physmem: Support coordinated discarding of RAM with guest_memfd

A new field, attributes, was introduced in RAMBlock to link to a
RamBlockAttributes object, which centralizes all guest_memfd related
information (such as fd and status bitmap) within a RAMBlock.

Create and initialize the RamBlockAttributes object upon ram_block_add().
Meanwhile, register the object in the target RAMBlock's MemoryRegion.
After that, guest_memfd-backed RAMBlock is associated with the
RamDiscardManager interface, and the users can execute RamDiscardManager
specific handling. For example, VFIO will register the
RamDiscardListener and get notifications when the state_change() helper
invokes.

As coordinate discarding of RAM with guest_memfd is now supported, only
block uncoordinated discard.

Tested-by: Alexey Kardashevskiy <aik@amd.com>
Reviewed-by: Alexey Kardashevskiy <aik@amd.com>
Acked-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Chenyi Qiang <chenyi.qiang@intel.com>
Link: https://lore.kernel.org/r/20250612082747.51539-6-chenyi.qiang@intel.com
Signed-off-by: Peter Xu <peterx@redhat.com>

3 files changed, 31 insertions, 2 deletions

diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index a317783..d095d1b 100644
--- a/accel/kvm/kvm-all.c
+++ b/accel/kvm/kvm-all.c
@@ -3091,6 +3091,15 @@ int kvm_convert_memory(hwaddr start, hwaddr size, bool to_private)
     addr = memory_region_get_ram_ptr(mr) + section.offset_within_region;
     rb = qemu_ram_block_from_host(addr, false, &offset);
 
+    ret = ram_block_attributes_state_change(RAM_BLOCK_ATTRIBUTES(mr->rdm),
+                                            offset, size, to_private);
+    if (ret) {
+        error_report("Failed to notify the listener the state change of "
+                     "(0x%"HWADDR_PRIx" + 0x%"HWADDR_PRIx") to %s",
+                     start, size, to_private ? "private" : "shared");
+        goto out_unref;
+    }
+
     if (to_private) {
         if (rb->page_size != qemu_real_host_page_size()) {
             /*
diff --git a/include/system/ramblock.h b/include/system/ramblock.h
index 1bab9e2..87e847e 100644
--- a/include/system/ramblock.h
+++ b/include/system/ramblock.h
@@ -46,6 +46,7 @@ struct RAMBlock {
     int fd;
     uint64_t fd_offset;
     int guest_memfd;
+    RamBlockAttributes *attributes;
     size_t page_size;
     /* dirty bitmap used during migration */
     unsigned long *bmap;
diff --git a/system/physmem.c b/system/physmem.c
index a8a9ca3..ff0ca40 100644
--- a/system/physmem.c
+++ b/system/physmem.c
@@ -1916,7 +1916,7 @@ 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 +1932,24 @@ 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 +2305,9 @@ 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);