diff options
Diffstat (limited to 'fs')
186 files changed, 5261 insertions, 3602 deletions
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index 24fdc74caeba..819c75233235 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -68,17 +68,22 @@ static void v9fs_issue_read(struct netfs_io_subrequest *subreq) { struct netfs_io_request *rreq = subreq->rreq; struct p9_fid *fid = rreq->netfs_priv; + unsigned long long pos = subreq->start + subreq->transferred; int total, err; - total = p9_client_read(fid, subreq->start + subreq->transferred, - &subreq->io_iter, &err); + total = p9_client_read(fid, pos, &subreq->io_iter, &err); /* if we just extended the file size, any portion not in * cache won't be on server and is zeroes */ if (subreq->rreq->origin != NETFS_DIO_READ) __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); + if (pos + total >= i_size_read(rreq->inode)) + __set_bit(NETFS_SREQ_HIT_EOF, &subreq->flags); - netfs_subreq_terminated(subreq, err ?: total, false); + if (!err) + subreq->transferred += total; + + netfs_read_subreq_terminated(subreq, err, false); } /** diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c index a183e213a4a5..21527189e430 100644 --- a/fs/adfs/inode.c +++ b/fs/adfs/inode.c @@ -55,12 +55,11 @@ static void adfs_write_failed(struct address_space *mapping, loff_t to) static int adfs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { int ret; - *pagep = NULL; - ret = cont_write_begin(file, mapping, pos, len, pagep, fsdata, + ret = cont_write_begin(file, mapping, pos, len, foliop, fsdata, adfs_get_block, &ADFS_I(mapping->host)->mmu_private); if (unlikely(ret)) diff --git a/fs/affs/dir.c b/fs/affs/dir.c index b2bf7016e1b3..bd40d5f08810 100644 --- a/fs/affs/dir.c +++ b/fs/affs/dir.c @@ -17,13 +17,44 @@ #include <linux/iversion.h> #include "affs.h" +struct affs_dir_data { + unsigned long ino; + u64 cookie; +}; + static int affs_readdir(struct file *, struct dir_context *); +static loff_t affs_dir_llseek(struct file *file, loff_t offset, int whence) +{ + struct affs_dir_data *data = file->private_data; + + return generic_llseek_cookie(file, offset, whence, &data->cookie); +} + +static int affs_dir_open(struct inode *inode, struct file *file) +{ + struct affs_dir_data *data; + + data = kzalloc(sizeof(struct affs_dir_data), GFP_KERNEL); + if (!data) + return -ENOMEM; + file->private_data = data; + return 0; +} + +static int affs_dir_release(struct inode *inode, struct file *file) +{ + kfree(file->private_data); + return 0; +} + const struct file_operations affs_dir_operations = { + .open = affs_dir_open, .read = generic_read_dir, - .llseek = generic_file_llseek, + .llseek = affs_dir_llseek, .iterate_shared = affs_readdir, .fsync = affs_file_fsync, + .release = affs_dir_release, }; /* @@ -45,6 +76,7 @@ static int affs_readdir(struct file *file, struct dir_context *ctx) { struct inode *inode = file_inode(file); + struct affs_dir_data *data = file->private_data; struct super_block *sb = inode->i_sb; struct buffer_head *dir_bh = NULL; struct buffer_head *fh_bh = NULL; @@ -59,7 +91,7 @@ affs_readdir(struct file *file, struct dir_context *ctx) pr_debug("%s(ino=%lu,f_pos=%llx)\n", __func__, inode->i_ino, ctx->pos); if (ctx->pos < 2) { - file->private_data = (void *)0; + data->ino = 0; if (!dir_emit_dots(file, ctx)) return 0; } @@ -80,8 +112,8 @@ affs_readdir(struct file *file, struct dir_context *ctx) /* If the directory hasn't changed since the last call to readdir(), * we can jump directly to where we left off. */ - ino = (u32)(long)file->private_data; - if (ino && inode_eq_iversion(inode, file->f_version)) { + ino = data->ino; + if (ino && inode_eq_iversion(inode, data->cookie)) { pr_debug("readdir() left off=%d\n", ino); goto inside; } @@ -131,8 +163,8 @@ inside: } while (ino); } done: - file->f_version = inode_query_iversion(inode); - file->private_data = (void *)(long)ino; + data->cookie = inode_query_iversion(inode); + data->ino = ino; affs_brelse(fh_bh); out_brelse_dir: diff --git a/fs/affs/file.c b/fs/affs/file.c index 04c018e19602..a5a861dd5223 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -417,12 +417,11 @@ affs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) static int affs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { int ret; - *pagep = NULL; - ret = cont_write_begin(file, mapping, pos, len, pagep, fsdata, + ret = cont_write_begin(file, mapping, pos, len, foliop, fsdata, affs_get_block, &AFFS_I(mapping->host)->mmu_private); if (unlikely(ret)) @@ -433,12 +432,12 @@ static int affs_write_begin(struct file *file, struct address_space *mapping, static int affs_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned int len, unsigned int copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { struct inode *inode = mapping->host; int ret; - ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata); + ret = generic_write_end(file, mapping, pos, len, copied, folio, fsdata); /* Clear Archived bit on file writes, as AmigaOS would do */ if (AFFS_I(inode)->i_protect & FIBF_ARCHIVED) { @@ -648,7 +647,7 @@ static int affs_read_folio_ofs(struct file *file, struct folio *folio) static int affs_write_begin_ofs(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { struct inode *inode = mapping->host; struct folio *folio; @@ -671,7 +670,7 @@ static int affs_write_begin_ofs(struct file *file, struct address_space *mapping mapping_gfp_mask(mapping)); if (IS_ERR(folio)) return PTR_ERR(folio); - *pagep = &folio->page; + *foliop = folio; if (folio_test_uptodate(folio)) return 0; @@ -687,9 +686,8 @@ static int affs_write_begin_ofs(struct file *file, struct address_space *mapping static int affs_write_end_ofs(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { - struct folio *folio = page_folio(page); struct inode *inode = mapping->host; struct super_block *sb = inode->i_sb; struct buffer_head *bh, *prev_bh; @@ -882,14 +880,14 @@ affs_truncate(struct inode *inode) if (inode->i_size > AFFS_I(inode)->mmu_private) { struct address_space *mapping = inode->i_mapping; - struct page *page; + struct folio *folio; void *fsdata = NULL; loff_t isize = inode->i_size; int res; - res = mapping->a_ops->write_begin(NULL, mapping, isize, 0, &page, &fsdata); + res = mapping->a_ops->write_begin(NULL, mapping, isize, 0, &folio, &fsdata); if (!res) - res = mapping->a_ops->write_end(NULL, mapping, isize, 0, 0, page, fsdata); + res = mapping->a_ops->write_end(NULL, mapping, isize, 0, 0, folio, fsdata); else inode->i_size = AFFS_I(inode)->mmu_private; mark_inode_dirty(inode); diff --git a/fs/afs/file.c b/fs/afs/file.c index ec1be0091fdb..492d857a3fa0 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -16,6 +16,7 @@ #include <linux/mm.h> #include <linux/swap.h> #include <linux/netfs.h> +#include <trace/events/netfs.h> #include "internal.h" static int afs_file_mmap(struct file *file, struct vm_area_struct *vma); @@ -242,9 +243,10 @@ static void afs_fetch_data_notify(struct afs_operation *op) req->error = error; if (subreq) { - if (subreq->rreq->origin != NETFS_DIO_READ) - __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); - netfs_subreq_terminated(subreq, error ?: req->actual_len, false); + subreq->rreq->i_size = req->file_size; + if (req->pos + req->actual_len >= req->file_size) + __set_bit(NETFS_SREQ_HIT_EOF, &subreq->flags); + netfs_read_subreq_terminated(subreq, error, false); req->subreq = NULL; } else if (req->done) { req->done(req); @@ -262,6 +264,12 @@ static void afs_fetch_data_success(struct afs_operation *op) afs_fetch_data_notify(op); } +static void afs_fetch_data_aborted(struct afs_operation *op) +{ + afs_check_for_remote_deletion(op); + afs_fetch_data_notify(op); +} + static void afs_fetch_data_put(struct afs_operation *op) { op->fetch.req->error = afs_op_error(op); @@ -272,7 +280,7 @@ static const struct afs_operation_ops afs_fetch_data_operation = { .issue_afs_rpc = afs_fs_fetch_data, .issue_yfs_rpc = yfs_fs_fetch_data, .success = afs_fetch_data_success, - .aborted = afs_check_for_remote_deletion, + .aborted = afs_fetch_data_aborted, .failed = afs_fetch_data_notify, .put = afs_fetch_data_put, }; @@ -294,7 +302,7 @@ int afs_fetch_data(struct afs_vnode *vnode, struct afs_read *req) op = afs_alloc_operation(req->key, vnode->volume); if (IS_ERR(op)) { if (req->subreq) - netfs_subreq_terminated(req->subreq, PTR_ERR(op), false); + netfs_read_subreq_terminated(req->subreq, PTR_ERR(op), false); return PTR_ERR(op); } @@ -305,14 +313,15 @@ int afs_fetch_data(struct afs_vnode *vnode, struct afs_read *req) return afs_do_sync_operation(op); } -static void afs_issue_read(struct netfs_io_subrequest *subreq) +static void afs_read_worker(struct work_struct *work) { + struct netfs_io_subrequest *subreq = container_of(work, struct netfs_io_subrequest, work); struct afs_vnode *vnode = AFS_FS_I(subreq->rreq->inode); struct afs_read *fsreq; fsreq = afs_alloc_read(GFP_NOFS); if (!fsreq) - return netfs_subreq_terminated(subreq, -ENOMEM, false); + return netfs_read_subreq_terminated(subreq, -ENOMEM, false); fsreq->subreq = subreq; fsreq->pos = subreq->start + subreq->transferred; @@ -321,10 +330,17 @@ static void afs_issue_read(struct netfs_io_subrequest *subreq) fsreq->vnode = vnode; fsreq->iter = &subreq->io_iter; + trace_netfs_sreq(subreq, netfs_sreq_trace_submit); afs_fetch_data(fsreq->vnode, fsreq); afs_put_read(fsreq); } +static void afs_issue_read(struct netfs_io_subrequest *subreq) +{ + INIT_WORK(&subreq->work, afs_read_worker); + queue_work(system_long_wq, &subreq->work); +} + static int afs_symlink_read_folio(struct file *file, struct folio *folio) { struct afs_vnode *vnode = AFS_FS_I(folio->mapping->host); diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index 79cd30775b7a..098fa034a1cc 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -304,6 +304,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) struct afs_vnode_param *vp = &op->file[0]; struct afs_read *req = op->fetch.req; const __be32 *bp; + size_t count_before; int ret; _enter("{%u,%zu,%zu/%llu}", @@ -345,10 +346,14 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) /* extract the returned data */ case 2: - _debug("extract data %zu/%llu", - iov_iter_count(call->iter), req->actual_len); + count_before = call->iov_len; + _debug("extract data %zu/%llu", count_before, req->actual_len); ret = afs_extract_data(call, true); + if (req->subreq) { + req->subreq->transferred += count_before - call->iov_len; + netfs_read_subreq_progress(req->subreq, false); + } if (ret < 0) return ret; diff --git a/fs/afs/write.c b/fs/afs/write.c index e959640694c2..34107b55f834 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -89,10 +89,12 @@ static const struct afs_operation_ops afs_store_data_operation = { */ void afs_prepare_write(struct netfs_io_subrequest *subreq) { + struct netfs_io_stream *stream = &subreq->rreq->io_streams[subreq->stream_nr]; + //if (test_bit(NETFS_SREQ_RETRYING, &subreq->flags)) // subreq->max_len = 512 * 1024; //else - subreq->max_len = 256 * 1024 * 1024; + stream->sreq_max_len = 256 * 1024 * 1024; } /* diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c index f521e66d3bf6..024227aba4cd 100644 --- a/fs/afs/yfsclient.c +++ b/fs/afs/yfsclient.c @@ -355,6 +355,7 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) struct afs_vnode_param *vp = &op->file[0]; struct afs_read *req = op->fetch.req; const __be32 *bp; + size_t count_before; int ret; _enter("{%u,%zu, %zu/%llu}", @@ -391,10 +392,14 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) /* extract the returned data */ case 2: - _debug("extract data %zu/%llu", - iov_iter_count(call->iter), req->actual_len); + count_before = call->iov_len; + _debug("extract data %zu/%llu", count_before, req->actual_len); ret = afs_extract_data(call, true); + if (req->subreq) { + req->subreq->transferred += count_before - call->iov_len; + netfs_read_subreq_progress(req->subreq, false); + } if (ret < 0) return ret; @@ -100,7 +100,7 @@ struct kioctx { unsigned long user_id; - struct __percpu kioctx_cpu *cpu; + struct kioctx_cpu __percpu *cpu; /* * For percpu reqs_available, number of slots we move to/from global diff --git a/fs/autofs/autofs_i.h b/fs/autofs/autofs_i.h index 8c1d587b3eef..77c7991d89aa 100644 --- a/fs/autofs/autofs_i.h +++ b/fs/autofs/autofs_i.h @@ -62,6 +62,7 @@ struct autofs_info { struct list_head expiring; struct autofs_sb_info *sbi; + unsigned long exp_timeout; unsigned long last_used; int count; @@ -81,6 +82,9 @@ struct autofs_info { */ #define AUTOFS_INF_PENDING (1<<2) /* dentry pending mount */ +#define AUTOFS_INF_EXPIRE_SET (1<<3) /* per-dentry expire timeout set for + this mount point. + */ struct autofs_wait_queue { wait_queue_head_t queue; struct autofs_wait_queue *next; diff --git a/fs/autofs/dev-ioctl.c b/fs/autofs/dev-ioctl.c index 5bf781ea6d67..f011e026358e 100644 --- a/fs/autofs/dev-ioctl.c +++ b/fs/autofs/dev-ioctl.c @@ -128,7 +128,13 @@ static int validate_dev_ioctl(int cmd, struct autofs_dev_ioctl *param) goto out; } + /* Setting the per-dentry expire timeout requires a trailing + * path component, ie. no '/', so invert the logic of the + * check_name() return for AUTOFS_DEV_IOCTL_TIMEOUT_CMD. + */ err = check_name(param->path); + if (cmd == AUTOFS_DEV_IOCTL_TIMEOUT_CMD) + err = err ? 0 : -EINVAL; if (err) { pr_warn("invalid path supplied for cmd(0x%08x)\n", cmd); @@ -396,16 +402,97 @@ static int autofs_dev_ioctl_catatonic(struct file *fp, return 0; } -/* Set the autofs mount timeout */ +/* + * Set the autofs mount expire timeout. + * + * There are two places an expire timeout can be set, in the autofs + * super block info. (this is all that's needed for direct and offset + * mounts because there's a distinct mount corresponding to each of + * these) and per-dentry within within the dentry info. If a per-dentry + * timeout is set it will override the expire timeout set in the parent + * autofs super block info. + * + * If setting the autofs super block expire timeout the autofs_dev_ioctl + * size field will be equal to the autofs_dev_ioctl structure size. If + * setting the per-dentry expire timeout the mount point name is passed + * in the autofs_dev_ioctl path field and the size field updated to + * reflect this. + * + * Setting the autofs mount expire timeout sets the timeout in the super + * block info. struct. Setting the per-dentry timeout does a little more. + * If the timeout is equal to -1 the per-dentry timeout (and flag) is + * cleared which reverts to using the super block timeout, otherwise if + * timeout is 0 the timeout is set to this value and the flag is left + * set which disables expiration for the mount point, lastly the flag + * and the timeout are set enabling the dentry to use this timeout. + */ static int autofs_dev_ioctl_timeout(struct file *fp, struct autofs_sb_info *sbi, struct autofs_dev_ioctl *param) { - unsigned long timeout; + unsigned long timeout = param->timeout.timeout; + + /* If setting the expire timeout for an individual indirect + * mount point dentry the mount trailing component path is + * placed in param->path and param->size adjusted to account + * for it otherwise param->size it is set to the structure + * size. + */ + if (param->size == AUTOFS_DEV_IOCTL_SIZE) { + param->timeout.timeout = sbi->exp_timeout / HZ; + sbi->exp_timeout = timeout * HZ; + } else { + struct dentry *base = fp->f_path.dentry; + struct inode *inode = base->d_inode; + int path_len = param->size - AUTOFS_DEV_IOCTL_SIZE - 1; + struct dentry *dentry; + struct autofs_info *ino; + + if (!autofs_type_indirect(sbi->type)) + return -EINVAL; + + /* An expire timeout greater than the superblock timeout + * could be a problem at shutdown but the super block + * timeout itself can change so all we can really do is + * warn the user. + */ + if (timeout >= sbi->exp_timeout) + pr_warn("per-mount expire timeout is greater than " + "the parent autofs mount timeout which could " + "prevent shutdown\n"); + + inode_lock_shared(inode); + dentry = try_lookup_one_len(param->path, base, path_len); + inode_unlock_shared(inode); + if (IS_ERR_OR_NULL(dentry)) + return dentry ? PTR_ERR(dentry) : -ENOENT; + ino = autofs_dentry_ino(dentry); + if (!ino) { + dput(dentry); + return -ENOENT; + } + + if (ino->exp_timeout && ino->flags & AUTOFS_INF_EXPIRE_SET) + param->timeout.timeout = ino->exp_timeout / HZ; + else + param->timeout.timeout = sbi->exp_timeout / HZ; + + if (timeout == -1) { + /* Revert to using the super block timeout */ + ino->flags &= ~AUTOFS_INF_EXPIRE_SET; + ino->exp_timeout = 0; + } else { + /* Set the dentry expire flag and timeout. + * + * If timeout is 0 it will prevent the expire + * of this particular automount. + */ + ino->flags |= AUTOFS_INF_EXPIRE_SET; + ino->exp_timeout = timeout * HZ; + } + dput(dentry); + } - timeout = param->timeout.timeout; - param->timeout.timeout = sbi->exp_timeout / HZ; - sbi->exp_timeout = timeout * HZ; return 0; } diff --git a/fs/autofs/expire.c b/fs/autofs/expire.c index 39d8c84c16f4..5c2d459e1e48 100644 --- a/fs/autofs/expire.c +++ b/fs/autofs/expire.c @@ -429,8 +429,6 @@ static struct dentry *autofs_expire_indirect(struct super_block *sb, if (!root) return NULL; - timeout = sbi->exp_timeout; - dentry = NULL; while ((dentry = get_next_positive_subdir(dentry, root))) { spin_lock(&sbi->fs_lock); @@ -441,6 +439,11 @@ static struct dentry *autofs_expire_indirect(struct super_block *sb, } spin_unlock(&sbi->fs_lock); + if (ino->flags & AUTOFS_INF_EXPIRE_SET) + timeout = ino->exp_timeout; + else + timeout = sbi->exp_timeout; + expired = should_expire(dentry, mnt, timeout, how); if (!expired) continue; diff --git a/fs/autofs/inode.c b/fs/autofs/inode.c index cf792d4de4f1..ee2edccaef70 100644 --- a/fs/autofs/inode.c +++ b/fs/autofs/inode.c @@ -19,6 +19,7 @@ struct autofs_info *autofs_new_ino(struct autofs_sb_info *sbi) INIT_LIST_HEAD(&ino->expiring); ino->last_used = jiffies; ino->sbi = sbi; + ino->exp_timeout = -1; ino->count = 1; } return ino; @@ -28,6 +29,7 @@ void autofs_clean_ino(struct autofs_info *ino) { ino->uid = GLOBAL_ROOT_UID; ino->gid = GLOBAL_ROOT_GID; + ino->exp_timeout = -1; ino->last_used = jiffies; } @@ -172,8 +174,7 @@ static int autofs_parse_fd(struct fs_context *fc, struct autofs_sb_info *sbi, ret = autofs_check_pipe(pipe); if (ret < 0) { errorf(fc, "Invalid/unusable pipe"); - if (param->type != fs_value_is_file) - fput(pipe); + fput(pipe); return -EBADF; } diff --git a/fs/bcachefs/alloc_background.c b/fs/bcachefs/alloc_background.c index ba46f1c1d78a..dc3a4024aab6 100644 --- a/fs/bcachefs/alloc_background.c +++ b/fs/bcachefs/alloc_background.c @@ -1968,8 +1968,8 @@ static void bch2_do_discards_fast_work(struct work_struct *work) break; } - bch2_write_ref_put(c, BCH_WRITE_REF_discard_fast); percpu_ref_put(&ca->io_ref); + bch2_write_ref_put(c, BCH_WRITE_REF_discard_fast); } static void bch2_discard_one_bucket_fast(struct bch_dev *ca, u64 bucket) @@ -1979,18 +1979,18 @@ static void bch2_discard_one_bucket_fast(struct bch_dev *ca, u64 bucket) if (discard_in_flight_add(ca, bucket, false)) return; - if (!bch2_dev_get_ioref(c, ca->dev_idx, WRITE)) + if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_discard_fast)) return; - if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_discard_fast)) - goto put_ioref; + if (!bch2_dev_get_ioref(c, ca->dev_idx, WRITE)) + goto put_ref; if (queue_work(c->write_ref_wq, &ca->discard_fast_work)) return; - bch2_write_ref_put(c, BCH_WRITE_REF_discard_fast); -put_ioref: percpu_ref_put(&ca->io_ref); +put_ref: + bch2_write_ref_put(c, BCH_WRITE_REF_discard_fast); } static int invalidate_one_bucket(struct btree_trans *trans, @@ -2132,26 +2132,26 @@ static void bch2_do_invalidates_work(struct work_struct *work) bch2_trans_iter_exit(trans, &iter); err: bch2_trans_put(trans); - bch2_write_ref_put(c, BCH_WRITE_REF_invalidate); percpu_ref_put(&ca->io_ref); + bch2_write_ref_put(c, BCH_WRITE_REF_invalidate); } void bch2_dev_do_invalidates(struct bch_dev *ca) { struct bch_fs *c = ca->fs; - if (!bch2_dev_get_ioref(c, ca->dev_idx, WRITE)) + if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_invalidate)) return; - if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_invalidate)) - goto put_ioref; + if (!bch2_dev_get_ioref(c, ca->dev_idx, WRITE)) + goto put_ref; if (queue_work(c->write_ref_wq, &ca->invalidate_work)) return; - bch2_write_ref_put(c, BCH_WRITE_REF_invalidate); -put_ioref: percpu_ref_put(&ca->io_ref); +put_ref: + bch2_write_ref_put(c, BCH_WRITE_REF_invalidate); } void bch2_do_invalidates(struct bch_fs *c) diff --git a/fs/bcachefs/btree_journal_iter.c b/fs/bcachefs/btree_journal_iter.c index 74933490aaba..c1657182c275 100644 --- a/fs/bcachefs/btree_journal_iter.c +++ b/fs/bcachefs/btree_journal_iter.c @@ -530,6 +530,8 @@ static void __journal_keys_sort(struct journal_keys *keys) { sort(keys->data, keys->nr, sizeof(keys->data[0]), journal_sort_key_cmp, NULL); + cond_resched(); + struct journal_key *dst = keys->data; darray_for_each(*keys, src) { diff --git a/fs/bcachefs/buckets.c b/fs/bcachefs/buckets.c index a2274429e7f4..721bbe1dffc1 100644 --- a/fs/bcachefs/buckets.c +++ b/fs/bcachefs/buckets.c @@ -100,12 +100,13 @@ static int bch2_check_fix_ptr(struct btree_trans *trans, struct bch_dev *ca = bch2_dev_tryget(c, p.ptr.dev); if (!ca) { - if (fsck_err(trans, ptr_to_invalid_device, - "pointer to missing device %u\n" - "while marking %s", - p.ptr.dev, - (printbuf_reset(&buf), - bch2_bkey_val_to_text(&buf, c, k), buf.buf))) + if (fsck_err_on(p.ptr.dev != BCH_SB_MEMBER_INVALID, + trans, ptr_to_invalid_device, + "pointer to missing device %u\n" + "while marking %s", + p.ptr.dev, + (printbuf_reset(&buf), + bch2_bkey_val_to_text(&buf, c, k), buf.buf))) *do_update = true; return 0; } @@ -562,7 +563,7 @@ static int bch2_trigger_pointer(struct btree_trans *trans, struct bch_fs *c = trans->c; struct bch_dev *ca = bch2_dev_tryget(c, p.ptr.dev); if (unlikely(!ca)) { - if (insert) + if (insert && p.ptr.dev != BCH_SB_MEMBER_INVALID) ret = -EIO; goto err; } @@ -876,7 +877,7 @@ int bch2_trigger_extent(struct btree_trans *trans, need_rebalance_delta -= s != 0; need_rebalance_sectors_delta -= s; - s = bch2_bkey_sectors_need_rebalance(c, old); + s = bch2_bkey_sectors_need_rebalance(c, new.s_c); need_rebalance_delta += s != 0; need_rebalance_sectors_delta += s; diff --git a/fs/bcachefs/ec.h b/fs/bcachefs/ec.h index 90962b3c0130..9baf3411a8f9 100644 --- a/fs/bcachefs/ec.h +++ b/fs/bcachefs/ec.h @@ -97,7 +97,9 @@ static inline bool __bch2_ptr_matches_stripe(const struct bch_extent_ptr *stripe const struct bch_extent_ptr *data_ptr, unsigned sectors) { - return data_ptr->dev == stripe_ptr->dev && + return (data_ptr->dev == stripe_ptr->dev || + data_ptr->dev == BCH_SB_MEMBER_INVALID || + stripe_ptr->dev == BCH_SB_MEMBER_INVALID) && data_ptr->gen == stripe_ptr->gen && data_ptr->offset >= stripe_ptr->offset && data_ptr->offset < stripe_ptr->offset + sectors; diff --git a/fs/bcachefs/extents.c b/fs/bcachefs/extents.c index eb31bda19544..324303bf4353 100644 --- a/fs/bcachefs/extents.c +++ b/fs/bcachefs/extents.c @@ -781,14 +781,17 @@ static union bch_extent_entry *extent_entry_prev(struct bkey_ptrs ptrs, /* * Returns pointer to the next entry after the one being dropped: */ -union bch_extent_entry *bch2_bkey_drop_ptr_noerror(struct bkey_s k, - struct bch_extent_ptr *ptr) +void bch2_bkey_drop_ptr_noerror(struct bkey_s k, struct bch_extent_ptr *ptr) { struct bkey_ptrs ptrs = bch2_bkey_ptrs(k); union bch_extent_entry *entry = to_entry(ptr), *next; - union bch_extent_entry *ret = entry; bool drop_crc = true; + if (k.k->type == KEY_TYPE_stripe) { + ptr->dev = BCH_SB_MEMBER_INVALID; + return; + } + EBUG_ON(ptr < &ptrs.start->ptr || ptr >= &ptrs.end->ptr); EBUG_ON(ptr->type != 1 << BCH_EXTENT_ENTRY_ptr); @@ -811,21 +814,16 @@ union bch_extent_entry *bch2_bkey_drop_ptr_noerror(struct bkey_s k, break; if ((extent_entry_is_crc(entry) && drop_crc) || - extent_entry_is_stripe_ptr(entry)) { - ret = (void *) ret - extent_entry_bytes(entry); + extent_entry_is_stripe_ptr(entry)) extent_entry_drop(k, entry); - } } - - return ret; } -union bch_extent_entry *bch2_bkey_drop_ptr(struct bkey_s k, - struct bch_extent_ptr *ptr) +void bch2_bkey_drop_ptr(struct bkey_s k, struct bch_extent_ptr *ptr) { bool have_dirty = bch2_bkey_dirty_devs(k.s_c).nr; - union bch_extent_entry *ret = - bch2_bkey_drop_ptr_noerror(k, ptr); + + bch2_bkey_drop_ptr_noerror(k, ptr); /* * If we deleted all the dirty pointers and there's still cached @@ -837,14 +835,10 @@ union bch_extent_entry *bch2_bkey_drop_ptr(struct bkey_s k, !bch2_bkey_dirty_devs(k.s_c).nr) { k.k->type = KEY_TYPE_error; set_bkey_val_u64s(k.k, 0); - ret = NULL; } else if (!bch2_bkey_nr_ptrs(k.s_c)) { k.k->type = KEY_TYPE_deleted; set_bkey_val_u64s(k.k, 0); - ret = NULL; } - - return ret; } void bch2_bkey_drop_device(struct bkey_s k, unsigned dev) diff --git a/fs/bcachefs/extents.h b/fs/bcachefs/extents.h index 709dd83183be..42a7c6d820a0 100644 --- a/fs/bcachefs/extents.h +++ b/fs/bcachefs/extents.h @@ -649,26 +649,21 @@ static inline void bch2_bkey_append_ptr(struct bkey_i *k, struct bch_extent_ptr void bch2_extent_ptr_decoded_append(struct bkey_i *, struct extent_ptr_decoded *); -union bch_extent_entry *bch2_bkey_drop_ptr_noerror(struct bkey_s, - struct bch_extent_ptr *); -union bch_extent_entry *bch2_bkey_drop_ptr(struct bkey_s, - struct bch_extent_ptr *); +void bch2_bkey_drop_ptr_noerror(struct bkey_s, struct bch_extent_ptr *); +void bch2_bkey_drop_ptr(struct bkey_s, struct bch_extent_ptr *); #define bch2_bkey_drop_ptrs(_k, _ptr, _cond) \ do { \ - struct bkey_ptrs _ptrs = bch2_bkey_ptrs(_k); \ + __label__ _again; \ + struct bkey_ptrs _ptrs; \ +_again: \ + _ptrs = bch2_bkey_ptrs(_k); \ \ - struct bch_extent_ptr *_ptr = &_ptrs.start->ptr; \ - \ - while ((_ptr = bkey_ptr_next(_ptrs, _ptr))) { \ + bkey_for_each_ptr(_ptrs, _ptr) \ if (_cond) { \ - _ptr = (void *) bch2_bkey_drop_ptr(_k, _ptr); \ - _ptrs = bch2_bkey_ptrs(_k); \ - continue; \ + bch2_bkey_drop_ptr(_k, _ptr); \ + goto _again; \ } \ - \ - (_ptr)++; \ - } \ } while (0) bool bch2_bkey_matches_ptr(struct bch_fs *, struct bkey_s_c, diff --git a/fs/bcachefs/fs-io-buffered.c b/fs/bcachefs/fs-io-buffered.c index ec8c427bf588..ff60c041abe5 100644 --- a/fs/bcachefs/fs-io-buffered.c +++ b/fs/bcachefs/fs-io-buffered.c @@ -659,7 +659,7 @@ int bch2_writepages(struct address_space *mapping, struct writeback_control *wbc int bch2_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { struct bch_inode_info *inode = to_bch_ei(mapping->host); struct bch_fs *c = inode->v.i_sb->s_fs_info; @@ -728,12 +728,11 @@ out: goto err; } - *pagep = &folio->page; + *foliop = folio; return 0; err: folio_unlock(folio); folio_put(folio); - *pagep = NULL; err_unlock: bch2_pagecache_add_put(inode); kfree(res); @@ -743,12 +742,11 @@ err_unlock: int bch2_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { struct bch_inode_info *inode = to_bch_ei(mapping->host); struct bch_fs *c = inode->v.i_sb->s_fs_info; struct bch2_folio_reservation *res = fsdata; - struct folio *folio = page_folio(page); unsigned offset = pos - folio_pos(folio); lockdep_assert_held(&inode->v.i_rwsem); diff --git a/fs/bcachefs/fs-io-buffered.h b/fs/bcachefs/fs-io-buffered.h index a6126ff790e6..3207ebbb4ab4 100644 --- a/fs/bcachefs/fs-io-buffered.h +++ b/fs/bcachefs/fs-io-buffered.h @@ -10,10 +10,10 @@ int bch2_read_folio(struct file *, struct folio *); int bch2_writepages(struct address_space *, struct writeback_control *); void bch2_readahead(struct readahead_control *); -int bch2_write_begin(struct file *, struct address_space *, loff_t, - unsigned, struct page **, void **); +int bch2_write_begin(struct file *, struct address_space *, loff_t pos, + unsigned len, struct folio **, void **); int bch2_write_end(struct file *, struct address_space *, loff_t, - unsigned, unsigned, struct page *, void *); + unsigned len, unsigned copied, struct folio *, void *); ssize_t bch2_write_iter(struct kiocb *, struct iov_iter *); diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c index 94c392abef65..011817afc3ad 100644 --- a/fs/bcachefs/fs.c +++ b/fs/bcachefs/fs.c @@ -177,6 +177,14 @@ static unsigned bch2_inode_hash(subvol_inum inum) return jhash_3words(inum.subvol, inum.inum >> 32, inum.inum, JHASH_INITVAL); } +struct bch_inode_info *__bch2_inode_hash_find(struct bch_fs *c, subvol_inum inum) +{ + return to_bch_ei(ilookup5_nowait(c->vfs_sb, + bch2_inode_hash(inum), + bch2_iget5_test, + &inum)); +} + static struct bch_inode_info *bch2_inode_insert(struct bch_fs *c, struct bch_inode_info *inode) { subvol_inum inum = inode_inum(inode); @@ -1644,14 +1652,16 @@ again: break; } } else if (clean_pass && this_pass_clean) { - wait_queue_head_t *wq = bit_waitqueue(&inode->v.i_state, __I_NEW); - DEFINE_WAIT_BIT(wait, &inode->v.i_state, __I_NEW); + struct wait_bit_queue_entry wqe; + struct wait_queue_head *wq_head; - prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); + wq_head = inode_bit_waitqueue(&wqe, &inode->v, __I_NEW); + prepare_to_wait_event(wq_head, &wqe.wq_entry, + TASK_UNINTERRUPTIBLE); mutex_unlock(&c->vfs_inodes_lock); schedule(); - finish_wait(wq, &wait.wq_entry); + finish_wait(wq_head, &wqe.wq_entry); goto again; } } diff --git a/fs/bcachefs/fs.h b/fs/bcachefs/fs.h index c3af7225ff69..990ec43e0365 100644 --- a/fs/bcachefs/fs.h +++ b/fs/bcachefs/fs.h @@ -56,6 +56,8 @@ static inline subvol_inum inode_inum(struct bch_inode_info *inode) }; } +struct bch_inode_info *__bch2_inode_hash_find(struct bch_fs *, subvol_inum); + /* * Set if we've gotten a btree error for this inode, and thus the vfs inode and * btree inode may be inconsistent: @@ -194,6 +196,11 @@ int bch2_vfs_init(void); #define bch2_inode_update_after_write(_trans, _inode, _inode_u, _fields) ({ do {} while (0); }) +static inline struct bch_inode_info *__bch2_inode_hash_find(struct bch_fs *c, subvol_inum inum) +{ + return NULL; +} + static inline void bch2_evict_subvolume_inodes(struct bch_fs *c, snapshot_id_list *s) {} static inline void bch2_vfs_exit(void) {} diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c index 83bd31b44aad..9b3470a97546 100644 --- a/fs/bcachefs/fsck.c +++ b/fs/bcachefs/fsck.c @@ -8,6 +8,7 @@ #include "darray.h" #include "dirent.h" #include "error.h" +#include "fs.h" #include "fs-common.h" #include "fsck.h" #include "inode.h" @@ -962,6 +963,22 @@ fsck_err: return ret; } +static bool bch2_inode_open(struct bch_fs *c, struct bpos p) +{ + subvol_inum inum = { + .subvol = snapshot_t(c, p.snapshot)->subvol, + .inum = p.offset, + }; + + /* snapshot tree corruption, can't safely delete */ + if (!inum.subvol) { + bch_err_ratelimited(c, "%s(): snapshot %u has no subvol", __func__, p.snapshot); + return true; + } + + return __bch2_inode_hash_find(c, inum) != NULL; +} + static int check_inode(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k, @@ -1040,6 +1057,7 @@ static int check_inode(struct btree_trans *trans, } if (u.bi_flags & BCH_INODE_unlinked && + !bch2_inode_open(c, k.k->p) && (!c->sb.clean || fsck_err(trans, inode_unlinked_but_clean, "filesystem marked clean, but inode %llu unlinked", diff --git a/fs/bcachefs/replicas.c b/fs/bcachefs/replicas.c index 12b1d28b7eb4..1f34c92a6d11 100644 --- a/fs/bcachefs/replicas.c +++ b/fs/bcachefs/replicas.c @@ -82,7 +82,8 @@ int bch2_replicas_entry_validate(struct bch_replicas_entry_v1 *r, } for (unsigned i = 0; i < r->nr_devs; i++) - if (!bch2_member_exists(sb, r->devs[i])) { + if (r->devs[i] != BCH_SB_MEMBER_INVALID && + !bch2_member_exists(sb, r->devs[i])) { prt_printf(err, "invalid device %u in entry ", r->devs[i]); goto bad; } @@ -795,7 +796,7 @@ bool bch2_have_enough_devs(struct bch_fs *c, struct bch_devs_mask devs, nr_online += test_bit(e->devs[i], devs.d); struct bch_dev *ca = bch2_dev_rcu(c, e->devs[i]); - nr_failed += ca && ca->mi.state == BCH_MEMBER_STATE_failed; + nr_failed += !ca || ca->mi.state == BCH_MEMBER_STATE_failed; } rcu_read_unlock(); diff --git a/fs/bcachefs/sb-members.c b/fs/bcachefs/sb-members.c index 39196f2a4197..4b765422dd77 100644 --- a/fs/bcachefs/sb-members.c +++ b/fs/bcachefs/sb-members.c @@ -11,7 +11,8 @@ void bch2_dev_missing(struct bch_fs *c, unsigned dev) { - bch2_fs_inconsistent(c, "pointer to nonexistent device %u", dev); + if (dev != BCH_SB_MEMBER_INVALID) + bch2_fs_inconsistent(c, "pointer to nonexistent device %u", dev); } void bch2_dev_bucket_missing(struct bch_fs *c, struct bpos bucket) diff --git a/fs/bcachefs/sb-members_format.h b/fs/bcachefs/sb-members_format.h index e2630548c0f6..d727d2dfda08 100644 --- a/fs/bcachefs/sb-members_format.h +++ b/fs/bcachefs/sb-members_format.h @@ -8,6 +8,11 @@ */ #define BCH_SB_MEMBERS_MAX 64 +/* + * Sentinal value - indicates a device that does not exist + */ +#define BCH_SB_MEMBER_INVALID 255 + #define BCH_MIN_NR_NBUCKETS (1 << 6) #define BCH_IOPS_MEASUREMENTS() \ diff --git a/fs/bcachefs/sysfs.c b/fs/bcachefs/sysfs.c index f393023a3ae2..33f2a64c14c9 100644 --- a/fs/bcachefs/sysfs.c +++ b/fs/bcachefs/sysfs.c @@ -461,7 +461,7 @@ STORE(bch2_fs) sc.gfp_mask = GFP_KERNEL; sc.nr_to_scan = strtoul_or_return(buf); - c->btree_key_cache.shrink->scan_objects(c->btree_cache.shrink, &sc); + c->btree_key_cache.shrink->scan_objects(c->btree_key_cache.shrink, &sc); } if (attr == &sysfs_trigger_gc) diff --git a/fs/bfs/file.c b/fs/bfs/file.c index a778411574a9..fa66a09e496a 100644 --- a/fs/bfs/file.c +++ b/fs/bfs/file.c @@ -172,11 +172,11 @@ static void bfs_write_failed(struct address_space *mapping, loff_t to) static int bfs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { int ret; - ret = block_write_begin(mapping, pos, len, pagep, bfs_get_block); + ret = block_write_begin(mapping, pos, len, foliop, bfs_get_block); if (unlikely(ret)) bfs_write_failed(mapping, pos + len); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 75fa563e4cac..c8568b1a61c4 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -459,7 +459,6 @@ struct btrfs_file_private { void *filldir_buf; u64 last_index; struct extent_state *llseek_cached_state; - bool fsync_skip_inode_lock; }; static inline u32 BTRFS_LEAF_DATA_SIZE(const struct btrfs_fs_info *info) diff --git a/fs/btrfs/direct-io.c b/fs/btrfs/direct-io.c index 67adbe9d294a..364bce34f034 100644 --- a/fs/btrfs/direct-io.c +++ b/fs/btrfs/direct-io.c @@ -864,13 +864,6 @@ again: if (IS_ERR_OR_NULL(dio)) { ret = PTR_ERR_OR_ZERO(dio); } else { - struct btrfs_file_private stack_private = { 0 }; - struct btrfs_file_private *private; - const bool have_private = (file->private_data != NULL); - - if (!have_private) - file->private_data = &stack_private; - /* * If we have a synchronous write, we must make sure the fsync * triggered by the iomap_dio_complete() call below doesn't @@ -879,13 +872,10 @@ again: * partial writes due to the input buffer (or parts of it) not * being already faulted in. */ - private = file->private_data; - private->fsync_skip_inode_lock = true; + ASSERT(current->journal_info == NULL); + current->journal_info = BTRFS_TRANS_DIO_WRITE_STUB; ret = iomap_dio_complete(dio); - private->fsync_skip_inode_lock = false; - - if (!have_private) - file->private_data = NULL; + current->journal_info = NULL; } /* No increment (+=) because iomap returns a cumulative value. */ diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 9914419f3b7d..2aeb8116549c 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1603,7 +1603,6 @@ static inline bool skip_inode_logging(const struct btrfs_log_ctx *ctx) */ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) { - struct btrfs_file_private *private = file->private_data; struct dentry *dentry = file_dentry(file); struct btrfs_inode *inode = BTRFS_I(d_inode(dentry)); struct btrfs_root *root = inode->root; @@ -1613,7 +1612,13 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) int ret = 0, err; u64 len; bool full_sync; - const bool skip_ilock = (private ? private->fsync_skip_inode_lock : false); + bool skip_ilock = false; + + if (current->journal_info == BTRFS_TRANS_DIO_WRITE_STUB) { + skip_ilock = true; + current->journal_info = NULL; + lockdep_assert_held(&inode->vfs_inode.i_rwsem); + } trace_btrfs_sync_file(file, datasync); diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 7d6f5d9420ec..feb8f9f2f358 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -4346,10 +4346,9 @@ static int __btrfs_qgroup_release_data(struct btrfs_inode *inode, int ret; if (btrfs_qgroup_mode(inode->root->fs_info) == BTRFS_QGROUP_MODE_DISABLED) { - extent_changeset_init(&changeset); return clear_record_extent_bits(&inode->io_tree, start, start + len - 1, - EXTENT_QGROUP_RESERVED, &changeset); + EXTENT_QGROUP_RESERVED, NULL); } /* In release case, we shouldn't have @reserved */ diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 98c03ddc760b..dd9ce9b9f69e 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -27,6 +27,12 @@ struct btrfs_root_item; struct btrfs_root; struct btrfs_path; +/* + * Signal that a direct IO write is in progress, to avoid deadlock for sync + * direct IO writes when fsync is called during the direct IO write path. + */ +#define BTRFS_TRANS_DIO_WRITE_STUB ((void *) 1) + /* Radix-tree tag for roots that are part of the trasaction. */ #define BTRFS_ROOT_TRANS_TAG 0 diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 66f63e82af79..047e3337852e 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1406,6 +1406,8 @@ static int btrfs_load_block_group_dup(struct btrfs_block_group *bg, return -EINVAL; } + bg->zone_capacity = min_not_zero(zone_info[0].capacity, zone_info[1].capacity); + if (zone_info[0].alloc_offset == WP_MISSING_DEV) { btrfs_err(bg->fs_info, "zoned: cannot recover write pointer for zone %llu", @@ -1432,7 +1434,6 @@ static int btrfs_load_block_group_dup(struct btrfs_block_group *bg, } bg->alloc_offset = zone_info[0].alloc_offset; - bg->zone_capacity = min(zone_info[0].capacity, zone_info[1].capacity); return 0; } @@ -1450,6 +1451,9 @@ static int btrfs_load_block_group_raid1(struct btrfs_block_group *bg, return -EINVAL; } + /* In case a device is missing we have a cap of 0, so don't use it. */ + bg->zone_capacity = min_not_zero(zone_info[0].capacity, zone_info[1].capacity); + for (i = 0; i < map->num_stripes; i++) { if (zone_info[i].alloc_offset == WP_MISSING_DEV || zone_info[i].alloc_offset == WP_CONVENTIONAL) @@ -1471,9 +1475,6 @@ static int btrfs_load_block_group_raid1(struct btrfs_block_group *bg, if (test_bit(0, active)) set_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &bg->runtime_flags); } - /* In case a device is missing we have a cap of 0, so don't use it. */ - bg->zone_capacity = min_not_zero(zone_info[0].capacity, - zone_info[1].capacity); } if (zone_info[0].alloc_offset != WP_MISSING_DEV) @@ -1563,6 +1564,7 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new) unsigned long *active = NULL; u64 last_alloc = 0; u32 num_sequential = 0, num_conventional = 0; + u64 profile; if (!btrfs_is_zoned(fs_info)) return 0; @@ -1623,7 +1625,8 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new) } } - switch (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) { + profile = map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK; + switch (profile) { case 0: /* single */ ret = btrfs_load_block_group_single(cache, &zone_info[0], active); break; @@ -1650,6 +1653,23 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new) goto out; } + if (ret == -EIO && profile != 0 && profile != BTRFS_BLOCK_GROUP_RAID0 && + profile != BTRFS_BLOCK_GROUP_RAID10) { + /* + * Detected broken write pointer. Make this block group + * unallocatable by setting the allocation pointer at the end of + * allocatable region. Relocating this block group will fix the + * mismatch. + * + * Currently, we cannot handle RAID0 or RAID10 case like this + * because we don't have a proper zone_capacity value. But, + * reading from this block group won't work anyway by a missing + * stripe. + */ + cache->alloc_offset = cache->zone_capacity; + ret = 0; + } + out: /* Reject non SINGLE data profiles without RST */ if ((map->type & BTRFS_BLOCK_GROUP_DATA) && diff --git a/fs/buffer.c b/fs/buffer.c index e55ad471c530..1fc9a50def0b 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -774,12 +774,11 @@ EXPORT_SYMBOL(block_dirty_folio); static int fsync_buffers_list(spinlock_t *lock, struct list_head *list) { struct buffer_head *bh; - struct list_head tmp; struct address_space *mapping; int err = 0, err2; struct blk_plug plug; + LIST_HEAD(tmp); - INIT_LIST_HEAD(&tmp); blk_start_plug(&plug); spin_lock(lock); @@ -958,12 +957,9 @@ no_grow: } EXPORT_SYMBOL_GPL(folio_alloc_buffers); -struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, - bool retry) +struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size) { gfp_t gfp = GFP_NOFS | __GFP_ACCOUNT; - if (retry) - gfp |= __GFP_NOFAIL; return folio_alloc_buffers(page_folio(page), size, gfp); } @@ -2168,11 +2164,10 @@ int __block_write_begin_int(struct folio *folio, loff_t pos, unsigned len, return err; } -int __block_write_begin(struct page *page, loff_t pos, unsigned len, +int __block_write_begin(struct folio *folio, loff_t pos, unsigned len, get_block_t *get_block) { - return __block_write_begin_int(page_folio(page), pos, len, get_block, - NULL); + return __block_write_begin_int(folio, pos, len, get_block, NULL); } EXPORT_SYMBOL(__block_write_begin); @@ -2222,33 +2217,33 @@ static void __block_commit_write(struct folio *folio, size_t from, size_t to) * The filesystem needs to handle block truncation upon failure. */ int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, get_block_t *get_block) + struct folio **foliop, get_block_t *get_block) { pgoff_t index = pos >> PAGE_SHIFT; - struct page *page; + struct folio *folio; int status; - page = grab_cache_page_write_begin(mapping, index); - if (!page) - return -ENOMEM; + folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN, + mapping_gfp_mask(mapping)); + if (IS_ERR(folio)) + return PTR_ERR(folio); - status = __block_write_begin(page, pos, len, get_block); + status = __block_write_begin_int(folio, pos, len, get_block, NULL); if (unlikely(status)) { - unlock_page(page); - put_page(page); - page = NULL; + folio_unlock(folio); + folio_put(folio); + folio = NULL; } - *pagep = page; + *foliop = folio; return status; } EXPORT_SYMBOL(block_write_begin); int block_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { - struct folio *folio = page_folio(page); size_t start = pos - folio_pos(folio); if (unlikely(copied < len)) { @@ -2280,19 +2275,19 @@ EXPORT_SYMBOL(block_write_end); int generic_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { struct inode *inode = mapping->host; loff_t old_size = inode->i_size; bool i_size_changed = false; - copied = block_write_end(file, mapping, pos, len, copied, page, fsdata); + copied = block_write_end(file, mapping, pos, len, copied, folio, fsdata); /* * No need to use i_size_read() here, the i_size cannot change under us * because we hold i_rwsem. * - * But it's important to update i_size while still holding page lock: + * But it's important to update i_size while still holding folio lock: * page writeout could otherwise come in and zero beyond i_size. */ if (pos + copied > inode->i_size) { @@ -2300,8 +2295,8 @@ int generic_write_end(struct file *file, struct address_space *mapping, i_size_changed = true; } - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); if (old_size < pos) pagecache_isize_extended(inode, old_size, pos); @@ -2467,7 +2462,7 @@ int generic_cont_expand_simple(struct inode *inode, loff_t size) { struct address_space *mapping = inode->i_mapping; const struct address_space_operations *aops = mapping->a_ops; - struct page *page; + struct folio *folio; void *fsdata = NULL; int err; @@ -2475,11 +2470,11 @@ int generic_cont_expand_simple(struct inode *inode, loff_t size) if (err) goto out; - err = aops->write_begin(NULL, mapping, size, 0, &page, &fsdata); + err = aops->write_begin(NULL, mapping, size, 0, &folio, &fsdata); if (err) goto out; - err = aops->write_end(NULL, mapping, size, 0, 0, page, fsdata); + err = aops->write_end(NULL, mapping, size, 0, 0, folio, fsdata); BUG_ON(err > 0); out: @@ -2493,7 +2488,7 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping, struct inode *inode = mapping->host; const struct address_space_operations *aops = mapping->a_ops; unsigned int blocksize = i_blocksize(inode); - struct page *page; + struct folio *folio; void *fsdata = NULL; pgoff_t index, curidx; loff_t curpos; @@ -2512,12 +2507,12 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping, len = PAGE_SIZE - zerofrom; err = aops->write_begin(file, mapping, curpos, len, - &page, &fsdata); + &folio, &fsdata); if (err) goto out; - zero_user(page, zerofrom, len); + folio_zero_range(folio, offset_in_folio(folio, curpos), len); err = aops->write_end(file, mapping, curpos, len, len, - page, fsdata); + folio, fsdata); if (err < 0) goto out; BUG_ON(err != len); @@ -2545,12 +2540,12 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping, len = offset - zerofrom; err = aops->write_begin(file, mapping, curpos, len, - &page, &fsdata); + &folio, &fsdata); if (err) goto out; - zero_user(page, zerofrom, len); + folio_zero_range(folio, offset_in_folio(folio, curpos), len); err = aops->write_end(file, mapping, curpos, len, len, - page, fsdata); + folio, fsdata); if (err < 0) goto out; BUG_ON(err != len); @@ -2566,7 +2561,7 @@ out: */ int cont_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata, + struct folio **foliop, void **fsdata, get_block_t *get_block, loff_t *bytes) { struct inode *inode = mapping->host; @@ -2584,7 +2579,7 @@ int cont_write_begin(struct file *file, struct address_space *mapping, (*bytes)++; } - return block_write_begin(mapping, pos, len, pagep, get_block); + return block_write_begin(mapping, pos, len, foliop, get_block); } EXPORT_SYMBOL(cont_write_begin); diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c index a91acd03ee12..6a821a959b59 100644 --- a/fs/cachefiles/io.c +++ b/fs/cachefiles/io.c @@ -627,11 +627,12 @@ static void cachefiles_prepare_write_subreq(struct netfs_io_subrequest *subreq) { struct netfs_io_request *wreq = subreq->rreq; struct netfs_cache_resources *cres = &wreq->cache_resources; + struct netfs_io_stream *stream = &wreq->io_streams[subreq->stream_nr]; _enter("W=%x[%x] %llx", wreq->debug_id, subreq->debug_index, subreq->start); - subreq->max_len = MAX_RW_COUNT; - subreq->max_nr_segs = BIO_MAX_VECS; + stream->sreq_max_len = MAX_RW_COUNT; + stream->sreq_max_segs = BIO_MAX_VECS; if (!cachefiles_cres_file(cres)) { if (!fscache_wait_for_operation(cres, FSCACHE_WANT_WRITE)) @@ -647,6 +648,7 @@ static void cachefiles_issue_write(struct netfs_io_subrequest *subreq) struct netfs_cache_resources *cres = &wreq->cache_resources; struct cachefiles_object *object = cachefiles_cres_object(cres); struct cachefiles_cache *cache = object->volume->cache; + struct netfs_io_stream *stream = &wreq->io_streams[subreq->stream_nr]; const struct cred *saved_cred; size_t off, pre, post, len = subreq->len; loff_t start = subreq->start; @@ -660,6 +662,7 @@ static void cachefiles_issue_write(struct netfs_io_subrequest *subreq) if (off) { pre = CACHEFILES_DIO_BLOCK_SIZE - off; if (pre >= len) { + fscache_count_dio_misfit(); netfs_write_subrequest_terminated(subreq, len, false); return; } @@ -670,10 +673,22 @@ static void cachefiles_issue_write(struct netfs_io_subrequest *subreq) } /* We also need to end on the cache granularity boundary */ + if (start + len == wreq->i_size) { + size_t part = len % CACHEFILES_DIO_BLOCK_SIZE; + size_t need = CACHEFILES_DIO_BLOCK_SIZE - part; + + if (part && stream->submit_extendable_to >= need) { + len += need; + subreq->len += need; + subreq->io_iter.count += need; + } + } + post = len & (CACHEFILES_DIO_BLOCK_SIZE - 1); if (post) { len -= post; if (len == 0) { + fscache_count_dio_misfit(); netfs_write_subrequest_terminated(subreq, post, false); return; } diff --git a/fs/cachefiles/xattr.c b/fs/cachefiles/xattr.c index 4dd8a993c60a..7c6f260a3be5 100644 --- a/fs/cachefiles/xattr.c +++ b/fs/cachefiles/xattr.c @@ -64,9 +64,15 @@ int cachefiles_set_object_xattr(struct cachefiles_object *object) memcpy(buf->data, fscache_get_aux(object->cookie), len); ret = cachefiles_inject_write_error(); - if (ret == 0) - ret = vfs_setxattr(&nop_mnt_idmap, dentry, cachefiles_xattr_cache, - buf, sizeof(struct cachefiles_xattr) + len, 0); + if (ret == 0) { + ret = mnt_want_write_file(file); + if (ret == 0) { + ret = vfs_setxattr(&nop_mnt_idmap, dentry, + cachefiles_xattr_cache, buf, + sizeof(struct cachefiles_xattr) + len, 0); + mnt_drop_write_file(file); + } + } if (ret < 0) { trace_cachefiles_vfs_error(object, file_inode(file), ret, cachefiles_trace_setxattr_error); @@ -151,8 +157,14 @@ int cachefiles_remove_object_xattr(struct cachefiles_cache *cache, int ret; ret = cachefiles_inject_remove_error(); - if (ret == 0) - ret = vfs_removexattr(&nop_mnt_idmap, dentry, cachefiles_xattr_cache); + if (ret == 0) { + ret = mnt_want_write(cache->mnt); + if (ret == 0) { + ret = vfs_removexattr(&nop_mnt_idmap, dentry, + cachefiles_xattr_cache); + mnt_drop_write(cache->mnt); + } + } if (ret < 0) { trace_cachefiles_vfs_error(object, d_inode(dentry), ret, cachefiles_trace_remxattr_error); @@ -208,9 +220,15 @@ bool cachefiles_set_volume_xattr(struct cachefiles_volume *volume) memcpy(buf->data, p, volume->vcookie->coherency_len); ret = cachefiles_inject_write_error(); - if (ret == 0) - ret = vfs_setxattr(&nop_mnt_idmap, dentry, cachefiles_xattr_cache, - buf, len, 0); + if (ret == 0) { + ret = mnt_want_write(volume->cache->mnt); + if (ret == 0) { + ret = vfs_setxattr(&nop_mnt_idmap, dentry, + cachefiles_xattr_cache, + buf, len, 0); + mnt_drop_write(volume->cache->mnt); + } + } if (ret < 0) { trace_cachefiles_vfs_error(NULL, d_inode(dentry), ret, cachefiles_trace_setxattr_error); diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index c4744a02db75..5d9ccda098cc 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -13,6 +13,7 @@ #include <linux/iversion.h> #include <linux/ktime.h> #include <linux/netfs.h> +#include <trace/events/netfs.h> #include "super.h" #include "mds_client.h" @@ -205,21 +206,6 @@ static void ceph_netfs_expand_readahead(struct netfs_io_request *rreq) } } -static bool ceph_netfs_clamp_length(struct netfs_io_subrequest *subreq) -{ - struct inode *inode = subreq->rreq->inode; - struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode); - struct ceph_inode_info *ci = ceph_inode(inode); - u64 objno, objoff; - u32 xlen; - - /* Truncate the extent at the end of the current block */ - ceph_calc_file_object_mapping(&ci->i_layout, subreq->start, subreq->len, - &objno, &objoff, &xlen); - subreq->len = min(xlen, fsc->mount_options->rsize); - return true; -} - static void finish_netfs_read(struct ceph_osd_request *req) { struct inode *inode = req->r_inode; @@ -264,7 +250,12 @@ static void finish_netfs_read(struct ceph_osd_request *req) calc_pages_for(osd_data->alignment, osd_data->length), false); } - netfs_subreq_terminated(subreq, err, false); + if (err > 0) { + subreq->transferred = err; + err = 0; + } + trace_netfs_sreq(subreq, netfs_sreq_trace_io_progress); + netfs_read_subreq_terminated(subreq, err, false); iput(req->r_inode); ceph_dec_osd_stopping_blocker(fsc->mdsc); } @@ -278,7 +269,6 @@ static bool ceph_netfs_issue_op_inline(struct netfs_io_subrequest *subreq) struct ceph_mds_request *req; struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb); struct ceph_inode_info *ci = ceph_inode(inode); - struct iov_iter iter; ssize_t err = 0; size_t len; int mode; @@ -301,6 +291,7 @@ static bool ceph_netfs_issue_op_inline(struct netfs_io_subrequest *subreq) req->r_args.getattr.mask = cpu_to_le32(CEPH_STAT_CAP_INLINE_DATA); req->r_num_caps = 2; + trace_netfs_sreq(subreq, netfs_sreq_trace_submit); err = ceph_mdsc_do_request(mdsc, NULL, req); if (err < 0) goto out; @@ -314,17 +305,36 @@ static bool ceph_netfs_issue_op_inline(struct netfs_io_subrequest *subreq) } len = min_t(size_t, iinfo->inline_len - subreq->start, subreq->len); - iov_iter_xarray(&iter, ITER_DEST, &rreq->mapping->i_pages, subreq->start, len); - err = copy_to_iter(iinfo->inline_data + subreq->start, len, &iter); - if (err == 0) + err = copy_to_iter(iinfo->inline_data + subreq->start, len, &subreq->io_iter); + if (err == 0) { err = -EFAULT; + } else { + subreq->transferred += err; + err = 0; + } ceph_mdsc_put_request(req); out: - netfs_subreq_terminated(subreq, err, false); + netfs_read_subreq_terminated(subreq, err, false); return true; } +static int ceph_netfs_prepare_read(struct netfs_io_subrequest *subreq) +{ + struct netfs_io_request *rreq = subreq->rreq; + struct inode *inode = rreq->inode; + struct ceph_inode_info *ci = ceph_inode(inode); + struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode); + u64 objno, objoff; + u32 xlen; + + /* Truncate the extent at the end of the current block */ + ceph_calc_file_object_mapping(&ci->i_layout, subreq->start, subreq->len, + &objno, &objoff, &xlen); + rreq->io_streams[0].sreq_max_len = umin(xlen, fsc->mount_options->rsize); + return 0; +} + static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq) { struct netfs_io_request *rreq = subreq->rreq; @@ -334,9 +344,8 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq) struct ceph_client *cl = fsc->client; struct ceph_osd_request *req = NULL; struct ceph_vino vino = ceph_vino(inode); - struct iov_iter iter; - int err = 0; - u64 len = subreq->len; + int err; + u64 len; bool sparse = IS_ENCRYPTED(inode) || ceph_test_mount_opt(fsc, SPARSEREAD); u64 off = subreq->start; int extent_cnt; @@ -349,6 +358,12 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq) if (ceph_has_inline_data(ci) && ceph_netfs_issue_op_inline(subreq)) return; + // TODO: This rounding here is slightly dodgy. It *should* work, for + // now, as the cache only deals in blocks that are a multiple of + // PAGE_SIZE and fscrypt blocks are at most PAGE_SIZE. What needs to + // happen is for the fscrypt driving to be moved into netfslib and the + // data in the cache also to be stored encrypted. + len = subreq->len; ceph_fscrypt_adjust_off_and_len(inode, &off, &len); req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout, vino, @@ -371,8 +386,6 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq) doutc(cl, "%llx.%llx pos=%llu orig_len=%zu len=%llu\n", ceph_vinop(inode), subreq->start, subreq->len, len); - iov_iter_xarray(&iter, ITER_DEST, &rreq->mapping->i_pages, subreq->start, len); - /* * FIXME: For now, use CEPH_OSD_DATA_TYPE_PAGES instead of _ITER for * encrypted inodes. We'd need infrastructure that handles an iov_iter @@ -384,7 +397,7 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq) struct page **pages; size_t page_off; - err = iov_iter_get_pages_alloc2(&iter, &pages, len, &page_off); + err = iov_iter_get_pages_alloc2(&subreq->io_iter, &pages, len, &page_off); if (err < 0) { doutc(cl, "%llx.%llx failed to allocate pages, %d\n", ceph_vinop(inode), err); @@ -399,7 +412,7 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq) osd_req_op_extent_osd_data_pages(req, 0, pages, len, 0, false, false); } else { - osd_req_op_extent_osd_iter(req, 0, &iter); + osd_req_op_extent_osd_iter(req, 0, &subreq->io_iter); } if (!ceph_inc_osd_stopping_blocker(fsc->mdsc)) { err = -EIO; @@ -410,17 +423,19 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq) req->r_inode = inode; ihold(inode); + trace_netfs_sreq(subreq, netfs_sreq_trace_submit); ceph_osdc_start_request(req->r_osdc, req); out: ceph_osdc_put_request(req); if (err) - netfs_subreq_terminated(subreq, err, false); + netfs_read_subreq_terminated(subreq, err, false); doutc(cl, "%llx.%llx result %d\n", ceph_vinop(inode), err); } static int ceph_init_request(struct netfs_io_request *rreq, struct file *file) { struct inode *inode = rreq->inode; + struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode); struct ceph_client *cl = ceph_inode_to_client(inode); int got = 0, want = CEPH_CAP_FILE_CACHE; struct ceph_netfs_request_data *priv; @@ -472,6 +487,7 @@ static int ceph_init_request(struct netfs_io_request *rreq, struct file *file) priv->caps = got; rreq->netfs_priv = priv; + rreq->io_streams[0].sreq_max_len = fsc->mount_options->rsize; out: if (ret < 0) @@ -496,9 +512,9 @@ static void ceph_netfs_free_request(struct netfs_io_request *rreq) const struct netfs_request_ops ceph_netfs_ops = { .init_request = ceph_init_request, .free_request = ceph_netfs_free_request, + .prepare_read = ceph_netfs_prepare_read, .issue_read = ceph_netfs_issue_read, .expand_readahead = ceph_netfs_expand_readahead, - .clamp_length = ceph_netfs_clamp_length, .check_write_begin = ceph_netfs_check_write_begin, }; @@ -1508,20 +1524,18 @@ static int ceph_netfs_check_write_begin(struct file *file, loff_t pos, unsigned */ static int ceph_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { struct inode *inode = file_inode(file); struct ceph_inode_info *ci = ceph_inode(inode); - struct folio *folio = NULL; int r; - r = netfs_write_begin(&ci->netfs, file, inode->i_mapping, pos, len, &folio, NULL); + r = netfs_write_begin(&ci->netfs, file, inode->i_mapping, pos, len, foliop, NULL); if (r < 0) return r; - folio_wait_private_2(folio); /* [DEPRECATED] */ - WARN_ON_ONCE(!folio_test_locked(folio)); - *pagep = &folio->page; + folio_wait_private_2(*foliop); /* [DEPRECATED] */ + WARN_ON_ONCE(!folio_test_locked(*foliop)); return 0; } @@ -1531,9 +1545,8 @@ static int ceph_write_begin(struct file *file, struct address_space *mapping, */ static int ceph_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *subpage, void *fsdata) + struct folio *folio, void *fsdata) { - struct folio *folio = page_folio(subpage); struct inode *inode = file_inode(file); struct ceph_client *cl = ceph_inode_to_client(inode); bool check_cap = false; diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 18c72b305858..ddec8c9244ee 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -707,7 +707,6 @@ static loff_t ceph_dir_llseek(struct file *file, loff_t offset, int whence) if (offset != file->f_pos) { file->f_pos = offset; - file->f_version = 0; dfi->file_info.flags &= ~CEPH_F_ATEND; } retval = offset; diff --git a/fs/coda/inode.c b/fs/coda/inode.c index 6898dc621011..6896fce122e1 100644 --- a/fs/coda/inode.c +++ b/fs/coda/inode.c @@ -119,31 +119,43 @@ static const struct fs_parameter_spec coda_param_specs[] = { {} }; -static int coda_parse_fd(struct fs_context *fc, int fd) +static int coda_set_idx(struct fs_context *fc, struct file *file) { struct coda_fs_context *ctx = fc->fs_private; - struct fd f; struct inode *inode; int idx; - f = fdget(fd); - if (!f.file) - return -EBADF; - inode = file_inode(f.file); + inode = file_inode(file); if (!S_ISCHR(inode->i_mode) || imajor(inode) != CODA_PSDEV_MAJOR) { - fdput(f); - return invalf(fc, "code: Not coda psdev"); + return invalf(fc, "coda: Not coda psdev"); } - idx = iminor(inode); - fdput(f); - if (idx < 0 || idx >= MAX_CODADEVS) return invalf(fc, "coda: Bad minor number"); ctx->idx = idx; return 0; } +static int coda_parse_fd(struct fs_context *fc, struct fs_parameter *param, + struct fs_parse_result *result) +{ + struct file *file; + int err; + + if (param->type == fs_value_is_file) { + file = param->file; + param->file = NULL; + } else { + file = fget(result->uint_32); + } + if (!file) + return -EBADF; + + err = coda_set_idx(fc, file); + fput(file); + return err; +} + static int coda_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct fs_parse_result result; @@ -155,7 +167,7 @@ static int coda_parse_param(struct fs_context *fc, struct fs_parameter *param) switch (opt) { case Opt_fd: - return coda_parse_fd(fc, result.uint_32); + return coda_parse_fd(fc, param, &result); } return 0; @@ -167,6 +179,7 @@ static int coda_parse_param(struct fs_context *fc, struct fs_parameter *param) */ static int coda_parse_monolithic(struct fs_context *fc, void *_data) { + struct file *file; struct coda_mount_data *data = _data; if (!data) @@ -175,7 +188,11 @@ static int coda_parse_monolithic(struct fs_context *fc, void *_data) if (data->version != CODA_MOUNT_VERSION) return invalf(fc, "coda: Bad mount version"); - coda_parse_fd(fc, data->fd); + file = fget(data->fd); + if (file) { + coda_set_idx(fc, file); + fput(file); + } return 0; } diff --git a/fs/dcache.c b/fs/dcache.c index 6386b9b625dd..0f6b16ba30d0 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -1913,8 +1913,13 @@ void d_instantiate_new(struct dentry *entry, struct inode *inode) __d_instantiate(entry, inode); WARN_ON(!(inode->i_state & I_NEW)); inode->i_state &= ~I_NEW & ~I_CREATING; + /* + * Pairs with the barrier in prepare_to_wait_event() to make sure + * ___wait_var_event() either sees the bit cleared or + * waitqueue_active() check in wake_up_var() sees the waiter. + */ smp_mb(); - wake_up_bit(&inode->i_state, __I_NEW); + inode_wake_up_bit(inode, __I_NEW); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(d_instantiate_new); @@ -2168,9 +2173,6 @@ seqretry: * without taking d_lock and checking d_seq sequence count against @seq * returned here. * - * A refcount may be taken on the found dentry with the d_rcu_to_refcount - * function. - * * Alternatively, __d_lookup_rcu may be called again to look up the child of * the returned dentry, so long as its parent's seqlock is checked after the * child is looked up. Thus, an interlocking stepping of sequence lock checks diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 91521576f500..66d9b3b4c588 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -89,12 +89,14 @@ enum { Opt_uid, Opt_gid, Opt_mode, + Opt_source, }; static const struct fs_parameter_spec debugfs_param_specs[] = { fsparam_gid ("gid", Opt_gid), fsparam_u32oct ("mode", Opt_mode), fsparam_uid ("uid", Opt_uid), + fsparam_string ("source", Opt_source), {} }; @@ -126,6 +128,12 @@ static int debugfs_parse_param(struct fs_context *fc, struct fs_parameter *param case Opt_mode: opts->mode = result.uint_32 & S_IALLUGO; break; + case Opt_source: + if (fc->source) + return invalfc(fc, "Multiple sources specified"); + fc->source = param->string; + param->string = NULL; + break; /* * We might like to report bad mount options here; * but traditionally debugfs has ignored all mount options diff --git a/fs/direct-io.c b/fs/direct-io.c index b0aafe640fa4..bbd05f1a2145 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -37,7 +37,6 @@ #include <linux/rwsem.h> #include <linux/uio.h> #include <linux/atomic.h> -#include <linux/prefetch.h> #include "internal.h" @@ -1121,11 +1120,6 @@ ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct blk_plug plug; unsigned long align = offset | iov_iter_alignment(iter); - /* - * Avoid references to bdev if not absolutely needed to give - * the early prefetch in the caller enough time. - */ - /* watch out for a 0 len io from a tricksy fs */ if (iov_iter_rw(iter) == READ && !count) return 0; diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c index e2483acc4366..287e5d407f08 100644 --- a/fs/ecryptfs/mmap.c +++ b/fs/ecryptfs/mmap.c @@ -234,17 +234,17 @@ out: /* * Called with lower inode mutex held. */ -static int fill_zeros_to_end_of_page(struct page *page, unsigned int to) +static int fill_zeros_to_end_of_page(struct folio *folio, unsigned int to) { - struct inode *inode = page->mapping->host; + struct inode *inode = folio->mapping->host; int end_byte_in_page; - if ((i_size_read(inode) / PAGE_SIZE) != page->index) + if ((i_size_read(inode) / PAGE_SIZE) != folio->index) goto out; end_byte_in_page = i_size_read(inode) % PAGE_SIZE; if (to > end_byte_in_page) end_byte_in_page = to; - zero_user_segment(page, end_byte_in_page, PAGE_SIZE); + folio_zero_segment(folio, end_byte_in_page, PAGE_SIZE); out: return 0; } @@ -255,7 +255,7 @@ out: * @mapping: The eCryptfs object * @pos: The file offset at which to start writing * @len: Length of the write - * @pagep: Pointer to return the page + * @foliop: Pointer to return the folio * @fsdata: Pointer to return fs data (unused) * * This function must zero any hole we create @@ -265,38 +265,39 @@ out: static int ecryptfs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { pgoff_t index = pos >> PAGE_SHIFT; - struct page *page; + struct folio *folio; loff_t prev_page_end_size; int rc = 0; - page = grab_cache_page_write_begin(mapping, index); - if (!page) - return -ENOMEM; - *pagep = page; + folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN, + mapping_gfp_mask(mapping)); + if (IS_ERR(folio)) + return PTR_ERR(folio); + *foliop = folio; prev_page_end_size = ((loff_t)index << PAGE_SHIFT); - if (!PageUptodate(page)) { + if (!folio_test_uptodate(folio)) { struct ecryptfs_crypt_stat *crypt_stat = &ecryptfs_inode_to_private(mapping->host)->crypt_stat; if (!(crypt_stat->flags & ECRYPTFS_ENCRYPTED)) { rc = ecryptfs_read_lower_page_segment( - page, index, 0, PAGE_SIZE, mapping->host); + &folio->page, index, 0, PAGE_SIZE, mapping->host); if (rc) { printk(KERN_ERR "%s: Error attempting to read " "lower page segment; rc = [%d]\n", __func__, rc); - ClearPageUptodate(page); + folio_clear_uptodate(folio); goto out; } else - SetPageUptodate(page); + folio_mark_uptodate(folio); } else if (crypt_stat->flags & ECRYPTFS_VIEW_AS_ENCRYPTED) { if (crypt_stat->flags & ECRYPTFS_METADATA_IN_XATTR) { rc = ecryptfs_copy_up_encrypted_with_header( - page, crypt_stat); + &folio->page, crypt_stat); if (rc) { printk(KERN_ERR "%s: Error attempting " "to copy the encrypted content " @@ -304,46 +305,46 @@ static int ecryptfs_write_begin(struct file *file, "inserting the metadata from " "the xattr into the header; rc " "= [%d]\n", __func__, rc); - ClearPageUptodate(page); + folio_clear_uptodate(folio); goto out; } - SetPageUptodate(page); + folio_mark_uptodate(folio); } else { rc = ecryptfs_read_lower_page_segment( - page, index, 0, PAGE_SIZE, + &folio->page, index, 0, PAGE_SIZE, mapping->host); if (rc) { printk(KERN_ERR "%s: Error reading " "page; rc = [%d]\n", __func__, rc); - ClearPageUptodate(page); + folio_clear_uptodate(folio); goto out; } - SetPageUptodate(page); + folio_mark_uptodate(folio); } } else { if (prev_page_end_size - >= i_size_read(page->mapping->host)) { - zero_user(page, 0, PAGE_SIZE); - SetPageUptodate(page); + >= i_size_read(mapping->host)) { + folio_zero_range(folio, 0, PAGE_SIZE); + folio_mark_uptodate(folio); } else if (len < PAGE_SIZE) { - rc = ecryptfs_decrypt_page(page); + rc = ecryptfs_decrypt_page(&folio->page); if (rc) { printk(KERN_ERR "%s: Error decrypting " "page at index [%ld]; " "rc = [%d]\n", - __func__, page->index, rc); - ClearPageUptodate(page); + __func__, folio->index, rc); + folio_clear_uptodate(folio); goto out; } - SetPageUptodate(page); + folio_mark_uptodate(folio); } } } /* If creating a page or more of holes, zero them out via truncate. * Note, this will increase i_size. */ if (index != 0) { - if (prev_page_end_size > i_size_read(page->mapping->host)) { + if (prev_page_end_size > i_size_read(mapping->host)) { rc = ecryptfs_truncate(file->f_path.dentry, prev_page_end_size); if (rc) { @@ -359,12 +360,11 @@ static int ecryptfs_write_begin(struct file *file, * of page? Zero it out. */ if ((i_size_read(mapping->host) == prev_page_end_size) && (pos != 0)) - zero_user(page, 0, PAGE_SIZE); + folio_zero_range(folio, 0, PAGE_SIZE); out: if (unlikely(rc)) { - unlock_page(page); - put_page(page); - *pagep = NULL; + folio_unlock(folio); + folio_put(folio); } return rc; } @@ -457,13 +457,13 @@ int ecryptfs_write_inode_size_to_metadata(struct inode *ecryptfs_inode) * @pos: The file position * @len: The length of the data (unused) * @copied: The amount of data copied - * @page: The eCryptfs page + * @folio: The eCryptfs folio * @fsdata: The fsdata (unused) */ static int ecryptfs_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { pgoff_t index = pos >> PAGE_SHIFT; unsigned from = pos & (PAGE_SIZE - 1); @@ -476,8 +476,8 @@ static int ecryptfs_write_end(struct file *file, ecryptfs_printk(KERN_DEBUG, "Calling fill_zeros_to_end_of_page" "(page w/ index = [0x%.16lx], to = [%d])\n", index, to); if (!(crypt_stat->flags & ECRYPTFS_ENCRYPTED)) { - rc = ecryptfs_write_lower_page_segment(ecryptfs_inode, page, 0, - to); + rc = ecryptfs_write_lower_page_segment(ecryptfs_inode, + &folio->page, 0, to); if (!rc) { rc = copied; fsstack_copy_inode_size(ecryptfs_inode, @@ -485,21 +485,21 @@ static int ecryptfs_write_end(struct file *file, } goto out; } - if (!PageUptodate(page)) { + if (!folio_test_uptodate(folio)) { if (copied < PAGE_SIZE) { rc = 0; goto out; } - SetPageUptodate(page); + folio_mark_uptodate(folio); } /* Fills in zeros if 'to' goes beyond inode size */ - rc = fill_zeros_to_end_of_page(page, to); + rc = fill_zeros_to_end_of_page(folio, to); if (rc) { ecryptfs_printk(KERN_WARNING, "Error attempting to fill " "zeros in page with index = [0x%.16lx]\n", index); goto out; } - rc = ecryptfs_encrypt_page(page); + rc = ecryptfs_encrypt_page(&folio->page); if (rc) { ecryptfs_printk(KERN_WARNING, "Error encrypting page (upper " "index [0x%.16lx])\n", index); @@ -518,8 +518,8 @@ static int ecryptfs_write_end(struct file *file, else rc = copied; out: - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); return rc; } diff --git a/fs/eventpoll.c b/fs/eventpoll.c index f53ca4f7fced..145f5349c612 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -420,7 +420,7 @@ static bool busy_loop_ep_timeout(unsigned long start_time, static bool ep_busy_loop_on(struct eventpoll *ep) { - return !!ep->busy_poll_usecs || net_busy_loop_on(); + return !!READ_ONCE(ep->busy_poll_usecs) || net_busy_loop_on(); } static bool ep_busy_loop_end(void *p, unsigned long start_time) @@ -2200,11 +2200,6 @@ static int do_epoll_create(int flags) error = PTR_ERR(file); goto out_free_fd; } -#ifdef CONFIG_NET_RX_BUSY_POLL - ep->busy_poll_usecs = 0; - ep->busy_poll_budget = 0; - ep->prefer_busy_poll = false; -#endif ep->file = file; fd_install(fd, file); return fd; diff --git a/fs/exec.c b/fs/exec.c index 50e76cc633c4..caae051c5a95 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -145,13 +145,11 @@ SYSCALL_DEFINE1(uselib, const char __user *, library) 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. + * Check do_open_execat() for an explanation. */ error = -EACCES; - if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode) || - path_noexec(&file->f_path))) + if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode)) || + path_noexec(&file->f_path)) goto exit; error = -ENOEXEC; @@ -954,7 +952,6 @@ EXPORT_SYMBOL(transfer_args_to_stack); static struct file *do_open_execat(int fd, struct filename *name, int flags) { struct file *file; - int err; struct open_flags open_exec_flags = { .open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC, .acc_mode = MAY_EXEC, @@ -971,24 +968,20 @@ static struct file *do_open_execat(int fd, struct filename *name, int flags) file = do_filp_open(fd, name, &open_exec_flags); if (IS_ERR(file)) - goto out; + return file; /* - * 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. + * In the past the regular type check was here. It moved to may_open() in + * 633fb6ac3980 ("exec: move S_ISREG() check earlier"). Since then it is + * an invariant that all non-regular files error out before we get here. */ - err = -EACCES; - if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode) || - path_noexec(&file->f_path))) - goto exit; + if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode)) || + path_noexec(&file->f_path)) { + fput(file); + return ERR_PTR(-EACCES); + } -out: return file; - -exit: - fput(file); - return ERR_PTR(err); } /** diff --git a/fs/exfat/file.c b/fs/exfat/file.c index 64c31867bc76..e19469e88000 100644 --- a/fs/exfat/file.c +++ b/fs/exfat/file.c @@ -535,20 +535,20 @@ static int exfat_file_zeroed_range(struct file *file, loff_t start, loff_t end) while (start < end) { u32 zerofrom, len; - struct page *page = NULL; + struct folio *folio; zerofrom = start & (PAGE_SIZE - 1); len = PAGE_SIZE - zerofrom; if (start + len > end) len = end - start; - err = ops->write_begin(file, mapping, start, len, &page, NULL); + err = ops->write_begin(file, mapping, start, len, &folio, NULL); if (err) goto out; - zero_user_segment(page, zerofrom, zerofrom + len); + folio_zero_range(folio, offset_in_folio(folio, start), len); - err = ops->write_end(file, mapping, start, len, len, page, NULL); + err = ops->write_end(file, mapping, start, len, len, folio, NULL); if (err < 0) goto out; start += len; diff --git a/fs/exfat/inode.c b/fs/exfat/inode.c index dd894e558c91..05f0e07b01d0 100644 --- a/fs/exfat/inode.c +++ b/fs/exfat/inode.c @@ -448,12 +448,11 @@ static void exfat_write_failed(struct address_space *mapping, loff_t to) static int exfat_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned int len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { int ret; - *pagep = NULL; - ret = block_write_begin(mapping, pos, len, pagep, exfat_get_block); + ret = block_write_begin(mapping, pos, len, foliop, exfat_get_block); if (ret < 0) exfat_write_failed(mapping, pos+len); @@ -463,13 +462,13 @@ static int exfat_write_begin(struct file *file, struct address_space *mapping, static int exfat_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned int len, unsigned int copied, - struct page *pagep, void *fsdata) + struct folio *folio, void *fsdata) { struct inode *inode = mapping->host; struct exfat_inode_info *ei = EXFAT_I(inode); int err; - err = generic_write_end(file, mapping, pos, len, copied, pagep, fsdata); + err = generic_write_end(file, mapping, pos, len, copied, folio, fsdata); if (ei->i_size_aligned < i_size_read(inode)) { exfat_fs_error(inode->i_sb, diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c index 087457061c6e..402fecf90a44 100644 --- a/fs/ext2/dir.c +++ b/fs/ext2/dir.c @@ -87,7 +87,7 @@ static void ext2_commit_chunk(struct folio *folio, loff_t pos, unsigned len) struct inode *dir = mapping->host; inode_inc_iversion(dir); - block_write_end(NULL, mapping, pos, len, len, &folio->page, NULL); + block_write_end(NULL, mapping, pos, len, len, folio, NULL); if (pos+len > dir->i_size) { i_size_write(dir, pos+len); @@ -263,7 +263,7 @@ ext2_readdir(struct file *file, struct dir_context *ctx) unsigned long n = pos >> PAGE_SHIFT; unsigned long npages = dir_pages(inode); unsigned chunk_mask = ~(ext2_chunk_size(inode)-1); - bool need_revalidate = !inode_eq_iversion(inode, file->f_version); + bool need_revalidate = !inode_eq_iversion(inode, *(u64 *)file->private_data); bool has_filetype; if (pos > inode->i_size - EXT2_DIR_REC_LEN(1)) @@ -290,7 +290,7 @@ ext2_readdir(struct file *file, struct dir_context *ctx) offset = ext2_validate_entry(kaddr, offset, chunk_mask); ctx->pos = (n<<PAGE_SHIFT) + offset; } - file->f_version = inode_query_iversion(inode); + *(u64 *)file->private_data = inode_query_iversion(inode); need_revalidate = false; } de = (ext2_dirent *)(kaddr+offset); @@ -434,7 +434,7 @@ int ext2_inode_by_name(struct inode *dir, const struct qstr *child, ino_t *ino) static int ext2_prepare_chunk(struct folio *folio, loff_t pos, unsigned len) { - return __block_write_begin(&folio->page, pos, len, ext2_get_block); + return __block_write_begin(folio, pos, len, ext2_get_block); } static int ext2_handle_dirsync(struct inode *dir) @@ -703,8 +703,30 @@ not_empty: return 0; } +static int ext2_dir_open(struct inode *inode, struct file *file) +{ + file->private_data = kzalloc(sizeof(u64), GFP_KERNEL); + if (!file->private_data) + return -ENOMEM; + return 0; +} + +static int ext2_dir_release(struct inode *inode, struct file *file) +{ + kfree(file->private_data); + return 0; +} + +static loff_t ext2_dir_llseek(struct file *file, loff_t offset, int whence) +{ + return generic_llseek_cookie(file, offset, whence, + (u64 *)file->private_data); +} + const struct file_operations ext2_dir_operations = { - .llseek = generic_file_llseek, + .open = ext2_dir_open, + .release = ext2_dir_release, + .llseek = ext2_dir_llseek, .read = generic_read_dir, .iterate_shared = ext2_readdir, .unlocked_ioctl = ext2_ioctl, diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 0caa1650cee8..30f8201c155f 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -916,11 +916,11 @@ static void ext2_readahead(struct readahead_control *rac) static int ext2_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, struct page **pagep, void **fsdata) + loff_t pos, unsigned len, struct folio **foliop, void **fsdata) { int ret; - ret = block_write_begin(mapping, pos, len, pagep, ext2_get_block); + ret = block_write_begin(mapping, pos, len, foliop, ext2_get_block); if (ret < 0) ext2_write_failed(mapping, pos + len); return ret; @@ -928,11 +928,11 @@ ext2_write_begin(struct file *file, struct address_space *mapping, static int ext2_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { int ret; - ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata); + ret = generic_write_end(file, mapping, pos, len, copied, folio, fsdata); if (ret < len) ext2_write_failed(mapping, pos + len); return ret; diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index ff4514e4626b..13196afe55ce 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -133,6 +133,7 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) struct super_block *sb = inode->i_sb; struct buffer_head *bh = NULL; struct fscrypt_str fstr = FSTR_INIT(NULL, 0); + struct dir_private_info *info = file->private_data; err = fscrypt_prepare_readdir(inode); if (err) @@ -229,7 +230,7 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) * readdir(2), then we might be pointing to an invalid * dirent right now. Scan from the start of the block * to make sure. */ - if (!inode_eq_iversion(inode, file->f_version)) { + if (!inode_eq_iversion(inode, info->cookie)) { for (i = 0; i < sb->s_blocksize && i < offset; ) { de = (struct ext4_dir_entry_2 *) (bh->b_data + i); @@ -249,7 +250,7 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) offset = i; ctx->pos = (ctx->pos & ~(sb->s_blocksize - 1)) | offset; - file->f_version = inode_query_iversion(inode); + info->cookie = inode_query_iversion(inode); } while (ctx->pos < inode->i_size @@ -384,6 +385,7 @@ static inline loff_t ext4_get_htree_eof(struct file *filp) static loff_t ext4_dir_llseek(struct file *file, loff_t offset, int whence) { struct inode *inode = file->f_mapping->host; + struct dir_private_info *info = file->private_data; int dx_dir = is_dx_dir(inode); loff_t ret, htree_max = ext4_get_htree_eof(file); @@ -392,7 +394,7 @@ static loff_t ext4_dir_llseek(struct file *file, loff_t offset, int whence) htree_max, htree_max); else ret = ext4_llseek(file, offset, whence); - file->f_version = inode_peek_iversion(inode) - 1; + info->cookie = inode_peek_iversion(inode) - 1; return ret; } @@ -429,18 +431,15 @@ static void free_rb_tree_fname(struct rb_root *root) *root = RB_ROOT; } - -static struct dir_private_info *ext4_htree_create_dir_info(struct file *filp, - loff_t pos) +static void ext4_htree_init_dir_info(struct file *filp, loff_t pos) { - struct dir_private_info *p; - - p = kzalloc(sizeof(*p), GFP_KERNEL); - if (!p) - return NULL; - p->curr_hash = pos2maj_hash(filp, pos); - p->curr_minor_hash = pos2min_hash(filp, pos); - return p; + struct dir_private_info *p = filp->private_data; + + if (is_dx_dir(file_inode(filp)) && !p->initialized) { + p->curr_hash = pos2maj_hash(filp, pos); + p->curr_minor_hash = pos2min_hash(filp, pos); + p->initialized = true; + } } void ext4_htree_free_dir_info(struct dir_private_info *p) @@ -552,12 +551,7 @@ static int ext4_dx_readdir(struct file *file, struct dir_context *ctx) struct fname *fname; int ret = 0; - if (!info) { - info = ext4_htree_create_dir_info(file, ctx->pos); - if (!info) - return -ENOMEM; - file->private_data = info; - } + ext4_htree_init_dir_info(file, ctx->pos); if (ctx->pos == ext4_get_htree_eof(file)) return 0; /* EOF */ @@ -590,10 +584,10 @@ static int ext4_dx_readdir(struct file *file, struct dir_context *ctx) * cached entries. */ if ((!info->curr_node) || - !inode_eq_iversion(inode, file->f_version)) { + !inode_eq_iversion(inode, info->cookie)) { info->curr_node = NULL; free_rb_tree_fname(&info->root); - file->f_version = inode_query_iversion(inode); + info->cookie = inode_query_iversion(inode); ret = ext4_htree_fill_tree(file, info->curr_hash, info->curr_minor_hash, &info->next_hash); @@ -664,7 +658,19 @@ int ext4_check_all_de(struct inode *dir, struct buffer_head *bh, void *buf, return 0; } +static int ext4_dir_open(struct inode *inode, struct file *file) +{ + struct dir_private_info *info; + + info = kzalloc(sizeof(*info), GFP_KERNEL); + if (!info) + return -ENOMEM; + file->private_data = info; + return 0; +} + const struct file_operations ext4_dir_operations = { + .open = ext4_dir_open, .llseek = ext4_dir_llseek, .read = generic_read_dir, .iterate_shared = ext4_readdir, diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 08acd152261e..ecc15e5f1eba 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2553,6 +2553,8 @@ struct dir_private_info { __u32 curr_hash; __u32 curr_minor_hash; __u32 next_hash; + u64 cookie; + bool initialized; }; /* calculate the first block number of the group */ @@ -3563,13 +3565,13 @@ int ext4_readpage_inline(struct inode *inode, struct folio *folio); extern int ext4_try_to_write_inline_data(struct address_space *mapping, struct inode *inode, loff_t pos, unsigned len, - struct page **pagep); + struct folio **foliop); int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len, unsigned copied, struct folio *folio); extern int ext4_da_write_inline_data_begin(struct address_space *mapping, struct inode *inode, loff_t pos, unsigned len, - struct page **pagep, + struct folio **foliop, void **fsdata); extern int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname, diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index e7a09a99837b..edf4aa99a974 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -601,10 +601,10 @@ retry: goto out; if (ext4_should_dioread_nolock(inode)) { - ret = __block_write_begin(&folio->page, from, to, + ret = __block_write_begin(folio, from, to, ext4_get_block_unwritten); } else - ret = __block_write_begin(&folio->page, from, to, ext4_get_block); + ret = __block_write_begin(folio, from, to, ext4_get_block); if (!ret && ext4_should_journal_data(inode)) { ret = ext4_walk_page_buffers(handle, inode, @@ -660,7 +660,7 @@ out_nofolio: int ext4_try_to_write_inline_data(struct address_space *mapping, struct inode *inode, loff_t pos, unsigned len, - struct page **pagep) + struct folio **foliop) { int ret; handle_t *handle; @@ -708,7 +708,7 @@ int ext4_try_to_write_inline_data(struct address_space *mapping, goto out; } - *pagep = &folio->page; + *foliop = folio; down_read(&EXT4_I(inode)->xattr_sem); if (!ext4_has_inline_data(inode)) { ret = 0; @@ -856,7 +856,7 @@ static int ext4_da_convert_inline_data_to_extent(struct address_space *mapping, goto out; } - ret = __block_write_begin(&folio->page, 0, inline_size, + ret = __block_write_begin(folio, 0, inline_size, ext4_da_get_block_prep); if (ret) { up_read(&EXT4_I(inode)->xattr_sem); @@ -891,7 +891,7 @@ out: int ext4_da_write_inline_data_begin(struct address_space *mapping, struct inode *inode, loff_t pos, unsigned len, - struct page **pagep, + struct folio **foliop, void **fsdata) { int ret; @@ -954,7 +954,7 @@ retry_journal: goto out_release_page; up_read(&EXT4_I(inode)->xattr_sem); - *pagep = &folio->page; + *foliop = folio; brelse(iloc.bh); return 1; out_release_page: @@ -1460,6 +1460,7 @@ int ext4_read_inline_dir(struct file *file, struct ext4_iloc iloc; void *dir_buf = NULL; int dotdot_offset, dotdot_size, extra_offset, extra_size; + struct dir_private_info *info = file->private_data; ret = ext4_get_inode_loc(inode, &iloc); if (ret) @@ -1503,12 +1504,12 @@ int ext4_read_inline_dir(struct file *file, extra_size = extra_offset + inline_size; /* - * If the version has changed since the last call to + * If the cookie has changed since the last call to * readdir(2), then we might be pointing to an invalid * dirent right now. Scan from the start of the inline * dir to make sure. */ - if (!inode_eq_iversion(inode, file->f_version)) { + if (!inode_eq_iversion(inode, info->cookie)) { for (i = 0; i < extra_size && i < offset;) { /* * "." is with offset 0 and @@ -1540,7 +1541,7 @@ int ext4_read_inline_dir(struct file *file, } offset = i; ctx->pos = offset; - file->f_version = inode_query_iversion(inode); + info->cookie = inode_query_iversion(inode); } while (ctx->pos < extra_size) { diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 941c1c0d5c6e..03374dc215d1 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1145,7 +1145,7 @@ static int ext4_block_write_begin(struct folio *folio, loff_t pos, unsigned len, */ static int ext4_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { struct inode *inode = mapping->host; int ret, needed_blocks; @@ -1170,7 +1170,7 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping, if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { ret = ext4_try_to_write_inline_data(mapping, inode, pos, len, - pagep); + foliop); if (ret < 0) return ret; if (ret == 1) @@ -1224,10 +1224,10 @@ retry_journal: ret = ext4_block_write_begin(folio, pos, len, ext4_get_block); #else if (ext4_should_dioread_nolock(inode)) - ret = __block_write_begin(&folio->page, pos, len, + ret = __block_write_begin(folio, pos, len, ext4_get_block_unwritten); else - ret = __block_write_begin(&folio->page, pos, len, ext4_get_block); + ret = __block_write_begin(folio, pos, len, ext4_get_block); #endif if (!ret && ext4_should_journal_data(inode)) { ret = ext4_walk_page_buffers(handle, inode, @@ -1270,7 +1270,7 @@ retry_journal: folio_put(folio); return ret; } - *pagep = &folio->page; + *foliop = folio; return ret; } @@ -1298,9 +1298,8 @@ static int write_end_fn(handle_t *handle, struct inode *inode, static int ext4_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { - struct folio *folio = page_folio(page); handle_t *handle = ext4_journal_current_handle(); struct inode *inode = mapping->host; loff_t old_size = inode->i_size; @@ -1315,7 +1314,7 @@ static int ext4_write_end(struct file *file, return ext4_write_inline_data_end(inode, pos, len, copied, folio); - copied = block_write_end(file, mapping, pos, len, copied, page, fsdata); + copied = block_write_end(file, mapping, pos, len, copied, folio, fsdata); /* * it's important to update i_size while still holding folio lock: * page writeout could otherwise come in and zero beyond i_size. @@ -1402,9 +1401,8 @@ static void ext4_journalled_zero_new_buffers(handle_t *handle, static int ext4_journalled_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { - struct folio *folio = page_folio(page); handle_t *handle = ext4_journal_current_handle(); struct inode *inode = mapping->host; loff_t old_size = inode->i_size; @@ -2926,7 +2924,7 @@ static int ext4_nonda_switch(struct super_block *sb) static int ext4_da_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { int ret, retries = 0; struct folio *folio; @@ -2941,14 +2939,14 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping, if (ext4_nonda_switch(inode->i_sb) || ext4_verity_in_progress(inode)) { *fsdata = (void *)FALL_BACK_TO_NONDELALLOC; return ext4_write_begin(file, mapping, pos, - len, pagep, fsdata); + len, foliop, fsdata); } *fsdata = (void *)0; trace_ext4_da_write_begin(inode, pos, len); if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { ret = ext4_da_write_inline_data_begin(mapping, inode, pos, len, - pagep, fsdata); + foliop, fsdata); if (ret < 0) return ret; if (ret == 1) @@ -2964,7 +2962,7 @@ retry: #ifdef CONFIG_FS_ENCRYPTION ret = ext4_block_write_begin(folio, pos, len, ext4_da_get_block_prep); #else - ret = __block_write_begin(&folio->page, pos, len, ext4_da_get_block_prep); + ret = __block_write_begin(folio, pos, len, ext4_da_get_block_prep); #endif if (ret < 0) { folio_unlock(folio); @@ -2983,7 +2981,7 @@ retry: return ret; } - *pagep = &folio->page; + *foliop = folio; return ret; } @@ -3029,7 +3027,7 @@ static int ext4_da_do_write_end(struct address_space *mapping, * flag, which all that's needed to trigger page writeback. */ copied = block_write_end(NULL, mapping, pos, len, copied, - &folio->page, NULL); + folio, NULL); new_i_size = pos + copied; /* @@ -3080,15 +3078,14 @@ static int ext4_da_do_write_end(struct address_space *mapping, static int ext4_da_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { struct inode *inode = mapping->host; int write_mode = (int)(unsigned long)fsdata; - struct folio *folio = page_folio(page); if (write_mode == FALL_BACK_TO_NONDELALLOC) return ext4_write_end(file, mapping, pos, - len, copied, &folio->page, fsdata); + len, copied, folio, fsdata); trace_ext4_da_write_end(inode, pos, len, copied); @@ -6219,7 +6216,7 @@ retry_alloc: if (folio_pos(folio) + len > size) len = size - folio_pos(folio); - err = __block_write_begin(&folio->page, 0, len, ext4_get_block); + err = __block_write_begin(folio, 0, len, ext4_get_block); if (!err) { ret = VM_FAULT_SIGBUS; if (ext4_journal_folio_buffers(handle, folio, len)) diff --git a/fs/ext4/verity.c b/fs/ext4/verity.c index 2f37e1ea3955..d9203228ce97 100644 --- a/fs/ext4/verity.c +++ b/fs/ext4/verity.c @@ -76,17 +76,17 @@ static int pagecache_write(struct inode *inode, const void *buf, size_t count, while (count) { size_t n = min_t(size_t, count, PAGE_SIZE - offset_in_page(pos)); - struct page *page; + struct folio *folio; void *fsdata = NULL; int res; - res = aops->write_begin(NULL, mapping, pos, n, &page, &fsdata); + res = aops->write_begin(NULL, mapping, pos, n, &folio, &fsdata); if (res) return res; - memcpy_to_page(page, offset_in_page(pos), buf, n); + memcpy_to_folio(folio, offset_in_folio(folio, pos), buf, n); - res = aops->write_end(NULL, mapping, pos, n, n, page, fsdata); + res = aops->write_end(NULL, mapping, pos, n, n, folio, fsdata); if (res < 0) return res; if (res != n) diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 6457e5bca9c9..5dfa0207ad8f 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -3552,12 +3552,12 @@ reserve_block: } static int f2fs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, struct page **pagep, void **fsdata) + loff_t pos, unsigned len, struct folio **foliop, void **fsdata) { struct inode *inode = mapping->host; struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct page *page = NULL; - pgoff_t index = ((unsigned long long) pos) >> PAGE_SHIFT; + struct folio *folio; + pgoff_t index = pos >> PAGE_SHIFT; bool need_balance = false; bool use_cow = false; block_t blkaddr = NULL_ADDR; @@ -3573,7 +3573,7 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping, /* * We should check this at this moment to avoid deadlock on inode page * and #0 page. The locking rule for inline_data conversion should be: - * lock_page(page #0) -> lock_page(inode_page) + * folio_lock(folio #0) -> folio_lock(inode_page) */ if (index != 0) { err = f2fs_convert_inline_inode(inode); @@ -3584,18 +3584,20 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping, #ifdef CONFIG_F2FS_FS_COMPRESSION if (f2fs_compressed_file(inode)) { int ret; + struct page *page; *fsdata = NULL; if (len == PAGE_SIZE && !(f2fs_is_atomic_file(inode))) goto repeat; - ret = f2fs_prepare_compress_overwrite(inode, pagep, + ret = f2fs_prepare_compress_overwrite(inode, &page, index, fsdata); if (ret < 0) { err = ret; goto fail; } else if (ret) { + *foliop = page_folio(page); return 0; } } @@ -3603,81 +3605,85 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping, repeat: /* - * Do not use grab_cache_page_write_begin() to avoid deadlock due to - * wait_for_stable_page. Will wait that below with our IO control. + * Do not use FGP_STABLE to avoid deadlock. + * Will wait that below with our IO control. */ - page = f2fs_pagecache_get_page(mapping, index, + folio = __filemap_get_folio(mapping, index, FGP_LOCK | FGP_WRITE | FGP_CREAT, GFP_NOFS); - if (!page) { - err = -ENOMEM; + if (IS_ERR(folio)) { + err = PTR_ERR(folio); goto fail; } /* TODO: cluster can be compressed due to race with .writepage */ - *pagep = page; + *foliop = folio; if (f2fs_is_atomic_file(inode)) - err = prepare_atomic_write_begin(sbi, page, pos, len, + err = prepare_atomic_write_begin(sbi, &folio->page, pos, len, &blkaddr, &need_balance, &use_cow); else - err = prepare_write_begin(sbi, page, pos, len, + err = prepare_write_begin(sbi, &folio->page, pos, len, &blkaddr, &need_balance); if (err) - goto fail; + goto put_folio; if (need_balance && !IS_NOQUOTA(inode) && has_not_enough_free_secs(sbi, 0, 0)) { - unlock_page(page); + folio_unlock(folio); f2fs_balance_fs(sbi, true); - lock_page(page); - if (page->mapping != mapping) { - /* The page got truncated from under us */ - f2fs_put_page(page, 1); + folio_lock(folio); + if (folio->mapping != mapping) { + /* The folio got truncated from under us */ + folio_unlock(folio); + folio_put(folio); goto repeat; } } - f2fs_wait_on_page_writeback(page, DATA, false, true); + f2fs_wait_on_page_writeback(&folio->page, DATA, false, true); - if (len == PAGE_SIZE || PageUptodate(page)) + if (len == folio_size(folio) || folio_test_uptodate(folio)) return 0; if (!(pos & (PAGE_SIZE - 1)) && (pos + len) >= i_size_read(inode) && !f2fs_verity_in_progress(inode)) { - zero_user_segment(page, len, PAGE_SIZE); + folio_zero_segment(folio, len, PAGE_SIZE); return 0; } if (blkaddr == NEW_ADDR) { - zero_user_segment(page, 0, PAGE_SIZE); - SetPageUptodate(page); + folio_zero_segment(folio, 0, folio_size(folio)); + folio_mark_uptodate(folio); } else { if (!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE_READ)) { err = -EFSCORRUPTED; - goto fail; + goto put_folio; } err = f2fs_submit_page_read(use_cow ? - F2FS_I(inode)->cow_inode : inode, page, + F2FS_I(inode)->cow_inode : inode, &folio->page, blkaddr, 0, true); if (err) - goto fail; + goto put_folio; - lock_page(page); - if (unlikely(page->mapping != mapping)) { - f2fs_put_page(page, 1); + folio_lock(folio); + if (unlikely(folio->mapping != mapping)) { + folio_unlock(folio); + folio_put(folio); goto repeat; } - if (unlikely(!PageUptodate(page))) { + if (unlikely(!folio_test_uptodate(folio))) { err = -EIO; - goto fail; + goto put_folio; } } return 0; +put_folio: + folio_unlock(folio); + folio_put(folio); fail: - f2fs_put_page(page, 1); f2fs_write_failed(inode, pos + len); return err; } @@ -3685,9 +3691,9 @@ fail: static int f2fs_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { - struct inode *inode = page->mapping->host; + struct inode *inode = folio->mapping->host; trace_f2fs_write_end(inode, pos, len, copied); @@ -3696,17 +3702,17 @@ static int f2fs_write_end(struct file *file, * should be PAGE_SIZE. Otherwise, we treat it with zero copied and * let generic_perform_write() try to copy data again through copied=0. */ - if (!PageUptodate(page)) { + if (!folio_test_uptodate(folio)) { if (unlikely(copied != len)) copied = 0; else - SetPageUptodate(page); + folio_mark_uptodate(folio); } #ifdef CONFIG_F2FS_FS_COMPRESSION /* overwrite compressed file */ if (f2fs_compressed_file(inode) && fsdata) { - f2fs_compress_write_end(inode, fsdata, page->index, copied); + f2fs_compress_write_end(inode, fsdata, folio->index, copied); f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); if (pos + copied > i_size_read(inode) && @@ -3719,7 +3725,7 @@ static int f2fs_write_end(struct file *file, if (!copied) goto unlock_out; - set_page_dirty(page); + folio_mark_dirty(folio); if (pos + copied > i_size_read(inode) && !f2fs_verity_in_progress(inode)) { @@ -3729,7 +3735,8 @@ static int f2fs_write_end(struct file *file, pos + copied); } unlock_out: - f2fs_put_page(page, 1); + folio_unlock(folio); + folio_put(folio); f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); return copied; } diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 3959fd137cc9..176b5177c89d 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -2677,7 +2677,7 @@ static ssize_t f2fs_quota_write(struct super_block *sb, int type, const struct address_space_operations *a_ops = mapping->a_ops; int offset = off & (sb->s_blocksize - 1); size_t towrite = len; - struct page *page; + struct folio *folio; void *fsdata = NULL; int err = 0; int tocopy; @@ -2687,7 +2687,7 @@ static ssize_t f2fs_quota_write(struct super_block *sb, int type, towrite); retry: err = a_ops->write_begin(NULL, mapping, off, tocopy, - &page, &fsdata); + &folio, &fsdata); if (unlikely(err)) { if (err == -ENOMEM) { f2fs_io_schedule_timeout(DEFAULT_IO_TIMEOUT); @@ -2697,10 +2697,10 @@ retry: break; } - memcpy_to_page(page, offset, data, tocopy); + memcpy_to_folio(folio, offset_in_folio(folio, off), data, tocopy); a_ops->write_end(NULL, mapping, off, tocopy, tocopy, - page, fsdata); + folio, fsdata); offset = 0; towrite -= tocopy; off += tocopy; diff --git a/fs/f2fs/verity.c b/fs/f2fs/verity.c index f7bb0c54502c..84a33fe49bed 100644 --- a/fs/f2fs/verity.c +++ b/fs/f2fs/verity.c @@ -80,17 +80,17 @@ static int pagecache_write(struct inode *inode, const void *buf, size_t count, while (count) { size_t n = min_t(size_t, count, PAGE_SIZE - offset_in_page(pos)); - struct page *page; + struct folio *folio; void *fsdata = NULL; int res; - res = aops->write_begin(NULL, mapping, pos, n, &page, &fsdata); + res = aops->write_begin(NULL, mapping, pos, n, &folio, &fsdata); if (res) return res; - memcpy_to_page(page, offset_in_page(pos), buf, n); + memcpy_to_folio(folio, offset_in_folio(folio, pos), buf, n); - res = aops->write_end(NULL, mapping, pos, n, n, page, fsdata); + res = aops->write_end(NULL, mapping, pos, n, n, folio, fsdata); if (res < 0) return res; if (res != n) diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 19115fd2d2a4..75722bbd6b5f 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -221,13 +221,12 @@ static void fat_write_failed(struct address_space *mapping, loff_t to) static int fat_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { int err; - *pagep = NULL; err = cont_write_begin(file, mapping, pos, len, - pagep, fsdata, fat_get_block, + foliop, fsdata, fat_get_block, &MSDOS_I(mapping->host)->mmu_private); if (err < 0) fat_write_failed(mapping, pos + len); @@ -236,11 +235,11 @@ static int fat_write_begin(struct file *file, struct address_space *mapping, static int fat_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *pagep, void *fsdata) + struct folio *folio, void *fsdata) { struct inode *inode = mapping->host; int err; - err = generic_write_end(file, mapping, pos, len, copied, pagep, fsdata); + err = generic_write_end(file, mapping, pos, len, copied, folio, fsdata); if (err < len) fat_write_failed(mapping, pos + len); if (!(err < 0) && !(MSDOS_I(inode)->i_attrs & ATTR_ARCH)) { diff --git a/fs/fcntl.c b/fs/fcntl.c index 300e5d9ad913..f6fde75a3bd5 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -33,6 +33,8 @@ #include <asm/siginfo.h> #include <linux/uaccess.h> +#include "internal.h" + #define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME) static int setfl(int fd, struct file * filp, unsigned int arg) @@ -87,22 +89,64 @@ static int setfl(int fd, struct file * filp, unsigned int arg) return error; } +/* + * Allocate an file->f_owner struct if it doesn't exist, handling racing + * allocations correctly. + */ +int file_f_owner_allocate(struct file *file) +{ + struct fown_struct *f_owner; + + f_owner = file_f_owner(file); + if (f_owner) + return 0; + + f_owner = kzalloc(sizeof(struct fown_struct), GFP_KERNEL); + if (!f_owner) + return -ENOMEM; + + rwlock_init(&f_owner->lock); + f_owner->file = file; + /* If someone else raced us, drop our allocation. */ + if (unlikely(cmpxchg(&file->f_owner, NULL, f_owner))) + kfree(f_owner); + return 0; +} +EXPORT_SYMBOL(file_f_owner_allocate); + +void file_f_owner_release(struct file *file) +{ + struct fown_struct *f_owner; + + f_owner = file_f_owner(file); + if (f_owner) { + put_pid(f_owner->pid); + kfree(f_owner); + } +} + static void f_modown(struct file *filp, struct pid *pid, enum pid_type type, int force) { - write_lock_irq(&filp->f_owner.lock); - if (force || !filp->f_owner.pid) { - put_pid(filp->f_owner.pid); - filp->f_owner.pid = get_pid(pid); - filp->f_owner.pid_type = type; + struct fown_struct *f_owner; + + f_owner = file_f_owner(filp); + if (WARN_ON_ONCE(!f_owner)) + return; + + write_lock_irq(&f_owner->lock); + if (force || !f_owner->pid) { + put_pid(f_owner->pid); + f_owner->pid = get_pid(pid); + f_owner->pid_type = type; if (pid) { const struct cred *cred = current_cred(); - filp->f_owner.uid = cred->uid; - filp->f_owner.euid = cred->euid; + f_owner->uid = cred->uid; + f_owner->euid = cred->euid; } } - write_unlock_irq(&filp->f_owner.lock); + write_unlock_irq(&f_owner->lock); } void __f_setown(struct file *filp, struct pid *pid, enum pid_type type, @@ -119,6 +163,8 @@ int f_setown(struct file *filp, int who, int force) struct pid *pid = NULL; int ret = 0; + might_sleep(); + type = PIDTYPE_TGID; if (who < 0) { /* avoid overflow below */ @@ -129,6 +175,10 @@ int f_setown(struct file *filp, int who, int force) who = -who; } + ret = file_f_owner_allocate(filp); + if (ret) + return ret; + rcu_read_lock(); if (who) { pid = find_vpid(who); @@ -152,16 +202,21 @@ void f_delown(struct file *filp) pid_t f_getown(struct file *filp) { pid_t pid = 0; + struct fown_struct *f_owner; + + f_owner = file_f_owner(filp); + if (!f_owner) + return pid; - read_lock_irq(&filp->f_owner.lock); + read_lock_irq(&f_owner->lock); rcu_read_lock(); - if (pid_task(filp->f_owner.pid, filp->f_owner.pid_type)) { - pid = pid_vnr(filp->f_owner.pid); - if (filp->f_owner.pid_type == PIDTYPE_PGID) + if (pid_task(f_owner->pid, f_owner->pid_type)) { + pid = pid_vnr(f_owner->pid); + if (f_owner->pid_type == PIDTYPE_PGID) pid = -pid; } rcu_read_unlock(); - read_unlock_irq(&filp->f_owner.lock); + read_unlock_irq(&f_owner->lock); return pid; } @@ -194,6 +249,10 @@ static int f_setown_ex(struct file *filp, unsigned long arg) return -EINVAL; } + ret = file_f_owner_allocate(filp); + if (ret) + return ret; + rcu_read_lock(); pid = find_vpid(owner.pid); if (owner.pid && !pid) @@ -210,13 +269,20 @@ static int f_getown_ex(struct file *filp, unsigned long arg) struct f_owner_ex __user *owner_p = (void __user *)arg; struct f_owner_ex owner = {}; int ret = 0; + struct fown_struct *f_owner; + enum pid_type pid_type = PIDTYPE_PID; - read_lock_irq(&filp->f_owner.lock); - rcu_read_lock(); - if (pid_task(filp->f_owner.pid, filp->f_owner.pid_type)) - owner.pid = pid_vnr(filp->f_owner.pid); - rcu_read_unlock(); - switch (filp->f_owner.pid_type) { + f_owner = file_f_owner(filp); + if (f_owner) { + read_lock_irq(&f_owner->lock); + rcu_read_lock(); + if (pid_task(f_owner->pid, f_owner->pid_type)) + owner.pid = pid_vnr(f_owner->pid); + rcu_read_unlock(); + pid_type = f_owner->pid_type; + } + + switch (pid_type) { case PIDTYPE_PID: owner.type = F_OWNER_TID; break; @@ -234,7 +300,8 @@ static int f_getown_ex(struct file *filp, unsigned long arg) ret = -EINVAL; break; } - read_unlock_irq(&filp->f_owner.lock); + if (f_owner) + read_unlock_irq(&f_owner->lock); if (!ret) { ret = copy_to_user(owner_p, &owner, sizeof(owner)); @@ -248,14 +315,18 @@ static int f_getown_ex(struct file *filp, unsigned long arg) static int f_getowner_uids(struct file *filp, unsigned long arg) { struct user_namespace *user_ns = current_user_ns(); + struct fown_struct *f_owner; uid_t __user *dst = (void __user *)arg; - uid_t src[2]; + uid_t src[2] = {0, 0}; int err; - read_lock_irq(&filp->f_owner.lock); - src[0] = from_kuid(user_ns, filp->f_owner.uid); - src[1] = from_kuid(user_ns, filp->f_owner.euid); - read_unlock_irq(&filp->f_owner.lock); + f_owner = file_f_owner(filp); + if (f_owner) { + read_lock_irq(&f_owner->lock); + src[0] = from_kuid(user_ns, f_owner->uid); + src[1] = from_kuid(user_ns, f_owner->euid); + read_unlock_irq(&f_owner->lock); + } err = put_user(src[0], &dst[0]); err |= put_user(src[1], &dst[1]); @@ -343,6 +414,36 @@ static long f_dupfd_query(int fd, struct file *filp) return f.file == filp; } +/* Let the caller figure out whether a given file was just created. */ +static long f_created_query(const struct file *filp) +{ + return !!(filp->f_mode & FMODE_CREATED); +} + +static int f_owner_sig(struct file *filp, int signum, bool setsig) +{ + int ret = 0; + struct fown_struct *f_owner; + + might_sleep(); + + if (setsig) { + if (!valid_signal(signum)) + return -EINVAL; + + ret = file_f_owner_allocate(filp); + if (ret) + return ret; + } + + f_owner = file_f_owner(filp); + if (setsig) + f_owner->signum = signum; + else if (f_owner) + ret = f_owner->signum; + return ret; +} + static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, struct file *filp) { @@ -352,6 +453,9 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, long err = -EINVAL; switch (cmd) { + case F_CREATED_QUERY: + err = f_created_query(filp); + break; case F_DUPFD: err = f_dupfd(argi, filp, 0); break; @@ -421,15 +525,10 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, err = f_getowner_uids(filp, arg); break; case F_GETSIG: - err = filp->f_owner.signum; + err = f_owner_sig(filp, 0, false); break; case F_SETSIG: - /* arg == 0 restores default behaviour. */ - if (!valid_signal(argi)) { - break; - } - err = 0; - filp->f_owner.signum = argi; + err = f_owner_sig(filp, argi, true); break; case F_GETLEASE: err = fcntl_getlease(filp); @@ -463,6 +562,7 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, static int check_fcntl_cmd(unsigned cmd) { switch (cmd) { + case F_CREATED_QUERY: case F_DUPFD: case F_DUPFD_CLOEXEC: case F_DUPFD_QUERY: @@ -844,14 +944,19 @@ static void send_sigurg_to_task(struct task_struct *p, do_send_sig_info(SIGURG, SEND_SIG_PRIV, p, type); } -int send_sigurg(struct fown_struct *fown) +int send_sigurg(struct file *file) { + struct fown_struct *fown; struct task_struct *p; enum pid_type type; struct pid *pid; unsigned long flags; int ret = 0; + fown = file_f_owner(file); + if (!fown) + return 0; + read_lock_irqsave(&fown->lock, flags); type = fown->pid_type; @@ -1027,13 +1132,16 @@ static void kill_fasync_rcu(struct fasync_struct *fa, int sig, int band) } read_lock_irqsave(&fa->fa_lock, flags); if (fa->fa_file) { - fown = &fa->fa_file->f_owner; + fown = file_f_owner(fa->fa_file); + if (!fown) + goto next; /* Don't send SIGURG to processes which have not set a queued signum: SIGURG has its own default signalling mechanism. */ if (!(sig == SIGURG && fown->signum == 0)) send_sigio(fown, fa->fa_fd, band); } +next: read_unlock_irqrestore(&fa->fa_lock, flags); fa = rcu_dereference(fa->fa_next); } diff --git a/fs/fhandle.c b/fs/fhandle.c index 6e8cea16790e..8cb665629f4a 100644 --- a/fs/fhandle.c +++ b/fs/fhandle.c @@ -16,7 +16,8 @@ static long do_sys_name_to_handle(const struct path *path, struct file_handle __user *ufh, - int __user *mnt_id, int fh_flags) + void __user *mnt_id, bool unique_mntid, + int fh_flags) { long retval; struct file_handle f_handle; @@ -69,9 +70,19 @@ static long do_sys_name_to_handle(const struct path *path, } else retval = 0; /* copy the mount id */ - if (put_user(real_mount(path->mnt)->mnt_id, mnt_id) || - copy_to_user(ufh, handle, - struct_size(handle, f_handle, handle_bytes))) + if (unique_mntid) { + if (put_user(real_mount(path->mnt)->mnt_id_unique, + (u64 __user *) mnt_id)) + retval = -EFAULT; + } else { + if (put_user(real_mount(path->mnt)->mnt_id, + (int __user *) mnt_id)) + retval = -EFAULT; + } + /* copy the handle */ + if (retval != -EFAULT && + copy_to_user(ufh, handle, + struct_size(handle, f_handle, handle_bytes))) retval = -EFAULT; kfree(handle); return retval; @@ -83,6 +94,7 @@ static long do_sys_name_to_handle(const struct path *path, * @name: name that should be converted to handle. * @handle: resulting file handle * @mnt_id: mount id of the file system containing the file + * (u64 if AT_HANDLE_MNT_ID_UNIQUE, otherwise int) * @flag: flag value to indicate whether to follow symlink or not * and whether a decodable file handle is required. * @@ -92,7 +104,7 @@ static long do_sys_name_to_handle(const struct path *path, * value required. */ SYSCALL_DEFINE5(name_to_handle_at, int, dfd, const char __user *, name, - struct file_handle __user *, handle, int __user *, mnt_id, + struct file_handle __user *, handle, void __user *, mnt_id, int, flag) { struct path path; @@ -100,7 +112,8 @@ SYSCALL_DEFINE5(name_to_handle_at, int, dfd, const char __user *, name, int fh_flags; int err; - if (flag & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH | AT_HANDLE_FID)) + if (flag & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH | AT_HANDLE_FID | + AT_HANDLE_MNT_ID_UNIQUE)) return -EINVAL; lookup_flags = (flag & AT_SYMLINK_FOLLOW) ? LOOKUP_FOLLOW : 0; @@ -109,7 +122,9 @@ SYSCALL_DEFINE5(name_to_handle_at, int, dfd, const char __user *, name, lookup_flags |= LOOKUP_EMPTY; err = user_path_at(dfd, name, lookup_flags, &path); if (!err) { - err = do_sys_name_to_handle(&path, handle, mnt_id, fh_flags); + err = do_sys_name_to_handle(&path, handle, mnt_id, + flag & AT_HANDLE_MNT_ID_UNIQUE, + fh_flags); path_put(&path); } return err; diff --git a/fs/file.c b/fs/file.c index 655338effe9c..976ecd4ce2c6 100644 --- a/fs/file.c +++ b/fs/file.c @@ -672,7 +672,7 @@ int close_fd(unsigned fd) return filp_close(file, files); } -EXPORT_SYMBOL(close_fd); /* for ksys_close() */ +EXPORT_SYMBOL(close_fd); /** * last_fd - return last valid index into fd table diff --git a/fs/file_table.c b/fs/file_table.c index ca7843dde56d..3cac9c34264f 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -136,6 +136,7 @@ static int __init init_fs_stat_sysctls(void) register_sysctl_init("fs", fs_stat_sysctls); if (IS_ENABLED(CONFIG_BINFMT_MISC)) { struct ctl_table_header *hdr; + hdr = register_sysctl_mount_point("fs/binfmt_misc"); kmemleak_not_leak(hdr); } @@ -155,8 +156,14 @@ static int init_file(struct file *f, int flags, const struct cred *cred) return error; } - rwlock_init(&f->f_owner.lock); spin_lock_init(&f->f_lock); + /* + * Note that f_pos_lock is only used for files raising + * FMODE_ATOMIC_POS and directories. Other files such as pipes + * don't need it and since f_pos_lock is in a union may reuse + * the space for other purposes. They are expected to initialize + * the respective member when opening the file. + */ mutex_init(&f->f_pos_lock); f->f_flags = flags; f->f_mode = OPEN_FMODE(flags); @@ -383,7 +390,9 @@ EXPORT_SYMBOL_GPL(alloc_file_pseudo_noaccount); struct file *alloc_file_clone(struct file *base, int flags, const struct file_operations *fops) { - struct file *f = alloc_file(&base->f_path, flags, fops); + struct file *f; + + f = alloc_file(&base->f_path, flags, fops); if (!IS_ERR(f)) { path_get(&f->f_path); f->f_mapping = base->f_mapping; @@ -425,7 +434,7 @@ static void __fput(struct file *file) cdev_put(inode->i_cdev); } fops_put(file->f_op); - put_pid(file->f_owner.pid); + file_f_owner_release(file); put_file_access(file); dput(dentry); if (unlikely(mode & FMODE_NEED_UNMOUNT)) @@ -512,9 +521,9 @@ EXPORT_SYMBOL(__fput_sync); void __init files_init(void) { - filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0, - SLAB_TYPESAFE_BY_RCU | SLAB_HWCACHE_ALIGN | - SLAB_PANIC | SLAB_ACCOUNT, NULL); + filp_cachep = kmem_cache_create_rcu("filp", sizeof(struct file), + offsetof(struct file, f_freeptr), + SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT); percpu_counter_init(&nr_files, 0, GFP_KERNEL); } diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index b865a3fa52f3..d8bec3c1bb1f 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1132,6 +1132,7 @@ out_bdi_put: /** * cgroup_writeback_umount - flush inode wb switches for umount + * @sb: target super_block * * This function is called when a super_block is about to be destroyed and * flushes in-flight inode wb switches. An inode wb switch goes through @@ -1140,8 +1141,12 @@ out_bdi_put: * rare occurrences and synchronize_rcu() can take a while, perform * flushing iff wb switches are in flight. */ -void cgroup_writeback_umount(void) +void cgroup_writeback_umount(struct super_block *sb) { + + if (!(sb->s_bdi->capabilities & BDI_CAP_WRITEBACK)) + return; + /* * SB_ACTIVE should be reliably cleared before checking * isw_nr_in_flight, see generic_shutdown_super(). @@ -1381,12 +1386,13 @@ static void requeue_io(struct inode *inode, struct bdi_writeback *wb) static void inode_sync_complete(struct inode *inode) { + assert_spin_locked(&inode->i_lock); + inode->i_state &= ~I_SYNC; /* If inode is clean an unused, put it into LRU now... */ inode_add_lru(inode); - /* Waiters must see I_SYNC cleared before being woken up */ - smp_mb(); - wake_up_bit(&inode->i_state, __I_SYNC); + /* Called with inode->i_lock which ensures memory ordering. */ + inode_wake_up_bit(inode, __I_SYNC); } static bool inode_dirtied_after(struct inode *inode, unsigned long t) @@ -1505,30 +1511,27 @@ static int write_inode(struct inode *inode, struct writeback_control *wbc) * Wait for writeback on an inode to complete. Called with i_lock held. * Caller must make sure inode cannot go away when we drop i_lock. */ -static void __inode_wait_for_writeback(struct inode *inode) - __releases(inode->i_lock) - __acquires(inode->i_lock) +void inode_wait_for_writeback(struct inode *inode) { - DEFINE_WAIT_BIT(wq, &inode->i_state, __I_SYNC); - wait_queue_head_t *wqh; + struct wait_bit_queue_entry wqe; + struct wait_queue_head *wq_head; + + assert_spin_locked(&inode->i_lock); - wqh = bit_waitqueue(&inode->i_state, __I_SYNC); - while (inode->i_state & I_SYNC) { + if (!(inode->i_state & I_SYNC)) + return; + + wq_head = inode_bit_waitqueue(&wqe, inode, __I_SYNC); + for (;;) { + prepare_to_wait_event(wq_head, &wqe.wq_entry, TASK_UNINTERRUPTIBLE); + /* Checking I_SYNC with inode->i_lock guarantees memory ordering. */ + if (!(inode->i_state & I_SYNC)) + break; spin_unlock(&inode->i_lock); - __wait_on_bit(wqh, &wq, bit_wait, - TASK_UNINTERRUPTIBLE); + schedule(); spin_lock(&inode->i_lock); } -} - -/* - * Wait for writeback on an inode to complete. Caller must have inode pinned. - */ -void inode_wait_for_writeback(struct inode *inode) -{ - spin_lock(&inode->i_lock); - __inode_wait_for_writeback(inode); - spin_unlock(&inode->i_lock); + finish_wait(wq_head, &wqe.wq_entry); } /* @@ -1539,16 +1542,20 @@ void inode_wait_for_writeback(struct inode *inode) static void inode_sleep_on_writeback(struct inode *inode) __releases(inode->i_lock) { - DEFINE_WAIT(wait); - wait_queue_head_t *wqh = bit_waitqueue(&inode->i_state, __I_SYNC); - int sleep; + struct wait_bit_queue_entry wqe; + struct wait_queue_head *wq_head; + bool sleep; + + assert_spin_locked(&inode->i_lock); - prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); - sleep = inode->i_state & I_SYNC; + wq_head = inode_bit_waitqueue(&wqe, inode, __I_SYNC); + prepare_to_wait_event(wq_head, &wqe.wq_entry, TASK_UNINTERRUPTIBLE); + /* Checking I_SYNC with inode->i_lock guarantees memory ordering. */ + sleep = !!(inode->i_state & I_SYNC); spin_unlock(&inode->i_lock); if (sleep) schedule(); - finish_wait(wqh, &wait); + finish_wait(wq_head, &wqe.wq_entry); } /* @@ -1752,7 +1759,7 @@ static int writeback_single_inode(struct inode *inode, */ if (wbc->sync_mode != WB_SYNC_ALL) goto out; - __inode_wait_for_writeback(inode); + inode_wait_for_writeback(inode); } WARN_ON(inode->i_state & I_SYNC); /* diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 7146038b2fe7..f0c9cd1a0b39 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -31,6 +31,8 @@ MODULE_ALIAS("devname:fuse"); static struct kmem_cache *fuse_req_cachep; +static void end_requests(struct list_head *head); + static struct fuse_dev *fuse_get_dev(struct file *file) { /* @@ -773,7 +775,6 @@ static int fuse_check_folio(struct folio *folio) (folio->flags & PAGE_FLAGS_CHECK_AT_PREP & ~(1 << PG_locked | 1 << PG_referenced | - 1 << PG_uptodate | 1 << PG_lru | 1 << PG_active | 1 << PG_workingset | @@ -818,9 +819,7 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep) newfolio = page_folio(buf->page); - if (!folio_test_uptodate(newfolio)) - folio_mark_uptodate(newfolio); - + folio_clear_uptodate(newfolio); folio_clear_mappedtodisk(newfolio); if (fuse_check_folio(newfolio) != 0) @@ -1822,6 +1821,13 @@ static void fuse_resend(struct fuse_conn *fc) } spin_lock(&fiq->lock); + if (!fiq->connected) { + spin_unlock(&fiq->lock); + list_for_each_entry(req, &to_queue, list) + clear_bit(FR_PENDING, &req->flags); + end_requests(&to_queue); + return; + } /* iq and pq requests are both oldest to newest */ list_splice(&to_queue, &fiq->pending); fiq->ops->wake_pending_and_unlock(fiq); diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 2b0d4781f394..8e96df9fd76c 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -670,7 +670,7 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, err = get_create_ext(&args, dir, entry, mode); if (err) - goto out_put_forget_req; + goto out_free_ff; err = fuse_simple_request(fm, &args); free_ext_value(&args); diff --git a/fs/fuse/file.c b/fs/fuse/file.c index f39456c65ed7..ba6df52a823e 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1832,10 +1832,16 @@ __acquires(fi->lock) fuse_writepage_finish(fm, wpa); spin_unlock(&fi->lock); - /* After fuse_writepage_finish() aux request list is private */ + /* After rb_erase() aux request list is private */ for (aux = wpa->next; aux; aux = next) { + struct backing_dev_info *bdi = inode_to_bdi(aux->inode); + next = aux->next; aux->next = NULL; + + dec_wb_stat(&bdi->wb, WB_WRITEBACK); + dec_node_page_state(aux->ia.ap.pages[0], NR_WRITEBACK_TEMP); + wb_writeout_inc(&bdi->wb); fuse_writepage_free(aux); } @@ -2387,76 +2393,77 @@ out: * but how to implement it without killing performance need more thinking. */ static int fuse_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, struct page **pagep, void **fsdata) + loff_t pos, unsigned len, struct folio **foliop, void **fsdata) { pgoff_t index = pos >> PAGE_SHIFT; struct fuse_conn *fc = get_fuse_conn(file_inode(file)); - struct page *page; + struct folio *folio; loff_t fsize; int err = -ENOMEM; WARN_ON(!fc->writeback_cache); - page = grab_cache_page_write_begin(mapping, index); - if (!page) + folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN, + mapping_gfp_mask(mapping)); + if (IS_ERR(folio)) goto error; - fuse_wait_on_page_writeback(mapping->host, page->index); + fuse_wait_on_page_writeback(mapping->host, folio->index); - if (PageUptodate(page) || len == PAGE_SIZE) + if (folio_test_uptodate(folio) || len >= folio_size(folio)) goto success; /* - * Check if the start this page comes after the end of file, in which - * case the readpage can be optimized away. + * Check if the start of this folio comes after the end of file, + * in which case the readpage can be optimized away. */ fsize = i_size_read(mapping->host); - if (fsize <= (pos & PAGE_MASK)) { - size_t off = pos & ~PAGE_MASK; + if (fsize <= folio_pos(folio)) { + size_t off = offset_in_folio(folio, pos); if (off) - zero_user_segment(page, 0, off); + folio_zero_segment(folio, 0, off); goto success; } - err = fuse_do_readpage(file, page); + err = fuse_do_readpage(file, &folio->page); if (err) goto cleanup; success: - *pagep = page; + *foliop = folio; return 0; cleanup: - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); error: return err; } static int fuse_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { - struct inode *inode = page->mapping->host; + struct inode *inode = folio->mapping->host; /* Haven't copied anything? Skip zeroing, size extending, dirtying. */ if (!copied) goto unlock; pos += copied; - if (!PageUptodate(page)) { + if (!folio_test_uptodate(folio)) { /* Zero any unwritten bytes at the end of the page */ size_t endoff = pos & ~PAGE_MASK; if (endoff) - zero_user_segment(page, endoff, PAGE_SIZE); - SetPageUptodate(page); + folio_zero_segment(folio, endoff, PAGE_SIZE); + folio_mark_uptodate(folio); } if (pos > inode->i_size) i_size_write(inode, pos); - set_page_dirty(page); + folio_mark_dirty(folio); unlock: - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); return copied; } diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index d8ab4e93916f..bebd89002328 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -1332,11 +1332,16 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args, * on a stacked fs (e.g. overlayfs) themselves and with * max_stack_depth == 1, FUSE fs can be stacked as the * underlying fs of a stacked fs (e.g. overlayfs). + * + * Also don't allow the combination of FUSE_PASSTHROUGH + * and FUSE_WRITEBACK_CACHE, current design doesn't handle + * them together. */ if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH) && (flags & FUSE_PASSTHROUGH) && arg->max_stack_depth > 0 && - arg->max_stack_depth <= FILESYSTEM_MAX_STACK_DEPTH) { + arg->max_stack_depth <= FILESYSTEM_MAX_STACK_DEPTH && + !(flags & FUSE_WRITEBACK_CACHE)) { fc->passthrough = 1; fc->max_stack_depth = arg->max_stack_depth; fm->sb->s_stack_depth = arg->max_stack_depth; diff --git a/fs/fuse/xattr.c b/fs/fuse/xattr.c index 5b423fdbb13f..9f568d345c51 100644 --- a/fs/fuse/xattr.c +++ b/fs/fuse/xattr.c @@ -81,7 +81,7 @@ ssize_t fuse_getxattr(struct inode *inode, const char *name, void *value, } ret = fuse_simple_request(fm, &args); if (!ret && !size) - ret = min_t(ssize_t, outarg.size, XATTR_SIZE_MAX); + ret = min_t(size_t, outarg.size, XATTR_SIZE_MAX); if (ret == -ENOSYS) { fm->fc->no_getxattr = 1; ret = -EOPNOTSUPP; @@ -143,7 +143,7 @@ ssize_t fuse_listxattr(struct dentry *entry, char *list, size_t size) } ret = fuse_simple_request(fm, &args); if (!ret && !size) - ret = min_t(ssize_t, outarg.size, XATTR_LIST_MAX); + ret = min_t(size_t, outarg.size, XATTR_LIST_MAX); if (ret > 0 && size) ret = fuse_verify_xattr_list(list, ret); if (ret == -ENOSYS) { diff --git a/fs/hfs/extent.c b/fs/hfs/extent.c index 6d1878b99b30..4a0ce131e233 100644 --- a/fs/hfs/extent.c +++ b/fs/hfs/extent.c @@ -487,15 +487,15 @@ void hfs_file_truncate(struct inode *inode) if (inode->i_size > HFS_I(inode)->phys_size) { struct address_space *mapping = inode->i_mapping; void *fsdata = NULL; - struct page *page; + struct folio *folio; /* XXX: Can use generic_cont_expand? */ size = inode->i_size - 1; - res = hfs_write_begin(NULL, mapping, size + 1, 0, &page, + res = hfs_write_begin(NULL, mapping, size + 1, 0, &folio, &fsdata); if (!res) { res = generic_write_end(NULL, mapping, size + 1, 0, 0, - page, fsdata); + folio, fsdata); } if (res) inode->i_size = HFS_I(inode)->phys_size; diff --git a/fs/hfs/hfs_fs.h b/fs/hfs/hfs_fs.h index b5a6ad5df357..a0c7cb0f79fc 100644 --- a/fs/hfs/hfs_fs.h +++ b/fs/hfs/hfs_fs.h @@ -202,7 +202,7 @@ extern const struct address_space_operations hfs_aops; extern const struct address_space_operations hfs_btree_aops; int hfs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, struct page **pagep, void **fsdata); + loff_t pos, unsigned len, struct folio **foliop, void **fsdata); extern struct inode *hfs_new_inode(struct inode *, const struct qstr *, umode_t); extern void hfs_inode_write_fork(struct inode *, struct hfs_extent *, __be32 *, __be32 *); extern int hfs_write_inode(struct inode *, struct writeback_control *); diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index 744e10b46904..a81ce7a740b9 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -45,12 +45,11 @@ static void hfs_write_failed(struct address_space *mapping, loff_t to) } int hfs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, struct page **pagep, void **fsdata) + loff_t pos, unsigned len, struct folio **foliop, void **fsdata) { int ret; - *pagep = NULL; - ret = cont_write_begin(file, mapping, pos, len, pagep, fsdata, + ret = cont_write_begin(file, mapping, pos, len, foliop, fsdata, hfs_get_block, &HFS_I(mapping->host)->phys_size); if (unlikely(ret)) diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c index 9c51867dddc5..a6d61685ae79 100644 --- a/fs/hfsplus/extents.c +++ b/fs/hfsplus/extents.c @@ -554,16 +554,16 @@ void hfsplus_file_truncate(struct inode *inode) if (inode->i_size > hip->phys_size) { struct address_space *mapping = inode->i_mapping; - struct page *page; + struct folio *folio; void *fsdata = NULL; loff_t size = inode->i_size; res = hfsplus_write_begin(NULL, mapping, size, 0, - &page, &fsdata); + &folio, &fsdata); if (res) return; res = generic_write_end(NULL, mapping, size, 0, 0, - page, fsdata); + folio, fsdata); if (res < 0) return; mark_inode_dirty(inode); diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h index 9e78f181c24f..59ce81dca73f 100644 --- a/fs/hfsplus/hfsplus_fs.h +++ b/fs/hfsplus/hfsplus_fs.h @@ -472,7 +472,7 @@ extern const struct address_space_operations hfsplus_btree_aops; extern const struct dentry_operations hfsplus_dentry_operations; int hfsplus_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, struct page **pagep, void **fsdata); + loff_t pos, unsigned len, struct folio **foliop, void **fsdata); struct inode *hfsplus_new_inode(struct super_block *sb, struct inode *dir, umode_t mode); void hfsplus_delete_inode(struct inode *inode); diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index 3d326926c195..f331e9574217 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -39,12 +39,11 @@ static void hfsplus_write_failed(struct address_space *mapping, loff_t to) } int hfsplus_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, struct page **pagep, void **fsdata) + loff_t pos, unsigned len, struct folio **foliop, void **fsdata) { int ret; - *pagep = NULL; - ret = cont_write_begin(file, mapping, pos, len, pagep, fsdata, + ret = cont_write_begin(file, mapping, pos, len, foliop, fsdata, hfsplus_get_block, &HFSPLUS_I(mapping->host)->phys_size); if (unlikely(ret)) diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index 22df574ca99e..6d1cf2436ead 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -465,31 +465,32 @@ static int hostfs_read_folio(struct file *file, struct folio *folio) static int hostfs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { pgoff_t index = pos >> PAGE_SHIFT; - *pagep = grab_cache_page_write_begin(mapping, index); - if (!*pagep) + *foliop = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN, + mapping_gfp_mask(mapping)); + if (!*foliop) return -ENOMEM; return 0; } static int hostfs_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { struct inode *inode = mapping->host; void *buffer; - unsigned from = pos & (PAGE_SIZE - 1); + size_t from = offset_in_folio(folio, pos); int err; - buffer = kmap_local_page(page); - err = write_file(FILE_HOSTFS_I(file)->fd, &pos, buffer + from, copied); + buffer = kmap_local_folio(folio, from); + err = write_file(FILE_HOSTFS_I(file)->fd, &pos, buffer, copied); kunmap_local(buffer); - if (!PageUptodate(page) && err == PAGE_SIZE) - SetPageUptodate(page); + if (!folio_test_uptodate(folio) && err == folio_size(folio)) + folio_mark_uptodate(folio); /* * If err > 0, write_file has added err to pos, so we are comparing @@ -497,8 +498,8 @@ static int hostfs_write_end(struct file *file, struct address_space *mapping, */ if (err > 0 && (pos > inode->i_size)) inode->i_size = pos; - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); return err; } diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c index 1bb8d97cd9ae..449a3fc1b8d9 100644 --- a/fs/hpfs/file.c +++ b/fs/hpfs/file.c @@ -190,12 +190,11 @@ static void hpfs_write_failed(struct address_space *mapping, loff_t to) static int hpfs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { int ret; - *pagep = NULL; - ret = cont_write_begin(file, mapping, pos, len, pagep, fsdata, + ret = cont_write_begin(file, mapping, pos, len, foliop, fsdata, hpfs_get_block, &hpfs_i(mapping->host)->mmu_private); if (unlikely(ret)) @@ -206,11 +205,11 @@ static int hpfs_write_begin(struct file *file, struct address_space *mapping, static int hpfs_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *pagep, void *fsdata) + struct folio *folio, void *fsdata) { struct inode *inode = mapping->host; int err; - err = generic_write_end(file, mapping, pos, len, copied, pagep, fsdata); + err = generic_write_end(file, mapping, pos, len, copied, folio, fsdata); if (err < len) hpfs_write_failed(mapping, pos + len); if (!(err < 0)) { diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 9f6cff356796..5cf327337e22 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -388,14 +388,14 @@ static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to) static int hugetlbfs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { return -EINVAL; } static int hugetlbfs_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { BUG(); return -EINVAL; diff --git a/fs/inode.c b/fs/inode.c index 10c4619faeef..af78f515403f 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -472,6 +472,17 @@ static void __inode_add_lru(struct inode *inode, bool rotate) inode->i_state |= I_REFERENCED; } +struct wait_queue_head *inode_bit_waitqueue(struct wait_bit_queue_entry *wqe, + struct inode *inode, u32 bit) +{ + void *bit_address; + + bit_address = inode_state_wait_address(inode, bit); + init_wait_var_entry(wqe, bit_address, 0); + return __var_waitqueue(bit_address); +} +EXPORT_SYMBOL(inode_bit_waitqueue); + /* * Add inode to LRU if needed (inode is unused and clean). * @@ -500,25 +511,35 @@ static void inode_unpin_lru_isolating(struct inode *inode) spin_lock(&inode->i_lock); WARN_ON(!(inode->i_state & I_LRU_ISOLATING)); inode->i_state &= ~I_LRU_ISOLATING; - smp_mb(); - wake_up_bit(&inode->i_state, __I_LRU_ISOLATING); + /* Called with inode->i_lock which ensures memory ordering. */ + inode_wake_up_bit(inode, __I_LRU_ISOLATING); spin_unlock(&inode->i_lock); } static void inode_wait_for_lru_isolating(struct inode *inode) { - spin_lock(&inode->i_lock); - if (inode->i_state & I_LRU_ISOLATING) { - DEFINE_WAIT_BIT(wq, &inode->i_state, __I_LRU_ISOLATING); - wait_queue_head_t *wqh; + struct wait_bit_queue_entry wqe; + struct wait_queue_head *wq_head; + + lockdep_assert_held(&inode->i_lock); + if (!(inode->i_state & I_LRU_ISOLATING)) + return; - wqh = bit_waitqueue(&inode->i_state, __I_LRU_ISOLATING); + wq_head = inode_bit_waitqueue(&wqe, inode, __I_LRU_ISOLATING); + for (;;) { + prepare_to_wait_event(wq_head, &wqe.wq_entry, TASK_UNINTERRUPTIBLE); + /* + * Checking I_LRU_ISOLATING with inode->i_lock guarantees + * memory ordering. + */ + if (!(inode->i_state & I_LRU_ISOLATING)) + break; spin_unlock(&inode->i_lock); - __wait_on_bit(wqh, &wq, bit_wait, TASK_UNINTERRUPTIBLE); + schedule(); spin_lock(&inode->i_lock); - WARN_ON(inode->i_state & I_LRU_ISOLATING); } - spin_unlock(&inode->i_lock); + finish_wait(wq_head, &wqe.wq_entry); + WARN_ON(inode->i_state & I_LRU_ISOLATING); } /** @@ -595,6 +616,7 @@ void dump_mapping(const struct address_space *mapping) struct hlist_node *dentry_first; struct dentry *dentry_ptr; struct dentry dentry; + char fname[64] = {}; unsigned long ino; /* @@ -631,11 +653,14 @@ void dump_mapping(const struct address_space *mapping) return; } + if (strncpy_from_kernel_nofault(fname, dentry.d_name.name, 63) < 0) + strscpy(fname, "<invalid>"); /* - * if dentry is corrupted, the %pd handler may still crash, - * but it's unlikely that we reach here with a corrupt mapping + * Even if strncpy_from_kernel_nofault() succeeded, + * the fname could be unreliable */ - pr_warn("aops:%ps ino:%lx dentry name:\"%pd\"\n", a_ops, ino, &dentry); + pr_warn("aops:%ps ino:%lx dentry name(?):\"%s\"\n", + a_ops, ino, fname); } void clear_inode(struct inode *inode) @@ -690,6 +715,7 @@ static void evict(struct inode *inode) inode_sb_list_del(inode); + spin_lock(&inode->i_lock); inode_wait_for_lru_isolating(inode); /* @@ -699,6 +725,7 @@ static void evict(struct inode *inode) * the inode. We just have to wait for running writeback to finish. */ inode_wait_for_writeback(inode); + spin_unlock(&inode->i_lock); if (op->evict_inode) { op->evict_inode(inode); @@ -722,7 +749,13 @@ static void evict(struct inode *inode) * used as an indicator whether blocking on it is safe. */ spin_lock(&inode->i_lock); - wake_up_bit(&inode->i_state, __I_NEW); + /* + * Pairs with the barrier in prepare_to_wait_event() to make sure + * ___wait_var_event() either sees the bit cleared or + * waitqueue_active() check in wake_up_var() sees the waiter. + */ + smp_mb(); + inode_wake_up_bit(inode, __I_NEW); BUG_ON(inode->i_state != (I_FREEING | I_CLEAR)); spin_unlock(&inode->i_lock); @@ -770,6 +803,10 @@ again: continue; spin_lock(&inode->i_lock); + if (atomic_read(&inode->i_count)) { + spin_unlock(&inode->i_lock); + continue; + } if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) { spin_unlock(&inode->i_lock); continue; @@ -1130,8 +1167,13 @@ void unlock_new_inode(struct inode *inode) spin_lock(&inode->i_lock); WARN_ON(!(inode->i_state & I_NEW)); inode->i_state &= ~I_NEW & ~I_CREATING; + /* + * Pairs with the barrier in prepare_to_wait_event() to make sure + * ___wait_var_event() either sees the bit cleared or + * waitqueue_active() check in wake_up_var() sees the waiter. + */ smp_mb(); - wake_up_bit(&inode->i_state, __I_NEW); + inode_wake_up_bit(inode, __I_NEW); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(unlock_new_inode); @@ -1142,8 +1184,13 @@ void discard_new_inode(struct inode *inode) spin_lock(&inode->i_lock); WARN_ON(!(inode->i_state & I_NEW)); inode->i_state &= ~I_NEW; + /* + * Pairs with the barrier in prepare_to_wait_event() to make sure + * ___wait_var_event() either sees the bit cleared or + * waitqueue_active() check in wake_up_var() sees the waiter. + */ smp_mb(); - wake_up_bit(&inode->i_state, __I_NEW); + inode_wake_up_bit(inode, __I_NEW); spin_unlock(&inode->i_lock); iput(inode); } @@ -1570,9 +1617,7 @@ struct inode *ilookup(struct super_block *sb, unsigned long ino) struct hlist_head *head = inode_hashtable + hash(sb, ino); struct inode *inode; again: - spin_lock(&inode_hash_lock); - inode = find_inode_fast(sb, head, ino, true); - spin_unlock(&inode_hash_lock); + inode = find_inode_fast(sb, head, ino, false); if (inode) { if (IS_ERR(inode)) @@ -2334,8 +2379,8 @@ EXPORT_SYMBOL(inode_needs_sync); */ static void __wait_on_freeing_inode(struct inode *inode, bool is_inode_hash_locked) { - wait_queue_head_t *wq; - DEFINE_WAIT_BIT(wait, &inode->i_state, __I_NEW); + struct wait_bit_queue_entry wqe; + struct wait_queue_head *wq_head; /* * Handle racing against evict(), see that routine for more details. @@ -2346,14 +2391,14 @@ static void __wait_on_freeing_inode(struct inode *inode, bool is_inode_hash_lock return; } - wq = bit_waitqueue(&inode->i_state, __I_NEW); - prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); + wq_head = inode_bit_waitqueue(&wqe, inode, __I_NEW); + prepare_to_wait_event(wq_head, &wqe.wq_entry, TASK_UNINTERRUPTIBLE); spin_unlock(&inode->i_lock); rcu_read_unlock(); if (is_inode_hash_locked) spin_unlock(&inode_hash_lock); schedule(); - finish_wait(wq, &wait.wq_entry); + finish_wait(wq_head, &wqe.wq_entry); if (is_inode_hash_locked) spin_lock(&inode_hash_lock); rcu_read_lock(); @@ -2502,18 +2547,11 @@ EXPORT_SYMBOL(inode_owner_or_capable); /* * Direct i/o helper functions */ -static void __inode_dio_wait(struct inode *inode) +bool inode_dio_finished(const struct inode *inode) { - wait_queue_head_t *wq = bit_waitqueue(&inode->i_state, __I_DIO_WAKEUP); - DEFINE_WAIT_BIT(q, &inode->i_state, __I_DIO_WAKEUP); - - do { - prepare_to_wait(wq, &q.wq_entry, TASK_UNINTERRUPTIBLE); - if (atomic_read(&inode->i_dio_count)) - schedule(); - } while (atomic_read(&inode->i_dio_count)); - finish_wait(wq, &q.wq_entry); + return atomic_read(&inode->i_dio_count) == 0; } +EXPORT_SYMBOL(inode_dio_finished); /** * inode_dio_wait - wait for outstanding DIO requests to finish @@ -2527,11 +2565,17 @@ static void __inode_dio_wait(struct inode *inode) */ void inode_dio_wait(struct inode *inode) { - if (atomic_read(&inode->i_dio_count)) - __inode_dio_wait(inode); + wait_var_event(&inode->i_dio_count, inode_dio_finished(inode)); } EXPORT_SYMBOL(inode_dio_wait); +void inode_dio_wait_interruptible(struct inode *inode) +{ + wait_var_event_interruptible(&inode->i_dio_count, + inode_dio_finished(inode)); +} +EXPORT_SYMBOL(inode_dio_wait_interruptible); + /* * inode_set_flags - atomically set some inode flags * diff --git a/fs/internal.h b/fs/internal.h index cdd73209eecb..8c1b7acbbe8f 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -337,3 +337,4 @@ static inline bool path_mounted(const struct path *path) { return path->mnt->mnt_root == path->dentry; } +void file_f_owner_release(struct file *file); diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index f420c53d86ac..9b4ca3811a24 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -900,7 +900,7 @@ static bool iomap_write_end(struct iomap_iter *iter, loff_t pos, size_t len, size_t bh_written; bh_written = block_write_end(NULL, iter->inode->i_mapping, pos, - len, copied, &folio->page, NULL); + len, copied, folio, NULL); WARN_ON_ONCE(bh_written != copied && bh_written != 0); return bh_written == copied; } diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c index e12cb145147e..13c18ccc13b0 100644 --- a/fs/jffs2/file.c +++ b/fs/jffs2/file.c @@ -23,10 +23,10 @@ static int jffs2_write_end(struct file *filp, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *pg, void *fsdata); + struct folio *folio, void *fsdata); static int jffs2_write_begin(struct file *filp, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata); + struct folio **foliop, void **fsdata); static int jffs2_read_folio(struct file *filp, struct folio *folio); int jffs2_fsync(struct file *filp, loff_t start, loff_t end, int datasync) @@ -77,29 +77,27 @@ const struct address_space_operations jffs2_file_address_operations = .write_end = jffs2_write_end, }; -static int jffs2_do_readpage_nolock (struct inode *inode, struct page *pg) +static int jffs2_do_readpage_nolock(struct inode *inode, struct folio *folio) { struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode); struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb); - unsigned char *pg_buf; + unsigned char *kaddr; int ret; jffs2_dbg(2, "%s(): ino #%lu, page at offset 0x%lx\n", - __func__, inode->i_ino, pg->index << PAGE_SHIFT); + __func__, inode->i_ino, folio->index << PAGE_SHIFT); - BUG_ON(!PageLocked(pg)); + BUG_ON(!folio_test_locked(folio)); - pg_buf = kmap(pg); - /* FIXME: Can kmap fail? */ - - ret = jffs2_read_inode_range(c, f, pg_buf, pg->index << PAGE_SHIFT, + kaddr = kmap_local_folio(folio, 0); + ret = jffs2_read_inode_range(c, f, kaddr, folio->index << PAGE_SHIFT, PAGE_SIZE); + kunmap_local(kaddr); if (!ret) - SetPageUptodate(pg); + folio_mark_uptodate(folio); - flush_dcache_page(pg); - kunmap(pg); + flush_dcache_folio(folio); jffs2_dbg(2, "readpage finished\n"); return ret; @@ -107,7 +105,7 @@ static int jffs2_do_readpage_nolock (struct inode *inode, struct page *pg) int __jffs2_read_folio(struct file *file, struct folio *folio) { - int ret = jffs2_do_readpage_nolock(folio->mapping->host, &folio->page); + int ret = jffs2_do_readpage_nolock(folio->mapping->host, folio); folio_unlock(folio); return ret; } @@ -125,9 +123,9 @@ static int jffs2_read_folio(struct file *file, struct folio *folio) static int jffs2_write_begin(struct file *filp, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { - struct page *pg; + struct folio *folio; struct inode *inode = mapping->host; struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode); struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb); @@ -206,29 +204,30 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, * page in read_cache_page(), which causes a deadlock. */ mutex_lock(&c->alloc_sem); - pg = grab_cache_page_write_begin(mapping, index); - if (!pg) { - ret = -ENOMEM; + folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN, + mapping_gfp_mask(mapping)); + if (IS_ERR(folio)) { + ret = PTR_ERR(folio); goto release_sem; } - *pagep = pg; + *foliop = folio; /* - * Read in the page if it wasn't already present. Cannot optimize away - * the whole page write case until jffs2_write_end can handle the + * Read in the folio if it wasn't already present. Cannot optimize away + * the whole folio write case until jffs2_write_end can handle the * case of a short-copy. */ - if (!PageUptodate(pg)) { + if (!folio_test_uptodate(folio)) { mutex_lock(&f->sem); - ret = jffs2_do_readpage_nolock(inode, pg); + ret = jffs2_do_readpage_nolock(inode, folio); mutex_unlock(&f->sem); if (ret) { - unlock_page(pg); - put_page(pg); + folio_unlock(folio); + folio_put(folio); goto release_sem; } } - jffs2_dbg(1, "end write_begin(). pg->flags %lx\n", pg->flags); + jffs2_dbg(1, "end write_begin(). folio->flags %lx\n", folio->flags); release_sem: mutex_unlock(&c->alloc_sem); @@ -238,7 +237,7 @@ out_err: static int jffs2_write_end(struct file *filp, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *pg, void *fsdata) + struct folio *folio, void *fsdata) { /* Actually commit the write from the page cache page we're looking at. * For now, we write the full page out each time. It sucks, but it's simple @@ -252,16 +251,17 @@ static int jffs2_write_end(struct file *filp, struct address_space *mapping, unsigned aligned_start = start & ~3; int ret = 0; uint32_t writtenlen = 0; + void *buf; - jffs2_dbg(1, "%s(): ino #%lu, page at 0x%lx, range %d-%d, flags %lx\n", - __func__, inode->i_ino, pg->index << PAGE_SHIFT, - start, end, pg->flags); + jffs2_dbg(1, "%s(): ino #%lu, page at 0x%llx, range %d-%d, flags %lx\n", + __func__, inode->i_ino, folio_pos(folio), + start, end, folio->flags); /* We need to avoid deadlock with page_cache_read() in - jffs2_garbage_collect_pass(). So the page must be + jffs2_garbage_collect_pass(). So the folio must be up to date to prevent page_cache_read() from trying to re-lock it. */ - BUG_ON(!PageUptodate(pg)); + BUG_ON(!folio_test_uptodate(folio)); if (end == PAGE_SIZE) { /* When writing out the end of a page, write out the @@ -276,8 +276,8 @@ static int jffs2_write_end(struct file *filp, struct address_space *mapping, if (!ri) { jffs2_dbg(1, "%s(): Allocation of raw inode failed\n", __func__); - unlock_page(pg); - put_page(pg); + folio_unlock(folio); + folio_put(folio); return -ENOMEM; } @@ -289,15 +289,11 @@ static int jffs2_write_end(struct file *filp, struct address_space *mapping, ri->isize = cpu_to_je32((uint32_t)inode->i_size); ri->atime = ri->ctime = ri->mtime = cpu_to_je32(JFFS2_NOW()); - /* In 2.4, it was already kmapped by generic_file_write(). Doesn't - hurt to do it again. The alternative is ifdefs, which are ugly. */ - kmap(pg); - - ret = jffs2_write_inode_range(c, f, ri, page_address(pg) + aligned_start, - (pg->index << PAGE_SHIFT) + aligned_start, + buf = kmap_local_folio(folio, aligned_start); + ret = jffs2_write_inode_range(c, f, ri, buf, + folio_pos(folio) + aligned_start, end - aligned_start, &writtenlen); - - kunmap(pg); + kunmap_local(buf); if (ret) mapping_set_error(mapping, ret); @@ -323,12 +319,12 @@ static int jffs2_write_end(struct file *filp, struct address_space *mapping, it gets reread */ jffs2_dbg(1, "%s(): Not all bytes written. Marking page !uptodate\n", __func__); - ClearPageUptodate(pg); + folio_clear_uptodate(folio); } jffs2_dbg(1, "%s() returning %d\n", __func__, writtenlen > 0 ? writtenlen : ret); - unlock_page(pg); - put_page(pg); + folio_unlock(folio); + folio_put(folio); return writtenlen > 0 ? writtenlen : ret; } diff --git a/fs/jffs2/gc.c b/fs/jffs2/gc.c index 5c6602f3c189..822949d0eb00 100644 --- a/fs/jffs2/gc.c +++ b/fs/jffs2/gc.c @@ -1171,7 +1171,7 @@ static int jffs2_garbage_collect_dnode(struct jffs2_sb_info *c, struct jffs2_era uint32_t alloclen, offset, orig_end, orig_start; int ret = 0; unsigned char *comprbuf = NULL, *writebuf; - struct page *page; + struct folio *folio; unsigned char *pg_ptr; memset(&ri, 0, sizeof(ri)); @@ -1317,25 +1317,25 @@ static int jffs2_garbage_collect_dnode(struct jffs2_sb_info *c, struct jffs2_era BUG_ON(start > orig_start); } - /* The rules state that we must obtain the page lock *before* f->sem, so + /* The rules state that we must obtain the folio lock *before* f->sem, so * drop f->sem temporarily. Since we also hold c->alloc_sem, nothing's * actually going to *change* so we're safe; we only allow reading. * * It is important to note that jffs2_write_begin() will ensure that its - * page is marked Uptodate before allocating space. That means that if we - * end up here trying to GC the *same* page that jffs2_write_begin() is - * trying to write out, read_cache_page() will not deadlock. */ + * folio is marked uptodate before allocating space. That means that if we + * end up here trying to GC the *same* folio that jffs2_write_begin() is + * trying to write out, read_cache_folio() will not deadlock. */ mutex_unlock(&f->sem); - page = read_cache_page(inode->i_mapping, start >> PAGE_SHIFT, + folio = read_cache_folio(inode->i_mapping, start >> PAGE_SHIFT, __jffs2_read_folio, NULL); - if (IS_ERR(page)) { - pr_warn("read_cache_page() returned error: %ld\n", - PTR_ERR(page)); + if (IS_ERR(folio)) { + pr_warn("read_cache_folio() returned error: %ld\n", + PTR_ERR(folio)); mutex_lock(&f->sem); - return PTR_ERR(page); + return PTR_ERR(folio); } - pg_ptr = kmap(page); + pg_ptr = kmap_local_folio(folio, 0); mutex_lock(&f->sem); offset = start; @@ -1400,7 +1400,6 @@ static int jffs2_garbage_collect_dnode(struct jffs2_sb_info *c, struct jffs2_era } } - kunmap(page); - put_page(page); + folio_release_kmap(folio, pg_ptr); return ret; } diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c index 1a6b5921d17a..07cfdc440596 100644 --- a/fs/jfs/inode.c +++ b/fs/jfs/inode.c @@ -292,11 +292,11 @@ static void jfs_write_failed(struct address_space *mapping, loff_t to) static int jfs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { int ret; - ret = block_write_begin(mapping, pos, len, pagep, jfs_get_block); + ret = block_write_begin(mapping, pos, len, foliop, jfs_get_block); if (unlikely(ret)) jfs_write_failed(mapping, pos + len); @@ -304,12 +304,12 @@ static int jfs_write_begin(struct file *file, struct address_space *mapping, } static int jfs_write_end(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, struct page *page, + loff_t pos, unsigned len, unsigned copied, struct folio *folio, void *fsdata) { int ret; - ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata); + ret = generic_write_end(file, mapping, pos, len, copied, folio, fsdata); if (ret < len) jfs_write_failed(mapping, pos + len); return ret; diff --git a/fs/libfs.c b/fs/libfs.c index 02602d00939e..46966fd8bcf9 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -914,7 +914,7 @@ static int simple_read_folio(struct file *file, struct folio *folio) int simple_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { struct folio *folio; @@ -923,7 +923,7 @@ int simple_write_begin(struct file *file, struct address_space *mapping, if (IS_ERR(folio)) return PTR_ERR(folio); - *pagep = &folio->page; + *foliop = folio; if (!folio_test_uptodate(folio) && (len != folio_size(folio))) { size_t from = offset_in_folio(folio, pos); @@ -942,11 +942,11 @@ EXPORT_SYMBOL(simple_write_begin); * @pos: " * @len: " * @copied: " - * @page: " + * @folio: " * @fsdata: " * - * simple_write_end does the minimum needed for updating a page after writing is - * done. It has the same API signature as the .write_end of + * simple_write_end does the minimum needed for updating a folio after + * writing is done. It has the same API signature as the .write_end of * address_space_operations vector. So it can just be set onto .write_end for * FSes that don't need any other processing. i_mutex is assumed to be held. * Block based filesystems should use generic_write_end(). @@ -959,9 +959,8 @@ EXPORT_SYMBOL(simple_write_begin); */ static int simple_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { - struct folio *folio = page_folio(page); struct inode *inode = folio->mapping->host; loff_t last_pos = pos + copied; @@ -2003,13 +2002,19 @@ bool inode_maybe_inc_iversion(struct inode *inode, bool force) * information, but the legacy inode_inc_iversion code used a spinlock * to serialize increments. * - * Here, we add full memory barriers to ensure that any de-facto - * ordering with other info is preserved. + * We add a full memory barrier to ensure that any de facto ordering + * with other state is preserved (either implicitly coming from cmpxchg + * or explicitly from smp_mb if we don't know upfront if we will execute + * the former). * - * This barrier pairs with the barrier in inode_query_iversion() + * These barriers pair with inode_query_iversion(). */ - smp_mb(); cur = inode_peek_iversion_raw(inode); + if (!force && !(cur & I_VERSION_QUERIED)) { + smp_mb(); + cur = inode_peek_iversion_raw(inode); + } + do { /* If flag is clear then we needn't do anything */ if (!force && !(cur & I_VERSION_QUERIED)) @@ -2038,20 +2043,22 @@ EXPORT_SYMBOL(inode_maybe_inc_iversion); u64 inode_query_iversion(struct inode *inode) { u64 cur, new; + bool fenced = false; + /* + * Memory barriers (implicit in cmpxchg, explicit in smp_mb) pair with + * inode_maybe_inc_iversion(), see that routine for more details. + */ cur = inode_peek_iversion_raw(inode); do { /* If flag is already set, then no need to swap */ if (cur & I_VERSION_QUERIED) { - /* - * This barrier (and the implicit barrier in the - * cmpxchg below) pairs with the barrier in - * inode_maybe_inc_iversion(). - */ - smp_mb(); + if (!fenced) + smp_mb(); break; } + fenced = true; new = cur | I_VERSION_QUERIED; } while (!atomic64_try_cmpxchg(&inode->i_version, &cur, new)); return cur >> I_VERSION_QUERIED_SHIFT; @@ -2117,12 +2124,12 @@ struct timespec64 simple_inode_init_ts(struct inode *inode) } EXPORT_SYMBOL(simple_inode_init_ts); -static inline struct dentry *get_stashed_dentry(struct dentry *stashed) +static inline struct dentry *get_stashed_dentry(struct dentry **stashed) { struct dentry *dentry; guard(rcu)(); - dentry = READ_ONCE(stashed); + dentry = rcu_dereference(*stashed); if (!dentry) return NULL; if (!lockref_get_not_dead(&dentry->d_lockref)) @@ -2219,7 +2226,7 @@ int path_from_stashed(struct dentry **stashed, struct vfsmount *mnt, void *data, const struct stashed_operations *sops = mnt->mnt_sb->s_fs_info; /* See if dentry can be reused. */ - path->dentry = get_stashed_dentry(*stashed); + path->dentry = get_stashed_dentry(stashed); if (path->dentry) { sops->put_data(data); goto out_path; diff --git a/fs/locks.c b/fs/locks.c index e45cad40f8b6..b51b1c395ce6 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1451,7 +1451,7 @@ int lease_modify(struct file_lease *fl, int arg, struct list_head *dispose) struct file *filp = fl->c.flc_file; f_delown(filp); - filp->f_owner.signum = 0; + file_f_owner(filp)->signum = 0; fasync_helper(0, fl->c.flc_file, 0, &fl->fl_fasync); if (fl->fl_fasync != NULL) { printk(KERN_ERR "locks_delete_lock: fasync == %p\n", fl->fl_fasync); @@ -1783,6 +1783,10 @@ generic_add_lease(struct file *filp, int arg, struct file_lease **flp, void **pr lease = *flp; trace_generic_add_lease(inode, lease); + error = file_f_owner_allocate(filp); + if (error) + return error; + /* Note that arg is never F_UNLCK here */ ctx = locks_get_lock_context(inode, arg); if (!ctx) diff --git a/fs/minix/dir.c b/fs/minix/dir.c index a224cf222570..dd2a425b41f0 100644 --- a/fs/minix/dir.c +++ b/fs/minix/dir.c @@ -40,18 +40,18 @@ minix_last_byte(struct inode *inode, unsigned long page_nr) return last_byte; } -static void dir_commit_chunk(struct page *page, loff_t pos, unsigned len) +static void dir_commit_chunk(struct folio *folio, loff_t pos, unsigned len) { - struct address_space *mapping = page->mapping; + struct address_space *mapping = folio->mapping; struct inode *dir = mapping->host; - block_write_end(NULL, mapping, pos, len, len, page, NULL); + block_write_end(NULL, mapping, pos, len, len, folio, NULL); if (pos+len > dir->i_size) { i_size_write(dir, pos+len); mark_inode_dirty(dir); } - unlock_page(page); + folio_unlock(folio); } static int minix_handle_dirsync(struct inode *dir) @@ -64,14 +64,15 @@ static int minix_handle_dirsync(struct inode *dir) return err; } -static void *dir_get_page(struct inode *dir, unsigned long n, struct page **p) +static void *dir_get_folio(struct inode *dir, unsigned long n, + struct folio **foliop) { - struct address_space *mapping = dir->i_mapping; - struct page *page = read_mapping_page(mapping, n, NULL); - if (IS_ERR(page)) - return ERR_CAST(page); - *p = page; - return kmap_local_page(page); + struct folio *folio = read_mapping_folio(dir->i_mapping, n, NULL); + + if (IS_ERR(folio)) + return ERR_CAST(folio); + *foliop = folio; + return kmap_local_folio(folio, 0); } static inline void *minix_next_entry(void *de, struct minix_sb_info *sbi) @@ -99,9 +100,9 @@ static int minix_readdir(struct file *file, struct dir_context *ctx) for ( ; n < npages; n++, offset = 0) { char *p, *kaddr, *limit; - struct page *page; + struct folio *folio; - kaddr = dir_get_page(inode, n, &page); + kaddr = dir_get_folio(inode, n, &folio); if (IS_ERR(kaddr)) continue; p = kaddr+offset; @@ -122,13 +123,13 @@ static int minix_readdir(struct file *file, struct dir_context *ctx) unsigned l = strnlen(name, sbi->s_namelen); if (!dir_emit(ctx, name, l, inumber, DT_UNKNOWN)) { - unmap_and_put_page(page, p); + folio_release_kmap(folio, p); return 0; } } ctx->pos += chunk_size; } - unmap_and_put_page(page, kaddr); + folio_release_kmap(folio, kaddr); } return 0; } @@ -144,12 +145,13 @@ static inline int namecompare(int len, int maxlen, /* * minix_find_entry() * - * finds an entry in the specified directory with the wanted name. It - * returns the cache buffer in which the entry was found, and the entry - * itself (as a parameter - res_dir). It does NOT read the inode of the + * finds an entry in the specified directory with the wanted name. + * It does NOT read the inode of the * entry - you'll have to do that yourself if you want to. + * + * On Success folio_release_kmap() should be called on *foliop. */ -minix_dirent *minix_find_entry(struct dentry *dentry, struct page **res_page) +minix_dirent *minix_find_entry(struct dentry *dentry, struct folio **foliop) { const char * name = dentry->d_name.name; int namelen = dentry->d_name.len; @@ -158,17 +160,15 @@ minix_dirent *minix_find_entry(struct dentry *dentry, struct page **res_page) struct minix_sb_info * sbi = minix_sb(sb); unsigned long n; unsigned long npages = dir_pages(dir); - struct page *page = NULL; char *p; char *namx; __u32 inumber; - *res_page = NULL; for (n = 0; n < npages; n++) { char *kaddr, *limit; - kaddr = dir_get_page(dir, n, &page); + kaddr = dir_get_folio(dir, n, foliop); if (IS_ERR(kaddr)) continue; @@ -188,12 +188,11 @@ minix_dirent *minix_find_entry(struct dentry *dentry, struct page **res_page) if (namecompare(namelen, sbi->s_namelen, name, namx)) goto found; } - unmap_and_put_page(page, kaddr); + folio_release_kmap(*foliop, kaddr); } return NULL; found: - *res_page = page; return (minix_dirent *)p; } @@ -204,7 +203,7 @@ int minix_add_link(struct dentry *dentry, struct inode *inode) int namelen = dentry->d_name.len; struct super_block * sb = dir->i_sb; struct minix_sb_info * sbi = minix_sb(sb); - struct page *page = NULL; + struct folio *folio = NULL; unsigned long npages = dir_pages(dir); unsigned long n; char *kaddr, *p; @@ -223,10 +222,10 @@ int minix_add_link(struct dentry *dentry, struct inode *inode) for (n = 0; n <= npages; n++) { char *limit, *dir_end; - kaddr = dir_get_page(dir, n, &page); + kaddr = dir_get_folio(dir, n, &folio); if (IS_ERR(kaddr)) return PTR_ERR(kaddr); - lock_page(page); + folio_lock(folio); dir_end = kaddr + minix_last_byte(dir, n); limit = kaddr + PAGE_SIZE - sbi->s_dirsize; for (p = kaddr; p <= limit; p = minix_next_entry(p, sbi)) { @@ -253,15 +252,15 @@ int minix_add_link(struct dentry *dentry, struct inode *inode) if (namecompare(namelen, sbi->s_namelen, name, namx)) goto out_unlock; } - unlock_page(page); - unmap_and_put_page(page, kaddr); + folio_unlock(folio); + folio_release_kmap(folio, kaddr); } BUG(); return -EINVAL; got_it: - pos = page_offset(page) + offset_in_page(p); - err = minix_prepare_chunk(page, pos, sbi->s_dirsize); + pos = folio_pos(folio) + offset_in_folio(folio, p); + err = minix_prepare_chunk(folio, pos, sbi->s_dirsize); if (err) goto out_unlock; memcpy (namx, name, namelen); @@ -272,37 +271,37 @@ got_it: memset (namx + namelen, 0, sbi->s_dirsize - namelen - 2); de->inode = inode->i_ino; } - dir_commit_chunk(page, pos, sbi->s_dirsize); + dir_commit_chunk(folio, pos, sbi->s_dirsize); inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); mark_inode_dirty(dir); err = minix_handle_dirsync(dir); out_put: - unmap_and_put_page(page, kaddr); + folio_release_kmap(folio, kaddr); return err; out_unlock: - unlock_page(page); + folio_unlock(folio); goto out_put; } -int minix_delete_entry(struct minix_dir_entry *de, struct page *page) +int minix_delete_entry(struct minix_dir_entry *de, struct folio *folio) { - struct inode *inode = page->mapping->host; - loff_t pos = page_offset(page) + offset_in_page(de); + struct inode *inode = folio->mapping->host; + loff_t pos = folio_pos(folio) + offset_in_folio(folio, de); struct minix_sb_info *sbi = minix_sb(inode->i_sb); unsigned len = sbi->s_dirsize; int err; - lock_page(page); - err = minix_prepare_chunk(page, pos, len); + folio_lock(folio); + err = minix_prepare_chunk(folio, pos, len); if (err) { - unlock_page(page); + folio_unlock(folio); return err; } if (sbi->s_version == MINIX_V3) ((minix3_dirent *)de)->inode = 0; else de->inode = 0; - dir_commit_chunk(page, pos, len); + dir_commit_chunk(folio, pos, len); inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); mark_inode_dirty(inode); return minix_handle_dirsync(inode); @@ -310,21 +309,21 @@ int minix_delete_entry(struct minix_dir_entry *de, struct page *page) int minix_make_empty(struct inode *inode, struct inode *dir) { - struct page *page = grab_cache_page(inode->i_mapping, 0); + struct folio *folio = filemap_grab_folio(inode->i_mapping, 0); struct minix_sb_info *sbi = minix_sb(inode->i_sb); char *kaddr; int err; - if (!page) - return -ENOMEM; - err = minix_prepare_chunk(page, 0, 2 * sbi->s_dirsize); + if (IS_ERR(folio)) + return PTR_ERR(folio); + err = minix_prepare_chunk(folio, 0, 2 * sbi->s_dirsize); if (err) { - unlock_page(page); + folio_unlock(folio); goto fail; } - kaddr = kmap_local_page(page); - memset(kaddr, 0, PAGE_SIZE); + kaddr = kmap_local_folio(folio, 0); + memset(kaddr, 0, folio_size(folio)); if (sbi->s_version == MINIX_V3) { minix3_dirent *de3 = (minix3_dirent *)kaddr; @@ -345,10 +344,10 @@ int minix_make_empty(struct inode *inode, struct inode *dir) } kunmap_local(kaddr); - dir_commit_chunk(page, 0, 2 * sbi->s_dirsize); + dir_commit_chunk(folio, 0, 2 * sbi->s_dirsize); err = minix_handle_dirsync(inode); fail: - put_page(page); + folio_put(folio); return err; } @@ -357,7 +356,7 @@ fail: */ int minix_empty_dir(struct inode * inode) { - struct page *page = NULL; + struct folio *folio = NULL; unsigned long i, npages = dir_pages(inode); struct minix_sb_info *sbi = minix_sb(inode->i_sb); char *name, *kaddr; @@ -366,7 +365,7 @@ int minix_empty_dir(struct inode * inode) for (i = 0; i < npages; i++) { char *p, *limit; - kaddr = dir_get_page(inode, i, &page); + kaddr = dir_get_folio(inode, i, &folio); if (IS_ERR(kaddr)) continue; @@ -395,44 +394,44 @@ int minix_empty_dir(struct inode * inode) goto not_empty; } } - unmap_and_put_page(page, kaddr); + folio_release_kmap(folio, kaddr); } return 1; not_empty: - unmap_and_put_page(page, kaddr); + folio_release_kmap(folio, kaddr); return 0; } /* Releases the page */ -int minix_set_link(struct minix_dir_entry *de, struct page *page, +int minix_set_link(struct minix_dir_entry *de, struct folio *folio, struct inode *inode) { - struct inode *dir = page->mapping->host; + struct inode *dir = folio->mapping->host; struct minix_sb_info *sbi = minix_sb(dir->i_sb); - loff_t pos = page_offset(page) + offset_in_page(de); + loff_t pos = folio_pos(folio) + offset_in_folio(folio, de); int err; - lock_page(page); - err = minix_prepare_chunk(page, pos, sbi->s_dirsize); + folio_lock(folio); + err = minix_prepare_chunk(folio, pos, sbi->s_dirsize); if (err) { - unlock_page(page); + folio_unlock(folio); return err; } if (sbi->s_version == MINIX_V3) ((minix3_dirent *)de)->inode = inode->i_ino; else de->inode = inode->i_ino; - dir_commit_chunk(page, pos, sbi->s_dirsize); + dir_commit_chunk(folio, pos, sbi->s_dirsize); inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); mark_inode_dirty(dir); return minix_handle_dirsync(dir); } -struct minix_dir_entry * minix_dotdot (struct inode *dir, struct page **p) +struct minix_dir_entry *minix_dotdot(struct inode *dir, struct folio **foliop) { struct minix_sb_info *sbi = minix_sb(dir->i_sb); - struct minix_dir_entry *de = dir_get_page(dir, 0, p); + struct minix_dir_entry *de = dir_get_folio(dir, 0, foliop); if (!IS_ERR(de)) return minix_next_entry(de, sbi); @@ -441,20 +440,19 @@ struct minix_dir_entry * minix_dotdot (struct inode *dir, struct page **p) ino_t minix_inode_by_name(struct dentry *dentry) { - struct page *page; - struct minix_dir_entry *de = minix_find_entry(dentry, &page); + struct folio *folio; + struct minix_dir_entry *de = minix_find_entry(dentry, &folio); ino_t res = 0; if (de) { - struct address_space *mapping = page->mapping; - struct inode *inode = mapping->host; + struct inode *inode = folio->mapping->host; struct minix_sb_info *sbi = minix_sb(inode->i_sb); if (sbi->s_version == MINIX_V3) res = ((minix3_dirent *) de)->inode; else res = de->inode; - unmap_and_put_page(page, de); + folio_release_kmap(folio, de); } return res; } diff --git a/fs/minix/inode.c b/fs/minix/inode.c index 1c3df63162ef..f007e389d5d2 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -427,9 +427,9 @@ static int minix_read_folio(struct file *file, struct folio *folio) return block_read_full_folio(folio, minix_get_block); } -int minix_prepare_chunk(struct page *page, loff_t pos, unsigned len) +int minix_prepare_chunk(struct folio *folio, loff_t pos, unsigned len) { - return __block_write_begin(page, pos, len, minix_get_block); + return __block_write_begin(folio, pos, len, minix_get_block); } static void minix_write_failed(struct address_space *mapping, loff_t to) @@ -444,11 +444,11 @@ static void minix_write_failed(struct address_space *mapping, loff_t to) static int minix_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { int ret; - ret = block_write_begin(mapping, pos, len, pagep, minix_get_block); + ret = block_write_begin(mapping, pos, len, foliop, minix_get_block); if (unlikely(ret)) minix_write_failed(mapping, pos + len); diff --git a/fs/minix/minix.h b/fs/minix/minix.h index d493507c064f..d54273c3c9ff 100644 --- a/fs/minix/minix.h +++ b/fs/minix/minix.h @@ -42,18 +42,18 @@ struct minix_sb_info { unsigned short s_version; }; -extern struct inode *minix_iget(struct super_block *, unsigned long); -extern struct minix_inode * minix_V1_raw_inode(struct super_block *, ino_t, struct buffer_head **); -extern struct minix2_inode * minix_V2_raw_inode(struct super_block *, ino_t, struct buffer_head **); -extern struct inode * minix_new_inode(const struct inode *, umode_t); -extern void minix_free_inode(struct inode * inode); -extern unsigned long minix_count_free_inodes(struct super_block *sb); -extern int minix_new_block(struct inode * inode); -extern void minix_free_block(struct inode *inode, unsigned long block); -extern unsigned long minix_count_free_blocks(struct super_block *sb); -extern int minix_getattr(struct mnt_idmap *, const struct path *, - struct kstat *, u32, unsigned int); -extern int minix_prepare_chunk(struct page *page, loff_t pos, unsigned len); +struct inode *minix_iget(struct super_block *, unsigned long); +struct minix_inode *minix_V1_raw_inode(struct super_block *, ino_t, struct buffer_head **); +struct minix2_inode *minix_V2_raw_inode(struct super_block *, ino_t, struct buffer_head **); +struct inode *minix_new_inode(const struct inode *, umode_t); +void minix_free_inode(struct inode *inode); +unsigned long minix_count_free_inodes(struct super_block *sb); +int minix_new_block(struct inode *inode); +void minix_free_block(struct inode *inode, unsigned long block); +unsigned long minix_count_free_blocks(struct super_block *sb); +int minix_getattr(struct mnt_idmap *, const struct path *, + struct kstat *, u32, unsigned int); +int minix_prepare_chunk(struct folio *folio, loff_t pos, unsigned len); extern void V1_minix_truncate(struct inode *); extern void V2_minix_truncate(struct inode *); @@ -64,15 +64,15 @@ extern int V2_minix_get_block(struct inode *, long, struct buffer_head *, int); extern unsigned V1_minix_blocks(loff_t, struct super_block *); extern unsigned V2_minix_blocks(loff_t, struct super_block *); -extern struct minix_dir_entry *minix_find_entry(struct dentry*, struct page**); -extern int minix_add_link(struct dentry*, struct inode*); -extern int minix_delete_entry(struct minix_dir_entry*, struct page*); -extern int minix_make_empty(struct inode*, struct inode*); -extern int minix_empty_dir(struct inode*); -int minix_set_link(struct minix_dir_entry *de, struct page *page, +struct minix_dir_entry *minix_find_entry(struct dentry *, struct folio **); +int minix_add_link(struct dentry*, struct inode*); +int minix_delete_entry(struct minix_dir_entry *, struct folio *); +int minix_make_empty(struct inode*, struct inode*); +int minix_empty_dir(struct inode*); +int minix_set_link(struct minix_dir_entry *de, struct folio *folio, struct inode *inode); -extern struct minix_dir_entry *minix_dotdot(struct inode*, struct page**); -extern ino_t minix_inode_by_name(struct dentry*); +struct minix_dir_entry *minix_dotdot(struct inode*, struct folio **); +ino_t minix_inode_by_name(struct dentry*); extern const struct inode_operations minix_file_inode_operations; extern const struct inode_operations minix_dir_inode_operations; diff --git a/fs/minix/namei.c b/fs/minix/namei.c index a944a0f17b53..5d9c1406fe27 100644 --- a/fs/minix/namei.c +++ b/fs/minix/namei.c @@ -141,15 +141,15 @@ out_fail: static int minix_unlink(struct inode * dir, struct dentry *dentry) { struct inode * inode = d_inode(dentry); - struct page * page; + struct folio *folio; struct minix_dir_entry * de; int err; - de = minix_find_entry(dentry, &page); + de = minix_find_entry(dentry, &folio); if (!de) return -ENOENT; - err = minix_delete_entry(de, page); - unmap_and_put_page(page, de); + err = minix_delete_entry(de, folio); + folio_release_kmap(folio, de); if (err) return err; @@ -180,28 +180,28 @@ static int minix_rename(struct mnt_idmap *idmap, { struct inode * old_inode = d_inode(old_dentry); struct inode * new_inode = d_inode(new_dentry); - struct page * dir_page = NULL; + struct folio * dir_folio = NULL; struct minix_dir_entry * dir_de = NULL; - struct page * old_page; + struct folio *old_folio; struct minix_dir_entry * old_de; int err = -ENOENT; if (flags & ~RENAME_NOREPLACE) return -EINVAL; - old_de = minix_find_entry(old_dentry, &old_page); + old_de = minix_find_entry(old_dentry, &old_folio); if (!old_de) goto out; if (S_ISDIR(old_inode->i_mode)) { err = -EIO; - dir_de = minix_dotdot(old_inode, &dir_page); + dir_de = minix_dotdot(old_inode, &dir_folio); if (!dir_de) goto out_old; } if (new_inode) { - struct page * new_page; + struct folio *new_folio; struct minix_dir_entry * new_de; err = -ENOTEMPTY; @@ -209,11 +209,11 @@ static int minix_rename(struct mnt_idmap *idmap, goto out_dir; err = -ENOENT; - new_de = minix_find_entry(new_dentry, &new_page); + new_de = minix_find_entry(new_dentry, &new_folio); if (!new_de) goto out_dir; - err = minix_set_link(new_de, new_page, old_inode); - unmap_and_put_page(new_page, new_de); + err = minix_set_link(new_de, new_folio, old_inode); + folio_release_kmap(new_folio, new_de); if (err) goto out_dir; inode_set_ctime_current(new_inode); @@ -228,22 +228,22 @@ static int minix_rename(struct mnt_idmap *idmap, inode_inc_link_count(new_dir); } - err = minix_delete_entry(old_de, old_page); + err = minix_delete_entry(old_de, old_folio); if (err) goto out_dir; mark_inode_dirty(old_inode); if (dir_de) { - err = minix_set_link(dir_de, dir_page, new_dir); + err = minix_set_link(dir_de, dir_folio, new_dir); if (!err) inode_dec_link_count(old_dir); } out_dir: if (dir_de) - unmap_and_put_page(dir_page, dir_de); + folio_release_kmap(dir_folio, dir_de); out_old: - unmap_and_put_page(old_page, old_de); + folio_release_kmap(old_folio, old_de); out: return err; } diff --git a/fs/mnt_idmapping.c b/fs/mnt_idmapping.c index 3c60f1eaca61..79491663dbc0 100644 --- a/fs/mnt_idmapping.c +++ b/fs/mnt_idmapping.c @@ -228,15 +228,15 @@ static int copy_mnt_idmap(struct uid_gid_map *map_from, return 0; } - forward = kmemdup(map_from->forward, - nr_extents * sizeof(struct uid_gid_extent), - GFP_KERNEL_ACCOUNT); + forward = kmemdup_array(map_from->forward, nr_extents, + sizeof(struct uid_gid_extent), + GFP_KERNEL_ACCOUNT); if (!forward) return -ENOMEM; - reverse = kmemdup(map_from->reverse, - nr_extents * sizeof(struct uid_gid_extent), - GFP_KERNEL_ACCOUNT); + reverse = kmemdup_array(map_from->reverse, nr_extents, + sizeof(struct uid_gid_extent), + GFP_KERNEL_ACCOUNT); if (!reverse) { kfree(forward); return -ENOMEM; diff --git a/fs/mount.h b/fs/mount.h index ad4b1ddebb54..185fc56afc13 100644 --- a/fs/mount.h +++ b/fs/mount.h @@ -153,5 +153,17 @@ static inline void move_from_ns(struct mount *mnt, struct list_head *dt_list) list_add_tail(&mnt->mnt_list, dt_list); } -extern void mnt_cursor_del(struct mnt_namespace *ns, struct mount *cursor); bool has_locked_children(struct mount *mnt, struct dentry *dentry); +struct mnt_namespace *__lookup_next_mnt_ns(struct mnt_namespace *mnt_ns, bool previous); +static inline struct mnt_namespace *lookup_next_mnt_ns(struct mnt_namespace *mntns) +{ + return __lookup_next_mnt_ns(mntns, false); +} +static inline struct mnt_namespace *lookup_prev_mnt_ns(struct mnt_namespace *mntns) +{ + return __lookup_next_mnt_ns(mntns, true); +} +static inline struct mnt_namespace *to_mnt_ns(struct ns_common *ns) +{ + return container_of(ns, struct mnt_namespace, ns); +} diff --git a/fs/namei.c b/fs/namei.c index 5512cb10fa89..891b169e38c9 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1639,6 +1639,20 @@ struct dentry *lookup_one_qstr_excl(const struct qstr *name, } EXPORT_SYMBOL(lookup_one_qstr_excl); +/** + * lookup_fast - do fast lockless (but racy) lookup of a dentry + * @nd: current nameidata + * + * Do a fast, but racy lookup in the dcache for the given dentry, and + * revalidate it. Returns a valid dentry pointer or NULL if one wasn't + * found. On error, an ERR_PTR will be returned. + * + * If this function returns a valid dentry and the walk is no longer + * lazy, the dentry will carry a reference that must later be put. If + * RCU mode is still in force, then this is not the case and the dentry + * must be legitimized before use. If this returns NULL, then the walk + * will no longer be in RCU mode. + */ static struct dentry *lookup_fast(struct nameidata *nd) { struct dentry *dentry, *parent = nd->path.dentry; @@ -3521,6 +3535,9 @@ static struct dentry *lookup_open(struct nameidata *nd, struct file *file, return dentry; } + if (open_flag & O_CREAT) + audit_inode(nd->name, dir, AUDIT_INODE_PARENT); + /* * Checking write permission is tricky, bacuse we don't know if we are * going to actually need it: O_CREAT opens should work as long as the @@ -3591,6 +3608,42 @@ out_dput: return ERR_PTR(error); } +static inline bool trailing_slashes(struct nameidata *nd) +{ + return (bool)nd->last.name[nd->last.len]; +} + +static struct dentry *lookup_fast_for_open(struct nameidata *nd, int open_flag) +{ + struct dentry *dentry; + + if (open_flag & O_CREAT) { + if (trailing_slashes(nd)) + return ERR_PTR(-EISDIR); + + /* Don't bother on an O_EXCL create */ + if (open_flag & O_EXCL) + return NULL; + } + + if (trailing_slashes(nd)) + nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY; + + dentry = lookup_fast(nd); + if (IS_ERR_OR_NULL(dentry)) + return dentry; + + if (open_flag & O_CREAT) { + /* Discard negative dentries. Need inode_lock to do the create */ + if (!dentry->d_inode) { + if (!(nd->flags & LOOKUP_RCU)) + dput(dentry); + dentry = NULL; + } + } + return dentry; +} + static const char *open_last_lookups(struct nameidata *nd, struct file *file, const struct open_flags *op) { @@ -3608,28 +3661,22 @@ static const char *open_last_lookups(struct nameidata *nd, return handle_dots(nd, nd->last_type); } - if (!(open_flag & O_CREAT)) { - if (nd->last.name[nd->last.len]) - nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY; - /* we _can_ be in RCU mode here */ - dentry = lookup_fast(nd); - if (IS_ERR(dentry)) - return ERR_CAST(dentry); - if (likely(dentry)) - goto finish_lookup; + /* We _can_ be in RCU mode here */ + dentry = lookup_fast_for_open(nd, open_flag); + if (IS_ERR(dentry)) + return ERR_CAST(dentry); + if (likely(dentry)) + goto finish_lookup; + + if (!(open_flag & O_CREAT)) { if (WARN_ON_ONCE(nd->flags & LOOKUP_RCU)) return ERR_PTR(-ECHILD); } else { - /* create side of things */ if (nd->flags & LOOKUP_RCU) { if (!try_to_unlazy(nd)) return ERR_PTR(-ECHILD); } - audit_inode(nd->name, dir, AUDIT_INODE_PARENT); - /* trailing slashes? */ - if (unlikely(nd->last.name[nd->last.len])) - return ERR_PTR(-EISDIR); } if (open_flag & (O_CREAT | O_TRUNC | O_WRONLY | O_RDWR)) { @@ -5304,7 +5351,7 @@ int page_symlink(struct inode *inode, const char *symname, int len) struct address_space *mapping = inode->i_mapping; const struct address_space_operations *aops = mapping->a_ops; bool nofs = !mapping_gfp_constraint(mapping, __GFP_FS); - struct page *page; + struct folio *folio; void *fsdata = NULL; int err; unsigned int flags; @@ -5312,16 +5359,16 @@ int page_symlink(struct inode *inode, const char *symname, int len) retry: if (nofs) flags = memalloc_nofs_save(); - err = aops->write_begin(NULL, mapping, 0, len-1, &page, &fsdata); + err = aops->write_begin(NULL, mapping, 0, len-1, &folio, &fsdata); if (nofs) memalloc_nofs_restore(flags); if (err) goto fail; - memcpy(page_address(page), symname, len-1); + memcpy(folio_address(folio), symname, len - 1); - err = aops->write_end(NULL, mapping, 0, len-1, len-1, - page, fsdata); + err = aops->write_end(NULL, mapping, 0, len - 1, len - 1, + folio, fsdata); if (err < 0) goto fail; if (err < len-1) diff --git a/fs/namespace.c b/fs/namespace.c index 328087a4df8a..e71e4564987b 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1774,7 +1774,7 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how) list_del_init(&p->mnt_child); } - /* Add propogated mounts to the tmp_list */ + /* Add propagated mounts to the tmp_list */ if (how & UMOUNT_PROPAGATE) propagate_umount(&tmp_list); @@ -2060,14 +2060,41 @@ static bool is_mnt_ns_file(struct dentry *dentry) dentry->d_fsdata == &mntns_operations; } -static struct mnt_namespace *to_mnt_ns(struct ns_common *ns) +struct ns_common *from_mnt_ns(struct mnt_namespace *mnt) { - return container_of(ns, struct mnt_namespace, ns); + return &mnt->ns; } -struct ns_common *from_mnt_ns(struct mnt_namespace *mnt) +struct mnt_namespace *__lookup_next_mnt_ns(struct mnt_namespace *mntns, bool previous) { - return &mnt->ns; + guard(read_lock)(&mnt_ns_tree_lock); + for (;;) { + struct rb_node *node; + + if (previous) + node = rb_prev(&mntns->mnt_ns_tree_node); + else + node = rb_next(&mntns->mnt_ns_tree_node); + if (!node) + return ERR_PTR(-ENOENT); + + mntns = node_to_mnt_ns(node); + node = &mntns->mnt_ns_tree_node; + + if (!ns_capable_noaudit(mntns->user_ns, CAP_SYS_ADMIN)) + continue; + + /* + * Holding mnt_ns_tree_lock prevents the mount namespace from + * being freed but it may well be on it's deathbed. We want an + * active reference, not just a passive one here as we're + * persisting the mount namespace. + */ + if (!refcount_inc_not_zero(&mntns->ns.count)) + continue; + + return mntns; + } } static bool mnt_ns_loop(struct dentry *dentry) @@ -2921,8 +2948,15 @@ static void mnt_warn_timestamp_expiry(struct path *mountpoint, struct vfsmount * if (!__mnt_is_readonly(mnt) && (!(sb->s_iflags & SB_I_TS_EXPIRY_WARNED)) && (ktime_get_real_seconds() + TIME_UPTIME_SEC_MAX > sb->s_time_max)) { - char *buf = (char *)__get_free_page(GFP_KERNEL); - char *mntpath = buf ? d_path(mountpoint, buf, PAGE_SIZE) : ERR_PTR(-ENOMEM); + char *buf, *mntpath; + + buf = (char *)__get_free_page(GFP_KERNEL); + if (buf) + mntpath = d_path(mountpoint, buf, PAGE_SIZE); + else + mntpath = ERR_PTR(-ENOMEM); + if (IS_ERR(mntpath)) + mntpath = "(unknown)"; pr_warn("%s filesystem being %s at %s supports timestamps until %ptTd (0x%llx)\n", sb->s_type->name, @@ -2930,8 +2964,9 @@ static void mnt_warn_timestamp_expiry(struct path *mountpoint, struct vfsmount * mntpath, &sb->s_time_max, (unsigned long long)sb->s_time_max); - free_page((unsigned long)buf); sb->s_iflags |= SB_I_TS_EXPIRY_WARNED; + if (buf) + free_page((unsigned long)buf); } } @@ -5243,12 +5278,37 @@ static int copy_mnt_id_req(const struct mnt_id_req __user *req, * that, or if not simply grab a passive reference on our mount namespace and * return that. */ -static struct mnt_namespace *grab_requested_mnt_ns(u64 mnt_ns_id) +static struct mnt_namespace *grab_requested_mnt_ns(const struct mnt_id_req *kreq) { - if (mnt_ns_id) - return lookup_mnt_ns(mnt_ns_id); - refcount_inc(¤t->nsproxy->mnt_ns->passive); - return current->nsproxy->mnt_ns; + struct mnt_namespace *mnt_ns; + + if (kreq->mnt_ns_id && kreq->spare) + return ERR_PTR(-EINVAL); + + if (kreq->mnt_ns_id) + return lookup_mnt_ns(kreq->mnt_ns_id); + + if (kreq->spare) { + struct ns_common *ns; + + CLASS(fd, f)(kreq->spare); + if (!f.file) + return ERR_PTR(-EBADF); + + if (!proc_ns_file(f.file)) + return ERR_PTR(-EINVAL); + + ns = get_proc_ns(file_inode(f.file)); + if (ns->ops->type != CLONE_NEWNS) + return ERR_PTR(-EINVAL); + + mnt_ns = to_mnt_ns(ns); + } else { + mnt_ns = current->nsproxy->mnt_ns; + } + + refcount_inc(&mnt_ns->passive); + return mnt_ns; } SYSCALL_DEFINE4(statmount, const struct mnt_id_req __user *, req, @@ -5269,7 +5329,7 @@ SYSCALL_DEFINE4(statmount, const struct mnt_id_req __user *, req, if (ret) return ret; - ns = grab_requested_mnt_ns(kreq.mnt_ns_id); + ns = grab_requested_mnt_ns(&kreq); if (!ns) return -ENOENT; @@ -5396,7 +5456,7 @@ SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req, if (!kmnt_ids) return -ENOMEM; - ns = grab_requested_mnt_ns(kreq.mnt_ns_id); + ns = grab_requested_mnt_ns(&kreq); if (!ns) return -ENOENT; @@ -5605,7 +5665,7 @@ static bool mnt_already_visible(struct mnt_namespace *ns, /* Only worry about locked mounts */ if (!(child->mnt.mnt_flags & MNT_LOCKED)) continue; - /* Is the directory permanetly empty? */ + /* Is the directory permanently empty? */ if (!is_empty_dir_inode(inode)) goto next; } diff --git a/fs/netfs/Makefile b/fs/netfs/Makefile index 8e6781e0b10b..d08b0bfb6756 100644 --- a/fs/netfs/Makefile +++ b/fs/netfs/Makefile @@ -5,12 +5,14 @@ netfs-y := \ buffered_write.o \ direct_read.o \ direct_write.o \ - io.o \ iterator.o \ locking.o \ main.o \ misc.o \ objects.o \ + read_collect.o \ + read_pgpriv2.o \ + read_retry.o \ write_collect.o \ write_issue.o diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index 27c750d39476..c40e226053cc 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -9,266 +9,388 @@ #include <linux/task_io_accounting_ops.h> #include "internal.h" -/* - * [DEPRECATED] Unlock the folios in a read operation for when the filesystem - * is using PG_private_2 and direct writing to the cache from here rather than - * marking the page for writeback. - * - * Note that we don't touch folio->private in this code. - */ -static void netfs_rreq_unlock_folios_pgpriv2(struct netfs_io_request *rreq, - size_t *account) +static void netfs_cache_expand_readahead(struct netfs_io_request *rreq, + unsigned long long *_start, + unsigned long long *_len, + unsigned long long i_size) { - struct netfs_io_subrequest *subreq; - struct folio *folio; - pgoff_t start_page = rreq->start / PAGE_SIZE; - pgoff_t last_page = ((rreq->start + rreq->len) / PAGE_SIZE) - 1; - bool subreq_failed = false; + struct netfs_cache_resources *cres = &rreq->cache_resources; - XA_STATE(xas, &rreq->mapping->i_pages, start_page); + if (cres->ops && cres->ops->expand_readahead) + cres->ops->expand_readahead(cres, _start, _len, i_size); +} - /* Walk through the pagecache and the I/O request lists simultaneously. - * We may have a mixture of cached and uncached sections and we only - * really want to write out the uncached sections. This is slightly - * complicated by the possibility that we might have huge pages with a - * mixture inside. +static void netfs_rreq_expand(struct netfs_io_request *rreq, + struct readahead_control *ractl) +{ + /* Give the cache a chance to change the request parameters. The + * resultant request must contain the original region. */ - subreq = list_first_entry(&rreq->subrequests, - struct netfs_io_subrequest, rreq_link); - subreq_failed = (subreq->error < 0); + netfs_cache_expand_readahead(rreq, &rreq->start, &rreq->len, rreq->i_size); - trace_netfs_rreq(rreq, netfs_rreq_trace_unlock_pgpriv2); + /* Give the netfs a chance to change the request parameters. The + * resultant request must contain the original region. + */ + if (rreq->netfs_ops->expand_readahead) + rreq->netfs_ops->expand_readahead(rreq); - rcu_read_lock(); - xas_for_each(&xas, folio, last_page) { - loff_t pg_end; - bool pg_failed = false; - bool folio_started = false; + /* Expand the request if the cache wants it to start earlier. Note + * that the expansion may get further extended if the VM wishes to + * insert THPs and the preferred start and/or end wind up in the middle + * of THPs. + * + * If this is the case, however, the THP size should be an integer + * multiple of the cache granule size, so we get a whole number of + * granules to deal with. + */ + if (rreq->start != readahead_pos(ractl) || + rreq->len != readahead_length(ractl)) { + readahead_expand(ractl, rreq->start, rreq->len); + rreq->start = readahead_pos(ractl); + rreq->len = readahead_length(ractl); - if (xas_retry(&xas, folio)) - continue; + trace_netfs_read(rreq, readahead_pos(ractl), readahead_length(ractl), + netfs_read_trace_expanded); + } +} - pg_end = folio_pos(folio) + folio_size(folio) - 1; +/* + * Begin an operation, and fetch the stored zero point value from the cookie if + * available. + */ +static int netfs_begin_cache_read(struct netfs_io_request *rreq, struct netfs_inode *ctx) +{ + return fscache_begin_read_operation(&rreq->cache_resources, netfs_i_cookie(ctx)); +} - for (;;) { - loff_t sreq_end; +/* + * Decant the list of folios to read into a rolling buffer. + */ +static size_t netfs_load_buffer_from_ra(struct netfs_io_request *rreq, + struct folio_queue *folioq) +{ + unsigned int order, nr; + size_t size = 0; + + nr = __readahead_batch(rreq->ractl, (struct page **)folioq->vec.folios, + ARRAY_SIZE(folioq->vec.folios)); + folioq->vec.nr = nr; + for (int i = 0; i < nr; i++) { + struct folio *folio = folioq_folio(folioq, i); + + trace_netfs_folio(folio, netfs_folio_trace_read); + order = folio_order(folio); + folioq->orders[i] = order; + size += PAGE_SIZE << order; + } - if (!subreq) { - pg_failed = true; - break; - } + for (int i = nr; i < folioq_nr_slots(folioq); i++) + folioq_clear(folioq, i); - if (!folio_started && - test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags) && - fscache_operation_valid(&rreq->cache_resources)) { - trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache); - folio_start_private_2(folio); - folio_started = true; - } + return size; +} - pg_failed |= subreq_failed; - sreq_end = subreq->start + subreq->len - 1; - if (pg_end < sreq_end) - break; +/* + * netfs_prepare_read_iterator - Prepare the subreq iterator for I/O + * @subreq: The subrequest to be set up + * + * Prepare the I/O iterator representing the read buffer on a subrequest for + * the filesystem to use for I/O (it can be passed directly to a socket). This + * is intended to be called from the ->issue_read() method once the filesystem + * has trimmed the request to the size it wants. + * + * Returns the limited size if successful and -ENOMEM if insufficient memory + * available. + * + * [!] NOTE: This must be run in the same thread as ->issue_read() was called + * in as we access the readahead_control struct. + */ +static ssize_t netfs_prepare_read_iterator(struct netfs_io_subrequest *subreq) +{ + struct netfs_io_request *rreq = subreq->rreq; + size_t rsize = subreq->len; + + if (subreq->source == NETFS_DOWNLOAD_FROM_SERVER) + rsize = umin(rsize, rreq->io_streams[0].sreq_max_len); + + if (rreq->ractl) { + /* If we don't have sufficient folios in the rolling buffer, + * extract a folioq's worth from the readahead region at a time + * into the buffer. Note that this acquires a ref on each page + * that we will need to release later - but we don't want to do + * that until after we've started the I/O. + */ + while (rreq->submitted < subreq->start + rsize) { + struct folio_queue *tail = rreq->buffer_tail, *new; + size_t added; + + new = kmalloc(sizeof(*new), GFP_NOFS); + if (!new) + return -ENOMEM; + netfs_stat(&netfs_n_folioq); + folioq_init(new); + new->prev = tail; + tail->next = new; + rreq->buffer_tail = new; + added = netfs_load_buffer_from_ra(rreq, new); + rreq->iter.count += added; + rreq->submitted += added; + } + } - *account += subreq->transferred; - if (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) { - subreq = list_next_entry(subreq, rreq_link); - subreq_failed = (subreq->error < 0); - } else { - subreq = NULL; - subreq_failed = false; - } + subreq->len = rsize; + if (unlikely(rreq->io_streams[0].sreq_max_segs)) { + size_t limit = netfs_limit_iter(&rreq->iter, 0, rsize, + rreq->io_streams[0].sreq_max_segs); - if (pg_end == sreq_end) - break; + if (limit < rsize) { + subreq->len = limit; + trace_netfs_sreq(subreq, netfs_sreq_trace_limited); } + } - if (!pg_failed) { - flush_dcache_folio(folio); - folio_mark_uptodate(folio); - } + subreq->io_iter = rreq->iter; - if (!test_bit(NETFS_RREQ_DONT_UNLOCK_FOLIOS, &rreq->flags)) { - if (folio->index == rreq->no_unlock_folio && - test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags)) - _debug("no unlock"); - else - folio_unlock(folio); + if (iov_iter_is_folioq(&subreq->io_iter)) { + if (subreq->io_iter.folioq_slot >= folioq_nr_slots(subreq->io_iter.folioq)) { + subreq->io_iter.folioq = subreq->io_iter.folioq->next; + subreq->io_iter.folioq_slot = 0; } + subreq->curr_folioq = (struct folio_queue *)subreq->io_iter.folioq; + subreq->curr_folioq_slot = subreq->io_iter.folioq_slot; + subreq->curr_folio_order = subreq->curr_folioq->orders[subreq->curr_folioq_slot]; } - rcu_read_unlock(); + + iov_iter_truncate(&subreq->io_iter, subreq->len); + iov_iter_advance(&rreq->iter, subreq->len); + return subreq->len; } -/* - * Unlock the folios in a read operation. We need to set PG_writeback on any - * folios we're going to write back before we unlock them. - * - * Note that if the deprecated NETFS_RREQ_USE_PGPRIV2 is set then we use - * PG_private_2 and do a direct write to the cache from here instead. - */ -void netfs_rreq_unlock_folios(struct netfs_io_request *rreq) +static enum netfs_io_source netfs_cache_prepare_read(struct netfs_io_request *rreq, + struct netfs_io_subrequest *subreq, + loff_t i_size) { - struct netfs_io_subrequest *subreq; - struct netfs_folio *finfo; - struct folio *folio; - pgoff_t start_page = rreq->start / PAGE_SIZE; - pgoff_t last_page = ((rreq->start + rreq->len) / PAGE_SIZE) - 1; - size_t account = 0; - bool subreq_failed = false; + struct netfs_cache_resources *cres = &rreq->cache_resources; - XA_STATE(xas, &rreq->mapping->i_pages, start_page); + if (!cres->ops) + return NETFS_DOWNLOAD_FROM_SERVER; + return cres->ops->prepare_read(subreq, i_size); +} - if (test_bit(NETFS_RREQ_FAILED, &rreq->flags)) { - __clear_bit(NETFS_RREQ_COPY_TO_CACHE, &rreq->flags); - list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { - __clear_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags); - } - } +static void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error, + bool was_async) +{ + struct netfs_io_subrequest *subreq = priv; - /* Handle deprecated PG_private_2 case. */ - if (test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags)) { - netfs_rreq_unlock_folios_pgpriv2(rreq, &account); - goto out; + if (transferred_or_error < 0) { + netfs_read_subreq_terminated(subreq, transferred_or_error, was_async); + return; } - /* Walk through the pagecache and the I/O request lists simultaneously. - * We may have a mixture of cached and uncached sections and we only - * really want to write out the uncached sections. This is slightly - * complicated by the possibility that we might have huge pages with a - * mixture inside. - */ - subreq = list_first_entry(&rreq->subrequests, - struct netfs_io_subrequest, rreq_link); - subreq_failed = (subreq->error < 0); - - trace_netfs_rreq(rreq, netfs_rreq_trace_unlock); + if (transferred_or_error > 0) + subreq->transferred += transferred_or_error; + netfs_read_subreq_terminated(subreq, 0, was_async); +} - rcu_read_lock(); - xas_for_each(&xas, folio, last_page) { - loff_t pg_end; - bool pg_failed = false; - bool wback_to_cache = false; +/* + * Issue a read against the cache. + * - Eats the caller's ref on subreq. + */ +static void netfs_read_cache_to_pagecache(struct netfs_io_request *rreq, + struct netfs_io_subrequest *subreq) +{ + struct netfs_cache_resources *cres = &rreq->cache_resources; - if (xas_retry(&xas, folio)) - continue; + netfs_stat(&netfs_n_rh_read); + cres->ops->read(cres, subreq->start, &subreq->io_iter, NETFS_READ_HOLE_IGNORE, + netfs_cache_read_terminated, subreq); +} - pg_end = folio_pos(folio) + folio_size(folio) - 1; +/* + * Perform a read to the pagecache from a series of sources of different types, + * slicing up the region to be read according to available cache blocks and + * network rsize. + */ +static void netfs_read_to_pagecache(struct netfs_io_request *rreq) +{ + struct netfs_inode *ictx = netfs_inode(rreq->inode); + unsigned long long start = rreq->start; + ssize_t size = rreq->len; + int ret = 0; + + atomic_inc(&rreq->nr_outstanding); + + do { + struct netfs_io_subrequest *subreq; + enum netfs_io_source source = NETFS_DOWNLOAD_FROM_SERVER; + ssize_t slice; + + subreq = netfs_alloc_subrequest(rreq); + if (!subreq) { + ret = -ENOMEM; + break; + } - for (;;) { - loff_t sreq_end; + subreq->start = start; + subreq->len = size; + + atomic_inc(&rreq->nr_outstanding); + spin_lock_bh(&rreq->lock); + list_add_tail(&subreq->rreq_link, &rreq->subrequests); + subreq->prev_donated = rreq->prev_donated; + rreq->prev_donated = 0; + trace_netfs_sreq(subreq, netfs_sreq_trace_added); + spin_unlock_bh(&rreq->lock); + + source = netfs_cache_prepare_read(rreq, subreq, rreq->i_size); + subreq->source = source; + if (source == NETFS_DOWNLOAD_FROM_SERVER) { + unsigned long long zp = umin(ictx->zero_point, rreq->i_size); + size_t len = subreq->len; + + if (subreq->start >= zp) { + subreq->source = source = NETFS_FILL_WITH_ZEROES; + goto fill_with_zeroes; + } - if (!subreq) { - pg_failed = true; + if (len > zp - subreq->start) + len = zp - subreq->start; + if (len == 0) { + pr_err("ZERO-LEN READ: R=%08x[%x] l=%zx/%zx s=%llx z=%llx i=%llx", + rreq->debug_id, subreq->debug_index, + subreq->len, size, + subreq->start, ictx->zero_point, rreq->i_size); break; } + subreq->len = len; + + netfs_stat(&netfs_n_rh_download); + if (rreq->netfs_ops->prepare_read) { + ret = rreq->netfs_ops->prepare_read(subreq); + if (ret < 0) { + atomic_dec(&rreq->nr_outstanding); + netfs_put_subrequest(subreq, false, + netfs_sreq_trace_put_cancel); + break; + } + trace_netfs_sreq(subreq, netfs_sreq_trace_prepare); + } - wback_to_cache |= test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags); - pg_failed |= subreq_failed; - sreq_end = subreq->start + subreq->len - 1; - if (pg_end < sreq_end) + slice = netfs_prepare_read_iterator(subreq); + if (slice < 0) { + atomic_dec(&rreq->nr_outstanding); + netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_cancel); + ret = slice; break; - - account += subreq->transferred; - if (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) { - subreq = list_next_entry(subreq, rreq_link); - subreq_failed = (subreq->error < 0); - } else { - subreq = NULL; - subreq_failed = false; } - if (pg_end == sreq_end) - break; + rreq->netfs_ops->issue_read(subreq); + goto done; } - if (!pg_failed) { - flush_dcache_folio(folio); - finfo = netfs_folio_info(folio); - if (finfo) { - trace_netfs_folio(folio, netfs_folio_trace_filled_gaps); - if (finfo->netfs_group) - folio_change_private(folio, finfo->netfs_group); - else - folio_detach_private(folio); - kfree(finfo); - } - folio_mark_uptodate(folio); - if (wback_to_cache && !WARN_ON_ONCE(folio_get_private(folio) != NULL)) { - trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache); - folio_attach_private(folio, NETFS_FOLIO_COPY_TO_CACHE); - filemap_dirty_folio(folio->mapping, folio); - } + fill_with_zeroes: + if (source == NETFS_FILL_WITH_ZEROES) { + subreq->source = NETFS_FILL_WITH_ZEROES; + trace_netfs_sreq(subreq, netfs_sreq_trace_submit); + netfs_stat(&netfs_n_rh_zero); + slice = netfs_prepare_read_iterator(subreq); + __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); + netfs_read_subreq_terminated(subreq, 0, false); + goto done; } - if (!test_bit(NETFS_RREQ_DONT_UNLOCK_FOLIOS, &rreq->flags)) { - if (folio->index == rreq->no_unlock_folio && - test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags)) - _debug("no unlock"); - else - folio_unlock(folio); + if (source == NETFS_READ_FROM_CACHE) { + trace_netfs_sreq(subreq, netfs_sreq_trace_submit); + slice = netfs_prepare_read_iterator(subreq); + netfs_read_cache_to_pagecache(rreq, subreq); + goto done; } - } - rcu_read_unlock(); -out: - task_io_account_read(account); - if (rreq->netfs_ops->done) - rreq->netfs_ops->done(rreq); -} + pr_err("Unexpected read source %u\n", source); + WARN_ON_ONCE(1); + break; -static void netfs_cache_expand_readahead(struct netfs_io_request *rreq, - unsigned long long *_start, - unsigned long long *_len, - unsigned long long i_size) -{ - struct netfs_cache_resources *cres = &rreq->cache_resources; + done: + size -= slice; + start += slice; + cond_resched(); + } while (size > 0); - if (cres->ops && cres->ops->expand_readahead) - cres->ops->expand_readahead(cres, _start, _len, i_size); + if (atomic_dec_and_test(&rreq->nr_outstanding)) + netfs_rreq_terminated(rreq, false); + + /* Defer error return as we may need to wait for outstanding I/O. */ + cmpxchg(&rreq->error, 0, ret); } -static void netfs_rreq_expand(struct netfs_io_request *rreq, - struct readahead_control *ractl) +/* + * Wait for the read operation to complete, successfully or otherwise. + */ +static int netfs_wait_for_read(struct netfs_io_request *rreq) { - /* Give the cache a chance to change the request parameters. The - * resultant request must contain the original region. - */ - netfs_cache_expand_readahead(rreq, &rreq->start, &rreq->len, rreq->i_size); + int ret; - /* Give the netfs a chance to change the request parameters. The - * resultant request must contain the original region. - */ - if (rreq->netfs_ops->expand_readahead) - rreq->netfs_ops->expand_readahead(rreq); + trace_netfs_rreq(rreq, netfs_rreq_trace_wait_ip); + wait_on_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS, TASK_UNINTERRUPTIBLE); + ret = rreq->error; + if (ret == 0 && rreq->submitted < rreq->len) { + trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_read); + ret = -EIO; + } - /* Expand the request if the cache wants it to start earlier. Note - * that the expansion may get further extended if the VM wishes to - * insert THPs and the preferred start and/or end wind up in the middle - * of THPs. - * - * If this is the case, however, the THP size should be an integer - * multiple of the cache granule size, so we get a whole number of - * granules to deal with. - */ - if (rreq->start != readahead_pos(ractl) || - rreq->len != readahead_length(ractl)) { - readahead_expand(ractl, rreq->start, rreq->len); - rreq->start = readahead_pos(ractl); - rreq->len = readahead_length(ractl); + return ret; +} - trace_netfs_read(rreq, readahead_pos(ractl), readahead_length(ractl), - netfs_read_trace_expanded); - } +/* + * Set up the initial folioq of buffer folios in the rolling buffer and set the + * iterator to refer to it. + */ +static int netfs_prime_buffer(struct netfs_io_request *rreq) +{ + struct folio_queue *folioq; + size_t added; + + folioq = kmalloc(sizeof(*folioq), GFP_KERNEL); + if (!folioq) + return -ENOMEM; + netfs_stat(&netfs_n_folioq); + folioq_init(folioq); + rreq->buffer = folioq; + rreq->buffer_tail = folioq; + rreq->submitted = rreq->start; + iov_iter_folio_queue(&rreq->iter, ITER_DEST, folioq, 0, 0, 0); + + added = netfs_load_buffer_from_ra(rreq, folioq); + rreq->iter.count += added; + rreq->submitted += added; + return 0; } /* - * Begin an operation, and fetch the stored zero point value from the cookie if - * available. + * Drop the ref on each folio that we inherited from the VM readahead code. We + * still have the folio locks to pin the page until we complete the I/O. + * + * Note that we can't just release the batch in each queue struct as we use the + * occupancy count in other places. */ -static int netfs_begin_cache_read(struct netfs_io_request *rreq, struct netfs_inode *ctx) +static void netfs_put_ra_refs(struct folio_queue *folioq) { - return fscache_begin_read_operation(&rreq->cache_resources, netfs_i_cookie(ctx)); + struct folio_batch fbatch; + + folio_batch_init(&fbatch); + while (folioq) { + for (unsigned int slot = 0; slot < folioq_count(folioq); slot++) { + struct folio *folio = folioq_folio(folioq, slot); + if (!folio) + continue; + trace_netfs_folio(folio, netfs_folio_trace_read_put); + if (!folio_batch_add(&fbatch, folio)) + folio_batch_release(&fbatch); + } + folioq = folioq->next; + } + + folio_batch_release(&fbatch); } /** @@ -289,22 +411,17 @@ static int netfs_begin_cache_read(struct netfs_io_request *rreq, struct netfs_in void netfs_readahead(struct readahead_control *ractl) { struct netfs_io_request *rreq; - struct netfs_inode *ctx = netfs_inode(ractl->mapping->host); + struct netfs_inode *ictx = netfs_inode(ractl->mapping->host); + unsigned long long start = readahead_pos(ractl); + size_t size = readahead_length(ractl); int ret; - _enter("%lx,%x", readahead_index(ractl), readahead_count(ractl)); - - if (readahead_count(ractl) == 0) - return; - - rreq = netfs_alloc_request(ractl->mapping, ractl->file, - readahead_pos(ractl), - readahead_length(ractl), + rreq = netfs_alloc_request(ractl->mapping, ractl->file, start, size, NETFS_READAHEAD); if (IS_ERR(rreq)) return; - ret = netfs_begin_cache_read(rreq, ctx); + ret = netfs_begin_cache_read(rreq, ictx); if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) goto cleanup_free; @@ -314,18 +431,15 @@ void netfs_readahead(struct readahead_control *ractl) netfs_rreq_expand(rreq, ractl); - /* Set up the output buffer */ - iov_iter_xarray(&rreq->iter, ITER_DEST, &ractl->mapping->i_pages, - rreq->start, rreq->len); + rreq->ractl = ractl; + if (netfs_prime_buffer(rreq) < 0) + goto cleanup_free; + netfs_read_to_pagecache(rreq); - /* Drop the refs on the folios here rather than in the cache or - * filesystem. The locks will be dropped in netfs_rreq_unlock(). - */ - while (readahead_folio(ractl)) - ; + /* Release the folio refs whilst we're waiting for the I/O. */ + netfs_put_ra_refs(rreq->buffer); - netfs_begin_read(rreq, false); - netfs_put_request(rreq, false, netfs_rreq_trace_put_return); + netfs_put_request(rreq, true, netfs_rreq_trace_put_return); return; cleanup_free: @@ -334,6 +448,117 @@ cleanup_free: } EXPORT_SYMBOL(netfs_readahead); +/* + * Create a rolling buffer with a single occupying folio. + */ +static int netfs_create_singular_buffer(struct netfs_io_request *rreq, struct folio *folio) +{ + struct folio_queue *folioq; + + folioq = kmalloc(sizeof(*folioq), GFP_KERNEL); + if (!folioq) + return -ENOMEM; + + netfs_stat(&netfs_n_folioq); + folioq_init(folioq); + folioq_append(folioq, folio); + BUG_ON(folioq_folio(folioq, 0) != folio); + BUG_ON(folioq_folio_order(folioq, 0) != folio_order(folio)); + rreq->buffer = folioq; + rreq->buffer_tail = folioq; + rreq->submitted = rreq->start + rreq->len; + iov_iter_folio_queue(&rreq->iter, ITER_DEST, folioq, 0, 0, rreq->len); + rreq->ractl = (struct readahead_control *)1UL; + return 0; +} + +/* + * Read into gaps in a folio partially filled by a streaming write. + */ +static int netfs_read_gaps(struct file *file, struct folio *folio) +{ + struct netfs_io_request *rreq; + struct address_space *mapping = folio->mapping; + struct netfs_folio *finfo = netfs_folio_info(folio); + struct netfs_inode *ctx = netfs_inode(mapping->host); + struct folio *sink = NULL; + struct bio_vec *bvec; + unsigned int from = finfo->dirty_offset; + unsigned int to = from + finfo->dirty_len; + unsigned int off = 0, i = 0; + size_t flen = folio_size(folio); + size_t nr_bvec = flen / PAGE_SIZE + 2; + size_t part; + int ret; + + _enter("%lx", folio->index); + + rreq = netfs_alloc_request(mapping, file, folio_pos(folio), flen, NETFS_READ_GAPS); + if (IS_ERR(rreq)) { + ret = PTR_ERR(rreq); + goto alloc_error; + } + + ret = netfs_begin_cache_read(rreq, ctx); + if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) + goto discard; + + netfs_stat(&netfs_n_rh_read_folio); + trace_netfs_read(rreq, rreq->start, rreq->len, netfs_read_trace_read_gaps); + + /* Fiddle the buffer so that a gap at the beginning and/or a gap at the + * end get copied to, but the middle is discarded. + */ + ret = -ENOMEM; + bvec = kmalloc_array(nr_bvec, sizeof(*bvec), GFP_KERNEL); + if (!bvec) + goto discard; + + sink = folio_alloc(GFP_KERNEL, 0); + if (!sink) { + kfree(bvec); + goto discard; + } + + trace_netfs_folio(folio, netfs_folio_trace_read_gaps); + + rreq->direct_bv = bvec; + rreq->direct_bv_count = nr_bvec; + if (from > 0) { + bvec_set_folio(&bvec[i++], folio, from, 0); + off = from; + } + while (off < to) { + part = min_t(size_t, to - off, PAGE_SIZE); + bvec_set_folio(&bvec[i++], sink, part, 0); + off += part; + } + if (to < flen) + bvec_set_folio(&bvec[i++], folio, flen - to, to); + iov_iter_bvec(&rreq->iter, ITER_DEST, bvec, i, rreq->len); + rreq->submitted = rreq->start + flen; + + netfs_read_to_pagecache(rreq); + + if (sink) + folio_put(sink); + + ret = netfs_wait_for_read(rreq); + if (ret == 0) { + flush_dcache_folio(folio); + folio_mark_uptodate(folio); + } + folio_unlock(folio); + netfs_put_request(rreq, false, netfs_rreq_trace_put_return); + return ret < 0 ? ret : 0; + +discard: + netfs_put_request(rreq, false, netfs_rreq_trace_put_discard); +alloc_error: + folio_unlock(folio); + return ret; +} + /** * netfs_read_folio - Helper to manage a read_folio request * @file: The file to read from @@ -353,9 +578,13 @@ int netfs_read_folio(struct file *file, struct folio *folio) struct address_space *mapping = folio->mapping; struct netfs_io_request *rreq; struct netfs_inode *ctx = netfs_inode(mapping->host); - struct folio *sink = NULL; int ret; + if (folio_test_dirty(folio)) { + trace_netfs_folio(folio, netfs_folio_trace_read_gaps); + return netfs_read_gaps(file, folio); + } + _enter("%lx", folio->index); rreq = netfs_alloc_request(mapping, file, @@ -374,54 +603,12 @@ int netfs_read_folio(struct file *file, struct folio *folio) trace_netfs_read(rreq, rreq->start, rreq->len, netfs_read_trace_readpage); /* Set up the output buffer */ - if (folio_test_dirty(folio)) { - /* Handle someone trying to read from an unflushed streaming - * write. We fiddle the buffer so that a gap at the beginning - * and/or a gap at the end get copied to, but the middle is - * discarded. - */ - struct netfs_folio *finfo = netfs_folio_info(folio); - struct bio_vec *bvec; - unsigned int from = finfo->dirty_offset; - unsigned int to = from + finfo->dirty_len; - unsigned int off = 0, i = 0; - size_t flen = folio_size(folio); - size_t nr_bvec = flen / PAGE_SIZE + 2; - size_t part; - - ret = -ENOMEM; - bvec = kmalloc_array(nr_bvec, sizeof(*bvec), GFP_KERNEL); - if (!bvec) - goto discard; - - sink = folio_alloc(GFP_KERNEL, 0); - if (!sink) - goto discard; - - trace_netfs_folio(folio, netfs_folio_trace_read_gaps); - - rreq->direct_bv = bvec; - rreq->direct_bv_count = nr_bvec; - if (from > 0) { - bvec_set_folio(&bvec[i++], folio, from, 0); - off = from; - } - while (off < to) { - part = min_t(size_t, to - off, PAGE_SIZE); - bvec_set_folio(&bvec[i++], sink, part, 0); - off += part; - } - if (to < flen) - bvec_set_folio(&bvec[i++], folio, flen - to, to); - iov_iter_bvec(&rreq->iter, ITER_DEST, bvec, i, rreq->len); - } else { - iov_iter_xarray(&rreq->iter, ITER_DEST, &mapping->i_pages, - rreq->start, rreq->len); - } + ret = netfs_create_singular_buffer(rreq, folio); + if (ret < 0) + goto discard; - ret = netfs_begin_read(rreq, true); - if (sink) - folio_put(sink); + netfs_read_to_pagecache(rreq); + ret = netfs_wait_for_read(rreq); netfs_put_request(rreq, false, netfs_rreq_trace_put_return); return ret < 0 ? ret : 0; @@ -494,13 +681,10 @@ zero_out: * * Pre-read data for a write-begin request by drawing data from the cache if * possible, or the netfs if not. Space beyond the EOF is zero-filled. - * Multiple I/O requests from different sources will get munged together. If - * necessary, the readahead window can be expanded in either direction to a - * more convenient alighment for RPC efficiency or to make storage in the cache - * feasible. + * Multiple I/O requests from different sources will get munged together. * * The calling netfs must provide a table of operations, only one of which, - * issue_op, is mandatory. + * issue_read, is mandatory. * * The check_write_begin() operation can be provided to check for and flush * conflicting writes once the folio is grabbed and locked. It is passed a @@ -528,8 +712,6 @@ int netfs_write_begin(struct netfs_inode *ctx, pgoff_t index = pos >> PAGE_SHIFT; int ret; - DEFINE_READAHEAD(ractl, file, NULL, mapping, index); - retry: folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN, mapping_gfp_mask(mapping)); @@ -577,22 +759,13 @@ retry: netfs_stat(&netfs_n_rh_write_begin); trace_netfs_read(rreq, pos, len, netfs_read_trace_write_begin); - /* Expand the request to meet caching requirements and download - * preferences. - */ - ractl._nr_pages = folio_nr_pages(folio); - netfs_rreq_expand(rreq, &ractl); - /* Set up the output buffer */ - iov_iter_xarray(&rreq->iter, ITER_DEST, &mapping->i_pages, - rreq->start, rreq->len); - - /* We hold the folio locks, so we can drop the references */ - folio_get(folio); - while (readahead_folio(&ractl)) - ; + ret = netfs_create_singular_buffer(rreq, folio); + if (ret < 0) + goto error_put; - ret = netfs_begin_read(rreq, true); + netfs_read_to_pagecache(rreq); + ret = netfs_wait_for_read(rreq); if (ret < 0) goto error; netfs_put_request(rreq, false, netfs_rreq_trace_put_return); @@ -652,10 +825,13 @@ int netfs_prefetch_for_write(struct file *file, struct folio *folio, trace_netfs_read(rreq, start, flen, netfs_read_trace_prefetch_for_write); /* Set up the output buffer */ - iov_iter_xarray(&rreq->iter, ITER_DEST, &mapping->i_pages, - rreq->start, rreq->len); + ret = netfs_create_singular_buffer(rreq, folio); + if (ret < 0) + goto error_put; - ret = netfs_begin_read(rreq, true); + folioq_mark2(rreq->buffer, 0); + netfs_read_to_pagecache(rreq); + ret = netfs_wait_for_read(rreq); netfs_put_request(rreq, false, netfs_rreq_trace_put_return); return ret; diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c index ca53c5d1622e..d7eae597e54d 100644 --- a/fs/netfs/buffered_write.c +++ b/fs/netfs/buffered_write.c @@ -13,91 +13,22 @@ #include <linux/pagevec.h> #include "internal.h" -/* - * Determined write method. Adjust netfs_folio_traces if this is changed. - */ -enum netfs_how_to_modify { - NETFS_FOLIO_IS_UPTODATE, /* Folio is uptodate already */ - NETFS_JUST_PREFETCH, /* We have to read the folio anyway */ - NETFS_WHOLE_FOLIO_MODIFY, /* We're going to overwrite the whole folio */ - NETFS_MODIFY_AND_CLEAR, /* We can assume there is no data to be downloaded. */ - NETFS_STREAMING_WRITE, /* Store incomplete data in non-uptodate page. */ - NETFS_STREAMING_WRITE_CONT, /* Continue streaming write. */ - NETFS_FLUSH_CONTENT, /* Flush incompatible content. */ -}; - -static void netfs_set_group(struct folio *folio, struct netfs_group *netfs_group) +static void __netfs_set_group(struct folio *folio, struct netfs_group *netfs_group) { - void *priv = folio_get_private(folio); - - if (netfs_group && (!priv || priv == NETFS_FOLIO_COPY_TO_CACHE)) + if (netfs_group) folio_attach_private(folio, netfs_get_group(netfs_group)); - else if (!netfs_group && priv == NETFS_FOLIO_COPY_TO_CACHE) - folio_detach_private(folio); } -/* - * Decide how we should modify a folio. We might be attempting to do - * write-streaming, in which case we don't want to a local RMW cycle if we can - * avoid it. If we're doing local caching or content crypto, we award that - * priority over avoiding RMW. If the file is open readably, then we also - * assume that we may want to read what we wrote. - */ -static enum netfs_how_to_modify netfs_how_to_modify(struct netfs_inode *ctx, - struct file *file, - struct folio *folio, - void *netfs_group, - size_t flen, - size_t offset, - size_t len, - bool maybe_trouble) +static void netfs_set_group(struct folio *folio, struct netfs_group *netfs_group) { - struct netfs_folio *finfo = netfs_folio_info(folio); - struct netfs_group *group = netfs_folio_group(folio); - loff_t pos = folio_pos(folio); - - _enter(""); - - if (group != netfs_group && group != NETFS_FOLIO_COPY_TO_CACHE) - return NETFS_FLUSH_CONTENT; - - if (folio_test_uptodate(folio)) - return NETFS_FOLIO_IS_UPTODATE; - - if (pos >= ctx->zero_point) - return NETFS_MODIFY_AND_CLEAR; - - if (!maybe_trouble && offset == 0 && len >= flen) - return NETFS_WHOLE_FOLIO_MODIFY; - - if (file->f_mode & FMODE_READ) - goto no_write_streaming; - - if (netfs_is_cache_enabled(ctx)) { - /* We don't want to get a streaming write on a file that loses - * caching service temporarily because the backing store got - * culled. - */ - goto no_write_streaming; - } + void *priv = folio_get_private(folio); - if (!finfo) - return NETFS_STREAMING_WRITE; - - /* We can continue a streaming write only if it continues on from the - * previous. If it overlaps, we must flush lest we suffer a partial - * copy and disjoint dirty regions. - */ - if (offset == finfo->dirty_offset + finfo->dirty_len) - return NETFS_STREAMING_WRITE_CONT; - return NETFS_FLUSH_CONTENT; - -no_write_streaming: - if (finfo) { - netfs_stat(&netfs_n_wh_wstream_conflict); - return NETFS_FLUSH_CONTENT; + if (unlikely(priv != netfs_group)) { + if (netfs_group && (!priv || priv == NETFS_FOLIO_COPY_TO_CACHE)) + folio_attach_private(folio, netfs_get_group(netfs_group)); + else if (!netfs_group && priv == NETFS_FOLIO_COPY_TO_CACHE) + folio_detach_private(folio); } - return NETFS_JUST_PREFETCH; } /* @@ -177,13 +108,10 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, .range_end = iocb->ki_pos + iter->count, }; struct netfs_io_request *wreq = NULL; - struct netfs_folio *finfo; - struct folio *folio, *writethrough = NULL; - enum netfs_how_to_modify howto; - enum netfs_folio_trace trace; + struct folio *folio = NULL, *writethrough = NULL; unsigned int bdp_flags = (iocb->ki_flags & IOCB_NOWAIT) ? BDP_ASYNC : 0; ssize_t written = 0, ret, ret2; - loff_t i_size, pos = iocb->ki_pos, from, to; + loff_t i_size, pos = iocb->ki_pos; size_t max_chunk = mapping_max_folio_size(mapping); bool maybe_trouble = false; @@ -213,15 +141,14 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, } do { + struct netfs_folio *finfo; + struct netfs_group *group; + unsigned long long fpos; size_t flen; size_t offset; /* Offset into pagecache folio */ size_t part; /* Bytes to write to folio */ size_t copied; /* Bytes copied from user */ - ret = balance_dirty_pages_ratelimited_flags(mapping, bdp_flags); - if (unlikely(ret < 0)) - break; - offset = pos & (max_chunk - 1); part = min(max_chunk - offset, iov_iter_count(iter)); @@ -247,7 +174,8 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, } flen = folio_size(folio); - offset = pos & (flen - 1); + fpos = folio_pos(folio); + offset = pos - fpos; part = min_t(size_t, flen - offset, part); /* Wait for writeback to complete. The writeback engine owns @@ -265,71 +193,52 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, goto error_folio_unlock; } - /* See if we need to prefetch the area we're going to modify. - * We need to do this before we get a lock on the folio in case - * there's more than one writer competing for the same cache - * block. + /* Decide how we should modify a folio. We might be attempting + * to do write-streaming, in which case we don't want to a + * local RMW cycle if we can avoid it. If we're doing local + * caching or content crypto, we award that priority over + * avoiding RMW. If the file is open readably, then we also + * assume that we may want to read what we wrote. */ - howto = netfs_how_to_modify(ctx, file, folio, netfs_group, - flen, offset, part, maybe_trouble); - _debug("howto %u", howto); - switch (howto) { - case NETFS_JUST_PREFETCH: - ret = netfs_prefetch_for_write(file, folio, offset, part); - if (ret < 0) { - _debug("prefetch = %zd", ret); - goto error_folio_unlock; - } - break; - case NETFS_FOLIO_IS_UPTODATE: - case NETFS_WHOLE_FOLIO_MODIFY: - case NETFS_STREAMING_WRITE_CONT: - break; - case NETFS_MODIFY_AND_CLEAR: - zero_user_segment(&folio->page, 0, offset); - break; - case NETFS_STREAMING_WRITE: - ret = -EIO; - if (WARN_ON(folio_get_private(folio))) - goto error_folio_unlock; - break; - case NETFS_FLUSH_CONTENT: - trace_netfs_folio(folio, netfs_flush_content); - from = folio_pos(folio); - to = from + folio_size(folio) - 1; - folio_unlock(folio); - folio_put(folio); - ret = filemap_write_and_wait_range(mapping, from, to); - if (ret < 0) - goto error_folio_unlock; - continue; - } - - if (mapping_writably_mapped(mapping)) - flush_dcache_folio(folio); - - copied = copy_folio_from_iter_atomic(folio, offset, part, iter); - - flush_dcache_folio(folio); - - /* Deal with a (partially) failed copy */ - if (copied == 0) { - ret = -EFAULT; - goto error_folio_unlock; + finfo = netfs_folio_info(folio); + group = netfs_folio_group(folio); + + if (unlikely(group != netfs_group) && + group != NETFS_FOLIO_COPY_TO_CACHE) + goto flush_content; + + if (folio_test_uptodate(folio)) { + if (mapping_writably_mapped(mapping)) + flush_dcache_folio(folio); + copied = copy_folio_from_iter_atomic(folio, offset, part, iter); + if (unlikely(copied == 0)) + goto copy_failed; + netfs_set_group(folio, netfs_group); + trace_netfs_folio(folio, netfs_folio_is_uptodate); + goto copied; } - trace = (enum netfs_folio_trace)howto; - switch (howto) { - case NETFS_FOLIO_IS_UPTODATE: - case NETFS_JUST_PREFETCH: - netfs_set_group(folio, netfs_group); - break; - case NETFS_MODIFY_AND_CLEAR: + /* If the page is above the zero-point then we assume that the + * server would just return a block of zeros or a short read if + * we try to read it. + */ + if (fpos >= ctx->zero_point) { + zero_user_segment(&folio->page, 0, offset); + copied = copy_folio_from_iter_atomic(folio, offset, part, iter); + if (unlikely(copied == 0)) + goto copy_failed; zero_user_segment(&folio->page, offset + copied, flen); - netfs_set_group(folio, netfs_group); + __netfs_set_group(folio, netfs_group); folio_mark_uptodate(folio); - break; - case NETFS_WHOLE_FOLIO_MODIFY: + trace_netfs_folio(folio, netfs_modify_and_clear); + goto copied; + } + + /* See if we can write a whole folio in one go. */ + if (!maybe_trouble && offset == 0 && part >= flen) { + copied = copy_folio_from_iter_atomic(folio, offset, part, iter); + if (unlikely(copied == 0)) + goto copy_failed; if (unlikely(copied < part)) { maybe_trouble = true; iov_iter_revert(iter, copied); @@ -337,16 +246,53 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, folio_unlock(folio); goto retry; } - netfs_set_group(folio, netfs_group); + __netfs_set_group(folio, netfs_group); folio_mark_uptodate(folio); - break; - case NETFS_STREAMING_WRITE: + trace_netfs_folio(folio, netfs_whole_folio_modify); + goto copied; + } + + /* We don't want to do a streaming write on a file that loses + * caching service temporarily because the backing store got + * culled and we don't really want to get a streaming write on + * a file that's open for reading as ->read_folio() then has to + * be able to flush it. + */ + if ((file->f_mode & FMODE_READ) || + netfs_is_cache_enabled(ctx)) { + if (finfo) { + netfs_stat(&netfs_n_wh_wstream_conflict); + goto flush_content; + } + ret = netfs_prefetch_for_write(file, folio, offset, part); + if (ret < 0) { + _debug("prefetch = %zd", ret); + goto error_folio_unlock; + } + /* Note that copy-to-cache may have been set. */ + + copied = copy_folio_from_iter_atomic(folio, offset, part, iter); + if (unlikely(copied == 0)) + goto copy_failed; + netfs_set_group(folio, netfs_group); + trace_netfs_folio(folio, netfs_just_prefetch); + goto copied; + } + + if (!finfo) { + ret = -EIO; + if (WARN_ON(folio_get_private(folio))) + goto error_folio_unlock; + copied = copy_folio_from_iter_atomic(folio, offset, part, iter); + if (unlikely(copied == 0)) + goto copy_failed; if (offset == 0 && copied == flen) { - netfs_set_group(folio, netfs_group); + __netfs_set_group(folio, netfs_group); folio_mark_uptodate(folio); - trace = netfs_streaming_filled_page; - break; + trace_netfs_folio(folio, netfs_streaming_filled_page); + goto copied; } + finfo = kzalloc(sizeof(*finfo), GFP_KERNEL); if (!finfo) { iov_iter_revert(iter, copied); @@ -358,9 +304,18 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, finfo->dirty_len = copied; folio_attach_private(folio, (void *)((unsigned long)finfo | NETFS_FOLIO_INFO)); - break; - case NETFS_STREAMING_WRITE_CONT: - finfo = netfs_folio_info(folio); + trace_netfs_folio(folio, netfs_streaming_write); + goto copied; + } + + /* We can continue a streaming write only if it continues on + * from the previous. If it overlaps, we must flush lest we + * suffer a partial copy and disjoint dirty regions. + */ + if (offset == finfo->dirty_offset + finfo->dirty_len) { + copied = copy_folio_from_iter_atomic(folio, offset, part, iter); + if (unlikely(copied == 0)) + goto copy_failed; finfo->dirty_len += copied; if (finfo->dirty_offset == 0 && finfo->dirty_len == flen) { if (finfo->netfs_group) @@ -369,17 +324,25 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, folio_detach_private(folio); folio_mark_uptodate(folio); kfree(finfo); - trace = netfs_streaming_cont_filled_page; + trace_netfs_folio(folio, netfs_streaming_cont_filled_page); + } else { + trace_netfs_folio(folio, netfs_streaming_write_cont); } - break; - default: - WARN(true, "Unexpected modify type %u ix=%lx\n", - howto, folio->index); - ret = -EIO; - goto error_folio_unlock; + goto copied; } - trace_netfs_folio(folio, trace); + /* Incompatible write; flush the folio and try again. */ + flush_content: + trace_netfs_folio(folio, netfs_flush_content); + folio_unlock(folio); + folio_put(folio); + ret = filemap_write_and_wait_range(mapping, fpos, fpos + flen - 1); + if (ret < 0) + goto error_folio_unlock; + continue; + + copied: + flush_dcache_folio(folio); /* Update the inode size if we moved the EOF marker */ pos += copied; @@ -401,12 +364,22 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, folio_put(folio); folio = NULL; + ret = balance_dirty_pages_ratelimited_flags(mapping, bdp_flags); + if (unlikely(ret < 0)) + break; + cond_resched(); } while (iov_iter_count(iter)); out: - if (likely(written) && ctx->ops->post_modify) - ctx->ops->post_modify(inode); + if (likely(written)) { + /* Set indication that ctime and mtime got updated in case + * close is deferred. + */ + set_bit(NETFS_ICTX_MODIFIED_ATTR, &ctx->flags); + if (unlikely(ctx->ops->post_modify)) + ctx->ops->post_modify(inode); + } if (unlikely(wreq)) { ret2 = netfs_end_writethrough(wreq, &wbc, writethrough); @@ -421,6 +394,8 @@ out: _leave(" = %zd [%zd]", written, ret); return written ? written : ret; +copy_failed: + ret = -EFAULT; error_folio_unlock: folio_unlock(folio); folio_put(folio); diff --git a/fs/netfs/direct_read.c b/fs/netfs/direct_read.c index 10a1e4da6bda..b1a66a6e6bc2 100644 --- a/fs/netfs/direct_read.c +++ b/fs/netfs/direct_read.c @@ -16,6 +16,143 @@ #include <linux/netfs.h> #include "internal.h" +static void netfs_prepare_dio_read_iterator(struct netfs_io_subrequest *subreq) +{ + struct netfs_io_request *rreq = subreq->rreq; + size_t rsize; + + rsize = umin(subreq->len, rreq->io_streams[0].sreq_max_len); + subreq->len = rsize; + + if (unlikely(rreq->io_streams[0].sreq_max_segs)) { + size_t limit = netfs_limit_iter(&rreq->iter, 0, rsize, + rreq->io_streams[0].sreq_max_segs); + + if (limit < rsize) { + subreq->len = limit; + trace_netfs_sreq(subreq, netfs_sreq_trace_limited); + } + } + + trace_netfs_sreq(subreq, netfs_sreq_trace_prepare); + + subreq->io_iter = rreq->iter; + iov_iter_truncate(&subreq->io_iter, subreq->len); + iov_iter_advance(&rreq->iter, subreq->len); +} + +/* + * Perform a read to a buffer from the server, slicing up the region to be read + * according to the network rsize. + */ +static int netfs_dispatch_unbuffered_reads(struct netfs_io_request *rreq) +{ + unsigned long long start = rreq->start; + ssize_t size = rreq->len; + int ret = 0; + + atomic_set(&rreq->nr_outstanding, 1); + + do { + struct netfs_io_subrequest *subreq; + ssize_t slice; + + subreq = netfs_alloc_subrequest(rreq); + if (!subreq) { + ret = -ENOMEM; + break; + } + + subreq->source = NETFS_DOWNLOAD_FROM_SERVER; + subreq->start = start; + subreq->len = size; + + atomic_inc(&rreq->nr_outstanding); + spin_lock_bh(&rreq->lock); + list_add_tail(&subreq->rreq_link, &rreq->subrequests); + subreq->prev_donated = rreq->prev_donated; + rreq->prev_donated = 0; + trace_netfs_sreq(subreq, netfs_sreq_trace_added); + spin_unlock_bh(&rreq->lock); + + netfs_stat(&netfs_n_rh_download); + if (rreq->netfs_ops->prepare_read) { + ret = rreq->netfs_ops->prepare_read(subreq); + if (ret < 0) { + atomic_dec(&rreq->nr_outstanding); + netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_cancel); + break; + } + } + + netfs_prepare_dio_read_iterator(subreq); + slice = subreq->len; + rreq->netfs_ops->issue_read(subreq); + + size -= slice; + start += slice; + rreq->submitted += slice; + + if (test_bit(NETFS_RREQ_BLOCKED, &rreq->flags) && + test_bit(NETFS_RREQ_NONBLOCK, &rreq->flags)) + break; + cond_resched(); + } while (size > 0); + + if (atomic_dec_and_test(&rreq->nr_outstanding)) + netfs_rreq_terminated(rreq, false); + return ret; +} + +/* + * Perform a read to an application buffer, bypassing the pagecache and the + * local disk cache. + */ +static int netfs_unbuffered_read(struct netfs_io_request *rreq, bool sync) +{ + int ret; + + _enter("R=%x %llx-%llx", + rreq->debug_id, rreq->start, rreq->start + rreq->len - 1); + + if (rreq->len == 0) { + pr_err("Zero-sized read [R=%x]\n", rreq->debug_id); + return -EIO; + } + + // TODO: Use bounce buffer if requested + + inode_dio_begin(rreq->inode); + + ret = netfs_dispatch_unbuffered_reads(rreq); + + if (!rreq->submitted) { + netfs_put_request(rreq, false, netfs_rreq_trace_put_no_submit); + inode_dio_end(rreq->inode); + ret = 0; + goto out; + } + + if (sync) { + trace_netfs_rreq(rreq, netfs_rreq_trace_wait_ip); + wait_on_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS, + TASK_UNINTERRUPTIBLE); + + ret = rreq->error; + if (ret == 0 && rreq->submitted < rreq->len && + rreq->origin != NETFS_DIO_READ) { + trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_read); + ret = -EIO; + } + } else { + ret = -EIOCBQUEUED; + } + +out: + _leave(" = %d", ret); + return ret; +} + /** * netfs_unbuffered_read_iter_locked - Perform an unbuffered or direct I/O read * @iocb: The I/O control descriptor describing the read @@ -31,7 +168,7 @@ ssize_t netfs_unbuffered_read_iter_locked(struct kiocb *iocb, struct iov_iter *i struct netfs_io_request *rreq; ssize_t ret; size_t orig_count = iov_iter_count(iter); - bool async = !is_sync_kiocb(iocb); + bool sync = is_sync_kiocb(iocb); _enter(""); @@ -78,13 +215,13 @@ ssize_t netfs_unbuffered_read_iter_locked(struct kiocb *iocb, struct iov_iter *i // TODO: Set up bounce buffer if needed - if (async) + if (!sync) rreq->iocb = iocb; - ret = netfs_begin_read(rreq, is_sync_kiocb(iocb)); + ret = netfs_unbuffered_read(rreq, sync); if (ret < 0) goto out; /* May be -EIOCBQUEUED */ - if (!async) { + if (sync) { // TODO: Copy from bounce buffer iocb->ki_pos += rreq->transferred; ret = rreq->transferred; @@ -94,8 +231,6 @@ out: netfs_put_request(rreq, false, netfs_rreq_trace_put_return); if (ret > 0) orig_count -= ret; - if (ret != -EIOCBQUEUED) - iov_iter_revert(iter, orig_count - iov_iter_count(iter)); return ret; } EXPORT_SYMBOL(netfs_unbuffered_read_iter_locked); diff --git a/fs/netfs/fscache_main.c b/fs/netfs/fscache_main.c index 42e98bb523e3..49849005eb7c 100644 --- a/fs/netfs/fscache_main.c +++ b/fs/netfs/fscache_main.c @@ -103,6 +103,7 @@ void __exit fscache_exit(void) kmem_cache_destroy(fscache_cookie_jar); fscache_proc_cleanup(); + timer_shutdown_sync(&fscache_cookie_lru_timer); destroy_workqueue(fscache_wq); pr_notice("FS-Cache unloaded\n"); } diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h index 7773f3d855a9..c9f0ed24cb7b 100644 --- a/fs/netfs/internal.h +++ b/fs/netfs/internal.h @@ -7,6 +7,7 @@ #include <linux/slab.h> #include <linux/seq_file.h> +#include <linux/folio_queue.h> #include <linux/netfs.h> #include <linux/fscache.h> #include <linux/fscache-cache.h> @@ -22,16 +23,10 @@ /* * buffered_read.c */ -void netfs_rreq_unlock_folios(struct netfs_io_request *rreq); int netfs_prefetch_for_write(struct file *file, struct folio *folio, size_t offset, size_t len); /* - * io.c - */ -int netfs_begin_read(struct netfs_io_request *rreq, bool sync); - -/* * main.c */ extern unsigned int netfs_debug; @@ -63,6 +58,11 @@ static inline void netfs_proc_del_rreq(struct netfs_io_request *rreq) {} /* * misc.c */ +int netfs_buffer_append_folio(struct netfs_io_request *rreq, struct folio *folio, + bool needs_put); +struct folio_queue *netfs_delete_buffer_head(struct netfs_io_request *wreq); +void netfs_clear_buffer(struct netfs_io_request *rreq); +void netfs_reset_iter(struct netfs_io_subrequest *subreq); /* * objects.c @@ -84,6 +84,28 @@ static inline void netfs_see_request(struct netfs_io_request *rreq, } /* + * read_collect.c + */ +void netfs_read_termination_worker(struct work_struct *work); +void netfs_rreq_terminated(struct netfs_io_request *rreq, bool was_async); + +/* + * read_pgpriv2.c + */ +void netfs_pgpriv2_mark_copy_to_cache(struct netfs_io_subrequest *subreq, + struct netfs_io_request *rreq, + struct folio_queue *folioq, + int slot); +void netfs_pgpriv2_write_to_the_cache(struct netfs_io_request *rreq); +bool netfs_pgpriv2_unlock_copied_folios(struct netfs_io_request *wreq); + +/* + * read_retry.c + */ +void netfs_retry_reads(struct netfs_io_request *rreq); +void netfs_unlock_abandoned_read_pages(struct netfs_io_request *rreq); + +/* * stats.c */ #ifdef CONFIG_NETFS_STATS @@ -110,6 +132,7 @@ extern atomic_t netfs_n_wh_buffered_write; extern atomic_t netfs_n_wh_writethrough; extern atomic_t netfs_n_wh_dio_write; extern atomic_t netfs_n_wh_writepages; +extern atomic_t netfs_n_wh_copy_to_cache; extern atomic_t netfs_n_wh_wstream_conflict; extern atomic_t netfs_n_wh_upload; extern atomic_t netfs_n_wh_upload_done; @@ -117,6 +140,9 @@ extern atomic_t netfs_n_wh_upload_failed; extern atomic_t netfs_n_wh_write; extern atomic_t netfs_n_wh_write_done; extern atomic_t netfs_n_wh_write_failed; +extern atomic_t netfs_n_wb_lock_skip; +extern atomic_t netfs_n_wb_lock_wait; +extern atomic_t netfs_n_folioq; int netfs_stats_show(struct seq_file *m, void *v); @@ -150,7 +176,10 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping, loff_t start, enum netfs_io_origin origin); void netfs_reissue_write(struct netfs_io_stream *stream, - struct netfs_io_subrequest *subreq); + struct netfs_io_subrequest *subreq, + struct iov_iter *source); +void netfs_issue_write(struct netfs_io_request *wreq, + struct netfs_io_stream *stream); int netfs_advance_write(struct netfs_io_request *wreq, struct netfs_io_stream *stream, loff_t start, size_t len, bool to_eof); diff --git a/fs/netfs/io.c b/fs/netfs/io.c deleted file mode 100644 index 943128507af5..000000000000 --- a/fs/netfs/io.c +++ /dev/null @@ -1,804 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* Network filesystem high-level read support. - * - * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - */ - -#include <linux/module.h> -#include <linux/export.h> -#include <linux/fs.h> -#include <linux/mm.h> -#include <linux/pagemap.h> -#include <linux/slab.h> -#include <linux/uio.h> -#include <linux/sched/mm.h> -#include <linux/task_io_accounting_ops.h> -#include "internal.h" - -/* - * Clear the unread part of an I/O request. - */ -static void netfs_clear_unread(struct netfs_io_subrequest *subreq) -{ - iov_iter_zero(iov_iter_count(&subreq->io_iter), &subreq->io_iter); -} - -static void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error, - bool was_async) -{ - struct netfs_io_subrequest *subreq = priv; - - netfs_subreq_terminated(subreq, transferred_or_error, was_async); -} - -/* - * Issue a read against the cache. - * - Eats the caller's ref on subreq. - */ -static void netfs_read_from_cache(struct netfs_io_request *rreq, - struct netfs_io_subrequest *subreq, - enum netfs_read_from_hole read_hole) -{ - struct netfs_cache_resources *cres = &rreq->cache_resources; - - netfs_stat(&netfs_n_rh_read); - cres->ops->read(cres, subreq->start, &subreq->io_iter, read_hole, - netfs_cache_read_terminated, subreq); -} - -/* - * Fill a subrequest region with zeroes. - */ -static void netfs_fill_with_zeroes(struct netfs_io_request *rreq, - struct netfs_io_subrequest *subreq) -{ - netfs_stat(&netfs_n_rh_zero); - __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); - netfs_subreq_terminated(subreq, 0, false); -} - -/* - * Ask the netfs to issue a read request to the server for us. - * - * The netfs is expected to read from subreq->pos + subreq->transferred to - * subreq->pos + subreq->len - 1. It may not backtrack and write data into the - * buffer prior to the transferred point as it might clobber dirty data - * obtained from the cache. - * - * Alternatively, the netfs is allowed to indicate one of two things: - * - * - NETFS_SREQ_SHORT_READ: A short read - it will get called again to try and - * make progress. - * - * - NETFS_SREQ_CLEAR_TAIL: A short read - the rest of the buffer will be - * cleared. - */ -static void netfs_read_from_server(struct netfs_io_request *rreq, - struct netfs_io_subrequest *subreq) -{ - netfs_stat(&netfs_n_rh_download); - - if (rreq->origin != NETFS_DIO_READ && - iov_iter_count(&subreq->io_iter) != subreq->len - subreq->transferred) - pr_warn("R=%08x[%u] ITER PRE-MISMATCH %zx != %zx-%zx %lx\n", - rreq->debug_id, subreq->debug_index, - iov_iter_count(&subreq->io_iter), subreq->len, - subreq->transferred, subreq->flags); - rreq->netfs_ops->issue_read(subreq); -} - -/* - * Release those waiting. - */ -static void netfs_rreq_completed(struct netfs_io_request *rreq, bool was_async) -{ - trace_netfs_rreq(rreq, netfs_rreq_trace_done); - netfs_clear_subrequests(rreq, was_async); - netfs_put_request(rreq, was_async, netfs_rreq_trace_put_complete); -} - -/* - * [DEPRECATED] Deal with the completion of writing the data to the cache. We - * have to clear the PG_fscache bits on the folios involved and release the - * caller's ref. - * - * May be called in softirq mode and we inherit a ref from the caller. - */ -static void netfs_rreq_unmark_after_write(struct netfs_io_request *rreq, - bool was_async) -{ - struct netfs_io_subrequest *subreq; - struct folio *folio; - pgoff_t unlocked = 0; - bool have_unlocked = false; - - rcu_read_lock(); - - list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { - XA_STATE(xas, &rreq->mapping->i_pages, subreq->start / PAGE_SIZE); - - xas_for_each(&xas, folio, (subreq->start + subreq->len - 1) / PAGE_SIZE) { - if (xas_retry(&xas, folio)) - continue; - - /* We might have multiple writes from the same huge - * folio, but we mustn't unlock a folio more than once. - */ - if (have_unlocked && folio->index <= unlocked) - continue; - unlocked = folio_next_index(folio) - 1; - trace_netfs_folio(folio, netfs_folio_trace_end_copy); - folio_end_private_2(folio); - have_unlocked = true; - } - } - - rcu_read_unlock(); - netfs_rreq_completed(rreq, was_async); -} - -static void netfs_rreq_copy_terminated(void *priv, ssize_t transferred_or_error, - bool was_async) /* [DEPRECATED] */ -{ - struct netfs_io_subrequest *subreq = priv; - struct netfs_io_request *rreq = subreq->rreq; - - if (IS_ERR_VALUE(transferred_or_error)) { - netfs_stat(&netfs_n_rh_write_failed); - trace_netfs_failure(rreq, subreq, transferred_or_error, - netfs_fail_copy_to_cache); - } else { - netfs_stat(&netfs_n_rh_write_done); - } - - trace_netfs_sreq(subreq, netfs_sreq_trace_write_term); - - /* If we decrement nr_copy_ops to 0, the ref belongs to us. */ - if (atomic_dec_and_test(&rreq->nr_copy_ops)) - netfs_rreq_unmark_after_write(rreq, was_async); - - netfs_put_subrequest(subreq, was_async, netfs_sreq_trace_put_terminated); -} - -/* - * [DEPRECATED] Perform any outstanding writes to the cache. We inherit a ref - * from the caller. - */ -static void netfs_rreq_do_write_to_cache(struct netfs_io_request *rreq) -{ - struct netfs_cache_resources *cres = &rreq->cache_resources; - struct netfs_io_subrequest *subreq, *next, *p; - struct iov_iter iter; - int ret; - - trace_netfs_rreq(rreq, netfs_rreq_trace_copy); - - /* We don't want terminating writes trying to wake us up whilst we're - * still going through the list. - */ - atomic_inc(&rreq->nr_copy_ops); - - list_for_each_entry_safe(subreq, p, &rreq->subrequests, rreq_link) { - if (!test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) { - list_del_init(&subreq->rreq_link); - netfs_put_subrequest(subreq, false, - netfs_sreq_trace_put_no_copy); - } - } - - list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { - /* Amalgamate adjacent writes */ - while (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) { - next = list_next_entry(subreq, rreq_link); - if (next->start != subreq->start + subreq->len) - break; - subreq->len += next->len; - list_del_init(&next->rreq_link); - netfs_put_subrequest(next, false, - netfs_sreq_trace_put_merged); - } - - ret = cres->ops->prepare_write(cres, &subreq->start, &subreq->len, - subreq->len, rreq->i_size, true); - if (ret < 0) { - trace_netfs_failure(rreq, subreq, ret, netfs_fail_prepare_write); - trace_netfs_sreq(subreq, netfs_sreq_trace_write_skip); - continue; - } - - iov_iter_xarray(&iter, ITER_SOURCE, &rreq->mapping->i_pages, - subreq->start, subreq->len); - - atomic_inc(&rreq->nr_copy_ops); - netfs_stat(&netfs_n_rh_write); - netfs_get_subrequest(subreq, netfs_sreq_trace_get_copy_to_cache); - trace_netfs_sreq(subreq, netfs_sreq_trace_write); - cres->ops->write(cres, subreq->start, &iter, - netfs_rreq_copy_terminated, subreq); - } - - /* If we decrement nr_copy_ops to 0, the usage ref belongs to us. */ - if (atomic_dec_and_test(&rreq->nr_copy_ops)) - netfs_rreq_unmark_after_write(rreq, false); -} - -static void netfs_rreq_write_to_cache_work(struct work_struct *work) /* [DEPRECATED] */ -{ - struct netfs_io_request *rreq = - container_of(work, struct netfs_io_request, work); - - netfs_rreq_do_write_to_cache(rreq); -} - -static void netfs_rreq_write_to_cache(struct netfs_io_request *rreq) /* [DEPRECATED] */ -{ - rreq->work.func = netfs_rreq_write_to_cache_work; - if (!queue_work(system_unbound_wq, &rreq->work)) - BUG(); -} - -/* - * Handle a short read. - */ -static void netfs_rreq_short_read(struct netfs_io_request *rreq, - struct netfs_io_subrequest *subreq) -{ - __clear_bit(NETFS_SREQ_SHORT_IO, &subreq->flags); - __set_bit(NETFS_SREQ_SEEK_DATA_READ, &subreq->flags); - - netfs_stat(&netfs_n_rh_short_read); - trace_netfs_sreq(subreq, netfs_sreq_trace_resubmit_short); - - netfs_get_subrequest(subreq, netfs_sreq_trace_get_short_read); - atomic_inc(&rreq->nr_outstanding); - if (subreq->source == NETFS_READ_FROM_CACHE) - netfs_read_from_cache(rreq, subreq, NETFS_READ_HOLE_CLEAR); - else - netfs_read_from_server(rreq, subreq); -} - -/* - * Reset the subrequest iterator prior to resubmission. - */ -static void netfs_reset_subreq_iter(struct netfs_io_request *rreq, - struct netfs_io_subrequest *subreq) -{ - size_t remaining = subreq->len - subreq->transferred; - size_t count = iov_iter_count(&subreq->io_iter); - - if (count == remaining) - return; - - _debug("R=%08x[%u] ITER RESUB-MISMATCH %zx != %zx-%zx-%llx %x\n", - rreq->debug_id, subreq->debug_index, - iov_iter_count(&subreq->io_iter), subreq->transferred, - subreq->len, rreq->i_size, - subreq->io_iter.iter_type); - - if (count < remaining) - iov_iter_revert(&subreq->io_iter, remaining - count); - else - iov_iter_advance(&subreq->io_iter, count - remaining); -} - -/* - * Resubmit any short or failed operations. Returns true if we got the rreq - * ref back. - */ -static bool netfs_rreq_perform_resubmissions(struct netfs_io_request *rreq) -{ - struct netfs_io_subrequest *subreq; - - WARN_ON(in_interrupt()); - - trace_netfs_rreq(rreq, netfs_rreq_trace_resubmit); - - /* We don't want terminating submissions trying to wake us up whilst - * we're still going through the list. - */ - atomic_inc(&rreq->nr_outstanding); - - __clear_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags); - list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { - if (subreq->error) { - if (subreq->source != NETFS_READ_FROM_CACHE) - break; - subreq->source = NETFS_DOWNLOAD_FROM_SERVER; - subreq->error = 0; - __set_bit(NETFS_SREQ_RETRYING, &subreq->flags); - netfs_stat(&netfs_n_rh_download_instead); - trace_netfs_sreq(subreq, netfs_sreq_trace_download_instead); - netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); - atomic_inc(&rreq->nr_outstanding); - netfs_reset_subreq_iter(rreq, subreq); - netfs_read_from_server(rreq, subreq); - } else if (test_bit(NETFS_SREQ_SHORT_IO, &subreq->flags)) { - __set_bit(NETFS_SREQ_RETRYING, &subreq->flags); - netfs_reset_subreq_iter(rreq, subreq); - netfs_rreq_short_read(rreq, subreq); - } - } - - /* If we decrement nr_outstanding to 0, the usage ref belongs to us. */ - if (atomic_dec_and_test(&rreq->nr_outstanding)) - return true; - - wake_up_var(&rreq->nr_outstanding); - return false; -} - -/* - * Check to see if the data read is still valid. - */ -static void netfs_rreq_is_still_valid(struct netfs_io_request *rreq) -{ - struct netfs_io_subrequest *subreq; - - if (!rreq->netfs_ops->is_still_valid || - rreq->netfs_ops->is_still_valid(rreq)) - return; - - list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { - if (subreq->source == NETFS_READ_FROM_CACHE) { - subreq->error = -ESTALE; - __set_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags); - } - } -} - -/* - * Determine how much we can admit to having read from a DIO read. - */ -static void netfs_rreq_assess_dio(struct netfs_io_request *rreq) -{ - struct netfs_io_subrequest *subreq; - unsigned int i; - size_t transferred = 0; - - for (i = 0; i < rreq->direct_bv_count; i++) { - flush_dcache_page(rreq->direct_bv[i].bv_page); - // TODO: cifs marks pages in the destination buffer - // dirty under some circumstances after a read. Do we - // need to do that too? - set_page_dirty(rreq->direct_bv[i].bv_page); - } - - list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { - if (subreq->error || subreq->transferred == 0) - break; - transferred += subreq->transferred; - if (subreq->transferred < subreq->len || - test_bit(NETFS_SREQ_HIT_EOF, &subreq->flags)) - break; - } - - for (i = 0; i < rreq->direct_bv_count; i++) - flush_dcache_page(rreq->direct_bv[i].bv_page); - - rreq->transferred = transferred; - task_io_account_read(transferred); - - if (rreq->iocb) { - rreq->iocb->ki_pos += transferred; - if (rreq->iocb->ki_complete) - rreq->iocb->ki_complete( - rreq->iocb, rreq->error ? rreq->error : transferred); - } - if (rreq->netfs_ops->done) - rreq->netfs_ops->done(rreq); - inode_dio_end(rreq->inode); -} - -/* - * Assess the state of a read request and decide what to do next. - * - * Note that we could be in an ordinary kernel thread, on a workqueue or in - * softirq context at this point. We inherit a ref from the caller. - */ -static void netfs_rreq_assess(struct netfs_io_request *rreq, bool was_async) -{ - trace_netfs_rreq(rreq, netfs_rreq_trace_assess); - -again: - netfs_rreq_is_still_valid(rreq); - - if (!test_bit(NETFS_RREQ_FAILED, &rreq->flags) && - test_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags)) { - if (netfs_rreq_perform_resubmissions(rreq)) - goto again; - return; - } - - if (rreq->origin != NETFS_DIO_READ) - netfs_rreq_unlock_folios(rreq); - else - netfs_rreq_assess_dio(rreq); - - trace_netfs_rreq(rreq, netfs_rreq_trace_wake_ip); - clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &rreq->flags); - wake_up_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS); - - if (test_bit(NETFS_RREQ_COPY_TO_CACHE, &rreq->flags) && - test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags)) - return netfs_rreq_write_to_cache(rreq); - - netfs_rreq_completed(rreq, was_async); -} - -static void netfs_rreq_work(struct work_struct *work) -{ - struct netfs_io_request *rreq = - container_of(work, struct netfs_io_request, work); - netfs_rreq_assess(rreq, false); -} - -/* - * Handle the completion of all outstanding I/O operations on a read request. - * We inherit a ref from the caller. - */ -static void netfs_rreq_terminated(struct netfs_io_request *rreq, - bool was_async) -{ - if (test_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags) && - was_async) { - if (!queue_work(system_unbound_wq, &rreq->work)) - BUG(); - } else { - netfs_rreq_assess(rreq, was_async); - } -} - -/** - * netfs_subreq_terminated - Note the termination of an I/O operation. - * @subreq: The I/O request that has terminated. - * @transferred_or_error: The amount of data transferred or an error code. - * @was_async: The termination was asynchronous - * - * This tells the read helper that a contributory I/O operation has terminated, - * one way or another, and that it should integrate the results. - * - * The caller indicates in @transferred_or_error the outcome of the operation, - * supplying a positive value to indicate the number of bytes transferred, 0 to - * indicate a failure to transfer anything that should be retried or a negative - * error code. The helper will look after reissuing I/O operations as - * appropriate and writing downloaded data to the cache. - * - * If @was_async is true, the caller might be running in softirq or interrupt - * context and we can't sleep. - */ -void netfs_subreq_terminated(struct netfs_io_subrequest *subreq, - ssize_t transferred_or_error, - bool was_async) -{ - struct netfs_io_request *rreq = subreq->rreq; - int u; - - _enter("R=%x[%x]{%llx,%lx},%zd", - rreq->debug_id, subreq->debug_index, - subreq->start, subreq->flags, transferred_or_error); - - switch (subreq->source) { - case NETFS_READ_FROM_CACHE: - netfs_stat(&netfs_n_rh_read_done); - break; - case NETFS_DOWNLOAD_FROM_SERVER: - netfs_stat(&netfs_n_rh_download_done); - break; - default: - break; - } - - if (IS_ERR_VALUE(transferred_or_error)) { - subreq->error = transferred_or_error; - trace_netfs_failure(rreq, subreq, transferred_or_error, - netfs_fail_read); - goto failed; - } - - if (WARN(transferred_or_error > subreq->len - subreq->transferred, - "Subreq overread: R%x[%x] %zd > %zu - %zu", - rreq->debug_id, subreq->debug_index, - transferred_or_error, subreq->len, subreq->transferred)) - transferred_or_error = subreq->len - subreq->transferred; - - subreq->error = 0; - subreq->transferred += transferred_or_error; - if (subreq->transferred < subreq->len && - !test_bit(NETFS_SREQ_HIT_EOF, &subreq->flags)) - goto incomplete; - -complete: - __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); - if (test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) - set_bit(NETFS_RREQ_COPY_TO_CACHE, &rreq->flags); - -out: - trace_netfs_sreq(subreq, netfs_sreq_trace_terminated); - - /* If we decrement nr_outstanding to 0, the ref belongs to us. */ - u = atomic_dec_return(&rreq->nr_outstanding); - if (u == 0) - netfs_rreq_terminated(rreq, was_async); - else if (u == 1) - wake_up_var(&rreq->nr_outstanding); - - netfs_put_subrequest(subreq, was_async, netfs_sreq_trace_put_terminated); - return; - -incomplete: - if (test_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags)) { - netfs_clear_unread(subreq); - subreq->transferred = subreq->len; - goto complete; - } - - if (transferred_or_error == 0) { - if (__test_and_set_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags)) { - if (rreq->origin != NETFS_DIO_READ) - subreq->error = -ENODATA; - goto failed; - } - } else { - __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); - } - - __set_bit(NETFS_SREQ_SHORT_IO, &subreq->flags); - set_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags); - goto out; - -failed: - if (subreq->source == NETFS_READ_FROM_CACHE) { - netfs_stat(&netfs_n_rh_read_failed); - set_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags); - } else { - netfs_stat(&netfs_n_rh_download_failed); - set_bit(NETFS_RREQ_FAILED, &rreq->flags); - rreq->error = subreq->error; - } - goto out; -} -EXPORT_SYMBOL(netfs_subreq_terminated); - -static enum netfs_io_source netfs_cache_prepare_read(struct netfs_io_subrequest *subreq, - loff_t i_size) -{ - struct netfs_io_request *rreq = subreq->rreq; - struct netfs_cache_resources *cres = &rreq->cache_resources; - - if (cres->ops) - return cres->ops->prepare_read(subreq, i_size); - if (subreq->start >= rreq->i_size) - return NETFS_FILL_WITH_ZEROES; - return NETFS_DOWNLOAD_FROM_SERVER; -} - -/* - * Work out what sort of subrequest the next one will be. - */ -static enum netfs_io_source -netfs_rreq_prepare_read(struct netfs_io_request *rreq, - struct netfs_io_subrequest *subreq, - struct iov_iter *io_iter) -{ - enum netfs_io_source source = NETFS_DOWNLOAD_FROM_SERVER; - struct netfs_inode *ictx = netfs_inode(rreq->inode); - size_t lsize; - - _enter("%llx-%llx,%llx", subreq->start, subreq->start + subreq->len, rreq->i_size); - - if (rreq->origin != NETFS_DIO_READ) { - source = netfs_cache_prepare_read(subreq, rreq->i_size); - if (source == NETFS_INVALID_READ) - goto out; - } - - if (source == NETFS_DOWNLOAD_FROM_SERVER) { - /* Call out to the netfs to let it shrink the request to fit - * its own I/O sizes and boundaries. If it shinks it here, it - * will be called again to make simultaneous calls; if it wants - * to make serial calls, it can indicate a short read and then - * we will call it again. - */ - if (rreq->origin != NETFS_DIO_READ) { - if (subreq->start >= ictx->zero_point) { - source = NETFS_FILL_WITH_ZEROES; - goto set; - } - if (subreq->len > ictx->zero_point - subreq->start) - subreq->len = ictx->zero_point - subreq->start; - - /* We limit buffered reads to the EOF, but let the - * server deal with larger-than-EOF DIO/unbuffered - * reads. - */ - if (subreq->len > rreq->i_size - subreq->start) - subreq->len = rreq->i_size - subreq->start; - } - if (rreq->rsize && subreq->len > rreq->rsize) - subreq->len = rreq->rsize; - - if (rreq->netfs_ops->clamp_length && - !rreq->netfs_ops->clamp_length(subreq)) { - source = NETFS_INVALID_READ; - goto out; - } - - if (subreq->max_nr_segs) { - lsize = netfs_limit_iter(io_iter, 0, subreq->len, - subreq->max_nr_segs); - if (subreq->len > lsize) { - subreq->len = lsize; - trace_netfs_sreq(subreq, netfs_sreq_trace_limited); - } - } - } - -set: - if (subreq->len > rreq->len) - pr_warn("R=%08x[%u] SREQ>RREQ %zx > %llx\n", - rreq->debug_id, subreq->debug_index, - subreq->len, rreq->len); - - if (WARN_ON(subreq->len == 0)) { - source = NETFS_INVALID_READ; - goto out; - } - - subreq->source = source; - trace_netfs_sreq(subreq, netfs_sreq_trace_prepare); - - subreq->io_iter = *io_iter; - iov_iter_truncate(&subreq->io_iter, subreq->len); - iov_iter_advance(io_iter, subreq->len); -out: - subreq->source = source; - trace_netfs_sreq(subreq, netfs_sreq_trace_prepare); - return source; -} - -/* - * Slice off a piece of a read request and submit an I/O request for it. - */ -static bool netfs_rreq_submit_slice(struct netfs_io_request *rreq, - struct iov_iter *io_iter) -{ - struct netfs_io_subrequest *subreq; - enum netfs_io_source source; - - subreq = netfs_alloc_subrequest(rreq); - if (!subreq) - return false; - - subreq->start = rreq->start + rreq->submitted; - subreq->len = io_iter->count; - - _debug("slice %llx,%zx,%llx", subreq->start, subreq->len, rreq->submitted); - list_add_tail(&subreq->rreq_link, &rreq->subrequests); - - /* Call out to the cache to find out what it can do with the remaining - * subset. It tells us in subreq->flags what it decided should be done - * and adjusts subreq->len down if the subset crosses a cache boundary. - * - * Then when we hand the subset, it can choose to take a subset of that - * (the starts must coincide), in which case, we go around the loop - * again and ask it to download the next piece. - */ - source = netfs_rreq_prepare_read(rreq, subreq, io_iter); - if (source == NETFS_INVALID_READ) - goto subreq_failed; - - atomic_inc(&rreq->nr_outstanding); - - rreq->submitted += subreq->len; - - trace_netfs_sreq(subreq, netfs_sreq_trace_submit); - switch (source) { - case NETFS_FILL_WITH_ZEROES: - netfs_fill_with_zeroes(rreq, subreq); - break; - case NETFS_DOWNLOAD_FROM_SERVER: - netfs_read_from_server(rreq, subreq); - break; - case NETFS_READ_FROM_CACHE: - netfs_read_from_cache(rreq, subreq, NETFS_READ_HOLE_IGNORE); - break; - default: - BUG(); - } - - return true; - -subreq_failed: - rreq->error = subreq->error; - netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_failed); - return false; -} - -/* - * Begin the process of reading in a chunk of data, where that data may be - * stitched together from multiple sources, including multiple servers and the - * local cache. - */ -int netfs_begin_read(struct netfs_io_request *rreq, bool sync) -{ - struct iov_iter io_iter; - int ret; - - _enter("R=%x %llx-%llx", - rreq->debug_id, rreq->start, rreq->start + rreq->len - 1); - - if (rreq->len == 0) { - pr_err("Zero-sized read [R=%x]\n", rreq->debug_id); - return -EIO; - } - - if (rreq->origin == NETFS_DIO_READ) - inode_dio_begin(rreq->inode); - - // TODO: Use bounce buffer if requested - rreq->io_iter = rreq->iter; - - INIT_WORK(&rreq->work, netfs_rreq_work); - - /* Chop the read into slices according to what the cache and the netfs - * want and submit each one. - */ - netfs_get_request(rreq, netfs_rreq_trace_get_for_outstanding); - atomic_set(&rreq->nr_outstanding, 1); - io_iter = rreq->io_iter; - do { - _debug("submit %llx + %llx >= %llx", - rreq->start, rreq->submitted, rreq->i_size); - if (!netfs_rreq_submit_slice(rreq, &io_iter)) - break; - if (test_bit(NETFS_SREQ_NO_PROGRESS, &rreq->flags)) - break; - if (test_bit(NETFS_RREQ_BLOCKED, &rreq->flags) && - test_bit(NETFS_RREQ_NONBLOCK, &rreq->flags)) - break; - - } while (rreq->submitted < rreq->len); - - if (!rreq->submitted) { - netfs_put_request(rreq, false, netfs_rreq_trace_put_no_submit); - if (rreq->origin == NETFS_DIO_READ) - inode_dio_end(rreq->inode); - ret = 0; - goto out; - } - - if (sync) { - /* Keep nr_outstanding incremented so that the ref always - * belongs to us, and the service code isn't punted off to a - * random thread pool to process. Note that this might start - * further work, such as writing to the cache. - */ - wait_var_event(&rreq->nr_outstanding, - atomic_read(&rreq->nr_outstanding) == 1); - if (atomic_dec_and_test(&rreq->nr_outstanding)) - netfs_rreq_assess(rreq, false); - - trace_netfs_rreq(rreq, netfs_rreq_trace_wait_ip); - wait_on_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS, - TASK_UNINTERRUPTIBLE); - - ret = rreq->error; - if (ret == 0) { - if (rreq->origin == NETFS_DIO_READ) { - ret = rreq->transferred; - } else if (rreq->submitted < rreq->len) { - trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_read); - ret = -EIO; - } - } - } else { - /* If we decrement nr_outstanding to 0, the ref belongs to us. */ - if (atomic_dec_and_test(&rreq->nr_outstanding)) - netfs_rreq_assess(rreq, false); - ret = -EIOCBQUEUED; - } - -out: - return ret; -} diff --git a/fs/netfs/iterator.c b/fs/netfs/iterator.c index b781bbbf1d8d..72a435e5fc6d 100644 --- a/fs/netfs/iterator.c +++ b/fs/netfs/iterator.c @@ -188,9 +188,59 @@ static size_t netfs_limit_xarray(const struct iov_iter *iter, size_t start_offse return min(span, max_size); } +/* + * Select the span of a folio queue iterator we're going to use. Limit it by + * both maximum size and maximum number of segments. Returns the size of the + * span in bytes. + */ +static size_t netfs_limit_folioq(const struct iov_iter *iter, size_t start_offset, + size_t max_size, size_t max_segs) +{ + const struct folio_queue *folioq = iter->folioq; + unsigned int nsegs = 0; + unsigned int slot = iter->folioq_slot; + size_t span = 0, n = iter->count; + + if (WARN_ON(!iov_iter_is_folioq(iter)) || + WARN_ON(start_offset > n) || + n == 0) + return 0; + max_size = umin(max_size, n - start_offset); + + if (slot >= folioq_nr_slots(folioq)) { + folioq = folioq->next; + slot = 0; + } + + start_offset += iter->iov_offset; + do { + size_t flen = folioq_folio_size(folioq, slot); + + if (start_offset < flen) { + span += flen - start_offset; + nsegs++; + start_offset = 0; + } else { + start_offset -= flen; + } + if (span >= max_size || nsegs >= max_segs) + break; + + slot++; + if (slot >= folioq_nr_slots(folioq)) { + folioq = folioq->next; + slot = 0; + } + } while (folioq); + + return umin(span, max_size); +} + size_t netfs_limit_iter(const struct iov_iter *iter, size_t start_offset, size_t max_size, size_t max_segs) { + if (iov_iter_is_folioq(iter)) + return netfs_limit_folioq(iter, start_offset, max_size, max_segs); if (iov_iter_is_bvec(iter)) return netfs_limit_bvec(iter, start_offset, max_size, max_segs); if (iov_iter_is_xarray(iter)) diff --git a/fs/netfs/locking.c b/fs/netfs/locking.c index 75dc52a49b3a..21eab56ee2f9 100644 --- a/fs/netfs/locking.c +++ b/fs/netfs/locking.c @@ -19,25 +19,13 @@ * Must be called under a lock that serializes taking new references * to i_dio_count, usually by inode->i_mutex. */ -static int inode_dio_wait_interruptible(struct inode *inode) +static int netfs_inode_dio_wait_interruptible(struct inode *inode) { - if (!atomic_read(&inode->i_dio_count)) + if (inode_dio_finished(inode)) return 0; - wait_queue_head_t *wq = bit_waitqueue(&inode->i_state, __I_DIO_WAKEUP); - DEFINE_WAIT_BIT(q, &inode->i_state, __I_DIO_WAKEUP); - - for (;;) { - prepare_to_wait(wq, &q.wq_entry, TASK_INTERRUPTIBLE); - if (!atomic_read(&inode->i_dio_count)) - break; - if (signal_pending(current)) - break; - schedule(); - } - finish_wait(wq, &q.wq_entry); - - return atomic_read(&inode->i_dio_count) ? -ERESTARTSYS : 0; + inode_dio_wait_interruptible(inode); + return !inode_dio_finished(inode) ? -ERESTARTSYS : 0; } /* Call with exclusively locked inode->i_rwsem */ @@ -46,7 +34,7 @@ static int netfs_block_o_direct(struct netfs_inode *ictx) if (!test_bit(NETFS_ICTX_ODIRECT, &ictx->flags)) return 0; clear_bit(NETFS_ICTX_ODIRECT, &ictx->flags); - return inode_dio_wait_interruptible(&ictx->inode); + return netfs_inode_dio_wait_interruptible(&ictx->inode); } /** diff --git a/fs/netfs/main.c b/fs/netfs/main.c index 5f0f438e5d21..6c7be1377ee0 100644 --- a/fs/netfs/main.c +++ b/fs/netfs/main.c @@ -36,13 +36,14 @@ DEFINE_SPINLOCK(netfs_proc_lock); static const char *netfs_origins[nr__netfs_io_origin] = { [NETFS_READAHEAD] = "RA", [NETFS_READPAGE] = "RP", + [NETFS_READ_GAPS] = "RG", [NETFS_READ_FOR_WRITE] = "RW", - [NETFS_COPY_TO_CACHE] = "CC", + [NETFS_DIO_READ] = "DR", [NETFS_WRITEBACK] = "WB", [NETFS_WRITETHROUGH] = "WT", [NETFS_UNBUFFERED_WRITE] = "UW", - [NETFS_DIO_READ] = "DR", [NETFS_DIO_WRITE] = "DW", + [NETFS_PGPRIV2_COPY_TO_CACHE] = "2C", }; /* @@ -62,7 +63,7 @@ static int netfs_requests_seq_show(struct seq_file *m, void *v) rreq = list_entry(v, struct netfs_io_request, proc_link); seq_printf(m, - "%08x %s %3d %2lx %4d %3d @%04llx %llx/%llx", + "%08x %s %3d %2lx %4ld %3d @%04llx %llx/%llx", rreq->debug_id, netfs_origins[rreq->origin], refcount_read(&rreq->ref), @@ -142,7 +143,7 @@ static int __init netfs_init(void) error_fscache: error_procfile: - remove_proc_entry("fs/netfs", NULL); + remove_proc_subtree("fs/netfs", NULL); error_proc: mempool_exit(&netfs_subrequest_pool); error_subreqpool: @@ -159,7 +160,7 @@ fs_initcall(netfs_init); static void __exit netfs_exit(void) { fscache_exit(); - remove_proc_entry("fs/netfs", NULL); + remove_proc_subtree("fs/netfs", NULL); mempool_exit(&netfs_subrequest_pool); kmem_cache_destroy(netfs_subrequest_slab); mempool_exit(&netfs_request_pool); diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c index c1f321cf5999..0ad0982ce0e2 100644 --- a/fs/netfs/misc.c +++ b/fs/netfs/misc.c @@ -8,6 +8,100 @@ #include <linux/swap.h> #include "internal.h" +/* + * Append a folio to the rolling queue. + */ +int netfs_buffer_append_folio(struct netfs_io_request *rreq, struct folio *folio, + bool needs_put) +{ + struct folio_queue *tail = rreq->buffer_tail; + unsigned int slot, order = folio_order(folio); + + if (WARN_ON_ONCE(!rreq->buffer && tail) || + WARN_ON_ONCE(rreq->buffer && !tail)) + return -EIO; + + if (!tail || folioq_full(tail)) { + tail = kmalloc(sizeof(*tail), GFP_NOFS); + if (!tail) + return -ENOMEM; + netfs_stat(&netfs_n_folioq); + folioq_init(tail); + tail->prev = rreq->buffer_tail; + if (tail->prev) + tail->prev->next = tail; + rreq->buffer_tail = tail; + if (!rreq->buffer) { + rreq->buffer = tail; + iov_iter_folio_queue(&rreq->io_iter, ITER_SOURCE, tail, 0, 0, 0); + } + rreq->buffer_tail_slot = 0; + } + + rreq->io_iter.count += PAGE_SIZE << order; + + slot = folioq_append(tail, folio); + /* Store the counter after setting the slot. */ + smp_store_release(&rreq->buffer_tail_slot, slot); + return 0; +} + +/* + * Delete the head of a rolling queue. + */ +struct folio_queue *netfs_delete_buffer_head(struct netfs_io_request *wreq) +{ + struct folio_queue *head = wreq->buffer, *next = head->next; + + if (next) + next->prev = NULL; + netfs_stat_d(&netfs_n_folioq); + kfree(head); + wreq->buffer = next; + return next; +} + +/* + * Clear out a rolling queue. + */ +void netfs_clear_buffer(struct netfs_io_request *rreq) +{ + struct folio_queue *p; + + while ((p = rreq->buffer)) { + rreq->buffer = p->next; + for (int slot = 0; slot < folioq_nr_slots(p); slot++) { + struct folio *folio = folioq_folio(p, slot); + if (!folio) + continue; + if (folioq_is_marked(p, slot)) { + trace_netfs_folio(folio, netfs_folio_trace_put); + folio_put(folio); + } + } + netfs_stat_d(&netfs_n_folioq); + kfree(p); + } +} + +/* + * Reset the subrequest iterator to refer just to the region remaining to be + * read. The iterator may or may not have been advanced by socket ops or + * extraction ops to an extent that may or may not match the amount actually + * read. + */ +void netfs_reset_iter(struct netfs_io_subrequest *subreq) +{ + struct iov_iter *io_iter = &subreq->io_iter; + size_t remain = subreq->len - subreq->transferred; + + if (io_iter->count > remain) + iov_iter_advance(io_iter, io_iter->count - remain); + else if (io_iter->count < remain) + iov_iter_revert(io_iter, remain - io_iter->count); + iov_iter_truncate(&subreq->io_iter, remain); +} + /** * netfs_dirty_folio - Mark folio dirty and pin a cache object for writeback * @mapping: The mapping the folio belongs to. diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c index 0294df70c3ff..31e388ec6e48 100644 --- a/fs/netfs/objects.c +++ b/fs/netfs/objects.c @@ -36,7 +36,6 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping, memset(rreq, 0, kmem_cache_size(cache)); rreq->start = start; rreq->len = len; - rreq->upper_len = len; rreq->origin = origin; rreq->netfs_ops = ctx->ops; rreq->mapping = mapping; @@ -44,13 +43,23 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping, rreq->i_size = i_size_read(inode); rreq->debug_id = atomic_inc_return(&debug_ids); rreq->wsize = INT_MAX; + rreq->io_streams[0].sreq_max_len = ULONG_MAX; + rreq->io_streams[0].sreq_max_segs = 0; spin_lock_init(&rreq->lock); INIT_LIST_HEAD(&rreq->io_streams[0].subrequests); INIT_LIST_HEAD(&rreq->io_streams[1].subrequests); INIT_LIST_HEAD(&rreq->subrequests); - INIT_WORK(&rreq->work, NULL); refcount_set(&rreq->ref, 1); + if (origin == NETFS_READAHEAD || + origin == NETFS_READPAGE || + origin == NETFS_READ_GAPS || + origin == NETFS_READ_FOR_WRITE || + origin == NETFS_DIO_READ) + INIT_WORK(&rreq->work, netfs_read_termination_worker); + else + INIT_WORK(&rreq->work, netfs_write_collection_worker); + __set_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags); if (file && file->f_flags & O_NONBLOCK) __set_bit(NETFS_RREQ_NONBLOCK, &rreq->flags); @@ -134,6 +143,7 @@ static void netfs_free_request(struct work_struct *work) } kvfree(rreq->direct_bv); } + netfs_clear_buffer(rreq); if (atomic_dec_and_test(&ictx->io_count)) wake_up_var(&ictx->io_count); @@ -155,7 +165,7 @@ void netfs_put_request(struct netfs_io_request *rreq, bool was_async, if (was_async) { rreq->work.func = netfs_free_request; if (!queue_work(system_unbound_wq, &rreq->work)) - BUG(); + WARN_ON(1); } else { netfs_free_request(&rreq->work); } diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c new file mode 100644 index 000000000000..b18c65ba5580 --- /dev/null +++ b/fs/netfs/read_collect.c @@ -0,0 +1,544 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Network filesystem read subrequest result collection, assessment and + * retrying. + * + * Copyright (C) 2024 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include <linux/export.h> +#include <linux/fs.h> +#include <linux/mm.h> +#include <linux/pagemap.h> +#include <linux/slab.h> +#include <linux/task_io_accounting_ops.h> +#include "internal.h" + +/* + * Clear the unread part of an I/O request. + */ +static void netfs_clear_unread(struct netfs_io_subrequest *subreq) +{ + netfs_reset_iter(subreq); + WARN_ON_ONCE(subreq->len - subreq->transferred != iov_iter_count(&subreq->io_iter)); + iov_iter_zero(iov_iter_count(&subreq->io_iter), &subreq->io_iter); + if (subreq->start + subreq->transferred >= subreq->rreq->i_size) + __set_bit(NETFS_SREQ_HIT_EOF, &subreq->flags); +} + +/* + * Flush, mark and unlock a folio that's now completely read. If we want to + * cache the folio, we set the group to NETFS_FOLIO_COPY_TO_CACHE, mark it + * dirty and let writeback handle it. + */ +static void netfs_unlock_read_folio(struct netfs_io_subrequest *subreq, + struct netfs_io_request *rreq, + struct folio_queue *folioq, + int slot) +{ + struct netfs_folio *finfo; + struct folio *folio = folioq_folio(folioq, slot); + + flush_dcache_folio(folio); + folio_mark_uptodate(folio); + + if (!test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags)) { + finfo = netfs_folio_info(folio); + if (finfo) { + trace_netfs_folio(folio, netfs_folio_trace_filled_gaps); + if (finfo->netfs_group) + folio_change_private(folio, finfo->netfs_group); + else + folio_detach_private(folio); + kfree(finfo); + } + + if (test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) { + if (!WARN_ON_ONCE(folio_get_private(folio) != NULL)) { + trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache); + folio_attach_private(folio, NETFS_FOLIO_COPY_TO_CACHE); + folio_mark_dirty(folio); + } + } else { + trace_netfs_folio(folio, netfs_folio_trace_read_done); + } + } else { + // TODO: Use of PG_private_2 is deprecated. + if (test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) + netfs_pgpriv2_mark_copy_to_cache(subreq, rreq, folioq, slot); + } + + if (!test_bit(NETFS_RREQ_DONT_UNLOCK_FOLIOS, &rreq->flags)) { + if (folio->index == rreq->no_unlock_folio && + test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags)) { + _debug("no unlock"); + } else { + trace_netfs_folio(folio, netfs_folio_trace_read_unlock); + folio_unlock(folio); + } + } +} + +/* + * Unlock any folios that are now completely read. Returns true if the + * subrequest is removed from the list. + */ +static bool netfs_consume_read_data(struct netfs_io_subrequest *subreq, bool was_async) +{ + struct netfs_io_subrequest *prev, *next; + struct netfs_io_request *rreq = subreq->rreq; + struct folio_queue *folioq = subreq->curr_folioq; + size_t avail, prev_donated, next_donated, fsize, part, excess; + loff_t fpos, start; + loff_t fend; + int slot = subreq->curr_folioq_slot; + + if (WARN(subreq->transferred > subreq->len, + "Subreq overread: R%x[%x] %zu > %zu", + rreq->debug_id, subreq->debug_index, + subreq->transferred, subreq->len)) + subreq->transferred = subreq->len; + +next_folio: + fsize = PAGE_SIZE << subreq->curr_folio_order; + fpos = round_down(subreq->start + subreq->consumed, fsize); + fend = fpos + fsize; + + if (WARN_ON_ONCE(!folioq) || + WARN_ON_ONCE(!folioq_folio(folioq, slot)) || + WARN_ON_ONCE(folioq_folio(folioq, slot)->index != fpos / PAGE_SIZE)) { + pr_err("R=%08x[%x] s=%llx-%llx ctl=%zx/%zx/%zx sl=%u\n", + rreq->debug_id, subreq->debug_index, + subreq->start, subreq->start + subreq->transferred - 1, + subreq->consumed, subreq->transferred, subreq->len, + slot); + if (folioq) { + struct folio *folio = folioq_folio(folioq, slot); + + pr_err("folioq: orders=%02x%02x%02x%02x\n", + folioq->orders[0], folioq->orders[1], + folioq->orders[2], folioq->orders[3]); + if (folio) + pr_err("folio: %llx-%llx ix=%llx o=%u qo=%u\n", + fpos, fend - 1, folio_pos(folio), folio_order(folio), + folioq_folio_order(folioq, slot)); + } + } + +donation_changed: + /* Try to consume the current folio if we've hit or passed the end of + * it. There's a possibility that this subreq doesn't start at the + * beginning of the folio, in which case we need to donate to/from the + * preceding subreq. + * + * We also need to include any potential donation back from the + * following subreq. + */ + prev_donated = READ_ONCE(subreq->prev_donated); + next_donated = READ_ONCE(subreq->next_donated); + if (prev_donated || next_donated) { + spin_lock_bh(&rreq->lock); + prev_donated = subreq->prev_donated; + next_donated = subreq->next_donated; + subreq->start -= prev_donated; + subreq->len += prev_donated; + subreq->transferred += prev_donated; + prev_donated = subreq->prev_donated = 0; + if (subreq->transferred == subreq->len) { + subreq->len += next_donated; + subreq->transferred += next_donated; + next_donated = subreq->next_donated = 0; + } + trace_netfs_sreq(subreq, netfs_sreq_trace_add_donations); + spin_unlock_bh(&rreq->lock); + } + + avail = subreq->transferred; + if (avail == subreq->len) + avail += next_donated; + start = subreq->start; + if (subreq->consumed == 0) { + start -= prev_donated; + avail += prev_donated; + } else { + start += subreq->consumed; + avail -= subreq->consumed; + } + part = umin(avail, fsize); + + trace_netfs_progress(subreq, start, avail, part); + + if (start + avail >= fend) { + if (fpos == start) { + /* Flush, unlock and mark for caching any folio we've just read. */ + subreq->consumed = fend - subreq->start; + netfs_unlock_read_folio(subreq, rreq, folioq, slot); + folioq_mark2(folioq, slot); + if (subreq->consumed >= subreq->len) + goto remove_subreq; + } else if (fpos < start) { + excess = fend - subreq->start; + + spin_lock_bh(&rreq->lock); + /* If we complete first on a folio split with the + * preceding subreq, donate to that subreq - otherwise + * we get the responsibility. + */ + if (subreq->prev_donated != prev_donated) { + spin_unlock_bh(&rreq->lock); + goto donation_changed; + } + + if (list_is_first(&subreq->rreq_link, &rreq->subrequests)) { + spin_unlock_bh(&rreq->lock); + pr_err("Can't donate prior to front\n"); + goto bad; + } + + prev = list_prev_entry(subreq, rreq_link); + WRITE_ONCE(prev->next_donated, prev->next_donated + excess); + subreq->start += excess; + subreq->len -= excess; + subreq->transferred -= excess; + trace_netfs_donate(rreq, subreq, prev, excess, + netfs_trace_donate_tail_to_prev); + trace_netfs_sreq(subreq, netfs_sreq_trace_donate_to_prev); + + if (subreq->consumed >= subreq->len) + goto remove_subreq_locked; + spin_unlock_bh(&rreq->lock); + } else { + pr_err("fpos > start\n"); + goto bad; + } + + /* Advance the rolling buffer to the next folio. */ + slot++; + if (slot >= folioq_nr_slots(folioq)) { + slot = 0; + folioq = folioq->next; + subreq->curr_folioq = folioq; + } + subreq->curr_folioq_slot = slot; + if (folioq && folioq_folio(folioq, slot)) + subreq->curr_folio_order = folioq->orders[slot]; + if (!was_async) + cond_resched(); + goto next_folio; + } + + /* Deal with partial progress. */ + if (subreq->transferred < subreq->len) + return false; + + /* Donate the remaining downloaded data to one of the neighbouring + * subrequests. Note that we may race with them doing the same thing. + */ + spin_lock_bh(&rreq->lock); + + if (subreq->prev_donated != prev_donated || + subreq->next_donated != next_donated) { + spin_unlock_bh(&rreq->lock); + cond_resched(); + goto donation_changed; + } + + /* Deal with the trickiest case: that this subreq is in the middle of a + * folio, not touching either edge, but finishes first. In such a + * case, we donate to the previous subreq, if there is one, so that the + * donation is only handled when that completes - and remove this + * subreq from the list. + * + * If the previous subreq finished first, we will have acquired their + * donation and should be able to unlock folios and/or donate nextwards. + */ + if (!subreq->consumed && + !prev_donated && + !list_is_first(&subreq->rreq_link, &rreq->subrequests)) { + prev = list_prev_entry(subreq, rreq_link); + WRITE_ONCE(prev->next_donated, prev->next_donated + subreq->len); + subreq->start += subreq->len; + subreq->len = 0; + subreq->transferred = 0; + trace_netfs_donate(rreq, subreq, prev, subreq->len, + netfs_trace_donate_to_prev); + trace_netfs_sreq(subreq, netfs_sreq_trace_donate_to_prev); + goto remove_subreq_locked; + } + + /* If we can't donate down the chain, donate up the chain instead. */ + excess = subreq->len - subreq->consumed + next_donated; + + if (!subreq->consumed) + excess += prev_donated; + + if (list_is_last(&subreq->rreq_link, &rreq->subrequests)) { + rreq->prev_donated = excess; + trace_netfs_donate(rreq, subreq, NULL, excess, + netfs_trace_donate_to_deferred_next); + } else { + next = list_next_entry(subreq, rreq_link); + WRITE_ONCE(next->prev_donated, excess); + trace_netfs_donate(rreq, subreq, next, excess, + netfs_trace_donate_to_next); + } + trace_netfs_sreq(subreq, netfs_sreq_trace_donate_to_next); + subreq->len = subreq->consumed; + subreq->transferred = subreq->consumed; + goto remove_subreq_locked; + +remove_subreq: + spin_lock_bh(&rreq->lock); +remove_subreq_locked: + subreq->consumed = subreq->len; + list_del(&subreq->rreq_link); + spin_unlock_bh(&rreq->lock); + netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_consumed); + return true; + +bad: + /* Errr... prev and next both donated to us, but insufficient to finish + * the folio. + */ + printk("R=%08x[%x] s=%llx-%llx %zx/%zx/%zx\n", + rreq->debug_id, subreq->debug_index, + subreq->start, subreq->start + subreq->transferred - 1, + subreq->consumed, subreq->transferred, subreq->len); + printk("folio: %llx-%llx\n", fpos, fend - 1); + printk("donated: prev=%zx next=%zx\n", prev_donated, next_donated); + printk("s=%llx av=%zx part=%zx\n", start, avail, part); + BUG(); +} + +/* + * Do page flushing and suchlike after DIO. + */ +static void netfs_rreq_assess_dio(struct netfs_io_request *rreq) +{ + struct netfs_io_subrequest *subreq; + unsigned int i; + + /* Collect unbuffered reads and direct reads, adding up the transfer + * sizes until we find the first short or failed subrequest. + */ + list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { + rreq->transferred += subreq->transferred; + + if (subreq->transferred < subreq->len || + test_bit(NETFS_SREQ_FAILED, &subreq->flags)) { + rreq->error = subreq->error; + break; + } + } + + if (rreq->origin == NETFS_DIO_READ) { + for (i = 0; i < rreq->direct_bv_count; i++) { + flush_dcache_page(rreq->direct_bv[i].bv_page); + // TODO: cifs marks pages in the destination buffer + // dirty under some circumstances after a read. Do we + // need to do that too? + set_page_dirty(rreq->direct_bv[i].bv_page); + } + } + + if (rreq->iocb) { + rreq->iocb->ki_pos += rreq->transferred; + if (rreq->iocb->ki_complete) + rreq->iocb->ki_complete( + rreq->iocb, rreq->error ? rreq->error : rreq->transferred); + } + if (rreq->netfs_ops->done) + rreq->netfs_ops->done(rreq); + if (rreq->origin == NETFS_DIO_READ) + inode_dio_end(rreq->inode); +} + +/* + * Assess the state of a read request and decide what to do next. + * + * Note that we're in normal kernel thread context at this point, possibly + * running on a workqueue. + */ +static void netfs_rreq_assess(struct netfs_io_request *rreq) +{ + trace_netfs_rreq(rreq, netfs_rreq_trace_assess); + + //netfs_rreq_is_still_valid(rreq); + + if (test_and_clear_bit(NETFS_RREQ_NEED_RETRY, &rreq->flags)) { + netfs_retry_reads(rreq); + return; + } + + if (rreq->origin == NETFS_DIO_READ || + rreq->origin == NETFS_READ_GAPS) + netfs_rreq_assess_dio(rreq); + task_io_account_read(rreq->transferred); + + trace_netfs_rreq(rreq, netfs_rreq_trace_wake_ip); + clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &rreq->flags); + wake_up_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS); + + trace_netfs_rreq(rreq, netfs_rreq_trace_done); + netfs_clear_subrequests(rreq, false); + netfs_unlock_abandoned_read_pages(rreq); + if (unlikely(test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags))) + netfs_pgpriv2_write_to_the_cache(rreq); +} + +void netfs_read_termination_worker(struct work_struct *work) +{ + struct netfs_io_request *rreq = + container_of(work, struct netfs_io_request, work); + netfs_see_request(rreq, netfs_rreq_trace_see_work); + netfs_rreq_assess(rreq); + netfs_put_request(rreq, false, netfs_rreq_trace_put_work_complete); +} + +/* + * Handle the completion of all outstanding I/O operations on a read request. + * We inherit a ref from the caller. + */ +void netfs_rreq_terminated(struct netfs_io_request *rreq, bool was_async) +{ + if (!was_async) + return netfs_rreq_assess(rreq); + if (!work_pending(&rreq->work)) { + netfs_get_request(rreq, netfs_rreq_trace_get_work); + if (!queue_work(system_unbound_wq, &rreq->work)) + netfs_put_request(rreq, was_async, netfs_rreq_trace_put_work_nq); + } +} + +/** + * netfs_read_subreq_progress - Note progress of a read operation. + * @subreq: The read request that has terminated. + * @was_async: True if we're in an asynchronous context. + * + * This tells the read side of netfs lib that a contributory I/O operation has + * made some progress and that it may be possible to unlock some folios. + * + * Before calling, the filesystem should update subreq->transferred to track + * the amount of data copied into the output buffer. + * + * If @was_async is true, the caller might be running in softirq or interrupt + * context and we can't sleep. + */ +void netfs_read_subreq_progress(struct netfs_io_subrequest *subreq, + bool was_async) +{ + struct netfs_io_request *rreq = subreq->rreq; + + trace_netfs_sreq(subreq, netfs_sreq_trace_progress); + + if (subreq->transferred > subreq->consumed && + (rreq->origin == NETFS_READAHEAD || + rreq->origin == NETFS_READPAGE || + rreq->origin == NETFS_READ_FOR_WRITE)) { + netfs_consume_read_data(subreq, was_async); + __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); + } +} +EXPORT_SYMBOL(netfs_read_subreq_progress); + +/** + * netfs_read_subreq_terminated - Note the termination of an I/O operation. + * @subreq: The I/O request that has terminated. + * @error: Error code indicating type of completion. + * @was_async: The termination was asynchronous + * + * This tells the read helper that a contributory I/O operation has terminated, + * one way or another, and that it should integrate the results. + * + * The caller indicates the outcome of the operation through @error, supplying + * 0 to indicate a successful or retryable transfer (if NETFS_SREQ_NEED_RETRY + * is set) or a negative error code. The helper will look after reissuing I/O + * operations as appropriate and writing downloaded data to the cache. + * + * Before calling, the filesystem should update subreq->transferred to track + * the amount of data copied into the output buffer. + * + * If @was_async is true, the caller might be running in softirq or interrupt + * context and we can't sleep. + */ +void netfs_read_subreq_terminated(struct netfs_io_subrequest *subreq, + int error, bool was_async) +{ + struct netfs_io_request *rreq = subreq->rreq; + + switch (subreq->source) { + case NETFS_READ_FROM_CACHE: + netfs_stat(&netfs_n_rh_read_done); + break; + case NETFS_DOWNLOAD_FROM_SERVER: + netfs_stat(&netfs_n_rh_download_done); + break; + default: + break; + } + + if (rreq->origin != NETFS_DIO_READ) { + /* Collect buffered reads. + * + * If the read completed validly short, then we can clear the + * tail before going on to unlock the folios. + */ + if (error == 0 && subreq->transferred < subreq->len && + (test_bit(NETFS_SREQ_HIT_EOF, &subreq->flags) || + test_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags))) { + netfs_clear_unread(subreq); + subreq->transferred = subreq->len; + trace_netfs_sreq(subreq, netfs_sreq_trace_clear); + } + if (subreq->transferred > subreq->consumed && + (rreq->origin == NETFS_READAHEAD || + rreq->origin == NETFS_READPAGE || + rreq->origin == NETFS_READ_FOR_WRITE)) { + netfs_consume_read_data(subreq, was_async); + __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); + } + rreq->transferred += subreq->transferred; + } + + /* Deal with retry requests, short reads and errors. If we retry + * but don't make progress, we abandon the attempt. + */ + if (!error && subreq->transferred < subreq->len) { + if (test_bit(NETFS_SREQ_HIT_EOF, &subreq->flags)) { + trace_netfs_sreq(subreq, netfs_sreq_trace_hit_eof); + } else { + trace_netfs_sreq(subreq, netfs_sreq_trace_short); + if (subreq->transferred > subreq->consumed) { + __set_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); + __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); + set_bit(NETFS_RREQ_NEED_RETRY, &rreq->flags); + } else if (!__test_and_set_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags)) { + __set_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); + set_bit(NETFS_RREQ_NEED_RETRY, &rreq->flags); + } else { + __set_bit(NETFS_SREQ_FAILED, &subreq->flags); + error = -ENODATA; + } + } + } + + subreq->error = error; + trace_netfs_sreq(subreq, netfs_sreq_trace_terminated); + + if (unlikely(error < 0)) { + trace_netfs_failure(rreq, subreq, error, netfs_fail_read); + if (subreq->source == NETFS_READ_FROM_CACHE) { + netfs_stat(&netfs_n_rh_read_failed); + } else { + netfs_stat(&netfs_n_rh_download_failed); + set_bit(NETFS_RREQ_FAILED, &rreq->flags); + rreq->error = subreq->error; + } + } + + if (atomic_dec_and_test(&rreq->nr_outstanding)) + netfs_rreq_terminated(rreq, was_async); + + netfs_put_subrequest(subreq, was_async, netfs_sreq_trace_put_terminated); +} +EXPORT_SYMBOL(netfs_read_subreq_terminated); diff --git a/fs/netfs/read_pgpriv2.c b/fs/netfs/read_pgpriv2.c new file mode 100644 index 000000000000..ba5af89d37fa --- /dev/null +++ b/fs/netfs/read_pgpriv2.c @@ -0,0 +1,264 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Read with PG_private_2 [DEPRECATED]. + * + * Copyright (C) 2024 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include <linux/export.h> +#include <linux/fs.h> +#include <linux/mm.h> +#include <linux/pagemap.h> +#include <linux/slab.h> +#include <linux/task_io_accounting_ops.h> +#include "internal.h" + +/* + * [DEPRECATED] Mark page as requiring copy-to-cache using PG_private_2. The + * third mark in the folio queue is used to indicate that this folio needs + * writing. + */ +void netfs_pgpriv2_mark_copy_to_cache(struct netfs_io_subrequest *subreq, + struct netfs_io_request *rreq, + struct folio_queue *folioq, + int slot) +{ + struct folio *folio = folioq_folio(folioq, slot); + + trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache); + folio_start_private_2(folio); + folioq_mark3(folioq, slot); +} + +/* + * [DEPRECATED] Cancel PG_private_2 on all marked folios in the event of an + * unrecoverable error. + */ +static void netfs_pgpriv2_cancel(struct folio_queue *folioq) +{ + struct folio *folio; + int slot; + + while (folioq) { + if (!folioq->marks3) { + folioq = folioq->next; + continue; + } + + slot = __ffs(folioq->marks3); + folio = folioq_folio(folioq, slot); + + trace_netfs_folio(folio, netfs_folio_trace_cancel_copy); + folio_end_private_2(folio); + folioq_unmark3(folioq, slot); + } +} + +/* + * [DEPRECATED] Copy a folio to the cache with PG_private_2 set. + */ +static int netfs_pgpriv2_copy_folio(struct netfs_io_request *wreq, struct folio *folio) +{ + struct netfs_io_stream *cache = &wreq->io_streams[1]; + size_t fsize = folio_size(folio), flen = fsize; + loff_t fpos = folio_pos(folio), i_size; + bool to_eof = false; + + _enter(""); + + /* netfs_perform_write() may shift i_size around the page or from out + * of the page to beyond it, but cannot move i_size into or through the + * page since we have it locked. + */ + i_size = i_size_read(wreq->inode); + + if (fpos >= i_size) { + /* mmap beyond eof. */ + _debug("beyond eof"); + folio_end_private_2(folio); + return 0; + } + + if (fpos + fsize > wreq->i_size) + wreq->i_size = i_size; + + if (flen > i_size - fpos) { + flen = i_size - fpos; + to_eof = true; + } else if (flen == i_size - fpos) { + to_eof = true; + } + + _debug("folio %zx %zx", flen, fsize); + + trace_netfs_folio(folio, netfs_folio_trace_store_copy); + + /* Attach the folio to the rolling buffer. */ + if (netfs_buffer_append_folio(wreq, folio, false) < 0) + return -ENOMEM; + + cache->submit_extendable_to = fsize; + cache->submit_off = 0; + cache->submit_len = flen; + + /* Attach the folio to one or more subrequests. For a big folio, we + * could end up with thousands of subrequests if the wsize is small - + * but we might need to wait during the creation of subrequests for + * network resources (eg. SMB credits). + */ + do { + ssize_t part; + + wreq->io_iter.iov_offset = cache->submit_off; + + atomic64_set(&wreq->issued_to, fpos + cache->submit_off); + cache->submit_extendable_to = fsize - cache->submit_off; + part = netfs_advance_write(wreq, cache, fpos + cache->submit_off, + cache->submit_len, to_eof); + cache->submit_off += part; + if (part > cache->submit_len) + cache->submit_len = 0; + else + cache->submit_len -= part; + } while (cache->submit_len > 0); + + wreq->io_iter.iov_offset = 0; + iov_iter_advance(&wreq->io_iter, fsize); + atomic64_set(&wreq->issued_to, fpos + fsize); + + if (flen < fsize) + netfs_issue_write(wreq, cache); + + _leave(" = 0"); + return 0; +} + +/* + * [DEPRECATED] Go through the buffer and write any folios that are marked with + * the third mark to the cache. + */ +void netfs_pgpriv2_write_to_the_cache(struct netfs_io_request *rreq) +{ + struct netfs_io_request *wreq; + struct folio_queue *folioq; + struct folio *folio; + int error = 0; + int slot = 0; + + _enter(""); + + if (!fscache_resources_valid(&rreq->cache_resources)) + goto couldnt_start; + + /* Need the first folio to be able to set up the op. */ + for (folioq = rreq->buffer; folioq; folioq = folioq->next) { + if (folioq->marks3) { + slot = __ffs(folioq->marks3); + break; + } + } + if (!folioq) + return; + folio = folioq_folio(folioq, slot); + + wreq = netfs_create_write_req(rreq->mapping, NULL, folio_pos(folio), + NETFS_PGPRIV2_COPY_TO_CACHE); + if (IS_ERR(wreq)) { + kleave(" [create %ld]", PTR_ERR(wreq)); + goto couldnt_start; + } + + trace_netfs_write(wreq, netfs_write_trace_copy_to_cache); + netfs_stat(&netfs_n_wh_copy_to_cache); + + for (;;) { + error = netfs_pgpriv2_copy_folio(wreq, folio); + if (error < 0) + break; + + folioq_unmark3(folioq, slot); + if (!folioq->marks3) { + folioq = folioq->next; + if (!folioq) + break; + } + + slot = __ffs(folioq->marks3); + folio = folioq_folio(folioq, slot); + } + + netfs_issue_write(wreq, &wreq->io_streams[1]); + smp_wmb(); /* Write lists before ALL_QUEUED. */ + set_bit(NETFS_RREQ_ALL_QUEUED, &wreq->flags); + + netfs_put_request(wreq, false, netfs_rreq_trace_put_return); + _leave(" = %d", error); +couldnt_start: + netfs_pgpriv2_cancel(rreq->buffer); +} + +/* + * [DEPRECATED] Remove the PG_private_2 mark from any folios we've finished + * copying. + */ +bool netfs_pgpriv2_unlock_copied_folios(struct netfs_io_request *wreq) +{ + struct folio_queue *folioq = wreq->buffer; + unsigned long long collected_to = wreq->collected_to; + unsigned int slot = wreq->buffer_head_slot; + bool made_progress = false; + + if (slot >= folioq_nr_slots(folioq)) { + folioq = netfs_delete_buffer_head(wreq); + slot = 0; + } + + for (;;) { + struct folio *folio; + unsigned long long fpos, fend; + size_t fsize, flen; + + folio = folioq_folio(folioq, slot); + if (WARN_ONCE(!folio_test_private_2(folio), + "R=%08x: folio %lx is not marked private_2\n", + wreq->debug_id, folio->index)) + trace_netfs_folio(folio, netfs_folio_trace_not_under_wback); + + fpos = folio_pos(folio); + fsize = folio_size(folio); + flen = fsize; + + fend = min_t(unsigned long long, fpos + flen, wreq->i_size); + + trace_netfs_collect_folio(wreq, folio, fend, collected_to); + + /* Unlock any folio we've transferred all of. */ + if (collected_to < fend) + break; + + trace_netfs_folio(folio, netfs_folio_trace_end_copy); + folio_end_private_2(folio); + wreq->cleaned_to = fpos + fsize; + made_progress = true; + + /* Clean up the head folioq. If we clear an entire folioq, then + * we can get rid of it provided it's not also the tail folioq + * being filled by the issuer. + */ + folioq_clear(folioq, slot); + slot++; + if (slot >= folioq_nr_slots(folioq)) { + if (READ_ONCE(wreq->buffer_tail) == folioq) + break; + folioq = netfs_delete_buffer_head(wreq); + slot = 0; + } + + if (fpos + fsize >= collected_to) + break; + } + + wreq->buffer = folioq; + wreq->buffer_head_slot = slot; + return made_progress; +} diff --git a/fs/netfs/read_retry.c b/fs/netfs/read_retry.c new file mode 100644 index 000000000000..0350592ea804 --- /dev/null +++ b/fs/netfs/read_retry.c @@ -0,0 +1,256 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Network filesystem read subrequest retrying. + * + * Copyright (C) 2024 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include <linux/fs.h> +#include <linux/slab.h> +#include "internal.h" + +static void netfs_reissue_read(struct netfs_io_request *rreq, + struct netfs_io_subrequest *subreq) +{ + struct iov_iter *io_iter = &subreq->io_iter; + + if (iov_iter_is_folioq(io_iter)) { + subreq->curr_folioq = (struct folio_queue *)io_iter->folioq; + subreq->curr_folioq_slot = io_iter->folioq_slot; + subreq->curr_folio_order = subreq->curr_folioq->orders[subreq->curr_folioq_slot]; + } + + atomic_inc(&rreq->nr_outstanding); + __set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); + netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); + subreq->rreq->netfs_ops->issue_read(subreq); +} + +/* + * Go through the list of failed/short reads, retrying all retryable ones. We + * need to switch failed cache reads to network downloads. + */ +static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) +{ + struct netfs_io_subrequest *subreq; + struct netfs_io_stream *stream0 = &rreq->io_streams[0]; + LIST_HEAD(sublist); + LIST_HEAD(queue); + + _enter("R=%x", rreq->debug_id); + + if (list_empty(&rreq->subrequests)) + return; + + if (rreq->netfs_ops->retry_request) + rreq->netfs_ops->retry_request(rreq, NULL); + + /* If there's no renegotiation to do, just resend each retryable subreq + * up to the first permanently failed one. + */ + if (!rreq->netfs_ops->prepare_read && + !test_bit(NETFS_RREQ_COPY_TO_CACHE, &rreq->flags)) { + struct netfs_io_subrequest *subreq; + + list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { + if (test_bit(NETFS_SREQ_FAILED, &subreq->flags)) + break; + if (__test_and_clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags)) { + netfs_reset_iter(subreq); + netfs_reissue_read(rreq, subreq); + } + } + return; + } + + /* Okay, we need to renegotiate all the download requests and flip any + * failed cache reads over to being download requests and negotiate + * those also. All fully successful subreqs have been removed from the + * list and any spare data from those has been donated. + * + * What we do is decant the list and rebuild it one subreq at a time so + * that we don't end up with donations jumping over a gap we're busy + * populating with smaller subrequests. In the event that the subreq + * we just launched finishes before we insert the next subreq, it'll + * fill in rreq->prev_donated instead. + + * Note: Alternatively, we could split the tail subrequest right before + * we reissue it and fix up the donations under lock. + */ + list_splice_init(&rreq->subrequests, &queue); + + do { + struct netfs_io_subrequest *from; + struct iov_iter source; + unsigned long long start, len; + size_t part, deferred_next_donated = 0; + bool boundary = false; + + /* Go through the subreqs and find the next span of contiguous + * buffer that we then rejig (cifs, for example, needs the + * rsize renegotiating) and reissue. + */ + from = list_first_entry(&queue, struct netfs_io_subrequest, rreq_link); + list_move_tail(&from->rreq_link, &sublist); + start = from->start + from->transferred; + len = from->len - from->transferred; + + _debug("from R=%08x[%x] s=%llx ctl=%zx/%zx/%zx", + rreq->debug_id, from->debug_index, + from->start, from->consumed, from->transferred, from->len); + + if (test_bit(NETFS_SREQ_FAILED, &from->flags) || + !test_bit(NETFS_SREQ_NEED_RETRY, &from->flags)) + goto abandon; + + deferred_next_donated = from->next_donated; + while ((subreq = list_first_entry_or_null( + &queue, struct netfs_io_subrequest, rreq_link))) { + if (subreq->start != start + len || + subreq->transferred > 0 || + !test_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags)) + break; + list_move_tail(&subreq->rreq_link, &sublist); + len += subreq->len; + deferred_next_donated = subreq->next_donated; + if (test_bit(NETFS_SREQ_BOUNDARY, &subreq->flags)) + break; + } + + _debug(" - range: %llx-%llx %llx", start, start + len - 1, len); + + /* Determine the set of buffers we're going to use. Each + * subreq gets a subset of a single overall contiguous buffer. + */ + netfs_reset_iter(from); + source = from->io_iter; + source.count = len; + + /* Work through the sublist. */ + while ((subreq = list_first_entry_or_null( + &sublist, struct netfs_io_subrequest, rreq_link))) { + list_del(&subreq->rreq_link); + + subreq->source = NETFS_DOWNLOAD_FROM_SERVER; + subreq->start = start - subreq->transferred; + subreq->len = len + subreq->transferred; + stream0->sreq_max_len = subreq->len; + + __clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); + __set_bit(NETFS_SREQ_RETRYING, &subreq->flags); + + spin_lock_bh(&rreq->lock); + list_add_tail(&subreq->rreq_link, &rreq->subrequests); + subreq->prev_donated += rreq->prev_donated; + rreq->prev_donated = 0; + trace_netfs_sreq(subreq, netfs_sreq_trace_retry); + spin_unlock_bh(&rreq->lock); + + BUG_ON(!len); + + /* Renegotiate max_len (rsize) */ + if (rreq->netfs_ops->prepare_read(subreq) < 0) { + trace_netfs_sreq(subreq, netfs_sreq_trace_reprep_failed); + __set_bit(NETFS_SREQ_FAILED, &subreq->flags); + } + + part = umin(len, stream0->sreq_max_len); + if (unlikely(rreq->io_streams[0].sreq_max_segs)) + part = netfs_limit_iter(&source, 0, part, stream0->sreq_max_segs); + subreq->len = subreq->transferred + part; + subreq->io_iter = source; + iov_iter_truncate(&subreq->io_iter, part); + iov_iter_advance(&source, part); + len -= part; + start += part; + if (!len) { + if (boundary) + __set_bit(NETFS_SREQ_BOUNDARY, &subreq->flags); + subreq->next_donated = deferred_next_donated; + } else { + __clear_bit(NETFS_SREQ_BOUNDARY, &subreq->flags); + subreq->next_donated = 0; + } + + netfs_reissue_read(rreq, subreq); + if (!len) + break; + + /* If we ran out of subrequests, allocate another. */ + if (list_empty(&sublist)) { + subreq = netfs_alloc_subrequest(rreq); + if (!subreq) + goto abandon; + subreq->source = NETFS_DOWNLOAD_FROM_SERVER; + subreq->start = start; + + /* We get two refs, but need just one. */ + netfs_put_subrequest(subreq, false, netfs_sreq_trace_new); + trace_netfs_sreq(subreq, netfs_sreq_trace_split); + list_add_tail(&subreq->rreq_link, &sublist); + } + } + + /* If we managed to use fewer subreqs, we can discard the + * excess. + */ + while ((subreq = list_first_entry_or_null( + &sublist, struct netfs_io_subrequest, rreq_link))) { + trace_netfs_sreq(subreq, netfs_sreq_trace_discard); + list_del(&subreq->rreq_link); + netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_done); + } + + } while (!list_empty(&queue)); + + return; + + /* If we hit ENOMEM, fail all remaining subrequests */ +abandon: + list_splice_init(&sublist, &queue); + list_for_each_entry(subreq, &queue, rreq_link) { + if (!subreq->error) + subreq->error = -ENOMEM; + __clear_bit(NETFS_SREQ_FAILED, &subreq->flags); + __clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); + __clear_bit(NETFS_SREQ_RETRYING, &subreq->flags); + } + spin_lock_bh(&rreq->lock); + list_splice_tail_init(&queue, &rreq->subrequests); + spin_unlock_bh(&rreq->lock); +} + +/* + * Retry reads. + */ +void netfs_retry_reads(struct netfs_io_request *rreq) +{ + trace_netfs_rreq(rreq, netfs_rreq_trace_resubmit); + + atomic_inc(&rreq->nr_outstanding); + + netfs_retry_read_subrequests(rreq); + + if (atomic_dec_and_test(&rreq->nr_outstanding)) + netfs_rreq_terminated(rreq, false); +} + +/* + * Unlock any the pages that haven't been unlocked yet due to abandoned + * subrequests. + */ +void netfs_unlock_abandoned_read_pages(struct netfs_io_request *rreq) +{ + struct folio_queue *p; + + for (p = rreq->buffer; p; p = p->next) { + for (int slot = 0; slot < folioq_count(p); slot++) { + struct folio *folio = folioq_folio(p, slot); + + if (folio && !folioq_is_marked2(p, slot)) { + trace_netfs_folio(folio, netfs_folio_trace_abandon); + folio_unlock(folio); + } + } + } +} diff --git a/fs/netfs/stats.c b/fs/netfs/stats.c index 0892768eea32..8e63516b40f6 100644 --- a/fs/netfs/stats.c +++ b/fs/netfs/stats.c @@ -32,6 +32,7 @@ atomic_t netfs_n_wh_buffered_write; atomic_t netfs_n_wh_writethrough; atomic_t netfs_n_wh_dio_write; atomic_t netfs_n_wh_writepages; +atomic_t netfs_n_wh_copy_to_cache; atomic_t netfs_n_wh_wstream_conflict; atomic_t netfs_n_wh_upload; atomic_t netfs_n_wh_upload_done; @@ -39,45 +40,53 @@ atomic_t netfs_n_wh_upload_failed; atomic_t netfs_n_wh_write; atomic_t netfs_n_wh_write_done; atomic_t netfs_n_wh_write_failed; +atomic_t netfs_n_wb_lock_skip; +atomic_t netfs_n_wb_lock_wait; +atomic_t netfs_n_folioq; int netfs_stats_show(struct seq_file *m, void *v) { - seq_printf(m, "Netfs : DR=%u RA=%u RF=%u WB=%u WBZ=%u\n", + seq_printf(m, "Reads : DR=%u RA=%u RF=%u WB=%u WBZ=%u\n", atomic_read(&netfs_n_rh_dio_read), atomic_read(&netfs_n_rh_readahead), atomic_read(&netfs_n_rh_read_folio), atomic_read(&netfs_n_rh_write_begin), atomic_read(&netfs_n_rh_write_zskip)); - seq_printf(m, "Netfs : BW=%u WT=%u DW=%u WP=%u\n", + seq_printf(m, "Writes : BW=%u WT=%u DW=%u WP=%u 2C=%u\n", atomic_read(&netfs_n_wh_buffered_write), atomic_read(&netfs_n_wh_writethrough), atomic_read(&netfs_n_wh_dio_write), - atomic_read(&netfs_n_wh_writepages)); - seq_printf(m, "Netfs : ZR=%u sh=%u sk=%u\n", + atomic_read(&netfs_n_wh_writepages), + atomic_read(&netfs_n_wh_copy_to_cache)); + seq_printf(m, "ZeroOps: ZR=%u sh=%u sk=%u\n", atomic_read(&netfs_n_rh_zero), atomic_read(&netfs_n_rh_short_read), atomic_read(&netfs_n_rh_write_zskip)); - seq_printf(m, "Netfs : DL=%u ds=%u df=%u di=%u\n", + seq_printf(m, "DownOps: DL=%u ds=%u df=%u di=%u\n", atomic_read(&netfs_n_rh_download), atomic_read(&netfs_n_rh_download_done), atomic_read(&netfs_n_rh_download_failed), atomic_read(&netfs_n_rh_download_instead)); - seq_printf(m, "Netfs : RD=%u rs=%u rf=%u\n", + seq_printf(m, "CaRdOps: RD=%u rs=%u rf=%u\n", atomic_read(&netfs_n_rh_read), atomic_read(&netfs_n_rh_read_done), atomic_read(&netfs_n_rh_read_failed)); - seq_printf(m, "Netfs : UL=%u us=%u uf=%u\n", + seq_printf(m, "UpldOps: UL=%u us=%u uf=%u\n", atomic_read(&netfs_n_wh_upload), atomic_read(&netfs_n_wh_upload_done), atomic_read(&netfs_n_wh_upload_failed)); - seq_printf(m, "Netfs : WR=%u ws=%u wf=%u\n", + seq_printf(m, "CaWrOps: WR=%u ws=%u wf=%u\n", atomic_read(&netfs_n_wh_write), atomic_read(&netfs_n_wh_write_done), atomic_read(&netfs_n_wh_write_failed)); - seq_printf(m, "Netfs : rr=%u sr=%u wsc=%u\n", + seq_printf(m, "Objs : rr=%u sr=%u foq=%u wsc=%u\n", atomic_read(&netfs_n_rh_rreq), atomic_read(&netfs_n_rh_sreq), + atomic_read(&netfs_n_folioq), atomic_read(&netfs_n_wh_wstream_conflict)); + seq_printf(m, "WbLock : skip=%u wait=%u\n", + atomic_read(&netfs_n_wb_lock_skip), + atomic_read(&netfs_n_wb_lock_wait)); return fscache_stats_show(m); } EXPORT_SYMBOL(netfs_stats_show); diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c index ae7a2043f670..1d438be2e1b4 100644 --- a/fs/netfs/write_collect.c +++ b/fs/netfs/write_collect.c @@ -15,15 +15,11 @@ /* Notes made in the collector */ #define HIT_PENDING 0x01 /* A front op was still pending */ -#define SOME_EMPTY 0x02 /* One of more streams are empty */ -#define ALL_EMPTY 0x04 /* All streams are empty */ -#define MAYBE_DISCONTIG 0x08 /* A front op may be discontiguous (rounded to PAGE_SIZE) */ -#define NEED_REASSESS 0x10 /* Need to loop round and reassess */ -#define REASSESS_DISCONTIG 0x20 /* Reassess discontiguity if contiguity advances */ -#define MADE_PROGRESS 0x40 /* Made progress cleaning up a stream or the folio set */ -#define BUFFERED 0x80 /* The pagecache needs cleaning up */ -#define NEED_RETRY 0x100 /* A front op requests retrying */ -#define SAW_FAILURE 0x200 /* One stream or hit a permanent failure */ +#define NEED_REASSESS 0x02 /* Need to loop round and reassess */ +#define MADE_PROGRESS 0x04 /* Made progress cleaning up a stream or the folio set */ +#define BUFFERED 0x08 /* The pagecache needs cleaning up */ +#define NEED_RETRY 0x10 /* A front op requests retrying */ +#define SAW_FAILURE 0x20 /* One stream or hit a permanent failure */ /* * Successful completion of write of a folio to the server and/or cache. Note @@ -82,55 +78,37 @@ end_wb: } /* - * Get hold of a folio we have under writeback. We don't want to get the - * refcount on it. + * Unlock any folios we've finished with. */ -static struct folio *netfs_writeback_lookup_folio(struct netfs_io_request *wreq, loff_t pos) +static void netfs_writeback_unlock_folios(struct netfs_io_request *wreq, + unsigned int *notes) { - XA_STATE(xas, &wreq->mapping->i_pages, pos / PAGE_SIZE); - struct folio *folio; - - rcu_read_lock(); - - for (;;) { - xas_reset(&xas); - folio = xas_load(&xas); - if (xas_retry(&xas, folio)) - continue; + struct folio_queue *folioq = wreq->buffer; + unsigned long long collected_to = wreq->collected_to; + unsigned int slot = wreq->buffer_head_slot; - if (!folio || xa_is_value(folio)) - kdebug("R=%08x: folio %lx (%llx) not present", - wreq->debug_id, xas.xa_index, pos / PAGE_SIZE); - BUG_ON(!folio || xa_is_value(folio)); - - if (folio == xas_reload(&xas)) - break; + if (wreq->origin == NETFS_PGPRIV2_COPY_TO_CACHE) { + if (netfs_pgpriv2_unlock_copied_folios(wreq)) + *notes |= MADE_PROGRESS; + return; } - rcu_read_unlock(); - - if (WARN_ONCE(!folio_test_writeback(folio), - "R=%08x: folio %lx is not under writeback\n", - wreq->debug_id, folio->index)) { - trace_netfs_folio(folio, netfs_folio_trace_not_under_wback); + if (slot >= folioq_nr_slots(folioq)) { + folioq = netfs_delete_buffer_head(wreq); + slot = 0; } - return folio; -} -/* - * Unlock any folios we've finished with. - */ -static void netfs_writeback_unlock_folios(struct netfs_io_request *wreq, - unsigned long long collected_to, - unsigned int *notes) -{ for (;;) { struct folio *folio; struct netfs_folio *finfo; unsigned long long fpos, fend; size_t fsize, flen; - folio = netfs_writeback_lookup_folio(wreq, wreq->cleaned_to); + folio = folioq_folio(folioq, slot); + if (WARN_ONCE(!folio_test_writeback(folio), + "R=%08x: folio %lx is not under writeback\n", + wreq->debug_id, folio->index)) + trace_netfs_folio(folio, netfs_folio_trace_not_under_wback); fpos = folio_pos(folio); fsize = folio_size(folio); @@ -141,12 +119,6 @@ static void netfs_writeback_unlock_folios(struct netfs_io_request *wreq, trace_netfs_collect_folio(wreq, folio, fend, collected_to); - if (fpos + fsize > wreq->contiguity) { - trace_netfs_collect_contig(wreq, fpos + fsize, - netfs_contig_trace_unlock); - wreq->contiguity = fpos + fsize; - } - /* Unlock any folio we've transferred all of. */ if (collected_to < fend) break; @@ -155,9 +127,25 @@ static void netfs_writeback_unlock_folios(struct netfs_io_request *wreq, wreq->cleaned_to = fpos + fsize; *notes |= MADE_PROGRESS; + /* Clean up the head folioq. If we clear an entire folioq, then + * we can get rid of it provided it's not also the tail folioq + * being filled by the issuer. + */ + folioq_clear(folioq, slot); + slot++; + if (slot >= folioq_nr_slots(folioq)) { + if (READ_ONCE(wreq->buffer_tail) == folioq) + break; + folioq = netfs_delete_buffer_head(wreq); + slot = 0; + } + if (fpos + fsize >= collected_to) break; } + + wreq->buffer = folioq; + wreq->buffer_head_slot = slot; } /* @@ -188,9 +176,12 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq, if (test_bit(NETFS_SREQ_FAILED, &subreq->flags)) break; if (__test_and_clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags)) { + struct iov_iter source = subreq->io_iter; + + iov_iter_revert(&source, subreq->len - source.count); __set_bit(NETFS_SREQ_RETRYING, &subreq->flags); netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); - netfs_reissue_write(stream, subreq); + netfs_reissue_write(stream, subreq, &source); } } return; @@ -200,6 +191,7 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq, do { struct netfs_io_subrequest *subreq = NULL, *from, *to, *tmp; + struct iov_iter source; unsigned long long start, len; size_t part; bool boundary = false; @@ -227,6 +219,13 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq, len += to->len; } + /* Determine the set of buffers we're going to use. Each + * subreq gets a subset of a single overall contiguous buffer. + */ + netfs_reset_iter(from); + source = from->io_iter; + source.count = len; + /* Work through the sublist. */ subreq = from; list_for_each_entry_from(subreq, &stream->subrequests, rreq_link) { @@ -238,7 +237,7 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq, __set_bit(NETFS_SREQ_RETRYING, &subreq->flags); stream->prepare_write(subreq); - part = min(len, subreq->max_len); + part = min(len, stream->sreq_max_len); subreq->len = part; subreq->start = start; subreq->transferred = 0; @@ -249,7 +248,7 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq, boundary = true; netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); - netfs_reissue_write(stream, subreq); + netfs_reissue_write(stream, subreq, &source); if (subreq == to) break; } @@ -278,8 +277,6 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq, subreq = netfs_alloc_subrequest(wreq); subreq->source = to->source; subreq->start = start; - subreq->max_len = len; - subreq->max_nr_segs = INT_MAX; subreq->debug_index = atomic_inc_return(&wreq->subreq_counter); subreq->stream_nr = to->stream_nr; __set_bit(NETFS_SREQ_RETRYING, &subreq->flags); @@ -293,10 +290,12 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq, to = list_next_entry(to, rreq_link); trace_netfs_sreq(subreq, netfs_sreq_trace_retry); + stream->sreq_max_len = len; + stream->sreq_max_segs = INT_MAX; switch (stream->source) { case NETFS_UPLOAD_TO_SERVER: netfs_stat(&netfs_n_wh_upload); - subreq->max_len = min(len, wreq->wsize); + stream->sreq_max_len = umin(len, wreq->wsize); break; case NETFS_WRITE_TO_CACHE: netfs_stat(&netfs_n_wh_write); @@ -307,7 +306,7 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq, stream->prepare_write(subreq); - part = min(len, subreq->max_len); + part = umin(len, stream->sreq_max_len); subreq->len = subreq->transferred + part; len -= part; start += part; @@ -316,7 +315,7 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq, boundary = false; } - netfs_reissue_write(stream, subreq); + netfs_reissue_write(stream, subreq, &source); if (!len) break; @@ -377,7 +376,7 @@ static void netfs_collect_write_results(struct netfs_io_request *wreq) { struct netfs_io_subrequest *front, *remove; struct netfs_io_stream *stream; - unsigned long long collected_to; + unsigned long long collected_to, issued_to; unsigned int notes; int s; @@ -386,28 +385,22 @@ static void netfs_collect_write_results(struct netfs_io_request *wreq) trace_netfs_rreq(wreq, netfs_rreq_trace_collect); reassess_streams: + issued_to = atomic64_read(&wreq->issued_to); smp_rmb(); collected_to = ULLONG_MAX; - if (wreq->origin == NETFS_WRITEBACK) - notes = ALL_EMPTY | BUFFERED | MAYBE_DISCONTIG; - else if (wreq->origin == NETFS_WRITETHROUGH) - notes = ALL_EMPTY | BUFFERED; + if (wreq->origin == NETFS_WRITEBACK || + wreq->origin == NETFS_WRITETHROUGH || + wreq->origin == NETFS_PGPRIV2_COPY_TO_CACHE) + notes = BUFFERED; else - notes = ALL_EMPTY; + notes = 0; /* Remove completed subrequests from the front of the streams and * advance the completion point on each stream. We stop when we hit * something that's in progress. The issuer thread may be adding stuff * to the tail whilst we're doing this. - * - * We must not, however, merge in discontiguities that span whole - * folios that aren't under writeback. This is made more complicated - * by the folios in the gap being of unpredictable sizes - if they even - * exist - but we don't want to look them up. */ for (s = 0; s < NR_IO_STREAMS; s++) { - loff_t rstart, rend; - stream = &wreq->io_streams[s]; /* Read active flag before list pointers */ if (!smp_load_acquire(&stream->active)) @@ -419,26 +412,10 @@ reassess_streams: //_debug("sreq [%x] %llx %zx/%zx", // front->debug_index, front->start, front->transferred, front->len); - /* Stall if there may be a discontinuity. */ - rstart = round_down(front->start, PAGE_SIZE); - if (rstart > wreq->contiguity) { - if (wreq->contiguity > stream->collected_to) { - trace_netfs_collect_gap(wreq, stream, - wreq->contiguity, 'D'); - stream->collected_to = wreq->contiguity; - } - notes |= REASSESS_DISCONTIG; - break; - } - rend = round_up(front->start + front->len, PAGE_SIZE); - if (rend > wreq->contiguity) { - trace_netfs_collect_contig(wreq, rend, - netfs_contig_trace_collect); - wreq->contiguity = rend; - if (notes & REASSESS_DISCONTIG) - notes |= NEED_REASSESS; + if (stream->collected_to < front->start) { + trace_netfs_collect_gap(wreq, stream, issued_to, 'F'); + stream->collected_to = front->start; } - notes &= ~MAYBE_DISCONTIG; /* Stall if the front is still undergoing I/O. */ if (test_bit(NETFS_SREQ_IN_PROGRESS, &front->flags)) { @@ -473,33 +450,27 @@ reassess_streams: cancel: /* Remove if completely consumed. */ - spin_lock(&wreq->lock); + spin_lock_bh(&wreq->lock); remove = front; list_del_init(&front->rreq_link); front = list_first_entry_or_null(&stream->subrequests, struct netfs_io_subrequest, rreq_link); stream->front = front; - if (!front) { - unsigned long long jump_to = atomic64_read(&wreq->issued_to); - - if (stream->collected_to < jump_to) { - trace_netfs_collect_gap(wreq, stream, jump_to, 'A'); - stream->collected_to = jump_to; - } - } - - spin_unlock(&wreq->lock); + spin_unlock_bh(&wreq->lock); netfs_put_subrequest(remove, false, notes & SAW_FAILURE ? netfs_sreq_trace_put_cancel : netfs_sreq_trace_put_done); } - if (front) - notes &= ~ALL_EMPTY; - else - notes |= SOME_EMPTY; + /* If we have an empty stream, we need to jump it forward + * otherwise the collection point will never advance. + */ + if (!front && issued_to > stream->collected_to) { + trace_netfs_collect_gap(wreq, stream, issued_to, 'E'); + stream->collected_to = issued_to; + } if (stream->collected_to < collected_to) collected_to = stream->collected_to; @@ -508,36 +479,6 @@ reassess_streams: if (collected_to != ULLONG_MAX && collected_to > wreq->collected_to) wreq->collected_to = collected_to; - /* If we have an empty stream, we need to jump it forward over any gap - * otherwise the collection point will never advance. - * - * Note that the issuer always adds to the stream with the lowest - * so-far submitted start, so if we see two consecutive subreqs in one - * stream with nothing between then in another stream, then the second - * stream has a gap that can be jumped. - */ - if (notes & SOME_EMPTY) { - unsigned long long jump_to = wreq->start + READ_ONCE(wreq->submitted); - - for (s = 0; s < NR_IO_STREAMS; s++) { - stream = &wreq->io_streams[s]; - if (stream->active && - stream->front && - stream->front->start < jump_to) - jump_to = stream->front->start; - } - - for (s = 0; s < NR_IO_STREAMS; s++) { - stream = &wreq->io_streams[s]; - if (stream->active && - !stream->front && - stream->collected_to < jump_to) { - trace_netfs_collect_gap(wreq, stream, jump_to, 'B'); - stream->collected_to = jump_to; - } - } - } - for (s = 0; s < NR_IO_STREAMS; s++) { stream = &wreq->io_streams[s]; if (stream->active) @@ -548,43 +489,14 @@ reassess_streams: /* Unlock any folios that we have now finished with. */ if (notes & BUFFERED) { - unsigned long long clean_to = min(wreq->collected_to, wreq->contiguity); - - if (wreq->cleaned_to < clean_to) - netfs_writeback_unlock_folios(wreq, clean_to, ¬es); + if (wreq->cleaned_to < wreq->collected_to) + netfs_writeback_unlock_folios(wreq, ¬es); } else { wreq->cleaned_to = wreq->collected_to; } // TODO: Discard encryption buffers - /* If all streams are discontiguous with the last folio we cleared, we - * may need to skip a set of folios. - */ - if ((notes & (MAYBE_DISCONTIG | ALL_EMPTY)) == MAYBE_DISCONTIG) { - unsigned long long jump_to = ULLONG_MAX; - - for (s = 0; s < NR_IO_STREAMS; s++) { - stream = &wreq->io_streams[s]; - if (stream->active && stream->front && - stream->front->start < jump_to) - jump_to = stream->front->start; - } - - trace_netfs_collect_contig(wreq, jump_to, netfs_contig_trace_jump); - wreq->contiguity = jump_to; - wreq->cleaned_to = jump_to; - wreq->collected_to = jump_to; - for (s = 0; s < NR_IO_STREAMS; s++) { - stream = &wreq->io_streams[s]; - if (stream->collected_to < jump_to) - stream->collected_to = jump_to; - } - //cond_resched(); - notes |= MADE_PROGRESS; - goto reassess_streams; - } - if (notes & NEED_RETRY) goto need_retry; if ((notes & MADE_PROGRESS) && test_bit(NETFS_RREQ_PAUSE, &wreq->flags)) { diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index 3f7e37e50c7d..04e66d587f77 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -95,7 +95,8 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping, struct netfs_io_request *wreq; struct netfs_inode *ictx; bool is_buffered = (origin == NETFS_WRITEBACK || - origin == NETFS_WRITETHROUGH); + origin == NETFS_WRITETHROUGH || + origin == NETFS_PGPRIV2_COPY_TO_CACHE); wreq = netfs_alloc_request(mapping, file, start, 0, origin); if (IS_ERR(wreq)) @@ -107,9 +108,7 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping, if (is_buffered && netfs_is_cache_enabled(ictx)) fscache_begin_write_operation(&wreq->cache_resources, netfs_i_cookie(ictx)); - wreq->contiguity = wreq->start; wreq->cleaned_to = wreq->start; - INIT_WORK(&wreq->work, netfs_write_collection_worker); wreq->io_streams[0].stream_nr = 0; wreq->io_streams[0].source = NETFS_UPLOAD_TO_SERVER; @@ -158,22 +157,19 @@ static void netfs_prepare_write(struct netfs_io_request *wreq, subreq = netfs_alloc_subrequest(wreq); subreq->source = stream->source; subreq->start = start; - subreq->max_len = ULONG_MAX; - subreq->max_nr_segs = INT_MAX; subreq->stream_nr = stream->stream_nr; + subreq->io_iter = wreq->io_iter; _enter("R=%x[%x]", wreq->debug_id, subreq->debug_index); - trace_netfs_sreq_ref(wreq->debug_id, subreq->debug_index, - refcount_read(&subreq->ref), - netfs_sreq_trace_new); - trace_netfs_sreq(subreq, netfs_sreq_trace_prepare); + stream->sreq_max_len = UINT_MAX; + stream->sreq_max_segs = INT_MAX; switch (stream->source) { case NETFS_UPLOAD_TO_SERVER: netfs_stat(&netfs_n_wh_upload); - subreq->max_len = wreq->wsize; + stream->sreq_max_len = wreq->wsize; break; case NETFS_WRITE_TO_CACHE: netfs_stat(&netfs_n_wh_write); @@ -192,7 +188,7 @@ static void netfs_prepare_write(struct netfs_io_request *wreq, * the list. The collector only goes nextwards and uses the lock to * remove entries off of the front. */ - spin_lock(&wreq->lock); + spin_lock_bh(&wreq->lock); list_add_tail(&subreq->rreq_link, &stream->subrequests); if (list_is_first(&subreq->rreq_link, &stream->subrequests)) { stream->front = subreq; @@ -203,7 +199,7 @@ static void netfs_prepare_write(struct netfs_io_request *wreq, } } - spin_unlock(&wreq->lock); + spin_unlock_bh(&wreq->lock); stream->construct = subreq; } @@ -223,41 +219,34 @@ static void netfs_do_issue_write(struct netfs_io_stream *stream, if (test_bit(NETFS_SREQ_FAILED, &subreq->flags)) return netfs_write_subrequest_terminated(subreq, subreq->error, false); - // TODO: Use encrypted buffer - if (test_bit(NETFS_RREQ_USE_IO_ITER, &wreq->flags)) { - subreq->io_iter = wreq->io_iter; - iov_iter_advance(&subreq->io_iter, - subreq->start + subreq->transferred - wreq->start); - iov_iter_truncate(&subreq->io_iter, - subreq->len - subreq->transferred); - } else { - iov_iter_xarray(&subreq->io_iter, ITER_SOURCE, &wreq->mapping->i_pages, - subreq->start + subreq->transferred, - subreq->len - subreq->transferred); - } - trace_netfs_sreq(subreq, netfs_sreq_trace_submit); stream->issue_write(subreq); } void netfs_reissue_write(struct netfs_io_stream *stream, - struct netfs_io_subrequest *subreq) + struct netfs_io_subrequest *subreq, + struct iov_iter *source) { + size_t size = subreq->len - subreq->transferred; + + // TODO: Use encrypted buffer + subreq->io_iter = *source; + iov_iter_advance(source, size); + iov_iter_truncate(&subreq->io_iter, size); + __set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); netfs_do_issue_write(stream, subreq); } -static void netfs_issue_write(struct netfs_io_request *wreq, - struct netfs_io_stream *stream) +void netfs_issue_write(struct netfs_io_request *wreq, + struct netfs_io_stream *stream) { struct netfs_io_subrequest *subreq = stream->construct; if (!subreq) return; stream->construct = NULL; - - if (subreq->start + subreq->len > wreq->start + wreq->submitted) - WRITE_ONCE(wreq->submitted, subreq->start + subreq->len - wreq->start); + subreq->io_iter.count = subreq->len; netfs_do_issue_write(stream, subreq); } @@ -290,13 +279,14 @@ int netfs_advance_write(struct netfs_io_request *wreq, netfs_prepare_write(wreq, stream, start); subreq = stream->construct; - part = min(subreq->max_len - subreq->len, len); - _debug("part %zx/%zx %zx/%zx", subreq->len, subreq->max_len, part, len); + part = umin(stream->sreq_max_len - subreq->len, len); + _debug("part %zx/%zx %zx/%zx", subreq->len, stream->sreq_max_len, part, len); subreq->len += part; subreq->nr_segs++; + stream->submit_extendable_to -= part; - if (subreq->len >= subreq->max_len || - subreq->nr_segs >= subreq->max_nr_segs || + if (subreq->len >= stream->sreq_max_len || + subreq->nr_segs >= stream->sreq_max_segs || to_eof) { netfs_issue_write(wreq, stream); subreq = NULL; @@ -410,19 +400,26 @@ static int netfs_write_folio(struct netfs_io_request *wreq, folio_unlock(folio); if (fgroup == NETFS_FOLIO_COPY_TO_CACHE) { - if (!fscache_resources_valid(&wreq->cache_resources)) { + if (!cache->avail) { trace_netfs_folio(folio, netfs_folio_trace_cancel_copy); netfs_issue_write(wreq, upload); netfs_folio_written_back(folio); return 0; } trace_netfs_folio(folio, netfs_folio_trace_store_copy); + } else if (!upload->avail && !cache->avail) { + trace_netfs_folio(folio, netfs_folio_trace_cancel_store); + netfs_folio_written_back(folio); + return 0; } else if (!upload->construct) { trace_netfs_folio(folio, netfs_folio_trace_store); } else { trace_netfs_folio(folio, netfs_folio_trace_store_plus); } + /* Attach the folio to the rolling buffer. */ + netfs_buffer_append_folio(wreq, folio, false); + /* Move the submission point forward to allow for write-streaming data * not starting at the front of the page. We don't do write-streaming * with the cache as the cache requires DIO alignment. @@ -432,7 +429,6 @@ static int netfs_write_folio(struct netfs_io_request *wreq, */ for (int s = 0; s < NR_IO_STREAMS; s++) { stream = &wreq->io_streams[s]; - stream->submit_max_len = fsize; stream->submit_off = foff; stream->submit_len = flen; if ((stream->source == NETFS_WRITE_TO_CACHE && streamw) || @@ -440,7 +436,6 @@ static int netfs_write_folio(struct netfs_io_request *wreq, fgroup == NETFS_FOLIO_COPY_TO_CACHE)) { stream->submit_off = UINT_MAX; stream->submit_len = 0; - stream->submit_max_len = 0; } } @@ -467,12 +462,13 @@ static int netfs_write_folio(struct netfs_io_request *wreq, if (choose_s < 0) break; stream = &wreq->io_streams[choose_s]; + wreq->io_iter.iov_offset = stream->submit_off; + atomic64_set(&wreq->issued_to, fpos + stream->submit_off); + stream->submit_extendable_to = fsize - stream->submit_off; part = netfs_advance_write(wreq, stream, fpos + stream->submit_off, stream->submit_len, to_eof); - atomic64_set(&wreq->issued_to, fpos + stream->submit_off); stream->submit_off += part; - stream->submit_max_len -= part; if (part > stream->submit_len) stream->submit_len = 0; else @@ -481,6 +477,8 @@ static int netfs_write_folio(struct netfs_io_request *wreq, debug = true; } + wreq->io_iter.iov_offset = 0; + iov_iter_advance(&wreq->io_iter, fsize); atomic64_set(&wreq->issued_to, fpos + fsize); if (!debug) @@ -505,10 +503,14 @@ int netfs_writepages(struct address_space *mapping, struct folio *folio; int error = 0; - if (wbc->sync_mode == WB_SYNC_ALL) + if (!mutex_trylock(&ictx->wb_lock)) { + if (wbc->sync_mode == WB_SYNC_NONE) { + netfs_stat(&netfs_n_wb_lock_skip); + return 0; + } + netfs_stat(&netfs_n_wb_lock_wait); mutex_lock(&ictx->wb_lock); - else if (!mutex_trylock(&ictx->wb_lock)) - return 0; + } /* Need the first folio to be able to set up the op. */ folio = writeback_iter(mapping, wbc, NULL, &error); @@ -525,10 +527,10 @@ int netfs_writepages(struct address_space *mapping, netfs_stat(&netfs_n_wh_writepages); do { - _debug("wbiter %lx %llx", folio->index, wreq->start + wreq->submitted); + _debug("wbiter %lx %llx", folio->index, atomic64_read(&wreq->issued_to)); /* It appears we don't have to handle cyclic writeback wrapping. */ - WARN_ON_ONCE(wreq && folio_pos(folio) < wreq->start + wreq->submitted); + WARN_ON_ONCE(wreq && folio_pos(folio) < atomic64_read(&wreq->issued_to)); if (netfs_folio_group(folio) != NETFS_FOLIO_COPY_TO_CACHE && unlikely(!test_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags))) { @@ -672,6 +674,7 @@ int netfs_unbuffered_write(struct netfs_io_request *wreq, bool may_wait, size_t part = netfs_advance_write(wreq, upload, start, len, false); start += part; len -= part; + iov_iter_advance(&wreq->io_iter, part); if (test_bit(NETFS_RREQ_PAUSE, &wreq->flags)) { trace_netfs_rreq(wreq, netfs_rreq_trace_wait_pause); wait_on_bit(&wreq->flags, NETFS_RREQ_PAUSE, TASK_UNINTERRUPTIBLE); diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 61a8cdb9f1e1..6800ee92d742 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -336,7 +336,7 @@ static bool nfs_want_read_modify_write(struct file *file, struct folio *folio, * increment the page use counts until he is done with the page. */ static int nfs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, struct page **pagep, + loff_t pos, unsigned len, struct folio **foliop, void **fsdata) { fgf_t fgp = FGP_WRITEBEGIN; @@ -353,7 +353,7 @@ start: mapping_gfp_mask(mapping)); if (IS_ERR(folio)) return PTR_ERR(folio); - *pagep = &folio->page; + *foliop = folio; ret = nfs_flush_incompatible(file, folio); if (ret) { @@ -372,10 +372,9 @@ start: static int nfs_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { struct nfs_open_context *ctx = nfs_file_open_context(file); - struct folio *folio = page_folio(page); unsigned offset = offset_in_folio(folio, pos); int status; diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index 7a558dea75c4..810269ee0a50 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -267,6 +267,7 @@ static int nfs_netfs_init_request(struct netfs_io_request *rreq, struct file *fi rreq->debug_id = atomic_inc_return(&nfs_netfs_debug_id); /* [DEPRECATED] Use PG_private_2 to mark folio being written to the cache. */ __set_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags); + rreq->io_streams[0].sreq_max_len = NFS_SB(rreq->inode->i_sb)->rsize; return 0; } @@ -288,14 +289,6 @@ static struct nfs_netfs_io_data *nfs_netfs_alloc(struct netfs_io_subrequest *sre return netfs; } -static bool nfs_netfs_clamp_length(struct netfs_io_subrequest *sreq) -{ - size_t rsize = NFS_SB(sreq->rreq->inode->i_sb)->rsize; - - sreq->len = min(sreq->len, rsize); - return true; -} - static void nfs_netfs_issue_read(struct netfs_io_subrequest *sreq) { struct nfs_netfs_io_data *netfs; @@ -304,17 +297,18 @@ static void nfs_netfs_issue_read(struct netfs_io_subrequest *sreq) struct nfs_open_context *ctx = sreq->rreq->netfs_priv; struct page *page; unsigned long idx; + pgoff_t start, last; int err; - pgoff_t start = (sreq->start + sreq->transferred) >> PAGE_SHIFT; - pgoff_t last = ((sreq->start + sreq->len - - sreq->transferred - 1) >> PAGE_SHIFT); + + start = (sreq->start + sreq->transferred) >> PAGE_SHIFT; + last = ((sreq->start + sreq->len - sreq->transferred - 1) >> PAGE_SHIFT); nfs_pageio_init_read(&pgio, inode, false, &nfs_async_read_completion_ops); netfs = nfs_netfs_alloc(sreq); if (!netfs) - return netfs_subreq_terminated(sreq, -ENOMEM, false); + return netfs_read_subreq_terminated(sreq, -ENOMEM, false); pgio.pg_netfs = netfs; /* used in completion */ @@ -380,5 +374,4 @@ const struct netfs_request_ops nfs_netfs_ops = { .init_request = nfs_netfs_init_request, .free_request = nfs_netfs_free_request, .issue_read = nfs_netfs_issue_read, - .clamp_length = nfs_netfs_clamp_length }; diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h index e8adae1bc260..772d485e96d3 100644 --- a/fs/nfs/fscache.h +++ b/fs/nfs/fscache.h @@ -60,8 +60,6 @@ static inline void nfs_netfs_get(struct nfs_netfs_io_data *netfs) static inline void nfs_netfs_put(struct nfs_netfs_io_data *netfs) { - ssize_t final_len; - /* Only the last RPC completion should call netfs_subreq_terminated() */ if (!refcount_dec_and_test(&netfs->refcount)) return; @@ -74,8 +72,9 @@ static inline void nfs_netfs_put(struct nfs_netfs_io_data *netfs) * Correct the final length here to be no larger than the netfs subrequest * length, and thus avoid netfs's "Subreq overread" warning message. */ - final_len = min_t(s64, netfs->sreq->len, atomic64_read(&netfs->transferred)); - netfs_subreq_terminated(netfs->sreq, netfs->error ?: final_len, false); + netfs->sreq->transferred = min_t(s64, netfs->sreq->len, + atomic64_read(&netfs->transferred)); + netfs_read_subreq_terminated(netfs->sreq, netfs->error, false); kfree(netfs); } static inline void nfs_netfs_inode_init(struct nfs_inode *nfsi) diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c index 4a29b0138d75..4b3e19d74925 100644 --- a/fs/nilfs2/dir.c +++ b/fs/nilfs2/dir.c @@ -83,7 +83,7 @@ static int nilfs_prepare_chunk(struct folio *folio, unsigned int from, { loff_t pos = folio_pos(folio) + from; - return __block_write_begin(&folio->page, pos, to - from, nilfs_get_block); + return __block_write_begin(folio, pos, to - from, nilfs_get_block); } static void nilfs_commit_chunk(struct folio *folio, @@ -96,7 +96,7 @@ static void nilfs_commit_chunk(struct folio *folio, int err; nr_dirty = nilfs_page_count_clean_buffers(&folio->page, from, to); - copied = block_write_end(NULL, mapping, pos, len, len, &folio->page, NULL); + copied = block_write_end(NULL, mapping, pos, len, len, folio, NULL); if (pos + copied > dir->i_size) i_size_write(dir, pos + copied); if (IS_DIRSYNC(dir)) diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 7340a01d80e1..8661f452dba6 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -250,7 +250,7 @@ void nilfs_write_failed(struct address_space *mapping, loff_t to) static int nilfs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { struct inode *inode = mapping->host; @@ -259,7 +259,7 @@ static int nilfs_write_begin(struct file *file, struct address_space *mapping, if (unlikely(err)) return err; - err = block_write_begin(mapping, pos, len, pagep, nilfs_get_block); + err = block_write_begin(mapping, pos, len, foliop, nilfs_get_block); if (unlikely(err)) { nilfs_write_failed(mapping, pos + len); nilfs_transaction_abort(inode->i_sb); @@ -269,16 +269,16 @@ static int nilfs_write_begin(struct file *file, struct address_space *mapping, static int nilfs_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { struct inode *inode = mapping->host; unsigned int start = pos & (PAGE_SIZE - 1); unsigned int nr_dirty; int err; - nr_dirty = nilfs_page_count_clean_buffers(page, start, + nr_dirty = nilfs_page_count_clean_buffers(&folio->page, start, start + copied); - copied = generic_write_end(file, mapping, pos, len, copied, page, + copied = generic_write_end(file, mapping, pos, len, copied, folio, fsdata); nilfs_set_file_dirty(inode, nr_dirty); err = nilfs_transaction_commit(inode->i_sb); diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c index b638dc06df2f..ec61ce9f29a2 100644 --- a/fs/nilfs2/recovery.c +++ b/fs/nilfs2/recovery.c @@ -498,7 +498,7 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs, struct inode *inode; struct nilfs_recovery_block *rb, *n; unsigned int blocksize = nilfs->ns_blocksize; - struct page *page; + struct folio *folio; loff_t pos; int err = 0, err2 = 0; @@ -512,7 +512,7 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs, pos = rb->blkoff << inode->i_blkbits; err = block_write_begin(inode->i_mapping, pos, blocksize, - &page, nilfs_get_block); + &folio, nilfs_get_block); if (unlikely(err)) { loff_t isize = inode->i_size; @@ -522,7 +522,7 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs, goto failed_inode; } - err = nilfs_recovery_copy_block(nilfs, rb, pos, page); + err = nilfs_recovery_copy_block(nilfs, rb, pos, &folio->page); if (unlikely(err)) goto failed_page; @@ -531,17 +531,17 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs, goto failed_page; block_write_end(NULL, inode->i_mapping, pos, blocksize, - blocksize, page, NULL); + blocksize, folio, NULL); - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); (*nr_salvaged_blocks)++; goto next; failed_page: - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); failed_inode: nilfs_warn(sb, @@ -716,6 +716,33 @@ static void nilfs_finish_roll_forward(struct the_nilfs *nilfs, } /** + * nilfs_abort_roll_forward - cleaning up after a failed rollforward recovery + * @nilfs: nilfs object + */ +static void nilfs_abort_roll_forward(struct the_nilfs *nilfs) +{ + struct nilfs_inode_info *ii, *n; + LIST_HEAD(head); + + /* Abandon inodes that have read recovery data */ + spin_lock(&nilfs->ns_inode_lock); + list_splice_init(&nilfs->ns_dirty_files, &head); + spin_unlock(&nilfs->ns_inode_lock); + if (list_empty(&head)) + return; + + set_nilfs_purging(nilfs); + list_for_each_entry_safe(ii, n, &head, i_dirty) { + spin_lock(&nilfs->ns_inode_lock); + list_del_init(&ii->i_dirty); + spin_unlock(&nilfs->ns_inode_lock); + + iput(&ii->vfs_inode); + } + clear_nilfs_purging(nilfs); +} + +/** * nilfs_salvage_orphan_logs - salvage logs written after the latest checkpoint * @nilfs: nilfs object * @sb: super block instance @@ -773,15 +800,19 @@ int nilfs_salvage_orphan_logs(struct the_nilfs *nilfs, if (unlikely(err)) { nilfs_err(sb, "error %d writing segment for recovery", err); - goto failed; + goto put_root; } nilfs_finish_roll_forward(nilfs, ri); } - failed: +put_root: nilfs_put_root(root); return err; + +failed: + nilfs_abort_roll_forward(nilfs); + goto put_root; } /** diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 0ca3110d6386..871ec35ea8e8 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -1812,6 +1812,9 @@ static void nilfs_segctor_abort_construction(struct nilfs_sc_info *sci, nilfs_abort_logs(&logs, ret ? : err); list_splice_tail_init(&sci->sc_segbufs, &logs); + if (list_empty(&logs)) + return; /* if the first segment buffer preparation failed */ + nilfs_cancel_segusage(&logs, nilfs->ns_sufile); nilfs_free_incomplete_logs(&logs, nilfs); @@ -2056,7 +2059,7 @@ static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode) err = nilfs_segctor_begin_construction(sci, nilfs); if (unlikely(err)) - goto out; + goto failed; /* Update time stamp */ sci->sc_seg_ctime = ktime_get_real_seconds(); @@ -2120,10 +2123,9 @@ static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode) return err; failed_to_write: - if (sci->sc_stage.flags & NILFS_CF_IFILE_STARTED) - nilfs_redirty_inodes(&sci->sc_dirty_files); - failed: + if (mode == SC_LSEG_SR && nilfs_sc_cstage_get(sci) >= NILFS_ST_IFILE) + nilfs_redirty_inodes(&sci->sc_dirty_files); if (nilfs_doing_gc()) nilfs_redirty_inodes(&sci->sc_gc_inodes); nilfs_segctor_abort_construction(sci, nilfs, err); diff --git a/fs/nilfs2/sysfs.c b/fs/nilfs2/sysfs.c index a5569b7f47a3..14868a3dd592 100644 --- a/fs/nilfs2/sysfs.c +++ b/fs/nilfs2/sysfs.c @@ -836,9 +836,15 @@ ssize_t nilfs_dev_revision_show(struct nilfs_dev_attr *attr, struct the_nilfs *nilfs, char *buf) { - struct nilfs_super_block **sbp = nilfs->ns_sbp; - u32 major = le32_to_cpu(sbp[0]->s_rev_level); - u16 minor = le16_to_cpu(sbp[0]->s_minor_rev_level); + struct nilfs_super_block *raw_sb; + u32 major; + u16 minor; + + down_read(&nilfs->ns_sem); + raw_sb = nilfs->ns_sbp[0]; + major = le32_to_cpu(raw_sb->s_rev_level); + minor = le16_to_cpu(raw_sb->s_minor_rev_level); + up_read(&nilfs->ns_sem); return sysfs_emit(buf, "%d.%d\n", major, minor); } @@ -856,8 +862,13 @@ ssize_t nilfs_dev_device_size_show(struct nilfs_dev_attr *attr, struct the_nilfs *nilfs, char *buf) { - struct nilfs_super_block **sbp = nilfs->ns_sbp; - u64 dev_size = le64_to_cpu(sbp[0]->s_dev_size); + struct nilfs_super_block *raw_sb; + u64 dev_size; + + down_read(&nilfs->ns_sem); + raw_sb = nilfs->ns_sbp[0]; + dev_size = le64_to_cpu(raw_sb->s_dev_size); + up_read(&nilfs->ns_sem); return sysfs_emit(buf, "%llu\n", dev_size); } @@ -879,9 +890,15 @@ ssize_t nilfs_dev_uuid_show(struct nilfs_dev_attr *attr, struct the_nilfs *nilfs, char *buf) { - struct nilfs_super_block **sbp = nilfs->ns_sbp; + struct nilfs_super_block *raw_sb; + ssize_t len; - return sysfs_emit(buf, "%pUb\n", sbp[0]->s_uuid); + down_read(&nilfs->ns_sem); + raw_sb = nilfs->ns_sbp[0]; + len = sysfs_emit(buf, "%pUb\n", raw_sb->s_uuid); + up_read(&nilfs->ns_sem); + + return len; } static @@ -889,10 +906,16 @@ ssize_t nilfs_dev_volume_name_show(struct nilfs_dev_attr *attr, struct the_nilfs *nilfs, char *buf) { - struct nilfs_super_block **sbp = nilfs->ns_sbp; + struct nilfs_super_block *raw_sb; + ssize_t len; + + down_read(&nilfs->ns_sem); + raw_sb = nilfs->ns_sbp[0]; + len = scnprintf(buf, sizeof(raw_sb->s_volume_name), "%s\n", + raw_sb->s_volume_name); + up_read(&nilfs->ns_sem); - return scnprintf(buf, sizeof(sbp[0]->s_volume_name), "%s\n", - sbp[0]->s_volume_name); + return len; } static const char dev_readme_str[] = diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c index f3669403fabf..46440fbb8662 100644 --- a/fs/notify/dnotify/dnotify.c +++ b/fs/notify/dnotify/dnotify.c @@ -110,7 +110,7 @@ static int dnotify_handle_event(struct fsnotify_mark *inode_mark, u32 mask, prev = &dn->dn_next; continue; } - fown = &dn->dn_filp->f_owner; + fown = file_f_owner(dn->dn_filp); send_sigio(fown, dn->dn_fd, POLL_MSG); if (dn->dn_mask & FS_DN_MULTISHOT) prev = &dn->dn_next; @@ -316,6 +316,10 @@ int fcntl_dirnotify(int fd, struct file *filp, unsigned int arg) goto out_err; } + error = file_f_owner_allocate(filp); + if (error) + goto out_err; + /* set up the new_fsn_mark and new_dn_mark */ new_fsn_mark = &new_dn_mark->fsn_mark; fsnotify_init_mark(new_fsn_mark, dnotify_group); diff --git a/fs/nsfs.c b/fs/nsfs.c index 97c37a9631e5..67ee176b8824 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -12,6 +12,7 @@ #include <linux/user_namespace.h> #include <linux/nsfs.h> #include <linux/uaccess.h> +#include <linux/mnt_namespace.h> #include "mount.h" #include "internal.h" @@ -128,6 +129,30 @@ int open_related_ns(struct ns_common *ns, } EXPORT_SYMBOL_GPL(open_related_ns); +static int copy_ns_info_to_user(const struct mnt_namespace *mnt_ns, + struct mnt_ns_info __user *uinfo, size_t usize, + struct mnt_ns_info *kinfo) +{ + /* + * If userspace and the kernel have the same struct size it can just + * be copied. If userspace provides an older struct, only the bits that + * userspace knows about will be copied. If userspace provides a new + * struct, only the bits that the kernel knows aobut will be copied and + * the size value will be set to the size the kernel knows about. + */ + kinfo->size = min(usize, sizeof(*kinfo)); + kinfo->mnt_ns_id = mnt_ns->seq; + kinfo->nr_mounts = READ_ONCE(mnt_ns->nr_mounts); + /* Subtract the root mount of the mount namespace. */ + if (kinfo->nr_mounts) + kinfo->nr_mounts--; + + if (copy_to_user(uinfo, kinfo, kinfo->size)) + return -EFAULT; + + return 0; +} + static long ns_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -135,6 +160,8 @@ static long ns_ioctl(struct file *filp, unsigned int ioctl, struct pid_namespace *pid_ns; struct task_struct *tsk; struct ns_common *ns = get_proc_ns(file_inode(filp)); + struct mnt_namespace *mnt_ns; + bool previous = false; uid_t __user *argp; uid_t uid; int ret; @@ -156,7 +183,6 @@ static long ns_ioctl(struct file *filp, unsigned int ioctl, uid = from_kuid_munged(current_user_ns(), user_ns->owner); return put_user(uid, argp); case NS_GET_MNTNS_ID: { - struct mnt_namespace *mnt_ns; __u64 __user *idp; __u64 id; @@ -211,7 +237,79 @@ static long ns_ioctl(struct file *filp, unsigned int ioctl, if (!ret) ret = -ESRCH; - break; + return ret; + } + } + + /* extensible ioctls */ + switch (_IOC_NR(ioctl)) { + case _IOC_NR(NS_MNT_GET_INFO): { + struct mnt_ns_info kinfo = {}; + struct mnt_ns_info __user *uinfo = (struct mnt_ns_info __user *)arg; + size_t usize = _IOC_SIZE(ioctl); + + if (ns->ops->type != CLONE_NEWNS) + return -EINVAL; + + if (!uinfo) + return -EINVAL; + + if (usize < MNT_NS_INFO_SIZE_VER0) + return -EINVAL; + + return copy_ns_info_to_user(to_mnt_ns(ns), uinfo, usize, &kinfo); + } + case _IOC_NR(NS_MNT_GET_PREV): + previous = true; + fallthrough; + case _IOC_NR(NS_MNT_GET_NEXT): { + struct mnt_ns_info kinfo = {}; + struct mnt_ns_info __user *uinfo = (struct mnt_ns_info __user *)arg; + struct path path __free(path_put) = {}; + struct file *f __free(fput) = NULL; + size_t usize = _IOC_SIZE(ioctl); + + if (ns->ops->type != CLONE_NEWNS) + return -EINVAL; + + if (usize < MNT_NS_INFO_SIZE_VER0) + return -EINVAL; + + if (previous) + mnt_ns = lookup_prev_mnt_ns(to_mnt_ns(ns)); + else + mnt_ns = lookup_next_mnt_ns(to_mnt_ns(ns)); + if (IS_ERR(mnt_ns)) + return PTR_ERR(mnt_ns); + + ns = to_ns_common(mnt_ns); + /* Transfer ownership of @mnt_ns reference to @path. */ + ret = path_from_stashed(&ns->stashed, nsfs_mnt, ns, &path); + if (ret) + return ret; + + CLASS(get_unused_fd, fd)(O_CLOEXEC); + if (fd < 0) + return fd; + + f = dentry_open(&path, O_RDONLY, current_cred()); + if (IS_ERR(f)) + return PTR_ERR(f); + + if (uinfo) { + /* + * If @uinfo is passed return all information about the + * mount namespace as well. + */ + ret = copy_ns_info_to_user(to_mnt_ns(ns), uinfo, usize, &kinfo); + if (ret) + return ret; + } + + /* Transfer reference of @f to caller's fdtable. */ + fd_install(fd, no_free_ptr(f)); + /* File descriptor is live so hand it off to the caller. */ + return take_fd(fd); } default: ret = -ENOTTY; diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c index ca1ddc46bd86..6202895a4542 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -182,7 +182,7 @@ static int ntfs_extend_initialized_size(struct file *file, for (;;) { u32 zerofrom, len; - struct page *page; + struct folio *folio; u8 bits; CLST vcn, lcn, clen; @@ -208,14 +208,13 @@ static int ntfs_extend_initialized_size(struct file *file, if (pos + len > new_valid) len = new_valid - pos; - err = ntfs_write_begin(file, mapping, pos, len, &page, NULL); + err = ntfs_write_begin(file, mapping, pos, len, &folio, NULL); if (err) goto out; - zero_user_segment(page, zerofrom, PAGE_SIZE); + folio_zero_range(folio, zerofrom, folio_size(folio)); - /* This function in any case puts page. */ - err = ntfs_write_end(file, mapping, pos, len, len, page, NULL); + err = ntfs_write_end(file, mapping, pos, len, len, folio, NULL); if (err < 0) goto out; pos += len; diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index 6b0bdc474e76..f672072e6bd4 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -901,7 +901,7 @@ static int ntfs_get_block_write_begin(struct inode *inode, sector_t vbn, } int ntfs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, u32 len, struct page **pagep, void **fsdata) + loff_t pos, u32 len, struct folio **foliop, void **fsdata) { int err; struct inode *inode = mapping->host; @@ -910,7 +910,6 @@ int ntfs_write_begin(struct file *file, struct address_space *mapping, if (unlikely(ntfs3_forced_shutdown(inode->i_sb))) return -EIO; - *pagep = NULL; if (is_resident(ni)) { struct folio *folio = __filemap_get_folio( mapping, pos >> PAGE_SHIFT, FGP_WRITEBEGIN, @@ -926,7 +925,7 @@ int ntfs_write_begin(struct file *file, struct address_space *mapping, ni_unlock(ni); if (!err) { - *pagep = &folio->page; + *foliop = folio; goto out; } folio_unlock(folio); @@ -936,7 +935,7 @@ int ntfs_write_begin(struct file *file, struct address_space *mapping, goto out; } - err = block_write_begin(mapping, pos, len, pagep, + err = block_write_begin(mapping, pos, len, foliop, ntfs_get_block_write_begin); out: @@ -947,9 +946,8 @@ out: * ntfs_write_end - Address_space_operations::write_end. */ int ntfs_write_end(struct file *file, struct address_space *mapping, loff_t pos, - u32 len, u32 copied, struct page *page, void *fsdata) + u32 len, u32 copied, struct folio *folio, void *fsdata) { - struct folio *folio = page_folio(page); struct inode *inode = mapping->host; struct ntfs_inode *ni = ntfs_i(inode); u64 valid = ni->i_valid; @@ -979,7 +977,7 @@ int ntfs_write_end(struct file *file, struct address_space *mapping, loff_t pos, folio_unlock(folio); folio_put(folio); } else { - err = generic_write_end(file, mapping, pos, len, copied, page, + err = generic_write_end(file, mapping, pos, len, copied, folio, fsdata); } @@ -1008,45 +1006,6 @@ int ntfs_write_end(struct file *file, struct address_space *mapping, loff_t pos, return err; } -int reset_log_file(struct inode *inode) -{ - int err; - loff_t pos = 0; - u32 log_size = inode->i_size; - struct address_space *mapping = inode->i_mapping; - - for (;;) { - u32 len; - void *kaddr; - struct page *page; - - len = pos + PAGE_SIZE > log_size ? (log_size - pos) : PAGE_SIZE; - - err = block_write_begin(mapping, pos, len, &page, - ntfs_get_block_write_begin); - if (err) - goto out; - - kaddr = kmap_atomic(page); - memset(kaddr, -1, len); - kunmap_atomic(kaddr); - flush_dcache_page(page); - - err = block_write_end(NULL, mapping, pos, len, len, page, NULL); - if (err < 0) - goto out; - pos += len; - - if (pos >= log_size) - break; - balance_dirty_pages_ratelimited(mapping); - } -out: - mark_inode_dirty_sync(inode); - - return err; -} - int ntfs3_write_inode(struct inode *inode, struct writeback_control *wbc) { return _ni_write_inode(inode, wbc->sync_mode == WB_SYNC_ALL); diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index e5255a251929..584f814715f4 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -708,13 +708,12 @@ int indx_update_dup(struct ntfs_inode *ni, struct ntfs_sb_info *sbi, struct inode *ntfs_iget5(struct super_block *sb, const struct MFT_REF *ref, const struct cpu_str *name); int ntfs_set_size(struct inode *inode, u64 new_size); -int reset_log_file(struct inode *inode); int ntfs_get_block(struct inode *inode, sector_t vbn, struct buffer_head *bh_result, int create); int ntfs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, u32 len, struct page **pagep, void **fsdata); + loff_t pos, u32 len, struct folio **foliop, void **fsdata); int ntfs_write_end(struct file *file, struct address_space *mapping, loff_t pos, - u32 len, u32 copied, struct page *page, void *fsdata); + u32 len, u32 copied, struct folio *folio, void *fsdata); int ntfs3_write_inode(struct inode *inode, struct writeback_control *wbc); int ntfs_sync_inode(struct inode *inode); int ntfs_flush_inodes(struct super_block *sb, struct inode *i1, diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 6be175a1ab3c..d6c985cc6353 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -1643,7 +1643,7 @@ static int ocfs2_zero_tail(struct inode *inode, struct buffer_head *di_bh, int ocfs2_write_begin_nolock(struct address_space *mapping, loff_t pos, unsigned len, ocfs2_write_type_t type, - struct page **pagep, void **fsdata, + struct folio **foliop, void **fsdata, struct buffer_head *di_bh, struct page *mmap_page) { int ret, cluster_of_pages, credits = OCFS2_INODE_UPDATE_CREDITS; @@ -1826,8 +1826,8 @@ try_again: ocfs2_free_alloc_context(meta_ac); success: - if (pagep) - *pagep = wc->w_target_page; + if (foliop) + *foliop = page_folio(wc->w_target_page); *fsdata = wc; return 0; out_quota: @@ -1879,7 +1879,7 @@ out: static int ocfs2_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { int ret; struct buffer_head *di_bh = NULL; @@ -1901,7 +1901,7 @@ static int ocfs2_write_begin(struct file *file, struct address_space *mapping, down_write(&OCFS2_I(inode)->ip_alloc_sem); ret = ocfs2_write_begin_nolock(mapping, pos, len, OCFS2_WRITE_BUFFER, - pagep, fsdata, di_bh, NULL); + foliop, fsdata, di_bh, NULL); if (ret) { mlog_errno(ret); goto out_fail; @@ -2076,7 +2076,7 @@ out: static int ocfs2_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { int ret; struct inode *inode = mapping->host; diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h index 3a520117fa59..45db1781ea73 100644 --- a/fs/ocfs2/aops.h +++ b/fs/ocfs2/aops.h @@ -38,7 +38,7 @@ typedef enum { int ocfs2_write_begin_nolock(struct address_space *mapping, loff_t pos, unsigned len, ocfs2_write_type_t type, - struct page **pagep, void **fsdata, + struct folio **foliop, void **fsdata, struct buffer_head *di_bh, struct page *mmap_page); int ocfs2_read_inline_data(struct inode *inode, struct page *page, diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index f0beb173dbba..ccef3f42b333 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -1932,6 +1932,7 @@ int ocfs2_readdir(struct file *file, struct dir_context *ctx) { int error = 0; struct inode *inode = file_inode(file); + struct ocfs2_file_private *fp = file->private_data; int lock_level = 0; trace_ocfs2_readdir((unsigned long long)OCFS2_I(inode)->ip_blkno); @@ -1952,7 +1953,7 @@ int ocfs2_readdir(struct file *file, struct dir_context *ctx) goto bail_nolock; } - error = ocfs2_dir_foreach_blk(inode, &file->f_version, ctx, false); + error = ocfs2_dir_foreach_blk(inode, &fp->cookie, ctx, false); ocfs2_inode_unlock(inode, lock_level); if (error) diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index ccc57038a977..ad131a2fc58e 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -755,7 +755,7 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from, u64 abs_to, struct buffer_head *di_bh) { struct address_space *mapping = inode->i_mapping; - struct page *page; + struct folio *folio; unsigned long index = abs_from >> PAGE_SHIFT; handle_t *handle; int ret = 0; @@ -774,9 +774,10 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from, goto out; } - page = find_or_create_page(mapping, index, GFP_NOFS); - if (!page) { - ret = -ENOMEM; + folio = __filemap_get_folio(mapping, index, + FGP_LOCK | FGP_ACCESSED | FGP_CREAT, GFP_NOFS); + if (IS_ERR(folio)) { + ret = PTR_ERR(folio); mlog_errno(ret); goto out_commit_trans; } @@ -803,7 +804,7 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from, * __block_write_begin and block_commit_write to zero the * whole block. */ - ret = __block_write_begin(page, block_start + 1, 0, + ret = __block_write_begin(folio, block_start + 1, 0, ocfs2_get_block); if (ret < 0) { mlog_errno(ret); @@ -812,7 +813,7 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from, /* must not update i_size! */ - block_commit_write(page, block_start + 1, block_start + 1); + block_commit_write(&folio->page, block_start + 1, block_start + 1); } /* @@ -833,8 +834,8 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from, } out_unlock: - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); out_commit_trans: if (handle) ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle); @@ -2750,6 +2751,13 @@ out_unlock: return remapped > 0 ? remapped : ret; } +static loff_t ocfs2_dir_llseek(struct file *file, loff_t offset, int whence) +{ + struct ocfs2_file_private *fp = file->private_data; + + return generic_llseek_cookie(file, offset, whence, &fp->cookie); +} + const struct inode_operations ocfs2_file_iops = { .setattr = ocfs2_setattr, .getattr = ocfs2_getattr, @@ -2797,7 +2805,7 @@ const struct file_operations ocfs2_fops = { WRAP_DIR_ITER(ocfs2_readdir) // FIXME! const struct file_operations ocfs2_dops = { - .llseek = generic_file_llseek, + .llseek = ocfs2_dir_llseek, .read = generic_read_dir, .iterate_shared = shared_ocfs2_readdir, .fsync = ocfs2_sync_file, @@ -2843,7 +2851,7 @@ const struct file_operations ocfs2_fops_no_plocks = { }; const struct file_operations ocfs2_dops_no_plocks = { - .llseek = generic_file_llseek, + .llseek = ocfs2_dir_llseek, .read = generic_read_dir, .iterate_shared = shared_ocfs2_readdir, .fsync = ocfs2_sync_file, diff --git a/fs/ocfs2/file.h b/fs/ocfs2/file.h index 8e53e4ac1120..41e65e45a9f3 100644 --- a/fs/ocfs2/file.h +++ b/fs/ocfs2/file.h @@ -20,6 +20,7 @@ struct ocfs2_alloc_context; enum ocfs2_alloc_restarted; struct ocfs2_file_private { + u64 cookie; struct file *fp_file; struct mutex fp_mutex; struct ocfs2_lock_res fp_flock; diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c index 1834f26522ed..6ef4cb045ccd 100644 --- a/fs/ocfs2/mmap.c +++ b/fs/ocfs2/mmap.c @@ -53,7 +53,7 @@ static vm_fault_t __ocfs2_page_mkwrite(struct file *file, loff_t pos = page_offset(page); unsigned int len = PAGE_SIZE; pgoff_t last_index; - struct page *locked_page = NULL; + struct folio *locked_folio = NULL; void *fsdata; loff_t size = i_size_read(inode); @@ -91,7 +91,7 @@ static vm_fault_t __ocfs2_page_mkwrite(struct file *file, len = ((size - 1) & ~PAGE_MASK) + 1; err = ocfs2_write_begin_nolock(mapping, pos, len, OCFS2_WRITE_MMAP, - &locked_page, &fsdata, di_bh, page); + &locked_folio, &fsdata, di_bh, page); if (err) { if (err != -ENOSPC) mlog_errno(err); @@ -99,7 +99,7 @@ static vm_fault_t __ocfs2_page_mkwrite(struct file *file, goto out; } - if (!locked_page) { + if (!locked_folio) { ret = VM_FAULT_NOPAGE; goto out; } diff --git a/fs/omfs/file.c b/fs/omfs/file.c index 6b580b9da8e3..98358d405b6a 100644 --- a/fs/omfs/file.c +++ b/fs/omfs/file.c @@ -312,11 +312,11 @@ static void omfs_write_failed(struct address_space *mapping, loff_t to) static int omfs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { int ret; - ret = block_write_begin(mapping, pos, len, pagep, omfs_get_block); + ret = block_write_begin(mapping, pos, len, foliop, omfs_get_block); if (unlikely(ret)) omfs_write_failed(mapping, pos + len); diff --git a/fs/open.c b/fs/open.c index 22adbef7ecc2..daf1b55ca818 100644 --- a/fs/open.c +++ b/fs/open.c @@ -252,40 +252,39 @@ int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len) if (offset < 0 || len <= 0) return -EINVAL; - /* Return error if mode is not supported */ - if (mode & ~FALLOC_FL_SUPPORTED_MASK) + if (mode & ~(FALLOC_FL_MODE_MASK | FALLOC_FL_KEEP_SIZE)) return -EOPNOTSUPP; - /* Punch hole and zero range are mutually exclusive */ - if ((mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE)) == - (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE)) - return -EOPNOTSUPP; - - /* Punch hole must have keep size set */ - if ((mode & FALLOC_FL_PUNCH_HOLE) && - !(mode & FALLOC_FL_KEEP_SIZE)) + /* + * Modes are exclusive, even if that is not obvious from the encoding + * as bit masks and the mix with the flag in the same namespace. + * + * To make things even more complicated, FALLOC_FL_ALLOCATE_RANGE is + * encoded as no bit set. + */ + switch (mode & FALLOC_FL_MODE_MASK) { + case FALLOC_FL_ALLOCATE_RANGE: + case FALLOC_FL_UNSHARE_RANGE: + case FALLOC_FL_ZERO_RANGE: + break; + case FALLOC_FL_PUNCH_HOLE: + if (!(mode & FALLOC_FL_KEEP_SIZE)) + return -EOPNOTSUPP; + break; + case FALLOC_FL_COLLAPSE_RANGE: + case FALLOC_FL_INSERT_RANGE: + if (mode & FALLOC_FL_KEEP_SIZE) + return -EOPNOTSUPP; + break; + default: return -EOPNOTSUPP; - - /* Collapse range should only be used exclusively. */ - if ((mode & FALLOC_FL_COLLAPSE_RANGE) && - (mode & ~FALLOC_FL_COLLAPSE_RANGE)) - return -EINVAL; - - /* Insert range should only be used exclusively. */ - if ((mode & FALLOC_FL_INSERT_RANGE) && - (mode & ~FALLOC_FL_INSERT_RANGE)) - return -EINVAL; - - /* Unshare range should only be used with allocate mode. */ - if ((mode & FALLOC_FL_UNSHARE_RANGE) && - (mode & ~(FALLOC_FL_UNSHARE_RANGE | FALLOC_FL_KEEP_SIZE))) - return -EINVAL; + } if (!(file->f_mode & FMODE_WRITE)) return -EBADF; /* - * We can only allow pure fallocate on append only files + * On append-only files only space preallocation is supported. */ if ((mode & ~FALLOC_FL_KEEP_SIZE) && IS_APPEND(inode)) return -EPERM; diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c index fdb9b65db1de..aae6d2b8767d 100644 --- a/fs/orangefs/inode.c +++ b/fs/orangefs/inode.c @@ -309,22 +309,18 @@ static int orangefs_read_folio(struct file *file, struct folio *folio) static int orangefs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { struct orangefs_write_range *wr; struct folio *folio; - struct page *page; - pgoff_t index; int ret; - index = pos >> PAGE_SHIFT; + folio = __filemap_get_folio(mapping, pos / PAGE_SIZE, FGP_WRITEBEGIN, + mapping_gfp_mask(mapping)); + if (IS_ERR(folio)) + return PTR_ERR(folio); - page = grab_cache_page_write_begin(mapping, index); - if (!page) - return -ENOMEM; - - *pagep = page; - folio = page_folio(page); + *foliop = folio; if (folio_test_dirty(folio) && !folio_test_private(folio)) { /* @@ -365,9 +361,10 @@ okay: } static int orangefs_write_end(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) + loff_t pos, unsigned len, unsigned copied, struct folio *folio, + void *fsdata) { - struct inode *inode = page->mapping->host; + struct inode *inode = folio->mapping->host; loff_t last_pos = pos + copied; /* @@ -377,23 +374,23 @@ static int orangefs_write_end(struct file *file, struct address_space *mapping, if (last_pos > inode->i_size) i_size_write(inode, last_pos); - /* zero the stale part of the page if we did a short copy */ - if (!PageUptodate(page)) { + /* zero the stale part of the folio if we did a short copy */ + if (!folio_test_uptodate(folio)) { unsigned from = pos & (PAGE_SIZE - 1); if (copied < len) { - zero_user(page, from + copied, len - copied); + folio_zero_range(folio, from + copied, len - copied); } /* Set fully written pages uptodate. */ - if (pos == page_offset(page) && + if (pos == folio_pos(folio) && (len == PAGE_SIZE || pos + len == inode->i_size)) { - zero_user_segment(page, from + copied, PAGE_SIZE); - SetPageUptodate(page); + folio_zero_segment(folio, from + copied, PAGE_SIZE); + folio_mark_uptodate(folio); } } - set_page_dirty(page); - unlock_page(page); - put_page(page); + folio_mark_dirty(folio); + folio_unlock(folio); + folio_put(folio); mark_inode_dirty_sync(file_inode(file)); return copied; diff --git a/fs/pipe.c b/fs/pipe.c index 7dff2aa50a6d..4083ba492cb6 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -686,7 +686,7 @@ pipe_poll(struct file *filp, poll_table *wait) if (filp->f_mode & FMODE_READ) { if (!pipe_empty(head, tail)) mask |= EPOLLIN | EPOLLRDNORM; - if (!pipe->writers && filp->f_version != pipe->w_counter) + if (!pipe->writers && filp->f_pipe != pipe->w_counter) mask |= EPOLLHUP; } @@ -945,6 +945,7 @@ int create_pipe_files(struct file **res, int flags) } f->private_data = inode->i_pipe; + f->f_pipe = 0; res[0] = alloc_file_clone(f, O_RDONLY | (flags & O_NONBLOCK), &pipefifo_fops); @@ -954,6 +955,7 @@ int create_pipe_files(struct file **res, int flags) return PTR_ERR(res[0]); } res[0]->private_data = inode->i_pipe; + res[0]->f_pipe = 0; res[1] = f; stream_open(inode, res[0]); stream_open(inode, res[1]); @@ -1108,7 +1110,7 @@ static int fifo_open(struct inode *inode, struct file *filp) bool is_pipe = inode->i_sb->s_magic == PIPEFS_MAGIC; int ret; - filp->f_version = 0; + filp->f_pipe = 0; spin_lock(&inode->i_lock); if (inode->i_pipe) { @@ -1155,7 +1157,7 @@ static int fifo_open(struct inode *inode, struct file *filp) if ((filp->f_flags & O_NONBLOCK)) { /* suppress EPOLLHUP until we have * seen a writer */ - filp->f_version = pipe->w_counter; + filp->f_pipe = pipe->w_counter; } else { if (wait_for_partner(pipe, &pipe->w_counter)) goto err_rd; @@ -1427,7 +1429,7 @@ static const struct super_operations pipefs_ops = { /* * pipefs should _never_ be mounted by userland - too much of security hassle, - * no real gain from having the whole whorehouse mounted. So we don't need + * no real gain from having the whole file system mounted. So we don't need * any operations on the root directory. However, we need a non-trivial * d_name - pipe: will go nicely and kill the special-casing in procfs. */ diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 3f87297dbfdb..6c66a37522d0 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -715,8 +715,8 @@ int posix_acl_update_mode(struct mnt_idmap *idmap, return error; if (error == 0) *acl = NULL; - if (!vfsgid_in_group_p(i_gid_into_vfsgid(idmap, inode)) && - !capable_wrt_inode_uidgid(idmap, inode, CAP_FSETID)) + if (!in_group_or_capable(idmap, inode, + i_gid_into_vfsgid(idmap, inode))) mode &= ~S_ISGID; *mode_p = mode; return 0; diff --git a/fs/proc/base.c b/fs/proc/base.c index 72a1acd03675..1ad51858528f 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -85,6 +85,7 @@ #include <linux/elf.h> #include <linux/pid_namespace.h> #include <linux/user_namespace.h> +#include <linux/fs_parser.h> #include <linux/fs_struct.h> #include <linux/slab.h> #include <linux/sched/autogroup.h> @@ -117,6 +118,40 @@ static u8 nlink_tid __ro_after_init; static u8 nlink_tgid __ro_after_init; +enum proc_mem_force { + PROC_MEM_FORCE_ALWAYS, + PROC_MEM_FORCE_PTRACE, + PROC_MEM_FORCE_NEVER +}; + +static enum proc_mem_force proc_mem_force_override __ro_after_init = + IS_ENABLED(CONFIG_PROC_MEM_NO_FORCE) ? PROC_MEM_FORCE_NEVER : + IS_ENABLED(CONFIG_PROC_MEM_FORCE_PTRACE) ? PROC_MEM_FORCE_PTRACE : + PROC_MEM_FORCE_ALWAYS; + +static const struct constant_table proc_mem_force_table[] __initconst = { + { "always", PROC_MEM_FORCE_ALWAYS }, + { "ptrace", PROC_MEM_FORCE_PTRACE }, + { "never", PROC_MEM_FORCE_NEVER }, + { } +}; + +static int __init early_proc_mem_force_override(char *buf) +{ + if (!buf) + return -EINVAL; + + /* + * lookup_constant() defaults to proc_mem_force_override to preseve + * the initial Kconfig choice in case an invalid param gets passed. + */ + proc_mem_force_override = lookup_constant(proc_mem_force_table, + buf, proc_mem_force_override); + + return 0; +} +early_param("proc_mem.force_override", early_proc_mem_force_override); + struct pid_entry { const char *name; unsigned int len; @@ -827,12 +862,31 @@ static int __mem_open(struct inode *inode, struct file *file, unsigned int mode) static int mem_open(struct inode *inode, struct file *file) { - int ret = __mem_open(inode, file, PTRACE_MODE_ATTACH); - - /* OK to pass negative loff_t, we can catch out-of-range */ - file->f_mode |= FMODE_UNSIGNED_OFFSET; + if (WARN_ON_ONCE(!(file->f_op->fop_flags & FOP_UNSIGNED_OFFSET))) + return -EINVAL; + return __mem_open(inode, file, PTRACE_MODE_ATTACH); +} - return ret; +static bool proc_mem_foll_force(struct file *file, struct mm_struct *mm) +{ + struct task_struct *task; + bool ptrace_active = false; + + switch (proc_mem_force_override) { + case PROC_MEM_FORCE_NEVER: + return false; + case PROC_MEM_FORCE_PTRACE: + task = get_proc_task(file_inode(file)); + if (task) { + ptrace_active = READ_ONCE(task->ptrace) && + READ_ONCE(task->mm) == mm && + READ_ONCE(task->parent) == current; + put_task_struct(task); + } + return ptrace_active; + default: + return true; + } } static ssize_t mem_rw(struct file *file, char __user *buf, @@ -855,7 +909,9 @@ static ssize_t mem_rw(struct file *file, char __user *buf, if (!mmget_not_zero(mm)) goto free; - flags = FOLL_FORCE | (write ? FOLL_WRITE : 0); + flags = write ? FOLL_WRITE : 0; + if (proc_mem_foll_force(file, mm)) + flags |= FOLL_FORCE; while (count > 0) { size_t this_len = min_t(size_t, count, PAGE_SIZE); @@ -932,6 +988,7 @@ static const struct file_operations proc_mem_operations = { .write = mem_write, .open = mem_open, .release = mem_release, + .fop_flags = FOP_UNSIGNED_OFFSET, }; static int environ_open(struct inode *inode, struct file *file) @@ -2276,8 +2333,8 @@ proc_map_files_instantiate(struct dentry *dentry, inode->i_op = &proc_map_files_link_inode_operations; inode->i_size = 64; - d_set_d_op(dentry, &tid_map_files_dentry_operations); - return d_splice_alias(inode, dentry); + return proc_splice_unmountable(inode, dentry, + &tid_map_files_dentry_operations); } static struct dentry *proc_map_files_lookup(struct inode *dir, @@ -3870,12 +3927,12 @@ static int proc_task_readdir(struct file *file, struct dir_context *ctx) if (!dir_emit_dots(file, ctx)) return 0; - /* f_version caches the tgid value that the last readdir call couldn't - * return. lseek aka telldir automagically resets f_version to 0. + /* We cache the tgid value that the last readdir call couldn't + * return and lseek resets it to 0. */ ns = proc_pid_ns(inode->i_sb); - tid = (int)file->f_version; - file->f_version = 0; + tid = (int)(intptr_t)file->private_data; + file->private_data = NULL; for (task = first_tid(proc_pid(inode), tid, ctx->pos - 2, ns); task; task = next_tid(task), ctx->pos++) { @@ -3890,7 +3947,7 @@ static int proc_task_readdir(struct file *file, struct dir_context *ctx) proc_task_instantiate, task, NULL)) { /* returning this tgid failed, save it as the first * pid for the next readir call */ - file->f_version = (u64)tid; + file->private_data = (void *)(intptr_t)tid; put_task_struct(task); break; } @@ -3915,6 +3972,24 @@ static int proc_task_getattr(struct mnt_idmap *idmap, return 0; } +/* + * proc_task_readdir() set @file->private_data to a positive integer + * value, so casting that to u64 is safe. generic_llseek_cookie() will + * set @cookie to 0, so casting to an int is safe. The WARN_ON_ONCE() is + * here to catch any unexpected change in behavior either in + * proc_task_readdir() or generic_llseek_cookie(). + */ +static loff_t proc_dir_llseek(struct file *file, loff_t offset, int whence) +{ + u64 cookie = (u64)(intptr_t)file->private_data; + loff_t off; + + off = generic_llseek_cookie(file, offset, whence, &cookie); + WARN_ON_ONCE(cookie > INT_MAX); + file->private_data = (void *)(intptr_t)cookie; /* serialized by f_pos_lock */ + return off; +} + static const struct inode_operations proc_task_inode_operations = { .lookup = proc_task_lookup, .getattr = proc_task_getattr, @@ -3925,7 +4000,7 @@ static const struct inode_operations proc_task_inode_operations = { static const struct file_operations proc_task_operations = { .read = generic_read_dir, .iterate_shared = proc_task_readdir, - .llseek = generic_file_llseek, + .llseek = proc_dir_llseek, }; void __init set_proc_pid_nlink(void) diff --git a/fs/proc/fd.c b/fs/proc/fd.c index 586bbc84ca04..1f54a54bfb91 100644 --- a/fs/proc/fd.c +++ b/fs/proc/fd.c @@ -59,7 +59,7 @@ static int seq_show(struct seq_file *m, void *v) real_mount(file->f_path.mnt)->mnt_id, file_inode(file)->i_ino); - /* show_fd_locks() never deferences files so a stale value is safe */ + /* show_fd_locks() never dereferences files, so a stale value is safe */ show_fd_locks(m, file, files); if (seq_has_overflowed(m)) goto out; @@ -220,8 +220,8 @@ static struct dentry *proc_fd_instantiate(struct dentry *dentry, ei->op.proc_get_link = proc_fd_link; tid_fd_update_inode(task, inode, data->mode); - d_set_d_op(dentry, &tid_fd_dentry_operations); - return d_splice_alias(inode, dentry); + return proc_splice_unmountable(inode, dentry, + &tid_fd_dentry_operations); } static struct dentry *proc_lookupfd_common(struct inode *dir, @@ -312,14 +312,14 @@ static int proc_readfd_count(struct inode *inode, loff_t *count) return 0; } -static int proc_readfd(struct file *file, struct dir_context *ctx) +static int proc_fd_iterate(struct file *file, struct dir_context *ctx) { return proc_readfd_common(file, ctx, proc_fd_instantiate); } const struct file_operations proc_fd_operations = { .read = generic_read_dir, - .iterate_shared = proc_readfd, + .iterate_shared = proc_fd_iterate, .llseek = generic_file_llseek, }; @@ -397,8 +397,8 @@ static struct dentry *proc_fdinfo_instantiate(struct dentry *dentry, inode->i_fop = &proc_fdinfo_file_operations; tid_fd_update_inode(task, inode, 0); - d_set_d_op(dentry, &tid_fd_dentry_operations); - return d_splice_alias(inode, dentry); + return proc_splice_unmountable(inode, dentry, + &tid_fd_dentry_operations); } static struct dentry * @@ -407,7 +407,7 @@ proc_lookupfdinfo(struct inode *dir, struct dentry *dentry, unsigned int flags) return proc_lookupfd_common(dir, dentry, proc_fdinfo_instantiate); } -static int proc_readfdinfo(struct file *file, struct dir_context *ctx) +static int proc_fdinfo_iterate(struct file *file, struct dir_context *ctx) { return proc_readfd_common(file, ctx, proc_fdinfo_instantiate); @@ -421,6 +421,6 @@ const struct inode_operations proc_fdinfo_inode_operations = { const struct file_operations proc_fdinfo_operations = { .read = generic_read_dir, - .iterate_shared = proc_readfdinfo, + .iterate_shared = proc_fdinfo_iterate, .llseek = generic_file_llseek, }; diff --git a/fs/proc/generic.c b/fs/proc/generic.c index c02f1e63f82d..dbe82cf23ee4 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -464,9 +464,9 @@ struct proc_dir_entry *proc_symlink(const char *name, (S_IFLNK | S_IRUGO | S_IWUGO | S_IXUGO),1); if (ent) { - ent->data = kmalloc((ent->size=strlen(dest))+1, GFP_KERNEL); + ent->size = strlen(dest); + ent->data = kmemdup(dest, ent->size + 1, GFP_KERNEL); if (ent->data) { - strcpy((char*)ent->data,dest); ent->proc_iops = &proc_link_inode_operations; ent = proc_register(parent, ent); } else { diff --git a/fs/proc/internal.h b/fs/proc/internal.h index a8a8576d8592..9e3f25e4c188 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -349,3 +349,16 @@ static inline void pde_force_lookup(struct proc_dir_entry *pde) /* /proc/net/ entries can be changed under us by setns(CLONE_NEWNET) */ pde->proc_dops = &proc_net_dentry_ops; } + +/* + * Add a new procfs dentry that can't serve as a mountpoint. That should + * encompass anything that is ephemeral and can just disappear while the + * process is still around. + */ +static inline struct dentry *proc_splice_unmountable(struct inode *inode, + struct dentry *dentry, const struct dentry_operations *d_ops) +{ + d_set_d_op(dentry, d_ops); + dont_mount(dentry); + return d_splice_alias(inode, dentry); +} diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index 8e08a9a1b7ed..7d0acdad74e2 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -235,7 +235,7 @@ static int kcore_ram_list(struct list_head *list) int nid, ret; unsigned long end_pfn; - /* Not inialized....update now */ + /* Not initialized....update now */ /* find out "max pfn" */ end_pfn = 0; for_each_node_state(nid, N_MEMORY) { diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 5f171ad7b436..2c5f4814aef9 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -976,7 +976,9 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) [ilog2(VM_PKEY_BIT0)] = "", [ilog2(VM_PKEY_BIT1)] = "", [ilog2(VM_PKEY_BIT2)] = "", +#if VM_PKEY_BIT3 [ilog2(VM_PKEY_BIT3)] = "", +#endif #if VM_PKEY_BIT4 [ilog2(VM_PKEY_BIT4)] = "", #endif diff --git a/fs/qnx6/dir.c b/fs/qnx6/dir.c index c1cfb8a19e9d..b4d10e45f2e4 100644 --- a/fs/qnx6/dir.c +++ b/fs/qnx6/dir.c @@ -24,13 +24,15 @@ static unsigned qnx6_lfile_checksum(char *name, unsigned size) return crc; } -static struct page *qnx6_get_page(struct inode *dir, unsigned long n) +static void *qnx6_get_folio(struct inode *dir, unsigned long n, + struct folio **foliop) { - struct address_space *mapping = dir->i_mapping; - struct page *page = read_mapping_page(mapping, n, NULL); - if (!IS_ERR(page)) - kmap(page); - return page; + struct folio *folio = read_mapping_folio(dir->i_mapping, n, NULL); + + if (IS_ERR(folio)) + return folio; + *foliop = folio; + return kmap_local_folio(folio, 0); } static unsigned last_entry(struct inode *inode, unsigned long page_nr) @@ -44,19 +46,20 @@ static unsigned last_entry(struct inode *inode, unsigned long page_nr) static struct qnx6_long_filename *qnx6_longname(struct super_block *sb, struct qnx6_long_dir_entry *de, - struct page **p) + struct folio **foliop) { struct qnx6_sb_info *sbi = QNX6_SB(sb); u32 s = fs32_to_cpu(sbi, de->de_long_inode); /* in block units */ u32 n = s >> (PAGE_SHIFT - sb->s_blocksize_bits); /* in pages */ - /* within page */ - u32 offs = (s << sb->s_blocksize_bits) & ~PAGE_MASK; + u32 offs; struct address_space *mapping = sbi->longfile->i_mapping; - struct page *page = read_mapping_page(mapping, n, NULL); - if (IS_ERR(page)) - return ERR_CAST(page); - kmap(*p = page); - return (struct qnx6_long_filename *)(page_address(page) + offs); + struct folio *folio = read_mapping_folio(mapping, n, NULL); + + if (IS_ERR(folio)) + return ERR_CAST(folio); + offs = offset_in_folio(folio, s << sb->s_blocksize_bits); + *foliop = folio; + return kmap_local_folio(folio, offs); } static int qnx6_dir_longfilename(struct inode *inode, @@ -67,7 +70,7 @@ static int qnx6_dir_longfilename(struct inode *inode, struct qnx6_long_filename *lf; struct super_block *s = inode->i_sb; struct qnx6_sb_info *sbi = QNX6_SB(s); - struct page *page; + struct folio *folio; int lf_size; if (de->de_size != 0xff) { @@ -76,7 +79,7 @@ static int qnx6_dir_longfilename(struct inode *inode, pr_err("invalid direntry size (%i).\n", de->de_size); return 0; } - lf = qnx6_longname(s, de, &page); + lf = qnx6_longname(s, de, &folio); if (IS_ERR(lf)) { pr_err("Error reading longname\n"); return 0; @@ -87,7 +90,7 @@ static int qnx6_dir_longfilename(struct inode *inode, if (lf_size > QNX6_LONG_NAME_MAX) { pr_debug("file %s\n", lf->lf_fname); pr_err("Filename too long (%i)\n", lf_size); - qnx6_put_page(page); + folio_release_kmap(folio, lf); return 0; } @@ -100,11 +103,11 @@ static int qnx6_dir_longfilename(struct inode *inode, pr_debug("qnx6_readdir:%.*s inode:%u\n", lf_size, lf->lf_fname, de_inode); if (!dir_emit(ctx, lf->lf_fname, lf_size, de_inode, DT_UNKNOWN)) { - qnx6_put_page(page); + folio_release_kmap(folio, lf); return 0; } - qnx6_put_page(page); + folio_release_kmap(folio, lf); /* success */ return 1; } @@ -117,26 +120,27 @@ static int qnx6_readdir(struct file *file, struct dir_context *ctx) loff_t pos = ctx->pos & ~(QNX6_DIR_ENTRY_SIZE - 1); unsigned long npages = dir_pages(inode); unsigned long n = pos >> PAGE_SHIFT; - unsigned start = (pos & ~PAGE_MASK) / QNX6_DIR_ENTRY_SIZE; + unsigned offset = (pos & ~PAGE_MASK) / QNX6_DIR_ENTRY_SIZE; bool done = false; ctx->pos = pos; if (ctx->pos >= inode->i_size) return 0; - for ( ; !done && n < npages; n++, start = 0) { - struct page *page = qnx6_get_page(inode, n); - int limit = last_entry(inode, n); + for ( ; !done && n < npages; n++, offset = 0) { struct qnx6_dir_entry *de; - int i = start; + struct folio *folio; + char *kaddr = qnx6_get_folio(inode, n, &folio); + char *limit; - if (IS_ERR(page)) { + if (IS_ERR(kaddr)) { pr_err("%s(): read failed\n", __func__); ctx->pos = (n + 1) << PAGE_SHIFT; - return PTR_ERR(page); + return PTR_ERR(kaddr); } - de = ((struct qnx6_dir_entry *)page_address(page)) + start; - for (; i < limit; i++, de++, ctx->pos += QNX6_DIR_ENTRY_SIZE) { + de = (struct qnx6_dir_entry *)(kaddr + offset); + limit = kaddr + last_entry(inode, n); + for (; (char *)de < limit; de++, ctx->pos += QNX6_DIR_ENTRY_SIZE) { int size = de->de_size; u32 no_inode = fs32_to_cpu(sbi, de->de_inode); @@ -164,7 +168,7 @@ static int qnx6_readdir(struct file *file, struct dir_context *ctx) } } } - qnx6_put_page(page); + folio_release_kmap(folio, kaddr); } return 0; } @@ -177,23 +181,23 @@ static unsigned qnx6_long_match(int len, const char *name, { struct super_block *s = dir->i_sb; struct qnx6_sb_info *sbi = QNX6_SB(s); - struct page *page; + struct folio *folio; int thislen; - struct qnx6_long_filename *lf = qnx6_longname(s, de, &page); + struct qnx6_long_filename *lf = qnx6_longname(s, de, &folio); if (IS_ERR(lf)) return 0; thislen = fs16_to_cpu(sbi, lf->lf_size); if (len != thislen) { - qnx6_put_page(page); + folio_release_kmap(folio, lf); return 0; } if (memcmp(name, lf->lf_fname, len) == 0) { - qnx6_put_page(page); + folio_release_kmap(folio, lf); return fs32_to_cpu(sbi, de->de_inode); } - qnx6_put_page(page); + folio_release_kmap(folio, lf); return 0; } @@ -210,20 +214,17 @@ static unsigned qnx6_match(struct super_block *s, int len, const char *name, } -unsigned qnx6_find_entry(int len, struct inode *dir, const char *name, - struct page **res_page) +unsigned qnx6_find_ino(int len, struct inode *dir, const char *name) { struct super_block *s = dir->i_sb; struct qnx6_inode_info *ei = QNX6_I(dir); - struct page *page = NULL; + struct folio *folio; unsigned long start, n; unsigned long npages = dir_pages(dir); unsigned ino; struct qnx6_dir_entry *de; struct qnx6_long_dir_entry *lde; - *res_page = NULL; - if (npages == 0) return 0; start = ei->i_dir_start_lookup; @@ -232,12 +233,11 @@ unsigned qnx6_find_entry(int len, struct inode *dir, const char *name, n = start; do { - page = qnx6_get_page(dir, n); - if (!IS_ERR(page)) { + de = qnx6_get_folio(dir, n, &folio); + if (!IS_ERR(de)) { int limit = last_entry(dir, n); int i; - de = (struct qnx6_dir_entry *)page_address(page); for (i = 0; i < limit; i++, de++) { if (len <= QNX6_SHORT_NAME_MAX) { /* short filename */ @@ -256,7 +256,7 @@ unsigned qnx6_find_entry(int len, struct inode *dir, const char *name, } else pr_err("undefined filename size in inode.\n"); } - qnx6_put_page(page); + folio_release_kmap(folio, de - i); } if (++n >= npages) @@ -265,8 +265,8 @@ unsigned qnx6_find_entry(int len, struct inode *dir, const char *name, return 0; found: - *res_page = page; ei->i_dir_start_lookup = n; + folio_release_kmap(folio, de); return ino; } diff --git a/fs/qnx6/inode.c b/fs/qnx6/inode.c index 4f1735b882b1..85925ec0051a 100644 --- a/fs/qnx6/inode.c +++ b/fs/qnx6/inode.c @@ -184,17 +184,17 @@ static const char *qnx6_checkroot(struct super_block *s) struct qnx6_dir_entry *dir_entry; struct inode *root = d_inode(s->s_root); struct address_space *mapping = root->i_mapping; - struct page *page = read_mapping_page(mapping, 0, NULL); - if (IS_ERR(page)) + struct folio *folio = read_mapping_folio(mapping, 0, NULL); + + if (IS_ERR(folio)) return "error reading root directory"; - kmap(page); - dir_entry = page_address(page); + dir_entry = kmap_local_folio(folio, 0); for (i = 0; i < 2; i++) { /* maximum 3 bytes - due to match_root limitation */ if (strncmp(dir_entry[i].de_fname, match_root[i], 3)) error = 1; } - qnx6_put_page(page); + folio_release_kmap(folio, dir_entry); if (error) return "error reading root directory."; return NULL; @@ -518,7 +518,7 @@ struct inode *qnx6_iget(struct super_block *sb, unsigned ino) struct inode *inode; struct qnx6_inode_info *ei; struct address_space *mapping; - struct page *page; + struct folio *folio; u32 n, offs; inode = iget_locked(sb, ino); @@ -538,17 +538,16 @@ struct inode *qnx6_iget(struct super_block *sb, unsigned ino) return ERR_PTR(-EIO); } n = (ino - 1) >> (PAGE_SHIFT - QNX6_INODE_SIZE_BITS); - offs = (ino - 1) & (~PAGE_MASK >> QNX6_INODE_SIZE_BITS); mapping = sbi->inodes->i_mapping; - page = read_mapping_page(mapping, n, NULL); - if (IS_ERR(page)) { + folio = read_mapping_folio(mapping, n, NULL); + if (IS_ERR(folio)) { pr_err("major problem: unable to read inode from dev %s\n", sb->s_id); iget_failed(inode); - return ERR_CAST(page); + return ERR_CAST(folio); } - kmap(page); - raw_inode = ((struct qnx6_inode_entry *)page_address(page)) + offs; + offs = offset_in_folio(folio, (ino - 1) << QNX6_INODE_SIZE_BITS); + raw_inode = kmap_local_folio(folio, offs); inode->i_mode = fs16_to_cpu(sbi, raw_inode->di_mode); i_uid_write(inode, (uid_t)fs32_to_cpu(sbi, raw_inode->di_uid)); @@ -578,7 +577,7 @@ struct inode *qnx6_iget(struct super_block *sb, unsigned ino) inode->i_mapping->a_ops = &qnx6_aops; } else init_special_inode(inode, inode->i_mode, 0); - qnx6_put_page(page); + folio_release_kmap(folio, raw_inode); unlock_new_inode(inode); return inode; } diff --git a/fs/qnx6/namei.c b/fs/qnx6/namei.c index e2e98e653b8d..0f0755a9ecb5 100644 --- a/fs/qnx6/namei.c +++ b/fs/qnx6/namei.c @@ -17,7 +17,6 @@ struct dentry *qnx6_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { unsigned ino; - struct page *page; struct inode *foundinode = NULL; const char *name = dentry->d_name.name; int len = dentry->d_name.len; @@ -25,10 +24,9 @@ struct dentry *qnx6_lookup(struct inode *dir, struct dentry *dentry, if (len > QNX6_LONG_NAME_MAX) return ERR_PTR(-ENAMETOOLONG); - ino = qnx6_find_entry(len, dir, name, &page); + ino = qnx6_find_ino(len, dir, name); if (ino) { foundinode = qnx6_iget(dir->i_sb, ino); - qnx6_put_page(page); if (IS_ERR(foundinode)) pr_debug("lookup->iget -> error %ld\n", PTR_ERR(foundinode)); diff --git a/fs/qnx6/qnx6.h b/fs/qnx6/qnx6.h index 34a6b126a3a9..56ed1367499e 100644 --- a/fs/qnx6/qnx6.h +++ b/fs/qnx6/qnx6.h @@ -126,11 +126,4 @@ static inline __fs16 cpu_to_fs16(struct qnx6_sb_info *sbi, __u16 n) extern struct qnx6_super_block *qnx6_mmi_fill_super(struct super_block *s, int silent); -static inline void qnx6_put_page(struct page *page) -{ - kunmap(page); - put_page(page); -} - -extern unsigned qnx6_find_entry(int len, struct inode *dir, const char *name, - struct page **res_page); +unsigned qnx6_find_ino(int len, struct inode *dir, const char *name); diff --git a/fs/read_write.c b/fs/read_write.c index 90e283b31ca1..070a7c33b9dd 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -36,22 +36,24 @@ EXPORT_SYMBOL(generic_ro_fops); static inline bool unsigned_offsets(struct file *file) { - return file->f_mode & FMODE_UNSIGNED_OFFSET; + return file->f_op->fop_flags & FOP_UNSIGNED_OFFSET; } /** - * vfs_setpos - update the file offset for lseek + * vfs_setpos_cookie - update the file offset for lseek and reset cookie * @file: file structure in question * @offset: file offset to seek to * @maxsize: maximum file size + * @cookie: cookie to reset * - * This is a low-level filesystem helper for updating the file offset to - * the value specified by @offset if the given offset is valid and it is - * not equal to the current file offset. + * Update the file offset to the value specified by @offset if the given + * offset is valid and it is not equal to the current file offset and + * reset the specified cookie to indicate that a seek happened. * * Return the specified offset on success and -EINVAL on invalid offset. */ -loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize) +static loff_t vfs_setpos_cookie(struct file *file, loff_t offset, + loff_t maxsize, u64 *cookie) { if (offset < 0 && !unsigned_offsets(file)) return -EINVAL; @@ -60,35 +62,48 @@ loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize) if (offset != file->f_pos) { file->f_pos = offset; - file->f_version = 0; + if (cookie) + *cookie = 0; } return offset; } -EXPORT_SYMBOL(vfs_setpos); /** - * generic_file_llseek_size - generic llseek implementation for regular files - * @file: file structure to seek on + * vfs_setpos - update the file offset for lseek + * @file: file structure in question * @offset: file offset to seek to - * @whence: type of seek - * @maxsize: max size of this file in file system - * @eof: offset used for SEEK_END position + * @maxsize: maximum file size * - * This is a variant of generic_file_llseek that allows passing in a custom - * maximum file size and a custom EOF position, for e.g. hashed directories + * This is a low-level filesystem helper for updating the file offset to + * the value specified by @offset if the given offset is valid and it is + * not equal to the current file offset. * - * Synchronization: - * SEEK_SET and SEEK_END are unsynchronized (but atomic on 64bit platforms) - * SEEK_CUR is synchronized against other SEEK_CURs, but not read/writes. - * read/writes behave like SEEK_SET against seeks. + * Return the specified offset on success and -EINVAL on invalid offset. */ -loff_t -generic_file_llseek_size(struct file *file, loff_t offset, int whence, - loff_t maxsize, loff_t eof) +loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize) +{ + return vfs_setpos_cookie(file, offset, maxsize, NULL); +} +EXPORT_SYMBOL(vfs_setpos); + +/** + * must_set_pos - check whether f_pos has to be updated + * @file: file to seek on + * @offset: offset to use + * @whence: type of seek operation + * @eof: end of file + * + * Check whether f_pos needs to be updated and update @offset according + * to @whence. + * + * Return: 0 if f_pos doesn't need to be updated, 1 if f_pos has to be + * updated, and negative error code on failure. + */ +static int must_set_pos(struct file *file, loff_t *offset, int whence, loff_t eof) { switch (whence) { case SEEK_END: - offset += eof; + *offset += eof; break; case SEEK_CUR: /* @@ -97,23 +112,17 @@ generic_file_llseek_size(struct file *file, loff_t offset, int whence, * f_pos value back to the file because a concurrent read(), * write() or lseek() might have altered it */ - if (offset == 0) - return file->f_pos; - /* - * f_lock protects against read/modify/write race with other - * SEEK_CURs. Note that parallel writes and reads behave - * like SEEK_SET. - */ - spin_lock(&file->f_lock); - offset = vfs_setpos(file, file->f_pos + offset, maxsize); - spin_unlock(&file->f_lock); - return offset; + if (*offset == 0) { + *offset = file->f_pos; + return 0; + } + break; case SEEK_DATA: /* * In the generic case the entire file is data, so as long as * offset isn't at the end of the file then the offset is data. */ - if ((unsigned long long)offset >= eof) + if ((unsigned long long)*offset >= eof) return -ENXIO; break; case SEEK_HOLE: @@ -121,17 +130,103 @@ generic_file_llseek_size(struct file *file, loff_t offset, int whence, * There is a virtual hole at the end of the file, so as long as * offset isn't i_size or larger, return i_size. */ - if ((unsigned long long)offset >= eof) + if ((unsigned long long)*offset >= eof) return -ENXIO; - offset = eof; + *offset = eof; break; } + return 1; +} + +/** + * generic_file_llseek_size - generic llseek implementation for regular files + * @file: file structure to seek on + * @offset: file offset to seek to + * @whence: type of seek + * @maxsize: max size of this file in file system + * @eof: offset used for SEEK_END position + * + * This is a variant of generic_file_llseek that allows passing in a custom + * maximum file size and a custom EOF position, for e.g. hashed directories + * + * Synchronization: + * SEEK_SET and SEEK_END are unsynchronized (but atomic on 64bit platforms) + * SEEK_CUR is synchronized against other SEEK_CURs, but not read/writes. + * read/writes behave like SEEK_SET against seeks. + */ +loff_t +generic_file_llseek_size(struct file *file, loff_t offset, int whence, + loff_t maxsize, loff_t eof) +{ + int ret; + + ret = must_set_pos(file, &offset, whence, eof); + if (ret < 0) + return ret; + if (ret == 0) + return offset; + + if (whence == SEEK_CUR) { + /* + * f_lock protects against read/modify/write race with + * other SEEK_CURs. Note that parallel writes and reads + * behave like SEEK_SET. + */ + guard(spinlock)(&file->f_lock); + return vfs_setpos(file, file->f_pos + offset, maxsize); + } + return vfs_setpos(file, offset, maxsize); } EXPORT_SYMBOL(generic_file_llseek_size); /** + * generic_llseek_cookie - versioned llseek implementation + * @file: file structure to seek on + * @offset: file offset to seek to + * @whence: type of seek + * @cookie: cookie to update + * + * See generic_file_llseek for a general description and locking assumptions. + * + * In contrast to generic_file_llseek, this function also resets a + * specified cookie to indicate a seek took place. + */ +loff_t generic_llseek_cookie(struct file *file, loff_t offset, int whence, + u64 *cookie) +{ + struct inode *inode = file->f_mapping->host; + loff_t maxsize = inode->i_sb->s_maxbytes; + loff_t eof = i_size_read(inode); + int ret; + + if (WARN_ON_ONCE(!cookie)) + return -EINVAL; + + /* + * Require that this is only used for directories that guarantee + * synchronization between readdir and seek so that an update to + * @cookie is correctly synchronized with concurrent readdir. + */ + if (WARN_ON_ONCE(!(file->f_mode & FMODE_ATOMIC_POS))) + return -EINVAL; + + ret = must_set_pos(file, &offset, whence, eof); + if (ret < 0) + return ret; + if (ret == 0) + return offset; + + /* No need to hold f_lock because we know that f_pos_lock is held. */ + if (whence == SEEK_CUR) + return vfs_setpos_cookie(file, file->f_pos + offset, maxsize, cookie); + + return vfs_setpos_cookie(file, offset, maxsize, cookie); +} +EXPORT_SYMBOL(generic_llseek_cookie); + +/** * generic_file_llseek - generic llseek implementation for regular files * @file: file structure to seek on * @offset: file offset to seek to @@ -270,10 +365,8 @@ loff_t default_llseek(struct file *file, loff_t offset, int whence) } retval = -EINVAL; if (offset >= 0 || unsigned_offsets(file)) { - if (offset != file->f_pos) { + if (offset != file->f_pos) file->f_pos = offset; - file->f_version = 0; - } retval = offset; } out: diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index 9b43a81a6488..72c53129c952 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -2178,7 +2178,7 @@ static int grab_tail_page(struct inode *inode, unsigned long offset = (inode->i_size) & (PAGE_SIZE - 1); struct buffer_head *bh; struct buffer_head *head; - struct page *page; + struct folio *folio; int error; /* @@ -2190,20 +2190,20 @@ static int grab_tail_page(struct inode *inode, if ((offset & (blocksize - 1)) == 0) { return -ENOENT; } - page = grab_cache_page(inode->i_mapping, index); - error = -ENOMEM; - if (!page) { - goto out; - } + folio = __filemap_get_folio(inode->i_mapping, index, + FGP_LOCK | FGP_ACCESSED | FGP_CREAT, + mapping_gfp_mask(inode->i_mapping)); + if (IS_ERR(folio)) + return PTR_ERR(folio); /* start within the page of the last block in the file */ start = (offset / blocksize) * blocksize; - error = __block_write_begin(page, start, offset - start, + error = __block_write_begin(folio, start, offset - start, reiserfs_get_block_create_0); if (error) goto unlock; - head = page_buffers(page); + head = folio_buffers(folio); bh = head; do { if (pos >= start) { @@ -2226,14 +2226,13 @@ static int grab_tail_page(struct inode *inode, goto unlock; } *bh_result = bh; - *page_result = page; + *page_result = &folio->page; -out: return error; unlock: - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); return error; } @@ -2736,23 +2735,24 @@ static void reiserfs_truncate_failed_write(struct inode *inode) static int reiserfs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { struct inode *inode; - struct page *page; + struct folio *folio; pgoff_t index; int ret; int old_ref = 0; inode = mapping->host; index = pos >> PAGE_SHIFT; - page = grab_cache_page_write_begin(mapping, index); - if (!page) - return -ENOMEM; - *pagep = page; + folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN, + mapping_gfp_mask(mapping)); + if (IS_ERR(folio)) + return PTR_ERR(folio); + *foliop = folio; reiserfs_wait_on_write_block(inode->i_sb); - fix_tail_page_for_writing(page); + fix_tail_page_for_writing(&folio->page); if (reiserfs_transaction_running(inode->i_sb)) { struct reiserfs_transaction_handle *th; th = (struct reiserfs_transaction_handle *)current-> @@ -2762,7 +2762,7 @@ static int reiserfs_write_begin(struct file *file, old_ref = th->t_refcount; th->t_refcount++; } - ret = __block_write_begin(page, pos, len, reiserfs_get_block); + ret = __block_write_begin(folio, pos, len, reiserfs_get_block); if (ret && reiserfs_transaction_running(inode->i_sb)) { struct reiserfs_transaction_handle *th = current->journal_info; /* @@ -2792,8 +2792,8 @@ static int reiserfs_write_begin(struct file *file, } } if (ret) { - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); /* Truncate allocated blocks */ reiserfs_truncate_failed_write(inode); } @@ -2822,7 +2822,7 @@ int __reiserfs_write_begin(struct page *page, unsigned from, unsigned len) th->t_refcount++; } - ret = __block_write_begin(page, from, len, reiserfs_get_block); + ret = __block_write_begin(page_folio(page), from, len, reiserfs_get_block); if (ret && reiserfs_transaction_running(inode->i_sb)) { struct reiserfs_transaction_handle *th = current->journal_info; /* @@ -2862,10 +2862,9 @@ static sector_t reiserfs_aop_bmap(struct address_space *as, sector_t block) static int reiserfs_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { - struct folio *folio = page_folio(page); - struct inode *inode = page->mapping->host; + struct inode *inode = folio->mapping->host; int ret = 0; int update_sd = 0; struct reiserfs_transaction_handle *th; @@ -2887,7 +2886,7 @@ static int reiserfs_write_end(struct file *file, struct address_space *mapping, } flush_dcache_folio(folio); - reiserfs_commit_page(inode, page, start, start + copied); + reiserfs_commit_page(inode, &folio->page, start, start + copied); /* * generic_commit_write does this for us, but does not update the @@ -2942,8 +2941,8 @@ static int reiserfs_write_end(struct file *file, struct address_space *mapping, out: if (locked) reiserfs_write_unlock(inode->i_sb); - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); if (pos + len > inode->i_size) reiserfs_truncate_failed_write(inode); diff --git a/fs/select.c b/fs/select.c index 9515c3fa1a03..1a4849e2afb9 100644 --- a/fs/select.c +++ b/fs/select.c @@ -840,7 +840,7 @@ SYSCALL_DEFINE1(old_select, struct sel_arg_struct __user *, arg) struct poll_list { struct poll_list *next; unsigned int len; - struct pollfd entries[]; + struct pollfd entries[] __counted_by(len); }; #define POLLFD_PER_PAGE ((PAGE_SIZE-sizeof(struct poll_list)) / sizeof(struct pollfd)) diff --git a/fs/smb/client/cifsencrypt.c b/fs/smb/client/cifsencrypt.c index 6322f0f68a17..7481b21a0489 100644 --- a/fs/smb/client/cifsencrypt.c +++ b/fs/smb/client/cifsencrypt.c @@ -21,127 +21,21 @@ #include <linux/random.h> #include <linux/highmem.h> #include <linux/fips.h> +#include <linux/iov_iter.h> #include "../common/arc4.h" #include <crypto/aead.h> -/* - * Hash data from a BVEC-type iterator. - */ -static int cifs_shash_bvec(const struct iov_iter *iter, ssize_t maxsize, - struct shash_desc *shash) +static size_t cifs_shash_step(void *iter_base, size_t progress, size_t len, + void *priv, void *priv2) { - const struct bio_vec *bv = iter->bvec; - unsigned long start = iter->iov_offset; - unsigned int i; - void *p; - int ret; - - for (i = 0; i < iter->nr_segs; i++) { - size_t off, len; - - len = bv[i].bv_len; - if (start >= len) { - start -= len; - continue; - } - - len = min_t(size_t, maxsize, len - start); - off = bv[i].bv_offset + start; + struct shash_desc *shash = priv; + int ret, *pret = priv2; - p = kmap_local_page(bv[i].bv_page); - ret = crypto_shash_update(shash, p + off, len); - kunmap_local(p); - if (ret < 0) - return ret; - - maxsize -= len; - if (maxsize <= 0) - break; - start = 0; + ret = crypto_shash_update(shash, iter_base, len); + if (ret < 0) { + *pret = ret; + return len; } - - return 0; -} - -/* - * Hash data from a KVEC-type iterator. - */ -static int cifs_shash_kvec(const struct iov_iter *iter, ssize_t maxsize, - struct shash_desc *shash) -{ - const struct kvec *kv = iter->kvec; - unsigned long start = iter->iov_offset; - unsigned int i; - int ret; - - for (i = 0; i < iter->nr_segs; i++) { - size_t len; - - len = kv[i].iov_len; - if (start >= len) { - start -= len; - continue; - } - - len = min_t(size_t, maxsize, len - start); - ret = crypto_shash_update(shash, kv[i].iov_base + start, len); - if (ret < 0) - return ret; - maxsize -= len; - - if (maxsize <= 0) - break; - start = 0; - } - - return 0; -} - -/* - * Hash data from an XARRAY-type iterator. - */ -static ssize_t cifs_shash_xarray(const struct iov_iter *iter, ssize_t maxsize, - struct shash_desc *shash) -{ - struct folio *folios[16], *folio; - unsigned int nr, i, j, npages; - loff_t start = iter->xarray_start + iter->iov_offset; - pgoff_t last, index = start / PAGE_SIZE; - ssize_t ret = 0; - size_t len, offset, foffset; - void *p; - - if (maxsize == 0) - return 0; - - last = (start + maxsize - 1) / PAGE_SIZE; - do { - nr = xa_extract(iter->xarray, (void **)folios, index, last, - ARRAY_SIZE(folios), XA_PRESENT); - if (nr == 0) - return -EIO; - - for (i = 0; i < nr; i++) { - folio = folios[i]; - npages = folio_nr_pages(folio); - foffset = start - folio_pos(folio); - offset = foffset % PAGE_SIZE; - for (j = foffset / PAGE_SIZE; j < npages; j++) { - len = min_t(size_t, maxsize, PAGE_SIZE - offset); - p = kmap_local_page(folio_page(folio, j)); - ret = crypto_shash_update(shash, p, len); - kunmap_local(p); - if (ret < 0) - return ret; - maxsize -= len; - if (maxsize <= 0) - return 0; - start += len; - offset = 0; - index++; - } - } - } while (nr == ARRAY_SIZE(folios)); return 0; } @@ -151,21 +45,13 @@ static ssize_t cifs_shash_xarray(const struct iov_iter *iter, ssize_t maxsize, static int cifs_shash_iter(const struct iov_iter *iter, size_t maxsize, struct shash_desc *shash) { - if (maxsize == 0) - return 0; + struct iov_iter tmp_iter = *iter; + int err = -EIO; - switch (iov_iter_type(iter)) { - case ITER_BVEC: - return cifs_shash_bvec(iter, maxsize, shash); - case ITER_KVEC: - return cifs_shash_kvec(iter, maxsize, shash); - case ITER_XARRAY: - return cifs_shash_xarray(iter, maxsize, shash); - default: - pr_err("cifs_shash_iter(%u) unsupported\n", iov_iter_type(iter)); - WARN_ON_ONCE(1); - return -EIO; - } + if (iterate_and_advance_kernel(&tmp_iter, maxsize, shash, &err, + cifs_shash_step) != maxsize) + return err; + return 0; } int __cifs_calc_signature(struct smb_rqst *rqst, diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 9eae8649f90c..2709c7b0be85 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -255,7 +255,7 @@ struct smb_rqst { struct kvec *rq_iov; /* array of kvecs */ unsigned int rq_nvec; /* number of kvecs in array */ struct iov_iter rq_iter; /* Data iterator */ - struct xarray rq_buffer; /* Page buffer for encryption */ + struct folio_queue *rq_buffer; /* Buffer for encryption */ }; struct mid_q_entry; @@ -1485,7 +1485,6 @@ struct cifs_io_subrequest { struct cifs_io_request *req; }; ssize_t got_bytes; - size_t actual_len; unsigned int xid; int result; bool have_xid; @@ -1550,7 +1549,6 @@ struct cifsInodeInfo { #define CIFS_INO_DELETE_PENDING (3) /* delete pending on server */ #define CIFS_INO_INVALID_MAPPING (4) /* pagecache is invalid */ #define CIFS_INO_LOCK (5) /* lock bit for synchronization */ -#define CIFS_INO_MODIFIED_ATTR (6) /* Indicate change in mtime/ctime */ #define CIFS_INO_CLOSE_ON_LOCK (7) /* Not to defer the close when lock is set */ unsigned long flags; spinlock_t writers_lock; diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index 6dce70f17208..d81da161d3ed 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -1261,16 +1261,30 @@ openRetry: return rc; } +static void cifs_readv_worker(struct work_struct *work) +{ + struct cifs_io_subrequest *rdata = + container_of(work, struct cifs_io_subrequest, subreq.work); + + netfs_read_subreq_terminated(&rdata->subreq, rdata->result, true); +} + static void cifs_readv_callback(struct mid_q_entry *mid) { struct cifs_io_subrequest *rdata = mid->callback_data; + struct netfs_inode *ictx = netfs_inode(rdata->rreq->inode); struct cifs_tcon *tcon = tlink_tcon(rdata->req->cfile->tlink); struct TCP_Server_Info *server = tcon->ses->server; struct smb_rqst rqst = { .rq_iov = rdata->iov, .rq_nvec = 2, .rq_iter = rdata->subreq.io_iter }; - struct cifs_credits credits = { .value = 1, .instance = 0 }; + struct cifs_credits credits = { + .value = 1, + .instance = 0, + .rreq_debug_id = rdata->rreq->debug_id, + .rreq_debug_index = rdata->subreq.debug_index, + }; cifs_dbg(FYI, "%s: mid=%llu state=%d result=%d bytes=%zu\n", __func__, mid->mid, mid->mid_state, rdata->result, @@ -1282,6 +1296,7 @@ cifs_readv_callback(struct mid_q_entry *mid) if (server->sign) { int rc = 0; + iov_iter_truncate(&rqst.rq_iter, rdata->got_bytes); rc = cifs_verify_signature(&rqst, server, mid->sequence_number); if (rc) @@ -1306,13 +1321,22 @@ cifs_readv_callback(struct mid_q_entry *mid) rdata->result = -EIO; } - if (rdata->result == 0 || rdata->result == -EAGAIN) - iov_iter_advance(&rdata->subreq.io_iter, rdata->got_bytes); + if (rdata->result == -ENODATA) { + __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); + rdata->result = 0; + } else { + size_t trans = rdata->subreq.transferred + rdata->got_bytes; + if (trans < rdata->subreq.len && + rdata->subreq.start + trans == ictx->remote_i_size) { + __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); + rdata->result = 0; + } + } + rdata->credits.value = 0; - netfs_subreq_terminated(&rdata->subreq, - (rdata->result == 0 || rdata->result == -EAGAIN) ? - rdata->got_bytes : rdata->result, - false); + rdata->subreq.transferred += rdata->got_bytes; + INIT_WORK(&rdata->subreq.work, cifs_readv_worker); + queue_work(cifsiod_wq, &rdata->subreq.work); release_mid(mid); add_credits(server, &credits, 0); } @@ -1619,9 +1643,15 @@ static void cifs_writev_callback(struct mid_q_entry *mid) { struct cifs_io_subrequest *wdata = mid->callback_data; + struct TCP_Server_Info *server = wdata->server; struct cifs_tcon *tcon = tlink_tcon(wdata->req->cfile->tlink); WRITE_RSP *smb = (WRITE_RSP *)mid->resp_buf; - struct cifs_credits credits = { .value = 1, .instance = 0 }; + struct cifs_credits credits = { + .value = 1, + .instance = 0, + .rreq_debug_id = wdata->rreq->debug_id, + .rreq_debug_index = wdata->subreq.debug_index, + }; ssize_t result; size_t written; @@ -1657,9 +1687,16 @@ cifs_writev_callback(struct mid_q_entry *mid) break; } + trace_smb3_rw_credits(credits.rreq_debug_id, credits.rreq_debug_index, + wdata->credits.value, + server->credits, server->in_flight, + 0, cifs_trace_rw_credits_write_response_clear); wdata->credits.value = 0; cifs_write_subrequest_terminated(wdata, result, true); release_mid(mid); + trace_smb3_rw_credits(credits.rreq_debug_id, credits.rreq_debug_index, 0, + server->credits, server->in_flight, + credits.value, cifs_trace_rw_credits_write_response_add); add_credits(tcon->ses->server, &credits, 0); } diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index c1c14274930a..5375b0c1dfb9 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -657,6 +657,19 @@ static bool server_unresponsive(struct TCP_Server_Info *server) { /* + * If we're in the process of mounting a share or reconnecting a session + * and the server abruptly shut down (e.g. socket wasn't closed, packet + * had been ACK'ed but no SMB response), don't wait longer than 20s to + * negotiate protocol. + */ + spin_lock(&server->srv_lock); + if (server->tcpStatus == CifsInNegotiate && + time_after(jiffies, server->lstrp + 20 * HZ)) { + spin_unlock(&server->srv_lock); + cifs_reconnect(server, false); + return true; + } + /* * We need to wait 3 echo intervals to make sure we handle such * situations right: * 1s client sends a normal SMB request @@ -667,7 +680,6 @@ server_unresponsive(struct TCP_Server_Info *server) * 65s kernel_recvmsg times out, and we see that we haven't gotten * a response in >60s. */ - spin_lock(&server->srv_lock); if ((server->tcpStatus == CifsGood || server->tcpStatus == CifsNeedNegotiate) && (!server->ops->can_echo || server->ops->can_echo(server)) && diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 2d387485f05b..bcde3f9c89e0 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -49,6 +49,7 @@ static void cifs_prepare_write(struct netfs_io_subrequest *subreq) struct cifs_io_subrequest *wdata = container_of(subreq, struct cifs_io_subrequest, subreq); struct cifs_io_request *req = wdata->req; + struct netfs_io_stream *stream = &req->rreq.io_streams[subreq->stream_nr]; struct TCP_Server_Info *server; struct cifsFileInfo *open_file = req->cfile; size_t wsize = req->rreq.wsize; @@ -73,7 +74,7 @@ retry: } } - rc = server->ops->wait_mtu_credits(server, wsize, &wdata->subreq.max_len, + rc = server->ops->wait_mtu_credits(server, wsize, &stream->sreq_max_len, &wdata->credits); if (rc < 0) { subreq->error = rc; @@ -92,7 +93,7 @@ retry: #ifdef CONFIG_CIFS_SMB_DIRECT if (server->smbd_conn) - subreq->max_nr_segs = server->smbd_conn->max_frmr_depth; + stream->sreq_max_segs = server->smbd_conn->max_frmr_depth; #endif } @@ -111,7 +112,6 @@ static void cifs_issue_write(struct netfs_io_subrequest *subreq) goto fail; } - wdata->actual_len = wdata->subreq.len; rc = adjust_credits(wdata->server, wdata, cifs_trace_rw_credits_issue_write_adjust); if (rc) goto fail; @@ -140,25 +140,22 @@ static void cifs_netfs_invalidate_cache(struct netfs_io_request *wreq) } /* - * Split the read up according to how many credits we can get for each piece. - * It's okay to sleep here if we need to wait for more credit to become - * available. - * - * We also choose the server and allocate an operation ID to be cleaned up - * later. + * Negotiate the size of a read operation on behalf of the netfs library. */ -static bool cifs_clamp_length(struct netfs_io_subrequest *subreq) +static int cifs_prepare_read(struct netfs_io_subrequest *subreq) { struct netfs_io_request *rreq = subreq->rreq; struct cifs_io_subrequest *rdata = container_of(subreq, struct cifs_io_subrequest, subreq); struct cifs_io_request *req = container_of(subreq->rreq, struct cifs_io_request, rreq); struct TCP_Server_Info *server = req->server; struct cifs_sb_info *cifs_sb = CIFS_SB(rreq->inode->i_sb); - size_t rsize; - int rc; + size_t size; + int rc = 0; - rdata->xid = get_xid(); - rdata->have_xid = true; + if (!rdata->have_xid) { + rdata->xid = get_xid(); + rdata->have_xid = true; + } rdata->server = server; if (cifs_sb->ctx->rsize == 0) @@ -166,13 +163,12 @@ static bool cifs_clamp_length(struct netfs_io_subrequest *subreq) server->ops->negotiate_rsize(tlink_tcon(req->cfile->tlink), cifs_sb->ctx); - rc = server->ops->wait_mtu_credits(server, cifs_sb->ctx->rsize, - &rsize, &rdata->credits); - if (rc) { - subreq->error = rc; - return false; - } + &size, &rdata->credits); + if (rc) + return rc; + + rreq->io_streams[0].sreq_max_len = size; rdata->credits.in_flight_check = 1; rdata->credits.rreq_debug_id = rreq->debug_id; @@ -184,14 +180,11 @@ static bool cifs_clamp_length(struct netfs_io_subrequest *subreq) server->credits, server->in_flight, 0, cifs_trace_rw_credits_read_submit); - subreq->len = umin(subreq->len, rsize); - rdata->actual_len = subreq->len; - #ifdef CONFIG_CIFS_SMB_DIRECT if (server->smbd_conn) - subreq->max_nr_segs = server->smbd_conn->max_frmr_depth; + rreq->io_streams[0].sreq_max_segs = server->smbd_conn->max_frmr_depth; #endif - return true; + return 0; } /* @@ -200,59 +193,41 @@ static bool cifs_clamp_length(struct netfs_io_subrequest *subreq) * to only read a portion of that, but as long as we read something, the netfs * helper will call us again so that we can issue another read. */ -static void cifs_req_issue_read(struct netfs_io_subrequest *subreq) +static void cifs_issue_read(struct netfs_io_subrequest *subreq) { struct netfs_io_request *rreq = subreq->rreq; struct cifs_io_subrequest *rdata = container_of(subreq, struct cifs_io_subrequest, subreq); struct cifs_io_request *req = container_of(subreq->rreq, struct cifs_io_request, rreq); struct TCP_Server_Info *server = req->server; - struct cifs_sb_info *cifs_sb = CIFS_SB(rreq->inode->i_sb); int rc = 0; cifs_dbg(FYI, "%s: op=%08x[%x] mapping=%p len=%zu/%zu\n", __func__, rreq->debug_id, subreq->debug_index, rreq->mapping, subreq->transferred, subreq->len); - if (test_bit(NETFS_SREQ_RETRYING, &subreq->flags)) { - /* - * As we're issuing a retry, we need to negotiate some new - * credits otherwise the server may reject the op with - * INVALID_PARAMETER. Note, however, we may get back less - * credit than we need to complete the op, in which case, we - * shorten the op and rely on additional rounds of retry. - */ - size_t rsize = umin(subreq->len - subreq->transferred, - cifs_sb->ctx->rsize); - - rc = server->ops->wait_mtu_credits(server, rsize, &rdata->actual_len, - &rdata->credits); - if (rc) - goto out; - - rdata->credits.in_flight_check = 1; - - trace_smb3_rw_credits(rdata->rreq->debug_id, - rdata->subreq.debug_index, - rdata->credits.value, - server->credits, server->in_flight, 0, - cifs_trace_rw_credits_read_resubmit); - } + rc = adjust_credits(server, rdata, cifs_trace_rw_credits_issue_read_adjust); + if (rc) + goto failed; if (req->cfile->invalidHandle) { do { rc = cifs_reopen_file(req->cfile, true); } while (rc == -EAGAIN); if (rc) - goto out; + goto failed; } if (subreq->rreq->origin != NETFS_DIO_READ) __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); + trace_netfs_sreq(subreq, netfs_sreq_trace_submit); rc = rdata->server->ops->async_readv(rdata); -out: if (rc) - netfs_subreq_terminated(subreq, rc, false); + goto failed; + return; + +failed: + netfs_read_subreq_terminated(subreq, rc, false); } /* @@ -316,12 +291,6 @@ static void cifs_rreq_done(struct netfs_io_request *rreq) inode_set_atime_to_ts(inode, inode_get_mtime(inode)); } -static void cifs_post_modify(struct inode *inode) -{ - /* Indication to update ctime and mtime as close is deferred */ - set_bit(CIFS_INO_MODIFIED_ATTR, &CIFS_I(inode)->flags); -} - static void cifs_free_request(struct netfs_io_request *rreq) { struct cifs_io_request *req = container_of(rreq, struct cifs_io_request, rreq); @@ -369,10 +338,9 @@ const struct netfs_request_ops cifs_req_ops = { .init_request = cifs_init_request, .free_request = cifs_free_request, .free_subrequest = cifs_free_subrequest, - .clamp_length = cifs_clamp_length, - .issue_read = cifs_req_issue_read, + .prepare_read = cifs_prepare_read, + .issue_read = cifs_issue_read, .done = cifs_rreq_done, - .post_modify = cifs_post_modify, .begin_writeback = cifs_begin_writeback, .prepare_write = cifs_prepare_write, .issue_write = cifs_issue_write, @@ -1396,7 +1364,7 @@ int cifs_close(struct inode *inode, struct file *file) dclose = kmalloc(sizeof(struct cifs_deferred_close), GFP_KERNEL); if ((cfile->status_file_deleted == false) && (smb2_can_defer_close(inode, dclose))) { - if (test_and_clear_bit(CIFS_INO_MODIFIED_ATTR, &cinode->flags)) { + if (test_and_clear_bit(NETFS_ICTX_MODIFIED_ATTR, &cinode->netfs.flags)) { inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); } diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index dd0afa23734c..73e2e6c230b7 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -172,6 +172,8 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr, CIFS_I(inode)->time = 0; /* force reval */ return -ESTALE; } + if (inode->i_state & I_NEW) + CIFS_I(inode)->netfs.zero_point = fattr->cf_eof; cifs_revalidate_cache(inode, fattr); diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c index 9f5bc41433c1..11a1c53c64e0 100644 --- a/fs/smb/client/smb2inode.c +++ b/fs/smb/client/smb2inode.c @@ -1106,6 +1106,8 @@ int smb2_rename_path(const unsigned int xid, co, DELETE, SMB2_OP_RENAME, cfile, source_dentry); if (rc == -EINVAL) { cifs_dbg(FYI, "invalid lease key, resending request without lease"); + cifs_get_writable_path(tcon, from_name, + FIND_WR_WITH_DELETE, &cfile); rc = smb2_set_path_attr(xid, tcon, from_name, to_name, cifs_sb, co, DELETE, SMB2_OP_RENAME, cfile, NULL); } @@ -1149,6 +1151,7 @@ smb2_set_path_size(const unsigned int xid, struct cifs_tcon *tcon, cfile, NULL, NULL, dentry); if (rc == -EINVAL) { cifs_dbg(FYI, "invalid lease key, resending request without lease"); + cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile); rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, &oparms, &in_iov, &(int){SMB2_OP_SET_EOF}, 1, diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 4df84ebe8dbe..159a063de6dd 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -13,6 +13,7 @@ #include <linux/sort.h> #include <crypto/aead.h> #include <linux/fiemap.h> +#include <linux/folio_queue.h> #include <uapi/linux/magic.h> #include "cifsfs.h" #include "cifsglob.h" @@ -301,7 +302,8 @@ smb2_adjust_credits(struct TCP_Server_Info *server, unsigned int /*enum smb3_rw_credits_trace*/ trace) { struct cifs_credits *credits = &subreq->credits; - int new_val = DIV_ROUND_UP(subreq->actual_len, SMB2_MAX_BUFFER_SIZE); + int new_val = DIV_ROUND_UP(subreq->subreq.len - subreq->subreq.transferred, + SMB2_MAX_BUFFER_SIZE); int scredits, in_flight; if (!credits->value || credits->value == new_val) @@ -316,7 +318,8 @@ smb2_adjust_credits(struct TCP_Server_Info *server, cifs_trace_rw_credits_no_adjust_up); trace_smb3_too_many_credits(server->CurrentMid, server->conn_id, server->hostname, 0, credits->value - new_val, 0); - cifs_server_dbg(VFS, "request has less credits (%d) than required (%d)", + cifs_server_dbg(VFS, "R=%x[%x] request has less credits (%d) than required (%d)", + subreq->rreq->debug_id, subreq->subreq.debug_index, credits->value, new_val); return -EOPNOTSUPP; @@ -338,8 +341,9 @@ smb2_adjust_credits(struct TCP_Server_Info *server, trace_smb3_reconnect_detected(server->CurrentMid, server->conn_id, server->hostname, scredits, credits->value - new_val, in_flight); - cifs_server_dbg(VFS, "trying to return %d credits to old session\n", - credits->value - new_val); + cifs_server_dbg(VFS, "R=%x[%x] trying to return %d credits to old session\n", + subreq->rreq->debug_id, subreq->subreq.debug_index, + credits->value - new_val); return -EAGAIN; } @@ -4390,30 +4394,86 @@ crypt_message(struct TCP_Server_Info *server, int num_rqst, } /* - * Clear a read buffer, discarding the folios which have XA_MARK_0 set. + * Clear a read buffer, discarding the folios which have the 1st mark set. */ -static void cifs_clear_xarray_buffer(struct xarray *buffer) +static void cifs_clear_folioq_buffer(struct folio_queue *buffer) { + struct folio_queue *folioq; + + while ((folioq = buffer)) { + for (int s = 0; s < folioq_count(folioq); s++) + if (folioq_is_marked(folioq, s)) + folio_put(folioq_folio(folioq, s)); + buffer = folioq->next; + kfree(folioq); + } +} + +/* + * Allocate buffer space into a folio queue. + */ +static struct folio_queue *cifs_alloc_folioq_buffer(ssize_t size) +{ + struct folio_queue *buffer = NULL, *tail = NULL, *p; struct folio *folio; + unsigned int slot; + + do { + if (!tail || folioq_full(tail)) { + p = kmalloc(sizeof(*p), GFP_NOFS); + if (!p) + goto nomem; + folioq_init(p); + if (tail) { + tail->next = p; + p->prev = tail; + } else { + buffer = p; + } + tail = p; + } + + folio = folio_alloc(GFP_KERNEL|__GFP_HIGHMEM, 0); + if (!folio) + goto nomem; + + slot = folioq_append_mark(tail, folio); + size -= folioq_folio_size(tail, slot); + } while (size > 0); + + return buffer; + +nomem: + cifs_clear_folioq_buffer(buffer); + return NULL; +} + +/* + * Copy data from an iterator to the folios in a folio queue buffer. + */ +static bool cifs_copy_iter_to_folioq(struct iov_iter *iter, size_t size, + struct folio_queue *buffer) +{ + for (; buffer; buffer = buffer->next) { + for (int s = 0; s < folioq_count(buffer); s++) { + struct folio *folio = folioq_folio(buffer, s); + size_t part = folioq_folio_size(buffer, s); - XA_STATE(xas, buffer, 0); + part = umin(part, size); - rcu_read_lock(); - xas_for_each_marked(&xas, folio, ULONG_MAX, XA_MARK_0) { - folio_put(folio); + if (copy_folio_from_iter(folio, 0, part, iter) != part) + return false; + size -= part; + } } - rcu_read_unlock(); - xa_destroy(buffer); + return true; } void smb3_free_compound_rqst(int num_rqst, struct smb_rqst *rqst) { - int i; - - for (i = 0; i < num_rqst; i++) - if (!xa_empty(&rqst[i].rq_buffer)) - cifs_clear_xarray_buffer(&rqst[i].rq_buffer); + for (int i = 0; i < num_rqst; i++) + cifs_clear_folioq_buffer(rqst[i].rq_buffer); } /* @@ -4434,52 +4494,32 @@ smb3_init_transform_rq(struct TCP_Server_Info *server, int num_rqst, struct smb_rqst *new_rq, struct smb_rqst *old_rq) { struct smb2_transform_hdr *tr_hdr = new_rq[0].rq_iov[0].iov_base; - struct page *page; unsigned int orig_len = 0; - int i, j; int rc = -ENOMEM; - for (i = 1; i < num_rqst; i++) { + for (int i = 1; i < num_rqst; i++) { struct smb_rqst *old = &old_rq[i - 1]; struct smb_rqst *new = &new_rq[i]; - struct xarray *buffer = &new->rq_buffer; - size_t size = iov_iter_count(&old->rq_iter), seg, copied = 0; + struct folio_queue *buffer; + size_t size = iov_iter_count(&old->rq_iter); orig_len += smb_rqst_len(server, old); new->rq_iov = old->rq_iov; new->rq_nvec = old->rq_nvec; - xa_init(buffer); - if (size > 0) { - unsigned int npages = DIV_ROUND_UP(size, PAGE_SIZE); - - for (j = 0; j < npages; j++) { - void *o; - - rc = -ENOMEM; - page = alloc_page(GFP_KERNEL|__GFP_HIGHMEM); - if (!page) - goto err_free; - page->index = j; - o = xa_store(buffer, j, page, GFP_KERNEL); - if (xa_is_err(o)) { - rc = xa_err(o); - put_page(page); - goto err_free; - } + buffer = cifs_alloc_folioq_buffer(size); + if (!buffer) + goto err_free; - xa_set_mark(buffer, j, XA_MARK_0); + new->rq_buffer = buffer; + iov_iter_folio_queue(&new->rq_iter, ITER_SOURCE, + buffer, 0, 0, size); - seg = min_t(size_t, size - copied, PAGE_SIZE); - if (copy_page_from_iter(page, 0, seg, &old->rq_iter) != seg) { - rc = -EFAULT; - goto err_free; - } - copied += seg; + if (!cifs_copy_iter_to_folioq(&old->rq_iter, size, buffer)) { + rc = -EIO; + goto err_free; } - iov_iter_xarray(&new->rq_iter, ITER_SOURCE, - buffer, 0, size); } } @@ -4543,22 +4583,23 @@ decrypt_raw_data(struct TCP_Server_Info *server, char *buf, } static int -cifs_copy_pages_to_iter(struct xarray *pages, unsigned int data_size, - unsigned int skip, struct iov_iter *iter) +cifs_copy_folioq_to_iter(struct folio_queue *folioq, size_t data_size, + size_t skip, struct iov_iter *iter) { - struct page *page; - unsigned long index; - - xa_for_each(pages, index, page) { - size_t n, len = min_t(unsigned int, PAGE_SIZE - skip, data_size); - - n = copy_page_to_iter(page, skip, len, iter); - if (n != len) { - cifs_dbg(VFS, "%s: something went wrong\n", __func__); - return -EIO; + for (; folioq; folioq = folioq->next) { + for (int s = 0; s < folioq_count(folioq); s++) { + struct folio *folio = folioq_folio(folioq, s); + size_t fsize = folio_size(folio); + size_t n, len = umin(fsize - skip, data_size); + + n = copy_folio_to_iter(folio, skip, len, iter); + if (n != len) { + cifs_dbg(VFS, "%s: something went wrong\n", __func__); + return -EIO; + } + data_size -= n; + skip = 0; } - data_size -= n; - skip = 0; } return 0; @@ -4566,8 +4607,8 @@ cifs_copy_pages_to_iter(struct xarray *pages, unsigned int data_size, static int handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, - char *buf, unsigned int buf_len, struct xarray *pages, - unsigned int pages_len, bool is_offloaded) + char *buf, unsigned int buf_len, struct folio_queue *buffer, + unsigned int buffer_len, bool is_offloaded) { unsigned int data_offset; unsigned int data_len; @@ -4664,7 +4705,7 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, return 0; } - if (data_len > pages_len - pad_len) { + if (data_len > buffer_len - pad_len) { /* data_len is corrupt -- discard frame */ rdata->result = -EIO; if (is_offloaded) @@ -4675,8 +4716,8 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, } /* Copy the data to the output I/O iterator. */ - rdata->result = cifs_copy_pages_to_iter(pages, pages_len, - cur_off, &rdata->subreq.io_iter); + rdata->result = cifs_copy_folioq_to_iter(buffer, buffer_len, + cur_off, &rdata->subreq.io_iter); if (rdata->result != 0) { if (is_offloaded) mid->mid_state = MID_RESPONSE_MALFORMED; @@ -4684,12 +4725,11 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, dequeue_mid(mid, rdata->result); return 0; } - rdata->got_bytes = pages_len; + rdata->got_bytes = buffer_len; } else if (buf_len >= data_offset + data_len) { /* read response payload is in buf */ - WARN_ONCE(pages && !xa_empty(pages), - "read data can be either in buf or in pages"); + WARN_ONCE(buffer, "read data can be either in buf or in buffer"); length = copy_to_iter(buf + data_offset, data_len, &rdata->subreq.io_iter); if (length < 0) return length; @@ -4715,7 +4755,7 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, struct smb2_decrypt_work { struct work_struct decrypt; struct TCP_Server_Info *server; - struct xarray buffer; + struct folio_queue *buffer; char *buf; unsigned int len; }; @@ -4729,7 +4769,7 @@ static void smb2_decrypt_offload(struct work_struct *work) struct mid_q_entry *mid; struct iov_iter iter; - iov_iter_xarray(&iter, ITER_DEST, &dw->buffer, 0, dw->len); + iov_iter_folio_queue(&iter, ITER_DEST, dw->buffer, 0, 0, dw->len); rc = decrypt_raw_data(dw->server, dw->buf, dw->server->vals->read_rsp_size, &iter, true); if (rc) { @@ -4745,7 +4785,7 @@ static void smb2_decrypt_offload(struct work_struct *work) mid->decrypted = true; rc = handle_read_data(dw->server, mid, dw->buf, dw->server->vals->read_rsp_size, - &dw->buffer, dw->len, + dw->buffer, dw->len, true); if (rc >= 0) { #ifdef CONFIG_CIFS_STATS2 @@ -4778,7 +4818,7 @@ static void smb2_decrypt_offload(struct work_struct *work) } free_pages: - cifs_clear_xarray_buffer(&dw->buffer); + cifs_clear_folioq_buffer(dw->buffer); cifs_small_buf_release(dw->buf); kfree(dw); } @@ -4788,20 +4828,17 @@ static int receive_encrypted_read(struct TCP_Server_Info *server, struct mid_q_entry **mid, int *num_mids) { - struct page *page; char *buf = server->smallbuf; struct smb2_transform_hdr *tr_hdr = (struct smb2_transform_hdr *)buf; struct iov_iter iter; - unsigned int len, npages; + unsigned int len; unsigned int buflen = server->pdu_size; int rc; - int i = 0; struct smb2_decrypt_work *dw; dw = kzalloc(sizeof(struct smb2_decrypt_work), GFP_KERNEL); if (!dw) return -ENOMEM; - xa_init(&dw->buffer); INIT_WORK(&dw->decrypt, smb2_decrypt_offload); dw->server = server; @@ -4817,26 +4854,14 @@ receive_encrypted_read(struct TCP_Server_Info *server, struct mid_q_entry **mid, len = le32_to_cpu(tr_hdr->OriginalMessageSize) - server->vals->read_rsp_size; dw->len = len; - npages = DIV_ROUND_UP(len, PAGE_SIZE); + len = round_up(dw->len, PAGE_SIZE); rc = -ENOMEM; - for (; i < npages; i++) { - void *old; - - page = alloc_page(GFP_KERNEL|__GFP_HIGHMEM); - if (!page) - goto discard_data; - page->index = i; - old = xa_store(&dw->buffer, i, page, GFP_KERNEL); - if (xa_is_err(old)) { - rc = xa_err(old); - put_page(page); - goto discard_data; - } - xa_set_mark(&dw->buffer, i, XA_MARK_0); - } + dw->buffer = cifs_alloc_folioq_buffer(len); + if (!dw->buffer) + goto discard_data; - iov_iter_xarray(&iter, ITER_DEST, &dw->buffer, 0, npages * PAGE_SIZE); + iov_iter_folio_queue(&iter, ITER_DEST, dw->buffer, 0, 0, len); /* Read the data into the buffer and clear excess bufferage. */ rc = cifs_read_iter_from_socket(server, &iter, dw->len); @@ -4844,9 +4869,9 @@ receive_encrypted_read(struct TCP_Server_Info *server, struct mid_q_entry **mid, goto discard_data; server->total_read += rc; - if (rc < npages * PAGE_SIZE) - iov_iter_zero(npages * PAGE_SIZE - rc, &iter); - iov_iter_revert(&iter, npages * PAGE_SIZE); + if (rc < len) + iov_iter_zero(len - rc, &iter); + iov_iter_revert(&iter, len); iov_iter_truncate(&iter, dw->len); rc = cifs_discard_remaining_data(server); @@ -4881,7 +4906,7 @@ receive_encrypted_read(struct TCP_Server_Info *server, struct mid_q_entry **mid, (*mid)->decrypted = true; rc = handle_read_data(server, *mid, buf, server->vals->read_rsp_size, - &dw->buffer, dw->len, false); + dw->buffer, dw->len, false); if (rc >= 0) { if (server->ops->is_network_name_deleted) { server->ops->is_network_name_deleted(buf, @@ -4891,7 +4916,7 @@ receive_encrypted_read(struct TCP_Server_Info *server, struct mid_q_entry **mid, } free_pages: - cifs_clear_xarray_buffer(&dw->buffer); + cifs_clear_folioq_buffer(dw->buffer); free_dw: kfree(dw); return rc; diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 88dc49d67037..95377bb91950 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -4498,9 +4498,7 @@ static void smb2_readv_worker(struct work_struct *work) struct cifs_io_subrequest *rdata = container_of(work, struct cifs_io_subrequest, subreq.work); - netfs_subreq_terminated(&rdata->subreq, - (rdata->result == 0 || rdata->result == -EAGAIN) ? - rdata->got_bytes : rdata->result, true); + netfs_read_subreq_terminated(&rdata->subreq, rdata->result, false); } static void @@ -4532,7 +4530,7 @@ smb2_readv_callback(struct mid_q_entry *mid) cifs_dbg(FYI, "%s: mid=%llu state=%d result=%d bytes=%zu/%zu\n", __func__, mid->mid, mid->mid_state, rdata->result, - rdata->actual_len, rdata->subreq.len - rdata->subreq.transferred); + rdata->got_bytes, rdata->subreq.len - rdata->subreq.transferred); switch (mid->mid_state) { case MID_RESPONSE_RECEIVED: @@ -4554,6 +4552,7 @@ smb2_readv_callback(struct mid_q_entry *mid) break; case MID_REQUEST_SUBMITTED: case MID_RETRY_NEEDED: + __set_bit(NETFS_SREQ_NEED_RETRY, &rdata->subreq.flags); rdata->result = -EAGAIN; if (server->sign && rdata->got_bytes) /* reset bytes number since we can not check a sign */ @@ -4588,7 +4587,7 @@ smb2_readv_callback(struct mid_q_entry *mid) rdata->req->cfile->fid.persistent_fid, tcon->tid, tcon->ses->Suid, rdata->subreq.start + rdata->subreq.transferred, - rdata->actual_len, + rdata->subreq.len - rdata->subreq.transferred, rdata->result); } else trace_smb3_read_done(rdata->rreq->debug_id, @@ -4603,9 +4602,9 @@ smb2_readv_callback(struct mid_q_entry *mid) __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); rdata->result = 0; } else { - if (rdata->got_bytes < rdata->actual_len && - rdata->subreq.start + rdata->subreq.transferred + rdata->got_bytes == - ictx->remote_i_size) { + size_t trans = rdata->subreq.transferred + rdata->got_bytes; + if (trans < rdata->subreq.len && + rdata->subreq.start + trans == ictx->remote_i_size) { __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); rdata->result = 0; } @@ -4614,6 +4613,10 @@ smb2_readv_callback(struct mid_q_entry *mid) server->credits, server->in_flight, 0, cifs_trace_rw_credits_read_response_clear); rdata->credits.value = 0; + rdata->subreq.transferred += rdata->got_bytes; + if (rdata->subreq.start + rdata->subreq.transferred >= rdata->subreq.rreq->i_size) + __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); + trace_netfs_sreq(&rdata->subreq, netfs_sreq_trace_io_progress); INIT_WORK(&rdata->subreq.work, smb2_readv_worker); queue_work(cifsiod_wq, &rdata->subreq.work); release_mid(mid); @@ -4648,7 +4651,7 @@ smb2_async_readv(struct cifs_io_subrequest *rdata) io_parms.tcon = tlink_tcon(rdata->req->cfile->tlink); io_parms.server = server = rdata->server; io_parms.offset = subreq->start + subreq->transferred; - io_parms.length = rdata->actual_len; + io_parms.length = subreq->len - subreq->transferred; io_parms.persistent_fid = rdata->req->cfile->fid.persistent_fid; io_parms.volatile_fid = rdata->req->cfile->fid.volatile_fid; io_parms.pid = rdata->req->pid; @@ -4669,7 +4672,7 @@ smb2_async_readv(struct cifs_io_subrequest *rdata) shdr = (struct smb2_hdr *)buf; if (rdata->credits.value > 0) { - shdr->CreditCharge = cpu_to_le16(DIV_ROUND_UP(rdata->actual_len, + shdr->CreditCharge = cpu_to_le16(DIV_ROUND_UP(io_parms.length, SMB2_MAX_BUFFER_SIZE)); credit_request = le16_to_cpu(shdr->CreditCharge) + 8; if (server->credits >= server->max_credits) @@ -4697,7 +4700,8 @@ smb2_async_readv(struct cifs_io_subrequest *rdata) rdata->xid, io_parms.persistent_fid, io_parms.tcon->tid, io_parms.tcon->ses->Suid, - io_parms.offset, rdata->actual_len, rc); + io_parms.offset, + subreq->len - subreq->transferred, rc); } async_readv_out: @@ -4880,6 +4884,7 @@ smb2_writev_callback(struct mid_q_entry *mid) server->credits, server->in_flight, 0, cifs_trace_rw_credits_write_response_clear); wdata->credits.value = 0; + trace_netfs_sreq(&wdata->subreq, netfs_sreq_trace_io_progress); cifs_write_subrequest_terminated(wdata, result ?: written, true); release_mid(mid); trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, 0, diff --git a/fs/smb/client/smbdirect.c b/fs/smb/client/smbdirect.c index 7bcc379014ca..80262a36030f 100644 --- a/fs/smb/client/smbdirect.c +++ b/fs/smb/client/smbdirect.c @@ -6,6 +6,7 @@ */ #include <linux/module.h> #include <linux/highmem.h> +#include <linux/folio_queue.h> #include "smbdirect.h" #include "cifs_debug.h" #include "cifsproto.h" @@ -2463,6 +2464,8 @@ static ssize_t smb_extract_bvec_to_rdma(struct iov_iter *iter, start = 0; } + if (ret > 0) + iov_iter_advance(iter, ret); return ret; } @@ -2519,50 +2522,65 @@ static ssize_t smb_extract_kvec_to_rdma(struct iov_iter *iter, start = 0; } + if (ret > 0) + iov_iter_advance(iter, ret); return ret; } /* - * Extract folio fragments from an XARRAY-class iterator and add them to an - * RDMA list. The folios are not pinned. + * Extract folio fragments from a FOLIOQ-class iterator and add them to an RDMA + * list. The folios are not pinned. */ -static ssize_t smb_extract_xarray_to_rdma(struct iov_iter *iter, +static ssize_t smb_extract_folioq_to_rdma(struct iov_iter *iter, struct smb_extract_to_rdma *rdma, ssize_t maxsize) { - struct xarray *xa = iter->xarray; - struct folio *folio; - loff_t start = iter->xarray_start + iter->iov_offset; - pgoff_t index = start / PAGE_SIZE; + const struct folio_queue *folioq = iter->folioq; + unsigned int slot = iter->folioq_slot; ssize_t ret = 0; - size_t off, len; - XA_STATE(xas, xa, index); + size_t offset = iter->iov_offset; - rcu_read_lock(); + BUG_ON(!folioq); - xas_for_each(&xas, folio, ULONG_MAX) { - if (xas_retry(&xas, folio)) - continue; - if (WARN_ON(xa_is_value(folio))) - break; - if (WARN_ON(folio_test_hugetlb(folio))) - break; + if (slot >= folioq_nr_slots(folioq)) { + folioq = folioq->next; + if (WARN_ON_ONCE(!folioq)) + return -EIO; + slot = 0; + } - off = offset_in_folio(folio, start); - len = min_t(size_t, maxsize, folio_size(folio) - off); + do { + struct folio *folio = folioq_folio(folioq, slot); + size_t fsize = folioq_folio_size(folioq, slot); - if (!smb_set_sge(rdma, folio_page(folio, 0), off, len)) { - rcu_read_unlock(); - return -EIO; + if (offset < fsize) { + size_t part = umin(maxsize - ret, fsize - offset); + + if (!smb_set_sge(rdma, folio_page(folio, 0), offset, part)) + return -EIO; + + offset += part; + ret += part; } - maxsize -= len; - ret += len; - if (rdma->nr_sge >= rdma->max_sge || maxsize <= 0) - break; - } + if (offset >= fsize) { + offset = 0; + slot++; + if (slot >= folioq_nr_slots(folioq)) { + if (!folioq->next) { + WARN_ON_ONCE(ret < iter->count); + break; + } + folioq = folioq->next; + slot = 0; + } + } + } while (rdma->nr_sge < rdma->max_sge || maxsize > 0); - rcu_read_unlock(); + iter->folioq = folioq; + iter->folioq_slot = slot; + iter->iov_offset = offset; + iter->count -= ret; return ret; } @@ -2590,17 +2608,15 @@ static ssize_t smb_extract_iter_to_rdma(struct iov_iter *iter, size_t len, case ITER_KVEC: ret = smb_extract_kvec_to_rdma(iter, rdma, len); break; - case ITER_XARRAY: - ret = smb_extract_xarray_to_rdma(iter, rdma, len); + case ITER_FOLIOQ: + ret = smb_extract_folioq_to_rdma(iter, rdma, len); break; default: WARN_ON_ONCE(1); return -EIO; } - if (ret > 0) { - iov_iter_advance(iter, ret); - } else if (ret < 0) { + if (ret < 0) { while (rdma->nr_sge > before) { struct ib_sge *sge = &rdma->sge[rdma->nr_sge--]; diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 20846a4d3031..8bdc59251418 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -1690,6 +1690,8 @@ int smb2_sess_setup(struct ksmbd_work *work) rc = ksmbd_session_register(conn, sess); if (rc) goto out_err; + + conn->binding = false; } else if (conn->dialect >= SMB30_PROT_ID && (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB3_MULTICHANNEL) && req->Flags & SMB2_SESSION_REQ_FLAG_BINDING) { @@ -1768,6 +1770,8 @@ int smb2_sess_setup(struct ksmbd_work *work) sess = NULL; goto out_err; } + + conn->binding = false; } work->sess = sess; diff --git a/fs/smb/server/transport_tcp.c b/fs/smb/server/transport_tcp.c index a84788396daa..aaed9e293b2e 100644 --- a/fs/smb/server/transport_tcp.c +++ b/fs/smb/server/transport_tcp.c @@ -624,8 +624,10 @@ int ksmbd_tcp_set_interfaces(char *ifc_list, int ifc_list_sz) for_each_netdev(&init_net, netdev) { if (netif_is_bridge_port(netdev)) continue; - if (!alloc_iface(kstrdup(netdev->name, GFP_KERNEL))) + if (!alloc_iface(kstrdup(netdev->name, GFP_KERNEL))) { + rtnl_unlock(); return -ENOMEM; + } } rtnl_unlock(); bind_additional_ifaces = 1; diff --git a/fs/smb/server/xattr.h b/fs/smb/server/xattr.h index 16499ca5c82d..fa3e27d6971b 100644 --- a/fs/smb/server/xattr.h +++ b/fs/smb/server/xattr.h @@ -76,7 +76,7 @@ struct xattr_acl_entry { struct xattr_smb_acl { int count; int next; - struct xattr_acl_entry entries[]; + struct xattr_acl_entry entries[] __counted_by(count); }; /* 64bytes hash in xattr_ntacl is computed with sha256 */ diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c index a8c1e7f9a609..21aaa96856c1 100644 --- a/fs/squashfs/file.c +++ b/fs/squashfs/file.c @@ -494,39 +494,73 @@ out: } static int squashfs_readahead_fragment(struct page **page, - unsigned int pages, unsigned int expected) + unsigned int pages, unsigned int expected, loff_t start) { struct inode *inode = page[0]->mapping->host; struct squashfs_cache_entry *buffer = squashfs_get_fragment(inode->i_sb, squashfs_i(inode)->fragment_block, squashfs_i(inode)->fragment_size); struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; - unsigned int n, mask = (1 << (msblk->block_log - PAGE_SHIFT)) - 1; - int error = buffer->error; + int i, bytes, copied; + struct squashfs_page_actor *actor; + unsigned int offset; + void *addr; + struct page *last_page; + + if (buffer->error) + goto out; - if (error) + actor = squashfs_page_actor_init_special(msblk, page, pages, + expected, start); + if (!actor) goto out; - expected += squashfs_i(inode)->fragment_offset; + squashfs_actor_nobuff(actor); + addr = squashfs_first_page(actor); + + for (copied = offset = 0; offset < expected; offset += PAGE_SIZE) { + int avail = min_t(int, expected - offset, PAGE_SIZE); + + if (!IS_ERR(addr)) { + bytes = squashfs_copy_data(addr, buffer, offset + + squashfs_i(inode)->fragment_offset, avail); + + if (bytes != avail) + goto failed; + } + + copied += avail; + addr = squashfs_next_page(actor); + } - for (n = 0; n < pages; n++) { - unsigned int base = (page[n]->index & mask) << PAGE_SHIFT; - unsigned int offset = base + squashfs_i(inode)->fragment_offset; + last_page = squashfs_page_actor_free(actor); - if (expected > offset) { - unsigned int avail = min_t(unsigned int, expected - - offset, PAGE_SIZE); + if (copied == expected && !IS_ERR(last_page)) { + /* Last page (if present) may have trailing bytes not filled */ + bytes = copied % PAGE_SIZE; + if (bytes && last_page) + memzero_page(last_page, bytes, PAGE_SIZE - bytes); - squashfs_fill_page(page[n], buffer, offset, avail); + for (i = 0; i < pages; i++) { + flush_dcache_page(page[i]); + SetPageUptodate(page[i]); } + } - unlock_page(page[n]); - put_page(page[n]); + for (i = 0; i < pages; i++) { + unlock_page(page[i]); + put_page(page[i]); } + squashfs_cache_put(buffer); + return 0; + +failed: + squashfs_page_actor_free(actor); + out: squashfs_cache_put(buffer); - return error; + return 1; } static void squashfs_readahead(struct readahead_control *ractl) @@ -551,7 +585,6 @@ static void squashfs_readahead(struct readahead_control *ractl) return; for (;;) { - pgoff_t index; int res, bsize; u64 block = 0; unsigned int expected; @@ -570,26 +603,21 @@ static void squashfs_readahead(struct readahead_control *ractl) if (readahead_pos(ractl) >= i_size_read(inode)) goto skip_pages; - index = pages[0]->index >> shift; - - if ((pages[nr_pages - 1]->index >> shift) != index) - goto skip_pages; - - if (index == file_end && squashfs_i(inode)->fragment_block != - SQUASHFS_INVALID_BLK) { + if (start >> msblk->block_log == file_end && + squashfs_i(inode)->fragment_block != SQUASHFS_INVALID_BLK) { res = squashfs_readahead_fragment(pages, nr_pages, - expected); + expected, start); if (res) goto skip_pages; continue; } - bsize = read_blocklist(inode, index, &block); + bsize = read_blocklist(inode, start >> msblk->block_log, &block); if (bsize == 0) goto skip_pages; actor = squashfs_page_actor_init_special(msblk, pages, nr_pages, - expected); + expected, start); if (!actor) goto skip_pages; @@ -597,12 +625,12 @@ static void squashfs_readahead(struct readahead_control *ractl) last_page = squashfs_page_actor_free(actor); - if (res == expected) { + if (res == expected && !IS_ERR(last_page)) { int bytes; /* Last page (if present) may have trailing bytes not filled */ bytes = res % PAGE_SIZE; - if (index == file_end && bytes && last_page) + if (start >> msblk->block_log == file_end && bytes && last_page) memzero_page(last_page, bytes, PAGE_SIZE - bytes); @@ -616,6 +644,8 @@ static void squashfs_readahead(struct readahead_control *ractl) unlock_page(pages[i]); put_page(pages[i]); } + + start += readahead_batch_length(ractl); } kfree(pages); diff --git a/fs/squashfs/file_direct.c b/fs/squashfs/file_direct.c index 2a689ce71de9..22251743fadf 100644 --- a/fs/squashfs/file_direct.c +++ b/fs/squashfs/file_direct.c @@ -23,15 +23,15 @@ int squashfs_readpage_block(struct page *target_page, u64 block, int bsize, int expected) { + struct folio *folio = page_folio(target_page); struct inode *inode = target_page->mapping->host; struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; - loff_t file_end = (i_size_read(inode) - 1) >> PAGE_SHIFT; int mask = (1 << (msblk->block_log - PAGE_SHIFT)) - 1; - loff_t start_index = target_page->index & ~mask; + loff_t start_index = folio->index & ~mask; loff_t end_index = start_index | mask; int i, n, pages, bytes, res = -ENOMEM; - struct page **page; + struct page **page, *last_page; struct squashfs_page_actor *actor; void *pageaddr; @@ -46,7 +46,7 @@ int squashfs_readpage_block(struct page *target_page, u64 block, int bsize, /* Try to grab all the pages covered by the Squashfs block */ for (i = 0, n = start_index; n <= end_index; n++) { - page[i] = (n == target_page->index) ? target_page : + page[i] = (n == folio->index) ? target_page : grab_cache_page_nowait(target_page->mapping, n); if (page[i] == NULL) @@ -67,27 +67,28 @@ int squashfs_readpage_block(struct page *target_page, u64 block, int bsize, * Create a "page actor" which will kmap and kunmap the * page cache pages appropriately within the decompressor */ - actor = squashfs_page_actor_init_special(msblk, page, pages, expected); + actor = squashfs_page_actor_init_special(msblk, page, pages, expected, + start_index << PAGE_SHIFT); if (actor == NULL) goto out; /* Decompress directly into the page cache buffers */ res = squashfs_read_data(inode->i_sb, block, bsize, NULL, actor); - squashfs_page_actor_free(actor); + last_page = squashfs_page_actor_free(actor); if (res < 0) goto mark_errored; - if (res != expected) { + if (res != expected || IS_ERR(last_page)) { res = -EIO; goto mark_errored; } /* Last page (if present) may have trailing bytes not filled */ bytes = res % PAGE_SIZE; - if (page[pages - 1]->index == end_index && bytes) { - pageaddr = kmap_local_page(page[pages - 1]); + if (end_index == file_end && last_page && bytes) { + pageaddr = kmap_local_page(last_page); memset(pageaddr + bytes, 0, PAGE_SIZE - bytes); kunmap_local(pageaddr); } diff --git a/fs/squashfs/page_actor.c b/fs/squashfs/page_actor.c index 81af6c4ca115..2b3e807d4dea 100644 --- a/fs/squashfs/page_actor.c +++ b/fs/squashfs/page_actor.c @@ -60,6 +60,11 @@ struct squashfs_page_actor *squashfs_page_actor_init(void **buffer, } /* Implementation of page_actor for decompressing directly into page cache. */ +static loff_t page_next_index(struct squashfs_page_actor *actor) +{ + return page_folio(actor->page[actor->next_page])->index; +} + static void *handle_next_page(struct squashfs_page_actor *actor) { int max_pages = (actor->length + PAGE_SIZE - 1) >> PAGE_SHIFT; @@ -68,7 +73,7 @@ static void *handle_next_page(struct squashfs_page_actor *actor) return NULL; if ((actor->next_page == actor->pages) || - (actor->next_index != actor->page[actor->next_page]->index)) { + (actor->next_index != page_next_index(actor))) { actor->next_index++; actor->returned_pages++; actor->last_page = NULL; @@ -103,7 +108,7 @@ static void direct_finish_page(struct squashfs_page_actor *actor) } struct squashfs_page_actor *squashfs_page_actor_init_special(struct squashfs_sb_info *msblk, - struct page **page, int pages, int length) + struct page **page, int pages, int length, loff_t start_index) { struct squashfs_page_actor *actor = kmalloc(sizeof(*actor), GFP_KERNEL); @@ -125,7 +130,7 @@ struct squashfs_page_actor *squashfs_page_actor_init_special(struct squashfs_sb_ actor->pages = pages; actor->next_page = 0; actor->returned_pages = 0; - actor->next_index = page[0]->index & ~((1 << (msblk->block_log - PAGE_SHIFT)) - 1); + actor->next_index = start_index >> PAGE_SHIFT; actor->pageaddr = NULL; actor->last_page = NULL; actor->alloc_buffer = msblk->decompressor->alloc_buffer; diff --git a/fs/squashfs/page_actor.h b/fs/squashfs/page_actor.h index 97d4983559b1..ffe25eb77c32 100644 --- a/fs/squashfs/page_actor.h +++ b/fs/squashfs/page_actor.h @@ -29,13 +29,15 @@ extern struct squashfs_page_actor *squashfs_page_actor_init(void **buffer, int pages, int length); extern struct squashfs_page_actor *squashfs_page_actor_init_special( struct squashfs_sb_info *msblk, - struct page **page, int pages, int length); + struct page **page, int pages, int length, + loff_t start_index); static inline struct page *squashfs_page_actor_free(struct squashfs_page_actor *actor) { - struct page *last_page = actor->last_page; + struct page *last_page = actor->next_page == actor->pages ? actor->last_page : ERR_PTR(-EIO); kfree(actor->tmp_buffer); kfree(actor); + return last_page; } static inline void *squashfs_first_page(struct squashfs_page_actor *actor) diff --git a/fs/super.c b/fs/super.c index b7913b55debc..1db230432960 100644 --- a/fs/super.c +++ b/fs/super.c @@ -621,7 +621,7 @@ void generic_shutdown_super(struct super_block *sb) sync_filesystem(sb); sb->s_flags &= ~SB_ACTIVE; - cgroup_writeback_umount(); + cgroup_writeback_umount(sb); /* Evict all inodes with zero refcount. */ evict_inodes(sb); @@ -1905,7 +1905,7 @@ static void lockdep_sb_freeze_release(struct super_block *sb) int level; for (level = SB_FREEZE_LEVELS - 1; level >= 0; level--) - percpu_rwsem_release(sb->s_writers.rw_sem + level, 0, _THIS_IP_); + percpu_rwsem_release(sb->s_writers.rw_sem + level, _THIS_IP_); } /* diff --git a/fs/sysv/dir.c b/fs/sysv/dir.c index 2e126d72d619..639307e2ff8c 100644 --- a/fs/sysv/dir.c +++ b/fs/sysv/dir.c @@ -28,17 +28,17 @@ const struct file_operations sysv_dir_operations = { .fsync = generic_file_fsync, }; -static void dir_commit_chunk(struct page *page, loff_t pos, unsigned len) +static void dir_commit_chunk(struct folio *folio, loff_t pos, unsigned len) { - struct address_space *mapping = page->mapping; + struct address_space *mapping = folio->mapping; struct inode *dir = mapping->host; - block_write_end(NULL, mapping, pos, len, len, page, NULL); + block_write_end(NULL, mapping, pos, len, len, folio, NULL); if (pos+len > dir->i_size) { i_size_write(dir, pos+len); mark_inode_dirty(dir); } - unlock_page(page); + folio_unlock(folio); } static int sysv_handle_dirsync(struct inode *dir) @@ -52,20 +52,21 @@ static int sysv_handle_dirsync(struct inode *dir) } /* - * Calls to dir_get_page()/unmap_and_put_page() must be nested according to the + * Calls to dir_get_folio()/folio_release_kmap() must be nested according to the * rules documented in mm/highmem.rst. * - * NOTE: sysv_find_entry() and sysv_dotdot() act as calls to dir_get_page() + * NOTE: sysv_find_entry() and sysv_dotdot() act as calls to dir_get_folio() * and must be treated accordingly for nesting purposes. */ -static void *dir_get_page(struct inode *dir, unsigned long n, struct page **p) +static void *dir_get_folio(struct inode *dir, unsigned long n, + struct folio **foliop) { - struct address_space *mapping = dir->i_mapping; - struct page *page = read_mapping_page(mapping, n, NULL); - if (IS_ERR(page)) - return ERR_CAST(page); - *p = page; - return kmap_local_page(page); + struct folio *folio = read_mapping_folio(dir->i_mapping, n, NULL); + + if (IS_ERR(folio)) + return ERR_CAST(folio); + *foliop = folio; + return kmap_local_folio(folio, 0); } static int sysv_readdir(struct file *file, struct dir_context *ctx) @@ -87,9 +88,9 @@ static int sysv_readdir(struct file *file, struct dir_context *ctx) for ( ; n < npages; n++, offset = 0) { char *kaddr, *limit; struct sysv_dir_entry *de; - struct page *page; + struct folio *folio; - kaddr = dir_get_page(inode, n, &page); + kaddr = dir_get_folio(inode, n, &folio); if (IS_ERR(kaddr)) continue; de = (struct sysv_dir_entry *)(kaddr+offset); @@ -103,11 +104,11 @@ static int sysv_readdir(struct file *file, struct dir_context *ctx) if (!dir_emit(ctx, name, strnlen(name,SYSV_NAMELEN), fs16_to_cpu(SYSV_SB(sb), de->inode), DT_UNKNOWN)) { - unmap_and_put_page(page, kaddr); + folio_release_kmap(folio, kaddr); return 0; } } - unmap_and_put_page(page, kaddr); + folio_release_kmap(folio, kaddr); } return 0; } @@ -126,39 +127,35 @@ static inline int namecompare(int len, int maxlen, /* * sysv_find_entry() * - * finds an entry in the specified directory with the wanted name. It - * returns the cache buffer in which the entry was found, and the entry - * itself (as a parameter - res_dir). It does NOT read the inode of the + * finds an entry in the specified directory with the wanted name. + * It does NOT read the inode of the * entry - you'll have to do that yourself if you want to. * - * On Success unmap_and_put_page() should be called on *res_page. + * On Success folio_release_kmap() should be called on *foliop. * - * sysv_find_entry() acts as a call to dir_get_page() and must be treated + * sysv_find_entry() acts as a call to dir_get_folio() and must be treated * accordingly for nesting purposes. */ -struct sysv_dir_entry *sysv_find_entry(struct dentry *dentry, struct page **res_page) +struct sysv_dir_entry *sysv_find_entry(struct dentry *dentry, struct folio **foliop) { const char * name = dentry->d_name.name; int namelen = dentry->d_name.len; struct inode * dir = d_inode(dentry->d_parent); unsigned long start, n; unsigned long npages = dir_pages(dir); - struct page *page = NULL; struct sysv_dir_entry *de; - *res_page = NULL; - start = SYSV_I(dir)->i_dir_start_lookup; if (start >= npages) start = 0; n = start; do { - char *kaddr = dir_get_page(dir, n, &page); + char *kaddr = dir_get_folio(dir, n, foliop); if (!IS_ERR(kaddr)) { de = (struct sysv_dir_entry *)kaddr; - kaddr += PAGE_SIZE - SYSV_DIRSIZE; + kaddr += folio_size(*foliop) - SYSV_DIRSIZE; for ( ; (char *) de <= kaddr ; de++) { if (!de->inode) continue; @@ -166,7 +163,7 @@ struct sysv_dir_entry *sysv_find_entry(struct dentry *dentry, struct page **res_ name, de->name)) goto found; } - unmap_and_put_page(page, kaddr); + folio_release_kmap(*foliop, kaddr); } if (++n >= npages) @@ -177,7 +174,6 @@ struct sysv_dir_entry *sysv_find_entry(struct dentry *dentry, struct page **res_ found: SYSV_I(dir)->i_dir_start_lookup = n; - *res_page = page; return de; } @@ -186,7 +182,7 @@ int sysv_add_link(struct dentry *dentry, struct inode *inode) struct inode *dir = d_inode(dentry->d_parent); const char * name = dentry->d_name.name; int namelen = dentry->d_name.len; - struct page *page = NULL; + struct folio *folio = NULL; struct sysv_dir_entry * de; unsigned long npages = dir_pages(dir); unsigned long n; @@ -196,7 +192,7 @@ int sysv_add_link(struct dentry *dentry, struct inode *inode) /* We take care of directory expansion in the same loop */ for (n = 0; n <= npages; n++) { - kaddr = dir_get_page(dir, n, &page); + kaddr = dir_get_folio(dir, n, &folio); if (IS_ERR(kaddr)) return PTR_ERR(kaddr); de = (struct sysv_dir_entry *)kaddr; @@ -206,49 +202,49 @@ int sysv_add_link(struct dentry *dentry, struct inode *inode) goto got_it; err = -EEXIST; if (namecompare(namelen, SYSV_NAMELEN, name, de->name)) - goto out_page; + goto out_folio; de++; } - unmap_and_put_page(page, kaddr); + folio_release_kmap(folio, kaddr); } BUG(); return -EINVAL; got_it: - pos = page_offset(page) + offset_in_page(de); - lock_page(page); - err = sysv_prepare_chunk(page, pos, SYSV_DIRSIZE); + pos = folio_pos(folio) + offset_in_folio(folio, de); + folio_lock(folio); + err = sysv_prepare_chunk(folio, pos, SYSV_DIRSIZE); if (err) goto out_unlock; memcpy (de->name, name, namelen); memset (de->name + namelen, 0, SYSV_DIRSIZE - namelen - 2); de->inode = cpu_to_fs16(SYSV_SB(inode->i_sb), inode->i_ino); - dir_commit_chunk(page, pos, SYSV_DIRSIZE); + dir_commit_chunk(folio, pos, SYSV_DIRSIZE); inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); mark_inode_dirty(dir); err = sysv_handle_dirsync(dir); -out_page: - unmap_and_put_page(page, kaddr); +out_folio: + folio_release_kmap(folio, kaddr); return err; out_unlock: - unlock_page(page); - goto out_page; + folio_unlock(folio); + goto out_folio; } -int sysv_delete_entry(struct sysv_dir_entry *de, struct page *page) +int sysv_delete_entry(struct sysv_dir_entry *de, struct folio *folio) { - struct inode *inode = page->mapping->host; - loff_t pos = page_offset(page) + offset_in_page(de); + struct inode *inode = folio->mapping->host; + loff_t pos = folio_pos(folio) + offset_in_folio(folio, de); int err; - lock_page(page); - err = sysv_prepare_chunk(page, pos, SYSV_DIRSIZE); + folio_lock(folio); + err = sysv_prepare_chunk(folio, pos, SYSV_DIRSIZE); if (err) { - unlock_page(page); + folio_unlock(folio); return err; } de->inode = 0; - dir_commit_chunk(page, pos, SYSV_DIRSIZE); + dir_commit_chunk(folio, pos, SYSV_DIRSIZE); inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); mark_inode_dirty(inode); return sysv_handle_dirsync(inode); @@ -256,33 +252,33 @@ int sysv_delete_entry(struct sysv_dir_entry *de, struct page *page) int sysv_make_empty(struct inode *inode, struct inode *dir) { - struct page *page = grab_cache_page(inode->i_mapping, 0); + struct folio *folio = filemap_grab_folio(inode->i_mapping, 0); struct sysv_dir_entry * de; - char *base; + char *kaddr; int err; - if (!page) - return -ENOMEM; - err = sysv_prepare_chunk(page, 0, 2 * SYSV_DIRSIZE); + if (IS_ERR(folio)) + return PTR_ERR(folio); + err = sysv_prepare_chunk(folio, 0, 2 * SYSV_DIRSIZE); if (err) { - unlock_page(page); + folio_unlock(folio); goto fail; } - base = kmap_local_page(page); - memset(base, 0, PAGE_SIZE); + kaddr = kmap_local_folio(folio, 0); + memset(kaddr, 0, folio_size(folio)); - de = (struct sysv_dir_entry *) base; + de = (struct sysv_dir_entry *)kaddr; de->inode = cpu_to_fs16(SYSV_SB(inode->i_sb), inode->i_ino); strcpy(de->name,"."); de++; de->inode = cpu_to_fs16(SYSV_SB(inode->i_sb), dir->i_ino); strcpy(de->name,".."); - kunmap_local(base); - dir_commit_chunk(page, 0, 2 * SYSV_DIRSIZE); + kunmap_local(kaddr); + dir_commit_chunk(folio, 0, 2 * SYSV_DIRSIZE); err = sysv_handle_dirsync(inode); fail: - put_page(page); + folio_put(folio); return err; } @@ -292,19 +288,19 @@ fail: int sysv_empty_dir(struct inode * inode) { struct super_block *sb = inode->i_sb; - struct page *page = NULL; + struct folio *folio = NULL; unsigned long i, npages = dir_pages(inode); char *kaddr; for (i = 0; i < npages; i++) { struct sysv_dir_entry *de; - kaddr = dir_get_page(inode, i, &page); + kaddr = dir_get_folio(inode, i, &folio); if (IS_ERR(kaddr)) continue; de = (struct sysv_dir_entry *)kaddr; - kaddr += PAGE_SIZE-SYSV_DIRSIZE; + kaddr += folio_size(folio) - SYSV_DIRSIZE; for ( ;(char *)de <= kaddr; de++) { if (!de->inode) @@ -321,46 +317,46 @@ int sysv_empty_dir(struct inode * inode) if (de->name[1] != '.' || de->name[2]) goto not_empty; } - unmap_and_put_page(page, kaddr); + folio_release_kmap(folio, kaddr); } return 1; not_empty: - unmap_and_put_page(page, kaddr); + folio_release_kmap(folio, kaddr); return 0; } /* Releases the page */ -int sysv_set_link(struct sysv_dir_entry *de, struct page *page, - struct inode *inode) +int sysv_set_link(struct sysv_dir_entry *de, struct folio *folio, + struct inode *inode) { - struct inode *dir = page->mapping->host; - loff_t pos = page_offset(page) + offset_in_page(de); + struct inode *dir = folio->mapping->host; + loff_t pos = folio_pos(folio) + offset_in_folio(folio, de); int err; - lock_page(page); - err = sysv_prepare_chunk(page, pos, SYSV_DIRSIZE); + folio_lock(folio); + err = sysv_prepare_chunk(folio, pos, SYSV_DIRSIZE); if (err) { - unlock_page(page); + folio_unlock(folio); return err; } de->inode = cpu_to_fs16(SYSV_SB(inode->i_sb), inode->i_ino); - dir_commit_chunk(page, pos, SYSV_DIRSIZE); + dir_commit_chunk(folio, pos, SYSV_DIRSIZE); inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); mark_inode_dirty(dir); return sysv_handle_dirsync(inode); } /* - * Calls to dir_get_page()/unmap_and_put_page() must be nested according to the + * Calls to dir_get_folio()/folio_release_kmap() must be nested according to the * rules documented in mm/highmem.rst. * - * sysv_dotdot() acts as a call to dir_get_page() and must be treated + * sysv_dotdot() acts as a call to dir_get_folio() and must be treated * accordingly for nesting purposes. */ -struct sysv_dir_entry *sysv_dotdot(struct inode *dir, struct page **p) +struct sysv_dir_entry *sysv_dotdot(struct inode *dir, struct folio **foliop) { - struct sysv_dir_entry *de = dir_get_page(dir, 0, p); + struct sysv_dir_entry *de = dir_get_folio(dir, 0, foliop); if (IS_ERR(de)) return NULL; @@ -370,13 +366,13 @@ struct sysv_dir_entry *sysv_dotdot(struct inode *dir, struct page **p) ino_t sysv_inode_by_name(struct dentry *dentry) { - struct page *page; - struct sysv_dir_entry *de = sysv_find_entry (dentry, &page); + struct folio *folio; + struct sysv_dir_entry *de = sysv_find_entry (dentry, &folio); ino_t res = 0; if (de) { res = fs16_to_cpu(SYSV_SB(dentry->d_sb), de->inode); - unmap_and_put_page(page, de); + folio_release_kmap(folio, de); } return res; } diff --git a/fs/sysv/itree.c b/fs/sysv/itree.c index 19bcb51a2203..451e95f474fa 100644 --- a/fs/sysv/itree.c +++ b/fs/sysv/itree.c @@ -466,9 +466,9 @@ static int sysv_read_folio(struct file *file, struct folio *folio) return block_read_full_folio(folio, get_block); } -int sysv_prepare_chunk(struct page *page, loff_t pos, unsigned len) +int sysv_prepare_chunk(struct folio *folio, loff_t pos, unsigned len) { - return __block_write_begin(page, pos, len, get_block); + return __block_write_begin(folio, pos, len, get_block); } static void sysv_write_failed(struct address_space *mapping, loff_t to) @@ -483,11 +483,11 @@ static void sysv_write_failed(struct address_space *mapping, loff_t to) static int sysv_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { int ret; - ret = block_write_begin(mapping, pos, len, pagep, get_block); + ret = block_write_begin(mapping, pos, len, foliop, get_block); if (unlikely(ret)) sysv_write_failed(mapping, pos + len); diff --git a/fs/sysv/namei.c b/fs/sysv/namei.c index d6b73798071b..fb8bd8437872 100644 --- a/fs/sysv/namei.c +++ b/fs/sysv/namei.c @@ -151,20 +151,20 @@ out_dir: static int sysv_unlink(struct inode * dir, struct dentry * dentry) { struct inode * inode = d_inode(dentry); - struct page * page; + struct folio *folio; struct sysv_dir_entry * de; int err; - de = sysv_find_entry(dentry, &page); + de = sysv_find_entry(dentry, &folio); if (!de) return -ENOENT; - err = sysv_delete_entry(de, page); + err = sysv_delete_entry(de, folio); if (!err) { inode_set_ctime_to_ts(inode, inode_get_ctime(dir)); inode_dec_link_count(inode); } - unmap_and_put_page(page, de); + folio_release_kmap(folio, de); return err; } @@ -194,28 +194,28 @@ static int sysv_rename(struct mnt_idmap *idmap, struct inode *old_dir, { struct inode * old_inode = d_inode(old_dentry); struct inode * new_inode = d_inode(new_dentry); - struct page * dir_page = NULL; + struct folio *dir_folio; struct sysv_dir_entry * dir_de = NULL; - struct page * old_page; + struct folio *old_folio; struct sysv_dir_entry * old_de; int err = -ENOENT; if (flags & ~RENAME_NOREPLACE) return -EINVAL; - old_de = sysv_find_entry(old_dentry, &old_page); + old_de = sysv_find_entry(old_dentry, &old_folio); if (!old_de) goto out; if (S_ISDIR(old_inode->i_mode)) { err = -EIO; - dir_de = sysv_dotdot(old_inode, &dir_page); + dir_de = sysv_dotdot(old_inode, &dir_folio); if (!dir_de) goto out_old; } if (new_inode) { - struct page * new_page; + struct folio *new_folio; struct sysv_dir_entry * new_de; err = -ENOTEMPTY; @@ -223,11 +223,11 @@ static int sysv_rename(struct mnt_idmap *idmap, struct inode *old_dir, goto out_dir; err = -ENOENT; - new_de = sysv_find_entry(new_dentry, &new_page); + new_de = sysv_find_entry(new_dentry, &new_folio); if (!new_de) goto out_dir; - err = sysv_set_link(new_de, new_page, old_inode); - unmap_and_put_page(new_page, new_de); + err = sysv_set_link(new_de, new_folio, old_inode); + folio_release_kmap(new_folio, new_de); if (err) goto out_dir; inode_set_ctime_current(new_inode); @@ -242,23 +242,23 @@ static int sysv_rename(struct mnt_idmap *idmap, struct inode *old_dir, inode_inc_link_count(new_dir); } - err = sysv_delete_entry(old_de, old_page); + err = sysv_delete_entry(old_de, old_folio); if (err) goto out_dir; mark_inode_dirty(old_inode); if (dir_de) { - err = sysv_set_link(dir_de, dir_page, new_dir); + err = sysv_set_link(dir_de, dir_folio, new_dir); if (!err) inode_dec_link_count(old_dir); } out_dir: if (dir_de) - unmap_and_put_page(dir_page, dir_de); + folio_release_kmap(dir_folio, dir_de); out_old: - unmap_and_put_page(old_page, old_de); + folio_release_kmap(old_folio, old_de); out: return err; } diff --git a/fs/sysv/sysv.h b/fs/sysv/sysv.h index e3f988b469ee..0a48b2e7edb1 100644 --- a/fs/sysv/sysv.h +++ b/fs/sysv/sysv.h @@ -133,8 +133,8 @@ extern void sysv_free_block(struct super_block *, sysv_zone_t); extern unsigned long sysv_count_free_blocks(struct super_block *); /* itree.c */ -extern void sysv_truncate(struct inode *); -extern int sysv_prepare_chunk(struct page *page, loff_t pos, unsigned len); +void sysv_truncate(struct inode *); +int sysv_prepare_chunk(struct folio *folio, loff_t pos, unsigned len); /* inode.c */ extern struct inode *sysv_iget(struct super_block *, unsigned int); @@ -148,15 +148,15 @@ extern void sysv_destroy_icache(void); /* dir.c */ -extern struct sysv_dir_entry *sysv_find_entry(struct dentry *, struct page **); -extern int sysv_add_link(struct dentry *, struct inode *); -extern int sysv_delete_entry(struct sysv_dir_entry *, struct page *); -extern int sysv_make_empty(struct inode *, struct inode *); -extern int sysv_empty_dir(struct inode *); -extern int sysv_set_link(struct sysv_dir_entry *, struct page *, +struct sysv_dir_entry *sysv_find_entry(struct dentry *, struct folio **); +int sysv_add_link(struct dentry *, struct inode *); +int sysv_delete_entry(struct sysv_dir_entry *, struct folio *); +int sysv_make_empty(struct inode *, struct inode *); +int sysv_empty_dir(struct inode *); +int sysv_set_link(struct sysv_dir_entry *, struct folio *, struct inode *); -extern struct sysv_dir_entry *sysv_dotdot(struct inode *, struct page **); -extern ino_t sysv_inode_by_name(struct dentry *); +struct sysv_dir_entry *sysv_dotdot(struct inode *, struct folio **); +ino_t sysv_inode_by_name(struct dentry *); extern const struct inode_operations sysv_file_inode_operations; diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c index 01e99e98457d..8705c77a9e75 100644 --- a/fs/tracefs/event_inode.c +++ b/fs/tracefs/event_inode.c @@ -862,7 +862,7 @@ static void eventfs_remove_rec(struct eventfs_inode *ei, int level) list_for_each_entry(ei_child, &ei->children, list) eventfs_remove_rec(ei_child, level + 1); - list_del(&ei->list); + list_del_rcu(&ei->list); free_ei(ei); } diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index c77ea57fe696..fda82f3e16e8 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -555,6 +555,11 @@ static unsigned int vfs_dent_type(uint8_t type) return 0; } +struct ubifs_dir_data { + struct ubifs_dent_node *dent; + u64 cookie; +}; + /* * The classical Unix view for directory is that it is a linear array of * (name, inode number) entries. Linux/VFS assumes this model as well. @@ -582,6 +587,7 @@ static int ubifs_readdir(struct file *file, struct dir_context *ctx) struct inode *dir = file_inode(file); struct ubifs_info *c = dir->i_sb->s_fs_info; bool encrypted = IS_ENCRYPTED(dir); + struct ubifs_dir_data *data = file->private_data; dbg_gen("dir ino %lu, f_pos %#llx", dir->i_ino, ctx->pos); @@ -604,27 +610,27 @@ static int ubifs_readdir(struct file *file, struct dir_context *ctx) fstr_real_len = fstr.len; } - if (file->f_version == 0) { + if (data->cookie == 0) { /* - * The file was seek'ed, which means that @file->private_data + * The file was seek'ed, which means that @data->dent * is now invalid. This may also be just the first * 'ubifs_readdir()' invocation, in which case - * @file->private_data is NULL, and the below code is + * @data->dent is NULL, and the below code is * basically a no-op. */ - kfree(file->private_data); - file->private_data = NULL; + kfree(data->dent); + data->dent = NULL; } /* - * 'generic_file_llseek()' unconditionally sets @file->f_version to - * zero, and we use this for detecting whether the file was seek'ed. + * 'ubifs_dir_llseek()' sets @data->cookie to zero, and we use this + * for detecting whether the file was seek'ed. */ - file->f_version = 1; + data->cookie = 1; /* File positions 0 and 1 correspond to "." and ".." */ if (ctx->pos < 2) { - ubifs_assert(c, !file->private_data); + ubifs_assert(c, !data->dent); if (!dir_emit_dots(file, ctx)) { if (encrypted) fscrypt_fname_free_buffer(&fstr); @@ -641,10 +647,10 @@ static int ubifs_readdir(struct file *file, struct dir_context *ctx) } ctx->pos = key_hash_flash(c, &dent->key); - file->private_data = dent; + data->dent = dent; } - dent = file->private_data; + dent = data->dent; if (!dent) { /* * The directory was seek'ed to and is now readdir'ed. @@ -658,7 +664,7 @@ static int ubifs_readdir(struct file *file, struct dir_context *ctx) goto out; } ctx->pos = key_hash_flash(c, &dent->key); - file->private_data = dent; + data->dent = dent; } while (1) { @@ -701,15 +707,15 @@ static int ubifs_readdir(struct file *file, struct dir_context *ctx) goto out; } - kfree(file->private_data); + kfree(data->dent); ctx->pos = key_hash_flash(c, &dent->key); - file->private_data = dent; + data->dent = dent; cond_resched(); } out: - kfree(file->private_data); - file->private_data = NULL; + kfree(data->dent); + data->dent = NULL; if (encrypted) fscrypt_fname_free_buffer(&fstr); @@ -733,7 +739,10 @@ out: /* Free saved readdir() state when the directory is closed */ static int ubifs_dir_release(struct inode *dir, struct file *file) { - kfree(file->private_data); + struct ubifs_dir_data *data = file->private_data; + + kfree(data->dent); + kfree(data); file->private_data = NULL; return 0; } @@ -1712,6 +1721,24 @@ int ubifs_getattr(struct mnt_idmap *idmap, const struct path *path, return 0; } +static int ubifs_dir_open(struct inode *inode, struct file *file) +{ + struct ubifs_dir_data *data; + + data = kzalloc(sizeof(struct ubifs_dir_data), GFP_KERNEL); + if (!data) + return -ENOMEM; + file->private_data = data; + return 0; +} + +static loff_t ubifs_dir_llseek(struct file *file, loff_t offset, int whence) +{ + struct ubifs_dir_data *data = file->private_data; + + return generic_llseek_cookie(file, offset, whence, &data->cookie); +} + const struct inode_operations ubifs_dir_inode_operations = { .lookup = ubifs_lookup, .create = ubifs_create, @@ -1732,7 +1759,8 @@ const struct inode_operations ubifs_dir_inode_operations = { }; const struct file_operations ubifs_dir_operations = { - .llseek = generic_file_llseek, + .open = ubifs_dir_open, + .llseek = ubifs_dir_llseek, .release = ubifs_dir_release, .read = generic_read_dir, .iterate_shared = ubifs_readdir, diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 68e104423a48..5130123005e4 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -211,7 +211,7 @@ static void release_existing_page_budget(struct ubifs_info *c) } static int write_begin_slow(struct address_space *mapping, - loff_t pos, unsigned len, struct page **pagep) + loff_t pos, unsigned len, struct folio **foliop) { struct inode *inode = mapping->host; struct ubifs_info *c = inode->i_sb->s_fs_info; @@ -298,7 +298,7 @@ static int write_begin_slow(struct address_space *mapping, ubifs_release_dirty_inode_budget(c, ui); } - *pagep = &folio->page; + *foliop = folio; return 0; } @@ -414,7 +414,7 @@ static int allocate_budget(struct ubifs_info *c, struct folio *folio, */ static int ubifs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { struct inode *inode = mapping->host; struct ubifs_info *c = inode->i_sb->s_fs_info; @@ -483,7 +483,7 @@ static int ubifs_write_begin(struct file *file, struct address_space *mapping, folio_unlock(folio); folio_put(folio); - return write_begin_slow(mapping, pos, len, pagep); + return write_begin_slow(mapping, pos, len, foliop); } /* @@ -492,7 +492,7 @@ static int ubifs_write_begin(struct file *file, struct address_space *mapping, * with @ui->ui_mutex locked if we are appending pages, and unlocked * otherwise. This is an optimization (slightly hacky though). */ - *pagep = &folio->page; + *foliop = folio; return 0; } @@ -524,9 +524,8 @@ static void cancel_budget(struct ubifs_info *c, struct folio *folio, static int ubifs_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { - struct folio *folio = page_folio(page); struct inode *inode = mapping->host; struct ubifs_inode *ui = ubifs_inode(inode); struct ubifs_info *c = inode->i_sb->s_fs_info; diff --git a/fs/udf/dir.c b/fs/udf/dir.c index f94f45fe2c91..5023dfe191e8 100644 --- a/fs/udf/dir.c +++ b/fs/udf/dir.c @@ -60,7 +60,7 @@ static int udf_readdir(struct file *file, struct dir_context *ctx) * identifying beginning of dir entry (names are under user control), * we need to scan the directory from the beginning. */ - if (!inode_eq_iversion(dir, file->f_version)) { + if (!inode_eq_iversion(dir, *(u64 *)file->private_data)) { emit_pos = nf_pos; nf_pos = 0; } else { @@ -122,15 +122,37 @@ out_iter: udf_fiiter_release(&iter); out: if (pos_valid) - file->f_version = inode_query_iversion(dir); + *(u64 *)file->private_data = inode_query_iversion(dir); kfree(fname); return ret; } +static int udf_dir_open(struct inode *inode, struct file *file) +{ + file->private_data = kzalloc(sizeof(u64), GFP_KERNEL); + if (!file->private_data) + return -ENOMEM; + return 0; +} + +static int udf_dir_release(struct inode *inode, struct file *file) +{ + kfree(file->private_data); + return 0; +} + +static loff_t udf_dir_llseek(struct file *file, loff_t offset, int whence) +{ + return generic_llseek_cookie(file, offset, whence, + (u64 *)file->private_data); +} + /* readdir and lookup functions */ const struct file_operations udf_dir_operations = { - .llseek = generic_file_llseek, + .open = udf_dir_open, + .release = udf_dir_release, + .llseek = udf_dir_llseek, .read = generic_read_dir, .iterate_shared = udf_readdir, .unlocked_ioctl = udf_ioctl, diff --git a/fs/udf/file.c b/fs/udf/file.c index 3a4179de316b..412fe7c4d348 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -62,7 +62,7 @@ static vm_fault_t udf_page_mkwrite(struct vm_fault *vmf) end = size & ~PAGE_MASK; else end = PAGE_SIZE; - err = __block_write_begin(&folio->page, 0, end, udf_get_block); + err = __block_write_begin(folio, 0, end, udf_get_block); if (err) { folio_unlock(folio); ret = vmf_fs_error(err); diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 4726a4d014b6..eaee57b91c6c 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -246,14 +246,14 @@ static void udf_readahead(struct readahead_control *rac) static int udf_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { struct udf_inode_info *iinfo = UDF_I(file_inode(file)); struct folio *folio; int ret; if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) { - ret = block_write_begin(mapping, pos, len, pagep, + ret = block_write_begin(mapping, pos, len, foliop, udf_get_block); if (unlikely(ret)) udf_write_failed(mapping, pos + len); @@ -265,7 +265,7 @@ static int udf_write_begin(struct file *file, struct address_space *mapping, mapping_gfp_mask(mapping)); if (IS_ERR(folio)) return PTR_ERR(folio); - *pagep = &folio->page; + *foliop = folio; if (!folio_test_uptodate(folio)) udf_adinicb_read_folio(folio); return 0; @@ -273,16 +273,14 @@ static int udf_write_begin(struct file *file, struct address_space *mapping, static int udf_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { struct inode *inode = file_inode(file); - struct folio *folio; loff_t last_pos; if (UDF_I(inode)->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) - return generic_write_end(file, mapping, pos, len, copied, page, + return generic_write_end(file, mapping, pos, len, copied, folio, fsdata); - folio = page_folio(page); last_pos = pos + copied; if (last_pos > inode->i_size) i_size_write(inode, last_pos); diff --git a/fs/ufs/dir.c b/fs/ufs/dir.c index 61f25d3cf3f7..d6e6a2198971 100644 --- a/fs/ufs/dir.c +++ b/fs/ufs/dir.c @@ -42,18 +42,18 @@ static inline int ufs_match(struct super_block *sb, int len, return !memcmp(name, de->d_name, len); } -static void ufs_commit_chunk(struct page *page, loff_t pos, unsigned len) +static void ufs_commit_chunk(struct folio *folio, loff_t pos, unsigned len) { - struct address_space *mapping = page->mapping; + struct address_space *mapping = folio->mapping; struct inode *dir = mapping->host; inode_inc_iversion(dir); - block_write_end(NULL, mapping, pos, len, len, page, NULL); + block_write_end(NULL, mapping, pos, len, len, folio, NULL); if (pos+len > dir->i_size) { i_size_write(dir, pos+len); mark_inode_dirty(dir); } - unlock_page(page); + folio_unlock(folio); } static int ufs_handle_dirsync(struct inode *dir) @@ -66,22 +66,16 @@ static int ufs_handle_dirsync(struct inode *dir) return err; } -static inline void ufs_put_page(struct page *page) -{ - kunmap(page); - put_page(page); -} - ino_t ufs_inode_by_name(struct inode *dir, const struct qstr *qstr) { ino_t res = 0; struct ufs_dir_entry *de; - struct page *page; + struct folio *folio; - de = ufs_find_entry(dir, qstr, &page); + de = ufs_find_entry(dir, qstr, &folio); if (de) { res = fs32_to_cpu(dir->i_sb, de->d_ino); - ufs_put_page(page); + folio_release_kmap(folio, de); } return res; } @@ -89,43 +83,40 @@ ino_t ufs_inode_by_name(struct inode *dir, const struct qstr *qstr) /* Releases the page */ void ufs_set_link(struct inode *dir, struct ufs_dir_entry *de, - struct page *page, struct inode *inode, + struct folio *folio, struct inode *inode, bool update_times) { - loff_t pos = page_offset(page) + - (char *) de - (char *) page_address(page); + loff_t pos = folio_pos(folio) + offset_in_folio(folio, de); unsigned len = fs16_to_cpu(dir->i_sb, de->d_reclen); int err; - lock_page(page); - err = ufs_prepare_chunk(page, pos, len); + folio_lock(folio); + err = ufs_prepare_chunk(folio, pos, len); BUG_ON(err); de->d_ino = cpu_to_fs32(dir->i_sb, inode->i_ino); ufs_set_de_type(dir->i_sb, de, inode->i_mode); - ufs_commit_chunk(page, pos, len); - ufs_put_page(page); + ufs_commit_chunk(folio, pos, len); + folio_release_kmap(folio, de); if (update_times) inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); mark_inode_dirty(dir); ufs_handle_dirsync(dir); } - -static bool ufs_check_page(struct page *page) +static bool ufs_check_folio(struct folio *folio, char *kaddr) { - struct inode *dir = page->mapping->host; + struct inode *dir = folio->mapping->host; struct super_block *sb = dir->i_sb; - char *kaddr = page_address(page); unsigned offs, rec_len; - unsigned limit = PAGE_SIZE; + unsigned limit = folio_size(folio); const unsigned chunk_mask = UFS_SB(sb)->s_uspi->s_dirblksize - 1; struct ufs_dir_entry *p; char *error; - if ((dir->i_size >> PAGE_SHIFT) == page->index) { - limit = dir->i_size & ~PAGE_MASK; + if (dir->i_size < folio_pos(folio) + limit) { + limit = offset_in_folio(folio, dir->i_size); if (limit & chunk_mask) goto Ebadsize; if (!limit) @@ -150,13 +141,13 @@ static bool ufs_check_page(struct page *page) if (offs != limit) goto Eend; out: - SetPageChecked(page); + folio_set_checked(folio); return true; /* Too bad, we had an error */ Ebadsize: - ufs_error(sb, "ufs_check_page", + ufs_error(sb, __func__, "size of directory #%lu is not a multiple of chunk size", dir->i_ino ); @@ -176,36 +167,40 @@ Espan: Einumber: error = "inode out of bounds"; bad_entry: - ufs_error (sb, "ufs_check_page", "bad entry in directory #%lu: %s - " - "offset=%lu, rec_len=%d, name_len=%d", - dir->i_ino, error, (page->index<<PAGE_SHIFT)+offs, + ufs_error(sb, __func__, "bad entry in directory #%lu: %s - " + "offset=%llu, rec_len=%d, name_len=%d", + dir->i_ino, error, folio_pos(folio) + offs, rec_len, ufs_get_de_namlen(sb, p)); goto fail; Eend: p = (struct ufs_dir_entry *)(kaddr + offs); ufs_error(sb, __func__, "entry in directory #%lu spans the page boundary" - "offset=%lu", - dir->i_ino, (page->index<<PAGE_SHIFT)+offs); + "offset=%llu", + dir->i_ino, folio_pos(folio) + offs); fail: return false; } -static struct page *ufs_get_page(struct inode *dir, unsigned long n) +static void *ufs_get_folio(struct inode *dir, unsigned long n, + struct folio **foliop) { struct address_space *mapping = dir->i_mapping; - struct page *page = read_mapping_page(mapping, n, NULL); - if (!IS_ERR(page)) { - kmap(page); - if (unlikely(!PageChecked(page))) { - if (!ufs_check_page(page)) - goto fail; - } + struct folio *folio = read_mapping_folio(mapping, n, NULL); + void *kaddr; + + if (IS_ERR(folio)) + return ERR_CAST(folio); + kaddr = kmap_local_folio(folio, 0); + if (unlikely(!folio_test_checked(folio))) { + if (!ufs_check_folio(folio, kaddr)) + goto fail; } - return page; + *foliop = folio; + return kaddr; fail: - ufs_put_page(page); + folio_release_kmap(folio, kaddr); return ERR_PTR(-EIO); } @@ -231,17 +226,14 @@ ufs_next_entry(struct super_block *sb, struct ufs_dir_entry *p) fs16_to_cpu(sb, p->d_reclen)); } -struct ufs_dir_entry *ufs_dotdot(struct inode *dir, struct page **p) +struct ufs_dir_entry *ufs_dotdot(struct inode *dir, struct folio **foliop) { - struct page *page = ufs_get_page(dir, 0); - struct ufs_dir_entry *de = NULL; + struct ufs_dir_entry *de = ufs_get_folio(dir, 0, foliop); - if (!IS_ERR(page)) { - de = ufs_next_entry(dir->i_sb, - (struct ufs_dir_entry *)page_address(page)); - *p = page; - } - return de; + if (!IS_ERR(de)) + return ufs_next_entry(dir->i_sb, de); + + return NULL; } /* @@ -253,7 +245,7 @@ struct ufs_dir_entry *ufs_dotdot(struct inode *dir, struct page **p) * Entry is guaranteed to be valid. */ struct ufs_dir_entry *ufs_find_entry(struct inode *dir, const struct qstr *qstr, - struct page **res_page) + struct folio **foliop) { struct super_block *sb = dir->i_sb; const unsigned char *name = qstr->name; @@ -261,7 +253,6 @@ struct ufs_dir_entry *ufs_find_entry(struct inode *dir, const struct qstr *qstr, unsigned reclen = UFS_DIR_REC_LEN(namelen); unsigned long start, n; unsigned long npages = dir_pages(dir); - struct page *page = NULL; struct ufs_inode_info *ui = UFS_I(dir); struct ufs_dir_entry *de; @@ -270,27 +261,23 @@ struct ufs_dir_entry *ufs_find_entry(struct inode *dir, const struct qstr *qstr, if (npages == 0 || namelen > UFS_MAXNAMLEN) goto out; - /* OFFSET_CACHE */ - *res_page = NULL; - start = ui->i_dir_start_lookup; if (start >= npages) start = 0; n = start; do { - char *kaddr; - page = ufs_get_page(dir, n); - if (!IS_ERR(page)) { - kaddr = page_address(page); - de = (struct ufs_dir_entry *) kaddr; + char *kaddr = ufs_get_folio(dir, n, foliop); + + if (!IS_ERR(kaddr)) { + de = (struct ufs_dir_entry *)kaddr; kaddr += ufs_last_byte(dir, n) - reclen; while ((char *) de <= kaddr) { if (ufs_match(sb, namelen, name, de)) goto found; de = ufs_next_entry(sb, de); } - ufs_put_page(page); + folio_release_kmap(*foliop, kaddr); } if (++n >= npages) n = 0; @@ -299,7 +286,6 @@ out: return NULL; found: - *res_page = page; ui->i_dir_start_lookup = n; return de; } @@ -316,11 +302,10 @@ int ufs_add_link(struct dentry *dentry, struct inode *inode) unsigned reclen = UFS_DIR_REC_LEN(namelen); const unsigned int chunk_size = UFS_SB(sb)->s_uspi->s_dirblksize; unsigned short rec_len, name_len; - struct page *page = NULL; + struct folio *folio = NULL; struct ufs_dir_entry *de; unsigned long npages = dir_pages(dir); unsigned long n; - char *kaddr; loff_t pos; int err; @@ -328,21 +313,19 @@ int ufs_add_link(struct dentry *dentry, struct inode *inode) /* * We take care of directory expansion in the same loop. - * This code plays outside i_size, so it locks the page + * This code plays outside i_size, so it locks the folio * to protect that region. */ for (n = 0; n <= npages; n++) { + char *kaddr = ufs_get_folio(dir, n, &folio); char *dir_end; - page = ufs_get_page(dir, n); - err = PTR_ERR(page); - if (IS_ERR(page)) - goto out; - lock_page(page); - kaddr = page_address(page); + if (IS_ERR(kaddr)) + return PTR_ERR(kaddr); + folio_lock(folio); dir_end = kaddr + ufs_last_byte(dir, n); de = (struct ufs_dir_entry *)kaddr; - kaddr += PAGE_SIZE - reclen; + kaddr += folio_size(folio) - reclen; while ((char *)de <= kaddr) { if ((char *)de == dir_end) { /* We hit i_size */ @@ -369,16 +352,15 @@ int ufs_add_link(struct dentry *dentry, struct inode *inode) goto got_it; de = (struct ufs_dir_entry *) ((char *) de + rec_len); } - unlock_page(page); - ufs_put_page(page); + folio_unlock(folio); + folio_release_kmap(folio, kaddr); } BUG(); return -EINVAL; got_it: - pos = page_offset(page) + - (char*)de - (char*)page_address(page); - err = ufs_prepare_chunk(page, pos, rec_len); + pos = folio_pos(folio) + offset_in_folio(folio, de); + err = ufs_prepare_chunk(folio, pos, rec_len); if (err) goto out_unlock; if (de->d_ino) { @@ -395,18 +377,17 @@ got_it: de->d_ino = cpu_to_fs32(sb, inode->i_ino); ufs_set_de_type(sb, de, inode->i_mode); - ufs_commit_chunk(page, pos, rec_len); + ufs_commit_chunk(folio, pos, rec_len); inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); mark_inode_dirty(dir); err = ufs_handle_dirsync(dir); /* OFFSET_CACHE */ out_put: - ufs_put_page(page); -out: + folio_release_kmap(folio, de); return err; out_unlock: - unlock_page(page); + folio_unlock(folio); goto out_put; } @@ -435,7 +416,7 @@ ufs_readdir(struct file *file, struct dir_context *ctx) unsigned long n = pos >> PAGE_SHIFT; unsigned long npages = dir_pages(inode); unsigned chunk_mask = ~(UFS_SB(sb)->s_uspi->s_dirblksize - 1); - bool need_revalidate = !inode_eq_iversion(inode, file->f_version); + bool need_revalidate = !inode_eq_iversion(inode, *(u64 *)file->private_data); unsigned flags = UFS_SB(sb)->s_flags; UFSD("BEGIN\n"); @@ -444,25 +425,24 @@ ufs_readdir(struct file *file, struct dir_context *ctx) return 0; for ( ; n < npages; n++, offset = 0) { - char *kaddr, *limit; struct ufs_dir_entry *de; + struct folio *folio; + char *kaddr = ufs_get_folio(inode, n, &folio); + char *limit; - struct page *page = ufs_get_page(inode, n); - - if (IS_ERR(page)) { + if (IS_ERR(kaddr)) { ufs_error(sb, __func__, "bad page in #%lu", inode->i_ino); ctx->pos += PAGE_SIZE - offset; - return -EIO; + return PTR_ERR(kaddr); } - kaddr = page_address(page); if (unlikely(need_revalidate)) { if (offset) { offset = ufs_validate_entry(sb, kaddr, offset, chunk_mask); ctx->pos = (n<<PAGE_SHIFT) + offset; } - file->f_version = inode_query_iversion(inode); + *(u64 *)file->private_data = inode_query_iversion(inode); need_revalidate = false; } de = (struct ufs_dir_entry *)(kaddr+offset); @@ -482,13 +462,13 @@ ufs_readdir(struct file *file, struct dir_context *ctx) ufs_get_de_namlen(sb, de), fs32_to_cpu(sb, de->d_ino), d_type)) { - ufs_put_page(page); + folio_release_kmap(folio, de); return 0; } } ctx->pos += fs16_to_cpu(sb, de->d_reclen); } - ufs_put_page(page); + folio_release_kmap(folio, kaddr); } return 0; } @@ -499,19 +479,23 @@ ufs_readdir(struct file *file, struct dir_context *ctx) * previous entry. */ int ufs_delete_entry(struct inode *inode, struct ufs_dir_entry *dir, - struct page * page) + struct folio *folio) { struct super_block *sb = inode->i_sb; - char *kaddr = page_address(page); - unsigned from = ((char*)dir - kaddr) & ~(UFS_SB(sb)->s_uspi->s_dirblksize - 1); - unsigned to = ((char*)dir - kaddr) + fs16_to_cpu(sb, dir->d_reclen); + size_t from, to; + char *kaddr; loff_t pos; - struct ufs_dir_entry *pde = NULL; - struct ufs_dir_entry *de = (struct ufs_dir_entry *) (kaddr + from); + struct ufs_dir_entry *de, *pde = NULL; int err; UFSD("ENTER\n"); + from = offset_in_folio(folio, dir); + to = from + fs16_to_cpu(sb, dir->d_reclen); + kaddr = (char *)dir - from; + from &= ~(UFS_SB(sb)->s_uspi->s_dirblksize - 1); + de = (struct ufs_dir_entry *) (kaddr + from); + UFSD("ino %u, reclen %u, namlen %u, name %s\n", fs32_to_cpu(sb, de->d_ino), fs16_to_cpu(sb, de->d_reclen), @@ -528,21 +512,20 @@ int ufs_delete_entry(struct inode *inode, struct ufs_dir_entry *dir, de = ufs_next_entry(sb, de); } if (pde) - from = (char*)pde - (char*)page_address(page); - - pos = page_offset(page) + from; - lock_page(page); - err = ufs_prepare_chunk(page, pos, to - from); + from = offset_in_folio(folio, pde); + pos = folio_pos(folio) + from; + folio_lock(folio); + err = ufs_prepare_chunk(folio, pos, to - from); BUG_ON(err); if (pde) pde->d_reclen = cpu_to_fs16(sb, to - from); dir->d_ino = 0; - ufs_commit_chunk(page, pos, to - from); + ufs_commit_chunk(folio, pos, to - from); inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); mark_inode_dirty(inode); err = ufs_handle_dirsync(inode); out: - ufs_put_page(page); + folio_release_kmap(folio, kaddr); UFSD("EXIT\n"); return err; } @@ -551,26 +534,25 @@ int ufs_make_empty(struct inode * inode, struct inode *dir) { struct super_block * sb = dir->i_sb; struct address_space *mapping = inode->i_mapping; - struct page *page = grab_cache_page(mapping, 0); + struct folio *folio = filemap_grab_folio(mapping, 0); const unsigned int chunk_size = UFS_SB(sb)->s_uspi->s_dirblksize; struct ufs_dir_entry * de; - char *base; int err; + char *kaddr; - if (!page) - return -ENOMEM; + if (IS_ERR(folio)) + return PTR_ERR(folio); - err = ufs_prepare_chunk(page, 0, chunk_size); + err = ufs_prepare_chunk(folio, 0, chunk_size); if (err) { - unlock_page(page); + folio_unlock(folio); goto fail; } - kmap(page); - base = (char*)page_address(page); - memset(base, 0, PAGE_SIZE); + kaddr = kmap_local_folio(folio, 0); + memset(kaddr, 0, folio_size(folio)); - de = (struct ufs_dir_entry *) base; + de = (struct ufs_dir_entry *)kaddr; de->d_ino = cpu_to_fs32(sb, inode->i_ino); ufs_set_de_type(sb, de, inode->i_mode); @@ -584,12 +566,12 @@ int ufs_make_empty(struct inode * inode, struct inode *dir) de->d_reclen = cpu_to_fs16(sb, chunk_size - UFS_DIR_REC_LEN(1)); ufs_set_de_namlen(sb, de, 2); strcpy (de->d_name, ".."); - kunmap(page); + kunmap_local(kaddr); - ufs_commit_chunk(page, 0, chunk_size); + ufs_commit_chunk(folio, 0, chunk_size); err = ufs_handle_dirsync(inode); fail: - put_page(page); + folio_put(folio); return err; } @@ -599,18 +581,17 @@ fail: int ufs_empty_dir(struct inode * inode) { struct super_block *sb = inode->i_sb; - struct page *page = NULL; + struct folio *folio; + char *kaddr; unsigned long i, npages = dir_pages(inode); for (i = 0; i < npages; i++) { - char *kaddr; struct ufs_dir_entry *de; - page = ufs_get_page(inode, i); - if (IS_ERR(page)) + kaddr = ufs_get_folio(inode, i, &folio); + if (IS_ERR(kaddr)) continue; - kaddr = page_address(page); de = (struct ufs_dir_entry *)kaddr; kaddr += ufs_last_byte(inode, i) - UFS_DIR_REC_LEN(1); @@ -637,18 +618,40 @@ int ufs_empty_dir(struct inode * inode) } de = ufs_next_entry(sb, de); } - ufs_put_page(page); + folio_release_kmap(folio, kaddr); } return 1; not_empty: - ufs_put_page(page); + folio_release_kmap(folio, kaddr); return 0; } +static int ufs_dir_open(struct inode *inode, struct file *file) +{ + file->private_data = kzalloc(sizeof(u64), GFP_KERNEL); + if (!file->private_data) + return -ENOMEM; + return 0; +} + +static int ufs_dir_release(struct inode *inode, struct file *file) +{ + kfree(file->private_data); + return 0; +} + +static loff_t ufs_dir_llseek(struct file *file, loff_t offset, int whence) +{ + return generic_llseek_cookie(file, offset, whence, + (u64 *)file->private_data); +} + const struct file_operations ufs_dir_operations = { + .open = ufs_dir_open, + .release = ufs_dir_release, .read = generic_read_dir, .iterate_shared = ufs_readdir, .fsync = generic_file_fsync, - .llseek = generic_file_llseek, + .llseek = ufs_dir_llseek, }; diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c index a7bb2e63cdde..5331ae7ebf3e 100644 --- a/fs/ufs/inode.c +++ b/fs/ufs/inode.c @@ -479,9 +479,9 @@ static int ufs_read_folio(struct file *file, struct folio *folio) return block_read_full_folio(folio, ufs_getfrag_block); } -int ufs_prepare_chunk(struct page *page, loff_t pos, unsigned len) +int ufs_prepare_chunk(struct folio *folio, loff_t pos, unsigned len) { - return __block_write_begin(page, pos, len, ufs_getfrag_block); + return __block_write_begin(folio, pos, len, ufs_getfrag_block); } static void ufs_truncate_blocks(struct inode *); @@ -498,11 +498,11 @@ static void ufs_write_failed(struct address_space *mapping, loff_t to) static int ufs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { int ret; - ret = block_write_begin(mapping, pos, len, pagep, ufs_getfrag_block); + ret = block_write_begin(mapping, pos, len, foliop, ufs_getfrag_block); if (unlikely(ret)) ufs_write_failed(mapping, pos + len); @@ -511,11 +511,11 @@ static int ufs_write_begin(struct file *file, struct address_space *mapping, static int ufs_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { int ret; - ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata); + ret = generic_write_end(file, mapping, pos, len, copied, folio, fsdata); if (ret < len) ufs_write_failed(mapping, pos + len); return ret; diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c index 9cad29463791..24bd12186647 100644 --- a/fs/ufs/namei.c +++ b/fs/ufs/namei.c @@ -209,14 +209,14 @@ static int ufs_unlink(struct inode *dir, struct dentry *dentry) { struct inode * inode = d_inode(dentry); struct ufs_dir_entry *de; - struct page *page; + struct folio *folio; int err = -ENOENT; - de = ufs_find_entry(dir, &dentry->d_name, &page); + de = ufs_find_entry(dir, &dentry->d_name, &folio); if (!de) goto out; - err = ufs_delete_entry(dir, de, page); + err = ufs_delete_entry(dir, de, folio); if (err) goto out; @@ -249,28 +249,28 @@ static int ufs_rename(struct mnt_idmap *idmap, struct inode *old_dir, { struct inode *old_inode = d_inode(old_dentry); struct inode *new_inode = d_inode(new_dentry); - struct page *dir_page = NULL; + struct folio *dir_folio = NULL; struct ufs_dir_entry * dir_de = NULL; - struct page *old_page; + struct folio *old_folio; struct ufs_dir_entry *old_de; int err = -ENOENT; if (flags & ~RENAME_NOREPLACE) return -EINVAL; - old_de = ufs_find_entry(old_dir, &old_dentry->d_name, &old_page); + old_de = ufs_find_entry(old_dir, &old_dentry->d_name, &old_folio); if (!old_de) goto out; if (S_ISDIR(old_inode->i_mode)) { err = -EIO; - dir_de = ufs_dotdot(old_inode, &dir_page); + dir_de = ufs_dotdot(old_inode, &dir_folio); if (!dir_de) goto out_old; } if (new_inode) { - struct page *new_page; + struct folio *new_folio; struct ufs_dir_entry *new_de; err = -ENOTEMPTY; @@ -278,10 +278,10 @@ static int ufs_rename(struct mnt_idmap *idmap, struct inode *old_dir, goto out_dir; err = -ENOENT; - new_de = ufs_find_entry(new_dir, &new_dentry->d_name, &new_page); + new_de = ufs_find_entry(new_dir, &new_dentry->d_name, &new_folio); if (!new_de) goto out_dir; - ufs_set_link(new_dir, new_de, new_page, old_inode, 1); + ufs_set_link(new_dir, new_de, new_folio, old_inode, 1); inode_set_ctime_current(new_inode); if (dir_de) drop_nlink(new_inode); @@ -300,29 +300,24 @@ static int ufs_rename(struct mnt_idmap *idmap, struct inode *old_dir, */ inode_set_ctime_current(old_inode); - ufs_delete_entry(old_dir, old_de, old_page); + ufs_delete_entry(old_dir, old_de, old_folio); mark_inode_dirty(old_inode); if (dir_de) { if (old_dir != new_dir) - ufs_set_link(old_inode, dir_de, dir_page, new_dir, 0); - else { - kunmap(dir_page); - put_page(dir_page); - } + ufs_set_link(old_inode, dir_de, dir_folio, new_dir, 0); + else + folio_release_kmap(dir_folio, new_dir); inode_dec_link_count(old_dir); } return 0; out_dir: - if (dir_de) { - kunmap(dir_page); - put_page(dir_page); - } + if (dir_de) + folio_release_kmap(dir_folio, dir_de); out_old: - kunmap(old_page); - put_page(old_page); + folio_release_kmap(old_folio, old_de); out: return err; } diff --git a/fs/ufs/ufs.h b/fs/ufs/ufs.h index 6b499180643b..a2c762cb65a0 100644 --- a/fs/ufs/ufs.h +++ b/fs/ufs/ufs.h @@ -99,15 +99,17 @@ extern void ufs_put_cylinder (struct super_block *, unsigned); /* dir.c */ extern const struct inode_operations ufs_dir_inode_operations; -extern int ufs_add_link (struct dentry *, struct inode *); -extern ino_t ufs_inode_by_name(struct inode *, const struct qstr *); -extern int ufs_make_empty(struct inode *, struct inode *); -extern struct ufs_dir_entry *ufs_find_entry(struct inode *, const struct qstr *, struct page **); -extern int ufs_delete_entry(struct inode *, struct ufs_dir_entry *, struct page *); -extern int ufs_empty_dir (struct inode *); -extern struct ufs_dir_entry *ufs_dotdot(struct inode *, struct page **); -extern void ufs_set_link(struct inode *dir, struct ufs_dir_entry *de, - struct page *page, struct inode *inode, bool update_times); + +int ufs_add_link(struct dentry *, struct inode *); +ino_t ufs_inode_by_name(struct inode *, const struct qstr *); +int ufs_make_empty(struct inode *, struct inode *); +struct ufs_dir_entry *ufs_find_entry(struct inode *, const struct qstr *, + struct folio **); +int ufs_delete_entry(struct inode *, struct ufs_dir_entry *, struct folio *); +int ufs_empty_dir(struct inode *); +struct ufs_dir_entry *ufs_dotdot(struct inode *, struct folio **); +void ufs_set_link(struct inode *dir, struct ufs_dir_entry *de, + struct folio *folio, struct inode *inode, bool update_times); /* file.c */ extern const struct inode_operations ufs_file_inode_operations; diff --git a/fs/ufs/util.h b/fs/ufs/util.h index 0ecd2ed792f5..bf708b68f150 100644 --- a/fs/ufs/util.h +++ b/fs/ufs/util.h @@ -250,9 +250,9 @@ ufs_set_inode_gid(struct super_block *sb, struct ufs_inode *inode, u32 value) } } -extern dev_t ufs_get_inode_dev(struct super_block *, struct ufs_inode_info *); -extern void ufs_set_inode_dev(struct super_block *, struct ufs_inode_info *, dev_t); -extern int ufs_prepare_chunk(struct page *page, loff_t pos, unsigned len); +dev_t ufs_get_inode_dev(struct super_block *, struct ufs_inode_info *); +void ufs_set_inode_dev(struct super_block *, struct ufs_inode_info *, dev_t); +int ufs_prepare_chunk(struct folio *folio, loff_t pos, unsigned len); /* * These functions manipulate ufs buffers diff --git a/fs/vboxsf/file.c b/fs/vboxsf/file.c index fdb4da24d662..b780deb81b02 100644 --- a/fs/vboxsf/file.c +++ b/fs/vboxsf/file.c @@ -300,23 +300,23 @@ static int vboxsf_writepage(struct page *page, struct writeback_control *wbc) static int vboxsf_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned int len, unsigned int copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { struct inode *inode = mapping->host; struct vboxsf_handle *sf_handle = file->private_data; - unsigned int from = pos & ~PAGE_MASK; + size_t from = offset_in_folio(folio, pos); u32 nwritten = len; u8 *buf; int err; - /* zero the stale part of the page if we did a short copy */ - if (!PageUptodate(page) && copied < len) - zero_user(page, from + copied, len - copied); + /* zero the stale part of the folio if we did a short copy */ + if (!folio_test_uptodate(folio) && copied < len) + folio_zero_range(folio, from + copied, len - copied); - buf = kmap(page); + buf = kmap(&folio->page); err = vboxsf_write(sf_handle->root, sf_handle->handle, pos, &nwritten, buf + from); - kunmap(page); + kunmap(&folio->page); if (err) { nwritten = 0; @@ -326,16 +326,16 @@ static int vboxsf_write_end(struct file *file, struct address_space *mapping, /* mtime changed */ VBOXSF_I(inode)->force_restat = 1; - if (!PageUptodate(page) && nwritten == PAGE_SIZE) - SetPageUptodate(page); + if (!folio_test_uptodate(folio) && nwritten == folio_size(folio)) + folio_mark_uptodate(folio); pos += nwritten; if (pos > inode->i_size) i_size_write(inode, pos); out: - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); return nwritten; } @@ -343,7 +343,7 @@ out: /* * Note simple_write_begin does not read the page from disk on partial writes * this is ok since vboxsf_write_end only writes the written parts of the - * page and it does not call SetPageUptodate for partial writes. + * page and it does not call folio_mark_uptodate for partial writes. */ const struct address_space_operations vboxsf_reg_aops = { .read_folio = vboxsf_read_folio, diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index fe2e2c930975..e9fdebaa40ea 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -653,6 +653,9 @@ xfs_alloc_file_space( xfs_bmbt_irec_t imaps[1], *imapp; int error; + if (xfs_is_always_cow_inode(ip)) + return 0; + trace_xfs_alloc_file_space(ip); if (xfs_is_shutdown(mp)) @@ -848,6 +851,14 @@ xfs_free_file_space( if (len <= 0) /* if nothing being freed */ return 0; + /* + * Now AIO and DIO has drained we flush and (if necessary) invalidate + * the cached range over the first operation we are about to run. + */ + error = xfs_flush_unmap_range(ip, offset, len); + if (error) + return error; + startoffset_fsb = XFS_B_TO_FSB(mp, offset); endoffset_fsb = XFS_B_TO_FSBT(mp, offset + len); diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 4cdc54dc9686..f6e4912769a0 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -852,6 +852,192 @@ static inline bool xfs_file_sync_writes(struct file *filp) return false; } +static int +xfs_falloc_newsize( + struct file *file, + int mode, + loff_t offset, + loff_t len, + loff_t *new_size) +{ + struct inode *inode = file_inode(file); + + if ((mode & FALLOC_FL_KEEP_SIZE) || offset + len <= i_size_read(inode)) + return 0; + *new_size = offset + len; + return inode_newsize_ok(inode, *new_size); +} + +static int +xfs_falloc_setsize( + struct file *file, + loff_t new_size) +{ + struct iattr iattr = { + .ia_valid = ATTR_SIZE, + .ia_size = new_size, + }; + + if (!new_size) + return 0; + return xfs_vn_setattr_size(file_mnt_idmap(file), file_dentry(file), + &iattr); +} + +static int +xfs_falloc_collapse_range( + struct file *file, + loff_t offset, + loff_t len) +{ + struct inode *inode = file_inode(file); + loff_t new_size = i_size_read(inode) - len; + int error; + + if (!xfs_is_falloc_aligned(XFS_I(inode), offset, len)) + return -EINVAL; + + /* + * There is no need to overlap collapse range with EOF, in which case it + * is effectively a truncate operation + */ + if (offset + len >= i_size_read(inode)) + return -EINVAL; + + error = xfs_collapse_file_space(XFS_I(inode), offset, len); + if (error) + return error; + return xfs_falloc_setsize(file, new_size); +} + +static int +xfs_falloc_insert_range( + struct file *file, + loff_t offset, + loff_t len) +{ + struct inode *inode = file_inode(file); + loff_t isize = i_size_read(inode); + int error; + + if (!xfs_is_falloc_aligned(XFS_I(inode), offset, len)) + return -EINVAL; + + /* + * New inode size must not exceed ->s_maxbytes, accounting for + * possible signed overflow. + */ + if (inode->i_sb->s_maxbytes - isize < len) + return -EFBIG; + + /* Offset should be less than i_size */ + if (offset >= isize) + return -EINVAL; + + error = xfs_falloc_setsize(file, isize + len); + if (error) + return error; + + /* + * Perform hole insertion now that the file size has been updated so + * that if we crash during the operation we don't leave shifted extents + * past EOF and hence losing access to the data that is contained within + * them. + */ + return xfs_insert_file_space(XFS_I(inode), offset, len); +} + +/* + * Punch a hole and prealloc the range. We use a hole punch rather than + * unwritten extent conversion for two reasons: + * + * 1.) Hole punch handles partial block zeroing for us. + * 2.) If prealloc returns ENOSPC, the file range is still zero-valued by + * virtue of the hole punch. + */ +static int +xfs_falloc_zero_range( + struct file *file, + int mode, + loff_t offset, + loff_t len) +{ + struct inode *inode = file_inode(file); + unsigned int blksize = i_blocksize(inode); + loff_t new_size = 0; + int error; + + trace_xfs_zero_file_space(XFS_I(inode)); + + error = xfs_falloc_newsize(file, mode, offset, len, &new_size); + if (error) + return error; + + error = xfs_free_file_space(XFS_I(inode), offset, len); + if (error) + return error; + + len = round_up(offset + len, blksize) - round_down(offset, blksize); + offset = round_down(offset, blksize); + error = xfs_alloc_file_space(XFS_I(inode), offset, len); + if (error) + return error; + return xfs_falloc_setsize(file, new_size); +} + +static int +xfs_falloc_unshare_range( + struct file *file, + int mode, + loff_t offset, + loff_t len) +{ + struct inode *inode = file_inode(file); + loff_t new_size = 0; + int error; + + error = xfs_falloc_newsize(file, mode, offset, len, &new_size); + if (error) + return error; + + error = xfs_reflink_unshare(XFS_I(inode), offset, len); + if (error) + return error; + + error = xfs_alloc_file_space(XFS_I(inode), offset, len); + if (error) + return error; + return xfs_falloc_setsize(file, new_size); +} + +static int +xfs_falloc_allocate_range( + struct file *file, + int mode, + loff_t offset, + loff_t len) +{ + struct inode *inode = file_inode(file); + loff_t new_size = 0; + int error; + + /* + * If always_cow mode we can't use preallocations and thus should not + * create them. + */ + if (xfs_is_always_cow_inode(XFS_I(inode))) + return -EOPNOTSUPP; + + error = xfs_falloc_newsize(file, mode, offset, len, &new_size); + if (error) + return error; + + error = xfs_alloc_file_space(XFS_I(inode), offset, len); + if (error) + return error; + return xfs_falloc_setsize(file, new_size); +} + #define XFS_FALLOC_FL_SUPPORTED \ (FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | \ FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE | \ @@ -868,8 +1054,6 @@ xfs_file_fallocate( struct xfs_inode *ip = XFS_I(inode); long error; uint iolock = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL; - loff_t new_size = 0; - bool do_file_insert = false; if (!S_ISREG(inode->i_mode)) return -EINVAL; @@ -890,156 +1074,35 @@ xfs_file_fallocate( */ inode_dio_wait(inode); - /* - * Now AIO and DIO has drained we flush and (if necessary) invalidate - * the cached range over the first operation we are about to run. - * - * We care about zero and collapse here because they both run a hole - * punch over the range first. Because that can zero data, and the range - * of invalidation for the shift operations is much larger, we still do - * the required flush for collapse in xfs_prepare_shift(). - * - * Insert has the same range requirements as collapse, and we extend the - * file first which can zero data. Hence insert has the same - * flush/invalidate requirements as collapse and so they are both - * handled at the right time by xfs_prepare_shift(). - */ - if (mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE | - FALLOC_FL_COLLAPSE_RANGE)) { - error = xfs_flush_unmap_range(ip, offset, len); - if (error) - goto out_unlock; - } - error = file_modified(file); if (error) goto out_unlock; - if (mode & FALLOC_FL_PUNCH_HOLE) { + switch (mode & FALLOC_FL_MODE_MASK) { + case FALLOC_FL_PUNCH_HOLE: error = xfs_free_file_space(ip, offset, len); - if (error) - goto out_unlock; - } else if (mode & FALLOC_FL_COLLAPSE_RANGE) { - if (!xfs_is_falloc_aligned(ip, offset, len)) { - error = -EINVAL; - goto out_unlock; - } - - /* - * There is no need to overlap collapse range with EOF, - * in which case it is effectively a truncate operation - */ - if (offset + len >= i_size_read(inode)) { - error = -EINVAL; - goto out_unlock; - } - - new_size = i_size_read(inode) - len; - - error = xfs_collapse_file_space(ip, offset, len); - if (error) - goto out_unlock; - } else if (mode & FALLOC_FL_INSERT_RANGE) { - loff_t isize = i_size_read(inode); - - if (!xfs_is_falloc_aligned(ip, offset, len)) { - error = -EINVAL; - goto out_unlock; - } - - /* - * New inode size must not exceed ->s_maxbytes, accounting for - * possible signed overflow. - */ - if (inode->i_sb->s_maxbytes - isize < len) { - error = -EFBIG; - goto out_unlock; - } - new_size = isize + len; - - /* Offset should be less than i_size */ - if (offset >= isize) { - error = -EINVAL; - goto out_unlock; - } - do_file_insert = true; - } else { - if (!(mode & FALLOC_FL_KEEP_SIZE) && - offset + len > i_size_read(inode)) { - new_size = offset + len; - error = inode_newsize_ok(inode, new_size); - if (error) - goto out_unlock; - } - - if (mode & FALLOC_FL_ZERO_RANGE) { - /* - * Punch a hole and prealloc the range. We use a hole - * punch rather than unwritten extent conversion for two - * reasons: - * - * 1.) Hole punch handles partial block zeroing for us. - * 2.) If prealloc returns ENOSPC, the file range is - * still zero-valued by virtue of the hole punch. - */ - unsigned int blksize = i_blocksize(inode); - - trace_xfs_zero_file_space(ip); - - error = xfs_free_file_space(ip, offset, len); - if (error) - goto out_unlock; - - len = round_up(offset + len, blksize) - - round_down(offset, blksize); - offset = round_down(offset, blksize); - } else if (mode & FALLOC_FL_UNSHARE_RANGE) { - error = xfs_reflink_unshare(ip, offset, len); - if (error) - goto out_unlock; - } else { - /* - * If always_cow mode we can't use preallocations and - * thus should not create them. - */ - if (xfs_is_always_cow_inode(ip)) { - error = -EOPNOTSUPP; - goto out_unlock; - } - } - - if (!xfs_is_always_cow_inode(ip)) { - error = xfs_alloc_file_space(ip, offset, len); - if (error) - goto out_unlock; - } - } - - /* Change file size if needed */ - if (new_size) { - struct iattr iattr; - - iattr.ia_valid = ATTR_SIZE; - iattr.ia_size = new_size; - error = xfs_vn_setattr_size(file_mnt_idmap(file), - file_dentry(file), &iattr); - if (error) - goto out_unlock; - } - - /* - * Perform hole insertion now that the file size has been - * updated so that if we crash during the operation we don't - * leave shifted extents past EOF and hence losing access to - * the data that is contained within them. - */ - if (do_file_insert) { - error = xfs_insert_file_space(ip, offset, len); - if (error) - goto out_unlock; + break; + case FALLOC_FL_COLLAPSE_RANGE: + error = xfs_falloc_collapse_range(file, offset, len); + break; + case FALLOC_FL_INSERT_RANGE: + error = xfs_falloc_insert_range(file, offset, len); + break; + case FALLOC_FL_ZERO_RANGE: + error = xfs_falloc_zero_range(file, mode, offset, len); + break; + case FALLOC_FL_UNSHARE_RANGE: + error = xfs_falloc_unshare_range(file, mode, offset, len); + break; + case FALLOC_FL_ALLOCATE_RANGE: + error = xfs_falloc_allocate_range(file, mode, offset, len); + break; + default: + error = -EOPNOTSUPP; + break; } - if (xfs_file_sync_writes(file)) + if (!error && xfs_file_sync_writes(file)) error = xfs_log_force_inode(ip); out_unlock: |