summary refs log tree commit diff stats
path: root/util
diff options
context:
space:
mode:
Diffstat (limited to 'util')
-rw-r--r--util/aio-wait.c2
-rw-r--r--util/async.c34
-rw-r--r--util/main-loop.c6
-rw-r--r--util/mmap-alloc.c28
-rw-r--r--util/qemu-coroutine.c10
-rw-r--r--util/rcu.c69
-rw-r--r--util/stats64.c11
-rw-r--r--util/systemd.c1
-rw-r--r--util/thread-pool.c25
-rw-r--r--util/trace-events1
10 files changed, 141 insertions, 46 deletions
diff --git a/util/aio-wait.c b/util/aio-wait.c
index 98c5accd29..b5336cf5fd 100644
--- a/util/aio-wait.c
+++ b/util/aio-wait.c
@@ -82,5 +82,5 @@ void aio_wait_bh_oneshot(AioContext *ctx, QEMUBHFunc *cb, void *opaque)
     assert(qemu_get_current_aio_context() == qemu_get_aio_context());
 
     aio_bh_schedule_oneshot(ctx, aio_wait_bh, &data);
-    AIO_WAIT_WHILE(ctx, !data.done);
+    AIO_WAIT_WHILE_UNLOCKED(NULL, !data.done);
 }
diff --git a/util/async.c b/util/async.c
index 21016a1ac7..055070ffbd 100644
--- a/util/async.c
+++ b/util/async.c
@@ -65,6 +65,7 @@ struct QEMUBH {
     void *opaque;
     QSLIST_ENTRY(QEMUBH) next;
     unsigned flags;
+    MemReentrancyGuard *reentrancy_guard;
 };
 
 /* Called concurrently from any thread */
@@ -137,7 +138,7 @@ void aio_bh_schedule_oneshot_full(AioContext *ctx, QEMUBHFunc *cb,
 }
 
 QEMUBH *aio_bh_new_full(AioContext *ctx, QEMUBHFunc *cb, void *opaque,
-                        const char *name)
+                        const char *name, MemReentrancyGuard *reentrancy_guard)
 {
     QEMUBH *bh;
     bh = g_new(QEMUBH, 1);
@@ -146,13 +147,30 @@ QEMUBH *aio_bh_new_full(AioContext *ctx, QEMUBHFunc *cb, void *opaque,
         .cb = cb,
         .opaque = opaque,
         .name = name,
+        .reentrancy_guard = reentrancy_guard,
     };
     return bh;
 }
 
 void aio_bh_call(QEMUBH *bh)
 {
+    bool last_engaged_in_io = false;
+
+    /* Make a copy of the guard-pointer as cb may free the bh */
+    MemReentrancyGuard *reentrancy_guard = bh->reentrancy_guard;
+    if (reentrancy_guard) {
+        last_engaged_in_io = reentrancy_guard->engaged_in_io;
+        if (reentrancy_guard->engaged_in_io) {
+            trace_reentrant_aio(bh->ctx, bh->name);
+        }
+        reentrancy_guard->engaged_in_io = true;
+    }
+
     bh->cb(bh->opaque);
+
+    if (reentrancy_guard) {
+        reentrancy_guard->engaged_in_io = last_engaged_in_io;
+    }
 }
 
 /* Multiple occurrences of aio_bh_poll cannot be called concurrently. */
@@ -164,7 +182,21 @@ int aio_bh_poll(AioContext *ctx)
 
     /* Synchronizes with QSLIST_INSERT_HEAD_ATOMIC in aio_bh_enqueue().  */
     QSLIST_MOVE_ATOMIC(&slice.bh_list, &ctx->bh_list);
+
+    /*
+     * GCC13 [-Werror=dangling-pointer=] complains that the local variable
+     * 'slice' is being stored in the global 'ctx->bh_slice_list' but the
+     * list is emptied before this function returns.
+     */
+#if !defined(__clang__)
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wpragmas"
+#pragma GCC diagnostic ignored "-Wdangling-pointer="
+#endif
     QSIMPLEQ_INSERT_TAIL(&ctx->bh_slice_list, &slice, next);
+#if !defined(__clang__)
+#pragma GCC diagnostic pop
+#endif
 
     while ((s = QSIMPLEQ_FIRST(&ctx->bh_slice_list))) {
         QEMUBH *bh;
diff --git a/util/main-loop.c b/util/main-loop.c
index e180c85145..7022f02ef8 100644
--- a/util/main-loop.c
+++ b/util/main-loop.c
@@ -605,9 +605,11 @@ void main_loop_wait(int nonblocking)
 
 /* Functions to operate on the main QEMU AioContext.  */
 
-QEMUBH *qemu_bh_new_full(QEMUBHFunc *cb, void *opaque, const char *name)
+QEMUBH *qemu_bh_new_full(QEMUBHFunc *cb, void *opaque, const char *name,
+                         MemReentrancyGuard *reentrancy_guard)
 {
-    return aio_bh_new_full(qemu_aio_context, cb, opaque, name);
+    return aio_bh_new_full(qemu_aio_context, cb, opaque, name,
+                           reentrancy_guard);
 }
 
 /*
diff --git a/util/mmap-alloc.c b/util/mmap-alloc.c
index 5ed7d29183..ed14f9c64d 100644
--- a/util/mmap-alloc.c
+++ b/util/mmap-alloc.c
@@ -27,8 +27,36 @@
 
 #ifdef CONFIG_LINUX
 #include <sys/vfs.h>
+#include <linux/magic.h>
 #endif
 
+QemuFsType qemu_fd_getfs(int fd)
+{
+#ifdef CONFIG_LINUX
+    struct statfs fs;
+    int ret;
+
+    if (fd < 0) {
+        return QEMU_FS_TYPE_UNKNOWN;
+    }
+
+    do {
+        ret = fstatfs(fd, &fs);
+    } while (ret != 0 && errno == EINTR);
+
+    switch (fs.f_type) {
+    case TMPFS_MAGIC:
+        return QEMU_FS_TYPE_TMPFS;
+    case HUGETLBFS_MAGIC:
+        return QEMU_FS_TYPE_HUGETLBFS;
+    default:
+        return QEMU_FS_TYPE_UNKNOWN;
+    }
+#else
+    return QEMU_FS_TYPE_UNKNOWN;
+#endif
+}
+
 size_t qemu_fd_getpagesize(int fd)
 {
 #ifdef CONFIG_LINUX
diff --git a/util/qemu-coroutine.c b/util/qemu-coroutine.c
index 8494523692..17a88f6505 100644
--- a/util/qemu-coroutine.c
+++ b/util/qemu-coroutine.c
@@ -127,9 +127,13 @@ void qemu_aio_coroutine_enter(AioContext *ctx, Coroutine *co)
         Coroutine *to = QSIMPLEQ_FIRST(&pending);
         CoroutineAction ret;
 
-        /* Cannot rely on the read barrier for to in aio_co_wake(), as there are
-         * callers outside of aio_co_wake() */
-        const char *scheduled = qatomic_mb_read(&to->scheduled);
+        /*
+         * Read to before to->scheduled; pairs with qatomic_cmpxchg in
+         * qemu_co_sleep(), aio_co_schedule() etc.
+         */
+        smp_read_barrier_depends();
+
+        const char *scheduled = qatomic_read(&to->scheduled);
 
         QSIMPLEQ_REMOVE_HEAD(&pending, co_queue_next);
 
diff --git a/util/rcu.c b/util/rcu.c
index b6d6c71cff..30a7e22026 100644
--- a/util/rcu.c
+++ b/util/rcu.c
@@ -83,12 +83,6 @@ static void wait_for_readers(void)
          */
         qemu_event_reset(&rcu_gp_event);
 
-        /* Instead of using qatomic_mb_set for index->waiting, and
-         * qatomic_mb_read for index->ctr, memory barriers are placed
-         * manually since writes to different threads are independent.
-         * qemu_event_reset has acquire semantics, so no memory barrier
-         * is needed here.
-         */
         QLIST_FOREACH(index, &registry, node) {
             qatomic_set(&index->waiting, true);
         }
@@ -96,6 +90,10 @@ static void wait_for_readers(void)
         /* Here, order the stores to index->waiting before the loads of
          * index->ctr.  Pairs with smp_mb_placeholder() in rcu_read_unlock(),
          * ensuring that the loads of index->ctr are sequentially consistent.
+         *
+         * If this is the last iteration, this barrier also prevents
+         * frees from seeping upwards, and orders the two wait phases
+         * on architectures with 32-bit longs; see synchronize_rcu().
          */
         smp_mb_global();
 
@@ -104,7 +102,7 @@ static void wait_for_readers(void)
                 QLIST_REMOVE(index, node);
                 QLIST_INSERT_HEAD(&qsreaders, index, node);
 
-                /* No need for mb_set here, worst of all we
+                /* No need for memory barriers here, worst of all we
                  * get some extra futex wakeups.
                  */
                 qatomic_set(&index->waiting, false);
@@ -149,26 +147,26 @@ void synchronize_rcu(void)
 
     /* Write RCU-protected pointers before reading p_rcu_reader->ctr.
      * Pairs with smp_mb_placeholder() in rcu_read_lock().
+     *
+     * Also orders write to RCU-protected pointers before
+     * write to rcu_gp_ctr.
      */
     smp_mb_global();
 
     QEMU_LOCK_GUARD(&rcu_registry_lock);
     if (!QLIST_EMPTY(&registry)) {
-        /* In either case, the qatomic_mb_set below blocks stores that free
-         * old RCU-protected pointers.
-         */
         if (sizeof(rcu_gp_ctr) < 8) {
             /* For architectures with 32-bit longs, a two-subphases algorithm
              * ensures we do not encounter overflow bugs.
              *
              * Switch parity: 0 -> 1, 1 -> 0.
              */
-            qatomic_mb_set(&rcu_gp_ctr, rcu_gp_ctr ^ RCU_GP_CTR);
+            qatomic_set(&rcu_gp_ctr, rcu_gp_ctr ^ RCU_GP_CTR);
             wait_for_readers();
-            qatomic_mb_set(&rcu_gp_ctr, rcu_gp_ctr ^ RCU_GP_CTR);
+            qatomic_set(&rcu_gp_ctr, rcu_gp_ctr ^ RCU_GP_CTR);
         } else {
             /* Increment current grace period.  */
-            qatomic_mb_set(&rcu_gp_ctr, rcu_gp_ctr + RCU_GP_CTR);
+            qatomic_set(&rcu_gp_ctr, rcu_gp_ctr + RCU_GP_CTR);
         }
 
         wait_for_readers();
@@ -191,8 +189,22 @@ static void enqueue(struct rcu_head *node)
     struct rcu_head **old_tail;
 
     node->next = NULL;
+
+    /*
+     * Make this node the tail of the list.  The node will be
+     * used by further enqueue operations, but it will not
+     * be dequeued yet...
+     */
     old_tail = qatomic_xchg(&tail, &node->next);
-    qatomic_mb_set(old_tail, node);
+
+    /*
+     * ... until it is pointed to from another item in the list.
+     * In the meantime, try_dequeue() will find a NULL next pointer
+     * and loop.
+     *
+     * Synchronizes with qatomic_load_acquire() in try_dequeue().
+     */
+    qatomic_store_release(old_tail, node);
 }
 
 static struct rcu_head *try_dequeue(void)
@@ -200,26 +212,31 @@ static struct rcu_head *try_dequeue(void)
     struct rcu_head *node, *next;
 
 retry:
-    /* Test for an empty list, which we do not expect.  Note that for
+    /* Head is only written by this thread, so no need for barriers.  */
+    node = head;
+
+    /*
+     * If the head node has NULL in its next pointer, the value is
+     * wrong and we need to wait until its enqueuer finishes the update.
+     */
+    next = qatomic_load_acquire(&node->next);
+    if (!next) {
+        return NULL;
+    }
+
+    /*
+     * Test for an empty list, which we do not expect.  Note that for
      * the consumer head and tail are always consistent.  The head
      * is consistent because only the consumer reads/writes it.
      * The tail, because it is the first step in the enqueuing.
      * It is only the next pointers that might be inconsistent.
      */
-    if (head == &dummy && qatomic_mb_read(&tail) == &dummy.next) {
+    if (head == &dummy && qatomic_read(&tail) == &dummy.next) {
         abort();
     }
 
-    /* If the head node has NULL in its next pointer, the value is
-     * wrong and we need to wait until its enqueuer finishes the update.
-     */
-    node = head;
-    next = qatomic_mb_read(&head->next);
-    if (!next) {
-        return NULL;
-    }
-
-    /* Since we are the sole consumer, and we excluded the empty case
+    /*
+     * Since we are the sole consumer, and we excluded the empty case
      * above, the queue will always have at least two nodes: the
      * dummy node, and the one being removed.  So we do not need to update
      * the tail pointer.
diff --git a/util/stats64.c b/util/stats64.c
index 897613c949..09736014ec 100644
--- a/util/stats64.c
+++ b/util/stats64.c
@@ -57,6 +57,17 @@ uint64_t stat64_get(const Stat64 *s)
     return ((uint64_t)high << 32) | low;
 }
 
+void stat64_set(Stat64 *s, uint64_t val)
+{
+    while (!stat64_wrtrylock(s)) {
+        cpu_relax();
+    }
+
+    qatomic_set(&s->high, val >> 32);
+    qatomic_set(&s->low, val);
+    stat64_wrunlock(s);
+}
+
 bool stat64_add32_carry(Stat64 *s, uint32_t low, uint32_t high)
 {
     uint32_t old;
diff --git a/util/systemd.c b/util/systemd.c
index 5bcac9b401..ced518f771 100644
--- a/util/systemd.c
+++ b/util/systemd.c
@@ -51,6 +51,7 @@ unsigned int check_socket_activation(void)
     /* So these are not passed to any child processes we might start. */
     unsetenv("LISTEN_FDS");
     unsetenv("LISTEN_PID");
+    unsetenv("LISTEN_FDNAMES");
 
     /* So the file descriptors don't leak into child processes. */
     for (i = 0; i < nr_fds; ++i) {
diff --git a/util/thread-pool.c b/util/thread-pool.c
index 31113b5860..0d97888df0 100644
--- a/util/thread-pool.c
+++ b/util/thread-pool.c
@@ -48,7 +48,7 @@ struct ThreadPoolElement {
     /* Access to this list is protected by lock.  */
     QTAILQ_ENTRY(ThreadPoolElement) reqs;
 
-    /* Access to this list is protected by the global mutex.  */
+    /* This list is only written by the thread pool's mother thread.  */
     QLIST_ENTRY(ThreadPoolElement) all;
 };
 
@@ -175,7 +175,6 @@ static void thread_pool_completion_bh(void *opaque)
     ThreadPool *pool = opaque;
     ThreadPoolElement *elem, *next;
 
-    aio_context_acquire(pool->ctx);
 restart:
     QLIST_FOREACH_SAFE(elem, &pool->head, all, next) {
         if (elem->state != THREAD_DONE) {
@@ -195,9 +194,7 @@ restart:
              */
             qemu_bh_schedule(pool->completion_bh);
 
-            aio_context_release(pool->ctx);
             elem->common.cb(elem->common.opaque, elem->ret);
-            aio_context_acquire(pool->ctx);
 
             /* We can safely cancel the completion_bh here regardless of someone
              * else having scheduled it meanwhile because we reenter the
@@ -211,7 +208,6 @@ restart:
             qemu_aio_unref(elem);
         }
     }
-    aio_context_release(pool->ctx);
 }
 
 static void thread_pool_cancel(BlockAIOCB *acb)
@@ -245,11 +241,15 @@ static const AIOCBInfo thread_pool_aiocb_info = {
     .get_aio_context    = thread_pool_get_aio_context,
 };
 
-BlockAIOCB *thread_pool_submit_aio(ThreadPool *pool,
-        ThreadPoolFunc *func, void *arg,
-        BlockCompletionFunc *cb, void *opaque)
+BlockAIOCB *thread_pool_submit_aio(ThreadPoolFunc *func, void *arg,
+                                   BlockCompletionFunc *cb, void *opaque)
 {
     ThreadPoolElement *req;
+    AioContext *ctx = qemu_get_current_aio_context();
+    ThreadPool *pool = aio_get_thread_pool(ctx);
+
+    /* Assert that the thread submitting work is the same running the pool */
+    assert(pool->ctx == qemu_get_current_aio_context());
 
     req = qemu_aio_get(&thread_pool_aiocb_info, NULL, cb, opaque);
     req->func = func;
@@ -284,19 +284,18 @@ static void thread_pool_co_cb(void *opaque, int ret)
     aio_co_wake(co->co);
 }
 
-int coroutine_fn thread_pool_submit_co(ThreadPool *pool, ThreadPoolFunc *func,
-                                       void *arg)
+int coroutine_fn thread_pool_submit_co(ThreadPoolFunc *func, void *arg)
 {
     ThreadPoolCo tpc = { .co = qemu_coroutine_self(), .ret = -EINPROGRESS };
     assert(qemu_in_coroutine());
-    thread_pool_submit_aio(pool, func, arg, thread_pool_co_cb, &tpc);
+    thread_pool_submit_aio(func, arg, thread_pool_co_cb, &tpc);
     qemu_coroutine_yield();
     return tpc.ret;
 }
 
-void thread_pool_submit(ThreadPool *pool, ThreadPoolFunc *func, void *arg)
+void thread_pool_submit(ThreadPoolFunc *func, void *arg)
 {
-    thread_pool_submit_aio(pool, func, arg, NULL, NULL);
+    thread_pool_submit_aio(func, arg, NULL, NULL);
 }
 
 void thread_pool_update_params(ThreadPool *pool, AioContext *ctx)
diff --git a/util/trace-events b/util/trace-events
index 16f78d8fe5..3f7e766683 100644
--- a/util/trace-events
+++ b/util/trace-events
@@ -11,6 +11,7 @@ poll_remove(void *ctx, void *node, int fd) "ctx %p node %p fd %d"
 # async.c
 aio_co_schedule(void *ctx, void *co) "ctx %p co %p"
 aio_co_schedule_bh_cb(void *ctx, void *co) "ctx %p co %p"
+reentrant_aio(void *ctx, const char *name) "ctx %p name %s"
 
 # thread-pool.c
 thread_pool_submit(void *pool, void *req, void *opaque) "pool %p req %p opaque %p"