From: Simon Glass <simon.glass@canonical.com> Copy resize.c, symlink.c, sysfs.c, truncate.h, verity.c, and readpage.c from Linux v6.18 fs/ext4 directory. - resize: online filesystem resize support - symlink: symbolic link operations - sysfs: sysfs attribute interface - truncate.h: truncate-related declarations - verity: fs-verity support - readpage: page reading operations Co-developed-by: Claude Opus 4.5 <noreply@anthropic.com> --- fs/ext4l/readpage.c | 422 +++++++++ fs/ext4l/resize.c | 2193 +++++++++++++++++++++++++++++++++++++++++++ fs/ext4l/symlink.c | 136 +++ fs/ext4l/sysfs.c | 648 +++++++++++++ fs/ext4l/truncate.h | 52 + fs/ext4l/verity.c | 399 ++++++++ 6 files changed, 3850 insertions(+) create mode 100644 fs/ext4l/readpage.c create mode 100644 fs/ext4l/resize.c create mode 100644 fs/ext4l/symlink.c create mode 100644 fs/ext4l/sysfs.c create mode 100644 fs/ext4l/truncate.h create mode 100644 fs/ext4l/verity.c diff --git a/fs/ext4l/readpage.c b/fs/ext4l/readpage.c new file mode 100644 index 00000000000..f329daf6e5c --- /dev/null +++ b/fs/ext4l/readpage.c @@ -0,0 +1,422 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/fs/ext4/readpage.c + * + * Copyright (C) 2002, Linus Torvalds. + * Copyright (C) 2015, Google, Inc. + * + * This was originally taken from fs/mpage.c + * + * The ext4_mpage_readpages() function here is intended to + * replace mpage_readahead() in the general case, not just for + * encrypted files. It has some limitations (see below), where it + * will fall back to read_block_full_page(), but these limitations + * should only be hit when page_size != block_size. + * + * This will allow us to attach a callback function to support ext4 + * encryption. + * + * If anything unusual happens, such as: + * + * - encountering a page which has buffers + * - encountering a page which has a non-hole after a hole + * - encountering a page with non-contiguous blocks + * + * then this code just gives up and calls the buffer_head-based read function. + * It does handle a page which has holes at the end - that is a common case: + * the end-of-file on blocksize < PAGE_SIZE setups. + * + */ + +#include <linux/kernel.h> +#include <linux/export.h> +#include <linux/mm.h> +#include <linux/kdev_t.h> +#include <linux/gfp.h> +#include <linux/bio.h> +#include <linux/fs.h> +#include <linux/buffer_head.h> +#include <linux/blkdev.h> +#include <linux/highmem.h> +#include <linux/prefetch.h> +#include <linux/mpage.h> +#include <linux/writeback.h> +#include <linux/backing-dev.h> +#include <linux/pagevec.h> + +#include "ext4.h" + +#define NUM_PREALLOC_POST_READ_CTXS 128 + +static struct kmem_cache *bio_post_read_ctx_cache; +static mempool_t *bio_post_read_ctx_pool; + +/* postprocessing steps for read bios */ +enum bio_post_read_step { + STEP_INITIAL = 0, + STEP_DECRYPT, + STEP_VERITY, + STEP_MAX, +}; + +struct bio_post_read_ctx { + struct bio *bio; + struct work_struct work; + unsigned int cur_step; + unsigned int enabled_steps; +}; + +static void __read_end_io(struct bio *bio) +{ + struct folio_iter fi; + + bio_for_each_folio_all(fi, bio) + folio_end_read(fi.folio, bio->bi_status == 0); + if (bio->bi_private) + mempool_free(bio->bi_private, bio_post_read_ctx_pool); + bio_put(bio); +} + +static void bio_post_read_processing(struct bio_post_read_ctx *ctx); + +static void decrypt_work(struct work_struct *work) +{ + struct bio_post_read_ctx *ctx = + container_of(work, struct bio_post_read_ctx, work); + struct bio *bio = ctx->bio; + + if (fscrypt_decrypt_bio(bio)) + bio_post_read_processing(ctx); + else + __read_end_io(bio); +} + +static void verity_work(struct work_struct *work) +{ + struct bio_post_read_ctx *ctx = + container_of(work, struct bio_post_read_ctx, work); + struct bio *bio = ctx->bio; + + /* + * fsverity_verify_bio() may call readahead() again, and although verity + * will be disabled for that, decryption may still be needed, causing + * another bio_post_read_ctx to be allocated. So to guarantee that + * mempool_alloc() never deadlocks we must free the current ctx first. + * This is safe because verity is the last post-read step. + */ + BUILD_BUG_ON(STEP_VERITY + 1 != STEP_MAX); + mempool_free(ctx, bio_post_read_ctx_pool); + bio->bi_private = NULL; + + fsverity_verify_bio(bio); + + __read_end_io(bio); +} + +static void bio_post_read_processing(struct bio_post_read_ctx *ctx) +{ + /* + * We use different work queues for decryption and for verity because + * verity may require reading metadata pages that need decryption, and + * we shouldn't recurse to the same workqueue. + */ + switch (++ctx->cur_step) { + case STEP_DECRYPT: + if (ctx->enabled_steps & (1 << STEP_DECRYPT)) { + INIT_WORK(&ctx->work, decrypt_work); + fscrypt_enqueue_decrypt_work(&ctx->work); + return; + } + ctx->cur_step++; + fallthrough; + case STEP_VERITY: + if (ctx->enabled_steps & (1 << STEP_VERITY)) { + INIT_WORK(&ctx->work, verity_work); + fsverity_enqueue_verify_work(&ctx->work); + return; + } + ctx->cur_step++; + fallthrough; + default: + __read_end_io(ctx->bio); + } +} + +static bool bio_post_read_required(struct bio *bio) +{ + return bio->bi_private && !bio->bi_status; +} + +/* + * I/O completion handler for multipage BIOs. + * + * The mpage code never puts partial pages into a BIO (except for end-of-file). + * If a page does not map to a contiguous run of blocks then it simply falls + * back to block_read_full_folio(). + * + * Why is this? If a page's completion depends on a number of different BIOs + * which can complete in any order (or at the same time) then determining the + * status of that page is hard. See end_buffer_async_read() for the details. + * There is no point in duplicating all that complexity. + */ +static void mpage_end_io(struct bio *bio) +{ + if (bio_post_read_required(bio)) { + struct bio_post_read_ctx *ctx = bio->bi_private; + + ctx->cur_step = STEP_INITIAL; + bio_post_read_processing(ctx); + return; + } + __read_end_io(bio); +} + +static inline bool ext4_need_verity(const struct inode *inode, pgoff_t idx) +{ + return fsverity_active(inode) && + idx < DIV_ROUND_UP(inode->i_size, PAGE_SIZE); +} + +static void ext4_set_bio_post_read_ctx(struct bio *bio, + const struct inode *inode, + pgoff_t first_idx) +{ + unsigned int post_read_steps = 0; + + if (fscrypt_inode_uses_fs_layer_crypto(inode)) + post_read_steps |= 1 << STEP_DECRYPT; + + if (ext4_need_verity(inode, first_idx)) + post_read_steps |= 1 << STEP_VERITY; + + if (post_read_steps) { + /* Due to the mempool, this never fails. */ + struct bio_post_read_ctx *ctx = + mempool_alloc(bio_post_read_ctx_pool, GFP_NOFS); + + ctx->bio = bio; + ctx->enabled_steps = post_read_steps; + bio->bi_private = ctx; + } +} + +static inline loff_t ext4_readpage_limit(struct inode *inode) +{ + if (IS_ENABLED(CONFIG_FS_VERITY) && IS_VERITY(inode)) + return inode->i_sb->s_maxbytes; + + return i_size_read(inode); +} + +int ext4_mpage_readpages(struct inode *inode, + struct readahead_control *rac, struct folio *folio) +{ + struct bio *bio = NULL; + sector_t last_block_in_bio = 0; + + const unsigned blkbits = inode->i_blkbits; + const unsigned blocks_per_page = PAGE_SIZE >> blkbits; + const unsigned blocksize = 1 << blkbits; + sector_t next_block; + sector_t block_in_file; + sector_t last_block; + sector_t last_block_in_file; + sector_t first_block; + unsigned page_block; + struct block_device *bdev = inode->i_sb->s_bdev; + int length; + unsigned relative_block = 0; + struct ext4_map_blocks map; + unsigned int nr_pages, folio_pages; + + map.m_pblk = 0; + map.m_lblk = 0; + map.m_len = 0; + map.m_flags = 0; + + nr_pages = rac ? readahead_count(rac) : folio_nr_pages(folio); + for (; nr_pages; nr_pages -= folio_pages) { + int fully_mapped = 1; + unsigned int first_hole; + unsigned int blocks_per_folio; + + if (rac) + folio = readahead_folio(rac); + + folio_pages = folio_nr_pages(folio); + prefetchw(&folio->flags); + + if (folio_buffers(folio)) + goto confused; + + blocks_per_folio = folio_size(folio) >> blkbits; + first_hole = blocks_per_folio; + block_in_file = next_block = + (sector_t)folio->index << (PAGE_SHIFT - blkbits); + last_block = block_in_file + nr_pages * blocks_per_page; + last_block_in_file = (ext4_readpage_limit(inode) + + blocksize - 1) >> blkbits; + if (last_block > last_block_in_file) + last_block = last_block_in_file; + page_block = 0; + + /* + * Map blocks using the previous result first. + */ + if ((map.m_flags & EXT4_MAP_MAPPED) && + block_in_file > map.m_lblk && + block_in_file < (map.m_lblk + map.m_len)) { + unsigned map_offset = block_in_file - map.m_lblk; + unsigned last = map.m_len - map_offset; + + first_block = map.m_pblk + map_offset; + for (relative_block = 0; ; relative_block++) { + if (relative_block == last) { + /* needed? */ + map.m_flags &= ~EXT4_MAP_MAPPED; + break; + } + if (page_block == blocks_per_folio) + break; + page_block++; + block_in_file++; + } + } + + /* + * Then do more ext4_map_blocks() calls until we are + * done with this folio. + */ + while (page_block < blocks_per_folio) { + if (block_in_file < last_block) { + map.m_lblk = block_in_file; + map.m_len = last_block - block_in_file; + + if (ext4_map_blocks(NULL, inode, &map, 0) < 0) { + set_error_page: + folio_zero_segment(folio, 0, + folio_size(folio)); + folio_unlock(folio); + goto next_page; + } + } + if ((map.m_flags & EXT4_MAP_MAPPED) == 0) { + fully_mapped = 0; + if (first_hole == blocks_per_folio) + first_hole = page_block; + page_block++; + block_in_file++; + continue; + } + if (first_hole != blocks_per_folio) + goto confused; /* hole -> non-hole */ + + /* Contiguous blocks? */ + if (!page_block) + first_block = map.m_pblk; + else if (first_block + page_block != map.m_pblk) + goto confused; + for (relative_block = 0; ; relative_block++) { + if (relative_block == map.m_len) { + /* needed? */ + map.m_flags &= ~EXT4_MAP_MAPPED; + break; + } else if (page_block == blocks_per_folio) + break; + page_block++; + block_in_file++; + } + } + if (first_hole != blocks_per_folio) { + folio_zero_segment(folio, first_hole << blkbits, + folio_size(folio)); + if (first_hole == 0) { + if (ext4_need_verity(inode, folio->index) && + !fsverity_verify_folio(folio)) + goto set_error_page; + folio_end_read(folio, true); + continue; + } + } else if (fully_mapped) { + folio_set_mappedtodisk(folio); + } + + /* + * This folio will go to BIO. Do we need to send this + * BIO off first? + */ + if (bio && (last_block_in_bio != first_block - 1 || + !fscrypt_mergeable_bio(bio, inode, next_block))) { + submit_and_realloc: + submit_bio(bio); + bio = NULL; + } + if (bio == NULL) { + /* + * bio_alloc will _always_ be able to allocate a bio if + * __GFP_DIRECT_RECLAIM is set, see bio_alloc_bioset(). + */ + bio = bio_alloc(bdev, bio_max_segs(nr_pages), + REQ_OP_READ, GFP_KERNEL); + fscrypt_set_bio_crypt_ctx(bio, inode, next_block, + GFP_KERNEL); + ext4_set_bio_post_read_ctx(bio, inode, folio->index); + bio->bi_iter.bi_sector = first_block << (blkbits - 9); + bio->bi_end_io = mpage_end_io; + if (rac) + bio->bi_opf |= REQ_RAHEAD; + } + + length = first_hole << blkbits; + if (!bio_add_folio(bio, folio, length, 0)) + goto submit_and_realloc; + + if (((map.m_flags & EXT4_MAP_BOUNDARY) && + (relative_block == map.m_len)) || + (first_hole != blocks_per_folio)) { + submit_bio(bio); + bio = NULL; + } else + last_block_in_bio = first_block + blocks_per_folio - 1; + continue; + confused: + if (bio) { + submit_bio(bio); + bio = NULL; + } + if (!folio_test_uptodate(folio)) + block_read_full_folio(folio, ext4_get_block); + else + folio_unlock(folio); +next_page: + ; /* A label shall be followed by a statement until C23 */ + } + if (bio) + submit_bio(bio); + return 0; +} + +int __init ext4_init_post_read_processing(void) +{ + bio_post_read_ctx_cache = KMEM_CACHE(bio_post_read_ctx, SLAB_RECLAIM_ACCOUNT); + + if (!bio_post_read_ctx_cache) + goto fail; + bio_post_read_ctx_pool = + mempool_create_slab_pool(NUM_PREALLOC_POST_READ_CTXS, + bio_post_read_ctx_cache); + if (!bio_post_read_ctx_pool) + goto fail_free_cache; + return 0; + +fail_free_cache: + kmem_cache_destroy(bio_post_read_ctx_cache); +fail: + return -ENOMEM; +} + +void ext4_exit_post_read_processing(void) +{ + mempool_destroy(bio_post_read_ctx_pool); + kmem_cache_destroy(bio_post_read_ctx_cache); +} diff --git a/fs/ext4l/resize.c b/fs/ext4l/resize.c new file mode 100644 index 00000000000..050f26168d9 --- /dev/null +++ b/fs/ext4l/resize.c @@ -0,0 +1,2193 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/fs/ext4/resize.c + * + * Support for resizing an ext4 filesystem while it is mounted. + * + * Copyright (C) 2001, 2002 Andreas Dilger <adilger@clusterfs.com> + * + * This could probably be made into a module, because it is not often in use. + */ + + +#include <linux/errno.h> +#include <linux/slab.h> +#include <linux/jiffies.h> + +#include "ext4_jbd2.h" + +struct ext4_rcu_ptr { + struct rcu_head rcu; + void *ptr; +}; + +static void ext4_rcu_ptr_callback(struct rcu_head *head) +{ + struct ext4_rcu_ptr *ptr; + + ptr = container_of(head, struct ext4_rcu_ptr, rcu); + kvfree(ptr->ptr); + kfree(ptr); +} + +void ext4_kvfree_array_rcu(void *to_free) +{ + struct ext4_rcu_ptr *ptr = kzalloc(sizeof(*ptr), GFP_KERNEL); + + if (ptr) { + ptr->ptr = to_free; + call_rcu(&ptr->rcu, ext4_rcu_ptr_callback); + return; + } + synchronize_rcu(); + kvfree(to_free); +} + +int ext4_resize_begin(struct super_block *sb) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + int ret = 0; + + if (!capable(CAP_SYS_RESOURCE)) + return -EPERM; + + /* + * If the reserved GDT blocks is non-zero, the resize_inode feature + * should always be set. + */ + if (sbi->s_es->s_reserved_gdt_blocks && + !ext4_has_feature_resize_inode(sb)) { + ext4_error(sb, "resize_inode disabled but reserved GDT blocks non-zero"); + return -EFSCORRUPTED; + } + + /* + * If we are not using the primary superblock/GDT copy don't resize, + * because the user tools have no way of handling this. Probably a + * bad time to do it anyways. + */ + if (EXT4_B2C(sbi, sbi->s_sbh->b_blocknr) != + le32_to_cpu(sbi->s_es->s_first_data_block)) { + ext4_warning(sb, "won't resize using backup superblock at %llu", + (unsigned long long)sbi->s_sbh->b_blocknr); + return -EPERM; + } + + /* + * We are not allowed to do online-resizing on a filesystem mounted + * with error, because it can destroy the filesystem easily. + */ + if (sbi->s_mount_state & EXT4_ERROR_FS) { + ext4_warning(sb, "There are errors in the filesystem, " + "so online resizing is not allowed"); + return -EPERM; + } + + if (ext4_has_feature_sparse_super2(sb)) { + ext4_msg(sb, KERN_ERR, "Online resizing not supported with sparse_super2"); + return -EOPNOTSUPP; + } + + if (test_and_set_bit_lock(EXT4_FLAGS_RESIZING, + &sbi->s_ext4_flags)) + ret = -EBUSY; + + return ret; +} + +int ext4_resize_end(struct super_block *sb, bool update_backups) +{ + clear_bit_unlock(EXT4_FLAGS_RESIZING, &EXT4_SB(sb)->s_ext4_flags); + smp_mb__after_atomic(); + if (update_backups) + return ext4_update_overhead(sb, true); + return 0; +} + +static ext4_grpblk_t ext4_group_overhead_blocks(struct super_block *sb, + ext4_group_t group) { + ext4_grpblk_t overhead; + overhead = ext4_bg_num_gdb(sb, group); + if (ext4_bg_has_super(sb, group)) + overhead += 1 + + le16_to_cpu(EXT4_SB(sb)->s_es->s_reserved_gdt_blocks); + return overhead; +} + +#define outside(b, first, last) ((b) < (first) || (b) >= (last)) +#define inside(b, first, last) ((b) >= (first) && (b) < (last)) + +static int verify_group_input(struct super_block *sb, + struct ext4_new_group_data *input) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_super_block *es = sbi->s_es; + ext4_fsblk_t start = ext4_blocks_count(es); + ext4_fsblk_t end = start + input->blocks_count; + ext4_group_t group = input->group; + ext4_fsblk_t itend = input->inode_table + sbi->s_itb_per_group; + unsigned overhead; + ext4_fsblk_t metaend; + struct buffer_head *bh = NULL; + ext4_grpblk_t free_blocks_count, offset; + int err = -EINVAL; + + if (group != sbi->s_groups_count) { + ext4_warning(sb, "Cannot add at group %u (only %u groups)", + input->group, sbi->s_groups_count); + return -EINVAL; + } + + overhead = ext4_group_overhead_blocks(sb, group); + metaend = start + overhead; + free_blocks_count = input->blocks_count - 2 - overhead - + sbi->s_itb_per_group; + input->free_clusters_count = EXT4_B2C(sbi, free_blocks_count); + + if (test_opt(sb, DEBUG)) + printk(KERN_DEBUG "EXT4-fs: adding %s group %u: %u blocks " + "(%d free, %u reserved)\n", + ext4_bg_has_super(sb, input->group) ? "normal" : + "no-super", input->group, input->blocks_count, + free_blocks_count, input->reserved_blocks); + + ext4_get_group_no_and_offset(sb, start, NULL, &offset); + if (offset != 0) + ext4_warning(sb, "Last group not full"); + else if (input->reserved_blocks > input->blocks_count / 5) + ext4_warning(sb, "Reserved blocks too high (%u)", + input->reserved_blocks); + else if (free_blocks_count < 0) + ext4_warning(sb, "Bad blocks count %u", + input->blocks_count); + else if (IS_ERR(bh = ext4_sb_bread(sb, end - 1, 0))) { + err = PTR_ERR(bh); + bh = NULL; + ext4_warning(sb, "Cannot read last block (%llu)", + end - 1); + } else if (outside(input->block_bitmap, start, end)) + ext4_warning(sb, "Block bitmap not in group (block %llu)", + (unsigned long long)input->block_bitmap); + else if (outside(input->inode_bitmap, start, end)) + ext4_warning(sb, "Inode bitmap not in group (block %llu)", + (unsigned long long)input->inode_bitmap); + else if (outside(input->inode_table, start, end) || + outside(itend - 1, start, end)) + ext4_warning(sb, "Inode table not in group (blocks %llu-%llu)", + (unsigned long long)input->inode_table, itend - 1); + else if (input->inode_bitmap == input->block_bitmap) + ext4_warning(sb, "Block bitmap same as inode bitmap (%llu)", + (unsigned long long)input->block_bitmap); + else if (inside(input->block_bitmap, input->inode_table, itend)) + ext4_warning(sb, "Block bitmap (%llu) in inode table " + "(%llu-%llu)", + (unsigned long long)input->block_bitmap, + (unsigned long long)input->inode_table, itend - 1); + else if (inside(input->inode_bitmap, input->inode_table, itend)) + ext4_warning(sb, "Inode bitmap (%llu) in inode table " + "(%llu-%llu)", + (unsigned long long)input->inode_bitmap, + (unsigned long long)input->inode_table, itend - 1); + else if (inside(input->block_bitmap, start, metaend)) + ext4_warning(sb, "Block bitmap (%llu) in GDT table (%llu-%llu)", + (unsigned long long)input->block_bitmap, + start, metaend - 1); + else if (inside(input->inode_bitmap, start, metaend)) + ext4_warning(sb, "Inode bitmap (%llu) in GDT table (%llu-%llu)", + (unsigned long long)input->inode_bitmap, + start, metaend - 1); + else if (inside(input->inode_table, start, metaend) || + inside(itend - 1, start, metaend)) + ext4_warning(sb, "Inode table (%llu-%llu) overlaps GDT table " + "(%llu-%llu)", + (unsigned long long)input->inode_table, + itend - 1, start, metaend - 1); + else + err = 0; + brelse(bh); + + return err; +} + +/* + * ext4_new_flex_group_data is used by 64bit-resize interface to add a flex + * group each time. + */ +struct ext4_new_flex_group_data { + struct ext4_new_group_data *groups; /* new_group_data for groups + in the flex group */ + __u16 *bg_flags; /* block group flags of groups + in @groups */ + ext4_group_t resize_bg; /* number of allocated + new_group_data */ + ext4_group_t count; /* number of groups in @groups + */ +}; + +/* + * Avoiding memory allocation failures due to too many groups added each time. + */ +#define MAX_RESIZE_BG 16384 + +/* + * alloc_flex_gd() allocates an ext4_new_flex_group_data that satisfies the + * resizing from @o_group to @n_group, its size is typically @flexbg_size. + * + * Returns NULL on failure otherwise address of the allocated structure. + */ +static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned int flexbg_size, + ext4_group_t o_group, ext4_group_t n_group) +{ + ext4_group_t last_group; + unsigned int max_resize_bg; + struct ext4_new_flex_group_data *flex_gd; + + flex_gd = kmalloc(sizeof(*flex_gd), GFP_NOFS); + if (flex_gd == NULL) + goto out3; + + max_resize_bg = umin(flexbg_size, MAX_RESIZE_BG); + flex_gd->resize_bg = max_resize_bg; + + /* Avoid allocating large 'groups' array if not needed */ + last_group = o_group | (flex_gd->resize_bg - 1); + if (n_group <= last_group) + flex_gd->resize_bg = 1 << fls(n_group - o_group); + else if (n_group - last_group < flex_gd->resize_bg) + flex_gd->resize_bg = 1 << max(fls(last_group - o_group), + fls(n_group - last_group)); + + if (WARN_ON_ONCE(flex_gd->resize_bg > max_resize_bg)) + flex_gd->resize_bg = max_resize_bg; + + flex_gd->groups = kmalloc_array(flex_gd->resize_bg, + sizeof(struct ext4_new_group_data), + GFP_NOFS); + if (flex_gd->groups == NULL) + goto out2; + + flex_gd->bg_flags = kmalloc_array(flex_gd->resize_bg, sizeof(__u16), + GFP_NOFS); + if (flex_gd->bg_flags == NULL) + goto out1; + + return flex_gd; + +out1: + kfree(flex_gd->groups); +out2: + kfree(flex_gd); +out3: + return NULL; +} + +static void free_flex_gd(struct ext4_new_flex_group_data *flex_gd) +{ + kfree(flex_gd->bg_flags); + kfree(flex_gd->groups); + kfree(flex_gd); +} + +/* + * ext4_alloc_group_tables() allocates block bitmaps, inode bitmaps + * and inode tables for a flex group. + * + * This function is used by 64bit-resize. Note that this function allocates + * group tables from the 1st group of groups contained by @flexgd, which may + * be a partial of a flex group. + * + * @sb: super block of fs to which the groups belongs + * + * Returns 0 on a successful allocation of the metadata blocks in the + * block group. + */ +static int ext4_alloc_group_tables(struct super_block *sb, + struct ext4_new_flex_group_data *flex_gd, + unsigned int flexbg_size) +{ + struct ext4_new_group_data *group_data = flex_gd->groups; + ext4_fsblk_t start_blk; + ext4_fsblk_t last_blk; + ext4_group_t src_group; + ext4_group_t bb_index = 0; + ext4_group_t ib_index = 0; + ext4_group_t it_index = 0; + ext4_group_t group; + ext4_group_t last_group; + unsigned overhead; + __u16 uninit_mask = (flexbg_size > 1) ? ~EXT4_BG_BLOCK_UNINIT : ~0; + int i; + + BUG_ON(flex_gd->count == 0 || group_data == NULL); + + src_group = group_data[0].group; + last_group = src_group + flex_gd->count - 1; + + BUG_ON((flexbg_size > 1) && ((src_group & ~(flexbg_size - 1)) != + (last_group & ~(flexbg_size - 1)))); +next_group: + group = group_data[0].group; + if (src_group >= group_data[0].group + flex_gd->count) + return -ENOSPC; + start_blk = ext4_group_first_block_no(sb, src_group); + last_blk = start_blk + group_data[src_group - group].blocks_count; + + overhead = ext4_group_overhead_blocks(sb, src_group); + + start_blk += overhead; + + /* We collect contiguous blocks as much as possible. */ + src_group++; + for (; src_group <= last_group; src_group++) { + overhead = ext4_group_overhead_blocks(sb, src_group); + if (overhead == 0) + last_blk += group_data[src_group - group].blocks_count; + else + break; + } + + /* Allocate block bitmaps */ + for (; bb_index < flex_gd->count; bb_index++) { + if (start_blk >= last_blk) + goto next_group; + group_data[bb_index].block_bitmap = start_blk++; + group = ext4_get_group_number(sb, start_blk - 1); + group -= group_data[0].group; + group_data[group].mdata_blocks++; + flex_gd->bg_flags[group] &= uninit_mask; + } + + /* Allocate inode bitmaps */ + for (; ib_index < flex_gd->count; ib_index++) { + if (start_blk >= last_blk) + goto next_group; + group_data[ib_index].inode_bitmap = start_blk++; + group = ext4_get_group_number(sb, start_blk - 1); + group -= group_data[0].group; + group_data[group].mdata_blocks++; + flex_gd->bg_flags[group] &= uninit_mask; + } + + /* Allocate inode tables */ + for (; it_index < flex_gd->count; it_index++) { + unsigned int itb = EXT4_SB(sb)->s_itb_per_group; + ext4_fsblk_t next_group_start; + + if (start_blk + itb > last_blk) + goto next_group; + group_data[it_index].inode_table = start_blk; + group = ext4_get_group_number(sb, start_blk); + next_group_start = ext4_group_first_block_no(sb, group + 1); + group -= group_data[0].group; + + if (start_blk + itb > next_group_start) { + flex_gd->bg_flags[group + 1] &= uninit_mask; + overhead = start_blk + itb - next_group_start; + group_data[group + 1].mdata_blocks += overhead; + itb -= overhead; + } + + group_data[group].mdata_blocks += itb; + flex_gd->bg_flags[group] &= uninit_mask; + start_blk += EXT4_SB(sb)->s_itb_per_group; + } + + /* Update free clusters count to exclude metadata blocks */ + for (i = 0; i < flex_gd->count; i++) { + group_data[i].free_clusters_count -= + EXT4_NUM_B2C(EXT4_SB(sb), + group_data[i].mdata_blocks); + } + + if (test_opt(sb, DEBUG)) { + int i; + group = group_data[0].group; + + printk(KERN_DEBUG "EXT4-fs: adding a flex group with " + "%u groups, flexbg size is %u:\n", flex_gd->count, + flexbg_size); + + for (i = 0; i < flex_gd->count; i++) { + ext4_debug( + "adding %s group %u: %u blocks (%u free, %u mdata blocks)\n", + ext4_bg_has_super(sb, group + i) ? "normal" : + "no-super", group + i, + group_data[i].blocks_count, + group_data[i].free_clusters_count, + group_data[i].mdata_blocks); + } + } + return 0; +} + +static struct buffer_head *bclean(handle_t *handle, struct super_block *sb, + ext4_fsblk_t blk) +{ + struct buffer_head *bh; + int err; + + bh = sb_getblk(sb, blk); + if (unlikely(!bh)) + return ERR_PTR(-ENOMEM); + BUFFER_TRACE(bh, "get_write_access"); + err = ext4_journal_get_write_access(handle, sb, bh, EXT4_JTR_NONE); + if (err) { + brelse(bh); + bh = ERR_PTR(err); + } else { + memset(bh->b_data, 0, sb->s_blocksize); + set_buffer_uptodate(bh); + } + + return bh; +} + +static int ext4_resize_ensure_credits_batch(handle_t *handle, int credits) +{ + return ext4_journal_ensure_credits_fn(handle, credits, + EXT4_MAX_TRANS_DATA, 0, 0); +} + +/* + * set_flexbg_block_bitmap() mark clusters [@first_cluster, @last_cluster] used. + * + * Helper function for ext4_setup_new_group_blocks() which set . + * + * @sb: super block + * @handle: journal handle + * @flex_gd: flex group data + */ +static int set_flexbg_block_bitmap(struct super_block *sb, handle_t *handle, + struct ext4_new_flex_group_data *flex_gd, + ext4_fsblk_t first_cluster, ext4_fsblk_t last_cluster) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + ext4_group_t count = last_cluster - first_cluster + 1; + ext4_group_t count2; + + ext4_debug("mark clusters [%llu-%llu] used\n", first_cluster, + last_cluster); + for (; count > 0; count -= count2, first_cluster += count2) { + ext4_fsblk_t start; + struct buffer_head *bh; + ext4_group_t group; + int err; + + group = ext4_get_group_number(sb, EXT4_C2B(sbi, first_cluster)); + start = EXT4_B2C(sbi, ext4_group_first_block_no(sb, group)); + group -= flex_gd->groups[0].group; + + count2 = EXT4_CLUSTERS_PER_GROUP(sb) - (first_cluster - start); + if (count2 > count) + count2 = count; + + if (flex_gd->bg_flags[group] & EXT4_BG_BLOCK_UNINIT) { + BUG_ON(flex_gd->count > 1); + continue; + } + + err = ext4_resize_ensure_credits_batch(handle, 1); + if (err < 0) + return err; + + bh = sb_getblk(sb, flex_gd->groups[group].block_bitmap); + if (unlikely(!bh)) + return -ENOMEM; + + BUFFER_TRACE(bh, "get_write_access"); + err = ext4_journal_get_write_access(handle, sb, bh, + EXT4_JTR_NONE); + if (err) { + brelse(bh); + return err; + } + ext4_debug("mark block bitmap %#04llx (+%llu/%u)\n", + first_cluster, first_cluster - start, count2); + mb_set_bits(bh->b_data, first_cluster - start, count2); + + err = ext4_handle_dirty_metadata(handle, NULL, bh); + brelse(bh); + if (unlikely(err)) + return err; + } + + return 0; +} + +/* + * Set up the block and inode bitmaps, and the inode table for the new groups. + * This doesn't need to be part of the main transaction, since we are only + * changing blocks outside the actual filesystem. We still do journaling to + * ensure the recovery is correct in case of a failure just after resize. + * If any part of this fails, we simply abort the resize. + * + * setup_new_flex_group_blocks handles a flex group as follow: + * 1. copy super block and GDT, and initialize group tables if necessary. + * In this step, we only set bits in blocks bitmaps for blocks taken by + * super block and GDT. + * 2. allocate group tables in block bitmaps, that is, set bits in block + * bitmap for blocks taken by group tables. + */ +static int setup_new_flex_group_blocks(struct super_block *sb, + struct ext4_new_flex_group_data *flex_gd) +{ + int group_table_count[] = {1, 1, EXT4_SB(sb)->s_itb_per_group}; + ext4_fsblk_t start; + ext4_fsblk_t block; + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_super_block *es = sbi->s_es; + struct ext4_new_group_data *group_data = flex_gd->groups; + __u16 *bg_flags = flex_gd->bg_flags; + handle_t *handle; + ext4_group_t group, count; + struct buffer_head *bh = NULL; + int reserved_gdb, i, j, err = 0, err2; + int meta_bg; + + BUG_ON(!flex_gd->count || !group_data || + group_data[0].group != sbi->s_groups_count); + + reserved_gdb = le16_to_cpu(es->s_reserved_gdt_blocks); + meta_bg = ext4_has_feature_meta_bg(sb); + + /* This transaction may be extended/restarted along the way */ + handle = ext4_journal_start_sb(sb, EXT4_HT_RESIZE, EXT4_MAX_TRANS_DATA); + if (IS_ERR(handle)) + return PTR_ERR(handle); + + group = group_data[0].group; + for (i = 0; i < flex_gd->count; i++, group++) { + unsigned long gdblocks; + ext4_grpblk_t overhead; + + gdblocks = ext4_bg_num_gdb(sb, group); + start = ext4_group_first_block_no(sb, group); + + if (meta_bg == 0 && !ext4_bg_has_super(sb, group)) + goto handle_itb; + + if (meta_bg == 1) + goto handle_itb; + + block = start + ext4_bg_has_super(sb, group); + /* Copy all of the GDT blocks into the backup in this group */ + for (j = 0; j < gdblocks; j++, block++) { + struct buffer_head *gdb; + + ext4_debug("update backup group %#04llx\n", block); + err = ext4_resize_ensure_credits_batch(handle, 1); + if (err < 0) + goto out; + + gdb = sb_getblk(sb, block); + if (unlikely(!gdb)) { + err = -ENOMEM; + goto out; + } + + BUFFER_TRACE(gdb, "get_write_access"); + err = ext4_journal_get_write_access(handle, sb, gdb, + EXT4_JTR_NONE); + if (err) { + brelse(gdb); + goto out; + } + memcpy(gdb->b_data, sbi_array_rcu_deref(sbi, + s_group_desc, j)->b_data, gdb->b_size); + set_buffer_uptodate(gdb); + + err = ext4_handle_dirty_metadata(handle, NULL, gdb); + if (unlikely(err)) { + brelse(gdb); + goto out; + } + brelse(gdb); + } + + /* Zero out all of the reserved backup group descriptor + * table blocks + */ + if (ext4_bg_has_super(sb, group)) { + err = sb_issue_zeroout(sb, gdblocks + start + 1, + reserved_gdb, GFP_NOFS); + if (err) + goto out; + } + +handle_itb: + /* Initialize group tables of the group @group */ + if (!(bg_flags[i] & EXT4_BG_INODE_ZEROED)) + goto handle_bb; + + /* Zero out all of the inode table blocks */ + block = group_data[i].inode_table; + ext4_debug("clear inode table blocks %#04llx -> %#04lx\n", + block, sbi->s_itb_per_group); + err = sb_issue_zeroout(sb, block, sbi->s_itb_per_group, + GFP_NOFS); + if (err) + goto out; + +handle_bb: + if (bg_flags[i] & EXT4_BG_BLOCK_UNINIT) + goto handle_ib; + + /* Initialize block bitmap of the @group */ + block = group_data[i].block_bitmap; + err = ext4_resize_ensure_credits_batch(handle, 1); + if (err < 0) + goto out; + + bh = bclean(handle, sb, block); + if (IS_ERR(bh)) { + err = PTR_ERR(bh); + goto out; + } + overhead = ext4_group_overhead_blocks(sb, group); + if (overhead != 0) { + ext4_debug("mark backup superblock %#04llx (+0)\n", + start); + mb_set_bits(bh->b_data, 0, + EXT4_NUM_B2C(sbi, overhead)); + } + ext4_mark_bitmap_end(EXT4_B2C(sbi, group_data[i].blocks_count), + sb->s_blocksize * 8, bh->b_data); + err = ext4_handle_dirty_metadata(handle, NULL, bh); + brelse(bh); + if (err) + goto out; + +handle_ib: + if (bg_flags[i] & EXT4_BG_INODE_UNINIT) + continue; + + /* Initialize inode bitmap of the @group */ + block = group_data[i].inode_bitmap; + err = ext4_resize_ensure_credits_batch(handle, 1); + if (err < 0) + goto out; + /* Mark unused entries in inode bitmap used */ + bh = bclean(handle, sb, block); + if (IS_ERR(bh)) { + err = PTR_ERR(bh); + goto out; + } + + ext4_mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), + sb->s_blocksize * 8, bh->b_data); + err = ext4_handle_dirty_metadata(handle, NULL, bh); + brelse(bh); + if (err) + goto out; + } + + /* Mark group tables in block bitmap */ + for (j = 0; j < GROUP_TABLE_COUNT; j++) { + count = group_table_count[j]; + start = (&group_data[0].block_bitmap)[j]; + block = start; + for (i = 1; i < flex_gd->count; i++) { + block += group_table_count[j]; + if (block == (&group_data[i].block_bitmap)[j]) { + count += group_table_count[j]; + continue; + } + err = set_flexbg_block_bitmap(sb, handle, + flex_gd, + EXT4_B2C(sbi, start), + EXT4_B2C(sbi, + start + count + - 1)); + if (err) + goto out; + count = group_table_count[j]; + start = (&group_data[i].block_bitmap)[j]; + block = start; + } + + err = set_flexbg_block_bitmap(sb, handle, + flex_gd, + EXT4_B2C(sbi, start), + EXT4_B2C(sbi, + start + count + - 1)); + if (err) + goto out; + } + +out: + err2 = ext4_journal_stop(handle); + if (err2 && !err) + err = err2; + + return err; +} + +/* + * Iterate through the groups which hold BACKUP superblock/GDT copies in an + * ext4 filesystem. The counters should be initialized to 1, 5, and 7 before + * calling this for the first time. In a sparse filesystem it will be the + * sequence of powers of 3, 5, and 7: 1, 3, 5, 7, 9, 25, 27, 49, 81, ... + * For a non-sparse filesystem it will be every group: 1, 2, 3, 4, ... + */ +unsigned int ext4_list_backups(struct super_block *sb, unsigned int *three, + unsigned int *five, unsigned int *seven) +{ + struct ext4_super_block *es = EXT4_SB(sb)->s_es; + unsigned int *min = three; + int mult = 3; + unsigned int ret; + + if (ext4_has_feature_sparse_super2(sb)) { + do { + if (*min > 2) + return UINT_MAX; + ret = le32_to_cpu(es->s_backup_bgs[*min - 1]); + *min += 1; + } while (!ret); + return ret; + } + + if (!ext4_has_feature_sparse_super(sb)) { + ret = *min; + *min += 1; + return ret; + } + + if (*five < *min) { + min = five; + mult = 5; + } + if (*seven < *min) { + min = seven; + mult = 7; + } + + ret = *min; + *min *= mult; + + return ret; +} + +/* + * Check that all of the backup GDT blocks are held in the primary GDT block. + * It is assumed that they are stored in group order. Returns the number of + * groups in current filesystem that have BACKUPS, or -ve error code. + */ +static int verify_reserved_gdb(struct super_block *sb, + ext4_group_t end, + struct buffer_head *primary) +{ + const ext4_fsblk_t blk = primary->b_blocknr; + unsigned three = 1; + unsigned five = 5; + unsigned seven = 7; + unsigned grp; + __le32 *p = (__le32 *)primary->b_data; + int gdbackups = 0; + + while ((grp = ext4_list_backups(sb, &three, &five, &seven)) < end) { + if (le32_to_cpu(*p++) != + grp * EXT4_BLOCKS_PER_GROUP(sb) + blk){ + ext4_warning(sb, "reserved GDT %llu" + " missing grp %d (%llu)", + blk, grp, + grp * + (ext4_fsblk_t)EXT4_BLOCKS_PER_GROUP(sb) + + blk); + return -EINVAL; + } + if (++gdbackups > EXT4_ADDR_PER_BLOCK(sb)) + return -EFBIG; + } + + return gdbackups; +} + +/* + * Called when we need to bring a reserved group descriptor table block into + * use from the resize inode. The primary copy of the new GDT block currently + * is an indirect block (under the double indirect block in the resize inode). + * The new backup GDT blocks will be stored as leaf blocks in this indirect + * block, in group order. Even though we know all the block numbers we need, + * we check to ensure that the resize inode has actually reserved these blocks. + * + * Don't need to update the block bitmaps because the blocks are still in use. + * + * We get all of the error cases out of the way, so that we are sure to not + * fail once we start modifying the data on disk, because JBD has no rollback. + */ +static int add_new_gdb(handle_t *handle, struct inode *inode, + ext4_group_t group) +{ + struct super_block *sb = inode->i_sb; + struct ext4_super_block *es = EXT4_SB(sb)->s_es; + unsigned long gdb_num = group / EXT4_DESC_PER_BLOCK(sb); + ext4_fsblk_t gdblock = EXT4_SB(sb)->s_sbh->b_blocknr + 1 + gdb_num; + struct buffer_head **o_group_desc, **n_group_desc = NULL; + struct buffer_head *dind = NULL; + struct buffer_head *gdb_bh = NULL; + int gdbackups; + struct ext4_iloc iloc = { .bh = NULL }; + __le32 *data; + int err; + + if (test_opt(sb, DEBUG)) + printk(KERN_DEBUG + "EXT4-fs: ext4_add_new_gdb: adding group block %lu\n", + gdb_num); + + gdb_bh = ext4_sb_bread(sb, gdblock, 0); + if (IS_ERR(gdb_bh)) + return PTR_ERR(gdb_bh); + + gdbackups = verify_reserved_gdb(sb, group, gdb_bh); + if (gdbackups < 0) { + err = gdbackups; + goto errout; + } + + data = EXT4_I(inode)->i_data + EXT4_DIND_BLOCK; + dind = ext4_sb_bread(sb, le32_to_cpu(*data), 0); + if (IS_ERR(dind)) { + err = PTR_ERR(dind); + dind = NULL; + goto errout; + } + + data = (__le32 *)dind->b_data; + if (le32_to_cpu(data[gdb_num % EXT4_ADDR_PER_BLOCK(sb)]) != gdblock) { + ext4_warning(sb, "new group %u GDT block %llu not reserved", + group, gdblock); + err = -EINVAL; + goto errout; + } + + 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 (unlikely(err)) + goto errout; + + BUFFER_TRACE(gdb_bh, "get_write_access"); + err = ext4_journal_get_write_access(handle, sb, gdb_bh, EXT4_JTR_NONE); + if (unlikely(err)) + goto errout; + + BUFFER_TRACE(dind, "get_write_access"); + err = ext4_journal_get_write_access(handle, sb, dind, EXT4_JTR_NONE); + if (unlikely(err)) { + ext4_std_error(sb, err); + goto errout; + } + + /* ext4_reserve_inode_write() gets a reference on the iloc */ + err = ext4_reserve_inode_write(handle, inode, &iloc); + if (unlikely(err)) + goto errout; + + n_group_desc = kvmalloc((gdb_num + 1) * sizeof(struct buffer_head *), + GFP_KERNEL); + if (!n_group_desc) { + err = -ENOMEM; + ext4_warning(sb, "not enough memory for %lu groups", + gdb_num + 1); + goto errout; + } + + /* + * Finally, we have all of the possible failures behind us... + * + * Remove new GDT block from inode double-indirect block and clear out + * the new GDT block for use (which also "frees" the backup GDT blocks + * from the reserved inode). We don't need to change the bitmaps for + * these blocks, because they are marked as in-use from being in the + * reserved inode, and will become GDT blocks (primary and backup). + */ + data[gdb_num % EXT4_ADDR_PER_BLOCK(sb)] = 0; + err = ext4_handle_dirty_metadata(handle, NULL, dind); + if (unlikely(err)) { + ext4_std_error(sb, err); + goto errout; + } + inode->i_blocks -= (gdbackups + 1) * sb->s_blocksize >> + (9 - EXT4_SB(sb)->s_cluster_bits); + ext4_mark_iloc_dirty(handle, inode, &iloc); + memset(gdb_bh->b_data, 0, sb->s_blocksize); + err = ext4_handle_dirty_metadata(handle, NULL, gdb_bh); + if (unlikely(err)) { + ext4_std_error(sb, err); + iloc.bh = NULL; + goto errout; + } + brelse(dind); + + rcu_read_lock(); + o_group_desc = rcu_dereference(EXT4_SB(sb)->s_group_desc); + memcpy(n_group_desc, o_group_desc, + EXT4_SB(sb)->s_gdb_count * sizeof(struct buffer_head *)); + rcu_read_unlock(); + n_group_desc[gdb_num] = gdb_bh; + rcu_assign_pointer(EXT4_SB(sb)->s_group_desc, n_group_desc); + EXT4_SB(sb)->s_gdb_count++; + ext4_kvfree_array_rcu(o_group_desc); + + lock_buffer(EXT4_SB(sb)->s_sbh); + le16_add_cpu(&es->s_reserved_gdt_blocks, -1); + ext4_superblock_csum_set(sb); + unlock_buffer(EXT4_SB(sb)->s_sbh); + err = ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh); + if (err) + ext4_std_error(sb, err); + return err; +errout: + kvfree(n_group_desc); + brelse(iloc.bh); + brelse(dind); + brelse(gdb_bh); + + ext4_debug("leaving with error %d\n", err); + return err; +} + +/* + * If there is no available space in the existing block group descriptors for + * the new block group and there are no reserved block group descriptors, then + * the meta_bg feature will get enabled, and es->s_first_meta_bg will get set + * to the first block group that is managed using meta_bg and s_first_meta_bg + * must be a multiple of EXT4_DESC_PER_BLOCK(sb). + * This function will be called when first group of meta_bg is added to bring + * new group descriptors block of new added meta_bg. + */ +static int add_new_gdb_meta_bg(struct super_block *sb, + handle_t *handle, ext4_group_t group) { + ext4_fsblk_t gdblock; + struct buffer_head *gdb_bh; + struct buffer_head **o_group_desc, **n_group_desc; + unsigned long gdb_num = group / EXT4_DESC_PER_BLOCK(sb); + int err; + + gdblock = ext4_group_first_block_no(sb, group) + + ext4_bg_has_super(sb, group); + gdb_bh = ext4_sb_bread(sb, gdblock, 0); + if (IS_ERR(gdb_bh)) + return PTR_ERR(gdb_bh); + n_group_desc = kvmalloc((gdb_num + 1) * sizeof(struct buffer_head *), + GFP_KERNEL); + if (!n_group_desc) { + brelse(gdb_bh); + err = -ENOMEM; + ext4_warning(sb, "not enough memory for %lu groups", + gdb_num + 1); + return err; + } + + rcu_read_lock(); + o_group_desc = rcu_dereference(EXT4_SB(sb)->s_group_desc); + memcpy(n_group_desc, o_group_desc, + EXT4_SB(sb)->s_gdb_count * sizeof(struct buffer_head *)); + rcu_read_unlock(); + n_group_desc[gdb_num] = gdb_bh; + + BUFFER_TRACE(gdb_bh, "get_write_access"); + err = ext4_journal_get_write_access(handle, sb, gdb_bh, EXT4_JTR_NONE); + if (err) { + kvfree(n_group_desc); + brelse(gdb_bh); + return err; + } + + rcu_assign_pointer(EXT4_SB(sb)->s_group_desc, n_group_desc); + EXT4_SB(sb)->s_gdb_count++; + ext4_kvfree_array_rcu(o_group_desc); + return err; +} + +/* + * Called when we are adding a new group which has a backup copy of each of + * the GDT blocks (i.e. sparse group) and there are reserved GDT blocks. + * We need to add these reserved backup GDT blocks to the resize inode, so + * that they are kept for future resizing and not allocated to files. + * + * Each reserved backup GDT block will go into a different indirect block. + * The indirect blocks are actually the primary reserved GDT blocks, + * so we know in advance what their block numbers are. We only get the + * double-indirect block to verify it is pointing to the primary reserved + * GDT blocks so we don't overwrite a data block by accident. The reserved + * backup GDT blocks are stored in their reserved primary GDT block. + */ +static int reserve_backup_gdb(handle_t *handle, struct inode *inode, + ext4_group_t group) +{ + struct super_block *sb = inode->i_sb; + int reserved_gdb =le16_to_cpu(EXT4_SB(sb)->s_es->s_reserved_gdt_blocks); + int cluster_bits = EXT4_SB(sb)->s_cluster_bits; + struct buffer_head **primary; + struct buffer_head *dind; + struct ext4_iloc iloc; + ext4_fsblk_t blk; + __le32 *data, *end; + int gdbackups = 0; + int res, i; + int err; + + primary = kmalloc_array(reserved_gdb, sizeof(*primary), GFP_NOFS); + if (!primary) + return -ENOMEM; + + data = EXT4_I(inode)->i_data + EXT4_DIND_BLOCK; + dind = ext4_sb_bread(sb, le32_to_cpu(*data), 0); + if (IS_ERR(dind)) { + err = PTR_ERR(dind); + dind = NULL; + goto exit_free; + } + + blk = EXT4_SB(sb)->s_sbh->b_blocknr + 1 + EXT4_SB(sb)->s_gdb_count; + data = (__le32 *)dind->b_data + (EXT4_SB(sb)->s_gdb_count % + EXT4_ADDR_PER_BLOCK(sb)); + end = (__le32 *)dind->b_data + EXT4_ADDR_PER_BLOCK(sb); + + /* Get each reserved primary GDT block and verify it holds backups */ + for (res = 0; res < reserved_gdb; res++, blk++) { + if (le32_to_cpu(*data) != blk) { + ext4_warning(sb, "reserved block %llu" + " not at offset %ld", + blk, + (long)(data - (__le32 *)dind->b_data)); + err = -EINVAL; + goto exit_bh; + } + primary[res] = ext4_sb_bread(sb, blk, 0); + if (IS_ERR(primary[res])) { + err = PTR_ERR(primary[res]); + primary[res] = NULL; + goto exit_bh; + } + gdbackups = verify_reserved_gdb(sb, group, primary[res]); + if (gdbackups < 0) { + brelse(primary[res]); + err = gdbackups; + goto exit_bh; + } + if (++data >= end) + data = (__le32 *)dind->b_data; + } + + for (i = 0; i < reserved_gdb; i++) { + BUFFER_TRACE(primary[i], "get_write_access"); + if ((err = ext4_journal_get_write_access(handle, sb, primary[i], + EXT4_JTR_NONE))) + goto exit_bh; + } + + if ((err = ext4_reserve_inode_write(handle, inode, &iloc))) + goto exit_bh; + + /* + * Finally we can add each of the reserved backup GDT blocks from + * the new group to its reserved primary GDT block. + */ + blk = group * EXT4_BLOCKS_PER_GROUP(sb); + for (i = 0; i < reserved_gdb; i++) { + int err2; + data = (__le32 *)primary[i]->b_data; + data[gdbackups] = cpu_to_le32(blk + primary[i]->b_blocknr); + err2 = ext4_handle_dirty_metadata(handle, NULL, primary[i]); + if (!err) + err = err2; + } + + inode->i_blocks += reserved_gdb * sb->s_blocksize >> (9 - cluster_bits); + ext4_mark_iloc_dirty(handle, inode, &iloc); + +exit_bh: + while (--res >= 0) + brelse(primary[res]); + brelse(dind); + +exit_free: + kfree(primary); + + return err; +} + +static inline void ext4_set_block_group_nr(struct super_block *sb, char *data, + ext4_group_t group) +{ + struct ext4_super_block *es = (struct ext4_super_block *) data; + + es->s_block_group_nr = cpu_to_le16(group); + if (ext4_has_feature_metadata_csum(sb)) + es->s_checksum = ext4_superblock_csum(es); +} + +/* + * Update the backup copies of the ext4 metadata. These don't need to be part + * of the main resize transaction, because e2fsck will re-write them if there + * is a problem (basically only OOM will cause a problem). However, we + * _should_ update the backups if possible, in case the primary gets trashed + * for some reason and we need to run e2fsck from a backup superblock. The + * important part is that the new block and inode counts are in the backup + * superblocks, and the location of the new group metadata in the GDT backups. + * + * We do not need take the s_resize_lock for this, because these + * blocks are not otherwise touched by the filesystem code when it is + * mounted. We don't need to worry about last changing from + * sbi->s_groups_count, because the worst that can happen is that we + * do not copy the full number of backups at this time. The resize + * which changed s_groups_count will backup again. + */ +static void update_backups(struct super_block *sb, sector_t blk_off, char *data, + int size, int meta_bg) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + ext4_group_t last; + const int bpg = EXT4_BLOCKS_PER_GROUP(sb); + unsigned three = 1; + unsigned five = 5; + unsigned seven = 7; + ext4_group_t group = 0; + int rest = sb->s_blocksize - size; + handle_t *handle; + int err = 0, err2; + + handle = ext4_journal_start_sb(sb, EXT4_HT_RESIZE, EXT4_MAX_TRANS_DATA); + if (IS_ERR(handle)) { + group = 1; + err = PTR_ERR(handle); + goto exit_err; + } + + if (meta_bg == 0) { + group = ext4_list_backups(sb, &three, &five, &seven); + last = sbi->s_groups_count; + } else { + group = ext4_get_group_number(sb, blk_off) + 1; + last = (ext4_group_t)(group + EXT4_DESC_PER_BLOCK(sb) - 2); + } + + while (group < sbi->s_groups_count) { + struct buffer_head *bh; + ext4_fsblk_t backup_block; + int has_super = ext4_bg_has_super(sb, group); + ext4_fsblk_t first_block = ext4_group_first_block_no(sb, group); + + /* Out of journal space, and can't get more - abort - so sad */ + err = ext4_resize_ensure_credits_batch(handle, 1); + if (err < 0) + break; + + if (meta_bg == 0) + backup_block = ((ext4_fsblk_t)group) * bpg + blk_off; + else + backup_block = first_block + has_super; + + bh = sb_getblk(sb, backup_block); + if (unlikely(!bh)) { + err = -ENOMEM; + break; + } + ext4_debug("update metadata backup %llu(+%llu)\n", + backup_block, backup_block - + ext4_group_first_block_no(sb, group)); + BUFFER_TRACE(bh, "get_write_access"); + if ((err = ext4_journal_get_write_access(handle, sb, bh, + EXT4_JTR_NONE))) { + brelse(bh); + break; + } + lock_buffer(bh); + memcpy(bh->b_data, data, size); + if (rest) + memset(bh->b_data + size, 0, rest); + if (has_super && (backup_block == first_block)) + ext4_set_block_group_nr(sb, bh->b_data, group); + set_buffer_uptodate(bh); + unlock_buffer(bh); + err = ext4_handle_dirty_metadata(handle, NULL, bh); + if (unlikely(err)) + ext4_std_error(sb, err); + brelse(bh); + + if (meta_bg == 0) + group = ext4_list_backups(sb, &three, &five, &seven); + else if (group == last) + break; + else + group = last; + } + if ((err2 = ext4_journal_stop(handle)) && !err) + err = err2; + + /* + * Ugh! Need to have e2fsck write the backup copies. It is too + * late to revert the resize, we shouldn't fail just because of + * the backup copies (they are only needed in case of corruption). + * + * However, if we got here we have a journal problem too, so we + * can't really start a transaction to mark the superblock. + * Chicken out and just set the flag on the hope it will be written + * to disk, and if not - we will simply wait until next fsck. + */ +exit_err: + if (err) { + ext4_warning(sb, "can't update backup for group %u (err %d), " + "forcing fsck on next reboot", group, err); + sbi->s_mount_state &= ~EXT4_VALID_FS; + sbi->s_es->s_state &= cpu_to_le16(~EXT4_VALID_FS); + mark_buffer_dirty(sbi->s_sbh); + } +} + +/* + * ext4_add_new_descs() adds @count group descriptor of groups + * starting at @group + * + * @handle: journal handle + * @sb: super block + * @group: the group no. of the first group desc to be added + * @resize_inode: the resize inode + * @count: number of group descriptors to be added + */ +static int ext4_add_new_descs(handle_t *handle, struct super_block *sb, + ext4_group_t group, struct inode *resize_inode, + ext4_group_t count) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_super_block *es = sbi->s_es; + struct buffer_head *gdb_bh; + int i, gdb_off, gdb_num, err = 0; + int meta_bg; + + meta_bg = ext4_has_feature_meta_bg(sb); + for (i = 0; i < count; i++, group++) { + int reserved_gdb = ext4_bg_has_super(sb, group) ? + le16_to_cpu(es->s_reserved_gdt_blocks) : 0; + + gdb_off = group % EXT4_DESC_PER_BLOCK(sb); + gdb_num = group / EXT4_DESC_PER_BLOCK(sb); + + /* + * We will only either add reserved group blocks to a backup group + * or remove reserved blocks for the first group in a new group block. + * Doing both would be mean more complex code, and sane people don't + * use non-sparse filesystems anymore. This is already checked above. + */ + if (gdb_off) { + gdb_bh = sbi_array_rcu_deref(sbi, s_group_desc, + gdb_num); + BUFFER_TRACE(gdb_bh, "get_write_access"); + err = ext4_journal_get_write_access(handle, sb, gdb_bh, + EXT4_JTR_NONE); + + if (!err && reserved_gdb && ext4_bg_num_gdb(sb, group)) + err = reserve_backup_gdb(handle, resize_inode, group); + } else if (meta_bg != 0) { + err = add_new_gdb_meta_bg(sb, handle, group); + } else { + err = add_new_gdb(handle, resize_inode, group); + } + if (err) + break; + } + return err; +} + +static struct buffer_head *ext4_get_bitmap(struct super_block *sb, __u64 block) +{ + struct buffer_head *bh = sb_getblk(sb, block); + if (unlikely(!bh)) + return NULL; + if (!bh_uptodate_or_lock(bh)) { + if (ext4_read_bh(bh, 0, NULL, false) < 0) { + brelse(bh); + return NULL; + } + } + + return bh; +} + +static int ext4_set_bitmap_checksums(struct super_block *sb, + struct ext4_group_desc *gdp, + struct ext4_new_group_data *group_data) +{ + struct buffer_head *bh; + + if (!ext4_has_feature_metadata_csum(sb)) + return 0; + + bh = ext4_get_bitmap(sb, group_data->inode_bitmap); + if (!bh) + return -EIO; + ext4_inode_bitmap_csum_set(sb, gdp, bh); + brelse(bh); + + bh = ext4_get_bitmap(sb, group_data->block_bitmap); + if (!bh) + return -EIO; + ext4_block_bitmap_csum_set(sb, gdp, bh); + brelse(bh); + + return 0; +} + +/* + * ext4_setup_new_descs() will set up the group descriptor descriptors of a flex bg + */ +static int ext4_setup_new_descs(handle_t *handle, struct super_block *sb, + struct ext4_new_flex_group_data *flex_gd) +{ + struct ext4_new_group_data *group_data = flex_gd->groups; + struct ext4_group_desc *gdp; + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct buffer_head *gdb_bh; + ext4_group_t group; + __u16 *bg_flags = flex_gd->bg_flags; + int i, gdb_off, gdb_num, err = 0; + + + for (i = 0; i < flex_gd->count; i++, group_data++, bg_flags++) { + group = group_data->group; + + gdb_off = group % EXT4_DESC_PER_BLOCK(sb); + gdb_num = group / EXT4_DESC_PER_BLOCK(sb); + + /* + * get_write_access() has been called on gdb_bh by ext4_add_new_desc(). + */ + gdb_bh = sbi_array_rcu_deref(sbi, s_group_desc, gdb_num); + /* Update group descriptor block for new group */ + gdp = (struct ext4_group_desc *)(gdb_bh->b_data + + gdb_off * EXT4_DESC_SIZE(sb)); + + memset(gdp, 0, EXT4_DESC_SIZE(sb)); + ext4_block_bitmap_set(sb, gdp, group_data->block_bitmap); + ext4_inode_bitmap_set(sb, gdp, group_data->inode_bitmap); + err = ext4_set_bitmap_checksums(sb, gdp, group_data); + if (err) { + ext4_std_error(sb, err); + break; + } + + ext4_inode_table_set(sb, gdp, group_data->inode_table); + ext4_free_group_clusters_set(sb, gdp, + group_data->free_clusters_count); + ext4_free_inodes_set(sb, gdp, EXT4_INODES_PER_GROUP(sb)); + if (ext4_has_group_desc_csum(sb)) + ext4_itable_unused_set(sb, gdp, + EXT4_INODES_PER_GROUP(sb)); + gdp->bg_flags = cpu_to_le16(*bg_flags); + ext4_group_desc_csum_set(sb, group, gdp); + + err = ext4_handle_dirty_metadata(handle, NULL, gdb_bh); + if (unlikely(err)) { + ext4_std_error(sb, err); + break; + } + + /* + * We can allocate memory for mb_alloc based on the new group + * descriptor + */ + err = ext4_mb_add_groupinfo(sb, group, gdp); + if (err) + break; + } + return err; +} + +static void ext4_add_overhead(struct super_block *sb, + const ext4_fsblk_t overhead) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_super_block *es = sbi->s_es; + + sbi->s_overhead += overhead; + es->s_overhead_clusters = cpu_to_le32(sbi->s_overhead); + smp_wmb(); +} + +/* + * ext4_update_super() updates the super block so that the newly added + * groups can be seen by the filesystem. + * + * @sb: super block + * @flex_gd: new added groups + */ +static void ext4_update_super(struct super_block *sb, + struct ext4_new_flex_group_data *flex_gd) +{ + ext4_fsblk_t blocks_count = 0; + ext4_fsblk_t free_blocks = 0; + ext4_fsblk_t reserved_blocks = 0; + struct ext4_new_group_data *group_data = flex_gd->groups; + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_super_block *es = sbi->s_es; + int i; + + BUG_ON(flex_gd->count == 0 || group_data == NULL); + /* + * Make the new blocks and inodes valid next. We do this before + * increasing the group count so that once the group is enabled, + * all of its blocks and inodes are already valid. + * + * We always allocate group-by-group, then block-by-block or + * inode-by-inode within a group, so enabling these + * blocks/inodes before the group is live won't actually let us + * allocate the new space yet. + */ + for (i = 0; i < flex_gd->count; i++) { + blocks_count += group_data[i].blocks_count; + free_blocks += EXT4_C2B(sbi, group_data[i].free_clusters_count); + } + + reserved_blocks = ext4_r_blocks_count(es) * 100; + reserved_blocks = div64_u64(reserved_blocks, ext4_blocks_count(es)); + reserved_blocks *= blocks_count; + do_div(reserved_blocks, 100); + + lock_buffer(sbi->s_sbh); + ext4_blocks_count_set(es, ext4_blocks_count(es) + blocks_count); + ext4_free_blocks_count_set(es, ext4_free_blocks_count(es) + free_blocks); + le32_add_cpu(&es->s_inodes_count, EXT4_INODES_PER_GROUP(sb) * + flex_gd->count); + le32_add_cpu(&es->s_free_inodes_count, EXT4_INODES_PER_GROUP(sb) * + flex_gd->count); + + ext4_debug("free blocks count %llu", ext4_free_blocks_count(es)); + /* + * We need to protect s_groups_count against other CPUs seeing + * inconsistent state in the superblock. + * + * The precise rules we use are: + * + * * Writers must perform a smp_wmb() after updating all + * dependent data and before modifying the groups count + * + * * Readers must perform an smp_rmb() after reading the groups + * count and before reading any dependent data. + * + * NB. These rules can be relaxed when checking the group count + * while freeing data, as we can only allocate from a block + * group after serialising against the group count, and we can + * only then free after serialising in turn against that + * allocation. + */ + smp_wmb(); + + /* Update the global fs size fields */ + sbi->s_groups_count += flex_gd->count; + sbi->s_blockfile_groups = min_t(ext4_group_t, sbi->s_groups_count, + (EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb))); + + /* Update the reserved block counts only once the new group is + * active. */ + ext4_r_blocks_count_set(es, ext4_r_blocks_count(es) + + reserved_blocks); + + /* Update the free space counts */ + percpu_counter_add(&sbi->s_freeclusters_counter, + EXT4_NUM_B2C(sbi, free_blocks)); + percpu_counter_add(&sbi->s_freeinodes_counter, + EXT4_INODES_PER_GROUP(sb) * flex_gd->count); + + ext4_debug("free blocks count %llu", + percpu_counter_read(&sbi->s_freeclusters_counter)); + if (ext4_has_feature_flex_bg(sb) && sbi->s_log_groups_per_flex) { + ext4_group_t flex_group; + struct flex_groups *fg; + + flex_group = ext4_flex_group(sbi, group_data[0].group); + fg = sbi_array_rcu_deref(sbi, s_flex_groups, flex_group); + atomic64_add(EXT4_NUM_B2C(sbi, free_blocks), + &fg->free_clusters); + atomic_add(EXT4_INODES_PER_GROUP(sb) * flex_gd->count, + &fg->free_inodes); + } + + /* + * Update the fs overhead information. + * + * For bigalloc, if the superblock already has a properly calculated + * overhead, update it with a value based on numbers already computed + * above for the newly allocated capacity. + */ + if (ext4_has_feature_bigalloc(sb) && (sbi->s_overhead != 0)) + ext4_add_overhead(sb, + EXT4_NUM_B2C(sbi, blocks_count - free_blocks)); + else + ext4_calculate_overhead(sb); + es->s_overhead_clusters = cpu_to_le32(sbi->s_overhead); + + ext4_superblock_csum_set(sb); + unlock_buffer(sbi->s_sbh); + if (test_opt(sb, DEBUG)) + printk(KERN_DEBUG "EXT4-fs: added group %u:" + "%llu blocks(%llu free %llu reserved)\n", flex_gd->count, + blocks_count, free_blocks, reserved_blocks); +} + +/* Add a flex group to an fs. Ensure we handle all possible error conditions + * _before_ we start modifying the filesystem, because we cannot abort the + * transaction and not have it write the data to disk. + */ +static int ext4_flex_group_add(struct super_block *sb, + struct inode *resize_inode, + struct ext4_new_flex_group_data *flex_gd) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_super_block *es = sbi->s_es; + ext4_fsblk_t o_blocks_count; + ext4_grpblk_t last; + ext4_group_t group; + handle_t *handle; + unsigned reserved_gdb; + int err = 0, err2 = 0, credit; + + BUG_ON(!flex_gd->count || !flex_gd->groups || !flex_gd->bg_flags); + + reserved_gdb = le16_to_cpu(es->s_reserved_gdt_blocks); + o_blocks_count = ext4_blocks_count(es); + ext4_get_group_no_and_offset(sb, o_blocks_count, &group, &last); + BUG_ON(last); + + err = setup_new_flex_group_blocks(sb, flex_gd); + if (err) + goto exit; + /* + * We will always be modifying at least the superblock and GDT + * blocks. If we are adding a group past the last current GDT block, + * we will also modify the inode and the dindirect block. If we + * are adding a group with superblock/GDT backups we will also + * modify each of the reserved GDT dindirect blocks. + */ + credit = 3; /* sb, resize inode, resize inode dindirect */ + /* GDT blocks */ + credit += 1 + DIV_ROUND_UP(flex_gd->count, EXT4_DESC_PER_BLOCK(sb)); + credit += reserved_gdb; /* Reserved GDT dindirect blocks */ + handle = ext4_journal_start_sb(sb, EXT4_HT_RESIZE, credit); + if (IS_ERR(handle)) { + err = PTR_ERR(handle); + goto exit; + } + + BUFFER_TRACE(sbi->s_sbh, "get_write_access"); + err = ext4_journal_get_write_access(handle, sb, sbi->s_sbh, + EXT4_JTR_NONE); + if (err) + goto exit_journal; + + group = flex_gd->groups[0].group; + BUG_ON(group != sbi->s_groups_count); + err = ext4_add_new_descs(handle, sb, group, + resize_inode, flex_gd->count); + if (err) + goto exit_journal; + + err = ext4_setup_new_descs(handle, sb, flex_gd); + if (err) + goto exit_journal; + + ext4_update_super(sb, flex_gd); + + err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh); + +exit_journal: + err2 = ext4_journal_stop(handle); + if (!err) + err = err2; + + if (!err) { + int gdb_num = group / EXT4_DESC_PER_BLOCK(sb); + int gdb_num_end = ((group + flex_gd->count - 1) / + EXT4_DESC_PER_BLOCK(sb)); + int meta_bg = ext4_has_feature_meta_bg(sb) && + gdb_num >= le32_to_cpu(es->s_first_meta_bg); + sector_t padding_blocks = meta_bg ? 0 : sbi->s_sbh->b_blocknr - + ext4_group_first_block_no(sb, 0); + + update_backups(sb, ext4_group_first_block_no(sb, 0), + (char *)es, sizeof(struct ext4_super_block), 0); + for (; gdb_num <= gdb_num_end; gdb_num++) { + struct buffer_head *gdb_bh; + + gdb_bh = sbi_array_rcu_deref(sbi, s_group_desc, + gdb_num); + update_backups(sb, gdb_bh->b_blocknr - padding_blocks, + gdb_bh->b_data, gdb_bh->b_size, meta_bg); + } + } +exit: + return err; +} + +static int ext4_setup_next_flex_gd(struct super_block *sb, + struct ext4_new_flex_group_data *flex_gd, + ext4_fsblk_t n_blocks_count) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_super_block *es = sbi->s_es; + struct ext4_new_group_data *group_data = flex_gd->groups; + ext4_fsblk_t o_blocks_count; + ext4_group_t n_group; + ext4_group_t group; + ext4_group_t last_group; + ext4_grpblk_t last; + ext4_grpblk_t clusters_per_group; + unsigned long i; + + clusters_per_group = EXT4_CLUSTERS_PER_GROUP(sb); + + o_blocks_count = ext4_blocks_count(es); + + if (o_blocks_count == n_blocks_count) + return 0; + + ext4_get_group_no_and_offset(sb, o_blocks_count, &group, &last); + BUG_ON(last); + ext4_get_group_no_and_offset(sb, n_blocks_count - 1, &n_group, &last); + + last_group = group | (flex_gd->resize_bg - 1); + if (last_group > n_group) + last_group = n_group; + + flex_gd->count = last_group - group + 1; + + for (i = 0; i < flex_gd->count; i++) { + int overhead; + + group_data[i].group = group + i; + group_data[i].blocks_count = EXT4_BLOCKS_PER_GROUP(sb); + overhead = ext4_group_overhead_blocks(sb, group + i); + group_data[i].mdata_blocks = overhead; + group_data[i].free_clusters_count = EXT4_CLUSTERS_PER_GROUP(sb); + if (ext4_has_group_desc_csum(sb)) { + flex_gd->bg_flags[i] = EXT4_BG_BLOCK_UNINIT | + EXT4_BG_INODE_UNINIT; + if (!test_opt(sb, INIT_INODE_TABLE)) + flex_gd->bg_flags[i] |= EXT4_BG_INODE_ZEROED; + } else + flex_gd->bg_flags[i] = EXT4_BG_INODE_ZEROED; + } + + if (last_group == n_group && ext4_has_group_desc_csum(sb)) + /* We need to initialize block bitmap of last group. */ + flex_gd->bg_flags[i - 1] &= ~EXT4_BG_BLOCK_UNINIT; + + if ((last_group == n_group) && (last != clusters_per_group - 1)) { + group_data[i - 1].blocks_count = EXT4_C2B(sbi, last + 1); + group_data[i - 1].free_clusters_count -= clusters_per_group - + last - 1; + } + + return 1; +} + +/* Add group descriptor data to an existing or new group descriptor block. + * Ensure we handle all possible error conditions _before_ we start modifying + * the filesystem, because we cannot abort the transaction and not have it + * write the data to disk. + * + * If we are on a GDT block boundary, we need to get the reserved GDT block. + * Otherwise, we may need to add backup GDT blocks for a sparse group. + * + * We only need to hold the superblock lock while we are actually adding + * in the new group's counts to the superblock. Prior to that we have + * not really "added" the group at all. We re-check that we are still + * adding in the last group in case things have changed since verifying. + */ +int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input) +{ + struct ext4_new_flex_group_data flex_gd; + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_super_block *es = sbi->s_es; + int reserved_gdb = ext4_bg_has_super(sb, input->group) ? + le16_to_cpu(es->s_reserved_gdt_blocks) : 0; + struct inode *inode = NULL; + int gdb_off; + int err; + __u16 bg_flags = 0; + + gdb_off = input->group % EXT4_DESC_PER_BLOCK(sb); + + if (gdb_off == 0 && !ext4_has_feature_sparse_super(sb)) { + ext4_warning(sb, "Can't resize non-sparse filesystem further"); + return -EPERM; + } + + if (ext4_blocks_count(es) + input->blocks_count < + ext4_blocks_count(es)) { + ext4_warning(sb, "blocks_count overflow"); + return -EINVAL; + } + + if (le32_to_cpu(es->s_inodes_count) + EXT4_INODES_PER_GROUP(sb) < + le32_to_cpu(es->s_inodes_count)) { + ext4_warning(sb, "inodes_count overflow"); + return -EINVAL; + } + + if (reserved_gdb || gdb_off == 0) { + if (!ext4_has_feature_resize_inode(sb) || + !le16_to_cpu(es->s_reserved_gdt_blocks)) { + ext4_warning(sb, + "No reserved GDT blocks, can't resize"); + return -EPERM; + } + inode = ext4_iget(sb, EXT4_RESIZE_INO, EXT4_IGET_SPECIAL); + if (IS_ERR(inode)) { + ext4_warning(sb, "Error opening resize inode"); + return PTR_ERR(inode); + } + } + + + err = verify_group_input(sb, input); + if (err) + goto out; + + err = ext4_alloc_flex_bg_array(sb, input->group + 1); + if (err) + goto out; + + err = ext4_mb_alloc_groupinfo(sb, input->group + 1); + if (err) + goto out; + + flex_gd.count = 1; + flex_gd.groups = input; + flex_gd.bg_flags = &bg_flags; + err = ext4_flex_group_add(sb, inode, &flex_gd); +out: + iput(inode); + return err; +} /* ext4_group_add */ + +/* + * extend a group without checking assuming that checking has been done. + */ +static int ext4_group_extend_no_check(struct super_block *sb, + ext4_fsblk_t o_blocks_count, ext4_grpblk_t add) +{ + struct ext4_super_block *es = EXT4_SB(sb)->s_es; + handle_t *handle; + int err = 0, err2; + + /* We will update the superblock, one block bitmap, and + * one group descriptor via ext4_group_add_blocks(). + */ + handle = ext4_journal_start_sb(sb, EXT4_HT_RESIZE, 3); + if (IS_ERR(handle)) { + err = PTR_ERR(handle); + ext4_warning(sb, "error %d on journal start", err); + return err; + } + + 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) { + ext4_warning(sb, "error %d on journal write access", err); + goto errout; + } + + lock_buffer(EXT4_SB(sb)->s_sbh); + ext4_blocks_count_set(es, o_blocks_count + add); + ext4_free_blocks_count_set(es, ext4_free_blocks_count(es) + add); + ext4_superblock_csum_set(sb); + unlock_buffer(EXT4_SB(sb)->s_sbh); + ext4_debug("freeing blocks %llu through %llu\n", o_blocks_count, + o_blocks_count + add); + /* We add the blocks to the bitmap and set the group need init bit */ + err = ext4_group_add_blocks(handle, sb, o_blocks_count, add); + if (err) + goto errout; + ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh); + ext4_debug("freed blocks %llu through %llu\n", o_blocks_count, + o_blocks_count + add); +errout: + err2 = ext4_journal_stop(handle); + if (err2 && !err) + err = err2; + + if (!err) { + if (test_opt(sb, DEBUG)) + printk(KERN_DEBUG "EXT4-fs: extended group to %llu " + "blocks\n", ext4_blocks_count(es)); + update_backups(sb, ext4_group_first_block_no(sb, 0), + (char *)es, sizeof(struct ext4_super_block), 0); + } + return err; +} + +/* + * Extend the filesystem to the new number of blocks specified. This entry + * point is only used to extend the current filesystem to the end of the last + * existing group. It can be accessed via ioctl, or by "remount,resize=<size>" + * for emergencies (because it has no dependencies on reserved blocks). + * + * If we _really_ wanted, we could use default values to call ext4_group_add() + * allow the "remount" trick to work for arbitrary resizing, assuming enough + * GDT blocks are reserved to grow to the desired size. + */ +int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es, + ext4_fsblk_t n_blocks_count) +{ + ext4_fsblk_t o_blocks_count; + ext4_grpblk_t last; + ext4_grpblk_t add; + struct buffer_head *bh; + ext4_group_t group; + + o_blocks_count = ext4_blocks_count(es); + + if (test_opt(sb, DEBUG)) + ext4_msg(sb, KERN_DEBUG, + "extending last group from %llu to %llu blocks", + o_blocks_count, n_blocks_count); + + if (n_blocks_count == 0 || n_blocks_count == o_blocks_count) + return 0; + + if (n_blocks_count > (sector_t)(~0ULL) >> (sb->s_blocksize_bits - 9)) { + ext4_msg(sb, KERN_ERR, + "filesystem too large to resize to %llu blocks safely", + n_blocks_count); + return -EINVAL; + } + + if (n_blocks_count < o_blocks_count) { + ext4_warning(sb, "can't shrink FS - resize aborted"); + return -EINVAL; + } + + /* Handle the remaining blocks in the last group only. */ + ext4_get_group_no_and_offset(sb, o_blocks_count, &group, &last); + + if (last == 0) { + ext4_warning(sb, "need to use ext2online to resize further"); + return -EPERM; + } + + add = EXT4_BLOCKS_PER_GROUP(sb) - last; + + if (o_blocks_count + add < o_blocks_count) { + ext4_warning(sb, "blocks_count overflow"); + return -EINVAL; + } + + if (o_blocks_count + add > n_blocks_count) + add = n_blocks_count - o_blocks_count; + + if (o_blocks_count + add < n_blocks_count) + ext4_warning(sb, "will only finish group (%llu blocks, %u new)", + o_blocks_count + add, add); + + /* See if the device is actually as big as what was requested */ + bh = ext4_sb_bread(sb, o_blocks_count + add - 1, 0); + if (IS_ERR(bh)) { + ext4_warning(sb, "can't read last block, resize aborted"); + return -ENOSPC; + } + brelse(bh); + + return ext4_group_extend_no_check(sb, o_blocks_count, add); +} /* ext4_group_extend */ + + +static int num_desc_blocks(struct super_block *sb, ext4_group_t groups) +{ + return (groups + EXT4_DESC_PER_BLOCK(sb) - 1) / EXT4_DESC_PER_BLOCK(sb); +} + +/* + * Release the resize inode and drop the resize_inode feature if there + * are no more reserved gdt blocks, and then convert the file system + * to enable meta_bg + */ +static int ext4_convert_meta_bg(struct super_block *sb, struct inode *inode) +{ + handle_t *handle; + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_super_block *es = sbi->s_es; + struct ext4_inode_info *ei = EXT4_I(inode); + ext4_fsblk_t nr; + int i, ret, err = 0; + int credits = 1; + + ext4_msg(sb, KERN_INFO, "Converting file system to meta_bg"); + if (inode) { + if (es->s_reserved_gdt_blocks) { + ext4_error(sb, "Unexpected non-zero " + "s_reserved_gdt_blocks"); + return -EPERM; + } + + /* Do a quick sanity check of the resize inode */ + if (inode->i_blocks != 1 << (inode->i_blkbits - + (9 - sbi->s_cluster_bits))) + goto invalid_resize_inode; + for (i = 0; i < EXT4_N_BLOCKS; i++) { + if (i == EXT4_DIND_BLOCK) { + if (ei->i_data[i]) + continue; + else + goto invalid_resize_inode; + } + if (ei->i_data[i]) + goto invalid_resize_inode; + } + credits += 3; /* block bitmap, bg descriptor, resize inode */ + } + + handle = ext4_journal_start_sb(sb, EXT4_HT_RESIZE, credits); + if (IS_ERR(handle)) + return PTR_ERR(handle); + + BUFFER_TRACE(sbi->s_sbh, "get_write_access"); + err = ext4_journal_get_write_access(handle, sb, sbi->s_sbh, + EXT4_JTR_NONE); + if (err) + goto errout; + + lock_buffer(sbi->s_sbh); + ext4_clear_feature_resize_inode(sb); + ext4_set_feature_meta_bg(sb); + sbi->s_es->s_first_meta_bg = + cpu_to_le32(num_desc_blocks(sb, sbi->s_groups_count)); + ext4_superblock_csum_set(sb); + unlock_buffer(sbi->s_sbh); + + err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh); + if (err) { + ext4_std_error(sb, err); + goto errout; + } + + if (inode) { + nr = le32_to_cpu(ei->i_data[EXT4_DIND_BLOCK]); + ext4_free_blocks(handle, inode, NULL, nr, 1, + EXT4_FREE_BLOCKS_METADATA | + EXT4_FREE_BLOCKS_FORGET); + ei->i_data[EXT4_DIND_BLOCK] = 0; + inode->i_blocks = 0; + + err = ext4_mark_inode_dirty(handle, inode); + if (err) + ext4_std_error(sb, err); + } + +errout: + ret = ext4_journal_stop(handle); + return err ? err : ret; + +invalid_resize_inode: + ext4_error(sb, "corrupted/inconsistent resize inode"); + return -EINVAL; +} + +/* + * ext4_resize_fs() resizes a fs to new size specified by @n_blocks_count + * + * @sb: super block of the fs to be resized + * @n_blocks_count: the number of blocks resides in the resized fs + */ +int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count) +{ + struct ext4_new_flex_group_data *flex_gd = NULL; + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_super_block *es = sbi->s_es; + struct buffer_head *bh; + struct inode *resize_inode = NULL; + ext4_grpblk_t add, offset; + unsigned long n_desc_blocks; + unsigned long o_desc_blocks; + ext4_group_t o_group; + ext4_group_t n_group; + ext4_fsblk_t o_blocks_count; + ext4_fsblk_t n_blocks_count_retry = 0; + unsigned long last_update_time = 0; + int err = 0; + int meta_bg; + unsigned int flexbg_size = ext4_flex_bg_size(sbi); + + /* See if the device is actually as big as what was requested */ + bh = ext4_sb_bread(sb, n_blocks_count - 1, 0); + if (IS_ERR(bh)) { + ext4_warning(sb, "can't read last block, resize aborted"); + return -ENOSPC; + } + brelse(bh); + + /* + * For bigalloc, trim the requested size to the nearest cluster + * boundary to avoid creating an unusable filesystem. We do this + * silently, instead of returning an error, to avoid breaking + * callers that blindly resize the filesystem to the full size of + * the underlying block device. + */ + if (ext4_has_feature_bigalloc(sb)) + n_blocks_count &= ~((1 << EXT4_CLUSTER_BITS(sb)) - 1); + +retry: + o_blocks_count = ext4_blocks_count(es); + + ext4_msg(sb, KERN_INFO, "resizing filesystem from %llu " + "to %llu blocks", o_blocks_count, n_blocks_count); + + if (n_blocks_count < o_blocks_count) { + /* On-line shrinking not supported */ + ext4_warning(sb, "can't shrink FS - resize aborted"); + return -EINVAL; + } + + if (n_blocks_count == o_blocks_count) + /* Nothing need to do */ + return 0; + + n_group = ext4_get_group_number(sb, n_blocks_count - 1); + if (n_group >= (0xFFFFFFFFUL / EXT4_INODES_PER_GROUP(sb))) { + ext4_warning(sb, "resize would cause inodes_count overflow"); + return -EINVAL; + } + ext4_get_group_no_and_offset(sb, o_blocks_count - 1, &o_group, &offset); + + n_desc_blocks = num_desc_blocks(sb, n_group + 1); + o_desc_blocks = num_desc_blocks(sb, sbi->s_groups_count); + + meta_bg = ext4_has_feature_meta_bg(sb); + + if (ext4_has_feature_resize_inode(sb)) { + if (meta_bg) { + ext4_error(sb, "resize_inode and meta_bg enabled " + "simultaneously"); + return -EINVAL; + } + if (n_desc_blocks > o_desc_blocks + + le16_to_cpu(es->s_reserved_gdt_blocks)) { + n_blocks_count_retry = n_blocks_count; + n_desc_blocks = o_desc_blocks + + le16_to_cpu(es->s_reserved_gdt_blocks); + n_group = n_desc_blocks * EXT4_DESC_PER_BLOCK(sb); + n_blocks_count = (ext4_fsblk_t)n_group * + EXT4_BLOCKS_PER_GROUP(sb) + + le32_to_cpu(es->s_first_data_block); + n_group--; /* set to last group number */ + } + + if (!resize_inode) + resize_inode = ext4_iget(sb, EXT4_RESIZE_INO, + EXT4_IGET_SPECIAL); + if (IS_ERR(resize_inode)) { + ext4_warning(sb, "Error opening resize inode"); + return PTR_ERR(resize_inode); + } + } + + if ((!resize_inode && !meta_bg && n_desc_blocks > o_desc_blocks) || n_blocks_count == o_blocks_count) { + err = ext4_convert_meta_bg(sb, resize_inode); + if (err) + goto out; + if (resize_inode) { + iput(resize_inode); + resize_inode = NULL; + } + if (n_blocks_count_retry) { + n_blocks_count = n_blocks_count_retry; + n_blocks_count_retry = 0; + goto retry; + } + } + + /* + * Make sure the last group has enough space so that it's + * guaranteed to have enough space for all metadata blocks + * that it might need to hold. (We might not need to store + * the inode table blocks in the last block group, but there + * will be cases where this might be needed.) + */ + if ((ext4_group_first_block_no(sb, n_group) + + ext4_group_overhead_blocks(sb, n_group) + 2 + + sbi->s_itb_per_group + sbi->s_cluster_ratio) >= n_blocks_count) { + n_blocks_count = ext4_group_first_block_no(sb, n_group); + n_group--; + n_blocks_count_retry = 0; + if (resize_inode) { + iput(resize_inode); + resize_inode = NULL; + } + goto retry; + } + + /* extend the last group */ + if (n_group == o_group) + add = n_blocks_count - o_blocks_count; + else + add = EXT4_C2B(sbi, EXT4_CLUSTERS_PER_GROUP(sb) - (offset + 1)); + if (add > 0) { + err = ext4_group_extend_no_check(sb, o_blocks_count, add); + if (err) + goto out; + } + + if (ext4_blocks_count(es) == n_blocks_count && n_blocks_count_retry == 0) + goto out; + + err = ext4_alloc_flex_bg_array(sb, n_group + 1); + if (err) + goto out; + + err = ext4_mb_alloc_groupinfo(sb, n_group + 1); + if (err) + goto out; + + flex_gd = alloc_flex_gd(flexbg_size, o_group, n_group); + if (flex_gd == NULL) { + err = -ENOMEM; + goto out; + } + + /* Add flex groups. Note that a regular group is a + * flex group with 1 group. + */ + while (ext4_setup_next_flex_gd(sb, flex_gd, n_blocks_count)) { + if (time_is_before_jiffies(last_update_time + HZ * 10)) { + if (last_update_time) + ext4_msg(sb, KERN_INFO, + "resized to %llu blocks", + ext4_blocks_count(es)); + last_update_time = jiffies; + } + if (ext4_alloc_group_tables(sb, flex_gd, flexbg_size) != 0) + break; + err = ext4_flex_group_add(sb, resize_inode, flex_gd); + if (unlikely(err)) + break; + } + + if (!err && n_blocks_count_retry) { + n_blocks_count = n_blocks_count_retry; + n_blocks_count_retry = 0; + free_flex_gd(flex_gd); + flex_gd = NULL; + if (resize_inode) { + iput(resize_inode); + resize_inode = NULL; + } + goto retry; + } + +out: + if (flex_gd) + free_flex_gd(flex_gd); + if (resize_inode != NULL) + iput(resize_inode); + if (err) + ext4_warning(sb, "error (%d) occurred during " + "file system resize", err); + ext4_msg(sb, KERN_INFO, "resized filesystem to %llu", + ext4_blocks_count(es)); + return err; +} diff --git a/fs/ext4l/symlink.c b/fs/ext4l/symlink.c new file mode 100644 index 00000000000..645240cc022 --- /dev/null +++ b/fs/ext4l/symlink.c @@ -0,0 +1,136 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/fs/ext4/symlink.c + * + * Only fast symlinks left here - the rest is done by generic code. AV, 1999 + * + * Copyright (C) 1992, 1993, 1994, 1995 + * Remy Card (card@masi.ibp.fr) + * Laboratoire MASI - Institut Blaise Pascal + * Universite Pierre et Marie Curie (Paris VI) + * + * from + * + * linux/fs/minix/symlink.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + * + * ext4 symlink handling code + */ + +#include <linux/fs.h> +#include <linux/namei.h> +#include "ext4.h" +#include "xattr.h" + +static const char *ext4_encrypted_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) +{ + struct buffer_head *bh = NULL; + const void *caddr; + unsigned int max_size; + const char *paddr; + + if (!dentry) + return ERR_PTR(-ECHILD); + + if (ext4_inode_is_fast_symlink(inode)) { + caddr = EXT4_I(inode)->i_data; + max_size = sizeof(EXT4_I(inode)->i_data); + } else { + bh = ext4_bread(NULL, inode, 0, 0); + if (IS_ERR(bh)) + return ERR_CAST(bh); + if (!bh) { + EXT4_ERROR_INODE(inode, "bad symlink."); + return ERR_PTR(-EFSCORRUPTED); + } + caddr = bh->b_data; + max_size = inode->i_sb->s_blocksize; + } + + paddr = fscrypt_get_symlink(inode, caddr, max_size, done); + brelse(bh); + return paddr; +} + +static int ext4_encrypted_symlink_getattr(struct mnt_idmap *idmap, + const struct path *path, + struct kstat *stat, u32 request_mask, + unsigned int query_flags) +{ + ext4_getattr(idmap, path, stat, request_mask, query_flags); + + return fscrypt_symlink_getattr(path, stat); +} + +static void ext4_free_link(void *bh) +{ + brelse(bh); +} + +static const char *ext4_get_link(struct dentry *dentry, struct inode *inode, + struct delayed_call *callback) +{ + struct buffer_head *bh; + char *inline_link; + + /* + * Create a new inlined symlink is not supported, just provide a + * method to read the leftovers. + */ + if (ext4_has_inline_data(inode)) { + if (!dentry) + return ERR_PTR(-ECHILD); + + inline_link = ext4_read_inline_link(inode); + if (!IS_ERR(inline_link)) + set_delayed_call(callback, kfree_link, inline_link); + return inline_link; + } + + if (!dentry) { + bh = ext4_getblk(NULL, inode, 0, EXT4_GET_BLOCKS_CACHED_NOWAIT); + if (IS_ERR(bh) || !bh) + return ERR_PTR(-ECHILD); + if (!ext4_buffer_uptodate(bh)) { + brelse(bh); + return ERR_PTR(-ECHILD); + } + } else { + bh = ext4_bread(NULL, inode, 0, 0); + if (IS_ERR(bh)) + return ERR_CAST(bh); + if (!bh) { + EXT4_ERROR_INODE(inode, "bad symlink."); + return ERR_PTR(-EFSCORRUPTED); + } + } + + set_delayed_call(callback, ext4_free_link, bh); + nd_terminate_link(bh->b_data, inode->i_size, + inode->i_sb->s_blocksize - 1); + return bh->b_data; +} + +const struct inode_operations ext4_encrypted_symlink_inode_operations = { + .get_link = ext4_encrypted_get_link, + .setattr = ext4_setattr, + .getattr = ext4_encrypted_symlink_getattr, + .listxattr = ext4_listxattr, +}; + +const struct inode_operations ext4_symlink_inode_operations = { + .get_link = ext4_get_link, + .setattr = ext4_setattr, + .getattr = ext4_getattr, + .listxattr = ext4_listxattr, +}; + +const struct inode_operations ext4_fast_symlink_inode_operations = { + .get_link = simple_get_link, + .setattr = ext4_setattr, + .getattr = ext4_getattr, + .listxattr = ext4_listxattr, +}; diff --git a/fs/ext4l/sysfs.c b/fs/ext4l/sysfs.c new file mode 100644 index 00000000000..987bd00f916 --- /dev/null +++ b/fs/ext4l/sysfs.c @@ -0,0 +1,648 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/fs/ext4/sysfs.c + * + * Copyright (C) 1992, 1993, 1994, 1995 + * Remy Card (card@masi.ibp.fr) + * Theodore Ts'o (tytso@mit.edu) + * + */ + +#include <linux/time.h> +#include <linux/fs.h> +#include <linux/seq_file.h> +#include <linux/slab.h> +#include <linux/proc_fs.h> +#include <linux/part_stat.h> + +#include "ext4.h" +#include "ext4_jbd2.h" + +typedef enum { + attr_noop, + attr_delayed_allocation_blocks, + attr_session_write_kbytes, + attr_lifetime_write_kbytes, + attr_reserved_clusters, + attr_sra_exceeded_retry_limit, + attr_inode_readahead, + attr_trigger_test_error, + attr_first_error_time, + attr_last_error_time, + attr_clusters_in_group, + attr_mb_order, + attr_feature, + attr_pointer_pi, + attr_pointer_ui, + attr_pointer_ul, + attr_pointer_u64, + attr_pointer_u8, + attr_pointer_string, + attr_pointer_atomic, + attr_journal_task, +} attr_id_t; + +typedef enum { + ptr_explicit, + ptr_ext4_sb_info_offset, + ptr_ext4_super_block_offset, +} attr_ptr_t; + +static const char proc_dirname[] = "fs/ext4"; +static struct proc_dir_entry *ext4_proc_root; + +struct ext4_attr { + struct attribute attr; + short attr_id; + short attr_ptr; + unsigned short attr_size; + union { + int offset; + void *explicit_ptr; + } u; +}; + +static ssize_t session_write_kbytes_show(struct ext4_sb_info *sbi, char *buf) +{ + struct super_block *sb = sbi->s_buddy_cache->i_sb; + + return sysfs_emit(buf, "%lu\n", + (part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) - + sbi->s_sectors_written_start) >> 1); +} + +static ssize_t lifetime_write_kbytes_show(struct ext4_sb_info *sbi, char *buf) +{ + struct super_block *sb = sbi->s_buddy_cache->i_sb; + + return sysfs_emit(buf, "%llu\n", + (unsigned long long)(sbi->s_kbytes_written + + ((part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) - + EXT4_SB(sb)->s_sectors_written_start) >> 1))); +} + +static ssize_t inode_readahead_blks_store(struct ext4_sb_info *sbi, + const char *buf, size_t count) +{ + unsigned long t; + int ret; + + ret = kstrtoul(skip_spaces(buf), 0, &t); + if (ret) + return ret; + + if (t && (!is_power_of_2(t) || t > 0x40000000)) + return -EINVAL; + + sbi->s_inode_readahead_blks = t; + return count; +} + +static ssize_t reserved_clusters_store(struct ext4_sb_info *sbi, + const char *buf, size_t count) +{ + unsigned long long val; + ext4_fsblk_t clusters = (ext4_blocks_count(sbi->s_es) >> + sbi->s_cluster_bits); + int ret; + + ret = kstrtoull(skip_spaces(buf), 0, &val); + if (ret || val >= clusters || (s64)val < 0) + return -EINVAL; + + atomic64_set(&sbi->s_resv_clusters, val); + return count; +} + +static ssize_t trigger_test_error(struct ext4_sb_info *sbi, + const char *buf, size_t count) +{ + int len = count; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (len && buf[len-1] == '\n') + len--; + + if (len) + ext4_error(sbi->s_sb, "%.*s", len, buf); + return count; +} + +static ssize_t journal_task_show(struct ext4_sb_info *sbi, char *buf) +{ + if (!sbi->s_journal) + return sysfs_emit(buf, "<none>\n"); + return sysfs_emit(buf, "%d\n", + task_pid_vnr(sbi->s_journal->j_task)); +} + +#define EXT4_ATTR(_name,_mode,_id) \ +static struct ext4_attr ext4_attr_##_name = { \ + .attr = {.name = __stringify(_name), .mode = _mode }, \ + .attr_id = attr_##_id, \ +} + +#define EXT4_ATTR_FUNC(_name,_mode) EXT4_ATTR(_name,_mode,_name) + +#define EXT4_ATTR_FEATURE(_name) EXT4_ATTR(_name, 0444, feature) + +#define EXT4_ATTR_OFFSET(_name,_mode,_id,_struct,_elname) \ +static struct ext4_attr ext4_attr_##_name = { \ + .attr = {.name = __stringify(_name), .mode = _mode }, \ + .attr_id = attr_##_id, \ + .attr_ptr = ptr_##_struct##_offset, \ + .u = { \ + .offset = offsetof(struct _struct, _elname),\ + }, \ +} + +#define EXT4_ATTR_STRING(_name,_mode,_size,_struct,_elname) \ +static struct ext4_attr ext4_attr_##_name = { \ + .attr = {.name = __stringify(_name), .mode = _mode }, \ + .attr_id = attr_pointer_string, \ + .attr_size = _size, \ + .attr_ptr = ptr_##_struct##_offset, \ + .u = { \ + .offset = offsetof(struct _struct, _elname),\ + }, \ +} + +#define EXT4_RO_ATTR_ES_UI(_name,_elname) \ + EXT4_ATTR_OFFSET(_name, 0444, pointer_ui, ext4_super_block, _elname) + +#define EXT4_RO_ATTR_ES_U8(_name,_elname) \ + EXT4_ATTR_OFFSET(_name, 0444, pointer_u8, ext4_super_block, _elname) + +#define EXT4_RO_ATTR_ES_U64(_name,_elname) \ + EXT4_ATTR_OFFSET(_name, 0444, pointer_u64, ext4_super_block, _elname) + +#define EXT4_RO_ATTR_ES_STRING(_name,_elname,_size) \ + EXT4_ATTR_STRING(_name, 0444, _size, ext4_super_block, _elname) + +#define EXT4_RW_ATTR_SBI_PI(_name,_elname) \ + EXT4_ATTR_OFFSET(_name, 0644, pointer_pi, ext4_sb_info, _elname) + +#define EXT4_RW_ATTR_SBI_UI(_name,_elname) \ + EXT4_ATTR_OFFSET(_name, 0644, pointer_ui, ext4_sb_info, _elname) + +#define EXT4_RW_ATTR_SBI_UL(_name,_elname) \ + EXT4_ATTR_OFFSET(_name, 0644, pointer_ul, ext4_sb_info, _elname) + +#define EXT4_RO_ATTR_SBI_ATOMIC(_name,_elname) \ + EXT4_ATTR_OFFSET(_name, 0444, pointer_atomic, ext4_sb_info, _elname) + +#define EXT4_ATTR_PTR(_name,_mode,_id,_ptr) \ +static struct ext4_attr ext4_attr_##_name = { \ + .attr = {.name = __stringify(_name), .mode = _mode }, \ + .attr_id = attr_##_id, \ + .attr_ptr = ptr_explicit, \ + .u = { \ + .explicit_ptr = _ptr, \ + }, \ +} + +#define ATTR_LIST(name) &ext4_attr_##name.attr + +EXT4_ATTR_FUNC(delayed_allocation_blocks, 0444); +EXT4_ATTR_FUNC(session_write_kbytes, 0444); +EXT4_ATTR_FUNC(lifetime_write_kbytes, 0444); +EXT4_ATTR_FUNC(reserved_clusters, 0644); +EXT4_ATTR_FUNC(sra_exceeded_retry_limit, 0444); + +EXT4_ATTR_OFFSET(inode_readahead_blks, 0644, inode_readahead, + ext4_sb_info, s_inode_readahead_blks); +EXT4_ATTR_OFFSET(mb_group_prealloc, 0644, clusters_in_group, + ext4_sb_info, s_mb_group_prealloc); +EXT4_ATTR_OFFSET(mb_best_avail_max_trim_order, 0644, mb_order, + ext4_sb_info, s_mb_best_avail_max_trim_order); +EXT4_RW_ATTR_SBI_UI(inode_goal, s_inode_goal); +EXT4_RW_ATTR_SBI_UI(mb_stats, s_mb_stats); +EXT4_RW_ATTR_SBI_UI(mb_max_to_scan, s_mb_max_to_scan); +EXT4_RW_ATTR_SBI_UI(mb_min_to_scan, s_mb_min_to_scan); +EXT4_RW_ATTR_SBI_UI(mb_order2_req, s_mb_order2_reqs); +EXT4_RW_ATTR_SBI_UI(mb_stream_req, s_mb_stream_request); +EXT4_RW_ATTR_SBI_UI(mb_max_linear_groups, s_mb_max_linear_groups); +EXT4_RW_ATTR_SBI_UI(extent_max_zeroout_kb, s_extent_max_zeroout_kb); +EXT4_ATTR(trigger_fs_error, 0200, trigger_test_error); +EXT4_RW_ATTR_SBI_PI(err_ratelimit_interval_ms, s_err_ratelimit_state.interval); +EXT4_RW_ATTR_SBI_PI(err_ratelimit_burst, s_err_ratelimit_state.burst); +EXT4_RW_ATTR_SBI_PI(warning_ratelimit_interval_ms, s_warning_ratelimit_state.interval); +EXT4_RW_ATTR_SBI_PI(warning_ratelimit_burst, s_warning_ratelimit_state.burst); +EXT4_RW_ATTR_SBI_PI(msg_ratelimit_interval_ms, s_msg_ratelimit_state.interval); +EXT4_RW_ATTR_SBI_PI(msg_ratelimit_burst, s_msg_ratelimit_state.burst); +#ifdef CONFIG_EXT4_DEBUG +EXT4_RW_ATTR_SBI_UL(simulate_fail, s_simulate_fail); +#endif +EXT4_RO_ATTR_SBI_ATOMIC(warning_count, s_warning_count); +EXT4_RO_ATTR_SBI_ATOMIC(msg_count, s_msg_count); +EXT4_RO_ATTR_ES_UI(errors_count, s_error_count); +EXT4_RO_ATTR_ES_U8(first_error_errcode, s_first_error_errcode); +EXT4_RO_ATTR_ES_U8(last_error_errcode, s_last_error_errcode); +EXT4_RO_ATTR_ES_UI(first_error_ino, s_first_error_ino); +EXT4_RO_ATTR_ES_UI(last_error_ino, s_last_error_ino); +EXT4_RO_ATTR_ES_U64(first_error_block, s_first_error_block); +EXT4_RO_ATTR_ES_U64(last_error_block, s_last_error_block); +EXT4_RO_ATTR_ES_UI(first_error_line, s_first_error_line); +EXT4_RO_ATTR_ES_UI(last_error_line, s_last_error_line); +EXT4_RO_ATTR_ES_STRING(first_error_func, s_first_error_func, 32); +EXT4_RO_ATTR_ES_STRING(last_error_func, s_last_error_func, 32); +EXT4_ATTR(first_error_time, 0444, first_error_time); +EXT4_ATTR(last_error_time, 0444, last_error_time); +EXT4_ATTR(journal_task, 0444, journal_task); +EXT4_RW_ATTR_SBI_UI(mb_prefetch, s_mb_prefetch); +EXT4_RW_ATTR_SBI_UI(mb_prefetch_limit, s_mb_prefetch_limit); +EXT4_RW_ATTR_SBI_UL(last_trim_minblks, s_last_trim_minblks); +EXT4_RW_ATTR_SBI_UI(sb_update_sec, s_sb_update_sec); +EXT4_RW_ATTR_SBI_UI(sb_update_kb, s_sb_update_kb); + +static unsigned int old_bump_val = 128; +EXT4_ATTR_PTR(max_writeback_mb_bump, 0444, pointer_ui, &old_bump_val); + +static struct attribute *ext4_attrs[] = { + ATTR_LIST(delayed_allocation_blocks), + ATTR_LIST(session_write_kbytes), + ATTR_LIST(lifetime_write_kbytes), + ATTR_LIST(reserved_clusters), + ATTR_LIST(sra_exceeded_retry_limit), + ATTR_LIST(inode_readahead_blks), + ATTR_LIST(inode_goal), + ATTR_LIST(mb_stats), + ATTR_LIST(mb_max_to_scan), + ATTR_LIST(mb_min_to_scan), + ATTR_LIST(mb_order2_req), + ATTR_LIST(mb_stream_req), + ATTR_LIST(mb_group_prealloc), + ATTR_LIST(mb_max_linear_groups), + ATTR_LIST(max_writeback_mb_bump), + ATTR_LIST(extent_max_zeroout_kb), + ATTR_LIST(trigger_fs_error), + ATTR_LIST(err_ratelimit_interval_ms), + ATTR_LIST(err_ratelimit_burst), + ATTR_LIST(warning_ratelimit_interval_ms), + ATTR_LIST(warning_ratelimit_burst), + ATTR_LIST(msg_ratelimit_interval_ms), + ATTR_LIST(msg_ratelimit_burst), + ATTR_LIST(mb_best_avail_max_trim_order), + ATTR_LIST(errors_count), + ATTR_LIST(warning_count), + ATTR_LIST(msg_count), + ATTR_LIST(first_error_ino), + ATTR_LIST(last_error_ino), + ATTR_LIST(first_error_block), + ATTR_LIST(last_error_block), + ATTR_LIST(first_error_line), + ATTR_LIST(last_error_line), + ATTR_LIST(first_error_func), + ATTR_LIST(last_error_func), + ATTR_LIST(first_error_errcode), + ATTR_LIST(last_error_errcode), + ATTR_LIST(first_error_time), + ATTR_LIST(last_error_time), + ATTR_LIST(journal_task), +#ifdef CONFIG_EXT4_DEBUG + ATTR_LIST(simulate_fail), +#endif + ATTR_LIST(mb_prefetch), + ATTR_LIST(mb_prefetch_limit), + ATTR_LIST(last_trim_minblks), + ATTR_LIST(sb_update_sec), + ATTR_LIST(sb_update_kb), + NULL, +}; +ATTRIBUTE_GROUPS(ext4); + +/* Features this copy of ext4 supports */ +EXT4_ATTR_FEATURE(lazy_itable_init); +EXT4_ATTR_FEATURE(batched_discard); +EXT4_ATTR_FEATURE(meta_bg_resize); +#ifdef CONFIG_FS_ENCRYPTION +EXT4_ATTR_FEATURE(encryption); +EXT4_ATTR_FEATURE(test_dummy_encryption_v2); +#endif +#if IS_ENABLED(CONFIG_UNICODE) +EXT4_ATTR_FEATURE(casefold); +#endif +#ifdef CONFIG_FS_VERITY +EXT4_ATTR_FEATURE(verity); +#endif +EXT4_ATTR_FEATURE(metadata_csum_seed); +EXT4_ATTR_FEATURE(fast_commit); +#if IS_ENABLED(CONFIG_UNICODE) && defined(CONFIG_FS_ENCRYPTION) +EXT4_ATTR_FEATURE(encrypted_casefold); +#endif + +static struct attribute *ext4_feat_attrs[] = { + ATTR_LIST(lazy_itable_init), + ATTR_LIST(batched_discard), + ATTR_LIST(meta_bg_resize), +#ifdef CONFIG_FS_ENCRYPTION + ATTR_LIST(encryption), + ATTR_LIST(test_dummy_encryption_v2), +#endif +#if IS_ENABLED(CONFIG_UNICODE) + ATTR_LIST(casefold), +#endif +#ifdef CONFIG_FS_VERITY + ATTR_LIST(verity), +#endif + ATTR_LIST(metadata_csum_seed), + ATTR_LIST(fast_commit), +#if IS_ENABLED(CONFIG_UNICODE) && defined(CONFIG_FS_ENCRYPTION) + ATTR_LIST(encrypted_casefold), +#endif + NULL, +}; +ATTRIBUTE_GROUPS(ext4_feat); + +static void *calc_ptr(struct ext4_attr *a, struct ext4_sb_info *sbi) +{ + switch (a->attr_ptr) { + case ptr_explicit: + return a->u.explicit_ptr; + case ptr_ext4_sb_info_offset: + return (void *) (((char *) sbi) + a->u.offset); + case ptr_ext4_super_block_offset: + return (void *) (((char *) sbi->s_es) + a->u.offset); + } + return NULL; +} + +static ssize_t __print_tstamp(char *buf, __le32 lo, __u8 hi) +{ + return sysfs_emit(buf, "%lld\n", + ((time64_t)hi << 32) + le32_to_cpu(lo)); +} + +#define print_tstamp(buf, es, tstamp) \ + __print_tstamp(buf, (es)->tstamp, (es)->tstamp ## _hi) + +static ssize_t ext4_generic_attr_show(struct ext4_attr *a, + struct ext4_sb_info *sbi, char *buf) +{ + void *ptr = calc_ptr(a, sbi); + + if (!ptr) + return 0; + + switch (a->attr_id) { + case attr_inode_readahead: + case attr_clusters_in_group: + case attr_mb_order: + case attr_pointer_pi: + case attr_pointer_ui: + if (a->attr_ptr == ptr_ext4_super_block_offset) + return sysfs_emit(buf, "%u\n", le32_to_cpup(ptr)); + return sysfs_emit(buf, "%u\n", *((unsigned int *) ptr)); + case attr_pointer_ul: + return sysfs_emit(buf, "%lu\n", *((unsigned long *) ptr)); + case attr_pointer_u8: + return sysfs_emit(buf, "%u\n", *((unsigned char *) ptr)); + case attr_pointer_u64: + if (a->attr_ptr == ptr_ext4_super_block_offset) + return sysfs_emit(buf, "%llu\n", le64_to_cpup(ptr)); + return sysfs_emit(buf, "%llu\n", *((unsigned long long *) ptr)); + case attr_pointer_string: + return sysfs_emit(buf, "%.*s\n", a->attr_size, (char *) ptr); + case attr_pointer_atomic: + return sysfs_emit(buf, "%d\n", atomic_read((atomic_t *) ptr)); + } + return 0; +} + +static ssize_t ext4_attr_show(struct kobject *kobj, + struct attribute *attr, char *buf) +{ + struct ext4_sb_info *sbi = container_of(kobj, struct ext4_sb_info, + s_kobj); + struct ext4_attr *a = container_of(attr, struct ext4_attr, attr); + + switch (a->attr_id) { + case attr_delayed_allocation_blocks: + return sysfs_emit(buf, "%llu\n", + (s64) EXT4_C2B(sbi, + percpu_counter_sum(&sbi->s_dirtyclusters_counter))); + case attr_session_write_kbytes: + return session_write_kbytes_show(sbi, buf); + case attr_lifetime_write_kbytes: + return lifetime_write_kbytes_show(sbi, buf); + case attr_reserved_clusters: + return sysfs_emit(buf, "%llu\n", + (unsigned long long) + atomic64_read(&sbi->s_resv_clusters)); + case attr_sra_exceeded_retry_limit: + return sysfs_emit(buf, "%llu\n", + (unsigned long long) + percpu_counter_sum(&sbi->s_sra_exceeded_retry_limit)); + case attr_feature: + return sysfs_emit(buf, "supported\n"); + case attr_first_error_time: + return print_tstamp(buf, sbi->s_es, s_first_error_time); + case attr_last_error_time: + return print_tstamp(buf, sbi->s_es, s_last_error_time); + case attr_journal_task: + return journal_task_show(sbi, buf); + default: + return ext4_generic_attr_show(a, sbi, buf); + } +} + +static ssize_t ext4_generic_attr_store(struct ext4_attr *a, + struct ext4_sb_info *sbi, + const char *buf, size_t len) +{ + int ret; + unsigned int t; + unsigned long lt; + void *ptr = calc_ptr(a, sbi); + + if (!ptr) + return 0; + + switch (a->attr_id) { + case attr_pointer_pi: + ret = kstrtouint(skip_spaces(buf), 0, &t); + if (ret) + return ret; + if ((int)t < 0) + return -EINVAL; + *((unsigned int *) ptr) = t; + return len; + case attr_pointer_ui: + ret = kstrtouint(skip_spaces(buf), 0, &t); + if (ret) + return ret; + if (a->attr_ptr == ptr_ext4_super_block_offset) + *((__le32 *) ptr) = cpu_to_le32(t); + else + *((unsigned int *) ptr) = t; + return len; + case attr_mb_order: + ret = kstrtouint(skip_spaces(buf), 0, &t); + if (ret) + return ret; + if (t > 64) + return -EINVAL; + *((unsigned int *) ptr) = t; + return len; + case attr_clusters_in_group: + ret = kstrtouint(skip_spaces(buf), 0, &t); + if (ret) + return ret; + if (t > sbi->s_clusters_per_group) + return -EINVAL; + *((unsigned int *) ptr) = t; + return len; + case attr_pointer_ul: + ret = kstrtoul(skip_spaces(buf), 0, <); + if (ret) + return ret; + *((unsigned long *) ptr) = lt; + return len; + } + return 0; +} + +static ssize_t ext4_attr_store(struct kobject *kobj, + struct attribute *attr, + const char *buf, size_t len) +{ + struct ext4_sb_info *sbi = container_of(kobj, struct ext4_sb_info, + s_kobj); + struct ext4_attr *a = container_of(attr, struct ext4_attr, attr); + + switch (a->attr_id) { + case attr_reserved_clusters: + return reserved_clusters_store(sbi, buf, len); + case attr_inode_readahead: + return inode_readahead_blks_store(sbi, buf, len); + case attr_trigger_test_error: + return trigger_test_error(sbi, buf, len); + default: + return ext4_generic_attr_store(a, sbi, buf, len); + } +} + +static void ext4_sb_release(struct kobject *kobj) +{ + struct ext4_sb_info *sbi = container_of(kobj, struct ext4_sb_info, + s_kobj); + complete(&sbi->s_kobj_unregister); +} + +static void ext4_feat_release(struct kobject *kobj) +{ + kfree(kobj); +} + +static const struct sysfs_ops ext4_attr_ops = { + .show = ext4_attr_show, + .store = ext4_attr_store, +}; + +static const struct kobj_type ext4_sb_ktype = { + .default_groups = ext4_groups, + .sysfs_ops = &ext4_attr_ops, + .release = ext4_sb_release, +}; + +static const struct kobj_type ext4_feat_ktype = { + .default_groups = ext4_feat_groups, + .sysfs_ops = &ext4_attr_ops, + .release = ext4_feat_release, +}; + +void ext4_notify_error_sysfs(struct ext4_sb_info *sbi) +{ + sysfs_notify(&sbi->s_kobj, NULL, "errors_count"); +} + +static struct kobject *ext4_root; + +static struct kobject *ext4_feat; + +int ext4_register_sysfs(struct super_block *sb) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + int err; + + init_completion(&sbi->s_kobj_unregister); + err = kobject_init_and_add(&sbi->s_kobj, &ext4_sb_ktype, ext4_root, + "%s", sb->s_id); + if (err) { + kobject_put(&sbi->s_kobj); + wait_for_completion(&sbi->s_kobj_unregister); + return err; + } + + if (ext4_proc_root) + sbi->s_proc = proc_mkdir(sb->s_id, ext4_proc_root); + if (sbi->s_proc) { + proc_create_single_data("options", S_IRUGO, sbi->s_proc, + ext4_seq_options_show, sb); + proc_create_single_data("es_shrinker_info", S_IRUGO, + sbi->s_proc, ext4_seq_es_shrinker_info_show, + sb); + proc_create_single_data("fc_info", 0444, sbi->s_proc, + ext4_fc_info_show, sb); + proc_create_seq_data("mb_groups", S_IRUGO, sbi->s_proc, + &ext4_mb_seq_groups_ops, sb); + proc_create_single_data("mb_stats", 0444, sbi->s_proc, + ext4_seq_mb_stats_show, sb); + proc_create_seq_data("mb_structs_summary", 0444, sbi->s_proc, + &ext4_mb_seq_structs_summary_ops, sb); + } + return 0; +} + +void ext4_unregister_sysfs(struct super_block *sb) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + + if (sbi->s_proc) + remove_proc_subtree(sb->s_id, ext4_proc_root); + kobject_del(&sbi->s_kobj); +} + +int __init ext4_init_sysfs(void) +{ + int ret; + + ext4_root = kobject_create_and_add("ext4", fs_kobj); + if (!ext4_root) + return -ENOMEM; + + ext4_feat = kzalloc(sizeof(*ext4_feat), GFP_KERNEL); + if (!ext4_feat) { + ret = -ENOMEM; + goto root_err; + } + + ret = kobject_init_and_add(ext4_feat, &ext4_feat_ktype, + ext4_root, "features"); + if (ret) + goto feat_err; + + ext4_proc_root = proc_mkdir(proc_dirname, NULL); + return ret; + +feat_err: + kobject_put(ext4_feat); + ext4_feat = NULL; +root_err: + kobject_put(ext4_root); + ext4_root = NULL; + return ret; +} + +void ext4_exit_sysfs(void) +{ + kobject_put(ext4_feat); + ext4_feat = NULL; + kobject_put(ext4_root); + ext4_root = NULL; + remove_proc_entry(proc_dirname, NULL); + ext4_proc_root = NULL; +} + diff --git a/fs/ext4l/truncate.h b/fs/ext4l/truncate.h new file mode 100644 index 00000000000..ce84aa2786c --- /dev/null +++ b/fs/ext4l/truncate.h @@ -0,0 +1,52 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/fs/ext4/truncate.h + * + * Common inline functions needed for truncate support + */ + +/* + * Truncate blocks that were not used by write. We have to truncate the + * pagecache as well so that corresponding buffers get properly unmapped. + */ +static inline void ext4_truncate_failed_write(struct inode *inode) +{ + struct address_space *mapping = inode->i_mapping; + + /* + * We don't need to call ext4_break_layouts() because the blocks we + * are truncating were never visible to userspace. + */ + filemap_invalidate_lock(mapping); + truncate_inode_pages(mapping, inode->i_size); + ext4_truncate(inode); + filemap_invalidate_unlock(mapping); +} + +/* + * Work out how many blocks we need to proceed with the next chunk of a + * truncate transaction. + */ +static inline unsigned long ext4_blocks_for_truncate(struct inode *inode) +{ + ext4_lblk_t needed; + + needed = inode->i_blocks >> (inode->i_sb->s_blocksize_bits - 9); + + /* Give ourselves just enough room to cope with inodes in which + * i_blocks is corrupt: we've seen disk corruptions in the past + * which resulted in random data in an inode which looked enough + * like a regular file for ext4 to try to delete it. Things + * will go a bit crazy if that happens, but at least we should + * try not to panic the whole kernel. */ + if (needed < 2) + needed = 2; + + /* But we need to bound the transaction so we don't overflow the + * journal. */ + if (needed > EXT4_MAX_TRANS_DATA) + needed = EXT4_MAX_TRANS_DATA; + + return EXT4_DATA_TRANS_BLOCKS(inode->i_sb) + needed; +} + diff --git a/fs/ext4l/verity.c b/fs/ext4l/verity.c new file mode 100644 index 00000000000..b0acb0c5031 --- /dev/null +++ b/fs/ext4l/verity.c @@ -0,0 +1,399 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * fs/ext4/verity.c: fs-verity support for ext4 + * + * Copyright 2019 Google LLC + */ + +/* + * Implementation of fsverity_operations for ext4. + * + * ext4 stores the verity metadata (Merkle tree and fsverity_descriptor) past + * the end of the file, starting at the first 64K boundary beyond i_size. This + * approach works because (a) verity files are readonly, and (b) pages fully + * beyond i_size aren't visible to userspace but can be read/written internally + * by ext4 with only some relatively small changes to ext4. This approach + * avoids having to depend on the EA_INODE feature and on rearchitecturing + * ext4's xattr support to support paging multi-gigabyte xattrs into memory, and + * to support encrypting xattrs. Note that the verity metadata *must* be + * encrypted when the file is, since it contains hashes of the plaintext data. + * + * Using a 64K boundary rather than a 4K one keeps things ready for + * architectures with 64K pages, and it doesn't necessarily waste space on-disk + * since there can be a hole between i_size and the start of the Merkle tree. + */ + +#include <linux/quotaops.h> + +#include "ext4.h" +#include "ext4_extents.h" +#include "ext4_jbd2.h" + +static inline loff_t ext4_verity_metadata_pos(const struct inode *inode) +{ + return round_up(inode->i_size, 65536); +} + +/* + * Read some verity metadata from the inode. __vfs_read() can't be used because + * we need to read beyond i_size. + */ +static int pagecache_read(struct inode *inode, void *buf, size_t count, + loff_t pos) +{ + while (count) { + struct folio *folio; + size_t n; + + folio = read_mapping_folio(inode->i_mapping, pos >> PAGE_SHIFT, + NULL); + if (IS_ERR(folio)) + return PTR_ERR(folio); + + n = memcpy_from_file_folio(buf, folio, pos, count); + folio_put(folio); + + buf += n; + pos += n; + count -= n; + } + return 0; +} + +/* + * Write some verity metadata to the inode for FS_IOC_ENABLE_VERITY. + * kernel_write() can't be used because the file descriptor is readonly. + */ +static int pagecache_write(struct inode *inode, const void *buf, size_t count, + loff_t pos) +{ + struct address_space *mapping = inode->i_mapping; + const struct address_space_operations *aops = mapping->a_ops; + + if (pos + count > inode->i_sb->s_maxbytes) + return -EFBIG; + + while (count) { + size_t n = min_t(size_t, count, + PAGE_SIZE - offset_in_page(pos)); + struct folio *folio; + void *fsdata = NULL; + int res; + + res = aops->write_begin(NULL, mapping, pos, n, &folio, &fsdata); + if (res) + return res; + + memcpy_to_folio(folio, offset_in_folio(folio, pos), buf, n); + + res = aops->write_end(NULL, mapping, pos, n, n, folio, fsdata); + if (res < 0) + return res; + if (res != n) + return -EIO; + + buf += n; + pos += n; + count -= n; + } + return 0; +} + +static int ext4_begin_enable_verity(struct file *filp) +{ + struct inode *inode = file_inode(filp); + const int credits = 2; /* superblock and inode for ext4_orphan_add() */ + handle_t *handle; + int err; + + if (IS_DAX(inode) || ext4_test_inode_flag(inode, EXT4_INODE_DAX)) + return -EINVAL; + + if (ext4_verity_in_progress(inode)) + return -EBUSY; + + /* + * Since the file was opened readonly, we have to initialize the jbd + * inode and quotas here and not rely on ->open() doing it. This must + * be done before evicting the inline data. + */ + + err = ext4_inode_attach_jinode(inode); + if (err) + return err; + + err = dquot_initialize(inode); + if (err) + return err; + + err = ext4_convert_inline_data(inode); + if (err) + return err; + + if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { + ext4_warning_inode(inode, + "verity is only allowed on extent-based files"); + return -EOPNOTSUPP; + } + + /* + * ext4 uses the last allocated block to find the verity descriptor, so + * we must remove any other blocks past EOF which might confuse things. + */ + err = ext4_truncate(inode); + if (err) + return err; + + handle = ext4_journal_start(inode, EXT4_HT_INODE, credits); + if (IS_ERR(handle)) + return PTR_ERR(handle); + + err = ext4_orphan_add(handle, inode); + if (err == 0) + ext4_set_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS); + + ext4_journal_stop(handle); + return err; +} + +/* + * ext4 stores the verity descriptor beginning on the next filesystem block + * boundary after the Merkle tree. Then, the descriptor size is stored in the + * last 4 bytes of the last allocated filesystem block --- which is either the + * block in which the descriptor ends, or the next block after that if there + * weren't at least 4 bytes remaining. + * + * We can't simply store the descriptor in an xattr because it *must* be + * encrypted when ext4 encryption is used, but ext4 encryption doesn't encrypt + * xattrs. Also, if the descriptor includes a large signature blob it may be + * too large to store in an xattr without the EA_INODE feature. + */ +static int ext4_write_verity_descriptor(struct inode *inode, const void *desc, + size_t desc_size, u64 merkle_tree_size) +{ + const u64 desc_pos = round_up(ext4_verity_metadata_pos(inode) + + merkle_tree_size, i_blocksize(inode)); + const u64 desc_end = desc_pos + desc_size; + const __le32 desc_size_disk = cpu_to_le32(desc_size); + const u64 desc_size_pos = round_up(desc_end + sizeof(desc_size_disk), + i_blocksize(inode)) - + sizeof(desc_size_disk); + int err; + + err = pagecache_write(inode, desc, desc_size, desc_pos); + if (err) + return err; + + return pagecache_write(inode, &desc_size_disk, sizeof(desc_size_disk), + desc_size_pos); +} + +static int ext4_end_enable_verity(struct file *filp, const void *desc, + size_t desc_size, u64 merkle_tree_size) +{ + struct inode *inode = file_inode(filp); + const int credits = 2; /* superblock and inode for ext4_orphan_del() */ + handle_t *handle; + struct ext4_iloc iloc; + int err = 0; + + /* + * If an error already occurred (which fs/verity/ signals by passing + * desc == NULL), then only clean-up is needed. + */ + if (desc == NULL) + goto cleanup; + + /* Append the verity descriptor. */ + err = ext4_write_verity_descriptor(inode, desc, desc_size, + merkle_tree_size); + if (err) + goto cleanup; + + /* + * Write all pages (both data and verity metadata). Note that this must + * happen before clearing EXT4_STATE_VERITY_IN_PROGRESS; otherwise pages + * beyond i_size won't be written properly. For crash consistency, this + * also must happen before the verity inode flag gets persisted. + */ + err = filemap_write_and_wait(inode->i_mapping); + if (err) + goto cleanup; + + /* + * Finally, set the verity inode flag and remove the inode from the + * orphan list (in a single transaction). + */ + + handle = ext4_journal_start(inode, EXT4_HT_INODE, credits); + if (IS_ERR(handle)) { + err = PTR_ERR(handle); + goto cleanup; + } + + err = ext4_orphan_del(handle, inode); + if (err) + goto stop_and_cleanup; + + err = ext4_reserve_inode_write(handle, inode, &iloc); + if (err) + goto stop_and_cleanup; + + ext4_set_inode_flag(inode, EXT4_INODE_VERITY); + ext4_set_inode_flags(inode, false); + err = ext4_mark_iloc_dirty(handle, inode, &iloc); + if (err) + goto stop_and_cleanup; + + ext4_journal_stop(handle); + + ext4_clear_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS); + return 0; + +stop_and_cleanup: + ext4_journal_stop(handle); +cleanup: + /* + * Verity failed to be enabled, so clean up by truncating any verity + * metadata that was written beyond i_size (both from cache and from + * disk), removing the inode from the orphan list (if it wasn't done + * already), and clearing EXT4_STATE_VERITY_IN_PROGRESS. + */ + truncate_inode_pages(inode->i_mapping, inode->i_size); + ext4_truncate(inode); + ext4_orphan_del(NULL, inode); + ext4_clear_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS); + return err; +} + +static int ext4_get_verity_descriptor_location(struct inode *inode, + size_t *desc_size_ret, + u64 *desc_pos_ret) +{ + struct ext4_ext_path *path; + struct ext4_extent *last_extent; + u32 end_lblk; + u64 desc_size_pos; + __le32 desc_size_disk; + u32 desc_size; + u64 desc_pos; + int err; + + /* + * Descriptor size is in last 4 bytes of last allocated block. + * See ext4_write_verity_descriptor(). + */ + + if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { + EXT4_ERROR_INODE(inode, "verity file doesn't use extents"); + return -EFSCORRUPTED; + } + + path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, 0); + if (IS_ERR(path)) + return PTR_ERR(path); + + last_extent = path[path->p_depth].p_ext; + if (!last_extent) { + EXT4_ERROR_INODE(inode, "verity file has no extents"); + ext4_free_ext_path(path); + return -EFSCORRUPTED; + } + + end_lblk = le32_to_cpu(last_extent->ee_block) + + ext4_ext_get_actual_len(last_extent); + desc_size_pos = (u64)end_lblk << inode->i_blkbits; + ext4_free_ext_path(path); + + if (desc_size_pos < sizeof(desc_size_disk)) + goto bad; + desc_size_pos -= sizeof(desc_size_disk); + + err = pagecache_read(inode, &desc_size_disk, sizeof(desc_size_disk), + desc_size_pos); + if (err) + return err; + desc_size = le32_to_cpu(desc_size_disk); + + /* + * The descriptor is stored just before the desc_size_disk, but starting + * on a filesystem block boundary. + */ + + if (desc_size > INT_MAX || desc_size > desc_size_pos) + goto bad; + + desc_pos = round_down(desc_size_pos - desc_size, i_blocksize(inode)); + if (desc_pos < ext4_verity_metadata_pos(inode)) + goto bad; + + *desc_size_ret = desc_size; + *desc_pos_ret = desc_pos; + return 0; + +bad: + EXT4_ERROR_INODE(inode, "verity file corrupted; can't find descriptor"); + return -EFSCORRUPTED; +} + +static int ext4_get_verity_descriptor(struct inode *inode, void *buf, + size_t buf_size) +{ + size_t desc_size = 0; + u64 desc_pos = 0; + int err; + + err = ext4_get_verity_descriptor_location(inode, &desc_size, &desc_pos); + if (err) + return err; + + if (buf_size) { + if (desc_size > buf_size) + return -ERANGE; + err = pagecache_read(inode, buf, desc_size, desc_pos); + if (err) + return err; + } + return desc_size; +} + +static struct page *ext4_read_merkle_tree_page(struct inode *inode, + pgoff_t index, + unsigned long num_ra_pages) +{ + struct folio *folio; + + index += ext4_verity_metadata_pos(inode) >> PAGE_SHIFT; + + folio = __filemap_get_folio(inode->i_mapping, index, FGP_ACCESSED, 0); + if (IS_ERR(folio) || !folio_test_uptodate(folio)) { + DEFINE_READAHEAD(ractl, NULL, NULL, inode->i_mapping, index); + + if (!IS_ERR(folio)) + folio_put(folio); + else if (num_ra_pages > 1) + page_cache_ra_unbounded(&ractl, num_ra_pages, 0); + folio = read_mapping_folio(inode->i_mapping, index, NULL); + if (IS_ERR(folio)) + return ERR_CAST(folio); + } + return folio_file_page(folio, index); +} + +static int ext4_write_merkle_tree_block(struct inode *inode, const void *buf, + u64 pos, unsigned int size) +{ + pos += ext4_verity_metadata_pos(inode); + + return pagecache_write(inode, buf, size, pos); +} + +const struct fsverity_operations ext4_verityops = { + .inode_info_offs = (int)offsetof(struct ext4_inode_info, i_verity_info) - + (int)offsetof(struct ext4_inode_info, vfs_inode), + .begin_enable_verity = ext4_begin_enable_verity, + .end_enable_verity = ext4_end_enable_verity, + .get_verity_descriptor = ext4_get_verity_descriptor, + .read_merkle_tree_page = ext4_read_merkle_tree_page, + .write_merkle_tree_block = ext4_write_merkle_tree_block, +}; -- 2.43.0