On 06/13/2018 11:50 AM, Peter Zijlstra wrote:

...

• lockdep_assert_held(&lock->wait_lock);
• if (owner && hold_ctx && __ww_ctx_stamp_after(hold_ctx, ww_ctx) &&

•    ww_ctx->acquired > 0) {
  

• WRITE_ONCE(hold_ctx->wounded, true);
  

• if (owner != current) {
  

• 	/*
  

• 	 * wake_up_process() inserts a write memory barrier to
  

It does no such thing. But yes, it does ensure the wakee sees all prior stores IFF the wakeup happened.

...

• 	 * make sure owner sees it is wounded before
  

• 	 * TASK_RUNNING in case it's sleeping on another
  

• 	 * ww_mutex. Note that owner points to a valid
  

• 	 * task_struct as long as we hold the wait_lock.
  

• 	 */
  

What exactly are you trying to say here ?

I'm thinking this is the pairing barrier to the smp_mb() below, with your list_empty() thing? Might make sense to write a single coherent comment and refer to the other location.

So what I'm trying to say here is that wake_up_process() ensures that the owner, if in !TASK_RUNNING, sees the write to hold_ctx->wounded before the transition to TASK_RUNNING. This was how I interpreted "woken up" in the wake up process documentation.

...

• 	wake_up_process(owner);
  

• }
  

• return true;
  

• }
• return false;

+}

• /*
  • Wake up any waiters that may have to back off when the lock is held by the
  • given context.
  • Due to the invariants on the wait list, this can only affect the first

• • waiter with a context.

• • waiter with a context, unless the Wound-Wait algorithm is used where
• • also subsequent waiters with a context main wound the lock holder.
  • The current task must not be on the wait list.
  */

@@ -303,6 +338,7 @@ static void __sched __ww_mutex_wakeup_for_backoff(struct mutex *lock, struct ww_acquire_ctx *ww_ctx) { struct mutex_waiter *cur;

• bool is_wait_die = ww_ctx->ww_class->is_wait_die;

lockdep_assert_held(&lock->wait_lock); @@ -310,13 +346,14 @@ __ww_mutex_wakeup_for_backoff(struct mutex *lock, struct ww_acquire_ctx *ww_ctx) if (!cur->ww_ctx) continue;

• if (cur->ww_ctx->acquired > 0 &&
  

• if (is_wait_die && cur->ww_ctx->acquired > 0 &&
  

  __ww_ctx_stamp_after(cur->ww_ctx, ww_ctx)) { debug_mutex_wake_waiter(lock, cur); wake_up_process(cur->task); }

• break;
  

• if (is_wait_die || __ww_mutex_wound(lock, cur->ww_ctx, ww_ctx))
  

• 	break;
  

  } }

@@ -338,12 +375,17 @@ ww_mutex_set_context_fastpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) * and keep spinning, or it will acquire wait_lock, add itself * to waiter list and sleep. */

• smp_mb(); /* ^^^ */

• smp_mb(); /* See comments above and below. */

/*

• * Check if lock is contended, if not there is nobody to wake up
  

• * Check if lock is contended, if not there is nobody to wake up.
  

• * Checking MUTEX_FLAG_WAITERS is not enough here,
  

That seems like a superfluous thing to say. It makes sense in the context of this patch because we change the FLAG check into a list check, but the resulting comment/code looks odd.

...

					   since we need to

• * order against the lock->ctx check in __ww_mutex_wound called from
  

• * __ww_mutex_add_waiter. We can use list_empty without taking the
  

• * wait_lock, given the memory barrier above and the list_empty
  

• * documentation.
  

I don't trust documentation. Please reason about implementation.

Will do.

...

*/

• if (likely(!(atomic_long_read(&lock->base.owner) & MUTEX_FLAG_WAITERS)))

• if (likely(list_empty(&lock->base.wait_list))) return;

/* @@ -653,6 +695,17 @@ __ww_mutex_lock_check_stamp(struct mutex *lock, struct mutex_waiter *waiter, struct ww_acquire_ctx *hold_ctx = READ_ONCE(ww->ctx); struct mutex_waiter *cur;

• /*

• * If we miss a wounded == true here, we will have a pending
  

Explain how we can miss that.

This is actually the pairing location of the wake_up_process() comment / code discussed above. Here we should have !TASK_RUNNING, and let's say ctx->wounded is set by another process immediately after we've read it (we "miss" it). At that point there must be a pending wake-up-process() for us and we'll pick up the set value of wounded on the next iteration after returning from schedule().

...

• * TASK_RUNNING and pick it up on the next schedule fall-through.
  

• */
  

• if (!ctx->ww_class->is_wait_die) {

• if (READ_ONCE(ctx->wounded))
  

• 	goto deadlock;
  

• else
  

• 	return 0;
  

• }
• if (hold_ctx && __ww_ctx_stamp_after(ctx, hold_ctx)) goto deadlock;

@@ -683,12 +736,15 @@ __ww_mutex_add_waiter(struct mutex_waiter *waiter, { struct mutex_waiter *cur; struct list_head *pos;

• bool is_wait_die;

if (!ww_ctx) { list_add_tail(&waiter->list, &lock->wait_list); return 0; }

• is_wait_die = ww_ctx->ww_class->is_wait_die;
• /*
  • Add the waiter before the first waiter with a higher stamp.
  • Waiters without a context are skipped to avoid starving

@@ -701,7 +757,7 @@ __ww_mutex_add_waiter(struct mutex_waiter *waiter, if (__ww_ctx_stamp_after(ww_ctx, cur->ww_ctx)) { /* Back off immediately if necessary. */

• 	if (ww_ctx->acquired > 0) {
  

• 	if (is_wait_die && ww_ctx->acquired > 0) {
  

  #ifdef CONFIG_DEBUG_MUTEXES struct ww_mutex *ww;

@@ -721,13 +777,26 @@ __ww_mutex_add_waiter(struct mutex_waiter *waiter, * Wake up the waiter so that it gets a chance to back * off. */

• if (cur->ww_ctx->acquired > 0) {
  

• if (is_wait_die && cur->ww_ctx->acquired > 0) {
  debug_mutex_wake_waiter(lock, cur);
  wake_up_process(cur->task);
  

  } }

list_add_tail(&waiter->list, pos);

• if (!is_wait_die) {

• struct ww_mutex *ww = container_of(lock, struct ww_mutex, base);
  

• /*
  

•  * Make sure a racing lock taker sees a non-empty waiting list
  

•  * before we read ww->ctx, so that if we miss ww->ctx, the
  

•  * racing lock taker will call __ww_mutex_wake_up_for_backoff()
  

•  * and wound itself.
  

•  */
  

• smp_mb();
  

• __ww_mutex_wound(lock, ww_ctx, ww->ctx);
  

• }
• return 0; }

@@ -750,6 +819,14 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, if (use_ww_ctx && ww_ctx) { if (unlikely(ww_ctx == READ_ONCE(ww->ctx))) return -EALREADY;

• /*
  

•  * Reset the wounded flag after a backoff.
  

•  * No other process can race and wound us here since they
  

•  * can't have a valid owner pointer at this time
  

•  */
  

• if (ww_ctx->acquired == 0)
  

• 	ww_ctx->wounded = false;
  

  }

preempt_disable(); @@ -858,6 +935,11 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, acquired: __set_current_state(TASK_RUNNING);

• /* We stole the lock. Need to check wounded status. */
• if (use_ww_ctx && ww_ctx && !ww_ctx->ww_class->is_wait_die &&

•    !__mutex_waiter_is_first(lock, &waiter))
  

• __ww_mutex_wakeup_for_backoff(lock, ww_ctx);
  

• mutex_remove_waiter(lock, &waiter, current); if (likely(list_empty(&lock->wait_list))) __mutex_clear_flag(lock, MUTEX_FLAGS);

I can't say I'm a fan. I'm already cursing the ww_mutex stuff every time I have to look at it, and you just made it worse spagethi.

Thanks for the review.

Well, I can't speak for the current ww implementation except I didn't think it was too hard to understand for a first time reader.

Admittedly the Wound-Wait path makes it worse since it's a preemptive algorithm and we need to touch other processes a acquire contexts and worry about ordering.

So, assuming your review comments are fixed up, is that a solid NAK or do you have any suggestion that would make you more comfortable with the code? like splitting out ww-stuff to a separate file?

/Thomas

On 06/13/2018 03:10 PM, Peter Zijlstra wrote:

On Wed, Jun 13, 2018 at 12:40:29PM +0200, Thomas Hellstrom wrote:

...

On 06/13/2018 11:50 AM, Peter Zijlstra wrote:

...

...

• lockdep_assert_held(&lock->wait_lock);
• if (owner && hold_ctx && __ww_ctx_stamp_after(hold_ctx, ww_ctx) &&

•    ww_ctx->acquired > 0) {
  

• WRITE_ONCE(hold_ctx->wounded, true);
  

• if (owner != current) {
  

• 	/*
  

• 	 * wake_up_process() inserts a write memory barrier to
  

It does no such thing. But yes, it does ensure the wakee sees all prior stores IFF the wakeup happened.

...

• 	 * make sure owner sees it is wounded before
  

• 	 * TASK_RUNNING in case it's sleeping on another
  

• 	 * ww_mutex. Note that owner points to a valid
  

• 	 * task_struct as long as we hold the wait_lock.
  

• 	 */
  

What exactly are you trying to say here ?

I'm thinking this is the pairing barrier to the smp_mb() below, with your list_empty() thing? Might make sense to write a single coherent comment and refer to the other location.

So what I'm trying to say here is that wake_up_process() ensures that the owner, if in !TASK_RUNNING, sees the write to hold_ctx->wounded before the transition to TASK_RUNNING. This was how I interpreted "woken up" in the wake up process documentation.

There is documentation!? :-) Aaah, you mean that kerneldoc comment with wake_up_process() ? Yeah, that needs fixing. /me puts on endless todo list.

Anyway, wakeup providing that ordering isn't something that needs a comment of that size; and I think the only comment here is that we care about the ordering and a reference to the site(s) that pairs with it.

Maybe something like:

/* * __ww_mutex_lock_check_stamp() will observe our wounded store. */

Yes.

Actually, I just found the set_current_state() kerneldoc which explains the built-in barrier pairing with wake_up_xxx. Perhaps I also should mention that as well. Looks like the use WRITE_ONCE() and READ_ONCE() can be dropped as well.

...

...

...

• if (likely(!(atomic_long_read(&lock->base.owner) & MUTEX_FLAG_WAITERS)))

• if (likely(list_empty(&lock->base.wait_list))) return; /*

@@ -653,6 +695,17 @@ __ww_mutex_lock_check_stamp(struct mutex *lock, struct mutex_waiter *waiter, struct ww_acquire_ctx *hold_ctx = READ_ONCE(ww->ctx); struct mutex_waiter *cur;

• /*

• * If we miss a wounded == true here, we will have a pending
  

Explain how we can miss that.

This is actually the pairing location of the wake_up_process() comment / code discussed above. Here we should have !TASK_RUNNING, and let's say ctx->wounded is set by another process immediately after we've read it (we "miss" it). At that point there must be a pending wake-up-process() for us and we'll pick up the set value of wounded on the next iteration after returning from schedule().

Right, so that's when the above wakeup isn't the one waking us.

...

...

I can't say I'm a fan. I'm already cursing the ww_mutex stuff every time I have to look at it, and you just made it worse spagethi.

Well, I can't speak for the current ww implementation except I didn't think it was too hard to understand for a first time reader.

Admittedly the Wound-Wait path makes it worse since it's a preemptive algorithm and we need to touch other processes a acquire contexts and worry about ordering.

So, assuming your review comments are fixed up, is that a solid NAK or do you have any suggestion that would make you more comfortable with the code? like splitting out ww-stuff to a separate file?

Nah, not a NAK, but we should look at whan can be done to improve code. Maybe add a few more comments that explain why. Part of the problem with ww_mutex is always that I forget exactly how they work and mutex.c doesn't have much useful comments in (most of those are in ww_mutex.h and I always forget to look there).

Understood.

Also; I'm not at all sure about the exact difference between what we have and what you propose. I did read the documentation part (I really should not have to) but it just doesn't jive.

I suspect you're using preemption entirely different from what we usually call a preemption.

I think that perhaps requires a good understanding of the difference of the algorithms in question before looking at the implementation. I put a short explanation and some URLs to CS websites describing the two algorithms and their pros and cons in the patch series introductory message. I'll forward that.

In short, with Wait-Die (before the patch) it's the process _taking_ the contended lock that backs off if necessary. No preemption required. With Wound-Wait, it's the process _holding_ the contended lock that gets wounded (preempted), and it needs to back off at its own discretion but no later than when it's going to sleep on another ww mutex. That point is where we intercept the preemption request. We're preempting the transaction rather than the process.

Also, __ww_ctx_stamp_after() is crap; did we want to write:

return (signed long)(a->stamp - b->stamp) > 0;

or something?

Hmm. Yes it indeed looks odd. Seems like the above code should do the trick.

/Thomas

On 06/14/2018 12:51 PM, Peter Zijlstra wrote:

On Wed, Jun 13, 2018 at 04:05:43PM +0200, Thomas Hellstrom wrote:

...

In short, with Wait-Die (before the patch) it's the process _taking_ the contended lock that backs off if necessary. No preemption required. With Wound-Wait, it's the process _holding_ the contended lock that gets wounded (preempted), and it needs to back off at its own discretion but no later than when it's going to sleep on another ww mutex. That point is where we intercept the preemption request. We're preempting the transaction rather than the process.

This:

Wait-die: The newer transactions are killed when: It (= the newer transaction) makes a reqeust for a lock being held by an older transactions

Wound-wait: The newer transactions are killed when: An older transaction makes a request for a lock being held by the newer transactions

Would make for an excellent comment somewhere. No talking about preemption, although I think I know what you mean with it, that is not how preemption is normally used.

Ok. I'll incorporate something along this line. Unfortunately that last statement is not fully true. It should read "The newer transactions are wounded when:", not "killed" when.

The literature makes a distinction between "killed" and "wounded". In our context, "Killed" is when a transaction actually receives an -EDEADLK and needs to back off. "Wounded" is when someone (typically another transaction) requests a transaction to kill itself. A wound will often, but not always, lead to a kill. If the wounded transaction has finished its locking sequence, or has the opportunity to grab uncontended ww mutexes or steal contended (non-handoff) ww mutexes to finish its transaction it will do so and never kill itself.

In scheduling speak preemption is when we pick a runnable (but !running) task to run instead of the current running task. In this case however, our T2 is blocked on a lock acquisition (one owned by our T1) and T1 is the only runnable task. Only when T1's progress is inhibited by T2 (T1 wants a lock held by T2) do we wound/wake T2.

Indeed. The preemption spoken about in the Wound-Wait litterature means that a transaction preempts another transaction when it wounds it. In distributed computing my understanding is that the preempted transaction is aborted instantly and restarted after a random delay. Of course, we have no means of mapping wounding to process preemption in the linux kernel, so that's why I referred to it as "lazy preemption". In process analogy "wounded" wound roughly correspond to (need_resched() == true), and returning -EDEADLK would correspond to voluntary preemption.

In any case, I had a little look at the current ww_mutex code and ended up with the below patch that hopefully clarifies things a little.

---

diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index f44f658ae629..a20c04619b2a 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -244,6 +244,10 @@ void __sched mutex_lock(struct mutex *lock) EXPORT_SYMBOL(mutex_lock); #endif +/*

• • Associate the ww_mutex @ww with the context @ww_ctx under which we acquired
• • it.
• */

IMO use of "acquire_context" or "context" is a little unfortunate when the literature uses "transaction", but otherwise fine.

static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww, struct ww_acquire_ctx *ww_ctx) { @@ -282,26 +286,36 @@ ww_mutex_lock_acquired(struct ww_mutex *ww, struct ww_acquire_ctx *ww_ctx) DEBUG_LOCKS_WARN_ON(ww_ctx->ww_class != ww->ww_class); #endif ww_ctx->acquired++;

• lock->ctx = ctx; }

+/*

• • Determine if context @a is 'after' context @b. IOW, @a should be wounded in
• • favour of @b.
• */

So "wounded" should never really be used with Wait-Die "Determine whether context @a represents a younger transaction than context @b"?

static inline bool __sched __ww_ctx_stamp_after(struct ww_acquire_ctx *a, struct ww_acquire_ctx *b) {

• return a->stamp - b->stamp <= LONG_MAX &&

•       (a->stamp != b->stamp || a > b);
  

• return (signed long)(a->stamp - b->stamp) > 0; }

/*

• • Wake up any waiters that may have to back off when the lock is held by the
• • given context.

• • We just acquired @lock under @ww_ctx, if there are later contexts waiting
• • behind us on the wait-list, wake them up so they can wound themselves.

Actually for Wait-Die, Back off or "Die" is the correct terminology.

• • Due to the invariants on the wait list, this can only affect the first
• • waiter with a context.

• • See __ww_mutex_add_waiter() for the list-order construction; basically the
• • list is ordered by stamp smallest (oldest) first, so if there is a later
• • (younger) stamp on the list behind us, wake it so it can wound itself.
• • Because __ww_mutex_add_waiter() and __ww_mutex_check_stamp() wake any
• • but the earliest context, this can only affect the first waiter (with a
• • context).

The wait list invariants are stated in Documentation/locking/ww-mutex-design.txt. Perhaps we could copy those into the code to make the comment more understandable: "  We maintain the following invariants for the wait list:   (1) Waiters with an acquire context are sorted by stamp order; waiters       without an acquire context are interspersed in FIFO order.   (2) For Wait-Die, among waiters with contexts, only the first one can have       other locks acquired already (ctx->acquired > 0). Note that this waiter       may come after other waiters without contexts in the list."

• The current task must not be on the wait list.

*/ static void __sched -__ww_mutex_wakeup_for_backoff(struct mutex *lock, struct ww_acquire_ctx *ww_ctx) +__ww_mutex_wakeup_for_wound(struct mutex *lock, struct ww_acquire_ctx *ww_ctx)

Again, "wound" is unsuitable for Wait-Die. + numerous additional places.

Thanks, Thomas

On 06/14/2018 04:42 PM, Peter Zijlstra wrote:

On Thu, Jun 14, 2018 at 01:48:39PM +0200, Thomas Hellstrom wrote:

...

The literature makes a distinction between "killed" and "wounded". In our context, "Killed" is when a transaction actually receives an -EDEADLK and needs to back off. "Wounded" is when someone (typically another transaction) requests a transaction to kill itself. A wound will often, but not always, lead to a kill. If the wounded transaction has finished its locking sequence, or has the opportunity to grab uncontended ww mutexes or steal contended (non-handoff) ww mutexes to finish its transaction it will do so and never kill itself.

Hopefully I got it all right this time; I folded your patch in and mucked around with it a bit, but haven't done anything except compile it.

I left the context/transaction thing because well, that's what we called the thing.

Overall, I think this looks fine. I'll just fix up the FLAG_WAITERS setting and affected comments and do some torture testing on it.

Are you OK with adding the new feature and the cleanup in the same patch?

Thomas

diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h index 39fda195bf78..50ef5a10cfa0 100644 --- a/include/linux/ww_mutex.h +++ b/include/linux/ww_mutex.h @@ -8,6 +8,8 @@

• Wound/wait implementation:
• Copyright (C) 2013 Canonical Ltd.

• • Choice of algorithm:
• • Copyright (C) 2018 WMWare Inc.
  • This file contains the main data structure and API definitions.
  */

@@ -23,14 +25,17 @@ struct ww_class { struct lock_class_key mutex_key; const char *acquire_name; const char *mutex_name;

• unsigned int is_wait_die; };

struct ww_acquire_ctx { struct task_struct *task; unsigned long stamp;

• unsigned acquired;

• unsigned int acquired;
• unsigned short wounded;
• unsigned short is_wait_die; #ifdef CONFIG_DEBUG_MUTEXES

• unsigned done_acquire;

• unsigned int done_acquire; struct ww_class *ww_class; struct ww_mutex *contending_lock; #endif

@@ -38,8 +43,8 @@ struct ww_acquire_ctx { struct lockdep_map dep_map; #endif #ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH

• unsigned deadlock_inject_interval;
• unsigned deadlock_inject_countdown;

• unsigned int deadlock_inject_interval;
• unsigned int deadlock_inject_countdown; #endif };

@@ -58,17 +63,21 @@ struct ww_mutex { # define __WW_CLASS_MUTEX_INITIALIZER(lockname, class) #endif -#define __WW_CLASS_INITIALIZER(ww_class) \ +#define __WW_CLASS_INITIALIZER(ww_class, _is_wait_die) \ { .stamp = ATOMIC_LONG_INIT(0) \ , .acquire_name = #ww_class "_acquire" \

• , .mutex_name = #ww_class "_mutex" }
  

• , .mutex_name = #ww_class "_mutex" \
  

• , .is_wait_die = _is_wait_die }
  

#define __WW_MUTEX_INITIALIZER(lockname, class) \ { .base = __MUTEX_INITIALIZER(lockname.base) \ __WW_CLASS_MUTEX_INITIALIZER(lockname, class) } +#define DEFINE_WD_CLASS(classname) \

• struct ww_class classname = __WW_CLASS_INITIALIZER(classname, 1)
• #define DEFINE_WW_CLASS(classname) \

• struct ww_class classname = __WW_CLASS_INITIALIZER(classname)

• struct ww_class classname = __WW_CLASS_INITIALIZER(classname, 0)

#define DEFINE_WW_MUTEX(mutexname, ww_class) \ struct ww_mutex mutexname = __WW_MUTEX_INITIALIZER(mutexname, ww_class) @@ -123,6 +132,8 @@ static inline void ww_acquire_init(struct ww_acquire_ctx *ctx, ctx->task = current; ctx->stamp = atomic_long_inc_return_relaxed(&ww_class->stamp); ctx->acquired = 0;

• ctx->wounded = false;
• ctx->is_wait_die = ww_class->is_wait_die; #ifdef CONFIG_DEBUG_MUTEXES ctx->ww_class = ww_class; ctx->done_acquire = 0;

diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index f44f658ae629..9e244af4647d 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -244,6 +244,22 @@ void __sched mutex_lock(struct mutex *lock) EXPORT_SYMBOL(mutex_lock); #endif +/*

• • Wait-Die:
• • The newer transactions are killed when:

• • It (the new transaction) makes a request for a lock being held
    

• • by an older transaction.
    

• • Wound-Wait:
• • The newer transactions are wounded when:

• • An older transaction makes a request for a lock being held by
    

• • the newer transaction.
    

• */

+/*

• • Associate the ww_mutex @ww with the context @ww_ctx under which we acquired
• • it.
• */ static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww, struct ww_acquire_ctx *ww_ctx) {

@@ -282,26 +298,96 @@ ww_mutex_lock_acquired(struct ww_mutex *ww, struct ww_acquire_ctx *ww_ctx) DEBUG_LOCKS_WARN_ON(ww_ctx->ww_class != ww->ww_class); #endif ww_ctx->acquired++;

• ww->ctx = ww_ctx; }

+/*

• • Determine if context @a is 'after' context @b. IOW, @a should be wounded in
• • favour of @b.
• */ static inline bool __sched __ww_ctx_stamp_after(struct ww_acquire_ctx *a, struct ww_acquire_ctx *b) {

• return a->stamp - b->stamp <= LONG_MAX &&

•       (a->stamp != b->stamp || a > b);
  

• return (signed long)(a->stamp - b->stamp) > 0; }

/*

• • Wake up any waiters that may have to back off when the lock is held by the
• • given context.

• • Wait-Die; wake a younger waiter context (when locks held) such that it can die.

• • Due to the invariants on the wait list, this can only affect the first
• • waiter with a context.

• • Among waiters with context, only the first one can have other locks acquired
• • already (ctx->acquired > 0), because __ww_mutex_add_waiter() and
• • __ww_mutex_check_wound() wake any but the earliest context.
• */

+static bool __ww_mutex_die(struct mutex *lock, struct mutex_waiter *waiter,

•            struct ww_acquire_ctx *ww_ctx)
  

+{

• if (!ww_ctx->is_wait_die)

• return false;
  

• if (waiter->ww_ctx->acquired > 0 &&

• 	__ww_ctx_stamp_after(waiter->ww_ctx, ww_ctx)) {
  

• debug_mutex_wake_waiter(lock, waiter);
  

• wake_up_process(waiter->task);
  

• }
• return true;

+}

+/*

• • Wound-Wait; wound a younger @hold_ctx (if it has locks held).
• • XXX more; explain why we too only need to wake the first.
• */

+static bool __ww_mutex_wound(struct mutex *lock,

• 	     struct ww_acquire_ctx *ww_ctx,
  

• 	     struct ww_acquire_ctx *hold_ctx)
  

+{

• struct task_struct *owner = __mutex_owner(lock);
• lockdep_assert_held(&lock->wait_lock);
• /*

• * Possible through __ww_mutex_add_waiter() when we race with
  

• * ww_mutex_set_context_fastpath(). In that case we'll get here again
  

• * through __ww_mutex_check_waiters().
  

• */
  

• if (!hold_ctx)

• return false;
  

• /*

• * Can have !owner because of __mutex_unlock_slowpath(), but if owner,
  

• * it cannot go away because we'll have FLAG_WAITERS set and hold
  

• * wait_lock.
  

• */
  

• if (!owner)

• return false;
  

• if (ww_ctx->acquired > 0 && __ww_ctx_stamp_after(hold_ctx, ww_ctx)) {

• hold_ctx->wounded = 1;
  

• if (owner != current)
  

• 	wake_up_process(owner);
  

• return true;
  

• }
• return false;

+}

+/*

• • We just acquired @lock under @ww_ctx, if there are later contexts waiting
• • behind us on the wait-list, check if they need wounding/killing.
• • See __ww_mutex_add_waiter() for the list-order construction; basically the
• • list is ordered by stamp, smallest (oldest) first.
• • This relies on never mixing wait-die/wound-wait on the same wait-list; which is
• • currently ensured by that being a ww_class property.
  • The current task must not be on the wait list.
  */ static void __sched

-__ww_mutex_wakeup_for_backoff(struct mutex *lock, struct ww_acquire_ctx *ww_ctx) +__ww_mutex_check_waiters(struct mutex *lock, struct ww_acquire_ctx *ww_ctx) { struct mutex_waiter *cur; @@ -311,66 +397,50 @@ __ww_mutex_wakeup_for_backoff(struct mutex *lock, struct ww_acquire_ctx *ww_ctx) if (!cur->ww_ctx) continue;

• if (cur->ww_ctx->acquired > 0 &&
  

•     __ww_ctx_stamp_after(cur->ww_ctx, ww_ctx)) {
  

• 	debug_mutex_wake_waiter(lock, cur);
  

• 	wake_up_process(cur->task);
  

• }
  

• break;
  

• if (__ww_mutex_die(lock, cur, ww_ctx) ||
  

•     __ww_mutex_wound(lock, cur->ww_ctx, ww_ctx))
  

• 	break;
  

  } }

/*

• • After acquiring lock with fastpath or when we lost out in contested
• • slowpath, set ctx and wake up any waiters so they can recheck.

• • After acquiring lock with fastpath, where we do not hold wait_lock, set ctx
• • and wake up any waiters so they can recheck.
  */ static __always_inline void ww_mutex_set_context_fastpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) { 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
  

• * the list_empty check 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(); /* ^^^ */

• smp_mb(); /* See comments above and below. */

/*

• * Check if lock is contended, if not there is nobody to wake up
  

• * [W] ww->ctx = ctx	[W] list_add_tail()
  

• *     MB		    MB
  

• * [R] list_empty()	[R] ww->ctx
  

• *
  

• * The memory barrier above pairs with the memory barrier in
  

• * __ww_mutex_add_waiter() and makes sure we either observe ww->ctx
  

• * and/or !empty list.
  

  */

• if (likely(!(atomic_long_read(&lock->base.owner) & MUTEX_FLAG_WAITERS)))

• if (likely(list_empty(&lock->base.wait_list))) return;

/*

• * Uh oh, we raced in fastpath, wake up everyone in this case,
  

• * so they can see the new lock->ctx.
  

• * Uh oh, we raced in fastpath, check if any of the waiters need wounding.
  

  */ spin_lock(&lock->base.wait_lock);

• __ww_mutex_wakeup_for_backoff(&lock->base, ctx);

• __ww_mutex_check_waiters(&lock->base, ctx); spin_unlock(&lock->base.wait_lock); }

-/*

• • After acquiring lock in the slowpath set ctx.
• • Unlike for the fast path, the caller ensures that waiters are woken up where
• • necessary.
• • 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) -{

• ww_mutex_lock_acquired(lock, ctx);
• lock->ctx = ctx;

-}

• #ifdef CONFIG_MUTEX_SPIN_ON_OWNER

static inline @@ -646,37 +716,83 @@ void __sched ww_mutex_unlock(struct ww_mutex *lock) } EXPORT_SYMBOL(ww_mutex_unlock);

+static __always_inline int __sched +__ww_mutex_kill(struct mutex *lock, struct ww_acquire_ctx *ww_ctx) +{

• if (ww_ctx->acquired > 0) {

+#ifdef CONFIG_DEBUG_MUTEXES

• struct ww_mutex *ww;
  

• ww = container_of(lock, struct ww_mutex, base);
  

• DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock);
  

• ww_ctx->contending_lock = ww;
  

+#endif

• return -EDEADLK;
  

• }
• return 0;

+}

+/*

• • Check the wound condition for the current lock acquire.
• • Wound-Wait: If we're wounded, kill ourself.
• • Wait-Die: If we're trying to acquire a lock already held by an older

• •       context, kill ourselves.
    

• • Since __ww_mutex_add_waiter() orders the wait-list on stamp, we only have to
• • look at waiters before us in the wait-list.
• */ static inline int __sched

-__ww_mutex_lock_check_stamp(struct mutex *lock, struct mutex_waiter *waiter, +__ww_mutex_check_wound(struct mutex *lock, struct mutex_waiter *waiter, 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); struct mutex_waiter *cur;

• if (ctx->acquired == 0)

• return 0;
  

• if (!ctx->is_wait_die) {

• if (ctx->wounded)
  

• 	return __ww_mutex_kill(lock, ctx);
  

• return 0;
  

• }
• if (hold_ctx && __ww_ctx_stamp_after(ctx, hold_ctx))

• goto deadlock;
  

• return __ww_mutex_kill(lock, ctx);
  

/* * If there is a waiter in front of us that has a context, then its

• * stamp is earlier than ours and we must back off.
  

• * stamp is earlier than ours and we must wound ourself.
  

  */ cur = waiter; list_for_each_entry_continue_reverse(cur, &lock->wait_list, list) {

• if (cur->ww_ctx)
  

• 	goto deadlock;
  

• if (!cur->ww_ctx)
  

• 	continue;
  

• return __ww_mutex_kill(lock, ctx);
  

  }

return 0;

-deadlock: -#ifdef CONFIG_DEBUG_MUTEXES

• DEBUG_LOCKS_WARN_ON(ctx->contending_lock);
• ctx->contending_lock = ww;

-#endif

• return -EDEADLK; }

+/*

• • Add @waiter to the wait-list, keep the wait-list ordered by stamp, smallest
• • first. Such that older contexts are preferred to acquire the lock over
• • younger contexts.
• • Waiters without context are interspersed in FIFO order.
• • Furthermore, for Wait-Die kill ourself immediately when possible (there are
• • older contexts already waiting) to avoid unnecessary waiting and for
• • Wound-Wait ensure we wound the owning context when it is younger.
• */ static inline int __sched __ww_mutex_add_waiter(struct mutex_waiter *waiter, struct mutex *lock,

@@ -684,16 +800,21 @@ __ww_mutex_add_waiter(struct mutex_waiter *waiter, { struct mutex_waiter *cur; struct list_head *pos;

• bool is_wait_die;

if (!ww_ctx) { list_add_tail(&waiter->list, &lock->wait_list); return 0; }

• is_wait_die = ww_ctx->is_wait_die;
• /*
  • Add the waiter before the first waiter with a higher stamp.
  • Waiters without a context are skipped to avoid starving

• * them.
  

• * them. Wait-Die waiters may back off here. Wound-Wait waiters
  

• * never back off here, but they are sorted in stamp order and
  

• * may wound the lock holder.
  

  */ pos = &lock->wait_list; list_for_each_entry_reverse(cur, &lock->wait_list, list) {

@@ -701,16 +822,16 @@ __ww_mutex_add_waiter(struct mutex_waiter *waiter, continue; if (__ww_ctx_stamp_after(ww_ctx, cur->ww_ctx)) {

• 	/* Back off immediately if necessary. */
  

• 	if (ww_ctx->acquired > 0) {
  

-#ifdef CONFIG_DEBUG_MUTEXES

• 		struct ww_mutex *ww;
  

• 		ww = container_of(lock, struct ww_mutex, base);
  

• 		DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock);
  

• 		ww_ctx->contending_lock = ww;
  

-#endif

• 		return -EDEADLK;
  

• 	/*
  

• 	 * Wait-Die: if we find an older context waiting, there
  

• 	 * is no point in queueing behind it, as we'd have to
  

• 	 * wound ourselves the moment it would acquire the
  

• 	 * lock.
  

• 	 */
  

• 	if (is_wait_die) {
  

• 		int ret = __ww_mutex_kill(lock, ww_ctx);
  

• 		if (ret)
  

• 			return ret;
  }
  

break; @@ -718,17 +839,29 @@ __ww_mutex_add_waiter(struct mutex_waiter *waiter, pos = &cur->list;

• /* Wait-Die: ensure younger waiters die. */
  

• __ww_mutex_die(lock, cur, ww_ctx);
  

• }
• list_add_tail(&waiter->list, pos);
• /*

• * Wound-Wait: if we're blocking on a mutex owned by a younger context,
  

• * wound that such that we might proceed.
  

• */
  

• if (!is_wait_die) {

• struct ww_mutex *ww = container_of(lock, struct ww_mutex, base);
  

• /*

•  * Wake up the waiter so that it gets a chance to back
  

•  * off.
  

•  * See ww_mutex_set_context_fastpath(). Orders the
  

•  * list_add_tail() vs the ww->ctx load, such that either we
  

•  * or the fastpath will wound @ww->ctx.
  

  */

• if (cur->ww_ctx->acquired > 0) {
  

• 	debug_mutex_wake_waiter(lock, cur);
  

• 	wake_up_process(cur->task);
  

• }
  

• smp_mb();
  

• __ww_mutex_wound(lock, ww_ctx, ww->ctx);
  

  }

• list_add_tail(&waiter->list, pos); return 0; }

@@ -751,6 +884,14 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, if (use_ww_ctx && ww_ctx) { if (unlikely(ww_ctx == READ_ONCE(ww->ctx))) return -EALREADY;

• /*
  

•  * Reset the wounded flag after a kill.  No other process can
  

•  * race and wound us here since they can't have a valid owner
  

•  * pointer at this time.
  

•  */
  

• if (ww_ctx->acquired == 0)
  

• 	ww_ctx->wounded = 0;
  

  }

preempt_disable(); @@ -772,7 +913,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, */ if (__mutex_trylock(lock)) { if (use_ww_ctx && ww_ctx)

• 	__ww_mutex_wakeup_for_backoff(lock, ww_ctx);
  

• 	__ww_mutex_check_waiters(lock, ww_ctx);
  

goto skip_wait; } @@ -790,10 +931,10 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, waiter.ww_ctx = MUTEX_POISON_WW_CTX; #endif } else {

• /* Add in stamp order, waking up waiters that must back off. */
  

• /* Add in stamp order, waking up waiters that must wound themselves. */
  

  ret = __ww_mutex_add_waiter(&waiter, lock, ww_ctx); if (ret)

• 	goto err_early_backoff;
  

• 	goto err_early_kill;
  

waiter.ww_ctx = ww_ctx; } @@ -824,8 +965,8 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, goto err; }

• if (use_ww_ctx && ww_ctx && ww_ctx->acquired > 0) {
  

• 	ret = __ww_mutex_lock_check_stamp(lock, &waiter, ww_ctx);
  

• if (use_ww_ctx && ww_ctx) {
  

• 	ret = __ww_mutex_check_wound(lock, &waiter, ww_ctx);
  if (ret)
  	goto err;
  

  }

@@ -859,6 +1000,16 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, acquired: __set_current_state(TASK_RUNNING);

• if (use_ww_ctx && ww_ctx) {

• /*
  

•  * Wound-Wait; we stole the lock (!first_waiter), check the
  

•  * waiters. This, together with XXX, ensures __ww_mutex_wound()
  

•  * only needs to check the first waiter (with context).
  

•  */
  

• if (!ww_ctx->is_wait_die && !__mutex_waiter_is_first(lock, &waiter))
  

• 	__ww_mutex_check_waiters(lock, ww_ctx);
  

• }
• mutex_remove_waiter(lock, &waiter, current); if (likely(list_empty(&lock->wait_list))) __mutex_clear_flag(lock, MUTEX_FLAGS);

@@ -870,7 +1021,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, lock_acquired(&lock->dep_map, ip); if (use_ww_ctx && ww_ctx)

• ww_mutex_set_context_slowpath(ww, ww_ctx);
  

• ww_mutex_lock_acquired(ww, ww_ctx);
  

spin_unlock(&lock->wait_lock); preempt_enable(); @@ -879,7 +1030,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, err: __set_current_state(TASK_RUNNING); mutex_remove_waiter(lock, &waiter, current); -err_early_backoff: +err_early_kill: spin_unlock(&lock->wait_lock); debug_mutex_free_waiter(&waiter); mutex_release(&lock->dep_map, 1, ip);