Merge tag 'locking-core-2023-10-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking updates from Info Molnar:
 "Futex improvements:

   - Add the 'futex2' syscall ABI, which is an attempt to get away from
     the multiplex syscall and adds a little room for extentions, while
     lifting some limitations.

   - Fix futex PI recursive rt_mutex waiter state bug

   - Fix inter-process shared futexes on no-MMU systems

   - Use folios instead of pages

  Micro-optimizations of locking primitives:

   - Improve arch_spin_value_unlocked() on asm-generic ticket spinlock
     architectures, to improve lockref code generation

   - Improve the x86-32 lockref_get_not_zero() main loop by adding
     build-time CMPXCHG8B support detection for the relevant lockref
     code, and by better interfacing the CMPXCHG8B assembly code with
     the compiler

   - Introduce arch_sync_try_cmpxchg() on x86 to improve
     sync_try_cmpxchg() code generation. Convert some sync_cmpxchg()
     users to sync_try_cmpxchg().

   - Micro-optimize rcuref_put_slowpath()

  Locking debuggability improvements:

   - Improve CONFIG_DEBUG_RT_MUTEXES=y to have a fast-path as well

   - Enforce atomicity of sched_submit_work(), which is de-facto atomic
     but was un-enforced previously.

   - Extend <linux/cleanup.h>'s no_free_ptr() with __must_check
     semantics

   - Fix ww_mutex self-tests

   - Clean up const-propagation in <linux/seqlock.h> and simplify the
     API-instantiation macros a bit

  RT locking improvements:

   - Provide the rt_mutex_*_schedule() primitives/helpers and use them
     in the rtmutex code to avoid recursion vs. rtlock on the PI state.

   - Add nested blocking lockdep asserts to rt_mutex_lock(),
     rtlock_lock() and rwbase_read_lock()

  .. plus misc fixes & cleanups"

* tag 'locking-core-2023-10-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (39 commits)
  futex: Don't include process MM in futex key on no-MMU
  locking/seqlock: Fix grammar in comment
  alpha: Fix up new futex syscall numbers
  locking/seqlock: Propagate 'const' pointers within read-only methods, remove forced type casts
  locking/lockdep: Fix string sizing bug that triggers a format-truncation compiler-warning
  locking/seqlock: Change __seqprop() to return the function pointer
  locking/seqlock: Simplify SEQCOUNT_LOCKNAME()
  locking/atomics: Use atomic_try_cmpxchg_release() to micro-optimize rcuref_put_slowpath()
  locking/atomic, xen: Use sync_try_cmpxchg() instead of sync_cmpxchg()
  locking/atomic/x86: Introduce arch_sync_try_cmpxchg()
  locking/atomic: Add generic support for sync_try_cmpxchg() and its fallback
  locking/seqlock: Fix typo in comment
  futex/requeue: Remove unnecessary ‘NULL’ initialization from futex_proxy_trylock_atomic()
  locking/local, arch: Rewrite local_add_unless() as a static inline function
  locking/debug: Fix debugfs API return value checks to use IS_ERR()
  locking/ww_mutex/test: Make sure we bail out instead of livelock
  locking/ww_mutex/test: Fix potential workqueue corruption
  locking/ww_mutex/test: Use prng instead of rng to avoid hangs at bootup
  futex: Add sys_futex_requeue()
  futex: Add flags2 argument to futex_requeue()
  ...

2 files changed, 16 insertions, 20 deletions

diff --git a/drivers/xen/events/events_fifo.c b/drivers/xen/events/events_fifo.c
index ad9fe51d3fb3..655775db7caf 100644
--- a/drivers/xen/events/events_fifo.c
+++ b/drivers/xen/events/events_fifo.c
@@ -226,21 +226,20 @@ static bool evtchn_fifo_is_masked(evtchn_port_t port)
  */
 static bool clear_masked_cond(volatile event_word_t *word)
 {
-	event_word_t new, old, w;
+	event_word_t new, old;
 
-	w = *word;
+	old = *word;
 
 	do {
-		if (!(w & (1 << EVTCHN_FIFO_MASKED)))
+		if (!(old & (1 << EVTCHN_FIFO_MASKED)))
 			return true;
 
-		if (w & (1 << EVTCHN_FIFO_PENDING))
+		if (old & (1 << EVTCHN_FIFO_PENDING))
 			return false;
 
-		old = w & ~(1 << EVTCHN_FIFO_BUSY);
+		old = old & ~(1 << EVTCHN_FIFO_BUSY);
 		new = old & ~(1 << EVTCHN_FIFO_MASKED);
-		w = sync_cmpxchg(word, old, new);
-	} while (w != old);
+	} while (!sync_try_cmpxchg(word, &old, new));
 
 	return true;
 }
@@ -259,17 +258,16 @@ static void evtchn_fifo_unmask(evtchn_port_t port)
 
 static uint32_t clear_linked(volatile event_word_t *word)
 {
-	event_word_t new, old, w;
+	event_word_t new, old;
 
-	w = *word;
+	old = *word;
 
 	do {
-		old = w;
-		new = (w & ~((1 << EVTCHN_FIFO_LINKED)
-			     | EVTCHN_FIFO_LINK_MASK));
-	} while ((w = sync_cmpxchg(word, old, new)) != old);
+		new = (old & ~((1 << EVTCHN_FIFO_LINKED)
+			       | EVTCHN_FIFO_LINK_MASK));
+	} while (!sync_try_cmpxchg(word, &old, new));
 
-	return w & EVTCHN_FIFO_LINK_MASK;
+	return old & EVTCHN_FIFO_LINK_MASK;
 }
 
 static void consume_one_event(unsigned cpu, struct evtchn_loop_ctrl *ctrl,
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index 35659bf70746..04a6b470b15d 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -427,16 +427,14 @@ EXPORT_SYMBOL_GPL(gnttab_grant_foreign_access);
 
 static int gnttab_end_foreign_access_ref_v1(grant_ref_t ref)
 {
-	u16 flags, nflags;
-	u16 *pflags;
+	u16 *pflags = &gnttab_shared.v1[ref].flags;
+	u16 flags;
 
-	pflags = &gnttab_shared.v1[ref].flags;
-	nflags = *pflags;
+	flags = *pflags;
 	do {
-		flags = nflags;
 		if (flags & (GTF_reading|GTF_writing))
 			return 0;
-	} while ((nflags = sync_cmpxchg(pflags, flags, 0)) != flags);
+	} while (!sync_try_cmpxchg(pflags, &flags, 0));
 
 	return 1;
 }