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/btrfs/compression.h | 183 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 183 insertions(+) create mode 100644 fs/btrfs/compression.h (limited to 'fs/btrfs/compression.h') diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h new file mode 100644 index 000000000..1022dc53e --- /dev/null +++ b/fs/btrfs/compression.h @@ -0,0 +1,183 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2008 Oracle. All rights reserved. + */ + +#ifndef BTRFS_COMPRESSION_H +#define BTRFS_COMPRESSION_H + +#include +#include +#include +#include +#include +#include +#include "bio.h" +#include "fs.h" +#include "btrfs_inode.h" + +struct address_space; +struct inode; +struct btrfs_inode; +struct btrfs_ordered_extent; + +/* + * We want to make sure that amount of RAM required to uncompress an extent is + * reasonable, so we limit the total size in ram of a compressed extent to + * 128k. This is a crucial number because it also controls how easily we can + * spread reads across cpus for decompression. + * + * We also want to make sure the amount of IO required to do a random read is + * reasonably small, so we limit the size of a compressed extent to 128k. + */ + +/* Maximum length of compressed data stored on disk */ +#define BTRFS_MAX_COMPRESSED (SZ_128K) +#define BTRFS_MAX_COMPRESSED_PAGES (BTRFS_MAX_COMPRESSED / PAGE_SIZE) +static_assert((BTRFS_MAX_COMPRESSED % PAGE_SIZE) == 0); + +/* The max size for a single worker to compress. */ +#define BTRFS_COMPRESSION_CHUNK_SIZE (SZ_512K) + +/* Maximum size of data before compression */ +#define BTRFS_MAX_UNCOMPRESSED (SZ_128K) + +#define BTRFS_ZLIB_DEFAULT_LEVEL 3 + +struct compressed_bio { + /* starting offset in the inode for our pages */ + u64 start; + + /* Number of bytes in the inode we're working on */ + unsigned int len; + + /* The compression algorithm for this bio */ + u8 compress_type; + + /* Whether this is a write for writeback. */ + bool writeback; + + /* For reads, this is the bio we are copying the data into. */ + struct btrfs_bio *orig_bbio; + + /* Must be last. */ + struct btrfs_bio bbio; +}; + +static inline struct btrfs_fs_info *cb_to_fs_info(const struct compressed_bio *cb) +{ + return cb->bbio.inode->root->fs_info; +} + +/* @range_end must be exclusive. */ +static inline u32 btrfs_calc_input_length(struct folio *folio, u64 range_end, u64 cur) +{ + /* @cur must be inside the folio. */ + ASSERT(folio_pos(folio) <= cur); + ASSERT(cur < folio_next_pos(folio)); + return umin(range_end, folio_next_pos(folio)) - cur; +} + +int btrfs_alloc_compress_wsm(struct btrfs_fs_info *fs_info); +void btrfs_free_compress_wsm(struct btrfs_fs_info *fs_info); + +int __init btrfs_init_compress(void); +void __cold btrfs_exit_compress(void); + +bool btrfs_compress_level_valid(unsigned int type, int level); +int btrfs_decompress(int type, const u8 *data_in, struct folio *dest_folio, + unsigned long dest_pgoff, size_t srclen, size_t destlen); +int btrfs_decompress_buf2page(const char *buf, u32 buf_len, + struct compressed_bio *cb, u32 decompressed); + +struct compressed_bio *btrfs_alloc_compressed_write(struct btrfs_inode *inode, + u64 start, u64 len); +void btrfs_submit_compressed_write(struct btrfs_ordered_extent *ordered, + struct compressed_bio *cb); +void btrfs_submit_compressed_read(struct btrfs_bio *bbio); + +int btrfs_compress_str2level(unsigned int type, const char *str, int *level_ret); + +struct folio *btrfs_alloc_compr_folio(struct btrfs_fs_info *fs_info, gfp_t gfp); +void btrfs_free_compr_folio(struct folio *folio); + +struct workspace_manager { + struct list_head idle_ws; + spinlock_t ws_lock; + /* Number of free workspaces */ + int free_ws; + /* Total number of allocated workspaces */ + atomic_t total_ws; + /* Waiters for a free workspace */ + wait_queue_head_t ws_wait; +}; + +struct list_head *btrfs_get_workspace(struct btrfs_fs_info *fs_info, int type, int level); +void btrfs_put_workspace(struct btrfs_fs_info *fs_info, int type, struct list_head *ws); + +struct btrfs_compress_levels { + /* Maximum level supported by the compression algorithm */ + int min_level; + int max_level; + int default_level; +}; + +/* The heuristic workspaces are managed via the 0th workspace manager */ +#define BTRFS_NR_WORKSPACE_MANAGERS BTRFS_NR_COMPRESS_TYPES + +extern const struct btrfs_compress_levels btrfs_heuristic_compress; +extern const struct btrfs_compress_levels btrfs_zlib_compress; +extern const struct btrfs_compress_levels btrfs_lzo_compress; +extern const struct btrfs_compress_levels btrfs_zstd_compress; + +const char* btrfs_compress_type2str(enum btrfs_compression_type type); +bool btrfs_compress_is_valid_type(const char *str, size_t len); + +int btrfs_compress_heuristic(struct btrfs_inode *inode, u64 start, u64 end); + +int btrfs_compress_filemap_get_folio(struct address_space *mapping, u64 start, + struct folio **in_folio_ret); +struct compressed_bio *btrfs_compress_bio(struct btrfs_inode *inode, + u64 start, u32 len, unsigned int type, + int level, blk_opf_t write_flags); + +static inline void cleanup_compressed_bio(struct compressed_bio *cb) +{ + struct bio *bio = &cb->bbio.bio; + struct folio_iter fi; + + bio_for_each_folio_all(fi, bio) + btrfs_free_compr_folio(fi.folio); + bio_put(bio); +} + +int zlib_compress_bio(struct list_head *ws, struct compressed_bio *cb); +int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb); +int zlib_decompress(struct list_head *ws, const u8 *data_in, + struct folio *dest_folio, unsigned long dest_pgoff, size_t srclen, + size_t destlen); +struct list_head *zlib_alloc_workspace(struct btrfs_fs_info *fs_info, unsigned int level); +void zlib_free_workspace(struct list_head *ws); +struct list_head *zlib_get_workspace(struct btrfs_fs_info *fs_info, unsigned int level); + +int lzo_compress_bio(struct list_head *ws, struct compressed_bio *cb); +int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb); +int lzo_decompress(struct list_head *ws, const u8 *data_in, + struct folio *dest_folio, unsigned long dest_pgoff, size_t srclen, + size_t destlen); +struct list_head *lzo_alloc_workspace(struct btrfs_fs_info *fs_info); +void lzo_free_workspace(struct list_head *ws); + +int zstd_compress_bio(struct list_head *ws, struct compressed_bio *cb); +int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb); +int zstd_decompress(struct list_head *ws, const u8 *data_in, + struct folio *dest_folio, unsigned long dest_pgoff, size_t srclen, + size_t destlen); +int zstd_alloc_workspace_manager(struct btrfs_fs_info *fs_info); +void zstd_free_workspace_manager(struct btrfs_fs_info *fs_info); +struct list_head *zstd_alloc_workspace(struct btrfs_fs_info *fs_info, int level); +void zstd_free_workspace(struct list_head *ws); +struct list_head *zstd_get_workspace(struct btrfs_fs_info *fs_info, int level); +void zstd_put_workspace(struct btrfs_fs_info *fs_info, struct list_head *ws); + +#endif -- cgit v1.3.1