Merge tag 'locking-core-2023-06-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking updates from Ingo Molnar:

 - Introduce cmpxchg128() -- aka. the demise of cmpxchg_double()

   The cmpxchg128() family of functions is basically & functionally the
   same as cmpxchg_double(), but with a saner interface.

   Instead of a 6-parameter horror that forced u128 - u64/u64-halves
   layout details on the interface and exposed users to complexity,
   fragility & bugs, use a natural 3-parameter interface with u128
   types.

 - Restructure the generated atomic headers, and add kerneldoc comments
   for all of the generic atomic{,64,_long}_t operations.

   The generated definitions are much cleaner now, and come with
   documentation.

 - Implement lock_set_cmp_fn() on lockdep, for defining an ordering when
   taking multiple locks of the same type.

   This gets rid of one use of lockdep_set_novalidate_class() in the
   bcache code.

 - Fix raw_cpu_generic_try_cmpxchg() bug due to an unintended variable
   shadowing generating garbage code on Clang on certain ARM builds.

* tag 'locking-core-2023-06-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (43 commits)
  locking/atomic: scripts: fix ${atomic}_dec_if_positive() kerneldoc
  percpu: Fix self-assignment of __old in raw_cpu_generic_try_cmpxchg()
  locking/atomic: treewide: delete arch_atomic_*() kerneldoc
  locking/atomic: docs: Add atomic operations to the driver basic API documentation
  locking/atomic: scripts: generate kerneldoc comments
  docs: scripts: kernel-doc: accept bitwise negation like ~@var
  locking/atomic: scripts: simplify raw_atomic*() definitions
  locking/atomic: scripts: simplify raw_atomic_long*() definitions
  locking/atomic: scripts: split pfx/name/sfx/order
  locking/atomic: scripts: restructure fallback ifdeffery
  locking/atomic: scripts: build raw_atomic_long*() directly
  locking/atomic: treewide: use raw_atomic*_<op>()
  locking/atomic: scripts: add trivial raw_atomic*_<op>()
  locking/atomic: scripts: factor out order template generation
  locking/atomic: scripts: remove leftover "${mult}"
  locking/atomic: scripts: remove bogus order parameter
  locking/atomic: xtensa: add preprocessor symbols
  locking/atomic: x86: add preprocessor symbols
  locking/atomic: sparc: add preprocessor symbols
  locking/atomic: sh: add preprocessor symbols
  ...

1 files changed, 25 insertions, 18 deletions

diff --git a/arch/x86/lib/cmpxchg16b_emu.S b/arch/x86/lib/cmpxchg16b_emu.S
index 33c70c0160ea..6962df315793 100644
--- a/arch/x86/lib/cmpxchg16b_emu.S
+++ b/arch/x86/lib/cmpxchg16b_emu.S
@@ -1,47 +1,54 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 #include <linux/linkage.h>
 #include <asm/percpu.h>
+#include <asm/processor-flags.h>
 
 .text
 
 /*
+ * Emulate 'cmpxchg16b %gs:(%rsi)'
+ *
  * Inputs:
  * %rsi : memory location to compare
  * %rax : low 64 bits of old value
  * %rdx : high 64 bits of old value
  * %rbx : low 64 bits of new value
  * %rcx : high 64 bits of new value
- * %al  : Operation successful
+ *
+ * Notably this is not LOCK prefixed and is not safe against NMIs
  */
 SYM_FUNC_START(this_cpu_cmpxchg16b_emu)
 
-#
-# Emulate 'cmpxchg16b %gs:(%rsi)' except we return the result in %al not
-# via the ZF.  Caller will access %al to get result.
-#
-# Note that this is only useful for a cpuops operation.  Meaning that we
-# do *not* have a fully atomic operation but just an operation that is
-# *atomic* on a single cpu (as provided by the this_cpu_xx class of
-# macros).
-#
 	pushfq
 	cli
 
-	cmpq PER_CPU_VAR((%rsi)), %rax
-	jne .Lnot_same
-	cmpq PER_CPU_VAR(8(%rsi)), %rdx
-	jne .Lnot_same
+	/* if (*ptr == old) */
+	cmpq	PER_CPU_VAR(0(%rsi)), %rax
+	jne	.Lnot_same
+	cmpq	PER_CPU_VAR(8(%rsi)), %rdx
+	jne	.Lnot_same
 
-	movq %rbx, PER_CPU_VAR((%rsi))
-	movq %rcx, PER_CPU_VAR(8(%rsi))
+	/* *ptr = new */
+	movq	%rbx, PER_CPU_VAR(0(%rsi))
+	movq	%rcx, PER_CPU_VAR(8(%rsi))
+
+	/* set ZF in EFLAGS to indicate success */
+	orl	$X86_EFLAGS_ZF, (%rsp)
 
 	popfq
-	mov $1, %al
 	RET
 
 .Lnot_same:
+	/* *ptr != old */
+
+	/* old = *ptr */
+	movq	PER_CPU_VAR(0(%rsi)), %rax
+	movq	PER_CPU_VAR(8(%rsi)), %rdx
+
+	/* clear ZF in EFLAGS to indicate failure */
+	andl	$(~X86_EFLAGS_ZF), (%rsp)
+
 	popfq
-	xor %al,%al
 	RET
 
 SYM_FUNC_END(this_cpu_cmpxchg16b_emu)