RAMBlock: Add support of KVM private guest memfd

Add KVM guest_memfd support to RAMBlock so both normal hva based memory
and kvm guest memfd based private memory can be associated in one RAMBlock.

Introduce new flag RAM_GUEST_MEMFD. When it's set, it calls KVM ioctl to
create private guest_memfd during RAMBlock setup.

Allocating a new RAM_GUEST_MEMFD flag to instruct the setup of guest memfd
is more flexible and extensible than simply relying on the VM type because
in the future we may have the case that not all the memory of a VM need
guest memfd. As a benefit, it also avoid getting MachineState in memory
subsystem.

Note, RAM_GUEST_MEMFD is supposed to be set for memory backends of
confidential guests, such as TDX VM. How and when to set it for memory
backends will be implemented in the following patches.

Introduce memory_region_has_guest_memfd() to query if the MemoryRegion has
KVM guest_memfd allocated.

Signed-off-by: Xiaoyao Li <xiaoyao.li@intel.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Message-ID: <20240320083945.991426-7-michael.roth@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

2 files changed, 36 insertions, 3 deletions

diff --git a/system/memory.c b/system/memory.c
index a229a79988..c756950c0c 100644
--- a/system/memory.c
+++ b/system/memory.c
@@ -1850,6 +1850,11 @@ bool memory_region_is_protected(MemoryRegion *mr)
     return mr->ram && (mr->ram_block->flags & RAM_PROTECTED);
 }
 
+bool memory_region_has_guest_memfd(MemoryRegion *mr)
+{
+    return mr->ram_block && mr->ram_block->guest_memfd >= 0;
+}
+
 uint8_t memory_region_get_dirty_log_mask(MemoryRegion *mr)
 {
     uint8_t mask = mr->dirty_log_mask;
diff --git a/system/physmem.c b/system/physmem.c
index a4fe3d2bf8..f5dfa20e57 100644
--- a/system/physmem.c
+++ b/system/physmem.c
@@ -1808,6 +1808,7 @@ static void ram_block_add(RAMBlock *new_block, Error **errp)
     const bool shared = qemu_ram_is_shared(new_block);
     RAMBlock *block;
     RAMBlock *last_block = NULL;
+    bool free_on_error = false;
     ram_addr_t old_ram_size, new_ram_size;
     Error *err = NULL;
 
@@ -1837,6 +1838,19 @@ static void ram_block_add(RAMBlock *new_block, Error **errp)
                 return;
             }
             memory_try_enable_merging(new_block->host, new_block->max_length);
+            free_on_error = true;
+        }
+    }
+
+    if (new_block->flags & RAM_GUEST_MEMFD) {
+        assert(kvm_enabled());
+        assert(new_block->guest_memfd < 0);
+
+        new_block->guest_memfd = kvm_create_guest_memfd(new_block->max_length,
+                                                        0, errp);
+        if (new_block->guest_memfd < 0) {
+            qemu_mutex_unlock_ramlist();
+            goto out_free;
         }
     }
 
@@ -1888,6 +1902,13 @@ static void ram_block_add(RAMBlock *new_block, Error **errp)
         ram_block_notify_add(new_block->host, new_block->used_length,
                              new_block->max_length);
     }
+    return;
+
+out_free:
+    if (free_on_error) {
+        qemu_anon_ram_free(new_block->host, new_block->max_length);
+        new_block->host = NULL;
+    }
 }
 
 #ifdef CONFIG_POSIX
@@ -1902,7 +1923,7 @@ RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, MemoryRegion *mr,
     /* Just support these ram flags by now. */
     assert((ram_flags & ~(RAM_SHARED | RAM_PMEM | RAM_NORESERVE |
                           RAM_PROTECTED | RAM_NAMED_FILE | RAM_READONLY |
-                          RAM_READONLY_FD)) == 0);
+                          RAM_READONLY_FD | RAM_GUEST_MEMFD)) == 0);
 
     if (xen_enabled()) {
         error_setg(errp, "-mem-path not supported with Xen");
@@ -1939,6 +1960,7 @@ RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, MemoryRegion *mr,
     new_block->used_length = size;
     new_block->max_length = size;
     new_block->flags = ram_flags;
+    new_block->guest_memfd = -1;
     new_block->host = file_ram_alloc(new_block, size, fd, !file_size, offset,
                                      errp);
     if (!new_block->host) {
@@ -2018,7 +2040,7 @@ RAMBlock *qemu_ram_alloc_internal(ram_addr_t size, ram_addr_t max_size,
     int align;
 
     assert((ram_flags & ~(RAM_SHARED | RAM_RESIZEABLE | RAM_PREALLOC |
-                          RAM_NORESERVE)) == 0);
+                          RAM_NORESERVE | RAM_GUEST_MEMFD)) == 0);
     assert(!host ^ (ram_flags & RAM_PREALLOC));
 
     align = qemu_real_host_page_size();
@@ -2033,6 +2055,7 @@ RAMBlock *qemu_ram_alloc_internal(ram_addr_t size, ram_addr_t max_size,
     new_block->max_length = max_size;
     assert(max_size >= size);
     new_block->fd = -1;
+    new_block->guest_memfd = -1;
     new_block->page_size = qemu_real_host_page_size();
     new_block->host = host;
     new_block->flags = ram_flags;
@@ -2055,7 +2078,7 @@ RAMBlock *qemu_ram_alloc_from_ptr(ram_addr_t size, void *host,
 RAMBlock *qemu_ram_alloc(ram_addr_t size, uint32_t ram_flags,
                          MemoryRegion *mr, Error **errp)
 {
-    assert((ram_flags & ~(RAM_SHARED | RAM_NORESERVE)) == 0);
+    assert((ram_flags & ~(RAM_SHARED | RAM_NORESERVE | RAM_GUEST_MEMFD)) == 0);
     return qemu_ram_alloc_internal(size, size, NULL, NULL, ram_flags, mr, errp);
 }
 
@@ -2083,6 +2106,11 @@ static void reclaim_ramblock(RAMBlock *block)
     } else {
         qemu_anon_ram_free(block->host, block->max_length);
     }
+
+    if (block->guest_memfd >= 0) {
+        close(block->guest_memfd);
+    }
+
     g_free(block);
 }