cutils: add a function to find non-zero content in a buffer

this adds buffer_find_nonzero_offset() which is a SSE2/Altivec
optimized function that searches for non-zero content in a
buffer.

the function starts full unrolling only after the first few chunks have
been checked one by one. analyzing real memory page data has revealed
that non-zero pages are non-zero within the first 256-512 bits in
most cases. as this function is also heavily used to check for zero memory
pages this tweak has been made to avoid the high setup costs of the fully
unrolled check for non-zero pages.

due to the optimizations used in the function there are restrictions
on buffer address and search length. the function
can_use_buffer_find_nonzero_content() can be used to check if
the function can be used safely.

Signed-off-by: Peter Lieven <pl@kamp.de>
Signed-off-by: Juan Quintela <quintela@redhat.com>

diff --git a/include/qemu-common.h b/include/qemu-common.h
index d7ad3a70f11e1eeada0972a91b8b997dc1d6b79b..31fff22f321058800e3b9ed906a7a9be861c991e 100644 (file)
--- a/include/qemu-common.h
+++ b/include/qemu-common.h
@@ -469,4 +469,14 @@ void hexdump(const char *buf, FILE *fp, const char *prefix, size_t size);
 #define ALL_EQ(v1, v2) ((v1) == (v2))
 #endif
 
+#define BUFFER_FIND_NONZERO_OFFSET_UNROLL_FACTOR 8
+static inline bool
+can_use_buffer_find_nonzero_offset(const void *buf, size_t len)
+{
+    return (len % (BUFFER_FIND_NONZERO_OFFSET_UNROLL_FACTOR
+                   * sizeof(VECTYPE)) == 0
+            && ((uintptr_t) buf) % sizeof(VECTYPE) == 0);
+}
+size_t buffer_find_nonzero_offset(const void *buf, size_t len);
+
 #endif

diff --git a/util/cutils.c b/util/cutils.c
index 1439da4f9915fe7fb12336cc2ce360d4f8d7554a..0696a3ba5e43970f7418db5b77127816281d71f2 100644 (file)
--- a/util/cutils.c
+++ b/util/cutils.c
@@ -142,6 +142,61 @@ int qemu_fdatasync(int fd)
 #endif
 }
 
+/*
+ * 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
  *