Implement sPAPR Virtual LAN (ibmveth)

[qemu.git] / block-migration.c

diff --git a/block-migration.c b/block-migration.c
index 0bfdb73c8b4f89df5948e3eea6affe97556b8fbf..8218bac09c6cd30286a4ce5b826ac378700036da 100644 (file)
--- a/block-migration.c
+++ b/block-migration.c
@@ -19,6 +19,7 @@
 #include "monitor.h"
 #include "block-migration.h"
 #include "migration.h"
+#include "blockdev.h"
 #include <assert.h>
 
 #define BLOCK_SIZE (BDRV_SECTORS_PER_DIRTY_CHUNK << BDRV_SECTOR_BITS)
@@ -49,12 +50,14 @@ typedef struct BlkMigDevState {
     int64_t total_sectors;
     int64_t dirty;
     QSIMPLEQ_ENTRY(BlkMigDevState) entry;
+    unsigned long *aio_bitmap;
 } BlkMigDevState;
 
 typedef struct BlkMigBlock {
     uint8_t *buf;
     BlkMigDevState *bmds;
     int64_t sector;
+    int nr_sectors;
     struct iovec iov;
     QEMUIOVector qiov;
     BlockDriverAIOCB *aiocb;
@@ -140,6 +143,52 @@ static inline long double compute_read_bwidth(void)
     return  (block_mig_state.reads * BLOCK_SIZE)/ block_mig_state.total_time;
 }
 
+static int bmds_aio_inflight(BlkMigDevState *bmds, int64_t sector)
+{
+    int64_t chunk = sector / (int64_t)BDRV_SECTORS_PER_DIRTY_CHUNK;
+
+    if ((sector << BDRV_SECTOR_BITS) < bdrv_getlength(bmds->bs)) {
+        return !!(bmds->aio_bitmap[chunk / (sizeof(unsigned long) * 8)] &
+            (1UL << (chunk % (sizeof(unsigned long) * 8))));
+    } else {
+        return 0;
+    }
+}
+
+static void bmds_set_aio_inflight(BlkMigDevState *bmds, int64_t sector_num,
+                             int nb_sectors, int set)
+{
+    int64_t start, end;
+    unsigned long val, idx, bit;
+
+    start = sector_num / BDRV_SECTORS_PER_DIRTY_CHUNK;
+    end = (sector_num + nb_sectors - 1) / BDRV_SECTORS_PER_DIRTY_CHUNK;
+
+    for (; start <= end; start++) {
+        idx = start / (sizeof(unsigned long) * 8);
+        bit = start % (sizeof(unsigned long) * 8);
+        val = bmds->aio_bitmap[idx];
+        if (set) {
+            val |= 1UL << bit;
+        } else {
+            val &= ~(1UL << bit);
+        }
+        bmds->aio_bitmap[idx] = val;
+    }
+}
+
+static void alloc_aio_bitmap(BlkMigDevState *bmds)
+{
+    BlockDriverState *bs = bmds->bs;
+    int64_t bitmap_size;
+
+    bitmap_size = (bdrv_getlength(bs) >> BDRV_SECTOR_BITS) +
+            BDRV_SECTORS_PER_DIRTY_CHUNK * 8 - 1;
+    bitmap_size /= BDRV_SECTORS_PER_DIRTY_CHUNK * 8;
+
+    bmds->aio_bitmap = qemu_mallocz(bitmap_size);
+}
+
 static void blk_mig_read_cb(void *opaque, int ret)
 {
     BlkMigBlock *blk = opaque;
@@ -151,6 +200,7 @@ static void blk_mig_read_cb(void *opaque, int ret)
     add_avg_read_time(blk->time);
 
     QSIMPLEQ_INSERT_TAIL(&block_mig_state.blk_list, blk, entry);
+    bmds_set_aio_inflight(blk->bmds, blk->sector, blk->nr_sectors, 0);
 
     block_mig_state.submitted--;
     block_mig_state.read_done++;
@@ -194,6 +244,7 @@ static int mig_save_device_bulk(Monitor *mon, QEMUFile *f,
     blk->buf = qemu_malloc(BLOCK_SIZE);
     blk->bmds = bmds;
     blk->sector = cur_sector;
+    blk->nr_sectors = nr_sectors;
 
     blk->iov.iov_base = blk->buf;
     blk->iov.iov_len = nr_sectors * BDRV_SECTOR_SIZE;
@@ -248,6 +299,9 @@ static void init_blk_migration_it(void *opaque, BlockDriverState *bs)
         bmds->total_sectors = sectors;
         bmds->completed_sectors = 0;
         bmds->shared_base = block_mig_state.shared_base;
+        alloc_aio_bitmap(bmds);
+        drive_get_ref(drive_get_by_blockdev(bs));
+        bdrv_set_in_use(bs, 1);
 
         block_mig_state.total_sector_sum += sectors;
 
@@ -299,7 +353,12 @@ static int blk_mig_save_bulked_block(Monitor *mon, QEMUFile *f)
         }
     }
 
-    progress = completed_sector_sum * 100 / block_mig_state.total_sector_sum;
+    if (block_mig_state.total_sector_sum != 0) {
+        progress = completed_sector_sum * 100 /
+                   block_mig_state.total_sector_sum;
+    } else {
+        progress = 100;
+    }
     if (progress != block_mig_state.prev_progress) {
         block_mig_state.prev_progress = progress;
         qemu_put_be64(f, (progress << BDRV_SECTOR_BITS)
@@ -329,6 +388,9 @@ static int mig_save_device_dirty(Monitor *mon, QEMUFile *f,
     int nr_sectors;
 
     for (sector = bmds->cur_dirty; sector < bmds->total_sectors;) {
+        if (bmds_aio_inflight(bmds, sector)) {
+            qemu_aio_flush();
+        }
         if (bdrv_get_dirty(bmds->bs, sector)) {
 
             if (total_sectors - sector < BDRV_SECTORS_PER_DIRTY_CHUNK) {
@@ -340,6 +402,7 @@ static int mig_save_device_dirty(Monitor *mon, QEMUFile *f,
             blk->buf = qemu_malloc(BLOCK_SIZE);
             blk->bmds = bmds;
             blk->sector = sector;
+            blk->nr_sectors = nr_sectors;
 
             if (is_async) {
                 blk->iov.iov_base = blk->buf;
@@ -354,6 +417,7 @@ static int mig_save_device_dirty(Monitor *mon, QEMUFile *f,
                     goto error;
                 }
                 block_mig_state.submitted++;
+                bmds_set_aio_inflight(bmds, sector, nr_sectors, 1);
             } else {
                 if (bdrv_read(bmds->bs, sector, blk->buf,
                               nr_sectors) < 0) {
@@ -472,8 +536,13 @@ static void blk_mig_cleanup(Monitor *mon)
     BlkMigDevState *bmds;
     BlkMigBlock *blk;
 
+    set_dirty_tracking(0);
+
     while ((bmds = QSIMPLEQ_FIRST(&block_mig_state.bmds_list)) != NULL) {
         QSIMPLEQ_REMOVE_HEAD(&block_mig_state.bmds_list, entry);
+        bdrv_set_in_use(bmds->bs, 0);
+        drive_put_ref(drive_get_by_blockdev(bmds->bs));
+        qemu_free(bmds->aio_bitmap);
         qemu_free(bmds);
     }
 
@@ -483,8 +552,6 @@ static void blk_mig_cleanup(Monitor *mon)
         qemu_free(blk);
     }
 
-    set_dirty_tracking(0);
-
     monitor_printf(mon, "\n");
 }
 
@@ -576,8 +643,10 @@ static int block_load(QEMUFile *f, void *opaque, int version_id)
     int len, flags;
     char device_name[256];
     int64_t addr;
-    BlockDriverState *bs;
+    BlockDriverState *bs, *bs_prev = NULL;
     uint8_t *buf;
+    int64_t total_sectors = 0;
+    int nr_sectors;
 
     do {
         addr = qemu_get_be64(f);
@@ -599,10 +668,26 @@ static int block_load(QEMUFile *f, void *opaque, int version_id)
                 return -EINVAL;
             }
 
+            if (bs != bs_prev) {
+                bs_prev = bs;
+                total_sectors = bdrv_getlength(bs) >> BDRV_SECTOR_BITS;
+                if (total_sectors <= 0) {
+                    error_report("Error getting length of block device %s\n",
+                                 device_name);
+                    return -EINVAL;
+                }
+            }
+
+            if (total_sectors - addr < BDRV_SECTORS_PER_DIRTY_CHUNK) {
+                nr_sectors = total_sectors - addr;
+            } else {
+                nr_sectors = BDRV_SECTORS_PER_DIRTY_CHUNK;
+            }
+
             buf = qemu_malloc(BLOCK_SIZE);
 
             qemu_get_buffer(f, buf, BLOCK_SIZE);
-            ret = bdrv_write(bs, addr, buf, BDRV_SECTORS_PER_DIRTY_CHUNK);
+            ret = bdrv_write(bs, addr, buf, nr_sectors);
 
             qemu_free(buf);
             if (ret < 0) {