681b
diff --git a/ap/os/linux/linux-3.4.x/fs/nfs/blocklayout/Makefile b/ap/os/linux/linux-3.4.x/fs/nfs/blocklayout/Makefile
new file mode 100644
index 0000000..d581550
--- /dev/null
+++ b/ap/os/linux/linux-3.4.x/fs/nfs/blocklayout/Makefile
@@ -0,0 +1,5 @@
+#
+# 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
diff --git a/ap/os/linux/linux-3.4.x/fs/nfs/blocklayout/blocklayout.c b/ap/os/linux/linux-3.4.x/fs/nfs/blocklayout/blocklayout.c
new file mode 100644
index 0000000..3a9c247
--- /dev/null
+++ b/ap/os/linux/linux-3.4.x/fs/nfs/blocklayout/blocklayout.c
@@ -0,0 +1,1338 @@
+/*
+ * linux/fs/nfs/blocklayout/blocklayout.c
+ *
+ * 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 <linux/module.h>
+#include <linux/init.h>
+#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 "../pnfs.h"
+#include "../internal.h"
+#include "blocklayout.h"
+
+#define NFSDBG_FACILITY NFSDBG_PNFS_LD
+
+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)
+{
+ 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);
+}
+
+/* The data we are handed might be spread across several bios. We need
+ * to track when the last one is finished.
+ */
+struct parallel_io {
+ struct kref refcnt;
+ void (*pnfs_callback) (void *data, int num_se);
+ void *data;
+ int bse_count;
+};
+
+static inline struct parallel_io *alloc_parallel(void *data)
+{
+ struct parallel_io *rv;
+
+ rv = kmalloc(sizeof(*rv), GFP_NOFS);
+ if (rv) {
+ rv->data = data;
+ kref_init(&rv->refcnt);
+ rv->bse_count = 0;
+ }
+ return rv;
+}
+
+static inline void get_parallel(struct parallel_io *p)
+{
+ kref_get(&p->refcnt);
+}
+
+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);
+ kfree(p);
+}
+
+static inline void put_parallel(struct parallel_io *p)
+{
+ kref_put(&p->refcnt, destroy_parallel);
+}
+
+static struct bio *
+bl_submit_bio(int rw, struct bio *bio)
+{
+ if (bio) {
+ get_parallel(bio->bi_private);
+ dprintk("%s submitting %s bio %u@%llu\n", __func__,
+ rw == READ ? "read" : "write",
+ bio->bi_size, (unsigned long long)bio->bi_sector);
+ submit_bio(rw, 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)
+{
+ struct bio *bio;
+
+ npg = min(npg, BIO_MAX_PAGES);
+ bio = bio_alloc(GFP_NOIO, npg);
+ if (!bio && (current->flags & PF_MEMALLOC)) {
+ while (!bio && (npg /= 2))
+ bio = bio_alloc(GFP_NOIO, npg);
+ }
+
+ if (bio) {
+ bio->bi_sector = isect - be->be_f_offset + be->be_v_offset;
+ bio->bi_bdev = be->be_mdev;
+ 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)
+{
+ isect = isect + (offset >> SECTOR_SHIFT);
+ dprintk("%s: npg %d rw %d isect %llu offset %u len %d\n", __func__,
+ npg, rw, (unsigned long long)isect, offset, len);
+retry:
+ if (!bio) {
+ bio = bl_alloc_init_bio(npg, isect, be, end_io, par);
+ if (!bio)
+ return ERR_PTR(-ENOMEM);
+ }
+ 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;
+ const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
+ struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
+ struct nfs_read_data *rdata = (struct nfs_read_data *)par->data;
+
+ do {
+ struct page *page = bvec->bv_page;
+
+ if (--bvec >= bio->bi_io_vec)
+ prefetchw(&bvec->bv_page->flags);
+ if (uptodate)
+ SetPageUptodate(page);
+ } while (bvec >= bio->bi_io_vec);
+ if (!uptodate) {
+ if (!rdata->pnfs_error)
+ rdata->pnfs_error = -EIO;
+ pnfs_set_lo_fail(rdata->lseg);
+ }
+ bio_put(bio);
+ put_parallel(par);
+}
+
+static void bl_read_cleanup(struct work_struct *work)
+{
+ struct rpc_task *task;
+ struct nfs_read_data *rdata;
+ dprintk("%s enter\n", __func__);
+ task = container_of(work, struct rpc_task, u.tk_work);
+ rdata = container_of(task, struct nfs_read_data, task);
+ pnfs_ld_read_done(rdata);
+}
+
+static void
+bl_end_par_io_read(void *data, int unused)
+{
+ struct nfs_read_data *rdata = data;
+
+ rdata->task.tk_status = rdata->pnfs_error;
+ INIT_WORK(&rdata->task.u.tk_work, bl_read_cleanup);
+ schedule_work(&rdata->task.u.tk_work);
+}
+
+static enum pnfs_try_status
+bl_read_pagelist(struct nfs_read_data *rdata)
+{
+ int i, hole;
+ struct bio *bio = NULL;
+ struct pnfs_block_extent *be = NULL, *cow_read = NULL;
+ sector_t isect, extent_length = 0;
+ struct parallel_io *par;
+ loff_t f_offset = rdata->args.offset;
+ struct page **pages = rdata->args.pages;
+ int pg_index = rdata->args.pgbase >> PAGE_CACHE_SHIFT;
+
+ dprintk("%s enter nr_pages %u offset %lld count %u\n", __func__,
+ rdata->npages, f_offset, (unsigned int)rdata->args.count);
+
+ par = alloc_parallel(rdata);
+ if (!par)
+ goto use_mds;
+ par->pnfs_callback = bl_end_par_io_read;
+ /* At this point, we can no longer jump to use_mds */
+
+ isect = (sector_t) (f_offset >> SECTOR_SHIFT);
+ /* Code assumes extents are page-aligned */
+ for (i = pg_index; i < rdata->npages; i++) {
+ if (!extent_length) {
+ /* 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(rdata->lseg),
+ isect, &cow_read);
+ if (!be) {
+ rdata->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);
+ }
+ }
+ hole = is_hole(be, isect);
+ if (hole && !cow_read) {
+ 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], 0, PAGE_CACHE_SIZE);
+ print_page(pages[i]);
+ SetPageUptodate(pages[i]);
+ } else {
+ struct pnfs_block_extent *be_read;
+
+ be_read = (hole && cow_read) ? cow_read : be;
+ bio = bl_add_page_to_bio(bio, rdata->npages - i, READ,
+ isect, pages[i], be_read,
+ bl_end_io_read, par);
+ if (IS_ERR(bio)) {
+ rdata->pnfs_error = PTR_ERR(bio);
+ bio = NULL;
+ goto out;
+ }
+ }
+ isect += PAGE_CACHE_SECTORS;
+ extent_length -= PAGE_CACHE_SECTORS;
+ }
+ if ((isect << SECTOR_SHIFT) >= rdata->inode->i_size) {
+ rdata->res.eof = 1;
+ rdata->res.count = rdata->inode->i_size - f_offset;
+ } else {
+ rdata->res.count = (isect << SECTOR_SHIFT) - f_offset;
+ }
+out:
+ bl_put_extent(be);
+ bl_put_extent(cow_read);
+ bl_submit_bio(READ, bio);
+ 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;
+ const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
+ struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
+ struct nfs_write_data *wdata = (struct nfs_write_data *)par->data;
+
+ do {
+ struct page *page = bvec->bv_page;
+
+ if (--bvec >= bio->bi_io_vec)
+ prefetchw(&bvec->bv_page->flags);
+ /* This is the zeroing page we added */
+ end_page_writeback(page);
+ page_cache_release(page);
+ } while (bvec >= bio->bi_io_vec);
+
+ if (unlikely(!uptodate)) {
+ if (!wdata->pnfs_error)
+ wdata->pnfs_error = -EIO;
+ pnfs_set_lo_fail(wdata->lseg);
+ }
+ bio_put(bio);
+ put_parallel(par);
+}
+
+static void bl_end_io_write(struct bio *bio, int err)
+{
+ struct parallel_io *par = bio->bi_private;
+ const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
+ struct nfs_write_data *wdata = (struct nfs_write_data *)par->data;
+
+ if (!uptodate) {
+ if (!wdata->pnfs_error)
+ wdata->pnfs_error = -EIO;
+ pnfs_set_lo_fail(wdata->lseg);
+ }
+ bio_put(bio);
+ put_parallel(par);
+}
+
+/* Function scheduled for call during bl_end_par_io_write,
+ * it marks sectors as written and extends the commitlist.
+ */
+static void bl_write_cleanup(struct work_struct *work)
+{
+ struct rpc_task *task;
+ struct nfs_write_data *wdata;
+ dprintk("%s enter\n", __func__);
+ task = container_of(work, struct rpc_task, u.tk_work);
+ wdata = container_of(task, struct nfs_write_data, task);
+ if (likely(!wdata->pnfs_error)) {
+ /* Marks for LAYOUTCOMMIT */
+ mark_extents_written(BLK_LSEG2EXT(wdata->lseg),
+ wdata->args.offset, wdata->args.count);
+ }
+ pnfs_ld_write_done(wdata);
+}
+
+/* Called when last of bios associated with a bl_write_pagelist call finishes */
+static void bl_end_par_io_write(void *data, int num_se)
+{
+ struct nfs_write_data *wdata = data;
+
+ if (unlikely(wdata->pnfs_error)) {
+ bl_free_short_extents(&BLK_LSEG2EXT(wdata->lseg)->bl_inval,
+ num_se);
+ }
+
+ wdata->task.tk_status = wdata->pnfs_error;
+ wdata->verf.committed = NFS_FILE_SYNC;
+ INIT_WORK(&wdata->task.u.tk_work, bl_write_cleanup);
+ schedule_work(&wdata->task.u.tk_work);
+}
+
+/* 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_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_write_data *wdata, int sync)
+{
+ int i, ret, npg_zero, pg_index, last = 0;
+ struct bio *bio = NULL;
+ struct pnfs_block_extent *be = NULL, *cow_read = NULL;
+ sector_t isect, last_isect = 0, extent_length = 0;
+ struct parallel_io *par;
+ loff_t offset = wdata->args.offset;
+ size_t count = wdata->args.count;
+ unsigned int pg_offset, pg_len, saved_len;
+ struct page **pages = wdata->args.pages;
+ struct page *page;
+ pgoff_t index;
+ u64 temp;
+ int npg_per_block =
+ NFS_SERVER(wdata->inode)->pnfs_blksize >> PAGE_CACHE_SHIFT;
+
+ dprintk("%s enter, %Zu@%lld\n", __func__, count, offset);
+ /* At this point, wdata->pages is a (sequential) list of nfs_pages.
+ * We want to write each, and if there is an error set pnfs_error
+ * to have it redone using nfs.
+ */
+ par = alloc_parallel(wdata);
+ if (!par)
+ goto out_mds;
+ 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(wdata->lseg), isect, &cow_read);
+ if (!be || !is_writable(be, isect)) {
+ dprintk("%s no matching extents!\n", __func__);
+ goto out_mds;
+ }
+
+ /* 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(wdata->inode, index,
+ cow_read);
+ if (unlikely(IS_ERR(page))) {
+ wdata->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);
+ wdata->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);
+ wdata->pnfs_error = -ENOMEM;
+ goto out;
+ }
+ /* FIXME: This should be done in bi_end_io */
+ mark_extents_written(BLK_LSEG2EXT(wdata->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)) {
+ wdata->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);
+
+ /* Middle pages */
+ pg_index = wdata->args.pgbase >> PAGE_CACHE_SHIFT;
+ for (i = pg_index; i < wdata->npages; i++) {
+ if (!extent_length) {
+ /* 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(wdata->lseg),
+ isect, &cow_read);
+ if (!be || !is_writable(be, isect)) {
+ wdata->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 {
+ wdata->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);
+ wdata->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);
+ wdata->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;
+ }
+ bio = do_add_page_to_bio(bio, wdata->npages - i, WRITE,
+ isect, pages[i], be,
+ bl_end_io_write, par,
+ pg_offset, pg_len);
+ if (IS_ERR(bio)) {
+ wdata->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;
+ }
+ }
+
+write_done:
+ wdata->res.count = wdata->args.count;
+out:
+ bl_put_extent(be);
+ bl_put_extent(cow_read);
+ bl_submit_bio(WRITE, bio);
+ 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);
+
+ dprintk("%s enter\n", __func__);
+ release_extents(bl, NULL);
+ release_inval_marks(&bl->bl_inval);
+ kfree(bl);
+}
+
+static struct pnfs_layout_hdr *bl_alloc_layout_hdr(struct inode *inode,
+ gfp_t gfp_flags)
+{
+ struct pnfs_block_layout *bl;
+
+ dprintk("%s enter\n", __func__);
+ bl = kzalloc(sizeof(*bl), gfp_flags);
+ if (!bl)
+ return NULL;
+ 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;
+}
+
+static void bl_free_lseg(struct pnfs_layout_segment *lseg)
+{
+ dprintk("%s enter\n", __func__);
+ 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;
+
+ 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);
+ }
+ return lseg;
+}
+
+static void
+bl_encode_layoutcommit(struct pnfs_layout_hdr *lo, struct xdr_stream *xdr,
+ const struct nfs4_layoutcommit_args *arg)
+{
+ dprintk("%s enter\n", __func__);
+ encode_pnfs_block_layoutupdate(BLK_LO2EXT(lo), xdr, arg);
+}
+
+static void
+bl_cleanup_layoutcommit(struct nfs4_layoutcommit_data *lcdata)
+{
+ struct pnfs_layout_hdr *lo = NFS_I(lcdata->args.inode)->layout;
+
+ dprintk("%s enter\n", __func__);
+ clean_pnfs_block_layoutupdate(BLK_LO2EXT(lo), &lcdata->args, lcdata->res.status);
+}
+
+static void free_blk_mountid(struct block_mount_id *mid)
+{
+ if (mid) {
+ struct pnfs_block_dev *dev, *tmp;
+
+ /* 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);
+ }
+}
+
+/* This is mostly copied from the filelayout's 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)
+{
+ struct pnfs_device *dev;
+ struct pnfs_block_dev *rv;
+ u32 max_resp_sz;
+ int max_pages;
+ struct page **pages = NULL;
+ int i, rc;
+
+ /*
+ * Use the session max response size as the basis for setting
+ * GETDEVICEINFO's maxcount
+ */
+ 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);
+ }
+
+ pages = kzalloc(max_pages * sizeof(struct page *), GFP_NOFS);
+ if (pages == NULL) {
+ kfree(dev);
+ return ERR_PTR(-ENOMEM);
+ }
+ for (i = 0; i < max_pages; i++) {
+ pages[i] = alloc_page(GFP_NOFS);
+ if (!pages[i]) {
+ rv = ERR_PTR(-ENOMEM);
+ goto out_free;
+ }
+ }
+
+ 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;
+
+ dprintk("%s: dev_id: %s\n", __func__, dev->dev_id.data);
+ rc = nfs4_proc_getdeviceinfo(server, dev);
+ dprintk("%s getdevice info returns %d\n", __func__, rc);
+ if (rc) {
+ rv = ERR_PTR(rc);
+ goto out_free;
+ }
+
+ 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;
+}
+
+static int
+bl_set_layoutdriver(struct nfs_server *server, const struct nfs_fh *fh)
+{
+ 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__);
+
+ 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;
+ }
+ 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);
+ }
+ }
+ dprintk("%s SUCCESS\n", __func__);
+ server->pnfs_ld_data = b_mt_id;
+
+ out_return:
+ kfree(dlist);
+ return status;
+
+ out_error:
+ free_blk_mountid(b_mt_id);
+ goto out_return;
+}
+
+static int
+bl_clear_layoutdriver(struct nfs_server *server)
+{
+ struct block_mount_id *b_mt_id = server->pnfs_ld_data;
+
+ dprintk("%s enter\n", __func__);
+ free_blk_mountid(b_mt_id);
+ dprintk("%s RETURNS\n", __func__);
+ return 0;
+}
+
+static const struct nfs_pageio_ops bl_pg_read_ops = {
+ .pg_init = pnfs_generic_pg_init_read,
+ .pg_test = pnfs_generic_pg_test,
+ .pg_doio = pnfs_generic_pg_readpages,
+};
+
+static const struct nfs_pageio_ops bl_pg_write_ops = {
+ .pg_init = pnfs_generic_pg_init_write,
+ .pg_test = pnfs_generic_pg_test,
+ .pg_doio = pnfs_generic_pg_writepages,
+};
+
+static struct pnfs_layoutdriver_type blocklayout_type = {
+ .id = LAYOUT_BLOCK_VOLUME,
+ .name = "LAYOUT_BLOCK_VOLUME",
+ .owner = THIS_MODULE,
+ .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,
+ .cleanup_layoutcommit = bl_cleanup_layoutcommit,
+ .set_layoutdriver = bl_set_layoutdriver,
+ .clear_layoutdriver = bl_clear_layoutdriver,
+ .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;
+
+ dprintk("%s: NFSv4 Block Layout Driver Registering...\n", __func__);
+
+ ret = pnfs_register_layoutdriver(&blocklayout_type);
+ if (ret)
+ goto out;
+
+ ret = rpc_pipefs_notifier_register(&nfs4blocklayout_block);
+ if (ret)
+ goto out_remove;
+ ret = register_pernet_subsys(&nfs4blocklayout_net_ops);
+ if (ret)
+ goto out_notifier;
+out:
+ return ret;
+
+out_notifier:
+ rpc_pipefs_notifier_unregister(&nfs4blocklayout_block);
+out_remove:
+ pnfs_unregister_layoutdriver(&blocklayout_type);
+ return ret;
+}
+
+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);
+ pnfs_unregister_layoutdriver(&blocklayout_type);
+}
+
+MODULE_ALIAS("nfs-layouttype4-3");
+
+module_init(nfs4blocklayout_init);
+module_exit(nfs4blocklayout_exit);
diff --git a/ap/os/linux/linux-3.4.x/fs/nfs/blocklayout/blocklayout.h b/ap/os/linux/linux-3.4.x/fs/nfs/blocklayout/blocklayout.h
new file mode 100644
index 0000000..39bb51a
--- /dev/null
+++ b/ap/os/linux/linux-3.4.x/fs/nfs/blocklayout/blocklayout.h
@@ -0,0 +1,211 @@
+/*
+ * 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.
+ */
+#ifndef FS_NFS_NFS4BLOCKLAYOUT_H
+#define FS_NFS_NFS4BLOCKLAYOUT_H
+
+#include <linux/device-mapper.h>
+#include <linux/nfs_fs.h>
+#include <linux/sunrpc/rpc_pipe_fs.h>
+
+#include "../pnfs.h"
+#include "../netns.h"
+
+#define PAGE_CACHE_SECTORS (PAGE_CACHE_SIZE >> SECTOR_SHIFT)
+#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 list_head bm_node;
+ struct nfs4_deviceid bm_mdevid; /* associated devid */
+ struct block_device *bm_mdev; /* meta device itself */
+ struct net *net;
+};
+
+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 MY_MAX_TAGS (15) /* tag bitnums used must be less than this */
+
+struct my_tree {
+ sector_t mtt_step_size; /* Internal sector alignment */
+ struct list_head mtt_stub; /* Should be a radix tree */
+};
+
+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_inval_tracking {
+ struct list_head it_link;
+ int it_sector;
+ int it_tags;
+};
+
+/* 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;
+ 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 */
+};
+
+/* 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;
+}
+
+struct pnfs_block_layout {
+ struct pnfs_layout_hdr bl_layout;
+ struct pnfs_inval_markings bl_inval; /* tracks INVAL->RW transition */
+ 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)
+{
+ return container_of(lo, struct pnfs_block_layout, bl_layout);
+}
+
+static inline struct pnfs_block_layout *
+BLK_LSEG2EXT(struct pnfs_layout_segment *lseg)
+{
+ return BLK_LO2EXT(lseg->pls_layout);
+}
+
+struct bl_pipe_msg {
+ struct rpc_pipe_msg msg;
+ wait_queue_head_t *bl_wq;
+};
+
+struct bl_msg_hdr {
+ u8 type;
+ u16 totallen; /* length of entire message, including hdr itself */
+};
+
+#define BL_DEVICE_UMOUNT 0x0 /* Umount--delete devices */
+#define BL_DEVICE_MOUNT 0x1 /* Mount--create devices*/
+#define BL_DEVICE_REQUEST_INIT 0x0 /* Start request */
+#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 *);
+struct block_device *nfs4_blkdev_get(dev_t dev);
+int 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);
+
+#endif /* FS_NFS_NFS4BLOCKLAYOUT_H */
diff --git a/ap/os/linux/linux-3.4.x/fs/nfs/blocklayout/blocklayoutdev.c b/ap/os/linux/linux-3.4.x/fs/nfs/blocklayout/blocklayoutdev.c
new file mode 100644
index 0000000..a5c88a5
--- /dev/null
+++ b/ap/os/linux/linux-3.4.x/fs/nfs/blocklayout/blocklayoutdev.c
@@ -0,0 +1,399 @@
+/*
+ * 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;
+}
+
+/* Open a block_device by device number. */
+struct block_device *nfs4_blkdev_get(dev_t dev)
+{
+ struct block_device *bd;
+
+ dprintk("%s enter\n", __func__);
+ bd = blkdev_get_by_dev(dev, FMODE_READ, NULL);
+ if (IS_ERR(bd))
+ goto fail;
+ return bd;
+fail:
+ dprintk("%s failed to open device : %ld\n",
+ __func__, PTR_ERR(bd));
+ return NULL;
+}
+
+/*
+ * Release the block device
+ */
+int nfs4_blkdev_put(struct block_device *bdev)
+{
+ dprintk("%s for device %d:%d\n", __func__, MAJOR(bdev->bd_dev),
+ MINOR(bdev->bd_dev));
+ return 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->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 = nfs4_blkdev_get(MKDEV(reply->major, reply->minor));
+ if (IS_ERR(bd)) {
+ rc = PTR_ERR(bd);
+ dprintk("%s failed to open device : %d\n", __func__, rc);
+ rv = ERR_PTR(rc);
+ 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/ap/os/linux/linux-3.4.x/fs/nfs/blocklayout/blocklayoutdm.c b/ap/os/linux/linux-3.4.x/fs/nfs/blocklayout/blocklayoutdm.c
new file mode 100644
index 0000000..6fc7b5c
--- /dev/null
+++ b/ap/os/linux/linux-3.4.x/fs/nfs/blocklayout/blocklayoutdm.c
@@ -0,0 +1,114 @@
+/*
+ * 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)
+{
+ int rv;
+
+ dprintk("%s Releasing\n", __func__);
+ rv = nfs4_blkdev_put(bdev->bm_mdev);
+ if (rv)
+ printk(KERN_ERR "NFS: %s nfs4_blkdev_put returns %d\n",
+ __func__, rv);
+
+ 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/ap/os/linux/linux-3.4.x/fs/nfs/blocklayout/extents.c b/ap/os/linux/linux-3.4.x/fs/nfs/blocklayout/extents.c
new file mode 100644
index 0000000..51f9ff2
--- /dev/null
+++ b/ap/os/linux/linux-3.4.x/fs/nfs/blocklayout/extents.c
@@ -0,0 +1,909 @@
+/*
+ * 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_del(&lce->bse_node);
+ list_add_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);
+}