migration: add bitmap for received page

This patch adds ability to track down already received
pages, it's necessary for calculation vCPU block time in
postcopy migration feature, and for recovery after
postcopy migration failure.

Also it's necessary to solve shared memory issue in
postcopy livemigration. Information about received pages
will be transferred to the software virtual bridge
(e.g. OVS-VSWITCHD), to avoid fallocate (unmap) for
already received pages. fallocate syscall is required for
remmaped shared memory, due to remmaping itself blocks
ioctl(UFFDIO_COPY, ioctl in this case will end with EEXIT
error (struct page is exists after remmap).

Bitmap is placed into RAMBlock as another postcopy/precopy
related bitmaps.

Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Alexey Perevalov <a.perevalov@samsung.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>

diff --git a/include/exec/ram_addr.h b/include/exec/ram_addr.h
index d017639f7ed15312bd9958bae38799fe9951e98c..6cbc02aa0fffb1f301184e5e0a864f0b961bf2d0 100644 (file)
--- a/include/exec/ram_addr.h
+++ b/include/exec/ram_addr.h
@@ -47,6 +47,8 @@ struct RAMBlock {
      * of the postcopy phase
      */
     unsigned long *unsentmap;
+    /* bitmap of already received pages in postcopy */
+    unsigned long *receivedmap;
 };
 
 static inline bool offset_in_ramblock(RAMBlock *b, ram_addr_t offset)
@@ -60,6 +62,14 @@ static inline void *ramblock_ptr(RAMBlock *block, ram_addr_t offset)
     return (char *)block->host + offset;
 }
 
+static inline unsigned long int ramblock_recv_bitmap_offset(void *host_addr,
+                                                            RAMBlock *rb)
+{
+    uint64_t host_addr_offset =
+            (uint64_t)(uintptr_t)(host_addr - (void *)rb->host);
+    return host_addr_offset >> TARGET_PAGE_BITS;
+}
+
 long qemu_getrampagesize(void);
 unsigned long last_ram_page(void);
 RAMBlock *qemu_ram_alloc_from_file(ram_addr_t size, MemoryRegion *mr,

diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c
index 8bf64325676c494fc66465ea92b5ccb1ec1a386f..bec6c2c66b55af4fb1a8f2b963c432273fc1d383 100644 (file)
--- a/migration/postcopy-ram.c
+++ b/migration/postcopy-ram.c
@@ -642,22 +642,28 @@ int postcopy_ram_enable_notify(MigrationIncomingState *mis)
 }
 
 static int qemu_ufd_copy_ioctl(int userfault_fd, void *host_addr,
-        void *from_addr, uint64_t pagesize)
+                               void *from_addr, uint64_t pagesize, RAMBlock *rb)
 {
+    int ret;
     if (from_addr) {
         struct uffdio_copy copy_struct;
         copy_struct.dst = (uint64_t)(uintptr_t)host_addr;
         copy_struct.src = (uint64_t)(uintptr_t)from_addr;
         copy_struct.len = pagesize;
         copy_struct.mode = 0;
-        return ioctl(userfault_fd, UFFDIO_COPY, &copy_struct);
+        ret = ioctl(userfault_fd, UFFDIO_COPY, &copy_struct);
     } else {
         struct uffdio_zeropage zero_struct;
         zero_struct.range.start = (uint64_t)(uintptr_t)host_addr;
         zero_struct.range.len = pagesize;
         zero_struct.mode = 0;
-        return ioctl(userfault_fd, UFFDIO_ZEROPAGE, &zero_struct);
+        ret = ioctl(userfault_fd, UFFDIO_ZEROPAGE, &zero_struct);
+    }
+    if (!ret) {
+        ramblock_recv_bitmap_set_range(rb, host_addr,
+                                       pagesize / qemu_target_page_size());
     }
+    return ret;
 }
 
 /*
@@ -674,7 +680,7 @@ int postcopy_place_page(MigrationIncomingState *mis, void *host, void *from,
      * which would be slightly cheaper, but we'd have to be careful
      * of the order of updating our page state.
      */
-    if (qemu_ufd_copy_ioctl(mis->userfault_fd, host, from, pagesize)) {
+    if (qemu_ufd_copy_ioctl(mis->userfault_fd, host, from, pagesize, rb)) {
         int e = errno;
         error_report("%s: %s copy host: %p from: %p (size: %zd)",
                      __func__, strerror(e), host, from, pagesize);
@@ -696,7 +702,8 @@ int postcopy_place_page_zero(MigrationIncomingState *mis, void *host,
     trace_postcopy_place_page_zero(host);
 
     if (qemu_ram_pagesize(rb) == getpagesize()) {
-        if (qemu_ufd_copy_ioctl(mis->userfault_fd, host, NULL, getpagesize())) {
+        if (qemu_ufd_copy_ioctl(mis->userfault_fd, host, NULL, getpagesize(),
+                                rb)) {
             int e = errno;
             error_report("%s: %s zero host: %p",
                          __func__, strerror(e), host);

diff --git a/migration/ram.c b/migration/ram.c
index bd4fc5ceb41e2df21799b5f7daf1d4d8d05826d5..7f6327f70896b63308b3673a67a5296a318ff798 100644 (file)
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -45,6 +45,7 @@
 #include "qapi/qmp/qerror.h"
 #include "trace.h"
 #include "exec/ram_addr.h"
+#include "exec/target_page.h"
 #include "qemu/rcu_queue.h"
 #include "migration/colo.h"
 #include "migration/block.h"
@@ -158,6 +159,35 @@ out:
     return ret;
 }
 
+static void ramblock_recv_map_init(void)
+{
+    RAMBlock *rb;
+
+    RAMBLOCK_FOREACH(rb) {
+        assert(!rb->receivedmap);
+        rb->receivedmap = bitmap_new(rb->max_length >> qemu_target_page_bits());
+    }
+}
+
+int ramblock_recv_bitmap_test(RAMBlock *rb, void *host_addr)
+{
+    return test_bit(ramblock_recv_bitmap_offset(host_addr, rb),
+                    rb->receivedmap);
+}
+
+void ramblock_recv_bitmap_set(RAMBlock *rb, void *host_addr)
+{
+    set_bit_atomic(ramblock_recv_bitmap_offset(host_addr, rb), rb->receivedmap);
+}
+
+void ramblock_recv_bitmap_set_range(RAMBlock *rb, void *host_addr,
+                                    size_t nr)
+{
+    bitmap_set_atomic(rb->receivedmap,
+                      ramblock_recv_bitmap_offset(host_addr, rb),
+                      nr);
+}
+
 /*
  * An outstanding page request, on the source, having been received
  * and queued
@@ -2021,6 +2051,8 @@ int ram_discard_range(const char *rbname, uint64_t start, size_t length)
         goto err;
     }
 
+    bitmap_clear(rb->receivedmap, start >> qemu_target_page_bits(),
+                 length >> qemu_target_page_bits());
     ret = ram_block_discard_range(rb, start, length);
 
 err:
@@ -2607,13 +2639,20 @@ static int ram_load_setup(QEMUFile *f, void *opaque)
 {
     xbzrle_load_setup();
     compress_threads_load_setup();
+    ramblock_recv_map_init();
     return 0;
 }
 
 static int ram_load_cleanup(void *opaque)
 {
+    RAMBlock *rb;
     xbzrle_load_cleanup();
     compress_threads_load_cleanup();
+
+    RAMBLOCK_FOREACH(rb) {
+        g_free(rb->receivedmap);
+        rb->receivedmap = NULL;
+    }
     return 0;
 }
 
@@ -2828,6 +2867,7 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
                 ret = -EINVAL;
                 break;
             }
+            ramblock_recv_bitmap_set(block, host);
             trace_ram_load_loop(block->idstr, (uint64_t)addr, flags, host);
         }
 

diff --git a/migration/ram.h b/migration/ram.h
index 511b3dc582c033e3870b84df12a70caeb264eb69..f9f7eef89492a505a948557848e4bbc0df31b4ec 100644 (file)
--- a/migration/ram.h
+++ b/migration/ram.h
@@ -57,4 +57,9 @@ int ram_discard_range(const char *block_name, uint64_t start, size_t length);
 int ram_postcopy_incoming_init(MigrationIncomingState *mis);
 
 void ram_handle_compressed(void *host, uint8_t ch, uint64_t size);
+
+int ramblock_recv_bitmap_test(RAMBlock *rb, void *host_addr);
+void ramblock_recv_bitmap_set(RAMBlock *rb, void *host_addr);
+void ramblock_recv_bitmap_set_range(RAMBlock *rb, void *host_addr, size_t nr);
+
 #endif