Re: [Qemu-devel] [PATCH v2] migration: ram_handle_compressed

[Michael R. Hines]

On 09/20/2013 03:51 AM, Isaku Yamahata wrote:
> ram_handle_compressed() should be aware of size > TARGET_PAGE_SIZE.
> migration-rdma can call it with larger size.
>
> Signed-off-by: Isaku Yamahata <address@hidden>
> ---
> changes v1 -> v2:
> - don't loop
> ---
>   arch_init.c |   11 ++++++-----
>   1 file changed, 6 insertions(+), 5 deletions(-)
>
> diff --git a/arch_init.c b/arch_init.c
> index e47e139..ab466fc 100644
> --- a/arch_init.c
> +++ b/arch_init.c
> @@ -844,13 +844,14 @@ static inline void *host_from_stream_offset(QEMUFile *f,
>    */
>   void ram_handle_compressed(void *host, uint8_t ch, uint64_t size)
>   {
> -    if (ch != 0 || !is_zero_page(host)) {
> +    if (ch != 0 || buffer_find_nonzero_offset(host, size) != size) {
>           memset(host, ch, size);
>   #ifndef _WIN32
> -        if (ch == 0 &&
> -            (!kvm_enabled() || kvm_has_sync_mmu()) &&
> -            getpagesize() <= TARGET_PAGE_SIZE) {
> -            qemu_madvise(host, TARGET_PAGE_SIZE, QEMU_MADV_DONTNEED);
> +        if (ch == 0 && (!kvm_enabled() || kvm_has_sync_mmu())) {
> +            size = size & ~(getpagesize() - 1);
> +            if (size > 0) {
> +                qemu_madvise(host, size, QEMU_MADV_DONTNEED);
> +            }
>           }
>   #endif
>       }

NACK.

Why don't you modify the is_zero_page function *itself*?

This seems like an overly complicated solution - just modify the
is_zero_page function to pass along the size parameter and let
buffer_find_nonzero_offset() run the same code.

Fix the original problem - don't breakup the memory into smaller
pieces.....

- Michael