Merge branch 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 updates and fixes from Thomas Gleixner:

 - Fix the (late) fallout from the vector management rework causing
   hlist corruption and irq descriptor reference leaks caused by a
   missing sanity check.

   The straight forward fix triggered another long standing issue to
   surface. The pre rework code hid the issue due to being way slower,
   but now the chance that user space sees an EBUSY error return when
   updating irq affinities is way higher, though quite a bunch of
   userspace tools do not handle it properly despite the fact that EBUSY
   could be returned for at least 10 years.

   It turned out that the EBUSY return can be avoided completely by
   utilizing the existing delayed affinity update mechanism for irq
   remapped scenarios as well. That's a bit more error handling in the
   kernel, but avoids fruitless fingerpointing discussions with tool
   developers.

 - Decouple PHYSICAL_MASK from AMD SME as its going to be required for
   the upcoming Intel memory encryption support as well.

 - Handle legacy device ACPI detection properly for newer platforms

 - Fix the wrong argument ordering in the vector allocation tracepoint

 - Simplify the IDT setup code for the APIC=n case

 - Use the proper string helpers in the MTRR code

 - Remove a stale unused VDSO source file

 - Convert the microcode update lock to a raw spinlock as its used in
   atomic context.

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/intel_rdt: Enable CMT and MBM on new Skylake stepping
  x86/apic/vector: Print APIC control bits in debugfs
  genirq/affinity: Defer affinity setting if irq chip is busy
  x86/platform/uv: Use apic_ack_irq()
  x86/ioapic: Use apic_ack_irq()
  irq_remapping: Use apic_ack_irq()
  x86/apic: Provide apic_ack_irq()
  genirq/migration: Avoid out of line call if pending is not set
  genirq/generic_pending: Do not lose pending affinity update
  x86/apic/vector: Prevent hlist corruption and leaks
  x86/vector: Fix the args of vector_alloc tracepoint
  x86/idt: Simplify the idt_setup_apic_and_irq_gates()
  x86/platform/uv: Remove extra parentheses
  x86/mm: Decouple dynamic __PHYSICAL_MASK from AMD SME
  x86: Mark native_set_p4d() as __always_inline
  x86/microcode: Make the late update update_lock a raw lock for RT
  x86/mtrr: Convert to use strncpy_from_user() helper
  x86/mtrr: Convert to use match_string() helper
  x86/vdso: Remove unused file
  x86/i8237: Register device based on FADT legacy boot flag

2 files changed, 55 insertions, 13 deletions

diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 4c2ef80..daeabd7 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -205,6 +205,39 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
 	return ret;
 }
 
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+static inline int irq_set_affinity_pending(struct irq_data *data,
+					   const struct cpumask *dest)
+{
+	struct irq_desc *desc = irq_data_to_desc(data);
+
+	irqd_set_move_pending(data);
+	irq_copy_pending(desc, dest);
+	return 0;
+}
+#else
+static inline int irq_set_affinity_pending(struct irq_data *data,
+					   const struct cpumask *dest)
+{
+	return -EBUSY;
+}
+#endif
+
+static int irq_try_set_affinity(struct irq_data *data,
+				const struct cpumask *dest, bool force)
+{
+	int ret = irq_do_set_affinity(data, dest, force);
+
+	/*
+	 * In case that the underlying vector management is busy and the
+	 * architecture supports the generic pending mechanism then utilize
+	 * this to avoid returning an error to user space.
+	 */
+	if (ret == -EBUSY && !force)
+		ret = irq_set_affinity_pending(data, dest);
+	return ret;
+}
+
 int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask,
 			    bool force)
 {
@@ -215,8 +248,8 @@ int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask,
 	if (!chip || !chip->irq_set_affinity)
 		return -EINVAL;
 
-	if (irq_can_move_pcntxt(data)) {
-		ret = irq_do_set_affinity(data, mask, force);
+	if (irq_can_move_pcntxt(data) && !irqd_is_setaffinity_pending(data)) {
+		ret = irq_try_set_affinity(data, mask, force);
 	} else {
 		irqd_set_move_pending(data);
 		irq_copy_pending(desc, mask);
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index 86ae0eb8..def48589 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -38,17 +38,18 @@ bool irq_fixup_move_pending(struct irq_desc *desc, bool force_clear)
 void irq_move_masked_irq(struct irq_data *idata)
 {
 	struct irq_desc *desc = irq_data_to_desc(idata);
-	struct irq_chip *chip = desc->irq_data.chip;
+	struct irq_data *data = &desc->irq_data;
+	struct irq_chip *chip = data->chip;
 
-	if (likely(!irqd_is_setaffinity_pending(&desc->irq_data)))
+	if (likely(!irqd_is_setaffinity_pending(data)))
 		return;
 
-	irqd_clr_move_pending(&desc->irq_data);
+	irqd_clr_move_pending(data);
 
 	/*
 	 * Paranoia: cpu-local interrupts shouldn't be calling in here anyway.
 	 */
-	if (irqd_is_per_cpu(&desc->irq_data)) {
+	if (irqd_is_per_cpu(data)) {
 		WARN_ON(1);
 		return;
 	}
@@ -73,13 +74,24 @@ void irq_move_masked_irq(struct irq_data *idata)
 	 * For correct operation this depends on the caller
 	 * masking the irqs.
 	 */
-	if (cpumask_any_and(desc->pending_mask, cpu_online_mask) < nr_cpu_ids)
-		irq_do_set_affinity(&desc->irq_data, desc->pending_mask, false);
-
+	if (cpumask_any_and(desc->pending_mask, cpu_online_mask) < nr_cpu_ids) {
+		int ret;
+
+		ret = irq_do_set_affinity(data, desc->pending_mask, false);
+		/*
+		 * If the there is a cleanup pending in the underlying
+		 * vector management, reschedule the move for the next
+		 * interrupt. Leave desc->pending_mask intact.
+		 */
+		if (ret == -EBUSY) {
+			irqd_set_move_pending(data);
+			return;
+		}
+	}
 	cpumask_clear(desc->pending_mask);
 }
 
-void irq_move_irq(struct irq_data *idata)
+void __irq_move_irq(struct irq_data *idata)
 {
 	bool masked;
 
@@ -90,9 +102,6 @@ void irq_move_irq(struct irq_data *idata)
 	 */
 	idata = irq_desc_get_irq_data(irq_data_to_desc(idata));
 
-	if (likely(!irqd_is_setaffinity_pending(idata)))
-		return;
-
 	if (unlikely(irqd_irq_disabled(idata)))
 		return;