RISC-V IMSIC driver improvements

index c5c2e6929a2f..73a93ce8668f 100644
@@ -77,6 +77,12 @@ static void imsic_handle_irq(struct irq_desc *desc)
 	struct imsic_vector *vec;
 	unsigned long local_id;
 
+	/*
+	 * First process pending IMSIC vector enable, disable and movement
+	 * on the current CPU.
+	 */
+	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);

index c708780e8760..b44eb0b3990b 100644
@@ -97,6 +97,7 @@ static int imsic_irq_set_affinity(struct irq_data *d, const struct cpumask *mask
 {
 	struct imsic_vector *old_vec, *new_vec;
 	struct irq_data *pd = d->parent_data;
+	struct imsic_vector tmp_vec;
 
 	old_vec = irq_data_get_irq_chip_data(pd);
 	if (WARN_ON(!old_vec))

@@ -115,6 +116,32 @@ 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 some 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 both
+	 * old MSI data and new MSI data on the old CPU for pending
+	 */
+
+	if (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(d, &tmp_vec);
+	}
+
 	/* Point device to the new vector */
 	imsic_msi_update_msg(d, new_vec);
 

92 lines not on this page · raw message

index 391e44280827..8fae6c99b019 100644
@@ -74,7 +74,7 @@ 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);

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;

index b44eb0b3990b..dc6f63f657e4 100644
@@ -96,10 +96,9 @@ 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;
 	struct imsic_vector tmp_vec;
 
-	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;
 

@@ -139,17 +138,17 @@ static int imsic_irq_set_affinity(struct irq_data *d, const struct cpumask *mask
 		tmp_vec.local_id = new_vec->local_id;
 
 		/* Point device to the temporary vector */
-		imsic_msi_update_msg(d, &tmp_vec);
+		imsic_msi_update_msg(irq_get_irq_data(d->irq), &tmp_vec);
 	}
 
 	/* 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);

@@ -162,6 +161,9 @@ 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 |

@@ -272,7 +274,7 @@ 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:

143 lines not on this page · raw message

index fa711f80957b..b689c8fe8d60 100644
@@ -567,6 +567,7 @@ struct irq_chip {
  *                                    in the suspend path if they are in disabled state
  * IRQCHIP_AFFINITY_PRE_STARTUP:      Default affinity update before startup
  * IRQCHIP_IMMUTABLE:		      Don't ever change anything in this chip
+ * IRQCHIP_MOVE_DEFERRED:             Move the interrupt in actual interrupt context
  */
 enum {
 	IRQCHIP_SET_TYPE_MASKED			= (1 <<  0),

@@ -581,6 +582,7 @@ enum {
 	IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND	= (1 <<  9),
 	IRQCHIP_AFFINITY_PRE_STARTUP		= (1 << 10),
 	IRQCHIP_IMMUTABLE			= (1 << 11),
+	IRQCHIP_MOVE_DEFERRED			= (1 << 12),
 };
 
 #include <linux/irqdesc.h>

@@ -634,6 +636,14 @@ static inline void irq_move_masked_irq(struct irq_data *data) { }
 static inline void irq_force_complete_move(struct irq_desc *desc) { }
 #endif
 
+#if defined(CONFIG_GENERIC_PENDING_IRQ_CHIPFLAGS)
+void irq_update_pcntxt_flag(unsigned int irq, const struct irq_chip *chip);
+#else
+static inline void irq_update_pcntxt_flag(unsigned int irq, const struct irq_chip *chip)
+{
+}
+#endif
+
 extern int no_irq_affinity;
 
 #ifdef CONFIG_HARDIRQS_SW_RESEND

index 271e9139de77..623959a24464 100644
@@ -33,6 +33,33 @@ struct irqaction chained_action = {
 	.handler = bad_chained_irq,
 };
 
+#ifdef CONFIG_GENERIC_PENDING_IRQ_CHIPFLAGS
+static void __irq_update_pcntxt_flag(struct irq_desc *desc,
+				     const struct irq_chip *chip)
+{
+	if (chip) {
+		if (chip->flags & IRQCHIP_MOVE_DEFERRED)
+			irqd_clear(&desc->irq_data, IRQD_MOVE_PCNTXT);
+		else
+			irqd_set(&desc->irq_data, IRQD_MOVE_PCNTXT);
+	}
+}
+
+void irq_update_pcntxt_flag(unsigned int irq, const struct irq_chip *chip)
+{
+	unsigned long flags;
+	struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0);
+
+	__irq_update_pcntxt_flag(desc, chip);
+	irq_put_desc_unlock(desc, flags);
+}
+#else
+static inline void __irq_update_pcntxt_flag(struct irq_desc *desc,
+					    const struct irq_chip *chip)
+{
+}
+#endif
+
 /**
  *	irq_set_chip - set the irq chip for an irq
  *	@irq:	irq number

@@ -47,6 +74,7 @@ int irq_set_chip(unsigned int irq, const struct irq_chip *chip)
 		return -EINVAL;
 
 	desc->irq_data.chip = (struct irq_chip *)(chip ?: &no_irq_chip);
+	__irq_update_pcntxt_flag(desc, chip);
 	irq_put_desc_unlock(desc, flags);
 	/*
 	 * For !CONFIG_SPARSE_IRQ make the irq show up in

@@ -1114,16 +1142,21 @@ void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set)
 	trigger = irqd_get_trigger_type(&desc->irq_data);
 
 	irqd_clear(&desc->irq_data, IRQD_NO_BALANCING | IRQD_PER_CPU |
-		   IRQD_TRIGGER_MASK | IRQD_LEVEL | IRQD_MOVE_PCNTXT);
+		   IRQD_TRIGGER_MASK | IRQD_LEVEL);
 	if (irq_settings_has_no_balance_set(desc))
 		irqd_set(&desc->irq_data, IRQD_NO_BALANCING);
 	if (irq_settings_is_per_cpu(desc))
 		irqd_set(&desc->irq_data, IRQD_PER_CPU);
-	if (irq_settings_can_move_pcntxt(desc))
-		irqd_set(&desc->irq_data, IRQD_MOVE_PCNTXT);
 	if (irq_settings_is_level(desc))
 		irqd_set(&desc->irq_data, IRQD_LEVEL);
 
+	/* Keep this around until x86 is converted over */
+	if (!IS_ENABLED(CONFIG_GENERIC_PENDING_IRQ_CHIPFLAGS)) {
+		irqd_clear(&desc->irq_data, IRQD_MOVE_PCNTXT);
+		if (irq_settings_can_move_pcntxt(desc))
+			irqd_set(&desc->irq_data, IRQD_MOVE_PCNTXT);
+	}
+
 	tmp = irq_settings_get_trigger_mask(desc);
 	if (tmp != IRQ_TYPE_NONE)
 		trigger = tmp;

index ec6d8e72d980..ec5fc1d8cebe 100644
@@ -1508,6 +1508,7 @@ int irq_domain_set_hwirq_and_chip(struct irq_domain *domain, unsigned int virq,
 	irq_data->hwirq = hwirq;
 	irq_data->chip = (struct irq_chip *)(chip ? chip : &no_irq_chip);
 	irq_data->chip_data = chip_data;
+	irq_update_pcntxt_flag(virq, chip);
 
 	return 0;
 }

index b689c8fe8d60..509c0ee4ef38 100644
@@ -496,6 +496,7 @@ 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 {

@@ -547,6 +548,10 @@ struct irq_chip {
 	int		(*irq_nmi_setup)(struct irq_data *data);
 	void		(*irq_nmi_teardown)(struct irq_data *data);
 
+#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_PENDING_IRQ)
+	void		(*irq_force_complete_move)(struct irq_data *data);
+#endif
+
 	unsigned long	flags;
 };
 

index eb150afd671f..2920024475a3 100644
@@ -5,6 +5,15 @@
 
 #include "internals.h"
 
+void __weak irq_force_complete_move(struct irq_desc *desc)
+{
+	struct irq_data *d = irq_desc_get_irq_data(desc);
+	struct irq_chip *chip = irq_data_get_irq_chip(d);
+
+	if (chip && chip->irq_force_complete_move)
+		chip->irq_force_complete_move(d);
+}
+
 /**
  * irq_fixup_move_pending - Cleanup irq move pending from a dying CPU
  * @desc:		Interrupt descriptor to clean up

index a8645084bd8f..da49a160ea09 100644
@@ -124,10 +124,11 @@ void __imsic_eix_update(unsigned long base_id, unsigned long num_id, bool pend,
 	}
 }
 
-static void __imsic_local_sync(struct imsic_local_priv *lpriv)
+static bool __imsic_local_sync(struct imsic_local_priv *lpriv)
 {
 	struct imsic_local_config *tlocal, *mlocal;
 	struct imsic_vector *vec, *tvec, *mvec;
+	bool ret = true;
 	int i;
 
 	lockdep_assert_held(&lpriv->lock);

@@ -142,15 +143,33 @@ static void __imsic_local_sync(struct imsic_local_priv *lpriv)
 		else
 			__imsic_id_clear_enable(vec->local_id);
 
+		/*
+		 * If the ID was being moved from an existing ID on some
+		 * other CPU then we clear the pervious vector pointer
+		 * only after the movement is complete.
+		 */
+		mvec = READ_ONCE(vec->move_prev);
+		if (mvec) {
+			/*
+			 * If the old IMSIC vector has not been updated then
+			 * try again in the next sync-up call.
+			 */
+			if (READ_ONCE(mvec->move_next)) {
+				ret = false;
+				continue;
+			}
+
+			WRITE_ONCE(vec->move_prev, NULL);
+		}
+
 		/*
 		 * If the ID was being moved to a new ID on some other CPU
 		 * then we can get a MSI during the movement so check the
 		 * ID pending bit and re-trigger the new ID on other CPU
 		 * using MMIO write.
 		 */
-		mvec = READ_ONCE(vec->move);
-		WRITE_ONCE(vec->move, NULL);
-		if (mvec && mvec != vec) {
+		mvec = READ_ONCE(vec->move_next);
+		if (mvec) {
 			/*
 			 * Device having non-atomic MSI update might see an
 			 * intermediate state so check both old ID and new ID

@@ -177,11 +196,14 @@ static void __imsic_local_sync(struct imsic_local_priv *lpriv)
 				writel_relaxed(mvec->local_id, mlocal->msi_va);
 			}
 
+			WRITE_ONCE(vec->move_next, NULL);
 			imsic_vector_free(vec);
 		}
 
 		bitmap_clear(lpriv->dirty_bitmap, vec->local_id, 1);
 	}
+
+	return ret;
 }
 
 void imsic_local_sync_all(bool force_all)

@@ -190,9 +212,16 @@ void imsic_local_sync_all(bool force_all)
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&lpriv->lock, flags);
+
 	if (force_all)
 		bitmap_fill(lpriv->dirty_bitmap, imsic->global.nr_ids + 1);
-	__imsic_local_sync(lpriv);
+	if (!__imsic_local_sync(lpriv)) {
+		if (!timer_pending(&lpriv->timer)) {
+			lpriv->timer.expires = jiffies + 1;
+			add_timer_on(&lpriv->timer, smp_processor_id());
+		}
+	}
+
 	raw_spin_unlock_irqrestore(&lpriv->lock, flags);
 }
 

@@ -232,8 +261,8 @@ static void __imsic_remote_sync(struct imsic_local_priv *lpriv, unsigned int cpu
 	 */
 	if (cpu_online(cpu)) {
 		if (cpu == smp_processor_id()) {
-			__imsic_local_sync(lpriv);
-			return;
+			if (__imsic_local_sync(lpriv))
+				return;
 		}
 
 		if (!timer_pending(&lpriv->timer)) {

@@ -294,8 +323,9 @@ void imsic_vector_unmask(struct imsic_vector *vec)
 	raw_spin_unlock(&lpriv->lock);
 }
 
-static bool imsic_vector_move_update(struct imsic_local_priv *lpriv, struct imsic_vector *vec,
-				     bool new_enable, struct imsic_vector *new_move)
+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)
 {
 	unsigned long flags;
 	bool enabled;

@@ -305,7 +335,10 @@ static bool imsic_vector_move_update(struct imsic_local_priv *lpriv, struct imsi
 	/* Update enable and move details */
 	enabled = READ_ONCE(vec->enable);
 	WRITE_ONCE(vec->enable, new_enable);
-	WRITE_ONCE(vec->move, new_move);
+	if (is_old_vec)
+		WRITE_ONCE(vec->move_next, move_vec);
+	else
+		WRITE_ONCE(vec->move_prev, move_vec);
 
 	/* Mark the vector as dirty and synchronize */
 	bitmap_set(lpriv->dirty_bitmap, vec->local_id, 1);

@@ -338,8 +371,8 @@ void imsic_vector_move(struct imsic_vector *old_vec, struct imsic_vector *new_ve
 	 * interrupt on the old vector while device was being moved
 	 * to the new vector.
 	 */
-	enabled = imsic_vector_move_update(old_lpriv, old_vec, false, new_vec);
-	imsic_vector_move_update(new_lpriv, new_vec, enabled, new_vec);
+	enabled = imsic_vector_move_update(old_lpriv, old_vec, true, false, new_vec);
+	imsic_vector_move_update(new_lpriv, new_vec, false, enabled, old_vec);
 }
 
 #ifdef CONFIG_GENERIC_IRQ_DEBUGFS

@@ -402,7 +435,8 @@ struct imsic_vector *imsic_vector_alloc(unsigned int hwirq, const struct cpumask
 	vec = &lpriv->vectors[local_id];
 	vec->hwirq = hwirq;
 	vec->enable = false;
-	vec->move = NULL;
+	vec->move_next = NULL;
+	vec->move_prev = NULL;
 
 	return vec;
 }

index 8fae6c99b019..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 {

@@ -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 2fab20d2ce3e..fae47b8ccf73 100644
@@ -156,6 +156,37 @@ 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 = {

@@ -164,6 +195,7 @@ 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 da49a160ea09..c915a5cf4187 100644
@@ -323,6 +323,23 @@ 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 73a93ce8668f..0c94ce8ce580 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 fae47b8ccf73..e6c81718ba78 100644
@@ -112,7 +112,7 @@ 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 c915a5cf4187..aca769d915bf 100644
@@ -434,7 +434,7 @@ 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;

@@ -450,7 +450,7 @@ 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;

@@ -463,7 +463,7 @@ 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);
 }

@@ -522,7 +522,7 @@ 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 e6c81718ba78..eac7f358bbba 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;

@@ -97,7 +102,20 @@ 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))

@@ -117,31 +135,13 @@ static int imsic_irq_set_affinity(struct irq_data *d, const struct cpumask *mask
 		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 some 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 both
-	 * old MSI data and new MSI data on the old CPU for pending
+	 * Downstream irqdomains (or devices) with non-atomic MSI update
+	 * may see an intermediate state when changing target IMSIC vector
+	 * from one CPU to another but using the IRQCHIP_MOVE_DEFERRED
+	 * flag this is taken care because imsic_irq_set_affinity() is
+	 * called in the interrupt-context with interrupt masked.
 	 */
 
-	if (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);
 

@@ -198,6 +198,7 @@ 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,

@@ -217,7 +218,7 @@ 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));

@@ -256,15 +257,36 @@ 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 aca769d915bf..c7649fb6bbe6 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 *tlocal, *mlocal;
-	struct imsic_vector *vec, *tvec, *mvec;
+	struct imsic_local_config *mlocal;
+	struct imsic_vector *vec, *mvec;
 	bool ret = true;
 	int i;
 

@@ -170,27 +170,6 @@ static bool __imsic_local_sync(struct imsic_local_priv *lpriv)
 		 */
 		mvec = READ_ONCE(vec->move_next);
 		if (mvec) {
-			/*
-			 * 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 && __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);