Actually, on 386, cmpxchg and cmpxchg_local fall back on
cmpxchg_386_u8/16/32: it disables interruptions around non atomic
updates to mimic the cmpxchg behavior.
The comment:
/* Poor man's cmpxchg for 386. Unsuitable for SMP */
already present in cmpxchg_386_u32 tells much about how this cmpxchg
implementation should not be used in a SMP context. However, the cmpxchg_local
can perfectly use this fallback, since it only needs to be atomic wrt the local
cpu.
This patch adds a cmpxchg_486_u64 and uses it as a fallback for cmpxchg64
and cmpxchg64_local on 80386 and 80486.
Q:
but why is it called cmpxchg_486 when the other functions are called
A:
Because the standard cmpxchg is missing only on 386, but cmpxchg8b is
missing both on 386 and 486.
Citing Intel's Instruction set reference:
cmpxchg:
This instruction is not supported on Intel processors earlier than the
Intel486 processors.
cmpxchg8b:
This instruction encoding is not supported on Intel processors earlier
than the Pentium processors.
Q:
What's the reason to have cmpxchg64_local on 32 bit architectures?
Without that need all this would just be a few simple defines.
A:
cmpxchg64_local on 32 bits architectures takes unsigned long long
parameters, but cmpxchg_local only takes longs. Since we have cmpxchg8b
to execute a 8 byte cmpxchg atomically on pentium and +, it makes sense
to provide a flavor of cmpxchg and cmpxchg_local using this instruction.
Also, for 32 bits architectures lacking the 64 bits atomic cmpxchg, it
makes sense _not_ to define cmpxchg64 while cmpxchg could still be
available.
Moreover, the fallback for cmpxchg8b on i386 for 386 and 486 is a
different case than cmpxchg (which is only required for 386). Using
different code makes this easier.
However, cmpxchg64_local will be emulated by disabling interrupts on all
architectures where it is not supported atomically.
Therefore, we *could* turn cmpxchg64_local into a cmpxchg_local, but it
would make the 386/486 fallbacks ugly, make its design different from
cmpxchg/cmpxchg64 (which really depends on atomic operations and cannot
be emulated) and require the __cmpxchg_local to be expressed as a macro
rather than an inline function so the parameters would not be fixed to
unsigned long long in every case.
So I think cmpxchg64_local makes sense there, but I am open to
suggestions.
Q:
Are there any callers?
A:
I am actually using it in LTTng in my timestamping code. I use it to
work around CPUs with asynchronous TSCs. I need to update 64 bits
values atomically on this 32 bits architecture.
Changelog:
- Ran though checkpatch.
Signed-off-by: Mathieu Desnoyers <[email protected]>
CC: [email protected]
CC: [email protected]
---
arch/i386/kernel/cpu/intel.c | 17 +++++
include/asm-i386/cmpxchg.h | 122 +++++++++++++++++++++++++++----------------
2 files changed, 96 insertions(+), 43 deletions(-)
Index: linux-2.6-lttng/arch/i386/kernel/cpu/intel.c
===================================================================
--- linux-2.6-lttng.orig/arch/i386/kernel/cpu/intel.c 2007-10-31 17:41:12.000000000 -0400
+++ linux-2.6-lttng/arch/i386/kernel/cpu/intel.c 2007-10-31 17:41:34.000000000 -0400
@@ -350,5 +350,22 @@ unsigned long cmpxchg_386_u32(volatile v
EXPORT_SYMBOL(cmpxchg_386_u32);
#endif
+#ifndef CONFIG_X86_CMPXCHG64
+unsigned long long cmpxchg_486_u64(volatile void *ptr, u64 old, u64 new)
+{
+ u64 prev;
+ unsigned long flags;
+
+ /* Poor man's cmpxchg8b for 386 and 486. Unsuitable for SMP */
+ local_irq_save(flags);
+ prev = *(u64 *)ptr;
+ if (prev == old)
+ *(u64 *)ptr = new;
+ local_irq_restore(flags);
+ return prev;
+}
+EXPORT_SYMBOL(cmpxchg_486_u64);
+#endif
+
// arch_initcall(intel_cpu_init);
Index: linux-2.6-lttng/include/asm-i386/cmpxchg.h
===================================================================
--- linux-2.6-lttng.orig/include/asm-i386/cmpxchg.h 2007-10-31 17:41:12.000000000 -0400
+++ linux-2.6-lttng/include/asm-i386/cmpxchg.h 2007-10-31 17:49:54.000000000 -0400
@@ -105,15 +105,24 @@ static inline unsigned long __xchg(unsig
#ifdef CONFIG_X86_CMPXCHG
#define __HAVE_ARCH_CMPXCHG 1
-#define cmpxchg(ptr,o,n)\
- ((__typeof__(*(ptr)))__cmpxchg((ptr),(unsigned long)(o),\
- (unsigned long)(n),sizeof(*(ptr))))
-#define sync_cmpxchg(ptr,o,n)\
- ((__typeof__(*(ptr)))__sync_cmpxchg((ptr),(unsigned long)(o),\
- (unsigned long)(n),sizeof(*(ptr))))
-#define cmpxchg_local(ptr,o,n)\
- ((__typeof__(*(ptr)))__cmpxchg_local((ptr),(unsigned long)(o),\
- (unsigned long)(n),sizeof(*(ptr))))
+#define cmpxchg(ptr, o, n) \
+ ((__typeof__(*(ptr)))__cmpxchg((ptr), (unsigned long)(o), \
+ (unsigned long)(n), sizeof(*(ptr))))
+#define sync_cmpxchg(ptr, o, n) \
+ ((__typeof__(*(ptr)))__sync_cmpxchg((ptr), (unsigned long)(o), \
+ (unsigned long)(n), sizeof(*(ptr))))
+#define cmpxchg_local(ptr, o, n) \
+ ((__typeof__(*(ptr)))__cmpxchg_local((ptr), (unsigned long)(o), \
+ (unsigned long)(n), sizeof(*(ptr))))
+#endif
+
+#ifdef CONFIG_X86_CMPXCHG64
+#define cmpxchg64(ptr, o, n) \
+ ((__typeof__(*(ptr)))__cmpxchg64((ptr), (unsigned long long)(o), \
+ (unsigned long long)(n)))
+#define cmpxchg64_local(ptr, o, n) \
+ ((__typeof__(*(ptr)))__cmpxchg64_local((ptr), (unsigned long long)(o),\
+ (unsigned long long)(n)))
#endif
static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
@@ -203,6 +212,34 @@ static inline unsigned long __cmpxchg_lo
return old;
}
+static inline unsigned long long __cmpxchg64(volatile void *ptr,
+ unsigned long long old, unsigned long long new)
+{
+ unsigned long long prev;
+ __asm__ __volatile__(LOCK_PREFIX "cmpxchg8b %3"
+ : "=A"(prev)
+ : "b"((unsigned long)new),
+ "c"((unsigned long)(new >> 32)),
+ "m"(*__xg(ptr)),
+ "0"(old)
+ : "memory");
+ return prev;
+}
+
+static inline unsigned long long __cmpxchg64_local(volatile void *ptr,
+ unsigned long long old, unsigned long long new)
+{
+ unsigned long long prev;
+ __asm__ __volatile__("cmpxchg8b %3"
+ : "=A"(prev)
+ : "b"((unsigned long)new),
+ "c"((unsigned long)(new >> 32)),
+ "m"(*__xg(ptr)),
+ "0"(old)
+ : "memory");
+ return prev;
+}
+
#ifndef CONFIG_X86_CMPXCHG
/*
* Building a kernel capable running on 80386. It may be necessary to
@@ -228,7 +265,7 @@ static inline unsigned long cmpxchg_386(
return old;
}
-#define cmpxchg(ptr,o,n) \
+#define cmpxchg(ptr, o, n) \
({ \
__typeof__(*(ptr)) __ret; \
if (likely(boot_cpu_data.x86 > 3)) \
@@ -239,7 +276,7 @@ static inline unsigned long cmpxchg_386(
(unsigned long)(n), sizeof(*(ptr))); \
__ret; \
})
-#define cmpxchg_local(ptr,o,n) \
+#define cmpxchg_local(ptr, o, n) \
({ \
__typeof__(*(ptr)) __ret; \
if (likely(boot_cpu_data.x86 > 3)) \
@@ -252,38 +289,37 @@ static inline unsigned long cmpxchg_386(
})
#endif
-static inline unsigned long long __cmpxchg64(volatile void *ptr, unsigned long long old,
- unsigned long long new)
-{
- unsigned long long prev;
- __asm__ __volatile__(LOCK_PREFIX "cmpxchg8b %3"
- : "=A"(prev)
- : "b"((unsigned long)new),
- "c"((unsigned long)(new >> 32)),
- "m"(*__xg(ptr)),
- "0"(old)
- : "memory");
- return prev;
-}
+#ifndef CONFIG_X86_CMPXCHG64
+/*
+ * Building a kernel capable running on 80386 and 80486. It may be necessary
+ * to simulate the cmpxchg8b on the 80386 and 80486 CPU.
+ */
-static inline unsigned long long __cmpxchg64_local(volatile void *ptr,
- unsigned long long old, unsigned long long new)
-{
- unsigned long long prev;
- __asm__ __volatile__("cmpxchg8b %3"
- : "=A"(prev)
- : "b"((unsigned long)new),
- "c"((unsigned long)(new >> 32)),
- "m"(*__xg(ptr)),
- "0"(old)
- : "memory");
- return prev;
-}
+extern unsigned long long cmpxchg_486_u64(volatile void *, u64, u64);
+
+#define cmpxchg64(ptr, o, n) \
+({ \
+ __typeof__(*(ptr)) __ret; \
+ if (likely(boot_cpu_data.x86 > 4)) \
+ __ret = __cmpxchg64((ptr), (unsigned long long)(o), \
+ (unsigned long long)(n)); \
+ else \
+ __ret = cmpxchg_486_u64((ptr), (unsigned long long)(o), \
+ (unsigned long long)(n)); \
+ __ret; \
+})
+#define cmpxchg64_local(ptr, o, n) \
+({ \
+ __typeof__(*(ptr)) __ret; \
+ if (likely(boot_cpu_data.x86 > 4)) \
+ __ret = __cmpxchg64_local((ptr), (unsigned long long)(o), \
+ (unsigned long long)(n)); \
+ else \
+ __ret = cmpxchg_486_u64((ptr), (unsigned long long)(o), \
+ (unsigned long long)(n)); \
+ __ret; \
+})
+
+#endif
-#define cmpxchg64(ptr,o,n)\
- ((__typeof__(*(ptr)))__cmpxchg64((ptr),(unsigned long long)(o),\
- (unsigned long long)(n)))
-#define cmpxchg64_local(ptr,o,n)\
- ((__typeof__(*(ptr)))__cmpxchg64_local((ptr),(unsigned long long)(o),\
- (unsigned long long)(n)))
#endif
--
Mathieu Desnoyers
Computer Engineering Ph.D. Student, Ecole Polytechnique de Montreal
OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
[Index of Archives]
[Kernel Newbies]
[Netfilter]
[Bugtraq]
[Photo]
[Stuff]
[Gimp]
[Yosemite News]
[MIPS Linux]
[ARM Linux]
[Linux Security]
[Linux RAID]
[Video 4 Linux]
[Linux for the blind]
[Linux Resources]
