From: Sean Christopherson <seanjc@google.com>

Accept gmem_flags in vm_mem_add() to be able to create a guest_memfd within
vm_mem_add().

When vm_mem_add() is used to set up a guest_memfd for a memslot, set up the
provided (or created) gmem_fd as the fd for the user memory region. This
makes it available to be mmap()-ed from just like fds from other memory
sources. mmap() from guest_memfd using the provided gmem_flags and
gmem_offset.

Add a kvm_slot_to_fd() helper to provide convenient access to the file
descriptor of a memslot.

Update existing callers of vm_mem_add() to pass 0 for gmem_flags to
preserve existing behavior.

Signed-off-by: Sean Christopherson <seanjc@google.com>
[For guest_memfds, mmap() using gmem_offset instead of 0 all the time.]
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
---
 tools/testing/selftests/kvm/include/kvm_util.h |  7 ++++++-
 tools/testing/selftests/kvm/lib/kvm_util.c     | 18 ++++++++++--------
 .../kvm/x86/private_mem_conversions_test.c     |  2 +-
 3 files changed, 17 insertions(+), 10 deletions(-)

diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 45159638d5dde..de8ae9be19067 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -678,7 +678,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 				 uint32_t flags);
 void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
 		uint64_t gpa, uint32_t slot, uint64_t npages, uint32_t flags,
-		int guest_memfd_fd, uint64_t guest_memfd_offset);
+		int gmem_fd, uint64_t gmem_offset, uint64_t gmem_flags);
 
 #ifndef vm_arch_has_protected_memory
 static inline bool vm_arch_has_protected_memory(struct kvm_vm *vm)
@@ -711,6 +711,11 @@ void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva);
 vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva);
 void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa);
 
+static inline int kvm_slot_to_fd(struct kvm_vm *vm, uint32_t slot)
+{
+	return memslot2region(vm, slot)->fd;
+}
+
 #ifndef vcpu_arch_put_guest
 #define vcpu_arch_put_guest(mem, val) do { (mem) = (val); } while (0)
 #endif
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 8b714270cf381..19c0445c0b296 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -944,12 +944,13 @@ void vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags
 /* FIXME: This thing needs to be ripped apart and rewritten. */
 void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
 		uint64_t gpa, uint32_t slot, uint64_t npages, uint32_t flags,
-		int gmem_fd, uint64_t gmem_offset)
+		int gmem_fd, uint64_t gmem_offset, uint64_t gmem_flags)
 {
 	int ret;
 	struct userspace_mem_region *region;
 	size_t backing_src_pagesz = get_backing_src_pagesz(src_type);
 	size_t mem_size = npages * vm->page_size;
+	off_t mmap_offset;
 	size_t alignment;
 
 	TEST_REQUIRE_SET_USER_MEMORY_REGION2();
@@ -1028,8 +1029,6 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
 
 	if (flags & KVM_MEM_GUEST_MEMFD) {
 		if (gmem_fd < 0) {
-			uint32_t gmem_flags = 0;
-
 			TEST_ASSERT(!gmem_offset,
 				    "Offset must be zero when creating new guest_memfd");
 			gmem_fd = vm_create_guest_memfd(vm, mem_size, gmem_flags);
@@ -1050,13 +1049,16 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
 	}
 
 	region->fd = -1;
-	if (backing_src_is_shared(src_type))
+	if (flags & KVM_MEM_GUEST_MEMFD && gmem_flags & GUEST_MEMFD_FLAG_MMAP)
+		region->fd = kvm_dup(gmem_fd);
+	else if (backing_src_is_shared(src_type))
 		region->fd = kvm_memfd_alloc(region->mmap_size,
 					     src_type == VM_MEM_SRC_SHARED_HUGETLB);
 
-	region->mmap_start = kvm_mmap(region->mmap_size, PROT_READ | PROT_WRITE,
-				      vm_mem_backing_src_alias(src_type)->flag,
-				      region->fd);
+	mmap_offset = flags & KVM_MEM_GUEST_MEMFD ? gmem_offset : 0;
+	region->mmap_start = __kvm_mmap(region->mmap_size, PROT_READ | PROT_WRITE,
+					vm_mem_backing_src_alias(src_type)->flag,
+					region->fd, mmap_offset);
 
 	TEST_ASSERT(!is_backing_src_hugetlb(src_type) ||
 		    region->mmap_start == align_ptr_up(region->mmap_start, backing_src_pagesz),
@@ -1117,7 +1119,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 				 uint64_t gpa, uint32_t slot, uint64_t npages,
 				 uint32_t flags)
 {
-	vm_mem_add(vm, src_type, gpa, slot, npages, flags, -1, 0);
+	vm_mem_add(vm, src_type, gpa, slot, npages, flags, -1, 0, 0);
 }
 
 /*
diff --git a/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c b/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c
index 1969f4ab9b280..41f6b38f04071 100644
--- a/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c
+++ b/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c
@@ -399,7 +399,7 @@ static void test_mem_conversions(enum vm_mem_backing_src_type src_type, uint32_t
 	for (i = 0; i < nr_memslots; i++)
 		vm_mem_add(vm, src_type, BASE_DATA_GPA + slot_size * i,
 			   BASE_DATA_SLOT + i, slot_size / vm->page_size,
-			   KVM_MEM_GUEST_MEMFD, memfd, slot_size * i);
+			   KVM_MEM_GUEST_MEMFD, memfd, slot_size * i, 0);
 
 	for (i = 0; i < nr_vcpus; i++) {
 		uint64_t gpa =  BASE_DATA_GPA + i * per_cpu_size;
-- 
2.51.0.858.gf9c4a03a3a-goog

Ackerley Tng <ackerleytng@google.com> writes:

> From: Sean Christopherson <seanjc@google.com>
>
> Accept gmem_flags in vm_mem_add() to be able to create a guest_memfd within
> vm_mem_add().
>
> When vm_mem_add() is used to set up a guest_memfd for a memslot, set up the
> provided (or created) gmem_fd as the fd for the user memory region. This
> makes it available to be mmap()-ed from just like fds from other memory
> sources. mmap() from guest_memfd using the provided gmem_flags and
> gmem_offset.
>
> Add a kvm_slot_to_fd() helper to provide convenient access to the file
> descriptor of a memslot.
>
> Update existing callers of vm_mem_add() to pass 0 for gmem_flags to
> preserve existing behavior.
>
> Signed-off-by: Sean Christopherson <seanjc@google.com>
> [For guest_memfds, mmap() using gmem_offset instead of 0 all the time.]
> Signed-off-by: Ackerley Tng <ackerleytng@google.com>
> ---
>  tools/testing/selftests/kvm/include/kvm_util.h |  7 ++++++-
>  tools/testing/selftests/kvm/lib/kvm_util.c     | 18 ++++++++++--------
>  .../kvm/x86/private_mem_conversions_test.c     |  2 +-
>  3 files changed, 17 insertions(+), 10 deletions(-)
>
> 
> [...snip...]
> 
> @@ -1050,13 +1049,16 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
>  	}
>  
>  	region->fd = -1;
> -	if (backing_src_is_shared(src_type))
> +	if (flags & KVM_MEM_GUEST_MEMFD && gmem_flags & GUEST_MEMFD_FLAG_MMAP)
> +		region->fd = kvm_dup(gmem_fd);
> +	else if (backing_src_is_shared(src_type))
>  		region->fd = kvm_memfd_alloc(region->mmap_size,
>  					     src_type == VM_MEM_SRC_SHARED_HUGETLB);
>  

Doing this makes it hard to test the legacy dual-backing case.

It actually broke x86/private_mem_conversions_test for the legacy
dual-backing case because there's no way to mmap or provide a
userspace_address from the memory provider that is not guest_memfd, as
determined by src_type.

I didn't test the legacy dual-backing case before posting this RFC and
probably should have.

> -	region->mmap_start = kvm_mmap(region->mmap_size, PROT_READ | PROT_WRITE,
> -				      vm_mem_backing_src_alias(src_type)->flag,
> -				      region->fd);
> +	mmap_offset = flags & KVM_MEM_GUEST_MEMFD ? gmem_offset : 0;
> +	region->mmap_start = __kvm_mmap(region->mmap_size, PROT_READ | PROT_WRITE,
> +					vm_mem_backing_src_alias(src_type)->flag,
> +					region->fd, mmap_offset);
>  
>  	TEST_ASSERT(!is_backing_src_hugetlb(src_type) ||
>  		    region->mmap_start == align_ptr_up(region->mmap_start, backing_src_pagesz),
> @@ -1117,7 +1119,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
>  				 uint64_t gpa, uint32_t slot, uint64_t npages,
>  				 uint32_t flags)
>  {
> -	vm_mem_add(vm, src_type, gpa, slot, npages, flags, -1, 0);
> +	vm_mem_add(vm, src_type, gpa, slot, npages, flags, -1, 0, 0);
>  }
>  
>  /*
> diff --git a/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c b/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c
> index 1969f4ab9b280..41f6b38f04071 100644
> --- a/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c
> +++ b/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c
> @@ -399,7 +399,7 @@ static void test_mem_conversions(enum vm_mem_backing_src_type src_type, uint32_t
>  	for (i = 0; i < nr_memslots; i++)
>  		vm_mem_add(vm, src_type, BASE_DATA_GPA + slot_size * i,
>  			   BASE_DATA_SLOT + i, slot_size / vm->page_size,
> -			   KVM_MEM_GUEST_MEMFD, memfd, slot_size * i);
> +			   KVM_MEM_GUEST_MEMFD, memfd, slot_size * i, 0);
>  
>  	for (i = 0; i < nr_vcpus; i++) {
>  		uint64_t gpa =  BASE_DATA_GPA + i * per_cpu_size;
> -- 
> 2.51.0.858.gf9c4a03a3a-goog

On Fri, Oct 24, 2025, Ackerley Tng wrote:
> Ackerley Tng <ackerleytng@google.com> writes:
> 
> > From: Sean Christopherson <seanjc@google.com>
> >
> > Accept gmem_flags in vm_mem_add() to be able to create a guest_memfd within
> > vm_mem_add().
> >
> > When vm_mem_add() is used to set up a guest_memfd for a memslot, set up the
> > provided (or created) gmem_fd as the fd for the user memory region. This
> > makes it available to be mmap()-ed from just like fds from other memory
> > sources. mmap() from guest_memfd using the provided gmem_flags and
> > gmem_offset.
> >
> > Add a kvm_slot_to_fd() helper to provide convenient access to the file
> > descriptor of a memslot.
> >
> > Update existing callers of vm_mem_add() to pass 0 for gmem_flags to
> > preserve existing behavior.
> >
> > Signed-off-by: Sean Christopherson <seanjc@google.com>
> > [For guest_memfds, mmap() using gmem_offset instead of 0 all the time.]
> > Signed-off-by: Ackerley Tng <ackerleytng@google.com>
> > ---
> >  tools/testing/selftests/kvm/include/kvm_util.h |  7 ++++++-
> >  tools/testing/selftests/kvm/lib/kvm_util.c     | 18 ++++++++++--------
> >  .../kvm/x86/private_mem_conversions_test.c     |  2 +-
> >  3 files changed, 17 insertions(+), 10 deletions(-)
> >
> > 
> > [...snip...]
> > 
> > @@ -1050,13 +1049,16 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
> >  	}
> >  
> >  	region->fd = -1;
> > -	if (backing_src_is_shared(src_type))
> > +	if (flags & KVM_MEM_GUEST_MEMFD && gmem_flags & GUEST_MEMFD_FLAG_MMAP)
> > +		region->fd = kvm_dup(gmem_fd);
> > +	else if (backing_src_is_shared(src_type))
> >  		region->fd = kvm_memfd_alloc(region->mmap_size,
> >  					     src_type == VM_MEM_SRC_SHARED_HUGETLB);
> >  
> 
> Doing this makes it hard to test the legacy dual-backing case.
> 
> It actually broke x86/private_mem_conversions_test for the legacy
> dual-backing case because there's no way to mmap or provide a
> userspace_address from the memory provider that is not guest_memfd, as
> determined by src_type.

Yes there is.  This patch is a giant nop.  The only thing that the core library
doesn't support is mmap() on guest_memfd *and* the other src_type, and IMO that
is big "don't care", because KVM doesn't even support that combination:

	if (kvm_gmem_supports_mmap(inode))
		slot->flags |= KVM_MEMSLOT_GMEM_ONLY;

I mean, we _could_ test that KVM ignores the hva for mapping, but that's a
different and unique test entirely.

I did break x86/private_mem_conversions_test (I could have sworn I tested, *sigh*),
but the bug is in:

  KVM: selftests: Provide function to look up guest_memfd details from gpa

not here.  And it's a trivial /facepalm-style fix:

diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index ee5b63f7cb50..23a8676fee6d 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -1680,7 +1680,7 @@ int kvm_gpa_to_guest_memfd(struct kvm_vm *vm, vm_paddr_t gpa, off_t *fd_offset,
        gpa_offset = gpa - region->region.guest_phys_addr;
        *fd_offset = region->region.guest_memfd_offset + gpa_offset;
        *nr_bytes = region->region.memory_size - gpa_offset;
-       return region->fd;
+       return region->region.guest_memfd;
 }
 
 /* Create an interrupt controller chip for the specified VM. */

Sean Christopherson <seanjc@google.com> writes:

> On Fri, Oct 24, 2025, Ackerley Tng wrote:
>> Ackerley Tng <ackerleytng@google.com> writes:
>> 
>> > From: Sean Christopherson <seanjc@google.com>
>> >
>> > Accept gmem_flags in vm_mem_add() to be able to create a guest_memfd within
>> > vm_mem_add().
>> >
>> > When vm_mem_add() is used to set up a guest_memfd for a memslot, set up the
>> > provided (or created) gmem_fd as the fd for the user memory region. This
>> > makes it available to be mmap()-ed from just like fds from other memory
>> > sources. mmap() from guest_memfd using the provided gmem_flags and
>> > gmem_offset.
>> >
>> > Add a kvm_slot_to_fd() helper to provide convenient access to the file
>> > descriptor of a memslot.
>> >
>> > Update existing callers of vm_mem_add() to pass 0 for gmem_flags to
>> > preserve existing behavior.
>> >
>> > Signed-off-by: Sean Christopherson <seanjc@google.com>
>> > [For guest_memfds, mmap() using gmem_offset instead of 0 all the time.]
>> > Signed-off-by: Ackerley Tng <ackerleytng@google.com>
>> > ---
>> >  tools/testing/selftests/kvm/include/kvm_util.h |  7 ++++++-
>> >  tools/testing/selftests/kvm/lib/kvm_util.c     | 18 ++++++++++--------
>> >  .../kvm/x86/private_mem_conversions_test.c     |  2 +-
>> >  3 files changed, 17 insertions(+), 10 deletions(-)
>> >
>> > 
>> > [...snip...]
>> > 
>> > @@ -1050,13 +1049,16 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
>> >  	}
>> >  
>> >  	region->fd = -1;
>> > -	if (backing_src_is_shared(src_type))
>> > +	if (flags & KVM_MEM_GUEST_MEMFD && gmem_flags & GUEST_MEMFD_FLAG_MMAP)
>> > +		region->fd = kvm_dup(gmem_fd);
>> > +	else if (backing_src_is_shared(src_type))
>> >  		region->fd = kvm_memfd_alloc(region->mmap_size,
>> >  					     src_type == VM_MEM_SRC_SHARED_HUGETLB);
>> >  
>> 
>> Doing this makes it hard to test the legacy dual-backing case.
>> 
>> It actually broke x86/private_mem_conversions_test for the legacy
>> dual-backing case because there's no way to mmap or provide a
>> userspace_address from the memory provider that is not guest_memfd, as
>> determined by src_type.
>
> Yes there is.  This patch is a giant nop.  The only thing that the core library
> doesn't support is mmap() on guest_memfd *and* the other src_type, and IMO that
> is big "don't care", because KVM doesn't even support that combination:
>
> 	if (kvm_gmem_supports_mmap(inode))
> 		slot->flags |= KVM_MEMSLOT_GMEM_ONLY;
>

Makes sense.

> I mean, we _could_ test that KVM ignores the hva for mapping, but that's a
> different and unique test entirely.
>
> I did break x86/private_mem_conversions_test (I could have sworn I tested, *sigh*),
> but the bug is in:
>
>   KVM: selftests: Provide function to look up guest_memfd details from gpa
>
> not here.  And it's a trivial /facepalm-style fix:
>
> diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
> index ee5b63f7cb50..23a8676fee6d 100644
> --- a/tools/testing/selftests/kvm/lib/kvm_util.c
> +++ b/tools/testing/selftests/kvm/lib/kvm_util.c
> @@ -1680,7 +1680,7 @@ int kvm_gpa_to_guest_memfd(struct kvm_vm *vm, vm_paddr_t gpa, off_t *fd_offset,
>         gpa_offset = gpa - region->region.guest_phys_addr;
>         *fd_offset = region->region.guest_memfd_offset + gpa_offset;
>         *nr_bytes = region->region.memory_size - gpa_offset;
> -       return region->fd;
> +       return region->region.guest_memfd;
>  }
>  
>  /* Create an interrupt controller chip for the specified VM. */

This works. Thanks!