Merge remote-tracking branch 'quintela/migration.next' into staging

# By Peter Lieven (9) and others
# Via Juan Quintela
* quintela/migration.next: (22 commits)
  Use qemu_put_buffer_async for guest memory pages
  Add qemu_put_buffer_async
  Use writev ops if available
  Store the data to send also in iovec
  Update bytes_xfer in qemu_put_byte
  Add socket_writev_buffer function
  Add QemuFileWritevBuffer QemuFileOps
  migration: use XBZRLE only after bulk stage
  migration: do not search dirty pages in bulk stage
  migration: do not sent zero pages in bulk stage
  migration: add an indicator for bulk state of ram migration
  migration: search for zero instead of dup pages
  bitops: unroll while loop in find_next_bit()
  buffer_is_zero: use vector optimizations if possible
  cutils: add a function to find non-zero content in a buffer
  move vector definitions to qemu-common.h
  savevm: Fix bugs in the VMSTATE_VBUFFER_MULTIPLY definition
  savevm: Add VMSTATE_STRUCT_VARRAY_POINTER_UINT32
  savevm: Add VMSTATE_FLOAT64 helpers
  savevm: Add VMSTATE_UINTTL_EQUAL helper
  ...

4 files changed, 84 insertions, 4 deletions

diff --git a/include/migration/migration.h b/include/migration/migration.h
index bb617fdacf..e2acec64c0 100644
--- a/include/migration/migration.h
+++ b/include/migration/migration.h
@@ -96,6 +96,8 @@ extern SaveVMHandlers savevm_ram_handlers;
 
 uint64_t dup_mig_bytes_transferred(void);
 uint64_t dup_mig_pages_transferred(void);
+uint64_t skipped_mig_bytes_transferred(void);
+uint64_t skipped_mig_pages_transferred(void);
 uint64_t norm_mig_bytes_transferred(void);
 uint64_t norm_mig_pages_transferred(void);
 uint64_t xbzrle_mig_bytes_transferred(void);
diff --git a/include/migration/qemu-file.h b/include/migration/qemu-file.h
index df812617f8..623c434b15 100644
--- a/include/migration/qemu-file.h
+++ b/include/migration/qemu-file.h
@@ -51,11 +51,18 @@ typedef int (QEMUFileCloseFunc)(void *opaque);
  */
 typedef int (QEMUFileGetFD)(void *opaque);
 
+/*
+ * This function writes an iovec to file.
+ */
+typedef ssize_t (QEMUFileWritevBufferFunc)(void *opaque, struct iovec *iov,
+                                           int iovcnt);
+
 typedef struct QEMUFileOps {
     QEMUFilePutBufferFunc *put_buffer;
     QEMUFileGetBufferFunc *get_buffer;
     QEMUFileCloseFunc *close;
     QEMUFileGetFD *get_fd;
+    QEMUFileWritevBufferFunc *writev_buffer;
 } QEMUFileOps;
 
 QEMUFile *qemu_fopen_ops(void *opaque, const QEMUFileOps *ops);
@@ -68,6 +75,11 @@ int qemu_fclose(QEMUFile *f);
 int64_t qemu_ftell(QEMUFile *f);
 void qemu_put_buffer(QEMUFile *f, const uint8_t *buf, int size);
 void qemu_put_byte(QEMUFile *f, int v);
+/*
+ * put_buffer without copying the buffer.
+ * The buffer should be available till it is sent asynchronously.
+ */
+void qemu_put_buffer_async(QEMUFile *f, const uint8_t *buf, int size);
 
 static inline void qemu_put_ubyte(QEMUFile *f, unsigned int v)
 {
diff --git a/include/migration/vmstate.h b/include/migration/vmstate.h
index 6666d27b25..65918a9abe 100644
--- a/include/migration/vmstate.h
+++ b/include/migration/vmstate.h
@@ -149,6 +149,7 @@ extern const VMStateInfo vmstate_info_uint8_equal;
 extern const VMStateInfo vmstate_info_uint16_equal;
 extern const VMStateInfo vmstate_info_int32_equal;
 extern const VMStateInfo vmstate_info_uint32_equal;
+extern const VMStateInfo vmstate_info_uint64_equal;
 extern const VMStateInfo vmstate_info_int32_le;
 
 extern const VMStateInfo vmstate_info_uint8;
@@ -156,6 +157,8 @@ extern const VMStateInfo vmstate_info_uint16;
 extern const VMStateInfo vmstate_info_uint32;
 extern const VMStateInfo vmstate_info_uint64;
 
+extern const VMStateInfo vmstate_info_float64;
+
 extern const VMStateInfo vmstate_info_timer;
 extern const VMStateInfo vmstate_info_buffer;
 extern const VMStateInfo vmstate_info_unused_buffer;
@@ -340,6 +343,16 @@ extern const VMStateInfo vmstate_info_bitmap;
     .offset     = vmstate_offset_pointer(_state, _field, _type),     \
 }
 
+#define VMSTATE_STRUCT_VARRAY_POINTER_UINT32(_field, _state, _field_num, _vmsd, _type) { \
+    .name       = (stringify(_field)),                               \
+    .version_id = 0,                                                 \
+    .num_offset = vmstate_offset_value(_state, _field_num, uint32_t),\
+    .size       = sizeof(_type),                                     \
+    .vmsd       = &(_vmsd),                                          \
+    .flags      = VMS_POINTER | VMS_VARRAY_INT32 | VMS_STRUCT,       \
+    .offset     = vmstate_offset_pointer(_state, _field, _type),     \
+}
+
 #define VMSTATE_STRUCT_VARRAY_POINTER_UINT16(_field, _state, _field_num, _vmsd, _type) { \
     .name       = (stringify(_field)),                               \
     .version_id = 0,                                                 \
@@ -380,14 +393,14 @@ extern const VMStateInfo vmstate_info_bitmap;
     .offset       = vmstate_offset_buffer(_state, _field) + _start,  \
 }
 
-#define VMSTATE_BUFFER_MULTIPLY(_field, _state, _version, _test, _start, _field_size, _multiply) { \
+#define VMSTATE_VBUFFER_MULTIPLY(_field, _state, _version, _test, _start, _field_size, _multiply) { \
     .name         = (stringify(_field)),                             \
     .version_id   = (_version),                                      \
     .field_exists = (_test),                                         \
     .size_offset  = vmstate_offset_value(_state, _field_size, uint32_t),\
     .size         = (_multiply),                                      \
     .info         = &vmstate_info_buffer,                            \
-    .flags        = VMS_VBUFFER|VMS_MULTIPLY,                        \
+    .flags        = VMS_VBUFFER|VMS_POINTER|VMS_MULTIPLY,            \
     .offset       = offsetof(_state, _field),                        \
     .start        = (_start),                                        \
 }
@@ -518,8 +531,17 @@ extern const VMStateInfo vmstate_info_bitmap;
 #define VMSTATE_INT32_EQUAL(_f, _s)                                   \
     VMSTATE_SINGLE(_f, _s, 0, vmstate_info_int32_equal, int32_t)
 
-#define VMSTATE_UINT32_EQUAL(_f, _s)                                   \
-    VMSTATE_SINGLE(_f, _s, 0, vmstate_info_uint32_equal, uint32_t)
+#define VMSTATE_UINT32_EQUAL_V(_f, _s, _v)                            \
+    VMSTATE_SINGLE(_f, _s, _v, vmstate_info_uint32_equal, uint32_t)
+
+#define VMSTATE_UINT32_EQUAL(_f, _s)                                  \
+    VMSTATE_UINT32_EQUAL_V(_f, _s, 0)
+
+#define VMSTATE_UINT64_EQUAL_V(_f, _s, _v)                            \
+    VMSTATE_SINGLE(_f, _s, _v, vmstate_info_uint64_equal, uint64_t)
+
+#define VMSTATE_UINT64_EQUAL(_f, _s)                                  \
+    VMSTATE_UINT64_EQUAL_V(_f, _s, 0)
 
 #define VMSTATE_INT32_LE(_f, _s)                                   \
     VMSTATE_SINGLE(_f, _s, 0, vmstate_info_int32_le, int32_t)
@@ -533,6 +555,13 @@ extern const VMStateInfo vmstate_info_bitmap;
 #define VMSTATE_UINT32_TEST(_f, _s, _t)                                  \
     VMSTATE_SINGLE_TEST(_f, _s, _t, 0, vmstate_info_uint32, uint32_t)
 
+
+#define VMSTATE_FLOAT64_V(_f, _s, _v)                                 \
+    VMSTATE_SINGLE(_f, _s, _v, vmstate_info_float64, float64)
+
+#define VMSTATE_FLOAT64(_f, _s)                                       \
+    VMSTATE_FLOAT64_V(_f, _s, 0)
+
 #define VMSTATE_TIMER_TEST(_f, _s, _test)                             \
     VMSTATE_POINTER_TEST(_f, _s, _test, vmstate_info_timer, QEMUTimer *)
 
@@ -599,6 +628,12 @@ extern const VMStateInfo vmstate_info_bitmap;
 #define VMSTATE_INT64_ARRAY(_f, _s, _n)                               \
     VMSTATE_INT64_ARRAY_V(_f, _s, _n, 0)
 
+#define VMSTATE_FLOAT64_ARRAY_V(_f, _s, _n, _v)                       \
+    VMSTATE_ARRAY(_f, _s, _n, _v, vmstate_info_float64, float64)
+
+#define VMSTATE_FLOAT64_ARRAY(_f, _s, _n)                             \
+    VMSTATE_FLOAT64_ARRAY_V(_f, _s, _n, 0)
+
 #define VMSTATE_BUFFER_V(_f, _s, _v)                                  \
     VMSTATE_STATIC_BUFFER(_f, _s, _v, NULL, 0, sizeof(typeof_field(_s, _f)))
 
diff --git a/include/qemu-common.h b/include/qemu-common.h
index 2371132c11..31fff22f32 100644
--- a/include/qemu-common.h
+++ b/include/qemu-common.h
@@ -448,4 +448,35 @@ int uleb128_decode_small(const uint8_t *in, uint32_t *n);
 
 void hexdump(const char *buf, FILE *fp, const char *prefix, size_t size);
 
+/* vector definitions */
+#ifdef __ALTIVEC__
+#include <altivec.h>
+#define VECTYPE        vector unsigned char
+#define SPLAT(p)       vec_splat(vec_ld(0, p), 0)
+#define ALL_EQ(v1, v2) vec_all_eq(v1, v2)
+/* altivec.h may redefine the bool macro as vector type.
+ * Reset it to POSIX semantics. */
+#undef bool
+#define bool _Bool
+#elif defined __SSE2__
+#include <emmintrin.h>
+#define VECTYPE        __m128i
+#define SPLAT(p)       _mm_set1_epi8(*(p))
+#define ALL_EQ(v1, v2) (_mm_movemask_epi8(_mm_cmpeq_epi8(v1, v2)) == 0xFFFF)
+#else
+#define VECTYPE        unsigned long
+#define SPLAT(p)       (*(p) * (~0UL / 255))
+#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