From 8646e53633f314e4d746a988240d3b951a92f94a Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 1 Sep 2021 13:30:26 -0700
Subject: KVM: rseq: Update rseq when processing NOTIFY_RESUME on xfer to KVM
guest
Invoke rseq's NOTIFY_RESUME handler when processing the flag prior to
transferring to a KVM guest, which is roughly equivalent to an exit to
userspace and processes many of the same pending actions. While the task
cannot be in an rseq critical section as the KVM path is reachable only
by via ioctl(KVM_RUN), the side effects that apply to rseq outside of a
critical section still apply, e.g. the current CPU needs to be updated if
the task is migrated.
Clearing TIF_NOTIFY_RESUME without informing rseq can lead to segfaults
and other badness in userspace VMMs that use rseq in combination with KVM,
e.g. due to the CPU ID being stale after task migration.
Fixes: 72c3c0fe54a3 ("x86/kvm: Use generic xfer to guest work function")
Reported-by: Peter Foley <pefoley@google.com>
Bisected-by: Doug Evans <dje@google.com>
Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210901203030.1292304-2-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
kernel/entry/kvm.c | 4 +++-
kernel/rseq.c | 14 +++++++++++---
2 files changed, 14 insertions(+), 4 deletions(-)
diff --git a/kernel/entry/kvm.c b/kernel/entry/kvm.c
index 49972ee99aff..049fd06b4c3d 100644
--- a/kernel/entry/kvm.c
+++ b/kernel/entry/kvm.c
@@ -19,8 +19,10 @@ static int xfer_to_guest_mode_work(struct kvm_vcpu *vcpu, unsigned long ti_work)
if (ti_work & _TIF_NEED_RESCHED)
schedule();
- if (ti_work & _TIF_NOTIFY_RESUME)
+ if (ti_work & _TIF_NOTIFY_RESUME) {
tracehook_notify_resume(NULL);
+ rseq_handle_notify_resume(NULL, NULL);
+ }
ret = arch_xfer_to_guest_mode_handle_work(vcpu, ti_work);
if (ret)
diff --git a/kernel/rseq.c b/kernel/rseq.c
index 35f7bd0fced0..6d45ac3dae7f 100644
--- a/kernel/rseq.c
+++ b/kernel/rseq.c
@@ -282,9 +282,17 @@ void __rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs)
if (unlikely(t->flags & PF_EXITING))
return;
- ret = rseq_ip_fixup(regs);
- if (unlikely(ret < 0))
- goto error;
+
+ /*
+ * regs is NULL if and only if the caller is in a syscall path. Skip
+ * fixup and leave rseq_cs as is so that rseq_sycall() will detect and
+ * kill a misbehaving userspace on debug kernels.
+ */
+ if (regs) {
+ ret = rseq_ip_fixup(regs);
+ if (unlikely(ret < 0))
+ goto error;
+ }
if (unlikely(rseq_update_cpu_id(t)))
goto error;
return;
--
cgit v1.2.3-70-g09d2
From a68de80f61f6af397bc06fb391ff2e571c9c4d80 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 1 Sep 2021 13:30:27 -0700
Subject: entry: rseq: Call rseq_handle_notify_resume() in
tracehook_notify_resume()
Invoke rseq_handle_notify_resume() from tracehook_notify_resume() now
that the two function are always called back-to-back by architectures
that have rseq. The rseq helper is stubbed out for architectures that
don't support rseq, i.e. this is a nop across the board.
Note, tracehook_notify_resume() is horribly named and arguably does not
belong in tracehook.h as literally every line of code in it has nothing
to do with tracing. But, that's been true since commit a42c6ded827d
("move key_repace_session_keyring() into tracehook_notify_resume()")
first usurped tracehook_notify_resume() back in 2012. Punt cleaning that
mess up to future patches.
No functional change intended.
Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210901203030.1292304-3-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
arch/arm/kernel/signal.c | 1 -
arch/arm64/kernel/signal.c | 4 +---
arch/csky/kernel/signal.c | 4 +---
arch/mips/kernel/signal.c | 4 +---
arch/powerpc/kernel/signal.c | 4 +---
include/linux/tracehook.h | 2 ++
kernel/entry/common.c | 4 +---
kernel/entry/kvm.c | 4 +---
8 files changed, 8 insertions(+), 19 deletions(-)
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index d0a800be0486..a41e27ace391 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -628,7 +628,6 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall)
uprobe_notify_resume(regs);
} else {
tracehook_notify_resume(regs);
- rseq_handle_notify_resume(NULL, regs);
}
}
local_irq_disable();
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 9fe70b12b34f..c287b9407f28 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -940,10 +940,8 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_flags)
if (thread_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL))
do_signal(regs);
- if (thread_flags & _TIF_NOTIFY_RESUME) {
+ if (thread_flags & _TIF_NOTIFY_RESUME)
tracehook_notify_resume(regs);
- rseq_handle_notify_resume(NULL, regs);
- }
if (thread_flags & _TIF_FOREIGN_FPSTATE)
fpsimd_restore_current_state();
diff --git a/arch/csky/kernel/signal.c b/arch/csky/kernel/signal.c
index 312f046d452d..bc4238b9f709 100644
--- a/arch/csky/kernel/signal.c
+++ b/arch/csky/kernel/signal.c
@@ -260,8 +260,6 @@ asmlinkage void do_notify_resume(struct pt_regs *regs,
if (thread_info_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL))
do_signal(regs);
- if (thread_info_flags & _TIF_NOTIFY_RESUME) {
+ if (thread_info_flags & _TIF_NOTIFY_RESUME)
tracehook_notify_resume(regs);
- rseq_handle_notify_resume(NULL, regs);
- }
}
diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c
index f1e985109da0..c9b2a75563e1 100644
--- a/arch/mips/kernel/signal.c
+++ b/arch/mips/kernel/signal.c
@@ -906,10 +906,8 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, void *unused,
if (thread_info_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL))
do_signal(regs);
- if (thread_info_flags & _TIF_NOTIFY_RESUME) {
+ if (thread_info_flags & _TIF_NOTIFY_RESUME)
tracehook_notify_resume(regs);
- rseq_handle_notify_resume(NULL, regs);
- }
user_enter();
}
diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
index e600764a926c..b93b87df499d 100644
--- a/arch/powerpc/kernel/signal.c
+++ b/arch/powerpc/kernel/signal.c
@@ -293,10 +293,8 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags)
do_signal(current);
}
- if (thread_info_flags & _TIF_NOTIFY_RESUME) {
+ if (thread_info_flags & _TIF_NOTIFY_RESUME)
tracehook_notify_resume(regs);
- rseq_handle_notify_resume(NULL, regs);
- }
}
static unsigned long get_tm_stackpointer(struct task_struct *tsk)
diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h
index 3e80c4bc66f7..2564b7434b4d 100644
--- a/include/linux/tracehook.h
+++ b/include/linux/tracehook.h
@@ -197,6 +197,8 @@ static inline void tracehook_notify_resume(struct pt_regs *regs)
mem_cgroup_handle_over_high();
blkcg_maybe_throttle_current();
+
+ rseq_handle_notify_resume(NULL, regs);
}
/*
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index bf16395b9e13..d5a61d565ad5 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -171,10 +171,8 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
if (ti_work & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL))
handle_signal_work(regs, ti_work);
- if (ti_work & _TIF_NOTIFY_RESUME) {
+ if (ti_work & _TIF_NOTIFY_RESUME)
tracehook_notify_resume(regs);
- rseq_handle_notify_resume(NULL, regs);
- }
/* Architecture specific TIF work */
arch_exit_to_user_mode_work(regs, ti_work);
diff --git a/kernel/entry/kvm.c b/kernel/entry/kvm.c
index 049fd06b4c3d..49972ee99aff 100644
--- a/kernel/entry/kvm.c
+++ b/kernel/entry/kvm.c
@@ -19,10 +19,8 @@ static int xfer_to_guest_mode_work(struct kvm_vcpu *vcpu, unsigned long ti_work)
if (ti_work & _TIF_NEED_RESCHED)
schedule();
- if (ti_work & _TIF_NOTIFY_RESUME) {
+ if (ti_work & _TIF_NOTIFY_RESUME)
tracehook_notify_resume(NULL);
- rseq_handle_notify_resume(NULL, NULL);
- }
ret = arch_xfer_to_guest_mode_handle_work(vcpu, ti_work);
if (ret)
--
cgit v1.2.3-70-g09d2
From de5f4213dafa8f8b0b52cdaf06bb35ad4cab1681 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 1 Sep 2021 13:30:28 -0700
Subject: tools: Move x86 syscall number fallbacks to .../uapi/
Move unistd_{32,64}.h from x86/include/asm to x86/include/uapi/asm so
that tools/selftests that install kernel headers, e.g. KVM selftests, can
include non-uapi tools headers, e.g. to get 'struct list_head', without
effectively overriding the installed non-tool uapi headers.
Swapping KVM's search order, e.g. to search the kernel headers before
tool headers, is not a viable option as doing results in linux/type.h and
other core headers getting pulled from the kernel headers, which do not
have the kernel-internal typedefs that are used through tools, including
many files outside of selftests/kvm's control.
Prior to commit cec07f53c398 ("perf tools: Move syscall number fallbacks
from perf-sys.h to tools/arch/x86/include/asm/"), the handcoded numbers
were actual fallbacks, i.e. overriding unistd_{32,64}.h from the kernel
headers was unintentional.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210901203030.1292304-4-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
tools/arch/x86/include/asm/unistd_32.h | 16 ----------------
tools/arch/x86/include/asm/unistd_64.h | 19 -------------------
tools/arch/x86/include/uapi/asm/unistd_32.h | 16 ++++++++++++++++
tools/arch/x86/include/uapi/asm/unistd_64.h | 19 +++++++++++++++++++
4 files changed, 35 insertions(+), 35 deletions(-)
delete mode 100644 tools/arch/x86/include/asm/unistd_32.h
delete mode 100644 tools/arch/x86/include/asm/unistd_64.h
create mode 100644 tools/arch/x86/include/uapi/asm/unistd_32.h
create mode 100644 tools/arch/x86/include/uapi/asm/unistd_64.h
diff --git a/tools/arch/x86/include/asm/unistd_32.h b/tools/arch/x86/include/asm/unistd_32.h
deleted file mode 100644
index 60a89dba01b6..000000000000
--- a/tools/arch/x86/include/asm/unistd_32.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __NR_perf_event_open
-# define __NR_perf_event_open 336
-#endif
-#ifndef __NR_futex
-# define __NR_futex 240
-#endif
-#ifndef __NR_gettid
-# define __NR_gettid 224
-#endif
-#ifndef __NR_getcpu
-# define __NR_getcpu 318
-#endif
-#ifndef __NR_setns
-# define __NR_setns 346
-#endif
diff --git a/tools/arch/x86/include/asm/unistd_64.h b/tools/arch/x86/include/asm/unistd_64.h
deleted file mode 100644
index 4205ed4158bf..000000000000
--- a/tools/arch/x86/include/asm/unistd_64.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __NR_userfaultfd
-#define __NR_userfaultfd 282
-#endif
-#ifndef __NR_perf_event_open
-# define __NR_perf_event_open 298
-#endif
-#ifndef __NR_futex
-# define __NR_futex 202
-#endif
-#ifndef __NR_gettid
-# define __NR_gettid 186
-#endif
-#ifndef __NR_getcpu
-# define __NR_getcpu 309
-#endif
-#ifndef __NR_setns
-#define __NR_setns 308
-#endif
diff --git a/tools/arch/x86/include/uapi/asm/unistd_32.h b/tools/arch/x86/include/uapi/asm/unistd_32.h
new file mode 100644
index 000000000000..60a89dba01b6
--- /dev/null
+++ b/tools/arch/x86/include/uapi/asm/unistd_32.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __NR_perf_event_open
+# define __NR_perf_event_open 336
+#endif
+#ifndef __NR_futex
+# define __NR_futex 240
+#endif
+#ifndef __NR_gettid
+# define __NR_gettid 224
+#endif
+#ifndef __NR_getcpu
+# define __NR_getcpu 318
+#endif
+#ifndef __NR_setns
+# define __NR_setns 346
+#endif
diff --git a/tools/arch/x86/include/uapi/asm/unistd_64.h b/tools/arch/x86/include/uapi/asm/unistd_64.h
new file mode 100644
index 000000000000..4205ed4158bf
--- /dev/null
+++ b/tools/arch/x86/include/uapi/asm/unistd_64.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __NR_userfaultfd
+#define __NR_userfaultfd 282
+#endif
+#ifndef __NR_perf_event_open
+# define __NR_perf_event_open 298
+#endif
+#ifndef __NR_futex
+# define __NR_futex 202
+#endif
+#ifndef __NR_gettid
+# define __NR_gettid 186
+#endif
+#ifndef __NR_getcpu
+# define __NR_getcpu 309
+#endif
+#ifndef __NR_setns
+#define __NR_setns 308
+#endif
--
cgit v1.2.3-70-g09d2
From 61e52f1630f54713f5dffa1ab4bb49772235aa5a Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 1 Sep 2021 13:30:29 -0700
Subject: 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@google.com>
Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Message-Id: <20210901203030.1292304-5-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
tools/testing/selftests/kvm/.gitignore | 1 +
tools/testing/selftests/kvm/Makefile | 3 +
tools/testing/selftests/kvm/rseq_test.c | 236 ++++++++++++++++++++++++++++++++
3 files changed, 240 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 98053d3afbda..618bf9bc7f3f 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -48,6 +48,7 @@
/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 5d05801ab816..9ac325cfc94a 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
@@ -93,6 +94,7 @@ 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
@@ -104,6 +106,7 @@ 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..060538bd405a
--- /dev/null
+++ b/tools/testing/selftests/kvm/rseq_test.c
@@ -0,0 +1,236 @@
+// 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 <asm/barrier.h>
+#include <linux/atomic.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,
+};
+
+/*
+ * Use an arbitrary, bogus signature for configuring rseq, this test does not
+ * actually enter an rseq critical section.
+ */
+#define RSEQ_SIG 0xdeadbeef
+
+/*
+ * Any bug related to task migration is likely to be timing-dependent; perform
+ * a large number of migrations to reduce the odds of a false negative.
+ */
+#define NR_TASK_MIGRATIONS 100000
+
+static pthread_t migration_thread;
+static cpu_set_t possible_mask;
+static bool done;
+
+static atomic_t seq_cnt;
+
+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 < NR_TASK_MIGRATIONS; i++) {
+ cpu = i % nr_cpus;
+ if (!CPU_ISSET(cpu, &possible_mask))
+ continue;
+
+ CPU_SET(cpu, &allowed_mask);
+
+ /*
+ * Bump the sequence count twice to allow the reader to detect
+ * that a migration may have occurred in between rseq and sched
+ * CPU ID reads. An odd sequence count indicates a migration
+ * is in-progress, while a completely different count indicates
+ * a migration occurred since the count was last read.
+ */
+ atomic_inc(&seq_cnt);
+
+ /*
+ * Ensure the odd count is visible while sched_getcpu() isn't
+ * stable, i.e. while changing affinity is in-progress.
+ */
+ smp_wmb();
+ r = sched_setaffinity(0, sizeof(allowed_mask), &allowed_mask);
+ TEST_ASSERT(!r, "sched_setaffinity failed, errno = %d (%s)",
+ errno, strerror(errno));
+ smp_wmb();
+ atomic_inc(&seq_cnt);
+
+ CPU_CLR(cpu, &allowed_mask);
+
+ /*
+ * Wait 1-10us before proceeding to the next iteration and more
+ * specifically, before bumping seq_cnt again. A delay is
+ * needed on three fronts:
+ *
+ * 1. To allow sched_setaffinity() to prompt migration before
+ * ioctl(KVM_RUN) enters the guest so that TIF_NOTIFY_RESUME
+ * (or TIF_NEED_RESCHED, which indirectly leads to handling
+ * NOTIFY_RESUME) is handled in KVM context.
+ *
+ * If NOTIFY_RESUME/NEED_RESCHED is set after KVM enters
+ * the guest, the guest will trigger a IO/MMIO exit all the
+ * way to userspace and the TIF flags will be handled by
+ * the generic "exit to userspace" logic, not by KVM. The
+ * exit to userspace is necessary to give the test a chance
+ * to check the rseq CPU ID (see #2).
+ *
+ * Alternatively, guest_code() could include an instruction
+ * to trigger an exit that is handled by KVM, but any such
+ * exit requires architecture specific code.
+ *
+ * 2. To let ioctl(KVM_RUN) make its way back to the test
+ * before the next round of migration. The test's check on
+ * the rseq CPU ID must wait for migration to complete in
+ * order to avoid false positive, thus any kernel rseq bug
+ * will be missed if the next migration starts before the
+ * check completes.
+ *
+ * 3. To ensure the read-side makes efficient forward progress,
+ * e.g. if sched_getcpu() involves a syscall. Stalling the
+ * read-side means the test will spend more time waiting for
+ * sched_getcpu() to stabilize and less time trying to hit
+ * the timing-dependent bug.
+ *
+ * Because any bug in this area is likely to be timing-dependent,
+ * run with a range of delays at 1us intervals from 1us to 10us
+ * as a best effort to avoid tuning the test to the point where
+ * it can hit _only_ the original bug and not detect future
+ * regressions.
+ *
+ * The original bug can reproduce with a delay up to ~500us on
+ * x86-64, but starts to require more iterations to reproduce
+ * as the delay creeps above ~10us, and the average runtime of
+ * each iteration obviously increases as well. Cap the delay
+ * at 10us to keep test runtime reasonable while minimizing
+ * potential coverage loss.
+ *
+ * The lower bound for reproducing the bug is likely below 1us,
+ * e.g. failures occur on x86-64 with nanosleep(0), but at that
+ * point the overhead of the syscall likely dominates the delay.
+ * Use usleep() for simplicity and to avoid unnecessary kernel
+ * dependencies.
+ */
+ usleep((i % 10) + 1);
+ }
+ done = true;
+ return NULL;
+}
+
+int main(int argc, char *argv[])
+{
+ int r, i, snapshot;
+ struct kvm_vm *vm;
+ u32 cpu, rseq_cpu;
+
+ /* 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);
+
+ for (i = 0; !done; i++) {
+ vcpu_run(vm, VCPU_ID);
+ TEST_ASSERT(get_ucall(vm, VCPU_ID, NULL) == UCALL_SYNC,
+ "Guest failed?");
+
+ /*
+ * Verify rseq's CPU matches sched's CPU. Ensure migration
+ * doesn't occur between sched_getcpu() and reading the rseq
+ * cpu_id by rereading both if the sequence count changes, or
+ * if the count is odd (migration in-progress).
+ */
+ do {
+ /*
+ * Drop bit 0 to force a mismatch if the count is odd,
+ * i.e. if a migration is in-progress.
+ */
+ snapshot = atomic_read(&seq_cnt) & ~1;
+
+ /*
+ * Ensure reading sched_getcpu() and rseq.cpu_id
+ * complete in a single "no migration" window, i.e. are
+ * not reordered across the seq_cnt reads.
+ */
+ smp_rmb();
+ cpu = sched_getcpu();
+ rseq_cpu = READ_ONCE(__rseq.cpu_id);
+ smp_rmb();
+ } while (snapshot != atomic_read(&seq_cnt));
+
+ TEST_ASSERT(rseq_cpu == cpu,
+ "rseq CPU = %d, sched CPU = %d\n", rseq_cpu, cpu);
+ }
+
+ /*
+ * Sanity check that the test was able to enter the guest a reasonable
+ * number of times, e.g. didn't get stalled too often/long waiting for
+ * sched_getcpu() to stabilize. A 2:1 migration:KVM_RUN ratio is a
+ * fairly conservative ratio on x86-64, which can do _more_ KVM_RUNs
+ * than migrations given the 1us+ delay in the migration task.
+ */
+ TEST_ASSERT(i > (NR_TASK_MIGRATIONS / 2),
+ "Only performed %d KVM_RUNs, task stalled too much?\n", i);
+
+ pthread_join(migration_thread, NULL);
+
+ kvm_vm_free(vm);
+
+ sys_rseq(RSEQ_FLAG_UNREGISTER);
+
+ return 0;
+}
--
cgit v1.2.3-70-g09d2
From 2da4a23599c263bd4a7658c2fe561cb3a73ea6ae Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 1 Sep 2021 13:30:30 -0700
Subject: KVM: selftests: Remove __NR_userfaultfd syscall fallback
Revert the __NR_userfaultfd syscall fallback added for KVM selftests now
that x86's unistd_{32,63}.h overrides are under uapi/ and thus not in
KVM selftests' search path, i.e. now that KVM gets x86 syscall numbers
from the installed kernel headers.
No functional change intended.
Reviewed-by: Ben Gardon <bgardon@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210901203030.1292304-6-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
tools/arch/x86/include/uapi/asm/unistd_64.h | 3 ---
1 file changed, 3 deletions(-)
diff --git a/tools/arch/x86/include/uapi/asm/unistd_64.h b/tools/arch/x86/include/uapi/asm/unistd_64.h
index 4205ed4158bf..cb52a3a8b8fc 100644
--- a/tools/arch/x86/include/uapi/asm/unistd_64.h
+++ b/tools/arch/x86/include/uapi/asm/unistd_64.h
@@ -1,7 +1,4 @@
/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __NR_userfaultfd
-#define __NR_userfaultfd 282
-#endif
#ifndef __NR_perf_event_open
# define __NR_perf_event_open 298
#endif
--
cgit v1.2.3-70-g09d2