From 034dd340b08be1f2f0477ad16131d609f9dbd53c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 30 Aug 2026 09:22:00 -0700 Subject: Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace Pull tracing fixes from Steven Rostedt: - Fix error output of boot instance creation failure Currently if a boot instance creation fails, instead of printing out the name of the instance that failed, it prints "(null)". That is because it prints "cur_str" that had already been processed by strsep(). Print the saved name instead. While at it, print the error code of the failure. - Fix use-after-free for same named historgrams Histograms can be named so that they can be used in multiple events. But if the named histogram has a variable attached, the second event that uses the named histogram which duplicates it and needs to free the original after duplication leaves the old variable in place and still visible. If another histogram uses than variable, it will use the stale one which will try to reference the freed duplicate histogram and crash the kernel. Free the duplicate variables along with the duplicated histogram data. - Check return value of kthread_run() in event self test The events self tests uses a kthread for testing but does not check if it succeeded in creating a kthread. If the kthread creation were to fail, the code will still try to call kthread_stop() on the error returned. - Fix race between reading trace_pipe and updating subbuffer size If a user is reading the trace_pipe file at the same time they update the ring buffer sub-buffer size, can cause the trace_pipe read to read stale data. Add trace_access_lock() around updating the ring buffer sub-buffer size. - Fix eventfs_inode on failure path in creation of the events directory In the creation of the "events" directory, if after allocating the eventfs_inode a failure is detected, it calls cleanup_ei() which calls free_ei(). The free_ei() will test if eventfs_inode being freed has no children. It is a bug if it does. But on the failure case of the creation of the "events" directory, the children lists have not yet been initialized and the free will trigger a warning because list_empty() on an uninitialized list returns false. Move the initialization into init_ei() where it makes more sense and makes sure that a created eventfs_inode has its lists initialized upon creation. - Check return value of kthread_run() in ftrace direct sample code The sample code that shows how to use the ftrace direct calls does not test the return of kthread_run() to see if it succeeds. Return a failure if the kthread_run() doesn't succeed. - Clear user events state on fork in case of alloc failure On fork, the child gets a pointer to the parent's user events state. It makes a copy of it then updates the child's pointer to it. But if the allocation fails, the duplication function leaves the child with a pointer to its parent's descriptor. When the child cleans up its data, it will free the parent's descriptor while the parent is still using it. In the duplication function, set the child's user_event_mm to NULL before testing if the allocation succeeded, and when it exits it will not free the parent's descriptor. - Fix retry exhaustion in simple ring buffer reader swap simple_ring_buffer_swap_reader_page() starts with retry set to 8 and post-decrements it only after a failed link replacement. On the final attempt, a successful replacement leaves retry at zero, while a failed replacement leaves it at -1. But the check for success expects the retry value to be non-zero and exits with an error on zero. This is the opposite result. Fix it. - Fail nicely when the remote swap_reader_page() returns an error Currently, if the swap_reader_page() of a remote buffer fails, it triggers a WARN_ON_ONCE() and continues normally. Instead, have it exit with an error and a pr_warn() print instead of a full WARNING. * tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: ring-buffer: Stop remote reader update when page swap fails tracing: Fix retry exhaustion in simple ring buffer reader swap tracing/user_events: Clear copied tracing state before fork duplication samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify eventfs: Initialize ei->children and ei->list in init_ei() tracing: Fix use-after-free in trace_pipe read on sub-buffer order change tracing: Fix crash passing ERR_PTR to kthread_stop() tracing: Fix use-after-free with same-name named triggers tracing: Fix logged instance name on creation failure --- fs/exportfs/Makefile | 7 + fs/exportfs/expfs.c | 610 +++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 617 insertions(+) create mode 100644 fs/exportfs/Makefile create mode 100644 fs/exportfs/expfs.c (limited to 'fs/exportfs') diff --git a/fs/exportfs/Makefile b/fs/exportfs/Makefile new file mode 100644 index 000000000..a04a8af83 --- /dev/null +++ b/fs/exportfs/Makefile @@ -0,0 +1,7 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# Makefile for the filesystem export support routines. + +obj-$(CONFIG_EXPORTFS) += exportfs.o + +exportfs-objs := expfs.o diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c new file mode 100644 index 000000000..eafd99507 --- /dev/null +++ b/fs/exportfs/expfs.c @@ -0,0 +1,610 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) Neil Brown 2002 + * Copyright (C) Christoph Hellwig 2007 + * + * This file contains the code mapping from inodes to NFS file handles, + * and for mapping back from file handles to dentries. + * + * For details on why we do all the strange and hairy things in here + * take a look at Documentation/filesystems/nfs/exporting.rst. + */ +#include +#include +#include +#include +#include +#include +#include +#include + +#define dprintk(fmt, args...) pr_debug(fmt, ##args) + + +static int get_name(const struct path *path, char *name, struct dentry *child); + + +static int exportfs_get_name(struct vfsmount *mnt, struct dentry *dir, + char *name, struct dentry *child) +{ + const struct export_operations *nop = dir->d_sb->s_export_op; + struct path path = {.mnt = mnt, .dentry = dir}; + + if (nop->get_name) + return nop->get_name(dir, name, child); + else + return get_name(&path, name, child); +} + +/* + * Check if the dentry or any of it's aliases is acceptable. + */ +static struct dentry * +find_acceptable_alias(struct dentry *result, + int (*acceptable)(void *context, struct dentry *dentry), + void *context) +{ + struct dentry *dentry, *toput = NULL; + struct inode *inode; + + if (acceptable(context, result)) + return result; + + inode = result->d_inode; + spin_lock(&inode->i_lock); + for_each_alias(dentry, inode) { + if (!dget_alias_ilocked(dentry)) + continue; + spin_unlock(&inode->i_lock); + dput(toput); + if (dentry != result && acceptable(context, dentry)) { + dput(result); + return dentry; + } + spin_lock(&inode->i_lock); + toput = dentry; + } + spin_unlock(&inode->i_lock); + + dput(toput); + return NULL; +} + +static bool dentry_connected(struct dentry *dentry) +{ + dget(dentry); + while (dentry->d_flags & DCACHE_DISCONNECTED) { + struct dentry *parent = dget_parent(dentry); + + dput(dentry); + if (dentry == parent) { + dput(parent); + return false; + } + dentry = parent; + } + dput(dentry); + return true; +} + +static void clear_disconnected(struct dentry *dentry) +{ + dget(dentry); + while (dentry->d_flags & DCACHE_DISCONNECTED) { + struct dentry *parent = dget_parent(dentry); + + WARN_ON_ONCE(IS_ROOT(dentry)); + + spin_lock(&dentry->d_lock); + dentry->d_flags &= ~DCACHE_DISCONNECTED; + spin_unlock(&dentry->d_lock); + + dput(dentry); + dentry = parent; + } + dput(dentry); +} + +/* + * Reconnect a directory dentry with its parent. + * + * This can return a dentry, or NULL, or an error. + * + * In the first case the returned dentry is the parent of the given + * dentry, and may itself need to be reconnected to its parent. + * + * In the NULL case, a concurrent VFS operation has either renamed or + * removed this directory. The concurrent operation has reconnected our + * dentry, so we no longer need to. + */ +static struct dentry *reconnect_one(struct vfsmount *mnt, + struct dentry *dentry, char *nbuf) +{ + struct dentry *parent; + struct dentry *tmp; + int err; + + parent = ERR_PTR(-EACCES); + if (mnt->mnt_sb->s_export_op->get_parent) + parent = mnt->mnt_sb->s_export_op->get_parent(dentry); + + if (IS_ERR(parent)) { + dprintk("get_parent of %llu failed, err %ld\n", + dentry->d_inode->i_ino, PTR_ERR(parent)); + return parent; + } + + dprintk("%s: find name of %llu in %llu\n", __func__, + dentry->d_inode->i_ino, parent->d_inode->i_ino); + err = exportfs_get_name(mnt, parent, nbuf, dentry); + if (err == -ENOENT) + goto out_reconnected; + if (err) + goto out_err; + dprintk("%s: found name: %s\n", __func__, nbuf); + tmp = lookup_one_unlocked(mnt_idmap(mnt), &QSTR(nbuf), parent); + if (IS_ERR(tmp)) { + dprintk("lookup failed: %ld\n", PTR_ERR(tmp)); + err = PTR_ERR(tmp); + goto out_err; + } + if (tmp != dentry) { + /* + * Somebody has renamed it since exportfs_get_name(); + * great, since it could've only been renamed if it + * got looked up and thus connected, and it would + * remain connected afterwards. We are done. + */ + dput(tmp); + goto out_reconnected; + } + dput(tmp); + if (IS_ROOT(dentry)) { + err = -ESTALE; + goto out_err; + } + return parent; + +out_err: + dput(parent); + return ERR_PTR(err); +out_reconnected: + dput(parent); + /* + * Someone must have renamed our entry into another parent, in + * which case it has been reconnected by the rename. + * + * Or someone removed it entirely, in which case filehandle + * lookup will succeed but the directory is now IS_DEAD and + * subsequent operations on it will fail. + * + * Alternatively, maybe there was no race at all, and the + * filesystem is just corrupt and gave us a parent that doesn't + * actually contain any entry pointing to this inode. So, + * double check that this worked and return -ESTALE if not: + */ + if (!dentry_connected(dentry)) + return ERR_PTR(-ESTALE); + return NULL; +} + +/* + * Make sure target_dir is fully connected to the dentry tree. + * + * On successful return, DCACHE_DISCONNECTED will be cleared on + * target_dir, and target_dir->d_parent->...->d_parent will reach the + * root of the filesystem. + * + * Whenever DCACHE_DISCONNECTED is unset, target_dir is fully connected. + * But the converse is not true: target_dir may have DCACHE_DISCONNECTED + * set but already be connected. In that case we'll verify the + * connection to root and then clear the flag. + * + * Note that target_dir could be removed by a concurrent operation. In + * that case reconnect_path may still succeed with target_dir fully + * connected, but further operations using the filehandle will fail when + * necessary (due to S_DEAD being set on the directory). + */ +static int +reconnect_path(struct vfsmount *mnt, struct dentry *target_dir, char *nbuf) +{ + struct dentry *dentry, *parent; + + dentry = dget(target_dir); + + while (dentry->d_flags & DCACHE_DISCONNECTED) { + BUG_ON(dentry == mnt->mnt_sb->s_root); + + if (IS_ROOT(dentry)) + parent = reconnect_one(mnt, dentry, nbuf); + else + parent = dget_parent(dentry); + + if (!parent) + break; + dput(dentry); + if (IS_ERR(parent)) + return PTR_ERR(parent); + dentry = parent; + } + dput(dentry); + clear_disconnected(target_dir); + return 0; +} + +struct getdents_callback { + struct dir_context ctx; + char *name; /* name that was found. It already points to a + buffer NAME_MAX+1 is size */ + u64 ino; /* the inum we are looking for */ + int found; /* inode matched? */ + int sequence; /* sequence counter */ +}; + +/* + * A rather strange filldir function to capture + * the name matching the specified inode number. + */ +static bool filldir_one(struct dir_context *ctx, const char *name, int len, + loff_t pos, u64 ino, unsigned int d_type) +{ + struct getdents_callback *buf = + container_of(ctx, struct getdents_callback, ctx); + + buf->sequence++; + if (buf->ino == ino && len <= NAME_MAX && + !name_is_dot_dotdot(name, len)) { + memcpy(buf->name, name, len); + buf->name[len] = '\0'; + buf->found = 1; + return false; // no more + } + return true; +} + +/** + * get_name - default export_operations->get_name function + * @path: the directory in which to find a name + * @name: a pointer to a %NAME_MAX+1 char buffer to store the name + * @child: the dentry for the child directory. + * + * calls readdir on the parent until it finds an entry with + * the same inode number as the child, and returns that. + */ +static int get_name(const struct path *path, char *name, struct dentry *child) +{ + const struct cred *cred = current_cred(); + struct inode *dir = path->dentry->d_inode; + int error; + struct file *file; + struct kstat stat; + struct path child_path = { + .mnt = path->mnt, + .dentry = child, + }; + struct getdents_callback buffer = { + .ctx.actor = filldir_one, + .ctx.count = INT_MAX, + .name = name, + }; + + error = -ENOTDIR; + if (!dir || !S_ISDIR(dir->i_mode)) + goto out; + error = -EINVAL; + if (!dir->i_fop) + goto out; + /* + * inode->i_ino is unsigned long, kstat->ino is u64, so the + * former would be insufficient on 32-bit hosts when the + * filesystem supports 64-bit inode numbers. So we need to + * actually call ->getattr, not just read i_ino: + */ + error = vfs_getattr_nosec(&child_path, &stat, + STATX_INO, AT_STATX_SYNC_AS_STAT); + if (error) + return error; + buffer.ino = stat.ino; + /* + * Open the directory ... + */ + file = dentry_open(path, O_RDONLY, cred); + error = PTR_ERR(file); + if (IS_ERR(file)) + goto out; + + error = -EINVAL; + if (!file->f_op->iterate_shared) + goto out_close; + + buffer.sequence = 0; + while (1) { + int old_seq = buffer.sequence; + + error = iterate_dir(file, &buffer.ctx); + if (buffer.found) { + error = 0; + break; + } + + if (error < 0) + break; + + error = -ENOENT; + if (old_seq == buffer.sequence) + break; + } + +out_close: + fput(file); +out: + return error; +} + +#define FILEID_INO64_GEN_LEN 3 + +/** + * exportfs_encode_ino64_fid - encode non-decodeable 64bit ino file id + * @inode: the object to encode + * @fid: where to store the file handle fragment + * @max_len: maximum length to store there (in 4 byte units) + * + * This generic function is used to encode a non-decodeable file id for + * fanotify for filesystems that do not support NFS export. + */ +static int exportfs_encode_ino64_fid(struct inode *inode, struct fid *fid, + int *max_len) +{ + if (*max_len < FILEID_INO64_GEN_LEN) { + *max_len = FILEID_INO64_GEN_LEN; + return FILEID_INVALID; + } + + fid->i64.ino = inode->i_ino; + fid->i64.gen = inode->i_generation; + *max_len = FILEID_INO64_GEN_LEN; + + return FILEID_INO64_GEN; +} + +/** + * exportfs_encode_inode_fh - encode a file handle from inode + * @inode: the object to encode + * @fid: where to store the file handle fragment + * @max_len: maximum length to store there + * @parent: parent directory inode, if wanted + * @flags: properties of the requested file handle + * + * Returns an enum fid_type or a negative errno. + */ +int exportfs_encode_inode_fh(struct inode *inode, struct fid *fid, + int *max_len, struct inode *parent, int flags) +{ + const struct export_operations *nop = inode->i_sb->s_export_op; + enum fid_type type; + + if (!exportfs_can_encode_fh(nop, flags)) + return -EOPNOTSUPP; + + if (!nop && (flags & EXPORT_FH_FID)) + type = exportfs_encode_ino64_fid(inode, fid, max_len); + else + type = nop->encode_fh(inode, fid->raw, max_len, parent); + + if (type > 0 && FILEID_USER_FLAGS(type)) { + pr_warn_once("%s: unexpected fh type value 0x%x from fstype %s.\n", + __func__, type, inode->i_sb->s_type->name); + return -EINVAL; + } + + return type; + +} +EXPORT_SYMBOL_GPL(exportfs_encode_inode_fh); + +/** + * exportfs_encode_fh - encode a file handle from dentry + * @dentry: the object to encode + * @fid: where to store the file handle fragment + * @max_len: maximum length to store there + * @flags: properties of the requested file handle + * + * Returns an enum fid_type or a negative errno. + */ +int exportfs_encode_fh(struct dentry *dentry, struct fid *fid, int *max_len, + int flags) +{ + int error; + struct dentry *p = NULL; + struct inode *inode = dentry->d_inode, *parent = NULL; + + if ((flags & EXPORT_FH_CONNECTABLE) && !S_ISDIR(inode->i_mode)) { + p = dget_parent(dentry); + /* + * note that while p might've ceased to be our parent already, + * it's still pinned by and still positive. + */ + parent = p->d_inode; + } + + error = exportfs_encode_inode_fh(inode, fid, max_len, parent, flags); + dput(p); + + return error; +} +EXPORT_SYMBOL_GPL(exportfs_encode_fh); + +struct dentry * +exportfs_decode_fh_raw(struct vfsmount *mnt, struct fid *fid, int fh_len, + int fileid_type, unsigned int flags, + int (*acceptable)(void *, struct dentry *), + void *context) +{ + const struct export_operations *nop = mnt->mnt_sb->s_export_op; + struct dentry *result, *alias; + char nbuf[NAME_MAX+1]; + int err; + + if (fileid_type < 0 || FILEID_USER_FLAGS(fileid_type)) + return ERR_PTR(-EINVAL); + + /* + * Try to get any dentry for the given file handle from the filesystem. + */ + if (!exportfs_can_decode_fh(nop)) + return ERR_PTR(-ESTALE); + result = nop->fh_to_dentry(mnt->mnt_sb, fid, fh_len, fileid_type); + if (IS_ERR_OR_NULL(result)) + return result; + + if ((flags & EXPORT_FH_DIR_ONLY) && !d_is_dir(result)) { + err = -ENOTDIR; + goto err_result; + } + + /* + * If no acceptance criteria was specified by caller, a disconnected + * dentry is also accepatable. Callers may use this mode to query if + * file handle is stale or to get a reference to an inode without + * risking the high overhead caused by directory reconnect. + */ + if (!acceptable) + return result; + + if (d_is_dir(result)) { + /* + * This request is for a directory. + * + * On the positive side there is only one dentry for each + * directory inode. On the negative side this implies that we + * to ensure our dentry is connected all the way up to the + * filesystem root. + */ + if (result->d_flags & DCACHE_DISCONNECTED) { + err = reconnect_path(mnt, result, nbuf); + if (err) + goto err_result; + } + + if (!acceptable(context, result)) { + err = -EACCES; + goto err_result; + } + + return result; + } else { + /* + * It's not a directory. Life is a little more complicated. + */ + struct dentry *target_dir, *nresult; + + /* + * See if either the dentry we just got from the filesystem + * or any alias for it is acceptable. This is always true + * if this filesystem is exported without the subtreecheck + * option. If the filesystem is exported with the subtree + * check option there's a fair chance we need to look at + * the parent directory in the file handle and make sure + * it's connected to the filesystem root. + */ + alias = find_acceptable_alias(result, acceptable, context); + if (alias) + return alias; + + /* + * Try to extract a dentry for the parent directory from the + * file handle. If this fails we'll have to give up. + */ + err = -ESTALE; + if (!nop->fh_to_parent) + goto err_result; + + target_dir = nop->fh_to_parent(mnt->mnt_sb, fid, + fh_len, fileid_type); + if (!target_dir) + goto err_result; + err = PTR_ERR(target_dir); + if (IS_ERR(target_dir)) + goto err_result; + + /* + * And as usual we need to make sure the parent directory is + * connected to the filesystem root. The VFS really doesn't + * like disconnected directories.. + */ + err = reconnect_path(mnt, target_dir, nbuf); + if (err) { + dput(target_dir); + goto err_result; + } + + /* + * Now that we've got both a well-connected parent and a + * dentry for the inode we're after, make sure that our + * inode is actually connected to the parent. + */ + err = exportfs_get_name(mnt, target_dir, nbuf, result); + if (err) { + dput(target_dir); + goto err_result; + } + + nresult = lookup_one_unlocked(mnt_idmap(mnt), &QSTR(nbuf), target_dir); + if (!IS_ERR(nresult)) { + if (unlikely(nresult->d_inode != result->d_inode)) { + dput(nresult); + nresult = ERR_PTR(-ESTALE); + } + } + /* + * At this point we are done with the parent, but it's pinned + * by the child dentry anyway. + */ + dput(target_dir); + + if (IS_ERR(nresult)) { + err = PTR_ERR(nresult); + goto err_result; + } + dput(result); + result = nresult; + + /* + * And finally make sure the dentry is actually acceptable + * to NFSD. + */ + alias = find_acceptable_alias(result, acceptable, context); + if (!alias) { + err = -EACCES; + goto err_result; + } + + return alias; + } + + err_result: + dput(result); + return ERR_PTR(err); +} +EXPORT_SYMBOL_GPL(exportfs_decode_fh_raw); + +struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid, + int fh_len, int fileid_type, + int (*acceptable)(void *, struct dentry *), + void *context) +{ + struct dentry *ret; + + ret = exportfs_decode_fh_raw(mnt, fid, fh_len, fileid_type, 0, + acceptable, context); + if (IS_ERR_OR_NULL(ret)) { + if (ret == ERR_PTR(-ENOMEM)) + return ret; + return ERR_PTR(-ESTALE); + } + return ret; +} +EXPORT_SYMBOL_GPL(exportfs_decode_fh); + +MODULE_DESCRIPTION("Code mapping from inodes to file handles"); +MODULE_LICENSE("GPL"); -- cgit v1.3.1