2 files changed, 77 insertions, 1 deletions

diff --git a/util/bitops.c b/util/bitops.c
index e72237ab2b..227c38b883 100644
--- a/util/bitops.c
+++ b/util/bitops.c
@@ -42,7 +42,23 @@ unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
         size -= BITS_PER_LONG;
         result += BITS_PER_LONG;
     }
-    while (size & ~(BITS_PER_LONG-1)) {
+    while (size >= 4*BITS_PER_LONG) {
+        unsigned long d1, d2, d3;
+        tmp = *p;
+        d1 = *(p+1);
+        d2 = *(p+2);
+        d3 = *(p+3);
+        if (tmp) {
+            goto found_middle;
+        }
+        if (d1 | d2 | d3) {
+            break;
+        }
+        p += 4;
+        result += 4*BITS_PER_LONG;
+        size -= 4*BITS_PER_LONG;
+    }
+    while (size >= BITS_PER_LONG) {
         if ((tmp = *(p++))) {
             goto found_middle;
         }
diff --git a/util/cutils.c b/util/cutils.c
index 1439da4f99..5024253405 100644
--- a/util/cutils.c
+++ b/util/cutils.c
@@ -143,6 +143,61 @@ int qemu_fdatasync(int fd)
 }
 
 /*
+ * Searches for an area with non-zero content in a buffer
+ *
+ * Attention! The len must be a multiple of
+ * BUFFER_FIND_NONZERO_OFFSET_UNROLL_FACTOR * sizeof(VECTYPE)
+ * and addr must be a multiple of sizeof(VECTYPE) due to
+ * restriction of optimizations in this function.
+ *
+ * can_use_buffer_find_nonzero_offset() can be used to check
+ * these requirements.
+ *
+ * The return value is the offset of the non-zero area rounded
+ * down to a multiple of sizeof(VECTYPE) for the first
+ * BUFFER_FIND_NONZERO_OFFSET_UNROLL_FACTOR chunks and down to
+ * BUFFER_FIND_NONZERO_OFFSET_UNROLL_FACTOR * sizeof(VECTYPE)
+ * afterwards.
+ *
+ * If the buffer is all zero the return value is equal to len.
+ */
+
+size_t buffer_find_nonzero_offset(const void *buf, size_t len)
+{
+    const VECTYPE *p = buf;
+    const VECTYPE zero = (VECTYPE){0};
+    size_t i;
+
+    assert(can_use_buffer_find_nonzero_offset(buf, len));
+
+    if (!len) {
+        return 0;
+    }
+
+    for (i = 0; i < BUFFER_FIND_NONZERO_OFFSET_UNROLL_FACTOR; i++) {
+        if (!ALL_EQ(p[i], zero)) {
+            return i * sizeof(VECTYPE);
+        }
+    }
+
+    for (i = BUFFER_FIND_NONZERO_OFFSET_UNROLL_FACTOR;
+         i < len / sizeof(VECTYPE);
+         i += BUFFER_FIND_NONZERO_OFFSET_UNROLL_FACTOR) {
+        VECTYPE tmp0 = p[i + 0] | p[i + 1];
+        VECTYPE tmp1 = p[i + 2] | p[i + 3];
+        VECTYPE tmp2 = p[i + 4] | p[i + 5];
+        VECTYPE tmp3 = p[i + 6] | p[i + 7];
+        VECTYPE tmp01 = tmp0 | tmp1;
+        VECTYPE tmp23 = tmp2 | tmp3;
+        if (!ALL_EQ(tmp01 | tmp23, zero)) {
+            break;
+        }
+    }
+
+    return i * sizeof(VECTYPE);
+}
+
+/*
  * Checks if a buffer is all zeroes
  *
  * Attention! The len must be a multiple of 4 * sizeof(long) due to
@@ -160,6 +215,11 @@ bool buffer_is_zero(const void *buf, size_t len)
     long d0, d1, d2, d3;
     const long * const data = buf;
 
+    /* use vector optimized zero check if possible */
+    if (can_use_buffer_find_nonzero_offset(buf, len)) {
+        return buffer_find_nonzero_offset(buf, len) == len;
+    }
+
     assert(len % (4 * sizeof(long)) == 0);
     len /= sizeof(long);