Merge remote-tracking branch 'remotes/mst/tags/for_upstream' into staging

vhost, pc, virtio features, fixes, cleanups

New features:
    VT-d support for devices behind a bridge
    vhost-user migration support

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

# gpg: Signature made Thu 22 Oct 2015 12:39:19 BST using RSA key ID D28D5469
# gpg: Good signature from "Michael S. Tsirkin <mst@kernel.org>"
# gpg:                 aka "Michael S. Tsirkin <mst@redhat.com>"

* remotes/mst/tags/for_upstream: (37 commits)
  hw/isa/lpc_ich9: inject the SMI on the VCPU that is writing to APM_CNT
  i386: keep cpu_model field in MachineState uptodate
  vhost: set the correct queue index in case of migration with multiqueue
  piix: fix resource leak reported by Coverity
  seccomp: add memfd_create to whitelist
  vhost-user-test: check ownership during migration
  vhost-user-test: add live-migration test
  vhost-user-test: learn to tweak various qemu arguments
  vhost-user-test: wrap server in TestServer struct
  vhost-user-test: remove useless static check
  vhost-user-test: move wait_for_fds() out
  vhost: add migration block if memfd failed
  vhost-user: use an enum helper for features mask
  vhost user: add rarp sending after live migration for legacy guest
  vhost user: add support of live migration
  net: add trace_vhost_user_event
  vhost-user: document migration log
  vhost: use a function for each call
  vhost-user: add a migration blocker
  vhost-user: send log shm fd along with log_base
  ...

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

4 files changed, 247 insertions, 27 deletions

diff --git a/util/Makefile.objs b/util/Makefile.objs
index 1363d1fce8..d7cc39907f 100644
--- a/util/Makefile.objs
+++ b/util/Makefile.objs
@@ -1,13 +1,20 @@
 util-obj-y = osdep.o cutils.o unicode.o qemu-timer-common.o
-util-obj-$(CONFIG_WIN32) += oslib-win32.o qemu-thread-win32.o event_notifier-win32.o
-util-obj-$(CONFIG_POSIX) += oslib-posix.o qemu-thread-posix.o event_notifier-posix.o qemu-openpty.o
+util-obj-$(CONFIG_POSIX) += compatfd.o
+util-obj-$(CONFIG_POSIX) += event_notifier-posix.o
+util-obj-$(CONFIG_POSIX) += mmap-alloc.o
+util-obj-$(CONFIG_POSIX) += oslib-posix.o
+util-obj-$(CONFIG_POSIX) += qemu-openpty.o
+util-obj-$(CONFIG_POSIX) += qemu-thread-posix.o
+util-obj-$(CONFIG_WIN32) += event_notifier-win32.o
+util-obj-$(CONFIG_POSIX) += memfd.o
+util-obj-$(CONFIG_WIN32) += oslib-win32.o
+util-obj-$(CONFIG_WIN32) += qemu-thread-win32.o
 util-obj-y += envlist.o path.o module.o
 util-obj-$(call lnot,$(CONFIG_INT128)) += host-utils.o
 util-obj-y += bitmap.o bitops.o hbitmap.o
 util-obj-y += fifo8.o
 util-obj-y += acl.o
 util-obj-y += error.o qemu-error.o
-util-obj-$(CONFIG_POSIX) += compatfd.o
 util-obj-y += id.o
 util-obj-y += iov.o qemu-config.o qemu-sockets.o uri.o notify.o
 util-obj-y += qemu-option.o qemu-progress.o
diff --git a/util/memfd.c b/util/memfd.c
new file mode 100644
index 0000000000..7c406914c5
--- /dev/null
+++ b/util/memfd.c
@@ -0,0 +1,162 @@
+/*
+ * memfd.c
+ *
+ * Copyright (c) 2015 Red Hat, Inc.
+ *
+ * QEMU library functions on POSIX which are shared between QEMU and
+ * the QEMU tools.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#include "qemu/osdep.h"
+
+#include <glib.h>
+#include <glib/gprintf.h>
+
+#include <sys/mman.h>
+
+#include "qemu/memfd.h"
+
+#ifdef CONFIG_MEMFD
+#include <sys/memfd.h>
+#elif defined CONFIG_LINUX
+#include <sys/syscall.h>
+#include <asm/unistd.h>
+
+static int memfd_create(const char *name, unsigned int flags)
+{
+#ifdef __NR_memfd_create
+    return syscall(__NR_memfd_create, name, flags);
+#else
+    return -1;
+#endif
+}
+#endif
+
+#ifndef MFD_CLOEXEC
+#define MFD_CLOEXEC 0x0001U
+#endif
+
+#ifndef MFD_ALLOW_SEALING
+#define MFD_ALLOW_SEALING 0x0002U
+#endif
+
+/*
+ * This is a best-effort helper for shared memory allocation, with
+ * optional sealing. The helper will do his best to allocate using
+ * memfd with sealing, but may fallback on other methods without
+ * sealing.
+ */
+void *qemu_memfd_alloc(const char *name, size_t size, unsigned int seals,
+                       int *fd)
+{
+    void *ptr;
+    int mfd = -1;
+
+    *fd = -1;
+
+#ifdef CONFIG_LINUX
+    if (seals) {
+        mfd = memfd_create(name, MFD_ALLOW_SEALING | MFD_CLOEXEC);
+    }
+
+    if (mfd == -1) {
+        /* some systems have memfd without sealing */
+        mfd = memfd_create(name, MFD_CLOEXEC);
+        seals = 0;
+    }
+#endif
+
+    if (mfd != -1) {
+        if (ftruncate(mfd, size) == -1) {
+            perror("ftruncate");
+            close(mfd);
+            return NULL;
+        }
+
+        if (seals && fcntl(mfd, F_ADD_SEALS, seals) == -1) {
+            perror("fcntl");
+            close(mfd);
+            return NULL;
+        }
+    } else {
+        const char *tmpdir = g_get_tmp_dir();
+        gchar *fname;
+
+        fname = g_strdup_printf("%s/memfd-XXXXXX", tmpdir);
+        mfd = mkstemp(fname);
+        unlink(fname);
+        g_free(fname);
+
+        if (mfd == -1) {
+            perror("mkstemp");
+            return NULL;
+        }
+
+        if (ftruncate(mfd, size) == -1) {
+            perror("ftruncate");
+            close(mfd);
+            return NULL;
+        }
+    }
+
+    ptr = mmap(0, size, PROT_READ | PROT_WRITE, MAP_SHARED, mfd, 0);
+    if (ptr == MAP_FAILED) {
+        perror("mmap");
+        close(mfd);
+        return NULL;
+    }
+
+    *fd = mfd;
+    return ptr;
+}
+
+void qemu_memfd_free(void *ptr, size_t size, int fd)
+{
+    if (ptr) {
+        munmap(ptr, size);
+    }
+
+    if (fd != -1) {
+        close(fd);
+    }
+}
+
+enum {
+    MEMFD_KO,
+    MEMFD_OK,
+    MEMFD_TODO
+};
+
+bool qemu_memfd_check(void)
+{
+    static int memfd_check = MEMFD_TODO;
+
+    if (memfd_check == MEMFD_TODO) {
+        int fd;
+        void *ptr;
+
+        ptr = qemu_memfd_alloc("test", 4096, 0, &fd);
+        memfd_check = ptr ? MEMFD_OK : MEMFD_KO;
+        qemu_memfd_free(ptr, 4096, fd);
+    }
+
+    return memfd_check == MEMFD_OK;
+}
diff --git a/util/mmap-alloc.c b/util/mmap-alloc.c
new file mode 100644
index 0000000000..13942694cc
--- /dev/null
+++ b/util/mmap-alloc.c
@@ -0,0 +1,71 @@
+/*
+ * Support for RAM backed by mmaped host memory.
+ *
+ * Copyright (c) 2015 Red Hat, Inc.
+ *
+ * Authors:
+ *  Michael S. Tsirkin <mst@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or
+ * later.  See the COPYING file in the top-level directory.
+ */
+#include <qemu/mmap-alloc.h>
+#include <sys/types.h>
+#include <sys/mman.h>
+#include <assert.h>
+
+void *qemu_ram_mmap(int fd, size_t size, size_t align, bool shared)
+{
+    /*
+     * Note: this always allocates at least one extra page of virtual address
+     * space, even if size is already aligned.
+     */
+    size_t total = size + align;
+    void *ptr = mmap(0, total, PROT_NONE, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+    size_t offset = QEMU_ALIGN_UP((uintptr_t)ptr, align) - (uintptr_t)ptr;
+    void *ptr1;
+
+    if (ptr == MAP_FAILED) {
+        return NULL;
+    }
+
+    /* Make sure align is a power of 2 */
+    assert(!(align & (align - 1)));
+    /* Always align to host page size */
+    assert(align >= getpagesize());
+
+    ptr1 = mmap(ptr + offset, size, PROT_READ | PROT_WRITE,
+                MAP_FIXED |
+                (fd == -1 ? MAP_ANONYMOUS : 0) |
+                (shared ? MAP_SHARED : MAP_PRIVATE),
+                fd, 0);
+    if (ptr1 == MAP_FAILED) {
+        munmap(ptr, total);
+        return NULL;
+    }
+
+    ptr += offset;
+    total -= offset;
+
+    if (offset > 0) {
+        munmap(ptr - offset, offset);
+    }
+
+    /*
+     * Leave a single PROT_NONE page allocated after the RAM block, to serve as
+     * a guard page guarding against potential buffer overflows.
+     */
+    if (total > size + getpagesize()) {
+        munmap(ptr + size + getpagesize(), total - size - getpagesize());
+    }
+
+    return ptr;
+}
+
+void qemu_ram_munmap(void *ptr, size_t size)
+{
+    if (ptr) {
+        /* Unmap both the RAM block and the guard page */
+        munmap(ptr, size + getpagesize());
+    }
+}
diff --git a/util/oslib-posix.c b/util/oslib-posix.c
index 40249183e6..914cef5c2c 100644
--- a/util/oslib-posix.c
+++ b/util/oslib-posix.c
@@ -72,6 +72,8 @@ extern int daemon(int, int);
 #include <sys/sysctl.h>
 #endif
 
+#include <qemu/mmap-alloc.h>
+
 int qemu_get_thread_id(void)
 {
 #if defined(__linux__)
@@ -128,10 +130,7 @@ void *qemu_memalign(size_t alignment, size_t size)
 void *qemu_anon_ram_alloc(size_t size, uint64_t *alignment)
 {
     size_t align = QEMU_VMALLOC_ALIGN;
-    size_t total = size + align;
-    void *ptr = mmap(0, total, PROT_NONE, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
-    size_t offset = QEMU_ALIGN_UP((uintptr_t)ptr, align) - (uintptr_t)ptr;
-    void *ptr1;
+    void *ptr = qemu_ram_mmap(-1, size, align, false);
 
     if (ptr == MAP_FAILED) {
         return NULL;
@@ -141,23 +140,6 @@ void *qemu_anon_ram_alloc(size_t size, uint64_t *alignment)
         *alignment = align;
     }
 
-    ptr1 = mmap(ptr + offset, size, PROT_READ | PROT_WRITE,
-                MAP_FIXED | MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
-    if (ptr1 == MAP_FAILED) {
-        munmap(ptr, total);
-        return NULL;
-    }
-
-    ptr += offset;
-    total -= offset;
-
-    if (offset > 0) {
-        munmap(ptr - offset, offset);
-    }
-    if (total > size + getpagesize()) {
-        munmap(ptr + size + getpagesize(), total - size - getpagesize());
-    }
-
     trace_qemu_anon_ram_alloc(size, ptr);
     return ptr;
 }
@@ -171,9 +153,7 @@ void qemu_vfree(void *ptr)
 void qemu_anon_ram_free(void *ptr, size_t size)
 {
     trace_qemu_anon_ram_free(ptr, size);
-    if (ptr) {
-        munmap(ptr, size + getpagesize());
-    }
+    qemu_ram_munmap(ptr, size);
 }
 
 void qemu_set_block(int fd)