|SMR_CALL(9)||Kernel Developer's Manual||SMR_CALL(9)|
smr_entry *smr, void
(*fn)(void *), void
Readers access SMR-protected objects inside an SMR read-side
critical section using
SMR_PTR_GET(9). The section is
smr_read_enter(), and exited with
smr_read_leave(). These routines never block.
Sleeping is not allowed within SMR read-side critical section.
smr_init() initializes the entry
smr for use with
smr_call() schedules a callback to be
invoked after the entry smr cannot be referenced by a
reader in SMR read-side critical section. On invocation, the system calls
function fn with argument arg in
process context without any locks held. The implementation may delay the
call in order to reduce overall system overhead by amortization.
smr_barrier() sleeps until any SMR
read-side critical sections that are active on other CPUs at the time of
invocation have ended. Like with
processing of the request may be delayed.
smr_flush() is like
smr_barrier() but the system is forced to process
the request as soon as possible. The use of this function is discouraged
because of the heavy impact on system performance.
The SMR implementation does not limit the number of deferred
calls. It is important to prevent arbitrary call rate of
smr_call(). Otherwise, it might be possible to
exhaust system resources if the system is not able to invoke callbacks
SMR_ASSERT_NONCRITICAL() can be used to assert that
the current CPU is or is not in SMR read-side critical section.
smr_init() can be called during autoconf, from process context, or from interrupt context.
smr_flush() can be called during autoconf, or from
|July 5, 2019||OpenBSD-current|