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, 365 insertions, 0 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index 9b92413..d200162 100644
--- a/kernel/Makefile
+++ b/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
 
diff --git a/kernel/fork.c b/kernel/fork.c
index c6d1c1c..08c6e5e 100644
--- a/kernel/fork.c
+++ b/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
diff --git a/kernel/rseq.c b/kernel/rseq.c
new file mode 100644
index 0000000..ae306f9
--- /dev/null
+++ b/kernel/rseq.c
@@ -0,0 +1,357 @@
+// 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;
+}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e9866f8..a98d54c 100644
--- a/kernel/sched/core.c
+++ b/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);
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 06b4cce..df55617 100644
--- a/kernel/sys_ni.c
+++ b/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);