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

5 files changed, 377 insertions, 1 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 14e4f9c12337..3aa4fcb74e76 100644
--- a/include/linux/sched.h
+++ b/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
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 390e814fdc8d..73810808cdf2 100644
--- a/include/linux/syscalls.h
+++ b/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
diff --git a/include/trace/events/rseq.h b/include/trace/events/rseq.h
new file mode 100644
index 000000000000..a04a64bc1a00
--- /dev/null
+++ b/include/trace/events/rseq.h
@@ -0,0 +1,57 @@
+/* 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>
diff --git a/include/uapi/linux/rseq.h b/include/uapi/linux/rseq.h
new file mode 100644
index 000000000000..d620fa43756c
--- /dev/null
+++ b/include/uapi/linux/rseq.h
@@ -0,0 +1,133 @@
+/* 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 */
diff --git a/include/uapi/linux/types_32_64.h b/include/uapi/linux/types_32_64.h
new file mode 100644
index 000000000000..0a87ace34a57
--- /dev/null
+++ b/include/uapi/linux/types_32_64.h
@@ -0,0 +1,50 @@
+/* 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 */