The conversion of X86 syscall, interrupt and exception entry/exit handling

to the generic code. Pretty much a straight forward 1:1 conversion plus the
 consolidation of the KVM handling of pending work before entering guest
 mode.
 -----BEGIN PGP SIGNATURE-----
 
 iQJHBAABCgAxFiEEQp8+kY+LLUocC4bMphj1TA10mKEFAl8pEFgTHHRnbHhAbGlu
 dXRyb25peC5kZQAKCRCmGPVMDXSYocEwD/474Eb7LzZ8yahyUBirWJP3k3qzgs9j
 dZUxqB6LNuDOstEyTGLPdx1dmQP2vHbFfjoM7YBOH37EGcHsqjGliLvn2Y05ZD7O
 6kYwjz6qVnJcm3IMtfSUn/8LkfO5pGUdKd3U5ngDmPLpkeaQ4nPKqiO0uIb0wzwa
 cO7l10tG4YjMCWQxPNIaOh8kncLieQBediJPFjkQjV+Fh33kSU3LWTl3fccz6b5+
 mgSUFL0qjQpp+Nl7lCaDQQiAop9GTUETfDtximRydZauiM2NpCfz+QBmQzq50Xv1
 G3DWZoBIZBjmWJUgfSmS/s4GOYkBTBnT/fUcZmIDcgdRwvtEvRzIhcP87/wn7P3N
 UKpLdHqmvA0BFDXZbNZgS362++29pj5Lnb+u3QbWSKQ9UqHN0NUlSY4wzfTLXsGp
 Mzpp4TW0u/8kyOlo7wK3lVDgNJaPG31aiNVuDPgLe4cEluO5cq7/7g2GcFBqF1Ly
 SqNGD1IccteNQTNvDopczPy7qUl5Lal+Ia06szNSPR48gLrvhSWdyYr2i1sD7vx4
 hAhR0Hsi9dacGv46TrRw1OdDzq9bOW68G8GIgLJgDXaayPXLnx6TQEUjzQtIkE/i
 ydTPUarp5QOFByt+RBjI90ZcW4RuLgMTOEVONPXtSn8IoCP2Kdg9u3gD9AmUW3Q2
 JFkKMiSiJPGxlw==
 =84y7
 -----END PGP SIGNATURE-----

Merge tag 'x86-entry-2020-08-04' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 conversion to generic entry code from Thomas Gleixner:
 "The conversion of X86 syscall, interrupt and exception entry/exit
  handling to the generic code.

  Pretty much a straight-forward 1:1 conversion plus the consolidation
  of the KVM handling of pending work before entering guest mode"

* tag 'x86-entry-2020-08-04' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/kvm: Use __xfer_to_guest_mode_work_pending() in kvm_run_vcpu()
  x86/kvm: Use generic xfer to guest work function
  x86/entry: Cleanup idtentry_enter/exit
  x86/entry: Use generic interrupt entry/exit code
  x86/entry: Cleanup idtentry_entry/exit_user
  x86/entry: Use generic syscall exit functionality
  x86/entry: Use generic syscall entry function
  x86/ptrace: Provide pt_regs helper for entry/exit
  x86/entry: Move user return notifier out of loop
  x86/entry: Consolidate 32/64 bit syscall entry
  x86/entry: Consolidate check_user_regs()
  x86: Correct noinstr qualifiers
  x86/idtentry: Remove stale comment
This commit is contained in:
Linus Torvalds 2020-08-04 21:05:46 -07:00
commit 125cfa0d4d
18 changed files with 174 additions and 669 deletions

View File

@ -115,6 +115,7 @@ config X86
select GENERIC_CPU_AUTOPROBE
select GENERIC_CPU_VULNERABILITIES
select GENERIC_EARLY_IOREMAP
select GENERIC_ENTRY
select GENERIC_FIND_FIRST_BIT
select GENERIC_IOMAP
select GENERIC_IRQ_EFFECTIVE_AFF_MASK if SMP

View File

@ -10,20 +10,13 @@
#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/tracehook.h>
#include <linux/audit.h>
#include <linux/seccomp.h>
#include <linux/signal.h>
#include <linux/export.h>
#include <linux/context_tracking.h>
#include <linux/user-return-notifier.h>
#include <linux/nospec.h>
#include <linux/uprobes.h>
#include <linux/livepatch.h>
#include <linux/syscalls.h>
#include <linux/uaccess.h>
@ -42,343 +35,12 @@
#include <asm/syscall.h>
#include <asm/irq_stack.h>
#define CREATE_TRACE_POINTS
#include <trace/events/syscalls.h>
/* Check that the stack and regs on entry from user mode are sane. */
static noinstr void check_user_regs(struct pt_regs *regs)
{
if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) {
/*
* Make sure that the entry code gave us a sensible EFLAGS
* register. Native because we want to check the actual CPU
* state, not the interrupt state as imagined by Xen.
*/
unsigned long flags = native_save_fl();
WARN_ON_ONCE(flags & (X86_EFLAGS_AC | X86_EFLAGS_DF |
X86_EFLAGS_NT));
/* We think we came from user mode. Make sure pt_regs agrees. */
WARN_ON_ONCE(!user_mode(regs));
/*
* All entries from user mode (except #DF) should be on the
* normal thread stack and should have user pt_regs in the
* correct location.
*/
WARN_ON_ONCE(!on_thread_stack());
WARN_ON_ONCE(regs != task_pt_regs(current));
}
}
#ifdef CONFIG_CONTEXT_TRACKING
/**
* enter_from_user_mode - Establish state when coming from user mode
*
* Syscall entry disables interrupts, but user mode is traced as interrupts
* enabled. Also with NO_HZ_FULL RCU might be idle.
*
* 1) Tell lockdep that interrupts are disabled
* 2) Invoke context tracking if enabled to reactivate RCU
* 3) Trace interrupts off state
*/
static noinstr void enter_from_user_mode(void)
{
enum ctx_state state = ct_state();
lockdep_hardirqs_off(CALLER_ADDR0);
user_exit_irqoff();
instrumentation_begin();
CT_WARN_ON(state != CONTEXT_USER);
trace_hardirqs_off_finish();
instrumentation_end();
}
#else
static __always_inline void enter_from_user_mode(void)
{
lockdep_hardirqs_off(CALLER_ADDR0);
instrumentation_begin();
trace_hardirqs_off_finish();
instrumentation_end();
}
#endif
/**
* exit_to_user_mode - Fixup state when exiting to user mode
*
* Syscall exit enables interrupts, but the kernel state is interrupts
* disabled when this is invoked. Also tell RCU about it.
*
* 1) Trace interrupts on state
* 2) Invoke context tracking if enabled to adjust RCU state
* 3) Clear CPU buffers if CPU is affected by MDS and the migitation is on.
* 4) Tell lockdep that interrupts are enabled
*/
static __always_inline void exit_to_user_mode(void)
{
instrumentation_begin();
trace_hardirqs_on_prepare();
lockdep_hardirqs_on_prepare(CALLER_ADDR0);
instrumentation_end();
user_enter_irqoff();
mds_user_clear_cpu_buffers();
lockdep_hardirqs_on(CALLER_ADDR0);
}
static void do_audit_syscall_entry(struct pt_regs *regs, u32 arch)
{
#ifdef CONFIG_X86_64
if (arch == AUDIT_ARCH_X86_64) {
audit_syscall_entry(regs->orig_ax, regs->di,
regs->si, regs->dx, regs->r10);
} else
#endif
{
audit_syscall_entry(regs->orig_ax, regs->bx,
regs->cx, regs->dx, regs->si);
}
}
/*
* Returns the syscall nr to run (which should match regs->orig_ax) or -1
* to skip the syscall.
*/
static long syscall_trace_enter(struct pt_regs *regs)
{
u32 arch = in_ia32_syscall() ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64;
struct thread_info *ti = current_thread_info();
unsigned long ret = 0;
u32 work;
work = READ_ONCE(ti->flags);
if (work & (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU)) {
ret = tracehook_report_syscall_entry(regs);
if (ret || (work & _TIF_SYSCALL_EMU))
return -1L;
}
#ifdef CONFIG_SECCOMP
/*
* Do seccomp after ptrace, to catch any tracer changes.
*/
if (work & _TIF_SECCOMP) {
struct seccomp_data sd;
sd.arch = arch;
sd.nr = regs->orig_ax;
sd.instruction_pointer = regs->ip;
#ifdef CONFIG_X86_64
if (arch == AUDIT_ARCH_X86_64) {
sd.args[0] = regs->di;
sd.args[1] = regs->si;
sd.args[2] = regs->dx;
sd.args[3] = regs->r10;
sd.args[4] = regs->r8;
sd.args[5] = regs->r9;
} else
#endif
{
sd.args[0] = regs->bx;
sd.args[1] = regs->cx;
sd.args[2] = regs->dx;
sd.args[3] = regs->si;
sd.args[4] = regs->di;
sd.args[5] = regs->bp;
}
ret = __secure_computing(&sd);
if (ret == -1)
return ret;
}
#endif
if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
trace_sys_enter(regs, regs->orig_ax);
do_audit_syscall_entry(regs, arch);
return ret ?: regs->orig_ax;
}
#define EXIT_TO_USERMODE_LOOP_FLAGS \
(_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE | \
_TIF_NEED_RESCHED | _TIF_USER_RETURN_NOTIFY | _TIF_PATCH_PENDING)
static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags)
{
/*
* In order to return to user mode, we need to have IRQs off with
* none of EXIT_TO_USERMODE_LOOP_FLAGS set. Several of these flags
* can be set at any time on preemptible kernels if we have IRQs on,
* so we need to loop. Disabling preemption wouldn't help: doing the
* work to clear some of the flags can sleep.
*/
while (true) {
/* We have work to do. */
local_irq_enable();
if (cached_flags & _TIF_NEED_RESCHED)
schedule();
if (cached_flags & _TIF_UPROBE)
uprobe_notify_resume(regs);
if (cached_flags & _TIF_PATCH_PENDING)
klp_update_patch_state(current);
/* deal with pending signal delivery */
if (cached_flags & _TIF_SIGPENDING)
do_signal(regs);
if (cached_flags & _TIF_NOTIFY_RESUME) {
clear_thread_flag(TIF_NOTIFY_RESUME);
tracehook_notify_resume(regs);
rseq_handle_notify_resume(NULL, regs);
}
if (cached_flags & _TIF_USER_RETURN_NOTIFY)
fire_user_return_notifiers();
/* Disable IRQs and retry */
local_irq_disable();
cached_flags = READ_ONCE(current_thread_info()->flags);
if (!(cached_flags & EXIT_TO_USERMODE_LOOP_FLAGS))
break;
}
}
static void __prepare_exit_to_usermode(struct pt_regs *regs)
{
struct thread_info *ti = current_thread_info();
u32 cached_flags;
addr_limit_user_check();
lockdep_assert_irqs_disabled();
lockdep_sys_exit();
cached_flags = READ_ONCE(ti->flags);
if (unlikely(cached_flags & EXIT_TO_USERMODE_LOOP_FLAGS))
exit_to_usermode_loop(regs, cached_flags);
/* Reload ti->flags; we may have rescheduled above. */
cached_flags = READ_ONCE(ti->flags);
if (unlikely(cached_flags & _TIF_IO_BITMAP))
tss_update_io_bitmap();
fpregs_assert_state_consistent();
if (unlikely(cached_flags & _TIF_NEED_FPU_LOAD))
switch_fpu_return();
#ifdef CONFIG_COMPAT
/*
* Compat syscalls set TS_COMPAT. Make sure we clear it before
* returning to user mode. We need to clear it *after* signal
* handling, because syscall restart has a fixup for compat
* syscalls. The fixup is exercised by the ptrace_syscall_32
* selftest.
*
* We also need to clear TS_REGS_POKED_I386: the 32-bit tracer
* special case only applies after poking regs and before the
* very next return to user mode.
*/
ti->status &= ~(TS_COMPAT|TS_I386_REGS_POKED);
#endif
}
static noinstr void prepare_exit_to_usermode(struct pt_regs *regs)
{
instrumentation_begin();
__prepare_exit_to_usermode(regs);
instrumentation_end();
exit_to_user_mode();
}
#define SYSCALL_EXIT_WORK_FLAGS \
(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
_TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT)
static void syscall_slow_exit_work(struct pt_regs *regs, u32 cached_flags)
{
bool step;
audit_syscall_exit(regs);
if (cached_flags & _TIF_SYSCALL_TRACEPOINT)
trace_sys_exit(regs, regs->ax);
/*
* If TIF_SYSCALL_EMU is set, we only get here because of
* TIF_SINGLESTEP (i.e. this is PTRACE_SYSEMU_SINGLESTEP).
* We already reported this syscall instruction in
* syscall_trace_enter().
*/
step = unlikely(
(cached_flags & (_TIF_SINGLESTEP | _TIF_SYSCALL_EMU))
== _TIF_SINGLESTEP);
if (step || cached_flags & _TIF_SYSCALL_TRACE)
tracehook_report_syscall_exit(regs, step);
}
static void __syscall_return_slowpath(struct pt_regs *regs)
{
struct thread_info *ti = current_thread_info();
u32 cached_flags = READ_ONCE(ti->flags);
CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
if (IS_ENABLED(CONFIG_PROVE_LOCKING) &&
WARN(irqs_disabled(), "syscall %ld left IRQs disabled", regs->orig_ax))
local_irq_enable();
rseq_syscall(regs);
/*
* First do one-time work. If these work items are enabled, we
* want to run them exactly once per syscall exit with IRQs on.
*/
if (unlikely(cached_flags & SYSCALL_EXIT_WORK_FLAGS))
syscall_slow_exit_work(regs, cached_flags);
local_irq_disable();
__prepare_exit_to_usermode(regs);
}
/*
* Called with IRQs on and fully valid regs. Returns with IRQs off in a
* state such that we can immediately switch to user mode.
*/
__visible noinstr void syscall_return_slowpath(struct pt_regs *regs)
{
instrumentation_begin();
__syscall_return_slowpath(regs);
instrumentation_end();
exit_to_user_mode();
}
#ifdef CONFIG_X86_64
__visible noinstr void do_syscall_64(unsigned long nr, struct pt_regs *regs)
{
struct thread_info *ti;
nr = syscall_enter_from_user_mode(regs, nr);
check_user_regs(regs);
enter_from_user_mode();
instrumentation_begin();
local_irq_enable();
ti = current_thread_info();
if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY)
nr = syscall_trace_enter(regs);
if (likely(nr < NR_syscalls)) {
nr = array_index_nospec(nr, NR_syscalls);
regs->ax = sys_call_table[nr](regs);
@ -390,66 +52,55 @@ __visible noinstr void do_syscall_64(unsigned long nr, struct pt_regs *regs)
regs->ax = x32_sys_call_table[nr](regs);
#endif
}
__syscall_return_slowpath(regs);
instrumentation_end();
exit_to_user_mode();
syscall_exit_to_user_mode(regs);
}
#endif
#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
/*
* Does a 32-bit syscall. Called with IRQs on in CONTEXT_KERNEL. Does
* all entry and exit work and returns with IRQs off. This function is
* extremely hot in workloads that use it, and it's usually called from
* do_fast_syscall_32, so forcibly inline it to improve performance.
*/
static void do_syscall_32_irqs_on(struct pt_regs *regs)
static __always_inline unsigned int syscall_32_enter(struct pt_regs *regs)
{
struct thread_info *ti = current_thread_info();
unsigned int nr = (unsigned int)regs->orig_ax;
#ifdef CONFIG_IA32_EMULATION
ti->status |= TS_COMPAT;
#endif
if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY) {
/*
* Subtlety here: if ptrace pokes something larger than
* 2^32-1 into orig_ax, this truncates it. This may or
* may not be necessary, but it matches the old asm
* behavior.
*/
nr = syscall_trace_enter(regs);
}
if (IS_ENABLED(CONFIG_IA32_EMULATION))
current_thread_info()->status |= TS_COMPAT;
/*
* Subtlety here: if ptrace pokes something larger than 2^32-1 into
* orig_ax, the unsigned int return value truncates it. This may
* or may not be necessary, but it matches the old asm behavior.
*/
return (unsigned int)syscall_enter_from_user_mode(regs, nr);
}
/*
* Invoke a 32-bit syscall. Called with IRQs on in CONTEXT_KERNEL.
*/
static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs,
unsigned int nr)
{
if (likely(nr < IA32_NR_syscalls)) {
instrumentation_begin();
nr = array_index_nospec(nr, IA32_NR_syscalls);
regs->ax = ia32_sys_call_table[nr](regs);
instrumentation_end();
}
__syscall_return_slowpath(regs);
}
/* Handles int $0x80 */
__visible noinstr void do_int80_syscall_32(struct pt_regs *regs)
{
check_user_regs(regs);
unsigned int nr = syscall_32_enter(regs);
enter_from_user_mode();
instrumentation_begin();
local_irq_enable();
do_syscall_32_irqs_on(regs);
instrumentation_end();
exit_to_user_mode();
do_syscall_32_irqs_on(regs, nr);
syscall_exit_to_user_mode(regs);
}
static bool __do_fast_syscall_32(struct pt_regs *regs)
static noinstr bool __do_fast_syscall_32(struct pt_regs *regs)
{
unsigned int nr = syscall_32_enter(regs);
int res;
instrumentation_begin();
/* Fetch EBP from where the vDSO stashed it. */
if (IS_ENABLED(CONFIG_X86_64)) {
/*
@ -462,17 +113,18 @@ static bool __do_fast_syscall_32(struct pt_regs *regs)
res = get_user(*(u32 *)&regs->bp,
(u32 __user __force *)(unsigned long)(u32)regs->sp);
}
instrumentation_end();
if (res) {
/* User code screwed up. */
regs->ax = -EFAULT;
local_irq_disable();
__prepare_exit_to_usermode(regs);
syscall_exit_to_user_mode(regs);
return false;
}
/* Now this is just like a normal syscall. */
do_syscall_32_irqs_on(regs);
do_syscall_32_irqs_on(regs, nr);
syscall_exit_to_user_mode(regs);
return true;
}
@ -485,9 +137,6 @@ __visible noinstr long do_fast_syscall_32(struct pt_regs *regs)
*/
unsigned long landing_pad = (unsigned long)current->mm->context.vdso +
vdso_image_32.sym_int80_landing_pad;
bool success;
check_user_regs(regs);
/*
* SYSENTER loses EIP, and even SYSCALL32 needs us to skip forward
@ -496,17 +145,8 @@ __visible noinstr long do_fast_syscall_32(struct pt_regs *regs)
*/
regs->ip = landing_pad;
enter_from_user_mode();
instrumentation_begin();
local_irq_enable();
success = __do_fast_syscall_32(regs);
instrumentation_end();
exit_to_user_mode();
/* If it failed, keep it simple: use IRET. */
if (!success)
/* Invoke the syscall. If it failed, keep it simple: use IRET. */
if (!__do_fast_syscall_32(regs))
return 0;
#ifdef CONFIG_X86_64
@ -558,204 +198,6 @@ SYSCALL_DEFINE0(ni_syscall)
return -ENOSYS;
}
/**
* idtentry_enter - Handle state tracking on ordinary idtentries
* @regs: Pointer to pt_regs of interrupted context
*
* Invokes:
* - lockdep irqflag state tracking as low level ASM entry disabled
* interrupts.
*
* - Context tracking if the exception hit user mode.
*
* - The hardirq tracer to keep the state consistent as low level ASM
* entry disabled interrupts.
*
* As a precondition, this requires that the entry came from user mode,
* idle, or a kernel context in which RCU is watching.
*
* For kernel mode entries RCU handling is done conditional. If RCU is
* watching then the only RCU requirement is to check whether the tick has
* to be restarted. If RCU is not watching then rcu_irq_enter() has to be
* invoked on entry and rcu_irq_exit() on exit.
*
* Avoiding the rcu_irq_enter/exit() calls is an optimization but also
* solves the problem of kernel mode pagefaults which can schedule, which
* is not possible after invoking rcu_irq_enter() without undoing it.
*
* For user mode entries enter_from_user_mode() must be invoked to
* establish the proper context for NOHZ_FULL. Otherwise scheduling on exit
* would not be possible.
*
* Returns: An opaque object that must be passed to idtentry_exit()
*
* The return value must be fed into the state argument of
* idtentry_exit().
*/
noinstr idtentry_state_t idtentry_enter(struct pt_regs *regs)
{
idtentry_state_t ret = {
.exit_rcu = false,
};
if (user_mode(regs)) {
check_user_regs(regs);
enter_from_user_mode();
return ret;
}
/*
* If this entry hit the idle task invoke rcu_irq_enter() whether
* RCU is watching or not.
*
* Interupts can nest when the first interrupt invokes softirq
* processing on return which enables interrupts.
*
* Scheduler ticks in the idle task can mark quiescent state and
* terminate a grace period, if and only if the timer interrupt is
* not nested into another interrupt.
*
* Checking for __rcu_is_watching() here would prevent the nesting
* interrupt to invoke rcu_irq_enter(). If that nested interrupt is
* the tick then rcu_flavor_sched_clock_irq() would wrongfully
* assume that it is the first interupt and eventually claim
* quiescient state and end grace periods prematurely.
*
* Unconditionally invoke rcu_irq_enter() so RCU state stays
* consistent.
*
* TINY_RCU does not support EQS, so let the compiler eliminate
* this part when enabled.
*/
if (!IS_ENABLED(CONFIG_TINY_RCU) && is_idle_task(current)) {
/*
* If RCU is not watching then the same careful
* sequence vs. lockdep and tracing is required
* as in enter_from_user_mode().
*/
lockdep_hardirqs_off(CALLER_ADDR0);
rcu_irq_enter();
instrumentation_begin();
trace_hardirqs_off_finish();
instrumentation_end();
ret.exit_rcu = true;
return ret;
}
/*
* If RCU is watching then RCU only wants to check whether it needs
* to restart the tick in NOHZ mode. rcu_irq_enter_check_tick()
* already contains a warning when RCU is not watching, so no point
* in having another one here.
*/
instrumentation_begin();
rcu_irq_enter_check_tick();
/* Use the combo lockdep/tracing function */
trace_hardirqs_off();
instrumentation_end();
return ret;
}
static void idtentry_exit_cond_resched(struct pt_regs *regs, bool may_sched)
{
if (may_sched && !preempt_count()) {
/* Sanity check RCU and thread stack */
rcu_irq_exit_check_preempt();
if (IS_ENABLED(CONFIG_DEBUG_ENTRY))
WARN_ON_ONCE(!on_thread_stack());
if (need_resched())
preempt_schedule_irq();
}
/* Covers both tracing and lockdep */
trace_hardirqs_on();
}
/**
* idtentry_exit - Handle return from exception that used idtentry_enter()
* @regs: Pointer to pt_regs (exception entry regs)
* @state: Return value from matching call to idtentry_enter()
*
* Depending on the return target (kernel/user) this runs the necessary
* preemption and work checks if possible and reguired and returns to
* the caller with interrupts disabled and no further work pending.
*
* This is the last action before returning to the low level ASM code which
* just needs to return to the appropriate context.
*
* Counterpart to idtentry_enter(). The return value of the entry
* function must be fed into the @state argument.
*/
noinstr void idtentry_exit(struct pt_regs *regs, idtentry_state_t state)
{
lockdep_assert_irqs_disabled();
/* Check whether this returns to user mode */
if (user_mode(regs)) {
prepare_exit_to_usermode(regs);
} else if (regs->flags & X86_EFLAGS_IF) {
/*
* If RCU was not watching on entry this needs to be done
* carefully and needs the same ordering of lockdep/tracing
* and RCU as the return to user mode path.
*/
if (state.exit_rcu) {
instrumentation_begin();
/* Tell the tracer that IRET will enable interrupts */
trace_hardirqs_on_prepare();
lockdep_hardirqs_on_prepare(CALLER_ADDR0);
instrumentation_end();
rcu_irq_exit();
lockdep_hardirqs_on(CALLER_ADDR0);
return;
}
instrumentation_begin();
idtentry_exit_cond_resched(regs, IS_ENABLED(CONFIG_PREEMPTION));
instrumentation_end();
} else {
/*
* IRQ flags state is correct already. Just tell RCU if it
* was not watching on entry.
*/
if (state.exit_rcu)
rcu_irq_exit();
}
}
/**
* idtentry_enter_user - Handle state tracking on idtentry from user mode
* @regs: Pointer to pt_regs of interrupted context
*
* Invokes enter_from_user_mode() to establish the proper context for
* NOHZ_FULL. Otherwise scheduling on exit would not be possible.
*/
noinstr void idtentry_enter_user(struct pt_regs *regs)
{
check_user_regs(regs);
enter_from_user_mode();
}
/**
* idtentry_exit_user - Handle return from exception to user mode
* @regs: Pointer to pt_regs (exception entry regs)
*
* Runs the necessary preemption and work checks and returns to the caller
* with interrupts disabled and no further work pending.
*
* This is the last action before returning to the low level ASM code which
* just needs to return to the appropriate context.
*
* Counterpart to idtentry_enter_user().
*/
noinstr void idtentry_exit_user(struct pt_regs *regs)
{
lockdep_assert_irqs_disabled();
prepare_exit_to_usermode(regs);
}
noinstr bool idtentry_enter_nmi(struct pt_regs *regs)
{
bool irq_state = lockdep_hardirqs_enabled();
@ -840,9 +282,9 @@ __visible noinstr void xen_pv_evtchn_do_upcall(struct pt_regs *regs)
{
struct pt_regs *old_regs;
bool inhcall;
idtentry_state_t state;
irqentry_state_t state;
state = idtentry_enter(regs);
state = irqentry_enter(regs);
old_regs = set_irq_regs(regs);
instrumentation_begin();
@ -854,11 +296,11 @@ __visible noinstr void xen_pv_evtchn_do_upcall(struct pt_regs *regs)
inhcall = get_and_clear_inhcall();
if (inhcall && !WARN_ON_ONCE(state.exit_rcu)) {
instrumentation_begin();
idtentry_exit_cond_resched(regs, true);
irqentry_exit_cond_resched();
instrumentation_end();
restore_inhcall(inhcall);
} else {
idtentry_exit(regs, state);
irqentry_exit(regs, state);
}
}
#endif /* CONFIG_XEN_PV */

View File

@ -846,7 +846,7 @@ SYM_CODE_START(ret_from_fork)
2:
/* When we fork, we trace the syscall return in the child, too. */
movl %esp, %eax
call syscall_return_slowpath
call syscall_exit_to_user_mode
jmp .Lsyscall_32_done
/* kernel thread */

View File

@ -283,7 +283,7 @@ SYM_CODE_START(ret_from_fork)
2:
UNWIND_HINT_REGS
movq %rsp, %rdi
call syscall_return_slowpath /* returns with IRQs disabled */
call syscall_exit_to_user_mode /* returns with IRQs disabled */
jmp swapgs_restore_regs_and_return_to_usermode
1:

View File

@ -0,0 +1,76 @@
/* SPDX-License-Identifier: GPL-2.0-only */
#ifndef _ASM_X86_ENTRY_COMMON_H
#define _ASM_X86_ENTRY_COMMON_H
#include <linux/user-return-notifier.h>
#include <asm/nospec-branch.h>
#include <asm/io_bitmap.h>
#include <asm/fpu/api.h>
/* Check that the stack and regs on entry from user mode are sane. */
static __always_inline void arch_check_user_regs(struct pt_regs *regs)
{
if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) {
/*
* Make sure that the entry code gave us a sensible EFLAGS
* register. Native because we want to check the actual CPU
* state, not the interrupt state as imagined by Xen.
*/
unsigned long flags = native_save_fl();
WARN_ON_ONCE(flags & (X86_EFLAGS_AC | X86_EFLAGS_DF |
X86_EFLAGS_NT));
/* We think we came from user mode. Make sure pt_regs agrees. */
WARN_ON_ONCE(!user_mode(regs));
/*
* All entries from user mode (except #DF) should be on the
* normal thread stack and should have user pt_regs in the
* correct location.
*/
WARN_ON_ONCE(!on_thread_stack());
WARN_ON_ONCE(regs != task_pt_regs(current));
}
}
#define arch_check_user_regs arch_check_user_regs
#define ARCH_SYSCALL_EXIT_WORK (_TIF_SINGLESTEP)
static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
unsigned long ti_work)
{
if (ti_work & _TIF_USER_RETURN_NOTIFY)
fire_user_return_notifiers();
if (unlikely(ti_work & _TIF_IO_BITMAP))
tss_update_io_bitmap();
fpregs_assert_state_consistent();
if (unlikely(ti_work & _TIF_NEED_FPU_LOAD))
switch_fpu_return();
#ifdef CONFIG_COMPAT
/*
* Compat syscalls set TS_COMPAT. Make sure we clear it before
* returning to user mode. We need to clear it *after* signal
* handling, because syscall restart has a fixup for compat
* syscalls. The fixup is exercised by the ptrace_syscall_32
* selftest.
*
* We also need to clear TS_REGS_POKED_I386: the 32-bit tracer
* special case only applies after poking regs and before the
* very next return to user mode.
*/
current_thread_info()->status &= ~(TS_COMPAT | TS_I386_REGS_POKED);
#endif
}
#define arch_exit_to_user_mode_prepare arch_exit_to_user_mode_prepare
static __always_inline void arch_exit_to_user_mode(void)
{
mds_user_clear_cpu_buffers();
}
#define arch_exit_to_user_mode arch_exit_to_user_mode
#endif

View File

@ -6,20 +6,11 @@
#include <asm/trapnr.h>
#ifndef __ASSEMBLY__
#include <linux/entry-common.h>
#include <linux/hardirq.h>
#include <asm/irq_stack.h>
void idtentry_enter_user(struct pt_regs *regs);
void idtentry_exit_user(struct pt_regs *regs);
typedef struct idtentry_state {
bool exit_rcu;
} idtentry_state_t;
idtentry_state_t idtentry_enter(struct pt_regs *regs);
void idtentry_exit(struct pt_regs *regs, idtentry_state_t state);
bool idtentry_enter_nmi(struct pt_regs *regs);
void idtentry_exit_nmi(struct pt_regs *regs, bool irq_state);
@ -52,8 +43,8 @@ void idtentry_exit_nmi(struct pt_regs *regs, bool irq_state);
* The macro is written so it acts as function definition. Append the
* body with a pair of curly brackets.
*
* idtentry_enter() contains common code which has to be invoked before
* arbitrary code in the body. idtentry_exit() contains common code
* irqentry_enter() contains common code which has to be invoked before
* arbitrary code in the body. irqentry_exit() contains common code
* which has to run before returning to the low level assembly code.
*/
#define DEFINE_IDTENTRY(func) \
@ -61,12 +52,12 @@ static __always_inline void __##func(struct pt_regs *regs); \
\
__visible noinstr void func(struct pt_regs *regs) \
{ \
idtentry_state_t state = idtentry_enter(regs); \
irqentry_state_t state = irqentry_enter(regs); \
\
instrumentation_begin(); \
__##func (regs); \
instrumentation_end(); \
idtentry_exit(regs, state); \
irqentry_exit(regs, state); \
} \
\
static __always_inline void __##func(struct pt_regs *regs)
@ -108,12 +99,12 @@ static __always_inline void __##func(struct pt_regs *regs, \
__visible noinstr void func(struct pt_regs *regs, \
unsigned long error_code) \
{ \
idtentry_state_t state = idtentry_enter(regs); \
irqentry_state_t state = irqentry_enter(regs); \
\
instrumentation_begin(); \
__##func (regs, error_code); \
instrumentation_end(); \
idtentry_exit(regs, state); \
irqentry_exit(regs, state); \
} \
\
static __always_inline void __##func(struct pt_regs *regs, \
@ -168,7 +159,7 @@ __visible noinstr void func(struct pt_regs *regs)
* body with a pair of curly brackets.
*
* Contrary to DEFINE_IDTENTRY_ERRORCODE() this does not invoke the
* idtentry_enter/exit() helpers before and after the body invocation. This
* irqentry_enter/exit() helpers before and after the body invocation. This
* needs to be done in the body itself if applicable. Use if extra work
* is required before the enter/exit() helpers are invoked.
*/
@ -194,11 +185,9 @@ __visible noinstr void func(struct pt_regs *regs, unsigned long error_code)
* to the function as error_code argument which needs to be truncated
* to an u8 because the push is sign extending.
*
* On 64-bit idtentry_enter/exit() are invoked in the ASM entry code before
* and after switching to the interrupt stack. On 32-bit this happens in C.
*
* irq_enter/exit_rcu() are invoked before the function body and the
* KVM L1D flush request is set.
* KVM L1D flush request is set. Stack switching to the interrupt stack
* has to be done in the function body if necessary.
*/
#define DEFINE_IDTENTRY_IRQ(func) \
static __always_inline void __##func(struct pt_regs *regs, u8 vector); \
@ -206,7 +195,7 @@ static __always_inline void __##func(struct pt_regs *regs, u8 vector); \
__visible noinstr void func(struct pt_regs *regs, \
unsigned long error_code) \
{ \
idtentry_state_t state = idtentry_enter(regs); \
irqentry_state_t state = irqentry_enter(regs); \
\
instrumentation_begin(); \
irq_enter_rcu(); \
@ -214,7 +203,7 @@ __visible noinstr void func(struct pt_regs *regs, \
__##func (regs, (u8)error_code); \
irq_exit_rcu(); \
instrumentation_end(); \
idtentry_exit(regs, state); \
irqentry_exit(regs, state); \
} \
\
static __always_inline void __##func(struct pt_regs *regs, u8 vector)
@ -238,7 +227,7 @@ static __always_inline void __##func(struct pt_regs *regs, u8 vector)
* DEFINE_IDTENTRY_SYSVEC - Emit code for system vector IDT entry points
* @func: Function name of the entry point
*
* idtentry_enter/exit() and irq_enter/exit_rcu() are invoked before the
* irqentry_enter/exit() and irq_enter/exit_rcu() are invoked before the
* function body. KVM L1D flush request is set.
*
* Runs the function on the interrupt stack if the entry hit kernel mode
@ -248,7 +237,7 @@ static void __##func(struct pt_regs *regs); \
\
__visible noinstr void func(struct pt_regs *regs) \
{ \
idtentry_state_t state = idtentry_enter(regs); \
irqentry_state_t state = irqentry_enter(regs); \
\
instrumentation_begin(); \
irq_enter_rcu(); \
@ -256,7 +245,7 @@ __visible noinstr void func(struct pt_regs *regs) \
run_on_irqstack_cond(__##func, regs, regs); \
irq_exit_rcu(); \
instrumentation_end(); \
idtentry_exit(regs, state); \
irqentry_exit(regs, state); \
} \
\
static noinline void __##func(struct pt_regs *regs)
@ -277,7 +266,7 @@ static __always_inline void __##func(struct pt_regs *regs); \
\
__visible noinstr void func(struct pt_regs *regs) \
{ \
idtentry_state_t state = idtentry_enter(regs); \
irqentry_state_t state = irqentry_enter(regs); \
\
instrumentation_begin(); \
__irq_enter_raw(); \
@ -285,7 +274,7 @@ __visible noinstr void func(struct pt_regs *regs) \
__##func (regs); \
__irq_exit_raw(); \
instrumentation_end(); \
idtentry_exit(regs, state); \
irqentry_exit(regs, state); \
} \
\
static __always_inline void __##func(struct pt_regs *regs)

View File

@ -209,6 +209,11 @@ static inline void user_stack_pointer_set(struct pt_regs *regs,
regs->sp = val;
}
static __always_inline bool regs_irqs_disabled(struct pt_regs *regs)
{
return !(regs->flags & X86_EFLAGS_IF);
}
/* Query offset/name of register from its name/offset */
extern int regs_query_register_offset(const char *name);
extern const char *regs_query_register_name(unsigned int offset);

View File

@ -35,7 +35,6 @@ typedef sigset_t compat_sigset_t;
#endif /* __ASSEMBLY__ */
#include <uapi/asm/signal.h>
#ifndef __ASSEMBLY__
extern void do_signal(struct pt_regs *regs);
#define __ARCH_HAS_SA_RESTORER

View File

@ -133,11 +133,6 @@ struct thread_info {
#define _TIF_X32 (1 << TIF_X32)
#define _TIF_FSCHECK (1 << TIF_FSCHECK)
/* Work to do before invoking the actual syscall. */
#define _TIF_WORK_SYSCALL_ENTRY \
(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | _TIF_SYSCALL_AUDIT | \
_TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT)
/* flags to check in __switch_to() */
#define _TIF_WORK_CTXSW_BASE \
(_TIF_NOCPUID | _TIF_NOTSC | _TIF_BLOCKSTEP | \

View File

@ -1047,7 +1047,7 @@ static __always_inline int patch_cmp(const void *key, const void *elt)
return 0;
}
int noinstr poke_int3_handler(struct pt_regs *regs)
noinstr int poke_int3_handler(struct pt_regs *regs)
{
struct bp_patching_desc *desc;
struct text_poke_loc *tp;

View File

@ -1215,7 +1215,7 @@ static void kill_me_maybe(struct callback_head *cb)
* backing the user stack, tracing that reads the user stack will cause
* potentially infinite recursion.
*/
void noinstr do_machine_check(struct pt_regs *regs)
noinstr void do_machine_check(struct pt_regs *regs)
{
DECLARE_BITMAP(valid_banks, MAX_NR_BANKS);
DECLARE_BITMAP(toclear, MAX_NR_BANKS);
@ -1930,11 +1930,11 @@ static __always_inline void exc_machine_check_kernel(struct pt_regs *regs)
static __always_inline void exc_machine_check_user(struct pt_regs *regs)
{
idtentry_enter_user(regs);
irqentry_enter_from_user_mode(regs);
instrumentation_begin();
machine_check_vector(regs);
instrumentation_end();
idtentry_exit_user(regs);
irqentry_exit_to_user_mode(regs);
}
#ifdef CONFIG_X86_64

View File

@ -233,7 +233,7 @@ EXPORT_SYMBOL_GPL(kvm_read_and_reset_apf_flags);
noinstr bool __kvm_handle_async_pf(struct pt_regs *regs, u32 token)
{
u32 reason = kvm_read_and_reset_apf_flags();
idtentry_state_t state;
irqentry_state_t state;
switch (reason) {
case KVM_PV_REASON_PAGE_NOT_PRESENT:
@ -243,7 +243,7 @@ noinstr bool __kvm_handle_async_pf(struct pt_regs *regs, u32 token)
return false;
}
state = idtentry_enter(regs);
state = irqentry_enter(regs);
instrumentation_begin();
/*
@ -264,7 +264,7 @@ noinstr bool __kvm_handle_async_pf(struct pt_regs *regs, u32 token)
}
instrumentation_end();
idtentry_exit(regs, state);
irqentry_exit(regs, state);
return true;
}

View File

@ -25,6 +25,7 @@
#include <linux/user-return-notifier.h>
#include <linux/uprobes.h>
#include <linux/context_tracking.h>
#include <linux/entry-common.h>
#include <linux/syscalls.h>
#include <asm/processor.h>
@ -803,7 +804,7 @@ static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs)
* want to handle. Thus you cannot kill init even with a SIGKILL even by
* mistake.
*/
void do_signal(struct pt_regs *regs)
void arch_do_signal(struct pt_regs *regs)
{
struct ksignal ksig;

View File

@ -245,7 +245,7 @@ static noinstr bool handle_bug(struct pt_regs *regs)
DEFINE_IDTENTRY_RAW(exc_invalid_op)
{
idtentry_state_t state;
irqentry_state_t state;
/*
* We use UD2 as a short encoding for 'CALL __WARN', as such
@ -255,11 +255,11 @@ DEFINE_IDTENTRY_RAW(exc_invalid_op)
if (!user_mode(regs) && handle_bug(regs))
return;
state = idtentry_enter(regs);
state = irqentry_enter(regs);
instrumentation_begin();
handle_invalid_op(regs);
instrumentation_end();
idtentry_exit(regs, state);
irqentry_exit(regs, state);
}
DEFINE_IDTENTRY(exc_coproc_segment_overrun)
@ -638,18 +638,18 @@ DEFINE_IDTENTRY_RAW(exc_int3)
return;
/*
* idtentry_enter_user() uses static_branch_{,un}likely() and therefore
* can trigger INT3, hence poke_int3_handler() must be done
* before. If the entry came from kernel mode, then use nmi_enter()
* because the INT3 could have been hit in any context including
* NMI.
* irqentry_enter_from_user_mode() uses static_branch_{,un}likely()
* and therefore can trigger INT3, hence poke_int3_handler() must
* be done before. If the entry came from kernel mode, then use
* nmi_enter() because the INT3 could have been hit in any context
* including NMI.
*/
if (user_mode(regs)) {
idtentry_enter_user(regs);
irqentry_enter_from_user_mode(regs);
instrumentation_begin();
do_int3_user(regs);
instrumentation_end();
idtentry_exit_user(regs);
irqentry_exit_to_user_mode(regs);
} else {
bool irq_state = idtentry_enter_nmi(regs);
instrumentation_begin();
@ -895,13 +895,13 @@ static __always_inline void exc_debug_user(struct pt_regs *regs,
*/
WARN_ON_ONCE(!user_mode(regs));
idtentry_enter_user(regs);
irqentry_enter_from_user_mode(regs);
instrumentation_begin();
handle_debug(regs, dr6, true);
instrumentation_end();
idtentry_exit_user(regs);
irqentry_exit_to_user_mode(regs);
}
#ifdef CONFIG_X86_64

View File

@ -42,6 +42,7 @@ config KVM
select HAVE_KVM_MSI
select HAVE_KVM_CPU_RELAX_INTERCEPT
select HAVE_KVM_NO_POLL
select KVM_XFER_TO_GUEST_WORK
select KVM_GENERIC_DIRTYLOG_READ_PROTECT
select KVM_VFIO
select SRCU

View File

@ -27,6 +27,7 @@
#include <linux/slab.h>
#include <linux/tboot.h>
#include <linux/trace_events.h>
#include <linux/entry-kvm.h>
#include <asm/apic.h>
#include <asm/asm.h>
@ -5373,14 +5374,12 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
}
/*
* Note, return 1 and not 0, vcpu_run() is responsible for
* morphing the pending signal into the proper return code.
* Note, return 1 and not 0, vcpu_run() will invoke
* xfer_to_guest_mode() which will create a proper return
* code.
*/
if (signal_pending(current))
if (__xfer_to_guest_mode_work_pending())
return 1;
if (need_resched())
schedule();
}
return 1;

View File

@ -56,6 +56,7 @@
#include <linux/sched/stat.h>
#include <linux/sched/isolation.h>
#include <linux/mem_encrypt.h>
#include <linux/entry-kvm.h>
#include <trace/events/kvm.h>
@ -1587,7 +1588,7 @@ EXPORT_SYMBOL_GPL(kvm_emulate_wrmsr);
bool kvm_vcpu_exit_request(struct kvm_vcpu *vcpu)
{
return vcpu->mode == EXITING_GUEST_MODE || kvm_request_pending(vcpu) ||
need_resched() || signal_pending(current);
xfer_to_guest_mode_work_pending();
}
EXPORT_SYMBOL_GPL(kvm_vcpu_exit_request);
@ -8681,15 +8682,11 @@ static int vcpu_run(struct kvm_vcpu *vcpu)
break;
}
if (signal_pending(current)) {
r = -EINTR;
vcpu->run->exit_reason = KVM_EXIT_INTR;
++vcpu->stat.signal_exits;
break;
}
if (need_resched()) {
if (__xfer_to_guest_mode_work_pending()) {
srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
cond_resched();
r = xfer_to_guest_mode_handle_work(vcpu);
if (r)
return r;
vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
}
}

View File

@ -1377,7 +1377,7 @@ handle_page_fault(struct pt_regs *regs, unsigned long error_code,
DEFINE_IDTENTRY_RAW_ERRORCODE(exc_page_fault)
{
unsigned long address = read_cr2();
idtentry_state_t state;
irqentry_state_t state;
prefetchw(&current->mm->mmap_lock);
@ -1412,11 +1412,11 @@ DEFINE_IDTENTRY_RAW_ERRORCODE(exc_page_fault)
* code reenabled RCU to avoid subsequent wreckage which helps
* debugability.
*/
state = idtentry_enter(regs);
state = irqentry_enter(regs);
instrumentation_begin();
handle_page_fault(regs, error_code, address);
instrumentation_end();
idtentry_exit(regs, state);
irqentry_exit(regs, state);
}