process.c

// SPDX-License-Identifier: GPL-2.0
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/prctl.h>
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/sched/idle.h>
#include <linux/sched/debug.h>
#include <linux/sched/task.h>
#include <linux/sched/task_stack.h>
#include <linux/init.h>
#include <linux/export.h>
#include <linux/pm.h>
#include <linux/tick.h>
#include <linux/random.h>
#include <linux/user-return-notifier.h>
#include <linux/dmi.h>
#include <linux/utsname.h>
#include <linux/stackprotector.h>
#include <linux/cpuidle.h>
#include <linux/acpi.h>
#include <linux/elf-randomize.h>
#include <trace/events/power.h>
#include <linux/hw_breakpoint.h>
#include <asm/cpu.h>
#include <asm/apic.h>
#include <asm/syscalls.h>
#include <linux/uaccess.h>
#include <asm/mwait.h>
#include <asm/fpu/internal.h>
#include <asm/debugreg.h>
#include <asm/nmi.h>
#include <asm/tlbflush.h>
#include <asm/mce.h>
#include <asm/vm86.h>
#include <asm/switch_to.h>
#include <asm/desc.h>
#include <asm/prctl.h>
#include <asm/spec-ctrl.h>
#include <asm/io_bitmap.h>
#include <asm/proto.h>

#include "process.h"

/*
 * per-CPU TSS segments. Threads are completely 'soft' on Linux,
 * no more per-task TSS's. The TSS size is kept cacheline-aligned
 * so they are allowed to end up in the .data..cacheline_aligned
 * section. Since TSS's are completely CPU-local, we want them
 * on exact cacheline boundaries, to eliminate cacheline ping-pong.
 */
__visible DEFINE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw) = {
	.x86_tss = {
		/*
		 * .sp0 is only used when entering ring 0 from a lower
		 * privilege level.  Since the init task never runs anything
		 * but ring 0 code, there is no need for a valid value here.
		 * Poison it.
		 */
		.sp0 = (1UL << (BITS_PER_LONG-1)) + 1,

		/*
		 * .sp1 is cpu_current_top_of_stack.  The init task never
		 * runs user code, but cpu_current_top_of_stack should still
		 * be well defined before the first context switch.
		 */
		.sp1 = TOP_OF_INIT_STACK,

#ifdef CONFIG_X86_32
		.ss0 = __KERNEL_DS,
		.ss1 = __KERNEL_CS,
#endif
		.io_bitmap_base	= IO_BITMAP_OFFSET_INVALID,
	 },
};
EXPORT_PER_CPU_SYMBOL(cpu_tss_rw);

DEFINE_PER_CPU(bool, __tss_limit_invalid);
EXPORT_PER_CPU_SYMBOL_GPL(__tss_limit_invalid);

/*
 * this gets called so that we can store lazy state into memory and copy the
 * current task into the new thread.
 */
int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
{
	memcpy(dst, src, arch_task_struct_size);
#ifdef CONFIG_VM86
	dst->thread.vm86 = NULL;
#endif

	return fpu__copy(dst, src);
}

/*
 * Free current thread data structures etc..
 */
void exit_thread(struct task_struct *tsk)
{
	struct thread_struct *t = &tsk->thread;
	struct io_bitmap *iobm = t->io_bitmap;
	struct fpu *fpu = &t->fpu;
	struct tss_struct *tss;

	if (iobm) {
		preempt_disable();
		tss = this_cpu_ptr(&cpu_tss_rw);

		t->io_bitmap = NULL;
		clear_thread_flag(TIF_IO_BITMAP);
		/* Invalidate the io bitmap base in the TSS */
		tss->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET_INVALID;
		preempt_enable();
		kfree(iobm);
	}

	free_vm86(t);

	fpu__drop(fpu);
}

static int set_new_tls(struct task_struct *p, unsigned long tls)
{
	struct user_desc __user *utls = (struct user_desc __user *)tls;

	if (in_ia32_syscall())
		return do_set_thread_area(p, -1, utls, 0);
	else
		return do_set_thread_area_64(p, ARCH_SET_FS, tls);
}

static inline int copy_io_bitmap(struct task_struct *tsk)
{
	struct io_bitmap *iobm = current->thread.io_bitmap;

	if (likely(!test_tsk_thread_flag(current, TIF_IO_BITMAP)))
		return 0;

	tsk->thread.io_bitmap = kmemdup(iobm, sizeof(*iobm), GFP_KERNEL);

	if (!tsk->thread.io_bitmap)
		return -ENOMEM;

	set_tsk_thread_flag(tsk, TIF_IO_BITMAP);
	return 0;
}

static inline void free_io_bitmap(struct task_struct *tsk)
{
	if (tsk->thread.io_bitmap) {
		kfree(tsk->thread.io_bitmap);
		tsk->thread.io_bitmap = NULL;
	}
}

int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
		    unsigned long arg, struct task_struct *p, unsigned long tls)
{
	struct inactive_task_frame *frame;
	struct fork_frame *fork_frame;
	struct pt_regs *childregs;
	int ret;

	childregs = task_pt_regs(p);
	fork_frame = container_of(childregs, struct fork_frame, regs);
	frame = &fork_frame->frame;

	frame->bp = 0;
	frame->ret_addr = (unsigned long) ret_from_fork;
	p->thread.sp = (unsigned long) fork_frame;
	p->thread.io_bitmap = NULL;
	memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));

#ifdef CONFIG_X86_64
	savesegment(gs, p->thread.gsindex);
	p->thread.gsbase = p->thread.gsindex ? 0 : current->thread.gsbase;
	savesegment(fs, p->thread.fsindex);
	p->thread.fsbase = p->thread.fsindex ? 0 : current->thread.fsbase;
	savesegment(es, p->thread.es);
	savesegment(ds, p->thread.ds);
#else
	p->thread.sp0 = (unsigned long) (childregs + 1);
	/*
	 * Clear all status flags including IF and set fixed bit. 64bit
	 * does not have this initialization as the frame does not contain
	 * flags. The flags consistency (especially vs. AC) is there
	 * ensured via objtool, which lacks 32bit support.
	 */
	frame->flags = X86_EFLAGS_FIXED;
#endif

	/* Kernel thread ? */
	if (unlikely(p->flags & PF_KTHREAD)) {
		memset(childregs, 0, sizeof(struct pt_regs));
		kthread_frame_init(frame, sp, arg);
		return 0;