Merge remote-tracking branch 'remotes/stefanha/tags/block-pull-request' into staging

# gpg: Signature made Tue 13 Jan 2015 13:48:06 GMT using RSA key ID 81AB73C8
# gpg: Good signature from "Stefan Hajnoczi <stefanha@redhat.com>"
# gpg:                 aka "Stefan Hajnoczi <stefanha@gmail.com>"

* remotes/stefanha/tags/block-pull-request: (38 commits)
  NVMe: Set correct VS Value for 1.1 Compliant Controllers
  MAINTAINERS: Add migration/block* to block subsystem
  MAINTAINERS: Update email addresses for Chrysostomos Nanakos
  nvme: Fix get/set number of queues feature
  ide: Implement VPD response for ATAPI
  block: Split BLOCK_OP_TYPE_COMMIT to BLOCK_OP_TYPE_COMMIT_{SOURCE, TARGET}
  block: limited request size in write zeroes unsupported path
  coroutine: try harder not to delete coroutines
  coroutine: drop qemu_coroutine_adjust_pool_size
  coroutine: rewrite pool to avoid mutex
  QSLIST: add lock-free operations
  test-coroutine: avoid overflow on 32-bit systems
  qemu-thread: add per-thread atexit functions
  coroutine-ucontext: use __thread
  qemu-iotests: Add supported os parameter for python tests
  qemu-iotests: Add "_supported_os Linux" to 058
  qemu-iotests: Replace "/bin/true" with "true"
  .gitignore: Ignore generated "common.env"
  libqos: Convert malloc-pc allocator to a generic allocator
  migration/block: fix pending() return value
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

1 files changed, 48 insertions, 55 deletions

diff --git a/qemu-coroutine.c b/qemu-coroutine.c
index bd574aa1b5..525247b050 100644
--- a/qemu-coroutine.c
+++ b/qemu-coroutine.c
@@ -15,31 +15,59 @@
 #include "trace.h"
 #include "qemu-common.h"
 #include "qemu/thread.h"
+#include "qemu/atomic.h"
 #include "block/coroutine.h"
 #include "block/coroutine_int.h"
 
 enum {
-    POOL_DEFAULT_SIZE = 64,
+    POOL_BATCH_SIZE = 64,
 };
 
 /** Free list to speed up creation */
-static QemuMutex pool_lock;
-static QSLIST_HEAD(, Coroutine) pool = QSLIST_HEAD_INITIALIZER(pool);
-static unsigned int pool_size;
-static unsigned int pool_max_size = POOL_DEFAULT_SIZE;
+static QSLIST_HEAD(, Coroutine) release_pool = QSLIST_HEAD_INITIALIZER(pool);
+static unsigned int release_pool_size;
+static __thread QSLIST_HEAD(, Coroutine) alloc_pool = QSLIST_HEAD_INITIALIZER(pool);
+static __thread unsigned int alloc_pool_size;
+static __thread Notifier coroutine_pool_cleanup_notifier;
+
+static void coroutine_pool_cleanup(Notifier *n, void *value)
+{
+    Coroutine *co;
+    Coroutine *tmp;
+
+    QSLIST_FOREACH_SAFE(co, &alloc_pool, pool_next, tmp) {
+        QSLIST_REMOVE_HEAD(&alloc_pool, pool_next);
+        qemu_coroutine_delete(co);
+    }
+}
 
 Coroutine *qemu_coroutine_create(CoroutineEntry *entry)
 {
     Coroutine *co = NULL;
 
     if (CONFIG_COROUTINE_POOL) {
-        qemu_mutex_lock(&pool_lock);
-        co = QSLIST_FIRST(&pool);
+        co = QSLIST_FIRST(&alloc_pool);
+        if (!co) {
+            if (release_pool_size > POOL_BATCH_SIZE) {
+                /* Slow path; a good place to register the destructor, too.  */
+                if (!coroutine_pool_cleanup_notifier.notify) {
+                    coroutine_pool_cleanup_notifier.notify = coroutine_pool_cleanup;
+                    qemu_thread_atexit_add(&coroutine_pool_cleanup_notifier);
+                }
+
+                /* This is not exact; there could be a little skew between
+                 * release_pool_size and the actual size of release_pool.  But
+                 * it is just a heuristic, it does not need to be perfect.
+                 */
+                alloc_pool_size = atomic_xchg(&release_pool_size, 0);
+                QSLIST_MOVE_ATOMIC(&alloc_pool, &release_pool);
+                co = QSLIST_FIRST(&alloc_pool);
+            }
+        }
         if (co) {
-            QSLIST_REMOVE_HEAD(&pool, pool_next);
-            pool_size--;
+            QSLIST_REMOVE_HEAD(&alloc_pool, pool_next);
+            alloc_pool_size--;
         }
-        qemu_mutex_unlock(&pool_lock);
     }
 
     if (!co) {
@@ -53,39 +81,24 @@ Coroutine *qemu_coroutine_create(CoroutineEntry *entry)
 
 static void coroutine_delete(Coroutine *co)
 {
+    co->caller = NULL;
+
     if (CONFIG_COROUTINE_POOL) {
-        qemu_mutex_lock(&pool_lock);
-        if (pool_size < pool_max_size) {
-            QSLIST_INSERT_HEAD(&pool, co, pool_next);
-            co->caller = NULL;
-            pool_size++;
-            qemu_mutex_unlock(&pool_lock);
+        if (release_pool_size < POOL_BATCH_SIZE * 2) {
+            QSLIST_INSERT_HEAD_ATOMIC(&release_pool, co, pool_next);
+            atomic_inc(&release_pool_size);
+            return;
+        }
+        if (alloc_pool_size < POOL_BATCH_SIZE) {
+            QSLIST_INSERT_HEAD(&alloc_pool, co, pool_next);
+            alloc_pool_size++;
             return;
         }
-        qemu_mutex_unlock(&pool_lock);
     }
 
     qemu_coroutine_delete(co);
 }
 
-static void __attribute__((constructor)) coroutine_pool_init(void)
-{
-    qemu_mutex_init(&pool_lock);
-}
-
-static void __attribute__((destructor)) coroutine_pool_cleanup(void)
-{
-    Coroutine *co;
-    Coroutine *tmp;
-
-    QSLIST_FOREACH_SAFE(co, &pool, pool_next, tmp) {
-        QSLIST_REMOVE_HEAD(&pool, pool_next);
-        qemu_coroutine_delete(co);
-    }
-
-    qemu_mutex_destroy(&pool_lock);
-}
-
 static void coroutine_swap(Coroutine *from, Coroutine *to)
 {
     CoroutineAction ret;
@@ -137,23 +150,3 @@ void coroutine_fn qemu_coroutine_yield(void)
     self->caller = NULL;
     coroutine_swap(self, to);
 }
-
-void qemu_coroutine_adjust_pool_size(int n)
-{
-    qemu_mutex_lock(&pool_lock);
-
-    pool_max_size += n;
-
-    /* Callers should never take away more than they added */
-    assert(pool_max_size >= POOL_DEFAULT_SIZE);
-
-    /* Trim oversized pool down to new max */
-    while (pool_size > pool_max_size) {
-        Coroutine *co = QSLIST_FIRST(&pool);
-        QSLIST_REMOVE_HEAD(&pool, pool_next);
-        pool_size--;
-        qemu_coroutine_delete(co);
-    }
-
-    qemu_mutex_unlock(&pool_lock);
-}