Currently, the TDVF cannot work with gmem in-place conversion because
current implementation of KVM_TDX_INIT_MEM_REGION in KVM requires
gmem of TDVF to be valid for both shared and private at the same time.
To workaround it, explicitly not enable in-place conversion for internal
MemoryRegion with gmem. So that TDVF doesn't use in-place conversion gmem
and KVM_TDX_INIT_MEM_REGION will initialize the gmem with the separate
shared memory.
To make in-place conversion work with TDX's initial memory, the
one possible solution and flow would be as below and it requires KVM
change:
- QEMU create gmem as shared;
- QEMU mmap the gmem and load TDVF binary into it;
- QEMU convert gmem to private with the content preserved[1];
- QEMU invokes KVM_TDX_INIT_MEM_REGION without valid src, so that KVM
knows to fetch the content in-place and use in-place PAGE.ADD for TDX.
[1] https://lore.kernel.org/all/aG0pNijVpl0czqXu@google.com/
Signed-off-by: Xiaoyao Li <xiaoyao.li@intel.com>
---
include/system/memory.h | 3 +++
system/memory.c | 2 +-
system/physmem.c | 8 +++++---
3 files changed, 9 insertions(+), 4 deletions(-)
diff --git a/include/system/memory.h b/include/system/memory.h
index f14fbf65805d..89d6449cef70 100644
--- a/include/system/memory.h
+++ b/include/system/memory.h
@@ -256,6 +256,9 @@ typedef struct IOMMUTLBEvent {
*/
#define RAM_PRIVATE (1 << 13)
+/* Don't use enable in-place conversion for the guest mmefd backend */
+#define RAM_GUEST_MEMFD_NO_INPLACE (1 << 14)
+
static inline void iommu_notifier_init(IOMMUNotifier *n, IOMMUNotify fn,
IOMMUNotifierFlag flags,
hwaddr start, hwaddr end,
diff --git a/system/memory.c b/system/memory.c
index 6870a41629ef..c1b73abc4c94 100644
--- a/system/memory.c
+++ b/system/memory.c
@@ -3702,7 +3702,7 @@ bool memory_region_init_ram_guest_memfd(MemoryRegion *mr,
DeviceState *owner_dev;
if (!memory_region_init_ram_flags_nomigrate(mr, owner, name, size,
- RAM_GUEST_MEMFD, errp)) {
+ RAM_GUEST_MEMFD | RAM_GUEST_MEMFD_NO_INPLACE, errp)) {
return false;
}
/* This will assert if owner is neither NULL nor a DeviceState.
diff --git a/system/physmem.c b/system/physmem.c
index ea1c27ea2b99..c23379082f38 100644
--- a/system/physmem.c
+++ b/system/physmem.c
@@ -1916,7 +1916,8 @@ static void ram_block_add(RAMBlock *new_block, Error **errp)
if (new_block->flags & RAM_GUEST_MEMFD) {
int ret;
- bool in_place = kvm_guest_memfd_inplace_supported;
+ bool in_place = !(new_block->flags & RAM_GUEST_MEMFD_NO_INPLACE) &&
+ kvm_guest_memfd_inplace_supported;
new_block->guest_memfd_flags = 0;
@@ -2230,7 +2231,8 @@ RAMBlock *qemu_ram_alloc_internal(ram_addr_t size, ram_addr_t max_size,
ram_flags &= ~RAM_PRIVATE;
assert((ram_flags & ~(RAM_SHARED | RAM_RESIZEABLE | RAM_PREALLOC |
- RAM_NORESERVE | RAM_GUEST_MEMFD)) == 0);
+ RAM_NORESERVE | RAM_GUEST_MEMFD |
+ RAM_GUEST_MEMFD_NO_INPLACE)) == 0);
assert(!host ^ (ram_flags & RAM_PREALLOC));
assert(max_size >= size);
@@ -2314,7 +2316,7 @@ RAMBlock *qemu_ram_alloc(ram_addr_t size, uint32_t ram_flags,
MemoryRegion *mr, Error **errp)
{
assert((ram_flags & ~(RAM_SHARED | RAM_NORESERVE | RAM_GUEST_MEMFD |
- RAM_PRIVATE)) == 0);
+ RAM_PRIVATE | RAM_GUEST_MEMFD_NO_INPLACE)) == 0);
return qemu_ram_alloc_internal(size, size, NULL, NULL, ram_flags, mr, errp);
}
--
2.43.0