1 files changed, 29 insertions, 14 deletions

diff --git a/system/physmem.c b/system/physmem.c
index a8a9ca3..e5dd760 100644
--- a/system/physmem.c
+++ b/system/physmem.c
@@ -165,13 +165,11 @@ static bool ram_is_cpr_compatible(RAMBlock *rb);
  * CPUAddressSpace: all the information a CPU needs about an AddressSpace
  * @cpu: the CPU whose AddressSpace this is
  * @as: the AddressSpace itself
- * @memory_dispatch: its dispatch pointer (cached, RCU protected)
  * @tcg_as_listener: listener for tracking changes to the AddressSpace
  */
 typedef struct CPUAddressSpace {
     CPUState *cpu;
     AddressSpace *as;
-    struct AddressSpaceDispatch *memory_dispatch;
     MemoryListener tcg_as_listener;
 } CPUAddressSpace;
 
@@ -692,7 +690,7 @@ address_space_translate_for_iotlb(CPUState *cpu, int asidx, hwaddr orig_addr,
     IOMMUTLBEntry iotlb;
     int iommu_idx;
     hwaddr addr = orig_addr;
-    AddressSpaceDispatch *d = cpu->cpu_ases[asidx].memory_dispatch;
+    AddressSpaceDispatch *d = address_space_to_dispatch(cpu->cpu_ases[asidx].as);
 
     for (;;) {
         section = address_space_translate_internal(d, addr, &addr, plen, false);
@@ -753,7 +751,7 @@ MemoryRegionSection *iotlb_to_section(CPUState *cpu,
 {
     int asidx = cpu_asidx_from_attrs(cpu, attrs);
     CPUAddressSpace *cpuas = &cpu->cpu_ases[asidx];
-    AddressSpaceDispatch *d = cpuas->memory_dispatch;
+    AddressSpaceDispatch *d = address_space_to_dispatch(cpuas->as);
     int section_index = index & ~TARGET_PAGE_MASK;
     MemoryRegionSection *ret;
 
@@ -1593,6 +1591,11 @@ ram_addr_t qemu_ram_get_offset(RAMBlock *rb)
     return rb->offset;
 }
 
+ram_addr_t qemu_ram_get_fd_offset(RAMBlock *rb)
+{
+    return rb->fd_offset;
+}
+
 ram_addr_t qemu_ram_get_used_length(RAMBlock *rb)
 {
     return rb->used_length;
@@ -1916,7 +1919,7 @@ static void ram_block_add(RAMBlock *new_block, Error **errp)
         }
         assert(new_block->guest_memfd < 0);
 
-        ret = ram_block_discard_require(true);
+        ret = ram_block_coordinated_discard_require(true);
         if (ret < 0) {
             error_setg_errno(errp, -ret,
                              "cannot set up private guest memory: discard currently blocked");
@@ -1932,6 +1935,24 @@ static void ram_block_add(RAMBlock *new_block, Error **errp)
         }
 
         /*
+         * The attribute bitmap of the RamBlockAttributes is default to
+         * discarded, which mimics the behavior of kvm_set_phys_mem() when it
+         * calls kvm_set_memory_attributes_private(). This leads to a brief
+         * period of inconsistency between the creation of the RAMBlock and its
+         * mapping into the physical address space. However, this is not
+         * problematic, as no users rely on the attribute status to perform
+         * any actions during this interval.
+         */
+        new_block->attributes = ram_block_attributes_create(new_block);
+        if (!new_block->attributes) {
+            error_setg(errp, "Failed to create ram block attribute");
+            close(new_block->guest_memfd);
+            ram_block_coordinated_discard_require(false);
+            qemu_mutex_unlock_ramlist();
+            goto out_free;
+        }
+
+        /*
          * Add a specific guest_memfd blocker if a generic one would not be
          * added by ram_block_add_cpr_blocker.
          */
@@ -2287,8 +2308,9 @@ static void reclaim_ramblock(RAMBlock *block)
     }
 
     if (block->guest_memfd >= 0) {
+        ram_block_attributes_destroy(block->attributes);
         close(block->guest_memfd);
-        ram_block_discard_require(false);
+        ram_block_coordinated_discard_require(false);
     }
 
     g_free(block);
@@ -2756,9 +2778,6 @@ static void tcg_log_global_after_sync(MemoryListener *listener)
 
 static void tcg_commit_cpu(CPUState *cpu, run_on_cpu_data data)
 {
-    CPUAddressSpace *cpuas = data.host_ptr;
-
-    cpuas->memory_dispatch = address_space_to_dispatch(cpuas->as);
     tlb_flush(cpu);
 }
 
@@ -2774,11 +2793,7 @@ static void tcg_commit(MemoryListener *listener)
     cpu = cpuas->cpu;
 
     /*
-     * Defer changes to as->memory_dispatch until the cpu is quiescent.
-     * Otherwise we race between (1) other cpu threads and (2) ongoing
-     * i/o for the current cpu thread, with data cached by mmu_lookup().
-     *
-     * In addition, queueing the work function will kick the cpu back to
+     * Queueing the work function will kick the cpu back to
      * the main loop, which will end the RCU critical section and reclaim
      * the memory data structures.
      *