* [PATCH RFC v3 33/43] KVM: selftests: Make TEST_EXPECT_SIGBUS thread-safe
From: Ackerley Tng @ 2026-03-13 6:13 UTC (permalink / raw)
To: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jroedel, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
Ackerley Tng
In-Reply-To: <20260313-gmem-inplace-conversion-v3-0-5fc12a70ec89@google.com>
The TEST_EXPECT_SIGBUS macro is not thread-safe as it uses a global
sigjmp_buf and installs a global SIGBUS signal handler. If multiple threads
execute the macro concurrently, they will race on installing the signal
handler and stomp on other threads' jump buffers, leading to incorrect test
behavior.
Make TEST_EXPECT_SIGBUS thread-safe with the following changes:
Share the KVM tests' global signal handler. sigaction() applies to all
threads; without sharing a global signal handler, one thread may have
removed the signal handler that another thread added, hence leading to
unexpected signals.
The alternative of layering signal handlers was considered, but calling
sigaction() within TEST_EXPECT_SIGBUS() necessarily creates a race. To
avoid adding new setup and teardown routines to do sigaction() and keep
usage of TEST_EXPECT_SIGBUS() simple, share the KVM tests' global signal
handler.
Opportunistically rename report_unexpected_signal to
catchall_signal_handler.
To continue to only expect SIGBUS within specific regions of code, use a
thread-specific variable, expecting_sigbus, to replace installing and
removing signal handlers.
Make the execution environment for the thread, sigjmp_buf, a
thread-specific variable.
As part of TEST_EXPECT_SIGBUS(), assert the prerequisite for this setup,
that the current signal handler is the catchall_signal_handler.
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
---
tools/testing/selftests/kvm/include/test_util.h | 30 +++++++++++++------------
tools/testing/selftests/kvm/lib/kvm_util.c | 18 ++++++++++-----
tools/testing/selftests/kvm/lib/test_util.c | 7 ------
3 files changed, 29 insertions(+), 26 deletions(-)
diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
index 2871a42928471..63e57d189f5fd 100644
--- a/tools/testing/selftests/kvm/include/test_util.h
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -80,21 +80,23 @@ do { \
__builtin_unreachable(); \
} while (0)
-extern sigjmp_buf expect_sigbus_jmpbuf;
-void expect_sigbus_handler(int signum);
+extern __thread sigjmp_buf expect_sigbus_jmpbuf;
+extern __thread bool expecting_sigbus;
+extern void catchall_signal_handler(int signum);
-#define TEST_EXPECT_SIGBUS(action) \
-do { \
- struct sigaction sa_old, sa_new = { \
- .sa_handler = expect_sigbus_handler, \
- }; \
- \
- sigaction(SIGBUS, &sa_new, &sa_old); \
- if (sigsetjmp(expect_sigbus_jmpbuf, 1) == 0) { \
- action; \
- TEST_FAIL("'%s' should have triggered SIGBUS", #action); \
- } \
- sigaction(SIGBUS, &sa_old, NULL); \
+#define TEST_EXPECT_SIGBUS(action) \
+do { \
+ struct sigaction sa = {}; \
+ \
+ TEST_ASSERT_EQ(sigaction(SIGBUS, NULL, &sa), 0); \
+ TEST_ASSERT_EQ(sa.sa_handler, &catchall_signal_handler); \
+ \
+ expecting_sigbus = true; \
+ if (sigsetjmp(expect_sigbus_jmpbuf, 1) == 0) { \
+ action; \
+ TEST_FAIL("'%s' should have triggered SIGBUS", #action);\
+ } \
+ expecting_sigbus = false; \
} while (0)
size_t parse_size(const char *size);
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 6f7d3adb25d0a..f4aa762f050aa 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -2347,13 +2347,20 @@ __weak void kvm_selftest_arch_init(void)
{
}
-static void report_unexpected_signal(int signum)
+__thread sigjmp_buf expect_sigbus_jmpbuf;
+__thread bool expecting_sigbus;
+
+void catchall_signal_handler(int signum)
{
+ switch (signum) {
+ case SIGBUS: {
+ if (expecting_sigbus)
+ siglongjmp(expect_sigbus_jmpbuf, 1);
+
+ TEST_FAIL("Unexpected SIGBUS (%d)\n", signum);
+ }
#define KVM_CASE_SIGNUM(sig) \
case sig: TEST_FAIL("Unexpected " #sig " (%d)\n", signum)
-
- switch (signum) {
- KVM_CASE_SIGNUM(SIGBUS);
KVM_CASE_SIGNUM(SIGSEGV);
KVM_CASE_SIGNUM(SIGILL);
KVM_CASE_SIGNUM(SIGFPE);
@@ -2365,12 +2372,13 @@ static void report_unexpected_signal(int signum)
void __attribute((constructor)) kvm_selftest_init(void)
{
struct sigaction sig_sa = {
- .sa_handler = report_unexpected_signal,
+ .sa_handler = catchall_signal_handler,
};
/* Tell stdout not to buffer its content. */
setbuf(stdout, NULL);
+ expecting_sigbus = false;
sigaction(SIGBUS, &sig_sa, NULL);
sigaction(SIGSEGV, &sig_sa, NULL);
sigaction(SIGILL, &sig_sa, NULL);
diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c
index 8a1848586a857..03eb99af9b8de 100644
--- a/tools/testing/selftests/kvm/lib/test_util.c
+++ b/tools/testing/selftests/kvm/lib/test_util.c
@@ -18,13 +18,6 @@
#include "test_util.h"
-sigjmp_buf expect_sigbus_jmpbuf;
-
-void __attribute__((used)) expect_sigbus_handler(int signum)
-{
- siglongjmp(expect_sigbus_jmpbuf, 1);
-}
-
/*
* Random number generator that is usable from guest code. This is the
* Park-Miller LCG using standard constants.
--
2.53.0.851.ga537e3e6e9-goog
^ permalink raw reply related
* [PATCH RFC v3 32/43] KVM: selftests: Check fd/flags provided to mmap() when setting up memslot
From: Ackerley Tng @ 2026-03-13 6:13 UTC (permalink / raw)
To: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jroedel, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
Ackerley Tng
In-Reply-To: <20260313-gmem-inplace-conversion-v3-0-5fc12a70ec89@google.com>
From: Sean Christopherson <seanjc@google.com>
Check that a valid fd provided to mmap() must be accompanied by MAP_SHARED.
With an invalid fd (usually used for anonymous mappings), there are no
constraints on mmap() flags.
Add this check to make sure that when a guest_memfd is used as region->fd,
the flag provided to mmap() will include MAP_SHARED.
Signed-off-by: Sean Christopherson <seanjc@google.com>
[Rephrase assertion message.]
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
---
tools/testing/selftests/kvm/lib/kvm_util.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 6deb6b333a066..6f7d3adb25d0a 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -1095,6 +1095,9 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
src_type == VM_MEM_SRC_SHARED_HUGETLB);
}
+ TEST_ASSERT(region->fd == -1 || backing_src_is_shared(src_type),
+ "A valid fd provided to mmap() must be accompanied by MAP_SHARED.");
+
region->mmap_start = __kvm_mmap(region->mmap_size, PROT_READ | PROT_WRITE,
vm_mem_backing_src_alias(src_type)->flag,
region->fd, mmap_offset);
--
2.53.0.851.ga537e3e6e9-goog
^ permalink raw reply related
* [PATCH RFC v3 31/43] KVM: selftests: Provide common function to set memory attributes
From: Ackerley Tng @ 2026-03-13 6:13 UTC (permalink / raw)
To: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jroedel, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
Ackerley Tng
In-Reply-To: <20260313-gmem-inplace-conversion-v3-0-5fc12a70ec89@google.com>
From: Sean Christopherson <seanjc@google.com>
Introduce vm_mem_set_memory_attributes(), which handles setting of memory
attributes for a range of guest physical addresses, regardless of whether
the attributes should be set via guest_memfd or via the memory attributes
at the VM level.
Refactor existing vm_mem_set_{shared,private} functions to use the new
function.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Co-developed-by: Ackerley Tng <ackerleytng@google.com>
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
---
tools/testing/selftests/kvm/include/kvm_util.h | 44 +++++++++++++++++++-------
1 file changed, 32 insertions(+), 12 deletions(-)
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index f05f5ebf0c569..e4de0050d1ab3 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -456,18 +456,6 @@ static inline void vm_set_memory_attributes(struct kvm_vm *vm, uint64_t gpa,
vm_ioctl(vm, KVM_SET_MEMORY_ATTRIBUTES2, &attr);
}
-static inline void vm_mem_set_private(struct kvm_vm *vm, uint64_t gpa,
- uint64_t size)
-{
- vm_set_memory_attributes(vm, gpa, size, KVM_MEMORY_ATTRIBUTE_PRIVATE);
-}
-
-static inline void vm_mem_set_shared(struct kvm_vm *vm, uint64_t gpa,
- uint64_t size)
-{
- vm_set_memory_attributes(vm, gpa, size, 0);
-}
-
static inline int __gmem_set_memory_attributes(int fd, loff_t offset,
uint64_t size,
uint64_t attributes,
@@ -531,6 +519,38 @@ static inline void gmem_set_shared(int fd, loff_t offset, uint64_t size)
gmem_set_memory_attributes(fd, offset, size, 0);
}
+static inline void vm_mem_set_memory_attributes(struct kvm_vm *vm, uint64_t gpa,
+ uint64_t size, uint64_t attrs)
+{
+ if (kvm_has_gmem_attributes) {
+ uint64_t end = gpa + size;
+ uint64_t addr, len;
+ off_t fd_offset;
+ int fd;
+
+ for (addr = gpa; addr < end; addr += len) {
+ fd = kvm_gpa_to_guest_memfd(vm, addr, &fd_offset, &len);
+ len = min(end - addr, len);
+
+ gmem_set_memory_attributes(fd, fd_offset, len, attrs);
+ }
+ } else {
+ vm_set_memory_attributes(vm, gpa, size, attrs);
+ }
+}
+
+static inline void vm_mem_set_private(struct kvm_vm *vm, uint64_t gpa,
+ uint64_t size)
+{
+ vm_mem_set_memory_attributes(vm, gpa, size, KVM_MEMORY_ATTRIBUTE_PRIVATE);
+}
+
+static inline void vm_mem_set_shared(struct kvm_vm *vm, uint64_t gpa,
+ uint64_t size)
+{
+ vm_mem_set_memory_attributes(vm, gpa, size, 0);
+}
+
void vm_guest_mem_fallocate(struct kvm_vm *vm, uint64_t gpa, uint64_t size,
bool punch_hole);
--
2.53.0.851.ga537e3e6e9-goog
^ permalink raw reply related
* [PATCH RFC v3 30/43] KVM: selftests: Provide function to look up guest_memfd details from gpa
From: Ackerley Tng @ 2026-03-13 6:13 UTC (permalink / raw)
To: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jroedel, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
Ackerley Tng
In-Reply-To: <20260313-gmem-inplace-conversion-v3-0-5fc12a70ec89@google.com>
Introduce a new helper, kvm_gpa_to_guest_memfd(), to find the
guest_memfd-related details of a memory region that contains a given guest
physical address (GPA).
The function returns the file descriptor for the memfd, the offset into
the file that corresponds to the GPA, and the number of bytes remaining
in the region from that GPA.
kvm_gpa_to_guest_memfd() was factored out from vm_guest_mem_fallocate();
refactor vm_guest_mem_fallocate() to use the new helper.
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
Co-developed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
tools/testing/selftests/kvm/include/kvm_util.h | 3 +++
tools/testing/selftests/kvm/lib/kvm_util.c | 34 ++++++++++++++++----------
2 files changed, 24 insertions(+), 13 deletions(-)
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 1c0f41bf847d0..f05f5ebf0c569 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -427,6 +427,9 @@ static inline void vm_enable_cap(struct kvm_vm *vm, uint32_t cap, uint64_t arg0)
vm_ioctl(vm, KVM_ENABLE_CAP, &enable_cap);
}
+int kvm_gpa_to_guest_memfd(struct kvm_vm *vm, vm_paddr_t gpa, off_t *fd_offset,
+ uint64_t *nr_bytes);
+
/*
* KVM_SET_MEMORY_ATTRIBUTES overwrites _all_ attributes. These flows need
* significant enhancements to support multiple attributes.
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 404efb5318f09..6deb6b333a066 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -1291,27 +1291,19 @@ void vm_guest_mem_fallocate(struct kvm_vm *vm, uint64_t base, uint64_t size,
bool punch_hole)
{
const int mode = FALLOC_FL_KEEP_SIZE | (punch_hole ? FALLOC_FL_PUNCH_HOLE : 0);
- struct userspace_mem_region *region;
uint64_t end = base + size;
uint64_t gpa, len;
off_t fd_offset;
- int ret;
+ int fd, ret;
for (gpa = base; gpa < end; gpa += len) {
- uint64_t offset;
+ fd = kvm_gpa_to_guest_memfd(vm, gpa, &fd_offset, &len);
+ len = min(end - gpa, len);
- region = userspace_mem_region_find(vm, gpa, gpa);
- TEST_ASSERT(region && region->region.flags & KVM_MEM_GUEST_MEMFD,
- "Private memory region not found for GPA 0x%lx", gpa);
-
- offset = gpa - region->region.guest_phys_addr;
- fd_offset = region->region.guest_memfd_offset + offset;
- len = min_t(uint64_t, end - gpa, region->region.memory_size - offset);
-
- ret = fallocate(region->region.guest_memfd, mode, fd_offset, len);
+ ret = fallocate(fd, mode, fd_offset, len);
TEST_ASSERT(!ret, "fallocate() failed to %s at %lx (len = %lu), fd = %d, mode = %x, offset = %lx",
punch_hole ? "punch hole" : "allocate", gpa, len,
- region->region.guest_memfd, mode, fd_offset);
+ fd, mode, fd_offset);
}
}
@@ -1717,6 +1709,22 @@ void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa)
return (void *) ((uintptr_t) region->host_alias + offset);
}
+int kvm_gpa_to_guest_memfd(struct kvm_vm *vm, vm_paddr_t gpa, off_t *fd_offset,
+ uint64_t *nr_bytes)
+{
+ struct userspace_mem_region *region;
+ vm_paddr_t gpa_offset;
+
+ region = userspace_mem_region_find(vm, gpa, gpa);
+ TEST_ASSERT(region && region->region.flags & KVM_MEM_GUEST_MEMFD,
+ "guest_memfd memory region not found for GPA 0x%lx", gpa);
+
+ 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->region.guest_memfd;
+}
+
/* Create an interrupt controller chip for the specified VM. */
void vm_create_irqchip(struct kvm_vm *vm)
{
--
2.53.0.851.ga537e3e6e9-goog
^ permalink raw reply related
* [PATCH RFC v3 29/43] KVM: selftests: Reset shared memory after hole-punching
From: Ackerley Tng @ 2026-03-13 6:13 UTC (permalink / raw)
To: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jroedel, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
Ackerley Tng
In-Reply-To: <20260313-gmem-inplace-conversion-v3-0-5fc12a70ec89@google.com>
private_mem_conversions_test used to reset the shared memory that was used
for the test to an initial pattern at the end of each test iteration. Then,
it would punch out the pages, which would zero memory.
Without in-place conversion, the resetting would write shared memory, and
hole-punching will zero private memory, hence resetting the test to the
state at the beginning of the for loop.
With in-place conversion, resetting writes memory as shared, and
hole-punching zeroes the same physical memory, hence undoing the reset
done before the hole punch.
Move the resetting after the hole-punching, and reset the entire
PER_CPU_DATA_SIZE instead of just the tested range.
With in-place conversion, this zeroes and then resets the same physical
memory. Without in-place conversion, the private memory is zeroed, and the
shared memory is reset to init_p.
This is sufficient since at each test stage, the memory is assumed to start
as shared, and private memory is always assumed to start zeroed. Conversion
zeroes memory, so the future test stages will work as expected.
Fixes: 43f623f350ce1 ("KVM: selftests: Add x86-only selftest for private memory conversions")
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
---
tools/testing/selftests/kvm/x86/private_mem_conversions_test.c | 9 ++++++---
1 file changed, 6 insertions(+), 3 deletions(-)
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 41f6b38f04071..47f1eb9212591 100644
--- a/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c
+++ b/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c
@@ -202,15 +202,18 @@ static void guest_test_explicit_conversion(uint64_t base_gpa, bool do_fallocate)
guest_sync_shared(gpa, size, p3, p4);
memcmp_g(gpa, p4, size);
- /* Reset the shared memory back to the initial pattern. */
- memset((void *)gpa, init_p, size);
-
/*
* Free (via PUNCH_HOLE) *all* private memory so that the next
* iteration starts from a clean slate, e.g. with respect to
* whether or not there are pages/folios in guest_mem.
*/
guest_map_shared(base_gpa, PER_CPU_DATA_SIZE, true);
+
+ /*
+ * Hole-punching above zeroed private memory. Reset shared
+ * memory in preparation for the next GUEST_STAGE.
+ */
+ memset((void *)base_gpa, init_p, PER_CPU_DATA_SIZE);
}
}
--
2.53.0.851.ga537e3e6e9-goog
^ permalink raw reply related
* [PATCH RFC v3 28/43] KVM: selftests: Test conversion with elevated page refcount
From: Ackerley Tng @ 2026-03-13 6:13 UTC (permalink / raw)
To: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jroedel, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
Ackerley Tng
In-Reply-To: <20260313-gmem-inplace-conversion-v3-0-5fc12a70ec89@google.com>
Add a selftest to verify that converting a shared guest_memfd page to a
private page fails if the page has an elevated reference count.
When KVM converts a shared page to a private one, it expects the page to
have a reference count equal to the reference counts taken by the
filemap. If another kernel subsystem holds a reference to the page, for
example via pin_user_pages(), the conversion must be aborted.
This test uses vmsplice to increment the refcount of a specific page. The
reference is kept on the page by not reading data out from vmsplice's
destination pipe. It then attempts to convert a range of pages, including
the page with elevated refcount, from shared to private.
The test asserts that both bulk and single-page conversion attempts
correctly fail with EAGAIN for the pinned page. After the page is unpinned,
the test verifies that subsequent conversions succeed.
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
Co-developed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
.../selftests/kvm/guest_memfd_conversions_test.c | 78 ++++++++++++++++++++++
1 file changed, 78 insertions(+)
diff --git a/tools/testing/selftests/kvm/guest_memfd_conversions_test.c b/tools/testing/selftests/kvm/guest_memfd_conversions_test.c
index c1a9cc7c9fae6..8727474325451 100644
--- a/tools/testing/selftests/kvm/guest_memfd_conversions_test.c
+++ b/tools/testing/selftests/kvm/guest_memfd_conversions_test.c
@@ -396,6 +396,84 @@ GMEM_CONVERSION_TEST_INIT_SHARED(forked_accesses)
kvm_munmap(test_state, sizeof(*test_state));
}
+static int pin_pipe[2] = { -1, -1 };
+
+static void pin_pages(void *vaddr, uint64_t size)
+{
+ struct iovec iov = {
+ .iov_base = vaddr,
+ .iov_len = size,
+ };
+
+ if (pin_pipe[1] < 0)
+ TEST_ASSERT_EQ(pipe(pin_pipe), 0);
+
+ TEST_ASSERT_EQ(vmsplice(pin_pipe[1], &iov, 1, 0), size);
+}
+
+static void unpin_pages(void)
+{
+ close(pin_pipe[1]);
+ pin_pipe[1] = -1;
+ close(pin_pipe[0]);
+ pin_pipe[0] = -1;
+}
+
+static void test_convert_to_private_fails(test_data_t *t, loff_t pgoff,
+ size_t nr_pages,
+ loff_t expected_error_offset)
+{
+ loff_t offset = pgoff * page_size;
+ loff_t error_offset = -1ul;
+ int ret;
+
+ do {
+ ret = __gmem_set_private(t->gmem_fd, offset,
+ nr_pages * page_size, &error_offset);
+ } while (ret == -1 && errno == EINTR);
+ TEST_ASSERT(ret == -1 && errno == EAGAIN,
+ "Wanted EAGAIN on page %lu, got %d (ret = %d)", pgoff,
+ errno, ret);
+ TEST_ASSERT_EQ(error_offset, expected_error_offset);
+}
+
+GMEM_CONVERSION_MULTIPAGE_TEST_INIT_SHARED(elevated_refcount, 4)
+{
+ int i;
+
+ pin_pages(t->mem + test_page * page_size, page_size);
+
+ for (i = 0; i < nr_pages; i++)
+ test_shared(t, i, 0, 'A', 'B');
+
+ /*
+ * Converting in bulk should fail as long any page in the range has
+ * unexpected refcounts.
+ */
+ test_convert_to_private_fails(t, 0, nr_pages, test_page * page_size);
+
+ for (i = 0; i < nr_pages; i++) {
+ /*
+ * Converting page-wise should also fail as long any page in the
+ * range has unexpected refcounts.
+ */
+ if (i == test_page)
+ test_convert_to_private_fails(t, i, 1, test_page * page_size);
+ else
+ test_convert_to_private(t, i, 'B', 'C');
+ }
+
+ unpin_pages();
+
+ gmem_set_private(t->gmem_fd, 0, nr_pages * page_size);
+
+ for (i = 0; i < nr_pages; i++) {
+ char expected = i == test_page ? 'B' : 'C';
+
+ test_private(t, i, expected, 'D');
+ }
+}
+
int main(int argc, char *argv[])
{
TEST_REQUIRE(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SW_PROTECTED_VM));
--
2.53.0.851.ga537e3e6e9-goog
^ permalink raw reply related
* [PATCH RFC v3 27/43] KVM: selftests: Test that shared/private status is consistent across processes
From: Ackerley Tng @ 2026-03-13 6:13 UTC (permalink / raw)
To: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jroedel, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
Ackerley Tng
In-Reply-To: <20260313-gmem-inplace-conversion-v3-0-5fc12a70ec89@google.com>
From: Sean Christopherson <seanjc@google.com>
Add a test to verify that a guest_memfd's shared/private status is
consistent across processes, and that any shared pages previously mapped in
any process are unmapped from all processes.
The test forks a child process after creating the shared guest_memfd
region so that the second process exists alongside the main process for the
entire test.
The processes then take turns to access memory to check that the
shared/private status is consistent across processes.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Co-developed-by: Ackerley Tng <ackerleytng@google.com>
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
---
.../selftests/kvm/guest_memfd_conversions_test.c | 74 ++++++++++++++++++++++
1 file changed, 74 insertions(+)
diff --git a/tools/testing/selftests/kvm/guest_memfd_conversions_test.c b/tools/testing/selftests/kvm/guest_memfd_conversions_test.c
index 89881a71902e6..c1a9cc7c9fae6 100644
--- a/tools/testing/selftests/kvm/guest_memfd_conversions_test.c
+++ b/tools/testing/selftests/kvm/guest_memfd_conversions_test.c
@@ -322,6 +322,80 @@ GMEM_CONVERSION_TEST_INIT_SHARED(truncate)
test_private(t, 0, 0, 'A');
}
+/* Test that shared/private memory protections work and are seen from any process. */
+GMEM_CONVERSION_TEST_INIT_SHARED(forked_accesses)
+{
+ /*
+ * No races are intended in this test, shared memory is only used to
+ * coordinate between processes.
+ */
+ static enum {
+ STATE_INIT,
+ STATE_CHECK_SHARED,
+ STATE_DONE_CHECKING_SHARED,
+ STATE_CHECK_PRIVATE,
+ STATE_DONE_CHECKING_PRIVATE,
+ } *test_state;
+ pid_t child_pid;
+
+ test_state = kvm_mmap(sizeof(*test_state), PROT_READ | PROT_WRITE,
+ MAP_SHARED | MAP_ANONYMOUS, -1);
+
+#define TEST_STATE_AWAIT(__state) \
+ while (READ_ONCE(*test_state) != __state) { \
+ if (child_pid != 0) { \
+ int status; \
+ pid_t pid; \
+ do { \
+ pid = waitpid(child_pid, &status, WNOHANG); \
+ } while (pid == -1 && errno == EINTR); \
+ if (pid == -1) \
+ TEST_FAIL("Couldn't check child status."); \
+ else if (pid != 0) \
+ TEST_FAIL("Child exited prematurely."); \
+ } \
+ }
+
+#define TEST_STATE_SET(__state) WRITE_ONCE(*test_state, __state)
+
+ child_pid = fork();
+ TEST_ASSERT(child_pid != -1, "fork failed");
+
+ if (child_pid == 0) {
+ const char inconsequential = 0xdd;
+
+ TEST_STATE_AWAIT(STATE_CHECK_SHARED);
+
+ /*
+ * This maps the pages into the child process as well, and tests
+ * that the conversion process will unmap the guest_memfd memory
+ * from all processes.
+ */
+ host_do_rmw(t->mem, 0, 0xB, 0xC);
+
+ TEST_STATE_SET(STATE_DONE_CHECKING_SHARED);
+ TEST_STATE_AWAIT(STATE_CHECK_PRIVATE);
+
+ TEST_EXPECT_SIGBUS(READ_ONCE(t->mem[0]));
+ TEST_EXPECT_SIGBUS(WRITE_ONCE(t->mem[0], inconsequential));
+
+ TEST_STATE_SET(STATE_DONE_CHECKING_PRIVATE);
+ exit(0);
+ }
+
+ test_shared(t, 0, 0, 0xA, 0xB);
+
+ TEST_STATE_SET(STATE_CHECK_SHARED);
+ TEST_STATE_AWAIT(STATE_DONE_CHECKING_SHARED);
+
+ test_convert_to_private(t, 0, 0xC, 0xD);
+
+ TEST_STATE_SET(STATE_CHECK_PRIVATE);
+ TEST_STATE_AWAIT(STATE_DONE_CHECKING_PRIVATE);
+
+ kvm_munmap(test_state, sizeof(*test_state));
+}
+
int main(int argc, char *argv[])
{
TEST_REQUIRE(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SW_PROTECTED_VM));
--
2.53.0.851.ga537e3e6e9-goog
^ permalink raw reply related
* [PATCH RFC v3 26/43] KVM: selftests: Test that truncation does not change shared/private status
From: Ackerley Tng @ 2026-03-13 6:13 UTC (permalink / raw)
To: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jroedel, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
Ackerley Tng
In-Reply-To: <20260313-gmem-inplace-conversion-v3-0-5fc12a70ec89@google.com>
Add a test to verify that deallocating a page in a guest memfd region via
fallocate() with FALLOC_FL_PUNCH_HOLE does not alter the shared or private
status of the corresponding memory range.
When a page backing a guest memfd mapping is deallocated, e.g., by punching
a hole or truncating the file, and then subsequently faulted back in, the
new page must inherit the correct shared/private status tracked by
guest_memfd.
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
Co-developed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
tools/testing/selftests/kvm/guest_memfd_conversions_test.c | 14 ++++++++++++++
1 file changed, 14 insertions(+)
diff --git a/tools/testing/selftests/kvm/guest_memfd_conversions_test.c b/tools/testing/selftests/kvm/guest_memfd_conversions_test.c
index b109f078bc6bd..89881a71902e6 100644
--- a/tools/testing/selftests/kvm/guest_memfd_conversions_test.c
+++ b/tools/testing/selftests/kvm/guest_memfd_conversions_test.c
@@ -10,6 +10,7 @@
#include <linux/sizes.h>
#include "kvm_util.h"
+#include "kvm_syscalls.h"
#include "kselftest_harness.h"
#include "test_util.h"
#include "ucall_common.h"
@@ -308,6 +309,19 @@ GMEM_CONVERSION_MULTIPAGE_TEST_INIT_SHARED(unallocated_folios, 8)
test_convert_to_shared(t, i, 'B', 'C', 'D');
}
+/* Truncation should not affect shared/private status. */
+GMEM_CONVERSION_TEST_INIT_SHARED(truncate)
+{
+ host_do_rmw(t->mem, 0, 0, 'A');
+ kvm_fallocate(t->gmem_fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, 0, page_size);
+ host_do_rmw(t->mem, 0, 0, 'A');
+
+ test_convert_to_private(t, 0, 'A', 'B');
+
+ kvm_fallocate(t->gmem_fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, 0, page_size);
+ test_private(t, 0, 0, 'A');
+}
+
int main(int argc, char *argv[])
{
TEST_REQUIRE(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SW_PROTECTED_VM));
--
2.53.0.851.ga537e3e6e9-goog
^ permalink raw reply related
* [PATCH RFC v3 25/43] KVM: selftests: Test precision of conversion
From: Ackerley Tng @ 2026-03-13 6:13 UTC (permalink / raw)
To: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jroedel, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
Ackerley Tng
In-Reply-To: <20260313-gmem-inplace-conversion-v3-0-5fc12a70ec89@google.com>
Enhance the guest_memfd indexing selftest to also verify the precision of
memory conversions between private and shared.
The existing test converted a single page within a multi-page mapping but
did not explicitly check the state of the surrounding pages after the
conversion loop.
Add checks to confirm that converting a single page from shared to private
only affects the target page. Iterate through all other pages in the
guest_memfd region to ensure they remain in their original shared state,
thus verifying that the conversion operation is precise and does not have
unintended side effects.
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
---
tools/testing/selftests/kvm/guest_memfd_conversions_test.c | 13 +++++++++++--
1 file changed, 11 insertions(+), 2 deletions(-)
diff --git a/tools/testing/selftests/kvm/guest_memfd_conversions_test.c b/tools/testing/selftests/kvm/guest_memfd_conversions_test.c
index 9dc47316112fa..b109f078bc6bd 100644
--- a/tools/testing/selftests/kvm/guest_memfd_conversions_test.c
+++ b/tools/testing/selftests/kvm/guest_memfd_conversions_test.c
@@ -227,7 +227,8 @@ GMEM_CONVERSION_TEST_INIT_SHARED(init_shared)
/*
* Test indexing of pages within guest_memfd, using test data that is a multiple
- * of page index.
+ * of page index. Also test the precision of conversion, that it does not
+ * affect surrounding pages.
*/
GMEM_CONVERSION_MULTIPAGE_TEST_INIT_SHARED(indexing, 4)
{
@@ -247,12 +248,20 @@ GMEM_CONVERSION_MULTIPAGE_TEST_INIT_SHARED(indexing, 4)
test_shared(t, i, i * 2, i * 3, i * 4);
}
+ /* Confirm that only one page was converted */
for (i = 0; i < nr_pages; ++i) {
if (i == test_page)
- test_convert_to_shared(t, i, i * 4, i * 5, i * 6);
+ test_private(t, i, i * 4, i * 6);
else
test_shared(t, i, i * 4, i * 5, i * 6);
}
+
+ for (i = 0; i < nr_pages; ++i) {
+ if (i == test_page)
+ test_convert_to_shared(t, i, i * 6, i * 7, i * 8);
+ else
+ test_shared(t, i, i * 6, i * 7, i * 8);
+ }
}
/*
--
2.53.0.851.ga537e3e6e9-goog
^ permalink raw reply related
* [PATCH RFC v3 24/43] KVM: selftests: Convert with allocated folios in different layouts
From: Ackerley Tng @ 2026-03-13 6:13 UTC (permalink / raw)
To: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jroedel, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
Ackerley Tng
In-Reply-To: <20260313-gmem-inplace-conversion-v3-0-5fc12a70ec89@google.com>
Add a guest_memfd selftest to verify that memory conversions work
correctly with allocated folios in different layouts.
By iterating through which pages are initially faulted, the test covers
various layouts of contiguous allocated and unallocated regions, exercising
conversion with different range layouts.
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
Co-developed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
.../selftests/kvm/guest_memfd_conversions_test.c | 30 ++++++++++++++++++++++
1 file changed, 30 insertions(+)
diff --git a/tools/testing/selftests/kvm/guest_memfd_conversions_test.c b/tools/testing/selftests/kvm/guest_memfd_conversions_test.c
index b48aa5d9f8cd4..9dc47316112fa 100644
--- a/tools/testing/selftests/kvm/guest_memfd_conversions_test.c
+++ b/tools/testing/selftests/kvm/guest_memfd_conversions_test.c
@@ -269,6 +269,36 @@ GMEM_CONVERSION_TEST_INIT_PRIVATE(before_allocation_private)
test_convert_to_shared(t, 0, 0, 'A', 'B');
}
+/*
+ * Test that when some of the folios in the conversion range are allocated,
+ * conversion requests are handled correctly in guest_memfd. Vary the ranges
+ * allocated before conversion, using test_page, to cover various layouts of
+ * contiguous allocated and unallocated regions.
+ */
+GMEM_CONVERSION_MULTIPAGE_TEST_INIT_SHARED(unallocated_folios, 8)
+{
+ const int second_page_to_fault = 4;
+ int i;
+
+ /*
+ * Fault 2 of the pages to test filemap range operations except when
+ * test_page == second_page_to_fault.
+ */
+ host_do_rmw(t->mem, test_page, 0, 'A');
+ if (test_page != second_page_to_fault)
+ host_do_rmw(t->mem, second_page_to_fault, 0, 'A');
+
+ gmem_set_private(t->gmem_fd, 0, nr_pages * page_size);
+ for (i = 0; i < nr_pages; ++i) {
+ char expected = (i == test_page || i == second_page_to_fault) ? 'A' : 0;
+
+ test_private(t, i, expected, 'B');
+ }
+
+ for (i = 0; i < nr_pages; ++i)
+ test_convert_to_shared(t, i, 'B', 'C', 'D');
+}
+
int main(int argc, char *argv[])
{
TEST_REQUIRE(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SW_PROTECTED_VM));
--
2.53.0.851.ga537e3e6e9-goog
^ permalink raw reply related
* [PATCH RFC v3 23/43] KVM: selftests: Test conversion before allocation
From: Ackerley Tng @ 2026-03-13 6:13 UTC (permalink / raw)
To: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jroedel, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
Ackerley Tng
In-Reply-To: <20260313-gmem-inplace-conversion-v3-0-5fc12a70ec89@google.com>
Add two test cases to the guest_memfd conversions selftest to cover
the scenario where a conversion is requested before any memory has been
allocated in the guest_memfd region.
The KVM_MEMORY_CONVERT_GUEST ioctl can be called on a memory region at any
time. If the guest has not yet faulted in any pages for that region, the
kernel must record the conversion request and apply the requested state
when the pages are eventually allocated.
The new tests cover both conversion directions.
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
Co-developed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
tools/testing/selftests/kvm/guest_memfd_conversions_test.c | 14 ++++++++++++++
1 file changed, 14 insertions(+)
diff --git a/tools/testing/selftests/kvm/guest_memfd_conversions_test.c b/tools/testing/selftests/kvm/guest_memfd_conversions_test.c
index 8044581d5e5e6..b48aa5d9f8cd4 100644
--- a/tools/testing/selftests/kvm/guest_memfd_conversions_test.c
+++ b/tools/testing/selftests/kvm/guest_memfd_conversions_test.c
@@ -255,6 +255,20 @@ GMEM_CONVERSION_MULTIPAGE_TEST_INIT_SHARED(indexing, 4)
}
}
+/*
+ * Test that even if there are no folios yet, conversion requests are recorded
+ * in guest_memfd.
+ */
+GMEM_CONVERSION_TEST_INIT_SHARED(before_allocation_shared)
+{
+ test_convert_to_private(t, 0, 0, 'A');
+}
+
+GMEM_CONVERSION_TEST_INIT_PRIVATE(before_allocation_private)
+{
+ test_convert_to_shared(t, 0, 0, 'A', 'B');
+}
+
int main(int argc, char *argv[])
{
TEST_REQUIRE(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SW_PROTECTED_VM));
--
2.53.0.851.ga537e3e6e9-goog
^ permalink raw reply related
* [PATCH RFC v3 22/43] KVM: selftests: Test indexing in guest_memfd
From: Ackerley Tng @ 2026-03-13 6:13 UTC (permalink / raw)
To: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jroedel, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
Ackerley Tng
In-Reply-To: <20260313-gmem-inplace-conversion-v3-0-5fc12a70ec89@google.com>
The existing guest_memfd conversion tests only use single-page memory
regions. This provides no coverage for multi-page guest_memfd objects,
specifically whether KVM correctly handles the page index for conversion
operations. An incorrect implementation could, for example, always operate
on the first page regardless of the index provided.
Add a new test case to verify that conversions between private and shared
memory correctly target the specified page within a multi-page guest_memfd.
To support this test, add a new GMEM_CONVERSION_MULTIPAGE_TEST_INIT_SHARED
macro that handles setting up and tearing down the VM for each page
iteration. The teardown logic is adjusted to prevent a double-free in this
new scenario.
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
Co-developed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
.../selftests/kvm/guest_memfd_conversions_test.c | 56 ++++++++++++++++++++++
1 file changed, 56 insertions(+)
diff --git a/tools/testing/selftests/kvm/guest_memfd_conversions_test.c b/tools/testing/selftests/kvm/guest_memfd_conversions_test.c
index 438937980f040..8044581d5e5e6 100644
--- a/tools/testing/selftests/kvm/guest_memfd_conversions_test.c
+++ b/tools/testing/selftests/kvm/guest_memfd_conversions_test.c
@@ -63,6 +63,9 @@ static void gmem_conversions_do_teardown(test_data_t *t)
{
/* No need to close gmem_fd, it's owned by the VM structure. */
kvm_vm_free(t->vcpu->vm);
+
+ /* NULL this out to avoid second free on full teardown in multipage tests. */
+ t->vcpu->vm = NULL;
}
FIXTURE_TEARDOWN(gmem_conversions)
@@ -101,6 +104,29 @@ static void __gmem_conversions_##test(test_data_t *t, int nr_pages) \
#define GMEM_CONVERSION_TEST_INIT_SHARED(test) \
__GMEM_CONVERSION_TEST_INIT_SHARED(test, 1)
+/*
+ * Repeats test over nr_pages in a guest_memfd of size nr_pages, providing each
+ * test iteration with test_page, the index of the page under test in
+ * guest_memfd. test_page takes values 0..(nr_pages - 1) inclusive.
+ */
+#define GMEM_CONVERSION_MULTIPAGE_TEST_INIT_SHARED(test, __nr_pages) \
+static void __gmem_conversions_multipage_##test(test_data_t *t, int nr_pages, \
+ const int test_page); \
+ \
+TEST_F(gmem_conversions, test) \
+{ \
+ const uint64_t flags = GUEST_MEMFD_FLAG_MMAP | GUEST_MEMFD_FLAG_INIT_SHARED; \
+ int i; \
+ \
+ for (i = 0; i < __nr_pages; ++i) { \
+ gmem_conversions_do_setup(self, __nr_pages, flags); \
+ __gmem_conversions_multipage_##test(self, __nr_pages, i); \
+ gmem_conversions_do_teardown(self); \
+ } \
+} \
+static void __gmem_conversions_multipage_##test(test_data_t *t, int nr_pages, \
+ const int test_page)
+
struct guest_check_data {
void *mem;
char expected_val;
@@ -199,6 +225,36 @@ GMEM_CONVERSION_TEST_INIT_SHARED(init_shared)
test_convert_to_shared(t, 0, 'C', 'D', 'E');
}
+/*
+ * Test indexing of pages within guest_memfd, using test data that is a multiple
+ * of page index.
+ */
+GMEM_CONVERSION_MULTIPAGE_TEST_INIT_SHARED(indexing, 4)
+{
+ int i;
+
+ /*
+ * Start with the highest index, to catch any errors when, perhaps, the
+ * first page is returned even for the last index.
+ */
+ for (i = nr_pages - 1; i >= 0; --i)
+ test_shared(t, i, 0, i, i * 2);
+
+ for (i = 0; i < nr_pages; ++i) {
+ if (i == test_page)
+ test_convert_to_private(t, i, i * 2, i * 4);
+ else
+ test_shared(t, i, i * 2, i * 3, i * 4);
+ }
+
+ for (i = 0; i < nr_pages; ++i) {
+ if (i == test_page)
+ test_convert_to_shared(t, i, i * 4, i * 5, i * 6);
+ else
+ test_shared(t, i, i * 4, i * 5, i * 6);
+ }
+}
+
int main(int argc, char *argv[])
{
TEST_REQUIRE(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SW_PROTECTED_VM));
--
2.53.0.851.ga537e3e6e9-goog
^ permalink raw reply related
* [PATCH RFC v3 21/43] KVM: selftests: Test conversion flow when INIT_SHARED
From: Ackerley Tng @ 2026-03-13 6:13 UTC (permalink / raw)
To: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jroedel, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
Ackerley Tng
In-Reply-To: <20260313-gmem-inplace-conversion-v3-0-5fc12a70ec89@google.com>
Add a test case to verify that conversions between private and shared
memory work correctly when the memory is initially created as shared.
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
Co-developed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
tools/testing/selftests/kvm/guest_memfd_conversions_test.c | 12 ++++++++++++
1 file changed, 12 insertions(+)
diff --git a/tools/testing/selftests/kvm/guest_memfd_conversions_test.c b/tools/testing/selftests/kvm/guest_memfd_conversions_test.c
index 48265215f218e..438937980f040 100644
--- a/tools/testing/selftests/kvm/guest_memfd_conversions_test.c
+++ b/tools/testing/selftests/kvm/guest_memfd_conversions_test.c
@@ -95,6 +95,12 @@ static void __gmem_conversions_##test(test_data_t *t, int nr_pages) \
#define GMEM_CONVERSION_TEST_INIT_PRIVATE(test) \
__GMEM_CONVERSION_TEST_INIT_PRIVATE(test, 1)
+#define __GMEM_CONVERSION_TEST_INIT_SHARED(test, __nr_pages) \
+ GMEM_CONVERSION_TEST(test, __nr_pages, GUEST_MEMFD_FLAG_INIT_SHARED)
+
+#define GMEM_CONVERSION_TEST_INIT_SHARED(test) \
+ __GMEM_CONVERSION_TEST_INIT_SHARED(test, 1)
+
struct guest_check_data {
void *mem;
char expected_val;
@@ -186,6 +192,12 @@ GMEM_CONVERSION_TEST_INIT_PRIVATE(init_private)
test_convert_to_private(t, 0, 'C', 'E');
}
+GMEM_CONVERSION_TEST_INIT_SHARED(init_shared)
+{
+ test_shared(t, 0, 0, 'A', 'B');
+ test_convert_to_private(t, 0, 'B', 'C');
+ test_convert_to_shared(t, 0, 'C', 'D', 'E');
+}
int main(int argc, char *argv[])
{
--
2.53.0.851.ga537e3e6e9-goog
^ permalink raw reply related
* [PATCH RFC v3 20/43] KVM: selftests: Test basic single-page conversion flow
From: Ackerley Tng @ 2026-03-13 6:12 UTC (permalink / raw)
To: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jroedel, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
Ackerley Tng
In-Reply-To: <20260313-gmem-inplace-conversion-v3-0-5fc12a70ec89@google.com>
Add a selftest for the guest_memfd memory attribute conversion ioctls.
The test starts the guest_memfd as all-private (the default state), and
verifies the basic flow of converting a single page to shared and then back
to private.
Add infrastructure that supports extensions to other conversion flow
tests. This infrastructure will be used in upcoming patches for other
conversion tests.
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
Co-developed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
tools/testing/selftests/kvm/Makefile.kvm | 1 +
.../selftests/kvm/guest_memfd_conversions_test.c | 199 +++++++++++++++++++++
2 files changed, 200 insertions(+)
diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm
index dc68371f76a33..0e2a9adfca57e 100644
--- a/tools/testing/selftests/kvm/Makefile.kvm
+++ b/tools/testing/selftests/kvm/Makefile.kvm
@@ -147,6 +147,7 @@ TEST_GEN_PROGS_x86 += access_tracking_perf_test
TEST_GEN_PROGS_x86 += coalesced_io_test
TEST_GEN_PROGS_x86 += dirty_log_perf_test
TEST_GEN_PROGS_x86 += guest_memfd_test
+TEST_GEN_PROGS_x86 += guest_memfd_conversions_test
TEST_GEN_PROGS_x86 += hardware_disable_test
TEST_GEN_PROGS_x86 += memslot_modification_stress_test
TEST_GEN_PROGS_x86 += memslot_perf_test
diff --git a/tools/testing/selftests/kvm/guest_memfd_conversions_test.c b/tools/testing/selftests/kvm/guest_memfd_conversions_test.c
new file mode 100644
index 0000000000000..48265215f218e
--- /dev/null
+++ b/tools/testing/selftests/kvm/guest_memfd_conversions_test.c
@@ -0,0 +1,199 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2024, Google LLC.
+ */
+#include <sys/mman.h>
+#include <unistd.h>
+
+#include <linux/align.h>
+#include <linux/kvm.h>
+#include <linux/sizes.h>
+
+#include "kvm_util.h"
+#include "kselftest_harness.h"
+#include "test_util.h"
+#include "ucall_common.h"
+
+FIXTURE(gmem_conversions) {
+ struct kvm_vcpu *vcpu;
+ int gmem_fd;
+ /* HVA of the first byte of the memory mmap()-ed from gmem_fd. */
+ char *mem;
+};
+
+typedef FIXTURE_DATA(gmem_conversions) test_data_t;
+
+FIXTURE_SETUP(gmem_conversions) { }
+
+static uint64_t page_size;
+
+static void guest_do_rmw(void);
+#define GUEST_MEMFD_SHARING_TEST_GVA 0x90000000ULL
+
+/*
+ * Defer setup until the individual test is invoked so that tests can specify
+ * the number of pages and flags for the guest_memfd instance.
+ */
+static void gmem_conversions_do_setup(test_data_t *t, int nr_pages,
+ int gmem_flags)
+{
+ const struct vm_shape shape = {
+ .mode = VM_MODE_DEFAULT,
+ .type = KVM_X86_SW_PROTECTED_VM,
+ };
+ /*
+ * Use high GPA above APIC_DEFAULT_PHYS_BASE to avoid clashing with
+ * APIC_DEFAULT_PHYS_BASE.
+ */
+ const uint64_t gpa = SZ_4G;
+ const uint32_t slot = 1;
+ struct kvm_vm *vm;
+
+ vm = __vm_create_shape_with_one_vcpu(shape, &t->vcpu, nr_pages, guest_do_rmw);
+
+ vm_mem_add(vm, VM_MEM_SRC_SHMEM, gpa, slot, nr_pages,
+ KVM_MEM_GUEST_MEMFD, -1, 0, gmem_flags);
+
+ t->gmem_fd = kvm_slot_to_fd(vm, slot);
+ t->mem = addr_gpa2hva(vm, gpa);
+ virt_map(vm, GUEST_MEMFD_SHARING_TEST_GVA, gpa, nr_pages);
+}
+
+static void gmem_conversions_do_teardown(test_data_t *t)
+{
+ /* No need to close gmem_fd, it's owned by the VM structure. */
+ kvm_vm_free(t->vcpu->vm);
+}
+
+FIXTURE_TEARDOWN(gmem_conversions)
+{
+ gmem_conversions_do_teardown(self);
+}
+
+/*
+ * In these test definition macros, __nr_pages and nr_pages is used to set up
+ * the total number of pages in the guest_memfd under test. This will be
+ * available in the test definitions as nr_pages.
+ */
+
+#define __GMEM_CONVERSION_TEST(test, __nr_pages, flags) \
+static void __gmem_conversions_##test(test_data_t *t, int nr_pages); \
+ \
+TEST_F(gmem_conversions, test) \
+{ \
+ gmem_conversions_do_setup(self, __nr_pages, flags); \
+ __gmem_conversions_##test(self, __nr_pages); \
+} \
+static void __gmem_conversions_##test(test_data_t *t, int nr_pages) \
+
+#define GMEM_CONVERSION_TEST(test, __nr_pages, flags) \
+ __GMEM_CONVERSION_TEST(test, __nr_pages, (flags) | GUEST_MEMFD_FLAG_MMAP)
+
+#define __GMEM_CONVERSION_TEST_INIT_PRIVATE(test, __nr_pages) \
+ GMEM_CONVERSION_TEST(test, __nr_pages, 0)
+
+#define GMEM_CONVERSION_TEST_INIT_PRIVATE(test) \
+ __GMEM_CONVERSION_TEST_INIT_PRIVATE(test, 1)
+
+struct guest_check_data {
+ void *mem;
+ char expected_val;
+ char write_val;
+};
+static struct guest_check_data guest_data;
+
+static void guest_do_rmw(void)
+{
+ for (;;) {
+ char *mem = READ_ONCE(guest_data.mem);
+
+ GUEST_ASSERT_EQ(READ_ONCE(*mem), READ_ONCE(guest_data.expected_val));
+ WRITE_ONCE(*mem, READ_ONCE(guest_data.write_val));
+
+ GUEST_SYNC(0);
+ }
+}
+
+static void run_guest_do_rmw(struct kvm_vcpu *vcpu, loff_t pgoff,
+ char expected_val, char write_val)
+{
+ struct ucall uc;
+ int r;
+
+ guest_data.mem = (void *)GUEST_MEMFD_SHARING_TEST_GVA + pgoff * page_size;
+ guest_data.expected_val = expected_val;
+ guest_data.write_val = write_val;
+ sync_global_to_guest(vcpu->vm, guest_data);
+
+ do {
+ r = __vcpu_run(vcpu);
+ } while (r == -1 && errno == EINTR);
+
+ TEST_ASSERT_EQ(r, 0);
+
+ switch (get_ucall(vcpu, &uc)) {
+ case UCALL_ABORT:
+ REPORT_GUEST_ASSERT(uc);
+ case UCALL_SYNC:
+ break;
+ default:
+ TEST_FAIL("Unexpected ucall %lu", uc.cmd);
+ }
+}
+
+static void host_do_rmw(char *mem, loff_t pgoff, char expected_val,
+ char write_val)
+{
+ TEST_ASSERT_EQ(READ_ONCE(mem[pgoff * page_size]), expected_val);
+ WRITE_ONCE(mem[pgoff * page_size], write_val);
+}
+
+static void test_private(test_data_t *t, loff_t pgoff, char starting_val,
+ char write_val)
+{
+ TEST_EXPECT_SIGBUS(WRITE_ONCE(t->mem[pgoff * page_size], write_val));
+ run_guest_do_rmw(t->vcpu, pgoff, starting_val, write_val);
+ TEST_EXPECT_SIGBUS(READ_ONCE(t->mem[pgoff * page_size]));
+}
+
+static void test_convert_to_private(test_data_t *t, loff_t pgoff,
+ char starting_val, char write_val)
+{
+ gmem_set_private(t->gmem_fd, pgoff * page_size, page_size);
+ test_private(t, pgoff, starting_val, write_val);
+}
+
+static void test_shared(test_data_t *t, loff_t pgoff, char starting_val,
+ char host_write_val, char write_val)
+{
+ host_do_rmw(t->mem, pgoff, starting_val, host_write_val);
+ run_guest_do_rmw(t->vcpu, pgoff, host_write_val, write_val);
+ TEST_ASSERT_EQ(READ_ONCE(t->mem[pgoff * page_size]), write_val);
+}
+
+static void test_convert_to_shared(test_data_t *t, loff_t pgoff,
+ char starting_val, char host_write_val,
+ char write_val)
+{
+ gmem_set_shared(t->gmem_fd, pgoff * page_size, page_size);
+ test_shared(t, pgoff, starting_val, host_write_val, write_val);
+}
+
+GMEM_CONVERSION_TEST_INIT_PRIVATE(init_private)
+{
+ test_private(t, 0, 0, 'A');
+ test_convert_to_shared(t, 0, 'A', 'B', 'C');
+ test_convert_to_private(t, 0, 'C', 'E');
+}
+
+
+int main(int argc, char *argv[])
+{
+ TEST_REQUIRE(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SW_PROTECTED_VM));
+ TEST_REQUIRE(kvm_check_cap(KVM_CAP_GUEST_MEMFD_MEMORY_ATTRIBUTES) &
+ KVM_MEMORY_ATTRIBUTE_PRIVATE);
+
+ page_size = getpagesize();
+
+ return test_harness_run(argc, argv);
+}
--
2.53.0.851.ga537e3e6e9-goog
^ permalink raw reply related
* [PATCH RFC v3 19/43] KVM: selftests: Test using guest_memfd for guest private memory
From: Ackerley Tng @ 2026-03-13 6:12 UTC (permalink / raw)
To: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jroedel, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
Ackerley Tng
In-Reply-To: <20260313-gmem-inplace-conversion-v3-0-5fc12a70ec89@google.com>
Add a selftest to verify that a memory region backed by a guest_memfd
can be used as private guest memory. This is a key use case for
confidential computing guests where the host should not have access to the
guest's memory contents.
The new test, test_guest_private_mem, creates a protected VM, maps a
guest_memfd into the guest's address space, and then marks the region as
private. The guest code then writes to and reads from this private memory
region to verify it is accessible.
To better distinguish between the test cases, rename the existing test
that verifies shared host/guest access from test_guest_memfd_guest to
test_guest_shared_mem.
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
---
tools/testing/selftests/kvm/guest_memfd_test.c | 57 ++++++++++++++++++++++++--
1 file changed, 53 insertions(+), 4 deletions(-)
diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c
index cc329b57ce2e9..10b57fd4fa9ba 100644
--- a/tools/testing/selftests/kvm/guest_memfd_test.c
+++ b/tools/testing/selftests/kvm/guest_memfd_test.c
@@ -406,7 +406,7 @@ static void test_guest_memfd(unsigned long vm_type)
kvm_vm_free(vm);
}
-static void guest_code(uint8_t *mem, uint64_t size)
+static void guest_code_test_guest_shared_mem(uint8_t *mem, uint64_t size)
{
size_t i;
@@ -418,7 +418,7 @@ static void guest_code(uint8_t *mem, uint64_t size)
GUEST_DONE();
}
-static void test_guest_memfd_guest(void)
+static void test_guest_shared_mem(void)
{
/*
* Skip the first 4gb and slot0. slot0 maps <1gb and is used to back
@@ -437,7 +437,8 @@ static void test_guest_memfd_guest(void)
if (!kvm_check_cap(KVM_CAP_GUEST_MEMFD_FLAGS))
return;
- vm = __vm_create_shape_with_one_vcpu(VM_SHAPE_DEFAULT, &vcpu, 1, guest_code);
+ vm = __vm_create_shape_with_one_vcpu(VM_SHAPE_DEFAULT, &vcpu, 1,
+ guest_code_test_guest_shared_mem);
TEST_ASSERT(vm_check_cap(vm, KVM_CAP_GUEST_MEMFD_FLAGS) & GUEST_MEMFD_FLAG_MMAP,
"Default VM type should support MMAP, supported flags = 0x%x",
@@ -469,6 +470,53 @@ static void test_guest_memfd_guest(void)
kvm_vm_free(vm);
}
+static void guest_code_test_guest_private_mem(uint8_t *mem)
+{
+ WRITE_ONCE(mem[0], 0xff);
+ GUEST_ASSERT_EQ(READ_ONCE(mem[0]), 0xff);
+
+ GUEST_DONE();
+}
+
+static void test_guest_private_mem(void)
+{
+ const struct vm_shape shape = {
+ .mode = VM_MODE_DEFAULT,
+ .type = KVM_X86_SW_PROTECTED_VM,
+ };
+ /*
+ * Skip the first 4gb and slot0. slot0 maps <1gb and is used to back
+ * the guest's code, stack, and page tables, and low memory contains
+ * the PCI hole and other MMIO regions that need to be avoided.
+ */
+ const uint64_t gpa = SZ_4G;
+ const int slot = 1;
+
+ struct kvm_vcpu *vcpu;
+ struct kvm_vm *vm;
+ size_t npages;
+ int fd;
+
+ npages = page_size / getpagesize();
+ vm = __vm_create_shape_with_one_vcpu(shape, &vcpu, npages,
+ guest_code_test_guest_private_mem);
+
+ fd = vm_create_guest_memfd(vm, page_size, 0);
+ vm_mem_add(vm, VM_MEM_SRC_SHMEM, gpa, slot, npages, KVM_MEM_GUEST_MEMFD,
+ fd, 0, 0);
+
+ virt_map(vm, gpa, gpa, npages);
+ vm_mem_set_private(vm, gpa, page_size);
+
+ vcpu_args_set(vcpu, 1, gpa);
+ vcpu_run(vcpu);
+
+ TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_DONE);
+
+ close(fd);
+ kvm_vm_free(vm);
+}
+
int main(int argc, char *argv[])
{
unsigned long vm_types, vm_type;
@@ -488,5 +536,6 @@ int main(int argc, char *argv[])
for_each_set_bit(vm_type, &vm_types, BITS_PER_TYPE(vm_types))
test_guest_memfd(vm_type);
- test_guest_memfd_guest();
+ test_guest_shared_mem();
+ test_guest_private_mem();
}
--
2.53.0.851.ga537e3e6e9-goog
^ permalink raw reply related
* [PATCH RFC v3 18/43] KVM: selftests: Add helpers for calling ioctls on guest_memfd
From: Ackerley Tng @ 2026-03-13 6:12 UTC (permalink / raw)
To: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jroedel, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
Ackerley Tng
In-Reply-To: <20260313-gmem-inplace-conversion-v3-0-5fc12a70ec89@google.com>
From: Sean Christopherson <seanjc@google.com>
Add helper functions to kvm_util.h to support calling ioctls, specifically
KVM_SET_MEMORY_ATTRIBUTES2, on a guest_memfd file descriptor.
Introduce gmem_ioctl() and __gmem_ioctl() macros, modeled after the
existing vm_ioctl() helpers, to provide a standard way to call ioctls
on a guest_memfd.
Add gmem_set_memory_attributes() and its derivatives (gmem_set_private(),
gmem_set_shared()) to set memory attributes on a guest_memfd region.
Also provide "__" variants that return the ioctl error code instead of
aborting the test. These helpers will be used by upcoming guest_memfd
tests.
To avoid code duplication, factor out the check for supported memory
attributes into a new macro, TEST_ASSERT_SUPPORTED_ATTRIBUTES, and use
it in both the existing vm_set_memory_attributes() and the new
gmem_set_memory_attributes() helpers.
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
tools/testing/selftests/kvm/include/kvm_util.h | 89 ++++++++++++++++++++++++--
1 file changed, 82 insertions(+), 7 deletions(-)
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index fc55ad3c67485..1c0f41bf847d0 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -333,6 +333,16 @@ static inline bool kvm_has_cap(long cap)
TEST_ASSERT(!ret, __KVM_IOCTL_ERROR(#cmd, ret)); \
})
+#define __gmem_ioctl(gmem_fd, cmd, arg) \
+ kvm_do_ioctl(gmem_fd, cmd, arg)
+
+#define gmem_ioctl(gmem_fd, cmd, arg) \
+({ \
+ int ret = __gmem_ioctl(gmem_fd, cmd, arg); \
+ \
+ TEST_ASSERT(!ret, __KVM_IOCTL_ERROR(#cmd, ret)); \
+})
+
static __always_inline void static_assert_is_vm(struct kvm_vm *vm) { }
#define __vm_ioctl(vm, cmd, arg) \
@@ -417,6 +427,14 @@ static inline void vm_enable_cap(struct kvm_vm *vm, uint32_t cap, uint64_t arg0)
vm_ioctl(vm, KVM_ENABLE_CAP, &enable_cap);
}
+/*
+ * KVM_SET_MEMORY_ATTRIBUTES overwrites _all_ attributes. These flows need
+ * significant enhancements to support multiple attributes.
+ */
+#define TEST_ASSERT_SUPPORTED_ATTRIBUTES(attributes) \
+ TEST_ASSERT(!attributes || attributes == KVM_MEMORY_ATTRIBUTE_PRIVATE, \
+ "Update me to support multiple attributes!")
+
static inline void vm_set_memory_attributes(struct kvm_vm *vm, uint64_t gpa,
uint64_t size, uint64_t attributes)
{
@@ -427,12 +445,7 @@ static inline void vm_set_memory_attributes(struct kvm_vm *vm, uint64_t gpa,
.flags = 0,
};
- /*
- * KVM_SET_MEMORY_ATTRIBUTES2 overwrites _all_ attributes. These flows
- * need significant enhancements to support multiple attributes.
- */
- TEST_ASSERT(!attributes || attributes == KVM_MEMORY_ATTRIBUTE_PRIVATE,
- "Update me to support multiple attributes!");
+ TEST_ASSERT_SUPPORTED_ATTRIBUTES(attributes);
__TEST_REQUIRE(kvm_check_cap(KVM_CAP_MEMORY_ATTRIBUTES2) > 0,
"No valid attributes for VM fd ioctl!");
@@ -440,7 +453,6 @@ static inline void vm_set_memory_attributes(struct kvm_vm *vm, uint64_t gpa,
vm_ioctl(vm, KVM_SET_MEMORY_ATTRIBUTES2, &attr);
}
-
static inline void vm_mem_set_private(struct kvm_vm *vm, uint64_t gpa,
uint64_t size)
{
@@ -453,6 +465,69 @@ static inline void vm_mem_set_shared(struct kvm_vm *vm, uint64_t gpa,
vm_set_memory_attributes(vm, gpa, size, 0);
}
+static inline int __gmem_set_memory_attributes(int fd, loff_t offset,
+ uint64_t size,
+ uint64_t attributes,
+ loff_t *error_offset)
+{
+ struct kvm_memory_attributes2 attr = {
+ .attributes = attributes,
+ .offset = offset,
+ .size = size,
+ .flags = 0,
+ };
+ int r;
+
+ TEST_ASSERT_SUPPORTED_ATTRIBUTES(attributes);
+
+ r = __gmem_ioctl(fd, KVM_SET_MEMORY_ATTRIBUTES2, &attr);
+ if (r)
+ *error_offset = attr.error_offset;
+ return r;
+}
+
+static inline int __gmem_set_private(int fd, loff_t offset, uint64_t size,
+ loff_t *error_offset)
+{
+ return __gmem_set_memory_attributes(fd, offset, size,
+ KVM_MEMORY_ATTRIBUTE_PRIVATE,
+ error_offset);
+}
+
+static inline int __gmem_set_shared(int fd, loff_t offset, uint64_t size,
+ loff_t *error_offset)
+{
+ return __gmem_set_memory_attributes(fd, offset, size, 0, error_offset);
+}
+
+static inline void gmem_set_memory_attributes(int fd, loff_t offset,
+ uint64_t size, uint64_t attributes)
+{
+ struct kvm_memory_attributes2 attr = {
+ .attributes = attributes,
+ .offset = offset,
+ .size = size,
+ .flags = 0,
+ };
+
+ TEST_ASSERT_SUPPORTED_ATTRIBUTES(attributes);
+
+ __TEST_REQUIRE(kvm_check_cap(KVM_CAP_GUEST_MEMFD_MEMORY_ATTRIBUTES) > 0,
+ "No valid attributes for guest_memfd ioctl!");
+
+ gmem_ioctl(fd, KVM_SET_MEMORY_ATTRIBUTES2, &attr);
+}
+
+static inline void gmem_set_private(int fd, loff_t offset, uint64_t size)
+{
+ gmem_set_memory_attributes(fd, offset, size, KVM_MEMORY_ATTRIBUTE_PRIVATE);
+}
+
+static inline void gmem_set_shared(int fd, loff_t offset, uint64_t size)
+{
+ gmem_set_memory_attributes(fd, offset, size, 0);
+}
+
void vm_guest_mem_fallocate(struct kvm_vm *vm, uint64_t gpa, uint64_t size,
bool punch_hole);
--
2.53.0.851.ga537e3e6e9-goog
^ permalink raw reply related
* [PATCH RFC v3 17/43] KVM: selftests: Update framework to use KVM_SET_MEMORY_ATTRIBUTES2
From: Ackerley Tng @ 2026-03-13 6:12 UTC (permalink / raw)
To: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jroedel, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
Ackerley Tng
In-Reply-To: <20260313-gmem-inplace-conversion-v3-0-5fc12a70ec89@google.com>
Update KVM selftest framework to use KVM_SET_MEMORY_ATTRIBUTES2 and the
accompanying struct kvm_memory_attributes2.
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
---
tools/testing/selftests/kvm/include/kvm_util.h | 9 ++++++---
1 file changed, 6 insertions(+), 3 deletions(-)
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index caca482aad859..fc55ad3c67485 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -420,7 +420,7 @@ static inline void vm_enable_cap(struct kvm_vm *vm, uint32_t cap, uint64_t arg0)
static inline void vm_set_memory_attributes(struct kvm_vm *vm, uint64_t gpa,
uint64_t size, uint64_t attributes)
{
- struct kvm_memory_attributes attr = {
+ struct kvm_memory_attributes2 attr = {
.attributes = attributes,
.address = gpa,
.size = size,
@@ -428,13 +428,16 @@ static inline void vm_set_memory_attributes(struct kvm_vm *vm, uint64_t gpa,
};
/*
- * KVM_SET_MEMORY_ATTRIBUTES overwrites _all_ attributes. These flows
+ * KVM_SET_MEMORY_ATTRIBUTES2 overwrites _all_ attributes. These flows
* need significant enhancements to support multiple attributes.
*/
TEST_ASSERT(!attributes || attributes == KVM_MEMORY_ATTRIBUTE_PRIVATE,
"Update me to support multiple attributes!");
- vm_ioctl(vm, KVM_SET_MEMORY_ATTRIBUTES, &attr);
+ __TEST_REQUIRE(kvm_check_cap(KVM_CAP_MEMORY_ATTRIBUTES2) > 0,
+ "No valid attributes for VM fd ioctl!");
+
+ vm_ioctl(vm, KVM_SET_MEMORY_ATTRIBUTES2, &attr);
}
--
2.53.0.851.ga537e3e6e9-goog
^ permalink raw reply related
* [PATCH RFC v3 16/43] KVM: selftests: Add selftests global for guest memory attributes capability
From: Ackerley Tng @ 2026-03-13 6:12 UTC (permalink / raw)
To: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jroedel, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
Ackerley Tng
In-Reply-To: <20260313-gmem-inplace-conversion-v3-0-5fc12a70ec89@google.com>
From: Sean Christopherson <seanjc@google.com>
Add a global variable, kvm_has_gmem_attributes, to make the result of
checking for KVM_CAP_GUEST_MEMFD_MEMORY_ATTRIBUTES available to all tests.
kvm_has_gmem_attributes is true if guest_memfd tracks memory attributes, as
opposed to VM-level tracking.
This global variable is synced to the guest for testing convenience, to
avoid introducing subtle bugs when host/guest state is desynced.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
---
tools/testing/selftests/kvm/include/test_util.h | 2 ++
tools/testing/selftests/kvm/lib/kvm_util.c | 5 +++++
2 files changed, 7 insertions(+)
diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
index b4872ba8ed124..2871a42928471 100644
--- a/tools/testing/selftests/kvm/include/test_util.h
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -113,6 +113,8 @@ struct guest_random_state {
extern uint32_t guest_random_seed;
extern struct guest_random_state guest_rng;
+extern bool kvm_has_gmem_attributes;
+
struct guest_random_state new_guest_random_state(uint32_t seed);
uint32_t guest_random_u32(struct guest_random_state *state);
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 82d6945efa29a..404efb5318f09 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -24,6 +24,8 @@ uint32_t guest_random_seed;
struct guest_random_state guest_rng;
static uint32_t last_guest_seed;
+bool kvm_has_gmem_attributes;
+
static size_t vcpu_mmap_sz(void);
int __open_path_or_exit(const char *path, int flags, const char *enoent_help)
@@ -521,6 +523,7 @@ struct kvm_vm *__vm_create(struct vm_shape shape, uint32_t nr_runnable_vcpus,
}
guest_rng = new_guest_random_state(guest_random_seed);
sync_global_to_guest(vm, guest_rng);
+ sync_global_to_guest(vm, kvm_has_gmem_attributes);
kvm_arch_vm_post_create(vm, nr_runnable_vcpus);
@@ -2365,6 +2368,8 @@ void __attribute((constructor)) kvm_selftest_init(void)
guest_random_seed = last_guest_seed = random();
pr_info("Random seed: 0x%x\n", guest_random_seed);
+ kvm_has_gmem_attributes = kvm_has_cap(KVM_CAP_GUEST_MEMFD_MEMORY_ATTRIBUTES);
+
kvm_selftest_arch_init();
}
--
2.53.0.851.ga537e3e6e9-goog
^ permalink raw reply related
* [PATCH RFC v3 15/43] KVM: selftests: Add support for mmap() on guest_memfd in core library
From: Ackerley Tng @ 2026-03-13 6:12 UTC (permalink / raw)
To: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jroedel, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
Ackerley Tng
In-Reply-To: <20260313-gmem-inplace-conversion-v3-0-5fc12a70ec89@google.com>
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 | 19 +++++++++++--------
.../selftests/kvm/x86/private_mem_conversions_test.c | 2 +-
3 files changed, 18 insertions(+), 10 deletions(-)
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 8b39cb919f4fc..caca482aad859 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -701,7 +701,7 @@ 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)
@@ -735,6 +735,11 @@ 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 3b64fbadcd88d..82d6945efa29a 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -979,12 +979,13 @@ 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 = 0;
size_t alignment;
TEST_REQUIRE_SET_USER_MEMORY_REGION2();
@@ -1063,8 +1064,6 @@ 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);
@@ -1085,13 +1084,17 @@ 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);
+ mmap_offset = gmem_offset;
+ } 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);
+ 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),
@@ -1152,7 +1155,7 @@ 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;
--
2.53.0.851.ga537e3e6e9-goog
^ permalink raw reply related
* [PATCH RFC v3 14/43] KVM: selftests: Rename guest_memfd{,_offset} to gmem_{fd,offset}
From: Ackerley Tng @ 2026-03-13 6:12 UTC (permalink / raw)
To: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jroedel, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
Ackerley Tng
In-Reply-To: <20260313-gmem-inplace-conversion-v3-0-5fc12a70ec89@google.com>
From: Sean Christopherson <seanjc@google.com>
Rename local variables and function parameters for the guest memory file
descriptor and its offset to use a "gmem_" prefix instead of
"guest_memfd_".
No functional change intended.
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
tools/testing/selftests/kvm/lib/kvm_util.c | 26 +++++++++++++-------------
1 file changed, 13 insertions(+), 13 deletions(-)
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 610cb32ff207e..3b64fbadcd88d 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -947,7 +947,7 @@ void vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
int __vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
uint64_t gpa, uint64_t size, void *hva,
- uint32_t guest_memfd, uint64_t guest_memfd_offset)
+ uint32_t gmem_fd, uint64_t gmem_offset)
{
struct kvm_userspace_memory_region2 region = {
.slot = slot,
@@ -955,8 +955,8 @@ int __vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flag
.guest_phys_addr = gpa,
.memory_size = size,
.userspace_addr = (uintptr_t)hva,
- .guest_memfd = guest_memfd,
- .guest_memfd_offset = guest_memfd_offset,
+ .guest_memfd = gmem_fd,
+ .guest_memfd_offset = gmem_offset,
};
TEST_REQUIRE_SET_USER_MEMORY_REGION2();
@@ -966,10 +966,10 @@ int __vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flag
void vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
uint64_t gpa, uint64_t size, void *hva,
- uint32_t guest_memfd, uint64_t guest_memfd_offset)
+ uint32_t gmem_fd, uint64_t gmem_offset)
{
int ret = __vm_set_user_memory_region2(vm, slot, flags, gpa, size, hva,
- guest_memfd, guest_memfd_offset);
+ gmem_fd, gmem_offset);
TEST_ASSERT(!ret, "KVM_SET_USER_MEMORY_REGION2 failed, errno = %d (%s)",
errno, strerror(errno));
@@ -979,7 +979,7 @@ 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 guest_memfd, uint64_t guest_memfd_offset)
+ int gmem_fd, uint64_t gmem_offset)
{
int ret;
struct userspace_mem_region *region;
@@ -1062,12 +1062,12 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
region->mmap_size += alignment;
if (flags & KVM_MEM_GUEST_MEMFD) {
- if (guest_memfd < 0) {
- uint32_t guest_memfd_flags = 0;
+ if (gmem_fd < 0) {
+ uint32_t gmem_flags = 0;
- TEST_ASSERT(!guest_memfd_offset,
+ TEST_ASSERT(!gmem_offset,
"Offset must be zero when creating new guest_memfd");
- guest_memfd = vm_create_guest_memfd(vm, mem_size, guest_memfd_flags);
+ gmem_fd = vm_create_guest_memfd(vm, mem_size, gmem_flags);
} else {
/*
* Install a unique fd for each memslot so that the fd
@@ -1075,11 +1075,11 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
* needing to track if the fd is owned by the framework
* or by the caller.
*/
- guest_memfd = kvm_dup(guest_memfd);
+ gmem_fd = kvm_dup(gmem_fd);
}
- region->region.guest_memfd = guest_memfd;
- region->region.guest_memfd_offset = guest_memfd_offset;
+ region->region.guest_memfd = gmem_fd;
+ region->region.guest_memfd_offset = gmem_offset;
} else {
region->region.guest_memfd = -1;
}
--
2.53.0.851.ga537e3e6e9-goog
^ permalink raw reply related
* [PATCH RFC v3 13/43] KVM: selftests: Create gmem fd before "regular" fd when adding memslot
From: Ackerley Tng @ 2026-03-13 6:12 UTC (permalink / raw)
To: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jroedel, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
Ackerley Tng
In-Reply-To: <20260313-gmem-inplace-conversion-v3-0-5fc12a70ec89@google.com>
From: Sean Christopherson <seanjc@google.com>
When adding a memslot associated a guest_memfd instance, create/dup the
guest_memfd before creating the "normal" backing file. This will allow
dup'ing the gmem fd as the normal fd when guest_memfd supports mmap(),
i.e. to make guest_memfd the _only_ backing source for the memslot.
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
tools/testing/selftests/kvm/lib/kvm_util.c | 45 +++++++++++++++---------------
1 file changed, 23 insertions(+), 22 deletions(-)
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 1959bf556e88e..610cb32ff207e 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -1061,6 +1061,29 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
if (alignment > 1)
region->mmap_size += alignment;
+ if (flags & KVM_MEM_GUEST_MEMFD) {
+ if (guest_memfd < 0) {
+ uint32_t guest_memfd_flags = 0;
+
+ TEST_ASSERT(!guest_memfd_offset,
+ "Offset must be zero when creating new guest_memfd");
+ guest_memfd = vm_create_guest_memfd(vm, mem_size, guest_memfd_flags);
+ } else {
+ /*
+ * Install a unique fd for each memslot so that the fd
+ * can be closed when the region is deleted without
+ * needing to track if the fd is owned by the framework
+ * or by the caller.
+ */
+ guest_memfd = kvm_dup(guest_memfd);
+ }
+
+ region->region.guest_memfd = guest_memfd;
+ region->region.guest_memfd_offset = guest_memfd_offset;
+ } else {
+ region->region.guest_memfd = -1;
+ }
+
region->fd = -1;
if (backing_src_is_shared(src_type))
region->fd = kvm_memfd_alloc(region->mmap_size,
@@ -1090,28 +1113,6 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
region->backing_src_type = src_type;
- if (flags & KVM_MEM_GUEST_MEMFD) {
- if (guest_memfd < 0) {
- uint32_t guest_memfd_flags = 0;
- TEST_ASSERT(!guest_memfd_offset,
- "Offset must be zero when creating new guest_memfd");
- guest_memfd = vm_create_guest_memfd(vm, mem_size, guest_memfd_flags);
- } else {
- /*
- * Install a unique fd for each memslot so that the fd
- * can be closed when the region is deleted without
- * needing to track if the fd is owned by the framework
- * or by the caller.
- */
- guest_memfd = kvm_dup(guest_memfd);
- }
-
- region->region.guest_memfd = guest_memfd;
- region->region.guest_memfd_offset = guest_memfd_offset;
- } else {
- region->region.guest_memfd = -1;
- }
-
region->unused_phy_pages = sparsebit_alloc();
if (vm_arch_has_protected_memory(vm))
region->protected_phy_pages = sparsebit_alloc();
--
2.53.0.851.ga537e3e6e9-goog
^ permalink raw reply related
* [PATCH RFC v3 12/43] KVM: Let userspace disable per-VM mem attributes, enable per-gmem attributes
From: Ackerley Tng @ 2026-03-13 6:12 UTC (permalink / raw)
To: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jroedel, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
Ackerley Tng
In-Reply-To: <20260313-gmem-inplace-conversion-v3-0-5fc12a70ec89@google.com>
From: Sean Christopherson <seanjc@google.com>
Make vm_memory_attributes a module parameter so that userspace can disable
the use of memory attributes on the VM level.
To avoid inconsistencies in the way memory attributes are tracked in KVM
and guest_memfd, the vm_memory_attributes module_param is made
read-only (0444).
Make CONFIG_KVM_VM_MEMORY_ATTRIBUTES selectable, only for (CoCo) VM types
that might use vm_memory_attributes.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
---
arch/x86/kvm/Kconfig | 13 +++++++++----
virt/kvm/kvm_main.c | 1 +
2 files changed, 10 insertions(+), 4 deletions(-)
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index b6d65ee664d0f..8b97d341bd33f 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -82,13 +82,20 @@ config KVM_WERROR
config KVM_VM_MEMORY_ATTRIBUTES
select KVM_MEMORY_ATTRIBUTES
- bool
+ depends on KVM_SW_PROTECTED_VM || KVM_INTEL_TDX || KVM_AMD_SEV
+ bool "Enable per-VM memory attributes (for CoCo VMs)"
+ help
+ Enable support for per-VM memory attributes, which are deprecated in
+ favor of tracking memory attributes in guest_memfd. Select this if
+ you need to run CoCo VMs using a VMM that doesn't support guest_memfd
+ memory attributes.
+
+ If unsure, say N.
config KVM_SW_PROTECTED_VM
bool "Enable support for KVM software-protected VMs"
depends on EXPERT
depends on KVM_X86 && X86_64
- select KVM_VM_MEMORY_ATTRIBUTES
help
Enable support for KVM software-protected VMs. Currently, software-
protected VMs are purely a development and testing vehicle for
@@ -139,7 +146,6 @@ config KVM_INTEL_TDX
bool "Intel Trust Domain Extensions (TDX) support"
default y
depends on INTEL_TDX_HOST
- select KVM_VM_MEMORY_ATTRIBUTES
select HAVE_KVM_ARCH_GMEM_POPULATE
help
Provides support for launching Intel Trust Domain Extensions (TDX)
@@ -163,7 +169,6 @@ config KVM_AMD_SEV
depends on KVM_AMD && X86_64
depends on CRYPTO_DEV_SP_PSP && !(KVM_AMD=y && CRYPTO_DEV_CCP_DD=m)
select ARCH_HAS_CC_PLATFORM
- select KVM_VM_MEMORY_ATTRIBUTES
select HAVE_KVM_ARCH_GMEM_PREPARE
select HAVE_KVM_ARCH_GMEM_INVALIDATE
select HAVE_KVM_ARCH_GMEM_POPULATE
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index b8f5ce3a33e27..9744d3a7fd917 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -105,6 +105,7 @@ module_param(allow_unsafe_mappings, bool, 0444);
#ifdef CONFIG_KVM_MEMORY_ATTRIBUTES
#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES
bool vm_memory_attributes = true;
+module_param(vm_memory_attributes, bool, 0444);
#endif
DEFINE_STATIC_CALL_RET0(__kvm_get_memory_attributes, kvm_get_memory_attributes_t);
EXPORT_SYMBOL_FOR_KVM_INTERNAL(STATIC_CALL_KEY(__kvm_get_memory_attributes));
--
2.53.0.851.ga537e3e6e9-goog
^ permalink raw reply related
* [PATCH RFC v3 11/43] KVM: Move KVM_VM_MEMORY_ATTRIBUTES config definition to x86
From: Ackerley Tng @ 2026-03-13 6:12 UTC (permalink / raw)
To: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jroedel, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
Ackerley Tng
In-Reply-To: <20260313-gmem-inplace-conversion-v3-0-5fc12a70ec89@google.com>
From: Sean Christopherson <seanjc@google.com>
Bury KVM_VM_MEMORY_ATTRIBUTES in x86 to discourage other architectures
from adding support for per-VM memory attributes, because tracking private
vs. shared memory on a per-VM basis is now deprecated in favor of tracking
on a per-guest_memfd basis, and no other memory attributes are on the
horizon.
This will also allow modifying KVM_VM_MEMORY_ATTRIBUTES to be
user-selectable (in x86) without creating weirdness in KVM's Kconfigs.
Now that guest_memfd support memory attributes, it's entirely possible to
run x86 CoCo VMs without support for KVM_VM_MEMORY_ATTRIBUTES.
Leave the code itself in common KVM so that it's trivial to undo this
change if new per-VM attributes do come along.
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
arch/x86/kvm/Kconfig | 4 ++++
virt/kvm/Kconfig | 4 ----
2 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 26f6afd51bbdc..b6d65ee664d0f 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -80,6 +80,10 @@ config KVM_WERROR
If in doubt, say "N".
+config KVM_VM_MEMORY_ATTRIBUTES
+ select KVM_MEMORY_ATTRIBUTES
+ bool
+
config KVM_SW_PROTECTED_VM
bool "Enable support for KVM software-protected VMs"
depends on EXPERT
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index e371e079e2c50..663de6421eda2 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -103,10 +103,6 @@ config KVM_MMU_LOCKLESS_AGING
config KVM_MEMORY_ATTRIBUTES
bool
-config KVM_VM_MEMORY_ATTRIBUTES
- select KVM_MEMORY_ATTRIBUTES
- bool
-
config KVM_GUEST_MEMFD
select XARRAY_MULTI
select KVM_MEMORY_ATTRIBUTES
--
2.53.0.851.ga537e3e6e9-goog
^ permalink raw reply related
* [PATCH RFC v3 10/43] KVM: guest_memfd: Handle lru_add fbatch refcounts during conversion safety check
From: Ackerley Tng @ 2026-03-13 6:12 UTC (permalink / raw)
To: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jroedel, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
Ackerley Tng
In-Reply-To: <20260313-gmem-inplace-conversion-v3-0-5fc12a70ec89@google.com>
When checking if a guest_memfd folio is safe for conversion, its refcount
is examined. A folio may be present in a per-CPU lru_add fbatch, which
temporarily increases its refcount. This can lead to a false positive,
incorrectly indicating that the folio is in use and preventing the
conversion, even if it is otherwise safe. The conversion process might not
be on the same CPU that holds the folio in its fbatch, making a simple
per-CPU check insufficient.
To address this, drain all CPUs' lru_add fbatches if an unexpectedly high
refcount is encountered during the safety check. This is performed at most
once per conversion request.
guest_memfd folios are unevictable, so they can only reside in the lru_add
fbatch. If the folio's refcount is still unsafe after draining, then the
conversion is truly deemed unsafe.
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
---
virt/kvm/guest_memfd.c | 22 ++++++++++++++++------
1 file changed, 16 insertions(+), 6 deletions(-)
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index 8e4866bb8145d..c4f6bdad6289e 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -8,6 +8,7 @@
#include <linux/mempolicy.h>
#include <linux/pseudo_fs.h>
#include <linux/pagemap.h>
+#include <linux/swap.h>
#include "kvm_mm.h"
@@ -566,25 +567,34 @@ static bool kvm_gmem_range_has_attributes(struct maple_tree *mt,
return true;
}
-static bool kvm_gmem_is_safe_for_conversion(struct inode *inode, pgoff_t start,
- size_t nr_pages, pgoff_t *err_index)
+static bool kvm_gmem_is_safe_for_conversion(struct inode *inode,
+ pgoff_t start, size_t nr_pages,
+ pgoff_t *err_index)
{
struct address_space *mapping = inode->i_mapping;
const int filemap_get_folios_refcount = 1;
pgoff_t last = start + nr_pages - 1;
struct folio_batch fbatch;
+ bool lru_drained = false;
bool safe = true;
int i;
folio_batch_init(&fbatch);
while (safe && filemap_get_folios(mapping, &start, last, &fbatch)) {
- for (i = 0; i < folio_batch_count(&fbatch); ++i) {
+ for (i = 0; i < folio_batch_count(&fbatch);) {
struct folio *folio = fbatch.folios[i];
- if (folio_ref_count(folio) !=
- folio_nr_pages(folio) + filemap_get_folios_refcount) {
- safe = false;
+ safe = (folio_ref_count(folio) ==
+ folio_nr_pages(folio) +
+ filemap_get_folios_refcount);
+
+ if (safe) {
+ ++i;
+ } else if (!lru_drained) {
+ lru_add_drain_all();
+ lru_drained = true;
+ } else {
*err_index = folio->index;
break;
}
--
2.53.0.851.ga537e3e6e9-goog
^ permalink raw reply related
* [PATCH RFC v3 09/43] KVM: guest_memfd: Add support for KVM_SET_MEMORY_ATTRIBUTES2
From: Ackerley Tng @ 2026-03-13 6:12 UTC (permalink / raw)
To: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jroedel, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
Ackerley Tng
In-Reply-To: <20260313-gmem-inplace-conversion-v3-0-5fc12a70ec89@google.com>
For shared to private conversions, if refcounts on any of the folios
within the range are elevated, fail the conversion with -EAGAIN.
At the point of shared to private conversion, all folios in range are
also unmapped. The filemap_invalidate_lock() is held, so no faulting
can occur. Hence, from that point on, only transient refcounts can be
taken on the folios associated with that guest_memfd.
Hence, it is safe to do the conversion from shared to private.
After conversion is complete, refcounts may become elevated, but that
is fine since users of transient refcounts don't actually access
memory.
For private to shared conversions, there are no refcount checks, since
the guest is the only user of private pages, and guest_memfd will be the
only holder of refcounts on private pages.
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
Co-developed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
Documentation/virt/kvm/api.rst | 48 +++++++++-
include/linux/kvm_host.h | 10 ++
include/uapi/linux/kvm.h | 9 +-
virt/kvm/Kconfig | 1 +
virt/kvm/guest_memfd.c | 211 ++++++++++++++++++++++++++++++++++++++---
virt/kvm/kvm_main.c | 15 +--
6 files changed, 264 insertions(+), 30 deletions(-)
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 0b61e2579e1d8..15148c80cfdb6 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -117,7 +117,7 @@ description:
x86 includes both i386 and x86_64.
Type:
- system, vm, or vcpu.
+ system, vm, vcpu or guest_memfd.
Parameters:
what parameters are accepted by the ioctl.
@@ -6557,11 +6557,22 @@ KVM_S390_KEYOP_SSKE
---------------------------------
:Capability: KVM_CAP_MEMORY_ATTRIBUTES2
-:Architectures: x86
-:Type: vm ioctl
+:Architectures: all
+:Type: vm, guest_memfd ioctl
:Parameters: struct kvm_memory_attributes2 (in/out)
:Returns: 0 on success, <0 on error
+Errors:
+
+ ========== ===============================================================
+ EINVAL The specified `offset` or `size` were invalid (e.g. not
+ page aligned, causes an overflow, or size is zero).
+ EFAULT The parameter address was invalid.
+ EAGAIN Some page within requested range had unexpected refcounts. The
+ offset of the page will be returned in `error_offset`.
+ ENOMEM Ran out of memory trying to track private/shared state
+ ========== ===============================================================
+
KVM_SET_MEMORY_ATTRIBUTES2 is an extension to
KVM_SET_MEMORY_ATTRIBUTES that supports returning (writing) values to
userspace. The original (pre-extension) fields are shared with
@@ -6572,15 +6583,42 @@ Attribute values are shared with KVM_SET_MEMORY_ATTRIBUTES.
::
struct kvm_memory_attributes2 {
- __u64 address;
+ /* in */
+ union {
+ __u64 address;
+ __u64 offset;
+ };
__u64 size;
__u64 attributes;
__u64 flags;
- __u64 reserved[12];
+ /* out */
+ __u64 error_offset;
+ __u64 reserved[11];
};
#define KVM_MEMORY_ATTRIBUTE_PRIVATE (1ULL << 3)
+Set attributes for a range of offsets within a guest_memfd to
+KVM_MEMORY_ATTRIBUTE_PRIVATE to limit the specified guest_memfd backed
+memory range for guest_use. Even if KVM_CAP_GUEST_MEMFD_MMAP is
+supported, after a successful call to set
+KVM_MEMORY_ATTRIBUTE_PRIVATE, the requested range will not be mappable
+into host userspace and will only be mappable by the guest.
+
+To allow the range to be mappable into host userspace again, call
+KVM_SET_MEMORY_ATTRIBUTES2 on the guest_memfd again with
+KVM_MEMORY_ATTRIBUTE_PRIVATE unset.
+
+If this ioctl returns -EAGAIN, the offset of the page with unexpected
+refcounts will be returned in `error_offset`. This can occur if there
+are transient refcounts on the pages, taken by other parts of the
+kernel.
+
+Userspace is expected to figure out how to remove all known refcounts
+on the shared pages, such as refcounts taken by get_user_pages(), and
+try the ioctl again. A possible source of these long term refcounts is
+if the guest_memfd memory was pinned in IOMMU page tables.
+
See also: :ref: `KVM_SET_MEMORY_ATTRIBUTES`.
.. _kvm_run:
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 19f026f8de390..1ea14c66fc82e 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2514,6 +2514,16 @@ static inline bool kvm_memslot_is_gmem_only(const struct kvm_memory_slot *slot)
}
#ifdef CONFIG_KVM_MEMORY_ATTRIBUTES
+static inline u64 kvm_supported_mem_attributes(struct kvm *kvm)
+{
+#ifdef kvm_arch_has_private_mem
+ if (!kvm || kvm_arch_has_private_mem(kvm))
+ return KVM_MEMORY_ATTRIBUTE_PRIVATE;
+#endif
+
+ return 0;
+}
+
typedef unsigned long (kvm_get_memory_attributes_t)(struct kvm *kvm, gfn_t gfn);
DECLARE_STATIC_CALL(__kvm_get_memory_attributes, kvm_get_memory_attributes_t);
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 16567d4a769e5..29baaa60de35a 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -990,6 +990,7 @@ struct kvm_enable_cap {
#define KVM_CAP_S390_USER_OPEREXEC 246
#define KVM_CAP_S390_KEYOP 247
#define KVM_CAP_MEMORY_ATTRIBUTES2 248
+#define KVM_CAP_GUEST_MEMFD_MEMORY_ATTRIBUTES 249
struct kvm_irq_routing_irqchip {
__u32 irqchip;
@@ -1642,11 +1643,15 @@ struct kvm_memory_attributes {
#define KVM_SET_MEMORY_ATTRIBUTES2 _IOWR(KVMIO, 0xd2, struct kvm_memory_attributes2)
struct kvm_memory_attributes2 {
- __u64 address;
+ union {
+ __u64 address;
+ __u64 offset;
+ };
__u64 size;
__u64 attributes;
__u64 flags;
- __u64 reserved[12];
+ __u64 error_offset;
+ __u64 reserved[11];
};
#define KVM_MEMORY_ATTRIBUTE_PRIVATE (1ULL << 3)
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index 3fea89c45cfb4..e371e079e2c50 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -109,6 +109,7 @@ config KVM_VM_MEMORY_ATTRIBUTES
config KVM_GUEST_MEMFD
select XARRAY_MULTI
+ select KVM_MEMORY_ATTRIBUTES
bool
config HAVE_KVM_ARCH_GMEM_PREPARE
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index 501f4d6e87909..8e4866bb8145d 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -178,10 +178,12 @@ static struct folio *kvm_gmem_get_folio(struct inode *inode, pgoff_t index)
static enum kvm_gfn_range_filter kvm_gmem_get_invalidate_filter(struct inode *inode)
{
- if (GMEM_I(inode)->flags & GUEST_MEMFD_FLAG_INIT_SHARED)
- return KVM_FILTER_SHARED;
-
- return KVM_FILTER_PRIVATE;
+ /*
+ * TODO: Limit invalidations based on the to-be-invalidated range, i.e.
+ * invalidate shared/private if and only if there can possibly be
+ * such mappings.
+ */
+ return KVM_FILTER_SHARED | KVM_FILTER_PRIVATE;
}
static void __kvm_gmem_invalidate_begin(struct gmem_file *f, pgoff_t start,
@@ -547,11 +549,201 @@ unsigned long kvm_gmem_get_memory_attributes(struct kvm *kvm, gfn_t gfn)
}
EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_gmem_get_memory_attributes);
+static bool kvm_gmem_range_has_attributes(struct maple_tree *mt,
+ pgoff_t index, size_t nr_pages,
+ u64 attributes)
+{
+ pgoff_t end = index + nr_pages - 1;
+ void *entry;
+
+ lockdep_assert(mt_lock_is_held(mt));
+
+ mt_for_each(mt, entry, index, end) {
+ if (xa_to_value(entry) != attributes)
+ return false;
+ }
+
+ return true;
+}
+
+static bool kvm_gmem_is_safe_for_conversion(struct inode *inode, pgoff_t start,
+ size_t nr_pages, pgoff_t *err_index)
+{
+ struct address_space *mapping = inode->i_mapping;
+ const int filemap_get_folios_refcount = 1;
+ pgoff_t last = start + nr_pages - 1;
+ struct folio_batch fbatch;
+ bool safe = true;
+ int i;
+
+ folio_batch_init(&fbatch);
+ while (safe && filemap_get_folios(mapping, &start, last, &fbatch)) {
+
+ for (i = 0; i < folio_batch_count(&fbatch); ++i) {
+ struct folio *folio = fbatch.folios[i];
+
+ if (folio_ref_count(folio) !=
+ folio_nr_pages(folio) + filemap_get_folios_refcount) {
+ safe = false;
+ *err_index = folio->index;
+ break;
+ }
+ }
+
+ folio_batch_release(&fbatch);
+ }
+
+ return safe;
+}
+
+/*
+ * Preallocate memory for attributes to be stored on a maple tree, pointed to
+ * by mas. Adjacent ranges with attributes identical to the new attributes
+ * will be merged. Also sets mas's bounds up for storing attributes.
+ *
+ * This maintains the invariant that ranges with the same attributes will
+ * always be merged.
+ */
+static int kvm_gmem_mas_preallocate(struct ma_state *mas, u64 attributes,
+ pgoff_t start, size_t nr_pages)
+{
+ pgoff_t end = start + nr_pages;
+ pgoff_t last = end - 1;
+ void *entry;
+
+ /* Try extending range. entry is NULL on overflow/wrap-around. */
+ mas_set_range(mas, end, end);
+ entry = mas_find(mas, end);
+ if (entry && xa_to_value(entry) == attributes)
+ last = mas->last;
+
+ if (start > 0) {
+ mas_set_range(mas, start - 1, start - 1);
+ entry = mas_find(mas, start - 1);
+ if (entry && xa_to_value(entry) == attributes)
+ start = mas->index;
+ }
+
+ mas_set_range(mas, start, last);
+ return mas_preallocate(mas, xa_mk_value(attributes), GFP_KERNEL);
+}
+
+static int __kvm_gmem_set_attributes(struct inode *inode, pgoff_t start,
+ size_t nr_pages, uint64_t attrs,
+ pgoff_t *err_index)
+{
+ struct address_space *mapping = inode->i_mapping;
+ struct gmem_inode *gi = GMEM_I(inode);
+ pgoff_t end = start + nr_pages;
+ struct maple_tree *mt;
+ struct ma_state mas;
+ int r;
+
+ mt = &gi->attributes;
+
+ filemap_invalidate_lock(mapping);
+
+ mas_init(&mas, mt, start);
+
+ if (kvm_gmem_range_has_attributes(mt, start, nr_pages, attrs)) {
+ r = 0;
+ goto out;
+ }
+
+ r = kvm_gmem_mas_preallocate(&mas, attrs, start, nr_pages);
+ if (r) {
+ *err_index = start;
+ goto out;
+ }
+
+ if (attrs & KVM_MEMORY_ATTRIBUTE_PRIVATE) {
+ unmap_mapping_pages(mapping, start, nr_pages, false);
+
+ if (!kvm_gmem_is_safe_for_conversion(inode, start, nr_pages,
+ err_index)) {
+ mas_destroy(&mas);
+ r = -EAGAIN;
+ goto out;
+ }
+ }
+
+ kvm_gmem_invalidate_begin(inode, start, end);
+
+ mas_store_prealloc(&mas, xa_mk_value(attrs));
+
+ kvm_gmem_invalidate_end(inode, start, end);
+out:
+ filemap_invalidate_unlock(mapping);
+ return r;
+}
+
+static long kvm_gmem_set_attributes(struct file *file, void __user *argp)
+{
+ struct gmem_file *f = file->private_data;
+ struct inode *inode = file_inode(file);
+ struct kvm_memory_attributes2 attrs;
+ pgoff_t err_index;
+ size_t nr_pages;
+ pgoff_t index;
+ int i, r;
+
+ if (copy_from_user(&attrs, argp, sizeof(attrs)))
+ return -EFAULT;
+
+ if (attrs.flags)
+ return -EINVAL;
+ if (attrs.error_offset)
+ return -EINVAL;
+ for (i = 0; i < ARRAY_SIZE(attrs.reserved); i++) {
+ if (attrs.reserved[i])
+ return -EINVAL;
+ }
+ if (attrs.attributes & ~kvm_supported_mem_attributes(f->kvm))
+ return -EINVAL;
+ if (attrs.size == 0 || attrs.offset + attrs.size < attrs.offset)
+ return -EINVAL;
+ if (!PAGE_ALIGNED(attrs.offset) || !PAGE_ALIGNED(attrs.size))
+ return -EINVAL;
+
+ if (attrs.offset >= inode->i_size ||
+ attrs.offset + attrs.size > inode->i_size)
+ return -EINVAL;
+
+ nr_pages = attrs.size >> PAGE_SHIFT;
+ index = attrs.offset >> PAGE_SHIFT;
+ r = __kvm_gmem_set_attributes(inode, index, nr_pages, attrs.attributes,
+ &err_index);
+ if (r) {
+ attrs.error_offset = err_index << PAGE_SHIFT;
+
+ if (copy_to_user(argp, &attrs, sizeof(attrs)))
+ return -EFAULT;
+ }
+
+ return r;
+}
+
+static long kvm_gmem_ioctl(struct file *file, unsigned int ioctl,
+ unsigned long arg)
+{
+ switch (ioctl) {
+ case KVM_SET_MEMORY_ATTRIBUTES2:
+ if (vm_memory_attributes)
+ return -ENOTTY;
+
+ return kvm_gmem_set_attributes(file, (void __user *)arg);
+ default:
+ return -ENOTTY;
+ }
+}
+
+
static struct file_operations kvm_gmem_fops = {
.mmap = kvm_gmem_mmap,
.open = generic_file_open,
.release = kvm_gmem_release,
.fallocate = kvm_gmem_fallocate,
+ .unlocked_ioctl = kvm_gmem_ioctl,
};
static int kvm_gmem_migrate_folio(struct address_space *mapping,
@@ -934,20 +1126,13 @@ EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_gmem_get_pfn);
static bool kvm_gmem_range_is_private(struct gmem_inode *gi, pgoff_t index,
size_t nr_pages, struct kvm *kvm, gfn_t gfn)
{
- pgoff_t end = index + nr_pages - 1;
- void *entry;
-
if (vm_memory_attributes)
return kvm_range_has_vm_memory_attributes(kvm, gfn, gfn + nr_pages,
KVM_MEMORY_ATTRIBUTE_PRIVATE,
KVM_MEMORY_ATTRIBUTE_PRIVATE);
- mt_for_each(&gi->attributes, entry, index, end) {
- if (xa_to_value(entry) != attributes)
- return false;
- }
-
- return true;
+ return kvm_gmem_range_has_attributes(&gi->attributes, index, nr_pages,
+ KVM_MEMORY_ATTRIBUTE_PRIVATE);
}
static long __kvm_gmem_populate(struct kvm *kvm, struct kvm_memory_slot *slot,
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 89c31eb71a1ca..b8f5ce3a33e27 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2435,16 +2435,6 @@ static int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm,
#endif /* CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */
#ifdef CONFIG_KVM_MEMORY_ATTRIBUTES
-static u64 kvm_supported_mem_attributes(struct kvm *kvm)
-{
-#ifdef kvm_arch_has_private_mem
- if (!kvm || kvm_arch_has_private_mem(kvm))
- return KVM_MEMORY_ATTRIBUTE_PRIVATE;
-#endif
-
- return 0;
-}
-
#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES
static unsigned long kvm_get_vm_memory_attributes(struct kvm *kvm, gfn_t gfn)
{
@@ -4978,6 +4968,11 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
return 1;
case KVM_CAP_GUEST_MEMFD_FLAGS:
return kvm_gmem_get_supported_flags(kvm);
+ case KVM_CAP_GUEST_MEMFD_MEMORY_ATTRIBUTES:
+ if (vm_memory_attributes)
+ return 0;
+
+ return kvm_supported_mem_attributes(kvm);
#endif
default:
break;
--
2.53.0.851.ga537e3e6e9-goog
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox