1 files changed, 181 insertions, 23 deletions

diff --git a/tools/testing/selftests/rseq/rseq.c b/tools/testing/selftests/rseq/rseq.c
index 4177f9507bbe..a736727b83c1 100644
--- a/tools/testing/selftests/rseq/rseq.c
+++ b/tools/testing/selftests/rseq/rseq.c
@@ -28,19 +28,33 @@
 #include <limits.h>
 #include <dlfcn.h>
 #include <stddef.h>
+#include <sys/auxv.h>
+#include <linux/auxvec.h>
 
-#include "../kselftest.h"
+#include <linux/compiler.h>
+
+#include "kselftest.h"
 #include "rseq.h"
 
-static const ptrdiff_t *libc_rseq_offset_p;
-static const unsigned int *libc_rseq_size_p;
-static const unsigned int *libc_rseq_flags_p;
+/*
+ * Define weak versions to play nice with binaries that are statically linked
+ * against a libc that doesn't support registering its own rseq.
+ */
+extern __weak ptrdiff_t __rseq_offset;
+extern __weak unsigned int __rseq_size;
+extern __weak unsigned int __rseq_flags;
+
+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.  */
+/* Offset from the thread pointer to the rseq area. */
 ptrdiff_t rseq_offset;
 
-/* Size of the registered rseq area.  0 if the registration was
-   unsuccessful.  */
+/*
+ * Size of the registered rseq area. 0 if the registration was
+ * unsuccessful.
+ */
 unsigned int rseq_size = -1U;
 
 /* Flags used during rseq registration.  */
@@ -48,9 +62,29 @@ unsigned int rseq_flags;
 
 static int rseq_ownership;
 
+/* 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 struct rseq_abi __rseq_abi __attribute__((tls_model("initial-exec"))) = {
-	.cpu_id = RSEQ_ABI_CPU_ID_UNINITIALIZED,
+__thread union rseq_tls __rseq __attribute__((tls_model("initial-exec"))) = {
+	.abi = {
+		.cpu_id = RSEQ_ABI_CPU_ID_UNINITIALIZED,
+	},
 };
 
 static int sys_rseq(struct rseq_abi *rseq_abi, uint32_t rseq_len,
@@ -59,7 +93,12 @@ static int sys_rseq(struct rseq_abi *rseq_abi, uint32_t rseq_len,
 	return syscall(__NR_rseq, rseq_abi, rseq_len, flags, sig);
 }
 
-int rseq_available(void)
+static int sys_getcpu(unsigned *cpu, unsigned *node)
+{
+	return syscall(__NR_getcpu, cpu, node, NULL);
+}
+
+bool rseq_available(void)
 {
 	int rc;
 
@@ -68,14 +107,51 @@ int rseq_available(void)
 		abort();
 	switch (errno) {
 	case ENOSYS:
-		return 0;
+		return false;
 	case EINVAL:
-		return 1;
+		return true;
 	default:
 		abort();
 	}
 }
 
+/* The rseq areas need to be at least 32 bytes. */
+static
+unsigned int get_rseq_min_alloc_size(void)
+{
+	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;
@@ -84,10 +160,29 @@ int rseq_register_current_thread(void)
 		/* Treat libc's ownership as a successful registration. */
 		return 0;
 	}
-	rc = sys_rseq(&__rseq_abi, sizeof(struct rseq_abi), 0, RSEQ_SIG);
-	if (rc)
+	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;
+	}
 	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;
 }
 
@@ -99,7 +194,7 @@ int rseq_unregister_current_thread(void)
 		/* Treat libc's ownership as a successful unregistration. */
 		return 0;
 	}
-	rc = sys_rseq(&__rseq_abi, sizeof(struct rseq_abi), RSEQ_ABI_FLAG_UNREGISTER, RSEQ_SIG);
+	rc = sys_rseq(&__rseq.abi, get_rseq_min_alloc_size(), RSEQ_ABI_FLAG_UNREGISTER, RSEQ_SIG);
 	if (rc)
 		return -1;
 	return 0;
@@ -108,23 +203,73 @@ int rseq_unregister_current_thread(void)
 static __attribute__((constructor))
 void rseq_init(void)
 {
-	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 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_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;
-		rseq_size = *libc_rseq_size_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;
 	}
-	if (!rseq_available())
-		return;
 	rseq_ownership = 1;
-	rseq_offset = (void *)&__rseq_abi - rseq_thread_pointer();
-	rseq_size = sizeof(struct rseq_abi);
+
+	/* 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))
@@ -148,3 +293,16 @@ int32_t rseq_fallback_current_cpu(void)
 	}
 	return cpu;
 }
+
+int32_t rseq_fallback_current_node(void)
+{
+	uint32_t cpu_id, node_id;
+	int ret;
+
+	ret = sys_getcpu(&cpu_id, &node_id);
+	if (ret) {
+		perror("sys_getcpu()");
+		return ret;
+	}
+	return (int32_t) node_id;
+}