* void S_INIT_LOCK(slock_t *lock)
* Initialize a spinlock (to the unlocked state).
*
- * void S_LOCK(slock_t *lock)
+ * int S_LOCK(slock_t *lock)
* Acquire a spinlock, waiting if necessary.
* Time out and abort() if unable to acquire the lock in a
* "reasonable" amount of time --- typically ~ 1 minute.
+ * Should return number of "delays"; see s_lock.c
*
* void S_UNLOCK(slock_t *lock)
* Unlock a previously acquired lock.
* Tests if the lock is free. Returns TRUE if free, FALSE if locked.
* This does *not* change the state of the lock.
*
+ * void SPIN_DELAY(void)
+ * Delay operation to occur inside spinlock wait loop.
+ *
* Note to implementors: there are default implementations for all these
* macros at the bottom of the file. Check if your platform can use
* these or needs to override them.
*
- * Usually, S_LOCK() is implemented in terms of an even lower-level macro
- * TAS():
+ * Usually, S_LOCK() is implemented in terms of even lower-level macros
+ * TAS() and TAS_SPIN():
*
* int TAS(slock_t *lock)
* Atomic test-and-set instruction. Attempt to acquire the lock,
* but do *not* wait. Returns 0 if successful, nonzero if unable
* to acquire the lock.
*
- * TAS() is NOT part of the API, and should never be called directly.
+ * int TAS_SPIN(slock_t *lock)
+ * Like TAS(), but this version is used when waiting for a lock
+ * previously found to be contended. By default, this is the
+ * same as TAS(), but on some architectures it's better to poll a
+ * contended lock using an unlocked instruction and retry the
+ * atomic test-and-set only when it appears free.
+ *
+ * TAS() and TAS_SPIN() are NOT part of the API, and should never be called
+ * directly.
*
- * CAUTION: on some platforms TAS() may sometimes report failure to acquire
- * a lock even when the lock is not locked. For example, on Alpha TAS()
- * will "fail" if interrupted. Therefore TAS() should always be invoked
- * in a retry loop, even if you are certain the lock is free.
+ * CAUTION: on some platforms TAS() and/or TAS_SPIN() may sometimes report
+ * failure to acquire a lock even when the lock is not locked. For example,
+ * on Alpha TAS() will "fail" if interrupted. Therefore a retry loop must
+ * always be used, even if you are certain the lock is free.
*
- * ANOTHER CAUTION: be sure that TAS() and S_UNLOCK() represent sequence
- * points, ie, loads and stores of other values must not be moved across
- * a lock or unlock. In most cases it suffices to make the operation be
- * done through a "volatile" pointer.
+ * Another caution for users of these macros is that it is the caller's
+ * responsibility to ensure that the compiler doesn't re-order accesses
+ * to shared memory to precede the actual lock acquisition, or follow the
+ * lock release. Typically we handle this by using volatile-qualified
+ * pointers to refer to both the spinlock itself and the shared data
+ * structure being accessed within the spinlocked critical section.
+ * That fixes it because compilers are not allowed to re-order accesses
+ * to volatile objects relative to other such accesses.
+ *
+ * On platforms with weak memory ordering, the TAS(), TAS_SPIN(), and
+ * S_UNLOCK() macros must further include hardware-level memory fence
+ * instructions to prevent similar re-ordering at the hardware level.
+ * TAS() and TAS_SPIN() must guarantee that loads and stores issued after
+ * the macro are not executed until the lock has been obtained. Conversely,
+ * S_UNLOCK() must guarantee that loads and stores issued before the macro
+ * have been executed before the lock is released.
*
* On most supported platforms, TAS() uses a tas() function written
* in assembly language to execute a hardware atomic-test-and-set
* instruction. Equivalent OS-supplied mutex routines could be used too.
*
- * If no system-specific TAS() is available (ie, HAS_TEST_AND_SET is not
+ * If no system-specific TAS() is available (ie, HAVE_SPINLOCKS is not
* defined), then we fall back on an emulation that uses SysV semaphores
* (see spin.c). This emulation will be MUCH MUCH slower than a proper TAS()
* implementation, because of the cost of a kernel call per lock or unlock.
* when using the SysV semaphore code.
*
*
- * Portions Copyright (c) 1996-2002, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1996-2014, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
- * $Id: s_lock.h,v 1.104 2003/04/04 05:32:30 tgl Exp $
+ * src/include/storage/s_lock.h
*
*-------------------------------------------------------------------------
*/
#ifndef S_LOCK_H
#define S_LOCK_H
-#include "storage/pg_sema.h"
-
+#ifdef HAVE_SPINLOCKS /* skip spinlocks if requested */
-#if defined(HAS_TEST_AND_SET)
-
-
-#if defined(__GNUC__)
+#if defined(__GNUC__) || defined(__INTEL_COMPILER)
/*************************************************************************
* All the gcc inlines
+ * Gcc consistently defines the CPU as __cpu__.
+ * Other compilers use __cpu or __cpu__ so we test for both in those cases.
*/
-/*
- * Standard gcc asm format:
- *
+/*----------
+ * Standard gcc asm format (assuming "volatile slock_t *lock"):
+
__asm__ __volatile__(
- " command \n"
- " command \n"
- " command \n"
-: "=r"(_res) return value, in register
-: "r"(lock) argument, 'lock pointer', in register
-: "r0"); inline code uses this register
+ " instruction \n"
+ " instruction \n"
+ " instruction \n"
+: "=r"(_res), "+m"(*lock) // return register, in/out lock value
+: "r"(lock) // lock pointer, in input register
+: "memory", "cc"); // show clobbered registers here
+
+ * The output-operands list (after first colon) should always include
+ * "+m"(*lock), whether or not the asm code actually refers to this
+ * operand directly. This ensures that gcc believes the value in the
+ * lock variable is used and set by the asm code. Also, the clobbers
+ * list (after third colon) should always include "memory"; this prevents
+ * gcc from thinking it can cache the values of shared-memory fields
+ * across the asm code. Add "cc" if your asm code changes the condition
+ * code register, and also list any temp registers the code uses.
+ *----------
*/
-#if defined(__i386__)
+#ifdef __i386__ /* 32-bit i386 */
+#define HAS_TEST_AND_SET
+
+typedef unsigned char slock_t;
+
#define TAS(lock) tas(lock)
static __inline__ int
{
register slock_t _res = 1;
+ /*
+ * Use a non-locking test before asserting the bus lock. Note that the
+ * extra test appears to be a small loss on some x86 platforms and a small
+ * win on others; it's by no means clear that we should keep it.
+ *
+ * When this was last tested, we didn't have separate TAS() and TAS_SPIN()
+ * macros. Nowadays it probably would be better to do a non-locking test
+ * in TAS_SPIN() but not in TAS(), like on x86_64, but no-one's done the
+ * testing to verify that. Without some empirical evidence, better to
+ * leave it alone.
+ */
__asm__ __volatile__(
+ " cmpb $0,%1 \n"
+ " jne 1f \n"
" lock \n"
" xchgb %0,%1 \n"
-: "=q"(_res), "=m"(*lock)
-: "0"(_res));
+ "1: \n"
+: "+q"(_res), "+m"(*lock)
+:
+: "memory", "cc");
return (int) _res;
}
+#define SPIN_DELAY() spin_delay()
+
+static __inline__ void
+spin_delay(void)
+{
+ /*
+ * This sequence is equivalent to the PAUSE instruction ("rep" is
+ * ignored by old IA32 processors if the following instruction is
+ * not a string operation); the IA-32 Architecture Software
+ * Developer's Manual, Vol. 3, Section 7.7.2 describes why using
+ * PAUSE in the inner loop of a spin lock is necessary for good
+ * performance:
+ *
+ * The PAUSE instruction improves the performance of IA-32
+ * processors supporting Hyper-Threading Technology when
+ * executing spin-wait loops and other routines where one
+ * thread is accessing a shared lock or semaphore in a tight
+ * polling loop. When executing a spin-wait loop, the
+ * processor can suffer a severe performance penalty when
+ * exiting the loop because it detects a possible memory order
+ * violation and flushes the core processor's pipeline. The
+ * PAUSE instruction provides a hint to the processor that the
+ * code sequence is a spin-wait loop. The processor uses this
+ * hint to avoid the memory order violation and prevent the
+ * pipeline flush. In addition, the PAUSE instruction
+ * de-pipelines the spin-wait loop to prevent it from
+ * consuming execution resources excessively.
+ */
+ __asm__ __volatile__(
+ " rep; nop \n");
+}
+
#endif /* __i386__ */
-#ifdef __ia64__
+#ifdef __x86_64__ /* AMD Opteron, Intel EM64T */
+#define HAS_TEST_AND_SET
+
+typedef unsigned char slock_t;
+
+#define TAS(lock) tas(lock)
+
+/*
+ * On Intel EM64T, it's a win to use a non-locking test before the xchg proper,
+ * but only when spinning.
+ *
+ * See also Implementing Scalable Atomic Locks for Multi-Core Intel(tm) EM64T
+ * and IA32, by Michael Chynoweth and Mary R. Lee. As of this writing, it is
+ * available at:
+ * http://software.intel.com/en-us/articles/implementing-scalable-atomic-locks-for-multi-core-intel-em64t-and-ia32-architectures
+ */
+#define TAS_SPIN(lock) (*(lock) ? 1 : TAS(lock))
+
+static __inline__ int
+tas(volatile slock_t *lock)
+{
+ register slock_t _res = 1;
+
+ __asm__ __volatile__(
+ " lock \n"
+ " xchgb %0,%1 \n"
+: "+q"(_res), "+m"(*lock)
+:
+: "memory", "cc");
+ return (int) _res;
+}
+
+#define SPIN_DELAY() spin_delay()
+
+static __inline__ void
+spin_delay(void)
+{
+ /*
+ * Adding a PAUSE in the spin delay loop is demonstrably a no-op on
+ * Opteron, but it may be of some use on EM64T, so we keep it.
+ */
+ __asm__ __volatile__(
+ " rep; nop \n");
+}
+
+#endif /* __x86_64__ */
+
+
+#if defined(__ia64__) || defined(__ia64)
+/*
+ * Intel Itanium, gcc or Intel's compiler.
+ *
+ * Itanium has weak memory ordering, but we rely on the compiler to enforce
+ * strict ordering of accesses to volatile data. In particular, while the
+ * xchg instruction implicitly acts as a memory barrier with 'acquire'
+ * semantics, we do not have an explicit memory fence instruction in the
+ * S_UNLOCK macro. We use a regular assignment to clear the spinlock, and
+ * trust that the compiler marks the generated store instruction with the
+ * ".rel" opcode.
+ *
+ * Testing shows that assumption to hold on gcc, although I could not find
+ * any explicit statement on that in the gcc manual. In Intel's compiler,
+ * the -m[no-]serialize-volatile option controls that, and testing shows that
+ * it is enabled by default.
+ */
+#define HAS_TEST_AND_SET
+
+typedef unsigned int slock_t;
+
#define TAS(lock) tas(lock)
+/* On IA64, it's a win to use a non-locking test before the xchg proper */
+#define TAS_SPIN(lock) (*(lock) ? 1 : TAS(lock))
+
+#ifndef __INTEL_COMPILER
+
static __inline__ int
tas(volatile slock_t *lock)
{
__asm__ __volatile__(
" xchg4 %0=%1,%2 \n"
-: "=r"(ret), "=m"(*lock)
-: "r"(1), "1"(*lock)
+: "=r"(ret), "+m"(*lock)
+: "r"(1)
: "memory");
-
return (int) ret;
}
-#endif /* __ia64__ */
+#else /* __INTEL_COMPILER */
+
+static __inline__ int
+tas(volatile slock_t *lock)
+{
+ int ret;
+
+ ret = _InterlockedExchange(lock,1); /* this is a xchg asm macro */
+
+ return ret;
+}
+
+#endif /* __INTEL_COMPILER */
+#endif /* __ia64__ || __ia64 */
-#if defined(__arm__) || defined(__arm__)
+/*
+ * On ARM, we use __sync_lock_test_and_set(int *, int) if available, and if
+ * not fall back on the SWPB instruction. SWPB does not work on ARMv6 or
+ * later, so the compiler builtin is preferred if available. Note also that
+ * the int-width variant of the builtin works on more chips than other widths.
+ */
+#if defined(__arm__) || defined(__arm)
+#define HAS_TEST_AND_SET
+
#define TAS(lock) tas(lock)
+#ifdef HAVE_GCC_INT_ATOMICS
+
+typedef int slock_t;
+
+static __inline__ int
+tas(volatile slock_t *lock)
+{
+ return __sync_lock_test_and_set(lock, 1);
+}
+
+#define S_UNLOCK(lock) __sync_lock_release(lock)
+
+#else /* !HAVE_GCC_INT_ATOMICS */
+
+typedef unsigned char slock_t;
+
static __inline__ int
tas(volatile slock_t *lock)
{
register slock_t _res = 1;
__asm__ __volatile__(
- " swpb %0, %0, [%3] \n"
-: "=r"(_res), "=m"(*lock)
-: "0"(_res), "r"(lock));
+ " swpb %0, %0, [%2] \n"
+: "+r"(_res), "+m"(*lock)
+: "r"(lock)
+: "memory");
return (int) _res;
}
+#endif /* HAVE_GCC_INT_ATOMICS */
#endif /* __arm__ */
-#if defined(__s390__) && !defined(__s390x__)
/*
- * S/390 Linux
+ * On ARM64, we use __sync_lock_test_and_set(int *, int) if available.
*/
-#define TAS(lock) tas(lock)
+#if defined(__aarch64__) || defined(__aarch64)
+#ifdef HAVE_GCC_INT_ATOMICS
+#define HAS_TEST_AND_SET
+
+#define TAS(lock) tas(lock)
+
+typedef int slock_t;
static __inline__ int
tas(volatile slock_t *lock)
{
- int _res;
-
- __asm__ __volatile__(
- " la 1,1 \n"
- " l 2,%2 \n"
- " slr 0,0 \n"
- " cs 0,1,0(2) \n"
- " lr %1,0 \n"
-: "=m"(lock), "=d"(_res)
-: "m"(lock)
-: "0", "1", "2");
-
- return (_res);
+ return __sync_lock_test_and_set(lock, 1);
}
-#endif /* __s390__ */
+#define S_UNLOCK(lock) __sync_lock_release(lock)
+
+#endif /* HAVE_GCC_INT_ATOMICS */
+#endif /* __aarch64__ */
+
+
+/* S/390 and S/390x Linux (32- and 64-bit zSeries) */
+#if defined(__s390__) || defined(__s390x__)
+#define HAS_TEST_AND_SET
+
+typedef unsigned int slock_t;
-#if defined(__s390x__)
-/*
- * S/390x Linux (64-bit zSeries)
- */
#define TAS(lock) tas(lock)
static __inline__ int
tas(volatile slock_t *lock)
{
- int _res;
+ int _res = 0;
__asm__ __volatile__(
- " la 1,1 \n"
- " lg 2,%2 \n"
- " slr 0,0 \n"
- " cs 0,1,0(2) \n"
- " lr %1,0 \n"
-: "=m"(lock), "=d"(_res)
-: "m"(lock)
-: "0", "1", "2");
-
- return (_res);
+ " cs %0,%3,0(%2) \n"
+: "+d"(_res), "+m"(*lock)
+: "a"(lock), "d"(1)
+: "memory", "cc");
+ return _res;
}
-#endif /* __s390x__ */
+#endif /* __s390__ || __s390x__ */
+
+
+#if defined(__sparc__) /* Sparc */
+#define HAS_TEST_AND_SET
+typedef unsigned char slock_t;
-#if defined(__sparc__)
#define TAS(lock) tas(lock)
static __inline__ int
tas(volatile slock_t *lock)
{
- register slock_t _res = 1;
+ register slock_t _res;
+ /*
+ * See comment in /pg/backend/port/tas/solaris_sparc.s for why this
+ * uses "ldstub", and that file uses "cas". gcc currently generates
+ * sparcv7-targeted binaries, so "cas" use isn't possible.
+ */
__asm__ __volatile__(
" ldstub [%2], %0 \n"
-: "=r"(_res), "=m"(*lock)
-: "r"(lock));
+: "=r"(_res), "+m"(*lock)
+: "r"(lock)
+: "memory");
return (int) _res;
}
#endif /* __sparc__ */
-#if defined(__powerpc__) || defined(__powerpc64__)
+
+/* PowerPC */
+#if defined(__ppc__) || defined(__powerpc__) || defined(__ppc64__) || defined(__powerpc64__)
+#define HAS_TEST_AND_SET
+
+typedef unsigned int slock_t;
+
+#define TAS(lock) tas(lock)
+
+/* On PPC, it's a win to use a non-locking test before the lwarx */
+#define TAS_SPIN(lock) (*(lock) ? 1 : TAS(lock))
+
+/*
+ * NOTE: per the Enhanced PowerPC Architecture manual, v1.0 dated 7-May-2002,
+ * an isync is a sufficient synchronization barrier after a lwarx/stwcx loop.
+ * On newer machines, we can use lwsync instead for better performance.
+ */
static __inline__ int
tas(volatile slock_t *lock)
{
int _res;
__asm__ __volatile__(
+#ifdef USE_PPC_LWARX_MUTEX_HINT
+" lwarx %0,0,%3,1 \n"
+#else
" lwarx %0,0,%3 \n"
+#endif
" cmpwi %0,0 \n"
" bne 1f \n"
" addi %0,%0,1 \n"
" stwcx. %0,0,%3 \n"
" beq 2f \n"
-"1: li %2,1 \n"
+"1: li %1,1 \n"
" b 3f \n"
"2: \n"
+#ifdef USE_PPC_LWSYNC
+" lwsync \n"
+#else
" isync \n"
-" li %2,0 \n"
+#endif
+" li %1,0 \n"
"3: \n"
-: "=&r" (_t), "=m" (lock), "=r" (_res)
-: "r" (lock)
-: "cc", "memory"
- );
+: "=&r"(_t), "=r"(_res), "+m"(*lock)
+: "r"(lock)
+: "memory", "cc");
return _res;
}
-#endif
+
+/*
+ * PowerPC S_UNLOCK is almost standard but requires a "sync" instruction.
+ * On newer machines, we can use lwsync instead for better performance.
+ */
+#ifdef USE_PPC_LWSYNC
+#define S_UNLOCK(lock) \
+do \
+{ \
+ __asm__ __volatile__ (" lwsync \n"); \
+ *((volatile slock_t *) (lock)) = 0; \
+} while (0)
+#else
+#define S_UNLOCK(lock) \
+do \
+{ \
+ __asm__ __volatile__ (" sync \n"); \
+ *((volatile slock_t *) (lock)) = 0; \
+} while (0)
+#endif /* USE_PPC_LWSYNC */
+
+#endif /* powerpc */
-#if defined(__mc68000__) && defined(__linux__)
+/* Linux Motorola 68k */
+#if (defined(__mc68000__) || defined(__m68k__)) && defined(__linux__)
+#define HAS_TEST_AND_SET
+
+typedef unsigned char slock_t;
+
#define TAS(lock) tas(lock)
static __inline__ int
" clrl %0 \n"
" tas %1 \n"
" sne %0 \n"
-: "=d"(rv), "=m"(*lock)
-: "1"(*lock)
-: "cc");
-
+: "=d"(rv), "+m"(*lock)
+:
+: "memory", "cc");
return rv;
}
-#endif /* defined(__mc68000__) && defined(__linux__) */
-
-
-#if defined(__ppc__) || defined(__powerpc__)
-/*
- * We currently use out-of-line assembler for TAS on PowerPC; see s_lock.c.
- * S_UNLOCK is almost standard but requires a "sync" instruction.
- */
-#define S_UNLOCK(lock) \
-do \
-{\
- __asm__ __volatile__ (" sync \n"); \
- *((volatile slock_t *) (lock)) = 0; \
-} while (0)
-
-#endif /* defined(__ppc__) || defined(__powerpc__) */
+#endif /* (__mc68000__ || __m68k__) && __linux__ */
-#if defined(NEED_VAX_TAS_ASM)
/*
* VAXen -- even multiprocessor ones
* (thanks to Tom Ivar Helbekkmo)
*/
+#if defined(__vax__)
+#define HAS_TEST_AND_SET
+
+typedef unsigned char slock_t;
+
#define TAS(lock) tas(lock)
static __inline__ int
register int _res;
__asm__ __volatile__(
- " movl $1, r0 \n"
- " bbssi $0, (%1), 1f \n"
- " clrl r0 \n"
- "1: movl r0, %0 \n"
-: "=r"(_res)
+ " movl $1, %0 \n"
+ " bbssi $0, (%2), 1f \n"
+ " clrl %0 \n"
+ "1: \n"
+: "=&r"(_res), "+m"(*lock)
: "r"(lock)
-: "r0");
+: "memory");
return _res;
}
-#endif /* NEED_VAX_TAS_ASM */
+#endif /* __vax__ */
+
+#if defined(__mips__) && !defined(__sgi) /* non-SGI MIPS */
+/* Note: on SGI we use the OS' mutex ABI, see below */
+/* Note: R10000 processors require a separate SYNC */
+#define HAS_TEST_AND_SET
+
+typedef unsigned int slock_t;
-#if defined(NEED_NS32K_TAS_ASM)
#define TAS(lock) tas(lock)
static __inline__ int
tas(volatile slock_t *lock)
{
- register int _res;
+ register volatile slock_t *_l = lock;
+ register int _res;
+ register int _tmp;
+
+ __asm__ __volatile__(
+ " .set push \n"
+ " .set mips2 \n"
+ " .set noreorder \n"
+ " .set nomacro \n"
+ " ll %0, %2 \n"
+ " or %1, %0, 1 \n"
+ " sc %1, %2 \n"
+ " xori %1, 1 \n"
+ " or %0, %0, %1 \n"
+ " sync \n"
+ " .set pop "
+: "=&r" (_res), "=&r" (_tmp), "+R" (*_l)
+:
+: "memory");
+ return _res;
+}
+
+/* MIPS S_UNLOCK is almost standard but requires a "sync" instruction */
+#define S_UNLOCK(lock) \
+do \
+{ \
+ __asm__ __volatile__( \
+ " .set push \n" \
+ " .set mips2 \n" \
+ " .set noreorder \n" \
+ " .set nomacro \n" \
+ " sync \n" \
+ " .set pop "); \
+ *((volatile slock_t *) (lock)) = 0; \
+} while (0)
+
+#endif /* __mips__ && !__sgi */
+
+
+#if defined(__m32r__) && defined(HAVE_SYS_TAS_H) /* Renesas' M32R */
+#define HAS_TEST_AND_SET
+
+#include <sys/tas.h>
+
+typedef int slock_t;
+
+#define TAS(lock) tas(lock)
+
+#endif /* __m32r__ */
+
+#if defined(__sh__) /* Renesas' SuperH */
+#define HAS_TEST_AND_SET
+
+typedef unsigned char slock_t;
+
+#define TAS(lock) tas(lock)
+
+static __inline__ int
+tas(volatile slock_t *lock)
+{
+ register int _res;
+
+ /*
+ * This asm is coded as if %0 could be any register, but actually SuperH
+ * restricts the target of xor-immediate to be R0. That's handled by
+ * the "z" constraint on _res.
+ */
__asm__ __volatile__(
- " sbitb 0, %0 \n"
- " sfsd %1 \n"
-: "=m"(*lock), "=r"(_res));
+ " tas.b @%2 \n"
+ " movt %0 \n"
+ " xor #1,%0 \n"
+: "=z"(_res), "+m"(*lock)
+: "r"(lock)
+: "memory", "t");
return _res;
}
-#endif /* NEED_NS32K_TAS_ASM */
+#endif /* __sh__ */
+
+
+/* These live in s_lock.c, but only for gcc */
+
+
+#if defined(__m68k__) && !defined(__linux__) /* non-Linux Motorola 68k */
+#define HAS_TEST_AND_SET
+
+typedef unsigned char slock_t;
+#endif
+
+#endif /* defined(__GNUC__) || defined(__INTEL_COMPILER) */
-#else /* !__GNUC__ */
-/***************************************************************************
- * All non-gcc inlines
+/*
+ * ---------------------------------------------------------------------
+ * Platforms that use non-gcc inline assembly:
+ * ---------------------------------------------------------------------
*/
-#if defined(NEED_I386_TAS_ASM) && defined(USE_UNIVEL_CC)
+#if !defined(HAS_TEST_AND_SET) /* We didn't trigger above, let's try here */
+
+
+#if defined(USE_UNIVEL_CC) /* Unixware compiler */
+#define HAS_TEST_AND_SET
+
+typedef unsigned char slock_t;
+
#define TAS(lock) tas(lock)
asm int
popl %ebx
}
-#endif /* defined(NEED_I386_TAS_ASM) && defined(USE_UNIVEL_CC) */
-
-#endif /* defined(__GNUC__) */
+#endif /* defined(USE_UNIVEL_CC) */
-
-/*************************************************************************
- * These are the platforms that do not use inline assembler (and hence
- * have common code for gcc and non-gcc compilers, if both are available).
+#if defined(__hppa) || defined(__hppa__) /* HP PA-RISC, GCC and HP compilers */
+/*
+ * HP's PA-RISC
+ *
+ * See src/backend/port/hpux/tas.c.template for details about LDCWX. Because
+ * LDCWX requires a 16-byte-aligned address, we declare slock_t as a 16-byte
+ * struct. The active word in the struct is whichever has the aligned address;
+ * the other three words just sit at -1.
+ *
+ * When using gcc, we can inline the required assembly code.
*/
+#define HAS_TEST_AND_SET
+typedef struct
+{
+ int sema[4];
+} slock_t;
-#if defined(__alpha)
+#define TAS_ACTIVE_WORD(lock) ((volatile int *) (((uintptr_t) (lock) + 15) & ~15))
-/*
- * Correct multi-processor locking methods are explained in section 5.5.3
- * of the Alpha AXP Architecture Handbook, which at this writing can be
- * found at ftp://ftp.netbsd.org/pub/NetBSD/misc/dec-docs/index.html.
- * For gcc we implement the handbook's code directly with inline assembler.
- */
#if defined(__GNUC__)
-#define TAS(lock) tas(lock)
-#define S_UNLOCK(lock) \
-do \
-{\
- __asm__ __volatile__ (" mb \n"); \
- *((volatile slock_t *) (lock)) = 0; \
-} while (0)
-
static __inline__ int
tas(volatile slock_t *lock)
{
- register slock_t _res;
+ volatile int *lockword = TAS_ACTIVE_WORD(lock);
+ register int lockval;
- __asm__ __volatile__(
- " ldq $0, %0 \n"
- " bne $0, 2f \n"
- " ldq_l %1, %0 \n"
- " bne %1, 2f \n"
- " mov 1, $0 \n"
- " stq_c $0, %0 \n"
- " beq $0, 2f \n"
- " mb \n"
- " br 3f \n"
- "2: mov 1, %1 \n"
- "3: \n"
-: "=m"(*lock), "=r"(_res)
-:
-: "0");
-
- return (int) _res;
+ __asm__ __volatile__(
+ " ldcwx 0(0,%2),%0 \n"
+: "=r"(lockval), "+m"(*lockword)
+: "r"(lockword)
+: "memory");
+ return (lockval == 0);
}
-#else /* !defined(__GNUC__) */
-
-/*
- * The Tru64 compiler doesn't support gcc-style inline asm, but it does
- * have some builtin functions that accomplish much the same results.
- * For simplicity, slock_t is defined as long (ie, quadword) on Alpha
- * regardless of the compiler in use. LOCK_LONG and UNLOCK_LONG only
- * operate on an int (ie, longword), but that's OK as long as we define
- * S_INIT_LOCK to zero out the whole quadword.
- */
-
-#include <alpha/builtins.h>
-
-#define S_INIT_LOCK(lock) (*(lock) = 0)
-#define TAS(lock) (__LOCK_LONG_RETRY((lock), 1) == 0)
-#define S_UNLOCK(lock) __UNLOCK_LONG(lock)
-
-#endif /* defined(__GNUC__) */
+#endif /* __GNUC__ */
-#endif /* __alpha */
+#define S_UNLOCK(lock) (*TAS_ACTIVE_WORD(lock) = -1)
-
-#if defined(__hpux)
-/*
- * HP-UX (PA-RISC)
- *
- * Note that slock_t on PA-RISC is a structure instead of char
- * (see include/port/hpux.h).
- *
- * a "set" slock_t has a single word cleared. a "clear" slock_t has
- * all words set to non-zero. tas() is in tas.s
- */
-
-#define S_UNLOCK(lock) \
+#define S_INIT_LOCK(lock) \
do { \
- volatile slock_t *lock_ = (volatile slock_t *) (lock); \
+ volatile slock_t *lock_ = (lock); \
lock_->sema[0] = -1; \
lock_->sema[1] = -1; \
lock_->sema[2] = -1; \
lock_->sema[3] = -1; \
} while (0)
-#define S_LOCK_FREE(lock) ( *(int *) (((long) (lock) + 15) & ~15) != 0)
-
-#endif /* __hpux */
-
-#if defined(__QNX__) && defined(__WATCOMC__)
-/*
- * QNX 4 using WATCOM C
- */
-#define TAS(lock) wc_tas(lock)
-extern slock_t wc_tas(volatile slock_t *lock);
-#pragma aux wc_tas =\
- " mov al,1 " \
- " lock xchg al,[esi]" \
- parm [esi] \
- value [al];
+#define S_LOCK_FREE(lock) (*TAS_ACTIVE_WORD(lock) != 0)
-#endif /* __QNX__ and __WATCOMC__*/
+#endif /* __hppa || __hppa__ */
-#if defined(__sgi)
+#if defined(__hpux) && defined(__ia64) && !defined(__GNUC__)
/*
- * SGI IRIX 5
- * slock_t is defined as a unsigned long. We use the standard SGI
- * mutex API.
+ * HP-UX on Itanium, non-gcc compiler
*
- * The following comment is left for historical reasons, but is probably
- * not a good idea since the mutex ABI is supported.
- *
- * This stuff may be supplemented in the future with Masato Kataoka's MIPS-II
- * assembly from his NECEWS SVR4 port, but we probably ought to retain this
- * for the R3000 chips out there.
- */
-#include "mutex.h"
-#define TAS(lock) (test_and_set(lock,1))
-#define S_UNLOCK(lock) (test_then_and(lock,0))
-#define S_INIT_LOCK(lock) (test_then_and(lock,0))
-#define S_LOCK_FREE(lock) (test_then_add(lock,0) == 0)
-#endif /* __sgi */
-
-#if defined(sinix)
-/*
- * SINIX / Reliant UNIX
- * slock_t is defined as a struct abilock_t, which has a single unsigned long
- * member. (Basically same as SGI)
+ * We assume that the compiler enforces strict ordering of loads/stores on
+ * volatile data (see comments on the gcc-version earlier in this file).
+ * Note that this assumption does *not* hold if you use the
+ * +Ovolatile=__unordered option on the HP-UX compiler, so don't do that.
*
+ * See also Implementing Spinlocks on the Intel Itanium Architecture and
+ * PA-RISC, by Tor Ekqvist and David Graves, for more information. As of
+ * this writing, version 1.0 of the manual is available at:
+ * http://h21007.www2.hp.com/portal/download/files/unprot/itanium/spinlocks.pdf
*/
-#define TAS(lock) (!acquire_lock(lock))
-#define S_UNLOCK(lock) release_lock(lock)
-#define S_INIT_LOCK(lock) init_lock(lock)
-#define S_LOCK_FREE(lock) (stat_lock(lock) == UNLOCKED)
-#endif /* sinix */
+#define HAS_TEST_AND_SET
+
+typedef unsigned int slock_t;
+#include <ia64/sys/inline.h>
+#define TAS(lock) _Asm_xchg(_SZ_W, lock, 1, _LDHINT_NONE)
+/* On IA64, it's a win to use a non-locking test before the xchg proper */
+#define TAS_SPIN(lock) (*(lock) ? 1 : TAS(lock))
-#if defined(_AIX)
+#endif /* HPUX on IA64, non gcc */
+
+#if defined(_AIX) /* AIX */
/*
* AIX (POWER)
- *
- * Note that slock_t on POWER/POWER2/PowerPC is int instead of char
*/
-#define TAS(lock) _check_lock(lock, 0, 1)
-#define S_UNLOCK(lock) _clear_lock(lock, 0)
+#define HAS_TEST_AND_SET
+
+#include <sys/atomic_op.h>
+
+typedef int slock_t;
+
+#define TAS(lock) _check_lock((slock_t *) (lock), 0, 1)
+#define S_UNLOCK(lock) _clear_lock((slock_t *) (lock), 0)
#endif /* _AIX */
-#if defined (nextstep)
-/*
- * NEXTSTEP (mach)
- * slock_t is defined as a struct mutex.
+/* These are in s_lock.c */
+
+#if defined(__SUNPRO_C) && (defined(__i386) || defined(__x86_64__) || defined(__sparc__) || defined(__sparc))
+#define HAS_TEST_AND_SET
+
+#if defined(__i386) || defined(__x86_64__) || defined(__sparcv9) || defined(__sparcv8plus)
+typedef unsigned int slock_t;
+#else
+typedef unsigned char slock_t;
+#endif
+
+extern slock_t pg_atomic_cas(volatile slock_t *lock, slock_t with,
+ slock_t cmp);
+
+#define TAS(a) (pg_atomic_cas((a), 1, 0) != 0)
+#endif
+
+
+#ifdef WIN32_ONLY_COMPILER
+typedef LONG slock_t;
+
+#define HAS_TEST_AND_SET
+#define TAS(lock) (InterlockedCompareExchange(lock, 1, 0))
+
+#define SPIN_DELAY() spin_delay()
+
+/* If using Visual C++ on Win64, inline assembly is unavailable.
+ * Use a _mm_pause instrinsic instead of rep nop.
*/
+#if defined(_WIN64)
+static __forceinline void
+spin_delay(void)
+{
+ _mm_pause();
+}
+#else
+static __forceinline void
+spin_delay(void)
+{
+ /* See comment for gcc code. Same code, MASM syntax */
+ __asm rep nop;
+}
+#endif
+
+#endif
+
+
+#endif /* !defined(HAS_TEST_AND_SET) */
-#define S_LOCK(lock) mutex_lock(lock)
-#define S_UNLOCK(lock) mutex_unlock(lock)
-#define S_INIT_LOCK(lock) mutex_init(lock)
-/* For Mach, we have to delve inside the entrails of `struct mutex'. Ick! */
-#define S_LOCK_FREE(alock) ((alock)->lock == 0)
-#endif /* nextstep */
+
+/* Blow up if we didn't have any way to do spinlocks */
+#ifndef HAS_TEST_AND_SET
+#error PostgreSQL does not have native spinlock support on this platform. To continue the compilation, rerun configure using --disable-spinlocks. However, performance will be poor. Please report this to pgsql-bugs@postgresql.org.
+#endif
+#else /* !HAVE_SPINLOCKS */
-#else /* !HAS_TEST_AND_SET */
/*
* Fake spinlock implementation using semaphores --- slow and prone
* to fall foul of kernel limits on number of semaphores, so don't use this
* unless you must! The subroutines appear in spin.c.
*/
-typedef PGSemaphoreData slock_t;
+typedef int slock_t;
extern bool s_lock_free_sema(volatile slock_t *lock);
extern void s_unlock_sema(volatile slock_t *lock);
#define S_INIT_LOCK(lock) s_init_lock_sema(lock)
#define TAS(lock) tas_sema(lock)
-#endif /* HAS_TEST_AND_SET */
+#endif /* HAVE_SPINLOCKS */
/*
#if !defined(S_LOCK)
#define S_LOCK(lock) \
- do { \
- if (TAS(lock)) \
- s_lock((lock), __FILE__, __LINE__); \
- } while (0)
+ (TAS(lock) ? s_lock((lock), __FILE__, __LINE__) : 0)
#endif /* S_LOCK */
#if !defined(S_LOCK_FREE)
#define S_INIT_LOCK(lock) S_UNLOCK(lock)
#endif /* S_INIT_LOCK */
+#if !defined(SPIN_DELAY)
+#define SPIN_DELAY() ((void) 0)
+#endif /* SPIN_DELAY */
+
#if !defined(TAS)
extern int tas(volatile slock_t *lock); /* in port/.../tas.s, or
* s_lock.c */
#define TAS(lock) tas(lock)
#endif /* TAS */
+#if !defined(TAS_SPIN)
+#define TAS_SPIN(lock) TAS(lock)
+#endif /* TAS_SPIN */
+
/*
* Platform-independent out-of-line support routines
*/
-extern void s_lock(volatile slock_t *lock, const char *file, int line);
+extern int s_lock(volatile slock_t *lock, const char *file, int line);
+
+/* Support for dynamic adjustment of spins_per_delay */
+#define DEFAULT_SPINS_PER_DELAY 100
+
+extern void set_spins_per_delay(int shared_spins_per_delay);
+extern int update_spins_per_delay(int shared_spins_per_delay);
#endif /* S_LOCK_H */