#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/mmu_context.h>
+#include <linux/percpu.h>
#include <linux/slab.h>
#include <linux/timer.h>
#include <linux/aio.h>
#define AIO_RING_PAGES 8
+struct kioctx_cpu {
+ unsigned reqs_available;
+};
+
struct kioctx {
atomic_t users;
atomic_t dead;
unsigned long user_id;
struct hlist_node list;
+ struct __percpu kioctx_cpu *cpu;
+
+ unsigned req_batch;
+
unsigned nr;
/* sys_io_setup currently limits this to an unsigned int */
unsigned long size, populate;
int nr_pages;
+ nr_events = max(nr_events, num_possible_cpus() * 4);
+ nr_events *= 2;
+
/* Compensate for the ring buffer's head/tail overlap entry */
nr_events += 2; /* 1 is required, 2 for good luck */
static void free_ioctx_rcu(struct rcu_head *head)
{
struct kioctx *ctx = container_of(head, struct kioctx, rcu_head);
+
+ free_percpu(ctx->cpu);
kmem_cache_free(kioctx_cachep, ctx);
}
struct aio_ring *ring;
struct io_event res;
struct kiocb *req;
- unsigned head, avail;
+ unsigned cpu, head, avail;
spin_lock_irq(&ctx->ctx_lock);
spin_unlock_irq(&ctx->ctx_lock);
+ for_each_possible_cpu(cpu) {
+ struct kioctx_cpu *kcpu = per_cpu_ptr(ctx->cpu, cpu);
+
+ atomic_add(kcpu->reqs_available, &ctx->reqs_available);
+ kcpu->reqs_available = 0;
+ }
+
ring = kmap_atomic(ctx->ring_pages[0]);
head = ring->head;
kunmap_atomic(ring);
INIT_LIST_HEAD(&ctx->active_reqs);
- if (aio_setup_ring(ctx) < 0)
+ ctx->cpu = alloc_percpu(struct kioctx_cpu);
+ if (!ctx->cpu)
goto out_freectx;
+ if (aio_setup_ring(ctx) < 0)
+ goto out_freepcpu;
+
atomic_set(&ctx->reqs_available, ctx->nr);
+ ctx->req_batch = ctx->nr / (num_possible_cpus() * 4);
+ BUG_ON(!ctx->req_batch);
/* limit the number of system wide aios */
spin_lock(&aio_nr_lock);
out_cleanup:
err = -EAGAIN;
aio_free_ring(ctx);
+out_freepcpu:
+ free_percpu(ctx->cpu);
out_freectx:
kmem_cache_free(kioctx_cachep, ctx);
pr_debug("error allocating ioctx %d\n", err);
}
}
+static void put_reqs_available(struct kioctx *ctx, unsigned nr)
+{
+ struct kioctx_cpu *kcpu;
+
+ preempt_disable();
+ kcpu = this_cpu_ptr(ctx->cpu);
+
+ kcpu->reqs_available += nr;
+ while (kcpu->reqs_available >= ctx->req_batch * 2) {
+ kcpu->reqs_available -= ctx->req_batch;
+ atomic_add(ctx->req_batch, &ctx->reqs_available);
+ }
+
+ preempt_enable();
+}
+
+static bool get_reqs_available(struct kioctx *ctx)
+{
+ struct kioctx_cpu *kcpu;
+ bool ret = false;
+
+ preempt_disable();
+ kcpu = this_cpu_ptr(ctx->cpu);
+
+ if (!kcpu->reqs_available) {
+ int old, avail = atomic_read(&ctx->reqs_available);
+
+ do {
+ if (avail < ctx->req_batch)
+ goto out;
+
+ old = avail;
+ avail = atomic_cmpxchg(&ctx->reqs_available,
+ avail, avail - ctx->req_batch);
+ } while (avail != old);
+
+ kcpu->reqs_available += ctx->req_batch;
+ }
+
+ ret = true;
+ kcpu->reqs_available--;
+out:
+ preempt_enable();
+ return ret;
+}
+
/* aio_get_req
* Allocate a slot for an aio request. Increments the ki_users count
* of the kioctx so that the kioctx stays around until all requests are
{
struct kiocb *req;
- if (atomic_dec_if_positive(&ctx->reqs_available) <= 0)
+ if (!get_reqs_available(ctx))
return NULL;
req = kmem_cache_alloc(kiocb_cachep, GFP_KERNEL|__GFP_ZERO);
atomic_set(&req->ki_users, 2);
req->ki_ctx = ctx;
-
return req;
out_put:
- atomic_inc(&ctx->reqs_available);
+ put_reqs_available(ctx, 1);
return NULL;
}
*/
if (unlikely(xchg(&iocb->ki_cancel,
KIOCB_CANCELLED) == KIOCB_CANCELLED)) {
+ /*
+ * Can't use the percpu reqs_available here - could race with
+ * free_ioctx()
+ */
atomic_inc(&ctx->reqs_available);
/* Still need the wake_up in case free_ioctx is waiting */
goto put_rq;
pr_debug("%d h%u t%u\n", ret, head, ctx->tail);
- atomic_add(ret, &ctx->reqs_available);
+ put_reqs_available(ctx, ret);
out:
mutex_unlock(&ctx->ring_lock);
return 0;
out_put_req:
- atomic_inc(&ctx->reqs_available);
+ put_reqs_available(ctx, 1);
aio_put_req(req); /* drop extra ref to req */
aio_put_req(req); /* drop i/o ref to req */
return ret;