1 files changed, 227 insertions, 75 deletions

diff --git a/tools/testing/selftests/rseq/rseq.c b/tools/testing/selftests/rseq/rseq.c
index 7159eb777fd3..663a9cef1952 100644
--- a/tools/testing/selftests/rseq/rseq.c
+++ b/tools/testing/selftests/rseq/rseq.c
@@ -26,104 +26,260 @@
 #include <assert.h>
 #include <signal.h>
 #include <limits.h>
+#include <dlfcn.h>
+#include <stddef.h>
+#include <sys/auxv.h>
+#include <linux/auxvec.h>
 
+#include <linux/compiler.h>
+
+#include "../kselftest.h"
 #include "rseq.h"
 
-#define ARRAY_SIZE(arr)	(sizeof(arr) / sizeof((arr)[0]))
+/*
+ * Define weak versions to play nice with binaries that are statically linked
+ * against a libc that doesn't support registering its own rseq.
+ */
+__weak ptrdiff_t __rseq_offset;
+__weak unsigned int __rseq_size;
+__weak unsigned int __rseq_flags;
 
-__thread volatile struct rseq __rseq_abi = {
-	.cpu_id = RSEQ_CPU_ID_UNINITIALIZED,
-};
+static const ptrdiff_t *libc_rseq_offset_p = &__rseq_offset;
+static const unsigned int *libc_rseq_size_p = &__rseq_size;
+static const unsigned int *libc_rseq_flags_p = &__rseq_flags;
+
+/* Offset from the thread pointer to the rseq area. */
+ptrdiff_t rseq_offset;
 
 /*
- * 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.
+ * Size of the registered rseq area. 0 if the registration was
+ * unsuccessful.
  */
-int __rseq_handled;
+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;
+/* Allocate a large area for the TLS. */
+#define RSEQ_THREAD_AREA_ALLOC_SIZE	1024
+
+/* Original struct rseq feature size is 20 bytes. */
+#define ORIG_RSEQ_FEATURE_SIZE		20
+
+/* Original struct rseq allocation size is 32 bytes. */
+#define ORIG_RSEQ_ALLOC_SIZE		32
+
+/*
+ * Use a union to ensure we allocate a TLS area of 1024 bytes to accomodate an
+ * rseq registration that is larger than the current rseq ABI.
+ */
+union rseq_tls {
+	struct rseq_abi abi;
+	char dummy[RSEQ_THREAD_AREA_ALLOC_SIZE];
+};
+
+static
+__thread union rseq_tls __rseq __attribute__((tls_model("initial-exec"))) = {
+	.abi = {
+		.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;
+	return syscall(__NR_rseq, rseq_abi, rseq_len, flags, sig);
+}
 
-	sigfillset(&set);
-	ret = pthread_sigmask(SIG_BLOCK, &set, oldset);
-	if (ret)
-		abort();
+static int sys_getcpu(unsigned *cpu, unsigned *node)
+{
+	return syscall(__NR_getcpu, cpu, node, NULL);
 }
 
-static void signal_restore(sigset_t oldset)
+bool 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();
+	switch (errno) {
+	case ENOSYS:
+		return false;
+	case EINVAL:
+		return true;
+	default:
+		abort();
+	}
 }
 
-static int sys_rseq(volatile struct rseq *rseq_abi, uint32_t rseq_len,
-		    int flags, uint32_t sig)
+/* The rseq areas need to be at least 32 bytes. */
+static
+unsigned int get_rseq_min_alloc_size(void)
 {
-	return syscall(__NR_rseq, rseq_abi, rseq_len, flags, sig);
+	unsigned int alloc_size = rseq_size;
+
+	if (alloc_size < ORIG_RSEQ_ALLOC_SIZE)
+		alloc_size = ORIG_RSEQ_ALLOC_SIZE;
+	return alloc_size;
+}
+
+/*
+ * Return the feature size supported by the kernel.
+ *
+ * Depending on the value returned by getauxval(AT_RSEQ_FEATURE_SIZE):
+ *
+ * 0:   Return ORIG_RSEQ_FEATURE_SIZE (20)
+ * > 0: Return the value from getauxval(AT_RSEQ_FEATURE_SIZE).
+ *
+ * It should never return a value below ORIG_RSEQ_FEATURE_SIZE.
+ */
+static
+unsigned int get_rseq_kernel_feature_size(void)
+{
+	unsigned long auxv_rseq_feature_size, auxv_rseq_align;
+
+	auxv_rseq_align = getauxval(AT_RSEQ_ALIGN);
+	assert(!auxv_rseq_align || auxv_rseq_align <= RSEQ_THREAD_AREA_ALLOC_SIZE);
+
+	auxv_rseq_feature_size = getauxval(AT_RSEQ_FEATURE_SIZE);
+	assert(!auxv_rseq_feature_size || auxv_rseq_feature_size <= RSEQ_THREAD_AREA_ALLOC_SIZE);
+	if (auxv_rseq_feature_size)
+		return auxv_rseq_feature_size;
+	else
+		return ORIG_RSEQ_FEATURE_SIZE;
 }
 
 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), 0, RSEQ_SIG);
-	if (!rc) {
-		assert(rseq_current_cpu_raw() >= 0);
-		goto end;
+	rc = sys_rseq(&__rseq.abi, get_rseq_min_alloc_size(), 0, RSEQ_SIG);
+	if (rc) {
+		/*
+		 * After at least one thread has registered successfully
+		 * (rseq_size > 0), the registration of other threads should
+		 * never fail.
+		 */
+		if (RSEQ_READ_ONCE(rseq_size) > 0) {
+			/* Incoherent success/failure within process. */
+			abort();
+		}
+		return -1;
 	}
-	if (errno != EBUSY)
-		__rseq_abi.cpu_id = RSEQ_CPU_ID_REGISTRATION_FAILED;
-	ret = -1;
-	__rseq_refcount--;
-end:
-	signal_restore(oldset);
-	return ret;
+	assert(rseq_current_cpu_raw() >= 0);
+
+	/*
+	 * The first thread to register sets the rseq_size to mimic the libc
+	 * behavior.
+	 */
+	if (RSEQ_READ_ONCE(rseq_size) == 0) {
+		RSEQ_WRITE_ONCE(rseq_size, get_rseq_kernel_feature_size());
+	}
+
+	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),
-		      RSEQ_FLAG_UNREGISTER, RSEQ_SIG);
-	if (!rc)
-		goto end;
-	__rseq_refcount = 1;
-	ret = -1;
-end:
-	signal_restore(oldset);
-	return ret;
+	rc = sys_rseq(&__rseq.abi, get_rseq_min_alloc_size(), RSEQ_ABI_FLAG_UNREGISTER, RSEQ_SIG);
+	if (rc)
+		return -1;
+	return 0;
+}
+
+static __attribute__((constructor))
+void rseq_init(void)
+{
+	/*
+	 * If the libc's registered rseq size isn't already valid, it may be
+	 * because the binary is dynamically linked and not necessarily due to
+	 * libc not having registered a restartable sequence.  Try to find the
+	 * symbols if that's the case.
+	 */
+	if (!*libc_rseq_size_p) {
+		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 &&
+			*libc_rseq_size_p != 0) {
+		unsigned int libc_rseq_size;
+
+		/* rseq registration owned by glibc */
+		rseq_offset = *libc_rseq_offset_p;
+		libc_rseq_size = *libc_rseq_size_p;
+		rseq_flags = *libc_rseq_flags_p;
+
+		/*
+		 * Previous versions of glibc expose the value
+		 * 32 even though the kernel only supported 20
+		 * bytes initially. Therefore treat 32 as a
+		 * special-case. glibc 2.40 exposes a 20 bytes
+		 * __rseq_size without using getauxval(3) to
+		 * query the supported size, while still allocating a 32
+		 * bytes area. Also treat 20 as a special-case.
+		 *
+		 * Special-cases are handled by using the following
+		 * value as active feature set size:
+		 *
+		 *   rseq_size = min(32, get_rseq_kernel_feature_size())
+		 */
+		switch (libc_rseq_size) {
+		case ORIG_RSEQ_FEATURE_SIZE:
+			fallthrough;
+		case ORIG_RSEQ_ALLOC_SIZE:
+		{
+			unsigned int rseq_kernel_feature_size = get_rseq_kernel_feature_size();
+
+			if (rseq_kernel_feature_size < ORIG_RSEQ_ALLOC_SIZE)
+				rseq_size = rseq_kernel_feature_size;
+			else
+				rseq_size = ORIG_RSEQ_ALLOC_SIZE;
+			break;
+		}
+		default:
+			/* Otherwise just use the __rseq_size from libc as rseq_size. */
+			rseq_size = libc_rseq_size;
+			break;
+		}
+		return;
+	}
+	rseq_ownership = 1;
+
+	/* Calculate the offset of the rseq area from the thread pointer. */
+	rseq_offset = (void *)&__rseq.abi - rseq_thread_pointer();
+
+	/* rseq flags are deprecated, always set to 0. */
+	rseq_flags = 0;
+
+	/*
+	 * Set the size to 0 until at least one thread registers to mimic the
+	 * libc behavior.
+	 */
+	rseq_size = 0;
+}
+
+static __attribute__((destructor))
+void rseq_exit(void)
+{
+	if (!rseq_ownership)
+		return;
+	rseq_offset = 0;
+	rseq_size = -1U;
+	rseq_ownership = 0;
 }
 
 int32_t rseq_fallback_current_cpu(void)
@@ -138,19 +294,15 @@ int32_t rseq_fallback_current_cpu(void)
 	return cpu;
 }
 
-void __attribute__((constructor)) rseq_init(void)
+int32_t rseq_fallback_current_node(void)
 {
-	/* Check whether rseq is handled by another library. */
-	if (__rseq_handled)
-		return;
-	__rseq_handled = 1;
-	rseq_ownership = 1;
-}
+	uint32_t cpu_id, node_id;
+	int ret;
 
-void __attribute__((destructor)) rseq_fini(void)
-{
-	if (!rseq_ownership)
-		return;
-	__rseq_handled = 0;
-	rseq_ownership = 0;
+	ret = sys_getcpu(&cpu_id, &node_id);
+	if (ret) {
+		perror("sys_getcpu()");
+		return ret;
+	}
+	return (int32_t) node_id;
 }