Merge remote-tracking branch 'remotes/juanquintela/tags/migration-pull-request' into staging

Pull request

# gpg: Signature made Mon 15 Jul 2019 14:49:41 BST
# gpg:                using RSA key 1899FF8EDEBF58CCEE034B82F487EF185872D723
# gpg: Good signature from "Juan Quintela <quintela@redhat.com>" [full]
# gpg:                 aka "Juan Quintela <quintela@trasno.org>" [full]
# Primary key fingerprint: 1899 FF8E DEBF 58CC EE03  4B82 F487 EF18 5872 D723

* remotes/juanquintela/tags/migration-pull-request: (21 commits)
  migration: always initial RAMBlock.bmap to 1 for new migration
  migration/postcopy: remove redundant cpu_synchronize_all_post_init
  migration/postcopy: fix document of postcopy_send_discard_bm_ram()
  migration: allow private destination ram with x-ignore-shared
  migration: Split log_clear() into smaller chunks
  kvm: Support KVM_CLEAR_DIRTY_LOG
  kvm: Introduce slots lock for memory listener
  kvm: Persistent per kvmslot dirty bitmap
  kvm: Update comments for sync_dirty_bitmap
  memory: Introduce memory listener hook log_clear()
  memory: Pass mr into snapshot_and_clear_dirty
  bitmap: Add bitmap_copy_with_{src|dst}_offset()
  memory: Don't set migration bitmap when without migration
  migration: No need to take rcu during sync_dirty_bitmap
  migration/ram.c: reset complete_round when we gets a queued page
  migration/multifd: sync packet_num after all thread are done
  cutils: remove one unnecessary pointer operation
  migration/xbzrle: update cache and current_data in one place
  migration/multifd: call multifd_send_sync_main when sending RAM_SAVE_FLAG_EOS
  migration-test: rename parameter to parameter_int
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

4 files changed, 119 insertions, 5 deletions

diff --git a/include/exec/memory.h b/include/exec/memory.h
index 2c5cdff..bb0961d 100644
--- a/include/exec/memory.h
+++ b/include/exec/memory.h
@@ -46,6 +46,8 @@
         OBJECT_GET_CLASS(IOMMUMemoryRegionClass, (obj), \
                          TYPE_IOMMU_MEMORY_REGION)
 
+extern bool global_dirty_log;
+
 typedef struct MemoryRegionOps MemoryRegionOps;
 typedef struct MemoryRegionMmio MemoryRegionMmio;
 
@@ -414,6 +416,7 @@ struct MemoryListener {
     void (*log_stop)(MemoryListener *listener, MemoryRegionSection *section,
                      int old, int new);
     void (*log_sync)(MemoryListener *listener, MemoryRegionSection *section);
+    void (*log_clear)(MemoryListener *listener, MemoryRegionSection *section);
     void (*log_global_start)(MemoryListener *listener);
     void (*log_global_stop)(MemoryListener *listener);
     void (*eventfd_add)(MemoryListener *listener, MemoryRegionSection *section,
@@ -1268,6 +1271,22 @@ void memory_region_set_dirty(MemoryRegion *mr, hwaddr addr,
                              hwaddr size);
 
 /**
+ * memory_region_clear_dirty_bitmap - clear dirty bitmap for memory range
+ *
+ * This function is called when the caller wants to clear the remote
+ * dirty bitmap of a memory range within the memory region.  This can
+ * be used by e.g. KVM to manually clear dirty log when
+ * KVM_CAP_MANUAL_DIRTY_LOG_PROTECT is declared support by the host
+ * kernel.
+ *
+ * @mr:     the memory region to clear the dirty log upon
+ * @start:  start address offset within the memory region
+ * @len:    length of the memory region to clear dirty bitmap
+ */
+void memory_region_clear_dirty_bitmap(MemoryRegion *mr, hwaddr start,
+                                      hwaddr len);
+
+/**
  * memory_region_snapshot_and_clear_dirty: Get a snapshot of the dirty
  *                                         bitmap and clear it.
  *
diff --git a/include/exec/ram_addr.h b/include/exec/ram_addr.h
index f96777b..b7b2e60 100644
--- a/include/exec/ram_addr.h
+++ b/include/exec/ram_addr.h
@@ -51,8 +51,70 @@ struct RAMBlock {
     unsigned long *unsentmap;
     /* bitmap of already received pages in postcopy */
     unsigned long *receivedmap;
+
+    /*
+     * bitmap to track already cleared dirty bitmap.  When the bit is
+     * set, it means the corresponding memory chunk needs a log-clear.
+     * Set this up to non-NULL to enable the capability to postpone
+     * and split clearing of dirty bitmap on the remote node (e.g.,
+     * KVM).  The bitmap will be set only when doing global sync.
+     *
+     * NOTE: this bitmap is different comparing to the other bitmaps
+     * in that one bit can represent multiple guest pages (which is
+     * decided by the `clear_bmap_shift' variable below).  On
+     * destination side, this should always be NULL, and the variable
+     * `clear_bmap_shift' is meaningless.
+     */
+    unsigned long *clear_bmap;
+    uint8_t clear_bmap_shift;
 };
 
+/**
+ * clear_bmap_size: calculate clear bitmap size
+ *
+ * @pages: number of guest pages
+ * @shift: guest page number shift
+ *
+ * Returns: number of bits for the clear bitmap
+ */
+static inline long clear_bmap_size(uint64_t pages, uint8_t shift)
+{
+    return DIV_ROUND_UP(pages, 1UL << shift);
+}
+
+/**
+ * clear_bmap_set: set clear bitmap for the page range
+ *
+ * @rb: the ramblock to operate on
+ * @start: the start page number
+ * @size: number of pages to set in the bitmap
+ *
+ * Returns: None
+ */
+static inline void clear_bmap_set(RAMBlock *rb, uint64_t start,
+                                  uint64_t npages)
+{
+    uint8_t shift = rb->clear_bmap_shift;
+
+    bitmap_set_atomic(rb->clear_bmap, start >> shift,
+                      clear_bmap_size(npages, shift));
+}
+
+/**
+ * clear_bmap_test_and_clear: test clear bitmap for the page, clear if set
+ *
+ * @rb: the ramblock to operate on
+ * @page: the page number to check
+ *
+ * Returns: true if the bit was set, false otherwise
+ */
+static inline bool clear_bmap_test_and_clear(RAMBlock *rb, uint64_t page)
+{
+    uint8_t shift = rb->clear_bmap_shift;
+
+    return bitmap_test_and_clear_atomic(rb->clear_bmap, page >> shift, 1);
+}
+
 static inline bool offset_in_ramblock(RAMBlock *b, ram_addr_t offset)
 {
     return (b && b->host && offset < b->used_length) ? true : false;
@@ -349,8 +411,13 @@ static inline void cpu_physical_memory_set_dirty_lebitmap(unsigned long *bitmap,
             if (bitmap[k]) {
                 unsigned long temp = leul_to_cpu(bitmap[k]);
 
-                atomic_or(&blocks[DIRTY_MEMORY_MIGRATION][idx][offset], temp);
                 atomic_or(&blocks[DIRTY_MEMORY_VGA][idx][offset], temp);
+
+                if (global_dirty_log) {
+                    atomic_or(&blocks[DIRTY_MEMORY_MIGRATION][idx][offset],
+                              temp);
+                }
+
                 if (tcg_enabled()) {
                     atomic_or(&blocks[DIRTY_MEMORY_CODE][idx][offset], temp);
                 }
@@ -367,6 +434,11 @@ static inline void cpu_physical_memory_set_dirty_lebitmap(unsigned long *bitmap,
         xen_hvm_modified_memory(start, pages << TARGET_PAGE_BITS);
     } else {
         uint8_t clients = tcg_enabled() ? DIRTY_CLIENTS_ALL : DIRTY_CLIENTS_NOCODE;
+
+        if (!global_dirty_log) {
+            clients &= ~(1 << DIRTY_MEMORY_MIGRATION);
+        }
+
         /*
          * bitmap-traveling is faster than memory-traveling (for addr...)
          * especially when most of the memory is not dirty.
@@ -394,7 +466,7 @@ bool cpu_physical_memory_test_and_clear_dirty(ram_addr_t start,
                                               unsigned client);
 
 DirtyBitmapSnapshot *cpu_physical_memory_snapshot_and_clear_dirty
-    (ram_addr_t start, ram_addr_t length, unsigned client);
+    (MemoryRegion *mr, hwaddr offset, hwaddr length, unsigned client);
 
 bool cpu_physical_memory_snapshot_get_dirty(DirtyBitmapSnapshot *snap,
                                             ram_addr_t start,
@@ -409,6 +481,7 @@ static inline void cpu_physical_memory_clear_dirty_range(ram_addr_t start,
 }
 
 
+/* Called with RCU critical section */
 static inline
 uint64_t cpu_physical_memory_sync_dirty_bitmap(RAMBlock *rb,
                                                ram_addr_t start,
@@ -432,8 +505,6 @@ uint64_t cpu_physical_memory_sync_dirty_bitmap(RAMBlock *rb,
                                         DIRTY_MEMORY_BLOCK_SIZE);
         unsigned long page = BIT_WORD(start >> TARGET_PAGE_BITS);
 
-        rcu_read_lock();
-
         src = atomic_rcu_read(
                 &ram_list.dirty_memory[DIRTY_MEMORY_MIGRATION])->blocks;
 
@@ -454,7 +525,18 @@ uint64_t cpu_physical_memory_sync_dirty_bitmap(RAMBlock *rb,
             }
         }
 
-        rcu_read_unlock();
+        if (rb->clear_bmap) {
+            /*
+             * Postpone the dirty bitmap clear to the point before we
+             * really send the pages, also we will split the clear
+             * dirty procedure into smaller chunks.
+             */
+            clear_bmap_set(rb, start >> TARGET_PAGE_BITS,
+                           length >> TARGET_PAGE_BITS);
+        } else {
+            /* Slow path - still do that in a huge chunk */
+            memory_region_clear_dirty_bitmap(rb->mr, start, length);
+        }
     } else {
         ram_addr_t offset = rb->offset;
 
diff --git a/include/qemu/bitmap.h b/include/qemu/bitmap.h
index 5c31334..82a1d2f 100644
--- a/include/qemu/bitmap.h
+++ b/include/qemu/bitmap.h
@@ -41,6 +41,10 @@
  * bitmap_find_next_zero_area(buf, len, pos, n, mask)	Find bit free area
  * bitmap_to_le(dst, src, nbits)      Convert bitmap to little endian
  * bitmap_from_le(dst, src, nbits)    Convert bitmap from little endian
+ * bitmap_copy_with_src_offset(dst, src, offset, nbits)
+ *                                    *dst = *src (with an offset into src)
+ * bitmap_copy_with_dst_offset(dst, src, offset, nbits)
+ *                                    *dst = *src (with an offset into dst)
  */
 
 /*
@@ -271,4 +275,9 @@ void bitmap_to_le(unsigned long *dst, const unsigned long *src,
 void bitmap_from_le(unsigned long *dst, const unsigned long *src,
                     long nbits);
 
+void bitmap_copy_with_src_offset(unsigned long *dst, const unsigned long *src,
+                                 unsigned long offset, unsigned long nbits);
+void bitmap_copy_with_dst_offset(unsigned long *dst, const unsigned long *src,
+                                 unsigned long shift, unsigned long nbits);
+
 #endif /* BITMAP_H */
diff --git a/include/sysemu/kvm_int.h b/include/sysemu/kvm_int.h
index f838412..31df465 100644
--- a/include/sysemu/kvm_int.h
+++ b/include/sysemu/kvm_int.h
@@ -21,10 +21,14 @@ typedef struct KVMSlot
     int slot;
     int flags;
     int old_flags;
+    /* Dirty bitmap cache for the slot */
+    unsigned long *dirty_bmap;
 } KVMSlot;
 
 typedef struct KVMMemoryListener {
     MemoryListener listener;
+    /* Protects the slots and all inside them */
+    QemuMutex slots_lock;
     KVMSlot *slots;
     int as_id;
 } KVMMemoryListener;