summaryrefslogtreecommitdiffstats
path: root/drivers
diff options
context:
space:
mode:
authorIgor Mammedov <imammedo@redhat.com>2015-06-16 18:33:35 +0200
committerMichael S. Tsirkin <mst@redhat.com>2015-07-01 10:12:12 +0200
commitbcfeacab45e6d419c6bafc0e57ea4b1125e23231 (patch)
treec994f9533d20d043525fd5730629ed3a97bd60b0 /drivers
parent8b0a9d42301e45d501d751074a6f767fded680b1 (diff)
downloadop-kernel-dev-bcfeacab45e6d419c6bafc0e57ea4b1125e23231.zip
op-kernel-dev-bcfeacab45e6d419c6bafc0e57ea4b1125e23231.tar.gz
vhost: use binary search instead of linear in find_region()
For default region layouts performance stays the same as linear search i.e. it takes around 210ns average for translate_desc() that inlines find_region(). But it scales better with larger amount of regions, 235ns BS vs 300ns LS with 55 memory regions and it will be about the same values when allowed number of slots is increased to 509 like it has been done in kvm. Signed-off-by: Igor Mammedov <imammedo@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Diffstat (limited to 'drivers')
-rw-r--r--drivers/vhost/vhost.c38
1 files changed, 28 insertions, 10 deletions
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 9e8e004..71bb468 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -25,6 +25,7 @@
#include <linux/kthread.h>
#include <linux/cgroup.h>
#include <linux/module.h>
+#include <linux/sort.h>
#include "vhost.h"
@@ -663,6 +664,16 @@ int vhost_vq_access_ok(struct vhost_virtqueue *vq)
}
EXPORT_SYMBOL_GPL(vhost_vq_access_ok);
+static int vhost_memory_reg_sort_cmp(const void *p1, const void *p2)
+{
+ const struct vhost_memory_region *r1 = p1, *r2 = p2;
+ if (r1->guest_phys_addr < r2->guest_phys_addr)
+ return 1;
+ if (r1->guest_phys_addr > r2->guest_phys_addr)
+ return -1;
+ return 0;
+}
+
static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
{
struct vhost_memory mem, *newmem, *oldmem;
@@ -682,9 +693,11 @@ static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
memcpy(newmem, &mem, size);
if (copy_from_user(newmem->regions, m->regions,
mem.nregions * sizeof *m->regions)) {
- kfree(newmem);
+ kvfree(newmem);
return -EFAULT;
}
+ sort(newmem->regions, newmem->nregions, sizeof(*newmem->regions),
+ vhost_memory_reg_sort_cmp, NULL);
if (!memory_access_ok(d, newmem, 0)) {
kfree(newmem);
@@ -992,17 +1005,22 @@ EXPORT_SYMBOL_GPL(vhost_dev_ioctl);
static const struct vhost_memory_region *find_region(struct vhost_memory *mem,
__u64 addr, __u32 len)
{
- struct vhost_memory_region *reg;
- int i;
+ const struct vhost_memory_region *reg;
+ int start = 0, end = mem->nregions;
- /* linear search is not brilliant, but we really have on the order of 6
- * regions in practice */
- for (i = 0; i < mem->nregions; ++i) {
- reg = mem->regions + i;
- if (reg->guest_phys_addr <= addr &&
- reg->guest_phys_addr + reg->memory_size - 1 >= addr)
- return reg;
+ while (start < end) {
+ int slot = start + (end - start) / 2;
+ reg = mem->regions + slot;
+ if (addr >= reg->guest_phys_addr)
+ end = slot;
+ else
+ start = slot + 1;
}
+
+ reg = mem->regions + start;
+ if (addr >= reg->guest_phys_addr &&
+ reg->guest_phys_addr + reg->memory_size > addr)
+ return reg;
return NULL;
}
OpenPOWER on IntegriCloud