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/ext2/file.c | 217 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 217 insertions(+) create mode 100644 fs/ext2/file.c (limited to 'fs/ext2/file.c') diff --git a/fs/ext2/file.c b/fs/ext2/file.c new file mode 100644 index 000000000..b9020df7d --- /dev/null +++ b/fs/ext2/file.c @@ -0,0 +1,217 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/fs/ext2/file.c + * + * Copyright (C) 1992, 1993, 1994, 1995 + * Remy Card (card@masi.ibp.fr) + * Laboratoire MASI - Institut Blaise Pascal + * Universite Pierre et Marie Curie (Paris VI) + * + * from + * + * linux/fs/minix/file.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + * + * ext2 fs regular file handling primitives + * + * 64-bit file support on 64-bit platforms by Jakub Jelinek + * (jj@sunsite.ms.mff.cuni.cz) + */ + +#include +#include +#include +#include +#include +#include +#include +#include "ext2.h" +#include "xattr.h" +#include "acl.h" +#include "trace.h" + + +/* + * Called when filp is released. This happens when all file descriptors + * for a single struct file are closed. Note that different open() calls + * for the same file yield different struct file structures. + */ +static int ext2_release_file (struct inode * inode, struct file * filp) +{ + if (filp->f_mode & FMODE_WRITE) { + mutex_lock(&EXT2_I(inode)->truncate_mutex); + ext2_discard_reservation(inode); + mutex_unlock(&EXT2_I(inode)->truncate_mutex); + } + return 0; +} + +static ssize_t ext2_dio_read_iter(struct kiocb *iocb, struct iov_iter *to) +{ + struct file *file = iocb->ki_filp; + struct inode *inode = file->f_mapping->host; + ssize_t ret; + + trace_ext2_dio_read_begin(iocb, to, 0); + inode_lock_shared(inode); + ret = iomap_dio_rw(iocb, to, &ext2_iomap_ops, NULL, 0, NULL, 0); + inode_unlock_shared(inode); + trace_ext2_dio_read_end(iocb, to, ret); + + return ret; +} + +static int ext2_dio_write_end_io(struct kiocb *iocb, ssize_t size, + int error, unsigned int flags) +{ + loff_t pos = iocb->ki_pos; + struct inode *inode = file_inode(iocb->ki_filp); + + if (error) + goto out; + + /* + * If we are extending the file, we have to update i_size here before + * page cache gets invalidated in iomap_dio_rw(). This prevents racing + * buffered reads from zeroing out too much from page cache pages. + * Note that all extending writes always happens synchronously with + * inode lock held by ext2_dio_write_iter(). So it is safe to update + * inode size here for extending file writes. + */ + pos += size; + if (pos > i_size_read(inode)) { + i_size_write(inode, pos); + mark_inode_dirty(inode); + } +out: + trace_ext2_dio_write_endio(iocb, size, error); + return error; +} + +static const struct iomap_dio_ops ext2_dio_write_ops = { + .end_io = ext2_dio_write_end_io, +}; + +static ssize_t ext2_dio_write_iter(struct kiocb *iocb, struct iov_iter *from) +{ + struct file *file = iocb->ki_filp; + struct inode *inode = file->f_mapping->host; + ssize_t ret; + unsigned int flags = 0; + unsigned long blocksize = inode->i_sb->s_blocksize; + loff_t offset = iocb->ki_pos; + loff_t count = iov_iter_count(from); + ssize_t status = 0; + + trace_ext2_dio_write_begin(iocb, from, 0); + inode_lock(inode); + ret = generic_write_checks(iocb, from); + if (ret <= 0) + goto out_unlock; + + ret = kiocb_modified(iocb); + if (ret) + goto out_unlock; + + /* use IOMAP_DIO_FORCE_WAIT for unaligned or extending writes */ + if (iocb->ki_pos + iov_iter_count(from) > i_size_read(inode) || + (!IS_ALIGNED(iocb->ki_pos | iov_iter_alignment(from), blocksize))) + flags |= IOMAP_DIO_FORCE_WAIT; + + ret = iomap_dio_rw(iocb, from, &ext2_iomap_ops, &ext2_dio_write_ops, + flags, NULL, 0); + + /* ENOTBLK is magic return value for fallback to buffered-io */ + if (ret == -ENOTBLK) + ret = 0; + + if (ret < 0 && ret != -EIOCBQUEUED) + ext2_write_failed(inode->i_mapping, offset + count); + + /* handle case for partial write and for fallback to buffered write */ + if (ret >= 0 && iov_iter_count(from)) { + loff_t pos, endbyte; + int ret2; + + iocb->ki_flags &= ~IOCB_DIRECT; + pos = iocb->ki_pos; + status = generic_perform_write(iocb, from); + if (unlikely(status < 0)) { + ret = status; + goto out_unlock; + } + + ret += status; + endbyte = pos + status - 1; + ret2 = filemap_write_and_wait_range(inode->i_mapping, pos, + endbyte); + if (!ret2) { + invalidate_mapping_pages(inode->i_mapping, + pos >> PAGE_SHIFT, + endbyte >> PAGE_SHIFT); + if (ret > 0) + ret = generic_write_sync(iocb, ret); + } else { + ret = ret2; + } + } + +out_unlock: + inode_unlock(inode); + if (status) + trace_ext2_dio_write_buff_end(iocb, from, status); + trace_ext2_dio_write_end(iocb, from, ret); + return ret; +} + +static ssize_t ext2_file_read_iter(struct kiocb *iocb, struct iov_iter *to) +{ + if (iocb->ki_flags & IOCB_DIRECT) + return ext2_dio_read_iter(iocb, to); + + return generic_file_read_iter(iocb, to); +} + +static ssize_t ext2_file_write_iter(struct kiocb *iocb, struct iov_iter *from) +{ + if (iocb->ki_flags & IOCB_DIRECT) + return ext2_dio_write_iter(iocb, from); + + return generic_file_write_iter(iocb, from); +} + +static int ext2_file_open(struct inode *inode, struct file *filp) +{ + filp->f_mode |= FMODE_CAN_ODIRECT; + return dquot_file_open(inode, filp); +} + +const struct file_operations ext2_file_operations = { + .llseek = generic_file_llseek, + .read_iter = ext2_file_read_iter, + .write_iter = ext2_file_write_iter, + .unlocked_ioctl = ext2_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = ext2_compat_ioctl, +#endif + .mmap_prepare = generic_file_mmap_prepare, + .open = ext2_file_open, + .release = ext2_release_file, + .fsync = simple_fsync, + .get_unmapped_area = thp_get_unmapped_area, + .splice_read = filemap_splice_read, + .splice_write = iter_file_splice_write, + .setlease = generic_setlease, +}; + +const struct inode_operations ext2_file_inode_operations = { + .listxattr = ext2_listxattr, + .getattr = ext2_getattr, + .setattr = ext2_setattr, + .get_inode_acl = ext2_get_acl, + .set_acl = ext2_set_acl, + .fiemap = ext2_fiemap, + .fileattr_get = ext2_fileattr_get, + .fileattr_set = ext2_fileattr_set, +}; -- cgit v1.3.1