1 files changed, 192 insertions, 144 deletions

diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 4acf1f78881b..6625d210fb45 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -25,6 +25,7 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/mm.h>
+#include <linux/ratelimit.h>
 
 #include "ext4_jbd2.h"
 #include "xattr.h"
@@ -46,46 +47,121 @@ void ext4_exit_pageio(void)
 }
 
 /*
- * This function is called by ext4_evict_inode() to make sure there is
- * no more pending I/O completion work left to do.
+ * Print an buffer I/O error compatible with the fs/buffer.c.  This
+ * provides compatibility with dmesg scrapers that look for a specific
+ * buffer I/O error message.  We really need a unified error reporting
+ * structure to userspace ala Digital Unix's uerf system, but it's
+ * probably not going to happen in my lifetime, due to LKML politics...
  */
-void ext4_ioend_shutdown(struct inode *inode)
+static void buffer_io_error(struct buffer_head *bh)
+{
+        char b[BDEVNAME_SIZE];
+        printk_ratelimited(KERN_ERR "Buffer I/O error on device %s, logical block %llu\n",
+                        bdevname(bh->b_bdev, b),
+                        (unsigned long long)bh->b_blocknr);
+}
+
+static void ext4_finish_bio(struct bio *bio)
 {
-        wait_queue_head_t *wq = ext4_ioend_wq(inode);
+        int i;
+        int error = !test_bit(BIO_UPTODATE, &bio->bi_flags);
 
-        wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_ioend_count) == 0));
-        /*
-         * We need to make sure the work structure is finished being
-         * used before we let the inode get destroyed.
-         */
-        if (work_pending(&EXT4_I(inode)->i_unwritten_work))
-                cancel_work_sync(&EXT4_I(inode)->i_unwritten_work);
+        for (i = 0; i < bio->bi_vcnt; i++) {
+                struct bio_vec *bvec = &bio->bi_io_vec[i];
+                struct page *page = bvec->bv_page;
+                struct buffer_head *bh, *head;
+                unsigned bio_start = bvec->bv_offset;
+                unsigned bio_end = bio_start + bvec->bv_len;
+                unsigned under_io = 0;
+                unsigned long flags;
+
+                if (!page)
+                        continue;
+
+                if (error) {
+                        SetPageError(page);
+                        set_bit(AS_EIO, &page->mapping->flags);
+                }
+                bh = head = page_buffers(page);
+                /*
+                 * We check all buffers in the page under BH_Uptodate_Lock
+                 * to avoid races with other end io clearing async_write flags
+                 */
+                local_irq_save(flags);
+                bit_spin_lock(BH_Uptodate_Lock, &head->b_state);
+                do {
+                        if (bh_offset(bh) < bio_start ||
+                            bh_offset(bh) + bh->b_size > bio_end) {
+                                if (buffer_async_write(bh))
+                                        under_io++;
+                                continue;
+                        }
+                        clear_buffer_async_write(bh);
+                        if (error)
+                                buffer_io_error(bh);
+                } while ((bh = bh->b_this_page) != head);
+                bit_spin_unlock(BH_Uptodate_Lock, &head->b_state);
+                local_irq_restore(flags);
+                if (!under_io)
+                        end_page_writeback(page);
+        }
+}
+
+static void ext4_release_io_end(ext4_io_end_t *io_end)
+{
+        struct bio *bio, *next_bio;
+
+        BUG_ON(!list_empty(&io_end->list));
+        BUG_ON(io_end->flag & EXT4_IO_END_UNWRITTEN);
+        WARN_ON(io_end->handle);
+
+        if (atomic_dec_and_test(&EXT4_I(io_end->inode)->i_ioend_count))
+                wake_up_all(ext4_ioend_wq(io_end->inode));
+
+        for (bio = io_end->bio; bio; bio = next_bio) {
+                next_bio = bio->bi_private;
+                ext4_finish_bio(bio);
+                bio_put(bio);
+        }
+        if (io_end->flag & EXT4_IO_END_DIRECT)
+                inode_dio_done(io_end->inode);
+        if (io_end->iocb)
+                aio_complete(io_end->iocb, io_end->result, 0);
+        kmem_cache_free(io_end_cachep, io_end);
 }
 
-void ext4_free_io_end(ext4_io_end_t *io)
+static void ext4_clear_io_unwritten_flag(ext4_io_end_t *io_end)
 {
-        BUG_ON(!io);
-        BUG_ON(!list_empty(&io->list));
-        BUG_ON(io->flag & EXT4_IO_END_UNWRITTEN);
+        struct inode *inode = io_end->inode;
 
-        if (atomic_dec_and_test(&EXT4_I(io->inode)->i_ioend_count))
-                wake_up_all(ext4_ioend_wq(io->inode));
-        kmem_cache_free(io_end_cachep, io);
+        io_end->flag &= ~EXT4_IO_END_UNWRITTEN;
+        /* Wake up anyone waiting on unwritten extent conversion */
+        if (atomic_dec_and_test(&EXT4_I(inode)->i_unwritten))
+                wake_up_all(ext4_ioend_wq(inode));
 }
 
-/* check a range of space and convert unwritten extents to written. */
+/*
+ * Check a range of space and convert unwritten extents to written. Note that
+ * we are protected from truncate touching same part of extent tree by the
+ * fact that truncate code waits for all DIO to finish (thus exclusion from
+ * direct IO is achieved) and also waits for PageWriteback bits. Thus we
+ * cannot get to ext4_ext_truncate() before all IOs overlapping that range are
+ * completed (happens from ext4_free_ioend()).
+ */
 static int ext4_end_io(ext4_io_end_t *io)
 {
         struct inode *inode = io->inode;
         loff_t offset = io->offset;
         ssize_t size = io->size;
+        handle_t *handle = io->handle;
         int ret = 0;
 
         ext4_debug("ext4_end_io_nolock: io 0x%p from inode %lu,list->next 0x%p,"
                    "list->prev 0x%p\n",
                    io, inode->i_ino, io->list.next, io->list.prev);
 
-        ret = ext4_convert_unwritten_extents(inode, offset, size);
+        io->handle = NULL;      /* Following call will use up the handle */
+        ret = ext4_convert_unwritten_extents(handle, inode, offset, size);
         if (ret < 0) {
                 ext4_msg(inode->i_sb, KERN_EMERG,
                          "failed to convert unwritten extents to written "
@@ -93,30 +169,22 @@ static int ext4_end_io(ext4_io_end_t *io)
                          "(inode %lu, offset %llu, size %zd, error %d)",
                          inode->i_ino, offset, size, ret);
         }
-        /* Wake up anyone waiting on unwritten extent conversion */
-        if (atomic_dec_and_test(&EXT4_I(inode)->i_unwritten))
-                wake_up_all(ext4_ioend_wq(inode));
-        if (io->flag & EXT4_IO_END_DIRECT)
-                inode_dio_done(inode);
-        if (io->iocb)
-                aio_complete(io->iocb, io->result, 0);
+        ext4_clear_io_unwritten_flag(io);
+        ext4_release_io_end(io);
         return ret;
 }
 
-static void dump_completed_IO(struct inode *inode)
+static void dump_completed_IO(struct inode *inode, struct list_head *head)
 {
 #ifdef  EXT4FS_DEBUG
         struct list_head *cur, *before, *after;
         ext4_io_end_t *io, *io0, *io1;
 
-        if (list_empty(&EXT4_I(inode)->i_completed_io_list)) {
-                ext4_debug("inode %lu completed_io list is empty\n",
-                           inode->i_ino);
+        if (list_empty(head))
                 return;
-        }
 
-        ext4_debug("Dump inode %lu completed_io list\n", inode->i_ino);
-        list_for_each_entry(io, &EXT4_I(inode)->i_completed_io_list, list) {
+        ext4_debug("Dump inode %lu completed io list\n", inode->i_ino);
+        list_for_each_entry(io, head, list) {
                 cur = &io->list;
                 before = cur->prev;
                 io0 = container_of(before, ext4_io_end_t, list);
@@ -130,23 +198,30 @@ static void dump_completed_IO(struct inode *inode)
 }
 
 /* Add the io_end to per-inode completed end_io list. */
-void ext4_add_complete_io(ext4_io_end_t *io_end)
+static void ext4_add_complete_io(ext4_io_end_t *io_end)
 {
         struct ext4_inode_info *ei = EXT4_I(io_end->inode);
         struct workqueue_struct *wq;
         unsigned long flags;
 
         BUG_ON(!(io_end->flag & EXT4_IO_END_UNWRITTEN));
-        wq = EXT4_SB(io_end->inode->i_sb)->dio_unwritten_wq;
-
         spin_lock_irqsave(&ei->i_completed_io_lock, flags);
-        if (list_empty(&ei->i_completed_io_list))
-                queue_work(wq, &ei->i_unwritten_work);
-        list_add_tail(&io_end->list, &ei->i_completed_io_list);
+        if (io_end->handle) {
+                wq = EXT4_SB(io_end->inode->i_sb)->rsv_conversion_wq;
+                if (list_empty(&ei->i_rsv_conversion_list))
+                        queue_work(wq, &ei->i_rsv_conversion_work);
+                list_add_tail(&io_end->list, &ei->i_rsv_conversion_list);
+        } else {
+                wq = EXT4_SB(io_end->inode->i_sb)->unrsv_conversion_wq;
+                if (list_empty(&ei->i_unrsv_conversion_list))
+                        queue_work(wq, &ei->i_unrsv_conversion_work);
+                list_add_tail(&io_end->list, &ei->i_unrsv_conversion_list);
+        }
         spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
 }
 
-static int ext4_do_flush_completed_IO(struct inode *inode)
+static int ext4_do_flush_completed_IO(struct inode *inode,
+                                      struct list_head *head)
 {
         ext4_io_end_t *io;
         struct list_head unwritten;
@@ -155,8 +230,8 @@ static int ext4_do_flush_completed_IO(struct inode *inode)
         int err, ret = 0;
 
         spin_lock_irqsave(&ei->i_completed_io_lock, flags);
-        dump_completed_IO(inode);
-        list_replace_init(&ei->i_completed_io_list, &unwritten);
+        dump_completed_IO(inode, head);
+        list_replace_init(head, &unwritten);
         spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
 
         while (!list_empty(&unwritten)) {
@@ -167,30 +242,25 @@ static int ext4_do_flush_completed_IO(struct inode *inode)
                 err = ext4_end_io(io);
                 if (unlikely(!ret && err))
                         ret = err;
-                io->flag &= ~EXT4_IO_END_UNWRITTEN;
-                ext4_free_io_end(io);
         }
         return ret;
 }
 
 /*
- * work on completed aio dio IO, to convert unwritten extents to extents
+ * work on completed IO, to convert unwritten extents to extents
  */
-void ext4_end_io_work(struct work_struct *work)
+void ext4_end_io_rsv_work(struct work_struct *work)
 {
         struct ext4_inode_info *ei = container_of(work, struct ext4_inode_info,
-                                                  i_unwritten_work);
-        ext4_do_flush_completed_IO(&ei->vfs_inode);
+                                                  i_rsv_conversion_work);
+        ext4_do_flush_completed_IO(&ei->vfs_inode, &ei->i_rsv_conversion_list);
 }
 
-int ext4_flush_unwritten_io(struct inode *inode)
+void ext4_end_io_unrsv_work(struct work_struct *work)
 {
-        int ret;
-        WARN_ON_ONCE(!mutex_is_locked(&inode->i_mutex) &&
-                     !(inode->i_state & I_FREEING));
-        ret = ext4_do_flush_completed_IO(inode);
-        ext4_unwritten_wait(inode);
-        return ret;
+        struct ext4_inode_info *ei = container_of(work, struct ext4_inode_info,
+                                                  i_unrsv_conversion_work);
+        ext4_do_flush_completed_IO(&ei->vfs_inode, &ei->i_unrsv_conversion_list);
 }
 
 ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags)
@@ -200,83 +270,59 @@ ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags)
                 atomic_inc(&EXT4_I(inode)->i_ioend_count);
                 io->inode = inode;
                 INIT_LIST_HEAD(&io->list);
+                atomic_set(&io->count, 1);
         }
         return io;
 }
 
-/*
- * Print an buffer I/O error compatible with the fs/buffer.c.  This
- * provides compatibility with dmesg scrapers that look for a specific
- * buffer I/O error message.  We really need a unified error reporting
- * structure to userspace ala Digital Unix's uerf system, but it's
- * probably not going to happen in my lifetime, due to LKML politics...
- */
-static void buffer_io_error(struct buffer_head *bh)
+void ext4_put_io_end_defer(ext4_io_end_t *io_end)
 {
-        char b[BDEVNAME_SIZE];
-        printk(KERN_ERR "Buffer I/O error on device %s, logical block %llu\n",
-                        bdevname(bh->b_bdev, b),
-                        (unsigned long long)bh->b_blocknr);
+        if (atomic_dec_and_test(&io_end->count)) {
+                if (!(io_end->flag & EXT4_IO_END_UNWRITTEN) || !io_end->size) {
+                        ext4_release_io_end(io_end);
+                        return;
+                }
+                ext4_add_complete_io(io_end);
+        }
 }
 
+int ext4_put_io_end(ext4_io_end_t *io_end)
+{
+        int err = 0;
+
+        if (atomic_dec_and_test(&io_end->count)) {
+                if (io_end->flag & EXT4_IO_END_UNWRITTEN) {
+                        err = ext4_convert_unwritten_extents(io_end->handle,
+                                                io_end->inode, io_end->offset,
+                                                io_end->size);
+                        io_end->handle = NULL;
+                        ext4_clear_io_unwritten_flag(io_end);
+                }
+                ext4_release_io_end(io_end);
+        }
+        return err;
+}
+
+ext4_io_end_t *ext4_get_io_end(ext4_io_end_t *io_end)
+{
+        atomic_inc(&io_end->count);
+        return io_end;
+}
+
+/* BIO completion function for page writeback */
 static void ext4_end_bio(struct bio *bio, int error)
 {
         ext4_io_end_t *io_end = bio->bi_private;
-        struct inode *inode;
-        int i;
-        int blocksize;
         sector_t bi_sector = bio->bi_sector;
 
         BUG_ON(!io_end);
-        inode = io_end->inode;
-        blocksize = 1 << inode->i_blkbits;
-        bio->bi_private = NULL;
         bio->bi_end_io = NULL;
         if (test_bit(BIO_UPTODATE, &bio->bi_flags))
                 error = 0;
-        for (i = 0; i < bio->bi_vcnt; i++) {
-                struct bio_vec *bvec = &bio->bi_io_vec[i];
-                struct page *page = bvec->bv_page;
-                struct buffer_head *bh, *head;
-                unsigned bio_start = bvec->bv_offset;
-                unsigned bio_end = bio_start + bvec->bv_len;
-                unsigned under_io = 0;
-                unsigned long flags;
-
-                if (!page)
-                        continue;
-
-                if (error) {
-                        SetPageError(page);
-                        set_bit(AS_EIO, &page->mapping->flags);
-                }
-                bh = head = page_buffers(page);
-                /*
-                 * We check all buffers in the page under BH_Uptodate_Lock
-                 * to avoid races with other end io clearing async_write flags
-                 */
-                local_irq_save(flags);
-                bit_spin_lock(BH_Uptodate_Lock, &head->b_state);
-                do {
-                        if (bh_offset(bh) < bio_start ||
-                            bh_offset(bh) + blocksize > bio_end) {
-                                if (buffer_async_write(bh))
-                                        under_io++;
-                                continue;
-                        }
-                        clear_buffer_async_write(bh);
-                        if (error)
-                                buffer_io_error(bh);
-                } while ((bh = bh->b_this_page) != head);
-                bit_spin_unlock(BH_Uptodate_Lock, &head->b_state);
-                local_irq_restore(flags);
-                if (!under_io)
-                        end_page_writeback(page);
-        }
-        bio_put(bio);
 
         if (error) {
-                io_end->flag |= EXT4_IO_END_ERROR;
+                struct inode *inode = io_end->inode;
+
                 ext4_warning(inode->i_sb, "I/O error writing to inode %lu "
                              "(offset %llu size %ld starting block %llu)",
                              inode->i_ino,
@@ -286,12 +332,23 @@ static void ext4_end_bio(struct bio *bio, int error)
                              bi_sector >> (inode->i_blkbits - 9));
         }
 
-        if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
-                ext4_free_io_end(io_end);
-                return;
+        if (io_end->flag & EXT4_IO_END_UNWRITTEN) {
+                /*
+                 * Link bio into list hanging from io_end. We have to do it
+                 * atomically as bio completions can be racing against each
+                 * other.
+                 */
+                bio->bi_private = xchg(&io_end->bio, bio);
+                ext4_put_io_end_defer(io_end);
+        } else {
+                /*
+                 * Drop io_end reference early. Inode can get freed once
+                 * we finish the bio.
+                 */
+                ext4_put_io_end_defer(io_end);
+                ext4_finish_bio(bio);
+                bio_put(bio);
         }
-
-        ext4_add_complete_io(io_end);
 }
 
 void ext4_io_submit(struct ext4_io_submit *io)
@@ -305,43 +362,38 @@ void ext4_io_submit(struct ext4_io_submit *io)
                 bio_put(io->io_bio);
         }
         io->io_bio = NULL;
-        io->io_op = 0;
+}
+
+void ext4_io_submit_init(struct ext4_io_submit *io,
+                         struct writeback_control *wbc)
+{
+        io->io_op = (wbc->sync_mode == WB_SYNC_ALL ?  WRITE_SYNC : WRITE);
+        io->io_bio = NULL;
         io->io_end = NULL;
 }
 
-static int io_submit_init(struct ext4_io_submit *io,
-                          struct inode *inode,
-                          struct writeback_control *wbc,
-                          struct buffer_head *bh)
+static int io_submit_init_bio(struct ext4_io_submit *io,
+                              struct buffer_head *bh)
 {
-        ext4_io_end_t *io_end;
-        struct page *page = bh->b_page;
         int nvecs = bio_get_nr_vecs(bh->b_bdev);
         struct bio *bio;
 
-        io_end = ext4_init_io_end(inode, GFP_NOFS);
-        if (!io_end)
-                return -ENOMEM;
         bio = bio_alloc(GFP_NOIO, min(nvecs, BIO_MAX_PAGES));
+        if (!bio)
+                return -ENOMEM;
         bio->bi_sector = bh->b_blocknr * (bh->b_size >> 9);
         bio->bi_bdev = bh->b_bdev;
-        bio->bi_private = io->io_end = io_end;
         bio->bi_end_io = ext4_end_bio;
-
-        io_end->offset = (page->index << PAGE_CACHE_SHIFT) + bh_offset(bh);
-
+        bio->bi_private = ext4_get_io_end(io->io_end);
         io->io_bio = bio;
-        io->io_op = (wbc->sync_mode == WB_SYNC_ALL ?  WRITE_SYNC : WRITE);
         io->io_next_block = bh->b_blocknr;
         return 0;
 }
 
 static int io_submit_add_bh(struct ext4_io_submit *io,
                             struct inode *inode,
-                            struct writeback_control *wbc,
                             struct buffer_head *bh)
 {
-        ext4_io_end_t *io_end;
         int ret;
 
         if (io->io_bio && bh->b_blocknr != io->io_next_block) {
@@ -349,18 +401,14 @@ submit_and_retry:
                 ext4_io_submit(io);
         }
         if (io->io_bio == NULL) {
-                ret = io_submit_init(io, inode, wbc, bh);
+                ret = io_submit_init_bio(io, bh);
                 if (ret)
                         return ret;
         }
-        io_end = io->io_end;
-        if (test_clear_buffer_uninit(bh))
-                ext4_set_io_unwritten_flag(inode, io_end);
-        io->io_end->size += bh->b_size;
-        io->io_next_block++;
         ret = bio_add_page(io->io_bio, bh->b_page, bh->b_size, bh_offset(bh));
         if (ret != bh->b_size)
                 goto submit_and_retry;
+        io->io_next_block++;
         return 0;
 }
 
@@ -432,7 +480,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
         do {
                 if (!buffer_async_write(bh))
                         continue;
-                ret = io_submit_add_bh(io, inode, wbc, bh);
+                ret = io_submit_add_bh(io, inode, bh);
                 if (ret) {
                         /*
                          * We only get here on ENOMEM.  Not much else