Merge tag 'core-rcu-2020-06-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull RCU updates from Ingo Molnar:
 "The RCU updates for this cycle were:

   - RCU-tasks update, including addition of RCU Tasks Trace for BPF use
     and TASKS_RUDE_RCU

   - kfree_rcu() updates.

   - Remove scheduler locking restriction

   - RCU CPU stall warning updates.

   - Torture-test updates.

   - Miscellaneous fixes and other updates"

* tag 'core-rcu-2020-06-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (103 commits)
  rcu: Allow for smp_call_function() running callbacks from idle
  rcu: Provide rcu_irq_exit_check_preempt()
  rcu: Abstract out rcu_irq_enter_check_tick() from rcu_nmi_enter()
  rcu: Provide __rcu_is_watching()
  rcu: Provide rcu_irq_exit_preempt()
  rcu: Make RCU IRQ enter/exit functions rely on in_nmi()
  rcu/tree: Mark the idle relevant functions noinstr
  x86: Replace ist_enter() with nmi_enter()
  x86/mce: Send #MC singal from task work
  x86/entry: Get rid of ist_begin/end_non_atomic()
  sched,rcu,tracing: Avoid tracing before in_nmi() is correct
  sh/ftrace: Move arch_ftrace_nmi_{enter,exit} into nmi exception
  lockdep: Always inline lockdep_{off,on}()
  hardirq/nmi: Allow nested nmi_enter()
  arm64: Prepare arch_nmi_enter() for recursion
  printk: Disallow instrumenting print_nmi_enter()
  printk: Prepare for nested printk_nmi_enter()
  rcutorture: Convert ULONG_CMP_LT() to time_before()
  torture: Add a --kasan argument
  torture: Save a few lines by using config_override_param initially
  ...

5 files changed, 58 insertions, 130 deletions

diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index c26a7e1d8a2c..6f6c417e1e46 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -118,11 +118,6 @@ void smp_spurious_interrupt(struct pt_regs *regs);
 void smp_error_interrupt(struct pt_regs *regs);
 asmlinkage void smp_irq_move_cleanup_interrupt(void);
 
-extern void ist_enter(struct pt_regs *regs);
-extern void ist_exit(struct pt_regs *regs);
-extern void ist_begin_non_atomic(struct pt_regs *regs);
-extern void ist_end_non_atomic(void);
-
 #ifdef CONFIG_VMAP_STACK
 void __noreturn handle_stack_overflow(const char *message,
 				      struct pt_regs *regs,
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 54165f3569e8..e9265e2f28c9 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -42,6 +42,8 @@
 #include <linux/export.h>
 #include <linux/jump_label.h>
 #include <linux/set_memory.h>
+#include <linux/task_work.h>
+#include <linux/hardirq.h>
 
 #include <asm/intel-family.h>
 #include <asm/processor.h>
@@ -1086,23 +1088,6 @@ static void mce_clear_state(unsigned long *toclear)
 	}
 }
 
-static int do_memory_failure(struct mce *m)
-{
-	int flags = MF_ACTION_REQUIRED;
-	int ret;
-
-	pr_err("Uncorrected hardware memory error in user-access at %llx", m->addr);
-	if (!(m->mcgstatus & MCG_STATUS_RIPV))
-		flags |= MF_MUST_KILL;
-	ret = memory_failure(m->addr >> PAGE_SHIFT, flags);
-	if (ret)
-		pr_err("Memory error not recovered");
-	else
-		set_mce_nospec(m->addr >> PAGE_SHIFT);
-	return ret;
-}
-
-
 /*
  * Cases where we avoid rendezvous handler timeout:
  * 1) If this CPU is offline.
@@ -1204,6 +1189,29 @@ static void __mc_scan_banks(struct mce *m, struct mce *final,
 	*m = *final;
 }
 
+static void kill_me_now(struct callback_head *ch)
+{
+	force_sig(SIGBUS);
+}
+
+static void kill_me_maybe(struct callback_head *cb)
+{
+	struct task_struct *p = container_of(cb, struct task_struct, mce_kill_me);
+	int flags = MF_ACTION_REQUIRED;
+
+	pr_err("Uncorrected hardware memory error in user-access at %llx", p->mce_addr);
+	if (!(p->mce_status & MCG_STATUS_RIPV))
+		flags |= MF_MUST_KILL;
+
+	if (!memory_failure(p->mce_addr >> PAGE_SHIFT, flags)) {
+		set_mce_nospec(p->mce_addr >> PAGE_SHIFT);
+		return;
+	}
+
+	pr_err("Memory error not recovered");
+	kill_me_now(cb);
+}
+
 /*
  * The actual machine check handler. This only handles real
  * exceptions when something got corrupted coming in through int 18.
@@ -1222,7 +1230,7 @@ static void __mc_scan_banks(struct mce *m, struct mce *final,
  * backing the user stack, tracing that reads the user stack will cause
  * potentially infinite recursion.
  */
-void notrace do_machine_check(struct pt_regs *regs, long error_code)
+void noinstr do_machine_check(struct pt_regs *regs, long error_code)
 {
 	DECLARE_BITMAP(valid_banks, MAX_NR_BANKS);
 	DECLARE_BITMAP(toclear, MAX_NR_BANKS);
@@ -1259,7 +1267,7 @@ void notrace do_machine_check(struct pt_regs *regs, long error_code)
 	if (__mc_check_crashing_cpu(cpu))
 		return;
 
-	ist_enter(regs);
+	nmi_enter();
 
 	this_cpu_inc(mce_exception_count);
 
@@ -1352,23 +1360,24 @@ void notrace do_machine_check(struct pt_regs *regs, long error_code)
 
 	/* Fault was in user mode and we need to take some action */
 	if ((m.cs & 3) == 3) {
-		ist_begin_non_atomic(regs);
-		local_irq_enable();
-
-		if (kill_it || do_memory_failure(&m))
-			force_sig(SIGBUS);
-		local_irq_disable();
-		ist_end_non_atomic();
+		/* If this triggers there is no way to recover. Die hard. */
+		BUG_ON(!on_thread_stack() || !user_mode(regs));
+
+		current->mce_addr = m.addr;
+		current->mce_status = m.mcgstatus;
+		current->mce_kill_me.func = kill_me_maybe;
+		if (kill_it)
+			current->mce_kill_me.func = kill_me_now;
+		task_work_add(current, &current->mce_kill_me, true);
 	} else {
 		if (!fixup_exception(regs, X86_TRAP_MC, error_code, 0))
 			mce_panic("Failed kernel mode recovery", &m, msg);
 	}
 
 out_ist:
-	ist_exit(regs);
+	nmi_exit();
 }
 EXPORT_SYMBOL_GPL(do_machine_check);
-NOKPROBE_SYMBOL(do_machine_check);
 
 #ifndef CONFIG_MEMORY_FAILURE
 int memory_failure(unsigned long pfn, int flags)
diff --git a/arch/x86/kernel/cpu/mce/p5.c b/arch/x86/kernel/cpu/mce/p5.c
index 4ae6df556526..5ee94aa1b766 100644
--- a/arch/x86/kernel/cpu/mce/p5.c
+++ b/arch/x86/kernel/cpu/mce/p5.c
@@ -7,6 +7,7 @@
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/smp.h>
+#include <linux/hardirq.h>
 
 #include <asm/processor.h>
 #include <asm/traps.h>
@@ -24,7 +25,7 @@ static void pentium_machine_check(struct pt_regs *regs, long error_code)
 {
 	u32 loaddr, hi, lotype;
 
-	ist_enter(regs);
+	nmi_enter();
 
 	rdmsr(MSR_IA32_P5_MC_ADDR, loaddr, hi);
 	rdmsr(MSR_IA32_P5_MC_TYPE, lotype, hi);
@@ -39,7 +40,7 @@ static void pentium_machine_check(struct pt_regs *regs, long error_code)
 
 	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
 
-	ist_exit(regs);
+	nmi_exit();
 }
 
 /* Set up machine check reporting for processors with Intel style MCE: */
diff --git a/arch/x86/kernel/cpu/mce/winchip.c b/arch/x86/kernel/cpu/mce/winchip.c
index a30ea13cccc2..b3938c195365 100644
--- a/arch/x86/kernel/cpu/mce/winchip.c
+++ b/arch/x86/kernel/cpu/mce/winchip.c
@@ -6,6 +6,7 @@
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
+#include <linux/hardirq.h>
 
 #include <asm/processor.h>
 #include <asm/traps.h>
@@ -18,12 +19,12 @@
 /* Machine check handler for WinChip C6: */
 static void winchip_machine_check(struct pt_regs *regs, long error_code)
 {
-	ist_enter(regs);
+	nmi_enter();
 
 	pr_emerg("CPU0: Machine Check Exception.\n");
 	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
 
-	ist_exit(regs);
+	nmi_exit();
 }
 
 /* Set up machine check reporting on the Winchip C6 series */
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index d54cffdc7cac..f7cfb9d0ad02 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -37,10 +37,12 @@
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/io.h>
+#include <linux/hardirq.h>
+#include <linux/atomic.h>
+
 #include <asm/stacktrace.h>
 #include <asm/processor.h>
 #include <asm/debugreg.h>
-#include <linux/atomic.h>
 #include <asm/text-patching.h>
 #include <asm/ftrace.h>
 #include <asm/traps.h>
@@ -82,78 +84,6 @@ static inline void cond_local_irq_disable(struct pt_regs *regs)
 		local_irq_disable();
 }
 
-/*
- * In IST context, we explicitly disable preemption.  This serves two
- * purposes: it makes it much less likely that we would accidentally
- * schedule in IST context and it will force a warning if we somehow
- * manage to schedule by accident.
- */
-void ist_enter(struct pt_regs *regs)
-{
-	if (user_mode(regs)) {
-		RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
-	} else {
-		/*
-		 * We might have interrupted pretty much anything.  In
-		 * fact, if we're a machine check, we can even interrupt
-		 * NMI processing.  We don't want in_nmi() to return true,
-		 * but we need to notify RCU.
-		 */
-		rcu_nmi_enter();
-	}
-
-	preempt_disable();
-
-	/* This code is a bit fragile.  Test it. */
-	RCU_LOCKDEP_WARN(!rcu_is_watching(), "ist_enter didn't work");
-}
-NOKPROBE_SYMBOL(ist_enter);
-
-void ist_exit(struct pt_regs *regs)
-{
-	preempt_enable_no_resched();
-
-	if (!user_mode(regs))
-		rcu_nmi_exit();
-}
-
-/**
- * ist_begin_non_atomic() - begin a non-atomic section in an IST exception
- * @regs:	regs passed to the IST exception handler
- *
- * IST exception handlers normally cannot schedule.  As a special
- * exception, if the exception interrupted userspace code (i.e.
- * user_mode(regs) would return true) and the exception was not
- * a double fault, it can be safe to schedule.  ist_begin_non_atomic()
- * begins a non-atomic section within an ist_enter()/ist_exit() region.
- * Callers are responsible for enabling interrupts themselves inside
- * the non-atomic section, and callers must call ist_end_non_atomic()
- * before ist_exit().
- */
-void ist_begin_non_atomic(struct pt_regs *regs)
-{
-	BUG_ON(!user_mode(regs));
-
-	/*
-	 * Sanity check: we need to be on the normal thread stack.  This
-	 * will catch asm bugs and any attempt to use ist_preempt_enable
-	 * from double_fault.
-	 */
-	BUG_ON(!on_thread_stack());
-
-	preempt_enable_no_resched();
-}
-
-/**
- * ist_end_non_atomic() - begin a non-atomic section in an IST exception
- *
- * Ends a non-atomic section started with ist_begin_non_atomic().
- */
-void ist_end_non_atomic(void)
-{
-	preempt_disable();
-}
-
 int is_valid_bugaddr(unsigned long addr)
 {
 	unsigned short ud;
@@ -363,7 +293,7 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code, unsign
 	 * The net result is that our #GP handler will think that we
 	 * entered from usermode with the bad user context.
 	 *
-	 * No need for ist_enter here because we don't use RCU.
+	 * No need for nmi_enter() here because we don't use RCU.
 	 */
 	if (((long)regs->sp >> P4D_SHIFT) == ESPFIX_PGD_ENTRY &&
 		regs->cs == __KERNEL_CS &&
@@ -398,7 +328,7 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code, unsign
 	}
 #endif
 
-	ist_enter(regs);
+	nmi_enter();
 	notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV);
 
 	tsk->thread.error_code = error_code;
@@ -592,19 +522,13 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
 		return;
 
 	/*
-	 * Unlike any other non-IST entry, we can be called from a kprobe in
-	 * non-CONTEXT_KERNEL kernel mode or even during context tracking
-	 * state changes.  Make sure that we wake up RCU even if we're coming
-	 * from kernel code.
-	 *
-	 * This means that we can't schedule even if we came from a
-	 * preemptible kernel context.  That's okay.
+	 * Unlike any other non-IST entry, we can be called from pretty much
+	 * any location in the kernel through kprobes -- text_poke() will most
+	 * likely be handled by poke_int3_handler() above. This means this
+	 * handler is effectively NMI-like.
 	 */
-	if (!user_mode(regs)) {
-		rcu_nmi_enter();
-		preempt_disable();
-	}
-	RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
+	if (!user_mode(regs))
+		nmi_enter();
 
 #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
 	if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
@@ -626,10 +550,8 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
 	cond_local_irq_disable(regs);
 
 exit:
-	if (!user_mode(regs)) {
-		preempt_enable_no_resched();
-		rcu_nmi_exit();
-	}
+	if (!user_mode(regs))
+		nmi_exit();
 }
 NOKPROBE_SYMBOL(do_int3);
 
@@ -733,7 +655,7 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code)
 	unsigned long dr6;
 	int si_code;
 
-	ist_enter(regs);
+	nmi_enter();
 
 	get_debugreg(dr6, 6);
 	/*
@@ -826,7 +748,7 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code)
 	debug_stack_usage_dec();
 
 exit:
-	ist_exit(regs);
+	nmi_exit();
 }
 NOKPROBE_SYMBOL(do_debug);