Merge tag 'x86-urgent-2020-08-30' of git://git.kernel.org/pub/scm/lin…

…ux/kernel/git/tip/tip

Pull x86 fixes from Thomas Gleixner:
 "Three interrupt related fixes for X86:

   - Move disabling of the local APIC after invoking fixup_irqs() to
     ensure that interrupts which are incoming are noted in the IRR and
     not ignored.

   - Unbreak affinity setting.

     The rework of the entry code reused the regular exception entry
     code for device interrupts. The vector number is pushed into the
     errorcode slot on the stack which is then lifted into an argument
     and set to -1 because that's regs->orig_ax which is used in quite
     some places to check whether the entry came from a syscall.

     But it was overlooked that orig_ax is used in the affinity cleanup
     code to validate whether the interrupt has arrived on the new
     target. It turned out that this vector check is pointless because
     interrupts are never moved from one vector to another on the same
     CPU. That check is a historical leftover from the time where x86
     supported multi-CPU affinities, but not longer needed with the now
     strict single CPU affinity. Famous last words ...

   - Add a missing check for an empty cpumask into the matrix allocator.

     The affinity change added a warning to catch the case where an
     interrupt is moved on the same CPU to a different vector. This
     triggers because a condition with an empty cpumask returns an
     assignment from the allocator as the allocator uses for_each_cpu()
     without checking the cpumask for being empty. The historical
     inconsistent for_each_cpu() behaviour of ignoring the cpumask and
     unconditionally claiming that CPU0 is in the mask struck again.
     Sigh.

  plus a new entry into the MAINTAINER file for the HPE/UV platform"

* tag 'x86-urgent-2020-08-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  genirq/matrix: Deal with the sillyness of for_each_cpu() on UP
  x86/irq: Unbreak interrupt affinity setting
  x86/hotplug: Silence APIC only after all interrupts are migrated
  MAINTAINERS: Add entry for HPE Superdome Flex (UV) maintainers

MAINTAINERS

@@ -18875,6 +18875,15 @@ S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/core
 F:	arch/x86/platform
 
+X86 PLATFORM UV HPE SUPERDOME FLEX
+M:	Steve Wahl <steve.wahl@hpe.com>
+R:	Dimitri Sivanich <dimitri.sivanich@hpe.com>
+R:	Russ Anderson <russ.anderson@hpe.com>
+S:	Supported
+F:	arch/x86/include/asm/uv/
+F:	arch/x86/kernel/apic/x2apic_uv_x.c
+F:	arch/x86/platform/uv/
+
 X86 VDSO
 M:	Andy Lutomirski <luto@kernel.org>
 L:	linux-kernel@vger.kernel.org

arch/x86/kernel/apic/vector.c

@@ -161,6 +161,7 @@ static void apic_update_vector(struct irq_data *irqd, unsigned int newvec,
 		apicd->move_in_progress = true;
 		apicd->prev_vector = apicd->vector;
 		apicd->prev_cpu = apicd->cpu;
+		WARN_ON_ONCE(apicd->cpu == newcpu);
 	} else {
 		irq_matrix_free(vector_matrix, apicd->cpu, apicd->vector,
 				managed);
@@ -910,23 +911,24 @@ void send_cleanup_vector(struct irq_cfg *cfg)
 		__send_cleanup_vector(apicd);
 }
 
-static void __irq_complete_move(struct irq_cfg *cfg, unsigned vector)
+void irq_complete_move(struct irq_cfg *cfg)
 {
 	struct apic_chip_data *apicd;
 
 	apicd = container_of(cfg, struct apic_chip_data, hw_irq_cfg);
 	if (likely(!apicd->move_in_progress))
 		return;
 
-	if (vector == apicd->vector && apicd->cpu == smp_processor_id())
+	/*
+	 * If the interrupt arrived on the new target CPU, cleanup the
+	 * vector on the old target CPU. A vector check is not required
+	 * because an interrupt can never move from one vector to another
+	 * on the same CPU.
+	 */
+	if (apicd->cpu == smp_processor_id())
 		__send_cleanup_vector(apicd);
 }
 
-void irq_complete_move(struct irq_cfg *cfg)
-{
-	__irq_complete_move(cfg, ~get_irq_regs()->orig_ax);
-}
-
 /*
  * Called from fixup_irqs() with @desc->lock held and interrupts disabled.
  */

arch/x86/kernel/smpboot.c

@@ -1594,14 +1594,28 @@ int native_cpu_disable(void)
 	if (ret)
 		return ret;
 
-	/*
-	 * Disable the local APIC. Otherwise IPI broadcasts will reach
-	 * it. It still responds normally to INIT, NMI, SMI, and SIPI
-	 * messages.
-	 */
-	apic_soft_disable();
 	cpu_disable_common();
 
+        /*
+         * Disable the local APIC. Otherwise IPI broadcasts will reach
+         * it. It still responds normally to INIT, NMI, SMI, and SIPI
+         * messages.
+         *
+         * Disabling the APIC must happen after cpu_disable_common()
+         * which invokes fixup_irqs().
+         *
+         * Disabling the APIC preserves already set bits in IRR, but
+         * an interrupt arriving after disabling the local APIC does not
+         * set the corresponding IRR bit.
+         *
+         * fixup_irqs() scans IRR for set bits so it can raise a not
+         * yet handled interrupt on the new destination CPU via an IPI
+         * but obviously it can't do so for IRR bits which are not set.
+         * IOW, interrupts arriving after disabling the local APIC will
+         * be lost.
+         */
+	apic_soft_disable();
+
 	return 0;
 }
 

kernel/irq/matrix.c

@@ -380,6 +380,13 @@ int irq_matrix_alloc(struct irq_matrix *m, const struct cpumask *msk,
 	unsigned int cpu, bit;
 	struct cpumap *cm;
 
+	/*
+	 * Not required in theory, but matrix_find_best_cpu() uses
+	 * for_each_cpu() which ignores the cpumask on UP .
+	 */
+	if (cpumask_empty(msk))
+		return -EINVAL;
+
 	cpu = matrix_find_best_cpu(m, msk);
 	if (cpu == UINT_MAX)
 		return -ENOSPC;