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 --- drivers/md/raid10.h | 179 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 179 insertions(+) create mode 100644 drivers/md/raid10.h (limited to 'drivers/md/raid10.h') diff --git a/drivers/md/raid10.h b/drivers/md/raid10.h new file mode 100644 index 000000000..b711626a5 --- /dev/null +++ b/drivers/md/raid10.h @@ -0,0 +1,179 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _RAID10_H +#define _RAID10_H + +/* Note: raid10_info.rdev can be set to NULL asynchronously by + * raid10_remove_disk. + * There are three safe ways to access raid10_info.rdev. + * 1/ when holding mddev->reconfig_mutex + * 2/ when resync/recovery/reshape is known to be happening - i.e. in code + * that is called as part of performing resync/recovery/reshape. + * 3/ while holding rcu_read_lock(), use rcu_dereference to get the pointer + * and if it is non-NULL, increment rdev->nr_pending before dropping the + * RCU lock. + * When .rdev is set to NULL, the nr_pending count checked again and if it has + * been incremented, the pointer is put back in .rdev. + */ + +struct raid10_info { + struct md_rdev *rdev, *replacement; + sector_t head_position; +}; + +struct r10conf { + struct mddev *mddev; + struct raid10_info *mirrors; + struct raid10_info *mirrors_new, *mirrors_old; + spinlock_t device_lock; + + /* geometry */ + struct geom { + int raid_disks; + int near_copies; /* number of copies laid out + * raid0 style */ + int far_copies; /* number of copies laid out + * at large strides across drives + */ + int far_offset; /* far_copies are offset by 1 + * stripe instead of many + */ + sector_t stride; /* distance between far copies. + * This is size / far_copies unless + * far_offset, in which case it is + * 1 stripe. + */ + int far_set_size; /* The number of devices in a set, + * where a 'set' are devices that + * contain far/offset copies of + * each other. + */ + int chunk_shift; /* shift from chunks to sectors */ + sector_t chunk_mask; + } prev, geo; + int copies; /* near_copies * far_copies. + * must be <= raid_disks + */ + + sector_t dev_sectors; /* temp copy of + * mddev->dev_sectors */ + sector_t reshape_progress; + sector_t reshape_safe; + unsigned long reshape_checkpoint; + sector_t offset_diff; + + struct list_head retry_list; + /* A separate list of r1bio which just need raid_end_bio_io called. + * This mustn't happen for writes which had any errors if the superblock + * needs to be written. + */ + struct list_head bio_end_io_list; + + /* queue pending writes and submit them on unplug */ + struct bio_list pending_bio_list; + + seqlock_t resync_lock; + atomic_t nr_pending; + int nr_waiting; + int nr_queued; + int barrier; + int array_freeze_pending; + sector_t next_resync; + int fullsync; /* set to 1 if a full sync is needed, + * (fresh device added). + * Cleared when a sync completes. + */ + int have_replacement; /* There is at least one + * replacement device. + */ + wait_queue_head_t wait_barrier; + + mempool_t *r10bio_pool; + mempool_t r10buf_pool; + struct page *tmppage; + struct bio_set bio_split; + + /* When taking over an array from a different personality, we store + * the new thread here until we fully activate the array. + */ + struct md_thread __rcu *thread; + + /* + * Keep track of cluster resync window to send to other nodes. + */ + sector_t cluster_sync_low; + sector_t cluster_sync_high; +}; + +/* + * this is our 'private' RAID10 bio. + * + * it contains information about what kind of IO operations were started + * for this RAID10 operation, and about their status: + */ + +struct r10bio { + atomic_t remaining; /* 'have we finished' count, + * used from IRQ handlers + */ + sector_t sector; /* virtual sector number */ + int sectors; + unsigned long state; + struct mddev *mddev; + /* + * original bio going to /dev/mdx + */ + struct bio *master_bio; + /* + * if the IO is in READ direction, then this is where we read + */ + int read_slot; + + struct list_head retry_list; + /* + * if the IO is in WRITE direction, then multiple bios are used, + * one for each copy. + * When resyncing we also use one for each copy. + * When reconstructing, we use 2 bios, one for read, one for write. + * We choose the number when they are allocated. + * We sometimes need an extra bio to write to the replacement. + */ + struct r10dev { + struct bio *bio; + union { + struct bio *repl_bio; /* used for resync and + * writes */ + struct md_rdev *rdev; /* used for reads + * (read_slot >= 0) */ + }; + sector_t addr; + int devnum; + } devs[]; +}; + +/* bits for r10bio.state */ +enum r10bio_state { + R10BIO_Uptodate, + R10BIO_IsSync, + R10BIO_IsRecover, + R10BIO_IsReshape, +/* Set ReadError on bios that experience a read error + * so that raid10d knows what to do with them. + */ + R10BIO_ReadError, +/* For bio_split errors, record that bi_end_io was called. */ + R10BIO_Returned, +/* If a write for this request means we can clear some + * known-bad-block records, we set this flag. + */ + R10BIO_MadeGood, + R10BIO_WriteError, +/* During a reshape we might be performing IO on the + * 'previous' part of the array, in which case this + * flag is set + */ + R10BIO_Previous, +/* failfast devices did receive failfast requests. */ + R10BIO_FailFast, + R10BIO_Discard, +}; +#endif -- cgit v1.3.1