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