Re: [Qemu-devel] [PATCH V9 4/6] util/mmap-alloc: support MAP_SYNC in qemu_ram_mmap()

[Michael S. Tsirkin]

On Wed, Jan 16, 2019 at 04:10:58PM +0800, Zhang Yi wrote:
> 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).
> 
> Signed-off-by: Haozhong Zhang <address@hidden>
> Signed-off-by: Zhang Yi <address@hidden>
> ---
>  include/qemu/mmap-alloc.h |  1 +
>  include/qemu/osdep.h      | 16 ++++++++++++++++
>  util/mmap-alloc.c         |  7 ++++++-
>  3 files changed, 23 insertions(+), 1 deletion(-)
> 
> diff --git a/include/qemu/mmap-alloc.h b/include/qemu/mmap-alloc.h
> index 6fe6ed4..a95d91c 100644
> --- a/include/qemu/mmap-alloc.h
> +++ b/include/qemu/mmap-alloc.h
> @@ -18,6 +18,7 @@ size_t qemu_mempath_getpagesize(const char *mem_path);
>   *  @flags: specifies additional properties of the mapping, which can be one 
> or
>   *          bit-or of following values
>   *          - RAM_SHARED: mmap with MAP_SHARED flag
> + *          - RAM_PMEM: mmap with MAP_SYNC flag
>   *          Other bits are ignored.
>   *
>   * Return:
> diff --git a/include/qemu/osdep.h b/include/qemu/osdep.h
> index 457d24e..27a6bfe 100644
> --- a/include/qemu/osdep.h
> +++ b/include/qemu/osdep.h
> @@ -419,6 +419,22 @@ 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 <asm-generic/mman.h>

I suspect this is a wrong way to pull in this header.

You are normally supposed to use
       #include <linux/mman.h>

but see below.


> +
> +#ifndef MAP_SYNC
> +#define MAP_SYNC 0x0
> +#endif

Oh that's bad.

So if you run with a new kernel but
your installed headers are old, you get MAP_SYNC 0
and no persistence transparently with no warning.



> +
> +#else  /* !CONFIG_LINUX */
> +#define MAP_SYNC              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 8f0a740..cba961c 100644
> --- a/util/mmap-alloc.c
> +++ b/util/mmap-alloc.c
> @@ -99,6 +99,8 @@ void *qemu_ram_mmap(int fd, size_t size, size_t align, 
> uint32_t flags)
>      void *ptr = mmap(0, total, PROT_NONE, MAP_ANONYMOUS | MAP_PRIVATE, -1, 
> 0);
>  #endif
>      bool shared = flags & RAM_SHARED;
> +    bool is_pmem = flags & RAM_PMEM;
> +    int mmap_xflags = 0;
>      size_t offset;
>      void *ptr1;
>  
> @@ -109,12 +111,15 @@ void *qemu_ram_mmap(int fd, size_t size, size_t align, 
> uint32_t flags)
>      assert(is_power_of_2(align));
>      /* Always align to host page size */
>      assert(align >= getpagesize());
> +    if (shared && is_pmem) {
> +        mmap_xflags |= MAP_SYNC;
> +    }
>  
>      offset = QEMU_ALIGN_UP((uintptr_t)ptr, align) - (uintptr_t)ptr;
>      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 (ptr1 == MAP_FAILED) {
>          munmap(ptr, total);
> -- 
> 2.7.4