* [PATCH v2 1/2] KVM: selftests: Wrap madvise() to assert success
2026-02-20 23:54 [PATCH v2 0/2] Test MADV_COLLAPSE on guest_memfd Ackerley Tng
@ 2026-02-20 23:54 ` Ackerley Tng
2026-02-20 23:54 ` [PATCH v2 2/2] KVM: selftests: Test MADV_COLLAPSE on guest_memfd Ackerley Tng
1 sibling, 0 replies; 3+ messages in thread
From: Ackerley Tng @ 2026-02-20 23:54 UTC (permalink / raw)
To: kartikey406, seanjc, pbonzini, shuah, kvm, linux-kselftest
Cc: vannapurve, Liam.Howlett, ackerleytng, akpm, baohua, baolin.wang,
david, dev.jain, i, lance.yang, linux-kernel, linux-mm,
lorenzo.stoakes, npache, ryan.roberts, shy828301, stable,
syzbot+33a04338019ac7e43a44, ziy
Extend kvm_syscalls.h to wrap madvise() to assert success. This will be
used in the next patch.
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
---
tools/testing/selftests/kvm/include/kvm_syscalls.h | 1 +
1 file changed, 1 insertion(+)
diff --git a/tools/testing/selftests/kvm/include/kvm_syscalls.h b/tools/testing/selftests/kvm/include/kvm_syscalls.h
index d4e613162bba9..843c9904c46f6 100644
--- a/tools/testing/selftests/kvm/include/kvm_syscalls.h
+++ b/tools/testing/selftests/kvm/include/kvm_syscalls.h
@@ -77,5 +77,6 @@ __KVM_SYSCALL_DEFINE(munmap, 2, void *, mem, size_t, size);
__KVM_SYSCALL_DEFINE(close, 1, int, fd);
__KVM_SYSCALL_DEFINE(fallocate, 4, int, fd, int, mode, loff_t, offset, loff_t, len);
__KVM_SYSCALL_DEFINE(ftruncate, 2, unsigned int, fd, off_t, length);
+__KVM_SYSCALL_DEFINE(madvise, 3, void *, addr, size_t, length, int, advice);
#endif /* SELFTEST_KVM_SYSCALLS_H */
--
2.53.0.345.g96ddfc5eaa-goog
^ permalink raw reply [flat|nested] 3+ messages in thread
* [PATCH v2 2/2] KVM: selftests: Test MADV_COLLAPSE on guest_memfd
2026-02-20 23:54 [PATCH v2 0/2] Test MADV_COLLAPSE on guest_memfd Ackerley Tng
2026-02-20 23:54 ` [PATCH v2 1/2] KVM: selftests: Wrap madvise() to assert success Ackerley Tng
@ 2026-02-20 23:54 ` Ackerley Tng
1 sibling, 0 replies; 3+ messages in thread
From: Ackerley Tng @ 2026-02-20 23:54 UTC (permalink / raw)
To: kartikey406, seanjc, pbonzini, shuah, kvm, linux-kselftest
Cc: vannapurve, Liam.Howlett, ackerleytng, akpm, baohua, baolin.wang,
david, dev.jain, i, lance.yang, linux-kernel, linux-mm,
lorenzo.stoakes, npache, ryan.roberts, shy828301, stable,
syzbot+33a04338019ac7e43a44, ziy
guest_memfd only supports PAGE_SIZE pages, and khugepaged or MADV_COLLAPSE
collapsing pages may result in private memory regions being mapped into
host page tables.
Add test to verify that MADV_COLLAPSE fails on guest_memfd folios, and any
subsequent usage of guest_memfd memory faults in PAGE_SIZE folios. Running
this test should not result in any memory failure logs or kernel WARNings.
This selftest was added as a result of a syzbot-reported issue where
khugepaged operating on guest_memfd memory with MADV_HUGEPAGE caused the
collapse of folios, which then subsequently resulted in a WARNing.
Link: https://syzkaller.appspot.com/bug?extid=33a04338019ac7e43a44
Suggested-by: David Hildenbrand <david@kernel.org>
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
---
.../testing/selftests/kvm/guest_memfd_test.c | 70 ++++++++++++++++++-
1 file changed, 67 insertions(+), 3 deletions(-)
diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c
index 618c937f3c90f..0edbc7cf6c1ad 100644
--- a/tools/testing/selftests/kvm/guest_memfd_test.c
+++ b/tools/testing/selftests/kvm/guest_memfd_test.c
@@ -171,6 +171,64 @@ static void test_numa_allocation(int fd, size_t total_size)
kvm_munmap(mem, total_size);
}
+static void test_collapse(int fd, uint64_t flags)
+{
+ const size_t pmd_size = get_trans_hugepagesz();
+ void *reserved_addr;
+ void *aligned_addr;
+ char *mem;
+ off_t i;
+
+ /*
+ * To even reach the point where the guest_memfd folios will
+ * get collapsed, both the userspace address and the offset
+ * within the guest_memfd have to be aligned to pmd_size.
+ *
+ * To achieve that alignment, reserve virtual address space
+ * with regular mmap, then use MAP_FIXED to allocate memory
+ * from a pmd_size-aligned offset (0) at a known, available
+ * virtual address.
+ */
+ reserved_addr = kvm_mmap(pmd_size * 2, PROT_NONE,
+ MAP_PRIVATE | MAP_ANONYMOUS, -1);
+ aligned_addr = align_ptr_up(reserved_addr, pmd_size);
+
+ mem = mmap(aligned_addr, pmd_size, PROT_READ | PROT_WRITE,
+ MAP_FIXED | MAP_SHARED, fd, 0);
+ TEST_ASSERT(IS_ALIGNED((u64)mem, pmd_size),
+ "Userspace address must be aligned to PMD size.");
+
+ /*
+ * Use reads to populate page table to avoid setting dirty
+ * flag on page.
+ */
+ for (i = 0; i < pmd_size; i += getpagesize())
+ READ_ONCE(mem[i]);
+
+ /*
+ * Advising the use of huge pages in guest_memfd should be
+ * fine...
+ */
+ kvm_madvise(mem, pmd_size, MADV_HUGEPAGE);
+
+ /*
+ * ... but collapsing folios must not be supported to avoid
+ * mapping beyond shared ranges into host userspace page
+ * tables.
+ */
+ TEST_ASSERT_EQ(madvise(mem, pmd_size, MADV_COLLAPSE), -1);
+ TEST_ASSERT_EQ(errno, EINVAL);
+
+ /*
+ * Removing from host page tables and re-faulting should be
+ * fine; should not end up faulting in a collapsed/huge folio.
+ */
+ kvm_madvise(mem, pmd_size, MADV_DONTNEED);
+ READ_ONCE(mem[0]);
+
+ kvm_munmap(reserved_addr, pmd_size * 2);
+}
+
static void test_fault_sigbus(int fd, size_t accessible_size, size_t map_size)
{
const char val = 0xaa;
@@ -350,14 +408,17 @@ static void test_guest_memfd_flags(struct kvm_vm *vm)
}
}
-#define gmem_test(__test, __vm, __flags) \
+#define __gmem_test(__test, __vm, __flags, __gmem_size) \
do { \
- int fd = vm_create_guest_memfd(__vm, page_size * 4, __flags); \
+ int fd = vm_create_guest_memfd(__vm, __gmem_size, __flags); \
\
- test_##__test(fd, page_size * 4); \
+ test_##__test(fd, __gmem_size); \
close(fd); \
} while (0)
+#define gmem_test(__test, __vm, __flags) \
+ __gmem_test(__test, __vm, __flags, page_size * 4)
+
static void __test_guest_memfd(struct kvm_vm *vm, uint64_t flags)
{
test_create_guest_memfd_multiple(vm);
@@ -367,9 +428,12 @@ static void __test_guest_memfd(struct kvm_vm *vm, uint64_t flags)
if (flags & GUEST_MEMFD_FLAG_MMAP) {
if (flags & GUEST_MEMFD_FLAG_INIT_SHARED) {
+ size_t pmd_size = get_trans_hugepagesz();
+
gmem_test(mmap_supported, vm, flags);
gmem_test(fault_overflow, vm, flags);
gmem_test(numa_allocation, vm, flags);
+ __gmem_test(collapse, vm, flags, pmd_size);
} else {
gmem_test(fault_private, vm, flags);
}
--
2.53.0.345.g96ddfc5eaa-goog
^ permalink raw reply [flat|nested] 3+ messages in thread