- NetBSD Manual Pages
PERCPU(9) NetBSD Kernel Developer's Manual PERCPU(9)
Powered by man-cgi (2021-06-01).
Maintained for NetBSD
by Kimmo Suominen.
Based on man-cgi by Panagiotis Christias.
percpu, percpu_alloc, percpu_create, percpu_free, percpu_getref,
percpu_putref, percpu_foreach, percpu_foreach_xcall -- per-CPU storage
typedef void (*percpu_callback_t)(void *, void *, struct cpu_info *);
percpu_create(size_t size, percpu_callback_t ctor,
percpu_callback_t dtor, void *arg);
percpu_free(percpu_t *pc, size_t size);
percpu_foreach(percpu_t *pc, percpu_callback_t cb, void *arg);
percpu_foreach_xcall(percpu_t *pc, u_int xcflags, percpu_callback_t cb,
The machine-independent percpu interface provides per-CPU, CPU-local mem-
ory reservations to kernel subsystems. percpu_alloc(size) reserves on
each CPU an independent memory region of size bytes that is local to that
CPU, returning a handle (percpu_t) to those regions. A thread may subse-
quently ask for a pointer, p, to the region held by the percpu_t on the
thread's current CPU. Until the thread relinquishes the pointer, or vol-
untarily sleeps, the thread may read or write the region at p without
causing interprocessor memory synchronization.
Call this in thread context to allocate size bytes of local
storage on each CPU. The storage is initialized with zeroes.
Treat this as an expensive operation. percpu_alloc() returns a
handle for the per-CPU storage.
percpu_create(size, ctor, dtor, arg)
Like percpu_alloc(), but before returning, for each CPU, call
(*ctor)(p, arg, ci) in the current thread, where p is the
pointer to that CPU's storage and ci is the struct cpu_info *
for that CPU. Further, arrange that percpu_free() will do the
same with (*dtor)(p, arg, ci).
ctor and dtor MAY sleep, e.g. to allocate memory or to wait for
users to drain before deallocating memory. Do not rely on any
particular order of iteration over the CPUs.
Call this in thread context to return to the system the per-CPU
storage held by pc. size should match the size passed to
percpu_alloc() or percpu_create(). When percpu_free() returns,
pc is undefined. Treat this as an expensive operation.
Disable preemption and return a pointer to the storage held by
pc on the local CPU. Use percpu_getref() in either thread or
interrupt context. Follow each percpu_getref() call with a
matching call to percpu_putref().
Caller MUST NOT sleep after percpu_getref(), not even on an
adaptive lock, before percpu_putref().
Indicate that the thread is finished with the pointer returned
by the matching call to percpu_getref(). Re-enables preemption.
percpu_foreach(pc, cb, arg)
For each CPU, with ci being the corresponding struct cpu_info *
and p the CPU-local storage held by pc, run (*cb)(p, arg, ci).
The call to cb runs in the current thread; use
percpu_foreach_xcall() to execute the call to cb on the remote
Must be used in thread context. cb MUST NOT sleep except on
adaptive locks, and should be fast. Do not rely on any particu-
lar order of iteration over the CPUs.
percpu_foreach_xcall(pc, xcflags, cb, arg)
Like percpu_foreach(), except the call to cb executes on the
remote CPUs. The xcflags argument specifies how the cross calls
are invoked; see xc_broadcast(9). The same caveats and restric-
tions that apply to percpu_foreach() also apply to
The percpu interface is implemented within the file
atomic_ops(3), kmem(9), pcq(9), pool_cache(9), xcall(9)
The percpu interface first appeared in NetBSD 6.0.
YAMAMOTO Takashi <yamt@NetBSD.org>
NetBSD 10.99 February 7, 2020 NetBSD 10.99