> assert(piecetwosize <= holesize);
>
> piecetwosize = MIN(above_4g_mem_size, piecetwosize);
> if ((above_4g_mem_size - piecetwosize) > 0) {
> memory_region_init_alias(ram_above_4g, NULL, "ram-above-4g",
> ram, 0x100000000ULL,
> above_4g_mem_size - piecetwosize);
> memory_region_add_subregion(system_memory, 0x100000000ULL,
> ram_above_4g);
> } else {
> g_free(ram_above_4g);
> }
> memory_region_init_alias(ram_above_4g_piecetwo, NULL,
> "ram-above-4g-piecetwo", ram,
> 0x100000000ULL - holesize, piecetwosize);
> memory_region_add_subregion(system_memory,
> 0x100000000ULL +
> above_4g_mem_size - piecetwosize,
> ram_above_4g_piecetwo);
There is still a small problem in that the 2MB rounding must not be
done for old machine types.
I did a really careful review of the code and everything else looks okay
to me. However, it grew by accretion from v1 and now it took me really a
long time to figure it out... I adjusted it a bit and the result seems
easier to understand to me.
Here's the hw/i386/pc.c part of the patch (the patch from v6 is unreadable):
diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index 12c436e..f2fd138 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -1156,8 +1156,10 @@ FWCfgState *pc_memory_init(MemoryRegion *system_memory,
{
int linux_boot, i;
MemoryRegion *ram, *option_rom_mr;
- MemoryRegion *ram_below_4g, *ram_above_4g;
+ MemoryRegion *ram_below_4g, *ram_above_4g_pieceone, *ram_above_4g_piecetwo;
FWCfgState *fw_cfg;
+ uint64_t holesize, pieceonesize, piecetwosize;
+ uint64_t memsize, align_offset;
linux_boot = (kernel_filename != NULL);
@@ -1165,26 +1167,74 @@ FWCfgState *pc_memory_init(MemoryRegion *system_memory,
* aliases to address portions of it, mostly for backwards compatibility
* with older qemus that used qemu_ram_alloc().
*/
+ memsize = below_4g_mem_size + above_4g_mem_size;
+ holesize = 0x100000000ULL - below_4g_mem_size;
+
+ /* If 1GB hugepages are used to back guest RAM, we want the
+ * physical address 4GB to map to 4GB in the RAM, so that
+ * memory beyond 4GB is aligned on a 1GB boundary, at the
+ * host physical address space. Thus, the ram block range
+ * [holestart, 4GB] is mapped to the last holesize bytes of RAM:
+ *
+ * 0 h 4G memsize-holesize
+ *
+ * contiguous-ram-block [xxxxxx][yyy][zzzzz]
+ * '-----------.
+ * guest-addr-space [xxxxxx] [zzzzz][yyy]
+ *
+ * This is only done in new-enough machine types, and of course
+ * it is only necessary if the [zzzzz] block exists at all.
+ */
+ if (guest_info->gb_align && above_4g_mem_size > holesize) {
+ /* Round the allocation up to 2 MB to use more hugepages.
+ * Remove the slack from the [yyy] piece so that pieceonesize
+ * (and thus the start of piecetwo) remains aligned.
+ */
+ align_offset = ROUND_UP(memsize, 1UL << 21) - memsize;
+ piecetwosize = holesize - align_offset;
+ } else {
+ /* There's no "piece one", all memory above 4G starts
+ * at below_4g_mem_size in the RAM block. Also no need
+ * to align anything.
+ */
+ align_offset = 0;
+ piecetwosize = above_4g_mem_size;
+ }
+
ram = g_malloc(sizeof(*ram));
- memory_region_init_ram(ram, NULL, "pc.ram",
- below_4g_mem_size + above_4g_mem_size);
+ memory_region_init_ram(ram, NULL, "pc.ram", memsize + align_offset);
vmstate_register_ram_global(ram);
*ram_memory = ram;
+
ram_below_4g = g_malloc(sizeof(*ram_below_4g));
memory_region_init_alias(ram_below_4g, NULL, "ram-below-4g", ram,
0, below_4g_mem_size);
memory_region_add_subregion(system_memory, 0, ram_below_4g);
+
+ pieceonesize = above_4g_mem_size - piecetwosize;
+ if (pieceonesize) {
+ ram_above_4g_pieceone = g_malloc(sizeof(*ram_above_4g_pieceone));
+ memory_region_init_alias(ram_above_4g_pieceone, NULL,
+ "ram-above-4g-pieceone", ram,
+ 0x100000000ULL, pieceonesize);
+ memory_region_add_subregion(system_memory, 0x100000000ULL,
+ ram_above_4g_pieceone);
+ }
+ if (piecetwosize) {
+ 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,
+ below_4g_mem_size, piecetwosize);
+ memory_region_add_subregion(system_memory,
+ 0x100000000ULL + pieceonesize,
+ ram_above_4g_piecetwo);
+ }
+
e820_add_entry(0, below_4g_mem_size, E820_RAM);
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,
- ram_above_4g);
e820_add_entry(0x100000000ULL, above_4g_mem_size, E820_RAM);
}
-
/* Initialize PC system firmware */
pc_system_firmware_init(rom_memory, guest_info->isapc_ram_fw);
Tests:
-m 3585 (without gb_align)
0000000100000000-00000001000fffff (prio 0, RW): alias ram-above-4g-piecetwo
@pc.ram 00000000e0000000-00000000e00fffff
-m 4096 (without gb_align)
0000000100000000-000000011fffffff (prio 0, RW): alias ram-above-4g-piecetwo
@pc.ram 00000000e0000000-00000000ffffffff
-m 4097 (without gb_align)
0000000100000000-00000001200fffff (prio 0, RW): alias ram-above-4g @pc.ram
00000000e0000000-00000001000fffff
-m 4097 (with gb_align, both high regions 2MB aligned, unused MB of RAM at
0xfff00000)
0000000100000000-00000001001fffff (prio 0, RW): alias ram-above-4g @pc.ram
0000000100000000-00000001001fffff
0000000100200000-00000001200fffff (prio 0, RW): alias ram-above-4g-piecetwo
@pc.ram 00000000e0000000-00000000ffefffff
-m 8192 (without gb_align)
0000000100000000-000000021fffffff (prio 0, RW): alias ram-above-4g-piecetwo
@pc.ram 00000000e0000000-00000001ffffffff
-m 8192 (with gb_align)
0000000100000000-00000001ffffffff (prio 0, RW): alias ram-above-4g @pc.ram
0000000100000000-00000001ffffffff
0000000200000000-000000021fffffff (prio 0, RW): alias ram-above-4g-piecetwo
@pc.ram 00000000e0000000-00000000ffffffff
-m 8193 (without gb_align)
0000000100000000-00000002200fffff (prio 0, RW): alias ram-above-4g-piecetwo
@pc.ram 00000000e0000000-00000002000fffff
-m 8193 (with gb_align)
0000000100000000-00000002001fffff (prio 0, RW): alias ram-above-4g @pc.ram
0000000100000000-00000002001fffff
0000000200200000-00000002200fffff (prio 0, RW): alias ram-above-4g-piecetwo
@pc.ram 00000000e0000000-00000000ffefffff
Ok to apply this version?
Paolo
