x86/msi: Force affinity setup before startup

The X86 MSI mechanism cannot handle interrupt affinity changes safely after
startup other than from an interrupt handler, unless interrupt remapping is
enabled. The startup sequence in the generic interrupt code violates that
assumption.

Mark the irq chips with the new IRQCHIP_AFFINITY_PRE_STARTUP flag so that
the default interrupt setting happens before the interrupt is started up
for the first time.

While the interrupt remapping MSI chip does not require this, there is no
point in treating it differently as this might spare an interrupt to a CPU
which is not in the default affinity mask.

For the non-remapping case go to the direct write path when the interrupt
is not yet started similar to the not yet activated case.

Fixes: 18404756765c ("genirq: Expose default irq affinity mask (take 3)")
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20210729222542.886722080@linutronix.de

diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
index 44ebe25..dbacb9e 100644 (file)
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -58,11 +58,13 @@ msi_set_affinity(struct irq_data *irqd, const struct cpumask *mask, bool force)
         *   The quirk bit is not set in this case.
         * - The new vector is the same as the old vector
         * - The old vector is MANAGED_IRQ_SHUTDOWN_VECTOR (interrupt starts up)
+        * - The interrupt is not yet started up
         * - The new destination CPU is the same as the old destination CPU
         */
        if (!irqd_msi_nomask_quirk(irqd) ||
            cfg->vector == old_cfg.vector ||
            old_cfg.vector == MANAGED_IRQ_SHUTDOWN_VECTOR ||
+           !irqd_is_started(irqd) ||
            cfg->dest_apicid == old_cfg.dest_apicid) {
                irq_msi_update_msg(irqd, cfg);
                return ret;
@@ -150,7 +152,8 @@ static struct irq_chip pci_msi_controller = {
        .irq_ack                = irq_chip_ack_parent,
        .irq_retrigger          = irq_chip_retrigger_hierarchy,
        .irq_set_affinity       = msi_set_affinity,
-       .flags                  = IRQCHIP_SKIP_SET_WAKE,
+       .flags                  = IRQCHIP_SKIP_SET_WAKE |
+                                 IRQCHIP_AFFINITY_PRE_STARTUP,
 };
 
 int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec,
@@ -219,7 +222,8 @@ static struct irq_chip pci_msi_ir_controller = {
        .irq_mask               = pci_msi_mask_irq,
        .irq_ack                = irq_chip_ack_parent,
        .irq_retrigger          = irq_chip_retrigger_hierarchy,
-       .flags                  = IRQCHIP_SKIP_SET_WAKE,
+       .flags                  = IRQCHIP_SKIP_SET_WAKE |
+                                 IRQCHIP_AFFINITY_PRE_STARTUP,
 };
 
 static struct msi_domain_info pci_msi_ir_domain_info = {
@@ -273,7 +277,8 @@ static struct irq_chip dmar_msi_controller = {
        .irq_retrigger          = irq_chip_retrigger_hierarchy,
        .irq_compose_msi_msg    = dmar_msi_compose_msg,
        .irq_write_msi_msg      = dmar_msi_write_msg,
-       .flags                  = IRQCHIP_SKIP_SET_WAKE,
+       .flags                  = IRQCHIP_SKIP_SET_WAKE |
+                                 IRQCHIP_AFFINITY_PRE_STARTUP,
 };
 
 static int dmar_msi_init(struct irq_domain *domain,

diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 08651a4..42fc41d 100644 (file)
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -508,7 +508,7 @@ static struct irq_chip hpet_msi_controller __ro_after_init = {
        .irq_set_affinity = msi_domain_set_affinity,
        .irq_retrigger = irq_chip_retrigger_hierarchy,
        .irq_write_msi_msg = hpet_msi_write_msg,
-       .flags = IRQCHIP_SKIP_SET_WAKE,
+       .flags = IRQCHIP_SKIP_SET_WAKE | IRQCHIP_AFFINITY_PRE_STARTUP,
 };
 
 static int hpet_msi_init(struct irq_domain *domain,