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/squashfs/cache.c | 557 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 557 insertions(+) create mode 100644 fs/squashfs/cache.c (limited to 'fs/squashfs/cache.c') diff --git a/fs/squashfs/cache.c b/fs/squashfs/cache.c new file mode 100644 index 000000000..c1a83bb0e --- /dev/null +++ b/fs/squashfs/cache.c @@ -0,0 +1,557 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Squashfs - a compressed read only filesystem for Linux + * + * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008 + * Phillip Lougher + * + * cache.c + */ + +/* + * Blocks in Squashfs are compressed. To avoid repeatedly decompressing + * recently accessed data Squashfs uses two small metadata and fragment caches. + * + * This file implements a generic cache implementation used for both caches, + * plus functions layered ontop of the generic cache implementation to + * access the metadata and fragment caches. + * + * To avoid out of memory and fragmentation issues with vmalloc the cache + * uses sequences of kmalloced PAGE_SIZE buffers. + * + * It should be noted that the cache is not used for file datablocks, these + * are decompressed and cached in the page-cache in the normal way. The + * cache is only used to temporarily cache fragment and metadata blocks + * which have been read as as a result of a metadata (i.e. inode or + * directory) or fragment access. Because metadata and fragments are packed + * together into blocks (to gain greater compression) the read of a particular + * piece of metadata or fragment will retrieve other metadata/fragments which + * have been packed with it, these because of locality-of-reference may be read + * in the near future. Temporarily caching them ensures they are available for + * near future access without requiring an additional read and decompress. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "squashfs_fs.h" +#include "squashfs_fs_sb.h" +#include "squashfs.h" +#include "page_actor.h" + +/* + * Waiters on cache->wait_queue are keyed by the block they want, so a wakeup + * can name who it is for. A NULL key is a capacity wakeup: one entry became + * free, so wake one waiter. A block key is a publication wakeup: that block + * now has an entry, so wake every waiter which can share it. + */ +struct squashfs_cache_wait { + wait_queue_entry_t wait; + u64 block; + bool capacity_wake; +}; + +static int squashfs_cache_wake_function(wait_queue_entry_t *wait, + unsigned int mode, int sync, void *key) +{ + struct squashfs_cache_wait *cache_wait = + container_of(wait, struct squashfs_cache_wait, wait); + u64 *block = key; + + if (block && cache_wait->block != *block) + return 0; + + WRITE_ONCE(cache_wait->capacity_wake, !block); + + /* + * Wake and unlink unconditionally instead of using + * autoremove_wake_function(), which unlinks only when it changed the + * task state. A waiter can be made runnable by something which does + * not go through this queue: wake_up_process() takes TASK_NORMAL, and + * a cgroup v2 thaw calls it on every task in the cgroup, as do + * free_pid() on a pid namespace init and a late rcuwait_wake_up(). + * try_to_wake_up() then fails. Leaving such a waiter queued with a + * reason already recorded would let it act on a freed entry it was not + * given, and the failure would not consume the exclusive budget, so a + * second waiter would be woken for the same entry. + * + * list_del_init_careful() must be the last access to @cache_wait: it + * releases the waiter, whose wait structure lives on its stack, and it + * pairs with list_empty_careful() in finish_wait() to publish the + * store above. __wake_up_common() samples ->flags and the next entry + * before calling here, so it does not touch @wait afterwards either. + */ + default_wake_function(wait, mode, sync, key); + list_del_init_careful(&wait->entry); + + return 1; +} + +static void squashfs_cache_wake_block(struct squashfs_cache *cache, u64 block) +{ + /* nr_exclusive == 0: wake every waiter which matches the key. */ + __wake_up(&cache->wait_queue, TASK_NORMAL, 0, &block); +} + +/* + * Look-up block in cache, and increment usage count. If not in cache, read + * and decompress it from disk. + * + * A caller which finds no free entry sleeps on cache->wait_queue as an + * exclusive waiter, so squashfs_cache_put() releasing one entry wakes exactly + * one task. Because a wakee may find its block published in the meantime and + * share that entry rather than claim the free one, a wakee which shares hands + * its wakeup on to the next waiter. + */ +struct squashfs_cache_entry *squashfs_cache_get(struct super_block *sb, + struct squashfs_cache *cache, u64 block, int length) +{ + int i, n; + struct squashfs_cache_entry *entry; + bool capacity_wake = false; + + spin_lock(&cache->lock); + + while (1) { + bool pending, wake_next, wake_block; + + for (i = cache->curr_blk, n = 0; n < cache->entries; n++) { + if (cache->entry[i].block == block) { + cache->curr_blk = i; + break; + } + i = (i + 1) % cache->entries; + } + + if (n == cache->entries) { + /* + * Block not in cache, if all cache entries are used + * go to sleep waiting for one to become available. + */ + if (cache->unused == 0) { + struct squashfs_cache_wait wait = { + .block = block, + .capacity_wake = false, + }; + + init_wait_func(&wait.wait, + squashfs_cache_wake_function); + cache->num_waiters++; + /* + * Enqueue while still holding cache->lock, so + * that a concurrent lookup either sees us + * queued or we see the block it publishes. + */ + prepare_to_wait_exclusive(&cache->wait_queue, + &wait.wait, TASK_UNINTERRUPTIBLE); + spin_unlock(&cache->lock); + schedule(); + finish_wait(&cache->wait_queue, &wait.wait); + capacity_wake = READ_ONCE(wait.capacity_wake); + spin_lock(&cache->lock); + cache->num_waiters--; + continue; + } + + /* + * At least one unused cache entry. A simple + * round-robin strategy is used to choose the entry to + * be evicted from the cache. + */ + i = cache->next_blk; + for (n = 0; n < cache->entries; n++) { + if (cache->entry[i].refcount == 0) + break; + i = (i + 1) % cache->entries; + } + + cache->next_blk = (i + 1) % cache->entries; + entry = &cache->entry[i]; + + /* + * Initialise chosen cache entry, and fill it in from + * disk. + */ + cache->unused--; + entry->block = block; + entry->refcount = 1; + entry->pending = 1; + entry->num_waiters = 0; + entry->error = 0; + wake_block = cache->num_waiters > 0; + spin_unlock(&cache->lock); + + /* + * The entry is now findable, so release everybody + * queued for this block to share it rather than each + * waiting for an entry of their own. They will block + * on entry->wait_queue below until the read completes. + */ + if (wake_block) + squashfs_cache_wake_block(cache, block); + + entry->length = squashfs_read_data(sb, block, length, + &entry->next_index, entry->actor); + + spin_lock(&cache->lock); + + if (entry->length < 0) + entry->error = entry->length; + + entry->pending = 0; + + /* + * While filling this entry one or more other processes + * have looked it up in the cache, and have slept + * waiting for it to become available. + */ + if (entry->num_waiters) { + spin_unlock(&cache->lock); + wake_up_all(&entry->wait_queue); + } else + spin_unlock(&cache->lock); + + goto out; + } + + /* + * Block already in cache. Increment refcount so it doesn't + * get reused until we're finished with it, if it was + * previously unused there's one less cache entry available + * for reuse. + */ + entry = &cache->entry[i]; + if (entry->refcount == 0) { + cache->unused--; + /* This claims the capacity we were woken for. */ + capacity_wake = false; + } + entry->refcount++; + + /* + * If the entry is currently being filled in by another process + * go to sleep waiting for it to become available. + */ + pending = entry->pending; + if (pending) + entry->num_waiters++; + + /* + * We were woken because an entry became free, but shared a + * block instead of claiming it. Hand the wakeup on, otherwise + * the free entry sits unclaimed while others sleep. + */ + wake_next = capacity_wake && cache->unused && cache->num_waiters; + spin_unlock(&cache->lock); + + if (wake_next) + wake_up(&cache->wait_queue); + if (pending) + wait_event(entry->wait_queue, !entry->pending); + + goto out; + } + +out: + TRACE("Got %s %d, start block %lld, refcount %d, error %d\n", + cache->name, i, entry->block, entry->refcount, entry->error); + + if (entry->error) + ERROR("Unable to read %s cache entry [%llx]\n", cache->name, + block); + return entry; +} + + +/* + * Release cache entry, once usage count is zero it can be reused. + */ +void squashfs_cache_put(struct squashfs_cache_entry *entry) +{ + struct squashfs_cache *cache = entry->cache; + + spin_lock(&cache->lock); + entry->refcount--; + if (entry->refcount == 0) { + cache->unused++; + /* + * If there's any processes waiting for a block to become + * available, wake one up. + */ + if (cache->num_waiters) { + spin_unlock(&cache->lock); + wake_up(&cache->wait_queue); + return; + } + } + spin_unlock(&cache->lock); +} + +/* + * Delete cache reclaiming all kmalloced buffers. + */ +void squashfs_cache_delete(struct squashfs_cache *cache) +{ + int i, j; + + if (IS_ERR(cache) || cache == NULL) + return; + + for (i = 0; i < cache->entries; i++) { + if (cache->entry[i].data) { + for (j = 0; j < cache->pages; j++) + kfree(cache->entry[i].data[j]); + kfree(cache->entry[i].data); + } + kfree(cache->entry[i].actor); + } + + kfree(cache->entry); + kfree(cache); +} + + +/* + * Initialise cache allocating the specified number of entries, each of + * size block_size. To avoid vmalloc fragmentation issues each entry + * is allocated as a sequence of kmalloced PAGE_SIZE buffers. + */ +struct squashfs_cache *squashfs_cache_init(char *name, int entries, + int block_size) +{ + int i, j; + struct squashfs_cache *cache; + + if (entries == 0) + return NULL; + + cache = kzalloc_obj(*cache); + if (cache == NULL) { + ERROR("Failed to allocate %s cache\n", name); + return ERR_PTR(-ENOMEM); + } + + cache->entry = kzalloc_objs(*(cache->entry), entries); + if (cache->entry == NULL) { + ERROR("Failed to allocate %s cache\n", name); + goto cleanup; + } + + cache->curr_blk = 0; + cache->next_blk = 0; + cache->unused = entries; + cache->entries = entries; + cache->block_size = block_size; + cache->pages = block_size >> PAGE_SHIFT; + cache->pages = cache->pages ? cache->pages : 1; + cache->name = name; + cache->num_waiters = 0; + spin_lock_init(&cache->lock); + init_waitqueue_head(&cache->wait_queue); + + for (i = 0; i < entries; i++) { + struct squashfs_cache_entry *entry = &cache->entry[i]; + + init_waitqueue_head(&cache->entry[i].wait_queue); + entry->cache = cache; + entry->block = SQUASHFS_INVALID_BLK; + entry->data = kcalloc(cache->pages, sizeof(void *), GFP_KERNEL); + if (entry->data == NULL) { + ERROR("Failed to allocate %s cache entry\n", name); + goto cleanup; + } + + for (j = 0; j < cache->pages; j++) { + entry->data[j] = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (entry->data[j] == NULL) { + ERROR("Failed to allocate %s buffer\n", name); + goto cleanup; + } + } + + entry->actor = squashfs_page_actor_init(entry->data, + cache->pages, 0); + if (entry->actor == NULL) { + ERROR("Failed to allocate %s cache entry\n", name); + goto cleanup; + } + } + + return cache; + +cleanup: + squashfs_cache_delete(cache); + return ERR_PTR(-ENOMEM); +} + + +/* + * Copy up to length bytes from cache entry to buffer starting at offset bytes + * into the cache entry. If there's not length bytes then copy the number of + * bytes available. In all cases return the number of bytes copied. + */ +int squashfs_copy_data(void *buffer, struct squashfs_cache_entry *entry, + int offset, int length) +{ + int remaining = length; + + if (length == 0 || offset < 0) + return 0; + else if (buffer == NULL) + return min(length, entry->length - offset); + + while (offset < entry->length) { + void *buff = entry->data[offset / PAGE_SIZE] + + (offset % PAGE_SIZE); + int bytes = min_t(int, entry->length - offset, + PAGE_SIZE - (offset % PAGE_SIZE)); + + if (bytes >= remaining) { + memcpy(buffer, buff, remaining); + remaining = 0; + break; + } + + memcpy(buffer, buff, bytes); + buffer += bytes; + remaining -= bytes; + offset += bytes; + } + + return length - remaining; +} + + +/* + * Read length bytes from metadata position (block is the + * start of the compressed block on disk, and offset is the offset into + * the block once decompressed). Data is packed into consecutive blocks, + * and length bytes may require reading more than one block. + */ +int squashfs_read_metadata(struct super_block *sb, void *buffer, + u64 *block, int *offset, int length) +{ + struct squashfs_sb_info *msblk = sb->s_fs_info; + int bytes, res = length; + struct squashfs_cache_entry *entry; + + TRACE("Entered squashfs_read_metadata [%llx:%x]\n", *block, *offset); + + if (unlikely(length < 0)) + return -EIO; + + if (unlikely(*offset < 0 || *offset >= SQUASHFS_METADATA_SIZE)) + return -EIO; + + while (length) { + entry = squashfs_cache_get(sb, msblk->block_cache, *block, 0); + if (entry->error) { + res = entry->error; + goto error; + } else if (*offset >= entry->length) { + res = -EIO; + goto error; + } + + bytes = squashfs_copy_data(buffer, entry, *offset, length); + if (buffer) + buffer += bytes; + length -= bytes; + *offset += bytes; + + if (*offset == entry->length) { + *block = entry->next_index; + *offset = 0; + } + + squashfs_cache_put(entry); + } + + return res; + +error: + squashfs_cache_put(entry); + return res; +} + + +/* + * Look-up in the fragmment cache the fragment located at in the + * filesystem. If necessary read and decompress it from disk. + */ +struct squashfs_cache_entry *squashfs_get_fragment(struct super_block *sb, + u64 start_block, int length) +{ + struct squashfs_sb_info *msblk = sb->s_fs_info; + + return squashfs_cache_get(sb, msblk->fragment_cache, start_block, + length); +} + + +/* + * Read and decompress the datablock located at in the + * filesystem. The cache is used here to avoid duplicating locking and + * read/decompress code. + */ +struct squashfs_cache_entry *squashfs_get_datablock(struct super_block *sb, + u64 start_block, int length) +{ + struct squashfs_sb_info *msblk = sb->s_fs_info; + + return squashfs_cache_get(sb, msblk->read_page, start_block, length); +} + + +/* + * Read a filesystem table (uncompressed sequence of bytes) from disk + */ +void *squashfs_read_table(struct super_block *sb, u64 block, int length) +{ + int pages = (length + PAGE_SIZE - 1) >> PAGE_SHIFT; + int i, res; + void *table, *buffer, **data; + struct squashfs_page_actor *actor; + + table = buffer = kmalloc(length, GFP_KERNEL); + if (table == NULL) + return ERR_PTR(-ENOMEM); + + data = kcalloc(pages, sizeof(void *), GFP_KERNEL); + if (data == NULL) { + res = -ENOMEM; + goto failed; + } + + actor = squashfs_page_actor_init(data, pages, length); + if (actor == NULL) { + res = -ENOMEM; + goto failed2; + } + + for (i = 0; i < pages; i++, buffer += PAGE_SIZE) + data[i] = buffer; + + res = squashfs_read_data(sb, block, length | + SQUASHFS_COMPRESSED_BIT_BLOCK, NULL, actor); + + kfree(data); + kfree(actor); + + if (res < 0) + goto failed; + + return table; + +failed2: + kfree(data); +failed: + kfree(table); + return ERR_PTR(res); +} -- cgit v1.3.1