diff options
Diffstat (limited to 'fs/ext4/inode.c')
| -rw-r--r-- | fs/ext4/inode.c | 6611 |
1 files changed, 4123 insertions, 2488 deletions
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 0188e65e1f58..0c466ccbed69 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ext4/inode.c * @@ -19,16 +20,18 @@ */ #include <linux/fs.h> +#include <linux/mount.h> #include <linux/time.h> -#include <linux/jbd2.h> #include <linux/highuid.h> #include <linux/pagemap.h> +#include <linux/dax.h> #include <linux/quotaops.h> #include <linux/string.h> #include <linux/buffer_head.h> #include <linux/writeback.h> #include <linux/pagevec.h> #include <linux/mpage.h> +#include <linux/rmap.h> #include <linux/namei.h> #include <linux/uio.h> #include <linux/bio.h> @@ -36,8 +39,9 @@ #include <linux/kernel.h> #include <linux/printk.h> #include <linux/slab.h> -#include <linux/ratelimit.h> -#include <linux/aio.h> +#include <linux/bitops.h> +#include <linux/iomap.h> +#include <linux/iversion.h> #include "ext4_jbd2.h" #include "xattr.h" @@ -46,31 +50,37 @@ #include <trace/events/ext4.h> -#define MPAGE_DA_EXTENT_TAIL 0x01 +static void ext4_journalled_zero_new_buffers(handle_t *handle, + struct inode *inode, + struct folio *folio, + unsigned from, unsigned to); static __u32 ext4_inode_csum(struct inode *inode, struct ext4_inode *raw, struct ext4_inode_info *ei) { - struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); - __u16 csum_lo; - __u16 csum_hi = 0; __u32 csum; + __u16 dummy_csum = 0; + int offset = offsetof(struct ext4_inode, i_checksum_lo); + unsigned int csum_size = sizeof(dummy_csum); - csum_lo = le16_to_cpu(raw->i_checksum_lo); - raw->i_checksum_lo = 0; - if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE && - EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) { - csum_hi = le16_to_cpu(raw->i_checksum_hi); - raw->i_checksum_hi = 0; - } - - csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)raw, - EXT4_INODE_SIZE(inode->i_sb)); + csum = ext4_chksum(ei->i_csum_seed, (__u8 *)raw, offset); + csum = ext4_chksum(csum, (__u8 *)&dummy_csum, csum_size); + offset += csum_size; + csum = ext4_chksum(csum, (__u8 *)raw + offset, + EXT4_GOOD_OLD_INODE_SIZE - offset); - raw->i_checksum_lo = cpu_to_le16(csum_lo); - if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE && - EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) - raw->i_checksum_hi = cpu_to_le16(csum_hi); + if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) { + offset = offsetof(struct ext4_inode, i_checksum_hi); + csum = ext4_chksum(csum, (__u8 *)raw + EXT4_GOOD_OLD_INODE_SIZE, + offset - EXT4_GOOD_OLD_INODE_SIZE); + if (EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) { + csum = ext4_chksum(csum, (__u8 *)&dummy_csum, + csum_size); + offset += csum_size; + } + csum = ext4_chksum(csum, (__u8 *)raw + offset, + EXT4_INODE_SIZE(inode->i_sb) - offset); + } return csum; } @@ -82,8 +92,7 @@ static int ext4_inode_csum_verify(struct inode *inode, struct ext4_inode *raw, if (EXT4_SB(inode->i_sb)->s_es->s_creator_os != cpu_to_le32(EXT4_OS_LINUX) || - !EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + !ext4_has_feature_metadata_csum(inode->i_sb)) return 1; provided = le16_to_cpu(raw->i_checksum_lo); @@ -97,15 +106,14 @@ static int ext4_inode_csum_verify(struct inode *inode, struct ext4_inode *raw, return provided == calculated; } -static void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw, - struct ext4_inode_info *ei) +void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw, + struct ext4_inode_info *ei) { __u32 csum; if (EXT4_SB(inode->i_sb)->s_es->s_creator_os != cpu_to_le32(EXT4_OS_LINUX) || - !EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + !ext4_has_feature_metadata_csum(inode->i_sb)) return; csum = ext4_inode_csum(inode, raw, ei); @@ -132,48 +140,23 @@ static inline int ext4_begin_ordered_truncate(struct inode *inode, new_size); } -static void ext4_invalidatepage(struct page *page, unsigned int offset, - unsigned int length); -static int __ext4_journalled_writepage(struct page *page, unsigned int len); -static int ext4_bh_delay_or_unwritten(handle_t *handle, struct buffer_head *bh); -static int ext4_meta_trans_blocks(struct inode *inode, int lblocks, - int pextents); - /* * Test whether an inode is a fast symlink. + * A fast symlink has its symlink data stored in ext4_inode_info->i_data. */ -static int ext4_inode_is_fast_symlink(struct inode *inode) -{ - int ea_blocks = EXT4_I(inode)->i_file_acl ? - (inode->i_sb->s_blocksize >> 9) : 0; - - return (S_ISLNK(inode->i_mode) && inode->i_blocks - ea_blocks == 0); -} - -/* - * Restart the transaction associated with *handle. This does a commit, - * so before we call here everything must be consistently dirtied against - * this transaction. - */ -int ext4_truncate_restart_trans(handle_t *handle, struct inode *inode, - int nblocks) +int ext4_inode_is_fast_symlink(struct inode *inode) { - int ret; + if (!ext4_has_feature_ea_inode(inode->i_sb)) { + int ea_blocks = EXT4_I(inode)->i_file_acl ? + EXT4_CLUSTER_SIZE(inode->i_sb) >> 9 : 0; - /* - * Drop i_data_sem to avoid deadlock with ext4_map_blocks. At this - * moment, get_block can be called only for blocks inside i_size since - * page cache has been already dropped and writes are blocked by - * i_mutex. So we can safely drop the i_data_sem here. - */ - BUG_ON(EXT4_JOURNAL(inode) == NULL); - jbd_debug(2, "restarting handle %p\n", handle); - up_write(&EXT4_I(inode)->i_data_sem); - ret = ext4_journal_restart(handle, nblocks); - down_write(&EXT4_I(inode)->i_data_sem); - ext4_discard_preallocations(inode); + if (ext4_has_inline_data(inode)) + return 0; - return ret; + return (S_ISLNK(inode->i_mode) && inode->i_blocks - ea_blocks == 0); + } + return S_ISLNK(inode->i_mode) && inode->i_size && + (inode->i_size < EXT4_N_BLOCKS * 4); } /* @@ -183,61 +166,64 @@ void ext4_evict_inode(struct inode *inode) { handle_t *handle; int err; + /* + * Credits for final inode cleanup and freeing: + * sb + inode (ext4_orphan_del()), block bitmap, group descriptor + * (xattr block freeing), bitmap, group descriptor (inode freeing) + */ + int extra_credits = 6; + struct ext4_xattr_inode_array *ea_inode_array = NULL; + bool freeze_protected = false; trace_ext4_evict_inode(inode); + dax_break_layout_final(inode); + + if (EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL) + ext4_evict_ea_inode(inode); if (inode->i_nlink) { - /* - * When journalling data dirty buffers are tracked only in the - * journal. So although mm thinks everything is clean and - * ready for reaping the inode might still have some pages to - * write in the running transaction or waiting to be - * checkpointed. Thus calling jbd2_journal_invalidatepage() - * (via truncate_inode_pages()) to discard these buffers can - * cause data loss. Also even if we did not discard these - * buffers, we would have no way to find them after the inode - * is reaped and thus user could see stale data if he tries to - * read them before the transaction is checkpointed. So be - * careful and force everything to disk here... We use - * ei->i_datasync_tid to store the newest transaction - * containing inode's data. - * - * Note that directories do not have this problem because they - * don't use page cache. - */ - if (ext4_should_journal_data(inode) && - (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode)) && - inode->i_ino != EXT4_JOURNAL_INO) { - journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; - tid_t commit_tid = EXT4_I(inode)->i_datasync_tid; - - jbd2_complete_transaction(journal, commit_tid); - filemap_write_and_wait(&inode->i_data); - } - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); - WARN_ON(atomic_read(&EXT4_I(inode)->i_ioend_count)); goto no_delete; } - if (!is_bad_inode(inode)) - dquot_initialize(inode); + if (is_bad_inode(inode)) + goto no_delete; + dquot_initialize(inode); if (ext4_should_order_data(inode)) ext4_begin_ordered_truncate(inode, 0); - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); - WARN_ON(atomic_read(&EXT4_I(inode)->i_ioend_count)); - if (is_bad_inode(inode)) - goto no_delete; + /* + * For inodes with journalled data, transaction commit could have + * dirtied the inode. And for inodes with dioread_nolock, unwritten + * extents converting worker could merge extents and also have dirtied + * the inode. Flush worker is ignoring it because of I_FREEING flag but + * we still need to remove the inode from the writeback lists. + */ + inode_io_list_del(inode); /* * Protect us against freezing - iput() caller didn't have to have any - * protection against it + * protection against it. When we are in a running transaction though, + * we are already protected against freezing and we cannot grab further + * protection due to lock ordering constraints. + */ + if (!ext4_journal_current_handle()) { + sb_start_intwrite(inode->i_sb); + freeze_protected = true; + } + + if (!IS_NOQUOTA(inode)) + extra_credits += EXT4_MAXQUOTAS_DEL_BLOCKS(inode->i_sb); + + /* + * Block bitmap, group descriptor, and inode are accounted in both + * ext4_blocks_for_truncate() and extra_credits. So subtract 3. */ - sb_start_intwrite(inode->i_sb); handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, - ext4_blocks_for_truncate(inode)+3); + ext4_blocks_for_truncate(inode) + extra_credits - 3); if (IS_ERR(handle)) { ext4_std_error(inode->i_sb, PTR_ERR(handle)); /* @@ -246,12 +232,23 @@ void ext4_evict_inode(struct inode *inode) * cleaned up. */ ext4_orphan_del(NULL, inode); - sb_end_intwrite(inode->i_sb); + if (freeze_protected) + sb_end_intwrite(inode->i_sb); goto no_delete; } if (IS_SYNC(inode)) ext4_handle_sync(handle); + + /* + * Set inode->i_size to 0 before calling ext4_truncate(). We need + * special handling of symlinks here because i_size is used to + * determine whether ext4_inode_info->i_data contains symlink data or + * block mappings. Setting i_size to 0 will remove its fast symlink + * status. Erase i_data so that it becomes a valid empty block map. + */ + if (ext4_inode_is_fast_symlink(inode)) + memset(EXT4_I(inode)->i_data, 0, sizeof(EXT4_I(inode)->i_data)); inode->i_size = 0; err = ext4_mark_inode_dirty(handle, inode); if (err) { @@ -259,28 +256,28 @@ void ext4_evict_inode(struct inode *inode) "couldn't mark inode dirty (err %d)", err); goto stop_handle; } - if (inode->i_blocks) - ext4_truncate(inode); + if (inode->i_blocks) { + err = ext4_truncate(inode); + if (err) { + ext4_error_err(inode->i_sb, -err, + "couldn't truncate inode %lu (err %d)", + inode->i_ino, err); + goto stop_handle; + } + } - /* - * ext4_ext_truncate() doesn't reserve any slop when it - * restarts journal transactions; therefore there may not be - * enough credits left in the handle to remove the inode from - * the orphan list and set the dtime field. - */ - if (!ext4_handle_has_enough_credits(handle, 3)) { - err = ext4_journal_extend(handle, 3); - if (err > 0) - err = ext4_journal_restart(handle, 3); - if (err != 0) { - ext4_warning(inode->i_sb, - "couldn't extend journal (err %d)", err); - stop_handle: - ext4_journal_stop(handle); - ext4_orphan_del(NULL, inode); + /* Remove xattr references. */ + err = ext4_xattr_delete_inode(handle, inode, &ea_inode_array, + extra_credits); + if (err) { + ext4_warning(inode->i_sb, "xattr delete (err %d)", err); +stop_handle: + ext4_journal_stop(handle); + ext4_orphan_del(NULL, inode); + if (freeze_protected) sb_end_intwrite(inode->i_sb); - goto no_delete; - } + ext4_xattr_inode_array_free(ea_inode_array); + goto no_delete; } /* @@ -292,7 +289,7 @@ void ext4_evict_inode(struct inode *inode) * (Well, we could do this if we need to, but heck - it works) */ ext4_orphan_del(handle, inode); - EXT4_I(inode)->i_dtime = get_seconds(); + EXT4_I(inode)->i_dtime = (__u32)ktime_get_real_seconds(); /* * One subtle ordering requirement: if anything has gone wrong @@ -307,9 +304,19 @@ void ext4_evict_inode(struct inode *inode) else ext4_free_inode(handle, inode); ext4_journal_stop(handle); - sb_end_intwrite(inode->i_sb); + if (freeze_protected) + sb_end_intwrite(inode->i_sb); + ext4_xattr_inode_array_free(ea_inode_array); return; no_delete: + /* + * Check out some where else accidentally dirty the evicting inode, + * which may probably cause inode use-after-free issues later. + */ + WARN_ON_ONCE(!list_empty_careful(&inode->i_io_list)); + + if (!list_empty(&EXT4_I(inode)->i_fc_list)) + ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM, NULL); ext4_clear_inode(inode); /* We must guarantee clearing of inode... */ } @@ -321,18 +328,6 @@ qsize_t *ext4_get_reserved_space(struct inode *inode) #endif /* - * Calculate the number of metadata blocks need to reserve - * to allocate a block located at @lblock - */ -static int ext4_calc_metadata_amount(struct inode *inode, ext4_lblk_t lblock) -{ - if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) - return ext4_ext_calc_metadata_amount(inode, lblock); - - return ext4_ind_calc_metadata_amount(inode, lblock); -} - -/* * Called with i_data_sem down, which is important since we can call * ext4_discard_preallocations() from here. */ @@ -353,36 +348,11 @@ void ext4_da_update_reserve_space(struct inode *inode, used = ei->i_reserved_data_blocks; } - if (unlikely(ei->i_allocated_meta_blocks > ei->i_reserved_meta_blocks)) { - ext4_warning(inode->i_sb, "ino %lu, allocated %d " - "with only %d reserved metadata blocks " - "(releasing %d blocks with reserved %d data blocks)", - inode->i_ino, ei->i_allocated_meta_blocks, - ei->i_reserved_meta_blocks, used, - ei->i_reserved_data_blocks); - WARN_ON(1); - ei->i_allocated_meta_blocks = ei->i_reserved_meta_blocks; - } - /* Update per-inode reservations */ ei->i_reserved_data_blocks -= used; - ei->i_reserved_meta_blocks -= ei->i_allocated_meta_blocks; - percpu_counter_sub(&sbi->s_dirtyclusters_counter, - used + ei->i_allocated_meta_blocks); - ei->i_allocated_meta_blocks = 0; + percpu_counter_sub(&sbi->s_dirtyclusters_counter, used); - if (ei->i_reserved_data_blocks == 0) { - /* - * We can release all of the reserved metadata blocks - * only when we have written all of the delayed - * allocation blocks. - */ - percpu_counter_sub(&sbi->s_dirtyclusters_counter, - ei->i_reserved_meta_blocks); - ei->i_reserved_meta_blocks = 0; - ei->i_da_metadata_calc_len = 0; - } - spin_unlock(&EXT4_I(inode)->i_block_reservation_lock); + spin_unlock(&ei->i_block_reservation_lock); /* Update quota subsystem for data blocks */ if (quota_claim) @@ -402,7 +372,7 @@ void ext4_da_update_reserve_space(struct inode *inode, * inode's preallocations. */ if ((ei->i_reserved_data_blocks == 0) && - (atomic_read(&inode->i_writecount) == 0)) + !inode_is_open_for_write(inode)) ext4_discard_preallocations(inode); } @@ -410,17 +380,62 @@ static int __check_block_validity(struct inode *inode, const char *func, unsigned int line, struct ext4_map_blocks *map) { - if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), map->m_pblk, - map->m_len)) { + journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; + + if (journal && inode == journal->j_inode) + return 0; + + if (!ext4_inode_block_valid(inode, map->m_pblk, map->m_len)) { ext4_error_inode(inode, func, line, map->m_pblk, - "lblock %lu mapped to illegal pblock " + "lblock %lu mapped to illegal pblock %llu " "(length %d)", (unsigned long) map->m_lblk, - map->m_len); - return -EIO; + map->m_pblk, map->m_len); + return -EFSCORRUPTED; } return 0; } +int ext4_issue_zeroout(struct inode *inode, ext4_lblk_t lblk, ext4_fsblk_t pblk, + ext4_lblk_t len) +{ + int ret; + + if (IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode)) + return fscrypt_zeroout_range(inode, lblk, pblk, len); + + ret = sb_issue_zeroout(inode->i_sb, pblk, len, GFP_NOFS); + if (ret > 0) + ret = 0; + + return ret; +} + +/* + * For generic regular files, when updating the extent tree, Ext4 should + * hold the i_rwsem and invalidate_lock exclusively. This ensures + * exclusion against concurrent page faults, as well as reads and writes. + */ +#ifdef CONFIG_EXT4_DEBUG +void ext4_check_map_extents_env(struct inode *inode) +{ + if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) + return; + + if (!S_ISREG(inode->i_mode) || + IS_NOQUOTA(inode) || IS_VERITY(inode) || + is_special_ino(inode->i_sb, inode->i_ino) || + (inode_state_read_once(inode) & (I_FREEING | I_WILL_FREE | I_NEW)) || + ext4_test_inode_flag(inode, EXT4_INODE_EA_INODE) || + ext4_verity_in_progress(inode)) + return; + + WARN_ON_ONCE(!inode_is_locked(inode) && + !rwsem_is_locked(&inode->i_mapping->invalidate_lock)); +} +#else +void ext4_check_map_extents_env(struct inode *inode) {} +#endif + #define check_block_validity(inode, map) \ __check_block_validity((inode), __func__, __LINE__, (map)) @@ -441,22 +456,13 @@ static void ext4_map_blocks_es_recheck(handle_t *handle, * out taking i_data_sem. So at the time the unwritten extent * could be converted. */ - if (!(flags & EXT4_GET_BLOCKS_NO_LOCK)) - down_read((&EXT4_I(inode)->i_data_sem)); + down_read(&EXT4_I(inode)->i_data_sem); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { - retval = ext4_ext_map_blocks(handle, inode, map, flags & - EXT4_GET_BLOCKS_KEEP_SIZE); + retval = ext4_ext_map_blocks(handle, inode, map, 0); } else { - retval = ext4_ind_map_blocks(handle, inode, map, flags & - EXT4_GET_BLOCKS_KEEP_SIZE); + retval = ext4_ind_map_blocks(handle, inode, map, 0); } - if (!(flags & EXT4_GET_BLOCKS_NO_LOCK)) - up_read((&EXT4_I(inode)->i_data_sem)); - /* - * Clear EXT4_MAP_FROM_CLUSTER and EXT4_MAP_BOUNDARY flag - * because it shouldn't be marked in es_map->m_flags. - */ - map->m_flags &= ~(EXT4_MAP_FROM_CLUSTER | EXT4_MAP_BOUNDARY); + up_read((&EXT4_I(inode)->i_data_sem)); /* * We don't check m_len because extent will be collpased in status @@ -465,7 +471,7 @@ static void ext4_map_blocks_es_recheck(handle_t *handle, if (es_map->m_lblk != map->m_lblk || es_map->m_flags != map->m_flags || es_map->m_pblk != map->m_pblk) { - printk("ES cache assertation failed for inode: %lu " + printk("ES cache assertion failed for inode: %lu " "es_cached ex [%d/%d/%llu/%x] != " "found ex [%d/%d/%llu/%x] retval %d flags %x\n", inode->i_ino, es_map->m_lblk, es_map->m_len, @@ -476,6 +482,191 @@ static void ext4_map_blocks_es_recheck(handle_t *handle, } #endif /* ES_AGGRESSIVE_TEST */ +static int ext4_map_query_blocks_next_in_leaf(handle_t *handle, + struct inode *inode, struct ext4_map_blocks *map, + unsigned int orig_mlen) +{ + struct ext4_map_blocks map2; + unsigned int status, status2; + int retval; + + status = map->m_flags & EXT4_MAP_UNWRITTEN ? + EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN; + + WARN_ON_ONCE(!(map->m_flags & EXT4_MAP_QUERY_LAST_IN_LEAF)); + WARN_ON_ONCE(orig_mlen <= map->m_len); + + /* Prepare map2 for lookup in next leaf block */ + map2.m_lblk = map->m_lblk + map->m_len; + map2.m_len = orig_mlen - map->m_len; + map2.m_flags = 0; + retval = ext4_ext_map_blocks(handle, inode, &map2, 0); + + if (retval <= 0) { + ext4_es_insert_extent(inode, map->m_lblk, map->m_len, + map->m_pblk, status, false); + return map->m_len; + } + + if (unlikely(retval != map2.m_len)) { + ext4_warning(inode->i_sb, + "ES len assertion failed for inode " + "%lu: retval %d != map->m_len %d", + inode->i_ino, retval, map2.m_len); + WARN_ON(1); + } + + status2 = map2.m_flags & EXT4_MAP_UNWRITTEN ? + EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN; + + /* + * If map2 is contiguous with map, then let's insert it as a single + * extent in es cache and return the combined length of both the maps. + */ + if (map->m_pblk + map->m_len == map2.m_pblk && + status == status2) { + ext4_es_insert_extent(inode, map->m_lblk, + map->m_len + map2.m_len, map->m_pblk, + status, false); + map->m_len += map2.m_len; + } else { + ext4_es_insert_extent(inode, map->m_lblk, map->m_len, + map->m_pblk, status, false); + } + + return map->m_len; +} + +static int ext4_map_query_blocks(handle_t *handle, struct inode *inode, + struct ext4_map_blocks *map, int flags) +{ + unsigned int status; + int retval; + unsigned int orig_mlen = map->m_len; + + flags &= EXT4_EX_QUERY_FILTER; + if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) + retval = ext4_ext_map_blocks(handle, inode, map, flags); + else + retval = ext4_ind_map_blocks(handle, inode, map, flags); + if (retval < 0) + return retval; + + /* A hole? */ + if (retval == 0) + goto out; + + if (unlikely(retval != map->m_len)) { + ext4_warning(inode->i_sb, + "ES len assertion failed for inode " + "%lu: retval %d != map->m_len %d", + inode->i_ino, retval, map->m_len); + WARN_ON(1); + } + + /* + * No need to query next in leaf: + * - if returned extent is not last in leaf or + * - if the last in leaf is the full requested range + */ + if (!(map->m_flags & EXT4_MAP_QUERY_LAST_IN_LEAF) || + map->m_len == orig_mlen) { + status = map->m_flags & EXT4_MAP_UNWRITTEN ? + EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN; + ext4_es_insert_extent(inode, map->m_lblk, map->m_len, + map->m_pblk, status, false); + } else { + retval = ext4_map_query_blocks_next_in_leaf(handle, inode, map, + orig_mlen); + } +out: + map->m_seq = READ_ONCE(EXT4_I(inode)->i_es_seq); + return retval; +} + +static int ext4_map_create_blocks(handle_t *handle, struct inode *inode, + struct ext4_map_blocks *map, int flags) +{ + struct extent_status es; + unsigned int status; + int err, retval = 0; + + /* + * We pass in the magic EXT4_GET_BLOCKS_DELALLOC_RESERVE + * indicates that the blocks and quotas has already been + * checked when the data was copied into the page cache. + */ + if (map->m_flags & EXT4_MAP_DELAYED) + flags |= EXT4_GET_BLOCKS_DELALLOC_RESERVE; + + /* + * Here we clear m_flags because after allocating an new extent, + * it will be set again. + */ + map->m_flags &= ~EXT4_MAP_FLAGS; + + /* + * We need to check for EXT4 here because migrate could have + * changed the inode type in between. + */ + if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { + retval = ext4_ext_map_blocks(handle, inode, map, flags); + } else { + retval = ext4_ind_map_blocks(handle, inode, map, flags); + + /* + * We allocated new blocks which will result in i_data's + * format changing. Force the migrate to fail by clearing + * migrate flags. + */ + if (retval > 0 && map->m_flags & EXT4_MAP_NEW) + ext4_clear_inode_state(inode, EXT4_STATE_EXT_MIGRATE); + } + if (retval <= 0) + return retval; + + if (unlikely(retval != map->m_len)) { + ext4_warning(inode->i_sb, + "ES len assertion failed for inode %lu: " + "retval %d != map->m_len %d", + inode->i_ino, retval, map->m_len); + WARN_ON(1); + } + + /* + * We have to zeroout blocks before inserting them into extent + * status tree. Otherwise someone could look them up there and + * use them before they are really zeroed. We also have to + * unmap metadata before zeroing as otherwise writeback can + * overwrite zeros with stale data from block device. + */ + if (flags & EXT4_GET_BLOCKS_ZERO && + map->m_flags & EXT4_MAP_MAPPED && map->m_flags & EXT4_MAP_NEW) { + err = ext4_issue_zeroout(inode, map->m_lblk, map->m_pblk, + map->m_len); + if (err) + return err; + } + + /* + * If the extent has been zeroed out, we don't need to update + * extent status tree. + */ + if (flags & EXT4_GET_BLOCKS_SPLIT_NOMERGE && + ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es, &map->m_seq)) { + if (ext4_es_is_written(&es)) + return retval; + } + + status = map->m_flags & EXT4_MAP_UNWRITTEN ? + EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN; + ext4_es_insert_extent(inode, map->m_lblk, map->m_len, map->m_pblk, + status, flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE); + map->m_seq = READ_ONCE(EXT4_I(inode)->i_es_seq); + + return retval; +} + /* * The ext4_map_blocks() function tries to look up the requested blocks, * and returns if the blocks are already mapped. @@ -488,13 +679,14 @@ static void ext4_map_blocks_es_recheck(handle_t *handle, * Otherwise, call with ext4_ind_map_blocks() to handle indirect mapping * based files * - * On success, it returns the number of blocks being mapped or allocate. - * if create==0 and the blocks are pre-allocated and uninitialized block, - * the result buffer head is unmapped. If the create ==1, it will make sure - * the buffer head is mapped. + * On success, it returns the number of blocks being mapped or allocated. + * If flags doesn't contain EXT4_GET_BLOCKS_CREATE the blocks are + * pre-allocated and unwritten, the resulting @map is marked as unwritten. + * If the flags contain EXT4_GET_BLOCKS_CREATE, it will mark @map as mapped. * * It returns 0 if plain look up failed (blocks have not been allocated), in - * that case, buffer head is unmapped + * that case, @map is returned as unmapped but we still do fill map->m_len to + * indicate the length of a hole starting at map->m_lblk. * * It returns the error in case of allocation failure. */ @@ -503,6 +695,8 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, { struct extent_status es; int retval; + int ret = 0; + unsigned int orig_mlen = map->m_len; #ifdef ES_AGGRESSIVE_TEST struct ext4_map_blocks orig_map; @@ -510,14 +704,31 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, #endif map->m_flags = 0; - ext_debug("ext4_map_blocks(): inode %lu, flag %d, max_blocks %u," - "logical block %lu\n", inode->i_ino, flags, map->m_len, - (unsigned long) map->m_lblk); + ext_debug(inode, "flag 0x%x, max_blocks %u, logical block %lu\n", + flags, map->m_len, (unsigned long) map->m_lblk); + + /* + * ext4_map_blocks returns an int, and m_len is an unsigned int + */ + if (unlikely(map->m_len > INT_MAX)) + map->m_len = INT_MAX; - ext4_es_lru_add(inode); + /* We can handle the block number less than EXT_MAX_BLOCKS */ + if (unlikely(map->m_lblk >= EXT_MAX_BLOCKS)) + return -EFSCORRUPTED; + + /* + * Callers from the context of data submission are the only exceptions + * for regular files that do not hold the i_rwsem or invalidate_lock. + * However, caching unrelated ranges is not permitted. + */ + if (flags & EXT4_GET_BLOCKS_IO_SUBMIT) + WARN_ON_ONCE(!(flags & EXT4_EX_NOCACHE)); + else + ext4_check_map_extents_env(inode); /* Lookup extent status tree firstly */ - if (ext4_es_lookup_extent(inode, map->m_lblk, &es)) { + if (ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es, &map->m_seq)) { if (ext4_es_is_written(&es) || ext4_es_is_unwritten(&es)) { map->m_pblk = ext4_es_pblock(&es) + map->m_lblk - es.es_lblk; @@ -528,60 +739,48 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, retval = map->m_len; map->m_len = retval; } else if (ext4_es_is_delayed(&es) || ext4_es_is_hole(&es)) { + map->m_pblk = 0; + map->m_flags |= ext4_es_is_delayed(&es) ? + EXT4_MAP_DELAYED : 0; + retval = es.es_len - (map->m_lblk - es.es_lblk); + if (retval > map->m_len) + retval = map->m_len; + map->m_len = retval; retval = 0; } else { - BUG_ON(1); + BUG(); } + + if (flags & EXT4_GET_BLOCKS_CACHED_NOWAIT) + return retval; #ifdef ES_AGGRESSIVE_TEST ext4_map_blocks_es_recheck(handle, inode, map, &orig_map, flags); #endif - goto found; + if (!(flags & EXT4_GET_BLOCKS_QUERY_LAST_IN_LEAF) || + orig_mlen == map->m_len) + goto found; + + map->m_len = orig_mlen; } + /* + * In the query cache no-wait mode, nothing we can do more if we + * cannot find extent in the cache. + */ + if (flags & EXT4_GET_BLOCKS_CACHED_NOWAIT) + return 0; /* * Try to see if we can get the block without requesting a new * file system block. */ - if (!(flags & EXT4_GET_BLOCKS_NO_LOCK)) - down_read((&EXT4_I(inode)->i_data_sem)); - if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { - retval = ext4_ext_map_blocks(handle, inode, map, flags & - EXT4_GET_BLOCKS_KEEP_SIZE); - } else { - retval = ext4_ind_map_blocks(handle, inode, map, flags & - EXT4_GET_BLOCKS_KEEP_SIZE); - } - if (retval > 0) { - int ret; - unsigned long long status; - -#ifdef ES_AGGRESSIVE_TEST - if (retval != map->m_len) { - printk("ES len assertation failed for inode: %lu " - "retval %d != map->m_len %d " - "in %s (lookup)\n", inode->i_ino, retval, - map->m_len, __func__); - } -#endif - - status = map->m_flags & EXT4_MAP_UNWRITTEN ? - EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN; - if (!(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) && - ext4_find_delalloc_range(inode, map->m_lblk, - map->m_lblk + map->m_len - 1)) - status |= EXTENT_STATUS_DELAYED; - ret = ext4_es_insert_extent(inode, map->m_lblk, - map->m_len, map->m_pblk, status); - if (ret < 0) - retval = ret; - } - if (!(flags & EXT4_GET_BLOCKS_NO_LOCK)) - up_read((&EXT4_I(inode)->i_data_sem)); + down_read(&EXT4_I(inode)->i_data_sem); + retval = ext4_map_query_blocks(handle, inode, map, flags); + up_read((&EXT4_I(inode)->i_data_sem)); found: if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) { - int ret = check_block_validity(inode, map); + ret = check_block_validity(inode, map); if (ret != 0) return ret; } @@ -594,119 +793,119 @@ found: * Returns if the blocks have already allocated * * Note that if blocks have been preallocated - * ext4_ext_get_block() returns the create = 0 - * with buffer head unmapped. + * ext4_ext_map_blocks() returns with buffer head unmapped */ if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) - return retval; + /* + * If we need to convert extent to unwritten + * we continue and do the actual work in + * ext4_ext_map_blocks() + */ + if (!(flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN)) + return retval; - /* - * Here we clear m_flags because after allocating an new extent, - * it will be set again. - */ - map->m_flags &= ~EXT4_MAP_FLAGS; + ext4_fc_track_inode(handle, inode); /* - * New blocks allocate and/or writing to uninitialized extent + * New blocks allocate and/or writing to unwritten extent * will possibly result in updating i_data, so we take - * the write lock of i_data_sem, and call get_blocks() + * the write lock of i_data_sem, and call get_block() * with create == 1 flag. */ - down_write((&EXT4_I(inode)->i_data_sem)); + down_write(&EXT4_I(inode)->i_data_sem); + retval = ext4_map_create_blocks(handle, inode, map, flags); + up_write((&EXT4_I(inode)->i_data_sem)); - /* - * if the caller is from delayed allocation writeout path - * we have already reserved fs blocks for allocation - * let the underlying get_block() function know to - * avoid double accounting - */ - if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) - ext4_set_inode_state(inode, EXT4_STATE_DELALLOC_RESERVED); - /* - * We need to check for EXT4 here because migrate - * could have changed the inode type in between - */ - if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { - retval = ext4_ext_map_blocks(handle, inode, map, flags); - } else { - retval = ext4_ind_map_blocks(handle, inode, map, flags); + if (retval < 0) + ext_debug(inode, "failed with err %d\n", retval); + if (retval <= 0) + return retval; - if (retval > 0 && map->m_flags & EXT4_MAP_NEW) { - /* - * We allocated new blocks which will result in - * i_data's format changing. Force the migrate - * to fail by clearing migrate flags - */ - ext4_clear_inode_state(inode, EXT4_STATE_EXT_MIGRATE); - } + if (map->m_flags & EXT4_MAP_MAPPED) { + ret = check_block_validity(inode, map); + if (ret != 0) + return ret; /* - * Update reserved blocks/metadata blocks after successful - * block allocation which had been deferred till now. We don't - * support fallocate for non extent files. So we can update - * reserve space here. + * Inodes with freshly allocated blocks where contents will be + * visible after transaction commit must be on transaction's + * ordered data list. */ - if ((retval > 0) && - (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)) - ext4_da_update_reserve_space(inode, retval, 1); + if (map->m_flags & EXT4_MAP_NEW && + !(map->m_flags & EXT4_MAP_UNWRITTEN) && + !(flags & EXT4_GET_BLOCKS_ZERO) && + !ext4_is_quota_file(inode) && + ext4_should_order_data(inode)) { + loff_t start_byte = EXT4_LBLK_TO_B(inode, map->m_lblk); + loff_t length = EXT4_LBLK_TO_B(inode, map->m_len); + + if (flags & EXT4_GET_BLOCKS_IO_SUBMIT) + ret = ext4_jbd2_inode_add_wait(handle, inode, + start_byte, length); + else + ret = ext4_jbd2_inode_add_write(handle, inode, + start_byte, length); + if (ret) + return ret; + } } - if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) - ext4_clear_inode_state(inode, EXT4_STATE_DELALLOC_RESERVED); - - if (retval > 0) { - int ret; - unsigned long long status; + ext4_fc_track_range(handle, inode, map->m_lblk, map->m_lblk + + map->m_len - 1); + return retval; +} -#ifdef ES_AGGRESSIVE_TEST - if (retval != map->m_len) { - printk("ES len assertation failed for inode: %lu " - "retval %d != map->m_len %d " - "in %s (allocation)\n", inode->i_ino, retval, - map->m_len, __func__); - } -#endif +/* + * Update EXT4_MAP_FLAGS in bh->b_state. For buffer heads attached to pages + * we have to be careful as someone else may be manipulating b_state as well. + */ +static void ext4_update_bh_state(struct buffer_head *bh, unsigned long flags) +{ + unsigned long old_state; + unsigned long new_state; - /* - * If the extent has been zeroed out, we don't need to update - * extent status tree. - */ - if ((flags & EXT4_GET_BLOCKS_PRE_IO) && - ext4_es_lookup_extent(inode, map->m_lblk, &es)) { - if (ext4_es_is_written(&es)) - goto has_zeroout; - } - status = map->m_flags & EXT4_MAP_UNWRITTEN ? - EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN; - if (!(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) && - ext4_find_delalloc_range(inode, map->m_lblk, - map->m_lblk + map->m_len - 1)) - status |= EXTENT_STATUS_DELAYED; - ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len, - map->m_pblk, status); - if (ret < 0) - retval = ret; - } + flags &= EXT4_MAP_FLAGS; -has_zeroout: - up_write((&EXT4_I(inode)->i_data_sem)); - if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) { - int ret = check_block_validity(inode, map); - if (ret != 0) - return ret; + /* Dummy buffer_head? Set non-atomically. */ + if (!bh->b_folio) { + bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | flags; + return; } - return retval; + /* + * Someone else may be modifying b_state. Be careful! This is ugly but + * once we get rid of using bh as a container for mapping information + * to pass to / from get_block functions, this can go away. + */ + old_state = READ_ONCE(bh->b_state); + do { + new_state = (old_state & ~EXT4_MAP_FLAGS) | flags; + } while (unlikely(!try_cmpxchg(&bh->b_state, &old_state, new_state))); } -/* Maximum number of blocks we map for direct IO at once. */ -#define DIO_MAX_BLOCKS 4096 +/* + * Make sure that the current journal transaction has enough credits to map + * one extent. Return -EAGAIN if it cannot extend the current running + * transaction. + */ +static inline int ext4_journal_ensure_extent_credits(handle_t *handle, + struct inode *inode) +{ + int credits; + int ret; + + /* Called from ext4_da_write_begin() which has no handle started? */ + if (!handle) + return 0; + + credits = ext4_chunk_trans_blocks(inode, 1); + ret = __ext4_journal_ensure_credits(handle, credits, credits, 0); + return ret <= 0 ? ret : -EAGAIN; +} static int _ext4_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh, int flags) { - handle_t *handle = ext4_journal_current_handle(); struct ext4_map_blocks map; - int ret = 0, started = 0; - int dio_credits; + int ret = 0; if (ext4_has_inline_data(inode)) return -ERANGE; @@ -714,29 +913,17 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock, map.m_lblk = iblock; map.m_len = bh->b_size >> inode->i_blkbits; - if (flags && !(flags & EXT4_GET_BLOCKS_NO_LOCK) && !handle) { - /* Direct IO write... */ - if (map.m_len > DIO_MAX_BLOCKS) - map.m_len = DIO_MAX_BLOCKS; - dio_credits = ext4_chunk_trans_blocks(inode, map.m_len); - handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, - dio_credits); - if (IS_ERR(handle)) { - ret = PTR_ERR(handle); - return ret; - } - started = 1; - } - - ret = ext4_map_blocks(handle, inode, &map, flags); + ret = ext4_map_blocks(ext4_journal_current_handle(), inode, &map, + flags); if (ret > 0) { map_bh(bh, inode->i_sb, map.m_pblk); - bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags; + ext4_update_bh_state(bh, map.m_flags); bh->b_size = inode->i_sb->s_blocksize * map.m_len; ret = 0; + } else if (ret == 0) { + /* hole case, need to fill in bh->b_size */ + bh->b_size = inode->i_sb->s_blocksize * map.m_len; } - if (started) - ext4_journal_stop(handle); return ret; } @@ -748,40 +935,76 @@ int ext4_get_block(struct inode *inode, sector_t iblock, } /* + * Get block function used when preparing for buffered write if we require + * creating an unwritten extent if blocks haven't been allocated. The extent + * will be converted to written after the IO is complete. + */ +int ext4_get_block_unwritten(struct inode *inode, sector_t iblock, + struct buffer_head *bh_result, int create) +{ + int ret = 0; + + ext4_debug("ext4_get_block_unwritten: inode %lu, create flag %d\n", + inode->i_ino, create); + ret = _ext4_get_block(inode, iblock, bh_result, + EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT); + + /* + * If the buffer is marked unwritten, mark it as new to make sure it is + * zeroed out correctly in case of partial writes. Otherwise, there is + * a chance of stale data getting exposed. + */ + if (ret == 0 && buffer_unwritten(bh_result)) + set_buffer_new(bh_result); + + return ret; +} + +/* Maximum number of blocks we map for direct IO at once. */ +#define DIO_MAX_BLOCKS 4096 + +/* * `handle' can be NULL if create is zero */ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode, - ext4_lblk_t block, int create, int *errp) + ext4_lblk_t block, int map_flags) { struct ext4_map_blocks map; struct buffer_head *bh; - int fatal = 0, err; + int create = map_flags & EXT4_GET_BLOCKS_CREATE; + bool nowait = map_flags & EXT4_GET_BLOCKS_CACHED_NOWAIT; + int err; - J_ASSERT(handle != NULL || create == 0); + ASSERT((EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) + || handle != NULL || create == 0); + ASSERT(create == 0 || !nowait); map.m_lblk = block; map.m_len = 1; - err = ext4_map_blocks(handle, inode, &map, - create ? EXT4_GET_BLOCKS_CREATE : 0); - - /* ensure we send some value back into *errp */ - *errp = 0; + err = ext4_map_blocks(handle, inode, &map, map_flags); - if (create && err == 0) - err = -ENOSPC; /* should never happen */ + if (err == 0) + return create ? ERR_PTR(-ENOSPC) : NULL; if (err < 0) - *errp = err; - if (err <= 0) - return NULL; + return ERR_PTR(err); - bh = sb_getblk(inode->i_sb, map.m_pblk); - if (unlikely(!bh)) { - *errp = -ENOMEM; - return NULL; - } + if (nowait) + return sb_find_get_block(inode->i_sb, map.m_pblk); + + /* + * Since bh could introduce extra ref count such as referred by + * journal_head etc. Try to avoid using __GFP_MOVABLE here + * as it may fail the migration when journal_head remains. + */ + bh = getblk_unmovable(inode->i_sb->s_bdev, map.m_pblk, + inode->i_sb->s_blocksize); + + if (unlikely(!bh)) + return ERR_PTR(-ENOMEM); if (map.m_flags & EXT4_MAP_NEW) { - J_ASSERT(create != 0); - J_ASSERT(handle != NULL); + ASSERT(create != 0); + ASSERT((EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) + || (handle != NULL)); /* * Now that we do not always journal data, we should @@ -792,52 +1015,98 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode, */ lock_buffer(bh); BUFFER_TRACE(bh, "call get_create_access"); - fatal = ext4_journal_get_create_access(handle, bh); - if (!fatal && !buffer_uptodate(bh)) { + err = ext4_journal_get_create_access(handle, inode->i_sb, bh, + EXT4_JTR_NONE); + if (unlikely(err)) { + unlock_buffer(bh); + goto errout; + } + if (!buffer_uptodate(bh)) { memset(bh->b_data, 0, inode->i_sb->s_blocksize); set_buffer_uptodate(bh); } unlock_buffer(bh); BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata"); err = ext4_handle_dirty_metadata(handle, inode, bh); - if (!fatal) - fatal = err; - } else { + if (unlikely(err)) + goto errout; + } else BUFFER_TRACE(bh, "not a new buffer"); - } - if (fatal) { - *errp = fatal; - brelse(bh); - bh = NULL; - } return bh; +errout: + brelse(bh); + return ERR_PTR(err); } struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode, - ext4_lblk_t block, int create, int *err) + ext4_lblk_t block, int map_flags) { struct buffer_head *bh; + int ret; - bh = ext4_getblk(handle, inode, block, create, err); - if (!bh) - return bh; - if (buffer_uptodate(bh)) + bh = ext4_getblk(handle, inode, block, map_flags); + if (IS_ERR(bh)) return bh; - ll_rw_block(READ | REQ_META | REQ_PRIO, 1, &bh); - wait_on_buffer(bh); - if (buffer_uptodate(bh)) + if (!bh || ext4_buffer_uptodate(bh)) return bh; - put_bh(bh); - *err = -EIO; - return NULL; + + ret = ext4_read_bh_lock(bh, REQ_META | REQ_PRIO, true); + if (ret) { + put_bh(bh); + return ERR_PTR(ret); + } + return bh; +} + +/* Read a contiguous batch of blocks. */ +int ext4_bread_batch(struct inode *inode, ext4_lblk_t block, int bh_count, + bool wait, struct buffer_head **bhs) +{ + int i, err; + + for (i = 0; i < bh_count; i++) { + bhs[i] = ext4_getblk(NULL, inode, block + i, 0 /* map_flags */); + if (IS_ERR(bhs[i])) { + err = PTR_ERR(bhs[i]); + bh_count = i; + goto out_brelse; + } + } + + for (i = 0; i < bh_count; i++) + /* Note that NULL bhs[i] is valid because of holes. */ + if (bhs[i] && !ext4_buffer_uptodate(bhs[i])) + ext4_read_bh_lock(bhs[i], REQ_META | REQ_PRIO, false); + + if (!wait) + return 0; + + for (i = 0; i < bh_count; i++) + if (bhs[i]) + wait_on_buffer(bhs[i]); + + for (i = 0; i < bh_count; i++) { + if (bhs[i] && !buffer_uptodate(bhs[i])) { + err = -EIO; + goto out_brelse; + } + } + return 0; + +out_brelse: + for (i = 0; i < bh_count; i++) { + brelse(bhs[i]); + bhs[i] = NULL; + } + return err; } -int ext4_walk_page_buffers(handle_t *handle, +int ext4_walk_page_buffers(handle_t *handle, struct inode *inode, struct buffer_head *head, unsigned from, unsigned to, int *partial, - int (*fn)(handle_t *handle, + int (*fn)(handle_t *handle, struct inode *inode, struct buffer_head *bh)) { struct buffer_head *bh; @@ -856,7 +1125,7 @@ int ext4_walk_page_buffers(handle_t *handle, *partial = 1; continue; } - err = (*fn)(handle, bh); + err = (*fn)(handle, inode, bh); if (!ret) ret = err; } @@ -864,80 +1133,179 @@ int ext4_walk_page_buffers(handle_t *handle, } /* - * To preserve ordering, it is essential that the hole instantiation and - * the data write be encapsulated in a single transaction. We cannot - * close off a transaction and start a new one between the ext4_get_block() - * and the commit_write(). So doing the jbd2_journal_start at the start of - * prepare_write() is the right place. - * - * Also, this function can nest inside ext4_writepage(). In that case, we - * *know* that ext4_writepage() has generated enough buffer credits to do the - * whole page. So we won't block on the journal in that case, which is good, - * because the caller may be PF_MEMALLOC. - * - * By accident, ext4 can be reentered when a transaction is open via - * quota file writes. If we were to commit the transaction while thus - * reentered, there can be a deadlock - we would be holding a quota - * lock, and the commit would never complete if another thread had a - * transaction open and was blocking on the quota lock - a ranking - * violation. - * - * So what we do is to rely on the fact that jbd2_journal_stop/journal_start - * will _not_ run commit under these circumstances because handle->h_ref - * is elevated. We'll still have enough credits for the tiny quotafile - * write. + * Helper for handling dirtying of journalled data. We also mark the folio as + * dirty so that writeback code knows about this page (and inode) contains + * dirty data. ext4_writepages() then commits appropriate transaction to + * make data stable. */ -int do_journal_get_write_access(handle_t *handle, - struct buffer_head *bh) +static int ext4_dirty_journalled_data(handle_t *handle, struct buffer_head *bh) { - int dirty = buffer_dirty(bh); - int ret; + struct folio *folio = bh->b_folio; + struct inode *inode = folio->mapping->host; + + /* only regular files have a_ops */ + if (S_ISREG(inode->i_mode)) + folio_mark_dirty(folio); + return ext4_handle_dirty_metadata(handle, NULL, bh); +} +int do_journal_get_write_access(handle_t *handle, struct inode *inode, + struct buffer_head *bh) +{ if (!buffer_mapped(bh) || buffer_freed(bh)) return 0; + BUFFER_TRACE(bh, "get write access"); + return ext4_journal_get_write_access(handle, inode->i_sb, bh, + EXT4_JTR_NONE); +} + +int ext4_block_write_begin(handle_t *handle, struct folio *folio, + loff_t pos, unsigned len, + get_block_t *get_block) +{ + unsigned int from = offset_in_folio(folio, pos); + unsigned to = from + len; + struct inode *inode = folio->mapping->host; + unsigned block_start, block_end; + sector_t block; + int err = 0; + unsigned int blocksize = i_blocksize(inode); + struct buffer_head *bh, *head, *wait[2]; + int nr_wait = 0; + int i; + bool should_journal_data = ext4_should_journal_data(inode); + + BUG_ON(!folio_test_locked(folio)); + BUG_ON(to > folio_size(folio)); + BUG_ON(from > to); + WARN_ON_ONCE(blocksize > folio_size(folio)); + + head = folio_buffers(folio); + if (!head) + head = create_empty_buffers(folio, blocksize, 0); + block = EXT4_PG_TO_LBLK(inode, folio->index); + + for (bh = head, block_start = 0; bh != head || !block_start; + block++, block_start = block_end, bh = bh->b_this_page) { + block_end = block_start + blocksize; + if (block_end <= from || block_start >= to) { + if (folio_test_uptodate(folio)) { + set_buffer_uptodate(bh); + } + continue; + } + if (WARN_ON_ONCE(buffer_new(bh))) + clear_buffer_new(bh); + if (!buffer_mapped(bh)) { + WARN_ON(bh->b_size != blocksize); + err = ext4_journal_ensure_extent_credits(handle, inode); + if (!err) + err = get_block(inode, block, bh, 1); + if (err) + break; + if (buffer_new(bh)) { + /* + * We may be zeroing partial buffers or all new + * buffers in case of failure. Prepare JBD2 for + * that. + */ + if (should_journal_data) + do_journal_get_write_access(handle, + inode, bh); + if (folio_test_uptodate(folio)) { + /* + * Unlike __block_write_begin() we leave + * dirtying of new uptodate buffers to + * ->write_end() time or + * folio_zero_new_buffers(). + */ + set_buffer_uptodate(bh); + continue; + } + if (block_end > to || block_start < from) + folio_zero_segments(folio, to, + block_end, + block_start, from); + continue; + } + } + if (folio_test_uptodate(folio)) { + set_buffer_uptodate(bh); + continue; + } + if (!buffer_uptodate(bh) && !buffer_delay(bh) && + !buffer_unwritten(bh) && + (block_start < from || block_end > to)) { + ext4_read_bh_lock(bh, 0, false); + wait[nr_wait++] = bh; + } + } /* - * __block_write_begin() could have dirtied some buffers. Clean - * the dirty bit as jbd2_journal_get_write_access() could complain - * otherwise about fs integrity issues. Setting of the dirty bit - * by __block_write_begin() isn't a real problem here as we clear - * the bit before releasing a page lock and thus writeback cannot - * ever write the buffer. + * If we issued read requests, let them complete. */ - if (dirty) - clear_buffer_dirty(bh); - ret = ext4_journal_get_write_access(handle, bh); - if (!ret && dirty) - ret = ext4_handle_dirty_metadata(handle, NULL, bh); - return ret; + for (i = 0; i < nr_wait; i++) { + wait_on_buffer(wait[i]); + if (!buffer_uptodate(wait[i])) + err = -EIO; + } + if (unlikely(err)) { + if (should_journal_data) + ext4_journalled_zero_new_buffers(handle, inode, folio, + from, to); + else + folio_zero_new_buffers(folio, from, to); + } else if (fscrypt_inode_uses_fs_layer_crypto(inode)) { + for (i = 0; i < nr_wait; i++) { + int err2; + + err2 = fscrypt_decrypt_pagecache_blocks(folio, + blocksize, bh_offset(wait[i])); + if (err2) { + clear_buffer_uptodate(wait[i]); + err = err2; + } + } + } + + return err; } -static int ext4_get_block_write_nolock(struct inode *inode, sector_t iblock, - struct buffer_head *bh_result, int create); -static int ext4_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, - struct page **pagep, void **fsdata) +/* + * To preserve ordering, it is essential that the hole instantiation and + * the data write be encapsulated in a single transaction. We cannot + * close off a transaction and start a new one between the ext4_get_block() + * and the ext4_write_end(). So doing the jbd2_journal_start at the start of + * ext4_write_begin() is the right place. + */ +static int ext4_write_begin(const struct kiocb *iocb, + struct address_space *mapping, + loff_t pos, unsigned len, + struct folio **foliop, void **fsdata) { struct inode *inode = mapping->host; int ret, needed_blocks; handle_t *handle; int retries = 0; - struct page *page; + struct folio *folio; pgoff_t index; unsigned from, to; - trace_ext4_write_begin(inode, pos, len, flags); + ret = ext4_emergency_state(inode->i_sb); + if (unlikely(ret)) + return ret; + + trace_ext4_write_begin(inode, pos, len); /* * Reserve one block more for addition to orphan list in case * we allocate blocks but write fails for some reason */ - needed_blocks = ext4_writepage_trans_blocks(inode) + 1; - index = pos >> PAGE_CACHE_SHIFT; - from = pos & (PAGE_CACHE_SIZE - 1); - to = from + len; + needed_blocks = ext4_chunk_trans_extent(inode, + ext4_journal_blocks_per_folio(inode)) + 1; + index = pos >> PAGE_SHIFT; if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { ret = ext4_try_to_write_inline_data(mapping, inode, pos, len, - flags, pagep); + foliop); if (ret < 0) return ret; if (ret == 1) @@ -945,61 +1313,80 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping, } /* - * grab_cache_page_write_begin() can take a long time if the - * system is thrashing due to memory pressure, or if the page + * write_begin_get_folio() can take a long time if the + * system is thrashing due to memory pressure, or if the folio * is being written back. So grab it first before we start * the transaction handle. This also allows us to allocate - * the page (if needed) without using GFP_NOFS. + * the folio (if needed) without using GFP_NOFS. */ retry_grab: - page = grab_cache_page_write_begin(mapping, index, flags); - if (!page) - return -ENOMEM; - unlock_page(page); + folio = write_begin_get_folio(iocb, mapping, index, len); + if (IS_ERR(folio)) + return PTR_ERR(folio); + + if (len > folio_next_pos(folio) - pos) + len = folio_next_pos(folio) - pos; + + from = offset_in_folio(folio, pos); + to = from + len; + + /* + * The same as page allocation, we prealloc buffer heads before + * starting the handle. + */ + if (!folio_buffers(folio)) + create_empty_buffers(folio, inode->i_sb->s_blocksize, 0); + + folio_unlock(folio); retry_journal: handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, needed_blocks); if (IS_ERR(handle)) { - page_cache_release(page); + folio_put(folio); return PTR_ERR(handle); } - lock_page(page); - if (page->mapping != mapping) { - /* The page got truncated from under us */ - unlock_page(page); - page_cache_release(page); + folio_lock(folio); + if (folio->mapping != mapping) { + /* The folio got truncated from under us */ + folio_unlock(folio); + folio_put(folio); ext4_journal_stop(handle); goto retry_grab; } - wait_on_page_writeback(page); + /* In case writeback began while the folio was unlocked */ + folio_wait_stable(folio); if (ext4_should_dioread_nolock(inode)) - ret = __block_write_begin(page, pos, len, ext4_get_block_write); + ret = ext4_block_write_begin(handle, folio, pos, len, + ext4_get_block_unwritten); else - ret = __block_write_begin(page, pos, len, ext4_get_block); - + ret = ext4_block_write_begin(handle, folio, pos, len, + ext4_get_block); if (!ret && ext4_should_journal_data(inode)) { - ret = ext4_walk_page_buffers(handle, page_buffers(page), - from, to, NULL, - do_journal_get_write_access); + ret = ext4_walk_page_buffers(handle, inode, + folio_buffers(folio), from, to, + NULL, do_journal_get_write_access); } if (ret) { - unlock_page(page); + bool extended = (pos + len > inode->i_size) && + !ext4_verity_in_progress(inode); + + folio_unlock(folio); /* - * __block_write_begin may have instantiated a few blocks + * ext4_block_write_begin may have instantiated a few blocks * outside i_size. Trim these off again. Don't need - * i_size_read because we hold i_mutex. + * i_size_read because we hold i_rwsem. * * Add inode to orphan list in case we crash before * truncate finishes */ - if (pos + len > inode->i_size && ext4_can_truncate(inode)) + if (extended && ext4_can_truncate(inode)) ext4_orphan_add(handle, inode); ext4_journal_stop(handle); - if (pos + len > inode->i_size) { + if (extended) { ext4_truncate_failed_write(inode); /* * If truncate failed early the inode might @@ -1011,110 +1398,96 @@ retry_journal: ext4_orphan_del(NULL, inode); } - if (ret == -ENOSPC && - ext4_should_retry_alloc(inode->i_sb, &retries)) + if (ret == -EAGAIN || + (ret == -ENOSPC && + ext4_should_retry_alloc(inode->i_sb, &retries))) goto retry_journal; - page_cache_release(page); + folio_put(folio); return ret; } - *pagep = page; + *foliop = folio; return ret; } /* For write_end() in data=journal mode */ -static int write_end_fn(handle_t *handle, struct buffer_head *bh) +static int write_end_fn(handle_t *handle, struct inode *inode, + struct buffer_head *bh) { int ret; if (!buffer_mapped(bh) || buffer_freed(bh)) return 0; set_buffer_uptodate(bh); - ret = ext4_handle_dirty_metadata(handle, NULL, bh); + ret = ext4_dirty_journalled_data(handle, bh); clear_buffer_meta(bh); clear_buffer_prio(bh); + clear_buffer_new(bh); return ret; } /* * We need to pick up the new inode size which generic_commit_write gave us - * `file' can be NULL - eg, when called from page_symlink(). + * `iocb` can be NULL - eg, when called from page_symlink(). * - * ext4 never places buffers on inode->i_mapping->private_list. metadata + * ext4 never places buffers on inode->i_mapping->i_private_list. metadata * buffers are managed internally. */ -static int ext4_write_end(struct file *file, +static int ext4_write_end(const struct kiocb *iocb, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { handle_t *handle = ext4_journal_current_handle(); struct inode *inode = mapping->host; + loff_t old_size = inode->i_size; int ret = 0, ret2; int i_size_changed = 0; + bool verity = ext4_verity_in_progress(inode); trace_ext4_write_end(inode, pos, len, copied); - if (ext4_test_inode_state(inode, EXT4_STATE_ORDERED_MODE)) { - ret = ext4_jbd2_file_inode(handle, inode); - if (ret) { - unlock_page(page); - page_cache_release(page); - goto errout; - } - } - if (ext4_has_inline_data(inode)) { - ret = ext4_write_inline_data_end(inode, pos, len, - copied, page); - if (ret < 0) - goto errout; - copied = ret; - } else - copied = block_write_end(file, mapping, pos, - len, copied, page, fsdata); + if (ext4_has_inline_data(inode) && + ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) + return ext4_write_inline_data_end(inode, pos, len, copied, + folio); + copied = block_write_end(pos, len, copied, folio); /* - * No need to use i_size_read() here, the i_size - * cannot change under us because we hole i_mutex. - * - * But it's important to update i_size while still holding page lock: + * it's important to update i_size while still holding folio lock: * page writeout could otherwise come in and zero beyond i_size. + * + * If FS_IOC_ENABLE_VERITY is running on this inode, then Merkle tree + * blocks are being written past EOF, so skip the i_size update. */ - if (pos + copied > inode->i_size) { - i_size_write(inode, pos + copied); - i_size_changed = 1; - } + if (!verity) + i_size_changed = ext4_update_inode_size(inode, pos + copied); + folio_unlock(folio); + folio_put(folio); - if (pos + copied > EXT4_I(inode)->i_disksize) { - /* We need to mark inode dirty even if - * new_i_size is less that inode->i_size - * but greater than i_disksize. (hint delalloc) - */ - ext4_update_i_disksize(inode, (pos + copied)); - i_size_changed = 1; + if (old_size < pos && !verity) { + pagecache_isize_extended(inode, old_size, pos); + ext4_zero_partial_blocks(handle, inode, old_size, pos - old_size); } - unlock_page(page); - page_cache_release(page); - /* - * Don't mark the inode dirty under page lock. First, it unnecessarily - * makes the holding time of page lock longer. Second, it forces lock - * ordering of page lock and transaction start for journaling + * Don't mark the inode dirty under folio lock. First, it unnecessarily + * makes the holding time of folio lock longer. Second, it forces lock + * ordering of folio lock and transaction start for journaling * filesystems. */ if (i_size_changed) - ext4_mark_inode_dirty(handle, inode); + ret = ext4_mark_inode_dirty(handle, inode); - if (pos + len > inode->i_size && ext4_can_truncate(inode)) + if (pos + len > inode->i_size && !verity && ext4_can_truncate(inode)) /* if we have allocated more blocks and copied * less. We will have blocks allocated outside * inode->i_size. So truncate them */ ext4_orphan_add(handle, inode); -errout: + ret2 = ext4_journal_stop(handle); if (!ret) ret = ret2; - if (pos + len > inode->i_size) { + if (pos + len > inode->i_size && !verity) { ext4_truncate_failed_write(inode); /* * If truncate failed early the inode might still be @@ -1128,54 +1501,98 @@ errout: return ret ? ret : copied; } -static int ext4_journalled_write_end(struct file *file, +/* + * This is a private version of folio_zero_new_buffers() which doesn't + * set the buffer to be dirty, since in data=journalled mode we need + * to call ext4_dirty_journalled_data() instead. + */ +static void ext4_journalled_zero_new_buffers(handle_t *handle, + struct inode *inode, + struct folio *folio, + unsigned from, unsigned to) +{ + unsigned int block_start = 0, block_end; + struct buffer_head *head, *bh; + + bh = head = folio_buffers(folio); + do { + block_end = block_start + bh->b_size; + if (buffer_new(bh)) { + if (block_end > from && block_start < to) { + if (!folio_test_uptodate(folio)) { + unsigned start, size; + + start = max(from, block_start); + size = min(to, block_end) - start; + + folio_zero_range(folio, start, size); + } + clear_buffer_new(bh); + write_end_fn(handle, inode, bh); + } + } + block_start = block_end; + bh = bh->b_this_page; + } while (bh != head); +} + +static int ext4_journalled_write_end(const struct kiocb *iocb, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { handle_t *handle = ext4_journal_current_handle(); struct inode *inode = mapping->host; + loff_t old_size = inode->i_size; int ret = 0, ret2; int partial = 0; unsigned from, to; - loff_t new_i_size; + int size_changed = 0; + bool verity = ext4_verity_in_progress(inode); trace_ext4_journalled_write_end(inode, pos, len, copied); - from = pos & (PAGE_CACHE_SIZE - 1); + from = pos & (PAGE_SIZE - 1); to = from + len; BUG_ON(!ext4_handle_valid(handle)); if (ext4_has_inline_data(inode)) - copied = ext4_write_inline_data_end(inode, pos, len, - copied, page); - else { - if (copied < len) { - if (!PageUptodate(page)) - copied = 0; - page_zero_new_buffers(page, from+copied, to); - } + return ext4_write_inline_data_end(inode, pos, len, copied, + folio); - ret = ext4_walk_page_buffers(handle, page_buffers(page), from, - to, &partial, write_end_fn); + if (unlikely(copied < len) && !folio_test_uptodate(folio)) { + copied = 0; + ext4_journalled_zero_new_buffers(handle, inode, folio, + from, to); + } else { + if (unlikely(copied < len)) + ext4_journalled_zero_new_buffers(handle, inode, folio, + from + copied, to); + ret = ext4_walk_page_buffers(handle, inode, + folio_buffers(folio), + from, from + copied, &partial, + write_end_fn); if (!partial) - SetPageUptodate(page); + folio_mark_uptodate(folio); } - new_i_size = pos + copied; - if (new_i_size > inode->i_size) - i_size_write(inode, pos+copied); - ext4_set_inode_state(inode, EXT4_STATE_JDATA); + if (!verity) + size_changed = ext4_update_inode_size(inode, pos + copied); EXT4_I(inode)->i_datasync_tid = handle->h_transaction->t_tid; - if (new_i_size > EXT4_I(inode)->i_disksize) { - ext4_update_i_disksize(inode, new_i_size); + folio_unlock(folio); + folio_put(folio); + + if (old_size < pos && !verity) { + pagecache_isize_extended(inode, old_size, pos); + ext4_zero_partial_blocks(handle, inode, old_size, pos - old_size); + } + + if (size_changed) { ret2 = ext4_mark_inode_dirty(handle, inode); if (!ret) ret = ret2; } - unlock_page(page); - page_cache_release(page); - if (pos + len > inode->i_size && ext4_can_truncate(inode)) + if (pos + len > inode->i_size && !verity && ext4_can_truncate(inode)) /* if we have allocated more blocks and copied * less. We will have blocks allocated outside * inode->i_size. So truncate them @@ -1185,7 +1602,7 @@ static int ext4_journalled_write_end(struct file *file, ret2 = ext4_journal_stop(handle); if (!ret) ret = ret2; - if (pos + len > inode->i_size) { + if (pos + len > inode->i_size && !verity) { ext4_truncate_failed_write(inode); /* * If truncate failed early the inode might still be @@ -1200,116 +1617,37 @@ static int ext4_journalled_write_end(struct file *file, } /* - * Reserve a metadata for a single block located at lblock - */ -static int ext4_da_reserve_metadata(struct inode *inode, ext4_lblk_t lblock) -{ - int retries = 0; - struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); - struct ext4_inode_info *ei = EXT4_I(inode); - unsigned int md_needed; - ext4_lblk_t save_last_lblock; - int save_len; - - /* - * recalculate the amount of metadata blocks to reserve - * in order to allocate nrblocks - * worse case is one extent per block - */ -repeat: - spin_lock(&ei->i_block_reservation_lock); - /* - * ext4_calc_metadata_amount() has side effects, which we have - * to be prepared undo if we fail to claim space. - */ - save_len = ei->i_da_metadata_calc_len; - save_last_lblock = ei->i_da_metadata_calc_last_lblock; - md_needed = EXT4_NUM_B2C(sbi, - ext4_calc_metadata_amount(inode, lblock)); - trace_ext4_da_reserve_space(inode, md_needed); - - /* - * We do still charge estimated metadata to the sb though; - * we cannot afford to run out of free blocks. - */ - if (ext4_claim_free_clusters(sbi, md_needed, 0)) { - ei->i_da_metadata_calc_len = save_len; - ei->i_da_metadata_calc_last_lblock = save_last_lblock; - spin_unlock(&ei->i_block_reservation_lock); - if (ext4_should_retry_alloc(inode->i_sb, &retries)) { - cond_resched(); - goto repeat; - } - return -ENOSPC; - } - ei->i_reserved_meta_blocks += md_needed; - spin_unlock(&ei->i_block_reservation_lock); - - return 0; /* success */ -} - -/* - * Reserve a single cluster located at lblock + * Reserve space for 'nr_resv' clusters */ -static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock) +static int ext4_da_reserve_space(struct inode *inode, int nr_resv) { - int retries = 0; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_inode_info *ei = EXT4_I(inode); - unsigned int md_needed; int ret; - ext4_lblk_t save_last_lblock; - int save_len; /* * We will charge metadata quota at writeout time; this saves * us from metadata over-estimation, though we may go over by * a small amount in the end. Here we just reserve for data. */ - ret = dquot_reserve_block(inode, EXT4_C2B(sbi, 1)); + ret = dquot_reserve_block(inode, EXT4_C2B(sbi, nr_resv)); if (ret) return ret; - /* - * recalculate the amount of metadata blocks to reserve - * in order to allocate nrblocks - * worse case is one extent per block - */ -repeat: spin_lock(&ei->i_block_reservation_lock); - /* - * ext4_calc_metadata_amount() has side effects, which we have - * to be prepared undo if we fail to claim space. - */ - save_len = ei->i_da_metadata_calc_len; - save_last_lblock = ei->i_da_metadata_calc_last_lblock; - md_needed = EXT4_NUM_B2C(sbi, - ext4_calc_metadata_amount(inode, lblock)); - trace_ext4_da_reserve_space(inode, md_needed); - - /* - * We do still charge estimated metadata to the sb though; - * we cannot afford to run out of free blocks. - */ - if (ext4_claim_free_clusters(sbi, md_needed + 1, 0)) { - ei->i_da_metadata_calc_len = save_len; - ei->i_da_metadata_calc_last_lblock = save_last_lblock; + if (ext4_claim_free_clusters(sbi, nr_resv, 0)) { spin_unlock(&ei->i_block_reservation_lock); - if (ext4_should_retry_alloc(inode->i_sb, &retries)) { - cond_resched(); - goto repeat; - } - dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1)); + dquot_release_reservation_block(inode, EXT4_C2B(sbi, nr_resv)); return -ENOSPC; } - ei->i_reserved_data_blocks++; - ei->i_reserved_meta_blocks += md_needed; + ei->i_reserved_data_blocks += nr_resv; + trace_ext4_da_reserve_space(inode, nr_resv); spin_unlock(&ei->i_block_reservation_lock); return 0; /* success */ } -static void ext4_da_release_space(struct inode *inode, int to_free) +void ext4_da_release_space(struct inode *inode, int to_free) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_inode_info *ei = EXT4_I(inode); @@ -1336,20 +1674,6 @@ static void ext4_da_release_space(struct inode *inode, int to_free) } ei->i_reserved_data_blocks -= to_free; - if (ei->i_reserved_data_blocks == 0) { - /* - * We can release all of the reserved metadata blocks - * only when we have written all of the delayed - * allocation blocks. - * Note that in case of bigalloc, i_reserved_meta_blocks, - * i_reserved_data_blocks, etc. refer to number of clusters. - */ - percpu_counter_sub(&sbi->s_dirtyclusters_counter, - ei->i_reserved_meta_blocks); - ei->i_reserved_meta_blocks = 0; - ei->i_da_metadata_calc_len = 0; - } - /* update fs dirty data blocks counter */ percpu_counter_sub(&sbi->s_dirtyclusters_counter, to_free); @@ -1358,116 +1682,87 @@ static void ext4_da_release_space(struct inode *inode, int to_free) dquot_release_reservation_block(inode, EXT4_C2B(sbi, to_free)); } -static void ext4_da_page_release_reservation(struct page *page, - unsigned int offset, - unsigned int length) -{ - int to_release = 0; - struct buffer_head *head, *bh; - unsigned int curr_off = 0; - struct inode *inode = page->mapping->host; - struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); - unsigned int stop = offset + length; - int num_clusters; - ext4_fsblk_t lblk; - - BUG_ON(stop > PAGE_CACHE_SIZE || stop < length); - - head = page_buffers(page); - bh = head; - do { - unsigned int next_off = curr_off + bh->b_size; - - if (next_off > stop) - break; - - if ((offset <= curr_off) && (buffer_delay(bh))) { - to_release++; - clear_buffer_delay(bh); - } - curr_off = next_off; - } while ((bh = bh->b_this_page) != head); - - if (to_release) { - lblk = page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits); - ext4_es_remove_extent(inode, lblk, to_release); - } - - /* If we have released all the blocks belonging to a cluster, then we - * need to release the reserved space for that cluster. */ - num_clusters = EXT4_NUM_B2C(sbi, to_release); - while (num_clusters > 0) { - lblk = (page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits)) + - ((num_clusters - 1) << sbi->s_cluster_bits); - if (sbi->s_cluster_ratio == 1 || - !ext4_find_delalloc_cluster(inode, lblk)) - ext4_da_release_space(inode, 1); - - num_clusters--; - } -} - /* * Delayed allocation stuff */ struct mpage_da_data { + /* These are input fields for ext4_do_writepages() */ struct inode *inode; struct writeback_control *wbc; + unsigned int can_map:1; /* Can writepages call map blocks? */ + + /* These are internal state of ext4_do_writepages() */ + loff_t start_pos; /* The start pos to write */ + loff_t next_pos; /* Current pos to examine */ + loff_t end_pos; /* Last pos to examine */ - pgoff_t first_page; /* The first page to write */ - pgoff_t next_page; /* Current page to examine */ - pgoff_t last_page; /* Last page to examine */ /* - * Extent to map - this can be after first_page because that can be + * Extent to map - this can be after start_pos because that can be * fully mapped. We somewhat abuse m_flags to store whether the extent * is delalloc or unwritten. */ struct ext4_map_blocks map; struct ext4_io_submit io_submit; /* IO submission data */ + unsigned int do_map:1; + unsigned int scanned_until_end:1; + unsigned int journalled_more_data:1; }; static void mpage_release_unused_pages(struct mpage_da_data *mpd, bool invalidate) { - int nr_pages, i; + unsigned nr, i; pgoff_t index, end; - struct pagevec pvec; + struct folio_batch fbatch; struct inode *inode = mpd->inode; struct address_space *mapping = inode->i_mapping; - /* This is necessary when next_page == 0. */ - if (mpd->first_page >= mpd->next_page) + /* This is necessary when next_pos == 0. */ + if (mpd->start_pos >= mpd->next_pos) return; - index = mpd->first_page; - end = mpd->next_page - 1; + mpd->scanned_until_end = 0; if (invalidate) { ext4_lblk_t start, last; - start = index << (PAGE_CACHE_SHIFT - inode->i_blkbits); - last = end << (PAGE_CACHE_SHIFT - inode->i_blkbits); - ext4_es_remove_extent(inode, start, last - start + 1); + start = EXT4_B_TO_LBLK(inode, mpd->start_pos); + last = mpd->next_pos >> inode->i_blkbits; + + /* + * avoid racing with extent status tree scans made by + * ext4_insert_delayed_block() + */ + down_write(&EXT4_I(inode)->i_data_sem); + ext4_es_remove_extent(inode, start, last - start); + up_write(&EXT4_I(inode)->i_data_sem); } - pagevec_init(&pvec, 0); - while (index <= end) { - nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE); - if (nr_pages == 0) + folio_batch_init(&fbatch); + index = mpd->start_pos >> PAGE_SHIFT; + end = mpd->next_pos >> PAGE_SHIFT; + while (index < end) { + nr = filemap_get_folios(mapping, &index, end - 1, &fbatch); + if (nr == 0) break; - for (i = 0; i < nr_pages; i++) { - struct page *page = pvec.pages[i]; - if (page->index > end) - break; - BUG_ON(!PageLocked(page)); - BUG_ON(PageWriteback(page)); + for (i = 0; i < nr; i++) { + struct folio *folio = fbatch.folios[i]; + + if (folio_pos(folio) < mpd->start_pos) + continue; + if (folio_next_index(folio) > end) + continue; + BUG_ON(!folio_test_locked(folio)); + BUG_ON(folio_test_writeback(folio)); if (invalidate) { - block_invalidatepage(page, 0, PAGE_CACHE_SIZE); - ClearPageUptodate(page); + if (folio_mapped(folio)) + folio_clear_dirty_for_io(folio); + block_invalidate_folio(folio, 0, + folio_size(folio)); + folio_clear_uptodate(folio); } - unlock_page(page); + folio_unlock(folio); } - index = pvec.pages[nr_pages - 1]->index + 1; - pagevec_release(&pvec); + folio_batch_release(&fbatch); } } @@ -1490,181 +1785,214 @@ static void ext4_print_free_blocks(struct inode *inode) ext4_msg(sb, KERN_CRIT, "Block reservation details"); ext4_msg(sb, KERN_CRIT, "i_reserved_data_blocks=%u", ei->i_reserved_data_blocks); - ext4_msg(sb, KERN_CRIT, "i_reserved_meta_blocks=%u", - ei->i_reserved_meta_blocks); - ext4_msg(sb, KERN_CRIT, "i_allocated_meta_blocks=%u", - ei->i_allocated_meta_blocks); return; } -static int ext4_bh_delay_or_unwritten(handle_t *handle, struct buffer_head *bh) +/* + * Check whether the cluster containing lblk has been allocated or has + * delalloc reservation. + * + * Returns 0 if the cluster doesn't have either, 1 if it has delalloc + * reservation, 2 if it's already been allocated, negative error code on + * failure. + */ +static int ext4_clu_alloc_state(struct inode *inode, ext4_lblk_t lblk) +{ + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + int ret; + + /* Has delalloc reservation? */ + if (ext4_es_scan_clu(inode, &ext4_es_is_delayed, lblk)) + return 1; + + /* Already been allocated? */ + if (ext4_es_scan_clu(inode, &ext4_es_is_mapped, lblk)) + return 2; + ret = ext4_clu_mapped(inode, EXT4_B2C(sbi, lblk)); + if (ret < 0) + return ret; + if (ret > 0) + return 2; + + return 0; +} + +/* + * ext4_insert_delayed_blocks - adds a multiple delayed blocks to the extents + * status tree, incrementing the reserved + * cluster/block count or making pending + * reservations where needed + * + * @inode - file containing the newly added block + * @lblk - start logical block to be added + * @len - length of blocks to be added + * + * Returns 0 on success, negative error code on failure. + */ +static int ext4_insert_delayed_blocks(struct inode *inode, ext4_lblk_t lblk, + ext4_lblk_t len) { - return (buffer_delay(bh) || buffer_unwritten(bh)) && buffer_dirty(bh); + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + int ret; + bool lclu_allocated = false; + bool end_allocated = false; + ext4_lblk_t resv_clu; + ext4_lblk_t end = lblk + len - 1; + + /* + * If the cluster containing lblk or end is shared with a delayed, + * written, or unwritten extent in a bigalloc file system, it's + * already been accounted for and does not need to be reserved. + * A pending reservation must be made for the cluster if it's + * shared with a written or unwritten extent and doesn't already + * have one. Written and unwritten extents can be purged from the + * extents status tree if the system is under memory pressure, so + * it's necessary to examine the extent tree if a search of the + * extents status tree doesn't get a match. + */ + if (sbi->s_cluster_ratio == 1) { + ret = ext4_da_reserve_space(inode, len); + if (ret != 0) /* ENOSPC */ + return ret; + } else { /* bigalloc */ + resv_clu = EXT4_B2C(sbi, end) - EXT4_B2C(sbi, lblk) + 1; + + ret = ext4_clu_alloc_state(inode, lblk); + if (ret < 0) + return ret; + if (ret > 0) { + resv_clu--; + lclu_allocated = (ret == 2); + } + + if (EXT4_B2C(sbi, lblk) != EXT4_B2C(sbi, end)) { + ret = ext4_clu_alloc_state(inode, end); + if (ret < 0) + return ret; + if (ret > 0) { + resv_clu--; + end_allocated = (ret == 2); + } + } + + if (resv_clu) { + ret = ext4_da_reserve_space(inode, resv_clu); + if (ret != 0) /* ENOSPC */ + return ret; + } + } + + ext4_es_insert_delayed_extent(inode, lblk, len, lclu_allocated, + end_allocated); + return 0; } /* - * This function is grabs code from the very beginning of - * ext4_map_blocks, but assumes that the caller is from delayed write - * time. This function looks up the requested blocks and sets the - * buffer delay bit under the protection of i_data_sem. + * Looks up the requested blocks and sets the delalloc extent map. + * First try to look up for the extent entry that contains the requested + * blocks in the extent status tree without i_data_sem, then try to look + * up for the ondisk extent mapping with i_data_sem in read mode, + * finally hold i_data_sem in write mode, looks up again and add a + * delalloc extent entry if it still couldn't find any extent. Pass out + * the mapped extent through @map and return 0 on success. */ -static int ext4_da_map_blocks(struct inode *inode, sector_t iblock, - struct ext4_map_blocks *map, - struct buffer_head *bh) +static int ext4_da_map_blocks(struct inode *inode, struct ext4_map_blocks *map) { struct extent_status es; int retval; - sector_t invalid_block = ~((sector_t) 0xffff); #ifdef ES_AGGRESSIVE_TEST struct ext4_map_blocks orig_map; memcpy(&orig_map, map, sizeof(*map)); #endif - if (invalid_block < ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es)) - invalid_block = ~0; - map->m_flags = 0; - ext_debug("ext4_da_map_blocks(): inode %lu, max_blocks %u," - "logical block %lu\n", inode->i_ino, map->m_len, + ext_debug(inode, "max_blocks %u, logical block %lu\n", map->m_len, (unsigned long) map->m_lblk); - ext4_es_lru_add(inode); + ext4_check_map_extents_env(inode); /* Lookup extent status tree firstly */ - if (ext4_es_lookup_extent(inode, iblock, &es)) { + if (ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es, NULL)) { + map->m_len = min_t(unsigned int, map->m_len, + es.es_len - (map->m_lblk - es.es_lblk)); - if (ext4_es_is_hole(&es)) { - retval = 0; - down_read((&EXT4_I(inode)->i_data_sem)); + if (ext4_es_is_hole(&es)) goto add_delayed; - } +found: /* * Delayed extent could be allocated by fallocate. * So we need to check it. */ - if (ext4_es_is_delayed(&es) && !ext4_es_is_unwritten(&es)) { - map_bh(bh, inode->i_sb, invalid_block); - set_buffer_new(bh); - set_buffer_delay(bh); + if (ext4_es_is_delayed(&es)) { + map->m_flags |= EXT4_MAP_DELAYED; return 0; } - map->m_pblk = ext4_es_pblock(&es) + iblock - es.es_lblk; - retval = es.es_len - (iblock - es.es_lblk); - if (retval > map->m_len) - retval = map->m_len; - map->m_len = retval; + map->m_pblk = ext4_es_pblock(&es) + map->m_lblk - es.es_lblk; if (ext4_es_is_written(&es)) map->m_flags |= EXT4_MAP_MAPPED; else if (ext4_es_is_unwritten(&es)) map->m_flags |= EXT4_MAP_UNWRITTEN; else - BUG_ON(1); + BUG(); #ifdef ES_AGGRESSIVE_TEST ext4_map_blocks_es_recheck(NULL, inode, map, &orig_map, 0); #endif - return retval; + return 0; } /* * Try to see if we can get the block without requesting a new * file system block. */ - down_read((&EXT4_I(inode)->i_data_sem)); - if (ext4_has_inline_data(inode)) { - /* - * We will soon create blocks for this page, and let - * us pretend as if the blocks aren't allocated yet. - * In case of clusters, we have to handle the work - * of mapping from cluster so that the reserved space - * is calculated properly. - */ - if ((EXT4_SB(inode->i_sb)->s_cluster_ratio > 1) && - ext4_find_delalloc_cluster(inode, map->m_lblk)) - map->m_flags |= EXT4_MAP_FROM_CLUSTER; + down_read(&EXT4_I(inode)->i_data_sem); + if (ext4_has_inline_data(inode)) retval = 0; - } else if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) - retval = ext4_ext_map_blocks(NULL, inode, map, - EXT4_GET_BLOCKS_NO_PUT_HOLE); else - retval = ext4_ind_map_blocks(NULL, inode, map, - EXT4_GET_BLOCKS_NO_PUT_HOLE); + retval = ext4_map_query_blocks(NULL, inode, map, 0); + up_read(&EXT4_I(inode)->i_data_sem); + if (retval) + return retval < 0 ? retval : 0; add_delayed: - if (retval == 0) { - int ret; - /* - * XXX: __block_prepare_write() unmaps passed block, - * is it OK? - */ - /* - * If the block was allocated from previously allocated cluster, - * then we don't need to reserve it again. However we still need - * to reserve metadata for every block we're going to write. - */ - if (!(map->m_flags & EXT4_MAP_FROM_CLUSTER)) { - ret = ext4_da_reserve_space(inode, iblock); - if (ret) { - /* not enough space to reserve */ - retval = ret; - goto out_unlock; - } - } else { - ret = ext4_da_reserve_metadata(inode, iblock); - if (ret) { - /* not enough space to reserve */ - retval = ret; - goto out_unlock; - } - } + down_write(&EXT4_I(inode)->i_data_sem); + /* + * Page fault path (ext4_page_mkwrite does not take i_rwsem) + * and fallocate path (no folio lock) can race. Make sure we + * lookup the extent status tree here again while i_data_sem + * is held in write mode, before inserting a new da entry in + * the extent status tree. + */ + if (ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es, NULL)) { + map->m_len = min_t(unsigned int, map->m_len, + es.es_len - (map->m_lblk - es.es_lblk)); - ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len, - ~0, EXTENT_STATUS_DELAYED); - if (ret) { - retval = ret; - goto out_unlock; + if (!ext4_es_is_hole(&es)) { + up_write(&EXT4_I(inode)->i_data_sem); + goto found; } - - /* Clear EXT4_MAP_FROM_CLUSTER flag since its purpose is served - * and it should not appear on the bh->b_state. - */ - map->m_flags &= ~EXT4_MAP_FROM_CLUSTER; - - map_bh(bh, inode->i_sb, invalid_block); - set_buffer_new(bh); - set_buffer_delay(bh); - } else if (retval > 0) { - int ret; - unsigned long long status; - -#ifdef ES_AGGRESSIVE_TEST - if (retval != map->m_len) { - printk("ES len assertation failed for inode: %lu " - "retval %d != map->m_len %d " - "in %s (lookup)\n", inode->i_ino, retval, - map->m_len, __func__); + } else if (!ext4_has_inline_data(inode)) { + retval = ext4_map_query_blocks(NULL, inode, map, 0); + if (retval) { + up_write(&EXT4_I(inode)->i_data_sem); + return retval < 0 ? retval : 0; } -#endif - - status = map->m_flags & EXT4_MAP_UNWRITTEN ? - EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN; - ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len, - map->m_pblk, status); - if (ret != 0) - retval = ret; } -out_unlock: - up_read((&EXT4_I(inode)->i_data_sem)); + map->m_flags |= EXT4_MAP_DELAYED; + retval = ext4_insert_delayed_blocks(inode, map->m_lblk, map->m_len); + if (!retval) + map->m_seq = READ_ONCE(EXT4_I(inode)->i_es_seq); + up_write(&EXT4_I(inode)->i_data_sem); return retval; } /* - * This is a special get_blocks_t callback which is used by + * This is a special get_block_t callback which is used by * ext4_da_write_begin(). It will either return mapped block or * reserve space for a single block. * @@ -1679,11 +2007,15 @@ int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, struct buffer_head *bh, int create) { struct ext4_map_blocks map; + sector_t invalid_block = ~((sector_t) 0xffff); int ret = 0; BUG_ON(create == 0); BUG_ON(bh->b_size != inode->i_sb->s_blocksize); + if (invalid_block < ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es)) + invalid_block = ~0; + map.m_lblk = iblock; map.m_len = 1; @@ -1692,12 +2024,19 @@ int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, * preallocated blocks are unmapped but should treated * the same as allocated blocks. */ - ret = ext4_da_map_blocks(inode, iblock, &map, bh); - if (ret <= 0) + ret = ext4_da_map_blocks(inode, &map); + if (ret < 0) return ret; + if (map.m_flags & EXT4_MAP_DELAYED) { + map_bh(bh, inode->i_sb, invalid_block); + set_buffer_new(bh); + set_buffer_delay(bh); + return 0; + } + map_bh(bh, inode->i_sb, map.m_pblk); - bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags; + ext4_update_bh_state(bh, map.m_flags); if (buffer_unwritten(bh)) { /* A delayed write to unwritten bh should be marked @@ -1712,196 +2051,50 @@ int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, return 0; } -static int bget_one(handle_t *handle, struct buffer_head *bh) -{ - get_bh(bh); - return 0; -} - -static int bput_one(handle_t *handle, struct buffer_head *bh) -{ - put_bh(bh); - return 0; -} - -static int __ext4_journalled_writepage(struct page *page, - unsigned int len) +static void mpage_folio_done(struct mpage_da_data *mpd, struct folio *folio) { - struct address_space *mapping = page->mapping; - struct inode *inode = mapping->host; - struct buffer_head *page_bufs = NULL; - handle_t *handle = NULL; - int ret = 0, err = 0; - int inline_data = ext4_has_inline_data(inode); - struct buffer_head *inode_bh = NULL; - - ClearPageChecked(page); - - if (inline_data) { - BUG_ON(page->index != 0); - BUG_ON(len > ext4_get_max_inline_size(inode)); - inode_bh = ext4_journalled_write_inline_data(inode, len, page); - if (inode_bh == NULL) - goto out; - } else { - page_bufs = page_buffers(page); - if (!page_bufs) { - BUG(); - goto out; - } - ext4_walk_page_buffers(handle, page_bufs, 0, len, - NULL, bget_one); - } - /* As soon as we unlock the page, it can go away, but we have - * references to buffers so we are safe */ - unlock_page(page); - - handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, - ext4_writepage_trans_blocks(inode)); - if (IS_ERR(handle)) { - ret = PTR_ERR(handle); - goto out; - } - - BUG_ON(!ext4_handle_valid(handle)); - - if (inline_data) { - ret = ext4_journal_get_write_access(handle, inode_bh); - - err = ext4_handle_dirty_metadata(handle, inode, inode_bh); - - } else { - ret = ext4_walk_page_buffers(handle, page_bufs, 0, len, NULL, - do_journal_get_write_access); - - err = ext4_walk_page_buffers(handle, page_bufs, 0, len, NULL, - write_end_fn); - } - if (ret == 0) - ret = err; - EXT4_I(inode)->i_datasync_tid = handle->h_transaction->t_tid; - err = ext4_journal_stop(handle); - if (!ret) - ret = err; - - if (!ext4_has_inline_data(inode)) - ext4_walk_page_buffers(handle, page_bufs, 0, len, - NULL, bput_one); - ext4_set_inode_state(inode, EXT4_STATE_JDATA); -out: - brelse(inode_bh); - return ret; + mpd->start_pos += folio_size(folio); + mpd->wbc->nr_to_write -= folio_nr_pages(folio); + folio_unlock(folio); } -/* - * Note that we don't need to start a transaction unless we're journaling data - * because we should have holes filled from ext4_page_mkwrite(). We even don't - * need to file the inode to the transaction's list in ordered mode because if - * we are writing back data added by write(), the inode is already there and if - * we are writing back data modified via mmap(), no one guarantees in which - * transaction the data will hit the disk. In case we are journaling data, we - * cannot start transaction directly because transaction start ranks above page - * lock so we have to do some magic. - * - * This function can get called via... - * - ext4_writepages after taking page lock (have journal handle) - * - journal_submit_inode_data_buffers (no journal handle) - * - shrink_page_list via the kswapd/direct reclaim (no journal handle) - * - grab_page_cache when doing write_begin (have journal handle) - * - * We don't do any block allocation in this function. If we have page with - * multiple blocks we need to write those buffer_heads that are mapped. This - * is important for mmaped based write. So if we do with blocksize 1K - * truncate(f, 1024); - * a = mmap(f, 0, 4096); - * a[0] = 'a'; - * truncate(f, 4096); - * we have in the page first buffer_head mapped via page_mkwrite call back - * but other buffer_heads would be unmapped but dirty (dirty done via the - * do_wp_page). So writepage should write the first block. If we modify - * the mmap area beyond 1024 we will again get a page_fault and the - * page_mkwrite callback will do the block allocation and mark the - * buffer_heads mapped. - * - * We redirty the page if we have any buffer_heads that is either delay or - * unwritten in the page. - * - * We can get recursively called as show below. - * - * ext4_writepage() -> kmalloc() -> __alloc_pages() -> page_launder() -> - * ext4_writepage() - * - * But since we don't do any block allocation we should not deadlock. - * Page also have the dirty flag cleared so we don't get recurive page_lock. - */ -static int ext4_writepage(struct page *page, - struct writeback_control *wbc) +static int mpage_submit_folio(struct mpage_da_data *mpd, struct folio *folio) { - int ret = 0; + size_t len; loff_t size; - unsigned int len; - struct buffer_head *page_bufs = NULL; - struct inode *inode = page->mapping->host; - struct ext4_io_submit io_submit; - - trace_ext4_writepage(page); - size = i_size_read(inode); - if (page->index == size >> PAGE_CACHE_SHIFT) - len = size & ~PAGE_CACHE_MASK; - else - len = PAGE_CACHE_SIZE; + int err; - page_bufs = page_buffers(page); + WARN_ON_ONCE(folio_pos(folio) != mpd->start_pos); + folio_clear_dirty_for_io(folio); /* - * We cannot do block allocation or other extent handling in this - * function. If there are buffers needing that, we have to redirty - * the page. But we may reach here when we do a journal commit via - * journal_submit_inode_data_buffers() and in that case we must write - * allocated buffers to achieve data=ordered mode guarantees. + * We have to be very careful here! Nothing protects writeback path + * against i_size changes and the page can be writeably mapped into + * page tables. So an application can be growing i_size and writing + * data through mmap while writeback runs. folio_clear_dirty_for_io() + * write-protects our page in page tables and the page cannot get + * written to again until we release folio lock. So only after + * folio_clear_dirty_for_io() we are safe to sample i_size for + * ext4_bio_write_folio() to zero-out tail of the written page. We rely + * on the barrier provided by folio_test_clear_dirty() in + * folio_clear_dirty_for_io() to make sure i_size is really sampled only + * after page tables are updated. */ - if (ext4_walk_page_buffers(NULL, page_bufs, 0, len, NULL, - ext4_bh_delay_or_unwritten)) { - redirty_page_for_writepage(wbc, page); - if (current->flags & PF_MEMALLOC) { - /* - * For memory cleaning there's no point in writing only - * some buffers. So just bail out. Warn if we came here - * from direct reclaim. - */ - WARN_ON_ONCE((current->flags & (PF_MEMALLOC|PF_KSWAPD)) - == PF_MEMALLOC); - unlock_page(page); - return 0; - } - } - - if (PageChecked(page) && ext4_should_journal_data(inode)) - /* - * It's mmapped pagecache. Add buffers and journal it. There - * doesn't seem much point in redirtying the page here. - */ - return __ext4_journalled_writepage(page, len); + size = i_size_read(mpd->inode); + len = folio_size(folio); + if (folio_pos(folio) + len > size && + !ext4_verity_in_progress(mpd->inode)) + len = size & (len - 1); + err = ext4_bio_write_folio(&mpd->io_submit, folio, len); - ext4_io_submit_init(&io_submit, wbc); - io_submit.io_end = ext4_init_io_end(inode, GFP_NOFS); - if (!io_submit.io_end) { - redirty_page_for_writepage(wbc, page); - unlock_page(page); - return -ENOMEM; - } - ret = ext4_bio_write_page(&io_submit, page, len, wbc); - ext4_io_submit(&io_submit); - /* Drop io_end reference we got from init */ - ext4_put_io_end_defer(io_submit.io_end); - return ret; + return err; } -#define BH_FLAGS ((1 << BH_Unwritten) | (1 << BH_Delay)) +#define BH_FLAGS (BIT(BH_Unwritten) | BIT(BH_Delay)) /* * mballoc gives us at most this number of blocks... * XXX: That seems to be only a limitation of ext4_mb_normalize_request(). - * The rest of mballoc seems to handle chunks upto full group size. + * The rest of mballoc seems to handle chunks up to full group size. */ #define MAX_WRITEPAGES_EXTENT_LEN 2048 @@ -1910,81 +2103,179 @@ static int ext4_writepage(struct page *page, * * @mpd - extent of blocks * @lblk - logical number of the block in the file - * @b_state - b_state of the buffer head added + * @bh - buffer head we want to add to the extent * - * the function is used to collect contig. blocks in same state + * The function is used to collect contig. blocks in the same state. If the + * buffer doesn't require mapping for writeback and we haven't started the + * extent of buffers to map yet, the function returns 'true' immediately - the + * caller can write the buffer right away. Otherwise the function returns true + * if the block has been added to the extent, false if the block couldn't be + * added. */ -static int mpage_add_bh_to_extent(struct mpage_da_data *mpd, ext4_lblk_t lblk, - unsigned long b_state) +static bool mpage_add_bh_to_extent(struct mpage_da_data *mpd, ext4_lblk_t lblk, + struct buffer_head *bh) { struct ext4_map_blocks *map = &mpd->map; - /* Don't go larger than mballoc is willing to allocate */ - if (map->m_len >= MAX_WRITEPAGES_EXTENT_LEN) - return 0; + /* Buffer that doesn't need mapping for writeback? */ + if (!buffer_dirty(bh) || !buffer_mapped(bh) || + (!buffer_delay(bh) && !buffer_unwritten(bh))) { + /* So far no extent to map => we write the buffer right away */ + if (map->m_len == 0) + return true; + return false; + } /* First block in the extent? */ if (map->m_len == 0) { + /* We cannot map unless handle is started... */ + if (!mpd->do_map) + return false; map->m_lblk = lblk; map->m_len = 1; - map->m_flags = b_state & BH_FLAGS; - return 1; + map->m_flags = bh->b_state & BH_FLAGS; + return true; } + /* Don't go larger than mballoc is willing to allocate */ + if (map->m_len >= MAX_WRITEPAGES_EXTENT_LEN) + return false; + /* Can we merge the block to our big extent? */ if (lblk == map->m_lblk + map->m_len && - (b_state & BH_FLAGS) == map->m_flags) { + (bh->b_state & BH_FLAGS) == map->m_flags) { map->m_len++; - return 1; + return true; } - return 0; + return false; } -static bool add_page_bufs_to_extent(struct mpage_da_data *mpd, - struct buffer_head *head, - struct buffer_head *bh, - ext4_lblk_t lblk) +/* + * mpage_process_page_bufs - submit page buffers for IO or add them to extent + * + * @mpd - extent of blocks for mapping + * @head - the first buffer in the page + * @bh - buffer we should start processing from + * @lblk - logical number of the block in the file corresponding to @bh + * + * Walk through page buffers from @bh upto @head (exclusive) and either submit + * the page for IO if all buffers in this page were mapped and there's no + * accumulated extent of buffers to map or add buffers in the page to the + * extent of buffers to map. The function returns 1 if the caller can continue + * by processing the next page, 0 if it should stop adding buffers to the + * extent to map because we cannot extend it anymore. It can also return value + * < 0 in case of error during IO submission. + */ +static int mpage_process_page_bufs(struct mpage_da_data *mpd, + struct buffer_head *head, + struct buffer_head *bh, + ext4_lblk_t lblk) { struct inode *inode = mpd->inode; - ext4_lblk_t blocks = (i_size_read(inode) + (1 << inode->i_blkbits) - 1) + int err; + ext4_lblk_t blocks = (i_size_read(inode) + i_blocksize(inode) - 1) >> inode->i_blkbits; + if (ext4_verity_in_progress(inode)) + blocks = EXT_MAX_BLOCKS; + do { BUG_ON(buffer_locked(bh)); - if (!buffer_dirty(bh) || !buffer_mapped(bh) || - (!buffer_delay(bh) && !buffer_unwritten(bh)) || - lblk >= blocks) { + if (lblk >= blocks || !mpage_add_bh_to_extent(mpd, lblk, bh)) { /* Found extent to map? */ if (mpd->map.m_len) - return false; - if (lblk >= blocks) - return true; - continue; + return 0; + /* Buffer needs mapping and handle is not started? */ + if (!mpd->do_map) + return 0; + /* Everything mapped so far and we hit EOF */ + break; } - if (!mpage_add_bh_to_extent(mpd, lblk, bh->b_state)) - return false; } while (lblk++, (bh = bh->b_this_page) != head); - return true; + /* So far everything mapped? Submit the page for IO. */ + if (mpd->map.m_len == 0) { + err = mpage_submit_folio(mpd, head->b_folio); + if (err < 0) + return err; + mpage_folio_done(mpd, head->b_folio); + } + if (lblk >= blocks) { + mpd->scanned_until_end = 1; + return 0; + } + return 1; } -static int mpage_submit_page(struct mpage_da_data *mpd, struct page *page) +/* + * mpage_process_folio - update folio buffers corresponding to changed extent + * and may submit fully mapped page for IO + * @mpd: description of extent to map, on return next extent to map + * @folio: Contains these buffers. + * @m_lblk: logical block mapping. + * @m_pblk: corresponding physical mapping. + * @map_bh: determines on return whether this page requires any further + * mapping or not. + * + * Scan given folio buffers corresponding to changed extent and update buffer + * state according to new extent state. + * We map delalloc buffers to their physical location, clear unwritten bits. + * If the given folio is not fully mapped, we update @mpd to the next extent in + * the given folio that needs mapping & return @map_bh as true. + */ +static int mpage_process_folio(struct mpage_da_data *mpd, struct folio *folio, + ext4_lblk_t *m_lblk, ext4_fsblk_t *m_pblk, + bool *map_bh) { - int len; - loff_t size = i_size_read(mpd->inode); - int err; + struct buffer_head *head, *bh; + ext4_io_end_t *io_end = mpd->io_submit.io_end; + ext4_lblk_t lblk = *m_lblk; + ext4_fsblk_t pblock = *m_pblk; + int err = 0; + ssize_t io_end_size = 0; + struct ext4_io_end_vec *io_end_vec = ext4_last_io_end_vec(io_end); - BUG_ON(page->index != mpd->first_page); - if (page->index == size >> PAGE_CACHE_SHIFT) - len = size & ~PAGE_CACHE_MASK; - else - len = PAGE_CACHE_SIZE; - clear_page_dirty_for_io(page); - err = ext4_bio_write_page(&mpd->io_submit, page, len, mpd->wbc); - if (!err) - mpd->wbc->nr_to_write--; - mpd->first_page++; + bh = head = folio_buffers(folio); + do { + if (lblk < mpd->map.m_lblk) + continue; + if (lblk >= mpd->map.m_lblk + mpd->map.m_len) { + /* + * Buffer after end of mapped extent. + * Find next buffer in the folio to map. + */ + mpd->map.m_len = 0; + mpd->map.m_flags = 0; + io_end_vec->size += io_end_size; + + err = mpage_process_page_bufs(mpd, head, bh, lblk); + if (err > 0) + err = 0; + if (!err && mpd->map.m_len && mpd->map.m_lblk > lblk) { + io_end_vec = ext4_alloc_io_end_vec(io_end); + if (IS_ERR(io_end_vec)) { + err = PTR_ERR(io_end_vec); + goto out; + } + io_end_vec->offset = EXT4_LBLK_TO_B(mpd->inode, + mpd->map.m_lblk); + } + *map_bh = true; + goto out; + } + if (buffer_delay(bh)) { + clear_buffer_delay(bh); + bh->b_blocknr = pblock++; + } + clear_buffer_unwritten(bh); + io_end_size += i_blocksize(mpd->inode); + } while (lblk++, (bh = bh->b_this_page) != head); + io_end_vec->size += io_end_size; + *map_bh = false; +out: + *m_lblk = lblk; + *m_pblk = pblock; return err; } @@ -1997,87 +2288,59 @@ static int mpage_submit_page(struct mpage_da_data *mpd, struct page *page) * Scan buffers corresponding to changed extent (we expect corresponding pages * to be already locked) and update buffer state according to new extent state. * We map delalloc buffers to their physical location, clear unwritten bits, - * and mark buffers as uninit when we perform writes to uninitialized extents + * and mark buffers as uninit when we perform writes to unwritten extents * and do extent conversion after IO is finished. If the last page is not fully * mapped, we update @map to the next extent in the last page that needs * mapping. Otherwise we submit the page for IO. */ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd) { - struct pagevec pvec; - int nr_pages, i; + struct folio_batch fbatch; + unsigned nr, i; struct inode *inode = mpd->inode; - struct buffer_head *head, *bh; - int bpp_bits = PAGE_CACHE_SHIFT - inode->i_blkbits; - ext4_lblk_t blocks = (i_size_read(inode) + (1 << inode->i_blkbits) - 1) - >> inode->i_blkbits; pgoff_t start, end; ext4_lblk_t lblk; - sector_t pblock; + ext4_fsblk_t pblock; int err; + bool map_bh = false; - start = mpd->map.m_lblk >> bpp_bits; - end = (mpd->map.m_lblk + mpd->map.m_len - 1) >> bpp_bits; - lblk = start << bpp_bits; + start = EXT4_LBLK_TO_PG(inode, mpd->map.m_lblk); + end = EXT4_LBLK_TO_PG(inode, mpd->map.m_lblk + mpd->map.m_len - 1); pblock = mpd->map.m_pblk; - pagevec_init(&pvec, 0); + folio_batch_init(&fbatch); while (start <= end) { - nr_pages = pagevec_lookup(&pvec, inode->i_mapping, start, - PAGEVEC_SIZE); - if (nr_pages == 0) + nr = filemap_get_folios(inode->i_mapping, &start, end, &fbatch); + if (nr == 0) break; - for (i = 0; i < nr_pages; i++) { - struct page *page = pvec.pages[i]; - - if (page->index > end) - break; - /* Upto 'end' pages must be contiguous */ - BUG_ON(page->index != start); - bh = head = page_buffers(page); - do { - if (lblk < mpd->map.m_lblk) - continue; - if (lblk >= mpd->map.m_lblk + mpd->map.m_len) { - /* - * Buffer after end of mapped extent. - * Find next buffer in the page to map. - */ - mpd->map.m_len = 0; - mpd->map.m_flags = 0; - add_page_bufs_to_extent(mpd, head, bh, - lblk); - pagevec_release(&pvec); - return 0; - } - if (buffer_delay(bh)) { - clear_buffer_delay(bh); - bh->b_blocknr = pblock++; - } - clear_buffer_unwritten(bh); - } while (++lblk < blocks && - (bh = bh->b_this_page) != head); + for (i = 0; i < nr; i++) { + struct folio *folio = fbatch.folios[i]; + lblk = EXT4_PG_TO_LBLK(inode, folio->index); + err = mpage_process_folio(mpd, folio, &lblk, &pblock, + &map_bh); /* - * FIXME: This is going to break if dioread_nolock - * supports blocksize < pagesize as we will try to - * convert potentially unmapped parts of inode. + * If map_bh is true, means page may require further bh + * mapping, or maybe the page was submitted for IO. + * So we return to call further extent mapping. */ - mpd->io_submit.io_end->size += PAGE_CACHE_SIZE; + if (err < 0 || map_bh) + goto out; /* Page fully mapped - let IO run! */ - err = mpage_submit_page(mpd, page); - if (err < 0) { - pagevec_release(&pvec); - return err; - } - start++; + err = mpage_submit_folio(mpd, folio); + if (err < 0) + goto out; + mpage_folio_done(mpd, folio); } - pagevec_release(&pvec); + folio_batch_release(&fbatch); } /* Extent fully mapped and matches with page boundary. We are done. */ mpd->map.m_len = 0; mpd->map.m_flags = 0; return 0; +out: + folio_batch_release(&fbatch); + return err; } static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd) @@ -2085,62 +2348,101 @@ static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd) struct inode *inode = mpd->inode; struct ext4_map_blocks *map = &mpd->map; int get_blocks_flags; - int err; + int err, dioread_nolock; + + /* Make sure transaction has enough credits for this extent */ + err = ext4_journal_ensure_extent_credits(handle, inode); + if (err < 0) + return err; trace_ext4_da_write_pages_extent(inode, map); /* * Call ext4_map_blocks() to allocate any delayed allocation blocks, or - * to convert an uninitialized extent to be initialized (in the case + * to convert an unwritten extent to be initialized (in the case * where we have written into one or more preallocated blocks). It is * possible that we're going to need more metadata blocks than * previously reserved. However we must not fail because we're in * writeback and there is nothing we can do about it so it might result * in data loss. So use reserved blocks to allocate metadata if - * possible. - * - * We pass in the magic EXT4_GET_BLOCKS_DELALLOC_RESERVE if the blocks - * in question are delalloc blocks. This affects functions in many - * different parts of the allocation call path. This flag exists - * primarily because we don't want to change *many* call functions, so - * ext4_map_blocks() will set the EXT4_STATE_DELALLOC_RESERVED flag - * once the inode's allocation semaphore is taken. + * possible. In addition, do not cache any unrelated extents, as it + * only holds the folio lock but does not hold the i_rwsem or + * invalidate_lock, which could corrupt the extent status tree. */ get_blocks_flags = EXT4_GET_BLOCKS_CREATE | - EXT4_GET_BLOCKS_METADATA_NOFAIL; - if (ext4_should_dioread_nolock(inode)) + EXT4_GET_BLOCKS_METADATA_NOFAIL | + EXT4_GET_BLOCKS_IO_SUBMIT | + EXT4_EX_NOCACHE; + + dioread_nolock = ext4_should_dioread_nolock(inode); + if (dioread_nolock) get_blocks_flags |= EXT4_GET_BLOCKS_IO_CREATE_EXT; - if (map->m_flags & (1 << BH_Delay)) - get_blocks_flags |= EXT4_GET_BLOCKS_DELALLOC_RESERVE; err = ext4_map_blocks(handle, inode, map, get_blocks_flags); if (err < 0) return err; - if (map->m_flags & EXT4_MAP_UNINIT) { + if (dioread_nolock && (map->m_flags & EXT4_MAP_UNWRITTEN)) { if (!mpd->io_submit.io_end->handle && ext4_handle_valid(handle)) { mpd->io_submit.io_end->handle = handle->h_rsv_handle; handle->h_rsv_handle = NULL; } - ext4_set_io_unwritten_flag(inode, mpd->io_submit.io_end); + ext4_set_io_unwritten_flag(mpd->io_submit.io_end); } BUG_ON(map->m_len == 0); - if (map->m_flags & EXT4_MAP_NEW) { - struct block_device *bdev = inode->i_sb->s_bdev; - int i; - - for (i = 0; i < map->m_len; i++) - unmap_underlying_metadata(bdev, map->m_pblk + i); - } return 0; } /* + * This is used to submit mapped buffers in a single folio that is not fully + * mapped for various reasons, such as insufficient space or journal credits. + */ +static int mpage_submit_partial_folio(struct mpage_da_data *mpd) +{ + struct inode *inode = mpd->inode; + struct folio *folio; + loff_t pos; + int ret; + + folio = filemap_get_folio(inode->i_mapping, + mpd->start_pos >> PAGE_SHIFT); + if (IS_ERR(folio)) + return PTR_ERR(folio); + /* + * The mapped position should be within the current processing folio + * but must not be the folio start position. + */ + pos = ((loff_t)mpd->map.m_lblk) << inode->i_blkbits; + if (WARN_ON_ONCE((folio_pos(folio) == pos) || + !folio_contains(folio, pos >> PAGE_SHIFT))) + return -EINVAL; + + ret = mpage_submit_folio(mpd, folio); + if (ret) + goto out; + /* + * Update start_pos to prevent this folio from being released in + * mpage_release_unused_pages(), it will be reset to the aligned folio + * pos when this folio is written again in the next round. Additionally, + * do not update wbc->nr_to_write here, as it will be updated once the + * entire folio has finished processing. + */ + mpd->start_pos = pos; +out: + folio_unlock(folio); + folio_put(folio); + return ret; +} + +/* * mpage_map_and_submit_extent - map extent starting at mpd->lblk of length * mpd->len and submit pages underlying it for IO * * @handle - handle for journal operations * @mpd - extent to map + * @give_up_on_write - we set this to true iff there is a fatal error and there + * is no hope of writing the data. The caller should discard + * dirty pages to avoid infinite loops. * * The function maps extent starting at mpd->lblk of length mpd->len. If it is * delayed, blocks are allocated, if it is unwritten, we may need to convert @@ -2160,24 +2462,40 @@ static int mpage_map_and_submit_extent(handle_t *handle, struct ext4_map_blocks *map = &mpd->map; int err; loff_t disksize; - - mpd->io_submit.io_end->offset = - ((loff_t)map->m_lblk) << inode->i_blkbits; - while (map->m_len) { + int progress = 0; + ext4_io_end_t *io_end = mpd->io_submit.io_end; + struct ext4_io_end_vec *io_end_vec; + + io_end_vec = ext4_alloc_io_end_vec(io_end); + if (IS_ERR(io_end_vec)) + return PTR_ERR(io_end_vec); + io_end_vec->offset = EXT4_LBLK_TO_B(inode, map->m_lblk); + do { err = mpage_map_one_extent(handle, mpd); if (err < 0) { struct super_block *sb = inode->i_sb; - if (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED) + if (ext4_emergency_state(sb)) goto invalidate_dirty_pages; /* * Let the uper layers retry transient errors. * In the case of ENOSPC, if ext4_count_free_blocks() * is non-zero, a commit should free up blocks. */ - if ((err == -ENOMEM) || - (err == -ENOSPC && ext4_count_free_clusters(sb))) + if ((err == -ENOMEM) || (err == -EAGAIN) || + (err == -ENOSPC && ext4_count_free_clusters(sb))) { + /* + * We may have already allocated extents for + * some bhs inside the folio, issue the + * corresponding data to prevent stale data. + */ + if (progress) { + if (mpage_submit_partial_folio(mpd)) + goto invalidate_dirty_pages; + goto update_disksize; + } return err; + } ext4_msg(sb, KERN_CRIT, "Delayed block allocation failed for " "inode %lu at logical offset %llu with" @@ -2194,61 +2512,98 @@ static int mpage_map_and_submit_extent(handle_t *handle, *give_up_on_write = true; return err; } + progress = 1; /* * Update buffer state, submit mapped pages, and get us new * extent to map */ err = mpage_map_and_submit_buffers(mpd); if (err < 0) - return err; - } + goto update_disksize; + } while (map->m_len); - /* Update on-disk size after IO is submitted */ - disksize = ((loff_t)mpd->first_page) << PAGE_CACHE_SHIFT; - if (disksize > i_size_read(inode)) - disksize = i_size_read(inode); - if (disksize > EXT4_I(inode)->i_disksize) { +update_disksize: + /* + * Update on-disk size after IO is submitted. Races with + * truncate are avoided by checking i_size under i_data_sem. + */ + disksize = mpd->start_pos; + if (disksize > READ_ONCE(EXT4_I(inode)->i_disksize)) { int err2; - - ext4_update_i_disksize(inode, disksize); + loff_t i_size; + + down_write(&EXT4_I(inode)->i_data_sem); + i_size = i_size_read(inode); + if (disksize > i_size) + disksize = i_size; + if (disksize > EXT4_I(inode)->i_disksize) + EXT4_I(inode)->i_disksize = disksize; + up_write(&EXT4_I(inode)->i_data_sem); err2 = ext4_mark_inode_dirty(handle, inode); - if (err2) - ext4_error(inode->i_sb, - "Failed to mark inode %lu dirty", - inode->i_ino); + if (err2) { + ext4_error_err(inode->i_sb, -err2, + "Failed to mark inode %lu dirty", + inode->i_ino); + } if (!err) err = err2; } return err; } -/* - * Calculate the total number of credits to reserve for one writepages - * iteration. This is called from ext4_writepages(). We map an extent of - * upto MAX_WRITEPAGES_EXTENT_LEN blocks and then we go on and finish mapping - * the last partial page. So in total we can map MAX_WRITEPAGES_EXTENT_LEN + - * bpp - 1 blocks in bpp different extents. - */ -static int ext4_da_writepages_trans_blocks(struct inode *inode) +static int ext4_journal_folio_buffers(handle_t *handle, struct folio *folio, + size_t len) +{ + struct buffer_head *page_bufs = folio_buffers(folio); + struct inode *inode = folio->mapping->host; + int ret, err; + + ret = ext4_walk_page_buffers(handle, inode, page_bufs, 0, len, + NULL, do_journal_get_write_access); + err = ext4_walk_page_buffers(handle, inode, page_bufs, 0, len, + NULL, write_end_fn); + if (ret == 0) + ret = err; + err = ext4_jbd2_inode_add_write(handle, inode, folio_pos(folio), len); + if (ret == 0) + ret = err; + EXT4_I(inode)->i_datasync_tid = handle->h_transaction->t_tid; + + return ret; +} + +static int mpage_journal_page_buffers(handle_t *handle, + struct mpage_da_data *mpd, + struct folio *folio) { - int bpp = ext4_journal_blocks_per_page(inode); + struct inode *inode = mpd->inode; + loff_t size = i_size_read(inode); + size_t len = folio_size(folio); + + folio_clear_checked(folio); + mpd->wbc->nr_to_write -= folio_nr_pages(folio); - return ext4_meta_trans_blocks(inode, - MAX_WRITEPAGES_EXTENT_LEN + bpp - 1, bpp); + if (folio_pos(folio) + len > size && + !ext4_verity_in_progress(inode)) + len = size & (len - 1); + + return ext4_journal_folio_buffers(handle, folio, len); } /* * mpage_prepare_extent_to_map - find & lock contiguous range of dirty pages - * and underlying extent to map + * needing mapping, submit mapped pages * * @mpd - where to look for pages * * Walk dirty pages in the mapping. If they are fully mapped, submit them for - * IO immediately. When we find a page which isn't mapped we start accumulating - * extent of buffers underlying these pages that needs mapping (formed by - * either delayed or unwritten buffers). We also lock the pages containing - * these buffers. The extent found is returned in @mpd structure (starting at - * mpd->lblk with length mpd->len blocks). + * IO immediately. If we cannot map blocks, we submit just already mapped + * buffers in the page for IO and keep page dirty. When we can map blocks and + * we find a page which isn't mapped we start accumulating extent of buffers + * underlying these pages that needs mapping (formed by either delayed or + * unwritten buffers). We also lock the pages containing these buffers. The + * extent found is returned in @mpd structure (starting at mpd->lblk with + * length mpd->len blocks). * * Note that this function can attach bios to one io_end structure which are * neither logically nor physically contiguous. Although it may seem as an @@ -2258,48 +2613,63 @@ static int ext4_da_writepages_trans_blocks(struct inode *inode) static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd) { struct address_space *mapping = mpd->inode->i_mapping; - struct pagevec pvec; - unsigned int nr_pages; - pgoff_t index = mpd->first_page; - pgoff_t end = mpd->last_page; - int tag; + struct folio_batch fbatch; + unsigned int nr_folios; + pgoff_t index = mpd->start_pos >> PAGE_SHIFT; + pgoff_t end = mpd->end_pos >> PAGE_SHIFT; + xa_mark_t tag; int i, err = 0; - int blkbits = mpd->inode->i_blkbits; ext4_lblk_t lblk; struct buffer_head *head; + handle_t *handle = NULL; + int bpp = ext4_journal_blocks_per_folio(mpd->inode); - if (mpd->wbc->sync_mode == WB_SYNC_ALL || mpd->wbc->tagged_writepages) - tag = PAGECACHE_TAG_TOWRITE; - else - tag = PAGECACHE_TAG_DIRTY; + tag = wbc_to_tag(mpd->wbc); - pagevec_init(&pvec, 0); mpd->map.m_len = 0; - mpd->next_page = index; + mpd->next_pos = mpd->start_pos; + if (ext4_should_journal_data(mpd->inode)) { + handle = ext4_journal_start(mpd->inode, EXT4_HT_WRITE_PAGE, + bpp); + if (IS_ERR(handle)) + return PTR_ERR(handle); + } + folio_batch_init(&fbatch); while (index <= end) { - nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag, - min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1); - if (nr_pages == 0) - goto out; + nr_folios = filemap_get_folios_tag(mapping, &index, end, + tag, &fbatch); + if (nr_folios == 0) + break; - for (i = 0; i < nr_pages; i++) { - struct page *page = pvec.pages[i]; + for (i = 0; i < nr_folios; i++) { + struct folio *folio = fbatch.folios[i]; /* - * At this point, the page may be truncated or - * invalidated (changing page->mapping to NULL), or - * even swizzled back from swapper_space to tmpfs file - * mapping. However, page->index will not change - * because we have a reference on the page. + * Accumulated enough dirty pages? This doesn't apply + * to WB_SYNC_ALL mode. For integrity sync we have to + * keep going because someone may be concurrently + * dirtying pages, and we might have synced a lot of + * newly appeared dirty pages, but have not synced all + * of the old dirty pages. */ - if (page->index > end) + if (mpd->wbc->sync_mode == WB_SYNC_NONE && + mpd->wbc->nr_to_write <= + EXT4_LBLK_TO_PG(mpd->inode, mpd->map.m_len)) goto out; /* If we can't merge this page, we are done. */ - if (mpd->map.m_len > 0 && mpd->next_page != page->index) + if (mpd->map.m_len > 0 && + mpd->next_pos != folio_pos(folio)) goto out; - lock_page(page); + if (handle) { + err = ext4_journal_ensure_credits(handle, bpp, + 0); + if (err < 0) + goto out; + } + + folio_lock(folio); /* * If the page is no longer dirty, or its mapping no * longer corresponds to inode we are writing (which @@ -2307,77 +2677,96 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd) * page is already under writeback and we are not doing * a data integrity writeback, skip the page */ - if (!PageDirty(page) || - (PageWriteback(page) && + if (!folio_test_dirty(folio) || + (folio_test_writeback(folio) && (mpd->wbc->sync_mode == WB_SYNC_NONE)) || - unlikely(page->mapping != mapping)) { - unlock_page(page); + unlikely(folio->mapping != mapping)) { + folio_unlock(folio); continue; } - wait_on_page_writeback(page); - BUG_ON(PageWriteback(page)); + folio_wait_writeback(folio); + BUG_ON(folio_test_writeback(folio)); - if (mpd->map.m_len == 0) - mpd->first_page = page->index; - mpd->next_page = page->index + 1; - /* Add all dirty buffers to mpd */ - lblk = ((ext4_lblk_t)page->index) << - (PAGE_CACHE_SHIFT - blkbits); - head = page_buffers(page); - if (!add_page_bufs_to_extent(mpd, head, head, lblk)) - goto out; - /* So far everything mapped? Submit the page for IO. */ - if (mpd->map.m_len == 0) { - err = mpage_submit_page(mpd, page); - if (err < 0) - goto out; + /* + * Should never happen but for buggy code in + * other subsystems that call + * set_page_dirty() without properly warning + * the file system first. See [1] for more + * information. + * + * [1] https://lore.kernel.org/linux-mm/20180103100430.GE4911@quack2.suse.cz + */ + if (!folio_buffers(folio)) { + ext4_warning_inode(mpd->inode, "page %lu does not have buffers attached", folio->index); + folio_clear_dirty(folio); + folio_unlock(folio); + continue; } + if (mpd->map.m_len == 0) + mpd->start_pos = folio_pos(folio); + mpd->next_pos = folio_next_pos(folio); /* - * Accumulated enough dirty pages? This doesn't apply - * to WB_SYNC_ALL mode. For integrity sync we have to - * keep going because someone may be concurrently - * dirtying pages, and we might have synced a lot of - * newly appeared dirty pages, but have not synced all - * of the old dirty pages. + * Writeout when we cannot modify metadata is simple. + * Just submit the page. For data=journal mode we + * first handle writeout of the page for checkpoint and + * only after that handle delayed page dirtying. This + * makes sure current data is checkpointed to the final + * location before possibly journalling it again which + * is desirable when the page is frequently dirtied + * through a pin. */ - if (mpd->wbc->sync_mode == WB_SYNC_NONE && - mpd->next_page - mpd->first_page >= - mpd->wbc->nr_to_write) - goto out; + if (!mpd->can_map) { + err = mpage_submit_folio(mpd, folio); + if (err < 0) + goto out; + /* Pending dirtying of journalled data? */ + if (folio_test_checked(folio)) { + err = mpage_journal_page_buffers(handle, + mpd, folio); + if (err < 0) + goto out; + mpd->journalled_more_data = 1; + } + mpage_folio_done(mpd, folio); + } else { + /* Add all dirty buffers to mpd */ + lblk = EXT4_PG_TO_LBLK(mpd->inode, folio->index); + head = folio_buffers(folio); + err = mpage_process_page_bufs(mpd, head, head, + lblk); + if (err <= 0) + goto out; + err = 0; + } } - pagevec_release(&pvec); + folio_batch_release(&fbatch); cond_resched(); } + mpd->scanned_until_end = 1; + if (handle) + ext4_journal_stop(handle); return 0; out: - pagevec_release(&pvec); + folio_batch_release(&fbatch); + if (handle) + ext4_journal_stop(handle); return err; } -static int __writepage(struct page *page, struct writeback_control *wbc, - void *data) -{ - struct address_space *mapping = data; - int ret = ext4_writepage(page, wbc); - mapping_set_error(mapping, ret); - return ret; -} - -static int ext4_writepages(struct address_space *mapping, - struct writeback_control *wbc) +static int ext4_do_writepages(struct mpage_da_data *mpd) { + struct writeback_control *wbc = mpd->wbc; pgoff_t writeback_index = 0; long nr_to_write = wbc->nr_to_write; int range_whole = 0; int cycled = 1; handle_t *handle = NULL; - struct mpage_da_data mpd; - struct inode *inode = mapping->host; + struct inode *inode = mpd->inode; + struct address_space *mapping = inode->i_mapping; int needed_blocks, rsv_blocks = 0, ret = 0; struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb); - bool done; struct blk_plug plug; bool give_up_on_write = false; @@ -2389,38 +2778,21 @@ static int ext4_writepages(struct address_space *mapping, * because that could violate lock ordering on umount */ if (!mapping->nrpages || !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) - return 0; - - if (ext4_should_journal_data(inode)) { - struct blk_plug plug; - int ret; - - blk_start_plug(&plug); - ret = write_cache_pages(mapping, wbc, __writepage, mapping); - blk_finish_plug(&plug); - return ret; - } + goto out_writepages; /* * If the filesystem has aborted, it is read-only, so return * right away instead of dumping stack traces later on that * will obscure the real source of the problem. We test - * EXT4_MF_FS_ABORTED instead of sb->s_flag's MS_RDONLY because + * fs shutdown state instead of sb->s_flag's SB_RDONLY because * the latter could be true if the filesystem is mounted * read-only, and in that case, ext4_writepages should * *never* be called, so if that ever happens, we would want * the stack trace. */ - if (unlikely(sbi->s_mount_flags & EXT4_MF_FS_ABORTED)) - return -EROFS; - - if (ext4_should_dioread_nolock(inode)) { - /* - * We may need to convert upto one extent per block in - * the page and we may dirty the inode. - */ - rsv_blocks = 1 + (PAGE_CACHE_SIZE >> inode->i_blkbits); - } + ret = ext4_emergency_state(mapping->host->i_sb); + if (unlikely(ret)) + goto out_writepages; /* * If we have inline data and arrive here, it means that @@ -2440,6 +2812,35 @@ static int ext4_writepages(struct address_space *mapping, ext4_journal_stop(handle); } + /* + * data=journal mode does not do delalloc so we just need to writeout / + * journal already mapped buffers. On the other hand we need to commit + * transaction to make data stable. We expect all the data to be + * already in the journal (the only exception are DMA pinned pages + * dirtied behind our back) so we commit transaction here and run the + * writeback loop to checkpoint them. The checkpointing is not actually + * necessary to make data persistent *but* quite a few places (extent + * shifting operations, fsverity, ...) depend on being able to drop + * pagecache pages after calling filemap_write_and_wait() and for that + * checkpointing needs to happen. + */ + if (ext4_should_journal_data(inode)) { + mpd->can_map = 0; + if (wbc->sync_mode == WB_SYNC_ALL) + ext4_fc_commit(sbi->s_journal, + EXT4_I(inode)->i_datasync_tid); + } + mpd->journalled_more_data = 0; + + if (ext4_should_dioread_nolock(inode)) { + int bpf = ext4_journal_blocks_per_folio(inode); + /* + * We may need to convert up to one extent per block in + * the folio and we may dirty the inode. + */ + rsv_blocks = 1 + ext4_ext_index_trans_blocks(inode, bpf); + } + if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) range_whole = 1; @@ -2447,29 +2848,52 @@ static int ext4_writepages(struct address_space *mapping, writeback_index = mapping->writeback_index; if (writeback_index) cycled = 0; - mpd.first_page = writeback_index; - mpd.last_page = -1; + mpd->start_pos = writeback_index << PAGE_SHIFT; + mpd->end_pos = LLONG_MAX; } else { - mpd.first_page = wbc->range_start >> PAGE_CACHE_SHIFT; - mpd.last_page = wbc->range_end >> PAGE_CACHE_SHIFT; + mpd->start_pos = wbc->range_start; + mpd->end_pos = wbc->range_end; } - mpd.inode = inode; - mpd.wbc = wbc; - ext4_io_submit_init(&mpd.io_submit, wbc); + ext4_io_submit_init(&mpd->io_submit, wbc); retry: if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) - tag_pages_for_writeback(mapping, mpd.first_page, mpd.last_page); - done = false; + tag_pages_for_writeback(mapping, mpd->start_pos >> PAGE_SHIFT, + mpd->end_pos >> PAGE_SHIFT); blk_start_plug(&plug); - while (!done && mpd.first_page <= mpd.last_page) { + + /* + * First writeback pages that don't need mapping - we can avoid + * starting a transaction unnecessarily and also avoid being blocked + * in the block layer on device congestion while having transaction + * started. + */ + mpd->do_map = 0; + mpd->scanned_until_end = 0; + mpd->io_submit.io_end = ext4_init_io_end(inode, GFP_KERNEL); + if (!mpd->io_submit.io_end) { + ret = -ENOMEM; + goto unplug; + } + ret = mpage_prepare_extent_to_map(mpd); + /* Unlock pages we didn't use */ + mpage_release_unused_pages(mpd, false); + /* Submit prepared bio */ + ext4_io_submit(&mpd->io_submit); + ext4_put_io_end_defer(mpd->io_submit.io_end); + mpd->io_submit.io_end = NULL; + if (ret < 0) + goto unplug; + + while (!mpd->scanned_until_end && wbc->nr_to_write > 0) { /* For each extent of pages we use new io_end */ - mpd.io_submit.io_end = ext4_init_io_end(inode, GFP_KERNEL); - if (!mpd.io_submit.io_end) { + mpd->io_submit.io_end = ext4_init_io_end(inode, GFP_KERNEL); + if (!mpd->io_submit.io_end) { ret = -ENOMEM; break; } + WARN_ON_ONCE(!mpd->can_map); /* * We have two constraints: We find one extent to map and we * must always write out whole page (makes a difference when @@ -2478,8 +2902,14 @@ retry: * not supported by delalloc. */ BUG_ON(ext4_should_journal_data(inode)); - needed_blocks = ext4_da_writepages_trans_blocks(inode); - + /* + * Calculate the number of credits needed to reserve for one + * extent of up to MAX_WRITEPAGES_EXTENT_LEN blocks. It will + * attempt to extend the transaction or start a new iteration + * if the reserved credits are insufficient. + */ + needed_blocks = ext4_chunk_trans_blocks(inode, + MAX_WRITEPAGES_EXTENT_LEN); /* start a new transaction */ handle = ext4_journal_start_with_reserve(inode, EXT4_HT_WRITE_PAGE, needed_blocks, rsv_blocks); @@ -2489,33 +2919,53 @@ retry: "%ld pages, ino %lu; err %d", __func__, wbc->nr_to_write, inode->i_ino, ret); /* Release allocated io_end */ - ext4_put_io_end(mpd.io_submit.io_end); + ext4_put_io_end(mpd->io_submit.io_end); + mpd->io_submit.io_end = NULL; break; } + mpd->do_map = 1; - trace_ext4_da_write_pages(inode, mpd.first_page, mpd.wbc); - ret = mpage_prepare_extent_to_map(&mpd); - if (!ret) { - if (mpd.map.m_len) - ret = mpage_map_and_submit_extent(handle, &mpd, + trace_ext4_da_write_folios_start(inode, mpd->start_pos, + mpd->next_pos, wbc); + ret = mpage_prepare_extent_to_map(mpd); + if (!ret && mpd->map.m_len) + ret = mpage_map_and_submit_extent(handle, mpd, &give_up_on_write); - else { - /* - * We scanned the whole range (or exhausted - * nr_to_write), submitted what was mapped and - * didn't find anything needing mapping. We are - * done. - */ - done = true; - } + /* + * Caution: If the handle is synchronous, + * ext4_journal_stop() can wait for transaction commit + * to finish which may depend on writeback of pages to + * complete or on page lock to be released. In that + * case, we have to wait until after we have + * submitted all the IO, released page locks we hold, + * and dropped io_end reference (for extent conversion + * to be able to complete) before stopping the handle. + */ + if (!ext4_handle_valid(handle) || handle->h_sync == 0) { + ext4_journal_stop(handle); + handle = NULL; + mpd->do_map = 0; } - ext4_journal_stop(handle); - /* Submit prepared bio */ - ext4_io_submit(&mpd.io_submit); /* Unlock pages we didn't use */ - mpage_release_unused_pages(&mpd, give_up_on_write); - /* Drop our io_end reference we got from init */ - ext4_put_io_end(mpd.io_submit.io_end); + mpage_release_unused_pages(mpd, give_up_on_write); + /* Submit prepared bio */ + ext4_io_submit(&mpd->io_submit); + + /* + * Drop our io_end reference we got from init. We have + * to be careful and use deferred io_end finishing if + * we are still holding the transaction as we can + * release the last reference to io_end which may end + * up doing unwritten extent conversion. + */ + if (handle) { + ext4_put_io_end_defer(mpd->io_submit.io_end); + ext4_journal_stop(handle); + } else + ext4_put_io_end(mpd->io_submit.io_end); + mpd->io_submit.io_end = NULL; + trace_ext4_da_write_folios_end(inode, mpd->start_pos, + mpd->next_pos, wbc, ret); if (ret == -ENOSPC && sbi->s_journal) { /* @@ -2527,15 +2977,18 @@ retry: ret = 0; continue; } + if (ret == -EAGAIN) + ret = 0; /* Fatal error - ENOMEM, EIO... */ if (ret) break; } +unplug: blk_finish_plug(&plug); - if (!ret && !cycled) { + if (!ret && !cycled && wbc->nr_to_write > 0) { cycled = 1; - mpd.last_page = writeback_index - 1; - mpd.first_page = 0; + mpd->end_pos = (writeback_index << PAGE_SHIFT) - 1; + mpd->start_pos = 0; goto retry; } @@ -2545,7 +2998,7 @@ retry: * Set the writeback_index so that range_cyclic * mode will write it back later */ - mapping->writeback_index = mpd.first_page; + mapping->writeback_index = mpd->start_pos >> PAGE_SHIFT; out_writepages: trace_ext4_writepages_result(inode, wbc, ret, @@ -2553,6 +3006,75 @@ out_writepages: return ret; } +static int ext4_writepages(struct address_space *mapping, + struct writeback_control *wbc) +{ + struct super_block *sb = mapping->host->i_sb; + struct mpage_da_data mpd = { + .inode = mapping->host, + .wbc = wbc, + .can_map = 1, + }; + int ret; + int alloc_ctx; + + ret = ext4_emergency_state(sb); + if (unlikely(ret)) + return ret; + + alloc_ctx = ext4_writepages_down_read(sb); + ret = ext4_do_writepages(&mpd); + /* + * For data=journal writeback we could have come across pages marked + * for delayed dirtying (PageChecked) which were just added to the + * running transaction. Try once more to get them to stable storage. + */ + if (!ret && mpd.journalled_more_data) + ret = ext4_do_writepages(&mpd); + ext4_writepages_up_read(sb, alloc_ctx); + + return ret; +} + +int ext4_normal_submit_inode_data_buffers(struct jbd2_inode *jinode) +{ + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL, + .nr_to_write = LONG_MAX, + .range_start = jinode->i_dirty_start, + .range_end = jinode->i_dirty_end, + }; + struct mpage_da_data mpd = { + .inode = jinode->i_vfs_inode, + .wbc = &wbc, + .can_map = 0, + }; + return ext4_do_writepages(&mpd); +} + +static int ext4_dax_writepages(struct address_space *mapping, + struct writeback_control *wbc) +{ + int ret; + long nr_to_write = wbc->nr_to_write; + struct inode *inode = mapping->host; + int alloc_ctx; + + ret = ext4_emergency_state(inode->i_sb); + if (unlikely(ret)) + return ret; + + alloc_ctx = ext4_writepages_down_read(inode->i_sb); + trace_ext4_writepages(inode, wbc); + + ret = dax_writeback_mapping_range(mapping, + EXT4_SB(inode->i_sb)->s_daxdev, wbc); + trace_ext4_writepages_result(inode, wbc, ret, + nr_to_write - wbc->nr_to_write); + ext4_writepages_up_read(inode->i_sb, alloc_ctx); + return ret; +} + static int ext4_nonda_switch(struct super_block *sb) { s64 free_clusters, dirty_clusters; @@ -2587,94 +3109,67 @@ static int ext4_nonda_switch(struct super_block *sb) return 0; } -static int ext4_da_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, - struct page **pagep, void **fsdata) +static int ext4_da_write_begin(const struct kiocb *iocb, + struct address_space *mapping, + loff_t pos, unsigned len, + struct folio **foliop, void **fsdata) { int ret, retries = 0; - struct page *page; + struct folio *folio; pgoff_t index; struct inode *inode = mapping->host; - handle_t *handle; - index = pos >> PAGE_CACHE_SHIFT; + ret = ext4_emergency_state(inode->i_sb); + if (unlikely(ret)) + return ret; + + index = pos >> PAGE_SHIFT; - if (ext4_nonda_switch(inode->i_sb)) { + if (ext4_nonda_switch(inode->i_sb) || ext4_verity_in_progress(inode)) { *fsdata = (void *)FALL_BACK_TO_NONDELALLOC; - return ext4_write_begin(file, mapping, pos, - len, flags, pagep, fsdata); + return ext4_write_begin(iocb, mapping, pos, + len, foliop, fsdata); } *fsdata = (void *)0; - trace_ext4_da_write_begin(inode, pos, len, flags); + trace_ext4_da_write_begin(inode, pos, len); if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { - ret = ext4_da_write_inline_data_begin(mapping, inode, - pos, len, flags, - pagep, fsdata); + ret = ext4_generic_write_inline_data(mapping, inode, pos, len, + foliop, fsdata, true); if (ret < 0) return ret; if (ret == 1) return 0; } - /* - * grab_cache_page_write_begin() can take a long time if the - * system is thrashing due to memory pressure, or if the page - * is being written back. So grab it first before we start - * the transaction handle. This also allows us to allocate - * the page (if needed) without using GFP_NOFS. - */ -retry_grab: - page = grab_cache_page_write_begin(mapping, index, flags); - if (!page) - return -ENOMEM; - unlock_page(page); - - /* - * With delayed allocation, we don't log the i_disksize update - * if there is delayed block allocation. But we still need - * to journalling the i_disksize update if writes to the end - * of file which has an already mapped buffer. - */ -retry_journal: - handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, 1); - if (IS_ERR(handle)) { - page_cache_release(page); - return PTR_ERR(handle); - } +retry: + folio = write_begin_get_folio(iocb, mapping, index, len); + if (IS_ERR(folio)) + return PTR_ERR(folio); - lock_page(page); - if (page->mapping != mapping) { - /* The page got truncated from under us */ - unlock_page(page); - page_cache_release(page); - ext4_journal_stop(handle); - goto retry_grab; - } - /* In case writeback began while the page was unlocked */ - wait_on_page_writeback(page); + if (len > folio_next_pos(folio) - pos) + len = folio_next_pos(folio) - pos; - ret = __block_write_begin(page, pos, len, ext4_da_get_block_prep); + ret = ext4_block_write_begin(NULL, folio, pos, len, + ext4_da_get_block_prep); if (ret < 0) { - unlock_page(page); - ext4_journal_stop(handle); + folio_unlock(folio); + folio_put(folio); /* - * block_write_begin may have instantiated a few blocks + * ext4_block_write_begin may have instantiated a few blocks * outside i_size. Trim these off again. Don't need - * i_size_read because we hold i_mutex. + * i_size_read because we hold inode lock. */ if (pos + len > inode->i_size) ext4_truncate_failed_write(inode); if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) - goto retry_journal; - - page_cache_release(page); + goto retry; return ret; } - *pagep = page; + *foliop = folio; return ret; } @@ -2682,15 +3177,15 @@ retry_journal: * Check if we should update i_disksize * when write to the end of file but not require block allocation */ -static int ext4_da_should_update_i_disksize(struct page *page, +static int ext4_da_should_update_i_disksize(struct folio *folio, unsigned long offset) { struct buffer_head *bh; - struct inode *inode = page->mapping->host; + struct inode *inode = folio->mapping->host; unsigned int idx; int i; - bh = page_buffers(page); + bh = folio_buffers(folio); idx = offset >> inode->i_blkbits; for (i = 0; i < idx; i++) @@ -2701,82 +3196,100 @@ static int ext4_da_should_update_i_disksize(struct page *page, return 1; } -static int ext4_da_write_end(struct file *file, - struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) +static int ext4_da_do_write_end(struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct folio *folio) { struct inode *inode = mapping->host; - int ret = 0, ret2; - handle_t *handle = ext4_journal_current_handle(); - loff_t new_i_size; - unsigned long start, end; - int write_mode = (int)(unsigned long)fsdata; - - if (write_mode == FALL_BACK_TO_NONDELALLOC) - return ext4_write_end(file, mapping, pos, - len, copied, page, fsdata); - - trace_ext4_da_write_end(inode, pos, len, copied); - start = pos & (PAGE_CACHE_SIZE - 1); - end = start + copied - 1; + loff_t old_size = inode->i_size; + bool disksize_changed = false; + loff_t new_i_size, zero_len = 0; + handle_t *handle; + if (unlikely(!folio_buffers(folio))) { + folio_unlock(folio); + folio_put(folio); + return -EIO; + } /* - * generic_write_end() will run mark_inode_dirty() if i_size - * changes. So let's piggyback the i_disksize mark_inode_dirty - * into that. + * block_write_end() will mark the inode as dirty with I_DIRTY_PAGES + * flag, which all that's needed to trigger page writeback. */ + copied = block_write_end(pos, len, copied, folio); new_i_size = pos + copied; - if (copied && new_i_size > EXT4_I(inode)->i_disksize) { - if (ext4_has_inline_data(inode) || - ext4_da_should_update_i_disksize(page, end)) { - down_write(&EXT4_I(inode)->i_data_sem); - if (new_i_size > EXT4_I(inode)->i_disksize) - EXT4_I(inode)->i_disksize = new_i_size; - up_write(&EXT4_I(inode)->i_data_sem); - /* We need to mark inode dirty even if - * new_i_size is less that inode->i_size - * bu greater than i_disksize.(hint delalloc) - */ - ext4_mark_inode_dirty(handle, inode); + + /* + * It's important to update i_size while still holding folio lock, + * because folio writeout could otherwise come in and zero beyond + * i_size. + * + * Since we are holding inode lock, we are sure i_disksize <= + * i_size. We also know that if i_disksize < i_size, there are + * delalloc writes pending in the range up to i_size. If the end of + * the current write is <= i_size, there's no need to touch + * i_disksize since writeback will push i_disksize up to i_size + * eventually. If the end of the current write is > i_size and + * inside an allocated block which ext4_da_should_update_i_disksize() + * checked, we need to update i_disksize here as certain + * ext4_writepages() paths not allocating blocks and update i_disksize. + */ + if (new_i_size > inode->i_size) { + unsigned long end; + + i_size_write(inode, new_i_size); + end = offset_in_folio(folio, new_i_size - 1); + if (copied && ext4_da_should_update_i_disksize(folio, end)) { + ext4_update_i_disksize(inode, new_i_size); + disksize_changed = true; } } - if (write_mode != CONVERT_INLINE_DATA && - ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA) && - ext4_has_inline_data(inode)) - ret2 = ext4_da_write_inline_data_end(inode, pos, len, copied, - page); - else - ret2 = generic_write_end(file, mapping, pos, len, copied, - page, fsdata); + folio_unlock(folio); + folio_put(folio); - copied = ret2; - if (ret2 < 0) - ret = ret2; - ret2 = ext4_journal_stop(handle); - if (!ret) - ret = ret2; + if (pos > old_size) { + pagecache_isize_extended(inode, old_size, pos); + zero_len = pos - old_size; + } - return ret ? ret : copied; + if (!disksize_changed && !zero_len) + return copied; + + handle = ext4_journal_start(inode, EXT4_HT_INODE, 2); + if (IS_ERR(handle)) + return PTR_ERR(handle); + if (zero_len) + ext4_zero_partial_blocks(handle, inode, old_size, zero_len); + ext4_mark_inode_dirty(handle, inode); + ext4_journal_stop(handle); + + return copied; } -static void ext4_da_invalidatepage(struct page *page, unsigned int offset, - unsigned int length) +static int ext4_da_write_end(const struct kiocb *iocb, + struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct folio *folio, void *fsdata) { - /* - * Drop reserved blocks - */ - BUG_ON(!PageLocked(page)); - if (!page_has_buffers(page)) - goto out; + struct inode *inode = mapping->host; + int write_mode = (int)(unsigned long)fsdata; + + if (write_mode == FALL_BACK_TO_NONDELALLOC) + return ext4_write_end(iocb, mapping, pos, + len, copied, folio, fsdata); - ext4_da_page_release_reservation(page, offset, length); + trace_ext4_da_write_end(inode, pos, len, copied); -out: - ext4_invalidatepage(page, offset, length); + if (write_mode != CONVERT_INLINE_DATA && + ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA) && + ext4_has_inline_data(inode)) + return ext4_write_inline_data_end(inode, pos, len, copied, + folio); - return; + if (unlikely(copied < len) && !folio_test_uptodate(folio)) + copied = 0; + + return ext4_da_do_write_end(mapping, pos, len, copied, folio); } /* @@ -2786,8 +3299,7 @@ int ext4_alloc_da_blocks(struct inode *inode) { trace_ext4_alloc_da_blocks(inode); - if (!EXT4_I(inode)->i_reserved_data_blocks && - !EXT4_I(inode)->i_reserved_meta_blocks) + if (!EXT4_I(inode)->i_reserved_data_blocks) return 0; /* @@ -2841,458 +3353,686 @@ int ext4_alloc_da_blocks(struct inode *inode) static sector_t ext4_bmap(struct address_space *mapping, sector_t block) { struct inode *inode = mapping->host; - journal_t *journal; - int err; + sector_t ret = 0; + inode_lock_shared(inode); /* * We can get here for an inline file via the FIBMAP ioctl */ if (ext4_has_inline_data(inode)) - return 0; + goto out; if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) && - test_opt(inode->i_sb, DELALLOC)) { + (test_opt(inode->i_sb, DELALLOC) || + ext4_should_journal_data(inode))) { /* - * With delalloc we want to sync the file - * so that we can make sure we allocate - * blocks for file + * With delalloc or journalled data we want to sync the file so + * that we can make sure we allocate blocks for file and data + * is in place for the user to see it */ filemap_write_and_wait(mapping); } - if (EXT4_JOURNAL(inode) && - ext4_test_inode_state(inode, EXT4_STATE_JDATA)) { - /* - * This is a REALLY heavyweight approach, but the use of - * bmap on dirty files is expected to be extremely rare: - * only if we run lilo or swapon on a freshly made file - * do we expect this to happen. - * - * (bmap requires CAP_SYS_RAWIO so this does not - * represent an unprivileged user DOS attack --- we'd be - * in trouble if mortal users could trigger this path at - * will.) - * - * NB. EXT4_STATE_JDATA is not set on files other than - * regular files. If somebody wants to bmap a directory - * or symlink and gets confused because the buffer - * hasn't yet been flushed to disk, they deserve - * everything they get. - */ - - ext4_clear_inode_state(inode, EXT4_STATE_JDATA); - journal = EXT4_JOURNAL(inode); - jbd2_journal_lock_updates(journal); - err = jbd2_journal_flush(journal); - jbd2_journal_unlock_updates(journal); - - if (err) - return 0; - } + ret = iomap_bmap(mapping, block, &ext4_iomap_ops); - return generic_block_bmap(mapping, block, ext4_get_block); +out: + inode_unlock_shared(inode); + return ret; } -static int ext4_readpage(struct file *file, struct page *page) +static int ext4_read_folio(struct file *file, struct folio *folio) { int ret = -EAGAIN; - struct inode *inode = page->mapping->host; + struct inode *inode = folio->mapping->host; - trace_ext4_readpage(page); + trace_ext4_read_folio(inode, folio); if (ext4_has_inline_data(inode)) - ret = ext4_readpage_inline(inode, page); + ret = ext4_readpage_inline(inode, folio); if (ret == -EAGAIN) - return mpage_readpage(page, ext4_get_block); + return ext4_mpage_readpages(inode, NULL, folio); return ret; } -static int -ext4_readpages(struct file *file, struct address_space *mapping, - struct list_head *pages, unsigned nr_pages) +static void ext4_readahead(struct readahead_control *rac) { - struct inode *inode = mapping->host; + struct inode *inode = rac->mapping->host; - /* If the file has inline data, no need to do readpages. */ + /* If the file has inline data, no need to do readahead. */ if (ext4_has_inline_data(inode)) - return 0; + return; - return mpage_readpages(mapping, pages, nr_pages, ext4_get_block); + ext4_mpage_readpages(inode, rac, NULL); } -static void ext4_invalidatepage(struct page *page, unsigned int offset, - unsigned int length) +static void ext4_invalidate_folio(struct folio *folio, size_t offset, + size_t length) { - trace_ext4_invalidatepage(page, offset, length); + trace_ext4_invalidate_folio(folio, offset, length); /* No journalling happens on data buffers when this function is used */ - WARN_ON(page_has_buffers(page) && buffer_jbd(page_buffers(page))); + WARN_ON(folio_buffers(folio) && buffer_jbd(folio_buffers(folio))); - block_invalidatepage(page, offset, length); + block_invalidate_folio(folio, offset, length); } -static int __ext4_journalled_invalidatepage(struct page *page, - unsigned int offset, - unsigned int length) +static int __ext4_journalled_invalidate_folio(struct folio *folio, + size_t offset, size_t length) { - journal_t *journal = EXT4_JOURNAL(page->mapping->host); + journal_t *journal = EXT4_JOURNAL(folio->mapping->host); - trace_ext4_journalled_invalidatepage(page, offset, length); + trace_ext4_journalled_invalidate_folio(folio, offset, length); /* * If it's a full truncate we just forget about the pending dirtying */ - if (offset == 0 && length == PAGE_CACHE_SIZE) - ClearPageChecked(page); + if (offset == 0 && length == folio_size(folio)) + folio_clear_checked(folio); - return jbd2_journal_invalidatepage(journal, page, offset, length); + return jbd2_journal_invalidate_folio(journal, folio, offset, length); } /* Wrapper for aops... */ -static void ext4_journalled_invalidatepage(struct page *page, - unsigned int offset, - unsigned int length) +static void ext4_journalled_invalidate_folio(struct folio *folio, + size_t offset, + size_t length) { - WARN_ON(__ext4_journalled_invalidatepage(page, offset, length) < 0); + WARN_ON(__ext4_journalled_invalidate_folio(folio, offset, length) < 0); } -static int ext4_releasepage(struct page *page, gfp_t wait) +static bool ext4_release_folio(struct folio *folio, gfp_t wait) { - journal_t *journal = EXT4_JOURNAL(page->mapping->host); + struct inode *inode = folio->mapping->host; + journal_t *journal = EXT4_JOURNAL(inode); - trace_ext4_releasepage(page); + trace_ext4_release_folio(inode, folio); /* Page has dirty journalled data -> cannot release */ - if (PageChecked(page)) - return 0; + if (folio_test_checked(folio)) + return false; if (journal) - return jbd2_journal_try_to_free_buffers(journal, page, wait); + return jbd2_journal_try_to_free_buffers(journal, folio); else - return try_to_free_buffers(page); + return try_to_free_buffers(folio); } -/* - * ext4_get_block used when preparing for a DIO write or buffer write. - * We allocate an uinitialized extent if blocks haven't been allocated. - * The extent will be converted to initialized after the IO is complete. - */ -int ext4_get_block_write(struct inode *inode, sector_t iblock, - struct buffer_head *bh_result, int create) +static bool ext4_inode_datasync_dirty(struct inode *inode) { - ext4_debug("ext4_get_block_write: inode %lu, create flag %d\n", - inode->i_ino, create); - return _ext4_get_block(inode, iblock, bh_result, - EXT4_GET_BLOCKS_IO_CREATE_EXT); + journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; + + if (journal) { + if (jbd2_transaction_committed(journal, + EXT4_I(inode)->i_datasync_tid)) + return false; + if (test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT)) + return !list_empty(&EXT4_I(inode)->i_fc_list); + return true; + } + + /* Any metadata buffers to write? */ + if (!list_empty(&inode->i_mapping->i_private_list)) + return true; + return inode_state_read_once(inode) & I_DIRTY_DATASYNC; } -static int ext4_get_block_write_nolock(struct inode *inode, sector_t iblock, - struct buffer_head *bh_result, int create) +static void ext4_set_iomap(struct inode *inode, struct iomap *iomap, + struct ext4_map_blocks *map, loff_t offset, + loff_t length, unsigned int flags) { - ext4_debug("ext4_get_block_write_nolock: inode %lu, create flag %d\n", - inode->i_ino, create); - return _ext4_get_block(inode, iblock, bh_result, - EXT4_GET_BLOCKS_NO_LOCK); + u8 blkbits = inode->i_blkbits; + + /* + * Writes that span EOF might trigger an I/O size update on completion, + * so consider them to be dirty for the purpose of O_DSYNC, even if + * there is no other metadata changes being made or are pending. + */ + iomap->flags = 0; + if (ext4_inode_datasync_dirty(inode) || + offset + length > i_size_read(inode)) + iomap->flags |= IOMAP_F_DIRTY; + + if (map->m_flags & EXT4_MAP_NEW) + iomap->flags |= IOMAP_F_NEW; + + /* HW-offload atomics are always used */ + if (flags & IOMAP_ATOMIC) + iomap->flags |= IOMAP_F_ATOMIC_BIO; + + if (flags & IOMAP_DAX) + iomap->dax_dev = EXT4_SB(inode->i_sb)->s_daxdev; + else + iomap->bdev = inode->i_sb->s_bdev; + iomap->offset = EXT4_LBLK_TO_B(inode, map->m_lblk); + iomap->length = EXT4_LBLK_TO_B(inode, map->m_len); + + if ((map->m_flags & EXT4_MAP_MAPPED) && + !ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) + iomap->flags |= IOMAP_F_MERGED; + + /* + * Flags passed to ext4_map_blocks() for direct I/O writes can result + * in m_flags having both EXT4_MAP_MAPPED and EXT4_MAP_UNWRITTEN bits + * set. In order for any allocated unwritten extents to be converted + * into written extents correctly within the ->end_io() handler, we + * need to ensure that the iomap->type is set appropriately. Hence, the + * reason why we need to check whether the EXT4_MAP_UNWRITTEN bit has + * been set first. + */ + if (map->m_flags & EXT4_MAP_UNWRITTEN) { + iomap->type = IOMAP_UNWRITTEN; + iomap->addr = (u64) map->m_pblk << blkbits; + if (flags & IOMAP_DAX) + iomap->addr += EXT4_SB(inode->i_sb)->s_dax_part_off; + } else if (map->m_flags & EXT4_MAP_MAPPED) { + iomap->type = IOMAP_MAPPED; + iomap->addr = (u64) map->m_pblk << blkbits; + if (flags & IOMAP_DAX) + iomap->addr += EXT4_SB(inode->i_sb)->s_dax_part_off; + } else if (map->m_flags & EXT4_MAP_DELAYED) { + iomap->type = IOMAP_DELALLOC; + iomap->addr = IOMAP_NULL_ADDR; + } else { + iomap->type = IOMAP_HOLE; + iomap->addr = IOMAP_NULL_ADDR; + } } -static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset, - ssize_t size, void *private, int ret, - bool is_async) +static int ext4_map_blocks_atomic_write_slow(handle_t *handle, + struct inode *inode, struct ext4_map_blocks *map) { - struct inode *inode = file_inode(iocb->ki_filp); - ext4_io_end_t *io_end = iocb->private; + ext4_lblk_t m_lblk = map->m_lblk; + unsigned int m_len = map->m_len; + unsigned int mapped_len = 0, m_flags = 0; + ext4_fsblk_t next_pblk = 0; + bool check_next_pblk = false; + int ret = 0; - /* if not async direct IO just return */ - if (!io_end) { - inode_dio_done(inode); - if (is_async) - aio_complete(iocb, ret, 0); - return; - } + WARN_ON_ONCE(!ext4_has_feature_bigalloc(inode->i_sb)); + + /* + * This is a slow path in case of mixed mapping. We use + * EXT4_GET_BLOCKS_CREATE_ZERO flag here to make sure we get a single + * contiguous mapped mapping. This will ensure any unwritten or hole + * regions within the requested range is zeroed out and we return + * a single contiguous mapped extent. + */ + m_flags = EXT4_GET_BLOCKS_CREATE_ZERO; - ext_debug("ext4_end_io_dio(): io_end 0x%p " - "for inode %lu, iocb 0x%p, offset %llu, size %zd\n", - iocb->private, io_end->inode->i_ino, iocb, offset, - size); + do { + ret = ext4_map_blocks(handle, inode, map, m_flags); + if (ret < 0 && ret != -ENOSPC) + goto out_err; + /* + * This should never happen, but let's return an error code to + * avoid an infinite loop in here. + */ + if (ret == 0) { + ret = -EFSCORRUPTED; + ext4_warning_inode(inode, + "ext4_map_blocks() couldn't allocate blocks m_flags: 0x%x, ret:%d", + m_flags, ret); + goto out_err; + } + /* + * With bigalloc we should never get ENOSPC nor discontiguous + * physical extents. + */ + if ((check_next_pblk && next_pblk != map->m_pblk) || + ret == -ENOSPC) { + ext4_warning_inode(inode, + "Non-contiguous allocation detected: expected %llu, got %llu, " + "or ext4_map_blocks() returned out of space ret: %d", + next_pblk, map->m_pblk, ret); + ret = -EFSCORRUPTED; + goto out_err; + } + next_pblk = map->m_pblk + map->m_len; + check_next_pblk = true; + + mapped_len += map->m_len; + map->m_lblk += map->m_len; + map->m_len = m_len - mapped_len; + } while (mapped_len < m_len); - iocb->private = NULL; - io_end->offset = offset; - io_end->size = size; - if (is_async) { - io_end->iocb = iocb; - io_end->result = ret; + /* + * We might have done some work in above loop, so we need to query the + * start of the physical extent, based on the origin m_lblk and m_len. + * Let's also ensure we were able to allocate the required range for + * mixed mapping case. + */ + map->m_lblk = m_lblk; + map->m_len = m_len; + map->m_flags = 0; + + ret = ext4_map_blocks(handle, inode, map, + EXT4_GET_BLOCKS_QUERY_LAST_IN_LEAF); + if (ret != m_len) { + ext4_warning_inode(inode, + "allocation failed for atomic write request m_lblk:%u, m_len:%u, ret:%d\n", + m_lblk, m_len, ret); + ret = -EINVAL; } - ext4_put_io_end_defer(io_end); + return ret; + +out_err: + /* reset map before returning an error */ + map->m_lblk = m_lblk; + map->m_len = m_len; + map->m_flags = 0; + return ret; } /* - * For ext4 extent files, ext4 will do direct-io write to holes, - * preallocated extents, and those write extend the file, no need to - * fall back to buffered IO. - * - * For holes, we fallocate those blocks, mark them as uninitialized - * If those blocks were preallocated, we mark sure they are split, but - * still keep the range to write as uninitialized. - * - * The unwritten extents will be converted to written when DIO is completed. - * For async direct IO, since the IO may still pending when return, we - * set up an end_io call back function, which will do the conversion - * when async direct IO completed. - * - * If the O_DIRECT write will extend the file then add this inode to the - * orphan list. So recovery will truncate it back to the original size - * if the machine crashes during the write. + * ext4_map_blocks_atomic: Helper routine to ensure the entire requested + * range in @map [lblk, lblk + len) is one single contiguous extent with no + * mixed mappings. * + * We first use m_flags passed to us by our caller (ext4_iomap_alloc()). + * We only call EXT4_GET_BLOCKS_ZERO in the slow path, when the underlying + * physical extent for the requested range does not have a single contiguous + * mapping type i.e. (Hole, Mapped, or Unwritten) throughout. + * In that case we will loop over the requested range to allocate and zero out + * the unwritten / holes in between, to get a single mapped extent from + * [m_lblk, m_lblk + m_len). Note that this is only possible because we know + * this can be called only with bigalloc enabled filesystem where the underlying + * cluster is already allocated. This avoids allocating discontiguous extents + * in the slow path due to multiple calls to ext4_map_blocks(). + * The slow path is mostly non-performance critical path, so it should be ok to + * loop using ext4_map_blocks() with appropriate flags to allocate & zero the + * underlying short holes/unwritten extents within the requested range. */ -static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, - const struct iovec *iov, loff_t offset, - unsigned long nr_segs) -{ - struct file *file = iocb->ki_filp; - struct inode *inode = file->f_mapping->host; - ssize_t ret; - size_t count = iov_length(iov, nr_segs); - int overwrite = 0; - get_block_t *get_block_func = NULL; - int dio_flags = 0; - loff_t final_size = offset + count; - ext4_io_end_t *io_end = NULL; - - /* Use the old path for reads and writes beyond i_size. */ - if (rw != WRITE || final_size > inode->i_size) - return ext4_ind_direct_IO(rw, iocb, iov, offset, nr_segs); - - BUG_ON(iocb->private == NULL); +static int ext4_map_blocks_atomic_write(handle_t *handle, struct inode *inode, + struct ext4_map_blocks *map, int m_flags, + bool *force_commit) +{ + ext4_lblk_t m_lblk = map->m_lblk; + unsigned int m_len = map->m_len; + int ret = 0; + + WARN_ON_ONCE(m_len > 1 && !ext4_has_feature_bigalloc(inode->i_sb)); + ret = ext4_map_blocks(handle, inode, map, m_flags); + if (ret < 0 || ret == m_len) + goto out; /* - * Make all waiters for direct IO properly wait also for extent - * conversion. This also disallows race between truncate() and - * overwrite DIO as i_dio_count needs to be incremented under i_mutex. + * This is a mixed mapping case where we were not able to allocate + * a single contiguous extent. In that case let's reset requested + * mapping and call the slow path. */ - if (rw == WRITE) - atomic_inc(&inode->i_dio_count); + map->m_lblk = m_lblk; + map->m_len = m_len; + map->m_flags = 0; - /* If we do a overwrite dio, i_mutex locking can be released */ - overwrite = *((int *)iocb->private); + /* + * slow path means we have mixed mapping, that means we will need + * to force txn commit. + */ + *force_commit = true; + return ext4_map_blocks_atomic_write_slow(handle, inode, map); +out: + return ret; +} - if (overwrite) { - down_read(&EXT4_I(inode)->i_data_sem); - mutex_unlock(&inode->i_mutex); - } +static int ext4_iomap_alloc(struct inode *inode, struct ext4_map_blocks *map, + unsigned int flags) +{ + handle_t *handle; + int ret, dio_credits, m_flags = 0, retries = 0; + bool force_commit = false; /* - * We could direct write to holes and fallocate. - * - * Allocated blocks to fill the hole are marked as - * uninitialized to prevent parallel buffered read to expose - * the stale data before DIO complete the data IO. - * - * As to previously fallocated extents, ext4 get_block will - * just simply mark the buffer mapped but still keep the - * extents uninitialized. - * - * For non AIO case, we will convert those unwritten extents - * to written after return back from blockdev_direct_IO. - * - * For async DIO, the conversion needs to be deferred when the - * IO is completed. The ext4 end_io callback function will be - * called to take care of the conversion work. Here for async - * case, we allocate an io_end structure to hook to the iocb. + * Trim the mapping request to the maximum value that we can map at + * once for direct I/O. */ - iocb->private = NULL; - ext4_inode_aio_set(inode, NULL); - if (!is_sync_kiocb(iocb)) { - io_end = ext4_init_io_end(inode, GFP_NOFS); - if (!io_end) { - ret = -ENOMEM; - goto retake_lock; + if (map->m_len > DIO_MAX_BLOCKS) + map->m_len = DIO_MAX_BLOCKS; + + /* + * journal credits estimation for atomic writes. We call + * ext4_map_blocks(), to find if there could be a mixed mapping. If yes, + * then let's assume the no. of pextents required can be m_len i.e. + * every alternate block can be unwritten and hole. + */ + if (flags & IOMAP_ATOMIC) { + unsigned int orig_mlen = map->m_len; + + ret = ext4_map_blocks(NULL, inode, map, 0); + if (ret < 0) + return ret; + if (map->m_len < orig_mlen) { + map->m_len = orig_mlen; + dio_credits = ext4_meta_trans_blocks(inode, orig_mlen, + map->m_len); + } else { + dio_credits = ext4_chunk_trans_blocks(inode, + map->m_len); } - io_end->flag |= EXT4_IO_END_DIRECT; - /* - * Grab reference for DIO. Will be dropped in ext4_end_io_dio() - */ - iocb->private = ext4_get_io_end(io_end); - /* - * we save the io structure for current async direct - * IO, so that later ext4_map_blocks() could flag the - * io structure whether there is a unwritten extents - * needs to be converted when IO is completed. - */ - ext4_inode_aio_set(inode, io_end); + } else { + dio_credits = ext4_chunk_trans_blocks(inode, map->m_len); } - if (overwrite) { - get_block_func = ext4_get_block_write_nolock; - } else { - get_block_func = ext4_get_block_write; - dio_flags = DIO_LOCKING; +retry: + /* + * Either we allocate blocks and then don't get an unwritten extent, so + * in that case we have reserved enough credits. Or, the blocks are + * already allocated and unwritten. In that case, the extent conversion + * fits into the credits as well. + */ + handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, dio_credits); + if (IS_ERR(handle)) + return PTR_ERR(handle); + + /* + * DAX and direct I/O are the only two operations that are currently + * supported with IOMAP_WRITE. + */ + WARN_ON(!(flags & (IOMAP_DAX | IOMAP_DIRECT))); + if (flags & IOMAP_DAX) + m_flags = EXT4_GET_BLOCKS_CREATE_ZERO; + /* + * We use i_size instead of i_disksize here because delalloc writeback + * can complete at any point during the I/O and subsequently push the + * i_disksize out to i_size. This could be beyond where direct I/O is + * happening and thus expose allocated blocks to direct I/O reads. + */ + else if (EXT4_LBLK_TO_B(inode, map->m_lblk) >= i_size_read(inode)) + m_flags = EXT4_GET_BLOCKS_CREATE; + else if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) + m_flags = EXT4_GET_BLOCKS_IO_CREATE_EXT; + + if (flags & IOMAP_ATOMIC) + ret = ext4_map_blocks_atomic_write(handle, inode, map, m_flags, + &force_commit); + else + ret = ext4_map_blocks(handle, inode, map, m_flags); + + /* + * We cannot fill holes in indirect tree based inodes as that could + * expose stale data in the case of a crash. Use the magic error code + * to fallback to buffered I/O. + */ + if (!m_flags && !ret) + ret = -ENOTBLK; + + ext4_journal_stop(handle); + if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) + goto retry; + + /* + * Force commit the current transaction if the allocation spans a mixed + * mapping range. This ensures any pending metadata updates (like + * unwritten to written extents conversion) in this range are in + * consistent state with the file data blocks, before performing the + * actual write I/O. If the commit fails, the whole I/O must be aborted + * to prevent any possible torn writes. + */ + if (ret > 0 && force_commit) { + int ret2; + + ret2 = ext4_force_commit(inode->i_sb); + if (ret2) + return ret2; } - ret = __blockdev_direct_IO(rw, iocb, inode, - inode->i_sb->s_bdev, iov, - offset, nr_segs, - get_block_func, - ext4_end_io_dio, - NULL, - dio_flags); + + return ret; +} + + +static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length, + unsigned flags, struct iomap *iomap, struct iomap *srcmap) +{ + int ret; + struct ext4_map_blocks map; + u8 blkbits = inode->i_blkbits; + unsigned int orig_mlen; + + if ((offset >> blkbits) > EXT4_MAX_LOGICAL_BLOCK) + return -EINVAL; + + if (WARN_ON_ONCE(ext4_has_inline_data(inode))) + return -ERANGE; /* - * Put our reference to io_end. This can free the io_end structure e.g. - * in sync IO case or in case of error. It can even perform extent - * conversion if all bios we submitted finished before we got here. - * Note that in that case iocb->private can be already set to NULL - * here. + * Calculate the first and last logical blocks respectively. */ - if (io_end) { - ext4_inode_aio_set(inode, NULL); - ext4_put_io_end(io_end); + map.m_lblk = offset >> blkbits; + map.m_len = min_t(loff_t, (offset + length - 1) >> blkbits, + EXT4_MAX_LOGICAL_BLOCK) - map.m_lblk + 1; + orig_mlen = map.m_len; + + if (flags & IOMAP_WRITE) { /* - * When no IO was submitted ext4_end_io_dio() was not - * called so we have to put iocb's reference. + * We check here if the blocks are already allocated, then we + * don't need to start a journal txn and we can directly return + * the mapping information. This could boost performance + * especially in multi-threaded overwrite requests. */ - if (ret <= 0 && ret != -EIOCBQUEUED && iocb->private) { - WARN_ON(iocb->private != io_end); - WARN_ON(io_end->flag & EXT4_IO_END_UNWRITTEN); - WARN_ON(io_end->iocb); + if (offset + length <= i_size_read(inode)) { + ret = ext4_map_blocks(NULL, inode, &map, 0); /* - * Generic code already did inode_dio_done() so we - * have to clear EXT4_IO_END_DIRECT to not do it for - * the second time. + * For atomic writes the entire requested length should + * be mapped. */ - io_end->flag = 0; - ext4_put_io_end(io_end); - iocb->private = NULL; + if (map.m_flags & EXT4_MAP_MAPPED) { + if ((!(flags & IOMAP_ATOMIC) && ret > 0) || + (flags & IOMAP_ATOMIC && ret >= orig_mlen)) + goto out; + } + map.m_len = orig_mlen; } - } - if (ret > 0 && !overwrite && ext4_test_inode_state(inode, - EXT4_STATE_DIO_UNWRITTEN)) { - int err; + ret = ext4_iomap_alloc(inode, &map, flags); + } else { /* - * for non AIO case, since the IO is already - * completed, we could do the conversion right here + * This can be called for overwrites path from + * ext4_iomap_overwrite_begin(). */ - err = ext4_convert_unwritten_extents(NULL, inode, - offset, ret); - if (err < 0) - ret = err; - ext4_clear_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN); + ret = ext4_map_blocks(NULL, inode, &map, 0); } -retake_lock: - if (rw == WRITE) - inode_dio_done(inode); - /* take i_mutex locking again if we do a ovewrite dio */ - if (overwrite) { - up_read(&EXT4_I(inode)->i_data_sem); - mutex_lock(&inode->i_mutex); + if (ret < 0) + return ret; +out: + /* + * When inline encryption is enabled, sometimes I/O to an encrypted file + * has to be broken up to guarantee DUN contiguity. Handle this by + * limiting the length of the mapping returned. + */ + map.m_len = fscrypt_limit_io_blocks(inode, map.m_lblk, map.m_len); + + /* + * Before returning to iomap, let's ensure the allocated mapping + * covers the entire requested length for atomic writes. + */ + if (flags & IOMAP_ATOMIC) { + if (map.m_len < (length >> blkbits)) { + WARN_ON_ONCE(1); + return -EINVAL; + } } + ext4_set_iomap(inode, iomap, &map, offset, length, flags); + + return 0; +} + +static int ext4_iomap_overwrite_begin(struct inode *inode, loff_t offset, + loff_t length, unsigned flags, struct iomap *iomap, + struct iomap *srcmap) +{ + int ret; + /* + * Even for writes we don't need to allocate blocks, so just pretend + * we are reading to save overhead of starting a transaction. + */ + flags &= ~IOMAP_WRITE; + ret = ext4_iomap_begin(inode, offset, length, flags, iomap, srcmap); + WARN_ON_ONCE(!ret && iomap->type != IOMAP_MAPPED); return ret; } -static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb, - const struct iovec *iov, loff_t offset, - unsigned long nr_segs) +const struct iomap_ops ext4_iomap_ops = { + .iomap_begin = ext4_iomap_begin, +}; + +const struct iomap_ops ext4_iomap_overwrite_ops = { + .iomap_begin = ext4_iomap_overwrite_begin, +}; + +static int ext4_iomap_begin_report(struct inode *inode, loff_t offset, + loff_t length, unsigned int flags, + struct iomap *iomap, struct iomap *srcmap) { - struct file *file = iocb->ki_filp; - struct inode *inode = file->f_mapping->host; - ssize_t ret; + int ret; + struct ext4_map_blocks map; + u8 blkbits = inode->i_blkbits; + + if ((offset >> blkbits) > EXT4_MAX_LOGICAL_BLOCK) + return -EINVAL; + + if (ext4_has_inline_data(inode)) { + ret = ext4_inline_data_iomap(inode, iomap); + if (ret != -EAGAIN) { + if (ret == 0 && offset >= iomap->length) + ret = -ENOENT; + return ret; + } + } /* - * If we are doing data journalling we don't support O_DIRECT + * Calculate the first and last logical block respectively. */ - if (ext4_should_journal_data(inode)) - return 0; + map.m_lblk = offset >> blkbits; + map.m_len = min_t(loff_t, (offset + length - 1) >> blkbits, + EXT4_MAX_LOGICAL_BLOCK) - map.m_lblk + 1; - /* Let buffer I/O handle the inline data case. */ - if (ext4_has_inline_data(inode)) - return 0; + /* + * Fiemap callers may call for offset beyond s_bitmap_maxbytes. + * So handle it here itself instead of querying ext4_map_blocks(). + * Since ext4_map_blocks() will warn about it and will return + * -EIO error. + */ + if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) { + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); - trace_ext4_direct_IO_enter(inode, offset, iov_length(iov, nr_segs), rw); - if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) - ret = ext4_ext_direct_IO(rw, iocb, iov, offset, nr_segs); - else - ret = ext4_ind_direct_IO(rw, iocb, iov, offset, nr_segs); - trace_ext4_direct_IO_exit(inode, offset, - iov_length(iov, nr_segs), rw, ret); - return ret; + if (offset >= sbi->s_bitmap_maxbytes) { + map.m_flags = 0; + goto set_iomap; + } + } + + ret = ext4_map_blocks(NULL, inode, &map, 0); + if (ret < 0) + return ret; +set_iomap: + ext4_set_iomap(inode, iomap, &map, offset, length, flags); + + return 0; } +const struct iomap_ops ext4_iomap_report_ops = { + .iomap_begin = ext4_iomap_begin_report, +}; + /* - * Pages can be marked dirty completely asynchronously from ext4's journalling - * activity. By filemap_sync_pte(), try_to_unmap_one(), etc. We cannot do - * much here because ->set_page_dirty is called under VFS locks. The page is - * not necessarily locked. - * - * We cannot just dirty the page and leave attached buffers clean, because the - * buffers' dirty state is "definitive". We cannot just set the buffers dirty - * or jbddirty because all the journalling code will explode. - * - * So what we do is to mark the page "pending dirty" and next time writepage - * is called, propagate that into the buffers appropriately. + * For data=journal mode, folio should be marked dirty only when it was + * writeably mapped. When that happens, it was already attached to the + * transaction and marked as jbddirty (we take care of this in + * ext4_page_mkwrite()). On transaction commit, we writeprotect page mappings + * so we should have nothing to do here, except for the case when someone + * had the page pinned and dirtied the page through this pin (e.g. by doing + * direct IO to it). In that case we'd need to attach buffers here to the + * transaction but we cannot due to lock ordering. We cannot just dirty the + * folio and leave attached buffers clean, because the buffers' dirty state is + * "definitive". We cannot just set the buffers dirty or jbddirty because all + * the journalling code will explode. So what we do is to mark the folio + * "pending dirty" and next time ext4_writepages() is called, attach buffers + * to the transaction appropriately. */ -static int ext4_journalled_set_page_dirty(struct page *page) +static bool ext4_journalled_dirty_folio(struct address_space *mapping, + struct folio *folio) +{ + WARN_ON_ONCE(!folio_buffers(folio)); + if (folio_maybe_dma_pinned(folio)) + folio_set_checked(folio); + return filemap_dirty_folio(mapping, folio); +} + +static bool ext4_dirty_folio(struct address_space *mapping, struct folio *folio) { - SetPageChecked(page); - return __set_page_dirty_nobuffers(page); + WARN_ON_ONCE(!folio_test_locked(folio) && !folio_test_dirty(folio)); + WARN_ON_ONCE(!folio_buffers(folio)); + return block_dirty_folio(mapping, folio); +} + +static int ext4_iomap_swap_activate(struct swap_info_struct *sis, + struct file *file, sector_t *span) +{ + return iomap_swapfile_activate(sis, file, span, + &ext4_iomap_report_ops); } static const struct address_space_operations ext4_aops = { - .readpage = ext4_readpage, - .readpages = ext4_readpages, - .writepage = ext4_writepage, + .read_folio = ext4_read_folio, + .readahead = ext4_readahead, .writepages = ext4_writepages, .write_begin = ext4_write_begin, .write_end = ext4_write_end, + .dirty_folio = ext4_dirty_folio, .bmap = ext4_bmap, - .invalidatepage = ext4_invalidatepage, - .releasepage = ext4_releasepage, - .direct_IO = ext4_direct_IO, - .migratepage = buffer_migrate_page, + .invalidate_folio = ext4_invalidate_folio, + .release_folio = ext4_release_folio, + .migrate_folio = buffer_migrate_folio, .is_partially_uptodate = block_is_partially_uptodate, - .error_remove_page = generic_error_remove_page, + .error_remove_folio = generic_error_remove_folio, + .swap_activate = ext4_iomap_swap_activate, }; static const struct address_space_operations ext4_journalled_aops = { - .readpage = ext4_readpage, - .readpages = ext4_readpages, - .writepage = ext4_writepage, + .read_folio = ext4_read_folio, + .readahead = ext4_readahead, .writepages = ext4_writepages, .write_begin = ext4_write_begin, .write_end = ext4_journalled_write_end, - .set_page_dirty = ext4_journalled_set_page_dirty, + .dirty_folio = ext4_journalled_dirty_folio, .bmap = ext4_bmap, - .invalidatepage = ext4_journalled_invalidatepage, - .releasepage = ext4_releasepage, - .direct_IO = ext4_direct_IO, + .invalidate_folio = ext4_journalled_invalidate_folio, + .release_folio = ext4_release_folio, + .migrate_folio = buffer_migrate_folio_norefs, .is_partially_uptodate = block_is_partially_uptodate, - .error_remove_page = generic_error_remove_page, + .error_remove_folio = generic_error_remove_folio, + .swap_activate = ext4_iomap_swap_activate, }; static const struct address_space_operations ext4_da_aops = { - .readpage = ext4_readpage, - .readpages = ext4_readpages, - .writepage = ext4_writepage, + .read_folio = ext4_read_folio, + .readahead = ext4_readahead, .writepages = ext4_writepages, .write_begin = ext4_da_write_begin, .write_end = ext4_da_write_end, + .dirty_folio = ext4_dirty_folio, .bmap = ext4_bmap, - .invalidatepage = ext4_da_invalidatepage, - .releasepage = ext4_releasepage, - .direct_IO = ext4_direct_IO, - .migratepage = buffer_migrate_page, + .invalidate_folio = ext4_invalidate_folio, + .release_folio = ext4_release_folio, + .migrate_folio = buffer_migrate_folio, .is_partially_uptodate = block_is_partially_uptodate, - .error_remove_page = generic_error_remove_page, + .error_remove_folio = generic_error_remove_folio, + .swap_activate = ext4_iomap_swap_activate, +}; + +static const struct address_space_operations ext4_dax_aops = { + .writepages = ext4_dax_writepages, + .dirty_folio = noop_dirty_folio, + .bmap = ext4_bmap, + .swap_activate = ext4_iomap_swap_activate, }; void ext4_set_aops(struct inode *inode) { switch (ext4_inode_journal_mode(inode)) { case EXT4_INODE_ORDERED_DATA_MODE: - ext4_set_inode_state(inode, EXT4_STATE_ORDERED_MODE); - break; case EXT4_INODE_WRITEBACK_DATA_MODE: - ext4_clear_inode_state(inode, EXT4_STATE_ORDERED_MODE); break; case EXT4_INODE_JOURNAL_DATA_MODE: inode->i_mapping->a_ops = &ext4_journalled_aops; @@ -3300,73 +4040,46 @@ void ext4_set_aops(struct inode *inode) default: BUG(); } - if (test_opt(inode->i_sb, DELALLOC)) + if (IS_DAX(inode)) + inode->i_mapping->a_ops = &ext4_dax_aops; + else if (test_opt(inode->i_sb, DELALLOC)) inode->i_mapping->a_ops = &ext4_da_aops; else inode->i_mapping->a_ops = &ext4_aops; } /* - * ext4_block_truncate_page() zeroes out a mapping from file offset `from' - * up to the end of the block which corresponds to `from'. - * This required during truncate. We need to physically zero the tail end - * of that block so it doesn't yield old data if the file is later grown. - */ -int ext4_block_truncate_page(handle_t *handle, - struct address_space *mapping, loff_t from) -{ - unsigned offset = from & (PAGE_CACHE_SIZE-1); - unsigned length; - unsigned blocksize; - struct inode *inode = mapping->host; - - blocksize = inode->i_sb->s_blocksize; - length = blocksize - (offset & (blocksize - 1)); - - return ext4_block_zero_page_range(handle, mapping, from, length); -} - -/* - * ext4_block_zero_page_range() zeros out a mapping of length 'length' - * starting from file offset 'from'. The range to be zero'd must - * be contained with in one block. If the specified range exceeds - * the end of the block it will be shortened to end of the block - * that cooresponds to 'from' + * Here we can't skip an unwritten buffer even though it usually reads zero + * because it might have data in pagecache (eg, if called from ext4_zero_range, + * ext4_punch_hole, etc) which needs to be properly zeroed out. Otherwise a + * racing writeback can come later and flush the stale pagecache to disk. */ -int ext4_block_zero_page_range(handle_t *handle, +static int __ext4_block_zero_page_range(handle_t *handle, struct address_space *mapping, loff_t from, loff_t length) { - ext4_fsblk_t index = from >> PAGE_CACHE_SHIFT; - unsigned offset = from & (PAGE_CACHE_SIZE-1); - unsigned blocksize, max, pos; + unsigned int offset, blocksize, pos; ext4_lblk_t iblock; struct inode *inode = mapping->host; struct buffer_head *bh; - struct page *page; + struct folio *folio; int err = 0; - page = find_or_create_page(mapping, from >> PAGE_CACHE_SHIFT, - mapping_gfp_mask(mapping) & ~__GFP_FS); - if (!page) - return -ENOMEM; + folio = __filemap_get_folio(mapping, from >> PAGE_SHIFT, + FGP_LOCK | FGP_ACCESSED | FGP_CREAT, + mapping_gfp_constraint(mapping, ~__GFP_FS)); + if (IS_ERR(folio)) + return PTR_ERR(folio); blocksize = inode->i_sb->s_blocksize; - max = blocksize - (offset & (blocksize - 1)); - - /* - * correct length if it does not fall between - * 'from' and the end of the block - */ - if (length > max || length < 0) - length = max; - iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits); + iblock = EXT4_PG_TO_LBLK(inode, folio->index); - if (!page_has_buffers(page)) - create_empty_buffers(page, blocksize, 0); + bh = folio_buffers(folio); + if (!bh) + bh = create_empty_buffers(folio, blocksize, 0); /* Find the buffer that contains "offset" */ - bh = page_buffers(page); + offset = offset_in_folio(folio, from); pos = blocksize; while (offset >= pos) { bh = bh->b_this_page; @@ -3388,41 +4101,102 @@ int ext4_block_zero_page_range(handle_t *handle, } /* Ok, it's mapped. Make sure it's up-to-date */ - if (PageUptodate(page)) + if (folio_test_uptodate(folio)) set_buffer_uptodate(bh); if (!buffer_uptodate(bh)) { - err = -EIO; - ll_rw_block(READ, 1, &bh); - wait_on_buffer(bh); - /* Uhhuh. Read error. Complain and punt. */ - if (!buffer_uptodate(bh)) + err = ext4_read_bh_lock(bh, 0, true); + if (err) goto unlock; + if (fscrypt_inode_uses_fs_layer_crypto(inode)) { + /* We expect the key to be set. */ + BUG_ON(!fscrypt_has_encryption_key(inode)); + err = fscrypt_decrypt_pagecache_blocks(folio, + blocksize, + bh_offset(bh)); + if (err) { + clear_buffer_uptodate(bh); + goto unlock; + } + } } if (ext4_should_journal_data(inode)) { BUFFER_TRACE(bh, "get write access"); - err = ext4_journal_get_write_access(handle, bh); + err = ext4_journal_get_write_access(handle, inode->i_sb, bh, + EXT4_JTR_NONE); if (err) goto unlock; } - zero_user(page, offset, length); + folio_zero_range(folio, offset, length); BUFFER_TRACE(bh, "zeroed end of block"); if (ext4_should_journal_data(inode)) { - err = ext4_handle_dirty_metadata(handle, inode, bh); + err = ext4_dirty_journalled_data(handle, bh); } else { err = 0; mark_buffer_dirty(bh); - if (ext4_test_inode_state(inode, EXT4_STATE_ORDERED_MODE)) - err = ext4_jbd2_file_inode(handle, inode); + if (ext4_should_order_data(inode)) + err = ext4_jbd2_inode_add_write(handle, inode, from, + length); } unlock: - unlock_page(page); - page_cache_release(page); + folio_unlock(folio); + folio_put(folio); return err; } +/* + * ext4_block_zero_page_range() zeros out a mapping of length 'length' + * starting from file offset 'from'. The range to be zero'd must + * be contained with in one block. If the specified range exceeds + * the end of the block it will be shortened to end of the block + * that corresponds to 'from' + */ +static int ext4_block_zero_page_range(handle_t *handle, + struct address_space *mapping, loff_t from, loff_t length) +{ + struct inode *inode = mapping->host; + unsigned blocksize = inode->i_sb->s_blocksize; + unsigned int max = blocksize - (from & (blocksize - 1)); + + /* + * correct length if it does not fall between + * 'from' and the end of the block + */ + if (length > max || length < 0) + length = max; + + if (IS_DAX(inode)) { + return dax_zero_range(inode, from, length, NULL, + &ext4_iomap_ops); + } + return __ext4_block_zero_page_range(handle, mapping, from, length); +} + +/* + * ext4_block_truncate_page() zeroes out a mapping from file offset `from' + * up to the end of the block which corresponds to `from'. + * This required during truncate. We need to physically zero the tail end + * of that block so it doesn't yield old data if the file is later grown. + */ +static int ext4_block_truncate_page(handle_t *handle, + struct address_space *mapping, loff_t from) +{ + unsigned length; + unsigned blocksize; + struct inode *inode = mapping->host; + + /* If we are processing an encrypted inode during orphan list handling */ + if (IS_ENCRYPTED(inode) && !fscrypt_has_encryption_key(inode)) + return 0; + + blocksize = i_blocksize(inode); + length = blocksize - (from & (blocksize - 1)); + + return ext4_block_zero_page_range(handle, mapping, from, length); +} + int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode, loff_t lstart, loff_t length) { @@ -3473,7 +4247,121 @@ int ext4_can_truncate(struct inode *inode) } /* - * ext4_punch_hole: punches a hole in a file by releaseing the blocks + * We have to make sure i_disksize gets properly updated before we truncate + * page cache due to hole punching or zero range. Otherwise i_disksize update + * can get lost as it may have been postponed to submission of writeback but + * that will never happen if we remove the folio containing i_size from the + * page cache. Also if we punch hole within i_size but above i_disksize, + * following ext4_page_mkwrite() may mistakenly allocate written blocks over + * the hole and thus introduce allocated blocks beyond i_disksize which is + * not allowed (e2fsck would complain in case of crash). + */ +int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset, + loff_t len) +{ + handle_t *handle; + int ret; + + loff_t size = i_size_read(inode); + + WARN_ON(!inode_is_locked(inode)); + if (offset > size) + return 0; + + if (offset + len < size) + size = offset + len; + if (EXT4_I(inode)->i_disksize >= size) + return 0; + + handle = ext4_journal_start(inode, EXT4_HT_MISC, 1); + if (IS_ERR(handle)) + return PTR_ERR(handle); + ext4_update_i_disksize(inode, size); + ret = ext4_mark_inode_dirty(handle, inode); + ext4_journal_stop(handle); + + return ret; +} + +static inline void ext4_truncate_folio(struct inode *inode, + loff_t start, loff_t end) +{ + unsigned long blocksize = i_blocksize(inode); + struct folio *folio; + + /* Nothing to be done if no complete block needs to be truncated. */ + if (round_up(start, blocksize) >= round_down(end, blocksize)) + return; + + folio = filemap_lock_folio(inode->i_mapping, start >> PAGE_SHIFT); + if (IS_ERR(folio)) + return; + + if (folio_mkclean(folio)) + folio_mark_dirty(folio); + folio_unlock(folio); + folio_put(folio); +} + +int ext4_truncate_page_cache_block_range(struct inode *inode, + loff_t start, loff_t end) +{ + unsigned long blocksize = i_blocksize(inode); + int ret; + + /* + * For journalled data we need to write (and checkpoint) pages + * before discarding page cache to avoid inconsitent data on disk + * in case of crash before freeing or unwritten converting trans + * is committed. + */ + if (ext4_should_journal_data(inode)) { + ret = filemap_write_and_wait_range(inode->i_mapping, start, + end - 1); + if (ret) + return ret; + goto truncate_pagecache; + } + + /* + * If the block size is less than the page size, the file's mapped + * blocks within one page could be freed or converted to unwritten. + * So it's necessary to remove writable userspace mappings, and then + * ext4_page_mkwrite() can be called during subsequent write access + * to these partial folios. + */ + if (!IS_ALIGNED(start | end, PAGE_SIZE) && + blocksize < PAGE_SIZE && start < inode->i_size) { + loff_t page_boundary = round_up(start, PAGE_SIZE); + + ext4_truncate_folio(inode, start, min(page_boundary, end)); + if (end > page_boundary) + ext4_truncate_folio(inode, + round_down(end, PAGE_SIZE), end); + } + +truncate_pagecache: + truncate_pagecache_range(inode, start, end - 1); + return 0; +} + +static void ext4_wait_dax_page(struct inode *inode) +{ + filemap_invalidate_unlock(inode->i_mapping); + schedule(); + filemap_invalidate_lock(inode->i_mapping); +} + +int ext4_break_layouts(struct inode *inode) +{ + if (WARN_ON_ONCE(!rwsem_is_locked(&inode->i_mapping->invalidate_lock))) + return -EINVAL; + + return dax_break_layout_inode(inode, ext4_wait_dax_page); +} + +/* + * ext4_punch_hole: punches a hole in a file by releasing the blocks * associated with the given offset and length * * @inode: File inode @@ -3483,130 +4371,144 @@ int ext4_can_truncate(struct inode *inode) * Returns: 0 on success or negative on failure */ -int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) +int ext4_punch_hole(struct file *file, loff_t offset, loff_t length) { + struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; - ext4_lblk_t first_block, stop_block; - struct address_space *mapping = inode->i_mapping; - loff_t first_block_offset, last_block_offset; + ext4_lblk_t start_lblk, end_lblk; + loff_t max_end = sb->s_maxbytes; + loff_t end = offset + length; handle_t *handle; unsigned int credits; - int ret = 0; - - if (!S_ISREG(inode->i_mode)) - return -EOPNOTSUPP; - - if (EXT4_SB(sb)->s_cluster_ratio > 1) { - /* TODO: Add support for bigalloc file systems */ - return -EOPNOTSUPP; - } + int ret; - trace_ext4_punch_hole(inode, offset, length); + trace_ext4_punch_hole(inode, offset, length, 0); + WARN_ON_ONCE(!inode_is_locked(inode)); /* - * Write out all dirty pages to avoid race conditions - * Then release them. + * For indirect-block based inodes, make sure that the hole within + * one block before last range. */ - if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) { - ret = filemap_write_and_wait_range(mapping, offset, - offset + length - 1); - if (ret) - return ret; - } - - mutex_lock(&inode->i_mutex); - /* It's not possible punch hole on append only file */ - if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) { - ret = -EPERM; - goto out_mutex; - } - if (IS_SWAPFILE(inode)) { - ret = -ETXTBSY; - goto out_mutex; - } + if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) + max_end = EXT4_SB(sb)->s_bitmap_maxbytes - sb->s_blocksize; /* No need to punch hole beyond i_size */ - if (offset >= inode->i_size) - goto out_mutex; + if (offset >= inode->i_size || offset >= max_end) + return 0; + + /* + * If the hole extends beyond i_size, set the hole to end after + * the block that contains i_size to save pointless tail block zeroing. + */ + if (end >= inode->i_size) + end = round_up(inode->i_size, sb->s_blocksize); + if (end > max_end) + end = max_end; + length = end - offset; /* - * If the hole extends beyond i_size, set the hole - * to end after the page that contains i_size + * Attach jinode to inode for jbd2 if we do any zeroing of partial + * block. */ - if (offset + length > inode->i_size) { - length = inode->i_size + - PAGE_CACHE_SIZE - (inode->i_size & (PAGE_CACHE_SIZE - 1)) - - offset; + if (!IS_ALIGNED(offset | end, sb->s_blocksize)) { + ret = ext4_inode_attach_jinode(inode); + if (ret < 0) + return ret; } - first_block_offset = round_up(offset, sb->s_blocksize); - last_block_offset = round_down((offset + length), sb->s_blocksize) - 1; - /* Now release the pages and zero block aligned part of pages*/ - if (last_block_offset > first_block_offset) - truncate_pagecache_range(inode, first_block_offset, - last_block_offset); + ret = ext4_update_disksize_before_punch(inode, offset, length); + if (ret) + return ret; - /* Wait all existing dio workers, newcomers will block on i_mutex */ - ext4_inode_block_unlocked_dio(inode); - inode_dio_wait(inode); + /* Now release the pages and zero block aligned part of pages*/ + ret = ext4_truncate_page_cache_block_range(inode, offset, end); + if (ret) + return ret; if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) - credits = ext4_writepage_trans_blocks(inode); + credits = ext4_chunk_trans_extent(inode, 2); else credits = ext4_blocks_for_truncate(inode); handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); ext4_std_error(sb, ret); - goto out_dio; + return ret; } - ret = ext4_zero_partial_blocks(handle, inode, offset, - length); + ret = ext4_zero_partial_blocks(handle, inode, offset, length); if (ret) - goto out_stop; + goto out_handle; - first_block = (offset + sb->s_blocksize - 1) >> - EXT4_BLOCK_SIZE_BITS(sb); - stop_block = (offset + length) >> EXT4_BLOCK_SIZE_BITS(sb); + /* If there are blocks to remove, do it */ + start_lblk = EXT4_B_TO_LBLK(inode, offset); + end_lblk = end >> inode->i_blkbits; - /* If there are no blocks to remove, return now */ - if (first_block >= stop_block) - goto out_stop; + if (end_lblk > start_lblk) { + ext4_lblk_t hole_len = end_lblk - start_lblk; - down_write(&EXT4_I(inode)->i_data_sem); - ext4_discard_preallocations(inode); + ext4_fc_track_inode(handle, inode); + ext4_check_map_extents_env(inode); + down_write(&EXT4_I(inode)->i_data_sem); + ext4_discard_preallocations(inode); - ret = ext4_es_remove_extent(inode, first_block, - stop_block - first_block); - if (ret) { + ext4_es_remove_extent(inode, start_lblk, hole_len); + + if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) + ret = ext4_ext_remove_space(inode, start_lblk, + end_lblk - 1); + else + ret = ext4_ind_remove_space(handle, inode, start_lblk, + end_lblk); + if (ret) { + up_write(&EXT4_I(inode)->i_data_sem); + goto out_handle; + } + + ext4_es_insert_extent(inode, start_lblk, hole_len, ~0, + EXTENT_STATUS_HOLE, 0); up_write(&EXT4_I(inode)->i_data_sem); - goto out_stop; } + ext4_fc_track_range(handle, inode, start_lblk, end_lblk); - if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) - ret = ext4_ext_remove_space(inode, first_block, - stop_block - 1); - else - ret = ext4_free_hole_blocks(handle, inode, first_block, - stop_block); + ret = ext4_mark_inode_dirty(handle, inode); + if (unlikely(ret)) + goto out_handle; - ext4_discard_preallocations(inode); - up_write(&EXT4_I(inode)->i_data_sem); + ext4_update_inode_fsync_trans(handle, inode, 1); if (IS_SYNC(inode)) ext4_handle_sync(handle); - inode->i_mtime = inode->i_ctime = ext4_current_time(inode); - ext4_mark_inode_dirty(handle, inode); -out_stop: +out_handle: ext4_journal_stop(handle); -out_dio: - ext4_inode_resume_unlocked_dio(inode); -out_mutex: - mutex_unlock(&inode->i_mutex); return ret; } +int ext4_inode_attach_jinode(struct inode *inode) +{ + struct ext4_inode_info *ei = EXT4_I(inode); + struct jbd2_inode *jinode; + + if (ei->jinode || !EXT4_SB(inode->i_sb)->s_journal) + return 0; + + jinode = jbd2_alloc_inode(GFP_KERNEL); + spin_lock(&inode->i_lock); + if (!ei->jinode) { + if (!jinode) { + spin_unlock(&inode->i_lock); + return -ENOMEM; + } + ei->jinode = jinode; + jbd2_journal_init_jbd_inode(ei->jinode, inode); + jinode = NULL; + } + spin_unlock(&inode->i_lock); + if (unlikely(jinode != NULL)) + jbd2_free_inode(jinode); + return 0; +} + /* * ext4_truncate() * @@ -3635,26 +4537,25 @@ out_mutex: * that's fine - as long as they are linked from the inode, the post-crash * ext4_truncate() run will find them and release them. */ -void ext4_truncate(struct inode *inode) +int ext4_truncate(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); unsigned int credits; + int err = 0, err2; handle_t *handle; struct address_space *mapping = inode->i_mapping; /* * There is a possibility that we're either freeing the inode - * or it completely new indode. In those cases we might not - * have i_mutex locked because it's not necessary. + * or it's a completely new inode. In those cases we might not + * have i_rwsem locked because it's not necessary. */ - if (!(inode->i_state & (I_NEW|I_FREEING))) - WARN_ON(!mutex_is_locked(&inode->i_mutex)); + if (!(inode_state_read_once(inode) & (I_NEW | I_FREEING))) + WARN_ON(!inode_is_locked(inode)); trace_ext4_truncate_enter(inode); if (!ext4_can_truncate(inode)) - return; - - ext4_clear_inode_flag(inode, EXT4_INODE_EOFBLOCKS); + goto out_trace; if (inode->i_size == 0 && !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC)) ext4_set_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE); @@ -3662,20 +4563,27 @@ void ext4_truncate(struct inode *inode) if (ext4_has_inline_data(inode)) { int has_inline = 1; - ext4_inline_data_truncate(inode, &has_inline); - if (has_inline) - return; + err = ext4_inline_data_truncate(inode, &has_inline); + if (err || has_inline) + goto out_trace; + } + + /* If we zero-out tail of the page, we have to create jinode for jbd2 */ + if (inode->i_size & (inode->i_sb->s_blocksize - 1)) { + err = ext4_inode_attach_jinode(inode); + if (err) + goto out_trace; } if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) - credits = ext4_writepage_trans_blocks(inode); + credits = ext4_chunk_trans_extent(inode, 1); else credits = ext4_blocks_for_truncate(inode); handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits); if (IS_ERR(handle)) { - ext4_std_error(inode->i_sb, PTR_ERR(handle)); - return; + err = PTR_ERR(handle); + goto out_trace; } if (inode->i_size & (inode->i_sb->s_blocksize - 1)) @@ -3690,19 +4598,24 @@ void ext4_truncate(struct inode *inode) * Implication: the file must always be in a sane, consistent * truncatable state while each transaction commits. */ - if (ext4_orphan_add(handle, inode)) + err = ext4_orphan_add(handle, inode); + if (err) goto out_stop; - down_write(&EXT4_I(inode)->i_data_sem); + ext4_fc_track_inode(handle, inode); + ext4_check_map_extents_env(inode); + down_write(&EXT4_I(inode)->i_data_sem); ext4_discard_preallocations(inode); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) - ext4_ext_truncate(handle, inode); + err = ext4_ext_truncate(handle, inode); else ext4_ind_truncate(handle, inode); up_write(&ei->i_data_sem); + if (err) + goto out_stop; if (IS_SYNC(inode)) ext4_handle_sync(handle); @@ -3712,39 +4625,192 @@ out_stop: * If this was a simple ftruncate() and the file will remain alive, * then we need to clear up the orphan record which we created above. * However, if this was a real unlink then we were called by - * ext4_delete_inode(), and we allow that function to clean up the + * ext4_evict_inode(), and we allow that function to clean up the * orphan info for us. */ if (inode->i_nlink) ext4_orphan_del(handle, inode); - inode->i_mtime = inode->i_ctime = ext4_current_time(inode); - ext4_mark_inode_dirty(handle, inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); + err2 = ext4_mark_inode_dirty(handle, inode); + if (unlikely(err2 && !err)) + err = err2; ext4_journal_stop(handle); +out_trace: trace_ext4_truncate_exit(inode); + return err; +} + +static inline u64 ext4_inode_peek_iversion(const struct inode *inode) +{ + if (unlikely(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) + return inode_peek_iversion_raw(inode); + else + return inode_peek_iversion(inode); +} + +static int ext4_inode_blocks_set(struct ext4_inode *raw_inode, + struct ext4_inode_info *ei) +{ + struct inode *inode = &(ei->vfs_inode); + u64 i_blocks = READ_ONCE(inode->i_blocks); + struct super_block *sb = inode->i_sb; + + if (i_blocks <= ~0U) { + /* + * i_blocks can be represented in a 32 bit variable + * as multiple of 512 bytes + */ + raw_inode->i_blocks_lo = cpu_to_le32(i_blocks); + raw_inode->i_blocks_high = 0; + ext4_clear_inode_flag(inode, EXT4_INODE_HUGE_FILE); + return 0; + } + + /* + * This should never happen since sb->s_maxbytes should not have + * allowed this, sb->s_maxbytes was set according to the huge_file + * feature in ext4_fill_super(). + */ + if (!ext4_has_feature_huge_file(sb)) + return -EFSCORRUPTED; + + if (i_blocks <= 0xffffffffffffULL) { + /* + * i_blocks can be represented in a 48 bit variable + * as multiple of 512 bytes + */ + raw_inode->i_blocks_lo = cpu_to_le32(i_blocks); + raw_inode->i_blocks_high = cpu_to_le16(i_blocks >> 32); + ext4_clear_inode_flag(inode, EXT4_INODE_HUGE_FILE); + } else { + ext4_set_inode_flag(inode, EXT4_INODE_HUGE_FILE); + /* i_block is stored in file system block size */ + i_blocks = i_blocks >> (inode->i_blkbits - 9); + raw_inode->i_blocks_lo = cpu_to_le32(i_blocks); + raw_inode->i_blocks_high = cpu_to_le16(i_blocks >> 32); + } + return 0; +} + +static int ext4_fill_raw_inode(struct inode *inode, struct ext4_inode *raw_inode) +{ + struct ext4_inode_info *ei = EXT4_I(inode); + uid_t i_uid; + gid_t i_gid; + projid_t i_projid; + int block; + int err; + + err = ext4_inode_blocks_set(raw_inode, ei); + + raw_inode->i_mode = cpu_to_le16(inode->i_mode); + i_uid = i_uid_read(inode); + i_gid = i_gid_read(inode); + i_projid = from_kprojid(&init_user_ns, ei->i_projid); + if (!(test_opt(inode->i_sb, NO_UID32))) { + raw_inode->i_uid_low = cpu_to_le16(low_16_bits(i_uid)); + raw_inode->i_gid_low = cpu_to_le16(low_16_bits(i_gid)); + /* + * Fix up interoperability with old kernels. Otherwise, + * old inodes get re-used with the upper 16 bits of the + * uid/gid intact. + */ + if (ei->i_dtime && !ext4_inode_orphan_tracked(inode)) { + raw_inode->i_uid_high = 0; + raw_inode->i_gid_high = 0; + } else { + raw_inode->i_uid_high = + cpu_to_le16(high_16_bits(i_uid)); + raw_inode->i_gid_high = + cpu_to_le16(high_16_bits(i_gid)); + } + } else { + raw_inode->i_uid_low = cpu_to_le16(fs_high2lowuid(i_uid)); + raw_inode->i_gid_low = cpu_to_le16(fs_high2lowgid(i_gid)); + raw_inode->i_uid_high = 0; + raw_inode->i_gid_high = 0; + } + raw_inode->i_links_count = cpu_to_le16(inode->i_nlink); + + EXT4_INODE_SET_CTIME(inode, raw_inode); + EXT4_INODE_SET_MTIME(inode, raw_inode); + EXT4_INODE_SET_ATIME(inode, raw_inode); + EXT4_EINODE_SET_XTIME(i_crtime, ei, raw_inode); + + raw_inode->i_dtime = cpu_to_le32(ei->i_dtime); + raw_inode->i_flags = cpu_to_le32(ei->i_flags & 0xFFFFFFFF); + if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) + raw_inode->i_file_acl_high = + cpu_to_le16(ei->i_file_acl >> 32); + raw_inode->i_file_acl_lo = cpu_to_le32(ei->i_file_acl); + ext4_isize_set(raw_inode, ei->i_disksize); + + raw_inode->i_generation = cpu_to_le32(inode->i_generation); + if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) { + if (old_valid_dev(inode->i_rdev)) { + raw_inode->i_block[0] = + cpu_to_le32(old_encode_dev(inode->i_rdev)); + raw_inode->i_block[1] = 0; + } else { + raw_inode->i_block[0] = 0; + raw_inode->i_block[1] = + cpu_to_le32(new_encode_dev(inode->i_rdev)); + raw_inode->i_block[2] = 0; + } + } else if (!ext4_has_inline_data(inode)) { + for (block = 0; block < EXT4_N_BLOCKS; block++) + raw_inode->i_block[block] = ei->i_data[block]; + } + + if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) { + u64 ivers = ext4_inode_peek_iversion(inode); + + raw_inode->i_disk_version = cpu_to_le32(ivers); + if (ei->i_extra_isize) { + if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi)) + raw_inode->i_version_hi = + cpu_to_le32(ivers >> 32); + raw_inode->i_extra_isize = + cpu_to_le16(ei->i_extra_isize); + } + } + + if (i_projid != EXT4_DEF_PROJID && + !ext4_has_feature_project(inode->i_sb)) + err = err ?: -EFSCORRUPTED; + + if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE && + EXT4_FITS_IN_INODE(raw_inode, ei, i_projid)) + raw_inode->i_projid = cpu_to_le32(i_projid); + + ext4_inode_csum_set(inode, raw_inode, ei); + return err; } /* * ext4_get_inode_loc returns with an extra refcount against the inode's - * underlying buffer_head on success. If 'in_mem' is true, we have all - * data in memory that is needed to recreate the on-disk version of this - * inode. + * underlying buffer_head on success. If we pass 'inode' and it does not + * have in-inode xattr, we have all inode data in memory that is needed + * to recreate the on-disk version of this inode. */ -static int __ext4_get_inode_loc(struct inode *inode, - struct ext4_iloc *iloc, int in_mem) +static int __ext4_get_inode_loc(struct super_block *sb, unsigned long ino, + struct inode *inode, struct ext4_iloc *iloc, + ext4_fsblk_t *ret_block) { struct ext4_group_desc *gdp; struct buffer_head *bh; - struct super_block *sb = inode->i_sb; ext4_fsblk_t block; + struct blk_plug plug; int inodes_per_block, inode_offset; iloc->bh = NULL; - if (!ext4_valid_inum(sb, inode->i_ino)) - return -EIO; + if (ino < EXT4_ROOT_INO || + ino > le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count)) + return -EFSCORRUPTED; - iloc->block_group = (inode->i_ino - 1) / EXT4_INODES_PER_GROUP(sb); + iloc->block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb); gdp = ext4_get_group_desc(sb, iloc->block_group, NULL); if (!gdp) return -EIO; @@ -3753,168 +4819,221 @@ static int __ext4_get_inode_loc(struct inode *inode, * Figure out the offset within the block group inode table */ inodes_per_block = EXT4_SB(sb)->s_inodes_per_block; - inode_offset = ((inode->i_ino - 1) % + inode_offset = ((ino - 1) % EXT4_INODES_PER_GROUP(sb)); - block = ext4_inode_table(sb, gdp) + (inode_offset / inodes_per_block); iloc->offset = (inode_offset % inodes_per_block) * EXT4_INODE_SIZE(sb); + block = ext4_inode_table(sb, gdp); + if ((block <= le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) || + (block >= ext4_blocks_count(EXT4_SB(sb)->s_es))) { + ext4_error(sb, "Invalid inode table block %llu in " + "block_group %u", block, iloc->block_group); + return -EFSCORRUPTED; + } + block += (inode_offset / inodes_per_block); + bh = sb_getblk(sb, block); if (unlikely(!bh)) return -ENOMEM; - if (!buffer_uptodate(bh)) { - lock_buffer(bh); - - /* - * If the buffer has the write error flag, we have failed - * to write out another inode in the same block. In this - * case, we don't have to read the block because we may - * read the old inode data successfully. - */ - if (buffer_write_io_error(bh) && !buffer_uptodate(bh)) - set_buffer_uptodate(bh); + if (ext4_buffer_uptodate(bh)) + goto has_buffer; - if (buffer_uptodate(bh)) { - /* someone brought it uptodate while we waited */ - unlock_buffer(bh); - goto has_buffer; - } + lock_buffer(bh); + if (ext4_buffer_uptodate(bh)) { + /* Someone brought it uptodate while we waited */ + unlock_buffer(bh); + goto has_buffer; + } - /* - * If we have all information of the inode in memory and this - * is the only valid inode in the block, we need not read the - * block. - */ - if (in_mem) { - struct buffer_head *bitmap_bh; - int i, start; + /* + * If we have all information of the inode in memory and this + * is the only valid inode in the block, we need not read the + * block. + */ + if (inode && !ext4_test_inode_state(inode, EXT4_STATE_XATTR)) { + struct buffer_head *bitmap_bh; + int i, start; - start = inode_offset & ~(inodes_per_block - 1); + start = inode_offset & ~(inodes_per_block - 1); - /* Is the inode bitmap in cache? */ - bitmap_bh = sb_getblk(sb, ext4_inode_bitmap(sb, gdp)); - if (unlikely(!bitmap_bh)) - goto make_io; + /* Is the inode bitmap in cache? */ + bitmap_bh = sb_getblk(sb, ext4_inode_bitmap(sb, gdp)); + if (unlikely(!bitmap_bh)) + goto make_io; - /* - * If the inode bitmap isn't in cache then the - * optimisation may end up performing two reads instead - * of one, so skip it. - */ - if (!buffer_uptodate(bitmap_bh)) { - brelse(bitmap_bh); - goto make_io; - } - for (i = start; i < start + inodes_per_block; i++) { - if (i == inode_offset) - continue; - if (ext4_test_bit(i, bitmap_bh->b_data)) - break; - } + /* + * If the inode bitmap isn't in cache then the + * optimisation may end up performing two reads instead + * of one, so skip it. + */ + if (!buffer_uptodate(bitmap_bh)) { brelse(bitmap_bh); - if (i == start + inodes_per_block) { - /* all other inodes are free, so skip I/O */ - memset(bh->b_data, 0, bh->b_size); - set_buffer_uptodate(bh); - unlock_buffer(bh); - goto has_buffer; - } + goto make_io; + } + for (i = start; i < start + inodes_per_block; i++) { + if (i == inode_offset) + continue; + if (ext4_test_bit(i, bitmap_bh->b_data)) + break; + } + brelse(bitmap_bh); + if (i == start + inodes_per_block) { + struct ext4_inode *raw_inode = + (struct ext4_inode *) (bh->b_data + iloc->offset); + + /* all other inodes are free, so skip I/O */ + memset(bh->b_data, 0, bh->b_size); + if (!ext4_test_inode_state(inode, EXT4_STATE_NEW)) + ext4_fill_raw_inode(inode, raw_inode); + set_buffer_uptodate(bh); + unlock_buffer(bh); + goto has_buffer; } + } make_io: - /* - * If we need to do any I/O, try to pre-readahead extra - * blocks from the inode table. - */ - if (EXT4_SB(sb)->s_inode_readahead_blks) { - ext4_fsblk_t b, end, table; - unsigned num; - __u32 ra_blks = EXT4_SB(sb)->s_inode_readahead_blks; - - table = ext4_inode_table(sb, gdp); - /* s_inode_readahead_blks is always a power of 2 */ - b = block & ~((ext4_fsblk_t) ra_blks - 1); - if (table > b) - b = table; - end = b + ra_blks; - num = EXT4_INODES_PER_GROUP(sb); - if (ext4_has_group_desc_csum(sb)) - num -= ext4_itable_unused_count(sb, gdp); - table += num / inodes_per_block; - if (end > table) - end = table; - while (b <= end) - sb_breadahead(sb, b++); - } + /* + * If we need to do any I/O, try to pre-readahead extra + * blocks from the inode table. + */ + blk_start_plug(&plug); + if (EXT4_SB(sb)->s_inode_readahead_blks) { + ext4_fsblk_t b, end, table; + unsigned num; + __u32 ra_blks = EXT4_SB(sb)->s_inode_readahead_blks; + + table = ext4_inode_table(sb, gdp); + /* s_inode_readahead_blks is always a power of 2 */ + b = block & ~((ext4_fsblk_t) ra_blks - 1); + if (table > b) + b = table; + end = b + ra_blks; + num = EXT4_INODES_PER_GROUP(sb); + if (ext4_has_group_desc_csum(sb)) + num -= ext4_itable_unused_count(sb, gdp); + table += num / inodes_per_block; + if (end > table) + end = table; + while (b <= end) + ext4_sb_breadahead_unmovable(sb, b++); + } - /* - * There are other valid inodes in the buffer, this inode - * has in-inode xattrs, or we don't have this inode in memory. - * Read the block from disk. - */ - trace_ext4_load_inode(inode); - get_bh(bh); - bh->b_end_io = end_buffer_read_sync; - submit_bh(READ | REQ_META | REQ_PRIO, bh); - wait_on_buffer(bh); - if (!buffer_uptodate(bh)) { - EXT4_ERROR_INODE_BLOCK(inode, block, - "unable to read itable block"); - brelse(bh); - return -EIO; - } + /* + * There are other valid inodes in the buffer, this inode + * has in-inode xattrs, or we don't have this inode in memory. + * Read the block from disk. + */ + trace_ext4_load_inode(sb, ino); + ext4_read_bh_nowait(bh, REQ_META | REQ_PRIO, NULL, + ext4_simulate_fail(sb, EXT4_SIM_INODE_EIO)); + blk_finish_plug(&plug); + wait_on_buffer(bh); + if (!buffer_uptodate(bh)) { + if (ret_block) + *ret_block = block; + brelse(bh); + return -EIO; } has_buffer: iloc->bh = bh; return 0; } +static int __ext4_get_inode_loc_noinmem(struct inode *inode, + struct ext4_iloc *iloc) +{ + ext4_fsblk_t err_blk = 0; + int ret; + + ret = __ext4_get_inode_loc(inode->i_sb, inode->i_ino, NULL, iloc, + &err_blk); + + if (ret == -EIO) + ext4_error_inode_block(inode, err_blk, EIO, + "unable to read itable block"); + + return ret; +} + int ext4_get_inode_loc(struct inode *inode, struct ext4_iloc *iloc) { - /* We have all inode data except xattrs in memory here. */ - return __ext4_get_inode_loc(inode, iloc, - !ext4_test_inode_state(inode, EXT4_STATE_XATTR)); + ext4_fsblk_t err_blk = 0; + int ret; + + ret = __ext4_get_inode_loc(inode->i_sb, inode->i_ino, inode, iloc, + &err_blk); + + if (ret == -EIO) + ext4_error_inode_block(inode, err_blk, EIO, + "unable to read itable block"); + + return ret; +} + + +int ext4_get_fc_inode_loc(struct super_block *sb, unsigned long ino, + struct ext4_iloc *iloc) +{ + return __ext4_get_inode_loc(sb, ino, NULL, iloc, NULL); +} + +static bool ext4_should_enable_dax(struct inode *inode) +{ + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + + if (test_opt2(inode->i_sb, DAX_NEVER)) + return false; + if (!S_ISREG(inode->i_mode)) + return false; + if (ext4_should_journal_data(inode)) + return false; + if (ext4_has_inline_data(inode)) + return false; + if (ext4_test_inode_flag(inode, EXT4_INODE_ENCRYPT)) + return false; + if (ext4_test_inode_flag(inode, EXT4_INODE_VERITY)) + return false; + if (!test_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags)) + return false; + if (test_opt(inode->i_sb, DAX_ALWAYS)) + return true; + + return ext4_test_inode_flag(inode, EXT4_INODE_DAX); } -void ext4_set_inode_flags(struct inode *inode) +void ext4_set_inode_flags(struct inode *inode, bool init) { unsigned int flags = EXT4_I(inode)->i_flags; + unsigned int new_fl = 0; + + WARN_ON_ONCE(IS_DAX(inode) && init); - inode->i_flags &= ~(S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC); if (flags & EXT4_SYNC_FL) - inode->i_flags |= S_SYNC; + new_fl |= S_SYNC; if (flags & EXT4_APPEND_FL) - inode->i_flags |= S_APPEND; + new_fl |= S_APPEND; if (flags & EXT4_IMMUTABLE_FL) - inode->i_flags |= S_IMMUTABLE; + new_fl |= S_IMMUTABLE; if (flags & EXT4_NOATIME_FL) - inode->i_flags |= S_NOATIME; + new_fl |= S_NOATIME; if (flags & EXT4_DIRSYNC_FL) - inode->i_flags |= S_DIRSYNC; -} - -/* Propagate flags from i_flags to EXT4_I(inode)->i_flags */ -void ext4_get_inode_flags(struct ext4_inode_info *ei) -{ - unsigned int vfs_fl; - unsigned long old_fl, new_fl; - - do { - vfs_fl = ei->vfs_inode.i_flags; - old_fl = ei->i_flags; - new_fl = old_fl & ~(EXT4_SYNC_FL|EXT4_APPEND_FL| - EXT4_IMMUTABLE_FL|EXT4_NOATIME_FL| - EXT4_DIRSYNC_FL); - if (vfs_fl & S_SYNC) - new_fl |= EXT4_SYNC_FL; - if (vfs_fl & S_APPEND) - new_fl |= EXT4_APPEND_FL; - if (vfs_fl & S_IMMUTABLE) - new_fl |= EXT4_IMMUTABLE_FL; - if (vfs_fl & S_NOATIME) - new_fl |= EXT4_NOATIME_FL; - if (vfs_fl & S_DIRSYNC) - new_fl |= EXT4_DIRSYNC_FL; - } while (cmpxchg(&ei->i_flags, old_fl, new_fl) != old_fl); + new_fl |= S_DIRSYNC; + + /* Because of the way inode_set_flags() works we must preserve S_DAX + * here if already set. */ + new_fl |= (inode->i_flags & S_DAX); + if (init && ext4_should_enable_dax(inode)) + new_fl |= S_DAX; + + if (flags & EXT4_ENCRYPT_FL) + new_fl |= S_ENCRYPTED; + if (flags & EXT4_CASEFOLD_FL) + new_fl |= S_CASEFOLD; + if (flags & EXT4_VERITY_FL) + new_fl |= S_VERITY; + inode_set_flags(inode, new_fl, + S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC|S_DAX| + S_ENCRYPTED|S_CASEFOLD|S_VERITY); } static blkcnt_t ext4_inode_blocks(struct ext4_inode *raw_inode, @@ -3924,8 +5043,7 @@ static blkcnt_t ext4_inode_blocks(struct ext4_inode *raw_inode, struct inode *inode = &(ei->vfs_inode); struct super_block *sb = inode->i_sb; - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_HUGE_FILE)) { + if (ext4_has_feature_huge_file(sb)) { /* we are using combined 48 bit field */ i_blocks = ((u64)le16_to_cpu(raw_inode->i_blocks_high)) << 32 | le32_to_cpu(raw_inode->i_blocks_lo); @@ -3940,89 +5058,220 @@ static blkcnt_t ext4_inode_blocks(struct ext4_inode *raw_inode, } } -static inline void ext4_iget_extra_inode(struct inode *inode, +static inline int ext4_iget_extra_inode(struct inode *inode, struct ext4_inode *raw_inode, struct ext4_inode_info *ei) { __le32 *magic = (void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize; - if (*magic == cpu_to_le32(EXT4_XATTR_MAGIC)) { + + if (EXT4_INODE_HAS_XATTR_SPACE(inode) && + *magic == cpu_to_le32(EXT4_XATTR_MAGIC)) { + int err; + + err = xattr_check_inode(inode, IHDR(inode, raw_inode), + ITAIL(inode, raw_inode)); + if (err) + return err; + ext4_set_inode_state(inode, EXT4_STATE_XATTR); - ext4_find_inline_data_nolock(inode); + err = ext4_find_inline_data_nolock(inode); + if (!err && ext4_has_inline_data(inode)) + ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); + return err; } else EXT4_I(inode)->i_inline_off = 0; + return 0; +} + +int ext4_get_projid(struct inode *inode, kprojid_t *projid) +{ + if (!ext4_has_feature_project(inode->i_sb)) + return -EOPNOTSUPP; + *projid = EXT4_I(inode)->i_projid; + return 0; +} + +/* + * ext4 has self-managed i_version for ea inodes, it stores the lower 32bit of + * refcount in i_version, so use raw values if inode has EXT4_EA_INODE_FL flag + * set. + */ +static inline void ext4_inode_set_iversion_queried(struct inode *inode, u64 val) +{ + if (unlikely(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) + inode_set_iversion_raw(inode, val); + else + inode_set_iversion_queried(inode, val); +} + +static int check_igot_inode(struct inode *inode, ext4_iget_flags flags, + const char *function, unsigned int line) +{ + const char *err_str; + + if (flags & EXT4_IGET_EA_INODE) { + if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) { + err_str = "missing EA_INODE flag"; + goto error; + } + if (ext4_test_inode_state(inode, EXT4_STATE_XATTR) || + EXT4_I(inode)->i_file_acl) { + err_str = "ea_inode with extended attributes"; + goto error; + } + } else { + if ((EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) { + /* + * open_by_handle_at() could provide an old inode number + * that has since been reused for an ea_inode; this does + * not indicate filesystem corruption + */ + if (flags & EXT4_IGET_HANDLE) + return -ESTALE; + err_str = "unexpected EA_INODE flag"; + goto error; + } + } + if (is_bad_inode(inode) && !(flags & EXT4_IGET_BAD)) { + err_str = "unexpected bad inode w/o EXT4_IGET_BAD"; + goto error; + } + return 0; + +error: + ext4_error_inode(inode, function, line, 0, "%s", err_str); + return -EFSCORRUPTED; +} + +void ext4_set_inode_mapping_order(struct inode *inode) +{ + struct super_block *sb = inode->i_sb; + u16 min_order, max_order; + + max_order = EXT4_SB(sb)->s_max_folio_order; + if (!max_order) + return; + + min_order = EXT4_SB(sb)->s_min_folio_order; + if (!min_order && !S_ISREG(inode->i_mode)) + return; + + if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA)) + max_order = min_order; + + mapping_set_folio_order_range(inode->i_mapping, min_order, max_order); } -struct inode *ext4_iget(struct super_block *sb, unsigned long ino) +struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, + ext4_iget_flags flags, const char *function, + unsigned int line) { struct ext4_iloc iloc; struct ext4_inode *raw_inode; struct ext4_inode_info *ei; + struct ext4_super_block *es = EXT4_SB(sb)->s_es; struct inode *inode; journal_t *journal = EXT4_SB(sb)->s_journal; long ret; + loff_t size; int block; uid_t i_uid; gid_t i_gid; + projid_t i_projid; + + if ((!(flags & EXT4_IGET_SPECIAL) && is_special_ino(sb, ino)) || + (ino < EXT4_ROOT_INO) || + (ino > le32_to_cpu(es->s_inodes_count))) { + if (flags & EXT4_IGET_HANDLE) + return ERR_PTR(-ESTALE); + __ext4_error(sb, function, line, false, EFSCORRUPTED, 0, + "inode #%lu: comm %s: iget: illegal inode #", + ino, current->comm); + return ERR_PTR(-EFSCORRUPTED); + } inode = iget_locked(sb, ino); if (!inode) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) + if (!(inode_state_read_once(inode) & I_NEW)) { + ret = check_igot_inode(inode, flags, function, line); + if (ret) { + iput(inode); + return ERR_PTR(ret); + } return inode; + } ei = EXT4_I(inode); iloc.bh = NULL; - ret = __ext4_get_inode_loc(inode, &iloc, 0); + ret = __ext4_get_inode_loc_noinmem(inode, &iloc); if (ret < 0) goto bad_inode; raw_inode = ext4_raw_inode(&iloc); + if ((flags & EXT4_IGET_HANDLE) && + (raw_inode->i_links_count == 0) && (raw_inode->i_mode == 0)) { + ret = -ESTALE; + goto bad_inode; + } + if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) { ei->i_extra_isize = le16_to_cpu(raw_inode->i_extra_isize); if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize > - EXT4_INODE_SIZE(inode->i_sb)) { - EXT4_ERROR_INODE(inode, "bad extra_isize (%u != %u)", - EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize, - EXT4_INODE_SIZE(inode->i_sb)); - ret = -EIO; + EXT4_INODE_SIZE(inode->i_sb) || + (ei->i_extra_isize & 3)) { + ext4_error_inode(inode, function, line, 0, + "iget: bad extra_isize %u " + "(inode size %u)", + ei->i_extra_isize, + EXT4_INODE_SIZE(inode->i_sb)); + ret = -EFSCORRUPTED; goto bad_inode; } } else ei->i_extra_isize = 0; /* Precompute checksum seed for inode metadata */ - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) { + if (ext4_has_feature_metadata_csum(sb)) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); __u32 csum; __le32 inum = cpu_to_le32(inode->i_ino); __le32 gen = raw_inode->i_generation; - csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&inum, + csum = ext4_chksum(sbi->s_csum_seed, (__u8 *)&inum, sizeof(inum)); - ei->i_csum_seed = ext4_chksum(sbi, csum, (__u8 *)&gen, - sizeof(gen)); + ei->i_csum_seed = ext4_chksum(csum, (__u8 *)&gen, sizeof(gen)); } - if (!ext4_inode_csum_verify(inode, raw_inode, ei)) { - EXT4_ERROR_INODE(inode, "checksum invalid"); - ret = -EIO; + if ((!ext4_inode_csum_verify(inode, raw_inode, ei) || + ext4_simulate_fail(sb, EXT4_SIM_INODE_CRC)) && + (!(EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY))) { + ext4_error_inode_err(inode, function, line, 0, + EFSBADCRC, "iget: checksum invalid"); + ret = -EFSBADCRC; goto bad_inode; } inode->i_mode = le16_to_cpu(raw_inode->i_mode); i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low); i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low); + if (ext4_has_feature_project(sb) && + EXT4_INODE_SIZE(sb) > EXT4_GOOD_OLD_INODE_SIZE && + EXT4_FITS_IN_INODE(raw_inode, ei, i_projid)) + i_projid = (projid_t)le32_to_cpu(raw_inode->i_projid); + else + i_projid = EXT4_DEF_PROJID; + if (!(test_opt(inode->i_sb, NO_UID32))) { i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16; i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16; } i_uid_write(inode, i_uid); i_gid_write(inode, i_gid); + ei->i_projid = make_kprojid(&init_user_ns, i_projid); set_nlink(inode, le16_to_cpu(raw_inode->i_links_count)); - ext4_clear_state_flags(ei); /* Only relevant on 32-bit archs */ ei->i_inline_off = 0; ei->i_dir_start_lookup = 0; ei->i_dtime = le32_to_cpu(raw_inode->i_dtime); @@ -4032,11 +5281,16 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) * NeilBrown 1999oct15 */ if (inode->i_nlink == 0) { - if ((inode->i_mode == 0 || + if ((inode->i_mode == 0 || flags & EXT4_IGET_SPECIAL || !(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS)) && ino != EXT4_BOOT_LOADER_INO) { - /* this inode is deleted */ - ret = -ESTALE; + /* this inode is deleted or unallocated */ + if (flags & EXT4_IGET_SPECIAL) { + ext4_error_inode(inode, function, line, 0, + "iget: special inode unallocated"); + ret = -EFSCORRUPTED; + } else + ret = -ESTALE; goto bad_inode; } /* The only unlinked inodes we let through here have @@ -4047,12 +5301,41 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) * not initialized on a new filesystem. */ } ei->i_flags = le32_to_cpu(raw_inode->i_flags); + ext4_set_inode_flags(inode, true); + /* Detect invalid flag combination - can't have both inline data and extents */ + if (ext4_test_inode_flag(inode, EXT4_INODE_INLINE_DATA) && + ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { + ext4_error_inode(inode, function, line, 0, + "inode has both inline data and extents flags"); + ret = -EFSCORRUPTED; + goto bad_inode; + } inode->i_blocks = ext4_inode_blocks(raw_inode, ei); ei->i_file_acl = le32_to_cpu(raw_inode->i_file_acl_lo); - if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_64BIT)) + if (ext4_has_feature_64bit(sb)) ei->i_file_acl |= ((__u64)le16_to_cpu(raw_inode->i_file_acl_high)) << 32; - inode->i_size = ext4_isize(raw_inode); + inode->i_size = ext4_isize(sb, raw_inode); + size = i_size_read(inode); + if (size < 0 || size > ext4_get_maxbytes(inode)) { + ext4_error_inode(inode, function, line, 0, + "iget: bad i_size value: %lld", size); + ret = -EFSCORRUPTED; + goto bad_inode; + } + /* + * If dir_index is not enabled but there's dir with INDEX flag set, + * we'd normally treat htree data as empty space. But with metadata + * checksumming that corrupts checksums so forbid that. + */ + if (!ext4_has_feature_dir_index(sb) && + ext4_has_feature_metadata_csum(sb) && + ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) { + ext4_error_inode(inode, function, line, 0, + "iget: Dir with htree data on filesystem without dir_index feature."); + ret = -EFSCORRUPTED; + goto bad_inode; + } ei->i_disksize = inode->i_size; #ifdef CONFIG_QUOTA ei->i_reserved_quota = 0; @@ -4067,6 +5350,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) for (block = 0; block < EXT4_N_BLOCKS; block++) ei->i_data[block] = raw_inode->i_block[block]; INIT_LIST_HEAD(&ei->i_orphan); + ext4_fc_init_inode(&ei->vfs_inode); /* * Set transaction id's of transactions that have to be committed @@ -4096,44 +5380,50 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) { if (ei->i_extra_isize == 0) { /* The extra space is currently unused. Use it. */ + BUILD_BUG_ON(sizeof(struct ext4_inode) & 3); ei->i_extra_isize = sizeof(struct ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE; } else { - ext4_iget_extra_inode(inode, raw_inode, ei); + ret = ext4_iget_extra_inode(inode, raw_inode, ei); + if (ret) + goto bad_inode; } } - EXT4_INODE_GET_XTIME(i_ctime, inode, raw_inode); - EXT4_INODE_GET_XTIME(i_mtime, inode, raw_inode); - EXT4_INODE_GET_XTIME(i_atime, inode, raw_inode); + EXT4_INODE_GET_CTIME(inode, raw_inode); + EXT4_INODE_GET_ATIME(inode, raw_inode); + EXT4_INODE_GET_MTIME(inode, raw_inode); EXT4_EINODE_GET_XTIME(i_crtime, ei, raw_inode); - inode->i_version = le32_to_cpu(raw_inode->i_disk_version); - if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) { - if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi)) - inode->i_version |= - (__u64)(le32_to_cpu(raw_inode->i_version_hi)) << 32; + if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) { + u64 ivers = le32_to_cpu(raw_inode->i_disk_version); + + if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) { + if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi)) + ivers |= + (__u64)(le32_to_cpu(raw_inode->i_version_hi)) << 32; + } + ext4_inode_set_iversion_queried(inode, ivers); } ret = 0; if (ei->i_file_acl && - !ext4_data_block_valid(EXT4_SB(sb), ei->i_file_acl, 1)) { - EXT4_ERROR_INODE(inode, "bad extended attribute block %llu", + !ext4_inode_block_valid(inode, ei->i_file_acl, 1)) { + ext4_error_inode(inode, function, line, 0, + "iget: bad extended attribute block %llu", ei->i_file_acl); - ret = -EIO; + ret = -EFSCORRUPTED; goto bad_inode; } else if (!ext4_has_inline_data(inode)) { - if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { - if ((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || - (S_ISLNK(inode->i_mode) && - !ext4_inode_is_fast_symlink(inode)))) - /* Validate extent which is part of inode */ + /* validate the block references in the inode */ + if (!(EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY) && + (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || + (S_ISLNK(inode->i_mode) && + !ext4_inode_is_fast_symlink(inode)))) { + if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) ret = ext4_ext_check_inode(inode); - } else if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || - (S_ISLNK(inode->i_mode) && - !ext4_inode_is_fast_symlink(inode))) { - /* Validate block references which are part of inode */ - ret = ext4_ind_check_inode(inode); + else + ret = ext4_ind_check_inode(inode); } } if (ret) @@ -4147,13 +5437,32 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) inode->i_op = &ext4_dir_inode_operations; inode->i_fop = &ext4_dir_operations; } else if (S_ISLNK(inode->i_mode)) { - if (ext4_inode_is_fast_symlink(inode)) { + /* VFS does not allow setting these so must be corruption */ + if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) { + ext4_error_inode(inode, function, line, 0, + "iget: immutable or append flags " + "not allowed on symlinks"); + ret = -EFSCORRUPTED; + goto bad_inode; + } + if (IS_ENCRYPTED(inode)) { + inode->i_op = &ext4_encrypted_symlink_inode_operations; + } else if (ext4_inode_is_fast_symlink(inode)) { inode->i_op = &ext4_fast_symlink_inode_operations; - nd_terminate_link(ei->i_data, inode->i_size, - sizeof(ei->i_data) - 1); + if (inode->i_size == 0 || + inode->i_size >= sizeof(ei->i_data) || + strnlen((char *)ei->i_data, inode->i_size + 1) != + inode->i_size) { + ext4_error_inode(inode, function, line, 0, + "invalid fast symlink length %llu", + (unsigned long long)inode->i_size); + ret = -EFSCORRUPTED; + goto bad_inode; + } + inode_set_cached_link(inode, (char *)ei->i_data, + inode->i_size); } else { inode->i_op = &ext4_symlink_inode_operations; - ext4_set_aops(inode); } } else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) || S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) { @@ -4167,12 +5476,37 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) } else if (ino == EXT4_BOOT_LOADER_INO) { make_bad_inode(inode); } else { - ret = -EIO; - EXT4_ERROR_INODE(inode, "bogus i_mode (%o)", inode->i_mode); + ret = -EFSCORRUPTED; + ext4_error_inode(inode, function, line, 0, + "iget: bogus i_mode (%o)", inode->i_mode); goto bad_inode; } + if (IS_CASEFOLDED(inode) && !ext4_has_feature_casefold(inode->i_sb)) { + ext4_error_inode(inode, function, line, 0, + "casefold flag without casefold feature"); + ret = -EFSCORRUPTED; + goto bad_inode; + } + + ext4_set_inode_mapping_order(inode); + + ret = check_igot_inode(inode, flags, function, line); + /* + * -ESTALE here means there is nothing inherently wrong with the inode, + * it's just not an inode we can return for an fhandle lookup. + */ + if (ret == -ESTALE) { + brelse(iloc.bh); + unlock_new_inode(inode); + iput(inode); + return ERR_PTR(-ESTALE); + } + if (ret) + goto bad_inode; brelse(iloc.bh); - ext4_set_inode_flags(inode); + /* Initialize the "no ACL's" state for the simple cases */ + if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR) && !ei->i_file_acl) + cache_no_acl(inode); unlock_new_inode(inode); return inode; @@ -4182,43 +5516,64 @@ bad_inode: return ERR_PTR(ret); } -static int ext4_inode_blocks_set(handle_t *handle, - struct ext4_inode *raw_inode, - struct ext4_inode_info *ei) +static void __ext4_update_other_inode_time(struct super_block *sb, + unsigned long orig_ino, + unsigned long ino, + struct ext4_inode *raw_inode) { - struct inode *inode = &(ei->vfs_inode); - u64 i_blocks = inode->i_blocks; - struct super_block *sb = inode->i_sb; + struct inode *inode; - if (i_blocks <= ~0U) { - /* - * i_blocks can be represented in a 32 bit variable - * as multiple of 512 bytes - */ - raw_inode->i_blocks_lo = cpu_to_le32(i_blocks); - raw_inode->i_blocks_high = 0; - ext4_clear_inode_flag(inode, EXT4_INODE_HUGE_FILE); - return 0; + inode = find_inode_by_ino_rcu(sb, ino); + if (!inode) + return; + + if (!inode_is_dirtytime_only(inode)) + return; + + spin_lock(&inode->i_lock); + if (inode_is_dirtytime_only(inode)) { + struct ext4_inode_info *ei = EXT4_I(inode); + + inode_state_clear(inode, I_DIRTY_TIME); + spin_unlock(&inode->i_lock); + + spin_lock(&ei->i_raw_lock); + EXT4_INODE_SET_CTIME(inode, raw_inode); + EXT4_INODE_SET_MTIME(inode, raw_inode); + EXT4_INODE_SET_ATIME(inode, raw_inode); + ext4_inode_csum_set(inode, raw_inode, ei); + spin_unlock(&ei->i_raw_lock); + trace_ext4_other_inode_update_time(inode, orig_ino); + return; } - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_HUGE_FILE)) - return -EFBIG; + spin_unlock(&inode->i_lock); +} - if (i_blocks <= 0xffffffffffffULL) { - /* - * i_blocks can be represented in a 48 bit variable - * as multiple of 512 bytes - */ - raw_inode->i_blocks_lo = cpu_to_le32(i_blocks); - raw_inode->i_blocks_high = cpu_to_le16(i_blocks >> 32); - ext4_clear_inode_flag(inode, EXT4_INODE_HUGE_FILE); - } else { - ext4_set_inode_flag(inode, EXT4_INODE_HUGE_FILE); - /* i_block is stored in file system block size */ - i_blocks = i_blocks >> (inode->i_blkbits - 9); - raw_inode->i_blocks_lo = cpu_to_le32(i_blocks); - raw_inode->i_blocks_high = cpu_to_le16(i_blocks >> 32); +/* + * Opportunistically update the other time fields for other inodes in + * the same inode table block. + */ +static void ext4_update_other_inodes_time(struct super_block *sb, + unsigned long orig_ino, char *buf) +{ + unsigned long ino; + int i, inodes_per_block = EXT4_SB(sb)->s_inodes_per_block; + int inode_size = EXT4_INODE_SIZE(sb); + + /* + * Calculate the first inode in the inode table block. Inode + * numbers are one-based. That is, the first inode in a block + * (assuming 4k blocks and 256 byte inodes) is (n*16 + 1). + */ + ino = ((orig_ino - 1) & ~(inodes_per_block - 1)) + 1; + rcu_read_lock(); + for (i = 0; i < inodes_per_block; i++, ino++, buf += inode_size) { + if (ino == orig_ino) + continue; + __ext4_update_other_inode_time(sb, orig_ino, ino, + (struct ext4_inode *)buf); } - return 0; + rcu_read_unlock(); } /* @@ -4235,119 +5590,63 @@ static int ext4_do_update_inode(handle_t *handle, struct ext4_inode *raw_inode = ext4_raw_inode(iloc); struct ext4_inode_info *ei = EXT4_I(inode); struct buffer_head *bh = iloc->bh; - int err = 0, rc, block; - int need_datasync = 0; - uid_t i_uid; - gid_t i_gid; + struct super_block *sb = inode->i_sb; + int err; + int need_datasync = 0, set_large_file = 0; + + spin_lock(&ei->i_raw_lock); - /* For fields not not tracking in the in-memory inode, - * initialise them to zero for new inodes. */ + /* + * For fields not tracked in the in-memory inode, initialise them + * to zero for new inodes. + */ if (ext4_test_inode_state(inode, EXT4_STATE_NEW)) memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size); - ext4_get_inode_flags(ei); - raw_inode->i_mode = cpu_to_le16(inode->i_mode); - i_uid = i_uid_read(inode); - i_gid = i_gid_read(inode); - if (!(test_opt(inode->i_sb, NO_UID32))) { - raw_inode->i_uid_low = cpu_to_le16(low_16_bits(i_uid)); - raw_inode->i_gid_low = cpu_to_le16(low_16_bits(i_gid)); -/* - * Fix up interoperability with old kernels. Otherwise, old inodes get - * re-used with the upper 16 bits of the uid/gid intact - */ - if (!ei->i_dtime) { - raw_inode->i_uid_high = - cpu_to_le16(high_16_bits(i_uid)); - raw_inode->i_gid_high = - cpu_to_le16(high_16_bits(i_gid)); - } else { - raw_inode->i_uid_high = 0; - raw_inode->i_gid_high = 0; - } - } else { - raw_inode->i_uid_low = cpu_to_le16(fs_high2lowuid(i_uid)); - raw_inode->i_gid_low = cpu_to_le16(fs_high2lowgid(i_gid)); - raw_inode->i_uid_high = 0; - raw_inode->i_gid_high = 0; - } - raw_inode->i_links_count = cpu_to_le16(inode->i_nlink); - - EXT4_INODE_SET_XTIME(i_ctime, inode, raw_inode); - EXT4_INODE_SET_XTIME(i_mtime, inode, raw_inode); - EXT4_INODE_SET_XTIME(i_atime, inode, raw_inode); - EXT4_EINODE_SET_XTIME(i_crtime, ei, raw_inode); - - if (ext4_inode_blocks_set(handle, raw_inode, ei)) - goto out_brelse; - raw_inode->i_dtime = cpu_to_le32(ei->i_dtime); - raw_inode->i_flags = cpu_to_le32(ei->i_flags & 0xFFFFFFFF); - if (EXT4_SB(inode->i_sb)->s_es->s_creator_os != - cpu_to_le32(EXT4_OS_HURD)) - raw_inode->i_file_acl_high = - cpu_to_le16(ei->i_file_acl >> 32); - raw_inode->i_file_acl_lo = cpu_to_le32(ei->i_file_acl); - if (ei->i_disksize != ext4_isize(raw_inode)) { - ext4_isize_set(raw_inode, ei->i_disksize); + if (READ_ONCE(ei->i_disksize) != ext4_isize(inode->i_sb, raw_inode)) need_datasync = 1; - } if (ei->i_disksize > 0x7fffffffULL) { - struct super_block *sb = inode->i_sb; - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_LARGE_FILE) || - EXT4_SB(sb)->s_es->s_rev_level == - cpu_to_le32(EXT4_GOOD_OLD_REV)) { - /* If this is the first large file - * created, add a flag to the superblock. - */ - err = ext4_journal_get_write_access(handle, - EXT4_SB(sb)->s_sbh); - if (err) - goto out_brelse; - ext4_update_dynamic_rev(sb); - EXT4_SET_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_LARGE_FILE); - ext4_handle_sync(handle); - err = ext4_handle_dirty_super(handle, sb); - } - } - raw_inode->i_generation = cpu_to_le32(inode->i_generation); - if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) { - if (old_valid_dev(inode->i_rdev)) { - raw_inode->i_block[0] = - cpu_to_le32(old_encode_dev(inode->i_rdev)); - raw_inode->i_block[1] = 0; - } else { - raw_inode->i_block[0] = 0; - raw_inode->i_block[1] = - cpu_to_le32(new_encode_dev(inode->i_rdev)); - raw_inode->i_block[2] = 0; - } - } else if (!ext4_has_inline_data(inode)) { - for (block = 0; block < EXT4_N_BLOCKS; block++) - raw_inode->i_block[block] = ei->i_data[block]; + if (!ext4_has_feature_large_file(sb) || + EXT4_SB(sb)->s_es->s_rev_level == cpu_to_le32(EXT4_GOOD_OLD_REV)) + set_large_file = 1; } - raw_inode->i_disk_version = cpu_to_le32(inode->i_version); - if (ei->i_extra_isize) { - if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi)) - raw_inode->i_version_hi = - cpu_to_le32(inode->i_version >> 32); - raw_inode->i_extra_isize = cpu_to_le16(ei->i_extra_isize); + err = ext4_fill_raw_inode(inode, raw_inode); + spin_unlock(&ei->i_raw_lock); + if (err) { + EXT4_ERROR_INODE(inode, "corrupted inode contents"); + goto out_brelse; } - ext4_inode_csum_set(inode, raw_inode, ei); + if (inode->i_sb->s_flags & SB_LAZYTIME) + ext4_update_other_inodes_time(inode->i_sb, inode->i_ino, + bh->b_data); BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata"); - rc = ext4_handle_dirty_metadata(handle, NULL, bh); - if (!err) - err = rc; + err = ext4_handle_dirty_metadata(handle, NULL, bh); + if (err) + goto out_error; ext4_clear_inode_state(inode, EXT4_STATE_NEW); - + if (set_large_file) { + BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get write access"); + err = ext4_journal_get_write_access(handle, sb, + EXT4_SB(sb)->s_sbh, + EXT4_JTR_NONE); + if (err) + goto out_error; + lock_buffer(EXT4_SB(sb)->s_sbh); + ext4_set_feature_large_file(sb); + ext4_superblock_csum_set(sb); + unlock_buffer(EXT4_SB(sb)->s_sbh); + ext4_handle_sync(handle); + err = ext4_handle_dirty_metadata(handle, NULL, + EXT4_SB(sb)->s_sbh); + } ext4_update_inode_fsync_trans(handle, inode, need_datasync); +out_error: + ext4_std_error(inode->i_sb, err); out_brelse: brelse(bh); - ext4_std_error(inode->i_sb, err); return err; } @@ -4356,21 +5655,20 @@ out_brelse: * * We are called from a few places: * - * - Within generic_file_write() for O_SYNC files. + * - Within generic_file_aio_write() -> generic_write_sync() for O_SYNC files. * Here, there will be no transaction running. We wait for any running * transaction to commit. * - * - Within sys_sync(), kupdate and such. - * We wait on commit, if tol to. + * - Within flush work (sys_sync(), kupdate and such). + * We wait on commit, if told to. * - * - Within prune_icache() (PF_MEMALLOC == true) - * Here we simply return. We can't afford to block kswapd on the - * journal commit. + * - Within iput_final() -> write_inode_now() + * We wait on commit, if told to. * * In all cases it is actually safe for us to return without doing anything, * because the inode has been copied into a raw inode buffer in - * ext4_mark_inode_dirty(). This is a correctness thing for O_SYNC and for - * knfsd. + * ext4_mark_inode_dirty(). This is a correctness thing for WB_SYNC_ALL + * writeback. * * Note that we are absolutely dependent upon all inode dirtiers doing the * right thing: they *must* call mark_inode_dirty() after dirtying info in @@ -4382,39 +5680,53 @@ out_brelse: * stuff(); * inode->i_size = expr; * - * is in error because a kswapd-driven write_inode() could occur while - * `stuff()' is running, and the new i_size will be lost. Plus the inode - * will no longer be on the superblock's dirty inode list. + * is in error because write_inode() could occur while `stuff()' is running, + * and the new i_size will be lost. Plus the inode will no longer be on the + * superblock's dirty inode list. */ int ext4_write_inode(struct inode *inode, struct writeback_control *wbc) { int err; - if (current->flags & PF_MEMALLOC) + if (WARN_ON_ONCE(current->flags & PF_MEMALLOC)) return 0; + err = ext4_emergency_state(inode->i_sb); + if (unlikely(err)) + return err; + if (EXT4_SB(inode->i_sb)->s_journal) { if (ext4_journal_current_handle()) { - jbd_debug(1, "called recursively, non-PF_MEMALLOC!\n"); + ext4_debug("called recursively, non-PF_MEMALLOC!\n"); dump_stack(); return -EIO; } - if (wbc->sync_mode != WB_SYNC_ALL) + /* + * No need to force transaction in WB_SYNC_NONE mode. Also + * ext4_sync_fs() will force the commit after everything is + * written. + */ + if (wbc->sync_mode != WB_SYNC_ALL || wbc->for_sync) return 0; - err = ext4_force_commit(inode->i_sb); + err = ext4_fc_commit(EXT4_SB(inode->i_sb)->s_journal, + EXT4_I(inode)->i_sync_tid); } else { struct ext4_iloc iloc; - err = __ext4_get_inode_loc(inode, &iloc, 0); + err = __ext4_get_inode_loc_noinmem(inode, &iloc); if (err) return err; - if (wbc->sync_mode == WB_SYNC_ALL) + /* + * sync(2) will flush the whole buffer cache. No need to do + * it here separately for each inode. + */ + if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync) sync_dirty_buffer(iloc.bh); if (buffer_req(iloc.bh) && !buffer_uptodate(iloc.bh)) { - EXT4_ERROR_INODE_BLOCK(inode, iloc.bh->b_blocknr, - "IO error syncing inode"); + ext4_error_inode_block(inode, iloc.bh->b_blocknr, EIO, + "IO error syncing inode"); err = -EIO; } brelse(iloc.bh); @@ -4423,43 +5735,49 @@ int ext4_write_inode(struct inode *inode, struct writeback_control *wbc) } /* - * In data=journal mode ext4_journalled_invalidatepage() may fail to invalidate - * buffers that are attached to a page stradding i_size and are undergoing + * In data=journal mode ext4_journalled_invalidate_folio() may fail to invalidate + * buffers that are attached to a folio straddling i_size and are undergoing * commit. In that case we have to wait for commit to finish and try again. */ static void ext4_wait_for_tail_page_commit(struct inode *inode) { - struct page *page; unsigned offset; journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; - tid_t commit_tid = 0; + tid_t commit_tid; int ret; + bool has_transaction; - offset = inode->i_size & (PAGE_CACHE_SIZE - 1); + offset = inode->i_size & (PAGE_SIZE - 1); /* - * All buffers in the last page remain valid? Then there's nothing to - * do. We do the check mainly to optimize the common PAGE_CACHE_SIZE == - * blocksize case + * If the folio is fully truncated, we don't need to wait for any commit + * (and we even should not as __ext4_journalled_invalidate_folio() may + * strip all buffers from the folio but keep the folio dirty which can then + * confuse e.g. concurrent ext4_writepages() seeing dirty folio without + * buffers). Also we don't need to wait for any commit if all buffers in + * the folio remain valid. This is most beneficial for the common case of + * blocksize == PAGESIZE. */ - if (offset > PAGE_CACHE_SIZE - (1 << inode->i_blkbits)) + if (!offset || offset > (PAGE_SIZE - i_blocksize(inode))) return; while (1) { - page = find_lock_page(inode->i_mapping, - inode->i_size >> PAGE_CACHE_SHIFT); - if (!page) + struct folio *folio = filemap_lock_folio(inode->i_mapping, + inode->i_size >> PAGE_SHIFT); + if (IS_ERR(folio)) return; - ret = __ext4_journalled_invalidatepage(page, offset, - PAGE_CACHE_SIZE - offset); - unlock_page(page); - page_cache_release(page); + ret = __ext4_journalled_invalidate_folio(folio, offset, + folio_size(folio) - offset); + folio_unlock(folio); + folio_put(folio); if (ret != -EBUSY) return; - commit_tid = 0; + has_transaction = false; read_lock(&journal->j_state_lock); - if (journal->j_committing_transaction) + if (journal->j_committing_transaction) { commit_tid = journal->j_committing_transaction->t_tid; + has_transaction = true; + } read_unlock(&journal->j_state_lock); - if (commit_tid) + if (has_transaction) jbd2_log_wait_commit(journal, commit_tid); } } @@ -4486,23 +5804,49 @@ static void ext4_wait_for_tail_page_commit(struct inode *inode) * transaction are already on disk (truncate waits for pages under * writeback). * - * Called with inode->i_mutex down. + * Called with inode->i_rwsem down. */ -int ext4_setattr(struct dentry *dentry, struct iattr *attr) +int ext4_setattr(struct mnt_idmap *idmap, struct dentry *dentry, + struct iattr *attr) { - struct inode *inode = dentry->d_inode; + struct inode *inode = d_inode(dentry); int error, rc = 0; int orphan = 0; const unsigned int ia_valid = attr->ia_valid; + bool inc_ivers = true; + + error = ext4_emergency_state(inode->i_sb); + if (unlikely(error)) + return error; + + if (unlikely(IS_IMMUTABLE(inode))) + return -EPERM; + + if (unlikely(IS_APPEND(inode) && + (ia_valid & (ATTR_MODE | ATTR_UID | + ATTR_GID | ATTR_TIMES_SET)))) + return -EPERM; + + error = setattr_prepare(idmap, dentry, attr); + if (error) + return error; + + error = fscrypt_prepare_setattr(dentry, attr); + if (error) + return error; - error = inode_change_ok(inode, attr); + error = fsverity_prepare_setattr(dentry, attr); if (error) return error; - if (is_quota_modification(inode, attr)) - dquot_initialize(inode); - if ((ia_valid & ATTR_UID && !uid_eq(attr->ia_uid, inode->i_uid)) || - (ia_valid & ATTR_GID && !gid_eq(attr->ia_gid, inode->i_gid))) { + if (is_quota_modification(idmap, inode, attr)) { + error = dquot_initialize(inode); + if (error) + return error; + } + + if (i_uid_needs_update(idmap, attr, inode) || + i_gid_needs_update(idmap, attr, inode)) { handle_t *handle; /* (user+group)*(old+new) structure, inode write (sb, @@ -4514,99 +5858,165 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) error = PTR_ERR(handle); goto err_out; } - error = dquot_transfer(inode, attr); + + /* dquot_transfer() calls back ext4_get_inode_usage() which + * counts xattr inode references. + */ + down_read(&EXT4_I(inode)->xattr_sem); + error = dquot_transfer(idmap, inode, attr); + up_read(&EXT4_I(inode)->xattr_sem); + if (error) { ext4_journal_stop(handle); return error; } /* Update corresponding info in inode so that everything is in * one transaction */ - if (attr->ia_valid & ATTR_UID) - inode->i_uid = attr->ia_uid; - if (attr->ia_valid & ATTR_GID) - inode->i_gid = attr->ia_gid; + i_uid_update(idmap, attr, inode); + i_gid_update(idmap, attr, inode); error = ext4_mark_inode_dirty(handle, inode); ext4_journal_stop(handle); + if (unlikely(error)) { + return error; + } } if (attr->ia_valid & ATTR_SIZE) { + handle_t *handle; + loff_t oldsize = inode->i_size; + loff_t old_disksize; + int shrink = (attr->ia_size < inode->i_size); if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); - if (attr->ia_size > sbi->s_bitmap_maxbytes) + if (attr->ia_size > sbi->s_bitmap_maxbytes) { return -EFBIG; + } } - } - - if (S_ISREG(inode->i_mode) && - attr->ia_valid & ATTR_SIZE && - (attr->ia_size < inode->i_size)) { - handle_t *handle; - - handle = ext4_journal_start(inode, EXT4_HT_INODE, 3); - if (IS_ERR(handle)) { - error = PTR_ERR(handle); - goto err_out; - } - if (ext4_handle_valid(handle)) { - error = ext4_orphan_add(handle, inode); - orphan = 1; + if (!S_ISREG(inode->i_mode)) { + return -EINVAL; } - EXT4_I(inode)->i_disksize = attr->ia_size; - rc = ext4_mark_inode_dirty(handle, inode); - if (!error) - error = rc; - ext4_journal_stop(handle); - if (ext4_should_order_data(inode)) { - error = ext4_begin_ordered_truncate(inode, + if (attr->ia_size == inode->i_size) + inc_ivers = false; + + if (shrink) { + if (ext4_should_order_data(inode)) { + error = ext4_begin_ordered_truncate(inode, attr->ia_size); - if (error) { - /* Do as much error cleanup as possible */ - handle = ext4_journal_start(inode, - EXT4_HT_INODE, 3); - if (IS_ERR(handle)) { - ext4_orphan_del(NULL, inode); + if (error) goto err_out; - } - ext4_orphan_del(handle, inode); - orphan = 0; - ext4_journal_stop(handle); - goto err_out; } + /* + * Blocks are going to be removed from the inode. Wait + * for dio in flight. + */ + inode_dio_wait(inode); + } + + filemap_invalidate_lock(inode->i_mapping); + + rc = ext4_break_layouts(inode); + if (rc) { + filemap_invalidate_unlock(inode->i_mapping); + goto err_out; } - } - if (attr->ia_valid & ATTR_SIZE) { if (attr->ia_size != inode->i_size) { - loff_t oldsize = inode->i_size; + /* attach jbd2 jinode for EOF folio tail zeroing */ + if (attr->ia_size & (inode->i_sb->s_blocksize - 1) || + oldsize & (inode->i_sb->s_blocksize - 1)) { + error = ext4_inode_attach_jinode(inode); + if (error) + goto out_mmap_sem; + } - i_size_write(inode, attr->ia_size); + handle = ext4_journal_start(inode, EXT4_HT_INODE, 3); + if (IS_ERR(handle)) { + error = PTR_ERR(handle); + goto out_mmap_sem; + } + if (ext4_handle_valid(handle) && shrink) { + error = ext4_orphan_add(handle, inode); + orphan = 1; + } /* - * Blocks are going to be removed from the inode. Wait - * for dio in flight. Temporarily disable - * dioread_nolock to prevent livelock. + * Update c/mtime and tail zero the EOF folio on + * truncate up. ext4_truncate() handles the shrink case + * below. */ - if (orphan) { - if (!ext4_should_journal_data(inode)) { - ext4_inode_block_unlocked_dio(inode); - inode_dio_wait(inode); - ext4_inode_resume_unlocked_dio(inode); - } else - ext4_wait_for_tail_page_commit(inode); + if (!shrink) { + inode_set_mtime_to_ts(inode, + inode_set_ctime_current(inode)); + if (oldsize & (inode->i_sb->s_blocksize - 1)) + ext4_block_truncate_page(handle, + inode->i_mapping, oldsize); } + + if (shrink) + ext4_fc_track_range(handle, inode, + (attr->ia_size > 0 ? attr->ia_size - 1 : 0) >> + inode->i_sb->s_blocksize_bits, + EXT_MAX_BLOCKS - 1); + else + ext4_fc_track_range( + handle, inode, + (oldsize > 0 ? oldsize - 1 : oldsize) >> + inode->i_sb->s_blocksize_bits, + (attr->ia_size > 0 ? attr->ia_size - 1 : 0) >> + inode->i_sb->s_blocksize_bits); + + down_write(&EXT4_I(inode)->i_data_sem); + old_disksize = EXT4_I(inode)->i_disksize; + EXT4_I(inode)->i_disksize = attr->ia_size; + /* - * Truncate pagecache after we've waited for commit - * in data=journal mode to make pages freeable. + * We have to update i_size under i_data_sem together + * with i_disksize to avoid races with writeback code + * running ext4_wb_update_i_disksize(). */ - truncate_pagecache(inode, oldsize, inode->i_size); + if (!error) + i_size_write(inode, attr->ia_size); + else + EXT4_I(inode)->i_disksize = old_disksize; + up_write(&EXT4_I(inode)->i_data_sem); + rc = ext4_mark_inode_dirty(handle, inode); + if (!error) + error = rc; + ext4_journal_stop(handle); + if (error) + goto out_mmap_sem; + if (!shrink) { + pagecache_isize_extended(inode, oldsize, + inode->i_size); + } else if (ext4_should_journal_data(inode)) { + ext4_wait_for_tail_page_commit(inode); + } + } + + /* + * Truncate pagecache after we've waited for commit + * in data=journal mode to make pages freeable. + */ + truncate_pagecache(inode, inode->i_size); + /* + * Call ext4_truncate() even if i_size didn't change to + * truncate possible preallocated blocks. + */ + if (attr->ia_size <= oldsize) { + rc = ext4_truncate(inode); + if (rc) + error = rc; } - ext4_truncate(inode); +out_mmap_sem: + filemap_invalidate_unlock(inode->i_mapping); } - if (!rc) { - setattr_copy(inode, attr); + if (!error) { + if (inc_ivers) + inode_inc_iversion(inode); + setattr_copy(idmap, inode, attr); mark_inode_dirty(inode); } @@ -4617,24 +6027,123 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) if (orphan && inode->i_nlink) ext4_orphan_del(NULL, inode); - if (!rc && (ia_valid & ATTR_MODE)) - rc = ext4_acl_chmod(inode); + if (!error && (ia_valid & ATTR_MODE)) + rc = posix_acl_chmod(idmap, dentry, inode->i_mode); err_out: - ext4_std_error(inode->i_sb, error); + if (error) + ext4_std_error(inode->i_sb, error); if (!error) error = rc; return error; } -int ext4_getattr(struct vfsmount *mnt, struct dentry *dentry, - struct kstat *stat) +u32 ext4_dio_alignment(struct inode *inode) { - struct inode *inode; - unsigned long long delalloc_blocks; + if (fsverity_active(inode)) + return 0; + if (ext4_should_journal_data(inode)) + return 0; + if (ext4_has_inline_data(inode)) + return 0; + if (IS_ENCRYPTED(inode)) { + if (!fscrypt_dio_supported(inode)) + return 0; + return i_blocksize(inode); + } + return 1; /* use the iomap defaults */ +} + +int ext4_getattr(struct mnt_idmap *idmap, const struct path *path, + struct kstat *stat, u32 request_mask, unsigned int query_flags) +{ + struct inode *inode = d_inode(path->dentry); + struct ext4_inode *raw_inode; + struct ext4_inode_info *ei = EXT4_I(inode); + unsigned int flags; + + if ((request_mask & STATX_BTIME) && + EXT4_FITS_IN_INODE(raw_inode, ei, i_crtime)) { + stat->result_mask |= STATX_BTIME; + stat->btime.tv_sec = ei->i_crtime.tv_sec; + stat->btime.tv_nsec = ei->i_crtime.tv_nsec; + } + + /* + * Return the DIO alignment restrictions if requested. We only return + * this information when requested, since on encrypted files it might + * take a fair bit of work to get if the file wasn't opened recently. + */ + if ((request_mask & STATX_DIOALIGN) && S_ISREG(inode->i_mode)) { + u32 dio_align = ext4_dio_alignment(inode); + + stat->result_mask |= STATX_DIOALIGN; + if (dio_align == 1) { + struct block_device *bdev = inode->i_sb->s_bdev; + + /* iomap defaults */ + stat->dio_mem_align = bdev_dma_alignment(bdev) + 1; + stat->dio_offset_align = bdev_logical_block_size(bdev); + } else { + stat->dio_mem_align = dio_align; + stat->dio_offset_align = dio_align; + } + } + + if ((request_mask & STATX_WRITE_ATOMIC) && S_ISREG(inode->i_mode)) { + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + unsigned int awu_min = 0, awu_max = 0; + + if (ext4_inode_can_atomic_write(inode)) { + awu_min = sbi->s_awu_min; + awu_max = sbi->s_awu_max; + } + + generic_fill_statx_atomic_writes(stat, awu_min, awu_max, 0); + } + + flags = ei->i_flags & EXT4_FL_USER_VISIBLE; + if (flags & EXT4_APPEND_FL) + stat->attributes |= STATX_ATTR_APPEND; + if (flags & EXT4_COMPR_FL) + stat->attributes |= STATX_ATTR_COMPRESSED; + if (flags & EXT4_ENCRYPT_FL) + stat->attributes |= STATX_ATTR_ENCRYPTED; + if (flags & EXT4_IMMUTABLE_FL) + stat->attributes |= STATX_ATTR_IMMUTABLE; + if (flags & EXT4_NODUMP_FL) + stat->attributes |= STATX_ATTR_NODUMP; + if (flags & EXT4_VERITY_FL) + stat->attributes |= STATX_ATTR_VERITY; + + stat->attributes_mask |= (STATX_ATTR_APPEND | + STATX_ATTR_COMPRESSED | + STATX_ATTR_ENCRYPTED | + STATX_ATTR_IMMUTABLE | + STATX_ATTR_NODUMP | + STATX_ATTR_VERITY); + + generic_fillattr(idmap, request_mask, inode, stat); + return 0; +} + +int ext4_file_getattr(struct mnt_idmap *idmap, + const struct path *path, struct kstat *stat, + u32 request_mask, unsigned int query_flags) +{ + struct inode *inode = d_inode(path->dentry); + u64 delalloc_blocks; + + ext4_getattr(idmap, path, stat, request_mask, query_flags); - inode = dentry->d_inode; - generic_fillattr(inode, stat); + /* + * If there is inline data in the inode, the inode will normally not + * have data blocks allocated (it may have an external xattr block). + * Report at least one sector for such files, so tools like tar, rsync, + * others don't incorrectly think the file is completely sparse. + */ + if (unlikely(ext4_has_inline_data(inode))) + stat->blocks += (stat->size + 511) >> 9; /* * We can't update i_blocks if the block allocation is delayed @@ -4647,9 +6156,8 @@ int ext4_getattr(struct vfsmount *mnt, struct dentry *dentry, * blocks for this file. */ delalloc_blocks = EXT4_C2B(EXT4_SB(inode->i_sb), - EXT4_I(inode)->i_reserved_data_blocks); - - stat->blocks += delalloc_blocks << (inode->i_sb->s_blocksize_bits-9); + EXT4_I(inode)->i_reserved_data_blocks); + stat->blocks += delalloc_blocks << (inode->i_sb->s_blocksize_bits - 9); return 0; } @@ -4672,22 +6180,19 @@ static int ext4_index_trans_blocks(struct inode *inode, int lblocks, * * Also account for superblock, inode, quota and xattr blocks */ -static int ext4_meta_trans_blocks(struct inode *inode, int lblocks, - int pextents) +int ext4_meta_trans_blocks(struct inode *inode, int lblocks, int pextents) { ext4_group_t groups, ngroups = ext4_get_groups_count(inode->i_sb); int gdpblocks; int idxblocks; - int ret = 0; + int ret; /* - * How many index blocks need to touch to map @lblocks logical blocks - * to @pextents physical extents? + * How many index and leaf blocks need to touch to map @lblocks + * logical blocks to @pextents physical extents? */ idxblocks = ext4_index_trans_blocks(inode, lblocks, pextents); - ret = idxblocks; - /* * Now let's see how many group bitmaps and group descriptors need * to account @@ -4700,7 +6205,7 @@ static int ext4_meta_trans_blocks(struct inode *inode, int lblocks, gdpblocks = EXT4_SB(inode->i_sb)->s_gdb_count; /* bitmaps and block group descriptor blocks */ - ret += groups + gdpblocks; + ret = idxblocks + groups + gdpblocks; /* Blocks for super block, inode, quota and xattr blocks */ ret += EXT4_META_TRANS_BLOCKS(inode->i_sb); @@ -4709,25 +6214,19 @@ static int ext4_meta_trans_blocks(struct inode *inode, int lblocks, } /* - * Calculate the total number of credits to reserve to fit - * the modification of a single pages into a single transaction, - * which may include multiple chunks of block allocations. - * - * This could be called via ext4_write_begin() - * - * We need to consider the worse case, when - * one new block per extent. + * Calculate the journal credits for modifying the number of blocks + * in a single extent within one transaction. 'nrblocks' is used only + * for non-extent inodes. For extent type inodes, 'nrblocks' can be + * zero if the exact number of blocks is unknown. */ -int ext4_writepage_trans_blocks(struct inode *inode) +int ext4_chunk_trans_extent(struct inode *inode, int nrblocks) { - int bpp = ext4_journal_blocks_per_page(inode); int ret; - ret = ext4_meta_trans_blocks(inode, bpp, bpp); - + ret = ext4_meta_trans_blocks(inode, nrblocks, 1); /* Account for data blocks for journalled mode */ if (ext4_should_journal_data(inode)) - ret += bpp; + ret += nrblocks; return ret; } @@ -4754,8 +6253,12 @@ int ext4_mark_iloc_dirty(handle_t *handle, { int err = 0; - if (IS_I_VERSION(inode)) - inode_inc_iversion(inode); + err = ext4_emergency_state(inode->i_sb); + if (unlikely(err)) { + put_bh(iloc->bh); + return err; + } + ext4_fc_track_inode(handle, inode); /* the do_update_inode consumes one bh->b_count */ get_bh(iloc->bh); @@ -4777,50 +6280,164 @@ ext4_reserve_inode_write(handle_t *handle, struct inode *inode, { int err; + err = ext4_emergency_state(inode->i_sb); + if (unlikely(err)) + return err; + err = ext4_get_inode_loc(inode, iloc); if (!err) { BUFFER_TRACE(iloc->bh, "get_write_access"); - err = ext4_journal_get_write_access(handle, iloc->bh); + err = ext4_journal_get_write_access(handle, inode->i_sb, + iloc->bh, EXT4_JTR_NONE); if (err) { brelse(iloc->bh); iloc->bh = NULL; } + ext4_fc_track_inode(handle, inode); } ext4_std_error(inode->i_sb, err); return err; } -/* - * Expand an inode by new_extra_isize bytes. - * Returns 0 on success or negative error number on failure. - */ -static int ext4_expand_extra_isize(struct inode *inode, - unsigned int new_extra_isize, - struct ext4_iloc iloc, - handle_t *handle) +static int __ext4_expand_extra_isize(struct inode *inode, + unsigned int new_extra_isize, + struct ext4_iloc *iloc, + handle_t *handle, int *no_expand) { struct ext4_inode *raw_inode; struct ext4_xattr_ibody_header *header; + unsigned int inode_size = EXT4_INODE_SIZE(inode->i_sb); + struct ext4_inode_info *ei = EXT4_I(inode); + int error; - if (EXT4_I(inode)->i_extra_isize >= new_extra_isize) - return 0; + /* this was checked at iget time, but double check for good measure */ + if ((EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize > inode_size) || + (ei->i_extra_isize & 3)) { + EXT4_ERROR_INODE(inode, "bad extra_isize %u (inode size %u)", + ei->i_extra_isize, + EXT4_INODE_SIZE(inode->i_sb)); + return -EFSCORRUPTED; + } + if ((new_extra_isize < ei->i_extra_isize) || + (new_extra_isize < 4) || + (new_extra_isize > inode_size - EXT4_GOOD_OLD_INODE_SIZE)) + return -EINVAL; /* Should never happen */ - raw_inode = ext4_raw_inode(&iloc); + raw_inode = ext4_raw_inode(iloc); header = IHDR(inode, raw_inode); /* No extended attributes present */ if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR) || header->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC)) { - memset((void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE, 0, - new_extra_isize); + memset((void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE + + EXT4_I(inode)->i_extra_isize, 0, + new_extra_isize - EXT4_I(inode)->i_extra_isize); EXT4_I(inode)->i_extra_isize = new_extra_isize; return 0; } + /* + * We may need to allocate external xattr block so we need quotas + * initialized. Here we can be called with various locks held so we + * cannot affort to initialize quotas ourselves. So just bail. + */ + if (dquot_initialize_needed(inode)) + return -EAGAIN; + /* try to expand with EAs present */ - return ext4_expand_extra_isize_ea(inode, new_extra_isize, - raw_inode, handle); + error = ext4_expand_extra_isize_ea(inode, new_extra_isize, + raw_inode, handle); + if (error) { + /* + * Inode size expansion failed; don't try again + */ + *no_expand = 1; + } + + return error; +} + +/* + * Expand an inode by new_extra_isize bytes. + * Returns 0 on success or negative error number on failure. + */ +static int ext4_try_to_expand_extra_isize(struct inode *inode, + unsigned int new_extra_isize, + struct ext4_iloc iloc, + handle_t *handle) +{ + int no_expand; + int error; + + if (ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND)) + return -EOVERFLOW; + + /* + * In nojournal mode, we can immediately attempt to expand + * the inode. When journaled, we first need to obtain extra + * buffer credits since we may write into the EA block + * with this same handle. If journal_extend fails, then it will + * only result in a minor loss of functionality for that inode. + * If this is felt to be critical, then e2fsck should be run to + * force a large enough s_min_extra_isize. + */ + if (ext4_journal_extend(handle, + EXT4_DATA_TRANS_BLOCKS(inode->i_sb), 0) != 0) + return -ENOSPC; + + if (ext4_write_trylock_xattr(inode, &no_expand) == 0) + return -EBUSY; + + error = __ext4_expand_extra_isize(inode, new_extra_isize, &iloc, + handle, &no_expand); + ext4_write_unlock_xattr(inode, &no_expand); + + return error; +} + +int ext4_expand_extra_isize(struct inode *inode, + unsigned int new_extra_isize, + struct ext4_iloc *iloc) +{ + handle_t *handle; + int no_expand; + int error, rc; + + if (ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND)) { + brelse(iloc->bh); + return -EOVERFLOW; + } + + handle = ext4_journal_start(inode, EXT4_HT_INODE, + EXT4_DATA_TRANS_BLOCKS(inode->i_sb)); + if (IS_ERR(handle)) { + error = PTR_ERR(handle); + brelse(iloc->bh); + return error; + } + + ext4_write_lock_xattr(inode, &no_expand); + + BUFFER_TRACE(iloc->bh, "get_write_access"); + error = ext4_journal_get_write_access(handle, inode->i_sb, iloc->bh, + EXT4_JTR_NONE); + if (error) { + brelse(iloc->bh); + goto out_unlock; + } + + error = __ext4_expand_extra_isize(inode, new_extra_isize, iloc, + handle, &no_expand); + + rc = ext4_mark_iloc_dirty(handle, inode, iloc); + if (!error) + error = rc; + +out_unlock: + ext4_write_unlock_xattr(inode, &no_expand); + ext4_journal_stop(handle); + return error; } /* @@ -4836,48 +6453,28 @@ static int ext4_expand_extra_isize(struct inode *inode, * Whenever the user wants stuff synced (sys_sync, sys_msync, sys_fsync) * we start and wait on commits. */ -int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode) +int __ext4_mark_inode_dirty(handle_t *handle, struct inode *inode, + const char *func, unsigned int line) { struct ext4_iloc iloc; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); - static unsigned int mnt_count; - int err, ret; + int err; might_sleep(); trace_ext4_mark_inode_dirty(inode, _RET_IP_); err = ext4_reserve_inode_write(handle, inode, &iloc); - if (ext4_handle_valid(handle) && - EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize && - !ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND)) { - /* - * We need extra buffer credits since we may write into EA block - * with this same handle. If journal_extend fails, then it will - * only result in a minor loss of functionality for that inode. - * If this is felt to be critical, then e2fsck should be run to - * force a large enough s_min_extra_isize. - */ - if ((jbd2_journal_extend(handle, - EXT4_DATA_TRANS_BLOCKS(inode->i_sb))) == 0) { - ret = ext4_expand_extra_isize(inode, - sbi->s_want_extra_isize, - iloc, handle); - if (ret) { - ext4_set_inode_state(inode, - EXT4_STATE_NO_EXPAND); - if (mnt_count != - le16_to_cpu(sbi->s_es->s_mnt_count)) { - ext4_warning(inode->i_sb, - "Unable to expand inode %lu. Delete" - " some EAs or run e2fsck.", - inode->i_ino); - mnt_count = - le16_to_cpu(sbi->s_es->s_mnt_count); - } - } - } - } - if (!err) - err = ext4_mark_iloc_dirty(handle, inode, &iloc); + if (err) + goto out; + + if (EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize) + ext4_try_to_expand_extra_isize(inode, sbi->s_want_extra_isize, + iloc, handle); + + err = ext4_mark_iloc_dirty(handle, inode, &iloc); +out: + if (unlikely(err)) + ext4_error_inode_err(inode, func, line, 0, err, + "mark_inode_dirty error"); return err; } @@ -4901,50 +6498,17 @@ void ext4_dirty_inode(struct inode *inode, int flags) handle = ext4_journal_start(inode, EXT4_HT_INODE, 2); if (IS_ERR(handle)) - goto out; - + return; ext4_mark_inode_dirty(handle, inode); - ext4_journal_stop(handle); -out: - return; } -#if 0 -/* - * Bind an inode's backing buffer_head into this transaction, to prevent - * it from being flushed to disk early. Unlike - * ext4_reserve_inode_write, this leaves behind no bh reference and - * returns no iloc structure, so the caller needs to repeat the iloc - * lookup to mark the inode dirty later. - */ -static int ext4_pin_inode(handle_t *handle, struct inode *inode) -{ - struct ext4_iloc iloc; - - int err = 0; - if (handle) { - err = ext4_get_inode_loc(inode, &iloc); - if (!err) { - BUFFER_TRACE(iloc.bh, "get_write_access"); - err = jbd2_journal_get_write_access(handle, iloc.bh); - if (!err) - err = ext4_handle_dirty_metadata(handle, - NULL, - iloc.bh); - brelse(iloc.bh); - } - } - ext4_std_error(inode->i_sb, err); - return err; -} -#endif - int ext4_change_inode_journal_flag(struct inode *inode, int val) { journal_t *journal; handle_t *handle; int err; + int alloc_ctx; /* * We have to be very careful here: changing a data block's @@ -4961,22 +6525,28 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) return 0; if (is_journal_aborted(journal)) return -EROFS; - /* We have to allocate physical blocks for delalloc blocks - * before flushing journal. otherwise delalloc blocks can not - * be allocated any more. even more truncate on delalloc blocks - * could trigger BUG by flushing delalloc blocks in journal. - * There is no delalloc block in non-journal data mode. - */ - if (val && test_opt(inode->i_sb, DELALLOC)) { - err = ext4_alloc_da_blocks(inode); - if (err < 0) - return err; - } /* Wait for all existing dio workers */ - ext4_inode_block_unlocked_dio(inode); inode_dio_wait(inode); + /* + * Before flushing the journal and switching inode's aops, we have + * to flush all dirty data the inode has. There can be outstanding + * delayed allocations, there can be unwritten extents created by + * fallocate or buffered writes in dioread_nolock mode covered by + * dirty data which can be converted only after flushing the dirty + * data (and journalled aops don't know how to handle these cases). + */ + filemap_invalidate_lock(inode->i_mapping); + err = filemap_write_and_wait(inode->i_mapping); + if (err < 0) { + filemap_invalidate_unlock(inode->i_mapping); + return err; + } + /* Before switch the inode journalling mode evict all the page cache. */ + truncate_pagecache(inode, 0); + + alloc_ctx = ext4_writepages_down_write(inode->i_sb); jbd2_journal_lock_updates(journal); /* @@ -4990,13 +6560,21 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) if (val) ext4_set_inode_flag(inode, EXT4_INODE_JOURNAL_DATA); else { - jbd2_journal_flush(journal); + err = jbd2_journal_flush(journal, 0); + if (err < 0) { + jbd2_journal_unlock_updates(journal); + ext4_writepages_up_write(inode->i_sb, alloc_ctx); + filemap_invalidate_unlock(inode->i_mapping); + return err; + } ext4_clear_inode_flag(inode, EXT4_INODE_JOURNAL_DATA); } ext4_set_aops(inode); + ext4_set_inode_mapping_order(inode); jbd2_journal_unlock_updates(journal); - ext4_inode_resume_unlocked_dio(inode); + ext4_writepages_up_write(inode->i_sb, alloc_ctx); + filemap_invalidate_unlock(inode->i_mapping); /* Finally we can mark the inode as dirty. */ @@ -5004,6 +6582,8 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) if (IS_ERR(handle)) return PTR_ERR(handle); + ext4_fc_mark_ineligible(inode->i_sb, + EXT4_FC_REASON_JOURNAL_FLAG_CHANGE, handle); err = ext4_mark_inode_dirty(handle, inode); ext4_handle_sync(handle); ext4_journal_stop(handle); @@ -5012,95 +6592,150 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) return err; } -static int ext4_bh_unmapped(handle_t *handle, struct buffer_head *bh) +static int ext4_bh_unmapped(handle_t *handle, struct inode *inode, + struct buffer_head *bh) { return !buffer_mapped(bh); } -int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) +static int ext4_block_page_mkwrite(struct inode *inode, struct folio *folio, + get_block_t get_block) { - struct page *page = vmf->page; + handle_t *handle; loff_t size; unsigned long len; + int credits; int ret; + + credits = ext4_chunk_trans_extent(inode, + ext4_journal_blocks_per_folio(inode)); + handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, credits); + if (IS_ERR(handle)) + return PTR_ERR(handle); + + folio_lock(folio); + size = i_size_read(inode); + /* Page got truncated from under us? */ + if (folio->mapping != inode->i_mapping || folio_pos(folio) > size) { + ret = -EFAULT; + goto out_error; + } + + len = folio_size(folio); + if (folio_pos(folio) + len > size) + len = size - folio_pos(folio); + + ret = ext4_block_write_begin(handle, folio, 0, len, get_block); + if (ret) + goto out_error; + + if (!ext4_should_journal_data(inode)) { + block_commit_write(folio, 0, len); + folio_mark_dirty(folio); + } else { + ret = ext4_journal_folio_buffers(handle, folio, len); + if (ret) + goto out_error; + } + ext4_journal_stop(handle); + folio_wait_stable(folio); + return ret; + +out_error: + folio_unlock(folio); + ext4_journal_stop(handle); + return ret; +} + +vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + struct folio *folio = page_folio(vmf->page); + loff_t size; + unsigned long len; + int err; + vm_fault_t ret; struct file *file = vma->vm_file; struct inode *inode = file_inode(file); struct address_space *mapping = inode->i_mapping; - handle_t *handle; - get_block_t *get_block; + get_block_t *get_block = ext4_get_block; int retries = 0; + if (unlikely(IS_IMMUTABLE(inode))) + return VM_FAULT_SIGBUS; + sb_start_pagefault(inode->i_sb); file_update_time(vma->vm_file); + + filemap_invalidate_lock_shared(mapping); + + err = ext4_convert_inline_data(inode); + if (err) + goto out_ret; + + /* + * On data journalling we skip straight to the transaction handle: + * there's no delalloc; page truncated will be checked later; the + * early return w/ all buffers mapped (calculates size/len) can't + * be used; and there's no dioread_nolock, so only ext4_get_block. + */ + if (ext4_should_journal_data(inode)) + goto retry_alloc; + /* Delalloc case is easy... */ if (test_opt(inode->i_sb, DELALLOC) && - !ext4_should_journal_data(inode) && !ext4_nonda_switch(inode->i_sb)) { do { - ret = __block_page_mkwrite(vma, vmf, + err = block_page_mkwrite(vma, vmf, ext4_da_get_block_prep); - } while (ret == -ENOSPC && + } while (err == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)); goto out_ret; } - lock_page(page); + folio_lock(folio); size = i_size_read(inode); /* Page got truncated from under us? */ - if (page->mapping != mapping || page_offset(page) > size) { - unlock_page(page); + if (folio->mapping != mapping || folio_pos(folio) > size) { + folio_unlock(folio); ret = VM_FAULT_NOPAGE; goto out; } - if (page->index == size >> PAGE_CACHE_SHIFT) - len = size & ~PAGE_CACHE_MASK; - else - len = PAGE_CACHE_SIZE; + len = folio_size(folio); + if (folio_pos(folio) + len > size) + len = size - folio_pos(folio); /* * Return if we have all the buffers mapped. This avoids the need to do * journal_start/journal_stop which can block and take a long time + * + * This cannot be done for data journalling, as we have to add the + * inode to the transaction's list to writeprotect pages on commit. */ - if (page_has_buffers(page)) { - if (!ext4_walk_page_buffers(NULL, page_buffers(page), + if (folio_buffers(folio)) { + if (!ext4_walk_page_buffers(NULL, inode, folio_buffers(folio), 0, len, NULL, ext4_bh_unmapped)) { /* Wait so that we don't change page under IO */ - wait_for_stable_page(page); + folio_wait_stable(folio); ret = VM_FAULT_LOCKED; goto out; } } - unlock_page(page); + folio_unlock(folio); /* OK, we need to fill the hole... */ if (ext4_should_dioread_nolock(inode)) - get_block = ext4_get_block_write; - else - get_block = ext4_get_block; + get_block = ext4_get_block_unwritten; retry_alloc: - handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, - ext4_writepage_trans_blocks(inode)); - if (IS_ERR(handle)) { - ret = VM_FAULT_SIGBUS; - goto out; - } - ret = __block_page_mkwrite(vma, vmf, get_block); - if (!ret && ext4_should_journal_data(inode)) { - if (ext4_walk_page_buffers(handle, page_buffers(page), 0, - PAGE_CACHE_SIZE, NULL, do_journal_get_write_access)) { - unlock_page(page); - ret = VM_FAULT_SIGBUS; - ext4_journal_stop(handle); - goto out; - } - ext4_set_inode_state(inode, EXT4_STATE_JDATA); - } - ext4_journal_stop(handle); - if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) + /* Start journal and allocate blocks */ + err = ext4_block_page_mkwrite(inode, folio, get_block); + if (err == -EAGAIN || + (err == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))) goto retry_alloc; out_ret: - ret = block_page_mkwrite_return(ret); + ret = vmf_fs_error(err); out: + filemap_invalidate_unlock_shared(mapping); sb_end_pagefault(inode->i_sb); return ret; } |