1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247
|
// SPDX-License-Identifier: GPL-2.0
#include <linux/irq-entry-common.h>
#include <linux/resume_user_mode.h>
#include <linux/highmem.h>
#include <linux/jump_label.h>
#include <linux/kmsan.h>
#include <linux/livepatch.h>
#include <linux/tick.h>
/* Workaround to allow gradual conversion of architecture code */
void __weak arch_do_signal_or_restart(struct pt_regs *regs) { }
/**
* exit_to_user_mode_loop - do any pending work before leaving to user space
* @regs: Pointer to pt_regs on entry stack
* @ti_work: TIF work flags as read by the caller
*/
__always_inline unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
unsigned long ti_work)
{
/*
* Before returning to user space ensure that all pending work
* items have been completed.
*/
while (ti_work & EXIT_TO_USER_MODE_WORK) {
local_irq_enable_exit_to_user(ti_work);
if (ti_work & (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY))
schedule();
if (ti_work & _TIF_UPROBE)
uprobe_notify_resume(regs);
if (ti_work & _TIF_PATCH_PENDING)
klp_update_patch_state(current);
if (ti_work & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL))
arch_do_signal_or_restart(regs);
if (ti_work & _TIF_NOTIFY_RESUME)
resume_user_mode_work(regs);
/* Architecture specific TIF work */
arch_exit_to_user_mode_work(regs, ti_work);
/*
* Disable interrupts and reevaluate the work flags as they
* might have changed while interrupts and preemption was
* enabled above.
*/
local_irq_disable_exit_to_user();
/* Check if any of the above work has queued a deferred wakeup */
tick_nohz_user_enter_prepare();
ti_work = read_thread_flags();
}
/* Return the latest work state for arch_exit_to_user_mode() */
return ti_work;
}
noinstr void irqentry_enter_from_user_mode(struct pt_regs *regs)
{
enter_from_user_mode(regs);
}
noinstr void irqentry_exit_to_user_mode(struct pt_regs *regs)
{
instrumentation_begin();
exit_to_user_mode_prepare(regs);
instrumentation_end();
exit_to_user_mode();
}
noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs)
{
irqentry_state_t ret = {
.exit_rcu = false,
};
if (user_mode(regs)) {
irqentry_enter_from_user_mode(regs);
return ret;
}
/*
* If this entry hit the idle task invoke ct_irq_enter() whether
* RCU is watching or not.
*
* Interrupts 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 ct_irq_enter(). If that nested interrupt is
* the tick then rcu_flavor_sched_clock_irq() would wrongfully
* assume that it is the first interrupt and eventually claim
* quiescent state and end grace periods prematurely.
*
* Unconditionally invoke ct_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) || arch_in_rcu_eqs())) {
/*
* If RCU is not watching then the same careful
* sequence vs. lockdep and tracing is required
* as in irqentry_enter_from_user_mode().
*/
lockdep_hardirqs_off(CALLER_ADDR0);
ct_irq_enter();
instrumentation_begin();
kmsan_unpoison_entry_regs(regs);
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.
*/
lockdep_hardirqs_off(CALLER_ADDR0);
instrumentation_begin();
kmsan_unpoison_entry_regs(regs);
rcu_irq_enter_check_tick();
trace_hardirqs_off_finish();
instrumentation_end();
return ret;
}
void raw_irqentry_exit_cond_resched(void)
{
if (!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();
}
}
#ifdef CONFIG_PREEMPT_DYNAMIC
#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
DEFINE_STATIC_CALL(irqentry_exit_cond_resched, raw_irqentry_exit_cond_resched);
#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
DEFINE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched);
void dynamic_irqentry_exit_cond_resched(void)
{
if (!static_branch_unlikely(&sk_dynamic_irqentry_exit_cond_resched))
return;
raw_irqentry_exit_cond_resched();
}
#endif
#endif
noinstr void irqentry_exit(struct pt_regs *regs, irqentry_state_t state)
{
lockdep_assert_irqs_disabled();
/* Check whether this returns to user mode */
if (user_mode(regs)) {
irqentry_exit_to_user_mode(regs);
} else if (!regs_irqs_disabled(regs)) {
/*
* 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();
instrumentation_end();
ct_irq_exit();
lockdep_hardirqs_on(CALLER_ADDR0);
return;
}
instrumentation_begin();
if (IS_ENABLED(CONFIG_PREEMPTION))
irqentry_exit_cond_resched();
/* Covers both tracing and lockdep */
trace_hardirqs_on();
instrumentation_end();
} else {
/*
* IRQ flags state is correct already. Just tell RCU if it
* was not watching on entry.
*/
if (state.exit_rcu)
ct_irq_exit();
}
}
irqentry_state_t noinstr irqentry_nmi_enter(struct pt_regs *regs)
{
irqentry_state_t irq_state;
irq_state.lockdep = lockdep_hardirqs_enabled();
__nmi_enter();
lockdep_hardirqs_off(CALLER_ADDR0);
lockdep_hardirq_enter();
ct_nmi_enter();
instrumentation_begin();
kmsan_unpoison_entry_regs(regs);
trace_hardirqs_off_finish();
ftrace_nmi_enter();
instrumentation_end();
return irq_state;
}
void noinstr irqentry_nmi_exit(struct pt_regs *regs, irqentry_state_t irq_state)
{
instrumentation_begin();
ftrace_nmi_exit();
if (irq_state.lockdep) {
trace_hardirqs_on_prepare();
lockdep_hardirqs_on_prepare();
}
instrumentation_end();
ct_nmi_exit();
lockdep_hardirq_exit();
if (irq_state.lockdep)
lockdep_hardirqs_on(CALLER_ADDR0);
__nmi_exit();
}
|