linux/kernel/rseq.c

// SPDX-License-Identifier: GPL-2.0+
/*
 * Restartable sequences system call
 *
 * Copyright (C) 2015, Google, Inc.,
 * Paul Turner <[email protected]> and Andrew Hunter <[email protected]>
 * Copyright (C) 2015-2018, EfficiOS Inc.,
 * Mathieu Desnoyers <[email protected]>
 */

#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>

/* The original rseq structure size (including padding) is 32 bytes. */
#define ORIG_RSEQ_SIZE …

#define RSEQ_CS_NO_RESTART_FLAGS …

/*
 *
 * 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_node_id(struct task_struct *t)
{ … }

static int rseq_reset_rseq_cpu_node_id(struct task_struct *t)
{ … }

static int rseq_get_rseq_cs(struct task_struct *t, struct rseq_cs *rseq_cs)
{ … }

static bool rseq_warn_flags(const char *str, u32 flags)
{ … }

static int rseq_need_restart(struct task_struct *t, u32 cs_flags)
{ … }

static int clear_rseq_cs(struct task_struct *t)
{ … }

/*
 * 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)
{ … }

static int rseq_ip_fixup(struct pt_regs *regs)
{ … }

/*
 * 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
 * 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 ksignal *ksig, struct pt_regs *regs)
{ … }

#ifdef CONFIG_DEBUG_RSEQ

/*
 * Terminate the process if a syscall is issued within a restartable
 * sequence.
 */
void rseq_syscall(struct pt_regs *regs)
{ … }

#endif

/*
 * sys_rseq - setup restartable sequences for caller thread.
 */
SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len,
		int, flags, u32, sig)
{ … }