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/afs/callback.c | 262 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 262 insertions(+) create mode 100644 fs/afs/callback.c (limited to 'fs/afs/callback.c') diff --git a/fs/afs/callback.c b/fs/afs/callback.c new file mode 100644 index 000000000..61354003c --- /dev/null +++ b/fs/afs/callback.c @@ -0,0 +1,262 @@ +/* + * Copyright (c) 2002, 2007 Red Hat, Inc. All rights reserved. + * + * This software may be freely redistributed under the terms of the + * GNU General Public License. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + * + * Authors: David Woodhouse + * David Howells + * + */ + +#include +#include +#include +#include +#include +#include "internal.h" + +/* + * Handle invalidation of an mmap'd file. We invalidate all the PTEs referring + * to the pages in this file's pagecache, forcing the kernel to go through + * ->fault() or ->page_mkwrite() - at which point we can handle invalidation + * more fully. + */ +void afs_invalidate_mmap_work(struct work_struct *work) +{ + struct afs_vnode *vnode = container_of(work, struct afs_vnode, cb_work); + + unmap_mapping_pages(vnode->netfs.inode.i_mapping, 0, 0, false); +} + +static void afs_volume_init_callback(struct afs_volume *volume) +{ + struct afs_vnode *vnode; + + down_read(&volume->open_mmaps_lock); + + list_for_each_entry(vnode, &volume->open_mmaps, cb_mmap_link) { + if (vnode->cb_v_check != atomic_read(&volume->cb_v_break)) { + afs_clear_cb_promise(vnode, afs_cb_promise_clear_vol_init_cb); + queue_work(system_dfl_wq, &vnode->cb_work); + } + } + + up_read(&volume->open_mmaps_lock); +} + +/* + * Allow the fileserver to request callback state (re-)initialisation. + * Unfortunately, UUIDs are not guaranteed unique. + */ +void afs_init_callback_state(struct afs_server *server) +{ + struct afs_server_entry *se; + + down_read(&server->cell->vs_lock); + + list_for_each_entry(se, &server->volumes, slink) { + se->cb_expires_at = AFS_NO_CB_PROMISE; + se->volume->cb_expires_at = AFS_NO_CB_PROMISE; + trace_afs_cb_v_break(se->volume->vid, atomic_read(&se->volume->cb_v_break), + afs_cb_break_for_s_reinit); + if (!list_empty(&se->volume->open_mmaps)) + afs_volume_init_callback(se->volume); + } + + up_read(&server->cell->vs_lock); +} + +/* + * actually break a callback + */ +void __afs_break_callback(struct afs_vnode *vnode, enum afs_cb_break_reason reason) +{ + _enter(""); + + clear_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags); + if (afs_clear_cb_promise(vnode, afs_cb_promise_clear_cb_break)) { + vnode->cb_break++; + vnode->cb_v_check = atomic_read(&vnode->volume->cb_v_break); + afs_clear_permits(vnode); + + if (vnode->lock_state == AFS_VNODE_LOCK_WAITING_FOR_CB) + afs_lock_may_be_available(vnode); + + if (reason != afs_cb_break_for_deleted && + vnode->status.type == AFS_FTYPE_FILE && + atomic_read(&vnode->cb_nr_mmap)) + queue_work(system_dfl_wq, &vnode->cb_work); + + trace_afs_cb_break(&vnode->fid, vnode->cb_break, reason, true); + } else { + trace_afs_cb_break(&vnode->fid, vnode->cb_break, reason, false); + } +} + +void afs_break_callback(struct afs_vnode *vnode, enum afs_cb_break_reason reason) +{ + write_seqlock(&vnode->cb_lock); + __afs_break_callback(vnode, reason); + write_sequnlock(&vnode->cb_lock); +} + +/* + * Look up a volume by volume ID under RCU conditions. + */ +static struct afs_volume *afs_lookup_volume_rcu(struct afs_cell *cell, + afs_volid_t vid) +{ + struct afs_volume *volume = NULL; + struct rb_node *p; + + scoped_seqlock_read(&cell->volume_lock, ss_lock) { + /* Unfortunately, rbtree walking doesn't give reliable results + * under just the RCU read lock, so we have to check for + * changes. + */ + p = rcu_dereference_raw(cell->volumes.rb_node); + while (p) { + volume = rb_entry(p, struct afs_volume, cell_node); + + if (volume->vid < vid) + p = rcu_dereference_raw(p->rb_left); + else if (volume->vid > vid) + p = rcu_dereference_raw(p->rb_right); + else + break; + volume = NULL; + } + + if (volume && afs_try_get_volume(volume, afs_volume_trace_get_callback)) + break; + volume = NULL; + } + + return volume; +} + +/* + * Allow the fileserver to break callbacks at the volume-level. This is + * typically done when, for example, a R/W volume is snapshotted to a R/O + * volume (the only way to change an R/O volume). It may also, however, happen + * when a volserver takes control of a volume (offlining it, moving it, etc.). + * + * Every file in that volume will need to be reevaluated. + */ +static void afs_break_volume_callback(struct afs_server *server, + struct afs_volume *volume) + __releases(RCU) +{ + struct afs_server_list *slist = rcu_dereference(volume->servers); + unsigned int i, cb_v_break; + + write_lock(&volume->cb_v_break_lock); + + for (i = 0; i < slist->nr_servers; i++) + if (slist->servers[i].server == server) + slist->servers[i].cb_expires_at = AFS_NO_CB_PROMISE; + volume->cb_expires_at = AFS_NO_CB_PROMISE; + + cb_v_break = atomic_inc_return_release(&volume->cb_v_break); + trace_afs_cb_v_break(volume->vid, cb_v_break, afs_cb_break_for_volume_callback); + + write_unlock(&volume->cb_v_break_lock); + rcu_read_unlock(); + + if (!list_empty(&volume->open_mmaps)) + afs_volume_init_callback(volume); +} + +/* + * allow the fileserver to explicitly break one callback + * - happens when + * - the backing file is changed + * - a lock is released + */ +static void afs_break_one_callback(struct afs_server *server, + struct afs_volume *volume, + struct afs_fid *fid) +{ + struct super_block *sb; + struct afs_vnode *vnode; + struct inode *inode; + + /* See if we can find a matching inode - even an I_NEW inode needs to + * be marked as it can have its callback broken before we finish + * setting up the local inode. + */ + sb = rcu_dereference(volume->sb); + if (!sb) + return; + + inode = find_inode_rcu(sb, fid->vnode, afs_ilookup5_test_by_fid, fid); + if (inode) { + vnode = AFS_FS_I(inode); + afs_break_callback(vnode, afs_cb_break_for_callback); + } else { + trace_afs_cb_miss(fid, afs_cb_break_for_callback); + } +} + +static void afs_break_some_callbacks(struct afs_server *server, + struct afs_callback_break *cbb, + size_t *_count) +{ + struct afs_callback_break *residue = cbb; + struct afs_volume *volume; + afs_volid_t vid = cbb->fid.vid; + size_t i; + + rcu_read_lock(); + volume = afs_lookup_volume_rcu(server->cell, vid); + if (!volume) { + /* Ignore breaks on unknown volumes. */ + rcu_read_unlock(); + *_count = 0; + } else if (cbb->fid.vnode == 0 && cbb->fid.unique == 0) { + afs_break_volume_callback(server, volume); + *_count -= 1; + if (*_count) + memmove(cbb, cbb + 1, sizeof(*cbb) * *_count); + } else { + /* TODO: Find all matching volumes if we couldn't match the server and + * break them anyway. + */ + + for (i = *_count; i > 0; cbb++, i--) { + if (cbb->fid.vid == vid) { + _debug("- Fid { vl=%08llx n=%llu u=%u }", + cbb->fid.vid, + cbb->fid.vnode, + cbb->fid.unique); + --*_count; + if (volume) + afs_break_one_callback(server, volume, &cbb->fid); + } else { + *residue++ = *cbb; + } + } + rcu_read_unlock(); + } + + afs_put_volume(volume, afs_volume_trace_put_callback); +} + +/* + * allow the fileserver to break callback promises + */ +void afs_break_callbacks(struct afs_server *server, size_t count, + struct afs_callback_break *callbacks) +{ + _enter("%p,%zu,", server, count); + + ASSERT(server != NULL); + + while (count > 0) + afs_break_some_callbacks(server, callbacks, &count); +} -- cgit v1.3.1