iov: avoid memcpy for "simple" iov_from_buf/iov_to_buf

memcpy can take a large amount of time for small reads and writes.
For virtio it is a common case that the first iovec can satisfy the
whole read or write.  In that case, and if bytes is a constant to
avoid excessive growth of code, inline the first iteration
into the caller.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-id: 1450782213-14227-1-git-send-email-pbonzini@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

2 files changed, 34 insertions, 8 deletions

diff --git a/include/qemu/iov.h b/include/qemu/iov.h
index 569b2c2a23..28475516eb 100644
--- a/include/qemu/iov.h
+++ b/include/qemu/iov.h
@@ -39,10 +39,36 @@ size_t iov_size(const struct iovec *iov, const unsigned int iov_cnt);
  * such "large" value is -1 (sinice size_t is unsigned),
  * so specifying `-1' as `bytes' means 'up to the end of iovec'.
  */
-size_t iov_from_buf(const struct iovec *iov, unsigned int iov_cnt,
-                    size_t offset, const void *buf, size_t bytes);
-size_t iov_to_buf(const struct iovec *iov, const unsigned int iov_cnt,
-                  size_t offset, void *buf, size_t bytes);
+size_t iov_from_buf_full(const struct iovec *iov, unsigned int iov_cnt,
+                         size_t offset, const void *buf, size_t bytes);
+size_t iov_to_buf_full(const struct iovec *iov, const unsigned int iov_cnt,
+		       size_t offset, void *buf, size_t bytes);
+
+static inline size_t
+iov_from_buf(const struct iovec *iov, unsigned int iov_cnt,
+             size_t offset, const void *buf, size_t bytes)
+{
+    if (__builtin_constant_p(bytes) && iov_cnt &&
+        offset <= iov[0].iov_len && bytes <= iov[0].iov_len - offset) {
+        memcpy(iov[0].iov_base + offset, buf, bytes);
+        return bytes;
+    } else {
+        return iov_from_buf_full(iov, iov_cnt, offset, buf, bytes);
+    }
+}
+
+static inline size_t
+iov_to_buf(const struct iovec *iov, const unsigned int iov_cnt,
+           size_t offset, void *buf, size_t bytes)
+{
+    if (__builtin_constant_p(bytes) && iov_cnt &&
+        offset <= iov[0].iov_len && bytes <= iov[0].iov_len - offset) {
+        memcpy(buf, iov[0].iov_base + offset, bytes);
+        return bytes;
+    } else {
+        return iov_to_buf_full(iov, iov_cnt, offset, buf, bytes);
+    }
+}
 
 /**
  * Set data bytes pointed out by iovec `iov' of size `iov_cnt' elements,
diff --git a/util/iov.c b/util/iov.c
index e802ee15bc..062f4e50c3 100644
--- a/util/iov.c
+++ b/util/iov.c
@@ -20,8 +20,8 @@
 #include "qemu/iov.h"
 #include "qemu/sockets.h"
 
-size_t iov_from_buf(const struct iovec *iov, unsigned int iov_cnt,
-                    size_t offset, const void *buf, size_t bytes)
+size_t iov_from_buf_full(const struct iovec *iov, unsigned int iov_cnt,
+                         size_t offset, const void *buf, size_t bytes)
 {
     size_t done;
     unsigned int i;
@@ -39,8 +39,8 @@ size_t iov_from_buf(const struct iovec *iov, unsigned int iov_cnt,
     return done;
 }
 
-size_t iov_to_buf(const struct iovec *iov, const unsigned int iov_cnt,
-                  size_t offset, void *buf, size_t bytes)
+size_t iov_to_buf_full(const struct iovec *iov, const unsigned int iov_cnt,
+                       size_t offset, void *buf, size_t bytes)
 {
     size_t done;
     unsigned int i;