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/ramfs/Makefile | 10 ++ fs/ramfs/file-mmu.c | 55 +++++++++ fs/ramfs/file-nommu.c | 276 ++++++++++++++++++++++++++++++++++++++++++ fs/ramfs/inode.c | 329 ++++++++++++++++++++++++++++++++++++++++++++++++++ fs/ramfs/internal.h | 9 ++ 5 files changed, 679 insertions(+) create mode 100644 fs/ramfs/Makefile create mode 100644 fs/ramfs/file-mmu.c create mode 100644 fs/ramfs/file-nommu.c create mode 100644 fs/ramfs/inode.c create mode 100644 fs/ramfs/internal.h (limited to 'fs/ramfs') diff --git a/fs/ramfs/Makefile b/fs/ramfs/Makefile new file mode 100644 index 000000000..d1198adb5 --- /dev/null +++ b/fs/ramfs/Makefile @@ -0,0 +1,10 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# Makefile for the linux ramfs routines. +# + +obj-y += ramfs.o + +file-mmu-y := file-nommu.o +file-mmu-$(CONFIG_MMU) := file-mmu.o +ramfs-objs += inode.o $(file-mmu-y) diff --git a/fs/ramfs/file-mmu.c b/fs/ramfs/file-mmu.c new file mode 100644 index 000000000..c3ed1c511 --- /dev/null +++ b/fs/ramfs/file-mmu.c @@ -0,0 +1,55 @@ +/* file-mmu.c: ramfs MMU-based file operations + * + * Resizable simple ram filesystem for Linux. + * + * Copyright (C) 2000 Linus Torvalds. + * 2000 Transmeta Corp. + * + * Usage limits added by David Gibson, Linuxcare Australia. + * This file is released under the GPL. + */ + +/* + * NOTE! This filesystem is probably most useful + * not as a real filesystem, but as an example of + * how virtual filesystems can be written. + * + * It doesn't get much simpler than this. Consider + * that this file implements the full semantics of + * a POSIX-compliant read-write filesystem. + * + * Note in particular how the filesystem does not + * need to implement any data structures of its own + * to keep track of the virtual data: using the VFS + * caches is sufficient. + */ + +#include +#include +#include +#include + +#include "internal.h" + +static unsigned long ramfs_mmu_get_unmapped_area(struct file *file, + unsigned long addr, unsigned long len, unsigned long pgoff, + unsigned long flags) +{ + return mm_get_unmapped_area(file, addr, len, pgoff, flags); +} + +const struct file_operations ramfs_file_operations = { + .read_iter = generic_file_read_iter, + .write_iter = generic_file_write_iter, + .mmap_prepare = generic_file_mmap_prepare, + .fsync = noop_fsync, + .splice_read = filemap_splice_read, + .splice_write = iter_file_splice_write, + .llseek = generic_file_llseek, + .get_unmapped_area = ramfs_mmu_get_unmapped_area, +}; + +const struct inode_operations ramfs_file_inode_operations = { + .setattr = simple_setattr, + .getattr = simple_getattr, +}; diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c new file mode 100644 index 000000000..fb471bf88 --- /dev/null +++ b/fs/ramfs/file-nommu.c @@ -0,0 +1,276 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* file-nommu.c: no-MMU version of ramfs + * + * Copyright (C) 2005 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include "internal.h" + +static int ramfs_nommu_setattr(struct mnt_idmap *, struct dentry *, struct iattr *); +static unsigned long ramfs_nommu_get_unmapped_area(struct file *file, + unsigned long addr, + unsigned long len, + unsigned long pgoff, + unsigned long flags); +static int ramfs_nommu_mmap_prepare(struct vm_area_desc *desc); + +static unsigned ramfs_mmap_capabilities(struct file *file) +{ + return NOMMU_MAP_DIRECT | NOMMU_MAP_COPY | NOMMU_MAP_READ | + NOMMU_MAP_WRITE | NOMMU_MAP_EXEC; +} + +const struct file_operations ramfs_file_operations = { + .mmap_capabilities = ramfs_mmap_capabilities, + .mmap_prepare = ramfs_nommu_mmap_prepare, + .get_unmapped_area = ramfs_nommu_get_unmapped_area, + .read_iter = generic_file_read_iter, + .write_iter = generic_file_write_iter, + .fsync = noop_fsync, + .splice_read = filemap_splice_read, + .splice_write = iter_file_splice_write, + .llseek = generic_file_llseek, +}; + +const struct inode_operations ramfs_file_inode_operations = { + .setattr = ramfs_nommu_setattr, + .getattr = simple_getattr, +}; + +/*****************************************************************************/ +/* + * add a contiguous set of pages into a ramfs inode when it's truncated from + * size 0 on the assumption that it's going to be used for an mmap of shared + * memory + */ +int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize) +{ + unsigned long npages, xpages, loop; + struct page *pages; + unsigned order; + void *data; + int ret; + gfp_t gfp = mapping_gfp_mask(inode->i_mapping); + + /* make various checks */ + if (!newsize) + return 0; + + order = get_order(newsize); + if (unlikely(order > MAX_PAGE_ORDER)) + return -EFBIG; + + ret = inode_newsize_ok(inode, newsize); + if (ret) + return ret; + + i_size_write(inode, newsize); + + /* allocate enough contiguous pages to be able to satisfy the + * request */ + pages = alloc_pages(gfp, order); + if (!pages) + return -ENOMEM; + + /* split the high-order page into an array of single pages */ + xpages = 1UL << order; + npages = (newsize + PAGE_SIZE - 1) >> PAGE_SHIFT; + + split_page(pages, order); + + /* trim off any pages we don't actually require */ + for (loop = npages; loop < xpages; loop++) + __free_page(pages + loop); + + /* clear the memory we allocated */ + newsize = PAGE_SIZE * npages; + data = page_address(pages); + memset(data, 0, newsize); + + /* attach all the pages to the inode's address space */ + for (loop = 0; loop < npages; loop++) { + struct page *page = pages + loop; + + ret = add_to_page_cache_lru(page, inode->i_mapping, loop, + gfp); + if (ret < 0) + goto add_error; + + /* prevent the page from being discarded on memory pressure */ + SetPageDirty(page); + SetPageUptodate(page); + + unlock_page(page); + put_page(page); + } + + return 0; + +add_error: + while (loop < npages) + __free_page(pages + loop++); + return ret; +} + +/*****************************************************************************/ +/* + * + */ +static int ramfs_nommu_resize(struct inode *inode, loff_t newsize, loff_t size) +{ + int ret; + + /* assume a truncate from zero size is going to be for the purposes of + * shared mmap */ + if (size == 0) { + if (unlikely(newsize >> 32)) + return -EFBIG; + + return ramfs_nommu_expand_for_mapping(inode, newsize); + } + + /* check that a decrease in size doesn't cut off any shared mappings */ + if (newsize < size) { + ret = nommu_shrink_inode_mappings(inode, size, newsize); + if (ret < 0) + return ret; + } + + truncate_setsize(inode, newsize); + return 0; +} + +/*****************************************************************************/ +/* + * handle a change of attributes + * - we're specifically interested in a change of size + */ +static int ramfs_nommu_setattr(struct mnt_idmap *idmap, + struct dentry *dentry, struct iattr *ia) +{ + struct inode *inode = d_inode(dentry); + unsigned int old_ia_valid = ia->ia_valid; + int ret = 0; + + /* POSIX UID/GID verification for setting inode attributes */ + ret = setattr_prepare(&nop_mnt_idmap, dentry, ia); + if (ret) + return ret; + + /* pick out size-changing events */ + if (ia->ia_valid & ATTR_SIZE) { + loff_t size = inode->i_size; + + if (ia->ia_size != size) { + ret = ramfs_nommu_resize(inode, ia->ia_size, size); + if (ret < 0 || ia->ia_valid == ATTR_SIZE) + goto out; + } else { + /* we skipped the truncate but must still update + * timestamps + */ + ia->ia_valid |= ATTR_MTIME|ATTR_CTIME; + } + } + + setattr_copy(&nop_mnt_idmap, inode, ia); + out: + ia->ia_valid = old_ia_valid; + return ret; +} + +/*****************************************************************************/ +/* + * try to determine where a shared mapping can be made + * - we require that: + * - the pages to be mapped must exist + * - the pages be physically contiguous in sequence + */ +static unsigned long ramfs_nommu_get_unmapped_area(struct file *file, + unsigned long addr, unsigned long len, + unsigned long pgoff, unsigned long flags) +{ + unsigned long maxpages, lpages, nr_folios, loop, ret, nr_pages, pfn; + struct inode *inode = file_inode(file); + struct folio_batch fbatch; + loff_t isize; + + /* the mapping mustn't extend beyond the EOF */ + lpages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT; + isize = i_size_read(inode); + + ret = -ENOSYS; + maxpages = (isize + PAGE_SIZE - 1) >> PAGE_SHIFT; + if (pgoff >= maxpages) + goto out; + + if (maxpages - pgoff < lpages) + goto out; + + /* gang-find the pages */ + folio_batch_init(&fbatch); + nr_pages = 0; +repeat: + nr_folios = filemap_get_folios_contig(inode->i_mapping, &pgoff, + ULONG_MAX, &fbatch); + if (!nr_folios) { + ret = -ENOSYS; + return ret; + } + + if (ret == -ENOSYS) { + ret = (unsigned long) folio_address(fbatch.folios[0]); + pfn = folio_pfn(fbatch.folios[0]); + } + /* check the pages for physical adjacency */ + for (loop = 0; loop < nr_folios; loop++) { + if (pfn + nr_pages != folio_pfn(fbatch.folios[loop])) { + ret = -ENOSYS; + goto out_free; /* leave if not physical adjacent */ + } + nr_pages += folio_nr_pages(fbatch.folios[loop]); + if (nr_pages >= lpages) + goto out_free; /* successfully found desired pages*/ + } + + if (nr_pages < lpages) { + folio_batch_release(&fbatch); + goto repeat; /* loop if pages are missing */ + } + /* okay - all conditions fulfilled */ + +out_free: + folio_batch_release(&fbatch); +out: + return ret; +} + +/*****************************************************************************/ +/* + * set up a mapping for shared memory segments + */ +static int ramfs_nommu_mmap_prepare(struct vm_area_desc *desc) +{ + if (!is_nommu_shared_vma_flags(&desc->vma_flags)) + return -ENOSYS; + + file_accessed(desc->file); + desc->vm_ops = &generic_file_vm_ops; + return 0; +} diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c new file mode 100644 index 000000000..0a88ede48 --- /dev/null +++ b/fs/ramfs/inode.c @@ -0,0 +1,329 @@ +/* + * Resizable simple ram filesystem for Linux. + * + * Copyright (C) 2000 Linus Torvalds. + * 2000 Transmeta Corp. + * + * Usage limits added by David Gibson, Linuxcare Australia. + * This file is released under the GPL. + */ + +/* + * NOTE! This filesystem is probably most useful + * not as a real filesystem, but as an example of + * how virtual filesystems can be written. + * + * It doesn't get much simpler than this. Consider + * that this file implements the full semantics of + * a POSIX-compliant read-write filesystem. + * + * Note in particular how the filesystem does not + * need to implement any data structures of its own + * to keep track of the virtual data: using the VFS + * caches is sufficient. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "internal.h" + +struct ramfs_mount_opts { + umode_t mode; +}; + +struct ramfs_fs_info { + struct ramfs_mount_opts mount_opts; +}; + +#define RAMFS_DEFAULT_MODE 0755 + +static const struct super_operations ramfs_ops; +static const struct inode_operations ramfs_dir_inode_operations; + +struct inode *ramfs_get_inode(struct super_block *sb, + const struct inode *dir, umode_t mode, dev_t dev) +{ + struct inode * inode = new_inode(sb); + + if (inode) { + inode->i_ino = get_next_ino(); + inode_init_owner(&nop_mnt_idmap, inode, dir, mode); + inode->i_mapping->a_ops = &ram_aops; + mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER); + mapping_set_unevictable(inode->i_mapping); + simple_inode_init_ts(inode); + switch (mode & S_IFMT) { + default: + init_special_inode(inode, mode, dev); + break; + case S_IFREG: + inode->i_op = &ramfs_file_inode_operations; + inode->i_fop = &ramfs_file_operations; + break; + case S_IFDIR: + inode->i_op = &ramfs_dir_inode_operations; + inode->i_fop = &simple_dir_operations; + + /* directory inodes start off with i_nlink == 2 (for "." entry) */ + inc_nlink(inode); + break; + case S_IFLNK: + inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); + break; + } + } + return inode; +} + +/* + * File creation. Allocate an inode, and we're done.. + */ +/* SMP-safe */ +static int +ramfs_mknod(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode, dev_t dev) +{ + struct inode * inode = ramfs_get_inode(dir->i_sb, dir, mode, dev); + int error = -ENOSPC; + + if (inode) { + error = security_inode_init_security(inode, dir, + &dentry->d_name, NULL, + NULL); + if (error) { + iput(inode); + goto out; + } + + d_make_persistent(dentry, inode); + error = 0; + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); + } +out: + return error; +} + +static struct dentry *ramfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode) +{ + int retval = ramfs_mknod(&nop_mnt_idmap, dir, dentry, mode, 0); + if (!retval) + inc_nlink(dir); + return ERR_PTR(retval); +} + +static int ramfs_create(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode) +{ + return ramfs_mknod(&nop_mnt_idmap, dir, dentry, mode | S_IFREG, 0); +} + +static int ramfs_symlink(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, const char *symname) +{ + struct inode *inode; + int error = -ENOSPC; + + inode = ramfs_get_inode(dir->i_sb, dir, S_IFLNK|S_IRWXUGO, 0); + if (inode) { + int l = strlen(symname)+1; + + error = security_inode_init_security(inode, dir, + &dentry->d_name, NULL, + NULL); + if (error) { + iput(inode); + goto out; + } + + error = page_symlink(inode, symname, l); + if (!error) { + d_make_persistent(dentry, inode); + inode_set_mtime_to_ts(dir, + inode_set_ctime_current(dir)); + } else + iput(inode); + } +out: + return error; +} + +static int ramfs_tmpfile(struct mnt_idmap *idmap, + struct inode *dir, struct file *file, umode_t mode) +{ + struct inode *inode; + int error; + + inode = ramfs_get_inode(dir->i_sb, dir, mode, 0); + if (!inode) + return -ENOSPC; + + error = security_inode_init_security(inode, dir, + &file_dentry(file)->d_name, NULL, + NULL); + if (error) { + iput(inode); + goto out; + } + + d_tmpfile(file, inode); +out: + return finish_open_simple(file, error); +} + +static const struct inode_operations ramfs_dir_inode_operations = { + .create = ramfs_create, + .lookup = simple_lookup, + .link = simple_link, + .unlink = simple_unlink, + .symlink = ramfs_symlink, + .mkdir = ramfs_mkdir, + .rmdir = simple_rmdir, + .mknod = ramfs_mknod, + .rename = simple_rename, + .tmpfile = ramfs_tmpfile, +}; + +/* + * Display the mount options in /proc/mounts. + */ +static int ramfs_show_options(struct seq_file *m, struct dentry *root) +{ + struct ramfs_fs_info *fsi = root->d_sb->s_fs_info; + + if (fsi->mount_opts.mode != RAMFS_DEFAULT_MODE) + seq_printf(m, ",mode=%o", fsi->mount_opts.mode); + return 0; +} + +static const struct super_operations ramfs_ops = { + .statfs = simple_statfs, + .drop_inode = inode_just_drop, + .show_options = ramfs_show_options, +}; + +enum ramfs_param { + Opt_mode, +}; + +const struct fs_parameter_spec ramfs_fs_parameters[] = { + fsparam_u32oct("mode", Opt_mode), + {} +}; + +static int ramfs_parse_param(struct fs_context *fc, struct fs_parameter *param) +{ + struct fs_parse_result result; + struct ramfs_fs_info *fsi = fc->s_fs_info; + int opt; + + opt = fs_parse(fc, ramfs_fs_parameters, param, &result); + if (opt == -ENOPARAM) { + opt = vfs_parse_fs_param_source(fc, param); + if (opt != -ENOPARAM) + return opt; + /* + * We might like to report bad mount options here; + * but traditionally ramfs has ignored all mount options, + * and as it is used as a !CONFIG_SHMEM simple substitute + * for tmpfs, better continue to ignore other mount options. + */ + return 0; + } + if (opt < 0) + return opt; + + switch (opt) { + case Opt_mode: + fsi->mount_opts.mode = result.uint_32 & S_IALLUGO; + break; + } + + return 0; +} + +static int ramfs_fill_super(struct super_block *sb, struct fs_context *fc) +{ + struct ramfs_fs_info *fsi = sb->s_fs_info; + struct inode *inode; + + sb->s_maxbytes = MAX_LFS_FILESIZE; + sb->s_blocksize = PAGE_SIZE; + sb->s_blocksize_bits = PAGE_SHIFT; + sb->s_magic = RAMFS_MAGIC; + sb->s_op = &ramfs_ops; + sb->s_d_flags = DCACHE_DONTCACHE; + sb->s_time_gran = 1; + + inode = ramfs_get_inode(sb, NULL, S_IFDIR | fsi->mount_opts.mode, 0); + sb->s_root = d_make_root(inode); + if (!sb->s_root) + return -ENOMEM; + + return 0; +} + +static int ramfs_get_tree(struct fs_context *fc) +{ + return get_tree_nodev(fc, ramfs_fill_super); +} + +static void ramfs_free_fc(struct fs_context *fc) +{ + kfree(fc->s_fs_info); +} + +static const struct fs_context_operations ramfs_context_ops = { + .free = ramfs_free_fc, + .parse_param = ramfs_parse_param, + .get_tree = ramfs_get_tree, +}; + +int ramfs_init_fs_context(struct fs_context *fc) +{ + struct ramfs_fs_info *fsi; + + fsi = kzalloc_obj(*fsi); + if (!fsi) + return -ENOMEM; + + fsi->mount_opts.mode = RAMFS_DEFAULT_MODE; + fc->s_fs_info = fsi; + fc->ops = &ramfs_context_ops; + return 0; +} + +void ramfs_kill_sb(struct super_block *sb) +{ + kfree(sb->s_fs_info); + kill_anon_super(sb); +} + +static struct file_system_type ramfs_fs_type = { + .name = "ramfs", + .init_fs_context = ramfs_init_fs_context, + .parameters = ramfs_fs_parameters, + .kill_sb = ramfs_kill_sb, + .fs_flags = FS_USERNS_MOUNT, +}; + +static int __init init_ramfs_fs(void) +{ + return register_filesystem(&ramfs_fs_type); +} +fs_initcall(init_ramfs_fs); diff --git a/fs/ramfs/internal.h b/fs/ramfs/internal.h new file mode 100644 index 000000000..3257fc180 --- /dev/null +++ b/fs/ramfs/internal.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* internal.h: ramfs internal definitions + * + * Copyright (C) 2005 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + + +extern const struct inode_operations ramfs_file_inode_operations; -- cgit v1.3.1