diff options
Diffstat (limited to 'fs')
158 files changed, 5138 insertions, 2781 deletions
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index d5990eb160bd..02781e78ffb6 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -341,6 +341,7 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp, struct msghdr msg; struct kvec iov[1]; size_t offset; + s64 tx_total_len; u32 abort_code; int ret; @@ -364,9 +365,20 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp, srx.transport.sin.sin_port = call->port; memcpy(&srx.transport.sin.sin_addr, addr, 4); + /* Work out the length we're going to transmit. This is awkward for + * calls such as FS.StoreData where there's an extra injection of data + * after the initial fixed part. + */ + tx_total_len = call->request_size; + if (call->send_pages) { + tx_total_len += call->last_to - call->first_offset; + tx_total_len += (call->last - call->first) * PAGE_SIZE; + } + /* create a call */ rxcall = rxrpc_kernel_begin_call(afs_socket, &srx, call->key, - (unsigned long) call, gfp, + (unsigned long)call, + tx_total_len, gfp, (async ? afs_wake_up_async_call : afs_wake_up_call_waiter)); @@ -738,6 +750,8 @@ void afs_send_empty_reply(struct afs_call *call) _enter(""); + rxrpc_kernel_set_tx_length(afs_socket, call->rxcall, 0); + msg.msg_name = NULL; msg.msg_namelen = 0; iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, NULL, 0, 0); @@ -772,6 +786,8 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len) _enter(""); + rxrpc_kernel_set_tx_length(afs_socket, call->rxcall, len); + iov[0].iov_base = (void *) buf; iov[0].iov_len = len; msg.msg_name = NULL; diff --git a/fs/block_dev.c b/fs/block_dev.c index a7df151f8aba..9941dc8342df 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -632,7 +632,7 @@ int blkdev_fsync(struct file *filp, loff_t start, loff_t end, int datasync) struct block_device *bdev = I_BDEV(bd_inode); int error; - error = filemap_write_and_wait_range(filp->f_mapping, start, end); + error = file_write_and_wait_range(filp, start, end); if (error) return error; @@ -1751,6 +1751,7 @@ static int blkdev_open(struct inode * inode, struct file * filp) return -ENOMEM; filp->f_mapping = bdev->bd_inode->i_mapping; + filp->f_wb_err = filemap_sample_wb_err(filp->f_mapping); return blkdev_get(bdev, filp->f_mode, filp); } diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c index 247b8dfaf6e5..8d8370ddb6b2 100644 --- a/fs/btrfs/acl.c +++ b/fs/btrfs/acl.c @@ -78,12 +78,6 @@ static int __btrfs_set_acl(struct btrfs_trans_handle *trans, switch (type) { case ACL_TYPE_ACCESS: name = XATTR_NAME_POSIX_ACL_ACCESS; - if (acl) { - ret = posix_acl_update_mode(inode, &inode->i_mode, &acl); - if (ret) - return ret; - } - ret = 0; break; case ACL_TYPE_DEFAULT: if (!S_ISDIR(inode->i_mode)) @@ -119,6 +113,13 @@ out: int btrfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) { + int ret; + + if (type == ACL_TYPE_ACCESS && acl) { + ret = posix_acl_update_mode(inode, &inode->i_mode, &acl); + if (ret) + return ret; + } return __btrfs_set_acl(NULL, inode, acl, type); } diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 24865da63d8f..f723c11bb763 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -16,7 +16,7 @@ * Boston, MA 021110-1307, USA. */ -#include <linux/vmalloc.h> +#include <linux/mm.h> #include <linux/rbtree.h> #include "ctree.h" #include "disk-io.h" @@ -2305,7 +2305,7 @@ struct btrfs_data_container *init_data_container(u32 total_bytes) size_t alloc_bytes; alloc_bytes = max_t(size_t, total_bytes, sizeof(*data)); - data = vmalloc(alloc_bytes); + data = kvmalloc(alloc_bytes, GFP_KERNEL); if (!data) return ERR_PTR(-ENOMEM); @@ -2339,9 +2339,9 @@ struct inode_fs_paths *init_ipath(s32 total_bytes, struct btrfs_root *fs_root, if (IS_ERR(fspath)) return (void *)fspath; - ifp = kmalloc(sizeof(*ifp), GFP_NOFS); + ifp = kmalloc(sizeof(*ifp), GFP_KERNEL); if (!ifp) { - vfree(fspath); + kvfree(fspath); return ERR_PTR(-ENOMEM); } @@ -2356,6 +2356,6 @@ void free_ipath(struct inode_fs_paths *ipath) { if (!ipath) return; - vfree(ipath->fspath); + kvfree(ipath->fspath); kfree(ipath); } diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c index 4ded1c3f92b8..11d37c94ce05 100644 --- a/fs/btrfs/check-integrity.c +++ b/fs/btrfs/check-integrity.c @@ -94,7 +94,7 @@ #include <linux/mutex.h> #include <linux/genhd.h> #include <linux/blkdev.h> -#include <linux/vmalloc.h> +#include <linux/mm.h> #include <linux/string.h> #include "ctree.h" #include "disk-io.h" @@ -1638,12 +1638,7 @@ static int btrfsic_read_block(struct btrfsic_state *state, struct bio *bio; unsigned int j; - bio = btrfs_io_bio_alloc(GFP_NOFS, num_pages - i); - if (!bio) { - pr_info("btrfsic: bio_alloc() for %u pages failed!\n", - num_pages - i); - return -1; - } + bio = btrfs_io_bio_alloc(num_pages - i); bio->bi_bdev = block_ctx->dev->bdev; bio->bi_iter.bi_sector = dev_bytenr >> 9; bio_set_op_attrs(bio, REQ_OP_READ, 0); @@ -1668,14 +1663,8 @@ static int btrfsic_read_block(struct btrfsic_state *state, dev_bytenr += (j - i) * PAGE_SIZE; i = j; } - for (i = 0; i < num_pages; i++) { + for (i = 0; i < num_pages; i++) block_ctx->datav[i] = kmap(block_ctx->pagev[i]); - if (!block_ctx->datav[i]) { - pr_info("btrfsic: kmap() failed (dev %s)!\n", - block_ctx->dev->name); - return -1; - } - } return block_ctx->len; } @@ -2822,44 +2811,47 @@ static void __btrfsic_submit_bio(struct bio *bio) dev_state = btrfsic_dev_state_lookup(bio->bi_bdev); if (NULL != dev_state && (bio_op(bio) == REQ_OP_WRITE) && bio_has_data(bio)) { - unsigned int i; + unsigned int i = 0; u64 dev_bytenr; u64 cur_bytenr; - struct bio_vec *bvec; + struct bio_vec bvec; + struct bvec_iter iter; int bio_is_patched; char **mapped_datav; + unsigned int segs = bio_segments(bio); dev_bytenr = 512 * bio->bi_iter.bi_sector; bio_is_patched = 0; if (dev_state->state->print_mask & BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH) pr_info("submit_bio(rw=%d,0x%x, bi_vcnt=%u, bi_sector=%llu (bytenr %llu), bi_bdev=%p)\n", - bio_op(bio), bio->bi_opf, bio->bi_vcnt, + bio_op(bio), bio->bi_opf, segs, (unsigned long long)bio->bi_iter.bi_sector, dev_bytenr, bio->bi_bdev); - mapped_datav = kmalloc_array(bio->bi_vcnt, + mapped_datav = kmalloc_array(segs, sizeof(*mapped_datav), GFP_NOFS); if (!mapped_datav) goto leave; cur_bytenr = dev_bytenr; - bio_for_each_segment_all(bvec, bio, i) { - BUG_ON(bvec->bv_len != PAGE_SIZE); - mapped_datav[i] = kmap(bvec->bv_page); + bio_for_each_segment(bvec, bio, iter) { + BUG_ON(bvec.bv_len != PAGE_SIZE); + mapped_datav[i] = kmap(bvec.bv_page); + i++; if (dev_state->state->print_mask & BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH_VERBOSE) pr_info("#%u: bytenr=%llu, len=%u, offset=%u\n", - i, cur_bytenr, bvec->bv_len, bvec->bv_offset); - cur_bytenr += bvec->bv_len; + i, cur_bytenr, bvec.bv_len, bvec.bv_offset); + cur_bytenr += bvec.bv_len; } btrfsic_process_written_block(dev_state, dev_bytenr, - mapped_datav, bio->bi_vcnt, + mapped_datav, segs, bio, &bio_is_patched, NULL, bio->bi_opf); - bio_for_each_segment_all(bvec, bio, i) - kunmap(bvec->bv_page); + bio_for_each_segment(bvec, bio, iter) + kunmap(bvec.bv_page); kfree(mapped_datav); } else if (NULL != dev_state && (bio->bi_opf & REQ_PREFLUSH)) { if (dev_state->state->print_mask & @@ -2923,13 +2915,10 @@ int btrfsic_mount(struct btrfs_fs_info *fs_info, fs_info->sectorsize, PAGE_SIZE); return -1; } - state = kzalloc(sizeof(*state), GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT); + state = kvzalloc(sizeof(*state), GFP_KERNEL); if (!state) { - state = vzalloc(sizeof(*state)); - if (!state) { - pr_info("btrfs check-integrity: vzalloc() failed!\n"); - return -1; - } + pr_info("btrfs check-integrity: allocation failed!\n"); + return -1; } if (!btrfsic_is_initialized) { diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index a2fad39f79ba..2c0b7b57fcd5 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -32,6 +32,7 @@ #include <linux/writeback.h> #include <linux/bit_spinlock.h> #include <linux/slab.h> +#include <linux/sched/mm.h> #include "ctree.h" #include "disk-io.h" #include "transaction.h" @@ -42,48 +43,7 @@ #include "extent_io.h" #include "extent_map.h" -struct compressed_bio { - /* number of bios pending for this compressed extent */ - refcount_t pending_bios; - - /* the pages with the compressed data on them */ - struct page **compressed_pages; - - /* inode that owns this data */ - struct inode *inode; - - /* starting offset in the inode for our pages */ - u64 start; - - /* number of bytes in the inode we're working on */ - unsigned long len; - - /* number of bytes on disk */ - unsigned long compressed_len; - - /* the compression algorithm for this bio */ - int compress_type; - - /* number of compressed pages in the array */ - unsigned long nr_pages; - - /* IO errors */ - int errors; - int mirror_num; - - /* for reads, this is the bio we are copying the data into */ - struct bio *orig_bio; - - /* - * the start of a variable length array of checksums only - * used by reads - */ - u32 sums; -}; - -static int btrfs_decompress_bio(int type, struct page **pages_in, - u64 disk_start, struct bio *orig_bio, - size_t srclen); +static int btrfs_decompress_bio(struct compressed_bio *cb); static inline int compressed_bio_size(struct btrfs_fs_info *fs_info, unsigned long disk_size) @@ -94,12 +54,6 @@ static inline int compressed_bio_size(struct btrfs_fs_info *fs_info, (DIV_ROUND_UP(disk_size, fs_info->sectorsize)) * csum_size; } -static struct bio *compressed_bio_alloc(struct block_device *bdev, - u64 first_byte, gfp_t gfp_flags) -{ - return btrfs_bio_alloc(bdev, first_byte >> 9, BIO_MAX_PAGES, gfp_flags); -} - static int check_compressed_csum(struct btrfs_inode *inode, struct compressed_bio *cb, u64 disk_start) @@ -173,11 +127,8 @@ static void end_compressed_bio_read(struct bio *bio) /* ok, we're the last bio for this extent, lets start * the decompression. */ - ret = btrfs_decompress_bio(cb->compress_type, - cb->compressed_pages, - cb->start, - cb->orig_bio, - cb->compressed_len); + ret = btrfs_decompress_bio(cb); + csum_failed: if (ret) cb->errors = 1; @@ -355,11 +306,7 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start, bdev = fs_info->fs_devices->latest_bdev; - bio = compressed_bio_alloc(bdev, first_byte, GFP_NOFS); - if (!bio) { - kfree(cb); - return BLK_STS_RESOURCE; - } + bio = btrfs_bio_alloc(bdev, first_byte); bio_set_op_attrs(bio, REQ_OP_WRITE, 0); bio->bi_private = cb; bio->bi_end_io = end_compressed_bio_write; @@ -406,8 +353,7 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start, bio_put(bio); - bio = compressed_bio_alloc(bdev, first_byte, GFP_NOFS); - BUG_ON(!bio); + bio = btrfs_bio_alloc(bdev, first_byte); bio_set_op_attrs(bio, REQ_OP_WRITE, 0); bio->bi_private = cb; bio->bi_end_io = end_compressed_bio_write; @@ -650,9 +596,7 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, /* include any pages we added in add_ra-bio_pages */ cb->len = bio->bi_iter.bi_size; - comp_bio = compressed_bio_alloc(bdev, cur_disk_byte, GFP_NOFS); - if (!comp_bio) - goto fail2; + comp_bio = btrfs_bio_alloc(bdev, cur_disk_byte); bio_set_op_attrs (comp_bio, REQ_OP_READ, 0); comp_bio->bi_private = cb; comp_bio->bi_end_io = end_compressed_bio_read; @@ -703,9 +647,7 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, bio_put(comp_bio); - comp_bio = compressed_bio_alloc(bdev, cur_disk_byte, - GFP_NOFS); - BUG_ON(!comp_bio); + comp_bio = btrfs_bio_alloc(bdev, cur_disk_byte); bio_set_op_attrs(comp_bio, REQ_OP_READ, 0); comp_bio->bi_private = cb; comp_bio->bi_end_io = end_compressed_bio_read; @@ -801,6 +743,7 @@ static struct list_head *find_workspace(int type) struct list_head *workspace; int cpus = num_online_cpus(); int idx = type - 1; + unsigned nofs_flag; struct list_head *idle_ws = &btrfs_comp_ws[idx].idle_ws; spinlock_t *ws_lock = &btrfs_comp_ws[idx].ws_lock; @@ -830,7 +773,15 @@ again: atomic_inc(total_ws); spin_unlock(ws_lock); + /* + * Allocation helpers call vmalloc that can't use GFP_NOFS, so we have + * to turn it off here because we might get called from the restricted + * context of btrfs_compress_bio/btrfs_compress_pages + */ + nofs_flag = memalloc_nofs_save(); workspace = btrfs_compress_op[idx]->alloc_workspace(); + memalloc_nofs_restore(nofs_flag); + if (IS_ERR(workspace)) { atomic_dec(total_ws); wake_up(ws_wait); @@ -961,19 +912,16 @@ int btrfs_compress_pages(int type, struct address_space *mapping, * be contiguous. They all correspond to the range of bytes covered by * the compressed extent. */ -static int btrfs_decompress_bio(int type, struct page **pages_in, - u64 disk_start, struct bio *orig_bio, - size_t srclen) +static int btrfs_decompress_bio(struct compressed_bio *cb) { struct list_head *workspace; int ret; + int type = cb->compress_type; workspace = find_workspace(type); - - ret = btrfs_compress_op[type-1]->decompress_bio(workspace, pages_in, - disk_start, orig_bio, - srclen); + ret = btrfs_compress_op[type - 1]->decompress_bio(workspace, cb); free_workspace(type, workspace); + return ret; } diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h index 680d4265d601..87f6d3332163 100644 --- a/fs/btrfs/compression.h +++ b/fs/btrfs/compression.h @@ -34,6 +34,45 @@ /* Maximum size of data before compression */ #define BTRFS_MAX_UNCOMPRESSED (SZ_128K) +struct compressed_bio { + /* number of bios pending for this compressed extent */ + refcount_t pending_bios; + + /* the pages with the compressed data on them */ + struct page **compressed_pages; + + /* inode that owns this data */ + struct inode *inode; + + /* starting offset in the inode for our pages */ + u64 start; + + /* number of bytes in the inode we're working on */ + unsigned long len; + + /* number of bytes on disk */ + unsigned long compressed_len; + + /* the compression algorithm for this bio */ + int compress_type; + + /* number of compressed pages in the array */ + unsigned long nr_pages; + + /* IO errors */ + int errors; + int mirror_num; + + /* for reads, this is the bio we are copying the data into */ + struct bio *orig_bio; + + /* + * the start of a variable length array of checksums only + * used by reads + */ + u32 sums; +}; + void btrfs_init_compress(void); void btrfs_exit_compress(void); @@ -78,10 +117,7 @@ struct btrfs_compress_op { unsigned long *total_out); int (*decompress_bio)(struct list_head *workspace, - struct page **pages_in, - u64 disk_start, - struct bio *orig_bio, - size_t srclen); + struct compressed_bio *cb); int (*decompress)(struct list_head *workspace, unsigned char *data_in, diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index a3a75f1de002..3f4daa9d6e2c 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -19,7 +19,7 @@ #include <linux/sched.h> #include <linux/slab.h> #include <linux/rbtree.h> -#include <linux/vmalloc.h> +#include <linux/mm.h> #include "ctree.h" #include "disk-io.h" #include "transaction.h" @@ -3667,14 +3667,14 @@ static noinline int __push_leaf_right(struct btrfs_fs_info *fs_info, /* make room in the right data area */ data_end = leaf_data_end(fs_info, right); memmove_extent_buffer(right, - btrfs_leaf_data(right) + data_end - push_space, - btrfs_leaf_data(right) + data_end, + BTRFS_LEAF_DATA_OFFSET + data_end - push_space, + BTRFS_LEAF_DATA_OFFSET + data_end, BTRFS_LEAF_DATA_SIZE(fs_info) - data_end); /* copy from the left data area */ - copy_extent_buffer(right, left, btrfs_leaf_data(right) + + copy_extent_buffer(right, left, BTRFS_LEAF_DATA_OFFSET + BTRFS_LEAF_DATA_SIZE(fs_info) - push_space, - btrfs_leaf_data(left) + leaf_data_end(fs_info, left), + BTRFS_LEAF_DATA_OFFSET + leaf_data_end(fs_info, left), push_space); memmove_extent_buffer(right, btrfs_item_nr_offset(push_items), @@ -3888,9 +3888,9 @@ static noinline int __push_leaf_left(struct btrfs_fs_info *fs_info, push_space = BTRFS_LEAF_DATA_SIZE(fs_info) - btrfs_item_offset_nr(right, push_items - 1); - copy_extent_buffer(left, right, btrfs_leaf_data(left) + + copy_extent_buffer(left, right, BTRFS_LEAF_DATA_OFFSET + leaf_data_end(fs_info, left) - push_space, - btrfs_leaf_data(right) + + BTRFS_LEAF_DATA_OFFSET + btrfs_item_offset_nr(right, push_items - 1), push_space); old_left_nritems = btrfs_header_nritems(left); @@ -3917,9 +3917,9 @@ static noinline int __push_leaf_left(struct btrfs_fs_info *fs_info, if (push_items < right_nritems) { push_space = btrfs_item_offset_nr(right, push_items - 1) - leaf_data_end(fs_info, right); - memmove_extent_buffer(right, btrfs_leaf_data(right) + + memmove_extent_buffer(right, BTRFS_LEAF_DATA_OFFSET + BTRFS_LEAF_DATA_SIZE(fs_info) - push_space, - btrfs_leaf_data(right) + + BTRFS_LEAF_DATA_OFFSET + leaf_data_end(fs_info, right), push_space); memmove_extent_buffer(right, btrfs_item_nr_offset(0), @@ -4069,8 +4069,8 @@ static noinline void copy_for_split(struct btrfs_trans_handle *trans, nritems * sizeof(struct btrfs_item)); copy_extent_buffer(right, l, - btrfs_leaf_data(right) + BTRFS_LEAF_DATA_SIZE(fs_info) - - data_copy_size, btrfs_leaf_data(l) + + BTRFS_LEAF_DATA_OFFSET + BTRFS_LEAF_DATA_SIZE(fs_info) - + data_copy_size, BTRFS_LEAF_DATA_OFFSET + leaf_data_end(fs_info, l), data_copy_size); rt_data_off = BTRFS_LEAF_DATA_SIZE(fs_info) - btrfs_item_end_nr(l, mid); @@ -4607,8 +4607,8 @@ void btrfs_truncate_item(struct btrfs_fs_info *fs_info, /* shift the data */ if (from_end) { - memmove_extent_buffer(leaf, btrfs_leaf_data(leaf) + - data_end + size_diff, btrfs_leaf_data(leaf) + + memmove_extent_buffer(leaf, BTRFS_LEAF_DATA_OFFSET + + data_end + size_diff, BTRFS_LEAF_DATA_OFFSET + data_end, old_data_start + new_size - data_end); } else { struct btrfs_disk_key disk_key; @@ -4634,8 +4634,8 @@ void btrfs_truncate_item(struct btrfs_fs_info *fs_info, } } - memmove_extent_buffer(leaf, btrfs_leaf_data(leaf) + - data_end + size_diff, btrfs_leaf_data(leaf) + + memmove_extent_buffer(leaf, BTRFS_LEAF_DATA_OFFSET + + data_end + size_diff, BTRFS_LEAF_DATA_OFFSET + data_end, old_data_start - data_end); offset = btrfs_disk_key_offset(&disk_key); @@ -4707,8 +4707,8 @@ void btrfs_extend_item(struct btrfs_fs_info *fs_info, struct btrfs_path *path, } /* shift the data */ - memmove_extent_buffer(leaf, btrfs_leaf_data(leaf) + - data_end - data_size, btrfs_leaf_data(leaf) + + memmove_extent_buffer(leaf, BTRFS_LEAF_DATA_OFFSET + + data_end - data_size, BTRFS_LEAF_DATA_OFFSET + data_end, old_data - data_end); data_end = old_data; @@ -4790,8 +4790,8 @@ void setup_items_for_insert(struct btrfs_root *root, struct btrfs_path *path, (nritems - slot) * sizeof(struct btrfs_item)); /* shift the data */ - memmove_extent_buffer(leaf, btrfs_leaf_data(leaf) + - data_end - total_data, btrfs_leaf_data(leaf) + + memmove_extent_buffer(leaf, BTRFS_LEAF_DATA_OFFSET + + data_end - total_data, BTRFS_LEAF_DATA_OFFSET + data_end, old_data - data_end); data_end = old_data; } @@ -4983,9 +4983,9 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, if (slot + nr != nritems) { int data_end = leaf_data_end(fs_info, leaf); - memmove_extent_buffer(leaf, btrfs_leaf_data(leaf) + + memmove_extent_buffer(leaf, BTRFS_LEAF_DATA_OFFSET + data_end + dsize, - btrfs_leaf_data(leaf) + data_end, + BTRFS_LEAF_DATA_OFFSET + data_end, last_off - data_end); for (i = slot + nr; i < nritems; i++) { diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index a0d0c79d95ed..3f3eb7b17cac 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -48,7 +48,6 @@ struct btrfs_trans_handle; struct btrfs_transaction; struct btrfs_pending_snapshot; extern struct kmem_cache *btrfs_trans_handle_cachep; -extern struct kmem_cache *btrfs_transaction_cachep; extern struct kmem_cache *btrfs_bit_radix_cachep; extern struct kmem_cache *btrfs_path_cachep; extern struct kmem_cache *btrfs_free_space_cachep; @@ -716,6 +715,10 @@ struct btrfs_delayed_root; #define BTRFS_FS_BTREE_ERR 11 #define BTRFS_FS_LOG1_ERR 12 #define BTRFS_FS_LOG2_ERR 13 +#define BTRFS_FS_QUOTA_OVERRIDE 14 +/* Used to record internally whether fs has been frozen */ +#define BTRFS_FS_FROZEN 15 + /* * Indicate that a whole-filesystem exclusive operation is running * (device replace, resize, device add/delete, balance) @@ -748,8 +751,7 @@ struct btrfs_fs_info { struct rb_root block_group_cache_tree; /* keep track of unallocated space */ - spinlock_t free_chunk_lock; - u64 free_chunk_space; + atomic64_t free_chunk_space; struct extent_io_tree freed_extents[2]; struct extent_io_tree *pinned_extents; @@ -797,17 +799,7 @@ struct btrfs_fs_info { * so it is also safe. */ u64 max_inline; - /* - * Protected by ->chunk_mutex and sb->s_umount. - * - * The reason that we use two lock to protect it is because only - * remount and mount operations can change it and these two operations - * are under sb->s_umount, but the read side (chunk allocation) can not - * acquire sb->s_umount or the deadlock would happen. So we use two - * locks to protect it. On the write side, we must acquire two locks, - * and on the read side, we just need acquire one of them. - */ - u64 alloc_start; + struct btrfs_transaction *running_transaction; wait_queue_head_t transaction_throttle; wait_queue_head_t transaction_wait; @@ -1107,9 +1099,6 @@ struct btrfs_fs_info { */ struct list_head pinned_chunks; - /* Used to record internally whether fs has been frozen */ - int fs_frozen; - /* Cached block sizes */ u32 nodesize; u32 sectorsize; @@ -1277,21 +1266,20 @@ struct btrfs_root { /* For qgroup metadata space reserve */ atomic64_t qgroup_meta_rsv; }; + static inline u32 btrfs_inode_sectorsize(const struct inode *inode) { return btrfs_sb(inode->i_sb)->sectorsize; } -static inline u32 __BTRFS_LEAF_DATA_SIZE(u32 blocksize) -{ - return blocksize - sizeof(struct btrfs_header); -} - static inline u32 BTRFS_LEAF_DATA_SIZE(const struct btrfs_fs_info *info) { - return __BTRFS_LEAF_DATA_SIZE(info->nodesize); + + return info->nodesize - sizeof(struct btrfs_header); } +#define BTRFS_LEAF_DATA_OFFSET offsetof(struct btrfs_leaf, items) + static inline u32 BTRFS_MAX_ITEM_SIZE(const struct btrfs_fs_info *info) { return BTRFS_LEAF_DATA_SIZE(info) - sizeof(struct btrfs_item); @@ -1553,8 +1541,27 @@ static inline void btrfs_set_##name(type *s, u##bits val) \ s->member = cpu_to_le##bits(val); \ } + +static inline u64 btrfs_device_total_bytes(struct extent_buffer *eb, + struct btrfs_dev_item *s) +{ + BUILD_BUG_ON(sizeof(u64) != + sizeof(((struct btrfs_dev_item *)0))->total_bytes); + return btrfs_get_64(eb, s, offsetof(struct btrfs_dev_item, + total_bytes)); +} +static inline void btrfs_set_device_total_bytes(struct extent_buffer *eb, + struct btrfs_dev_item *s, + u64 val) +{ + BUILD_BUG_ON(sizeof(u64) != + sizeof(((struct btrfs_dev_item *)0))->total_bytes); + WARN_ON(!IS_ALIGNED(val, eb->fs_info->sectorsize)); + btrfs_set_64(eb, s, offsetof(struct btrfs_dev_item, total_bytes), val); +} + + BTRFS_SETGET_FUNCS(device_type, struct btrfs_dev_item, type, 64); -BTRFS_SETGET_FUNCS(device_total_bytes, struct btrfs_dev_item, total_bytes, 64); BTRFS_SETGET_FUNCS(device_bytes_used, struct btrfs_dev_item, bytes_used, 64); BTRFS_SETGET_FUNCS(device_io_align, struct btrfs_dev_item, io_align, 32); BTRFS_SETGET_FUNCS(device_io_width, struct btrfs_dev_item, io_width, 32); @@ -2324,10 +2331,6 @@ static inline int btrfs_super_csum_size(struct btrfs_super_block *s) return btrfs_csum_sizes[t]; } -static inline unsigned long btrfs_leaf_data(struct extent_buffer *l) -{ - return offsetof(struct btrfs_leaf, items); -} /* * The leaf data grows from end-to-front in the node. @@ -2538,11 +2541,11 @@ BTRFS_SETGET_STACK_FUNCS(stack_dev_replace_cursor_right, /* helper function to cast into the data area of the leaf. */ #define btrfs_item_ptr(leaf, slot, type) \ - ((type *)(btrfs_leaf_data(leaf) + \ + ((type *)(BTRFS_LEAF_DATA_OFFSET + \ btrfs_item_offset_nr(leaf, slot))) #define btrfs_item_ptr_offset(leaf, slot) \ - ((unsigned long)(btrfs_leaf_data(leaf) + \ + ((unsigned long)(BTRFS_LEAF_DATA_OFFSET + \ btrfs_item_offset_nr(leaf, slot))) static inline bool btrfs_mixed_space_info(struct btrfs_space_info *space_info) @@ -2680,7 +2683,9 @@ void btrfs_get_block_group_trimming(struct btrfs_block_group_cache *cache); void btrfs_put_block_group_trimming(struct btrfs_block_group_cache *cache); void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info); -u64 btrfs_get_alloc_profile(struct btrfs_root *root, int data); +u64 btrfs_data_alloc_profile(struct btrfs_fs_info *fs_info); +u64 btrfs_metadata_alloc_profile(struct btrfs_fs_info *fs_info); +u64 btrfs_system_alloc_profile(struct btrfs_fs_info *fs_info); void btrfs_clear_space_info_full(struct btrfs_fs_info *info); enum btrfs_reserve_flush_enum { @@ -2703,9 +2708,13 @@ enum btrfs_flush_state { COMMIT_TRANS = 6, }; -int btrfs_check_data_free_space(struct inode *inode, u64 start, u64 len); int btrfs_alloc_data_chunk_ondemand(struct btrfs_inode *inode, u64 bytes); -void btrfs_free_reserved_data_space(struct inode *inode, u64 start, u64 len); +int btrfs_check_data_free_space(struct inode *inode, + struct extent_changeset **reserved, u64 start, u64 len); +void btrfs_free_reserved_data_space(struct inode *inode, + struct extent_changeset *reserved, u64 start, u64 len); +void btrfs_delalloc_release_space(struct inode *inode, + struct extent_changeset *reserved, u64 start, u64 len); void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start, u64 len); void btrfs_trans_release_metadata(struct btrfs_trans_handle *trans, @@ -2722,8 +2731,8 @@ void btrfs_subvolume_release_metadata(struct btrfs_fs_info *fs_info, struct btrfs_block_rsv *rsv); int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes); void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes); -int btrfs_delalloc_reserve_space(struct inode *inode, u64 start, u64 len); -void btrfs_delalloc_release_space(struct inode *inode, u64 start, u64 len); +int btrfs_delalloc_reserve_space(struct inode *inode, + struct extent_changeset **reserved, u64 start, u64 len); void btrfs_init_block_rsv(struct btrfs_block_rsv *rsv, unsigned short type); struct btrfs_block_rsv *btrfs_alloc_block_rsv(struct btrfs_fs_info *fs_info, unsigned short type); @@ -3031,12 +3040,14 @@ struct btrfs_dir_item *btrfs_lookup_xattr(struct btrfs_trans_handle *trans, const char *name, u16 name_len, int mod); int verify_dir_item(struct btrfs_fs_info *fs_info, - struct extent_buffer *leaf, + struct extent_buffer *leaf, int slot, struct btrfs_dir_item *dir_item); struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_fs_info *fs_info, struct btrfs_path *path, const char *name, int name_len); +bool btrfs_is_name_len_valid(struct extent_buffer *leaf, int slot, + unsigned long start, u16 name_len); /* orphan.c */ int btrfs_insert_orphan_item(struct btrfs_trans_handle *trans, @@ -3171,6 +3182,7 @@ int btrfs_create_subvol_root(struct btrfs_trans_handle *trans, int btrfs_merge_bio_hook(struct page *page, unsigned long offset, size_t size, struct bio *bio, unsigned long bio_flags); +void btrfs_set_range_writeback(void *private_data, u64 start, u64 end); int btrfs_page_mkwrite(struct vm_fault *vmf); int btrfs_readpage(struct file *file, struct page *page); void btrfs_evict_inode(struct inode *inode); diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index be70d90dfee5..93ffa898df6d 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -470,7 +470,8 @@ add_tail: static noinline void update_existing_head_ref(struct btrfs_delayed_ref_root *delayed_refs, struct btrfs_delayed_ref_node *existing, - struct btrfs_delayed_ref_node *update) + struct btrfs_delayed_ref_node *update, + int *old_ref_mod_ret) { struct btrfs_delayed_ref_head *existing_ref; struct btrfs_delayed_ref_head *ref; @@ -523,6 +524,8 @@ update_existing_head_ref(struct btrfs_delayed_ref_root *delayed_refs, * currently, for refs we just added we know we're a-ok. */ old_ref_mod = existing_ref->total_ref_mod; + if (old_ref_mod_ret) + *old_ref_mod_ret = old_ref_mod; existing->ref_mod += update->ref_mod; existing_ref->total_ref_mod += update->ref_mod; @@ -550,7 +553,8 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info, struct btrfs_delayed_ref_node *ref, struct btrfs_qgroup_extent_record *qrecord, u64 bytenr, u64 num_bytes, u64 ref_root, u64 reserved, - int action, int is_data, int *qrecord_inserted_ret) + int action, int is_data, int *qrecord_inserted_ret, + int *old_ref_mod, int *new_ref_mod) { struct btrfs_delayed_ref_head *existing; struct btrfs_delayed_ref_head *head_ref = NULL; @@ -638,7 +642,8 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info, if (existing) { WARN_ON(ref_root && reserved && existing->qgroup_ref_root && existing->qgroup_reserved); - update_existing_head_ref(delayed_refs, &existing->node, ref); + update_existing_head_ref(delayed_refs, &existing->node, ref, + old_ref_mod); /* * we've updated the existing ref, free the newly * allocated ref @@ -646,6 +651,8 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info, kmem_cache_free(btrfs_delayed_ref_head_cachep, head_ref); head_ref = existing; } else { + if (old_ref_mod) + *old_ref_mod = 0; if (is_data && count_mod < 0) delayed_refs->pending_csums += num_bytes; delayed_refs->num_heads++; @@ -655,6 +662,8 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info, } if (qrecord_inserted_ret) *qrecord_inserted_ret = qrecord_inserted; + if (new_ref_mod) + *new_ref_mod = head_ref->total_ref_mod; return head_ref; } @@ -778,7 +787,8 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info, struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, u64 parent, u64 ref_root, int level, int action, - struct btrfs_delayed_extent_op *extent_op) + struct btrfs_delayed_extent_op *extent_op, + int *old_ref_mod, int *new_ref_mod) { struct btrfs_delayed_tree_ref *ref; struct btrfs_delayed_ref_head *head_ref; @@ -813,7 +823,8 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info, */ head_ref = add_delayed_ref_head(fs_info, trans, &head_ref->node, record, bytenr, num_bytes, 0, 0, action, 0, - &qrecord_inserted); + &qrecord_inserted, old_ref_mod, + new_ref_mod); add_delayed_tree_ref(fs_info, trans, head_ref, &ref->node, bytenr, num_bytes, parent, ref_root, level, action); @@ -838,7 +849,8 @@ int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info, struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, u64 parent, u64 ref_root, - u64 owner, u64 offset, u64 reserved, int action) + u64 owner, u64 offset, u64 reserved, int action, + int *old_ref_mod, int *new_ref_mod) { struct btrfs_delayed_data_ref *ref; struct btrfs_delayed_ref_head *head_ref; @@ -878,7 +890,8 @@ int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info, */ head_ref = add_delayed_ref_head(fs_info, trans, &head_ref->node, record, bytenr, num_bytes, ref_root, reserved, - action, 1, &qrecord_inserted); + action, 1, &qrecord_inserted, + old_ref_mod, new_ref_mod); add_delayed_data_ref(fs_info, trans, head_ref, &ref->node, bytenr, num_bytes, parent, ref_root, owner, offset, @@ -909,7 +922,7 @@ int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info, add_delayed_ref_head(fs_info, trans, &head_ref->node, NULL, bytenr, num_bytes, 0, 0, BTRFS_UPDATE_DELAYED_HEAD, - extent_op->is_data, NULL); + extent_op->is_data, NULL, NULL, NULL); spin_unlock(&delayed_refs->lock); return 0; diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h index c0264ff01b53..ce88e4ac5276 100644 --- a/fs/btrfs/delayed-ref.h +++ b/fs/btrfs/delayed-ref.h @@ -247,12 +247,14 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info, struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, u64 parent, u64 ref_root, int level, int action, - struct btrfs_delayed_extent_op *extent_op); + struct btrfs_delayed_extent_op *extent_op, + int *old_ref_mod, int *new_ref_mod); int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info, struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, u64 parent, u64 ref_root, - u64 owner, u64 offset, u64 reserved, int action); + u64 owner, u64 offset, u64 reserved, int action, + int *old_ref_mod, int *new_ref_mod); int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info, struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 5fe1ca8abc70..bee3edeea7a3 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -388,7 +388,7 @@ int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info, if (ret) btrfs_err(fs_info, "kobj add dev failed %d", ret); - btrfs_wait_ordered_roots(fs_info, -1, 0, (u64)-1); + btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1); /* force writing the updated state information to disk */ trans = btrfs_start_transaction(root, 0); @@ -507,7 +507,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, mutex_unlock(&dev_replace->lock_finishing_cancel_unmount); return ret; } - btrfs_wait_ordered_roots(fs_info, -1, 0, (u64)-1); + btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1); trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c index c24d615e3d7f..41cb9196eaa8 100644 --- a/fs/btrfs/dir-item.c +++ b/fs/btrfs/dir-item.c @@ -395,8 +395,6 @@ struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_fs_info *fs_info, leaf = path->nodes[0]; dir_item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_dir_item); - if (verify_dir_item(fs_info, leaf, dir_item)) - return NULL; total_len = btrfs_item_size_nr(leaf, path->slots[0]); while (cur < total_len) { @@ -405,6 +403,8 @@ struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_fs_info *fs_info, btrfs_dir_data_len(leaf, dir_item); name_ptr = (unsigned long)(dir_item + 1); + if (verify_dir_item(fs_info, leaf, path->slots[0], dir_item)) + return NULL; if (btrfs_dir_name_len(leaf, dir_item) == name_len && memcmp_extent_buffer(leaf, name, name_ptr, name_len) == 0) return dir_item; @@ -453,9 +453,11 @@ int btrfs_delete_one_dir_name(struct btrfs_trans_handle *trans, int verify_dir_item(struct btrfs_fs_info *fs_info, struct extent_buffer *leaf, + int slot, struct btrfs_dir_item *dir_item) { u16 namelen = BTRFS_NAME_LEN; + int ret; u8 type = btrfs_dir_type(leaf, dir_item); if (type >= BTRFS_FT_MAX) { @@ -472,6 +474,12 @@ int verify_dir_item(struct btrfs_fs_info *fs_info, return 1; } + namelen = btrfs_dir_name_len(leaf, dir_item); + ret = btrfs_is_name_len_valid(leaf, slot, + (unsigned long)(dir_item + 1), namelen); + if (!ret) + return 1; + /* BTRFS_MAX_XATTR_SIZE is the same for all dir items */ if ((btrfs_dir_data_len(leaf, dir_item) + btrfs_dir_name_len(leaf, dir_item)) > @@ -484,3 +492,67 @@ int verify_dir_item(struct btrfs_fs_info *fs_info, return 0; } + +bool btrfs_is_name_len_valid(struct extent_buffer *leaf, int slot, + unsigned long start, u16 name_len) +{ + struct btrfs_fs_info *fs_info = leaf->fs_info; + struct btrfs_key key; + u32 read_start; + u32 read_end; + u32 item_start; + u32 item_end; + u32 size; + bool ret = true; + + ASSERT(start > BTRFS_LEAF_DATA_OFFSET); + + read_start = start - BTRFS_LEAF_DATA_OFFSET; + read_end = read_start + name_len; + item_start = btrfs_item_offset_nr(leaf, slot); + item_end = btrfs_item_end_nr(leaf, slot); + + btrfs_item_key_to_cpu(leaf, &key, slot); + + switch (key.type) { + case BTRFS_DIR_ITEM_KEY: + case BTRFS_XATTR_ITEM_KEY: + case BTRFS_DIR_INDEX_KEY: + size = sizeof(struct btrfs_dir_item); + break; + case BTRFS_INODE_REF_KEY: + size = sizeof(struct btrfs_inode_ref); + break; + case BTRFS_INODE_EXTREF_KEY: + size = sizeof(struct btrfs_inode_extref); + break; + case BTRFS_ROOT_REF_KEY: + case BTRFS_ROOT_BACKREF_KEY: + size = sizeof(struct btrfs_root_ref); + break; + default: + ret = false; + goto out; + } + + if (read_start < item_start) { + ret = false; + goto out; + } + if (read_end > item_end) { + ret = false; + goto out; + } + + /* there shall be item(s) before name */ + if (read_start - item_start < size) { + ret = false; + goto out; + } + +out: + if (!ret) + btrfs_crit(fs_info, "invalid dir item name len: %u", + (unsigned int)name_len); + return ret; +} diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 6036d15b47b8..086dcbadce09 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -89,7 +89,6 @@ struct btrfs_end_io_wq { struct btrfs_fs_info *info; blk_status_t status; enum btrfs_wq_endio_type metadata; - struct list_head list; struct btrfs_work work; }; @@ -118,9 +117,9 @@ void btrfs_end_io_wq_exit(void) * just before they are sent down the IO stack. */ struct async_submit_bio { - struct inode *inode; + void *private_data; + struct btrfs_fs_info *fs_info; struct bio *bio; - struct list_head list; extent_submit_bio_hook_t *submit_bio_start; extent_submit_bio_hook_t *submit_bio_done; int mirror_num; @@ -871,7 +870,7 @@ static void run_one_async_start(struct btrfs_work *work) blk_status_t ret; async = container_of(work, struct async_submit_bio, work); - ret = async->submit_bio_start(async->inode, async->bio, + ret = async->submit_bio_start(async->private_data, async->bio, async->mirror_num, async->bio_flags, async->bio_offset); if (ret) @@ -885,7 +884,7 @@ static void run_one_async_done(struct btrfs_work *work) int limit; async = container_of(work, struct async_submit_bio, work); - fs_info = BTRFS_I(async->inode)->root->fs_info; + fs_info = async->fs_info; limit = btrfs_async_submit_limit(fs_info); limit = limit * 2 / 3; @@ -904,7 +903,7 @@ static void run_one_async_done(struct btrfs_work *work) return; } - async->submit_bio_done(async->inode, async->bio, async->mirror_num, + async->submit_bio_done(async->private_data, async->bio, async->mirror_num, async->bio_flags, async->bio_offset); } @@ -916,11 +915,11 @@ static void run_one_async_free(struct btrfs_work *work) kfree(async); } -blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, - struct inode *inode, struct bio *bio, int mirror_num, - unsigned long bio_flags, u64 bio_offset, - extent_submit_bio_hook_t *submit_bio_start, - extent_submit_bio_hook_t *submit_bio_done) +blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio, + int mirror_num, unsigned long bio_flags, + u64 bio_offset, void *private_data, + extent_submit_bio_hook_t *submit_bio_start, + extent_submit_bio_hook_t *submit_bio_done) { struct async_submit_bio *async; @@ -928,7 +927,8 @@ blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, if (!async) return BLK_STS_RESOURCE; - async->inode = inode; + async->private_data = private_data; + async->fs_info = fs_info; async->bio = bio; async->mirror_num = mirror_num; async->submit_bio_start = submit_bio_start; @@ -974,9 +974,9 @@ static blk_status_t btree_csum_one_bio(struct bio *bio) return errno_to_blk_status(ret); } -static blk_status_t __btree_submit_bio_start(struct inode *inode, - struct bio *bio, int mirror_num, unsigned long bio_flags, - u64 bio_offset) +static blk_status_t __btree_submit_bio_start(void *private_data, struct bio *bio, + int mirror_num, unsigned long bio_flags, + u64 bio_offset) { /* * when we're called for a write, we're already in the async @@ -985,10 +985,11 @@ static blk_status_t __btree_submit_bio_start(struct inode *inode, return btree_csum_one_bio(bio); } -static blk_status_t __btree_submit_bio_done(struct inode *inode, - struct bio *bio, int mirror_num, unsigned long bio_flags, - u64 bio_offset) +static blk_status_t __btree_submit_bio_done(void *private_data, struct bio *bio, + int mirror_num, unsigned long bio_flags, + u64 bio_offset) { + struct inode *inode = private_data; blk_status_t ret; /* @@ -1014,10 +1015,11 @@ static int check_async_write(unsigned long bio_flags) return 1; } -static blk_status_t btree_submit_bio_hook(struct inode *inode, struct bio *bio, - int mirror_num, unsigned long bio_flags, - u64 bio_offset) +static blk_status_t btree_submit_bio_hook(void *private_data, struct bio *bio, + int mirror_num, unsigned long bio_flags, + u64 bio_offset) { + struct inode *inode = private_data; struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); int async = check_async_write(bio_flags); blk_status_t ret; @@ -1042,8 +1044,8 @@ static blk_status_t btree_submit_bio_hook(struct inode *inode, struct bio *bio, * kthread helpers are used to submit writes so that * checksumming can happen in parallel across all CPUs */ - ret = btrfs_wq_submit_bio(fs_info, inode, bio, mirror_num, 0, - bio_offset, + ret = btrfs_wq_submit_bio(fs_info, bio, mirror_num, 0, + bio_offset, private_data, __btree_submit_bio_start, __btree_submit_bio_done); } @@ -1221,10 +1223,10 @@ int btrfs_write_tree_block(struct extent_buffer *buf) buf->start + buf->len - 1); } -int btrfs_wait_tree_block_writeback(struct extent_buffer *buf) +void btrfs_wait_tree_block_writeback(struct extent_buffer *buf) { - return filemap_fdatawait_range(buf->pages[0]->mapping, - buf->start, buf->start + buf->len - 1); + filemap_fdatawait_range(buf->pages[0]->mapping, + buf->start, buf->start + buf->len - 1); } struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr, @@ -1254,9 +1256,9 @@ void clean_tree_block(struct btrfs_fs_info *fs_info, btrfs_assert_tree_locked(buf); if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &buf->bflags)) { - __percpu_counter_add(&fs_info->dirty_metadata_bytes, - -buf->len, - fs_info->dirty_metadata_batch); + percpu_counter_add_batch(&fs_info->dirty_metadata_bytes, + -buf->len, + fs_info->dirty_metadata_batch); /* ugh, clear_extent_buffer_dirty needs to lock the page */ btrfs_set_lock_blocking(buf); clear_extent_buffer_dirty(buf); @@ -1346,8 +1348,7 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info, root->log_transid_committed = -1; root->last_log_commit = 0; if (!dummy) - extent_io_tree_init(&root->dirty_log_pages, - fs_info->btree_inode->i_mapping); + extent_io_tree_init(&root->dirty_log_pages, NULL); memset(&root->root_key, 0, sizeof(root->root_key)); memset(&root->root_item, 0, sizeof(root->root_item)); @@ -2308,7 +2309,7 @@ static void btrfs_init_btree_inode(struct btrfs_fs_info *fs_info) inode->i_mapping->a_ops = &btree_aops; RB_CLEAR_NODE(&BTRFS_I(inode)->rb_node); - extent_io_tree_init(&BTRFS_I(inode)->io_tree, inode->i_mapping); + extent_io_tree_init(&BTRFS_I(inode)->io_tree, inode); BTRFS_I(inode)->io_tree.track_uptodate = 0; extent_map_tree_init(&BTRFS_I(inode)->extent_tree); @@ -2625,7 +2626,6 @@ int open_ctree(struct super_block *sb, spin_lock_init(&fs_info->fs_roots_radix_lock); spin_lock_init(&fs_info->delayed_iput_lock); spin_lock_init(&fs_info->defrag_inodes_lock); - spin_lock_init(&fs_info->free_chunk_lock); spin_lock_init(&fs_info->tree_mod_seq_lock); spin_lock_init(&fs_info->super_lock); spin_lock_init(&fs_info->qgroup_op_lock); @@ -2661,12 +2661,11 @@ int open_ctree(struct super_block *sb, atomic_set(&fs_info->qgroup_op_seq, 0); atomic_set(&fs_info->reada_works_cnt, 0); atomic64_set(&fs_info->tree_mod_seq, 0); - fs_info->fs_frozen = 0; fs_info->sb = sb; fs_info->max_inline = BTRFS_DEFAULT_MAX_INLINE; fs_info->metadata_ratio = 0; fs_info->defrag_inodes = RB_ROOT; - fs_info->free_chunk_space = 0; + atomic64_set(&fs_info->free_chunk_space, 0); fs_info->tree_mod_log = RB_ROOT; fs_info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL; fs_info->avg_delayed_ref_runtime = NSEC_PER_SEC >> 6; /* div by 64 */ @@ -2703,10 +2702,8 @@ int open_ctree(struct super_block *sb, fs_info->block_group_cache_tree = RB_ROOT; fs_info->first_logical_byte = (u64)-1; - extent_io_tree_init(&fs_info->freed_extents[0], - fs_info->btree_inode->i_mapping); - extent_io_tree_init(&fs_info->freed_extents[1], - fs_info->btree_inode->i_mapping); + extent_io_tree_init(&fs_info->freed_extents[0], NULL); + extent_io_tree_init(&fs_info->freed_extents[1], NULL); fs_info->pinned_extents = &fs_info->freed_extents[0]; set_bit(BTRFS_FS_BARRIER, &fs_info->flags); @@ -3484,65 +3481,61 @@ static int write_dev_supers(struct btrfs_device *device, */ static void btrfs_end_empty_barrier(struct bio *bio) { - if (bio->bi_private) - complete(bio->bi_private); - bio_put(bio); + complete(bio->bi_private); } /* - * trigger flushes for one the devices. If you pass wait == 0, the flushes are - * sent down. With wait == 1, it waits for the previous flush. - * - * any device where the flush fails with eopnotsupp are flagged as not-barrier - * capable + * Submit a flush request to the device if it supports it. Error handling is + * done in the waiting counterpart. */ -static blk_status_t write_dev_flush(struct btrfs_device *device, int wait) +static void write_dev_flush(struct btrfs_device *device) { struct request_queue *q = bdev_get_queue(device->bdev); - struct bio *bio; - blk_status_t ret = 0; + struct bio *bio = device->flush_bio; if (!test_bit(QUEUE_FLAG_WC, &q->queue_flags)) - return 0; + return; - if (wait) { - bio = device->flush_bio; - if (!bio) - return 0; + bio_reset(bio); + bio->bi_end_io = btrfs_end_empty_barrier; + bio->bi_bdev = device->bdev; + bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH; + init_completion(&device->flush_wait); + bio->bi_private = &device->flush_wait; - wait_for_completion(&device->flush_wait); + submit_bio(bio); + device->flush_bio_sent = 1; +} - if (bio->bi_status) { - ret = bio->bi_status; - btrfs_dev_stat_inc_and_print(device, - BTRFS_DEV_STAT_FLUSH_ERRS); - } +/* + * If the flush bio has been submitted by write_dev_flush, wait for it. + */ +static blk_status_t wait_dev_flush(struct btrfs_device *device) +{ + struct bio *bio = device->flush_bio; - /* drop the reference from the wait == 0 run */ - bio_put(bio); - device->flush_bio = NULL; + if (!device->flush_bio_sent) + return 0; - return ret; - } + device->flush_bio_sent = 0; + wait_for_completion_io(&device->flush_wait); - /* - * one reference for us, and we leave it for the - * caller - */ - device->flush_bio = NULL; - bio = btrfs_io_bio_alloc(GFP_NOFS, 0); - if (!bio) - return BLK_STS_RESOURCE; + return bio->bi_status; +} - bio->bi_end_io = btrfs_end_empty_barrier; - bio->bi_bdev = device->bdev; - bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH; - init_completion(&device->flush_wait); - bio->bi_private = &device->flush_wait; - device->flush_bio = bio; +static int check_barrier_error(struct btrfs_fs_devices *fsdevs) +{ + int dev_flush_error = 0; + struct btrfs_device *dev; - bio_get(bio); - btrfsic_submit_bio(bio); + list_for_each_entry_rcu(dev, &fsdevs->devices, dev_list) { + if (!dev->bdev || dev->last_flush_error) + dev_flush_error++; + } + + if (dev_flush_error > + fsdevs->fs_info->num_tolerated_disk_barrier_failures) + return -EIO; return 0; } @@ -3555,7 +3548,6 @@ static int barrier_all_devices(struct btrfs_fs_info *info) { struct list_head *head; struct btrfs_device *dev; - int errors_send = 0; int errors_wait = 0; blk_status_t ret; @@ -3564,16 +3556,13 @@ static int barrier_all_devices(struct btrfs_fs_info *info) list_for_each_entry_rcu(dev, head, dev_list) { if (dev->missing) continue; - if (!dev->bdev) { - errors_send++; + if (!dev->bdev) continue; - } if (!dev->in_fs_metadata || !dev->writeable) continue; - ret = write_dev_flush(dev, 0); - if (ret) - errors_send++; + write_dev_flush(dev); + dev->last_flush_error = 0; } /* wait for all the barriers */ @@ -3587,13 +3576,23 @@ static int barrier_all_devices(struct btrfs_fs_info *info) if (!dev->in_fs_metadata || !dev->writeable) continue; - ret = write_dev_flush(dev, 1); - if (ret) + ret = wait_dev_flush(dev); + if (ret) { + dev->last_flush_error = ret; + btrfs_dev_stat_inc_and_print(dev, + BTRFS_DEV_STAT_FLUSH_ERRS); errors_wait++; + } + } + + if (errors_wait) { + /* + * At some point we need the status of all disks + * to arrive at the volume status. So error checking + * is being pushed to a separate loop. + */ + return check_barrier_error(info->fs_devices); } - if (errors_send > info->num_tolerated_disk_barrier_failures || - errors_wait > info->num_tolerated_disk_barrier_failures) - return -EIO; return 0; } @@ -4048,9 +4047,9 @@ void btrfs_mark_buffer_dirty(struct extent_buffer *buf) buf->start, transid, fs_info->generation); was_dirty = set_extent_buffer_dirty(buf); if (!was_dirty) - __percpu_counter_add(&fs_info->dirty_metadata_bytes, - buf->len, - fs_info->dirty_metadata_batch); + percpu_counter_add_batch(&fs_info->dirty_metadata_bytes, + buf->len, + fs_info->dirty_metadata_batch); #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY if (btrfs_header_level(buf) == 0 && check_leaf(root, buf)) { btrfs_print_leaf(fs_info, buf); @@ -4577,11 +4576,6 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans, cur_trans->state =TRANS_STATE_COMPLETED; wake_up(&cur_trans->commit_wait); - - /* - memset(cur_trans, 0, sizeof(*cur_trans)); - kmem_cache_free(btrfs_transaction_cachep, cur_trans); - */ } static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info) @@ -4637,6 +4631,12 @@ static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info) return 0; } +static struct btrfs_fs_info *btree_fs_info(void *private_data) +{ + struct inode *inode = private_data; + return btrfs_sb(inode->i_sb); +} + static const struct extent_io_ops btree_extent_io_ops = { /* mandatory callbacks */ .submit_bio_hook = btree_submit_bio_hook, @@ -4644,6 +4644,8 @@ static const struct extent_io_ops btree_extent_io_ops = { /* note we're sharing with inode.c for the merge bio hook */ .merge_bio_hook = btrfs_merge_bio_hook, .readpage_io_failed_hook = btree_io_failed_hook, + .set_range_writeback = btrfs_set_range_writeback, + .tree_fs_info = btree_fs_info, /* optional callbacks */ }; diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index c581927555f3..0a634d3ffc16 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -120,14 +120,14 @@ u32 btrfs_csum_data(const char *data, u32 seed, size_t len); void btrfs_csum_final(u32 crc, u8 *result); blk_status_t btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio, enum btrfs_wq_endio_type metadata); -blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, - struct inode *inode, struct bio *bio, int mirror_num, - unsigned long bio_flags, u64 bio_offset, - extent_submit_bio_hook_t *submit_bio_start, - extent_submit_bio_hook_t *submit_bio_done); +blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio, + int mirror_num, unsigned long bio_flags, + u64 bio_offset, void *private_data, + extent_submit_bio_hook_t *submit_bio_start, + extent_submit_bio_hook_t *submit_bio_done); unsigned long btrfs_async_submit_limit(struct btrfs_fs_info *info); int btrfs_write_tree_block(struct extent_buffer *buf); -int btrfs_wait_tree_block_writeback(struct extent_buffer *buf); +void btrfs_wait_tree_block_writeback(struct extent_buffer *buf); int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info); int btrfs_add_log_tree(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c index 87144c9f9593..fa66980726c9 100644 --- a/fs/btrfs/export.c +++ b/fs/btrfs/export.c @@ -282,6 +282,11 @@ static int btrfs_get_name(struct dentry *parent, char *name, name_len = btrfs_inode_ref_name_len(leaf, iref); } + ret = btrfs_is_name_len_valid(leaf, path->slots[0], name_ptr, name_len); + if (!ret) { + btrfs_free_path(path); + return -EIO; + } read_extent_buffer(leaf, name, name_ptr, name_len); btrfs_free_path(path); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 33d979e9ea2a..375f8c728d91 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -97,10 +97,11 @@ static int btrfs_free_reserved_bytes(struct btrfs_block_group_cache *cache, u64 num_bytes, int delalloc); static int block_rsv_use_bytes(struct btrfs_block_rsv *block_rsv, u64 num_bytes); -static int __reserve_metadata_bytes(struct btrfs_root *root, +static int __reserve_metadata_bytes(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info, u64 orig_bytes, - enum btrfs_reserve_flush_enum flush); + enum btrfs_reserve_flush_enum flush, + bool system_chunk); static void space_info_add_new_bytes(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info, u64 num_bytes); @@ -766,6 +767,26 @@ static struct btrfs_space_info *__find_space_info(struct btrfs_fs_info *info, return NULL; } +static void add_pinned_bytes(struct btrfs_fs_info *fs_info, s64 num_bytes, + u64 owner, u64 root_objectid) +{ + struct btrfs_space_info *space_info; + u64 flags; + + if (owner < BTRFS_FIRST_FREE_OBJECTID) { + if (root_objectid == BTRFS_CHUNK_TREE_OBJECTID) + flags = BTRFS_BLOCK_GROUP_SYSTEM; + else + flags = BTRFS_BLOCK_GROUP_METADATA; + } else { + flags = BTRFS_BLOCK_GROUP_DATA; + } + + space_info = __find_space_info(fs_info, flags); + ASSERT(space_info); + percpu_counter_add(&space_info->total_bytes_pinned, num_bytes); +} + /* * after adding space to the filesystem, we need to clear the full flags * on all the space infos. @@ -2092,6 +2113,7 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, u64 parent, u64 root_objectid, u64 owner, u64 offset) { + int old_ref_mod, new_ref_mod; int ret; BUG_ON(owner < BTRFS_FIRST_FREE_OBJECTID && @@ -2099,15 +2121,21 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, if (owner < BTRFS_FIRST_FREE_OBJECTID) { ret = btrfs_add_delayed_tree_ref(fs_info, trans, bytenr, - num_bytes, - parent, root_objectid, (int)owner, - BTRFS_ADD_DELAYED_REF, NULL); + num_bytes, parent, + root_objectid, (int)owner, + BTRFS_ADD_DELAYED_REF, NULL, + &old_ref_mod, &new_ref_mod); } else { ret = btrfs_add_delayed_data_ref(fs_info, trans, bytenr, - num_bytes, parent, root_objectid, - owner, offset, 0, - BTRFS_ADD_DELAYED_REF); + num_bytes, parent, + root_objectid, owner, offset, + 0, BTRFS_ADD_DELAYED_REF, + &old_ref_mod, &new_ref_mod); } + + if (ret == 0 && old_ref_mod < 0 && new_ref_mod >= 0) + add_pinned_bytes(fs_info, -num_bytes, owner, root_objectid); + return ret; } @@ -2411,6 +2439,16 @@ static int run_one_delayed_ref(struct btrfs_trans_handle *trans, head = btrfs_delayed_node_to_head(node); trace_run_delayed_ref_head(fs_info, node, head, node->action); + if (head->total_ref_mod < 0) { + struct btrfs_block_group_cache *cache; + + cache = btrfs_lookup_block_group(fs_info, node->bytenr); + ASSERT(cache); + percpu_counter_add(&cache->space_info->total_bytes_pinned, + -node->num_bytes); + btrfs_put_block_group(cache); + } + if (insert_reserved) { btrfs_pin_extent(fs_info, node->bytenr, node->num_bytes, 1); @@ -3364,6 +3402,7 @@ static int cache_save_setup(struct btrfs_block_group_cache *block_group, struct btrfs_fs_info *fs_info = block_group->fs_info; struct btrfs_root *root = fs_info->tree_root; struct inode *inode = NULL; + struct extent_changeset *data_reserved = NULL; u64 alloc_hint = 0; int dcs = BTRFS_DC_ERROR; u64 num_pages = 0; @@ -3483,7 +3522,7 @@ again: num_pages *= 16; num_pages *= PAGE_SIZE; - ret = btrfs_check_data_free_space(inode, 0, num_pages); + ret = btrfs_check_data_free_space(inode, &data_reserved, 0, num_pages); if (ret) goto out_put; @@ -3514,6 +3553,7 @@ out: block_group->disk_cache_state = dcs; spin_unlock(&block_group->lock); + extent_changeset_free(data_reserved); return ret; } @@ -3924,88 +3964,83 @@ static const char *alloc_name(u64 flags) }; } -static int update_space_info(struct btrfs_fs_info *info, u64 flags, - u64 total_bytes, u64 bytes_used, - u64 bytes_readonly, - struct btrfs_space_info **space_info) +static int create_space_info(struct btrfs_fs_info *info, u64 flags, + struct btrfs_space_info **new) { - struct btrfs_space_info *found; + + struct btrfs_space_info *space_info; int i; - int factor; int ret; - if (flags & (BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1 | - BTRFS_BLOCK_GROUP_RAID10)) - factor = 2; - else - factor = 1; - - found = __find_space_info(info, flags); - if (found) { - spin_lock(&found->lock); - found->total_bytes += total_bytes; - found->disk_total += total_bytes * factor; - found->bytes_used += bytes_used; - found->disk_used += bytes_used * factor; - found->bytes_readonly += bytes_readonly; - if (total_bytes > 0) - found->full = 0; - space_info_add_new_bytes(info, found, total_bytes - - bytes_used - bytes_readonly); - spin_unlock(&found->lock); - *space_info = found; - return 0; - } - found = kzalloc(sizeof(*found), GFP_NOFS); - if (!found) + space_info = kzalloc(sizeof(*space_info), GFP_NOFS); + if (!space_info) return -ENOMEM; - ret = percpu_counter_init(&found->total_bytes_pinned, 0, GFP_KERNEL); + ret = percpu_counter_init(&space_info->total_bytes_pinned, 0, + GFP_KERNEL); if (ret) { - kfree(found); + kfree(space_info); return ret; } for (i = 0; i < BTRFS_NR_RAID_TYPES; i++) - INIT_LIST_HEAD(&found->block_groups[i]); - init_rwsem(&found->groups_sem); - spin_lock_init(&found->lock); - found->flags = flags & BTRFS_BLOCK_GROUP_TYPE_MASK; - found->total_bytes = total_bytes; - found->disk_total = total_bytes * factor; - found->bytes_used = bytes_used; - found->disk_used = bytes_used * factor; - found->bytes_pinned = 0; - found->bytes_reserved = 0; - found->bytes_readonly = bytes_readonly; - found->bytes_may_use = 0; - found->full = 0; - found->max_extent_size = 0; - found->force_alloc = CHUNK_ALLOC_NO_FORCE; - found->chunk_alloc = 0; - found->flush = 0; - init_waitqueue_head(&found->wait); - INIT_LIST_HEAD(&found->ro_bgs); - INIT_LIST_HEAD(&found->tickets); - INIT_LIST_HEAD(&found->priority_tickets); - - ret = kobject_init_and_add(&found->kobj, &space_info_ktype, + INIT_LIST_HEAD(&space_info->block_groups[i]); + init_rwsem(&space_info->groups_sem); + spin_lock_init(&space_info->lock); + space_info->flags = flags & BTRFS_BLOCK_GROUP_TYPE_MASK; + space_info->force_alloc = CHUNK_ALLOC_NO_FORCE; + init_waitqueue_head(&space_info->wait); + INIT_LIST_HEAD(&space_info->ro_bgs); + INIT_LIST_HEAD(&space_info->tickets); + INIT_LIST_HEAD(&space_info->priority_tickets); + + ret = kobject_init_and_add(&space_info->kobj, &space_info_ktype, info->space_info_kobj, "%s", - alloc_name(found->flags)); + alloc_name(space_info->flags)); if (ret) { - percpu_counter_destroy(&found->total_bytes_pinned); - kfree(found); + percpu_counter_destroy(&space_info->total_bytes_pinned); + kfree(space_info); return ret; } - *space_info = found; - list_add_rcu(&found->list, &info->space_info); + *new = space_info; + list_add_rcu(&space_info->list, &info->space_info); if (flags & BTRFS_BLOCK_GROUP_DATA) - info->data_sinfo = found; + info->data_sinfo = space_info; return ret; } +static void update_space_info(struct btrfs_fs_info *info, u64 flags, + u64 total_bytes, u64 bytes_used, + u64 bytes_readonly, + struct btrfs_space_info **space_info) +{ + struct btrfs_space_info *found; + int factor; + + if (flags & (BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1 | + BTRFS_BLOCK_GROUP_RAID10)) + factor = 2; + else + factor = 1; + + found = __find_space_info(info, flags); + ASSERT(found); + spin_lock(&found->lock); + found->total_bytes += total_bytes; + found->disk_total += total_bytes * factor; + found->bytes_used += bytes_used; + found->disk_used += bytes_used * factor; + found->bytes_readonly += bytes_readonly; + if (total_bytes > 0) + found->full = 0; + space_info_add_new_bytes(info, found, total_bytes - + bytes_used - bytes_readonly); + spin_unlock(&found->lock); + *space_info = found; +} + static void set_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags) { u64 extra_flags = chunk_to_extended(flags) & @@ -4121,7 +4156,7 @@ static u64 get_alloc_profile(struct btrfs_fs_info *fs_info, u64 orig_flags) return btrfs_reduce_alloc_profile(fs_info, flags); } -u64 btrfs_get_alloc_profile(struct btrfs_root *root, int data) +static u64 get_alloc_profile_by_root(struct btrfs_root *root, int data) { struct btrfs_fs_info *fs_info = root->fs_info; u64 flags; @@ -4138,6 +4173,21 @@ u64 btrfs_get_alloc_profile(struct btrfs_root *root, int data) return ret; } +u64 btrfs_data_alloc_profile(struct btrfs_fs_info *fs_info) +{ + return get_alloc_profile(fs_info, BTRFS_BLOCK_GROUP_DATA); +} + +u64 btrfs_metadata_alloc_profile(struct btrfs_fs_info *fs_info) +{ + return get_alloc_profile(fs_info, BTRFS_BLOCK_GROUP_METADATA); +} + +u64 btrfs_system_alloc_profile(struct btrfs_fs_info *fs_info) +{ + return get_alloc_profile(fs_info, BTRFS_BLOCK_GROUP_SYSTEM); +} + static u64 btrfs_space_info_used(struct btrfs_space_info *s_info, bool may_use_included) { @@ -4187,7 +4237,7 @@ again: data_sinfo->force_alloc = CHUNK_ALLOC_FORCE; spin_unlock(&data_sinfo->lock); alloc: - alloc_target = btrfs_get_alloc_profile(root, 1); + alloc_target = btrfs_data_alloc_profile(fs_info); /* * It is ugly that we don't call nolock join * transaction for the free space inode case here. @@ -4238,7 +4288,7 @@ commit_trans: if (need_commit > 0) { btrfs_start_delalloc_roots(fs_info, 0, -1); - btrfs_wait_ordered_roots(fs_info, -1, 0, + btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1); } @@ -4278,12 +4328,8 @@ commit_trans: return ret; } -/* - * New check_data_free_space() with ability for precious data reservation - * Will replace old btrfs_check_data_free_space(), but for patch split, - * add a new function first and then replace it. - */ -int btrfs_check_data_free_space(struct inode *inode, u64 start, u64 len) +int btrfs_check_data_free_space(struct inode *inode, + struct extent_changeset **reserved, u64 start, u64 len) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); int ret; @@ -4298,9 +4344,11 @@ int btrfs_check_data_free_space(struct inode *inode, u64 start, u64 len) return ret; /* Use new btrfs_qgroup_reserve_data to reserve precious data space. */ - ret = btrfs_qgroup_reserve_data(inode, start, len); - if (ret) + ret = btrfs_qgroup_reserve_data(inode, reserved, start, len); + if (ret < 0) btrfs_free_reserved_data_space_noquota(inode, start, len); + else + ret = 0; return ret; } @@ -4341,7 +4389,8 @@ void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start, * This one will handle the per-inode data rsv map for accurate reserved * space framework. */ -void btrfs_free_reserved_data_space(struct inode *inode, u64 start, u64 len) +void btrfs_free_reserved_data_space(struct inode *inode, + struct extent_changeset *reserved, u64 start, u64 len) { struct btrfs_root *root = BTRFS_I(inode)->root; @@ -4351,7 +4400,7 @@ void btrfs_free_reserved_data_space(struct inode *inode, u64 start, u64 len) start = round_down(start, root->fs_info->sectorsize); btrfs_free_reserved_data_space_noquota(inode, start, len); - btrfs_qgroup_free_data(inode, start, len); + btrfs_qgroup_free_data(inode, reserved, start, len); } static void force_metadata_allocation(struct btrfs_fs_info *info) @@ -4463,9 +4512,8 @@ void check_system_chunk(struct btrfs_trans_handle *trans, } if (left < thresh) { - u64 flags; + u64 flags = btrfs_system_alloc_profile(fs_info); - flags = btrfs_get_alloc_profile(fs_info->chunk_root, 0); /* * Ignore failure to create system chunk. We might end up not * needing it, as we might not need to COW all nodes/leafs from @@ -4506,10 +4554,10 @@ static int do_chunk_alloc(struct btrfs_trans_handle *trans, space_info = __find_space_info(fs_info, flags); if (!space_info) { - ret = update_space_info(fs_info, flags, 0, 0, 0, &space_info); - BUG_ON(ret); /* -ENOMEM */ + ret = create_space_info(fs_info, flags, &space_info); + if (ret) + return ret; } - BUG_ON(!space_info); /* Logic error */ again: spin_lock(&space_info->lock); @@ -4614,11 +4662,11 @@ out: return ret; } -static int can_overcommit(struct btrfs_root *root, +static int can_overcommit(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info, u64 bytes, - enum btrfs_reserve_flush_enum flush) + enum btrfs_reserve_flush_enum flush, + bool system_chunk) { - struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv; u64 profile; u64 space_size; @@ -4629,7 +4677,11 @@ static int can_overcommit(struct btrfs_root *root, if (space_info->flags & BTRFS_BLOCK_GROUP_DATA) return 0; - profile = btrfs_get_alloc_profile(root, 0); + if (system_chunk) + profile = btrfs_system_alloc_profile(fs_info); + else + profile = btrfs_metadata_alloc_profile(fs_info); + used = btrfs_space_info_used(space_info, false); /* @@ -4646,9 +4698,7 @@ static int can_overcommit(struct btrfs_root *root, used += space_info->bytes_may_use; - spin_lock(&fs_info->free_chunk_lock); - avail = fs_info->free_chunk_space; - spin_unlock(&fs_info->free_chunk_lock); + avail = atomic64_read(&fs_info->free_chunk_space); /* * If we have dup, raid1 or raid10 then only half of the free @@ -4698,14 +4748,14 @@ static void btrfs_writeback_inodes_sb_nr(struct btrfs_fs_info *fs_info, } } -static inline int calc_reclaim_items_nr(struct btrfs_fs_info *fs_info, +static inline u64 calc_reclaim_items_nr(struct btrfs_fs_info *fs_info, u64 to_reclaim) { u64 bytes; - int nr; + u64 nr; bytes = btrfs_calc_trans_metadata_size(fs_info, 1); - nr = (int)div64_u64(to_reclaim, bytes); + nr = div64_u64(to_reclaim, bytes); if (!nr) nr = 1; return nr; @@ -4716,24 +4766,23 @@ static inline int calc_reclaim_items_nr(struct btrfs_fs_info *fs_info, /* * shrink metadata reservation for delalloc */ -static void shrink_delalloc(struct btrfs_root *root, u64 to_reclaim, u64 orig, - bool wait_ordered) +static void shrink_delalloc(struct btrfs_fs_info *fs_info, u64 to_reclaim, + u64 orig, bool wait_ordered) { - struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_block_rsv *block_rsv; struct btrfs_space_info *space_info; struct btrfs_trans_handle *trans; u64 delalloc_bytes; u64 max_reclaim; + u64 items; long time_left; unsigned long nr_pages; int loops; - int items; enum btrfs_reserve_flush_enum flush; /* Calc the number of the pages we need flush for space reservation */ items = calc_reclaim_items_nr(fs_info, to_reclaim); - to_reclaim = (u64)items * EXTENT_SIZE_PER_ITEM; + to_reclaim = items * EXTENT_SIZE_PER_ITEM; trans = (struct btrfs_trans_handle *)current->journal_info; block_rsv = &fs_info->delalloc_block_rsv; @@ -4776,7 +4825,7 @@ skip_async: else flush = BTRFS_RESERVE_NO_FLUSH; spin_lock(&space_info->lock); - if (can_overcommit(root, space_info, orig, flush)) { + if (can_overcommit(fs_info, space_info, orig, flush, false)) { spin_unlock(&space_info->lock); break; } @@ -4838,7 +4887,7 @@ static int may_commit_transaction(struct btrfs_fs_info *fs_info, spin_lock(&delayed_rsv->lock); if (percpu_counter_compare(&space_info->total_bytes_pinned, - bytes - delayed_rsv->size) >= 0) { + bytes - delayed_rsv->size) < 0) { spin_unlock(&delayed_rsv->lock); return -ENOSPC; } @@ -4886,7 +4935,7 @@ static int flush_space(struct btrfs_fs_info *fs_info, break; case FLUSH_DELALLOC: case FLUSH_DELALLOC_WAIT: - shrink_delalloc(root, num_bytes * 2, orig_bytes, + shrink_delalloc(fs_info, num_bytes * 2, orig_bytes, state == FLUSH_DELALLOC_WAIT); break; case ALLOC_CHUNK: @@ -4896,7 +4945,7 @@ static int flush_space(struct btrfs_fs_info *fs_info, break; } ret = do_chunk_alloc(trans, fs_info, - btrfs_get_alloc_profile(root, 0), + btrfs_metadata_alloc_profile(fs_info), CHUNK_ALLOC_NO_FORCE); btrfs_end_transaction(trans); if (ret > 0 || ret == -ENOSPC) @@ -4917,8 +4966,9 @@ static int flush_space(struct btrfs_fs_info *fs_info, } static inline u64 -btrfs_calc_reclaim_metadata_size(struct btrfs_root *root, - struct btrfs_space_info *space_info) +btrfs_calc_reclaim_metadata_size(struct btrfs_fs_info *fs_info, + struct btrfs_space_info *space_info, + bool system_chunk) { struct reserve_ticket *ticket; u64 used; @@ -4933,14 +4983,14 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_root *root, return to_reclaim; to_reclaim = min_t(u64, num_online_cpus() * SZ_1M, SZ_16M); - if (can_overcommit(root, space_info, to_reclaim, - BTRFS_RESERVE_FLUSH_ALL)) + if (can_overcommit(fs_info, space_info, to_reclaim, + BTRFS_RESERVE_FLUSH_ALL, system_chunk)) return 0; - used = space_info->bytes_used + space_info->bytes_reserved + - space_info->bytes_pinned + space_info->bytes_readonly + - space_info->bytes_may_use; - if (can_overcommit(root, space_info, SZ_1M, BTRFS_RESERVE_FLUSH_ALL)) + used = btrfs_space_info_used(space_info, true); + + if (can_overcommit(fs_info, space_info, SZ_1M, + BTRFS_RESERVE_FLUSH_ALL, system_chunk)) expected = div_factor_fine(space_info->total_bytes, 95); else expected = div_factor_fine(space_info->total_bytes, 90); @@ -4954,17 +5004,18 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_root *root, return to_reclaim; } -static inline int need_do_async_reclaim(struct btrfs_space_info *space_info, - struct btrfs_root *root, u64 used) +static inline int need_do_async_reclaim(struct btrfs_fs_info *fs_info, + struct btrfs_space_info *space_info, + u64 used, bool system_chunk) { - struct btrfs_fs_info *fs_info = root->fs_info; u64 thresh = div_factor_fine(space_info->total_bytes, 98); /* If we're just plain full then async reclaim just slows us down. */ if ((space_info->bytes_used + space_info->bytes_reserved) >= thresh) return 0; - if (!btrfs_calc_reclaim_metadata_size(root, space_info)) + if (!btrfs_calc_reclaim_metadata_size(fs_info, space_info, + system_chunk)) return 0; return (used >= thresh && !btrfs_fs_closing(fs_info) && @@ -5001,8 +5052,8 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work) space_info = __find_space_info(fs_info, BTRFS_BLOCK_GROUP_METADATA); spin_lock(&space_info->lock); - to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info->fs_root, - space_info); + to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, space_info, + false); if (!to_reclaim) { space_info->flush = 0; spin_unlock(&space_info->lock); @@ -5024,8 +5075,9 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work) spin_unlock(&space_info->lock); return; } - to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info->fs_root, - space_info); + to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, + space_info, + false); ticket = list_first_entry(&space_info->tickets, struct reserve_ticket, list); if (last_tickets_id == space_info->tickets_id) { @@ -5063,8 +5115,8 @@ static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info, int flush_state = FLUSH_DELAYED_ITEMS_NR; spin_lock(&space_info->lock); - to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info->extent_root, - space_info); + to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, space_info, + false); if (!to_reclaim) { spin_unlock(&space_info->lock); return; @@ -5143,12 +5195,12 @@ static int wait_reserve_ticket(struct btrfs_fs_info *fs_info, * regain reservations will be made and this will fail if there is not enough * space already. */ -static int __reserve_metadata_bytes(struct btrfs_root *root, +static int __reserve_metadata_bytes(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info, u64 orig_bytes, - enum btrfs_reserve_flush_enum flush) + enum btrfs_reserve_flush_enum flush, + bool system_chunk) { - struct btrfs_fs_info *fs_info = root->fs_info; struct reserve_ticket ticket; u64 used; int ret = 0; @@ -5170,7 +5222,8 @@ static int __reserve_metadata_bytes(struct btrfs_root *root, trace_btrfs_space_reservation(fs_info, "space_info", space_info->flags, orig_bytes, 1); ret = 0; - } else if (can_overcommit(root, space_info, orig_bytes, flush)) { + } else if (can_overcommit(fs_info, space_info, orig_bytes, flush, + system_chunk)) { space_info->bytes_may_use += orig_bytes; trace_btrfs_space_reservation(fs_info, "space_info", space_info->flags, orig_bytes, 1); @@ -5197,7 +5250,7 @@ static int __reserve_metadata_bytes(struct btrfs_root *root, orig_bytes, flush, "enospc"); queue_work(system_unbound_wq, - &root->fs_info->async_reclaim_work); + &fs_info->async_reclaim_work); } } else { list_add_tail(&ticket.list, @@ -5211,7 +5264,8 @@ static int __reserve_metadata_bytes(struct btrfs_root *root, * the async reclaim as we will panic. */ if (!test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags) && - need_do_async_reclaim(space_info, root, used) && + need_do_async_reclaim(fs_info, space_info, + used, system_chunk) && !work_busy(&fs_info->async_reclaim_work)) { trace_btrfs_trigger_flush(fs_info, space_info->flags, orig_bytes, flush, "preempt"); @@ -5269,9 +5323,10 @@ static int reserve_metadata_bytes(struct btrfs_root *root, struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv; int ret; + bool system_chunk = (root == fs_info->chunk_root); - ret = __reserve_metadata_bytes(root, block_rsv->space_info, orig_bytes, - flush); + ret = __reserve_metadata_bytes(fs_info, block_rsv->space_info, + orig_bytes, flush, system_chunk); if (ret == -ENOSPC && unlikely(root->orphan_cleanup_state == ORPHAN_CLEANUP_STARTED)) { if (block_rsv != global_rsv && @@ -5380,9 +5435,7 @@ static void space_info_add_old_bytes(struct btrfs_fs_info *fs_info, * overcommit, and if we can't then we just need to free up our space * and not satisfy any requests. */ - used = space_info->bytes_used + space_info->bytes_reserved + - space_info->bytes_pinned + space_info->bytes_readonly + - space_info->bytes_may_use; + used = btrfs_space_info_used(space_info, true); if (used - num_bytes >= space_info->total_bytes) check_overcommit = true; again: @@ -5394,8 +5447,7 @@ again: * adding the ticket space would be a double count. */ if (check_overcommit && - !can_overcommit(fs_info->extent_root, space_info, 0, - flush)) + !can_overcommit(fs_info, space_info, 0, flush, false)) break; if (num_bytes >= ticket->bytes) { list_del_init(&ticket->list); @@ -6124,6 +6176,8 @@ void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes) * @inode: inode we're writing to * @start: start range we are writing to * @len: how long the range we are writing to + * @reserved: mandatory parameter, record actually reserved qgroup ranges of + * current reservation. * * This will do the following things * @@ -6141,16 +6195,17 @@ void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes) * Return 0 for success * Return <0 for error(-ENOSPC or -EQUOT) */ -int btrfs_delalloc_reserve_space(struct inode *inode, u64 start, u64 len) +int btrfs_delalloc_reserve_space(struct inode *inode, + struct extent_changeset **reserved, u64 start, u64 len) { int ret; - ret = btrfs_check_data_free_space(inode, start, len); + ret = btrfs_check_data_free_space(inode, reserved, start, len); if (ret < 0) return ret; ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), len); if (ret < 0) - btrfs_free_reserved_data_space(inode, start, len); + btrfs_free_reserved_data_space(inode, *reserved, start, len); return ret; } @@ -6169,10 +6224,11 @@ int btrfs_delalloc_reserve_space(struct inode *inode, u64 start, u64 len) * list if there are no delalloc bytes left. * Also it will handle the qgroup reserved space. */ -void btrfs_delalloc_release_space(struct inode *inode, u64 start, u64 len) +void btrfs_delalloc_release_space(struct inode *inode, + struct extent_changeset *reserved, u64 start, u64 len) { btrfs_delalloc_release_metadata(BTRFS_I(inode), len); - btrfs_free_reserved_data_space(inode, start, len); + btrfs_free_reserved_data_space(inode, reserved, start, len); } static int update_block_group(struct btrfs_trans_handle *trans, @@ -6248,6 +6304,8 @@ static int update_block_group(struct btrfs_trans_handle *trans, trace_btrfs_space_reservation(info, "pinned", cache->space_info->flags, num_bytes, 1); + percpu_counter_add(&cache->space_info->total_bytes_pinned, + num_bytes); set_extent_dirty(info->pinned_extents, bytenr, bytenr + num_bytes - 1, GFP_NOFS | __GFP_NOFAIL); @@ -6324,6 +6382,7 @@ static int pin_down_extent(struct btrfs_fs_info *fs_info, trace_btrfs_space_reservation(fs_info, "pinned", cache->space_info->flags, num_bytes, 1); + percpu_counter_add(&cache->space_info->total_bytes_pinned, num_bytes); set_extent_dirty(fs_info->pinned_extents, bytenr, bytenr + num_bytes - 1, GFP_NOFS | __GFP_NOFAIL); return 0; @@ -6794,27 +6853,6 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans, return 0; } -static void add_pinned_bytes(struct btrfs_fs_info *fs_info, u64 num_bytes, - u64 owner, u64 root_objectid) -{ - struct btrfs_space_info *space_info; - u64 flags; - - if (owner < BTRFS_FIRST_FREE_OBJECTID) { - if (root_objectid == BTRFS_CHUNK_TREE_OBJECTID) - flags = BTRFS_BLOCK_GROUP_SYSTEM; - else - flags = BTRFS_BLOCK_GROUP_METADATA; - } else { - flags = BTRFS_BLOCK_GROUP_DATA; - } - - space_info = __find_space_info(fs_info, flags); - BUG_ON(!space_info); /* Logic bug */ - percpu_counter_add(&space_info->total_bytes_pinned, num_bytes); -} - - static int __btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_fs_info *info, struct btrfs_delayed_ref_node *node, u64 parent, @@ -7037,8 +7075,6 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, goto out; } } - add_pinned_bytes(info, -num_bytes, owner_objectid, - root_objectid); } else { if (found_extent) { BUG_ON(is_data && refs_to_drop != @@ -7170,19 +7206,19 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, int ret; if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) { - ret = btrfs_add_delayed_tree_ref(fs_info, trans, - buf->start, buf->len, - parent, + int old_ref_mod, new_ref_mod; + + ret = btrfs_add_delayed_tree_ref(fs_info, trans, buf->start, + buf->len, parent, root->root_key.objectid, btrfs_header_level(buf), - BTRFS_DROP_DELAYED_REF, NULL); + BTRFS_DROP_DELAYED_REF, NULL, + &old_ref_mod, &new_ref_mod); BUG_ON(ret); /* -ENOMEM */ + pin = old_ref_mod >= 0 && new_ref_mod < 0; } - if (!last_ref) - return; - - if (btrfs_header_generation(buf) == trans->transid) { + if (last_ref && btrfs_header_generation(buf) == trans->transid) { struct btrfs_block_group_cache *cache; if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) { @@ -7191,6 +7227,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, goto out; } + pin = 0; cache = btrfs_lookup_block_group(fs_info, buf->start); if (btrfs_header_flag(buf, BTRFS_HEADER_FLAG_WRITTEN)) { @@ -7206,18 +7243,19 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, btrfs_free_reserved_bytes(cache, buf->len, 0); btrfs_put_block_group(cache); trace_btrfs_reserved_extent_free(fs_info, buf->start, buf->len); - pin = 0; } out: if (pin) add_pinned_bytes(fs_info, buf->len, btrfs_header_level(buf), root->root_key.objectid); - /* - * Deleting the buffer, clear the corrupt flag since it doesn't matter - * anymore. - */ - clear_bit(EXTENT_BUFFER_CORRUPT, &buf->bflags); + if (last_ref) { + /* + * Deleting the buffer, clear the corrupt flag since it doesn't + * matter anymore. + */ + clear_bit(EXTENT_BUFFER_CORRUPT, &buf->bflags); + } } /* Can return -ENOMEM */ @@ -7226,12 +7264,12 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, u64 parent, u64 root_objectid, u64 owner, u64 offset) { + int old_ref_mod, new_ref_mod; int ret; if (btrfs_is_testing(fs_info)) return 0; - add_pinned_bytes(fs_info, num_bytes, owner, root_objectid); /* * tree log blocks never actually go into the extent allocation @@ -7241,19 +7279,25 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans, WARN_ON(owner >= BTRFS_FIRST_FREE_OBJECTID); /* unlocks the pinned mutex */ btrfs_pin_extent(fs_info, bytenr, num_bytes, 1); + old_ref_mod = new_ref_mod = 0; ret = 0; } else if (owner < BTRFS_FIRST_FREE_OBJECTID) { ret = btrfs_add_delayed_tree_ref(fs_info, trans, bytenr, - num_bytes, - parent, root_objectid, (int)owner, - BTRFS_DROP_DELAYED_REF, NULL); + num_bytes, parent, + root_objectid, (int)owner, + BTRFS_DROP_DELAYED_REF, NULL, + &old_ref_mod, &new_ref_mod); } else { ret = btrfs_add_delayed_data_ref(fs_info, trans, bytenr, - num_bytes, - parent, root_objectid, owner, - offset, 0, - BTRFS_DROP_DELAYED_REF); + num_bytes, parent, + root_objectid, owner, offset, + 0, BTRFS_DROP_DELAYED_REF, + &old_ref_mod, &new_ref_mod); } + + if (ret == 0 && old_ref_mod >= 0 && new_ref_mod < 0) + add_pinned_bytes(fs_info, num_bytes, owner, root_objectid); + return ret; } @@ -7956,7 +8000,7 @@ int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes, u64 flags; int ret; - flags = btrfs_get_alloc_profile(root, is_data); + flags = get_alloc_profile_by_root(root, is_data); again: WARN_ON(num_bytes < fs_info->sectorsize); ret = find_free_extent(fs_info, ram_bytes, num_bytes, empty_size, @@ -8200,9 +8244,9 @@ int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans, BUG_ON(root_objectid == BTRFS_TREE_LOG_OBJECTID); ret = btrfs_add_delayed_data_ref(fs_info, trans, ins->objectid, - ins->offset, 0, - root_objectid, owner, offset, - ram_bytes, BTRFS_ADD_DELAYED_EXTENT); + ins->offset, 0, root_objectid, owner, + offset, ram_bytes, + BTRFS_ADD_DELAYED_EXTENT, NULL, NULL); return ret; } @@ -8422,11 +8466,11 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans, extent_op->is_data = false; extent_op->level = level; - ret = btrfs_add_delayed_tree_ref(fs_info, trans, - ins.objectid, ins.offset, - parent, root_objectid, level, + ret = btrfs_add_delayed_tree_ref(fs_info, trans, ins.objectid, + ins.offset, parent, + root_objectid, level, BTRFS_ADD_DELAYED_EXTENT, - extent_op); + extent_op, NULL, NULL); if (ret) goto out_free_delayed; } @@ -10059,19 +10103,9 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info) } trace_btrfs_add_block_group(info, cache, 0); - ret = update_space_info(info, cache->flags, found_key.offset, - btrfs_block_group_used(&cache->item), - cache->bytes_super, &space_info); - if (ret) { - btrfs_remove_free_space_cache(cache); - spin_lock(&info->block_group_cache_lock); - rb_erase(&cache->cache_node, - &info->block_group_cache_tree); - RB_CLEAR_NODE(&cache->cache_node); - spin_unlock(&info->block_group_cache_lock); - btrfs_put_block_group(cache); - goto error; - } + update_space_info(info, cache->flags, found_key.offset, + btrfs_block_group_used(&cache->item), + cache->bytes_super, &space_info); cache->space_info = space_info; @@ -10203,16 +10237,19 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, } #endif /* - * Call to ensure the corresponding space_info object is created and - * assigned to our block group, but don't update its counters just yet. - * We want our bg to be added to the rbtree with its ->space_info set. + * Ensure the corresponding space_info object is created and + * assigned to our block group. We want our bg to be added to the rbtree + * with its ->space_info set. */ - ret = update_space_info(fs_info, cache->flags, 0, 0, 0, - &cache->space_info); - if (ret) { - btrfs_remove_free_space_cache(cache); - btrfs_put_block_group(cache); - return ret; + cache->space_info = __find_space_info(fs_info, cache->flags); + if (!cache->space_info) { + ret = create_space_info(fs_info, cache->flags, + &cache->space_info); + if (ret) { + btrfs_remove_free_space_cache(cache); + btrfs_put_block_group(cache); + return ret; + } } ret = btrfs_add_block_group_cache(fs_info, cache); @@ -10227,18 +10264,8 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, * the rbtree, update the space info's counters. */ trace_btrfs_add_block_group(fs_info, cache, 1); - ret = update_space_info(fs_info, cache->flags, size, bytes_used, + update_space_info(fs_info, cache->flags, size, bytes_used, cache->bytes_super, &cache->space_info); - if (ret) { - btrfs_remove_free_space_cache(cache); - spin_lock(&fs_info->block_group_cache_lock); - rb_erase(&cache->cache_node, - &fs_info->block_group_cache_tree); - RB_CLEAR_NODE(&cache->cache_node); - spin_unlock(&fs_info->block_group_cache_lock); - btrfs_put_block_group(cache); - return ret; - } update_global_block_rsv(fs_info); __link_block_group(cache->space_info, cache); @@ -10786,21 +10813,21 @@ int btrfs_init_space_info(struct btrfs_fs_info *fs_info) mixed = 1; flags = BTRFS_BLOCK_GROUP_SYSTEM; - ret = update_space_info(fs_info, flags, 0, 0, 0, &space_info); + ret = create_space_info(fs_info, flags, &space_info); if (ret) goto out; if (mixed) { flags = BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA; - ret = update_space_info(fs_info, flags, 0, 0, 0, &space_info); + ret = create_space_info(fs_info, flags, &space_info); } else { flags = BTRFS_BLOCK_GROUP_METADATA; - ret = update_space_info(fs_info, flags, 0, 0, 0, &space_info); + ret = create_space_info(fs_info, flags, &space_info); if (ret) goto out; flags = BTRFS_BLOCK_GROUP_DATA; - ret = update_space_info(fs_info, flags, 0, 0, 0, &space_info); + ret = create_space_info(fs_info, flags, &space_info); } out: return ret; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index d1cd60140817..556484cf5d93 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -87,19 +87,9 @@ void btrfs_leak_debug_check(void) static inline void __btrfs_debug_check_extent_io_range(const char *caller, struct extent_io_tree *tree, u64 start, u64 end) { - struct inode *inode; - u64 isize; - - if (!tree->mapping) - return; - - inode = tree->mapping->host; - isize = i_size_read(inode); - if (end >= PAGE_SIZE && (end % 2) == 0 && end != isize - 1) { - btrfs_debug_rl(BTRFS_I(inode)->root->fs_info, - "%s: ino %llu isize %llu odd range [%llu,%llu]", - caller, btrfs_ino(BTRFS_I(inode)), isize, start, end); - } + if (tree->ops && tree->ops->check_extent_io_range) + tree->ops->check_extent_io_range(tree->private_data, caller, + start, end); } #else #define btrfs_leak_debug_add(new, head) do {} while (0) @@ -154,9 +144,9 @@ static noinline void flush_write_bio(void *data); static inline struct btrfs_fs_info * tree_fs_info(struct extent_io_tree *tree) { - if (!tree->mapping) - return NULL; - return btrfs_sb(tree->mapping->host->i_sb); + if (tree->ops) + return tree->ops->tree_fs_info(tree->private_data); + return NULL; } int __init extent_io_init(void) @@ -214,13 +204,13 @@ void extent_io_exit(void) } void extent_io_tree_init(struct extent_io_tree *tree, - struct address_space *mapping) + void *private_data) { tree->state = RB_ROOT; tree->ops = NULL; tree->dirty_bytes = 0; spin_lock_init(&tree->lock); - tree->mapping = mapping; + tree->private_data = private_data; } static struct extent_state *alloc_extent_state(gfp_t mask) @@ -370,8 +360,7 @@ static void merge_cb(struct extent_io_tree *tree, struct extent_state *new, struct extent_state *other) { if (tree->ops && tree->ops->merge_extent_hook) - tree->ops->merge_extent_hook(tree->mapping->host, new, - other); + tree->ops->merge_extent_hook(tree->private_data, new, other); } /* @@ -422,15 +411,14 @@ static void set_state_cb(struct extent_io_tree *tree, struct extent_state *state, unsigned *bits) { if (tree->ops && tree->ops->set_bit_hook) - tree->ops->set_bit_hook(tree->mapping->host, state, bits); + tree->ops->set_bit_hook(tree->private_data, state, bits); } static void clear_state_cb(struct extent_io_tree *tree, struct extent_state *state, unsigned *bits) { if (tree->ops && tree->ops->clear_bit_hook) - tree->ops->clear_bit_hook(BTRFS_I(tree->mapping->host), - state, bits); + tree->ops->clear_bit_hook(tree->private_data, state, bits); } static void set_state_bits(struct extent_io_tree *tree, @@ -479,7 +467,7 @@ static void split_cb(struct extent_io_tree *tree, struct extent_state *orig, u64 split) { if (tree->ops && tree->ops->split_extent_hook) - tree->ops->split_extent_hook(tree->mapping->host, orig, split); + tree->ops->split_extent_hook(tree->private_data, orig, split); } /* @@ -1403,17 +1391,7 @@ void extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end) */ static void set_range_writeback(struct extent_io_tree *tree, u64 start, u64 end) { - unsigned long index = start >> PAGE_SHIFT; - unsigned long end_index = end >> PAGE_SHIFT; - struct page *page; - - while (index <= end_index) { - page = find_get_page(tree->mapping, index); - BUG_ON(!page); /* Pages should be in the extent_io_tree */ - set_page_writeback(page); - put_page(page); - index++; - } + tree->ops->set_range_writeback(tree->private_data, start, end); } /* find the first state struct with 'bits' set after 'start', and @@ -1962,11 +1940,12 @@ static void check_page_uptodate(struct extent_io_tree *tree, struct page *page) SetPageUptodate(page); } -int free_io_failure(struct btrfs_inode *inode, struct io_failure_record *rec) +int free_io_failure(struct extent_io_tree *failure_tree, + struct extent_io_tree *io_tree, + struct io_failure_record *rec) { int ret; int err = 0; - struct extent_io_tree *failure_tree = &inode->io_failure_tree; set_state_failrec(failure_tree, rec->start, NULL); ret = clear_extent_bits(failure_tree, rec->start, @@ -1975,7 +1954,7 @@ int free_io_failure(struct btrfs_inode *inode, struct io_failure_record *rec) if (ret) err = ret; - ret = clear_extent_bits(&inode->io_tree, rec->start, + ret = clear_extent_bits(io_tree, rec->start, rec->start + rec->len - 1, EXTENT_DAMAGED); if (ret && !err) @@ -1995,11 +1974,10 @@ int free_io_failure(struct btrfs_inode *inode, struct io_failure_record *rec) * currently, there can be no more than two copies of every data bit. thus, * exactly one rewrite is required. */ -int repair_io_failure(struct btrfs_inode *inode, u64 start, u64 length, - u64 logical, struct page *page, - unsigned int pg_offset, int mirror_num) +int repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start, + u64 length, u64 logical, struct page *page, + unsigned int pg_offset, int mirror_num) { - struct btrfs_fs_info *fs_info = inode->root->fs_info; struct bio *bio; struct btrfs_device *dev; u64 map_length = 0; @@ -2010,9 +1988,7 @@ int repair_io_failure(struct btrfs_inode *inode, u64 start, u64 length, ASSERT(!(fs_info->sb->s_flags & MS_RDONLY)); BUG_ON(!mirror_num); - bio = btrfs_io_bio_alloc(GFP_NOFS, 1); - if (!bio) - return -EIO; + bio = btrfs_io_bio_alloc(1); bio->bi_iter.bi_size = 0; map_length = length; @@ -2071,7 +2047,7 @@ int repair_io_failure(struct btrfs_inode *inode, u64 start, u64 length, btrfs_info_rl_in_rcu(fs_info, "read error corrected: ino %llu off %llu (dev %s sector %llu)", - btrfs_ino(inode), start, + ino, start, rcu_str_deref(dev->name), sector); btrfs_bio_counter_dec(fs_info); bio_put(bio); @@ -2091,8 +2067,7 @@ int repair_eb_io_failure(struct btrfs_fs_info *fs_info, for (i = 0; i < num_pages; i++) { struct page *p = eb->pages[i]; - ret = repair_io_failure(BTRFS_I(fs_info->btree_inode), start, - PAGE_SIZE, start, p, + ret = repair_io_failure(fs_info, 0, start, PAGE_SIZE, start, p, start - page_offset(p), mirror_num); if (ret) break; @@ -2106,24 +2081,24 @@ int repair_eb_io_failure(struct btrfs_fs_info *fs_info, * each time an IO finishes, we do a fast check in the IO failure tree * to see if we need to process or clean up an io_failure_record */ -int clean_io_failure(struct btrfs_inode *inode, u64 start, struct page *page, - unsigned int pg_offset) +int clean_io_failure(struct btrfs_fs_info *fs_info, + struct extent_io_tree *failure_tree, + struct extent_io_tree *io_tree, u64 start, + struct page *page, u64 ino, unsigned int pg_offset) { u64 private; struct io_failure_record *failrec; - struct btrfs_fs_info *fs_info = inode->root->fs_info; struct extent_state *state; int num_copies; int ret; private = 0; - ret = count_range_bits(&inode->io_failure_tree, &private, - (u64)-1, 1, EXTENT_DIRTY, 0); + ret = count_range_bits(failure_tree, &private, (u64)-1, 1, + EXTENT_DIRTY, 0); if (!ret) return 0; - ret = get_state_failrec(&inode->io_failure_tree, start, - &failrec); + ret = get_state_failrec(failure_tree, start, &failrec); if (ret) return 0; @@ -2139,25 +2114,25 @@ int clean_io_failure(struct btrfs_inode *inode, u64 start, struct page *page, if (fs_info->sb->s_flags & MS_RDONLY) goto out; - spin_lock(&inode->io_tree.lock); - state = find_first_extent_bit_state(&inode->io_tree, + spin_lock(&io_tree->lock); + state = find_first_extent_bit_state(io_tree, failrec->start, EXTENT_LOCKED); - spin_unlock(&inode->io_tree.lock); + spin_unlock(&io_tree->lock); if (state && state->start <= failrec->start && state->end >= failrec->start + failrec->len - 1) { num_copies = btrfs_num_copies(fs_info, failrec->logical, failrec->len); if (num_copies > 1) { - repair_io_failure(inode, start, failrec->len, - failrec->logical, page, - pg_offset, failrec->failed_mirror); + repair_io_failure(fs_info, ino, start, failrec->len, + failrec->logical, page, pg_offset, + failrec->failed_mirror); } } out: - free_io_failure(inode, failrec); + free_io_failure(failure_tree, io_tree, failrec); return 0; } @@ -2357,10 +2332,7 @@ struct bio *btrfs_create_repair_bio(struct inode *inode, struct bio *failed_bio, struct btrfs_io_bio *btrfs_failed_bio; struct btrfs_io_bio *btrfs_bio; - bio = btrfs_io_bio_alloc(GFP_NOFS, 1); - if (!bio) - return NULL; - + bio = btrfs_io_bio_alloc(1); bio->bi_end_io = endio_func; bio->bi_iter.bi_sector = failrec->logical >> 9; bio->bi_bdev = fs_info->fs_devices->latest_bdev; @@ -2398,6 +2370,7 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset, struct io_failure_record *failrec; struct inode *inode = page->mapping->host; struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree; + struct extent_io_tree *failure_tree = &BTRFS_I(inode)->io_failure_tree; struct bio *bio; int read_mode = 0; blk_status_t status; @@ -2411,7 +2384,7 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset, ret = btrfs_check_repairable(inode, failed_bio, failrec, failed_mirror); if (!ret) { - free_io_failure(BTRFS_I(inode), failrec); + free_io_failure(failure_tree, tree, failrec); return -EIO; } @@ -2424,7 +2397,7 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset, (int)phy_offset, failed_bio->bi_end_io, NULL); if (!bio) { - free_io_failure(BTRFS_I(inode), failrec); + free_io_failure(failure_tree, tree, failrec); return -EIO; } bio_set_op_attrs(bio, REQ_OP_READ, read_mode); @@ -2433,10 +2406,10 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset, "Repair Read Error: submitting new read[%#x] to this_mirror=%d, in_validation=%d", read_mode, failrec->this_mirror, failrec->in_validation); - status = tree->ops->submit_bio_hook(inode, bio, failrec->this_mirror, + status = tree->ops->submit_bio_hook(tree->private_data, bio, failrec->this_mirror, failrec->bio_flags, 0); if (status) { - free_io_failure(BTRFS_I(inode), failrec); + free_io_failure(failure_tree, tree, failrec); bio_put(bio); ret = blk_status_to_errno(status); } @@ -2542,7 +2515,7 @@ static void end_bio_extent_readpage(struct bio *bio) struct bio_vec *bvec; int uptodate = !bio->bi_status; struct btrfs_io_bio *io_bio = btrfs_io_bio(bio); - struct extent_io_tree *tree; + struct extent_io_tree *tree, *failure_tree; u64 offset = 0; u64 start; u64 end; @@ -2563,6 +2536,7 @@ static void end_bio_extent_readpage(struct bio *bio) (u64)bio->bi_iter.bi_sector, bio->bi_status, io_bio->mirror_num); tree = &BTRFS_I(inode)->io_tree; + failure_tree = &BTRFS_I(inode)->io_failure_tree; /* We always issue full-page reads, but if some block * in a page fails to read, blk_update_request() will @@ -2592,8 +2566,10 @@ static void end_bio_extent_readpage(struct bio *bio) if (ret) uptodate = 0; else - clean_io_failure(BTRFS_I(inode), start, - page, 0); + clean_io_failure(BTRFS_I(inode)->root->fs_info, + failure_tree, tree, start, + page, + btrfs_ino(BTRFS_I(inode)), 0); } if (likely(uptodate)) @@ -2682,67 +2658,70 @@ readpage_ok: } /* - * this allocates from the btrfs_bioset. We're returning a bio right now - * but you can call btrfs_io_bio for the appropriate container_of magic + * Initialize the members up to but not including 'bio'. Use after allocating a + * new bio by bio_alloc_bioset as it does not initialize the bytes outside of + * 'bio' because use of __GFP_ZERO is not supported. */ -struct bio * -btrfs_bio_alloc(struct block_device *bdev, u64 first_sector, int nr_vecs, - gfp_t gfp_flags) +static inline void btrfs_io_bio_init(struct btrfs_io_bio *btrfs_bio) { - struct btrfs_io_bio *btrfs_bio; - struct bio *bio; - - bio = bio_alloc_bioset(gfp_flags, nr_vecs, btrfs_bioset); + memset(btrfs_bio, 0, offsetof(struct btrfs_io_bio, bio)); +} - if (bio == NULL && (current->flags & PF_MEMALLOC)) { - while (!bio && (nr_vecs /= 2)) { - bio = bio_alloc_bioset(gfp_flags, - nr_vecs, btrfs_bioset); - } - } +/* + * The following helpers allocate a bio. As it's backed by a bioset, it'll + * never fail. We're returning a bio right now but you can call btrfs_io_bio + * for the appropriate container_of magic + */ +struct bio *btrfs_bio_alloc(struct block_device *bdev, u64 first_byte) +{ + struct bio *bio; - if (bio) { - bio->bi_bdev = bdev; - bio->bi_iter.bi_sector = first_sector; - btrfs_bio = btrfs_io_bio(bio); - btrfs_bio->csum = NULL; - btrfs_bio->csum_allocated = NULL; - btrfs_bio->end_io = NULL; - } + bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_PAGES, btrfs_bioset); + bio->bi_bdev = bdev; + bio->bi_iter.bi_sector = first_byte >> 9; + btrfs_io_bio_init(btrfs_io_bio(bio)); return bio; } -struct bio *btrfs_bio_clone(struct bio *bio, gfp_t gfp_mask) +struct bio *btrfs_bio_clone(struct bio *bio) { struct btrfs_io_bio *btrfs_bio; struct bio *new; - new = bio_clone_bioset(bio, gfp_mask, btrfs_bioset); - if (new) { - btrfs_bio = btrfs_io_bio(new); - btrfs_bio->csum = NULL; - btrfs_bio->csum_allocated = NULL; - btrfs_bio->end_io = NULL; - } + /* Bio allocation backed by a bioset does not fail */ + new = bio_clone_fast(bio, GFP_NOFS, btrfs_bioset); + btrfs_bio = btrfs_io_bio(new); + btrfs_io_bio_init(btrfs_bio); + btrfs_bio->iter = bio->bi_iter; return new; } -/* this also allocates from the btrfs_bioset */ -struct bio *btrfs_io_bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs) +struct bio *btrfs_io_bio_alloc(unsigned int nr_iovecs) { - struct btrfs_io_bio *btrfs_bio; struct bio *bio; - bio = bio_alloc_bioset(gfp_mask, nr_iovecs, btrfs_bioset); - if (bio) { - btrfs_bio = btrfs_io_bio(bio); - btrfs_bio->csum = NULL; - btrfs_bio->csum_allocated = NULL; - btrfs_bio->end_io = NULL; - } + /* Bio allocation backed by a bioset does not fail */ + bio = bio_alloc_bioset(GFP_NOFS, nr_iovecs, btrfs_bioset); + btrfs_io_bio_init(btrfs_io_bio(bio)); return bio; } +struct bio *btrfs_bio_clone_partial(struct bio *orig, int offset, int size) +{ + struct bio *bio; + struct btrfs_io_bio *btrfs_bio; + + /* this will never fail when it's backed by a bioset */ + bio = bio_clone_fast(orig, GFP_NOFS, btrfs_bioset); + ASSERT(bio); + + btrfs_bio = btrfs_io_bio(bio); + btrfs_io_bio_init(btrfs_bio); + + bio_trim(bio, offset >> 9, size >> 9); + btrfs_bio->iter = bio->bi_iter; + return bio; +} static int __must_check submit_one_bio(struct bio *bio, int mirror_num, unsigned long bio_flags) @@ -2759,7 +2738,7 @@ static int __must_check submit_one_bio(struct bio *bio, int mirror_num, bio_get(bio); if (tree->ops) - ret = tree->ops->submit_bio_hook(page->mapping->host, bio, + ret = tree->ops->submit_bio_hook(tree->private_data, bio, mirror_num, bio_flags, start); else btrfsic_submit_bio(bio); @@ -2822,11 +2801,7 @@ static int submit_extent_page(int op, int op_flags, struct extent_io_tree *tree, } } - bio = btrfs_bio_alloc(bdev, sector, BIO_MAX_PAGES, - GFP_NOFS | __GFP_HIGH); - if (!bio) - return -ENOMEM; - + bio = btrfs_bio_alloc(bdev, sector << 9); bio_add_page(bio, page, page_size, offset); bio->bi_end_io = end_io_func; bio->bi_private = tree; @@ -3602,9 +3577,9 @@ lock_extent_buffer_for_io(struct extent_buffer *eb, set_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags); spin_unlock(&eb->refs_lock); btrfs_set_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN); - __percpu_counter_add(&fs_info->dirty_metadata_bytes, - -eb->len, - fs_info->dirty_metadata_batch); + percpu_counter_add_batch(&fs_info->dirty_metadata_bytes, + -eb->len, + fs_info->dirty_metadata_batch); ret = 1; } else { spin_unlock(&eb->refs_lock); @@ -3762,7 +3737,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb, * header 0 1 2 .. N ... data_N .. data_2 data_1 data_0 */ start = btrfs_item_nr_offset(nritems); - end = btrfs_leaf_data(eb) + leaf_data_end(fs_info, eb); + end = BTRFS_LEAF_DATA_OFFSET + leaf_data_end(fs_info, eb); memzero_extent_buffer(eb, start, end - start); } @@ -4468,29 +4443,25 @@ try_submit_last: } /* - * Sanity check for fiemap cache + * Emit last fiemap cache * - * All fiemap cache should be submitted by emit_fiemap_extent() - * Iteration should be terminated either by last fiemap extent or - * fieinfo->fi_extents_max. - * So no cached fiemap should exist. + * The last fiemap cache may still be cached in the following case: + * 0 4k 8k + * |<- Fiemap range ->| + * |<------------ First extent ----------->| + * + * In this case, the first extent range will be cached but not emitted. + * So we must emit it before ending extent_fiemap(). */ -static int check_fiemap_cache(struct btrfs_fs_info *fs_info, - struct fiemap_extent_info *fieinfo, - struct fiemap_cache *cache) +static int emit_last_fiemap_cache(struct btrfs_fs_info *fs_info, + struct fiemap_extent_info *fieinfo, + struct fiemap_cache *cache) { int ret; if (!cache->cached) return 0; - /* Small and recoverbale problem, only to info developer */ -#ifdef CONFIG_BTRFS_DEBUG - WARN_ON(1); -#endif - btrfs_warn(fs_info, - "unhandled fiemap cache detected: offset=%llu phys=%llu len=%llu flags=0x%x", - cache->offset, cache->phys, cache->len, cache->flags); ret = fiemap_fill_next_extent(fieinfo, cache->offset, cache->phys, cache->len, cache->flags); cache->cached = false; @@ -4706,7 +4677,7 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, } out_free: if (!ret) - ret = check_fiemap_cache(root->fs_info, fieinfo, &cache); + ret = emit_last_fiemap_cache(root->fs_info, fieinfo, &cache); free_extent_map(em); out: btrfs_free_path(path); diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 487ca0207cb6..3fb8513bf02e 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -92,9 +92,9 @@ struct btrfs_inode; struct btrfs_io_bio; struct io_failure_record; -typedef blk_status_t (extent_submit_bio_hook_t)(struct inode *inode, - struct bio *bio, int mirror_num, unsigned long bio_flags, - u64 bio_offset); +typedef blk_status_t (extent_submit_bio_hook_t)(void *private_data, struct bio *bio, + int mirror_num, unsigned long bio_flags, + u64 bio_offset); struct extent_io_ops { /* * The following callbacks must be allways defined, the function @@ -108,32 +108,36 @@ struct extent_io_ops { size_t size, struct bio *bio, unsigned long bio_flags); int (*readpage_io_failed_hook)(struct page *page, int failed_mirror); + struct btrfs_fs_info *(*tree_fs_info)(void *private_data); + void (*set_range_writeback)(void *private_data, u64 start, u64 end); /* * Optional hooks, called if the pointer is not NULL */ - int (*fill_delalloc)(struct inode *inode, struct page *locked_page, + int (*fill_delalloc)(void *private_data, struct page *locked_page, u64 start, u64 end, int *page_started, unsigned long *nr_written); int (*writepage_start_hook)(struct page *page, u64 start, u64 end); void (*writepage_end_io_hook)(struct page *page, u64 start, u64 end, struct extent_state *state, int uptodate); - void (*set_bit_hook)(struct inode *inode, struct extent_state *state, + void (*set_bit_hook)(void *private_data, struct extent_state *state, unsigned *bits); - void (*clear_bit_hook)(struct btrfs_inode *inode, + void (*clear_bit_hook)(void *private_data, struct extent_state *state, unsigned *bits); - void (*merge_extent_hook)(struct inode *inode, + void (*merge_extent_hook)(void *private_data, struct extent_state *new, struct extent_state *other); - void (*split_extent_hook)(struct inode *inode, + void (*split_extent_hook)(void *private_data, struct extent_state *orig, u64 split); + void (*check_extent_io_range)(void *private_data, const char *caller, + u64 start, u64 end); }; struct extent_io_tree { struct rb_root state; - struct address_space *mapping; + void *private_data; u64 dirty_bytes; int track_uptodate; spinlock_t lock; @@ -205,12 +209,46 @@ struct extent_buffer { */ struct extent_changeset { /* How many bytes are set/cleared in this operation */ - u64 bytes_changed; + unsigned int bytes_changed; /* Changed ranges */ struct ulist range_changed; }; +static inline void extent_changeset_init(struct extent_changeset *changeset) +{ + changeset->bytes_changed = 0; + ulist_init(&changeset->range_changed); +} + +static inline struct extent_changeset *extent_changeset_alloc(void) +{ + struct extent_changeset *ret; + + ret = kmalloc(sizeof(*ret), GFP_KERNEL); + if (!ret) + return NULL; + + extent_changeset_init(ret); + return ret; +} + +static inline void extent_changeset_release(struct extent_changeset *changeset) +{ + if (!changeset) + return; + changeset->bytes_changed = 0; + ulist_release(&changeset->range_changed); +} + +static inline void extent_changeset_free(struct extent_changeset *changeset) +{ + if (!changeset) + return; + extent_changeset_release(changeset); + kfree(changeset); +} + static inline void extent_set_compress_type(unsigned long *bio_flags, int compress_type) { @@ -230,8 +268,7 @@ typedef struct extent_map *(get_extent_t)(struct btrfs_inode *inode, u64 start, u64 len, int create); -void extent_io_tree_init(struct extent_io_tree *tree, - struct address_space *mapping); +void extent_io_tree_init(struct extent_io_tree *tree, void *private_data); int try_release_extent_mapping(struct extent_map_tree *map, struct extent_io_tree *tree, struct page *page, gfp_t mask); @@ -459,20 +496,21 @@ void extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end, u64 delalloc_end, struct page *locked_page, unsigned bits_to_clear, unsigned long page_ops); -struct bio * -btrfs_bio_alloc(struct block_device *bdev, u64 first_sector, int nr_vecs, - gfp_t gfp_flags); -struct bio *btrfs_io_bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs); -struct bio *btrfs_bio_clone(struct bio *bio, gfp_t gfp_mask); +struct bio *btrfs_bio_alloc(struct block_device *bdev, u64 first_byte); +struct bio *btrfs_io_bio_alloc(unsigned int nr_iovecs); +struct bio *btrfs_bio_clone(struct bio *bio); +struct bio *btrfs_bio_clone_partial(struct bio *orig, int offset, int size); struct btrfs_fs_info; struct btrfs_inode; -int repair_io_failure(struct btrfs_inode *inode, u64 start, u64 length, - u64 logical, struct page *page, - unsigned int pg_offset, int mirror_num); -int clean_io_failure(struct btrfs_inode *inode, u64 start, - struct page *page, unsigned int pg_offset); +int repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start, + u64 length, u64 logical, struct page *page, + unsigned int pg_offset, int mirror_num); +int clean_io_failure(struct btrfs_fs_info *fs_info, + struct extent_io_tree *failure_tree, + struct extent_io_tree *io_tree, u64 start, + struct page *page, u64 ino, unsigned int pg_offset); void end_extent_writepage(struct page *page, int err, u64 start, u64 end); int repair_eb_io_failure(struct btrfs_fs_info *fs_info, struct extent_buffer *eb, int mirror_num); @@ -507,7 +545,9 @@ struct bio *btrfs_create_repair_bio(struct inode *inode, struct bio *failed_bio, struct io_failure_record *failrec, struct page *page, int pg_offset, int icsum, bio_end_io_t *endio_func, void *data); -int free_io_failure(struct btrfs_inode *inode, struct io_failure_record *rec); +int free_io_failure(struct extent_io_tree *failure_tree, + struct extent_io_tree *io_tree, + struct io_failure_record *rec); #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS noinline u64 find_lock_delalloc_range(struct inode *inode, struct extent_io_tree *tree, diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index 5b1c7090e546..fdcb41002623 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -164,7 +164,8 @@ static blk_status_t __btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio u64 logical_offset, u32 *dst, int dio) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct bio_vec *bvec; + struct bio_vec bvec; + struct bvec_iter iter; struct btrfs_io_bio *btrfs_bio = btrfs_io_bio(bio); struct btrfs_csum_item *item = NULL; struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; @@ -177,7 +178,7 @@ static blk_status_t __btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio u64 page_bytes_left; u32 diff; int nblocks; - int count = 0, i; + int count = 0; u16 csum_size = btrfs_super_csum_size(fs_info->super_copy); path = btrfs_alloc_path(); @@ -206,8 +207,6 @@ static blk_status_t __btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio if (bio->bi_iter.bi_size > PAGE_SIZE * 8) path->reada = READA_FORWARD; - WARN_ON(bio->bi_vcnt <= 0); - /* * the free space stuff is only read when it hasn't been * updated in the current transaction. So, we can safely @@ -223,13 +222,13 @@ static blk_status_t __btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio if (dio) offset = logical_offset; - bio_for_each_segment_all(bvec, bio, i) { - page_bytes_left = bvec->bv_len; + bio_for_each_segment(bvec, bio, iter) { + page_bytes_left = bvec.bv_len; if (count) goto next; if (!dio) - offset = page_offset(bvec->bv_page) + bvec->bv_offset; + offset = page_offset(bvec.bv_page) + bvec.bv_offset; count = btrfs_find_ordered_sum(inode, offset, disk_bytenr, (u32 *)csum, nblocks); if (count) @@ -440,15 +439,15 @@ blk_status_t btrfs_csum_one_bio(struct inode *inode, struct bio *bio, struct btrfs_ordered_sum *sums; struct btrfs_ordered_extent *ordered = NULL; char *data; - struct bio_vec *bvec; + struct bvec_iter iter; + struct bio_vec bvec; int index; int nr_sectors; - int i, j; unsigned long total_bytes = 0; unsigned long this_sum_bytes = 0; + int i; u64 offset; - WARN_ON(bio->bi_vcnt <= 0); sums = kzalloc(btrfs_ordered_sum_size(fs_info, bio->bi_iter.bi_size), GFP_NOFS); if (!sums) @@ -465,19 +464,19 @@ blk_status_t btrfs_csum_one_bio(struct inode *inode, struct bio *bio, sums->bytenr = (u64)bio->bi_iter.bi_sector << 9; index = 0; - bio_for_each_segment_all(bvec, bio, j) { + bio_for_each_segment(bvec, bio, iter) { if (!contig) - offset = page_offset(bvec->bv_page) + bvec->bv_offset; + offset = page_offset(bvec.bv_page) + bvec.bv_offset; if (!ordered) { ordered = btrfs_lookup_ordered_extent(inode, offset); BUG_ON(!ordered); /* Logic error */ } - data = kmap_atomic(bvec->bv_page); + data = kmap_atomic(bvec.bv_page); nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, - bvec->bv_len + fs_info->sectorsize + bvec.bv_len + fs_info->sectorsize - 1); for (i = 0; i < nr_sectors; i++) { @@ -504,12 +503,12 @@ blk_status_t btrfs_csum_one_bio(struct inode *inode, struct bio *bio, + total_bytes; index = 0; - data = kmap_atomic(bvec->bv_page); + data = kmap_atomic(bvec.bv_page); } sums->sums[index] = ~(u32)0; sums->sums[index] - = btrfs_csum_data(data + bvec->bv_offset + = btrfs_csum_data(data + bvec.bv_offset + (i * fs_info->sectorsize), sums->sums[index], fs_info->sectorsize); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 59e2dccdf75b..a85d7903fbdd 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1581,6 +1581,7 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file, struct btrfs_root *root = BTRFS_I(inode)->root; struct page **pages = NULL; struct extent_state *cached_state = NULL; + struct extent_changeset *data_reserved = NULL; u64 release_bytes = 0; u64 lockstart; u64 lockend; @@ -1628,7 +1629,9 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file, reserve_bytes = round_up(write_bytes + sector_offset, fs_info->sectorsize); - ret = btrfs_check_data_free_space(inode, pos, write_bytes); + extent_changeset_release(data_reserved); + ret = btrfs_check_data_free_space(inode, &data_reserved, pos, + write_bytes); if (ret < 0) { if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | BTRFS_INODE_PREALLOC)) && @@ -1657,8 +1660,9 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file, reserve_bytes); if (ret) { if (!only_release_metadata) - btrfs_free_reserved_data_space(inode, pos, - write_bytes); + btrfs_free_reserved_data_space(inode, + data_reserved, pos, + write_bytes); else btrfs_end_write_no_snapshoting(root); break; @@ -1740,8 +1744,9 @@ again: __pos = round_down(pos, fs_info->sectorsize) + (dirty_pages << PAGE_SHIFT); - btrfs_delalloc_release_space(inode, __pos, - release_bytes); + btrfs_delalloc_release_space(inode, + data_reserved, __pos, + release_bytes); } } @@ -1796,12 +1801,13 @@ again: btrfs_delalloc_release_metadata(BTRFS_I(inode), release_bytes); } else { - btrfs_delalloc_release_space(inode, - round_down(pos, fs_info->sectorsize), - release_bytes); + btrfs_delalloc_release_space(inode, data_reserved, + round_down(pos, fs_info->sectorsize), + release_bytes); } } + extent_changeset_free(data_reserved); return num_written ? num_written : ret; } @@ -2026,7 +2032,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_trans_handle *trans; struct btrfs_log_ctx ctx; - int ret = 0; + int ret = 0, err; bool full_sync = 0; u64 len; @@ -2045,7 +2051,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) */ ret = start_ordered_ops(inode, start, end); if (ret) - return ret; + goto out; inode_lock(inode); atomic_inc(&root->log_batch); @@ -2150,10 +2156,10 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) * An ordered extent might have started before and completed * already with io errors, in which case the inode was not * updated and we end up here. So check the inode's mapping - * flags for any errors that might have happened while doing - * writeback of file data. + * for any errors that might have happened since we last + * checked called fsync. */ - ret = filemap_check_errors(inode->i_mapping); + ret = filemap_check_wb_err(inode->i_mapping, file->f_wb_err); inode_unlock(inode); goto out; } @@ -2242,6 +2248,9 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) ret = btrfs_end_transaction(trans); } out: + err = file_check_and_advance_wb_err(file); + if (!ret) + ret = err; return ret > 0 ? -EIO : ret; } @@ -2405,10 +2414,13 @@ out: */ static int find_first_non_hole(struct inode *inode, u64 *start, u64 *len) { + struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct extent_map *em; int ret = 0; - em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, *start, *len, 0); + em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, + round_down(*start, fs_info->sectorsize), + round_up(*len, fs_info->sectorsize), 0); if (IS_ERR(em)) return PTR_ERR(em); @@ -2784,6 +2796,7 @@ static long btrfs_fallocate(struct file *file, int mode, { struct inode *inode = file_inode(file); struct extent_state *cached_state = NULL; + struct extent_changeset *data_reserved = NULL; struct falloc_range *range; struct falloc_range *tmp; struct list_head reserve_list; @@ -2913,8 +2926,8 @@ static long btrfs_fallocate(struct file *file, int mode, free_extent_map(em); break; } - ret = btrfs_qgroup_reserve_data(inode, cur_offset, - last_byte - cur_offset); + ret = btrfs_qgroup_reserve_data(inode, &data_reserved, + cur_offset, last_byte - cur_offset); if (ret < 0) { free_extent_map(em); break; @@ -2925,8 +2938,8 @@ static long btrfs_fallocate(struct file *file, int mode, * range, free reserved data space first, otherwise * it'll result in false ENOSPC error. */ - btrfs_free_reserved_data_space(inode, cur_offset, - last_byte - cur_offset); + btrfs_free_reserved_data_space(inode, data_reserved, + cur_offset, last_byte - cur_offset); } free_extent_map(em); cur_offset = last_byte; @@ -2945,8 +2958,9 @@ static long btrfs_fallocate(struct file *file, int mode, range->len, i_blocksize(inode), offset + len, &alloc_hint); else - btrfs_free_reserved_data_space(inode, range->start, - range->len); + btrfs_free_reserved_data_space(inode, + data_reserved, range->start, + range->len); list_del(&range->list); kfree(range); } @@ -2984,8 +2998,9 @@ out: inode_unlock(inode); /* Let go of our reservation. */ if (ret != 0) - btrfs_free_reserved_data_space(inode, alloc_start, - alloc_end - cur_offset); + btrfs_free_reserved_data_space(inode, data_reserved, + alloc_start, alloc_end - cur_offset); + extent_changeset_free(data_reserved); return ret; } diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c index fc0bd8406758..a5e34de06c2f 100644 --- a/fs/btrfs/free-space-tree.c +++ b/fs/btrfs/free-space-tree.c @@ -17,7 +17,7 @@ */ #include <linux/kernel.h> -#include <linux/vmalloc.h> +#include <linux/sched/mm.h> #include "ctree.h" #include "disk-io.h" #include "locking.h" @@ -153,21 +153,21 @@ static inline u32 free_space_bitmap_size(u64 size, u32 sectorsize) static u8 *alloc_bitmap(u32 bitmap_size) { - void *mem; + u8 *ret; + unsigned int nofs_flag; /* - * The allocation size varies, observed numbers were < 4K up to 16K. - * Using vmalloc unconditionally would be too heavy, we'll try - * contiguous allocations first. + * GFP_NOFS doesn't work with kvmalloc(), but we really can't recurse + * into the filesystem as the free space bitmap can be modified in the + * critical section of a transaction commit. + * + * TODO: push the memalloc_nofs_{save,restore}() to the caller where we + * know that recursion is unsafe. */ - if (bitmap_size <= PAGE_SIZE) - return kzalloc(bitmap_size, GFP_NOFS); - - mem = kzalloc(bitmap_size, GFP_NOFS | __GFP_NOWARN); - if (mem) - return mem; - - return __vmalloc(bitmap_size, GFP_NOFS | __GFP_ZERO, PAGE_KERNEL); + nofs_flag = memalloc_nofs_save(); + ret = kvzalloc(bitmap_size, GFP_KERNEL); + memalloc_nofs_restore(nofs_flag); + return ret; } int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans, @@ -1188,11 +1188,7 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info) btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID); clear_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags); - ret = btrfs_commit_transaction(trans); - if (ret) - return ret; - - return 0; + return btrfs_commit_transaction(trans); abort: clear_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags); @@ -1277,11 +1273,7 @@ int btrfs_clear_free_space_tree(struct btrfs_fs_info *fs_info) free_extent_buffer(free_space_root->commit_root); kfree(free_space_root); - ret = btrfs_commit_transaction(trans); - if (ret) - return ret; - - return 0; + return btrfs_commit_transaction(trans); abort: btrfs_abort_transaction(trans, ret); diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c index 5c6c20ec64d8..d02019747d00 100644 --- a/fs/btrfs/inode-map.c +++ b/fs/btrfs/inode-map.c @@ -400,6 +400,7 @@ int btrfs_save_ino_cache(struct btrfs_root *root, struct btrfs_path *path; struct inode *inode; struct btrfs_block_rsv *rsv; + struct extent_changeset *data_reserved = NULL; u64 num_bytes; u64 alloc_hint = 0; int ret; @@ -492,7 +493,7 @@ again: /* Just to make sure we have enough space */ prealloc += 8 * PAGE_SIZE; - ret = btrfs_delalloc_reserve_space(inode, 0, prealloc); + ret = btrfs_delalloc_reserve_space(inode, &data_reserved, 0, prealloc); if (ret) goto out_put; @@ -516,6 +517,7 @@ out: trans->bytes_reserved = num_bytes; btrfs_free_path(path); + extent_changeset_free(data_reserved); return ret; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 556c93060606..06dea7c89bbd 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -86,7 +86,6 @@ static const struct extent_io_ops btrfs_extent_io_ops; static struct kmem_cache *btrfs_inode_cachep; struct kmem_cache *btrfs_trans_handle_cachep; -struct kmem_cache *btrfs_transaction_cachep; struct kmem_cache *btrfs_path_cachep; struct kmem_cache *btrfs_free_space_cachep; @@ -178,7 +177,6 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans, char *kaddr; unsigned long ptr; struct btrfs_file_extent_item *ei; - int err = 0; int ret; size_t cur_size = size; unsigned long offset; @@ -200,10 +198,8 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans, path->leave_spinning = 1; ret = btrfs_insert_empty_item(trans, root, path, &key, datasize); - if (ret) { - err = ret; + if (ret) goto fail; - } } leaf = path->nodes[0]; ei = btrfs_item_ptr(leaf, path->slots[0], @@ -258,9 +254,8 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans, BTRFS_I(inode)->disk_i_size = inode->i_size; ret = btrfs_update_inode(trans, root, inode); - return ret; fail: - return err; + return ret; } @@ -350,7 +345,7 @@ out: * And at reserve time, it's always aligned to page size, so * just free one page here. */ - btrfs_qgroup_free_data(inode, 0, PAGE_SIZE); + btrfs_qgroup_free_data(inode, NULL, 0, PAGE_SIZE); btrfs_free_path(path); btrfs_end_transaction(trans); return ret; @@ -608,12 +603,11 @@ cont: /* * one last check to make sure the compression is really a - * win, compare the page count read with the blocks on disk + * win, compare the page count read with the blocks on disk, + * compression must free at least one sector size */ total_in = ALIGN(total_in, PAGE_SIZE); - if (total_compressed >= total_in) { - will_compress = 0; - } else { + if (total_compressed + blocksize <= total_in) { num_bytes = total_in; *num_added += 1; @@ -1568,10 +1562,11 @@ static inline int need_force_cow(struct inode *inode, u64 start, u64 end) /* * extent_io.c call back to do delayed allocation processing */ -static int run_delalloc_range(struct inode *inode, struct page *locked_page, +static int run_delalloc_range(void *private_data, struct page *locked_page, u64 start, u64 end, int *page_started, unsigned long *nr_written) { + struct inode *inode = private_data; int ret; int force_cow = need_force_cow(inode, start, end); @@ -1595,9 +1590,10 @@ static int run_delalloc_range(struct inode *inode, struct page *locked_page, return ret; } -static void btrfs_split_extent_hook(struct inode *inode, +static void btrfs_split_extent_hook(void *private_data, struct extent_state *orig, u64 split) { + struct inode *inode = private_data; u64 size; /* not delalloc, ignore it */ @@ -1632,10 +1628,11 @@ static void btrfs_split_extent_hook(struct inode *inode, * extents, such as when we are doing sequential writes, so we can properly * account for the metadata space we'll need. */ -static void btrfs_merge_extent_hook(struct inode *inode, +static void btrfs_merge_extent_hook(void *private_data, struct extent_state *new, struct extent_state *other) { + struct inode *inode = private_data; u64 new_size, old_size; u32 num_extents; @@ -1735,9 +1732,10 @@ static void btrfs_del_delalloc_inode(struct btrfs_root *root, * bytes in this file, and to maintain the list of inodes that * have pending delalloc work to be done. */ -static void btrfs_set_bit_hook(struct inode *inode, +static void btrfs_set_bit_hook(void *private_data, struct extent_state *state, unsigned *bits) { + struct inode *inode = private_data; struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); @@ -1765,8 +1763,8 @@ static void btrfs_set_bit_hook(struct inode *inode, if (btrfs_is_testing(fs_info)) return; - __percpu_counter_add(&fs_info->delalloc_bytes, len, - fs_info->delalloc_batch); + percpu_counter_add_batch(&fs_info->delalloc_bytes, len, + fs_info->delalloc_batch); spin_lock(&BTRFS_I(inode)->lock); BTRFS_I(inode)->delalloc_bytes += len; if (*bits & EXTENT_DEFRAG) @@ -1789,10 +1787,11 @@ static void btrfs_set_bit_hook(struct inode *inode, /* * extent_io.c clear_bit_hook, see set_bit_hook for why */ -static void btrfs_clear_bit_hook(struct btrfs_inode *inode, +static void btrfs_clear_bit_hook(void *private_data, struct extent_state *state, unsigned *bits) { + struct btrfs_inode *inode = BTRFS_I((struct inode *)private_data); struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb); u64 len = state->end + 1 - state->start; u32 num_extents = count_max_extents(len); @@ -1839,8 +1838,8 @@ static void btrfs_clear_bit_hook(struct btrfs_inode *inode, &inode->vfs_inode, state->start, len); - __percpu_counter_add(&fs_info->delalloc_bytes, -len, - fs_info->delalloc_batch); + percpu_counter_add_batch(&fs_info->delalloc_bytes, -len, + fs_info->delalloc_batch); spin_lock(&inode->lock); inode->delalloc_bytes -= len; if (do_list && inode->delalloc_bytes == 0 && @@ -1900,10 +1899,11 @@ int btrfs_merge_bio_hook(struct page *page, unsigned long offset, * At IO completion time the cums attached on the ordered extent record * are inserted into the btree */ -static blk_status_t __btrfs_submit_bio_start(struct inode *inode, - struct bio *bio, int mirror_num, unsigned long bio_flags, - u64 bio_offset) +static blk_status_t __btrfs_submit_bio_start(void *private_data, struct bio *bio, + int mirror_num, unsigned long bio_flags, + u64 bio_offset) { + struct inode *inode = private_data; blk_status_t ret = 0; ret = btrfs_csum_one_bio(inode, bio, 0, 0); @@ -1919,10 +1919,11 @@ static blk_status_t __btrfs_submit_bio_start(struct inode *inode, * At IO completion time the cums attached on the ordered extent record * are inserted into the btree */ -static blk_status_t __btrfs_submit_bio_done(struct inode *inode, - struct bio *bio, int mirror_num, unsigned long bio_flags, - u64 bio_offset) +static blk_status_t __btrfs_submit_bio_done(void *private_data, struct bio *bio, + int mirror_num, unsigned long bio_flags, + u64 bio_offset) { + struct inode *inode = private_data; struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); blk_status_t ret; @@ -1938,10 +1939,11 @@ static blk_status_t __btrfs_submit_bio_done(struct inode *inode, * extent_io.c submission hook. This does the right thing for csum calculation * on write, or reading the csums from the tree before a read */ -static blk_status_t btrfs_submit_bio_hook(struct inode *inode, struct bio *bio, - int mirror_num, unsigned long bio_flags, - u64 bio_offset) +static blk_status_t btrfs_submit_bio_hook(void *private_data, struct bio *bio, + int mirror_num, unsigned long bio_flags, + u64 bio_offset) { + struct inode *inode = private_data; struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_root *root = BTRFS_I(inode)->root; enum btrfs_wq_endio_type metadata = BTRFS_WQ_ENDIO_DATA; @@ -1975,8 +1977,8 @@ static blk_status_t btrfs_submit_bio_hook(struct inode *inode, struct bio *bio, if (root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID) goto mapit; /* we're doing a write, do the async checksumming */ - ret = btrfs_wq_submit_bio(fs_info, inode, bio, mirror_num, - bio_flags, bio_offset, + ret = btrfs_wq_submit_bio(fs_info, bio, mirror_num, bio_flags, + bio_offset, inode, __btrfs_submit_bio_start, __btrfs_submit_bio_done); goto out; @@ -2034,6 +2036,7 @@ static void btrfs_writepage_fixup_worker(struct btrfs_work *work) struct btrfs_writepage_fixup *fixup; struct btrfs_ordered_extent *ordered; struct extent_state *cached_state = NULL; + struct extent_changeset *data_reserved = NULL; struct page *page; struct inode *inode; u64 page_start; @@ -2071,7 +2074,7 @@ again: goto again; } - ret = btrfs_delalloc_reserve_space(inode, page_start, + ret = btrfs_delalloc_reserve_space(inode, &data_reserved, page_start, PAGE_SIZE); if (ret) { mapping_set_error(page->mapping, ret); @@ -2091,6 +2094,7 @@ out_page: unlock_page(page); put_page(page); kfree(fixup); + extent_changeset_free(data_reserved); } /* @@ -2142,6 +2146,7 @@ static int insert_reserved_file_extent(struct btrfs_trans_handle *trans, struct btrfs_path *path; struct extent_buffer *leaf; struct btrfs_key ins; + u64 qg_released; int extent_inserted = 0; int ret; @@ -2197,13 +2202,17 @@ static int insert_reserved_file_extent(struct btrfs_trans_handle *trans, ins.objectid = disk_bytenr; ins.offset = disk_num_bytes; ins.type = BTRFS_EXTENT_ITEM_KEY; - ret = btrfs_alloc_reserved_file_extent(trans, root->root_key.objectid, - btrfs_ino(BTRFS_I(inode)), file_pos, ram_bytes, &ins); + /* * Release the reserved range from inode dirty range map, as it is * already moved into delayed_ref_head */ - btrfs_qgroup_release_data(inode, file_pos, ram_bytes); + ret = btrfs_qgroup_release_data(inode, file_pos, ram_bytes); + if (ret < 0) + goto out; + qg_released = ret; + ret = btrfs_alloc_reserved_file_extent(trans, root->root_key.objectid, + btrfs_ino(BTRFS_I(inode)), file_pos, qg_released, &ins); out: btrfs_free_path(path); @@ -2925,7 +2934,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) * space for NOCOW range. * As NOCOW won't cause a new delayed ref, just free the space */ - btrfs_qgroup_free_data(inode, ordered_extent->file_offset, + btrfs_qgroup_free_data(inode, NULL, ordered_extent->file_offset, ordered_extent->len); btrfs_ordered_update_i_size(inode, 0, ordered_extent); if (nolock) @@ -4761,6 +4770,7 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len, struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; struct btrfs_ordered_extent *ordered; struct extent_state *cached_state = NULL; + struct extent_changeset *data_reserved = NULL; char *kaddr; u32 blocksize = fs_info->sectorsize; pgoff_t index = from >> PAGE_SHIFT; @@ -4775,7 +4785,7 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len, (!len || ((len & (blocksize - 1)) == 0))) goto out; - ret = btrfs_delalloc_reserve_space(inode, + ret = btrfs_delalloc_reserve_space(inode, &data_reserved, round_down(from, blocksize), blocksize); if (ret) goto out; @@ -4783,7 +4793,7 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len, again: page = find_or_create_page(mapping, index, mask); if (!page) { - btrfs_delalloc_release_space(inode, + btrfs_delalloc_release_space(inode, data_reserved, round_down(from, blocksize), blocksize); ret = -ENOMEM; @@ -4855,11 +4865,12 @@ again: out_unlock: if (ret) - btrfs_delalloc_release_space(inode, block_start, + btrfs_delalloc_release_space(inode, data_reserved, block_start, blocksize); unlock_page(page); put_page(page); out: + extent_changeset_free(data_reserved); return ret; } @@ -5254,7 +5265,7 @@ static void evict_inode_truncate_pages(struct inode *inode) * Note, end is the bytenr of last byte, so we need + 1 here. */ if (state->state & EXTENT_DELALLOC) - btrfs_qgroup_free_data(inode, start, end - start + 1); + btrfs_qgroup_free_data(inode, NULL, start, end - start + 1); clear_extent_bit(io_tree, start, end, EXTENT_LOCKED | EXTENT_DIRTY | @@ -5867,7 +5878,6 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx) struct inode *inode = file_inode(file); struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_root *root = BTRFS_I(inode)->root; - struct btrfs_item *item; struct btrfs_dir_item *di; struct btrfs_key key; struct btrfs_key found_key; @@ -5918,7 +5928,6 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx) continue; } - item = btrfs_item_nr(slot); btrfs_item_key_to_cpu(leaf, &found_key, slot); if (found_key.objectid != key.objectid) @@ -5933,7 +5942,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx) ctx->pos = found_key.offset; di = btrfs_item_ptr(leaf, slot, struct btrfs_dir_item); - if (verify_dir_item(fs_info, leaf, di)) + if (verify_dir_item(fs_info, leaf, slot, di)) goto next; name_len = btrfs_dir_name_len(leaf, di); @@ -7479,7 +7488,7 @@ out: bool btrfs_page_exists_in_range(struct inode *inode, loff_t start, loff_t end) { struct radix_tree_root *root = &inode->i_mapping->page_tree; - int found = false; + bool found = false; void **pagep = NULL; struct page *page = NULL; unsigned long start_idx; @@ -7977,9 +7986,12 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio, bio_end_io_t *repair_endio, void *repair_arg) { struct io_failure_record *failrec; + struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; + struct extent_io_tree *failure_tree = &BTRFS_I(inode)->io_failure_tree; struct bio *bio; int isector; int read_mode = 0; + int segs; int ret; BUG_ON(bio_op(failed_bio) == REQ_OP_WRITE); @@ -7991,13 +8003,13 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio, ret = btrfs_check_dio_repairable(inode, failed_bio, failrec, failed_mirror); if (!ret) { - free_io_failure(BTRFS_I(inode), failrec); + free_io_failure(failure_tree, io_tree, failrec); return -EIO; } - if ((failed_bio->bi_vcnt > 1) - || (failed_bio->bi_io_vec->bv_len - > btrfs_inode_sectorsize(inode))) + segs = bio_segments(failed_bio); + if (segs > 1 || + (failed_bio->bi_io_vec->bv_len > btrfs_inode_sectorsize(inode))) read_mode |= REQ_FAILFAST_DEV; isector = start - btrfs_io_bio(failed_bio)->logical; @@ -8005,7 +8017,7 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio, bio = btrfs_create_repair_bio(inode, failed_bio, failrec, page, pgoff, isector, repair_endio, repair_arg); if (!bio) { - free_io_failure(BTRFS_I(inode), failrec); + free_io_failure(failure_tree, io_tree, failrec); return -EIO; } bio_set_op_attrs(bio, REQ_OP_READ, read_mode); @@ -8016,7 +8028,7 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio, ret = submit_dio_repair_bio(inode, bio, failrec->this_mirror); if (ret) { - free_io_failure(BTRFS_I(inode), failrec); + free_io_failure(failure_tree, io_tree, failrec); bio_put(bio); } @@ -8033,19 +8045,24 @@ struct btrfs_retry_complete { static void btrfs_retry_endio_nocsum(struct bio *bio) { struct btrfs_retry_complete *done = bio->bi_private; + struct inode *inode = done->inode; struct bio_vec *bvec; + struct extent_io_tree *io_tree, *failure_tree; int i; if (bio->bi_status) goto end; ASSERT(bio->bi_vcnt == 1); - ASSERT(bio->bi_io_vec->bv_len == btrfs_inode_sectorsize(done->inode)); + io_tree = &BTRFS_I(inode)->io_tree; + failure_tree = &BTRFS_I(inode)->io_failure_tree; + ASSERT(bio->bi_io_vec->bv_len == btrfs_inode_sectorsize(inode)); done->uptodate = 1; bio_for_each_segment_all(bvec, bio, i) - clean_io_failure(BTRFS_I(done->inode), done->start, - bvec->bv_page, 0); + clean_io_failure(BTRFS_I(inode)->root->fs_info, failure_tree, + io_tree, done->start, bvec->bv_page, + btrfs_ino(BTRFS_I(inode)), 0); end: complete(&done->done); bio_put(bio); @@ -8055,36 +8072,40 @@ static int __btrfs_correct_data_nocsum(struct inode *inode, struct btrfs_io_bio *io_bio) { struct btrfs_fs_info *fs_info; - struct bio_vec *bvec; + struct bio_vec bvec; + struct bvec_iter iter; struct btrfs_retry_complete done; u64 start; unsigned int pgoff; u32 sectorsize; int nr_sectors; - int i; int ret; + int err = 0; fs_info = BTRFS_I(inode)->root->fs_info; sectorsize = fs_info->sectorsize; start = io_bio->logical; done.inode = inode; + io_bio->bio.bi_iter = io_bio->iter; - bio_for_each_segment_all(bvec, &io_bio->bio, i) { - nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec->bv_len); - pgoff = bvec->bv_offset; + bio_for_each_segment(bvec, &io_bio->bio, iter) { + nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec.bv_len); + pgoff = bvec.bv_offset; next_block_or_try_again: done.uptodate = 0; done.start = start; init_completion(&done.done); - ret = dio_read_error(inode, &io_bio->bio, bvec->bv_page, + ret = dio_read_error(inode, &io_bio->bio, bvec.bv_page, pgoff, start, start + sectorsize - 1, io_bio->mirror_num, btrfs_retry_endio_nocsum, &done); - if (ret) - return ret; + if (ret) { + err = ret; + goto next; + } wait_for_completion(&done.done); @@ -8093,6 +8114,7 @@ next_block_or_try_again: goto next_block_or_try_again; } +next: start += sectorsize; nr_sectors--; @@ -8103,13 +8125,15 @@ next_block_or_try_again: } } - return 0; + return err; } static void btrfs_retry_endio(struct bio *bio) { struct btrfs_retry_complete *done = bio->bi_private; struct btrfs_io_bio *io_bio = btrfs_io_bio(bio); + struct extent_io_tree *io_tree, *failure_tree; + struct inode *inode = done->inode; struct bio_vec *bvec; int uptodate; int ret; @@ -8123,13 +8147,19 @@ static void btrfs_retry_endio(struct bio *bio) ASSERT(bio->bi_vcnt == 1); ASSERT(bio->bi_io_vec->bv_len == btrfs_inode_sectorsize(done->inode)); + io_tree = &BTRFS_I(inode)->io_tree; + failure_tree = &BTRFS_I(inode)->io_failure_tree; + bio_for_each_segment_all(bvec, bio, i) { - ret = __readpage_endio_check(done->inode, io_bio, i, - bvec->bv_page, bvec->bv_offset, - done->start, bvec->bv_len); + ret = __readpage_endio_check(inode, io_bio, i, bvec->bv_page, + bvec->bv_offset, done->start, + bvec->bv_len); if (!ret) - clean_io_failure(BTRFS_I(done->inode), done->start, - bvec->bv_page, bvec->bv_offset); + clean_io_failure(BTRFS_I(inode)->root->fs_info, + failure_tree, io_tree, done->start, + bvec->bv_page, + btrfs_ino(BTRFS_I(inode)), + bvec->bv_offset); else uptodate = 0; } @@ -8144,7 +8174,8 @@ static blk_status_t __btrfs_subio_endio_read(struct inode *inode, struct btrfs_io_bio *io_bio, blk_status_t err) { struct btrfs_fs_info *fs_info; - struct bio_vec *bvec; + struct bio_vec bvec; + struct bvec_iter iter; struct btrfs_retry_complete done; u64 start; u64 offset = 0; @@ -8152,7 +8183,7 @@ static blk_status_t __btrfs_subio_endio_read(struct inode *inode, int nr_sectors; unsigned int pgoff; int csum_pos; - int i; + bool uptodate = (err == 0); int ret; fs_info = BTRFS_I(inode)->root->fs_info; @@ -8161,24 +8192,26 @@ static blk_status_t __btrfs_subio_endio_read(struct inode *inode, err = 0; start = io_bio->logical; done.inode = inode; + io_bio->bio.bi_iter = io_bio->iter; - bio_for_each_segment_all(bvec, &io_bio->bio, i) { - nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec->bv_len); + bio_for_each_segment(bvec, &io_bio->bio, iter) { + nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec.bv_len); - pgoff = bvec->bv_offset; + pgoff = bvec.bv_offset; next_block: - csum_pos = BTRFS_BYTES_TO_BLKS(fs_info, offset); - ret = __readpage_endio_check(inode, io_bio, csum_pos, - bvec->bv_page, pgoff, start, - sectorsize); - if (likely(!ret)) - goto next; + if (uptodate) { + csum_pos = BTRFS_BYTES_TO_BLKS(fs_info, offset); + ret = __readpage_endio_check(inode, io_bio, csum_pos, + bvec.bv_page, pgoff, start, sectorsize); + if (likely(!ret)) + goto next; + } try_again: done.uptodate = 0; done.start = start; init_completion(&done.done); - ret = dio_read_error(inode, &io_bio->bio, bvec->bv_page, + ret = dio_read_error(inode, &io_bio->bio, bvec.bv_page, pgoff, start, start + sectorsize - 1, io_bio->mirror_num, btrfs_retry_endio, &done); @@ -8233,8 +8266,11 @@ static void btrfs_endio_direct_read(struct bio *bio) struct btrfs_io_bio *io_bio = btrfs_io_bio(bio); blk_status_t err = bio->bi_status; - if (dip->flags & BTRFS_DIO_ORIG_BIO_SUBMITTED) + if (dip->flags & BTRFS_DIO_ORIG_BIO_SUBMITTED) { err = btrfs_subio_endio_read(inode, io_bio, err); + if (!err) + bio->bi_status = 0; + } unlock_extent(&BTRFS_I(inode)->io_tree, dip->logical_offset, dip->logical_offset + dip->bytes - 1); @@ -8307,10 +8343,11 @@ static void btrfs_endio_direct_write(struct bio *bio) bio_put(bio); } -static blk_status_t __btrfs_submit_bio_start_direct_io(struct inode *inode, +static blk_status_t __btrfs_submit_bio_start_direct_io(void *private_data, struct bio *bio, int mirror_num, unsigned long bio_flags, u64 offset) { + struct inode *inode = private_data; blk_status_t ret; ret = btrfs_csum_one_bio(inode, bio, offset, 1); BUG_ON(ret); /* -ENOMEM */ @@ -8357,16 +8394,6 @@ out: bio_put(bio); } -static struct bio *btrfs_dio_bio_alloc(struct block_device *bdev, - u64 first_sector, gfp_t gfp_flags) -{ - struct bio *bio; - bio = btrfs_bio_alloc(bdev, first_sector, BIO_MAX_PAGES, gfp_flags); - if (bio) - bio_associate_current(bio); - return bio; -} - static inline blk_status_t btrfs_lookup_and_bind_dio_csum(struct inode *inode, struct btrfs_dio_private *dip, struct bio *bio, @@ -8422,8 +8449,8 @@ static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode, goto map; if (write && async_submit) { - ret = btrfs_wq_submit_bio(fs_info, inode, bio, 0, 0, - file_offset, + ret = btrfs_wq_submit_bio(fs_info, bio, 0, 0, + file_offset, inode, __btrfs_submit_bio_start_direct_io, __btrfs_submit_bio_done); goto err; @@ -8453,103 +8480,83 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip, { struct inode *inode = dip->inode; struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct btrfs_root *root = BTRFS_I(inode)->root; struct bio *bio; struct bio *orig_bio = dip->orig_bio; - struct bio_vec *bvec; u64 start_sector = orig_bio->bi_iter.bi_sector; u64 file_offset = dip->logical_offset; - u64 submit_len = 0; u64 map_length; - u32 blocksize = fs_info->sectorsize; int async_submit = 0; - int nr_sectors; + u64 submit_len; + int clone_offset = 0; + int clone_len; int ret; - int i, j; map_length = orig_bio->bi_iter.bi_size; + submit_len = map_length; ret = btrfs_map_block(fs_info, btrfs_op(orig_bio), start_sector << 9, &map_length, NULL, 0); if (ret) return -EIO; - if (map_length >= orig_bio->bi_iter.bi_size) { + if (map_length >= submit_len) { bio = orig_bio; dip->flags |= BTRFS_DIO_ORIG_BIO_SUBMITTED; goto submit; } /* async crcs make it difficult to collect full stripe writes. */ - if (btrfs_get_alloc_profile(root, 1) & BTRFS_BLOCK_GROUP_RAID56_MASK) + if (btrfs_data_alloc_profile(fs_info) & BTRFS_BLOCK_GROUP_RAID56_MASK) async_submit = 0; else async_submit = 1; - bio = btrfs_dio_bio_alloc(orig_bio->bi_bdev, start_sector, GFP_NOFS); - if (!bio) - return -ENOMEM; - - bio->bi_opf = orig_bio->bi_opf; - bio->bi_private = dip; - bio->bi_end_io = btrfs_end_dio_bio; - btrfs_io_bio(bio)->logical = file_offset; + /* bio split */ + ASSERT(map_length <= INT_MAX); atomic_inc(&dip->pending_bios); + do { + clone_len = min_t(int, submit_len, map_length); - bio_for_each_segment_all(bvec, orig_bio, j) { - nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec->bv_len); - i = 0; -next_block: - if (unlikely(map_length < submit_len + blocksize || - bio_add_page(bio, bvec->bv_page, blocksize, - bvec->bv_offset + (i * blocksize)) < blocksize)) { - /* - * inc the count before we submit the bio so - * we know the end IO handler won't happen before - * we inc the count. Otherwise, the dip might get freed - * before we're done setting it up - */ - atomic_inc(&dip->pending_bios); - ret = __btrfs_submit_dio_bio(bio, inode, - file_offset, skip_sum, - async_submit); - if (ret) { - bio_put(bio); - atomic_dec(&dip->pending_bios); - goto out_err; - } - - start_sector += submit_len >> 9; - file_offset += submit_len; + /* + * This will never fail as it's passing GPF_NOFS and + * the allocation is backed by btrfs_bioset. + */ + bio = btrfs_bio_clone_partial(orig_bio, clone_offset, + clone_len); + bio->bi_private = dip; + bio->bi_end_io = btrfs_end_dio_bio; + btrfs_io_bio(bio)->logical = file_offset; + + ASSERT(submit_len >= clone_len); + submit_len -= clone_len; + if (submit_len == 0) + break; - submit_len = 0; + /* + * Increase the count before we submit the bio so we know + * the end IO handler won't happen before we increase the + * count. Otherwise, the dip might get freed before we're + * done setting it up. + */ + atomic_inc(&dip->pending_bios); - bio = btrfs_dio_bio_alloc(orig_bio->bi_bdev, - start_sector, GFP_NOFS); - if (!bio) - goto out_err; - bio->bi_opf = orig_bio->bi_opf; - bio->bi_private = dip; - bio->bi_end_io = btrfs_end_dio_bio; - btrfs_io_bio(bio)->logical = file_offset; + ret = __btrfs_submit_dio_bio(bio, inode, file_offset, skip_sum, + async_submit); + if (ret) { + bio_put(bio); + atomic_dec(&dip->pending_bios); + goto out_err; + } - map_length = orig_bio->bi_iter.bi_size; - ret = btrfs_map_block(fs_info, btrfs_op(orig_bio), - start_sector << 9, - &map_length, NULL, 0); - if (ret) { - bio_put(bio); - goto out_err; - } + clone_offset += clone_len; + start_sector += clone_len >> 9; + file_offset += clone_len; - goto next_block; - } else { - submit_len += blocksize; - if (--nr_sectors) { - i++; - goto next_block; - } - } - } + map_length = submit_len; + ret = btrfs_map_block(fs_info, btrfs_op(orig_bio), + start_sector << 9, &map_length, NULL, 0); + if (ret) + goto out_err; + } while (submit_len > 0); submit: ret = __btrfs_submit_dio_bio(bio, inode, file_offset, skip_sum, @@ -8576,19 +8583,15 @@ static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode, loff_t file_offset) { struct btrfs_dio_private *dip = NULL; - struct bio *io_bio = NULL; - struct btrfs_io_bio *btrfs_bio; + struct bio *bio = NULL; + struct btrfs_io_bio *io_bio; int skip_sum; bool write = (bio_op(dio_bio) == REQ_OP_WRITE); int ret = 0; skip_sum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM; - io_bio = btrfs_bio_clone(dio_bio, GFP_NOFS); - if (!io_bio) { - ret = -ENOMEM; - goto free_ordered; - } + bio = btrfs_bio_clone(dio_bio); dip = kzalloc(sizeof(*dip), GFP_NOFS); if (!dip) { @@ -8601,17 +8604,17 @@ static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode, dip->logical_offset = file_offset; dip->bytes = dio_bio->bi_iter.bi_size; dip->disk_bytenr = (u64)dio_bio->bi_iter.bi_sector << 9; - io_bio->bi_private = dip; - dip->orig_bio = io_bio; + bio->bi_private = dip; + dip->orig_bio = bio; dip->dio_bio = dio_bio; atomic_set(&dip->pending_bios, 0); - btrfs_bio = btrfs_io_bio(io_bio); - btrfs_bio->logical = file_offset; + io_bio = btrfs_io_bio(bio); + io_bio->logical = file_offset; if (write) { - io_bio->bi_end_io = btrfs_endio_direct_write; + bio->bi_end_io = btrfs_endio_direct_write; } else { - io_bio->bi_end_io = btrfs_endio_direct_read; + bio->bi_end_io = btrfs_endio_direct_read; dip->subio_endio = btrfs_subio_endio_read; } @@ -8634,8 +8637,8 @@ static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode, if (!ret) return; - if (btrfs_bio->end_io) - btrfs_bio->end_io(btrfs_bio, ret); + if (io_bio->end_io) + io_bio->end_io(io_bio, ret); free_ordered: /* @@ -8647,16 +8650,15 @@ free_ordered: * same as btrfs_endio_direct_[write|read] because we can't call these * callbacks - they require an allocated dip and a clone of dio_bio. */ - if (io_bio && dip) { - io_bio->bi_status = BLK_STS_IOERR; - bio_endio(io_bio); + if (bio && dip) { + bio_io_error(bio); /* - * The end io callbacks free our dip, do the final put on io_bio + * The end io callbacks free our dip, do the final put on bio * and all the cleanup and final put for dio_bio (through * dio_end_io()). */ dip = NULL; - io_bio = NULL; + bio = NULL; } else { if (write) __endio_write_update_ordered(inode, @@ -8674,8 +8676,8 @@ free_ordered: */ dio_end_io(dio_bio); } - if (io_bio) - bio_put(io_bio); + if (bio) + bio_put(bio); kfree(dip); } @@ -8719,6 +8721,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) struct inode *inode = file->f_mapping->host; struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_dio_data dio_data = { 0 }; + struct extent_changeset *data_reserved = NULL; loff_t offset = iocb->ki_pos; size_t count = 0; int flags = 0; @@ -8758,7 +8761,8 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) ret = -EAGAIN; goto out; } - ret = btrfs_delalloc_reserve_space(inode, offset, count); + ret = btrfs_delalloc_reserve_space(inode, &data_reserved, + offset, count); if (ret) goto out; dio_data.outstanding_extents = count_max_extents(count); @@ -8790,8 +8794,8 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) current->journal_info = NULL; if (ret < 0 && ret != -EIOCBQUEUED) { if (dio_data.reserve) - btrfs_delalloc_release_space(inode, offset, - dio_data.reserve); + btrfs_delalloc_release_space(inode, data_reserved, + offset, dio_data.reserve); /* * On error we might have left some ordered extents * without submitting corresponding bios for them, so @@ -8806,8 +8810,8 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) dio_data.unsubmitted_oe_range_start, false); } else if (ret >= 0 && (size_t)ret < count) - btrfs_delalloc_release_space(inode, offset, - count - (size_t)ret); + btrfs_delalloc_release_space(inode, data_reserved, + offset, count - (size_t)ret); } out: if (wakeup) @@ -8815,6 +8819,7 @@ out: if (relock) inode_lock(inode); + extent_changeset_free(data_reserved); return ret; } @@ -9005,7 +9010,7 @@ again: * free the entire extent. */ if (PageDirty(page)) - btrfs_qgroup_free_data(inode, page_start, PAGE_SIZE); + btrfs_qgroup_free_data(inode, NULL, page_start, PAGE_SIZE); if (!inode_evicting) { clear_extent_bit(tree, page_start, page_end, EXTENT_LOCKED | EXTENT_DIRTY | @@ -9047,6 +9052,7 @@ int btrfs_page_mkwrite(struct vm_fault *vmf) struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; struct btrfs_ordered_extent *ordered; struct extent_state *cached_state = NULL; + struct extent_changeset *data_reserved = NULL; char *kaddr; unsigned long zero_start; loff_t size; @@ -9072,7 +9078,7 @@ int btrfs_page_mkwrite(struct vm_fault *vmf) * end up waiting indefinitely to get a lock on the page currently * being processed by btrfs_page_mkwrite() function. */ - ret = btrfs_delalloc_reserve_space(inode, page_start, + ret = btrfs_delalloc_reserve_space(inode, &data_reserved, page_start, reserved_space); if (!ret) { ret = file_update_time(vmf->vma->vm_file); @@ -9126,8 +9132,8 @@ again: spin_lock(&BTRFS_I(inode)->lock); BTRFS_I(inode)->outstanding_extents++; spin_unlock(&BTRFS_I(inode)->lock); - btrfs_delalloc_release_space(inode, page_start, - PAGE_SIZE - reserved_space); + btrfs_delalloc_release_space(inode, data_reserved, + page_start, PAGE_SIZE - reserved_space); } } @@ -9178,13 +9184,16 @@ again: out_unlock: if (!ret) { sb_end_pagefault(inode->i_sb); + extent_changeset_free(data_reserved); return VM_FAULT_LOCKED; } unlock_page(page); out: - btrfs_delalloc_release_space(inode, page_start, reserved_space); + btrfs_delalloc_release_space(inode, data_reserved, page_start, + reserved_space); out_noreserve: sb_end_pagefault(inode->i_sb); + extent_changeset_free(data_reserved); return ret; } @@ -9406,8 +9415,8 @@ struct inode *btrfs_alloc_inode(struct super_block *sb) inode = &ei->vfs_inode; extent_map_tree_init(&ei->extent_tree); - extent_io_tree_init(&ei->io_tree, &inode->i_data); - extent_io_tree_init(&ei->io_failure_tree, &inode->i_data); + extent_io_tree_init(&ei->io_tree, inode); + extent_io_tree_init(&ei->io_failure_tree, inode); ei->io_tree.track_uptodate = 1; ei->io_failure_tree.track_uptodate = 1; atomic_set(&ei->sync_writers, 0); @@ -9516,7 +9525,6 @@ void btrfs_destroy_cachep(void) rcu_barrier(); kmem_cache_destroy(btrfs_inode_cachep); kmem_cache_destroy(btrfs_trans_handle_cachep); - kmem_cache_destroy(btrfs_transaction_cachep); kmem_cache_destroy(btrfs_path_cachep); kmem_cache_destroy(btrfs_free_space_cachep); } @@ -9536,12 +9544,6 @@ int btrfs_init_cachep(void) if (!btrfs_trans_handle_cachep) goto fail; - btrfs_transaction_cachep = kmem_cache_create("btrfs_transaction", - sizeof(struct btrfs_transaction), 0, - SLAB_TEMPORARY | SLAB_MEM_SPREAD, NULL); - if (!btrfs_transaction_cachep) - goto fail; - btrfs_path_cachep = kmem_cache_create("btrfs_path", sizeof(struct btrfs_path), 0, SLAB_MEM_SPREAD, NULL); @@ -9566,6 +9568,24 @@ static int btrfs_getattr(const struct path *path, struct kstat *stat, u64 delalloc_bytes; struct inode *inode = d_inode(path->dentry); u32 blocksize = inode->i_sb->s_blocksize; + u32 bi_flags = BTRFS_I(inode)->flags; + + stat->result_mask |= STATX_BTIME; + stat->btime.tv_sec = BTRFS_I(inode)->i_otime.tv_sec; + stat->btime.tv_nsec = BTRFS_I(inode)->i_otime.tv_nsec; + if (bi_flags & BTRFS_INODE_APPEND) + stat->attributes |= STATX_ATTR_APPEND; + if (bi_flags & BTRFS_INODE_COMPRESS) + stat->attributes |= STATX_ATTR_COMPRESSED; + if (bi_flags & BTRFS_INODE_IMMUTABLE) + stat->attributes |= STATX_ATTR_IMMUTABLE; + if (bi_flags & BTRFS_INODE_NODUMP) + stat->attributes |= STATX_ATTR_NODUMP; + + stat->attributes_mask |= (STATX_ATTR_APPEND | + STATX_ATTR_COMPRESSED | + STATX_ATTR_IMMUTABLE | + STATX_ATTR_NODUMP); generic_fillattr(inode, stat); stat->dev = BTRFS_I(inode)->root->anon_dev; @@ -10540,7 +10560,7 @@ next: btrfs_end_transaction(trans); } if (cur_offset < end) - btrfs_free_reserved_data_space(inode, cur_offset, + btrfs_free_reserved_data_space(inode, NULL, cur_offset, end - cur_offset + 1); return ret; } @@ -10661,6 +10681,42 @@ static int btrfs_readpage_io_failed_hook(struct page *page, int failed_mirror) return -EAGAIN; } +static struct btrfs_fs_info *iotree_fs_info(void *private_data) +{ + struct inode *inode = private_data; + return btrfs_sb(inode->i_sb); +} + +static void btrfs_check_extent_io_range(void *private_data, const char *caller, + u64 start, u64 end) +{ + struct inode *inode = private_data; + u64 isize; + + isize = i_size_read(inode); + if (end >= PAGE_SIZE && (end % 2) == 0 && end != isize - 1) { + btrfs_debug_rl(BTRFS_I(inode)->root->fs_info, + "%s: ino %llu isize %llu odd range [%llu,%llu]", + caller, btrfs_ino(BTRFS_I(inode)), isize, start, end); + } +} + +void btrfs_set_range_writeback(void *private_data, u64 start, u64 end) +{ + struct inode *inode = private_data; + unsigned long index = start >> PAGE_SHIFT; + unsigned long end_index = end >> PAGE_SHIFT; + struct page *page; + + while (index <= end_index) { + page = find_get_page(inode->i_mapping, index); + ASSERT(page); /* Pages should be in the extent_io_tree */ + set_page_writeback(page); + put_page(page); + index++; + } +} + static const struct inode_operations btrfs_dir_inode_operations = { .getattr = btrfs_getattr, .lookup = btrfs_lookup, @@ -10704,6 +10760,8 @@ static const struct extent_io_ops btrfs_extent_io_ops = { .readpage_end_io_hook = btrfs_readpage_end_io_hook, .merge_bio_hook = btrfs_merge_bio_hook, .readpage_io_failed_hook = btrfs_readpage_io_failed_hook, + .tree_fs_info = iotree_fs_info, + .set_range_writeback = btrfs_set_range_writeback, /* optional callbacks */ .fill_delalloc = run_delalloc_range, @@ -10713,6 +10771,7 @@ static const struct extent_io_ops btrfs_extent_io_ops = { .clear_bit_hook = btrfs_clear_bit_hook, .merge_extent_hook = btrfs_merge_extent_hook, .split_extent_hook = btrfs_split_extent_hook, + .check_extent_io_range = btrfs_check_extent_io_range, }; /* diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index e176375f374f..fa1b78cf25f6 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -37,7 +37,7 @@ #include <linux/bit_spinlock.h> #include <linux/security.h> #include <linux/xattr.h> -#include <linux/vmalloc.h> +#include <linux/mm.h> #include <linux/slab.h> #include <linux/blkdev.h> #include <linux/uuid.h> @@ -689,7 +689,7 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, if (ret) goto dec_and_free; - btrfs_wait_ordered_extents(root, -1, 0, (u64)-1); + btrfs_wait_ordered_extents(root, U64_MAX, 0, (u64)-1); btrfs_init_block_rsv(&pending_snapshot->block_rsv, BTRFS_BLOCK_RSV_TEMP); @@ -1127,6 +1127,7 @@ static int cluster_pages_for_defrag(struct inode *inode, struct btrfs_ordered_extent *ordered; struct extent_state *cached_state = NULL; struct extent_io_tree *tree; + struct extent_changeset *data_reserved = NULL; gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping); file_end = (isize - 1) >> PAGE_SHIFT; @@ -1135,7 +1136,7 @@ static int cluster_pages_for_defrag(struct inode *inode, page_cnt = min_t(u64, (u64)num_pages, (u64)file_end - start_index + 1); - ret = btrfs_delalloc_reserve_space(inode, + ret = btrfs_delalloc_reserve_space(inode, &data_reserved, start_index << PAGE_SHIFT, page_cnt << PAGE_SHIFT); if (ret) @@ -1226,7 +1227,7 @@ again: spin_lock(&BTRFS_I(inode)->lock); BTRFS_I(inode)->outstanding_extents++; spin_unlock(&BTRFS_I(inode)->lock); - btrfs_delalloc_release_space(inode, + btrfs_delalloc_release_space(inode, data_reserved, start_index << PAGE_SHIFT, (page_cnt - i_done) << PAGE_SHIFT); } @@ -1247,15 +1248,17 @@ again: unlock_page(pages[i]); put_page(pages[i]); } + extent_changeset_free(data_reserved); return i_done; out: for (i = 0; i < i_done; i++) { unlock_page(pages[i]); put_page(pages[i]); } - btrfs_delalloc_release_space(inode, + btrfs_delalloc_release_space(inode, data_reserved, start_index << PAGE_SHIFT, page_cnt << PAGE_SHIFT); + extent_changeset_free(data_reserved); return ret; } @@ -4588,7 +4591,7 @@ static long btrfs_ioctl_logical_to_ino(struct btrfs_fs_info *fs_info, out: btrfs_free_path(path); - vfree(inodes); + kvfree(inodes); kfree(loi); return ret; @@ -4897,7 +4900,6 @@ static long btrfs_ioctl_qgroup_assign(struct file *file, void __user *arg) goto out; } - /* FIXME: check if the IDs really exist */ if (sa->assign) { ret = btrfs_add_qgroup_relation(trans, fs_info, sa->src, sa->dst); @@ -4956,7 +4958,6 @@ static long btrfs_ioctl_qgroup_create(struct file *file, void __user *arg) goto out; } - /* FIXME: check if the IDs really exist */ if (sa->create) { ret = btrfs_create_qgroup(trans, fs_info, sa->qgroupid); } else { @@ -5010,7 +5011,6 @@ static long btrfs_ioctl_qgroup_limit(struct file *file, void __user *arg) qgroupid = root->root_key.objectid; } - /* FIXME: check if the IDs really exist */ ret = btrfs_limit_qgroup(trans, fs_info, qgroupid, &sa->lim); err = btrfs_end_transaction(trans); diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c index f48c8c14dc14..d433e75d489a 100644 --- a/fs/btrfs/lzo.c +++ b/fs/btrfs/lzo.c @@ -18,13 +18,14 @@ #include <linux/kernel.h> #include <linux/slab.h> -#include <linux/vmalloc.h> +#include <linux/mm.h> #include <linux/init.h> #include <linux/err.h> #include <linux/sched.h> #include <linux/pagemap.h> #include <linux/bio.h> #include <linux/lzo.h> +#include <linux/refcount.h> #include "compression.h" #define LZO_LEN 4 @@ -40,9 +41,9 @@ static void lzo_free_workspace(struct list_head *ws) { struct workspace *workspace = list_entry(ws, struct workspace, list); - vfree(workspace->buf); - vfree(workspace->cbuf); - vfree(workspace->mem); + kvfree(workspace->buf); + kvfree(workspace->cbuf); + kvfree(workspace->mem); kfree(workspace); } @@ -50,13 +51,13 @@ static struct list_head *lzo_alloc_workspace(void) { struct workspace *workspace; - workspace = kzalloc(sizeof(*workspace), GFP_NOFS); + workspace = kzalloc(sizeof(*workspace), GFP_KERNEL); if (!workspace) return ERR_PTR(-ENOMEM); - workspace->mem = vmalloc(LZO1X_MEM_COMPRESS); - workspace->buf = vmalloc(lzo1x_worst_compress(PAGE_SIZE)); - workspace->cbuf = vmalloc(lzo1x_worst_compress(PAGE_SIZE)); + workspace->mem = kvmalloc(LZO1X_MEM_COMPRESS, GFP_KERNEL); + workspace->buf = kvmalloc(lzo1x_worst_compress(PAGE_SIZE), GFP_KERNEL); + workspace->cbuf = kvmalloc(lzo1x_worst_compress(PAGE_SIZE), GFP_KERNEL); if (!workspace->mem || !workspace->buf || !workspace->cbuf) goto fail; @@ -141,7 +142,7 @@ static int lzo_compress_pages(struct list_head *ws, ret = lzo1x_1_compress(data_in, in_len, workspace->cbuf, &out_len, workspace->mem); if (ret != LZO_E_OK) { - pr_debug("BTRFS: deflate in loop returned %d\n", + pr_debug("BTRFS: lzo in loop returned %d\n", ret); ret = -EIO; goto out; @@ -229,8 +230,10 @@ static int lzo_compress_pages(struct list_head *ws, in_len = min(bytes_left, PAGE_SIZE); } - if (tot_out > tot_in) + if (tot_out >= tot_in) { + ret = -E2BIG; goto out; + } /* store the size of all chunks of compressed data */ cpage_out = kmap(pages[0]); @@ -254,16 +257,13 @@ out: return ret; } -static int lzo_decompress_bio(struct list_head *ws, - struct page **pages_in, - u64 disk_start, - struct bio *orig_bio, - size_t srclen) +static int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb) { struct workspace *workspace = list_entry(ws, struct workspace, list); int ret = 0, ret2; char *data_in; unsigned long page_in_index = 0; + size_t srclen = cb->compressed_len; unsigned long total_pages_in = DIV_ROUND_UP(srclen, PAGE_SIZE); unsigned long buf_start; unsigned long buf_offset = 0; @@ -278,6 +278,9 @@ static int lzo_decompress_bio(struct list_head *ws, unsigned long tot_len; char *buf; bool may_late_unmap, need_unmap; + struct page **pages_in = cb->compressed_pages; + u64 disk_start = cb->start; + struct bio *orig_bio = cb->orig_bio; data_in = kmap(pages_in[0]); tot_len = read_compress_length(data_in); diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 7b40e2e7292a..a3aca495e33e 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -663,7 +663,7 @@ static void btrfs_run_ordered_extent_work(struct btrfs_work *work) * wait for all the ordered extents in a root. This is done when balancing * space between drives. */ -int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr, +u64 btrfs_wait_ordered_extents(struct btrfs_root *root, u64 nr, const u64 range_start, const u64 range_len) { struct btrfs_fs_info *fs_info = root->fs_info; @@ -671,7 +671,7 @@ int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr, LIST_HEAD(skipped); LIST_HEAD(works); struct btrfs_ordered_extent *ordered, *next; - int count = 0; + u64 count = 0; const u64 range_end = range_start + range_len; mutex_lock(&root->ordered_extent_mutex); @@ -701,7 +701,7 @@ int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr, cond_resched(); spin_lock(&root->ordered_extent_lock); - if (nr != -1) + if (nr != U64_MAX) nr--; count++; } @@ -720,13 +720,13 @@ int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr, return count; } -int btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr, - const u64 range_start, const u64 range_len) +u64 btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr, + const u64 range_start, const u64 range_len) { struct btrfs_root *root; struct list_head splice; - int done; - int total_done = 0; + u64 total_done = 0; + u64 done; INIT_LIST_HEAD(&splice); @@ -748,9 +748,8 @@ int btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr, total_done += done; spin_lock(&fs_info->ordered_root_lock); - if (nr != -1) { + if (nr != U64_MAX) { nr -= done; - WARN_ON(nr < 0); } } list_splice_tail(&splice, &fs_info->ordered_roots); diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h index e0c1d5b8d859..56c4c0ee6381 100644 --- a/fs/btrfs/ordered-data.h +++ b/fs/btrfs/ordered-data.h @@ -200,9 +200,9 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset, struct btrfs_ordered_extent *ordered); int btrfs_find_ordered_sum(struct inode *inode, u64 offset, u64 disk_bytenr, u32 *sum, int len); -int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr, +u64 btrfs_wait_ordered_extents(struct btrfs_root *root, u64 nr, const u64 range_start, const u64 range_len); -int btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr, +u64 btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr, const u64 range_start, const u64 range_len); void btrfs_get_logged_extents(struct btrfs_inode *inode, struct list_head *logged_list, diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c index cdafbf92ef0c..fcae61e175f3 100644 --- a/fs/btrfs/print-tree.c +++ b/fs/btrfs/print-tree.c @@ -261,8 +261,11 @@ void btrfs_print_leaf(struct btrfs_fs_info *fs_info, struct extent_buffer *l) case BTRFS_BLOCK_GROUP_ITEM_KEY: bi = btrfs_item_ptr(l, i, struct btrfs_block_group_item); - pr_info("\t\tblock group used %llu\n", - btrfs_disk_block_group_used(l, bi)); + pr_info( + "\t\tblock group used %llu chunk_objectid %llu flags %llu\n", + btrfs_disk_block_group_used(l, bi), + btrfs_disk_block_group_chunk_objectid(l, bi), + btrfs_disk_block_group_flags(l, bi)); break; case BTRFS_CHUNK_ITEM_KEY: print_chunk(l, btrfs_item_ptr(l, i, diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c index d6cb155ef7a1..4b23ae5d0e5c 100644 --- a/fs/btrfs/props.c +++ b/fs/btrfs/props.c @@ -164,6 +164,7 @@ static int iterate_object_props(struct btrfs_root *root, size_t), void *ctx) { + struct btrfs_fs_info *fs_info = root->fs_info; int ret; char *name_buf = NULL; char *value_buf = NULL; @@ -214,6 +215,12 @@ static int iterate_object_props(struct btrfs_root *root, name_ptr = (unsigned long)(di + 1); data_ptr = name_ptr + name_len; + if (verify_dir_item(fs_info, leaf, + path->slots[0], di)) { + ret = -EIO; + goto out; + } + if (name_len <= XATTR_BTRFS_PREFIX_LEN || memcmp_extent_buffer(leaf, XATTR_BTRFS_PREFIX, name_ptr, diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index deffbeb74a0b..4ce351efe281 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1406,38 +1406,6 @@ out: return ret; } -int btrfs_qgroup_prepare_account_extents(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info) -{ - struct btrfs_qgroup_extent_record *record; - struct btrfs_delayed_ref_root *delayed_refs; - struct rb_node *node; - u64 qgroup_to_skip; - int ret = 0; - - delayed_refs = &trans->transaction->delayed_refs; - qgroup_to_skip = delayed_refs->qgroup_to_skip; - - /* - * No need to do lock, since this function will only be called in - * btrfs_commit_transaction(). - */ - node = rb_first(&delayed_refs->dirty_extent_root); - while (node) { - record = rb_entry(node, struct btrfs_qgroup_extent_record, - node); - if (WARN_ON(!record->old_roots)) - ret = btrfs_find_all_roots(NULL, fs_info, - record->bytenr, 0, &record->old_roots); - if (ret < 0) - break; - if (qgroup_to_skip) - ulist_del(record->old_roots, qgroup_to_skip, 0); - node = rb_next(node); - } - return ret; -} - int btrfs_qgroup_trace_extent_nolock(struct btrfs_fs_info *fs_info, struct btrfs_delayed_ref_root *delayed_refs, struct btrfs_qgroup_extent_record *record) @@ -1559,6 +1527,7 @@ int btrfs_qgroup_trace_leaf_items(struct btrfs_trans_handle *trans, if (ret) return ret; } + cond_resched(); return 0; } @@ -1918,6 +1887,35 @@ static int qgroup_update_counters(struct btrfs_fs_info *fs_info, return 0; } +/* + * Check if the @roots potentially is a list of fs tree roots + * + * Return 0 for definitely not a fs/subvol tree roots ulist + * Return 1 for possible fs/subvol tree roots in the list (considering an empty + * one as well) + */ +static int maybe_fs_roots(struct ulist *roots) +{ + struct ulist_node *unode; + struct ulist_iterator uiter; + + /* Empty one, still possible for fs roots */ + if (!roots || roots->nnodes == 0) + return 1; + + ULIST_ITER_INIT(&uiter); + unode = ulist_next(roots, &uiter); + if (!unode) + return 1; + + /* + * If it contains fs tree roots, then it must belong to fs/subvol + * trees. + * If it contains a non-fs tree, it won't be shared with fs/subvol trees. + */ + return is_fstree(unode->val); +} + int btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, @@ -1934,10 +1932,20 @@ btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) return 0; - if (new_roots) + if (new_roots) { + if (!maybe_fs_roots(new_roots)) + goto out_free; nr_new_roots = new_roots->nnodes; - if (old_roots) + } + if (old_roots) { + if (!maybe_fs_roots(old_roots)) + goto out_free; nr_old_roots = old_roots->nnodes; + } + + /* Quick exit, either not fs tree roots, or won't affect any qgroup */ + if (nr_old_roots == 0 && nr_new_roots == 0) + goto out_free; BUG_ON(!fs_info->quota_root); @@ -2017,6 +2025,19 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans, if (!ret) { /* + * Old roots should be searched when inserting qgroup + * extent record + */ + if (WARN_ON(!record->old_roots)) { + /* Search commit root to find old_roots */ + ret = btrfs_find_all_roots(NULL, fs_info, + record->bytenr, 0, + &record->old_roots); + if (ret < 0) + goto cleanup; + } + + /* * Use SEQ_LAST as time_seq to do special search, which * doesn't lock tree or delayed_refs and search current * root. It's safe inside commit_transaction(). @@ -2025,8 +2046,11 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans, record->bytenr, SEQ_LAST, &new_roots); if (ret < 0) goto cleanup; - if (qgroup_to_skip) + if (qgroup_to_skip) { ulist_del(new_roots, qgroup_to_skip, 0); + ulist_del(record->old_roots, qgroup_to_skip, + 0); + } ret = btrfs_qgroup_account_extent(trans, fs_info, record->bytenr, record->num_bytes, record->old_roots, new_roots); @@ -2338,6 +2362,11 @@ static int qgroup_reserve(struct btrfs_root *root, u64 num_bytes, bool enforce) if (num_bytes == 0) return 0; + + if (test_bit(BTRFS_FS_QUOTA_OVERRIDE, &fs_info->flags) && + capable(CAP_SYS_RESOURCE)) + enforce = false; + retry: spin_lock(&fs_info->qgroup_lock); quota_root = fs_info->quota_root; @@ -2376,7 +2405,7 @@ retry: ret = btrfs_start_delalloc_inodes(root, 0); if (ret) return ret; - btrfs_wait_ordered_extents(root, -1, 0, (u64)-1); + btrfs_wait_ordered_extents(root, U64_MAX, 0, (u64)-1); trans = btrfs_join_transaction(root); if (IS_ERR(trans)) return PTR_ERR(trans); @@ -2806,55 +2835,130 @@ btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info) * Return <0 for error (including -EQUOT) * * NOTE: this function may sleep for memory allocation. + * if btrfs_qgroup_reserve_data() is called multiple times with + * same @reserved, caller must ensure when error happens it's OK + * to free *ALL* reserved space. */ -int btrfs_qgroup_reserve_data(struct inode *inode, u64 start, u64 len) +int btrfs_qgroup_reserve_data(struct inode *inode, + struct extent_changeset **reserved_ret, u64 start, + u64 len) { struct btrfs_root *root = BTRFS_I(inode)->root; - struct extent_changeset changeset; struct ulist_node *unode; struct ulist_iterator uiter; + struct extent_changeset *reserved; + u64 orig_reserved; + u64 to_reserve; int ret; if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &root->fs_info->flags) || !is_fstree(root->objectid) || len == 0) return 0; - changeset.bytes_changed = 0; - ulist_init(&changeset.range_changed); + /* @reserved parameter is mandatory for qgroup */ + if (WARN_ON(!reserved_ret)) + return -EINVAL; + if (!*reserved_ret) { + *reserved_ret = extent_changeset_alloc(); + if (!*reserved_ret) + return -ENOMEM; + } + reserved = *reserved_ret; + /* Record already reserved space */ + orig_reserved = reserved->bytes_changed; ret = set_record_extent_bits(&BTRFS_I(inode)->io_tree, start, - start + len -1, EXTENT_QGROUP_RESERVED, &changeset); + start + len -1, EXTENT_QGROUP_RESERVED, reserved); + + /* Newly reserved space */ + to_reserve = reserved->bytes_changed - orig_reserved; trace_btrfs_qgroup_reserve_data(inode, start, len, - changeset.bytes_changed, - QGROUP_RESERVE); + to_reserve, QGROUP_RESERVE); if (ret < 0) goto cleanup; - ret = qgroup_reserve(root, changeset.bytes_changed, true); + ret = qgroup_reserve(root, to_reserve, true); if (ret < 0) goto cleanup; - ulist_release(&changeset.range_changed); return ret; cleanup: - /* cleanup already reserved ranges */ + /* cleanup *ALL* already reserved ranges */ ULIST_ITER_INIT(&uiter); - while ((unode = ulist_next(&changeset.range_changed, &uiter))) + while ((unode = ulist_next(&reserved->range_changed, &uiter))) clear_extent_bit(&BTRFS_I(inode)->io_tree, unode->val, unode->aux, EXTENT_QGROUP_RESERVED, 0, 0, NULL, GFP_NOFS); - ulist_release(&changeset.range_changed); + extent_changeset_release(reserved); + return ret; +} + +/* Free ranges specified by @reserved, normally in error path */ +static int qgroup_free_reserved_data(struct inode *inode, + struct extent_changeset *reserved, u64 start, u64 len) +{ + struct btrfs_root *root = BTRFS_I(inode)->root; + struct ulist_node *unode; + struct ulist_iterator uiter; + struct extent_changeset changeset; + int freed = 0; + int ret; + + extent_changeset_init(&changeset); + len = round_up(start + len, root->fs_info->sectorsize); + start = round_down(start, root->fs_info->sectorsize); + + ULIST_ITER_INIT(&uiter); + while ((unode = ulist_next(&reserved->range_changed, &uiter))) { + u64 range_start = unode->val; + /* unode->aux is the inclusive end */ + u64 range_len = unode->aux - range_start + 1; + u64 free_start; + u64 free_len; + + extent_changeset_release(&changeset); + + /* Only free range in range [start, start + len) */ + if (range_start >= start + len || + range_start + range_len <= start) + continue; + free_start = max(range_start, start); + free_len = min(start + len, range_start + range_len) - + free_start; + /* + * TODO: To also modify reserved->ranges_reserved to reflect + * the modification. + * + * However as long as we free qgroup reserved according to + * EXTENT_QGROUP_RESERVED, we won't double free. + * So not need to rush. + */ + ret = clear_record_extent_bits(&BTRFS_I(inode)->io_failure_tree, + free_start, free_start + free_len - 1, + EXTENT_QGROUP_RESERVED, &changeset); + if (ret < 0) + goto out; + freed += changeset.bytes_changed; + } + btrfs_qgroup_free_refroot(root->fs_info, root->objectid, freed); + ret = freed; +out: + extent_changeset_release(&changeset); return ret; } -static int __btrfs_qgroup_release_data(struct inode *inode, u64 start, u64 len, - int free) +static int __btrfs_qgroup_release_data(struct inode *inode, + struct extent_changeset *reserved, u64 start, u64 len, + int free) { struct extent_changeset changeset; int trace_op = QGROUP_RELEASE; int ret; - changeset.bytes_changed = 0; - ulist_init(&changeset.range_changed); + /* In release case, we shouldn't have @reserved */ + WARN_ON(!free && reserved); + if (free && reserved) + return qgroup_free_reserved_data(inode, reserved, start, len); + extent_changeset_init(&changeset); ret = clear_record_extent_bits(&BTRFS_I(inode)->io_tree, start, start + len -1, EXTENT_QGROUP_RESERVED, &changeset); if (ret < 0) @@ -2868,8 +2972,9 @@ static int __btrfs_qgroup_release_data(struct inode *inode, u64 start, u64 len, btrfs_qgroup_free_refroot(BTRFS_I(inode)->root->fs_info, BTRFS_I(inode)->root->objectid, changeset.bytes_changed); + ret = changeset.bytes_changed; out: - ulist_release(&changeset.range_changed); + extent_changeset_release(&changeset); return ret; } @@ -2878,14 +2983,17 @@ out: * * Should be called when a range of pages get invalidated before reaching disk. * Or for error cleanup case. + * if @reserved is given, only reserved range in [@start, @start + @len) will + * be freed. * * For data written to disk, use btrfs_qgroup_release_data(). * * NOTE: This function may sleep for memory allocation. */ -int btrfs_qgroup_free_data(struct inode *inode, u64 start, u64 len) +int btrfs_qgroup_free_data(struct inode *inode, + struct extent_changeset *reserved, u64 start, u64 len) { - return __btrfs_qgroup_release_data(inode, start, len, 1); + return __btrfs_qgroup_release_data(inode, reserved, start, len, 1); } /* @@ -2905,7 +3013,7 @@ int btrfs_qgroup_free_data(struct inode *inode, u64 start, u64 len) */ int btrfs_qgroup_release_data(struct inode *inode, u64 start, u64 len) { - return __btrfs_qgroup_release_data(inode, start, len, 0); + return __btrfs_qgroup_release_data(inode, NULL, start, len, 0); } int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes, @@ -2969,8 +3077,7 @@ void btrfs_qgroup_check_reserved_leak(struct inode *inode) struct ulist_iterator iter; int ret; - changeset.bytes_changed = 0; - ulist_init(&changeset.range_changed); + extent_changeset_init(&changeset); ret = clear_record_extent_bits(&BTRFS_I(inode)->io_tree, 0, (u64)-1, EXTENT_QGROUP_RESERVED, &changeset); @@ -2987,5 +3094,5 @@ void btrfs_qgroup_check_reserved_leak(struct inode *inode) changeset.bytes_changed); } - ulist_release(&changeset.range_changed); + extent_changeset_release(&changeset); } diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h index fe04d3f295c6..d9984e87cddf 100644 --- a/fs/btrfs/qgroup.h +++ b/fs/btrfs/qgroup.h @@ -134,8 +134,7 @@ int btrfs_limit_qgroup(struct btrfs_trans_handle *trans, int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info); void btrfs_free_qgroup_config(struct btrfs_fs_info *fs_info); struct btrfs_delayed_extent_op; -int btrfs_qgroup_prepare_account_extents(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info); + /* * Inform qgroup to trace one dirty extent, its info is recorded in @record. * So qgroup can account it at transaction committing time. @@ -243,9 +242,11 @@ int btrfs_verify_qgroup_counts(struct btrfs_fs_info *fs_info, u64 qgroupid, #endif /* New io_tree based accurate qgroup reserve API */ -int btrfs_qgroup_reserve_data(struct inode *inode, u64 start, u64 len); +int btrfs_qgroup_reserve_data(struct inode *inode, + struct extent_changeset **reserved, u64 start, u64 len); int btrfs_qgroup_release_data(struct inode *inode, u64 start, u64 len); -int btrfs_qgroup_free_data(struct inode *inode, u64 start, u64 len); +int btrfs_qgroup_free_data(struct inode *inode, + struct extent_changeset *reserved, u64 start, u64 len); int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes, bool enforce); diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index f3d30d9ea8f9..6f845d219cd6 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -31,7 +31,7 @@ #include <linux/hash.h> #include <linux/list_sort.h> #include <linux/raid/xor.h> -#include <linux/vmalloc.h> +#include <linux/mm.h> #include <asm/div64.h> #include "ctree.h" #include "extent_map.h" @@ -218,12 +218,9 @@ int btrfs_alloc_stripe_hash_table(struct btrfs_fs_info *info) * of a failing mount. */ table_size = sizeof(*table) + sizeof(*h) * num_entries; - table = kzalloc(table_size, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT); - if (!table) { - table = vzalloc(table_size); - if (!table) - return -ENOMEM; - } + table = kvzalloc(table_size, GFP_KERNEL); + if (!table) + return -ENOMEM; spin_lock_init(&table->cache_lock); INIT_LIST_HEAD(&table->stripe_cache); @@ -1101,10 +1098,7 @@ static int rbio_add_io_page(struct btrfs_raid_bio *rbio, } /* put a new bio on the list */ - bio = btrfs_io_bio_alloc(GFP_NOFS, bio_max_len >> PAGE_SHIFT?:1); - if (!bio) - return -ENOMEM; - + bio = btrfs_io_bio_alloc(bio_max_len >> PAGE_SHIFT ?: 1); bio->bi_iter.bi_size = 0; bio->bi_bdev = stripe->dev->bdev; bio->bi_iter.bi_sector = disk_start >> 9; diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c index a17e775a4a89..ab852b8e3e37 100644 --- a/fs/btrfs/reada.c +++ b/fs/btrfs/reada.c @@ -66,7 +66,6 @@ struct reada_extctl { struct reada_extent { u64 logical; struct btrfs_key top; - int err; struct list_head extctl; int refcnt; spinlock_t lock; diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index d60df51959f7..65661d1aae4e 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -3093,11 +3093,12 @@ int prealloc_file_extent_cluster(struct inode *inode, u64 prealloc_start = cluster->start - offset; u64 prealloc_end = cluster->end - offset; u64 cur_offset; + struct extent_changeset *data_reserved = NULL; BUG_ON(cluster->start != cluster->boundary[0]); inode_lock(inode); - ret = btrfs_check_data_free_space(inode, prealloc_start, + ret = btrfs_check_data_free_space(inode, &data_reserved, prealloc_start, prealloc_end + 1 - prealloc_start); if (ret) goto out; @@ -3113,8 +3114,8 @@ int prealloc_file_extent_cluster(struct inode *inode, lock_extent(&BTRFS_I(inode)->io_tree, start, end); num_bytes = end + 1 - start; if (cur_offset < start) - btrfs_free_reserved_data_space(inode, cur_offset, - start - cur_offset); + btrfs_free_reserved_data_space(inode, data_reserved, + cur_offset, start - cur_offset); ret = btrfs_prealloc_file_range(inode, 0, start, num_bytes, num_bytes, end + 1, &alloc_hint); @@ -3125,10 +3126,11 @@ int prealloc_file_extent_cluster(struct inode *inode, nr++; } if (cur_offset < prealloc_end) - btrfs_free_reserved_data_space(inode, cur_offset, - prealloc_end + 1 - cur_offset); + btrfs_free_reserved_data_space(inode, data_reserved, + cur_offset, prealloc_end + 1 - cur_offset); out: inode_unlock(inode); + extent_changeset_free(data_reserved); return ret; } @@ -4269,8 +4271,7 @@ static struct reloc_control *alloc_reloc_control(struct btrfs_fs_info *fs_info) INIT_LIST_HEAD(&rc->reloc_roots); backref_cache_init(&rc->backref_cache); mapping_tree_init(&rc->reloc_root_tree); - extent_io_tree_init(&rc->processed_blocks, - fs_info->btree_inode->i_mapping); + extent_io_tree_init(&rc->processed_blocks, NULL); return rc; } @@ -4372,7 +4373,7 @@ int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start) btrfs_wait_block_group_reservations(rc->block_group); btrfs_wait_nocow_writers(rc->block_group); - btrfs_wait_ordered_roots(fs_info, -1, + btrfs_wait_ordered_roots(fs_info, U64_MAX, rc->block_group->key.objectid, rc->block_group->key.offset); diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index 7d6bc308bf43..460db0cb2d07 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -390,6 +390,13 @@ again: WARN_ON(btrfs_root_ref_dirid(leaf, ref) != dirid); WARN_ON(btrfs_root_ref_name_len(leaf, ref) != name_len); ptr = (unsigned long)(ref + 1); + ret = btrfs_is_name_len_valid(leaf, path->slots[0], ptr, + name_len); + if (!ret) { + err = -EIO; + goto out; + } + WARN_ON(memcmp_extent_buffer(leaf, name, ptr, name_len)); *sequence = btrfs_root_ref_sequence(leaf, ref); diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index ba5595d19de1..6f1e4c984b94 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -18,6 +18,7 @@ #include <linux/blkdev.h> #include <linux/ratelimit.h> +#include <linux/sched/mm.h> #include "ctree.h" #include "volumes.h" #include "disk-io.h" @@ -161,14 +162,6 @@ struct scrub_parity { unsigned long bitmap[0]; }; -struct scrub_wr_ctx { - struct scrub_bio *wr_curr_bio; - struct btrfs_device *tgtdev; - int pages_per_wr_bio; /* <= SCRUB_PAGES_PER_WR_BIO */ - atomic_t flush_all_writes; - struct mutex wr_lock; -}; - struct scrub_ctx { struct scrub_bio *bios[SCRUB_BIOS_PER_SCTX]; struct btrfs_fs_info *fs_info; @@ -183,11 +176,14 @@ struct scrub_ctx { atomic_t cancel_req; int readonly; int pages_per_rd_bio; - u32 sectorsize; - u32 nodesize; int is_dev_replace; - struct scrub_wr_ctx wr_ctx; + + struct scrub_bio *wr_curr_bio; + struct mutex wr_lock; + int pages_per_wr_bio; /* <= SCRUB_PAGES_PER_WR_BIO */ + atomic_t flush_all_writes; + struct btrfs_device *wr_tgtdev; /* * statistics @@ -289,10 +285,6 @@ static void scrub_remap_extent(struct btrfs_fs_info *fs_info, u64 *extent_physical, struct btrfs_device **extent_dev, int *extent_mirror_num); -static int scrub_setup_wr_ctx(struct scrub_wr_ctx *wr_ctx, - struct btrfs_device *dev, - int is_dev_replace); -static void scrub_free_wr_ctx(struct scrub_wr_ctx *wr_ctx); static int scrub_add_page_to_wr_bio(struct scrub_ctx *sctx, struct scrub_page *spage); static void scrub_wr_submit(struct scrub_ctx *sctx); @@ -643,8 +635,6 @@ static noinline_for_stack void scrub_free_ctx(struct scrub_ctx *sctx) if (!sctx) return; - scrub_free_wr_ctx(&sctx->wr_ctx); - /* this can happen when scrub is cancelled */ if (sctx->curr != -1) { struct scrub_bio *sbio = sctx->bios[sctx->curr]; @@ -664,6 +654,7 @@ static noinline_for_stack void scrub_free_ctx(struct scrub_ctx *sctx) kfree(sbio); } + kfree(sctx->wr_curr_bio); scrub_free_csums(sctx); kfree(sctx); } @@ -680,7 +671,6 @@ struct scrub_ctx *scrub_setup_ctx(struct btrfs_device *dev, int is_dev_replace) struct scrub_ctx *sctx; int i; struct btrfs_fs_info *fs_info = dev->fs_info; - int ret; sctx = kzalloc(sizeof(*sctx), GFP_KERNEL); if (!sctx) @@ -710,8 +700,6 @@ struct scrub_ctx *scrub_setup_ctx(struct btrfs_device *dev, int is_dev_replace) sctx->bios[i]->next_free = -1; } sctx->first_free = 0; - sctx->nodesize = fs_info->nodesize; - sctx->sectorsize = fs_info->sectorsize; atomic_set(&sctx->bios_in_flight, 0); atomic_set(&sctx->workers_pending, 0); atomic_set(&sctx->cancel_req, 0); @@ -722,12 +710,16 @@ struct scrub_ctx *scrub_setup_ctx(struct btrfs_device *dev, int is_dev_replace) spin_lock_init(&sctx->stat_lock); init_waitqueue_head(&sctx->list_wait); - ret = scrub_setup_wr_ctx(&sctx->wr_ctx, - fs_info->dev_replace.tgtdev, is_dev_replace); - if (ret) { - scrub_free_ctx(sctx); - return ERR_PTR(ret); + WARN_ON(sctx->wr_curr_bio != NULL); + mutex_init(&sctx->wr_lock); + sctx->wr_curr_bio = NULL; + if (is_dev_replace) { + WARN_ON(!fs_info->dev_replace.tgtdev); + sctx->pages_per_wr_bio = SCRUB_PAGES_PER_WR_BIO; + sctx->wr_tgtdev = fs_info->dev_replace.tgtdev; + atomic_set(&sctx->flush_all_writes, 0); } + return sctx; nomem: @@ -742,6 +734,7 @@ static int scrub_print_warning_inode(u64 inum, u64 offset, u64 root, u32 nlink; int ret; int i; + unsigned nofs_flag; struct extent_buffer *eb; struct btrfs_inode_item *inode_item; struct scrub_warning *swarn = warn_ctx; @@ -780,7 +773,14 @@ static int scrub_print_warning_inode(u64 inum, u64 offset, u64 root, nlink = btrfs_inode_nlink(eb, inode_item); btrfs_release_path(swarn->path); + /* + * init_path might indirectly call vmalloc, or use GFP_KERNEL. Scrub + * uses GFP_NOFS in this context, so we keep it consistent but it does + * not seem to be strictly necessary. + */ + nofs_flag = memalloc_nofs_save(); ipath = init_ipath(4096, local_root, swarn->path); + memalloc_nofs_restore(nofs_flag); if (IS_ERR(ipath)) { ret = PTR_ERR(ipath); ipath = NULL; @@ -954,7 +954,7 @@ static int scrub_fixup_readpage(u64 inum, u64 offset, u64 root, void *fixup_ctx) ret = -EIO; goto out; } - ret = repair_io_failure(BTRFS_I(inode), offset, PAGE_SIZE, + ret = repair_io_failure(fs_info, inum, offset, PAGE_SIZE, fixup->logical, page, offset - page_offset(page), fixup->mirror_num); @@ -1737,12 +1737,7 @@ static void scrub_recheck_block(struct btrfs_fs_info *fs_info, } WARN_ON(!page->page); - bio = btrfs_io_bio_alloc(GFP_NOFS, 1); - if (!bio) { - page->io_error = 1; - sblock->no_io_error_seen = 0; - continue; - } + bio = btrfs_io_bio_alloc(1); bio->bi_bdev = page->dev->bdev; bio_add_page(bio, page->page, PAGE_SIZE, 0); @@ -1830,9 +1825,7 @@ static int scrub_repair_page_from_good_copy(struct scrub_block *sblock_bad, return -EIO; } - bio = btrfs_io_bio_alloc(GFP_NOFS, 1); - if (!bio) - return -EIO; + bio = btrfs_io_bio_alloc(1); bio->bi_bdev = page_bad->dev->bdev; bio->bi_iter.bi_sector = page_bad->physical >> 9; bio_set_op_attrs(bio, REQ_OP_WRITE, 0); @@ -1898,37 +1891,31 @@ static int scrub_write_page_to_dev_replace(struct scrub_block *sblock, static int scrub_add_page_to_wr_bio(struct scrub_ctx *sctx, struct scrub_page *spage) { - struct scrub_wr_ctx *wr_ctx = &sctx->wr_ctx; struct scrub_bio *sbio; int ret; - mutex_lock(&wr_ctx->wr_lock); + mutex_lock(&sctx->wr_lock); again: - if (!wr_ctx->wr_curr_bio) { - wr_ctx->wr_curr_bio = kzalloc(sizeof(*wr_ctx->wr_curr_bio), + if (!sctx->wr_curr_bio) { + sctx->wr_curr_bio = kzalloc(sizeof(*sctx->wr_curr_bio), GFP_KERNEL); - if (!wr_ctx->wr_curr_bio) { - mutex_unlock(&wr_ctx->wr_lock); + if (!sctx->wr_curr_bio) { + mutex_unlock(&sctx->wr_lock); return -ENOMEM; } - wr_ctx->wr_curr_bio->sctx = sctx; - wr_ctx->wr_curr_bio->page_count = 0; + sctx->wr_curr_bio->sctx = sctx; + sctx->wr_curr_bio->page_count = 0; } - sbio = wr_ctx->wr_curr_bio; + sbio = sctx->wr_curr_bio; if (sbio->page_count == 0) { struct bio *bio; sbio->physical = spage->physical_for_dev_replace; sbio->logical = spage->logical; - sbio->dev = wr_ctx->tgtdev; + sbio->dev = sctx->wr_tgtdev; bio = sbio->bio; if (!bio) { - bio = btrfs_io_bio_alloc(GFP_KERNEL, - wr_ctx->pages_per_wr_bio); - if (!bio) { - mutex_unlock(&wr_ctx->wr_lock); - return -ENOMEM; - } + bio = btrfs_io_bio_alloc(sctx->pages_per_wr_bio); sbio->bio = bio; } @@ -1951,7 +1938,7 @@ again: if (sbio->page_count < 1) { bio_put(sbio->bio); sbio->bio = NULL; - mutex_unlock(&wr_ctx->wr_lock); + mutex_unlock(&sctx->wr_lock); return -EIO; } scrub_wr_submit(sctx); @@ -1961,23 +1948,22 @@ again: sbio->pagev[sbio->page_count] = spage; scrub_page_get(spage); sbio->page_count++; - if (sbio->page_count == wr_ctx->pages_per_wr_bio) + if (sbio->page_count == sctx->pages_per_wr_bio) scrub_wr_submit(sctx); - mutex_unlock(&wr_ctx->wr_lock); + mutex_unlock(&sctx->wr_lock); return 0; } static void scrub_wr_submit(struct scrub_ctx *sctx) { - struct scrub_wr_ctx *wr_ctx = &sctx->wr_ctx; struct scrub_bio *sbio; - if (!wr_ctx->wr_curr_bio) + if (!sctx->wr_curr_bio) return; - sbio = wr_ctx->wr_curr_bio; - wr_ctx->wr_curr_bio = NULL; + sbio = sctx->wr_curr_bio; + sctx->wr_curr_bio = NULL; WARN_ON(!sbio->bio->bi_bdev); scrub_pending_bio_inc(sctx); /* process all writes in a single worker thread. Then the block layer @@ -2081,7 +2067,7 @@ static int scrub_checksum_data(struct scrub_block *sblock) page = sblock->pagev[0]->page; buffer = kmap_atomic(page); - len = sctx->sectorsize; + len = sctx->fs_info->sectorsize; index = 0; for (;;) { u64 l = min_t(u64, len, PAGE_SIZE); @@ -2146,7 +2132,7 @@ static int scrub_checksum_tree_block(struct scrub_block *sblock) BTRFS_UUID_SIZE)) sblock->header_error = 1; - len = sctx->nodesize - BTRFS_CSUM_SIZE; + len = sctx->fs_info->nodesize - BTRFS_CSUM_SIZE; mapped_size = PAGE_SIZE - BTRFS_CSUM_SIZE; p = ((u8 *)mapped_buffer) + BTRFS_CSUM_SIZE; index = 0; @@ -2329,10 +2315,7 @@ again: sbio->dev = spage->dev; bio = sbio->bio; if (!bio) { - bio = btrfs_io_bio_alloc(GFP_KERNEL, - sctx->pages_per_rd_bio); - if (!bio) - return -ENOMEM; + bio = btrfs_io_bio_alloc(sctx->pages_per_rd_bio); sbio->bio = bio; } @@ -2420,10 +2403,10 @@ static void scrub_missing_raid56_worker(struct btrfs_work *work) scrub_block_put(sblock); if (sctx->is_dev_replace && - atomic_read(&sctx->wr_ctx.flush_all_writes)) { - mutex_lock(&sctx->wr_ctx.wr_lock); + atomic_read(&sctx->flush_all_writes)) { + mutex_lock(&sctx->wr_lock); scrub_wr_submit(sctx); - mutex_unlock(&sctx->wr_ctx.wr_lock); + mutex_unlock(&sctx->wr_lock); } scrub_pending_bio_dec(sctx); @@ -2458,10 +2441,7 @@ static void scrub_missing_raid56_pages(struct scrub_block *sblock) goto bbio_out; } - bio = btrfs_io_bio_alloc(GFP_NOFS, 0); - if (!bio) - goto bbio_out; - + bio = btrfs_io_bio_alloc(0); bio->bi_iter.bi_sector = logical >> 9; bio->bi_private = sblock; bio->bi_end_io = scrub_missing_raid56_end_io; @@ -2628,10 +2608,10 @@ static void scrub_bio_end_io_worker(struct btrfs_work *work) spin_unlock(&sctx->list_lock); if (sctx->is_dev_replace && - atomic_read(&sctx->wr_ctx.flush_all_writes)) { - mutex_lock(&sctx->wr_ctx.wr_lock); + atomic_read(&sctx->flush_all_writes)) { + mutex_lock(&sctx->wr_lock); scrub_wr_submit(sctx); - mutex_unlock(&sctx->wr_ctx.wr_lock); + mutex_unlock(&sctx->wr_lock); } scrub_pending_bio_dec(sctx); @@ -2726,8 +2706,8 @@ static int scrub_find_csum(struct scrub_ctx *sctx, u64 logical, u8 *csum) if (!sum) return 0; - index = ((u32)(logical - sum->bytenr)) / sctx->sectorsize; - num_sectors = sum->len / sctx->sectorsize; + index = ((u32)(logical - sum->bytenr)) / sctx->fs_info->sectorsize; + num_sectors = sum->len / sctx->fs_info->sectorsize; memcpy(csum, sum->sums + index, sctx->csum_size); if (index == num_sectors - 1) { list_del(&sum->list); @@ -2746,19 +2726,19 @@ static int scrub_extent(struct scrub_ctx *sctx, u64 logical, u64 len, u32 blocksize; if (flags & BTRFS_EXTENT_FLAG_DATA) { - blocksize = sctx->sectorsize; + blocksize = sctx->fs_info->sectorsize; spin_lock(&sctx->stat_lock); sctx->stat.data_extents_scrubbed++; sctx->stat.data_bytes_scrubbed += len; spin_unlock(&sctx->stat_lock); } else if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) { - blocksize = sctx->nodesize; + blocksize = sctx->fs_info->nodesize; spin_lock(&sctx->stat_lock); sctx->stat.tree_extents_scrubbed++; sctx->stat.tree_bytes_scrubbed += len; spin_unlock(&sctx->stat_lock); } else { - blocksize = sctx->sectorsize; + blocksize = sctx->fs_info->sectorsize; WARN_ON(1); } @@ -2892,11 +2872,11 @@ static int scrub_extent_for_parity(struct scrub_parity *sparity, } if (flags & BTRFS_EXTENT_FLAG_DATA) { - blocksize = sctx->sectorsize; + blocksize = sctx->fs_info->sectorsize; } else if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) { - blocksize = sctx->nodesize; + blocksize = sctx->fs_info->nodesize; } else { - blocksize = sctx->sectorsize; + blocksize = sctx->fs_info->sectorsize; WARN_ON(1); } @@ -3037,10 +3017,7 @@ static void scrub_parity_check_and_repair(struct scrub_parity *sparity) if (ret || !bbio || !bbio->raid_map) goto bbio_out; - bio = btrfs_io_bio_alloc(GFP_NOFS, 0); - if (!bio) - goto bbio_out; - + bio = btrfs_io_bio_alloc(0); bio->bi_iter.bi_sector = sparity->logic_start >> 9; bio->bi_private = sparity; bio->bi_end_io = scrub_parity_bio_endio; @@ -3305,9 +3282,9 @@ out: logic_end - logic_start); scrub_parity_put(sparity); scrub_submit(sctx); - mutex_lock(&sctx->wr_ctx.wr_lock); + mutex_lock(&sctx->wr_lock); scrub_wr_submit(sctx); - mutex_unlock(&sctx->wr_ctx.wr_lock); + mutex_unlock(&sctx->wr_lock); btrfs_release_path(path); return ret < 0 ? ret : 0; @@ -3463,14 +3440,14 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, */ if (atomic_read(&fs_info->scrub_pause_req)) { /* push queued extents */ - atomic_set(&sctx->wr_ctx.flush_all_writes, 1); + atomic_set(&sctx->flush_all_writes, 1); scrub_submit(sctx); - mutex_lock(&sctx->wr_ctx.wr_lock); + mutex_lock(&sctx->wr_lock); scrub_wr_submit(sctx); - mutex_unlock(&sctx->wr_ctx.wr_lock); + mutex_unlock(&sctx->wr_lock); wait_event(sctx->list_wait, atomic_read(&sctx->bios_in_flight) == 0); - atomic_set(&sctx->wr_ctx.flush_all_writes, 0); + atomic_set(&sctx->flush_all_writes, 0); scrub_blocked_if_needed(fs_info); } @@ -3677,9 +3654,9 @@ skip: out: /* push queued extents */ scrub_submit(sctx); - mutex_lock(&sctx->wr_ctx.wr_lock); + mutex_lock(&sctx->wr_lock); scrub_wr_submit(sctx); - mutex_unlock(&sctx->wr_ctx.wr_lock); + mutex_unlock(&sctx->wr_lock); blk_finish_plug(&plug); btrfs_free_path(path); @@ -3859,7 +3836,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, */ btrfs_wait_block_group_reservations(cache); btrfs_wait_nocow_writers(cache); - ret = btrfs_wait_ordered_roots(fs_info, -1, + ret = btrfs_wait_ordered_roots(fs_info, U64_MAX, cache->key.objectid, cache->key.offset); if (ret > 0) { @@ -3916,11 +3893,11 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, * write requests are really completed when bios_in_flight * changes to 0. */ - atomic_set(&sctx->wr_ctx.flush_all_writes, 1); + atomic_set(&sctx->flush_all_writes, 1); scrub_submit(sctx); - mutex_lock(&sctx->wr_ctx.wr_lock); + mutex_lock(&sctx->wr_lock); scrub_wr_submit(sctx); - mutex_unlock(&sctx->wr_ctx.wr_lock); + mutex_unlock(&sctx->wr_lock); wait_event(sctx->list_wait, atomic_read(&sctx->bios_in_flight) == 0); @@ -3934,7 +3911,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, */ wait_event(sctx->list_wait, atomic_read(&sctx->workers_pending) == 0); - atomic_set(&sctx->wr_ctx.flush_all_writes, 0); + atomic_set(&sctx->flush_all_writes, 0); scrub_pause_off(fs_info); @@ -4337,32 +4314,6 @@ static void scrub_remap_extent(struct btrfs_fs_info *fs_info, btrfs_put_bbio(bbio); } -static int scrub_setup_wr_ctx(struct scrub_wr_ctx *wr_ctx, - struct btrfs_device *dev, - int is_dev_replace) -{ - WARN_ON(wr_ctx->wr_curr_bio != NULL); - - mutex_init(&wr_ctx->wr_lock); - wr_ctx->wr_curr_bio = NULL; - if (!is_dev_replace) - return 0; - - WARN_ON(!dev->bdev); - wr_ctx->pages_per_wr_bio = SCRUB_PAGES_PER_WR_BIO; - wr_ctx->tgtdev = dev; - atomic_set(&wr_ctx->flush_all_writes, 0); - return 0; -} - -static void scrub_free_wr_ctx(struct scrub_wr_ctx *wr_ctx) -{ - mutex_lock(&wr_ctx->wr_lock); - kfree(wr_ctx->wr_curr_bio); - wr_ctx->wr_curr_bio = NULL; - mutex_unlock(&wr_ctx->wr_lock); -} - static int copy_nocow_pages(struct scrub_ctx *sctx, u64 logical, u64 len, int mirror_num, u64 physical_for_dev_replace) { @@ -4665,7 +4616,7 @@ static int write_page_nocow(struct scrub_ctx *sctx, struct btrfs_device *dev; int ret; - dev = sctx->wr_ctx.tgtdev; + dev = sctx->wr_tgtdev; if (!dev) return -EIO; if (!dev->bdev) { @@ -4673,13 +4624,7 @@ static int write_page_nocow(struct scrub_ctx *sctx, "scrub write_page_nocow(bdev == NULL) is unexpected"); return -EIO; } - bio = btrfs_io_bio_alloc(GFP_NOFS, 1); - if (!bio) { - spin_lock(&sctx->stat_lock); - sctx->stat.malloc_errors++; - spin_unlock(&sctx->stat_lock); - return -ENOMEM; - } + bio = btrfs_io_bio_alloc(1); bio->bi_iter.bi_size = 0; bio->bi_iter.bi_sector = physical_for_dev_replace >> 9; bio->bi_bdev = dev->bdev; diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index fc496a6f842a..e937c10b8287 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -1069,6 +1069,12 @@ static int iterate_dir_item(struct btrfs_root *root, struct btrfs_path *path, } } + ret = btrfs_is_name_len_valid(eb, path->slots[0], + (unsigned long)(di + 1), name_len + data_len); + if (!ret) { + ret = -EIO; + goto out; + } if (name_len + data_len > buf_len) { buf_len = name_len + data_len; if (is_vmalloc_addr(buf)) { @@ -1083,7 +1089,7 @@ static int iterate_dir_item(struct btrfs_root *root, struct btrfs_path *path, buf = tmp; } if (!buf) { - buf = vmalloc(buf_len); + buf = kvmalloc(buf_len, GFP_KERNEL); if (!buf) { ret = -ENOMEM; goto out; @@ -2769,15 +2775,20 @@ out: struct recorded_ref { struct list_head list; - char *dir_path; char *name; struct fs_path *full_path; u64 dir; u64 dir_gen; - int dir_path_len; int name_len; }; +static void set_ref_path(struct recorded_ref *ref, struct fs_path *path) +{ + ref->full_path = path; + ref->name = (char *)kbasename(ref->full_path->start); + ref->name_len = ref->full_path->end - ref->name; +} + /* * We need to process new refs before deleted refs, but compare_tree gives us * everything mixed. So we first record all refs and later process them. @@ -2794,17 +2805,7 @@ static int __record_ref(struct list_head *head, u64 dir, ref->dir = dir; ref->dir_gen = dir_gen; - ref->full_path = path; - - ref->name = (char *)kbasename(ref->full_path->start); - ref->name_len = ref->full_path->end - ref->name; - ref->dir_path = ref->full_path->start; - if (ref->name == ref->full_path->start) - ref->dir_path_len = 0; - else - ref->dir_path_len = ref->full_path->end - - ref->full_path->start - 1 - ref->name_len; - + set_ref_path(ref, path); list_add_tail(&ref->list, head); return 0; } @@ -3546,9 +3547,17 @@ static int is_ancestor(struct btrfs_root *root, struct fs_path *fs_path) { u64 ino = ino2; + bool free_path = false; + int ret = 0; + + if (!fs_path) { + fs_path = fs_path_alloc(); + if (!fs_path) + return -ENOMEM; + free_path = true; + } while (ino > BTRFS_FIRST_FREE_OBJECTID) { - int ret; u64 parent; u64 parent_gen; @@ -3557,13 +3566,18 @@ static int is_ancestor(struct btrfs_root *root, if (ret < 0) { if (ret == -ENOENT && ino == ino2) ret = 0; - return ret; + goto out; + } + if (parent == ino1) { + ret = parent_gen == ino1_gen ? 1 : 0; + goto out; } - if (parent == ino1) - return parent_gen == ino1_gen ? 1 : 0; ino = parent; } - return 0; + out: + if (free_path) + fs_path_free(fs_path); + return ret; } static int wait_for_parent_move(struct send_ctx *sctx, @@ -3686,6 +3700,7 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move) int is_orphan = 0; u64 last_dir_ino_rm = 0; bool can_rename = true; + bool orphanized_ancestor = false; btrfs_debug(fs_info, "process_recorded_refs %llu", sctx->cur_ino); @@ -3837,9 +3852,16 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move) * might contain the pre-orphanization name of * ow_inode, which is no longer valid. */ - fs_path_reset(valid_path); - ret = get_cur_path(sctx, sctx->cur_ino, - sctx->cur_inode_gen, valid_path); + ret = is_ancestor(sctx->parent_root, + ow_inode, ow_gen, + sctx->cur_ino, NULL); + if (ret > 0) { + orphanized_ancestor = true; + fs_path_reset(valid_path); + ret = get_cur_path(sctx, sctx->cur_ino, + sctx->cur_inode_gen, + valid_path); + } if (ret < 0) goto out; } else { @@ -3960,6 +3982,43 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move) if (ret < 0) goto out; if (!ret) { + /* + * If we orphanized any ancestor before, we need + * to recompute the full path for deleted names, + * since any such path was computed before we + * processed any references and orphanized any + * ancestor inode. + */ + if (orphanized_ancestor) { + struct fs_path *new_path; + + /* + * Our reference's name member points to + * its full_path member string, so we + * use here a new path. + */ + new_path = fs_path_alloc(); + if (!new_path) { + ret = -ENOMEM; + goto out; + } + ret = get_cur_path(sctx, cur->dir, + cur->dir_gen, + new_path); + if (ret < 0) { + fs_path_free(new_path); + goto out; + } + ret = fs_path_add(new_path, + cur->name, + cur->name_len); + if (ret < 0) { + fs_path_free(new_path); + goto out; + } + fs_path_free(cur->full_path); + set_ref_path(cur, new_path); + } ret = send_unlink(sctx, cur->full_path); if (ret < 0) goto out; @@ -6397,13 +6456,10 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_) alloc_size = sizeof(struct clone_root) * (arg->clone_sources_count + 1); - sctx->clone_roots = kzalloc(alloc_size, GFP_KERNEL | __GFP_NOWARN); + sctx->clone_roots = kzalloc(alloc_size, GFP_KERNEL); if (!sctx->clone_roots) { - sctx->clone_roots = vzalloc(alloc_size); - if (!sctx->clone_roots) { - ret = -ENOMEM; - goto out; - } + ret = -ENOMEM; + goto out; } alloc_size = arg->clone_sources_count * sizeof(*arg->clone_sources); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 4f1cdd5058f1..74e47794e63f 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -601,18 +601,8 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, } break; case Opt_alloc_start: - num = match_strdup(&args[0]); - if (num) { - mutex_lock(&info->chunk_mutex); - info->alloc_start = memparse(num, NULL); - mutex_unlock(&info->chunk_mutex); - kfree(num); - btrfs_info(info, "allocations start at %llu", - info->alloc_start); - } else { - ret = -ENOMEM; - goto out; - } + btrfs_info(info, + "option alloc_start is obsolete, ignored"); break; case Opt_acl: #ifdef CONFIG_BTRFS_FS_POSIX_ACL @@ -1187,7 +1177,7 @@ int btrfs_sync_fs(struct super_block *sb, int wait) return 0; } - btrfs_wait_ordered_roots(fs_info, -1, 0, (u64)-1); + btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1); trans = btrfs_attach_transaction_barrier(root); if (IS_ERR(trans)) { @@ -1232,8 +1222,6 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry) seq_puts(seq, ",nobarrier"); if (info->max_inline != BTRFS_DEFAULT_MAX_INLINE) seq_printf(seq, ",max_inline=%llu", info->max_inline); - if (info->alloc_start != 0) - seq_printf(seq, ",alloc_start=%llu", info->alloc_start); if (info->thread_pool_size != min_t(unsigned long, num_online_cpus() + 2, 8)) seq_printf(seq, ",thread_pool=%d", info->thread_pool_size); @@ -1716,7 +1704,6 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) unsigned long old_opts = fs_info->mount_opt; unsigned long old_compress_type = fs_info->compress_type; u64 old_max_inline = fs_info->max_inline; - u64 old_alloc_start = fs_info->alloc_start; int old_thread_pool_size = fs_info->thread_pool_size; unsigned int old_metadata_ratio = fs_info->metadata_ratio; int ret; @@ -1855,9 +1842,6 @@ restore: fs_info->mount_opt = old_opts; fs_info->compress_type = old_compress_type; fs_info->max_inline = old_max_inline; - mutex_lock(&fs_info->chunk_mutex); - fs_info->alloc_start = old_alloc_start; - mutex_unlock(&fs_info->chunk_mutex); btrfs_resize_thread_pool(fs_info, old_thread_pool_size, fs_info->thread_pool_size); fs_info->metadata_ratio = old_metadata_ratio; @@ -1898,18 +1882,15 @@ static inline void btrfs_descending_sort_devices( static int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info, u64 *free_bytes) { - struct btrfs_root *root = fs_info->tree_root; struct btrfs_device_info *devices_info; struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; struct btrfs_device *device; u64 skip_space; u64 type; u64 avail_space; - u64 used_space; u64 min_stripe_size; int min_stripes = 1, num_stripes = 1; int i = 0, nr_devices; - int ret; /* * We aren't under the device list lock, so this is racy-ish, but good @@ -1927,12 +1908,12 @@ static int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info, } devices_info = kmalloc_array(nr_devices, sizeof(*devices_info), - GFP_NOFS); + GFP_KERNEL); if (!devices_info) return -ENOMEM; /* calc min stripe number for data space allocation */ - type = btrfs_get_alloc_profile(root, 1); + type = btrfs_data_alloc_profile(fs_info); if (type & BTRFS_BLOCK_GROUP_RAID0) { min_stripes = 2; num_stripes = nr_devices; @@ -1949,8 +1930,6 @@ static int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info, else min_stripe_size = BTRFS_STRIPE_LEN; - if (fs_info->alloc_start) - mutex_lock(&fs_devices->device_list_mutex); rcu_read_lock(); list_for_each_entry_rcu(device, &fs_devices->devices, dev_list) { if (!device->in_fs_metadata || !device->bdev || @@ -1973,34 +1952,6 @@ static int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info, */ skip_space = SZ_1M; - /* user can set the offset in fs_info->alloc_start. */ - if (fs_info->alloc_start && - fs_info->alloc_start + BTRFS_STRIPE_LEN <= - device->total_bytes) { - rcu_read_unlock(); - skip_space = max(fs_info->alloc_start, skip_space); - - /* - * btrfs can not use the free space in - * [0, skip_space - 1], we must subtract it from the - * total. In order to implement it, we account the used - * space in this range first. - */ - ret = btrfs_account_dev_extents_size(device, 0, - skip_space - 1, - &used_space); - if (ret) { - kfree(devices_info); - mutex_unlock(&fs_devices->device_list_mutex); - return ret; - } - - rcu_read_lock(); - - /* calc the free space in [0, skip_space - 1] */ - skip_space -= used_space; - } - /* * we can use the free space in [0, skip_space - 1], subtract * it from the total. @@ -2019,8 +1970,6 @@ static int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info, i++; } rcu_read_unlock(); - if (fs_info->alloc_start) - mutex_unlock(&fs_devices->device_list_mutex); nr_devices = i; @@ -2057,10 +2006,9 @@ static int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info, * multiplier to scale the sizes. * * Unused device space usage is based on simulating the chunk allocator - * algorithm that respects the device sizes, order of allocations and the - * 'alloc_start' value, this is a close approximation of the actual use but - * there are other factors that may change the result (like a new metadata - * chunk). + * algorithm that respects the device sizes and order of allocations. This is + * a close approximation of the actual use but there are other factors that may + * change the result (like a new metadata chunk). * * If metadata is exhausted, f_bavail will be 0. */ @@ -2243,7 +2191,7 @@ static int btrfs_freeze(struct super_block *sb) struct btrfs_fs_info *fs_info = btrfs_sb(sb); struct btrfs_root *root = fs_info->tree_root; - fs_info->fs_frozen = 1; + set_bit(BTRFS_FS_FROZEN, &fs_info->flags); /* * We don't need a barrier here, we'll wait for any transaction that * could be in progress on other threads (and do delayed iputs that @@ -2262,7 +2210,9 @@ static int btrfs_freeze(struct super_block *sb) static int btrfs_unfreeze(struct super_block *sb) { - btrfs_sb(sb)->fs_frozen = 0; + struct btrfs_fs_info *fs_info = btrfs_sb(sb); + + clear_bit(BTRFS_FS_FROZEN, &fs_info->flags); return 0; } diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index 1f157fba8940..c2d5f3580b4c 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -447,11 +447,52 @@ static ssize_t btrfs_clone_alignment_show(struct kobject *kobj, BTRFS_ATTR(clone_alignment, btrfs_clone_alignment_show); +static ssize_t quota_override_show(struct kobject *kobj, + struct kobj_attribute *a, char *buf) +{ + struct btrfs_fs_info *fs_info = to_fs_info(kobj); + int quota_override; + + quota_override = test_bit(BTRFS_FS_QUOTA_OVERRIDE, &fs_info->flags); + return snprintf(buf, PAGE_SIZE, "%d\n", quota_override); +} + +static ssize_t quota_override_store(struct kobject *kobj, + struct kobj_attribute *a, + const char *buf, size_t len) +{ + struct btrfs_fs_info *fs_info = to_fs_info(kobj); + unsigned long knob; + int err; + + if (!fs_info) + return -EPERM; + + if (!capable(CAP_SYS_RESOURCE)) + return -EPERM; + + err = kstrtoul(buf, 10, &knob); + if (err) + return err; + if (knob > 1) + return -EINVAL; + + if (knob) + set_bit(BTRFS_FS_QUOTA_OVERRIDE, &fs_info->flags); + else + clear_bit(BTRFS_FS_QUOTA_OVERRIDE, &fs_info->flags); + + return len; +} + +BTRFS_ATTR_RW(quota_override, quota_override_show, quota_override_store); + static const struct attribute *btrfs_attrs[] = { BTRFS_ATTR_PTR(label), BTRFS_ATTR_PTR(nodesize), BTRFS_ATTR_PTR(sectorsize), BTRFS_ATTR_PTR(clone_alignment), + BTRFS_ATTR_PTR(quota_override), NULL, }; diff --git a/fs/btrfs/tests/extent-io-tests.c b/fs/btrfs/tests/extent-io-tests.c index 133753232a94..d06b1c931d05 100644 --- a/fs/btrfs/tests/extent-io-tests.c +++ b/fs/btrfs/tests/extent-io-tests.c @@ -87,7 +87,7 @@ static int test_find_delalloc(u32 sectorsize) return -ENOMEM; } - extent_io_tree_init(&tmp, &inode->i_data); + extent_io_tree_init(&tmp, inode); /* * First go through and create and mark all of our pages dirty, we pin diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 2168654c90a1..f615d59b0489 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -93,7 +93,7 @@ void btrfs_put_transaction(struct btrfs_transaction *transaction) btrfs_put_block_group_trimming(cache); btrfs_put_block_group(cache); } - kmem_cache_free(btrfs_transaction_cachep, transaction); + kfree(transaction); } } @@ -228,7 +228,7 @@ loop: */ BUG_ON(type == TRANS_JOIN_NOLOCK); - cur_trans = kmem_cache_alloc(btrfs_transaction_cachep, GFP_NOFS); + cur_trans = kmalloc(sizeof(*cur_trans), GFP_NOFS); if (!cur_trans) return -ENOMEM; @@ -238,11 +238,11 @@ loop: * someone started a transaction after we unlocked. Make sure * to redo the checks above */ - kmem_cache_free(btrfs_transaction_cachep, cur_trans); + kfree(cur_trans); goto loop; } else if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) { spin_unlock(&fs_info->trans_lock); - kmem_cache_free(btrfs_transaction_cachep, cur_trans); + kfree(cur_trans); return -EROFS; } @@ -294,7 +294,7 @@ loop: spin_lock_init(&cur_trans->dropped_roots_lock); list_add_tail(&cur_trans->list, &fs_info->trans_list); extent_io_tree_init(&cur_trans->dirty_pages, - fs_info->btree_inode->i_mapping); + fs_info->btree_inode); fs_info->generation++; cur_trans->transid = fs_info->generation; fs_info->running_transaction = cur_trans; @@ -1374,9 +1374,6 @@ static int qgroup_account_snapshot(struct btrfs_trans_handle *trans, ret = commit_fs_roots(trans, fs_info); if (ret) goto out; - ret = btrfs_qgroup_prepare_account_extents(trans, fs_info); - if (ret < 0) - goto out; ret = btrfs_qgroup_account_extents(trans, fs_info); if (ret < 0) goto out; @@ -1926,7 +1923,7 @@ static inline int btrfs_start_delalloc_flush(struct btrfs_fs_info *fs_info) static inline void btrfs_wait_delalloc_flush(struct btrfs_fs_info *fs_info) { if (btrfs_test_opt(fs_info, FLUSHONCOMMIT)) - btrfs_wait_ordered_roots(fs_info, -1, 0, (u64)-1); + btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1); } static inline void @@ -2180,13 +2177,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) goto scrub_continue; } - ret = btrfs_qgroup_prepare_account_extents(trans, fs_info); - if (ret) { - mutex_unlock(&fs_info->tree_log_mutex); - mutex_unlock(&fs_info->reloc_mutex); - goto scrub_continue; - } - /* * Since fs roots are all committed, we can get a quite accurate * new_roots. So let's do quota accounting. @@ -2314,7 +2304,8 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) * it'll result in deadlock about SB_FREEZE_FS. */ if (current != fs_info->transaction_kthread && - current != fs_info->cleaner_kthread && !fs_info->fs_frozen) + current != fs_info->cleaner_kthread && + !test_bit(BTRFS_FS_FROZEN, &fs_info->flags)) btrfs_run_delayed_iputs(fs_info); return ret; diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index ccfe9fe7754a..f20ef211a73d 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -1175,15 +1175,19 @@ next: return 0; } -static int extref_get_fields(struct extent_buffer *eb, unsigned long ref_ptr, - u32 *namelen, char **name, u64 *index, - u64 *parent_objectid) +static int extref_get_fields(struct extent_buffer *eb, int slot, + unsigned long ref_ptr, u32 *namelen, char **name, + u64 *index, u64 *parent_objectid) { struct btrfs_inode_extref *extref; extref = (struct btrfs_inode_extref *)ref_ptr; *namelen = btrfs_inode_extref_name_len(eb, extref); + if (!btrfs_is_name_len_valid(eb, slot, (unsigned long)&extref->name, + *namelen)) + return -EIO; + *name = kmalloc(*namelen, GFP_NOFS); if (*name == NULL) return -ENOMEM; @@ -1198,14 +1202,19 @@ static int extref_get_fields(struct extent_buffer *eb, unsigned long ref_ptr, return 0; } -static int ref_get_fields(struct extent_buffer *eb, unsigned long ref_ptr, - u32 *namelen, char **name, u64 *index) +static int ref_get_fields(struct extent_buffer *eb, int slot, + unsigned long ref_ptr, u32 *namelen, char **name, + u64 *index) { struct btrfs_inode_ref *ref; ref = (struct btrfs_inode_ref *)ref_ptr; *namelen = btrfs_inode_ref_name_len(eb, ref); + if (!btrfs_is_name_len_valid(eb, slot, (unsigned long)(ref + 1), + *namelen)) + return -EIO; + *name = kmalloc(*namelen, GFP_NOFS); if (*name == NULL) return -ENOMEM; @@ -1280,8 +1289,8 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans, while (ref_ptr < ref_end) { if (log_ref_ver) { - ret = extref_get_fields(eb, ref_ptr, &namelen, &name, - &ref_index, &parent_objectid); + ret = extref_get_fields(eb, slot, ref_ptr, &namelen, + &name, &ref_index, &parent_objectid); /* * parent object can change from one array * item to another. @@ -1293,8 +1302,8 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans, goto out; } } else { - ret = ref_get_fields(eb, ref_ptr, &namelen, &name, - &ref_index); + ret = ref_get_fields(eb, slot, ref_ptr, &namelen, + &name, &ref_index); } if (ret) goto out; @@ -1841,7 +1850,7 @@ static noinline int replay_one_dir_item(struct btrfs_trans_handle *trans, ptr_end = ptr + item_size; while (ptr < ptr_end) { di = (struct btrfs_dir_item *)ptr; - if (verify_dir_item(fs_info, eb, di)) + if (verify_dir_item(fs_info, eb, slot, di)) return -EIO; name_len = btrfs_dir_name_len(eb, di); ret = replay_one_name(trans, root, path, eb, di, key); @@ -2017,7 +2026,7 @@ again: ptr_end = ptr + item_size; while (ptr < ptr_end) { di = (struct btrfs_dir_item *)ptr; - if (verify_dir_item(fs_info, eb, di)) { + if (verify_dir_item(fs_info, eb, slot, di)) { ret = -EIO; goto out; } @@ -2102,6 +2111,7 @@ static int replay_xattr_deletes(struct btrfs_trans_handle *trans, struct btrfs_path *path, const u64 ino) { + struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_key search_key; struct btrfs_path *log_path; int i; @@ -2143,6 +2153,12 @@ process_leaf: u32 this_len = sizeof(*di) + name_len + data_len; char *name; + ret = verify_dir_item(fs_info, path->nodes[0], + path->slots[0], di); + if (ret) { + ret = -EIO; + goto out; + } name = kmalloc(name_len, GFP_NOFS); if (!name) { ret = -ENOMEM; @@ -4546,6 +4562,12 @@ static int btrfs_check_ref_name_override(struct extent_buffer *eb, this_len = sizeof(*extref) + this_name_len; } + ret = btrfs_is_name_len_valid(eb, slot, name_ptr, + this_name_len); + if (!ret) { + ret = -EIO; + goto out; + } if (this_name_len > name_len) { char *new_name; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 84a495967e0a..5eb7217738ed 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -242,6 +242,17 @@ static struct btrfs_device *__alloc_device(void) if (!dev) return ERR_PTR(-ENOMEM); + /* + * Preallocate a bio that's always going to be used for flushing device + * barriers and matches the device lifespan + */ + dev->flush_bio = bio_alloc_bioset(GFP_KERNEL, 0, NULL); + if (!dev->flush_bio) { + kfree(dev); + return ERR_PTR(-ENOMEM); + } + bio_get(dev->flush_bio); + INIT_LIST_HEAD(&dev->dev_list); INIT_LIST_HEAD(&dev->dev_alloc_list); INIT_LIST_HEAD(&dev->resized_list); @@ -838,6 +849,7 @@ static void __free_device(struct work_struct *work) device = container_of(work, struct btrfs_device, rcu_work); rcu_string_free(device->name); + bio_put(device->flush_bio); kfree(device); } @@ -1353,15 +1365,13 @@ int find_free_dev_extent_start(struct btrfs_transaction *transaction, int ret; int slot; struct extent_buffer *l; - u64 min_search_start; /* * We don't want to overwrite the superblock on the drive nor any area * used by the boot loader (grub for example), so we make sure to start * at an offset of at least 1MB. */ - min_search_start = max(fs_info->alloc_start, 1024ull * 1024); - search_start = max(search_start, min_search_start); + search_start = max_t(u64, search_start, SZ_1M); path = btrfs_alloc_path(); if (!path) @@ -2387,7 +2397,8 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path device->io_width = fs_info->sectorsize; device->io_align = fs_info->sectorsize; device->sector_size = fs_info->sectorsize; - device->total_bytes = i_size_read(bdev->bd_inode); + device->total_bytes = round_down(i_size_read(bdev->bd_inode), + fs_info->sectorsize); device->disk_total_bytes = device->total_bytes; device->commit_total_bytes = device->total_bytes; device->fs_info = fs_info; @@ -2417,16 +2428,14 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path fs_info->fs_devices->total_devices++; fs_info->fs_devices->total_rw_bytes += device->total_bytes; - spin_lock(&fs_info->free_chunk_lock); - fs_info->free_chunk_space += device->total_bytes; - spin_unlock(&fs_info->free_chunk_lock); + atomic64_add(device->total_bytes, &fs_info->free_chunk_space); if (!blk_queue_nonrot(q)) fs_info->fs_devices->rotating = 1; tmp = btrfs_super_total_bytes(fs_info->super_copy); btrfs_set_super_total_bytes(fs_info->super_copy, - tmp + device->total_bytes); + round_down(tmp + device->total_bytes, fs_info->sectorsize)); tmp = btrfs_super_num_devices(fs_info->super_copy); btrfs_set_super_num_devices(fs_info->super_copy, tmp + 1); @@ -2574,7 +2583,7 @@ int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, goto error; } - name = rcu_string_strdup(device_path, GFP_NOFS); + name = rcu_string_strdup(device_path, GFP_KERNEL); if (!name) { kfree(device); ret = -ENOMEM; @@ -2689,6 +2698,8 @@ int btrfs_grow_device(struct btrfs_trans_handle *trans, if (!device->writeable) return -EACCES; + new_size = round_down(new_size, fs_info->sectorsize); + mutex_lock(&fs_info->chunk_mutex); old_total = btrfs_super_total_bytes(super_copy); diff = new_size - device->total_bytes; @@ -2701,7 +2712,8 @@ int btrfs_grow_device(struct btrfs_trans_handle *trans, fs_devices = fs_info->fs_devices; - btrfs_set_super_total_bytes(super_copy, old_total + diff); + btrfs_set_super_total_bytes(super_copy, + round_down(old_total + diff, fs_info->sectorsize)); device->fs_devices->total_rw_bytes += diff; btrfs_device_set_total_bytes(device, new_size); @@ -2874,9 +2886,7 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans, mutex_lock(&fs_info->chunk_mutex); btrfs_device_set_bytes_used(device, device->bytes_used - dev_extent_len); - spin_lock(&fs_info->free_chunk_lock); - fs_info->free_chunk_space += dev_extent_len; - spin_unlock(&fs_info->free_chunk_lock); + atomic64_add(dev_extent_len, &fs_info->free_chunk_space); btrfs_clear_space_info_full(fs_info); mutex_unlock(&fs_info->chunk_mutex); } @@ -4393,7 +4403,10 @@ int btrfs_shrink_device(struct btrfs_device *device, u64 new_size) struct btrfs_super_block *super_copy = fs_info->super_copy; u64 old_total = btrfs_super_total_bytes(super_copy); u64 old_size = btrfs_device_get_total_bytes(device); - u64 diff = old_size - new_size; + u64 diff; + + new_size = round_down(new_size, fs_info->sectorsize); + diff = old_size - new_size; if (device->is_tgtdev_for_dev_replace) return -EINVAL; @@ -4409,9 +4422,7 @@ int btrfs_shrink_device(struct btrfs_device *device, u64 new_size) btrfs_device_set_total_bytes(device, new_size); if (device->writeable) { device->fs_devices->total_rw_bytes -= diff; - spin_lock(&fs_info->free_chunk_lock); - fs_info->free_chunk_space -= diff; - spin_unlock(&fs_info->free_chunk_lock); + atomic64_sub(diff, &fs_info->free_chunk_space); } mutex_unlock(&fs_info->chunk_mutex); @@ -4522,7 +4533,8 @@ again: &fs_info->fs_devices->resized_devices); WARN_ON(diff > old_total); - btrfs_set_super_total_bytes(super_copy, old_total - diff); + btrfs_set_super_total_bytes(super_copy, + round_down(old_total - diff, fs_info->sectorsize)); mutex_unlock(&fs_info->chunk_mutex); /* Now btrfs_update_device() will change the on-disk size. */ @@ -4535,9 +4547,7 @@ done: btrfs_device_set_total_bytes(device, old_size); if (device->writeable) device->fs_devices->total_rw_bytes += diff; - spin_lock(&fs_info->free_chunk_lock); - fs_info->free_chunk_space += diff; - spin_unlock(&fs_info->free_chunk_lock); + atomic64_add(diff, &fs_info->free_chunk_space); mutex_unlock(&fs_info->chunk_mutex); } return ret; @@ -4882,9 +4892,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, btrfs_device_set_bytes_used(map->stripes[i].dev, num_bytes); } - spin_lock(&info->free_chunk_lock); - info->free_chunk_space -= (stripe_size * map->num_stripes); - spin_unlock(&info->free_chunk_lock); + atomic64_sub(stripe_size * map->num_stripes, &info->free_chunk_space); free_extent_map(em); check_raid56_incompat_flag(info, type); @@ -5029,20 +5037,19 @@ int btrfs_alloc_chunk(struct btrfs_trans_handle *trans, static noinline int init_first_rw_device(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info) { - struct btrfs_root *extent_root = fs_info->extent_root; u64 chunk_offset; u64 sys_chunk_offset; u64 alloc_profile; int ret; chunk_offset = find_next_chunk(fs_info); - alloc_profile = btrfs_get_alloc_profile(extent_root, 0); + alloc_profile = btrfs_metadata_alloc_profile(fs_info); ret = __btrfs_alloc_chunk(trans, chunk_offset, alloc_profile); if (ret) return ret; sys_chunk_offset = find_next_chunk(fs_info); - alloc_profile = btrfs_get_alloc_profile(fs_info->chunk_root, 0); + alloc_profile = btrfs_system_alloc_profile(fs_info); ret = __btrfs_alloc_chunk(trans, sys_chunk_offset, alloc_profile); return ret; } @@ -6267,10 +6274,9 @@ int btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio, continue; } - if (dev_nr < total_devs - 1) { - bio = btrfs_bio_clone(first_bio, GFP_NOFS); - BUG_ON(!bio); /* -ENOMEM */ - } else + if (dev_nr < total_devs - 1) + bio = btrfs_bio_clone(first_bio); + else bio = first_bio; submit_stripe_bio(bbio, bio, bbio->stripes[dev_nr].physical, @@ -6685,10 +6691,8 @@ static int read_one_dev(struct btrfs_fs_info *fs_info, device->in_fs_metadata = 1; if (device->writeable && !device->is_tgtdev_for_dev_replace) { device->fs_devices->total_rw_bytes += device->total_bytes; - spin_lock(&fs_info->free_chunk_lock); - fs_info->free_chunk_space += device->total_bytes - - device->bytes_used; - spin_unlock(&fs_info->free_chunk_lock); + atomic64_add(device->total_bytes - device->bytes_used, + &fs_info->free_chunk_space); } ret = 0; return ret; diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index c7d0fbc915ca..6f45fd60d15a 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -74,6 +74,8 @@ struct btrfs_device { int missing; int can_discard; int is_tgtdev_for_dev_replace; + int last_flush_error; + int flush_bio_sent; #ifdef __BTRFS_NEED_DEVICE_DATA_ORDERED seqcount_t data_seqcount; @@ -279,6 +281,11 @@ struct btrfs_io_bio { u8 csum_inline[BTRFS_BIO_INLINE_CSUM_SIZE]; u8 *csum_allocated; btrfs_io_bio_end_io_t *end_io; + struct bvec_iter iter; + /* + * This member must come last, bio_alloc_bioset will allocate enough + * bytes for entire btrfs_io_bio but relies on bio being last. + */ struct bio bio; }; diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index b3cbf80c5acf..2c7e53f9ff1b 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -336,7 +336,7 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size) u32 this_len = sizeof(*di) + name_len + data_len; unsigned long name_ptr = (unsigned long)(di + 1); - if (verify_dir_item(fs_info, leaf, di)) { + if (verify_dir_item(fs_info, leaf, slot, di)) { ret = -EIO; goto err; } diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c index 135b10823c6d..c248f9286366 100644 --- a/fs/btrfs/zlib.c +++ b/fs/btrfs/zlib.c @@ -24,12 +24,13 @@ #include <linux/slab.h> #include <linux/zlib.h> #include <linux/zutil.h> -#include <linux/vmalloc.h> +#include <linux/mm.h> #include <linux/init.h> #include <linux/err.h> #include <linux/sched.h> #include <linux/pagemap.h> #include <linux/bio.h> +#include <linux/refcount.h> #include "compression.h" struct workspace { @@ -42,7 +43,7 @@ static void zlib_free_workspace(struct list_head *ws) { struct workspace *workspace = list_entry(ws, struct workspace, list); - vfree(workspace->strm.workspace); + kvfree(workspace->strm.workspace); kfree(workspace->buf); kfree(workspace); } @@ -52,14 +53,14 @@ static struct list_head *zlib_alloc_workspace(void) struct workspace *workspace; int workspacesize; - workspace = kzalloc(sizeof(*workspace), GFP_NOFS); + workspace = kzalloc(sizeof(*workspace), GFP_KERNEL); if (!workspace) return ERR_PTR(-ENOMEM); workspacesize = max(zlib_deflate_workspacesize(MAX_WBITS, MAX_MEM_LEVEL), zlib_inflate_workspacesize()); - workspace->strm.workspace = vmalloc(workspacesize); - workspace->buf = kmalloc(PAGE_SIZE, GFP_NOFS); + workspace->strm.workspace = kvmalloc(workspacesize, GFP_KERNEL); + workspace->buf = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!workspace->strm.workspace || !workspace->buf) goto fail; @@ -211,10 +212,7 @@ out: return ret; } -static int zlib_decompress_bio(struct list_head *ws, struct page **pages_in, - u64 disk_start, - struct bio *orig_bio, - size_t srclen) +static int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb) { struct workspace *workspace = list_entry(ws, struct workspace, list); int ret = 0, ret2; @@ -222,8 +220,12 @@ static int zlib_decompress_bio(struct list_head *ws, struct page **pages_in, char *data_in; size_t total_out = 0; unsigned long page_in_index = 0; + size_t srclen = cb->compressed_len; unsigned long total_pages_in = DIV_ROUND_UP(srclen, PAGE_SIZE); unsigned long buf_start; + struct page **pages_in = cb->compressed_pages; + u64 disk_start = cb->start; + struct bio *orig_bio = cb->orig_bio; data_in = kmap(pages_in[page_in_index]); workspace->strm.next_in = data_in; diff --git a/fs/buffer.c b/fs/buffer.c index 5c2cba8d2387..233e2983c5db 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -178,7 +178,7 @@ void end_buffer_write_sync(struct buffer_head *bh, int uptodate) set_buffer_uptodate(bh); } else { buffer_io_error(bh, ", lost sync page write"); - set_buffer_write_io_error(bh); + mark_buffer_write_io_error(bh); clear_buffer_uptodate(bh); } unlock_buffer(bh); @@ -352,8 +352,7 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate) set_buffer_uptodate(bh); } else { buffer_io_error(bh, ", lost async page write"); - mapping_set_error(page->mapping, -EIO); - set_buffer_write_io_error(bh); + mark_buffer_write_io_error(bh); clear_buffer_uptodate(bh); SetPageError(page); } @@ -481,8 +480,6 @@ static void __remove_assoc_queue(struct buffer_head *bh) { list_del_init(&bh->b_assoc_buffers); WARN_ON(!bh->b_assoc_map); - if (buffer_write_io_error(bh)) - set_bit(AS_EIO, &bh->b_assoc_map->flags); bh->b_assoc_map = NULL; } @@ -1181,6 +1178,17 @@ void mark_buffer_dirty(struct buffer_head *bh) } EXPORT_SYMBOL(mark_buffer_dirty); +void mark_buffer_write_io_error(struct buffer_head *bh) +{ + set_buffer_write_io_error(bh); + /* FIXME: do we need to set this in both places? */ + if (bh->b_page && bh->b_page->mapping) + mapping_set_error(bh->b_page->mapping, -EIO); + if (bh->b_assoc_map) + mapping_set_error(bh->b_assoc_map, -EIO); +} +EXPORT_SYMBOL(mark_buffer_write_io_error); + /* * Decrement a buffer_head's reference count. If all buffers against a page * have zero reference count, are clean and unlocked, and if the page is clean @@ -3023,11 +3031,11 @@ EXPORT_SYMBOL(block_write_full_page); sector_t generic_block_bmap(struct address_space *mapping, sector_t block, get_block_t *get_block) { - struct buffer_head tmp; struct inode *inode = mapping->host; - tmp.b_state = 0; - tmp.b_blocknr = 0; - tmp.b_size = i_blocksize(inode); + struct buffer_head tmp = { + .b_size = i_blocksize(inode), + }; + get_block(inode, block, &tmp, 0); return tmp.b_blocknr; } @@ -3282,8 +3290,6 @@ drop_buffers(struct page *page, struct buffer_head **buffers_to_free) bh = head; do { - if (buffer_write_io_error(bh) && page->mapping) - mapping_set_error(page->mapping, -EIO); if (buffer_busy(bh)) goto failed; bh = bh->b_this_page; diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig index 034f00f21390..afeefe79c25e 100644 --- a/fs/cifs/Kconfig +++ b/fs/cifs/Kconfig @@ -146,6 +146,15 @@ config CIFS_DEBUG2 option can be turned off unless you are debugging cifs problems. If unsure, say N. +config CIFS_DEBUG_DUMP_KEYS + bool "Dump encryption keys for offline decryption (Unsafe)" + depends on CIFS_DEBUG && CIFS_SMB2 + help + Enabling this will dump the encryption and decryption keys + used to communicate on an encrypted share connection on the + console. This allows Wireshark to decrypt and dissect + encrypted network captures. Enable this carefully. + config CIFS_DFS_UPCALL bool "DFS feature support" depends on CIFS && KEYS diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c index a0b3e7d1be48..e0445e2075b2 100644 --- a/fs/cifs/cifs_unicode.c +++ b/fs/cifs/cifs_unicode.c @@ -79,6 +79,10 @@ convert_sfu_char(const __u16 src_char, char *target) static bool convert_sfm_char(const __u16 src_char, char *target) { + if (src_char >= 0xF001 && src_char <= 0xF01F) { + *target = src_char - 0xF000; + return true; + } switch (src_char) { case SFM_COLON: *target = ':'; @@ -417,6 +421,10 @@ static __le16 convert_to_sfm_char(char src_char, bool end_of_string) { __le16 dest_char; + if (src_char >= 0x01 && src_char <= 0x1F) { + dest_char = cpu_to_le16(src_char + 0xF000); + return dest_char; + } switch (src_char) { case ':': dest_char = cpu_to_le16(SFM_COLON); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index fcef70602b27..bc09df6b473a 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -2234,14 +2234,16 @@ cifs_writepage_locked(struct page *page, struct writeback_control *wbc) set_page_writeback(page); retry_write: rc = cifs_partialpagewrite(page, 0, PAGE_SIZE); - if (rc == -EAGAIN && wbc->sync_mode == WB_SYNC_ALL) - goto retry_write; - else if (rc == -EAGAIN) + if (rc == -EAGAIN) { + if (wbc->sync_mode == WB_SYNC_ALL) + goto retry_write; redirty_page_for_writepage(wbc, page); - else if (rc != 0) + } else if (rc != 0) { SetPageError(page); - else + mapping_set_error(page->mapping, rc); + } else { SetPageUptodate(page); + } end_page_writeback(page); put_page(page); free_xid(xid); @@ -2810,12 +2812,12 @@ cifs_writev(struct kiocb *iocb, struct iov_iter *from) struct TCP_Server_Info *server = tlink_tcon(cfile->tlink)->ses->server; ssize_t rc; + inode_lock(inode); /* * We need to hold the sem to be sure nobody modifies lock list * with a brlock that prevents writing. */ down_read(&cinode->lock_sem); - inode_lock(inode); rc = generic_write_checks(iocb, from); if (rc <= 0) @@ -2828,11 +2830,11 @@ cifs_writev(struct kiocb *iocb, struct iov_iter *from) else rc = -EACCES; out: + up_read(&cinode->lock_sem); inode_unlock(inode); if (rc > 0) rc = generic_write_sync(iocb, rc); - up_read(&cinode->lock_sem); return rc; } diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 7e48561abd29..ccbb397debbc 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -1288,6 +1288,108 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon, return rc; } +#ifdef CONFIG_CIFS_ACL +static struct cifs_ntsd * +get_smb2_acl_by_fid(struct cifs_sb_info *cifs_sb, + const struct cifs_fid *cifsfid, u32 *pacllen) +{ + struct cifs_ntsd *pntsd = NULL; + unsigned int xid; + int rc = -EOPNOTSUPP; + struct tcon_link *tlink = cifs_sb_tlink(cifs_sb); + + if (IS_ERR(tlink)) + return ERR_CAST(tlink); + + xid = get_xid(); + cifs_dbg(FYI, "trying to get acl\n"); + + rc = SMB2_query_acl(xid, tlink_tcon(tlink), cifsfid->persistent_fid, + cifsfid->volatile_fid, (void **)&pntsd, pacllen); + free_xid(xid); + + cifs_put_tlink(tlink); + + cifs_dbg(FYI, "%s: rc = %d ACL len %d\n", __func__, rc, *pacllen); + if (rc) + return ERR_PTR(rc); + return pntsd; + +} + +static struct cifs_ntsd * +get_smb2_acl_by_path(struct cifs_sb_info *cifs_sb, + const char *path, u32 *pacllen) +{ + struct cifs_ntsd *pntsd = NULL; + u8 oplock = SMB2_OPLOCK_LEVEL_NONE; + unsigned int xid; + int rc; + struct cifs_tcon *tcon; + struct tcon_link *tlink = cifs_sb_tlink(cifs_sb); + struct cifs_fid fid; + struct cifs_open_parms oparms; + __le16 *utf16_path; + + cifs_dbg(FYI, "get smb3 acl for path %s\n", path); + if (IS_ERR(tlink)) + return ERR_CAST(tlink); + + tcon = tlink_tcon(tlink); + xid = get_xid(); + + if (backup_cred(cifs_sb)) + oparms.create_options = CREATE_OPEN_BACKUP_INTENT; + else + oparms.create_options = 0; + + utf16_path = cifs_convert_path_to_utf16(path, cifs_sb); + if (!utf16_path) + return ERR_PTR(-ENOMEM); + + oparms.tcon = tcon; + oparms.desired_access = READ_CONTROL; + oparms.disposition = FILE_OPEN; + oparms.fid = &fid; + oparms.reconnect = false; + + rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL); + kfree(utf16_path); + if (!rc) { + rc = SMB2_query_acl(xid, tlink_tcon(tlink), fid.persistent_fid, + fid.volatile_fid, (void **)&pntsd, pacllen); + SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); + } + + cifs_put_tlink(tlink); + free_xid(xid); + + cifs_dbg(FYI, "%s: rc = %d ACL len %d\n", __func__, rc, *pacllen); + if (rc) + return ERR_PTR(rc); + return pntsd; +} + +/* Retrieve an ACL from the server */ +static struct cifs_ntsd * +get_smb2_acl(struct cifs_sb_info *cifs_sb, + struct inode *inode, const char *path, + u32 *pacllen) +{ + struct cifs_ntsd *pntsd = NULL; + struct cifsFileInfo *open_file = NULL; + + if (inode) + open_file = find_readable_file(CIFS_I(inode), true); + if (!open_file) + return get_smb2_acl_by_path(cifs_sb, path, pacllen); + + pntsd = get_smb2_acl_by_fid(cifs_sb, &open_file->fid, pacllen); + cifsFileInfo_put(open_file); + return pntsd; +} +#endif + static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, loff_t offset, loff_t len, bool keep_size) { @@ -2393,6 +2495,11 @@ struct smb_version_operations smb20_operations = { .dir_needs_close = smb2_dir_needs_close, .get_dfs_refer = smb2_get_dfs_refer, .select_sectype = smb2_select_sectype, +#ifdef CONFIG_CIFS_ACL + .get_acl = get_smb2_acl, + .get_acl_by_fid = get_smb2_acl_by_fid, +/* .set_acl = set_smb3_acl, */ +#endif /* CIFS_ACL */ }; struct smb_version_operations smb21_operations = { @@ -2477,6 +2584,11 @@ struct smb_version_operations smb21_operations = { .enum_snapshots = smb3_enum_snapshots, .get_dfs_refer = smb2_get_dfs_refer, .select_sectype = smb2_select_sectype, +#ifdef CONFIG_CIFS_ACL + .get_acl = get_smb2_acl, + .get_acl_by_fid = get_smb2_acl_by_fid, +/* .set_acl = set_smb3_acl, */ +#endif /* CIFS_ACL */ }; struct smb_version_operations smb30_operations = { @@ -2571,6 +2683,11 @@ struct smb_version_operations smb30_operations = { .receive_transform = smb3_receive_transform, .get_dfs_refer = smb2_get_dfs_refer, .select_sectype = smb2_select_sectype, +#ifdef CONFIG_CIFS_ACL + .get_acl = get_smb2_acl, + .get_acl_by_fid = get_smb2_acl_by_fid, +/* .set_acl = set_smb3_acl, */ +#endif /* CIFS_ACL */ }; #ifdef CONFIG_CIFS_SMB311 @@ -2753,7 +2870,7 @@ struct smb_version_values smb302_values = { struct smb_version_values smb311_values = { .version_string = SMB311_VERSION_STRING, .protocol_id = SMB311_PROT_ID, - .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES, + .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION, .large_lock_type = 0, .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK, .shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK, diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index e4afdaae743f..4938e8b6d32f 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -2081,8 +2081,9 @@ validate_and_copy_buf(unsigned int offset, unsigned int buffer_length, static int query_info(const unsigned int xid, struct cifs_tcon *tcon, - u64 persistent_fid, u64 volatile_fid, u8 info_class, - size_t output_len, size_t min_len, void *data) + u64 persistent_fid, u64 volatile_fid, u8 info_class, u8 info_type, + u32 additional_info, size_t output_len, size_t min_len, void **data, + u32 *dlen) { struct smb2_query_info_req *req; struct smb2_query_info_rsp *rsp = NULL; @@ -2108,10 +2109,11 @@ query_info(const unsigned int xid, struct cifs_tcon *tcon, if (encryption_required(tcon)) flags |= CIFS_TRANSFORM_REQ; - req->InfoType = SMB2_O_INFO_FILE; + req->InfoType = info_type; req->FileInfoClass = info_class; req->PersistentFileId = persistent_fid; req->VolatileFileId = volatile_fid; + req->AdditionalInformation = cpu_to_le32(additional_info); /* 4 for rfc1002 length field and 1 for Buffer */ req->InputBufferOffset = cpu_to_le16(sizeof(struct smb2_query_info_req) - 1 - 4); @@ -2130,24 +2132,51 @@ query_info(const unsigned int xid, struct cifs_tcon *tcon, goto qinf_exit; } + if (dlen) { + *dlen = le32_to_cpu(rsp->OutputBufferLength); + if (!*data) { + *data = kmalloc(*dlen, GFP_KERNEL); + if (!*data) { + cifs_dbg(VFS, + "Error %d allocating memory for acl\n", + rc); + *dlen = 0; + goto qinf_exit; + } + } + } + rc = validate_and_copy_buf(le16_to_cpu(rsp->OutputBufferOffset), le32_to_cpu(rsp->OutputBufferLength), - &rsp->hdr, min_len, data); + &rsp->hdr, min_len, *data); qinf_exit: free_rsp_buf(resp_buftype, rsp); return rc; } +int SMB2_query_info(const unsigned int xid, struct cifs_tcon *tcon, + u64 persistent_fid, u64 volatile_fid, struct smb2_file_all_info *data) +{ + return query_info(xid, tcon, persistent_fid, volatile_fid, + FILE_ALL_INFORMATION, SMB2_O_INFO_FILE, 0, + sizeof(struct smb2_file_all_info) + PATH_MAX * 2, + sizeof(struct smb2_file_all_info), (void **)&data, + NULL); +} + int -SMB2_query_info(const unsigned int xid, struct cifs_tcon *tcon, +SMB2_query_acl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, - struct smb2_file_all_info *data) + void **data, u32 *plen) { + __u32 additional_info = OWNER_SECINFO | GROUP_SECINFO | DACL_SECINFO; + *plen = 0; + return query_info(xid, tcon, persistent_fid, volatile_fid, - FILE_ALL_INFORMATION, - sizeof(struct smb2_file_all_info) + PATH_MAX * 2, - sizeof(struct smb2_file_all_info), data); + 0, SMB2_O_INFO_SECURITY, additional_info, + SMB2_MAX_BUFFER_SIZE, + sizeof(struct smb2_file_all_info), data, plen); } int @@ -2155,9 +2184,10 @@ SMB2_get_srv_num(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, __le64 *uniqueid) { return query_info(xid, tcon, persistent_fid, volatile_fid, - FILE_INTERNAL_INFORMATION, + FILE_INTERNAL_INFORMATION, SMB2_O_INFO_FILE, 0, + sizeof(struct smb2_file_internal_info), sizeof(struct smb2_file_internal_info), - sizeof(struct smb2_file_internal_info), uniqueid); + (void **)&uniqueid, NULL); } /* diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index 6853454fc871..3595cd755147 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -135,6 +135,9 @@ extern int SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon, extern int SMB2_query_info(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_file_id, u64 volatile_file_id, struct smb2_file_all_info *data); +extern int SMB2_query_acl(const unsigned int xid, struct cifs_tcon *tcon, + u64 persistent_file_id, u64 volatile_file_id, + void **data, unsigned int *plen); extern int SMB2_get_srv_num(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, __le64 *uniqueid); diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c index c69ec96e92ac..67367cf1f8cd 100644 --- a/fs/cifs/smb2transport.c +++ b/fs/cifs/smb2transport.c @@ -335,9 +335,31 @@ generate_smb3signingkey(struct cifs_ses *ses, if (rc) return rc; - return generate_key(ses, ptriplet->decryption.label, - ptriplet->decryption.context, - ses->smb3decryptionkey, SMB3_SIGN_KEY_SIZE); + rc = generate_key(ses, ptriplet->decryption.label, + ptriplet->decryption.context, + ses->smb3decryptionkey, SMB3_SIGN_KEY_SIZE); + + if (rc) + return rc; + +#ifdef CONFIG_CIFS_DEBUG_DUMP_KEYS + cifs_dbg(VFS, "%s: dumping generated AES session keys\n", __func__); + /* + * The session id is opaque in terms of endianness, so we can't + * print it as a long long. we dump it as we got it on the wire + */ + cifs_dbg(VFS, "Session Id %*ph\n", (int)sizeof(ses->Suid), + &ses->Suid); + cifs_dbg(VFS, "Session Key %*ph\n", + SMB2_NTLMV2_SESSKEY_SIZE, ses->auth_key.response); + cifs_dbg(VFS, "Signing Key %*ph\n", + SMB3_SIGN_KEY_SIZE, ses->smb3signingkey); + cifs_dbg(VFS, "ServerIn Key %*ph\n", + SMB3_SIGN_KEY_SIZE, ses->smb3encryptionkey); + cifs_dbg(VFS, "ServerOut Key %*ph\n", + SMB3_SIGN_KEY_SIZE, ses->smb3decryptionkey); +#endif + return rc; } int diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 47a125ece11e..7efbab013957 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -536,11 +536,14 @@ cifs_call_async(struct TCP_Server_Info *server, struct smb_rqst *rqst, list_add_tail(&mid->qhead, &server->pending_mid_q); spin_unlock(&GlobalMid_Lock); - + /* + * Need to store the time in mid before calling I/O. For call_async, + * I/O response may come back and free the mid entry on another thread. + */ + cifs_save_when_sent(mid); cifs_in_send_inc(server); rc = smb_send_rqst(server, rqst, flags); cifs_in_send_dec(server); - cifs_save_when_sent(mid); if (rc < 0) { server->sequence_number -= 2; diff --git a/fs/coda/file.c b/fs/coda/file.c index 9d956cd6d46f..363402fcb3ed 100644 --- a/fs/coda/file.c +++ b/fs/coda/file.c @@ -34,7 +34,7 @@ coda_file_read_iter(struct kiocb *iocb, struct iov_iter *to) BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC); - return vfs_iter_read(cfi->cfi_container, to, &iocb->ki_pos); + return vfs_iter_read(cfi->cfi_container, to, &iocb->ki_pos, 0); } static ssize_t @@ -51,7 +51,7 @@ coda_file_write_iter(struct kiocb *iocb, struct iov_iter *to) host_file = cfi->cfi_container; file_start_write(host_file); inode_lock(coda_inode); - ret = vfs_iter_write(cfi->cfi_container, to, &iocb->ki_pos); + ret = vfs_iter_write(cfi->cfi_container, to, &iocb->ki_pos, 0); coda_inode->i_size = file_inode(host_file)->i_size; coda_inode->i_blocks = (coda_inode->i_size + 511) >> 9; coda_inode->i_mtime = coda_inode->i_ctime = current_time(coda_inode); diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index 6116d5275a3e..2dd4a7af7dd7 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -739,23 +739,22 @@ static int do_i2c_smbus_ioctl(struct file *file, unsigned int cmd, struct i2c_smbus_ioctl_data32 __user *udata) { struct i2c_smbus_ioctl_data __user *tdata; - compat_caddr_t datap; + union { + /* beginnings of those have identical layouts */ + struct i2c_smbus_ioctl_data32 data32; + struct i2c_smbus_ioctl_data data; + } v; tdata = compat_alloc_user_space(sizeof(*tdata)); if (tdata == NULL) return -ENOMEM; - if (!access_ok(VERIFY_WRITE, tdata, sizeof(*tdata))) - return -EFAULT; - if (!access_ok(VERIFY_READ, udata, sizeof(*udata))) + memset(&v, 0, sizeof(v)); + if (copy_from_user(&v.data32, udata, sizeof(v.data32))) return -EFAULT; + v.data.data = compat_ptr(v.data32.data); - if (__copy_in_user(&tdata->read_write, &udata->read_write, 2 * sizeof(u8))) - return -EFAULT; - if (__copy_in_user(&tdata->size, &udata->size, 2 * sizeof(u32))) - return -EFAULT; - if (__get_user(datap, &udata->data) || - __put_user(compat_ptr(datap), &tdata->data)) + if (copy_to_user(tdata, &v.data, sizeof(v.data))) return -EFAULT; return do_ioctl(file, cmd, (unsigned long)tdata); @@ -866,8 +865,6 @@ COMPATIBLE_IOCTL(TIOCGDEV) COMPATIBLE_IOCTL(TIOCCBRK) COMPATIBLE_IOCTL(TIOCGSID) COMPATIBLE_IOCTL(TIOCGICOUNT) -COMPATIBLE_IOCTL(TIOCGPKT) -COMPATIBLE_IOCTL(TIOCGPTLCK) COMPATIBLE_IOCTL(TIOCGEXCL) /* Little t */ COMPATIBLE_IOCTL(TIOCGETD) @@ -883,16 +880,12 @@ COMPATIBLE_IOCTL(TIOCMGET) COMPATIBLE_IOCTL(TIOCMBIC) COMPATIBLE_IOCTL(TIOCMBIS) COMPATIBLE_IOCTL(TIOCMSET) -COMPATIBLE_IOCTL(TIOCPKT) COMPATIBLE_IOCTL(TIOCNOTTY) COMPATIBLE_IOCTL(TIOCSTI) COMPATIBLE_IOCTL(TIOCOUTQ) COMPATIBLE_IOCTL(TIOCSPGRP) COMPATIBLE_IOCTL(TIOCGPGRP) -COMPATIBLE_IOCTL(TIOCGPTN) -COMPATIBLE_IOCTL(TIOCSPTLCK) COMPATIBLE_IOCTL(TIOCSERGETLSR) -COMPATIBLE_IOCTL(TIOCSIG) #ifdef TIOCSRS485 COMPATIBLE_IOCTL(TIOCSRS485) #endif diff --git a/fs/crypto/Kconfig b/fs/crypto/Kconfig index 08b46e6e3995..02b7d91c9231 100644 --- a/fs/crypto/Kconfig +++ b/fs/crypto/Kconfig @@ -7,6 +7,7 @@ config FS_ENCRYPTION select CRYPTO_XTS select CRYPTO_CTS select CRYPTO_CTR + select CRYPTO_SHA256 select KEYS help Enable encryption of files and directories. This diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c index 6d6eca394d4d..c7835df7e7b8 100644 --- a/fs/crypto/crypto.c +++ b/fs/crypto/crypto.c @@ -26,6 +26,7 @@ #include <linux/ratelimit.h> #include <linux/dcache.h> #include <linux/namei.h> +#include <crypto/aes.h> #include "fscrypt_private.h" static unsigned int num_prealloc_crypto_pages = 32; @@ -147,8 +148,8 @@ int fscrypt_do_page_crypto(const struct inode *inode, fscrypt_direction_t rw, { struct { __le64 index; - u8 padding[FS_XTS_TWEAK_SIZE - sizeof(__le64)]; - } xts_tweak; + u8 padding[FS_IV_SIZE - sizeof(__le64)]; + } iv; struct skcipher_request *req = NULL; DECLARE_FS_COMPLETION_RESULT(ecr); struct scatterlist dst, src; @@ -158,6 +159,16 @@ int fscrypt_do_page_crypto(const struct inode *inode, fscrypt_direction_t rw, BUG_ON(len == 0); + BUILD_BUG_ON(sizeof(iv) != FS_IV_SIZE); + BUILD_BUG_ON(AES_BLOCK_SIZE != FS_IV_SIZE); + iv.index = cpu_to_le64(lblk_num); + memset(iv.padding, 0, sizeof(iv.padding)); + + if (ci->ci_essiv_tfm != NULL) { + crypto_cipher_encrypt_one(ci->ci_essiv_tfm, (u8 *)&iv, + (u8 *)&iv); + } + req = skcipher_request_alloc(tfm, gfp_flags); if (!req) { printk_ratelimited(KERN_ERR @@ -170,15 +181,11 @@ int fscrypt_do_page_crypto(const struct inode *inode, fscrypt_direction_t rw, req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, page_crypt_complete, &ecr); - BUILD_BUG_ON(sizeof(xts_tweak) != FS_XTS_TWEAK_SIZE); - xts_tweak.index = cpu_to_le64(lblk_num); - memset(xts_tweak.padding, 0, sizeof(xts_tweak.padding)); - sg_init_table(&dst, 1); sg_set_page(&dst, dest_page, len, offs); sg_init_table(&src, 1); sg_set_page(&src, src_page, len, offs); - skcipher_request_set_crypt(req, &src, &dst, len, &xts_tweak); + skcipher_request_set_crypt(req, &src, &dst, len, &iv); if (rw == FS_DECRYPT) res = crypto_skcipher_decrypt(req); else @@ -477,6 +484,8 @@ static void __exit fscrypt_exit(void) destroy_workqueue(fscrypt_read_workqueue); kmem_cache_destroy(fscrypt_ctx_cachep); kmem_cache_destroy(fscrypt_info_cachep); + + fscrypt_essiv_cleanup(); } module_exit(fscrypt_exit); diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c index d1bb02b1ee58..ad9f814fdead 100644 --- a/fs/crypto/fname.c +++ b/fs/crypto/fname.c @@ -453,12 +453,3 @@ errout: return ret; } EXPORT_SYMBOL(fscrypt_setup_filename); - -void fscrypt_free_filename(struct fscrypt_name *fname) -{ - kfree(fname->crypto_buf.name); - fname->crypto_buf.name = NULL; - fname->usr_fname = NULL; - fname->disk_name.name = NULL; -} -EXPORT_SYMBOL(fscrypt_free_filename); diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h index 1e1f8a361b75..a1d5021c31ef 100644 --- a/fs/crypto/fscrypt_private.h +++ b/fs/crypto/fscrypt_private.h @@ -12,10 +12,13 @@ #define _FSCRYPT_PRIVATE_H #include <linux/fscrypt_supp.h> +#include <crypto/hash.h> /* Encryption parameters */ -#define FS_XTS_TWEAK_SIZE 16 +#define FS_IV_SIZE 16 #define FS_AES_128_ECB_KEY_SIZE 16 +#define FS_AES_128_CBC_KEY_SIZE 16 +#define FS_AES_128_CTS_KEY_SIZE 16 #define FS_AES_256_GCM_KEY_SIZE 32 #define FS_AES_256_CBC_KEY_SIZE 32 #define FS_AES_256_CTS_KEY_SIZE 32 @@ -54,6 +57,7 @@ struct fscrypt_info { u8 ci_filename_mode; u8 ci_flags; struct crypto_skcipher *ci_ctfm; + struct crypto_cipher *ci_essiv_tfm; u8 ci_master_key[FS_KEY_DESCRIPTOR_SIZE]; }; @@ -87,4 +91,7 @@ extern int fscrypt_do_page_crypto(const struct inode *inode, extern struct page *fscrypt_alloc_bounce_page(struct fscrypt_ctx *ctx, gfp_t gfp_flags); +/* keyinfo.c */ +extern void __exit fscrypt_essiv_cleanup(void); + #endif /* _FSCRYPT_PRIVATE_H */ diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c index 179e578b875b..018c588c7ac3 100644 --- a/fs/crypto/keyinfo.c +++ b/fs/crypto/keyinfo.c @@ -10,8 +10,13 @@ #include <keys/user-type.h> #include <linux/scatterlist.h> +#include <linux/ratelimit.h> +#include <crypto/aes.h> +#include <crypto/sha.h> #include "fscrypt_private.h" +static struct crypto_shash *essiv_hash_tfm; + static void derive_crypt_complete(struct crypto_async_request *req, int rc) { struct fscrypt_completion_result *ecr = req->data; @@ -27,13 +32,13 @@ static void derive_crypt_complete(struct crypto_async_request *req, int rc) * derive_key_aes() - Derive a key using AES-128-ECB * @deriving_key: Encryption key used for derivation. * @source_key: Source key to which to apply derivation. - * @derived_key: Derived key. + * @derived_raw_key: Derived raw key. * * Return: Zero on success; non-zero otherwise. */ static int derive_key_aes(u8 deriving_key[FS_AES_128_ECB_KEY_SIZE], - u8 source_key[FS_AES_256_XTS_KEY_SIZE], - u8 derived_key[FS_AES_256_XTS_KEY_SIZE]) + const struct fscrypt_key *source_key, + u8 derived_raw_key[FS_MAX_KEY_SIZE]) { int res = 0; struct skcipher_request *req = NULL; @@ -60,10 +65,10 @@ static int derive_key_aes(u8 deriving_key[FS_AES_128_ECB_KEY_SIZE], if (res < 0) goto out; - sg_init_one(&src_sg, source_key, FS_AES_256_XTS_KEY_SIZE); - sg_init_one(&dst_sg, derived_key, FS_AES_256_XTS_KEY_SIZE); - skcipher_request_set_crypt(req, &src_sg, &dst_sg, - FS_AES_256_XTS_KEY_SIZE, NULL); + sg_init_one(&src_sg, source_key->raw, source_key->size); + sg_init_one(&dst_sg, derived_raw_key, source_key->size); + skcipher_request_set_crypt(req, &src_sg, &dst_sg, source_key->size, + NULL); res = crypto_skcipher_encrypt(req); if (res == -EINPROGRESS || res == -EBUSY) { wait_for_completion(&ecr.completion); @@ -77,7 +82,7 @@ out: static int validate_user_key(struct fscrypt_info *crypt_info, struct fscrypt_context *ctx, u8 *raw_key, - const char *prefix) + const char *prefix, int min_keysize) { char *description; struct key *keyring_key; @@ -111,50 +116,60 @@ static int validate_user_key(struct fscrypt_info *crypt_info, master_key = (struct fscrypt_key *)ukp->data; BUILD_BUG_ON(FS_AES_128_ECB_KEY_SIZE != FS_KEY_DERIVATION_NONCE_SIZE); - if (master_key->size != FS_AES_256_XTS_KEY_SIZE) { + if (master_key->size < min_keysize || master_key->size > FS_MAX_KEY_SIZE + || master_key->size % AES_BLOCK_SIZE != 0) { printk_once(KERN_WARNING "%s: key size incorrect: %d\n", __func__, master_key->size); res = -ENOKEY; goto out; } - res = derive_key_aes(ctx->nonce, master_key->raw, raw_key); + res = derive_key_aes(ctx->nonce, master_key, raw_key); out: up_read(&keyring_key->sem); key_put(keyring_key); return res; } +static const struct { + const char *cipher_str; + int keysize; +} available_modes[] = { + [FS_ENCRYPTION_MODE_AES_256_XTS] = { "xts(aes)", + FS_AES_256_XTS_KEY_SIZE }, + [FS_ENCRYPTION_MODE_AES_256_CTS] = { "cts(cbc(aes))", + FS_AES_256_CTS_KEY_SIZE }, + [FS_ENCRYPTION_MODE_AES_128_CBC] = { "cbc(aes)", + FS_AES_128_CBC_KEY_SIZE }, + [FS_ENCRYPTION_MODE_AES_128_CTS] = { "cts(cbc(aes))", + FS_AES_128_CTS_KEY_SIZE }, +}; + static int determine_cipher_type(struct fscrypt_info *ci, struct inode *inode, const char **cipher_str_ret, int *keysize_ret) { - if (S_ISREG(inode->i_mode)) { - if (ci->ci_data_mode == FS_ENCRYPTION_MODE_AES_256_XTS) { - *cipher_str_ret = "xts(aes)"; - *keysize_ret = FS_AES_256_XTS_KEY_SIZE; - return 0; - } - pr_warn_once("fscrypto: unsupported contents encryption mode " - "%d for inode %lu\n", - ci->ci_data_mode, inode->i_ino); - return -ENOKEY; + u32 mode; + + if (!fscrypt_valid_enc_modes(ci->ci_data_mode, ci->ci_filename_mode)) { + pr_warn_ratelimited("fscrypt: inode %lu uses unsupported encryption modes (contents mode %d, filenames mode %d)\n", + inode->i_ino, + ci->ci_data_mode, ci->ci_filename_mode); + return -EINVAL; } - if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) { - if (ci->ci_filename_mode == FS_ENCRYPTION_MODE_AES_256_CTS) { - *cipher_str_ret = "cts(cbc(aes))"; - *keysize_ret = FS_AES_256_CTS_KEY_SIZE; - return 0; - } - pr_warn_once("fscrypto: unsupported filenames encryption mode " - "%d for inode %lu\n", - ci->ci_filename_mode, inode->i_ino); - return -ENOKEY; + if (S_ISREG(inode->i_mode)) { + mode = ci->ci_data_mode; + } else if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) { + mode = ci->ci_filename_mode; + } else { + WARN_ONCE(1, "fscrypt: filesystem tried to load encryption info for inode %lu, which is not encryptable (file type %d)\n", + inode->i_ino, (inode->i_mode & S_IFMT)); + return -EINVAL; } - pr_warn_once("fscrypto: unsupported file type %d for inode %lu\n", - (inode->i_mode & S_IFMT), inode->i_ino); - return -ENOKEY; + *cipher_str_ret = available_modes[mode].cipher_str; + *keysize_ret = available_modes[mode].keysize; + return 0; } static void put_crypt_info(struct fscrypt_info *ci) @@ -163,9 +178,76 @@ static void put_crypt_info(struct fscrypt_info *ci) return; crypto_free_skcipher(ci->ci_ctfm); + crypto_free_cipher(ci->ci_essiv_tfm); kmem_cache_free(fscrypt_info_cachep, ci); } +static int derive_essiv_salt(const u8 *key, int keysize, u8 *salt) +{ + struct crypto_shash *tfm = READ_ONCE(essiv_hash_tfm); + + /* init hash transform on demand */ + if (unlikely(!tfm)) { + struct crypto_shash *prev_tfm; + + tfm = crypto_alloc_shash("sha256", 0, 0); + if (IS_ERR(tfm)) { + pr_warn_ratelimited("fscrypt: error allocating SHA-256 transform: %ld\n", + PTR_ERR(tfm)); + return PTR_ERR(tfm); + } + prev_tfm = cmpxchg(&essiv_hash_tfm, NULL, tfm); + if (prev_tfm) { + crypto_free_shash(tfm); + tfm = prev_tfm; + } + } + + { + SHASH_DESC_ON_STACK(desc, tfm); + desc->tfm = tfm; + desc->flags = 0; + + return crypto_shash_digest(desc, key, keysize, salt); + } +} + +static int init_essiv_generator(struct fscrypt_info *ci, const u8 *raw_key, + int keysize) +{ + int err; + struct crypto_cipher *essiv_tfm; + u8 salt[SHA256_DIGEST_SIZE]; + + essiv_tfm = crypto_alloc_cipher("aes", 0, 0); + if (IS_ERR(essiv_tfm)) + return PTR_ERR(essiv_tfm); + + ci->ci_essiv_tfm = essiv_tfm; + + err = derive_essiv_salt(raw_key, keysize, salt); + if (err) + goto out; + + /* + * Using SHA256 to derive the salt/key will result in AES-256 being + * used for IV generation. File contents encryption will still use the + * configured keysize (AES-128) nevertheless. + */ + err = crypto_cipher_setkey(essiv_tfm, salt, sizeof(salt)); + if (err) + goto out; + +out: + memzero_explicit(salt, sizeof(salt)); + return err; +} + +void __exit fscrypt_essiv_cleanup(void) +{ + crypto_free_shash(essiv_hash_tfm); +} + int fscrypt_get_encryption_info(struct inode *inode) { struct fscrypt_info *crypt_info; @@ -212,6 +294,7 @@ int fscrypt_get_encryption_info(struct inode *inode) crypt_info->ci_data_mode = ctx.contents_encryption_mode; crypt_info->ci_filename_mode = ctx.filenames_encryption_mode; crypt_info->ci_ctfm = NULL; + crypt_info->ci_essiv_tfm = NULL; memcpy(crypt_info->ci_master_key, ctx.master_key_descriptor, sizeof(crypt_info->ci_master_key)); @@ -228,10 +311,12 @@ int fscrypt_get_encryption_info(struct inode *inode) if (!raw_key) goto out; - res = validate_user_key(crypt_info, &ctx, raw_key, FS_KEY_DESC_PREFIX); + res = validate_user_key(crypt_info, &ctx, raw_key, FS_KEY_DESC_PREFIX, + keysize); if (res && inode->i_sb->s_cop->key_prefix) { int res2 = validate_user_key(crypt_info, &ctx, raw_key, - inode->i_sb->s_cop->key_prefix); + inode->i_sb->s_cop->key_prefix, + keysize); if (res2) { if (res2 == -ENOKEY) res = -ENOKEY; @@ -243,18 +328,30 @@ int fscrypt_get_encryption_info(struct inode *inode) ctfm = crypto_alloc_skcipher(cipher_str, 0, 0); if (!ctfm || IS_ERR(ctfm)) { res = ctfm ? PTR_ERR(ctfm) : -ENOMEM; - printk(KERN_DEBUG - "%s: error %d (inode %u) allocating crypto tfm\n", - __func__, res, (unsigned) inode->i_ino); + pr_debug("%s: error %d (inode %lu) allocating crypto tfm\n", + __func__, res, inode->i_ino); goto out; } crypt_info->ci_ctfm = ctfm; crypto_skcipher_clear_flags(ctfm, ~0); crypto_skcipher_set_flags(ctfm, CRYPTO_TFM_REQ_WEAK_KEY); + /* + * if the provided key is longer than keysize, we use the first + * keysize bytes of the derived key only + */ res = crypto_skcipher_setkey(ctfm, raw_key, keysize); if (res) goto out; + if (S_ISREG(inode->i_mode) && + crypt_info->ci_data_mode == FS_ENCRYPTION_MODE_AES_128_CBC) { + res = init_essiv_generator(crypt_info, raw_key, keysize); + if (res) { + pr_debug("%s: error %d (inode %lu) allocating essiv tfm\n", + __func__, res, inode->i_ino); + goto out; + } + } if (cmpxchg(&inode->i_crypt_info, NULL, crypt_info) == NULL) crypt_info = NULL; out: diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c index 210976e7a269..ce07a86200f3 100644 --- a/fs/crypto/policy.c +++ b/fs/crypto/policy.c @@ -38,12 +38,8 @@ static int create_encryption_context_from_policy(struct inode *inode, memcpy(ctx.master_key_descriptor, policy->master_key_descriptor, FS_KEY_DESCRIPTOR_SIZE); - if (!fscrypt_valid_contents_enc_mode( - policy->contents_encryption_mode)) - return -EINVAL; - - if (!fscrypt_valid_filenames_enc_mode( - policy->filenames_encryption_mode)) + if (!fscrypt_valid_enc_modes(policy->contents_encryption_mode, + policy->filenames_encryption_mode)) return -EINVAL; if (policy->flags & ~FS_POLICY_FLAGS_VALID) @@ -260,6 +256,7 @@ int fscrypt_inherit_context(struct inode *parent, struct inode *child, memcpy(ctx.master_key_descriptor, ci->ci_master_key, FS_KEY_DESCRIPTOR_SIZE); get_random_bytes(ctx.nonce, FS_KEY_DERIVATION_NONCE_SIZE); + BUILD_BUG_ON(sizeof(ctx) != FSCRYPT_SET_CONTEXT_MAX_SIZE); res = parent->i_sb->s_cop->set_context(child, &ctx, sizeof(ctx), fs_data); if (res) @@ -25,7 +25,6 @@ #include <linux/mm.h> #include <linux/mutex.h> #include <linux/pagevec.h> -#include <linux/pmem.h> #include <linux/sched.h> #include <linux/sched/signal.h> #include <linux/uio.h> @@ -784,7 +783,7 @@ static int dax_writeback_one(struct block_device *bdev, } dax_mapping_entry_mkclean(mapping, index, pfn_t_to_pfn(pfn)); - wb_cache_pmem(kaddr, size); + dax_flush(dax_dev, pgoff, kaddr, size); /* * After we have flushed the cache, we can clear the dirty tag. There * cannot be new dirty data in the pfn after the flush has completed as @@ -856,8 +855,10 @@ int dax_writeback_mapping_range(struct address_space *mapping, ret = dax_writeback_one(bdev, dax_dev, mapping, indices[i], pvec.pages[i]); - if (ret < 0) + if (ret < 0) { + mapping_set_error(mapping, ret); goto out; + } } start_index = indices[pvec.nr - 1] + 1; } @@ -976,7 +977,8 @@ int __dax_zero_page_range(struct block_device *bdev, dax_read_unlock(id); return rc; } - clear_pmem(kaddr + offset, size); + memset(kaddr + offset, 0, size); + dax_flush(dax_dev, pgoff, kaddr + offset, size); dax_read_unlock(id); } return 0; @@ -1055,7 +1057,8 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data, map_len = end - pos; if (iov_iter_rw(iter) == WRITE) - map_len = copy_from_iter_pmem(kaddr, map_len, iter); + map_len = dax_copy_from_iter(dax_dev, pgoff, kaddr, + map_len, iter); else map_len = copy_to_iter(kaddr, map_len, iter); if (map_len <= 0) { @@ -1213,7 +1216,7 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf, case IOMAP_MAPPED: if (iomap.flags & IOMAP_F_NEW) { count_vm_event(PGMAJFAULT); - mem_cgroup_count_vm_event(vmf->vma->vm_mm, PGMAJFAULT); + count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT); major = VM_FAULT_MAJOR; } error = dax_insert_mapping(mapping, iomap.bdev, iomap.dax_dev, diff --git a/fs/dcache.c b/fs/dcache.c index a9f995f6859e..7ece68d0d4db 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -277,6 +277,33 @@ static inline int dname_external(const struct dentry *dentry) return dentry->d_name.name != dentry->d_iname; } +void take_dentry_name_snapshot(struct name_snapshot *name, struct dentry *dentry) +{ + spin_lock(&dentry->d_lock); + if (unlikely(dname_external(dentry))) { + struct external_name *p = external_name(dentry); + atomic_inc(&p->u.count); + spin_unlock(&dentry->d_lock); + name->name = p->name; + } else { + memcpy(name->inline_name, dentry->d_iname, DNAME_INLINE_LEN); + spin_unlock(&dentry->d_lock); + name->name = name->inline_name; + } +} +EXPORT_SYMBOL(take_dentry_name_snapshot); + +void release_dentry_name_snapshot(struct name_snapshot *name) +{ + if (unlikely(name->name != name->inline_name)) { + struct external_name *p; + p = container_of(name->name, struct external_name, name[0]); + if (unlikely(atomic_dec_and_test(&p->u.count))) + kfree_rcu(p, u.head); + } +} +EXPORT_SYMBOL(release_dentry_name_snapshot); + static inline void __d_set_inode_and_type(struct dentry *dentry, struct inode *inode, unsigned type_flags) @@ -3546,8 +3573,6 @@ __setup("dhash_entries=", set_dhash_entries); static void __init dcache_init_early(void) { - unsigned int loop; - /* If hashes are distributed across NUMA nodes, defer * hash allocation until vmalloc space is available. */ @@ -3559,24 +3584,19 @@ static void __init dcache_init_early(void) sizeof(struct hlist_bl_head), dhash_entries, 13, - HASH_EARLY, + HASH_EARLY | HASH_ZERO, &d_hash_shift, &d_hash_mask, 0, 0); - - for (loop = 0; loop < (1U << d_hash_shift); loop++) - INIT_HLIST_BL_HEAD(dentry_hashtable + loop); } static void __init dcache_init(void) { - unsigned int loop; - - /* + /* * A constructor could be added for stable state like the lists, * but it is probably not worth it because of the cache nature - * of the dcache. + * of the dcache. */ dentry_cache = KMEM_CACHE(dentry, SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_MEM_SPREAD|SLAB_ACCOUNT); @@ -3590,14 +3610,11 @@ static void __init dcache_init(void) sizeof(struct hlist_bl_head), dhash_entries, 13, - 0, + HASH_ZERO, &d_hash_shift, &d_hash_mask, 0, 0); - - for (loop = 0; loop < (1U << d_hash_shift); loop++) - INIT_HLIST_BL_HEAD(dentry_hashtable + loop); } /* SLAB cache for __getname() consumers */ @@ -3608,6 +3625,11 @@ EXPORT_SYMBOL(d_genocide); void __init vfs_caches_init_early(void) { + int i; + + for (i = 0; i < ARRAY_SIZE(in_lookup_hashtable); i++) + INIT_HLIST_BL_HEAD(&in_lookup_hashtable[i]); + dcache_init_early(); inode_init_early(); } diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index 354e2ab62031..6dabc4a10396 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -9,7 +9,7 @@ * 2 as published by the Free Software Foundation. * * debugfs is for people to use instead of /proc or /sys. - * See Documentation/DocBook/filesystems for more details. + * See Documentation/filesystems/ for more details. * */ diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index e892ae7d89f8..a0e4e2f7e0be 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -9,7 +9,7 @@ * 2 as published by the Free Software Foundation. * * debugfs is for people to use instead of /proc or /sys. - * See Documentation/DocBook/kernel-api for more details. + * See ./Documentation/core-api/kernel-api.rst for more details. * */ @@ -766,7 +766,7 @@ struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry, { int error; struct dentry *dentry = NULL, *trap; - const char *old_name; + struct name_snapshot old_name; trap = lock_rename(new_dir, old_dir); /* Source or destination directories don't exist? */ @@ -781,19 +781,19 @@ struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry, if (IS_ERR(dentry) || dentry == trap || d_really_is_positive(dentry)) goto exit; - old_name = fsnotify_oldname_init(old_dentry->d_name.name); + take_dentry_name_snapshot(&old_name, old_dentry); error = simple_rename(d_inode(old_dir), old_dentry, d_inode(new_dir), dentry, 0); if (error) { - fsnotify_oldname_free(old_name); + release_dentry_name_snapshot(&old_name); goto exit; } d_move(old_dentry, dentry); - fsnotify_move(d_inode(old_dir), d_inode(new_dir), old_name, + fsnotify_move(d_inode(old_dir), d_inode(new_dir), old_name.name, d_is_dir(old_dentry), NULL, old_dentry); - fsnotify_oldname_free(old_name); + release_dentry_name_snapshot(&old_name); unlock_rename(new_dir, old_dir); dput(dentry); return old_dentry; diff --git a/fs/eventfd.c b/fs/eventfd.c index 9736df2ce89d..2fb4eadaa118 100644 --- a/fs/eventfd.c +++ b/fs/eventfd.c @@ -215,8 +215,8 @@ EXPORT_SYMBOL_GPL(eventfd_ctx_remove_wait_queue); * * Returns %0 if successful, or the following error codes: * - * -EAGAIN : The operation would have blocked but @no_wait was non-zero. - * -ERESTARTSYS : A signal interrupted the wait operation. + * - -EAGAIN : The operation would have blocked but @no_wait was non-zero. + * - -ERESTARTSYS : A signal interrupted the wait operation. * * If @no_wait is zero, the function might sleep until the eventfd internal * counter becomes greater than zero. diff --git a/fs/exec.c b/fs/exec.c index 904199086490..62175cbcc801 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -220,8 +220,7 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, if (write) { unsigned long size = bprm->vma->vm_end - bprm->vma->vm_start; - unsigned long ptr_size; - struct rlimit *rlim; + unsigned long ptr_size, limit; /* * Since the stack will hold pointers to the strings, we @@ -250,14 +249,16 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, return page; /* - * Limit to 1/4-th the stack size for the argv+env strings. + * Limit to 1/4 of the max stack size or 3/4 of _STK_LIM + * (whichever is smaller) for the argv+env strings. * This ensures that: * - the remaining binfmt code will not run out of stack space, * - the program will have a reasonable amount of stack left * to work from. */ - rlim = current->signal->rlim; - if (size > READ_ONCE(rlim[RLIMIT_STACK].rlim_cur) / 4) + limit = _STK_LIM / 4 * 3; + limit = min(limit, rlimit(RLIMIT_STACK) / 4); + if (size > limit) goto fail; } diff --git a/fs/exofs/dir.c b/fs/exofs/dir.c index 8eeb694332fe..98233a97b7b8 100644 --- a/fs/exofs/dir.c +++ b/fs/exofs/dir.c @@ -72,7 +72,7 @@ static int exofs_commit_chunk(struct page *page, loff_t pos, unsigned len) set_page_dirty(page); if (IS_DIRSYNC(dir)) - err = write_one_page(page, 1); + err = write_one_page(page); else unlock_page(page); diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c index d9650c9508e4..e2709695b177 100644 --- a/fs/ext2/dir.c +++ b/fs/ext2/dir.c @@ -100,7 +100,7 @@ static int ext2_commit_chunk(struct page *page, loff_t pos, unsigned len) } if (IS_DIRSYNC(dir)) { - err = write_one_page(page, 1); + err = write_one_page(page); if (!err) err = sync_inode_metadata(dir, 1); } else { diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index 03f5ce1d3dbe..23ebb92484c6 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -113,7 +113,7 @@ struct ext2_sb_info { * of the mount options. */ spinlock_t s_lock; - struct mb_cache *s_mb_cache; + struct mb_cache *s_ea_block_cache; }; static inline spinlock_t * diff --git a/fs/ext2/file.c b/fs/ext2/file.c index b21891a6bfca..d34d32bdc944 100644 --- a/fs/ext2/file.c +++ b/fs/ext2/file.c @@ -174,15 +174,12 @@ int ext2_fsync(struct file *file, loff_t start, loff_t end, int datasync) { int ret; struct super_block *sb = file->f_mapping->host->i_sb; - struct address_space *mapping = sb->s_bdev->bd_inode->i_mapping; ret = generic_file_fsync(file, start, end, datasync); - if (ret == -EIO || test_and_clear_bit(AS_EIO, &mapping->flags)) { + if (ret == -EIO) /* We don't really know where the IO error happened... */ ext2_error(sb, __func__, "detected IO error when writing metadata buffers"); - ret = -EIO; - } return ret; } diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 9c2028b50e5c..7b1bc9059863 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -147,9 +147,9 @@ static void ext2_put_super (struct super_block * sb) ext2_quota_off_umount(sb); - if (sbi->s_mb_cache) { - ext2_xattr_destroy_cache(sbi->s_mb_cache); - sbi->s_mb_cache = NULL; + if (sbi->s_ea_block_cache) { + ext2_xattr_destroy_cache(sbi->s_ea_block_cache); + sbi->s_ea_block_cache = NULL; } if (!(sb->s_flags & MS_RDONLY)) { struct ext2_super_block *es = sbi->s_es; @@ -1131,9 +1131,9 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) } #ifdef CONFIG_EXT2_FS_XATTR - sbi->s_mb_cache = ext2_xattr_create_cache(); - if (!sbi->s_mb_cache) { - ext2_msg(sb, KERN_ERR, "Failed to create an mb_cache"); + sbi->s_ea_block_cache = ext2_xattr_create_cache(); + if (!sbi->s_ea_block_cache) { + ext2_msg(sb, KERN_ERR, "Failed to create ea_block_cache"); goto failed_mount3; } #endif @@ -1182,8 +1182,8 @@ cantfind_ext2: sb->s_id); goto failed_mount; failed_mount3: - if (sbi->s_mb_cache) - ext2_xattr_destroy_cache(sbi->s_mb_cache); + if (sbi->s_ea_block_cache) + ext2_xattr_destroy_cache(sbi->s_ea_block_cache); percpu_counter_destroy(&sbi->s_freeblocks_counter); percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c index fbdb8f171893..1b9b1268d418 100644 --- a/fs/ext2/xattr.c +++ b/fs/ext2/xattr.c @@ -121,6 +121,8 @@ const struct xattr_handler *ext2_xattr_handlers[] = { NULL }; +#define EA_BLOCK_CACHE(inode) (EXT2_SB(inode->i_sb)->s_ea_block_cache) + static inline const struct xattr_handler * ext2_xattr_handler(int name_index) { @@ -150,7 +152,7 @@ ext2_xattr_get(struct inode *inode, int name_index, const char *name, size_t name_len, size; char *end; int error; - struct mb_cache *ext2_mb_cache = EXT2_SB(inode->i_sb)->s_mb_cache; + struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode); ea_idebug(inode, "name=%d.%s, buffer=%p, buffer_size=%ld", name_index, name, buffer, (long)buffer_size); @@ -195,7 +197,7 @@ bad_block: ext2_error(inode->i_sb, "ext2_xattr_get", goto found; entry = next; } - if (ext2_xattr_cache_insert(ext2_mb_cache, bh)) + if (ext2_xattr_cache_insert(ea_block_cache, bh)) ea_idebug(inode, "cache insert failed"); error = -ENODATA; goto cleanup; @@ -208,7 +210,7 @@ found: le16_to_cpu(entry->e_value_offs) + size > inode->i_sb->s_blocksize) goto bad_block; - if (ext2_xattr_cache_insert(ext2_mb_cache, bh)) + if (ext2_xattr_cache_insert(ea_block_cache, bh)) ea_idebug(inode, "cache insert failed"); if (buffer) { error = -ERANGE; @@ -246,7 +248,7 @@ ext2_xattr_list(struct dentry *dentry, char *buffer, size_t buffer_size) char *end; size_t rest = buffer_size; int error; - struct mb_cache *ext2_mb_cache = EXT2_SB(inode->i_sb)->s_mb_cache; + struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode); ea_idebug(inode, "buffer=%p, buffer_size=%ld", buffer, (long)buffer_size); @@ -281,7 +283,7 @@ bad_block: ext2_error(inode->i_sb, "ext2_xattr_list", goto bad_block; entry = next; } - if (ext2_xattr_cache_insert(ext2_mb_cache, bh)) + if (ext2_xattr_cache_insert(ea_block_cache, bh)) ea_idebug(inode, "cache insert failed"); /* list the attribute names */ @@ -493,8 +495,8 @@ bad_block: ext2_error(sb, "ext2_xattr_set", * This must happen under buffer lock for * ext2_xattr_set2() to reliably detect modified block */ - mb_cache_entry_delete_block(EXT2_SB(sb)->s_mb_cache, - hash, bh->b_blocknr); + mb_cache_entry_delete(EA_BLOCK_CACHE(inode), hash, + bh->b_blocknr); /* keep the buffer locked while modifying it. */ } else { @@ -627,7 +629,7 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh, struct super_block *sb = inode->i_sb; struct buffer_head *new_bh = NULL; int error; - struct mb_cache *ext2_mb_cache = EXT2_SB(sb)->s_mb_cache; + struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode); if (header) { new_bh = ext2_xattr_cache_find(inode, header); @@ -655,7 +657,7 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh, don't need to change the reference count. */ new_bh = old_bh; get_bh(new_bh); - ext2_xattr_cache_insert(ext2_mb_cache, new_bh); + ext2_xattr_cache_insert(ea_block_cache, new_bh); } else { /* We need to allocate a new block */ ext2_fsblk_t goal = ext2_group_first_block_no(sb, @@ -676,7 +678,7 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh, memcpy(new_bh->b_data, header, new_bh->b_size); set_buffer_uptodate(new_bh); unlock_buffer(new_bh); - ext2_xattr_cache_insert(ext2_mb_cache, new_bh); + ext2_xattr_cache_insert(ea_block_cache, new_bh); ext2_xattr_update_super_block(sb); } @@ -721,8 +723,8 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh, * This must happen under buffer lock for * ext2_xattr_set2() to reliably detect freed block */ - mb_cache_entry_delete_block(ext2_mb_cache, - hash, old_bh->b_blocknr); + mb_cache_entry_delete(ea_block_cache, hash, + old_bh->b_blocknr); /* Free the old block. */ ea_bdebug(old_bh, "freeing"); ext2_free_blocks(inode, old_bh->b_blocknr, 1); @@ -795,8 +797,8 @@ ext2_xattr_delete_inode(struct inode *inode) * This must happen under buffer lock for ext2_xattr_set2() to * reliably detect freed block */ - mb_cache_entry_delete_block(EXT2_SB(inode->i_sb)->s_mb_cache, - hash, bh->b_blocknr); + mb_cache_entry_delete(EA_BLOCK_CACHE(inode), hash, + bh->b_blocknr); ext2_free_blocks(inode, EXT2_I(inode)->i_file_acl, 1); get_bh(bh); bforget(bh); @@ -897,21 +899,21 @@ ext2_xattr_cache_find(struct inode *inode, struct ext2_xattr_header *header) { __u32 hash = le32_to_cpu(header->h_hash); struct mb_cache_entry *ce; - struct mb_cache *ext2_mb_cache = EXT2_SB(inode->i_sb)->s_mb_cache; + struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode); if (!header->h_hash) return NULL; /* never share */ ea_idebug(inode, "looking for cached blocks [%x]", (int)hash); again: - ce = mb_cache_entry_find_first(ext2_mb_cache, hash); + ce = mb_cache_entry_find_first(ea_block_cache, hash); while (ce) { struct buffer_head *bh; - bh = sb_bread(inode->i_sb, ce->e_block); + bh = sb_bread(inode->i_sb, ce->e_value); if (!bh) { ext2_error(inode->i_sb, "ext2_xattr_cache_find", "inode %ld: block %ld read error", - inode->i_ino, (unsigned long) ce->e_block); + inode->i_ino, (unsigned long) ce->e_value); } else { lock_buffer(bh); /* @@ -924,27 +926,27 @@ again: * entry is still hashed is reliable. */ if (hlist_bl_unhashed(&ce->e_hash_list)) { - mb_cache_entry_put(ext2_mb_cache, ce); + mb_cache_entry_put(ea_block_cache, ce); unlock_buffer(bh); brelse(bh); goto again; } else if (le32_to_cpu(HDR(bh)->h_refcount) > EXT2_XATTR_REFCOUNT_MAX) { ea_idebug(inode, "block %ld refcount %d>%d", - (unsigned long) ce->e_block, + (unsigned long) ce->e_value, le32_to_cpu(HDR(bh)->h_refcount), EXT2_XATTR_REFCOUNT_MAX); } else if (!ext2_xattr_cmp(header, HDR(bh))) { ea_bdebug(bh, "b_count=%d", atomic_read(&(bh->b_count))); - mb_cache_entry_touch(ext2_mb_cache, ce); - mb_cache_entry_put(ext2_mb_cache, ce); + mb_cache_entry_touch(ea_block_cache, ce); + mb_cache_entry_put(ea_block_cache, ce); return bh; } unlock_buffer(bh); brelse(bh); } - ce = mb_cache_entry_find_next(ext2_mb_cache, ce); + ce = mb_cache_entry_find_next(ea_block_cache, ce); } return NULL; } diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c index 3ec0e46de95f..09441ae07a5b 100644 --- a/fs/ext4/acl.c +++ b/fs/ext4/acl.c @@ -183,7 +183,7 @@ ext4_get_acl(struct inode *inode, int type) */ static int __ext4_set_acl(handle_t *handle, struct inode *inode, int type, - struct posix_acl *acl) + struct posix_acl *acl, int xattr_flags) { int name_index; void *value = NULL; @@ -218,7 +218,7 @@ __ext4_set_acl(handle_t *handle, struct inode *inode, int type, } error = ext4_xattr_set_handle(handle, inode, name_index, "", - value, size, 0); + value, size, xattr_flags); kfree(value); if (!error) @@ -231,18 +231,23 @@ int ext4_set_acl(struct inode *inode, struct posix_acl *acl, int type) { handle_t *handle; - int error, retries = 0; + int error, credits, retries = 0; + size_t acl_size = acl ? ext4_acl_size(acl->a_count) : 0; error = dquot_initialize(inode); if (error) return error; retry: - handle = ext4_journal_start(inode, EXT4_HT_XATTR, - ext4_jbd2_credits_xattr(inode)); + error = ext4_xattr_set_credits(inode, acl_size, false /* is_create */, + &credits); + if (error) + return error; + + handle = ext4_journal_start(inode, EXT4_HT_XATTR, credits); if (IS_ERR(handle)) return PTR_ERR(handle); - error = __ext4_set_acl(handle, inode, type, acl); + error = __ext4_set_acl(handle, inode, type, acl, 0 /* xattr_flags */); ext4_journal_stop(handle); if (error == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) goto retry; @@ -267,13 +272,13 @@ ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir) if (default_acl) { error = __ext4_set_acl(handle, inode, ACL_TYPE_DEFAULT, - default_acl); + default_acl, XATTR_CREATE); posix_acl_release(default_acl); } if (acl) { if (!error) error = __ext4_set_acl(handle, inode, ACL_TYPE_ACCESS, - acl); + acl, XATTR_CREATE); posix_acl_release(acl); } return error; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 32191548abed..9ebde0cd632e 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1114,6 +1114,7 @@ struct ext4_inode_info { /* * Mount flags set via mount options or defaults */ +#define EXT4_MOUNT_NO_MBCACHE 0x00001 /* Do not use mbcache */ #define EXT4_MOUNT_GRPID 0x00004 /* Create files with directory's group */ #define EXT4_MOUNT_DEBUG 0x00008 /* Some debugging messages */ #define EXT4_MOUNT_ERRORS_CONT 0x00010 /* Continue on errors */ @@ -1444,6 +1445,8 @@ struct ext4_sb_info { unsigned int *s_mb_maxs; unsigned int s_group_info_size; unsigned int s_mb_free_pending; + struct list_head s_freed_data_list; /* List of blocks to be freed + after commit completed */ /* tunables */ unsigned long s_stripe; @@ -1516,7 +1519,8 @@ struct ext4_sb_info { struct list_head s_es_list; /* List of inodes with reclaimable extents */ long s_es_nr_inode; struct ext4_es_stats s_es_stats; - struct mb_cache *s_mb_cache; + struct mb_cache *s_ea_block_cache; + struct mb_cache *s_ea_inode_cache; spinlock_t s_es_lock ____cacheline_aligned_in_smp; /* Ratelimit ext4 messages. */ @@ -1797,10 +1801,12 @@ EXT4_FEATURE_INCOMPAT_FUNCS(encrypt, ENCRYPT) EXT4_FEATURE_INCOMPAT_EXTENTS| \ EXT4_FEATURE_INCOMPAT_64BIT| \ EXT4_FEATURE_INCOMPAT_FLEX_BG| \ + EXT4_FEATURE_INCOMPAT_EA_INODE| \ EXT4_FEATURE_INCOMPAT_MMP | \ EXT4_FEATURE_INCOMPAT_INLINE_DATA | \ EXT4_FEATURE_INCOMPAT_ENCRYPT | \ - EXT4_FEATURE_INCOMPAT_CSUM_SEED) + EXT4_FEATURE_INCOMPAT_CSUM_SEED | \ + EXT4_FEATURE_INCOMPAT_LARGEDIR) #define EXT4_FEATURE_RO_COMPAT_SUPP (EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \ EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \ EXT4_FEATURE_RO_COMPAT_GDT_CSUM| \ @@ -2098,6 +2104,12 @@ static inline struct ext4_inode *ext4_raw_inode(struct ext4_iloc *iloc) return (struct ext4_inode *) (iloc->bh->b_data + iloc->offset); } +static inline bool ext4_is_quota_file(struct inode *inode) +{ + return IS_NOQUOTA(inode) && + !(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL); +} + /* * This structure is stuffed into the struct file's private_data field * for directories. It is where we put information so that we can do @@ -2126,6 +2138,16 @@ ext4_group_first_block_no(struct super_block *sb, ext4_group_t group_no) */ #define ERR_BAD_DX_DIR (-(MAX_ERRNO - 1)) +/* htree levels for ext4 */ +#define EXT4_HTREE_LEVEL_COMPAT 2 +#define EXT4_HTREE_LEVEL 3 + +static inline int ext4_dir_htree_level(struct super_block *sb) +{ + return ext4_has_feature_largedir(sb) ? + EXT4_HTREE_LEVEL : EXT4_HTREE_LEVEL_COMPAT; +} + /* * Timeout and state flag for lazy initialization inode thread. */ @@ -2389,16 +2411,17 @@ extern int ext4fs_dirhash(const char *name, int len, struct /* ialloc.c */ extern struct inode *__ext4_new_inode(handle_t *, struct inode *, umode_t, const struct qstr *qstr, __u32 goal, - uid_t *owner, int handle_type, - unsigned int line_no, int nblocks); + uid_t *owner, __u32 i_flags, + int handle_type, unsigned int line_no, + int nblocks); -#define ext4_new_inode(handle, dir, mode, qstr, goal, owner) \ +#define ext4_new_inode(handle, dir, mode, qstr, goal, owner, i_flags) \ __ext4_new_inode((handle), (dir), (mode), (qstr), (goal), (owner), \ - 0, 0, 0) + i_flags, 0, 0, 0) #define ext4_new_inode_start_handle(dir, mode, qstr, goal, owner, \ type, nblocks) \ __ext4_new_inode(NULL, (dir), (mode), (qstr), (goal), (owner), \ - (type), __LINE__, (nblocks)) + 0, (type), __LINE__, (nblocks)) extern void ext4_free_inode(handle_t *, struct inode *); @@ -2433,6 +2456,7 @@ extern int ext4_mb_add_groupinfo(struct super_block *sb, extern int ext4_group_add_blocks(handle_t *handle, struct super_block *sb, ext4_fsblk_t block, unsigned long count); extern int ext4_trim_fs(struct super_block *, struct fstrim_range *); +extern void ext4_process_freed_data(struct super_block *sb, tid_t commit_tid); /* inode.c */ int ext4_inode_is_fast_symlink(struct inode *inode); @@ -2704,19 +2728,20 @@ extern void ext4_group_desc_csum_set(struct super_block *sb, __u32 group, extern int ext4_register_li_request(struct super_block *sb, ext4_group_t first_not_zeroed); -static inline int ext4_has_group_desc_csum(struct super_block *sb) -{ - return ext4_has_feature_gdt_csum(sb) || - EXT4_SB(sb)->s_chksum_driver != NULL; -} - static inline int ext4_has_metadata_csum(struct super_block *sb) { WARN_ON_ONCE(ext4_has_feature_metadata_csum(sb) && !EXT4_SB(sb)->s_chksum_driver); - return (EXT4_SB(sb)->s_chksum_driver != NULL); + return ext4_has_feature_metadata_csum(sb) && + (EXT4_SB(sb)->s_chksum_driver != NULL); } + +static inline int ext4_has_group_desc_csum(struct super_block *sb) +{ + return ext4_has_feature_gdt_csum(sb) || ext4_has_metadata_csum(sb); +} + static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es) { return ((ext4_fsblk_t)le32_to_cpu(es->s_blocks_count_hi) << 32) | @@ -2756,13 +2781,15 @@ static inline void ext4_r_blocks_count_set(struct ext4_super_block *es, es->s_r_blocks_count_hi = cpu_to_le32(blk >> 32); } -static inline loff_t ext4_isize(struct ext4_inode *raw_inode) +static inline loff_t ext4_isize(struct super_block *sb, + struct ext4_inode *raw_inode) { - if (S_ISREG(le16_to_cpu(raw_inode->i_mode))) + if (ext4_has_feature_largedir(sb) || + S_ISREG(le16_to_cpu(raw_inode->i_mode))) return ((loff_t)le32_to_cpu(raw_inode->i_size_high) << 32) | le32_to_cpu(raw_inode->i_size_lo); - else - return (loff_t) le32_to_cpu(raw_inode->i_size_lo); + + return (loff_t) le32_to_cpu(raw_inode->i_size_lo); } static inline void ext4_isize_set(struct ext4_inode *raw_inode, loff_t i_size) diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index f97611171023..dabad1bc8617 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -77,7 +77,14 @@ #define EXT4_RESERVE_TRANS_BLOCKS 12U -#define EXT4_INDEX_EXTRA_TRANS_BLOCKS 8 +/* + * Number of credits needed if we need to insert an entry into a + * directory. For each new index block, we need 4 blocks (old index + * block, new index block, bitmap block, bg summary). For normal + * htree directories there are 2 levels; if the largedir feature + * enabled it's 3 levels. + */ +#define EXT4_INDEX_EXTRA_TRANS_BLOCKS 12U #ifdef CONFIG_QUOTA /* Amount of blocks needed for quota update - we know that the structure was @@ -104,20 +111,6 @@ #define EXT4_MAXQUOTAS_INIT_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_INIT_BLOCKS(sb)) #define EXT4_MAXQUOTAS_DEL_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_DEL_BLOCKS(sb)) -static inline int ext4_jbd2_credits_xattr(struct inode *inode) -{ - int credits = EXT4_DATA_TRANS_BLOCKS(inode->i_sb); - - /* - * In case of inline data, we may push out the data to a block, - * so we need to reserve credits for this eventuality - */ - if (ext4_has_inline_data(inode)) - credits += ext4_writepage_trans_blocks(inode) + 1; - return credits; -} - - /* * Ext4 handle operation types -- for logging purposes */ diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 3e36508610b7..e0a8425ff74d 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -2488,7 +2488,8 @@ int ext4_ext_index_trans_blocks(struct inode *inode, int extents) static inline int get_default_free_blocks_flags(struct inode *inode) { - if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) + if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode) || + ext4_test_inode_flag(inode, EXT4_INODE_EA_INODE)) return EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET; else if (ext4_should_journal_data(inode)) return EXT4_FREE_BLOCKS_FORGET; diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 58e2eeaa0bc4..58294c9a7e1d 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -364,13 +364,6 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma) if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) return -EIO; - if (ext4_encrypted_inode(inode)) { - int err = fscrypt_get_encryption_info(inode); - if (err) - return 0; - if (!fscrypt_has_encryption_key(inode)) - return -ENOKEY; - } file_accessed(file); if (IS_DAX(file_inode(file))) { vma->vm_ops = &ext4_dax_vm_ops; diff --git a/fs/ext4/fsmap.c b/fs/ext4/fsmap.c index b19436098837..7ec340898598 100644 --- a/fs/ext4/fsmap.c +++ b/fs/ext4/fsmap.c @@ -480,6 +480,7 @@ static int ext4_getfsmap_datadev(struct super_block *sb, struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t start_fsb; ext4_fsblk_t end_fsb; + ext4_fsblk_t bofs; ext4_fsblk_t eofs; ext4_group_t start_ag; ext4_group_t end_ag; @@ -487,9 +488,12 @@ static int ext4_getfsmap_datadev(struct super_block *sb, ext4_grpblk_t last_cluster; int error = 0; + bofs = le32_to_cpu(sbi->s_es->s_first_data_block); eofs = ext4_blocks_count(sbi->s_es); if (keys[0].fmr_physical >= eofs) return 0; + else if (keys[0].fmr_physical < bofs) + keys[0].fmr_physical = bofs; if (keys[1].fmr_physical >= eofs) keys[1].fmr_physical = eofs - 1; start_fsb = keys[0].fmr_physical; diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index 9d549608fd30..aae2c3971cef 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -124,7 +124,7 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) goto out; } - ret = filemap_write_and_wait_range(inode->i_mapping, start, end); + ret = file_write_and_wait_range(file, start, end); if (ret) return ret; /* diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 98ac2f1f23b3..507bfb3344d4 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -294,7 +294,6 @@ void ext4_free_inode(handle_t *handle, struct inode *inode) * as writing the quota to disk may need the lock as well. */ dquot_initialize(inode); - ext4_xattr_delete_inode(handle, inode); dquot_free_inode(inode); dquot_drop(inode); @@ -743,8 +742,9 @@ out: */ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir, umode_t mode, const struct qstr *qstr, - __u32 goal, uid_t *owner, int handle_type, - unsigned int line_no, int nblocks) + __u32 goal, uid_t *owner, __u32 i_flags, + int handle_type, unsigned int line_no, + int nblocks) { struct super_block *sb; struct buffer_head *inode_bitmap_bh = NULL; @@ -766,30 +766,69 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir, if (!dir || !dir->i_nlink) return ERR_PTR(-EPERM); - if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb)))) + sb = dir->i_sb; + sbi = EXT4_SB(sb); + + if (unlikely(ext4_forced_shutdown(sbi))) return ERR_PTR(-EIO); - if ((ext4_encrypted_inode(dir) || - DUMMY_ENCRYPTION_ENABLED(EXT4_SB(dir->i_sb))) && - (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))) { + if ((ext4_encrypted_inode(dir) || DUMMY_ENCRYPTION_ENABLED(sbi)) && + (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) && + !(i_flags & EXT4_EA_INODE_FL)) { err = fscrypt_get_encryption_info(dir); if (err) return ERR_PTR(err); if (!fscrypt_has_encryption_key(dir)) return ERR_PTR(-ENOKEY); - if (!handle) - nblocks += EXT4_DATA_TRANS_BLOCKS(dir->i_sb); encrypt = 1; } - sb = dir->i_sb; + if (!handle && sbi->s_journal && !(i_flags & EXT4_EA_INODE_FL)) { +#ifdef CONFIG_EXT4_FS_POSIX_ACL + struct posix_acl *p = get_acl(dir, ACL_TYPE_DEFAULT); + + if (p) { + int acl_size = p->a_count * sizeof(ext4_acl_entry); + + nblocks += (S_ISDIR(mode) ? 2 : 1) * + __ext4_xattr_set_credits(sb, NULL /* inode */, + NULL /* block_bh */, acl_size, + true /* is_create */); + posix_acl_release(p); + } +#endif + +#ifdef CONFIG_SECURITY + { + int num_security_xattrs = 1; + +#ifdef CONFIG_INTEGRITY + num_security_xattrs++; +#endif + /* + * We assume that security xattrs are never + * more than 1k. In practice they are under + * 128 bytes. + */ + nblocks += num_security_xattrs * + __ext4_xattr_set_credits(sb, NULL /* inode */, + NULL /* block_bh */, 1024, + true /* is_create */); + } +#endif + if (encrypt) + nblocks += __ext4_xattr_set_credits(sb, + NULL /* inode */, NULL /* block_bh */, + FSCRYPT_SET_CONTEXT_MAX_SIZE, + true /* is_create */); + } + ngroups = ext4_get_groups_count(sb); trace_ext4_request_inode(dir, mode); inode = new_inode(sb); if (!inode) return ERR_PTR(-ENOMEM); ei = EXT4_I(inode); - sbi = EXT4_SB(sb); /* * Initialize owners and quota early so that we don't have to account @@ -1053,6 +1092,7 @@ got: /* Don't inherit extent flag from directory, amongst others. */ ei->i_flags = ext4_mask_flags(mode, EXT4_I(dir)->i_flags & EXT4_FL_INHERITED); + ei->i_flags |= i_flags; ei->i_file_acl = 0; ei->i_dtime = 0; ei->i_block_group = group; @@ -1109,13 +1149,15 @@ got: goto fail_free_drop; } - err = ext4_init_acl(handle, inode, dir); - if (err) - goto fail_free_drop; + if (!(ei->i_flags & EXT4_EA_INODE_FL)) { + err = ext4_init_acl(handle, inode, dir); + if (err) + goto fail_free_drop; - err = ext4_init_security(handle, inode, dir, qstr); - if (err) - goto fail_free_drop; + err = ext4_init_security(handle, inode, dir, qstr); + if (err) + goto fail_free_drop; + } if (ext4_has_feature_extents(sb)) { /* set extent flag only for directory, file and normal symlink*/ diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index bc15c2c17633..7ffa290cbb8e 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -829,7 +829,8 @@ static int ext4_clear_blocks(handle_t *handle, struct inode *inode, int flags = EXT4_FREE_BLOCKS_VALIDATED; int err; - if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) + if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode) || + ext4_test_inode_flag(inode, EXT4_INODE_EA_INODE)) flags |= EXT4_FREE_BLOCKS_FORGET | EXT4_FREE_BLOCKS_METADATA; else if (ext4_should_journal_data(inode)) flags |= EXT4_FREE_BLOCKS_FORGET; diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 8d141c0c8ff9..28c5c3abddb3 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -61,7 +61,7 @@ static int get_max_inline_xattr_value_size(struct inode *inode, /* Compute min_offs. */ for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) { - if (!entry->e_value_block && entry->e_value_size) { + if (!entry->e_value_inum && entry->e_value_size) { size_t offs = le16_to_cpu(entry->e_value_offs); if (offs < min_offs) min_offs = offs; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 5cf82d03968c..3c600f02673f 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -144,16 +144,12 @@ static int ext4_meta_trans_blocks(struct inode *inode, int lblocks, /* * Test whether an inode is a fast symlink. + * A fast symlink has its symlink data stored in ext4_inode_info->i_data. */ int ext4_inode_is_fast_symlink(struct inode *inode) { - int ea_blocks = EXT4_I(inode)->i_file_acl ? - EXT4_CLUSTER_SIZE(inode->i_sb) >> 9 : 0; - - if (ext4_has_inline_data(inode)) - return 0; - - return (S_ISLNK(inode->i_mode) && inode->i_blocks - ea_blocks == 0); + return S_ISLNK(inode->i_mode) && inode->i_size && + (inode->i_size < EXT4_N_BLOCKS * 4); } /* @@ -189,6 +185,8 @@ void ext4_evict_inode(struct inode *inode) { handle_t *handle; int err; + int extra_credits = 3; + struct ext4_xattr_inode_array *ea_inode_array = NULL; trace_ext4_evict_inode(inode); @@ -213,7 +211,8 @@ void ext4_evict_inode(struct inode *inode) */ if (inode->i_ino != EXT4_JOURNAL_INO && ext4_should_journal_data(inode) && - (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode))) { + (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode)) && + inode->i_data.nrpages) { journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; tid_t commit_tid = EXT4_I(inode)->i_datasync_tid; @@ -238,8 +237,12 @@ void ext4_evict_inode(struct inode *inode) * protection against it */ sb_start_intwrite(inode->i_sb); + + if (!IS_NOQUOTA(inode)) + extra_credits += EXT4_MAXQUOTAS_DEL_BLOCKS(inode->i_sb); + handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, - ext4_blocks_for_truncate(inode)+3); + ext4_blocks_for_truncate(inode)+extra_credits); if (IS_ERR(handle)) { ext4_std_error(inode->i_sb, PTR_ERR(handle)); /* @@ -254,6 +257,16 @@ void ext4_evict_inode(struct inode *inode) if (IS_SYNC(inode)) ext4_handle_sync(handle); + + /* + * Set inode->i_size to 0 before calling ext4_truncate(). We need + * special handling of symlinks here because i_size is used to + * determine whether ext4_inode_info->i_data contains symlink data or + * block mappings. Setting i_size to 0 will remove its fast symlink + * status. Erase i_data so that it becomes a valid empty block map. + */ + if (ext4_inode_is_fast_symlink(inode)) + memset(EXT4_I(inode)->i_data, 0, sizeof(EXT4_I(inode)->i_data)); inode->i_size = 0; err = ext4_mark_inode_dirty(handle, inode); if (err) { @@ -271,25 +284,17 @@ void ext4_evict_inode(struct inode *inode) } } - /* - * ext4_ext_truncate() doesn't reserve any slop when it - * restarts journal transactions; therefore there may not be - * enough credits left in the handle to remove the inode from - * the orphan list and set the dtime field. - */ - if (!ext4_handle_has_enough_credits(handle, 3)) { - err = ext4_journal_extend(handle, 3); - if (err > 0) - err = ext4_journal_restart(handle, 3); - if (err != 0) { - ext4_warning(inode->i_sb, - "couldn't extend journal (err %d)", err); - stop_handle: - ext4_journal_stop(handle); - ext4_orphan_del(NULL, inode); - sb_end_intwrite(inode->i_sb); - goto no_delete; - } + /* Remove xattr references. */ + err = ext4_xattr_delete_inode(handle, inode, &ea_inode_array, + extra_credits); + if (err) { + ext4_warning(inode->i_sb, "xattr delete (err %d)", err); +stop_handle: + ext4_journal_stop(handle); + ext4_orphan_del(NULL, inode); + sb_end_intwrite(inode->i_sb); + ext4_xattr_inode_array_free(ea_inode_array); + goto no_delete; } /* @@ -317,6 +322,7 @@ void ext4_evict_inode(struct inode *inode) ext4_free_inode(handle, inode); ext4_journal_stop(handle); sb_end_intwrite(inode->i_sb); + ext4_xattr_inode_array_free(ea_inode_array); return; no_delete: ext4_clear_inode(inode); /* We must guarantee clearing of inode... */ @@ -710,7 +716,7 @@ out_sem: if (map->m_flags & EXT4_MAP_NEW && !(map->m_flags & EXT4_MAP_UNWRITTEN) && !(flags & EXT4_GET_BLOCKS_ZERO) && - !IS_NOQUOTA(inode) && + !ext4_is_quota_file(inode) && ext4_should_order_data(inode)) { if (flags & EXT4_GET_BLOCKS_IO_SUBMIT) ret = ext4_jbd2_inode_add_wait(handle, inode); @@ -4712,7 +4718,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) if (ext4_has_feature_64bit(sb)) ei->i_file_acl |= ((__u64)le16_to_cpu(raw_inode->i_file_acl_high)) << 32; - inode->i_size = ext4_isize(raw_inode); + inode->i_size = ext4_isize(sb, raw_inode); if ((size = i_size_read(inode)) < 0) { EXT4_ERROR_INODE(inode, "bad i_size value: %lld", size); ret = -EFSCORRUPTED; @@ -4846,6 +4852,15 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) } brelse(iloc.bh); ext4_set_inode_flags(inode); + + if (ei->i_flags & EXT4_EA_INODE_FL) { + ext4_xattr_inode_set_class(inode); + + inode_lock(inode); + inode->i_flags |= S_NOQUOTA; + inode_unlock(inode); + } + unlock_new_inode(inode); return inode; @@ -5037,7 +5052,7 @@ static int ext4_do_update_inode(handle_t *handle, raw_inode->i_file_acl_high = cpu_to_le16(ei->i_file_acl >> 32); raw_inode->i_file_acl_lo = cpu_to_le32(ei->i_file_acl); - if (ei->i_disksize != ext4_isize(raw_inode)) { + if (ei->i_disksize != ext4_isize(inode->i_sb, raw_inode)) { ext4_isize_set(raw_inode, ei->i_disksize); need_datasync = 1; } @@ -5287,7 +5302,14 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) error = PTR_ERR(handle); goto err_out; } + + /* dquot_transfer() calls back ext4_get_inode_usage() which + * counts xattr inode references. + */ + down_read(&EXT4_I(inode)->xattr_sem); error = dquot_transfer(inode, attr); + up_read(&EXT4_I(inode)->xattr_sem); + if (error) { ext4_journal_stop(handle); return error; @@ -5307,6 +5329,14 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) loff_t oldsize = inode->i_size; int shrink = (attr->ia_size <= inode->i_size); + if (ext4_encrypted_inode(inode)) { + error = fscrypt_get_encryption_info(inode); + if (error) + return error; + if (!fscrypt_has_encryption_key(inode)) + return -ENOKEY; + } + if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 0c21e22acd74..42b3a73143cf 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -218,7 +218,7 @@ static int ext4_ioctl_setflags(struct inode *inode, unsigned int jflag; /* Is it quota file? Do not allow user to mess with it */ - if (IS_NOQUOTA(inode)) + if (ext4_is_quota_file(inode)) goto flags_out; oldflags = ei->i_flags; @@ -342,7 +342,7 @@ static int ext4_ioctl_setproject(struct file *filp, __u32 projid) err = -EPERM; inode_lock(inode); /* Is it quota file? Do not allow user to mess with it */ - if (IS_NOQUOTA(inode)) + if (ext4_is_quota_file(inode)) goto out_unlock; err = ext4_get_inode_loc(inode, &iloc); @@ -373,7 +373,13 @@ static int ext4_ioctl_setproject(struct file *filp, __u32 projid) transfer_to[PRJQUOTA] = dqget(sb, make_kqid_projid(kprojid)); if (!IS_ERR(transfer_to[PRJQUOTA])) { + + /* __dquot_transfer() calls back ext4_get_inode_usage() which + * counts xattr inode references. + */ + down_read(&EXT4_I(inode)->xattr_sem); err = __dquot_transfer(inode, transfer_to); + up_read(&EXT4_I(inode)->xattr_sem); dqput(transfer_to[PRJQUOTA]); if (err) goto out_dirty; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index b7928cddd539..581e357e8406 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -367,8 +367,6 @@ static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, ext4_group_t group); static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap, ext4_group_t group); -static void ext4_free_data_callback(struct super_block *sb, - struct ext4_journal_cb_entry *jce, int rc); static inline void *mb_correct_addr_and_bit(int *bit, void *addr) { @@ -2639,6 +2637,7 @@ int ext4_mb_init(struct super_block *sb) spin_lock_init(&sbi->s_md_lock); spin_lock_init(&sbi->s_bal_lock); sbi->s_mb_free_pending = 0; + INIT_LIST_HEAD(&sbi->s_freed_data_list); sbi->s_mb_max_to_scan = MB_DEFAULT_MAX_TO_SCAN; sbi->s_mb_min_to_scan = MB_DEFAULT_MIN_TO_SCAN; @@ -2782,7 +2781,8 @@ int ext4_mb_release(struct super_block *sb) } static inline int ext4_issue_discard(struct super_block *sb, - ext4_group_t block_group, ext4_grpblk_t cluster, int count) + ext4_group_t block_group, ext4_grpblk_t cluster, int count, + struct bio **biop) { ext4_fsblk_t discard_block; @@ -2791,18 +2791,18 @@ static inline int ext4_issue_discard(struct super_block *sb, count = EXT4_C2B(EXT4_SB(sb), count); trace_ext4_discard_blocks(sb, (unsigned long long) discard_block, count); - return sb_issue_discard(sb, discard_block, count, GFP_NOFS, 0); + if (biop) { + return __blkdev_issue_discard(sb->s_bdev, + (sector_t)discard_block << (sb->s_blocksize_bits - 9), + (sector_t)count << (sb->s_blocksize_bits - 9), + GFP_NOFS, 0, biop); + } else + return sb_issue_discard(sb, discard_block, count, GFP_NOFS, 0); } -/* - * This function is called by the jbd2 layer once the commit has finished, - * so we know we can free the blocks that were released with that commit. - */ -static void ext4_free_data_callback(struct super_block *sb, - struct ext4_journal_cb_entry *jce, - int rc) +static void ext4_free_data_in_buddy(struct super_block *sb, + struct ext4_free_data *entry) { - struct ext4_free_data *entry = (struct ext4_free_data *)jce; struct ext4_buddy e4b; struct ext4_group_info *db; int err, count = 0, count2 = 0; @@ -2810,18 +2810,6 @@ static void ext4_free_data_callback(struct super_block *sb, mb_debug(1, "gonna free %u blocks in group %u (0x%p):", entry->efd_count, entry->efd_group, entry); - if (test_opt(sb, DISCARD)) { - err = ext4_issue_discard(sb, entry->efd_group, - entry->efd_start_cluster, - entry->efd_count); - if (err && err != -EOPNOTSUPP) - ext4_msg(sb, KERN_WARNING, "discard request in" - " group:%d block:%d count:%d failed" - " with %d", entry->efd_group, - entry->efd_start_cluster, - entry->efd_count, err); - } - err = ext4_mb_load_buddy(sb, entry->efd_group, &e4b); /* we expect to find existing buddy because it's pinned */ BUG_ON(err != 0); @@ -2862,6 +2850,56 @@ static void ext4_free_data_callback(struct super_block *sb, mb_debug(1, "freed %u blocks in %u structures\n", count, count2); } +/* + * This function is called by the jbd2 layer once the commit has finished, + * so we know we can free the blocks that were released with that commit. + */ +void ext4_process_freed_data(struct super_block *sb, tid_t commit_tid) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_free_data *entry, *tmp; + struct bio *discard_bio = NULL; + struct list_head freed_data_list; + struct list_head *cut_pos = NULL; + int err; + + INIT_LIST_HEAD(&freed_data_list); + + spin_lock(&sbi->s_md_lock); + list_for_each_entry(entry, &sbi->s_freed_data_list, efd_list) { + if (entry->efd_tid != commit_tid) + break; + cut_pos = &entry->efd_list; + } + if (cut_pos) + list_cut_position(&freed_data_list, &sbi->s_freed_data_list, + cut_pos); + spin_unlock(&sbi->s_md_lock); + + if (test_opt(sb, DISCARD)) { + list_for_each_entry(entry, &freed_data_list, efd_list) { + err = ext4_issue_discard(sb, entry->efd_group, + entry->efd_start_cluster, + entry->efd_count, + &discard_bio); + if (err && err != -EOPNOTSUPP) { + ext4_msg(sb, KERN_WARNING, "discard request in" + " group:%d block:%d count:%d failed" + " with %d", entry->efd_group, + entry->efd_start_cluster, + entry->efd_count, err); + } else if (err == -EOPNOTSUPP) + break; + } + + if (discard_bio) + submit_bio_wait(discard_bio); + } + + list_for_each_entry_safe(entry, tmp, &freed_data_list, efd_list) + ext4_free_data_in_buddy(sb, entry); +} + int __init ext4_init_mballoc(void) { ext4_pspace_cachep = KMEM_CACHE(ext4_prealloc_space, @@ -3529,7 +3567,7 @@ void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, ext4_set_bits(bitmap, start, len); preallocated += len; } - mb_debug(1, "prellocated %u for group %u\n", preallocated, group); + mb_debug(1, "preallocated %u for group %u\n", preallocated, group); } static void ext4_mb_pa_callback(struct rcu_head *head) @@ -4464,7 +4502,7 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle, trace_ext4_request_blocks(ar); /* Allow to use superuser reservation for quota file */ - if (IS_NOQUOTA(ar->inode)) + if (ext4_is_quota_file(ar->inode)) ar->flags |= EXT4_MB_USE_ROOT_BLOCKS; if ((ar->flags & EXT4_MB_DELALLOC_RESERVED) == 0) { @@ -4583,14 +4621,28 @@ out: * are contiguous, AND the extents were freed by the same transaction, * AND the blocks are associated with the same group. */ -static int can_merge(struct ext4_free_data *entry1, - struct ext4_free_data *entry2) +static void ext4_try_merge_freed_extent(struct ext4_sb_info *sbi, + struct ext4_free_data *entry, + struct ext4_free_data *new_entry, + struct rb_root *entry_rb_root) { - if ((entry1->efd_tid == entry2->efd_tid) && - (entry1->efd_group == entry2->efd_group) && - ((entry1->efd_start_cluster + entry1->efd_count) == entry2->efd_start_cluster)) - return 1; - return 0; + if ((entry->efd_tid != new_entry->efd_tid) || + (entry->efd_group != new_entry->efd_group)) + return; + if (entry->efd_start_cluster + entry->efd_count == + new_entry->efd_start_cluster) { + new_entry->efd_start_cluster = entry->efd_start_cluster; + new_entry->efd_count += entry->efd_count; + } else if (new_entry->efd_start_cluster + new_entry->efd_count == + entry->efd_start_cluster) { + new_entry->efd_count += entry->efd_count; + } else + return; + spin_lock(&sbi->s_md_lock); + list_del(&entry->efd_list); + spin_unlock(&sbi->s_md_lock); + rb_erase(&entry->efd_node, entry_rb_root); + kmem_cache_free(ext4_free_data_cachep, entry); } static noinline_for_stack int @@ -4646,29 +4698,19 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b, node = rb_prev(new_node); if (node) { entry = rb_entry(node, struct ext4_free_data, efd_node); - if (can_merge(entry, new_entry) && - ext4_journal_callback_try_del(handle, &entry->efd_jce)) { - new_entry->efd_start_cluster = entry->efd_start_cluster; - new_entry->efd_count += entry->efd_count; - rb_erase(node, &(db->bb_free_root)); - kmem_cache_free(ext4_free_data_cachep, entry); - } + ext4_try_merge_freed_extent(sbi, entry, new_entry, + &(db->bb_free_root)); } node = rb_next(new_node); if (node) { entry = rb_entry(node, struct ext4_free_data, efd_node); - if (can_merge(new_entry, entry) && - ext4_journal_callback_try_del(handle, &entry->efd_jce)) { - new_entry->efd_count += entry->efd_count; - rb_erase(node, &(db->bb_free_root)); - kmem_cache_free(ext4_free_data_cachep, entry); - } + ext4_try_merge_freed_extent(sbi, entry, new_entry, + &(db->bb_free_root)); } - /* Add the extent to transaction's private list */ - new_entry->efd_jce.jce_func = ext4_free_data_callback; + spin_lock(&sbi->s_md_lock); - _ext4_journal_callback_add(handle, &new_entry->efd_jce); + list_add_tail(&new_entry->efd_list, &sbi->s_freed_data_list); sbi->s_mb_free_pending += clusters; spin_unlock(&sbi->s_md_lock); return 0; @@ -4871,7 +4913,8 @@ do_more: * them with group lock_held */ if (test_opt(sb, DISCARD)) { - err = ext4_issue_discard(sb, block_group, bit, count); + err = ext4_issue_discard(sb, block_group, bit, count, + NULL); if (err && err != -EOPNOTSUPP) ext4_msg(sb, KERN_WARNING, "discard request in" " group:%d block:%d count:%lu failed" @@ -5094,7 +5137,7 @@ __acquires(bitlock) */ mb_mark_used(e4b, &ex); ext4_unlock_group(sb, group); - ret = ext4_issue_discard(sb, group, start, count); + ret = ext4_issue_discard(sb, group, start, count, NULL); ext4_lock_group(sb, group); mb_free_blocks(NULL, e4b, start, ex.fe_len); return ret; diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h index 2bed62084a8c..009300ee1561 100644 --- a/fs/ext4/mballoc.h +++ b/fs/ext4/mballoc.h @@ -78,10 +78,8 @@ do { \ struct ext4_free_data { - /* MUST be the first member */ - struct ext4_journal_cb_entry efd_jce; - - /* ext4_free_data private data starts from here */ + /* this links the free block information from sb_info */ + struct list_head efd_list; /* this links the free block information from group_info */ struct rb_node efd_node; diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index 364ea4d4a943..cf5181b62df1 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -475,7 +475,7 @@ int ext4_ext_migrate(struct inode *inode) owner[0] = i_uid_read(inode); owner[1] = i_gid_read(inode); tmp_inode = ext4_new_inode(handle, d_inode(inode->i_sb->s_root), - S_IFREG, NULL, goal, owner); + S_IFREG, NULL, goal, owner, 0); if (IS_ERR(tmp_inode)) { retval = PTR_ERR(tmp_inode); ext4_journal_stop(handle); diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index c992ef2c2f94..9bb36909ec92 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -484,7 +484,7 @@ mext_check_arguments(struct inode *orig_inode, return -EBUSY; } - if (IS_NOQUOTA(orig_inode) || IS_NOQUOTA(donor_inode)) { + if (ext4_is_quota_file(orig_inode) && ext4_is_quota_file(donor_inode)) { ext4_debug("ext4 move extent: The argument files should " "not be quota files [ino:orig %lu, donor %lu]\n", orig_inode->i_ino, donor_inode->i_ino); diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 404256caf9cf..13f0cadb1238 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -513,7 +513,7 @@ ext4_next_entry(struct ext4_dir_entry_2 *p, unsigned long blocksize) static inline ext4_lblk_t dx_get_block(struct dx_entry *entry) { - return le32_to_cpu(entry->block) & 0x00ffffff; + return le32_to_cpu(entry->block) & 0x0fffffff; } static inline void dx_set_block(struct dx_entry *entry, ext4_lblk_t value) @@ -739,6 +739,7 @@ dx_probe(struct ext4_filename *fname, struct inode *dir, struct dx_frame *ret_err = ERR_PTR(ERR_BAD_DX_DIR); u32 hash; + memset(frame_in, 0, EXT4_HTREE_LEVEL * sizeof(frame_in[0])); frame->bh = ext4_read_dirblock(dir, 0, INDEX); if (IS_ERR(frame->bh)) return (struct dx_frame *) frame->bh; @@ -768,9 +769,15 @@ dx_probe(struct ext4_filename *fname, struct inode *dir, } indirect = root->info.indirect_levels; - if (indirect > 1) { - ext4_warning_inode(dir, "Unimplemented hash depth: %#06x", - root->info.indirect_levels); + if (indirect >= ext4_dir_htree_level(dir->i_sb)) { + ext4_warning(dir->i_sb, + "Directory (ino: %lu) htree depth %#06x exceed" + "supported value", dir->i_ino, + ext4_dir_htree_level(dir->i_sb)); + if (ext4_dir_htree_level(dir->i_sb) < EXT4_HTREE_LEVEL) { + ext4_warning(dir->i_sb, "Enable large directory " + "feature to access it"); + } goto fail; } @@ -859,12 +866,19 @@ fail: static void dx_release(struct dx_frame *frames) { + struct dx_root_info *info; + int i; + if (frames[0].bh == NULL) return; - if (((struct dx_root *)frames[0].bh->b_data)->info.indirect_levels) - brelse(frames[1].bh); - brelse(frames[0].bh); + info = &((struct dx_root *)frames[0].bh->b_data)->info; + for (i = 0; i <= info->indirect_levels; i++) { + if (frames[i].bh == NULL) + break; + brelse(frames[i].bh); + frames[i].bh = NULL; + } } /* @@ -1050,7 +1064,7 @@ int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash, { struct dx_hash_info hinfo; struct ext4_dir_entry_2 *de; - struct dx_frame frames[2], *frame; + struct dx_frame frames[EXT4_HTREE_LEVEL], *frame; struct inode *dir; ext4_lblk_t block; int count = 0; @@ -1428,11 +1442,11 @@ restart: goto next; wait_on_buffer(bh); if (!buffer_uptodate(bh)) { - /* read error, skip block & hope for the best */ EXT4_ERROR_INODE(dir, "reading directory lblock %lu", (unsigned long) block); brelse(bh); - goto next; + ret = ERR_PTR(-EIO); + goto cleanup_and_exit; } if (!buffer_verified(bh) && !is_dx_internal_node(dir, block, @@ -1442,7 +1456,8 @@ restart: EXT4_ERROR_INODE(dir, "checksumming directory " "block %lu", (unsigned long)block); brelse(bh); - goto next; + ret = ERR_PTR(-EFSBADCRC); + goto cleanup_and_exit; } set_buffer_verified(bh); i = search_dirblock(bh, dir, &fname, @@ -1485,7 +1500,7 @@ static struct buffer_head * ext4_dx_find_entry(struct inode *dir, struct ext4_dir_entry_2 **res_dir) { struct super_block * sb = dir->i_sb; - struct dx_frame frames[2], *frame; + struct dx_frame frames[EXT4_HTREE_LEVEL], *frame; struct buffer_head *bh; ext4_lblk_t block; int retval; @@ -1889,7 +1904,7 @@ static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname, */ dir->i_mtime = dir->i_ctime = current_time(dir); ext4_update_dx_flag(dir); - dir->i_version++; + inode_inc_iversion(dir); ext4_mark_inode_dirty(handle, dir); BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata"); err = ext4_handle_dirty_dirent_node(handle, dir, bh); @@ -1908,7 +1923,7 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, { struct buffer_head *bh2; struct dx_root *root; - struct dx_frame frames[2], *frame; + struct dx_frame frames[EXT4_HTREE_LEVEL], *frame; struct dx_entry *entries; struct ext4_dir_entry_2 *de, *de2; struct ext4_dir_entry_tail *t; @@ -2127,13 +2142,16 @@ out: static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname, struct inode *dir, struct inode *inode) { - struct dx_frame frames[2], *frame; + struct dx_frame frames[EXT4_HTREE_LEVEL], *frame; struct dx_entry *entries, *at; struct buffer_head *bh; struct super_block *sb = dir->i_sb; struct ext4_dir_entry_2 *de; + int restart; int err; +again: + restart = 0; frame = dx_probe(fname, dir, NULL, frames); if (IS_ERR(frame)) return PTR_ERR(frame); @@ -2155,24 +2173,44 @@ static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname, if (err != -ENOSPC) goto cleanup; + err = 0; /* Block full, should compress but for now just split */ dxtrace(printk(KERN_DEBUG "using %u of %u node entries\n", dx_get_count(entries), dx_get_limit(entries))); /* Need to split index? */ if (dx_get_count(entries) == dx_get_limit(entries)) { ext4_lblk_t newblock; - unsigned icount = dx_get_count(entries); - int levels = frame - frames; + int levels = frame - frames + 1; + unsigned int icount; + int add_level = 1; struct dx_entry *entries2; struct dx_node *node2; struct buffer_head *bh2; - if (levels && (dx_get_count(frames->entries) == - dx_get_limit(frames->entries))) { - ext4_warning_inode(dir, "Directory index full!"); + while (frame > frames) { + if (dx_get_count((frame - 1)->entries) < + dx_get_limit((frame - 1)->entries)) { + add_level = 0; + break; + } + frame--; /* split higher index block */ + at = frame->at; + entries = frame->entries; + restart = 1; + } + if (add_level && levels == ext4_dir_htree_level(sb)) { + ext4_warning(sb, "Directory (ino: %lu) index full, " + "reach max htree level :%d", + dir->i_ino, levels); + if (ext4_dir_htree_level(sb) < EXT4_HTREE_LEVEL) { + ext4_warning(sb, "Large directory feature is " + "not enabled on this " + "filesystem"); + } err = -ENOSPC; goto cleanup; } + icount = dx_get_count(entries); bh2 = ext4_append(handle, dir, &newblock); if (IS_ERR(bh2)) { err = PTR_ERR(bh2); @@ -2187,7 +2225,7 @@ static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname, err = ext4_journal_get_write_access(handle, frame->bh); if (err) goto journal_error; - if (levels) { + if (!add_level) { unsigned icount1 = icount/2, icount2 = icount - icount1; unsigned hash2 = dx_get_hash(entries + icount1); dxtrace(printk(KERN_DEBUG "Split index %i/%i\n", @@ -2195,7 +2233,7 @@ static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname, BUFFER_TRACE(frame->bh, "get_write_access"); /* index root */ err = ext4_journal_get_write_access(handle, - frames[0].bh); + (frame - 1)->bh); if (err) goto journal_error; @@ -2211,17 +2249,25 @@ static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname, frame->entries = entries = entries2; swap(frame->bh, bh2); } - dx_insert_block(frames + 0, hash2, newblock); - dxtrace(dx_show_index("node", frames[1].entries)); + dx_insert_block((frame - 1), hash2, newblock); + dxtrace(dx_show_index("node", frame->entries)); dxtrace(dx_show_index("node", ((struct dx_node *) bh2->b_data)->entries)); err = ext4_handle_dirty_dx_node(handle, dir, bh2); if (err) goto journal_error; brelse (bh2); + err = ext4_handle_dirty_dx_node(handle, dir, + (frame - 1)->bh); + if (err) + goto journal_error; + if (restart) { + err = ext4_handle_dirty_dx_node(handle, dir, + frame->bh); + goto journal_error; + } } else { - dxtrace(printk(KERN_DEBUG - "Creating second level index...\n")); + struct dx_root *dxroot; memcpy((char *) entries2, (char *) entries, icount * sizeof(struct dx_entry)); dx_set_limit(entries2, dx_node_limit(dir)); @@ -2229,22 +2275,18 @@ static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname, /* Set up root */ dx_set_count(entries, 1); dx_set_block(entries + 0, newblock); - ((struct dx_root *) frames[0].bh->b_data)->info.indirect_levels = 1; - - /* Add new access path frame */ - frame = frames + 1; - frame->at = at = at - entries + entries2; - frame->entries = entries = entries2; - frame->bh = bh2; - err = ext4_journal_get_write_access(handle, - frame->bh); + dxroot = (struct dx_root *)frames[0].bh->b_data; + dxroot->info.indirect_levels += 1; + dxtrace(printk(KERN_DEBUG + "Creating %d level index...\n", + info->indirect_levels)); + err = ext4_handle_dirty_dx_node(handle, dir, frame->bh); if (err) goto journal_error; - } - err = ext4_handle_dirty_dx_node(handle, dir, frames[0].bh); - if (err) { - ext4_std_error(inode->i_sb, err); - goto cleanup; + err = ext4_handle_dirty_dx_node(handle, dir, bh2); + brelse(bh2); + restart = 1; + goto journal_error; } } de = do_split(handle, dir, &bh, frame, &fname->hinfo); @@ -2256,10 +2298,15 @@ static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname, goto cleanup; journal_error: - ext4_std_error(dir->i_sb, err); + ext4_std_error(dir->i_sb, err); /* this is a no-op if err == 0 */ cleanup: brelse(bh); dx_release(frames); + /* @restart is true means htree-path has been changed, we need to + * repeat dx_probe() to find out valid htree-path + */ + if (restart && err == 0) + goto again; return err; } @@ -2296,7 +2343,7 @@ int ext4_generic_delete_entry(handle_t *handle, blocksize); else de->inode = 0; - dir->i_version++; + inode_inc_iversion(dir); return 0; } i += ext4_rec_len_from_disk(de->rec_len, blocksize); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 9006cb5857b8..0886fe82e9c4 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -373,6 +373,9 @@ static void ext4_journal_commit_callback(journal_t *journal, transaction_t *txn) struct ext4_journal_cb_entry *jce; BUG_ON(txn->t_state == T_FINISHED); + + ext4_process_freed_data(sb, txn->t_tid); + spin_lock(&sbi->s_md_lock); while (!list_empty(&txn->t_private_list)) { jce = list_entry(txn->t_private_list.next, @@ -927,9 +930,13 @@ static void ext4_put_super(struct super_block *sb) invalidate_bdev(sbi->journal_bdev); ext4_blkdev_remove(sbi); } - if (sbi->s_mb_cache) { - ext4_xattr_destroy_cache(sbi->s_mb_cache); - sbi->s_mb_cache = NULL; + if (sbi->s_ea_inode_cache) { + ext4_xattr_destroy_cache(sbi->s_ea_inode_cache); + sbi->s_ea_inode_cache = NULL; + } + if (sbi->s_ea_block_cache) { + ext4_xattr_destroy_cache(sbi->s_ea_block_cache); + sbi->s_ea_block_cache = NULL; } if (sbi->s_mmp_tsk) kthread_stop(sbi->s_mmp_tsk); @@ -1143,7 +1150,16 @@ static int ext4_set_context(struct inode *inode, const void *ctx, size_t len, void *fs_data) { handle_t *handle = fs_data; - int res, res2, retries = 0; + int res, res2, credits, retries = 0; + + /* + * Encrypting the root directory is not allowed because e2fsck expects + * lost+found to exist and be unencrypted, and encrypting the root + * directory would imply encrypting the lost+found directory as well as + * the filename "lost+found" itself. + */ + if (inode->i_ino == EXT4_ROOT_INO) + return -EPERM; res = ext4_convert_inline_data(inode); if (res) @@ -1178,8 +1194,12 @@ static int ext4_set_context(struct inode *inode, const void *ctx, size_t len, if (res) return res; retry: - handle = ext4_journal_start(inode, EXT4_HT_MISC, - ext4_jbd2_credits_xattr(inode)); + res = ext4_xattr_set_credits(inode, len, false /* is_create */, + &credits); + if (res) + return res; + + handle = ext4_journal_start(inode, EXT4_HT_MISC, credits); if (IS_ERR(handle)) return PTR_ERR(handle); @@ -1203,7 +1223,7 @@ retry: return res; } -static int ext4_dummy_context(struct inode *inode) +static bool ext4_dummy_context(struct inode *inode) { return DUMMY_ENCRYPTION_ENABLED(EXT4_SB(inode->i_sb)); } @@ -1256,16 +1276,17 @@ static struct dquot **ext4_get_dquots(struct inode *inode) } static const struct dquot_operations ext4_quota_operations = { - .get_reserved_space = ext4_get_reserved_space, - .write_dquot = ext4_write_dquot, - .acquire_dquot = ext4_acquire_dquot, - .release_dquot = ext4_release_dquot, - .mark_dirty = ext4_mark_dquot_dirty, - .write_info = ext4_write_info, - .alloc_dquot = dquot_alloc, - .destroy_dquot = dquot_destroy, - .get_projid = ext4_get_projid, - .get_next_id = ext4_get_next_id, + .get_reserved_space = ext4_get_reserved_space, + .write_dquot = ext4_write_dquot, + .acquire_dquot = ext4_acquire_dquot, + .release_dquot = ext4_release_dquot, + .mark_dirty = ext4_mark_dquot_dirty, + .write_info = ext4_write_info, + .alloc_dquot = dquot_alloc, + .destroy_dquot = dquot_destroy, + .get_projid = ext4_get_projid, + .get_inode_usage = ext4_get_inode_usage, + .get_next_id = ext4_get_next_id, }; static const struct quotactl_ops ext4_qctl_operations = { @@ -1328,7 +1349,7 @@ enum { Opt_inode_readahead_blks, Opt_journal_ioprio, Opt_dioread_nolock, Opt_dioread_lock, Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable, - Opt_max_dir_size_kb, Opt_nojournal_checksum, + Opt_max_dir_size_kb, Opt_nojournal_checksum, Opt_nombcache, }; static const match_table_t tokens = { @@ -1411,6 +1432,8 @@ static const match_table_t tokens = { {Opt_noinit_itable, "noinit_itable"}, {Opt_max_dir_size_kb, "max_dir_size_kb=%u"}, {Opt_test_dummy_encryption, "test_dummy_encryption"}, + {Opt_nombcache, "nombcache"}, + {Opt_nombcache, "no_mbcache"}, /* for backward compatibility */ {Opt_removed, "check=none"}, /* mount option from ext2/3 */ {Opt_removed, "nocheck"}, /* mount option from ext2/3 */ {Opt_removed, "reservation"}, /* mount option from ext2/3 */ @@ -1618,6 +1641,7 @@ static const struct mount_opts { {Opt_jqfmt_vfsv1, QFMT_VFS_V1, MOPT_QFMT}, {Opt_max_dir_size_kb, 0, MOPT_GTE0}, {Opt_test_dummy_encryption, 0, MOPT_GTE0}, + {Opt_nombcache, EXT4_MOUNT_NO_MBCACHE, MOPT_SET}, {Opt_err, 0, 0} }; @@ -3445,7 +3469,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } /* Load the checksum driver */ - if (ext4_has_feature_metadata_csum(sb)) { + if (ext4_has_feature_metadata_csum(sb) || + ext4_has_feature_ea_inode(sb)) { sbi->s_chksum_driver = crypto_alloc_shash("crc32c", 0, 0); if (IS_ERR(sbi->s_chksum_driver)) { ext4_msg(sb, KERN_ERR, "Cannot load crc32c driver."); @@ -3467,7 +3492,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) /* Precompute checksum seed for all metadata */ if (ext4_has_feature_csum_seed(sb)) sbi->s_csum_seed = le32_to_cpu(es->s_checksum_seed); - else if (ext4_has_metadata_csum(sb)) + else if (ext4_has_metadata_csum(sb) || ext4_has_feature_ea_inode(sb)) sbi->s_csum_seed = ext4_chksum(sbi, ~0, es->s_uuid, sizeof(es->s_uuid)); @@ -3597,6 +3622,16 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) "The Hurd can't support 64-bit file systems"); goto failed_mount; } + + /* + * ea_inode feature uses l_i_version field which is not + * available in HURD_COMPAT mode. + */ + if (ext4_has_feature_ea_inode(sb)) { + ext4_msg(sb, KERN_ERR, + "ea_inode feature is not supported for Hurd"); + goto failed_mount; + } } if (IS_EXT2_SB(sb)) { @@ -4061,10 +4096,22 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_journal->j_commit_callback = ext4_journal_commit_callback; no_journal: - sbi->s_mb_cache = ext4_xattr_create_cache(); - if (!sbi->s_mb_cache) { - ext4_msg(sb, KERN_ERR, "Failed to create an mb_cache"); - goto failed_mount_wq; + if (!test_opt(sb, NO_MBCACHE)) { + sbi->s_ea_block_cache = ext4_xattr_create_cache(); + if (!sbi->s_ea_block_cache) { + ext4_msg(sb, KERN_ERR, + "Failed to create ea_block_cache"); + goto failed_mount_wq; + } + + if (ext4_has_feature_ea_inode(sb)) { + sbi->s_ea_inode_cache = ext4_xattr_create_cache(); + if (!sbi->s_ea_inode_cache) { + ext4_msg(sb, KERN_ERR, + "Failed to create ea_inode_cache"); + goto failed_mount_wq; + } + } } if ((DUMMY_ENCRYPTION_ENABLED(sbi) || ext4_has_feature_encrypt(sb)) && @@ -4296,9 +4343,13 @@ failed_mount4: if (EXT4_SB(sb)->rsv_conversion_wq) destroy_workqueue(EXT4_SB(sb)->rsv_conversion_wq); failed_mount_wq: - if (sbi->s_mb_cache) { - ext4_xattr_destroy_cache(sbi->s_mb_cache); - sbi->s_mb_cache = NULL; + if (sbi->s_ea_inode_cache) { + ext4_xattr_destroy_cache(sbi->s_ea_inode_cache); + sbi->s_ea_inode_cache = NULL; + } + if (sbi->s_ea_block_cache) { + ext4_xattr_destroy_cache(sbi->s_ea_block_cache); + sbi->s_ea_block_cache = NULL; } if (sbi->s_journal) { jbd2_journal_destroy(sbi->s_journal); @@ -4957,6 +5008,12 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) } } + if ((sbi->s_mount_opt ^ old_opts.s_mount_opt) & EXT4_MOUNT_NO_MBCACHE) { + ext4_msg(sb, KERN_ERR, "can't enable nombcache during remount"); + err = -EINVAL; + goto restore_opts; + } + if ((sbi->s_mount_opt ^ old_opts.s_mount_opt) & EXT4_MOUNT_DAX) { ext4_msg(sb, KERN_WARNING, "warning: refusing change of " "dax flag with busy inodes while remounting"); diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index d74dc5f81a04..48c7a7d55ed3 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -100,7 +100,7 @@ static ssize_t reserved_clusters_store(struct ext4_attr *a, int ret; ret = kstrtoull(skip_spaces(buf), 0, &val); - if (!ret || val >= clusters) + if (ret || val >= clusters) return -EINVAL; atomic64_set(&sbi->s_resv_clusters, val); diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 5d3c2536641c..cff4f41ced61 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -72,12 +72,14 @@ # define ea_bdebug(bh, fmt, ...) no_printk(fmt, ##__VA_ARGS__) #endif -static void ext4_xattr_cache_insert(struct mb_cache *, struct buffer_head *); -static struct buffer_head *ext4_xattr_cache_find(struct inode *, - struct ext4_xattr_header *, - struct mb_cache_entry **); -static void ext4_xattr_rehash(struct ext4_xattr_header *, - struct ext4_xattr_entry *); +static void ext4_xattr_block_cache_insert(struct mb_cache *, + struct buffer_head *); +static struct buffer_head * +ext4_xattr_block_cache_find(struct inode *, struct ext4_xattr_header *, + struct mb_cache_entry **); +static __le32 ext4_xattr_hash_entry(char *name, size_t name_len, __le32 *value, + size_t value_count); +static void ext4_xattr_rehash(struct ext4_xattr_header *); static const struct xattr_handler * const ext4_xattr_handler_map[] = { [EXT4_XATTR_INDEX_USER] = &ext4_xattr_user_handler, @@ -104,8 +106,22 @@ const struct xattr_handler *ext4_xattr_handlers[] = { NULL }; -#define EXT4_GET_MB_CACHE(inode) (((struct ext4_sb_info *) \ - inode->i_sb->s_fs_info)->s_mb_cache) +#define EA_BLOCK_CACHE(inode) (((struct ext4_sb_info *) \ + inode->i_sb->s_fs_info)->s_ea_block_cache) + +#define EA_INODE_CACHE(inode) (((struct ext4_sb_info *) \ + inode->i_sb->s_fs_info)->s_ea_inode_cache) + +static int +ext4_expand_inode_array(struct ext4_xattr_inode_array **ea_inode_array, + struct inode *inode); + +#ifdef CONFIG_LOCKDEP +void ext4_xattr_inode_set_class(struct inode *ea_inode) +{ + lockdep_set_subclass(&ea_inode->i_rwsem, 1); +} +#endif static __le32 ext4_xattr_block_csum(struct inode *inode, sector_t block_nr, @@ -177,9 +193,8 @@ ext4_xattr_check_entries(struct ext4_xattr_entry *entry, void *end, /* Check the values */ while (!IS_LAST_ENTRY(entry)) { - if (entry->e_value_block != 0) - return -EFSCORRUPTED; - if (entry->e_value_size != 0) { + if (entry->e_value_size != 0 && + entry->e_value_inum == 0) { u16 offs = le16_to_cpu(entry->e_value_offs); u32 size = le32_to_cpu(entry->e_value_size); void *value; @@ -269,6 +284,185 @@ ext4_xattr_find_entry(struct ext4_xattr_entry **pentry, int name_index, return cmp ? -ENODATA : 0; } +static u32 +ext4_xattr_inode_hash(struct ext4_sb_info *sbi, const void *buffer, size_t size) +{ + return ext4_chksum(sbi, sbi->s_csum_seed, buffer, size); +} + +static u64 ext4_xattr_inode_get_ref(struct inode *ea_inode) +{ + return ((u64)ea_inode->i_ctime.tv_sec << 32) | + ((u32)ea_inode->i_version); +} + +static void ext4_xattr_inode_set_ref(struct inode *ea_inode, u64 ref_count) +{ + ea_inode->i_ctime.tv_sec = (u32)(ref_count >> 32); + ea_inode->i_version = (u32)ref_count; +} + +static u32 ext4_xattr_inode_get_hash(struct inode *ea_inode) +{ + return (u32)ea_inode->i_atime.tv_sec; +} + +static void ext4_xattr_inode_set_hash(struct inode *ea_inode, u32 hash) +{ + ea_inode->i_atime.tv_sec = hash; +} + +/* + * Read the EA value from an inode. + */ +static int ext4_xattr_inode_read(struct inode *ea_inode, void *buf, size_t size) +{ + unsigned long block = 0; + struct buffer_head *bh; + int blocksize = ea_inode->i_sb->s_blocksize; + size_t csize, copied = 0; + void *copy_pos = buf; + + while (copied < size) { + csize = (size - copied) > blocksize ? blocksize : size - copied; + bh = ext4_bread(NULL, ea_inode, block, 0); + if (IS_ERR(bh)) + return PTR_ERR(bh); + if (!bh) + return -EFSCORRUPTED; + + memcpy(copy_pos, bh->b_data, csize); + brelse(bh); + + copy_pos += csize; + block += 1; + copied += csize; + } + return 0; +} + +static int ext4_xattr_inode_iget(struct inode *parent, unsigned long ea_ino, + struct inode **ea_inode) +{ + struct inode *inode; + int err; + + inode = ext4_iget(parent->i_sb, ea_ino); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + ext4_error(parent->i_sb, + "error while reading EA inode %lu err=%d", ea_ino, + err); + return err; + } + + if (is_bad_inode(inode)) { + ext4_error(parent->i_sb, + "error while reading EA inode %lu is_bad_inode", + ea_ino); + err = -EIO; + goto error; + } + + if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) { + ext4_error(parent->i_sb, + "EA inode %lu does not have EXT4_EA_INODE_FL flag", + ea_ino); + err = -EINVAL; + goto error; + } + + *ea_inode = inode; + return 0; +error: + iput(inode); + return err; +} + +static int +ext4_xattr_inode_verify_hashes(struct inode *ea_inode, + struct ext4_xattr_entry *entry, void *buffer, + size_t size) +{ + u32 hash; + + /* Verify stored hash matches calculated hash. */ + hash = ext4_xattr_inode_hash(EXT4_SB(ea_inode->i_sb), buffer, size); + if (hash != ext4_xattr_inode_get_hash(ea_inode)) + return -EFSCORRUPTED; + + if (entry) { + __le32 e_hash, tmp_data; + + /* Verify entry hash. */ + tmp_data = cpu_to_le32(hash); + e_hash = ext4_xattr_hash_entry(entry->e_name, entry->e_name_len, + &tmp_data, 1); + if (e_hash != entry->e_hash) + return -EFSCORRUPTED; + } + return 0; +} + +#define EXT4_XATTR_INODE_GET_PARENT(inode) ((__u32)(inode)->i_mtime.tv_sec) + +/* + * Read xattr value from the EA inode. + */ +static int +ext4_xattr_inode_get(struct inode *inode, struct ext4_xattr_entry *entry, + void *buffer, size_t size) +{ + struct mb_cache *ea_inode_cache = EA_INODE_CACHE(inode); + struct inode *ea_inode; + int err; + + err = ext4_xattr_inode_iget(inode, le32_to_cpu(entry->e_value_inum), + &ea_inode); + if (err) { + ea_inode = NULL; + goto out; + } + + if (i_size_read(ea_inode) != size) { + ext4_warning_inode(ea_inode, + "ea_inode file size=%llu entry size=%zu", + i_size_read(ea_inode), size); + err = -EFSCORRUPTED; + goto out; + } + + err = ext4_xattr_inode_read(ea_inode, buffer, size); + if (err) + goto out; + + err = ext4_xattr_inode_verify_hashes(ea_inode, entry, buffer, size); + /* + * Compatibility check for old Lustre ea_inode implementation. Old + * version does not have hash validation, but it has a backpointer + * from ea_inode to the parent inode. + */ + if (err == -EFSCORRUPTED) { + if (EXT4_XATTR_INODE_GET_PARENT(ea_inode) != inode->i_ino || + ea_inode->i_generation != inode->i_generation) { + ext4_warning_inode(ea_inode, + "EA inode hash validation failed"); + goto out; + } + /* Do not add ea_inode to the cache. */ + ea_inode_cache = NULL; + } else if (err) + goto out; + + if (ea_inode_cache) + mb_cache_entry_create(ea_inode_cache, GFP_NOFS, + ext4_xattr_inode_get_hash(ea_inode), + ea_inode->i_ino, true /* reusable */); +out: + iput(ea_inode); + return err; +} + static int ext4_xattr_block_get(struct inode *inode, int name_index, const char *name, void *buffer, size_t buffer_size) @@ -277,7 +471,7 @@ ext4_xattr_block_get(struct inode *inode, int name_index, const char *name, struct ext4_xattr_entry *entry; size_t size; int error; - struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode); + struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode); ea_idebug(inode, "name=%d.%s, buffer=%p, buffer_size=%ld", name_index, name, buffer, (long)buffer_size); @@ -298,7 +492,7 @@ ext4_xattr_block_get(struct inode *inode, int name_index, const char *name, error = -EFSCORRUPTED; goto cleanup; } - ext4_xattr_cache_insert(ext4_mb_cache, bh); + ext4_xattr_block_cache_insert(ea_block_cache, bh); entry = BFIRST(bh); error = ext4_xattr_find_entry(&entry, name_index, name, 1); if (error) @@ -308,8 +502,15 @@ ext4_xattr_block_get(struct inode *inode, int name_index, const char *name, error = -ERANGE; if (size > buffer_size) goto cleanup; - memcpy(buffer, bh->b_data + le16_to_cpu(entry->e_value_offs), - size); + if (entry->e_value_inum) { + error = ext4_xattr_inode_get(inode, entry, buffer, + size); + if (error) + goto cleanup; + } else { + memcpy(buffer, bh->b_data + + le16_to_cpu(entry->e_value_offs), size); + } } error = size; @@ -350,8 +551,15 @@ ext4_xattr_ibody_get(struct inode *inode, int name_index, const char *name, error = -ERANGE; if (size > buffer_size) goto cleanup; - memcpy(buffer, (void *)IFIRST(header) + - le16_to_cpu(entry->e_value_offs), size); + if (entry->e_value_inum) { + error = ext4_xattr_inode_get(inode, entry, buffer, + size); + if (error) + goto cleanup; + } else { + memcpy(buffer, (void *)IFIRST(header) + + le16_to_cpu(entry->e_value_offs), size); + } } error = size; @@ -428,7 +636,6 @@ ext4_xattr_block_list(struct dentry *dentry, char *buffer, size_t buffer_size) struct inode *inode = d_inode(dentry); struct buffer_head *bh = NULL; int error; - struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode); ea_idebug(inode, "buffer=%p, buffer_size=%ld", buffer, (long)buffer_size); @@ -450,7 +657,7 @@ ext4_xattr_block_list(struct dentry *dentry, char *buffer, size_t buffer_size) error = -EFSCORRUPTED; goto cleanup; } - ext4_xattr_cache_insert(ext4_mb_cache, bh); + ext4_xattr_block_cache_insert(EA_BLOCK_CACHE(inode), bh); error = ext4_xattr_list_entries(dentry, BFIRST(bh), buffer, buffer_size); cleanup: @@ -539,15 +746,445 @@ static void ext4_xattr_update_super_block(handle_t *handle, } } +int ext4_get_inode_usage(struct inode *inode, qsize_t *usage) +{ + struct ext4_iloc iloc = { .bh = NULL }; + struct buffer_head *bh = NULL; + struct ext4_inode *raw_inode; + struct ext4_xattr_ibody_header *header; + struct ext4_xattr_entry *entry; + qsize_t ea_inode_refs = 0; + void *end; + int ret; + + lockdep_assert_held_read(&EXT4_I(inode)->xattr_sem); + + if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) { + ret = ext4_get_inode_loc(inode, &iloc); + if (ret) + goto out; + raw_inode = ext4_raw_inode(&iloc); + header = IHDR(inode, raw_inode); + end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size; + ret = xattr_check_inode(inode, header, end); + if (ret) + goto out; + + for (entry = IFIRST(header); !IS_LAST_ENTRY(entry); + entry = EXT4_XATTR_NEXT(entry)) + if (entry->e_value_inum) + ea_inode_refs++; + } + + if (EXT4_I(inode)->i_file_acl) { + bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl); + if (!bh) { + ret = -EIO; + goto out; + } + + if (ext4_xattr_check_block(inode, bh)) { + ret = -EFSCORRUPTED; + goto out; + } + + for (entry = BFIRST(bh); !IS_LAST_ENTRY(entry); + entry = EXT4_XATTR_NEXT(entry)) + if (entry->e_value_inum) + ea_inode_refs++; + } + *usage = ea_inode_refs + 1; + ret = 0; +out: + brelse(iloc.bh); + brelse(bh); + return ret; +} + +static inline size_t round_up_cluster(struct inode *inode, size_t length) +{ + struct super_block *sb = inode->i_sb; + size_t cluster_size = 1 << (EXT4_SB(sb)->s_cluster_bits + + inode->i_blkbits); + size_t mask = ~(cluster_size - 1); + + return (length + cluster_size - 1) & mask; +} + +static int ext4_xattr_inode_alloc_quota(struct inode *inode, size_t len) +{ + int err; + + err = dquot_alloc_inode(inode); + if (err) + return err; + err = dquot_alloc_space_nodirty(inode, round_up_cluster(inode, len)); + if (err) + dquot_free_inode(inode); + return err; +} + +static void ext4_xattr_inode_free_quota(struct inode *inode, size_t len) +{ + dquot_free_space_nodirty(inode, round_up_cluster(inode, len)); + dquot_free_inode(inode); +} + +int __ext4_xattr_set_credits(struct super_block *sb, struct inode *inode, + struct buffer_head *block_bh, size_t value_len, + bool is_create) +{ + int credits; + int blocks; + + /* + * 1) Owner inode update + * 2) Ref count update on old xattr block + * 3) new xattr block + * 4) block bitmap update for new xattr block + * 5) group descriptor for new xattr block + * 6) block bitmap update for old xattr block + * 7) group descriptor for old block + * + * 6 & 7 can happen if we have two racing threads T_a and T_b + * which are each trying to set an xattr on inodes I_a and I_b + * which were both initially sharing an xattr block. + */ + credits = 7; + + /* Quota updates. */ + credits += EXT4_MAXQUOTAS_TRANS_BLOCKS(sb); + + /* + * In case of inline data, we may push out the data to a block, + * so we need to reserve credits for this eventuality + */ + if (inode && ext4_has_inline_data(inode)) + credits += ext4_writepage_trans_blocks(inode) + 1; + + /* We are done if ea_inode feature is not enabled. */ + if (!ext4_has_feature_ea_inode(sb)) + return credits; + + /* New ea_inode, inode map, block bitmap, group descriptor. */ + credits += 4; + + /* Data blocks. */ + blocks = (value_len + sb->s_blocksize - 1) >> sb->s_blocksize_bits; + + /* Indirection block or one level of extent tree. */ + blocks += 1; + + /* Block bitmap and group descriptor updates for each block. */ + credits += blocks * 2; + + /* Blocks themselves. */ + credits += blocks; + + if (!is_create) { + /* Dereference ea_inode holding old xattr value. + * Old ea_inode, inode map, block bitmap, group descriptor. + */ + credits += 4; + + /* Data blocks for old ea_inode. */ + blocks = XATTR_SIZE_MAX >> sb->s_blocksize_bits; + + /* Indirection block or one level of extent tree for old + * ea_inode. + */ + blocks += 1; + + /* Block bitmap and group descriptor updates for each block. */ + credits += blocks * 2; + } + + /* We may need to clone the existing xattr block in which case we need + * to increment ref counts for existing ea_inodes referenced by it. + */ + if (block_bh) { + struct ext4_xattr_entry *entry = BFIRST(block_bh); + + for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) + if (entry->e_value_inum) + /* Ref count update on ea_inode. */ + credits += 1; + } + return credits; +} + +static int ext4_xattr_ensure_credits(handle_t *handle, struct inode *inode, + int credits, struct buffer_head *bh, + bool dirty, bool block_csum) +{ + int error; + + if (!ext4_handle_valid(handle)) + return 0; + + if (handle->h_buffer_credits >= credits) + return 0; + + error = ext4_journal_extend(handle, credits - handle->h_buffer_credits); + if (!error) + return 0; + if (error < 0) { + ext4_warning(inode->i_sb, "Extend journal (error %d)", error); + return error; + } + + if (bh && dirty) { + if (block_csum) + ext4_xattr_block_csum_set(inode, bh); + error = ext4_handle_dirty_metadata(handle, NULL, bh); + if (error) { + ext4_warning(inode->i_sb, "Handle metadata (error %d)", + error); + return error; + } + } + + error = ext4_journal_restart(handle, credits); + if (error) { + ext4_warning(inode->i_sb, "Restart journal (error %d)", error); + return error; + } + + if (bh) { + error = ext4_journal_get_write_access(handle, bh); + if (error) { + ext4_warning(inode->i_sb, + "Get write access failed (error %d)", + error); + return error; + } + } + return 0; +} + +static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode, + int ref_change) +{ + struct mb_cache *ea_inode_cache = EA_INODE_CACHE(ea_inode); + struct ext4_iloc iloc; + s64 ref_count; + u32 hash; + int ret; + + inode_lock(ea_inode); + + ret = ext4_reserve_inode_write(handle, ea_inode, &iloc); + if (ret) { + iloc.bh = NULL; + goto out; + } + + ref_count = ext4_xattr_inode_get_ref(ea_inode); + ref_count += ref_change; + ext4_xattr_inode_set_ref(ea_inode, ref_count); + + if (ref_change > 0) { + WARN_ONCE(ref_count <= 0, "EA inode %lu ref_count=%lld", + ea_inode->i_ino, ref_count); + + if (ref_count == 1) { + WARN_ONCE(ea_inode->i_nlink, "EA inode %lu i_nlink=%u", + ea_inode->i_ino, ea_inode->i_nlink); + + set_nlink(ea_inode, 1); + ext4_orphan_del(handle, ea_inode); + + if (ea_inode_cache) { + hash = ext4_xattr_inode_get_hash(ea_inode); + mb_cache_entry_create(ea_inode_cache, + GFP_NOFS, hash, + ea_inode->i_ino, + true /* reusable */); + } + } + } else { + WARN_ONCE(ref_count < 0, "EA inode %lu ref_count=%lld", + ea_inode->i_ino, ref_count); + + if (ref_count == 0) { + WARN_ONCE(ea_inode->i_nlink != 1, + "EA inode %lu i_nlink=%u", + ea_inode->i_ino, ea_inode->i_nlink); + + clear_nlink(ea_inode); + ext4_orphan_add(handle, ea_inode); + + if (ea_inode_cache) { + hash = ext4_xattr_inode_get_hash(ea_inode); + mb_cache_entry_delete(ea_inode_cache, hash, + ea_inode->i_ino); + } + } + } + + ret = ext4_mark_iloc_dirty(handle, ea_inode, &iloc); + iloc.bh = NULL; + if (ret) + ext4_warning_inode(ea_inode, + "ext4_mark_iloc_dirty() failed ret=%d", ret); +out: + brelse(iloc.bh); + inode_unlock(ea_inode); + return ret; +} + +static int ext4_xattr_inode_inc_ref(handle_t *handle, struct inode *ea_inode) +{ + return ext4_xattr_inode_update_ref(handle, ea_inode, 1); +} + +static int ext4_xattr_inode_dec_ref(handle_t *handle, struct inode *ea_inode) +{ + return ext4_xattr_inode_update_ref(handle, ea_inode, -1); +} + +static int ext4_xattr_inode_inc_ref_all(handle_t *handle, struct inode *parent, + struct ext4_xattr_entry *first) +{ + struct inode *ea_inode; + struct ext4_xattr_entry *entry; + struct ext4_xattr_entry *failed_entry; + unsigned int ea_ino; + int err, saved_err; + + for (entry = first; !IS_LAST_ENTRY(entry); + entry = EXT4_XATTR_NEXT(entry)) { + if (!entry->e_value_inum) + continue; + ea_ino = le32_to_cpu(entry->e_value_inum); + err = ext4_xattr_inode_iget(parent, ea_ino, &ea_inode); + if (err) + goto cleanup; + err = ext4_xattr_inode_inc_ref(handle, ea_inode); + if (err) { + ext4_warning_inode(ea_inode, "inc ref error %d", err); + iput(ea_inode); + goto cleanup; + } + iput(ea_inode); + } + return 0; + +cleanup: + saved_err = err; + failed_entry = entry; + + for (entry = first; entry != failed_entry; + entry = EXT4_XATTR_NEXT(entry)) { + if (!entry->e_value_inum) + continue; + ea_ino = le32_to_cpu(entry->e_value_inum); + err = ext4_xattr_inode_iget(parent, ea_ino, &ea_inode); + if (err) { + ext4_warning(parent->i_sb, + "cleanup ea_ino %u iget error %d", ea_ino, + err); + continue; + } + err = ext4_xattr_inode_dec_ref(handle, ea_inode); + if (err) + ext4_warning_inode(ea_inode, "cleanup dec ref error %d", + err); + iput(ea_inode); + } + return saved_err; +} + +static void +ext4_xattr_inode_dec_ref_all(handle_t *handle, struct inode *parent, + struct buffer_head *bh, + struct ext4_xattr_entry *first, bool block_csum, + struct ext4_xattr_inode_array **ea_inode_array, + int extra_credits, bool skip_quota) +{ + struct inode *ea_inode; + struct ext4_xattr_entry *entry; + bool dirty = false; + unsigned int ea_ino; + int err; + int credits; + + /* One credit for dec ref on ea_inode, one for orphan list addition, */ + credits = 2 + extra_credits; + + for (entry = first; !IS_LAST_ENTRY(entry); + entry = EXT4_XATTR_NEXT(entry)) { + if (!entry->e_value_inum) + continue; + ea_ino = le32_to_cpu(entry->e_value_inum); + err = ext4_xattr_inode_iget(parent, ea_ino, &ea_inode); + if (err) + continue; + + err = ext4_expand_inode_array(ea_inode_array, ea_inode); + if (err) { + ext4_warning_inode(ea_inode, + "Expand inode array err=%d", err); + iput(ea_inode); + continue; + } + + err = ext4_xattr_ensure_credits(handle, parent, credits, bh, + dirty, block_csum); + if (err) { + ext4_warning_inode(ea_inode, "Ensure credits err=%d", + err); + continue; + } + + err = ext4_xattr_inode_dec_ref(handle, ea_inode); + if (err) { + ext4_warning_inode(ea_inode, "ea_inode dec ref err=%d", + err); + continue; + } + + if (!skip_quota) + ext4_xattr_inode_free_quota(parent, + le32_to_cpu(entry->e_value_size)); + + /* + * Forget about ea_inode within the same transaction that + * decrements the ref count. This avoids duplicate decrements in + * case the rest of the work spills over to subsequent + * transactions. + */ + entry->e_value_inum = 0; + entry->e_value_size = 0; + + dirty = true; + } + + if (dirty) { + /* + * Note that we are deliberately skipping csum calculation for + * the final update because we do not expect any journal + * restarts until xattr block is freed. + */ + + err = ext4_handle_dirty_metadata(handle, NULL, bh); + if (err) + ext4_warning_inode(parent, + "handle dirty metadata err=%d", err); + } +} + /* * Release the xattr block BH: If the reference count is > 1, decrement it; * otherwise free the block. */ static void ext4_xattr_release_block(handle_t *handle, struct inode *inode, - struct buffer_head *bh) + struct buffer_head *bh, + struct ext4_xattr_inode_array **ea_inode_array, + int extra_credits) { - struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode); + struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode); u32 hash, ref; int error = 0; @@ -565,9 +1202,19 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode, * This must happen under buffer lock for * ext4_xattr_block_set() to reliably detect freed block */ - mb_cache_entry_delete_block(ext4_mb_cache, hash, bh->b_blocknr); + if (ea_block_cache) + mb_cache_entry_delete(ea_block_cache, hash, + bh->b_blocknr); get_bh(bh); unlock_buffer(bh); + + if (ext4_has_feature_ea_inode(inode->i_sb)) + ext4_xattr_inode_dec_ref_all(handle, inode, bh, + BFIRST(bh), + true /* block_csum */, + ea_inode_array, + extra_credits, + true /* skip_quota */); ext4_free_blocks(handle, inode, bh, 0, 1, EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET); @@ -577,11 +1224,13 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode, if (ref == EXT4_XATTR_REFCOUNT_MAX - 1) { struct mb_cache_entry *ce; - ce = mb_cache_entry_get(ext4_mb_cache, hash, - bh->b_blocknr); - if (ce) { - ce->e_reusable = 1; - mb_cache_entry_put(ext4_mb_cache, ce); + if (ea_block_cache) { + ce = mb_cache_entry_get(ea_block_cache, hash, + bh->b_blocknr); + if (ce) { + ce->e_reusable = 1; + mb_cache_entry_put(ea_block_cache, ce); + } } } @@ -620,7 +1269,7 @@ static size_t ext4_xattr_free_space(struct ext4_xattr_entry *last, size_t *min_offs, void *base, int *total) { for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) { - if (last->e_value_size) { + if (!last->e_value_inum && last->e_value_size) { size_t offs = le16_to_cpu(last->e_value_offs); if (offs < *min_offs) *min_offs = offs; @@ -631,113 +1280,454 @@ static size_t ext4_xattr_free_space(struct ext4_xattr_entry *last, return (*min_offs - ((void *)last - base) - sizeof(__u32)); } -static int -ext4_xattr_set_entry(struct ext4_xattr_info *i, struct ext4_xattr_search *s) +/* + * Write the value of the EA in an inode. + */ +static int ext4_xattr_inode_write(handle_t *handle, struct inode *ea_inode, + const void *buf, int bufsize) +{ + struct buffer_head *bh = NULL; + unsigned long block = 0; + int blocksize = ea_inode->i_sb->s_blocksize; + int max_blocks = (bufsize + blocksize - 1) >> ea_inode->i_blkbits; + int csize, wsize = 0; + int ret = 0; + int retries = 0; + +retry: + while (ret >= 0 && ret < max_blocks) { + struct ext4_map_blocks map; + map.m_lblk = block += ret; + map.m_len = max_blocks -= ret; + + ret = ext4_map_blocks(handle, ea_inode, &map, + EXT4_GET_BLOCKS_CREATE); + if (ret <= 0) { + ext4_mark_inode_dirty(handle, ea_inode); + if (ret == -ENOSPC && + ext4_should_retry_alloc(ea_inode->i_sb, &retries)) { + ret = 0; + goto retry; + } + break; + } + } + + if (ret < 0) + return ret; + + block = 0; + while (wsize < bufsize) { + if (bh != NULL) + brelse(bh); + csize = (bufsize - wsize) > blocksize ? blocksize : + bufsize - wsize; + bh = ext4_getblk(handle, ea_inode, block, 0); + if (IS_ERR(bh)) + return PTR_ERR(bh); + ret = ext4_journal_get_write_access(handle, bh); + if (ret) + goto out; + + memcpy(bh->b_data, buf, csize); + set_buffer_uptodate(bh); + ext4_handle_dirty_metadata(handle, ea_inode, bh); + + buf += csize; + wsize += csize; + block += 1; + } + + inode_lock(ea_inode); + i_size_write(ea_inode, wsize); + ext4_update_i_disksize(ea_inode, wsize); + inode_unlock(ea_inode); + + ext4_mark_inode_dirty(handle, ea_inode); + +out: + brelse(bh); + + return ret; +} + +/* + * Create an inode to store the value of a large EA. + */ +static struct inode *ext4_xattr_inode_create(handle_t *handle, + struct inode *inode, u32 hash) +{ + struct inode *ea_inode = NULL; + uid_t owner[2] = { i_uid_read(inode), i_gid_read(inode) }; + int err; + + /* + * Let the next inode be the goal, so we try and allocate the EA inode + * in the same group, or nearby one. + */ + ea_inode = ext4_new_inode(handle, inode->i_sb->s_root->d_inode, + S_IFREG | 0600, NULL, inode->i_ino + 1, owner, + EXT4_EA_INODE_FL); + if (!IS_ERR(ea_inode)) { + ea_inode->i_op = &ext4_file_inode_operations; + ea_inode->i_fop = &ext4_file_operations; + ext4_set_aops(ea_inode); + ext4_xattr_inode_set_class(ea_inode); + unlock_new_inode(ea_inode); + ext4_xattr_inode_set_ref(ea_inode, 1); + ext4_xattr_inode_set_hash(ea_inode, hash); + err = ext4_mark_inode_dirty(handle, ea_inode); + if (!err) + err = ext4_inode_attach_jinode(ea_inode); + if (err) { + iput(ea_inode); + return ERR_PTR(err); + } + + /* + * Xattr inodes are shared therefore quota charging is performed + * at a higher level. + */ + dquot_free_inode(ea_inode); + dquot_drop(ea_inode); + inode_lock(ea_inode); + ea_inode->i_flags |= S_NOQUOTA; + inode_unlock(ea_inode); + } + + return ea_inode; +} + +static struct inode * +ext4_xattr_inode_cache_find(struct inode *inode, const void *value, + size_t value_len, u32 hash) +{ + struct inode *ea_inode; + struct mb_cache_entry *ce; + struct mb_cache *ea_inode_cache = EA_INODE_CACHE(inode); + void *ea_data; + + if (!ea_inode_cache) + return NULL; + + ce = mb_cache_entry_find_first(ea_inode_cache, hash); + if (!ce) + return NULL; + + ea_data = ext4_kvmalloc(value_len, GFP_NOFS); + if (!ea_data) { + mb_cache_entry_put(ea_inode_cache, ce); + return NULL; + } + + while (ce) { + ea_inode = ext4_iget(inode->i_sb, ce->e_value); + if (!IS_ERR(ea_inode) && + !is_bad_inode(ea_inode) && + (EXT4_I(ea_inode)->i_flags & EXT4_EA_INODE_FL) && + i_size_read(ea_inode) == value_len && + !ext4_xattr_inode_read(ea_inode, ea_data, value_len) && + !ext4_xattr_inode_verify_hashes(ea_inode, NULL, ea_data, + value_len) && + !memcmp(value, ea_data, value_len)) { + mb_cache_entry_touch(ea_inode_cache, ce); + mb_cache_entry_put(ea_inode_cache, ce); + kvfree(ea_data); + return ea_inode; + } + + if (!IS_ERR(ea_inode)) + iput(ea_inode); + ce = mb_cache_entry_find_next(ea_inode_cache, ce); + } + kvfree(ea_data); + return NULL; +} + +/* + * Add value of the EA in an inode. + */ +static int ext4_xattr_inode_lookup_create(handle_t *handle, struct inode *inode, + const void *value, size_t value_len, + struct inode **ret_inode) +{ + struct inode *ea_inode; + u32 hash; + int err; + + hash = ext4_xattr_inode_hash(EXT4_SB(inode->i_sb), value, value_len); + ea_inode = ext4_xattr_inode_cache_find(inode, value, value_len, hash); + if (ea_inode) { + err = ext4_xattr_inode_inc_ref(handle, ea_inode); + if (err) { + iput(ea_inode); + return err; + } + + *ret_inode = ea_inode; + return 0; + } + + /* Create an inode for the EA value */ + ea_inode = ext4_xattr_inode_create(handle, inode, hash); + if (IS_ERR(ea_inode)) + return PTR_ERR(ea_inode); + + err = ext4_xattr_inode_write(handle, ea_inode, value, value_len); + if (err) { + ext4_xattr_inode_dec_ref(handle, ea_inode); + iput(ea_inode); + return err; + } + + if (EA_INODE_CACHE(inode)) + mb_cache_entry_create(EA_INODE_CACHE(inode), GFP_NOFS, hash, + ea_inode->i_ino, true /* reusable */); + + *ret_inode = ea_inode; + return 0; +} + +/* + * Reserve min(block_size/8, 1024) bytes for xattr entries/names if ea_inode + * feature is enabled. + */ +#define EXT4_XATTR_BLOCK_RESERVE(inode) min(i_blocksize(inode)/8, 1024U) + +static int ext4_xattr_set_entry(struct ext4_xattr_info *i, + struct ext4_xattr_search *s, + handle_t *handle, struct inode *inode, + bool is_block) { struct ext4_xattr_entry *last; - size_t free, min_offs = s->end - s->base, name_len = strlen(i->name); + struct ext4_xattr_entry *here = s->here; + size_t min_offs = s->end - s->base, name_len = strlen(i->name); + int in_inode = i->in_inode; + struct inode *old_ea_inode = NULL; + struct inode *new_ea_inode = NULL; + size_t old_size, new_size; + int ret; + + /* Space used by old and new values. */ + old_size = (!s->not_found && !here->e_value_inum) ? + EXT4_XATTR_SIZE(le32_to_cpu(here->e_value_size)) : 0; + new_size = (i->value && !in_inode) ? EXT4_XATTR_SIZE(i->value_len) : 0; + + /* + * Optimization for the simple case when old and new values have the + * same padded sizes. Not applicable if external inodes are involved. + */ + if (new_size && new_size == old_size) { + size_t offs = le16_to_cpu(here->e_value_offs); + void *val = s->base + offs; + + here->e_value_size = cpu_to_le32(i->value_len); + if (i->value == EXT4_ZERO_XATTR_VALUE) { + memset(val, 0, new_size); + } else { + memcpy(val, i->value, i->value_len); + /* Clear padding bytes. */ + memset(val + i->value_len, 0, new_size - i->value_len); + } + return 0; + } /* Compute min_offs and last. */ last = s->first; for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) { - if (last->e_value_size) { + if (!last->e_value_inum && last->e_value_size) { size_t offs = le16_to_cpu(last->e_value_offs); if (offs < min_offs) min_offs = offs; } } - free = min_offs - ((void *)last - s->base) - sizeof(__u32); - if (!s->not_found) { - if (s->here->e_value_size) { - size_t size = le32_to_cpu(s->here->e_value_size); - free += EXT4_XATTR_SIZE(size); - } - free += EXT4_XATTR_LEN(name_len); - } + + /* Check whether we have enough space. */ if (i->value) { - if (free < EXT4_XATTR_LEN(name_len) + - EXT4_XATTR_SIZE(i->value_len)) - return -ENOSPC; + size_t free; + + free = min_offs - ((void *)last - s->base) - sizeof(__u32); + if (!s->not_found) + free += EXT4_XATTR_LEN(name_len) + old_size; + + if (free < EXT4_XATTR_LEN(name_len) + new_size) { + ret = -ENOSPC; + goto out; + } + + /* + * If storing the value in an external inode is an option, + * reserve space for xattr entries/names in the external + * attribute block so that a long value does not occupy the + * whole space and prevent futher entries being added. + */ + if (ext4_has_feature_ea_inode(inode->i_sb) && + new_size && is_block && + (min_offs + old_size - new_size) < + EXT4_XATTR_BLOCK_RESERVE(inode)) { + ret = -ENOSPC; + goto out; + } } - if (i->value && s->not_found) { - /* Insert the new name. */ - size_t size = EXT4_XATTR_LEN(name_len); - size_t rest = (void *)last - (void *)s->here + sizeof(__u32); - memmove((void *)s->here + size, s->here, rest); - memset(s->here, 0, size); - s->here->e_name_index = i->name_index; - s->here->e_name_len = name_len; - memcpy(s->here->e_name, i->name, name_len); - } else { - if (s->here->e_value_size) { - void *first_val = s->base + min_offs; - size_t offs = le16_to_cpu(s->here->e_value_offs); - void *val = s->base + offs; - size_t size = EXT4_XATTR_SIZE( - le32_to_cpu(s->here->e_value_size)); - - if (i->value && size == EXT4_XATTR_SIZE(i->value_len)) { - /* The old and the new value have the same - size. Just replace. */ - s->here->e_value_size = - cpu_to_le32(i->value_len); - if (i->value == EXT4_ZERO_XATTR_VALUE) { - memset(val, 0, size); - } else { - /* Clear pad bytes first. */ - memset(val + size - EXT4_XATTR_PAD, 0, - EXT4_XATTR_PAD); - memcpy(val, i->value, i->value_len); - } - return 0; - } + /* + * Getting access to old and new ea inodes is subject to failures. + * Finish that work before doing any modifications to the xattr data. + */ + if (!s->not_found && here->e_value_inum) { + ret = ext4_xattr_inode_iget(inode, + le32_to_cpu(here->e_value_inum), + &old_ea_inode); + if (ret) { + old_ea_inode = NULL; + goto out; + } + } + if (i->value && in_inode) { + WARN_ON_ONCE(!i->value_len); + + ret = ext4_xattr_inode_alloc_quota(inode, i->value_len); + if (ret) + goto out; + + ret = ext4_xattr_inode_lookup_create(handle, inode, i->value, + i->value_len, + &new_ea_inode); + if (ret) { + new_ea_inode = NULL; + ext4_xattr_inode_free_quota(inode, i->value_len); + goto out; + } + } - /* Remove the old value. */ - memmove(first_val + size, first_val, val - first_val); - memset(first_val, 0, size); - s->here->e_value_size = 0; - s->here->e_value_offs = 0; - min_offs += size; - - /* Adjust all value offsets. */ - last = s->first; - while (!IS_LAST_ENTRY(last)) { - size_t o = le16_to_cpu(last->e_value_offs); - if (last->e_value_size && o < offs) - last->e_value_offs = - cpu_to_le16(o + size); - last = EXT4_XATTR_NEXT(last); + if (old_ea_inode) { + /* We are ready to release ref count on the old_ea_inode. */ + ret = ext4_xattr_inode_dec_ref(handle, old_ea_inode); + if (ret) { + /* Release newly required ref count on new_ea_inode. */ + if (new_ea_inode) { + int err; + + err = ext4_xattr_inode_dec_ref(handle, + new_ea_inode); + if (err) + ext4_warning_inode(new_ea_inode, + "dec ref new_ea_inode err=%d", + err); + ext4_xattr_inode_free_quota(inode, + i->value_len); } + goto out; } - if (!i->value) { - /* Remove the old name. */ - size_t size = EXT4_XATTR_LEN(name_len); - last = ENTRY((void *)last - size); - memmove(s->here, (void *)s->here + size, - (void *)last - (void *)s->here + sizeof(__u32)); - memset(last, 0, size); + + ext4_xattr_inode_free_quota(inode, + le32_to_cpu(here->e_value_size)); + } + + /* No failures allowed past this point. */ + + if (!s->not_found && here->e_value_offs) { + /* Remove the old value. */ + void *first_val = s->base + min_offs; + size_t offs = le16_to_cpu(here->e_value_offs); + void *val = s->base + offs; + + memmove(first_val + old_size, first_val, val - first_val); + memset(first_val, 0, old_size); + min_offs += old_size; + + /* Adjust all value offsets. */ + last = s->first; + while (!IS_LAST_ENTRY(last)) { + size_t o = le16_to_cpu(last->e_value_offs); + + if (!last->e_value_inum && + last->e_value_size && o < offs) + last->e_value_offs = cpu_to_le16(o + old_size); + last = EXT4_XATTR_NEXT(last); } } + if (!i->value) { + /* Remove old name. */ + size_t size = EXT4_XATTR_LEN(name_len); + + last = ENTRY((void *)last - size); + memmove(here, (void *)here + size, + (void *)last - (void *)here + sizeof(__u32)); + memset(last, 0, size); + } else if (s->not_found) { + /* Insert new name. */ + size_t size = EXT4_XATTR_LEN(name_len); + size_t rest = (void *)last - (void *)here + sizeof(__u32); + + memmove((void *)here + size, here, rest); + memset(here, 0, size); + here->e_name_index = i->name_index; + here->e_name_len = name_len; + memcpy(here->e_name, i->name, name_len); + } else { + /* This is an update, reset value info. */ + here->e_value_inum = 0; + here->e_value_offs = 0; + here->e_value_size = 0; + } + if (i->value) { - /* Insert the new value. */ - s->here->e_value_size = cpu_to_le32(i->value_len); - if (i->value_len) { - size_t size = EXT4_XATTR_SIZE(i->value_len); - void *val = s->base + min_offs - size; - s->here->e_value_offs = cpu_to_le16(min_offs - size); + /* Insert new value. */ + if (in_inode) { + here->e_value_inum = cpu_to_le32(new_ea_inode->i_ino); + } else if (i->value_len) { + void *val = s->base + min_offs - new_size; + + here->e_value_offs = cpu_to_le16(min_offs - new_size); if (i->value == EXT4_ZERO_XATTR_VALUE) { - memset(val, 0, size); + memset(val, 0, new_size); } else { - /* Clear the pad bytes first. */ - memset(val + size - EXT4_XATTR_PAD, 0, - EXT4_XATTR_PAD); memcpy(val, i->value, i->value_len); + /* Clear padding bytes. */ + memset(val + i->value_len, 0, + new_size - i->value_len); } } + here->e_value_size = cpu_to_le32(i->value_len); } - return 0; + + if (i->value) { + __le32 hash = 0; + + /* Entry hash calculation. */ + if (in_inode) { + __le32 crc32c_hash; + + /* + * Feed crc32c hash instead of the raw value for entry + * hash calculation. This is to avoid walking + * potentially long value buffer again. + */ + crc32c_hash = cpu_to_le32( + ext4_xattr_inode_get_hash(new_ea_inode)); + hash = ext4_xattr_hash_entry(here->e_name, + here->e_name_len, + &crc32c_hash, 1); + } else if (is_block) { + __le32 *value = s->base + min_offs - new_size; + + hash = ext4_xattr_hash_entry(here->e_name, + here->e_name_len, value, + new_size >> 2); + } + here->e_hash = hash; + } + + if (is_block) + ext4_xattr_rehash((struct ext4_xattr_header *)s->base); + + ret = 0; +out: + iput(old_ea_inode); + iput(new_ea_inode); + return ret; } struct ext4_xattr_block_find { @@ -794,15 +1784,16 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, { struct super_block *sb = inode->i_sb; struct buffer_head *new_bh = NULL; - struct ext4_xattr_search *s = &bs->s; + struct ext4_xattr_search s_copy = bs->s; + struct ext4_xattr_search *s = &s_copy; struct mb_cache_entry *ce = NULL; int error = 0; - struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode); + struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode); + struct inode *ea_inode = NULL; + size_t old_ea_inode_size = 0; #define header(x) ((struct ext4_xattr_header *)(x)) - if (i->value && i->value_len > sb->s_blocksize) - return -ENOSPC; if (s->base) { BUFFER_TRACE(bs->bh, "get_write_access"); error = ext4_journal_get_write_access(handle, bs->bh); @@ -818,17 +1809,15 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, * ext4_xattr_block_set() to reliably detect modified * block */ - mb_cache_entry_delete_block(ext4_mb_cache, hash, - bs->bh->b_blocknr); + if (ea_block_cache) + mb_cache_entry_delete(ea_block_cache, hash, + bs->bh->b_blocknr); ea_bdebug(bs->bh, "modifying in-place"); - error = ext4_xattr_set_entry(i, s); - if (!error) { - if (!IS_LAST_ENTRY(s->first)) - ext4_xattr_rehash(header(s->base), - s->here); - ext4_xattr_cache_insert(ext4_mb_cache, - bs->bh); - } + error = ext4_xattr_set_entry(i, s, handle, inode, + true /* is_block */); + if (!error) + ext4_xattr_block_cache_insert(ea_block_cache, + bs->bh); ext4_xattr_block_csum_set(inode, bs->bh); unlock_buffer(bs->bh); if (error == -EFSCORRUPTED) @@ -854,6 +1843,24 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, header(s->base)->h_refcount = cpu_to_le32(1); s->here = ENTRY(s->base + offset); s->end = s->base + bs->bh->b_size; + + /* + * If existing entry points to an xattr inode, we need + * to prevent ext4_xattr_set_entry() from decrementing + * ref count on it because the reference belongs to the + * original block. In this case, make the entry look + * like it has an empty value. + */ + if (!s->not_found && s->here->e_value_inum) { + /* + * Defer quota free call for previous inode + * until success is guaranteed. + */ + old_ea_inode_size = le32_to_cpu( + s->here->e_value_size); + s->here->e_value_inum = 0; + s->here->e_value_size = 0; + } } } else { /* Allocate a buffer where we construct the new block. */ @@ -870,17 +1877,33 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, s->end = s->base + sb->s_blocksize; } - error = ext4_xattr_set_entry(i, s); + error = ext4_xattr_set_entry(i, s, handle, inode, true /* is_block */); if (error == -EFSCORRUPTED) goto bad_block; if (error) goto cleanup; - if (!IS_LAST_ENTRY(s->first)) - ext4_xattr_rehash(header(s->base), s->here); + + if (i->value && s->here->e_value_inum) { + unsigned int ea_ino; + + /* + * A ref count on ea_inode has been taken as part of the call to + * ext4_xattr_set_entry() above. We would like to drop this + * extra ref but we have to wait until the xattr block is + * initialized and has its own ref count on the ea_inode. + */ + ea_ino = le32_to_cpu(s->here->e_value_inum); + error = ext4_xattr_inode_iget(inode, ea_ino, &ea_inode); + if (error) { + ea_inode = NULL; + goto cleanup; + } + } inserted: if (!IS_LAST_ENTRY(s->first)) { - new_bh = ext4_xattr_cache_find(inode, header(s->base), &ce); + new_bh = ext4_xattr_block_cache_find(inode, header(s->base), + &ce); if (new_bh) { /* We found an identical block in the cache. */ if (new_bh == bs->bh) @@ -925,7 +1948,7 @@ inserted: EXT4_C2B(EXT4_SB(sb), 1)); brelse(new_bh); - mb_cache_entry_put(ext4_mb_cache, ce); + mb_cache_entry_put(ea_block_cache, ce); ce = NULL; new_bh = NULL; goto inserted; @@ -944,8 +1967,8 @@ inserted: if (error) goto cleanup_dquot; } - mb_cache_entry_touch(ext4_mb_cache, ce); - mb_cache_entry_put(ext4_mb_cache, ce); + mb_cache_entry_touch(ea_block_cache, ce); + mb_cache_entry_put(ea_block_cache, ce); ce = NULL; } else if (bs->bh && s->base == bs->bh->b_data) { /* We were modifying this block in-place. */ @@ -984,6 +2007,22 @@ getblk_failed: EXT4_FREE_BLOCKS_METADATA); goto cleanup; } + error = ext4_xattr_inode_inc_ref_all(handle, inode, + ENTRY(header(s->base)+1)); + if (error) + goto getblk_failed; + if (ea_inode) { + /* Drop the extra ref on ea_inode. */ + error = ext4_xattr_inode_dec_ref(handle, + ea_inode); + if (error) + ext4_warning_inode(ea_inode, + "dec ref error=%d", + error); + iput(ea_inode); + ea_inode = NULL; + } + lock_buffer(new_bh); error = ext4_journal_get_create_access(handle, new_bh); if (error) { @@ -995,7 +2034,7 @@ getblk_failed: ext4_xattr_block_csum_set(inode, new_bh); set_buffer_uptodate(new_bh); unlock_buffer(new_bh); - ext4_xattr_cache_insert(ext4_mb_cache, new_bh); + ext4_xattr_block_cache_insert(ea_block_cache, new_bh); error = ext4_handle_dirty_metadata(handle, inode, new_bh); if (error) @@ -1003,17 +2042,40 @@ getblk_failed: } } + if (old_ea_inode_size) + ext4_xattr_inode_free_quota(inode, old_ea_inode_size); + /* Update the inode. */ EXT4_I(inode)->i_file_acl = new_bh ? new_bh->b_blocknr : 0; /* Drop the previous xattr block. */ - if (bs->bh && bs->bh != new_bh) - ext4_xattr_release_block(handle, inode, bs->bh); + if (bs->bh && bs->bh != new_bh) { + struct ext4_xattr_inode_array *ea_inode_array = NULL; + + ext4_xattr_release_block(handle, inode, bs->bh, + &ea_inode_array, + 0 /* extra_credits */); + ext4_xattr_inode_array_free(ea_inode_array); + } error = 0; cleanup: + if (ea_inode) { + int error2; + + error2 = ext4_xattr_inode_dec_ref(handle, ea_inode); + if (error2) + ext4_warning_inode(ea_inode, "dec ref error=%d", + error2); + + /* If there was an error, revert the quota charge. */ + if (error) + ext4_xattr_inode_free_quota(inode, + i_size_read(ea_inode)); + iput(ea_inode); + } if (ce) - mb_cache_entry_put(ext4_mb_cache, ce); + mb_cache_entry_put(ea_block_cache, ce); brelse(new_bh); if (!(bs->bh && s->base == bs->bh->b_data)) kfree(s->base); @@ -1070,7 +2132,7 @@ int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode, if (EXT4_I(inode)->i_extra_isize == 0) return -ENOSPC; - error = ext4_xattr_set_entry(i, s); + error = ext4_xattr_set_entry(i, s, handle, inode, false /* is_block */); if (error) { if (error == -ENOSPC && ext4_has_inline_data(inode)) { @@ -1082,7 +2144,8 @@ int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode, error = ext4_xattr_ibody_find(inode, i, is); if (error) return error; - error = ext4_xattr_set_entry(i, s); + error = ext4_xattr_set_entry(i, s, handle, inode, + false /* is_block */); } if (error) return error; @@ -1098,7 +2161,7 @@ int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode, return 0; } -static int ext4_xattr_ibody_set(struct inode *inode, +static int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode, struct ext4_xattr_info *i, struct ext4_xattr_ibody_find *is) { @@ -1108,7 +2171,7 @@ static int ext4_xattr_ibody_set(struct inode *inode, if (EXT4_I(inode)->i_extra_isize == 0) return -ENOSPC; - error = ext4_xattr_set_entry(i, s); + error = ext4_xattr_set_entry(i, s, handle, inode, false /* is_block */); if (error) return error; header = IHDR(inode, ext4_raw_inode(&is->iloc)); @@ -1127,12 +2190,31 @@ static int ext4_xattr_value_same(struct ext4_xattr_search *s, { void *value; + /* When e_value_inum is set the value is stored externally. */ + if (s->here->e_value_inum) + return 0; if (le32_to_cpu(s->here->e_value_size) != i->value_len) return 0; value = ((void *)s->base) + le16_to_cpu(s->here->e_value_offs); return !memcmp(value, i->value, i->value_len); } +static struct buffer_head *ext4_xattr_get_block(struct inode *inode) +{ + struct buffer_head *bh; + int error; + + if (!EXT4_I(inode)->i_file_acl) + return NULL; + bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl); + if (!bh) + return ERR_PTR(-EIO); + error = ext4_xattr_check_block(inode, bh); + if (error) + return ERR_PTR(error); + return bh; +} + /* * ext4_xattr_set_handle() * @@ -1155,7 +2237,7 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index, .name = name, .value = value, .value_len = value_len, - + .in_inode = 0, }; struct ext4_xattr_ibody_find is = { .s = { .not_found = -ENODATA, }, @@ -1173,6 +2255,28 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index, ext4_write_lock_xattr(inode, &no_expand); + /* Check journal credits under write lock. */ + if (ext4_handle_valid(handle)) { + struct buffer_head *bh; + int credits; + + bh = ext4_xattr_get_block(inode); + if (IS_ERR(bh)) { + error = PTR_ERR(bh); + goto cleanup; + } + + credits = __ext4_xattr_set_credits(inode->i_sb, inode, bh, + value_len, + flags & XATTR_CREATE); + brelse(bh); + + if (!ext4_handle_has_enough_credits(handle, credits)) { + error = -ENOSPC; + goto cleanup; + } + } + error = ext4_reserve_inode_write(handle, inode, &is.iloc); if (error) goto cleanup; @@ -1202,9 +2306,10 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index, if (flags & XATTR_CREATE) goto cleanup; } + if (!value) { if (!is.s.not_found) - error = ext4_xattr_ibody_set(inode, &i, &is); + error = ext4_xattr_ibody_set(handle, inode, &i, &is); else if (!bs.s.not_found) error = ext4_xattr_block_set(handle, inode, &i, &bs); } else { @@ -1215,7 +2320,12 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index, if (!bs.s.not_found && ext4_xattr_value_same(&bs.s, &i)) goto cleanup; - error = ext4_xattr_ibody_set(inode, &i, &is); + if (ext4_has_feature_ea_inode(inode->i_sb) && + (EXT4_XATTR_SIZE(i.value_len) > + EXT4_XATTR_MIN_LARGE_EA_SIZE(inode->i_sb->s_blocksize))) + i.in_inode = 1; +retry_inode: + error = ext4_xattr_ibody_set(handle, inode, &i, &is); if (!error && !bs.s.not_found) { i.value = NULL; error = ext4_xattr_block_set(handle, inode, &i, &bs); @@ -1226,11 +2336,20 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index, goto cleanup; } error = ext4_xattr_block_set(handle, inode, &i, &bs); - if (error) - goto cleanup; - if (!is.s.not_found) { + if (!error && !is.s.not_found) { i.value = NULL; - error = ext4_xattr_ibody_set(inode, &i, &is); + error = ext4_xattr_ibody_set(handle, inode, &i, + &is); + } else if (error == -ENOSPC) { + /* + * Xattr does not fit in the block, store at + * external inode if possible. + */ + if (ext4_has_feature_ea_inode(inode->i_sb) && + !i.in_inode) { + i.in_inode = 1; + goto retry_inode; + } } } } @@ -1256,6 +2375,33 @@ cleanup: return error; } +int ext4_xattr_set_credits(struct inode *inode, size_t value_len, + bool is_create, int *credits) +{ + struct buffer_head *bh; + int err; + + *credits = 0; + + if (!EXT4_SB(inode->i_sb)->s_journal) + return 0; + + down_read(&EXT4_I(inode)->xattr_sem); + + bh = ext4_xattr_get_block(inode); + if (IS_ERR(bh)) { + err = PTR_ERR(bh); + } else { + *credits = __ext4_xattr_set_credits(inode->i_sb, inode, bh, + value_len, is_create); + brelse(bh); + err = 0; + } + + up_read(&EXT4_I(inode)->xattr_sem); + return err; +} + /* * ext4_xattr_set() * @@ -1269,13 +2415,20 @@ ext4_xattr_set(struct inode *inode, int name_index, const char *name, const void *value, size_t value_len, int flags) { handle_t *handle; + struct super_block *sb = inode->i_sb; int error, retries = 0; - int credits = ext4_jbd2_credits_xattr(inode); + int credits; error = dquot_initialize(inode); if (error) return error; + retry: + error = ext4_xattr_set_credits(inode, value_len, flags & XATTR_CREATE, + &credits); + if (error) + return error; + handle = ext4_journal_start(inode, EXT4_HT_XATTR, credits); if (IS_ERR(handle)) { error = PTR_ERR(handle); @@ -1286,7 +2439,7 @@ retry: value, value_len, flags); error2 = ext4_journal_stop(handle); if (error == -ENOSPC && - ext4_should_retry_alloc(inode->i_sb, &retries)) + ext4_should_retry_alloc(sb, &retries)) goto retry; if (error == 0) error = error2; @@ -1311,7 +2464,7 @@ static void ext4_xattr_shift_entries(struct ext4_xattr_entry *entry, /* Adjust the value offsets of the entries */ for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) { - if (last->e_value_size) { + if (!last->e_value_inum && last->e_value_size) { new_offs = le16_to_cpu(last->e_value_offs) + value_offs_shift; last->e_value_offs = cpu_to_le16(new_offs); @@ -1331,18 +2484,16 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode, struct ext4_xattr_ibody_find *is = NULL; struct ext4_xattr_block_find *bs = NULL; char *buffer = NULL, *b_entry_name = NULL; - size_t value_offs, value_size; + size_t value_size = le32_to_cpu(entry->e_value_size); struct ext4_xattr_info i = { .value = NULL, .value_len = 0, .name_index = entry->e_name_index, + .in_inode = !!entry->e_value_inum, }; struct ext4_xattr_ibody_header *header = IHDR(inode, raw_inode); int error; - value_offs = le16_to_cpu(entry->e_value_offs); - value_size = le32_to_cpu(entry->e_value_size); - is = kzalloc(sizeof(struct ext4_xattr_ibody_find), GFP_NOFS); bs = kzalloc(sizeof(struct ext4_xattr_block_find), GFP_NOFS); buffer = kmalloc(value_size, GFP_NOFS); @@ -1358,7 +2509,15 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode, bs->bh = NULL; /* Save the entry name and the entry value */ - memcpy(buffer, (void *)IFIRST(header) + value_offs, value_size); + if (entry->e_value_inum) { + error = ext4_xattr_inode_get(inode, entry, buffer, value_size); + if (error) + goto out; + } else { + size_t value_offs = le16_to_cpu(entry->e_value_offs); + memcpy(buffer, (void *)IFIRST(header) + value_offs, value_size); + } + memcpy(b_entry_name, entry->e_name, entry->e_name_len); b_entry_name[entry->e_name_len] = '\0'; i.name = b_entry_name; @@ -1372,11 +2531,10 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode, goto out; /* Remove the chosen entry from the inode */ - error = ext4_xattr_ibody_set(inode, &i, is); + error = ext4_xattr_ibody_set(handle, inode, &i, is); if (error) goto out; - i.name = b_entry_name; i.value = buffer; i.value_len = value_size; error = ext4_xattr_block_find(inode, &i, bs); @@ -1420,9 +2578,10 @@ static int ext4_xattr_make_inode_space(handle_t *handle, struct inode *inode, last = IFIRST(header); /* Find the entry best suited to be pushed into EA block */ for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) { - total_size = - EXT4_XATTR_SIZE(le32_to_cpu(last->e_value_size)) + - EXT4_XATTR_LEN(last->e_name_len); + total_size = EXT4_XATTR_LEN(last->e_name_len); + if (!last->e_value_inum) + total_size += EXT4_XATTR_SIZE( + le32_to_cpu(last->e_value_size)); if (total_size <= bfree && total_size < min_total_size) { if (total_size + ifree < isize_diff) { @@ -1441,8 +2600,10 @@ static int ext4_xattr_make_inode_space(handle_t *handle, struct inode *inode, } entry_size = EXT4_XATTR_LEN(entry->e_name_len); - total_size = entry_size + - EXT4_XATTR_SIZE(le32_to_cpu(entry->e_value_size)); + total_size = entry_size; + if (!entry->e_value_inum) + total_size += EXT4_XATTR_SIZE( + le32_to_cpu(entry->e_value_size)); error = ext4_xattr_move_to_block(handle, inode, raw_inode, entry); if (error) @@ -1571,51 +2732,172 @@ cleanup: return error; } +#define EIA_INCR 16 /* must be 2^n */ +#define EIA_MASK (EIA_INCR - 1) +/* Add the large xattr @inode into @ea_inode_array for deferred iput(). + * If @ea_inode_array is new or full it will be grown and the old + * contents copied over. + */ +static int +ext4_expand_inode_array(struct ext4_xattr_inode_array **ea_inode_array, + struct inode *inode) +{ + if (*ea_inode_array == NULL) { + /* + * Start with 15 inodes, so it fits into a power-of-two size. + * If *ea_inode_array is NULL, this is essentially offsetof() + */ + (*ea_inode_array) = + kmalloc(offsetof(struct ext4_xattr_inode_array, + inodes[EIA_MASK]), + GFP_NOFS); + if (*ea_inode_array == NULL) + return -ENOMEM; + (*ea_inode_array)->count = 0; + } else if (((*ea_inode_array)->count & EIA_MASK) == EIA_MASK) { + /* expand the array once all 15 + n * 16 slots are full */ + struct ext4_xattr_inode_array *new_array = NULL; + int count = (*ea_inode_array)->count; + + /* if new_array is NULL, this is essentially offsetof() */ + new_array = kmalloc( + offsetof(struct ext4_xattr_inode_array, + inodes[count + EIA_INCR]), + GFP_NOFS); + if (new_array == NULL) + return -ENOMEM; + memcpy(new_array, *ea_inode_array, + offsetof(struct ext4_xattr_inode_array, inodes[count])); + kfree(*ea_inode_array); + *ea_inode_array = new_array; + } + (*ea_inode_array)->inodes[(*ea_inode_array)->count++] = inode; + return 0; +} /* * ext4_xattr_delete_inode() * - * Free extended attribute resources associated with this inode. This - * is called immediately before an inode is freed. We have exclusive - * access to the inode. + * Free extended attribute resources associated with this inode. Traverse + * all entries and decrement reference on any xattr inodes associated with this + * inode. This is called immediately before an inode is freed. We have exclusive + * access to the inode. If an orphan inode is deleted it will also release its + * references on xattr block and xattr inodes. */ -void -ext4_xattr_delete_inode(handle_t *handle, struct inode *inode) +int ext4_xattr_delete_inode(handle_t *handle, struct inode *inode, + struct ext4_xattr_inode_array **ea_inode_array, + int extra_credits) { struct buffer_head *bh = NULL; + struct ext4_xattr_ibody_header *header; + struct ext4_iloc iloc = { .bh = NULL }; + struct ext4_xattr_entry *entry; + int error; - if (!EXT4_I(inode)->i_file_acl) - goto cleanup; - bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl); - if (!bh) { - EXT4_ERROR_INODE(inode, "block %llu read error", - EXT4_I(inode)->i_file_acl); + error = ext4_xattr_ensure_credits(handle, inode, extra_credits, + NULL /* bh */, + false /* dirty */, + false /* block_csum */); + if (error) { + EXT4_ERROR_INODE(inode, "ensure credits (error %d)", error); goto cleanup; } - if (BHDR(bh)->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC) || - BHDR(bh)->h_blocks != cpu_to_le32(1)) { - EXT4_ERROR_INODE(inode, "bad block %llu", - EXT4_I(inode)->i_file_acl); - goto cleanup; + + if (ext4_has_feature_ea_inode(inode->i_sb) && + ext4_test_inode_state(inode, EXT4_STATE_XATTR)) { + + error = ext4_get_inode_loc(inode, &iloc); + if (error) { + EXT4_ERROR_INODE(inode, "inode loc (error %d)", error); + goto cleanup; + } + + error = ext4_journal_get_write_access(handle, iloc.bh); + if (error) { + EXT4_ERROR_INODE(inode, "write access (error %d)", + error); + goto cleanup; + } + + header = IHDR(inode, ext4_raw_inode(&iloc)); + if (header->h_magic == cpu_to_le32(EXT4_XATTR_MAGIC)) + ext4_xattr_inode_dec_ref_all(handle, inode, iloc.bh, + IFIRST(header), + false /* block_csum */, + ea_inode_array, + extra_credits, + false /* skip_quota */); } - ext4_xattr_release_block(handle, inode, bh); - EXT4_I(inode)->i_file_acl = 0; + if (EXT4_I(inode)->i_file_acl) { + bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl); + if (!bh) { + EXT4_ERROR_INODE(inode, "block %llu read error", + EXT4_I(inode)->i_file_acl); + error = -EIO; + goto cleanup; + } + error = ext4_xattr_check_block(inode, bh); + if (error) { + EXT4_ERROR_INODE(inode, "bad block %llu (error %d)", + EXT4_I(inode)->i_file_acl, error); + goto cleanup; + } + + if (ext4_has_feature_ea_inode(inode->i_sb)) { + for (entry = BFIRST(bh); !IS_LAST_ENTRY(entry); + entry = EXT4_XATTR_NEXT(entry)) + if (entry->e_value_inum) + ext4_xattr_inode_free_quota(inode, + le32_to_cpu(entry->e_value_size)); + + } + + ext4_xattr_release_block(handle, inode, bh, ea_inode_array, + extra_credits); + /* + * Update i_file_acl value in the same transaction that releases + * block. + */ + EXT4_I(inode)->i_file_acl = 0; + error = ext4_mark_inode_dirty(handle, inode); + if (error) { + EXT4_ERROR_INODE(inode, "mark inode dirty (error %d)", + error); + goto cleanup; + } + } + error = 0; cleanup: + brelse(iloc.bh); brelse(bh); + return error; +} + +void ext4_xattr_inode_array_free(struct ext4_xattr_inode_array *ea_inode_array) +{ + int idx; + + if (ea_inode_array == NULL) + return; + + for (idx = 0; idx < ea_inode_array->count; ++idx) + iput(ea_inode_array->inodes[idx]); + kfree(ea_inode_array); } /* - * ext4_xattr_cache_insert() + * ext4_xattr_block_cache_insert() * - * Create a new entry in the extended attribute cache, and insert + * Create a new entry in the extended attribute block cache, and insert * it unless such an entry is already in the cache. * * Returns 0, or a negative error number on failure. */ static void -ext4_xattr_cache_insert(struct mb_cache *ext4_mb_cache, struct buffer_head *bh) +ext4_xattr_block_cache_insert(struct mb_cache *ea_block_cache, + struct buffer_head *bh) { struct ext4_xattr_header *header = BHDR(bh); __u32 hash = le32_to_cpu(header->h_hash); @@ -1623,7 +2905,9 @@ ext4_xattr_cache_insert(struct mb_cache *ext4_mb_cache, struct buffer_head *bh) EXT4_XATTR_REFCOUNT_MAX; int error; - error = mb_cache_entry_create(ext4_mb_cache, GFP_NOFS, hash, + if (!ea_block_cache) + return; + error = mb_cache_entry_create(ea_block_cache, GFP_NOFS, hash, bh->b_blocknr, reusable); if (error) { if (error == -EBUSY) @@ -1655,11 +2939,11 @@ ext4_xattr_cmp(struct ext4_xattr_header *header1, entry1->e_name_index != entry2->e_name_index || entry1->e_name_len != entry2->e_name_len || entry1->e_value_size != entry2->e_value_size || + entry1->e_value_inum != entry2->e_value_inum || memcmp(entry1->e_name, entry2->e_name, entry1->e_name_len)) return 1; - if (entry1->e_value_block != 0 || entry2->e_value_block != 0) - return -EFSCORRUPTED; - if (memcmp((char *)header1 + le16_to_cpu(entry1->e_value_offs), + if (!entry1->e_value_inum && + memcmp((char *)header1 + le16_to_cpu(entry1->e_value_offs), (char *)header2 + le16_to_cpu(entry2->e_value_offs), le32_to_cpu(entry1->e_value_size))) return 1; @@ -1673,7 +2957,7 @@ ext4_xattr_cmp(struct ext4_xattr_header *header1, } /* - * ext4_xattr_cache_find() + * ext4_xattr_block_cache_find() * * Find an identical extended attribute block. * @@ -1681,30 +2965,33 @@ ext4_xattr_cmp(struct ext4_xattr_header *header1, * not found or an error occurred. */ static struct buffer_head * -ext4_xattr_cache_find(struct inode *inode, struct ext4_xattr_header *header, - struct mb_cache_entry **pce) +ext4_xattr_block_cache_find(struct inode *inode, + struct ext4_xattr_header *header, + struct mb_cache_entry **pce) { __u32 hash = le32_to_cpu(header->h_hash); struct mb_cache_entry *ce; - struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode); + struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode); + if (!ea_block_cache) + return NULL; if (!header->h_hash) return NULL; /* never share */ ea_idebug(inode, "looking for cached blocks [%x]", (int)hash); - ce = mb_cache_entry_find_first(ext4_mb_cache, hash); + ce = mb_cache_entry_find_first(ea_block_cache, hash); while (ce) { struct buffer_head *bh; - bh = sb_bread(inode->i_sb, ce->e_block); + bh = sb_bread(inode->i_sb, ce->e_value); if (!bh) { EXT4_ERROR_INODE(inode, "block %lu read error", - (unsigned long) ce->e_block); + (unsigned long)ce->e_value); } else if (ext4_xattr_cmp(header, BHDR(bh)) == 0) { *pce = ce; return bh; } brelse(bh); - ce = mb_cache_entry_find_next(ext4_mb_cache, ce); + ce = mb_cache_entry_find_next(ea_block_cache, ce); } return NULL; } @@ -1717,30 +3004,22 @@ ext4_xattr_cache_find(struct inode *inode, struct ext4_xattr_header *header, * * Compute the hash of an extended attribute. */ -static inline void ext4_xattr_hash_entry(struct ext4_xattr_header *header, - struct ext4_xattr_entry *entry) +static __le32 ext4_xattr_hash_entry(char *name, size_t name_len, __le32 *value, + size_t value_count) { __u32 hash = 0; - char *name = entry->e_name; - int n; - for (n = 0; n < entry->e_name_len; n++) { + while (name_len--) { hash = (hash << NAME_HASH_SHIFT) ^ (hash >> (8*sizeof(hash) - NAME_HASH_SHIFT)) ^ *name++; } - - if (entry->e_value_size != 0) { - __le32 *value = (__le32 *)((char *)header + - le16_to_cpu(entry->e_value_offs)); - for (n = (le32_to_cpu(entry->e_value_size) + - EXT4_XATTR_ROUND) >> EXT4_XATTR_PAD_BITS; n; n--) { - hash = (hash << VALUE_HASH_SHIFT) ^ - (hash >> (8*sizeof(hash) - VALUE_HASH_SHIFT)) ^ - le32_to_cpu(*value++); - } + while (value_count--) { + hash = (hash << VALUE_HASH_SHIFT) ^ + (hash >> (8*sizeof(hash) - VALUE_HASH_SHIFT)) ^ + le32_to_cpu(*value++); } - entry->e_hash = cpu_to_le32(hash); + return cpu_to_le32(hash); } #undef NAME_HASH_SHIFT @@ -1753,13 +3032,11 @@ static inline void ext4_xattr_hash_entry(struct ext4_xattr_header *header, * * Re-compute the extended attribute hash value after an entry has changed. */ -static void ext4_xattr_rehash(struct ext4_xattr_header *header, - struct ext4_xattr_entry *entry) +static void ext4_xattr_rehash(struct ext4_xattr_header *header) { struct ext4_xattr_entry *here; __u32 hash = 0; - ext4_xattr_hash_entry(header, entry); here = ENTRY(header+1); while (!IS_LAST_ENTRY(here)) { if (!here->e_hash) { diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h index 099c8b670ef5..0d2dde1fa87a 100644 --- a/fs/ext4/xattr.h +++ b/fs/ext4/xattr.h @@ -44,7 +44,7 @@ struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ - __le32 e_value_block; /* disk block attribute is stored on (n/i) */ + __le32 e_value_inum; /* inode in which the value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ @@ -69,6 +69,13 @@ struct ext4_xattr_entry { EXT4_I(inode)->i_extra_isize)) #define IFIRST(hdr) ((struct ext4_xattr_entry *)((hdr)+1)) +/* + * The minimum size of EA value when you start storing it in an external inode + * size of block - size of header - size of 1 entry - 4 null bytes +*/ +#define EXT4_XATTR_MIN_LARGE_EA_SIZE(b) \ + ((b) - EXT4_XATTR_LEN(3) - sizeof(struct ext4_xattr_header) - 4) + #define BHDR(bh) ((struct ext4_xattr_header *)((bh)->b_data)) #define ENTRY(ptr) ((struct ext4_xattr_entry *)(ptr)) #define BFIRST(bh) ENTRY(BHDR(bh)+1) @@ -77,10 +84,11 @@ struct ext4_xattr_entry { #define EXT4_ZERO_XATTR_VALUE ((void *)-1) struct ext4_xattr_info { - int name_index; const char *name; const void *value; size_t value_len; + int name_index; + int in_inode; }; struct ext4_xattr_search { @@ -96,6 +104,11 @@ struct ext4_xattr_ibody_find { struct ext4_iloc iloc; }; +struct ext4_xattr_inode_array { + unsigned int count; /* # of used items in the array */ + struct inode *inodes[0]; +}; + extern const struct xattr_handler ext4_xattr_user_handler; extern const struct xattr_handler ext4_xattr_trusted_handler; extern const struct xattr_handler ext4_xattr_security_handler; @@ -139,8 +152,16 @@ extern ssize_t ext4_listxattr(struct dentry *, char *, size_t); extern int ext4_xattr_get(struct inode *, int, const char *, void *, size_t); extern int ext4_xattr_set(struct inode *, int, const char *, const void *, size_t, int); extern int ext4_xattr_set_handle(handle_t *, struct inode *, int, const char *, const void *, size_t, int); +extern int ext4_xattr_set_credits(struct inode *inode, size_t value_len, + bool is_create, int *credits); +extern int __ext4_xattr_set_credits(struct super_block *sb, struct inode *inode, + struct buffer_head *block_bh, size_t value_len, + bool is_create); -extern void ext4_xattr_delete_inode(handle_t *, struct inode *); +extern int ext4_xattr_delete_inode(handle_t *handle, struct inode *inode, + struct ext4_xattr_inode_array **array, + int extra_credits); +extern void ext4_xattr_inode_array_free(struct ext4_xattr_inode_array *array); extern int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize, struct ext4_inode *raw_inode, handle_t *handle); @@ -169,3 +190,11 @@ static inline int ext4_init_security(handle_t *handle, struct inode *inode, return 0; } #endif + +#ifdef CONFIG_LOCKDEP +extern void ext4_xattr_inode_set_class(struct inode *ea_inode); +#else +static inline void ext4_xattr_inode_set_class(struct inode *ea_inode) { } +#endif + +extern int ext4_get_inode_usage(struct inode *inode, qsize_t *usage); diff --git a/fs/fcntl.c b/fs/fcntl.c index ed051f825bad..3b01b646e528 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -109,20 +109,34 @@ void __f_setown(struct file *filp, struct pid *pid, enum pid_type type, } EXPORT_SYMBOL(__f_setown); -void f_setown(struct file *filp, unsigned long arg, int force) +int f_setown(struct file *filp, unsigned long arg, int force) { enum pid_type type; - struct pid *pid; - int who = arg; + struct pid *pid = NULL; + int who = arg, ret = 0; + type = PIDTYPE_PID; if (who < 0) { + /* avoid overflow below */ + if (who == INT_MIN) + return -EINVAL; + type = PIDTYPE_PGID; who = -who; } + rcu_read_lock(); - pid = find_vpid(who); - __f_setown(filp, pid, type, force); + if (who) { + pid = find_vpid(who); + if (!pid) + ret = -ESRCH; + } + + if (!ret) + __f_setown(filp, pid, type, force); rcu_read_unlock(); + + return ret; } EXPORT_SYMBOL(f_setown); @@ -307,6 +321,8 @@ static long fcntl_rw_hint(struct file *file, unsigned int cmd, static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, struct file *filp) { + void __user *argp = (void __user *)arg; + struct flock flock; long err = -EINVAL; switch (cmd) { @@ -334,7 +350,11 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, case F_OFD_GETLK: #endif case F_GETLK: - err = fcntl_getlk(filp, cmd, (struct flock __user *) arg); + if (copy_from_user(&flock, argp, sizeof(flock))) + return -EFAULT; + err = fcntl_getlk(filp, cmd, &flock); + if (!err && copy_to_user(argp, &flock, sizeof(flock))) + return -EFAULT; break; #if BITS_PER_LONG != 32 /* 32-bit arches must use fcntl64() */ @@ -344,7 +364,9 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, /* Fallthrough */ case F_SETLK: case F_SETLKW: - err = fcntl_setlk(fd, filp, cmd, (struct flock __user *) arg); + if (copy_from_user(&flock, argp, sizeof(flock))) + return -EFAULT; + err = fcntl_setlk(fd, filp, cmd, &flock); break; case F_GETOWN: /* @@ -358,8 +380,7 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, force_successful_syscall_return(); break; case F_SETOWN: - f_setown(filp, arg, 1); - err = 0; + err = f_setown(filp, arg, 1); break; case F_GETOWN_EX: err = f_getown_ex(filp, arg); @@ -450,7 +471,9 @@ out: SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { + void __user *argp = (void __user *)arg; struct fd f = fdget_raw(fd); + struct flock64 flock; long err = -EBADF; if (!f.file) @@ -468,14 +491,21 @@ SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, switch (cmd) { case F_GETLK64: case F_OFD_GETLK: - err = fcntl_getlk64(f.file, cmd, (struct flock64 __user *) arg); + err = -EFAULT; + if (copy_from_user(&flock, argp, sizeof(flock))) + break; + err = fcntl_getlk64(f.file, cmd, &flock); + if (!err && copy_to_user(argp, &flock, sizeof(flock))) + err = -EFAULT; break; case F_SETLK64: case F_SETLKW64: case F_OFD_SETLK: case F_OFD_SETLKW: - err = fcntl_setlk64(fd, f.file, cmd, - (struct flock64 __user *) arg); + err = -EFAULT; + if (copy_from_user(&flock, argp, sizeof(flock))) + break; + err = fcntl_setlk64(fd, f.file, cmd, &flock); break; default: err = do_fcntl(fd, cmd, arg, f.file); @@ -489,57 +519,56 @@ out: #endif #ifdef CONFIG_COMPAT -static int get_compat_flock(struct flock *kfl, struct compat_flock __user *ufl) -{ - if (!access_ok(VERIFY_READ, ufl, sizeof(*ufl)) || - __get_user(kfl->l_type, &ufl->l_type) || - __get_user(kfl->l_whence, &ufl->l_whence) || - __get_user(kfl->l_start, &ufl->l_start) || - __get_user(kfl->l_len, &ufl->l_len) || - __get_user(kfl->l_pid, &ufl->l_pid)) +/* careful - don't use anywhere else */ +#define copy_flock_fields(dst, src) \ + (dst)->l_type = (src)->l_type; \ + (dst)->l_whence = (src)->l_whence; \ + (dst)->l_start = (src)->l_start; \ + (dst)->l_len = (src)->l_len; \ + (dst)->l_pid = (src)->l_pid; + +static int get_compat_flock(struct flock *kfl, const struct compat_flock __user *ufl) +{ + struct compat_flock fl; + + if (copy_from_user(&fl, ufl, sizeof(struct compat_flock))) return -EFAULT; + copy_flock_fields(kfl, &fl); return 0; } -static int put_compat_flock(struct flock *kfl, struct compat_flock __user *ufl) +static int get_compat_flock64(struct flock *kfl, const struct compat_flock64 __user *ufl) { - if (!access_ok(VERIFY_WRITE, ufl, sizeof(*ufl)) || - __put_user(kfl->l_type, &ufl->l_type) || - __put_user(kfl->l_whence, &ufl->l_whence) || - __put_user(kfl->l_start, &ufl->l_start) || - __put_user(kfl->l_len, &ufl->l_len) || - __put_user(kfl->l_pid, &ufl->l_pid)) + struct compat_flock64 fl; + + if (copy_from_user(&fl, ufl, sizeof(struct compat_flock64))) return -EFAULT; + copy_flock_fields(kfl, &fl); return 0; } -#ifndef HAVE_ARCH_GET_COMPAT_FLOCK64 -static int get_compat_flock64(struct flock *kfl, struct compat_flock64 __user *ufl) +static int put_compat_flock(const struct flock *kfl, struct compat_flock __user *ufl) { - if (!access_ok(VERIFY_READ, ufl, sizeof(*ufl)) || - __get_user(kfl->l_type, &ufl->l_type) || - __get_user(kfl->l_whence, &ufl->l_whence) || - __get_user(kfl->l_start, &ufl->l_start) || - __get_user(kfl->l_len, &ufl->l_len) || - __get_user(kfl->l_pid, &ufl->l_pid)) + struct compat_flock fl; + + memset(&fl, 0, sizeof(struct compat_flock)); + copy_flock_fields(&fl, kfl); + if (copy_to_user(ufl, &fl, sizeof(struct compat_flock))) return -EFAULT; return 0; } -#endif -#ifndef HAVE_ARCH_PUT_COMPAT_FLOCK64 -static int put_compat_flock64(struct flock *kfl, struct compat_flock64 __user *ufl) +static int put_compat_flock64(const struct flock *kfl, struct compat_flock64 __user *ufl) { - if (!access_ok(VERIFY_WRITE, ufl, sizeof(*ufl)) || - __put_user(kfl->l_type, &ufl->l_type) || - __put_user(kfl->l_whence, &ufl->l_whence) || - __put_user(kfl->l_start, &ufl->l_start) || - __put_user(kfl->l_len, &ufl->l_len) || - __put_user(kfl->l_pid, &ufl->l_pid)) + struct compat_flock64 fl; + + memset(&fl, 0, sizeof(struct compat_flock64)); + copy_flock_fields(&fl, kfl); + if (copy_to_user(ufl, &fl, sizeof(struct compat_flock64))) return -EFAULT; return 0; } -#endif +#undef copy_flock_fields static unsigned int convert_fcntl_cmd(unsigned int cmd) @@ -556,76 +585,92 @@ convert_fcntl_cmd(unsigned int cmd) return cmd; } +/* + * GETLK was successful and we need to return the data, but it needs to fit in + * the compat structure. + * l_start shouldn't be too big, unless the original start + end is greater than + * COMPAT_OFF_T_MAX, in which case the app was asking for trouble, so we return + * -EOVERFLOW in that case. l_len could be too big, in which case we just + * truncate it, and only allow the app to see that part of the conflicting lock + * that might make sense to it anyway + */ +static int fixup_compat_flock(struct flock *flock) +{ + if (flock->l_start > COMPAT_OFF_T_MAX) + return -EOVERFLOW; + if (flock->l_len > COMPAT_OFF_T_MAX) + flock->l_len = COMPAT_OFF_T_MAX; + return 0; +} + COMPAT_SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, compat_ulong_t, arg) { - mm_segment_t old_fs; - struct flock f; - long ret; - unsigned int conv_cmd; + struct fd f = fdget_raw(fd); + struct flock flock; + long err = -EBADF; + + if (!f.file) + return err; + + if (unlikely(f.file->f_mode & FMODE_PATH)) { + if (!check_fcntl_cmd(cmd)) + goto out_put; + } + + err = security_file_fcntl(f.file, cmd, arg); + if (err) + goto out_put; switch (cmd) { case F_GETLK: + err = get_compat_flock(&flock, compat_ptr(arg)); + if (err) + break; + err = fcntl_getlk(f.file, convert_fcntl_cmd(cmd), &flock); + if (err) + break; + err = fixup_compat_flock(&flock); + if (err) + return err; + err = put_compat_flock(&flock, compat_ptr(arg)); + break; + case F_GETLK64: + case F_OFD_GETLK: + err = get_compat_flock64(&flock, compat_ptr(arg)); + if (err) + break; + err = fcntl_getlk(f.file, convert_fcntl_cmd(cmd), &flock); + if (err) + break; + err = fixup_compat_flock(&flock); + if (err) + return err; + err = put_compat_flock64(&flock, compat_ptr(arg)); + break; case F_SETLK: case F_SETLKW: - ret = get_compat_flock(&f, compat_ptr(arg)); - if (ret != 0) + err = get_compat_flock(&flock, compat_ptr(arg)); + if (err) break; - old_fs = get_fs(); - set_fs(KERNEL_DS); - ret = sys_fcntl(fd, cmd, (unsigned long)&f); - set_fs(old_fs); - if (cmd == F_GETLK && ret == 0) { - /* GETLK was successful and we need to return the data... - * but it needs to fit in the compat structure. - * l_start shouldn't be too big, unless the original - * start + end is greater than COMPAT_OFF_T_MAX, in which - * case the app was asking for trouble, so we return - * -EOVERFLOW in that case. - * l_len could be too big, in which case we just truncate it, - * and only allow the app to see that part of the conflicting - * lock that might make sense to it anyway - */ - - if (f.l_start > COMPAT_OFF_T_MAX) - ret = -EOVERFLOW; - if (f.l_len > COMPAT_OFF_T_MAX) - f.l_len = COMPAT_OFF_T_MAX; - if (ret == 0) - ret = put_compat_flock(&f, compat_ptr(arg)); - } + err = fcntl_setlk(fd, f.file, convert_fcntl_cmd(cmd), &flock); break; - - case F_GETLK64: case F_SETLK64: case F_SETLKW64: - case F_OFD_GETLK: case F_OFD_SETLK: case F_OFD_SETLKW: - ret = get_compat_flock64(&f, compat_ptr(arg)); - if (ret != 0) + err = get_compat_flock64(&flock, compat_ptr(arg)); + if (err) break; - old_fs = get_fs(); - set_fs(KERNEL_DS); - conv_cmd = convert_fcntl_cmd(cmd); - ret = sys_fcntl(fd, conv_cmd, (unsigned long)&f); - set_fs(old_fs); - if ((conv_cmd == F_GETLK || conv_cmd == F_OFD_GETLK) && ret == 0) { - /* need to return lock information - see above for commentary */ - if (f.l_start > COMPAT_LOFF_T_MAX) - ret = -EOVERFLOW; - if (f.l_len > COMPAT_LOFF_T_MAX) - f.l_len = COMPAT_LOFF_T_MAX; - if (ret == 0) - ret = put_compat_flock64(&f, compat_ptr(arg)); - } + err = fcntl_setlk(fd, f.file, convert_fcntl_cmd(cmd), &flock); break; - default: - ret = sys_fcntl(fd, cmd, arg); + err = do_fcntl(fd, cmd, arg, f.file); break; } - return ret; +out_put: + fdput(f); + return err; } COMPAT_SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, diff --git a/fs/file.c b/fs/file.c index 1c2972e3a405..1fc7fbbb4510 100644 --- a/fs/file.c +++ b/fs/file.c @@ -30,21 +30,6 @@ unsigned int sysctl_nr_open_min = BITS_PER_LONG; unsigned int sysctl_nr_open_max = __const_min(INT_MAX, ~(size_t)0/sizeof(void *)) & -BITS_PER_LONG; -static void *alloc_fdmem(size_t size) -{ - /* - * Very large allocations can stress page reclaim, so fall back to - * vmalloc() if the allocation size will be considered "large" by the VM. - */ - if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) { - void *data = kmalloc(size, GFP_KERNEL_ACCOUNT | - __GFP_NOWARN | __GFP_NORETRY); - if (data != NULL) - return data; - } - return __vmalloc(size, GFP_KERNEL_ACCOUNT, PAGE_KERNEL); -} - static void __free_fdtable(struct fdtable *fdt) { kvfree(fdt->fd); @@ -131,13 +116,14 @@ static struct fdtable * alloc_fdtable(unsigned int nr) if (!fdt) goto out; fdt->max_fds = nr; - data = alloc_fdmem(nr * sizeof(struct file *)); + data = kvmalloc_array(nr, sizeof(struct file *), GFP_KERNEL_ACCOUNT); if (!data) goto out_fdt; fdt->fd = data; - data = alloc_fdmem(max_t(size_t, - 2 * nr / BITS_PER_BYTE + BITBIT_SIZE(nr), L1_CACHE_BYTES)); + data = kvmalloc(max_t(size_t, + 2 * nr / BITS_PER_BYTE + BITBIT_SIZE(nr), L1_CACHE_BYTES), + GFP_KERNEL_ACCOUNT); if (!data) goto out_arr; fdt->open_fds = data; diff --git a/fs/file_table.c b/fs/file_table.c index 954d510b765a..72e861a35a7f 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -168,6 +168,7 @@ struct file *alloc_file(const struct path *path, fmode_t mode, file->f_path = *path; file->f_inode = path->dentry->d_inode; file->f_mapping = path->dentry->d_inode->i_mapping; + file->f_wb_err = filemap_sample_wb_err(file->f_mapping); if ((mode & FMODE_READ) && likely(fop->read || fop->read_iter)) mode |= FMODE_CAN_READ; diff --git a/fs/filesystems.c b/fs/filesystems.c index cac75547d35c..8b99955e3504 100644 --- a/fs/filesystems.c +++ b/fs/filesystems.c @@ -275,8 +275,10 @@ struct file_system_type *get_fs_type(const char *name) int len = dot ? dot - name : strlen(name); fs = __get_fs_type(name, len); - if (!fs && (request_module("fs-%.*s", len, name) == 0)) + if (!fs && (request_module("fs-%.*s", len, name) == 0)) { fs = __get_fs_type(name, len); + WARN_ONCE(!fs, "request_module fs-%.*s succeeded, but still no fs?\n", len, name); + } if (dot && fs && !(fs->fs_flags & FS_HAS_SUBTYPE)) { put_filesystem(fs); diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 63ee2940775c..8b426f83909f 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -2052,11 +2052,13 @@ static noinline void block_dump___mark_inode_dirty(struct inode *inode) } /** - * __mark_inode_dirty - internal function - * @inode: inode to mark - * @flags: what kind of dirty (i.e. I_DIRTY_SYNC) - * Mark an inode as dirty. Callers should use mark_inode_dirty or - * mark_inode_dirty_sync. + * __mark_inode_dirty - internal function + * + * @inode: inode to mark + * @flags: what kind of dirty (i.e. I_DIRTY_SYNC) + * + * Mark an inode as dirty. Callers should use mark_inode_dirty or + * mark_inode_dirty_sync. * * Put the inode on the super block's dirty list. * diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 4d810be532dd..9fa3aef9a5b3 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -970,7 +970,7 @@ more_rgrps: continue; bn = be64_to_cpu(*p); if (gfs2_holder_initialized(rd_gh)) { - rgd = (struct gfs2_rgrpd *)rd_gh->gh_gl->gl_object; + rgd = gfs2_glock2rgrp(rd_gh->gh_gl); gfs2_assert_withdraw(sdp, gfs2_glock_is_locked_by_me(rd_gh->gh_gl)); } else { diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c index 79113219be5f..db427658ccd9 100644 --- a/fs/gfs2/dir.c +++ b/fs/gfs2/dir.c @@ -1444,7 +1444,7 @@ static int gfs2_dir_read_leaf(struct inode *inode, struct dir_context *ctx, "g.offset (%u)\n", (unsigned long long)bh->b_blocknr, entries2, g.offset); - + gfs2_consist_inode(ip); error = -EIO; goto out_free; } @@ -1612,6 +1612,7 @@ int gfs2_dir_read(struct inode *inode, struct dir_context *ctx, (unsigned long long)dip->i_no_addr, dip->i_entries, g.offset); + gfs2_consist_inode(dip); error = -EIO; goto out; } @@ -2031,8 +2032,8 @@ static int leaf_dealloc(struct gfs2_inode *dip, u32 index, u32 len, gfs2_rlist_alloc(&rlist, LM_ST_EXCLUSIVE); for (x = 0; x < rlist.rl_rgrps; x++) { - struct gfs2_rgrpd *rgd; - rgd = rlist.rl_ghs[x].gh_gl->gl_object; + struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(rlist.rl_ghs[x].gh_gl); + rg_blocks += rgd->rd_length; } diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 959a19ced4d5..c38ab6c81898 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -80,9 +80,9 @@ static struct rhashtable_params ht_parms = { static struct rhashtable gl_hash_table; -void gfs2_glock_free(struct gfs2_glock *gl) +static void gfs2_glock_dealloc(struct rcu_head *rcu) { - struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; + struct gfs2_glock *gl = container_of(rcu, struct gfs2_glock, gl_rcu); if (gl->gl_ops->go_flags & GLOF_ASPACE) { kmem_cache_free(gfs2_glock_aspace_cachep, gl); @@ -90,6 +90,13 @@ void gfs2_glock_free(struct gfs2_glock *gl) kfree(gl->gl_lksb.sb_lvbptr); kmem_cache_free(gfs2_glock_cachep, gl); } +} + +void gfs2_glock_free(struct gfs2_glock *gl) +{ + struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; + + call_rcu(&gl->gl_rcu, gfs2_glock_dealloc); if (atomic_dec_and_test(&sdp->sd_glock_disposal)) wake_up(&sdp->sd_glock_wait); } @@ -152,20 +159,34 @@ static void gfs2_glock_remove_from_lru(struct gfs2_glock *gl) spin_unlock(&lru_lock); } -/** - * gfs2_glock_put() - Decrement reference count on glock - * @gl: The glock to put - * +/* + * Enqueue the glock on the work queue. Passes one glock reference on to the + * work queue. */ +static void __gfs2_glock_queue_work(struct gfs2_glock *gl, unsigned long delay) { + if (!queue_delayed_work(glock_workqueue, &gl->gl_work, delay)) { + /* + * We are holding the lockref spinlock, and the work was still + * queued above. The queued work (glock_work_func) takes that + * spinlock before dropping its glock reference(s), so it + * cannot have dropped them in the meantime. + */ + GLOCK_BUG_ON(gl, gl->gl_lockref.count < 2); + gl->gl_lockref.count--; + } +} -void gfs2_glock_put(struct gfs2_glock *gl) +static void gfs2_glock_queue_work(struct gfs2_glock *gl, unsigned long delay) { + spin_lock(&gl->gl_lockref.lock); + __gfs2_glock_queue_work(gl, delay); + spin_unlock(&gl->gl_lockref.lock); +} + +static void __gfs2_glock_put(struct gfs2_glock *gl) { struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; struct address_space *mapping = gfs2_glock2aspace(gl); - if (lockref_put_or_lock(&gl->gl_lockref)) - return; - lockref_mark_dead(&gl->gl_lockref); gfs2_glock_remove_from_lru(gl); @@ -178,6 +199,20 @@ void gfs2_glock_put(struct gfs2_glock *gl) } /** + * gfs2_glock_put() - Decrement reference count on glock + * @gl: The glock to put + * + */ + +void gfs2_glock_put(struct gfs2_glock *gl) +{ + if (lockref_put_or_lock(&gl->gl_lockref)) + return; + + __gfs2_glock_put(gl); +} + +/** * may_grant - check if its ok to grant a new lock * @gl: The glock * @gh: The lock request which we wish to grant @@ -482,8 +517,7 @@ __acquires(&gl->gl_lockref.lock) target == LM_ST_UNLOCKED && test_bit(SDF_SKIP_DLM_UNLOCK, &sdp->sd_flags)) { finish_xmote(gl, target); - if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0) - gfs2_glock_put(gl); + gfs2_glock_queue_work(gl, 0); } else if (ret) { pr_err("lm_lock ret %d\n", ret); @@ -492,8 +526,7 @@ __acquires(&gl->gl_lockref.lock) } } else { /* lock_nolock */ finish_xmote(gl, target); - if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0) - gfs2_glock_put(gl); + gfs2_glock_queue_work(gl, 0); } spin_lock(&gl->gl_lockref.lock); @@ -565,8 +598,7 @@ out_sched: clear_bit(GLF_LOCK, &gl->gl_flags); smp_mb__after_atomic(); gl->gl_lockref.count++; - if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0) - gl->gl_lockref.count--; + __gfs2_glock_queue_work(gl, 0); return; out_unlock: @@ -601,11 +633,11 @@ static void glock_work_func(struct work_struct *work) { unsigned long delay = 0; struct gfs2_glock *gl = container_of(work, struct gfs2_glock, gl_work.work); - int drop_ref = 0; + unsigned int drop_refs = 1; if (test_and_clear_bit(GLF_REPLY_PENDING, &gl->gl_flags)) { finish_xmote(gl, gl->gl_reply); - drop_ref = 1; + drop_refs++; } spin_lock(&gl->gl_lockref.lock); if (test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) && @@ -623,17 +655,25 @@ static void glock_work_func(struct work_struct *work) } } run_queue(gl, 0); - spin_unlock(&gl->gl_lockref.lock); - if (!delay) - gfs2_glock_put(gl); - else { + if (delay) { + /* Keep one glock reference for the work we requeue. */ + drop_refs--; if (gl->gl_name.ln_type != LM_TYPE_INODE) delay = 0; - if (queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0) - gfs2_glock_put(gl); + __gfs2_glock_queue_work(gl, delay); } - if (drop_ref) - gfs2_glock_put(gl); + + /* + * Drop the remaining glock references manually here. (Mind that + * __gfs2_glock_queue_work depends on the lockref spinlock begin held + * here as well.) + */ + gl->gl_lockref.count -= drop_refs; + if (!gl->gl_lockref.count) { + __gfs2_glock_put(gl); + return; + } + spin_unlock(&gl->gl_lockref.lock); } /** @@ -986,8 +1026,7 @@ int gfs2_glock_nq(struct gfs2_holder *gh) test_and_clear_bit(GLF_FROZEN, &gl->gl_flags))) { set_bit(GLF_REPLY_PENDING, &gl->gl_flags); gl->gl_lockref.count++; - if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0) - gl->gl_lockref.count--; + __gfs2_glock_queue_work(gl, 0); } run_queue(gl, 1); spin_unlock(&gl->gl_lockref.lock); @@ -1047,17 +1086,15 @@ void gfs2_glock_dq(struct gfs2_holder *gh) gfs2_glock_add_to_lru(gl); trace_gfs2_glock_queue(gh, 0); + if (unlikely(!fast_path)) { + gl->gl_lockref.count++; + if (test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) && + !test_bit(GLF_DEMOTE, &gl->gl_flags) && + gl->gl_name.ln_type == LM_TYPE_INODE) + delay = gl->gl_hold_time; + __gfs2_glock_queue_work(gl, delay); + } spin_unlock(&gl->gl_lockref.lock); - if (likely(fast_path)) - return; - - gfs2_glock_hold(gl); - if (test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) && - !test_bit(GLF_DEMOTE, &gl->gl_flags) && - gl->gl_name.ln_type == LM_TYPE_INODE) - delay = gl->gl_hold_time; - if (queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0) - gfs2_glock_put(gl); } void gfs2_glock_dq_wait(struct gfs2_holder *gh) @@ -1233,9 +1270,8 @@ void gfs2_glock_cb(struct gfs2_glock *gl, unsigned int state) spin_lock(&gl->gl_lockref.lock); handle_callback(gl, state, delay, true); + __gfs2_glock_queue_work(gl, delay); spin_unlock(&gl->gl_lockref.lock); - if (queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0) - gfs2_glock_put(gl); } /** @@ -1294,10 +1330,8 @@ void gfs2_glock_complete(struct gfs2_glock *gl, int ret) gl->gl_lockref.count++; set_bit(GLF_REPLY_PENDING, &gl->gl_flags); + __gfs2_glock_queue_work(gl, 0); spin_unlock(&gl->gl_lockref.lock); - - if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0) - gfs2_glock_put(gl); } static int glock_cmp(void *priv, struct list_head *a, struct list_head *b) @@ -1355,8 +1389,7 @@ add_back_to_lru: if (demote_ok(gl)) handle_callback(gl, LM_ST_UNLOCKED, 0, false); WARN_ON(!test_and_clear_bit(GLF_LOCK, &gl->gl_flags)); - if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0) - gl->gl_lockref.count--; + __gfs2_glock_queue_work(gl, 0); spin_unlock(&gl->gl_lockref.lock); cond_resched_lock(&lru_lock); } @@ -1462,13 +1495,12 @@ static void glock_hash_walk(glock_examiner examiner, const struct gfs2_sbd *sdp) static void thaw_glock(struct gfs2_glock *gl) { - if (!test_and_clear_bit(GLF_FROZEN, &gl->gl_flags)) - goto out; - set_bit(GLF_REPLY_PENDING, &gl->gl_flags); - if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0) { -out: + if (!test_and_clear_bit(GLF_FROZEN, &gl->gl_flags)) { gfs2_glock_put(gl); + return; } + set_bit(GLF_REPLY_PENDING, &gl->gl_flags); + gfs2_glock_queue_work(gl, 0); } /** @@ -1484,9 +1516,8 @@ static void clear_glock(struct gfs2_glock *gl) spin_lock(&gl->gl_lockref.lock); if (gl->gl_state != LM_ST_UNLOCKED) handle_callback(gl, LM_ST_UNLOCKED, 0, false); + __gfs2_glock_queue_work(gl, 0); spin_unlock(&gl->gl_lockref.lock); - if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0) - gfs2_glock_put(gl); } /** diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h index ab1ef322f7a5..9ad4a6ac6c84 100644 --- a/fs/gfs2/glock.h +++ b/fs/gfs2/glock.h @@ -257,4 +257,11 @@ static inline bool gfs2_holder_initialized(struct gfs2_holder *gh) return gh->gh_gl; } +static inline void glock_set_object(struct gfs2_glock *gl, void *object) +{ + spin_lock(&gl->gl_lockref.lock); + gl->gl_object = object; + spin_unlock(&gl->gl_lockref.lock); +} + #endif /* __GLOCK_DOT_H__ */ diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 5db59d444838..5e69636d4dd3 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -137,7 +137,7 @@ void gfs2_ail_flush(struct gfs2_glock *gl, bool fsync) * * Called when demoting or unlocking an EX glock. We must flush * to disk all dirty buffers/pages relating to this glock, and must not - * not return to caller to demote/unlock the glock until I/O is complete. + * return to caller to demote/unlock the glock until I/O is complete. */ static void rgrp_go_sync(struct gfs2_glock *gl) @@ -184,7 +184,7 @@ static void rgrp_go_inval(struct gfs2_glock *gl, int flags) { struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; struct address_space *mapping = &sdp->sd_aspace; - struct gfs2_rgrpd *rgd = gl->gl_object; + struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl); if (rgd) gfs2_rgrp_brelse(rgd); @@ -197,6 +197,38 @@ static void rgrp_go_inval(struct gfs2_glock *gl, int flags) rgd->rd_flags &= ~GFS2_RDF_UPTODATE; } +static struct gfs2_inode *gfs2_glock2inode(struct gfs2_glock *gl) +{ + struct gfs2_inode *ip; + + spin_lock(&gl->gl_lockref.lock); + ip = gl->gl_object; + if (ip) + set_bit(GIF_GLOP_PENDING, &ip->i_flags); + spin_unlock(&gl->gl_lockref.lock); + return ip; +} + +struct gfs2_rgrpd *gfs2_glock2rgrp(struct gfs2_glock *gl) +{ + struct gfs2_rgrpd *rgd; + + spin_lock(&gl->gl_lockref.lock); + rgd = gl->gl_object; + spin_unlock(&gl->gl_lockref.lock); + + return rgd; +} + +static void gfs2_clear_glop_pending(struct gfs2_inode *ip) +{ + if (!ip) + return; + + clear_bit_unlock(GIF_GLOP_PENDING, &ip->i_flags); + wake_up_bit(&ip->i_flags, GIF_GLOP_PENDING); +} + /** * inode_go_sync - Sync the dirty data and/or metadata for an inode glock * @gl: the glock protecting the inode @@ -205,25 +237,24 @@ static void rgrp_go_inval(struct gfs2_glock *gl, int flags) static void inode_go_sync(struct gfs2_glock *gl) { - struct gfs2_inode *ip = gl->gl_object; + struct gfs2_inode *ip = gfs2_glock2inode(gl); + int isreg = ip && S_ISREG(ip->i_inode.i_mode); struct address_space *metamapping = gfs2_glock2aspace(gl); int error; - if (ip && !S_ISREG(ip->i_inode.i_mode)) - ip = NULL; - if (ip) { + if (isreg) { if (test_and_clear_bit(GIF_SW_PAGED, &ip->i_flags)) unmap_shared_mapping_range(ip->i_inode.i_mapping, 0, 0); inode_dio_wait(&ip->i_inode); } if (!test_and_clear_bit(GLF_DIRTY, &gl->gl_flags)) - return; + goto out; GLOCK_BUG_ON(gl, gl->gl_state != LM_ST_EXCLUSIVE); gfs2_log_flush(gl->gl_name.ln_sbd, gl, NORMAL_FLUSH); filemap_fdatawrite(metamapping); - if (ip) { + if (isreg) { struct address_space *mapping = ip->i_inode.i_mapping; filemap_fdatawrite(mapping); error = filemap_fdatawait(mapping); @@ -238,6 +269,9 @@ static void inode_go_sync(struct gfs2_glock *gl) */ smp_mb__before_atomic(); clear_bit(GLF_DIRTY, &gl->gl_flags); + +out: + gfs2_clear_glop_pending(ip); } /** @@ -253,7 +287,7 @@ static void inode_go_sync(struct gfs2_glock *gl) static void inode_go_inval(struct gfs2_glock *gl, int flags) { - struct gfs2_inode *ip = gl->gl_object; + struct gfs2_inode *ip = gfs2_glock2inode(gl); gfs2_assert_withdraw(gl->gl_name.ln_sbd, !atomic_read(&gl->gl_ail_count)); @@ -274,6 +308,8 @@ static void inode_go_inval(struct gfs2_glock *gl, int flags) } if (ip && S_ISREG(ip->i_inode.i_mode)) truncate_inode_pages(ip->i_inode.i_mapping, 0); + + gfs2_clear_glop_pending(ip); } /** @@ -541,7 +577,7 @@ static int freeze_go_demote_ok(const struct gfs2_glock *gl) */ static void iopen_go_callback(struct gfs2_glock *gl, bool remote) { - struct gfs2_inode *ip = (struct gfs2_inode *)gl->gl_object; + struct gfs2_inode *ip = gl->gl_object; struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; if (!remote || (sdp->sd_vfs->s_flags & MS_RDONLY)) diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index aa3d44527fa2..73fce76e67ee 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -336,7 +336,6 @@ enum { }; struct gfs2_glock { - struct hlist_bl_node gl_list; unsigned long gl_flags; /* GLF_... */ struct lm_lockname gl_name; @@ -374,6 +373,7 @@ struct gfs2_glock { loff_t end; } gl_vm; }; + struct rcu_head gl_rcu; struct rhash_head gl_node; }; @@ -386,6 +386,7 @@ enum { GIF_SW_PAGED = 3, GIF_ORDERED = 4, GIF_FREE_VFS_INODE = 5, + GIF_GLOP_PENDING = 6, }; struct gfs2_inode { @@ -820,7 +821,6 @@ struct gfs2_sbd { wait_queue_head_t sd_reserving_log_wait; unsigned int sd_log_flush_head; - u64 sd_log_flush_wrapped; spinlock_t sd_ail_lock; struct list_head sd_ail1_list; @@ -857,5 +857,7 @@ static inline void gfs2_sbstats_inc(const struct gfs2_glock *gl, int which) preempt_enable(); } +extern struct gfs2_rgrpd *gfs2_glock2rgrp(struct gfs2_glock *gl); + #endif /* __INCORE_DOT_H__ */ diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 9f605ea4810c..acca501f8110 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -144,7 +144,8 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, error = gfs2_glock_get(sdp, no_addr, &gfs2_inode_glops, CREATE, &ip->i_gl); if (unlikely(error)) goto fail; - ip->i_gl->gl_object = ip; + flush_delayed_work(&ip->i_gl->gl_work); + glock_set_object(ip->i_gl, ip); error = gfs2_glock_get(sdp, no_addr, &gfs2_iopen_glops, CREATE, &io_gl); if (unlikely(error)) @@ -173,8 +174,8 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh); if (unlikely(error)) goto fail_put; - - ip->i_iopen_gh.gh_gl->gl_object = ip; + flush_delayed_work(&ip->i_iopen_gh.gh_gl->gl_work); + glock_set_object(ip->i_iopen_gh.gh_gl, ip); gfs2_glock_put(io_gl); io_gl = NULL; @@ -201,14 +202,14 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, fail_refresh: ip->i_iopen_gh.gh_flags |= GL_NOCACHE; - ip->i_iopen_gh.gh_gl->gl_object = NULL; + glock_set_object(ip->i_iopen_gh.gh_gl, NULL); gfs2_glock_dq_uninit(&ip->i_iopen_gh); fail_put: if (io_gl) gfs2_glock_put(io_gl); if (gfs2_holder_initialized(&i_gh)) gfs2_glock_dq_uninit(&i_gh); - ip->i_gl->gl_object = NULL; + glock_set_object(ip->i_gl, NULL); fail: iget_failed(inode); return ERR_PTR(error); @@ -607,6 +608,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, error = gfs2_glock_nq_init(dip->i_gl, LM_ST_EXCLUSIVE, 0, ghs); if (error) goto fail; + gfs2_holder_mark_uninitialized(ghs + 1); error = create_ok(dip, name, mode); if (error) @@ -705,7 +707,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, if (error) goto fail_free_inode; - ip->i_gl->gl_object = ip; + glock_set_object(ip->i_gl, ip); error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, ghs + 1); if (error) goto fail_free_inode; @@ -731,7 +733,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, if (error) goto fail_gunlock2; - ip->i_iopen_gh.gh_gl->gl_object = ip; + glock_set_object(ip->i_iopen_gh.gh_gl, ip); gfs2_glock_put(io_gl); gfs2_set_iop(inode); insert_inode_hash(inode); @@ -778,7 +780,6 @@ fail_gunlock3: fail_gunlock2: if (io_gl) clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags); - gfs2_glock_dq_uninit(ghs + 1); fail_free_inode: if (ip->i_gl) gfs2_glock_put(ip->i_gl); @@ -799,6 +800,8 @@ fail_gunlock: &GFS2_I(inode)->i_flags); iput(inode); } + if (gfs2_holder_initialized(ghs + 1)) + gfs2_glock_dq_uninit(ghs + 1); fail: return error; } diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index d2955daf17a4..9a624f694400 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -722,7 +722,6 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, clear_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags); sdp->sd_log_flush_head = sdp->sd_log_head; - sdp->sd_log_flush_wrapped = 0; tr = sdp->sd_log_tr; if (tr) { sdp->sd_log_tr = NULL; @@ -775,7 +774,6 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, } atomic_dec(&sdp->sd_log_blks_free); /* Adjust for unreserved buffer */ trace_gfs2_log_blocks(sdp, -1); - sdp->sd_log_flush_wrapped = 0; log_write_header(sdp, 0); sdp->sd_log_head = sdp->sd_log_flush_head; } @@ -880,7 +878,6 @@ void gfs2_log_shutdown(struct gfs2_sbd *sdp) gfs2_assert_withdraw(sdp, list_empty(&sdp->sd_ail1_list)); sdp->sd_log_flush_head = sdp->sd_log_head; - sdp->sd_log_flush_wrapped = 0; log_write_header(sdp, GFS2_LOG_HEAD_UNMOUNT); diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index 885d36e7a29f..3010f9edd177 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -71,7 +71,7 @@ static void maybe_release_space(struct gfs2_bufdata *bd) { struct gfs2_glock *gl = bd->bd_gl; struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; - struct gfs2_rgrpd *rgd = gl->gl_object; + struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl); unsigned int index = bd->bd_bh->b_blocknr - gl->gl_name.ln_number; struct gfs2_bitmap *bi = rgd->rd_bits + index; @@ -134,10 +134,8 @@ static void gfs2_log_incr_head(struct gfs2_sbd *sdp) BUG_ON((sdp->sd_log_flush_head == sdp->sd_log_tail) && (sdp->sd_log_flush_head != sdp->sd_log_head)); - if (++sdp->sd_log_flush_head == sdp->sd_jdesc->jd_blocks) { + if (++sdp->sd_log_flush_head == sdp->sd_jdesc->jd_blocks) sdp->sd_log_flush_head = 0; - sdp->sd_log_flush_wrapped = 1; - } } static u64 gfs2_log_bmap(struct gfs2_sbd *sdp) @@ -182,7 +180,7 @@ static void gfs2_end_log_write_bh(struct gfs2_sbd *sdp, struct bio_vec *bvec, bh = bh->b_this_page; do { if (error) - set_buffer_write_io_error(bh); + mark_buffer_write_io_error(bh); unlock_buffer(bh); next = bh->b_this_page; size -= bh->b_size; diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index 67d1fc4668f7..0a89e6f7a314 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -52,7 +52,6 @@ static void gfs2_init_glock_once(void *foo) { struct gfs2_glock *gl = foo; - INIT_HLIST_BL_NODE(&gl->gl_list); spin_lock_init(&gl->gl_lockref.lock); INIT_LIST_HEAD(&gl->gl_holders); INIT_LIST_HEAD(&gl->gl_lru); diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 83c9909ff14a..836e38ba5d0a 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -705,9 +705,7 @@ void gfs2_clear_rgrpd(struct gfs2_sbd *sdp) rb_erase(n, &sdp->sd_rindex_tree); if (gl) { - spin_lock(&gl->gl_lockref.lock); - gl->gl_object = NULL; - spin_unlock(&gl->gl_lockref.lock); + glock_set_object(gl, NULL); gfs2_glock_add_to_lru(gl); gfs2_glock_put(gl); } @@ -917,7 +915,7 @@ static int read_rindex_entry(struct gfs2_inode *ip) error = rgd_insert(rgd); spin_unlock(&sdp->sd_rindex_spin); if (!error) { - rgd->rd_gl->gl_object = rgd; + glock_set_object(rgd->rd_gl, rgd); rgd->rd_gl->gl_vm.start = (rgd->rd_addr * bsize) & PAGE_MASK; rgd->rd_gl->gl_vm.end = PAGE_ALIGN((rgd->rd_addr + rgd->rd_length) * bsize) - 1; diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 29b0473f6e74..fdedec379b78 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -1105,9 +1105,12 @@ static int gfs2_statfs_slow(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host gfs2_holder_uninit(gh); error = err; } else { - if (!error) - error = statfs_slow_fill( - gh->gh_gl->gl_object, sc); + if (!error) { + struct gfs2_rgrpd *rgd = + gfs2_glock2rgrp(gh->gh_gl); + + error = statfs_slow_fill(rgd, sc); + } gfs2_glock_dq_uninit(gh); } } @@ -1535,6 +1538,12 @@ static void gfs2_evict_inode(struct inode *inode) if (inode->i_nlink || (sb->s_flags & MS_RDONLY)) goto out; + if (test_bit(GIF_ALLOC_FAILED, &ip->i_flags)) { + BUG_ON(!gfs2_glock_is_locked_by_me(ip->i_gl)); + gfs2_holder_mark_uninitialized(&gh); + goto alloc_failed; + } + /* Must not read inode block until block type has been verified */ error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, &gh); if (unlikely(error)) { @@ -1543,11 +1552,9 @@ static void gfs2_evict_inode(struct inode *inode) goto out; } - if (!test_bit(GIF_ALLOC_FAILED, &ip->i_flags)) { - error = gfs2_check_blk_type(sdp, ip->i_no_addr, GFS2_BLKST_UNLINKED); - if (error) - goto out_truncate; - } + error = gfs2_check_blk_type(sdp, ip->i_no_addr, GFS2_BLKST_UNLINKED); + if (error) + goto out_truncate; if (test_bit(GIF_INVALID, &ip->i_flags)) { error = gfs2_inode_refresh(ip); @@ -1555,6 +1562,7 @@ static void gfs2_evict_inode(struct inode *inode) goto out_truncate; } +alloc_failed: if (gfs2_holder_initialized(&ip->i_iopen_gh) && test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags)) { ip->i_iopen_gh.gh_flags |= GL_NOCACHE; @@ -1621,7 +1629,8 @@ out_unlock: } gfs2_holder_uninit(&ip->i_iopen_gh); } - gfs2_glock_dq_uninit(&gh); + if (gfs2_holder_initialized(&gh)) + gfs2_glock_dq_uninit(&gh); if (error && error != GLR_TRYFAILED && error != -EROFS) fs_warn(sdp, "gfs2_evict_inode: %d\n", error); out: @@ -1631,13 +1640,13 @@ out: gfs2_ordered_del_inode(ip); clear_inode(inode); gfs2_dir_hash_inval(ip); - ip->i_gl->gl_object = NULL; - flush_delayed_work(&ip->i_gl->gl_work); + glock_set_object(ip->i_gl, NULL); + wait_on_bit_io(&ip->i_flags, GIF_GLOP_PENDING, TASK_UNINTERRUPTIBLE); gfs2_glock_add_to_lru(ip->i_gl); gfs2_glock_put(ip->i_gl); ip->i_gl = NULL; if (gfs2_holder_initialized(&ip->i_iopen_gh)) { - ip->i_iopen_gh.gh_gl->gl_object = NULL; + glock_set_object(ip->i_iopen_gh.gh_gl, NULL); ip->i_iopen_gh.gh_flags |= GL_NOCACHE; gfs2_glock_dq_uninit(&ip->i_iopen_gh); } diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c index e77bc52b468f..ca1f97ff898c 100644 --- a/fs/gfs2/sys.c +++ b/fs/gfs2/sys.c @@ -626,12 +626,12 @@ static struct attribute *tune_attrs[] = { NULL, }; -static struct attribute_group tune_group = { +static const struct attribute_group tune_group = { .name = "tune", .attrs = tune_attrs, }; -static struct attribute_group lock_module_group = { +static const struct attribute_group lock_module_group = { .name = "lock_module", .attrs = lock_module_attrs, }; diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c index d87721aeb575..54179554c7d2 100644 --- a/fs/gfs2/xattr.c +++ b/fs/gfs2/xattr.c @@ -1327,8 +1327,8 @@ static int ea_dealloc_indirect(struct gfs2_inode *ip) gfs2_rlist_alloc(&rlist, LM_ST_EXCLUSIVE); for (x = 0; x < rlist.rl_rgrps; x++) { - struct gfs2_rgrpd *rgd; - rgd = rlist.rl_ghs[x].gh_gl->gl_object; + struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(rlist.rl_ghs[x].gh_gl); + rg_blocks += rgd->rd_length; } diff --git a/fs/inode.c b/fs/inode.c index ab3b9a795c0b..50370599e371 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1915,8 +1915,6 @@ __setup("ihash_entries=", set_ihash_entries); */ void __init inode_init_early(void) { - unsigned int loop; - /* If hashes are distributed across NUMA nodes, defer * hash allocation until vmalloc space is available. */ @@ -1928,20 +1926,15 @@ void __init inode_init_early(void) sizeof(struct hlist_head), ihash_entries, 14, - HASH_EARLY, + HASH_EARLY | HASH_ZERO, &i_hash_shift, &i_hash_mask, 0, 0); - - for (loop = 0; loop < (1U << i_hash_shift); loop++) - INIT_HLIST_HEAD(&inode_hashtable[loop]); } void __init inode_init(void) { - unsigned int loop; - /* inode slab cache */ inode_cachep = kmem_cache_create("inode_cache", sizeof(struct inode), @@ -1959,14 +1952,11 @@ void __init inode_init(void) sizeof(struct hlist_head), ihash_entries, 14, - 0, + HASH_ZERO, &i_hash_shift, &i_hash_mask, 0, 0); - - for (loop = 0; loop < (1U << i_hash_shift); loop++) - INIT_HLIST_HEAD(&inode_hashtable[loop]); } void init_special_inode(struct inode *inode, umode_t mode, dev_t rdev) @@ -2024,7 +2014,7 @@ bool inode_owner_or_capable(const struct inode *inode) return true; ns = current_user_ns(); - if (ns_capable(ns, CAP_FOWNER) && kuid_has_mapping(ns, inode->i_uid)) + if (kuid_has_mapping(ns, inode->i_uid) && ns_capable(ns, CAP_FOWNER)) return true; return false; } diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index b6b194ec1b4f..3c1c31321d9b 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -263,18 +263,10 @@ static int journal_finish_inode_data_buffers(journal_t *journal, continue; jinode->i_flags |= JI_COMMIT_RUNNING; spin_unlock(&journal->j_list_lock); - err = filemap_fdatawait(jinode->i_vfs_inode->i_mapping); - if (err) { - /* - * Because AS_EIO is cleared by - * filemap_fdatawait_range(), set it again so - * that user process can get -EIO from fsync(). - */ - mapping_set_error(jinode->i_vfs_inode->i_mapping, -EIO); - - if (!ret) - ret = err; - } + err = filemap_fdatawait_keep_errors( + jinode->i_vfs_inode->i_mapping); + if (!ret) + ret = err; spin_lock(&journal->j_list_lock); jinode->i_flags &= ~JI_COMMIT_RUNNING; smp_mb(); diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 2d30a6da7013..8b08044b3120 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -409,25 +409,6 @@ static handle_t *new_handle(int nblocks) return handle; } -/** - * handle_t *jbd2_journal_start() - Obtain a new handle. - * @journal: Journal to start transaction on. - * @nblocks: number of block buffer we might modify - * - * We make sure that the transaction can guarantee at least nblocks of - * modified buffers in the log. We block until the log can guarantee - * that much space. Additionally, if rsv_blocks > 0, we also create another - * handle with rsv_blocks reserved blocks in the journal. This handle is - * is stored in h_rsv_handle. It is not attached to any particular transaction - * and thus doesn't block transaction commit. If the caller uses this reserved - * handle, it has to set h_rsv_handle to NULL as otherwise jbd2_journal_stop() - * on the parent handle will dispose the reserved one. Reserved handle has to - * be converted to a normal handle using jbd2_journal_start_reserved() before - * it can be used. - * - * Return a pointer to a newly allocated handle, or an ERR_PTR() value - * on failure. - */ handle_t *jbd2__journal_start(journal_t *journal, int nblocks, int rsv_blocks, gfp_t gfp_mask, unsigned int type, unsigned int line_no) @@ -478,6 +459,25 @@ handle_t *jbd2__journal_start(journal_t *journal, int nblocks, int rsv_blocks, EXPORT_SYMBOL(jbd2__journal_start); +/** + * handle_t *jbd2_journal_start() - Obtain a new handle. + * @journal: Journal to start transaction on. + * @nblocks: number of block buffer we might modify + * + * We make sure that the transaction can guarantee at least nblocks of + * modified buffers in the log. We block until the log can guarantee + * that much space. Additionally, if rsv_blocks > 0, we also create another + * handle with rsv_blocks reserved blocks in the journal. This handle is + * is stored in h_rsv_handle. It is not attached to any particular transaction + * and thus doesn't block transaction commit. If the caller uses this reserved + * handle, it has to set h_rsv_handle to NULL as otherwise jbd2_journal_stop() + * on the parent handle will dispose the reserved one. Reserved handle has to + * be converted to a normal handle using jbd2_journal_start_reserved() before + * it can be used. + * + * Return a pointer to a newly allocated handle, or an ERR_PTR() value + * on failure. + */ handle_t *jbd2_journal_start(journal_t *journal, int nblocks) { return jbd2__journal_start(journal, nblocks, 0, GFP_NOFS, 0, 0); @@ -1072,10 +1072,10 @@ out: * @handle: transaction to add buffer modifications to * @bh: bh to be used for metadata writes * - * Returns an error code or 0 on success. + * Returns: error code or 0 on success. * * In full data journalling mode the buffer may be of type BJ_AsyncData, - * because we're write()ing a buffer which is also part of a shared mapping. + * because we're ``write()ing`` a buffer which is also part of a shared mapping. */ int jbd2_journal_get_write_access(handle_t *handle, struct buffer_head *bh) diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c index ce93db3aef3c..65120a471729 100644 --- a/fs/jfs/jfs_metapage.c +++ b/fs/jfs/jfs_metapage.c @@ -664,6 +664,7 @@ struct metapage *__get_metapage(struct inode *inode, unsigned long lblock, INCREMENT(mpStat.pagealloc); mp = alloc_metapage(GFP_NOFS); mp->page = page; + mp->sb = inode->i_sb; mp->flag = 0; mp->xflag = COMMIT_PAGE; mp->count = 1; @@ -711,7 +712,8 @@ void force_metapage(struct metapage *mp) get_page(page); lock_page(page); set_page_dirty(page); - write_one_page(page, 1); + if (write_one_page(page)) + jfs_error(mp->sb, "write_one_page() failed\n"); clear_bit(META_forcewrite, &mp->flag); put_page(page); } @@ -756,7 +758,8 @@ void release_metapage(struct metapage * mp) set_page_dirty(page); if (test_bit(META_sync, &mp->flag)) { clear_bit(META_sync, &mp->flag); - write_one_page(page, 1); + if (write_one_page(page)) + jfs_error(mp->sb, "write_one_page() failed\n"); lock_page(page); /* write_one_page unlocks the page */ } } else if (mp->lsn) /* discard_metapage doesn't remove it */ diff --git a/fs/jfs/jfs_metapage.h b/fs/jfs/jfs_metapage.h index a869fb4a20d6..8b0ee514eb84 100644 --- a/fs/jfs/jfs_metapage.h +++ b/fs/jfs/jfs_metapage.h @@ -38,6 +38,7 @@ struct metapage { /* implementation */ struct page *page; + struct super_block *sb; unsigned int logical_size; /* Journal management */ diff --git a/fs/libfs.c b/fs/libfs.c index a04395334bb1..3aabe553fc45 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -974,7 +974,7 @@ int __generic_file_fsync(struct file *file, loff_t start, loff_t end, int err; int ret; - err = filemap_write_and_wait_range(inode->i_mapping, start, end); + err = file_write_and_wait_range(file, start, end); if (err) return err; @@ -991,6 +991,10 @@ int __generic_file_fsync(struct file *file, loff_t start, loff_t end, out: inode_unlock(inode); + /* check and advance again to catch errors after syncing out buffers */ + err = file_check_and_advance_wb_err(file); + if (ret == 0) + ret = err; return ret; } EXPORT_SYMBOL(__generic_file_fsync); diff --git a/fs/locks.c b/fs/locks.c index af2031a1fcff..afefeb4ad6de 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1858,8 +1858,8 @@ EXPORT_SYMBOL(generic_setlease); * * Call this to establish a lease on the file. The "lease" argument is not * used for F_UNLCK requests and may be NULL. For commands that set or alter - * an existing lease, the (*lease)->fl_lmops->lm_break operation must be set; - * if not, this function will return -ENOLCK (and generate a scary-looking + * an existing lease, the ``(*lease)->fl_lmops->lm_break`` operation must be + * set; if not, this function will return -ENOLCK (and generate a scary-looking * stack trace). * * The "priv" pointer is passed directly to the lm_setup function as-is. It @@ -1972,15 +1972,13 @@ EXPORT_SYMBOL(locks_lock_inode_wait); * @cmd: the type of lock to apply. * * Apply a %FL_FLOCK style lock to an open file descriptor. - * The @cmd can be one of + * The @cmd can be one of: * - * %LOCK_SH -- a shared lock. - * - * %LOCK_EX -- an exclusive lock. - * - * %LOCK_UN -- remove an existing lock. - * - * %LOCK_MAND -- a `mandatory' flock. This exists to emulate Windows Share Modes. + * - %LOCK_SH -- a shared lock. + * - %LOCK_EX -- an exclusive lock. + * - %LOCK_UN -- remove an existing lock. + * - %LOCK_MAND -- a 'mandatory' flock. + * This exists to emulate Windows Share Modes. * * %LOCK_MAND can be combined with %LOCK_READ or %LOCK_WRITE to allow other * processes read and write access respectively. @@ -2086,26 +2084,22 @@ static void posix_lock_to_flock64(struct flock64 *flock, struct file_lock *fl) /* Report the first existing lock that would conflict with l. * This implements the F_GETLK command of fcntl(). */ -int fcntl_getlk(struct file *filp, unsigned int cmd, struct flock __user *l) +int fcntl_getlk(struct file *filp, unsigned int cmd, struct flock *flock) { struct file_lock file_lock; - struct flock flock; int error; - error = -EFAULT; - if (copy_from_user(&flock, l, sizeof(flock))) - goto out; error = -EINVAL; - if ((flock.l_type != F_RDLCK) && (flock.l_type != F_WRLCK)) + if (flock->l_type != F_RDLCK && flock->l_type != F_WRLCK) goto out; - error = flock_to_posix_lock(filp, &file_lock, &flock); + error = flock_to_posix_lock(filp, &file_lock, flock); if (error) goto out; if (cmd == F_OFD_GETLK) { error = -EINVAL; - if (flock.l_pid != 0) + if (flock->l_pid != 0) goto out; cmd = F_GETLK; @@ -2117,15 +2111,12 @@ int fcntl_getlk(struct file *filp, unsigned int cmd, struct flock __user *l) if (error) goto out; - flock.l_type = file_lock.fl_type; + flock->l_type = file_lock.fl_type; if (file_lock.fl_type != F_UNLCK) { - error = posix_lock_to_flock(&flock, &file_lock); + error = posix_lock_to_flock(flock, &file_lock); if (error) goto rel_priv; } - error = -EFAULT; - if (!copy_to_user(l, &flock, sizeof(flock))) - error = 0; rel_priv: locks_release_private(&file_lock); out: @@ -2218,26 +2209,16 @@ check_fmode_for_setlk(struct file_lock *fl) * This implements both the F_SETLK and F_SETLKW commands of fcntl(). */ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd, - struct flock __user *l) + struct flock *flock) { struct file_lock *file_lock = locks_alloc_lock(); - struct flock flock; - struct inode *inode; + struct inode *inode = locks_inode(filp); struct file *f; int error; if (file_lock == NULL) return -ENOLCK; - inode = locks_inode(filp); - - /* - * This might block, so we do it before checking the inode. - */ - error = -EFAULT; - if (copy_from_user(&flock, l, sizeof(flock))) - goto out; - /* Don't allow mandatory locks on files that may be memory mapped * and shared. */ @@ -2246,7 +2227,7 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd, goto out; } - error = flock_to_posix_lock(filp, file_lock, &flock); + error = flock_to_posix_lock(filp, file_lock, flock); if (error) goto out; @@ -2261,7 +2242,7 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd, switch (cmd) { case F_OFD_SETLK: error = -EINVAL; - if (flock.l_pid != 0) + if (flock->l_pid != 0) goto out; cmd = F_SETLK; @@ -2270,7 +2251,7 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd, break; case F_OFD_SETLKW: error = -EINVAL; - if (flock.l_pid != 0) + if (flock->l_pid != 0) goto out; cmd = F_SETLKW; @@ -2315,26 +2296,22 @@ out: /* Report the first existing lock that would conflict with l. * This implements the F_GETLK command of fcntl(). */ -int fcntl_getlk64(struct file *filp, unsigned int cmd, struct flock64 __user *l) +int fcntl_getlk64(struct file *filp, unsigned int cmd, struct flock64 *flock) { struct file_lock file_lock; - struct flock64 flock; int error; - error = -EFAULT; - if (copy_from_user(&flock, l, sizeof(flock))) - goto out; error = -EINVAL; - if ((flock.l_type != F_RDLCK) && (flock.l_type != F_WRLCK)) + if (flock->l_type != F_RDLCK && flock->l_type != F_WRLCK) goto out; - error = flock64_to_posix_lock(filp, &file_lock, &flock); + error = flock64_to_posix_lock(filp, &file_lock, flock); if (error) goto out; if (cmd == F_OFD_GETLK) { error = -EINVAL; - if (flock.l_pid != 0) + if (flock->l_pid != 0) goto out; cmd = F_GETLK64; @@ -2346,13 +2323,9 @@ int fcntl_getlk64(struct file *filp, unsigned int cmd, struct flock64 __user *l) if (error) goto out; - flock.l_type = file_lock.fl_type; + flock->l_type = file_lock.fl_type; if (file_lock.fl_type != F_UNLCK) - posix_lock_to_flock64(&flock, &file_lock); - - error = -EFAULT; - if (!copy_to_user(l, &flock, sizeof(flock))) - error = 0; + posix_lock_to_flock64(flock, &file_lock); locks_release_private(&file_lock); out: @@ -2363,26 +2336,16 @@ out: * This implements both the F_SETLK and F_SETLKW commands of fcntl(). */ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd, - struct flock64 __user *l) + struct flock64 *flock) { struct file_lock *file_lock = locks_alloc_lock(); - struct flock64 flock; - struct inode *inode; + struct inode *inode = locks_inode(filp); struct file *f; int error; if (file_lock == NULL) return -ENOLCK; - /* - * This might block, so we do it before checking the inode. - */ - error = -EFAULT; - if (copy_from_user(&flock, l, sizeof(flock))) - goto out; - - inode = locks_inode(filp); - /* Don't allow mandatory locks on files that may be memory mapped * and shared. */ @@ -2391,7 +2354,7 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd, goto out; } - error = flock64_to_posix_lock(filp, file_lock, &flock); + error = flock64_to_posix_lock(filp, file_lock, flock); if (error) goto out; @@ -2406,7 +2369,7 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd, switch (cmd) { case F_OFD_SETLK: error = -EINVAL; - if (flock.l_pid != 0) + if (flock->l_pid != 0) goto out; cmd = F_SETLK64; @@ -2415,7 +2378,7 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd, break; case F_OFD_SETLKW: error = -EINVAL; - if (flock.l_pid != 0) + if (flock->l_pid != 0) goto out; cmd = F_SETLKW64; diff --git a/fs/mbcache.c b/fs/mbcache.c index b19be429d655..d818fd236787 100644 --- a/fs/mbcache.c +++ b/fs/mbcache.c @@ -10,13 +10,14 @@ /* * Mbcache is a simple key-value store. Keys need not be unique, however * key-value pairs are expected to be unique (we use this fact in - * mb_cache_entry_delete_block()). + * mb_cache_entry_delete()). * * Ext2 and ext4 use this cache for deduplication of extended attribute blocks. - * They use hash of a block contents as a key and block number as a value. - * That's why keys need not be unique (different xattr blocks may end up having - * the same hash). However block number always uniquely identifies a cache - * entry. + * Ext4 also uses it for deduplication of xattr values stored in inodes. + * They use hash of data as a key and provide a value that may represent a + * block or inode number. That's why keys need not be unique (hash of different + * data may be the same). However user provided value always uniquely + * identifies a cache entry. * * We provide functions for creation and removal of entries, search by key, * and a special "delete entry with given key-value pair" operation. Fixed @@ -62,15 +63,15 @@ static inline struct hlist_bl_head *mb_cache_entry_head(struct mb_cache *cache, * @cache - cache where the entry should be created * @mask - gfp mask with which the entry should be allocated * @key - key of the entry - * @block - block that contains data - * @reusable - is the block reusable by other inodes? + * @value - value of the entry + * @reusable - is the entry reusable by others? * - * Creates entry in @cache with key @key and records that data is stored in - * block @block. The function returns -EBUSY if entry with the same key - * and for the same block already exists in cache. Otherwise 0 is returned. + * Creates entry in @cache with key @key and value @value. The function returns + * -EBUSY if entry with the same key and value already exists in cache. + * Otherwise 0 is returned. */ int mb_cache_entry_create(struct mb_cache *cache, gfp_t mask, u32 key, - sector_t block, bool reusable) + u64 value, bool reusable) { struct mb_cache_entry *entry, *dup; struct hlist_bl_node *dup_node; @@ -91,12 +92,12 @@ int mb_cache_entry_create(struct mb_cache *cache, gfp_t mask, u32 key, /* One ref for hash, one ref returned */ atomic_set(&entry->e_refcnt, 1); entry->e_key = key; - entry->e_block = block; + entry->e_value = value; entry->e_reusable = reusable; head = mb_cache_entry_head(cache, key); hlist_bl_lock(head); hlist_bl_for_each_entry(dup, dup_node, head, e_hash_list) { - if (dup->e_key == key && dup->e_block == block) { + if (dup->e_key == key && dup->e_value == value) { hlist_bl_unlock(head); kmem_cache_free(mb_entry_cache, entry); return -EBUSY; @@ -187,13 +188,13 @@ struct mb_cache_entry *mb_cache_entry_find_next(struct mb_cache *cache, EXPORT_SYMBOL(mb_cache_entry_find_next); /* - * mb_cache_entry_get - get a cache entry by block number (and key) + * mb_cache_entry_get - get a cache entry by value (and key) * @cache - cache we work with - * @key - key of block number @block - * @block - block number + * @key - key + * @value - value */ struct mb_cache_entry *mb_cache_entry_get(struct mb_cache *cache, u32 key, - sector_t block) + u64 value) { struct hlist_bl_node *node; struct hlist_bl_head *head; @@ -202,7 +203,7 @@ struct mb_cache_entry *mb_cache_entry_get(struct mb_cache *cache, u32 key, head = mb_cache_entry_head(cache, key); hlist_bl_lock(head); hlist_bl_for_each_entry(entry, node, head, e_hash_list) { - if (entry->e_key == key && entry->e_block == block) { + if (entry->e_key == key && entry->e_value == value) { atomic_inc(&entry->e_refcnt); goto out; } @@ -214,15 +215,14 @@ out: } EXPORT_SYMBOL(mb_cache_entry_get); -/* mb_cache_entry_delete_block - remove information about block from cache +/* mb_cache_entry_delete - remove a cache entry * @cache - cache we work with - * @key - key of block @block - * @block - block number + * @key - key + * @value - value * - * Remove entry from cache @cache with key @key with data stored in @block. + * Remove entry from cache @cache with key @key and value @value. */ -void mb_cache_entry_delete_block(struct mb_cache *cache, u32 key, - sector_t block) +void mb_cache_entry_delete(struct mb_cache *cache, u32 key, u64 value) { struct hlist_bl_node *node; struct hlist_bl_head *head; @@ -231,7 +231,7 @@ void mb_cache_entry_delete_block(struct mb_cache *cache, u32 key, head = mb_cache_entry_head(cache, key); hlist_bl_lock(head); hlist_bl_for_each_entry(entry, node, head, e_hash_list) { - if (entry->e_key == key && entry->e_block == block) { + if (entry->e_key == key && entry->e_value == value) { /* We keep hash list reference to keep entry alive */ hlist_bl_del_init(&entry->e_hash_list); hlist_bl_unlock(head); @@ -248,7 +248,7 @@ void mb_cache_entry_delete_block(struct mb_cache *cache, u32 key, } hlist_bl_unlock(head); } -EXPORT_SYMBOL(mb_cache_entry_delete_block); +EXPORT_SYMBOL(mb_cache_entry_delete); /* mb_cache_entry_touch - cache entry got used * @cache - cache the entry belongs to diff --git a/fs/minix/dir.c b/fs/minix/dir.c index 7edc9b395700..baa9721f1299 100644 --- a/fs/minix/dir.c +++ b/fs/minix/dir.c @@ -57,7 +57,7 @@ static int dir_commit_chunk(struct page *page, loff_t pos, unsigned len) mark_inode_dirty(dir); } if (IS_DIRSYNC(dir)) - err = write_one_page(page, 1); + err = write_one_page(page); else unlock_page(page); return err; diff --git a/fs/minix/itree_common.c b/fs/minix/itree_common.c index 4c57c9af6946..2d1ca08870f7 100644 --- a/fs/minix/itree_common.c +++ b/fs/minix/itree_common.c @@ -142,7 +142,7 @@ changed: return -EAGAIN; } -static inline int get_block(struct inode * inode, sector_t block, +static int get_block(struct inode * inode, sector_t block, struct buffer_head *bh, int create) { int err = -EIO; diff --git a/fs/mount.h b/fs/mount.h index bf1fda6eed8f..de45d9e76748 100644 --- a/fs/mount.h +++ b/fs/mount.h @@ -58,6 +58,7 @@ struct mount { struct mnt_namespace *mnt_ns; /* containing namespace */ struct mountpoint *mnt_mp; /* where is it mounted */ struct hlist_node mnt_mp_list; /* list mounts with the same mountpoint */ + struct list_head mnt_umounting; /* list entry for umount propagation */ #ifdef CONFIG_FSNOTIFY struct fsnotify_mark_connector __rcu *mnt_fsnotify_marks; __u32 mnt_fsnotify_mask; diff --git a/fs/mpage.c b/fs/mpage.c index d6d1486d6f99..2e4c41ccb5c9 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -345,6 +345,7 @@ confused: * * So an mpage read of the first 16 blocks of an ext2 file will cause I/O to be * submitted in the following order: + * * 12 0 1 2 3 4 5 6 7 8 9 10 11 13 14 15 16 * * because the indirect block has to be read to get the mappings of blocks diff --git a/fs/namei.c b/fs/namei.c index 6571a5f5112e..e0b46eb0e212 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1008,7 +1008,7 @@ static int may_linkat(struct path *link) /* Source inode owner (or CAP_FOWNER) can hardlink all they like, * otherwise, it must be a safe source. */ - if (inode_owner_or_capable(inode) || safe_hardlink_source(inode)) + if (safe_hardlink_source(inode) || inode_owner_or_capable(inode)) return 0; audit_log_link_denied("linkat", link); @@ -4332,6 +4332,7 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname * The worst of all namespace operations - renaming directory. "Perverted" * doesn't even start to describe it. Somebody in UCB had a heck of a trip... * Problems: + * * a) we can get into loop creation. * b) race potential - two innocent renames can create a loop together. * That's where 4.4 screws up. Current fix: serialization on @@ -4362,11 +4363,11 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, { int error; bool is_dir = d_is_dir(old_dentry); - const unsigned char *old_name; struct inode *source = old_dentry->d_inode; struct inode *target = new_dentry->d_inode; bool new_is_dir = false; unsigned max_links = new_dir->i_sb->s_max_links; + struct name_snapshot old_name; if (source == target) return 0; @@ -4413,7 +4414,7 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, if (error) return error; - old_name = fsnotify_oldname_init(old_dentry->d_name.name); + take_dentry_name_snapshot(&old_name, old_dentry); dget(new_dentry); if (!is_dir || (flags & RENAME_EXCHANGE)) lock_two_nondirectories(source, target); @@ -4468,14 +4469,14 @@ out: inode_unlock(target); dput(new_dentry); if (!error) { - fsnotify_move(old_dir, new_dir, old_name, is_dir, + fsnotify_move(old_dir, new_dir, old_name.name, is_dir, !(flags & RENAME_EXCHANGE) ? target : NULL, old_dentry); if (flags & RENAME_EXCHANGE) { fsnotify_move(new_dir, old_dir, old_dentry->d_name.name, new_is_dir, NULL, new_dentry); } } - fsnotify_oldname_free(old_name); + release_dentry_name_snapshot(&old_name); return error; } diff --git a/fs/namespace.c b/fs/namespace.c index 5a4438445bf7..81f934b5d571 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -236,6 +236,7 @@ static struct mount *alloc_vfsmnt(const char *name) INIT_LIST_HEAD(&mnt->mnt_slave_list); INIT_LIST_HEAD(&mnt->mnt_slave); INIT_HLIST_NODE(&mnt->mnt_mp_list); + INIT_LIST_HEAD(&mnt->mnt_umounting); init_fs_pin(&mnt->mnt_umount, drop_mountpoint); } return mnt; @@ -3238,7 +3239,6 @@ static void __init init_mount_tree(void) void __init mnt_init(void) { - unsigned u; int err; mnt_cache = kmem_cache_create("mnt_cache", sizeof(struct mount), @@ -3247,22 +3247,17 @@ void __init mnt_init(void) mount_hashtable = alloc_large_system_hash("Mount-cache", sizeof(struct hlist_head), mhash_entries, 19, - 0, + HASH_ZERO, &m_hash_shift, &m_hash_mask, 0, 0); mountpoint_hashtable = alloc_large_system_hash("Mountpoint-cache", sizeof(struct hlist_head), mphash_entries, 19, - 0, + HASH_ZERO, &mp_hash_shift, &mp_hash_mask, 0, 0); if (!mount_hashtable || !mountpoint_hashtable) panic("Failed to allocate mount hash table\n"); - for (u = 0; u <= m_hash_mask; u++) - INIT_HLIST_HEAD(&mount_hashtable[u]); - for (u = 0; u <= mp_hash_mask; u++) - INIT_HLIST_HEAD(&mountpoint_hashtable[u]); - kernfs_init(); err = sysfs_init(); diff --git a/fs/ncpfs/mmap.c b/fs/ncpfs/mmap.c index 0c3905e0542e..6719c0be674d 100644 --- a/fs/ncpfs/mmap.c +++ b/fs/ncpfs/mmap.c @@ -89,7 +89,7 @@ static int ncp_file_mmap_fault(struct vm_fault *vmf) * -- nyc */ count_vm_event(PGMAJFAULT); - mem_cgroup_count_vm_event(vmf->vma->vm_mm, PGMAJFAULT); + count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT); return VM_FAULT_MAJOR; } diff --git a/fs/nfs/super.c b/fs/nfs/super.c index eceb4eabb064..c5334c0e23a1 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -2545,10 +2545,25 @@ EXPORT_SYMBOL_GPL(nfs_set_sb_security); int nfs_clone_sb_security(struct super_block *s, struct dentry *mntroot, struct nfs_mount_info *mount_info) { + int error; + unsigned long kflags = 0, kflags_out = 0; + /* clone any lsm security options from the parent to the new sb */ if (d_inode(mntroot)->i_op != NFS_SB(s)->nfs_client->rpc_ops->dir_inode_ops) return -ESTALE; - return security_sb_clone_mnt_opts(mount_info->cloned->sb, s); + + if (NFS_SB(s)->caps & NFS_CAP_SECURITY_LABEL) + kflags |= SECURITY_LSM_NATIVE_LABELS; + + error = security_sb_clone_mnt_opts(mount_info->cloned->sb, s, kflags, + &kflags_out); + if (error) + return error; + + if (NFS_SB(s)->caps & NFS_CAP_SECURITY_LABEL && + !(kflags_out & SECURITY_LSM_NATIVE_LABELS)) + NFS_SB(s)->caps &= ~NFS_CAP_SECURITY_LABEL; + return 0; } EXPORT_SYMBOL_GPL(nfs_clone_sb_security); diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 2be32955d7f2..38d0383dc7f9 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -911,24 +911,13 @@ __be32 nfsd_splice_read(struct svc_rqst *rqstp, __be32 nfsd_readv(struct file *file, loff_t offset, struct kvec *vec, int vlen, unsigned long *count) { - mm_segment_t oldfs; + struct iov_iter iter; int host_err; - oldfs = get_fs(); - set_fs(KERNEL_DS); - host_err = vfs_readv(file, (struct iovec __user *)vec, vlen, &offset, 0); - set_fs(oldfs); - return nfsd_finish_read(file, count, host_err); -} + iov_iter_kvec(&iter, READ | ITER_KVEC, vec, vlen, *count); + host_err = vfs_iter_read(file, &iter, &offset, 0); -static __be32 -nfsd_vfs_read(struct svc_rqst *rqstp, struct file *file, - loff_t offset, struct kvec *vec, int vlen, unsigned long *count) -{ - if (file->f_op->splice_read && test_bit(RQ_SPLICE_OK, &rqstp->rq_flags)) - return nfsd_splice_read(rqstp, file, offset, count); - else - return nfsd_readv(file, offset, vec, vlen, count); + return nfsd_finish_read(file, count, host_err); } /* @@ -974,7 +963,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, unsigned long *cnt, int stable) { struct svc_export *exp; - mm_segment_t oldfs; + struct iov_iter iter; __be32 err = 0; int host_err; int use_wgather; @@ -1000,10 +989,8 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, if (stable && !use_wgather) flags |= RWF_SYNC; - /* Write the data. */ - oldfs = get_fs(); set_fs(KERNEL_DS); - host_err = vfs_writev(file, (struct iovec __user *)vec, vlen, &pos, flags); - set_fs(oldfs); + iov_iter_kvec(&iter, WRITE | ITER_KVEC, vec, vlen, *cnt); + host_err = vfs_iter_write(file, &iter, &pos, flags); if (host_err < 0) goto out_nfserr; *cnt = host_err; @@ -1044,7 +1031,12 @@ __be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp, ra = nfsd_init_raparms(file); trace_read_opened(rqstp, fhp, offset, vlen); - err = nfsd_vfs_read(rqstp, file, offset, vec, vlen, count); + + if (file->f_op->splice_read && test_bit(RQ_SPLICE_OK, &rqstp->rq_flags)) + err = nfsd_splice_read(rqstp, file, offset, count); + else + err = nfsd_readv(file, offset, vec, vlen, count); + trace_read_io_done(rqstp, fhp, offset, vlen); if (ra) @@ -1464,41 +1456,34 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, __be32 nfsd_readlink(struct svc_rqst *rqstp, struct svc_fh *fhp, char *buf, int *lenp) { - mm_segment_t oldfs; __be32 err; - int host_err; + const char *link; struct path path; + DEFINE_DELAYED_CALL(done); + int len; err = fh_verify(rqstp, fhp, S_IFLNK, NFSD_MAY_NOP); - if (err) - goto out; + if (unlikely(err)) + return err; path.mnt = fhp->fh_export->ex_path.mnt; path.dentry = fhp->fh_dentry; - err = nfserr_inval; - if (!d_is_symlink(path.dentry)) - goto out; + if (unlikely(!d_is_symlink(path.dentry))) + return nfserr_inval; touch_atime(&path); - /* N.B. Why does this call need a get_fs()?? - * Remove the set_fs and watch the fireworks:-) --okir - */ - oldfs = get_fs(); set_fs(KERNEL_DS); - host_err = vfs_readlink(path.dentry, (char __user *)buf, *lenp); - set_fs(oldfs); - - if (host_err < 0) - goto out_nfserr; - *lenp = host_err; - err = 0; -out: - return err; + link = vfs_get_link(path.dentry, &done); + if (IS_ERR(link)) + return nfserrno(PTR_ERR(link)); -out_nfserr: - err = nfserrno(host_err); - goto out; + len = strlen(link); + if (len < *lenp) + *lenp = len; + memcpy(buf, link, *lenp); + do_delayed_call(&done); + return 0; } /* diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index 01a9f0f007d4..0c4583b61717 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -161,16 +161,20 @@ int __fsnotify_parent(const struct path *path, struct dentry *dentry, __u32 mask if (unlikely(!fsnotify_inode_watches_children(p_inode))) __fsnotify_update_child_dentry_flags(p_inode); else if (p_inode->i_fsnotify_mask & mask) { + struct name_snapshot name; + /* we are notifying a parent so come up with the new mask which * specifies these are events which came from a child. */ mask |= FS_EVENT_ON_CHILD; + take_dentry_name_snapshot(&name, dentry); if (path) ret = fsnotify(p_inode, mask, path, FSNOTIFY_EVENT_PATH, - dentry->d_name.name, 0); + name.name, 0); else ret = fsnotify(p_inode, mask, dentry->d_inode, FSNOTIFY_EVENT_INODE, - dentry->d_name.name, 0); + name.name, 0); + release_dentry_name_snapshot(&name); } dput(parent); diff --git a/fs/ocfs2/cluster/netdebug.c b/fs/ocfs2/cluster/netdebug.c index 564c504d6efd..74a21f6695c8 100644 --- a/fs/ocfs2/cluster/netdebug.c +++ b/fs/ocfs2/cluster/netdebug.c @@ -426,6 +426,7 @@ static int sc_fop_release(struct inode *inode, struct file *file) struct o2net_sock_container *dummy_sc = sd->dbg_sock; o2net_debug_del_sc(dummy_sc); + kfree(dummy_sc); return seq_release_private(inode, file); } diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c index 382401d3e88f..1a1e0078ab38 100644 --- a/fs/ocfs2/inode.c +++ b/fs/ocfs2/inode.c @@ -136,7 +136,7 @@ struct inode *ocfs2_ilookup(struct super_block *sb, u64 blkno) struct inode *ocfs2_iget(struct ocfs2_super *osb, u64 blkno, unsigned flags, int sysfile_type) { - int rc = 0; + int rc = -ESTALE; struct inode *inode = NULL; struct super_block *sb = osb->sb; struct ocfs2_find_inode_args args; diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h index 44d178b8d1aa..5bb4a89f9045 100644 --- a/fs/ocfs2/ocfs2_fs.h +++ b/fs/ocfs2/ocfs2_fs.h @@ -25,6 +25,8 @@ #ifndef _OCFS2_FS_H #define _OCFS2_FS_H +#include <linux/magic.h> + /* Version */ #define OCFS2_MAJOR_REV_LEVEL 0 #define OCFS2_MINOR_REV_LEVEL 90 @@ -56,9 +58,6 @@ #define OCFS2_MIN_BLOCKSIZE 512 #define OCFS2_MAX_BLOCKSIZE OCFS2_MIN_CLUSTERSIZE -/* Filesystem magic number */ -#define OCFS2_SUPER_MAGIC 0x7461636f - /* Object signatures */ #define OCFS2_SUPER_BLOCK_SIGNATURE "OCFSV2" #define OCFS2_INODE_SIGNATURE "INODE01" diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c index 820359096c7a..d6c350ba25b9 100644 --- a/fs/ocfs2/stackglue.c +++ b/fs/ocfs2/stackglue.c @@ -631,7 +631,7 @@ static struct attribute *ocfs2_attrs[] = { NULL, }; -static struct attribute_group ocfs2_attr_group = { +static const struct attribute_group ocfs2_attr_group = { .attrs = ocfs2_attrs, }; diff --git a/fs/open.c b/fs/open.c index 3fe0c4aa7d27..35bb784763a4 100644 --- a/fs/open.c +++ b/fs/open.c @@ -707,6 +707,9 @@ static int do_dentry_open(struct file *f, f->f_inode = inode; f->f_mapping = inode->i_mapping; + /* Ensure that we skip any errors that predate opening of the file */ + f->f_wb_err = filemap_sample_wb_err(f->f_mapping); + if (unlikely(f->f_flags & O_PATH)) { f->f_mode = FMODE_PATH; f->f_op = &empty_fops; diff --git a/fs/pnode.c b/fs/pnode.c index 5bc7896d122a..53d411a371ce 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -24,6 +24,11 @@ static inline struct mount *first_slave(struct mount *p) return list_entry(p->mnt_slave_list.next, struct mount, mnt_slave); } +static inline struct mount *last_slave(struct mount *p) +{ + return list_entry(p->mnt_slave_list.prev, struct mount, mnt_slave); +} + static inline struct mount *next_slave(struct mount *p) { return list_entry(p->mnt_slave.next, struct mount, mnt_slave); @@ -162,6 +167,19 @@ static struct mount *propagation_next(struct mount *m, } } +static struct mount *skip_propagation_subtree(struct mount *m, + struct mount *origin) +{ + /* + * Advance m such that propagation_next will not return + * the slaves of m. + */ + if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list)) + m = last_slave(m); + + return m; +} + static struct mount *next_group(struct mount *m, struct mount *origin) { while (1) { @@ -413,65 +431,104 @@ void propagate_mount_unlock(struct mount *mnt) } } -/* - * Mark all mounts that the MNT_LOCKED logic will allow to be unmounted. - */ -static void mark_umount_candidates(struct mount *mnt) +static void umount_one(struct mount *mnt, struct list_head *to_umount) { - struct mount *parent = mnt->mnt_parent; - struct mount *m; - - BUG_ON(parent == mnt); - - for (m = propagation_next(parent, parent); m; - m = propagation_next(m, parent)) { - struct mount *child = __lookup_mnt(&m->mnt, - mnt->mnt_mountpoint); - if (!child || (child->mnt.mnt_flags & MNT_UMOUNT)) - continue; - if (!IS_MNT_LOCKED(child) || IS_MNT_MARKED(m)) { - SET_MNT_MARK(child); - } - } + CLEAR_MNT_MARK(mnt); + mnt->mnt.mnt_flags |= MNT_UMOUNT; + list_del_init(&mnt->mnt_child); + list_del_init(&mnt->mnt_umounting); + list_move_tail(&mnt->mnt_list, to_umount); } /* * NOTE: unmounting 'mnt' naturally propagates to all other mounts its * parent propagates to. */ -static void __propagate_umount(struct mount *mnt) +static bool __propagate_umount(struct mount *mnt, + struct list_head *to_umount, + struct list_head *to_restore) { - struct mount *parent = mnt->mnt_parent; - struct mount *m; + bool progress = false; + struct mount *child; - BUG_ON(parent == mnt); + /* + * The state of the parent won't change if this mount is + * already unmounted or marked as without children. + */ + if (mnt->mnt.mnt_flags & (MNT_UMOUNT | MNT_MARKED)) + goto out; - for (m = propagation_next(parent, parent); m; - m = propagation_next(m, parent)) { - struct mount *topper; - struct mount *child = __lookup_mnt(&m->mnt, - mnt->mnt_mountpoint); - /* - * umount the child only if the child has no children - * and the child is marked safe to unmount. - */ - if (!child || !IS_MNT_MARKED(child)) + /* Verify topper is the only grandchild that has not been + * speculatively unmounted. + */ + list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { + if (child->mnt_mountpoint == mnt->mnt.mnt_root) continue; - CLEAR_MNT_MARK(child); + if (!list_empty(&child->mnt_umounting) && IS_MNT_MARKED(child)) + continue; + /* Found a mounted child */ + goto children; + } - /* If there is exactly one mount covering all of child - * replace child with that mount. - */ - topper = find_topper(child); - if (topper) - mnt_change_mountpoint(child->mnt_parent, child->mnt_mp, - topper); + /* Mark mounts that can be unmounted if not locked */ + SET_MNT_MARK(mnt); + progress = true; + + /* If a mount is without children and not locked umount it. */ + if (!IS_MNT_LOCKED(mnt)) { + umount_one(mnt, to_umount); + } else { +children: + list_move_tail(&mnt->mnt_umounting, to_restore); + } +out: + return progress; +} + +static void umount_list(struct list_head *to_umount, + struct list_head *to_restore) +{ + struct mount *mnt, *child, *tmp; + list_for_each_entry(mnt, to_umount, mnt_list) { + list_for_each_entry_safe(child, tmp, &mnt->mnt_mounts, mnt_child) { + /* topper? */ + if (child->mnt_mountpoint == mnt->mnt.mnt_root) + list_move_tail(&child->mnt_umounting, to_restore); + else + umount_one(child, to_umount); + } + } +} - if (list_empty(&child->mnt_mounts)) { - list_del_init(&child->mnt_child); - child->mnt.mnt_flags |= MNT_UMOUNT; - list_move_tail(&child->mnt_list, &mnt->mnt_list); +static void restore_mounts(struct list_head *to_restore) +{ + /* Restore mounts to a clean working state */ + while (!list_empty(to_restore)) { + struct mount *mnt, *parent; + struct mountpoint *mp; + + mnt = list_first_entry(to_restore, struct mount, mnt_umounting); + CLEAR_MNT_MARK(mnt); + list_del_init(&mnt->mnt_umounting); + + /* Should this mount be reparented? */ + mp = mnt->mnt_mp; + parent = mnt->mnt_parent; + while (parent->mnt.mnt_flags & MNT_UMOUNT) { + mp = parent->mnt_mp; + parent = parent->mnt_parent; } + if (parent != mnt->mnt_parent) + mnt_change_mountpoint(parent, mp, mnt); + } +} + +static void cleanup_umount_visitations(struct list_head *visited) +{ + while (!list_empty(visited)) { + struct mount *mnt = + list_first_entry(visited, struct mount, mnt_umounting); + list_del_init(&mnt->mnt_umounting); } } @@ -485,11 +542,68 @@ static void __propagate_umount(struct mount *mnt) int propagate_umount(struct list_head *list) { struct mount *mnt; + LIST_HEAD(to_restore); + LIST_HEAD(to_umount); + LIST_HEAD(visited); + + /* Find candidates for unmounting */ + list_for_each_entry_reverse(mnt, list, mnt_list) { + struct mount *parent = mnt->mnt_parent; + struct mount *m; + + /* + * If this mount has already been visited it is known that it's + * entire peer group and all of their slaves in the propagation + * tree for the mountpoint has already been visited and there is + * no need to visit them again. + */ + if (!list_empty(&mnt->mnt_umounting)) + continue; + + list_add_tail(&mnt->mnt_umounting, &visited); + for (m = propagation_next(parent, parent); m; + m = propagation_next(m, parent)) { + struct mount *child = __lookup_mnt(&m->mnt, + mnt->mnt_mountpoint); + if (!child) + continue; + + if (!list_empty(&child->mnt_umounting)) { + /* + * If the child has already been visited it is + * know that it's entire peer group and all of + * their slaves in the propgation tree for the + * mountpoint has already been visited and there + * is no need to visit this subtree again. + */ + m = skip_propagation_subtree(m, parent); + continue; + } else if (child->mnt.mnt_flags & MNT_UMOUNT) { + /* + * We have come accross an partially unmounted + * mount in list that has not been visited yet. + * Remember it has been visited and continue + * about our merry way. + */ + list_add_tail(&child->mnt_umounting, &visited); + continue; + } + + /* Check the child and parents while progress is made */ + while (__propagate_umount(child, + &to_umount, &to_restore)) { + /* Is the parent a umount candidate? */ + child = child->mnt_parent; + if (list_empty(&child->mnt_umounting)) + break; + } + } + } - list_for_each_entry_reverse(mnt, list, mnt_list) - mark_umount_candidates(mnt); + umount_list(&to_umount, &to_restore); + restore_mounts(&to_restore); + cleanup_umount_visitations(&visited); + list_splice_tail(&to_umount, list); - list_for_each_entry(mnt, list, mnt_list) - __propagate_umount(mnt); return 0; } diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index 4ee55274f155..45629f4b5402 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -504,7 +504,7 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) if (&m->list == &kclist_head) { if (clear_user(buffer, tsz)) return -EFAULT; - } else if (is_vmalloc_or_module_addr((void *)start)) { + } else if (m->type == KCORE_VMALLOC) { vread(buf, (char *)start, tsz); /* we have to zero-fill user buffer even if no read */ if (copy_to_user(buffer, buf, tsz)) diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c index 792a4e5f9226..4d02c3b65061 100644 --- a/fs/pstore/inode.c +++ b/fs/pstore/inode.c @@ -349,48 +349,48 @@ int pstore_mkfile(struct dentry *root, struct pstore_record *record) switch (record->type) { case PSTORE_TYPE_DMESG: - scnprintf(name, sizeof(name), "dmesg-%s-%lld%s", + scnprintf(name, sizeof(name), "dmesg-%s-%llu%s", record->psi->name, record->id, record->compressed ? ".enc.z" : ""); break; case PSTORE_TYPE_CONSOLE: - scnprintf(name, sizeof(name), "console-%s-%lld", + scnprintf(name, sizeof(name), "console-%s-%llu", record->psi->name, record->id); break; case PSTORE_TYPE_FTRACE: - scnprintf(name, sizeof(name), "ftrace-%s-%lld", + scnprintf(name, sizeof(name), "ftrace-%s-%llu", record->psi->name, record->id); break; case PSTORE_TYPE_MCE: - scnprintf(name, sizeof(name), "mce-%s-%lld", + scnprintf(name, sizeof(name), "mce-%s-%llu", record->psi->name, record->id); break; case PSTORE_TYPE_PPC_RTAS: - scnprintf(name, sizeof(name), "rtas-%s-%lld", + scnprintf(name, sizeof(name), "rtas-%s-%llu", record->psi->name, record->id); break; case PSTORE_TYPE_PPC_OF: - scnprintf(name, sizeof(name), "powerpc-ofw-%s-%lld", + scnprintf(name, sizeof(name), "powerpc-ofw-%s-%llu", record->psi->name, record->id); break; case PSTORE_TYPE_PPC_COMMON: - scnprintf(name, sizeof(name), "powerpc-common-%s-%lld", + scnprintf(name, sizeof(name), "powerpc-common-%s-%llu", record->psi->name, record->id); break; case PSTORE_TYPE_PMSG: - scnprintf(name, sizeof(name), "pmsg-%s-%lld", + scnprintf(name, sizeof(name), "pmsg-%s-%llu", record->psi->name, record->id); break; case PSTORE_TYPE_PPC_OPAL: - scnprintf(name, sizeof(name), "powerpc-opal-%s-%lld", + scnprintf(name, sizeof(name), "powerpc-opal-%s-%llu", record->psi->name, record->id); break; case PSTORE_TYPE_UNKNOWN: - scnprintf(name, sizeof(name), "unknown-%s-%lld", + scnprintf(name, sizeof(name), "unknown-%s-%llu", record->psi->name, record->id); break; default: - scnprintf(name, sizeof(name), "type%d-%s-%lld", + scnprintf(name, sizeof(name), "type%d-%s-%llu", record->type, record->psi->name, record->id); break; } diff --git a/fs/pstore/internal.h b/fs/pstore/internal.h index c416e653dc4f..58051265626f 100644 --- a/fs/pstore/internal.h +++ b/fs/pstore/internal.h @@ -30,5 +30,7 @@ extern void pstore_get_backend_records(struct pstore_info *psi, extern int pstore_mkfile(struct dentry *root, struct pstore_record *record); extern bool pstore_is_mounted(void); +extern void pstore_record_init(struct pstore_record *record, + struct pstore_info *psi); #endif diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index d468eec9b8a6..1b6e0ff6bff5 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -474,6 +474,20 @@ static size_t copy_kmsg_to_buffer(int hsize, size_t len) return total_len; } +void pstore_record_init(struct pstore_record *record, + struct pstore_info *psinfo) +{ + memset(record, 0, sizeof(*record)); + + record->psi = psinfo; + + /* Report zeroed timestamp if called before timekeeping has resumed. */ + if (__getnstimeofday(&record->time)) { + record->time.tv_sec = 0; + record->time.tv_nsec = 0; + } +} + /* * callback from kmsg_dump. (s2,l2) has the most recently * written bytes, older bytes are in (s1,l1). Save as much @@ -509,15 +523,14 @@ static void pstore_dump(struct kmsg_dumper *dumper, int header_size; int zipped_len = -1; size_t dump_size; - struct pstore_record record = { - .type = PSTORE_TYPE_DMESG, - .count = oopscount, - .reason = reason, - .part = part, - .compressed = false, - .buf = psinfo->buf, - .psi = psinfo, - }; + struct pstore_record record; + + pstore_record_init(&record, psinfo); + record.type = PSTORE_TYPE_DMESG; + record.count = oopscount; + record.reason = reason; + record.part = part; + record.buf = psinfo->buf; if (big_oops_buf && is_locked) { dst = big_oops_buf; @@ -587,12 +600,12 @@ static void pstore_console_write(struct console *con, const char *s, unsigned c) const char *e = s + c; while (s < e) { - struct pstore_record record = { - .type = PSTORE_TYPE_CONSOLE, - .psi = psinfo, - }; + struct pstore_record record; unsigned long flags; + pstore_record_init(&record, psinfo); + record.type = PSTORE_TYPE_CONSOLE; + if (c > psinfo->bufsize) c = psinfo->bufsize; @@ -640,19 +653,16 @@ static int pstore_write_user_compat(struct pstore_record *record, if (record->buf) return -EINVAL; - record->buf = kmalloc(record->size, GFP_KERNEL); - if (!record->buf) - return -ENOMEM; - - if (unlikely(copy_from_user(record->buf, buf, record->size))) { - ret = -EFAULT; + record->buf = memdup_user(buf, record->size); + if (unlikely(IS_ERR(record->buf))) { + ret = PTR_ERR(record->buf); goto out; } ret = record->psi->write(record); -out: kfree(record->buf); +out: record->buf = NULL; return unlikely(ret < 0) ? ret : record->size; @@ -770,8 +780,11 @@ static void decompress_record(struct pstore_record *record) int unzipped_len; char *decompressed; + if (!record->compressed) + return; + /* Only PSTORE_TYPE_DMESG support compression. */ - if (!record->compressed || record->type != PSTORE_TYPE_DMESG) { + if (record->type != PSTORE_TYPE_DMESG) { pr_warn("ignored compressed record type %d\n", record->type); return; } @@ -819,6 +832,7 @@ void pstore_get_backend_records(struct pstore_info *psi, struct dentry *root, int quiet) { int failed = 0; + unsigned int stop_loop = 65536; if (!psi || !root) return; @@ -832,7 +846,7 @@ void pstore_get_backend_records(struct pstore_info *psi, * may reallocate record.buf. On success, pstore_mkfile() will keep * the record.buf, so free it only on failure. */ - for (;;) { + for (; stop_loop; stop_loop--) { struct pstore_record *record; int rc; @@ -841,13 +855,15 @@ void pstore_get_backend_records(struct pstore_info *psi, pr_err("out of memory creating record\n"); break; } - record->psi = psi; + pstore_record_init(record, psi); record->size = psi->read(record); /* No more records left in backend? */ - if (record->size <= 0) + if (record->size <= 0) { + kfree(record); break; + } decompress_record(record); rc = pstore_mkfile(root, record); @@ -865,8 +881,11 @@ out: mutex_unlock(&psi->read_mutex); if (failed) - pr_warn("failed to load %d record(s) from '%s'\n", + pr_warn("failed to create %d record(s) from '%s'\n", failed, psi->name); + if (!stop_loop) + pr_err("looping? Too many records seen from '%s'\n", + psi->name); } static void pstore_dowork(struct work_struct *work) diff --git a/fs/pstore/pmsg.c b/fs/pstore/pmsg.c index 209755e0d7c8..24db02de1787 100644 --- a/fs/pstore/pmsg.c +++ b/fs/pstore/pmsg.c @@ -22,16 +22,16 @@ static DEFINE_MUTEX(pmsg_lock); static ssize_t write_pmsg(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { - struct pstore_record record = { - .type = PSTORE_TYPE_PMSG, - .size = count, - .psi = psinfo, - }; + struct pstore_record record; int ret; if (!count) return 0; + pstore_record_init(&record, psinfo); + record.type = PSTORE_TYPE_PMSG; + record.size = count; + /* check outside lock, page in any data. write_user also checks */ if (!access_ok(VERIFY_READ, buf, count)) return -EFAULT; diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index 5cb022c8cd33..7125b398d312 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -27,7 +27,6 @@ #include <linux/module.h> #include <linux/version.h> #include <linux/pstore.h> -#include <linux/time.h> #include <linux/io.h> #include <linux/ioport.h> #include <linux/platform_device.h> @@ -356,20 +355,15 @@ out: } static size_t ramoops_write_kmsg_hdr(struct persistent_ram_zone *prz, - bool compressed) + struct pstore_record *record) { char *hdr; - struct timespec timestamp; size_t len; - /* Report zeroed timestamp if called before timekeeping has resumed. */ - if (__getnstimeofday(×tamp)) { - timestamp.tv_sec = 0; - timestamp.tv_nsec = 0; - } hdr = kasprintf(GFP_ATOMIC, RAMOOPS_KERNMSG_HDR "%lu.%lu-%c\n", - (long)timestamp.tv_sec, (long)(timestamp.tv_nsec / 1000), - compressed ? 'C' : 'D'); + record->time.tv_sec, + record->time.tv_nsec / 1000, + record->compressed ? 'C' : 'D'); WARN_ON_ONCE(!hdr); len = hdr ? strlen(hdr) : 0; persistent_ram_write(prz, hdr, len); @@ -440,7 +434,7 @@ static int notrace ramoops_pstore_write(struct pstore_record *record) prz = cxt->dprzs[cxt->dump_write_cnt]; /* Build header and append record contents. */ - hlen = ramoops_write_kmsg_hdr(prz, record->compressed); + hlen = ramoops_write_kmsg_hdr(prz, record); size = record->size; if (size + hlen > prz->buffer_size) size = prz->buffer_size - hlen; diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 48813aeaab80..53a17496c5c5 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -1910,6 +1910,7 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) { qsize_t space, cur_space; qsize_t rsv_space = 0; + qsize_t inode_usage = 1; struct dquot *transfer_from[MAXQUOTAS] = {}; int cnt, ret = 0; char is_valid[MAXQUOTAS] = {}; @@ -1919,6 +1920,13 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) if (IS_NOQUOTA(inode)) return 0; + + if (inode->i_sb->dq_op->get_inode_usage) { + ret = inode->i_sb->dq_op->get_inode_usage(inode, &inode_usage); + if (ret) + return ret; + } + /* Initialize the arrays */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { warn_to[cnt].w_type = QUOTA_NL_NOWARN; @@ -1946,7 +1954,7 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) continue; is_valid[cnt] = 1; transfer_from[cnt] = i_dquot(inode)[cnt]; - ret = check_idq(transfer_to[cnt], 1, &warn_to[cnt]); + ret = check_idq(transfer_to[cnt], inode_usage, &warn_to[cnt]); if (ret) goto over_quota; ret = check_bdq(transfer_to[cnt], space, 0, &warn_to[cnt]); @@ -1963,7 +1971,7 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) /* Due to IO error we might not have transfer_from[] structure */ if (transfer_from[cnt]) { int wtype; - wtype = info_idq_free(transfer_from[cnt], 1); + wtype = info_idq_free(transfer_from[cnt], inode_usage); if (wtype != QUOTA_NL_NOWARN) prepare_warning(&warn_from_inodes[cnt], transfer_from[cnt], wtype); @@ -1971,13 +1979,13 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) if (wtype != QUOTA_NL_NOWARN) prepare_warning(&warn_from_space[cnt], transfer_from[cnt], wtype); - dquot_decr_inodes(transfer_from[cnt], 1); + dquot_decr_inodes(transfer_from[cnt], inode_usage); dquot_decr_space(transfer_from[cnt], cur_space); dquot_free_reserved_space(transfer_from[cnt], rsv_space); } - dquot_incr_inodes(transfer_to[cnt], 1); + dquot_incr_inodes(transfer_to[cnt], inode_usage); dquot_incr_space(transfer_to[cnt], cur_space); dquot_resv_space(transfer_to[cnt], rsv_space); diff --git a/fs/read_write.c b/fs/read_write.c index d591eeed061f..0cc7033aa413 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -356,46 +356,6 @@ out_putf: } #endif -ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos) -{ - struct kiocb kiocb; - ssize_t ret; - - if (!file->f_op->read_iter) - return -EINVAL; - - init_sync_kiocb(&kiocb, file); - kiocb.ki_pos = *ppos; - - iter->type |= READ; - ret = call_read_iter(file, &kiocb, iter); - BUG_ON(ret == -EIOCBQUEUED); - if (ret > 0) - *ppos = kiocb.ki_pos; - return ret; -} -EXPORT_SYMBOL(vfs_iter_read); - -ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos) -{ - struct kiocb kiocb; - ssize_t ret; - - if (!file->f_op->write_iter) - return -EINVAL; - - init_sync_kiocb(&kiocb, file); - kiocb.ki_pos = *ppos; - - iter->type |= WRITE; - ret = call_write_iter(file, &kiocb, iter); - BUG_ON(ret == -EIOCBQUEUED); - if (ret > 0) - *ppos = kiocb.ki_pos; - return ret; -} -EXPORT_SYMBOL(vfs_iter_write); - int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t count) { struct inode *inode; @@ -910,86 +870,114 @@ out: } #endif -static ssize_t __do_readv_writev(int type, struct file *file, - struct iov_iter *iter, loff_t *pos, int flags) +static ssize_t do_iter_read(struct file *file, struct iov_iter *iter, + loff_t *pos, int flags) { size_t tot_len; ssize_t ret = 0; + if (!(file->f_mode & FMODE_READ)) + return -EBADF; + if (!(file->f_mode & FMODE_CAN_READ)) + return -EINVAL; + tot_len = iov_iter_count(iter); if (!tot_len) goto out; - ret = rw_verify_area(type, file, pos, tot_len); + ret = rw_verify_area(READ, file, pos, tot_len); if (ret < 0) - goto out; - - if (type != READ) - file_start_write(file); + return ret; - if ((type == READ && file->f_op->read_iter) || - (type == WRITE && file->f_op->write_iter)) - ret = do_iter_readv_writev(file, iter, pos, type, flags); + if (file->f_op->read_iter) + ret = do_iter_readv_writev(file, iter, pos, READ, flags); else - ret = do_loop_readv_writev(file, iter, pos, type, flags); - - if (type != READ) - file_end_write(file); - + ret = do_loop_readv_writev(file, iter, pos, READ, flags); out: - if ((ret + (type == READ)) > 0) { - if (type == READ) - fsnotify_access(file); - else - fsnotify_modify(file); - } + if (ret >= 0) + fsnotify_access(file); return ret; } -static ssize_t do_readv_writev(int type, struct file *file, - const struct iovec __user *uvector, - unsigned long nr_segs, loff_t *pos, - int flags) +ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, + int flags) { - struct iovec iovstack[UIO_FASTIOV]; - struct iovec *iov = iovstack; - struct iov_iter iter; - ssize_t ret; + if (!file->f_op->read_iter) + return -EINVAL; + return do_iter_read(file, iter, ppos, flags); +} +EXPORT_SYMBOL(vfs_iter_read); + +static ssize_t do_iter_write(struct file *file, struct iov_iter *iter, + loff_t *pos, int flags) +{ + size_t tot_len; + ssize_t ret = 0; + + if (!(file->f_mode & FMODE_WRITE)) + return -EBADF; + if (!(file->f_mode & FMODE_CAN_WRITE)) + return -EINVAL; - ret = import_iovec(type, uvector, nr_segs, - ARRAY_SIZE(iovstack), &iov, &iter); + tot_len = iov_iter_count(iter); + if (!tot_len) + return 0; + ret = rw_verify_area(WRITE, file, pos, tot_len); if (ret < 0) return ret; - ret = __do_readv_writev(type, file, &iter, pos, flags); - kfree(iov); - + if (file->f_op->write_iter) + ret = do_iter_readv_writev(file, iter, pos, WRITE, flags); + else + ret = do_loop_readv_writev(file, iter, pos, WRITE, flags); + if (ret > 0) + fsnotify_modify(file); return ret; } +ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos, + int flags) +{ + if (!file->f_op->write_iter) + return -EINVAL; + return do_iter_write(file, iter, ppos, flags); +} +EXPORT_SYMBOL(vfs_iter_write); + ssize_t vfs_readv(struct file *file, const struct iovec __user *vec, unsigned long vlen, loff_t *pos, int flags) { - if (!(file->f_mode & FMODE_READ)) - return -EBADF; - if (!(file->f_mode & FMODE_CAN_READ)) - return -EINVAL; + struct iovec iovstack[UIO_FASTIOV]; + struct iovec *iov = iovstack; + struct iov_iter iter; + ssize_t ret; - return do_readv_writev(READ, file, vec, vlen, pos, flags); -} + ret = import_iovec(READ, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter); + if (ret >= 0) { + ret = do_iter_read(file, &iter, pos, flags); + kfree(iov); + } + return ret; +} EXPORT_SYMBOL(vfs_readv); ssize_t vfs_writev(struct file *file, const struct iovec __user *vec, unsigned long vlen, loff_t *pos, int flags) { - if (!(file->f_mode & FMODE_WRITE)) - return -EBADF; - if (!(file->f_mode & FMODE_CAN_WRITE)) - return -EINVAL; + struct iovec iovstack[UIO_FASTIOV]; + struct iovec *iov = iovstack; + struct iov_iter iter; + ssize_t ret; - return do_readv_writev(WRITE, file, vec, vlen, pos, flags); + ret = import_iovec(WRITE, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter); + if (ret >= 0) { + file_start_write(file); + ret = do_iter_write(file, &iter, pos, flags); + file_end_write(file); + kfree(iov); + } + return ret; } - EXPORT_SYMBOL(vfs_writev); static ssize_t do_readv(unsigned long fd, const struct iovec __user *vec, @@ -1137,44 +1125,20 @@ SYSCALL_DEFINE6(pwritev2, unsigned long, fd, const struct iovec __user *, vec, } #ifdef CONFIG_COMPAT - -static ssize_t compat_do_readv_writev(int type, struct file *file, - const struct compat_iovec __user *uvector, - unsigned long nr_segs, loff_t *pos, - int flags) +static size_t compat_readv(struct file *file, + const struct compat_iovec __user *vec, + unsigned long vlen, loff_t *pos, int flags) { struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; struct iov_iter iter; ssize_t ret; - ret = compat_import_iovec(type, uvector, nr_segs, - UIO_FASTIOV, &iov, &iter); - if (ret < 0) - return ret; - - ret = __do_readv_writev(type, file, &iter, pos, flags); - kfree(iov); - - return ret; -} - -static size_t compat_readv(struct file *file, - const struct compat_iovec __user *vec, - unsigned long vlen, loff_t *pos, int flags) -{ - ssize_t ret = -EBADF; - - if (!(file->f_mode & FMODE_READ)) - goto out; - - ret = -EINVAL; - if (!(file->f_mode & FMODE_CAN_READ)) - goto out; - - ret = compat_do_readv_writev(READ, file, vec, vlen, pos, flags); - -out: + ret = compat_import_iovec(READ, vec, vlen, UIO_FASTIOV, &iov, &iter); + if (ret >= 0) { + ret = do_iter_read(file, &iter, pos, flags); + kfree(iov); + } if (ret > 0) add_rchar(current, ret); inc_syscr(current); @@ -1270,18 +1234,18 @@ static size_t compat_writev(struct file *file, const struct compat_iovec __user *vec, unsigned long vlen, loff_t *pos, int flags) { - ssize_t ret = -EBADF; - - if (!(file->f_mode & FMODE_WRITE)) - goto out; - - ret = -EINVAL; - if (!(file->f_mode & FMODE_CAN_WRITE)) - goto out; - - ret = compat_do_readv_writev(WRITE, file, vec, vlen, pos, flags); + struct iovec iovstack[UIO_FASTIOV]; + struct iovec *iov = iovstack; + struct iov_iter iter; + ssize_t ret; -out: + ret = compat_import_iovec(WRITE, vec, vlen, UIO_FASTIOV, &iov, &iter); + if (ret >= 0) { + file_start_write(file); + ret = do_iter_write(file, &iter, pos, flags); + file_end_write(file); + kfree(iov); + } if (ret > 0) add_wchar(current, ret); inc_syscw(current); diff --git a/fs/select.c b/fs/select.c index 5b524a977d91..9d5f15ed87fe 100644 --- a/fs/select.c +++ b/fs/select.c @@ -1161,59 +1161,25 @@ static int compat_get_fd_set(unsigned long nr, compat_ulong_t __user *ufdset, unsigned long *fdset) { - nr = DIV_ROUND_UP(nr, __COMPAT_NFDBITS); if (ufdset) { - unsigned long odd; - - if (!access_ok(VERIFY_WRITE, ufdset, nr*sizeof(compat_ulong_t))) - return -EFAULT; - - odd = nr & 1UL; - nr &= ~1UL; - while (nr) { - unsigned long h, l; - if (__get_user(l, ufdset) || __get_user(h, ufdset+1)) - return -EFAULT; - ufdset += 2; - *fdset++ = h << 32 | l; - nr -= 2; - } - if (odd && __get_user(*fdset, ufdset)) - return -EFAULT; + return compat_get_bitmap(fdset, ufdset, nr); } else { /* Tricky, must clear full unsigned long in the - * kernel fdset at the end, this makes sure that + * kernel fdset at the end, ALIGN makes sure that * actually happens. */ - memset(fdset, 0, ((nr + 1) & ~1)*sizeof(compat_ulong_t)); + memset(fdset, 0, ALIGN(nr, BITS_PER_LONG)); + return 0; } - return 0; } static int compat_set_fd_set(unsigned long nr, compat_ulong_t __user *ufdset, unsigned long *fdset) { - unsigned long odd; - nr = DIV_ROUND_UP(nr, __COMPAT_NFDBITS); - if (!ufdset) return 0; - - odd = nr & 1UL; - nr &= ~1UL; - while (nr) { - unsigned long h, l; - l = *fdset++; - h = l >> 32; - if (__put_user(l, ufdset) || __put_user(h, ufdset+1)) - return -EFAULT; - ufdset += 2; - nr -= 2; - } - if (odd && __put_user(*fdset, ufdset)) - return -EFAULT; - return 0; + return compat_put_bitmap(ufdset, fdset, nr); } diff --git a/fs/splice.c b/fs/splice.c index 540c4a44756c..ae41201d0325 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -762,7 +762,7 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out, iov_iter_bvec(&from, ITER_BVEC | WRITE, array, n, sd.total_len - left); - ret = vfs_iter_write(out, &from, &sd.pos); + ret = vfs_iter_write(out, &from, &sd.pos, 0); if (ret <= 0) break; diff --git a/fs/statfs.c b/fs/statfs.c index 4e4623c7a126..fab9b6a3c116 100644 --- a/fs/statfs.c +++ b/fs/statfs.c @@ -38,6 +38,8 @@ static int flags_by_sb(int s_flags) flags |= ST_SYNCHRONOUS; if (s_flags & MS_MANDLOCK) flags |= ST_MANDLOCK; + if (s_flags & MS_RDONLY) + flags |= ST_RDONLY; return flags; } @@ -244,6 +246,7 @@ SYSCALL_DEFINE2(ustat, unsigned, dev, struct ustat __user *, ubuf) #ifdef CONFIG_COMPAT static int put_compat_statfs(struct compat_statfs __user *ubuf, struct kstatfs *kbuf) { + struct compat_statfs buf; if (sizeof ubuf->f_blocks == 4) { if ((kbuf->f_blocks | kbuf->f_bfree | kbuf->f_bavail | kbuf->f_bsize | kbuf->f_frsize) & 0xffffffff00000000ULL) @@ -257,20 +260,20 @@ static int put_compat_statfs(struct compat_statfs __user *ubuf, struct kstatfs * && (kbuf->f_ffree & 0xffffffff00000000ULL)) return -EOVERFLOW; } - if (!access_ok(VERIFY_WRITE, ubuf, sizeof(*ubuf)) || - __put_user(kbuf->f_type, &ubuf->f_type) || - __put_user(kbuf->f_bsize, &ubuf->f_bsize) || - __put_user(kbuf->f_blocks, &ubuf->f_blocks) || - __put_user(kbuf->f_bfree, &ubuf->f_bfree) || - __put_user(kbuf->f_bavail, &ubuf->f_bavail) || - __put_user(kbuf->f_files, &ubuf->f_files) || - __put_user(kbuf->f_ffree, &ubuf->f_ffree) || - __put_user(kbuf->f_namelen, &ubuf->f_namelen) || - __put_user(kbuf->f_fsid.val[0], &ubuf->f_fsid.val[0]) || - __put_user(kbuf->f_fsid.val[1], &ubuf->f_fsid.val[1]) || - __put_user(kbuf->f_frsize, &ubuf->f_frsize) || - __put_user(kbuf->f_flags, &ubuf->f_flags) || - __clear_user(ubuf->f_spare, sizeof(ubuf->f_spare))) + memset(&buf, 0, sizeof(struct compat_statfs)); + buf.f_type = kbuf->f_type; + buf.f_bsize = kbuf->f_bsize; + buf.f_blocks = kbuf->f_blocks; + buf.f_bfree = kbuf->f_bfree; + buf.f_bavail = kbuf->f_bavail; + buf.f_files = kbuf->f_files; + buf.f_ffree = kbuf->f_ffree; + buf.f_namelen = kbuf->f_namelen; + buf.f_fsid.val[0] = kbuf->f_fsid.val[0]; + buf.f_fsid.val[1] = kbuf->f_fsid.val[1]; + buf.f_frsize = kbuf->f_frsize; + buf.f_flags = kbuf->f_flags; + if (copy_to_user(ubuf, &buf, sizeof(struct compat_statfs))) return -EFAULT; return 0; } @@ -299,6 +302,7 @@ COMPAT_SYSCALL_DEFINE2(fstatfs, unsigned int, fd, struct compat_statfs __user *, static int put_compat_statfs64(struct compat_statfs64 __user *ubuf, struct kstatfs *kbuf) { + struct compat_statfs64 buf; if (sizeof(ubuf->f_bsize) == 4) { if ((kbuf->f_type | kbuf->f_bsize | kbuf->f_namelen | kbuf->f_frsize | kbuf->f_flags) & 0xffffffff00000000ULL) @@ -312,20 +316,20 @@ static int put_compat_statfs64(struct compat_statfs64 __user *ubuf, struct kstat && (kbuf->f_ffree & 0xffffffff00000000ULL)) return -EOVERFLOW; } - if (!access_ok(VERIFY_WRITE, ubuf, sizeof(*ubuf)) || - __put_user(kbuf->f_type, &ubuf->f_type) || - __put_user(kbuf->f_bsize, &ubuf->f_bsize) || - __put_user(kbuf->f_blocks, &ubuf->f_blocks) || - __put_user(kbuf->f_bfree, &ubuf->f_bfree) || - __put_user(kbuf->f_bavail, &ubuf->f_bavail) || - __put_user(kbuf->f_files, &ubuf->f_files) || - __put_user(kbuf->f_ffree, &ubuf->f_ffree) || - __put_user(kbuf->f_namelen, &ubuf->f_namelen) || - __put_user(kbuf->f_fsid.val[0], &ubuf->f_fsid.val[0]) || - __put_user(kbuf->f_fsid.val[1], &ubuf->f_fsid.val[1]) || - __put_user(kbuf->f_frsize, &ubuf->f_frsize) || - __put_user(kbuf->f_flags, &ubuf->f_flags) || - __clear_user(ubuf->f_spare, sizeof(ubuf->f_spare))) + memset(&buf, 0, sizeof(struct compat_statfs64)); + buf.f_type = kbuf->f_type; + buf.f_bsize = kbuf->f_bsize; + buf.f_blocks = kbuf->f_blocks; + buf.f_bfree = kbuf->f_bfree; + buf.f_bavail = kbuf->f_bavail; + buf.f_files = kbuf->f_files; + buf.f_ffree = kbuf->f_ffree; + buf.f_namelen = kbuf->f_namelen; + buf.f_fsid.val[0] = kbuf->f_fsid.val[0]; + buf.f_fsid.val[1] = kbuf->f_fsid.val[1]; + buf.f_frsize = kbuf->f_frsize; + buf.f_flags = kbuf->f_flags; + if (copy_to_user(ubuf, &buf, sizeof(struct compat_statfs64))) return -EFAULT; return 0; } diff --git a/fs/sync.c b/fs/sync.c index 11ba023434b1..2a54c1f22035 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -192,7 +192,7 @@ int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync) spin_unlock(&inode->i_lock); mark_inode_dirty_sync(inode); } - return call_fsync(file, start, end, datasync); + return file->f_op->fsync(file, start, end, datasync); } EXPORT_SYMBOL(vfs_fsync_range); diff --git a/fs/sysv/dir.c b/fs/sysv/dir.c index 5bdae85ceef7..f5191cb2c947 100644 --- a/fs/sysv/dir.c +++ b/fs/sysv/dir.c @@ -45,7 +45,7 @@ static int dir_commit_chunk(struct page *page, loff_t pos, unsigned len) mark_inode_dirty(dir); } if (IS_DIRSYNC(dir)) - err = write_one_page(page, 1); + err = write_one_page(page); else unlock_page(page); return err; diff --git a/fs/timerfd.c b/fs/timerfd.c index c543cdb5f8ed..ece0c02d7e63 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -169,7 +169,7 @@ static ktime_t timerfd_get_remaining(struct timerfd_ctx *ctx) } static int timerfd_setup(struct timerfd_ctx *ctx, int flags, - const struct itimerspec *ktmr) + const struct itimerspec64 *ktmr) { enum hrtimer_mode htmode; ktime_t texp; @@ -178,10 +178,10 @@ static int timerfd_setup(struct timerfd_ctx *ctx, int flags, htmode = (flags & TFD_TIMER_ABSTIME) ? HRTIMER_MODE_ABS: HRTIMER_MODE_REL; - texp = timespec_to_ktime(ktmr->it_value); + texp = timespec64_to_ktime(ktmr->it_value); ctx->expired = 0; ctx->ticks = 0; - ctx->tintv = timespec_to_ktime(ktmr->it_interval); + ctx->tintv = timespec64_to_ktime(ktmr->it_interval); if (isalarm(ctx)) { alarm_init(&ctx->t.alarm, @@ -432,16 +432,15 @@ SYSCALL_DEFINE2(timerfd_create, int, clockid, int, flags) } static int do_timerfd_settime(int ufd, int flags, - const struct itimerspec *new, - struct itimerspec *old) + const struct itimerspec64 *new, + struct itimerspec64 *old) { struct fd f; struct timerfd_ctx *ctx; int ret; if ((flags & ~TFD_SETTIME_FLAGS) || - !timespec_valid(&new->it_value) || - !timespec_valid(&new->it_interval)) + !itimerspec64_valid(new)) return -EINVAL; ret = timerfd_fget(ufd, &f); @@ -487,8 +486,8 @@ static int do_timerfd_settime(int ufd, int flags, hrtimer_forward_now(&ctx->t.tmr, ctx->tintv); } - old->it_value = ktime_to_timespec(timerfd_get_remaining(ctx)); - old->it_interval = ktime_to_timespec(ctx->tintv); + old->it_value = ktime_to_timespec64(timerfd_get_remaining(ctx)); + old->it_interval = ktime_to_timespec64(ctx->tintv); /* * Re-program the timer to the new value ... @@ -500,7 +499,7 @@ static int do_timerfd_settime(int ufd, int flags, return ret; } -static int do_timerfd_gettime(int ufd, struct itimerspec *t) +static int do_timerfd_gettime(int ufd, struct itimerspec64 *t) { struct fd f; struct timerfd_ctx *ctx; @@ -525,8 +524,8 @@ static int do_timerfd_gettime(int ufd, struct itimerspec *t) hrtimer_restart(&ctx->t.tmr); } } - t->it_value = ktime_to_timespec(timerfd_get_remaining(ctx)); - t->it_interval = ktime_to_timespec(ctx->tintv); + t->it_value = ktime_to_timespec64(timerfd_get_remaining(ctx)); + t->it_interval = ktime_to_timespec64(ctx->tintv); spin_unlock_irq(&ctx->wqh.lock); fdput(f); return 0; @@ -536,15 +535,15 @@ SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags, const struct itimerspec __user *, utmr, struct itimerspec __user *, otmr) { - struct itimerspec new, old; + struct itimerspec64 new, old; int ret; - if (copy_from_user(&new, utmr, sizeof(new))) + if (get_itimerspec64(&new, utmr)) return -EFAULT; ret = do_timerfd_settime(ufd, flags, &new, &old); if (ret) return ret; - if (otmr && copy_to_user(otmr, &old, sizeof(old))) + if (otmr && put_itimerspec64(&old, otmr)) return -EFAULT; return ret; @@ -552,11 +551,11 @@ SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags, SYSCALL_DEFINE2(timerfd_gettime, int, ufd, struct itimerspec __user *, otmr) { - struct itimerspec kotmr; + struct itimerspec64 kotmr; int ret = do_timerfd_gettime(ufd, &kotmr); if (ret) return ret; - return copy_to_user(otmr, &kotmr, sizeof(kotmr)) ? -EFAULT: 0; + return put_itimerspec64(&kotmr, otmr) ? -EFAULT : 0; } #ifdef CONFIG_COMPAT @@ -564,15 +563,15 @@ COMPAT_SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags, const struct compat_itimerspec __user *, utmr, struct compat_itimerspec __user *, otmr) { - struct itimerspec new, old; + struct itimerspec64 new, old; int ret; - if (get_compat_itimerspec(&new, utmr)) + if (get_compat_itimerspec64(&new, utmr)) return -EFAULT; ret = do_timerfd_settime(ufd, flags, &new, &old); if (ret) return ret; - if (otmr && put_compat_itimerspec(otmr, &old)) + if (otmr && put_compat_itimerspec64(&old, otmr)) return -EFAULT; return ret; } @@ -580,10 +579,10 @@ COMPAT_SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags, COMPAT_SYSCALL_DEFINE2(timerfd_gettime, int, ufd, struct compat_itimerspec __user *, otmr) { - struct itimerspec kotmr; + struct itimerspec64 kotmr; int ret = do_timerfd_gettime(ufd, &kotmr); if (ret) return ret; - return put_compat_itimerspec(otmr, &kotmr) ? -EFAULT: 0; + return put_compat_itimerspec64(&kotmr, otmr) ? -EFAULT : 0; } #endif diff --git a/fs/ufs/dir.c b/fs/ufs/dir.c index de01b8f2aa78..48609f1d9580 100644 --- a/fs/ufs/dir.c +++ b/fs/ufs/dir.c @@ -53,7 +53,7 @@ static int ufs_commit_chunk(struct page *page, loff_t pos, unsigned len) mark_inode_dirty(dir); } if (IS_DIRSYNC(dir)) - err = write_one_page(page, 1); + err = write_one_page(page); else unlock_page(page); return err; diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 6148ccd6cccf..cadcd12a3d35 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -214,6 +214,7 @@ static inline struct uffd_msg userfault_msg(unsigned long address, * hugepmd ranges. */ static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx, + struct vm_area_struct *vma, unsigned long address, unsigned long flags, unsigned long reason) @@ -224,7 +225,7 @@ static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx, VM_BUG_ON(!rwsem_is_locked(&mm->mmap_sem)); - pte = huge_pte_offset(mm, address); + pte = huge_pte_offset(mm, address, vma_mmu_pagesize(vma)); if (!pte) goto out; @@ -243,6 +244,7 @@ out: } #else static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx, + struct vm_area_struct *vma, unsigned long address, unsigned long flags, unsigned long reason) @@ -448,7 +450,8 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason) must_wait = userfaultfd_must_wait(ctx, vmf->address, vmf->flags, reason); else - must_wait = userfaultfd_huge_must_wait(ctx, vmf->address, + must_wait = userfaultfd_huge_must_wait(ctx, vmf->vma, + vmf->address, vmf->flags, reason); up_read(&mm->mmap_sem); @@ -1114,11 +1117,6 @@ static ssize_t userfaultfd_read(struct file *file, char __user *buf, static void __wake_userfault(struct userfaultfd_ctx *ctx, struct userfaultfd_wake_range *range) { - unsigned long start, end; - - start = range->start; - end = range->start + range->len; - spin_lock(&ctx->fault_pending_wqh.lock); /* wake all in the range and autoremove */ if (waitqueue_active(&ctx->fault_pending_wqh)) diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 17f27a2fb5e2..51dfae5576a4 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -140,7 +140,7 @@ xfs_file_fsync( trace_xfs_file_fsync(ip); - error = filemap_write_and_wait_range(inode->i_mapping, start, end); + error = file_write_and_wait_range(file, start, end); if (error) return error; diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index d249546da15e..43d07f9c4e9e 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -1211,7 +1211,7 @@ xfs_mod_icount( struct xfs_mount *mp, int64_t delta) { - __percpu_counter_add(&mp->m_icount, delta, XFS_ICOUNT_BATCH); + percpu_counter_add_batch(&mp->m_icount, delta, XFS_ICOUNT_BATCH); if (__percpu_counter_compare(&mp->m_icount, 0, XFS_ICOUNT_BATCH) < 0) { ASSERT(0); percpu_counter_add(&mp->m_icount, -delta); @@ -1290,7 +1290,7 @@ xfs_mod_fdblocks( else batch = XFS_FDBLOCKS_BATCH; - __percpu_counter_add(&mp->m_fdblocks, delta, batch); + percpu_counter_add_batch(&mp->m_fdblocks, delta, batch); if (__percpu_counter_compare(&mp->m_fdblocks, mp->m_alloc_set_aside, XFS_FDBLOCKS_BATCH) >= 0) { /* we had space! */ |
