| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20210818001210.4073390-5-seanjc@google.com>
Date: Tue, 17 Aug 2021 17:12:09 -0700
From: Sean Christopherson <seanjc@...gle.com>
To: Russell King <linux@...linux.org.uk>,
Catalin Marinas <catalin.marinas@....com>,
Will Deacon <will@...nel.org>, Guo Ren <guoren@...nel.org>,
Thomas Bogendoerfer <tsbogend@...ha.franken.de>,
Michael Ellerman <mpe@...erman.id.au>,
Heiko Carstens <hca@...ux.ibm.com>,
Vasily Gorbik <gor@...ux.ibm.com>,
Christian Borntraeger <borntraeger@...ibm.com>,
Oleg Nesterov <oleg@...hat.com>,
Steven Rostedt <rostedt@...dmis.org>,
Ingo Molnar <mingo@...hat.com>,
Thomas Gleixner <tglx@...utronix.de>,
Peter Zijlstra <peterz@...radead.org>,
Andy Lutomirski <luto@...nel.org>,
Mathieu Desnoyers <mathieu.desnoyers@...icios.com>,
"Paul E. McKenney" <paulmck@...nel.org>,
Boqun Feng <boqun.feng@...il.com>,
Paolo Bonzini <pbonzini@...hat.com>,
Shuah Khan <shuah@...nel.org>
Cc: Benjamin Herrenschmidt <benh@...nel.crashing.org>,
Paul Mackerras <paulus@...ba.org>,
linux-arm-kernel@...ts.infradead.org, linux-kernel@...r.kernel.org,
linux-csky@...r.kernel.org, linux-mips@...r.kernel.org,
linuxppc-dev@...ts.ozlabs.org, linux-s390@...r.kernel.org,
kvm@...r.kernel.org, linux-kselftest@...r.kernel.org,
Peter Foley <pefoley@...gle.com>,
Shakeel Butt <shakeelb@...gle.com>,
Sean Christopherson <seanjc@...gle.com>,
Ben Gardon <bgardon@...gle.com>
Subject: [PATCH 4/5] KVM: selftests: Add a test for KVM_RUN+rseq to detect
task migration bugs
Add a test to verify an rseq's CPU ID is updated correctly if the task is
migrated while the kernel is handling KVM_RUN. This is a regression test
for a bug introduced by commit 72c3c0fe54a3 ("x86/kvm: Use generic xfer
to guest work function"), where TIF_NOTIFY_RESUME would be cleared by KVM
without updating rseq, leading to a stale CPU ID and other badness.
Signed-off-by: Sean Christopherson <seanjc@...gle.com>
---
tools/testing/selftests/kvm/.gitignore | 1 +
tools/testing/selftests/kvm/Makefile | 3 +
tools/testing/selftests/kvm/rseq_test.c | 131 ++++++++++++++++++++++++
3 files changed, 135 insertions(+)
create mode 100644 tools/testing/selftests/kvm/rseq_test.c
diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 0709af0144c8..6d031ff6b68e 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -47,6 +47,7 @@
/kvm_page_table_test
/memslot_modification_stress_test
/memslot_perf_test
+/rseq_test
/set_memory_region_test
/steal_time
/kvm_binary_stats_test
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 5832f510a16c..0756e79cb513 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -80,6 +80,7 @@ TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus
TEST_GEN_PROGS_x86_64 += kvm_page_table_test
TEST_GEN_PROGS_x86_64 += memslot_modification_stress_test
TEST_GEN_PROGS_x86_64 += memslot_perf_test
+TEST_GEN_PROGS_x86_64 += rseq_test
TEST_GEN_PROGS_x86_64 += set_memory_region_test
TEST_GEN_PROGS_x86_64 += steal_time
TEST_GEN_PROGS_x86_64 += kvm_binary_stats_test
@@ -92,6 +93,7 @@ TEST_GEN_PROGS_aarch64 += dirty_log_test
TEST_GEN_PROGS_aarch64 += dirty_log_perf_test
TEST_GEN_PROGS_aarch64 += kvm_create_max_vcpus
TEST_GEN_PROGS_aarch64 += kvm_page_table_test
+TEST_GEN_PROGS_aarch64 += rseq_test
TEST_GEN_PROGS_aarch64 += set_memory_region_test
TEST_GEN_PROGS_aarch64 += steal_time
TEST_GEN_PROGS_aarch64 += kvm_binary_stats_test
@@ -103,6 +105,7 @@ TEST_GEN_PROGS_s390x += demand_paging_test
TEST_GEN_PROGS_s390x += dirty_log_test
TEST_GEN_PROGS_s390x += kvm_create_max_vcpus
TEST_GEN_PROGS_s390x += kvm_page_table_test
+TEST_GEN_PROGS_s390x += rseq_test
TEST_GEN_PROGS_s390x += set_memory_region_test
TEST_GEN_PROGS_s390x += kvm_binary_stats_test
diff --git a/tools/testing/selftests/kvm/rseq_test.c b/tools/testing/selftests/kvm/rseq_test.c
new file mode 100644
index 000000000000..90ed535eded7
--- /dev/null
+++ b/tools/testing/selftests/kvm/rseq_test.c
@@ -0,0 +1,131 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#include <errno.h>
+#include <fcntl.h>
+#include <pthread.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <signal.h>
+#include <syscall.h>
+#include <sys/ioctl.h>
+#include <linux/rseq.h>
+#include <linux/unistd.h>
+
+#include "kvm_util.h"
+#include "processor.h"
+#include "test_util.h"
+
+#define VCPU_ID 0
+
+static __thread volatile struct rseq __rseq = {
+ .cpu_id = RSEQ_CPU_ID_UNINITIALIZED,
+};
+
+#define RSEQ_SIG 0xdeadbeef
+
+static pthread_t migration_thread;
+static cpu_set_t possible_mask;
+static bool done;
+
+static void guest_code(void)
+{
+ for (;;)
+ GUEST_SYNC(0);
+}
+
+static void sys_rseq(int flags)
+{
+ int r;
+
+ r = syscall(__NR_rseq, &__rseq, sizeof(__rseq), flags, RSEQ_SIG);
+ TEST_ASSERT(!r, "rseq failed, errno = %d (%s)", errno, strerror(errno));
+}
+
+static void *migration_worker(void *ign)
+{
+ cpu_set_t allowed_mask;
+ int r, i, nr_cpus, cpu;
+
+ CPU_ZERO(&allowed_mask);
+
+ nr_cpus = CPU_COUNT(&possible_mask);
+
+ for (i = 0; i < 20000; i++) {
+ cpu = i % nr_cpus;
+ if (!CPU_ISSET(cpu, &possible_mask))
+ continue;
+
+ CPU_SET(cpu, &allowed_mask);
+
+ r = sched_setaffinity(0, sizeof(allowed_mask), &allowed_mask);
+ TEST_ASSERT(!r, "sched_setaffinity failed, errno = %d (%s)", errno,
+ strerror(errno));
+
+ CPU_CLR(cpu, &allowed_mask);
+
+ usleep(10);
+ }
+ done = true;
+ return NULL;
+}
+
+int main(int argc, char *argv[])
+{
+ struct kvm_vm *vm;
+ u32 cpu, rseq_cpu;
+ int r;
+
+ /* Tell stdout not to buffer its content */
+ setbuf(stdout, NULL);
+
+ r = sched_getaffinity(0, sizeof(possible_mask), &possible_mask);
+ TEST_ASSERT(!r, "sched_getaffinity failed, errno = %d (%s)", errno,
+ strerror(errno));
+
+ if (CPU_COUNT(&possible_mask) < 2) {
+ print_skip("Only one CPU, task migration not possible\n");
+ exit(KSFT_SKIP);
+ }
+
+ sys_rseq(0);
+
+ /*
+ * Create and run a dummy VM that immediately exits to userspace via
+ * GUEST_SYNC, while concurrently migrating the process by setting its
+ * CPU affinity.
+ */
+ vm = vm_create_default(VCPU_ID, 0, guest_code);
+
+ pthread_create(&migration_thread, NULL, migration_worker, 0);
+
+ while (!done) {
+ vcpu_run(vm, VCPU_ID);
+ TEST_ASSERT(get_ucall(vm, VCPU_ID, NULL) == UCALL_SYNC,
+ "Guest failed?");
+
+ cpu = sched_getcpu();
+ rseq_cpu = READ_ONCE(__rseq.cpu_id);
+
+ /*
+ * Verify rseq's CPU matches sched's CPU, and that sched's CPU
+ * is stable. This doesn't handle the case where the task is
+ * migrated between sched_getcpu() and reading rseq, and again
+ * between reading rseq and sched_getcpu(), but in practice no
+ * false positives have been observed, while on the other hand
+ * blocking migration while this thread reads CPUs messes with
+ * the timing and prevents hitting failures on a buggy kernel.
+ */
+ TEST_ASSERT(rseq_cpu == cpu || cpu != sched_getcpu(),
+ "rseq CPU = %d, sched CPU = %d\n", rseq_cpu, cpu);
+ }
+
+ pthread_join(migration_thread, NULL);
+
+ kvm_vm_free(vm);
+
+ sys_rseq(RSEQ_FLAG_UNREGISTER);
+
+ return 0;
+}
--
2.33.0.rc1.237.g0d66db33f3-goog
Powered by blists - more mailing lists