linux/arch/x86/kernel/process_64.c

/*
 *  Copyright (C) 1995  Linus Torvalds
 *
 *  Pentium III FXSR, SSE support
 *	Gareth Hughes <gareth@valinux.com>, May 2000
 *
 *  X86-64 port
 *	Andi Kleen.
 *
 *	CPU hotplug support - ashok.raj@intel.com
 */

/*
 * This file handles the architecture-dependent parts of process handling..
 */

#include <linux/cpu.h>
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/elfcore.h>
#include <linux/smp.h>
#include <linux/slab.h>
#include <linux/user.h>
#include <linux/interrupt.h>
#include <linux/delay.h>
#include <linux/module.h>
#include <linux/ptrace.h>
#include <linux/notifier.h>
#include <linux/kprobes.h>
#include <linux/kdebug.h>
#include <linux/prctl.h>
#include <linux/uaccess.h>
#include <linux/io.h>
#include <linux/ftrace.h>

#include <asm/pgtable.h>
#include <asm/processor.h>
#include <asm/fpu/internal.h>
#include <asm/mmu_context.h>
#include <asm/prctl.h>
#include <asm/desc.h>
#include <asm/proto.h>
#include <asm/ia32.h>
#include <asm/idle.h>
#include <asm/syscalls.h>
#include <asm/debugreg.h>
#include <asm/switch_to.h>
#include <asm/xen/hypervisor.h>

asmlinkage extern void ret_from_fork(void);

__visible DEFINE_PER_CPU(unsigned long, rsp_scratch);

/* Prints also some state that isn't saved in the pt_regs */
void __show_regs(struct pt_regs *regs, int all)
{
	unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L, fs, gs, shadowgs;
	unsigned long d0, d1, d2, d3, d6, d7;
	unsigned int fsindex, gsindex;
	unsigned int ds, cs, es;

	printk(KERN_DEFAULT "RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->ip);
	printk_address(regs->ip);
	printk(KERN_DEFAULT "RSP: %04lx:%016lx  EFLAGS: %08lx\n", regs->ss,
			regs->sp, regs->flags);
	printk(KERN_DEFAULT "RAX: %016lx RBX: %016lx RCX: %016lx\n",
	       regs->ax, regs->bx, regs->cx);
	printk(KERN_DEFAULT "RDX: %016lx RSI: %016lx RDI: %016lx\n",
	       regs->dx, regs->si, regs->di);
	printk(KERN_DEFAULT "RBP: %016lx R08: %016lx R09: %016lx\n",
	       regs->bp, regs->r8, regs->r9);
	printk(KERN_DEFAULT "R10: %016lx R11: %016lx R12: %016lx\n",
	       regs->r10, regs->r11, regs->r12);
	printk(KERN_DEFAULT "R13: %016lx R14: %016lx R15: %016lx\n",
	       regs->r13, regs->r14, regs->r15);

	asm("movl %%ds,%0" : "=r" (ds));
	asm("movl %%cs,%0" : "=r" (cs));
	asm("movl %%es,%0" : "=r" (es));
	asm("movl %%fs,%0" : "=r" (fsindex));
	asm("movl %%gs,%0" : "=r" (gsindex));

	rdmsrl(MSR_FS_BASE, fs);
	rdmsrl(MSR_GS_BASE, gs);
	rdmsrl(MSR_KERNEL_GS_BASE, shadowgs);

	if (!all)
		return;

	cr0 = read_cr0();
	cr2 = read_cr2();
	cr3 = read_cr3();
	cr4 = __read_cr4();

	printk(KERN_DEFAULT "FS:  %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n",
	       fs, fsindex, gs, gsindex, shadowgs);
	printk(KERN_DEFAULT "CS:  %04x DS: %04x ES: %04x CR0: %016lx\n", cs, ds,
			es, cr0);
	printk(KERN_DEFAULT "CR2: %016lx CR3: %016lx CR4: %016lx\n", cr2, cr3,
			cr4);

	get_debugreg(d0, 0);
	get_debugreg(d1, 1);
	get_debugreg(d2, 2);
	get_debugreg(d3, 3);
	get_debugreg(d6, 6);
	get_debugreg(d7, 7);

	/* Only print out debug registers if they are in their non-default state. */
	if ((d0 == 0) && (d1 == 0) && (d2 == 0) && (d3 == 0) &&
	    (d6 == DR6_RESERVED) && (d7 == 0x400))
		return;

	printk(KERN_DEFAULT "DR0: %016lx DR1: %016lx DR2: %016lx\n", d0, d1, d2);
	printk(KERN_DEFAULT "DR3: %016lx DR6: %016lx DR7: %016lx\n", d3, d6, d7);

	if (boot_cpu_has(X86_FEATURE_OSPKE))
		printk(KERN_DEFAULT "PKRU: %08x\n", read_pkru());
}

void release_thread(struct task_struct *dead_task)
{
	if (dead_task->mm) {
#ifdef CONFIG_MODIFY_LDT_SYSCALL
		if (dead_task->mm->context.ldt) {
			pr_warn("WARNING: dead process %s still has LDT? <%p/%d>\n",
				dead_task->comm,
				dead_task->mm->context.ldt->entries,
				dead_task->mm->context.ldt->size);
			BUG();
		}
#endif
	}
}

static inline void set_32bit_tls(struct task_struct *t, int tls, u32 addr)
{
	struct user_desc ud = {
		.base_addr = addr,
		.limit = 0xfffff,
		.seg_32bit = 1,
		.limit_in_pages = 1,
		.useable = 1,
	};
	struct desc_struct *desc = t->thread.tls_array;
	desc += tls;
	fill_ldt(desc, &ud);
}

static inline u32 read_32bit_tls(struct task_struct *t, int tls)
{
	return get_desc_base(&t->thread.tls_array[tls]);
}

int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
		unsigned long arg, struct task_struct *p, unsigned long tls)
{
	int err;
	struct pt_regs *childregs;
	struct task_struct *me = current;

	p->thread.sp0 = (unsigned long)task_stack_page(p) + THREAD_SIZE;
	childregs = task_pt_regs(p);
	p->thread.sp = (unsigned long) childregs;
	set_tsk_thread_flag(p, TIF_FORK);
	p->thread.io_bitmap_ptr = NULL;

	savesegment(gs, p->thread.gsindex);
	p->thread.gs = p->thread.gsindex ? 0 : me->thread.gs;
	savesegment(fs, p->thread.fsindex);
	p->thread.fs = p->thread.fsindex ? 0 : me->thread.fs;
	savesegment(es, p->thread.es);
	savesegment(ds, p->thread.ds);
	memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));

	if (unlikely(p->flags & PF_KTHREAD)) {
		/* kernel thread */
		memset(childregs, 0, sizeof(struct pt_regs));
		childregs->sp = (unsigned long)childregs;
		childregs->ss = __KERNEL_DS;
		childregs->bx = sp; /* function */
		childregs->bp = arg;
		childregs->orig_ax = -1;
		childregs->cs = __KERNEL_CS | get_kernel_rpl();
		childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_FIXED;
		return 0;
	}
	*childregs = *current_pt_regs();

	childregs->ax = 0;
	if (sp)
		childregs->sp = sp;

	err = -ENOMEM;
	if (unlikely(test_tsk_thread_flag(me, TIF_IO_BITMAP))) {
		p->thread.io_bitmap_ptr = kmemdup(me->thread.io_bitmap_ptr,
						  IO_BITMAP_BYTES, GFP_KERNEL);
		if (!p->thread.io_bitmap_ptr) {
			p->thread.io_bitmap_max = 0;
			return -ENOMEM;
		}
		set_tsk_thread_flag(p, TIF_IO_BITMAP);
	}

	/*
	 * Set a new TLS for the child thread?
	 */
	if (clone_flags & CLONE_SETTLS) {
#ifdef CONFIG_IA32_EMULATION
		if (is_ia32_task())
			err = do_set_thread_area(p, -1,
				(struct user_desc __user *)tls, 0);
		else
#endif
			err = do_arch_prctl(p, ARCH_SET_FS, tls);
		if (err)
			goto out;
	}
	err = 0;
out:
	if (err && p->thread.io_bitmap_ptr) {
		kfree(p->thread.io_bitmap_ptr);
		p->thread.io_bitmap_max = 0;
	}

	return err;
}

static void
start_thread_common(struct pt_regs *regs, unsigned long new_ip,
		    unsigned long new_sp,
		    unsigned int _cs, unsigned int _ss, unsigned int _ds)
{
	loadsegment(fs, 0);
	loadsegment(es, _ds);
	loadsegment(ds, _ds);
	load_gs_index(0);
	regs->ip		= new_ip;
	regs->sp		= new_sp;
	regs->cs		= _cs;
	regs->ss		= _ss;
	regs->flags		= X86_EFLAGS_IF;
	force_iret();
}

void
start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp)
{
	start_thread_common(regs, new_ip, new_sp,
			    __USER_CS, __USER_DS, 0);
}

#ifdef CONFIG_COMPAT
void compat_start_thread(struct pt_regs *regs, u32 new_ip, u32 new_sp)
{
	start_thread_common(regs, new_ip, new_sp,
			    test_thread_flag(TIF_X32)
			    ? __USER_CS : __USER32_CS,
			    __USER_DS, __USER_DS);
}
#endif

/*
 *	switch_to(x,y) should switch tasks from x to y.
 *
 * This could still be optimized:
 * - fold all the options into a flag word and test it with a single test.
 * - could test fs/gs bitsliced
 *
 * Kprobes not supported here. Set the probe on schedule instead.
 * Function graph tracer not supported too.
 */
__visible __notrace_funcgraph struct task_struct *
__switch_to(struct task_struct *prev_p, struct task_struct *next_p)
{
	struct thread_struct *prev = &prev_p->thread;
	struct thread_struct *next = &next_p->thread;
	struct fpu *prev_fpu = &prev->fpu;
	struct fpu *next_fpu = &next->fpu;
	int cpu = smp_processor_id();
	struct tss_struct *tss = &per_cpu(cpu_tss, cpu);
	unsigned fsindex, gsindex;
	fpu_switch_t fpu_switch;

	fpu_switch = switch_fpu_prepare(prev_fpu, next_fpu, cpu);

	/* We must save %fs and %gs before load_TLS() because
	 * %fs and %gs may be cleared by load_TLS().
	 *
	 * (e.g. xen_load_tls())
	 */
	savesegment(fs, fsindex);
	savesegment(gs, gsindex);

	/*
	 * Load TLS before restoring any segments so that segment loads
	 * reference the correct GDT entries.
	 */
	load_TLS(next, cpu);

	/*
	 * Leave lazy mode, flushing any hypercalls made here.  This
	 * must be done after loading TLS entries in the GDT but before
	 * loading segments that might reference them, and and it must
	 * be done before fpu__restore(), so the TS bit is up to
	 * date.
	 */
	arch_end_context_switch(next_p);

	/* Switch DS and ES.
	 *
	 * Reading them only returns the selectors, but writing them (if
	 * nonzero) loads the full descriptor from the GDT or LDT.  The
	 * LDT for next is loaded in switch_mm, and the GDT is loaded
	 * above.
	 *
	 * We therefore need to write new values to the segment
	 * registers on every context switch unless both the new and old
	 * values are zero.
	 *
	 * Note that we don't need to do anything for CS and SS, as
	 * those are saved and restored as part of pt_regs.
	 */
	savesegment(es, prev->es);
	if (unlikely(next->es | prev->es))
		loadsegment(es, next->es);

	savesegment(ds, prev->ds);
	if (unlikely(next->ds | prev->ds))
		loadsegment(ds, next->ds);

	/*
	 * Switch FS and GS.
	 *
	 * These are even more complicated than DS and ES: they have
	 * 64-bit bases are that controlled by arch_prctl.  Those bases
	 * only differ from the values in the GDT or LDT if the selector
	 * is 0.
	 *
	 * Loading the segment register resets the hidden base part of
	 * the register to 0 or the value from the GDT / LDT.  If the
	 * next base address zero, writing 0 to the segment register is
	 * much faster than using wrmsr to explicitly zero the base.
	 *
	 * The thread_struct.fs and thread_struct.gs values are 0
	 * if the fs and gs bases respectively are not overridden
	 * from the values implied by fsindex and gsindex.  They
	 * are nonzero, and store the nonzero base addresses, if
	 * the bases are overridden.
	 *
	 * (fs != 0 && fsindex != 0) || (gs != 0 && gsindex != 0) should
	 * be impossible.
	 *
	 * Therefore we need to reload the segment registers if either
	 * the old or new selector is nonzero, and we need to override
	 * the base address if next thread expects it to be overridden.
	 *
	 * This code is unnecessarily slow in the case where the old and
	 * new indexes are zero and the new base is nonzero -- it will
	 * unnecessarily write 0 to the selector before writing the new
	 * base address.
	 *
	 * Note: This all depends on arch_prctl being the only way that
	 * user code can override the segment base.  Once wrfsbase and
	 * wrgsbase are enabled, most of this code will need to change.
	 */
	if (unlikely(fsindex | next->fsindex | prev->fs)) {
		loadsegment(fs, next->fsindex);

		/*
		 * If user code wrote a nonzero value to FS, then it also
		 * cleared the overridden base address.
		 *
		 * XXX: if user code wrote 0 to FS and cleared the base
		 * address itself, we won't notice and we'll incorrectly
		 * restore the prior base address next time we reschdule
		 * the process.
		 */
		if (fsindex)
			prev->fs = 0;
	}
	if (next->fs)
		wrmsrl(MSR_FS_BASE, next->fs);
	prev->fsindex = fsindex;

	if (unlikely(gsindex | next->gsindex | prev->gs)) {
		load_gs_index(next->gsindex);

		/* This works (and fails) the same way as fsindex above. */
		if (gsindex)
			prev->gs = 0;
	}
	if (next->gs)
		wrmsrl(MSR_KERNEL_GS_BASE, next->gs);
	prev->gsindex = gsindex;

	switch_fpu_finish(next_fpu, fpu_switch);

	/*
	 * Switch the PDA and FPU contexts.
	 */
	this_cpu_write(current_task, next_p);

	/* Reload esp0 and ss1.  This changes current_thread_info(). */
	load_sp0(tss, next);

	/*
	 * Now maybe reload the debug registers and handle I/O bitmaps
	 */
	if (unlikely(task_thread_info(next_p)->flags & _TIF_WORK_CTXSW_NEXT ||
		     task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV))
		__switch_to_xtra(prev_p, next_p, tss);

#ifdef CONFIG_XEN
	/*
	 * On Xen PV, IOPL bits in pt_regs->flags have no effect, and
	 * current_pt_regs()->flags may not match the current task's
	 * intended IOPL.  We need to switch it manually.
	 */
	if (unlikely(static_cpu_has(X86_FEATURE_XENPV) &&
		     prev->iopl != next->iopl))
		xen_set_iopl_mask(next->iopl);
#endif

	if (static_cpu_has_bug(X86_BUG_SYSRET_SS_ATTRS)) {
		/*
		 * AMD CPUs have a misfeature: SYSRET sets the SS selector but
		 * does not update the cached descriptor.  As a result, if we
		 * do SYSRET while SS is NULL, we'll end up in user mode with
		 * SS apparently equal to __USER_DS but actually unusable.
		 *
		 * The straightforward workaround would be to fix it up just
		 * before SYSRET, but that would slow down the system call
		 * fast paths.  Instead, we ensure that SS is never NULL in
		 * system call context.  We do this by replacing NULL SS
		 * selectors at every context switch.  SYSCALL sets up a valid
		 * SS, so the only way to get NULL is to re-enter the kernel
		 * from CPL 3 through an interrupt.  Since that can't happen
		 * in the same task as a running syscall, we are guaranteed to
		 * context switch between every interrupt vector entry and a
		 * subsequent SYSRET.
		 *
		 * We read SS first because SS reads are much faster than
		 * writes.  Out of caution, we force SS to __KERNEL_DS even if
		 * it previously had a different non-NULL value.
		 */
		unsigned short ss_sel;
		savesegment(ss, ss_sel);
		if (ss_sel != __KERNEL_DS)
			loadsegment(ss, __KERNEL_DS);
	}

	return prev_p;
}

void set_personality_64bit(void)
{
	/* inherit personality from parent */

	/* Make sure to be in 64bit mode */
	clear_thread_flag(TIF_IA32);
	clear_thread_flag(TIF_ADDR32);
	clear_thread_flag(TIF_X32);

	/* Ensure the corresponding mm is not marked. */
	if (current->mm)
		current->mm->context.ia32_compat = 0;

	/* TBD: overwrites user setup. Should have two bits.
	   But 64bit processes have always behaved this way,
	   so it's not too bad. The main problem is just that
	   32bit childs are affected again. */
	current->personality &= ~READ_IMPLIES_EXEC;
}

void set_personality_ia32(bool x32)
{
	/* inherit personality from parent */

	/* Make sure to be in 32bit mode */
	set_thread_flag(TIF_ADDR32);

	/* Mark the associated mm as containing 32-bit tasks. */
	if (x32) {
		clear_thread_flag(TIF_IA32);
		set_thread_flag(TIF_X32);
		if (current->mm)
			current->mm->context.ia32_compat = TIF_X32;
		current->personality &= ~READ_IMPLIES_EXEC;
		/* in_compat_syscall() uses the presence of the x32
		   syscall bit flag to determine compat status */
		current_thread_info()->status &= ~TS_COMPAT;
	} else {
		set_thread_flag(TIF_IA32);
		clear_thread_flag(TIF_X32);
		if (current->mm)
			current->mm->context.ia32_compat = TIF_IA32;
		current->personality |= force_personality32;
		/* Prepare the first "return" to user space */
		current_thread_info()->status |= TS_COMPAT;
	}
}
EXPORT_SYMBOL_GPL(set_personality_ia32);

long do_arch_prctl(struct task_struct *task, int code, unsigned long addr)
{
	int ret = 0;
	int doit = task == current;
	int cpu;

	switch (code) {
	case ARCH_SET_GS:
		if (addr >= TASK_SIZE_OF(task))
			return -EPERM;
		cpu = get_cpu();
		/* handle small bases via the GDT because that's faster to
		   switch. */
		if (addr <= 0xffffffff) {
			set_32bit_tls(task, GS_TLS, addr);
			if (doit) {
				load_TLS(&task->thread, cpu);
				load_gs_index(GS_TLS_SEL);
			}
			task->thread.gsindex = GS_TLS_SEL;
			task->thread.gs = 0;
		} else {
			task->thread.gsindex = 0;
			task->thread.gs = addr;
			if (doit) {
				load_gs_index(0);
				ret = wrmsrl_safe(MSR_KERNEL_GS_BASE, addr);
			}
		}
		put_cpu();
		break;
	case ARCH_SET_FS:
		/* Not strictly needed for fs, but do it for symmetry
		   with gs */
		if (addr >= TASK_SIZE_OF(task))
			return -EPERM;
		cpu = get_cpu();
		/* handle small bases via the GDT because that's faster to
		   switch. */
		if (addr <= 0xffffffff) {
			set_32bit_tls(task, FS_TLS, addr);
			if (doit) {
				load_TLS(&task->thread, cpu);
				loadsegment(fs, FS_TLS_SEL);
			}
			task->thread.fsindex = FS_TLS_SEL;
			task->thread.fs = 0;
		} else {
			task->thread.fsindex = 0;
			task->thread.fs = addr;
			if (doit) {
				/* set the selector to 0 to not confuse
				   __switch_to */
				loadsegment(fs, 0);
				ret = wrmsrl_safe(MSR_FS_BASE, addr);
			}
		}
		put_cpu();
		break;
	case ARCH_GET_FS: {
		unsigned long base;
		if (task->thread.fsindex == FS_TLS_SEL)
			base = read_32bit_tls(task, FS_TLS);
		else if (doit)
			rdmsrl(MSR_FS_BASE, base);
		else
			base = task->thread.fs;
		ret = put_user(base, (unsigned long __user *)addr);
		break;
	}
	case ARCH_GET_GS: {
		unsigned long base;
		unsigned gsindex;
		if (task->thread.gsindex == GS_TLS_SEL)
			base = read_32bit_tls(task, GS_TLS);
		else if (doit) {
			savesegment(gs, gsindex);
			if (gsindex)
				rdmsrl(MSR_KERNEL_GS_BASE, base);
			else
				base = task->thread.gs;
		} else
			base = task->thread.gs;
		ret = put_user(base, (unsigned long __user *)addr);
		break;
	}

	default:
		ret = -EINVAL;
		break;
	}

	return ret;
}

long sys_arch_prctl(int code, unsigned long addr)
{
	return do_arch_prctl(current, code, addr);
}

unsigned long KSTK_ESP(struct task_struct *task)
{
	return task_pt_regs(task)->sp;
}