Re: [PATCH] qemu-kvm: Speed up of the dirty-bitmap-traveling

[OHMURA Kei <ohmura.kei@lab.ntt.co.jp>]

> Please reuse the changelog when reposing a patch, this makes it easier
> for me to apply it.

Thanks.  Will follow it from next time.


> Should be a host long size, not guest. This will fail when running a
> 32-bit qemu-system-x86_64 binary.

Sorry. That was our mistake.


> Instead of using a nested loop if bitmap_ul[i] != 0, it is possible to
> use just a single loop (while (c>  0)), and process a long's worth of data.
>
> The only trickery is with big endian hosts, where the conversion from
> bit number to page number is a bit complicated.

To convert the bitmap from big endian to little endian, le_bswap macro in
bswap.h seems useful, which is now undefined.  What do you think about this
approach?

This is an example bitmap-traveling code using le_bswap:
     /* 
      * bitmap-traveling is faster than memory-traveling (for addr...) 
      * especially when most of the memory is not dirty.
      */
     for (i = 0; i < len; i++) {
        if (bitmap_ul[i] != 0) {
            c = le_bswap(bitmap_ul[i], HOST_LONG_BITS);
            while (c > 0) {
                j = ffsl(c) - 1;
                c &= ~(1ul << j);
                page_number = i * HOST_LONG_BITS + j;
                addr1 = page_number * TARGET_PAGE_SIZE;
                addr = offset + addr1;
                ram_addr = cpu_get_physical_page_desc(addr);
                cpu_physical_memory_set_dirty(ram_addr);
            }
         }
     }