Commit b968e84b authored by Peter Zijlstra's avatar Peter Zijlstra
Browse files

x86/iopl: Fake iopl(3) CLI/STI usage 



Since commit c8137ace ("x86/iopl: Restrict iopl() permission
scope") it's possible to emulate iopl(3) using ioperm(), except for
the CLI/STI usage.

Userspace CLI/STI usage is very dubious (read broken), since any
exception taken during that window can lead to rescheduling anyway (or
worse). The IOPL(2) manpage even states that usage of CLI/STI is highly
discouraged and might even crash the system.

Of course, that won't stop people and HP has the dubious honour of
being the first vendor to be found using this in their hp-health
package.

In order to enable this 'software' to still 'work', have the #GP treat
the CLI/STI instructions as NOPs when iopl(3). Warn the user that
their program is doing dubious things.

Fixes: a24ca997 ("x86/iopl: Remove legacy IOPL option")
Reported-by: default avatarOndrej Zary <linux@zary.sk>
Signed-off-by: default avatarPeter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: default avatarThomas Gleixner <tglx@linutronix.de>
Cc: stable@kernel.org # v5.5+
Link: https://lkml.kernel.org/r/20210918090641.GD5106@worktop.programming.kicks-ass.net
parent 6880fa6c

arch/x86/include/asm/insn-eval.h

+1 −0
Original line number Diff line number Diff line
@@ -21,6 +21,7 @@ int insn_get_modrm_rm_off(struct insn *insn, struct pt_regs *regs); 
int insn_get_modrm_reg_off(struct insn *insn, struct pt_regs *regs);

unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx);

int insn_get_code_seg_params(struct pt_regs *regs);

int insn_get_effective_ip(struct pt_regs *regs, unsigned long *ip);

int insn_fetch_from_user(struct pt_regs *regs,

			 unsigned char buf[MAX_INSN_SIZE]);

int insn_fetch_from_user_inatomic(struct pt_regs *regs,

arch/x86/include/asm/processor.h

+1 −0
Original line number Diff line number Diff line
@@ -518,6 +518,7 @@ struct thread_struct { 
	 */

	unsigned long		iopl_emul;



	unsigned int		iopl_warn:1;

	unsigned int		sig_on_uaccess_err:1;



	/*

arch/x86/kernel/process.c

+1 −0
Original line number Diff line number Diff line
@@ -132,6 +132,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg, 
	frame->ret_addr = (unsigned long) ret_from_fork;

	p->thread.sp = (unsigned long) fork_frame;

	p->thread.io_bitmap = NULL;

	p->thread.iopl_warn = 0;

	memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));



#ifdef CONFIG_X86_64

arch/x86/kernel/traps.c

+33 −0
Original line number Diff line number Diff line
@@ -528,6 +528,36 @@ static enum kernel_gp_hint get_kernel_gp_address(struct pt_regs *regs, 


#define GPFSTR "general protection fault"



static bool fixup_iopl_exception(struct pt_regs *regs)

{

	struct thread_struct *t = &current->thread;

	unsigned char byte;

	unsigned long ip;



	if (!IS_ENABLED(CONFIG_X86_IOPL_IOPERM) || t->iopl_emul != 3)

		return false;



	if (insn_get_effective_ip(regs, &ip))

		return false;



	if (get_user(byte, (const char __user *)ip))

		return false;



	if (byte != 0xfa && byte != 0xfb)

		return false;



	if (!t->iopl_warn && printk_ratelimit()) {

		pr_err("%s[%d] attempts to use CLI/STI, pretending it's a NOP, ip:%lx",

		       current->comm, task_pid_nr(current), ip);

		print_vma_addr(KERN_CONT " in ", ip);

		pr_cont("\n");

		t->iopl_warn = 1;

	}



	regs->ip += 1;

	return true;

}



DEFINE_IDTENTRY_ERRORCODE(exc_general_protection)

{

	char desc[sizeof(GPFSTR) + 50 + 2*sizeof(unsigned long) + 1] = GPFSTR;
@@ -553,6 +583,9 @@ DEFINE_IDTENTRY_ERRORCODE(exc_general_protection) 
	tsk = current;



	if (user_mode(regs)) {

		if (fixup_iopl_exception(regs))

			goto exit;



		tsk->thread.error_code = error_code;

		tsk->thread.trap_nr = X86_TRAP_GP;

arch/x86/lib/insn-eval.c

+1 −1
Original line number Diff line number Diff line
@@ -1417,7 +1417,7 @@ void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs) 
	}

}



static int insn_get_effective_ip(struct pt_regs *regs, unsigned long *ip)

int insn_get_effective_ip(struct pt_regs *regs, unsigned long *ip)

{

	unsigned long seg_base = 0;