This completes the xchg implementation for sh architecture. Note: The
llsc variant is tricky since this only supports 4 byte atomics, the
existing implementation of 1 byte xchg is wrong: we need to do a 4 byte
cmpxchg and retry if any bytes changed meanwhile.
Write this in C for clarity.
Suggested-by: Rich Felker <dalias@xxxxxxxx>
Signed-off-by: Michael S. Tsirkin <mst@xxxxxxxxxx>
---
arch/sh/include/asm/cmpxchg-grb.h | 22 +++++++++++++++
arch/sh/include/asm/cmpxchg-irq.h | 11 ++++++++
arch/sh/include/asm/cmpxchg-llsc.h | 58 +++++++++++++++++++++++---------------
arch/sh/include/asm/cmpxchg.h | 3 ++
4 files changed, 72 insertions(+), 22 deletions(-)
diff --git a/arch/sh/include/asm/cmpxchg-grb.h b/arch/sh/include/asm/cmpxchg-grb.h
index f848dec..2ed557b 100644
--- a/arch/sh/include/asm/cmpxchg-grb.h
+++ b/arch/sh/include/asm/cmpxchg-grb.h
@@ -23,6 +23,28 @@ static inline unsigned long xchg_u32(volatile u32 *m, unsigned long val)
return retval;
}
+static inline unsigned long xchg_u16(volatile u16 *m, unsigned long val)
+{
+ unsigned long retval;
+
+ __asm__ __volatile__ (
+ " .align 2 \n\t"
+ " mova 1f, r0 \n\t" /* r0 = end point */
+ " mov r15, r1 \n\t" /* r1 = saved sp */
+ " mov #-6, r15 \n\t" /* LOGIN */
+ " mov.w @%1, %0 \n\t" /* load old value */
+ " extu.w %0, %0 \n\t" /* extend as unsigned */
+ " mov.w %2, @%1 \n\t" /* store new value */
+ "1: mov r1, r15 \n\t" /* LOGOUT */
+ : "=&r" (retval),
+ "+r" (m),
+ "+r" (val) /* inhibit r15 overloading */
+ :
+ : "memory" , "r0", "r1");
+
+ return retval;
+}
+
static inline unsigned long xchg_u8(volatile u8 *m, unsigned long val)
{
unsigned long retval;
diff --git a/arch/sh/include/asm/cmpxchg-irq.h b/arch/sh/include/asm/cmpxchg-irq.h
index bd11f63..f888772 100644
--- a/arch/sh/include/asm/cmpxchg-irq.h
+++ b/arch/sh/include/asm/cmpxchg-irq.h
@@ -14,6 +14,17 @@ static inline unsigned long xchg_u32(volatile u32 *m, unsigned long val)
return retval;
}
+static inline unsigned long xchg_u16(volatile u16 *m, unsigned long val)
+{
+ unsigned long flags, retval;
+
+ local_irq_save(flags);
+ retval = *m;
+ *m = val;
+ local_irq_restore(flags);
+ return retval;
+}
+
static inline unsigned long xchg_u8(volatile u8 *m, unsigned long val)
{
unsigned long flags, retval;
diff --git a/arch/sh/include/asm/cmpxchg-llsc.h b/arch/sh/include/asm/cmpxchg-llsc.h
index 4713666..e754794 100644
--- a/arch/sh/include/asm/cmpxchg-llsc.h
+++ b/arch/sh/include/asm/cmpxchg-llsc.h
@@ -1,6 +1,9 @@
#ifndef __ASM_SH_CMPXCHG_LLSC_H
#define __ASM_SH_CMPXCHG_LLSC_H
+#include <linux/bitops.h>
+#include <asm/byteorder.h>
+
static inline unsigned long xchg_u32(volatile u32 *m, unsigned long val)
{
unsigned long retval;
@@ -22,29 +25,8 @@ static inline unsigned long xchg_u32(volatile u32 *m, unsigned long val)
return retval;
}
-static inline unsigned long xchg_u8(volatile u8 *m, unsigned long val)
-{
- unsigned long retval;
- unsigned long tmp;
-
- __asm__ __volatile__ (
- "1: \n\t"
- "movli.l @%2, %0 ! xchg_u8 \n\t"
- "mov %0, %1 \n\t"
- "mov %3, %0 \n\t"
- "movco.l %0, @%2 \n\t"
- "bf 1b \n\t"
- "synco \n\t"
- : "=&z"(tmp), "=&r" (retval)
- : "r" (m), "r" (val & 0xff)
- : "t", "memory"
- );
-
- return retval;
-}
-
static inline unsigned long
-__cmpxchg_u32(volatile int *m, unsigned long old, unsigned long new)
+__cmpxchg_u32(volatile u32 *m, unsigned long old, unsigned long new)
{
unsigned long retval;
unsigned long tmp;
@@ -68,4 +50,36 @@ __cmpxchg_u32(volatile int *m, unsigned long old, unsigned long new)
return retval;
}
+static inline u32 __xchg_cmpxchg(volatile void *ptr, u32 x, int size)
+{
+ int off = (unsigned long)ptr % sizeof(u32);
+ volatile u32 *p = ptr - off;
+#ifdef __BIG_ENDIAN
+ int bitoff = (sizeof(u32) - 1 - off) * BITS_PER_BYTE;
+#else
+ int bitoff = off * BITS_PER_BYTE;
+#endif
+ u32 bitmask = ((0x1 << size * BITS_PER_BYTE) - 1) << bitoff;
+ u32 oldv, newv;
+ u32 ret;
+
+ do {
+ oldv = READ_ONCE(*p);
+ ret = (oldv & bitmask) >> bitoff;
+ newv = (oldv & ~bitmask) | (x << bitoff);
+ } while (__cmpxchg_u32(p, oldv, newv) != oldv);
+
+ return ret;
+}
+
+static inline unsigned long xchg_u16(volatile u16 *m, unsigned long val)
+{
+ return __xchg_cmpxchg(m, val, sizeof *m);
+}
+
+static inline unsigned long xchg_u8(volatile u8 *m, unsigned long val)
+{
+ return __xchg_cmpxchg(m, val, sizeof *m);
+}
+
#endif /* __ASM_SH_CMPXCHG_LLSC_H */
diff --git a/arch/sh/include/asm/cmpxchg.h b/arch/sh/include/asm/cmpxchg.h
index 85c97b18..5225916 100644
--- a/arch/sh/include/asm/cmpxchg.h
+++ b/arch/sh/include/asm/cmpxchg.h
@@ -27,6 +27,9 @@ extern void __xchg_called_with_bad_pointer(void);
case 4: \
__xchg__res = xchg_u32(__xchg_ptr, x); \
break; \
+ case 2: \
+ __xchg__res = xchg_u16(__xchg_ptr, x); \
+ break; \
case 1: \
__xchg__res = xchg_u8(__xchg_ptr, x); \
break; \
--
MST
