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/ecryptfs/file.c | 442 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 442 insertions(+) create mode 100644 fs/ecryptfs/file.c (limited to 'fs/ecryptfs/file.c') diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c new file mode 100644 index 000000000..49b0fbe04 --- /dev/null +++ b/fs/ecryptfs/file.c @@ -0,0 +1,442 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * eCryptfs: Linux filesystem encryption layer + * + * Copyright (C) 1997-2004 Erez Zadok + * Copyright (C) 2001-2004 Stony Brook University + * Copyright (C) 2004-2007 International Business Machines Corp. + * Author(s): Michael A. Halcrow + * Michael C. Thompson + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include "ecryptfs_kernel.h" + +/* + * ecryptfs_read_update_atime + * + * generic_file_read updates the atime of upper layer inode. But, it + * doesn't give us a chance to update the atime of the lower layer + * inode. This function is a wrapper to generic_file_read. It + * updates the atime of the lower level inode if generic_file_read + * returns without any errors. This is to be used only for file reads. + * The function to be used for directory reads is ecryptfs_read. + */ +static ssize_t ecryptfs_read_update_atime(struct kiocb *iocb, + struct iov_iter *to) +{ + ssize_t rc; + struct file *file = iocb->ki_filp; + + rc = generic_file_read_iter(iocb, to); + if (rc >= 0) { + struct path path = ecryptfs_lower_path(file->f_path.dentry); + touch_atime(&path); + } + return rc; +} + +/* + * ecryptfs_splice_read_update_atime + * + * filemap_splice_read updates the atime of upper layer inode. But, it + * doesn't give us a chance to update the atime of the lower layer inode. This + * function is a wrapper to generic_file_read. It updates the atime of the + * lower level inode if generic_file_read returns without any errors. This is + * to be used only for file reads. The function to be used for directory reads + * is ecryptfs_read. + */ +static ssize_t ecryptfs_splice_read_update_atime(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, + size_t len, unsigned int flags) +{ + ssize_t rc; + + rc = filemap_splice_read(in, ppos, pipe, len, flags); + if (rc >= 0) { + struct path path = ecryptfs_lower_path(in->f_path.dentry); + touch_atime(&path); + } + return rc; +} + +struct ecryptfs_getdents_callback { + struct dir_context ctx; + struct dir_context *caller; + struct super_block *sb; + int filldir_called; + int entries_written; +}; + +/* Inspired by generic filldir in fs/readdir.c */ +static bool +ecryptfs_filldir(struct dir_context *ctx, const char *lower_name, + int lower_namelen, loff_t offset, u64 ino, unsigned int d_type) +{ + struct ecryptfs_getdents_callback *buf = + container_of(ctx, struct ecryptfs_getdents_callback, ctx); + size_t name_size; + char *name; + int err; + bool res; + + buf->filldir_called++; + err = ecryptfs_decode_and_decrypt_filename(&name, &name_size, + buf->sb, lower_name, + lower_namelen); + if (err) { + if (err != -EINVAL) { + ecryptfs_printk(KERN_DEBUG, + "%s: Error attempting to decode and decrypt filename [%s]; rc = [%d]\n", + __func__, lower_name, err); + return false; + } + + /* Mask -EINVAL errors as these are most likely due a plaintext + * filename present in the lower filesystem despite filename + * encryption being enabled. One unavoidable example would be + * the "lost+found" dentry in the root directory of an Ext4 + * filesystem. + */ + return true; + } + + buf->caller->pos = buf->ctx.pos; + res = dir_emit(buf->caller, name, name_size, ino, d_type); + kfree(name); + if (res) + buf->entries_written++; + return res; +} + +/** + * ecryptfs_readdir + * @file: The eCryptfs directory file + * @ctx: The actor to feed the entries to + */ +static int ecryptfs_readdir(struct file *file, struct dir_context *ctx) +{ + int rc; + struct file *lower_file; + struct inode *inode = file_inode(file); + struct ecryptfs_getdents_callback buf = { + .ctx.actor = ecryptfs_filldir, + .caller = ctx, + .sb = inode->i_sb, + }; + lower_file = ecryptfs_file_to_lower(file); + rc = iterate_dir(lower_file, &buf.ctx); + ctx->pos = buf.ctx.pos; + if (rc >= 0 && (buf.entries_written || !buf.filldir_called)) + fsstack_copy_attr_atime(inode, file_inode(lower_file)); + return rc; +} + +struct kmem_cache *ecryptfs_file_info_cache; + +static int read_or_initialize_metadata(struct dentry *dentry) +{ + struct inode *inode = d_inode(dentry); + struct ecryptfs_mount_crypt_stat *mount_crypt_stat; + struct ecryptfs_crypt_stat *crypt_stat; + int rc; + + crypt_stat = &ecryptfs_inode_to_private(inode)->crypt_stat; + mount_crypt_stat = &ecryptfs_superblock_to_private( + inode->i_sb)->mount_crypt_stat; + mutex_lock(&crypt_stat->cs_mutex); + + if (crypt_stat->flags & ECRYPTFS_POLICY_APPLIED && + crypt_stat->flags & ECRYPTFS_KEY_VALID) { + rc = 0; + goto out; + } + + rc = ecryptfs_read_metadata(dentry); + if (!rc) + goto out; + + if (mount_crypt_stat->flags & ECRYPTFS_PLAINTEXT_PASSTHROUGH_ENABLED) { + crypt_stat->flags &= ~(ECRYPTFS_I_SIZE_INITIALIZED + | ECRYPTFS_ENCRYPTED); + rc = 0; + goto out; + } + + if (!(mount_crypt_stat->flags & ECRYPTFS_XATTR_METADATA_ENABLED) && + !i_size_read(ecryptfs_inode_to_lower(inode))) { + rc = ecryptfs_initialize_file(dentry, inode); + if (!rc) + goto out; + } + + rc = -EIO; +out: + mutex_unlock(&crypt_stat->cs_mutex); + return rc; +} + +static int ecryptfs_mmap(struct file *file, struct vm_area_struct *vma) +{ + struct file *lower_file = ecryptfs_file_to_lower(file); + /* + * Don't allow mmap on top of file systems that don't support it + * natively. If FILESYSTEM_MAX_STACK_DEPTH > 2 or ecryptfs + * allows recursive mounting, this will need to be extended. + */ + if (!can_mmap_file(lower_file)) + return -ENODEV; + return generic_file_mmap(file, vma); +} + +/** + * ecryptfs_open + * @inode: inode specifying file to open + * @file: Structure to return filled in + * + * Opens the file specified by inode. + * + * Returns zero on success; non-zero otherwise + */ +static int ecryptfs_open(struct inode *inode, struct file *file) +{ + int rc = 0; + struct ecryptfs_crypt_stat *crypt_stat = NULL; + struct dentry *ecryptfs_dentry = file->f_path.dentry; + /* Private value of ecryptfs_dentry allocated in + * ecryptfs_lookup() */ + struct ecryptfs_file_info *file_info; + + /* Released in ecryptfs_release or end of function if failure */ + file_info = kmem_cache_zalloc(ecryptfs_file_info_cache, GFP_KERNEL); + ecryptfs_set_file_private(file, file_info); + if (!file_info) { + ecryptfs_printk(KERN_ERR, + "Error attempting to allocate memory\n"); + rc = -ENOMEM; + goto out; + } + crypt_stat = &ecryptfs_inode_to_private(inode)->crypt_stat; + mutex_lock(&crypt_stat->cs_mutex); + if (!(crypt_stat->flags & ECRYPTFS_POLICY_APPLIED)) { + ecryptfs_printk(KERN_DEBUG, "Setting flags for stat...\n"); + /* Policy code enabled in future release */ + crypt_stat->flags |= (ECRYPTFS_POLICY_APPLIED + | ECRYPTFS_ENCRYPTED); + } + mutex_unlock(&crypt_stat->cs_mutex); + rc = ecryptfs_get_lower_file(ecryptfs_dentry, inode); + if (rc) { + printk(KERN_ERR "%s: Error attempting to initialize " + "the lower file for the dentry with name " + "[%pd]; rc = [%d]\n", __func__, + ecryptfs_dentry, rc); + goto out_free; + } + if ((ecryptfs_inode_to_private(inode)->lower_file->f_flags & O_ACCMODE) + == O_RDONLY && (file->f_flags & O_ACCMODE) != O_RDONLY) { + rc = -EPERM; + printk(KERN_WARNING "%s: Lower file is RO; eCryptfs " + "file must hence be opened RO\n", __func__); + goto out_put; + } + ecryptfs_set_file_lower( + file, ecryptfs_inode_to_private(inode)->lower_file); + rc = read_or_initialize_metadata(ecryptfs_dentry); + if (rc) + goto out_put; + ecryptfs_printk(KERN_DEBUG, "inode w/ addr = [0x%p], i_ino = " + "[0x%.16llx] size: [0x%.16llx]\n", inode, inode->i_ino, + (unsigned long long)i_size_read(inode)); + goto out; +out_put: + ecryptfs_put_lower_file(inode); +out_free: + kmem_cache_free(ecryptfs_file_info_cache, + ecryptfs_file_to_private(file)); +out: + return rc; +} + +/** + * ecryptfs_dir_open + * @inode: inode specifying file to open + * @file: Structure to return filled in + * + * Opens the file specified by inode. + * + * Returns zero on success; non-zero otherwise + */ +static int ecryptfs_dir_open(struct inode *inode, struct file *file) +{ + struct dentry *ecryptfs_dentry = file->f_path.dentry; + /* Private value of ecryptfs_dentry allocated in + * ecryptfs_lookup() */ + struct ecryptfs_file_info *file_info; + struct file *lower_file; + struct path path; + + /* Released in ecryptfs_release or end of function if failure */ + file_info = kmem_cache_zalloc(ecryptfs_file_info_cache, GFP_KERNEL); + ecryptfs_set_file_private(file, file_info); + if (unlikely(!file_info)) { + ecryptfs_printk(KERN_ERR, + "Error attempting to allocate memory\n"); + return -ENOMEM; + } + path = ecryptfs_lower_path(ecryptfs_dentry); + lower_file = dentry_open(&path, file->f_flags, current_cred()); + if (IS_ERR(lower_file)) { + printk(KERN_ERR "%s: Error attempting to initialize " + "the lower file for the dentry with name " + "[%pd]; rc = [%ld]\n", __func__, + ecryptfs_dentry, PTR_ERR(lower_file)); + kmem_cache_free(ecryptfs_file_info_cache, file_info); + return PTR_ERR(lower_file); + } + ecryptfs_set_file_lower(file, lower_file); + return 0; +} + +static int ecryptfs_flush(struct file *file, fl_owner_t td) +{ + struct file *lower_file = ecryptfs_file_to_lower(file); + + if (lower_file->f_op->flush) { + filemap_write_and_wait(file->f_mapping); + return lower_file->f_op->flush(lower_file, td); + } + + return 0; +} + +static int ecryptfs_release(struct inode *inode, struct file *file) +{ + ecryptfs_put_lower_file(inode); + kmem_cache_free(ecryptfs_file_info_cache, + ecryptfs_file_to_private(file)); + return 0; +} + +static int ecryptfs_dir_release(struct inode *inode, struct file *file) +{ + fput(ecryptfs_file_to_lower(file)); + kmem_cache_free(ecryptfs_file_info_cache, + ecryptfs_file_to_private(file)); + return 0; +} + +static loff_t ecryptfs_dir_llseek(struct file *file, loff_t offset, int whence) +{ + return vfs_llseek(ecryptfs_file_to_lower(file), offset, whence); +} + +static int +ecryptfs_fsync(struct file *file, loff_t start, loff_t end, int datasync) +{ + int rc; + + rc = file_write_and_wait(file); + if (rc) + return rc; + + return vfs_fsync(ecryptfs_file_to_lower(file), datasync); +} + +static int ecryptfs_fasync(int fd, struct file *file, int flag) +{ + int rc = 0; + struct file *lower_file = NULL; + + lower_file = ecryptfs_file_to_lower(file); + if (lower_file->f_op->fasync) + rc = lower_file->f_op->fasync(fd, lower_file, flag); + return rc; +} + +static long +ecryptfs_unlocked_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + struct file *lower_file = ecryptfs_file_to_lower(file); + long rc = -ENOTTY; + + if (!lower_file->f_op->unlocked_ioctl) + return rc; + + switch (cmd) { + case FITRIM: + case FS_IOC_GETFLAGS: + case FS_IOC_SETFLAGS: + case FS_IOC_GETVERSION: + case FS_IOC_SETVERSION: + rc = lower_file->f_op->unlocked_ioctl(lower_file, cmd, arg); + fsstack_copy_attr_all(file_inode(file), file_inode(lower_file)); + + return rc; + default: + return rc; + } +} + +#ifdef CONFIG_COMPAT +static long +ecryptfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + struct file *lower_file = ecryptfs_file_to_lower(file); + long rc = -ENOIOCTLCMD; + + if (!lower_file->f_op->compat_ioctl) + return rc; + + switch (cmd) { + case FITRIM: + case FS_IOC32_GETFLAGS: + case FS_IOC32_SETFLAGS: + case FS_IOC32_GETVERSION: + case FS_IOC32_SETVERSION: + rc = lower_file->f_op->compat_ioctl(lower_file, cmd, arg); + fsstack_copy_attr_all(file_inode(file), file_inode(lower_file)); + + return rc; + default: + return rc; + } +} +#endif + +const struct file_operations ecryptfs_dir_fops = { + .iterate_shared = ecryptfs_readdir, + .read = generic_read_dir, + .unlocked_ioctl = ecryptfs_unlocked_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = ecryptfs_compat_ioctl, +#endif + .open = ecryptfs_dir_open, + .release = ecryptfs_dir_release, + .fsync = ecryptfs_fsync, + .llseek = ecryptfs_dir_llseek, +}; + +const struct file_operations ecryptfs_main_fops = { + .llseek = generic_file_llseek, + .read_iter = ecryptfs_read_update_atime, + .write_iter = generic_file_write_iter, + .unlocked_ioctl = ecryptfs_unlocked_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = ecryptfs_compat_ioctl, +#endif + .mmap = ecryptfs_mmap, + .open = ecryptfs_open, + .flush = ecryptfs_flush, + .release = ecryptfs_release, + .fsync = ecryptfs_fsync, + .fasync = ecryptfs_fasync, + .splice_read = ecryptfs_splice_read_update_atime, +}; -- cgit v1.3.1