summaryrefslogtreecommitdiff
path: root/lib
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2013-07-03 06:52:14 +0400
committerLinus Torvalds <torvalds@linux-foundation.org>2013-07-03 06:52:14 +0400
commit13cc56013842a847a0f6ff805d9ed9181e753ef8 (patch)
tree76b55717efc36f83c934ee894a8522e8a28eb57f /lib
parent7c6809ff2bd63d4c97ce9e0b94d39d5180842c48 (diff)
parenta4244454df1296e90cc961c1b636b1176ef0d9a0 (diff)
downloadlinux-13cc56013842a847a0f6ff805d9ed9181e753ef8.tar.xz
Merge branch 'for-3.11' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu
Pull per-cpu changes from Tejun Heo: "This pull request contains Kent's per-cpu reference counter. It has gone through several iterations since the last time and the dynamic allocation is gone. The usual usage is relatively straight-forward although async kill confirm interface, which is not used int most cases, is somewhat icky. There also are some interface concerns - e.g. I'm not sure about passing in @relesae callback during init as that becomes funny when we later implement synchronous kill_and_drain - but nothing too serious and it's quite useable now. cgroup_subsys_state refcnting has already been converted and we should convert module refcnt (Kent?)" * 'for-3.11' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu: percpu-refcount: use RCU-sched insted of normal RCU percpu-refcount: implement percpu_tryget() along with percpu_ref_kill_and_confirm() percpu-refcount: implement percpu_ref_cancel_init() percpu-refcount: add __must_check to percpu_ref_init() and don't use ACCESS_ONCE() in percpu_ref_kill_rcu() percpu-refcount: cosmetic updates percpu-refcount: consistently use plain (non-sched) RCU percpu-refcount: Don't use silly cmpxchg() percpu: implement generic percpu refcounting
Diffstat (limited to 'lib')
-rw-r--r--lib/Makefile2
-rw-r--r--lib/percpu-refcount.c158
2 files changed, 159 insertions, 1 deletions
diff --git a/lib/Makefile b/lib/Makefile
index 22f0f4e8a9e1..8f8d385187f2 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -13,7 +13,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \
sha1.o md5.o irq_regs.o reciprocal_div.o argv_split.o \
proportions.o flex_proportions.o prio_heap.o ratelimit.o show_mem.o \
is_single_threaded.o plist.o decompress.o kobject_uevent.o \
- earlycpio.o
+ earlycpio.o percpu-refcount.o
obj-$(CONFIG_ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS) += usercopy.o
lib-$(CONFIG_MMU) += ioremap.o
diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c
new file mode 100644
index 000000000000..7deeb6297a48
--- /dev/null
+++ b/lib/percpu-refcount.c
@@ -0,0 +1,158 @@
+#define pr_fmt(fmt) "%s: " fmt "\n", __func__
+
+#include <linux/kernel.h>
+#include <linux/percpu-refcount.h>
+
+/*
+ * Initially, a percpu refcount is just a set of percpu counters. Initially, we
+ * don't try to detect the ref hitting 0 - which means that get/put can just
+ * increment or decrement the local counter. Note that the counter on a
+ * particular cpu can (and will) wrap - this is fine, when we go to shutdown the
+ * percpu counters will all sum to the correct value
+ *
+ * (More precisely: because moduler arithmatic is commutative the sum of all the
+ * pcpu_count vars will be equal to what it would have been if all the gets and
+ * puts were done to a single integer, even if some of the percpu integers
+ * overflow or underflow).
+ *
+ * The real trick to implementing percpu refcounts is shutdown. We can't detect
+ * the ref hitting 0 on every put - this would require global synchronization
+ * and defeat the whole purpose of using percpu refs.
+ *
+ * What we do is require the user to keep track of the initial refcount; we know
+ * the ref can't hit 0 before the user drops the initial ref, so as long as we
+ * convert to non percpu mode before the initial ref is dropped everything
+ * works.
+ *
+ * Converting to non percpu mode is done with some RCUish stuff in
+ * percpu_ref_kill. Additionally, we need a bias value so that the atomic_t
+ * can't hit 0 before we've added up all the percpu refs.
+ */
+
+#define PCPU_COUNT_BIAS (1U << 31)
+
+/**
+ * percpu_ref_init - initialize a percpu refcount
+ * @ref: percpu_ref to initialize
+ * @release: function which will be called when refcount hits 0
+ *
+ * Initializes the refcount in single atomic counter mode with a refcount of 1;
+ * analagous to atomic_set(ref, 1).
+ *
+ * Note that @release must not sleep - it may potentially be called from RCU
+ * callback context by percpu_ref_kill().
+ */
+int percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release)
+{
+ atomic_set(&ref->count, 1 + PCPU_COUNT_BIAS);
+
+ ref->pcpu_count = alloc_percpu(unsigned);
+ if (!ref->pcpu_count)
+ return -ENOMEM;
+
+ ref->release = release;
+ return 0;
+}
+
+/**
+ * percpu_ref_cancel_init - cancel percpu_ref_init()
+ * @ref: percpu_ref to cancel init for
+ *
+ * Once a percpu_ref is initialized, its destruction is initiated by
+ * percpu_ref_kill() and completes asynchronously, which can be painful to
+ * do when destroying a half-constructed object in init failure path.
+ *
+ * This function destroys @ref without invoking @ref->release and the
+ * memory area containing it can be freed immediately on return. To
+ * prevent accidental misuse, it's required that @ref has finished
+ * percpu_ref_init(), whether successful or not, but never used.
+ *
+ * The weird name and usage restriction are to prevent people from using
+ * this function by mistake for normal shutdown instead of
+ * percpu_ref_kill().
+ */
+void percpu_ref_cancel_init(struct percpu_ref *ref)
+{
+ unsigned __percpu *pcpu_count = ref->pcpu_count;
+ int cpu;
+
+ WARN_ON_ONCE(atomic_read(&ref->count) != 1 + PCPU_COUNT_BIAS);
+
+ if (pcpu_count) {
+ for_each_possible_cpu(cpu)
+ WARN_ON_ONCE(*per_cpu_ptr(pcpu_count, cpu));
+ free_percpu(ref->pcpu_count);
+ }
+}
+
+static void percpu_ref_kill_rcu(struct rcu_head *rcu)
+{
+ struct percpu_ref *ref = container_of(rcu, struct percpu_ref, rcu);
+ unsigned __percpu *pcpu_count = ref->pcpu_count;
+ unsigned count = 0;
+ int cpu;
+
+ /* Mask out PCPU_REF_DEAD */
+ pcpu_count = (unsigned __percpu *)
+ (((unsigned long) pcpu_count) & ~PCPU_STATUS_MASK);
+
+ for_each_possible_cpu(cpu)
+ count += *per_cpu_ptr(pcpu_count, cpu);
+
+ free_percpu(pcpu_count);
+
+ pr_debug("global %i pcpu %i", atomic_read(&ref->count), (int) count);
+
+ /*
+ * It's crucial that we sum the percpu counters _before_ adding the sum
+ * to &ref->count; since gets could be happening on one cpu while puts
+ * happen on another, adding a single cpu's count could cause
+ * @ref->count to hit 0 before we've got a consistent value - but the
+ * sum of all the counts will be consistent and correct.
+ *
+ * Subtracting the bias value then has to happen _after_ adding count to
+ * &ref->count; we need the bias value to prevent &ref->count from
+ * reaching 0 before we add the percpu counts. But doing it at the same
+ * time is equivalent and saves us atomic operations:
+ */
+
+ atomic_add((int) count - PCPU_COUNT_BIAS, &ref->count);
+
+ /* @ref is viewed as dead on all CPUs, send out kill confirmation */
+ if (ref->confirm_kill)
+ ref->confirm_kill(ref);
+
+ /*
+ * Now we're in single atomic_t mode with a consistent refcount, so it's
+ * safe to drop our initial ref:
+ */
+ percpu_ref_put(ref);
+}
+
+/**
+ * percpu_ref_kill_and_confirm - drop the initial ref and schedule confirmation
+ * @ref: percpu_ref to kill
+ * @confirm_kill: optional confirmation callback
+ *
+ * Equivalent to percpu_ref_kill() but also schedules kill confirmation if
+ * @confirm_kill is not NULL. @confirm_kill, which may not block, will be
+ * called after @ref is seen as dead from all CPUs - all further
+ * invocations of percpu_ref_tryget() will fail. See percpu_ref_tryget()
+ * for more details.
+ *
+ * Due to the way percpu_ref is implemented, @confirm_kill will be called
+ * after at least one full RCU grace period has passed but this is an
+ * implementation detail and callers must not depend on it.
+ */
+void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
+ percpu_ref_func_t *confirm_kill)
+{
+ WARN_ONCE(REF_STATUS(ref->pcpu_count) == PCPU_REF_DEAD,
+ "percpu_ref_kill() called more than once!\n");
+
+ ref->pcpu_count = (unsigned __percpu *)
+ (((unsigned long) ref->pcpu_count)|PCPU_REF_DEAD);
+ ref->confirm_kill = confirm_kill;
+
+ call_rcu_sched(&ref->rcu, percpu_ref_kill_rcu);
+}