android_kernel_xiaomi_sm8450/kernel/sched/wait.c
Greg Kroah-Hartman afc997898e This is the 5.10.85 stable release
-----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCAAdFiEEZH8oZUiU471FcZm+ONu9yGCSaT4FAmG4cugACgkQONu9yGCS
 aT4+uxAAiLJvOIA6ElsmMq2c3pNu9UDPh58j1FlmhggAxr7baIvR1UuEZURTSLW9
 pnu+r9bHkhJGBOpANfPJAQZqv+JtCi3crMhw0mwHJ0Mls3TNSmclzB1+jGM4w93E
 cT+5hoDeQqwZwpKYvWI7u9UGEE0BXluVTRCvmuncaJ8wGbxnDgV0AEXe32XDlFxB
 kSLAXO1FFn8Z1yMg9BMVURU9IAszdwCIhqbcNWnPunOPowdHDWBJdF7eSZUqmJfq
 TMyFgm6c6ENbBrwYt+9qf+1oS/D9r6TEjwaFoRJ4ApWSAD4iKV7U6dA0rxm9mrMl
 nSAxNXuSXXYszoYjrxPPRGhCY/URahs1Vmju1WK//4vz3brxk5N88T+2nN7PMYKn
 bIHGTl9SadlrHvi/OBqOvbsNMHX+ln/V/y7ct0fsxXeNBHYXdXCtimRDvtsj9kmp
 HO9OLXVsF6DUM22ODW28Vxt7HGN3XQzs0y2jwfzdMV81p3oEqP9wWQITwG2LVVAE
 WdkvQ/3ugdkR9F15Vp0cjkbJQLN4UbYUJW5K7SZTW013TgsYyIHQrP5qj9xvfwNt
 KdILXVMH2JqPXAkRqmFqIeNIUX2oevWwpgV/SwqIj3T5ytmXPluZsaMlGg5xZ401
 Xuhp0LPU6rl+wcCt1bInZvn8nrTVDADpao7xTbSyoel5TAunVrk=
 =u1Am
 -----END PGP SIGNATURE-----

Merge 5.10.85 into android12-5.10-lts

Changes in 5.10.85
	usb: gadget: uvc: fix multiple opens
	gcc-plugins: simplify GCC plugin-dev capability test
	gcc-plugins: fix gcc 11 indigestion with plugins...
	HID: quirks: Add quirk for the Microsoft Surface 3 type-cover
	HID: google: add eel USB id
	HID: add hid_is_usb() function to make it simpler for USB detection
	HID: add USB_HID dependancy to hid-prodikeys
	HID: add USB_HID dependancy to hid-chicony
	HID: add USB_HID dependancy on some USB HID drivers
	HID: bigbenff: prevent null pointer dereference
	HID: wacom: fix problems when device is not a valid USB device
	HID: check for valid USB device for many HID drivers
	nft_set_pipapo: Fix bucket load in AVX2 lookup routine for six 8-bit groups
	IB/hfi1: Insure use of smp_processor_id() is preempt disabled
	IB/hfi1: Fix early init panic
	IB/hfi1: Fix leak of rcvhdrtail_dummy_kvaddr
	can: kvaser_usb: get CAN clock frequency from device
	can: kvaser_pciefd: kvaser_pciefd_rx_error_frame(): increase correct stats->{rx,tx}_errors counter
	can: sja1000: fix use after free in ems_pcmcia_add_card()
	x86/sme: Explicitly map new EFI memmap table as encrypted
	drm/amd/amdkfd: adjust dummy functions' placement
	drm/amdkfd: separate kfd_iommu_resume from kfd_resume
	drm/amdgpu: add amdgpu_amdkfd_resume_iommu
	drm/amdgpu: move iommu_resume before ip init/resume
	drm/amdgpu: init iommu after amdkfd device init
	drm/amdkfd: fix boot failure when iommu is disabled in Picasso.
	nfc: fix potential NULL pointer deref in nfc_genl_dump_ses_done
	selftests: netfilter: add a vrf+conntrack testcase
	vrf: don't run conntrack on vrf with !dflt qdisc
	bpf, x86: Fix "no previous prototype" warning
	bpf: Fix the off-by-two error in range markings
	ice: ignore dropped packets during init
	bonding: make tx_rebalance_counter an atomic
	nfp: Fix memory leak in nfp_cpp_area_cache_add()
	seg6: fix the iif in the IPv6 socket control block
	udp: using datalen to cap max gso segments
	netfilter: conntrack: annotate data-races around ct->timeout
	iavf: restore MSI state on reset
	iavf: Fix reporting when setting descriptor count
	IB/hfi1: Correct guard on eager buffer deallocation
	devlink: fix netns refcount leak in devlink_nl_cmd_reload()
	net/sched: fq_pie: prevent dismantle issue
	KVM: x86: Wait for IPIs to be delivered when handling Hyper-V TLB flush hypercall
	mm: bdi: initialize bdi_min_ratio when bdi is unregistered
	ALSA: ctl: Fix copy of updated id with element read/write
	ALSA: hda/realtek - Add headset Mic support for Lenovo ALC897 platform
	ALSA: hda/realtek: Fix quirk for TongFang PHxTxX1
	ALSA: pcm: oss: Fix negative period/buffer sizes
	ALSA: pcm: oss: Limit the period size to 16MB
	ALSA: pcm: oss: Handle missing errors in snd_pcm_oss_change_params*()
	scsi: qla2xxx: Format log strings only if needed
	btrfs: clear extent buffer uptodate when we fail to write it
	btrfs: replace the BUG_ON in btrfs_del_root_ref with proper error handling
	md: fix update super 1.0 on rdev size change
	nfsd: fix use-after-free due to delegation race
	nfsd: Fix nsfd startup race (again)
	tracefs: Have new files inherit the ownership of their parent
	mmc: renesas_sdhi: initialize variable properly when tuning
	clk: qcom: regmap-mux: fix parent clock lookup
	drm/syncobj: Deal with signalled fences in drm_syncobj_find_fence.
	can: pch_can: pch_can_rx_normal: fix use after free
	can: m_can: Disable and ignore ELO interrupt
	libata: add horkage for ASMedia 1092
	wait: add wake_up_pollfree()
	binder: use wake_up_pollfree()
	signalfd: use wake_up_pollfree()
	aio: keep poll requests on waitqueue until completed
	aio: fix use-after-free due to missing POLLFREE handling
	net: mvpp2: fix XDP rx queues registering
	tracefs: Set all files to the same group ownership as the mount option
	block: fix ioprio_get(IOPRIO_WHO_PGRP) vs setuid(2)
	scsi: pm80xx: Do not call scsi_remove_host() in pm8001_alloc()
	scsi: scsi_debug: Fix buffer size of REPORT ZONES command
	qede: validate non LSO skb length
	PM: runtime: Fix pm_runtime_active() kerneldoc comment
	ASoC: rt5682: Fix crash due to out of scope stack vars
	ASoC: qdsp6: q6routing: Fix return value from msm_routing_put_audio_mixer
	ASoC: codecs: wsa881x: fix return values from kcontrol put
	ASoC: codecs: wcd934x: handle channel mappping list correctly
	ASoC: codecs: wcd934x: return correct value from mixer put
	RDMA/hns: Do not halt commands during reset until later
	RDMA/hns: Do not destroy QP resources in the hw resetting phase
	clk: imx: use module_platform_driver
	i40e: Fix failed opcode appearing if handling messages from VF
	i40e: Fix pre-set max number of queues for VF
	mtd: rawnand: fsmc: Take instruction delay into account
	mtd: rawnand: fsmc: Fix timing computation
	i40e: Fix NULL pointer dereference in i40e_dbg_dump_desc
	Revert "PCI: aardvark: Fix support for PCI_ROM_ADDRESS1 on emulated bridge"
	perf tools: Fix SMT detection fast read path
	Documentation/locking/locktypes: Update migrate_disable() bits.
	dt-bindings: net: Reintroduce PHY no lane swap binding
	tools build: Remove needless libpython-version feature check that breaks test-all fast path
	net: cdc_ncm: Allow for dwNtbOutMaxSize to be unset or zero
	net: altera: set a couple error code in probe()
	net: fec: only clear interrupt of handling queue in fec_enet_rx_queue()
	net, neigh: clear whole pneigh_entry at alloc time
	net/qla3xxx: fix an error code in ql_adapter_up()
	selftests/fib_tests: Rework fib_rp_filter_test()
	USB: gadget: detect too-big endpoint 0 requests
	USB: gadget: zero allocate endpoint 0 buffers
	usb: core: config: fix validation of wMaxPacketValue entries
	xhci: Remove CONFIG_USB_DEFAULT_PERSIST to prevent xHCI from runtime suspending
	usb: core: config: using bit mask instead of individual bits
	xhci: avoid race between disable slot command and host runtime suspend
	iio: gyro: adxrs290: fix data signedness
	iio: trigger: Fix reference counting
	iio: trigger: stm32-timer: fix MODULE_ALIAS
	iio: stk3310: Don't return error code in interrupt handler
	iio: mma8452: Fix trigger reference couting
	iio: ltr501: Don't return error code in trigger handler
	iio: kxsd9: Don't return error code in trigger handler
	iio: itg3200: Call iio_trigger_notify_done() on error
	iio: dln2-adc: Fix lockdep complaint
	iio: dln2: Check return value of devm_iio_trigger_register()
	iio: at91-sama5d2: Fix incorrect sign extension
	iio: adc: stm32: fix a current leak by resetting pcsel before disabling vdda
	iio: adc: axp20x_adc: fix charging current reporting on AXP22x
	iio: ad7768-1: Call iio_trigger_notify_done() on error
	iio: accel: kxcjk-1013: Fix possible memory leak in probe and remove
	csky: fix typo of fpu config macro
	irqchip/aspeed-scu: Replace update_bits with write_bits.
	irqchip/armada-370-xp: Fix return value of armada_370_xp_msi_alloc()
	irqchip/armada-370-xp: Fix support for Multi-MSI interrupts
	irqchip/irq-gic-v3-its.c: Force synchronisation when issuing INVALL
	irqchip: nvic: Fix offset for Interrupt Priority Offsets
	misc: fastrpc: fix improper packet size calculation
	bpf: Add selftests to cover packet access corner cases
	kbuild: simplify GCC_PLUGINS enablement in dummy-tools/gcc
	doc: gcc-plugins: update gcc-plugins.rst
	MAINTAINERS: adjust GCC PLUGINS after gcc-plugin.sh removal
	Documentation/Kbuild: Remove references to gcc-plugin.sh
	Linux 5.10.85

Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
Change-Id: I351da1b00f30a370b021125180a48b1c1ecb97ce
2021-12-14 15:11:46 +01:00

475 lines
14 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/*
* Generic waiting primitives.
*
* (C) 2004 Nadia Yvette Chambers, Oracle
*/
#include "sched.h"
#include <trace/hooks/sched.h>
void __init_waitqueue_head(struct wait_queue_head *wq_head, const char *name, struct lock_class_key *key)
{
spin_lock_init(&wq_head->lock);
lockdep_set_class_and_name(&wq_head->lock, key, name);
INIT_LIST_HEAD(&wq_head->head);
}
EXPORT_SYMBOL(__init_waitqueue_head);
void add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
{
unsigned long flags;
wq_entry->flags &= ~WQ_FLAG_EXCLUSIVE;
spin_lock_irqsave(&wq_head->lock, flags);
__add_wait_queue(wq_head, wq_entry);
spin_unlock_irqrestore(&wq_head->lock, flags);
}
EXPORT_SYMBOL(add_wait_queue);
void add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
{
unsigned long flags;
wq_entry->flags |= WQ_FLAG_EXCLUSIVE;
spin_lock_irqsave(&wq_head->lock, flags);
__add_wait_queue_entry_tail(wq_head, wq_entry);
spin_unlock_irqrestore(&wq_head->lock, flags);
}
EXPORT_SYMBOL(add_wait_queue_exclusive);
void remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
{
unsigned long flags;
spin_lock_irqsave(&wq_head->lock, flags);
__remove_wait_queue(wq_head, wq_entry);
spin_unlock_irqrestore(&wq_head->lock, flags);
}
EXPORT_SYMBOL(remove_wait_queue);
/*
* Scan threshold to break wait queue walk.
* This allows a waker to take a break from holding the
* wait queue lock during the wait queue walk.
*/
#define WAITQUEUE_WALK_BREAK_CNT 64
/*
* The core wakeup function. Non-exclusive wakeups (nr_exclusive == 0) just
* wake everything up. If it's an exclusive wakeup (nr_exclusive == small +ve
* number) then we wake all the non-exclusive tasks and one exclusive task.
*
* There are circumstances in which we can try to wake a task which has already
* started to run but is not in state TASK_RUNNING. try_to_wake_up() returns
* zero in this (rare) case, and we handle it by continuing to scan the queue.
*/
static int __wake_up_common(struct wait_queue_head *wq_head, unsigned int mode,
int nr_exclusive, int wake_flags, void *key,
wait_queue_entry_t *bookmark)
{
wait_queue_entry_t *curr, *next;
int cnt = 0;
lockdep_assert_held(&wq_head->lock);
if (bookmark && (bookmark->flags & WQ_FLAG_BOOKMARK)) {
curr = list_next_entry(bookmark, entry);
list_del(&bookmark->entry);
bookmark->flags = 0;
} else
curr = list_first_entry(&wq_head->head, wait_queue_entry_t, entry);
if (&curr->entry == &wq_head->head)
return nr_exclusive;
list_for_each_entry_safe_from(curr, next, &wq_head->head, entry) {
unsigned flags = curr->flags;
int ret;
if (flags & WQ_FLAG_BOOKMARK)
continue;
ret = curr->func(curr, mode, wake_flags, key);
if (ret < 0)
break;
if (ret && (flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive)
break;
if (bookmark && (++cnt > WAITQUEUE_WALK_BREAK_CNT) &&
(&next->entry != &wq_head->head)) {
bookmark->flags = WQ_FLAG_BOOKMARK;
list_add_tail(&bookmark->entry, &next->entry);
break;
}
}
return nr_exclusive;
}
static void __wake_up_common_lock(struct wait_queue_head *wq_head, unsigned int mode,
int nr_exclusive, int wake_flags, void *key)
{
unsigned long flags;
wait_queue_entry_t bookmark;
bookmark.flags = 0;
bookmark.private = NULL;
bookmark.func = NULL;
INIT_LIST_HEAD(&bookmark.entry);
do {
spin_lock_irqsave(&wq_head->lock, flags);
nr_exclusive = __wake_up_common(wq_head, mode, nr_exclusive,
wake_flags, key, &bookmark);
spin_unlock_irqrestore(&wq_head->lock, flags);
} while (bookmark.flags & WQ_FLAG_BOOKMARK);
}
/**
* __wake_up - wake up threads blocked on a waitqueue.
* @wq_head: the waitqueue
* @mode: which threads
* @nr_exclusive: how many wake-one or wake-many threads to wake up
* @key: is directly passed to the wakeup function
*
* If this function wakes up a task, it executes a full memory barrier before
* accessing the task state.
*/
void __wake_up(struct wait_queue_head *wq_head, unsigned int mode,
int nr_exclusive, void *key)
{
__wake_up_common_lock(wq_head, mode, nr_exclusive, 0, key);
}
EXPORT_SYMBOL(__wake_up);
/*
* Same as __wake_up but called with the spinlock in wait_queue_head_t held.
*/
void __wake_up_locked(struct wait_queue_head *wq_head, unsigned int mode, int nr)
{
__wake_up_common(wq_head, mode, nr, 0, NULL, NULL);
}
EXPORT_SYMBOL_GPL(__wake_up_locked);
void __wake_up_locked_key(struct wait_queue_head *wq_head, unsigned int mode, void *key)
{
__wake_up_common(wq_head, mode, 1, 0, key, NULL);
}
EXPORT_SYMBOL_GPL(__wake_up_locked_key);
void __wake_up_locked_key_bookmark(struct wait_queue_head *wq_head,
unsigned int mode, void *key, wait_queue_entry_t *bookmark)
{
__wake_up_common(wq_head, mode, 1, 0, key, bookmark);
}
EXPORT_SYMBOL_GPL(__wake_up_locked_key_bookmark);
/**
* __wake_up_sync_key - wake up threads blocked on a waitqueue.
* @wq_head: the waitqueue
* @mode: which threads
* @key: opaque value to be passed to wakeup targets
*
* The sync wakeup differs that the waker knows that it will schedule
* away soon, so while the target thread will be woken up, it will not
* be migrated to another CPU - ie. the two threads are 'synchronized'
* with each other. This can prevent needless bouncing between CPUs.
*
* On UP it can prevent extra preemption.
*
* If this function wakes up a task, it executes a full memory barrier before
* accessing the task state.
*/
void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode,
void *key)
{
int wake_flags = WF_SYNC;
if (unlikely(!wq_head))
return;
trace_android_vh_set_wake_flags(&wake_flags, &mode);
__wake_up_common_lock(wq_head, mode, 1, wake_flags, key);
}
EXPORT_SYMBOL_GPL(__wake_up_sync_key);
/**
* __wake_up_locked_sync_key - wake up a thread blocked on a locked waitqueue.
* @wq_head: the waitqueue
* @mode: which threads
* @key: opaque value to be passed to wakeup targets
*
* The sync wakeup differs in that the waker knows that it will schedule
* away soon, so while the target thread will be woken up, it will not
* be migrated to another CPU - ie. the two threads are 'synchronized'
* with each other. This can prevent needless bouncing between CPUs.
*
* On UP it can prevent extra preemption.
*
* If this function wakes up a task, it executes a full memory barrier before
* accessing the task state.
*/
void __wake_up_locked_sync_key(struct wait_queue_head *wq_head,
unsigned int mode, void *key)
{
__wake_up_common(wq_head, mode, 1, WF_SYNC, key, NULL);
}
EXPORT_SYMBOL_GPL(__wake_up_locked_sync_key);
/*
* __wake_up_sync - see __wake_up_sync_key()
*/
void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode)
{
__wake_up_sync_key(wq_head, mode, NULL);
}
EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */
void __wake_up_pollfree(struct wait_queue_head *wq_head)
{
__wake_up(wq_head, TASK_NORMAL, 0, poll_to_key(EPOLLHUP | POLLFREE));
/* POLLFREE must have cleared the queue. */
WARN_ON_ONCE(waitqueue_active(wq_head));
}
/*
* Note: we use "set_current_state()" _after_ the wait-queue add,
* because we need a memory barrier there on SMP, so that any
* wake-function that tests for the wait-queue being active
* will be guaranteed to see waitqueue addition _or_ subsequent
* tests in this thread will see the wakeup having taken place.
*
* The spin_unlock() itself is semi-permeable and only protects
* one way (it only protects stuff inside the critical region and
* stops them from bleeding out - it would still allow subsequent
* loads to move into the critical region).
*/
void
prepare_to_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state)
{
unsigned long flags;
wq_entry->flags &= ~WQ_FLAG_EXCLUSIVE;
spin_lock_irqsave(&wq_head->lock, flags);
if (list_empty(&wq_entry->entry))
__add_wait_queue(wq_head, wq_entry);
set_current_state(state);
spin_unlock_irqrestore(&wq_head->lock, flags);
}
EXPORT_SYMBOL(prepare_to_wait);
/* Returns true if we are the first waiter in the queue, false otherwise. */
bool
prepare_to_wait_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state)
{
unsigned long flags;
bool was_empty = false;
wq_entry->flags |= WQ_FLAG_EXCLUSIVE;
spin_lock_irqsave(&wq_head->lock, flags);
if (list_empty(&wq_entry->entry)) {
was_empty = list_empty(&wq_head->head);
__add_wait_queue_entry_tail(wq_head, wq_entry);
}
set_current_state(state);
spin_unlock_irqrestore(&wq_head->lock, flags);
return was_empty;
}
EXPORT_SYMBOL(prepare_to_wait_exclusive);
void init_wait_entry(struct wait_queue_entry *wq_entry, int flags)
{
wq_entry->flags = flags;
wq_entry->private = current;
wq_entry->func = autoremove_wake_function;
INIT_LIST_HEAD(&wq_entry->entry);
}
EXPORT_SYMBOL(init_wait_entry);
long prepare_to_wait_event(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state)
{
unsigned long flags;
long ret = 0;
spin_lock_irqsave(&wq_head->lock, flags);
if (signal_pending_state(state, current)) {
/*
* Exclusive waiter must not fail if it was selected by wakeup,
* it should "consume" the condition we were waiting for.
*
* The caller will recheck the condition and return success if
* we were already woken up, we can not miss the event because
* wakeup locks/unlocks the same wq_head->lock.
*
* But we need to ensure that set-condition + wakeup after that
* can't see us, it should wake up another exclusive waiter if
* we fail.
*/
list_del_init(&wq_entry->entry);
ret = -ERESTARTSYS;
} else {
if (list_empty(&wq_entry->entry)) {
if (wq_entry->flags & WQ_FLAG_EXCLUSIVE)
__add_wait_queue_entry_tail(wq_head, wq_entry);
else
__add_wait_queue(wq_head, wq_entry);
}
set_current_state(state);
}
spin_unlock_irqrestore(&wq_head->lock, flags);
return ret;
}
EXPORT_SYMBOL(prepare_to_wait_event);
/*
* Note! These two wait functions are entered with the
* wait-queue lock held (and interrupts off in the _irq
* case), so there is no race with testing the wakeup
* condition in the caller before they add the wait
* entry to the wake queue.
*/
int do_wait_intr(wait_queue_head_t *wq, wait_queue_entry_t *wait)
{
if (likely(list_empty(&wait->entry)))
__add_wait_queue_entry_tail(wq, wait);
set_current_state(TASK_INTERRUPTIBLE);
if (signal_pending(current))
return -ERESTARTSYS;
spin_unlock(&wq->lock);
schedule();
spin_lock(&wq->lock);
return 0;
}
EXPORT_SYMBOL(do_wait_intr);
int do_wait_intr_irq(wait_queue_head_t *wq, wait_queue_entry_t *wait)
{
if (likely(list_empty(&wait->entry)))
__add_wait_queue_entry_tail(wq, wait);
set_current_state(TASK_INTERRUPTIBLE);
if (signal_pending(current))
return -ERESTARTSYS;
spin_unlock_irq(&wq->lock);
schedule();
spin_lock_irq(&wq->lock);
return 0;
}
EXPORT_SYMBOL(do_wait_intr_irq);
/**
* finish_wait - clean up after waiting in a queue
* @wq_head: waitqueue waited on
* @wq_entry: wait descriptor
*
* Sets current thread back to running state and removes
* the wait descriptor from the given waitqueue if still
* queued.
*/
void finish_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
{
unsigned long flags;
__set_current_state(TASK_RUNNING);
/*
* We can check for list emptiness outside the lock
* IFF:
* - we use the "careful" check that verifies both
* the next and prev pointers, so that there cannot
* be any half-pending updates in progress on other
* CPU's that we haven't seen yet (and that might
* still change the stack area.
* and
* - all other users take the lock (ie we can only
* have _one_ other CPU that looks at or modifies
* the list).
*/
if (!list_empty_careful(&wq_entry->entry)) {
spin_lock_irqsave(&wq_head->lock, flags);
list_del_init(&wq_entry->entry);
spin_unlock_irqrestore(&wq_head->lock, flags);
}
}
EXPORT_SYMBOL(finish_wait);
__sched int autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned int mode,
int sync, void *key)
{
int ret = default_wake_function(wq_entry, mode, sync, key);
if (ret)
list_del_init_careful(&wq_entry->entry);
return ret;
}
EXPORT_SYMBOL(autoremove_wake_function);
static inline bool is_kthread_should_stop(void)
{
return (current->flags & PF_KTHREAD) && kthread_should_stop();
}
/*
* DEFINE_WAIT_FUNC(wait, woken_wake_func);
*
* add_wait_queue(&wq_head, &wait);
* for (;;) {
* if (condition)
* break;
*
* // in wait_woken() // in woken_wake_function()
*
* p->state = mode; wq_entry->flags |= WQ_FLAG_WOKEN;
* smp_mb(); // A try_to_wake_up():
* if (!(wq_entry->flags & WQ_FLAG_WOKEN)) <full barrier>
* schedule() if (p->state & mode)
* p->state = TASK_RUNNING; p->state = TASK_RUNNING;
* wq_entry->flags &= ~WQ_FLAG_WOKEN; ~~~~~~~~~~~~~~~~~~
* smp_mb(); // B condition = true;
* } smp_mb(); // C
* remove_wait_queue(&wq_head, &wait); wq_entry->flags |= WQ_FLAG_WOKEN;
*/
__sched long wait_woken(struct wait_queue_entry *wq_entry, unsigned int mode, long timeout)
{
/*
* The below executes an smp_mb(), which matches with the full barrier
* executed by the try_to_wake_up() in woken_wake_function() such that
* either we see the store to wq_entry->flags in woken_wake_function()
* or woken_wake_function() sees our store to current->state.
*/
set_current_state(mode); /* A */
if (!(wq_entry->flags & WQ_FLAG_WOKEN) && !is_kthread_should_stop())
timeout = schedule_timeout(timeout);
__set_current_state(TASK_RUNNING);
/*
* The below executes an smp_mb(), which matches with the smp_mb() (C)
* in woken_wake_function() such that either we see the wait condition
* being true or the store to wq_entry->flags in woken_wake_function()
* follows ours in the coherence order.
*/
smp_store_mb(wq_entry->flags, wq_entry->flags & ~WQ_FLAG_WOKEN); /* B */
return timeout;
}
EXPORT_SYMBOL(wait_woken);
__sched int woken_wake_function(struct wait_queue_entry *wq_entry, unsigned int mode,
int sync, void *key)
{
/* Pairs with the smp_store_mb() in wait_woken(). */
smp_mb(); /* C */
wq_entry->flags |= WQ_FLAG_WOKEN;
return default_wake_function(wq_entry, mode, sync, key);
}
EXPORT_SYMBOL(woken_wake_function);