sparc32,parisc,csky: Provide one-byte and two-byte cmpxchg() support

This series provides native one-byte and two-byte cmpxchg() support
 for sparc32 and parisc, courtesy of Al Viro.  This support is provided
 by the same hashed-array-of-locks technique used for the other atomic
 operations provided for these two platforms.
 
 This series also provides emulated one-byte cmpxchg() support for csky
 using a new cmpxchg_emu_u8() function that uses a four-byte cmpxchg()
 to emulate the one-byte variant.
 
 Similar patches for emulation of one-byte cmpxchg() for arc, sh, and
 xtensa have not yet received maintainer acks, so they are slated for
 the v6.11 merge window.
 -----BEGIN PGP SIGNATURE-----
 
 iQJHBAABCgAxFiEEbK7UrM+RBIrCoViJnr8S83LZ+4wFAmY/gZ8THHBhdWxtY2tA
 a2VybmVsLm9yZwAKCRCevxLzctn7jFIjD/0Uu4VZZN96jYbSaDbC5aAkEHg/swBK
 6OVn+yspLOvkebVZlSfus+7rc5VUrxT3GA/gvAWEQsUlPqpYg6Qja/efFpPPRjIq
 lwkFE5HFgE0J4lBo9p78ggm6Hx60WUPlNg9uS23qURZbFTx5TYQyAdzXw9HlYzr8
 jg5IuTtO5L5AZzR2ocDRh4A5sqfcBJCVdVsKO+XzdFLLtgum+kJY7StYLPdY8VtL
 pIV3+ZQENoiwzE+wccnCb2R/4kt6jsEDShlpV4VEfv76HwbjBdvSq4jEg4jS2N3/
 AIyThclD97AEdbbM1oJ3oZdjD3GLGVPhVFfiMSGD5HGA+JVJPjJe2it4o+xY7CIR
 sSdI/E3Rs67qgaga6t2vHygDZABOwgNLAsc4VwM7X6I20fRixkYVc7aVOTnAPzmr
 15iaFd/T7fLKJcC3m/IXb9iNdlfe0Op4+YVD0lOTWmzIk80Xgf45a39u1VFlqQvh
 CLIZG3IdmuxXSWjOmk70iokzJgoSmBriGLbAT3K++pzGYUN/BNQs6XRR77BczFsX
 CbZTZKnEWZMR1U0UWa/TbvUKcsVBZTYebJSvJOG2/+oVqayzvwYfBsE/vWZcI72K
 XEEpKY9ZPDf/gCs/G4OFWt2QPJ0PL+Nt4UZDr5Khrqgo1PwN0uIXstA4mnJ0WjqQ
 sGiACjdTXk4h0w==
 =AEPy
 -----END PGP SIGNATURE-----

Merge tag 'cmpxchg.2024.05.11a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu

Pull cmpxchg updates from Paul McKenney:
 "Provide one-byte and two-byte cmpxchg() support on sparc32, parisc,
  and csky

  This provides native one-byte and two-byte cmpxchg() support for
  sparc32 and parisc, courtesy of Al Viro. This support is provided by
  the same hashed-array-of-locks technique used for the other atomic
  operations provided for these two platforms.

  There is also emulated one-byte cmpxchg() support for csky using a new
  cmpxchg_emu_u8() function that uses a four-byte cmpxchg() to emulate
  the one-byte variant.

  Similar patches for emulation of one-byte cmpxchg() for arc, sh, and
  xtensa have not yet received maintainer acks, so they are slated for
  the v6.11 merge window"

* tag 'cmpxchg.2024.05.11a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu:
  csky: Emulate one-byte cmpxchg
  lib: Add one-byte emulation function
  parisc: add u16 support to cmpxchg()
  parisc: add missing export of __cmpxchg_u8()
  parisc: unify implementations of __cmpxchg_u{8,32,64}
  parisc: __cmpxchg_u32(): lift conversion into the callers
  sparc32: add __cmpxchg_u{8,16}() and teach __cmpxchg() to handle those sizes
  sparc32: unify __cmpxchg_u{32,64}
  sparc32: make the first argument of __cmpxchg_u64() volatile u64 *
  sparc32: make __cmpxchg_u32() return u32

arch/Kconfig

@@ -1617,4 +1617,7 @@ config CC_HAS_SANE_FUNCTION_ALIGNMENT
 	# strict alignment always, even with -falign-functions.
 	def_bool CC_HAS_MIN_FUNCTION_ALIGNMENT || CC_IS_CLANG
 
+config ARCH_NEED_CMPXCHG_1_EMU
+	bool
+
 endmenu

arch/csky/Kconfig

@@ -37,6 +37,7 @@ config CSKY
 	select ARCH_INLINE_SPIN_UNLOCK_BH if !PREEMPTION
 	select ARCH_INLINE_SPIN_UNLOCK_IRQ if !PREEMPTION
 	select ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE if !PREEMPTION
+	select ARCH_NEED_CMPXCHG_1_EMU
 	select ARCH_WANT_FRAME_POINTERS if !CPU_CK610 && $(cc-option,-mbacktrace)
 	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
 	select COMMON_CLK

arch/csky/include/asm/cmpxchg.h

@@ -6,6 +6,7 @@
 #ifdef CONFIG_SMP
 #include <linux/bug.h>
 #include <asm/barrier.h>
+#include <linux/cmpxchg-emu.h>
 
 #define __xchg_relaxed(new, ptr, size)				\
 ({								\
@@ -61,6 +62,9 @@
 	__typeof__(old) __old = (old);				\
 	__typeof__(*(ptr)) __ret;				\
 	switch (size) {						\
+	case 1:							\
+		__ret = (__typeof__(*(ptr)))cmpxchg_emu_u8((volatile u8 *)__ptr, (uintptr_t)__old, (uintptr_t)__new); \
+		break;						\
 	case 4:							\
 		asm volatile (					\
 		"1:	ldex.w		%0, (%3) \n"		\
@@ -91,6 +95,9 @@
 	__typeof__(old) __old = (old);				\
 	__typeof__(*(ptr)) __ret;				\
 	switch (size) {						\
+	case 1:							\
+		__ret = (__typeof__(*(ptr)))cmpxchg_emu_u8((volatile u8 *)__ptr, (uintptr_t)__old, (uintptr_t)__new); \
+		break;						\
 	case 4:							\
 		asm volatile (					\
 		"1:	ldex.w		%0, (%3) \n"		\
@@ -122,6 +129,9 @@
 	__typeof__(old) __old = (old);				\
 	__typeof__(*(ptr)) __ret;				\
 	switch (size) {						\
+	case 1:							\
+		__ret = (__typeof__(*(ptr)))cmpxchg_emu_u8((volatile u8 *)__ptr, (uintptr_t)__old, (uintptr_t)__new); \
+		break;						\
 	case 4:							\
 		asm volatile (					\
 		RELEASE_FENCE					\

arch/parisc/include/asm/cmpxchg.h

@@ -56,26 +56,24 @@ __arch_xchg(unsigned long x, volatile void *ptr, int size)
 /* bug catcher for when unsupported size is used - won't link */
 extern void __cmpxchg_called_with_bad_pointer(void);
 
-/* __cmpxchg_u32/u64 defined in arch/parisc/lib/bitops.c */
-extern unsigned long __cmpxchg_u32(volatile unsigned int *m, unsigned int old,
-				   unsigned int new_);
-extern u64 __cmpxchg_u64(volatile u64 *ptr, u64 old, u64 new_);
+/* __cmpxchg_u... defined in arch/parisc/lib/bitops.c */
 extern u8 __cmpxchg_u8(volatile u8 *ptr, u8 old, u8 new_);
+extern u16 __cmpxchg_u16(volatile u16 *ptr, u16 old, u16 new_);
+extern u32 __cmpxchg_u32(volatile u32 *m, u32 old, u32 new_);
+extern u64 __cmpxchg_u64(volatile u64 *ptr, u64 old, u64 new_);
 
 /* don't worry...optimizer will get rid of most of this */
 static inline unsigned long
 __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new_, int size)
 {
-	switch (size) {
+	return
 #ifdef CONFIG_64BIT
-	case 8: return __cmpxchg_u64((u64 *)ptr, old, new_);
+		size == 8 ? __cmpxchg_u64(ptr, old, new_) :
 #endif
-	case 4: return __cmpxchg_u32((unsigned int *)ptr,
-				     (unsigned int)old, (unsigned int)new_);
-	case 1: return __cmpxchg_u8((u8 *)ptr, old & 0xff, new_ & 0xff);
-	}
-	__cmpxchg_called_with_bad_pointer();
-	return old;
+		size == 4 ? __cmpxchg_u32(ptr, old, new_) :
+		size == 2 ? __cmpxchg_u16(ptr, old, new_) :
+		size == 1 ? __cmpxchg_u8(ptr, old, new_) :
+			(__cmpxchg_called_with_bad_pointer(), old);
 }
 
 #define arch_cmpxchg(ptr, o, n)						 \

arch/parisc/kernel/parisc_ksyms.c

@@ -22,6 +22,8 @@ EXPORT_SYMBOL(memset);
 #include <linux/atomic.h>
 EXPORT_SYMBOL(__xchg8);
 EXPORT_SYMBOL(__xchg32);
+EXPORT_SYMBOL(__cmpxchg_u8);
+EXPORT_SYMBOL(__cmpxchg_u16);
 EXPORT_SYMBOL(__cmpxchg_u32);
 EXPORT_SYMBOL(__cmpxchg_u64);
 #ifdef CONFIG_SMP

arch/parisc/lib/bitops.c

@@ -56,38 +56,20 @@ unsigned long notrace __xchg8(char x, volatile char *ptr)
 }
 
 
-u64 notrace __cmpxchg_u64(volatile u64 *ptr, u64 old, u64 new)
-{
-	unsigned long flags;
-	u64 prev;
+#define CMPXCHG(T)						\
+	T notrace __cmpxchg_##T(volatile T *ptr, T old, T new)	\
+	{							\
+		unsigned long flags;				\
+		T prev;						\
+								\
+		_atomic_spin_lock_irqsave(ptr, flags);		\
+		if ((prev = *ptr) == old)			\
+			*ptr = new;				\
+		_atomic_spin_unlock_irqrestore(ptr, flags);	\
+		return prev;					\
+	}
 
-	_atomic_spin_lock_irqsave(ptr, flags);
-	if ((prev = *ptr) == old)
-		*ptr = new;
-	_atomic_spin_unlock_irqrestore(ptr, flags);
-	return prev;
-}
-
-unsigned long notrace __cmpxchg_u32(volatile unsigned int *ptr, unsigned int old, unsigned int new)
-{
-	unsigned long flags;
-	unsigned int prev;
-
-	_atomic_spin_lock_irqsave(ptr, flags);
-	if ((prev = *ptr) == old)
-		*ptr = new;
-	_atomic_spin_unlock_irqrestore(ptr, flags);
-	return (unsigned long)prev;
-}
-
-u8 notrace __cmpxchg_u8(volatile u8 *ptr, u8 old, u8 new)
-{
-	unsigned long flags;
-	u8 prev;
-
-	_atomic_spin_lock_irqsave(ptr, flags);
-	if ((prev = *ptr) == old)
-		*ptr = new;
-	_atomic_spin_unlock_irqrestore(ptr, flags);
-	return prev;
-}
+CMPXCHG(u64)
+CMPXCHG(u32)
+CMPXCHG(u16)
+CMPXCHG(u8)

arch/sparc/include/asm/cmpxchg_32.h

@@ -38,21 +38,19 @@ static __always_inline unsigned long __arch_xchg(unsigned long x, __volatile__ v
 
 /* bug catcher for when unsupported size is used - won't link */
 void __cmpxchg_called_with_bad_pointer(void);
-/* we only need to support cmpxchg of a u32 on sparc */
-unsigned long __cmpxchg_u32(volatile u32 *m, u32 old, u32 new_);
+u8 __cmpxchg_u8(volatile u8 *m, u8 old, u8 new_);
+u16 __cmpxchg_u16(volatile u16 *m, u16 old, u16 new_);
+u32 __cmpxchg_u32(volatile u32 *m, u32 old, u32 new_);
 
 /* don't worry...optimizer will get rid of most of this */
 static inline unsigned long
 __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new_, int size)
 {
-	switch (size) {
-	case 4:
-		return __cmpxchg_u32((u32 *)ptr, (u32)old, (u32)new_);
-	default:
-		__cmpxchg_called_with_bad_pointer();
-		break;
-	}
-	return old;
+	return
+		size == 1 ? __cmpxchg_u8(ptr, old, new_) :
+		size == 2 ? __cmpxchg_u16(ptr, old, new_) :
+		size == 4 ? __cmpxchg_u32(ptr, old, new_) :
+			(__cmpxchg_called_with_bad_pointer(), old);
 }
 
 #define arch_cmpxchg(ptr, o, n)						\
@@ -63,7 +61,7 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new_, int size)
 			(unsigned long)_n_, sizeof(*(ptr)));		\
 })
 
-u64 __cmpxchg_u64(u64 *ptr, u64 old, u64 new);
+u64 __cmpxchg_u64(volatile u64 *ptr, u64 old, u64 new);
 #define arch_cmpxchg64(ptr, old, new)	__cmpxchg_u64(ptr, old, new)
 
 #include <asm-generic/cmpxchg-local.h>

arch/sparc/lib/atomic32.c

@@ -159,32 +159,27 @@ unsigned long sp32___change_bit(unsigned long *addr, unsigned long mask)
 }
 EXPORT_SYMBOL(sp32___change_bit);
 
-unsigned long __cmpxchg_u32(volatile u32 *ptr, u32 old, u32 new)
-{
-	unsigned long flags;
-	u32 prev;
+#define CMPXCHG(T)						\
+	T __cmpxchg_##T(volatile T *ptr, T old, T new)		\
+	{							\
+		unsigned long flags;				\
+		T prev;						\
+								\
+		spin_lock_irqsave(ATOMIC_HASH(ptr), flags);	\
+		if ((prev = *ptr) == old)			\
+			*ptr = new;				\
+		spin_unlock_irqrestore(ATOMIC_HASH(ptr), flags);\
+								\
+		return prev;					\
+	}
 
-	spin_lock_irqsave(ATOMIC_HASH(ptr), flags);
-	if ((prev = *ptr) == old)
-		*ptr = new;
-	spin_unlock_irqrestore(ATOMIC_HASH(ptr), flags);
-
-	return (unsigned long)prev;
-}
+CMPXCHG(u8)
+CMPXCHG(u16)
+CMPXCHG(u32)
+CMPXCHG(u64)
+EXPORT_SYMBOL(__cmpxchg_u8);
+EXPORT_SYMBOL(__cmpxchg_u16);
 EXPORT_SYMBOL(__cmpxchg_u32);
-
-u64 __cmpxchg_u64(u64 *ptr, u64 old, u64 new)
-{
-	unsigned long flags;
-	u64 prev;
-
-	spin_lock_irqsave(ATOMIC_HASH(ptr), flags);
-	if ((prev = *ptr) == old)
-		*ptr = new;
-	spin_unlock_irqrestore(ATOMIC_HASH(ptr), flags);
-
-	return prev;
-}
 EXPORT_SYMBOL(__cmpxchg_u64);
 
 unsigned long __xchg_u32(volatile u32 *ptr, u32 new)

include/linux/cmpxchg-emu.h

@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Emulated 1-byte and 2-byte cmpxchg operations for architectures
+ * lacking direct support for these sizes.  These are implemented in terms
+ * of 4-byte cmpxchg operations.
+ *
+ * Copyright (C) 2024 Paul E. McKenney.
+ */
+
+#ifndef __LINUX_CMPXCHG_EMU_H
+#define __LINUX_CMPXCHG_EMU_H
+
+uintptr_t cmpxchg_emu_u8(volatile u8 *p, uintptr_t old, uintptr_t new);
+
+#endif /* __LINUX_CMPXCHG_EMU_H */

lib/Makefile

@@ -236,6 +236,7 @@ obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
 lib-$(CONFIG_GENERIC_BUG) += bug.o
 
 obj-$(CONFIG_HAVE_ARCH_TRACEHOOK) += syscall.o
+obj-$(CONFIG_ARCH_NEED_CMPXCHG_1_EMU) += cmpxchg-emu.o
 
 obj-$(CONFIG_DYNAMIC_DEBUG_CORE) += dynamic_debug.o
 #ensure exported functions have prototypes

lib/cmpxchg-emu.c

@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Emulated 1-byte cmpxchg operation for architectures lacking direct
+ * support for this size.  This is implemented in terms of 4-byte cmpxchg
+ * operations.
+ *
+ * Copyright (C) 2024 Paul E. McKenney.
+ */
+
+#include <linux/types.h>
+#include <linux/export.h>
+#include <linux/instrumented.h>
+#include <linux/atomic.h>
+#include <linux/panic.h>
+#include <linux/bug.h>
+#include <asm-generic/rwonce.h>
+#include <linux/cmpxchg-emu.h>
+
+union u8_32 {
+	u8 b[4];
+	u32 w;
+};
+
+/* Emulate one-byte cmpxchg() in terms of 4-byte cmpxchg. */
+uintptr_t cmpxchg_emu_u8(volatile u8 *p, uintptr_t old, uintptr_t new)
+{
+	u32 *p32 = (u32 *)(((uintptr_t)p) & ~0x3);
+	int i = ((uintptr_t)p) & 0x3;
+	union u8_32 old32;
+	union u8_32 new32;
+	u32 ret;
+
+	ret = READ_ONCE(*p32);
+	do {
+		old32.w = ret;
+		if (old32.b[i] != old)
+			return old32.b[i];
+		new32.w = old32.w;
+		new32.b[i] = new;
+		instrument_atomic_read_write(p, 1);
+		ret = data_race(cmpxchg(p32, old32.w, new32.w)); // Overridden above.
+	} while (ret != old32.w);
+	return old;
+}
+EXPORT_SYMBOL_GPL(cmpxchg_emu_u8);