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/volume.c | 472 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 472 insertions(+) create mode 100644 fs/afs/volume.c (limited to 'fs/afs/volume.c') diff --git a/fs/afs/volume.c b/fs/afs/volume.c new file mode 100644 index 000000000..4f79d25ec --- /dev/null +++ b/fs/afs/volume.c @@ -0,0 +1,472 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* AFS volume management + * + * Copyright (C) 2002, 2007 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include +#include +#include "internal.h" + +static unsigned __read_mostly afs_volume_record_life = 60 * 60; +static atomic_t afs_volume_debug_id; + +static void afs_destroy_volume(struct work_struct *work); + +/* + * Insert a volume into a cell. If there's an existing volume record, that is + * returned instead with a ref held. + */ +static struct afs_volume *afs_insert_volume_into_cell(struct afs_cell *cell, + struct afs_volume *volume) +{ + struct afs_volume *p; + struct rb_node *parent = NULL, **pp; + + write_seqlock(&cell->volume_lock); + + pp = &cell->volumes.rb_node; + while (*pp) { + parent = *pp; + p = rb_entry(parent, struct afs_volume, cell_node); + if (p->vid < volume->vid) { + pp = &(*pp)->rb_left; + } else if (p->vid > volume->vid) { + pp = &(*pp)->rb_right; + } else { + if (afs_try_get_volume(p, afs_volume_trace_get_cell_insert)) { + volume = p; + goto found; + } + + set_bit(AFS_VOLUME_RM_TREE, &p->flags); + rb_replace_node_rcu(&p->cell_node, &volume->cell_node, &cell->volumes); + } + } + + rb_link_node_rcu(&volume->cell_node, parent, pp); + rb_insert_color(&volume->cell_node, &cell->volumes); + hlist_add_head_rcu(&volume->proc_link, &cell->proc_volumes); + +found: + write_sequnlock(&cell->volume_lock); + return volume; + +} + +static void afs_remove_volume_from_cell(struct afs_volume *volume) +{ + struct afs_cell *cell = volume->cell; + + if (!hlist_unhashed(&volume->proc_link)) { + trace_afs_volume(volume->debug_id, volume->vid, refcount_read(&volume->ref), + afs_volume_trace_remove); + write_seqlock(&cell->volume_lock); + hlist_del_rcu(&volume->proc_link); + if (!test_and_set_bit(AFS_VOLUME_RM_TREE, &volume->flags)) + rb_erase(&volume->cell_node, &cell->volumes); + write_sequnlock(&cell->volume_lock); + } +} + +/* + * Allocate a volume record and load it up from a vldb record. + */ +static struct afs_volume *afs_alloc_volume(struct afs_fs_context *params, + struct afs_vldb_entry *vldb, + struct afs_server_list **_slist) +{ + struct afs_server_list *slist; + struct afs_volume *volume; + int ret = -ENOMEM, i; + + volume = kzalloc_obj(struct afs_volume); + if (!volume) + goto error_0; + + volume->debug_id = atomic_inc_return(&afs_volume_debug_id); + volume->vid = vldb->vid[params->type]; + volume->update_at = ktime_get_real_seconds() + afs_volume_record_life; + volume->cell = afs_get_cell(params->cell, afs_cell_trace_get_vol); + volume->type = params->type; + volume->type_force = params->force; + volume->name_len = vldb->name_len; + volume->creation_time = TIME64_MIN; + volume->update_time = TIME64_MIN; + + refcount_set(&volume->ref, 1); + INIT_HLIST_NODE(&volume->proc_link); + INIT_WORK(&volume->destructor, afs_destroy_volume); + rwlock_init(&volume->servers_lock); + mutex_init(&volume->volsync_lock); + mutex_init(&volume->cb_check_lock); + rwlock_init(&volume->cb_v_break_lock); + INIT_LIST_HEAD(&volume->open_mmaps); + init_rwsem(&volume->open_mmaps_lock); + memcpy(volume->name, vldb->name, vldb->name_len + 1); + + for (i = 0; i < AFS_MAXTYPES; i++) + volume->vids[i] = vldb->vid[i]; + + slist = afs_alloc_server_list(volume, params->key, vldb); + if (IS_ERR(slist)) { + ret = PTR_ERR(slist); + goto error_1; + } + + *_slist = slist; + rcu_assign_pointer(volume->servers, slist); + trace_afs_volume(volume->debug_id, volume->vid, 1, afs_volume_trace_alloc); + return volume; + +error_1: + afs_put_cell(volume->cell, afs_cell_trace_put_vol); + kfree(volume); +error_0: + return ERR_PTR(ret); +} + +/* + * Look up or allocate a volume record. + */ +static struct afs_volume *afs_lookup_volume(struct afs_fs_context *params, + struct afs_vldb_entry *vldb) +{ + struct afs_server_list *slist; + struct afs_volume *candidate, *volume; + + candidate = afs_alloc_volume(params, vldb, &slist); + if (IS_ERR(candidate)) + return candidate; + + volume = afs_insert_volume_into_cell(params->cell, candidate); + if (volume == candidate) + afs_attach_volume_to_servers(volume, slist); + else + afs_put_volume(candidate, afs_volume_trace_put_cell_dup); + return volume; +} + +/* + * Look up a VLDB record for a volume. + */ +static struct afs_vldb_entry *afs_vl_lookup_vldb(struct afs_cell *cell, + struct key *key, + const char *volname, + size_t volnamesz) +{ + struct afs_vldb_entry *vldb = ERR_PTR(-EDESTADDRREQ); + struct afs_vl_cursor vc; + int ret; + + if (!afs_begin_vlserver_operation(&vc, cell, key)) + return ERR_PTR(-ERESTARTSYS); + + while (afs_select_vlserver(&vc)) { + vldb = afs_vl_get_entry_by_name_u(&vc, volname, volnamesz); + } + + ret = afs_end_vlserver_operation(&vc); + return ret < 0 ? ERR_PTR(ret) : vldb; +} + +/* + * Look up a volume in the VL server and create a candidate volume record for + * it. + * + * The volume name can be one of the following: + * "%[cell:]volume[.]" R/W volume + * "#[cell:]volume[.]" R/O or R/W volume (rwparent=0), + * or R/W (rwparent=1) volume + * "%[cell:]volume.readonly" R/O volume + * "#[cell:]volume.readonly" R/O volume + * "%[cell:]volume.backup" Backup volume + * "#[cell:]volume.backup" Backup volume + * + * The cell name is optional, and defaults to the current cell. + * + * See "The Rules of Mount Point Traversal" in Chapter 5 of the AFS SysAdmin + * Guide + * - Rule 1: Explicit type suffix forces access of that type or nothing + * (no suffix, then use Rule 2 & 3) + * - Rule 2: If parent volume is R/O, then mount R/O volume by preference, R/W + * if not available + * - Rule 3: If parent volume is R/W, then only mount R/W volume unless + * explicitly told otherwise + */ +struct afs_volume *afs_create_volume(struct afs_fs_context *params) +{ + struct afs_vldb_entry *vldb; + struct afs_volume *volume; + unsigned long type_mask = 1UL << params->type; + + vldb = afs_vl_lookup_vldb(params->cell, params->key, + params->volname, params->volnamesz); + if (IS_ERR(vldb)) + return ERR_CAST(vldb); + + if (test_bit(AFS_VLDB_QUERY_ERROR, &vldb->flags)) { + volume = ERR_PTR(vldb->error); + goto error; + } + + /* Make the final decision on the type we want */ + volume = ERR_PTR(-ENOMEDIUM); + if (params->force) { + if (!(vldb->flags & type_mask)) + goto error; + } else if (test_bit(AFS_VLDB_HAS_RO, &vldb->flags)) { + params->type = AFSVL_ROVOL; + } else if (test_bit(AFS_VLDB_HAS_RW, &vldb->flags)) { + params->type = AFSVL_RWVOL; + } else { + goto error; + } + + volume = afs_lookup_volume(params, vldb); + +error: + kfree(vldb); + return volume; +} + +/* + * Destroy a volume record + */ +static void afs_destroy_volume(struct work_struct *work) +{ + struct afs_volume *volume = container_of(work, struct afs_volume, destructor); + struct afs_server_list *slist = rcu_access_pointer(volume->servers); + + _enter("%p", volume); + +#ifdef CONFIG_AFS_FSCACHE + ASSERTCMP(volume->cache, ==, NULL); +#endif + + afs_detach_volume_from_servers(volume, slist); + afs_remove_volume_from_cell(volume); + afs_put_serverlist(volume->cell->net, slist); + afs_put_cell(volume->cell, afs_cell_trace_put_vol); + trace_afs_volume(volume->debug_id, volume->vid, refcount_read(&volume->ref), + afs_volume_trace_free); + kfree_rcu(volume, rcu); + + _leave(" [destroyed]"); +} + +/* + * Try to get a reference on a volume record. + */ +bool afs_try_get_volume(struct afs_volume *volume, enum afs_volume_trace reason) +{ + int r; + + if (__refcount_inc_not_zero(&volume->ref, &r)) { + trace_afs_volume(volume->debug_id, volume->vid, r + 1, reason); + return true; + } + return false; +} + +/* + * Get a reference on a volume record. + */ +struct afs_volume *afs_get_volume(struct afs_volume *volume, + enum afs_volume_trace reason) +{ + if (volume) { + int r; + + __refcount_inc(&volume->ref, &r); + trace_afs_volume(volume->debug_id, volume->vid, r + 1, reason); + } + return volume; +} + + +/* + * Drop a reference on a volume record. + */ +void afs_put_volume(struct afs_volume *volume, enum afs_volume_trace reason) +{ + if (volume) { + unsigned int debug_id = volume->debug_id; + afs_volid_t vid = volume->vid; + bool zero; + int r; + + zero = __refcount_dec_and_test(&volume->ref, &r); + trace_afs_volume(debug_id, vid, r - 1, reason); + if (zero) + schedule_work(&volume->destructor); + } +} + +/* + * Activate a volume. + */ +int afs_activate_volume(struct afs_volume *volume) +{ +#ifdef CONFIG_AFS_FSCACHE + struct fscache_volume *vcookie; + char *name; + + name = kasprintf(GFP_KERNEL, "afs,%s,%llx", + volume->cell->name, volume->vid); + if (!name) + return -ENOMEM; + + vcookie = fscache_acquire_volume(name, NULL, NULL, 0); + if (IS_ERR(vcookie)) { + if (vcookie != ERR_PTR(-EBUSY)) { + kfree(name); + return PTR_ERR(vcookie); + } + pr_err("AFS: Cache volume key already in use (%s)\n", name); + vcookie = NULL; + } + volume->cache = vcookie; + kfree(name); +#endif + return 0; +} + +/* + * Deactivate a volume. + */ +void afs_deactivate_volume(struct afs_volume *volume) +{ + _enter("%s", volume->name); + +#ifdef CONFIG_AFS_FSCACHE + fscache_relinquish_volume(volume->cache, NULL, + test_bit(AFS_VOLUME_DELETED, &volume->flags)); + volume->cache = NULL; +#endif + + _leave(""); +} + +/* + * Query the VL service to update the volume status. + */ +static int afs_update_volume_status(struct afs_volume *volume, struct key *key) +{ + struct afs_server_list *new, *old, *discard; + struct afs_vldb_entry *vldb; + char idbuf[24]; + int ret, idsz; + + _enter(""); + + /* We look up an ID by passing it as a decimal string in the + * operation's name parameter. + */ + idsz = snprintf(idbuf, sizeof(idbuf), "%llu", volume->vid); + + vldb = afs_vl_lookup_vldb(volume->cell, key, idbuf, idsz); + if (IS_ERR(vldb)) { + ret = PTR_ERR(vldb); + goto error; + } + + /* See if the volume got renamed. */ + if (vldb->name_len != volume->name_len || + memcmp(vldb->name, volume->name, vldb->name_len) != 0) { + /* TODO: Use RCU'd string. */ + memcpy(volume->name, vldb->name, AFS_MAXVOLNAME); + volume->name_len = vldb->name_len; + } + + /* See if the volume's server list got updated. */ + new = afs_alloc_server_list(volume, key, vldb); + if (IS_ERR(new)) { + ret = PTR_ERR(new); + goto error_vldb; + } + + write_lock(&volume->servers_lock); + + discard = new; + old = rcu_dereference_protected(volume->servers, + lockdep_is_held(&volume->servers_lock)); + if (afs_annotate_server_list(new, old)) { + new->seq = volume->servers_seq + 1; + rcu_assign_pointer(volume->servers, new); + smp_wmb(); + volume->servers_seq++; + discard = old; + } + + /* Check more often if replication is ongoing. */ + if (new->ro_replicating) + volume->update_at = ktime_get_real_seconds() + 10 * 60; + else + volume->update_at = ktime_get_real_seconds() + afs_volume_record_life; + write_unlock(&volume->servers_lock); + + if (discard == old) + afs_reattach_volume_to_servers(volume, new, old); + afs_put_serverlist(volume->cell->net, discard); + ret = 0; +error_vldb: + kfree(vldb); +error: + _leave(" = %d", ret); + return ret; +} + +/* + * Make sure the volume record is up to date. + */ +int afs_check_volume_status(struct afs_volume *volume, struct afs_operation *op) +{ + int ret, retries = 0; + + _enter(""); + +retry: + if (test_bit(AFS_VOLUME_WAIT, &volume->flags)) + goto wait; + if (volume->update_at <= ktime_get_real_seconds() || + test_bit(AFS_VOLUME_NEEDS_UPDATE, &volume->flags)) + goto update; + _leave(" = 0"); + return 0; + +update: + if (!test_and_set_bit_lock(AFS_VOLUME_UPDATING, &volume->flags)) { + clear_bit(AFS_VOLUME_NEEDS_UPDATE, &volume->flags); + ret = afs_update_volume_status(volume, op->key); + if (ret < 0) + set_bit(AFS_VOLUME_NEEDS_UPDATE, &volume->flags); + clear_bit_unlock(AFS_VOLUME_WAIT, &volume->flags); + clear_bit_unlock(AFS_VOLUME_UPDATING, &volume->flags); + wake_up_bit(&volume->flags, AFS_VOLUME_WAIT); + _leave(" = %d", ret); + return ret; + } + +wait: + if (!test_bit(AFS_VOLUME_WAIT, &volume->flags)) { + _leave(" = 0 [no wait]"); + return 0; + } + + ret = wait_on_bit(&volume->flags, AFS_VOLUME_WAIT, + (op->flags & AFS_OPERATION_UNINTR) ? + TASK_UNINTERRUPTIBLE : TASK_INTERRUPTIBLE); + if (ret == -ERESTARTSYS) { + _leave(" = %d", ret); + return ret; + } + + retries++; + if (retries == 4) { + _leave(" = -ESTALE"); + return -ESTALE; + } + goto retry; +} -- cgit v1.3.1