selftests/rseq: Uplift rseq selftests for compatibility with glibc-2.35

glibc-2.35 (upcoming release date 2022-02-01) exposes the rseq per-thread
data in the TCB, accessible at an offset from the thread pointer, rather
than through an actual Thread-Local Storage (TLS) variable, as the
Linux kernel selftests initially expected.

The __rseq_abi TLS and glibc-2.35's ABI for per-thread data cannot
actively coexist in a process, because the kernel supports only a single
rseq registration per thread.

Here is the scheme introduced to ensure selftests can work both with an
older glibc and with glibc-2.35+:

- librseq exposes its own "rseq_offset, rseq_size, rseq_flags" ABI.

- librseq queries for glibc rseq ABI (__rseq_offset, __rseq_size,
  __rseq_flags) using dlsym() in a librseq library constructor. If those
  are found, copy their values into rseq_offset, rseq_size, and
  rseq_flags.

- Else, if those glibc symbols are not found, handle rseq registration
  from librseq and use its own IE-model TLS to implement the rseq ABI
  per-thread storage.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20220124171253.22072-8-mathieu.desnoyers@efficios.com

diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile
index 2af9d39a97168c14dc4c008d59017d45146ff5bf..215e1067f03763075649077b3072f0a560907657 100644 (file)
--- a/tools/testing/selftests/rseq/Makefile
+++ b/tools/testing/selftests/rseq/Makefile
@@ -6,7 +6,7 @@ endif
 
 CFLAGS += -O2 -Wall -g -I./ -I../../../../usr/include/ -L$(OUTPUT) -Wl,-rpath=./ \
          $(CLANG_FLAGS)
-LDLIBS += -lpthread
+LDLIBS += -lpthread -ldl
 
 # Own dependencies because we only want to build against 1st prerequisite, but
 # still track changes to header files and depend on shared object.

diff --git a/tools/testing/selftests/rseq/rseq.c b/tools/testing/selftests/rseq/rseq.c
index 1f905b60728a351c50a4a2e229fa24f20d760f12..07ba0d463a967443b221a247b315cb01c1f20e8b 100644 (file)
--- a/tools/testing/selftests/rseq/rseq.c
+++ b/tools/testing/selftests/rseq/rseq.c
@@ -26,130 +26,123 @@
 #include <assert.h>
 #include <signal.h>
 #include <limits.h>
+#include <dlfcn.h>
 
 #include "../kselftest.h"
 #include "rseq.h"
 
-__thread struct rseq_abi __rseq_abi = {
-       .cpu_id = RSEQ_ABI_CPU_ID_UNINITIALIZED,
-};
+static const int *libc_rseq_offset_p;
+static const unsigned int *libc_rseq_size_p;
+static const unsigned int *libc_rseq_flags_p;
 
-/*
- * Shared with other libraries. This library may take rseq ownership if it is
- * still 0 when executing the library constructor. Set to 1 by library
- * constructor when handling rseq. Set to 0 in destructor if handling rseq.
- */
-int __rseq_handled;
+/* Offset from the thread pointer to the rseq area.  */
+int rseq_offset;
+
+/* Size of the registered rseq area.  0 if the registration was
+   unsuccessful.  */
+unsigned int rseq_size = -1U;
+
+/* Flags used during rseq registration.  */
+unsigned int rseq_flags;
 
-/* Whether this library have ownership of rseq registration. */
 static int rseq_ownership;
 
-static __thread volatile uint32_t __rseq_refcount;
+static
+__thread struct rseq_abi __rseq_abi __attribute__((tls_model("initial-exec"))) = {
+       .cpu_id = RSEQ_ABI_CPU_ID_UNINITIALIZED,
+};
 
-static void signal_off_save(sigset_t *oldset)
+static int sys_rseq(struct rseq_abi *rseq_abi, uint32_t rseq_len,
+                   int flags, uint32_t sig)
 {
-       sigset_t set;
-       int ret;
-
-       sigfillset(&set);
-       ret = pthread_sigmask(SIG_BLOCK, &set, oldset);
-       if (ret)
-               abort();
+       return syscall(__NR_rseq, rseq_abi, rseq_len, flags, sig);
 }
 
-static void signal_restore(sigset_t oldset)
+int rseq_available(void)
 {
-       int ret;
+       int rc;
 
-       ret = pthread_sigmask(SIG_SETMASK, &oldset, NULL);
-       if (ret)
+       rc = sys_rseq(NULL, 0, 0, 0);
+       if (rc != -1)
                abort();
-}
-
-static int sys_rseq(volatile struct rseq_abi *rseq_abi, uint32_t rseq_len,
-                   int flags, uint32_t sig)
-{
-       return syscall(__NR_rseq, rseq_abi, rseq_len, flags, sig);
+       switch (errno) {
+       case ENOSYS:
+               return 0;
+       case EINVAL:
+               return 1;
+       default:
+               abort();
+       }
 }
 
 int rseq_register_current_thread(void)
 {
-       int rc, ret = 0;
-       sigset_t oldset;
+       int rc;
 
-       if (!rseq_ownership)
+       if (!rseq_ownership) {
+               /* Treat libc's ownership as a successful registration. */
                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_abi), 0, RSEQ_SIG);
-       if (!rc) {
-               assert(rseq_current_cpu_raw() >= 0);
-               goto end;
-       }
-       if (errno != EBUSY)
-               RSEQ_WRITE_ONCE(__rseq_abi.cpu_id, RSEQ_ABI_CPU_ID_REGISTRATION_FAILED);
-       ret = -1;
-       __rseq_refcount--;
-end:
-       signal_restore(oldset);
-       return ret;
+       if (rc)
+               return -1;
+       assert(rseq_current_cpu_raw() >= 0);
+       return 0;
 }
 
 int rseq_unregister_current_thread(void)
 {
-       int rc, ret = 0;
-       sigset_t oldset;
+       int rc;
 
-       if (!rseq_ownership)
+       if (!rseq_ownership) {
+               /* Treat libc's ownership as a successful unregistration. */
                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_abi),
-                     RSEQ_ABI_FLAG_UNREGISTER, RSEQ_SIG);
-       if (!rc)
-               goto end;
-       __rseq_refcount = 1;
-       ret = -1;
-end:
-       signal_restore(oldset);
-       return ret;
+       rc = sys_rseq(&__rseq_abi, sizeof(struct rseq_abi), RSEQ_ABI_FLAG_UNREGISTER, RSEQ_SIG);
+       if (rc)
+               return -1;
+       return 0;
 }
 
-int32_t rseq_fallback_current_cpu(void)
+static __attribute__((constructor))
+void rseq_init(void)
 {
-       int32_t cpu;
-
-       cpu = sched_getcpu();
-       if (cpu < 0) {
-               perror("sched_getcpu()");
-               abort();
+       libc_rseq_offset_p = dlsym(RTLD_NEXT, "__rseq_offset");
+       libc_rseq_size_p = dlsym(RTLD_NEXT, "__rseq_size");
+       libc_rseq_flags_p = dlsym(RTLD_NEXT, "__rseq_flags");
+       if (libc_rseq_size_p && libc_rseq_offset_p && libc_rseq_flags_p) {
+               /* rseq registration owned by glibc */
+               rseq_offset = *libc_rseq_offset_p;
+               rseq_size = *libc_rseq_size_p;
+               rseq_flags = *libc_rseq_flags_p;
+               return;
        }
-       return cpu;
-}
-
-void __attribute__((constructor)) rseq_init(void)
-{
-       /* Check whether rseq is handled by another library. */
-       if (__rseq_handled)
+       if (!rseq_available())
                return;
-       __rseq_handled = 1;
        rseq_ownership = 1;
+       rseq_offset = (void *)&__rseq_abi - rseq_thread_pointer();
+       rseq_size = sizeof(struct rseq_abi);
+       rseq_flags = 0;
 }
 
-void __attribute__((destructor)) rseq_fini(void)
+static __attribute__((destructor))
+void rseq_exit(void)
 {
        if (!rseq_ownership)
                return;
-       __rseq_handled = 0;
+       rseq_offset = 0;
+       rseq_size = -1U;
        rseq_ownership = 0;
 }
+
+int32_t rseq_fallback_current_cpu(void)
+{
+       int32_t cpu;
+
+       cpu = sched_getcpu();
+       if (cpu < 0) {
+               perror("sched_getcpu()");
+               abort();
+       }
+       return cpu;
+}

diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h
index ca668a2af1729f15f75364403c2fe0ea3ca7f0d2..17531ccd3090657517863daafefc145c78844a3c 100644 (file)
--- a/tools/testing/selftests/rseq/rseq.h
+++ b/tools/testing/selftests/rseq/rseq.h
@@ -43,12 +43,19 @@
 #define RSEQ_INJECT_FAILED
 #endif
 
-extern __thread struct rseq_abi __rseq_abi;
-extern int __rseq_handled;
+#include "rseq-thread-pointer.h"
+
+/* Offset from the thread pointer to the rseq area.  */
+extern int rseq_offset;
+/* Size of the registered rseq area.  0 if the registration was
+   unsuccessful.  */
+extern unsigned int rseq_size;
+/* Flags used during rseq registration.  */
+extern unsigned int rseq_flags;
 
 static inline struct rseq_abi *rseq_get_abi(void)
 {
-       return &__rseq_abi;
+       return (struct rseq_abi *) ((uintptr_t) rseq_thread_pointer() + rseq_offset);
 }
 
 #define rseq_likely(x)         __builtin_expect(!!(x), 1)