[sheepdog] [PATCH 1/3] introduce more bit opreations into sheep
Liu Yuan
namei.unix at gmail.com
Wed May 16 09:52:53 CEST 2012
From: Liu Yuan <tailai.ly at taobao.com>
The code is excerpted from Linux kernel. We need some of thme by object cache.
Other opertions are expected be used by future dev.
Signed-off-by: Liu Yuan <tailai.ly at taobao.com>
---
include/bitops.h | 394 ++++++++++++++++++++++++++++++++++++++++++++++++++++--
1 files changed, 385 insertions(+), 9 deletions(-)
diff --git a/include/bitops.h b/include/bitops.h
index 0e0f402..3876cbd 100644
--- a/include/bitops.h
+++ b/include/bitops.h
@@ -5,10 +5,126 @@
unsigned long name[BITS_TO_LONGS(bits)]
#define BITS_PER_LONG (BITS_PER_BYTE * sizeof(long))
-#define __ffs(x) (x ? __builtin_ffsl(x) - 1 : 0)
-#define ffz(x) __ffs(~(x))
-
#define BITOP_WORD(nr) ((nr) / BITS_PER_LONG)
+#define LOCK_PREFIX "lock ; "
+
+/**
+ * __ffs - find first set bit in word
+ * @word: The word to search
+ *
+ * The first bit(least significant) is at position 0
+ * Undefined if no bit exists, so code should check against 0 first.
+ */
+static inline unsigned long __ffs(unsigned long word)
+{
+ asm("bsf %1,%0"
+ : "=r" (word)
+ : "rm" (word));
+ return word;
+}
+
+/**
+ * ffz - find first zero bit in word
+ * @word: The word to search
+ *
+ * The first zero bit(least significant) is at position 0
+ * Undefined if no zero exists, so code should check against ~0UL first.
+ */
+static inline unsigned long ffz(unsigned long word)
+{
+ asm("bsf %1,%0"
+ : "=r" (word)
+ : "r" (~word));
+ return word;
+}
+
+/*
+ * __fls: find last set bit in word
+ * @word: The word to search
+ *
+ * The last (most significant) bit is at position 31 or 63
+ * Undefined if no set bit exists, so code should check against 0 first.
+ */
+static inline unsigned long __fls(unsigned long word)
+{
+ asm("bsr %1,%0"
+ : "=r" (word)
+ : "rm" (word));
+ return word;
+}
+
+/**
+ * fls - find last set bit in word
+ * @x: the word to search
+ *
+ * This is defined in a similar way as the libc and compiler builtin
+ * ffs, but returns the position of the most significant set bit.
+ *
+ * fls(value) returns 0 if value is 0 or the position of the last
+ * set bit if value is nonzero. The last (most significant) bit is
+ * at position 32.
+ */
+static inline int fls(int x)
+{
+ int r;
+
+#ifdef __x86_64__
+ /*
+ * AMD64 says BSRL won't clobber the dest reg if x==0; Intel64 says the
+ * dest reg is undefined if x==0, but their CPU architect says its
+ * value is written to set it to the same as before, except that the
+ * top 32 bits will be cleared.
+ *
+ * We cannot do this on 32 bits because at the very least some
+ * 486 CPUs did not behave this way.
+ */
+ long tmp = -1;
+ asm("bsrl %1,%0"
+ : "=r" (r)
+ : "rm" (x), "0" (tmp));
+#else
+ asm("bsrl %1,%0\n\t"
+ "jnz 1f\n\t"
+ "movl $-1,%0\n"
+ "1:" : "=r" (r) : "rm" (x));
+#endif
+ return r + 1;
+}
+
+/**
+ * fls64 - find last set bit in a 64-bit word
+ * @x: the word to search
+ *
+ * This is defined in a similar way as the libc and compiler builtin
+ * ffsll, but returns the position of the most significant set bit.
+ *
+ * fls64(value) returns 0 if value is 0 or the position of the last
+ * set bit if value is nonzero. The last (most significant) bit is
+ * at position 64.
+ */
+#ifdef __x86_64__
+static __always_inline int fls64(uint64_t x)
+{
+ long bitpos = -1;
+ /*
+ * AMD64 says BSRQ won't clobber the dest reg if x==0; Intel64 says the
+ * dest reg is undefined if x==0, but their CPU architect says its
+ * value is written to set it to the same as before.
+ */
+ asm("bsrq %1,%0"
+ : "+r" (bitpos)
+ : "rm" (x));
+ return bitpos + 1;
+}
+#else
+static __always_inline int fls64(uint64_t x)
+{
+ uint32_t h = x >> 32;
+ if (h)
+ return fls(h) + 32;
+ return fls(x);
+}
+#endif
static inline unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
unsigned long offset)
@@ -88,18 +204,278 @@ found_middle:
return result + __ffs(tmp);
}
-static inline void set_bit(int nr, unsigned long *addr)
+static inline unsigned long find_last_bit(const unsigned long *addr,
+ unsigned long size)
+{
+ unsigned long words;
+ unsigned long tmp;
+
+ /* Start at final word. */
+ words = size / BITS_PER_LONG;
+
+ /* Partial final word? */
+ if (size & (BITS_PER_LONG-1)) {
+ tmp = (addr[words] & (~0UL >> (BITS_PER_LONG
+ - (size & (BITS_PER_LONG-1)))));
+ if (tmp)
+ goto found;
+ }
+
+ while (words) {
+ tmp = addr[--words];
+ if (tmp) {
+found:
+ return words * BITS_PER_LONG + __fls(tmp);
+ }
+ }
+
+ /* Not found */
+ return size;
+}
+
+/*
+ * These have to be done with inline assembly: that way the bit-setting
+ * is guaranteed to be atomic. All bit operations return 0 if the bit
+ * was cleared before the operation and != 0 if it was not.
+ *
+ * bit 0 is the LSB of addr; bit 32 is the LSB of (addr+1).
+ */
+
+#if __GNUC__ < 4 || (__GNUC__ == 4 && __GNUC_MINOR__ < 1)
+/* Technically wrong, but this avoids compilation errors on some gcc
+ versions. */
+#define BITOP_ADDR(x) "=m" (*(volatile long *) (x))
+#else
+#define BITOP_ADDR(x) "+m" (*(volatile long *) (x))
+#endif
+
+#define ADDR BITOP_ADDR(addr)
+
+/*
+ * We do the locked ops that don't return the old value as
+ * a mask operation on a byte.
+ */
+#define IS_IMMEDIATE(nr) (__builtin_constant_p(nr))
+#define CONST_MASK_ADDR(nr, addr) BITOP_ADDR((unsigned long *)(addr) \
+ + ((nr)>>3))
+#define CONST_MASK(nr) (1 << ((nr) & 7))
+
+/**
+ * set_bit - Atomically set a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * This function is atomic and may not be reordered. See __set_bit()
+ * if you do not require the atomic guarantees.
+ *
+ * Note: there are no guarantees that this function will not be reordered
+ * on non x86 architectures, so if you are writing portable code,
+ * make sure not to rely on its reordering guarantees.
+ *
+ * Note that @nr may be almost arbitrarily large; this function is not
+ * restricted to acting on a single-word quantity.
+ */
+static __always_inline void
+set_bit(unsigned int nr, volatile unsigned long *addr)
+{
+ if (IS_IMMEDIATE(nr)) {
+ asm volatile(LOCK_PREFIX "orb %1,%0"
+ : CONST_MASK_ADDR(nr, addr)
+ : "iq" ((uint8_t)CONST_MASK(nr))
+ : "memory");
+ } else {
+ asm volatile(LOCK_PREFIX "bts %1,%0"
+ : BITOP_ADDR(addr) : "Ir" (nr) : "memory");
+ }
+}
+
+/**
+ * __set_bit - Set a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * Unlike set_bit(), this function is non-atomic and may be reordered.
+ * If it's called on the same region of memory simultaneously, the effect
+ * may be that only one operation succeeds.
+ */
+static inline void __set_bit(int nr, volatile unsigned long *addr)
{
- addr[nr / BITS_PER_LONG] |= 1UL << (nr % BITS_PER_LONG);
+ asm volatile("bts %1,%0" : ADDR : "Ir" (nr) : "memory");
}
-static inline int test_bit(unsigned int nr, const unsigned long *addr)
+/**
+ * clear_bit - Clears a bit in memory
+ * @nr: Bit to clear
+ * @addr: Address to start counting from
+ *
+ * clear_bit() is atomic and may not be reordered. However, it does
+ * not contain a memory barrier, so if it is used for locking purposes,
+ * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
+ * in order to ensure changes are visible on other processors.
+ */
+static __always_inline void
+clear_bit(int nr, volatile unsigned long *addr)
+{
+ if (IS_IMMEDIATE(nr)) {
+ asm volatile(LOCK_PREFIX "andb %1,%0"
+ : CONST_MASK_ADDR(nr, addr)
+ : "iq" ((uint8_t)~CONST_MASK(nr)));
+ } else {
+ asm volatile(LOCK_PREFIX "btr %1,%0"
+ : BITOP_ADDR(addr)
+ : "Ir" (nr));
+ }
+}
+
+static inline void __clear_bit(int nr, volatile unsigned long *addr)
+{
+ asm volatile("btr %1,%0" : ADDR : "Ir" (nr));
+}
+
+static __always_inline int constant_test_bit(unsigned int nr, const volatile unsigned long *addr)
{
return ((1UL << (nr % BITS_PER_LONG)) &
- (((unsigned long *)addr)[nr / BITS_PER_LONG])) != 0;
+ (addr[nr / BITS_PER_LONG])) != 0;
+}
+
+static inline int variable_test_bit(int nr, volatile const unsigned long *addr)
+{
+ int oldbit;
+
+ asm volatile("bt %2,%1\n\t"
+ "sbb %0,%0"
+ : "=r" (oldbit)
+ : "m" (*(unsigned long *)addr), "Ir" (nr));
+
+ return oldbit;
}
-static inline void clear_bit(unsigned int nr, unsigned long *addr)
+#define test_bit(nr, addr) \
+ (__builtin_constant_p((nr)) \
+ ? constant_test_bit((nr), (addr)) \
+ : variable_test_bit((nr), (addr)))
+
+/**
+ * __change_bit - Toggle a bit in memory
+ * @nr: the bit to change
+ * @addr: the address to start counting from
+ *
+ * Unlike change_bit(), this function is non-atomic and may be reordered.
+ * If it's called on the same region of memory simultaneously, the effect
+ * may be that only one operation succeeds.
+ */
+static inline void __change_bit(int nr, volatile unsigned long *addr)
+{
+ asm volatile("btc %1,%0" : ADDR : "Ir" (nr));
+}
+
+/**
+ * change_bit - Toggle a bit in memory
+ * @nr: Bit to change
+ * @addr: Address to start counting from
+ *
+ * change_bit() is atomic and may not be reordered.
+ * Note that @nr may be almost arbitrarily large; this function is not
+ * restricted to acting on a single-word quantity.
+ */
+static inline void change_bit(int nr, volatile unsigned long *addr)
+{
+ if (IS_IMMEDIATE(nr)) {
+ asm volatile(LOCK_PREFIX "xorb %1,%0"
+ : CONST_MASK_ADDR(nr, addr)
+ : "iq" ((uint8_t)CONST_MASK(nr)));
+ } else {
+ asm volatile(LOCK_PREFIX "btc %1,%0"
+ : BITOP_ADDR(addr)
+ : "Ir" (nr));
+ }
+}
+
+/**
+ * test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is atomic and cannot be reordered.
+ * It also implies a memory barrier.
+ */
+static inline int test_and_set_bit(int nr, volatile unsigned long *addr)
{
- addr[nr / BITS_PER_LONG] &= ~(1UL << (nr % BITS_PER_LONG));
+ int oldbit;
+
+ asm volatile(LOCK_PREFIX "bts %2,%1\n\t"
+ "sbb %0,%0" : "=r" (oldbit), ADDR : "Ir" (nr) : "memory");
+
+ return oldbit;
+}
+
+/**
+ * test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ *
+ * This operation is atomic and cannot be reordered.
+ * It also implies a memory barrier.
+ */
+static inline int test_and_clear_bit(int nr, volatile unsigned long *addr)
+{
+ int oldbit;
+
+ asm volatile(LOCK_PREFIX "btr %2,%1\n\t"
+ "sbb %0,%0"
+ : "=r" (oldbit), ADDR : "Ir" (nr) : "memory");
+
+ return oldbit;
+}
+
+/**
+ * __test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail. You must protect multiple accesses with a lock.
+ */
+static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
+{
+ int oldbit;
+
+ asm volatile("btr %2,%1\n\t"
+ "sbb %0,%0"
+ : "=r" (oldbit), ADDR
+ : "Ir" (nr));
+ return oldbit;
+}
+
+/* WARNING: non atomic and it can be reordered! */
+static inline int __test_and_change_bit(int nr, volatile unsigned long *addr)
+{
+ int oldbit;
+
+ asm volatile("btc %2,%1\n\t"
+ "sbb %0,%0"
+ : "=r" (oldbit), ADDR
+ : "Ir" (nr) : "memory");
+
+ return oldbit;
+}
+
+/**
+ * test_and_change_bit - Change a bit and return its old value
+ * @nr: Bit to change
+ * @addr: Address to count from
+ *
+ * This operation is atomic and cannot be reordered.
+ * It also implies a memory barrier.
+ */
+static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
+{
+ int oldbit;
+
+ asm volatile(LOCK_PREFIX "btc %2,%1\n\t"
+ "sbb %0,%0"
+ : "=r" (oldbit), ADDR : "Ir" (nr) : "memory");
+
+ return oldbit;
}
--
1.7.8.2
More information about the sheepdog
mailing list