From 302dfbeb21fc5154c24ca50d296e865a3778c7da Mon Sep 17 00:00:00 2001
From: Orit Wasserman <owasserm@redhat.com>
Date: Mon, 6 Aug 2012 21:42:52 +0300
Subject: [PATCH] Add xbzrle_encode_buffer and xbzrle_decode_buffer functions

For performance we are encoding long word at a time.
For nzrun we use long-word-at-a-time NULL-detection tricks from strcmp():
using ((lword - 0x0101010101010101) & (~lword) & 0x8080808080808080) test
to find out if any byte in the long word is zero.

Signed-off-by: Benoit Hudzia <benoit.hudzia@sap.com>
Signed-off-by: Petter Svard <petters@cs.umu.se>
Signed-off-by: Aidan Shribman <aidan.shribman@sap.com>
Signed-off-by: Orit Wasserman <owasserm@redhat.com>
Signed-off-by: Eric Blake <eblake@redhat.com>

Reviewed-by: Luiz Capitulino <lcapitulino@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
---
 migration.h |   4 ++
 savevm.c    | 159 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 163 insertions(+)

diff --git a/migration.h b/migration.h
index 713aae0253..743c366149 100644
--- a/migration.h
+++ b/migration.h
@@ -100,4 +100,8 @@ void migrate_add_blocker(Error *reason);
  */
 void migrate_del_blocker(Error *reason);
 
+int xbzrle_encode_buffer(uint8_t *old_buf, uint8_t *new_buf, int slen,
+                         uint8_t *dst, int dlen);
+int xbzrle_decode_buffer(uint8_t *src, int slen, uint8_t *dst, int dlen);
+
 #endif
diff --git a/savevm.c b/savevm.c
index 6e82b2d3e3..0ea10c9b66 100644
--- a/savevm.c
+++ b/savevm.c
@@ -2392,3 +2392,162 @@ void vmstate_register_ram_global(MemoryRegion *mr)
 {
     vmstate_register_ram(mr, NULL);
 }
+
+/*
+  page = zrun nzrun
+       | zrun nzrun page
+
+  zrun = length
+
+  nzrun = length byte...
+
+  length = uleb128 encoded integer
+ */
+int xbzrle_encode_buffer(uint8_t *old_buf, uint8_t *new_buf, int slen,
+                         uint8_t *dst, int dlen)
+{
+    uint32_t zrun_len = 0, nzrun_len = 0;
+    int d = 0, i = 0;
+    long res, xor;
+    uint8_t *nzrun_start = NULL;
+
+    g_assert(!(((uintptr_t)old_buf | (uintptr_t)new_buf | slen) %
+               sizeof(long)));
+
+    while (i < slen) {
+        /* overflow */
+        if (d + 2 > dlen) {
+            return -1;
+        }
+
+        /* not aligned to sizeof(long) */
+        res = (slen - i) % sizeof(long);
+        while (res && old_buf[i] == new_buf[i]) {
+            zrun_len++;
+            i++;
+            res--;
+        }
+
+        /* word at a time for speed */
+        if (!res) {
+            while (i < slen &&
+                   (*(long *)(old_buf + i)) == (*(long *)(new_buf + i))) {
+                i += sizeof(long);
+                zrun_len += sizeof(long);
+            }
+
+            /* go over the rest */
+            while (i < slen && old_buf[i] == new_buf[i]) {
+                zrun_len++;
+                i++;
+            }
+        }
+
+        /* buffer unchanged */
+        if (zrun_len == slen) {
+            return 0;
+        }
+
+        /* skip last zero run */
+        if (i == slen) {
+            return d;
+        }
+
+        d += uleb128_encode_small(dst + d, zrun_len);
+
+        zrun_len = 0;
+        nzrun_start = new_buf + i;
+
+        /* overflow */
+        if (d + 2 > dlen) {
+            return -1;
+        }
+        /* not aligned to sizeof(long) */
+        res = (slen - i) % sizeof(long);
+        while (res && old_buf[i] != new_buf[i]) {
+            i++;
+            nzrun_len++;
+            res--;
+        }
+
+        /* word at a time for speed, use of 32-bit long okay */
+        if (!res) {
+            /* truncation to 32-bit long okay */
+            long mask = 0x0101010101010101ULL;
+            while (i < slen) {
+                xor = *(long *)(old_buf + i) ^ *(long *)(new_buf + i);
+                if ((xor - mask) & ~xor & (mask << 7)) {
+                    /* found the end of an nzrun within the current long */
+                    while (old_buf[i] != new_buf[i]) {
+                        nzrun_len++;
+                        i++;
+                    }
+                    break;
+                } else {
+                    i += sizeof(long);
+                    nzrun_len += sizeof(long);
+                }
+            }
+        }
+
+        d += uleb128_encode_small(dst + d, nzrun_len);
+        /* overflow */
+        if (d + nzrun_len > dlen) {
+            return -1;
+        }
+        memcpy(dst + d, nzrun_start, nzrun_len);
+        d += nzrun_len;
+        nzrun_len = 0;
+    }
+
+    return d;
+}
+
+int xbzrle_decode_buffer(uint8_t *src, int slen, uint8_t *dst, int dlen)
+{
+    int i = 0, d = 0;
+    int ret;
+    uint32_t count = 0;
+
+    while (i < slen) {
+
+        /* zrun */
+        if ((slen - i) < 2) {
+            return -1;
+        }
+
+        ret = uleb128_decode_small(src + i, &count);
+        if (ret < 0 || (i && !count)) {
+            return -1;
+        }
+        i += ret;
+        d += count;
+
+        /* overflow */
+        if (d > dlen) {
+            return -1;
+        }
+
+        /* nzrun */
+        if ((slen - i) < 2) {
+            return -1;
+        }
+
+        ret = uleb128_decode_small(src + i, &count);
+        if (ret < 0 || !count) {
+            return -1;
+        }
+        i += ret;
+
+        /* overflow */
+        if (d + count > dlen || i + count > slen) {
+            return -1;
+        }
+
+        memcpy(dst + d, src + i, count);
+        d += count;
+        i += count;
+    }
+
+    return d;
+}