[Qemu-devel] [PATCH v11 2/3] util/mmap-alloc: support MAP_SYNC in qemu_ram_mmap()

[Zhang, Yi]

From: Zhang Yi <address@hidden>

When a file supporting DAX is used as vNVDIMM backend, mmap it with
MAP_SYNC flag in addition which can ensure file system metadata
synced in each guest writes to the backend file, without other QEMU
actions (e.g., periodic fsync() by QEMU).

Current, We have below different possible use cases:

1. pmem=on is set, shared=on is set, MAP_SYNC supported:
   a: backend is a dax supporting file.
    - MAP_SYNC will active.
   b: backend is not a dax supporting file.
    - mmap will trigger a warning. then MAP_SYNC flag will be ignored

2. The rest of cases:
   - we will never pass the MAP_SYNC to mmap2

Signed-off-by: Haozhong Zhang <address@hidden>
Signed-off-by: Zhang Yi <address@hidden>
---
 include/qemu/osdep.h | 21 +++++++++++++++++++++
 util/mmap-alloc.c    | 28 +++++++++++++++++++++++++++-
 2 files changed, 48 insertions(+), 1 deletion(-)

diff --git a/include/qemu/osdep.h b/include/qemu/osdep.h
index 457d24e..96209bb 100644
--- a/include/qemu/osdep.h
+++ b/include/qemu/osdep.h
@@ -419,6 +419,27 @@ void qemu_anon_ram_free(void *ptr, size_t size);
 #  define QEMU_VMALLOC_ALIGN getpagesize()
 #endif
 
+/*
+ * MAP_SHARED_VALIDATE and MAP_SYNC are introduced in Linux kernel
+ * 4.15, so they may not be defined when compiling on older kernels.
+ */
+#ifdef CONFIG_LINUX
+
+#include <linux/mman.h>
+
+#ifndef MAP_SYNC
+#define MAP_SYNC 0x80000
+#endif
+
+#ifndef MAP_SHARED_VALIDATE
+#define MAP_SHARED_VALIDATE 0x03
+#endif
+
+#else  /* !CONFIG_LINUX */
+#define MAP_SYNC              0x0
+#define MAP_SHARED_VALIDATE   0x0
+#endif /* CONFIG_LINUX */
+
 #ifdef CONFIG_POSIX
 struct qemu_signalfd_siginfo {
     uint32_t ssi_signo;   /* Signal number */
diff --git a/util/mmap-alloc.c b/util/mmap-alloc.c
index 97bbeed..2c86ad2 100644
--- a/util/mmap-alloc.c
+++ b/util/mmap-alloc.c
@@ -101,6 +101,7 @@ void *qemu_ram_mmap(int fd,
 #else
     void *ptr = mmap(0, total, PROT_NONE, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
 #endif
+    int mmap_xflags = 0;
     size_t offset;
     void *ptr1;
 
@@ -111,13 +112,38 @@ void *qemu_ram_mmap(int fd,
     assert(is_power_of_2(align));
     /* Always align to host page size */
     assert(align >= getpagesize());
+    if (shared && is_pmem) {
+        mmap_xflags = MAP_SYNC | MAP_SHARED_VALIDATE;
+    }
 
     offset = QEMU_ALIGN_UP((uintptr_t)ptr, align) - (uintptr_t)ptr;
+retry_mmap:
     ptr1 = mmap(ptr + offset, size, PROT_READ | PROT_WRITE,
                 MAP_FIXED |
                 (fd == -1 ? MAP_ANONYMOUS : 0) |
-                (shared ? MAP_SHARED : MAP_PRIVATE),
+                (shared ? MAP_SHARED : MAP_PRIVATE) | mmap_xflags,
                 fd, 0);
+
+    /* if map failed with MAP_SHARED_VALIDATE | MAP_SYNC,
+     * we try with MAP_SHARED_VALIDATE without MAP_SYNC
+     */
+    if (ptr1 == MAP_FAILED &&
+        mmap_xflags == (MAP_SYNC | MAP_SHARED_VALIDATE)) {
+        if (errno == ENOTSUP) {
+            perror("failed to validate with mapping flags");
+        }
+        mmap_xflags = MAP_SHARED_VALIDATE;
+        goto retry_mmap;
+    }
+    /* MAP_SHARED_VALIDATE flag is available since Linux 4.15
+     * Test only with MAP_SHARED_VALIDATE flag for compatibility.
+     * Then ignore the MAP_SHARED_VALIDATE flag and retry again
+     */
+    if (mmap_xflags == MAP_SHARED_VALIDATE &&
+        ptr1 == MAP_FAILED) {
+            mmap_xflags &= ~MAP_SHARED_VALIDATE;
+            goto retry_mmap;
+    }
     if (ptr1 == MAP_FAILED) {
         munmap(ptr, total);
         return MAP_FAILED;
-- 
2.7.4