diff options
Diffstat (limited to 'fs/nilfs2/inode.c')
-rw-r--r-- | fs/nilfs2/inode.c | 351 |
1 files changed, 288 insertions, 63 deletions
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index eccb2f2e2315..2fd440d8d6b8 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -34,6 +34,12 @@ #include "cpfile.h" #include "ifile.h" +struct nilfs_iget_args { + u64 ino; + __u64 cno; + struct nilfs_root *root; + int for_gc; +}; /** * nilfs_get_block() - get a file block on the filesystem (callback function) @@ -52,7 +58,7 @@ int nilfs_get_block(struct inode *inode, sector_t blkoff, struct nilfs_inode_info *ii = NILFS_I(inode); __u64 blknum = 0; int err = 0, ret; - struct inode *dat = nilfs_dat_inode(NILFS_I_NILFS(inode)); + struct inode *dat = NILFS_I_NILFS(inode)->ns_dat; unsigned maxblocks = bh_result->b_size >> inode->i_blkbits; down_read(&NILFS_MDT(dat)->mi_sem); @@ -90,11 +96,6 @@ int nilfs_get_block(struct inode *inode, sector_t blkoff, inode->i_ino, (unsigned long long)blkoff); err = 0; - } else if (err == -EINVAL) { - nilfs_error(inode->i_sb, __func__, - "broken bmap (inode=%lu)\n", - inode->i_ino); - err = -EIO; } nilfs_transaction_abort(inode->i_sb); goto out; @@ -103,6 +104,7 @@ int nilfs_get_block(struct inode *inode, sector_t blkoff, nilfs_transaction_commit(inode->i_sb); /* never fails */ /* Error handling should be detailed */ set_buffer_new(bh_result); + set_buffer_delay(bh_result); map_bh(bh_result, inode->i_sb, 0); /* dbn must be changed to proper value */ } else if (ret == -ENOENT) { @@ -179,10 +181,9 @@ static int nilfs_set_page_dirty(struct page *page) if (ret) { struct inode *inode = page->mapping->host; - struct nilfs_sb_info *sbi = NILFS_SB(inode->i_sb); unsigned nr_dirty = 1 << (PAGE_SHIFT - inode->i_blkbits); - nilfs_set_file_dirty(sbi, inode, nr_dirty); + nilfs_set_file_dirty(inode, nr_dirty); } return ret; } @@ -223,7 +224,7 @@ static int nilfs_write_end(struct file *file, struct address_space *mapping, start + copied); copied = generic_write_end(file, mapping, pos, len, copied, page, fsdata); - nilfs_set_file_dirty(NILFS_SB(inode->i_sb), inode, nr_dirty); + nilfs_set_file_dirty(inode, nr_dirty); err = nilfs_transaction_commit(inode->i_sb); return err ? : copied; } @@ -279,6 +280,7 @@ struct inode *nilfs_new_inode(struct inode *dir, int mode) struct nilfs_sb_info *sbi = NILFS_SB(sb); struct inode *inode; struct nilfs_inode_info *ii; + struct nilfs_root *root; int err = -ENOMEM; ino_t ino; @@ -289,15 +291,17 @@ struct inode *nilfs_new_inode(struct inode *dir, int mode) mapping_set_gfp_mask(inode->i_mapping, mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS); + root = NILFS_I(dir)->i_root; ii = NILFS_I(inode); ii->i_state = 1 << NILFS_I_NEW; + ii->i_root = root; - err = nilfs_ifile_create_inode(sbi->s_ifile, &ino, &ii->i_bh); + err = nilfs_ifile_create_inode(root->ifile, &ino, &ii->i_bh); if (unlikely(err)) goto failed_ifile_create_inode; /* reference count of i_bh inherits from nilfs_mdt_read_block() */ - atomic_inc(&sbi->s_inodes_count); + atomic_inc(&root->inodes_count); inode_init_owner(inode, dir, mode); inode->i_ino = ino; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; @@ -320,7 +324,6 @@ struct inode *nilfs_new_inode(struct inode *dir, int mode) /* ii->i_file_acl = 0; */ /* ii->i_dir_acl = 0; */ ii->i_dir_start_lookup = 0; - ii->i_cno = 0; nilfs_set_inode_flags(inode); spin_lock(&sbi->s_next_gen_lock); inode->i_generation = sbi->s_next_generation++; @@ -350,16 +353,6 @@ struct inode *nilfs_new_inode(struct inode *dir, int mode) return ERR_PTR(err); } -void nilfs_free_inode(struct inode *inode) -{ - struct super_block *sb = inode->i_sb; - struct nilfs_sb_info *sbi = NILFS_SB(sb); - - /* XXX: check error code? Is there any thing I can do? */ - (void) nilfs_ifile_delete_inode(sbi->s_ifile, inode->i_ino); - atomic_dec(&sbi->s_inodes_count); -} - void nilfs_set_inode_flags(struct inode *inode) { unsigned int flags = NILFS_I(inode)->i_flags; @@ -410,7 +403,6 @@ int nilfs_read_inode_common(struct inode *inode, 0 : le32_to_cpu(raw_inode->i_dir_acl); #endif ii->i_dir_start_lookup = 0; - ii->i_cno = 0; inode->i_generation = le32_to_cpu(raw_inode->i_generation); if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || @@ -424,21 +416,21 @@ int nilfs_read_inode_common(struct inode *inode, return 0; } -static int __nilfs_read_inode(struct super_block *sb, unsigned long ino, +static int __nilfs_read_inode(struct super_block *sb, + struct nilfs_root *root, unsigned long ino, struct inode *inode) { - struct nilfs_sb_info *sbi = NILFS_SB(sb); - struct inode *dat = nilfs_dat_inode(sbi->s_nilfs); + struct the_nilfs *nilfs = NILFS_SB(sb)->s_nilfs; struct buffer_head *bh; struct nilfs_inode *raw_inode; int err; - down_read(&NILFS_MDT(dat)->mi_sem); /* XXX */ - err = nilfs_ifile_get_inode_block(sbi->s_ifile, ino, &bh); + down_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem); + err = nilfs_ifile_get_inode_block(root->ifile, ino, &bh); if (unlikely(err)) goto bad_inode; - raw_inode = nilfs_ifile_map_inode(sbi->s_ifile, ino, bh); + raw_inode = nilfs_ifile_map_inode(root->ifile, ino, bh); err = nilfs_read_inode_common(inode, raw_inode); if (err) @@ -461,33 +453,110 @@ static int __nilfs_read_inode(struct super_block *sb, unsigned long ino, inode, inode->i_mode, huge_decode_dev(le64_to_cpu(raw_inode->i_device_code))); } - nilfs_ifile_unmap_inode(sbi->s_ifile, ino, bh); + nilfs_ifile_unmap_inode(root->ifile, ino, bh); brelse(bh); - up_read(&NILFS_MDT(dat)->mi_sem); /* XXX */ + up_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem); nilfs_set_inode_flags(inode); return 0; failed_unmap: - nilfs_ifile_unmap_inode(sbi->s_ifile, ino, bh); + nilfs_ifile_unmap_inode(root->ifile, ino, bh); brelse(bh); bad_inode: - up_read(&NILFS_MDT(dat)->mi_sem); /* XXX */ + up_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem); return err; } -struct inode *nilfs_iget(struct super_block *sb, unsigned long ino) +static int nilfs_iget_test(struct inode *inode, void *opaque) +{ + struct nilfs_iget_args *args = opaque; + struct nilfs_inode_info *ii; + + if (args->ino != inode->i_ino || args->root != NILFS_I(inode)->i_root) + return 0; + + ii = NILFS_I(inode); + if (!test_bit(NILFS_I_GCINODE, &ii->i_state)) + return !args->for_gc; + + return args->for_gc && args->cno == ii->i_cno; +} + +static int nilfs_iget_set(struct inode *inode, void *opaque) +{ + struct nilfs_iget_args *args = opaque; + + inode->i_ino = args->ino; + if (args->for_gc) { + NILFS_I(inode)->i_state = 1 << NILFS_I_GCINODE; + NILFS_I(inode)->i_cno = args->cno; + NILFS_I(inode)->i_root = NULL; + } else { + if (args->root && args->ino == NILFS_ROOT_INO) + nilfs_get_root(args->root); + NILFS_I(inode)->i_root = args->root; + } + return 0; +} + +struct inode *nilfs_ilookup(struct super_block *sb, struct nilfs_root *root, + unsigned long ino) +{ + struct nilfs_iget_args args = { + .ino = ino, .root = root, .cno = 0, .for_gc = 0 + }; + + return ilookup5(sb, ino, nilfs_iget_test, &args); +} + +struct inode *nilfs_iget_locked(struct super_block *sb, struct nilfs_root *root, + unsigned long ino) +{ + struct nilfs_iget_args args = { + .ino = ino, .root = root, .cno = 0, .for_gc = 0 + }; + + return iget5_locked(sb, ino, nilfs_iget_test, nilfs_iget_set, &args); +} + +struct inode *nilfs_iget(struct super_block *sb, struct nilfs_root *root, + unsigned long ino) +{ + struct inode *inode; + int err; + + inode = nilfs_iget_locked(sb, root, ino); + if (unlikely(!inode)) + return ERR_PTR(-ENOMEM); + if (!(inode->i_state & I_NEW)) + return inode; + + err = __nilfs_read_inode(sb, root, ino, inode); + if (unlikely(err)) { + iget_failed(inode); + return ERR_PTR(err); + } + unlock_new_inode(inode); + return inode; +} + +struct inode *nilfs_iget_for_gc(struct super_block *sb, unsigned long ino, + __u64 cno) { + struct nilfs_iget_args args = { + .ino = ino, .root = NULL, .cno = cno, .for_gc = 1 + }; struct inode *inode; int err; - inode = iget_locked(sb, ino); + inode = iget5_locked(sb, ino, nilfs_iget_test, nilfs_iget_set, &args); if (unlikely(!inode)) return ERR_PTR(-ENOMEM); if (!(inode->i_state & I_NEW)) return inode; - err = __nilfs_read_inode(sb, ino, inode); + err = nilfs_init_gcinode(inode); if (unlikely(err)) { iget_failed(inode); return ERR_PTR(err); @@ -528,21 +597,20 @@ void nilfs_update_inode(struct inode *inode, struct buffer_head *ibh) { ino_t ino = inode->i_ino; struct nilfs_inode_info *ii = NILFS_I(inode); - struct super_block *sb = inode->i_sb; - struct nilfs_sb_info *sbi = NILFS_SB(sb); + struct inode *ifile = ii->i_root->ifile; struct nilfs_inode *raw_inode; - raw_inode = nilfs_ifile_map_inode(sbi->s_ifile, ino, ibh); + raw_inode = nilfs_ifile_map_inode(ifile, ino, ibh); if (test_and_clear_bit(NILFS_I_NEW, &ii->i_state)) - memset(raw_inode, 0, NILFS_MDT(sbi->s_ifile)->mi_entry_size); + memset(raw_inode, 0, NILFS_MDT(ifile)->mi_entry_size); set_bit(NILFS_I_INODE_DIRTY, &ii->i_state); nilfs_write_inode_common(inode, raw_inode, 0); /* XXX: call with has_bmap = 0 is a workaround to avoid deadlock of bmap. This delays update of i_bmap to just before writing */ - nilfs_ifile_unmap_inode(sbi->s_ifile, ino, ibh); + nilfs_ifile_unmap_inode(ifile, ino, ibh); } #define NILFS_MAX_TRUNCATE_BLOCKS 16384 /* 64MB for 4KB block */ @@ -555,7 +623,7 @@ static void nilfs_truncate_bmap(struct nilfs_inode_info *ii, if (!test_bit(NILFS_I_BMAP, &ii->i_state)) return; - repeat: +repeat: ret = nilfs_bmap_last_key(ii->i_bmap, &b); if (ret == -ENOENT) return; @@ -572,14 +640,10 @@ static void nilfs_truncate_bmap(struct nilfs_inode_info *ii, nilfs_bmap_truncate(ii->i_bmap, b) == 0)) goto repeat; - failed: - if (ret == -EINVAL) - nilfs_error(ii->vfs_inode.i_sb, __func__, - "bmap is broken (ino=%lu)", ii->vfs_inode.i_ino); - else - nilfs_warning(ii->vfs_inode.i_sb, __func__, - "failed to truncate bmap (ino=%lu, err=%d)", - ii->vfs_inode.i_ino, ret); +failed: + nilfs_warning(ii->vfs_inode.i_sb, __func__, + "failed to truncate bmap (ino=%lu, err=%d)", + ii->vfs_inode.i_ino, ret); } void nilfs_truncate(struct inode *inode) @@ -608,7 +672,7 @@ void nilfs_truncate(struct inode *inode) nilfs_set_transaction_flag(NILFS_TI_SYNC); nilfs_mark_inode_dirty(inode); - nilfs_set_file_dirty(NILFS_SB(sb), inode, 0); + nilfs_set_file_dirty(inode, 0); nilfs_transaction_commit(sb); /* May construct a logical segment and may fail in sync mode. But truncate has no return value. */ @@ -617,6 +681,7 @@ void nilfs_truncate(struct inode *inode) static void nilfs_clear_inode(struct inode *inode) { struct nilfs_inode_info *ii = NILFS_I(inode); + struct nilfs_mdt_info *mdi = NILFS_MDT(inode); /* * Free resources allocated in nilfs_read_inode(), here. @@ -625,10 +690,16 @@ static void nilfs_clear_inode(struct inode *inode) brelse(ii->i_bh); ii->i_bh = NULL; + if (mdi && mdi->mi_palloc_cache) + nilfs_palloc_destroy_cache(inode); + if (test_bit(NILFS_I_BMAP, &ii->i_state)) nilfs_bmap_clear(ii->i_bmap); nilfs_btnode_cache_clear(&ii->i_btnode_cache); + + if (ii->i_root && inode->i_ino == NILFS_ROOT_INO) + nilfs_put_root(ii->i_root); } void nilfs_evict_inode(struct inode *inode) @@ -637,7 +708,7 @@ void nilfs_evict_inode(struct inode *inode) struct super_block *sb = inode->i_sb; struct nilfs_inode_info *ii = NILFS_I(inode); - if (inode->i_nlink || unlikely(is_bad_inode(inode))) { + if (inode->i_nlink || !ii->i_root || unlikely(is_bad_inode(inode))) { if (inode->i_data.nrpages) truncate_inode_pages(&inode->i_data, 0); end_writeback(inode); @@ -649,12 +720,16 @@ void nilfs_evict_inode(struct inode *inode) if (inode->i_data.nrpages) truncate_inode_pages(&inode->i_data, 0); + /* TODO: some of the following operations may fail. */ nilfs_truncate_bmap(ii, 0); nilfs_mark_inode_dirty(inode); end_writeback(inode); + + nilfs_ifile_delete_inode(ii->i_root->ifile, inode->i_ino); + atomic_dec(&ii->i_root->inodes_count); + nilfs_clear_inode(inode); - nilfs_free_inode(inode); - /* nilfs_free_inode() marks inode buffer dirty */ + if (IS_SYNC(inode)) nilfs_set_transaction_flag(NILFS_TI_SYNC); nilfs_transaction_commit(sb); @@ -700,17 +775,32 @@ out_err: return err; } -int nilfs_load_inode_block(struct nilfs_sb_info *sbi, struct inode *inode, - struct buffer_head **pbh) +int nilfs_permission(struct inode *inode, int mask, unsigned int flags) +{ + struct nilfs_root *root; + + if (flags & IPERM_FLAG_RCU) + return -ECHILD; + + root = NILFS_I(inode)->i_root; + if ((mask & MAY_WRITE) && root && + root->cno != NILFS_CPTREE_CURRENT_CNO) + return -EROFS; /* snapshot is not writable */ + + return generic_permission(inode, mask, flags, NULL); +} + +int nilfs_load_inode_block(struct inode *inode, struct buffer_head **pbh) { + struct nilfs_sb_info *sbi = NILFS_SB(inode->i_sb); struct nilfs_inode_info *ii = NILFS_I(inode); int err; spin_lock(&sbi->s_inode_lock); if (ii->i_bh == NULL) { spin_unlock(&sbi->s_inode_lock); - err = nilfs_ifile_get_inode_block(sbi->s_ifile, inode->i_ino, - pbh); + err = nilfs_ifile_get_inode_block(ii->i_root->ifile, + inode->i_ino, pbh); if (unlikely(err)) return err; spin_lock(&sbi->s_inode_lock); @@ -743,9 +833,9 @@ int nilfs_inode_dirty(struct inode *inode) return ret; } -int nilfs_set_file_dirty(struct nilfs_sb_info *sbi, struct inode *inode, - unsigned nr_dirty) +int nilfs_set_file_dirty(struct inode *inode, unsigned nr_dirty) { + struct nilfs_sb_info *sbi = NILFS_SB(inode->i_sb); struct nilfs_inode_info *ii = NILFS_I(inode); atomic_add(nr_dirty, &sbi->s_nilfs->ns_ndirtyblks); @@ -778,11 +868,10 @@ int nilfs_set_file_dirty(struct nilfs_sb_info *sbi, struct inode *inode, int nilfs_mark_inode_dirty(struct inode *inode) { - struct nilfs_sb_info *sbi = NILFS_SB(inode->i_sb); struct buffer_head *ibh; int err; - err = nilfs_load_inode_block(sbi, inode, &ibh); + err = nilfs_load_inode_block(inode, &ibh); if (unlikely(err)) { nilfs_warning(inode->i_sb, __func__, "failed to reget inode block.\n"); @@ -790,7 +879,7 @@ int nilfs_mark_inode_dirty(struct inode *inode) } nilfs_update_inode(inode, ibh); nilfs_mdt_mark_buffer_dirty(ibh); - nilfs_mdt_mark_dirty(sbi->s_ifile); + nilfs_mdt_mark_dirty(NILFS_I(inode)->i_root->ifile); brelse(ibh); return 0; } @@ -808,6 +897,7 @@ int nilfs_mark_inode_dirty(struct inode *inode) void nilfs_dirty_inode(struct inode *inode) { struct nilfs_transaction_info ti; + struct nilfs_mdt_info *mdi = NILFS_MDT(inode); if (is_bad_inode(inode)) { nilfs_warning(inode->i_sb, __func__, @@ -815,7 +905,142 @@ void nilfs_dirty_inode(struct inode *inode) dump_stack(); return; } + if (mdi) { + nilfs_mdt_mark_dirty(inode); + return; + } nilfs_transaction_begin(inode->i_sb, &ti, 0); nilfs_mark_inode_dirty(inode); nilfs_transaction_commit(inode->i_sb); /* never fails */ } + +int nilfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, + __u64 start, __u64 len) +{ + struct the_nilfs *nilfs = NILFS_I_NILFS(inode); + __u64 logical = 0, phys = 0, size = 0; + __u32 flags = 0; + loff_t isize; + sector_t blkoff, end_blkoff; + sector_t delalloc_blkoff; + unsigned long delalloc_blklen; + unsigned int blkbits = inode->i_blkbits; + int ret, n; + + ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC); + if (ret) + return ret; + + mutex_lock(&inode->i_mutex); + + isize = i_size_read(inode); + + blkoff = start >> blkbits; + end_blkoff = (start + len - 1) >> blkbits; + + delalloc_blklen = nilfs_find_uncommitted_extent(inode, blkoff, + &delalloc_blkoff); + + do { + __u64 blkphy; + unsigned int maxblocks; + + if (delalloc_blklen && blkoff == delalloc_blkoff) { + if (size) { + /* End of the current extent */ + ret = fiemap_fill_next_extent( + fieinfo, logical, phys, size, flags); + if (ret) + break; + } + if (blkoff > end_blkoff) + break; + + flags = FIEMAP_EXTENT_MERGED | FIEMAP_EXTENT_DELALLOC; + logical = blkoff << blkbits; + phys = 0; + size = delalloc_blklen << blkbits; + + blkoff = delalloc_blkoff + delalloc_blklen; + delalloc_blklen = nilfs_find_uncommitted_extent( + inode, blkoff, &delalloc_blkoff); + continue; + } + + /* + * Limit the number of blocks that we look up so as + * not to get into the next delayed allocation extent. + */ + maxblocks = INT_MAX; + if (delalloc_blklen) + maxblocks = min_t(sector_t, delalloc_blkoff - blkoff, + maxblocks); + blkphy = 0; + + down_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem); + n = nilfs_bmap_lookup_contig( + NILFS_I(inode)->i_bmap, blkoff, &blkphy, maxblocks); + up_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem); + + if (n < 0) { + int past_eof; + + if (unlikely(n != -ENOENT)) + break; /* error */ + + /* HOLE */ + blkoff++; + past_eof = ((blkoff << blkbits) >= isize); + + if (size) { + /* End of the current extent */ + + if (past_eof) + flags |= FIEMAP_EXTENT_LAST; + + ret = fiemap_fill_next_extent( + fieinfo, logical, phys, size, flags); + if (ret) + break; + size = 0; + } + if (blkoff > end_blkoff || past_eof) + break; + } else { + if (size) { + if (phys && blkphy << blkbits == phys + size) { + /* The current extent goes on */ + size += n << blkbits; + } else { + /* Terminate the current extent */ + ret = fiemap_fill_next_extent( + fieinfo, logical, phys, size, + flags); + if (ret || blkoff > end_blkoff) + break; + + /* Start another extent */ + flags = FIEMAP_EXTENT_MERGED; + logical = blkoff << blkbits; + phys = blkphy << blkbits; + size = n << blkbits; + } + } else { + /* Start a new extent */ + flags = FIEMAP_EXTENT_MERGED; + logical = blkoff << blkbits; + phys = blkphy << blkbits; + size = n << blkbits; + } + blkoff += n; + } + cond_resched(); + } while (true); + + /* If ret is 1 then we just hit the end of the extent array */ + if (ret == 1) + ret = 0; + + mutex_unlock(&inode->i_mutex); + return ret; +} |