[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20200925181518.4141-2-mathieu.desnoyers@efficios.com>
Date: Fri, 25 Sep 2020 14:15:18 -0400
From: Mathieu Desnoyers <mathieu.desnoyers@...icios.com>
To: Peter Zijlstra <peterz@...radead.org>
Cc: linux-kernel@...r.kernel.org, Thomas Gleixner <tglx@...utronix.de>,
"Paul E . McKenney" <paulmck@...nel.org>,
Boqun Feng <boqun.feng@...il.com>,
"H . Peter Anvin" <hpa@...or.com>, Paul Turner <pjt@...gle.com>,
linux-api@...r.kernel.org,
Christian Brauner <christian.brauner@...ntu.com>,
Florian Weimer <fw@...eb.enyo.de>, carlos@...hat.com,
Mathieu Desnoyers <mathieu.desnoyers@...icios.com>
Subject: [RFC PATCH 2/2] selftests/rseq: Adapt x86-64 rseq selftest to rseq KTLS prototype
The rseq KTLS ABI only requires a single SET_KTLS_OFFSET system call at
library init for the entire thread group. There is no more need for
per-thread registration.
The only architecture-specific part of this patch is
rseq_get_thread_pointer, which is only implemented for x86-64
so far. Other architectures can rely on __builtin_thread_pointer(), but
it is unfortunately unimplemented by gcc for at least x86-32 and x86-64
at the moment.
This is a minimal change to the rseq selftests which keeps using a
fixed-size __rseq_abi TLS inital-exec variable in user-space, but
use the rseq KTLS ABI for registration to the kernel.
In order to facilitate prototyping without requiring an updated glibc,
there is one per-thread operation which is still performed right after
thread creation: RSEQ_FLAG_SET_KTLS_THREAD. It sets the rseq_ktls flag
to true in the current task struct. This is meant to be performed by
glibc through use of clone3 CLONE_RSEQ_KTLS.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@...icios.com>
Cc: Carlos O'Donell <carlos@...hat.com>
Cc: "Florian Weimer <fweimer@...hat.com>
Cc: Peter Zijlstra (Intel) <peterz@...radead.org>
Cc: "Paul E. McKenney" <paulmck@...nel.org>
Cc: Boqun Feng <boqun.feng@...il.com>
---
tools/testing/selftests/rseq/rseq-x86.h | 8 ++
tools/testing/selftests/rseq/rseq.c | 101 ++++++++----------------
tools/testing/selftests/rseq/rseq.h | 2 +-
3 files changed, 44 insertions(+), 67 deletions(-)
diff --git a/tools/testing/selftests/rseq/rseq-x86.h b/tools/testing/selftests/rseq/rseq-x86.h
index b2da6004fe30..e959d3fb1dea 100644
--- a/tools/testing/selftests/rseq/rseq-x86.h
+++ b/tools/testing/selftests/rseq/rseq-x86.h
@@ -28,6 +28,14 @@
#ifdef __x86_64__
+static inline void *rseq_get_thread_pointer(void)
+{
+ void *p;
+
+ asm ("mov %%fs:0, %0" : "=r" (p));
+ return p;
+}
+
#define rseq_smp_mb() \
__asm__ __volatile__ ("lock; addl $0,-128(%%rsp)" ::: "memory", "cc")
#define rseq_smp_rmb() rseq_barrier()
diff --git a/tools/testing/selftests/rseq/rseq.c b/tools/testing/selftests/rseq/rseq.c
index 7159eb777fd3..9bc5c195a79a 100644
--- a/tools/testing/selftests/rseq/rseq.c
+++ b/tools/testing/selftests/rseq/rseq.c
@@ -31,7 +31,7 @@
#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]))
-__thread volatile struct rseq __rseq_abi = {
+__thread struct rseq __rseq_abi = {
.cpu_id = RSEQ_CPU_ID_UNINITIALIZED,
};
@@ -47,83 +47,26 @@ static int rseq_ownership;
static __thread volatile uint32_t __rseq_refcount;
-static void signal_off_save(sigset_t *oldset)
-{
- sigset_t set;
- int ret;
-
- sigfillset(&set);
- ret = pthread_sigmask(SIG_BLOCK, &set, oldset);
- if (ret)
- abort();
-}
-
-static void signal_restore(sigset_t oldset)
-{
- int ret;
-
- ret = pthread_sigmask(SIG_SETMASK, &oldset, NULL);
- if (ret)
- abort();
-}
-
-static int sys_rseq(volatile struct rseq *rseq_abi, uint32_t rseq_len,
+static int sys_rseq(void *ptr, uint32_t rseq_len,
int flags, uint32_t sig)
{
- return syscall(__NR_rseq, rseq_abi, rseq_len, flags, sig);
+ return syscall(__NR_rseq, ptr, rseq_len, flags, sig);
}
int rseq_register_current_thread(void)
{
- int rc, ret = 0;
- sigset_t oldset;
+ int rc;
- if (!rseq_ownership)
- return 0;
- signal_off_save(&oldset);
- if (__rseq_refcount == UINT_MAX) {
- ret = -1;
- goto end;
- }
- if (__rseq_refcount++)
- goto end;
- rc = sys_rseq(&__rseq_abi, sizeof(struct rseq), 0, RSEQ_SIG);
- if (!rc) {
- assert(rseq_current_cpu_raw() >= 0);
- goto end;
+ rc = sys_rseq(NULL, 0, RSEQ_FLAG_SET_KTLS_THREAD, 0);
+ if (rc) {
+ abort();
}
- if (errno != EBUSY)
- __rseq_abi.cpu_id = RSEQ_CPU_ID_REGISTRATION_FAILED;
- ret = -1;
- __rseq_refcount--;
-end:
- signal_restore(oldset);
- return ret;
+ return 0;
}
int rseq_unregister_current_thread(void)
{
- int rc, ret = 0;
- sigset_t oldset;
-
- if (!rseq_ownership)
- return 0;
- signal_off_save(&oldset);
- if (!__rseq_refcount) {
- ret = -1;
- goto end;
- }
- if (--__rseq_refcount)
- goto end;
- rc = sys_rseq(&__rseq_abi, sizeof(struct rseq),
- RSEQ_FLAG_UNREGISTER, RSEQ_SIG);
- if (!rc)
- goto end;
- __rseq_refcount = 1;
- ret = -1;
-end:
- signal_restore(oldset);
- return ret;
+ return 0;
}
int32_t rseq_fallback_current_cpu(void)
@@ -140,11 +83,37 @@ int32_t rseq_fallback_current_cpu(void)
void __attribute__((constructor)) rseq_init(void)
{
+ int rc;
+ long rseq_abi_offset;
+ struct rseq_ktls_layout layout;
+ struct rseq_ktls_offset offset;
+
/* Check whether rseq is handled by another library. */
if (__rseq_handled)
return;
__rseq_handled = 1;
rseq_ownership = 1;
+
+ rseq_abi_offset = (long) &__rseq_abi - (long) rseq_get_thread_pointer();
+
+ rc = sys_rseq(&layout, 0, RSEQ_FLAG_GET_KTLS_LAYOUT, 0);
+ if (rc) {
+ abort();
+ }
+ if (layout.size > sizeof(struct rseq) || layout.alignment > __alignof__(struct rseq)) {
+ abort();
+ }
+ offset.offset = rseq_abi_offset;
+ rc = sys_rseq(&offset, 0, RSEQ_FLAG_SET_KTLS_OFFSET, 0);
+ if (rc) {
+ abort();
+ }
+ rc = sys_rseq(NULL, 0, RSEQ_FLAG_SET_SIG, RSEQ_SIG);
+ if (rc) {
+ abort();
+ }
+
+ assert(rseq_current_cpu_raw() >= 0);
}
void __attribute__((destructor)) rseq_fini(void)
diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h
index 3f63eb362b92..3c4fad7be4f7 100644
--- a/tools/testing/selftests/rseq/rseq.h
+++ b/tools/testing/selftests/rseq/rseq.h
@@ -43,7 +43,7 @@
#define RSEQ_INJECT_FAILED
#endif
-extern __thread volatile struct rseq __rseq_abi;
+extern __thread __attribute__((tls_model("initial-exec"))) struct rseq __rseq_abi;
extern int __rseq_handled;
#define rseq_likely(x) __builtin_expect(!!(x), 1)
--
2.17.1
Powered by blists - more mailing lists