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/jfs/inode.c | 422 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 422 insertions(+) create mode 100644 fs/jfs/inode.c (limited to 'fs/jfs/inode.c') diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c new file mode 100644 index 000000000..c7914dbc9 --- /dev/null +++ b/fs/jfs/inode.c @@ -0,0 +1,422 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) International Business Machines Corp., 2000-2004 + * Portions Copyright (C) Christoph Hellwig, 2001-2002 + */ + +#include +#include +#include +#include +#include +#include +#include +#include "jfs_incore.h" +#include "jfs_inode.h" +#include "jfs_filsys.h" +#include "jfs_imap.h" +#include "jfs_extent.h" +#include "jfs_unicode.h" +#include "jfs_debug.h" +#include "jfs_dmap.h" + + +struct inode *jfs_iget(struct super_block *sb, unsigned long ino) +{ + struct inode *inode; + int ret; + + inode = iget_locked(sb, ino); + if (!inode) + return ERR_PTR(-ENOMEM); + if (!(inode_state_read_once(inode) & I_NEW)) + return inode; + + ret = diRead(inode); + if (ret < 0) { + iget_failed(inode); + return ERR_PTR(ret); + } + + if (S_ISREG(inode->i_mode)) { + inode->i_op = &jfs_file_inode_operations; + inode->i_fop = &jfs_file_operations; + inode->i_mapping->a_ops = &jfs_aops; + } else if (S_ISDIR(inode->i_mode)) { + inode->i_op = &jfs_dir_inode_operations; + inode->i_fop = &jfs_dir_operations; + } else if (S_ISLNK(inode->i_mode)) { + if (inode->i_size >= IDATASIZE) { + inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); + inode->i_mapping->a_ops = &jfs_aops; + } else { + inode->i_op = &jfs_fast_symlink_inode_operations; + inode->i_link = JFS_IP(inode)->i_inline; + /* + * The inline data should be null-terminated, but + * don't let on-disk corruption crash the kernel + */ + inode->i_link[inode->i_size] = '\0'; + } + } else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) || + S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) { + inode->i_op = &jfs_file_inode_operations; + init_special_inode(inode, inode->i_mode, inode->i_rdev); + } else { + printk(KERN_DEBUG "JFS: Invalid file type 0%04o for inode %llu.\n", + inode->i_mode, inode->i_ino); + iget_failed(inode); + return ERR_PTR(-EIO); + } + unlock_new_inode(inode); + return inode; +} + +/* + * Workhorse of both fsync & write_inode + */ +int jfs_commit_inode(struct inode *inode, int wait) +{ + int rc = 0; + tid_t tid; + static int noisy = 5; + + jfs_info("In jfs_commit_inode, inode = 0x%p", inode); + + /* + * Don't commit if inode has been committed since last being + * marked dirty, or if it has been deleted. + */ + if (inode->i_nlink == 0 || !test_cflag(COMMIT_Dirty, inode)) + return 0; + + if (isReadOnly(inode)) { + /* kernel allows writes to devices on read-only + * partitions and may think inode is dirty + */ + if (!special_file(inode->i_mode) && noisy) { + jfs_err("jfs_commit_inode(0x%p) called on read-only volume", + inode); + jfs_err("Is remount racy?"); + noisy--; + } + return 0; + } + + tid = txBegin(inode->i_sb, COMMIT_INODE); + mutex_lock(&JFS_IP(inode)->commit_mutex); + + /* + * Retest inode state after taking commit_mutex + */ + if (inode->i_nlink && test_cflag(COMMIT_Dirty, inode)) + rc = txCommit(tid, 1, &inode, wait ? COMMIT_SYNC : 0); + + txEnd(tid); + mutex_unlock(&JFS_IP(inode)->commit_mutex); + return rc; +} + +int jfs_write_inode(struct inode *inode, struct writeback_control *wbc) +{ + int wait = wbc->sync_mode == WB_SYNC_ALL; + + if (inode->i_nlink == 0) + return 0; + /* + * If COMMIT_DIRTY is not set, the inode isn't really dirty. + * It has been committed since the last change, but was still + * on the dirty inode list. + */ + if (!test_cflag(COMMIT_Dirty, inode)) { + /* Make sure committed changes hit the disk */ + jfs_flush_journal(JFS_SBI(inode->i_sb)->log, wait); + return 0; + } + + if (jfs_commit_inode(inode, wait)) { + jfs_err("jfs_write_inode: jfs_commit_inode failed!"); + return -EIO; + } else + return 0; +} + +void jfs_evict_inode(struct inode *inode) +{ + struct jfs_inode_info *ji = JFS_IP(inode); + + jfs_info("In jfs_evict_inode, inode = 0x%p", inode); + + if (!inode->i_nlink && !is_bad_inode(inode)) { + dquot_initialize(inode); + + truncate_inode_pages_final(&inode->i_data); + if (JFS_IP(inode)->fileset == FILESYSTEM_I) { + struct inode *ipimap = JFS_SBI(inode->i_sb)->ipimap; + + if (test_cflag(COMMIT_Freewmap, inode)) + jfs_free_zero_link(inode); + + if (ipimap && JFS_IP(ipimap)->i_imap) + diFree(inode); + + /* + * Free the inode from the quota allocation. + */ + dquot_free_inode(inode); + } + } else { + truncate_inode_pages_final(&inode->i_data); + } + clear_inode(inode); + dquot_drop(inode); + + BUG_ON(!list_empty(&ji->anon_inode_list)); + + spin_lock_irq(&ji->ag_lock); + if (ji->active_ag != -1) { + struct bmap *bmap = JFS_SBI(inode->i_sb)->bmap; + atomic_dec(&bmap->db_active[ji->active_ag]); + ji->active_ag = -1; + } + spin_unlock_irq(&ji->ag_lock); +} + +void jfs_dirty_inode(struct inode *inode, int flags) +{ + static int noisy = 5; + + if (isReadOnly(inode)) { + if (!special_file(inode->i_mode) && noisy) { + /* kernel allows writes to devices on read-only + * partitions and may try to mark inode dirty + */ + jfs_err("jfs_dirty_inode called on read-only volume"); + jfs_err("Is remount racy?"); + noisy--; + } + return; + } + + set_cflag(COMMIT_Dirty, inode); +} + +int jfs_get_block(struct inode *ip, sector_t lblock, + struct buffer_head *bh_result, int create) +{ + s64 lblock64 = lblock; + int rc = 0; + xad_t xad; + s64 xaddr; + int xflag; + s32 xlen = bh_result->b_size >> ip->i_blkbits; + + /* + * Take appropriate lock on inode + */ + if (create) + IWRITE_LOCK(ip, RDWRLOCK_NORMAL); + else + IREAD_LOCK(ip, RDWRLOCK_NORMAL); + + if (((lblock64 << ip->i_sb->s_blocksize_bits) < ip->i_size) && + (!xtLookup(ip, lblock64, xlen, &xflag, &xaddr, &xlen, 0)) && + xaddr) { + if (xflag & XAD_NOTRECORDED) { + if (!create) + /* + * Allocated but not recorded, read treats + * this as a hole + */ + goto unlock; + XADoffset(&xad, lblock64); + XADlength(&xad, xlen); + XADaddress(&xad, xaddr); + rc = extRecord(ip, &xad); + if (rc) + goto unlock; + set_buffer_new(bh_result); + } + + map_bh(bh_result, ip->i_sb, xaddr); + bh_result->b_size = xlen << ip->i_blkbits; + goto unlock; + } + if (!create) + goto unlock; + + /* + * Allocate a new block + */ + if ((rc = extHint(ip, lblock64 << ip->i_sb->s_blocksize_bits, &xad))) + goto unlock; + rc = extAlloc(ip, xlen, lblock64, &xad, false); + if (rc) + goto unlock; + + set_buffer_new(bh_result); + map_bh(bh_result, ip->i_sb, addressXAD(&xad)); + bh_result->b_size = lengthXAD(&xad) << ip->i_blkbits; + + unlock: + /* + * Release lock on inode + */ + if (create) + IWRITE_UNLOCK(ip); + else + IREAD_UNLOCK(ip); + return rc; +} + +static int jfs_writepages(struct address_space *mapping, + struct writeback_control *wbc) +{ + return mpage_writepages(mapping, wbc, jfs_get_block); +} + +static int jfs_read_folio(struct file *file, struct folio *folio) +{ + return mpage_read_folio(folio, jfs_get_block); +} + +static void jfs_readahead(struct readahead_control *rac) +{ + mpage_readahead(rac, jfs_get_block); +} + +static void jfs_write_failed(struct address_space *mapping, loff_t to) +{ + struct inode *inode = mapping->host; + + if (to > inode->i_size) { + truncate_pagecache(inode, inode->i_size); + jfs_truncate(inode); + } +} + +static int jfs_write_begin(const struct kiocb *iocb, + struct address_space *mapping, + loff_t pos, unsigned len, + struct folio **foliop, void **fsdata) +{ + int ret; + + ret = block_write_begin(mapping, pos, len, foliop, jfs_get_block); + if (unlikely(ret)) + jfs_write_failed(mapping, pos + len); + + return ret; +} + +static int jfs_write_end(const struct kiocb *iocb, + struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct folio *folio, void *fsdata) +{ + int ret; + + ret = generic_write_end(iocb, mapping, pos, len, copied, folio, fsdata); + if (ret < len) + jfs_write_failed(mapping, pos + len); + return ret; +} + +static sector_t jfs_bmap(struct address_space *mapping, sector_t block) +{ + return generic_block_bmap(mapping, block, jfs_get_block); +} + +static ssize_t jfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) +{ + struct file *file = iocb->ki_filp; + struct address_space *mapping = file->f_mapping; + struct inode *inode = file->f_mapping->host; + size_t count = iov_iter_count(iter); + ssize_t ret; + + ret = blockdev_direct_IO(iocb, inode, iter, jfs_get_block); + + /* + * In case of error extending write may have instantiated a few + * blocks outside i_size. Trim these off again. + */ + if (unlikely(iov_iter_rw(iter) == WRITE && ret < 0)) { + loff_t isize = i_size_read(inode); + loff_t end = iocb->ki_pos + count; + + if (end > isize) + jfs_write_failed(mapping, end); + } + + return ret; +} + +const struct address_space_operations jfs_aops = { + .dirty_folio = block_dirty_folio, + .invalidate_folio = block_invalidate_folio, + .read_folio = jfs_read_folio, + .readahead = jfs_readahead, + .writepages = jfs_writepages, + .write_begin = jfs_write_begin, + .write_end = jfs_write_end, + .bmap = jfs_bmap, + .direct_IO = jfs_direct_IO, + .migrate_folio = buffer_migrate_folio, +}; + +/* + * Guts of jfs_truncate. Called with locks already held. Can be called + * with directory for truncating directory index table. + */ +void jfs_truncate_nolock(struct inode *ip, loff_t length) +{ + loff_t newsize; + tid_t tid; + + ASSERT(length >= 0); + + if (test_cflag(COMMIT_Nolink, ip) || isReadOnly(ip)) { + xtTruncate(0, ip, length, COMMIT_WMAP); + return; + } + + do { + tid = txBegin(ip->i_sb, 0); + + /* + * The commit_mutex cannot be taken before txBegin. + * txBegin may block and there is a chance the inode + * could be marked dirty and need to be committed + * before txBegin unblocks + */ + mutex_lock(&JFS_IP(ip)->commit_mutex); + + newsize = xtTruncate(tid, ip, length, + COMMIT_TRUNCATE | COMMIT_PWMAP); + if (newsize < 0) { + txEnd(tid); + mutex_unlock(&JFS_IP(ip)->commit_mutex); + break; + } + + inode_set_mtime_to_ts(ip, inode_set_ctime_current(ip)); + mark_inode_dirty(ip); + + txCommit(tid, 1, &ip, 0); + txEnd(tid); + mutex_unlock(&JFS_IP(ip)->commit_mutex); + } while (newsize > length); /* Truncate isn't always atomic */ +} + +void jfs_truncate(struct inode *ip) +{ + jfs_info("jfs_truncate: size = 0x%lx", (ulong) ip->i_size); + + block_truncate_page(ip->i_mapping, ip->i_size, jfs_get_block); + + IWRITE_LOCK(ip, RDWRLOCK_NORMAL); + jfs_truncate_nolock(ip, ip->i_size); + IWRITE_UNLOCK(ip); +} -- cgit v1.3.1