diff options
Diffstat (limited to 'fs')
171 files changed, 5736 insertions, 1377 deletions
diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index 15a99f9c7253..39def020a074 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -500,10 +500,9 @@ void v9fs_session_close(struct v9fs_session_info *v9ses) } #ifdef CONFIG_9P_FSCACHE - if (v9ses->fscache) { + if (v9ses->fscache) v9fs_cache_session_put_cookie(v9ses); - kfree(v9ses->cachetag); - } + kfree(v9ses->cachetag); #endif kfree(v9ses->uname); kfree(v9ses->aname); diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index c9255d399917..ae0c38ad1fcb 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -223,8 +223,7 @@ v9fs_blank_wstat(struct p9_wstat *wstat) struct inode *v9fs_alloc_inode(struct super_block *sb) { struct v9fs_inode *v9inode; - v9inode = (struct v9fs_inode *)kmem_cache_alloc(v9fs_inode_cache, - GFP_KERNEL); + v9inode = kmem_cache_alloc(v9fs_inode_cache, GFP_KERNEL); if (!v9inode) return NULL; #ifdef CONFIG_9P_FSCACHE @@ -368,59 +367,6 @@ struct inode *v9fs_get_inode(struct super_block *sb, umode_t mode, dev_t rdev) return inode; } -/* -static struct v9fs_fid* -v9fs_clone_walk(struct v9fs_session_info *v9ses, u32 fid, struct dentry *dentry) -{ - int err; - int nfid; - struct v9fs_fid *ret; - struct v9fs_fcall *fcall; - - nfid = v9fs_get_idpool(&v9ses->fidpool); - if (nfid < 0) { - eprintk(KERN_WARNING, "no free fids available\n"); - return ERR_PTR(-ENOSPC); - } - - err = v9fs_t_walk(v9ses, fid, nfid, (char *) dentry->d_name.name, - &fcall); - - if (err < 0) { - if (fcall && fcall->id == RWALK) - goto clunk_fid; - - PRINT_FCALL_ERROR("walk error", fcall); - v9fs_put_idpool(nfid, &v9ses->fidpool); - goto error; - } - - kfree(fcall); - fcall = NULL; - ret = v9fs_fid_create(v9ses, nfid); - if (!ret) { - err = -ENOMEM; - goto clunk_fid; - } - - err = v9fs_fid_insert(ret, dentry); - if (err < 0) { - v9fs_fid_destroy(ret); - goto clunk_fid; - } - - return ret; - -clunk_fid: - v9fs_t_clunk(v9ses, nfid); - -error: - kfree(fcall); - return ERR_PTR(err); -} -*/ - - /** * v9fs_clear_inode - release an inode * @inode: inode to release @@ -1090,7 +1036,7 @@ static int v9fs_vfs_setattr(struct dentry *dentry, struct iattr *iattr) { int retval; struct v9fs_session_info *v9ses; - struct p9_fid *fid; + struct p9_fid *fid = NULL; struct p9_wstat wstat; p9_debug(P9_DEBUG_VFS, "\n"); @@ -1100,7 +1046,12 @@ static int v9fs_vfs_setattr(struct dentry *dentry, struct iattr *iattr) retval = -EPERM; v9ses = v9fs_dentry2v9ses(dentry); - fid = v9fs_fid_lookup(dentry); + if (iattr->ia_valid & ATTR_FILE) { + fid = iattr->ia_file->private_data; + WARN_ON(!fid); + } + if (!fid) + fid = v9fs_fid_lookup(dentry); if(IS_ERR(fid)) return PTR_ERR(fid); diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index 60328b21c5fb..0028eccb665a 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -540,7 +540,7 @@ static int v9fs_mapped_iattr_valid(int iattr_valid) int v9fs_vfs_setattr_dotl(struct dentry *dentry, struct iattr *iattr) { int retval; - struct p9_fid *fid; + struct p9_fid *fid = NULL; struct p9_iattr_dotl p9attr; struct inode *inode = d_inode(dentry); @@ -560,7 +560,12 @@ int v9fs_vfs_setattr_dotl(struct dentry *dentry, struct iattr *iattr) p9attr.mtime_sec = iattr->ia_mtime.tv_sec; p9attr.mtime_nsec = iattr->ia_mtime.tv_nsec; - fid = v9fs_fid_lookup(dentry); + if (iattr->ia_valid & ATTR_FILE) { + fid = iattr->ia_file->private_data; + WARN_ON(!fid); + } + if (!fid) + fid = v9fs_fid_lookup(dentry); if (IS_ERR(fid)) return PTR_ERR(fid); diff --git a/fs/autofs/dev-ioctl.c b/fs/autofs/dev-ioctl.c index f3a0f412b43b..75105f45c51a 100644 --- a/fs/autofs/dev-ioctl.c +++ b/fs/autofs/dev-ioctl.c @@ -20,7 +20,7 @@ * another mount. This situation arises when starting automount(8) * or other user space daemon which uses direct mounts or offset * mounts (used for autofs lazy mount/umount of nested mount trees), - * which have been left busy at at service shutdown. + * which have been left busy at service shutdown. */ typedef int (*ioctl_fn)(struct file *, struct autofs_sb_info *, @@ -496,7 +496,7 @@ static int autofs_dev_ioctl_askumount(struct file *fp, * located path is the root of a mount we return 1 along with * the super magic of the mount or 0 otherwise. * - * In both cases the the device number (as returned by + * In both cases the device number (as returned by * new_encode_dev()) is also returned. */ static int autofs_dev_ioctl_ismountpoint(struct file *fp, diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index ea10f7bc99ab..ea1c28ccb44f 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -2303,7 +2303,7 @@ struct btrfs_backref_iter *btrfs_backref_iter_alloc( return NULL; ret->path = btrfs_alloc_path(); - if (!ret) { + if (!ret->path) { kfree(ret); return NULL; } diff --git a/fs/btrfs/extent-io-tree.h b/fs/btrfs/extent-io-tree.h index f39d47a2d01a..219a09a2b734 100644 --- a/fs/btrfs/extent-io-tree.h +++ b/fs/btrfs/extent-io-tree.h @@ -34,6 +34,8 @@ struct io_failure_record; */ #define CHUNK_ALLOCATED EXTENT_DIRTY #define CHUNK_TRIMMED EXTENT_DEFRAG +#define CHUNK_STATE_MASK (CHUNK_ALLOCATED | \ + CHUNK_TRIMMED) enum { IO_TREE_FS_PINNED_EXTENTS, diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 61ede335f6c3..de6fe176fdfb 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -33,6 +33,7 @@ #include "delalloc-space.h" #include "block-group.h" #include "discard.h" +#include "rcu-string.h" #undef SCRAMBLE_DELAYED_REFS @@ -5668,6 +5669,19 @@ static int btrfs_trim_free_extents(struct btrfs_device *device, u64 *trimmed) &start, &end, CHUNK_TRIMMED | CHUNK_ALLOCATED); + /* Check if there are any CHUNK_* bits left */ + if (start > device->total_bytes) { + WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG)); + btrfs_warn_in_rcu(fs_info, +"ignoring attempt to trim beyond device size: offset %llu length %llu device %s device size %llu", + start, end - start + 1, + rcu_str_deref(device->name), + device->total_bytes); + mutex_unlock(&fs_info->chunk_mutex); + ret = 0; + break; + } + /* Ensure we skip the reserved area in the first 1M */ start = max_t(u64, start, SZ_1M); diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 6d961e11639e..ef0fd7afb0b1 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -2282,7 +2282,7 @@ out: static bool try_merge_free_space(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *info, bool update_stat) { - struct btrfs_free_space *left_info; + struct btrfs_free_space *left_info = NULL; struct btrfs_free_space *right_info; bool merged = false; u64 offset = info->offset; @@ -2298,7 +2298,7 @@ static bool try_merge_free_space(struct btrfs_free_space_ctl *ctl, if (right_info && rb_prev(&right_info->offset_index)) left_info = rb_entry(rb_prev(&right_info->offset_index), struct btrfs_free_space, offset_index); - else + else if (!right_info) left_info = tree_search_offset(ctl, offset - 1, 0, 0); /* See try_merge_free_space() comment. */ diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 6dc03bab0c9d..51fcd82d41c0 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -654,12 +654,18 @@ cont: page_error_op | PAGE_END_WRITEBACK); - for (i = 0; i < nr_pages; i++) { - WARN_ON(pages[i]->mapping); - put_page(pages[i]); + /* + * Ensure we only free the compressed pages if we have + * them allocated, as we can still reach here with + * inode_need_compress() == false. + */ + if (pages) { + for (i = 0; i < nr_pages; i++) { + WARN_ON(pages[i]->mapping); + put_page(pages[i]); + } + kfree(pages); } - kfree(pages); - return 0; } } @@ -6622,7 +6628,7 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode, extent_type == BTRFS_FILE_EXTENT_PREALLOC) { /* Only regular file could have regular/prealloc extent */ if (!S_ISREG(inode->vfs_inode.i_mode)) { - ret = -EUCLEAN; + err = -EUCLEAN; btrfs_crit(fs_info, "regular/prealloc extent found for non-regular inode %llu", btrfs_ino(inode)); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 5a9dc31d95c9..e529ddb35b87 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -517,6 +517,7 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, char *compress_type; bool compress_force = false; enum btrfs_compression_type saved_compress_type; + int saved_compress_level; bool saved_compress_force; int no_compress = 0; @@ -598,6 +599,7 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, info->compress_type : BTRFS_COMPRESS_NONE; saved_compress_force = btrfs_test_opt(info, FORCE_COMPRESS); + saved_compress_level = info->compress_level; if (token == Opt_compress || token == Opt_compress_force || strncmp(args[0].from, "zlib", 4) == 0) { @@ -642,6 +644,8 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, no_compress = 0; } else if (strncmp(args[0].from, "no", 2) == 0) { compress_type = "no"; + info->compress_level = 0; + info->compress_type = 0; btrfs_clear_opt(info->mount_opt, COMPRESS); btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS); compress_force = false; @@ -662,11 +666,11 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, */ btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS); } - if ((btrfs_test_opt(info, COMPRESS) && - (info->compress_type != saved_compress_type || - compress_force != saved_compress_force)) || - (!btrfs_test_opt(info, COMPRESS) && - no_compress == 1)) { + if (no_compress == 1) { + btrfs_info(info, "use no compression"); + } else if ((info->compress_type != saved_compress_type) || + (compress_force != saved_compress_force) || + (info->compress_level != saved_compress_level)) { btrfs_info(info, "%s %s compression, level %d", (compress_force) ? "force" : "use", compress_type, info->compress_level); @@ -1382,6 +1386,7 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry) { struct btrfs_fs_info *info = btrfs_sb(dentry->d_sb); const char *compress_type; + const char *subvol_name; if (btrfs_test_opt(info, DEGRADED)) seq_puts(seq, ",degraded"); @@ -1468,8 +1473,13 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry) seq_puts(seq, ",ref_verify"); seq_printf(seq, ",subvolid=%llu", BTRFS_I(d_inode(dentry))->root->root_key.objectid); - seq_puts(seq, ",subvol="); - seq_dentry(seq, dentry, " \t\n\\"); + subvol_name = btrfs_get_subvol_name_from_objectid(info, + BTRFS_I(d_inode(dentry))->root->root_key.objectid); + if (!IS_ERR(subvol_name)) { + seq_puts(seq, ",subvol="); + seq_escape(seq, subvol_name, " \t\n\\"); + kfree(subvol_name); + } return 0; } @@ -1950,6 +1960,12 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) set_bit(BTRFS_FS_OPEN, &fs_info->flags); } out: + /* + * We need to set SB_I_VERSION here otherwise it'll get cleared by VFS, + * since the absence of the flag means it can be toggled off by remount. + */ + *flags |= SB_I_VERSION; + wake_up_process(fs_info->transaction_kthread); btrfs_remount_cleanup(fs_info, old_opts); clear_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state); diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index 104c80caaa74..c8df2edafd85 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -1565,9 +1565,11 @@ void btrfs_sysfs_del_qgroups(struct btrfs_fs_info *fs_info) rbtree_postorder_for_each_entry_safe(qgroup, next, &fs_info->qgroup_tree, node) btrfs_sysfs_del_one_qgroup(fs_info, qgroup); - kobject_del(fs_info->qgroups_kobj); - kobject_put(fs_info->qgroups_kobj); - fs_info->qgroups_kobj = NULL; + if (fs_info->qgroups_kobj) { + kobject_del(fs_info->qgroups_kobj); + kobject_put(fs_info->qgroups_kobj); + fs_info->qgroups_kobj = NULL; + } } /* Called when qgroups get initialized, thus there is no need for locking */ diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index ea8136dcf71f..696dd861cc3c 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -4036,11 +4036,8 @@ static noinline int copy_items(struct btrfs_trans_handle *trans, fs_info->csum_root, ds + cs, ds + cs + cl - 1, &ordered_sums, 0); - if (ret) { - btrfs_release_path(dst_path); - kfree(ins_data); - return ret; - } + if (ret) + break; } } } @@ -4053,7 +4050,6 @@ static noinline int copy_items(struct btrfs_trans_handle *trans, * we have to do this after the loop above to avoid changing the * log tree while trying to change the log tree. */ - ret = 0; while (!list_empty(&ordered_sums)) { struct btrfs_ordered_sum *sums = list_entry(ordered_sums.next, struct btrfs_ordered_sum, diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index d7670e2a9f39..ee96c5869f57 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -4720,6 +4720,10 @@ again: } mutex_lock(&fs_info->chunk_mutex); + /* Clear all state bits beyond the shrunk device size */ + clear_extent_bits(&device->alloc_state, new_size, (u64)-1, + CHUNK_STATE_MASK); + btrfs_device_set_disk_total_bytes(device, new_size); if (list_empty(&device->post_commit_list)) list_add_tail(&device->post_commit_list, diff --git a/fs/ceph/Kconfig b/fs/ceph/Kconfig index cf235f6eacf9..471e40156065 100644 --- a/fs/ceph/Kconfig +++ b/fs/ceph/Kconfig @@ -13,7 +13,7 @@ config CEPH_FS scalable file system designed to provide high performance, reliable access to petabytes of storage. - More information at http://ceph.newdream.net/. + More information at https://ceph.io/. If unsure, say N. diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 01ad09733ac7..6ea761c84494 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -862,8 +862,7 @@ static void writepages_finish(struct ceph_osd_request *req) osd_data = osd_req_op_extent_osd_data(req, 0); if (osd_data->pages_from_pool) - mempool_free(osd_data->pages, - ceph_sb_to_client(inode->i_sb)->wb_pagevec_pool); + mempool_free(osd_data->pages, ceph_wb_pagevec_pool); else kfree(osd_data->pages); ceph_osdc_put_request(req); @@ -955,10 +954,10 @@ retry: int num_ops = 0, op_idx; unsigned i, pvec_pages, max_pages, locked_pages = 0; struct page **pages = NULL, **data_pages; - mempool_t *pool = NULL; /* Becomes non-null if mempool used */ struct page *page; pgoff_t strip_unit_end = 0; u64 offset = 0, len = 0; + bool from_pool = false; max_pages = wsize >> PAGE_SHIFT; @@ -1057,16 +1056,16 @@ get_more_pages: sizeof(*pages), GFP_NOFS); if (!pages) { - pool = fsc->wb_pagevec_pool; - pages = mempool_alloc(pool, GFP_NOFS); + from_pool = true; + pages = mempool_alloc(ceph_wb_pagevec_pool, GFP_NOFS); BUG_ON(!pages); } len = 0; } else if (page->index != (offset + len) >> PAGE_SHIFT) { - if (num_ops >= (pool ? CEPH_OSD_SLAB_OPS : - CEPH_OSD_MAX_OPS)) { + if (num_ops >= (from_pool ? CEPH_OSD_SLAB_OPS : + CEPH_OSD_MAX_OPS)) { redirty_page_for_writepage(wbc, page); unlock_page(page); break; @@ -1161,7 +1160,7 @@ new_request: offset, len); osd_req_op_extent_osd_data_pages(req, op_idx, data_pages, len, 0, - !!pool, false); + from_pool, false); osd_req_op_extent_update(req, op_idx, len); len = 0; @@ -1188,12 +1187,12 @@ new_request: dout("writepages got pages at %llu~%llu\n", offset, len); osd_req_op_extent_osd_data_pages(req, op_idx, data_pages, len, - 0, !!pool, false); + 0, from_pool, false); osd_req_op_extent_update(req, op_idx, len); BUG_ON(op_idx + 1 != req->r_num_ops); - pool = NULL; + from_pool = false; if (i < locked_pages) { BUG_ON(num_ops <= req->r_num_ops); num_ops -= req->r_num_ops; @@ -1204,8 +1203,8 @@ new_request: pages = kmalloc_array(locked_pages, sizeof(*pages), GFP_NOFS); if (!pages) { - pool = fsc->wb_pagevec_pool; - pages = mempool_alloc(pool, GFP_NOFS); + from_pool = true; + pages = mempool_alloc(ceph_wb_pagevec_pool, GFP_NOFS); BUG_ON(!pages); } memcpy(pages, data_pages + i, diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 972c13aa4225..55ccccf77cea 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -668,6 +668,7 @@ void ceph_add_cap(struct inode *inode, spin_lock(&session->s_cap_lock); list_add_tail(&cap->session_caps, &session->s_caps); session->s_nr_caps++; + atomic64_inc(&mdsc->metric.total_caps); spin_unlock(&session->s_cap_lock); } else { spin_lock(&session->s_cap_lock); @@ -1161,6 +1162,7 @@ void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release) } else { list_del_init(&cap->session_caps); session->s_nr_caps--; + atomic64_dec(&mdsc->metric.total_caps); cap->session = NULL; removed = 1; } @@ -4187,10 +4189,8 @@ void ceph_check_delayed_caps(struct ceph_mds_client *mdsc) struct ceph_inode_info *ci; dout("check_delayed_caps\n"); - while (1) { - spin_lock(&mdsc->cap_delay_lock); - if (list_empty(&mdsc->cap_delay_list)) - break; + spin_lock(&mdsc->cap_delay_lock); + while (!list_empty(&mdsc->cap_delay_list)) { ci = list_first_entry(&mdsc->cap_delay_list, struct ceph_inode_info, i_cap_delay_list); @@ -4200,13 +4200,13 @@ void ceph_check_delayed_caps(struct ceph_mds_client *mdsc) list_del_init(&ci->i_cap_delay_list); inode = igrab(&ci->vfs_inode); - spin_unlock(&mdsc->cap_delay_lock); - if (inode) { + spin_unlock(&mdsc->cap_delay_lock); dout("check_delayed_caps on %p\n", inode); ceph_check_caps(ci, 0, NULL); /* avoid calling iput_final() in tick thread */ ceph_async_iput(inode); + spin_lock(&mdsc->cap_delay_lock); } } spin_unlock(&mdsc->cap_delay_lock); diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c index 070ed8481340..97539b497e4c 100644 --- a/fs/ceph/debugfs.c +++ b/fs/ceph/debugfs.c @@ -145,7 +145,7 @@ static int metric_show(struct seq_file *s, void *p) struct ceph_fs_client *fsc = s->private; struct ceph_mds_client *mdsc = fsc->mdsc; struct ceph_client_metric *m = &mdsc->metric; - int i, nr_caps = 0; + int nr_caps = 0; s64 total, sum, avg, min, max, sq; seq_printf(s, "item total avg_lat(us) min_lat(us) max_lat(us) stdev(us)\n"); @@ -190,17 +190,7 @@ static int metric_show(struct seq_file *s, void *p) percpu_counter_sum(&m->d_lease_mis), percpu_counter_sum(&m->d_lease_hit)); - mutex_lock(&mdsc->mutex); - for (i = 0; i < mdsc->max_sessions; i++) { - struct ceph_mds_session *s; - - s = __ceph_lookup_mds_session(mdsc, i); - if (!s) - continue; - nr_caps += s->s_nr_caps; - ceph_put_mds_session(s); - } - mutex_unlock(&mdsc->mutex); + nr_caps = atomic64_read(&m->total_caps); seq_printf(s, "%-14s%-16d%-16lld%lld\n", "caps", nr_caps, percpu_counter_sum(&m->i_caps_mis), percpu_counter_sum(&m->i_caps_hit)); @@ -272,7 +262,7 @@ static int mds_sessions_show(struct seq_file *s, void *ptr) struct ceph_mds_client *mdsc = fsc->mdsc; struct ceph_auth_client *ac = fsc->client->monc.auth; struct ceph_options *opt = fsc->client->options; - int mds = -1; + int mds; mutex_lock(&mdsc->mutex); diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 39f5311404b0..060bdcc5ce32 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -930,6 +930,10 @@ static int ceph_symlink(struct inode *dir, struct dentry *dentry, req->r_num_caps = 2; req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_AUTH_EXCL; req->r_dentry_unless = CEPH_CAP_FILE_EXCL; + if (as_ctx.pagelist) { + req->r_pagelist = as_ctx.pagelist; + as_ctx.pagelist = NULL; + } err = ceph_mdsc_do_request(mdsc, dir, req); if (!err && !req->r_reply_info.head->is_dentry) err = ceph_handle_notrace_create(dir, dentry); diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 160644ddaeed..d51c3f2fdca0 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -1538,6 +1538,7 @@ static ssize_t ceph_read_iter(struct kiocb *iocb, struct iov_iter *to) struct inode *inode = file_inode(filp); struct ceph_inode_info *ci = ceph_inode(inode); struct page *pinned_page = NULL; + bool direct_lock = iocb->ki_flags & IOCB_DIRECT; ssize_t ret; int want, got = 0; int retry_op = 0, read = 0; @@ -1546,7 +1547,7 @@ again: dout("aio_read %p %llx.%llx %llu~%u trying to get caps on %p\n", inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len, inode); - if (iocb->ki_flags & IOCB_DIRECT) + if (direct_lock) ceph_start_io_direct(inode); else ceph_start_io_read(inode); @@ -1603,7 +1604,7 @@ again: } ceph_put_cap_refs(ci, got); - if (iocb->ki_flags & IOCB_DIRECT) + if (direct_lock) ceph_end_io_direct(inode); else ceph_end_io_read(inode); diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index a50497142e59..4a26862d7667 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -1103,8 +1103,7 @@ static int __choose_mds(struct ceph_mds_client *mdsc, frag.frag, mds); if (ceph_mdsmap_get_state(mdsc->mdsmap, mds) >= CEPH_MDS_STATE_ACTIVE) { - if (mode == USE_ANY_MDS && - !ceph_mdsmap_is_laggy(mdsc->mdsmap, + if (!ceph_mdsmap_is_laggy(mdsc->mdsmap, mds)) goto out; } @@ -1168,7 +1167,7 @@ static struct ceph_msg *create_session_msg(u32 op, u64 seq) static const unsigned char feature_bits[] = CEPHFS_FEATURES_CLIENT_SUPPORTED; #define FEATURE_BYTES(c) (DIV_ROUND_UP((size_t)feature_bits[c - 1] + 1, 64) * 8) -static void encode_supported_features(void **p, void *end) +static int encode_supported_features(void **p, void *end) { static const size_t count = ARRAY_SIZE(feature_bits); @@ -1176,16 +1175,64 @@ static void encode_supported_features(void **p, void *end) size_t i; size_t size = FEATURE_BYTES(count); - BUG_ON(*p + 4 + size > end); + if (WARN_ON_ONCE(*p + 4 + size > end)) + return -ERANGE; + ceph_encode_32(p, size); memset(*p, 0, size); for (i = 0; i < count; i++) ((unsigned char*)(*p))[i / 8] |= BIT(feature_bits[i] % 8); *p += size; } else { - BUG_ON(*p + 4 > end); + if (WARN_ON_ONCE(*p + 4 > end)) + return -ERANGE; + ceph_encode_32(p, 0); } + + return 0; +} + +static const unsigned char metric_bits[] = CEPHFS_METRIC_SPEC_CLIENT_SUPPORTED; +#define METRIC_BYTES(cnt) (DIV_ROUND_UP((size_t)metric_bits[cnt - 1] + 1, 64) * 8) +static int encode_metric_spec(void **p, void *end) +{ + static const size_t count = ARRAY_SIZE(metric_bits); + + /* header */ + if (WARN_ON_ONCE(*p + 2 > end)) + return -ERANGE; + + ceph_encode_8(p, 1); /* version */ + ceph_encode_8(p, 1); /* compat */ + + if (count > 0) { + size_t i; + size_t size = METRIC_BYTES(count); + + if (WARN_ON_ONCE(*p + 4 + 4 + size > end)) + return -ERANGE; + + /* metric spec info length */ + ceph_encode_32(p, 4 + size); + + /* metric spec */ + ceph_encode_32(p, size); + memset(*p, 0, size); + for (i = 0; i < count; i++) + ((unsigned char *)(*p))[i / 8] |= BIT(metric_bits[i] % 8); + *p += size; + } else { + if (WARN_ON_ONCE(*p + 4 + 4 > end)) + return -ERANGE; + + /* metric spec info length */ + ceph_encode_32(p, 4); + /* metric spec */ + ceph_encode_32(p, 0); + } + + return 0; } /* @@ -1203,6 +1250,7 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6 struct ceph_mount_options *fsopt = mdsc->fsc->mount_options; size_t size, count; void *p, *end; + int ret; const char* metadata[][2] = { {"hostname", mdsc->nodename}, @@ -1227,12 +1275,19 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6 size = FEATURE_BYTES(count); extra_bytes += 4 + size; + /* metric spec */ + size = 0; + count = ARRAY_SIZE(metric_bits); + if (count > 0) + size = METRIC_BYTES(count); + extra_bytes += 2 + 4 + 4 + size; + /* Allocate the message */ msg = ceph_msg_new(CEPH_MSG_CLIENT_SESSION, sizeof(*h) + extra_bytes, GFP_NOFS, false); if (!msg) { pr_err("create_session_msg ENOMEM creating msg\n"); - return NULL; + return ERR_PTR(-ENOMEM); } p = msg->front.iov_base; end = p + msg->front.iov_len; @@ -1245,9 +1300,9 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6 * Serialize client metadata into waiting buffer space, using * the format that userspace expects for map<string, string> * - * ClientSession messages with metadata are v3 + * ClientSession messages with metadata are v4 */ - msg->hdr.version = cpu_to_le16(3); + msg->hdr.version = cpu_to_le16(4); msg->hdr.compat_version = cpu_to_le16(1); /* The write pointer, following the session_head structure */ @@ -1269,7 +1324,20 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6 p += val_len; } - encode_supported_features(&p, end); + ret = encode_supported_features(&p, end); + if (ret) { + pr_err("encode_supported_features failed!\n"); + ceph_msg_put(msg); + return ERR_PTR(ret); + } + + ret = encode_metric_spec(&p, end); + if (ret) { + pr_err("encode_metric_spec failed!\n"); + ceph_msg_put(msg); + return ERR_PTR(ret); + } + msg->front.iov_len = p - msg->front.iov_base; msg->hdr.front_len = cpu_to_le32(msg->front.iov_len); @@ -1297,8 +1365,8 @@ static int __open_session(struct ceph_mds_client *mdsc, /* send connect message */ msg = create_session_open_msg(mdsc, session->s_seq); - if (!msg) - return -ENOMEM; + if (IS_ERR(msg)) + return PTR_ERR(msg); ceph_con_send(&session->s_con, msg); return 0; } @@ -1312,6 +1380,7 @@ static struct ceph_mds_session * __open_export_target_session(struct ceph_mds_client *mdsc, int target) { struct ceph_mds_session *session; + int ret; session = __ceph_lookup_mds_session(mdsc, target); if (!session) { @@ -1320,8 +1389,11 @@ __open_export_target_session(struct ceph_mds_client *mdsc, int target) return session; } if (session->s_state == CEPH_MDS_SESSION_NEW || - session->s_state == CEPH_MDS_SESSION_CLOSING) - __open_session(mdsc, session); + session->s_state == CEPH_MDS_SESSION_CLOSING) { + ret = __open_session(mdsc, session); + if (ret) + return ERR_PTR(ret); + } return session; } @@ -1485,6 +1557,7 @@ int ceph_iterate_session_caps(struct ceph_mds_session *session, cap->session = NULL; list_del_init(&cap->session_caps); session->s_nr_caps--; + atomic64_dec(&session->s_mdsc->metric.total_caps); if (cap->queue_release) __ceph_queue_cap_release(session, cap); else @@ -1785,8 +1858,7 @@ static void renewed_caps(struct ceph_mds_client *mdsc, /* * send a session close request */ -static int request_close_session(struct ceph_mds_client *mdsc, - struct ceph_mds_session *session) +static int request_close_session(struct ceph_mds_session *session) { struct ceph_msg *msg; @@ -1809,7 +1881,7 @@ static int __close_session(struct ceph_mds_client *mdsc, if (session->s_state >= CEPH_MDS_SESSION_CLOSING) return 0; session->s_state = CEPH_MDS_SESSION_CLOSING; - return request_close_session(mdsc, session); + return request_close_session(session); } static bool drop_negative_children(struct dentry *dentry) @@ -2520,7 +2592,12 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc, ceph_encode_copy(&p, &ts, sizeof(ts)); } - BUG_ON(p > end); + if (WARN_ON_ONCE(p > end)) { + ceph_msg_put(msg); + msg = ERR_PTR(-ERANGE); + goto out_free2; + } + msg->front.iov_len = p - msg->front.iov_base; msg->hdr.front_len = cpu_to_le32(msg->front.iov_len); @@ -2756,7 +2833,9 @@ static void __do_request(struct ceph_mds_client *mdsc, } if (session->s_state == CEPH_MDS_SESSION_NEW || session->s_state == CEPH_MDS_SESSION_CLOSING) { - __open_session(mdsc, session); + err = __open_session(mdsc, session); + if (err) + goto out_session; /* retry the same mds later */ if (random) req->r_resend_mds = mds; @@ -3279,8 +3358,10 @@ static void handle_session(struct ceph_mds_session *session, goto bad; /* version >= 3, feature bits */ ceph_decode_32_safe(&p, end, len, bad); - ceph_decode_64_safe(&p, end, features, bad); - p += len - sizeof(features); + if (len) { + ceph_decode_64_safe(&p, end, features, bad); + p += len - sizeof(features); + } } mutex_lock(&mdsc->mutex); @@ -3310,6 +3391,8 @@ static void handle_session(struct ceph_mds_session *session, session->s_state = CEPH_MDS_SESSION_OPEN; session->s_features = features; renewed_caps(mdsc, session, 0); + if (test_bit(CEPHFS_FEATURE_METRIC_COLLECT, &session->s_features)) + metric_schedule_delayed(&mdsc->metric); wake = 1; if (mdsc->stopping) __close_session(mdsc, session); @@ -4263,6 +4346,30 @@ static void maybe_recover_session(struct ceph_mds_client *mdsc) ceph_force_reconnect(fsc->sb); } +bool check_session_state(struct ceph_mds_session *s) +{ + if (s->s_state == CEPH_MDS_SESSION_CLOSING) { + dout("resending session close request for mds%d\n", + s->s_mds); + request_close_session(s); + return false; + } + if (s->s_ttl && time_after(jiffies, s->s_ttl)) { + if (s->s_state == CEPH_MDS_SESSION_OPEN) { + s->s_state = CEPH_MDS_SESSION_HUNG; + pr_info("mds%d hung\n", s->s_mds); + } + } + if (s->s_state == CEPH_MDS_SESSION_NEW || + s->s_state == CEPH_MDS_SESSION_RESTARTING || + s->s_state == CEPH_MDS_SESSION_CLOSED || + s->s_state == CEPH_MDS_SESSION_REJECTED) + /* this mds is failed or recovering, just wait */ + return false; + + return true; +} + /* * delayed work -- periodically trim expired leases, renew caps with mds */ @@ -4283,6 +4390,9 @@ static void delayed_work(struct work_struct *work) dout("mdsc delayed_work\n"); + if (mdsc->stopping) + return; + mutex_lock(&mdsc->mutex); renew_interval = mdsc->mdsmap->m_session_timeout >> 2; renew_caps = time_after_eq(jiffies, HZ*renew_interval + @@ -4294,23 +4404,8 @@ static void delayed_work(struct work_struct *work) struct ceph_mds_session *s = __ceph_lookup_mds_session(mdsc, i); if (!s) continue; - if (s->s_state == CEPH_MDS_SESSION_CLOSING) { - dout("resending session close request for mds%d\n", - s->s_mds); - request_close_session(mdsc, s); - ceph_put_mds_session(s); - continue; - } - if (s->s_ttl && time_after(jiffies, s->s_ttl)) { - if (s->s_state == CEPH_MDS_SESSION_OPEN) { - s->s_state = CEPH_MDS_SESSION_HUNG; - pr_info("mds%d hung\n", s->s_mds); - } - } - if (s->s_state == CEPH_MDS_SESSION_NEW || - s->s_state == CEPH_MDS_SESSION_RESTARTING || - s->s_state == CEPH_MDS_SESSION_REJECTED) { - /* this mds is failed or recovering, just wait */ + + if (!check_session_state(s)) { ceph_put_mds_session(s); continue; } @@ -4359,7 +4454,6 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc) goto err_mdsc; } - fsc->mdsc = mdsc; init_completion(&mdsc->safe_umount_waiters); init_waitqueue_head(&mdsc->session_close_wq); INIT_LIST_HEAD(&mdsc->waiting_for_map); @@ -4414,6 +4508,8 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc) strscpy(mdsc->nodename, utsname()->nodename, sizeof(mdsc->nodename)); + + fsc->mdsc = mdsc; return 0; err_mdsmap: @@ -4657,7 +4753,16 @@ void ceph_mdsc_force_umount(struct ceph_mds_client *mdsc) static void ceph_mdsc_stop(struct ceph_mds_client *mdsc) { dout("stop\n"); - cancel_delayed_work_sync(&mdsc->delayed_work); /* cancel timer */ + /* + * Make sure the delayed work stopped before releasing + * the resources. + * + * Because the cancel_delayed_work_sync() will only + * guarantee that the work finishes executing. But the + * delayed work will re-arm itself again after that. + */ + flush_delayed_work(&mdsc->delayed_work); + if (mdsc->mdsmap) ceph_mdsmap_destroy(mdsc->mdsmap); kfree(mdsc->sessions); @@ -4680,6 +4785,7 @@ void ceph_mdsc_destroy(struct ceph_fs_client *fsc) ceph_metric_destroy(&mdsc->metric); + flush_delayed_work(&mdsc->metric.delayed_work); fsc->mdsc = NULL; kfree(mdsc); dout("mdsc_destroy %p done\n", mdsc); diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 5e0c4073a6be..bc9e95937d7c 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -18,6 +18,7 @@ #include <linux/ceph/auth.h> #include "metric.h" +#include "super.h" /* The first 8 bits are reserved for old ceph releases */ enum ceph_feature_type { @@ -27,8 +28,9 @@ enum ceph_feature_type { CEPHFS_FEATURE_LAZY_CAP_WANTED, CEPHFS_FEATURE_MULTI_RECONNECT, CEPHFS_FEATURE_DELEG_INO, + CEPHFS_FEATURE_METRIC_COLLECT, - CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_DELEG_INO, + CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_METRIC_COLLECT, }; /* @@ -42,6 +44,7 @@ enum ceph_feature_type { CEPHFS_FEATURE_LAZY_CAP_WANTED, \ CEPHFS_FEATURE_MULTI_RECONNECT, \ CEPHFS_FEATURE_DELEG_INO, \ + CEPHFS_FEATURE_METRIC_COLLECT, \ \ CEPHFS_FEATURE_MAX, \ } @@ -476,6 +479,8 @@ struct ceph_mds_client { extern const char *ceph_mds_op_name(int op); +extern bool check_session_state(struct ceph_mds_session *s); + extern struct ceph_mds_session * __ceph_lookup_mds_session(struct ceph_mds_client *, int mds); diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c index 889627817e52..e4aba6c6d3b5 100644 --- a/fs/ceph/mdsmap.c +++ b/fs/ceph/mdsmap.c @@ -120,7 +120,7 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end) const void *start = *p; int i, j, n; int err; - u8 mdsmap_v, mdsmap_cv; + u8 mdsmap_v; u16 mdsmap_ev; m = kzalloc(sizeof(*m), GFP_NOFS); @@ -129,7 +129,7 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end) ceph_decode_need(p, end, 1 + 1, bad); mdsmap_v = ceph_decode_8(p); - mdsmap_cv = ceph_decode_8(p); + *p += sizeof(u8); /* mdsmap_cv */ if (mdsmap_v >= 4) { u32 mdsmap_len; ceph_decode_32_safe(p, end, mdsmap_len, bad); @@ -174,7 +174,6 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end) u64 global_id; u32 namelen; s32 mds, inc, state; - u64 state_seq; u8 info_v; void *info_end = NULL; struct ceph_entity_addr addr; @@ -189,9 +188,8 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end) info_v= ceph_decode_8(p); if (info_v >= 4) { u32 info_len; - u8 info_cv; ceph_decode_need(p, end, 1 + sizeof(u32), bad); - info_cv = ceph_decode_8(p); + *p += sizeof(u8); /* info_cv */ info_len = ceph_decode_32(p); info_end = *p + info_len; if (info_end > end) @@ -210,7 +208,7 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end) mds = ceph_decode_32(p); inc = ceph_decode_32(p); state = ceph_decode_32(p); - state_seq = ceph_decode_64(p); + *p += sizeof(u64); /* state_seq */ err = ceph_decode_entity_addr(p, end, &addr); if (err) goto corrupt; diff --git a/fs/ceph/metric.c b/fs/ceph/metric.c index 9217f35bc2b9..2466b261fba2 100644 --- a/fs/ceph/metric.c +++ b/fs/ceph/metric.c @@ -1,10 +1,150 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#include <linux/ceph/ceph_debug.h> #include <linux/types.h> #include <linux/percpu_counter.h> #include <linux/math64.h> #include "metric.h" +#include "mds_client.h" + +static bool ceph_mdsc_send_metrics(struct ceph_mds_client *mdsc, + struct ceph_mds_session *s) +{ + struct ceph_metric_head *head; + struct ceph_metric_cap *cap; + struct ceph_metric_read_latency *read; + struct ceph_metric_write_latency *write; + struct ceph_metric_metadata_latency *meta; + struct ceph_client_metric *m = &mdsc->metric; + u64 nr_caps = atomic64_read(&m->total_caps); + struct ceph_msg *msg; + struct timespec64 ts; + s64 sum; + s32 items = 0; + s32 len; + + len = sizeof(*head) + sizeof(*cap) + sizeof(*read) + sizeof(*write) + + sizeof(*meta); + + msg = ceph_msg_new(CEPH_MSG_CLIENT_METRICS, len, GFP_NOFS, true); + if (!msg) { + pr_err("send metrics to mds%d, failed to allocate message\n", + s->s_mds); + return false; + } + + head = msg->front.iov_base; + + /* encode the cap metric */ + cap = (struct ceph_metric_cap *)(head + 1); + cap->type = cpu_to_le32(CLIENT_METRIC_TYPE_CAP_INFO); + cap->ver = 1; + cap->compat = 1; + cap->data_len = cpu_to_le32(sizeof(*cap) - 10); + cap->hit = cpu_to_le64(percpu_counter_sum(&mdsc->metric.i_caps_hit)); + cap->mis = cpu_to_le64(percpu_counter_sum(&mdsc->metric.i_caps_mis)); + cap->total = cpu_to_le64(nr_caps); + items++; + + /* encode the read latency metric */ + read = (struct ceph_metric_read_latency *)(cap + 1); + read->type = cpu_to_le32(CLIENT_METRIC_TYPE_READ_LATENCY); + read->ver = 1; + read->compat = 1; + read->data_len = cpu_to_le32(sizeof(*read) - 10); + sum = m->read_latency_sum; + jiffies_to_timespec64(sum, &ts); + read->sec = cpu_to_le32(ts.tv_sec); + read->nsec = cpu_to_le32(ts.tv_nsec); + items++; + + /* encode the write latency metric */ + write = (struct ceph_metric_write_latency *)(read + 1); + write->type = cpu_to_le32(CLIENT_METRIC_TYPE_WRITE_LATENCY); + write->ver = 1; + write->compat = 1; + write->data_len = cpu_to_le32(sizeof(*write) - 10); + sum = m->write_latency_sum; + jiffies_to_timespec64(sum, &ts); + write->sec = cpu_to_le32(ts.tv_sec); + write->nsec = cpu_to_le32(ts.tv_nsec); + items++; + + /* encode the metadata latency metric */ + meta = (struct ceph_metric_metadata_latency *)(write + 1); + meta->type = cpu_to_le32(CLIENT_METRIC_TYPE_METADATA_LATENCY); + meta->ver = 1; + meta->compat = 1; + meta->data_len = cpu_to_le32(sizeof(*meta) - 10); + sum = m->metadata_latency_sum; + jiffies_to_timespec64(sum, &ts); + meta->sec = cpu_to_le32(ts.tv_sec); + meta->nsec = cpu_to_le32(ts.tv_nsec); + items++; + + put_unaligned_le32(items, &head->num); + msg->front.iov_len = len; + msg->hdr.version = cpu_to_le16(1); + msg->hdr.compat_version = cpu_to_le16(1); + msg->hdr.front_len = cpu_to_le32(msg->front.iov_len); + dout("client%llu send metrics to mds%d\n", + ceph_client_gid(mdsc->fsc->client), s->s_mds); + ceph_con_send(&s->s_con, msg); + + return true; +} + + +static void metric_get_session(struct ceph_mds_client *mdsc) +{ + struct ceph_mds_session *s; + int i; + + mutex_lock(&mdsc->mutex); + for (i = 0; i < mdsc->max_sessions; i++) { + s = __ceph_lookup_mds_session(mdsc, i); + if (!s) + continue; + + /* + * Skip it if MDS doesn't support the metric collection, + * or the MDS will close the session's socket connection + * directly when it get this message. + */ + if (check_session_state(s) && + test_bit(CEPHFS_FEATURE_METRIC_COLLECT, &s->s_features)) { + mdsc->metric.session = s; + break; + } + + ceph_put_mds_session(s); + } + mutex_unlock(&mdsc->mutex); +} + +static void metric_delayed_work(struct work_struct *work) +{ + struct ceph_client_metric *m = + container_of(work, struct ceph_client_metric, delayed_work.work); + struct ceph_mds_client *mdsc = + container_of(m, struct ceph_mds_client, metric); + + if (mdsc->stopping) + return; + + if (!m->session || !check_session_state(m->session)) { + if (m->session) { + ceph_put_mds_session(m->session); + m->session = NULL; + } + metric_get_session(mdsc); + } + if (m->session) { + ceph_mdsc_send_metrics(mdsc, m->session); + metric_schedule_delayed(m); + } +} int ceph_metric_init(struct ceph_client_metric *m) { @@ -22,6 +162,7 @@ int ceph_metric_init(struct ceph_client_metric *m) if (ret) goto err_d_lease_mis; + atomic64_set(&m->total_caps, 0); ret = percpu_counter_init(&m->i_caps_hit, 0, GFP_KERNEL); if (ret) goto err_i_caps_hit; @@ -51,6 +192,9 @@ int ceph_metric_init(struct ceph_client_metric *m) m->total_metadatas = 0; m->metadata_latency_sum = 0; + m->session = NULL; + INIT_DELAYED_WORK(&m->delayed_work, metric_delayed_work); + return 0; err_i_caps_mis: @@ -72,6 +216,11 @@ void ceph_metric_destroy(struct ceph_client_metric *m) percpu_counter_destroy(&m->i_caps_hit); percpu_counter_destroy(&m->d_lease_mis); percpu_counter_destroy(&m->d_lease_hit); + + cancel_delayed_work_sync(&m->delayed_work); + + if (m->session) + ceph_put_mds_session(m->session); } static inline void __update_latency(ktime_t *totalp, ktime_t *lsump, diff --git a/fs/ceph/metric.h b/fs/ceph/metric.h index ccd81285a450..1d0959d669d7 100644 --- a/fs/ceph/metric.h +++ b/fs/ceph/metric.h @@ -6,12 +6,91 @@ #include <linux/percpu_counter.h> #include <linux/ktime.h> +extern bool disable_send_metrics; + +enum ceph_metric_type { + CLIENT_METRIC_TYPE_CAP_INFO, + CLIENT_METRIC_TYPE_READ_LATENCY, + CLIENT_METRIC_TYPE_WRITE_LATENCY, + CLIENT_METRIC_TYPE_METADATA_LATENCY, + CLIENT_METRIC_TYPE_DENTRY_LEASE, + + CLIENT_METRIC_TYPE_MAX = CLIENT_METRIC_TYPE_DENTRY_LEASE, +}; + +/* + * This will always have the highest metric bit value + * as the last element of the array. + */ +#define CEPHFS_METRIC_SPEC_CLIENT_SUPPORTED { \ + CLIENT_METRIC_TYPE_CAP_INFO, \ + CLIENT_METRIC_TYPE_READ_LATENCY, \ + CLIENT_METRIC_TYPE_WRITE_LATENCY, \ + CLIENT_METRIC_TYPE_METADATA_LATENCY, \ + \ + CLIENT_METRIC_TYPE_MAX, \ +} + +/* metric caps header */ +struct ceph_metric_cap { + __le32 type; /* ceph metric type */ + + __u8 ver; + __u8 compat; + + __le32 data_len; /* length of sizeof(hit + mis + total) */ + __le64 hit; + __le64 mis; + __le64 total; +} __packed; + +/* metric read latency header */ +struct ceph_metric_read_latency { + __le32 type; /* ceph metric type */ + + __u8 ver; + __u8 compat; + + __le32 data_len; /* length of sizeof(sec + nsec) */ + __le32 sec; + __le32 nsec; +} __packed; + +/* metric write latency header */ +struct ceph_metric_write_latency { + __le32 type; /* ceph metric type */ + + __u8 ver; + __u8 compat; + + __le32 data_len; /* length of sizeof(sec + nsec) */ + __le32 sec; + __le32 nsec; +} __packed; + +/* metric metadata latency header */ +struct ceph_metric_metadata_latency { + __le32 type; /* ceph metric type */ + + __u8 ver; + __u8 compat; + + __le32 data_len; /* length of sizeof(sec + nsec) */ + __le32 sec; + __le32 nsec; +} __packed; + +struct ceph_metric_head { + __le32 num; /* the number of metrics that will be sent */ +} __packed; + /* This is the global metrics */ struct ceph_client_metric { atomic64_t total_dentries; struct percpu_counter d_lease_hit; struct percpu_counter d_lease_mis; + atomic64_t total_caps; struct percpu_counter i_caps_hit; struct percpu_counter i_caps_mis; @@ -35,8 +114,20 @@ struct ceph_client_metric { ktime_t metadata_latency_sq_sum; ktime_t metadata_latency_min; ktime_t metadata_latency_max; + + struct ceph_mds_session *session; + struct delayed_work delayed_work; /* delayed work */ }; +static inline void metric_schedule_delayed(struct ceph_client_metric *m) +{ + if (disable_send_metrics) + return; + + /* per second */ + schedule_delayed_work(&m->delayed_work, round_jiffies_relative(HZ)); +} + extern int ceph_metric_init(struct ceph_client_metric *m); extern void ceph_metric_destroy(struct ceph_client_metric *m); diff --git a/fs/ceph/super.c b/fs/ceph/super.c index c9784eb1159a..7ec0e6d03d10 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -27,6 +27,9 @@ #include <linux/ceph/auth.h> #include <linux/ceph/debugfs.h> +static DEFINE_SPINLOCK(ceph_fsc_lock); +static LIST_HEAD(ceph_fsc_list); + /* * Ceph superblock operations * @@ -634,8 +637,6 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt, struct ceph_options *opt) { struct ceph_fs_client *fsc; - int page_count; - size_t size; int err; fsc = kzalloc(sizeof(*fsc), GFP_KERNEL); @@ -683,18 +684,12 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt, if (!fsc->cap_wq) goto fail_inode_wq; - /* set up mempools */ - err = -ENOMEM; - page_count = fsc->mount_options->wsize >> PAGE_SHIFT; - size = sizeof (struct page *) * (page_count ? page_count : 1); - fsc->wb_pagevec_pool = mempool_create_kmalloc_pool(10, size); - if (!fsc->wb_pagevec_pool) - goto fail_cap_wq; + spin_lock(&ceph_fsc_lock); + list_add_tail(&fsc->metric_wakeup, &ceph_fsc_list); + spin_unlock(&ceph_fsc_lock); return fsc; -fail_cap_wq: - destroy_workqueue(fsc->cap_wq); fail_inode_wq: destroy_workqueue(fsc->inode_wq); fail_client: @@ -717,12 +712,14 @@ static void destroy_fs_client(struct ceph_fs_client *fsc) { dout("destroy_fs_client %p\n", fsc); + spin_lock(&ceph_fsc_lock); + list_del(&fsc->metric_wakeup); + spin_unlock(&ceph_fsc_lock); + ceph_mdsc_destroy(fsc); destroy_workqueue(fsc->inode_wq); destroy_workqueue(fsc->cap_wq); - mempool_destroy(fsc->wb_pagevec_pool); - destroy_mount_options(fsc->mount_options); ceph_destroy_client(fsc->client); @@ -741,6 +738,7 @@ struct kmem_cache *ceph_dentry_cachep; struct kmem_cache *ceph_file_cachep; struct kmem_cache *ceph_dir_file_cachep; struct kmem_cache *ceph_mds_request_cachep; +mempool_t *ceph_wb_pagevec_pool; static void ceph_inode_init_once(void *foo) { @@ -785,6 +783,10 @@ static int __init init_caches(void) if (!ceph_mds_request_cachep) goto bad_mds_req; + ceph_wb_pagevec_pool = mempool_create_kmalloc_pool(10, CEPH_MAX_WRITE_SIZE >> PAGE_SHIFT); + if (!ceph_wb_pagevec_pool) + goto bad_pagevec_pool; + error = ceph_fscache_register(); if (error) goto bad_fscache; @@ -793,6 +795,8 @@ static int __init init_caches(void) bad_fscache: kmem_cache_destroy(ceph_mds_request_cachep); +bad_pagevec_pool: + mempool_destroy(ceph_wb_pagevec_pool); bad_mds_req: kmem_cache_destroy(ceph_dir_file_cachep); bad_dir_file: @@ -823,12 +827,13 @@ static void destroy_caches(void) kmem_cache_destroy(ceph_file_cachep); kmem_cache_destroy(ceph_dir_file_cachep); kmem_cache_destroy(ceph_mds_request_cachep); + mempool_destroy(ceph_wb_pagevec_pool); ceph_fscache_unregister(); } /* - * ceph_umount_begin - initiate forced umount. Tear down down the + * ceph_umount_begin - initiate forced umount. Tear down the * mount, skipping steps that may hang while waiting for server(s). */ static void ceph_umount_begin(struct super_block *sb) @@ -1282,6 +1287,37 @@ static void __exit exit_ceph(void) destroy_caches(); } +static int param_set_metrics(const char *val, const struct kernel_param *kp) +{ + struct ceph_fs_client *fsc; + int ret; + + ret = param_set_bool(val, kp); + if (ret) { + pr_err("Failed to parse sending metrics switch value '%s'\n", + val); + return ret; + } else if (!disable_send_metrics) { + // wake up all the mds clients + spin_lock(&ceph_fsc_lock); + list_for_each_entry(fsc, &ceph_fsc_list, metric_wakeup) { + metric_schedule_delayed(&fsc->mdsc->metric); + } + spin_unlock(&ceph_fsc_lock); + } + + return 0; +} + +static const struct kernel_param_ops param_ops_metrics = { + .set = param_set_metrics, + .get = param_get_bool, +}; + +bool disable_send_metrics = false; +module_param_cb(disable_send_metrics, ¶m_ops_metrics, &disable_send_metrics, 0644); +MODULE_PARM_DESC(disable_send_metrics, "Enable sending perf metrics to ceph cluster (default: on)"); + module_init(init_ceph); module_exit(exit_ceph); diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 5a6cdd39bc10..4c3c964b1c54 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -101,6 +101,8 @@ struct ceph_mount_options { struct ceph_fs_client { struct super_block *sb; + struct list_head metric_wakeup; + struct ceph_mount_options *mount_options; struct ceph_client *client; @@ -116,8 +118,6 @@ struct ceph_fs_client { struct ceph_mds_client *mdsc; - /* writeback */ - mempool_t *wb_pagevec_pool; atomic_long_t writeback_count; struct workqueue_struct *inode_wq; @@ -353,7 +353,7 @@ struct ceph_inode_info { unsigned i_dirty_caps, i_flushing_caps; /* mask of dirtied fields */ /* - * Link to the the auth cap's session's s_cap_dirty list. s_cap_dirty + * Link to the auth cap's session's s_cap_dirty list. s_cap_dirty * is protected by the mdsc->cap_dirty_lock, but each individual item * is also protected by the inode's i_ceph_lock. Walking s_cap_dirty * requires the mdsc->cap_dirty_lock. List presence for an item can diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index 71ee34d160c3..3a733ac33d9b 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -497,10 +497,10 @@ static int __set_xattr(struct ceph_inode_info *ci, kfree(*newxattr); *newxattr = NULL; if (xattr->should_free_val) - kfree((void *)xattr->val); + kfree(xattr->val); if (update_xattr) { - kfree((void *)name); + kfree(name); name = xattr->name; } ci->i_xattrs.names_size -= xattr->name_len; @@ -566,9 +566,9 @@ static void __free_xattr(struct ceph_inode_xattr *xattr) BUG_ON(!xattr); if (xattr->should_free_name) - kfree((void *)xattr->name); + kfree(xattr->name); if (xattr->should_free_val) - kfree((void *)xattr->val); + kfree(xattr->val); kfree(xattr); } @@ -582,9 +582,9 @@ static int __remove_xattr(struct ceph_inode_info *ci, rb_erase(&xattr->node, &ci->i_xattrs.index); if (xattr->should_free_name) - kfree((void *)xattr->name); + kfree(xattr->name); if (xattr->should_free_val) - kfree((void *)xattr->val); + kfree(xattr->val); ci->i_xattrs.names_size -= xattr->name_len; ci->i_xattrs.vals_size -= xattr->val_len; diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 0ad1309e88d3..a275ee399dce 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -4886,6 +4886,7 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *vol) full_path = build_unc_path_to_root(vol, cifs_sb, !!count); if (IS_ERR(full_path)) { rc = PTR_ERR(full_path); + full_path = NULL; break; } /* Chase referral */ diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c index b9db73687eaa..eba01d0908dd 100644 --- a/fs/cifs/smb2inode.c +++ b/fs/cifs/smb2inode.c @@ -115,6 +115,7 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, vars->oparms.fid = &fid; vars->oparms.reconnect = false; vars->oparms.mode = mode; + vars->oparms.cifs_sb = cifs_sb; rqst[num_rqst].rq_iov = &vars->open_iov[0]; rqst[num_rqst].rq_nvec = SMB2_CREATE_IOV_SIZE; diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 24c2ac360591..667d70aa335f 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -3913,7 +3913,7 @@ smb2_readv_callback(struct mid_q_entry *mid) case MID_RESPONSE_MALFORMED: credits.value = le16_to_cpu(shdr->CreditRequest); credits.instance = server->reconnect_instance; - /* fall through */ + fallthrough; default: rdata->result = -EIO; } @@ -4146,7 +4146,7 @@ smb2_writev_callback(struct mid_q_entry *mid) case MID_RESPONSE_MALFORMED: credits.value = le16_to_cpu(rsp->sync_hdr.CreditRequest); credits.instance = server->reconnect_instance; - /* fall through */ + fallthrough; default: wdata->result = -EIO; break; diff --git a/fs/coredump.c b/fs/coredump.c index 7237f07ff6be..76e7c10edfc0 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -153,10 +153,10 @@ int cn_esc_printf(struct core_name *cn, const char *fmt, ...) return ret; } -static int cn_print_exe_file(struct core_name *cn) +static int cn_print_exe_file(struct core_name *cn, bool name_only) { struct file *exe_file; - char *pathbuf, *path; + char *pathbuf, *path, *ptr; int ret; exe_file = get_mm_exe_file(current->mm); @@ -175,6 +175,11 @@ static int cn_print_exe_file(struct core_name *cn) goto free_buf; } + if (name_only) { + ptr = strrchr(path, '/'); + if (ptr) + path = ptr + 1; + } ret = cn_esc_printf(cn, "%s", path); free_buf: @@ -301,12 +306,16 @@ static int format_corename(struct core_name *cn, struct coredump_params *cprm, utsname()->nodename); up_read(&uts_sem); break; - /* executable */ + /* executable, could be changed by prctl PR_SET_NAME etc */ case 'e': err = cn_esc_printf(cn, "%s", current->comm); break; + /* file name of executable */ + case 'f': + err = cn_print_exe_file(cn, true); + break; case 'E': - err = cn_print_exe_file(cn); + err = cn_print_exe_file(cn, false); break; /* core limit size */ case 'c': @@ -488,7 +488,7 @@ retry: if (dax_is_conflict(entry)) goto fallback; if (!xa_is_value(entry)) { - xas_set_err(xas, EIO); + xas_set_err(xas, -EIO); goto out_unlock; } @@ -680,21 +680,20 @@ int dax_invalidate_mapping_entry_sync(struct address_space *mapping, return __dax_invalidate_entry(mapping, index, false); } -static int copy_user_dax(struct block_device *bdev, struct dax_device *dax_dev, - sector_t sector, size_t size, struct page *to, - unsigned long vaddr) +static int copy_cow_page_dax(struct block_device *bdev, struct dax_device *dax_dev, + sector_t sector, struct page *to, unsigned long vaddr) { void *vto, *kaddr; pgoff_t pgoff; long rc; int id; - rc = bdev_dax_pgoff(bdev, sector, size, &pgoff); + rc = bdev_dax_pgoff(bdev, sector, PAGE_SIZE, &pgoff); if (rc) return rc; id = dax_read_lock(); - rc = dax_direct_access(dax_dev, pgoff, PHYS_PFN(size), &kaddr, NULL); + rc = dax_direct_access(dax_dev, pgoff, PHYS_PFN(PAGE_SIZE), &kaddr, NULL); if (rc < 0) { dax_read_unlock(id); return rc; @@ -1305,8 +1304,8 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp, clear_user_highpage(vmf->cow_page, vaddr); break; case IOMAP_MAPPED: - error = copy_user_dax(iomap.bdev, iomap.dax_dev, - sector, PAGE_SIZE, vmf->cow_page, vaddr); + error = copy_cow_page_dax(iomap.bdev, iomap.dax_dev, + sector, vmf->cow_page, vaddr); break; default: WARN_ON_ONCE(1); diff --git a/fs/dcache.c b/fs/dcache.c index 361ea7ab30ea..ea0485861d93 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -1746,7 +1746,7 @@ static struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) dentry->d_lockref.count = 1; dentry->d_flags = 0; spin_lock_init(&dentry->d_lock); - seqcount_init(&dentry->d_seq); + seqcount_spinlock_init(&dentry->d_seq, &dentry->d_lock); dentry->d_inode = NULL; dentry->d_parent = dentry; dentry->d_sb = sb; diff --git a/fs/exec.c b/fs/exec.c index 3698252719a3..a91003e28eaa 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -141,12 +141,14 @@ SYSCALL_DEFINE1(uselib, const char __user *, library) if (IS_ERR(file)) goto out; - error = -EINVAL; - if (!S_ISREG(file_inode(file)->i_mode)) - goto exit; - + /* + * may_open() has already checked for this, so it should be + * impossible to trip now. But we need to be extra cautious + * and check again at the very end too. + */ error = -EACCES; - if (path_noexec(&file->f_path)) + if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode) || + path_noexec(&file->f_path))) goto exit; fsnotify_open(file); @@ -215,7 +217,7 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, * We are doing an exec(). 'current' is the process * doing the exec and bprm->mm is the new process's mm. */ - ret = get_user_pages_remote(current, bprm->mm, pos, 1, gup_flags, + ret = get_user_pages_remote(bprm->mm, pos, 1, gup_flags, &page, NULL, NULL); if (ret <= 0) return NULL; @@ -909,11 +911,14 @@ static struct file *do_open_execat(int fd, struct filename *name, int flags) if (IS_ERR(file)) goto out; + /* + * may_open() has already checked for this, so it should be + * impossible to trip now. But we need to be extra cautious + * and check again at the very end too. + */ err = -EACCES; - if (!S_ISREG(file_inode(file)->i_mode)) - goto exit; - - if (path_noexec(&file->f_path)) + if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode) || + path_noexec(&file->f_path))) goto exit; err = deny_write_access(file); @@ -1402,7 +1407,12 @@ int begin_new_exec(struct linux_binprm * bprm) if (retval) goto out_unlock; - set_fs(USER_DS); + /* + * Ensure that the uaccess routines can actually operate on userspace + * pointers: + */ + force_uaccess_begin(); + me->flags &= ~(PF_RANDOMIZE | PF_FORKNOEXEC | PF_KTHREAD | PF_NOFREEZE | PF_NO_SETAFFINITY); flush_thread(); diff --git a/fs/exfat/balloc.c b/fs/exfat/balloc.c index 4055eb00ea9b..a987919686c0 100644 --- a/fs/exfat/balloc.c +++ b/fs/exfat/balloc.c @@ -158,7 +158,7 @@ int exfat_set_bitmap(struct inode *inode, unsigned int clu) b = BITMAP_OFFSET_BIT_IN_SECTOR(sb, ent_idx); set_bit_le(b, sbi->vol_amap[i]->b_data); - exfat_update_bh(sb, sbi->vol_amap[i], IS_DIRSYNC(inode)); + exfat_update_bh(sbi->vol_amap[i], IS_DIRSYNC(inode)); return 0; } @@ -180,7 +180,7 @@ void exfat_clear_bitmap(struct inode *inode, unsigned int clu) b = BITMAP_OFFSET_BIT_IN_SECTOR(sb, ent_idx); clear_bit_le(b, sbi->vol_amap[i]->b_data); - exfat_update_bh(sb, sbi->vol_amap[i], IS_DIRSYNC(inode)); + exfat_update_bh(sbi->vol_amap[i], IS_DIRSYNC(inode)); if (opts->discard) { int ret_discard; diff --git a/fs/exfat/dir.c b/fs/exfat/dir.c index 119abf0d8dd6..573659bfbc55 100644 --- a/fs/exfat/dir.c +++ b/fs/exfat/dir.c @@ -470,7 +470,7 @@ int exfat_init_dir_entry(struct inode *inode, struct exfat_chain *p_dir, &ep->dentry.file.access_date, NULL); - exfat_update_bh(sb, bh, IS_DIRSYNC(inode)); + exfat_update_bh(bh, IS_DIRSYNC(inode)); brelse(bh); ep = exfat_get_dentry(sb, p_dir, entry + 1, &bh, §or); @@ -480,7 +480,7 @@ int exfat_init_dir_entry(struct inode *inode, struct exfat_chain *p_dir, exfat_init_stream_entry(ep, (type == TYPE_FILE) ? ALLOC_FAT_CHAIN : ALLOC_NO_FAT_CHAIN, start_clu, size); - exfat_update_bh(sb, bh, IS_DIRSYNC(inode)); + exfat_update_bh(bh, IS_DIRSYNC(inode)); brelse(bh); return 0; @@ -516,7 +516,7 @@ int exfat_update_dir_chksum(struct inode *inode, struct exfat_chain *p_dir, } fep->dentry.file.checksum = cpu_to_le16(chksum); - exfat_update_bh(sb, fbh, IS_DIRSYNC(inode)); + exfat_update_bh(fbh, IS_DIRSYNC(inode)); release_fbh: brelse(fbh); return ret; @@ -538,7 +538,7 @@ int exfat_init_ext_entry(struct inode *inode, struct exfat_chain *p_dir, return -EIO; ep->dentry.file.num_ext = (unsigned char)(num_entries - 1); - exfat_update_bh(sb, bh, sync); + exfat_update_bh(bh, sync); brelse(bh); ep = exfat_get_dentry(sb, p_dir, entry + 1, &bh, §or); @@ -547,7 +547,7 @@ int exfat_init_ext_entry(struct inode *inode, struct exfat_chain *p_dir, ep->dentry.stream.name_len = p_uniname->name_len; ep->dentry.stream.name_hash = cpu_to_le16(p_uniname->name_hash); - exfat_update_bh(sb, bh, sync); + exfat_update_bh(bh, sync); brelse(bh); for (i = EXFAT_FIRST_CLUSTER; i < num_entries; i++) { @@ -556,7 +556,7 @@ int exfat_init_ext_entry(struct inode *inode, struct exfat_chain *p_dir, return -EIO; exfat_init_name_entry(ep, uniname); - exfat_update_bh(sb, bh, sync); + exfat_update_bh(bh, sync); brelse(bh); uniname += EXFAT_FILE_NAME_LEN; } @@ -580,7 +580,7 @@ int exfat_remove_entries(struct inode *inode, struct exfat_chain *p_dir, return -EIO; exfat_set_entry_type(ep, TYPE_DELETED); - exfat_update_bh(sb, bh, IS_DIRSYNC(inode)); + exfat_update_bh(bh, IS_DIRSYNC(inode)); brelse(bh); } @@ -604,16 +604,20 @@ void exfat_update_dir_chksum_with_entry_set(struct exfat_entry_set_cache *es) es->modified = true; } -void exfat_free_dentry_set(struct exfat_entry_set_cache *es, int sync) +int exfat_free_dentry_set(struct exfat_entry_set_cache *es, int sync) { - int i; + int i, err = 0; - for (i = 0; i < es->num_bh; i++) { - if (es->modified) - exfat_update_bh(es->sb, es->bh[i], sync); - brelse(es->bh[i]); - } + if (es->modified) + err = exfat_update_bhs(es->bh, es->num_bh, sync); + + for (i = 0; i < es->num_bh; i++) + if (err) + bforget(es->bh[i]); + else + brelse(es->bh[i]); kfree(es); + return err; } static int exfat_walk_fat_chain(struct super_block *sb, diff --git a/fs/exfat/exfat_fs.h b/fs/exfat/exfat_fs.h index 75c7bdbeba6d..95d717f8620c 100644 --- a/fs/exfat/exfat_fs.h +++ b/fs/exfat/exfat_fs.h @@ -13,8 +13,6 @@ #define EXFAT_SUPER_MAGIC 0x2011BAB0UL #define EXFAT_ROOT_INO 1 -#define EXFAT_SB_DIRTY 0 - #define EXFAT_CLUSTERS_UNTRACKED (~0u) /* @@ -226,7 +224,8 @@ struct exfat_sb_info { unsigned int num_FAT_sectors; /* num of FAT sectors */ unsigned int root_dir; /* root dir cluster */ unsigned int dentries_per_clu; /* num of dentries per cluster */ - unsigned int vol_flag; /* volume dirty flag */ + unsigned int vol_flags; /* volume flags */ + unsigned int vol_flags_persistent; /* volume flags to retain */ struct buffer_head *boot_bh; /* buffer_head of BOOT sector */ unsigned int map_clu; /* allocation bitmap start cluster */ @@ -238,7 +237,6 @@ struct exfat_sb_info { unsigned int clu_srch_ptr; /* cluster search pointer */ unsigned int used_clusters; /* number of used clusters */ - unsigned long s_state; struct mutex s_lock; /* superblock lock */ struct exfat_mount_options options; struct nls_table *nls_io; /* Charset used for input and display */ @@ -383,7 +381,8 @@ static inline int exfat_sector_to_cluster(struct exfat_sb_info *sbi, } /* super.c */ -int exfat_set_vol_flags(struct super_block *sb, unsigned short new_flag); +int exfat_set_volume_dirty(struct super_block *sb); +int exfat_clear_volume_dirty(struct super_block *sb); /* fatent.c */ #define exfat_get_next_cluster(sb, pclu) exfat_ent_get(sb, *(pclu), pclu) @@ -463,7 +462,7 @@ struct exfat_dentry *exfat_get_dentry_cached(struct exfat_entry_set_cache *es, int num); struct exfat_entry_set_cache *exfat_get_dentry_set(struct super_block *sb, struct exfat_chain *p_dir, int entry, unsigned int type); -void exfat_free_dentry_set(struct exfat_entry_set_cache *es, int sync); +int exfat_free_dentry_set(struct exfat_entry_set_cache *es, int sync); int exfat_count_dir_entries(struct super_block *sb, struct exfat_chain *p_dir); /* inode.c */ @@ -515,7 +514,8 @@ void exfat_set_entry_time(struct exfat_sb_info *sbi, struct timespec64 *ts, u8 *tz, __le16 *time, __le16 *date, u8 *time_cs); u16 exfat_calc_chksum16(void *data, int len, u16 chksum, int type); u32 exfat_calc_chksum32(void *data, int len, u32 chksum, int type); -void exfat_update_bh(struct super_block *sb, struct buffer_head *bh, int sync); +void exfat_update_bh(struct buffer_head *bh, int sync); +int exfat_update_bhs(struct buffer_head **bhs, int nr_bhs, int sync); void exfat_chain_set(struct exfat_chain *ec, unsigned int dir, unsigned int size, unsigned char flags); void exfat_chain_dup(struct exfat_chain *dup, struct exfat_chain *ec); diff --git a/fs/exfat/exfat_raw.h b/fs/exfat/exfat_raw.h index 350ce59cc324..6aec6288e1f2 100644 --- a/fs/exfat/exfat_raw.h +++ b/fs/exfat/exfat_raw.h @@ -14,9 +14,8 @@ #define EXFAT_MAX_FILE_LEN 255 -#define VOL_CLEAN 0x0000 -#define VOL_DIRTY 0x0002 -#define ERR_MEDIUM 0x0004 +#define VOLUME_DIRTY 0x0002 +#define MEDIA_FAILURE 0x0004 #define EXFAT_EOF_CLUSTER 0xFFFFFFFFu #define EXFAT_BAD_CLUSTER 0xFFFFFFF7u diff --git a/fs/exfat/fatent.c b/fs/exfat/fatent.c index 4e5c5c9c0f2d..c3c9afee7418 100644 --- a/fs/exfat/fatent.c +++ b/fs/exfat/fatent.c @@ -75,7 +75,7 @@ int exfat_ent_set(struct super_block *sb, unsigned int loc, fat_entry = (__le32 *)&(bh->b_data[off]); *fat_entry = cpu_to_le32(content); - exfat_update_bh(sb, bh, sb->s_flags & SB_SYNCHRONOUS); + exfat_update_bh(bh, sb->s_flags & SB_SYNCHRONOUS); exfat_mirror_bh(sb, sec, bh); brelse(bh); return 0; @@ -174,7 +174,6 @@ int exfat_free_cluster(struct inode *inode, struct exfat_chain *p_chain) return -EIO; } - set_bit(EXFAT_SB_DIRTY, &sbi->s_state); clu = p_chain->dir; if (p_chain->flags == ALLOC_NO_FAT_CHAIN) { @@ -230,21 +229,6 @@ int exfat_find_last_cluster(struct super_block *sb, struct exfat_chain *p_chain, return 0; } -static inline int exfat_sync_bhs(struct buffer_head **bhs, int nr_bhs) -{ - int i, err = 0; - - for (i = 0; i < nr_bhs; i++) - write_dirty_buffer(bhs[i], 0); - - for (i = 0; i < nr_bhs; i++) { - wait_on_buffer(bhs[i]); - if (!err && !buffer_uptodate(bhs[i])) - err = -EIO; - } - return err; -} - int exfat_zeroed_cluster(struct inode *dir, unsigned int clu) { struct super_block *sb = dir->i_sb; @@ -266,41 +250,23 @@ int exfat_zeroed_cluster(struct inode *dir, unsigned int clu) } /* Zeroing the unused blocks on this cluster */ - n = 0; while (blknr < last_blknr) { - bhs[n] = sb_getblk(sb, blknr); - if (!bhs[n]) { - err = -ENOMEM; - goto release_bhs; - } - memset(bhs[n]->b_data, 0, sb->s_blocksize); - exfat_update_bh(sb, bhs[n], 0); - - n++; - blknr++; - - if (n == nr_bhs) { - if (IS_DIRSYNC(dir)) { - err = exfat_sync_bhs(bhs, n); - if (err) - goto release_bhs; + for (n = 0; n < nr_bhs && blknr < last_blknr; n++, blknr++) { + bhs[n] = sb_getblk(sb, blknr); + if (!bhs[n]) { + err = -ENOMEM; + goto release_bhs; } - - for (i = 0; i < n; i++) - brelse(bhs[i]); - n = 0; + memset(bhs[n]->b_data, 0, sb->s_blocksize); } - } - if (IS_DIRSYNC(dir)) { - err = exfat_sync_bhs(bhs, n); + err = exfat_update_bhs(bhs, n, IS_DIRSYNC(dir)); if (err) goto release_bhs; - } - - for (i = 0; i < n; i++) - brelse(bhs[i]); + for (i = 0; i < n; i++) + brelse(bhs[i]); + } return 0; release_bhs: @@ -358,8 +324,6 @@ int exfat_alloc_cluster(struct inode *inode, unsigned int num_alloc, } } - set_bit(EXFAT_SB_DIRTY, &sbi->s_state); - p_chain->dir = EXFAT_EOF_CLUSTER; while ((new_clu = exfat_find_free_bitmap(sb, hint_clu)) != diff --git a/fs/exfat/file.c b/fs/exfat/file.c index a6a063830edc..f41f523a58ad 100644 --- a/fs/exfat/file.c +++ b/fs/exfat/file.c @@ -106,7 +106,7 @@ int __exfat_truncate(struct inode *inode, loff_t new_size) if (ei->type != TYPE_FILE && ei->type != TYPE_DIR) return -EPERM; - exfat_set_vol_flags(sb, VOL_DIRTY); + exfat_set_volume_dirty(sb); num_clusters_new = EXFAT_B_TO_CLU_ROUND_UP(i_size_read(inode), sbi); num_clusters_phys = @@ -154,6 +154,7 @@ int __exfat_truncate(struct inode *inode, loff_t new_size) struct timespec64 ts; struct exfat_dentry *ep, *ep2; struct exfat_entry_set_cache *es; + int err; es = exfat_get_dentry_set(sb, &(ei->dir), ei->entry, ES_ALL_ENTRIES); @@ -188,7 +189,9 @@ int __exfat_truncate(struct inode *inode, loff_t new_size) } exfat_update_dir_chksum_with_entry_set(es); - exfat_free_dentry_set(es, inode_needs_sync(inode)); + err = exfat_free_dentry_set(es, inode_needs_sync(inode)); + if (err) + return err; } /* cut off from the FAT chain */ @@ -217,7 +220,7 @@ int __exfat_truncate(struct inode *inode, loff_t new_size) if (exfat_free_cluster(inode, &clu)) return -EIO; - exfat_set_vol_flags(sb, VOL_CLEAN); + exfat_clear_volume_dirty(sb); return 0; } diff --git a/fs/exfat/inode.c b/fs/exfat/inode.c index cf9ca6c4d046..7f90204adef5 100644 --- a/fs/exfat/inode.c +++ b/fs/exfat/inode.c @@ -39,7 +39,7 @@ static int __exfat_write_inode(struct inode *inode, int sync) if (is_dir && ei->dir.dir == sbi->root_dir && ei->entry == -1) return 0; - exfat_set_vol_flags(sb, VOL_DIRTY); + exfat_set_volume_dirty(sb); /* get the directory entry of given file or directory */ es = exfat_get_dentry_set(sb, &(ei->dir), ei->entry, ES_ALL_ENTRIES); @@ -77,8 +77,7 @@ static int __exfat_write_inode(struct inode *inode, int sync) ep2->dentry.stream.size = ep2->dentry.stream.valid_size; exfat_update_dir_chksum_with_entry_set(es); - exfat_free_dentry_set(es, sync); - return 0; + return exfat_free_dentry_set(es, sync); } int exfat_write_inode(struct inode *inode, struct writeback_control *wbc) @@ -168,7 +167,7 @@ static int exfat_map_cluster(struct inode *inode, unsigned int clu_offset, } if (*clu == EXFAT_EOF_CLUSTER) { - exfat_set_vol_flags(sb, VOL_DIRTY); + exfat_set_volume_dirty(sb); new_clu.dir = (last_clu == EXFAT_EOF_CLUSTER) ? EXFAT_EOF_CLUSTER : last_clu + 1; @@ -222,6 +221,7 @@ static int exfat_map_cluster(struct inode *inode, unsigned int clu_offset, if (ei->dir.dir != DIR_DELETED && modified) { struct exfat_dentry *ep; struct exfat_entry_set_cache *es; + int err; es = exfat_get_dentry_set(sb, &(ei->dir), ei->entry, ES_ALL_ENTRIES); @@ -240,8 +240,9 @@ static int exfat_map_cluster(struct inode *inode, unsigned int clu_offset, ep->dentry.stream.valid_size; exfat_update_dir_chksum_with_entry_set(es); - exfat_free_dentry_set(es, inode_needs_sync(inode)); - + err = exfat_free_dentry_set(es, inode_needs_sync(inode)); + if (err) + return err; } /* end of if != DIR_DELETED */ inode->i_blocks += diff --git a/fs/exfat/misc.c b/fs/exfat/misc.c index 17d41f3d3709..d34e6193258d 100644 --- a/fs/exfat/misc.c +++ b/fs/exfat/misc.c @@ -163,9 +163,8 @@ u32 exfat_calc_chksum32(void *data, int len, u32 chksum, int type) return chksum; } -void exfat_update_bh(struct super_block *sb, struct buffer_head *bh, int sync) +void exfat_update_bh(struct buffer_head *bh, int sync) { - set_bit(EXFAT_SB_DIRTY, &EXFAT_SB(sb)->s_state); set_buffer_uptodate(bh); mark_buffer_dirty(bh); @@ -173,6 +172,25 @@ void exfat_update_bh(struct super_block *sb, struct buffer_head *bh, int sync) sync_dirty_buffer(bh); } +int exfat_update_bhs(struct buffer_head **bhs, int nr_bhs, int sync) +{ + int i, err = 0; + + for (i = 0; i < nr_bhs; i++) { + set_buffer_uptodate(bhs[i]); + mark_buffer_dirty(bhs[i]); + if (sync) + write_dirty_buffer(bhs[i], 0); + } + + for (i = 0; i < nr_bhs && sync; i++) { + wait_on_buffer(bhs[i]); + if (!err && !buffer_uptodate(bhs[i])) + err = -EIO; + } + return err; +} + void exfat_chain_set(struct exfat_chain *ec, unsigned int dir, unsigned int size, unsigned char flags) { diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c index 2b9e21094a96..e73f20f66cb2 100644 --- a/fs/exfat/namei.c +++ b/fs/exfat/namei.c @@ -387,7 +387,7 @@ static int exfat_find_empty_entry(struct inode *inode, ep->dentry.stream.valid_size = cpu_to_le64(size); ep->dentry.stream.size = ep->dentry.stream.valid_size; ep->dentry.stream.flags = p_dir->flags; - exfat_update_bh(sb, bh, IS_DIRSYNC(inode)); + exfat_update_bh(bh, IS_DIRSYNC(inode)); brelse(bh); if (exfat_update_dir_chksum(inode, &(ei->dir), ei->entry)) @@ -562,10 +562,10 @@ static int exfat_create(struct inode *dir, struct dentry *dentry, umode_t mode, int err; mutex_lock(&EXFAT_SB(sb)->s_lock); - exfat_set_vol_flags(sb, VOL_DIRTY); + exfat_set_volume_dirty(sb); err = exfat_add_entry(dir, dentry->d_name.name, &cdir, TYPE_FILE, &info); - exfat_set_vol_flags(sb, VOL_CLEAN); + exfat_clear_volume_dirty(sb); if (err) goto unlock; @@ -834,7 +834,7 @@ static int exfat_unlink(struct inode *dir, struct dentry *dentry) num_entries++; brelse(bh); - exfat_set_vol_flags(sb, VOL_DIRTY); + exfat_set_volume_dirty(sb); /* update the directory entry */ if (exfat_remove_entries(dir, &cdir, entry, 0, num_entries)) { err = -EIO; @@ -843,7 +843,7 @@ static int exfat_unlink(struct inode *dir, struct dentry *dentry) /* This doesn't modify ei */ ei->dir.dir = DIR_DELETED; - exfat_set_vol_flags(sb, VOL_CLEAN); + exfat_clear_volume_dirty(sb); inode_inc_iversion(dir); dir->i_mtime = dir->i_atime = current_time(dir); @@ -873,10 +873,10 @@ static int exfat_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) int err; mutex_lock(&EXFAT_SB(sb)->s_lock); - exfat_set_vol_flags(sb, VOL_DIRTY); + exfat_set_volume_dirty(sb); err = exfat_add_entry(dir, dentry->d_name.name, &cdir, TYPE_DIR, &info); - exfat_set_vol_flags(sb, VOL_CLEAN); + exfat_clear_volume_dirty(sb); if (err) goto unlock; @@ -1001,14 +1001,14 @@ static int exfat_rmdir(struct inode *dir, struct dentry *dentry) num_entries++; brelse(bh); - exfat_set_vol_flags(sb, VOL_DIRTY); + exfat_set_volume_dirty(sb); err = exfat_remove_entries(dir, &cdir, entry, 0, num_entries); if (err) { exfat_err(sb, "failed to exfat_remove_entries : err(%d)", err); goto unlock; } ei->dir.dir = DIR_DELETED; - exfat_set_vol_flags(sb, VOL_CLEAN); + exfat_clear_volume_dirty(sb); inode_inc_iversion(dir); dir->i_mtime = dir->i_atime = current_time(dir); @@ -1071,7 +1071,7 @@ static int exfat_rename_file(struct inode *inode, struct exfat_chain *p_dir, epnew->dentry.file.attr |= cpu_to_le16(ATTR_ARCHIVE); ei->attr |= ATTR_ARCHIVE; } - exfat_update_bh(sb, new_bh, sync); + exfat_update_bh(new_bh, sync); brelse(old_bh); brelse(new_bh); @@ -1087,7 +1087,7 @@ static int exfat_rename_file(struct inode *inode, struct exfat_chain *p_dir, } memcpy(epnew, epold, DENTRY_SIZE); - exfat_update_bh(sb, new_bh, sync); + exfat_update_bh(new_bh, sync); brelse(old_bh); brelse(new_bh); @@ -1104,7 +1104,7 @@ static int exfat_rename_file(struct inode *inode, struct exfat_chain *p_dir, epold->dentry.file.attr |= cpu_to_le16(ATTR_ARCHIVE); ei->attr |= ATTR_ARCHIVE; } - exfat_update_bh(sb, old_bh, sync); + exfat_update_bh(old_bh, sync); brelse(old_bh); ret = exfat_init_ext_entry(inode, p_dir, oldentry, num_new_entries, p_uniname); @@ -1159,7 +1159,7 @@ static int exfat_move_file(struct inode *inode, struct exfat_chain *p_olddir, epnew->dentry.file.attr |= cpu_to_le16(ATTR_ARCHIVE); ei->attr |= ATTR_ARCHIVE; } - exfat_update_bh(sb, new_bh, IS_DIRSYNC(inode)); + exfat_update_bh(new_bh, IS_DIRSYNC(inode)); brelse(mov_bh); brelse(new_bh); @@ -1175,7 +1175,7 @@ static int exfat_move_file(struct inode *inode, struct exfat_chain *p_olddir, } memcpy(epnew, epmov, DENTRY_SIZE); - exfat_update_bh(sb, new_bh, IS_DIRSYNC(inode)); + exfat_update_bh(new_bh, IS_DIRSYNC(inode)); brelse(mov_bh); brelse(new_bh); @@ -1300,7 +1300,7 @@ static int __exfat_rename(struct inode *old_parent_inode, if (ret) goto out; - exfat_set_vol_flags(sb, VOL_DIRTY); + exfat_set_volume_dirty(sb); if (olddir.dir == newdir.dir) ret = exfat_rename_file(new_parent_inode, &olddir, dentry, @@ -1355,7 +1355,7 @@ del_out: */ new_ei->dir.dir = DIR_DELETED; } - exfat_set_vol_flags(sb, VOL_CLEAN); + exfat_clear_volume_dirty(sb); out: return ret; } diff --git a/fs/exfat/super.c b/fs/exfat/super.c index 253a92460d52..3b6a1659892f 100644 --- a/fs/exfat/super.c +++ b/fs/exfat/super.c @@ -45,9 +45,6 @@ static void exfat_put_super(struct super_block *sb) struct exfat_sb_info *sbi = EXFAT_SB(sb); mutex_lock(&sbi->s_lock); - if (test_and_clear_bit(EXFAT_SB_DIRTY, &sbi->s_state)) - sync_blockdev(sb->s_bdev); - exfat_set_vol_flags(sb, VOL_CLEAN); exfat_free_bitmap(sbi); brelse(sbi->boot_bh); mutex_unlock(&sbi->s_lock); @@ -60,13 +57,14 @@ static int exfat_sync_fs(struct super_block *sb, int wait) struct exfat_sb_info *sbi = EXFAT_SB(sb); int err = 0; + if (!wait) + return 0; + /* If there are some dirty buffers in the bdev inode */ mutex_lock(&sbi->s_lock); - if (test_and_clear_bit(EXFAT_SB_DIRTY, &sbi->s_state)) { - sync_blockdev(sb->s_bdev); - if (exfat_set_vol_flags(sb, VOL_CLEAN)) - err = -EIO; - } + sync_blockdev(sb->s_bdev); + if (exfat_clear_volume_dirty(sb)) + err = -EIO; mutex_unlock(&sbi->s_lock); return err; } @@ -98,17 +96,20 @@ static int exfat_statfs(struct dentry *dentry, struct kstatfs *buf) return 0; } -int exfat_set_vol_flags(struct super_block *sb, unsigned short new_flag) +static int exfat_set_vol_flags(struct super_block *sb, unsigned short new_flags) { struct exfat_sb_info *sbi = EXFAT_SB(sb); struct boot_sector *p_boot = (struct boot_sector *)sbi->boot_bh->b_data; bool sync; + /* retain persistent-flags */ + new_flags |= sbi->vol_flags_persistent; + /* flags are not changed */ - if (sbi->vol_flag == new_flag) + if (sbi->vol_flags == new_flags) return 0; - sbi->vol_flag = new_flag; + sbi->vol_flags = new_flags; /* skip updating volume dirty flag, * if this volume has been mounted with read-only @@ -116,9 +117,9 @@ int exfat_set_vol_flags(struct super_block *sb, unsigned short new_flag) if (sb_rdonly(sb)) return 0; - p_boot->vol_flags = cpu_to_le16(new_flag); + p_boot->vol_flags = cpu_to_le16(new_flags); - if (new_flag == VOL_DIRTY && !buffer_dirty(sbi->boot_bh)) + if ((new_flags & VOLUME_DIRTY) && !buffer_dirty(sbi->boot_bh)) sync = true; else sync = false; @@ -131,6 +132,20 @@ int exfat_set_vol_flags(struct super_block *sb, unsigned short new_flag) return 0; } +int exfat_set_volume_dirty(struct super_block *sb) +{ + struct exfat_sb_info *sbi = EXFAT_SB(sb); + + return exfat_set_vol_flags(sb, sbi->vol_flags | VOLUME_DIRTY); +} + +int exfat_clear_volume_dirty(struct super_block *sb) +{ + struct exfat_sb_info *sbi = EXFAT_SB(sb); + + return exfat_set_vol_flags(sb, sbi->vol_flags & ~VOLUME_DIRTY); +} + static int exfat_show_options(struct seq_file *m, struct dentry *root) { struct super_block *sb = root->d_sb; @@ -459,7 +474,8 @@ static int exfat_read_boot_sector(struct super_block *sb) sbi->dentries_per_clu = 1 << (sbi->cluster_size_bits - DENTRY_SIZE_BITS); - sbi->vol_flag = le16_to_cpu(p_boot->vol_flags); + sbi->vol_flags = le16_to_cpu(p_boot->vol_flags); + sbi->vol_flags_persistent = sbi->vol_flags & (VOLUME_DIRTY | MEDIA_FAILURE); sbi->clu_srch_ptr = EXFAT_FIRST_CLUSTER; sbi->used_clusters = EXFAT_CLUSTERS_UNTRACKED; @@ -474,9 +490,9 @@ static int exfat_read_boot_sector(struct super_block *sb) exfat_err(sb, "bogus data start sector"); return -EINVAL; } - if (sbi->vol_flag & VOL_DIRTY) + if (sbi->vol_flags & VOLUME_DIRTY) exfat_warn(sb, "Volume was not properly unmounted. Some data may be corrupt. Please run fsck."); - if (sbi->vol_flag & ERR_MEDIUM) + if (sbi->vol_flags & MEDIA_FAILURE) exfat_warn(sb, "Medium has reported failures. Some data may be lost."); /* exFAT file size is limited by a disk volume size */ diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 236064930251..ff807e14c891 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -523,7 +523,7 @@ void f2fs_remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type) __remove_ino_entry(sbi, ino, type); } -/* mode should be APPEND_INO or UPDATE_INO */ +/* mode should be APPEND_INO, UPDATE_INO or TRANS_DIR_INO */ bool f2fs_exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode) { struct inode_management *im = &sbi->im[mode]; @@ -1258,8 +1258,6 @@ void f2fs_wait_on_all_pages(struct f2fs_sb_info *sbi, int type) DEFINE_WAIT(wait); for (;;) { - prepare_to_wait(&sbi->cp_wait, &wait, TASK_UNINTERRUPTIBLE); - if (!get_pages(sbi, type)) break; @@ -1269,6 +1267,10 @@ void f2fs_wait_on_all_pages(struct f2fs_sb_info *sbi, int type) if (type == F2FS_DIRTY_META) f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO); + else if (type == F2FS_WB_CP_DATA) + f2fs_submit_merged_write(sbi, DATA); + + prepare_to_wait(&sbi->cp_wait, &wait, TASK_UNINTERRUPTIBLE); io_schedule_timeout(DEFAULT_IO_TIMEOUT); } finish_wait(&sbi->cp_wait, &wait); @@ -1415,7 +1417,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) curseg_alloc_type(sbi, i + CURSEG_HOT_DATA); } - /* 2 cp + n data seg summary + orphan inode blocks */ + /* 2 cp + n data seg summary + orphan inode blocks */ data_sum_blocks = f2fs_npages_for_summary_flush(sbi, false); spin_lock_irqsave(&sbi->cp_lock, flags); if (data_sum_blocks < NR_CURSEG_DATA_TYPE) @@ -1515,9 +1517,10 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) /* * invalidate intermediate page cache borrowed from meta inode which are - * used for migration of encrypted or verity inode's blocks. + * used for migration of encrypted, verity or compressed inode's blocks. */ - if (f2fs_sb_has_encrypt(sbi) || f2fs_sb_has_verity(sbi)) + if (f2fs_sb_has_encrypt(sbi) || f2fs_sb_has_verity(sbi) || + f2fs_sb_has_compression(sbi)) invalidate_mapping_pages(META_MAPPING(sbi), MAIN_BLKADDR(sbi), MAX_BLKADDR(sbi) - 1); diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c index 29e50fbe7eca..1dfb126a0cb2 100644 --- a/fs/f2fs/compress.c +++ b/fs/f2fs/compress.c @@ -49,6 +49,13 @@ bool f2fs_is_compressed_page(struct page *page) return false; if (IS_ATOMIC_WRITTEN_PAGE(page) || IS_DUMMY_WRITTEN_PAGE(page)) return false; + /* + * page->private may be set with pid. + * pid_max is enough to check if it is traced. + */ + if (IS_IO_TRACED_PAGE(page)) + return false; + f2fs_bug_on(F2FS_M_SB(page->mapping), *((u32 *)page_private(page)) != F2FS_COMPRESSED_PAGE_MAGIC); return true; @@ -506,7 +513,7 @@ bool f2fs_is_compress_backend_ready(struct inode *inode) return f2fs_cops[F2FS_I(inode)->i_compress_algorithm]; } -static mempool_t *compress_page_pool = NULL; +static mempool_t *compress_page_pool; static int num_compress_pages = 512; module_param(num_compress_pages, uint, 0444); MODULE_PARM_DESC(num_compress_pages, @@ -663,6 +670,7 @@ void f2fs_decompress_pages(struct bio *bio, struct page *page, bool verity) const struct f2fs_compress_ops *cops = f2fs_cops[fi->i_compress_algorithm]; int ret; + int i; dec_page_count(sbi, F2FS_RD_DATA); @@ -681,6 +689,26 @@ void f2fs_decompress_pages(struct bio *bio, struct page *page, bool verity) goto out_free_dic; } + dic->tpages = f2fs_kzalloc(sbi, sizeof(struct page *) * + dic->cluster_size, GFP_NOFS); + if (!dic->tpages) { + ret = -ENOMEM; + goto out_free_dic; + } + + for (i = 0; i < dic->cluster_size; i++) { + if (dic->rpages[i]) { + dic->tpages[i] = dic->rpages[i]; + continue; + } + + dic->tpages[i] = f2fs_compress_alloc_page(); + if (!dic->tpages[i]) { + ret = -ENOMEM; + goto out_free_dic; + } + } + if (cops->init_decompress_ctx) { ret = cops->init_decompress_ctx(dic); if (ret) @@ -821,7 +849,7 @@ static int f2fs_compressed_blocks(struct compress_ctx *cc) } /* return # of valid blocks in compressed cluster */ -static int f2fs_cluster_blocks(struct compress_ctx *cc, bool compr) +static int f2fs_cluster_blocks(struct compress_ctx *cc) { return __f2fs_cluster_blocks(cc, false); } @@ -835,7 +863,7 @@ int f2fs_is_compressed_cluster(struct inode *inode, pgoff_t index) .cluster_idx = index >> F2FS_I(inode)->i_log_cluster_size, }; - return f2fs_cluster_blocks(&cc, false); + return f2fs_cluster_blocks(&cc); } static bool cluster_may_compress(struct compress_ctx *cc) @@ -886,7 +914,7 @@ static int prepare_compress_overwrite(struct compress_ctx *cc, bool prealloc; retry: - ret = f2fs_cluster_blocks(cc, false); + ret = f2fs_cluster_blocks(cc); if (ret <= 0) return ret; @@ -949,7 +977,7 @@ retry: } if (prealloc) { - __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, true); + f2fs_do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, true); set_new_dnode(&dn, cc->inode, NULL, NULL, 0); @@ -964,7 +992,7 @@ retry: break; } - __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, false); + f2fs_do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, false); } if (likely(!ret)) { @@ -1096,8 +1124,16 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc, loff_t psize; int i, err; - if (!IS_NOQUOTA(inode) && !f2fs_trylock_op(sbi)) + if (IS_NOQUOTA(inode)) { + /* + * We need to wait for node_write to avoid block allocation during + * checkpoint. This can only happen to quota writes which can cause + * the below discard race condition. + */ + down_read(&sbi->node_write); + } else if (!f2fs_trylock_op(sbi)) { return -EAGAIN; + } set_new_dnode(&dn, cc->inode, NULL, NULL, 0); @@ -1137,6 +1173,13 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc, f2fs_set_compressed_page(cc->cpages[i], inode, cc->rpages[i + 1]->index, cic); fio.compressed_page = cc->cpages[i]; + + fio.old_blkaddr = data_blkaddr(dn.inode, dn.node_page, + dn.ofs_in_node + i + 1); + + /* wait for GCed page writeback via META_MAPPING */ + f2fs_wait_on_block_writeback(inode, fio.old_blkaddr); + if (fio.encrypted) { fio.page = cc->rpages[i + 1]; err = f2fs_encrypt_one_page(&fio); @@ -1203,7 +1246,9 @@ unlock_continue: set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN); f2fs_put_dnode(&dn); - if (!IS_NOQUOTA(inode)) + if (IS_NOQUOTA(inode)) + up_read(&sbi->node_write); + else f2fs_unlock_op(sbi); spin_lock(&fi->i_size_lock); @@ -1230,7 +1275,9 @@ out_put_cic: out_put_dnode: f2fs_put_dnode(&dn); out_unlock_op: - if (!IS_NOQUOTA(inode)) + if (IS_NOQUOTA(inode)) + up_read(&sbi->node_write); + else f2fs_unlock_op(sbi); return -EAGAIN; } @@ -1310,6 +1357,12 @@ retry_write: congestion_wait(BLK_RW_ASYNC, DEFAULT_IO_TIMEOUT); lock_page(cc->rpages[i]); + + if (!PageDirty(cc->rpages[i])) { + unlock_page(cc->rpages[i]); + continue; + } + clear_page_dirty_for_io(cc->rpages[i]); goto retry_write; } @@ -1353,6 +1406,8 @@ int f2fs_write_multi_pages(struct compress_ctx *cc, err = f2fs_write_compressed_pages(cc, submitted, wbc, io_type); cops->destroy_compress_ctx(cc); + kfree(cc->cpages); + cc->cpages = NULL; if (!err) return 0; f2fs_bug_on(F2FS_I_SB(cc->inode), err != -EAGAIN); @@ -1415,22 +1470,6 @@ struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc) dic->cpages[i] = page; } - dic->tpages = f2fs_kzalloc(sbi, sizeof(struct page *) * - dic->cluster_size, GFP_NOFS); - if (!dic->tpages) - goto out_free; - - for (i = 0; i < dic->cluster_size; i++) { - if (cc->rpages[i]) { - dic->tpages[i] = cc->rpages[i]; - continue; - } - - dic->tpages[i] = f2fs_compress_alloc_page(); - if (!dic->tpages[i]) - goto out_free; - } - return dic; out_free: diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 5f527073143e..ed2bca0fce92 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -87,7 +87,7 @@ static bool __is_cp_guaranteed(struct page *page) sbi = F2FS_I_SB(inode); if (inode->i_ino == F2FS_META_INO(sbi) || - inode->i_ino == F2FS_NODE_INO(sbi) || + inode->i_ino == F2FS_NODE_INO(sbi) || S_ISDIR(inode->i_mode) || (S_ISREG(inode->i_mode) && (f2fs_is_atomic_file(inode) || IS_NOQUOTA(inode))) || @@ -1073,12 +1073,13 @@ static void f2fs_release_read_bio(struct bio *bio) /* This can handle encryption stuffs */ static int f2fs_submit_page_read(struct inode *inode, struct page *page, - block_t blkaddr, bool for_write) + block_t blkaddr, int op_flags, bool for_write) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct bio *bio; - bio = f2fs_grab_read_bio(inode, blkaddr, 1, 0, page->index, for_write); + bio = f2fs_grab_read_bio(inode, blkaddr, 1, op_flags, + page->index, for_write); if (IS_ERR(bio)) return PTR_ERR(bio); @@ -1193,7 +1194,7 @@ int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index) int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index) { - struct extent_info ei = {0,0,0}; + struct extent_info ei = {0, 0, 0}; struct inode *inode = dn->inode; if (f2fs_lookup_extent_cache(inode, index, &ei)) { @@ -1265,7 +1266,8 @@ got_it: return page; } - err = f2fs_submit_page_read(inode, page, dn.data_blkaddr, for_write); + err = f2fs_submit_page_read(inode, page, dn.data_blkaddr, + op_flags, for_write); if (err) goto put_err; return page; @@ -1414,7 +1416,7 @@ alloc: set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version); old_blkaddr = dn->data_blkaddr; f2fs_allocate_data_block(sbi, NULL, old_blkaddr, &dn->data_blkaddr, - &sum, seg_type, NULL, false); + &sum, seg_type, NULL); if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO) invalidate_mapping_pages(META_MAPPING(sbi), old_blkaddr, old_blkaddr); @@ -1474,7 +1476,7 @@ map_blocks: return err; } -void __do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock) +void f2fs_do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock) { if (flag == F2FS_GET_BLOCK_PRE_AIO) { if (lock) @@ -1539,7 +1541,7 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, next_dnode: if (map->m_may_create) - __do_map_lock(sbi, flag, true); + f2fs_do_map_lock(sbi, flag, true); /* When reading holes, we need its node page */ set_new_dnode(&dn, inode, NULL, NULL, 0); @@ -1688,7 +1690,7 @@ skip: f2fs_put_dnode(&dn); if (map->m_may_create) { - __do_map_lock(sbi, flag, false); + f2fs_do_map_lock(sbi, flag, false); f2fs_balance_fs(sbi, dn.node_changed); } goto next_dnode; @@ -1714,7 +1716,7 @@ sync_out: f2fs_put_dnode(&dn); unlock_out: if (map->m_may_create) { - __do_map_lock(sbi, flag, false); + f2fs_do_map_lock(sbi, flag, false); f2fs_balance_fs(sbi, dn.node_changed); } out: @@ -1861,6 +1863,7 @@ static int f2fs_xattr_fiemap(struct inode *inode, flags |= FIEMAP_EXTENT_LAST; err = fiemap_fill_next_extent(fieinfo, 0, phys, len, flags); + trace_f2fs_fiemap(inode, 0, phys, len, flags, err); if (err || err == 1) return err; } @@ -1884,8 +1887,10 @@ static int f2fs_xattr_fiemap(struct inode *inode, flags = FIEMAP_EXTENT_LAST; } - if (phys) + if (phys) { err = fiemap_fill_next_extent(fieinfo, 0, phys, len, flags); + trace_f2fs_fiemap(inode, 0, phys, len, flags, err); + } return (err < 0 ? err : 0); } @@ -1979,6 +1984,7 @@ next: ret = fiemap_fill_next_extent(fieinfo, logical, phys, size, flags); + trace_f2fs_fiemap(inode, logical, phys, size, flags, ret); if (ret) goto out; size = 0; @@ -2213,9 +2219,7 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret, if (ret) goto out; - /* cluster was overwritten as normal cluster */ - if (dn.data_blkaddr != COMPRESS_ADDR) - goto out; + f2fs_bug_on(sbi, dn.data_blkaddr != COMPRESS_ADDR); for (i = 1; i < cc->cluster_size; i++) { block_t blkaddr; @@ -2342,6 +2346,7 @@ static int f2fs_mpage_readpages(struct inode *inode, unsigned nr_pages = rac ? readahead_count(rac) : 1; unsigned max_nr_pages = nr_pages; int ret = 0; + bool drop_ra = false; map.m_pblk = 0; map.m_lblk = 0; @@ -2352,10 +2357,26 @@ static int f2fs_mpage_readpages(struct inode *inode, map.m_seg_type = NO_CHECK_TYPE; map.m_may_create = false; + /* + * Two readahead threads for same address range can cause race condition + * which fragments sequential read IOs. So let's avoid each other. + */ + if (rac && readahead_count(rac)) { + if (READ_ONCE(F2FS_I(inode)->ra_offset) == readahead_index(rac)) + drop_ra = true; + else + WRITE_ONCE(F2FS_I(inode)->ra_offset, + readahead_index(rac)); + } + for (; nr_pages; nr_pages--) { if (rac) { page = readahead_page(rac); prefetchw(&page->flags); + if (drop_ra) { + f2fs_put_page(page, 1); + continue; + } } #ifdef CONFIG_F2FS_FS_COMPRESSION @@ -2418,6 +2439,9 @@ next_page: } if (bio) __submit_bio(F2FS_I_SB(inode), bio, DATA); + + if (rac && readahead_count(rac) && !drop_ra) + WRITE_ONCE(F2FS_I(inode)->ra_offset, -1); return ret; } @@ -2772,8 +2796,20 @@ write: /* Dentry/quota blocks are controlled by checkpoint */ if (S_ISDIR(inode->i_mode) || IS_NOQUOTA(inode)) { + /* + * We need to wait for node_write to avoid block allocation during + * checkpoint. This can only happen to quota writes which can cause + * the below discard race condition. + */ + if (IS_NOQUOTA(inode)) + down_read(&sbi->node_write); + fio.need_lock = LOCK_DONE; err = f2fs_do_write_data_page(&fio); + + if (IS_NOQUOTA(inode)) + up_read(&sbi->node_write); + goto done; } @@ -3268,7 +3304,7 @@ static int prepare_write_begin(struct f2fs_sb_info *sbi, if (f2fs_has_inline_data(inode) || (pos & PAGE_MASK) >= i_size_read(inode)) { - __do_map_lock(sbi, flag, true); + f2fs_do_map_lock(sbi, flag, true); locked = true; } @@ -3305,7 +3341,7 @@ restart: err = f2fs_get_dnode_of_data(&dn, index, LOOKUP_NODE); if (err || dn.data_blkaddr == NULL_ADDR) { f2fs_put_dnode(&dn); - __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, + f2fs_do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, true); WARN_ON(flag != F2FS_GET_BLOCK_PRE_AIO); locked = true; @@ -3321,7 +3357,7 @@ out: f2fs_put_dnode(&dn); unlock_out: if (locked) - __do_map_lock(sbi, flag, false); + f2fs_do_map_lock(sbi, flag, false); return err; } @@ -3433,7 +3469,7 @@ repeat: err = -EFSCORRUPTED; goto fail; } - err = f2fs_submit_page_read(inode, page, blkaddr, true); + err = f2fs_submit_page_read(inode, page, blkaddr, 0, true); if (err) goto fail; @@ -3483,6 +3519,10 @@ static int f2fs_write_end(struct file *file, if (f2fs_compressed_file(inode) && fsdata) { f2fs_compress_write_end(inode, fsdata, page->index, copied); f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); + + if (pos + copied > i_size_read(inode) && + !f2fs_verity_in_progress(inode)) + f2fs_i_size_write(inode, pos + copied); return copied; } #endif @@ -3742,10 +3782,9 @@ static sector_t f2fs_bmap_compress(struct inode *inode, sector_t block) } f2fs_put_dnode(&dn); - return blknr; #else - return -EOPNOTSUPP; + return 0; #endif } @@ -3753,18 +3792,26 @@ static sector_t f2fs_bmap_compress(struct inode *inode, sector_t block) static sector_t f2fs_bmap(struct address_space *mapping, sector_t block) { struct inode *inode = mapping->host; + struct buffer_head tmp = { + .b_size = i_blocksize(inode), + }; + sector_t blknr = 0; if (f2fs_has_inline_data(inode)) - return 0; + goto out; /* make sure allocating whole blocks */ if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) filemap_write_and_wait(mapping); if (f2fs_compressed_file(inode)) - return f2fs_bmap_compress(inode, block); + blknr = f2fs_bmap_compress(inode, block); - return generic_block_bmap(mapping, block, get_data_block_bmap); + if (!get_data_block_bmap(inode, block, &tmp, 0)) + blknr = tmp.b_blocknr; +out: + trace_f2fs_bmap(inode, block, blknr); + return blknr; } #ifdef CONFIG_MIGRATION diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c index 0dbcb0f9c019..4276c0f79beb 100644 --- a/fs/f2fs/debug.c +++ b/fs/f2fs/debug.c @@ -174,6 +174,26 @@ static void update_general_status(struct f2fs_sb_info *sbi) for (i = META_CP; i < META_MAX; i++) si->meta_count[i] = atomic_read(&sbi->meta_count[i]); + for (i = 0; i < NO_CHECK_TYPE; i++) { + si->dirty_seg[i] = 0; + si->full_seg[i] = 0; + si->valid_blks[i] = 0; + } + + for (i = 0; i < MAIN_SEGS(sbi); i++) { + int blks = get_seg_entry(sbi, i)->valid_blocks; + int type = get_seg_entry(sbi, i)->type; + + if (!blks) + continue; + + if (blks == sbi->blocks_per_seg) + si->full_seg[type]++; + else + si->dirty_seg[type]++; + si->valid_blks[type] += blks; + } + for (i = 0; i < 2; i++) { si->segment_count[i] = sbi->segment_count[i]; si->block_count[i] = sbi->block_count[i]; @@ -329,30 +349,50 @@ static int stat_show(struct seq_file *s, void *v) seq_printf(s, "\nMain area: %d segs, %d secs %d zones\n", si->main_area_segs, si->main_area_sections, si->main_area_zones); - seq_printf(s, " - COLD data: %d, %d, %d\n", + seq_printf(s, " TYPE %8s %8s %8s %10s %10s %10s\n", + "segno", "secno", "zoneno", "dirty_seg", "full_seg", "valid_blk"); + seq_printf(s, " - COLD data: %8d %8d %8d %10u %10u %10u\n", si->curseg[CURSEG_COLD_DATA], si->cursec[CURSEG_COLD_DATA], - si->curzone[CURSEG_COLD_DATA]); - seq_printf(s, " - WARM data: %d, %d, %d\n", + si->curzone[CURSEG_COLD_DATA], + si->dirty_seg[CURSEG_COLD_DATA], + si->full_seg[CURSEG_COLD_DATA], + si->valid_blks[CURSEG_COLD_DATA]); + seq_printf(s, " - WARM data: %8d %8d %8d %10u %10u %10u\n", si->curseg[CURSEG_WARM_DATA], si->cursec[CURSEG_WARM_DATA], - si->curzone[CURSEG_WARM_DATA]); - seq_printf(s, " - HOT data: %d, %d, %d\n", + si->curzone[CURSEG_WARM_DATA], + si->dirty_seg[CURSEG_WARM_DATA], + si->full_seg[CURSEG_WARM_DATA], + si->valid_blks[CURSEG_WARM_DATA]); + seq_printf(s, " - HOT data: %8d %8d %8d %10u %10u %10u\n", si->curseg[CURSEG_HOT_DATA], si->cursec[CURSEG_HOT_DATA], - si->curzone[CURSEG_HOT_DATA]); - seq_printf(s, " - Dir dnode: %d, %d, %d\n", + si->curzone[CURSEG_HOT_DATA], + si->dirty_seg[CURSEG_HOT_DATA], + si->full_seg[CURSEG_HOT_DATA], + si->valid_blks[CURSEG_HOT_DATA]); + seq_printf(s, " - Dir dnode: %8d %8d %8d %10u %10u %10u\n", si->curseg[CURSEG_HOT_NODE], si->cursec[CURSEG_HOT_NODE], - si->curzone[CURSEG_HOT_NODE]); - seq_printf(s, " - File dnode: %d, %d, %d\n", + si->curzone[CURSEG_HOT_NODE], + si->dirty_seg[CURSEG_HOT_NODE], + si->full_seg[CURSEG_HOT_NODE], + si->valid_blks[CURSEG_HOT_NODE]); + seq_printf(s, " - File dnode: %8d %8d %8d %10u %10u %10u\n", si->curseg[CURSEG_WARM_NODE], si->cursec[CURSEG_WARM_NODE], - si->curzone[CURSEG_WARM_NODE]); - seq_printf(s, " - Indir nodes: %d, %d, %d\n", + si->curzone[CURSEG_WARM_NODE], + si->dirty_seg[CURSEG_WARM_NODE], + si->full_seg[CURSEG_WARM_NODE], + si->valid_blks[CURSEG_WARM_NODE]); + seq_printf(s, " - Indir nodes: %8d %8d %8d %10u %10u %10u\n", si->curseg[CURSEG_COLD_NODE], si->cursec[CURSEG_COLD_NODE], - si->curzone[CURSEG_COLD_NODE]); + si->curzone[CURSEG_COLD_NODE], + si->dirty_seg[CURSEG_COLD_NODE], + si->full_seg[CURSEG_COLD_NODE], + si->valid_blks[CURSEG_COLD_NODE]); seq_printf(s, "\n - Valid: %d\n - Dirty: %d\n", si->main_area_segs - si->dirty_count - si->prefree_count - si->free_segs, diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index d35976785e8c..069f498af1e3 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -779,7 +779,7 @@ int f2fs_do_add_link(struct inode *dir, const struct qstr *name, return err; /* - * An immature stakable filesystem shows a race condition between lookup + * An immature stackable filesystem shows a race condition between lookup * and create. If we have same task when doing lookup and create, it's * definitely fine as expected by VFS normally. Otherwise, let's just * verify on-disk dentry one more time, which guarantees filesystem diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c index e60078460ad1..686c68b98610 100644 --- a/fs/f2fs/extent_cache.c +++ b/fs/f2fs/extent_cache.c @@ -325,9 +325,10 @@ static void __drop_largest_extent(struct extent_tree *et, } /* return true, if inode page is changed */ -static bool __f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext) +static void __f2fs_init_extent_tree(struct inode *inode, struct page *ipage) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct f2fs_extent *i_ext = ipage ? &F2FS_INODE(ipage)->i_ext : NULL; struct extent_tree *et; struct extent_node *en; struct extent_info ei; @@ -335,16 +336,18 @@ static bool __f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_e if (!f2fs_may_extent_tree(inode)) { /* drop largest extent */ if (i_ext && i_ext->len) { + f2fs_wait_on_page_writeback(ipage, NODE, true, true); i_ext->len = 0; - return true; + set_page_dirty(ipage); + return; } - return false; + return; } et = __grab_extent_tree(inode); if (!i_ext || !i_ext->len) - return false; + return; get_extent_info(&ei, i_ext); @@ -360,17 +363,14 @@ static bool __f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_e } out: write_unlock(&et->lock); - return false; } -bool f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext) +void f2fs_init_extent_tree(struct inode *inode, struct page *ipage) { - bool ret = __f2fs_init_extent_tree(inode, i_ext); + __f2fs_init_extent_tree(inode, ipage); if (!F2FS_I(inode)->extent_tree) set_inode_flag(inode, FI_NO_EXTENT); - - return ret; } static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs, diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index b35a50f4953c..16322ea5b463 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -402,12 +402,8 @@ static inline bool __has_cursum_space(struct f2fs_journal *journal, } /* - * ioctl commands + * f2fs-specific ioctl commands */ -#define F2FS_IOC_GETFLAGS FS_IOC_GETFLAGS -#define F2FS_IOC_SETFLAGS FS_IOC_SETFLAGS -#define F2FS_IOC_GETVERSION FS_IOC_GETVERSION - #define F2FS_IOCTL_MAGIC 0xf5 #define F2FS_IOC_START_ATOMIC_WRITE _IO(F2FS_IOCTL_MAGIC, 1) #define F2FS_IOC_COMMIT_ATOMIC_WRITE _IO(F2FS_IOCTL_MAGIC, 2) @@ -434,13 +430,8 @@ static inline bool __has_cursum_space(struct f2fs_journal *journal, _IOR(F2FS_IOCTL_MAGIC, 18, __u64) #define F2FS_IOC_RESERVE_COMPRESS_BLOCKS \ _IOR(F2FS_IOCTL_MAGIC, 19, __u64) - -#define F2FS_IOC_GET_VOLUME_NAME FS_IOC_GETFSLABEL -#define F2FS_IOC_SET_VOLUME_NAME FS_IOC_SETFSLABEL - -#define F2FS_IOC_SET_ENCRYPTION_POLICY FS_IOC_SET_ENCRYPTION_POLICY -#define F2FS_IOC_GET_ENCRYPTION_POLICY FS_IOC_GET_ENCRYPTION_POLICY -#define F2FS_IOC_GET_ENCRYPTION_PWSALT FS_IOC_GET_ENCRYPTION_PWSALT +#define F2FS_IOC_SEC_TRIM_FILE _IOW(F2FS_IOCTL_MAGIC, 20, \ + struct f2fs_sectrim_range) /* * should be same as XFS_IOC_GOINGDOWN. @@ -453,17 +444,12 @@ static inline bool __has_cursum_space(struct f2fs_journal *journal, #define F2FS_GOING_DOWN_METAFLUSH 0x3 /* going down with meta flush */ #define F2FS_GOING_DOWN_NEED_FSCK 0x4 /* going down to trigger fsck */ -#if defined(__KERNEL__) && defined(CONFIG_COMPAT) /* - * ioctl commands in 32 bit emulation + * Flags used by F2FS_IOC_SEC_TRIM_FILE */ -#define F2FS_IOC32_GETFLAGS FS_IOC32_GETFLAGS -#define F2FS_IOC32_SETFLAGS FS_IOC32_SETFLAGS -#define F2FS_IOC32_GETVERSION FS_IOC32_GETVERSION -#endif - -#define F2FS_IOC_FSGETXATTR FS_IOC_FSGETXATTR -#define F2FS_IOC_FSSETXATTR FS_IOC_FSSETXATTR +#define F2FS_TRIM_FILE_DISCARD 0x1 /* send discard command */ +#define F2FS_TRIM_FILE_ZEROOUT 0x2 /* zero out */ +#define F2FS_TRIM_FILE_MASK 0x3 struct f2fs_gc_range { u32 sync; @@ -488,6 +474,12 @@ struct f2fs_flush_device { u32 segments; /* # of segments to flush */ }; +struct f2fs_sectrim_range { + u64 start; + u64 len; + u64 flags; +}; + /* for inline stuff */ #define DEF_INLINE_RESERVED_SIZE 1 static inline int get_extra_isize(struct inode *inode); @@ -794,6 +786,7 @@ struct f2fs_inode_info { struct list_head inmem_pages; /* inmemory pages managed by f2fs */ struct task_struct *inmem_task; /* store inmemory task */ struct mutex inmem_lock; /* lock for inmemory pages */ + pgoff_t ra_offset; /* ongoing readahead offset */ struct extent_tree *extent_tree; /* cached extent_tree entry */ /* avoid racing between foreground op and gc */ @@ -1267,7 +1260,8 @@ enum { GC_NORMAL, GC_IDLE_CB, GC_IDLE_GREEDY, - GC_URGENT, + GC_URGENT_HIGH, + GC_URGENT_LOW, }; enum { @@ -1313,6 +1307,14 @@ enum fsync_mode { #define IS_DUMMY_WRITTEN_PAGE(page) \ (page_private(page) == (unsigned long)DUMMY_WRITTEN_PAGE) +#ifdef CONFIG_F2FS_IO_TRACE +#define IS_IO_TRACED_PAGE(page) \ + (page_private(page) > 0 && \ + page_private(page) < (unsigned long)PID_MAX_LIMIT) +#else +#define IS_IO_TRACED_PAGE(page) (0) +#endif + #ifdef CONFIG_FS_ENCRYPTION #define DUMMY_ENCRYPTION_ENABLED(sbi) \ (unlikely(F2FS_OPTION(sbi).dummy_enc_ctx.ctx != NULL)) @@ -1438,7 +1440,7 @@ struct f2fs_sb_info { unsigned long last_time[MAX_TIME]; /* to store time in jiffies */ long interval_time[MAX_TIME]; /* to store thresholds */ - struct inode_management im[MAX_INO_ENTRY]; /* manage inode cache */ + struct inode_management im[MAX_INO_ENTRY]; /* manage inode cache */ spinlock_t fsync_node_lock; /* for node entry lock */ struct list_head fsync_node_list; /* node list head */ @@ -1516,8 +1518,9 @@ struct f2fs_sb_info { unsigned int cur_victim_sec; /* current victim section num */ unsigned int gc_mode; /* current GC state */ unsigned int next_victim_seg[2]; /* next segment in victim section */ + /* for skip statistic */ - unsigned int atomic_files; /* # of opened atomic file */ + unsigned int atomic_files; /* # of opened atomic file */ unsigned long long skipped_atomic_files[2]; /* FG_GC and BG_GC */ unsigned long long skipped_gc_rwsem; /* FG_GC only */ @@ -2456,7 +2459,7 @@ static inline void *f2fs_kmem_cache_alloc(struct kmem_cache *cachep, static inline bool is_idle(struct f2fs_sb_info *sbi, int type) { - if (sbi->gc_mode == GC_URGENT) + if (sbi->gc_mode == GC_URGENT_HIGH) return true; if (get_pages(sbi, F2FS_RD_DATA) || get_pages(sbi, F2FS_RD_NODE) || @@ -2474,6 +2477,10 @@ static inline bool is_idle(struct f2fs_sb_info *sbi, int type) atomic_read(&SM_I(sbi)->fcc_info->queued_flush)) return false; + if (sbi->gc_mode == GC_URGENT_LOW && + (type == DISCARD_TIME || type == GC_TIME)) + return true; + return f2fs_time_over(sbi, type); } @@ -2649,7 +2656,7 @@ static inline void __mark_inode_dirty_flag(struct inode *inode, static inline void set_inode_flag(struct inode *inode, int flag) { - test_and_set_bit(flag, F2FS_I(inode)->flags); + set_bit(flag, F2FS_I(inode)->flags); __mark_inode_dirty_flag(inode, flag, true); } @@ -2660,7 +2667,7 @@ static inline int is_inode_flag_set(struct inode *inode, int flag) static inline void clear_inode_flag(struct inode *inode, int flag) { - test_and_clear_bit(flag, F2FS_I(inode)->flags); + clear_bit(flag, F2FS_I(inode)->flags); __mark_inode_dirty_flag(inode, flag, false); } @@ -3275,7 +3282,7 @@ void f2fs_ra_node_page(struct f2fs_sb_info *sbi, nid_t nid); struct page *f2fs_get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid); struct page *f2fs_get_node_page_ra(struct page *parent, int start); int f2fs_move_node_page(struct page *node_page, int gc_type); -int f2fs_flush_inline_data(struct f2fs_sb_info *sbi); +void f2fs_flush_inline_data(struct f2fs_sb_info *sbi); int f2fs_fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode, struct writeback_control *wbc, bool atomic, unsigned int *seq_id); @@ -3287,7 +3294,7 @@ bool f2fs_alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid); void f2fs_alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid); void f2fs_alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid); int f2fs_try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink); -void f2fs_recover_inline_xattr(struct inode *inode, struct page *page); +int f2fs_recover_inline_xattr(struct inode *inode, struct page *page); int f2fs_recover_xattr_data(struct inode *inode, struct page *page); int f2fs_recover_inode_page(struct f2fs_sb_info *sbi, struct page *page); int f2fs_restore_node_summary(struct f2fs_sb_info *sbi, @@ -3325,9 +3332,10 @@ block_t f2fs_get_unusable_blocks(struct f2fs_sb_info *sbi); int f2fs_disable_cp_again(struct f2fs_sb_info *sbi, block_t unusable); void f2fs_release_discard_addrs(struct f2fs_sb_info *sbi); int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra); -void allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type, +void f2fs_allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type, unsigned int start, unsigned int end); -void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi, int type); +void f2fs_allocate_new_segment(struct f2fs_sb_info *sbi, int type); +void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi); int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range); bool f2fs_exist_trim_candidates(struct f2fs_sb_info *sbi, struct cp_control *cpc); @@ -3350,7 +3358,7 @@ void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn, void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, block_t old_blkaddr, block_t *new_blkaddr, struct f2fs_summary *sum, int type, - struct f2fs_io_info *fio, bool add_list); + struct f2fs_io_info *fio); void f2fs_wait_on_page_writeback(struct page *page, enum page_type type, bool ordered, bool locked); void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr); @@ -3448,7 +3456,7 @@ struct page *f2fs_get_lock_data_page(struct inode *inode, pgoff_t index, struct page *f2fs_get_new_data_page(struct inode *inode, struct page *ipage, pgoff_t index, bool new_i_size); int f2fs_do_write_data_page(struct f2fs_io_info *fio); -void __do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock); +void f2fs_do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock); int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, int create, int flag); int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, @@ -3536,6 +3544,9 @@ struct f2fs_stat_info { int curseg[NR_CURSEG_TYPE]; int cursec[NR_CURSEG_TYPE]; int curzone[NR_CURSEG_TYPE]; + unsigned int dirty_seg[NR_CURSEG_TYPE]; + unsigned int full_seg[NR_CURSEG_TYPE]; + unsigned int valid_blks[NR_CURSEG_TYPE]; unsigned int meta_count[META_MAX]; unsigned int segment_count[2]; @@ -3750,7 +3761,7 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page); int f2fs_convert_inline_inode(struct inode *inode); int f2fs_try_convert_inline_dir(struct inode *dir, struct dentry *dentry); int f2fs_write_inline_data(struct inode *inode, struct page *page); -bool f2fs_recover_inline_data(struct inode *inode, struct page *npage); +int f2fs_recover_inline_data(struct inode *inode, struct page *npage); struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir, const struct f2fs_filename *fname, struct page **res_page); @@ -3795,7 +3806,7 @@ struct rb_entry *f2fs_lookup_rb_tree_ret(struct rb_root_cached *root, bool f2fs_check_rb_tree_consistence(struct f2fs_sb_info *sbi, struct rb_root_cached *root); unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink); -bool f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext); +void f2fs_init_extent_tree(struct inode *inode, struct page *ipage); void f2fs_drop_extent_tree(struct inode *inode); unsigned int f2fs_destroy_extent_node(struct inode *inode); void f2fs_destroy_extent_tree(struct inode *inode); diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 3268f8dd59bb..8a422400e824 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -21,6 +21,7 @@ #include <linux/uuid.h> #include <linux/file.h> #include <linux/nls.h> +#include <linux/sched/signal.h> #include "f2fs.h" #include "node.h" @@ -105,11 +106,11 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf) if (need_alloc) { /* block allocation */ - __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, true); + f2fs_do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, true); set_new_dnode(&dn, inode, NULL, NULL, 0); err = f2fs_get_block(&dn, page->index); f2fs_put_dnode(&dn); - __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, false); + f2fs_do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, false); } #ifdef CONFIG_F2FS_FS_COMPRESSION @@ -1373,8 +1374,6 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len) truncate_pagecache(inode, offset); new_size = i_size_read(inode) - len; - truncate_pagecache(inode, new_size); - ret = f2fs_truncate_blocks(inode, new_size, true); up_write(&F2FS_I(inode)->i_mmap_sem); if (!ret) @@ -1660,7 +1659,7 @@ next_alloc: map.m_seg_type = CURSEG_COLD_DATA_PINNED; f2fs_lock_op(sbi); - f2fs_allocate_new_segments(sbi, CURSEG_COLD_DATA); + f2fs_allocate_new_segment(sbi, CURSEG_COLD_DATA); f2fs_unlock_op(sbi); err = f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_DIO); @@ -2527,6 +2526,11 @@ do_more: } ret = f2fs_gc(sbi, range.sync, true, GET_SEGNO(sbi, range.start)); + if (ret) { + if (ret == -EBUSY) + ret = -EAGAIN; + goto out; + } range.start += BLKS_PER_SEC(sbi); if (range.start <= end) goto do_more; @@ -3359,7 +3363,7 @@ static int f2fs_ioc_measure_verity(struct file *filp, unsigned long arg) return fsverity_ioctl_measure(filp, (void __user *)arg); } -static int f2fs_get_volume_name(struct file *filp, unsigned long arg) +static int f2fs_ioc_getfslabel(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); @@ -3385,7 +3389,7 @@ static int f2fs_get_volume_name(struct file *filp, unsigned long arg) return err; } -static int f2fs_set_volume_name(struct file *filp, unsigned long arg) +static int f2fs_ioc_setfslabel(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); @@ -3531,14 +3535,14 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg) if (ret) goto out; - if (!F2FS_I(inode)->i_compr_blocks) - goto out; - F2FS_I(inode)->i_flags |= F2FS_IMMUTABLE_FL; f2fs_set_inode_flags(inode); inode->i_ctime = current_time(inode); f2fs_mark_inode_dirty_sync(inode, true); + if (!F2FS_I(inode)->i_compr_blocks) + goto out; + down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); down_write(&F2FS_I(inode)->i_mmap_sem); @@ -3756,6 +3760,193 @@ out: return ret; } +static int f2fs_secure_erase(struct block_device *bdev, struct inode *inode, + pgoff_t off, block_t block, block_t len, u32 flags) +{ + struct request_queue *q = bdev_get_queue(bdev); + sector_t sector = SECTOR_FROM_BLOCK(block); + sector_t nr_sects = SECTOR_FROM_BLOCK(len); + int ret = 0; + + if (!q) + return -ENXIO; + + if (flags & F2FS_TRIM_FILE_DISCARD) + ret = blkdev_issue_discard(bdev, sector, nr_sects, GFP_NOFS, + blk_queue_secure_erase(q) ? + BLKDEV_DISCARD_SECURE : 0); + + if (!ret && (flags & F2FS_TRIM_FILE_ZEROOUT)) { + if (IS_ENCRYPTED(inode)) + ret = fscrypt_zeroout_range(inode, off, block, len); + else + ret = blkdev_issue_zeroout(bdev, sector, nr_sects, + GFP_NOFS, 0); + } + + return ret; +} + +static int f2fs_sec_trim_file(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct address_space *mapping = inode->i_mapping; + struct block_device *prev_bdev = NULL; + struct f2fs_sectrim_range range; + pgoff_t index, pg_end, prev_index = 0; + block_t prev_block = 0, len = 0; + loff_t end_addr; + bool to_end = false; + int ret = 0; + + if (!(filp->f_mode & FMODE_WRITE)) + return -EBADF; + + if (copy_from_user(&range, (struct f2fs_sectrim_range __user *)arg, + sizeof(range))) + return -EFAULT; + + if (range.flags == 0 || (range.flags & ~F2FS_TRIM_FILE_MASK) || + !S_ISREG(inode->i_mode)) + return -EINVAL; + + if (((range.flags & F2FS_TRIM_FILE_DISCARD) && + !f2fs_hw_support_discard(sbi)) || + ((range.flags & F2FS_TRIM_FILE_ZEROOUT) && + IS_ENCRYPTED(inode) && f2fs_is_multi_device(sbi))) + return -EOPNOTSUPP; + + file_start_write(filp); + inode_lock(inode); + + if (f2fs_is_atomic_file(inode) || f2fs_compressed_file(inode) || + range.start >= inode->i_size) { + ret = -EINVAL; + goto err; + } + + if (range.len == 0) + goto err; + + if (inode->i_size - range.start > range.len) { + end_addr = range.start + range.len; + } else { + end_addr = range.len == (u64)-1 ? + sbi->sb->s_maxbytes : inode->i_size; + to_end = true; + } + + if (!IS_ALIGNED(range.start, F2FS_BLKSIZE) || + (!to_end && !IS_ALIGNED(end_addr, F2FS_BLKSIZE))) { + ret = -EINVAL; + goto err; + } + + index = F2FS_BYTES_TO_BLK(range.start); + pg_end = DIV_ROUND_UP(end_addr, F2FS_BLKSIZE); + + ret = f2fs_convert_inline_inode(inode); + if (ret) + goto err; + + down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + down_write(&F2FS_I(inode)->i_mmap_sem); + + ret = filemap_write_and_wait_range(mapping, range.start, + to_end ? LLONG_MAX : end_addr - 1); + if (ret) + goto out; + + truncate_inode_pages_range(mapping, range.start, + to_end ? -1 : end_addr - 1); + + while (index < pg_end) { + struct dnode_of_data dn; + pgoff_t end_offset, count; + int i; + + set_new_dnode(&dn, inode, NULL, NULL, 0); + ret = f2fs_get_dnode_of_data(&dn, index, LOOKUP_NODE); + if (ret) { + if (ret == -ENOENT) { + index = f2fs_get_next_page_offset(&dn, index); + continue; + } + goto out; + } + + end_offset = ADDRS_PER_PAGE(dn.node_page, inode); + count = min(end_offset - dn.ofs_in_node, pg_end - index); + for (i = 0; i < count; i++, index++, dn.ofs_in_node++) { + struct block_device *cur_bdev; + block_t blkaddr = f2fs_data_blkaddr(&dn); + + if (!__is_valid_data_blkaddr(blkaddr)) + continue; + + if (!f2fs_is_valid_blkaddr(sbi, blkaddr, + DATA_GENERIC_ENHANCE)) { + ret = -EFSCORRUPTED; + f2fs_put_dnode(&dn); + goto out; + } + + cur_bdev = f2fs_target_device(sbi, blkaddr, NULL); + if (f2fs_is_multi_device(sbi)) { + int di = f2fs_target_device_index(sbi, blkaddr); + + blkaddr -= FDEV(di).start_blk; + } + + if (len) { + if (prev_bdev == cur_bdev && + index == prev_index + len && + blkaddr == prev_block + len) { + len++; + } else { + ret = f2fs_secure_erase(prev_bdev, + inode, prev_index, prev_block, + len, range.flags); + if (ret) { + f2fs_put_dnode(&dn); + goto out; + } + + len = 0; + } + } + + if (!len) { + prev_bdev = cur_bdev; + prev_index = index; + prev_block = blkaddr; + len = 1; + } + } + + f2fs_put_dnode(&dn); + + if (fatal_signal_pending(current)) { + ret = -EINTR; + goto out; + } + cond_resched(); + } + + if (len) + ret = f2fs_secure_erase(prev_bdev, inode, prev_index, + prev_block, len, range.flags); +out: + up_write(&F2FS_I(inode)->i_mmap_sem); + up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); +err: + inode_unlock(inode); + file_end_write(filp); + + return ret; +} + long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { if (unlikely(f2fs_cp_error(F2FS_I_SB(file_inode(filp))))) @@ -3764,11 +3955,11 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return -ENOSPC; switch (cmd) { - case F2FS_IOC_GETFLAGS: + case FS_IOC_GETFLAGS: return f2fs_ioc_getflags(filp, arg); - case F2FS_IOC_SETFLAGS: + case FS_IOC_SETFLAGS: return f2fs_ioc_setflags(filp, arg); - case F2FS_IOC_GETVERSION: + case FS_IOC_GETVERSION: return f2fs_ioc_getversion(filp, arg); case F2FS_IOC_START_ATOMIC_WRITE: return f2fs_ioc_start_atomic_write(filp); @@ -3784,11 +3975,11 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return f2fs_ioc_shutdown(filp, arg); case FITRIM: return f2fs_ioc_fitrim(filp, arg); - case F2FS_IOC_SET_ENCRYPTION_POLICY: + case FS_IOC_SET_ENCRYPTION_POLICY: return f2fs_ioc_set_encryption_policy(filp, arg); - case F2FS_IOC_GET_ENCRYPTION_POLICY: + case FS_IOC_GET_ENCRYPTION_POLICY: return f2fs_ioc_get_encryption_policy(filp, arg); - case F2FS_IOC_GET_ENCRYPTION_PWSALT: + case FS_IOC_GET_ENCRYPTION_PWSALT: return f2fs_ioc_get_encryption_pwsalt(filp, arg); case FS_IOC_GET_ENCRYPTION_POLICY_EX: return f2fs_ioc_get_encryption_policy_ex(filp, arg); @@ -3816,9 +4007,9 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return f2fs_ioc_flush_device(filp, arg); case F2FS_IOC_GET_FEATURES: return f2fs_ioc_get_features(filp, arg); - case F2FS_IOC_FSGETXATTR: + case FS_IOC_FSGETXATTR: return f2fs_ioc_fsgetxattr(filp, arg); - case F2FS_IOC_FSSETXATTR: + case FS_IOC_FSSETXATTR: return f2fs_ioc_fssetxattr(filp, arg); case F2FS_IOC_GET_PIN_FILE: return f2fs_ioc_get_pin_file(filp, arg); @@ -3832,16 +4023,18 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return f2fs_ioc_enable_verity(filp, arg); case FS_IOC_MEASURE_VERITY: return f2fs_ioc_measure_verity(filp, arg); - case F2FS_IOC_GET_VOLUME_NAME: - return f2fs_get_volume_name(filp, arg); - case F2FS_IOC_SET_VOLUME_NAME: - return f2fs_set_volume_name(filp, arg); + case FS_IOC_GETFSLABEL: + return f2fs_ioc_getfslabel(filp, arg); + case FS_IOC_SETFSLABEL: + return f2fs_ioc_setfslabel(filp, arg); case F2FS_IOC_GET_COMPRESS_BLOCKS: return f2fs_get_compress_blocks(filp, arg); case F2FS_IOC_RELEASE_COMPRESS_BLOCKS: return f2fs_release_compress_blocks(filp, arg); case F2FS_IOC_RESERVE_COMPRESS_BLOCKS: return f2fs_reserve_compress_blocks(filp, arg); + case F2FS_IOC_SEC_TRIM_FILE: + return f2fs_sec_trim_file(filp, arg); default: return -ENOTTY; } @@ -3966,14 +4159,14 @@ out: long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { switch (cmd) { - case F2FS_IOC32_GETFLAGS: - cmd = F2FS_IOC_GETFLAGS; + case FS_IOC32_GETFLAGS: + cmd = FS_IOC_GETFLAGS; break; - case F2FS_IOC32_SETFLAGS: - cmd = F2FS_IOC_SETFLAGS; + case FS_IOC32_SETFLAGS: + cmd = FS_IOC_SETFLAGS; break; - case F2FS_IOC32_GETVERSION: - cmd = F2FS_IOC_GETVERSION; + case FS_IOC32_GETVERSION: + cmd = FS_IOC_GETVERSION; break; case F2FS_IOC_START_ATOMIC_WRITE: case F2FS_IOC_COMMIT_ATOMIC_WRITE: @@ -3982,9 +4175,9 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case F2FS_IOC_ABORT_VOLATILE_WRITE: case F2FS_IOC_SHUTDOWN: case FITRIM: - case F2FS_IOC_SET_ENCRYPTION_POLICY: - case F2FS_IOC_GET_ENCRYPTION_PWSALT: - case F2FS_IOC_GET_ENCRYPTION_POLICY: + case FS_IOC_SET_ENCRYPTION_POLICY: + case FS_IOC_GET_ENCRYPTION_PWSALT: + case FS_IOC_GET_ENCRYPTION_POLICY: case FS_IOC_GET_ENCRYPTION_POLICY_EX: case FS_IOC_ADD_ENCRYPTION_KEY: case FS_IOC_REMOVE_ENCRYPTION_KEY: @@ -3998,19 +4191,20 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case F2FS_IOC_MOVE_RANGE: case F2FS_IOC_FLUSH_DEVICE: case F2FS_IOC_GET_FEATURES: - case F2FS_IOC_FSGETXATTR: - case F2FS_IOC_FSSETXATTR: + case FS_IOC_FSGETXATTR: + case FS_IOC_FSSETXATTR: case F2FS_IOC_GET_PIN_FILE: case F2FS_IOC_SET_PIN_FILE: case F2FS_IOC_PRECACHE_EXTENTS: case F2FS_IOC_RESIZE_FS: case FS_IOC_ENABLE_VERITY: case FS_IOC_MEASURE_VERITY: - case F2FS_IOC_GET_VOLUME_NAME: - case F2FS_IOC_SET_VOLUME_NAME: + case FS_IOC_GETFSLABEL: + case FS_IOC_SETFSLABEL: case F2FS_IOC_GET_COMPRESS_BLOCKS: case F2FS_IOC_RELEASE_COMPRESS_BLOCKS: case F2FS_IOC_RESERVE_COMPRESS_BLOCKS: + case F2FS_IOC_SEC_TRIM_FILE: break; default: return -ENOIOCTLCMD; diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 5b95d5a146eb..11b4adde9baf 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -21,6 +21,9 @@ #include "gc.h" #include <trace/events/f2fs.h> +static unsigned int count_bits(const unsigned long *addr, + unsigned int offset, unsigned int len); + static int gc_thread_func(void *data) { struct f2fs_sb_info *sbi = data; @@ -79,7 +82,7 @@ static int gc_thread_func(void *data) * invalidated soon after by user update or deletion. * So, I'd like to wait some time to collect dirty segments. */ - if (sbi->gc_mode == GC_URGENT) { + if (sbi->gc_mode == GC_URGENT_HIGH) { wait_ms = gc_th->urgent_sleep_time; down_write(&sbi->gc_lock); goto do_gc; @@ -173,7 +176,7 @@ static int select_gc_type(struct f2fs_sb_info *sbi, int gc_type) gc_mode = GC_CB; break; case GC_IDLE_GREEDY: - case GC_URGENT: + case GC_URGENT_HIGH: gc_mode = GC_GREEDY; break; } @@ -187,14 +190,20 @@ static void select_policy(struct f2fs_sb_info *sbi, int gc_type, if (p->alloc_mode == SSR) { p->gc_mode = GC_GREEDY; - p->dirty_segmap = dirty_i->dirty_segmap[type]; + p->dirty_bitmap = dirty_i->dirty_segmap[type]; p->max_search = dirty_i->nr_dirty[type]; p->ofs_unit = 1; } else { p->gc_mode = select_gc_type(sbi, gc_type); - p->dirty_segmap = dirty_i->dirty_segmap[DIRTY]; - p->max_search = dirty_i->nr_dirty[DIRTY]; p->ofs_unit = sbi->segs_per_sec; + if (__is_large_section(sbi)) { + p->dirty_bitmap = dirty_i->dirty_secmap; + p->max_search = count_bits(p->dirty_bitmap, + 0, MAIN_SECS(sbi)); + } else { + p->dirty_bitmap = dirty_i->dirty_segmap[DIRTY]; + p->max_search = dirty_i->nr_dirty[DIRTY]; + } } /* @@ -202,7 +211,7 @@ static void select_policy(struct f2fs_sb_info *sbi, int gc_type, * foreground GC and urgent GC cases. */ if (gc_type != FG_GC && - (sbi->gc_mode != GC_URGENT) && + (sbi->gc_mode != GC_URGENT_HIGH) && p->max_search > sbi->max_victim_search) p->max_search = sbi->max_victim_search; @@ -321,6 +330,7 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi, unsigned int secno, last_victim; unsigned int last_segment; unsigned int nsearched = 0; + int ret = 0; mutex_lock(&dirty_i->seglist_lock); last_segment = MAIN_SECS(sbi) * sbi->segs_per_sec; @@ -332,12 +342,19 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi, p.min_cost = get_max_cost(sbi, &p); if (*result != NULL_SEGNO) { - if (get_valid_blocks(sbi, *result, false) && - !sec_usage_check(sbi, GET_SEC_FROM_SEG(sbi, *result))) + if (!get_valid_blocks(sbi, *result, false)) { + ret = -ENODATA; + goto out; + } + + if (sec_usage_check(sbi, GET_SEC_FROM_SEG(sbi, *result))) + ret = -EBUSY; + else p.min_segno = *result; goto out; } + ret = -ENODATA; if (p.max_search == 0) goto out; @@ -365,10 +382,14 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi, } while (1) { - unsigned long cost; - unsigned int segno; - - segno = find_next_bit(p.dirty_segmap, last_segment, p.offset); + unsigned long cost, *dirty_bitmap; + unsigned int unit_no, segno; + + dirty_bitmap = p.dirty_bitmap; + unit_no = find_next_bit(dirty_bitmap, + last_segment / p.ofs_unit, + p.offset / p.ofs_unit); + segno = unit_no * p.ofs_unit; if (segno >= last_segment) { if (sm->last_victim[p.gc_mode]) { last_segment = @@ -381,14 +402,7 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi, } p.offset = segno + p.ofs_unit; - if (p.ofs_unit > 1) { - p.offset -= segno % p.ofs_unit; - nsearched += count_bits(p.dirty_segmap, - p.offset - p.ofs_unit, - p.ofs_unit); - } else { - nsearched++; - } + nsearched++; #ifdef CONFIG_F2FS_CHECK_FS /* @@ -421,9 +435,10 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi, next: if (nsearched >= p.max_search) { if (!sm->last_victim[p.gc_mode] && segno <= last_victim) - sm->last_victim[p.gc_mode] = last_victim + 1; + sm->last_victim[p.gc_mode] = + last_victim + p.ofs_unit; else - sm->last_victim[p.gc_mode] = segno + 1; + sm->last_victim[p.gc_mode] = segno + p.ofs_unit; sm->last_victim[p.gc_mode] %= (MAIN_SECS(sbi) * sbi->segs_per_sec); break; @@ -440,6 +455,7 @@ got_result: else set_bit(secno, dirty_i->victim_secmap); } + ret = 0; } out: @@ -449,7 +465,7 @@ out: prefree_segments(sbi), free_segments(sbi)); mutex_unlock(&dirty_i->seglist_lock); - return (p.min_segno == NULL_SEGNO) ? 0 : 1; + return ret; } static const struct victim_selection default_v_ops = { @@ -833,8 +849,10 @@ static int move_data_block(struct inode *inode, block_t bidx, mpage = f2fs_grab_cache_page(META_MAPPING(fio.sbi), fio.old_blkaddr, false); - if (!mpage) + if (!mpage) { + err = -ENOMEM; goto up_out; + } fio.encrypted_page = mpage; @@ -859,7 +877,7 @@ static int move_data_block(struct inode *inode, block_t bidx, } f2fs_allocate_data_block(fio.sbi, NULL, fio.old_blkaddr, &newaddr, - &sum, CURSEG_COLD_DATA, NULL, false); + &sum, CURSEG_COLD_DATA, NULL); fio.encrypted_page = f2fs_pagecache_get_page(META_MAPPING(fio.sbi), newaddr, FGP_LOCK | FGP_CREAT, GFP_NOFS); @@ -1333,10 +1351,9 @@ gc_more: ret = -EINVAL; goto stop; } - if (!__get_victim(sbi, &segno, gc_type)) { - ret = -ENODATA; + ret = __get_victim(sbi, &segno, gc_type); + if (ret) goto stop; - } seg_freed = do_garbage_collect(sbi, segno, &gc_list, gc_type); if (gc_type == FG_GC && seg_freed == sbi->segs_per_sec) @@ -1434,7 +1451,7 @@ static int free_segment_range(struct f2fs_sb_info *sbi, /* Move out cursegs from the target range */ for (type = CURSEG_HOT_DATA; type < NR_CURSEG_TYPE; type++) - allocate_segment_for_resize(sbi, type, start, end); + f2fs_allocate_segment_for_resize(sbi, type, start, end); /* do GC to move out valid blocks in the range */ for (segno = start; segno <= end; segno += sbi->segs_per_sec) { diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index dbade310dc79..102df444f623 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -12,6 +12,7 @@ #include "f2fs.h" #include "node.h" +#include <trace/events/f2fs.h> bool f2fs_may_inline_data(struct inode *inode) { @@ -253,7 +254,7 @@ int f2fs_write_inline_data(struct inode *inode, struct page *page) return 0; } -bool f2fs_recover_inline_data(struct inode *inode, struct page *npage) +int f2fs_recover_inline_data(struct inode *inode, struct page *npage) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_inode *ri = NULL; @@ -275,7 +276,8 @@ bool f2fs_recover_inline_data(struct inode *inode, struct page *npage) ri && (ri->i_inline & F2FS_INLINE_DATA)) { process_inline: ipage = f2fs_get_node_page(sbi, inode->i_ino); - f2fs_bug_on(sbi, IS_ERR(ipage)); + if (IS_ERR(ipage)) + return PTR_ERR(ipage); f2fs_wait_on_page_writeback(ipage, NODE, true, true); @@ -288,21 +290,25 @@ process_inline: set_page_dirty(ipage); f2fs_put_page(ipage, 1); - return true; + return 1; } if (f2fs_has_inline_data(inode)) { ipage = f2fs_get_node_page(sbi, inode->i_ino); - f2fs_bug_on(sbi, IS_ERR(ipage)); + if (IS_ERR(ipage)) + return PTR_ERR(ipage); f2fs_truncate_inline_inode(inode, ipage, 0); clear_inode_flag(inode, FI_INLINE_DATA); f2fs_put_page(ipage, 1); } else if (ri && (ri->i_inline & F2FS_INLINE_DATA)) { - if (f2fs_truncate_blocks(inode, 0, false)) - return false; + int ret; + + ret = f2fs_truncate_blocks(inode, 0, false); + if (ret) + return ret; goto process_inline; } - return false; + return 0; } struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir, @@ -776,6 +782,7 @@ int f2fs_inline_data_fiemap(struct inode *inode, byteaddr += (char *)inline_data_addr(inode, ipage) - (char *)F2FS_INODE(ipage); err = fiemap_fill_next_extent(fieinfo, start, byteaddr, ilen, flags); + trace_f2fs_fiemap(inode, start, byteaddr, ilen, flags, err); out: f2fs_put_page(ipage, 1); return err; diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 44582a4db513..66969ae852b9 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -367,8 +367,7 @@ static int do_read_inode(struct inode *inode) fi->i_pino = le32_to_cpu(ri->i_pino); fi->i_dir_level = ri->i_dir_level; - if (f2fs_init_extent_tree(inode, &ri->i_ext)) - set_page_dirty(node_page); + f2fs_init_extent_tree(inode, node_page); get_inline_info(inode, ri); @@ -402,6 +401,7 @@ static int do_read_inode(struct inode *inode) /* try to recover cold bit for non-dir inode */ if (!S_ISDIR(inode->i_mode) && !is_cold_node(node_page)) { + f2fs_wait_on_page_writeback(node_page, NODE, true, true); set_cold_node(node_page, false); set_page_dirty(node_page); } diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index e94e02c6580a..84e4bbc1a64d 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -569,15 +569,17 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry) trace_f2fs_unlink_enter(dir, dentry); - if (unlikely(f2fs_cp_error(sbi))) - return -EIO; + if (unlikely(f2fs_cp_error(sbi))) { + err = -EIO; + goto fail; + } err = dquot_initialize(dir); if (err) - return err; + goto fail; err = dquot_initialize(inode); if (err) - return err; + goto fail; de = f2fs_find_entry(dir, &dentry->d_name, &page); if (!de) { @@ -600,7 +602,7 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry) /* VFS negative dentries are incompatible with Encoding and * Case-insensitiveness. Eventually we'll want avoid * invalidating the dentries here, alongside with returning the - * negative dentries at f2fs_lookup(), when it is better + * negative dentries at f2fs_lookup(), when it is better * supported by the VFS for the CI case. */ if (IS_CASEFOLDED(dir)) @@ -1285,7 +1287,7 @@ static const char *f2fs_encrypted_get_link(struct dentry *dentry, } const struct inode_operations f2fs_encrypted_symlink_inode_operations = { - .get_link = f2fs_encrypted_get_link, + .get_link = f2fs_encrypted_get_link, .getattr = f2fs_getattr, .setattr = f2fs_setattr, .listxattr = f2fs_listxattr, @@ -1311,7 +1313,7 @@ const struct inode_operations f2fs_dir_inode_operations = { }; const struct inode_operations f2fs_symlink_inode_operations = { - .get_link = f2fs_get_link, + .get_link = f2fs_get_link, .getattr = f2fs_getattr, .setattr = f2fs_setattr, .listxattr = f2fs_listxattr, @@ -1319,7 +1321,7 @@ const struct inode_operations f2fs_symlink_inode_operations = { const struct inode_operations f2fs_special_inode_operations = { .getattr = f2fs_getattr, - .setattr = f2fs_setattr, + .setattr = f2fs_setattr, .get_acl = f2fs_get_acl, .set_acl = f2fs_set_acl, .listxattr = f2fs_listxattr, diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 03e24df1c84f..9bbaa2614679 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -1041,8 +1041,10 @@ int f2fs_truncate_inode_blocks(struct inode *inode, pgoff_t from) trace_f2fs_truncate_inode_blocks_enter(inode, from); level = get_node_path(inode, from, offset, noffset); - if (level < 0) + if (level < 0) { + trace_f2fs_truncate_inode_blocks_exit(inode, level); return level; + } page = f2fs_get_node_page(sbi, inode->i_ino); if (IS_ERR(page)) { @@ -1726,7 +1728,7 @@ continue_unlock: set_dentry_mark(page, f2fs_need_dentry_mark(sbi, ino)); } - /* may be written by other thread */ + /* may be written by other thread */ if (!PageDirty(page)) set_page_dirty(page); } @@ -1814,12 +1816,11 @@ static bool flush_dirty_inode(struct page *page) return true; } -int f2fs_flush_inline_data(struct f2fs_sb_info *sbi) +void f2fs_flush_inline_data(struct f2fs_sb_info *sbi) { pgoff_t index = 0; struct pagevec pvec; int nr_pages; - int ret = 0; pagevec_init(&pvec); @@ -1858,7 +1859,6 @@ continue_unlock: pagevec_release(&pvec); cond_resched(); } - return ret; } int f2fs_sync_node_pages(struct f2fs_sb_info *sbi, @@ -1924,8 +1924,12 @@ continue_unlock: goto continue_unlock; } - /* flush inline_data, if it's async context. */ - if (do_balance && is_inline_node(page)) { + /* flush inline_data/inode, if it's async context. */ + if (!do_balance) + goto write_node; + + /* flush inline_data */ + if (is_inline_node(page)) { clear_inline_node(page); unlock_page(page); flush_inline_data(sbi, ino_of_node(page)); @@ -1938,7 +1942,7 @@ continue_unlock: if (flush_dirty_inode(page)) goto lock_node; } - +write_node: f2fs_wait_on_page_writeback(page, NODE, true, true); if (!clear_page_dirty_for_io(page)) @@ -2097,7 +2101,7 @@ const struct address_space_operations f2fs_node_aops = { .invalidatepage = f2fs_invalidate_page, .releasepage = f2fs_release_page, #ifdef CONFIG_MIGRATION - .migratepage = f2fs_migrate_page, + .migratepage = f2fs_migrate_page, #endif }; @@ -2108,7 +2112,7 @@ static struct free_nid *__lookup_free_nid_list(struct f2fs_nm_info *nm_i, } static int __insert_free_nid(struct f2fs_sb_info *sbi, - struct free_nid *i, enum nid_state state) + struct free_nid *i) { struct f2fs_nm_info *nm_i = NM_I(sbi); @@ -2116,10 +2120,8 @@ static int __insert_free_nid(struct f2fs_sb_info *sbi, if (err) return err; - f2fs_bug_on(sbi, state != i->state); - nm_i->nid_cnt[state]++; - if (state == FREE_NID) - list_add_tail(&i->list, &nm_i->free_nid_list); + nm_i->nid_cnt[FREE_NID]++; + list_add_tail(&i->list, &nm_i->free_nid_list); return 0; } @@ -2241,7 +2243,7 @@ static bool add_free_nid(struct f2fs_sb_info *sbi, } } ret = true; - err = __insert_free_nid(sbi, i, FREE_NID); + err = __insert_free_nid(sbi, i); err_out: if (update) { update_free_nid_bitmap(sbi, nid, ret, build); @@ -2572,7 +2574,7 @@ int f2fs_try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink) return nr - nr_shrink; } -void f2fs_recover_inline_xattr(struct inode *inode, struct page *page) +int f2fs_recover_inline_xattr(struct inode *inode, struct page *page) { void *src_addr, *dst_addr; size_t inline_size; @@ -2580,7 +2582,8 @@ void f2fs_recover_inline_xattr(struct inode *inode, struct page *page) struct f2fs_inode *ri; ipage = f2fs_get_node_page(F2FS_I_SB(inode), inode->i_ino); - f2fs_bug_on(F2FS_I_SB(inode), IS_ERR(ipage)); + if (IS_ERR(ipage)) + return PTR_ERR(ipage); ri = F2FS_INODE(page); if (ri->i_inline & F2FS_INLINE_XATTR) { @@ -2599,6 +2602,7 @@ void f2fs_recover_inline_xattr(struct inode *inode, struct page *page) update_inode: f2fs_update_inode(inode, ipage); f2fs_put_page(ipage, 1); + return 0; } int f2fs_recover_xattr_data(struct inode *inode, struct page *page) diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index ae5310f02e7f..4f12ade6410a 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -544,7 +544,9 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode, /* step 1: recover xattr */ if (IS_INODE(page)) { - f2fs_recover_inline_xattr(inode, page); + err = f2fs_recover_inline_xattr(inode, page); + if (err) + goto out; } else if (f2fs_has_xattr_block(ofs_of_node(page))) { err = f2fs_recover_xattr_data(inode, page); if (!err) @@ -553,8 +555,12 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode, } /* step 2: recover inline data */ - if (f2fs_recover_inline_data(inode, page)) + err = f2fs_recover_inline_data(inode, page); + if (err) { + if (err == 1) + err = 0; goto out; + } /* step 3: recover data indices */ start = f2fs_start_bidx_of_node(ofs_of_node(page), inode); @@ -742,7 +748,7 @@ next: f2fs_put_page(page, 1); } if (!err) - f2fs_allocate_new_segments(sbi, NO_CHECK_TYPE); + f2fs_allocate_new_segments(sbi); return err; } diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 196f31503511..a65d357f89a9 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -174,7 +174,7 @@ bool f2fs_need_SSR(struct f2fs_sb_info *sbi) if (f2fs_lfs_mode(sbi)) return false; - if (sbi->gc_mode == GC_URGENT) + if (sbi->gc_mode == GC_URGENT_HIGH) return true; if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) return true; @@ -796,6 +796,18 @@ static void __locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno, } if (!test_and_set_bit(segno, dirty_i->dirty_segmap[t])) dirty_i->nr_dirty[t]++; + + if (__is_large_section(sbi)) { + unsigned int secno = GET_SEC_FROM_SEG(sbi, segno); + unsigned short valid_blocks = + get_valid_blocks(sbi, segno, true); + + f2fs_bug_on(sbi, unlikely(!valid_blocks || + valid_blocks == BLKS_PER_SEC(sbi))); + + if (!IS_CURSEC(sbi, secno)) + set_bit(secno, dirty_i->dirty_secmap); + } } } @@ -803,6 +815,7 @@ static void __remove_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno, enum dirty_type dirty_type) { struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + unsigned short valid_blocks; if (test_and_clear_bit(segno, dirty_i->dirty_segmap[dirty_type])) dirty_i->nr_dirty[dirty_type]--; @@ -814,13 +827,26 @@ static void __remove_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno, if (test_and_clear_bit(segno, dirty_i->dirty_segmap[t])) dirty_i->nr_dirty[t]--; - if (get_valid_blocks(sbi, segno, true) == 0) { + valid_blocks = get_valid_blocks(sbi, segno, true); + if (valid_blocks == 0) { clear_bit(GET_SEC_FROM_SEG(sbi, segno), dirty_i->victim_secmap); #ifdef CONFIG_F2FS_CHECK_FS clear_bit(segno, SIT_I(sbi)->invalid_segmap); #endif } + if (__is_large_section(sbi)) { + unsigned int secno = GET_SEC_FROM_SEG(sbi, segno); + + if (!valid_blocks || + valid_blocks == BLKS_PER_SEC(sbi)) { + clear_bit(secno, dirty_i->dirty_secmap); + return; + } + + if (!IS_CURSEC(sbi, secno)) + set_bit(secno, dirty_i->dirty_secmap); + } } } @@ -1733,7 +1759,7 @@ static int issue_discard_thread(void *data) continue; } - if (sbi->gc_mode == GC_URGENT) + if (sbi->gc_mode == GC_URGENT_HIGH) __init_discard_policy(sbi, &dpolicy, DPOLICY_FORCE, 1); sb_start_intwrite(sbi->sb); @@ -2140,7 +2166,7 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del) new_vblocks = se->valid_blocks + del; offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr); - f2fs_bug_on(sbi, (new_vblocks >> (sizeof(unsigned short) << 3) || + f2fs_bug_on(sbi, (new_vblocks < 0 || (new_vblocks > sbi->blocks_per_seg))); se->valid_blocks = new_vblocks; @@ -2605,7 +2631,7 @@ static int get_ssr_segment(struct f2fs_sb_info *sbi, int type) bool reversed = false; /* f2fs_need_SSR() already forces to do this */ - if (v_ops->get_victim(sbi, &segno, BG_GC, type, SSR)) { + if (!v_ops->get_victim(sbi, &segno, BG_GC, type, SSR)) { curseg->next_segno = segno; return 1; } @@ -2632,7 +2658,7 @@ static int get_ssr_segment(struct f2fs_sb_info *sbi, int type) for (; cnt-- > 0; reversed ? i-- : i++) { if (i == type) continue; - if (v_ops->get_victim(sbi, &segno, BG_GC, i, SSR)) { + if (!v_ops->get_victim(sbi, &segno, BG_GC, i, SSR)) { curseg->next_segno = segno; return 1; } @@ -2674,7 +2700,7 @@ static void allocate_segment_by_default(struct f2fs_sb_info *sbi, stat_inc_seg_type(sbi, curseg); } -void allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type, +void f2fs_allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type, unsigned int start, unsigned int end) { struct curseg_info *curseg = CURSEG_I(sbi, type); @@ -2707,28 +2733,35 @@ unlock: up_read(&SM_I(sbi)->curseg_lock); } -void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi, int type) +static void __allocate_new_segment(struct f2fs_sb_info *sbi, int type) { - struct curseg_info *curseg; + struct curseg_info *curseg = CURSEG_I(sbi, type); unsigned int old_segno; - int i; - down_write(&SIT_I(sbi)->sentry_lock); + if (!curseg->next_blkoff && + !get_valid_blocks(sbi, curseg->segno, false) && + !get_ckpt_valid_blocks(sbi, curseg->segno)) + return; - for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) { - if (type != NO_CHECK_TYPE && i != type) - continue; + old_segno = curseg->segno; + SIT_I(sbi)->s_ops->allocate_segment(sbi, type, true); + locate_dirty_segment(sbi, old_segno); +} - curseg = CURSEG_I(sbi, i); - if (type == NO_CHECK_TYPE || curseg->next_blkoff || - get_valid_blocks(sbi, curseg->segno, false) || - get_ckpt_valid_blocks(sbi, curseg->segno)) { - old_segno = curseg->segno; - SIT_I(sbi)->s_ops->allocate_segment(sbi, i, true); - locate_dirty_segment(sbi, old_segno); - } - } +void f2fs_allocate_new_segment(struct f2fs_sb_info *sbi, int type) +{ + down_write(&SIT_I(sbi)->sentry_lock); + __allocate_new_segment(sbi, type); + up_write(&SIT_I(sbi)->sentry_lock); +} +void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi) +{ + int i; + + down_write(&SIT_I(sbi)->sentry_lock); + for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) + __allocate_new_segment(sbi, i); up_write(&SIT_I(sbi)->sentry_lock); } @@ -3089,7 +3122,7 @@ static int __get_segment_type(struct f2fs_io_info *fio) void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, block_t old_blkaddr, block_t *new_blkaddr, struct f2fs_summary *sum, int type, - struct f2fs_io_info *fio, bool add_list) + struct f2fs_io_info *fio) { struct sit_info *sit_i = SIT_I(sbi); struct curseg_info *curseg = CURSEG_I(sbi, type); @@ -3107,14 +3140,6 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, type = CURSEG_COLD_DATA; } - /* - * We need to wait for node_write to avoid block allocation during - * checkpoint. This can only happen to quota writes which can cause - * the below discard race condition. - */ - if (IS_DATASEG(type)) - down_write(&sbi->node_write); - down_read(&SM_I(sbi)->curseg_lock); mutex_lock(&curseg->curseg_mutex); @@ -3165,7 +3190,7 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, if (F2FS_IO_ALIGNED(sbi)) fio->retry = false; - if (add_list) { + if (fio) { struct f2fs_bio_info *io; INIT_LIST_HEAD(&fio->list); @@ -3180,9 +3205,6 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, up_read(&SM_I(sbi)->curseg_lock); - if (IS_DATASEG(type)) - up_write(&sbi->node_write); - if (put_pin_sem) up_read(&sbi->pin_sem); } @@ -3217,7 +3239,7 @@ static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio) down_read(&fio->sbi->io_order_lock); reallocate: f2fs_allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr, - &fio->new_blkaddr, sum, type, fio, true); + &fio->new_blkaddr, sum, type, fio); if (GET_SEGNO(fio->sbi, fio->old_blkaddr) != NULL_SEGNO) invalidate_mapping_pages(META_MAPPING(fio->sbi), fio->old_blkaddr, fio->old_blkaddr); @@ -4293,8 +4315,9 @@ static void init_dirty_segmap(struct f2fs_sb_info *sbi) { struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); struct free_segmap_info *free_i = FREE_I(sbi); - unsigned int segno = 0, offset = 0; + unsigned int segno = 0, offset = 0, secno; unsigned short valid_blocks; + unsigned short blks_per_sec = BLKS_PER_SEC(sbi); while (1) { /* find dirty segment based on free segmap */ @@ -4313,6 +4336,22 @@ static void init_dirty_segmap(struct f2fs_sb_info *sbi) __locate_dirty_segment(sbi, segno, DIRTY); mutex_unlock(&dirty_i->seglist_lock); } + + if (!__is_large_section(sbi)) + return; + + mutex_lock(&dirty_i->seglist_lock); + for (segno = 0; segno < MAIN_SECS(sbi); segno += blks_per_sec) { + valid_blocks = get_valid_blocks(sbi, segno, true); + secno = GET_SEC_FROM_SEG(sbi, segno); + + if (!valid_blocks || valid_blocks == blks_per_sec) + continue; + if (IS_CURSEC(sbi, secno)) + continue; + set_bit(secno, dirty_i->dirty_secmap); + } + mutex_unlock(&dirty_i->seglist_lock); } static int init_victim_secmap(struct f2fs_sb_info *sbi) @@ -4349,6 +4388,14 @@ static int build_dirty_segmap(struct f2fs_sb_info *sbi) return -ENOMEM; } + if (__is_large_section(sbi)) { + bitmap_size = f2fs_bitmap_size(MAIN_SECS(sbi)); + dirty_i->dirty_secmap = f2fs_kvzalloc(sbi, + bitmap_size, GFP_KERNEL); + if (!dirty_i->dirty_secmap) + return -ENOMEM; + } + init_dirty_segmap(sbi); return init_victim_secmap(sbi); } @@ -4775,6 +4822,12 @@ static void destroy_dirty_segmap(struct f2fs_sb_info *sbi) for (i = 0; i < NR_DIRTY_TYPE; i++) discard_dirty_segmap(sbi, i); + if (__is_large_section(sbi)) { + mutex_lock(&dirty_i->seglist_lock); + kvfree(dirty_i->dirty_secmap); + mutex_unlock(&dirty_i->seglist_lock); + } + destroy_victim_secmap(sbi); SM_I(sbi)->dirty_info = NULL; kvfree(dirty_i); diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index cba16cca5189..752b177073b2 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -166,8 +166,11 @@ enum { struct victim_sel_policy { int alloc_mode; /* LFS or SSR */ int gc_mode; /* GC_CB or GC_GREEDY */ - unsigned long *dirty_segmap; /* dirty segment bitmap */ - unsigned int max_search; /* maximum # of segments to search */ + unsigned long *dirty_bitmap; /* dirty segment/section bitmap */ + unsigned int max_search; /* + * maximum # of segments/sections + * to search + */ unsigned int offset; /* last scanned bitmap offset */ unsigned int ofs_unit; /* bitmap search unit */ unsigned int min_cost; /* minimum cost */ @@ -184,7 +187,7 @@ struct seg_entry { unsigned char *cur_valid_map_mir; /* mirror of current valid bitmap */ #endif /* - * # of valid blocks and the validity bitmap stored in the the last + * # of valid blocks and the validity bitmap stored in the last * checkpoint pack. This information is used by the SSR mode. */ unsigned char *ckpt_valid_map; /* validity bitmap of blocks last cp */ @@ -266,6 +269,7 @@ enum dirty_type { struct dirty_seglist_info { const struct victim_selection *v_ops; /* victim selction operation */ unsigned long *dirty_segmap[NR_DIRTY_TYPE]; + unsigned long *dirty_secmap; struct mutex seglist_lock; /* lock for segment bitmaps */ int nr_dirty[NR_DIRTY_TYPE]; /* # of dirty segments */ unsigned long *victim_secmap; /* background GC victims */ diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 23c49c313fb6..dfa072fa8081 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -350,7 +350,7 @@ static int f2fs_set_qf_name(struct super_block *sb, int qtype, set_opt(sbi, QUOTA); return 0; errout: - kvfree(qname); + kfree(qname); return ret; } @@ -362,7 +362,7 @@ static int f2fs_clear_qf_name(struct super_block *sb, int qtype) f2fs_err(sbi, "Cannot change journaled quota options when quota turned on"); return -EINVAL; } - kvfree(F2FS_OPTION(sbi).s_qf_names[qtype]); + kfree(F2FS_OPTION(sbi).s_qf_names[qtype]); F2FS_OPTION(sbi).s_qf_names[qtype] = NULL; return 0; } @@ -462,9 +462,12 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount) { struct f2fs_sb_info *sbi = F2FS_SB(sb); substring_t args[MAX_OPT_ARGS]; +#ifdef CONFIG_F2FS_FS_COMPRESSION unsigned char (*ext)[F2FS_EXTENSION_LEN]; + int ext_cnt; +#endif char *p, *name; - int arg = 0, ext_cnt; + int arg = 0; kuid_t uid; kgid_t gid; int ret; @@ -496,10 +499,10 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount) } else if (!strcmp(name, "sync")) { F2FS_OPTION(sbi).bggc_mode = BGGC_MODE_SYNC; } else { - kvfree(name); + kfree(name); return -EINVAL; } - kvfree(name); + kfree(name); break; case Opt_disable_roll_forward: set_opt(sbi, DISABLE_ROLL_FORWARD); @@ -656,17 +659,17 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount) if (!strcmp(name, "adaptive")) { if (f2fs_sb_has_blkzoned(sbi)) { f2fs_warn(sbi, "adaptive mode is not allowed with zoned block device feature"); - kvfree(name); + kfree(name); return -EINVAL; } F2FS_OPTION(sbi).fs_mode = FS_MODE_ADAPTIVE; } else if (!strcmp(name, "lfs")) { F2FS_OPTION(sbi).fs_mode = FS_MODE_LFS; } else { - kvfree(name); + kfree(name); return -EINVAL; } - kvfree(name); + kfree(name); break; case Opt_io_size_bits: if (args->from && match_int(args, &arg)) @@ -792,10 +795,10 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount) } else if (!strcmp(name, "fs-based")) { F2FS_OPTION(sbi).whint_mode = WHINT_MODE_FS; } else { - kvfree(name); + kfree(name); return -EINVAL; } - kvfree(name); + kfree(name); break; case Opt_alloc: name = match_strdup(&args[0]); @@ -807,10 +810,10 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount) } else if (!strcmp(name, "reuse")) { F2FS_OPTION(sbi).alloc_mode = ALLOC_MODE_REUSE; } else { - kvfree(name); + kfree(name); return -EINVAL; } - kvfree(name); + kfree(name); break; case Opt_fsync: name = match_strdup(&args[0]); @@ -824,10 +827,10 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount) F2FS_OPTION(sbi).fsync_mode = FSYNC_MODE_NOBARRIER; } else { - kvfree(name); + kfree(name); return -EINVAL; } - kvfree(name); + kfree(name); break; case Opt_test_dummy_encryption: ret = f2fs_set_test_dummy_encryption(sb, p, &args[0], @@ -862,6 +865,7 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount) case Opt_checkpoint_enable: clear_opt(sbi, DISABLE_CHECKPOINT); break; +#ifdef CONFIG_F2FS_FS_COMPRESSION case Opt_compress_algorithm: if (!f2fs_sb_has_compression(sbi)) { f2fs_err(sbi, "Compression feature if off"); @@ -927,6 +931,13 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount) F2FS_OPTION(sbi).compress_ext_cnt++; kfree(name); break; +#else + case Opt_compress_algorithm: + case Opt_compress_log_size: + case Opt_compress_extension: + f2fs_info(sbi, "compression options not supported"); + break; +#endif default: f2fs_err(sbi, "Unrecognized mount option \"%s\" or missing value", p); @@ -1024,6 +1035,8 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb) /* Will be used by directory only */ fi->i_dir_level = F2FS_SB(sb)->dir_level; + fi->ra_offset = -1; + return &fi->vfs_inode; } @@ -1182,6 +1195,9 @@ static void f2fs_put_super(struct super_block *sb) int i; bool dropped; + /* unregister procfs/sysfs entries in advance to avoid race case */ + f2fs_unregister_sysfs(sbi); + f2fs_quota_off_umount(sb); /* prevent remaining shrinker jobs */ @@ -1247,19 +1263,17 @@ static void f2fs_put_super(struct super_block *sb) kvfree(sbi->ckpt); - f2fs_unregister_sysfs(sbi); - sb->s_fs_info = NULL; if (sbi->s_chksum_driver) crypto_free_shash(sbi->s_chksum_driver); - kvfree(sbi->raw_super); + kfree(sbi->raw_super); destroy_device_list(sbi); f2fs_destroy_xattr_caches(sbi); mempool_destroy(sbi->write_io_dummy); #ifdef CONFIG_QUOTA for (i = 0; i < MAXQUOTAS; i++) - kvfree(F2FS_OPTION(sbi).s_qf_names[i]); + kfree(F2FS_OPTION(sbi).s_qf_names[i]); #endif fscrypt_free_dummy_context(&F2FS_OPTION(sbi).dummy_enc_ctx); destroy_percpu_info(sbi); @@ -1268,7 +1282,7 @@ static void f2fs_put_super(struct super_block *sb) #ifdef CONFIG_UNICODE utf8_unload(sbi->s_encoding); #endif - kvfree(sbi); + kfree(sbi); } int f2fs_sync_fs(struct super_block *sb, int sync) @@ -1617,7 +1631,9 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) else if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_NOBARRIER) seq_printf(seq, ",fsync_mode=%s", "nobarrier"); +#ifdef CONFIG_F2FS_FS_COMPRESSION f2fs_show_compress_options(seq, sbi->sb); +#endif return 0; } @@ -1768,7 +1784,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) GFP_KERNEL); if (!org_mount_opt.s_qf_names[i]) { for (j = 0; j < i; j++) - kvfree(org_mount_opt.s_qf_names[j]); + kfree(org_mount_opt.s_qf_names[j]); return -ENOMEM; } } else { @@ -1893,7 +1909,7 @@ skip: #ifdef CONFIG_QUOTA /* Release old quota file names */ for (i = 0; i < MAXQUOTAS; i++) - kvfree(org_mount_opt.s_qf_names[i]); + kfree(org_mount_opt.s_qf_names[i]); #endif /* Update the POSIXACL Flag */ sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | @@ -1914,7 +1930,7 @@ restore_opts: #ifdef CONFIG_QUOTA F2FS_OPTION(sbi).s_jquota_fmt = org_mount_opt.s_jquota_fmt; for (i = 0; i < MAXQUOTAS; i++) { - kvfree(F2FS_OPTION(sbi).s_qf_names[i]); + kfree(F2FS_OPTION(sbi).s_qf_names[i]); F2FS_OPTION(sbi).s_qf_names[i] = org_mount_opt.s_qf_names[i]; } #endif @@ -3172,7 +3188,7 @@ static int read_raw_super_block(struct f2fs_sb_info *sbi, /* No valid superblock */ if (!*raw_super) - kvfree(super); + kfree(super); else err = 0; @@ -3846,16 +3862,16 @@ free_bio_info: free_options: #ifdef CONFIG_QUOTA for (i = 0; i < MAXQUOTAS; i++) - kvfree(F2FS_OPTION(sbi).s_qf_names[i]); + kfree(F2FS_OPTION(sbi).s_qf_names[i]); #endif fscrypt_free_dummy_context(&F2FS_OPTION(sbi).dummy_enc_ctx); kvfree(options); free_sb_buf: - kvfree(raw_super); + kfree(raw_super); free_sbi: if (sbi->s_chksum_driver) crypto_free_shash(sbi->s_chksum_driver); - kvfree(sbi); + kfree(sbi); /* give only one another chance */ if (retry_cnt > 0 && skip_recovery) { diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index e877c59b9fdb..88ed9969cc86 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -27,7 +27,7 @@ enum { NM_INFO, /* struct f2fs_nm_info */ F2FS_SBI, /* struct f2fs_sb_info */ #ifdef CONFIG_F2FS_STAT_FS - STAT_INFO, /* struct f2fs_stat_info */ + STAT_INFO, /* struct f2fs_stat_info */ #endif #ifdef CONFIG_F2FS_FAULT_INJECTION FAULT_INFO_RATE, /* struct f2fs_fault_info */ @@ -223,6 +223,13 @@ static ssize_t avg_vblocks_show(struct f2fs_attr *a, } #endif +static ssize_t main_blkaddr_show(struct f2fs_attr *a, + struct f2fs_sb_info *sbi, char *buf) +{ + return snprintf(buf, PAGE_SIZE, "%llu\n", + (unsigned long long)MAIN_BLKADDR(sbi)); +} + static ssize_t f2fs_sbi_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) { @@ -350,16 +357,20 @@ out: return -EINVAL; if (!strcmp(a->attr.name, "gc_urgent")) { - if (t >= 1) { - sbi->gc_mode = GC_URGENT; + if (t == 0) { + sbi->gc_mode = GC_NORMAL; + } else if (t == 1) { + sbi->gc_mode = GC_URGENT_HIGH; if (sbi->gc_thread) { sbi->gc_thread->gc_wake = 1; wake_up_interruptible_all( &sbi->gc_thread->gc_wait_queue_head); wake_up_discard_thread(sbi, true); } + } else if (t == 2) { + sbi->gc_mode = GC_URGENT_LOW; } else { - sbi->gc_mode = GC_NORMAL; + return -EINVAL; } return count; } @@ -522,7 +533,6 @@ F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_no_gc_sleep_time, no_gc_sleep_time); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_idle, gc_mode); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_urgent, gc_mode); F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, reclaim_segments, rec_prefree_segments); -F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, main_blkaddr, main_blkaddr); F2FS_RW_ATTR(DCC_INFO, discard_cmd_control, max_small_discards, max_discards); F2FS_RW_ATTR(DCC_INFO, discard_cmd_control, discard_granularity, discard_granularity); F2FS_RW_ATTR(RESERVED_BLOCKS, f2fs_sb_info, reserved_blocks, reserved_blocks); @@ -565,6 +575,7 @@ F2FS_GENERAL_RO_ATTR(current_reserved_blocks); F2FS_GENERAL_RO_ATTR(unusable); F2FS_GENERAL_RO_ATTR(encoding); F2FS_GENERAL_RO_ATTR(mounted_time_sec); +F2FS_GENERAL_RO_ATTR(main_blkaddr); #ifdef CONFIG_F2FS_STAT_FS F2FS_STAT_ATTR(STAT_INFO, f2fs_stat_info, cp_foreground_calls, cp_count); F2FS_STAT_ATTR(STAT_INFO, f2fs_stat_info, cp_background_calls, bg_cp_count); @@ -706,7 +717,7 @@ static struct kobj_type f2fs_ktype = { }; static struct kset f2fs_kset = { - .kobj = {.ktype = &f2fs_ktype}, + .kobj = {.ktype = &f2fs_ktype}, }; static struct kobj_type f2fs_feat_ktype = { diff --git a/fs/f2fs/verity.c b/fs/f2fs/verity.c index 865c9fb774fb..9eb0dba851e8 100644 --- a/fs/f2fs/verity.c +++ b/fs/f2fs/verity.c @@ -29,6 +29,8 @@ #include "f2fs.h" #include "xattr.h" +#define F2FS_VERIFY_VER (1) + static inline loff_t f2fs_verity_metadata_pos(const struct inode *inode) { return round_up(inode->i_size, 65536); @@ -152,7 +154,7 @@ static int f2fs_end_enable_verity(struct file *filp, const void *desc, struct inode *inode = file_inode(filp); u64 desc_pos = f2fs_verity_metadata_pos(inode) + merkle_tree_size; struct fsverity_descriptor_location dloc = { - .version = cpu_to_le32(1), + .version = cpu_to_le32(F2FS_VERIFY_VER), .size = cpu_to_le32(desc_size), .pos = cpu_to_le64(desc_pos), }; @@ -199,7 +201,7 @@ static int f2fs_get_verity_descriptor(struct inode *inode, void *buf, F2FS_XATTR_NAME_VERITY, &dloc, sizeof(dloc), NULL); if (res < 0 && res != -ERANGE) return res; - if (res != sizeof(dloc) || dloc.version != cpu_to_le32(1)) { + if (res != sizeof(dloc) || dloc.version != cpu_to_le32(F2FS_VERIFY_VER)) { f2fs_warn(F2FS_I_SB(inode), "unknown verity xattr format"); return -EINVAL; } diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index 4f6582ef7ee3..1b0736ce0918 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -175,8 +175,8 @@ const struct xattr_handler f2fs_xattr_trusted_handler = { const struct xattr_handler f2fs_xattr_advise_handler = { .name = F2FS_SYSTEM_ADVISE_NAME, .flags = F2FS_XATTR_INDEX_ADVISE, - .get = f2fs_xattr_advise_get, - .set = f2fs_xattr_advise_set, + .get = f2fs_xattr_advise_get, + .set = f2fs_xattr_advise_set, }; const struct xattr_handler f2fs_xattr_security_handler = { diff --git a/fs/fat/Kconfig b/fs/fat/Kconfig index ca31993dcb47..66532a71e8fd 100644 --- a/fs/fat/Kconfig +++ b/fs/fat/Kconfig @@ -41,7 +41,7 @@ config MSDOS_FS they are compressed; to access compressed MSDOS partitions under Linux, you can either use the DOS emulator DOSEMU, described in the DOSEMU-HOWTO, available from - <http://www.tldp.org/docs.html#howto>, or try dmsdosfs in + <https://www.tldp.org/docs.html#howto>, or try dmsdosfs in <ftp://ibiblio.org/pub/Linux/system/filesystems/dosfs/>. If you intend to use dosemu with a non-compressed MSDOS partition, say Y here) and MSDOS floppies. This means that file access becomes diff --git a/fs/fat/fatent.c b/fs/fat/fatent.c index bbfe18c07417..f7e3304b7802 100644 --- a/fs/fat/fatent.c +++ b/fs/fat/fatent.c @@ -657,6 +657,9 @@ static void fat_ra_init(struct super_block *sb, struct fatent_ra *ra, unsigned long ra_pages = sb->s_bdi->ra_pages; unsigned int reada_blocks; + if (fatent->entry >= ent_limit) + return; + if (ra_pages > sb->s_bdi->io_pages) ra_pages = rounddown(ra_pages, sb->s_bdi->io_pages); reada_blocks = ra_pages << (PAGE_SHIFT - sb->s_blocksize_bits + 1); diff --git a/fs/fat/file.c b/fs/fat/file.c index 42134c58c87e..f9ee27cf4d7c 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -25,9 +25,9 @@ static int fat_ioctl_get_attributes(struct inode *inode, u32 __user *user_attr) { u32 attr; - inode_lock(inode); + inode_lock_shared(inode); attr = fat_make_attrs(inode); - inode_unlock(inode); + inode_unlock_shared(inode); return put_user(attr, user_attr); } diff --git a/fs/fs_struct.c b/fs/fs_struct.c index ca639ed967b7..04b3f5b9c629 100644 --- a/fs/fs_struct.c +++ b/fs/fs_struct.c @@ -117,7 +117,7 @@ struct fs_struct *copy_fs_struct(struct fs_struct *old) fs->users = 1; fs->in_exec = 0; spin_lock_init(&fs->lock); - seqcount_init(&fs->seq); + seqcount_spinlock_init(&fs->seq, &fs->lock); fs->umask = old->umask; spin_lock(&old->lock); @@ -163,6 +163,6 @@ EXPORT_SYMBOL(current_umask); struct fs_struct init_fs = { .users = 1, .lock = __SPIN_LOCK_UNLOCKED(init_fs.lock), - .seq = SEQCNT_ZERO(init_fs.seq), + .seq = SEQCNT_SPINLOCK_ZERO(init_fs.seq, &init_fs.lock), .umask = 0022, }; diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c index 4c4ef5d69298..104f35de5270 100644 --- a/fs/fuse/virtio_fs.c +++ b/fs/fuse/virtio_fs.c @@ -606,8 +606,8 @@ static int virtio_fs_setup_vqs(struct virtio_device *vdev, unsigned int i; int ret = 0; - virtio_cread(vdev, struct virtio_fs_config, num_request_queues, - &fs->num_request_queues); + virtio_cread_le(vdev, struct virtio_fs_config, num_request_queues, + &fs->num_request_queues); if (fs->num_request_queues == 0) return -EINVAL; diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 8dfe09f52cbc..770f3a720db9 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -1351,9 +1351,15 @@ int gfs2_extent_map(struct inode *inode, u64 lblock, int *new, u64 *dblock, unsi return ret; } +/* + * NOTE: Never call gfs2_block_zero_range with an open transaction because it + * uses iomap write to perform its actions, which begin their own transactions + * (iomap_begin, page_prepare, etc.) + */ static int gfs2_block_zero_range(struct inode *inode, loff_t from, unsigned int length) { + BUG_ON(current->journal_info); return iomap_zero_range(inode, from, length, NULL, &gfs2_iomap_ops); } @@ -1414,6 +1420,16 @@ static int trunc_start(struct inode *inode, u64 newsize) u64 oldsize = inode->i_size; int error; + if (!gfs2_is_stuffed(ip)) { + unsigned int blocksize = i_blocksize(inode); + unsigned int offs = newsize & (blocksize - 1); + if (offs) { + error = gfs2_block_zero_range(inode, newsize, + blocksize - offs); + if (error) + return error; + } + } if (journaled) error = gfs2_trans_begin(sdp, RES_DINODE + RES_JDATA, GFS2_JTRUNC_REVOKES); else @@ -1427,19 +1443,10 @@ static int trunc_start(struct inode *inode, u64 newsize) gfs2_trans_add_meta(ip->i_gl, dibh); - if (gfs2_is_stuffed(ip)) { + if (gfs2_is_stuffed(ip)) gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode) + newsize); - } else { - unsigned int blocksize = i_blocksize(inode); - unsigned int offs = newsize & (blocksize - 1); - if (offs) { - error = gfs2_block_zero_range(inode, newsize, - blocksize - offs); - if (error) - goto out; - } + else ip->i_diskflags |= GFS2_DIF_TRUNC_IN_PROG; - } i_size_write(inode, newsize); ip->i_inode.i_mtime = ip->i_inode.i_ctime = current_time(&ip->i_inode); @@ -2448,25 +2455,7 @@ int __gfs2_punch_hole(struct file *file, loff_t offset, loff_t length) loff_t start, end; int error; - start = round_down(offset, blocksize); - end = round_up(offset + length, blocksize) - 1; - error = filemap_write_and_wait_range(inode->i_mapping, start, end); - if (error) - return error; - - if (gfs2_is_jdata(ip)) - error = gfs2_trans_begin(sdp, RES_DINODE + 2 * RES_JDATA, - GFS2_JTRUNC_REVOKES); - else - error = gfs2_trans_begin(sdp, RES_DINODE, 0); - if (error) - return error; - - if (gfs2_is_stuffed(ip)) { - error = stuffed_zero_range(inode, offset, length); - if (error) - goto out; - } else { + if (!gfs2_is_stuffed(ip)) { unsigned int start_off, end_len; start_off = offset & (blocksize - 1); @@ -2489,6 +2478,26 @@ int __gfs2_punch_hole(struct file *file, loff_t offset, loff_t length) } } + start = round_down(offset, blocksize); + end = round_up(offset + length, blocksize) - 1; + error = filemap_write_and_wait_range(inode->i_mapping, start, end); + if (error) + return error; + + if (gfs2_is_jdata(ip)) + error = gfs2_trans_begin(sdp, RES_DINODE + 2 * RES_JDATA, + GFS2_JTRUNC_REVOKES); + else + error = gfs2_trans_begin(sdp, RES_DINODE, 0); + if (error) + return error; + + if (gfs2_is_stuffed(ip)) { + error = stuffed_zero_range(inode, offset, length); + if (error) + goto out; + } + if (gfs2_is_jdata(ip)) { BUG_ON(!current->journal_info); gfs2_journaled_truncate_range(inode, offset, length); diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index b085a3bea4f0..b39b339feddc 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -781,39 +781,39 @@ static int gfs2_fsync(struct file *file, loff_t start, loff_t end, return ret ? ret : ret1; } -static ssize_t gfs2_file_direct_read(struct kiocb *iocb, struct iov_iter *to) +static ssize_t gfs2_file_direct_read(struct kiocb *iocb, struct iov_iter *to, + struct gfs2_holder *gh) { struct file *file = iocb->ki_filp; struct gfs2_inode *ip = GFS2_I(file->f_mapping->host); size_t count = iov_iter_count(to); - struct gfs2_holder gh; ssize_t ret; if (!count) return 0; /* skip atime */ - gfs2_holder_init(ip->i_gl, LM_ST_DEFERRED, 0, &gh); - ret = gfs2_glock_nq(&gh); + gfs2_holder_init(ip->i_gl, LM_ST_DEFERRED, 0, gh); + ret = gfs2_glock_nq(gh); if (ret) goto out_uninit; ret = iomap_dio_rw(iocb, to, &gfs2_iomap_ops, NULL, is_sync_kiocb(iocb)); - gfs2_glock_dq(&gh); + gfs2_glock_dq(gh); out_uninit: - gfs2_holder_uninit(&gh); + gfs2_holder_uninit(gh); return ret; } -static ssize_t gfs2_file_direct_write(struct kiocb *iocb, struct iov_iter *from) +static ssize_t gfs2_file_direct_write(struct kiocb *iocb, struct iov_iter *from, + struct gfs2_holder *gh) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; struct gfs2_inode *ip = GFS2_I(inode); size_t len = iov_iter_count(from); loff_t offset = iocb->ki_pos; - struct gfs2_holder gh; ssize_t ret; /* @@ -824,8 +824,8 @@ static ssize_t gfs2_file_direct_write(struct kiocb *iocb, struct iov_iter *from) * unfortunately, have the option of only flushing a range like the * VFS does. */ - gfs2_holder_init(ip->i_gl, LM_ST_DEFERRED, 0, &gh); - ret = gfs2_glock_nq(&gh); + gfs2_holder_init(ip->i_gl, LM_ST_DEFERRED, 0, gh); + ret = gfs2_glock_nq(gh); if (ret) goto out_uninit; @@ -838,9 +838,9 @@ static ssize_t gfs2_file_direct_write(struct kiocb *iocb, struct iov_iter *from) if (ret == -ENOTBLK) ret = 0; out: - gfs2_glock_dq(&gh); + gfs2_glock_dq(gh); out_uninit: - gfs2_holder_uninit(&gh); + gfs2_holder_uninit(gh); return ret; } @@ -852,7 +852,7 @@ static ssize_t gfs2_file_read_iter(struct kiocb *iocb, struct iov_iter *to) ssize_t ret; if (iocb->ki_flags & IOCB_DIRECT) { - ret = gfs2_file_direct_read(iocb, to); + ret = gfs2_file_direct_read(iocb, to, &gh); if (likely(ret != -ENOTBLK)) return ret; iocb->ki_flags &= ~IOCB_DIRECT; @@ -901,13 +901,12 @@ static ssize_t gfs2_file_write_iter(struct kiocb *iocb, struct iov_iter *from) struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); struct gfs2_inode *ip = GFS2_I(inode); + struct gfs2_holder gh; ssize_t ret; gfs2_size_hint(file, iocb->ki_pos, iov_iter_count(from)); if (iocb->ki_flags & IOCB_APPEND) { - struct gfs2_holder gh; - ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, 0, &gh); if (ret) return ret; @@ -931,7 +930,7 @@ static ssize_t gfs2_file_write_iter(struct kiocb *iocb, struct iov_iter *from) struct address_space *mapping = file->f_mapping; ssize_t buffered, ret2; - ret = gfs2_file_direct_write(iocb, from); + ret = gfs2_file_direct_write(iocb, from, &gh); if (ret < 0 || !iov_iter_count(from)) goto out_unlock; diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 8545024a1401..f13b136654ca 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -790,9 +790,11 @@ static void gfs2_glock_poke(struct gfs2_glock *gl) struct gfs2_holder gh; int error; - error = gfs2_glock_nq_init(gl, LM_ST_SHARED, flags, &gh); + gfs2_holder_init(gl, LM_ST_SHARED, flags, &gh); + error = gfs2_glock_nq(&gh); if (!error) gfs2_glock_dq(&gh); + gfs2_holder_uninit(&gh); } static bool gfs2_try_evict(struct gfs2_glock *gl) @@ -2106,6 +2108,12 @@ static const char *gflags2str(char *buf, const struct gfs2_glock *gl) *p++ = 'o'; if (test_bit(GLF_BLOCKING, gflags)) *p++ = 'b'; + if (test_bit(GLF_INODE_CREATING, gflags)) + *p++ = 'c'; + if (test_bit(GLF_PENDING_DELETE, gflags)) + *p++ = 'P'; + if (test_bit(GLF_FREEING, gflags)) + *p++ = 'x'; *p = 0; return buf; } diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index a76e55bc28eb..a58333e3980d 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -1092,7 +1092,7 @@ static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr) * or the total number of used blocks (pinned blocks plus AIL blocks) * is greater than thresh2. * - * At mount time thresh1 is 1/3rd of journal size, thresh2 is 2/3rd of + * At mount time thresh1 is 2/5ths of journal size, thresh2 is 4/5ths of * journal size. * * Returns: errno diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 47d0ae158b69..9f4d9e7be839 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -566,6 +566,7 @@ static void gfs2_dirty_inode(struct inode *inode, int flags) ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh); if (ret) { fs_err(sdp, "dirty_inode: glock %d\n", ret); + gfs2_dump_glock(NULL, ip->i_gl, true); return; } need_unlock = 1; diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c index a3dfa3aa87ad..e1c7eb6eb00a 100644 --- a/fs/gfs2/trans.c +++ b/fs/gfs2/trans.c @@ -25,13 +25,28 @@ #include "util.h" #include "trace_gfs2.h" +static void gfs2_print_trans(struct gfs2_sbd *sdp, const struct gfs2_trans *tr) +{ + fs_warn(sdp, "Transaction created at: %pSR\n", (void *)tr->tr_ip); + fs_warn(sdp, "blocks=%u revokes=%u reserved=%u touched=%u\n", + tr->tr_blocks, tr->tr_revokes, tr->tr_reserved, + test_bit(TR_TOUCHED, &tr->tr_flags)); + fs_warn(sdp, "Buf %u/%u Databuf %u/%u Revoke %u/%u\n", + tr->tr_num_buf_new, tr->tr_num_buf_rm, + tr->tr_num_databuf_new, tr->tr_num_databuf_rm, + tr->tr_num_revoke, tr->tr_num_revoke_rm); +} + int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks, unsigned int revokes) { struct gfs2_trans *tr; int error; - BUG_ON(current->journal_info); + if (current->journal_info) { + gfs2_print_trans(sdp, current->journal_info); + BUG(); + } BUG_ON(blocks == 0 && revokes == 0); if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) @@ -72,18 +87,6 @@ fail: return error; } -static void gfs2_print_trans(struct gfs2_sbd *sdp, const struct gfs2_trans *tr) -{ - fs_warn(sdp, "Transaction created at: %pSR\n", (void *)tr->tr_ip); - fs_warn(sdp, "blocks=%u revokes=%u reserved=%u touched=%u\n", - tr->tr_blocks, tr->tr_revokes, tr->tr_reserved, - test_bit(TR_TOUCHED, &tr->tr_flags)); - fs_warn(sdp, "Buf %u/%u Databuf %u/%u Revoke %u/%u\n", - tr->tr_num_buf_new, tr->tr_num_buf_rm, - tr->tr_num_databuf_new, tr->tr_num_databuf_rm, - tr->tr_num_revoke, tr->tr_num_revoke_rm); -} - void gfs2_trans_end(struct gfs2_sbd *sdp) { struct gfs2_trans *tr = current->journal_info; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 523954d00dff..b5c109703daa 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -1364,6 +1364,12 @@ hugetlbfs_fill_super(struct super_block *sb, struct fs_context *fc) sb->s_magic = HUGETLBFS_MAGIC; sb->s_op = &hugetlbfs_ops; sb->s_time_gran = 1; + + /* + * Due to the special and limited functionality of hugetlbfs, it does + * not work well as a stacking filesystem. + */ + sb->s_stack_depth = FILESYSTEM_MAX_STACK_DEPTH; sb->s_root = d_make_root(hugetlbfs_get_root(sb, ctx)); if (!sb->s_root) goto out_free; diff --git a/fs/io_uring.c b/fs/io_uring.c index 2a3af95be4ca..dc506b75659c 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -508,9 +508,9 @@ struct io_async_msghdr { struct io_async_rw { struct iovec fast_iov[UIO_FASTIOV]; - struct iovec *iov; - ssize_t nr_segs; - ssize_t size; + const struct iovec *free_iovec; + struct iov_iter iter; + size_t bytes_done; struct wait_page_queue wpq; }; @@ -898,6 +898,7 @@ static void io_put_req(struct io_kiocb *req); static void io_double_put_req(struct io_kiocb *req); static void __io_double_put_req(struct io_kiocb *req); static struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req); +static void __io_queue_linked_timeout(struct io_kiocb *req); static void io_queue_linked_timeout(struct io_kiocb *req); static int __io_sqe_files_update(struct io_ring_ctx *ctx, struct io_uring_files_update *ip, @@ -914,9 +915,9 @@ static void io_file_put_work(struct work_struct *work); static ssize_t io_import_iovec(int rw, struct io_kiocb *req, struct iovec **iovec, struct iov_iter *iter, bool needs_lock); -static int io_setup_async_rw(struct io_kiocb *req, ssize_t io_size, - struct iovec *iovec, struct iovec *fast_iov, - struct iov_iter *iter); +static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec, + const struct iovec *fast_iov, + struct iov_iter *iter, bool force); static struct kmem_cache *req_cachep; @@ -1107,10 +1108,16 @@ static void __io_commit_cqring(struct io_ring_ctx *ctx) } } -static void io_req_clean_work(struct io_kiocb *req) +/* + * Returns true if we need to defer file table putting. This can only happen + * from the error path with REQ_F_COMP_LOCKED set. + */ +static bool io_req_clean_work(struct io_kiocb *req) { if (!(req->flags & REQ_F_WORK_INITIALIZED)) - return; + return false; + + req->flags &= ~REQ_F_WORK_INITIALIZED; if (req->work.mm) { mmdrop(req->work.mm); @@ -1123,6 +1130,9 @@ static void io_req_clean_work(struct io_kiocb *req) if (req->work.fs) { struct fs_struct *fs = req->work.fs; + if (req->flags & REQ_F_COMP_LOCKED) + return true; + spin_lock(&req->work.fs->lock); if (--fs->users) fs = NULL; @@ -1131,7 +1141,8 @@ static void io_req_clean_work(struct io_kiocb *req) free_fs_struct(fs); req->work.fs = NULL; } - req->flags &= ~REQ_F_WORK_INITIALIZED; + + return false; } static void io_prep_async_work(struct io_kiocb *req) @@ -1179,7 +1190,7 @@ static void io_prep_async_link(struct io_kiocb *req) io_prep_async_work(cur); } -static void __io_queue_async_work(struct io_kiocb *req) +static struct io_kiocb *__io_queue_async_work(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; struct io_kiocb *link = io_prep_linked_timeout(req); @@ -1187,16 +1198,19 @@ static void __io_queue_async_work(struct io_kiocb *req) trace_io_uring_queue_async_work(ctx, io_wq_is_hashed(&req->work), req, &req->work, req->flags); io_wq_enqueue(ctx->io_wq, &req->work); - - if (link) - io_queue_linked_timeout(link); + return link; } static void io_queue_async_work(struct io_kiocb *req) { + struct io_kiocb *link; + /* init ->work of the whole link before punting */ io_prep_async_link(req); - __io_queue_async_work(req); + link = __io_queue_async_work(req); + + if (link) + io_queue_linked_timeout(link); } static void io_kill_timeout(struct io_kiocb *req) @@ -1229,12 +1243,19 @@ static void __io_queue_deferred(struct io_ring_ctx *ctx) do { struct io_defer_entry *de = list_first_entry(&ctx->defer_list, struct io_defer_entry, list); + struct io_kiocb *link; if (req_need_defer(de->req, de->seq)) break; list_del_init(&de->list); /* punt-init is done before queueing for defer */ - __io_queue_async_work(de->req); + link = __io_queue_async_work(de->req); + if (link) { + __io_queue_linked_timeout(link); + /* drop submission reference */ + link->flags |= REQ_F_COMP_LOCKED; + io_put_req(link); + } kfree(de); } while (!list_empty(&ctx->defer_list)); } @@ -1533,7 +1554,7 @@ static inline void io_put_file(struct io_kiocb *req, struct file *file, fput(file); } -static void io_dismantle_req(struct io_kiocb *req) +static bool io_dismantle_req(struct io_kiocb *req) { io_clean_op(req); @@ -1541,7 +1562,6 @@ static void io_dismantle_req(struct io_kiocb *req) kfree(req->io); if (req->file) io_put_file(req, req->file, (req->flags & REQ_F_FIXED_FILE)); - io_req_clean_work(req); if (req->flags & REQ_F_INFLIGHT) { struct io_ring_ctx *ctx = req->ctx; @@ -1553,15 +1573,15 @@ static void io_dismantle_req(struct io_kiocb *req) wake_up(&ctx->inflight_wait); spin_unlock_irqrestore(&ctx->inflight_lock, flags); } + + return io_req_clean_work(req); } -static void __io_free_req(struct io_kiocb *req) +static void __io_free_req_finish(struct io_kiocb *req) { - struct io_ring_ctx *ctx; + struct io_ring_ctx *ctx = req->ctx; - io_dismantle_req(req); __io_put_req_task(req); - ctx = req->ctx; if (likely(!io_is_fallback_req(req))) kmem_cache_free(req_cachep, req); else @@ -1569,6 +1589,39 @@ static void __io_free_req(struct io_kiocb *req) percpu_ref_put(&ctx->refs); } +static void io_req_task_file_table_put(struct callback_head *cb) +{ + struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work); + struct fs_struct *fs = req->work.fs; + + spin_lock(&req->work.fs->lock); + if (--fs->users) + fs = NULL; + spin_unlock(&req->work.fs->lock); + if (fs) + free_fs_struct(fs); + req->work.fs = NULL; + __io_free_req_finish(req); +} + +static void __io_free_req(struct io_kiocb *req) +{ + if (!io_dismantle_req(req)) { + __io_free_req_finish(req); + } else { + int ret; + + init_task_work(&req->task_work, io_req_task_file_table_put); + ret = task_work_add(req->task, &req->task_work, TWA_RESUME); + if (unlikely(ret)) { + struct task_struct *tsk; + + tsk = io_wq_get_task(req->ctx->io_wq); + task_work_add(tsk, &req->task_work, 0); + } + } +} + static bool io_link_cancel_timeout(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; @@ -1598,6 +1651,7 @@ static bool __io_kill_linked_timeout(struct io_kiocb *req) return false; list_del_init(&link->link_list); + link->flags |= REQ_F_COMP_LOCKED; wake_ev = io_link_cancel_timeout(link); req->flags &= ~REQ_F_LINK_TIMEOUT; return wake_ev; @@ -1656,6 +1710,7 @@ static void __io_fail_links(struct io_kiocb *req) trace_io_uring_fail_link(req, link); io_cqring_fill_event(link, -ECANCELED); + link->flags |= REQ_F_COMP_LOCKED; __io_double_put_req(link); req->flags &= ~REQ_F_LINK_TIMEOUT; } @@ -1710,22 +1765,22 @@ static int io_req_task_work_add(struct io_kiocb *req, struct callback_head *cb) { struct task_struct *tsk = req->task; struct io_ring_ctx *ctx = req->ctx; - int ret, notify = TWA_RESUME; + int ret, notify; /* - * SQPOLL kernel thread doesn't need notification, just a wakeup. - * If we're not using an eventfd, then TWA_RESUME is always fine, - * as we won't have dependencies between request completions for - * other kernel wait conditions. + * SQPOLL kernel thread doesn't need notification, just a wakeup. For + * all other cases, use TWA_SIGNAL unconditionally to ensure we're + * processing task_work. There's no reliable way to tell if TWA_RESUME + * will do the job. */ - if (ctx->flags & IORING_SETUP_SQPOLL) - notify = 0; - else if (ctx->cq_ev_fd) + notify = 0; + if (!(ctx->flags & IORING_SETUP_SQPOLL)) notify = TWA_SIGNAL; ret = task_work_add(tsk, cb, notify); if (!ret) wake_up_process(tsk); + return ret; } @@ -1766,8 +1821,10 @@ static void __io_req_task_submit(struct io_kiocb *req) static void io_req_task_submit(struct callback_head *cb) { struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work); + struct io_ring_ctx *ctx = req->ctx; __io_req_task_submit(req); + percpu_ref_put(&ctx->refs); } static void io_req_task_queue(struct io_kiocb *req) @@ -1775,6 +1832,7 @@ static void io_req_task_queue(struct io_kiocb *req) int ret; init_task_work(&req->task_work, io_req_task_submit); + percpu_ref_get(&req->ctx->refs); ret = io_req_task_work_add(req, &req->task_work); if (unlikely(ret)) { @@ -1855,7 +1913,7 @@ static void io_req_free_batch(struct req_batch *rb, struct io_kiocb *req) req->flags &= ~REQ_F_TASK_PINNED; } - io_dismantle_req(req); + WARN_ON_ONCE(io_dismantle_req(req)); rb->reqs[rb->to_free++] = req; if (unlikely(rb->to_free == ARRAY_SIZE(rb->reqs))) __io_req_free_batch_flush(req->ctx, rb); @@ -2241,7 +2299,7 @@ static bool io_resubmit_prep(struct io_kiocb *req, int error) ret = io_import_iovec(rw, req, &iovec, &iter, false); if (ret < 0) goto end_req; - ret = io_setup_async_rw(req, ret, iovec, inline_vecs, &iter); + ret = io_setup_async_rw(req, iovec, inline_vecs, &iter, false); if (!ret) return true; kfree(iovec); @@ -2263,6 +2321,8 @@ static void io_rw_resubmit(struct callback_head *cb) refcount_inc(&req->refs); io_queue_async_work(req); } + + percpu_ref_put(&ctx->refs); } #endif @@ -2275,6 +2335,8 @@ static bool io_rw_reissue(struct io_kiocb *req, long res) return false; init_task_work(&req->task_work, io_rw_resubmit); + percpu_ref_get(&req->ctx->refs); + ret = io_req_task_work_add(req, &req->task_work); if (!ret) return true; @@ -2527,6 +2589,14 @@ static void kiocb_done(struct kiocb *kiocb, ssize_t ret, { struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb); + /* add previously done IO, if any */ + if (req->io && req->io->rw.bytes_done > 0) { + if (ret < 0) + ret = req->io->rw.bytes_done; + else + ret += req->io->rw.bytes_done; + } + if (req->flags & REQ_F_CUR_POS) req->file->f_pos = kiocb->ki_pos; if (ret >= 0 && kiocb->ki_complete == io_complete_rw) @@ -2758,6 +2828,13 @@ static ssize_t io_import_iovec(int rw, struct io_kiocb *req, ssize_t ret; u8 opcode; + if (req->io) { + struct io_async_rw *iorw = &req->io->rw; + + *iovec = NULL; + return iov_iter_count(&iorw->iter); + } + opcode = req->opcode; if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) { *iovec = NULL; @@ -2783,14 +2860,6 @@ static ssize_t io_import_iovec(int rw, struct io_kiocb *req, return ret < 0 ? ret : sqe_len; } - if (req->io) { - struct io_async_rw *iorw = &req->io->rw; - - iov_iter_init(iter, rw, iorw->iov, iorw->nr_segs, iorw->size); - *iovec = NULL; - return iorw->size; - } - if (req->flags & REQ_F_BUFFER_SELECT) { ret = io_iov_buffer_select(req, *iovec, needs_lock); if (!ret) { @@ -2868,21 +2937,30 @@ static ssize_t loop_rw_iter(int rw, struct file *file, struct kiocb *kiocb, return ret; } -static void io_req_map_rw(struct io_kiocb *req, ssize_t io_size, - struct iovec *iovec, struct iovec *fast_iov, - struct iov_iter *iter) +static void io_req_map_rw(struct io_kiocb *req, const struct iovec *iovec, + const struct iovec *fast_iov, struct iov_iter *iter) { struct io_async_rw *rw = &req->io->rw; - rw->nr_segs = iter->nr_segs; - rw->size = io_size; + memcpy(&rw->iter, iter, sizeof(*iter)); + rw->free_iovec = NULL; + rw->bytes_done = 0; + /* can only be fixed buffers, no need to do anything */ + if (iter->type == ITER_BVEC) + return; if (!iovec) { - rw->iov = rw->fast_iov; - if (rw->iov != fast_iov) - memcpy(rw->iov, fast_iov, + unsigned iov_off = 0; + + rw->iter.iov = rw->fast_iov; + if (iter->iov != fast_iov) { + iov_off = iter->iov - fast_iov; + rw->iter.iov += iov_off; + } + if (rw->fast_iov != fast_iov) + memcpy(rw->fast_iov + iov_off, fast_iov + iov_off, sizeof(struct iovec) * iter->nr_segs); } else { - rw->iov = iovec; + rw->free_iovec = iovec; req->flags |= REQ_F_NEED_CLEANUP; } } @@ -2901,17 +2979,17 @@ static int io_alloc_async_ctx(struct io_kiocb *req) return __io_alloc_async_ctx(req); } -static int io_setup_async_rw(struct io_kiocb *req, ssize_t io_size, - struct iovec *iovec, struct iovec *fast_iov, - struct iov_iter *iter) +static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec, + const struct iovec *fast_iov, + struct iov_iter *iter, bool force) { - if (!io_op_defs[req->opcode].async_ctx) + if (!force && !io_op_defs[req->opcode].async_ctx) return 0; if (!req->io) { if (__io_alloc_async_ctx(req)) return -ENOMEM; - io_req_map_rw(req, io_size, iovec, fast_iov, iter); + io_req_map_rw(req, iovec, fast_iov, iter); } return 0; } @@ -2919,18 +2997,19 @@ static int io_setup_async_rw(struct io_kiocb *req, ssize_t io_size, static inline int io_rw_prep_async(struct io_kiocb *req, int rw, bool force_nonblock) { - struct io_async_ctx *io = req->io; - struct iov_iter iter; + struct io_async_rw *iorw = &req->io->rw; ssize_t ret; - io->rw.iov = io->rw.fast_iov; + iorw->iter.iov = iorw->fast_iov; + /* reset ->io around the iovec import, we don't want to use it */ req->io = NULL; - ret = io_import_iovec(rw, req, &io->rw.iov, &iter, !force_nonblock); - req->io = io; + ret = io_import_iovec(rw, req, (struct iovec **) &iorw->iter.iov, + &iorw->iter, !force_nonblock); + req->io = container_of(iorw, struct io_async_ctx, rw); if (unlikely(ret < 0)) return ret; - io_req_map_rw(req, ret, io->rw.iov, io->rw.fast_iov, &iter); + io_req_map_rw(req, iorw->iter.iov, iorw->fast_iov, &iorw->iter); return 0; } @@ -2952,6 +3031,16 @@ static int io_read_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe, return io_rw_prep_async(req, READ, force_nonblock); } +/* + * This is our waitqueue callback handler, registered through lock_page_async() + * when we initially tried to do the IO with the iocb armed our waitqueue. + * This gets called when the page is unlocked, and we generally expect that to + * happen when the page IO is completed and the page is now uptodate. This will + * queue a task_work based retry of the operation, attempting to copy the data + * again. If the latter fails because the page was NOT uptodate, then we will + * do a thread based blocking retry of the operation. That's the unexpected + * slow path. + */ static int io_async_buf_func(struct wait_queue_entry *wait, unsigned mode, int sync, void *arg) { @@ -2965,13 +3054,11 @@ static int io_async_buf_func(struct wait_queue_entry *wait, unsigned mode, if (!wake_page_match(wpq, key)) return 0; - /* Stop waking things up if the page is locked again */ - if (test_bit(key->bit_nr, &key->page->flags)) - return -1; - list_del_init(&wait->entry); init_task_work(&req->task_work, io_req_task_submit); + percpu_ref_get(&req->ctx->refs); + /* submit ref gets dropped, acquire a new one */ refcount_inc(&req->refs); ret = io_req_task_work_add(req, &req->task_work); @@ -3008,7 +3095,18 @@ static inline int kiocb_wait_page_queue_init(struct kiocb *kiocb, return -EOPNOTSUPP; } - +/* + * This controls whether a given IO request should be armed for async page + * based retry. If we return false here, the request is handed to the async + * worker threads for retry. If we're doing buffered reads on a regular file, + * we prepare a private wait_page_queue entry and retry the operation. This + * will either succeed because the page is now uptodate and unlocked, or it + * will register a callback when the page is unlocked at IO completion. Through + * that callback, io_uring uses task_work to setup a retry of the operation. + * That retry will attempt the buffered read again. The retry will generally + * succeed, or in rare cases where it fails, we then fall back to using the + * async worker threads for a blocking retry. + */ static bool io_rw_should_retry(struct io_kiocb *req) { struct kiocb *kiocb = &req->rw.kiocb; @@ -3018,8 +3116,8 @@ static bool io_rw_should_retry(struct io_kiocb *req) if (req->flags & REQ_F_NOWAIT) return false; - /* already tried, or we're doing O_DIRECT */ - if (kiocb->ki_flags & (IOCB_DIRECT | IOCB_WAITQ)) + /* Only for buffered IO */ + if (kiocb->ki_flags & IOCB_DIRECT) return false; /* * just use poll if we can, and don't attempt if the fs doesn't @@ -3028,13 +3126,6 @@ static bool io_rw_should_retry(struct io_kiocb *req) if (file_can_poll(req->file) || !(req->file->f_mode & FMODE_BUF_RASYNC)) return false; - /* - * If request type doesn't require req->io to defer in general, - * we need to allocate it here - */ - if (!req->io && __io_alloc_async_ctx(req)) - return false; - ret = kiocb_wait_page_queue_init(kiocb, &req->io->rw.wpq, io_async_buf_func, req); if (!ret) { @@ -3049,7 +3140,10 @@ static int io_iter_do_read(struct io_kiocb *req, struct iov_iter *iter) { if (req->file->f_op->read_iter) return call_read_iter(req->file, &req->rw.kiocb, iter); - return loop_rw_iter(READ, req->file, &req->rw.kiocb, iter); + else if (req->file->f_op->read) + return loop_rw_iter(READ, req->file, &req->rw.kiocb, iter); + else + return -EINVAL; } static int io_read(struct io_kiocb *req, bool force_nonblock, @@ -3057,16 +3151,19 @@ static int io_read(struct io_kiocb *req, bool force_nonblock, { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; struct kiocb *kiocb = &req->rw.kiocb; - struct iov_iter iter; - size_t iov_count; + struct iov_iter __iter, *iter = &__iter; ssize_t io_size, ret, ret2; - unsigned long nr_segs; + size_t iov_count; + + if (req->io) + iter = &req->io->rw.iter; - ret = io_import_iovec(READ, req, &iovec, &iter, !force_nonblock); + ret = io_import_iovec(READ, req, &iovec, iter, !force_nonblock); if (ret < 0) return ret; io_size = ret; req->result = io_size; + ret = 0; /* Ensure we clear previously set non-block flag */ if (!force_nonblock) @@ -3076,40 +3173,70 @@ static int io_read(struct io_kiocb *req, bool force_nonblock, if (force_nonblock && !io_file_supports_async(req->file, READ)) goto copy_iov; - iov_count = iov_iter_count(&iter); - nr_segs = iter.nr_segs; + iov_count = iov_iter_count(iter); ret = rw_verify_area(READ, req->file, &kiocb->ki_pos, iov_count); if (unlikely(ret)) goto out_free; - ret2 = io_iter_do_read(req, &iter); + ret = io_iter_do_read(req, iter); - /* Catch -EAGAIN return for forced non-blocking submission */ - if (!force_nonblock || (ret2 != -EAGAIN && ret2 != -EIO)) { - kiocb_done(kiocb, ret2, cs); - } else { - iter.count = iov_count; - iter.nr_segs = nr_segs; -copy_iov: - ret = io_setup_async_rw(req, io_size, iovec, inline_vecs, - &iter); + if (!ret) { + goto done; + } else if (ret == -EIOCBQUEUED) { + ret = 0; + goto out_free; + } else if (ret == -EAGAIN) { + if (!force_nonblock) + goto done; + ret = io_setup_async_rw(req, iovec, inline_vecs, iter, false); if (ret) goto out_free; - /* it's copied and will be cleaned with ->io */ - iovec = NULL; - /* if we can retry, do so with the callbacks armed */ - if (io_rw_should_retry(req)) { - ret2 = io_iter_do_read(req, &iter); - if (ret2 == -EIOCBQUEUED) { - goto out_free; - } else if (ret2 != -EAGAIN) { - kiocb_done(kiocb, ret2, cs); - goto out_free; - } - } + return -EAGAIN; + } else if (ret < 0) { + goto out_free; + } + + /* read it all, or we did blocking attempt. no retry. */ + if (!iov_iter_count(iter) || !force_nonblock || + (req->file->f_flags & O_NONBLOCK)) + goto done; + + io_size -= ret; +copy_iov: + ret2 = io_setup_async_rw(req, iovec, inline_vecs, iter, true); + if (ret2) { + ret = ret2; + goto out_free; + } + /* it's copied and will be cleaned with ->io */ + iovec = NULL; + /* now use our persistent iterator, if we aren't already */ + iter = &req->io->rw.iter; +retry: + req->io->rw.bytes_done += ret; + /* if we can retry, do so with the callbacks armed */ + if (!io_rw_should_retry(req)) { kiocb->ki_flags &= ~IOCB_WAITQ; return -EAGAIN; } + + /* + * Now retry read with the IOCB_WAITQ parts set in the iocb. If we + * get -EIOCBQUEUED, then we'll get a notification when the desired + * page gets unlocked. We can also get a partial read here, and if we + * do, then just retry at the new offset. + */ + ret = io_iter_do_read(req, iter); + if (ret == -EIOCBQUEUED) { + ret = 0; + goto out_free; + } else if (ret > 0 && ret < io_size) { + /* we got some bytes, but not all. retry. */ + goto retry; + } +done: + kiocb_done(kiocb, ret, cs); + ret = 0; out_free: if (iovec) kfree(iovec); @@ -3139,12 +3266,14 @@ static int io_write(struct io_kiocb *req, bool force_nonblock, { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; struct kiocb *kiocb = &req->rw.kiocb; - struct iov_iter iter; + struct iov_iter __iter, *iter = &__iter; size_t iov_count; ssize_t ret, ret2, io_size; - unsigned long nr_segs; - ret = io_import_iovec(WRITE, req, &iovec, &iter, !force_nonblock); + if (req->io) + iter = &req->io->rw.iter; + + ret = io_import_iovec(WRITE, req, &iovec, iter, !force_nonblock); if (ret < 0) return ret; io_size = ret; @@ -3163,8 +3292,7 @@ static int io_write(struct io_kiocb *req, bool force_nonblock, (req->flags & REQ_F_ISREG)) goto copy_iov; - iov_count = iov_iter_count(&iter); - nr_segs = iter.nr_segs; + iov_count = iov_iter_count(iter); ret = rw_verify_area(WRITE, req->file, &kiocb->ki_pos, iov_count); if (unlikely(ret)) goto out_free; @@ -3185,9 +3313,11 @@ static int io_write(struct io_kiocb *req, bool force_nonblock, kiocb->ki_flags |= IOCB_WRITE; if (req->file->f_op->write_iter) - ret2 = call_write_iter(req->file, kiocb, &iter); + ret2 = call_write_iter(req->file, kiocb, iter); + else if (req->file->f_op->write) + ret2 = loop_rw_iter(WRITE, req->file, kiocb, iter); else - ret2 = loop_rw_iter(WRITE, req->file, kiocb, &iter); + ret2 = -EINVAL; /* * Raw bdev writes will return -EOPNOTSUPP for IOCB_NOWAIT. Just @@ -3198,16 +3328,10 @@ static int io_write(struct io_kiocb *req, bool force_nonblock, if (!force_nonblock || ret2 != -EAGAIN) { kiocb_done(kiocb, ret2, cs); } else { - iter.count = iov_count; - iter.nr_segs = nr_segs; copy_iov: - ret = io_setup_async_rw(req, io_size, iovec, inline_vecs, - &iter); - if (ret) - goto out_free; - /* it's copied and will be cleaned with ->io */ - iovec = NULL; - return -EAGAIN; + ret = io_setup_async_rw(req, iovec, inline_vecs, iter, false); + if (!ret) + return -EAGAIN; } out_free: if (iovec) @@ -4488,6 +4612,8 @@ static int __io_async_wake(struct io_kiocb *req, struct io_poll_iocb *poll, req->result = mask; init_task_work(&req->task_work, func); + percpu_ref_get(&req->ctx->refs); + /* * If this fails, then the task is exiting. When a task exits, the * work gets canceled, so just cancel this request as well instead @@ -4526,9 +4652,24 @@ static bool io_poll_rewait(struct io_kiocb *req, struct io_poll_iocb *poll) return false; } -static void io_poll_remove_double(struct io_kiocb *req, void *data) +static struct io_poll_iocb *io_poll_get_double(struct io_kiocb *req) { - struct io_poll_iocb *poll = data; + /* pure poll stashes this in ->io, poll driven retry elsewhere */ + if (req->opcode == IORING_OP_POLL_ADD) + return (struct io_poll_iocb *) req->io; + return req->apoll->double_poll; +} + +static struct io_poll_iocb *io_poll_get_single(struct io_kiocb *req) +{ + if (req->opcode == IORING_OP_POLL_ADD) + return &req->poll; + return &req->apoll->poll; +} + +static void io_poll_remove_double(struct io_kiocb *req) +{ + struct io_poll_iocb *poll = io_poll_get_double(req); lockdep_assert_held(&req->ctx->completion_lock); @@ -4548,7 +4689,7 @@ static void io_poll_complete(struct io_kiocb *req, __poll_t mask, int error) { struct io_ring_ctx *ctx = req->ctx; - io_poll_remove_double(req, req->io); + io_poll_remove_double(req); req->poll.done = true; io_cqring_fill_event(req, error ? error : mangle_poll(mask)); io_commit_cqring(ctx); @@ -4575,18 +4716,20 @@ static void io_poll_task_handler(struct io_kiocb *req, struct io_kiocb **nxt) static void io_poll_task_func(struct callback_head *cb) { struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work); + struct io_ring_ctx *ctx = req->ctx; struct io_kiocb *nxt = NULL; io_poll_task_handler(req, &nxt); if (nxt) __io_req_task_submit(nxt); + percpu_ref_put(&ctx->refs); } static int io_poll_double_wake(struct wait_queue_entry *wait, unsigned mode, int sync, void *key) { struct io_kiocb *req = wait->private; - struct io_poll_iocb *poll = req->apoll->double_poll; + struct io_poll_iocb *poll = io_poll_get_single(req); __poll_t mask = key_to_poll(key); /* for instances that support it check for an event match first: */ @@ -4600,6 +4743,8 @@ static int io_poll_double_wake(struct wait_queue_entry *wait, unsigned mode, done = list_empty(&poll->wait.entry); if (!done) list_del_init(&poll->wait.entry); + /* make sure double remove sees this as being gone */ + wait->private = NULL; spin_unlock(&poll->head->lock); if (!done) __io_async_wake(req, poll, mask, io_poll_task_func); @@ -4675,6 +4820,7 @@ static void io_async_task_func(struct callback_head *cb) if (io_poll_rewait(req, &apoll->poll)) { spin_unlock_irq(&ctx->completion_lock); + percpu_ref_put(&ctx->refs); return; } @@ -4682,7 +4828,7 @@ static void io_async_task_func(struct callback_head *cb) if (hash_hashed(&req->hash_node)) hash_del(&req->hash_node); - io_poll_remove_double(req, apoll->double_poll); + io_poll_remove_double(req); spin_unlock_irq(&ctx->completion_lock); if (!READ_ONCE(apoll->poll.canceled)) @@ -4690,6 +4836,7 @@ static void io_async_task_func(struct callback_head *cb) else __io_req_task_cancel(req, -ECANCELED); + percpu_ref_put(&ctx->refs); kfree(apoll->double_poll); kfree(apoll); } @@ -4791,8 +4938,8 @@ static bool io_arm_poll_handler(struct io_kiocb *req) ret = __io_arm_poll_handler(req, &apoll->poll, &ipt, mask, io_async_wake); - if (ret) { - io_poll_remove_double(req, apoll->double_poll); + if (ret || ipt.error) { + io_poll_remove_double(req); spin_unlock_irq(&ctx->completion_lock); kfree(apoll->double_poll); kfree(apoll); @@ -4824,14 +4971,13 @@ static bool io_poll_remove_one(struct io_kiocb *req) { bool do_complete; + io_poll_remove_double(req); + if (req->opcode == IORING_OP_POLL_ADD) { - io_poll_remove_double(req, req->io); do_complete = __io_poll_remove_one(req, &req->poll); } else { struct async_poll *apoll = req->apoll; - io_poll_remove_double(req, apoll->double_poll); - /* non-poll requests have submit ref still */ do_complete = __io_poll_remove_one(req, &apoll->poll); if (do_complete) { @@ -4845,6 +4991,7 @@ static bool io_poll_remove_one(struct io_kiocb *req) io_cqring_fill_event(req, -ECANCELED); io_commit_cqring(req->ctx); req->flags |= REQ_F_COMP_LOCKED; + req_set_fail_links(req); io_put_req(req); } @@ -5017,6 +5164,23 @@ static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer) return HRTIMER_NORESTART; } +static int __io_timeout_cancel(struct io_kiocb *req) +{ + int ret; + + list_del_init(&req->timeout.list); + + ret = hrtimer_try_to_cancel(&req->io->timeout.timer); + if (ret == -1) + return -EALREADY; + + req_set_fail_links(req); + req->flags |= REQ_F_COMP_LOCKED; + io_cqring_fill_event(req, -ECANCELED); + io_put_req(req); + return 0; +} + static int io_timeout_cancel(struct io_ring_ctx *ctx, __u64 user_data) { struct io_kiocb *req; @@ -5024,7 +5188,6 @@ static int io_timeout_cancel(struct io_ring_ctx *ctx, __u64 user_data) list_for_each_entry(req, &ctx->timeout_list, timeout.list) { if (user_data == req->user_data) { - list_del_init(&req->timeout.list); ret = 0; break; } @@ -5033,14 +5196,7 @@ static int io_timeout_cancel(struct io_ring_ctx *ctx, __u64 user_data) if (ret == -ENOENT) return ret; - ret = hrtimer_try_to_cancel(&req->io->timeout.timer); - if (ret == -1) - return -EALREADY; - - req_set_fail_links(req); - io_cqring_fill_event(req, -ECANCELED); - io_put_req(req); - return 0; + return __io_timeout_cancel(req); } static int io_timeout_remove_prep(struct io_kiocb *req, @@ -5481,8 +5637,8 @@ static void __io_clean_op(struct io_kiocb *req) case IORING_OP_WRITEV: case IORING_OP_WRITE_FIXED: case IORING_OP_WRITE: - if (io->rw.iov != io->rw.fast_iov) - kfree(io->rw.iov); + if (io->rw.free_iovec) + kfree(io->rw.free_iovec); break; case IORING_OP_RECVMSG: case IORING_OP_SENDMSG: @@ -5917,15 +6073,12 @@ static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer) return HRTIMER_NORESTART; } -static void io_queue_linked_timeout(struct io_kiocb *req) +static void __io_queue_linked_timeout(struct io_kiocb *req) { - struct io_ring_ctx *ctx = req->ctx; - /* * If the list is now empty, then our linked request finished before * we got a chance to setup the timer */ - spin_lock_irq(&ctx->completion_lock); if (!list_empty(&req->link_list)) { struct io_timeout_data *data = &req->io->timeout; @@ -5933,6 +6086,14 @@ static void io_queue_linked_timeout(struct io_kiocb *req) hrtimer_start(&data->timer, timespec64_to_ktime(data->ts), data->mode); } +} + +static void io_queue_linked_timeout(struct io_kiocb *req) +{ + struct io_ring_ctx *ctx = req->ctx; + + spin_lock_irq(&ctx->completion_lock); + __io_queue_linked_timeout(req); spin_unlock_irq(&ctx->completion_lock); /* drop submission reference */ @@ -7837,6 +7998,71 @@ static bool io_wq_files_match(struct io_wq_work *work, void *data) return work->files == files; } +/* + * Returns true if 'preq' is the link parent of 'req' + */ +static bool io_match_link(struct io_kiocb *preq, struct io_kiocb *req) +{ + struct io_kiocb *link; + + if (!(preq->flags & REQ_F_LINK_HEAD)) + return false; + + list_for_each_entry(link, &preq->link_list, link_list) { + if (link == req) + return true; + } + + return false; +} + +/* + * We're looking to cancel 'req' because it's holding on to our files, but + * 'req' could be a link to another request. See if it is, and cancel that + * parent request if so. + */ +static bool io_poll_remove_link(struct io_ring_ctx *ctx, struct io_kiocb *req) +{ + struct hlist_node *tmp; + struct io_kiocb *preq; + bool found = false; + int i; + + spin_lock_irq(&ctx->completion_lock); + for (i = 0; i < (1U << ctx->cancel_hash_bits); i++) { + struct hlist_head *list; + + list = &ctx->cancel_hash[i]; + hlist_for_each_entry_safe(preq, tmp, list, hash_node) { + found = io_match_link(preq, req); + if (found) { + io_poll_remove_one(preq); + break; + } + } + } + spin_unlock_irq(&ctx->completion_lock); + return found; +} + +static bool io_timeout_remove_link(struct io_ring_ctx *ctx, + struct io_kiocb *req) +{ + struct io_kiocb *preq; + bool found = false; + + spin_lock_irq(&ctx->completion_lock); + list_for_each_entry(preq, &ctx->timeout_list, timeout.list) { + found = io_match_link(preq, req); + if (found) { + __io_timeout_cancel(preq); + break; + } + } + spin_unlock_irq(&ctx->completion_lock); + return found; +} + static void io_uring_cancel_files(struct io_ring_ctx *ctx, struct files_struct *files) { @@ -7891,6 +8117,9 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx, } } else { io_wq_cancel_work(ctx->io_wq, &cancel_req->work); + /* could be a link, check and remove if it is */ + if (!io_poll_remove_link(ctx, cancel_req)) + io_timeout_remove_link(ctx, cancel_req); io_put_req(cancel_req); } @@ -8171,6 +8400,10 @@ static int io_allocate_scq_urings(struct io_ring_ctx *ctx, struct io_rings *rings; size_t size, sq_array_offset; + /* make sure these are sane, as we already accounted them */ + ctx->sq_entries = p->sq_entries; + ctx->cq_entries = p->cq_entries; + size = rings_size(p->sq_entries, p->cq_entries, &sq_array_offset); if (size == SIZE_MAX) return -EOVERFLOW; @@ -8187,8 +8420,6 @@ static int io_allocate_scq_urings(struct io_ring_ctx *ctx, rings->cq_ring_entries = p->cq_entries; ctx->sq_mask = rings->sq_ring_mask; ctx->cq_mask = rings->cq_ring_mask; - ctx->sq_entries = rings->sq_ring_entries; - ctx->cq_entries = rings->cq_ring_entries; size = array_size(sizeof(struct io_uring_sqe), p->sq_entries); if (size == SIZE_MAX) { @@ -8317,6 +8548,16 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, ctx->user = user; ctx->creds = get_current_cred(); + /* + * Account memory _before_ installing the file descriptor. Once + * the descriptor is installed, it can get closed at any time. Also + * do this before hitting the general error path, as ring freeing + * will un-account as well. + */ + io_account_mem(ctx, ring_pages(p->sq_entries, p->cq_entries), + ACCT_LOCKED); + ctx->limit_mem = limit_mem; + ret = io_allocate_scq_urings(ctx, p); if (ret) goto err; @@ -8354,14 +8595,6 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, } /* - * Account memory _before_ installing the file descriptor. Once - * the descriptor is installed, it can get closed at any time. - */ - io_account_mem(ctx, ring_pages(p->sq_entries, p->cq_entries), - ACCT_LOCKED); - ctx->limit_mem = limit_mem; - - /* * Install ring fd as the very last thing, so we don't risk someone * having closed it before we finish setup */ diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c index f20cff1194bb..776493713153 100644 --- a/fs/jffs2/dir.c +++ b/fs/jffs2/dir.c @@ -590,10 +590,14 @@ static int jffs2_rmdir (struct inode *dir_i, struct dentry *dentry) int ret; uint32_t now = JFFS2_NOW(); + mutex_lock(&f->sem); for (fd = f->dents ; fd; fd = fd->next) { - if (fd->ino) + if (fd->ino) { + mutex_unlock(&f->sem); return -ENOTEMPTY; + } } + mutex_unlock(&f->sem); ret = jffs2_do_unlink(c, dir_f, dentry->d_name.name, dentry->d_name.len, f, now); diff --git a/fs/jffs2/scan.c b/fs/jffs2/scan.c index 5f7e284e0df3..db72a9d2d0af 100644 --- a/fs/jffs2/scan.c +++ b/fs/jffs2/scan.c @@ -261,7 +261,8 @@ int jffs2_scan_medium(struct jffs2_sb_info *c) } #endif if (c->nr_erasing_blocks) { - if ( !c->used_size && ((c->nr_free_blocks+empty_blocks+bad_blocks)!= c->nr_blocks || bad_blocks == c->nr_blocks) ) { + if (!c->used_size && !c->unchecked_size && + ((c->nr_free_blocks+empty_blocks+bad_blocks) != c->nr_blocks || bad_blocks == c->nr_blocks)) { pr_notice("Cowardly refusing to erase blocks on filesystem with no valid JFFS2 nodes\n"); pr_notice("empty_blocks %d, bad_blocks %d, c->nr_blocks %d\n", empty_blocks, bad_blocks, c->nr_blocks); diff --git a/fs/locks.c b/fs/locks.c index 938fe325bc54..8fc0542f5132 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1808,6 +1808,9 @@ check_conflicting_open(struct file *filp, const long arg, int flags) if (flags & FL_LAYOUT) return 0; + if (flags & FL_DELEG) + /* We leave these checks to the caller. */ + return 0; if (arg == F_RDLCK) return inode_is_open_for_write(inode) ? -EAGAIN : 0; diff --git a/fs/minix/inode.c b/fs/minix/inode.c index 7cb5fd38eb14..7b09a9158e40 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -150,6 +150,25 @@ static int minix_remount (struct super_block * sb, int * flags, char * data) return 0; } +static bool minix_check_superblock(struct super_block *sb) +{ + struct minix_sb_info *sbi = minix_sb(sb); + + if (sbi->s_imap_blocks == 0 || sbi->s_zmap_blocks == 0) + return false; + + /* + * s_max_size must not exceed the block mapping limitation. This check + * is only needed for V1 filesystems, since V2/V3 support an extra level + * of indirect blocks which places the limit well above U32_MAX. + */ + if (sbi->s_version == MINIX_V1 && + sb->s_maxbytes > (7 + 512 + 512*512) * BLOCK_SIZE) + return false; + + return true; +} + static int minix_fill_super(struct super_block *s, void *data, int silent) { struct buffer_head *bh; @@ -185,7 +204,7 @@ static int minix_fill_super(struct super_block *s, void *data, int silent) sbi->s_zmap_blocks = ms->s_zmap_blocks; sbi->s_firstdatazone = ms->s_firstdatazone; sbi->s_log_zone_size = ms->s_log_zone_size; - sbi->s_max_size = ms->s_max_size; + s->s_maxbytes = ms->s_max_size; s->s_magic = ms->s_magic; if (s->s_magic == MINIX_SUPER_MAGIC) { sbi->s_version = MINIX_V1; @@ -216,7 +235,7 @@ static int minix_fill_super(struct super_block *s, void *data, int silent) sbi->s_zmap_blocks = m3s->s_zmap_blocks; sbi->s_firstdatazone = m3s->s_firstdatazone; sbi->s_log_zone_size = m3s->s_log_zone_size; - sbi->s_max_size = m3s->s_max_size; + s->s_maxbytes = m3s->s_max_size; sbi->s_ninodes = m3s->s_ninodes; sbi->s_nzones = m3s->s_zones; sbi->s_dirsize = 64; @@ -228,11 +247,12 @@ static int minix_fill_super(struct super_block *s, void *data, int silent) } else goto out_no_fs; + if (!minix_check_superblock(s)) + goto out_illegal_sb; + /* * Allocate the buffer map to keep the superblock small. */ - if (sbi->s_imap_blocks == 0 || sbi->s_zmap_blocks == 0) - goto out_illegal_sb; i = (sbi->s_imap_blocks + sbi->s_zmap_blocks) * sizeof(bh); map = kzalloc(i, GFP_KERNEL); if (!map) @@ -468,6 +488,13 @@ static struct inode *V1_minix_iget(struct inode *inode) iget_failed(inode); return ERR_PTR(-EIO); } + if (raw_inode->i_nlinks == 0) { + printk("MINIX-fs: deleted inode referenced: %lu\n", + inode->i_ino); + brelse(bh); + iget_failed(inode); + return ERR_PTR(-ESTALE); + } inode->i_mode = raw_inode->i_mode; i_uid_write(inode, raw_inode->i_uid); i_gid_write(inode, raw_inode->i_gid); @@ -501,6 +528,13 @@ static struct inode *V2_minix_iget(struct inode *inode) iget_failed(inode); return ERR_PTR(-EIO); } + if (raw_inode->i_nlinks == 0) { + printk("MINIX-fs: deleted inode referenced: %lu\n", + inode->i_ino); + brelse(bh); + iget_failed(inode); + return ERR_PTR(-ESTALE); + } inode->i_mode = raw_inode->i_mode; i_uid_write(inode, raw_inode->i_uid); i_gid_write(inode, raw_inode->i_gid); diff --git a/fs/minix/itree_common.c b/fs/minix/itree_common.c index 043c3fdbc8e7..446148792f41 100644 --- a/fs/minix/itree_common.c +++ b/fs/minix/itree_common.c @@ -75,6 +75,7 @@ static int alloc_branch(struct inode *inode, int n = 0; int i; int parent = minix_new_block(inode); + int err = -ENOSPC; branch[0].key = cpu_to_block(parent); if (parent) for (n = 1; n < num; n++) { @@ -85,6 +86,11 @@ static int alloc_branch(struct inode *inode, break; branch[n].key = cpu_to_block(nr); bh = sb_getblk(inode->i_sb, parent); + if (!bh) { + minix_free_block(inode, nr); + err = -ENOMEM; + break; + } lock_buffer(bh); memset(bh->b_data, 0, bh->b_size); branch[n].bh = bh; @@ -103,7 +109,7 @@ static int alloc_branch(struct inode *inode, bforget(branch[i].bh); for (i = 0; i < n; i++) minix_free_block(inode, block_to_cpu(branch[i].key)); - return -ENOSPC; + return err; } static inline int splice_branch(struct inode *inode, diff --git a/fs/minix/itree_v1.c b/fs/minix/itree_v1.c index 046cc96ee7ad..1fed906042aa 100644 --- a/fs/minix/itree_v1.c +++ b/fs/minix/itree_v1.c @@ -29,12 +29,12 @@ static int block_to_path(struct inode * inode, long block, int offsets[DEPTH]) if (block < 0) { printk("MINIX-fs: block_to_path: block %ld < 0 on dev %pg\n", block, inode->i_sb->s_bdev); - } else if (block >= (minix_sb(inode->i_sb)->s_max_size/BLOCK_SIZE)) { - if (printk_ratelimit()) - printk("MINIX-fs: block_to_path: " - "block %ld too big on dev %pg\n", - block, inode->i_sb->s_bdev); - } else if (block < 7) { + return 0; + } + if ((u64)block * BLOCK_SIZE >= inode->i_sb->s_maxbytes) + return 0; + + if (block < 7) { offsets[n++] = block; } else if ((block -= 7) < 512) { offsets[n++] = 7; diff --git a/fs/minix/itree_v2.c b/fs/minix/itree_v2.c index f7fc7ecccccc..9d00f31a2d9d 100644 --- a/fs/minix/itree_v2.c +++ b/fs/minix/itree_v2.c @@ -32,13 +32,12 @@ static int block_to_path(struct inode * inode, long block, int offsets[DEPTH]) if (block < 0) { printk("MINIX-fs: block_to_path: block %ld < 0 on dev %pg\n", block, sb->s_bdev); - } else if ((u64)block * (u64)sb->s_blocksize >= - minix_sb(sb)->s_max_size) { - if (printk_ratelimit()) - printk("MINIX-fs: block_to_path: " - "block %ld too big on dev %pg\n", - block, sb->s_bdev); - } else if (block < DIRCOUNT) { + return 0; + } + if ((u64)block * (u64)sb->s_blocksize >= sb->s_maxbytes) + return 0; + + if (block < DIRCOUNT) { offsets[n++] = block; } else if ((block -= DIRCOUNT) < INDIRCOUNT(sb)) { offsets[n++] = DIRCOUNT; diff --git a/fs/minix/minix.h b/fs/minix/minix.h index df081e8afcc3..168d45d3de73 100644 --- a/fs/minix/minix.h +++ b/fs/minix/minix.h @@ -32,7 +32,6 @@ struct minix_sb_info { unsigned long s_zmap_blocks; unsigned long s_firstdatazone; unsigned long s_log_zone_size; - unsigned long s_max_size; int s_dirsize; int s_namelen; struct buffer_head ** s_imap; diff --git a/fs/namei.c b/fs/namei.c index fde8fe086c09..e99e2a9da0f7 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2851,16 +2851,24 @@ static int may_open(const struct path *path, int acc_mode, int flag) case S_IFDIR: if (acc_mode & MAY_WRITE) return -EISDIR; + if (acc_mode & MAY_EXEC) + return -EACCES; break; case S_IFBLK: case S_IFCHR: if (!may_open_dev(path)) return -EACCES; - /*FALLTHRU*/ + fallthrough; case S_IFIFO: case S_IFSOCK: + if (acc_mode & MAY_EXEC) + return -EACCES; flag &= ~O_TRUNC; break; + case S_IFREG: + if ((acc_mode & MAY_EXEC) && path_noexec(path)) + return -EACCES; + break; } error = inode_permission(inode, MAY_OPEN | acc_mode); @@ -3770,11 +3778,11 @@ exit2: mnt_drop_write(path.mnt); exit1: path_put(&path); - putname(name); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } + putname(name); return error; } diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile index 2433c3e03cfa..22d11fdc6deb 100644 --- a/fs/nfs/Makefile +++ b/fs/nfs/Makefile @@ -30,7 +30,7 @@ nfsv4-y := nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o nfs4super.o nfs4file.o nfsv4-$(CONFIG_NFS_USE_LEGACY_DNS) += cache_lib.o nfsv4-$(CONFIG_SYSCTL) += nfs4sysctl.o nfsv4-$(CONFIG_NFS_V4_1) += pnfs.o pnfs_dev.o pnfs_nfs.o -nfsv4-$(CONFIG_NFS_V4_2) += nfs42proc.o +nfsv4-$(CONFIG_NFS_V4_2) += nfs42proc.o nfs42xattr.o obj-$(CONFIG_PNFS_FILE_LAYOUT) += filelayout/ obj-$(CONFIG_PNFS_BLOCK) += blocklayout/ diff --git a/fs/nfs/blocklayout/rpc_pipefs.c b/fs/nfs/blocklayout/rpc_pipefs.c index 9fb067a6f7e0..ef9db135c649 100644 --- a/fs/nfs/blocklayout/rpc_pipefs.c +++ b/fs/nfs/blocklayout/rpc_pipefs.c @@ -79,7 +79,7 @@ bl_resolve_deviceid(struct nfs_server *server, struct pnfs_block_volume *b, goto out_free_data; bl_msg = msg->data; - bl_msg->type = BL_DEVICE_MOUNT, + bl_msg->type = BL_DEVICE_MOUNT; bl_msg->totallen = b->simple.len; nfs4_encode_simple(msg->data + sizeof(*bl_msg), b); diff --git a/fs/nfs/client.c b/fs/nfs/client.c index f1ff3076e4a4..4b8cc93913f7 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -50,6 +50,7 @@ #include "nfs.h" #include "netns.h" #include "sysfs.h" +#include "nfs42.h" #define NFSDBG_FACILITY NFSDBG_CLIENT @@ -749,7 +750,7 @@ error: static void nfs_server_set_fsinfo(struct nfs_server *server, struct nfs_fsinfo *fsinfo) { - unsigned long max_rpc_payload; + unsigned long max_rpc_payload, raw_max_rpc_payload; /* Work out a lot of parameters */ if (server->rsize == 0) @@ -762,7 +763,9 @@ static void nfs_server_set_fsinfo(struct nfs_server *server, if (fsinfo->wtmax >= 512 && server->wsize > fsinfo->wtmax) server->wsize = nfs_block_size(fsinfo->wtmax, NULL); - max_rpc_payload = nfs_block_size(rpc_max_payload(server->client), NULL); + raw_max_rpc_payload = rpc_max_payload(server->client); + max_rpc_payload = nfs_block_size(raw_max_rpc_payload, NULL); + if (server->rsize > max_rpc_payload) server->rsize = max_rpc_payload; if (server->rsize > NFS_MAX_FILE_IO_SIZE) @@ -795,6 +798,21 @@ static void nfs_server_set_fsinfo(struct nfs_server *server, server->clone_blksize = fsinfo->clone_blksize; /* We're airborne Set socket buffersize */ rpc_setbufsize(server->client, server->wsize + 100, server->rsize + 100); + +#ifdef CONFIG_NFS_V4_2 + /* + * Defaults until limited by the session parameters. + */ + server->gxasize = min_t(unsigned int, raw_max_rpc_payload, + XATTR_SIZE_MAX); + server->sxasize = min_t(unsigned int, raw_max_rpc_payload, + XATTR_SIZE_MAX); + server->lxasize = min_t(unsigned int, raw_max_rpc_payload, + nfs42_listxattr_xdrsize(XATTR_LIST_MAX)); + + if (fsinfo->xattr_support) + server->caps |= NFS_CAP_XATTR; +#endif } /* diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 5a331da5f55a..a12f42e7d8c7 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -2460,7 +2460,7 @@ static struct nfs_access_entry *nfs_access_search_rbtree(struct inode *inode, co return NULL; } -static int nfs_access_get_cached(struct inode *inode, const struct cred *cred, struct nfs_access_entry *res, bool may_block) +static int nfs_access_get_cached_locked(struct inode *inode, const struct cred *cred, struct nfs_access_entry *res, bool may_block) { struct nfs_inode *nfsi = NFS_I(inode); struct nfs_access_entry *cache; @@ -2533,6 +2533,20 @@ out: return err; } +int nfs_access_get_cached(struct inode *inode, const struct cred *cred, struct +nfs_access_entry *res, bool may_block) +{ + int status; + + status = nfs_access_get_cached_rcu(inode, cred, res); + if (status != 0) + status = nfs_access_get_cached_locked(inode, cred, res, + may_block); + + return status; +} +EXPORT_SYMBOL_GPL(nfs_access_get_cached); + static void nfs_access_add_rbtree(struct inode *inode, struct nfs_access_entry *set) { struct nfs_inode *nfsi = NFS_I(inode); @@ -2647,9 +2661,7 @@ static int nfs_do_access(struct inode *inode, const struct cred *cred, int mask) trace_nfs_access_enter(inode); - status = nfs_access_get_cached_rcu(inode, cred, &cache); - if (status != 0) - status = nfs_access_get_cached(inode, cred, &cache, may_block); + status = nfs_access_get_cached(inode, cred, &cache, may_block); if (status == 0) goto out_cached; @@ -2661,6 +2673,10 @@ static int nfs_do_access(struct inode *inode, const struct cred *cred, int mask) * Determine which access bits we want to ask for... */ cache.mask = NFS_ACCESS_READ | NFS_ACCESS_MODIFY | NFS_ACCESS_EXTEND; + if (nfs_server_capable(inode, NFS_CAP_XATTR)) { + cache.mask |= NFS_ACCESS_XAREAD | NFS_ACCESS_XAWRITE | + NFS_ACCESS_XALIST; + } if (S_ISDIR(inode->i_mode)) cache.mask |= NFS_ACCESS_DELETE | NFS_ACCESS_LOOKUP; else diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 1b79dd5cf661..2d30a4da49fa 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -896,7 +896,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, */ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter) { - ssize_t result = -EINVAL, requested; + ssize_t result, requested; size_t count; struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; diff --git a/fs/nfs/file.c b/fs/nfs/file.c index f96367a2463e..63940a7a70be 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -140,6 +140,7 @@ static int nfs_file_flush(struct file *file, fl_owner_t id) { struct inode *inode = file_inode(file); + errseq_t since; dprintk("NFS: flush(%pD2)\n", file); @@ -148,7 +149,9 @@ nfs_file_flush(struct file *file, fl_owner_t id) return 0; /* Flush writes to the server and return any errors */ - return nfs_wb_all(inode); + since = filemap_sample_wb_err(file->f_mapping); + nfs_wb_all(inode); + return filemap_check_wb_err(file->f_mapping, since); } ssize_t @@ -587,12 +590,14 @@ static const struct vm_operations_struct nfs_file_vm_ops = { .page_mkwrite = nfs_vm_page_mkwrite, }; -static int nfs_need_check_write(struct file *filp, struct inode *inode) +static int nfs_need_check_write(struct file *filp, struct inode *inode, + int error) { struct nfs_open_context *ctx; ctx = nfs_file_open_context(filp); - if (nfs_ctx_key_to_expire(ctx, inode)) + if (nfs_error_is_fatal_on_server(error) || + nfs_ctx_key_to_expire(ctx, inode)) return 1; return 0; } @@ -603,6 +608,8 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from) struct inode *inode = file_inode(file); unsigned long written = 0; ssize_t result; + errseq_t since; + int error; result = nfs_key_timeout_notify(file, inode); if (result) @@ -627,6 +634,7 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from) if (iocb->ki_pos > i_size_read(inode)) nfs_revalidate_mapping(inode, file->f_mapping); + since = filemap_sample_wb_err(file->f_mapping); nfs_start_io_write(inode); result = generic_write_checks(iocb, from); if (result > 0) { @@ -645,7 +653,8 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from) goto out; /* Return error values */ - if (nfs_need_check_write(file, inode)) { + error = filemap_check_wb_err(file->f_mapping, since); + if (nfs_need_check_write(file, inode, error)) { int err = nfs_wb_all(inode); if (err < 0) result = err; diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index de03e440b7ee..965145592750 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -790,6 +790,19 @@ ff_layout_choose_best_ds_for_read(struct pnfs_layout_segment *lseg, return ff_layout_choose_any_ds_for_read(lseg, start_idx, best_idx); } +static struct nfs4_pnfs_ds * +ff_layout_get_ds_for_read(struct nfs_pageio_descriptor *pgio, int *best_idx) +{ + struct pnfs_layout_segment *lseg = pgio->pg_lseg; + struct nfs4_pnfs_ds *ds; + + ds = ff_layout_choose_best_ds_for_read(lseg, pgio->pg_mirror_idx, + best_idx); + if (ds || !pgio->pg_mirror_idx) + return ds; + return ff_layout_choose_best_ds_for_read(lseg, 0, best_idx); +} + static void ff_layout_pg_get_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req, @@ -840,12 +853,11 @@ retry: goto out_nolseg; } - ds = ff_layout_choose_best_ds_for_read(pgio->pg_lseg, 0, &ds_idx); + ds = ff_layout_get_ds_for_read(pgio, &ds_idx); if (!ds) { if (!ff_layout_no_fallback_to_mds(pgio->pg_lseg)) goto out_mds; - pnfs_put_lseg(pgio->pg_lseg); - pgio->pg_lseg = NULL; + pnfs_generic_pg_cleanup(pgio); /* Sleep for 1 second before retrying */ ssleep(1); goto retry; @@ -871,8 +883,6 @@ out_mds: 0, NFS4_MAX_UINT64, IOMODE_READ, NFS_I(pgio->pg_inode)->layout, pgio->pg_lseg); - pnfs_put_lseg(pgio->pg_lseg); - pgio->pg_lseg = NULL; pgio->pg_maxretrans = 0; nfs_pageio_reset_read_mds(pgio); } @@ -916,8 +926,7 @@ retry: if (!ds) { if (!ff_layout_no_fallback_to_mds(pgio->pg_lseg)) goto out_mds; - pnfs_put_lseg(pgio->pg_lseg); - pgio->pg_lseg = NULL; + pnfs_generic_pg_cleanup(pgio); /* Sleep for 1 second before retrying */ ssleep(1); goto retry; @@ -939,8 +948,6 @@ out_mds: 0, NFS4_MAX_UINT64, IOMODE_RW, NFS_I(pgio->pg_inode)->layout, pgio->pg_lseg); - pnfs_put_lseg(pgio->pg_lseg); - pgio->pg_lseg = NULL; pgio->pg_maxretrans = 0; nfs_pageio_reset_write_mds(pgio); pgio->pg_error = -EAGAIN; @@ -953,8 +960,8 @@ ff_layout_pg_get_mirror_count_write(struct nfs_pageio_descriptor *pgio, if (!pgio->pg_lseg) { pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, nfs_req_openctx(req), - 0, - NFS4_MAX_UINT64, + req_offset(req), + req->wb_bytes, IOMODE_RW, false, GFP_NOFS); @@ -1028,11 +1035,24 @@ static void ff_layout_reset_write(struct nfs_pgio_header *hdr, bool retry_pnfs) } } +static void ff_layout_resend_pnfs_read(struct nfs_pgio_header *hdr) +{ + u32 idx = hdr->pgio_mirror_idx + 1; + int new_idx = 0; + + if (ff_layout_choose_any_ds_for_read(hdr->lseg, idx + 1, &new_idx)) + ff_layout_send_layouterror(hdr->lseg); + else + pnfs_error_mark_layout_for_return(hdr->inode, hdr->lseg); + pnfs_read_resend_pnfs(hdr, new_idx); +} + static void ff_layout_reset_read(struct nfs_pgio_header *hdr) { struct rpc_task *task = &hdr->task; pnfs_layoutcommit_inode(hdr->inode, false); + pnfs_error_mark_layout_for_return(hdr->inode, hdr->lseg); if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) { dprintk("%s Reset task %5u for i/o through MDS " @@ -1234,6 +1254,12 @@ static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg, break; case NFS4ERR_NXIO: ff_layout_mark_ds_unreachable(lseg, idx); + /* + * Don't return the layout if this is a read and we still + * have layouts to try + */ + if (opnum == OP_READ) + break; /* Fallthrough */ default: pnfs_error_mark_layout_for_return(lseg->pls_layout->plh_inode, @@ -1247,7 +1273,6 @@ static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg, static int ff_layout_read_done_cb(struct rpc_task *task, struct nfs_pgio_header *hdr) { - int new_idx = hdr->pgio_mirror_idx; int err; if (task->tk_status < 0) { @@ -1267,10 +1292,6 @@ static int ff_layout_read_done_cb(struct rpc_task *task, clear_bit(NFS_IOHDR_RESEND_MDS, &hdr->flags); switch (err) { case -NFS4ERR_RESET_TO_PNFS: - if (ff_layout_choose_best_ds_for_read(hdr->lseg, - hdr->pgio_mirror_idx + 1, - &new_idx)) - goto out_layouterror; set_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags); return task->tk_status; case -NFS4ERR_RESET_TO_MDS: @@ -1281,10 +1302,6 @@ static int ff_layout_read_done_cb(struct rpc_task *task, } return 0; -out_layouterror: - ff_layout_read_record_layoutstats_done(task, hdr); - ff_layout_send_layouterror(hdr->lseg); - hdr->pgio_mirror_idx = new_idx; out_eagain: rpc_restart_call_prepare(task); return -EAGAIN; @@ -1411,10 +1428,9 @@ static void ff_layout_read_release(void *data) struct nfs_pgio_header *hdr = data; ff_layout_read_record_layoutstats_done(&hdr->task, hdr); - if (test_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags)) { - ff_layout_send_layouterror(hdr->lseg); - pnfs_read_resend_pnfs(hdr); - } else if (test_bit(NFS_IOHDR_RESEND_MDS, &hdr->flags)) + if (test_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags)) + ff_layout_resend_pnfs_read(hdr); + else if (test_bit(NFS_IOHDR_RESEND_MDS, &hdr->flags)) ff_layout_reset_read(hdr); pnfs_generic_rw_release(data); } diff --git a/fs/nfs/fs_context.c b/fs/nfs/fs_context.c index ccc88be88d6a..66949da0e827 100644 --- a/fs/nfs/fs_context.c +++ b/fs/nfs/fs_context.c @@ -982,7 +982,7 @@ static int nfs23_parse_monolithic(struct fs_context *fc, /* * The legacy version 6 binary mount data from userspace has a * field used only to transport selinux information into the - * the kernel. To continue to support that functionality we + * kernel. To continue to support that functionality we * have a touch of selinux knowledge here in the NFS code. The * userspace code converted context=blah to just blah so we are * converting back to the full string selinux understands. diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 0bf1f835de01..aa6493905bbe 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -193,6 +193,7 @@ bool nfs_check_cache_invalid(struct inode *inode, unsigned long flags) return nfs_check_cache_invalid_not_delegated(inode, flags); } +EXPORT_SYMBOL_GPL(nfs_check_cache_invalid); static void nfs_set_cache_invalid(struct inode *inode, unsigned long flags) { @@ -204,7 +205,8 @@ static void nfs_set_cache_invalid(struct inode *inode, unsigned long flags) flags &= ~NFS_INO_INVALID_OTHER; flags &= ~(NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_SIZE - | NFS_INO_REVAL_PAGECACHE); + | NFS_INO_REVAL_PAGECACHE + | NFS_INO_INVALID_XATTR); } if (inode->i_mapping->nrpages == 0) @@ -233,11 +235,13 @@ static void nfs_zap_caches_locked(struct inode *inode) | NFS_INO_INVALID_DATA | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL + | NFS_INO_INVALID_XATTR | NFS_INO_REVAL_PAGECACHE); } else nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL + | NFS_INO_INVALID_XATTR | NFS_INO_REVAL_PAGECACHE); nfs_zap_label_cache_locked(nfsi); } @@ -542,6 +546,8 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st inode->i_gid = fattr->gid; else if (nfs_server_capable(inode, NFS_CAP_OWNER_GROUP)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_OTHER); + if (nfs_server_capable(inode, NFS_CAP_XATTR)) + nfs_set_cache_invalid(inode, NFS_INO_INVALID_XATTR); if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED) inode->i_blocks = fattr->du.nfs2.blocks; if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) { @@ -794,8 +800,10 @@ int nfs_getattr(const struct path *path, struct kstat *stat, trace_nfs_getattr_enter(inode); - if ((query_flags & AT_STATX_DONT_SYNC) && !force_sync) + if ((query_flags & AT_STATX_DONT_SYNC) && !force_sync) { + nfs_readdirplus_parent_cache_hit(path->dentry); goto out_no_update; + } /* Flush out writes to the server in order to update c/mtime. */ if ((request_mask & (STATX_CTIME|STATX_MTIME)) && @@ -1375,6 +1383,8 @@ static void nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr) inode_set_iversion_raw(inode, fattr->change_attr); if (S_ISDIR(inode->i_mode)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA); + else if (nfs_server_capable(inode, NFS_CAP_XATTR)) + nfs_set_cache_invalid(inode, NFS_INO_INVALID_XATTR); } /* If we have atomic WCC data, we may update some attributes */ ts = inode->i_ctime; @@ -1892,7 +1902,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) if (!(have_writers || have_delegation)) { invalid |= NFS_INO_INVALID_DATA | NFS_INO_INVALID_ACCESS - | NFS_INO_INVALID_ACL; + | NFS_INO_INVALID_ACL + | NFS_INO_INVALID_XATTR; /* Force revalidate of all attributes */ save_cache_validity |= NFS_INO_INVALID_CTIME | NFS_INO_INVALID_MTIME @@ -2095,6 +2106,9 @@ struct inode *nfs_alloc_inode(struct super_block *sb) #if IS_ENABLED(CONFIG_NFS_V4) nfsi->nfs4_acl = NULL; #endif /* CONFIG_NFS_V4 */ +#ifdef CONFIG_NFS_V4_2 + nfsi->xattr_cache = NULL; +#endif return &nfsi->vfs_inode; } EXPORT_SYMBOL_GPL(nfs_alloc_inode); diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h index c891af949886..0fe5aacbcfdf 100644 --- a/fs/nfs/nfs42.h +++ b/fs/nfs/nfs42.h @@ -6,6 +6,8 @@ #ifndef __LINUX_FS_NFS_NFS4_2_H #define __LINUX_FS_NFS_NFS4_2_H +#include <linux/xattr.h> + /* * FIXME: four LAYOUTSTATS calls per compound at most! Do we need to support * more? Need to consider not to pre-alloc too much for a compound. @@ -36,5 +38,27 @@ static inline bool nfs42_files_from_same_server(struct file *in, return nfs4_check_serverowner_major_id(c_in->cl_serverowner, c_out->cl_serverowner); } + +ssize_t nfs42_proc_getxattr(struct inode *inode, const char *name, + void *buf, size_t buflen); +int nfs42_proc_setxattr(struct inode *inode, const char *name, + const void *buf, size_t buflen, int flags); +ssize_t nfs42_proc_listxattrs(struct inode *inode, void *buf, + size_t buflen, u64 *cookiep, bool *eofp); +int nfs42_proc_removexattr(struct inode *inode, const char *name); + +/* + * Maximum XDR buffer size needed for a listxattr buffer of buflen size. + * + * The upper boundary is a buffer with all 1-byte sized attribute names. + * They would be 7 bytes long in the eventual buffer ("user.x\0"), and + * 8 bytes long XDR-encoded. + * + * Include the trailing eof word as well. + */ +static inline u32 nfs42_listxattr_xdrsize(u32 buflen) +{ + return ((buflen / (XATTR_USER_PREFIX_LEN + 2)) * 8) + 4; +} #endif /* CONFIG_NFS_V4_2 */ #endif /* __LINUX_FS_NFS_NFS4_2_H */ diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index e2ae54b35dfe..142225f0af59 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -17,6 +17,7 @@ #include "nfs4session.h" #include "internal.h" #include "delegation.h" +#include "nfs4trace.h" #define NFSDBG_FACILITY NFSDBG_PROC static int nfs42_do_offload_cancel_async(struct file *dst, nfs4_stateid *std); @@ -714,7 +715,7 @@ nfs42_layoutstat_done(struct rpc_task *task, void *calldata) switch (task->tk_status) { case 0: - break; + return; case -NFS4ERR_BADHANDLE: case -ESTALE: pnfs_destroy_layout(NFS_I(inode)); @@ -760,6 +761,8 @@ nfs42_layoutstat_done(struct rpc_task *task, void *calldata) case -EOPNOTSUPP: NFS_SERVER(inode)->caps &= ~NFS_CAP_LAYOUTSTATS; } + + trace_nfs4_layoutstats(inode, &data->args.stateid, task->tk_status); } static void @@ -882,7 +885,7 @@ nfs42_layouterror_done(struct rpc_task *task, void *calldata) switch (task->tk_status) { case 0: - break; + return; case -NFS4ERR_BADHANDLE: case -ESTALE: pnfs_destroy_layout(NFS_I(inode)); @@ -926,6 +929,9 @@ nfs42_layouterror_done(struct rpc_task *task, void *calldata) case -EOPNOTSUPP: NFS_SERVER(inode)->caps &= ~NFS_CAP_LAYOUTERROR; } + + trace_nfs4_layouterror(inode, &data->args.errors[0].stateid, + task->tk_status); } static void @@ -1088,3 +1094,251 @@ out_put_src_lock: nfs_put_lock_context(src_lock); return err; } + +#define NFS4XATTR_MAXPAGES DIV_ROUND_UP(XATTR_SIZE_MAX, PAGE_SIZE) + +static int _nfs42_proc_removexattr(struct inode *inode, const char *name) +{ + struct nfs_server *server = NFS_SERVER(inode); + struct nfs42_removexattrargs args = { + .fh = NFS_FH(inode), + .xattr_name = name, + }; + struct nfs42_removexattrres res; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_REMOVEXATTR], + .rpc_argp = &args, + .rpc_resp = &res, + }; + int ret; + unsigned long timestamp = jiffies; + + ret = nfs4_call_sync(server->client, server, &msg, &args.seq_args, + &res.seq_res, 1); + if (!ret) + nfs4_update_changeattr(inode, &res.cinfo, timestamp, 0); + + return ret; +} + +static int _nfs42_proc_setxattr(struct inode *inode, const char *name, + const void *buf, size_t buflen, int flags) +{ + struct nfs_server *server = NFS_SERVER(inode); + struct page *pages[NFS4XATTR_MAXPAGES]; + struct nfs42_setxattrargs arg = { + .fh = NFS_FH(inode), + .xattr_pages = pages, + .xattr_len = buflen, + .xattr_name = name, + .xattr_flags = flags, + }; + struct nfs42_setxattrres res; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_SETXATTR], + .rpc_argp = &arg, + .rpc_resp = &res, + }; + int ret, np; + unsigned long timestamp = jiffies; + + if (buflen > server->sxasize) + return -ERANGE; + + if (buflen > 0) { + np = nfs4_buf_to_pages_noslab(buf, buflen, arg.xattr_pages); + if (np < 0) + return np; + } else + np = 0; + + ret = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, + &res.seq_res, 1); + + for (; np > 0; np--) + put_page(pages[np - 1]); + + if (!ret) + nfs4_update_changeattr(inode, &res.cinfo, timestamp, 0); + + return ret; +} + +static ssize_t _nfs42_proc_getxattr(struct inode *inode, const char *name, + void *buf, size_t buflen) +{ + struct nfs_server *server = NFS_SERVER(inode); + struct page *pages[NFS4XATTR_MAXPAGES] = {}; + struct nfs42_getxattrargs arg = { + .fh = NFS_FH(inode), + .xattr_pages = pages, + .xattr_len = buflen, + .xattr_name = name, + }; + struct nfs42_getxattrres res; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_GETXATTR], + .rpc_argp = &arg, + .rpc_resp = &res, + }; + int ret, np; + + ret = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, + &res.seq_res, 0); + if (ret < 0) + return ret; + + /* + * Normally, the caching is done one layer up, but for successful + * RPCS, always cache the result here, even if the caller was + * just querying the length, or if the reply was too big for + * the caller. This avoids a second RPC in the case of the + * common query-alloc-retrieve cycle for xattrs. + * + * Note that xattr_len is always capped to XATTR_SIZE_MAX. + */ + + nfs4_xattr_cache_add(inode, name, NULL, pages, res.xattr_len); + + if (buflen) { + if (res.xattr_len > buflen) + return -ERANGE; + _copy_from_pages(buf, pages, 0, res.xattr_len); + } + + np = DIV_ROUND_UP(res.xattr_len, PAGE_SIZE); + while (--np >= 0) + __free_page(pages[np]); + + return res.xattr_len; +} + +static ssize_t _nfs42_proc_listxattrs(struct inode *inode, void *buf, + size_t buflen, u64 *cookiep, bool *eofp) +{ + struct nfs_server *server = NFS_SERVER(inode); + struct page **pages; + struct nfs42_listxattrsargs arg = { + .fh = NFS_FH(inode), + .cookie = *cookiep, + }; + struct nfs42_listxattrsres res = { + .eof = false, + .xattr_buf = buf, + .xattr_len = buflen, + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LISTXATTRS], + .rpc_argp = &arg, + .rpc_resp = &res, + }; + u32 xdrlen; + int ret, np; + + + res.scratch = alloc_page(GFP_KERNEL); + if (!res.scratch) + return -ENOMEM; + + xdrlen = nfs42_listxattr_xdrsize(buflen); + if (xdrlen > server->lxasize) + xdrlen = server->lxasize; + np = xdrlen / PAGE_SIZE + 1; + + pages = kcalloc(np, sizeof(struct page *), GFP_KERNEL); + if (pages == NULL) { + __free_page(res.scratch); + return -ENOMEM; + } + + arg.xattr_pages = pages; + arg.count = xdrlen; + + ret = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, + &res.seq_res, 0); + + if (ret >= 0) { + ret = res.copied; + *cookiep = res.cookie; + *eofp = res.eof; + } + + while (--np >= 0) { + if (pages[np]) + __free_page(pages[np]); + } + + __free_page(res.scratch); + kfree(pages); + + return ret; + +} + +ssize_t nfs42_proc_getxattr(struct inode *inode, const char *name, + void *buf, size_t buflen) +{ + struct nfs4_exception exception = { }; + ssize_t err; + + do { + err = _nfs42_proc_getxattr(inode, name, buf, buflen); + if (err >= 0) + break; + err = nfs4_handle_exception(NFS_SERVER(inode), err, + &exception); + } while (exception.retry); + + return err; +} + +int nfs42_proc_setxattr(struct inode *inode, const char *name, + const void *buf, size_t buflen, int flags) +{ + struct nfs4_exception exception = { }; + int err; + + do { + err = _nfs42_proc_setxattr(inode, name, buf, buflen, flags); + if (!err) + break; + err = nfs4_handle_exception(NFS_SERVER(inode), err, + &exception); + } while (exception.retry); + + return err; +} + +ssize_t nfs42_proc_listxattrs(struct inode *inode, void *buf, + size_t buflen, u64 *cookiep, bool *eofp) +{ + struct nfs4_exception exception = { }; + ssize_t err; + + do { + err = _nfs42_proc_listxattrs(inode, buf, buflen, + cookiep, eofp); + if (err >= 0) + break; + err = nfs4_handle_exception(NFS_SERVER(inode), err, + &exception); + } while (exception.retry); + + return err; +} + +int nfs42_proc_removexattr(struct inode *inode, const char *name) +{ + struct nfs4_exception exception = { }; + int err; + + do { + err = _nfs42_proc_removexattr(inode, name); + if (!err) + break; + err = nfs4_handle_exception(NFS_SERVER(inode), err, + &exception); + } while (exception.retry); + + return err; +} diff --git a/fs/nfs/nfs42xattr.c b/fs/nfs/nfs42xattr.c new file mode 100644 index 000000000000..86777996cfec --- /dev/null +++ b/fs/nfs/nfs42xattr.c @@ -0,0 +1,1056 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright 2019, 2020 Amazon.com, Inc. or its affiliates. All rights reserved. + * + * User extended attribute client side cache functions. + * + * Author: Frank van der Linden <fllinden@amazon.com> + */ +#include <linux/errno.h> +#include <linux/nfs_fs.h> +#include <linux/hashtable.h> +#include <linux/refcount.h> +#include <uapi/linux/xattr.h> + +#include "nfs4_fs.h" +#include "internal.h" + +/* + * User extended attributes client side caching is implemented by having + * a cache structure attached to NFS inodes. This structure is allocated + * when needed, and freed when the cache is zapped. + * + * The cache structure contains as hash table of entries, and a pointer + * to a special-cased entry for the listxattr cache. + * + * Accessing and allocating / freeing the caches is done via reference + * counting. The cache entries use a similar refcounting scheme. + * + * This makes freeing a cache, both from the shrinker and from the + * zap cache path, easy. It also means that, in current use cases, + * the large majority of inodes will not waste any memory, as they + * will never have any user extended attributes assigned to them. + * + * Attribute entries are hashed in to a simple hash table. They are + * also part of an LRU. + * + * There are three shrinkers. + * + * Two shrinkers deal with the cache entries themselves: one for + * large entries (> PAGE_SIZE), and one for smaller entries. The + * shrinker for the larger entries works more aggressively than + * those for the smaller entries. + * + * The other shrinker frees the cache structures themselves. + */ + +/* + * 64 buckets is a good default. There is likely no reasonable + * workload that uses more than even 64 user extended attributes. + * You can certainly add a lot more - but you get what you ask for + * in those circumstances. + */ +#define NFS4_XATTR_HASH_SIZE 64 + +#define NFSDBG_FACILITY NFSDBG_XATTRCACHE + +struct nfs4_xattr_cache; +struct nfs4_xattr_entry; + +struct nfs4_xattr_bucket { + spinlock_t lock; + struct hlist_head hlist; + struct nfs4_xattr_cache *cache; + bool draining; +}; + +struct nfs4_xattr_cache { + struct kref ref; + spinlock_t hash_lock; /* protects hashtable and lru */ + struct nfs4_xattr_bucket buckets[NFS4_XATTR_HASH_SIZE]; + struct list_head lru; + struct list_head dispose; + atomic_long_t nent; + spinlock_t listxattr_lock; + struct inode *inode; + struct nfs4_xattr_entry *listxattr; +}; + +struct nfs4_xattr_entry { + struct kref ref; + struct hlist_node hnode; + struct list_head lru; + struct list_head dispose; + char *xattr_name; + void *xattr_value; + size_t xattr_size; + struct nfs4_xattr_bucket *bucket; + uint32_t flags; +}; + +#define NFS4_XATTR_ENTRY_EXTVAL 0x0001 + +/* + * LRU list of NFS inodes that have xattr caches. + */ +static struct list_lru nfs4_xattr_cache_lru; +static struct list_lru nfs4_xattr_entry_lru; +static struct list_lru nfs4_xattr_large_entry_lru; + +static struct kmem_cache *nfs4_xattr_cache_cachep; + +/* + * Hashing helper functions. + */ +static void +nfs4_xattr_hash_init(struct nfs4_xattr_cache *cache) +{ + unsigned int i; + + for (i = 0; i < NFS4_XATTR_HASH_SIZE; i++) { + INIT_HLIST_HEAD(&cache->buckets[i].hlist); + spin_lock_init(&cache->buckets[i].lock); + cache->buckets[i].cache = cache; + cache->buckets[i].draining = false; + } +} + +/* + * Locking order: + * 1. inode i_lock or bucket lock + * 2. list_lru lock (taken by list_lru_* functions) + */ + +/* + * Wrapper functions to add a cache entry to the right LRU. + */ +static bool +nfs4_xattr_entry_lru_add(struct nfs4_xattr_entry *entry) +{ + struct list_lru *lru; + + lru = (entry->flags & NFS4_XATTR_ENTRY_EXTVAL) ? + &nfs4_xattr_large_entry_lru : &nfs4_xattr_entry_lru; + + return list_lru_add(lru, &entry->lru); +} + +static bool +nfs4_xattr_entry_lru_del(struct nfs4_xattr_entry *entry) +{ + struct list_lru *lru; + + lru = (entry->flags & NFS4_XATTR_ENTRY_EXTVAL) ? + &nfs4_xattr_large_entry_lru : &nfs4_xattr_entry_lru; + + return list_lru_del(lru, &entry->lru); +} + +/* + * This function allocates cache entries. They are the normal + * extended attribute name/value pairs, but may also be a listxattr + * cache. Those allocations use the same entry so that they can be + * treated as one by the memory shrinker. + * + * xattr cache entries are allocated together with names. If the + * value fits in to one page with the entry structure and the name, + * it will also be part of the same allocation (kmalloc). This is + * expected to be the vast majority of cases. Larger allocations + * have a value pointer that is allocated separately by kvmalloc. + * + * Parameters: + * + * @name: Name of the extended attribute. NULL for listxattr cache + * entry. + * @value: Value of attribute, or listxattr cache. NULL if the + * value is to be copied from pages instead. + * @pages: Pages to copy the value from, if not NULL. Passed in to + * make it easier to copy the value after an RPC, even if + * the value will not be passed up to application (e.g. + * for a 'query' getxattr with NULL buffer). + * @len: Length of the value. Can be 0 for zero-length attribues. + * @value and @pages will be NULL if @len is 0. + */ +static struct nfs4_xattr_entry * +nfs4_xattr_alloc_entry(const char *name, const void *value, + struct page **pages, size_t len) +{ + struct nfs4_xattr_entry *entry; + void *valp; + char *namep; + size_t alloclen, slen; + char *buf; + uint32_t flags; + + BUILD_BUG_ON(sizeof(struct nfs4_xattr_entry) + + XATTR_NAME_MAX + 1 > PAGE_SIZE); + + alloclen = sizeof(struct nfs4_xattr_entry); + if (name != NULL) { + slen = strlen(name) + 1; + alloclen += slen; + } else + slen = 0; + + if (alloclen + len <= PAGE_SIZE) { + alloclen += len; + flags = 0; + } else { + flags = NFS4_XATTR_ENTRY_EXTVAL; + } + + buf = kmalloc(alloclen, GFP_KERNEL_ACCOUNT | GFP_NOFS); + if (buf == NULL) + return NULL; + entry = (struct nfs4_xattr_entry *)buf; + + if (name != NULL) { + namep = buf + sizeof(struct nfs4_xattr_entry); + memcpy(namep, name, slen); + } else { + namep = NULL; + } + + + if (flags & NFS4_XATTR_ENTRY_EXTVAL) { + valp = kvmalloc(len, GFP_KERNEL_ACCOUNT | GFP_NOFS); + if (valp == NULL) { + kfree(buf); + return NULL; + } + } else if (len != 0) { + valp = buf + sizeof(struct nfs4_xattr_entry) + slen; + } else + valp = NULL; + + if (valp != NULL) { + if (value != NULL) + memcpy(valp, value, len); + else + _copy_from_pages(valp, pages, 0, len); + } + + entry->flags = flags; + entry->xattr_value = valp; + kref_init(&entry->ref); + entry->xattr_name = namep; + entry->xattr_size = len; + entry->bucket = NULL; + INIT_LIST_HEAD(&entry->lru); + INIT_LIST_HEAD(&entry->dispose); + INIT_HLIST_NODE(&entry->hnode); + + return entry; +} + +static void +nfs4_xattr_free_entry(struct nfs4_xattr_entry *entry) +{ + if (entry->flags & NFS4_XATTR_ENTRY_EXTVAL) + kvfree(entry->xattr_value); + kfree(entry); +} + +static void +nfs4_xattr_free_entry_cb(struct kref *kref) +{ + struct nfs4_xattr_entry *entry; + + entry = container_of(kref, struct nfs4_xattr_entry, ref); + + if (WARN_ON(!list_empty(&entry->lru))) + return; + + nfs4_xattr_free_entry(entry); +} + +static void +nfs4_xattr_free_cache_cb(struct kref *kref) +{ + struct nfs4_xattr_cache *cache; + int i; + + cache = container_of(kref, struct nfs4_xattr_cache, ref); + + for (i = 0; i < NFS4_XATTR_HASH_SIZE; i++) { + if (WARN_ON(!hlist_empty(&cache->buckets[i].hlist))) + return; + cache->buckets[i].draining = false; + } + + cache->listxattr = NULL; + + kmem_cache_free(nfs4_xattr_cache_cachep, cache); + +} + +static struct nfs4_xattr_cache * +nfs4_xattr_alloc_cache(void) +{ + struct nfs4_xattr_cache *cache; + + cache = kmem_cache_alloc(nfs4_xattr_cache_cachep, + GFP_KERNEL_ACCOUNT | GFP_NOFS); + if (cache == NULL) + return NULL; + + kref_init(&cache->ref); + atomic_long_set(&cache->nent, 0); + + return cache; +} + +/* + * Set the listxattr cache, which is a special-cased cache entry. + * The special value ERR_PTR(-ESTALE) is used to indicate that + * the cache is being drained - this prevents a new listxattr + * cache from being added to what is now a stale cache. + */ +static int +nfs4_xattr_set_listcache(struct nfs4_xattr_cache *cache, + struct nfs4_xattr_entry *new) +{ + struct nfs4_xattr_entry *old; + int ret = 1; + + spin_lock(&cache->listxattr_lock); + + old = cache->listxattr; + + if (old == ERR_PTR(-ESTALE)) { + ret = 0; + goto out; + } + + cache->listxattr = new; + if (new != NULL && new != ERR_PTR(-ESTALE)) + nfs4_xattr_entry_lru_add(new); + + if (old != NULL) { + nfs4_xattr_entry_lru_del(old); + kref_put(&old->ref, nfs4_xattr_free_entry_cb); + } +out: + spin_unlock(&cache->listxattr_lock); + + return ret; +} + +/* + * Unlink a cache from its parent inode, clearing out an invalid + * cache. Must be called with i_lock held. + */ +static struct nfs4_xattr_cache * +nfs4_xattr_cache_unlink(struct inode *inode) +{ + struct nfs_inode *nfsi; + struct nfs4_xattr_cache *oldcache; + + nfsi = NFS_I(inode); + + oldcache = nfsi->xattr_cache; + if (oldcache != NULL) { + list_lru_del(&nfs4_xattr_cache_lru, &oldcache->lru); + oldcache->inode = NULL; + } + nfsi->xattr_cache = NULL; + nfsi->cache_validity &= ~NFS_INO_INVALID_XATTR; + + return oldcache; + +} + +/* + * Discard a cache. Called by get_cache() if there was an old, + * invalid cache. Can also be called from a shrinker callback. + * + * The cache is dead, it has already been unlinked from its inode, + * and no longer appears on the cache LRU list. + * + * Mark all buckets as draining, so that no new entries are added. This + * could still happen in the unlikely, but possible case that another + * thread had grabbed a reference before it was unlinked from the inode, + * and is still holding it for an add operation. + * + * Remove all entries from the LRU lists, so that there is no longer + * any way to 'find' this cache. Then, remove the entries from the hash + * table. + * + * At that point, the cache will remain empty and can be freed when the final + * reference drops, which is very likely the kref_put at the end of + * this function, or the one called immediately afterwards in the + * shrinker callback. + */ +static void +nfs4_xattr_discard_cache(struct nfs4_xattr_cache *cache) +{ + unsigned int i; + struct nfs4_xattr_entry *entry; + struct nfs4_xattr_bucket *bucket; + struct hlist_node *n; + + nfs4_xattr_set_listcache(cache, ERR_PTR(-ESTALE)); + + for (i = 0; i < NFS4_XATTR_HASH_SIZE; i++) { + bucket = &cache->buckets[i]; + + spin_lock(&bucket->lock); + bucket->draining = true; + hlist_for_each_entry_safe(entry, n, &bucket->hlist, hnode) { + nfs4_xattr_entry_lru_del(entry); + hlist_del_init(&entry->hnode); + kref_put(&entry->ref, nfs4_xattr_free_entry_cb); + } + spin_unlock(&bucket->lock); + } + + atomic_long_set(&cache->nent, 0); + + kref_put(&cache->ref, nfs4_xattr_free_cache_cb); +} + +/* + * Get a referenced copy of the cache structure. Avoid doing allocs + * while holding i_lock. Which means that we do some optimistic allocation, + * and might have to free the result in rare cases. + * + * This function only checks the NFS_INO_INVALID_XATTR cache validity bit + * and acts accordingly, replacing the cache when needed. For the read case + * (!add), this means that the caller must make sure that the cache + * is valid before caling this function. getxattr and listxattr call + * revalidate_inode to do this. The attribute cache timeout (for the + * non-delegated case) is expected to be dealt with in the revalidate + * call. + */ + +static struct nfs4_xattr_cache * +nfs4_xattr_get_cache(struct inode *inode, int add) +{ + struct nfs_inode *nfsi; + struct nfs4_xattr_cache *cache, *oldcache, *newcache; + + nfsi = NFS_I(inode); + + cache = oldcache = NULL; + + spin_lock(&inode->i_lock); + + if (nfsi->cache_validity & NFS_INO_INVALID_XATTR) + oldcache = nfs4_xattr_cache_unlink(inode); + else + cache = nfsi->xattr_cache; + + if (cache != NULL) + kref_get(&cache->ref); + + spin_unlock(&inode->i_lock); + + if (add && cache == NULL) { + newcache = NULL; + + cache = nfs4_xattr_alloc_cache(); + if (cache == NULL) + goto out; + + spin_lock(&inode->i_lock); + if (nfsi->cache_validity & NFS_INO_INVALID_XATTR) { + /* + * The cache was invalidated again. Give up, + * since what we want to enter is now likely + * outdated anyway. + */ + spin_unlock(&inode->i_lock); + kref_put(&cache->ref, nfs4_xattr_free_cache_cb); + cache = NULL; + goto out; + } + + /* + * Check if someone beat us to it. + */ + if (nfsi->xattr_cache != NULL) { + newcache = nfsi->xattr_cache; + kref_get(&newcache->ref); + } else { + kref_get(&cache->ref); + nfsi->xattr_cache = cache; + cache->inode = inode; + list_lru_add(&nfs4_xattr_cache_lru, &cache->lru); + } + + spin_unlock(&inode->i_lock); + + /* + * If there was a race, throw away the cache we just + * allocated, and use the new one allocated by someone + * else. + */ + if (newcache != NULL) { + kref_put(&cache->ref, nfs4_xattr_free_cache_cb); + cache = newcache; + } + } + +out: + /* + * Discard the now orphaned old cache. + */ + if (oldcache != NULL) + nfs4_xattr_discard_cache(oldcache); + + return cache; +} + +static inline struct nfs4_xattr_bucket * +nfs4_xattr_hash_bucket(struct nfs4_xattr_cache *cache, const char *name) +{ + return &cache->buckets[jhash(name, strlen(name), 0) & + (ARRAY_SIZE(cache->buckets) - 1)]; +} + +static struct nfs4_xattr_entry * +nfs4_xattr_get_entry(struct nfs4_xattr_bucket *bucket, const char *name) +{ + struct nfs4_xattr_entry *entry; + + entry = NULL; + + hlist_for_each_entry(entry, &bucket->hlist, hnode) { + if (!strcmp(entry->xattr_name, name)) + break; + } + + return entry; +} + +static int +nfs4_xattr_hash_add(struct nfs4_xattr_cache *cache, + struct nfs4_xattr_entry *entry) +{ + struct nfs4_xattr_bucket *bucket; + struct nfs4_xattr_entry *oldentry = NULL; + int ret = 1; + + bucket = nfs4_xattr_hash_bucket(cache, entry->xattr_name); + entry->bucket = bucket; + + spin_lock(&bucket->lock); + + if (bucket->draining) { + ret = 0; + goto out; + } + + oldentry = nfs4_xattr_get_entry(bucket, entry->xattr_name); + if (oldentry != NULL) { + hlist_del_init(&oldentry->hnode); + nfs4_xattr_entry_lru_del(oldentry); + } else { + atomic_long_inc(&cache->nent); + } + + hlist_add_head(&entry->hnode, &bucket->hlist); + nfs4_xattr_entry_lru_add(entry); + +out: + spin_unlock(&bucket->lock); + + if (oldentry != NULL) + kref_put(&oldentry->ref, nfs4_xattr_free_entry_cb); + + return ret; +} + +static void +nfs4_xattr_hash_remove(struct nfs4_xattr_cache *cache, const char *name) +{ + struct nfs4_xattr_bucket *bucket; + struct nfs4_xattr_entry *entry; + + bucket = nfs4_xattr_hash_bucket(cache, name); + + spin_lock(&bucket->lock); + + entry = nfs4_xattr_get_entry(bucket, name); + if (entry != NULL) { + hlist_del_init(&entry->hnode); + nfs4_xattr_entry_lru_del(entry); + atomic_long_dec(&cache->nent); + } + + spin_unlock(&bucket->lock); + + if (entry != NULL) + kref_put(&entry->ref, nfs4_xattr_free_entry_cb); +} + +static struct nfs4_xattr_entry * +nfs4_xattr_hash_find(struct nfs4_xattr_cache *cache, const char *name) +{ + struct nfs4_xattr_bucket *bucket; + struct nfs4_xattr_entry *entry; + + bucket = nfs4_xattr_hash_bucket(cache, name); + + spin_lock(&bucket->lock); + + entry = nfs4_xattr_get_entry(bucket, name); + if (entry != NULL) + kref_get(&entry->ref); + + spin_unlock(&bucket->lock); + + return entry; +} + +/* + * Entry point to retrieve an entry from the cache. + */ +ssize_t nfs4_xattr_cache_get(struct inode *inode, const char *name, char *buf, + ssize_t buflen) +{ + struct nfs4_xattr_cache *cache; + struct nfs4_xattr_entry *entry; + ssize_t ret; + + cache = nfs4_xattr_get_cache(inode, 0); + if (cache == NULL) + return -ENOENT; + + ret = 0; + entry = nfs4_xattr_hash_find(cache, name); + + if (entry != NULL) { + dprintk("%s: cache hit '%s', len %lu\n", __func__, + entry->xattr_name, (unsigned long)entry->xattr_size); + if (buflen == 0) { + /* Length probe only */ + ret = entry->xattr_size; + } else if (buflen < entry->xattr_size) + ret = -ERANGE; + else { + memcpy(buf, entry->xattr_value, entry->xattr_size); + ret = entry->xattr_size; + } + kref_put(&entry->ref, nfs4_xattr_free_entry_cb); + } else { + dprintk("%s: cache miss '%s'\n", __func__, name); + ret = -ENOENT; + } + + kref_put(&cache->ref, nfs4_xattr_free_cache_cb); + + return ret; +} + +/* + * Retrieve a cached list of xattrs from the cache. + */ +ssize_t nfs4_xattr_cache_list(struct inode *inode, char *buf, ssize_t buflen) +{ + struct nfs4_xattr_cache *cache; + struct nfs4_xattr_entry *entry; + ssize_t ret; + + cache = nfs4_xattr_get_cache(inode, 0); + if (cache == NULL) + return -ENOENT; + + spin_lock(&cache->listxattr_lock); + + entry = cache->listxattr; + + if (entry != NULL && entry != ERR_PTR(-ESTALE)) { + if (buflen == 0) { + /* Length probe only */ + ret = entry->xattr_size; + } else if (entry->xattr_size > buflen) + ret = -ERANGE; + else { + memcpy(buf, entry->xattr_value, entry->xattr_size); + ret = entry->xattr_size; + } + } else { + ret = -ENOENT; + } + + spin_unlock(&cache->listxattr_lock); + + kref_put(&cache->ref, nfs4_xattr_free_cache_cb); + + return ret; +} + +/* + * Add an xattr to the cache. + * + * This also invalidates the xattr list cache. + */ +void nfs4_xattr_cache_add(struct inode *inode, const char *name, + const char *buf, struct page **pages, ssize_t buflen) +{ + struct nfs4_xattr_cache *cache; + struct nfs4_xattr_entry *entry; + + dprintk("%s: add '%s' len %lu\n", __func__, + name, (unsigned long)buflen); + + cache = nfs4_xattr_get_cache(inode, 1); + if (cache == NULL) + return; + + entry = nfs4_xattr_alloc_entry(name, buf, pages, buflen); + if (entry == NULL) + goto out; + + (void)nfs4_xattr_set_listcache(cache, NULL); + + if (!nfs4_xattr_hash_add(cache, entry)) + kref_put(&entry->ref, nfs4_xattr_free_entry_cb); + +out: + kref_put(&cache->ref, nfs4_xattr_free_cache_cb); +} + + +/* + * Remove an xattr from the cache. + * + * This also invalidates the xattr list cache. + */ +void nfs4_xattr_cache_remove(struct inode *inode, const char *name) +{ + struct nfs4_xattr_cache *cache; + + dprintk("%s: remove '%s'\n", __func__, name); + + cache = nfs4_xattr_get_cache(inode, 0); + if (cache == NULL) + return; + + (void)nfs4_xattr_set_listcache(cache, NULL); + nfs4_xattr_hash_remove(cache, name); + + kref_put(&cache->ref, nfs4_xattr_free_cache_cb); +} + +/* + * Cache listxattr output, replacing any possible old one. + */ +void nfs4_xattr_cache_set_list(struct inode *inode, const char *buf, + ssize_t buflen) +{ + struct nfs4_xattr_cache *cache; + struct nfs4_xattr_entry *entry; + + cache = nfs4_xattr_get_cache(inode, 1); + if (cache == NULL) + return; + + entry = nfs4_xattr_alloc_entry(NULL, buf, NULL, buflen); + if (entry == NULL) + goto out; + + /* + * This is just there to be able to get to bucket->cache, + * which is obviously the same for all buckets, so just + * use bucket 0. + */ + entry->bucket = &cache->buckets[0]; + + if (!nfs4_xattr_set_listcache(cache, entry)) + kref_put(&entry->ref, nfs4_xattr_free_entry_cb); + +out: + kref_put(&cache->ref, nfs4_xattr_free_cache_cb); +} + +/* + * Zap the entire cache. Called when an inode is evicted. + */ +void nfs4_xattr_cache_zap(struct inode *inode) +{ + struct nfs4_xattr_cache *oldcache; + + spin_lock(&inode->i_lock); + oldcache = nfs4_xattr_cache_unlink(inode); + spin_unlock(&inode->i_lock); + + if (oldcache) + nfs4_xattr_discard_cache(oldcache); +} + +/* + * The entry LRU is shrunk more aggressively than the cache LRU, + * by settings @seeks to 1. + * + * Cache structures are freed only when they've become empty, after + * pruning all but one entry. + */ + +static unsigned long nfs4_xattr_cache_count(struct shrinker *shrink, + struct shrink_control *sc); +static unsigned long nfs4_xattr_entry_count(struct shrinker *shrink, + struct shrink_control *sc); +static unsigned long nfs4_xattr_cache_scan(struct shrinker *shrink, + struct shrink_control *sc); +static unsigned long nfs4_xattr_entry_scan(struct shrinker *shrink, + struct shrink_control *sc); + +static struct shrinker nfs4_xattr_cache_shrinker = { + .count_objects = nfs4_xattr_cache_count, + .scan_objects = nfs4_xattr_cache_scan, + .seeks = DEFAULT_SEEKS, + .flags = SHRINKER_MEMCG_AWARE, +}; + +static struct shrinker nfs4_xattr_entry_shrinker = { + .count_objects = nfs4_xattr_entry_count, + .scan_objects = nfs4_xattr_entry_scan, + .seeks = DEFAULT_SEEKS, + .batch = 512, + .flags = SHRINKER_MEMCG_AWARE, +}; + +static struct shrinker nfs4_xattr_large_entry_shrinker = { + .count_objects = nfs4_xattr_entry_count, + .scan_objects = nfs4_xattr_entry_scan, + .seeks = 1, + .batch = 512, + .flags = SHRINKER_MEMCG_AWARE, +}; + +static enum lru_status +cache_lru_isolate(struct list_head *item, + struct list_lru_one *lru, spinlock_t *lru_lock, void *arg) +{ + struct list_head *dispose = arg; + struct inode *inode; + struct nfs4_xattr_cache *cache = container_of(item, + struct nfs4_xattr_cache, lru); + + if (atomic_long_read(&cache->nent) > 1) + return LRU_SKIP; + + /* + * If a cache structure is on the LRU list, we know that + * its inode is valid. Try to lock it to break the link. + * Since we're inverting the lock order here, only try. + */ + inode = cache->inode; + + if (!spin_trylock(&inode->i_lock)) + return LRU_SKIP; + + kref_get(&cache->ref); + + cache->inode = NULL; + NFS_I(inode)->xattr_cache = NULL; + NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_XATTR; + list_lru_isolate(lru, &cache->lru); + + spin_unlock(&inode->i_lock); + + list_add_tail(&cache->dispose, dispose); + return LRU_REMOVED; +} + +static unsigned long +nfs4_xattr_cache_scan(struct shrinker *shrink, struct shrink_control *sc) +{ + LIST_HEAD(dispose); + unsigned long freed; + struct nfs4_xattr_cache *cache; + + freed = list_lru_shrink_walk(&nfs4_xattr_cache_lru, sc, + cache_lru_isolate, &dispose); + while (!list_empty(&dispose)) { + cache = list_first_entry(&dispose, struct nfs4_xattr_cache, + dispose); + list_del_init(&cache->dispose); + nfs4_xattr_discard_cache(cache); + kref_put(&cache->ref, nfs4_xattr_free_cache_cb); + } + + return freed; +} + + +static unsigned long +nfs4_xattr_cache_count(struct shrinker *shrink, struct shrink_control *sc) +{ + unsigned long count; + + count = list_lru_count(&nfs4_xattr_cache_lru); + return vfs_pressure_ratio(count); +} + +static enum lru_status +entry_lru_isolate(struct list_head *item, + struct list_lru_one *lru, spinlock_t *lru_lock, void *arg) +{ + struct list_head *dispose = arg; + struct nfs4_xattr_bucket *bucket; + struct nfs4_xattr_cache *cache; + struct nfs4_xattr_entry *entry = container_of(item, + struct nfs4_xattr_entry, lru); + + bucket = entry->bucket; + cache = bucket->cache; + + /* + * Unhook the entry from its parent (either a cache bucket + * or a cache structure if it's a listxattr buf), so that + * it's no longer found. Then add it to the isolate list, + * to be freed later. + * + * In both cases, we're reverting lock order, so use + * trylock and skip the entry if we can't get the lock. + */ + if (entry->xattr_name != NULL) { + /* Regular cache entry */ + if (!spin_trylock(&bucket->lock)) + return LRU_SKIP; + + kref_get(&entry->ref); + + hlist_del_init(&entry->hnode); + atomic_long_dec(&cache->nent); + list_lru_isolate(lru, &entry->lru); + + spin_unlock(&bucket->lock); + } else { + /* Listxattr cache entry */ + if (!spin_trylock(&cache->listxattr_lock)) + return LRU_SKIP; + + kref_get(&entry->ref); + + cache->listxattr = NULL; + list_lru_isolate(lru, &entry->lru); + + spin_unlock(&cache->listxattr_lock); + } + + list_add_tail(&entry->dispose, dispose); + return LRU_REMOVED; +} + +static unsigned long +nfs4_xattr_entry_scan(struct shrinker *shrink, struct shrink_control *sc) +{ + LIST_HEAD(dispose); + unsigned long freed; + struct nfs4_xattr_entry *entry; + struct list_lru *lru; + + lru = (shrink == &nfs4_xattr_large_entry_shrinker) ? + &nfs4_xattr_large_entry_lru : &nfs4_xattr_entry_lru; + + freed = list_lru_shrink_walk(lru, sc, entry_lru_isolate, &dispose); + + while (!list_empty(&dispose)) { + entry = list_first_entry(&dispose, struct nfs4_xattr_entry, + dispose); + list_del_init(&entry->dispose); + + /* + * Drop two references: the one that we just grabbed + * in entry_lru_isolate, and the one that was set + * when the entry was first allocated. + */ + kref_put(&entry->ref, nfs4_xattr_free_entry_cb); + kref_put(&entry->ref, nfs4_xattr_free_entry_cb); + } + + return freed; +} + +static unsigned long +nfs4_xattr_entry_count(struct shrinker *shrink, struct shrink_control *sc) +{ + unsigned long count; + struct list_lru *lru; + + lru = (shrink == &nfs4_xattr_large_entry_shrinker) ? + &nfs4_xattr_large_entry_lru : &nfs4_xattr_entry_lru; + + count = list_lru_count(lru); + return vfs_pressure_ratio(count); +} + + +static void nfs4_xattr_cache_init_once(void *p) +{ + struct nfs4_xattr_cache *cache = (struct nfs4_xattr_cache *)p; + + spin_lock_init(&cache->listxattr_lock); + atomic_long_set(&cache->nent, 0); + nfs4_xattr_hash_init(cache); + cache->listxattr = NULL; + INIT_LIST_HEAD(&cache->lru); + INIT_LIST_HEAD(&cache->dispose); +} + +int __init nfs4_xattr_cache_init(void) +{ + int ret = 0; + + nfs4_xattr_cache_cachep = kmem_cache_create("nfs4_xattr_cache_cache", + sizeof(struct nfs4_xattr_cache), 0, + (SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|SLAB_ACCOUNT), + nfs4_xattr_cache_init_once); + if (nfs4_xattr_cache_cachep == NULL) + return -ENOMEM; + + ret = list_lru_init_memcg(&nfs4_xattr_large_entry_lru, + &nfs4_xattr_large_entry_shrinker); + if (ret) + goto out4; + + ret = list_lru_init_memcg(&nfs4_xattr_entry_lru, + &nfs4_xattr_entry_shrinker); + if (ret) + goto out3; + + ret = list_lru_init_memcg(&nfs4_xattr_cache_lru, + &nfs4_xattr_cache_shrinker); + if (ret) + goto out2; + + ret = register_shrinker(&nfs4_xattr_cache_shrinker); + if (ret) + goto out1; + + ret = register_shrinker(&nfs4_xattr_entry_shrinker); + if (ret) + goto out; + + ret = register_shrinker(&nfs4_xattr_large_entry_shrinker); + if (!ret) + return 0; + + unregister_shrinker(&nfs4_xattr_entry_shrinker); +out: + unregister_shrinker(&nfs4_xattr_cache_shrinker); +out1: + list_lru_destroy(&nfs4_xattr_cache_lru); +out2: + list_lru_destroy(&nfs4_xattr_entry_lru); +out3: + list_lru_destroy(&nfs4_xattr_large_entry_lru); +out4: + kmem_cache_destroy(nfs4_xattr_cache_cachep); + + return ret; +} + +void nfs4_xattr_cache_exit(void) +{ + unregister_shrinker(&nfs4_xattr_entry_shrinker); + unregister_shrinker(&nfs4_xattr_cache_shrinker); + list_lru_destroy(&nfs4_xattr_entry_lru); + list_lru_destroy(&nfs4_xattr_cache_lru); + kmem_cache_destroy(nfs4_xattr_cache_cachep); +} diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c index c03f3246d6c5..cc50085e151c 100644 --- a/fs/nfs/nfs42xdr.c +++ b/fs/nfs/nfs42xdr.c @@ -169,6 +169,78 @@ decode_clone_maxsz + \ decode_getattr_maxsz) +/* Not limited by NFS itself, limited by the generic xattr code */ +#define nfs4_xattr_name_maxsz XDR_QUADLEN(XATTR_NAME_MAX) + +#define encode_getxattr_maxsz (op_encode_hdr_maxsz + 1 + \ + nfs4_xattr_name_maxsz) +#define decode_getxattr_maxsz (op_decode_hdr_maxsz + 1 + 1) +#define encode_setxattr_maxsz (op_encode_hdr_maxsz + \ + 1 + nfs4_xattr_name_maxsz + 1) +#define decode_setxattr_maxsz (op_decode_hdr_maxsz + decode_change_info_maxsz) +#define encode_listxattrs_maxsz (op_encode_hdr_maxsz + 2 + 1) +#define decode_listxattrs_maxsz (op_decode_hdr_maxsz + 2 + 1 + 1) +#define encode_removexattr_maxsz (op_encode_hdr_maxsz + 1 + \ + nfs4_xattr_name_maxsz) +#define decode_removexattr_maxsz (op_decode_hdr_maxsz + \ + decode_change_info_maxsz) + +#define NFS4_enc_getxattr_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_getxattr_maxsz) +#define NFS4_dec_getxattr_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_getxattr_maxsz) +#define NFS4_enc_setxattr_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_setxattr_maxsz) +#define NFS4_dec_setxattr_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_setxattr_maxsz) +#define NFS4_enc_listxattrs_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_listxattrs_maxsz) +#define NFS4_dec_listxattrs_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_listxattrs_maxsz) +#define NFS4_enc_removexattr_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_removexattr_maxsz) +#define NFS4_dec_removexattr_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_removexattr_maxsz) + +/* + * These values specify the maximum amount of data that is not + * associated with the extended attribute name or extended + * attribute list in the SETXATTR, GETXATTR and LISTXATTR + * respectively. + */ +const u32 nfs42_maxsetxattr_overhead = ((RPC_MAX_HEADER_WITH_AUTH + + compound_encode_hdr_maxsz + + encode_sequence_maxsz + + encode_putfh_maxsz + 1 + + nfs4_xattr_name_maxsz) + * XDR_UNIT); + +const u32 nfs42_maxgetxattr_overhead = ((RPC_MAX_HEADER_WITH_AUTH + + compound_decode_hdr_maxsz + + decode_sequence_maxsz + + decode_putfh_maxsz + 1) * XDR_UNIT); + +const u32 nfs42_maxlistxattrs_overhead = ((RPC_MAX_HEADER_WITH_AUTH + + compound_decode_hdr_maxsz + + decode_sequence_maxsz + + decode_putfh_maxsz + 3) * XDR_UNIT); + static void encode_fallocate(struct xdr_stream *xdr, const struct nfs42_falloc_args *args) { @@ -333,6 +405,210 @@ static void encode_layouterror(struct xdr_stream *xdr, encode_device_error(xdr, &args->errors[0]); } +static void encode_setxattr(struct xdr_stream *xdr, + const struct nfs42_setxattrargs *arg, + struct compound_hdr *hdr) +{ + __be32 *p; + + BUILD_BUG_ON(XATTR_CREATE != SETXATTR4_CREATE); + BUILD_BUG_ON(XATTR_REPLACE != SETXATTR4_REPLACE); + + encode_op_hdr(xdr, OP_SETXATTR, decode_setxattr_maxsz, hdr); + p = reserve_space(xdr, 4); + *p = cpu_to_be32(arg->xattr_flags); + encode_string(xdr, strlen(arg->xattr_name), arg->xattr_name); + p = reserve_space(xdr, 4); + *p = cpu_to_be32(arg->xattr_len); + if (arg->xattr_len) + xdr_write_pages(xdr, arg->xattr_pages, 0, arg->xattr_len); +} + +static int decode_setxattr(struct xdr_stream *xdr, + struct nfs4_change_info *cinfo) +{ + int status; + + status = decode_op_hdr(xdr, OP_SETXATTR); + if (status) + goto out; + status = decode_change_info(xdr, cinfo); +out: + return status; +} + + +static void encode_getxattr(struct xdr_stream *xdr, const char *name, + struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_GETXATTR, decode_getxattr_maxsz, hdr); + encode_string(xdr, strlen(name), name); +} + +static int decode_getxattr(struct xdr_stream *xdr, + struct nfs42_getxattrres *res, + struct rpc_rqst *req) +{ + int status; + __be32 *p; + u32 len, rdlen; + + status = decode_op_hdr(xdr, OP_GETXATTR); + if (status) + return status; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + return -EIO; + + len = be32_to_cpup(p); + if (len > req->rq_rcv_buf.page_len) + return -ERANGE; + + res->xattr_len = len; + + if (len > 0) { + rdlen = xdr_read_pages(xdr, len); + if (rdlen < len) + return -EIO; + } + + return 0; +} + +static void encode_removexattr(struct xdr_stream *xdr, const char *name, + struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_REMOVEXATTR, decode_removexattr_maxsz, hdr); + encode_string(xdr, strlen(name), name); +} + + +static int decode_removexattr(struct xdr_stream *xdr, + struct nfs4_change_info *cinfo) +{ + int status; + + status = decode_op_hdr(xdr, OP_REMOVEXATTR); + if (status) + goto out; + + status = decode_change_info(xdr, cinfo); +out: + return status; +} + +static void encode_listxattrs(struct xdr_stream *xdr, + const struct nfs42_listxattrsargs *arg, + struct compound_hdr *hdr) +{ + __be32 *p; + + encode_op_hdr(xdr, OP_LISTXATTRS, decode_listxattrs_maxsz + 1, hdr); + + p = reserve_space(xdr, 12); + if (unlikely(!p)) + return; + + p = xdr_encode_hyper(p, arg->cookie); + /* + * RFC 8276 says to specify the full max length of the LISTXATTRS + * XDR reply. Count is set to the XDR length of the names array + * plus the EOF marker. So, add the cookie and the names count. + */ + *p = cpu_to_be32(arg->count + 8 + 4); +} + +static int decode_listxattrs(struct xdr_stream *xdr, + struct nfs42_listxattrsres *res) +{ + int status; + __be32 *p; + u32 count, len, ulen; + size_t left, copied; + char *buf; + + status = decode_op_hdr(xdr, OP_LISTXATTRS); + if (status) { + /* + * Special case: for LISTXATTRS, NFS4ERR_TOOSMALL + * should be translated to ERANGE. + */ + if (status == -ETOOSMALL) + status = -ERANGE; + goto out; + } + + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + return -EIO; + + xdr_decode_hyper(p, &res->cookie); + + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + return -EIO; + + left = res->xattr_len; + buf = res->xattr_buf; + + count = be32_to_cpup(p); + copied = 0; + + /* + * We have asked for enough room to encode the maximum number + * of possible attribute names, so everything should fit. + * + * But, don't rely on that assumption. Just decode entries + * until they don't fit anymore, just in case the server did + * something odd. + */ + while (count--) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + return -EIO; + + len = be32_to_cpup(p); + if (len > (XATTR_NAME_MAX - XATTR_USER_PREFIX_LEN)) { + status = -ERANGE; + goto out; + } + + p = xdr_inline_decode(xdr, len); + if (unlikely(!p)) + return -EIO; + + ulen = len + XATTR_USER_PREFIX_LEN + 1; + if (buf) { + if (ulen > left) { + status = -ERANGE; + goto out; + } + + memcpy(buf, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN); + memcpy(buf + XATTR_USER_PREFIX_LEN, p, len); + + buf[ulen - 1] = 0; + buf += ulen; + left -= ulen; + } + copied += ulen; + } + + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + return -EIO; + + res->eof = be32_to_cpup(p); + res->copied = copied; + +out: + if (status == -ERANGE && res->xattr_len == XATTR_LIST_MAX) + status = -E2BIG; + + return status; +} + /* * Encode ALLOCATE request */ @@ -988,4 +1264,166 @@ out: return status; } +#ifdef CONFIG_NFS_V4_2 +static void nfs4_xdr_enc_setxattr(struct rpc_rqst *req, struct xdr_stream *xdr, + const void *data) +{ + const struct nfs42_setxattrargs *args = data; + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->fh, &hdr); + encode_setxattr(xdr, args, &hdr); + encode_nops(&hdr); +} + +static int nfs4_xdr_dec_setxattr(struct rpc_rqst *req, struct xdr_stream *xdr, + void *data) +{ + struct nfs42_setxattrres *res = data; + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, req); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + + status = decode_setxattr(xdr, &res->cinfo); +out: + return status; +} + +static void nfs4_xdr_enc_getxattr(struct rpc_rqst *req, struct xdr_stream *xdr, + const void *data) +{ + const struct nfs42_getxattrargs *args = data; + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + size_t plen; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->fh, &hdr); + encode_getxattr(xdr, args->xattr_name, &hdr); + + plen = args->xattr_len ? args->xattr_len : XATTR_SIZE_MAX; + + rpc_prepare_reply_pages(req, args->xattr_pages, 0, plen, + hdr.replen); + req->rq_rcv_buf.flags |= XDRBUF_SPARSE_PAGES; + + encode_nops(&hdr); +} + +static int nfs4_xdr_dec_getxattr(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, void *data) +{ + struct nfs42_getxattrres *res = data; + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_getxattr(xdr, res, rqstp); +out: + return status; +} + +static void nfs4_xdr_enc_listxattrs(struct rpc_rqst *req, + struct xdr_stream *xdr, const void *data) +{ + const struct nfs42_listxattrsargs *args = data; + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->fh, &hdr); + encode_listxattrs(xdr, args, &hdr); + + rpc_prepare_reply_pages(req, args->xattr_pages, 0, args->count, + hdr.replen); + req->rq_rcv_buf.flags |= XDRBUF_SPARSE_PAGES; + + encode_nops(&hdr); +} + +static int nfs4_xdr_dec_listxattrs(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, void *data) +{ + struct nfs42_listxattrsres *res = data; + struct compound_hdr hdr; + int status; + + xdr_set_scratch_buffer(xdr, page_address(res->scratch), PAGE_SIZE); + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_listxattrs(xdr, res); +out: + return status; +} + +static void nfs4_xdr_enc_removexattr(struct rpc_rqst *req, + struct xdr_stream *xdr, const void *data) +{ + const struct nfs42_removexattrargs *args = data; + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->fh, &hdr); + encode_removexattr(xdr, args->xattr_name, &hdr); + encode_nops(&hdr); +} + +static int nfs4_xdr_dec_removexattr(struct rpc_rqst *req, + struct xdr_stream *xdr, void *data) +{ + struct nfs42_removexattrres *res = data; + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, req); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + + status = decode_removexattr(xdr, &res->cinfo); +out: + return status; +} +#endif #endif /* __LINUX_FS_NFS_NFS4_2XDR_H */ diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 2b7f6dcd2eb8..0c9505dc852c 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -117,7 +117,7 @@ struct nfs4_state_owner { unsigned long so_flags; struct list_head so_states; struct nfs_seqid_counter so_seqid; - seqcount_t so_reclaim_seqcount; + seqcount_spinlock_t so_reclaim_seqcount; struct mutex so_delegreturn_mutex; }; @@ -324,6 +324,13 @@ extern int update_open_stateid(struct nfs4_state *state, extern int nfs4_proc_get_lease_time(struct nfs_client *clp, struct nfs_fsinfo *fsinfo); +extern void nfs4_update_changeattr(struct inode *dir, + struct nfs4_change_info *cinfo, + unsigned long timestamp, + unsigned long cache_validity); +extern int nfs4_buf_to_pages_noslab(const void *buf, size_t buflen, + struct page **pages); + #if defined(CONFIG_NFS_V4_1) extern int nfs41_sequence_done(struct rpc_task *, struct nfs4_sequence_res *); extern int nfs4_proc_create_session(struct nfs_client *, const struct cred *); @@ -557,6 +564,12 @@ static inline void nfs4_unregister_sysctl(void) /* nfs4xdr.c */ extern const struct rpc_procinfo nfs4_procedures[]; +#ifdef CONFIG_NFS_V4_2 +extern const u32 nfs42_maxsetxattr_overhead; +extern const u32 nfs42_maxgetxattr_overhead; +extern const u32 nfs42_maxlistxattrs_overhead; +#endif + struct nfs4_mount_data; /* callback_xdr.c */ @@ -613,12 +626,34 @@ static inline bool nfs4_state_match_open_stateid_other(const struct nfs4_state * nfs4_stateid_match_other(&state->open_stateid, stateid); } +/* nfs42xattr.c */ +#ifdef CONFIG_NFS_V4_2 +extern int __init nfs4_xattr_cache_init(void); +extern void nfs4_xattr_cache_exit(void); +extern void nfs4_xattr_cache_add(struct inode *inode, const char *name, + const char *buf, struct page **pages, + ssize_t buflen); +extern void nfs4_xattr_cache_remove(struct inode *inode, const char *name); +extern ssize_t nfs4_xattr_cache_get(struct inode *inode, const char *name, + char *buf, ssize_t buflen); +extern void nfs4_xattr_cache_set_list(struct inode *inode, const char *buf, + ssize_t buflen); +extern ssize_t nfs4_xattr_cache_list(struct inode *inode, char *buf, + ssize_t buflen); +extern void nfs4_xattr_cache_zap(struct inode *inode); #else +static inline void nfs4_xattr_cache_zap(struct inode *inode) +{ +} +#endif /* CONFIG_NFS_V4_2 */ + +#else /* CONFIG_NFS_V4 */ #define nfs4_close_state(a, b) do { } while (0) #define nfs4_close_sync(a, b) do { } while (0) #define nfs4_state_protect(a, b, c, d) do { } while (0) #define nfs4_state_protect_write(a, b, c, d) do { } while (0) + #endif /* CONFIG_NFS_V4 */ #endif /* __LINUX_FS_NFS_NFS4_FS.H */ diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 0bd77cc1f639..daacc78a3d48 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -880,7 +880,7 @@ static int nfs4_set_client(struct nfs_server *server, if (minorversion == 0) __set_bit(NFS_CS_REUSEPORT, &cl_init.init_flags); - else if (proto == XPRT_TRANSPORT_TCP) + if (proto == XPRT_TRANSPORT_TCP) cl_init.nconnect = nconnect; if (server->flags & NFS_MOUNT_NORESVPORT) @@ -992,6 +992,36 @@ static void nfs4_session_limit_rwsize(struct nfs_server *server) #endif /* CONFIG_NFS_V4_1 */ } +/* + * Limit xattr sizes using the channel attributes. + */ +static void nfs4_session_limit_xasize(struct nfs_server *server) +{ +#ifdef CONFIG_NFS_V4_2 + struct nfs4_session *sess; + u32 server_gxa_sz; + u32 server_sxa_sz; + u32 server_lxa_sz; + + if (!nfs4_has_session(server->nfs_client)) + return; + + sess = server->nfs_client->cl_session; + + server_gxa_sz = sess->fc_attrs.max_resp_sz - nfs42_maxgetxattr_overhead; + server_sxa_sz = sess->fc_attrs.max_rqst_sz - nfs42_maxsetxattr_overhead; + server_lxa_sz = sess->fc_attrs.max_resp_sz - + nfs42_maxlistxattrs_overhead; + + if (server->gxasize > server_gxa_sz) + server->gxasize = server_gxa_sz; + if (server->sxasize > server_sxa_sz) + server->sxasize = server_sxa_sz; + if (server->lxasize > server_lxa_sz) + server->lxasize = server_lxa_sz; +#endif +} + static int nfs4_server_common_setup(struct nfs_server *server, struct nfs_fh *mntfh, bool auth_probe) { @@ -1039,6 +1069,7 @@ static int nfs4_server_common_setup(struct nfs_server *server, goto out; nfs4_session_limit_rwsize(server); + nfs4_session_limit_xasize(server); if (server->namelen == 0 || server->namelen > NFS4_MAXNAMLEN) server->namelen = NFS4_MAXNAMLEN; diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 8e5d6223ddd3..a33970765467 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -110,6 +110,7 @@ static int nfs4_file_flush(struct file *file, fl_owner_t id) { struct inode *inode = file_inode(file); + errseq_t since; dprintk("NFS: flush(%pD2)\n", file); @@ -125,7 +126,9 @@ nfs4_file_flush(struct file *file, fl_owner_t id) return filemap_fdatawrite(file->f_mapping); /* Flush writes to the server and return any errors */ - return nfs_wb_all(inode); + since = filemap_sample_wb_err(file->f_mapping); + nfs_wb_all(inode); + return filemap_check_wb_err(file->f_mapping, since); } #ifdef CONFIG_NFS_V4_2 diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 8963062da57e..dbd01548335b 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -66,6 +66,7 @@ #include "nfs4idmap.h" #include "nfs4session.h" #include "fscache.h" +#include "nfs42.h" #include "nfs4trace.h" @@ -256,6 +257,7 @@ const u32 nfs4_fsinfo_bitmap[3] = { FATTR4_WORD0_MAXFILESIZE | FATTR4_WORD1_FS_LAYOUT_TYPES, FATTR4_WORD2_LAYOUT_BLKSIZE | FATTR4_WORD2_CLONE_BLKSIZE + | FATTR4_WORD2_XATTR_SUPPORT }; const u32 nfs4_fs_locations_bitmap[3] = { @@ -1173,37 +1175,49 @@ nfs4_dec_nlink_locked(struct inode *inode) } static void -update_changeattr_locked(struct inode *dir, struct nfs4_change_info *cinfo, +nfs4_update_changeattr_locked(struct inode *inode, + struct nfs4_change_info *cinfo, unsigned long timestamp, unsigned long cache_validity) { - struct nfs_inode *nfsi = NFS_I(dir); + struct nfs_inode *nfsi = NFS_I(inode); nfsi->cache_validity |= NFS_INO_INVALID_CTIME | NFS_INO_INVALID_MTIME - | NFS_INO_INVALID_DATA | cache_validity; - if (cinfo->atomic && cinfo->before == inode_peek_iversion_raw(dir)) { + + if (cinfo->atomic && cinfo->before == inode_peek_iversion_raw(inode)) { nfsi->cache_validity &= ~NFS_INO_REVAL_PAGECACHE; nfsi->attrtimeo_timestamp = jiffies; } else { - nfs_force_lookup_revalidate(dir); - if (cinfo->before != inode_peek_iversion_raw(dir)) + if (S_ISDIR(inode->i_mode)) { + nfsi->cache_validity |= NFS_INO_INVALID_DATA; + nfs_force_lookup_revalidate(inode); + } else { + if (!NFS_PROTO(inode)->have_delegation(inode, + FMODE_READ)) + nfsi->cache_validity |= NFS_INO_REVAL_PAGECACHE; + } + + if (cinfo->before != inode_peek_iversion_raw(inode)) nfsi->cache_validity |= NFS_INO_INVALID_ACCESS | - NFS_INO_INVALID_ACL; + NFS_INO_INVALID_ACL | + NFS_INO_INVALID_XATTR; } - inode_set_iversion_raw(dir, cinfo->after); + inode_set_iversion_raw(inode, cinfo->after); nfsi->read_cache_jiffies = timestamp; nfsi->attr_gencount = nfs_inc_attr_generation_counter(); nfsi->cache_validity &= ~NFS_INO_INVALID_CHANGE; - nfs_fscache_invalidate(dir); + + if (nfsi->cache_validity & NFS_INO_INVALID_DATA) + nfs_fscache_invalidate(inode); } -static void -update_changeattr(struct inode *dir, struct nfs4_change_info *cinfo, +void +nfs4_update_changeattr(struct inode *dir, struct nfs4_change_info *cinfo, unsigned long timestamp, unsigned long cache_validity) { spin_lock(&dir->i_lock); - update_changeattr_locked(dir, cinfo, timestamp, cache_validity); + nfs4_update_changeattr_locked(dir, cinfo, timestamp, cache_validity); spin_unlock(&dir->i_lock); } @@ -1356,6 +1370,12 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, NFS4_ACCESS_MODIFY | NFS4_ACCESS_EXTEND | NFS4_ACCESS_EXECUTE; +#ifdef CONFIG_NFS_V4_2 + if (server->caps & NFS_CAP_XATTR) + p->o_arg.access |= NFS4_ACCESS_XAREAD | + NFS4_ACCESS_XAWRITE | + NFS4_ACCESS_XALIST; +#endif } } p->o_arg.clientid = server->nfs_client->cl_clientid; @@ -2653,8 +2673,9 @@ static int _nfs4_proc_open(struct nfs4_opendata *data, data->file_created = true; if (data->file_created || inode_peek_iversion_raw(dir) != o_res->cinfo.after) - update_changeattr(dir, &o_res->cinfo, - o_res->f_attr->time_start, 0); + nfs4_update_changeattr(dir, &o_res->cinfo, + o_res->f_attr->time_start, + NFS_INO_INVALID_DATA); } if ((o_res->rflags & NFS4_OPEN_RESULT_LOCKTYPE_POSIX) == 0) server->caps &= ~NFS_CAP_POSIX_LOCK; @@ -3756,7 +3777,7 @@ static void nfs4_close_context(struct nfs_open_context *ctx, int is_sync) #define FATTR4_WORD1_NFS40_MASK (2*FATTR4_WORD1_MOUNTED_ON_FILEID - 1UL) #define FATTR4_WORD2_NFS41_MASK (2*FATTR4_WORD2_SUPPATTR_EXCLCREAT - 1UL) -#define FATTR4_WORD2_NFS42_MASK (2*FATTR4_WORD2_MODE_UMASK - 1UL) +#define FATTR4_WORD2_NFS42_MASK (2*FATTR4_WORD2_XATTR_SUPPORT - 1UL) static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle) { @@ -4540,7 +4561,8 @@ _nfs4_proc_remove(struct inode *dir, const struct qstr *name, u32 ftype) status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 1); if (status == 0) { spin_lock(&dir->i_lock); - update_changeattr_locked(dir, &res.cinfo, timestamp, 0); + nfs4_update_changeattr_locked(dir, &res.cinfo, timestamp, + NFS_INO_INVALID_DATA); /* Removing a directory decrements nlink in the parent */ if (ftype == NF4DIR && dir->i_nlink > 2) nfs4_dec_nlink_locked(dir); @@ -4624,8 +4646,9 @@ static int nfs4_proc_unlink_done(struct rpc_task *task, struct inode *dir) &data->timeout) == -EAGAIN) return 0; if (task->tk_status == 0) - update_changeattr(dir, &res->cinfo, - res->dir_attr->time_start, 0); + nfs4_update_changeattr(dir, &res->cinfo, + res->dir_attr->time_start, + NFS_INO_INVALID_DATA); return 1; } @@ -4669,16 +4692,18 @@ static int nfs4_proc_rename_done(struct rpc_task *task, struct inode *old_dir, if (task->tk_status == 0) { if (new_dir != old_dir) { /* Note: If we moved a directory, nlink will change */ - update_changeattr(old_dir, &res->old_cinfo, + nfs4_update_changeattr(old_dir, &res->old_cinfo, res->old_fattr->time_start, - NFS_INO_INVALID_OTHER); - update_changeattr(new_dir, &res->new_cinfo, + NFS_INO_INVALID_OTHER | + NFS_INO_INVALID_DATA); + nfs4_update_changeattr(new_dir, &res->new_cinfo, res->new_fattr->time_start, - NFS_INO_INVALID_OTHER); + NFS_INO_INVALID_OTHER | + NFS_INO_INVALID_DATA); } else - update_changeattr(old_dir, &res->old_cinfo, + nfs4_update_changeattr(old_dir, &res->old_cinfo, res->old_fattr->time_start, - 0); + NFS_INO_INVALID_DATA); } return 1; } @@ -4719,7 +4744,8 @@ static int _nfs4_proc_link(struct inode *inode, struct inode *dir, const struct status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1); if (!status) { - update_changeattr(dir, &res.cinfo, res.fattr->time_start, 0); + nfs4_update_changeattr(dir, &res.cinfo, res.fattr->time_start, + NFS_INO_INVALID_DATA); status = nfs_post_op_update_inode(inode, res.fattr); if (!status) nfs_setsecurity(inode, res.fattr, res.label); @@ -4797,8 +4823,9 @@ static int nfs4_do_create(struct inode *dir, struct dentry *dentry, struct nfs4_ &data->arg.seq_args, &data->res.seq_res, 1); if (status == 0) { spin_lock(&dir->i_lock); - update_changeattr_locked(dir, &data->res.dir_cinfo, - data->res.fattr->time_start, 0); + nfs4_update_changeattr_locked(dir, &data->res.dir_cinfo, + data->res.fattr->time_start, + NFS_INO_INVALID_DATA); /* Creating a directory bumps nlink in the parent */ if (data->arg.ftype == NF4DIR) nfs4_inc_nlink_locked(dir); @@ -5531,7 +5558,7 @@ static inline int nfs4_server_supports_acls(struct nfs_server *server) */ #define NFS4ACL_MAXPAGES DIV_ROUND_UP(XATTR_SIZE_MAX, PAGE_SIZE) -static int buf_to_pages_noslab(const void *buf, size_t buflen, +int nfs4_buf_to_pages_noslab(const void *buf, size_t buflen, struct page **pages) { struct page *newpage, **spages; @@ -5773,7 +5800,7 @@ static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t bufl return -EOPNOTSUPP; if (npages > ARRAY_SIZE(pages)) return -ERANGE; - i = buf_to_pages_noslab(buf, buflen, arg.acl_pages); + i = nfs4_buf_to_pages_noslab(buf, buflen, arg.acl_pages); if (i < 0) return i; nfs4_inode_make_writeable(inode); @@ -5845,8 +5872,6 @@ static int _nfs4_get_security_label(struct inode *inode, void *buf, return ret; if (!(fattr.valid & NFS_ATTR_FATTR_V4_SECURITY_LABEL)) return -ENOENT; - if (buflen < label.len) - return -ERANGE; return 0; } @@ -7430,6 +7455,133 @@ nfs4_listxattr_nfs4_label(struct inode *inode, char *list, size_t list_len) #endif +#ifdef CONFIG_NFS_V4_2 +static int nfs4_xattr_set_nfs4_user(const struct xattr_handler *handler, + struct dentry *unused, struct inode *inode, + const char *key, const void *buf, + size_t buflen, int flags) +{ + struct nfs_access_entry cache; + int ret; + + if (!nfs_server_capable(inode, NFS_CAP_XATTR)) + return -EOPNOTSUPP; + + /* + * There is no mapping from the MAY_* flags to the NFS_ACCESS_XA* + * flags right now. Handling of xattr operations use the normal + * file read/write permissions. + * + * Just in case the server has other ideas (which RFC 8276 allows), + * do a cached access check for the XA* flags to possibly avoid + * doing an RPC and getting EACCES back. + */ + if (!nfs_access_get_cached(inode, current_cred(), &cache, true)) { + if (!(cache.mask & NFS_ACCESS_XAWRITE)) + return -EACCES; + } + + if (buf == NULL) { + ret = nfs42_proc_removexattr(inode, key); + if (!ret) + nfs4_xattr_cache_remove(inode, key); + } else { + ret = nfs42_proc_setxattr(inode, key, buf, buflen, flags); + if (!ret) + nfs4_xattr_cache_add(inode, key, buf, NULL, buflen); + } + + return ret; +} + +static int nfs4_xattr_get_nfs4_user(const struct xattr_handler *handler, + struct dentry *unused, struct inode *inode, + const char *key, void *buf, size_t buflen) +{ + struct nfs_access_entry cache; + ssize_t ret; + + if (!nfs_server_capable(inode, NFS_CAP_XATTR)) + return -EOPNOTSUPP; + + if (!nfs_access_get_cached(inode, current_cred(), &cache, true)) { + if (!(cache.mask & NFS_ACCESS_XAREAD)) + return -EACCES; + } + + ret = nfs_revalidate_inode(NFS_SERVER(inode), inode); + if (ret) + return ret; + + ret = nfs4_xattr_cache_get(inode, key, buf, buflen); + if (ret >= 0 || (ret < 0 && ret != -ENOENT)) + return ret; + + ret = nfs42_proc_getxattr(inode, key, buf, buflen); + + return ret; +} + +static ssize_t +nfs4_listxattr_nfs4_user(struct inode *inode, char *list, size_t list_len) +{ + u64 cookie; + bool eof; + ssize_t ret, size; + char *buf; + size_t buflen; + struct nfs_access_entry cache; + + if (!nfs_server_capable(inode, NFS_CAP_XATTR)) + return 0; + + if (!nfs_access_get_cached(inode, current_cred(), &cache, true)) { + if (!(cache.mask & NFS_ACCESS_XALIST)) + return 0; + } + + ret = nfs_revalidate_inode(NFS_SERVER(inode), inode); + if (ret) + return ret; + + ret = nfs4_xattr_cache_list(inode, list, list_len); + if (ret >= 0 || (ret < 0 && ret != -ENOENT)) + return ret; + + cookie = 0; + eof = false; + buflen = list_len ? list_len : XATTR_LIST_MAX; + buf = list_len ? list : NULL; + size = 0; + + while (!eof) { + ret = nfs42_proc_listxattrs(inode, buf, buflen, + &cookie, &eof); + if (ret < 0) + return ret; + + if (list_len) { + buf += ret; + buflen -= ret; + } + size += ret; + } + + if (list_len) + nfs4_xattr_cache_set_list(inode, list, size); + + return size; +} + +#else + +static ssize_t +nfs4_listxattr_nfs4_user(struct inode *inode, char *list, size_t list_len) +{ + return 0; +} +#endif /* CONFIG_NFS_V4_2 */ + /* * nfs_fhget will use either the mounted_on_fileid or the fileid */ @@ -10035,7 +10187,7 @@ const struct nfs4_minor_version_ops *nfs_v4_minor_ops[] = { static ssize_t nfs4_listxattr(struct dentry *dentry, char *list, size_t size) { - ssize_t error, error2; + ssize_t error, error2, error3; error = generic_listxattr(dentry, list, size); if (error < 0) @@ -10048,7 +10200,17 @@ static ssize_t nfs4_listxattr(struct dentry *dentry, char *list, size_t size) error2 = nfs4_listxattr_nfs4_label(d_inode(dentry), list, size); if (error2 < 0) return error2; - return error + error2; + + if (list) { + list += error2; + size -= error2; + } + + error3 = nfs4_listxattr_nfs4_user(d_inode(dentry), list, size); + if (error3 < 0) + return error3; + + return error + error2 + error3; } static const struct inode_operations nfs4_dir_inode_operations = { @@ -10136,11 +10298,22 @@ static const struct xattr_handler nfs4_xattr_nfs4_acl_handler = { .set = nfs4_xattr_set_nfs4_acl, }; +#ifdef CONFIG_NFS_V4_2 +static const struct xattr_handler nfs4_xattr_nfs4_user_handler = { + .prefix = XATTR_USER_PREFIX, + .get = nfs4_xattr_get_nfs4_user, + .set = nfs4_xattr_set_nfs4_user, +}; +#endif + const struct xattr_handler *nfs4_xattr_handlers[] = { &nfs4_xattr_nfs4_acl_handler, #ifdef CONFIG_NFS_V4_SECURITY_LABEL &nfs4_xattr_nfs4_label_handler, #endif +#ifdef CONFIG_NFS_V4_2 + &nfs4_xattr_nfs4_user_handler, +#endif NULL }; diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index a8dc25ce48bb..b1dba24918f8 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -509,7 +509,7 @@ nfs4_alloc_state_owner(struct nfs_server *server, nfs4_init_seqid_counter(&sp->so_seqid); atomic_set(&sp->so_count, 1); INIT_LIST_HEAD(&sp->so_lru); - seqcount_init(&sp->so_reclaim_seqcount); + seqcount_spinlock_init(&sp->so_reclaim_seqcount, &sp->so_lock); mutex_init(&sp->so_delegreturn_mutex); return sp; } diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c index 1475f932d7da..0c1ab846b83d 100644 --- a/fs/nfs/nfs4super.c +++ b/fs/nfs/nfs4super.c @@ -69,6 +69,7 @@ static void nfs4_evict_inode(struct inode *inode) pnfs_destroy_layout(NFS_I(inode)); /* First call standard NFS clear_inode() code */ nfs_clear_inode(inode); + nfs4_xattr_cache_zap(inode); } struct nfs_referral_count { @@ -268,6 +269,12 @@ static int __init init_nfs_v4(void) if (err) goto out1; +#ifdef CONFIG_NFS_V4_2 + err = nfs4_xattr_cache_init(); + if (err) + goto out2; +#endif + err = nfs4_register_sysctl(); if (err) goto out2; @@ -288,6 +295,9 @@ static void __exit exit_nfs_v4(void) nfs4_pnfs_v3_ds_connect_unload(); unregister_nfs_version(&nfs_v4); +#ifdef CONFIG_NFS_V4_2 + nfs4_xattr_cache_exit(); +#endif nfs4_unregister_sysctl(); nfs_idmap_quit(); nfs_dns_resolver_destroy(); diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h index 543541173a3d..b4f852d4d099 100644 --- a/fs/nfs/nfs4trace.h +++ b/fs/nfs/nfs4trace.h @@ -1727,6 +1727,13 @@ DEFINE_NFS4_IDMAP_EVENT(nfs4_map_group_to_gid); DEFINE_NFS4_IDMAP_EVENT(nfs4_map_uid_to_name); DEFINE_NFS4_IDMAP_EVENT(nfs4_map_gid_to_group); +#ifdef CONFIG_NFS_V4_1 +#define NFS4_LSEG_LAYOUT_STATEID_HASH(lseg) \ + (lseg ? nfs_stateid_hash(&lseg->pls_layout->plh_stateid) : 0) +#else +#define NFS4_LSEG_LAYOUT_STATEID_HASH(lseg) (0) +#endif + DECLARE_EVENT_CLASS(nfs4_read_event, TP_PROTO( const struct nfs_pgio_header *hdr, @@ -1745,6 +1752,8 @@ DECLARE_EVENT_CLASS(nfs4_read_event, __field(unsigned long, error) __field(int, stateid_seq) __field(u32, stateid_hash) + __field(int, layoutstateid_seq) + __field(u32, layoutstateid_hash) ), TP_fast_assign( @@ -1754,6 +1763,7 @@ DECLARE_EVENT_CLASS(nfs4_read_event, hdr->args.fh : &nfsi->fh; const struct nfs4_state *state = hdr->args.context->state; + const struct pnfs_layout_segment *lseg = hdr->lseg; __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; @@ -1766,11 +1776,15 @@ DECLARE_EVENT_CLASS(nfs4_read_event, be32_to_cpu(state->stateid.seqid); __entry->stateid_hash = nfs_stateid_hash(&state->stateid); + __entry->layoutstateid_seq = lseg ? lseg->pls_seq : 0; + __entry->layoutstateid_hash = + NFS4_LSEG_LAYOUT_STATEID_HASH(lseg); ), TP_printk( "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " - "offset=%lld count=%u res=%u stateid=%d:0x%08x", + "offset=%lld count=%u res=%u stateid=%d:0x%08x " + "layoutstateid=%d:0x%08x", -__entry->error, show_nfsv4_errors(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), @@ -1778,7 +1792,8 @@ DECLARE_EVENT_CLASS(nfs4_read_event, __entry->fhandle, (long long)__entry->offset, __entry->arg_count, __entry->res_count, - __entry->stateid_seq, __entry->stateid_hash + __entry->stateid_seq, __entry->stateid_hash, + __entry->layoutstateid_seq, __entry->layoutstateid_hash ) ); #define DEFINE_NFS4_READ_EVENT(name) \ @@ -1811,6 +1826,8 @@ DECLARE_EVENT_CLASS(nfs4_write_event, __field(unsigned long, error) __field(int, stateid_seq) __field(u32, stateid_hash) + __field(int, layoutstateid_seq) + __field(u32, layoutstateid_hash) ), TP_fast_assign( @@ -1820,6 +1837,7 @@ DECLARE_EVENT_CLASS(nfs4_write_event, hdr->args.fh : &nfsi->fh; const struct nfs4_state *state = hdr->args.context->state; + const struct pnfs_layout_segment *lseg = hdr->lseg; __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; @@ -1832,11 +1850,15 @@ DECLARE_EVENT_CLASS(nfs4_write_event, be32_to_cpu(state->stateid.seqid); __entry->stateid_hash = nfs_stateid_hash(&state->stateid); + __entry->layoutstateid_seq = lseg ? lseg->pls_seq : 0; + __entry->layoutstateid_hash = + NFS4_LSEG_LAYOUT_STATEID_HASH(lseg); ), TP_printk( "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " - "offset=%lld count=%u res=%u stateid=%d:0x%08x", + "offset=%lld count=%u res=%u stateid=%d:0x%08x " + "layoutstateid=%d:0x%08x", -__entry->error, show_nfsv4_errors(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), @@ -1844,7 +1866,8 @@ DECLARE_EVENT_CLASS(nfs4_write_event, __entry->fhandle, (long long)__entry->offset, __entry->arg_count, __entry->res_count, - __entry->stateid_seq, __entry->stateid_hash + __entry->stateid_seq, __entry->stateid_hash, + __entry->layoutstateid_seq, __entry->layoutstateid_hash ) ); @@ -1875,6 +1898,8 @@ DECLARE_EVENT_CLASS(nfs4_commit_event, __field(unsigned long, error) __field(loff_t, offset) __field(u32, count) + __field(int, layoutstateid_seq) + __field(u32, layoutstateid_hash) ), TP_fast_assign( @@ -1882,6 +1907,7 @@ DECLARE_EVENT_CLASS(nfs4_commit_event, const struct nfs_inode *nfsi = NFS_I(inode); const struct nfs_fh *fh = data->args.fh ? data->args.fh : &nfsi->fh; + const struct pnfs_layout_segment *lseg = data->lseg; __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; @@ -1889,18 +1915,22 @@ DECLARE_EVENT_CLASS(nfs4_commit_event, __entry->offset = data->args.offset; __entry->count = data->args.count; __entry->error = error < 0 ? -error : 0; + __entry->layoutstateid_seq = lseg ? lseg->pls_seq : 0; + __entry->layoutstateid_hash = + NFS4_LSEG_LAYOUT_STATEID_HASH(lseg); ), TP_printk( "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " - "offset=%lld count=%u", + "offset=%lld count=%u layoutstateid=%d:0x%08x", -__entry->error, show_nfsv4_errors(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, (long long)__entry->offset, - __entry->count + __entry->count, + __entry->layoutstateid_seq, __entry->layoutstateid_hash ) ); #define DEFINE_NFS4_COMMIT_EVENT(name) \ @@ -1993,7 +2023,9 @@ TRACE_EVENT(nfs4_layoutget, DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_layoutcommit); DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_layoutreturn); -DEFINE_NFS4_INODE_EVENT(nfs4_layoutreturn_on_close); +DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_layoutreturn_on_close); +DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_layouterror); +DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_layoutstats); TRACE_DEFINE_ENUM(PNFS_UPDATE_LAYOUT_UNKNOWN); TRACE_DEFINE_ENUM(PNFS_UPDATE_LAYOUT_NO_PNFS); diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 47817ef0aadb..0b3510f62623 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -4166,7 +4166,11 @@ static int decode_attr_security_label(struct xdr_stream *xdr, uint32_t *bitmap, return -EIO; if (len < NFS4_MAXLABELLEN) { if (label) { - memcpy(label->label, p, len); + if (label->len) { + if (label->len < len) + return -ERANGE; + memcpy(label->label, p, len); + } label->len = len; label->pi = pi; label->lfs = lfs; @@ -4201,6 +4205,26 @@ static int decode_attr_time_modify(struct xdr_stream *xdr, uint32_t *bitmap, str return status; } +static int decode_attr_xattrsupport(struct xdr_stream *xdr, uint32_t *bitmap, + uint32_t *res) +{ + __be32 *p; + + *res = 0; + if (unlikely(bitmap[2] & (FATTR4_WORD2_XATTR_SUPPORT - 1U))) + return -EIO; + if (likely(bitmap[2] & FATTR4_WORD2_XATTR_SUPPORT)) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + return -EIO; + *res = be32_to_cpup(p); + bitmap[2] &= ~FATTR4_WORD2_XATTR_SUPPORT; + } + dprintk("%s: XATTR support=%s\n", __func__, + *res == 0 ? "false" : "true"); + return 0; +} + static int verify_attr_len(struct xdr_stream *xdr, unsigned int savep, uint32_t attrlen) { unsigned int attrwords = XDR_QUADLEN(attrlen); @@ -4855,6 +4879,11 @@ static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo) if (status) goto xdr_error; + status = decode_attr_xattrsupport(xdr, bitmap, + &fsinfo->xattr_support); + if (status) + goto xdr_error; + status = verify_attr_len(xdr, savep, attrlen); xdr_error: dprintk("%s: xdr returned %d!\n", __func__, -status); @@ -5227,7 +5256,7 @@ static int decode_readlink(struct xdr_stream *xdr, struct rpc_rqst *req) * The XDR encode routine has set things up so that * the link text will be copied directly into the * buffer. We just have to do overflow-checking, - * and and null-terminate the text (the VFS expects + * and null-terminate the text (the VFS expects * null-termination). */ xdr_terminate_string(rcvbuf, len); @@ -7456,6 +7485,8 @@ static struct { { NFS4ERR_SYMLINK, -ELOOP }, { NFS4ERR_OP_ILLEGAL, -EOPNOTSUPP }, { NFS4ERR_DEADLOCK, -EDEADLK }, + { NFS4ERR_NOXATTR, -ENODATA }, + { NFS4ERR_XATTR2BIG, -E2BIG }, { -1, -EIO } }; @@ -7584,6 +7615,10 @@ const struct rpc_procinfo nfs4_procedures[] = { PROC42(COPY_NOTIFY, enc_copy_notify, dec_copy_notify), PROC(LOOKUPP, enc_lookupp, dec_lookupp), PROC42(LAYOUTERROR, enc_layouterror, dec_layouterror), + PROC42(GETXATTR, enc_getxattr, dec_getxattr), + PROC42(SETXATTR, enc_setxattr, dec_setxattr), + PROC42(LISTXATTRS, enc_listxattrs, dec_listxattrs), + PROC42(REMOVEXATTR, enc_removexattr, dec_removexattr), }; static unsigned int nfs_version4_counts[ARRAY_SIZE(nfs4_procedures)]; diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index 547cec79899f..5a59dcdce0b2 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -59,7 +59,8 @@ TRACE_DEFINE_ENUM(NFS_INO_INVALID_OTHER); { NFS_INO_INVALID_CTIME, "INVALID_CTIME" }, \ { NFS_INO_INVALID_MTIME, "INVALID_MTIME" }, \ { NFS_INO_INVALID_SIZE, "INVALID_SIZE" }, \ - { NFS_INO_INVALID_OTHER, "INVALID_OTHER" }) + { NFS_INO_INVALID_OTHER, "INVALID_OTHER" }, \ + { NFS_INO_INVALID_XATTR, "INVALID_XATTR" }) TRACE_DEFINE_ENUM(NFS_INO_ADVISE_RDPLUS); TRACE_DEFINE_ENUM(NFS_INO_STALE); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index dd2e14f5875d..40332c758d84 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1226,31 +1226,27 @@ out: return status; } +static bool +pnfs_layout_segments_returnable(struct pnfs_layout_hdr *lo, + enum pnfs_iomode iomode, + u32 seq) +{ + struct pnfs_layout_range recall_range = { + .length = NFS4_MAX_UINT64, + .iomode = iomode, + }; + return pnfs_mark_matching_lsegs_return(lo, &lo->plh_return_segs, + &recall_range, seq) != -EBUSY; +} + /* Return true if layoutreturn is needed */ static bool pnfs_layout_need_return(struct pnfs_layout_hdr *lo) { - struct pnfs_layout_segment *s; - enum pnfs_iomode iomode; - u32 seq; - if (!test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags)) return false; - - seq = lo->plh_return_seq; - iomode = lo->plh_return_iomode; - - /* Defer layoutreturn until all recalled lsegs are done */ - list_for_each_entry(s, &lo->plh_segs, pls_list) { - if (seq && pnfs_seqid_is_newer(s->pls_seq, seq)) - continue; - if (iomode != IOMODE_ANY && s->pls_range.iomode != iomode) - continue; - if (test_bit(NFS_LSEG_LAYOUTRETURN, &s->pls_flags)) - return false; - } - - return true; + return pnfs_layout_segments_returnable(lo, lo->plh_return_iomode, + lo->plh_return_seq); } static void pnfs_layoutreturn_before_put_layout_hdr(struct pnfs_layout_hdr *lo) @@ -1549,12 +1545,12 @@ void pnfs_roc_release(struct nfs4_layoutreturn_args *args, default: arg_stateid = &args->stateid; } + trace_nfs4_layoutreturn_on_close(args->inode, &args->stateid, ret); pnfs_layoutreturn_free_lsegs(lo, arg_stateid, &args->range, res_stateid); if (ld_private && ld_private->ops && ld_private->ops->free) ld_private->ops->free(ld_private); pnfs_put_layout_hdr(lo); - trace_nfs4_layoutreturn_on_close(args->inode, 0); } bool pnfs_wait_on_layoutreturn(struct inode *ino, struct rpc_task *task) @@ -2392,16 +2388,6 @@ out_forget: return ERR_PTR(-EAGAIN); } -static int -mark_lseg_invalid_or_return(struct pnfs_layout_segment *lseg, - struct list_head *tmp_list) -{ - if (!mark_lseg_invalid(lseg, tmp_list)) - return 0; - pnfs_cache_lseg_for_layoutreturn(lseg->pls_layout, lseg); - return 1; -} - /** * pnfs_mark_matching_lsegs_return - Free or return matching layout segments * @lo: pointer to layout header @@ -2438,7 +2424,7 @@ pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo, lseg, lseg->pls_range.iomode, lseg->pls_range.offset, lseg->pls_range.length); - if (mark_lseg_invalid_or_return(lseg, tmp_list)) + if (mark_lseg_invalid(lseg, tmp_list)) continue; remaining++; set_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags); @@ -2953,7 +2939,8 @@ pnfs_try_to_read_data(struct nfs_pgio_header *hdr, } /* Resend all requests through pnfs. */ -void pnfs_read_resend_pnfs(struct nfs_pgio_header *hdr) +void pnfs_read_resend_pnfs(struct nfs_pgio_header *hdr, + unsigned int mirror_idx) { struct nfs_pageio_descriptor pgio; @@ -2964,6 +2951,7 @@ void pnfs_read_resend_pnfs(struct nfs_pgio_header *hdr) nfs_pageio_init_read(&pgio, hdr->inode, false, hdr->completion_ops); + pgio.pg_mirror_idx = mirror_idx; hdr->task.tk_status = nfs_pageio_resend(&pgio, hdr); } } diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 8e0ada581b92..2661c44c62db 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -311,7 +311,7 @@ int _pnfs_return_layout(struct inode *); int pnfs_commit_and_return_layout(struct inode *); void pnfs_ld_write_done(struct nfs_pgio_header *); void pnfs_ld_read_done(struct nfs_pgio_header *); -void pnfs_read_resend_pnfs(struct nfs_pgio_header *); +void pnfs_read_resend_pnfs(struct nfs_pgio_header *, unsigned int mirror_idx); struct pnfs_layout_segment *pnfs_update_layout(struct inode *ino, struct nfs_open_context *ctx, loff_t pos, diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index 9217cb64bf0e..7346acda9d76 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -171,7 +171,7 @@ struct nfsd_net { unsigned int longest_chain_cachesize; struct shrinker nfsd_reply_cache_shrinker; - /* utsname taken from the the process that starts the server */ + /* utsname taken from the process that starts the server */ char nfsd_name[UNX_MAXNODENAME+1]; }; diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c index 9460be8a8321..f92161ce1f97 100644 --- a/fs/nfsd/nfs4idmap.c +++ b/fs/nfsd/nfs4idmap.c @@ -168,7 +168,7 @@ idtoname_show(struct seq_file *m, struct cache_detail *cd, struct cache_head *h) ent->id); if (test_bit(CACHE_VALID, &h->flags)) seq_printf(m, " %s", ent->name); - seq_printf(m, "\n"); + seq_putc(m, '\n'); return 0; } @@ -346,7 +346,7 @@ nametoid_show(struct seq_file *m, struct cache_detail *cd, struct cache_head *h) ent->name); if (test_bit(CACHE_VALID, &h->flags)) seq_printf(m, " %u", ent->id); - seq_printf(m, "\n"); + seq_putc(m, '\n'); return 0; } diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index a09c35f0f6f0..a527da3d8052 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -566,8 +566,14 @@ nfsd4_access(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_access *access = &u->access; + u32 access_full; - if (access->ac_req_access & ~NFS3_ACCESS_FULL) + access_full = NFS3_ACCESS_FULL; + if (cstate->minorversion >= 2) + access_full |= NFS4_ACCESS_XALIST | NFS4_ACCESS_XAREAD | + NFS4_ACCESS_XAWRITE; + + if (access->ac_req_access & ~access_full) return nfserr_inval; access->ac_resp_access = access->ac_req_access; @@ -2091,6 +2097,68 @@ out: } #endif /* CONFIG_NFSD_PNFS */ +static __be32 +nfsd4_getxattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) +{ + struct nfsd4_getxattr *getxattr = &u->getxattr; + + return nfsd_getxattr(rqstp, &cstate->current_fh, + getxattr->getxa_name, &getxattr->getxa_buf, + &getxattr->getxa_len); +} + +static __be32 +nfsd4_setxattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) +{ + struct nfsd4_setxattr *setxattr = &u->setxattr; + __be32 ret; + + if (opens_in_grace(SVC_NET(rqstp))) + return nfserr_grace; + + ret = nfsd_setxattr(rqstp, &cstate->current_fh, setxattr->setxa_name, + setxattr->setxa_buf, setxattr->setxa_len, + setxattr->setxa_flags); + + if (!ret) + set_change_info(&setxattr->setxa_cinfo, &cstate->current_fh); + + return ret; +} + +static __be32 +nfsd4_listxattrs(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) +{ + /* + * Get the entire list, then copy out only the user attributes + * in the encode function. + */ + return nfsd_listxattr(rqstp, &cstate->current_fh, + &u->listxattrs.lsxa_buf, &u->listxattrs.lsxa_len); +} + +static __be32 +nfsd4_removexattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) +{ + struct nfsd4_removexattr *removexattr = &u->removexattr; + __be32 ret; + + if (opens_in_grace(SVC_NET(rqstp))) + return nfserr_grace; + + ret = nfsd_removexattr(rqstp, &cstate->current_fh, + removexattr->rmxa_name); + + if (!ret) + set_change_info(&removexattr->rmxa_cinfo, &cstate->current_fh); + + return ret; +} + /* * NULL call. */ @@ -2700,6 +2768,42 @@ static inline u32 nfsd4_seek_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) return (op_encode_hdr_size + 3) * sizeof(__be32); } +static inline u32 nfsd4_getxattr_rsize(struct svc_rqst *rqstp, + struct nfsd4_op *op) +{ + u32 maxcount, rlen; + + maxcount = svc_max_payload(rqstp); + rlen = min_t(u32, XATTR_SIZE_MAX, maxcount); + + return (op_encode_hdr_size + 1 + XDR_QUADLEN(rlen)) * sizeof(__be32); +} + +static inline u32 nfsd4_setxattr_rsize(struct svc_rqst *rqstp, + struct nfsd4_op *op) +{ + return (op_encode_hdr_size + op_encode_change_info_maxsz) + * sizeof(__be32); +} +static inline u32 nfsd4_listxattrs_rsize(struct svc_rqst *rqstp, + struct nfsd4_op *op) +{ + u32 maxcount, rlen; + + maxcount = svc_max_payload(rqstp); + rlen = min(op->u.listxattrs.lsxa_maxcount, maxcount); + + return (op_encode_hdr_size + 4 + XDR_QUADLEN(rlen)) * sizeof(__be32); +} + +static inline u32 nfsd4_removexattr_rsize(struct svc_rqst *rqstp, + struct nfsd4_op *op) +{ + return (op_encode_hdr_size + op_encode_change_info_maxsz) + * sizeof(__be32); +} + + static const struct nfsd4_operation nfsd4_ops[] = { [OP_ACCESS] = { .op_func = nfsd4_access, @@ -3081,6 +3185,28 @@ static const struct nfsd4_operation nfsd4_ops[] = { .op_name = "OP_COPY_NOTIFY", .op_rsize_bop = nfsd4_copy_notify_rsize, }, + [OP_GETXATTR] = { + .op_func = nfsd4_getxattr, + .op_name = "OP_GETXATTR", + .op_rsize_bop = nfsd4_getxattr_rsize, + }, + [OP_SETXATTR] = { + .op_func = nfsd4_setxattr, + .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, + .op_name = "OP_SETXATTR", + .op_rsize_bop = nfsd4_setxattr_rsize, + }, + [OP_LISTXATTRS] = { + .op_func = nfsd4_listxattrs, + .op_name = "OP_LISTXATTRS", + .op_rsize_bop = nfsd4_listxattrs_rsize, + }, + [OP_REMOVEXATTR] = { + .op_func = nfsd4_removexattr, + .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, + .op_name = "OP_REMOVEXATTR", + .op_rsize_bop = nfsd4_removexattr_rsize, + }, }; /** diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index 9e40dfecf1b1..186fa2c2c6ba 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -747,13 +747,11 @@ struct cld_upcall { }; static int -__cld_pipe_upcall(struct rpc_pipe *pipe, void *cmsg) +__cld_pipe_upcall(struct rpc_pipe *pipe, void *cmsg, struct nfsd_net *nn) { int ret; struct rpc_pipe_msg msg; struct cld_upcall *cup = container_of(cmsg, struct cld_upcall, cu_u); - struct nfsd_net *nn = net_generic(pipe->dentry->d_sb->s_fs_info, - nfsd_net_id); memset(&msg, 0, sizeof(msg)); msg.data = cmsg; @@ -773,7 +771,7 @@ out: } static int -cld_pipe_upcall(struct rpc_pipe *pipe, void *cmsg) +cld_pipe_upcall(struct rpc_pipe *pipe, void *cmsg, struct nfsd_net *nn) { int ret; @@ -782,7 +780,7 @@ cld_pipe_upcall(struct rpc_pipe *pipe, void *cmsg) * upcalls queued. */ do { - ret = __cld_pipe_upcall(pipe, cmsg); + ret = __cld_pipe_upcall(pipe, cmsg, nn); } while (ret == -EAGAIN); return ret; @@ -1115,7 +1113,7 @@ nfsd4_cld_create(struct nfs4_client *clp) memcpy(cup->cu_u.cu_msg.cm_u.cm_name.cn_id, clp->cl_name.data, clp->cl_name.len); - ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_u.cu_msg); + ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_u.cu_msg, nn); if (!ret) { ret = cup->cu_u.cu_msg.cm_status; set_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags); @@ -1180,7 +1178,7 @@ nfsd4_cld_create_v2(struct nfs4_client *clp) } else cmsg->cm_u.cm_clntinfo.cc_princhash.cp_len = 0; - ret = cld_pipe_upcall(cn->cn_pipe, cmsg); + ret = cld_pipe_upcall(cn->cn_pipe, cmsg, nn); if (!ret) { ret = cmsg->cm_status; set_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags); @@ -1218,7 +1216,7 @@ nfsd4_cld_remove(struct nfs4_client *clp) memcpy(cup->cu_u.cu_msg.cm_u.cm_name.cn_id, clp->cl_name.data, clp->cl_name.len); - ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_u.cu_msg); + ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_u.cu_msg, nn); if (!ret) { ret = cup->cu_u.cu_msg.cm_status; clear_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags); @@ -1261,7 +1259,7 @@ nfsd4_cld_check_v0(struct nfs4_client *clp) memcpy(cup->cu_u.cu_msg.cm_u.cm_name.cn_id, clp->cl_name.data, clp->cl_name.len); - ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_u.cu_msg); + ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_u.cu_msg, nn); if (!ret) { ret = cup->cu_u.cu_msg.cm_status; set_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags); @@ -1404,7 +1402,7 @@ nfsd4_cld_grace_start(struct nfsd_net *nn) } cup->cu_u.cu_msg.cm_cmd = Cld_GraceStart; - ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_u.cu_msg); + ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_u.cu_msg, nn); if (!ret) ret = cup->cu_u.cu_msg.cm_status; @@ -1432,7 +1430,7 @@ nfsd4_cld_grace_done_v0(struct nfsd_net *nn) cup->cu_u.cu_msg.cm_cmd = Cld_GraceDone; cup->cu_u.cu_msg.cm_u.cm_gracetime = nn->boot_time; - ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_u.cu_msg); + ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_u.cu_msg, nn); if (!ret) ret = cup->cu_u.cu_msg.cm_status; @@ -1460,7 +1458,7 @@ nfsd4_cld_grace_done(struct nfsd_net *nn) } cup->cu_u.cu_msg.cm_cmd = Cld_GraceDone; - ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_u.cu_msg); + ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_u.cu_msg, nn); if (!ret) ret = cup->cu_u.cu_msg.cm_status; @@ -1524,7 +1522,7 @@ nfsd4_cld_get_version(struct nfsd_net *nn) goto out_err; } cup->cu_u.cu_msg.cm_cmd = Cld_GetVersion; - ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_u.cu_msg); + ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_u.cu_msg, nn); if (!ret) { ret = cup->cu_u.cu_msg.cm_status; if (ret) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index c9056316a0b3..81ed8e8bab3f 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -4940,6 +4940,32 @@ static struct file_lock *nfs4_alloc_init_lease(struct nfs4_delegation *dp, return fl; } +static int nfsd4_check_conflicting_opens(struct nfs4_client *clp, + struct nfs4_file *fp) +{ + struct nfs4_clnt_odstate *co; + struct file *f = fp->fi_deleg_file->nf_file; + struct inode *ino = locks_inode(f); + int writes = atomic_read(&ino->i_writecount); + + if (fp->fi_fds[O_WRONLY]) + writes--; + if (fp->fi_fds[O_RDWR]) + writes--; + WARN_ON_ONCE(writes < 0); + if (writes > 0) + return -EAGAIN; + spin_lock(&fp->fi_lock); + list_for_each_entry(co, &fp->fi_clnt_odstate, co_perfile) { + if (co->co_client != clp) { + spin_unlock(&fp->fi_lock); + return -EAGAIN; + } + } + spin_unlock(&fp->fi_lock); + return 0; +} + static struct nfs4_delegation * nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh, struct nfs4_file *fp, struct nfs4_clnt_odstate *odstate) @@ -4959,9 +4985,12 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh, nf = find_readable_file(fp); if (!nf) { - /* We should always have a readable file here */ - WARN_ON_ONCE(1); - return ERR_PTR(-EBADF); + /* + * We probably could attempt another open and get a read + * delegation, but for now, don't bother until the + * client actually sends us one. + */ + return ERR_PTR(-EAGAIN); } spin_lock(&state_lock); spin_lock(&fp->fi_lock); @@ -4991,11 +5020,19 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh, if (!fl) goto out_clnt_odstate; + status = nfsd4_check_conflicting_opens(clp, fp); + if (status) { + locks_free_lock(fl); + goto out_clnt_odstate; + } status = vfs_setlease(fp->fi_deleg_file->nf_file, fl->fl_type, &fl, NULL); if (fl) locks_free_lock(fl); if (status) goto out_clnt_odstate; + status = nfsd4_check_conflicting_opens(clp, fp); + if (status) + goto out_clnt_odstate; spin_lock(&state_lock); spin_lock(&fp->fi_lock); @@ -5077,17 +5114,6 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open, goto out_no_deleg; if (!cb_up || !(oo->oo_flags & NFS4_OO_CONFIRMED)) goto out_no_deleg; - /* - * Also, if the file was opened for write or - * create, there's a good chance the client's - * about to write to it, resulting in an - * immediate recall (since we don't support - * write delegations): - */ - if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE) - goto out_no_deleg; - if (open->op_create == NFS4_OPEN_CREATE) - goto out_no_deleg; break; default: goto out_no_deleg; diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 996ac01ee977..259d5ad0e3f4 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -41,6 +41,8 @@ #include <linux/pagemap.h> #include <linux/sunrpc/svcauth_gss.h> #include <linux/sunrpc/addr.h> +#include <linux/xattr.h> +#include <uapi/linux/xattr.h> #include "idmap.h" #include "acl.h" @@ -257,6 +259,44 @@ svcxdr_dupstr(struct nfsd4_compoundargs *argp, void *buf, u32 len) return p; } +static __be32 +svcxdr_construct_vector(struct nfsd4_compoundargs *argp, struct kvec *head, + struct page ***pagelist, u32 buflen) +{ + int avail; + int len; + int pages; + + /* Sorry .. no magic macros for this.. * + * READ_BUF(write->wr_buflen); + * SAVEMEM(write->wr_buf, write->wr_buflen); + */ + avail = (char *)argp->end - (char *)argp->p; + if (avail + argp->pagelen < buflen) { + dprintk("NFSD: xdr error (%s:%d)\n", + __FILE__, __LINE__); + return nfserr_bad_xdr; + } + head->iov_base = argp->p; + head->iov_len = avail; + *pagelist = argp->pagelist; + + len = XDR_QUADLEN(buflen) << 2; + if (len >= avail) { + len -= avail; + + pages = len >> PAGE_SHIFT; + argp->pagelist += pages; + argp->pagelen -= pages * PAGE_SIZE; + len -= pages * PAGE_SIZE; + + next_decode_page(argp); + } + argp->p += XDR_QUADLEN(len); + + return 0; +} + /** * savemem - duplicate a chunk of memory for later processing * @argp: NFSv4 compound argument structure to be freed with @@ -1265,8 +1305,6 @@ nfsd4_decode_verify(struct nfsd4_compoundargs *argp, struct nfsd4_verify *verify static __be32 nfsd4_decode_write(struct nfsd4_compoundargs *argp, struct nfsd4_write *write) { - int avail; - int len; DECODE_HEAD; status = nfsd4_decode_stateid(argp, &write->wr_stateid); @@ -1279,34 +1317,10 @@ nfsd4_decode_write(struct nfsd4_compoundargs *argp, struct nfsd4_write *write) goto xdr_error; write->wr_buflen = be32_to_cpup(p++); - /* Sorry .. no magic macros for this.. * - * READ_BUF(write->wr_buflen); - * SAVEMEM(write->wr_buf, write->wr_buflen); - */ - avail = (char*)argp->end - (char*)argp->p; - if (avail + argp->pagelen < write->wr_buflen) { - dprintk("NFSD: xdr error (%s:%d)\n", - __FILE__, __LINE__); - goto xdr_error; - } - write->wr_head.iov_base = p; - write->wr_head.iov_len = avail; - write->wr_pagelist = argp->pagelist; - - len = XDR_QUADLEN(write->wr_buflen) << 2; - if (len >= avail) { - int pages; - - len -= avail; - - pages = len >> PAGE_SHIFT; - argp->pagelist += pages; - argp->pagelen -= pages * PAGE_SIZE; - len -= pages * PAGE_SIZE; - - next_decode_page(argp); - } - argp->p += XDR_QUADLEN(len); + status = svcxdr_construct_vector(argp, &write->wr_head, + &write->wr_pagelist, write->wr_buflen); + if (status) + return status; DECODE_TAIL; } @@ -1865,6 +1879,208 @@ nfsd4_decode_seek(struct nfsd4_compoundargs *argp, struct nfsd4_seek *seek) DECODE_TAIL; } +/* + * XDR data that is more than PAGE_SIZE in size is normally part of a + * read or write. However, the size of extended attributes is limited + * by the maximum request size, and then further limited by the underlying + * filesystem limits. This can exceed PAGE_SIZE (currently, XATTR_SIZE_MAX + * is 64k). Since there is no kvec- or page-based interface to xattrs, + * and we're not dealing with contiguous pages, we need to do some copying. + */ + +/* + * Decode data into buffer. Uses head and pages constructed by + * svcxdr_construct_vector. + */ +static __be32 +nfsd4_vbuf_from_vector(struct nfsd4_compoundargs *argp, struct kvec *head, + struct page **pages, char **bufp, u32 buflen) +{ + char *tmp, *dp; + u32 len; + + if (buflen <= head->iov_len) { + /* + * We're in luck, the head has enough space. Just return + * the head, no need for copying. + */ + *bufp = head->iov_base; + return 0; + } + + tmp = svcxdr_tmpalloc(argp, buflen); + if (tmp == NULL) + return nfserr_jukebox; + + dp = tmp; + memcpy(dp, head->iov_base, head->iov_len); + buflen -= head->iov_len; + dp += head->iov_len; + + while (buflen > 0) { + len = min_t(u32, buflen, PAGE_SIZE); + memcpy(dp, page_address(*pages), len); + + buflen -= len; + dp += len; + pages++; + } + + *bufp = tmp; + return 0; +} + +/* + * Get a user extended attribute name from the XDR buffer. + * It will not have the "user." prefix, so prepend it. + * Lastly, check for nul characters in the name. + */ +static __be32 +nfsd4_decode_xattr_name(struct nfsd4_compoundargs *argp, char **namep) +{ + DECODE_HEAD; + char *name, *sp, *dp; + u32 namelen, cnt; + + READ_BUF(4); + namelen = be32_to_cpup(p++); + + if (namelen > (XATTR_NAME_MAX - XATTR_USER_PREFIX_LEN)) + return nfserr_nametoolong; + + if (namelen == 0) + goto xdr_error; + + READ_BUF(namelen); + + name = svcxdr_tmpalloc(argp, namelen + XATTR_USER_PREFIX_LEN + 1); + if (!name) + return nfserr_jukebox; + + memcpy(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN); + + /* + * Copy the extended attribute name over while checking for 0 + * characters. + */ + sp = (char *)p; + dp = name + XATTR_USER_PREFIX_LEN; + cnt = namelen; + + while (cnt-- > 0) { + if (*sp == '\0') + goto xdr_error; + *dp++ = *sp++; + } + *dp = '\0'; + + *namep = name; + + DECODE_TAIL; +} + +/* + * A GETXATTR op request comes without a length specifier. We just set the + * maximum length for the reply based on XATTR_SIZE_MAX and the maximum + * channel reply size. nfsd_getxattr will probe the length of the xattr, + * check it against getxa_len, and allocate + return the value. + */ +static __be32 +nfsd4_decode_getxattr(struct nfsd4_compoundargs *argp, + struct nfsd4_getxattr *getxattr) +{ + __be32 status; + u32 maxcount; + + status = nfsd4_decode_xattr_name(argp, &getxattr->getxa_name); + if (status) + return status; + + maxcount = svc_max_payload(argp->rqstp); + maxcount = min_t(u32, XATTR_SIZE_MAX, maxcount); + + getxattr->getxa_len = maxcount; + + return status; +} + +static __be32 +nfsd4_decode_setxattr(struct nfsd4_compoundargs *argp, + struct nfsd4_setxattr *setxattr) +{ + DECODE_HEAD; + u32 flags, maxcount, size; + struct kvec head; + struct page **pagelist; + + READ_BUF(4); + flags = be32_to_cpup(p++); + + if (flags > SETXATTR4_REPLACE) + return nfserr_inval; + setxattr->setxa_flags = flags; + + status = nfsd4_decode_xattr_name(argp, &setxattr->setxa_name); + if (status) + return status; + + maxcount = svc_max_payload(argp->rqstp); + maxcount = min_t(u32, XATTR_SIZE_MAX, maxcount); + + READ_BUF(4); + size = be32_to_cpup(p++); + if (size > maxcount) + return nfserr_xattr2big; + + setxattr->setxa_len = size; + if (size > 0) { + status = svcxdr_construct_vector(argp, &head, &pagelist, size); + if (status) + return status; + + status = nfsd4_vbuf_from_vector(argp, &head, pagelist, + &setxattr->setxa_buf, size); + } + + DECODE_TAIL; +} + +static __be32 +nfsd4_decode_listxattrs(struct nfsd4_compoundargs *argp, + struct nfsd4_listxattrs *listxattrs) +{ + DECODE_HEAD; + u32 maxcount; + + READ_BUF(12); + p = xdr_decode_hyper(p, &listxattrs->lsxa_cookie); + + /* + * If the cookie is too large to have even one user.x attribute + * plus trailing '\0' left in a maximum size buffer, it's invalid. + */ + if (listxattrs->lsxa_cookie >= + (XATTR_LIST_MAX / (XATTR_USER_PREFIX_LEN + 2))) + return nfserr_badcookie; + + maxcount = be32_to_cpup(p++); + if (maxcount < 8) + /* Always need at least 2 words (length and one character) */ + return nfserr_inval; + + maxcount = min(maxcount, svc_max_payload(argp->rqstp)); + listxattrs->lsxa_maxcount = maxcount; + + DECODE_TAIL; +} + +static __be32 +nfsd4_decode_removexattr(struct nfsd4_compoundargs *argp, + struct nfsd4_removexattr *removexattr) +{ + return nfsd4_decode_xattr_name(argp, &removexattr->rmxa_name); +} + static __be32 nfsd4_decode_noop(struct nfsd4_compoundargs *argp, void *p) { @@ -1961,6 +2177,11 @@ static const nfsd4_dec nfsd4_dec_ops[] = { [OP_SEEK] = (nfsd4_dec)nfsd4_decode_seek, [OP_WRITE_SAME] = (nfsd4_dec)nfsd4_decode_notsupp, [OP_CLONE] = (nfsd4_dec)nfsd4_decode_clone, + /* RFC 8276 extended atributes operations */ + [OP_GETXATTR] = (nfsd4_dec)nfsd4_decode_getxattr, + [OP_SETXATTR] = (nfsd4_dec)nfsd4_decode_setxattr, + [OP_LISTXATTRS] = (nfsd4_dec)nfsd4_decode_listxattrs, + [OP_REMOVEXATTR] = (nfsd4_dec)nfsd4_decode_removexattr, }; static inline bool @@ -2992,6 +3213,15 @@ out_acl: } #endif + if (bmval2 & FATTR4_WORD2_XATTR_SUPPORT) { + p = xdr_reserve_space(xdr, 4); + if (!p) + goto out_resource; + err = xattr_supported_namespace(d_inode(dentry), + XATTR_USER_PREFIX); + *p++ = cpu_to_be32(err == 0); + } + attrlen = htonl(xdr->buf->len - attrlen_offset - 4); write_bytes_to_xdr_buf(xdr->buf, attrlen_offset, &attrlen, 4); status = nfs_ok; @@ -4446,6 +4676,241 @@ nfsd4_encode_noop(struct nfsd4_compoundres *resp, __be32 nfserr, void *p) return nfserr; } +/* + * Encode kmalloc-ed buffer in to XDR stream. + */ +static int +nfsd4_vbuf_to_stream(struct xdr_stream *xdr, char *buf, u32 buflen) +{ + u32 cplen; + __be32 *p; + + cplen = min_t(unsigned long, buflen, + ((void *)xdr->end - (void *)xdr->p)); + p = xdr_reserve_space(xdr, cplen); + if (!p) + return nfserr_resource; + + memcpy(p, buf, cplen); + buf += cplen; + buflen -= cplen; + + while (buflen) { + cplen = min_t(u32, buflen, PAGE_SIZE); + p = xdr_reserve_space(xdr, cplen); + if (!p) + return nfserr_resource; + + memcpy(p, buf, cplen); + + if (cplen < PAGE_SIZE) { + /* + * We're done, with a length that wasn't page + * aligned, so possibly not word aligned. Pad + * any trailing bytes with 0. + */ + xdr_encode_opaque_fixed(p, NULL, cplen); + break; + } + + buflen -= PAGE_SIZE; + buf += PAGE_SIZE; + } + + return 0; +} + +static __be32 +nfsd4_encode_getxattr(struct nfsd4_compoundres *resp, __be32 nfserr, + struct nfsd4_getxattr *getxattr) +{ + struct xdr_stream *xdr = &resp->xdr; + __be32 *p, err; + + p = xdr_reserve_space(xdr, 4); + if (!p) + return nfserr_resource; + + *p = cpu_to_be32(getxattr->getxa_len); + + if (getxattr->getxa_len == 0) + return 0; + + err = nfsd4_vbuf_to_stream(xdr, getxattr->getxa_buf, + getxattr->getxa_len); + + kvfree(getxattr->getxa_buf); + + return err; +} + +static __be32 +nfsd4_encode_setxattr(struct nfsd4_compoundres *resp, __be32 nfserr, + struct nfsd4_setxattr *setxattr) +{ + struct xdr_stream *xdr = &resp->xdr; + __be32 *p; + + p = xdr_reserve_space(xdr, 20); + if (!p) + return nfserr_resource; + + encode_cinfo(p, &setxattr->setxa_cinfo); + + return 0; +} + +/* + * See if there are cookie values that can be rejected outright. + */ +static __be32 +nfsd4_listxattr_validate_cookie(struct nfsd4_listxattrs *listxattrs, + u32 *offsetp) +{ + u64 cookie = listxattrs->lsxa_cookie; + + /* + * If the cookie is larger than the maximum number we can fit + * in either the buffer we just got back from vfs_listxattr, or, + * XDR-encoded, in the return buffer, it's invalid. + */ + if (cookie > (listxattrs->lsxa_len) / (XATTR_USER_PREFIX_LEN + 2)) + return nfserr_badcookie; + + if (cookie > (listxattrs->lsxa_maxcount / + (XDR_QUADLEN(XATTR_USER_PREFIX_LEN + 2) + 4))) + return nfserr_badcookie; + + *offsetp = (u32)cookie; + return 0; +} + +static __be32 +nfsd4_encode_listxattrs(struct nfsd4_compoundres *resp, __be32 nfserr, + struct nfsd4_listxattrs *listxattrs) +{ + struct xdr_stream *xdr = &resp->xdr; + u32 cookie_offset, count_offset, eof; + u32 left, xdrleft, slen, count; + u32 xdrlen, offset; + u64 cookie; + char *sp; + __be32 status; + __be32 *p; + u32 nuser; + + eof = 1; + + status = nfsd4_listxattr_validate_cookie(listxattrs, &offset); + if (status) + goto out; + + /* + * Reserve space for the cookie and the name array count. Record + * the offsets to save them later. + */ + cookie_offset = xdr->buf->len; + count_offset = cookie_offset + 8; + p = xdr_reserve_space(xdr, 12); + if (!p) { + status = nfserr_resource; + goto out; + } + + count = 0; + left = listxattrs->lsxa_len; + sp = listxattrs->lsxa_buf; + nuser = 0; + + xdrleft = listxattrs->lsxa_maxcount; + + while (left > 0 && xdrleft > 0) { + slen = strlen(sp); + + /* + * Check if this a user. attribute, skip it if not. + */ + if (strncmp(sp, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN)) + goto contloop; + + slen -= XATTR_USER_PREFIX_LEN; + xdrlen = 4 + ((slen + 3) & ~3); + if (xdrlen > xdrleft) { + if (count == 0) { + /* + * Can't even fit the first attribute name. + */ + status = nfserr_toosmall; + goto out; + } + eof = 0; + goto wreof; + } + + left -= XATTR_USER_PREFIX_LEN; + sp += XATTR_USER_PREFIX_LEN; + if (nuser++ < offset) + goto contloop; + + + p = xdr_reserve_space(xdr, xdrlen); + if (!p) { + status = nfserr_resource; + goto out; + } + + p = xdr_encode_opaque(p, sp, slen); + + xdrleft -= xdrlen; + count++; +contloop: + sp += slen + 1; + left -= slen + 1; + } + + /* + * If there were user attributes to copy, but we didn't copy + * any, the offset was too large (e.g. the cookie was invalid). + */ + if (nuser > 0 && count == 0) { + status = nfserr_badcookie; + goto out; + } + +wreof: + p = xdr_reserve_space(xdr, 4); + if (!p) { + status = nfserr_resource; + goto out; + } + *p = cpu_to_be32(eof); + + cookie = offset + count; + + write_bytes_to_xdr_buf(xdr->buf, cookie_offset, &cookie, 8); + count = htonl(count); + write_bytes_to_xdr_buf(xdr->buf, count_offset, &count, 4); +out: + if (listxattrs->lsxa_len) + kvfree(listxattrs->lsxa_buf); + return status; +} + +static __be32 +nfsd4_encode_removexattr(struct nfsd4_compoundres *resp, __be32 nfserr, + struct nfsd4_removexattr *removexattr) +{ + struct xdr_stream *xdr = &resp->xdr; + __be32 *p; + + p = xdr_reserve_space(xdr, 20); + if (!p) + return nfserr_resource; + + p = encode_cinfo(p, &removexattr->rmxa_cinfo); + return 0; +} + typedef __be32(* nfsd4_enc)(struct nfsd4_compoundres *, __be32, void *); /* @@ -4535,6 +5000,12 @@ static const nfsd4_enc nfsd4_enc_ops[] = { [OP_SEEK] = (nfsd4_enc)nfsd4_encode_seek, [OP_WRITE_SAME] = (nfsd4_enc)nfsd4_encode_noop, [OP_CLONE] = (nfsd4_enc)nfsd4_encode_noop, + + /* RFC 8276 extended atributes operations */ + [OP_GETXATTR] = (nfsd4_enc)nfsd4_encode_getxattr, + [OP_SETXATTR] = (nfsd4_enc)nfsd4_encode_setxattr, + [OP_LISTXATTRS] = (nfsd4_enc)nfsd4_encode_listxattrs, + [OP_REMOVEXATTR] = (nfsd4_enc)nfsd4_encode_removexattr, }; /* diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 57c832d1b30f..cb742e17e04a 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -286,6 +286,8 @@ void nfsd_lockd_shutdown(void); #define nfserr_wrong_lfs cpu_to_be32(NFS4ERR_WRONG_LFS) #define nfserr_badlabel cpu_to_be32(NFS4ERR_BADLABEL) #define nfserr_file_open cpu_to_be32(NFS4ERR_FILE_OPEN) +#define nfserr_xattr2big cpu_to_be32(NFS4ERR_XATTR2BIG) +#define nfserr_noxattr cpu_to_be32(NFS4ERR_NOXATTR) /* error codes for internal use */ /* if a request fails due to kmalloc failure, it gets dropped. @@ -387,7 +389,8 @@ void nfsd_lockd_shutdown(void); (NFSD4_1_SUPPORTED_ATTRS_WORD2 | \ FATTR4_WORD2_CHANGE_ATTR_TYPE | \ FATTR4_WORD2_MODE_UMASK | \ - NFSD4_2_SECURITY_ATTRS) + NFSD4_2_SECURITY_ATTRS | \ + FATTR4_WORD2_XATTR_SUPPORT) extern const u32 nfsd_suppattrs[3][3]; diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index d22a056da477..7d2933b85b65 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -612,6 +612,12 @@ static struct accessmap nfs3_regaccess[] = { { NFS3_ACCESS_MODIFY, NFSD_MAY_WRITE|NFSD_MAY_TRUNC }, { NFS3_ACCESS_EXTEND, NFSD_MAY_WRITE }, +#ifdef CONFIG_NFSD_V4 + { NFS4_ACCESS_XAREAD, NFSD_MAY_READ }, + { NFS4_ACCESS_XAWRITE, NFSD_MAY_WRITE }, + { NFS4_ACCESS_XALIST, NFSD_MAY_READ }, +#endif + { 0, 0 } }; @@ -622,6 +628,12 @@ static struct accessmap nfs3_diraccess[] = { { NFS3_ACCESS_EXTEND, NFSD_MAY_EXEC|NFSD_MAY_WRITE }, { NFS3_ACCESS_DELETE, NFSD_MAY_REMOVE }, +#ifdef CONFIG_NFSD_V4 + { NFS4_ACCESS_XAREAD, NFSD_MAY_READ }, + { NFS4_ACCESS_XAWRITE, NFSD_MAY_WRITE }, + { NFS4_ACCESS_XALIST, NFSD_MAY_READ }, +#endif + { 0, 0 } }; @@ -2065,6 +2077,233 @@ static int exp_rdonly(struct svc_rqst *rqstp, struct svc_export *exp) return nfsexp_flags(rqstp, exp) & NFSEXP_READONLY; } +#ifdef CONFIG_NFSD_V4 +/* + * Helper function to translate error numbers. In the case of xattr operations, + * some error codes need to be translated outside of the standard translations. + * + * ENODATA needs to be translated to nfserr_noxattr. + * E2BIG to nfserr_xattr2big. + * + * Additionally, vfs_listxattr can return -ERANGE. This means that the + * file has too many extended attributes to retrieve inside an + * XATTR_LIST_MAX sized buffer. This is a bug in the xattr implementation: + * filesystems will allow the adding of extended attributes until they hit + * their own internal limit. This limit may be larger than XATTR_LIST_MAX. + * So, at that point, the attributes are present and valid, but can't + * be retrieved using listxattr, since the upper level xattr code enforces + * the XATTR_LIST_MAX limit. + * + * This bug means that we need to deal with listxattr returning -ERANGE. The + * best mapping is to return TOOSMALL. + */ +static __be32 +nfsd_xattr_errno(int err) +{ + switch (err) { + case -ENODATA: + return nfserr_noxattr; + case -E2BIG: + return nfserr_xattr2big; + case -ERANGE: + return nfserr_toosmall; + } + return nfserrno(err); +} + +/* + * Retrieve the specified user extended attribute. To avoid always + * having to allocate the maximum size (since we are not getting + * a maximum size from the RPC), do a probe + alloc. Hold a reader + * lock on i_rwsem to prevent the extended attribute from changing + * size while we're doing this. + */ +__be32 +nfsd_getxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name, + void **bufp, int *lenp) +{ + ssize_t len; + __be32 err; + char *buf; + struct inode *inode; + struct dentry *dentry; + + err = fh_verify(rqstp, fhp, 0, NFSD_MAY_READ); + if (err) + return err; + + err = nfs_ok; + dentry = fhp->fh_dentry; + inode = d_inode(dentry); + + inode_lock_shared(inode); + + len = vfs_getxattr(dentry, name, NULL, 0); + + /* + * Zero-length attribute, just return. + */ + if (len == 0) { + *bufp = NULL; + *lenp = 0; + goto out; + } + + if (len < 0) { + err = nfsd_xattr_errno(len); + goto out; + } + + if (len > *lenp) { + err = nfserr_toosmall; + goto out; + } + + buf = kvmalloc(len, GFP_KERNEL | GFP_NOFS); + if (buf == NULL) { + err = nfserr_jukebox; + goto out; + } + + len = vfs_getxattr(dentry, name, buf, len); + if (len <= 0) { + kvfree(buf); + buf = NULL; + err = nfsd_xattr_errno(len); + } + + *lenp = len; + *bufp = buf; + +out: + inode_unlock_shared(inode); + + return err; +} + +/* + * Retrieve the xattr names. Since we can't know how many are + * user extended attributes, we must get all attributes here, + * and have the XDR encode filter out the "user." ones. + * + * While this could always just allocate an XATTR_LIST_MAX + * buffer, that's a waste, so do a probe + allocate. To + * avoid any changes between the probe and allocate, wrap + * this in inode_lock. + */ +__be32 +nfsd_listxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char **bufp, + int *lenp) +{ + ssize_t len; + __be32 err; + char *buf; + struct inode *inode; + struct dentry *dentry; + + err = fh_verify(rqstp, fhp, 0, NFSD_MAY_READ); + if (err) + return err; + + dentry = fhp->fh_dentry; + inode = d_inode(dentry); + *lenp = 0; + + inode_lock_shared(inode); + + len = vfs_listxattr(dentry, NULL, 0); + if (len <= 0) { + err = nfsd_xattr_errno(len); + goto out; + } + + if (len > XATTR_LIST_MAX) { + err = nfserr_xattr2big; + goto out; + } + + /* + * We're holding i_rwsem - use GFP_NOFS. + */ + buf = kvmalloc(len, GFP_KERNEL | GFP_NOFS); + if (buf == NULL) { + err = nfserr_jukebox; + goto out; + } + + len = vfs_listxattr(dentry, buf, len); + if (len <= 0) { + kvfree(buf); + err = nfsd_xattr_errno(len); + goto out; + } + + *lenp = len; + *bufp = buf; + + err = nfs_ok; +out: + inode_unlock_shared(inode); + + return err; +} + +/* + * Removexattr and setxattr need to call fh_lock to both lock the inode + * and set the change attribute. Since the top-level vfs_removexattr + * and vfs_setxattr calls already do their own inode_lock calls, call + * the _locked variant. Pass in a NULL pointer for delegated_inode, + * and let the client deal with NFS4ERR_DELAY (same as with e.g. + * setattr and remove). + */ +__be32 +nfsd_removexattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name) +{ + int err, ret; + + err = fh_verify(rqstp, fhp, 0, NFSD_MAY_WRITE); + if (err) + return err; + + ret = fh_want_write(fhp); + if (ret) + return nfserrno(ret); + + fh_lock(fhp); + + ret = __vfs_removexattr_locked(fhp->fh_dentry, name, NULL); + + fh_unlock(fhp); + fh_drop_write(fhp); + + return nfsd_xattr_errno(ret); +} + +__be32 +nfsd_setxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name, + void *buf, u32 len, u32 flags) +{ + int err, ret; + + err = fh_verify(rqstp, fhp, 0, NFSD_MAY_WRITE); + if (err) + return err; + + ret = fh_want_write(fhp); + if (ret) + return nfserrno(ret); + fh_lock(fhp); + + ret = __vfs_setxattr_locked(fhp->fh_dentry, name, buf, len, flags, + NULL); + + fh_unlock(fhp); + fh_drop_write(fhp); + + return nfsd_xattr_errno(ret); +} +#endif + /* * Check for a user's access permissions to this inode. */ diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h index 3eb660ad80d1..a2442ebe5acf 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -76,6 +76,16 @@ __be32 do_nfsd_create(struct svc_rqst *, struct svc_fh *, __be32 nfsd_commit(struct svc_rqst *, struct svc_fh *, loff_t, unsigned long, __be32 *verf); #endif /* CONFIG_NFSD_V3 */ +#ifdef CONFIG_NFSD_V4 +__be32 nfsd_getxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, + char *name, void **bufp, int *lenp); +__be32 nfsd_listxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, + char **bufp, int *lenp); +__be32 nfsd_removexattr(struct svc_rqst *rqstp, struct svc_fh *fhp, + char *name); +__be32 nfsd_setxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, + char *name, void *buf, u32 len, u32 flags); +#endif int nfsd_open_break_lease(struct inode *, int); __be32 nfsd_open(struct svc_rqst *, struct svc_fh *, umode_t, int, struct file **); diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index db63d39b1507..66499fb6b567 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -224,6 +224,32 @@ struct nfsd4_putfh { bool no_verify; /* represents foreigh fh */ }; +struct nfsd4_getxattr { + char *getxa_name; /* request */ + u32 getxa_len; /* request */ + void *getxa_buf; +}; + +struct nfsd4_setxattr { + u32 setxa_flags; /* request */ + char *setxa_name; /* request */ + char *setxa_buf; /* request */ + u32 setxa_len; /* request */ + struct nfsd4_change_info setxa_cinfo; /* response */ +}; + +struct nfsd4_removexattr { + char *rmxa_name; /* request */ + struct nfsd4_change_info rmxa_cinfo; /* response */ +}; + +struct nfsd4_listxattrs { + u64 lsxa_cookie; /* request */ + u32 lsxa_maxcount; /* request */ + char *lsxa_buf; /* unfiltered buffer (reply) */ + u32 lsxa_len; /* unfiltered len (reply) */ +}; + struct nfsd4_open { u32 op_claim_type; /* request */ struct xdr_netobj op_fname; /* request - everything but CLAIM_PREV */ @@ -649,6 +675,11 @@ struct nfsd4_op { struct nfsd4_offload_status offload_status; struct nfsd4_copy_notify copy_notify; struct nfsd4_seek seek; + + struct nfsd4_getxattr getxattr; + struct nfsd4_setxattr setxattr; + struct nfsd4_listxattrs listxattrs; + struct nfsd4_removexattr removexattr; } u; struct nfs4_replay * replay; }; diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c index 235b959fc2b3..adf3bb0a8048 100644 --- a/fs/nilfs2/alloc.c +++ b/fs/nilfs2/alloc.c @@ -613,10 +613,10 @@ void nilfs_palloc_commit_free_entry(struct inode *inode, lock = nilfs_mdt_bgl_lock(inode, group); if (!nilfs_clear_bit_atomic(lock, group_offset, bitmap)) - nilfs_msg(inode->i_sb, KERN_WARNING, - "%s (ino=%lu): entry number %llu already freed", - __func__, inode->i_ino, - (unsigned long long)req->pr_entry_nr); + nilfs_warn(inode->i_sb, + "%s (ino=%lu): entry number %llu already freed", + __func__, inode->i_ino, + (unsigned long long)req->pr_entry_nr); else nilfs_palloc_group_desc_add_entries(desc, lock, 1); @@ -654,10 +654,10 @@ void nilfs_palloc_abort_alloc_entry(struct inode *inode, lock = nilfs_mdt_bgl_lock(inode, group); if (!nilfs_clear_bit_atomic(lock, group_offset, bitmap)) - nilfs_msg(inode->i_sb, KERN_WARNING, - "%s (ino=%lu): entry number %llu already freed", - __func__, inode->i_ino, - (unsigned long long)req->pr_entry_nr); + nilfs_warn(inode->i_sb, + "%s (ino=%lu): entry number %llu already freed", + __func__, inode->i_ino, + (unsigned long long)req->pr_entry_nr); else nilfs_palloc_group_desc_add_entries(desc, lock, 1); @@ -763,10 +763,10 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems) do { if (!nilfs_clear_bit_atomic(lock, group_offset, bitmap)) { - nilfs_msg(inode->i_sb, KERN_WARNING, - "%s (ino=%lu): entry number %llu already freed", - __func__, inode->i_ino, - (unsigned long long)entry_nrs[j]); + nilfs_warn(inode->i_sb, + "%s (ino=%lu): entry number %llu already freed", + __func__, inode->i_ino, + (unsigned long long)entry_nrs[j]); } else { n++; } @@ -808,10 +808,10 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems) ret = nilfs_palloc_delete_entry_block(inode, last_nrs[k]); if (ret && ret != -ENOENT) - nilfs_msg(inode->i_sb, KERN_WARNING, - "error %d deleting block that object (entry=%llu, ino=%lu) belongs to", - ret, (unsigned long long)last_nrs[k], - inode->i_ino); + nilfs_warn(inode->i_sb, + "error %d deleting block that object (entry=%llu, ino=%lu) belongs to", + ret, (unsigned long long)last_nrs[k], + inode->i_ino); } desc_kaddr = kmap_atomic(desc_bh->b_page); @@ -826,9 +826,9 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems) if (nfree == nilfs_palloc_entries_per_group(inode)) { ret = nilfs_palloc_delete_bitmap_block(inode, group); if (ret && ret != -ENOENT) - nilfs_msg(inode->i_sb, KERN_WARNING, - "error %d deleting bitmap block of group=%lu, ino=%lu", - ret, group, inode->i_ino); + nilfs_warn(inode->i_sb, + "error %d deleting bitmap block of group=%lu, ino=%lu", + ret, group, inode->i_ino); } } return 0; diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index 23e043eca237..f42ab57201e7 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -351,10 +351,10 @@ static int nilfs_btree_node_broken(const struct nilfs_btree_node *node, (flags & NILFS_BTREE_NODE_ROOT) || nchildren < 0 || nchildren > NILFS_BTREE_NODE_NCHILDREN_MAX(size))) { - nilfs_msg(inode->i_sb, KERN_CRIT, - "bad btree node (ino=%lu, blocknr=%llu): level = %d, flags = 0x%x, nchildren = %d", - inode->i_ino, (unsigned long long)blocknr, level, - flags, nchildren); + nilfs_crit(inode->i_sb, + "bad btree node (ino=%lu, blocknr=%llu): level = %d, flags = 0x%x, nchildren = %d", + inode->i_ino, (unsigned long long)blocknr, level, + flags, nchildren); ret = 1; } return ret; @@ -381,9 +381,9 @@ static int nilfs_btree_root_broken(const struct nilfs_btree_node *node, level >= NILFS_BTREE_LEVEL_MAX || nchildren < 0 || nchildren > NILFS_BTREE_ROOT_NCHILDREN_MAX)) { - nilfs_msg(inode->i_sb, KERN_CRIT, - "bad btree root (ino=%lu): level = %d, flags = 0x%x, nchildren = %d", - inode->i_ino, level, flags, nchildren); + nilfs_crit(inode->i_sb, + "bad btree root (ino=%lu): level = %d, flags = 0x%x, nchildren = %d", + inode->i_ino, level, flags, nchildren); ret = 1; } return ret; @@ -450,10 +450,10 @@ static int nilfs_btree_bad_node(const struct nilfs_bmap *btree, { if (unlikely(nilfs_btree_node_get_level(node) != level)) { dump_stack(); - nilfs_msg(btree->b_inode->i_sb, KERN_CRIT, - "btree level mismatch (ino=%lu): %d != %d", - btree->b_inode->i_ino, - nilfs_btree_node_get_level(node), level); + nilfs_crit(btree->b_inode->i_sb, + "btree level mismatch (ino=%lu): %d != %d", + btree->b_inode->i_ino, + nilfs_btree_node_get_level(node), level); return 1; } return 0; @@ -508,7 +508,7 @@ static int __nilfs_btree_get_block(const struct nilfs_bmap *btree, __u64 ptr, out_no_wait: if (!buffer_uptodate(bh)) { - nilfs_msg(btree->b_inode->i_sb, KERN_ERR, + nilfs_err(btree->b_inode->i_sb, "I/O error reading b-tree node block (ino=%lu, blocknr=%llu)", btree->b_inode->i_ino, (unsigned long long)ptr); brelse(bh); @@ -2074,10 +2074,10 @@ static int nilfs_btree_propagate(struct nilfs_bmap *btree, ret = nilfs_btree_do_lookup(btree, path, key, NULL, level + 1, 0); if (ret < 0) { if (unlikely(ret == -ENOENT)) - nilfs_msg(btree->b_inode->i_sb, KERN_CRIT, - "writing node/leaf block does not appear in b-tree (ino=%lu) at key=%llu, level=%d", - btree->b_inode->i_ino, - (unsigned long long)key, level); + nilfs_crit(btree->b_inode->i_sb, + "writing node/leaf block does not appear in b-tree (ino=%lu) at key=%llu, level=%d", + btree->b_inode->i_ino, + (unsigned long long)key, level); goto out; } @@ -2114,11 +2114,11 @@ static void nilfs_btree_add_dirty_buffer(struct nilfs_bmap *btree, if (level < NILFS_BTREE_LEVEL_NODE_MIN || level >= NILFS_BTREE_LEVEL_MAX) { dump_stack(); - nilfs_msg(btree->b_inode->i_sb, KERN_WARNING, - "invalid btree level: %d (key=%llu, ino=%lu, blocknr=%llu)", - level, (unsigned long long)key, - btree->b_inode->i_ino, - (unsigned long long)bh->b_blocknr); + nilfs_warn(btree->b_inode->i_sb, + "invalid btree level: %d (key=%llu, ino=%lu, blocknr=%llu)", + level, (unsigned long long)key, + btree->b_inode->i_ino, + (unsigned long long)bh->b_blocknr); return; } diff --git a/fs/nilfs2/cpfile.c b/fs/nilfs2/cpfile.c index 8d41311b5db4..86d4d850d130 100644 --- a/fs/nilfs2/cpfile.c +++ b/fs/nilfs2/cpfile.c @@ -322,7 +322,7 @@ int nilfs_cpfile_delete_checkpoints(struct inode *cpfile, int ret, ncps, nicps, nss, count, i; if (unlikely(start == 0 || start > end)) { - nilfs_msg(cpfile->i_sb, KERN_ERR, + nilfs_err(cpfile->i_sb, "cannot delete checkpoints: invalid range [%llu, %llu)", (unsigned long long)start, (unsigned long long)end); return -EINVAL; @@ -376,7 +376,7 @@ int nilfs_cpfile_delete_checkpoints(struct inode *cpfile, cpfile, cno); if (ret == 0) continue; - nilfs_msg(cpfile->i_sb, KERN_ERR, + nilfs_err(cpfile->i_sb, "error %d deleting checkpoint block", ret); break; @@ -981,12 +981,10 @@ int nilfs_cpfile_read(struct super_block *sb, size_t cpsize, int err; if (cpsize > sb->s_blocksize) { - nilfs_msg(sb, KERN_ERR, - "too large checkpoint size: %zu bytes", cpsize); + nilfs_err(sb, "too large checkpoint size: %zu bytes", cpsize); return -EINVAL; } else if (cpsize < NILFS_MIN_CHECKPOINT_SIZE) { - nilfs_msg(sb, KERN_ERR, - "too small checkpoint size: %zu bytes", cpsize); + nilfs_err(sb, "too small checkpoint size: %zu bytes", cpsize); return -EINVAL; } diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c index 6f4066636be9..8bccdf1158fc 100644 --- a/fs/nilfs2/dat.c +++ b/fs/nilfs2/dat.c @@ -340,11 +340,11 @@ int nilfs_dat_move(struct inode *dat, __u64 vblocknr, sector_t blocknr) kaddr = kmap_atomic(entry_bh->b_page); entry = nilfs_palloc_block_get_entry(dat, vblocknr, entry_bh, kaddr); if (unlikely(entry->de_blocknr == cpu_to_le64(0))) { - nilfs_msg(dat->i_sb, KERN_CRIT, - "%s: invalid vblocknr = %llu, [%llu, %llu)", - __func__, (unsigned long long)vblocknr, - (unsigned long long)le64_to_cpu(entry->de_start), - (unsigned long long)le64_to_cpu(entry->de_end)); + nilfs_crit(dat->i_sb, + "%s: invalid vblocknr = %llu, [%llu, %llu)", + __func__, (unsigned long long)vblocknr, + (unsigned long long)le64_to_cpu(entry->de_start), + (unsigned long long)le64_to_cpu(entry->de_end)); kunmap_atomic(kaddr); brelse(entry_bh); return -EINVAL; @@ -471,11 +471,11 @@ int nilfs_dat_read(struct super_block *sb, size_t entry_size, int err; if (entry_size > sb->s_blocksize) { - nilfs_msg(sb, KERN_ERR, "too large DAT entry size: %zu bytes", + nilfs_err(sb, "too large DAT entry size: %zu bytes", entry_size); return -EINVAL; } else if (entry_size < NILFS_MIN_DAT_ENTRY_SIZE) { - nilfs_msg(sb, KERN_ERR, "too small DAT entry size: %zu bytes", + nilfs_err(sb, "too small DAT entry size: %zu bytes", entry_size); return -EINVAL; } diff --git a/fs/nilfs2/direct.c b/fs/nilfs2/direct.c index 533e24ea3a88..f353101955e3 100644 --- a/fs/nilfs2/direct.c +++ b/fs/nilfs2/direct.c @@ -328,16 +328,18 @@ static int nilfs_direct_assign(struct nilfs_bmap *bmap, key = nilfs_bmap_data_get_key(bmap, *bh); if (unlikely(key > NILFS_DIRECT_KEY_MAX)) { - nilfs_msg(bmap->b_inode->i_sb, KERN_CRIT, - "%s (ino=%lu): invalid key: %llu", __func__, - bmap->b_inode->i_ino, (unsigned long long)key); + nilfs_crit(bmap->b_inode->i_sb, + "%s (ino=%lu): invalid key: %llu", + __func__, + bmap->b_inode->i_ino, (unsigned long long)key); return -EINVAL; } ptr = nilfs_direct_get_ptr(bmap, key); if (unlikely(ptr == NILFS_BMAP_INVALID_PTR)) { - nilfs_msg(bmap->b_inode->i_sb, KERN_CRIT, - "%s (ino=%lu): invalid pointer: %llu", __func__, - bmap->b_inode->i_ino, (unsigned long long)ptr); + nilfs_crit(bmap->b_inode->i_sb, + "%s (ino=%lu): invalid pointer: %llu", + __func__, + bmap->b_inode->i_ino, (unsigned long long)ptr); return -EINVAL; } diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c index aa3c328ee189..448320496856 100644 --- a/fs/nilfs2/gcinode.c +++ b/fs/nilfs2/gcinode.c @@ -142,7 +142,7 @@ int nilfs_gccache_wait_and_mark_dirty(struct buffer_head *bh) if (!buffer_uptodate(bh)) { struct inode *inode = bh->b_page->mapping->host; - nilfs_msg(inode->i_sb, KERN_ERR, + nilfs_err(inode->i_sb, "I/O error reading %s block for GC (ino=%lu, vblocknr=%llu)", buffer_nilfs_node(bh) ? "node" : "data", inode->i_ino, (unsigned long long)bh->b_blocknr); diff --git a/fs/nilfs2/ifile.c b/fs/nilfs2/ifile.c index 4140d232cadc..02727ed3a7c6 100644 --- a/fs/nilfs2/ifile.c +++ b/fs/nilfs2/ifile.c @@ -142,8 +142,8 @@ int nilfs_ifile_get_inode_block(struct inode *ifile, ino_t ino, err = nilfs_palloc_get_entry_block(ifile, ino, 0, out_bh); if (unlikely(err)) - nilfs_msg(sb, KERN_WARNING, "error %d reading inode: ino=%lu", - err, (unsigned long)ino); + nilfs_warn(sb, "error %d reading inode: ino=%lu", + err, (unsigned long)ino); return err; } diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 28009ec54420..745d371d6fea 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -104,10 +104,10 @@ int nilfs_get_block(struct inode *inode, sector_t blkoff, * However, the page having this block must * be locked in this case. */ - nilfs_msg(inode->i_sb, KERN_WARNING, - "%s (ino=%lu): a race condition while inserting a data block at offset=%llu", - __func__, inode->i_ino, - (unsigned long long)blkoff); + nilfs_warn(inode->i_sb, + "%s (ino=%lu): a race condition while inserting a data block at offset=%llu", + __func__, inode->i_ino, + (unsigned long long)blkoff); err = 0; } nilfs_transaction_abort(inode->i_sb); @@ -388,7 +388,8 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode) failed_after_creation: clear_nlink(inode); - unlock_new_inode(inode); + if (inode->i_state & I_NEW) + unlock_new_inode(inode); iput(inode); /* * raw_inode will be deleted through * nilfs_evict_inode(). @@ -706,9 +707,8 @@ repeat: goto repeat; failed: - nilfs_msg(ii->vfs_inode.i_sb, KERN_WARNING, - "error %d truncating bmap (ino=%lu)", ret, - ii->vfs_inode.i_ino); + nilfs_warn(ii->vfs_inode.i_sb, "error %d truncating bmap (ino=%lu)", + ret, ii->vfs_inode.i_ino); } void nilfs_truncate(struct inode *inode) @@ -919,9 +919,9 @@ int nilfs_set_file_dirty(struct inode *inode, unsigned int nr_dirty) * This will happen when somebody is freeing * this inode. */ - nilfs_msg(inode->i_sb, KERN_WARNING, - "cannot set file dirty (ino=%lu): the file is being freed", - inode->i_ino); + nilfs_warn(inode->i_sb, + "cannot set file dirty (ino=%lu): the file is being freed", + inode->i_ino); spin_unlock(&nilfs->ns_inode_lock); return -EINVAL; /* * NILFS_I_DIRTY may remain for @@ -942,9 +942,9 @@ int __nilfs_mark_inode_dirty(struct inode *inode, int flags) err = nilfs_load_inode_block(inode, &ibh); if (unlikely(err)) { - nilfs_msg(inode->i_sb, KERN_WARNING, - "cannot mark inode dirty (ino=%lu): error %d loading inode block", - inode->i_ino, err); + nilfs_warn(inode->i_sb, + "cannot mark inode dirty (ino=%lu): error %d loading inode block", + inode->i_ino, err); return err; } nilfs_update_inode(inode, ibh, flags); @@ -970,8 +970,8 @@ void nilfs_dirty_inode(struct inode *inode, int flags) struct nilfs_mdt_info *mdi = NILFS_MDT(inode); if (is_bad_inode(inode)) { - nilfs_msg(inode->i_sb, KERN_WARNING, - "tried to mark bad_inode dirty. ignored."); + nilfs_warn(inode->i_sb, + "tried to mark bad_inode dirty. ignored."); dump_stack(); return; } diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c index 4ba73dbf3e8d..07d26f61f22a 100644 --- a/fs/nilfs2/ioctl.c +++ b/fs/nilfs2/ioctl.c @@ -569,25 +569,25 @@ static int nilfs_ioctl_move_inode_block(struct inode *inode, if (unlikely(ret < 0)) { if (ret == -ENOENT) - nilfs_msg(inode->i_sb, KERN_CRIT, - "%s: invalid virtual block address (%s): ino=%llu, cno=%llu, offset=%llu, blocknr=%llu, vblocknr=%llu", - __func__, vdesc->vd_flags ? "node" : "data", - (unsigned long long)vdesc->vd_ino, - (unsigned long long)vdesc->vd_cno, - (unsigned long long)vdesc->vd_offset, - (unsigned long long)vdesc->vd_blocknr, - (unsigned long long)vdesc->vd_vblocknr); + nilfs_crit(inode->i_sb, + "%s: invalid virtual block address (%s): ino=%llu, cno=%llu, offset=%llu, blocknr=%llu, vblocknr=%llu", + __func__, vdesc->vd_flags ? "node" : "data", + (unsigned long long)vdesc->vd_ino, + (unsigned long long)vdesc->vd_cno, + (unsigned long long)vdesc->vd_offset, + (unsigned long long)vdesc->vd_blocknr, + (unsigned long long)vdesc->vd_vblocknr); return ret; } if (unlikely(!list_empty(&bh->b_assoc_buffers))) { - nilfs_msg(inode->i_sb, KERN_CRIT, - "%s: conflicting %s buffer: ino=%llu, cno=%llu, offset=%llu, blocknr=%llu, vblocknr=%llu", - __func__, vdesc->vd_flags ? "node" : "data", - (unsigned long long)vdesc->vd_ino, - (unsigned long long)vdesc->vd_cno, - (unsigned long long)vdesc->vd_offset, - (unsigned long long)vdesc->vd_blocknr, - (unsigned long long)vdesc->vd_vblocknr); + nilfs_crit(inode->i_sb, + "%s: conflicting %s buffer: ino=%llu, cno=%llu, offset=%llu, blocknr=%llu, vblocknr=%llu", + __func__, vdesc->vd_flags ? "node" : "data", + (unsigned long long)vdesc->vd_ino, + (unsigned long long)vdesc->vd_cno, + (unsigned long long)vdesc->vd_offset, + (unsigned long long)vdesc->vd_blocknr, + (unsigned long long)vdesc->vd_vblocknr); brelse(bh); return -EEXIST; } @@ -837,8 +837,7 @@ int nilfs_ioctl_prepare_clean_segments(struct the_nilfs *nilfs, return 0; failed: - nilfs_msg(nilfs->ns_sb, KERN_ERR, "error %d preparing GC: %s", ret, - msg); + nilfs_err(nilfs->ns_sb, "error %d preparing GC: %s", ret, msg); return ret; } @@ -947,7 +946,7 @@ static int nilfs_ioctl_clean_segments(struct inode *inode, struct file *filp, ret = nilfs_ioctl_move_blocks(inode->i_sb, &argv[0], kbufs[0]); if (ret < 0) { - nilfs_msg(inode->i_sb, KERN_ERR, + nilfs_err(inode->i_sb, "error %d preparing GC: cannot read source blocks", ret); } else { diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c index 700870a92bc4..c0361ce45f62 100644 --- a/fs/nilfs2/mdt.c +++ b/fs/nilfs2/mdt.c @@ -199,7 +199,7 @@ static int nilfs_mdt_read_block(struct inode *inode, unsigned long block, out_no_wait: err = -EIO; if (!buffer_uptodate(first_bh)) { - nilfs_msg(inode->i_sb, KERN_ERR, + nilfs_err(inode->i_sb, "I/O error reading meta-data file (ino=%lu, block-offset=%lu)", inode->i_ino, block); goto failed_bh; diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c index 9fe6d4ab74f0..a6ec7961d4f5 100644 --- a/fs/nilfs2/namei.c +++ b/fs/nilfs2/namei.c @@ -272,9 +272,9 @@ static int nilfs_do_unlink(struct inode *dir, struct dentry *dentry) goto out; if (!inode->i_nlink) { - nilfs_msg(inode->i_sb, KERN_WARNING, - "deleting nonexistent file (ino=%lu), %d", - inode->i_ino, inode->i_nlink); + nilfs_warn(inode->i_sb, + "deleting nonexistent file (ino=%lu), %d", + inode->i_ino, inode->i_nlink); set_nlink(inode, 1); } err = nilfs_delete_entry(de, page); diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index 42395ba52da6..f8450ee3fd06 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -289,9 +289,8 @@ static inline int nilfs_mark_inode_dirty_sync(struct inode *inode) /* super.c */ extern struct inode *nilfs_alloc_inode(struct super_block *); -extern __printf(3, 4) -void __nilfs_msg(struct super_block *sb, const char *level, - const char *fmt, ...); +__printf(2, 3) +void __nilfs_msg(struct super_block *sb, const char *fmt, ...); extern __printf(3, 4) void __nilfs_error(struct super_block *sb, const char *function, const char *fmt, ...); @@ -299,7 +298,7 @@ void __nilfs_error(struct super_block *sb, const char *function, #ifdef CONFIG_PRINTK #define nilfs_msg(sb, level, fmt, ...) \ - __nilfs_msg(sb, level, fmt, ##__VA_ARGS__) + __nilfs_msg(sb, level fmt, ##__VA_ARGS__) #define nilfs_error(sb, fmt, ...) \ __nilfs_error(sb, __func__, fmt, ##__VA_ARGS__) @@ -307,7 +306,7 @@ void __nilfs_error(struct super_block *sb, const char *function, #define nilfs_msg(sb, level, fmt, ...) \ do { \ - no_printk(fmt, ##__VA_ARGS__); \ + no_printk(level fmt, ##__VA_ARGS__); \ (void)(sb); \ } while (0) #define nilfs_error(sb, fmt, ...) \ @@ -318,6 +317,15 @@ void __nilfs_error(struct super_block *sb, const char *function, #endif /* CONFIG_PRINTK */ +#define nilfs_crit(sb, fmt, ...) \ + nilfs_msg(sb, KERN_CRIT, fmt, ##__VA_ARGS__) +#define nilfs_err(sb, fmt, ...) \ + nilfs_msg(sb, KERN_ERR, fmt, ##__VA_ARGS__) +#define nilfs_warn(sb, fmt, ...) \ + nilfs_msg(sb, KERN_WARNING, fmt, ##__VA_ARGS__) +#define nilfs_info(sb, fmt, ...) \ + nilfs_msg(sb, KERN_INFO, fmt, ##__VA_ARGS__) + extern struct nilfs_super_block * nilfs_read_super_block(struct super_block *, u64, int, struct buffer_head **); extern int nilfs_store_magic_and_option(struct super_block *, diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index d7fc8d369d89..b175f1330408 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -391,9 +391,8 @@ void nilfs_clear_dirty_page(struct page *page, bool silent) BUG_ON(!PageLocked(page)); if (!silent) - nilfs_msg(sb, KERN_WARNING, - "discard dirty page: offset=%lld, ino=%lu", - page_offset(page), inode->i_ino); + nilfs_warn(sb, "discard dirty page: offset=%lld, ino=%lu", + page_offset(page), inode->i_ino); ClearPageUptodate(page); ClearPageMappedToDisk(page); @@ -409,9 +408,9 @@ void nilfs_clear_dirty_page(struct page *page, bool silent) do { lock_buffer(bh); if (!silent) - nilfs_msg(sb, KERN_WARNING, - "discard dirty block: blocknr=%llu, size=%zu", - (u64)bh->b_blocknr, bh->b_size); + nilfs_warn(sb, + "discard dirty block: blocknr=%llu, size=%zu", + (u64)bh->b_blocknr, bh->b_size); set_mask_bits(&bh->b_state, clear_bits, 0); unlock_buffer(bh); diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c index 140b663e91c7..0b453ef8fae5 100644 --- a/fs/nilfs2/recovery.c +++ b/fs/nilfs2/recovery.c @@ -51,7 +51,7 @@ static int nilfs_warn_segment_error(struct super_block *sb, int err) switch (err) { case NILFS_SEG_FAIL_IO: - nilfs_msg(sb, KERN_ERR, "I/O error reading segment"); + nilfs_err(sb, "I/O error reading segment"); return -EIO; case NILFS_SEG_FAIL_MAGIC: msg = "Magic number mismatch"; @@ -72,10 +72,10 @@ static int nilfs_warn_segment_error(struct super_block *sb, int err) msg = "No super root in the last segment"; break; default: - nilfs_msg(sb, KERN_ERR, "unrecognized segment error %d", err); + nilfs_err(sb, "unrecognized segment error %d", err); return -EINVAL; } - nilfs_msg(sb, KERN_WARNING, "invalid segment: %s", msg); + nilfs_warn(sb, "invalid segment: %s", msg); return -EINVAL; } @@ -543,10 +543,10 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs, put_page(page); failed_inode: - nilfs_msg(sb, KERN_WARNING, - "error %d recovering data block (ino=%lu, block-offset=%llu)", - err, (unsigned long)rb->ino, - (unsigned long long)rb->blkoff); + nilfs_warn(sb, + "error %d recovering data block (ino=%lu, block-offset=%llu)", + err, (unsigned long)rb->ino, + (unsigned long long)rb->blkoff); if (!err2) err2 = err; next: @@ -669,8 +669,7 @@ static int nilfs_do_roll_forward(struct the_nilfs *nilfs, } if (nsalvaged_blocks) { - nilfs_msg(sb, KERN_INFO, "salvaged %lu blocks", - nsalvaged_blocks); + nilfs_info(sb, "salvaged %lu blocks", nsalvaged_blocks); ri->ri_need_recovery = NILFS_RECOVERY_ROLLFORWARD_DONE; } out: @@ -681,7 +680,7 @@ static int nilfs_do_roll_forward(struct the_nilfs *nilfs, confused: err = -EINVAL; failed: - nilfs_msg(sb, KERN_ERR, + nilfs_err(sb, "error %d roll-forwarding partial segment at blocknr = %llu", err, (unsigned long long)pseg_start); goto out; @@ -703,8 +702,8 @@ static void nilfs_finish_roll_forward(struct the_nilfs *nilfs, set_buffer_dirty(bh); err = sync_dirty_buffer(bh); if (unlikely(err)) - nilfs_msg(nilfs->ns_sb, KERN_WARNING, - "buffer sync write failed during post-cleaning of recovery."); + nilfs_warn(nilfs->ns_sb, + "buffer sync write failed during post-cleaning of recovery."); brelse(bh); } @@ -739,8 +738,7 @@ int nilfs_salvage_orphan_logs(struct the_nilfs *nilfs, err = nilfs_attach_checkpoint(sb, ri->ri_cno, true, &root); if (unlikely(err)) { - nilfs_msg(sb, KERN_ERR, - "error %d loading the latest checkpoint", err); + nilfs_err(sb, "error %d loading the latest checkpoint", err); return err; } @@ -751,8 +749,7 @@ int nilfs_salvage_orphan_logs(struct the_nilfs *nilfs, if (ri->ri_need_recovery == NILFS_RECOVERY_ROLLFORWARD_DONE) { err = nilfs_prepare_segment_for_recovery(nilfs, sb, ri); if (unlikely(err)) { - nilfs_msg(sb, KERN_ERR, - "error %d preparing segment for recovery", + nilfs_err(sb, "error %d preparing segment for recovery", err); goto failed; } @@ -766,8 +763,7 @@ int nilfs_salvage_orphan_logs(struct the_nilfs *nilfs, nilfs_detach_log_writer(sb); if (unlikely(err)) { - nilfs_msg(sb, KERN_ERR, - "error %d writing segment for recovery", + nilfs_err(sb, "error %d writing segment for recovery", err); goto failed; } diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c index 20c479b5e41b..1a8729eded8b 100644 --- a/fs/nilfs2/segbuf.c +++ b/fs/nilfs2/segbuf.c @@ -505,7 +505,7 @@ static int nilfs_segbuf_wait(struct nilfs_segment_buffer *segbuf) } while (--segbuf->sb_nbio > 0); if (unlikely(atomic_read(&segbuf->sb_err) > 0)) { - nilfs_msg(segbuf->sb_super, KERN_ERR, + nilfs_err(segbuf->sb_super, "I/O error writing log (start-blocknr=%llu, block-count=%lu) in segment %llu", (unsigned long long)segbuf->sb_pseg_start, segbuf->sb_sum.nblocks, diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 91b58c897f92..a651e821c2de 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -158,7 +158,7 @@ static int nilfs_prepare_segment_lock(struct super_block *sb, * it is saved and will be restored on * nilfs_transaction_commit(). */ - nilfs_msg(sb, KERN_WARNING, "journal info from a different FS"); + nilfs_warn(sb, "journal info from a different FS"); save = current->journal_info; } if (!ti) { @@ -1940,9 +1940,9 @@ static int nilfs_segctor_collect_dirty_files(struct nilfs_sc_info *sci, err = nilfs_ifile_get_inode_block( ifile, ii->vfs_inode.i_ino, &ibh); if (unlikely(err)) { - nilfs_msg(sci->sc_super, KERN_WARNING, - "log writer: error %d getting inode block (ino=%lu)", - err, ii->vfs_inode.i_ino); + nilfs_warn(sci->sc_super, + "log writer: error %d getting inode block (ino=%lu)", + err, ii->vfs_inode.i_ino); return err; } spin_lock(&nilfs->ns_inode_lock); @@ -2449,7 +2449,7 @@ int nilfs_clean_segments(struct super_block *sb, struct nilfs_argv *argv, if (likely(!err)) break; - nilfs_msg(sb, KERN_WARNING, "error %d cleaning segments", err); + nilfs_warn(sb, "error %d cleaning segments", err); set_current_state(TASK_INTERRUPTIBLE); schedule_timeout(sci->sc_interval); } @@ -2457,9 +2457,9 @@ int nilfs_clean_segments(struct super_block *sb, struct nilfs_argv *argv, int ret = nilfs_discard_segments(nilfs, sci->sc_freesegs, sci->sc_nfreesegs); if (ret) { - nilfs_msg(sb, KERN_WARNING, - "error %d on discard request, turning discards off for the device", - ret); + nilfs_warn(sb, + "error %d on discard request, turning discards off for the device", + ret); nilfs_clear_opt(nilfs, DISCARD); } } @@ -2540,9 +2540,9 @@ static int nilfs_segctor_thread(void *arg) /* start sync. */ sci->sc_task = current; wake_up(&sci->sc_wait_task); /* for nilfs_segctor_start_thread() */ - nilfs_msg(sci->sc_super, KERN_INFO, - "segctord starting. Construction interval = %lu seconds, CP frequency < %lu seconds", - sci->sc_interval / HZ, sci->sc_mjcp_freq / HZ); + nilfs_info(sci->sc_super, + "segctord starting. Construction interval = %lu seconds, CP frequency < %lu seconds", + sci->sc_interval / HZ, sci->sc_mjcp_freq / HZ); spin_lock(&sci->sc_state_lock); loop: @@ -2616,8 +2616,8 @@ static int nilfs_segctor_start_thread(struct nilfs_sc_info *sci) if (IS_ERR(t)) { int err = PTR_ERR(t); - nilfs_msg(sci->sc_super, KERN_ERR, - "error %d creating segctord thread", err); + nilfs_err(sci->sc_super, "error %d creating segctord thread", + err); return err; } wait_event(sci->sc_wait_task, sci->sc_task != NULL); @@ -2727,14 +2727,14 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci) nilfs_segctor_write_out(sci); if (!list_empty(&sci->sc_dirty_files)) { - nilfs_msg(sci->sc_super, KERN_WARNING, - "disposed unprocessed dirty file(s) when stopping log writer"); + nilfs_warn(sci->sc_super, + "disposed unprocessed dirty file(s) when stopping log writer"); nilfs_dispose_list(nilfs, &sci->sc_dirty_files, 1); } if (!list_empty(&sci->sc_iput_queue)) { - nilfs_msg(sci->sc_super, KERN_WARNING, - "disposed unprocessed inode(s) in iput queue when stopping log writer"); + nilfs_warn(sci->sc_super, + "disposed unprocessed inode(s) in iput queue when stopping log writer"); nilfs_dispose_list(nilfs, &sci->sc_iput_queue, 1); } @@ -2812,8 +2812,8 @@ void nilfs_detach_log_writer(struct super_block *sb) spin_lock(&nilfs->ns_inode_lock); if (!list_empty(&nilfs->ns_dirty_files)) { list_splice_init(&nilfs->ns_dirty_files, &garbage_list); - nilfs_msg(sb, KERN_WARNING, - "disposed unprocessed dirty file(s) when detaching log writer"); + nilfs_warn(sb, + "disposed unprocessed dirty file(s) when detaching log writer"); } spin_unlock(&nilfs->ns_inode_lock); up_write(&nilfs->ns_segctor_sem); diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c index bf3f8f05c89b..42ff67c0c14f 100644 --- a/fs/nilfs2/sufile.c +++ b/fs/nilfs2/sufile.c @@ -171,9 +171,9 @@ int nilfs_sufile_updatev(struct inode *sufile, __u64 *segnumv, size_t nsegs, down_write(&NILFS_MDT(sufile)->mi_sem); for (seg = segnumv; seg < segnumv + nsegs; seg++) { if (unlikely(*seg >= nilfs_sufile_get_nsegments(sufile))) { - nilfs_msg(sufile->i_sb, KERN_WARNING, - "%s: invalid segment number: %llu", - __func__, (unsigned long long)*seg); + nilfs_warn(sufile->i_sb, + "%s: invalid segment number: %llu", + __func__, (unsigned long long)*seg); nerr++; } } @@ -230,9 +230,8 @@ int nilfs_sufile_update(struct inode *sufile, __u64 segnum, int create, int ret; if (unlikely(segnum >= nilfs_sufile_get_nsegments(sufile))) { - nilfs_msg(sufile->i_sb, KERN_WARNING, - "%s: invalid segment number: %llu", - __func__, (unsigned long long)segnum); + nilfs_warn(sufile->i_sb, "%s: invalid segment number: %llu", + __func__, (unsigned long long)segnum); return -EINVAL; } down_write(&NILFS_MDT(sufile)->mi_sem); @@ -410,9 +409,8 @@ void nilfs_sufile_do_cancel_free(struct inode *sufile, __u64 segnum, kaddr = kmap_atomic(su_bh->b_page); su = nilfs_sufile_block_get_segment_usage(sufile, segnum, su_bh, kaddr); if (unlikely(!nilfs_segment_usage_clean(su))) { - nilfs_msg(sufile->i_sb, KERN_WARNING, - "%s: segment %llu must be clean", __func__, - (unsigned long long)segnum); + nilfs_warn(sufile->i_sb, "%s: segment %llu must be clean", + __func__, (unsigned long long)segnum); kunmap_atomic(kaddr); return; } @@ -468,9 +466,8 @@ void nilfs_sufile_do_free(struct inode *sufile, __u64 segnum, kaddr = kmap_atomic(su_bh->b_page); su = nilfs_sufile_block_get_segment_usage(sufile, segnum, su_bh, kaddr); if (nilfs_segment_usage_clean(su)) { - nilfs_msg(sufile->i_sb, KERN_WARNING, - "%s: segment %llu is already clean", - __func__, (unsigned long long)segnum); + nilfs_warn(sufile->i_sb, "%s: segment %llu is already clean", + __func__, (unsigned long long)segnum); kunmap_atomic(kaddr); return; } @@ -1168,12 +1165,12 @@ int nilfs_sufile_read(struct super_block *sb, size_t susize, int err; if (susize > sb->s_blocksize) { - nilfs_msg(sb, KERN_ERR, - "too large segment usage size: %zu bytes", susize); + nilfs_err(sb, "too large segment usage size: %zu bytes", + susize); return -EINVAL; } else if (susize < NILFS_MIN_SEGMENT_USAGE_SIZE) { - nilfs_msg(sb, KERN_ERR, - "too small segment usage size: %zu bytes", susize); + nilfs_err(sb, "too small segment usage size: %zu bytes", + susize); return -EINVAL; } diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 5729ee86da9a..2eee5fb1a882 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -62,19 +62,25 @@ struct kmem_cache *nilfs_btree_path_cache; static int nilfs_setup_super(struct super_block *sb, int is_mount); static int nilfs_remount(struct super_block *sb, int *flags, char *data); -void __nilfs_msg(struct super_block *sb, const char *level, const char *fmt, - ...) +void __nilfs_msg(struct super_block *sb, const char *fmt, ...) { struct va_format vaf; va_list args; + int level; va_start(args, fmt); - vaf.fmt = fmt; + + level = printk_get_level(fmt); + vaf.fmt = printk_skip_level(fmt); vaf.va = &args; + if (sb) - printk("%sNILFS (%s): %pV\n", level, sb->s_id, &vaf); + printk("%c%cNILFS (%s): %pV\n", + KERN_SOH_ASCII, level, sb->s_id, &vaf); else - printk("%sNILFS: %pV\n", level, &vaf); + printk("%c%cNILFS: %pV\n", + KERN_SOH_ASCII, level, &vaf); + va_end(args); } @@ -106,7 +112,7 @@ static void nilfs_set_error(struct super_block *sb) * * This implements the body of nilfs_error() macro. Normally, * nilfs_error() should be used. As for sustainable errors such as a - * single-shot I/O error, nilfs_msg() should be used instead. + * single-shot I/O error, nilfs_err() should be used instead. * * Callers should not add a trailing newline since this will do it. */ @@ -178,8 +184,7 @@ static int nilfs_sync_super(struct super_block *sb, int flag) } if (unlikely(err)) { - nilfs_msg(sb, KERN_ERR, "unable to write superblock: err=%d", - err); + nilfs_err(sb, "unable to write superblock: err=%d", err); if (err == -EIO && nilfs->ns_sbh[1]) { /* * sbp[0] points to newer log than sbp[1], @@ -249,7 +254,7 @@ struct nilfs_super_block **nilfs_prepare_super(struct super_block *sb, sbp[1]->s_magic == cpu_to_le16(NILFS_SUPER_MAGIC)) { memcpy(sbp[0], sbp[1], nilfs->ns_sbsize); } else { - nilfs_msg(sb, KERN_CRIT, "superblock broke"); + nilfs_crit(sb, "superblock broke"); return NULL; } } else if (sbp[1] && @@ -359,9 +364,9 @@ static int nilfs_move_2nd_super(struct super_block *sb, loff_t sb2off) offset = sb2off & (nilfs->ns_blocksize - 1); nsbh = sb_getblk(sb, newblocknr); if (!nsbh) { - nilfs_msg(sb, KERN_WARNING, - "unable to move secondary superblock to block %llu", - (unsigned long long)newblocknr); + nilfs_warn(sb, + "unable to move secondary superblock to block %llu", + (unsigned long long)newblocknr); ret = -EIO; goto out; } @@ -524,7 +529,7 @@ int nilfs_attach_checkpoint(struct super_block *sb, __u64 cno, int curr_mnt, up_read(&nilfs->ns_segctor_sem); if (unlikely(err)) { if (err == -ENOENT || err == -EINVAL) { - nilfs_msg(sb, KERN_ERR, + nilfs_err(sb, "Invalid checkpoint (checkpoint number=%llu)", (unsigned long long)cno); err = -EINVAL; @@ -622,8 +627,7 @@ static int nilfs_statfs(struct dentry *dentry, struct kstatfs *buf) err = nilfs_ifile_count_free_inodes(root->ifile, &nmaxinodes, &nfreeinodes); if (unlikely(err)) { - nilfs_msg(sb, KERN_WARNING, - "failed to count free inodes: err=%d", err); + nilfs_warn(sb, "failed to count free inodes: err=%d", err); if (err == -ERANGE) { /* * If nilfs_palloc_count_max_entries() returns @@ -755,7 +759,7 @@ static int parse_options(char *options, struct super_block *sb, int is_remount) break; case Opt_snapshot: if (is_remount) { - nilfs_msg(sb, KERN_ERR, + nilfs_err(sb, "\"%s\" option is invalid for remount", p); return 0; @@ -771,8 +775,7 @@ static int parse_options(char *options, struct super_block *sb, int is_remount) nilfs_clear_opt(nilfs, DISCARD); break; default: - nilfs_msg(sb, KERN_ERR, - "unrecognized mount option \"%s\"", p); + nilfs_err(sb, "unrecognized mount option \"%s\"", p); return 0; } } @@ -808,10 +811,10 @@ static int nilfs_setup_super(struct super_block *sb, int is_mount) mnt_count = le16_to_cpu(sbp[0]->s_mnt_count); if (nilfs->ns_mount_state & NILFS_ERROR_FS) { - nilfs_msg(sb, KERN_WARNING, "mounting fs with errors"); + nilfs_warn(sb, "mounting fs with errors"); #if 0 } else if (max_mnt_count >= 0 && mnt_count >= max_mnt_count) { - nilfs_msg(sb, KERN_WARNING, "maximal mount count reached"); + nilfs_warn(sb, "maximal mount count reached"); #endif } if (!max_mnt_count) @@ -874,7 +877,7 @@ int nilfs_check_feature_compatibility(struct super_block *sb, features = le64_to_cpu(sbp->s_feature_incompat) & ~NILFS_FEATURE_INCOMPAT_SUPP; if (features) { - nilfs_msg(sb, KERN_ERR, + nilfs_err(sb, "couldn't mount because of unsupported optional features (%llx)", (unsigned long long)features); return -EINVAL; @@ -882,7 +885,7 @@ int nilfs_check_feature_compatibility(struct super_block *sb, features = le64_to_cpu(sbp->s_feature_compat_ro) & ~NILFS_FEATURE_COMPAT_RO_SUPP; if (!sb_rdonly(sb) && features) { - nilfs_msg(sb, KERN_ERR, + nilfs_err(sb, "couldn't mount RDWR because of unsupported optional features (%llx)", (unsigned long long)features); return -EINVAL; @@ -901,12 +904,12 @@ static int nilfs_get_root_dentry(struct super_block *sb, inode = nilfs_iget(sb, root, NILFS_ROOT_INO); if (IS_ERR(inode)) { ret = PTR_ERR(inode); - nilfs_msg(sb, KERN_ERR, "error %d getting root inode", ret); + nilfs_err(sb, "error %d getting root inode", ret); goto out; } if (!S_ISDIR(inode->i_mode) || !inode->i_blocks || !inode->i_size) { iput(inode); - nilfs_msg(sb, KERN_ERR, "corrupt root inode"); + nilfs_err(sb, "corrupt root inode"); ret = -EINVAL; goto out; } @@ -934,7 +937,7 @@ static int nilfs_get_root_dentry(struct super_block *sb, return ret; failed_dentry: - nilfs_msg(sb, KERN_ERR, "error %d getting root dentry", ret); + nilfs_err(sb, "error %d getting root dentry", ret); goto out; } @@ -954,7 +957,7 @@ static int nilfs_attach_snapshot(struct super_block *s, __u64 cno, ret = (ret == -ENOENT) ? -EINVAL : ret; goto out; } else if (!ret) { - nilfs_msg(s, KERN_ERR, + nilfs_err(s, "The specified checkpoint is not a snapshot (checkpoint number=%llu)", (unsigned long long)cno); ret = -EINVAL; @@ -963,7 +966,7 @@ static int nilfs_attach_snapshot(struct super_block *s, __u64 cno, ret = nilfs_attach_checkpoint(s, cno, false, &root); if (ret) { - nilfs_msg(s, KERN_ERR, + nilfs_err(s, "error %d while loading snapshot (checkpoint number=%llu)", ret, (unsigned long long)cno); goto out; @@ -1060,7 +1063,7 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent) cno = nilfs_last_cno(nilfs); err = nilfs_attach_checkpoint(sb, cno, true, &fsroot); if (err) { - nilfs_msg(sb, KERN_ERR, + nilfs_err(sb, "error %d while loading last checkpoint (checkpoint number=%llu)", err, (unsigned long long)cno); goto failed_unload; @@ -1122,8 +1125,8 @@ static int nilfs_remount(struct super_block *sb, int *flags, char *data) err = -EINVAL; if (!nilfs_valid_fs(nilfs)) { - nilfs_msg(sb, KERN_WARNING, - "couldn't remount because the filesystem is in an incomplete recovery state"); + nilfs_warn(sb, + "couldn't remount because the filesystem is in an incomplete recovery state"); goto restore_opts; } @@ -1155,9 +1158,9 @@ static int nilfs_remount(struct super_block *sb, int *flags, char *data) ~NILFS_FEATURE_COMPAT_RO_SUPP; up_read(&nilfs->ns_sem); if (features) { - nilfs_msg(sb, KERN_WARNING, - "couldn't remount RDWR because of unsupported optional features (%llx)", - (unsigned long long)features); + nilfs_warn(sb, + "couldn't remount RDWR because of unsupported optional features (%llx)", + (unsigned long long)features); err = -EROFS; goto restore_opts; } @@ -1216,7 +1219,7 @@ static int nilfs_parse_snapshot_option(const char *option, return 0; parse_error: - nilfs_msg(NULL, KERN_ERR, "invalid option \"%s\": %s", option, msg); + nilfs_err(NULL, "invalid option \"%s\": %s", option, msg); return 1; } @@ -1319,7 +1322,7 @@ nilfs_mount(struct file_system_type *fs_type, int flags, } else if (!sd.cno) { if (nilfs_tree_is_busy(s->s_root)) { if ((flags ^ s->s_flags) & SB_RDONLY) { - nilfs_msg(s, KERN_ERR, + nilfs_err(s, "the device already has a %s mount.", sb_rdonly(s) ? "read-only" : "read/write"); err = -EBUSY; diff --git a/fs/nilfs2/sysfs.c b/fs/nilfs2/sysfs.c index e60be7bb55b0..303d71430bdd 100644 --- a/fs/nilfs2/sysfs.c +++ b/fs/nilfs2/sysfs.c @@ -263,8 +263,8 @@ nilfs_checkpoints_checkpoints_number_show(struct nilfs_checkpoints_attr *attr, err = nilfs_cpfile_get_stat(nilfs->ns_cpfile, &cpstat); up_read(&nilfs->ns_segctor_sem); if (err < 0) { - nilfs_msg(nilfs->ns_sb, KERN_ERR, - "unable to get checkpoint stat: err=%d", err); + nilfs_err(nilfs->ns_sb, "unable to get checkpoint stat: err=%d", + err); return err; } @@ -286,8 +286,8 @@ nilfs_checkpoints_snapshots_number_show(struct nilfs_checkpoints_attr *attr, err = nilfs_cpfile_get_stat(nilfs->ns_cpfile, &cpstat); up_read(&nilfs->ns_segctor_sem); if (err < 0) { - nilfs_msg(nilfs->ns_sb, KERN_ERR, - "unable to get checkpoint stat: err=%d", err); + nilfs_err(nilfs->ns_sb, "unable to get checkpoint stat: err=%d", + err); return err; } @@ -405,8 +405,8 @@ nilfs_segments_dirty_segments_show(struct nilfs_segments_attr *attr, err = nilfs_sufile_get_stat(nilfs->ns_sufile, &sustat); up_read(&nilfs->ns_segctor_sem); if (err < 0) { - nilfs_msg(nilfs->ns_sb, KERN_ERR, - "unable to get segment stat: err=%d", err); + nilfs_err(nilfs->ns_sb, "unable to get segment stat: err=%d", + err); return err; } @@ -779,15 +779,15 @@ nilfs_superblock_sb_update_frequency_store(struct nilfs_superblock_attr *attr, err = kstrtouint(skip_spaces(buf), 0, &val); if (err) { - nilfs_msg(nilfs->ns_sb, KERN_ERR, - "unable to convert string: err=%d", err); + nilfs_err(nilfs->ns_sb, "unable to convert string: err=%d", + err); return err; } if (val < NILFS_SB_FREQ) { val = NILFS_SB_FREQ; - nilfs_msg(nilfs->ns_sb, KERN_WARNING, - "superblock update frequency cannot be lesser than 10 seconds"); + nilfs_warn(nilfs->ns_sb, + "superblock update frequency cannot be lesser than 10 seconds"); } down_write(&nilfs->ns_sem); @@ -990,8 +990,7 @@ int nilfs_sysfs_create_device_group(struct super_block *sb) nilfs->ns_dev_subgroups = kzalloc(devgrp_size, GFP_KERNEL); if (unlikely(!nilfs->ns_dev_subgroups)) { err = -ENOMEM; - nilfs_msg(sb, KERN_ERR, - "unable to allocate memory for device group"); + nilfs_err(sb, "unable to allocate memory for device group"); goto failed_create_device_group; } @@ -1101,15 +1100,13 @@ int __init nilfs_sysfs_init(void) nilfs_kset = kset_create_and_add(NILFS_ROOT_GROUP_NAME, NULL, fs_kobj); if (!nilfs_kset) { err = -ENOMEM; - nilfs_msg(NULL, KERN_ERR, - "unable to create sysfs entry: err=%d", err); + nilfs_err(NULL, "unable to create sysfs entry: err=%d", err); goto failed_sysfs_init; } err = sysfs_create_group(&nilfs_kset->kobj, &nilfs_feature_attr_group); if (unlikely(err)) { - nilfs_msg(NULL, KERN_ERR, - "unable to create feature group: err=%d", err); + nilfs_err(NULL, "unable to create feature group: err=%d", err); goto cleanup_sysfs_init; } diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index 484785cdf96e..221a1cc597f0 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -183,7 +183,7 @@ static int nilfs_store_log_cursor(struct the_nilfs *nilfs, nilfs_get_segnum_of_block(nilfs, nilfs->ns_last_pseg); nilfs->ns_cno = nilfs->ns_last_cno + 1; if (nilfs->ns_segnum >= nilfs->ns_nsegments) { - nilfs_msg(nilfs->ns_sb, KERN_ERR, + nilfs_err(nilfs->ns_sb, "pointed segment number is out of range: segnum=%llu, nsegments=%lu", (unsigned long long)nilfs->ns_segnum, nilfs->ns_nsegments); @@ -210,12 +210,12 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb) int err; if (!valid_fs) { - nilfs_msg(sb, KERN_WARNING, "mounting unchecked fs"); + nilfs_warn(sb, "mounting unchecked fs"); if (s_flags & SB_RDONLY) { - nilfs_msg(sb, KERN_INFO, - "recovery required for readonly filesystem"); - nilfs_msg(sb, KERN_INFO, - "write access will be enabled during recovery"); + nilfs_info(sb, + "recovery required for readonly filesystem"); + nilfs_info(sb, + "write access will be enabled during recovery"); } } @@ -230,12 +230,11 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb) goto scan_error; if (!nilfs_valid_sb(sbp[1])) { - nilfs_msg(sb, KERN_WARNING, - "unable to fall back to spare super block"); + nilfs_warn(sb, + "unable to fall back to spare super block"); goto scan_error; } - nilfs_msg(sb, KERN_INFO, - "trying rollback from an earlier position"); + nilfs_info(sb, "trying rollback from an earlier position"); /* * restore super block with its spare and reconfigure @@ -248,9 +247,9 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb) /* verify consistency between two super blocks */ blocksize = BLOCK_SIZE << le32_to_cpu(sbp[0]->s_log_block_size); if (blocksize != nilfs->ns_blocksize) { - nilfs_msg(sb, KERN_WARNING, - "blocksize differs between two super blocks (%d != %d)", - blocksize, nilfs->ns_blocksize); + nilfs_warn(sb, + "blocksize differs between two super blocks (%d != %d)", + blocksize, nilfs->ns_blocksize); goto scan_error; } @@ -269,8 +268,7 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb) err = nilfs_load_super_root(nilfs, sb, ri.ri_super_root); if (unlikely(err)) { - nilfs_msg(sb, KERN_ERR, "error %d while loading super root", - err); + nilfs_err(sb, "error %d while loading super root", err); goto failed; } @@ -281,28 +279,28 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb) __u64 features; if (nilfs_test_opt(nilfs, NORECOVERY)) { - nilfs_msg(sb, KERN_INFO, - "norecovery option specified, skipping roll-forward recovery"); + nilfs_info(sb, + "norecovery option specified, skipping roll-forward recovery"); goto skip_recovery; } features = le64_to_cpu(nilfs->ns_sbp[0]->s_feature_compat_ro) & ~NILFS_FEATURE_COMPAT_RO_SUPP; if (features) { - nilfs_msg(sb, KERN_ERR, + nilfs_err(sb, "couldn't proceed with recovery because of unsupported optional features (%llx)", (unsigned long long)features); err = -EROFS; goto failed_unload; } if (really_read_only) { - nilfs_msg(sb, KERN_ERR, + nilfs_err(sb, "write access unavailable, cannot proceed"); err = -EROFS; goto failed_unload; } sb->s_flags &= ~SB_RDONLY; } else if (nilfs_test_opt(nilfs, NORECOVERY)) { - nilfs_msg(sb, KERN_ERR, + nilfs_err(sb, "recovery cancelled because norecovery option was specified for a read/write mount"); err = -EINVAL; goto failed_unload; @@ -318,12 +316,12 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb) up_write(&nilfs->ns_sem); if (err) { - nilfs_msg(sb, KERN_ERR, + nilfs_err(sb, "error %d updating super block. recovery unfinished.", err); goto failed_unload; } - nilfs_msg(sb, KERN_INFO, "recovery complete"); + nilfs_info(sb, "recovery complete"); skip_recovery: nilfs_clear_recovery_info(&ri); @@ -331,7 +329,7 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb) return 0; scan_error: - nilfs_msg(sb, KERN_ERR, "error %d while searching super root", err); + nilfs_err(sb, "error %d while searching super root", err); goto failed; failed_unload: @@ -378,7 +376,7 @@ static int nilfs_store_disk_layout(struct the_nilfs *nilfs, struct nilfs_super_block *sbp) { if (le32_to_cpu(sbp->s_rev_level) < NILFS_MIN_SUPP_REV) { - nilfs_msg(nilfs->ns_sb, KERN_ERR, + nilfs_err(nilfs->ns_sb, "unsupported revision (superblock rev.=%d.%d, current rev.=%d.%d). Please check the version of mkfs.nilfs(2).", le32_to_cpu(sbp->s_rev_level), le16_to_cpu(sbp->s_minor_rev_level), @@ -391,13 +389,11 @@ static int nilfs_store_disk_layout(struct the_nilfs *nilfs, nilfs->ns_inode_size = le16_to_cpu(sbp->s_inode_size); if (nilfs->ns_inode_size > nilfs->ns_blocksize) { - nilfs_msg(nilfs->ns_sb, KERN_ERR, - "too large inode size: %d bytes", + nilfs_err(nilfs->ns_sb, "too large inode size: %d bytes", nilfs->ns_inode_size); return -EINVAL; } else if (nilfs->ns_inode_size < NILFS_MIN_INODE_SIZE) { - nilfs_msg(nilfs->ns_sb, KERN_ERR, - "too small inode size: %d bytes", + nilfs_err(nilfs->ns_sb, "too small inode size: %d bytes", nilfs->ns_inode_size); return -EINVAL; } @@ -406,8 +402,7 @@ static int nilfs_store_disk_layout(struct the_nilfs *nilfs, nilfs->ns_blocks_per_segment = le32_to_cpu(sbp->s_blocks_per_segment); if (nilfs->ns_blocks_per_segment < NILFS_SEG_MIN_BLOCKS) { - nilfs_msg(nilfs->ns_sb, KERN_ERR, - "too short segment: %lu blocks", + nilfs_err(nilfs->ns_sb, "too short segment: %lu blocks", nilfs->ns_blocks_per_segment); return -EINVAL; } @@ -417,7 +412,7 @@ static int nilfs_store_disk_layout(struct the_nilfs *nilfs, le32_to_cpu(sbp->s_r_segments_percentage); if (nilfs->ns_r_segments_percentage < 1 || nilfs->ns_r_segments_percentage > 99) { - nilfs_msg(nilfs->ns_sb, KERN_ERR, + nilfs_err(nilfs->ns_sb, "invalid reserved segments percentage: %lu", nilfs->ns_r_segments_percentage); return -EINVAL; @@ -503,16 +498,16 @@ static int nilfs_load_super_block(struct the_nilfs *nilfs, if (!sbp[0]) { if (!sbp[1]) { - nilfs_msg(sb, KERN_ERR, "unable to read superblock"); + nilfs_err(sb, "unable to read superblock"); return -EIO; } - nilfs_msg(sb, KERN_WARNING, - "unable to read primary superblock (blocksize = %d)", - blocksize); + nilfs_warn(sb, + "unable to read primary superblock (blocksize = %d)", + blocksize); } else if (!sbp[1]) { - nilfs_msg(sb, KERN_WARNING, - "unable to read secondary superblock (blocksize = %d)", - blocksize); + nilfs_warn(sb, + "unable to read secondary superblock (blocksize = %d)", + blocksize); } /* @@ -534,14 +529,14 @@ static int nilfs_load_super_block(struct the_nilfs *nilfs, } if (!valid[swp]) { nilfs_release_super_block(nilfs); - nilfs_msg(sb, KERN_ERR, "couldn't find nilfs on the device"); + nilfs_err(sb, "couldn't find nilfs on the device"); return -EINVAL; } if (!valid[!swp]) - nilfs_msg(sb, KERN_WARNING, - "broken superblock, retrying with spare superblock (blocksize = %d)", - blocksize); + nilfs_warn(sb, + "broken superblock, retrying with spare superblock (blocksize = %d)", + blocksize); if (swp) nilfs_swap_super_block(nilfs); @@ -575,7 +570,7 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data) blocksize = sb_min_blocksize(sb, NILFS_MIN_BLOCK_SIZE); if (!blocksize) { - nilfs_msg(sb, KERN_ERR, "unable to set blocksize"); + nilfs_err(sb, "unable to set blocksize"); err = -EINVAL; goto out; } @@ -594,7 +589,7 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data) blocksize = BLOCK_SIZE << le32_to_cpu(sbp->s_log_block_size); if (blocksize < NILFS_MIN_BLOCK_SIZE || blocksize > NILFS_MAX_BLOCK_SIZE) { - nilfs_msg(sb, KERN_ERR, + nilfs_err(sb, "couldn't mount because of unsupported filesystem blocksize %d", blocksize); err = -EINVAL; @@ -604,7 +599,7 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data) int hw_blocksize = bdev_logical_block_size(sb->s_bdev); if (blocksize < hw_blocksize) { - nilfs_msg(sb, KERN_ERR, + nilfs_err(sb, "blocksize %d too small for device (sector-size = %d)", blocksize, hw_blocksize); err = -EINVAL; diff --git a/fs/open.c b/fs/open.c index c80e9f497e9b..9af548fb841b 100644 --- a/fs/open.c +++ b/fs/open.c @@ -779,12 +779,6 @@ static int do_dentry_open(struct file *f, return 0; } - /* Any file opened for execve()/uselib() has to be a regular file. */ - if (unlikely(f->f_flags & FMODE_EXEC && !S_ISREG(inode->i_mode))) { - error = -EACCES; - goto cleanup_file; - } - if (f->f_mode & FMODE_WRITE && !special_file(inode->i_mode)) { error = get_write_access(inode); if (unlikely(error)) diff --git a/fs/orangefs/acl.c b/fs/orangefs/acl.c index eced272a3c57..a25e6c890975 100644 --- a/fs/orangefs/acl.c +++ b/fs/orangefs/acl.c @@ -122,6 +122,8 @@ int orangefs_set_acl(struct inode *inode, struct posix_acl *acl, int type) struct iattr iattr; int rc; + memset(&iattr, 0, sizeof iattr); + if (type == ACL_TYPE_ACCESS && acl) { /* * posix_acl_update_mode checks to see if the permissions @@ -138,18 +140,17 @@ int orangefs_set_acl(struct inode *inode, struct posix_acl *acl, int type) return error; } - if (acl) { - rc = __orangefs_set_acl(inode, acl, type); - } else { + if (inode->i_mode != iattr.ia_mode) iattr.ia_valid = ATTR_MODE; - rc = __orangefs_setattr(inode, &iattr); - } - return rc; - - } else { - return -EINVAL; } + + rc = __orangefs_set_acl(inode, acl, type); + + if (!rc && (iattr.ia_valid == ATTR_MODE)) + rc = __orangefs_setattr(inode, &iattr); + + return rc; } int orangefs_init_acl(struct inode *inode, struct inode *dir) diff --git a/fs/orangefs/orangefs-mod.c b/fs/orangefs/orangefs-mod.c index 289b648ae196..74a3d6337ef4 100644 --- a/fs/orangefs/orangefs-mod.c +++ b/fs/orangefs/orangefs-mod.c @@ -149,7 +149,6 @@ static int __init orangefs_init(void) pr_info("%s: module version %s loaded\n", __func__, ORANGEFS_VERSION); - ret = 0; goto out; } diff --git a/fs/proc/base.c b/fs/proc/base.c index a333caeca291..617db4e0faa0 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -551,8 +551,17 @@ static int proc_oom_score(struct seq_file *m, struct pid_namespace *ns, { unsigned long totalpages = totalram_pages() + total_swap_pages; unsigned long points = 0; + long badness; + + badness = oom_badness(task, totalpages); + /* + * Special case OOM_SCORE_ADJ_MIN for all others scale the + * badness value into [0, 2000] range which we have been + * exporting for a long time so userspace might depend on it. + */ + if (badness != LONG_MIN) + points = (1000 + badness * 1000 / (long)totalpages) * 2 / 3; - points = oom_badness(task, totalpages) * 1000 / totalpages; seq_printf(m, "%lu\n", points); return 0; diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index dbda4499a859..5066b0251ed8 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -786,7 +786,7 @@ static void __show_smap(struct seq_file *m, const struct mem_size_stats *mss, SEQ_PUT_DEC(" kB\nLazyFree: ", mss->lazyfree); SEQ_PUT_DEC(" kB\nAnonHugePages: ", mss->anonymous_thp); SEQ_PUT_DEC(" kB\nShmemPmdMapped: ", mss->shmem_thp); - SEQ_PUT_DEC(" kB\nFilePmdMapped: ", mss->file_thp); + SEQ_PUT_DEC(" kB\nFilePmdMapped: ", mss->file_thp); SEQ_PUT_DEC(" kB\nShared_Hugetlb: ", mss->shared_hugetlb); seq_put_decimal_ull_width(m, " kB\nPrivate_Hugetlb: ", mss->private_hugetlb >> 10, 7); @@ -816,7 +816,7 @@ static int show_smap(struct seq_file *m, void *v) __show_smap(m, &mss, false); - seq_printf(m, "THPeligible: %d\n", + seq_printf(m, "THPeligible: %d\n", transparent_hugepage_enabled(vma)); if (arch_pkeys_enabled()) diff --git a/fs/signalfd.c b/fs/signalfd.c index 44b6845b071c..5b78719be445 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -314,9 +314,10 @@ SYSCALL_DEFINE4(signalfd4, int, ufd, sigset_t __user *, user_mask, { sigset_t mask; - if (sizemask != sizeof(sigset_t) || - copy_from_user(&mask, user_mask, sizeof(mask))) + if (sizemask != sizeof(sigset_t)) return -EINVAL; + if (copy_from_user(&mask, user_mask, sizeof(mask))) + return -EFAULT; return do_signalfd4(ufd, &mask, flags); } @@ -325,9 +326,10 @@ SYSCALL_DEFINE3(signalfd, int, ufd, sigset_t __user *, user_mask, { sigset_t mask; - if (sizemask != sizeof(sigset_t) || - copy_from_user(&mask, user_mask, sizeof(mask))) + if (sizemask != sizeof(sigset_t)) return -EINVAL; + if (copy_from_user(&mask, user_mask, sizeof(mask))) + return -EFAULT; return do_signalfd4(ufd, &mask, 0); } diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c index 2e6264318bd9..4a5b06f8d812 100644 --- a/fs/ubifs/journal.c +++ b/fs/ubifs/journal.c @@ -539,7 +539,7 @@ int ubifs_jnl_update(struct ubifs_info *c, const struct inode *dir, const struct fscrypt_name *nm, const struct inode *inode, int deletion, int xent) { - int err, dlen, ilen, len, lnum, ino_offs, dent_offs; + int err, dlen, ilen, len, lnum, ino_offs, dent_offs, orphan_added = 0; int aligned_dlen, aligned_ilen, sync = IS_DIRSYNC(dir); int last_reference = !!(deletion && inode->i_nlink == 0); struct ubifs_inode *ui = ubifs_inode(inode); @@ -630,6 +630,7 @@ int ubifs_jnl_update(struct ubifs_info *c, const struct inode *dir, goto out_finish; } ui->del_cmtno = c->cmt_no; + orphan_added = 1; } err = write_head(c, BASEHD, dent, len, &lnum, &dent_offs, sync); @@ -702,7 +703,7 @@ out_release: kfree(dent); out_ro: ubifs_ro_mode(c, err); - if (last_reference) + if (orphan_added) ubifs_delete_orphan(c, inode->i_ino); finish_reservation(c); return err; @@ -1218,7 +1219,7 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir, void *p; union ubifs_key key; struct ubifs_dent_node *dent, *dent2; - int err, dlen1, dlen2, ilen, lnum, offs, len; + int err, dlen1, dlen2, ilen, lnum, offs, len, orphan_added = 0; int aligned_dlen1, aligned_dlen2, plen = UBIFS_INO_NODE_SZ; int last_reference = !!(new_inode && new_inode->i_nlink == 0); int move = (old_dir != new_dir); @@ -1334,6 +1335,7 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir, goto out_finish; } new_ui->del_cmtno = c->cmt_no; + orphan_added = 1; } err = write_head(c, BASEHD, dent, len, &lnum, &offs, sync); @@ -1415,7 +1417,7 @@ out_release: release_head(c, BASEHD); out_ro: ubifs_ro_mode(c, err); - if (last_reference) + if (orphan_added) ubifs_delete_orphan(c, new_inode->i_ino); out_finish: finish_reservation(c); diff --git a/fs/ubifs/misc.h b/fs/ubifs/misc.h index c97a4d537d83..615878e884ba 100644 --- a/fs/ubifs/misc.h +++ b/fs/ubifs/misc.h @@ -121,7 +121,7 @@ static inline const char *ubifs_compr_name(struct ubifs_info *c, int compr_type) * ubifs_wbuf_sync - synchronize write-buffer. * @wbuf: write-buffer to synchronize * - * This is the same as as 'ubifs_wbuf_sync_nolock()' but it does not assume + * This is the same as 'ubifs_wbuf_sync_nolock()' but it does not assume * that the write-buffer is already locked. */ static inline int ubifs_wbuf_sync(struct ubifs_wbuf *wbuf) diff --git a/fs/ubifs/sb.c b/fs/ubifs/sb.c index 4b4b65b48c57..c0d3e4008d23 100644 --- a/fs/ubifs/sb.c +++ b/fs/ubifs/sb.c @@ -174,7 +174,8 @@ static int create_default_filesystem(struct ubifs_info *c) tmp64 = (long long)max_buds * c->leb_size; if (big_lpt) sup_flags |= UBIFS_FLG_BIGLPT; - sup_flags |= UBIFS_FLG_DOUBLE_HASH; + if (ubifs_default_version > 4) + sup_flags |= UBIFS_FLG_DOUBLE_HASH; if (ubifs_authenticated(c)) { sup_flags |= UBIFS_FLG_AUTHENTICATION; @@ -200,7 +201,7 @@ static int create_default_filesystem(struct ubifs_info *c) sup->jhead_cnt = cpu_to_le32(DEFAULT_JHEADS_CNT); sup->fanout = cpu_to_le32(DEFAULT_FANOUT); sup->lsave_cnt = cpu_to_le32(c->lsave_cnt); - sup->fmt_version = cpu_to_le32(UBIFS_FORMAT_VERSION); + sup->fmt_version = cpu_to_le32(ubifs_default_version); sup->time_gran = cpu_to_le32(DEFAULT_TIME_GRAN); if (c->mount_opts.override_compr) sup->default_compr = cpu_to_le16(c->mount_opts.compr_type); diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 7fc2f3f07c16..a2420c900275 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -26,6 +26,24 @@ #include <linux/writeback.h> #include "ubifs.h" +static int ubifs_default_version_set(const char *val, const struct kernel_param *kp) +{ + int n = 0, ret; + + ret = kstrtoint(val, 10, &n); + if (ret != 0 || n < 4 || n > UBIFS_FORMAT_VERSION) + return -EINVAL; + return param_set_int(val, kp); +} + +static const struct kernel_param_ops ubifs_default_version_ops = { + .set = ubifs_default_version_set, + .get = param_get_int, +}; + +int ubifs_default_version = UBIFS_FORMAT_VERSION; +module_param_cb(default_version, &ubifs_default_version_ops, &ubifs_default_version, 0600); + /* * Maximum amount of memory we may 'kmalloc()' without worrying that we are * allocating too much. diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index bff682309fbe..4ffd832e3b93 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -1504,6 +1504,7 @@ extern const struct file_operations ubifs_dir_operations; extern const struct inode_operations ubifs_dir_inode_operations; extern const struct inode_operations ubifs_symlink_inode_operations; extern struct ubifs_compressor *ubifs_compressors[UBIFS_COMPR_TYPES_CNT]; +extern int ubifs_default_version; /* auth.c */ static inline int ubifs_authenticated(const struct ubifs_info *c) diff --git a/fs/ufs/super.c b/fs/ufs/super.c index 1da0be667409..e3b69fb280e8 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -101,7 +101,7 @@ static struct inode *ufs_nfs_get_inode(struct super_block *sb, u64 ino, u32 gene struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi; struct inode *inode; - if (ino < UFS_ROOTINO || ino > uspi->s_ncg * uspi->s_ipg) + if (ino < UFS_ROOTINO || ino > (u64)uspi->s_ncg * uspi->s_ipg) return ERR_PTR(-ESTALE); inode = ufs_iget(sb, ino); diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 6e264dded46e..0e4a3837da52 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -61,7 +61,7 @@ struct userfaultfd_ctx { /* waitqueue head for events */ wait_queue_head_t event_wqh; /* a refile sequence protected by fault_pending_wqh lock */ - struct seqcount refile_seq; + seqcount_spinlock_t refile_seq; /* pseudo fd refcounting */ refcount_t refcount; /* userfaultfd syscall flags */ @@ -1961,7 +1961,7 @@ static void init_once_userfaultfd_ctx(void *mem) init_waitqueue_head(&ctx->fault_wqh); init_waitqueue_head(&ctx->event_wqh); init_waitqueue_head(&ctx->fd_wqh); - seqcount_init(&ctx->refile_seq); + seqcount_spinlock_init(&ctx->refile_seq, &ctx->fault_pending_wqh.lock); } SYSCALL_DEFINE1(userfaultfd, int, flags) diff --git a/fs/xattr.c b/fs/xattr.c index 91608d9bfc6a..386b45676d7e 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -134,6 +134,33 @@ xattr_permission(struct inode *inode, const char *name, int mask) return inode_permission(inode, mask); } +/* + * Look for any handler that deals with the specified namespace. + */ +int +xattr_supported_namespace(struct inode *inode, const char *prefix) +{ + const struct xattr_handler **handlers = inode->i_sb->s_xattr; + const struct xattr_handler *handler; + size_t preflen; + + if (!(inode->i_opflags & IOP_XATTR)) { + if (unlikely(is_bad_inode(inode))) + return -EIO; + return -EOPNOTSUPP; + } + + preflen = strlen(prefix); + + for_each_xattr_handler(handlers, handler) { + if (!strncmp(xattr_prefix(handler), prefix, preflen)) + return 0; + } + + return -EOPNOTSUPP; +} +EXPORT_SYMBOL(xattr_supported_namespace); + int __vfs_setxattr(struct dentry *dentry, struct inode *inode, const char *name, const void *value, size_t size, int flags) @@ -204,10 +231,22 @@ int __vfs_setxattr_noperm(struct dentry *dentry, const char *name, return error; } - +/** + * __vfs_setxattr_locked: set an extended attribute while holding the inode + * lock + * + * @dentry - object to perform setxattr on + * @name - xattr name to set + * @value - value to set @name to + * @size - size of @value + * @flags - flags to pass into filesystem operations + * @delegated_inode - on return, will contain an inode pointer that + * a delegation was broken on, NULL if none. + */ int -vfs_setxattr(struct dentry *dentry, const char *name, const void *value, - size_t size, int flags) +__vfs_setxattr_locked(struct dentry *dentry, const char *name, + const void *value, size_t size, int flags, + struct inode **delegated_inode) { struct inode *inode = dentry->d_inode; int error; @@ -216,15 +255,40 @@ vfs_setxattr(struct dentry *dentry, const char *name, const void *value, if (error) return error; - inode_lock(inode); error = security_inode_setxattr(dentry, name, value, size, flags); if (error) goto out; + error = try_break_deleg(inode, delegated_inode); + if (error) + goto out; + error = __vfs_setxattr_noperm(dentry, name, value, size, flags); out: + return error; +} +EXPORT_SYMBOL_GPL(__vfs_setxattr_locked); + +int +vfs_setxattr(struct dentry *dentry, const char *name, const void *value, + size_t size, int flags) +{ + struct inode *inode = dentry->d_inode; + struct inode *delegated_inode = NULL; + int error; + +retry_deleg: + inode_lock(inode); + error = __vfs_setxattr_locked(dentry, name, value, size, flags, + &delegated_inode); inode_unlock(inode); + + if (delegated_inode) { + error = break_deleg_wait(&delegated_inode); + if (!error) + goto retry_deleg; + } return error; } EXPORT_SYMBOL_GPL(vfs_setxattr); @@ -378,8 +442,18 @@ __vfs_removexattr(struct dentry *dentry, const char *name) } EXPORT_SYMBOL(__vfs_removexattr); +/** + * __vfs_removexattr_locked: set an extended attribute while holding the inode + * lock + * + * @dentry - object to perform setxattr on + * @name - name of xattr to remove + * @delegated_inode - on return, will contain an inode pointer that + * a delegation was broken on, NULL if none. + */ int -vfs_removexattr(struct dentry *dentry, const char *name) +__vfs_removexattr_locked(struct dentry *dentry, const char *name, + struct inode **delegated_inode) { struct inode *inode = dentry->d_inode; int error; @@ -388,11 +462,14 @@ vfs_removexattr(struct dentry *dentry, const char *name) if (error) return error; - inode_lock(inode); error = security_inode_removexattr(dentry, name); if (error) goto out; + error = try_break_deleg(inode, delegated_inode); + if (error) + goto out; + error = __vfs_removexattr(dentry, name); if (!error) { @@ -401,12 +478,32 @@ vfs_removexattr(struct dentry *dentry, const char *name) } out: + return error; +} +EXPORT_SYMBOL_GPL(__vfs_removexattr_locked); + +int +vfs_removexattr(struct dentry *dentry, const char *name) +{ + struct inode *inode = dentry->d_inode; + struct inode *delegated_inode = NULL; + int error; + +retry_deleg: + inode_lock(inode); + error = __vfs_removexattr_locked(dentry, name, &delegated_inode); inode_unlock(inode); + + if (delegated_inode) { + error = break_deleg_wait(&delegated_inode); + if (!error) + goto retry_deleg; + } + return error; } EXPORT_SYMBOL_GPL(vfs_removexattr); - /* * Extended attribute SET operations */ diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index 4df87546bd40..ae9aaf1f34bf 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -600,7 +600,7 @@ xfs_sb_quota_to_disk( * disk. If neither are active, we should NULL the inode. * * In all cases, the separate pquotino must remain 0 because it - * it beyond the "end" of the valid non-pquotino superblock. + * is beyond the "end" of the valid non-pquotino superblock. */ if (from->sb_qflags & XFS_GQUOTA_ACCT) to->sb_gquotino = cpu_to_be64(from->sb_gquotino); diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c index e380bd1a9bfc..50f922cad91a 100644 --- a/fs/xfs/xfs_attr_list.c +++ b/fs/xfs/xfs_attr_list.c @@ -44,7 +44,7 @@ xfs_attr_shortform_compare(const void *a, const void *b) /* * Copy out entries of shortform attribute lists for attr_list(). * Shortform attribute lists are not stored in hashval sorted order. - * If the output buffer is not large enough to hold them all, then we + * If the output buffer is not large enough to hold them all, then * we have to calculate each entries' hashvalue and sort them before * we can begin returning them to the user. */ diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 5bb6f22cc11a..408d1b572d3f 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -127,7 +127,7 @@ xfs_buf_item_size_segment( * stretch of non-contiguous chunks to be logged. Contiguous chunks are logged * in a single iovec. * - * Discontiguous buffers need a format structure per region that that is being + * Discontiguous buffers need a format structure per region that is being * logged. This makes the changes in the buffer appear to log recovery as though * they came from separate buffers, just like would occur if multiple buffers * were used instead of a single discontiguous buffer. This enables diff --git a/fs/xfs/xfs_buf_item_recover.c b/fs/xfs/xfs_buf_item_recover.c index d480f11e6b00..8f0457d67d77 100644 --- a/fs/xfs/xfs_buf_item_recover.c +++ b/fs/xfs/xfs_buf_item_recover.c @@ -948,7 +948,7 @@ xlog_recover_buf_commit_pass2( * or inode_cluster_size bytes, whichever is bigger. The inode * buffers in the log can be a different size if the log was generated * by an older kernel using unclustered inode buffers or a newer kernel - * running with a different inode cluster size. Regardless, if the + * running with a different inode cluster size. Regardless, if * the inode buffer size isn't max(blocksize, inode_cluster_size) * for *our* value of inode_cluster_size, then we need to keep * the buffer out of the buffer cache so that the buffer won't diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index 04dc2be19c3a..bcd73b9c2994 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -807,7 +807,7 @@ xfs_qm_dqget_checks( } /* - * Given the file system, id, and type (UDQUOT/GDQUOT), return a a locked + * Given the file system, id, and type (UDQUOT/GDQUOT), return a locked * dquot, doing an allocation (if requested) as needed. */ int diff --git a/fs/xfs/xfs_export.c b/fs/xfs/xfs_export.c index 5a4b0119143a..465fd9e048d4 100644 --- a/fs/xfs/xfs_export.c +++ b/fs/xfs/xfs_export.c @@ -56,7 +56,7 @@ xfs_fs_encode_fh( fileid_type = FILEID_INO32_GEN_PARENT; /* - * If the the filesystem may contain 64bit inode numbers, we need + * If the filesystem may contain 64bit inode numbers, we need * to use larger file handles that can represent them. * * While we only allocate inodes that do not fit into 32 bits any diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 407d6299606d..c06129cffba9 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -451,7 +451,7 @@ xfs_lock_inodes( /* * Currently supports between 2 and 5 inodes with exclusive locking. We * support an arbitrary depth of locking here, but absolute limits on - * inodes depend on the the type of locking and the limits placed by + * inodes depend on the type of locking and the limits placed by * lockdep annotations in xfs_lock_inumorder. These are all checked by * the asserts. */ @@ -3105,7 +3105,7 @@ out_trans_abort: /* * xfs_rename_alloc_whiteout() * - * Return a referenced, unlinked, unlocked inode that that can be used as a + * Return a referenced, unlinked, unlocked inode that can be used as a * whiteout in a rename transaction. We use a tmpfile inode here so that if we * crash between allocating the inode and linking it into the rename transaction * recovery will free the inode and we won't leak it. diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 895f61b2b4f0..6c65938cee1c 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -191,7 +191,7 @@ xfs_inode_item_format_data_fork( ip->i_df.if_bytes > 0) { /* * Round i_bytes up to a word boundary. - * The underlying memory is guaranteed to + * The underlying memory is guaranteed * to be there by xfs_idata_realloc(). */ data_bytes = roundup(ip->i_df.if_bytes, 4); @@ -275,7 +275,7 @@ xfs_inode_item_format_attr_fork( ip->i_afp->if_bytes > 0) { /* * Round i_bytes up to a word boundary. - * The underlying memory is guaranteed to + * The underlying memory is guaranteed * to be there by xfs_idata_realloc(). */ data_bytes = roundup(ip->i_afp->if_bytes, 4); diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 0e3f62cde375..3abb8b9d6f4c 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -865,7 +865,7 @@ xfs_buffered_write_iomap_begin( } /* - * Search the data fork fork first to look up our source mapping. We + * Search the data fork first to look up our source mapping. We * always need the data fork map, as we have to return it to the * iomap code so that the higher level write code can read data in to * perform read-modify-write cycles for unaligned writes. diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index 56c32eecffea..b0ef071b3cb5 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -239,7 +239,7 @@ xfs_cil_prepare_item( * this CIL context and so we need to pin it. If we are replacing the * old_lv, then remove the space it accounts for and make it the shadow * buffer for later freeing. In both cases we are now switching to the - * shadow buffer, so update the the pointer to it appropriately. + * shadow buffer, so update the pointer to it appropriately. */ if (!old_lv) { if (lv->lv_item->li_ops->iop_pin) diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 52a65a74208f..e2ec91b2d0f4 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -1100,7 +1100,7 @@ xlog_verify_head( * * Note that xlog_find_tail() clears the blocks at the new head * (i.e., the records with invalid CRC) if the cycle number - * matches the the current cycle. + * matches the current cycle. */ found = xlog_rseek_logrec_hdr(log, first_bad, *tail_blk, 1, buffer, rhead_blk, rhead, wrapped); diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c index 7b2c72bc2858..ca93b6488377 100644 --- a/fs/xfs/xfs_refcount_item.c +++ b/fs/xfs/xfs_refcount_item.c @@ -485,7 +485,7 @@ xfs_cui_item_recover( * transaction. Normally, any work that needs to be deferred * gets attached to the same defer_ops that scheduled the * refcount update. However, we're in log recovery here, so we - * we use the passed in defer_ops and to finish up any work that + * use the passed in defer_ops and to finish up any work that * doesn't fit. We need to reserve enough blocks to handle a * full btree split on either end of the refcount range. */ diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index aac83f9d6107..16098dc42add 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -721,7 +721,7 @@ xfs_reflink_end_cow( * repeatedly cycles the ILOCK to allocate one transaction per remapped * extent. * - * If we're being called by writeback then the the pages will still + * If we're being called by writeback then the pages will still * have PageWriteback set, which prevents races with reflink remapping * and truncate. Reflink remapping prevents races with writeback by * taking the iolock and mmaplock before flushing the pages and diff --git a/fs/xfs/xfs_sysfs.h b/fs/xfs/xfs_sysfs.h index e9f810fc6731..43585850f154 100644 --- a/fs/xfs/xfs_sysfs.h +++ b/fs/xfs/xfs_sysfs.h @@ -32,9 +32,11 @@ xfs_sysfs_init( struct xfs_kobj *parent_kobj, const char *name) { + struct kobject *parent; + + parent = parent_kobj ? &parent_kobj->kobject : NULL; init_completion(&kobj->complete); - return kobject_init_and_add(&kobj->kobject, ktype, - &parent_kobj->kobject, "%s", name); + return kobject_init_and_add(&kobj->kobject, ktype, parent, "%s", name); } static inline void diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c index 0c783d339675..dbb69b4bf3ed 100644 --- a/fs/xfs/xfs_trans_ail.c +++ b/fs/xfs/xfs_trans_ail.c @@ -480,7 +480,7 @@ xfsaild_push( * inode buffer is locked because we already pushed the * updates to it as part of inode clustering. * - * We do not want to to stop flushing just because lots + * We do not want to stop flushing just because lots * of items are already being flushed, but we need to * re-try the flushing relatively soon if most of the * AIL is being flushed. @@ -515,7 +515,7 @@ xfsaild_push( /* * Are there too many items we can't do anything with? * - * If we we are skipping too many items because we can't flush + * If we are skipping too many items because we can't flush * them or they are already being flushed, we back off and * given them time to complete whatever operation is being * done. i.e. remove pressure from the AIL while we can't make diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index 4a0bff65d3d6..8ec7c8f109d7 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -335,7 +335,7 @@ static void zonefs_io_error(struct inode *inode, bool write) struct zonefs_sb_info *sbi = ZONEFS_SB(sb); unsigned int noio_flag; unsigned int nr_zones = - zi->i_max_size >> (sbi->s_zone_sectors_shift + SECTOR_SHIFT); + zi->i_zone_size >> (sbi->s_zone_sectors_shift + SECTOR_SHIFT); struct zonefs_ioerr_data err = { .inode = inode, .write = write, @@ -398,7 +398,7 @@ static int zonefs_file_truncate(struct inode *inode, loff_t isize) goto unlock; ret = blkdev_zone_mgmt(inode->i_sb->s_bdev, op, zi->i_zsector, - zi->i_max_size >> SECTOR_SHIFT, GFP_NOFS); + zi->i_zone_size >> SECTOR_SHIFT, GFP_NOFS); if (ret) { zonefs_err(inode->i_sb, "Zone management operation at %llu failed %d", @@ -1053,14 +1053,16 @@ static void zonefs_init_file_inode(struct inode *inode, struct blk_zone *zone, zi->i_ztype = type; zi->i_zsector = zone->start; + zi->i_zone_size = zone->len << SECTOR_SHIFT; + zi->i_max_size = min_t(loff_t, MAX_LFS_FILESIZE, - zone->len << SECTOR_SHIFT); + zone->capacity << SECTOR_SHIFT); zi->i_wpoffset = zonefs_check_zone_condition(inode, zone, true, true); inode->i_uid = sbi->s_uid; inode->i_gid = sbi->s_gid; inode->i_size = zi->i_wpoffset; - inode->i_blocks = zone->len; + inode->i_blocks = zi->i_max_size >> SECTOR_SHIFT; inode->i_op = &zonefs_file_inode_operations; inode->i_fop = &zonefs_file_operations; @@ -1167,12 +1169,18 @@ static int zonefs_create_zgroup(struct zonefs_zone_data *zd, if (zonefs_zone_type(next) != type) break; zone->len += next->len; + zone->capacity += next->capacity; if (next->cond == BLK_ZONE_COND_READONLY && zone->cond != BLK_ZONE_COND_OFFLINE) zone->cond = BLK_ZONE_COND_READONLY; else if (next->cond == BLK_ZONE_COND_OFFLINE) zone->cond = BLK_ZONE_COND_OFFLINE; } + if (zone->capacity != zone->len) { + zonefs_err(sb, "Invalid conventional zone capacity\n"); + ret = -EINVAL; + goto free; + } } /* diff --git a/fs/zonefs/zonefs.h b/fs/zonefs/zonefs.h index ad17fef7ce91..55b39970acb2 100644 --- a/fs/zonefs/zonefs.h +++ b/fs/zonefs/zonefs.h @@ -56,6 +56,9 @@ struct zonefs_inode_info { /* File maximum size */ loff_t i_max_size; + /* File zone size */ + loff_t i_zone_size; + /* * To serialise fully against both syscall and mmap based IO and * sequential file truncation, two locks are used. For serializing |