Merge branch 'core-rseq-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull restartable sequence support from Thomas Gleixner:
 "The restartable sequences syscall (finally):

  After a lot of back and forth discussion and massive delays caused by
  the speculative distraction of maintainers, the core set of
  restartable sequences has finally reached a consensus.

  It comes with the basic non disputed core implementation along with
  support for arm, powerpc and x86 and a full set of selftests

  It was exposed to linux-next earlier this week, so it does not fully
  comply with the merge window requirements, but there is really no
  point to drag it out for yet another cycle"

* 'core-rseq-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  rseq/selftests: Provide Makefile, scripts, gitignore
  rseq/selftests: Provide parametrized tests
  rseq/selftests: Provide basic percpu ops test
  rseq/selftests: Provide basic test
  rseq/selftests: Provide rseq library
  selftests/lib.mk: Introduce OVERRIDE_TARGETS
  powerpc: Wire up restartable sequences system call
  powerpc: Add syscall detection for restartable sequences
  powerpc: Add support for restartable sequences
  x86: Wire up restartable sequence system call
  x86: Add support for restartable sequences
  arm: Wire up restartable sequences system call
  arm: Add syscall detection for restartable sequences
  arm: Add restartable sequences support
  rseq: Introduce restartable sequences system call
  uapi/headers: Provide types_32_64.h

MAINTAINERS

@@ -12134,6 +12134,18 @@ F:	include/dt-bindings/reset/
 F:	include/linux/reset.h
 F:	include/linux/reset-controller.h
 
+RESTARTABLE SEQUENCES SUPPORT
+M:	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+M:	Peter Zijlstra <peterz@infradead.org>
+M:	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
+M:	Boqun Feng <boqun.feng@gmail.com>
+L:	linux-kernel@vger.kernel.org
+S:	Supported
+F:	kernel/rseq.c
+F:	include/uapi/linux/rseq.h
+F:	include/trace/events/rseq.h
+F:	tools/testing/selftests/rseq/
+
 RFKILL
 M:	Johannes Berg <johannes@sipsolutions.net>
 L:	linux-wireless@vger.kernel.org

arch/Kconfig

@@ -272,6 +272,13 @@ config HAVE_REGS_AND_STACK_ACCESS_API
 	  declared in asm/ptrace.h
 	  For example the kprobes-based event tracer needs this API.
 
+config HAVE_RSEQ
+	bool
+	depends on HAVE_REGS_AND_STACK_ACCESS_API
+	help
+	  This symbol should be selected by an architecture if it
+	  supports an implementation of restartable sequences.
+
 config HAVE_CLK
 	bool
 	help

arch/arm/Kconfig

@@ -91,6 +91,7 @@ config ARM
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_RCU_TABLE_FREE if (SMP && ARM_LPAE)
 	select HAVE_REGS_AND_STACK_ACCESS_API
+	select HAVE_RSEQ
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_UID16
 	select HAVE_VIRT_CPU_ACCOUNTING_GEN

arch/arm/kernel/entry-common.S

@@ -39,12 +39,13 @@ saved_pc	.req	lr
 
 	.section .entry.text,"ax",%progbits
 	.align	5
-#if !(IS_ENABLED(CONFIG_TRACE_IRQFLAGS) || IS_ENABLED(CONFIG_CONTEXT_TRACKING))
+#if !(IS_ENABLED(CONFIG_TRACE_IRQFLAGS) || IS_ENABLED(CONFIG_CONTEXT_TRACKING) || \
+	IS_ENABLED(CONFIG_DEBUG_RSEQ))
 /*
  * This is the fast syscall return path.  We do as little as possible here,
  * such as avoiding writing r0 to the stack.  We only use this path if we
- * have tracing and context tracking disabled - the overheads from those
- * features make this path too inefficient.
+ * have tracing, context tracking and rseq debug disabled - the overheads
+ * from those features make this path too inefficient.
  */
 ret_fast_syscall:
  UNWIND(.fnstart	)
@@ -71,14 +72,20 @@ fast_work_pending:
 	/* fall through to work_pending */
 #else
 /*
- * The "replacement" ret_fast_syscall for when tracing or context tracking
- * is enabled.  As we will need to call out to some C functions, we save
- * r0 first to avoid needing to save registers around each C function call.
+ * The "replacement" ret_fast_syscall for when tracing, context tracking,
+ * or rseq debug is enabled.  As we will need to call out to some C functions,
+ * we save r0 first to avoid needing to save registers around each C function
+ * call.
  */
 ret_fast_syscall:
  UNWIND(.fnstart	)
  UNWIND(.cantunwind	)
 	str	r0, [sp, #S_R0 + S_OFF]!	@ save returned r0
+#if IS_ENABLED(CONFIG_DEBUG_RSEQ)
+	/* do_rseq_syscall needs interrupts enabled. */
+	mov	r0, sp				@ 'regs'
+	bl	do_rseq_syscall
+#endif
 	disable_irq_notrace			@ disable interrupts
 	ldr	r2, [tsk, #TI_ADDR_LIMIT]
 	cmp	r2, #TASK_SIZE
@@ -113,6 +120,12 @@ ENDPROC(ret_fast_syscall)
  */
 ENTRY(ret_to_user)
 ret_slow_syscall:
+#if IS_ENABLED(CONFIG_DEBUG_RSEQ)
+	/* do_rseq_syscall needs interrupts enabled. */
+	enable_irq_notrace			@ enable interrupts
+	mov	r0, sp				@ 'regs'
+	bl	do_rseq_syscall
+#endif
 	disable_irq_notrace			@ disable interrupts
 ENTRY(ret_to_user_from_irq)
 	ldr	r2, [tsk, #TI_ADDR_LIMIT]

arch/arm/kernel/signal.c

@@ -540,6 +540,12 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 	sigset_t *oldset = sigmask_to_save();
 	int ret;
 
+	/*
+	 * Increment event counter and perform fixup for the pre-signal
+	 * frame.
+	 */
+	rseq_signal_deliver(regs);
+
 	/*
 	 * Set up the stack frame
 	 */
@@ -660,6 +666,7 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall)
 			} else {
 				clear_thread_flag(TIF_NOTIFY_RESUME);
 				tracehook_notify_resume(regs);
+				rseq_handle_notify_resume(regs);
 			}
 		}
 		local_irq_disable();
@@ -703,3 +710,10 @@ asmlinkage void addr_limit_check_failed(void)
 {
 	addr_limit_user_check();
 }
+
+#ifdef CONFIG_DEBUG_RSEQ
+asmlinkage void do_rseq_syscall(struct pt_regs *regs)
+{
+	rseq_syscall(regs);
+}
+#endif

arch/arm/tools/syscall.tbl

@@ -412,3 +412,4 @@
 395	common	pkey_alloc		sys_pkey_alloc
 396	common	pkey_free		sys_pkey_free
 397	common	statx			sys_statx
+398	common	rseq			sys_rseq

arch/powerpc/Kconfig

@@ -220,6 +220,7 @@ config PPC
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_VIRT_CPU_ACCOUNTING
 	select HAVE_IRQ_TIME_ACCOUNTING
+	select HAVE_RSEQ
 	select IOMMU_HELPER			if PPC64
 	select IRQ_DOMAIN
 	select IRQ_FORCED_THREADING

arch/powerpc/include/asm/systbl.h

@@ -392,3 +392,4 @@ SYSCALL(statx)
 SYSCALL(pkey_alloc)
 SYSCALL(pkey_free)
 SYSCALL(pkey_mprotect)
+SYSCALL(rseq)

arch/powerpc/include/asm/unistd.h

@@ -12,7 +12,7 @@
 #include <uapi/asm/unistd.h>
 
 
-#define NR_syscalls		387
+#define NR_syscalls		388
 
 #define __NR__exit __NR_exit
 

arch/powerpc/include/uapi/asm/unistd.h

@@ -398,5 +398,6 @@
 #define __NR_pkey_alloc		384
 #define __NR_pkey_free		385
 #define __NR_pkey_mprotect	386
+#define __NR_rseq		387
 
 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */

arch/powerpc/kernel/entry_32.S

@@ -365,6 +365,13 @@ syscall_dotrace_cont:
 	blrl			/* Call handler */
 	.globl	ret_from_syscall
 ret_from_syscall:
+#ifdef CONFIG_DEBUG_RSEQ
+	/* Check whether the syscall is issued inside a restartable sequence */
+	stw	r3,GPR3(r1)
+	addi    r3,r1,STACK_FRAME_OVERHEAD
+	bl      rseq_syscall
+	lwz	r3,GPR3(r1)
+#endif
 	mr	r6,r3
 	CURRENT_THREAD_INFO(r12, r1)
 	/* disable interrupts so current_thread_info()->flags can't change */

arch/powerpc/kernel/entry_64.S

@@ -194,6 +194,14 @@ system_call:			/* label this so stack traces look sane */
 
 .Lsyscall_exit:
 	std	r3,RESULT(r1)
+
+#ifdef CONFIG_DEBUG_RSEQ
+	/* Check whether the syscall is issued inside a restartable sequence */
+	addi    r3,r1,STACK_FRAME_OVERHEAD
+	bl      rseq_syscall
+	ld	r3,RESULT(r1)
+#endif
+
 	CURRENT_THREAD_INFO(r12, r1)
 
 	ld	r8,_MSR(r1)

arch/powerpc/kernel/signal.c

@@ -134,6 +134,8 @@ static void do_signal(struct task_struct *tsk)
 	/* Re-enable the breakpoints for the signal stack */
 	thread_change_pc(tsk, tsk->thread.regs);
 
+	rseq_signal_deliver(tsk->thread.regs);
+
 	if (is32) {
         	if (ksig.ka.sa.sa_flags & SA_SIGINFO)
 			ret = handle_rt_signal32(&ksig, oldset, tsk);
@@ -168,6 +170,7 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags)
 	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
 		clear_thread_flag(TIF_NOTIFY_RESUME);
 		tracehook_notify_resume(regs);
+		rseq_handle_notify_resume(regs);
 	}
 
 	user_enter();

arch/x86/Kconfig

@@ -183,6 +183,7 @@ config X86
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RELIABLE_STACKTRACE		if X86_64 && UNWINDER_FRAME_POINTER && STACK_VALIDATION
 	select HAVE_STACK_VALIDATION		if X86_64
+	select HAVE_RSEQ
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_UNSTABLE_SCHED_CLOCK
 	select HAVE_USER_RETURN_NOTIFIER

arch/x86/entry/common.c

@@ -164,6 +164,7 @@ static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags)
 		if (cached_flags & _TIF_NOTIFY_RESUME) {
 			clear_thread_flag(TIF_NOTIFY_RESUME);
 			tracehook_notify_resume(regs);
+			rseq_handle_notify_resume(regs);
 		}
 
 		if (cached_flags & _TIF_USER_RETURN_NOTIFY)
@@ -254,6 +255,8 @@ __visible inline void syscall_return_slowpath(struct pt_regs *regs)
 	    WARN(irqs_disabled(), "syscall %ld left IRQs disabled", regs->orig_ax))
 		local_irq_enable();
 
+	rseq_syscall(regs);
+
 	/*
 	 * First do one-time work.  If these work items are enabled, we
 	 * want to run them exactly once per syscall exit with IRQs on.

arch/x86/entry/syscalls/syscall_32.tbl

@@ -397,3 +397,4 @@
 383	i386	statx			sys_statx			__ia32_sys_statx
 384	i386	arch_prctl		sys_arch_prctl			__ia32_compat_sys_arch_prctl
 385	i386	io_pgetevents		sys_io_pgetevents		__ia32_compat_sys_io_pgetevents
+386	i386	rseq			sys_rseq			__ia32_sys_rseq

arch/x86/entry/syscalls/syscall_64.tbl

@@ -342,6 +342,7 @@
 331	common	pkey_free		__x64_sys_pkey_free
 332	common	statx			__x64_sys_statx
 333	common	io_pgetevents		__x64_sys_io_pgetevents
+334	common	rseq			__x64_sys_rseq
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact

arch/x86/kernel/signal.c

@@ -688,6 +688,12 @@ setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs)
 	sigset_t *set = sigmask_to_save();
 	compat_sigset_t *cset = (compat_sigset_t *) set;
 
+	/*
+	 * Increment event counter and perform fixup for the pre-signal
+	 * frame.
+	 */
+	rseq_signal_deliver(regs);
+
 	/* Set up the stack frame */
 	if (is_ia32_frame(ksig)) {
 		if (ksig->ka.sa.sa_flags & SA_SIGINFO)

fs/exec.c

@@ -1824,6 +1824,7 @@ static int __do_execve_file(int fd, struct filename *filename,
 	current->fs->in_exec = 0;
 	current->in_execve = 0;
 	membarrier_execve(current);
+	rseq_execve(current);
 	acct_update_integrals(current);
 	task_numa_free(current);
 	free_bprm(bprm);

include/linux/sched.h

@@ -27,6 +27,7 @@
 #include <linux/signal_types.h>
 #include <linux/mm_types_task.h>
 #include <linux/task_io_accounting.h>
+#include <linux/rseq.h>
 
 /* task_struct member predeclarations (sorted alphabetically): */
 struct audit_context;
@@ -1047,6 +1048,17 @@ struct task_struct {
 	unsigned long			numa_pages_migrated;
 #endif /* CONFIG_NUMA_BALANCING */
 
+#ifdef CONFIG_RSEQ
+	struct rseq __user *rseq;
+	u32 rseq_len;
+	u32 rseq_sig;
+	/*
+	 * RmW on rseq_event_mask must be performed atomically
+	 * with respect to preemption.
+	 */
+	unsigned long rseq_event_mask;
+#endif
+
 	struct tlbflush_unmap_batch	tlb_ubc;
 
 	struct rcu_head			rcu;
@@ -1757,4 +1769,126 @@ extern long sched_getaffinity(pid_t pid, struct cpumask *mask);
 #define TASK_SIZE_OF(tsk)	TASK_SIZE
 #endif
 
+#ifdef CONFIG_RSEQ
+
+/*
+ * Map the event mask on the user-space ABI enum rseq_cs_flags
+ * for direct mask checks.
+ */
+enum rseq_event_mask_bits {
+	RSEQ_EVENT_PREEMPT_BIT	= RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT,
+	RSEQ_EVENT_SIGNAL_BIT	= RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT,
+	RSEQ_EVENT_MIGRATE_BIT	= RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT,
+};
+
+enum rseq_event_mask {
+	RSEQ_EVENT_PREEMPT	= (1U << RSEQ_EVENT_PREEMPT_BIT),
+	RSEQ_EVENT_SIGNAL	= (1U << RSEQ_EVENT_SIGNAL_BIT),
+	RSEQ_EVENT_MIGRATE	= (1U << RSEQ_EVENT_MIGRATE_BIT),
+};
+
+static inline void rseq_set_notify_resume(struct task_struct *t)
+{
+	if (t->rseq)
+		set_tsk_thread_flag(t, TIF_NOTIFY_RESUME);
+}
+
+void __rseq_handle_notify_resume(struct pt_regs *regs);
+
+static inline void rseq_handle_notify_resume(struct pt_regs *regs)
+{
+	if (current->rseq)
+		__rseq_handle_notify_resume(regs);
+}
+
+static inline void rseq_signal_deliver(struct pt_regs *regs)
+{
+	preempt_disable();
+	__set_bit(RSEQ_EVENT_SIGNAL_BIT, &current->rseq_event_mask);
+	preempt_enable();
+	rseq_handle_notify_resume(regs);
+}
+
+/* rseq_preempt() requires preemption to be disabled. */
+static inline void rseq_preempt(struct task_struct *t)
+{
+	__set_bit(RSEQ_EVENT_PREEMPT_BIT, &t->rseq_event_mask);
+	rseq_set_notify_resume(t);
+}
+
+/* rseq_migrate() requires preemption to be disabled. */
+static inline void rseq_migrate(struct task_struct *t)
+{
+	__set_bit(RSEQ_EVENT_MIGRATE_BIT, &t->rseq_event_mask);
+	rseq_set_notify_resume(t);
+}
+
+/*
+ * If parent process has a registered restartable sequences area, the
+ * child inherits. Only applies when forking a process, not a thread. In
+ * case a parent fork() in the middle of a restartable sequence, set the
+ * resume notifier to force the child to retry.
+ */
+static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags)
+{
+	if (clone_flags & CLONE_THREAD) {
+		t->rseq = NULL;
+		t->rseq_len = 0;
+		t->rseq_sig = 0;
+		t->rseq_event_mask = 0;
+	} else {
+		t->rseq = current->rseq;
+		t->rseq_len = current->rseq_len;
+		t->rseq_sig = current->rseq_sig;
+		t->rseq_event_mask = current->rseq_event_mask;
+		rseq_preempt(t);
+	}
+}
+
+static inline void rseq_execve(struct task_struct *t)
+{
+	t->rseq = NULL;
+	t->rseq_len = 0;
+	t->rseq_sig = 0;
+	t->rseq_event_mask = 0;
+}
+
+#else
+
+static inline void rseq_set_notify_resume(struct task_struct *t)
+{
+}
+static inline void rseq_handle_notify_resume(struct pt_regs *regs)
+{
+}
+static inline void rseq_signal_deliver(struct pt_regs *regs)
+{
+}
+static inline void rseq_preempt(struct task_struct *t)
+{
+}
+static inline void rseq_migrate(struct task_struct *t)
+{
+}
+static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags)
+{
+}
+static inline void rseq_execve(struct task_struct *t)
+{
+}
+
+#endif
+
+#ifdef CONFIG_DEBUG_RSEQ
+
+void rseq_syscall(struct pt_regs *regs);
+
+#else
+
+static inline void rseq_syscall(struct pt_regs *regs)
+{
+}
+
+#endif
+
 #endif

include/linux/syscalls.h

@@ -66,6 +66,7 @@ struct old_linux_dirent;
 struct perf_event_attr;
 struct file_handle;
 struct sigaltstack;
+struct rseq;
 union bpf_attr;
 
 #include <linux/types.h>
@@ -897,7 +898,8 @@ asmlinkage long sys_pkey_alloc(unsigned long flags, unsigned long init_val);
 asmlinkage long sys_pkey_free(int pkey);
 asmlinkage long sys_statx(int dfd, const char __user *path, unsigned flags,
 			  unsigned mask, struct statx __user *buffer);
-
+asmlinkage long sys_rseq(struct rseq __user *rseq, uint32_t rseq_len,
+			 int flags, uint32_t sig);
 
 /*
  * Architecture-specific system calls

include/trace/events/rseq.h

+/* SPDX-License-Identifier: GPL-2.0+ */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM rseq
+
+#if !defined(_TRACE_RSEQ_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_RSEQ_H
+
+#include <linux/tracepoint.h>
+#include <linux/types.h>
+
+TRACE_EVENT(rseq_update,
+
+	TP_PROTO(struct task_struct *t),
+
+	TP_ARGS(t),
+
+	TP_STRUCT__entry(
+		__field(s32, cpu_id)
+	),
+
+	TP_fast_assign(
+		__entry->cpu_id = raw_smp_processor_id();
+	),
+
+	TP_printk("cpu_id=%d", __entry->cpu_id)
+);
+
+TRACE_EVENT(rseq_ip_fixup,
+
+	TP_PROTO(unsigned long regs_ip, unsigned long start_ip,
+		unsigned long post_commit_offset, unsigned long abort_ip),
+
+	TP_ARGS(regs_ip, start_ip, post_commit_offset, abort_ip),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, regs_ip)
+		__field(unsigned long, start_ip)
+		__field(unsigned long, post_commit_offset)
+		__field(unsigned long, abort_ip)
+	),
+
+	TP_fast_assign(
+		__entry->regs_ip = regs_ip;
+		__entry->start_ip = start_ip;
+		__entry->post_commit_offset = post_commit_offset;
+		__entry->abort_ip = abort_ip;
+	),
+
+	TP_printk("regs_ip=0x%lx start_ip=0x%lx post_commit_offset=%lu abort_ip=0x%lx",
+		__entry->regs_ip, __entry->start_ip,
+		__entry->post_commit_offset, __entry->abort_ip)
+);
+
+#endif /* _TRACE_SOCK_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>

include/uapi/linux/rseq.h

+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_RSEQ_H
+#define _UAPI_LINUX_RSEQ_H
+
+/*
+ * linux/rseq.h
+ *
+ * Restartable sequences system call API
+ *
+ * Copyright (c) 2015-2018 Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+#ifdef __KERNEL__
+# include <linux/types.h>
+#else
+# include <stdint.h>
+#endif
+
+#include <linux/types_32_64.h>
+
+enum rseq_cpu_id_state {
+	RSEQ_CPU_ID_UNINITIALIZED		= -1,
+	RSEQ_CPU_ID_REGISTRATION_FAILED		= -2,
+};
+
+enum rseq_flags {
+	RSEQ_FLAG_UNREGISTER = (1 << 0),
+};
+
+enum rseq_cs_flags_bit {
+	RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT	= 0,
+	RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT	= 1,
+	RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT	= 2,
+};
+
+enum rseq_cs_flags {
+	RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT	=
+		(1U << RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT),
+	RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL	=
+		(1U << RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT),
+	RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE	=
+		(1U << RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT),
+};
+
+/*
+ * struct rseq_cs is aligned on 4 * 8 bytes to ensure it is always
+ * contained within a single cache-line. It is usually declared as
+ * link-time constant data.
+ */
+struct rseq_cs {
+	/* Version of this structure. */
+	__u32 version;
+	/* enum rseq_cs_flags */
+	__u32 flags;
+	LINUX_FIELD_u32_u64(start_ip);
+	/* Offset from start_ip. */
+	LINUX_FIELD_u32_u64(post_commit_offset);
+	LINUX_FIELD_u32_u64(abort_ip);
+} __attribute__((aligned(4 * sizeof(__u64))));
+
+/*
+ * struct rseq is aligned on 4 * 8 bytes to ensure it is always
+ * contained within a single cache-line.
+ *
+ * A single struct rseq per thread is allowed.
+ */
+struct rseq {
+	/*
+	 * Restartable sequences cpu_id_start field. Updated by the
+	 * kernel, and read by user-space with single-copy atomicity
+	 * semantics. Aligned on 32-bit. Always contains a value in the
+	 * range of possible CPUs, although the value may not be the
+	 * actual current CPU (e.g. if rseq is not initialized). This
+	 * CPU number value should always be compared against the value
+	 * of the cpu_id field before performing a rseq commit or
+	 * returning a value read from a data structure indexed using
+	 * the cpu_id_start value.
+	 */
+	__u32 cpu_id_start;
+	/*
+	 * Restartable sequences cpu_id field. Updated by the kernel,
+	 * and read by user-space with single-copy atomicity semantics.
+	 * Aligned on 32-bit. Values RSEQ_CPU_ID_UNINITIALIZED and
+	 * RSEQ_CPU_ID_REGISTRATION_FAILED have a special semantic: the
+	 * former means "rseq uninitialized", and latter means "rseq
+	 * initialization failed". This value is meant to be read within
+	 * rseq critical sections and compared with the cpu_id_start
+	 * value previously read, before performing the commit instruction,
+	 * or read and compared with the cpu_id_start value before returning
+	 * a value loaded from a data structure indexed using the
+	 * cpu_id_start value.
+	 */
+	__u32 cpu_id;
+	/*
+	 * Restartable sequences rseq_cs field.
+	 *
+	 * Contains NULL when no critical section is active for the current
+	 * thread, or holds a pointer to the currently active struct rseq_cs.
+	 *
+	 * Updated by user-space, which sets the address of the currently
+	 * active rseq_cs at the beginning of assembly instruction sequence
+	 * block, and set to NULL by the kernel when it restarts an assembly
+	 * instruction sequence block, as well as when the kernel detects that
+	 * it is preempting or delivering a signal outside of the range
+	 * targeted by the rseq_cs. Also needs to be set to NULL by user-space
+	 * before reclaiming memory that contains the targeted struct rseq_cs.
+	 *
+	 * Read and set by the kernel with single-copy atomicity semantics.
+	 * Set by user-space with single-copy atomicity semantics. Aligned
+	 * on 64-bit.
+	 */
+	LINUX_FIELD_u32_u64(rseq_cs);
+	/*
+	 * - RSEQ_DISABLE flag:
+	 *
+	 * Fallback fast-track flag for single-stepping.
+	 * Set by user-space if lack of progress is detected.
+	 * Cleared by user-space after rseq finish.
+	 * Read by the kernel.
+	 * - RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT
+	 *     Inhibit instruction sequence block restart and event
+	 *     counter increment on preemption for this thread.
+	 * - RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL
+	 *     Inhibit instruction sequence block restart and event
+	 *     counter increment on signal delivery for this thread.
+	 * - RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE
+	 *     Inhibit instruction sequence block restart and event
+	 *     counter increment on migration for this thread.
+	 */
+	__u32 flags;
+} __attribute__((aligned(4 * sizeof(__u64))));
+
+#endif /* _UAPI_LINUX_RSEQ_H */

include/uapi/linux/types_32_64.h

+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_TYPES_32_64_H
+#define _UAPI_LINUX_TYPES_32_64_H
+
+/*
+ * linux/types_32_64.h
+ *
+ * Integer type declaration for pointers across 32-bit and 64-bit systems.
+ *
+ * Copyright (c) 2015-2018 Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+#ifdef __KERNEL__
+# include <linux/types.h>
+#else
+# include <stdint.h>
+#endif
+
+#include <asm/byteorder.h>
+
+#ifdef __BYTE_ORDER
+# if (__BYTE_ORDER == __BIG_ENDIAN)
+#  define LINUX_BYTE_ORDER_BIG_ENDIAN
+# else
+#  define LINUX_BYTE_ORDER_LITTLE_ENDIAN
+# endif
+#else
+# ifdef __BIG_ENDIAN
+#  define LINUX_BYTE_ORDER_BIG_ENDIAN
+# else
+#  define LINUX_BYTE_ORDER_LITTLE_ENDIAN
+# endif
+#endif
+
+#ifdef __LP64__
+# define LINUX_FIELD_u32_u64(field)			__u64 field
+# define LINUX_FIELD_u32_u64_INIT_ONSTACK(field, v)	field = (intptr_t)v
+#else
+# ifdef LINUX_BYTE_ORDER_BIG_ENDIAN
+#  define LINUX_FIELD_u32_u64(field)	__u32 field ## _padding, field
+#  define LINUX_FIELD_u32_u64_INIT_ONSTACK(field, v)	\
+	field ## _padding = 0, field = (intptr_t)v
+# else
+#  define LINUX_FIELD_u32_u64(field)	__u32 field, field ## _padding
+#  define LINUX_FIELD_u32_u64_INIT_ONSTACK(field, v)	\
+	field = (intptr_t)v, field ## _padding = 0
+# endif
+#endif
+
+#endif /* _UAPI_LINUX_TYPES_32_64_H */

init/Kconfig

@@ -1428,6 +1428,29 @@ config ARCH_HAS_MEMBARRIER_CALLBACKS
 config ARCH_HAS_MEMBARRIER_SYNC_CORE
 	bool
 
+config RSEQ
+	bool "Enable rseq() system call" if EXPERT
+	default y
+	depends on HAVE_RSEQ
+	select MEMBARRIER
+	help
+	  Enable the restartable sequences system call. It provides a
+	  user-space cache for the current CPU number value, which
+	  speeds up getting the current CPU number from user-space,
+	  as well as an ABI to speed up user-space operations on
+	  per-CPU data.
+
+	  If unsure, say Y.
+
+config DEBUG_RSEQ
+	default n
+	bool "Enabled debugging of rseq() system call" if EXPERT
+	depends on RSEQ && DEBUG_KERNEL
+	help
+	  Enable extra debugging checks for the rseq system call.
+
+	  If unsure, say N.
+
 config EMBEDDED
 	bool "Embedded system"
 	option allnoconfig_y

kernel/Makefile

@@ -114,6 +114,7 @@ obj-$(CONFIG_TORTURE_TEST) += torture.o
 
 obj-$(CONFIG_HAS_IOMEM) += iomem.o
 obj-$(CONFIG_ZONE_DEVICE) += memremap.o
+obj-$(CONFIG_RSEQ) += rseq.o
 
 $(obj)/configs.o: $(obj)/config_data.h
 

kernel/fork.c

@@ -1900,6 +1900,8 @@ static __latent_entropy struct task_struct *copy_process(
 	 */
 	copy_seccomp(p);
 
+	rseq_fork(p, clone_flags);
+
 	/*
 	 * Process group and session signals need to be delivered to just the
 	 * parent before the fork or both the parent and the child after the

kernel/rseq.c

+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Restartable sequences system call
+ *
+ * Copyright (C) 2015, Google, Inc.,
+ * Paul Turner <pjt@google.com> and Andrew Hunter <ahh@google.com>
+ * Copyright (C) 2015-2018, EfficiOS Inc.,
+ * Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+#include <linux/sched.h>
+#include <linux/uaccess.h>
+#include <linux/syscalls.h>
+#include <linux/rseq.h>
+#include <linux/types.h>
+#include <asm/ptrace.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/rseq.h>
+
+#define RSEQ_CS_PREEMPT_MIGRATE_FLAGS (RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE | \
+				       RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT)
+
+/*
+ *
+ * Restartable sequences are a lightweight interface that allows
+ * user-level code to be executed atomically relative to scheduler
+ * preemption and signal delivery. Typically used for implementing
+ * per-cpu operations.
+ *
+ * It allows user-space to perform update operations on per-cpu data
+ * without requiring heavy-weight atomic operations.
+ *
+ * Detailed algorithm of rseq user-space assembly sequences:
+ *
+ *                     init(rseq_cs)
+ *                     cpu = TLS->rseq::cpu_id_start
+ *   [1]               TLS->rseq::rseq_cs = rseq_cs
+ *   [start_ip]        ----------------------------
+ *   [2]               if (cpu != TLS->rseq::cpu_id)
+ *                             goto abort_ip;
+ *   [3]               <last_instruction_in_cs>
+ *   [post_commit_ip]  ----------------------------
+ *
+ *   The address of jump target abort_ip must be outside the critical
+ *   region, i.e.:
+ *
+ *     [abort_ip] < [start_ip]  || [abort_ip] >= [post_commit_ip]
+ *
+ *   Steps [2]-[3] (inclusive) need to be a sequence of instructions in
+ *   userspace that can handle being interrupted between any of those
+ *   instructions, and then resumed to the abort_ip.
+ *
+ *   1.  Userspace stores the address of the struct rseq_cs assembly
+ *       block descriptor into the rseq_cs field of the registered
+ *       struct rseq TLS area. This update is performed through a single
+ *       store within the inline assembly instruction sequence.
+ *       [start_ip]
+ *
+ *   2.  Userspace tests to check whether the current cpu_id field match
+ *       the cpu number loaded before start_ip, branching to abort_ip
+ *       in case of a mismatch.
+ *
+ *       If the sequence is preempted or interrupted by a signal
+ *       at or after start_ip and before post_commit_ip, then the kernel
+ *       clears TLS->__rseq_abi::rseq_cs, and sets the user-space return
+ *       ip to abort_ip before returning to user-space, so the preempted
+ *       execution resumes at abort_ip.
+ *
+ *   3.  Userspace critical section final instruction before
+ *       post_commit_ip is the commit. The critical section is
+ *       self-terminating.
+ *       [post_commit_ip]
+ *
+ *   4.  <success>
+ *
+ *   On failure at [2], or if interrupted by preempt or signal delivery
+ *   between [1] and [3]:
+ *
+ *       [abort_ip]
+ *   F1. <failure>
+ */
+
+static int rseq_update_cpu_id(struct task_struct *t)
+{
+	u32 cpu_id = raw_smp_processor_id();
+
+	if (__put_user(cpu_id, &t->rseq->cpu_id_start))
+		return -EFAULT;
+	if (__put_user(cpu_id, &t->rseq->cpu_id))
+		return -EFAULT;
+	trace_rseq_update(t);
+	return 0;
+}
+
+static int rseq_reset_rseq_cpu_id(struct task_struct *t)
+{
+	u32 cpu_id_start = 0, cpu_id = RSEQ_CPU_ID_UNINITIALIZED;
+
+	/*
+	 * Reset cpu_id_start to its initial state (0).
+	 */
+	if (__put_user(cpu_id_start, &t->rseq->cpu_id_start))
+		return -EFAULT;
+	/*
+	 * Reset cpu_id to RSEQ_CPU_ID_UNINITIALIZED, so any user coming
+	 * in after unregistration can figure out that rseq needs to be
+	 * registered again.
+	 */
+	if (__put_user(cpu_id, &t->rseq->cpu_id))
+		return -EFAULT;
+	return 0;
+}
+
+static int rseq_get_rseq_cs(struct task_struct *t, struct rseq_cs *rseq_cs)
+{
+	struct rseq_cs __user *urseq_cs;
+	unsigned long ptr;
+	u32 __user *usig;
+	u32 sig;
+	int ret;
+
+	ret = __get_user(ptr, &t->rseq->rseq_cs);
+	if (ret)
+		return ret;
+	if (!ptr) {
+		memset(rseq_cs, 0, sizeof(*rseq_cs));
+		return 0;
+	}
+	urseq_cs = (struct rseq_cs __user *)ptr;
+	if (copy_from_user(rseq_cs, urseq_cs, sizeof(*rseq_cs)))
+		return -EFAULT;
+	if (rseq_cs->version > 0)
+		return -EINVAL;
+
+	/* Ensure that abort_ip is not in the critical section. */
+	if (rseq_cs->abort_ip - rseq_cs->start_ip < rseq_cs->post_commit_offset)
+		return -EINVAL;
+
+	usig = (u32 __user *)(rseq_cs->abort_ip - sizeof(u32));
+	ret = get_user(sig, usig);
+	if (ret)
+		return ret;
+
+	if (current->rseq_sig != sig) {
+		printk_ratelimited(KERN_WARNING
+			"Possible attack attempt. Unexpected rseq signature 0x%x, expecting 0x%x (pid=%d, addr=%p).\n",
+			sig, current->rseq_sig, current->pid, usig);
+		return -EPERM;
+	}
+	return 0;
+}
+
+static int rseq_need_restart(struct task_struct *t, u32 cs_flags)
+{
+	u32 flags, event_mask;
+	int ret;
+
+	/* Get thread flags. */
+	ret = __get_user(flags, &t->rseq->flags);
+	if (ret)
+		return ret;
+
+	/* Take critical section flags into account. */
+	flags |= cs_flags;
+
+	/*
+	 * Restart on signal can only be inhibited when restart on
+	 * preempt and restart on migrate are inhibited too. Otherwise,
+	 * a preempted signal handler could fail to restart the prior
+	 * execution context on sigreturn.
+	 */
+	if (unlikely((flags & RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL) &&
+		     (flags & RSEQ_CS_PREEMPT_MIGRATE_FLAGS) !=
+		     RSEQ_CS_PREEMPT_MIGRATE_FLAGS))
+		return -EINVAL;
+
+	/*
+	 * Load and clear event mask atomically with respect to
+	 * scheduler preemption.
+	 */
+	preempt_disable();
+	event_mask = t->rseq_event_mask;
+	t->rseq_event_mask = 0;
+	preempt_enable();
+
+	return !!(event_mask & ~flags);
+}
+
+static int clear_rseq_cs(struct task_struct *t)
+{
+	/*
+	 * The rseq_cs field is set to NULL on preemption or signal
+	 * delivery on top of rseq assembly block, as well as on top
+	 * of code outside of the rseq assembly block. This performs
+	 * a lazy clear of the rseq_cs field.
+	 *
+	 * Set rseq_cs to NULL with single-copy atomicity.
+	 */
+	return __put_user(0UL, &t->rseq->rseq_cs);
+}
+
+/*
+ * Unsigned comparison will be true when ip >= start_ip, and when
+ * ip < start_ip + post_commit_offset.
+ */
+static bool in_rseq_cs(unsigned long ip, struct rseq_cs *rseq_cs)
+{
+	return ip - rseq_cs->start_ip < rseq_cs->post_commit_offset;
+}
+
+static int rseq_ip_fixup(struct pt_regs *regs)
+{
+	unsigned long ip = instruction_pointer(regs);
+	struct task_struct *t = current;
+	struct rseq_cs rseq_cs;
+	int ret;
+
+	ret = rseq_get_rseq_cs(t, &rseq_cs);
+	if (ret)
+		return ret;
+
+	/*
+	 * Handle potentially not being within a critical section.
+	 * If not nested over a rseq critical section, restart is useless.
+	 * Clear the rseq_cs pointer and return.
+	 */
+	if (!in_rseq_cs(ip, &rseq_cs))
+		return clear_rseq_cs(t);
+	ret = rseq_need_restart(t, rseq_cs.flags);
+	if (ret <= 0)
+		return ret;
+	ret = clear_rseq_cs(t);
+	if (ret)
+		return ret;
+	trace_rseq_ip_fixup(ip, rseq_cs.start_ip, rseq_cs.post_commit_offset,
+			    rseq_cs.abort_ip);
+	instruction_pointer_set(regs, (unsigned long)rseq_cs.abort_ip);
+	return 0;
+}
+
+/*
+ * This resume handler must always be executed between any of:
+ * - preemption,
+ * - signal delivery,
+ * and return to user-space.
+ *
+ * This is how we can ensure that the entire rseq critical section,
+ * consisting of both the C part and the assembly instruction sequence,
+ * will issue the commit instruction only if executed atomically with
+ * respect to other threads scheduled on the same CPU, and with respect
+ * to signal handlers.
+ */
+void __rseq_handle_notify_resume(struct pt_regs *regs)
+{
+	struct task_struct *t = current;
+	int ret;
+
+	if (unlikely(t->flags & PF_EXITING))
+		return;
+	if (unlikely(!access_ok(VERIFY_WRITE, t->rseq, sizeof(*t->rseq))))
+		goto error;
+	ret = rseq_ip_fixup(regs);
+	if (unlikely(ret < 0))
+		goto error;
+	if (unlikely(rseq_update_cpu_id(t)))
+		goto error;
+	return;
+
+error:
+	force_sig(SIGSEGV, t);
+}
+
+#ifdef CONFIG_DEBUG_RSEQ
+
+/*
+ * Terminate the process if a syscall is issued within a restartable
+ * sequence.
+ */
+void rseq_syscall(struct pt_regs *regs)
+{
+	unsigned long ip = instruction_pointer(regs);
+	struct task_struct *t = current;
+	struct rseq_cs rseq_cs;
+
+	if (!t->rseq)
+		return;
+	if (!access_ok(VERIFY_READ, t->rseq, sizeof(*t->rseq)) ||
+	    rseq_get_rseq_cs(t, &rseq_cs) || in_rseq_cs(ip, &rseq_cs))
+		force_sig(SIGSEGV, t);
+}
+
+#endif
+
+/*
+ * sys_rseq - setup restartable sequences for caller thread.
+ */
+SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len,
+		int, flags, u32, sig)
+{
+	int ret;
+
+	if (flags & RSEQ_FLAG_UNREGISTER) {
+		/* Unregister rseq for current thread. */
+		if (current->rseq != rseq || !current->rseq)
+			return -EINVAL;
+		if (current->rseq_len != rseq_len)
+			return -EINVAL;
+		if (current->rseq_sig != sig)
+			return -EPERM;
+		ret = rseq_reset_rseq_cpu_id(current);
+		if (ret)
+			return ret;
+		current->rseq = NULL;
+		current->rseq_len = 0;
+		current->rseq_sig = 0;
+		return 0;
+	}
+
+	if (unlikely(flags))
+		return -EINVAL;
+
+	if (current->rseq) {
+		/*
+		 * If rseq is already registered, check whether
+		 * the provided address differs from the prior
+		 * one.
+		 */
+		if (current->rseq != rseq || current->rseq_len != rseq_len)
+			return -EINVAL;
+		if (current->rseq_sig != sig)
+			return -EPERM;
+		/* Already registered. */
+		return -EBUSY;
+	}
+
+	/*
+	 * If there was no rseq previously registered,
+	 * ensure the provided rseq is properly aligned and valid.
+	 */
+	if (!IS_ALIGNED((unsigned long)rseq, __alignof__(*rseq)) ||
+	    rseq_len != sizeof(*rseq))
+		return -EINVAL;
+	if (!access_ok(VERIFY_WRITE, rseq, rseq_len))
+		return -EFAULT;
+	current->rseq = rseq;
+	current->rseq_len = rseq_len;
+	current->rseq_sig = sig;
+	/*
+	 * If rseq was previously inactive, and has just been
+	 * registered, ensure the cpu_id_start and cpu_id fields
+	 * are updated before returning to user-space.
+	 */
+	rseq_set_notify_resume(current);
+
+	return 0;
+}

kernel/sched/core.c

@@ -1191,6 +1191,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 		if (p->sched_class->migrate_task_rq)
 			p->sched_class->migrate_task_rq(p);
 		p->se.nr_migrations++;
+		rseq_migrate(p);
 		perf_event_task_migrate(p);
 	}
 
@@ -2634,6 +2635,7 @@ prepare_task_switch(struct rq *rq, struct task_struct *prev,
 {
 	sched_info_switch(rq, prev, next);
 	perf_event_task_sched_out(prev, next);
+	rseq_preempt(prev);
 	fire_sched_out_preempt_notifiers(prev, next);
 	prepare_task(next);
 	prepare_arch_switch(next);

kernel/sys_ni.c

@@ -432,3 +432,6 @@ COND_SYSCALL(setresgid16);
 COND_SYSCALL(setresuid16);
 COND_SYSCALL(setreuid16);
 COND_SYSCALL(setuid16);
+
+/* restartable sequence */
+COND_SYSCALL(rseq);

tools/testing/selftests/Makefile

@@ -29,6 +29,7 @@ TARGETS += powerpc
 TARGETS += proc
 TARGETS += pstore
 TARGETS += ptrace
+TARGETS += rseq
 TARGETS += rtc
 TARGETS += seccomp
 TARGETS += sigaltstack

tools/testing/selftests/lib.mk

@@ -133,6 +133,9 @@ COMPILE.S = $(CC) $(ASFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c
 LINK.S = $(CC) $(ASFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH)
 endif
 
+# Selftest makefiles can override those targets by setting
+# OVERRIDE_TARGETS = 1.
+ifeq ($(OVERRIDE_TARGETS),)
 $(OUTPUT)/%:%.c
 	$(LINK.c) $^ $(LDLIBS) -o $@
 
@@ -141,5 +144,6 @@ $(OUTPUT)/%.o:%.S
 
 $(OUTPUT)/%:%.S
 	$(LINK.S) $^ $(LDLIBS) -o $@
+endif
 
 .PHONY: run_tests all clean install emit_tests

tools/testing/selftests/rseq/.gitignore

+basic_percpu_ops_test
+basic_test
+basic_rseq_op_test
+param_test
+param_test_benchmark
+param_test_compare_twice

tools/testing/selftests/rseq/Makefile

+# SPDX-License-Identifier: GPL-2.0+ OR MIT
+CFLAGS += -O2 -Wall -g -I./ -I../../../../usr/include/ -L./ -Wl,-rpath=./
+LDLIBS += -lpthread
+
+# Own dependencies because we only want to build against 1st prerequisite, but
+# still track changes to header files and depend on shared object.
+OVERRIDE_TARGETS = 1
+
+TEST_GEN_PROGS = basic_test basic_percpu_ops_test param_test \
+		param_test_benchmark param_test_compare_twice
+
+TEST_GEN_PROGS_EXTENDED = librseq.so
+
+TEST_PROGS = run_param_test.sh
+
+include ../lib.mk
+
+$(OUTPUT)/librseq.so: rseq.c rseq.h rseq-*.h
+	$(CC) $(CFLAGS) -shared -fPIC $< $(LDLIBS) -o $@
+
+$(OUTPUT)/%: %.c $(TEST_GEN_PROGS_EXTENDED) rseq.h rseq-*.h
+	$(CC) $(CFLAGS) $< $(LDLIBS) -lrseq -o $@
+
+$(OUTPUT)/param_test_benchmark: param_test.c $(TEST_GEN_PROGS_EXTENDED) \
+					rseq.h rseq-*.h
+	$(CC) $(CFLAGS) -DBENCHMARK $< $(LDLIBS) -lrseq -o $@
+
+$(OUTPUT)/param_test_compare_twice: param_test.c $(TEST_GEN_PROGS_EXTENDED) \
+					rseq.h rseq-*.h
+	$(CC) $(CFLAGS) -DRSEQ_COMPARE_TWICE $< $(LDLIBS) -lrseq -o $@

tools/testing/selftests/rseq/basic_percpu_ops_test.c

+// SPDX-License-Identifier: LGPL-2.1
+#define _GNU_SOURCE
+#include <assert.h>
+#include <pthread.h>
+#include <sched.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stddef.h>
+
+#include "rseq.h"
+
+#define ARRAY_SIZE(arr)	(sizeof(arr) / sizeof((arr)[0]))
+
+struct percpu_lock_entry {
+	intptr_t v;
+} __attribute__((aligned(128)));
+
+struct percpu_lock {
+	struct percpu_lock_entry c[CPU_SETSIZE];
+};
+
+struct test_data_entry {
+	intptr_t count;
+} __attribute__((aligned(128)));
+
+struct spinlock_test_data {
+	struct percpu_lock lock;
+	struct test_data_entry c[CPU_SETSIZE];
+	int reps;
+};
+
+struct percpu_list_node {
+	intptr_t data;
+	struct percpu_list_node *next;
+};
+
+struct percpu_list_entry {
+	struct percpu_list_node *head;
+} __attribute__((aligned(128)));
+
+struct percpu_list {
+	struct percpu_list_entry c[CPU_SETSIZE];
+};
+
+/* A simple percpu spinlock.  Returns the cpu lock was acquired on. */
+int rseq_this_cpu_lock(struct percpu_lock *lock)
+{
+	int cpu;
+
+	for (;;) {
+		int ret;
+
+		cpu = rseq_cpu_start();
+		ret = rseq_cmpeqv_storev(&lock->c[cpu].v,
+					 0, 1, cpu);
+		if (rseq_likely(!ret))
+			break;
+		/* Retry if comparison fails or rseq aborts. */
+	}
+	/*
+	 * Acquire semantic when taking lock after control dependency.
+	 * Matches rseq_smp_store_release().
+	 */
+	rseq_smp_acquire__after_ctrl_dep();
+	return cpu;
+}
+
+void rseq_percpu_unlock(struct percpu_lock *lock, int cpu)
+{
+	assert(lock->c[cpu].v == 1);
+	/*
+	 * Release lock, with release semantic. Matches
+	 * rseq_smp_acquire__after_ctrl_dep().
+	 */
+	rseq_smp_store_release(&lock->c[cpu].v, 0);
+}
+
+void *test_percpu_spinlock_thread(void *arg)
+{
+	struct spinlock_test_data *data = arg;
+	int i, cpu;
+
+	if (rseq_register_current_thread()) {
+		fprintf(stderr, "Error: rseq_register_current_thread(...) failed(%d): %s\n",
+			errno, strerror(errno));
+		abort();
+	}
+	for (i = 0; i < data->reps; i++) {
+		cpu = rseq_this_cpu_lock(&data->lock);
+		data->c[cpu].count++;
+		rseq_percpu_unlock(&data->lock, cpu);
+	}
+	if (rseq_unregister_current_thread()) {
+		fprintf(stderr, "Error: rseq_unregister_current_thread(...) failed(%d): %s\n",
+			errno, strerror(errno));
+		abort();
+	}
+
+	return NULL;
+}
+
+/*
+ * A simple test which implements a sharded counter using a per-cpu
+ * lock.  Obviously real applications might prefer to simply use a
+ * per-cpu increment; however, this is reasonable for a test and the
+ * lock can be extended to synchronize more complicated operations.
+ */
+void test_percpu_spinlock(void)
+{
+	const int num_threads = 200;
+	int i;
+	uint64_t sum;
+	pthread_t test_threads[num_threads];
+	struct spinlock_test_data data;
+
+	memset(&data, 0, sizeof(data));
+	data.reps = 5000;
+
+	for (i = 0; i < num_threads; i++)
+		pthread_create(&test_threads[i], NULL,
+			       test_percpu_spinlock_thread, &data);
+
+	for (i = 0; i < num_threads; i++)
+		pthread_join(test_threads[i], NULL);
+
+	sum = 0;
+	for (i = 0; i < CPU_SETSIZE; i++)
+		sum += data.c[i].count;
+
+	assert(sum == (uint64_t)data.reps * num_threads);
+}
+
+void this_cpu_list_push(struct percpu_list *list,
+			struct percpu_list_node *node,
+			int *_cpu)
+{
+	int cpu;
+
+	for (;;) {
+		intptr_t *targetptr, newval, expect;
+		int ret;
+
+		cpu = rseq_cpu_start();
+		/* Load list->c[cpu].head with single-copy atomicity. */
+		expect = (intptr_t)RSEQ_READ_ONCE(list->c[cpu].head);
+		newval = (intptr_t)node;
+		targetptr = (intptr_t *)&list->c[cpu].head;
+		node->next = (struct percpu_list_node *)expect;
+		ret = rseq_cmpeqv_storev(targetptr, expect, newval, cpu);
+		if (rseq_likely(!ret))
+			break;
+		/* Retry if comparison fails or rseq aborts. */
+	}
+	if (_cpu)
+		*_cpu = cpu;
+}
+
+/*
+ * Unlike a traditional lock-less linked list; the availability of a
+ * rseq primitive allows us to implement pop without concerns over
+ * ABA-type races.
+ */
+struct percpu_list_node *this_cpu_list_pop(struct percpu_list *list,
+					   int *_cpu)
+{
+	for (;;) {
+		struct percpu_list_node *head;
+		intptr_t *targetptr, expectnot, *load;
+		off_t offset;
+		int ret, cpu;
+
+		cpu = rseq_cpu_start();
+		targetptr = (intptr_t *)&list->c[cpu].head;
+		expectnot = (intptr_t)NULL;
+		offset = offsetof(struct percpu_list_node, next);
+		load = (intptr_t *)&head;
+		ret = rseq_cmpnev_storeoffp_load(targetptr, expectnot,
+						 offset, load, cpu);
+		if (rseq_likely(!ret)) {
+			if (_cpu)
+				*_cpu = cpu;
+			return head;
+		}
+		if (ret > 0)
+			return NULL;
+		/* Retry if rseq aborts. */
+	}
+}
+
+/*
+ * __percpu_list_pop is not safe against concurrent accesses. Should
+ * only be used on lists that are not concurrently modified.
+ */
+struct percpu_list_node *__percpu_list_pop(struct percpu_list *list, int cpu)
+{
+	struct percpu_list_node *node;
+
+	node = list->c[cpu].head;
+	if (!node)
+		return NULL;
+	list->c[cpu].head = node->next;
+	return node;
+}
+
+void *test_percpu_list_thread(void *arg)
+{
+	int i;
+	struct percpu_list *list = (struct percpu_list *)arg;
+
+	if (rseq_register_current_thread()) {
+		fprintf(stderr, "Error: rseq_register_current_thread(...) failed(%d): %s\n",
+			errno, strerror(errno));
+		abort();
+	}
+
+	for (i = 0; i < 100000; i++) {
+		struct percpu_list_node *node;
+
+		node = this_cpu_list_pop(list, NULL);
+		sched_yield();  /* encourage shuffling */
+		if (node)
+			this_cpu_list_push(list, node, NULL);
+	}
+
+	if (rseq_unregister_current_thread()) {
+		fprintf(stderr, "Error: rseq_unregister_current_thread(...) failed(%d): %s\n",
+			errno, strerror(errno));
+		abort();
+	}
+
+	return NULL;
+}
+
+/* Simultaneous modification to a per-cpu linked list from many threads.  */
+void test_percpu_list(void)
+{
+	int i, j;
+	uint64_t sum = 0, expected_sum = 0;
+	struct percpu_list list;
+	pthread_t test_threads[200];
+	cpu_set_t allowed_cpus;
+
+	memset(&list, 0, sizeof(list));
+
+	/* Generate list entries for every usable cpu. */
+	sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus);
+	for (i = 0; i < CPU_SETSIZE; i++) {
+		if (!CPU_ISSET(i, &allowed_cpus))
+			continue;
+		for (j = 1; j <= 100; j++) {
+			struct percpu_list_node *node;
+
+			expected_sum += j;
+
+			node = malloc(sizeof(*node));
+			assert(node);
+			node->data = j;
+			node->next = list.c[i].head;
+			list.c[i].head = node;
+		}
+	}
+
+	for (i = 0; i < 200; i++)
+		pthread_create(&test_threads[i], NULL,
+		       test_percpu_list_thread, &list);
+
+	for (i = 0; i < 200; i++)
+		pthread_join(test_threads[i], NULL);
+
+	for (i = 0; i < CPU_SETSIZE; i++) {
+		struct percpu_list_node *node;
+
+		if (!CPU_ISSET(i, &allowed_cpus))
+			continue;
+
+		while ((node = __percpu_list_pop(&list, i))) {
+			sum += node->data;
+			free(node);
+		}
+	}
+
+	/*
+	 * All entries should now be accounted for (unless some external
+	 * actor is interfering with our allowed affinity while this
+	 * test is running).
+	 */
+	assert(sum == expected_sum);
+}
+
+int main(int argc, char **argv)
+{
+	if (rseq_register_current_thread()) {
+		fprintf(stderr, "Error: rseq_register_current_thread(...) failed(%d): %s\n",
+			errno, strerror(errno));
+		goto error;
+	}
+	printf("spinlock\n");
+	test_percpu_spinlock();
+	printf("percpu_list\n");
+	test_percpu_list();
+	if (rseq_unregister_current_thread()) {
+		fprintf(stderr, "Error: rseq_unregister_current_thread(...) failed(%d): %s\n",
+			errno, strerror(errno));
+		goto error;
+	}
+	return 0;
+
+error:
+	return -1;
+}

tools/testing/selftests/rseq/basic_test.c

+// SPDX-License-Identifier: LGPL-2.1
+/*
+ * Basic test coverage for critical regions and rseq_current_cpu().
+ */
+
+#define _GNU_SOURCE
+#include <assert.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/time.h>
+
+#include "rseq.h"
+
+void test_cpu_pointer(void)
+{
+	cpu_set_t affinity, test_affinity;
+	int i;
+
+	sched_getaffinity(0, sizeof(affinity), &affinity);
+	CPU_ZERO(&test_affinity);
+	for (i = 0; i < CPU_SETSIZE; i++) {
+		if (CPU_ISSET(i, &affinity)) {
+			CPU_SET(i, &test_affinity);
+			sched_setaffinity(0, sizeof(test_affinity),
+					&test_affinity);
+			assert(sched_getcpu() == i);
+			assert(rseq_current_cpu() == i);
+			assert(rseq_current_cpu_raw() == i);
+			assert(rseq_cpu_start() == i);
+			CPU_CLR(i, &test_affinity);
+		}
+	}
+	sched_setaffinity(0, sizeof(affinity), &affinity);
+}
+
+int main(int argc, char **argv)
+{
+	if (rseq_register_current_thread()) {
+		fprintf(stderr, "Error: rseq_register_current_thread(...) failed(%d): %s\n",
+			errno, strerror(errno));
+		goto init_thread_error;
+	}
+	printf("testing current cpu\n");
+	test_cpu_pointer();
+	if (rseq_unregister_current_thread()) {
+		fprintf(stderr, "Error: rseq_unregister_current_thread(...) failed(%d): %s\n",
+			errno, strerror(errno));
+		goto init_thread_error;
+	}
+	return 0;
+
+init_thread_error:
+	return -1;
+}

tools/testing/selftests/rseq/rseq-skip.h

+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * rseq-skip.h
+ *
+ * (C) Copyright 2017-2018 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
+{
+	return -1;
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
+			       off_t voffp, intptr_t *load, int cpu)
+{
+	return -1;
+}
+
+static inline __attribute__((always_inline))
+int rseq_addv(intptr_t *v, intptr_t count, int cpu)
+{
+	return -1;
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
+				 intptr_t *v2, intptr_t newv2,
+				 intptr_t newv, int cpu)
+{
+	return -1;
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
+					 intptr_t *v2, intptr_t newv2,
+					 intptr_t newv, int cpu)
+{
+	return -1;
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
+			      intptr_t *v2, intptr_t expect2,
+			      intptr_t newv, int cpu)
+{
+	return -1;
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
+				 void *dst, void *src, size_t len,
+				 intptr_t newv, int cpu)
+{
+	return -1;
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
+					 void *dst, void *src, size_t len,
+					 intptr_t newv, int cpu)
+{
+	return -1;
+}

tools/testing/selftests/rseq/rseq.c

+// SPDX-License-Identifier: LGPL-2.1
+/*
+ * rseq.c
+ *
+ * Copyright (C) 2016 Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ *
+ * This library is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation; only
+ * version 2.1 of the License.
+ *
+ * This library is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * Lesser General Public License for more details.
+ */
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <syscall.h>
+#include <assert.h>
+#include <signal.h>
+
+#include "rseq.h"
+
+#define ARRAY_SIZE(arr)	(sizeof(arr) / sizeof((arr)[0]))
+
+__attribute__((tls_model("initial-exec"))) __thread
+volatile struct rseq __rseq_abi = {
+	.cpu_id = RSEQ_CPU_ID_UNINITIALIZED,
+};
+
+static __attribute__((tls_model("initial-exec"))) __thread
+volatile int 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,
+		    int flags, uint32_t sig)
+{
+	return syscall(__NR_rseq, rseq_abi, rseq_len, flags, sig);
+}
+
+int rseq_register_current_thread(void)
+{
+	int rc, ret = 0;
+	sigset_t oldset;
+
+	signal_off_save(&oldset);
+	if (refcount++)
+		goto end;
+	rc = sys_rseq(&__rseq_abi, sizeof(struct rseq), 0, RSEQ_SIG);
+	if (!rc) {
+		assert(rseq_current_cpu_raw() >= 0);
+		goto end;
+	}
+	if (errno != EBUSY)
+		__rseq_abi.cpu_id = -2;
+	ret = -1;
+	refcount--;
+end:
+	signal_restore(oldset);
+	return ret;
+}
+
+int rseq_unregister_current_thread(void)
+{
+	int rc, ret = 0;
+	sigset_t oldset;
+
+	signal_off_save(&oldset);
+	if (--refcount)
+		goto end;
+	rc = sys_rseq(&__rseq_abi, sizeof(struct rseq),
+		      RSEQ_FLAG_UNREGISTER, RSEQ_SIG);
+	if (!rc)
+		goto end;
+	ret = -1;
+end:
+	signal_restore(oldset);
+	return ret;
+}
+
+int32_t rseq_fallback_current_cpu(void)
+{
+	int32_t cpu;
+
+	cpu = sched_getcpu();
+	if (cpu < 0) {
+		perror("sched_getcpu()");
+		abort();
+	}
+	return cpu;
+}

tools/testing/selftests/rseq/rseq.h

+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * rseq.h
+ *
+ * (C) Copyright 2016-2018 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+#ifndef RSEQ_H
+#define RSEQ_H
+
+#include <stdint.h>
+#include <stdbool.h>
+#include <pthread.h>
+#include <signal.h>
+#include <sched.h>
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <sched.h>
+#include <linux/rseq.h>
+
+/*
+ * Empty code injection macros, override when testing.
+ * It is important to consider that the ASM injection macros need to be
+ * fully reentrant (e.g. do not modify the stack).
+ */
+#ifndef RSEQ_INJECT_ASM
+#define RSEQ_INJECT_ASM(n)
+#endif
+
+#ifndef RSEQ_INJECT_C
+#define RSEQ_INJECT_C(n)
+#endif
+
+#ifndef RSEQ_INJECT_INPUT
+#define RSEQ_INJECT_INPUT
+#endif
+
+#ifndef RSEQ_INJECT_CLOBBER
+#define RSEQ_INJECT_CLOBBER
+#endif
+
+#ifndef RSEQ_INJECT_FAILED
+#define RSEQ_INJECT_FAILED
+#endif
+
+extern __thread volatile struct rseq __rseq_abi;
+
+#define rseq_likely(x)		__builtin_expect(!!(x), 1)
+#define rseq_unlikely(x)	__builtin_expect(!!(x), 0)
+#define rseq_barrier()		__asm__ __volatile__("" : : : "memory")
+
+#define RSEQ_ACCESS_ONCE(x)	(*(__volatile__  __typeof__(x) *)&(x))
+#define RSEQ_WRITE_ONCE(x, v)	__extension__ ({ RSEQ_ACCESS_ONCE(x) = (v); })
+#define RSEQ_READ_ONCE(x)	RSEQ_ACCESS_ONCE(x)
+
+#define __rseq_str_1(x)	#x
+#define __rseq_str(x)		__rseq_str_1(x)
+
+#define rseq_log(fmt, args...)						       \
+	fprintf(stderr, fmt "(in %s() at " __FILE__ ":" __rseq_str(__LINE__)"\n", \
+		## args, __func__)
+
+#define rseq_bug(fmt, args...)		\
+	do {				\
+		rseq_log(fmt, ##args);	\
+		abort();		\
+	} while (0)
+
+#if defined(__x86_64__) || defined(__i386__)
+#include <rseq-x86.h>
+#elif defined(__ARMEL__)
+#include <rseq-arm.h>
+#elif defined(__PPC__)
+#include <rseq-ppc.h>
+#else
+#error unsupported target
+#endif
+
+/*
+ * Register rseq for the current thread. This needs to be called once
+ * by any thread which uses restartable sequences, before they start
+ * using restartable sequences, to ensure restartable sequences
+ * succeed. A restartable sequence executed from a non-registered
+ * thread will always fail.
+ */
+int rseq_register_current_thread(void);
+
+/*
+ * Unregister rseq for current thread.
+ */
+int rseq_unregister_current_thread(void);
+
+/*
+ * Restartable sequence fallback for reading the current CPU number.
+ */
+int32_t rseq_fallback_current_cpu(void);
+
+/*
+ * Values returned can be either the current CPU number, -1 (rseq is
+ * uninitialized), or -2 (rseq initialization has failed).
+ */
+static inline int32_t rseq_current_cpu_raw(void)
+{
+	return RSEQ_ACCESS_ONCE(__rseq_abi.cpu_id);
+}
+
+/*
+ * Returns a possible CPU number, which is typically the current CPU.
+ * The returned CPU number can be used to prepare for an rseq critical
+ * section, which will confirm whether the cpu number is indeed the
+ * current one, and whether rseq is initialized.
+ *
+ * The CPU number returned by rseq_cpu_start should always be validated
+ * by passing it to a rseq asm sequence, or by comparing it to the
+ * return value of rseq_current_cpu_raw() if the rseq asm sequence
+ * does not need to be invoked.
+ */
+static inline uint32_t rseq_cpu_start(void)
+{
+	return RSEQ_ACCESS_ONCE(__rseq_abi.cpu_id_start);
+}
+
+static inline uint32_t rseq_current_cpu(void)
+{
+	int32_t cpu;
+
+	cpu = rseq_current_cpu_raw();
+	if (rseq_unlikely(cpu < 0))
+		cpu = rseq_fallback_current_cpu();
+	return cpu;
+}
+
+/*
+ * rseq_prepare_unload() should be invoked by each thread using rseq_finish*()
+ * at least once between their last rseq_finish*() and library unload of the
+ * library defining the rseq critical section (struct rseq_cs). This also
+ * applies to use of rseq in code generated by JIT: rseq_prepare_unload()
+ * should be invoked at least once by each thread using rseq_finish*() before
+ * reclaim of the memory holding the struct rseq_cs.
+ */
+static inline void rseq_prepare_unload(void)
+{
+	__rseq_abi.rseq_cs = 0;
+}
+
+#endif  /* RSEQ_H_ */

tools/testing/selftests/rseq/run_param_test.sh

+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+ or MIT
+
+EXTRA_ARGS=${@}
+
+OLDIFS="$IFS"
+IFS=$'\n'
+TEST_LIST=(
+	"-T s"
+	"-T l"
+	"-T b"
+	"-T b -M"
+	"-T m"
+	"-T m -M"
+	"-T i"
+)
+
+TEST_NAME=(
+	"spinlock"
+	"list"
+	"buffer"
+	"buffer with barrier"
+	"memcpy"
+	"memcpy with barrier"
+	"increment"
+)
+IFS="$OLDIFS"
+
+REPS=1000
+SLOW_REPS=100
+
+function do_tests()
+{
+	local i=0
+	while [ "$i" -lt "${#TEST_LIST[@]}" ]; do
+		echo "Running test ${TEST_NAME[$i]}"
+		./param_test ${TEST_LIST[$i]} -r ${REPS} ${@} ${EXTRA_ARGS} || exit 1
+		echo "Running compare-twice test ${TEST_NAME[$i]}"
+		./param_test_compare_twice ${TEST_LIST[$i]} -r ${REPS} ${@} ${EXTRA_ARGS} || exit 1
+		let "i++"
+	done
+}
+
+echo "Default parameters"
+do_tests
+
+echo "Loop injection: 10000 loops"
+
+OLDIFS="$IFS"
+IFS=$'\n'
+INJECT_LIST=(
+	"1"
+	"2"
+	"3"
+	"4"
+	"5"
+	"6"
+	"7"
+	"8"
+	"9"
+)
+IFS="$OLDIFS"
+
+NR_LOOPS=10000
+
+i=0
+while [ "$i" -lt "${#INJECT_LIST[@]}" ]; do
+	echo "Injecting at <${INJECT_LIST[$i]}>"
+	do_tests -${INJECT_LIST[i]} ${NR_LOOPS}
+	let "i++"
+done
+NR_LOOPS=
+
+function inject_blocking()
+{
+	OLDIFS="$IFS"
+	IFS=$'\n'
+	INJECT_LIST=(
+		"7"
+		"8"
+		"9"
+	)
+	IFS="$OLDIFS"
+
+	NR_LOOPS=-1
+
+	i=0
+	while [ "$i" -lt "${#INJECT_LIST[@]}" ]; do
+		echo "Injecting at <${INJECT_LIST[$i]}>"
+		do_tests -${INJECT_LIST[i]} -1 ${@}
+		let "i++"
+	done
+	NR_LOOPS=
+}
+
+echo "Yield injection (25%)"
+inject_blocking -m 4 -y
+
+echo "Yield injection (50%)"
+inject_blocking -m 2 -y
+
+echo "Yield injection (100%)"
+inject_blocking -m 1 -y
+
+echo "Kill injection (25%)"
+inject_blocking -m 4 -k
+
+echo "Kill injection (50%)"
+inject_blocking -m 2 -k
+
+echo "Kill injection (100%)"
+inject_blocking -m 1 -k
+
+echo "Sleep injection (1ms, 25%)"
+inject_blocking -m 4 -s 1
+
+echo "Sleep injection (1ms, 50%)"
+inject_blocking -m 2 -s 1
+
+echo "Sleep injection (1ms, 100%)"
+inject_blocking -m 1 -s 1