diff options
Diffstat (limited to 'fs')
121 files changed, 2138 insertions, 782 deletions
diff --git a/fs/9p/xattr.c b/fs/9p/xattr.c index 50f7f3f6b55e..1974a38bce20 100644 --- a/fs/9p/xattr.c +++ b/fs/9p/xattr.c @@ -35,10 +35,12 @@ ssize_t v9fs_fid_xattr_get(struct p9_fid *fid, const char *name, return retval; } if (attr_size > buffer_size) { - if (!buffer_size) /* request to get the attr_size */ - retval = attr_size; - else + if (buffer_size) retval = -ERANGE; + else if (attr_size > SSIZE_MAX) + retval = -EOVERFLOW; + else /* request to get the attr_size */ + retval = attr_size; } else { iov_iter_truncate(&to, attr_size); retval = p9_client_read(attr_fid, 0, &to, &err); diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 90e40d5ceccd..e54f0884802a 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -1921,8 +1921,7 @@ int btrfs_is_data_extent_shared(struct btrfs_inode *inode, u64 bytenr, level = -1; ULIST_ITER_INIT(&uiter); while (1) { - bool is_shared; - bool cached; + const unsigned long prev_ref_count = ctx->refs.nnodes; walk_ctx.bytenr = bytenr; ret = find_parent_nodes(&walk_ctx, &shared); @@ -1940,21 +1939,36 @@ int btrfs_is_data_extent_shared(struct btrfs_inode *inode, u64 bytenr, ret = 0; /* - * If our data extent was not directly shared (without multiple - * reference items), than it might have a single reference item - * with a count > 1 for the same offset, which means there are 2 - * (or more) file extent items that point to the data extent - - * this happens when a file extent item needs to be split and - * then one item gets moved to another leaf due to a b+tree leaf - * split when inserting some item. In this case the file extent - * items may be located in different leaves and therefore some - * of the leaves may be referenced through shared subtrees while - * others are not. Since our extent buffer cache only works for - * a single path (by far the most common case and simpler to - * deal with), we can not use it if we have multiple leaves - * (which implies multiple paths). + * More than one extent buffer (bytenr) may have been added to + * the ctx->refs ulist, in which case we have to check multiple + * tree paths in case the first one is not shared, so we can not + * use the path cache which is made for a single path. Multiple + * extent buffers at the current level happen when: + * + * 1) level -1, the data extent: If our data extent was not + * directly shared (without multiple reference items), then + * it might have a single reference item with a count > 1 for + * the same offset, which means there are 2 (or more) file + * extent items that point to the data extent - this happens + * when a file extent item needs to be split and then one + * item gets moved to another leaf due to a b+tree leaf split + * when inserting some item. In this case the file extent + * items may be located in different leaves and therefore + * some of the leaves may be referenced through shared + * subtrees while others are not. Since our extent buffer + * cache only works for a single path (by far the most common + * case and simpler to deal with), we can not use it if we + * have multiple leaves (which implies multiple paths). + * + * 2) level >= 0, a tree node/leaf: We can have a mix of direct + * and indirect references on a b+tree node/leaf, so we have + * to check multiple paths, and the extent buffer (the + * current bytenr) may be shared or not. One example is + * during relocation as we may get a shared tree block ref + * (direct ref) and a non-shared tree block ref (indirect + * ref) for the same node/leaf. */ - if (level == -1 && ctx->refs.nnodes > 1) + if ((ctx->refs.nnodes - prev_ref_count) > 1) ctx->use_path_cache = false; if (level >= 0) @@ -1964,12 +1978,17 @@ int btrfs_is_data_extent_shared(struct btrfs_inode *inode, u64 bytenr, if (!node) break; bytenr = node->val; - level++; - cached = lookup_backref_shared_cache(ctx, root, bytenr, level, - &is_shared); - if (cached) { - ret = (is_shared ? 1 : 0); - break; + if (ctx->use_path_cache) { + bool is_shared; + bool cached; + + level++; + cached = lookup_backref_shared_cache(ctx, root, bytenr, + level, &is_shared); + if (cached) { + ret = (is_shared ? 1 : 0); + break; + } } shared.share_count = 0; shared.have_delayed_delete_refs = false; @@ -1977,6 +1996,28 @@ int btrfs_is_data_extent_shared(struct btrfs_inode *inode, u64 bytenr, } /* + * If the path cache is disabled, then it means at some tree level we + * got multiple parents due to a mix of direct and indirect backrefs or + * multiple leaves with file extent items pointing to the same data + * extent. We have to invalidate the cache and cache only the sharedness + * result for the levels where we got only one node/reference. + */ + if (!ctx->use_path_cache) { + int i = 0; + + level--; + if (ret >= 0 && level >= 0) { + bytenr = ctx->path_cache_entries[level].bytenr; + ctx->use_path_cache = true; + store_backref_shared_cache(ctx, root, bytenr, level, ret); + i = level + 1; + } + + for ( ; i < BTRFS_MAX_LEVEL; i++) + ctx->path_cache_entries[i].bytenr = 0; + } + + /* * Cache the sharedness result for the data extent if we know our inode * has more than 1 file extent item that refers to the data extent. */ diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c index d8b90f95b157..726592868e9c 100644 --- a/fs/btrfs/bio.c +++ b/fs/btrfs/bio.c @@ -287,7 +287,7 @@ static void btrfs_log_dev_io_error(struct bio *bio, struct btrfs_device *dev) if (btrfs_op(bio) == BTRFS_MAP_WRITE) btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_WRITE_ERRS); - if (!(bio->bi_opf & REQ_RAHEAD)) + else if (!(bio->bi_opf & REQ_RAHEAD)) btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_READ_ERRS); if (bio->bi_opf & REQ_PREFLUSH) btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_FLUSH_ERRS); diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 5b10401d803b..5fc670c27f86 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -558,14 +558,15 @@ u64 add_new_free_space(struct btrfs_block_group *block_group, u64 start, u64 end static int sample_block_group_extent_item(struct btrfs_caching_control *caching_ctl, struct btrfs_block_group *block_group, int index, int max_index, - struct btrfs_key *key) + struct btrfs_key *found_key) { struct btrfs_fs_info *fs_info = block_group->fs_info; struct btrfs_root *extent_root; - int ret = 0; u64 search_offset; u64 search_end = block_group->start + block_group->length; struct btrfs_path *path; + struct btrfs_key search_key; + int ret = 0; ASSERT(index >= 0); ASSERT(index <= max_index); @@ -585,37 +586,24 @@ static int sample_block_group_extent_item(struct btrfs_caching_control *caching_ path->reada = READA_FORWARD; search_offset = index * div_u64(block_group->length, max_index); - key->objectid = block_group->start + search_offset; - key->type = BTRFS_EXTENT_ITEM_KEY; - key->offset = 0; + search_key.objectid = block_group->start + search_offset; + search_key.type = BTRFS_EXTENT_ITEM_KEY; + search_key.offset = 0; - while (1) { - ret = btrfs_search_forward(extent_root, key, path, 0); - if (ret != 0) - goto out; + btrfs_for_each_slot(extent_root, &search_key, found_key, path, ret) { /* Success; sampled an extent item in the block group */ - if (key->type == BTRFS_EXTENT_ITEM_KEY && - key->objectid >= block_group->start && - key->objectid + key->offset <= search_end) - goto out; + if (found_key->type == BTRFS_EXTENT_ITEM_KEY && + found_key->objectid >= block_group->start && + found_key->objectid + found_key->offset <= search_end) + break; /* We can't possibly find a valid extent item anymore */ - if (key->objectid >= search_end) { + if (found_key->objectid >= search_end) { ret = 1; break; } - if (key->type < BTRFS_EXTENT_ITEM_KEY) - key->type = BTRFS_EXTENT_ITEM_KEY; - else - key->objectid++; - btrfs_release_path(path); - up_read(&fs_info->commit_root_sem); - mutex_unlock(&caching_ctl->mutex); - cond_resched(); - mutex_lock(&caching_ctl->mutex); - down_read(&fs_info->commit_root_sem); } -out: + lockdep_assert_held(&caching_ctl->mutex); lockdep_assert_held_read(&fs_info->commit_root_sem); btrfs_free_path(path); @@ -659,6 +647,7 @@ out: static int load_block_group_size_class(struct btrfs_caching_control *caching_ctl, struct btrfs_block_group *block_group) { + struct btrfs_fs_info *fs_info = block_group->fs_info; struct btrfs_key key; int i; u64 min_size = block_group->length; @@ -668,6 +657,8 @@ static int load_block_group_size_class(struct btrfs_caching_control *caching_ctl if (!btrfs_block_group_should_use_size_class(block_group)) return 0; + lockdep_assert_held(&caching_ctl->mutex); + lockdep_assert_held_read(&fs_info->commit_root_sem); for (i = 0; i < 5; ++i) { ret = sample_block_group_extent_item(caching_ctl, block_group, i, 5, &key); if (ret < 0) @@ -682,7 +673,6 @@ static int load_block_group_size_class(struct btrfs_caching_control *caching_ctl block_group->size_class = size_class; spin_unlock(&block_group->lock); } - out: return ret; } @@ -1185,14 +1175,8 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, < block_group->zone_unusable); WARN_ON(block_group->space_info->disk_total < block_group->length * factor); - WARN_ON(test_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, - &block_group->runtime_flags) && - block_group->space_info->active_total_bytes - < block_group->length); } block_group->space_info->total_bytes -= block_group->length; - if (test_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &block_group->runtime_flags)) - block_group->space_info->active_total_bytes -= block_group->length; block_group->space_info->bytes_readonly -= (block_group->length - block_group->zone_unusable); block_group->space_info->bytes_zone_unusable -= @@ -1836,7 +1820,8 @@ void btrfs_reclaim_bgs_work(struct work_struct *work) btrfs_info(fs_info, "reclaiming chunk %llu with %llu%% used %llu%% unusable", - bg->start, div_u64(bg->used * 100, bg->length), + bg->start, + div64_u64(bg->used * 100, bg->length), div64_u64(zone_unusable * 100, bg->length)); trace_btrfs_reclaim_block_group(bg); ret = btrfs_relocate_chunk(fs_info, bg->start); @@ -2493,18 +2478,29 @@ static int insert_block_group_item(struct btrfs_trans_handle *trans, struct btrfs_block_group_item bgi; struct btrfs_root *root = btrfs_block_group_root(fs_info); struct btrfs_key key; + u64 old_commit_used; + int ret; spin_lock(&block_group->lock); btrfs_set_stack_block_group_used(&bgi, block_group->used); btrfs_set_stack_block_group_chunk_objectid(&bgi, block_group->global_root_id); btrfs_set_stack_block_group_flags(&bgi, block_group->flags); + old_commit_used = block_group->commit_used; + block_group->commit_used = block_group->used; key.objectid = block_group->start; key.type = BTRFS_BLOCK_GROUP_ITEM_KEY; key.offset = block_group->length; spin_unlock(&block_group->lock); - return btrfs_insert_item(trans, root, &key, &bgi, sizeof(bgi)); + ret = btrfs_insert_item(trans, root, &key, &bgi, sizeof(bgi)); + if (ret < 0) { + spin_lock(&block_group->lock); + block_group->commit_used = old_commit_used; + spin_unlock(&block_group->lock); + } + + return ret; } static int insert_dev_extent(struct btrfs_trans_handle *trans, @@ -3474,6 +3470,7 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans, spin_unlock(&info->delalloc_root_lock); while (total) { + struct btrfs_space_info *space_info; bool reclaim = false; cache = btrfs_lookup_block_group(info, bytenr); @@ -3481,6 +3478,7 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans, ret = -ENOENT; break; } + space_info = cache->space_info; factor = btrfs_bg_type_to_factor(cache->flags); /* @@ -3495,7 +3493,7 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans, byte_in_group = bytenr - cache->start; WARN_ON(byte_in_group > cache->length); - spin_lock(&cache->space_info->lock); + spin_lock(&space_info->lock); spin_lock(&cache->lock); if (btrfs_test_opt(info, SPACE_CACHE) && @@ -3508,24 +3506,24 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans, old_val += num_bytes; cache->used = old_val; cache->reserved -= num_bytes; - cache->space_info->bytes_reserved -= num_bytes; - cache->space_info->bytes_used += num_bytes; - cache->space_info->disk_used += num_bytes * factor; + space_info->bytes_reserved -= num_bytes; + space_info->bytes_used += num_bytes; + space_info->disk_used += num_bytes * factor; spin_unlock(&cache->lock); - spin_unlock(&cache->space_info->lock); + spin_unlock(&space_info->lock); } else { old_val -= num_bytes; cache->used = old_val; cache->pinned += num_bytes; - btrfs_space_info_update_bytes_pinned(info, - cache->space_info, num_bytes); - cache->space_info->bytes_used -= num_bytes; - cache->space_info->disk_used -= num_bytes * factor; + btrfs_space_info_update_bytes_pinned(info, space_info, + num_bytes); + space_info->bytes_used -= num_bytes; + space_info->disk_used -= num_bytes * factor; reclaim = should_reclaim_block_group(cache, num_bytes); spin_unlock(&cache->lock); - spin_unlock(&cache->space_info->lock); + spin_unlock(&space_info->lock); set_extent_dirty(&trans->transaction->pinned_extents, bytenr, bytenr + num_bytes - 1, diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 0095c6e4c3d1..6b457b010cbc 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1048,7 +1048,7 @@ again: * so there is only one iref. The case that several irefs are * in the same item doesn't exist. */ - btrfs_del_item(trans, root, path); + ret = btrfs_del_item(trans, root, path); out: btrfs_release_delayed_iref(node); btrfs_release_path(path); diff --git a/fs/btrfs/discard.c b/fs/btrfs/discard.c index 317aeff6c1da..a6d77fe41e1a 100644 --- a/fs/btrfs/discard.c +++ b/fs/btrfs/discard.c @@ -56,11 +56,9 @@ #define BTRFS_DISCARD_DELAY (120ULL * NSEC_PER_SEC) #define BTRFS_DISCARD_UNUSED_DELAY (10ULL * NSEC_PER_SEC) -/* Target completion latency of discarding all discardable extents */ -#define BTRFS_DISCARD_TARGET_MSEC (6 * 60 * 60UL * MSEC_PER_SEC) #define BTRFS_DISCARD_MIN_DELAY_MSEC (1UL) #define BTRFS_DISCARD_MAX_DELAY_MSEC (1000UL) -#define BTRFS_DISCARD_MAX_IOPS (10U) +#define BTRFS_DISCARD_MAX_IOPS (1000U) /* Monotonically decreasing minimum length filters after index 0 */ static int discard_minlen[BTRFS_NR_DISCARD_LISTS] = { @@ -577,6 +575,7 @@ void btrfs_discard_calc_delay(struct btrfs_discard_ctl *discard_ctl) s32 discardable_extents; s64 discardable_bytes; u32 iops_limit; + unsigned long min_delay = BTRFS_DISCARD_MIN_DELAY_MSEC; unsigned long delay; discardable_extents = atomic_read(&discard_ctl->discardable_extents); @@ -607,13 +606,19 @@ void btrfs_discard_calc_delay(struct btrfs_discard_ctl *discard_ctl) } iops_limit = READ_ONCE(discard_ctl->iops_limit); - if (iops_limit) + + if (iops_limit) { delay = MSEC_PER_SEC / iops_limit; - else - delay = BTRFS_DISCARD_TARGET_MSEC / discardable_extents; + } else { + /* + * Unset iops_limit means go as fast as possible, so allow a + * delay of 0. + */ + delay = 0; + min_delay = 0; + } - delay = clamp(delay, BTRFS_DISCARD_MIN_DELAY_MSEC, - BTRFS_DISCARD_MAX_DELAY_MSEC); + delay = clamp(delay, min_delay, BTRFS_DISCARD_MAX_DELAY_MSEC); discard_ctl->delay_ms = delay; spin_unlock(&discard_ctl->lock); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index b53f0e30ce2b..9e1596bb208d 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2250,6 +2250,20 @@ static int btrfs_init_csum_hash(struct btrfs_fs_info *fs_info, u16 csum_type) fs_info->csum_shash = csum_shash; + /* + * Check if the checksum implementation is a fast accelerated one. + * As-is this is a bit of a hack and should be replaced once the csum + * implementations provide that information themselves. + */ + switch (csum_type) { + case BTRFS_CSUM_TYPE_CRC32: + if (!strstr(crypto_shash_driver_name(csum_shash), "generic")) + set_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags); + break; + default: + break; + } + btrfs_info(fs_info, "using %s (%s) checksum algorithm", btrfs_super_csum_name(csum_type), crypto_shash_driver_name(csum_shash)); diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index be94030e1dfb..138afa955370 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -763,7 +763,13 @@ void btrfs_drop_extent_map_range(struct btrfs_inode *inode, u64 start, u64 end, goto next; } + flags = em->flags; clear_bit(EXTENT_FLAG_PINNED, &em->flags); + /* + * In case we split the extent map, we want to preserve the + * EXTENT_FLAG_LOGGING flag on our extent map, but we don't want + * it on the new extent maps. + */ clear_bit(EXTENT_FLAG_LOGGING, &flags); modified = !list_empty(&em->list); @@ -774,7 +780,6 @@ void btrfs_drop_extent_map_range(struct btrfs_inode *inode, u64 start, u64 end, if (em->start >= start && em_end <= end) goto remove_em; - flags = em->flags; gen = em->generation; compressed = test_bit(EXTENT_FLAG_COMPRESSED, &em->flags); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 5cc5a1faaef5..f649647392e0 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -3730,10 +3730,15 @@ static int check_direct_read(struct btrfs_fs_info *fs_info, if (!iter_is_iovec(iter)) return 0; - for (seg = 0; seg < iter->nr_segs; seg++) - for (i = seg + 1; i < iter->nr_segs; i++) - if (iter->iov[seg].iov_base == iter->iov[i].iov_base) + for (seg = 0; seg < iter->nr_segs; seg++) { + for (i = seg + 1; i < iter->nr_segs; i++) { + const struct iovec *iov1 = iter_iov(iter) + seg; + const struct iovec *iov2 = iter_iov(iter) + i; + + if (iov1->iov_base == iov2->iov_base) return -EINVAL; + } + } return 0; } diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 0d250d052487..d84cef89cdff 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -2693,8 +2693,13 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group, bg_reclaim_threshold = READ_ONCE(sinfo->bg_reclaim_threshold); spin_lock(&ctl->tree_lock); + /* Count initial region as zone_unusable until it gets activated. */ if (!used) to_free = size; + else if (initial && + test_bit(BTRFS_FS_ACTIVE_ZONE_TRACKING, &block_group->fs_info->flags) && + (block_group->flags & (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_SYSTEM))) + to_free = 0; else if (initial) to_free = block_group->zone_capacity; else if (offset >= block_group->alloc_offset) @@ -2722,7 +2727,8 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group, reclaimable_unusable = block_group->zone_unusable - (block_group->length - block_group->zone_capacity); /* All the region is now unusable. Mark it as unused and reclaim */ - if (block_group->zone_unusable == block_group->length) { + if (block_group->zone_unusable == block_group->length && + block_group->alloc_offset) { btrfs_mark_bg_unused(block_group); } else if (bg_reclaim_threshold && reclaimable_unusable >= diff --git a/fs/btrfs/fs.h b/fs/btrfs/fs.h index 4c477eae6891..24cd49229408 100644 --- a/fs/btrfs/fs.h +++ b/fs/btrfs/fs.h @@ -120,11 +120,8 @@ enum { /* Indicate that we want to commit the transaction. */ BTRFS_FS_NEED_TRANS_COMMIT, - /* - * Indicate metadata over-commit is disabled. This is set when active - * zone tracking is needed. - */ - BTRFS_FS_NO_OVERCOMMIT, + /* This is set when active zone tracking is needed. */ + BTRFS_FS_ACTIVE_ZONE_TRACKING, /* * Indicate if we have some features changed, this is mostly for diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 6c18dc9a1831..957e4d76a7b6 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -5421,8 +5421,13 @@ static int btrfs_inode_by_name(struct btrfs_inode *dir, struct dentry *dentry, return -ENOMEM; ret = fscrypt_setup_filename(&dir->vfs_inode, &dentry->d_name, 1, &fname); - if (ret) + if (ret < 0) goto out; + /* + * fscrypt_setup_filename() should never return a positive value, but + * gcc on sparc/parisc thinks it can, so assert that doesn't happen. + */ + ASSERT(ret == 0); /* This needs to handle no-key deletions later on */ diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 84626c8ad5bf..ba769a1eb87a 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2859,6 +2859,7 @@ static long btrfs_ioctl_dev_info(struct btrfs_fs_info *fs_info, di_args->bytes_used = btrfs_device_get_bytes_used(dev); di_args->total_bytes = btrfs_device_get_total_bytes(dev); memcpy(di_args->uuid, dev->uuid, sizeof(di_args->uuid)); + memcpy(di_args->fsid, dev->fs_devices->fsid, BTRFS_UUID_SIZE); if (dev->name) strscpy(di_args->path, btrfs_dev_name(dev), sizeof(di_args->path)); else @@ -3731,7 +3732,9 @@ static long btrfs_ioctl_qgroup_assign(struct file *file, void __user *arg) } /* update qgroup status and info */ + mutex_lock(&fs_info->qgroup_ioctl_lock); err = btrfs_run_qgroups(trans); + mutex_unlock(&fs_info->qgroup_ioctl_lock); if (err < 0) btrfs_handle_fs_error(fs_info, err, "failed to update qgroup status and info"); diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 52a7d2fa2284..f41da7ac360d 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -2828,13 +2828,22 @@ cleanup: } /* - * called from commit_transaction. Writes all changed qgroups to disk. + * Writes all changed qgroups to disk. + * Called by the transaction commit path and the qgroup assign ioctl. */ int btrfs_run_qgroups(struct btrfs_trans_handle *trans) { struct btrfs_fs_info *fs_info = trans->fs_info; int ret = 0; + /* + * In case we are called from the qgroup assign ioctl, assert that we + * are holding the qgroup_ioctl_lock, otherwise we can race with a quota + * disable operation (ioctl) and access a freed quota root. + */ + if (trans->transaction->state != TRANS_STATE_COMMIT_DOING) + lockdep_assert_held(&fs_info->qgroup_ioctl_lock); + if (!fs_info->quota_root) return ret; diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index 69c09508afb5..3eecce86f63f 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -308,8 +308,6 @@ void btrfs_add_bg_to_space_info(struct btrfs_fs_info *info, ASSERT(found); spin_lock(&found->lock); found->total_bytes += block_group->length; - if (test_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &block_group->runtime_flags)) - found->active_total_bytes += block_group->length; found->disk_total += block_group->length * factor; found->bytes_used += block_group->used; found->disk_used += block_group->used * factor; @@ -379,22 +377,6 @@ static u64 calc_available_free_space(struct btrfs_fs_info *fs_info, return avail; } -static inline u64 writable_total_bytes(struct btrfs_fs_info *fs_info, - struct btrfs_space_info *space_info) -{ - /* - * On regular filesystem, all total_bytes are always writable. On zoned - * filesystem, there may be a limitation imposed by max_active_zones. - * For metadata allocation, we cannot finish an existing active block - * group to avoid a deadlock. Thus, we need to consider only the active - * groups to be writable for metadata space. - */ - if (!btrfs_is_zoned(fs_info) || (space_info->flags & BTRFS_BLOCK_GROUP_DATA)) - return space_info->total_bytes; - - return space_info->active_total_bytes; -} - int btrfs_can_overcommit(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info, u64 bytes, enum btrfs_reserve_flush_enum flush) @@ -407,13 +389,13 @@ int btrfs_can_overcommit(struct btrfs_fs_info *fs_info, return 0; used = btrfs_space_info_used(space_info, true); - if (test_bit(BTRFS_FS_NO_OVERCOMMIT, &fs_info->flags) && + if (test_bit(BTRFS_FS_ACTIVE_ZONE_TRACKING, &fs_info->flags) && (space_info->flags & BTRFS_BLOCK_GROUP_METADATA)) avail = 0; else avail = calc_available_free_space(fs_info, space_info, flush); - if (used + bytes < writable_total_bytes(fs_info, space_info) + avail) + if (used + bytes < space_info->total_bytes + avail) return 1; return 0; } @@ -449,7 +431,7 @@ again: ticket = list_first_entry(head, struct reserve_ticket, list); /* Check and see if our ticket can be satisfied now. */ - if ((used + ticket->bytes <= writable_total_bytes(fs_info, space_info)) || + if ((used + ticket->bytes <= space_info->total_bytes) || btrfs_can_overcommit(fs_info, space_info, ticket->bytes, flush)) { btrfs_space_info_update_bytes_may_use(fs_info, @@ -829,7 +811,6 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_fs_info *fs_info, { u64 used; u64 avail; - u64 total; u64 to_reclaim = space_info->reclaim_size; lockdep_assert_held(&space_info->lock); @@ -844,9 +825,8 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_fs_info *fs_info, * space. If that's the case add in our overage so we make sure to put * appropriate pressure on the flushing state machine. */ - total = writable_total_bytes(fs_info, space_info); - if (total + avail < used) - to_reclaim += used - (total + avail); + if (space_info->total_bytes + avail < used) + to_reclaim += used - (space_info->total_bytes + avail); return to_reclaim; } @@ -856,11 +836,10 @@ static bool need_preemptive_reclaim(struct btrfs_fs_info *fs_info, { u64 global_rsv_size = fs_info->global_block_rsv.reserved; u64 ordered, delalloc; - u64 total = writable_total_bytes(fs_info, space_info); u64 thresh; u64 used; - thresh = mult_perc(total, 90); + thresh = mult_perc(space_info->total_bytes, 90); lockdep_assert_held(&space_info->lock); @@ -923,8 +902,8 @@ static bool need_preemptive_reclaim(struct btrfs_fs_info *fs_info, BTRFS_RESERVE_FLUSH_ALL); used = space_info->bytes_used + space_info->bytes_reserved + space_info->bytes_readonly + global_rsv_size; - if (used < total) - thresh += total - used; + if (used < space_info->total_bytes) + thresh += space_info->total_bytes - used; thresh >>= space_info->clamp; used = space_info->bytes_pinned; @@ -1651,7 +1630,7 @@ static int __reserve_bytes(struct btrfs_fs_info *fs_info, * can_overcommit() to ensure we can overcommit to continue. */ if (!pending_tickets && - ((used + orig_bytes <= writable_total_bytes(fs_info, space_info)) || + ((used + orig_bytes <= space_info->total_bytes) || btrfs_can_overcommit(fs_info, space_info, orig_bytes, flush))) { btrfs_space_info_update_bytes_may_use(fs_info, space_info, orig_bytes); @@ -1665,8 +1644,7 @@ static int __reserve_bytes(struct btrfs_fs_info *fs_info, */ if (ret && unlikely(flush == BTRFS_RESERVE_FLUSH_EMERGENCY)) { used = btrfs_space_info_used(space_info, false); - if (used + orig_bytes <= - writable_total_bytes(fs_info, space_info)) { + if (used + orig_bytes <= space_info->total_bytes) { btrfs_space_info_update_bytes_may_use(fs_info, space_info, orig_bytes); ret = 0; diff --git a/fs/btrfs/space-info.h b/fs/btrfs/space-info.h index fc99ea2b0c34..2033b71b18ce 100644 --- a/fs/btrfs/space-info.h +++ b/fs/btrfs/space-info.h @@ -96,8 +96,6 @@ struct btrfs_space_info { u64 bytes_may_use; /* number of bytes that may be used for delalloc/allocations */ u64 bytes_readonly; /* total bytes that are read only */ - /* Total bytes in the space, but only accounts active block groups. */ - u64 active_total_bytes; u64 bytes_zone_unusable; /* total bytes that are unusable until resetting the device zone */ diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 581845bc206a..366fb4cde145 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1516,8 +1516,6 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type, shrinker_debugfs_rename(&s->s_shrink, "sb-%s:%s", fs_type->name, s->s_id); btrfs_sb(s)->bdev_holder = fs_type; - if (!strstr(crc32c_impl(), "generic")) - set_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags); error = btrfs_fill_super(s, fs_devices, data); } if (!error) @@ -1631,6 +1629,8 @@ static void btrfs_resize_thread_pool(struct btrfs_fs_info *fs_info, btrfs_workqueue_set_max(fs_info->hipri_workers, new_pool_size); btrfs_workqueue_set_max(fs_info->delalloc_workers, new_pool_size); btrfs_workqueue_set_max(fs_info->caching_workers, new_pool_size); + workqueue_set_max_active(fs_info->endio_workers, new_pool_size); + workqueue_set_max_active(fs_info->endio_meta_workers, new_pool_size); btrfs_workqueue_set_max(fs_info->endio_write_workers, new_pool_size); btrfs_workqueue_set_max(fs_info->endio_freespace_worker, new_pool_size); btrfs_workqueue_set_max(fs_info->delayed_workers, new_pool_size); diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index 8c5efa5813b3..37fc58a7f27e 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -9,6 +9,7 @@ #include <linux/spinlock.h> #include <linux/completion.h> #include <linux/bug.h> +#include <linux/list.h> #include <crypto/hash.h> #include "messages.h" #include "ctree.h" @@ -778,6 +779,45 @@ static ssize_t btrfs_chunk_size_store(struct kobject *kobj, return len; } +static ssize_t btrfs_size_classes_show(struct kobject *kobj, + struct kobj_attribute *a, char *buf) +{ + struct btrfs_space_info *sinfo = to_space_info(kobj); + struct btrfs_block_group *bg; + u32 none = 0; + u32 small = 0; + u32 medium = 0; + u32 large = 0; + + for (int i = 0; i < BTRFS_NR_RAID_TYPES; ++i) { + down_read(&sinfo->groups_sem); + list_for_each_entry(bg, &sinfo->block_groups[i], list) { + if (!btrfs_block_group_should_use_size_class(bg)) + continue; + switch (bg->size_class) { + case BTRFS_BG_SZ_NONE: + none++; + break; + case BTRFS_BG_SZ_SMALL: + small++; + break; + case BTRFS_BG_SZ_MEDIUM: + medium++; + break; + case BTRFS_BG_SZ_LARGE: + large++; + break; + } + } + up_read(&sinfo->groups_sem); + } + return sysfs_emit(buf, "none %u\n" + "small %u\n" + "medium %u\n" + "large %u\n", + none, small, medium, large); +} + #ifdef CONFIG_BTRFS_DEBUG /* * Request chunk allocation with current chunk size. @@ -835,6 +875,7 @@ SPACE_INFO_ATTR(bytes_zone_unusable); SPACE_INFO_ATTR(disk_used); SPACE_INFO_ATTR(disk_total); BTRFS_ATTR_RW(space_info, chunk_size, btrfs_chunk_size_show, btrfs_chunk_size_store); +BTRFS_ATTR(space_info, size_classes, btrfs_size_classes_show); static ssize_t btrfs_sinfo_bg_reclaim_threshold_show(struct kobject *kobj, struct kobj_attribute *a, @@ -887,6 +928,7 @@ static struct attribute *space_info_attrs[] = { BTRFS_ATTR_PTR(space_info, disk_total), BTRFS_ATTR_PTR(space_info, bg_reclaim_threshold), BTRFS_ATTR_PTR(space_info, chunk_size), + BTRFS_ATTR_PTR(space_info, size_classes), #ifdef CONFIG_BTRFS_DEBUG BTRFS_ATTR_PTR(space_info, force_chunk_alloc), #endif diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 18329ebcb1cb..b8d5b1fa9a03 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -2035,7 +2035,20 @@ static void cleanup_transaction(struct btrfs_trans_handle *trans, int err) if (current->journal_info == trans) current->journal_info = NULL; - btrfs_scrub_cancel(fs_info); + + /* + * If relocation is running, we can't cancel scrub because that will + * result in a deadlock. Before relocating a block group, relocation + * pauses scrub, then starts and commits a transaction before unpausing + * scrub. If the transaction commit is being done by the relocation + * task or triggered by another task and the relocation task is waiting + * for the commit, and we end up here due to an error in the commit + * path, then calling btrfs_scrub_cancel() will deadlock, as we are + * asking for scrub to stop while having it asked to be paused higher + * above in relocation code. + */ + if (!test_bit(BTRFS_FS_RELOC_RUNNING, &fs_info->flags)) + btrfs_scrub_cancel(fs_info); kmem_cache_free(btrfs_trans_handle_cachep, trans); } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 7823168c08a6..c6d592870400 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1366,8 +1366,17 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, fmode_t flags, * So, we need to add a special mount option to scan for * later supers, using BTRFS_SUPER_MIRROR_MAX instead */ - flags |= FMODE_EXCL; + /* + * Avoid using flag |= FMODE_EXCL here, as the systemd-udev may + * initiate the device scan which may race with the user's mount + * or mkfs command, resulting in failure. + * Since the device scan is solely for reading purposes, there is + * no need for FMODE_EXCL. Additionally, the devices are read again + * during the mount process. It is ok to get some inconsistent + * values temporarily, as the device paths of the fsid are the only + * required information for assembling the volume. + */ bdev = blkdev_get_by_path(path, flags, holder); if (IS_ERR(bdev)) return ERR_CAST(bdev); @@ -3266,8 +3275,15 @@ int btrfs_relocate_chunk(struct btrfs_fs_info *fs_info, u64 chunk_offset) btrfs_scrub_pause(fs_info); ret = btrfs_relocate_block_group(fs_info, chunk_offset); btrfs_scrub_continue(fs_info); - if (ret) + if (ret) { + /* + * If we had a transaction abort, stop all running scrubs. + * See transaction.c:cleanup_transaction() why we do it here. + */ + if (BTRFS_FS_ERROR(fs_info)) + btrfs_scrub_cancel(fs_info); return ret; + } block_group = btrfs_lookup_block_group(fs_info, chunk_offset); if (!block_group) @@ -6363,7 +6379,8 @@ int __btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, ASSERT(op != BTRFS_MAP_DISCARD); em = btrfs_get_chunk_map(fs_info, logical, *length); - ASSERT(!IS_ERR(em)); + if (IS_ERR(em)) + return PTR_ERR(em); map = em->map_lookup; data_stripes = nr_data_stripes(map); diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index f95b2c94d619..45d04092f2f8 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -524,8 +524,7 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache) } atomic_set(&zone_info->active_zones_left, max_active_zones - nactive); - /* Overcommit does not work well with active zone tacking. */ - set_bit(BTRFS_FS_NO_OVERCOMMIT, &fs_info->flags); + set_bit(BTRFS_FS_ACTIVE_ZONE_TRACKING, &fs_info->flags); } /* Validate superblock log */ @@ -1581,9 +1580,19 @@ void btrfs_calc_zone_unusable(struct btrfs_block_group *cache) return; WARN_ON(cache->bytes_super != 0); - unusable = (cache->alloc_offset - cache->used) + - (cache->length - cache->zone_capacity); - free = cache->zone_capacity - cache->alloc_offset; + + /* Check for block groups never get activated */ + if (test_bit(BTRFS_FS_ACTIVE_ZONE_TRACKING, &cache->fs_info->flags) && + cache->flags & (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_SYSTEM) && + !test_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &cache->runtime_flags) && + cache->alloc_offset == 0) { + unusable = cache->length; + free = 0; + } else { + unusable = (cache->alloc_offset - cache->used) + + (cache->length - cache->zone_capacity); + free = cache->zone_capacity - cache->alloc_offset; + } /* We only need ->free_space in ALLOC_SEQ block groups */ cache->cached = BTRFS_CACHE_FINISHED; @@ -1902,7 +1911,11 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group) /* Successfully activated all the zones */ set_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &block_group->runtime_flags); - space_info->active_total_bytes += block_group->length; + WARN_ON(block_group->alloc_offset != 0); + if (block_group->zone_unusable == block_group->length) { + block_group->zone_unusable = block_group->length - block_group->zone_capacity; + space_info->bytes_zone_unusable -= block_group->zone_capacity; + } spin_unlock(&block_group->lock); btrfs_try_granting_tickets(fs_info, space_info); spin_unlock(&space_info->lock); @@ -2086,11 +2099,21 @@ bool btrfs_can_activate_zone(struct btrfs_fs_devices *fs_devices, u64 flags) if (!device->bdev) continue; - if (!zinfo->max_active_zones || - atomic_read(&zinfo->active_zones_left)) { + if (!zinfo->max_active_zones) { ret = true; break; } + + switch (flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) { + case 0: /* single */ + ret = (atomic_read(&zinfo->active_zones_left) >= 1); + break; + case BTRFS_BLOCK_GROUP_DUP: + ret = (atomic_read(&zinfo->active_zones_left) >= 2); + break; + } + if (ret) + break; } mutex_unlock(&fs_info->chunk_mutex); @@ -2256,7 +2279,7 @@ int btrfs_zone_finish_one_bg(struct btrfs_fs_info *fs_info) u64 avail; spin_lock(&block_group->lock); - if (block_group->reserved || + if (block_group->reserved || block_group->alloc_offset == 0 || (block_group->flags & BTRFS_BLOCK_GROUP_SYSTEM)) { spin_unlock(&block_group->lock); continue; @@ -2293,10 +2316,6 @@ int btrfs_zoned_activate_one_bg(struct btrfs_fs_info *fs_info, if (!btrfs_is_zoned(fs_info) || (space_info->flags & BTRFS_BLOCK_GROUP_DATA)) return 0; - /* No more block groups to activate */ - if (space_info->active_total_bytes == space_info->total_bytes) - return 0; - for (;;) { int ret; bool need_finish = false; diff --git a/fs/cifs/cached_dir.c b/fs/cifs/cached_dir.c index 75d5e06306ea..bfc964b36c72 100644 --- a/fs/cifs/cached_dir.c +++ b/fs/cifs/cached_dir.c @@ -99,6 +99,23 @@ path_to_dentry(struct cifs_sb_info *cifs_sb, const char *path) return dentry; } +static const char *path_no_prefix(struct cifs_sb_info *cifs_sb, + const char *path) +{ + size_t len = 0; + + if (!*path) + return path; + + if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH) && + cifs_sb->prepath) { + len = strlen(cifs_sb->prepath) + 1; + if (unlikely(len > strlen(path))) + return ERR_PTR(-EINVAL); + } + return path + len; +} + /* * Open the and cache a directory handle. * If error then *cfid is not initialized. @@ -125,6 +142,7 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, struct dentry *dentry = NULL; struct cached_fid *cfid; struct cached_fids *cfids; + const char *npath; if (tcon == NULL || tcon->cfids == NULL || tcon->nohandlecache || is_smb1_server(tcon->ses->server)) @@ -161,6 +179,20 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, } /* + * Skip any prefix paths in @path as lookup_positive_unlocked() ends up + * calling ->lookup() which already adds those through + * build_path_from_dentry(). Also, do it earlier as we might reconnect + * below when trying to send compounded request and then potentially + * having a different prefix path (e.g. after DFS failover). + */ + npath = path_no_prefix(cifs_sb, path); + if (IS_ERR(npath)) { + rc = PTR_ERR(npath); + kfree(utf16_path); + return rc; + } + + /* * We do not hold the lock for the open because in case * SMB2_open needs to reconnect. * This is safe because no other thread will be able to get a ref @@ -184,6 +216,7 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, oparms = (struct cifs_open_parms) { .tcon = tcon, + .path = path, .create_options = cifs_create_options(cifs_sb, CREATE_NOT_FILE), .desired_access = FILE_READ_ATTRIBUTES, .disposition = FILE_OPEN, @@ -251,10 +284,10 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, (char *)&cfid->file_all_info)) cfid->file_all_info_is_valid = true; - if (!path[0]) + if (!npath[0]) dentry = dget(cifs_sb->root); else { - dentry = path_to_dentry(cifs_sb, path); + dentry = path_to_dentry(cifs_sb, npath); if (IS_ERR(dentry)) { rc = -ENOENT; goto oshr_free; diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index 1911f7016fa1..e9c8c088d948 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -176,7 +176,7 @@ static int cifs_debug_files_proc_show(struct seq_file *m, void *v) seq_puts(m, "# Version:1\n"); seq_puts(m, "# Format:\n"); - seq_puts(m, "# <tree id> <persistent fid> <flags> <count> <pid> <uid>"); + seq_puts(m, "# <tree id> <ses id> <persistent fid> <flags> <count> <pid> <uid>"); #ifdef CONFIG_CIFS_DEBUG2 seq_printf(m, " <filename> <mid>\n"); #else @@ -189,8 +189,9 @@ static int cifs_debug_files_proc_show(struct seq_file *m, void *v) spin_lock(&tcon->open_file_lock); list_for_each_entry(cfile, &tcon->openFileList, tlist) { seq_printf(m, - "0x%x 0x%llx 0x%x %d %d %d %pd", + "0x%x 0x%llx 0x%llx 0x%x %d %d %d %pd", tcon->tid, + ses->Suid, cfile->fid.persistent_fid, cfile->f_flags, cfile->count, @@ -216,6 +217,7 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v) { struct mid_q_entry *mid_entry; struct TCP_Server_Info *server; + struct TCP_Server_Info *chan_server; struct cifs_ses *ses; struct cifs_tcon *tcon; struct cifs_server_iface *iface; @@ -420,6 +422,11 @@ skip_rdma: from_kuid(&init_user_ns, ses->linux_uid), from_kuid(&init_user_ns, ses->cred_uid)); + if (ses->dfs_root_ses) { + seq_printf(m, "\n\tDFS root session id: 0x%llx", + ses->dfs_root_ses->Suid); + } + spin_lock(&ses->chan_lock); if (CIFS_CHAN_NEEDS_RECONNECT(ses, 0)) seq_puts(m, "\tPrimary channel: DISCONNECTED "); @@ -469,23 +476,35 @@ skip_rdma: seq_puts(m, "\t\t[CONNECTED]\n"); } spin_unlock(&ses->iface_lock); + + seq_puts(m, "\n\n\tMIDs: "); + spin_lock(&ses->chan_lock); + for (j = 0; j < ses->chan_count; j++) { + chan_server = ses->chans[j].server; + if (!chan_server) + continue; + + if (list_empty(&chan_server->pending_mid_q)) + continue; + + seq_printf(m, "\n\tServer ConnectionId: 0x%llx", + chan_server->conn_id); + spin_lock(&chan_server->mid_lock); + list_for_each_entry(mid_entry, &chan_server->pending_mid_q, qhead) { + seq_printf(m, "\n\t\tState: %d com: %d pid: %d cbdata: %p mid %llu", + mid_entry->mid_state, + le16_to_cpu(mid_entry->command), + mid_entry->pid, + mid_entry->callback_data, + mid_entry->mid); + } + spin_unlock(&chan_server->mid_lock); + } + spin_unlock(&ses->chan_lock); + seq_puts(m, "\n--\n"); } if (i == 0) seq_printf(m, "\n\t\t[NONE]"); - - seq_puts(m, "\n\n\tMIDs: "); - spin_lock(&server->mid_lock); - list_for_each_entry(mid_entry, &server->pending_mid_q, qhead) { - seq_printf(m, "\n\tState: %d com: %d pid:" - " %d cbdata: %p mid %llu\n", - mid_entry->mid_state, - le16_to_cpu(mid_entry->command), - mid_entry->pid, - mid_entry->callback_data, - mid_entry->mid); - } - spin_unlock(&server->mid_lock); - seq_printf(m, "\n--\n"); } if (c == 0) seq_printf(m, "\n\t[NONE]"); diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c index 2b1a8d55b4ec..0329a907bdfe 100644 --- a/fs/cifs/cifs_dfs_ref.c +++ b/fs/cifs/cifs_dfs_ref.c @@ -171,14 +171,13 @@ static struct vfsmount *cifs_dfs_do_automount(struct path *path) mnt = ERR_CAST(full_path); goto out; } - - convert_delimiter(full_path, '/'); cifs_dbg(FYI, "%s: full_path: %s\n", __func__, full_path); tmp = *cur_ctx; tmp.source = full_path; tmp.leaf_fullpath = NULL; tmp.UNC = tmp.prepath = NULL; + tmp.dfs_root_ses = NULL; rc = smb3_fs_context_dup(ctx, &tmp); if (rc) { diff --git a/fs/cifs/cifs_fs_sb.h b/fs/cifs/cifs_fs_sb.h index 013a4bd65280..651759192280 100644 --- a/fs/cifs/cifs_fs_sb.h +++ b/fs/cifs/cifs_fs_sb.h @@ -61,8 +61,6 @@ struct cifs_sb_info { /* only used when CIFS_MOUNT_USE_PREFIX_PATH is set */ char *prepath; - /* randomly generated 128-bit number for indexing dfs mount groups in referral cache */ - uuid_t dfs_mount_id; /* * Indicate whether serverino option was turned off later * (cifs_autodisable_serverino) in order to match new mounts. diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index cbcf210d56e4..ac9034fce409 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -731,13 +731,16 @@ static void cifs_umount_begin(struct super_block *sb) spin_lock(&tcon->tc_lock); if ((tcon->tc_count > 1) || (tcon->status == TID_EXITING)) { /* we have other mounts to same share or we have - already tried to force umount this and woken up + already tried to umount this and woken up all waiting network requests, nothing to do */ spin_unlock(&tcon->tc_lock); spin_unlock(&cifs_tcp_ses_lock); return; - } else if (tcon->tc_count == 1) - tcon->status = TID_EXITING; + } + /* + * can not set tcon->status to TID_EXITING yet since we don't know if umount -f will + * fail later (e.g. due to open files). TID_EXITING will be set just before tdis req sent + */ spin_unlock(&tcon->tc_lock); spin_unlock(&cifs_tcp_ses_lock); diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 71fe0a0a7992..415176b2cf32 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -124,7 +124,10 @@ extern const struct dentry_operations cifs_ci_dentry_ops; #ifdef CONFIG_CIFS_DFS_UPCALL extern struct vfsmount *cifs_dfs_d_automount(struct path *path); #else -#define cifs_dfs_d_automount NULL +static inline struct vfsmount *cifs_dfs_d_automount(struct path *path) +{ + return ERR_PTR(-EREMOTE); +} #endif /* Functions related to symlinks */ diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index a99883f16d94..08a73dcb7786 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -1233,6 +1233,7 @@ struct cifs_tcon { /* BB add field for back pointer to sb struct(s)? */ #ifdef CONFIG_CIFS_DFS_UPCALL struct list_head ulist; /* cache update list */ + struct list_head dfs_ses_list; #endif struct delayed_work query_interfaces; /* query interfaces workqueue job */ }; @@ -1749,9 +1750,8 @@ struct cifs_mount_ctx { struct TCP_Server_Info *server; struct cifs_ses *ses; struct cifs_tcon *tcon; - struct cifs_ses *root_ses; - uuid_t mount_id; char *origin_fullpath, *leaf_fullpath; + struct list_head dfs_ses_list; }; static inline void free_dfs_info_param(struct dfs_info3_param *param) diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index a43c78396dd8..9d963caec35c 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -71,7 +71,7 @@ cifs_reconnect_tcon(struct cifs_tcon *tcon, int smb_command) int rc; struct cifs_ses *ses; struct TCP_Server_Info *server; - struct nls_table *nls_codepage; + struct nls_table *nls_codepage = NULL; /* * SMBs NegProt, SessSetup, uLogoff do not have tcon yet so check for @@ -86,13 +86,11 @@ cifs_reconnect_tcon(struct cifs_tcon *tcon, int smb_command) /* * only tree disconnect, open, and write, (and ulogoff which does not - * have tcon) are allowed as we start force umount + * have tcon) are allowed as we start umount */ spin_lock(&tcon->tc_lock); if (tcon->status == TID_EXITING) { - if (smb_command != SMB_COM_WRITE_ANDX && - smb_command != SMB_COM_OPEN_ANDX && - smb_command != SMB_COM_TREE_DISCONNECT) { + if (smb_command != SMB_COM_TREE_DISCONNECT) { spin_unlock(&tcon->tc_lock); cifs_dbg(FYI, "can not send cmd %d while umounting\n", smb_command); @@ -101,6 +99,7 @@ cifs_reconnect_tcon(struct cifs_tcon *tcon, int smb_command) } spin_unlock(&tcon->tc_lock); +again: rc = cifs_wait_for_server_reconnect(server, tcon->retry); if (rc) return rc; @@ -112,8 +111,7 @@ cifs_reconnect_tcon(struct cifs_tcon *tcon, int smb_command) } spin_unlock(&ses->chan_lock); - nls_codepage = load_nls_default(); - + mutex_lock(&ses->session_mutex); /* * Recheck after acquire mutex. If another thread is negotiating * and the server never sends an answer the socket will be closed @@ -122,29 +120,38 @@ cifs_reconnect_tcon(struct cifs_tcon *tcon, int smb_command) spin_lock(&server->srv_lock); if (server->tcpStatus == CifsNeedReconnect) { spin_unlock(&server->srv_lock); + mutex_unlock(&ses->session_mutex); + + if (tcon->retry) + goto again; rc = -EHOSTDOWN; goto out; } spin_unlock(&server->srv_lock); + nls_codepage = load_nls_default(); + /* * need to prevent multiple threads trying to simultaneously * reconnect the same SMB session */ + spin_lock(&ses->ses_lock); spin_lock(&ses->chan_lock); - if (!cifs_chan_needs_reconnect(ses, server)) { + if (!cifs_chan_needs_reconnect(ses, server) && + ses->ses_status == SES_GOOD) { spin_unlock(&ses->chan_lock); + spin_unlock(&ses->ses_lock); /* this means that we only need to tree connect */ if (tcon->need_reconnect) goto skip_sess_setup; - rc = -EHOSTDOWN; + mutex_unlock(&ses->session_mutex); goto out; } spin_unlock(&ses->chan_lock); + spin_unlock(&ses->ses_lock); - mutex_lock(&ses->session_mutex); rc = cifs_negotiate_protocol(0, ses, server); if (!rc) rc = cifs_setup_session(0, ses, server, nls_codepage); @@ -4375,8 +4382,13 @@ CIFSGetDFSRefer(const unsigned int xid, struct cifs_ses *ses, return -ENODEV; getDFSRetry: - rc = smb_init(SMB_COM_TRANSACTION2, 15, ses->tcon_ipc, (void **) &pSMB, - (void **) &pSMBr); + /* + * Use smb_init_no_reconnect() instead of smb_init() as + * CIFSGetDFSRefer() may be called from cifs_reconnect_tcon() and thus + * causing an infinite recursion. + */ + rc = smb_init_no_reconnect(SMB_COM_TRANSACTION2, 15, ses->tcon_ipc, + (void **)&pSMB, (void **)&pSMBr); if (rc) return rc; diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 5233f14f0636..1cbb90587995 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -212,31 +212,42 @@ cifs_mark_tcp_ses_conns_for_reconnect(struct TCP_Server_Info *server, cifs_chan_update_iface(ses, server); spin_lock(&ses->chan_lock); - if (!mark_smb_session && cifs_chan_needs_reconnect(ses, server)) - goto next_session; + if (!mark_smb_session && cifs_chan_needs_reconnect(ses, server)) { + spin_unlock(&ses->chan_lock); + continue; + } if (mark_smb_session) CIFS_SET_ALL_CHANS_NEED_RECONNECT(ses); else cifs_chan_set_need_reconnect(ses, server); + cifs_dbg(FYI, "%s: channel connect bitmap: 0x%lx\n", + __func__, ses->chans_need_reconnect); + /* If all channels need reconnect, then tcon needs reconnect */ - if (!mark_smb_session && !CIFS_ALL_CHANS_NEED_RECONNECT(ses)) - goto next_session; + if (!mark_smb_session && !CIFS_ALL_CHANS_NEED_RECONNECT(ses)) { + spin_unlock(&ses->chan_lock); + continue; + } + spin_unlock(&ses->chan_lock); + spin_lock(&ses->ses_lock); ses->ses_status = SES_NEED_RECON; + spin_unlock(&ses->ses_lock); list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { tcon->need_reconnect = true; + spin_lock(&tcon->tc_lock); tcon->status = TID_NEED_RECON; + spin_unlock(&tcon->tc_lock); } if (ses->tcon_ipc) { ses->tcon_ipc->need_reconnect = true; + spin_lock(&ses->tcon_ipc->tc_lock); ses->tcon_ipc->status = TID_NEED_RECON; + spin_unlock(&ses->tcon_ipc->tc_lock); } - -next_session: - spin_unlock(&ses->chan_lock); } spin_unlock(&cifs_tcp_ses_lock); } @@ -1721,7 +1732,7 @@ out_err: return ERR_PTR(rc); } -/* this function must be called with ses_lock held */ +/* this function must be called with ses_lock and chan_lock held */ static int match_session(struct cifs_ses *ses, struct smb3_fs_context *ctx) { if (ctx->sectype != Unspecified && @@ -1732,12 +1743,8 @@ static int match_session(struct cifs_ses *ses, struct smb3_fs_context *ctx) * If an existing session is limited to less channels than * requested, it should not be reused */ - spin_lock(&ses->chan_lock); - if (ses->chan_max < ctx->max_channels) { - spin_unlock(&ses->chan_lock); + if (ses->chan_max < ctx->max_channels) return 0; - } - spin_unlock(&ses->chan_lock); switch (ses->sectype) { case Kerberos: @@ -1865,10 +1872,13 @@ cifs_find_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) spin_unlock(&ses->ses_lock); continue; } + spin_lock(&ses->chan_lock); if (!match_session(ses, ctx)) { + spin_unlock(&ses->chan_lock); spin_unlock(&ses->ses_lock); continue; } + spin_unlock(&ses->chan_lock); spin_unlock(&ses->ses_lock); ++ses->ses_count; @@ -2229,6 +2239,7 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) * need to lock before changing something in the session. */ spin_lock(&cifs_tcp_ses_lock); + ses->dfs_root_ses = ctx->dfs_root_ses; list_add(&ses->smb_ses_list, &server->smb_ses_list); spin_unlock(&cifs_tcp_ses_lock); @@ -2313,6 +2324,7 @@ cifs_put_tcon(struct cifs_tcon *tcon) WARN_ON(tcon->tc_count < 0); list_del_init(&tcon->tcon_list); + tcon->status = TID_EXITING; spin_unlock(&tcon->tc_lock); spin_unlock(&cifs_tcp_ses_lock); @@ -2692,6 +2704,7 @@ cifs_match_super(struct super_block *sb, void *data) spin_lock(&tcp_srv->srv_lock); spin_lock(&ses->ses_lock); + spin_lock(&ses->chan_lock); spin_lock(&tcon->tc_lock); if (!match_server(tcp_srv, ctx, dfs_super_cmp) || !match_session(ses, ctx) || @@ -2704,6 +2717,7 @@ cifs_match_super(struct super_block *sb, void *data) rc = compare_mount_options(sb, mnt_data); out: spin_unlock(&tcon->tc_lock); + spin_unlock(&ses->chan_lock); spin_unlock(&ses->ses_lock); spin_unlock(&tcp_srv->srv_lock); @@ -3407,7 +3421,8 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx) bool isdfs; int rc; - uuid_gen(&mnt_ctx.mount_id); + INIT_LIST_HEAD(&mnt_ctx.dfs_ses_list); + rc = dfs_mount_share(&mnt_ctx, &isdfs); if (rc) goto error; @@ -3427,7 +3442,6 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx) kfree(cifs_sb->prepath); cifs_sb->prepath = ctx->prepath; ctx->prepath = NULL; - uuid_copy(&cifs_sb->dfs_mount_id, &mnt_ctx.mount_id); out: cifs_try_adding_channels(cifs_sb, mnt_ctx.ses); @@ -3439,7 +3453,7 @@ out: return rc; error: - dfs_cache_put_refsrv_sessions(&mnt_ctx.mount_id); + dfs_put_root_smb_sessions(&mnt_ctx.dfs_ses_list); kfree(mnt_ctx.origin_fullpath); kfree(mnt_ctx.leaf_fullpath); cifs_mount_put_conns(&mnt_ctx); @@ -3637,9 +3651,6 @@ cifs_umount(struct cifs_sb_info *cifs_sb) spin_unlock(&cifs_sb->tlink_tree_lock); kfree(cifs_sb->prepath); -#ifdef CONFIG_CIFS_DFS_UPCALL - dfs_cache_put_refsrv_sessions(&cifs_sb->dfs_mount_id); -#endif call_rcu(&cifs_sb->rcu, delayed_free); } @@ -3654,11 +3665,19 @@ cifs_negotiate_protocol(const unsigned int xid, struct cifs_ses *ses, /* only send once per connect */ spin_lock(&server->srv_lock); - if (!server->ops->need_neg(server) || + if (server->tcpStatus != CifsGood && + server->tcpStatus != CifsNew && server->tcpStatus != CifsNeedNegotiate) { spin_unlock(&server->srv_lock); + return -EHOSTDOWN; + } + + if (!server->ops->need_neg(server) && + server->tcpStatus == CifsGood) { + spin_unlock(&server->srv_lock); return 0; } + server->tcpStatus = CifsInNegotiate; spin_unlock(&server->srv_lock); @@ -3692,23 +3711,28 @@ cifs_setup_session(const unsigned int xid, struct cifs_ses *ses, bool is_binding = false; spin_lock(&ses->ses_lock); + cifs_dbg(FYI, "%s: channel connect bitmap: 0x%lx\n", + __func__, ses->chans_need_reconnect); + if (ses->ses_status != SES_GOOD && ses->ses_status != SES_NEW && ses->ses_status != SES_NEED_RECON) { spin_unlock(&ses->ses_lock); - return 0; + return -EHOSTDOWN; } /* only send once per connect */ spin_lock(&ses->chan_lock); - if (CIFS_ALL_CHANS_GOOD(ses) || - cifs_chan_in_reconnect(ses, server)) { + if (CIFS_ALL_CHANS_GOOD(ses)) { + if (ses->ses_status == SES_NEED_RECON) + ses->ses_status = SES_GOOD; spin_unlock(&ses->chan_lock); spin_unlock(&ses->ses_lock); return 0; } - is_binding = !CIFS_ALL_CHANS_NEED_RECONNECT(ses); + cifs_chan_set_in_reconnect(ses, server); + is_binding = !CIFS_ALL_CHANS_NEED_RECONNECT(ses); spin_unlock(&ses->chan_lock); if (!is_binding) @@ -4038,9 +4062,13 @@ int cifs_tree_connect(const unsigned int xid, struct cifs_tcon *tcon, const stru /* only send once per connect */ spin_lock(&tcon->tc_lock); - if (tcon->ses->ses_status != SES_GOOD || - (tcon->status != TID_NEW && - tcon->status != TID_NEED_TCON)) { + if (tcon->status != TID_NEW && + tcon->status != TID_NEED_TCON) { + spin_unlock(&tcon->tc_lock); + return -EHOSTDOWN; + } + + if (tcon->status == TID_GOOD) { spin_unlock(&tcon->tc_lock); return 0; } diff --git a/fs/cifs/dfs.c b/fs/cifs/dfs.c index b64d20374b9c..3a11716b6e13 100644 --- a/fs/cifs/dfs.c +++ b/fs/cifs/dfs.c @@ -95,25 +95,31 @@ static int get_session(struct cifs_mount_ctx *mnt_ctx, const char *full_path) ctx->leaf_fullpath = (char *)full_path; rc = cifs_mount_get_session(mnt_ctx); ctx->leaf_fullpath = NULL; - if (!rc) { - struct cifs_ses *ses = mnt_ctx->ses; - mutex_lock(&ses->session_mutex); - ses->dfs_root_ses = mnt_ctx->root_ses; - mutex_unlock(&ses->session_mutex); - } return rc; } -static void set_root_ses(struct cifs_mount_ctx *mnt_ctx) +static int get_root_smb_session(struct cifs_mount_ctx *mnt_ctx) { - if (mnt_ctx->ses) { + struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; + struct dfs_root_ses *root_ses; + struct cifs_ses *ses = mnt_ctx->ses; + + if (ses) { + root_ses = kmalloc(sizeof(*root_ses), GFP_KERNEL); + if (!root_ses) + return -ENOMEM; + + INIT_LIST_HEAD(&root_ses->list); + spin_lock(&cifs_tcp_ses_lock); - mnt_ctx->ses->ses_count++; + ses->ses_count++; spin_unlock(&cifs_tcp_ses_lock); - dfs_cache_add_refsrv_session(&mnt_ctx->mount_id, mnt_ctx->ses); + root_ses->ses = ses; + list_add_tail(&root_ses->list, &mnt_ctx->dfs_ses_list); } - mnt_ctx->root_ses = mnt_ctx->ses; + ctx->dfs_root_ses = ses; + return 0; } static int get_dfs_conn(struct cifs_mount_ctx *mnt_ctx, const char *ref_path, const char *full_path, @@ -121,7 +127,8 @@ static int get_dfs_conn(struct cifs_mount_ctx *mnt_ctx, const char *ref_path, co { struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; struct dfs_info3_param ref = {}; - int rc; + bool is_refsrv = false; + int rc, rc2; rc = dfs_cache_get_tgt_referral(ref_path + 1, tit, &ref); if (rc) @@ -136,8 +143,7 @@ static int get_dfs_conn(struct cifs_mount_ctx *mnt_ctx, const char *ref_path, co if (rc) goto out; - if (ref.flags & DFSREF_REFERRAL_SERVER) - set_root_ses(mnt_ctx); + is_refsrv = !!(ref.flags & DFSREF_REFERRAL_SERVER); rc = -EREMOTE; if (ref.flags & DFSREF_STORAGE_SERVER) { @@ -146,13 +152,17 @@ static int get_dfs_conn(struct cifs_mount_ctx *mnt_ctx, const char *ref_path, co goto out; /* some servers may not advertise referral capability under ref.flags */ - if (!(ref.flags & DFSREF_REFERRAL_SERVER) && - is_tcon_dfs(mnt_ctx->tcon)) - set_root_ses(mnt_ctx); + is_refsrv |= is_tcon_dfs(mnt_ctx->tcon); rc = cifs_is_path_remote(mnt_ctx); } + if (rc == -EREMOTE && is_refsrv) { + rc2 = get_root_smb_session(mnt_ctx); + if (rc2) + rc = rc2; + } + out: free_dfs_info_param(&ref); return rc; @@ -165,6 +175,7 @@ static int __dfs_mount_share(struct cifs_mount_ctx *mnt_ctx) char *ref_path = NULL, *full_path = NULL; struct dfs_cache_tgt_iterator *tit; struct TCP_Server_Info *server; + struct cifs_tcon *tcon; char *origin_fullpath = NULL; int num_links = 0; int rc; @@ -234,12 +245,22 @@ static int __dfs_mount_share(struct cifs_mount_ctx *mnt_ctx) if (!rc) { server = mnt_ctx->server; + tcon = mnt_ctx->tcon; mutex_lock(&server->refpath_lock); - server->origin_fullpath = origin_fullpath; - server->current_fullpath = server->leaf_fullpath; + if (!server->origin_fullpath) { + server->origin_fullpath = origin_fullpath; + server->current_fullpath = server->leaf_fullpath; + origin_fullpath = NULL; + } mutex_unlock(&server->refpath_lock); - origin_fullpath = NULL; + + if (list_empty(&tcon->dfs_ses_list)) { + list_replace_init(&mnt_ctx->dfs_ses_list, + &tcon->dfs_ses_list); + } else { + dfs_put_root_smb_sessions(&mnt_ctx->dfs_ses_list); + } } out: @@ -260,7 +281,7 @@ int dfs_mount_share(struct cifs_mount_ctx *mnt_ctx, bool *isdfs) rc = get_session(mnt_ctx, NULL); if (rc) return rc; - mnt_ctx->root_ses = mnt_ctx->ses; + ctx->dfs_root_ses = mnt_ctx->ses; /* * If called with 'nodfs' mount option, then skip DFS resolving. Otherwise unconditionally * try to get an DFS referral (even cached) to determine whether it is an DFS mount. @@ -280,7 +301,9 @@ int dfs_mount_share(struct cifs_mount_ctx *mnt_ctx, bool *isdfs) } *isdfs = true; - set_root_ses(mnt_ctx); + rc = get_root_smb_session(mnt_ctx); + if (rc) + return rc; return __dfs_mount_share(mnt_ctx); } @@ -479,9 +502,13 @@ int cifs_tree_connect(const unsigned int xid, struct cifs_tcon *tcon, const stru /* only send once per connect */ spin_lock(&tcon->tc_lock); - if (tcon->ses->ses_status != SES_GOOD || - (tcon->status != TID_NEW && - tcon->status != TID_NEED_TCON)) { + if (tcon->status != TID_NEW && + tcon->status != TID_NEED_TCON) { + spin_unlock(&tcon->tc_lock); + return -EHOSTDOWN; + } + + if (tcon->status == TID_GOOD) { spin_unlock(&tcon->tc_lock); return 0; } diff --git a/fs/cifs/dfs.h b/fs/cifs/dfs.h index 344bea6d8bab..0b8cbf721fff 100644 --- a/fs/cifs/dfs.h +++ b/fs/cifs/dfs.h @@ -10,6 +10,11 @@ #include "fs_context.h" #include "cifs_unicode.h" +struct dfs_root_ses { + struct list_head list; + struct cifs_ses *ses; +}; + int dfs_parse_target_referral(const char *full_path, const struct dfs_info3_param *ref, struct smb3_fs_context *ctx); int dfs_mount_share(struct cifs_mount_ctx *mnt_ctx, bool *isdfs); @@ -22,25 +27,51 @@ static inline char *dfs_get_path(struct cifs_sb_info *cifs_sb, const char *path) static inline int dfs_get_referral(struct cifs_mount_ctx *mnt_ctx, const char *path, struct dfs_info3_param *ref, struct dfs_cache_tgt_list *tl) { + struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb; - return dfs_cache_find(mnt_ctx->xid, mnt_ctx->root_ses, cifs_sb->local_nls, + return dfs_cache_find(mnt_ctx->xid, ctx->dfs_root_ses, cifs_sb->local_nls, cifs_remap(cifs_sb), path, ref, tl); } +/* Return DFS full path out of a dentry set for automount */ static inline char *dfs_get_automount_devname(struct dentry *dentry, void *page) { struct cifs_sb_info *cifs_sb = CIFS_SB(dentry->d_sb); struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); struct TCP_Server_Info *server = tcon->ses->server; + size_t len; + char *s; if (unlikely(!server->origin_fullpath)) return ERR_PTR(-EREMOTE); - return __build_path_from_dentry_optional_prefix(dentry, page, - server->origin_fullpath, - strlen(server->origin_fullpath), - true); + s = dentry_path_raw(dentry, page, PATH_MAX); + if (IS_ERR(s)) + return s; + /* for root, we want "" */ + if (!s[1]) + s++; + + len = strlen(server->origin_fullpath); + if (s < (char *)page + len) + return ERR_PTR(-ENAMETOOLONG); + + s -= len; + memcpy(s, server->origin_fullpath, len); + convert_delimiter(s, '/'); + return s; +} + +static inline void dfs_put_root_smb_sessions(struct list_head *head) +{ + struct dfs_root_ses *root, *tmp; + + list_for_each_entry_safe(root, tmp, head, list) { + list_del_init(&root->list); + cifs_put_smb_ses(root->ses); + kfree(root); + } } #endif /* _CIFS_DFS_H */ diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c index ac86bd0ebd63..30cbdf8514a5 100644 --- a/fs/cifs/dfs_cache.c +++ b/fs/cifs/dfs_cache.c @@ -49,17 +49,6 @@ struct cache_entry { struct cache_dfs_tgt *tgthint; }; -/* List of referral server sessions per dfs mount */ -struct mount_group { - struct list_head list; - uuid_t id; - struct cifs_ses *sessions[CACHE_MAX_ENTRIES]; - int num_sessions; - spinlock_t lock; - struct list_head refresh_list; - struct kref refcount; -}; - static struct kmem_cache *cache_slab __read_mostly; static struct workqueue_struct *dfscache_wq __read_mostly; @@ -76,85 +65,10 @@ static atomic_t cache_count; static struct hlist_head cache_htable[CACHE_HTABLE_SIZE]; static DECLARE_RWSEM(htable_rw_lock); -static LIST_HEAD(mount_group_list); -static DEFINE_MUTEX(mount_group_list_lock); - static void refresh_cache_worker(struct work_struct *work); static DECLARE_DELAYED_WORK(refresh_task, refresh_cache_worker); -static void __mount_group_release(struct mount_group *mg) -{ - int i; - - for (i = 0; i < mg->num_sessions; i++) - cifs_put_smb_ses(mg->sessions[i]); - kfree(mg); -} - -static void mount_group_release(struct kref *kref) -{ - struct mount_group *mg = container_of(kref, struct mount_group, refcount); - - mutex_lock(&mount_group_list_lock); - list_del(&mg->list); - mutex_unlock(&mount_group_list_lock); - __mount_group_release(mg); -} - -static struct mount_group *find_mount_group_locked(const uuid_t *id) -{ - struct mount_group *mg; - - list_for_each_entry(mg, &mount_group_list, list) { - if (uuid_equal(&mg->id, id)) - return mg; - } - return ERR_PTR(-ENOENT); -} - -static struct mount_group *__get_mount_group_locked(const uuid_t *id) -{ - struct mount_group *mg; - - mg = find_mount_group_locked(id); - if (!IS_ERR(mg)) - return mg; - - mg = kmalloc(sizeof(*mg), GFP_KERNEL); - if (!mg) - return ERR_PTR(-ENOMEM); - kref_init(&mg->refcount); - uuid_copy(&mg->id, id); - mg->num_sessions = 0; - spin_lock_init(&mg->lock); - list_add(&mg->list, &mount_group_list); - return mg; -} - -static struct mount_group *get_mount_group(const uuid_t *id) -{ - struct mount_group *mg; - - mutex_lock(&mount_group_list_lock); - mg = __get_mount_group_locked(id); - if (!IS_ERR(mg)) - kref_get(&mg->refcount); - mutex_unlock(&mount_group_list_lock); - - return mg; -} - -static void free_mount_group_list(void) -{ - struct mount_group *mg, *tmp_mg; - - list_for_each_entry_safe(mg, tmp_mg, &mount_group_list, list) { - list_del_init(&mg->list); - __mount_group_release(mg); - } -} - /** * dfs_cache_canonical_path - get a canonical DFS path * @@ -704,7 +618,6 @@ void dfs_cache_destroy(void) { cancel_delayed_work_sync(&refresh_task); unload_nls(cache_cp); - free_mount_group_list(); flush_cache_ents(); kmem_cache_destroy(cache_slab); destroy_workqueue(dfscache_wq); @@ -1111,54 +1024,6 @@ out_unlock: return rc; } -/** - * dfs_cache_add_refsrv_session - add SMB session of referral server - * - * @mount_id: mount group uuid to lookup. - * @ses: reference counted SMB session of referral server. - */ -void dfs_cache_add_refsrv_session(const uuid_t *mount_id, struct cifs_ses *ses) -{ - struct mount_group *mg; - - if (WARN_ON_ONCE(!mount_id || uuid_is_null(mount_id) || !ses)) - return; - - mg = get_mount_group(mount_id); - if (WARN_ON_ONCE(IS_ERR(mg))) - return; - - spin_lock(&mg->lock); - if (mg->num_sessions < ARRAY_SIZE(mg->sessions)) - mg->sessions[mg->num_sessions++] = ses; - spin_unlock(&mg->lock); - kref_put(&mg->refcount, mount_group_release); -} - -/** - * dfs_cache_put_refsrv_sessions - put all referral server sessions - * - * Put all SMB sessions from the given mount group id. - * - * @mount_id: mount group uuid to lookup. - */ -void dfs_cache_put_refsrv_sessions(const uuid_t *mount_id) -{ - struct mount_group *mg; - - if (!mount_id || uuid_is_null(mount_id)) - return; - - mutex_lock(&mount_group_list_lock); - mg = find_mount_group_locked(mount_id); - if (IS_ERR(mg)) { - mutex_unlock(&mount_group_list_lock); - return; - } - mutex_unlock(&mount_group_list_lock); - kref_put(&mg->refcount, mount_group_release); -} - /* Extract share from DFS target and return a pointer to prefix path or NULL */ static const char *parse_target_share(const char *target, char **share) { @@ -1326,7 +1191,7 @@ static int __refresh_tcon(const char *path, struct cifs_tcon *tcon, bool force_r } spin_lock(&ipc->tc_lock); - if (ses->ses_status != SES_GOOD || ipc->status != TID_GOOD) { + if (ipc->status != TID_GOOD) { spin_unlock(&ipc->tc_lock); cifs_dbg(FYI, "%s: skip cache refresh due to disconnected ipc\n", __func__); goto out; @@ -1384,11 +1249,6 @@ int dfs_cache_remount_fs(struct cifs_sb_info *cifs_sb) cifs_dbg(FYI, "%s: not a dfs mount\n", __func__); return 0; } - - if (uuid_is_null(&cifs_sb->dfs_mount_id)) { - cifs_dbg(FYI, "%s: no dfs mount group id\n", __func__); - return -EINVAL; - } /* * After reconnecting to a different server, unique ids won't match anymore, so we disable * serverino. This prevents dentry revalidation to think the dentry are stale (ESTALE). diff --git a/fs/cifs/dfs_cache.h b/fs/cifs/dfs_cache.h index be3b5a44cf82..e0d39393035a 100644 --- a/fs/cifs/dfs_cache.h +++ b/fs/cifs/dfs_cache.h @@ -40,8 +40,6 @@ int dfs_cache_get_tgt_referral(const char *path, const struct dfs_cache_tgt_iter struct dfs_info3_param *ref); int dfs_cache_get_tgt_share(char *path, const struct dfs_cache_tgt_iterator *it, char **share, char **prefix); -void dfs_cache_put_refsrv_sessions(const uuid_t *mount_id); -void dfs_cache_add_refsrv_session(const uuid_t *mount_id, struct cifs_ses *ses); char *dfs_cache_canonical_path(const char *path, const struct nls_table *cp, int remap); int dfs_cache_remount_fs(struct cifs_sb_info *cifs_sb); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 4d4a2d82636d..b33d2e7b0f98 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -174,13 +174,13 @@ cifs_mark_open_files_invalid(struct cifs_tcon *tcon) struct list_head *tmp1; /* only send once per connect */ - spin_lock(&tcon->ses->ses_lock); - if ((tcon->ses->ses_status != SES_GOOD) || (tcon->status != TID_NEED_RECON)) { - spin_unlock(&tcon->ses->ses_lock); + spin_lock(&tcon->tc_lock); + if (tcon->status != TID_NEED_RECON) { + spin_unlock(&tcon->tc_lock); return; } tcon->status = TID_IN_FILES_INVALIDATE; - spin_unlock(&tcon->ses->ses_lock); + spin_unlock(&tcon->tc_lock); /* list all files open on tree connection and mark them invalid */ spin_lock(&tcon->open_file_lock); @@ -4010,7 +4010,6 @@ static void collect_uncached_read_data(struct cifs_aio_ctx *ctx) { struct cifs_readdata *rdata, *tmp; - struct iov_iter *to = &ctx->iter; struct cifs_sb_info *cifs_sb; int rc; @@ -4076,9 +4075,6 @@ again: kref_put(&rdata->refcount, cifs_readdata_release); } - if (!ctx->direct_io) - ctx->total_len = ctx->len - iov_iter_count(to); - /* mask nodata case */ if (rc == -ENODATA) rc = 0; diff --git a/fs/cifs/fs_context.c b/fs/cifs/fs_context.c index 6d13f8207e96..ace11a1a7c8a 100644 --- a/fs/cifs/fs_context.c +++ b/fs/cifs/fs_context.c @@ -441,13 +441,14 @@ out: * but there are some bugs that prevent rename from working if there are * multiple delimiters. * - * Returns a sanitized duplicate of @path. The caller is responsible for - * cleaning up the original. + * Returns a sanitized duplicate of @path. @gfp indicates the GFP_* flags + * for kstrdup. + * The caller is responsible for freeing the original. */ #define IS_DELIM(c) ((c) == '/' || (c) == '\\') -static char *sanitize_path(char *path) +char *cifs_sanitize_prepath(char *prepath, gfp_t gfp) { - char *cursor1 = path, *cursor2 = path; + char *cursor1 = prepath, *cursor2 = prepath; /* skip all prepended delimiters */ while (IS_DELIM(*cursor1)) @@ -469,7 +470,7 @@ static char *sanitize_path(char *path) cursor2--; *(cursor2) = '\0'; - return kstrdup(path, GFP_KERNEL); + return kstrdup(prepath, gfp); } /* @@ -531,7 +532,7 @@ smb3_parse_devname(const char *devname, struct smb3_fs_context *ctx) if (!*pos) return 0; - ctx->prepath = sanitize_path(pos); + ctx->prepath = cifs_sanitize_prepath(pos, GFP_KERNEL); if (!ctx->prepath) return -ENOMEM; diff --git a/fs/cifs/fs_context.h b/fs/cifs/fs_context.h index 44cb5639ed3b..f4eaf8558902 100644 --- a/fs/cifs/fs_context.h +++ b/fs/cifs/fs_context.h @@ -265,6 +265,7 @@ struct smb3_fs_context { bool rootfs:1; /* if it's a SMB root file system */ bool witness:1; /* use witness protocol */ char *leaf_fullpath; + struct cifs_ses *dfs_root_ses; }; extern const struct fs_parameter_spec smb3_fs_parameters[]; @@ -285,5 +286,8 @@ extern void smb3_update_mnt_flags(struct cifs_sb_info *cifs_sb); * max deferred close timeout (jiffies) - 2^30 */ #define SMB3_MAX_DCLOSETIMEO (1 << 30) -#define SMB3_DEF_DCLOSETIMEO (5 * HZ) /* Can increase later, other clients use larger */ +#define SMB3_DEF_DCLOSETIMEO (1 * HZ) /* even 1 sec enough to help eg open/write/close/open/read */ + +extern char *cifs_sanitize_prepath(char *prepath, gfp_t gfp); + #endif diff --git a/fs/cifs/link.c b/fs/cifs/link.c index 7d97c10f2453..c66be4904e1f 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -360,6 +360,7 @@ smb3_query_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, oparms = (struct cifs_open_parms) { .tcon = tcon, .cifs_sb = cifs_sb, + .path = path, .desired_access = GENERIC_READ, .create_options = cifs_create_options(cifs_sb, CREATE_NOT_DIR), .disposition = FILE_OPEN, @@ -427,6 +428,7 @@ smb3_create_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, oparms = (struct cifs_open_parms) { .tcon = tcon, .cifs_sb = cifs_sb, + .path = path, .desired_access = GENERIC_WRITE, .create_options = cifs_create_options(cifs_sb, CREATE_NOT_DIR), .disposition = FILE_CREATE, diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index a0d286ee723d..7f085ed2d866 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -22,6 +22,7 @@ #ifdef CONFIG_CIFS_DFS_UPCALL #include "dns_resolve.h" #include "dfs_cache.h" +#include "dfs.h" #endif #include "fs_context.h" #include "cached_dir.h" @@ -134,6 +135,9 @@ tconInfoAlloc(void) spin_lock_init(&ret_buf->stat_lock); atomic_set(&ret_buf->num_local_opens, 0); atomic_set(&ret_buf->num_remote_opens, 0); +#ifdef CONFIG_CIFS_DFS_UPCALL + INIT_LIST_HEAD(&ret_buf->dfs_ses_list); +#endif return ret_buf; } @@ -149,6 +153,9 @@ tconInfoFree(struct cifs_tcon *tcon) atomic_dec(&tconInfoAllocCount); kfree(tcon->nativeFileSystem); kfree_sensitive(tcon->password); +#ifdef CONFIG_CIFS_DFS_UPCALL + dfs_put_root_smb_sessions(&tcon->dfs_ses_list); +#endif kfree(tcon); } @@ -1188,7 +1195,7 @@ int cifs_update_super_prepath(struct cifs_sb_info *cifs_sb, char *prefix) kfree(cifs_sb->prepath); if (prefix && *prefix) { - cifs_sb->prepath = kstrdup(prefix, GFP_ATOMIC); + cifs_sb->prepath = cifs_sanitize_prepath(prefix, GFP_ATOMIC); if (!cifs_sb->prepath) return -ENOMEM; @@ -1255,6 +1262,7 @@ int cifs_inval_name_dfs_link_error(const unsigned int xid, * removing cached DFS targets that the client would eventually * need during failover. */ + ses = CIFS_DFS_ROOT_SES(ses); if (ses->server->ops->get_dfs_refer && !ses->server->ops->get_dfs_refer(xid, ses, ref_path, &refs, &num_refs, cifs_sb->local_nls, diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c index 9b956294e864..163a03298430 100644 --- a/fs/cifs/smb2inode.c +++ b/fs/cifs/smb2inode.c @@ -107,6 +107,7 @@ static int smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, vars->oparms = (struct cifs_open_parms) { .tcon = tcon, + .path = full_path, .desired_access = desired_access, .disposition = create_disposition, .create_options = cifs_create_options(cifs_sb, create_options), @@ -234,15 +235,32 @@ static int smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, size[0] = 8; /* sizeof __le64 */ data[0] = ptr; - rc = SMB2_set_info_init(tcon, server, - &rqst[num_rqst], COMPOUND_FID, - COMPOUND_FID, current->tgid, - FILE_END_OF_FILE_INFORMATION, - SMB2_O_INFO_FILE, 0, data, size); + if (cfile) { + rc = SMB2_set_info_init(tcon, server, + &rqst[num_rqst], + cfile->fid.persistent_fid, + cfile->fid.volatile_fid, + current->tgid, + FILE_END_OF_FILE_INFORMATION, + SMB2_O_INFO_FILE, 0, + data, size); + } else { + rc = SMB2_set_info_init(tcon, server, + &rqst[num_rqst], + COMPOUND_FID, + COMPOUND_FID, + current->tgid, + FILE_END_OF_FILE_INFORMATION, + SMB2_O_INFO_FILE, 0, + data, size); + if (!rc) { + smb2_set_next_command(tcon, &rqst[num_rqst]); + smb2_set_related(&rqst[num_rqst]); + } + } if (rc) goto finished; - smb2_set_next_command(tcon, &rqst[num_rqst]); - smb2_set_related(&rqst[num_rqst++]); + num_rqst++; trace_smb3_set_eof_enter(xid, ses->Suid, tcon->tid, full_path); break; case SMB2_OP_SET_INFO: diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 6dfb865ee9d7..a81758225fcd 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -530,6 +530,14 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf, p = buf; spin_lock(&ses->iface_lock); + /* do not query too frequently, this time with lock held */ + if (ses->iface_last_update && + time_before(jiffies, ses->iface_last_update + + (SMB_INTERFACE_POLL_INTERVAL * HZ))) { + spin_unlock(&ses->iface_lock); + return 0; + } + /* * Go through iface_list and do kref_put to remove * any unused ifaces. ifaces in use will be removed @@ -696,6 +704,12 @@ SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon, bool in_ struct network_interface_info_ioctl_rsp *out_buf = NULL; struct cifs_ses *ses = tcon->ses; + /* do not query too frequently */ + if (ses->iface_last_update && + time_before(jiffies, ses->iface_last_update + + (SMB_INTERFACE_POLL_INTERVAL * HZ))) + return 0; + rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID, FSCTL_QUERY_NETWORK_INTERFACE_INFO, NULL /* no data input */, 0 /* no data input */, @@ -703,7 +717,7 @@ SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon, bool in_ if (rc == -EOPNOTSUPP) { cifs_dbg(FYI, "server does not support query network interfaces\n"); - goto out; + ret_data_len = 0; } else if (rc != 0) { cifs_tcon_dbg(VFS, "error %d on ioctl to get interface list\n", rc); goto out; @@ -731,6 +745,7 @@ smb3_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon, oparms = (struct cifs_open_parms) { .tcon = tcon, + .path = "", .desired_access = FILE_READ_ATTRIBUTES, .disposition = FILE_OPEN, .create_options = cifs_create_options(cifs_sb, 0), @@ -774,6 +789,7 @@ smb2_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon, oparms = (struct cifs_open_parms) { .tcon = tcon, + .path = "", .desired_access = FILE_READ_ATTRIBUTES, .disposition = FILE_OPEN, .create_options = cifs_create_options(cifs_sb, 0), @@ -821,6 +837,7 @@ smb2_is_path_accessible(const unsigned int xid, struct cifs_tcon *tcon, oparms = (struct cifs_open_parms) { .tcon = tcon, + .path = full_path, .desired_access = FILE_READ_ATTRIBUTES, .disposition = FILE_OPEN, .create_options = cifs_create_options(cifs_sb, 0), @@ -1105,6 +1122,7 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon, oparms = (struct cifs_open_parms) { .tcon = tcon, + .path = path, .desired_access = FILE_WRITE_EA, .disposition = FILE_OPEN, .create_options = cifs_create_options(cifs_sb, 0), @@ -2096,6 +2114,7 @@ smb3_notify(const unsigned int xid, struct file *pfile, tcon = cifs_sb_master_tcon(cifs_sb); oparms = (struct cifs_open_parms) { .tcon = tcon, + .path = path, .desired_access = FILE_READ_ATTRIBUTES | FILE_READ_DATA, .disposition = FILE_OPEN, .create_options = cifs_create_options(cifs_sb, 0), @@ -2168,6 +2187,7 @@ smb2_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon, oparms = (struct cifs_open_parms) { .tcon = tcon, + .path = path, .desired_access = FILE_READ_ATTRIBUTES | FILE_READ_DATA, .disposition = FILE_OPEN, .create_options = cifs_create_options(cifs_sb, 0), @@ -2500,6 +2520,7 @@ smb2_query_info_compound(const unsigned int xid, struct cifs_tcon *tcon, oparms = (struct cifs_open_parms) { .tcon = tcon, + .path = path, .desired_access = desired_access, .disposition = FILE_OPEN, .create_options = cifs_create_options(cifs_sb, 0), @@ -2634,6 +2655,7 @@ smb311_queryfs(const unsigned int xid, struct cifs_tcon *tcon, oparms = (struct cifs_open_parms) { .tcon = tcon, + .path = "", .desired_access = FILE_READ_ATTRIBUTES, .disposition = FILE_OPEN, .create_options = cifs_create_options(cifs_sb, 0), @@ -2928,6 +2950,7 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon, oparms = (struct cifs_open_parms) { .tcon = tcon, + .path = full_path, .desired_access = FILE_READ_ATTRIBUTES, .disposition = FILE_OPEN, .create_options = cifs_create_options(cifs_sb, create_options), @@ -3068,6 +3091,7 @@ smb2_query_reparse_tag(const unsigned int xid, struct cifs_tcon *tcon, oparms = (struct cifs_open_parms) { .tcon = tcon, + .path = full_path, .desired_access = FILE_READ_ATTRIBUTES, .disposition = FILE_OPEN, .create_options = cifs_create_options(cifs_sb, OPEN_REPARSE_POINT), @@ -3208,6 +3232,7 @@ get_smb2_acl_by_path(struct cifs_sb_info *cifs_sb, oparms = (struct cifs_open_parms) { .tcon = tcon, + .path = path, .desired_access = READ_CONTROL, .disposition = FILE_OPEN, /* diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 0e53265e1462..366f0c3b799b 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -144,7 +144,7 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon, struct TCP_Server_Info *server) { int rc = 0; - struct nls_table *nls_codepage; + struct nls_table *nls_codepage = NULL; struct cifs_ses *ses; /* @@ -165,13 +165,9 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon, spin_lock(&tcon->tc_lock); if (tcon->status == TID_EXITING) { /* - * only tree disconnect, open, and write, - * (and ulogoff which does not have tcon) - * are allowed as we start force umount. + * only tree disconnect allowed when disconnecting ... */ - if ((smb2_command != SMB2_WRITE) && - (smb2_command != SMB2_CREATE) && - (smb2_command != SMB2_TREE_DISCONNECT)) { + if (smb2_command != SMB2_TREE_DISCONNECT) { spin_unlock(&tcon->tc_lock); cifs_dbg(FYI, "can not send cmd %d while umounting\n", smb2_command); @@ -203,6 +199,7 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon, } spin_unlock(&server->srv_lock); +again: rc = cifs_wait_for_server_reconnect(server, tcon->retry); if (rc) return rc; @@ -219,8 +216,7 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon, tcon->ses->chans_need_reconnect, tcon->need_reconnect); - nls_codepage = load_nls_default(); - + mutex_lock(&ses->session_mutex); /* * Recheck after acquire mutex. If another thread is negotiating * and the server never sends an answer the socket will be closed @@ -229,28 +225,38 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon, spin_lock(&server->srv_lock); if (server->tcpStatus == CifsNeedReconnect) { spin_unlock(&server->srv_lock); + mutex_unlock(&ses->session_mutex); + + if (tcon->retry) + goto again; + rc = -EHOSTDOWN; goto out; } spin_unlock(&server->srv_lock); + nls_codepage = load_nls_default(); + /* * need to prevent multiple threads trying to simultaneously * reconnect the same SMB session */ + spin_lock(&ses->ses_lock); spin_lock(&ses->chan_lock); - if (!cifs_chan_needs_reconnect(ses, server)) { + if (!cifs_chan_needs_reconnect(ses, server) && + ses->ses_status == SES_GOOD) { spin_unlock(&ses->chan_lock); - + spin_unlock(&ses->ses_lock); /* this means that we only need to tree connect */ if (tcon->need_reconnect) goto skip_sess_setup; + mutex_unlock(&ses->session_mutex); goto out; } spin_unlock(&ses->chan_lock); + spin_unlock(&ses->ses_lock); - mutex_lock(&ses->session_mutex); rc = cifs_negotiate_protocol(0, ses, server); if (!rc) { rc = cifs_setup_session(0, ses, server, nls_codepage); @@ -266,10 +272,8 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon, mutex_unlock(&ses->session_mutex); goto out; } - mutex_unlock(&ses->session_mutex); skip_sess_setup: - mutex_lock(&ses->session_mutex); if (!tcon->need_reconnect) { mutex_unlock(&ses->session_mutex); goto out; @@ -284,7 +288,7 @@ skip_sess_setup: cifs_dbg(FYI, "reconnect tcon rc = %d\n", rc); if (rc) { /* If sess reconnected but tcon didn't, something strange ... */ - pr_warn_once("reconnect tcon failed rc = %d\n", rc); + cifs_dbg(VFS, "reconnect tcon failed rc = %d\n", rc); goto out; } @@ -306,7 +310,6 @@ out: case SMB2_READ: case SMB2_WRITE: case SMB2_LOCK: - case SMB2_IOCTL: case SMB2_QUERY_DIRECTORY: case SMB2_CHANGE_NOTIFY: case SMB2_QUERY_INFO: @@ -584,11 +587,15 @@ assemble_neg_contexts(struct smb2_negotiate_req *req, } +/* If invalid preauth context warn but use what we requested, SHA-512 */ static void decode_preauth_context(struct smb2_preauth_neg_context *ctxt) { unsigned int len = le16_to_cpu(ctxt->DataLength); - /* If invalid preauth context warn but use what we requested, SHA-512 */ + /* + * Caller checked that DataLength remains within SMB boundary. We still + * need to confirm that one HashAlgorithms member is accounted for. + */ if (len < MIN_PREAUTH_CTXT_DATA_LEN) { pr_warn_once("server sent bad preauth context\n"); return; @@ -607,7 +614,11 @@ static void decode_compress_ctx(struct TCP_Server_Info *server, { unsigned int len = le16_to_cpu(ctxt->DataLength); - /* sizeof compress context is a one element compression capbility struct */ + /* + * Caller checked that DataLength remains within SMB boundary. We still + * need to confirm that one CompressionAlgorithms member is accounted + * for. + */ if (len < 10) { pr_warn_once("server sent bad compression cntxt\n"); return; @@ -629,6 +640,11 @@ static int decode_encrypt_ctx(struct TCP_Server_Info *server, unsigned int len = le16_to_cpu(ctxt->DataLength); cifs_dbg(FYI, "decode SMB3.11 encryption neg context of len %d\n", len); + /* + * Caller checked that DataLength remains within SMB boundary. We still + * need to confirm that one Cipher flexible array member is accounted + * for. + */ if (len < MIN_ENCRYPT_CTXT_DATA_LEN) { pr_warn_once("server sent bad crypto ctxt len\n"); return -EINVAL; @@ -675,6 +691,11 @@ static void decode_signing_ctx(struct TCP_Server_Info *server, { unsigned int len = le16_to_cpu(pctxt->DataLength); + /* + * Caller checked that DataLength remains within SMB boundary. We still + * need to confirm that one SigningAlgorithms flexible array member is + * accounted for. + */ if ((len < 4) || (len > 16)) { pr_warn_once("server sent bad signing negcontext\n"); return; @@ -716,14 +737,19 @@ static int smb311_decode_neg_context(struct smb2_negotiate_rsp *rsp, for (i = 0; i < ctxt_cnt; i++) { int clen; /* check that offset is not beyond end of SMB */ - if (len_of_ctxts == 0) - break; - if (len_of_ctxts < sizeof(struct smb2_neg_context)) break; pctx = (struct smb2_neg_context *)(offset + (char *)rsp); - clen = le16_to_cpu(pctx->DataLength); + clen = sizeof(struct smb2_neg_context) + + le16_to_cpu(pctx->DataLength); + /* + * 2.2.4 SMB2 NEGOTIATE Response + * Subsequent negotiate contexts MUST appear at the first 8-byte + * aligned offset following the previous negotiate context. + */ + if (i + 1 != ctxt_cnt) + clen = ALIGN(clen, 8); if (clen > len_of_ctxts) break; @@ -744,12 +770,10 @@ static int smb311_decode_neg_context(struct smb2_negotiate_rsp *rsp, else cifs_server_dbg(VFS, "unknown negcontext of type %d ignored\n", le16_to_cpu(pctx->ContextType)); - if (rc) break; - /* offsets must be 8 byte aligned */ - clen = ALIGN(clen, 8); - offset += clen + sizeof(struct smb2_neg_context); + + offset += clen; len_of_ctxts -= clen; } return rc; @@ -1256,9 +1280,9 @@ SMB2_sess_alloc_buffer(struct SMB2_sess_data *sess_data) if (rc) return rc; - spin_lock(&ses->chan_lock); - is_binding = !CIFS_ALL_CHANS_NEED_RECONNECT(ses); - spin_unlock(&ses->chan_lock); + spin_lock(&ses->ses_lock); + is_binding = (ses->ses_status == SES_GOOD); + spin_unlock(&ses->ses_lock); if (is_binding) { req->hdr.SessionId = cpu_to_le64(ses->Suid); @@ -1416,9 +1440,9 @@ SMB2_auth_kerberos(struct SMB2_sess_data *sess_data) goto out_put_spnego_key; } - spin_lock(&ses->chan_lock); - is_binding = !CIFS_ALL_CHANS_NEED_RECONNECT(ses); - spin_unlock(&ses->chan_lock); + spin_lock(&ses->ses_lock); + is_binding = (ses->ses_status == SES_GOOD); + spin_unlock(&ses->ses_lock); /* keep session key if binding */ if (!is_binding) { @@ -1542,9 +1566,9 @@ SMB2_sess_auth_rawntlmssp_negotiate(struct SMB2_sess_data *sess_data) cifs_dbg(FYI, "rawntlmssp session setup challenge phase\n"); - spin_lock(&ses->chan_lock); - is_binding = !CIFS_ALL_CHANS_NEED_RECONNECT(ses); - spin_unlock(&ses->chan_lock); + spin_lock(&ses->ses_lock); + is_binding = (ses->ses_status == SES_GOOD); + spin_unlock(&ses->ses_lock); /* keep existing ses id and flags if binding */ if (!is_binding) { @@ -1610,9 +1634,9 @@ SMB2_sess_auth_rawntlmssp_authenticate(struct SMB2_sess_data *sess_data) rsp = (struct smb2_sess_setup_rsp *)sess_data->iov[0].iov_base; - spin_lock(&ses->chan_lock); - is_binding = !CIFS_ALL_CHANS_NEED_RECONNECT(ses); - spin_unlock(&ses->chan_lock); + spin_lock(&ses->ses_lock); + is_binding = (ses->ses_status == SES_GOOD); + spin_unlock(&ses->ses_lock); /* keep existing ses id and flags if binding */ if (!is_binding) { @@ -2705,7 +2729,7 @@ int smb311_posix_mkdir(const unsigned int xid, struct inode *inode, rqst.rq_nvec = n_iov; /* no need to inc num_remote_opens because we close it just below */ - trace_smb3_posix_mkdir_enter(xid, tcon->tid, ses->Suid, CREATE_NOT_FILE, + trace_smb3_posix_mkdir_enter(xid, tcon->tid, ses->Suid, full_path, CREATE_NOT_FILE, FILE_WRITE_ATTRIBUTES); /* resource #4: response buffer */ rc = cifs_send_recv(xid, ses, server, @@ -2973,7 +2997,7 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, if (rc) goto creat_exit; - trace_smb3_open_enter(xid, tcon->tid, tcon->ses->Suid, + trace_smb3_open_enter(xid, tcon->tid, tcon->ses->Suid, oparms->path, oparms->create_options, oparms->desired_access); rc = cifs_send_recv(xid, ses, server, @@ -4156,10 +4180,12 @@ smb2_readv_callback(struct mid_q_entry *mid) struct smb2_hdr *shdr = (struct smb2_hdr *)rdata->iov[0].iov_base; struct cifs_credits credits = { .value = 0, .instance = 0 }; - struct smb_rqst rqst = { .rq_iov = &rdata->iov[1], - .rq_nvec = 1, - .rq_iter = rdata->iter, - .rq_iter_size = iov_iter_count(&rdata->iter), }; + struct smb_rqst rqst = { .rq_iov = &rdata->iov[1], .rq_nvec = 1 }; + + if (rdata->got_bytes) { + rqst.rq_iter = rdata->iter; + rqst.rq_iter_size = iov_iter_count(&rdata->iter); + }; WARN_ONCE(rdata->server != mid->server, "rdata server %p != mid server %p", diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c index 381babc1212c..790acf65a092 100644 --- a/fs/cifs/smb2transport.c +++ b/fs/cifs/smb2transport.c @@ -81,6 +81,7 @@ int smb2_get_sign_key(__u64 ses_id, struct TCP_Server_Info *server, u8 *key) struct cifs_ses *ses = NULL; int i; int rc = 0; + bool is_binding = false; spin_lock(&cifs_tcp_ses_lock); @@ -97,9 +98,12 @@ int smb2_get_sign_key(__u64 ses_id, struct TCP_Server_Info *server, u8 *key) goto out; found: + spin_lock(&ses->ses_lock); spin_lock(&ses->chan_lock); - if (cifs_chan_needs_reconnect(ses, server) && - !CIFS_ALL_CHANS_NEED_RECONNECT(ses)) { + + is_binding = (cifs_chan_needs_reconnect(ses, server) && + ses->ses_status == SES_GOOD); + if (is_binding) { /* * If we are in the process of binding a new channel * to an existing session, use the master connection @@ -107,6 +111,7 @@ found: */ memcpy(key, ses->smb3signingkey, SMB3_SIGN_KEY_SIZE); spin_unlock(&ses->chan_lock); + spin_unlock(&ses->ses_lock); goto out; } @@ -119,10 +124,12 @@ found: if (chan->server == server) { memcpy(key, chan->signkey, SMB3_SIGN_KEY_SIZE); spin_unlock(&ses->chan_lock); + spin_unlock(&ses->ses_lock); goto out; } } spin_unlock(&ses->chan_lock); + spin_unlock(&ses->ses_lock); cifs_dbg(VFS, "%s: Could not find channel signing key for session 0x%llx\n", @@ -392,11 +399,15 @@ generate_smb3signingkey(struct cifs_ses *ses, bool is_binding = false; int chan_index = 0; + spin_lock(&ses->ses_lock); spin_lock(&ses->chan_lock); - is_binding = !CIFS_ALL_CHANS_NEED_RECONNECT(ses); + is_binding = (cifs_chan_needs_reconnect(ses, server) && + ses->ses_status == SES_GOOD); + chan_index = cifs_ses_get_chan_index(ses, server); /* TODO: introduce ref counting for channels when the can be freed */ spin_unlock(&ses->chan_lock); + spin_unlock(&ses->ses_lock); /* * All channels use the same encryption/decryption keys but @@ -425,7 +436,7 @@ generate_smb3signingkey(struct cifs_ses *ses, /* safe to access primary channel, since it will never go away */ spin_lock(&ses->chan_lock); - memcpy(ses->chans[0].signkey, ses->smb3signingkey, + memcpy(ses->chans[chan_index].signkey, ses->smb3signingkey, SMB3_SIGN_KEY_SIZE); spin_unlock(&ses->chan_lock); diff --git a/fs/cifs/trace.h b/fs/cifs/trace.h index 110070ba8b04..d3053bd8ae73 100644 --- a/fs/cifs/trace.h +++ b/fs/cifs/trace.h @@ -701,13 +701,15 @@ DECLARE_EVENT_CLASS(smb3_open_enter_class, TP_PROTO(unsigned int xid, __u32 tid, __u64 sesid, + const char *full_path, int create_options, int desired_access), - TP_ARGS(xid, tid, sesid, create_options, desired_access), + TP_ARGS(xid, tid, sesid, full_path, create_options, desired_access), TP_STRUCT__entry( __field(unsigned int, xid) __field(__u32, tid) __field(__u64, sesid) + __string(path, full_path) __field(int, create_options) __field(int, desired_access) ), @@ -715,11 +717,12 @@ DECLARE_EVENT_CLASS(smb3_open_enter_class, __entry->xid = xid; __entry->tid = tid; __entry->sesid = sesid; + __assign_str(path, full_path); __entry->create_options = create_options; __entry->desired_access = desired_access; ), - TP_printk("xid=%u sid=0x%llx tid=0x%x cr_opts=0x%x des_access=0x%x", - __entry->xid, __entry->sesid, __entry->tid, + TP_printk("xid=%u sid=0x%llx tid=0x%x path=%s cr_opts=0x%x des_access=0x%x", + __entry->xid, __entry->sesid, __entry->tid, __get_str(path), __entry->create_options, __entry->desired_access) ) @@ -728,9 +731,10 @@ DEFINE_EVENT(smb3_open_enter_class, smb3_##name, \ TP_PROTO(unsigned int xid, \ __u32 tid, \ __u64 sesid, \ + const char *full_path, \ int create_options, \ int desired_access), \ - TP_ARGS(xid, tid, sesid, create_options, desired_access)) + TP_ARGS(xid, tid, sesid, full_path, create_options, desired_access)) DEFINE_SMB3_OPEN_ENTER_EVENT(open_enter); DEFINE_SMB3_OPEN_ENTER_EVENT(posix_mkdir_enter); diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index b42050c68e6c..24bdd5f4d3bc 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -278,7 +278,7 @@ static int __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, struct smb_rqst *rqst) { - int rc = 0; + int rc; struct kvec *iov; int n_vec; unsigned int send_length = 0; @@ -289,6 +289,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, struct msghdr smb_msg = {}; __be32 rfc1002_marker; + cifs_in_send_inc(server); if (cifs_rdma_enabled(server)) { /* return -EAGAIN when connecting or reconnecting */ rc = -EAGAIN; @@ -297,14 +298,17 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, goto smbd_done; } + rc = -EAGAIN; if (ssocket == NULL) - return -EAGAIN; + goto out; + rc = -ERESTARTSYS; if (fatal_signal_pending(current)) { cifs_dbg(FYI, "signal pending before send request\n"); - return -ERESTARTSYS; + goto out; } + rc = 0; /* cork the socket */ tcp_sock_set_cork(ssocket->sk, true); @@ -407,7 +411,8 @@ smbd_done: rc); else if (rc > 0) rc = 0; - +out: + cifs_in_send_dec(server); return rc; } @@ -826,9 +831,7 @@ cifs_call_async(struct TCP_Server_Info *server, struct smb_rqst *rqst, * 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, 1, rqst, flags); - cifs_in_send_dec(server); if (rc < 0) { revert_current_mid(server, mid->credits); @@ -1144,9 +1147,7 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, else midQ[i]->callback = cifs_compound_last_callback; } - cifs_in_send_inc(server); rc = smb_send_rqst(server, num_rqst, rqst, flags); - cifs_in_send_dec(server); for (i = 0; i < num_rqst; i++) cifs_save_when_sent(midQ[i]); @@ -1396,9 +1397,7 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses, midQ->mid_state = MID_REQUEST_SUBMITTED; - cifs_in_send_inc(server); rc = smb_send(server, in_buf, len); - cifs_in_send_dec(server); cifs_save_when_sent(midQ); if (rc < 0) @@ -1539,9 +1538,7 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon, } midQ->mid_state = MID_REQUEST_SUBMITTED; - cifs_in_send_inc(server); rc = smb_send(server, in_buf, len); - cifs_in_send_dec(server); cifs_save_when_sent(midQ); if (rc < 0) diff --git a/fs/crypto/keyring.c b/fs/crypto/keyring.c index 78086f8dbda5..13d336a6cc5d 100644 --- a/fs/crypto/keyring.c +++ b/fs/crypto/keyring.c @@ -92,6 +92,8 @@ void fscrypt_put_master_key_activeref(struct super_block *sb, * destroying any subkeys embedded in it. */ + if (WARN_ON(!sb->s_master_keys)) + return; spin_lock(&sb->s_master_keys->lock); hlist_del_rcu(&mk->mk_node); spin_unlock(&sb->s_master_keys->lock); @@ -207,10 +209,11 @@ static int allocate_filesystem_keyring(struct super_block *sb) * Release all encryption keys that have been added to the filesystem, along * with the keyring that contains them. * - * This is called at unmount time. The filesystem's underlying block device(s) - * are still available at this time; this is important because after user file - * accesses have been allowed, this function may need to evict keys from the - * keyslots of an inline crypto engine, which requires the block device(s). + * This is called at unmount time, after all potentially-encrypted inodes have + * been evicted. The filesystem's underlying block device(s) are still + * available at this time; this is important because after user file accesses + * have been allowed, this function may need to evict keys from the keyslots of + * an inline crypto engine, which requires the block device(s). */ void fscrypt_destroy_keyring(struct super_block *sb) { @@ -227,12 +230,12 @@ void fscrypt_destroy_keyring(struct super_block *sb) hlist_for_each_entry_safe(mk, tmp, bucket, mk_node) { /* - * Since all inodes were already evicted, every key - * remaining in the keyring should have an empty inode - * list, and should only still be in the keyring due to - * the single active ref associated with ->mk_secret. - * There should be no structural refs beyond the one - * associated with the active ref. + * Since all potentially-encrypted inodes were already + * evicted, every key remaining in the keyring should + * have an empty inode list, and should only still be in + * the keyring due to the single active ref associated + * with ->mk_secret. There should be no structural refs + * beyond the one associated with the active ref. */ WARN_ON(refcount_read(&mk->mk_active_refs) != 1); WARN_ON(refcount_read(&mk->mk_struct_refs) != 1); @@ -781,6 +781,33 @@ out: return ret; } +static int __dax_clear_dirty_range(struct address_space *mapping, + pgoff_t start, pgoff_t end) +{ + XA_STATE(xas, &mapping->i_pages, start); + unsigned int scanned = 0; + void *entry; + + xas_lock_irq(&xas); + xas_for_each(&xas, entry, end) { + entry = get_unlocked_entry(&xas, 0); + xas_clear_mark(&xas, PAGECACHE_TAG_DIRTY); + xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE); + put_unlocked_entry(&xas, entry, WAKE_NEXT); + + if (++scanned % XA_CHECK_SCHED) + continue; + + xas_pause(&xas); + xas_unlock_irq(&xas); + cond_resched(); + xas_lock_irq(&xas); + } + xas_unlock_irq(&xas); + + return 0; +} + /* * Delete DAX entry at @index from @mapping. Wait for it * to be unlocked before deleting it. @@ -1258,15 +1285,20 @@ static s64 dax_unshare_iter(struct iomap_iter *iter) /* don't bother with blocks that are not shared to start with */ if (!(iomap->flags & IOMAP_F_SHARED)) return length; - /* don't bother with holes or unwritten extents */ - if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN) - return length; id = dax_read_lock(); ret = dax_iomap_direct_access(iomap, pos, length, &daddr, NULL); if (ret < 0) goto out_unlock; + /* zero the distance if srcmap is HOLE or UNWRITTEN */ + if (srcmap->flags & IOMAP_F_SHARED || srcmap->type == IOMAP_UNWRITTEN) { + memset(daddr, 0, length); + dax_flush(iomap->dax_dev, daddr, length); + ret = length; + goto out_unlock; + } + ret = dax_iomap_direct_access(srcmap, pos, length, &saddr, NULL); if (ret < 0) goto out_unlock; @@ -1435,6 +1467,16 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi, * written by write(2) is visible in mmap. */ if (iomap->flags & IOMAP_F_NEW || cow) { + /* + * Filesystem allows CoW on non-shared extents. The src extents + * may have been mmapped with dirty mark before. To be able to + * invalidate its dax entries, we need to clear the dirty mark + * in advance. + */ + if (cow) + __dax_clear_dirty_range(iomi->inode->i_mapping, + pos >> PAGE_SHIFT, + (end - 1) >> PAGE_SHIFT); invalidate_inode_pages2_range(iomi->inode->i_mapping, pos >> PAGE_SHIFT, (end - 1) >> PAGE_SHIFT); @@ -2022,8 +2064,8 @@ int dax_dedupe_file_range_compare(struct inode *src, loff_t srcoff, while ((ret = iomap_iter(&src_iter, ops)) > 0 && (ret = iomap_iter(&dst_iter, ops)) > 0) { - compared = dax_range_compare_iter(&src_iter, &dst_iter, len, - same); + compared = dax_range_compare_iter(&src_iter, &dst_iter, + min(src_iter.len, dst_iter.len), same); if (compared < 0) return ret; src_iter.processed = dst_iter.processed = compared; diff --git a/fs/erofs/data.c b/fs/erofs/data.c index e16545849ea7..c08c0f578bc6 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -376,7 +376,7 @@ static ssize_t erofs_file_read_iter(struct kiocb *iocb, struct iov_iter *to) if (bdev) blksize_mask = bdev_logical_block_size(bdev) - 1; else - blksize_mask = (1 << inode->i_blkbits) - 1; + blksize_mask = i_blocksize(inode) - 1; if ((iocb->ki_pos | iov_iter_count(to) | iov_iter_alignment(to)) & blksize_mask) diff --git a/fs/erofs/decompressor_lzma.c b/fs/erofs/decompressor_lzma.c index 091fd5adf818..d38e19c11270 100644 --- a/fs/erofs/decompressor_lzma.c +++ b/fs/erofs/decompressor_lzma.c @@ -47,7 +47,7 @@ void z_erofs_lzma_exit(void) } } -int z_erofs_lzma_init(void) +int __init z_erofs_lzma_init(void) { unsigned int i; @@ -278,7 +278,7 @@ again: } } if (no < nrpages_out && strm->buf.out) - kunmap(rq->in[no]); + kunmap(rq->out[no]); if (ni < nrpages_in) kunmap(rq->in[ni]); /* 4. push back LZMA stream context to the global list */ diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index 3f3561d37d1b..1db018f8c2e8 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -486,7 +486,7 @@ static inline void *erofs_vm_map_ram(struct page **pages, unsigned int count) void *erofs_get_pcpubuf(unsigned int requiredpages); void erofs_put_pcpubuf(void *ptr); int erofs_pcpubuf_growsize(unsigned int nrpages); -void erofs_pcpubuf_init(void); +void __init erofs_pcpubuf_init(void); void erofs_pcpubuf_exit(void); int erofs_register_sysfs(struct super_block *sb); @@ -545,7 +545,7 @@ static inline int z_erofs_fill_inode(struct inode *inode) { return -EOPNOTSUPP; #endif /* !CONFIG_EROFS_FS_ZIP */ #ifdef CONFIG_EROFS_FS_ZIP_LZMA -int z_erofs_lzma_init(void); +int __init z_erofs_lzma_init(void); void z_erofs_lzma_exit(void); int z_erofs_load_lzma_config(struct super_block *sb, struct erofs_super_block *dsb, diff --git a/fs/erofs/pcpubuf.c b/fs/erofs/pcpubuf.c index a2efd833d1b6..c7a4b1d77069 100644 --- a/fs/erofs/pcpubuf.c +++ b/fs/erofs/pcpubuf.c @@ -114,7 +114,7 @@ out: return ret; } -void erofs_pcpubuf_init(void) +void __init erofs_pcpubuf_init(void) { int cpu; diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 3247d2422bea..f1708c77a991 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -1312,12 +1312,12 @@ static int z_erofs_decompress_pcluster(struct z_erofs_decompress_backend *be, if (!be->decompressed_pages) be->decompressed_pages = - kcalloc(be->nr_pages, sizeof(struct page *), - GFP_KERNEL | __GFP_NOFAIL); + kvcalloc(be->nr_pages, sizeof(struct page *), + GFP_KERNEL | __GFP_NOFAIL); if (!be->compressed_pages) be->compressed_pages = - kcalloc(pclusterpages, sizeof(struct page *), - GFP_KERNEL | __GFP_NOFAIL); + kvcalloc(pclusterpages, sizeof(struct page *), + GFP_KERNEL | __GFP_NOFAIL); z_erofs_parse_out_bvecs(be); err2 = z_erofs_parse_in_bvecs(be, &overlapped); @@ -1365,7 +1365,7 @@ out: } if (be->compressed_pages < be->onstack_pages || be->compressed_pages >= be->onstack_pages + Z_EROFS_ONSTACK_PAGES) - kfree(be->compressed_pages); + kvfree(be->compressed_pages); z_erofs_fill_other_copies(be, err); for (i = 0; i < be->nr_pages; ++i) { @@ -1384,7 +1384,7 @@ out: } if (be->decompressed_pages != be->onstack_pages) - kfree(be->decompressed_pages); + kvfree(be->decompressed_pages); pcl->length = 0; pcl->partial = true; diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c index 8bf6d30518b6..655da4d739cb 100644 --- a/fs/erofs/zmap.c +++ b/fs/erofs/zmap.c @@ -757,9 +757,6 @@ int z_erofs_map_blocks_iter(struct inode *inode, struct erofs_map_blocks *map, err = z_erofs_do_map_blocks(inode, map, flags); out: trace_z_erofs_map_blocks_iter_exit(inode, map, flags, err); - - /* aggressively BUG_ON iff CONFIG_EROFS_FS_DEBUG is on */ - DBG_BUGON(err < 0 && err != -ENOMEM); return err; } diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 4eeb02d456a9..08b29c289da4 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1387,7 +1387,7 @@ struct ext4_super_block { __le32 s_first_meta_bg; /* First metablock block group */ __le32 s_mkfs_time; /* When the filesystem was created */ __le32 s_jnl_blocks[17]; /* Backup of the journal inode */ - /* 64bit support valid if EXT4_FEATURE_COMPAT_64BIT */ + /* 64bit support valid if EXT4_FEATURE_INCOMPAT_64BIT */ /*150*/ __le32 s_blocks_count_hi; /* Blocks count */ __le32 s_r_blocks_count_hi; /* Reserved blocks count */ __le32 s_free_blocks_count_hi; /* Free blocks count */ diff --git a/fs/ext4/fsmap.c b/fs/ext4/fsmap.c index 4493ef0c715e..cdf9bfe10137 100644 --- a/fs/ext4/fsmap.c +++ b/fs/ext4/fsmap.c @@ -486,6 +486,8 @@ static int ext4_getfsmap_datadev(struct super_block *sb, keys[0].fmr_physical = bofs; if (keys[1].fmr_physical >= eofs) keys[1].fmr_physical = eofs - 1; + if (keys[1].fmr_physical < keys[0].fmr_physical) + return 0; start_fsb = keys[0].fmr_physical; end_fsb = keys[1].fmr_physical; diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 2b42ececa46d..1602d74b5eeb 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -159,7 +159,6 @@ int ext4_find_inline_data_nolock(struct inode *inode) (void *)ext4_raw_inode(&is.iloc)); EXT4_I(inode)->i_inline_size = EXT4_MIN_INLINE_DATA_SIZE + le32_to_cpu(is.s.here->e_value_size); - ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); } out: brelse(is.iloc.bh); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index d251d705c276..bf0b7dea4900 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4797,8 +4797,13 @@ static inline int ext4_iget_extra_inode(struct inode *inode, if (EXT4_INODE_HAS_XATTR_SPACE(inode) && *magic == cpu_to_le32(EXT4_XATTR_MAGIC)) { + int err; + ext4_set_inode_state(inode, EXT4_STATE_XATTR); - return ext4_find_inline_data_nolock(inode); + err = ext4_find_inline_data_nolock(inode); + if (!err && ext4_has_inline_data(inode)) + ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); + return err; } else EXT4_I(inode)->i_inline_off = 0; return 0; diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 12435d61f09e..f9a430152063 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -431,6 +431,7 @@ static long swap_inode_boot_loader(struct super_block *sb, ei_bl->i_flags = 0; inode_set_iversion(inode_bl, 1); i_size_write(inode_bl, 0); + EXT4_I(inode_bl)->i_disksize = inode_bl->i_size; inode_bl->i_mode = S_IFREG; if (ext4_has_feature_extents(sb)) { ext4_set_inode_flag(inode_bl, EXT4_INODE_EXTENTS); diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 94608b7df7e8..a5010b5b8a8c 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1595,11 +1595,10 @@ static struct buffer_head *__ext4_find_entry(struct inode *dir, int has_inline_data = 1; ret = ext4_find_inline_entry(dir, fname, res_dir, &has_inline_data); - if (has_inline_data) { - if (inlined) - *inlined = 1; + if (inlined) + *inlined = has_inline_data; + if (has_inline_data) goto cleanup_and_exit; - } } if ((namelen <= 2) && (name[0] == '.') && @@ -3646,7 +3645,8 @@ static void ext4_resetent(handle_t *handle, struct ext4_renament *ent, * so the old->de may no longer valid and need to find it again * before reset old inode info. */ - old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, NULL); + old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, + &old.inlined); if (IS_ERR(old.bh)) retval = PTR_ERR(old.bh); if (!old.bh) @@ -3813,9 +3813,20 @@ static int ext4_rename(struct mnt_idmap *idmap, struct inode *old_dir, return retval; } - old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, NULL); - if (IS_ERR(old.bh)) - return PTR_ERR(old.bh); + /* + * We need to protect against old.inode directory getting converted + * from inline directory format into a normal one. + */ + if (S_ISDIR(old.inode->i_mode)) + inode_lock_nested(old.inode, I_MUTEX_NONDIR2); + + old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, + &old.inlined); + if (IS_ERR(old.bh)) { + retval = PTR_ERR(old.bh); + goto unlock_moved_dir; + } + /* * Check for inode number is _not_ due to possible IO errors. * We might rmdir the source, keep it as pwd of some process @@ -3872,16 +3883,9 @@ static int ext4_rename(struct mnt_idmap *idmap, struct inode *old_dir, if (new.dir != old.dir && EXT4_DIR_LINK_MAX(new.dir)) goto end_rename; } - /* - * We need to protect against old.inode directory getting - * converted from inline directory format into a normal one. - */ - inode_lock_nested(old.inode, I_MUTEX_NONDIR2); retval = ext4_rename_dir_prepare(handle, &old); - if (retval) { - inode_unlock(old.inode); + if (retval) goto end_rename; - } } /* * If we're renaming a file within an inline_data dir and adding or @@ -4013,12 +4017,15 @@ end_rename: } else { ext4_journal_stop(handle); } - if (old.dir_bh) - inode_unlock(old.inode); release_bh: brelse(old.dir_bh); brelse(old.bh); brelse(new.bh); + +unlock_moved_dir: + if (S_ISDIR(old.inode->i_mode)) + inode_unlock(old.inode); + return retval; } diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index beaec6d81074..1e4db96a04e6 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -409,7 +409,8 @@ static void io_submit_init_bio(struct ext4_io_submit *io, static void io_submit_add_bh(struct ext4_io_submit *io, struct inode *inode, - struct page *page, + struct page *pagecache_page, + struct page *bounce_page, struct buffer_head *bh) { int ret; @@ -421,10 +422,11 @@ submit_and_retry: } if (io->io_bio == NULL) io_submit_init_bio(io, bh); - ret = bio_add_page(io->io_bio, page, bh->b_size, bh_offset(bh)); + ret = bio_add_page(io->io_bio, bounce_page ?: pagecache_page, + bh->b_size, bh_offset(bh)); if (ret != bh->b_size) goto submit_and_retry; - wbc_account_cgroup_owner(io->io_wbc, page, bh->b_size); + wbc_account_cgroup_owner(io->io_wbc, pagecache_page, bh->b_size); io->io_next_block++; } @@ -561,8 +563,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io, do { if (!buffer_async_write(bh)) continue; - io_submit_add_bh(io, inode, - bounce_page ? bounce_page : page, bh); + io_submit_add_bh(io, inode, page, bounce_page, bh); } while ((bh = bh->b_this_page) != head); unlock: unlock_page(page); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 88f7b8a88c76..76d1ef0efbf4 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2500,7 +2500,7 @@ static void ext4_apply_quota_options(struct fs_context *fc, qname = rcu_replace_pointer(sbi->s_qf_names[i], qname, lockdep_is_held(&sb->s_umount)); if (qname) - kfree_rcu(qname); + kfree_rcu_mightsleep(qname); } } @@ -5726,6 +5726,28 @@ static struct inode *ext4_get_journal_inode(struct super_block *sb, return journal_inode; } +static int ext4_journal_bmap(journal_t *journal, sector_t *block) +{ + struct ext4_map_blocks map; + int ret; + + if (journal->j_inode == NULL) + return 0; + + map.m_lblk = *block; + map.m_len = 1; + ret = ext4_map_blocks(NULL, journal->j_inode, &map, 0); + if (ret <= 0) { + ext4_msg(journal->j_inode->i_sb, KERN_CRIT, + "journal bmap failed: block %llu ret %d\n", + *block, ret); + jbd2_journal_abort(journal, ret ? ret : -EIO); + return ret; + } + *block = map.m_pblk; + return 0; +} + static journal_t *ext4_get_journal(struct super_block *sb, unsigned int journal_inum) { @@ -5746,6 +5768,7 @@ static journal_t *ext4_get_journal(struct super_block *sb, return NULL; } journal->j_private = sb; + journal->j_bmap = ext4_journal_bmap; ext4_init_journal_params(sb, journal); return journal; } @@ -5920,6 +5943,7 @@ static int ext4_load_journal(struct super_block *sb, err = jbd2_journal_wipe(journal, !really_read_only); if (!err) { char *save = kmalloc(EXT4_S_ERR_LEN, GFP_KERNEL); + if (save) memcpy(save, ((char *) es) + EXT4_S_ERR_START, EXT4_S_ERR_LEN); @@ -5928,6 +5952,14 @@ static int ext4_load_journal(struct super_block *sb, memcpy(((char *) es) + EXT4_S_ERR_START, save, EXT4_S_ERR_LEN); kfree(save); + es->s_state |= cpu_to_le16(EXT4_SB(sb)->s_mount_state & + EXT4_ERROR_FS); + /* Write out restored error information to the superblock */ + if (!bdev_read_only(sb->s_bdev)) { + int err2; + err2 = ext4_commit_super(sb); + err = err ? : err2; + } } if (err) { @@ -6157,11 +6189,13 @@ static int ext4_clear_journal_err(struct super_block *sb, errstr = ext4_decode_error(sb, j_errno, nbuf); ext4_warning(sb, "Filesystem error recorded " "from previous mount: %s", errstr); - ext4_warning(sb, "Marking fs in need of filesystem check."); EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; es->s_state |= cpu_to_le16(EXT4_ERROR_FS); - ext4_commit_super(sb); + j_errno = ext4_commit_super(sb); + if (j_errno) + return j_errno; + ext4_warning(sb, "Marked fs in need of filesystem check."); jbd2_journal_clear_err(journal); jbd2_journal_update_sb_errno(journal); diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index e2b8b3437c58..12d6252e3e22 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -501,13 +501,13 @@ static const struct sysfs_ops ext4_attr_ops = { .store = ext4_attr_store, }; -static struct kobj_type ext4_sb_ktype = { +static const struct kobj_type ext4_sb_ktype = { .default_groups = ext4_groups, .sysfs_ops = &ext4_attr_ops, .release = ext4_sb_release, }; -static struct kobj_type ext4_feat_ktype = { +static const struct kobj_type ext4_feat_ktype = { .default_groups = ext4_feat_groups, .sysfs_ops = &ext4_attr_ops, .release = ext4_feat_release, diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 62f2ec599218..767454d74cd6 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -2852,6 +2852,9 @@ shift: (void *)header, total_ino); EXT4_I(inode)->i_extra_isize = new_extra_isize; + if (ext4_has_inline_data(inode)) + error = ext4_find_inline_data_nolock(inode); + cleanup: if (error && (mnt_count != le16_to_cpu(sbi->s_es->s_mnt_count))) { ext4_warning(inode->i_sb, "Unable to expand inode %lu. Delete some EAs or run e2fsck.", diff --git a/fs/file.c b/fs/file.c index c942c89ca4cd..7893ea161d77 100644 --- a/fs/file.c +++ b/fs/file.c @@ -642,6 +642,7 @@ static struct file *pick_file(struct files_struct *files, unsigned fd) if (fd >= fdt->max_fds) return NULL; + fd = array_index_nospec(fd, fdt->max_fds); file = fdt->fd[fd]; if (file) { rcu_assign_pointer(fdt->fd[fd], NULL); diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 195dc23e0d83..1db3e3c24b43 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -978,6 +978,16 @@ restart: continue; } + /* + * If wb_tryget fails, the wb has been shutdown, skip it. + * + * Pin @wb so that it stays on @bdi->wb_list. This allows + * continuing iteration from @wb after dropping and + * regrabbing rcu read lock. + */ + if (!wb_tryget(wb)) + continue; + /* alloc failed, execute synchronously using on-stack fallback */ work = &fallback_work; *work = *base_work; @@ -986,13 +996,6 @@ restart: work->done = &fallback_work_done; wb_queue_work(wb, work); - - /* - * Pin @wb so that it stays on @bdi->wb_list. This allows - * continuing iteration from @wb after dropping and - * regrabbing rcu read lock. - */ - wb_get(wb); last_wb = wb; rcu_read_unlock(); diff --git a/fs/fuse/file.c b/fs/fuse/file.c index de37a3a06a71..89d97f6188e0 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1419,7 +1419,7 @@ out: static inline unsigned long fuse_get_user_addr(const struct iov_iter *ii) { - return (unsigned long)ii->iov->iov_base + ii->iov_offset; + return (unsigned long)iter_iov(ii)->iov_base + ii->iov_offset; } static inline size_t fuse_get_frag_size(const struct iov_iter *ii, diff --git a/fs/gfs2/dentry.c b/fs/gfs2/dentry.c index 6fe9ca253b70..2e215e8c3c88 100644 --- a/fs/gfs2/dentry.c +++ b/fs/gfs2/dentry.c @@ -83,8 +83,26 @@ static int gfs2_dhash(const struct dentry *dentry, struct qstr *str) return 0; } +static int gfs2_dentry_delete(const struct dentry *dentry) +{ + struct gfs2_inode *ginode; + + if (d_really_is_negative(dentry)) + return 0; + + ginode = GFS2_I(d_inode(dentry)); + if (!gfs2_holder_initialized(&ginode->i_iopen_gh)) + return 0; + + if (test_bit(GLF_DEMOTE, &ginode->i_iopen_gh.gh_gl->gl_flags)) + return 1; + + return 0; +} + const struct dentry_operations gfs2_dops = { .d_revalidate = gfs2_drevalidate, .d_hash = gfs2_dhash, + .d_delete = gfs2_dentry_delete, }; diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index e80c781731f8..8ae419152ff6 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -969,10 +969,13 @@ int jbd2_journal_bmap(journal_t *journal, unsigned long blocknr, { int err = 0; unsigned long long ret; - sector_t block = 0; + sector_t block = blocknr; - if (journal->j_inode) { - block = blocknr; + if (journal->j_bmap) { + err = journal->j_bmap(journal, &block); + if (err == 0) + *retp = block; + } else if (journal->j_inode) { ret = bmap(journal->j_inode, &block); if (ret || !block) { diff --git a/fs/ksmbd/auth.c b/fs/ksmbd/auth.c index 6e61b5bc7d86..cead696b656a 100644 --- a/fs/ksmbd/auth.c +++ b/fs/ksmbd/auth.c @@ -727,8 +727,9 @@ static int generate_key(struct ksmbd_conn *conn, struct ksmbd_session *sess, goto smb3signkey_ret; } - if (conn->cipher_type == SMB2_ENCRYPTION_AES256_CCM || - conn->cipher_type == SMB2_ENCRYPTION_AES256_GCM) + if (key_size == SMB3_ENC_DEC_KEY_SIZE && + (conn->cipher_type == SMB2_ENCRYPTION_AES256_CCM || + conn->cipher_type == SMB2_ENCRYPTION_AES256_GCM)) rc = crypto_shash_update(CRYPTO_HMACSHA256(ctx), L256, 4); else rc = crypto_shash_update(CRYPTO_HMACSHA256(ctx), L128, 4); diff --git a/fs/ksmbd/connection.c b/fs/ksmbd/connection.c index 5b10b03800c1..365ac32af505 100644 --- a/fs/ksmbd/connection.c +++ b/fs/ksmbd/connection.c @@ -112,10 +112,8 @@ void ksmbd_conn_enqueue_request(struct ksmbd_work *work) struct ksmbd_conn *conn = work->conn; struct list_head *requests_queue = NULL; - if (conn->ops->get_cmd_val(work) != SMB2_CANCEL_HE) { + if (conn->ops->get_cmd_val(work) != SMB2_CANCEL_HE) requests_queue = &conn->requests; - work->synchronous = true; - } if (requests_queue) { atomic_inc(&conn->req_running); @@ -136,14 +134,14 @@ int ksmbd_conn_try_dequeue_request(struct ksmbd_work *work) if (!work->multiRsp) atomic_dec(&conn->req_running); - spin_lock(&conn->request_lock); if (!work->multiRsp) { + spin_lock(&conn->request_lock); list_del_init(&work->request_entry); - if (!work->synchronous) - list_del_init(&work->async_request_entry); + spin_unlock(&conn->request_lock); + if (work->asynchronous) + release_async_work(work); ret = 0; } - spin_unlock(&conn->request_lock); wake_up_all(&conn->req_running_q); return ret; @@ -298,7 +296,7 @@ int ksmbd_conn_handler_loop(void *p) kvfree(conn->request_buf); conn->request_buf = NULL; - size = t->ops->read(t, hdr_buf, sizeof(hdr_buf)); + size = t->ops->read(t, hdr_buf, sizeof(hdr_buf), -1); if (size != sizeof(hdr_buf)) break; @@ -319,20 +317,14 @@ int ksmbd_conn_handler_loop(void *p) } /* - * Check if pdu size is valid (min : smb header size, - * max : 0x00FFFFFF). + * Check maximum pdu size(0x00FFFFFF). */ - if (pdu_size < __SMB2_HEADER_STRUCTURE_SIZE || - pdu_size > MAX_STREAM_PROT_LEN) { + if (pdu_size > MAX_STREAM_PROT_LEN) break; - } /* 4 for rfc1002 length field */ size = pdu_size + 4; - conn->request_buf = kvmalloc(size, - GFP_KERNEL | - __GFP_NOWARN | - __GFP_NORETRY); + conn->request_buf = kvmalloc(size, GFP_KERNEL); if (!conn->request_buf) break; @@ -344,7 +336,7 @@ int ksmbd_conn_handler_loop(void *p) * We already read 4 bytes to find out PDU size, now * read in PDU */ - size = t->ops->read(t, conn->request_buf + 4, pdu_size); + size = t->ops->read(t, conn->request_buf + 4, pdu_size, 2); if (size < 0) { pr_err("sock_read failed: %d\n", size); break; diff --git a/fs/ksmbd/connection.h b/fs/ksmbd/connection.h index 3643354a3fa7..0e3a848defaf 100644 --- a/fs/ksmbd/connection.h +++ b/fs/ksmbd/connection.h @@ -114,7 +114,8 @@ struct ksmbd_transport_ops { int (*prepare)(struct ksmbd_transport *t); void (*disconnect)(struct ksmbd_transport *t); void (*shutdown)(struct ksmbd_transport *t); - int (*read)(struct ksmbd_transport *t, char *buf, unsigned int size); + int (*read)(struct ksmbd_transport *t, char *buf, + unsigned int size, int max_retries); int (*writev)(struct ksmbd_transport *t, struct kvec *iovs, int niov, int size, bool need_invalidate_rkey, unsigned int remote_key); diff --git a/fs/ksmbd/ksmbd_work.h b/fs/ksmbd/ksmbd_work.h index 3234f2cf6327..f8ae6144c0ae 100644 --- a/fs/ksmbd/ksmbd_work.h +++ b/fs/ksmbd/ksmbd_work.h @@ -68,7 +68,7 @@ struct ksmbd_work { /* Request is encrypted */ bool encrypted:1; /* Is this SYNC or ASYNC ksmbd_work */ - bool synchronous:1; + bool asynchronous:1; bool need_invalidate_rkey:1; unsigned int remote_key; diff --git a/fs/ksmbd/server.c b/fs/ksmbd/server.c index 394b6ceac431..0d8242789dc8 100644 --- a/fs/ksmbd/server.c +++ b/fs/ksmbd/server.c @@ -289,10 +289,7 @@ static int queue_ksmbd_work(struct ksmbd_conn *conn) work->request_buf = conn->request_buf; conn->request_buf = NULL; - if (ksmbd_init_smb_server(work)) { - ksmbd_free_work_struct(work); - return -EINVAL; - } + ksmbd_init_smb_server(work); ksmbd_conn_enqueue_request(work); atomic_inc(&conn->r_count); diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 0685c1c77b9f..67b7e766a06b 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -229,9 +229,6 @@ int init_smb2_neg_rsp(struct ksmbd_work *work) struct smb2_negotiate_rsp *rsp; struct ksmbd_conn *conn = work->conn; - if (conn->need_neg == false) - return -EINVAL; - *(__be32 *)work->response_buf = cpu_to_be32(conn->vals->header_size); @@ -498,12 +495,6 @@ int init_smb2_rsp_hdr(struct ksmbd_work *work) rsp_hdr->SessionId = rcv_hdr->SessionId; memcpy(rsp_hdr->Signature, rcv_hdr->Signature, 16); - work->synchronous = true; - if (work->async_id) { - ksmbd_release_id(&conn->async_ida, work->async_id); - work->async_id = 0; - } - return 0; } @@ -644,7 +635,7 @@ int setup_async_work(struct ksmbd_work *work, void (*fn)(void **), void **arg) pr_err("Failed to alloc async message id\n"); return id; } - work->synchronous = false; + work->asynchronous = true; work->async_id = id; rsp_hdr->Id.AsyncId = cpu_to_le64(id); @@ -664,6 +655,24 @@ int setup_async_work(struct ksmbd_work *work, void (*fn)(void **), void **arg) return 0; } +void release_async_work(struct ksmbd_work *work) +{ + struct ksmbd_conn *conn = work->conn; + + spin_lock(&conn->request_lock); + list_del_init(&work->async_request_entry); + spin_unlock(&conn->request_lock); + + work->asynchronous = 0; + work->cancel_fn = NULL; + kfree(work->cancel_argv); + work->cancel_argv = NULL; + if (work->async_id) { + ksmbd_release_id(&conn->async_ida, work->async_id); + work->async_id = 0; + } +} + void smb2_send_interim_resp(struct ksmbd_work *work, __le32 status) { struct smb2_hdr *rsp_hdr; @@ -867,17 +876,21 @@ static void assemble_neg_contexts(struct ksmbd_conn *conn, } static __le32 decode_preauth_ctxt(struct ksmbd_conn *conn, - struct smb2_preauth_neg_context *pneg_ctxt) + struct smb2_preauth_neg_context *pneg_ctxt, + int len_of_ctxts) { - __le32 err = STATUS_NO_PREAUTH_INTEGRITY_HASH_OVERLAP; + /* + * sizeof(smb2_preauth_neg_context) assumes SMB311_SALT_SIZE Salt, + * which may not be present. Only check for used HashAlgorithms[1]. + */ + if (len_of_ctxts < MIN_PREAUTH_CTXT_DATA_LEN) + return STATUS_INVALID_PARAMETER; - if (pneg_ctxt->HashAlgorithms == SMB2_PREAUTH_INTEGRITY_SHA512) { - conn->preauth_info->Preauth_HashId = - SMB2_PREAUTH_INTEGRITY_SHA512; - err = STATUS_SUCCESS; - } + if (pneg_ctxt->HashAlgorithms != SMB2_PREAUTH_INTEGRITY_SHA512) + return STATUS_NO_PREAUTH_INTEGRITY_HASH_OVERLAP; - return err; + conn->preauth_info->Preauth_HashId = SMB2_PREAUTH_INTEGRITY_SHA512; + return STATUS_SUCCESS; } static void decode_encrypt_ctxt(struct ksmbd_conn *conn, @@ -1005,7 +1018,8 @@ static __le32 deassemble_neg_contexts(struct ksmbd_conn *conn, break; status = decode_preauth_ctxt(conn, - (struct smb2_preauth_neg_context *)pctx); + (struct smb2_preauth_neg_context *)pctx, + len_of_ctxts); if (status != STATUS_SUCCESS) break; } else if (pctx->ContextType == SMB2_ENCRYPTION_CAPABILITIES) { @@ -2977,8 +2991,11 @@ int smb2_open(struct ksmbd_work *work) sizeof(struct smb_acl) + sizeof(struct smb_ace) * ace_num * 2, GFP_KERNEL); - if (!pntsd) + if (!pntsd) { + posix_acl_release(fattr.cf_acls); + posix_acl_release(fattr.cf_dacls); goto err_out; + } rc = build_sec_desc(idmap, pntsd, NULL, 0, @@ -4934,6 +4951,10 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, info->Attributes |= cpu_to_le32(server_conf.share_fake_fscaps); + if (test_share_config_flag(work->tcon->share_conf, + KSMBD_SHARE_FLAG_STREAMS)) + info->Attributes |= cpu_to_le32(FILE_NAMED_STREAMS); + info->MaxPathNameComponentLength = cpu_to_le32(stfs.f_namelen); len = smbConvertToUTF16((__le16 *)info->FileSystemName, "NTFS", PATH_MAX, conn->local_nls, 0); @@ -7038,13 +7059,9 @@ skip: ksmbd_vfs_posix_lock_wait(flock); - spin_lock(&work->conn->request_lock); spin_lock(&fp->f_lock); list_del(&work->fp_entry); - work->cancel_fn = NULL; - kfree(argv); spin_unlock(&fp->f_lock); - spin_unlock(&work->conn->request_lock); if (work->state != KSMBD_WORK_ACTIVE) { list_del(&smb_lock->llist); @@ -7062,6 +7079,7 @@ skip: work->send_no_response = 1; goto out; } + init_smb2_rsp_hdr(work); smb2_set_err_rsp(work); rsp->hdr.Status = @@ -7074,7 +7092,7 @@ skip: spin_lock(&work->conn->llist_lock); list_del(&smb_lock->clist); spin_unlock(&work->conn->llist_lock); - + release_async_work(work); goto retry; } else if (!rc) { spin_lock(&work->conn->llist_lock); @@ -7444,13 +7462,16 @@ static int fsctl_query_allocated_ranges(struct ksmbd_work *work, u64 id, if (in_count == 0) return -EINVAL; + start = le64_to_cpu(qar_req->file_offset); + length = le64_to_cpu(qar_req->length); + + if (start < 0 || length < 0) + return -EINVAL; + fp = ksmbd_lookup_fd_fast(work, id); if (!fp) return -ENOENT; - start = le64_to_cpu(qar_req->file_offset); - length = le64_to_cpu(qar_req->length); - ret = ksmbd_vfs_fqar_lseek(fp, start, length, qar_rsp, in_count, out_count); if (ret && ret != -E2BIG) @@ -7751,7 +7772,7 @@ int smb2_ioctl(struct ksmbd_work *work) off = le64_to_cpu(zero_data->FileOffset); bfz = le64_to_cpu(zero_data->BeyondFinalZero); - if (off > bfz) { + if (off < 0 || bfz < 0 || off > bfz) { ret = -EINVAL; goto out; } diff --git a/fs/ksmbd/smb2pdu.h b/fs/ksmbd/smb2pdu.h index 0c8a770fe318..9420dd2813fb 100644 --- a/fs/ksmbd/smb2pdu.h +++ b/fs/ksmbd/smb2pdu.h @@ -486,6 +486,7 @@ int find_matching_smb2_dialect(int start_index, __le16 *cli_dialects, struct file_lock *smb_flock_init(struct file *f); int setup_async_work(struct ksmbd_work *work, void (*fn)(void **), void **arg); +void release_async_work(struct ksmbd_work *work); void smb2_send_interim_resp(struct ksmbd_work *work, __le32 status); struct channel *lookup_chann_list(struct ksmbd_session *sess, struct ksmbd_conn *conn); diff --git a/fs/ksmbd/smb_common.c b/fs/ksmbd/smb_common.c index fa2b54df6ee6..af0c2a9b8529 100644 --- a/fs/ksmbd/smb_common.c +++ b/fs/ksmbd/smb_common.c @@ -283,20 +283,121 @@ err_out: return BAD_PROT_ID; } -int ksmbd_init_smb_server(struct ksmbd_work *work) +#define SMB_COM_NEGOTIATE_EX 0x0 + +/** + * get_smb1_cmd_val() - get smb command value from smb header + * @work: smb work containing smb header + * + * Return: smb command value + */ +static u16 get_smb1_cmd_val(struct ksmbd_work *work) { - struct ksmbd_conn *conn = work->conn; + return SMB_COM_NEGOTIATE_EX; +} - if (conn->need_neg == false) +/** + * init_smb1_rsp_hdr() - initialize smb negotiate response header + * @work: smb work containing smb request + * + * Return: 0 on success, otherwise -EINVAL + */ +static int init_smb1_rsp_hdr(struct ksmbd_work *work) +{ + struct smb_hdr *rsp_hdr = (struct smb_hdr *)work->response_buf; + struct smb_hdr *rcv_hdr = (struct smb_hdr *)work->request_buf; + + /* + * Remove 4 byte direct TCP header. + */ + *(__be32 *)work->response_buf = + cpu_to_be32(sizeof(struct smb_hdr) - 4); + + rsp_hdr->Command = SMB_COM_NEGOTIATE; + *(__le32 *)rsp_hdr->Protocol = SMB1_PROTO_NUMBER; + rsp_hdr->Flags = SMBFLG_RESPONSE; + rsp_hdr->Flags2 = SMBFLG2_UNICODE | SMBFLG2_ERR_STATUS | + SMBFLG2_EXT_SEC | SMBFLG2_IS_LONG_NAME; + rsp_hdr->Pid = rcv_hdr->Pid; + rsp_hdr->Mid = rcv_hdr->Mid; + return 0; +} + +/** + * smb1_check_user_session() - check for valid session for a user + * @work: smb work containing smb request buffer + * + * Return: 0 on success, otherwise error + */ +static int smb1_check_user_session(struct ksmbd_work *work) +{ + unsigned int cmd = work->conn->ops->get_cmd_val(work); + + if (cmd == SMB_COM_NEGOTIATE_EX) return 0; - init_smb3_11_server(conn); + return -EINVAL; +} + +/** + * smb1_allocate_rsp_buf() - allocate response buffer for a command + * @work: smb work containing smb request + * + * Return: 0 on success, otherwise -ENOMEM + */ +static int smb1_allocate_rsp_buf(struct ksmbd_work *work) +{ + work->response_buf = kmalloc(MAX_CIFS_SMALL_BUFFER_SIZE, + GFP_KERNEL | __GFP_ZERO); + work->response_sz = MAX_CIFS_SMALL_BUFFER_SIZE; + + if (!work->response_buf) { + pr_err("Failed to allocate %u bytes buffer\n", + MAX_CIFS_SMALL_BUFFER_SIZE); + return -ENOMEM; + } - if (conn->ops->get_cmd_val(work) != SMB_COM_NEGOTIATE) - conn->need_neg = false; return 0; } +static struct smb_version_ops smb1_server_ops = { + .get_cmd_val = get_smb1_cmd_val, + .init_rsp_hdr = init_smb1_rsp_hdr, + .allocate_rsp_buf = smb1_allocate_rsp_buf, + .check_user_session = smb1_check_user_session, +}; + +static int smb1_negotiate(struct ksmbd_work *work) +{ + return ksmbd_smb_negotiate_common(work, SMB_COM_NEGOTIATE); +} + +static struct smb_version_cmds smb1_server_cmds[1] = { + [SMB_COM_NEGOTIATE_EX] = { .proc = smb1_negotiate, }, +}; + +static void init_smb1_server(struct ksmbd_conn *conn) +{ + conn->ops = &smb1_server_ops; + conn->cmds = smb1_server_cmds; + conn->max_cmds = ARRAY_SIZE(smb1_server_cmds); +} + +void ksmbd_init_smb_server(struct ksmbd_work *work) +{ + struct ksmbd_conn *conn = work->conn; + __le32 proto; + + if (conn->need_neg == false) + return; + + proto = *(__le32 *)((struct smb_hdr *)work->request_buf)->Protocol; + if (proto == SMB1_PROTO_NUMBER) + init_smb1_server(conn); + else + init_smb3_11_server(conn); +} + int ksmbd_populate_dot_dotdot_entries(struct ksmbd_work *work, int info_level, struct ksmbd_file *dir, struct ksmbd_dir_info *d_info, @@ -434,7 +535,7 @@ int ksmbd_extract_shortname(struct ksmbd_conn *conn, const char *longname, static int __smb2_negotiate(struct ksmbd_conn *conn) { - return (conn->dialect >= SMB21_PROT_ID && + return (conn->dialect >= SMB20_PROT_ID && conn->dialect <= SMB311_PROT_ID); } @@ -442,9 +543,16 @@ static int smb_handle_negotiate(struct ksmbd_work *work) { struct smb_negotiate_rsp *neg_rsp = work->response_buf; - ksmbd_debug(SMB, "Unsupported SMB protocol\n"); - neg_rsp->hdr.Status.CifsError = STATUS_INVALID_LOGON_TYPE; - return -EINVAL; + ksmbd_debug(SMB, "Unsupported SMB1 protocol\n"); + + /* Add 2 byte bcc and 2 byte DialectIndex. */ + inc_rfc1001_len(work->response_buf, 4); + neg_rsp->hdr.Status.CifsError = STATUS_SUCCESS; + + neg_rsp->hdr.WordCount = 1; + neg_rsp->DialectIndex = cpu_to_le16(work->conn->dialect); + neg_rsp->ByteCount = 0; + return 0; } int ksmbd_smb_negotiate_common(struct ksmbd_work *work, unsigned int command) @@ -457,23 +565,12 @@ int ksmbd_smb_negotiate_common(struct ksmbd_work *work, unsigned int command) ksmbd_debug(SMB, "conn->dialect 0x%x\n", conn->dialect); if (command == SMB2_NEGOTIATE_HE) { - struct smb2_hdr *smb2_hdr = smb2_get_msg(work->request_buf); - - if (smb2_hdr->ProtocolId != SMB2_PROTO_NUMBER) { - ksmbd_debug(SMB, "Downgrade to SMB1 negotiation\n"); - command = SMB_COM_NEGOTIATE; - } - } - - if (command == SMB2_NEGOTIATE_HE && __smb2_negotiate(conn)) { ret = smb2_handle_negotiate(work); - init_smb2_neg_rsp(work); return ret; } if (command == SMB_COM_NEGOTIATE) { if (__smb2_negotiate(conn)) { - conn->need_neg = true; init_smb3_11_server(conn); init_smb2_neg_rsp(work); ksmbd_debug(SMB, "Upgrade to SMB2 negotiation\n"); diff --git a/fs/ksmbd/smb_common.h b/fs/ksmbd/smb_common.h index e663ab9ea759..9130d2e3cd78 100644 --- a/fs/ksmbd/smb_common.h +++ b/fs/ksmbd/smb_common.h @@ -158,8 +158,15 @@ #define SMB1_PROTO_NUMBER cpu_to_le32(0x424d53ff) #define SMB_COM_NEGOTIATE 0x72 - #define SMB1_CLIENT_GUID_SIZE (16) + +#define SMBFLG_RESPONSE 0x80 /* this PDU is a response from server */ + +#define SMBFLG2_IS_LONG_NAME cpu_to_le16(0x40) +#define SMBFLG2_EXT_SEC cpu_to_le16(0x800) +#define SMBFLG2_ERR_STATUS cpu_to_le16(0x4000) +#define SMBFLG2_UNICODE cpu_to_le16(0x8000) + struct smb_hdr { __be32 smb_buf_length; __u8 Protocol[4]; @@ -199,28 +206,7 @@ struct smb_negotiate_req { struct smb_negotiate_rsp { struct smb_hdr hdr; /* wct = 17 */ __le16 DialectIndex; /* 0xFFFF = no dialect acceptable */ - __u8 SecurityMode; - __le16 MaxMpxCount; - __le16 MaxNumberVcs; - __le32 MaxBufferSize; - __le32 MaxRawSize; - __le32 SessionKey; - __le32 Capabilities; /* see below */ - __le32 SystemTimeLow; - __le32 SystemTimeHigh; - __le16 ServerTimeZone; - __u8 EncryptionKeyLength; __le16 ByteCount; - union { - unsigned char EncryptionKey[8]; /* cap extended security off */ - /* followed by Domain name - if extended security is off */ - /* followed by 16 bytes of server GUID */ - /* then security blob if cap_extended_security negotiated */ - struct { - unsigned char GUID[SMB1_CLIENT_GUID_SIZE]; - unsigned char SecurityBlob[1]; - } __packed extended_response; - } __packed u; } __packed; struct filesystem_attribute_info { @@ -441,7 +427,7 @@ bool ksmbd_smb_request(struct ksmbd_conn *conn); int ksmbd_lookup_dialect_by_id(__le16 *cli_dialects, __le16 dialects_count); -int ksmbd_init_smb_server(struct ksmbd_work *work); +void ksmbd_init_smb_server(struct ksmbd_work *work); struct ksmbd_kstat; int ksmbd_populate_dot_dotdot_entries(struct ksmbd_work *work, diff --git a/fs/ksmbd/transport_rdma.c b/fs/ksmbd/transport_rdma.c index 096eda9ef873..c06efc020bd9 100644 --- a/fs/ksmbd/transport_rdma.c +++ b/fs/ksmbd/transport_rdma.c @@ -670,7 +670,7 @@ static int smb_direct_post_recv(struct smb_direct_transport *t, } static int smb_direct_read(struct ksmbd_transport *t, char *buf, - unsigned int size) + unsigned int size, int unused) { struct smb_direct_recvmsg *recvmsg; struct smb_direct_data_transfer *data_transfer; diff --git a/fs/ksmbd/transport_tcp.c b/fs/ksmbd/transport_tcp.c index 603893fd87f5..20e85e2701f2 100644 --- a/fs/ksmbd/transport_tcp.c +++ b/fs/ksmbd/transport_tcp.c @@ -291,16 +291,18 @@ static int ksmbd_tcp_run_kthread(struct interface *iface) /** * ksmbd_tcp_readv() - read data from socket in given iovec - * @t: TCP transport instance - * @iov_orig: base IO vector - * @nr_segs: number of segments in base iov - * @to_read: number of bytes to read from socket + * @t: TCP transport instance + * @iov_orig: base IO vector + * @nr_segs: number of segments in base iov + * @to_read: number of bytes to read from socket + * @max_retries: maximum retry count * * Return: on success return number of bytes read from socket, * otherwise return error number */ static int ksmbd_tcp_readv(struct tcp_transport *t, struct kvec *iov_orig, - unsigned int nr_segs, unsigned int to_read) + unsigned int nr_segs, unsigned int to_read, + int max_retries) { int length = 0; int total_read; @@ -308,7 +310,6 @@ static int ksmbd_tcp_readv(struct tcp_transport *t, struct kvec *iov_orig, struct msghdr ksmbd_msg; struct kvec *iov; struct ksmbd_conn *conn = KSMBD_TRANS(t)->conn; - int max_retry = 2; iov = get_conn_iovec(t, nr_segs); if (!iov) @@ -335,14 +336,23 @@ static int ksmbd_tcp_readv(struct tcp_transport *t, struct kvec *iov_orig, } else if (conn->status == KSMBD_SESS_NEED_RECONNECT) { total_read = -EAGAIN; break; - } else if ((length == -ERESTARTSYS || length == -EAGAIN) && - max_retry) { + } else if (length == -ERESTARTSYS || length == -EAGAIN) { + /* + * If max_retries is negative, Allow unlimited + * retries to keep connection with inactive sessions. + */ + if (max_retries == 0) { + total_read = length; + break; + } else if (max_retries > 0) { + max_retries--; + } + usleep_range(1000, 2000); length = 0; - max_retry--; continue; } else if (length <= 0) { - total_read = -EAGAIN; + total_read = length; break; } } @@ -358,14 +368,15 @@ static int ksmbd_tcp_readv(struct tcp_transport *t, struct kvec *iov_orig, * Return: on success return number of bytes read from socket, * otherwise return error number */ -static int ksmbd_tcp_read(struct ksmbd_transport *t, char *buf, unsigned int to_read) +static int ksmbd_tcp_read(struct ksmbd_transport *t, char *buf, + unsigned int to_read, int max_retries) { struct kvec iov; iov.iov_base = buf; iov.iov_len = to_read; - return ksmbd_tcp_readv(TCP_TRANS(t), &iov, 1, to_read); + return ksmbd_tcp_readv(TCP_TRANS(t), &iov, 1, to_read, max_retries); } static int ksmbd_tcp_writev(struct ksmbd_transport *t, struct kvec *iov, diff --git a/fs/ksmbd/unicode.c b/fs/ksmbd/unicode.c index a0db699ddafd..9ae676906ed3 100644 --- a/fs/ksmbd/unicode.c +++ b/fs/ksmbd/unicode.c @@ -114,24 +114,6 @@ cp_convert: } /* - * is_char_allowed() - check for valid character - * @ch: input character to be checked - * - * Return: 1 if char is allowed, otherwise 0 - */ -static inline int is_char_allowed(char *ch) -{ - /* check for control chars, wildcards etc. */ - if (!(*ch & 0x80) && - (*ch <= 0x1f || - *ch == '?' || *ch == '"' || *ch == '<' || - *ch == '>' || *ch == '|')) - return 0; - - return 1; -} - -/* * smb_from_utf16() - convert utf16le string to local charset * @to: destination buffer * @from: source buffer diff --git a/fs/lockd/clnt4xdr.c b/fs/lockd/clnt4xdr.c index 7df6324ccb8a..8161667c976f 100644 --- a/fs/lockd/clnt4xdr.c +++ b/fs/lockd/clnt4xdr.c @@ -261,7 +261,6 @@ static int decode_nlm4_holder(struct xdr_stream *xdr, struct nlm_res *result) u32 exclusive; int error; __be32 *p; - s32 end; memset(lock, 0, sizeof(*lock)); locks_init_lock(fl); @@ -285,13 +284,7 @@ static int decode_nlm4_holder(struct xdr_stream *xdr, struct nlm_res *result) fl->fl_type = exclusive != 0 ? F_WRLCK : F_RDLCK; p = xdr_decode_hyper(p, &l_offset); xdr_decode_hyper(p, &l_len); - end = l_offset + l_len - 1; - - fl->fl_start = (loff_t)l_offset; - if (l_len == 0 || end < 0) - fl->fl_end = OFFSET_MAX; - else - fl->fl_end = (loff_t)end; + nlm4svc_set_file_lock_range(fl, l_offset, l_len); error = 0; out: return error; diff --git a/fs/lockd/xdr4.c b/fs/lockd/xdr4.c index 712fdfeb8ef0..5fcbf30cd275 100644 --- a/fs/lockd/xdr4.c +++ b/fs/lockd/xdr4.c @@ -33,6 +33,17 @@ loff_t_to_s64(loff_t offset) return res; } +void nlm4svc_set_file_lock_range(struct file_lock *fl, u64 off, u64 len) +{ + s64 end = off + len - 1; + + fl->fl_start = off; + if (len == 0 || end < 0) + fl->fl_end = OFFSET_MAX; + else + fl->fl_end = end; +} + /* * NLM file handles are defined by specification to be a variable-length * XDR opaque no longer than 1024 bytes. However, this implementation @@ -80,7 +91,7 @@ svcxdr_decode_lock(struct xdr_stream *xdr, struct nlm_lock *lock) locks_init_lock(fl); fl->fl_flags = FL_POSIX; fl->fl_type = F_RDLCK; - + nlm4svc_set_file_lock_range(fl, lock->lock_start, lock->lock_len); return true; } diff --git a/fs/locks.c b/fs/locks.c index 66b4eef09db5..df8b26a42524 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1863,9 +1863,10 @@ int generic_setlease(struct file *filp, long arg, struct file_lock **flp, void **priv) { struct inode *inode = file_inode(filp); + vfsuid_t vfsuid = i_uid_into_vfsuid(file_mnt_idmap(filp), inode); int error; - if ((!uid_eq(current_fsuid(), inode->i_uid)) && !capable(CAP_LEASE)) + if ((!vfsuid_eq_kuid(vfsuid, current_fsuid())) && !capable(CAP_LEASE)) return -EACCES; if (!S_ISREG(inode->i_mode)) return -EINVAL; @@ -2425,7 +2426,6 @@ int fcntl_getlk64(struct file *filp, unsigned int cmd, struct flock64 *flock) if (flock->l_pid != 0) goto out; - cmd = F_GETLK64; fl->fl_flags |= FL_OFDLCK; fl->fl_owner = filp; } diff --git a/fs/namespace.c b/fs/namespace.c index bc0f15257b49..6836e937ee61 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -4183,9 +4183,9 @@ out: unlock_mount_hash(); if (kattr->propagation) { - namespace_unlock(); if (err) cleanup_group_ids(mnt, NULL); + namespace_unlock(); } return err; diff --git a/fs/netfs/iterator.c b/fs/netfs/iterator.c index e9a45dea748a..8a4c86687429 100644 --- a/fs/netfs/iterator.c +++ b/fs/netfs/iterator.c @@ -139,7 +139,7 @@ static ssize_t netfs_extract_user_to_sg(struct iov_iter *iter, size_t seg = min_t(size_t, PAGE_SIZE - off, len); *pages++ = NULL; - sg_set_page(sg, page, len, off); + sg_set_page(sg, page, seg, off); sgtable->nents++; sg++; len -= seg; diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index 14a72224b657..c1c7ed2fd860 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -75,7 +75,6 @@ config NFS_V3_ACL config NFS_V4 tristate "NFS client support for NFS version 4" depends on NFS_FS - select SUNRPC_GSS select KEYS help This option enables support for version 4 of the NFS protocol diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index a41c3ee4549c..6fbcbb8d6587 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -3089,7 +3089,6 @@ static void nfs_access_add_rbtree(struct inode *inode, else goto found; } - set->timestamp = ktime_get_ns(); rb_link_node(&set->rb_node, parent, p); rb_insert_color(&set->rb_node, root_node); list_add_tail(&set->lru, &nfsi->access_cache_entry_lru); @@ -3114,6 +3113,7 @@ void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set, cache->fsgid = cred->fsgid; cache->group_info = get_group_info(cred->group_info); cache->mask = set->mask; + cache->timestamp = ktime_get_ns(); /* The above field assignments must be visible * before this item appears on the lru. We cannot easily diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 22a93ae46cd7..5607b1e2b821 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1980,8 +1980,7 @@ _nfs4_opendata_reclaim_to_nfs4_state(struct nfs4_opendata *data) if (!data->rpc_done) { if (data->rpc_status) return ERR_PTR(data->rpc_status); - /* cached opens have already been processed */ - goto update; + return nfs4_try_open_cached(data); } ret = nfs_refresh_inode(inode, &data->f_attr); @@ -1990,7 +1989,7 @@ _nfs4_opendata_reclaim_to_nfs4_state(struct nfs4_opendata *data) if (data->o_res.delegation_type != 0) nfs4_opendata_check_deleg(data, state); -update: + if (!update_open_stateid(state, &data->o_res.stateid, NULL, data->o_arg.fmode)) return ERR_PTR(-EAGAIN); diff --git a/fs/nfs/read.c b/fs/nfs/read.c index c380cff4108e..e90988591df4 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -15,6 +15,7 @@ #include <linux/stat.h> #include <linux/mm.h> #include <linux/slab.h> +#include <linux/task_io_accounting_ops.h> #include <linux/pagemap.h> #include <linux/sunrpc/clnt.h> #include <linux/nfs_fs.h> @@ -337,6 +338,7 @@ int nfs_read_folio(struct file *file, struct folio *folio) trace_nfs_aop_readpage(inode, folio); nfs_inc_stats(inode, NFSIOS_VFSREADPAGE); + task_io_account_read(folio_size(folio)); /* * Try to flush any pending writes to the file.. @@ -393,6 +395,7 @@ void nfs_readahead(struct readahead_control *ractl) trace_nfs_aop_readahead(inode, readahead_pos(ractl), nr_pages); nfs_inc_stats(inode, NFSIOS_VFSREADPAGES); + task_io_account_read(readahead_length(ractl)); ret = -ESTALE; if (NFS_STALE(inode)) diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig index 7c441f2bd444..43b88eaf0673 100644 --- a/fs/nfsd/Kconfig +++ b/fs/nfsd/Kconfig @@ -73,7 +73,7 @@ config NFSD_V4 bool "NFS server support for NFS version 4" depends on NFSD && PROC_FS select FS_POSIX_ACL - select SUNRPC_GSS + select RPCSEC_GSS_KRB5 select CRYPTO select CRYPTO_MD5 select CRYPTO_SHA256 diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c index 04697f8dc37d..01d7fd108cf3 100644 --- a/fs/nfsd/blocklayout.c +++ b/fs/nfsd/blocklayout.c @@ -297,6 +297,7 @@ nfsd4_block_get_device_info_scsi(struct super_block *sb, out_free_dev: kfree(dev); + gdp->gd_device = NULL; return ret; } diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 2a815f5a52c4..4039ffcf90ba 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -946,8 +946,8 @@ static const struct cred *get_backchannel_cred(struct nfs4_client *clp, struct r if (!kcred) return NULL; - kcred->uid = ses->se_cb_sec.uid; - kcred->gid = ses->se_cb_sec.gid; + kcred->fsuid = ses->se_cb_sec.uid; + kcred->fsgid = ses->se_cb_sec.gid; return kcred; } } diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index e12e5a4ad502..e2e485167ac4 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -2476,10 +2476,12 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) for (i = 0; i < argp->opcnt; i++) { op = &argp->ops[i]; op->replay = NULL; + op->opdesc = NULL; if (xdr_stream_decode_u32(argp->xdr, &op->opnum) < 0) return false; if (nfsd4_opnum_in_range(argp, op)) { + op->opdesc = OPDESC(op); op->status = nfsd4_dec_ops[op->opnum](argp, &op->u); if (op->status != nfs_ok) trace_nfsd_compound_decode_err(argp->rqstp, @@ -2490,7 +2492,7 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) op->opnum = OP_ILLEGAL; op->status = nfserr_op_illegal; } - op->opdesc = OPDESC(op); + /* * We'll try to cache the result in the DRC if any one * op in the compound wants to be cached: @@ -5400,10 +5402,8 @@ nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op) __be32 *p; p = xdr_reserve_space(xdr, 8); - if (!p) { - WARN_ON_ONCE(1); - return; - } + if (!p) + goto release; *p++ = cpu_to_be32(op->opnum); post_err_offset = xdr->buf->len; @@ -5418,8 +5418,6 @@ nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op) op->status = encoder(resp, op->status, &op->u); if (op->status) trace_nfsd_compound_encode_err(rqstp, op->opnum, op->status); - if (opdesc && opdesc->op_release) - opdesc->op_release(&op->u); xdr_commit_encode(xdr); /* nfsd4_check_resp_size guarantees enough room for error status */ @@ -5460,6 +5458,9 @@ nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op) } status: *p = op->status; +release: + if (opdesc && opdesc->op_release) + opdesc->op_release(&op->u); } /* diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index e7462b5e5f1e..5783209f17fc 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -941,8 +941,15 @@ nfsd_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf, struct page *last_page; last_page = page + (offset + sd->len - 1) / PAGE_SIZE; - for (page += offset / PAGE_SIZE; page <= last_page; page++) + for (page += offset / PAGE_SIZE; page <= last_page; page++) { + /* + * Skip page replacement when extending the contents + * of the current page. + */ + if (page == *(rqstp->rq_next_page - 1)) + continue; svc_rqst_replace_page(rqstp, page); + } if (rqstp->rq_res.page_len == 0) // first call rqstp->rq_res.page_base = offset % PAGE_SIZE; rqstp->rq_res.page_len += sd->len; @@ -1104,7 +1111,9 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf, since = READ_ONCE(file->f_wb_err); if (verf) nfsd_copy_write_verifier(verf, nn); + file_start_write(file); host_err = vfs_iter_write(file, &iter, &pos, flags); + file_end_write(file); if (host_err < 0) { nfsd_reset_write_verifier(nn); trace_nfsd_writeverf_reset(nn, rqstp, host_err); diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index 2681a449edc1..13592e82eaf6 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -2219,6 +2219,7 @@ static int nilfs_btree_assign_p(struct nilfs_bmap *btree, /* on-disk format */ binfo->bi_dat.bi_blkoff = cpu_to_le64(key); binfo->bi_dat.bi_level = level; + memset(binfo->bi_dat.bi_pad, 0, sizeof(binfo->bi_dat.bi_pad)); return 0; } diff --git a/fs/nilfs2/direct.c b/fs/nilfs2/direct.c index a35f2795b242..4c85914f2abc 100644 --- a/fs/nilfs2/direct.c +++ b/fs/nilfs2/direct.c @@ -314,6 +314,7 @@ static int nilfs_direct_assign_p(struct nilfs_bmap *direct, binfo->bi_dat.bi_blkoff = cpu_to_le64(key); binfo->bi_dat.bi_level = 0; + memset(binfo->bi_dat.bi_pad, 0, sizeof(binfo->bi_dat.bi_pad)); return 0; } diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c index 5ccc638ae92f..1dfbc0c34513 100644 --- a/fs/nilfs2/ioctl.c +++ b/fs/nilfs2/ioctl.c @@ -71,7 +71,7 @@ static int nilfs_ioctl_wrap_copy(struct the_nilfs *nilfs, if (argv->v_index > ~(__u64)0 - argv->v_nmembs) return -EINVAL; - buf = (void *)__get_free_pages(GFP_NOFS, 0); + buf = (void *)get_zeroed_page(GFP_NOFS); if (unlikely(!buf)) return -ENOMEM; maxmembs = PAGE_SIZE / argv->v_size; diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 19446a8243d7..228659612c0d 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -430,6 +430,23 @@ static int nilfs_segctor_reset_segment_buffer(struct nilfs_sc_info *sci) return 0; } +/** + * nilfs_segctor_zeropad_segsum - zero pad the rest of the segment summary area + * @sci: segment constructor object + * + * nilfs_segctor_zeropad_segsum() zero-fills unallocated space at the end of + * the current segment summary block. + */ +static void nilfs_segctor_zeropad_segsum(struct nilfs_sc_info *sci) +{ + struct nilfs_segsum_pointer *ssp; + + ssp = sci->sc_blk_cnt > 0 ? &sci->sc_binfo_ptr : &sci->sc_finfo_ptr; + if (ssp->offset < ssp->bh->b_size) + memset(ssp->bh->b_data + ssp->offset, 0, + ssp->bh->b_size - ssp->offset); +} + static int nilfs_segctor_feed_segment(struct nilfs_sc_info *sci) { sci->sc_nblk_this_inc += sci->sc_curseg->sb_sum.nblocks; @@ -438,6 +455,7 @@ static int nilfs_segctor_feed_segment(struct nilfs_sc_info *sci) * The current segment is filled up * (internal code) */ + nilfs_segctor_zeropad_segsum(sci); sci->sc_curseg = NILFS_NEXT_SEGBUF(sci->sc_curseg); return nilfs_segctor_reset_segment_buffer(sci); } @@ -542,6 +560,7 @@ static int nilfs_segctor_add_file_block(struct nilfs_sc_info *sci, goto retry; } if (unlikely(required)) { + nilfs_segctor_zeropad_segsum(sci); err = nilfs_segbuf_extend_segsum(segbuf); if (unlikely(err)) goto failed; @@ -1533,6 +1552,7 @@ static int nilfs_segctor_collect(struct nilfs_sc_info *sci, nadd = min_t(int, nadd << 1, SC_MAX_SEGDELTA); sci->sc_stage = prev_stage; } + nilfs_segctor_zeropad_segsum(sci); nilfs_segctor_truncate_segments(sci, sci->sc_curseg, nilfs->ns_sufile); return 0; @@ -2609,11 +2629,10 @@ static int nilfs_segctor_thread(void *arg) goto loop; end_thread: - spin_unlock(&sci->sc_state_lock); - /* end sync. */ sci->sc_task = NULL; wake_up(&sci->sc_wait_task); /* for nilfs_segctor_kill_thread() */ + spin_unlock(&sci->sc_state_lock); return 0; } diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 1422b8ba24ed..77f1e5778d1c 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -482,6 +482,7 @@ static void nilfs_put_super(struct super_block *sb) up_write(&nilfs->ns_sem); } + nilfs_sysfs_delete_device_group(nilfs); iput(nilfs->ns_sufile); iput(nilfs->ns_cpfile); iput(nilfs->ns_dat); @@ -1105,6 +1106,7 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent) nilfs_put_root(fsroot); failed_unload: + nilfs_sysfs_delete_device_group(nilfs); iput(nilfs->ns_sufile); iput(nilfs->ns_cpfile); iput(nilfs->ns_dat); diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index 3a4c9c150cbf..2894152a6b25 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -87,7 +87,6 @@ void destroy_nilfs(struct the_nilfs *nilfs) { might_sleep(); if (nilfs_init(nilfs)) { - nilfs_sysfs_delete_device_group(nilfs); brelse(nilfs->ns_sbh[0]); brelse(nilfs->ns_sbh[1]); } @@ -305,6 +304,10 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb) goto failed; } + err = nilfs_sysfs_create_device_group(sb); + if (unlikely(err)) + goto sysfs_error; + if (valid_fs) goto skip_recovery; @@ -366,6 +369,9 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb) goto failed; failed_unload: + nilfs_sysfs_delete_device_group(nilfs); + + sysfs_error: iput(nilfs->ns_cpfile); iput(nilfs->ns_sufile); iput(nilfs->ns_dat); @@ -697,10 +703,6 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data) if (err) goto failed_sbh; - err = nilfs_sysfs_create_device_group(sb); - if (err) - goto failed_sbh; - set_nilfs_init(nilfs); err = 0; out: diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 1d65f6ef00ca..0394505fdce3 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -1977,11 +1977,26 @@ int ocfs2_write_end_nolock(struct address_space *mapping, } if (unlikely(copied < len) && wc->w_target_page) { + loff_t new_isize; + if (!PageUptodate(wc->w_target_page)) copied = 0; - ocfs2_zero_new_buffers(wc->w_target_page, start+copied, - start+len); + new_isize = max_t(loff_t, i_size_read(inode), pos + copied); + if (new_isize > page_offset(wc->w_target_page)) + ocfs2_zero_new_buffers(wc->w_target_page, start+copied, + start+len); + else { + /* + * When page is fully beyond new isize (data copy + * failed), do not bother zeroing the page. Invalidate + * it instead so that writeback does not get confused + * put page & buffer dirty bits into inconsistent + * state. + */ + block_invalidate_folio(page_folio(wc->w_target_page), + 0, PAGE_SIZE); + } } if (wc->w_target_page) flush_dcache_page(wc->w_target_page); diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 9175dbc47201..17c52225b87d 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -242,6 +242,7 @@ static int ocfs2_mknod(struct mnt_idmap *idmap, int want_meta = 0; int xattr_credits = 0; struct ocfs2_security_xattr_info si = { + .name = NULL, .enable = 1, }; int did_quota_inode = 0; @@ -1805,6 +1806,7 @@ static int ocfs2_symlink(struct mnt_idmap *idmap, int want_clusters = 0; int xattr_credits = 0; struct ocfs2_security_xattr_info si = { + .name = NULL, .enable = 1, }; int did_quota = 0, did_quota_inode = 0; diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index 389308efe854..469ec45baee2 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -7259,9 +7259,21 @@ static int ocfs2_xattr_security_set(const struct xattr_handler *handler, static int ocfs2_initxattrs(struct inode *inode, const struct xattr *xattr_array, void *fs_info) { + struct ocfs2_security_xattr_info *si = fs_info; const struct xattr *xattr; int err = 0; + if (si) { + si->value = kmemdup(xattr_array->value, xattr_array->value_len, + GFP_KERNEL); + if (!si->value) + return -ENOMEM; + + si->name = xattr_array->name; + si->value_len = xattr_array->value_len; + return 0; + } + for (xattr = xattr_array; xattr->name != NULL; xattr++) { err = ocfs2_xattr_set(inode, OCFS2_XATTR_INDEX_SECURITY, xattr->name, xattr->value, @@ -7277,13 +7289,23 @@ int ocfs2_init_security_get(struct inode *inode, const struct qstr *qstr, struct ocfs2_security_xattr_info *si) { + int ret; + /* check whether ocfs2 support feature xattr */ if (!ocfs2_supports_xattr(OCFS2_SB(dir->i_sb))) return -EOPNOTSUPP; - if (si) - return security_old_inode_init_security(inode, dir, qstr, - &si->name, &si->value, - &si->value_len); + if (si) { + ret = security_inode_init_security(inode, dir, qstr, + &ocfs2_initxattrs, si); + /* + * security_inode_init_security() does not return -EOPNOTSUPP, + * we have to check the xattr ourselves. + */ + if (!ret && !si->name) + si->enable = 0; + + return ret; + } return security_inode_init_security(inode, dir, qstr, &ocfs2_initxattrs, NULL); diff --git a/fs/read_write.c b/fs/read_write.c index 7a2ff6157eda..a21ba3be7dbe 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -749,15 +749,14 @@ static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter, return -EOPNOTSUPP; while (iov_iter_count(iter)) { - struct iovec iovec = iov_iter_iovec(iter); ssize_t nr; if (type == READ) { - nr = filp->f_op->read(filp, iovec.iov_base, - iovec.iov_len, ppos); + nr = filp->f_op->read(filp, iter_iov_addr(iter), + iter_iov_len(iter), ppos); } else { - nr = filp->f_op->write(filp, iovec.iov_base, - iovec.iov_len, ppos); + nr = filp->f_op->write(filp, iter_iov_addr(iter), + iter_iov_len(iter), ppos); } if (nr < 0) { @@ -766,7 +765,7 @@ static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter, break; } ret += nr; - if (nr != iovec.iov_len) + if (nr != iter_iov_len(iter)) break; iov_iter_advance(iter, nr); } diff --git a/fs/reiserfs/xattr_security.c b/fs/reiserfs/xattr_security.c index 41c0ea84fbff..6e0a099dd788 100644 --- a/fs/reiserfs/xattr_security.c +++ b/fs/reiserfs/xattr_security.c @@ -39,6 +39,22 @@ static bool security_list(struct dentry *dentry) return !IS_PRIVATE(d_inode(dentry)); } +static int +reiserfs_initxattrs(struct inode *inode, const struct xattr *xattr_array, + void *fs_info) +{ + struct reiserfs_security_handle *sec = fs_info; + + sec->value = kmemdup(xattr_array->value, xattr_array->value_len, + GFP_KERNEL); + if (!sec->value) + return -ENOMEM; + + sec->name = xattr_array->name; + sec->length = xattr_array->value_len; + return 0; +} + /* Initializes the security context for a new inode and returns the number * of blocks needed for the transaction. If successful, reiserfs_security * must be released using reiserfs_security_free when the caller is done. */ @@ -56,12 +72,9 @@ int reiserfs_security_init(struct inode *dir, struct inode *inode, if (IS_PRIVATE(dir)) return 0; - error = security_old_inode_init_security(inode, dir, qstr, &sec->name, - &sec->value, &sec->length); + error = security_inode_init_security(inode, dir, qstr, + &reiserfs_initxattrs, sec); if (error) { - if (error == -EOPNOTSUPP) - error = 0; - sec->name = NULL; sec->value = NULL; sec->length = 0; @@ -82,11 +95,15 @@ int reiserfs_security_write(struct reiserfs_transaction_handle *th, struct inode *inode, struct reiserfs_security_handle *sec) { + char xattr_name[XATTR_NAME_MAX + 1] = XATTR_SECURITY_PREFIX; int error; - if (strlen(sec->name) < sizeof(XATTR_SECURITY_PREFIX)) + + if (XATTR_SECURITY_PREFIX_LEN + strlen(sec->name) > XATTR_NAME_MAX) return -EINVAL; - error = reiserfs_xattr_set_handle(th, inode, sec->name, sec->value, + strlcat(xattr_name, sec->name, sizeof(xattr_name)); + + error = reiserfs_xattr_set_handle(th, inode, xattr_name, sec->value, sec->length, XATTR_CREATE); if (error == -ENODATA || error == -EOPNOTSUPP) error = 0; diff --git a/fs/splice.c b/fs/splice.c index 2e76dbb81a8f..2c3dec2b6dfa 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -937,7 +937,6 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd, /* * Do the splice. */ - ret = 0; bytes = 0; len = sd->total_len; flags = sd->flags; diff --git a/fs/super.c b/fs/super.c index 84332d5cb817..04bc62ab7dfe 100644 --- a/fs/super.c +++ b/fs/super.c @@ -475,13 +475,22 @@ void generic_shutdown_super(struct super_block *sb) cgroup_writeback_umount(); - /* evict all inodes with zero refcount */ + /* Evict all inodes with zero refcount. */ evict_inodes(sb); - /* only nonzero refcount inodes can have marks */ + + /* + * Clean up and evict any inodes that still have references due + * to fsnotify or the security policy. + */ fsnotify_sb_delete(sb); - fscrypt_destroy_keyring(sb); security_sb_delete(sb); + /* + * Now that all potentially-encrypted inodes have been evicted, + * the fscrypt keyring can be destroyed. + */ + fscrypt_destroy_keyring(sb); + if (sb->s_dio_done_wq) { destroy_workqueue(sb->s_dio_done_wq); sb->s_dio_done_wq = NULL; diff --git a/fs/udf/inode.c b/fs/udf/inode.c index f7a9607c2b95..2210e5eb1ea0 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -193,7 +193,7 @@ static int udf_adinicb_writepage(struct folio *folio, struct udf_inode_info *iinfo = UDF_I(inode); BUG_ON(!PageLocked(page)); - memcpy_to_page(page, 0, iinfo->i_data + iinfo->i_lenEAttr, + memcpy_from_page(iinfo->i_data + iinfo->i_lenEAttr, page, 0, i_size_read(inode)); unlock_page(page); mark_inode_dirty(inode); @@ -241,6 +241,15 @@ static int udf_read_folio(struct file *file, struct folio *folio) static void udf_readahead(struct readahead_control *rac) { + struct udf_inode_info *iinfo = UDF_I(rac->mapping->host); + + /* + * No readahead needed for in-ICB files and udf_get_block() would get + * confused for such file anyway. + */ + if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) + return; + mpage_readahead(rac, udf_get_block); } @@ -407,6 +416,9 @@ static int udf_map_block(struct inode *inode, struct udf_map_rq *map) int err; struct udf_inode_info *iinfo = UDF_I(inode); + if (WARN_ON_ONCE(iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB)) + return -EFSCORRUPTED; + map->oflags = 0; if (!(map->iflags & UDF_MAP_CREATE)) { struct kernel_lb_addr eloc; diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 44d1ee429eb0..40f9e1a2ebdd 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -1955,8 +1955,10 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx, ret = -EFAULT; if (copy_from_user(&uffdio_api, buf, sizeof(uffdio_api))) goto out; - /* Ignore unsupported features (userspace built against newer kernel) */ - features = uffdio_api.features & UFFD_API_FEATURES; + features = uffdio_api.features; + ret = -EINVAL; + if (uffdio_api.api != UFFD_API || (features & ~UFFD_API_FEATURES)) + goto err_out; ret = -EPERM; if ((features & UFFD_FEATURE_EVENT_FORK) && !capable(CAP_SYS_PTRACE)) goto err_out; diff --git a/fs/verity/enable.c b/fs/verity/enable.c index e13db6507b38..7a0e3a84d370 100644 --- a/fs/verity/enable.c +++ b/fs/verity/enable.c @@ -8,7 +8,6 @@ #include "fsverity_private.h" #include <linux/mount.h> -#include <linux/pagemap.h> #include <linux/sched/signal.h> #include <linux/uaccess.h> @@ -367,25 +366,27 @@ int fsverity_ioctl_enable(struct file *filp, const void __user *uarg) goto out_drop_write; err = enable_verity(filp, &arg); - if (err) - goto out_allow_write_access; /* - * Some pages of the file may have been evicted from pagecache after - * being used in the Merkle tree construction, then read into pagecache - * again by another process reading from the file concurrently. Since - * these pages didn't undergo verification against the file digest which - * fs-verity now claims to be enforcing, we have to wipe the pagecache - * to ensure that all future reads are verified. + * We no longer drop the inode's pagecache after enabling verity. This + * used to be done to try to avoid a race condition where pages could be + * evicted after being used in the Merkle tree construction, then + * re-instantiated by a concurrent read. Such pages are unverified, and + * the backing storage could have filled them with different content, so + * they shouldn't be used to fulfill reads once verity is enabled. + * + * But, dropping the pagecache has a big performance impact, and it + * doesn't fully solve the race condition anyway. So for those reasons, + * and also because this race condition isn't very important relatively + * speaking (especially for small-ish files, where the chance of a page + * being used, evicted, *and* re-instantiated all while enabling verity + * is quite small), we no longer drop the inode's pagecache. */ - filemap_write_and_wait(inode->i_mapping); - invalidate_inode_pages2(inode->i_mapping); /* * allow_write_access() is needed to pair with deny_write_access(). * Regardless, the filesystem won't allow writing to verity files. */ -out_allow_write_access: allow_write_access(filp); out_drop_write: mnt_drop_write_file(filp); diff --git a/fs/verity/verify.c b/fs/verity/verify.c index f50e3b5b52c9..e2508222750b 100644 --- a/fs/verity/verify.c +++ b/fs/verity/verify.c @@ -387,15 +387,15 @@ EXPORT_SYMBOL_GPL(fsverity_enqueue_verify_work); int __init fsverity_init_workqueue(void) { /* - * Use an unbound workqueue to allow bios to be verified in parallel - * even when they happen to complete on the same CPU. This sacrifices - * locality, but it's worthwhile since hashing is CPU-intensive. + * Use a high-priority workqueue to prioritize verification work, which + * blocks reads from completing, over regular application tasks. * - * Also use a high-priority workqueue to prioritize verification work, - * which blocks reads from completing, over regular application tasks. + * For performance reasons, don't use an unbound workqueue. Using an + * unbound workqueue for crypto operations causes excessive scheduler + * latency on ARM64. */ fsverity_read_workqueue = alloc_workqueue("fsverity_read_queue", - WQ_UNBOUND | WQ_HIGHPRI, + WQ_HIGHPRI, num_online_cpus()); if (!fsverity_read_workqueue) return -ENOMEM; diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile index 03135a1c31b6..92d88dc3c9f7 100644 --- a/fs/xfs/Makefile +++ b/fs/xfs/Makefile @@ -63,6 +63,7 @@ xfs-y += xfs_aops.o \ xfs_bmap_util.o \ xfs_bio_io.o \ xfs_buf.o \ + xfs_dahash_test.o \ xfs_dir2_readdir.o \ xfs_discard.o \ xfs_error.o \ diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 6a037173d20d..203f16c48c19 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -3045,6 +3045,8 @@ xfs_alloc_read_agf( pag->pagf_refcount_level = be32_to_cpu(agf->agf_refcount_level); if (xfs_agfl_needs_reset(pag->pag_mount, agf)) set_bit(XFS_AGSTATE_AGFL_NEEDS_RESET, &pag->pag_opstate); + else + clear_bit(XFS_AGSTATE_AGFL_NEEDS_RESET, &pag->pag_opstate); /* * Update the in-core allocbt counter. Filter out the rmapbt @@ -3255,6 +3257,8 @@ xfs_alloc_vextent_finish( XFS_STATS_INC(mp, xs_allocx); XFS_STATS_ADD(mp, xs_allocb, args->len); + trace_xfs_alloc_vextent_finish(args); + out_drop_perag: if (drop_perag && args->pag) { xfs_perag_rele(args->pag); @@ -3279,8 +3283,14 @@ xfs_alloc_vextent_this_ag( xfs_agnumber_t minimum_agno; int error; + ASSERT(args->pag != NULL); + ASSERT(args->pag->pag_agno == agno); + args->agno = agno; args->agbno = 0; + + trace_xfs_alloc_vextent_this_ag(args); + error = xfs_alloc_vextent_check_args(args, XFS_AGB_TO_FSB(mp, agno, 0), &minimum_agno); if (error) { @@ -3323,11 +3333,14 @@ xfs_alloc_vextent_iterate_ags( uint32_t flags) { struct xfs_mount *mp = args->mp; + xfs_agnumber_t restart_agno = minimum_agno; xfs_agnumber_t agno; int error = 0; + if (flags & XFS_ALLOC_FLAG_TRYLOCK) + restart_agno = 0; restart: - for_each_perag_wrap_range(mp, start_agno, minimum_agno, + for_each_perag_wrap_range(mp, start_agno, restart_agno, mp->m_sb.sb_agcount, agno, args->pag) { args->agno = agno; error = xfs_alloc_vextent_prepare_ag(args); @@ -3366,6 +3379,7 @@ restart: */ if (flags) { flags = 0; + restart_agno = minimum_agno; goto restart; } @@ -3394,8 +3408,13 @@ xfs_alloc_vextent_start_ag( bool bump_rotor = false; int error; + ASSERT(args->pag == NULL); + args->agno = NULLAGNUMBER; args->agbno = NULLAGBLOCK; + + trace_xfs_alloc_vextent_start_ag(args); + error = xfs_alloc_vextent_check_args(args, target, &minimum_agno); if (error) { if (error == -ENOSPC) @@ -3442,8 +3461,13 @@ xfs_alloc_vextent_first_ag( xfs_agnumber_t start_agno; int error; + ASSERT(args->pag == NULL); + args->agno = NULLAGNUMBER; args->agbno = NULLAGBLOCK; + + trace_xfs_alloc_vextent_first_ag(args); + error = xfs_alloc_vextent_check_args(args, target, &minimum_agno); if (error) { if (error == -ENOSPC) @@ -3470,8 +3494,14 @@ xfs_alloc_vextent_exact_bno( xfs_agnumber_t minimum_agno; int error; + ASSERT(args->pag != NULL); + ASSERT(args->pag->pag_agno == XFS_FSB_TO_AGNO(mp, target)); + args->agno = XFS_FSB_TO_AGNO(mp, target); args->agbno = XFS_FSB_TO_AGBNO(mp, target); + + trace_xfs_alloc_vextent_exact_bno(args); + error = xfs_alloc_vextent_check_args(args, target, &minimum_agno); if (error) { if (error == -ENOSPC) @@ -3502,8 +3532,14 @@ xfs_alloc_vextent_near_bno( bool needs_perag = args->pag == NULL; int error; + if (!needs_perag) + ASSERT(args->pag->pag_agno == XFS_FSB_TO_AGNO(mp, target)); + args->agno = XFS_FSB_TO_AGNO(mp, target); args->agbno = XFS_FSB_TO_AGBNO(mp, target); + + trace_xfs_alloc_vextent_near_bno(args); + error = xfs_alloc_vextent_check_args(args, target, &minimum_agno); if (error) { if (error == -ENOSPC) diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 41734202796f..2ef78aa1d3f6 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -449,15 +449,17 @@ xfs_prepare_ioend( } /* - * If the page has delalloc blocks on it, we need to punch them out before we - * invalidate the page. If we don't, we leave a stale delalloc mapping on the - * inode that can trip up a later direct I/O read operation on the same region. + * If the folio has delalloc blocks on it, the caller is asking us to punch them + * out. If we don't, we can leave a stale delalloc mapping covered by a clean + * page that needs to be dirtied again before the delalloc mapping can be + * converted. This stale delalloc mapping can trip up a later direct I/O read + * operation on the same region. * - * We prevent this by truncating away the delalloc regions on the page. Because + * We prevent this by truncating away the delalloc regions on the folio. Because * they are delalloc, we can do this without needing a transaction. Indeed - if * we get ENOSPC errors, we have to be able to do this truncation without a - * transaction as there is no space left for block reservation (typically why we - * see a ENOSPC in writeback). + * transaction as there is no space left for block reservation (typically why + * we see a ENOSPC in writeback). */ static void xfs_discard_folio( @@ -475,8 +477,13 @@ xfs_discard_folio( "page discard on page "PTR_FMT", inode 0x%llx, pos %llu.", folio, ip->i_ino, pos); + /* + * The end of the punch range is always the offset of the the first + * byte of the next folio. Hence the end offset is only dependent on the + * folio itself and not the start offset that is passed in. + */ error = xfs_bmap_punch_delalloc_range(ip, pos, - round_up(pos, folio_size(folio))); + folio_pos(folio) + folio_size(folio)); if (error && !xfs_is_shutdown(mp)) xfs_alert(mp, "page discard unable to remove delalloc mapping."); diff --git a/fs/xfs/xfs_dahash_test.c b/fs/xfs/xfs_dahash_test.c new file mode 100644 index 000000000000..230651ab5ce4 --- /dev/null +++ b/fs/xfs/xfs_dahash_test.c @@ -0,0 +1,662 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2023 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <djwong@kernel.org> + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_da_format.h" +#include "xfs_da_btree.h" +#include "xfs_dahash_test.h" + +/* 4096 random bytes */ +static uint8_t __initdata __attribute__((__aligned__(8))) test_buf[] = +{ + 0x5b, 0x85, 0x21, 0xcb, 0x09, 0x68, 0x7d, 0x30, + 0xc7, 0x69, 0xd7, 0x30, 0x92, 0xde, 0x59, 0xe4, + 0xc9, 0x6e, 0x8b, 0xdb, 0x98, 0x6b, 0xaa, 0x60, + 0xa8, 0xb5, 0xbc, 0x6c, 0xa9, 0xb1, 0x5b, 0x2c, + 0xea, 0xb4, 0x92, 0x6a, 0x3f, 0x79, 0x91, 0xe4, + 0xe9, 0x70, 0x51, 0x8c, 0x7f, 0x95, 0x6f, 0x1a, + 0x56, 0xa1, 0x5c, 0x27, 0x03, 0x67, 0x9f, 0x3a, + 0xe2, 0x31, 0x11, 0x29, 0x6b, 0x98, 0xfc, 0xc4, + 0x53, 0x24, 0xc5, 0x8b, 0xce, 0x47, 0xb2, 0xb9, + 0x32, 0xcb, 0xc1, 0xd0, 0x03, 0x57, 0x4e, 0xd4, + 0xe9, 0x3c, 0xa1, 0x63, 0xcf, 0x12, 0x0e, 0xca, + 0xe1, 0x13, 0xd1, 0x93, 0xa6, 0x88, 0x5c, 0x61, + 0x5b, 0xbb, 0xf0, 0x19, 0x46, 0xb4, 0xcf, 0x9e, + 0xb6, 0x6b, 0x4c, 0x3a, 0xcf, 0x60, 0xf9, 0x7a, + 0x8d, 0x07, 0x63, 0xdb, 0x40, 0xe9, 0x0b, 0x6f, + 0xad, 0x97, 0xf1, 0xed, 0xd0, 0x1e, 0x26, 0xfd, + 0xbf, 0xb7, 0xc8, 0x04, 0x94, 0xf8, 0x8b, 0x8c, + 0xf1, 0xab, 0x7a, 0xd4, 0xdd, 0xf3, 0xe8, 0x88, + 0xc3, 0xed, 0x17, 0x8a, 0x9b, 0x40, 0x0d, 0x53, + 0x62, 0x12, 0x03, 0x5f, 0x1b, 0x35, 0x32, 0x1f, + 0xb4, 0x7b, 0x93, 0x78, 0x0d, 0xdb, 0xce, 0xa4, + 0xc0, 0x47, 0xd5, 0xbf, 0x68, 0xe8, 0x5d, 0x74, + 0x8f, 0x8e, 0x75, 0x1c, 0xb2, 0x4f, 0x9a, 0x60, + 0xd1, 0xbe, 0x10, 0xf4, 0x5c, 0xa1, 0x53, 0x09, + 0xa5, 0xe0, 0x09, 0x54, 0x85, 0x5c, 0xdc, 0x07, + 0xe7, 0x21, 0x69, 0x7b, 0x8a, 0xfd, 0x90, 0xf1, + 0x22, 0xd0, 0xb4, 0x36, 0x28, 0xe6, 0xb8, 0x0f, + 0x39, 0xde, 0xc8, 0xf3, 0x86, 0x60, 0x34, 0xd2, + 0x5e, 0xdf, 0xfd, 0xcf, 0x0f, 0xa9, 0x65, 0xf0, + 0xd5, 0x4d, 0x96, 0x40, 0xe3, 0xdf, 0x3f, 0x95, + 0x5a, 0x39, 0x19, 0x93, 0xf4, 0x75, 0xce, 0x22, + 0x00, 0x1c, 0x93, 0xe2, 0x03, 0x66, 0xf4, 0x93, + 0x73, 0x86, 0x81, 0x8e, 0x29, 0x44, 0x48, 0x86, + 0x61, 0x7c, 0x48, 0xa3, 0x43, 0xd2, 0x9c, 0x8d, + 0xd4, 0x95, 0xdd, 0xe1, 0x22, 0x89, 0x3a, 0x40, + 0x4c, 0x1b, 0x8a, 0x04, 0xa8, 0x09, 0x69, 0x8b, + 0xea, 0xc6, 0x55, 0x8e, 0x57, 0xe6, 0x64, 0x35, + 0xf0, 0xc7, 0x16, 0x9f, 0x5d, 0x5e, 0x86, 0x40, + 0x46, 0xbb, 0xe5, 0x45, 0x88, 0xfe, 0xc9, 0x63, + 0x15, 0xfb, 0xf5, 0xbd, 0x71, 0x61, 0xeb, 0x7b, + 0x78, 0x70, 0x07, 0x31, 0x03, 0x9f, 0xb2, 0xc8, + 0xa7, 0xab, 0x47, 0xfd, 0xdf, 0xa0, 0x78, 0x72, + 0xa4, 0x2a, 0xe4, 0xb6, 0xba, 0xc0, 0x1e, 0x86, + 0x71, 0xe6, 0x3d, 0x18, 0x37, 0x70, 0xe6, 0xff, + 0xe0, 0xbc, 0x0b, 0x22, 0xa0, 0x1f, 0xd3, 0xed, + 0xa2, 0x55, 0x39, 0xab, 0xa8, 0x13, 0x73, 0x7c, + 0x3f, 0xb2, 0xd6, 0x19, 0xac, 0xff, 0x99, 0xed, + 0xe8, 0xe6, 0xa6, 0x22, 0xe3, 0x9c, 0xf1, 0x30, + 0xdc, 0x01, 0x0a, 0x56, 0xfa, 0xe4, 0xc9, 0x99, + 0xdd, 0xa8, 0xd8, 0xda, 0x35, 0x51, 0x73, 0xb4, + 0x40, 0x86, 0x85, 0xdb, 0x5c, 0xd5, 0x85, 0x80, + 0x14, 0x9c, 0xfd, 0x98, 0xa9, 0x82, 0xc5, 0x37, + 0xff, 0x32, 0x5d, 0xd0, 0x0b, 0xfa, 0xdc, 0x04, + 0x5e, 0x09, 0xd2, 0xca, 0x17, 0x4b, 0x1a, 0x8e, + 0x15, 0xe1, 0xcc, 0x4e, 0x52, 0x88, 0x35, 0xbd, + 0x48, 0xfe, 0x15, 0xa0, 0x91, 0xfd, 0x7e, 0x6c, + 0x0e, 0x5d, 0x79, 0x1b, 0x81, 0x79, 0xd2, 0x09, + 0x34, 0x70, 0x3d, 0x81, 0xec, 0xf6, 0x24, 0xbb, + 0xfb, 0xf1, 0x7b, 0xdf, 0x54, 0xea, 0x80, 0x9b, + 0xc7, 0x99, 0x9e, 0xbd, 0x16, 0x78, 0x12, 0x53, + 0x5e, 0x01, 0xa7, 0x4e, 0xbd, 0x67, 0xe1, 0x9b, + 0x4c, 0x0e, 0x61, 0x45, 0x97, 0xd2, 0xf0, 0x0f, + 0xfe, 0x15, 0x08, 0xb7, 0x11, 0x4c, 0xe7, 0xff, + 0x81, 0x53, 0xff, 0x91, 0x25, 0x38, 0x7e, 0x40, + 0x94, 0xe5, 0xe0, 0xad, 0xe6, 0xd9, 0x79, 0xb6, + 0x92, 0xc9, 0xfc, 0xde, 0xc3, 0x1a, 0x23, 0xbb, + 0xdd, 0xc8, 0x51, 0x0c, 0x3a, 0x72, 0xfa, 0x73, + 0x6f, 0xb7, 0xee, 0x61, 0x39, 0x03, 0x01, 0x3f, + 0x7f, 0x94, 0x2e, 0x2e, 0xba, 0x3a, 0xbb, 0xb4, + 0xfa, 0x6a, 0x17, 0xfe, 0xea, 0xef, 0x5e, 0x66, + 0x97, 0x3f, 0x32, 0x3d, 0xd7, 0x3e, 0xb1, 0xf1, + 0x6c, 0x14, 0x4c, 0xfd, 0x37, 0xd3, 0x38, 0x80, + 0xfb, 0xde, 0xa6, 0x24, 0x1e, 0xc8, 0xca, 0x7f, + 0x3a, 0x93, 0xd8, 0x8b, 0x18, 0x13, 0xb2, 0xe5, + 0xe4, 0x93, 0x05, 0x53, 0x4f, 0x84, 0x66, 0xa7, + 0x58, 0x5c, 0x7b, 0x86, 0x52, 0x6d, 0x0d, 0xce, + 0xa4, 0x30, 0x7d, 0xb6, 0x18, 0x9f, 0xeb, 0xff, + 0x22, 0xbb, 0x72, 0x29, 0xb9, 0x44, 0x0b, 0x48, + 0x1e, 0x84, 0x71, 0x81, 0xe3, 0x6d, 0x73, 0x26, + 0x92, 0xb4, 0x4d, 0x2a, 0x29, 0xb8, 0x1f, 0x72, + 0xed, 0xd0, 0xe1, 0x64, 0x77, 0xea, 0x8e, 0x88, + 0x0f, 0xef, 0x3f, 0xb1, 0x3b, 0xad, 0xf9, 0xc9, + 0x8b, 0xd0, 0xac, 0xc6, 0xcc, 0xa9, 0x40, 0xcc, + 0x76, 0xf6, 0x3b, 0x53, 0xb5, 0x88, 0xcb, 0xc8, + 0x37, 0xf1, 0xa2, 0xba, 0x23, 0x15, 0x99, 0x09, + 0xcc, 0xe7, 0x7a, 0x3b, 0x37, 0xf7, 0x58, 0xc8, + 0x46, 0x8c, 0x2b, 0x2f, 0x4e, 0x0e, 0xa6, 0x5c, + 0xea, 0x85, 0x55, 0xba, 0x02, 0x0e, 0x0e, 0x48, + 0xbc, 0xe1, 0xb1, 0x01, 0x35, 0x79, 0x13, 0x3d, + 0x1b, 0xc0, 0x53, 0x68, 0x11, 0xe7, 0x95, 0x0f, + 0x9d, 0x3f, 0x4c, 0x47, 0x7b, 0x4d, 0x1c, 0xae, + 0x50, 0x9b, 0xcb, 0xdd, 0x05, 0x8d, 0x9a, 0x97, + 0xfd, 0x8c, 0xef, 0x0c, 0x1d, 0x67, 0x73, 0xa8, + 0x28, 0x36, 0xd5, 0xb6, 0x92, 0x33, 0x40, 0x75, + 0x0b, 0x51, 0xc3, 0x64, 0xba, 0x1d, 0xc2, 0xcc, + 0xee, 0x7d, 0x54, 0x0f, 0x27, 0x69, 0xa7, 0x27, + 0x63, 0x30, 0x29, 0xd9, 0xc8, 0x84, 0xd8, 0xdf, + 0x9f, 0x68, 0x8d, 0x04, 0xca, 0xa6, 0xc5, 0xc7, + 0x7a, 0x5c, 0xc8, 0xd1, 0xcb, 0x4a, 0xec, 0xd0, + 0xd8, 0x20, 0x69, 0xc5, 0x17, 0xcd, 0x78, 0xc8, + 0x75, 0x23, 0x30, 0x69, 0xc9, 0xd4, 0xea, 0x5c, + 0x4f, 0x6b, 0x86, 0x3f, 0x8b, 0xfe, 0xee, 0x44, + 0xc9, 0x7c, 0xb7, 0xdd, 0x3e, 0xe5, 0xec, 0x54, + 0x03, 0x3e, 0xaa, 0x82, 0xc6, 0xdf, 0xb2, 0x38, + 0x0e, 0x5d, 0xb3, 0x88, 0xd9, 0xd3, 0x69, 0x5f, + 0x8f, 0x70, 0x8a, 0x7e, 0x11, 0xd9, 0x1e, 0x7b, + 0x38, 0xf1, 0x42, 0x1a, 0xc0, 0x35, 0xf5, 0xc7, + 0x36, 0x85, 0xf5, 0xf7, 0xb8, 0x7e, 0xc7, 0xef, + 0x18, 0xf1, 0x63, 0xd6, 0x7a, 0xc6, 0xc9, 0x0e, + 0x4d, 0x69, 0x4f, 0x84, 0xef, 0x26, 0x41, 0x0c, + 0xec, 0xc7, 0xe0, 0x7e, 0x3c, 0x67, 0x01, 0x4c, + 0x62, 0x1a, 0x20, 0x6f, 0xee, 0x47, 0x4d, 0xc0, + 0x99, 0x13, 0x8d, 0x91, 0x4a, 0x26, 0xd4, 0x37, + 0x28, 0x90, 0x58, 0x75, 0x66, 0x2b, 0x0a, 0xdf, + 0xda, 0xee, 0x92, 0x25, 0x90, 0x62, 0x39, 0x9e, + 0x44, 0x98, 0xad, 0xc1, 0x88, 0xed, 0xe4, 0xb4, + 0xaf, 0xf5, 0x8c, 0x9b, 0x48, 0x4d, 0x56, 0x60, + 0x97, 0x0f, 0x61, 0x59, 0x9e, 0xa6, 0x27, 0xfe, + 0xc1, 0x91, 0x15, 0x38, 0xb8, 0x0f, 0xae, 0x61, + 0x7d, 0x26, 0x13, 0x5a, 0x73, 0xff, 0x1c, 0xa3, + 0x61, 0x04, 0x58, 0x48, 0x55, 0x44, 0x11, 0xfe, + 0x15, 0xca, 0xc3, 0xbd, 0xca, 0xc5, 0xb4, 0x40, + 0x5d, 0x1b, 0x7f, 0x39, 0xb5, 0x9c, 0x35, 0xec, + 0x61, 0x15, 0x32, 0x32, 0xb8, 0x4e, 0x40, 0x9f, + 0x17, 0x1f, 0x0a, 0x4d, 0xa9, 0x91, 0xef, 0xb7, + 0xb0, 0xeb, 0xc2, 0x83, 0x9a, 0x6c, 0xd2, 0x79, + 0x43, 0x78, 0x5e, 0x2f, 0xe5, 0xdd, 0x1a, 0x3c, + 0x45, 0xab, 0x29, 0x40, 0x3a, 0x37, 0x5b, 0x6f, + 0xd7, 0xfc, 0x48, 0x64, 0x3c, 0x49, 0xfb, 0x21, + 0xbe, 0xc3, 0xff, 0x07, 0xfb, 0x17, 0xe9, 0xc9, + 0x0c, 0x4c, 0x5c, 0x15, 0x9e, 0x8e, 0x22, 0x30, + 0x0a, 0xde, 0x48, 0x7f, 0xdb, 0x0d, 0xd1, 0x2b, + 0x87, 0x38, 0x9e, 0xcc, 0x5a, 0x01, 0x16, 0xee, + 0x75, 0x49, 0x0d, 0x30, 0x01, 0x34, 0x6a, 0xb6, + 0x9a, 0x5a, 0x2a, 0xec, 0xbb, 0x48, 0xac, 0xd3, + 0x77, 0x83, 0xd8, 0x08, 0x86, 0x4f, 0x48, 0x09, + 0x29, 0x41, 0x79, 0xa1, 0x03, 0x12, 0xc4, 0xcd, + 0x90, 0x55, 0x47, 0x66, 0x74, 0x9a, 0xcc, 0x4f, + 0x35, 0x8c, 0xd6, 0x98, 0xef, 0xeb, 0x45, 0xb9, + 0x9a, 0x26, 0x2f, 0x39, 0xa5, 0x70, 0x6d, 0xfc, + 0xb4, 0x51, 0xee, 0xf4, 0x9c, 0xe7, 0x38, 0x59, + 0xad, 0xf4, 0xbc, 0x46, 0xff, 0x46, 0x8e, 0x60, + 0x9c, 0xa3, 0x60, 0x1d, 0xf8, 0x26, 0x72, 0xf5, + 0x72, 0x9d, 0x68, 0x80, 0x04, 0xf6, 0x0b, 0xa1, + 0x0a, 0xd5, 0xa7, 0x82, 0x3a, 0x3e, 0x47, 0xa8, + 0x5a, 0xde, 0x59, 0x4f, 0x7b, 0x07, 0xb3, 0xe9, + 0x24, 0x19, 0x3d, 0x34, 0x05, 0xec, 0xf1, 0xab, + 0x6e, 0x64, 0x8f, 0xd3, 0xe6, 0x41, 0x86, 0x80, + 0x70, 0xe3, 0x8d, 0x60, 0x9c, 0x34, 0x25, 0x01, + 0x07, 0x4d, 0x19, 0x41, 0x4e, 0x3d, 0x5c, 0x7e, + 0xa8, 0xf5, 0xcc, 0xd5, 0x7b, 0xe2, 0x7d, 0x3d, + 0x49, 0x86, 0x7d, 0x07, 0xb7, 0x10, 0xe3, 0x35, + 0xb8, 0x84, 0x6d, 0x76, 0xab, 0x17, 0xc6, 0x38, + 0xb4, 0xd3, 0x28, 0x57, 0xad, 0xd3, 0x88, 0x5a, + 0xda, 0xea, 0xc8, 0x94, 0xcc, 0x37, 0x19, 0xac, + 0x9c, 0x9f, 0x4b, 0x00, 0x15, 0xc0, 0xc8, 0xca, + 0x1f, 0x15, 0xaa, 0xe0, 0xdb, 0xf9, 0x2f, 0x57, + 0x1b, 0x24, 0xc7, 0x6f, 0x76, 0x29, 0xfb, 0xed, + 0x25, 0x0d, 0xc0, 0xfe, 0xbd, 0x5a, 0xbf, 0x20, + 0x08, 0x51, 0x05, 0xec, 0x71, 0xa3, 0xbf, 0xef, + 0x5e, 0x99, 0x75, 0xdb, 0x3c, 0x5f, 0x9a, 0x8c, + 0xbb, 0x19, 0x5c, 0x0e, 0x93, 0x19, 0xf8, 0x6a, + 0xbc, 0xf2, 0x12, 0x54, 0x2f, 0xcb, 0x28, 0x64, + 0x88, 0xb3, 0x92, 0x0d, 0x96, 0xd1, 0xa6, 0xe4, + 0x1f, 0xf1, 0x4d, 0xa4, 0xab, 0x1c, 0xee, 0x54, + 0xf2, 0xad, 0x29, 0x6d, 0x32, 0x37, 0xb2, 0x16, + 0x77, 0x5c, 0xdc, 0x2e, 0x54, 0xec, 0x75, 0x26, + 0xc6, 0x36, 0xd9, 0x17, 0x2c, 0xf1, 0x7a, 0xdc, + 0x4b, 0xf1, 0xe2, 0xd9, 0x95, 0xba, 0xac, 0x87, + 0xc1, 0xf3, 0x8e, 0x58, 0x08, 0xd8, 0x87, 0x60, + 0xc9, 0xee, 0x6a, 0xde, 0xa4, 0xd2, 0xfc, 0x0d, + 0xe5, 0x36, 0xc4, 0x5c, 0x52, 0xb3, 0x07, 0x54, + 0x65, 0x24, 0xc1, 0xb1, 0xd1, 0xb1, 0x53, 0x13, + 0x31, 0x79, 0x7f, 0x05, 0x76, 0xeb, 0x37, 0x59, + 0x15, 0x2b, 0xd1, 0x3f, 0xac, 0x08, 0x97, 0xeb, + 0x91, 0x98, 0xdf, 0x6c, 0x09, 0x0d, 0x04, 0x9f, + 0xdc, 0x3b, 0x0e, 0x60, 0x68, 0x47, 0x23, 0x15, + 0x16, 0xc6, 0x0b, 0x35, 0xf8, 0x77, 0xa2, 0x78, + 0x50, 0xd4, 0x64, 0x22, 0x33, 0xff, 0xfb, 0x93, + 0x71, 0x46, 0x50, 0x39, 0x1b, 0x9c, 0xea, 0x4e, + 0x8d, 0x0c, 0x37, 0xe5, 0x5c, 0x51, 0x3a, 0x31, + 0xb2, 0x85, 0x84, 0x3f, 0x41, 0xee, 0xa2, 0xc1, + 0xc6, 0x13, 0x3b, 0x54, 0x28, 0xd2, 0x18, 0x37, + 0xcc, 0x46, 0x9f, 0x6a, 0x91, 0x3d, 0x5a, 0x15, + 0x3c, 0x89, 0xa3, 0x61, 0x06, 0x7d, 0x2e, 0x78, + 0xbe, 0x7d, 0x40, 0xba, 0x2f, 0x95, 0xb1, 0x2f, + 0x87, 0x3b, 0x8a, 0xbe, 0x6a, 0xf4, 0xc2, 0x31, + 0x74, 0xee, 0x91, 0xe0, 0x23, 0xaa, 0x5d, 0x7f, + 0xdd, 0xf0, 0x44, 0x8c, 0x0b, 0x59, 0x2b, 0xfc, + 0x48, 0x3a, 0xdf, 0x07, 0x05, 0x38, 0x6c, 0xc9, + 0xeb, 0x18, 0x24, 0x68, 0x8d, 0x58, 0x98, 0xd3, + 0x31, 0xa3, 0xe4, 0x70, 0x59, 0xb1, 0x21, 0xbe, + 0x7e, 0x65, 0x7d, 0xb8, 0x04, 0xab, 0xf6, 0xe4, + 0xd7, 0xda, 0xec, 0x09, 0x8f, 0xda, 0x6d, 0x24, + 0x07, 0xcc, 0x29, 0x17, 0x05, 0x78, 0x1a, 0xc1, + 0xb1, 0xce, 0xfc, 0xaa, 0x2d, 0xe7, 0xcc, 0x85, + 0x84, 0x84, 0x03, 0x2a, 0x0c, 0x3f, 0xa9, 0xf8, + 0xfd, 0x84, 0x53, 0x59, 0x5c, 0xf0, 0xd4, 0x09, + 0xf0, 0xd2, 0x6c, 0x32, 0x03, 0xb0, 0xa0, 0x8c, + 0x52, 0xeb, 0x23, 0x91, 0x88, 0x43, 0x13, 0x46, + 0xf6, 0x1e, 0xb4, 0x1b, 0xf5, 0x8e, 0x3a, 0xb5, + 0x3d, 0x00, 0xf6, 0xe5, 0x08, 0x3d, 0x5f, 0x39, + 0xd3, 0x21, 0x69, 0xbc, 0x03, 0x22, 0x3a, 0xd2, + 0x5c, 0x84, 0xf8, 0x15, 0xc4, 0x80, 0x0b, 0xbc, + 0x29, 0x3c, 0xf3, 0x95, 0x98, 0xcd, 0x8f, 0x35, + 0xbc, 0xa5, 0x3e, 0xfc, 0xd4, 0x13, 0x9e, 0xde, + 0x4f, 0xce, 0x71, 0x9d, 0x09, 0xad, 0xf2, 0x80, + 0x6b, 0x65, 0x7f, 0x03, 0x00, 0x14, 0x7c, 0x15, + 0x85, 0x40, 0x6d, 0x70, 0xea, 0xdc, 0xb3, 0x63, + 0x35, 0x4f, 0x4d, 0xe0, 0xd9, 0xd5, 0x3c, 0x58, + 0x56, 0x23, 0x80, 0xe2, 0x36, 0xdd, 0x75, 0x1d, + 0x94, 0x11, 0x41, 0x8e, 0xe0, 0x81, 0x8e, 0xcf, + 0xe0, 0xe5, 0xf6, 0xde, 0xd1, 0xe7, 0x04, 0x12, + 0x79, 0x92, 0x2b, 0x71, 0x2a, 0x79, 0x8b, 0x7c, + 0x44, 0x79, 0x16, 0x30, 0x4e, 0xf4, 0xf6, 0x9b, + 0xb7, 0x40, 0xa3, 0x5a, 0xa7, 0x69, 0x3e, 0xc1, + 0x3a, 0x04, 0xd0, 0x88, 0xa0, 0x3b, 0xdd, 0xc6, + 0x9e, 0x7e, 0x1e, 0x1e, 0x8f, 0x44, 0xf7, 0x73, + 0x67, 0x1e, 0x1a, 0x78, 0xfa, 0x62, 0xf4, 0xa9, + 0xa8, 0xc6, 0x5b, 0xb8, 0xfa, 0x06, 0x7d, 0x5e, + 0x38, 0x1c, 0x9a, 0x39, 0xe9, 0x39, 0x98, 0x22, + 0x0b, 0xa7, 0xac, 0x0b, 0xf3, 0xbc, 0xf1, 0xeb, + 0x8c, 0x81, 0xe3, 0x48, 0x8a, 0xed, 0x42, 0xc2, + 0x38, 0xcf, 0x3e, 0xda, 0xd2, 0x89, 0x8d, 0x9c, + 0x53, 0xb5, 0x2f, 0x41, 0x01, 0x26, 0x84, 0x9c, + 0xa3, 0x56, 0xf6, 0x49, 0xc7, 0xd4, 0x9f, 0x93, + 0x1b, 0x96, 0x49, 0x5e, 0xad, 0xb3, 0x84, 0x1f, + 0x3c, 0xa4, 0xe0, 0x9b, 0xd1, 0x90, 0xbc, 0x38, + 0x6c, 0xdd, 0x95, 0x4d, 0x9d, 0xb1, 0x71, 0x57, + 0x2d, 0x34, 0xe8, 0xb8, 0x42, 0xc7, 0x99, 0x03, + 0xc7, 0x07, 0x30, 0x65, 0x91, 0x55, 0xd5, 0x90, + 0x70, 0x97, 0x37, 0x68, 0xd4, 0x11, 0xf9, 0xe8, + 0xce, 0xec, 0xdc, 0x34, 0xd5, 0xd3, 0xb7, 0xc4, + 0xb8, 0x97, 0x05, 0x92, 0xad, 0xf8, 0xe2, 0x36, + 0x64, 0x41, 0xc9, 0xc5, 0x41, 0x77, 0x52, 0xd7, + 0x2c, 0xa5, 0x24, 0x2f, 0xd9, 0x34, 0x0b, 0x47, + 0x35, 0xa7, 0x28, 0x8b, 0xc5, 0xcd, 0xe9, 0x46, + 0xac, 0x39, 0x94, 0x3c, 0x10, 0xc6, 0x29, 0x73, + 0x0e, 0x0e, 0x5d, 0xe0, 0x71, 0x03, 0x8a, 0x72, + 0x0e, 0x26, 0xb0, 0x7d, 0x84, 0xed, 0x95, 0x23, + 0x49, 0x5a, 0x45, 0x83, 0x45, 0x60, 0x11, 0x4a, + 0x46, 0x31, 0xd4, 0xd8, 0x16, 0x54, 0x98, 0x58, + 0xed, 0x6d, 0xcc, 0x5d, 0xd6, 0x50, 0x61, 0x9f, + 0x9d, 0xc5, 0x3e, 0x9d, 0x32, 0x47, 0xde, 0x96, + 0xe1, 0x5d, 0xd8, 0xf8, 0xb4, 0x69, 0x6f, 0xb9, + 0x15, 0x90, 0x57, 0x7a, 0xf6, 0xad, 0xb0, 0x5b, + 0xf5, 0xa6, 0x36, 0x94, 0xfd, 0x84, 0xce, 0x1c, + 0x0f, 0x4b, 0xd0, 0xc2, 0x5b, 0x6b, 0x56, 0xef, + 0x73, 0x93, 0x0b, 0xc3, 0xee, 0xd9, 0xcf, 0xd3, + 0xa4, 0x22, 0x58, 0xcd, 0x50, 0x6e, 0x65, 0xf4, + 0xe9, 0xb7, 0x71, 0xaf, 0x4b, 0xb3, 0xb6, 0x2f, + 0x0f, 0x0e, 0x3b, 0xc9, 0x85, 0x14, 0xf5, 0x17, + 0xe8, 0x7a, 0x3a, 0xbf, 0x5f, 0x5e, 0xf8, 0x18, + 0x48, 0xa6, 0x72, 0xab, 0x06, 0x95, 0xe9, 0xc8, + 0xa7, 0xf4, 0x32, 0x44, 0x04, 0x0c, 0x84, 0x98, + 0x73, 0xe3, 0x89, 0x8d, 0x5f, 0x7e, 0x4a, 0x42, + 0x8f, 0xc5, 0x28, 0xb1, 0x82, 0xef, 0x1c, 0x97, + 0x31, 0x3b, 0x4d, 0xe0, 0x0e, 0x10, 0x10, 0x97, + 0x93, 0x49, 0x78, 0x2f, 0x0d, 0x86, 0x8b, 0xa1, + 0x53, 0xa9, 0x81, 0x20, 0x79, 0xe7, 0x07, 0x77, + 0xb6, 0xac, 0x5e, 0xd2, 0x05, 0xcd, 0xe9, 0xdb, + 0x8a, 0x94, 0x82, 0x8a, 0x23, 0xb9, 0x3d, 0x1c, + 0xa9, 0x7d, 0x72, 0x4a, 0xed, 0x33, 0xa3, 0xdb, + 0x21, 0xa7, 0x86, 0x33, 0x45, 0xa5, 0xaa, 0x56, + 0x45, 0xb5, 0x83, 0x29, 0x40, 0x47, 0x79, 0x04, + 0x6e, 0xb9, 0x95, 0xd0, 0x81, 0x77, 0x2d, 0x48, + 0x1e, 0xfe, 0xc3, 0xc2, 0x1e, 0xe5, 0xf2, 0xbe, + 0xfd, 0x3b, 0x94, 0x9f, 0xc4, 0xc4, 0x26, 0x9d, + 0xe4, 0x66, 0x1e, 0x19, 0xee, 0x6c, 0x79, 0x97, + 0x11, 0x31, 0x4b, 0x0d, 0x01, 0xcb, 0xde, 0xa8, + 0xf6, 0x6d, 0x7c, 0x39, 0x46, 0x4e, 0x7e, 0x3f, + 0x94, 0x17, 0xdf, 0xa1, 0x7d, 0xd9, 0x1c, 0x8e, + 0xbc, 0x7d, 0x33, 0x7d, 0xe3, 0x12, 0x40, 0xca, + 0xab, 0x37, 0x11, 0x46, 0xd4, 0xae, 0xef, 0x44, + 0xa2, 0xb3, 0x6a, 0x66, 0x0e, 0x0c, 0x90, 0x7f, + 0xdf, 0x5c, 0x66, 0x5f, 0xf2, 0x94, 0x9f, 0xa6, + 0x73, 0x4f, 0xeb, 0x0d, 0xad, 0xbf, 0xc0, 0x63, + 0x5c, 0xdc, 0x46, 0x51, 0xe8, 0x8e, 0x90, 0x19, + 0xa8, 0xa4, 0x3c, 0x91, 0x79, 0xfa, 0x7e, 0x58, + 0x85, 0x13, 0x55, 0xc5, 0x19, 0x82, 0x37, 0x1b, + 0x0a, 0x02, 0x1f, 0x99, 0x6b, 0x18, 0xf1, 0x28, + 0x08, 0xa2, 0x73, 0xb8, 0x0f, 0x2e, 0xcd, 0xbf, + 0xf3, 0x86, 0x7f, 0xea, 0xef, 0xd0, 0xbb, 0xa6, + 0x21, 0xdf, 0x49, 0x73, 0x51, 0xcc, 0x36, 0xd3, + 0x3e, 0xa0, 0xf8, 0x44, 0xdf, 0xd3, 0xa6, 0xbe, + 0x8a, 0xd4, 0x57, 0xdd, 0x72, 0x94, 0x61, 0x0f, + 0x82, 0xd1, 0x07, 0xb8, 0x7c, 0x18, 0x83, 0xdf, + 0x3a, 0xe5, 0x50, 0x6a, 0x82, 0x20, 0xac, 0xa9, + 0xa8, 0xff, 0xd9, 0xf3, 0x77, 0x33, 0x5a, 0x9e, + 0x7f, 0x6d, 0xfe, 0x5d, 0x33, 0x41, 0x42, 0xe7, + 0x6c, 0x19, 0xe0, 0x44, 0x8a, 0x15, 0xf6, 0x70, + 0x98, 0xb7, 0x68, 0x4d, 0xfa, 0x97, 0x39, 0xb0, + 0x8e, 0xe8, 0x84, 0x8b, 0x75, 0x30, 0xb7, 0x7d, + 0x92, 0x69, 0x20, 0x9c, 0x81, 0xfb, 0x4b, 0xf4, + 0x01, 0x50, 0xeb, 0xce, 0x0c, 0x1c, 0x6c, 0xb5, + 0x4a, 0xd7, 0x27, 0x0c, 0xce, 0xbb, 0xe5, 0x85, + 0xf0, 0xb6, 0xee, 0xd5, 0x70, 0xdd, 0x3b, 0xfc, + 0xd4, 0x99, 0xf1, 0x33, 0xdd, 0x8b, 0xc4, 0x2f, + 0xae, 0xab, 0x74, 0x96, 0x32, 0xc7, 0x4c, 0x56, + 0x3c, 0x89, 0x0f, 0x96, 0x0b, 0x42, 0xc0, 0xcb, + 0xee, 0x0f, 0x0b, 0x8c, 0xfb, 0x7e, 0x47, 0x7b, + 0x64, 0x48, 0xfd, 0xb2, 0x00, 0x80, 0x89, 0xa5, + 0x13, 0x55, 0x62, 0xfc, 0x8f, 0xe2, 0x42, 0x03, + 0xb7, 0x4e, 0x2a, 0x79, 0xb4, 0x82, 0xea, 0x23, + 0x49, 0xda, 0xaf, 0x52, 0x63, 0x1e, 0x60, 0x03, + 0x89, 0x06, 0x44, 0x46, 0x08, 0xc3, 0xc4, 0x87, + 0x70, 0x2e, 0xda, 0x94, 0xad, 0x6b, 0xe0, 0xe4, + 0xd1, 0x8a, 0x06, 0xc2, 0xa8, 0xc0, 0xa7, 0x43, + 0x3c, 0x47, 0x52, 0x0e, 0xc3, 0x77, 0x81, 0x11, + 0x67, 0x0e, 0xa0, 0x70, 0x04, 0x47, 0x29, 0x40, + 0x86, 0x0d, 0x34, 0x56, 0xa7, 0xc9, 0x35, 0x59, + 0x68, 0xdc, 0x93, 0x81, 0x70, 0xee, 0x86, 0xd9, + 0x80, 0x06, 0x40, 0x4f, 0x1a, 0x0d, 0x40, 0x30, + 0x0b, 0xcb, 0x96, 0x47, 0xc1, 0xb7, 0x52, 0xfd, + 0x56, 0xe0, 0x72, 0x4b, 0xfb, 0xbd, 0x92, 0x45, + 0x61, 0x71, 0xc2, 0x33, 0x11, 0xbf, 0x52, 0x83, + 0x79, 0x26, 0xe0, 0x49, 0x6b, 0xb7, 0x05, 0x8b, + 0xe8, 0x0e, 0x87, 0x31, 0xd7, 0x9d, 0x8a, 0xf5, + 0xc0, 0x5f, 0x2e, 0x58, 0x4a, 0xdb, 0x11, 0xb3, + 0x6c, 0x30, 0x2a, 0x46, 0x19, 0xe3, 0x27, 0x84, + 0x1f, 0x63, 0x6e, 0xf6, 0x57, 0xc7, 0xc9, 0xd8, + 0x5e, 0xba, 0xb3, 0x87, 0xd5, 0x83, 0x26, 0x34, + 0x21, 0x9e, 0x65, 0xde, 0x42, 0xd3, 0xbe, 0x7b, + 0xbc, 0x91, 0x71, 0x44, 0x4d, 0x99, 0x3b, 0x31, + 0xe5, 0x3f, 0x11, 0x4e, 0x7f, 0x13, 0x51, 0x3b, + 0xae, 0x79, 0xc9, 0xd3, 0x81, 0x8e, 0x25, 0x40, + 0x10, 0xfc, 0x07, 0x1e, 0xf9, 0x7b, 0x9a, 0x4b, + 0x6c, 0xe3, 0xb3, 0xad, 0x1a, 0x0a, 0xdd, 0x9e, + 0x59, 0x0c, 0xa2, 0xcd, 0xae, 0x48, 0x4a, 0x38, + 0x5b, 0x47, 0x41, 0x94, 0x65, 0x6b, 0xbb, 0xeb, + 0x5b, 0xe3, 0xaf, 0x07, 0x5b, 0xd4, 0x4a, 0xa2, + 0xc9, 0x5d, 0x2f, 0x64, 0x03, 0xd7, 0x3a, 0x2c, + 0x6e, 0xce, 0x76, 0x95, 0xb4, 0xb3, 0xc0, 0xf1, + 0xe2, 0x45, 0x73, 0x7a, 0x5c, 0xab, 0xc1, 0xfc, + 0x02, 0x8d, 0x81, 0x29, 0xb3, 0xac, 0x07, 0xec, + 0x40, 0x7d, 0x45, 0xd9, 0x7a, 0x59, 0xee, 0x34, + 0xf0, 0xe9, 0xd5, 0x7b, 0x96, 0xb1, 0x3d, 0x95, + 0xcc, 0x86, 0xb5, 0xb6, 0x04, 0x2d, 0xb5, 0x92, + 0x7e, 0x76, 0xf4, 0x06, 0xa9, 0xa3, 0x12, 0x0f, + 0xb1, 0xaf, 0x26, 0xba, 0x7c, 0xfc, 0x7e, 0x1c, + 0xbc, 0x2c, 0x49, 0x97, 0x53, 0x60, 0x13, 0x0b, + 0xa6, 0x61, 0x83, 0x89, 0x42, 0xd4, 0x17, 0x0c, + 0x6c, 0x26, 0x52, 0xc3, 0xb3, 0xd4, 0x67, 0xf5, + 0xe3, 0x04, 0xb7, 0xf4, 0xcb, 0x80, 0xb8, 0xcb, + 0x77, 0x56, 0x3e, 0xaa, 0x57, 0x54, 0xee, 0xb4, + 0x2c, 0x67, 0xcf, 0xf2, 0xdc, 0xbe, 0x55, 0xf9, + 0x43, 0x1f, 0x6e, 0x22, 0x97, 0x67, 0x7f, 0xc4, + 0xef, 0xb1, 0x26, 0x31, 0x1e, 0x27, 0xdf, 0x41, + 0x80, 0x47, 0x6c, 0xe2, 0xfa, 0xa9, 0x8c, 0x2a, + 0xf6, 0xf2, 0xab, 0xf0, 0x15, 0xda, 0x6c, 0xc8, + 0xfe, 0xb5, 0x23, 0xde, 0xa9, 0x05, 0x3f, 0x06, + 0x54, 0x4c, 0xcd, 0xe1, 0xab, 0xfc, 0x0e, 0x62, + 0x33, 0x31, 0x73, 0x2c, 0x76, 0xcb, 0xb4, 0x47, + 0x1e, 0x20, 0xad, 0xd8, 0xf2, 0x31, 0xdd, 0xc4, + 0x8b, 0x0c, 0x77, 0xbe, 0xe1, 0x8b, 0x26, 0x00, + 0x02, 0x58, 0xd6, 0x8d, 0xef, 0xad, 0x74, 0x67, + 0xab, 0x3f, 0xef, 0xcb, 0x6f, 0xb0, 0xcc, 0x81, + 0x44, 0x4c, 0xaf, 0xe9, 0x49, 0x4f, 0xdb, 0xa0, + 0x25, 0xa4, 0xf0, 0x89, 0xf1, 0xbe, 0xd8, 0x10, + 0xff, 0xb1, 0x3b, 0x4b, 0xfa, 0x98, 0xf5, 0x79, + 0x6d, 0x1e, 0x69, 0x4d, 0x57, 0xb1, 0xc8, 0x19, + 0x1b, 0xbd, 0x1e, 0x8c, 0x84, 0xb7, 0x7b, 0xe8, + 0xd2, 0x2d, 0x09, 0x41, 0x41, 0x37, 0x3d, 0xb1, + 0x6f, 0x26, 0x5d, 0x71, 0x16, 0x3d, 0xb7, 0x83, + 0x27, 0x2c, 0xa7, 0xb6, 0x50, 0xbd, 0x91, 0x86, + 0xab, 0x24, 0xa1, 0x38, 0xfd, 0xea, 0x71, 0x55, + 0x7e, 0x9a, 0x07, 0x77, 0x4b, 0xfa, 0x61, 0x66, + 0x20, 0x1e, 0x28, 0x95, 0x18, 0x1b, 0xa4, 0xa0, + 0xfd, 0xc0, 0x89, 0x72, 0x43, 0xd9, 0x3b, 0x49, + 0x5a, 0x3f, 0x9d, 0xbf, 0xdb, 0xb4, 0x46, 0xea, + 0x42, 0x01, 0x77, 0x23, 0x68, 0x95, 0xb6, 0x24, + 0xb3, 0xa8, 0x6c, 0x28, 0x3b, 0x11, 0x40, 0x7e, + 0x18, 0x65, 0x6d, 0xd8, 0x24, 0x42, 0x7d, 0x88, + 0xc0, 0x52, 0xd9, 0x05, 0xe4, 0x95, 0x90, 0x87, + 0x8c, 0xf4, 0xd0, 0x6b, 0xb9, 0x83, 0x99, 0x34, + 0x6d, 0xfe, 0x54, 0x40, 0x94, 0x52, 0x21, 0x4f, + 0x14, 0x25, 0xc5, 0xd6, 0x5e, 0x95, 0xdc, 0x0a, + 0x2b, 0x89, 0x20, 0x11, 0x84, 0x48, 0xd6, 0x3a, + 0xcd, 0x5c, 0x24, 0xad, 0x62, 0xe3, 0xb1, 0x93, + 0x25, 0x8d, 0xcd, 0x7e, 0xfc, 0x27, 0xa3, 0x37, + 0xfd, 0x84, 0xfc, 0x1b, 0xb2, 0xf1, 0x27, 0x38, + 0x5a, 0xb7, 0xfc, 0xf2, 0xfa, 0x95, 0x66, 0xd4, + 0xfb, 0xba, 0xa7, 0xd7, 0xa3, 0x72, 0x69, 0x48, + 0x48, 0x8c, 0xeb, 0x28, 0x89, 0xfe, 0x33, 0x65, + 0x5a, 0x36, 0x01, 0x7e, 0x06, 0x79, 0x0a, 0x09, + 0x3b, 0x74, 0x11, 0x9a, 0x6e, 0xbf, 0xd4, 0x9e, + 0x58, 0x90, 0x49, 0x4f, 0x4d, 0x08, 0xd4, 0xe5, + 0x4a, 0x09, 0x21, 0xef, 0x8b, 0xb8, 0x74, 0x3b, + 0x91, 0xdd, 0x36, 0x85, 0x60, 0x2d, 0xfa, 0xd4, + 0x45, 0x7b, 0x45, 0x53, 0xf5, 0x47, 0x87, 0x7e, + 0xa6, 0x37, 0xc8, 0x78, 0x7a, 0x68, 0x9d, 0x8d, + 0x65, 0x2c, 0x0e, 0x91, 0x5c, 0xa2, 0x60, 0xf0, + 0x8e, 0x3f, 0xe9, 0x1a, 0xcd, 0xaa, 0xe7, 0xd5, + 0x77, 0x18, 0xaf, 0xc9, 0xbc, 0x18, 0xea, 0x48, + 0x1b, 0xfb, 0x22, 0x48, 0x70, 0x16, 0x29, 0x9e, + 0x5b, 0xc1, 0x2c, 0x66, 0x23, 0xbc, 0xf0, 0x1f, + 0xef, 0xaf, 0xe4, 0xd6, 0x04, 0x19, 0x82, 0x7a, + 0x0b, 0xba, 0x4b, 0x46, 0xb1, 0x6a, 0x85, 0x5d, + 0xb4, 0x73, 0xd6, 0x21, 0xa1, 0x71, 0x60, 0x14, + 0xee, 0x0a, 0x77, 0xc4, 0x66, 0x2e, 0xf9, 0x69, + 0x30, 0xaf, 0x41, 0x0b, 0xc8, 0x83, 0x3c, 0x53, + 0x99, 0x19, 0x27, 0x46, 0xf7, 0x41, 0x6e, 0x56, + 0xdc, 0x94, 0x28, 0x67, 0x4e, 0xb7, 0x25, 0x48, + 0x8a, 0xc2, 0xe0, 0x60, 0x96, 0xcc, 0x18, 0xf4, + 0x84, 0xdd, 0xa7, 0x5e, 0x3e, 0x05, 0x0b, 0x26, + 0x26, 0xb2, 0x5c, 0x1f, 0x57, 0x1a, 0x04, 0x7e, + 0x6a, 0xe3, 0x2f, 0xb4, 0x35, 0xb6, 0x38, 0x40, + 0x40, 0xcd, 0x6f, 0x87, 0x2e, 0xef, 0xa3, 0xd7, + 0xa9, 0xc2, 0xe8, 0x0d, 0x27, 0xdf, 0x44, 0x62, + 0x99, 0xa0, 0xfc, 0xcf, 0x81, 0x78, 0xcb, 0xfe, + 0xe5, 0xa0, 0x03, 0x4e, 0x6c, 0xd7, 0xf4, 0xaf, + 0x7a, 0xbb, 0x61, 0x82, 0xfe, 0x71, 0x89, 0xb2, + 0x22, 0x7c, 0x8e, 0x83, 0x04, 0xce, 0xf6, 0x5d, + 0x84, 0x8f, 0x95, 0x6a, 0x7f, 0xad, 0xfd, 0x32, + 0x9c, 0x5e, 0xe4, 0x9c, 0x89, 0x60, 0x54, 0xaa, + 0x96, 0x72, 0xd2, 0xd7, 0x36, 0x85, 0xa9, 0x45, + 0xd2, 0x2a, 0xa1, 0x81, 0x49, 0x6f, 0x7e, 0x04, + 0xfa, 0xe2, 0xfe, 0x90, 0x26, 0x77, 0x5a, 0x33, + 0xb8, 0x04, 0x9a, 0x7a, 0xe6, 0x4c, 0x4f, 0xad, + 0x72, 0x96, 0x08, 0x28, 0x58, 0x13, 0xf8, 0xc4, + 0x1c, 0xf0, 0xc3, 0x45, 0x95, 0x49, 0x20, 0x8c, + 0x9f, 0x39, 0x70, 0xe1, 0x77, 0xfe, 0xd5, 0x4b, + 0xaf, 0x86, 0xda, 0xef, 0x22, 0x06, 0x83, 0x36, + 0x29, 0x12, 0x11, 0x40, 0xbc, 0x3b, 0x86, 0xaa, + 0xaa, 0x65, 0x60, 0xc3, 0x80, 0xca, 0xed, 0xa9, + 0xf3, 0xb0, 0x79, 0x96, 0xa2, 0x55, 0x27, 0x28, + 0x55, 0x73, 0x26, 0xa5, 0x50, 0xea, 0x92, 0x4b, + 0x3c, 0x5c, 0x82, 0x33, 0xf0, 0x01, 0x3f, 0x03, + 0xc1, 0x08, 0x05, 0xbf, 0x98, 0xf4, 0x9b, 0x6d, + 0xa5, 0xa8, 0xb4, 0x82, 0x0c, 0x06, 0xfa, 0xff, + 0x2d, 0x08, 0xf3, 0x05, 0x4f, 0x57, 0x2a, 0x39, + 0xd4, 0x83, 0x0d, 0x75, 0x51, 0xd8, 0x5b, 0x1b, + 0xd3, 0x51, 0x5a, 0x32, 0x2a, 0x9b, 0x32, 0xb2, + 0xf2, 0xa4, 0x96, 0x12, 0xf2, 0xae, 0x40, 0x34, + 0x67, 0xa8, 0xf5, 0x44, 0xd5, 0x35, 0x53, 0xfe, + 0xa3, 0x60, 0x96, 0x63, 0x0f, 0x1f, 0x6e, 0xb0, + 0x5a, 0x42, 0xa6, 0xfc, 0x51, 0x0b, 0x60, 0x27, + 0xbc, 0x06, 0x71, 0xed, 0x65, 0x5b, 0x23, 0x86, + 0x4a, 0x07, 0x3b, 0x22, 0x07, 0x46, 0xe6, 0x90, + 0x3e, 0xf3, 0x25, 0x50, 0x1b, 0x4c, 0x7f, 0x03, + 0x08, 0xa8, 0x36, 0x6b, 0x87, 0xe5, 0xe3, 0xdb, + 0x9a, 0x38, 0x83, 0xff, 0x9f, 0x1a, 0x9f, 0x57, + 0xa4, 0x2a, 0xf6, 0x37, 0xbc, 0x1a, 0xff, 0xc9, + 0x1e, 0x35, 0x0c, 0xc3, 0x7c, 0xa3, 0xb2, 0xe5, + 0xd2, 0xc6, 0xb4, 0x57, 0x47, 0xe4, 0x32, 0x16, + 0x6d, 0xa9, 0xae, 0x64, 0xe6, 0x2d, 0x8d, 0xc5, + 0x8d, 0x50, 0x8e, 0xe8, 0x1a, 0x22, 0x34, 0x2a, + 0xd9, 0xeb, 0x51, 0x90, 0x4a, 0xb1, 0x41, 0x7d, + 0x64, 0xf9, 0xb9, 0x0d, 0xf6, 0x23, 0x33, 0xb0, + 0x33, 0xf4, 0xf7, 0x3f, 0x27, 0x84, 0xc6, 0x0f, + 0x54, 0xa5, 0xc0, 0x2e, 0xec, 0x0b, 0x3a, 0x48, + 0x6e, 0x80, 0x35, 0x81, 0x43, 0x9b, 0x90, 0xb1, + 0xd0, 0x2b, 0xea, 0x21, 0xdc, 0xda, 0x5b, 0x09, + 0xf4, 0xcc, 0x10, 0xb4, 0xc7, 0xfe, 0x79, 0x51, + 0xc3, 0xc5, 0xac, 0x88, 0x74, 0x84, 0x0b, 0x4b, + 0xca, 0x79, 0x16, 0x29, 0xfb, 0x69, 0x54, 0xdf, + 0x41, 0x7e, 0xe9, 0xc7, 0x8e, 0xea, 0xa5, 0xfe, + 0xfc, 0x76, 0x0e, 0x90, 0xc4, 0x92, 0x38, 0xad, + 0x7b, 0x48, 0xe6, 0x6e, 0xf7, 0x21, 0xfd, 0x4e, + 0x93, 0x0a, 0x7b, 0x41, 0x83, 0x68, 0xfb, 0x57, + 0x51, 0x76, 0x34, 0xa9, 0x6c, 0x00, 0xaa, 0x4f, + 0x66, 0x65, 0x98, 0x4a, 0x4f, 0xa3, 0xa0, 0xef, + 0x69, 0x3f, 0xe3, 0x1c, 0x92, 0x8c, 0xfd, 0xd8, + 0xe8, 0xde, 0x7c, 0x7f, 0x3e, 0x84, 0x8e, 0x69, + 0x3c, 0xf1, 0xf2, 0x05, 0x46, 0xdc, 0x2f, 0x9d, + 0x5e, 0x6e, 0x4c, 0xfb, 0xb5, 0x99, 0x2a, 0x59, + 0x63, 0xc1, 0x34, 0xbc, 0x57, 0xc0, 0x0d, 0xb9, + 0x61, 0x25, 0xf3, 0x33, 0x23, 0x51, 0xb6, 0x0d, + 0x07, 0xa6, 0xab, 0x94, 0x4a, 0xb7, 0x2a, 0xea, + 0xee, 0xac, 0xa3, 0xc3, 0x04, 0x8b, 0x0e, 0x56, + 0xfe, 0x44, 0xa7, 0x39, 0xe2, 0xed, 0xed, 0xb4, + 0x22, 0x2b, 0xac, 0x12, 0x32, 0x28, 0x91, 0xd8, + 0xa5, 0xab, 0xff, 0x5f, 0xe0, 0x4b, 0xda, 0x78, + 0x17, 0xda, 0xf1, 0x01, 0x5b, 0xcd, 0xe2, 0x5f, + 0x50, 0x45, 0x73, 0x2b, 0xe4, 0x76, 0x77, 0xf4, + 0x64, 0x1d, 0x43, 0xfb, 0x84, 0x7a, 0xea, 0x91, + 0xae, 0xf9, 0x9e, 0xb7, 0xb4, 0xb0, 0x91, 0x5f, + 0x16, 0x35, 0x9a, 0x11, 0xb8, 0xc7, 0xc1, 0x8c, + 0xc6, 0x10, 0x8d, 0x2f, 0x63, 0x4a, 0xa7, 0x57, + 0x3a, 0x51, 0xd6, 0x32, 0x2d, 0x64, 0x72, 0xd4, + 0x66, 0xdc, 0x10, 0xa6, 0x67, 0xd6, 0x04, 0x23, + 0x9d, 0x0a, 0x11, 0x77, 0xdd, 0x37, 0x94, 0x17, + 0x3c, 0xbf, 0x8b, 0x65, 0xb0, 0x2e, 0x5e, 0x66, + 0x47, 0x64, 0xac, 0xdd, 0xf0, 0x84, 0xfd, 0x39, + 0xfa, 0x15, 0x5d, 0xef, 0xae, 0xca, 0xc1, 0x36, + 0xa7, 0x5c, 0xbf, 0xc7, 0x08, 0xc2, 0x66, 0x00, + 0x74, 0x74, 0x4e, 0x27, 0x3f, 0x55, 0x8a, 0xb7, + 0x38, 0x66, 0x83, 0x6d, 0xcf, 0x99, 0x9e, 0x60, + 0x8f, 0xdd, 0x2e, 0x62, 0x22, 0x0e, 0xef, 0x0c, + 0x98, 0xa7, 0x85, 0x74, 0x3b, 0x9d, 0xec, 0x9e, + 0xa9, 0x19, 0x72, 0xa5, 0x7f, 0x2c, 0x39, 0xb7, + 0x7d, 0xb7, 0xf1, 0x12, 0x65, 0x27, 0x4b, 0x5a, + 0xde, 0x17, 0xfe, 0xad, 0x44, 0xf3, 0x20, 0x4d, + 0xfd, 0xe4, 0x1f, 0xb5, 0x81, 0xb0, 0x36, 0x37, + 0x08, 0x6f, 0xc3, 0x0c, 0xe9, 0x85, 0x98, 0x82, + 0xa9, 0x62, 0x0c, 0xc4, 0x97, 0xc0, 0x50, 0xc8, + 0xa7, 0x3c, 0x50, 0x9f, 0x43, 0xb9, 0xcd, 0x5e, + 0x4d, 0xfa, 0x1c, 0x4b, 0x0b, 0xa9, 0x98, 0x85, + 0x38, 0x92, 0xac, 0x8d, 0xe4, 0xad, 0x9b, 0x98, + 0xab, 0xd9, 0x38, 0xac, 0x62, 0x52, 0xa3, 0x22, + 0x63, 0x0f, 0xbf, 0x95, 0x48, 0xdf, 0x69, 0xe7, + 0x8b, 0x33, 0xd5, 0xb2, 0xbd, 0x05, 0x49, 0x49, + 0x9d, 0x57, 0x73, 0x19, 0x33, 0xae, 0xfa, 0x33, + 0xf1, 0x19, 0xa8, 0x80, 0xce, 0x04, 0x9f, 0xbc, + 0x1d, 0x65, 0x82, 0x1b, 0xe5, 0x3a, 0x51, 0xc8, + 0x1c, 0x21, 0xe3, 0x5d, 0xf3, 0x7d, 0x9b, 0x2f, + 0x2c, 0x1d, 0x4a, 0x7f, 0x9b, 0x68, 0x35, 0xa3, + 0xb2, 0x50, 0xf7, 0x62, 0x79, 0xcd, 0xf4, 0x98, + 0x4f, 0xe5, 0x63, 0x7c, 0x3e, 0x45, 0x31, 0x8c, + 0x16, 0xa0, 0x12, 0xc8, 0x58, 0xce, 0x39, 0xa6, + 0xbc, 0x54, 0xdb, 0xc5, 0xe0, 0xd5, 0xba, 0xbc, + 0xb9, 0x04, 0xf4, 0x8d, 0xe8, 0x2f, 0x15, 0x9d, +}; + +/* 100 test cases */ +static struct dahash_test { + uint16_t start; /* random 12 bit offset in buf */ + uint16_t length; /* random 8 bit length of test */ + xfs_dahash_t dahash; /* expected dahash result */ +} test[] __initdata = +{ + {0x0567, 0x0097, 0x96951389}, + {0x0869, 0x0055, 0x6455ab4f}, + {0x0c51, 0x00be, 0x8663afde}, + {0x044a, 0x00fc, 0x98fbe432}, + {0x0f29, 0x0079, 0x42371997}, + {0x08ba, 0x0052, 0x942be4f7}, + {0x01f2, 0x0013, 0x5262687e}, + {0x09e3, 0x00e2, 0x8ffb0908}, + {0x007c, 0x0051, 0xb3158491}, + {0x0854, 0x001f, 0x83bb20d9}, + {0x031b, 0x0008, 0x98970bdf}, + {0x0de7, 0x0027, 0xbfbf6f6c}, + {0x0f76, 0x0005, 0x906a7105}, + {0x092e, 0x00d0, 0x86631850}, + {0x0233, 0x0082, 0xdbdd914e}, + {0x04c9, 0x0075, 0x5a400a9e}, + {0x0b66, 0x0099, 0xae128b45}, + {0x000d, 0x00ed, 0xe61c216a}, + {0x0a31, 0x003d, 0xf69663b9}, + {0x00a3, 0x0052, 0x643c39ae}, + {0x0125, 0x00d5, 0x7c310b0d}, + {0x0105, 0x004a, 0x06a77e74}, + {0x0858, 0x008e, 0x265bc739}, + {0x045e, 0x0095, 0x13d6b192}, + {0x0dab, 0x003c, 0xc4498704}, + {0x00cd, 0x00b5, 0x802a4e2d}, + {0x069b, 0x008c, 0x5df60f71}, + {0x0454, 0x006c, 0x5f03d8bb}, + {0x040e, 0x0032, 0x0ce513b5}, + {0x0874, 0x00e2, 0x6a811fb3}, + {0x0521, 0x00b4, 0x93296833}, + {0x0ddc, 0x00cf, 0xf9305338}, + {0x0a70, 0x0023, 0x239549ea}, + {0x083e, 0x0027, 0x2d88ba97}, + {0x0241, 0x00a7, 0xfe0b32e1}, + {0x0dfc, 0x0096, 0x1a11e815}, + {0x023e, 0x001e, 0xebc9a1f3}, + {0x067e, 0x0066, 0xb1067f81}, + {0x09ea, 0x000e, 0x46fd7247}, + {0x036b, 0x008c, 0x1a39acdf}, + {0x078f, 0x0030, 0x964042ab}, + {0x085c, 0x008f, 0x1829edab}, + {0x02ec, 0x009f, 0x6aefa72d}, + {0x043b, 0x00ce, 0x65642ff5}, + {0x0a32, 0x00b8, 0xbd82759e}, + {0x0d3c, 0x0087, 0xf4d66d54}, + {0x09ec, 0x008a, 0x06bfa1ff}, + {0x0902, 0x0015, 0x755025d2}, + {0x08fe, 0x000e, 0xf690ce2d}, + {0x00fb, 0x00dc, 0xe55f1528}, + {0x0eaa, 0x003a, 0x0fe0a8d7}, + {0x05fb, 0x0006, 0x86281cfb}, + {0x0dd1, 0x00a7, 0x60ab51b4}, + {0x0005, 0x001b, 0xf51d969b}, + {0x077c, 0x00dd, 0xc2fed268}, + {0x0575, 0x00f5, 0x432c0b1a}, + {0x05be, 0x0088, 0x78baa04b}, + {0x0c89, 0x0068, 0xeda9e428}, + {0x0f5c, 0x0068, 0xec143c76}, + {0x06a8, 0x0009, 0xd72651ce}, + {0x060f, 0x008e, 0x765426cd}, + {0x07b1, 0x0047, 0x2cfcfa0c}, + {0x04f1, 0x0041, 0x55b172f9}, + {0x0e05, 0x00ac, 0x61efde93}, + {0x0bf7, 0x0097, 0x05b83eee}, + {0x04e9, 0x00f3, 0x9928223a}, + {0x023a, 0x0005, 0xdfada9bc}, + {0x0acb, 0x000e, 0x2217cecd}, + {0x0148, 0x0060, 0xbc3f7405}, + {0x0764, 0x0059, 0xcbc201b1}, + {0x021f, 0x0059, 0x5d6b2256}, + {0x0f1e, 0x006c, 0xdefeeb45}, + {0x071c, 0x00b9, 0xb9b59309}, + {0x0564, 0x0063, 0xae064271}, + {0x0b14, 0x0044, 0xdb867d9b}, + {0x0e5a, 0x0055, 0xff06b685}, + {0x015e, 0x00ba, 0x1115ccbc}, + {0x0379, 0x00e6, 0x5f4e58dd}, + {0x013b, 0x0067, 0x4897427e}, + {0x0e64, 0x0071, 0x7af2b7a4}, + {0x0a11, 0x0050, 0x92105726}, + {0x0109, 0x0055, 0xd0d000f9}, + {0x00aa, 0x0022, 0x815d229d}, + {0x09ac, 0x004f, 0x02f9d985}, + {0x0e1b, 0x00ce, 0x5cf92ab4}, + {0x08af, 0x00d8, 0x17ca72d1}, + {0x0e33, 0x000a, 0xda2dba6b}, + {0x0ee3, 0x006a, 0xb00048e5}, + {0x0648, 0x001a, 0x2364b8cb}, + {0x0315, 0x0085, 0x0596fd0d}, + {0x0fbb, 0x003e, 0x298230ca}, + {0x0422, 0x006a, 0x78ada4ab}, + {0x04ba, 0x0073, 0xced1fbc2}, + {0x007d, 0x0061, 0x4b7ff236}, + {0x070b, 0x00d0, 0x261cf0ae}, + {0x0c1a, 0x0035, 0x8be92ee2}, + {0x0af8, 0x0063, 0x824dcf03}, + {0x08f8, 0x006d, 0xd289710c}, + {0x021b, 0x00ee, 0x6ac1c41d}, + {0x05b5, 0x00da, 0x8e52f0e2}, +}; + +int __init +xfs_dahash_test(void) +{ + unsigned int i; + unsigned int errors = 0; + + for (i = 0; i < ARRAY_SIZE(test); i++) { + xfs_dahash_t hash; + + hash = xfs_da_hashname(test_buf + test[i].start, + test[i].length); + if (hash != test[i].dahash) + errors++; + } + + if (errors) { + printk(KERN_ERR "xfs dir/attr hash test failed %u times!", + errors); + return -ERANGE; + } + + return 0; +} diff --git a/fs/xfs/xfs_dahash_test.h b/fs/xfs/xfs_dahash_test.h new file mode 100644 index 000000000000..1a05bf4bd9e1 --- /dev/null +++ b/fs/xfs/xfs_dahash_test.h @@ -0,0 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2023 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <djwong@kernel.org> + */ +#ifndef __XFS_DAHASH_TEST_H__ +#define __XFS_DAHASH_TEST_H__ + +int xfs_dahash_test(void); + +#endif /* __XFS_DAHASH_TEST_H__ */ + diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 69dbe7814128..285885c308bd 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1090,9 +1090,12 @@ xfs_buffered_write_iomap_begin( */ if (xfs_has_allocsize(mp)) prealloc_blocks = mp->m_allocsize_blocks; - else + else if (allocfork == XFS_DATA_FORK) prealloc_blocks = xfs_iomap_prealloc_size(ip, allocfork, offset, count, &icur); + else + prealloc_blocks = xfs_iomap_prealloc_size(ip, allocfork, + offset, count, &ccur); if (prealloc_blocks) { xfs_extlen_t align; xfs_off_t end_offset; diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 7dc0db7f5a76..6abcc34fafd8 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -1321,15 +1321,14 @@ xfs_qm_quotacheck( error = xfs_iwalk_threaded(mp, 0, 0, xfs_qm_dqusage_adjust, 0, true, NULL); - if (error) { - /* - * The inode walk may have partially populated the dquot - * caches. We must purge them before disabling quota and - * tearing down the quotainfo, or else the dquots will leak. - */ - xfs_qm_dqpurge_all(mp); - goto error_return; - } + + /* + * On error, the inode walk may have partially populated the dquot + * caches. We must purge them before disabling quota and tearing down + * the quotainfo, or else the dquots will leak. + */ + if (error) + goto error_purge; /* * We've made all the changes that we need to make incore. Flush them @@ -1363,10 +1362,8 @@ xfs_qm_quotacheck( * and turn quotaoff. The dquots won't be attached to any of the inodes * at this point (because we intentionally didn't in dqget_noattach). */ - if (error) { - xfs_qm_dqpurge_all(mp); - goto error_return; - } + if (error) + goto error_purge; /* * If one type of quotas is off, then it will lose its @@ -1376,7 +1373,7 @@ xfs_qm_quotacheck( mp->m_qflags &= ~XFS_ALL_QUOTA_CHKD; mp->m_qflags |= flags; - error_return: +error_return: xfs_buf_delwri_cancel(&buffer_list); if (error) { @@ -1395,6 +1392,21 @@ xfs_qm_quotacheck( } else xfs_notice(mp, "Quotacheck: Done."); return error; + +error_purge: + /* + * On error, we may have inodes queued for inactivation. This may try + * to attach dquots to the inode before running cleanup operations on + * the inode and this can race with the xfs_qm_destroy_quotainfo() call + * below that frees mp->m_quotainfo. To avoid this race, flush all the + * pending inodegc operations before we purge the dquots from memory, + * ensuring that background inactivation is idle whilst we turn off + * quotas. + */ + xfs_inodegc_flush(mp); + xfs_qm_dqpurge_all(mp); + goto error_return; + } /* diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 2479b5cbd75e..4f814f9e12ab 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -41,6 +41,7 @@ #include "xfs_attr_item.h" #include "xfs_xattr.h" #include "xfs_iunlink_item.h" +#include "xfs_dahash_test.h" #include <linux/magic.h> #include <linux/fs_context.h> @@ -2286,6 +2287,10 @@ init_xfs_fs(void) xfs_check_ondisk_structs(); + error = xfs_dahash_test(); + if (error) + return error; + printk(KERN_INFO XFS_VERSION_STRING " with " XFS_BUILD_OPTIONS " enabled\n"); diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 7dc0fd6a6504..9c0006c55fec 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -1883,6 +1883,13 @@ DEFINE_ALLOC_EVENT(xfs_alloc_vextent_noagbp); DEFINE_ALLOC_EVENT(xfs_alloc_vextent_loopfailed); DEFINE_ALLOC_EVENT(xfs_alloc_vextent_allfailed); +DEFINE_ALLOC_EVENT(xfs_alloc_vextent_this_ag); +DEFINE_ALLOC_EVENT(xfs_alloc_vextent_start_ag); +DEFINE_ALLOC_EVENT(xfs_alloc_vextent_first_ag); +DEFINE_ALLOC_EVENT(xfs_alloc_vextent_exact_bno); +DEFINE_ALLOC_EVENT(xfs_alloc_vextent_near_bno); +DEFINE_ALLOC_EVENT(xfs_alloc_vextent_finish); + TRACE_EVENT(xfs_alloc_cur_check, TP_PROTO(struct xfs_mount *mp, xfs_btnum_t btnum, xfs_agblock_t bno, xfs_extlen_t len, xfs_extlen_t diff, bool new), diff --git a/fs/zonefs/file.c b/fs/zonefs/file.c index 738b0e28d74b..132f01d3461f 100644 --- a/fs/zonefs/file.c +++ b/fs/zonefs/file.c @@ -382,14 +382,28 @@ static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from) struct zonefs_zone *z = zonefs_inode_zone(inode); struct block_device *bdev = inode->i_sb->s_bdev; unsigned int max = bdev_max_zone_append_sectors(bdev); + pgoff_t start, end; struct bio *bio; - ssize_t size; + ssize_t size = 0; int nr_pages; ssize_t ret; max = ALIGN_DOWN(max << SECTOR_SHIFT, inode->i_sb->s_blocksize); iov_iter_truncate(from, max); + /* + * If the inode block size (zone write granularity) is smaller than the + * page size, we may be appending data belonging to the last page of the + * inode straddling inode->i_size, with that page already cached due to + * a buffered read or readahead. So make sure to invalidate that page. + * This will always be a no-op for the case where the block size is + * equal to the page size. + */ + start = iocb->ki_pos >> PAGE_SHIFT; + end = (iocb->ki_pos + iov_iter_count(from) - 1) >> PAGE_SHIFT; + if (invalidate_inode_pages2_range(inode->i_mapping, start, end)) + return -EBUSY; + nr_pages = iov_iter_npages(from, BIO_MAX_VECS); if (!nr_pages) return 0; @@ -426,7 +440,7 @@ static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from) if (bio->bi_iter.bi_sector != wpsector) { zonefs_warn(inode->i_sb, "Corrupted write pointer %llu for zone at %llu\n", - wpsector, z->z_sector); + bio->bi_iter.bi_sector, z->z_sector); ret = -EIO; } } @@ -567,11 +581,21 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from) append = sync; } - if (append) + if (append) { ret = zonefs_file_dio_append(iocb, from); - else + } else { + /* + * iomap_dio_rw() may return ENOTBLK if there was an issue with + * page invalidation. Overwrite that error code with EBUSY to + * be consistent with zonefs_file_dio_append() return value for + * similar issues. + */ ret = iomap_dio_rw(iocb, from, &zonefs_write_iomap_ops, &zonefs_write_dio_ops, 0, NULL, 0); + if (ret == -ENOTBLK) + ret = -EBUSY; + } + if (zonefs_zone_is_seq(z) && (ret > 0 || ret == -EIOCBQUEUED)) { if (ret > 0) |