* refs/heads/tmp-4b8fc9f UPSTREAM: locking: avoid passing around 'thread_info' in mutex debugging code ANDROID: arm64: fix undeclared 'init_thread_info' error UPSTREAM: kdb: use task_cpu() instead of task_thread_info()->cpu Linux 4.4.82 net: account for current skb length when deciding about UFO ipv4: Should use consistent conditional judgement for ip fragment in __ip_append_data and ip_finish_output mm/mempool: avoid KASAN marking mempool poison checks as use-after-free KVM: arm/arm64: Handle hva aging while destroying the vm sparc64: Prevent perf from running during super critical sections udp: consistently apply ufo or fragmentation revert "ipv4: Should use consistent conditional judgement for ip fragment in __ip_append_data and ip_finish_output" revert "net: account for current skb length when deciding about UFO" packet: fix tp_reserve race in packet_set_ring net: avoid skb_warn_bad_offload false positives on UFO tcp: fastopen: tcp_connect() must refresh the route net: sched: set xt_tgchk_param par.nft_compat as 0 in ipt_init_target bpf, s390: fix jit branch offset related to ldimm64 net: fix keepalive code vs TCP_FASTOPEN_CONNECT tcp: avoid setting cwnd to invalid ssthresh after cwnd reduction states ANDROID: keychord: Fix for a memory leak in keychord. ANDROID: keychord: Fix races in keychord_write. Use %zu to print resid (size_t). ANDROID: keychord: Fix a slab out-of-bounds read. Linux 4.4.81 workqueue: implicit ordered attribute should be overridable net: account for current skb length when deciding about UFO ipv4: Should use consistent conditional judgement for ip fragment in __ip_append_data and ip_finish_output mm: don't dereference struct page fields of invalid pages signal: protect SIGNAL_UNKILLABLE from unintentional clearing. lib/Kconfig.debug: fix frv build failure mm, slab: make sure that KMALLOC_MAX_SIZE will fit into MAX_ORDER ARM: 8632/1: ftrace: fix syscall name matching virtio_blk: fix panic in initialization error path drm/virtio: fix framebuffer sparse warning scsi: qla2xxx: Get mutex lock before checking optrom_state phy state machine: failsafe leave invalid RUNNING state x86/boot: Add missing declaration of string functions tg3: Fix race condition in tg3_get_stats64(). net: phy: dp83867: fix irq generation sh_eth: R8A7740 supports packet shecksumming wext: handle NULL extra data in iwe_stream_add_point better sparc64: Measure receiver forward progress to avoid send mondo timeout xen-netback: correctly schedule rate-limited queues net: phy: Fix PHY unbind crash net: phy: Correctly process PHY_HALTED in phy_stop_machine() net/mlx5: Fix command bad flow on command entry allocation failure sctp: fix the check for _sctp_walk_params and _sctp_walk_errors sctp: don't dereference ptr before leaving _sctp_walk_{params, errors}() dccp: fix a memleak for dccp_feat_init err process dccp: fix a memleak that dccp_ipv4 doesn't put reqsk properly dccp: fix a memleak that dccp_ipv6 doesn't put reqsk properly net: ethernet: nb8800: Handle all 4 RGMII modes identically ipv6: Don't increase IPSTATS_MIB_FRAGFAILS twice in ip6_fragment() packet: fix use-after-free in prb_retire_rx_blk_timer_expired() openvswitch: fix potential out of bound access in parse_ct mcs7780: Fix initialization when CONFIG_VMAP_STACK is enabled rtnetlink: allocate more memory for dev_set_mac_address() ipv4: initialize fib_trie prior to register_netdev_notifier call. ipv6: avoid overflow of offset in ip6_find_1stfragopt net: Zero terminate ifr_name in dev_ifname(). ipv4: ipv6: initialize treq->txhash in cookie_v[46]_check() saa7164: fix double fetch PCIe access condition drm: rcar-du: fix backport bug f2fs: sanity check checkpoint segno and blkoff media: lirc: LIRC_GET_REC_RESOLUTION should return microseconds mm, mprotect: flush TLB if potentially racing with a parallel reclaim leaving stale TLB entries iser-target: Avoid isert_conn->cm_id dereference in isert_login_recv_done iscsi-target: Fix delayed logout processing greater than SECONDS_FOR_LOGOUT_COMP iscsi-target: Fix initial login PDU asynchronous socket close OOPs iscsi-target: Fix early sk_data_ready LOGIN_FLAGS_READY race iscsi-target: Always wait for kthread_should_stop() before kthread exit target: Avoid mappedlun symlink creation during lun shutdown media: platform: davinci: return -EINVAL for VPFE_CMD_S_CCDC_RAW_PARAMS ioctl ARM: dts: armada-38x: Fix irq type for pca955 ext4: fix overflow caused by missing cast in ext4_resize_fs() ext4: fix SEEK_HOLE/SEEK_DATA for blocksize < pagesize mm/page_alloc: Remove kernel address exposure in free_reserved_area() KVM: async_pf: make rcu irq exit if not triggered from idle task ASoC: do not close shared backend dailink ALSA: hda - Fix speaker output from VAIO VPCL14M1R workqueue: restore WQ_UNBOUND/max_active==1 to be ordered libata: array underflow in ata_find_dev() ANDROID: binder: don't queue async transactions to thread. ANDROID: binder: don't enqueue death notifications to thread todo. ANDROID: binder: call poll_wait() unconditionally. android: configs: move quota-related configs to recommended BACKPORT: arm64: split thread_info from task stack UPSTREAM: arm64: assembler: introduce ldr_this_cpu UPSTREAM: arm64: make cpu number a percpu variable UPSTREAM: arm64: smp: prepare for smp_processor_id() rework BACKPORT: arm64: move sp_el0 and tpidr_el1 into cpu_suspend_ctx UPSTREAM: arm64: prep stack walkers for THREAD_INFO_IN_TASK UPSTREAM: arm64: unexport walk_stackframe UPSTREAM: arm64: traps: simplify die() and __die() UPSTREAM: arm64: factor out current_stack_pointer BACKPORT: arm64: asm-offsets: remove unused definitions UPSTREAM: arm64: thread_info remove stale items UPSTREAM: thread_info: include <current.h> for THREAD_INFO_IN_TASK UPSTREAM: thread_info: factor out restart_block UPSTREAM: kthread: Pin the stack via try_get_task_stack()/put_task_stack() in to_live_kthread() function UPSTREAM: sched/core: Add try_get_task_stack() and put_task_stack() UPSTREAM: sched/core: Allow putting thread_info into task_struct UPSTREAM: printk: when dumping regs, show the stack, not thread_info UPSTREAM: fix up initial thread stack pointer vs thread_info confusion UPSTREAM: Clarify naming of thread info/stack allocators ANDROID: sdcardfs: override credential for ioctl to lower fs Conflicts: android/configs/android-base.cfg arch/arm64/Kconfig arch/arm64/include/asm/suspend.h arch/arm64/kernel/head.S arch/arm64/kernel/smp.c arch/arm64/kernel/suspend.c arch/arm64/kernel/traps.c arch/arm64/mm/proc.S kernel/fork.c sound/soc/soc-pcm.c Change-Id: I273e216c94899a838bbd208391c6cbe20b2bf683 Signed-off-by: Blagovest Kolenichev <bkolenichev@codeaurora.org>
988 lines
26 KiB
C
988 lines
26 KiB
C
/*
|
|
* kernel/locking/mutex.c
|
|
*
|
|
* Mutexes: blocking mutual exclusion locks
|
|
*
|
|
* Started by Ingo Molnar:
|
|
*
|
|
* Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
|
|
*
|
|
* Many thanks to Arjan van de Ven, Thomas Gleixner, Steven Rostedt and
|
|
* David Howells for suggestions and improvements.
|
|
*
|
|
* - Adaptive spinning for mutexes by Peter Zijlstra. (Ported to mainline
|
|
* from the -rt tree, where it was originally implemented for rtmutexes
|
|
* by Steven Rostedt, based on work by Gregory Haskins, Peter Morreale
|
|
* and Sven Dietrich.
|
|
*
|
|
* Also see Documentation/locking/mutex-design.txt.
|
|
*/
|
|
#include <linux/mutex.h>
|
|
#include <linux/ww_mutex.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/sched/rt.h>
|
|
#include <linux/export.h>
|
|
#include <linux/spinlock.h>
|
|
#include <linux/interrupt.h>
|
|
#include <linux/debug_locks.h>
|
|
#include <linux/osq_lock.h>
|
|
#include <linux/delay.h>
|
|
|
|
/*
|
|
* In the DEBUG case we are using the "NULL fastpath" for mutexes,
|
|
* which forces all calls into the slowpath:
|
|
*/
|
|
#ifdef CONFIG_DEBUG_MUTEXES
|
|
# include "mutex-debug.h"
|
|
# include <asm-generic/mutex-null.h>
|
|
/*
|
|
* Must be 0 for the debug case so we do not do the unlock outside of the
|
|
* wait_lock region. debug_mutex_unlock() will do the actual unlock in this
|
|
* case.
|
|
*/
|
|
# undef __mutex_slowpath_needs_to_unlock
|
|
# define __mutex_slowpath_needs_to_unlock() 0
|
|
#else
|
|
# include "mutex.h"
|
|
# include <asm/mutex.h>
|
|
#endif
|
|
|
|
void
|
|
__mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key)
|
|
{
|
|
atomic_set(&lock->count, 1);
|
|
spin_lock_init(&lock->wait_lock);
|
|
INIT_LIST_HEAD(&lock->wait_list);
|
|
mutex_clear_owner(lock);
|
|
#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
|
|
osq_lock_init(&lock->osq);
|
|
#endif
|
|
|
|
debug_mutex_init(lock, name, key);
|
|
}
|
|
|
|
EXPORT_SYMBOL(__mutex_init);
|
|
|
|
#ifndef CONFIG_DEBUG_LOCK_ALLOC
|
|
/*
|
|
* We split the mutex lock/unlock logic into separate fastpath and
|
|
* slowpath functions, to reduce the register pressure on the fastpath.
|
|
* We also put the fastpath first in the kernel image, to make sure the
|
|
* branch is predicted by the CPU as default-untaken.
|
|
*/
|
|
__visible void __sched __mutex_lock_slowpath(atomic_t *lock_count);
|
|
|
|
/**
|
|
* mutex_lock - acquire the mutex
|
|
* @lock: the mutex to be acquired
|
|
*
|
|
* Lock the mutex exclusively for this task. If the mutex is not
|
|
* available right now, it will sleep until it can get it.
|
|
*
|
|
* The mutex must later on be released by the same task that
|
|
* acquired it. Recursive locking is not allowed. The task
|
|
* may not exit without first unlocking the mutex. Also, kernel
|
|
* memory where the mutex resides must not be freed with
|
|
* the mutex still locked. The mutex must first be initialized
|
|
* (or statically defined) before it can be locked. memset()-ing
|
|
* the mutex to 0 is not allowed.
|
|
*
|
|
* ( The CONFIG_DEBUG_MUTEXES .config option turns on debugging
|
|
* checks that will enforce the restrictions and will also do
|
|
* deadlock debugging. )
|
|
*
|
|
* This function is similar to (but not equivalent to) down().
|
|
*/
|
|
void __sched mutex_lock(struct mutex *lock)
|
|
{
|
|
might_sleep();
|
|
/*
|
|
* The locking fastpath is the 1->0 transition from
|
|
* 'unlocked' into 'locked' state.
|
|
*/
|
|
__mutex_fastpath_lock(&lock->count, __mutex_lock_slowpath);
|
|
mutex_set_owner(lock);
|
|
}
|
|
|
|
EXPORT_SYMBOL(mutex_lock);
|
|
#endif
|
|
|
|
static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww,
|
|
struct ww_acquire_ctx *ww_ctx)
|
|
{
|
|
#ifdef CONFIG_DEBUG_MUTEXES
|
|
/*
|
|
* If this WARN_ON triggers, you used ww_mutex_lock to acquire,
|
|
* but released with a normal mutex_unlock in this call.
|
|
*
|
|
* This should never happen, always use ww_mutex_unlock.
|
|
*/
|
|
DEBUG_LOCKS_WARN_ON(ww->ctx);
|
|
|
|
/*
|
|
* Not quite done after calling ww_acquire_done() ?
|
|
*/
|
|
DEBUG_LOCKS_WARN_ON(ww_ctx->done_acquire);
|
|
|
|
if (ww_ctx->contending_lock) {
|
|
/*
|
|
* After -EDEADLK you tried to
|
|
* acquire a different ww_mutex? Bad!
|
|
*/
|
|
DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock != ww);
|
|
|
|
/*
|
|
* You called ww_mutex_lock after receiving -EDEADLK,
|
|
* but 'forgot' to unlock everything else first?
|
|
*/
|
|
DEBUG_LOCKS_WARN_ON(ww_ctx->acquired > 0);
|
|
ww_ctx->contending_lock = NULL;
|
|
}
|
|
|
|
/*
|
|
* Naughty, using a different class will lead to undefined behavior!
|
|
*/
|
|
DEBUG_LOCKS_WARN_ON(ww_ctx->ww_class != ww->ww_class);
|
|
#endif
|
|
ww_ctx->acquired++;
|
|
}
|
|
|
|
/*
|
|
* After acquiring lock with fastpath or when we lost out in contested
|
|
* slowpath, set ctx and wake up any waiters so they can recheck.
|
|
*
|
|
* This function is never called when CONFIG_DEBUG_LOCK_ALLOC is set,
|
|
* as the fastpath and opportunistic spinning are disabled in that case.
|
|
*/
|
|
static __always_inline void
|
|
ww_mutex_set_context_fastpath(struct ww_mutex *lock,
|
|
struct ww_acquire_ctx *ctx)
|
|
{
|
|
unsigned long flags;
|
|
struct mutex_waiter *cur;
|
|
|
|
ww_mutex_lock_acquired(lock, ctx);
|
|
|
|
lock->ctx = ctx;
|
|
|
|
/*
|
|
* The lock->ctx update should be visible on all cores before
|
|
* the atomic read is done, otherwise contended waiters might be
|
|
* missed. The contended waiters will either see ww_ctx == NULL
|
|
* and keep spinning, or it will acquire wait_lock, add itself
|
|
* to waiter list and sleep.
|
|
*/
|
|
smp_mb(); /* ^^^ */
|
|
|
|
/*
|
|
* Check if lock is contended, if not there is nobody to wake up
|
|
*/
|
|
if (likely(atomic_read(&lock->base.count) == 0))
|
|
return;
|
|
|
|
/*
|
|
* Uh oh, we raced in fastpath, wake up everyone in this case,
|
|
* so they can see the new lock->ctx.
|
|
*/
|
|
spin_lock_mutex(&lock->base.wait_lock, flags);
|
|
list_for_each_entry(cur, &lock->base.wait_list, list) {
|
|
debug_mutex_wake_waiter(&lock->base, cur);
|
|
wake_up_process(cur->task);
|
|
}
|
|
spin_unlock_mutex(&lock->base.wait_lock, flags);
|
|
}
|
|
|
|
/*
|
|
* After acquiring lock in the slowpath set ctx and wake up any
|
|
* waiters so they can recheck.
|
|
*
|
|
* Callers must hold the mutex wait_lock.
|
|
*/
|
|
static __always_inline void
|
|
ww_mutex_set_context_slowpath(struct ww_mutex *lock,
|
|
struct ww_acquire_ctx *ctx)
|
|
{
|
|
struct mutex_waiter *cur;
|
|
|
|
ww_mutex_lock_acquired(lock, ctx);
|
|
lock->ctx = ctx;
|
|
|
|
/*
|
|
* Give any possible sleeping processes the chance to wake up,
|
|
* so they can recheck if they have to back off.
|
|
*/
|
|
list_for_each_entry(cur, &lock->base.wait_list, list) {
|
|
debug_mutex_wake_waiter(&lock->base, cur);
|
|
wake_up_process(cur->task);
|
|
}
|
|
}
|
|
|
|
#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
|
|
/*
|
|
* Look out! "owner" is an entirely speculative pointer
|
|
* access and not reliable.
|
|
*/
|
|
static noinline
|
|
bool mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner)
|
|
{
|
|
bool ret = true;
|
|
|
|
rcu_read_lock();
|
|
while (lock->owner == owner) {
|
|
/*
|
|
* Ensure we emit the owner->on_cpu, dereference _after_
|
|
* checking lock->owner still matches owner. If that fails,
|
|
* owner might point to freed memory. If it still matches,
|
|
* the rcu_read_lock() ensures the memory stays valid.
|
|
*/
|
|
barrier();
|
|
|
|
if (!owner->on_cpu || need_resched()) {
|
|
ret = false;
|
|
break;
|
|
}
|
|
|
|
cpu_relax_lowlatency();
|
|
}
|
|
rcu_read_unlock();
|
|
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* Initial check for entering the mutex spinning loop
|
|
*/
|
|
static inline int mutex_can_spin_on_owner(struct mutex *lock)
|
|
{
|
|
struct task_struct *owner;
|
|
int retval = 1;
|
|
|
|
if (need_resched())
|
|
return 0;
|
|
|
|
rcu_read_lock();
|
|
owner = READ_ONCE(lock->owner);
|
|
if (owner)
|
|
retval = owner->on_cpu;
|
|
rcu_read_unlock();
|
|
/*
|
|
* if lock->owner is not set, the mutex owner may have just acquired
|
|
* it and not set the owner yet or the mutex has been released.
|
|
*/
|
|
return retval;
|
|
}
|
|
|
|
/*
|
|
* Atomically try to take the lock when it is available
|
|
*/
|
|
static inline bool mutex_try_to_acquire(struct mutex *lock)
|
|
{
|
|
return !mutex_is_locked(lock) &&
|
|
(atomic_cmpxchg_acquire(&lock->count, 1, 0) == 1);
|
|
}
|
|
|
|
/*
|
|
* Optimistic spinning.
|
|
*
|
|
* We try to spin for acquisition when we find that the lock owner
|
|
* is currently running on a (different) CPU and while we don't
|
|
* need to reschedule. The rationale is that if the lock owner is
|
|
* running, it is likely to release the lock soon.
|
|
*
|
|
* Since this needs the lock owner, and this mutex implementation
|
|
* doesn't track the owner atomically in the lock field, we need to
|
|
* track it non-atomically.
|
|
*
|
|
* We can't do this for DEBUG_MUTEXES because that relies on wait_lock
|
|
* to serialize everything.
|
|
*
|
|
* The mutex spinners are queued up using MCS lock so that only one
|
|
* spinner can compete for the mutex. However, if mutex spinning isn't
|
|
* going to happen, there is no point in going through the lock/unlock
|
|
* overhead.
|
|
*
|
|
* Returns true when the lock was taken, otherwise false, indicating
|
|
* that we need to jump to the slowpath and sleep.
|
|
*/
|
|
static bool mutex_optimistic_spin(struct mutex *lock,
|
|
struct ww_acquire_ctx *ww_ctx, const bool use_ww_ctx)
|
|
{
|
|
struct task_struct *task = current;
|
|
|
|
if (!mutex_can_spin_on_owner(lock))
|
|
goto done;
|
|
|
|
/*
|
|
* In order to avoid a stampede of mutex spinners trying to
|
|
* acquire the mutex all at once, the spinners need to take a
|
|
* MCS (queued) lock first before spinning on the owner field.
|
|
*/
|
|
if (!osq_lock(&lock->osq))
|
|
goto done;
|
|
|
|
while (true) {
|
|
struct task_struct *owner;
|
|
|
|
if (use_ww_ctx && ww_ctx->acquired > 0) {
|
|
struct ww_mutex *ww;
|
|
|
|
ww = container_of(lock, struct ww_mutex, base);
|
|
/*
|
|
* If ww->ctx is set the contents are undefined, only
|
|
* by acquiring wait_lock there is a guarantee that
|
|
* they are not invalid when reading.
|
|
*
|
|
* As such, when deadlock detection needs to be
|
|
* performed the optimistic spinning cannot be done.
|
|
*/
|
|
if (READ_ONCE(ww->ctx))
|
|
break;
|
|
}
|
|
|
|
/*
|
|
* If there's an owner, wait for it to either
|
|
* release the lock or go to sleep.
|
|
*/
|
|
owner = READ_ONCE(lock->owner);
|
|
if (owner && !mutex_spin_on_owner(lock, owner))
|
|
break;
|
|
|
|
/* Try to acquire the mutex if it is unlocked. */
|
|
if (mutex_try_to_acquire(lock)) {
|
|
lock_acquired(&lock->dep_map, ip);
|
|
|
|
if (use_ww_ctx) {
|
|
struct ww_mutex *ww;
|
|
ww = container_of(lock, struct ww_mutex, base);
|
|
|
|
ww_mutex_set_context_fastpath(ww, ww_ctx);
|
|
}
|
|
|
|
mutex_set_owner(lock);
|
|
osq_unlock(&lock->osq);
|
|
return true;
|
|
}
|
|
|
|
/*
|
|
* When there's no owner, we might have preempted between the
|
|
* owner acquiring the lock and setting the owner field. If
|
|
* we're an RT task that will live-lock because we won't let
|
|
* the owner complete.
|
|
*/
|
|
if (!owner && (need_resched() || rt_task(task)))
|
|
break;
|
|
|
|
/*
|
|
* The cpu_relax() call is a compiler barrier which forces
|
|
* everything in this loop to be re-loaded. We don't need
|
|
* memory barriers as we'll eventually observe the right
|
|
* values at the cost of a few extra spins.
|
|
*/
|
|
cpu_relax_lowlatency();
|
|
|
|
/*
|
|
* On arm systems, we must slow down the waiter's repeated
|
|
* aquisition of spin_mlock and atomics on the lock count, or
|
|
* we risk starving out a thread attempting to release the
|
|
* mutex. The mutex slowpath release must take spin lock
|
|
* wait_lock. This spin lock can share a monitor with the
|
|
* other waiter atomics in the mutex data structure, so must
|
|
* take care to rate limit the waiters.
|
|
*/
|
|
udelay(1);
|
|
}
|
|
|
|
osq_unlock(&lock->osq);
|
|
done:
|
|
/*
|
|
* If we fell out of the spin path because of need_resched(),
|
|
* reschedule now, before we try-lock the mutex. This avoids getting
|
|
* scheduled out right after we obtained the mutex.
|
|
*/
|
|
if (need_resched()) {
|
|
/*
|
|
* We _should_ have TASK_RUNNING here, but just in case
|
|
* we do not, make it so, otherwise we might get stuck.
|
|
*/
|
|
__set_current_state(TASK_RUNNING);
|
|
schedule_preempt_disabled();
|
|
}
|
|
|
|
return false;
|
|
}
|
|
#else
|
|
static bool mutex_optimistic_spin(struct mutex *lock,
|
|
struct ww_acquire_ctx *ww_ctx, const bool use_ww_ctx)
|
|
{
|
|
return false;
|
|
}
|
|
#endif
|
|
|
|
__visible __used noinline
|
|
void __sched __mutex_unlock_slowpath(atomic_t *lock_count);
|
|
|
|
/**
|
|
* mutex_unlock - release the mutex
|
|
* @lock: the mutex to be released
|
|
*
|
|
* Unlock a mutex that has been locked by this task previously.
|
|
*
|
|
* This function must not be used in interrupt context. Unlocking
|
|
* of a not locked mutex is not allowed.
|
|
*
|
|
* This function is similar to (but not equivalent to) up().
|
|
*/
|
|
void __sched mutex_unlock(struct mutex *lock)
|
|
{
|
|
/*
|
|
* The unlocking fastpath is the 0->1 transition from 'locked'
|
|
* into 'unlocked' state:
|
|
*/
|
|
#ifndef CONFIG_DEBUG_MUTEXES
|
|
/*
|
|
* When debugging is enabled we must not clear the owner before time,
|
|
* the slow path will always be taken, and that clears the owner field
|
|
* after verifying that it was indeed current.
|
|
*/
|
|
mutex_clear_owner(lock);
|
|
#endif
|
|
__mutex_fastpath_unlock(&lock->count, __mutex_unlock_slowpath);
|
|
}
|
|
|
|
EXPORT_SYMBOL(mutex_unlock);
|
|
|
|
/**
|
|
* ww_mutex_unlock - release the w/w mutex
|
|
* @lock: the mutex to be released
|
|
*
|
|
* Unlock a mutex that has been locked by this task previously with any of the
|
|
* ww_mutex_lock* functions (with or without an acquire context). It is
|
|
* forbidden to release the locks after releasing the acquire context.
|
|
*
|
|
* This function must not be used in interrupt context. Unlocking
|
|
* of a unlocked mutex is not allowed.
|
|
*/
|
|
void __sched ww_mutex_unlock(struct ww_mutex *lock)
|
|
{
|
|
/*
|
|
* The unlocking fastpath is the 0->1 transition from 'locked'
|
|
* into 'unlocked' state:
|
|
*/
|
|
if (lock->ctx) {
|
|
#ifdef CONFIG_DEBUG_MUTEXES
|
|
DEBUG_LOCKS_WARN_ON(!lock->ctx->acquired);
|
|
#endif
|
|
if (lock->ctx->acquired > 0)
|
|
lock->ctx->acquired--;
|
|
lock->ctx = NULL;
|
|
}
|
|
|
|
#ifndef CONFIG_DEBUG_MUTEXES
|
|
/*
|
|
* When debugging is enabled we must not clear the owner before time,
|
|
* the slow path will always be taken, and that clears the owner field
|
|
* after verifying that it was indeed current.
|
|
*/
|
|
mutex_clear_owner(&lock->base);
|
|
#endif
|
|
__mutex_fastpath_unlock(&lock->base.count, __mutex_unlock_slowpath);
|
|
}
|
|
EXPORT_SYMBOL(ww_mutex_unlock);
|
|
|
|
static inline int __sched
|
|
__ww_mutex_lock_check_stamp(struct mutex *lock, struct ww_acquire_ctx *ctx)
|
|
{
|
|
struct ww_mutex *ww = container_of(lock, struct ww_mutex, base);
|
|
struct ww_acquire_ctx *hold_ctx = READ_ONCE(ww->ctx);
|
|
|
|
if (!hold_ctx)
|
|
return 0;
|
|
|
|
if (ctx->stamp - hold_ctx->stamp <= LONG_MAX &&
|
|
(ctx->stamp != hold_ctx->stamp || ctx > hold_ctx)) {
|
|
#ifdef CONFIG_DEBUG_MUTEXES
|
|
DEBUG_LOCKS_WARN_ON(ctx->contending_lock);
|
|
ctx->contending_lock = ww;
|
|
#endif
|
|
return -EDEADLK;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Lock a mutex (possibly interruptible), slowpath:
|
|
*/
|
|
static __always_inline int __sched
|
|
__mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
|
|
struct lockdep_map *nest_lock, unsigned long ip,
|
|
struct ww_acquire_ctx *ww_ctx, const bool use_ww_ctx)
|
|
{
|
|
struct task_struct *task = current;
|
|
struct mutex_waiter waiter;
|
|
unsigned long flags;
|
|
int ret;
|
|
|
|
if (use_ww_ctx) {
|
|
struct ww_mutex *ww = container_of(lock, struct ww_mutex, base);
|
|
if (unlikely(ww_ctx == READ_ONCE(ww->ctx)))
|
|
return -EALREADY;
|
|
}
|
|
|
|
preempt_disable();
|
|
mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, ip);
|
|
|
|
if (mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx)) {
|
|
/* got the lock, yay! */
|
|
preempt_enable();
|
|
return 0;
|
|
}
|
|
|
|
spin_lock_mutex(&lock->wait_lock, flags);
|
|
|
|
/*
|
|
* Once more, try to acquire the lock. Only try-lock the mutex if
|
|
* it is unlocked to reduce unnecessary xchg() operations.
|
|
*/
|
|
if (!mutex_is_locked(lock) &&
|
|
(atomic_xchg_acquire(&lock->count, 0) == 1))
|
|
goto skip_wait;
|
|
|
|
debug_mutex_lock_common(lock, &waiter);
|
|
debug_mutex_add_waiter(lock, &waiter, task);
|
|
|
|
/* add waiting tasks to the end of the waitqueue (FIFO): */
|
|
list_add_tail(&waiter.list, &lock->wait_list);
|
|
waiter.task = task;
|
|
|
|
lock_contended(&lock->dep_map, ip);
|
|
|
|
for (;;) {
|
|
/*
|
|
* Lets try to take the lock again - this is needed even if
|
|
* we get here for the first time (shortly after failing to
|
|
* acquire the lock), to make sure that we get a wakeup once
|
|
* it's unlocked. Later on, if we sleep, this is the
|
|
* operation that gives us the lock. We xchg it to -1, so
|
|
* that when we release the lock, we properly wake up the
|
|
* other waiters. We only attempt the xchg if the count is
|
|
* non-negative in order to avoid unnecessary xchg operations:
|
|
*/
|
|
if (atomic_read(&lock->count) >= 0 &&
|
|
(atomic_xchg_acquire(&lock->count, -1) == 1))
|
|
break;
|
|
|
|
/*
|
|
* got a signal? (This code gets eliminated in the
|
|
* TASK_UNINTERRUPTIBLE case.)
|
|
*/
|
|
if (unlikely(signal_pending_state(state, task))) {
|
|
ret = -EINTR;
|
|
goto err;
|
|
}
|
|
|
|
if (use_ww_ctx && ww_ctx->acquired > 0) {
|
|
ret = __ww_mutex_lock_check_stamp(lock, ww_ctx);
|
|
if (ret)
|
|
goto err;
|
|
}
|
|
|
|
__set_task_state(task, state);
|
|
|
|
/* didn't get the lock, go to sleep: */
|
|
spin_unlock_mutex(&lock->wait_lock, flags);
|
|
schedule_preempt_disabled();
|
|
spin_lock_mutex(&lock->wait_lock, flags);
|
|
}
|
|
__set_task_state(task, TASK_RUNNING);
|
|
|
|
mutex_remove_waiter(lock, &waiter, task);
|
|
/* set it to 0 if there are no waiters left: */
|
|
if (likely(list_empty(&lock->wait_list)))
|
|
atomic_set(&lock->count, 0);
|
|
debug_mutex_free_waiter(&waiter);
|
|
|
|
skip_wait:
|
|
/* got the lock - cleanup and rejoice! */
|
|
lock_acquired(&lock->dep_map, ip);
|
|
mutex_set_owner(lock);
|
|
|
|
if (use_ww_ctx) {
|
|
struct ww_mutex *ww = container_of(lock, struct ww_mutex, base);
|
|
ww_mutex_set_context_slowpath(ww, ww_ctx);
|
|
}
|
|
|
|
spin_unlock_mutex(&lock->wait_lock, flags);
|
|
preempt_enable();
|
|
return 0;
|
|
|
|
err:
|
|
mutex_remove_waiter(lock, &waiter, task);
|
|
spin_unlock_mutex(&lock->wait_lock, flags);
|
|
debug_mutex_free_waiter(&waiter);
|
|
mutex_release(&lock->dep_map, 1, ip);
|
|
preempt_enable();
|
|
return ret;
|
|
}
|
|
|
|
#ifdef CONFIG_DEBUG_LOCK_ALLOC
|
|
void __sched
|
|
mutex_lock_nested(struct mutex *lock, unsigned int subclass)
|
|
{
|
|
might_sleep();
|
|
__mutex_lock_common(lock, TASK_UNINTERRUPTIBLE,
|
|
subclass, NULL, _RET_IP_, NULL, 0);
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(mutex_lock_nested);
|
|
|
|
void __sched
|
|
_mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest)
|
|
{
|
|
might_sleep();
|
|
__mutex_lock_common(lock, TASK_UNINTERRUPTIBLE,
|
|
0, nest, _RET_IP_, NULL, 0);
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(_mutex_lock_nest_lock);
|
|
|
|
int __sched
|
|
mutex_lock_killable_nested(struct mutex *lock, unsigned int subclass)
|
|
{
|
|
might_sleep();
|
|
return __mutex_lock_common(lock, TASK_KILLABLE,
|
|
subclass, NULL, _RET_IP_, NULL, 0);
|
|
}
|
|
EXPORT_SYMBOL_GPL(mutex_lock_killable_nested);
|
|
|
|
int __sched
|
|
mutex_lock_interruptible_nested(struct mutex *lock, unsigned int subclass)
|
|
{
|
|
might_sleep();
|
|
return __mutex_lock_common(lock, TASK_INTERRUPTIBLE,
|
|
subclass, NULL, _RET_IP_, NULL, 0);
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(mutex_lock_interruptible_nested);
|
|
|
|
static inline int
|
|
ww_mutex_deadlock_injection(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
|
|
{
|
|
#ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH
|
|
unsigned tmp;
|
|
|
|
if (ctx->deadlock_inject_countdown-- == 0) {
|
|
tmp = ctx->deadlock_inject_interval;
|
|
if (tmp > UINT_MAX/4)
|
|
tmp = UINT_MAX;
|
|
else
|
|
tmp = tmp*2 + tmp + tmp/2;
|
|
|
|
ctx->deadlock_inject_interval = tmp;
|
|
ctx->deadlock_inject_countdown = tmp;
|
|
ctx->contending_lock = lock;
|
|
|
|
ww_mutex_unlock(lock);
|
|
|
|
return -EDEADLK;
|
|
}
|
|
#endif
|
|
|
|
return 0;
|
|
}
|
|
|
|
int __sched
|
|
__ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
|
|
{
|
|
int ret;
|
|
|
|
might_sleep();
|
|
ret = __mutex_lock_common(&lock->base, TASK_UNINTERRUPTIBLE,
|
|
0, &ctx->dep_map, _RET_IP_, ctx, 1);
|
|
if (!ret && ctx->acquired > 1)
|
|
return ww_mutex_deadlock_injection(lock, ctx);
|
|
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL_GPL(__ww_mutex_lock);
|
|
|
|
int __sched
|
|
__ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
|
|
{
|
|
int ret;
|
|
|
|
might_sleep();
|
|
ret = __mutex_lock_common(&lock->base, TASK_INTERRUPTIBLE,
|
|
0, &ctx->dep_map, _RET_IP_, ctx, 1);
|
|
|
|
if (!ret && ctx->acquired > 1)
|
|
return ww_mutex_deadlock_injection(lock, ctx);
|
|
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL_GPL(__ww_mutex_lock_interruptible);
|
|
|
|
#endif
|
|
|
|
/*
|
|
* Release the lock, slowpath:
|
|
*/
|
|
static inline void
|
|
__mutex_unlock_common_slowpath(struct mutex *lock, int nested)
|
|
{
|
|
unsigned long flags;
|
|
|
|
/*
|
|
* As a performance measurement, release the lock before doing other
|
|
* wakeup related duties to follow. This allows other tasks to acquire
|
|
* the lock sooner, while still handling cleanups in past unlock calls.
|
|
* This can be done as we do not enforce strict equivalence between the
|
|
* mutex counter and wait_list.
|
|
*
|
|
*
|
|
* Some architectures leave the lock unlocked in the fastpath failure
|
|
* case, others need to leave it locked. In the later case we have to
|
|
* unlock it here - as the lock counter is currently 0 or negative.
|
|
*/
|
|
if (__mutex_slowpath_needs_to_unlock())
|
|
atomic_set(&lock->count, 1);
|
|
|
|
spin_lock_mutex(&lock->wait_lock, flags);
|
|
mutex_release(&lock->dep_map, nested, _RET_IP_);
|
|
debug_mutex_unlock(lock);
|
|
|
|
if (!list_empty(&lock->wait_list)) {
|
|
/* get the first entry from the wait-list: */
|
|
struct mutex_waiter *waiter =
|
|
list_entry(lock->wait_list.next,
|
|
struct mutex_waiter, list);
|
|
|
|
debug_mutex_wake_waiter(lock, waiter);
|
|
|
|
wake_up_process(waiter->task);
|
|
}
|
|
|
|
spin_unlock_mutex(&lock->wait_lock, flags);
|
|
}
|
|
|
|
/*
|
|
* Release the lock, slowpath:
|
|
*/
|
|
__visible void
|
|
__mutex_unlock_slowpath(atomic_t *lock_count)
|
|
{
|
|
struct mutex *lock = container_of(lock_count, struct mutex, count);
|
|
|
|
__mutex_unlock_common_slowpath(lock, 1);
|
|
}
|
|
|
|
#ifndef CONFIG_DEBUG_LOCK_ALLOC
|
|
/*
|
|
* Here come the less common (and hence less performance-critical) APIs:
|
|
* mutex_lock_interruptible() and mutex_trylock().
|
|
*/
|
|
static noinline int __sched
|
|
__mutex_lock_killable_slowpath(struct mutex *lock);
|
|
|
|
static noinline int __sched
|
|
__mutex_lock_interruptible_slowpath(struct mutex *lock);
|
|
|
|
/**
|
|
* mutex_lock_interruptible - acquire the mutex, interruptible
|
|
* @lock: the mutex to be acquired
|
|
*
|
|
* Lock the mutex like mutex_lock(), and return 0 if the mutex has
|
|
* been acquired or sleep until the mutex becomes available. If a
|
|
* signal arrives while waiting for the lock then this function
|
|
* returns -EINTR.
|
|
*
|
|
* This function is similar to (but not equivalent to) down_interruptible().
|
|
*/
|
|
int __sched mutex_lock_interruptible(struct mutex *lock)
|
|
{
|
|
int ret;
|
|
|
|
might_sleep();
|
|
ret = __mutex_fastpath_lock_retval(&lock->count);
|
|
if (likely(!ret)) {
|
|
mutex_set_owner(lock);
|
|
return 0;
|
|
} else
|
|
return __mutex_lock_interruptible_slowpath(lock);
|
|
}
|
|
|
|
EXPORT_SYMBOL(mutex_lock_interruptible);
|
|
|
|
int __sched mutex_lock_killable(struct mutex *lock)
|
|
{
|
|
int ret;
|
|
|
|
might_sleep();
|
|
ret = __mutex_fastpath_lock_retval(&lock->count);
|
|
if (likely(!ret)) {
|
|
mutex_set_owner(lock);
|
|
return 0;
|
|
} else
|
|
return __mutex_lock_killable_slowpath(lock);
|
|
}
|
|
EXPORT_SYMBOL(mutex_lock_killable);
|
|
|
|
__visible void __sched
|
|
__mutex_lock_slowpath(atomic_t *lock_count)
|
|
{
|
|
struct mutex *lock = container_of(lock_count, struct mutex, count);
|
|
|
|
__mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0,
|
|
NULL, _RET_IP_, NULL, 0);
|
|
}
|
|
|
|
static noinline int __sched
|
|
__mutex_lock_killable_slowpath(struct mutex *lock)
|
|
{
|
|
return __mutex_lock_common(lock, TASK_KILLABLE, 0,
|
|
NULL, _RET_IP_, NULL, 0);
|
|
}
|
|
|
|
static noinline int __sched
|
|
__mutex_lock_interruptible_slowpath(struct mutex *lock)
|
|
{
|
|
return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, 0,
|
|
NULL, _RET_IP_, NULL, 0);
|
|
}
|
|
|
|
static noinline int __sched
|
|
__ww_mutex_lock_slowpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
|
|
{
|
|
return __mutex_lock_common(&lock->base, TASK_UNINTERRUPTIBLE, 0,
|
|
NULL, _RET_IP_, ctx, 1);
|
|
}
|
|
|
|
static noinline int __sched
|
|
__ww_mutex_lock_interruptible_slowpath(struct ww_mutex *lock,
|
|
struct ww_acquire_ctx *ctx)
|
|
{
|
|
return __mutex_lock_common(&lock->base, TASK_INTERRUPTIBLE, 0,
|
|
NULL, _RET_IP_, ctx, 1);
|
|
}
|
|
|
|
#endif
|
|
|
|
/*
|
|
* Spinlock based trylock, we take the spinlock and check whether we
|
|
* can get the lock:
|
|
*/
|
|
static inline int __mutex_trylock_slowpath(atomic_t *lock_count)
|
|
{
|
|
struct mutex *lock = container_of(lock_count, struct mutex, count);
|
|
unsigned long flags;
|
|
int prev;
|
|
|
|
/* No need to trylock if the mutex is locked. */
|
|
if (mutex_is_locked(lock))
|
|
return 0;
|
|
|
|
spin_lock_mutex(&lock->wait_lock, flags);
|
|
|
|
prev = atomic_xchg_acquire(&lock->count, -1);
|
|
if (likely(prev == 1)) {
|
|
mutex_set_owner(lock);
|
|
mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_);
|
|
}
|
|
|
|
/* Set it back to 0 if there are no waiters: */
|
|
if (likely(list_empty(&lock->wait_list)))
|
|
atomic_set(&lock->count, 0);
|
|
|
|
spin_unlock_mutex(&lock->wait_lock, flags);
|
|
|
|
return prev == 1;
|
|
}
|
|
|
|
/**
|
|
* mutex_trylock - try to acquire the mutex, without waiting
|
|
* @lock: the mutex to be acquired
|
|
*
|
|
* Try to acquire the mutex atomically. Returns 1 if the mutex
|
|
* has been acquired successfully, and 0 on contention.
|
|
*
|
|
* NOTE: this function follows the spin_trylock() convention, so
|
|
* it is negated from the down_trylock() return values! Be careful
|
|
* about this when converting semaphore users to mutexes.
|
|
*
|
|
* This function must not be used in interrupt context. The
|
|
* mutex must be released by the same task that acquired it.
|
|
*/
|
|
int __sched mutex_trylock(struct mutex *lock)
|
|
{
|
|
int ret;
|
|
|
|
ret = __mutex_fastpath_trylock(&lock->count, __mutex_trylock_slowpath);
|
|
if (ret)
|
|
mutex_set_owner(lock);
|
|
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL(mutex_trylock);
|
|
|
|
#ifndef CONFIG_DEBUG_LOCK_ALLOC
|
|
int __sched
|
|
__ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
|
|
{
|
|
int ret;
|
|
|
|
might_sleep();
|
|
|
|
ret = __mutex_fastpath_lock_retval(&lock->base.count);
|
|
|
|
if (likely(!ret)) {
|
|
ww_mutex_set_context_fastpath(lock, ctx);
|
|
mutex_set_owner(&lock->base);
|
|
} else
|
|
ret = __ww_mutex_lock_slowpath(lock, ctx);
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL(__ww_mutex_lock);
|
|
|
|
int __sched
|
|
__ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
|
|
{
|
|
int ret;
|
|
|
|
might_sleep();
|
|
|
|
ret = __mutex_fastpath_lock_retval(&lock->base.count);
|
|
|
|
if (likely(!ret)) {
|
|
ww_mutex_set_context_fastpath(lock, ctx);
|
|
mutex_set_owner(&lock->base);
|
|
} else
|
|
ret = __ww_mutex_lock_interruptible_slowpath(lock, ctx);
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL(__ww_mutex_lock_interruptible);
|
|
|
|
#endif
|
|
|
|
/**
|
|
* atomic_dec_and_mutex_lock - return holding mutex if we dec to 0
|
|
* @cnt: the atomic which we are to dec
|
|
* @lock: the mutex to return holding if we dec to 0
|
|
*
|
|
* return true and hold lock if we dec to 0, return false otherwise
|
|
*/
|
|
int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock)
|
|
{
|
|
/* dec if we can't possibly hit 0 */
|
|
if (atomic_add_unless(cnt, -1, 1))
|
|
return 0;
|
|
/* we might hit 0, so take the lock */
|
|
mutex_lock(lock);
|
|
if (!atomic_dec_and_test(cnt)) {
|
|
/* when we actually did the dec, we didn't hit 0 */
|
|
mutex_unlock(lock);
|
|
return 0;
|
|
}
|
|
/* we hit 0, and we hold the lock */
|
|
return 1;
|
|
}
|
|
EXPORT_SYMBOL(atomic_dec_and_mutex_lock);
|