x86/mce: Send #MC singal from task work

Convert #MC over to using task_work_add(); it will run the same code
slightly later, on the return to user path of the same exception.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Reviewed-by: Alexandre Chartre <alexandre.chartre@oracle.com>
Link: https://lkml.kernel.org/r/20200505134100.957390899@linutronix.de

2 files changed, 37 insertions, 25 deletions

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 98bf91cd7d5d..2f0ef95795f3 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -42,6 +42,7 @@
 #include <linux/export.h>
 #include <linux/jump_label.h>
 #include <linux/set_memory.h>
+#include <linux/task_work.h>
 
 #include <asm/intel-family.h>
 #include <asm/processor.h>
@@ -1086,23 +1087,6 @@ 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 +1188,29 @@ 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 +1229,7 @@ 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);
@@ -1354,13 +1361,13 @@ void notrace do_machine_check(struct pt_regs *regs, long error_code)
 	if ((m.cs & 3) == 3) {
 		/* If this triggers there is no way to recover. Die hard. */
 		BUG_ON(!on_thread_stack() || !user_mode(regs));
-		local_irq_enable();
-		preempt_enable();
 
-		if (kill_it || do_memory_failure(&m))
-			force_sig(SIGBUS);
-		preempt_disable();
-		local_irq_disable();
+		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);
@@ -1370,7 +1377,6 @@ out_ist:
 	ist_exit(regs);
 }
 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/include/linux/sched.h b/include/linux/sched.h
index 9437b53cc603..57d0ed061ae4 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1297,6 +1297,12 @@ struct task_struct {
 	unsigned long			prev_lowest_stack;
 #endif
 
+#ifdef CONFIG_X86_MCE
+	u64				mce_addr;
+	u64				mce_status;
+	struct callback_head		mce_kill_me;
+#endif
+
 	/*
 	 * New fields for task_struct should be added above here, so that
 	 * they are included in the randomized portion of task_struct.