[PATCH v3 08/19] system/memory: Re-use memory-backend-guest-memfd inode for private memory

[Michael Roth <michael.roth@amd.com>]

When convert-in-place=true, the guest_memfd instance created by
memory-backend-memfd (when guest-memfd=on option is specified) should
also be used internally for private memory.

Do this by dup()'ing the guest_memfd FD provided by the backend so the
separate cleanup paths for shared vs. private FDs can be managed in the
same way they are currently for convert-in-place=false (where shared
memory must come from something other than guest_memfd).

Introduce a new RAM_GUEST_MEMFD_SHAREABLE flag that can be used to
limit this dup()'ing to specific backend types like
memory-backend-memfd.

Signed-off-by: Michael Roth <michael.roth@amd.com>
---
 backends/hostmem-memfd.c |  1 +
 include/system/memory.h  |  7 ++++++
 system/physmem.c         | 50 +++++++++++++++++++++++++++++++++++++---
 3 files changed, 55 insertions(+), 3 deletions(-)

diff --git a/backends/hostmem-memfd.c b/backends/hostmem-memfd.c
index 666593ff6c..c1ea6eefbd 100644
--- a/backends/hostmem-memfd.c
+++ b/backends/hostmem-memfd.c
@@ -90,6 +90,7 @@ have_fd:
     backend->aligned = true;
     ram_flags = backend->share ? RAM_SHARED : RAM_PRIVATE;
     ram_flags |= backend->reserve ? 0 : RAM_NORESERVE;
+    ram_flags |= RAM_GUEST_MEMFD_SHAREABLE;
     ram_flags |= backend->guest_memfd_private ? RAM_GUEST_MEMFD_PRIVATE : 0;
     return memory_region_init_ram_from_fd(&backend->mr, OBJECT(backend), name,
                                           backend->size, ram_flags, fd, 0, errp);
diff --git a/include/system/memory.h b/include/system/memory.h
index 027ca81bd2..ef6c767021 100644
--- a/include/system/memory.h
+++ b/include/system/memory.h
@@ -274,6 +274,13 @@ typedef struct IOMMUTLBEvent {
  */
 #define RAM_PRIVATE (1 << 13)
 
+/*
+ * RAM is backed by a guest-memfd instance that supports being used as shared
+ * memory (as opposed to RAM_GUEST_MEMFD_PRIVATE which, by itself, entails
+ * the guest-memfd instance can only ever be used for private memory).
+ */
+#define RAM_GUEST_MEMFD_SHAREABLE   (1 << 14)
+
 static inline void iommu_notifier_init(IOMMUNotifier *n, IOMMUNotify fn,
                                        IOMMUNotifierFlag flags,
                                        hwaddr start, hwaddr end,
diff --git a/system/physmem.c b/system/physmem.c
index 86046d46df..b9b4864a94 100644
--- a/system/physmem.c
+++ b/system/physmem.c
@@ -59,6 +59,7 @@
 #include "system/hostmem.h"
 #include "system/hw_accel.h"
 #include "system/xen-mapcache.h"
+#include "system/confidential-guest-support.h"
 #include "trace.h"
 
 #ifdef CONFIG_FALLOCATE_PUNCH_HOLE
@@ -2187,6 +2188,8 @@ static void ram_block_add(RAMBlock *new_block, Error **errp)
     if (new_block->flags & RAM_GUEST_MEMFD_PRIVATE) {
         int ret;
 
+        assert(current_machine->cgs);
+
         if (!kvm_enabled()) {
             error_setg(errp, "cannot set up private guest memory for %s: KVM required",
                        object_get_typename(OBJECT(current_machine->cgs)));
@@ -2211,9 +2214,44 @@ static void ram_block_add(RAMBlock *new_block, Error **errp)
             goto out_free;
         }
 
-        new_block->guest_memfd_private =
-            kvm_create_guest_memfd_private(new_block->max_length, errp);
+        /*
+         * If both shared/private memory are handled by guest_memfd, make sure
+         * to re-use the guest_memfd inode that should have already been created
+         * for handling shared memory.
+         */
+        if (machine_require_guest_memfd_convert_in_place(current_machine)) {
+            if (!(new_block->flags & RAM_GUEST_MEMFD_SHAREABLE)) {
+                error_setg(errp, "configured memory backend is not compatible"
+                                 " with in-place conversion");
+                ram_block_coordinated_discard_require(false);
+                qemu_mutex_unlock_ramlist();
+                goto out_free;
+            }
+            assert(new_block->fd >= 0);
+
+            /*
+             * Current logic calculates guest_memfd_offset on the assumption
+             * that offset 0 corresponds to the first GPA that is backed by the
+             * RAM block/backend. For cases where the guest_memfd is only used
+             * for private memory and created internally as-needed this is
+             * always the case, but when re-using a guest_memfd that's also
+             * usable for shared memory (e.g. via memory-backend-guest-memfd)
+             * it's possible that guest_memfd might be mmap()'d starting at some
+             * non-zero offset. For now, this isn't a reachable condition, but
+             * assert this in case this ever changes and the logic needs to be
+             * updated to account for this.
+             */
+            assert(new_block->fd_offset == 0);
+
+            new_block->guest_memfd_private = qemu_dup(new_block->fd);
+        } else {
+            new_block->guest_memfd_private =
+                kvm_create_guest_memfd_private(new_block->max_length, &err);
+        }
+
         if (new_block->guest_memfd_private < 0) {
+            error_propagate(errp, err);
+            ram_block_coordinated_discard_require(false);
             qemu_mutex_unlock_ramlist();
             goto out_free;
         }
@@ -2323,7 +2361,7 @@ RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, ram_addr_t max_size,
     assert((ram_flags & ~(RAM_SHARED | RAM_PMEM | RAM_NORESERVE |
                           RAM_PROTECTED | RAM_NAMED_FILE | RAM_READONLY |
                           RAM_READONLY_FD | RAM_GUEST_MEMFD_PRIVATE |
-                          RAM_RESIZEABLE)) == 0);
+                          RAM_RESIZEABLE | RAM_GUEST_MEMFD_SHAREABLE)) == 0);
     assert(max_size >= size);
 
     if (xen_enabled()) {
@@ -2835,6 +2873,12 @@ int ram_block_rebind(Error **errp)
 {
     RAMBlock *block;
 
+    if (machine_require_guest_memfd_convert_in_place(current_machine)) {
+        error_setg(errp,
+                   "rebind support is not yet enabled for in-place conversion");
+        return -1;
+    }
+
     qemu_mutex_lock_ramlist();
 
     RAMBLOCK_FOREACH(block) {
-- 
2.43.0