Re: [PATCH 3/3] migration: Pre-fault memory before starting background snasphot

[David Hildenbrand <david@redhat.com>]

> +/*
> + * ram_block_populate_pages: populate memory in the RAM block by reading
> + *   an integer from the beginning of each page.
> + *
> + * Since it's solely used for userfault_fd WP feature, here we just
> + *   hardcode page size to TARGET_PAGE_SIZE.
> + *
> + * @bs: RAM block to populate
> + */
> +volatile int ram_block_populate_pages__tmp;
> +static void ram_block_populate_pages(RAMBlock *bs)
> +{
> +    ram_addr_t offset = 0;
> +    int tmp = 0;
> +
> +    for (char *ptr = (char *) bs->host; offset < bs->used_length;
> +            ptr += TARGET_PAGE_SIZE, offset += TARGET_PAGE_SIZE) {

You'll want qemu_real_host_page_size instead of TARGET_PAGE_SIZE

> +        /* Try to do it without memory writes */
> +        tmp += *(volatile int *) ptr;
> +    }


The following is slightly simpler and doesn't rely on volatile semantics [1].
Should work on any arch I guess.

static void ram_block_populate_pages(RAMBlock *bs)
{
     char *ptr = (char *) bs->host;
     ram_addr_t offset;

     for (offset = 0; offset < bs->used_length;
          offset += qemu_real_host_page_size) {
	char tmp = *(volatile char *)(ptr + offset)

	/* Don't optimize the read out. */
	asm volatile ("" : "+r" (tmp));
}

Compiles to

     for (offset = 0; offset < bs->used_length;
     316d:       48 8b 4b 30             mov    0x30(%rbx),%rcx
     char *ptr = (char *) bs->host;
     3171:       48 8b 73 18             mov    0x18(%rbx),%rsi
     for (offset = 0; offset < bs->used_length;
     3175:       48 85 c9                test   %rcx,%rcx
     3178:       74 ce                   je     3148 <ram_write_tracking_prepare+0x58>
          offset += qemu_real_host_page_size) {
     317a:       48 8b 05 00 00 00 00    mov    0x0(%rip),%rax        # 3181 <ram_write_tracking_prepare+0x91>
     3181:       48 8b 38                mov    (%rax),%rdi
     3184:       0f 1f 40 00             nopl   0x0(%rax)
         char tmp = *(volatile char *)(ptr + offset);
     3188:       48 8d 04 16             lea    (%rsi,%rdx,1),%rax
     318c:       0f b6 00                movzbl (%rax),%eax
          offset += qemu_real_host_page_size) {
     318f:       48 01 fa                add    %rdi,%rdx
     for (offset = 0; offset < bs->used_length;
     3192:       48 39 ca                cmp    %rcx,%rdx
     3195:       72 f1                   jb     3188 <ram_write_tracking_prepare+0x98>


[1] https://programfan.github.io/blog/2015/04/27/prevent-gcc-optimize-away-code/


I'll send patches soon to take care of virtio-mem via RamDiscardManager -
to skip populating the parts that are supposed to remain discarded and not migrated.
Unfortunately, the RamDiscardManager patches are still stuck waiting for
acks ... and now we're in soft-freeze.

-- 
Thanks,

David / dhildenb