RISC-V IMSIC driver improvements

index c708780e8760..5d7c30ad8855 100644
@@ -96,9 +96,8 @@ static int imsic_irq_set_affinity(struct irq_data *d, const struct cpumask *mask
 				  bool force)
 {
 	struct imsic_vector *old_vec, *new_vec;
-	struct irq_data *pd = d->parent_data;
 
-	old_vec = irq_data_get_irq_chip_data(pd);
+	old_vec = irq_data_get_irq_chip_data(d);
 	if (WARN_ON(!old_vec))
 		return -ENOENT;
 

@@ -116,13 +115,13 @@ static int imsic_irq_set_affinity(struct irq_data *d, const struct cpumask *mask
 		return -ENOSPC;
 
 	/* Point device to the new vector */
-	imsic_msi_update_msg(d, new_vec);
+	imsic_msi_update_msg(irq_get_irq_data(d->irq), new_vec);
 
 	/* Update irq descriptors with the new vector */
-	pd->chip_data = new_vec;
+	d->chip_data = new_vec;
 
-	/* Update effective affinity of parent irq data */
-	irq_data_update_effective_affinity(pd, cpumask_of(new_vec->cpu));
+	/* Update effective affinity */
+	irq_data_update_effective_affinity(d, cpumask_of(new_vec->cpu));
 
 	/* Move state of the old vector to the new vector */
 	imsic_vector_move(old_vec, new_vec);

@@ -135,6 +134,9 @@ static struct irq_chip imsic_irq_base_chip = {
 	.name			= "IMSIC",
 	.irq_mask		= imsic_irq_mask,
 	.irq_unmask		= imsic_irq_unmask,
+#ifdef CONFIG_SMP
+	.irq_set_affinity	= imsic_irq_set_affinity,
+#endif
 	.irq_retrigger		= imsic_irq_retrigger,
 	.irq_compose_msi_msg	= imsic_irq_compose_msg,
 	.flags			= IRQCHIP_SKIP_SET_WAKE |

@@ -245,7 +247,7 @@ static bool imsic_init_dev_msi_info(struct device *dev,
 		if (WARN_ON_ONCE(domain != real_parent))
 			return false;
 #ifdef CONFIG_SMP
-		info->chip->irq_set_affinity = imsic_irq_set_affinity;
+		info->chip->irq_set_affinity = irq_chip_set_affinity_parent;
 #endif
 		break;
 	default:

index be35c5349986..1e3476c335ca 100644
@@ -255,6 +255,7 @@ static void __init gicv2m_teardown(void)
 static struct msi_parent_ops gicv2m_msi_parent_ops = {
 	.supported_flags	= GICV2M_MSI_FLAGS_SUPPORTED,
 	.required_flags		= GICV2M_MSI_FLAGS_REQUIRED,
+	.chip_flags		= MSI_CHIP_FLAG_SET_EOI | MSI_CHIP_FLAG_SET_ACK,
 	.bus_select_token	= DOMAIN_BUS_NEXUS,
 	.bus_select_mask	= MATCH_PCI_MSI | MATCH_PLATFORM_MSI,
 	.prefix			= "GICv2m-",

index 4342a21de1eb..69aacdfc8bef 100644
@@ -214,6 +214,7 @@ static void imx_mu_msi_irq_handler(struct irq_desc *desc)
 static const struct msi_parent_ops imx_mu_msi_parent_ops = {
 	.supported_flags	= IMX_MU_MSI_FLAGS_SUPPORTED,
 	.required_flags		= IMX_MU_MSI_FLAGS_REQUIRED,
+	.chip_flags		= MSI_CHIP_FLAG_SET_EOI | MSI_CHIP_FLAG_SET_ACK,
 	.bus_select_token       = DOMAIN_BUS_NEXUS,
 	.bus_select_mask	= MATCH_PLATFORM_MSI,
 	.prefix			= "MU-MSI-",

index d8e29fc0d406..51464c6257f3 100644
@@ -28,6 +28,7 @@ bool msi_lib_init_dev_msi_info(struct device *dev, struct irq_domain *domain,
 			       struct msi_domain_info *info)
 {
 	const struct msi_parent_ops *pops = real_parent->msi_parent_ops;
+	struct irq_chip *chip = info->chip;
 	u32 required_flags;
 
 	/* Parent ops available? */

@@ -92,10 +93,10 @@ bool msi_lib_init_dev_msi_info(struct device *dev, struct irq_domain *domain,
 	info->flags			|= required_flags;
 
 	/* Chip updates for all child bus types */
-	if (!info->chip->irq_eoi)
-		info->chip->irq_eoi	= irq_chip_eoi_parent;
-	if (!info->chip->irq_ack)
-		info->chip->irq_ack	= irq_chip_ack_parent;
+	if (!chip->irq_eoi && (pops->chip_flags & MSI_CHIP_FLAG_SET_EOI))
+		chip->irq_eoi = irq_chip_eoi_parent;
+	if (!chip->irq_ack && (pops->chip_flags & MSI_CHIP_FLAG_SET_ACK))
+		chip->irq_ack = irq_chip_ack_parent;
 
 	/*
 	 * The device MSI domain can never have a set affinity callback. It

@@ -105,7 +106,7 @@ bool msi_lib_init_dev_msi_info(struct device *dev, struct irq_domain *domain,
 	 * device MSI domain aside of mask/unmask which is provided e.g. by
 	 * PCI/MSI device domains.
 	 */
-	info->chip->irq_set_affinity	= msi_domain_set_affinity;
+	chip->irq_set_affinity = msi_domain_set_affinity;
 	return true;
 }
 EXPORT_SYMBOL_GPL(msi_lib_init_dev_msi_info);

index 2b6183919ea4..d67f93f6d750 100644
@@ -161,6 +161,7 @@ static const struct irq_domain_ops gicp_domain_ops = {
 static const struct msi_parent_ops gicp_msi_parent_ops = {
 	.supported_flags	= GICP_MSI_FLAGS_SUPPORTED,
 	.required_flags		= GICP_MSI_FLAGS_REQUIRED,
+	.chip_flags		= MSI_CHIP_FLAG_SET_EOI | MSI_CHIP_FLAG_SET_ACK,
 	.bus_select_token       = DOMAIN_BUS_GENERIC_MSI,
 	.bus_select_mask	= MATCH_PLATFORM_MSI,
 	.prefix			= "GICP-",

index ff19bfd258dc..28f7e81df94f 100644
@@ -157,6 +157,7 @@ static const struct irq_domain_ops odmi_domain_ops = {
 static const struct msi_parent_ops odmi_msi_parent_ops = {
 	.supported_flags	= ODMI_MSI_FLAGS_SUPPORTED,
 	.required_flags		= ODMI_MSI_FLAGS_REQUIRED,
+	.chip_flags		= MSI_CHIP_FLAG_SET_EOI | MSI_CHIP_FLAG_SET_ACK,
 	.bus_select_token	= DOMAIN_BUS_GENERIC_MSI,
 	.bus_select_mask	= MATCH_PLATFORM_MSI,
 	.prefix			= "ODMI-",

index 065166ab5dbc..ebd4a9014e8d 100644
@@ -356,6 +356,7 @@ static void mvebu_sei_reset(struct mvebu_sei *sei)
 static const struct msi_parent_ops sei_msi_parent_ops = {
 	.supported_flags	= SEI_MSI_FLAGS_SUPPORTED,
 	.required_flags		= SEI_MSI_FLAGS_REQUIRED,
+	.chip_flags		= MSI_CHIP_FLAG_SET_EOI | MSI_CHIP_FLAG_SET_ACK,
 	.bus_select_mask	= MATCH_PLATFORM_MSI,
 	.bus_select_token	= DOMAIN_BUS_GENERIC_MSI,
 	.prefix			= "SEI-",

index b10093c4d00e..9abef442c146 100644
@@ -558,11 +558,21 @@ enum {
 	MSI_FLAG_NO_AFFINITY		= (1 << 21),
 };
 
+/*
+ * Flags for msi_parent_ops::chip_flags
+ */
+enum {
+	MSI_CHIP_FLAG_SET_EOI		= (1 << 0),
+	MSI_CHIP_FLAG_SET_ACK		= (1 << 1),
+};
+
 /**
  * struct msi_parent_ops - MSI parent domain callbacks and configuration info
  *
  * @supported_flags:	Required: The supported MSI flags of the parent domain
  * @required_flags:	Optional: The required MSI flags of the parent MSI domain
+ * @chip_flags:		Optional: Select MSI chip callbacks to update with defaults
+ *			in msi_lib_init_dev_msi_info().
  * @bus_select_token:	Optional: The bus token of the real parent domain for
  *			irq_domain::select()
  * @bus_select_mask:	Optional: A mask of supported BUS_DOMAINs for

@@ -575,6 +585,7 @@ enum {
 struct msi_parent_ops {
 	u32		supported_flags;
 	u32		required_flags;
+	u32		chip_flags;
 	u32		bus_select_token;
 	u32		bus_select_mask;
 	const char	*prefix;

143 lines not on this page · raw message

index 736f62812f5c..72fa4bb78f0a 100644
@@ -888,8 +888,109 @@ static int apic_set_affinity(struct irq_data *irqd,
 	return err ? err : IRQ_SET_MASK_OK;
 }
 
+static void free_moved_vector(struct apic_chip_data *apicd)
+{
+	unsigned int vector = apicd->prev_vector;
+	unsigned int cpu = apicd->prev_cpu;
+	bool managed = apicd->is_managed;
+
+	/*
+	 * Managed interrupts are usually not migrated away
+	 * from an online CPU, but CPU isolation 'managed_irq'
+	 * can make that happen.
+	 * 1) Activation does not take the isolation into account
+	 *    to keep the code simple
+	 * 2) Migration away from an isolated CPU can happen when
+	 *    a non-isolated CPU which is in the calculated
+	 *    affinity mask comes online.
+	 */
+	trace_vector_free_moved(apicd->irq, cpu, vector, managed);
+	irq_matrix_free(vector_matrix, cpu, vector, managed);
+	per_cpu(vector_irq, cpu)[vector] = VECTOR_UNUSED;
+	hlist_del_init(&apicd->clist);
+	apicd->prev_vector = 0;
+	apicd->move_in_progress = 0;
+}
+
+/*
+ * Called from fixup_irqs() with @desc->lock held and interrupts disabled.
+ */
+static void apic_force_complete_move(struct irq_data *irqd)
+{
+	unsigned int cpu = smp_processor_id();
+	struct apic_chip_data *apicd;
+	unsigned int vector;
+
+	guard(raw_spinlock)(&vector_lock);
+	apicd = apic_chip_data(irqd);
+	if (!apicd)
+		return;
+
+	/*
+	 * If prev_vector is empty or the descriptor is neither currently
+	 * nor previously on the outgoing CPU no action required.
+	 */
+	vector = apicd->prev_vector;
+	if (!vector || (apicd->cpu != cpu && apicd->prev_cpu != cpu))
+		return;
+
+	/*
+	 * This is tricky. If the cleanup of the old vector has not been
+	 * done yet, then the following setaffinity call will fail with
+	 * -EBUSY. This can leave the interrupt in a stale state.
+	 *
+	 * All CPUs are stuck in stop machine with interrupts disabled so
+	 * calling __irq_complete_move() would be completely pointless.
+	 *
+	 * 1) The interrupt is in move_in_progress state. That means that we
+	 *    have not seen an interrupt since the io_apic was reprogrammed to
+	 *    the new vector.
+	 *
+	 * 2) The interrupt has fired on the new vector, but the cleanup IPIs
+	 *    have not been processed yet.
+	 */
+	if (apicd->move_in_progress) {
+		/*
+		 * In theory there is a race:
+		 *
+		 * set_ioapic(new_vector) <-- Interrupt is raised before update
+		 *			      is effective, i.e. it's raised on
+		 *			      the old vector.
+		 *
+		 * So if the target cpu cannot handle that interrupt before
+		 * the old vector is cleaned up, we get a spurious interrupt
+		 * and in the worst case the ioapic irq line becomes stale.
+		 *
+		 * But in case of cpu hotplug this should be a non issue
+		 * because if the affinity update happens right before all
+		 * cpus rendezvous in stop machine, there is no way that the
+		 * interrupt can be blocked on the target cpu because all cpus
+		 * loops first with interrupts enabled in stop machine, so the
+		 * old vector is not yet cleaned up when the interrupt fires.
+		 *
+		 * So the only way to run into this issue is if the delivery
+		 * of the interrupt on the apic/system bus would be delayed
+		 * beyond the point where the target cpu disables interrupts
+		 * in stop machine. I doubt that it can happen, but at least
+		 * there is a theoretical chance. Virtualization might be
+		 * able to expose this, but AFAICT the IOAPIC emulation is not
+		 * as stupid as the real hardware.
+		 *
+		 * Anyway, there is nothing we can do about that at this point
+		 * w/o refactoring the whole fixup_irq() business completely.
+		 * We print at least the irq number and the old vector number,
+		 * so we have the necessary information when a problem in that
+		 * area arises.
+		 */
+		pr_warn("IRQ fixup: irq %d move in progress, old vector %d\n",
+			irqd->irq, vector);
+	}
+	free_moved_vector(apicd);
+}
+
 #else
-# define apic_set_affinity	NULL
+# define apic_set_affinity		NULL
+# define apic_force_complete_move	NULL
 #endif
 
 static int apic_retrigger_irq(struct irq_data *irqd)

@@ -923,39 +1024,16 @@ static void x86_vector_msi_compose_msg(struct irq_data *data,
 }
 
 static struct irq_chip lapic_controller = {
-	.name			= "APIC",
-	.irq_ack		= apic_ack_edge,
-	.irq_set_affinity	= apic_set_affinity,
-	.irq_compose_msi_msg	= x86_vector_msi_compose_msg,
-	.irq_retrigger		= apic_retrigger_irq,
+	.name				= "APIC",
+	.irq_ack			= apic_ack_edge,
+	.irq_set_affinity		= apic_set_affinity,
+	.irq_compose_msi_msg		= x86_vector_msi_compose_msg,
+	.irq_force_complete_move	= apic_force_complete_move,
+	.irq_retrigger			= apic_retrigger_irq,
 };
 
 #ifdef CONFIG_SMP
 
-static void free_moved_vector(struct apic_chip_data *apicd)
-{
-	unsigned int vector = apicd->prev_vector;
-	unsigned int cpu = apicd->prev_cpu;
-	bool managed = apicd->is_managed;
-
-	/*
-	 * Managed interrupts are usually not migrated away
-	 * from an online CPU, but CPU isolation 'managed_irq'
-	 * can make that happen.
-	 * 1) Activation does not take the isolation into account
-	 *    to keep the code simple
-	 * 2) Migration away from an isolated CPU can happen when
-	 *    a non-isolated CPU which is in the calculated
-	 *    affinity mask comes online.
-	 */
-	trace_vector_free_moved(apicd->irq, cpu, vector, managed);
-	irq_matrix_free(vector_matrix, cpu, vector, managed);
-	per_cpu(vector_irq, cpu)[vector] = VECTOR_UNUSED;
-	hlist_del_init(&apicd->clist);
-	apicd->prev_vector = 0;
-	apicd->move_in_progress = 0;
-}
-
 static void __vector_cleanup(struct vector_cleanup *cl, bool check_irr)
 {
 	struct apic_chip_data *apicd;

@@ -1068,99 +1146,6 @@ void irq_complete_move(struct irq_cfg *cfg)
 		__vector_schedule_cleanup(apicd);
 }
 
-/*
- * Called from fixup_irqs() with @desc->lock held and interrupts disabled.
- */
-void irq_force_complete_move(struct irq_desc *desc)
-{
-	unsigned int cpu = smp_processor_id();
-	struct apic_chip_data *apicd;
-	struct irq_data *irqd;
-	unsigned int vector;
-
-	/*
-	 * The function is called for all descriptors regardless of which
-	 * irqdomain they belong to. For example if an IRQ is provided by
-	 * an irq_chip as part of a GPIO driver, the chip data for that
-	 * descriptor is specific to the irq_chip in question.
-	 *
-	 * Check first that the chip_data is what we expect
-	 * (apic_chip_data) before touching it any further.
-	 */
-	irqd = irq_domain_get_irq_data(x86_vector_domain,
-				       irq_desc_get_irq(desc));
-	if (!irqd)
-		return;
-
-	raw_spin_lock(&vector_lock);
-	apicd = apic_chip_data(irqd);
-	if (!apicd)
-		goto unlock;
-
-	/*
-	 * If prev_vector is empty or the descriptor is neither currently
-	 * nor previously on the outgoing CPU no action required.
-	 */
-	vector = apicd->prev_vector;
-	if (!vector || (apicd->cpu != cpu && apicd->prev_cpu != cpu))
-		goto unlock;
-
-	/*
-	 * This is tricky. If the cleanup of the old vector has not been
-	 * done yet, then the following setaffinity call will fail with
-	 * -EBUSY. This can leave the interrupt in a stale state.
-	 *
-	 * All CPUs are stuck in stop machine with interrupts disabled so
-	 * calling __irq_complete_move() would be completely pointless.
-	 *
-	 * 1) The interrupt is in move_in_progress state. That means that we
-	 *    have not seen an interrupt since the io_apic was reprogrammed to
-	 *    the new vector.
-	 *
-	 * 2) The interrupt has fired on the new vector, but the cleanup IPIs
-	 *    have not been processed yet.
-	 */
-	if (apicd->move_in_progress) {
-		/*
-		 * In theory there is a race:
-		 *
-		 * set_ioapic(new_vector) <-- Interrupt is raised before update
-		 *			      is effective, i.e. it's raised on
-		 *			      the old vector.
-		 *
-		 * So if the target cpu cannot handle that interrupt before
-		 * the old vector is cleaned up, we get a spurious interrupt
-		 * and in the worst case the ioapic irq line becomes stale.
-		 *
-		 * But in case of cpu hotplug this should be a non issue
-		 * because if the affinity update happens right before all
-		 * cpus rendezvous in stop machine, there is no way that the
-		 * interrupt can be blocked on the target cpu because all cpus
-		 * loops first with interrupts enabled in stop machine, so the
-		 * old vector is not yet cleaned up when the interrupt fires.
-		 *
-		 * So the only way to run into this issue is if the delivery
-		 * of the interrupt on the apic/system bus would be delayed
-		 * beyond the point where the target cpu disables interrupts
-		 * in stop machine. I doubt that it can happen, but at least
-		 * there is a theoretical chance. Virtualization might be
-		 * able to expose this, but AFAICT the IOAPIC emulation is not
-		 * as stupid as the real hardware.
-		 *
-		 * Anyway, there is nothing we can do about that at this point
-		 * w/o refactoring the whole fixup_irq() business completely.
-		 * We print at least the irq number and the old vector number,
-		 * so we have the necessary information when a problem in that
-		 * area arises.
-		 */
-		pr_warn("IRQ fixup: irq %d move in progress, old vector %d\n",
-			irqd->irq, vector);
-	}
-	free_moved_vector(apicd);
-unlock:
-	raw_spin_unlock(&vector_lock);
-}
-
 #ifdef CONFIG_HOTPLUG_CPU
 /*
  * Note, this is not accurate accounting, but at least good enough to

index 8daa17f0107a..56f6583093d2 100644
@@ -486,6 +486,7 @@ static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d)
  * @ipi_send_mask:	send an IPI to destination cpus in cpumask
  * @irq_nmi_setup:	function called from core code before enabling an NMI
  * @irq_nmi_teardown:	function called from core code after disabling an NMI
+ * @irq_force_complete_move:	optional function to force complete pending irq move
  * @flags:		chip specific flags
  */
 struct irq_chip {

@@ -537,6 +538,8 @@ struct irq_chip {
 	int		(*irq_nmi_setup)(struct irq_data *data);
 	void		(*irq_nmi_teardown)(struct irq_data *data);
 
+	void		(*irq_force_complete_move)(struct irq_data *data);
+
 	unsigned long	flags;
 };
 

@@ -619,11 +622,9 @@ static inline void irq_move_irq(struct irq_data *data)
 		__irq_move_irq(data);
 }
 void irq_move_masked_irq(struct irq_data *data);
-void irq_force_complete_move(struct irq_desc *desc);
 #else
 static inline void irq_move_irq(struct irq_data *data) { }
 static inline void irq_move_masked_irq(struct irq_data *data) { }
-static inline void irq_force_complete_move(struct irq_desc *desc) { }
 #endif
 
 extern int no_irq_affinity;

index a979523640d0..d4e190e690bd 100644
@@ -442,6 +442,7 @@ static inline struct cpumask *irq_desc_get_pending_mask(struct irq_desc *desc)
 	return desc->pending_mask;
 }
 bool irq_fixup_move_pending(struct irq_desc *desc, bool force_clear);
+void irq_force_complete_move(struct irq_desc *desc);
 #else /* CONFIG_GENERIC_PENDING_IRQ */
 static inline bool irq_can_move_pcntxt(struct irq_data *data)
 {

@@ -467,6 +468,7 @@ static inline bool irq_fixup_move_pending(struct irq_desc *desc, bool fclear)
 {
 	return false;
 }
+static inline void irq_force_complete_move(struct irq_desc *desc) { }
 #endif /* !CONFIG_GENERIC_PENDING_IRQ */
 
 #if !defined(CONFIG_IRQ_DOMAIN) || !defined(CONFIG_IRQ_DOMAIN_HIERARCHY)

index eb150afd671f..e110300ad650 100644
@@ -35,6 +35,16 @@ bool irq_fixup_move_pending(struct irq_desc *desc, bool force_clear)
 	return true;
 }
 
+void irq_force_complete_move(struct irq_desc *desc)
+{
+	for (struct irq_data *d = irq_desc_get_irq_data(desc); d; d = d->parent_data) {
+		if (d->chip && d->chip->irq_force_complete_move) {
+			d->chip->irq_force_complete_move(d);
+			return;
+		}
+	}
+}
+
 void irq_move_masked_irq(struct irq_data *idata)
 {
 	struct irq_desc *desc = irq_data_to_desc(idata);

index 56f6583093d2..dd5df1e2d032 100644
@@ -615,6 +615,7 @@ extern int irq_affinity_online_cpu(unsigned int cpu);
 #endif
 
 #if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_PENDING_IRQ)
+bool irq_can_move_in_process_context(struct irq_data *data);
 void __irq_move_irq(struct irq_data *data);
 static inline void irq_move_irq(struct irq_data *data)
 {

@@ -623,6 +624,7 @@ static inline void irq_move_irq(struct irq_data *data)
 }
 void irq_move_masked_irq(struct irq_data *data);
 #else
+static inline bool irq_can_move_in_process_context(struct irq_data *data) { return true; }
 static inline void irq_move_irq(struct irq_data *data) { }
 static inline void irq_move_masked_irq(struct irq_data *data) { }
 #endif

index e110300ad650..5acea2ac57be 100644
@@ -127,3 +127,14 @@ void __irq_move_irq(struct irq_data *idata)
 	if (!masked)
 		idata->chip->irq_unmask(idata);
 }
+
+bool irq_can_move_in_process_context(struct irq_data *data)
+{
+	/*
+	 * Get top level irq_data when CONFIG_IRQ_DOMAIN_HIERARCHY is enabled,
+	 * and it should be optimized away when CONFIG_IRQ_DOMAIN_HIERARCHY is
+	 * disabled. So we avoid an "#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY" here.
+	 */
+	data = irq_desc_get_irq_data(irq_data_to_desc(data));
+	return irq_can_move_pcntxt(data);
+}

index c5c2e6929a2f..b5def6268936 100644
@@ -77,6 +77,12 @@ static void imsic_handle_irq(struct irq_desc *desc)
 	struct imsic_vector *vec;
 	unsigned long local_id;
 
+	/*
+	 * Process pending local synchronization instead of waiting
+	 * for per-CPU local timer to expire.
+	 */
+	imsic_local_sync_all(false);
+
 	chained_irq_enter(chip, desc);
 
 	while ((local_id = csr_swap(CSR_TOPEI, 0))) {

@@ -120,7 +126,7 @@ static int imsic_starting_cpu(unsigned int cpu)
 	 * Interrupts identities might have been enabled/disabled while
 	 * this CPU was not running so sync-up local enable/disable state.
 	 */
-	imsic_local_sync_all();
+	imsic_local_sync_all(true);
 
 	/* Enable local interrupt delivery */
 	imsic_local_delivery(true);

168 lines not on this page · raw message

index 391e44280827..f02842b84ed5 100644
@@ -23,7 +23,8 @@ struct imsic_vector {
 	unsigned int				hwirq;
 	/* Details accessed using local lock held */
 	bool					enable;
-	struct imsic_vector			*move;
+	struct imsic_vector			*move_next;
+	struct imsic_vector			*move_prev;
 };
 
 struct imsic_local_priv {

@@ -74,7 +75,7 @@ static inline void __imsic_id_clear_enable(unsigned long id)
 	__imsic_eix_update(id, 1, false, false);
 }
 
-void imsic_local_sync_all(void);
+void imsic_local_sync_all(bool force_all);
 void imsic_local_delivery(bool enable);
 
 void imsic_vector_mask(struct imsic_vector *vec);

@@ -87,7 +88,7 @@ static inline bool imsic_vector_isenabled(struct imsic_vector *vec)
 
 static inline struct imsic_vector *imsic_vector_get_move(struct imsic_vector *vec)
 {
-	return READ_ONCE(vec->move);
+	return READ_ONCE(vec->move_prev);
 }
 
 void imsic_vector_move(struct imsic_vector *old_vec, struct imsic_vector *new_vec);

index 9a5e7b4541f6..b9e3f9030bdf 100644
@@ -129,6 +129,37 @@ static int imsic_irq_set_affinity(struct irq_data *d, const struct cpumask *mask
 
 	return IRQ_SET_MASK_OK_DONE;
 }
+
+static void imsic_irq_force_complete_move(struct irq_data *d)
+{
+	struct imsic_vector *mvec, *vec = irq_data_get_irq_chip_data(d);
+	unsigned int cpu = smp_processor_id();
+
+	if (WARN_ON(!vec))
+		return;
+
+	/* Do nothing if there is no in-flight move */
+	mvec = imsic_vector_get_move(vec);
+	if (!mvec)
+		return;
+
+	/* Do nothing if the old IMSIC vector does not belong to current CPU */
+	if (mvec->cpu != cpu)
+		return;
+
+	/*
+	 * The best we can do is force cleanup the old IMSIC vector.
+	 *
+	 * The challenges over here are same as x86 vector domain so
+	 * refer to the comments in irq_force_complete_move() function
+	 * implemented at arch/x86/kernel/apic/vector.c.
+	 */
+
+	/* Force cleanup in-flight move */
+	pr_info("IRQ fixup: irq %d move in progress, old vector cpu %d local_id %d\n",
+		d->irq, mvec->cpu, mvec->local_id);
+	imsic_vector_force_move_cleanup(vec);
+}
 #endif
 
 static struct irq_chip imsic_irq_base_chip = {

@@ -137,6 +168,7 @@ static struct irq_chip imsic_irq_base_chip = {
 	.irq_unmask		= imsic_irq_unmask,
 #ifdef CONFIG_SMP
 	.irq_set_affinity	= imsic_irq_set_affinity,
+	.irq_force_complete_move = imsic_irq_force_complete_move,
 #endif
 	.irq_retrigger		= imsic_irq_retrigger,
 	.irq_compose_msi_msg	= imsic_irq_compose_msg,

index 96e994443fc7..5ec2b6bdffb2 100644
@@ -311,6 +311,23 @@ void imsic_vector_unmask(struct imsic_vector *vec)
 	raw_spin_unlock(&lpriv->lock);
 }
 
+void imsic_vector_force_move_cleanup(struct imsic_vector *vec)
+{
+	struct imsic_local_priv *lpriv;
+	struct imsic_vector *mvec;
+	unsigned long flags;
+
+	lpriv = per_cpu_ptr(imsic->lpriv, vec->cpu);
+	raw_spin_lock_irqsave(&lpriv->lock, flags);
+
+	mvec = READ_ONCE(vec->move_prev);
+	WRITE_ONCE(vec->move_prev, NULL);
+	if (mvec)
+		imsic_vector_free(mvec);
+
+	raw_spin_unlock_irqrestore(&lpriv->lock, flags);
+}
+
 static bool imsic_vector_move_update(struct imsic_local_priv *lpriv,
 				     struct imsic_vector *vec, bool is_old_vec,
 				     bool new_enable, struct imsic_vector *move_vec)

index f02842b84ed5..19dea0c77738 100644
@@ -91,6 +91,7 @@ static inline struct imsic_vector *imsic_vector_get_move(struct imsic_vector *ve
 	return READ_ONCE(vec->move_prev);
 }
 
+void imsic_vector_force_move_cleanup(struct imsic_vector *vec);
 void imsic_vector_move(struct imsic_vector *old_vec, struct imsic_vector *new_vec);
 
 struct imsic_vector *imsic_vector_from_local_id(unsigned int cpu, unsigned int local_id);

index b5def6268936..d2e8ed70d396 100644
@@ -73,7 +73,7 @@ static int __init imsic_ipi_domain_init(void) { return 0; }
 static void imsic_handle_irq(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
-	int err, cpu = smp_processor_id();
+	int cpu = smp_processor_id();
 	struct imsic_vector *vec;
 	unsigned long local_id;
 

@@ -103,9 +103,7 @@ static void imsic_handle_irq(struct irq_desc *desc)
 			continue;
 		}
 
-		err = generic_handle_domain_irq(imsic->base_domain, vec->hwirq);
-		if (unlikely(err))
-			pr_warn_ratelimited("hwirq 0x%x mapping not found\n", vec->hwirq);
+		generic_handle_irq(vec->irq);
 	}
 
 	chained_irq_exit(chip, desc);

index b9e3f9030bdf..6bf5d63f614e 100644
@@ -111,7 +111,7 @@ static int imsic_irq_set_affinity(struct irq_data *d, const struct cpumask *mask
 		return -EBUSY;
 
 	/* Get a new vector on the desired set of CPUs */
-	new_vec = imsic_vector_alloc(old_vec->hwirq, mask_val);
+	new_vec = imsic_vector_alloc(old_vec->irq, mask_val);
 	if (!new_vec)
 		return -ENOSPC;
 

index 5ec2b6bdffb2..d0148e48ab05 100644
@@ -422,7 +422,7 @@ struct imsic_vector *imsic_vector_from_local_id(unsigned int cpu, unsigned int l
 	return &lpriv->vectors[local_id];
 }
 
-struct imsic_vector *imsic_vector_alloc(unsigned int hwirq, const struct cpumask *mask)
+struct imsic_vector *imsic_vector_alloc(unsigned int irq, const struct cpumask *mask)
 {
 	struct imsic_vector *vec = NULL;
 	struct imsic_local_priv *lpriv;

@@ -438,7 +438,7 @@ struct imsic_vector *imsic_vector_alloc(unsigned int hwirq, const struct cpumask
 
 	lpriv = per_cpu_ptr(imsic->lpriv, cpu);
 	vec = &lpriv->vectors[local_id];
-	vec->hwirq = hwirq;
+	vec->irq = irq;
 	vec->enable = false;
 	vec->move_next = NULL;
 	vec->move_prev = NULL;

@@ -451,7 +451,7 @@ void imsic_vector_free(struct imsic_vector *vec)
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&imsic->matrix_lock, flags);
-	vec->hwirq = UINT_MAX;
+	vec->irq = 0;
 	irq_matrix_free(imsic->matrix, vec->cpu, vec->local_id, false);
 	raw_spin_unlock_irqrestore(&imsic->matrix_lock, flags);
 }

@@ -510,7 +510,7 @@ static int __init imsic_local_init(void)
 			vec = &lpriv->vectors[i];
 			vec->cpu = cpu;
 			vec->local_id = i;
-			vec->hwirq = UINT_MAX;
+			vec->irq = 0;
 		}
 	}
 

index 19dea0c77738..3202ffa4e849 100644
@@ -20,7 +20,7 @@ struct imsic_vector {
 	unsigned int				cpu;
 	unsigned int				local_id;
 	/* Details saved by driver in the vector */
-	unsigned int				hwirq;
+	unsigned int				irq;
 	/* Details accessed using local lock held */
 	bool					enable;
 	struct imsic_vector			*move_next;

@@ -96,7 +96,7 @@ void imsic_vector_move(struct imsic_vector *old_vec, struct imsic_vector *new_ve
 
 struct imsic_vector *imsic_vector_from_local_id(unsigned int cpu, unsigned int local_id);
 
-struct imsic_vector *imsic_vector_alloc(unsigned int hwirq, const struct cpumask *mask);
+struct imsic_vector *imsic_vector_alloc(unsigned int irq, const struct cpumask *mask);
 void imsic_vector_free(struct imsic_vector *vector);
 
 void imsic_vector_debug_show(struct seq_file *m, struct imsic_vector *vec, int ind);

index 6bf5d63f614e..828102c46f51 100644
@@ -64,6 +64,11 @@ static int imsic_irq_retrigger(struct irq_data *d)
 	return 0;
 }
 
+static void imsic_irq_ack(struct irq_data *d)
+{
+	irq_move_irq(d);
+}
+
 static void imsic_irq_compose_vector_msg(struct imsic_vector *vec, struct msi_msg *msg)
 {
 	phys_addr_t msi_addr;

@@ -97,6 +102,21 @@ static int imsic_irq_set_affinity(struct irq_data *d, const struct cpumask *mask
 				  bool force)
 {
 	struct imsic_vector *old_vec, *new_vec;
+	struct imsic_vector tmp_vec;
+
+	/*
+	 * Requirements for the downstream irqdomains (or devices):
+	 *
+	 * 1) Downstream irqdomains (or devices) with atomic MSI update can
+	 *    happily do imsic_irq_set_affinity() in the process-context on
+	 *    any CPU so the irqchip of such irqdomains must not set the
+	 *    IRQCHIP_MOVE_DEFERRED flag.
+	 *
+	 * 2) Downstream irqdomains (or devices) with non-atomic MSI update
+	 *    must do imsic_irq_set_affinity() in the interrupt-context upon
+	 *    next interrupt so the irqchip of such irqdomains must set the
+	 *    IRQCHIP_MOVE_DEFERRED flag.
+	 */
 
 	old_vec = irq_data_get_irq_chip_data(d);
 	if (WARN_ON(!old_vec))

@@ -115,6 +135,33 @@ static int imsic_irq_set_affinity(struct irq_data *d, const struct cpumask *mask
 	if (!new_vec)
 		return -ENOSPC;
 
+	/*
+	 * Device having non-atomic MSI update might see an intermediate
+	 * state when changing target IMSIC vector from one CPU to another.
+	 *
+	 * To avoid losing interrupt to such intermediate state, do the
+	 * following (just like x86 APIC):
+	 *
+	 * 1) First write a temporary IMSIC vector to the device which
+	 * has MSI address same as the old IMSIC vector but MSI data
+	 * matches the new IMSIC vector.
+	 *
+	 * 2) Next write the new IMSIC vector to the device.
+	 *
+	 * Based on the above, the __imsic_local_sync() must check pending
+	 * status of both old MSI data and new MSI data on the old CPU.
+	 */
+
+	if (!irq_can_move_in_process_context(d) &&
+	    new_vec->local_id != old_vec->local_id) {
+		/* Setup temporary vector */
+		tmp_vec.cpu = old_vec->cpu;
+		tmp_vec.local_id = new_vec->local_id;
+
+		/* Point device to the temporary vector */
+		imsic_msi_update_msg(irq_get_irq_data(d->irq), &tmp_vec);
+	}
+
 	/* Point device to the new vector */
 	imsic_msi_update_msg(irq_get_irq_data(d->irq), new_vec);
 

@@ -171,6 +218,7 @@ static struct irq_chip imsic_irq_base_chip = {
 	.irq_force_complete_move = imsic_irq_force_complete_move,
 #endif
 	.irq_retrigger		= imsic_irq_retrigger,
+	.irq_ack		= imsic_irq_ack,
 	.irq_compose_msi_msg	= imsic_irq_compose_msg,
 	.flags			= IRQCHIP_SKIP_SET_WAKE |
 				  IRQCHIP_MASK_ON_SUSPEND,

@@ -190,7 +238,7 @@ static int imsic_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
 		return -ENOSPC;
 
 	irq_domain_set_info(domain, virq, virq, &imsic_irq_base_chip, vec,
-			    handle_simple_irq, NULL, NULL);
+			    handle_edge_irq, NULL, NULL);
 	irq_set_noprobe(virq);
 	irq_set_affinity(virq, cpu_online_mask);
 	irq_data_update_effective_affinity(irq_get_irq_data(virq), cpumask_of(vec->cpu));

@@ -229,15 +277,36 @@ static const struct irq_domain_ops imsic_base_domain_ops = {
 #endif
 };
 
+static bool imsic_init_dev_msi_info(struct device *dev,
+				    struct irq_domain *domain,
+				    struct irq_domain *real_parent,
+				    struct msi_domain_info *info)
+{
+	if (!msi_lib_init_dev_msi_info(dev, domain, real_parent, info))
+		return false;
+
+	switch (info->bus_token) {
+	case DOMAIN_BUS_PCI_DEVICE_MSI:
+	case DOMAIN_BUS_PCI_DEVICE_MSIX:
+		info->chip->flags |= IRQCHIP_MOVE_DEFERRED;
+		break;
+	default:
+		break;
+	}
+
+	return true;
+}
+
 static const struct msi_parent_ops imsic_msi_parent_ops = {
 	.supported_flags	= MSI_GENERIC_FLAGS_MASK |
 				  MSI_FLAG_PCI_MSIX,
 	.required_flags		= MSI_FLAG_USE_DEF_DOM_OPS |
 				  MSI_FLAG_USE_DEF_CHIP_OPS |
 				  MSI_FLAG_PCI_MSI_MASK_PARENT,
+	.chip_flags		= MSI_CHIP_FLAG_SET_ACK,
 	.bus_select_token	= DOMAIN_BUS_NEXUS,
 	.bus_select_mask	= MATCH_PCI_MSI | MATCH_PLATFORM_MSI,
-	.init_dev_msi_info	= msi_lib_init_dev_msi_info,
+	.init_dev_msi_info	= imsic_init_dev_msi_info,
 };
 
 int imsic_irqdomain_init(void)

index d0148e48ab05..3a2a381e4fa1 100644
@@ -126,8 +126,8 @@ void __imsic_eix_update(unsigned long base_id, unsigned long num_id, bool pend,
 
 static bool __imsic_local_sync(struct imsic_local_priv *lpriv)
 {
-	struct imsic_local_config *mlocal;
-	struct imsic_vector *vec, *mvec;
+	struct imsic_local_config *tlocal, *mlocal;
+	struct imsic_vector *vec, *tvec, *mvec;
 	bool ret = true;
 	int i;
 

@@ -169,13 +169,36 @@ static bool __imsic_local_sync(struct imsic_local_priv *lpriv)
 		 */
 		mvec = READ_ONCE(vec->move_next);
 		if (mvec) {
-			if (__imsic_id_read_clear_pending(i)) {
+			/*
+			 * Device having non-atomic MSI update might see an
+			 * intermediate state so check both old ID and new ID
+			 * for pending interrupts.
+			 *
+			 * For details, refer imsic_irq_set_affinity().
+			 */
+
+			tvec = vec->local_id == mvec->local_id ?
+			       NULL : &lpriv->vectors[mvec->local_id];
+			if (tvec &&
+			    !irq_can_move_in_process_context(irq_get_irq_data(vec->irq)) &&
+			    __imsic_id_read_clear_pending(tvec->local_id)) {
+				/* Retrigger temporary vector if it was already in-use */
+				if (READ_ONCE(tvec->enable)) {
+					tlocal = per_cpu_ptr(imsic->global.local, tvec->cpu);
+					writel_relaxed(tvec->local_id, tlocal->msi_va);
+				}
+
+				mlocal = per_cpu_ptr(imsic->global.local, mvec->cpu);
+				writel_relaxed(mvec->local_id, mlocal->msi_va);
+			}
+
+			if (__imsic_id_read_clear_pending(vec->local_id)) {
 				mlocal = per_cpu_ptr(imsic->global.local, mvec->cpu);
 				writel_relaxed(mvec->local_id, mlocal->msi_va);
 			}
 
 			WRITE_ONCE(vec->move_next, NULL);
-			imsic_vector_free(&lpriv->vectors[i]);
+			imsic_vector_free(vec);
 		}
 
 skip: