Fix a NULL VMSA deref bug (which is probably the tip of the iceberg with
respect to what all can go wrong) due to a race between KVM_CREATE_VCPU and
KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM, where a non-SEV-ES vCPU can be created in
an SEV-ES VM.
Found by running syzkaller on a bare metal SEV-ES host. C repro below.
Sean Christopherson (2):
KVM: SVM: Reject SEV{-ES} intra host migration if vCPU creation is
in-flight
KVM: SVM: Initialize vmsa_pa in VMCB to INVALID_PAGE if VMSA page is
NULL
arch/x86/kvm/svm/sev.c | 12 ++++++++++--
1 file changed, 10 insertions(+), 2 deletions(-)
base-commit: 0ff41df1cb268fc69e703a08a57ee14ae967d0ca
--
2.49.0.1204.g71687c7c1d-goog
// autogenerated by syzkaller (https://github.com/google/syzkaller)
#define _GNU_SOURCE
#include <dirent.h>
#include <errno.h>
#include <fcntl.h>
#include <pthread.h>
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/ioctl.h>
#include <sys/syscall.h>
#include <sys/wait.h>
#include <linux/futex.h>
#include <linux/kvm.h>
static unsigned long long procid;
static void sleep_ms(uint64_t ms)
{
usleep(ms * 1000);
}
static uint64_t current_time_ms(void)
{
struct timespec ts;
if (clock_gettime(CLOCK_MONOTONIC, &ts))
exit(1);
return (uint64_t)ts.tv_sec * 1000 + (uint64_t)ts.tv_nsec / 1000000;
}
static void thread_start(void* (*fn)(void*), void* arg)
{
pthread_t th;
pthread_attr_t attr;
pthread_attr_init(&attr);
pthread_attr_setstacksize(&attr, 128 << 10);
int i = 0;
for (; i < 100; i++) {
if (pthread_create(&th, &attr, fn, arg) == 0) {
pthread_attr_destroy(&attr);
return;
}
if (errno == EAGAIN) {
usleep(50);
continue;
}
break;
}
exit(1);
}
typedef struct {
int state;
} event_t;
static void event_init(event_t* ev)
{
ev->state = 0;
}
static void event_reset(event_t* ev)
{
ev->state = 0;
}
static void event_set(event_t* ev)
{
if (ev->state)
exit(1);
__atomic_store_n(&ev->state, 1, __ATOMIC_RELEASE);
syscall(SYS_futex, &ev->state, FUTEX_WAKE | FUTEX_PRIVATE_FLAG, 1000000);
}
static void event_wait(event_t* ev)
{
while (!__atomic_load_n(&ev->state, __ATOMIC_ACQUIRE))
syscall(SYS_futex, &ev->state, FUTEX_WAIT | FUTEX_PRIVATE_FLAG, 0, 0);
}
static int event_isset(event_t* ev)
{
return __atomic_load_n(&ev->state, __ATOMIC_ACQUIRE);
}
static int event_timedwait(event_t* ev, uint64_t timeout)
{
uint64_t start = current_time_ms();
uint64_t now = start;
for (;;) {
uint64_t remain = timeout - (now - start);
struct timespec ts;
ts.tv_sec = remain / 1000;
ts.tv_nsec = (remain % 1000) * 1000 * 1000;
syscall(SYS_futex, &ev->state, FUTEX_WAIT | FUTEX_PRIVATE_FLAG, 0, &ts);
if (__atomic_load_n(&ev->state, __ATOMIC_ACQUIRE))
return 1;
now = current_time_ms();
if (now - start > timeout)
return 0;
}
}
struct thread_t {
int created, call;
event_t ready, done;
};
static struct thread_t threads[16];
static void execute_call(int call);
static int running;
static void* thr(void* arg)
{
struct thread_t* th = (struct thread_t*)arg;
for (;;) {
event_wait(&th->ready);
event_reset(&th->ready);
execute_call(th->call);
__atomic_fetch_sub(&running, 1, __ATOMIC_RELAXED);
event_set(&th->done);
}
return 0;
}
static void execute_one(void)
{
if (write(1, "executing program\n", sizeof("executing program\n") - 1)) {
}
int i, call, thread;
for (call = 0; call < 9; call++) {
for (thread = 0; thread < (int)(sizeof(threads) / sizeof(threads[0]));
thread++) {
struct thread_t* th = &threads[thread];
if (!th->created) {
th->created = 1;
event_init(&th->ready);
event_init(&th->done);
event_set(&th->done);
thread_start(thr, th);
}
if (!event_isset(&th->done))
continue;
event_reset(&th->done);
th->call = call;
__atomic_fetch_add(&running, 1, __ATOMIC_RELAXED);
event_set(&th->ready);
if (call == 2 || call == 5 || call == 7)
break;
event_timedwait(&th->done, 50);
break;
}
}
for (i = 0; i < 100 && __atomic_load_n(&running, __ATOMIC_RELAXED); i++)
sleep_ms(1);
}
static void loop(void)
{
int iter = 0;
for (; iter < 100; iter++) {
int pid = fork();
if (pid < 0)
exit(1);
if (pid == 0) {
execute_one();
exit(0);
}
int status = 0;
uint64_t start = current_time_ms();
for (;;) {
sleep_ms(10);
if (waitpid(-1, &status, WNOHANG | __WALL) == pid)
break;
if (current_time_ms() - start < 5000)
continue;
break;
}
}
}
uint64_t r[4] = {0xffffffffffffffff, 0xffffffffffffffff, 0xffffffffffffffff,
0xffffffffffffffff};
void execute_call(int call)
{
switch (call) {
case 0:
r[1] = syscall(__NR_ioctl, /*fd=*/r[0], /*cmd=*/KVM_CREATE_VM, /*type=*/0ul);
break;
case 3:
r[3] = syscall(__NR_ioctl, /*fd=*/r[0], /*cmd=*/KVM_CREATE_VM, /*type=*/0ul);
break;
case 5:
syscall(__NR_ioctl, /*fd=*/r[3], /*cmd=*/KVM_CREATE_VCPU, /*id=*/0ul);
for (int i = 0; i < 32; i++) {
syscall(__NR_ioctl, /*fd=*/r[3], /*cmd=*/KVM_CREATE_VCPU, /*id=*/0ul);
}
break;
case 6:
*(uint64_t*)0x200000000040 = 1;
*(uint32_t*)0x200000000048 = 8;
*(uint32_t*)0x20000000004c = 0;
*(uint64_t*)0x200000000050 = 0x5625e9b0;
*(uint64_t*)0x200000000058 = 0;
memset((void*)0x200000000060, 0, 16);
syscall(__NR_ioctl, /*fd=*/r[1], /*cmd=*/KVM_MEMORY_ENCRYPT_OP,
/*arg=*/0x200000000040ul);
for (int i = 0; i < 32; i++) {
syscall(__NR_ioctl, /*fd=*/r[1], /*cmd=*/KVM_MEMORY_ENCRYPT_OP,
/*arg=*/0x200000000040ul);
}
break;
case 7:
*(uint32_t*)0x200000000080 = KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM;
*(uint32_t*)0x200000000084 = 0;
*(uint32_t*)0x200000000088 = r[1];
syscall(__NR_ioctl, /*fd=*/r[3], /*cmd=*/KVM_ENABLE_CAP,
/*arg=*/0x200000000080ul);
break;
}
}
int main(void)
{
syscall(__NR_mmap, /*addr=*/0x1ffffffff000ul, /*len=*/0x1000ul, /*prot=*/0ul,
/*flags=MAP_FIXED|MAP_ANONYMOUS|MAP_PRIVATE*/ 0x32ul,
/*fd=*/(intptr_t)-1, /*offset=*/0ul);
syscall(__NR_mmap, /*addr=*/0x200000000000ul, /*len=*/0x1000000ul,
/*prot=PROT_WRITE|PROT_READ|PROT_EXEC*/ 7ul,
/*flags=MAP_FIXED|MAP_ANONYMOUS|MAP_PRIVATE*/ 0x32ul,
/*fd=*/(intptr_t)-1, /*offset=*/0ul);
syscall(__NR_mmap, /*addr=*/0x200001000000ul, /*len=*/0x1000ul, /*prot=*/0ul,
/*flags=MAP_FIXED|MAP_ANONYMOUS|MAP_PRIVATE*/ 0x32ul,
/*fd=*/(intptr_t)-1, /*offset=*/0ul);
for (procid = 0; procid < 10; procid++) {
if (fork() == 0) {
r[0] = open("/dev/kvm", O_RDWR);
loop();
}
}
sleep(1000000);
return 0;
}
