Contributors: 29
Author Tokens Token Proportion Commits Commit Proportion
Thomas Gleixner 526 37.30% 17 20.99%
Andrew Lutomirski 337 23.90% 18 22.22%
Brian Gerst 158 11.21% 5 6.17%
H. Peter Anvin 139 9.86% 4 4.94%
Nikolay Borisov 41 2.91% 2 2.47%
David Vrabel 32 2.27% 1 1.23%
Peter Zijlstra 31 2.20% 3 3.70%
Xin Li (Intel) 22 1.56% 1 1.23%
Linus Torvalds (pre-git) 18 1.28% 4 4.94%
Linus Torvalds 18 1.28% 3 3.70%
Dan J Williams 17 1.21% 1 1.23%
Dominik Brodowski 12 0.85% 2 2.47%
Andi Kleen 8 0.57% 2 2.47%
Vitaly Kuznetsov 6 0.43% 1 1.23%
Sami Tolvanen 6 0.43% 1 1.23%
Kees Cook 6 0.43% 1 1.23%
Pawan Gupta 5 0.35% 1 1.23%
Ingo Molnar 4 0.28% 2 2.47%
Jeremy Fitzhardinge 3 0.21% 1 1.23%
Thomas Garnier 3 0.21% 1 1.23%
Benjamin Thiel 3 0.21% 1 1.23%
Roland McGrath 3 0.21% 1 1.23%
Alex Nixon 3 0.21% 2 2.47%
Boris Ostrovsky 2 0.14% 1 1.23%
Borislav Petkov 2 0.14% 1 1.23%
Rik Van Riel 2 0.14% 1 1.23%
Valentin Schneider 1 0.07% 1 1.23%
Paul Gortmaker 1 0.07% 1 1.23%
Juergen Gross 1 0.07% 1 1.23%
Total 1410 81 
123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523
// SPDX-License-Identifier: GPL-2.0-only
/*
 * common.c - C code for kernel entry and exit
 * Copyright (c) 2015 Andrew Lutomirski
 *
 * Based on asm and ptrace code by many authors.  The code here originated
 * in ptrace.c and signal.c.
 */

#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/sched/task_stack.h>
#include <linux/entry-common.h>
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/errno.h>
#include <linux/ptrace.h>
#include <linux/export.h>
#include <linux/nospec.h>
#include <linux/syscalls.h>
#include <linux/uaccess.h>
#include <linux/init.h>

#ifdef CONFIG_XEN_PV
#include <xen/xen-ops.h>
#include <xen/events.h>
#endif

#include <asm/apic.h>
#include <asm/desc.h>
#include <asm/traps.h>
#include <asm/vdso.h>
#include <asm/cpufeature.h>
#include <asm/fpu/api.h>
#include <asm/nospec-branch.h>
#include <asm/io_bitmap.h>
#include <asm/syscall.h>
#include <asm/irq_stack.h>

#ifdef CONFIG_X86_64

static __always_inline bool do_syscall_x64(struct pt_regs *regs, int nr)
{
	/*
	 * Convert negative numbers to very high and thus out of range
	 * numbers for comparisons.
	 */
	unsigned int unr = nr;

	if (likely(unr < NR_syscalls)) {
		unr = array_index_nospec(unr, NR_syscalls);
		regs->ax = x64_sys_call(regs, unr);
		return true;
	}
	return false;
}

static __always_inline bool do_syscall_x32(struct pt_regs *regs, int nr)
{
	/*
	 * Adjust the starting offset of the table, and convert numbers
	 * < __X32_SYSCALL_BIT to very high and thus out of range
	 * numbers for comparisons.
	 */
	unsigned int xnr = nr - __X32_SYSCALL_BIT;

	if (IS_ENABLED(CONFIG_X86_X32_ABI) && likely(xnr < X32_NR_syscalls)) {
		xnr = array_index_nospec(xnr, X32_NR_syscalls);
		regs->ax = x32_sys_call(regs, xnr);
		return true;
	}
	return false;
}

/* Returns true to return using SYSRET, or false to use IRET */
__visible noinstr bool do_syscall_64(struct pt_regs *regs, int nr)
{
	add_random_kstack_offset();
	nr = syscall_enter_from_user_mode(regs, nr);

	instrumentation_begin();

	if (!do_syscall_x64(regs, nr) && !do_syscall_x32(regs, nr) && nr != -1) {
		/* Invalid system call, but still a system call. */
		regs->ax = __x64_sys_ni_syscall(regs);
	}

	instrumentation_end();
	syscall_exit_to_user_mode(regs);

	/*
	 * Check that the register state is valid for using SYSRET to exit
	 * to userspace.  Otherwise use the slower but fully capable IRET
	 * exit path.
	 */

	/* XEN PV guests always use the IRET path */
	if (cpu_feature_enabled(X86_FEATURE_XENPV))
		return false;

	/* SYSRET requires RCX == RIP and R11 == EFLAGS */
	if (unlikely(regs->cx != regs->ip || regs->r11 != regs->flags))
		return false;

	/* CS and SS must match the values set in MSR_STAR */
	if (unlikely(regs->cs != __USER_CS || regs->ss != __USER_DS))
		return false;

	/*
	 * On Intel CPUs, SYSRET with non-canonical RCX/RIP will #GP
	 * in kernel space.  This essentially lets the user take over
	 * the kernel, since userspace controls RSP.
	 *
	 * TASK_SIZE_MAX covers all user-accessible addresses other than
	 * the deprecated vsyscall page.
	 */
	if (unlikely(regs->ip >= TASK_SIZE_MAX))
		return false;

	/*
	 * SYSRET cannot restore RF.  It can restore TF, but unlike IRET,
	 * restoring TF results in a trap from userspace immediately after
	 * SYSRET.
	 */
	if (unlikely(regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF)))
		return false;

	/* Use SYSRET to exit to userspace */
	return true;
}
#endif

#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
static __always_inline int syscall_32_enter(struct pt_regs *regs)
{
	if (IS_ENABLED(CONFIG_IA32_EMULATION))
		current_thread_info()->status |= TS_COMPAT;

	return (int)regs->orig_ax;
}

#ifdef CONFIG_IA32_EMULATION
bool __ia32_enabled __ro_after_init = !IS_ENABLED(CONFIG_IA32_EMULATION_DEFAULT_DISABLED);

static int ia32_emulation_override_cmdline(char *arg)
{
	return kstrtobool(arg, &__ia32_enabled);
}
early_param("ia32_emulation", ia32_emulation_override_cmdline);
#endif

/*
 * Invoke a 32-bit syscall.  Called with IRQs on in CT_STATE_KERNEL.
 */
static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs, int nr)
{
	/*
	 * Convert negative numbers to very high and thus out of range
	 * numbers for comparisons.
	 */
	unsigned int unr = nr;

	if (likely(unr < IA32_NR_syscalls)) {
		unr = array_index_nospec(unr, IA32_NR_syscalls);
		regs->ax = ia32_sys_call(regs, unr);
	} else if (nr != -1) {
		regs->ax = __ia32_sys_ni_syscall(regs);
	}
}

#ifdef CONFIG_IA32_EMULATION
static __always_inline bool int80_is_external(void)
{
	const unsigned int offs = (0x80 / 32) * 0x10;
	const u32 bit = BIT(0x80 % 32);

	/* The local APIC on XENPV guests is fake */
	if (cpu_feature_enabled(X86_FEATURE_XENPV))
		return false;

	/*
	 * If vector 0x80 is set in the APIC ISR then this is an external
	 * interrupt. Either from broken hardware or injected by a VMM.
	 *
	 * Note: In guest mode this is only valid for secure guests where
	 * the secure module fully controls the vAPIC exposed to the guest.
	 */
	return apic_read(APIC_ISR + offs) & bit;
}

/**
 * do_int80_emulation - 32-bit legacy syscall C entry from asm
 *
 * This entry point can be used by 32-bit and 64-bit programs to perform
 * 32-bit system calls.  Instances of INT $0x80 can be found inline in
 * various programs and libraries.  It is also used by the vDSO's
 * __kernel_vsyscall fallback for hardware that doesn't support a faster
 * entry method.  Restarted 32-bit system calls also fall back to INT
 * $0x80 regardless of what instruction was originally used to do the
 * system call.
 *
 * This is considered a slow path.  It is not used by most libc
 * implementations on modern hardware except during process startup.
 *
 * The arguments for the INT $0x80 based syscall are on stack in the
 * pt_regs structure:
 *   eax:				system call number
 *   ebx, ecx, edx, esi, edi, ebp:	arg1 - arg 6
 */
__visible noinstr void do_int80_emulation(struct pt_regs *regs)
{
	int nr;

	/* Kernel does not use INT $0x80! */
	if (unlikely(!user_mode(regs))) {
		irqentry_enter(regs);
		instrumentation_begin();
		panic("Unexpected external interrupt 0x80\n");
	}

	/*
	 * Establish kernel context for instrumentation, including for
	 * int80_is_external() below which calls into the APIC driver.
	 * Identical for soft and external interrupts.
	 */
	enter_from_user_mode(regs);

	instrumentation_begin();
	add_random_kstack_offset();

	/* Validate that this is a soft interrupt to the extent possible */
	if (unlikely(int80_is_external()))
		panic("Unexpected external interrupt 0x80\n");

	/*
	 * The low level idtentry code pushed -1 into regs::orig_ax
	 * and regs::ax contains the syscall number.
	 *
	 * User tracing code (ptrace or signal handlers) might assume
	 * that the regs::orig_ax contains a 32-bit number on invoking
	 * a 32-bit syscall.
	 *
	 * Establish the syscall convention by saving the 32bit truncated
	 * syscall number in regs::orig_ax and by invalidating regs::ax.
	 */
	regs->orig_ax = regs->ax & GENMASK(31, 0);
	regs->ax = -ENOSYS;

	nr = syscall_32_enter(regs);

	local_irq_enable();
	nr = syscall_enter_from_user_mode_work(regs, nr);
	do_syscall_32_irqs_on(regs, nr);

	instrumentation_end();
	syscall_exit_to_user_mode(regs);
}

#ifdef CONFIG_X86_FRED
/*
 * A FRED-specific INT80 handler is warranted for the follwing reasons:
 *
 * 1) As INT instructions and hardware interrupts are separate event
 *    types, FRED does not preclude the use of vector 0x80 for external
 *    interrupts. As a result, the FRED setup code does not reserve
 *    vector 0x80 and calling int80_is_external() is not merely
 *    suboptimal but actively incorrect: it could cause a system call
 *    to be incorrectly ignored.
 *
 * 2) It is called only for handling vector 0x80 of event type
 *    EVENT_TYPE_SWINT and will never be called to handle any external
 *    interrupt (event type EVENT_TYPE_EXTINT).
 *
 * 3) FRED has separate entry flows depending on if the event came from
 *    user space or kernel space, and because the kernel does not use
 *    INT insns, the FRED kernel entry handler fred_entry_from_kernel()
 *    falls through to fred_bad_type() if the event type is
 *    EVENT_TYPE_SWINT, i.e., INT insns. So if the kernel is handling
 *    an INT insn, it can only be from a user level.
 *
 * 4) int80_emulation() does a CLEAR_BRANCH_HISTORY. While FRED will
 *    likely take a different approach if it is ever needed: it
 *    probably belongs in either fred_intx()/ fred_other() or
 *    asm_fred_entrypoint_user(), depending on if this ought to be done
 *    for all entries from userspace or only system
 *    calls.
 *
 * 5) INT $0x80 is the fast path for 32-bit system calls under FRED.
 */
DEFINE_FREDENTRY_RAW(int80_emulation)
{
	int nr;

	enter_from_user_mode(regs);

	instrumentation_begin();
	add_random_kstack_offset();

	/*
	 * FRED pushed 0 into regs::orig_ax and regs::ax contains the
	 * syscall number.
	 *
	 * User tracing code (ptrace or signal handlers) might assume
	 * that the regs::orig_ax contains a 32-bit number on invoking
	 * a 32-bit syscall.
	 *
	 * Establish the syscall convention by saving the 32bit truncated
	 * syscall number in regs::orig_ax and by invalidating regs::ax.
	 */
	regs->orig_ax = regs->ax & GENMASK(31, 0);
	regs->ax = -ENOSYS;

	nr = syscall_32_enter(regs);

	local_irq_enable();
	nr = syscall_enter_from_user_mode_work(regs, nr);
	do_syscall_32_irqs_on(regs, nr);

	instrumentation_end();
	syscall_exit_to_user_mode(regs);
}
#endif
#else /* CONFIG_IA32_EMULATION */

/* Handles int $0x80 on a 32bit kernel */
__visible noinstr void do_int80_syscall_32(struct pt_regs *regs)
{
	int nr = syscall_32_enter(regs);

	add_random_kstack_offset();
	/*
	 * Subtlety here: if ptrace pokes something larger than 2^31-1 into
	 * orig_ax, the int return value truncates it. This matches
	 * the semantics of syscall_get_nr().
	 */
	nr = syscall_enter_from_user_mode(regs, nr);
	instrumentation_begin();

	do_syscall_32_irqs_on(regs, nr);

	instrumentation_end();
	syscall_exit_to_user_mode(regs);
}
#endif /* !CONFIG_IA32_EMULATION */

static noinstr bool __do_fast_syscall_32(struct pt_regs *regs)
{
	int nr = syscall_32_enter(regs);
	int res;

	add_random_kstack_offset();
	/*
	 * This cannot use syscall_enter_from_user_mode() as it has to
	 * fetch EBP before invoking any of the syscall entry work
	 * functions.
	 */
	syscall_enter_from_user_mode_prepare(regs);

	instrumentation_begin();
	/* Fetch EBP from where the vDSO stashed it. */
	if (IS_ENABLED(CONFIG_X86_64)) {
		/*
		 * Micro-optimization: the pointer we're following is
		 * explicitly 32 bits, so it can't be out of range.
		 */
		res = __get_user(*(u32 *)&regs->bp,
			 (u32 __user __force *)(unsigned long)(u32)regs->sp);
	} else {
		res = get_user(*(u32 *)&regs->bp,
		       (u32 __user __force *)(unsigned long)(u32)regs->sp);
	}

	if (res) {
		/* User code screwed up. */
		regs->ax = -EFAULT;

		local_irq_disable();
		instrumentation_end();
		irqentry_exit_to_user_mode(regs);
		return false;
	}

	nr = syscall_enter_from_user_mode_work(regs, nr);

	/* Now this is just like a normal syscall. */
	do_syscall_32_irqs_on(regs, nr);

	instrumentation_end();
	syscall_exit_to_user_mode(regs);
	return true;
}

/* Returns true to return using SYSEXIT/SYSRETL, or false to use IRET */
__visible noinstr bool do_fast_syscall_32(struct pt_regs *regs)
{
	/*
	 * Called using the internal vDSO SYSENTER/SYSCALL32 calling
	 * convention.  Adjust regs so it looks like we entered using int80.
	 */
	unsigned long landing_pad = (unsigned long)current->mm->context.vdso +
					vdso_image_32.sym_int80_landing_pad;

	/*
	 * SYSENTER loses EIP, and even SYSCALL32 needs us to skip forward
	 * so that 'regs->ip -= 2' lands back on an int $0x80 instruction.
	 * Fix it up.
	 */
	regs->ip = landing_pad;

	/* Invoke the syscall. If it failed, keep it simple: use IRET. */
	if (!__do_fast_syscall_32(regs))
		return false;

	/*
	 * Check that the register state is valid for using SYSRETL/SYSEXIT
	 * to exit to userspace.  Otherwise use the slower but fully capable
	 * IRET exit path.
	 */

	/* XEN PV guests always use the IRET path */
	if (cpu_feature_enabled(X86_FEATURE_XENPV))
		return false;

	/* EIP must point to the VDSO landing pad */
	if (unlikely(regs->ip != landing_pad))
		return false;

	/* CS and SS must match the values set in MSR_STAR */
	if (unlikely(regs->cs != __USER32_CS || regs->ss != __USER_DS))
		return false;

	/* If the TF, RF, or VM flags are set, use IRET */
	if (unlikely(regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF | X86_EFLAGS_VM)))
		return false;

	/* Use SYSRETL/SYSEXIT to exit to userspace */
	return true;
}

/* Returns true to return using SYSEXIT/SYSRETL, or false to use IRET */
__visible noinstr bool do_SYSENTER_32(struct pt_regs *regs)
{
	/* SYSENTER loses RSP, but the vDSO saved it in RBP. */
	regs->sp = regs->bp;

	/* SYSENTER clobbers EFLAGS.IF.  Assume it was set in usermode. */
	regs->flags |= X86_EFLAGS_IF;

	return do_fast_syscall_32(regs);
}
#endif

SYSCALL_DEFINE0(ni_syscall)
{
	return -ENOSYS;
}

#ifdef CONFIG_XEN_PV
#ifndef CONFIG_PREEMPTION
/*
 * Some hypercalls issued by the toolstack can take many 10s of
 * seconds. Allow tasks running hypercalls via the privcmd driver to
 * be voluntarily preempted even if full kernel preemption is
 * disabled.
 *
 * Such preemptible hypercalls are bracketed by
 * xen_preemptible_hcall_begin() and xen_preemptible_hcall_end()
 * calls.
 */
DEFINE_PER_CPU(bool, xen_in_preemptible_hcall);
EXPORT_SYMBOL_GPL(xen_in_preemptible_hcall);

/*
 * In case of scheduling the flag must be cleared and restored after
 * returning from schedule as the task might move to a different CPU.
 */
static __always_inline bool get_and_clear_inhcall(void)
{
	bool inhcall = __this_cpu_read(xen_in_preemptible_hcall);

	__this_cpu_write(xen_in_preemptible_hcall, false);
	return inhcall;
}

static __always_inline void restore_inhcall(bool inhcall)
{
	__this_cpu_write(xen_in_preemptible_hcall, inhcall);
}
#else
static __always_inline bool get_and_clear_inhcall(void) { return false; }
static __always_inline void restore_inhcall(bool inhcall) { }
#endif

static void __xen_pv_evtchn_do_upcall(struct pt_regs *regs)
{
	struct pt_regs *old_regs = set_irq_regs(regs);

	inc_irq_stat(irq_hv_callback_count);

	xen_evtchn_do_upcall();

	set_irq_regs(old_regs);
}

__visible noinstr void xen_pv_evtchn_do_upcall(struct pt_regs *regs)
{
	irqentry_state_t state = irqentry_enter(regs);
	bool inhcall;

	instrumentation_begin();
	run_sysvec_on_irqstack_cond(__xen_pv_evtchn_do_upcall, regs);

	inhcall = get_and_clear_inhcall();
	if (inhcall && !WARN_ON_ONCE(state.exit_rcu)) {
		irqentry_exit_cond_resched();
		instrumentation_end();
		restore_inhcall(inhcall);
	} else {
		instrumentation_end();
		irqentry_exit(regs, state);
	}
}
#endif /* CONFIG_XEN_PV */