[RFC PATCH v2 09/12] asm-generic/bitops/atomic.h: Rewrite using atomic_fetch_*

From: Will Deacon
Date: Mon Feb 26 2018 - 10:07:33 EST


The atomic bitops can actually be implemented pretty efficiently using
the atomic_fetch_* ops, rather than explicit use of spinlocks.

Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Signed-off-by: Will Deacon <will.deacon@xxxxxxx>
---
include/asm-generic/bitops/atomic.h | 188 +++++++-----------------------------
1 file changed, 33 insertions(+), 155 deletions(-)

diff --git a/include/asm-generic/bitops/atomic.h b/include/asm-generic/bitops/atomic.h
index 04deffaf5f7d..bca92586c2f6 100644
--- a/include/asm-generic/bitops/atomic.h
+++ b/include/asm-generic/bitops/atomic.h
@@ -2,189 +2,67 @@
#ifndef _ASM_GENERIC_BITOPS_ATOMIC_H_
#define _ASM_GENERIC_BITOPS_ATOMIC_H_

-#include <asm/types.h>
-#include <linux/irqflags.h>
-
-#ifdef CONFIG_SMP
-#include <asm/spinlock.h>
-#include <asm/cache.h> /* we use L1_CACHE_BYTES */
-
-/* Use an array of spinlocks for our atomic_ts.
- * Hash function to index into a different SPINLOCK.
- * Since "a" is usually an address, use one spinlock per cacheline.
- */
-# define ATOMIC_HASH_SIZE 4
-# define ATOMIC_HASH(a) (&(__atomic_hash[ (((unsigned long) a)/L1_CACHE_BYTES) & (ATOMIC_HASH_SIZE-1) ]))
-
-extern arch_spinlock_t __atomic_hash[ATOMIC_HASH_SIZE] __lock_aligned;
-
-/* Can't use raw_spin_lock_irq because of #include problems, so
- * this is the substitute */
-#define _atomic_spin_lock_irqsave(l,f) do { \
- arch_spinlock_t *s = ATOMIC_HASH(l); \
- local_irq_save(f); \
- arch_spin_lock(s); \
-} while(0)
-
-#define _atomic_spin_unlock_irqrestore(l,f) do { \
- arch_spinlock_t *s = ATOMIC_HASH(l); \
- arch_spin_unlock(s); \
- local_irq_restore(f); \
-} while(0)
-
-
-#else
-# define _atomic_spin_lock_irqsave(l,f) do { local_irq_save(f); } while (0)
-# define _atomic_spin_unlock_irqrestore(l,f) do { local_irq_restore(f); } while (0)
-#endif
+#include <linux/atomic.h>
+#include <linux/compiler.h>
+#include <asm/barrier.h>

/*
- * NMI events can occur at any time, including when interrupts have been
- * disabled by *_irqsave(). So you can get NMI events occurring while a
- * *_bit function is holding a spin lock. If the NMI handler also wants
- * to do bit manipulation (and they do) then you can get a deadlock
- * between the original caller of *_bit() and the NMI handler.
- *
- * by Keith Owens
+ * Implementation of atomic bitops using atomic-fetch ops.
+ * See Documentation/atomic_bitops.txt for details.
*/

-/**
- * 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 inline void set_bit(int nr, volatile unsigned long *addr)
+static inline void set_bit(unsigned int nr, volatile unsigned long *p)
{
- unsigned long mask = BIT_MASK(nr);
- unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
- unsigned long flags;
-
- _atomic_spin_lock_irqsave(p, flags);
- *p |= mask;
- _atomic_spin_unlock_irqrestore(p, flags);
+ p += BIT_WORD(nr);
+ atomic_long_fetch_or_relaxed(BIT_MASK(nr), (atomic_long_t *)p);
}

-/**
- * 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_atomic() and/or smp_mb__after_atomic()
- * in order to ensure changes are visible on other processors.
- */
-static inline void clear_bit(int nr, volatile unsigned long *addr)
+static inline void clear_bit(unsigned int nr, volatile unsigned long *p)
{
- unsigned long mask = BIT_MASK(nr);
- unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
- unsigned long flags;
-
- _atomic_spin_lock_irqsave(p, flags);
- *p &= ~mask;
- _atomic_spin_unlock_irqrestore(p, flags);
+ p += BIT_WORD(nr);
+ atomic_long_fetch_andnot_relaxed(BIT_MASK(nr), (atomic_long_t *)p);
}

-/**
- * 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. It may be
- * reordered on other architectures than x86.
- * 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)
+static inline void change_bit(unsigned int nr, volatile unsigned long *p)
{
- unsigned long mask = BIT_MASK(nr);
- unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
- unsigned long flags;
-
- _atomic_spin_lock_irqsave(p, flags);
- *p ^= mask;
- _atomic_spin_unlock_irqrestore(p, flags);
+ p += BIT_WORD(nr);
+ atomic_long_fetch_xor_relaxed(BIT_MASK(nr), (atomic_long_t *)p);
}

-/**
- * 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 may be reordered on other architectures than x86.
- * It also implies a memory barrier.
- */
-static inline int test_and_set_bit(int nr, volatile unsigned long *addr)
+static inline int test_and_set_bit(unsigned int nr, volatile unsigned long *p)
{
+ long old;
unsigned long mask = BIT_MASK(nr);
- unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
- unsigned long old;
- unsigned long flags;

- _atomic_spin_lock_irqsave(p, flags);
- old = *p;
- *p = old | mask;
- _atomic_spin_unlock_irqrestore(p, flags);
+ p += BIT_WORD(nr);
+ if (READ_ONCE(*p) & mask)
+ return 1;

- return (old & mask) != 0;
+ old = atomic_long_fetch_or(mask, (atomic_long_t *)p);
+ return !!(old & mask);
}

-/**
- * 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 can be reorderdered on other architectures other than x86.
- * It also implies a memory barrier.
- */
-static inline int test_and_clear_bit(int nr, volatile unsigned long *addr)
+static inline int test_and_clear_bit(unsigned int nr, volatile unsigned long *p)
{
+ long old;
unsigned long mask = BIT_MASK(nr);
- unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
- unsigned long old;
- unsigned long flags;

- _atomic_spin_lock_irqsave(p, flags);
- old = *p;
- *p = old & ~mask;
- _atomic_spin_unlock_irqrestore(p, flags);
+ p += BIT_WORD(nr);
+ if (!(READ_ONCE(*p) & mask))
+ return 0;

- return (old & mask) != 0;
+ old = atomic_long_fetch_andnot(mask, (atomic_long_t *)p);
+ return !!(old & mask);
}

-/**
- * 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)
+static inline int test_and_change_bit(unsigned int nr, volatile unsigned long *p)
{
+ long old;
unsigned long mask = BIT_MASK(nr);
- unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
- unsigned long old;
- unsigned long flags;
-
- _atomic_spin_lock_irqsave(p, flags);
- old = *p;
- *p = old ^ mask;
- _atomic_spin_unlock_irqrestore(p, flags);

- return (old & mask) != 0;
+ p += BIT_WORD(nr);
+ old = atomic_long_fetch_xor(mask, (atomic_long_t *)p);
+ return !!(old & mask);
}

#endif /* _ASM_GENERIC_BITOPS_ATOMIC_H */
--
2.1.4