diff mbox series

alpha cmpxchg.h (was Re: [PATCH v2 cmpxchg 12/13] sh: Emulate one-byte cmpxchg)

Message ID 20240502210122.GA2322432@ZenIV (mailing list archive)
State New, archived
Headers show
Series alpha cmpxchg.h (was Re: [PATCH v2 cmpxchg 12/13] sh: Emulate one-byte cmpxchg) | expand

Commit Message

Al Viro May 2, 2024, 9:01 p.m. UTC 
On Thu, May 02, 2024 at 09:53:45PM +0100, Al Viro wrote:
> What's more, load-locked/store-conditional doesn't have 16bit and 8bit
> variants on any Alphas - it's always 32bit (ldl_l) or 64bit (ldq_l).
> 
> What BWX adds is load/store byte/word, load/store byte/word unaligned
> and sign-extend byte/word.  IOW, it's absolutely irrelevant for
> cmpxchg (or xchg) purposes.

FWIW, I do have a cmpxchg-related patch for alpha - the mess with xchg.h
(parametrized double include) is no longer needed, and hadn't been since
2018 (fbfcd0199170 "locking/xchg/alpha: Remove superfluous memory barriers
from the _local() variants" was the point when the things settled down).
Only tangentially related to your stuff, but it makes the damn thing
easier to follow.


commit e992b5436ccd504b07a390118cf2be686355b957
Author: Al Viro <viro@zeniv.linux.org.uk>
Date:   Mon Apr 8 17:43:37 2024 -0400

    alpha: no need to include asm/xchg.h twice
    
    We used to generate different helpers for local and full
    {cmp,}xchg(); these days the barriers are in arch_{cmp,}xchg()
    instead and generated helpers are identical for local and
    full cases.  No need for those parametrized includes of
    asm/xchg.h - we might as well insert its contents directly
    in asm/cmpxchg.h and do it only once.
    
    Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

Comments

Linus Torvalds May 2, 2024, 10:16 p.m. UTC | #1 
On Thu, 2 May 2024 at 14:01, Al Viro <viro@zeniv.linux.org.uk> wrote:
>
> +static inline unsigned long
> +____xchg_u8(volatile char *m, unsigned long val)
> +{
> +       unsigned long ret, tmp, addr64;
> +
> +       __asm__ __volatile__(
> +       "       andnot  %4,7,%3\n"
> +       "       insbl   %1,%4,%1\n"
> +       "1:     ldq_l   %2,0(%3)\n"
> +       "       extbl   %2,%4,%0\n"
> +       "       mskbl   %2,%4,%2\n"
> +       "       or      %1,%2,%2\n"
> +       "       stq_c   %2,0(%3)\n"
> +       "       beq     %2,2f\n"
> +       ".subsection 2\n"
> +       "2:     br      1b\n"
> +       ".previous"
> +       : "=&r" (ret), "=&r" (val), "=&r" (tmp), "=&r" (addr64)
> +       : "r" ((long)m), "1" (val) : "memory");
> +
> +       return ret;
> +}

Side note: if you move this around, I think you should just uninline
it too and turn it into a function call.

This inline asm doesn't actually take any advantage of the inlining.
The main reason to inline something like this is that you could then
deal with different compile-time alignments better than using the
generic software sequence. But that's not what the inline asm actually
does, and it uses the worst-case code sequence for inserting the byte.

Put that together with "byte and word xchg are rare", and it really
smells to me like we shouldn't be inlining this.

Now, the 32-bit and 64-bit cases are different - more common, but also
much simpler code sequences. They seem worth inlining.

That said, maybe for alpha, the "just move code around" is better than
"fix up old bad decisions" just because the effort is lower.

              Linus
diff mbox series

Patch

diff --git a/arch/alpha/include/asm/cmpxchg.h b/arch/alpha/include/asm/cmpxchg.h
index 91d4a4d9258c..ae1b96479d0c 100644
--- a/arch/alpha/include/asm/cmpxchg.h
+++ b/arch/alpha/include/asm/cmpxchg.h
@@ -3,17 +3,232 @@ 
 #define _ALPHA_CMPXCHG_H
 
 /*
- * Atomic exchange routines.
+ * Atomic exchange.
+ * Since it can be used to implement critical sections
+ * it must clobber "memory" (also for interrupts in UP).
  */
 
-#define ____xchg(type, args...)		__arch_xchg ## type ## _local(args)
-#define ____cmpxchg(type, args...)	__cmpxchg ## type ## _local(args)
-#include <asm/xchg.h>
+static inline unsigned long
+____xchg_u8(volatile char *m, unsigned long val)
+{
+	unsigned long ret, tmp, addr64;
+
+	__asm__ __volatile__(
+	"	andnot	%4,7,%3\n"
+	"	insbl	%1,%4,%1\n"
+	"1:	ldq_l	%2,0(%3)\n"
+	"	extbl	%2,%4,%0\n"
+	"	mskbl	%2,%4,%2\n"
+	"	or	%1,%2,%2\n"
+	"	stq_c	%2,0(%3)\n"
+	"	beq	%2,2f\n"
+	".subsection 2\n"
+	"2:	br	1b\n"
+	".previous"
+	: "=&r" (ret), "=&r" (val), "=&r" (tmp), "=&r" (addr64)
+	: "r" ((long)m), "1" (val) : "memory");
+
+	return ret;
+}
+
+static inline unsigned long
+____xchg_u16(volatile short *m, unsigned long val)
+{
+	unsigned long ret, tmp, addr64;
+
+	__asm__ __volatile__(
+	"	andnot	%4,7,%3\n"
+	"	inswl	%1,%4,%1\n"
+	"1:	ldq_l	%2,0(%3)\n"
+	"	extwl	%2,%4,%0\n"
+	"	mskwl	%2,%4,%2\n"
+	"	or	%1,%2,%2\n"
+	"	stq_c	%2,0(%3)\n"
+	"	beq	%2,2f\n"
+	".subsection 2\n"
+	"2:	br	1b\n"
+	".previous"
+	: "=&r" (ret), "=&r" (val), "=&r" (tmp), "=&r" (addr64)
+	: "r" ((long)m), "1" (val) : "memory");
+
+	return ret;
+}
+
+static inline unsigned long
+____xchg_u32(volatile int *m, unsigned long val)
+{
+	unsigned long dummy;
+
+	__asm__ __volatile__(
+	"1:	ldl_l %0,%4\n"
+	"	bis $31,%3,%1\n"
+	"	stl_c %1,%2\n"
+	"	beq %1,2f\n"
+	".subsection 2\n"
+	"2:	br 1b\n"
+	".previous"
+	: "=&r" (val), "=&r" (dummy), "=m" (*m)
+	: "rI" (val), "m" (*m) : "memory");
+
+	return val;
+}
+
+static inline unsigned long
+____xchg_u64(volatile long *m, unsigned long val)
+{
+	unsigned long dummy;
+
+	__asm__ __volatile__(
+	"1:	ldq_l %0,%4\n"
+	"	bis $31,%3,%1\n"
+	"	stq_c %1,%2\n"
+	"	beq %1,2f\n"
+	".subsection 2\n"
+	"2:	br 1b\n"
+	".previous"
+	: "=&r" (val), "=&r" (dummy), "=m" (*m)
+	: "rI" (val), "m" (*m) : "memory");
+
+	return val;
+}
+
+/* This function doesn't exist, so you'll get a linker error
+   if something tries to do an invalid xchg().  */
+extern void __xchg_called_with_bad_pointer(void);
+
+static __always_inline unsigned long
+____xchg(volatile void *ptr, unsigned long x, int size)
+{
+	return
+		size == 1 ? ____xchg_u8(ptr, x) :
+		size == 2 ? ____xchg_u16(ptr, x) :
+		size == 4 ? ____xchg_u32(ptr, x) :
+		size == 8 ? ____xchg_u64(ptr, x) :
+			(__xchg_called_with_bad_pointer(), x);
+}
+
+/*
+ * Atomic compare and exchange.  Compare OLD with MEM, if identical,
+ * store NEW in MEM.  Return the initial value in MEM.  Success is
+ * indicated by comparing RETURN with OLD.
+ */
+
+static inline unsigned long
+____cmpxchg_u8(volatile char *m, unsigned char old, unsigned char new)
+{
+	unsigned long prev, tmp, cmp, addr64;
+
+	__asm__ __volatile__(
+	"	andnot	%5,7,%4\n"
+	"	insbl	%1,%5,%1\n"
+	"1:	ldq_l	%2,0(%4)\n"
+	"	extbl	%2,%5,%0\n"
+	"	cmpeq	%0,%6,%3\n"
+	"	beq	%3,2f\n"
+	"	mskbl	%2,%5,%2\n"
+	"	or	%1,%2,%2\n"
+	"	stq_c	%2,0(%4)\n"
+	"	beq	%2,3f\n"
+	"2:\n"
+	".subsection 2\n"
+	"3:	br	1b\n"
+	".previous"
+	: "=&r" (prev), "=&r" (new), "=&r" (tmp), "=&r" (cmp), "=&r" (addr64)
+	: "r" ((long)m), "Ir" (old), "1" (new) : "memory");
+
+	return prev;
+}
+
+static inline unsigned long
+____cmpxchg_u16(volatile short *m, unsigned short old, unsigned short new)
+{
+	unsigned long prev, tmp, cmp, addr64;
+
+	__asm__ __volatile__(
+	"	andnot	%5,7,%4\n"
+	"	inswl	%1,%5,%1\n"
+	"1:	ldq_l	%2,0(%4)\n"
+	"	extwl	%2,%5,%0\n"
+	"	cmpeq	%0,%6,%3\n"
+	"	beq	%3,2f\n"
+	"	mskwl	%2,%5,%2\n"
+	"	or	%1,%2,%2\n"
+	"	stq_c	%2,0(%4)\n"
+	"	beq	%2,3f\n"
+	"2:\n"
+	".subsection 2\n"
+	"3:	br	1b\n"
+	".previous"
+	: "=&r" (prev), "=&r" (new), "=&r" (tmp), "=&r" (cmp), "=&r" (addr64)
+	: "r" ((long)m), "Ir" (old), "1" (new) : "memory");
+
+	return prev;
+}
+
+static inline unsigned long
+____cmpxchg_u32(volatile int *m, int old, int new)
+{
+	unsigned long prev, cmp;
+
+	__asm__ __volatile__(
+	"1:	ldl_l %0,%5\n"
+	"	cmpeq %0,%3,%1\n"
+	"	beq %1,2f\n"
+	"	mov %4,%1\n"
+	"	stl_c %1,%2\n"
+	"	beq %1,3f\n"
+	"2:\n"
+	".subsection 2\n"
+	"3:	br 1b\n"
+	".previous"
+	: "=&r"(prev), "=&r"(cmp), "=m"(*m)
+	: "r"((long) old), "r"(new), "m"(*m) : "memory");
+
+	return prev;
+}
+
+static inline unsigned long
+____cmpxchg_u64(volatile long *m, unsigned long old, unsigned long new)
+{
+	unsigned long prev, cmp;
+
+	__asm__ __volatile__(
+	"1:	ldq_l %0,%5\n"
+	"	cmpeq %0,%3,%1\n"
+	"	beq %1,2f\n"
+	"	mov %4,%1\n"
+	"	stq_c %1,%2\n"
+	"	beq %1,3f\n"
+	"2:\n"
+	".subsection 2\n"
+	"3:	br 1b\n"
+	".previous"
+	: "=&r"(prev), "=&r"(cmp), "=m"(*m)
+	: "r"((long) old), "r"(new), "m"(*m) : "memory");
+
+	return prev;
+}
+
+/* This function doesn't exist, so you'll get a linker error
+   if something tries to do an invalid cmpxchg().  */
+extern void __cmpxchg_called_with_bad_pointer(void);
+
+static __always_inline unsigned long
+____cmpxchg(volatile void *ptr, unsigned long old, unsigned long new,
+	      int size)
+{
+	return
+		size == 1 ? ____cmpxchg_u8(ptr, old, new) :
+		size == 2 ? ____cmpxchg_u16(ptr, old, new) :
+		size == 4 ? ____cmpxchg_u32(ptr, old, new) :
+		size == 8 ? ____cmpxchg_u64(ptr, old, new) :
+			(__cmpxchg_called_with_bad_pointer(), old);
+}
 
 #define xchg_local(ptr, x)						\
 ({									\
 	__typeof__(*(ptr)) _x_ = (x);					\
-	(__typeof__(*(ptr))) __arch_xchg_local((ptr), (unsigned long)_x_,\
+	(__typeof__(*(ptr))) ____xchg((ptr), (unsigned long)_x_,	\
 					       sizeof(*(ptr)));		\
 })
 
@@ -21,7 +236,7 @@ 
 ({									\
 	__typeof__(*(ptr)) _o_ = (o);					\
 	__typeof__(*(ptr)) _n_ = (n);					\
-	(__typeof__(*(ptr))) __cmpxchg_local((ptr), (unsigned long)_o_,	\
+	(__typeof__(*(ptr))) ____cmpxchg((ptr), (unsigned long)_o_,	\
 					  (unsigned long)_n_,		\
 					  sizeof(*(ptr)));		\
 })
@@ -32,12 +247,6 @@ 
 	cmpxchg_local((ptr), (o), (n));					\
 })
 
-#undef ____xchg
-#undef ____cmpxchg
-#define ____xchg(type, args...)		__arch_xchg ##type(args)
-#define ____cmpxchg(type, args...)	__cmpxchg ##type(args)
-#include <asm/xchg.h>
-
 /*
  * The leading and the trailing memory barriers guarantee that these
  * operations are fully ordered.
@@ -48,7 +257,7 @@ 
 	__typeof__(*(ptr)) _x_ = (x);					\
 	smp_mb();							\
 	__ret = (__typeof__(*(ptr)))					\
-		__arch_xchg((ptr), (unsigned long)_x_, sizeof(*(ptr)));	\
+		____xchg((ptr), (unsigned long)_x_, sizeof(*(ptr)));	\
 	smp_mb();							\
 	__ret;								\
 })
@@ -59,7 +268,7 @@ 
 	__typeof__(*(ptr)) _o_ = (o);					\
 	__typeof__(*(ptr)) _n_ = (n);					\
 	smp_mb();							\
-	__ret = (__typeof__(*(ptr))) __cmpxchg((ptr),			\
+	__ret = (__typeof__(*(ptr))) ____cmpxchg((ptr),			\
 		(unsigned long)_o_, (unsigned long)_n_, sizeof(*(ptr)));\
 	smp_mb();							\
 	__ret;								\
@@ -71,6 +280,4 @@ 
 	arch_cmpxchg((ptr), (o), (n));					\
 })
 
-#undef ____cmpxchg
-
 #endif /* _ALPHA_CMPXCHG_H */
diff --git a/arch/alpha/include/asm/xchg.h b/arch/alpha/include/asm/xchg.h
deleted file mode 100644
index 7adb80c6746a..000000000000
--- a/arch/alpha/include/asm/xchg.h
+++ /dev/null
@@ -1,246 +0,0 @@ 
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ALPHA_CMPXCHG_H
-#error Do not include xchg.h directly!
-#else
-/*
- * xchg/xchg_local and cmpxchg/cmpxchg_local share the same code
- * except that local version do not have the expensive memory barrier.
- * So this file is included twice from asm/cmpxchg.h.
- */
-
-/*
- * Atomic exchange.
- * Since it can be used to implement critical sections
- * it must clobber "memory" (also for interrupts in UP).
- */
-
-static inline unsigned long
-____xchg(_u8, volatile char *m, unsigned long val)
-{
-	unsigned long ret, tmp, addr64;
-
-	__asm__ __volatile__(
-	"	andnot	%4,7,%3\n"
-	"	insbl	%1,%4,%1\n"
-	"1:	ldq_l	%2,0(%3)\n"
-	"	extbl	%2,%4,%0\n"
-	"	mskbl	%2,%4,%2\n"
-	"	or	%1,%2,%2\n"
-	"	stq_c	%2,0(%3)\n"
-	"	beq	%2,2f\n"
-	".subsection 2\n"
-	"2:	br	1b\n"
-	".previous"
-	: "=&r" (ret), "=&r" (val), "=&r" (tmp), "=&r" (addr64)
-	: "r" ((long)m), "1" (val) : "memory");
-
-	return ret;
-}
-
-static inline unsigned long
-____xchg(_u16, volatile short *m, unsigned long val)
-{
-	unsigned long ret, tmp, addr64;
-
-	__asm__ __volatile__(
-	"	andnot	%4,7,%3\n"
-	"	inswl	%1,%4,%1\n"
-	"1:	ldq_l	%2,0(%3)\n"
-	"	extwl	%2,%4,%0\n"
-	"	mskwl	%2,%4,%2\n"
-	"	or	%1,%2,%2\n"
-	"	stq_c	%2,0(%3)\n"
-	"	beq	%2,2f\n"
-	".subsection 2\n"
-	"2:	br	1b\n"
-	".previous"
-	: "=&r" (ret), "=&r" (val), "=&r" (tmp), "=&r" (addr64)
-	: "r" ((long)m), "1" (val) : "memory");
-
-	return ret;
-}
-
-static inline unsigned long
-____xchg(_u32, volatile int *m, unsigned long val)
-{
-	unsigned long dummy;
-
-	__asm__ __volatile__(
-	"1:	ldl_l %0,%4\n"
-	"	bis $31,%3,%1\n"
-	"	stl_c %1,%2\n"
-	"	beq %1,2f\n"
-	".subsection 2\n"
-	"2:	br 1b\n"
-	".previous"
-	: "=&r" (val), "=&r" (dummy), "=m" (*m)
-	: "rI" (val), "m" (*m) : "memory");
-
-	return val;
-}
-
-static inline unsigned long
-____xchg(_u64, volatile long *m, unsigned long val)
-{
-	unsigned long dummy;
-
-	__asm__ __volatile__(
-	"1:	ldq_l %0,%4\n"
-	"	bis $31,%3,%1\n"
-	"	stq_c %1,%2\n"
-	"	beq %1,2f\n"
-	".subsection 2\n"
-	"2:	br 1b\n"
-	".previous"
-	: "=&r" (val), "=&r" (dummy), "=m" (*m)
-	: "rI" (val), "m" (*m) : "memory");
-
-	return val;
-}
-
-/* This function doesn't exist, so you'll get a linker error
-   if something tries to do an invalid xchg().  */
-extern void __xchg_called_with_bad_pointer(void);
-
-static __always_inline unsigned long
-____xchg(, volatile void *ptr, unsigned long x, int size)
-{
-	switch (size) {
-		case 1:
-			return ____xchg(_u8, ptr, x);
-		case 2:
-			return ____xchg(_u16, ptr, x);
-		case 4:
-			return ____xchg(_u32, ptr, x);
-		case 8:
-			return ____xchg(_u64, ptr, x);
-	}
-	__xchg_called_with_bad_pointer();
-	return x;
-}
-
-/*
- * Atomic compare and exchange.  Compare OLD with MEM, if identical,
- * store NEW in MEM.  Return the initial value in MEM.  Success is
- * indicated by comparing RETURN with OLD.
- */
-
-static inline unsigned long
-____cmpxchg(_u8, volatile char *m, unsigned char old, unsigned char new)
-{
-	unsigned long prev, tmp, cmp, addr64;
-
-	__asm__ __volatile__(
-	"	andnot	%5,7,%4\n"
-	"	insbl	%1,%5,%1\n"
-	"1:	ldq_l	%2,0(%4)\n"
-	"	extbl	%2,%5,%0\n"
-	"	cmpeq	%0,%6,%3\n"
-	"	beq	%3,2f\n"
-	"	mskbl	%2,%5,%2\n"
-	"	or	%1,%2,%2\n"
-	"	stq_c	%2,0(%4)\n"
-	"	beq	%2,3f\n"
-	"2:\n"
-	".subsection 2\n"
-	"3:	br	1b\n"
-	".previous"
-	: "=&r" (prev), "=&r" (new), "=&r" (tmp), "=&r" (cmp), "=&r" (addr64)
-	: "r" ((long)m), "Ir" (old), "1" (new) : "memory");
-
-	return prev;
-}
-
-static inline unsigned long
-____cmpxchg(_u16, volatile short *m, unsigned short old, unsigned short new)
-{
-	unsigned long prev, tmp, cmp, addr64;
-
-	__asm__ __volatile__(
-	"	andnot	%5,7,%4\n"
-	"	inswl	%1,%5,%1\n"
-	"1:	ldq_l	%2,0(%4)\n"
-	"	extwl	%2,%5,%0\n"
-	"	cmpeq	%0,%6,%3\n"
-	"	beq	%3,2f\n"
-	"	mskwl	%2,%5,%2\n"
-	"	or	%1,%2,%2\n"
-	"	stq_c	%2,0(%4)\n"
-	"	beq	%2,3f\n"
-	"2:\n"
-	".subsection 2\n"
-	"3:	br	1b\n"
-	".previous"
-	: "=&r" (prev), "=&r" (new), "=&r" (tmp), "=&r" (cmp), "=&r" (addr64)
-	: "r" ((long)m), "Ir" (old), "1" (new) : "memory");
-
-	return prev;
-}
-
-static inline unsigned long
-____cmpxchg(_u32, volatile int *m, int old, int new)
-{
-	unsigned long prev, cmp;
-
-	__asm__ __volatile__(
-	"1:	ldl_l %0,%5\n"
-	"	cmpeq %0,%3,%1\n"
-	"	beq %1,2f\n"
-	"	mov %4,%1\n"
-	"	stl_c %1,%2\n"
-	"	beq %1,3f\n"
-	"2:\n"
-	".subsection 2\n"
-	"3:	br 1b\n"
-	".previous"
-	: "=&r"(prev), "=&r"(cmp), "=m"(*m)
-	: "r"((long) old), "r"(new), "m"(*m) : "memory");
-
-	return prev;
-}
-
-static inline unsigned long
-____cmpxchg(_u64, volatile long *m, unsigned long old, unsigned long new)
-{
-	unsigned long prev, cmp;
-
-	__asm__ __volatile__(
-	"1:	ldq_l %0,%5\n"
-	"	cmpeq %0,%3,%1\n"
-	"	beq %1,2f\n"
-	"	mov %4,%1\n"
-	"	stq_c %1,%2\n"
-	"	beq %1,3f\n"
-	"2:\n"
-	".subsection 2\n"
-	"3:	br 1b\n"
-	".previous"
-	: "=&r"(prev), "=&r"(cmp), "=m"(*m)
-	: "r"((long) old), "r"(new), "m"(*m) : "memory");
-
-	return prev;
-}
-
-/* This function doesn't exist, so you'll get a linker error
-   if something tries to do an invalid cmpxchg().  */
-extern void __cmpxchg_called_with_bad_pointer(void);
-
-static __always_inline unsigned long
-____cmpxchg(, volatile void *ptr, unsigned long old, unsigned long new,
-	      int size)
-{
-	switch (size) {
-		case 1:
-			return ____cmpxchg(_u8, ptr, old, new);
-		case 2:
-			return ____cmpxchg(_u16, ptr, old, new);
-		case 4:
-			return ____cmpxchg(_u32, ptr, old, new);
-		case 8:
-			return ____cmpxchg(_u64, ptr, old, new);
-	}
-	__cmpxchg_called_with_bad_pointer();
-	return old;
-}
-
-#endif