| commit | 9506d57de3bc8277a4e306e0d439976862f68c6d | [log] [tgz] |
|---|---|---|
| author | Paolo Bonzini <pbonzini@redhat.com> | Tue May 06 13:05:25 2014 +0200 |
| committer | Paolo Bonzini <pbonzini@redhat.com> | Fri Jul 11 09:14:03 2014 +0200 |
| tree | aac16beac03ddc018f7ffec0d453d1a89d4a11f0 | |
| parent | 5cfc7e0f5e5e1adf998df94f8e36edaf5d30d38e [diff] |
KVM: emulate: avoid per-byte copying in instruction fetches We do not need a memory copying loop anymore in insn_fetch; we can use a byte-aligned pointer to access instruction fields directly from the fetch_cache. This eliminates 50-150 cycles (corresponding to a 5-10% improvement in performance) from each instruction. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>