exec: optimize phys_page_set_level
phys_page_set_level is writing zeroes to a struct that has just been
filled in by phys_map_node_alloc. Instead, tell phys_map_node_alloc
whether to fill in the page "as a leaf" or "as a non-leaf".
memcpy is faster than struct assignment, which copies each bitfield
individually. A compiler bug (https://gcc.gnu.org/PR66391), and
small memcpys like this one are special-cased anyway, and optimized
to a register move, so just use the memcpy.
This cuts the cost of phys_page_set_level from 25% to 5% when
booting qboot.
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
diff --git a/exec.c b/exec.c
index e19ab22..fc8d05d 100644
--- a/exec.c
+++ b/exec.c
@@ -173,17 +173,22 @@
}
}
-static uint32_t phys_map_node_alloc(PhysPageMap *map)
+static uint32_t phys_map_node_alloc(PhysPageMap *map, bool leaf)
{
unsigned i;
uint32_t ret;
+ PhysPageEntry e;
+ PhysPageEntry *p;
ret = map->nodes_nb++;
+ p = map->nodes[ret];
assert(ret != PHYS_MAP_NODE_NIL);
assert(ret != map->nodes_nb_alloc);
+
+ e.skip = leaf ? 0 : 1;
+ e.ptr = leaf ? PHYS_SECTION_UNASSIGNED : PHYS_MAP_NODE_NIL;
for (i = 0; i < P_L2_SIZE; ++i) {
- map->nodes[ret][i].skip = 1;
- map->nodes[ret][i].ptr = PHYS_MAP_NODE_NIL;
+ memcpy(&p[i], &e, sizeof(e));
}
return ret;
}
@@ -193,21 +198,12 @@
int level)
{
PhysPageEntry *p;
- int i;
hwaddr step = (hwaddr)1 << (level * P_L2_BITS);
if (lp->skip && lp->ptr == PHYS_MAP_NODE_NIL) {
- lp->ptr = phys_map_node_alloc(map);
- p = map->nodes[lp->ptr];
- if (level == 0) {
- for (i = 0; i < P_L2_SIZE; i++) {
- p[i].skip = 0;
- p[i].ptr = PHYS_SECTION_UNASSIGNED;
- }
- }
- } else {
- p = map->nodes[lp->ptr];
+ lp->ptr = phys_map_node_alloc(map, level == 0);
}
+ p = map->nodes[lp->ptr];
lp = &p[(*index >> (level * P_L2_BITS)) & (P_L2_SIZE - 1)];
while (*nb && lp < &p[P_L2_SIZE]) {