mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-04 01:49:36 +00:00
![Kent Overstreet](/assets/img/avatar_default.png)
There has been a long standing page cache coherence bug with direct IO. This provides part of a mechanism to fix it, currently just used by bcachefs but potentially worth promoting to the VFS. Direct IO evicts the range of the pagecache being read or written to. For reads, we need dirty pages to be written to disk, so that the read doesn't return stale data. For writes, we need to evict that range of the pagecache so that it's not stale after the write completes. However, without a locking mechanism to prevent those pages from being re-added to the pagecache - by a buffered read or page fault - page cache inconsistency is still possible. This isn't necessarily just an issue for userspace when they're playing games; filesystems may hang arbitrary state off the pagecache, and so page cache inconsistency may cause real filesystem bugs, depending on the filesystem. This is less of an issue for iomap based filesystems, but e.g. buffer heads caches disk block mappings (!) and attaches them to the pagecache, and bcachefs attaches disk reservations to pagecache pages. This issue has been hard to fix, because - we need to add a lock (henceforth called pagecache_add_lock), which would be held for the duration of the direct IO - page faults add pages to the page cache, thus need to take the same lock - dio -> gup -> page fault thus can deadlock And we cannot enforce a lock ordering with this lock, since userspace will be controlling the lock ordering (via the fd and buffer arguments to direct IOs), so we need a different method of deadlock avoidance. We need to tell the page fault handler that we're already holding a pagecache_add_lock, and since plumbing it through the entire gup() path would be highly impractical this adds a field to task_struct. Then the full method is: - in the dio path, when we first take the pagecache_add_lock, note the mapping in the current task_struct - in the page fault handler, if faults_disabled_mapping is set, we check if it's the same mapping as the one we're taking a page fault for, and if so return an error. Then we check lock ordering: if there's a lock ordering violation and trylock fails, we'll have to cycle the locks and return an error that tells the DIO path to retry: faults_disabled_mapping is also used for signalling "locks were dropped, please retry". Also relevant to this patch: mapping->invalidate_lock. mapping->invalidate_lock provides most of the required semantics - it's used by truncate/fallocate to block pages being added to the pagecache. However, since it's a rwsem, direct IOs would need to take the write side in order to block page cache adds, and would then be exclusive with each other - we'll need a new type of lock to pair with this approach. Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev> Cc: Jan Kara <jack@suse.cz> Cc: Darrick J. Wong <djwong@kernel.org> Cc: linux-fsdevel@vger.kernel.org Cc: Andreas Grünbacher <andreas.gruenbacher@gmail.com>
223 lines
6.2 KiB
C
223 lines
6.2 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
#include <linux/init_task.h>
|
|
#include <linux/export.h>
|
|
#include <linux/mqueue.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/sched/sysctl.h>
|
|
#include <linux/sched/rt.h>
|
|
#include <linux/sched/task.h>
|
|
#include <linux/init.h>
|
|
#include <linux/fs.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/audit.h>
|
|
#include <linux/numa.h>
|
|
#include <linux/scs.h>
|
|
|
|
#include <linux/uaccess.h>
|
|
|
|
static struct signal_struct init_signals = {
|
|
.nr_threads = 1,
|
|
.thread_head = LIST_HEAD_INIT(init_task.thread_node),
|
|
.wait_chldexit = __WAIT_QUEUE_HEAD_INITIALIZER(init_signals.wait_chldexit),
|
|
.shared_pending = {
|
|
.list = LIST_HEAD_INIT(init_signals.shared_pending.list),
|
|
.signal = {{0}}
|
|
},
|
|
.multiprocess = HLIST_HEAD_INIT,
|
|
.rlim = INIT_RLIMITS,
|
|
.cred_guard_mutex = __MUTEX_INITIALIZER(init_signals.cred_guard_mutex),
|
|
.exec_update_lock = __RWSEM_INITIALIZER(init_signals.exec_update_lock),
|
|
#ifdef CONFIG_POSIX_TIMERS
|
|
.posix_timers = LIST_HEAD_INIT(init_signals.posix_timers),
|
|
.cputimer = {
|
|
.cputime_atomic = INIT_CPUTIME_ATOMIC,
|
|
},
|
|
#endif
|
|
INIT_CPU_TIMERS(init_signals)
|
|
.pids = {
|
|
[PIDTYPE_PID] = &init_struct_pid,
|
|
[PIDTYPE_TGID] = &init_struct_pid,
|
|
[PIDTYPE_PGID] = &init_struct_pid,
|
|
[PIDTYPE_SID] = &init_struct_pid,
|
|
},
|
|
INIT_PREV_CPUTIME(init_signals)
|
|
};
|
|
|
|
static struct sighand_struct init_sighand = {
|
|
.count = REFCOUNT_INIT(1),
|
|
.action = { { { .sa_handler = SIG_DFL, } }, },
|
|
.siglock = __SPIN_LOCK_UNLOCKED(init_sighand.siglock),
|
|
.signalfd_wqh = __WAIT_QUEUE_HEAD_INITIALIZER(init_sighand.signalfd_wqh),
|
|
};
|
|
|
|
#ifdef CONFIG_SHADOW_CALL_STACK
|
|
unsigned long init_shadow_call_stack[SCS_SIZE / sizeof(long)]
|
|
__init_task_data = {
|
|
[(SCS_SIZE / sizeof(long)) - 1] = SCS_END_MAGIC
|
|
};
|
|
#endif
|
|
|
|
/*
|
|
* Set up the first task table, touch at your own risk!. Base=0,
|
|
* limit=0x1fffff (=2MB)
|
|
*/
|
|
struct task_struct init_task
|
|
#ifdef CONFIG_ARCH_TASK_STRUCT_ON_STACK
|
|
__init_task_data
|
|
#endif
|
|
__aligned(L1_CACHE_BYTES)
|
|
= {
|
|
#ifdef CONFIG_THREAD_INFO_IN_TASK
|
|
.thread_info = INIT_THREAD_INFO(init_task),
|
|
.stack_refcount = REFCOUNT_INIT(1),
|
|
#endif
|
|
.__state = 0,
|
|
.stack = init_stack,
|
|
.usage = REFCOUNT_INIT(2),
|
|
.flags = PF_KTHREAD,
|
|
.prio = MAX_PRIO - 20,
|
|
.static_prio = MAX_PRIO - 20,
|
|
.normal_prio = MAX_PRIO - 20,
|
|
.policy = SCHED_NORMAL,
|
|
.cpus_ptr = &init_task.cpus_mask,
|
|
.user_cpus_ptr = NULL,
|
|
.cpus_mask = CPU_MASK_ALL,
|
|
.nr_cpus_allowed= NR_CPUS,
|
|
.mm = NULL,
|
|
.active_mm = &init_mm,
|
|
.faults_disabled_mapping = NULL,
|
|
.restart_block = {
|
|
.fn = do_no_restart_syscall,
|
|
},
|
|
.se = {
|
|
.group_node = LIST_HEAD_INIT(init_task.se.group_node),
|
|
},
|
|
.rt = {
|
|
.run_list = LIST_HEAD_INIT(init_task.rt.run_list),
|
|
.time_slice = RR_TIMESLICE,
|
|
},
|
|
.tasks = LIST_HEAD_INIT(init_task.tasks),
|
|
#ifdef CONFIG_SMP
|
|
.pushable_tasks = PLIST_NODE_INIT(init_task.pushable_tasks, MAX_PRIO),
|
|
#endif
|
|
#ifdef CONFIG_CGROUP_SCHED
|
|
.sched_task_group = &root_task_group,
|
|
#endif
|
|
.ptraced = LIST_HEAD_INIT(init_task.ptraced),
|
|
.ptrace_entry = LIST_HEAD_INIT(init_task.ptrace_entry),
|
|
.real_parent = &init_task,
|
|
.parent = &init_task,
|
|
.children = LIST_HEAD_INIT(init_task.children),
|
|
.sibling = LIST_HEAD_INIT(init_task.sibling),
|
|
.group_leader = &init_task,
|
|
RCU_POINTER_INITIALIZER(real_cred, &init_cred),
|
|
RCU_POINTER_INITIALIZER(cred, &init_cred),
|
|
.comm = INIT_TASK_COMM,
|
|
.thread = INIT_THREAD,
|
|
.fs = &init_fs,
|
|
.files = &init_files,
|
|
#ifdef CONFIG_IO_URING
|
|
.io_uring = NULL,
|
|
#endif
|
|
.signal = &init_signals,
|
|
.sighand = &init_sighand,
|
|
.nsproxy = &init_nsproxy,
|
|
.pending = {
|
|
.list = LIST_HEAD_INIT(init_task.pending.list),
|
|
.signal = {{0}}
|
|
},
|
|
.blocked = {{0}},
|
|
.alloc_lock = __SPIN_LOCK_UNLOCKED(init_task.alloc_lock),
|
|
.journal_info = NULL,
|
|
INIT_CPU_TIMERS(init_task)
|
|
.pi_lock = __RAW_SPIN_LOCK_UNLOCKED(init_task.pi_lock),
|
|
.timer_slack_ns = 50000, /* 50 usec default slack */
|
|
.thread_pid = &init_struct_pid,
|
|
.thread_group = LIST_HEAD_INIT(init_task.thread_group),
|
|
.thread_node = LIST_HEAD_INIT(init_signals.thread_head),
|
|
#ifdef CONFIG_AUDIT
|
|
.loginuid = INVALID_UID,
|
|
.sessionid = AUDIT_SID_UNSET,
|
|
#endif
|
|
#ifdef CONFIG_PERF_EVENTS
|
|
.perf_event_mutex = __MUTEX_INITIALIZER(init_task.perf_event_mutex),
|
|
.perf_event_list = LIST_HEAD_INIT(init_task.perf_event_list),
|
|
#endif
|
|
#ifdef CONFIG_PREEMPT_RCU
|
|
.rcu_read_lock_nesting = 0,
|
|
.rcu_read_unlock_special.s = 0,
|
|
.rcu_node_entry = LIST_HEAD_INIT(init_task.rcu_node_entry),
|
|
.rcu_blocked_node = NULL,
|
|
#endif
|
|
#ifdef CONFIG_TASKS_RCU
|
|
.rcu_tasks_holdout = false,
|
|
.rcu_tasks_holdout_list = LIST_HEAD_INIT(init_task.rcu_tasks_holdout_list),
|
|
.rcu_tasks_idle_cpu = -1,
|
|
#endif
|
|
#ifdef CONFIG_TASKS_TRACE_RCU
|
|
.trc_reader_nesting = 0,
|
|
.trc_reader_special.s = 0,
|
|
.trc_holdout_list = LIST_HEAD_INIT(init_task.trc_holdout_list),
|
|
.trc_blkd_node = LIST_HEAD_INIT(init_task.trc_blkd_node),
|
|
#endif
|
|
#ifdef CONFIG_CPUSETS
|
|
.mems_allowed_seq = SEQCNT_SPINLOCK_ZERO(init_task.mems_allowed_seq,
|
|
&init_task.alloc_lock),
|
|
#endif
|
|
#ifdef CONFIG_RT_MUTEXES
|
|
.pi_waiters = RB_ROOT_CACHED,
|
|
.pi_top_task = NULL,
|
|
#endif
|
|
INIT_PREV_CPUTIME(init_task)
|
|
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
|
|
.vtime.seqcount = SEQCNT_ZERO(init_task.vtime_seqcount),
|
|
.vtime.starttime = 0,
|
|
.vtime.state = VTIME_SYS,
|
|
#endif
|
|
#ifdef CONFIG_NUMA_BALANCING
|
|
.numa_preferred_nid = NUMA_NO_NODE,
|
|
.numa_group = NULL,
|
|
.numa_faults = NULL,
|
|
#endif
|
|
#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
|
|
.kasan_depth = 1,
|
|
#endif
|
|
#ifdef CONFIG_KCSAN
|
|
.kcsan_ctx = {
|
|
.scoped_accesses = {LIST_POISON1, NULL},
|
|
},
|
|
#endif
|
|
#ifdef CONFIG_TRACE_IRQFLAGS
|
|
.softirqs_enabled = 1,
|
|
#endif
|
|
#ifdef CONFIG_LOCKDEP
|
|
.lockdep_depth = 0, /* no locks held yet */
|
|
.curr_chain_key = INITIAL_CHAIN_KEY,
|
|
.lockdep_recursion = 0,
|
|
#endif
|
|
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
|
|
.ret_stack = NULL,
|
|
.tracing_graph_pause = ATOMIC_INIT(0),
|
|
#endif
|
|
#if defined(CONFIG_TRACING) && defined(CONFIG_PREEMPTION)
|
|
.trace_recursion = 0,
|
|
#endif
|
|
#ifdef CONFIG_LIVEPATCH
|
|
.patch_state = KLP_UNDEFINED,
|
|
#endif
|
|
#ifdef CONFIG_SECURITY
|
|
.security = NULL,
|
|
#endif
|
|
#ifdef CONFIG_SECCOMP_FILTER
|
|
.seccomp = { .filter_count = ATOMIC_INIT(0) },
|
|
#endif
|
|
};
|
|
EXPORT_SYMBOL(init_task);
|
|
|
|
/*
|
|
* Initial thread structure. Alignment of this is handled by a special
|
|
* linker map entry.
|
|
*/
|
|
#ifndef CONFIG_THREAD_INFO_IN_TASK
|
|
struct thread_info init_thread_info __init_thread_info = INIT_THREAD_INFO(init_task);
|
|
#endif
|