Il 24/10/2013 22:12, Marcelo Tosatti ha scritto:
> Align guest physical address and host physical address
> beyond guest 4GB on a 1GB boundary, in case hugetlbfs is used.
>
> Otherwise 1GB TLBs cannot be cached for the range.
>
> Signed-off-by: Marcelo Tosatti <mtosa...@redhat.com>
>
> Index: qemu/hw/i386/pc.c
> ===================================================================
> --- qemu.orig/hw/i386/pc.c
> +++ qemu/hw/i386/pc.c
> @@ -1116,8 +1116,9 @@ FWCfgState *pc_memory_init(MemoryRegion
> {
> int linux_boot, i;
> MemoryRegion *ram, *option_rom_mr;
> - MemoryRegion *ram_below_4g, *ram_above_4g;
> + MemoryRegion *ram_below_4g, *ram_above_4g, *ram_above_4g_piecetwo;
> FWCfgState *fw_cfg;
> + unsigned long hpagesize;
>
> linux_boot = (kernel_filename != NULL);
>
> @@ -1129,6 +1130,7 @@ FWCfgState *pc_memory_init(MemoryRegion
> memory_region_init_ram(ram, NULL, "pc.ram",
> below_4g_mem_size + above_4g_mem_size);
> vmstate_register_ram_global(ram);
> + hpagesize = qemu_get_ram_hpagesize(ram->ram_addr);
> *ram_memory = ram;
> ram_below_4g = g_malloc(sizeof(*ram_below_4g));
> memory_region_init_alias(ram_below_4g, NULL, "ram-below-4g", ram,
> @@ -1136,10 +1138,46 @@ FWCfgState *pc_memory_init(MemoryRegion
> memory_region_add_subregion(system_memory, 0, ram_below_4g);
> if (above_4g_mem_size > 0) {
> ram_above_4g = g_malloc(sizeof(*ram_above_4g));
> - memory_region_init_alias(ram_above_4g, NULL, "ram-above-4g", ram,
> - below_4g_mem_size, above_4g_mem_size);
> - memory_region_add_subregion(system_memory, 0x100000000ULL,
> +
> + /*
> + *
> + * If 1GB hugepages are used to back guest RAM, map guest address
> + * space in the range [ramsize,ramsize+holesize] to the ram block
> + * range [holestart, 4GB]
> + *
> + * 0 h 4G
> [ramsize,ramsize+holesize]
> + *
> + * guest-addr-space [ ] [ ][xxx]
> + * /----------/
> + * contiguous-ram-block [ ][xxx][ ]
> + *
> + * So that memory beyond 4GB is aligned on a 1GB boundary,
> + * at the host physical address space.
> + *
> + */
> + if (hpagesize == (1<<30)) {
> + unsigned long holesize = 0x100000000ULL - below_4g_mem_size;
> +
> + memory_region_init_alias(ram_above_4g, NULL, "ram-above-4g", ram,
> + 0x100000000ULL,
> + above_4g_mem_size - holesize);
> + memory_region_add_subregion(system_memory, 0x100000000ULL,
> + ram_above_4g);
> +
> + ram_above_4g_piecetwo = g_malloc(sizeof(*ram_above_4g_piecetwo));
> + memory_region_init_alias(ram_above_4g_piecetwo, NULL,
> + "ram-above-4g-piecetwo", ram,
> + 0x100000000ULL - holesize, holesize);
> + memory_region_add_subregion(system_memory,
> + 0x100000000ULL +
> + above_4g_mem_size - holesize,
> + ram_above_4g_piecetwo);
Why break it in two? You can just allocate extra holesize bytes in the
"ram" MemoryRegion, and not map the part that corresponds to
[0x100000000ULL - holesize, 0x100000000ULL).
Also, as Peter said this cannot depend on host considerations. Just do
it unconditionally, but only for new machine types (pc-1.8 and q35-1.8,
since unfortunately we're too close to hard freeze).
Paolo
> + } else {
> + memory_region_init_alias(ram_above_4g, NULL, "ram-above-4g", ram,
> + below_4g_mem_size, above_4g_mem_size);
> + memory_region_add_subregion(system_memory, 0x100000000ULL,
> ram_above_4g);
> + }
> }
