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, 20 insertions, 16 deletions

diff --git a/scripts/atomic/gen-atomic-fallback.sh b/scripts/atomic/gen-atomic-fallback.sh
index a45154cefa48..f80d69cfeb1f 100755
--- a/scripts/atomic/gen-atomic-fallback.sh
+++ b/scripts/atomic/gen-atomic-fallback.sh
@@ -223,14 +223,15 @@ gen_xchg_fallbacks()
 
 gen_try_cmpxchg_fallback()
 {
+	local prefix="$1"; shift
 	local cmpxchg="$1"; shift;
-	local order="$1"; shift;
+	local suffix="$1"; shift;
 
 cat <<EOF
-#define raw_try_${cmpxchg}${order}(_ptr, _oldp, _new) \\
+#define raw_${prefix}try_${cmpxchg}${suffix}(_ptr, _oldp, _new) \\
 ({ \\
 	typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \\
-	___r = raw_${cmpxchg}${order}((_ptr), ___o, (_new)); \\
+	___r = raw_${prefix}${cmpxchg}${suffix}((_ptr), ___o, (_new)); \\
 	if (unlikely(___r != ___o)) \\
 		*___op = ___r; \\
 	likely(___r == ___o); \\
@@ -259,11 +260,11 @@ gen_try_cmpxchg_order_fallback()
 	fi
 
 	printf "#else\n"
-	gen_try_cmpxchg_fallback "${cmpxchg}" "${order}"
+	gen_try_cmpxchg_fallback "" "${cmpxchg}" "${order}"
 	printf "#endif\n\n"
 }
 
-gen_try_cmpxchg_fallbacks()
+gen_try_cmpxchg_order_fallbacks()
 {
 	local cmpxchg="$1"; shift;
 
@@ -272,15 +273,17 @@ gen_try_cmpxchg_fallbacks()
 	done
 }
 
-gen_cmpxchg_local_fallbacks()
+gen_def_and_try_cmpxchg_fallback()
 {
+	local prefix="$1"; shift
 	local cmpxchg="$1"; shift
+	local suffix="$1"; shift
 
-	printf "#define raw_${cmpxchg} arch_${cmpxchg}\n\n"
-	printf "#ifdef arch_try_${cmpxchg}\n"
-	printf "#define raw_try_${cmpxchg} arch_try_${cmpxchg}\n"
+	printf "#define raw_${prefix}${cmpxchg}${suffix} arch_${prefix}${cmpxchg}${suffix}\n\n"
+	printf "#ifdef arch_${prefix}try_${cmpxchg}${suffix}\n"
+	printf "#define raw_${prefix}try_${cmpxchg}${suffix} arch_${prefix}try_${cmpxchg}${suffix}\n"
 	printf "#else\n"
-	gen_try_cmpxchg_fallback "${cmpxchg}" ""
+	gen_try_cmpxchg_fallback "${prefix}" "${cmpxchg}" "${suffix}"
 	printf "#endif\n\n"
 }
 
@@ -302,15 +305,15 @@ for xchg in "xchg" "cmpxchg" "cmpxchg64" "cmpxchg128"; do
 done
 
 for cmpxchg in "cmpxchg" "cmpxchg64" "cmpxchg128"; do
-	gen_try_cmpxchg_fallbacks "${cmpxchg}"
+	gen_try_cmpxchg_order_fallbacks "${cmpxchg}"
 done
 
-for cmpxchg in "cmpxchg_local" "cmpxchg64_local" "cmpxchg128_local"; do
-	gen_cmpxchg_local_fallbacks "${cmpxchg}" ""
+for cmpxchg in "cmpxchg" "cmpxchg64" "cmpxchg128"; do
+	gen_def_and_try_cmpxchg_fallback "" "${cmpxchg}" "_local"
 done
 
-for cmpxchg in "sync_cmpxchg"; do
-	printf "#define raw_${cmpxchg} arch_${cmpxchg}\n\n"
+for cmpxchg in "cmpxchg"; do
+	gen_def_and_try_cmpxchg_fallback "sync_" "${cmpxchg}" ""
 done
 
 grep '^[a-z]' "$1" | while read name meta args; do
diff --git a/scripts/atomic/gen-atomic-instrumented.sh b/scripts/atomic/gen-atomic-instrumented.sh
index 8f8f8e3b20f9..592f3ec89b5f 100755
--- a/scripts/atomic/gen-atomic-instrumented.sh
+++ b/scripts/atomic/gen-atomic-instrumented.sh
@@ -169,7 +169,8 @@ for xchg in "xchg" "cmpxchg" "cmpxchg64" "cmpxchg128" "try_cmpxchg" "try_cmpxchg
 	done
 done
 
-for xchg in "cmpxchg_local" "cmpxchg64_local" "cmpxchg128_local" "sync_cmpxchg" "try_cmpxchg_local" "try_cmpxchg64_local" "try_cmpxchg128_local"; do
+for xchg in "cmpxchg_local" "cmpxchg64_local" "cmpxchg128_local" "sync_cmpxchg" \
+	    "try_cmpxchg_local" "try_cmpxchg64_local" "try_cmpxchg128_local" "sync_try_cmpxchg"; do
 	gen_xchg "${xchg}" ""
 	printf "\n"
 done