Merge remote-tracking branch 'remotes/bonzini/tags/for-upstream' into staging

* device_del fix (Julia)
* FXAM fix (myself)
* memdev refactoring (Igor)
* memory region API cleanups (Peter, Philippe)
* ioeventfd optimization (Stefan)
* new WHPX maintainer (Sunil)
* Large guest startup optimizations (Chen)

# gpg: Signature made Tue 25 Feb 2020 12:42:24 GMT
# gpg:                using RSA key BFFBD25F78C7AE83
# gpg: Good signature from "Paolo Bonzini <bonzini@gnu.org>" [full]
# gpg:                 aka "Paolo Bonzini <pbonzini@redhat.com>" [full]
# Primary key fingerprint: 46F5 9FBD 57D6 12E7 BFD4  E2F7 7E15 100C CD36 69B1
#      Subkey fingerprint: F133 3857 4B66 2389 866C  7682 BFFB D25F 78C7 AE83

* remotes/bonzini/tags/for-upstream: (104 commits)
  WHPX: Assigning maintainer for Windows Hypervisor Platform
  accel/kvm: Check ioctl(KVM_SET_USER_MEMORY_REGION) return value
  target/i386: check for empty register in FXAM
  qdev-monitor: Forbid repeated device_del
  mem-prealloc: optimize large guest startup
  memory: batch allocate ioeventfds[] in address_space_update_ioeventfds()
  Avoid cpu_physical_memory_rw() with a constant is_write argument
  Let cpu_[physical]_memory() calls pass a boolean 'is_write' argument
  exec: Let cpu_[physical]_memory API use a boolean 'is_write' argument
  Avoid address_space_rw() with a constant is_write argument
  Let address_space_rw() calls pass a boolean 'is_write' argument
  exec: Let address_space_unmap() use a boolean 'is_write' argument
  hw/virtio: Let vhost_memory_map() use a boolean 'is_write' argument
  hw/virtio: Let virtqueue_map_iovec() use a boolean 'is_write' argument
  hw/ide: Let the DMAIntFunc prototype use a boolean 'is_write' argument
  hw/ide/internal: Remove unused DMARestartFunc typedef
  Remove unnecessary cast when using the cpu_[physical]_memory API
  exec: Let the cpu_[physical]_memory API use void pointer arguments
  Remove unnecessary cast when using the address_space API
  hw/net: Avoid casting non-const pointer, use address_space_write()
  ...

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

1 files changed, 24 insertions, 8 deletions

diff --git a/util/oslib-posix.c b/util/oslib-posix.c
index 5a291cc982..897e8f3ba6 100644
--- a/util/oslib-posix.c
+++ b/util/oslib-posix.c
@@ -76,6 +76,10 @@ static MemsetThread *memset_thread;
 static int memset_num_threads;
 static bool memset_thread_failed;
 
+static QemuMutex page_mutex;
+static QemuCond page_cond;
+static bool threads_created_flag;
+
 int qemu_get_thread_id(void)
 {
 #if defined(__linux__)
@@ -403,6 +407,17 @@ static void *do_touch_pages(void *arg)
     MemsetThread *memset_args = (MemsetThread *)arg;
     sigset_t set, oldset;
 
+    /*
+     * On Linux, the page faults from the loop below can cause mmap_sem
+     * contention with allocation of the thread stacks.  Do not start
+     * clearing until all threads have been created.
+     */
+    qemu_mutex_lock(&page_mutex);
+    while(!threads_created_flag){
+        qemu_cond_wait(&page_cond, &page_mutex);
+    }
+    qemu_mutex_unlock(&page_mutex);
+
     /* unblock SIGBUS */
     sigemptyset(&set);
     sigaddset(&set, SIGBUS);
@@ -451,27 +466,28 @@ static inline int get_memset_num_threads(int smp_cpus)
 static bool touch_all_pages(char *area, size_t hpagesize, size_t numpages,
                             int smp_cpus)
 {
-    size_t numpages_per_thread;
-    size_t size_per_thread;
+    size_t numpages_per_thread, leftover;
     char *addr = area;
     int i = 0;
 
     memset_thread_failed = false;
+    threads_created_flag = false;
     memset_num_threads = get_memset_num_threads(smp_cpus);
     memset_thread = g_new0(MemsetThread, memset_num_threads);
-    numpages_per_thread = (numpages / memset_num_threads);
-    size_per_thread = (hpagesize * numpages_per_thread);
+    numpages_per_thread = numpages / memset_num_threads;
+    leftover = numpages % memset_num_threads;
     for (i = 0; i < memset_num_threads; i++) {
         memset_thread[i].addr = addr;
-        memset_thread[i].numpages = (i == (memset_num_threads - 1)) ?
-                                    numpages : numpages_per_thread;
+        memset_thread[i].numpages = numpages_per_thread + (i < leftover);
         memset_thread[i].hpagesize = hpagesize;
         qemu_thread_create(&memset_thread[i].pgthread, "touch_pages",
                            do_touch_pages, &memset_thread[i],
                            QEMU_THREAD_JOINABLE);
-        addr += size_per_thread;
-        numpages -= numpages_per_thread;
+        addr += memset_thread[i].numpages * hpagesize;
     }
+    threads_created_flag = true;
+    qemu_cond_broadcast(&page_cond);
+
     for (i = 0; i < memset_num_threads; i++) {
         qemu_thread_join(&memset_thread[i].pgthread);
     }