seqlock.h File Reference

Reader/writer consistent mechanism without starving writers. More...

Data Structures
struct	SeqLock_s
struct	seqcount
Defines
#define	smp_rmb()   __asm__ __volatile__( "lock; addl $0,0(%%esp)" ::: "memory" )
#define	smp_wmb()   __asm__ __volatile__( "" : : : "memory" )
#define	SEQ_LOCK(var, name)   SeqLock_s var = { 0, INIT_SPIN_LOCK( name ) }
#define	INIT_SEQ_LOCK(name)   { 0, INIT_SPIN_LOCK( name ) }
#define	SEQCNT_ZERO   { 0 }
#define	seqcount_init(x)   do { *(x) = (seqcount_t) SEQCNT_ZERO; } while (0)
#define	read_seqbegin_cli(lock, flags)   ({ flags = cli(); read_seqbegin(lock); })
#define	read_seqretry_restore(lock, iv, flags)
Typedefs
typedef seqcount	seqcount_t

---

Detailed Description

Reader/writer consistent mechanism without starving writers.

This type of lock for data where the reader wants a consitent set of information and is willing to retry if the information changes. Readers never block but they may have to retry if a writer is in progress. Writers do not wait for readers.

This is not as cache friendly as brlock. Also, this will not work for data that contains pointers, because any writer could invalidate a pointer that a reader was following.

Expected reader usage: do { seq = read_seqbegin(&foo); ... } while (read_seqretry(&foo, seq));

On non-SMP the spin locks disappear but the writer still needs to increment the sequence variables because an interrupt routine could change the state of the data.

Based on x86_64 vsyscall gettimeofday by Keith Owens and Andrea Arcangeli

---

Define Documentation

#define read_seqretry_restore	(	lock,
		iv,
		flags		)

Value:

({                                                              \
                int ret = read_seqretry(lock, iv);                      \
                put_cpu_flags(flags);                                   \
                ret;                                                    \
        })

---