[PATCH v2 -tip 0/5] x86, MSI, AHCI: Support multiple MSIs

@@ -305,6 +305,11 @@ static int alloc_irq_from(unsigned int from, int node)
 	return irq_alloc_desc_from(from, node);
 }
 
+static int alloc_irqs_from(unsigned int from, unsigned int count, int node)
+{
+	return irq_alloc_descs_from(from, count, node);
+}
+
 static void free_irq_at(unsigned int at, struct irq_cfg *cfg)
 {
 	free_irq_cfg(at, cfg);

@@ -3039,6 +3044,55 @@ int create_irq(void)
 	return irq;
 }
 
+unsigned int create_irqs(unsigned int from, unsigned int count, int node)
+{
+	struct irq_cfg **cfg;
+	unsigned long flags;
+	int irq, i;
+
+	if (from < nr_irqs_gsi)
+		from = nr_irqs_gsi;
+
+	cfg = kzalloc_node(count * sizeof(cfg[0]), GFP_KERNEL, node);
+	if (!cfg)
+		return 0;
+
+	irq = alloc_irqs_from(from, count, node);
+	if (irq < 0)
+		goto out_cfgs;
+
+	for (i = 0; i < count; i++) {
+		cfg[i] = alloc_irq_cfg(irq + i, node);
+		if (!cfg[i])
+			goto out_irqs;
+	}
+
+	raw_spin_lock_irqsave(&vector_lock, flags);
+	for (i = 0; i < count; i++)
+		if (__assign_irq_vector(irq + i, cfg[i], apic->target_cpus()))
+			goto out_vecs;
+	raw_spin_unlock_irqrestore(&vector_lock, flags);
+
+	for (i = 0; i < count; i++) {
+		irq_set_chip_data(irq + i, cfg[i]);
+		irq_clear_status_flags(irq + i, IRQ_NOREQUEST);
+	}
+
+	kfree(cfg);
+	return irq;
+
+out_vecs:
+	for (; i; i--)
+		__clear_irq_vector(irq + i - 1, cfg[i - 1]);
+	raw_spin_unlock_irqrestore(&vector_lock, flags);
+out_irqs:
+	for (i = 0; i < count; i++)
+		free_irq_at(irq + i, cfg[i]);
+out_cfgs:
+	kfree(cfg);
+	return 0;
+}
+
 void destroy_irq(unsigned int irq)
 {
 	struct irq_cfg *cfg = irq_get_chip_data(irq);

@@ -3054,6 +3108,27 @@ void destroy_irq(unsigned int irq)
 	free_irq_at(irq, cfg);
 }
 
+static inline void destroy_irqs(unsigned int irq, unsigned int count)
+{
+	unsigned int i;
+	for (i = 0; i < count; i++)
+		destroy_irq(irq + i);
+}
+
+static inline int
+can_create_pow_of_two_irqs(unsigned int from, unsigned int count)
+{
+	if ((count > 1) && (count % 2))
+		return -EINVAL;
+
+	for (; count; count = count / 2) {
+		if (!irq_can_alloc_irqs(from, count))
+			return count;
+	}
+
+	return -ENOSPC;
+}
+
 /*
  * MSI message composition
  */

@@ -3145,18 +3220,25 @@ static struct irq_chip msi_chip = {
 	.irq_retrigger		= ioapic_retrigger_irq,
 };
 
-static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq)
+static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc,
+			 unsigned int irq_base, unsigned int irq_offset)
 {
 	struct irq_chip *chip = &msi_chip;
 	struct msi_msg msg;
+	unsigned int irq = irq_base + irq_offset;
 	int ret;
 
 	ret = msi_compose_msg(dev, irq, &msg, -1);
 	if (ret < 0)
 		return ret;
 
-	irq_set_msi_desc(irq, msidesc);
-	write_msi_msg(irq, &msg);
+	irq_set_msi_desc_off(irq_base, irq_offset, msidesc);
+
+	/* MSI-X message is written per-IRQ, the offset is always 0.
+	 * MSI message denotes a contiguous group of IRQs, written for 0th IRQ.
+	 */
+	if (!irq_offset)
+		write_msi_msg(irq, &msg);
 
 	if (irq_remapped(irq_get_chip_data(irq))) {
 		irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);

@@ -3170,16 +3252,12 @@ static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq)
 	return 0;
 }
 
-int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+int setup_msix_irqs(struct pci_dev *dev, int nvec)
 {
 	int node, ret, sub_handle, index = 0;
 	unsigned int irq, irq_want;
 	struct msi_desc *msidesc;
 
-	/* x86 doesn't support multiple MSI yet */
-	if (type == PCI_CAP_ID_MSI && nvec > 1)
-		return 1;
-
 	node = dev_to_node(&dev->dev);
 	irq_want = nr_irqs_gsi;
 	sub_handle = 0;

@@ -3208,7 +3286,7 @@ int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 				goto error;
 		}
 no_ir:
-		ret = setup_msi_irq(dev, msidesc, irq);
+		ret = setup_msi_irq(dev, msidesc, irq, 0);
 		if (ret < 0)
 			goto error;
 		sub_handle++;

@@ -3220,6 +3298,76 @@ error:
 	return ret;
 }
 
+int setup_msi_irqs(struct pci_dev *dev, int nvec)
+{
+	int node, ret, sub_handle, index = 0;
+	unsigned int irq;
+	struct msi_desc *msidesc;
+
+	if (nvec > 1 && !irq_remapping_enabled)
+		return 1;
+
+	nvec = __roundup_pow_of_two(nvec);
+	ret = can_create_pow_of_two_irqs(nr_irqs_gsi, nvec);
+	if (ret != nvec)
+		return ret;
+
+	WARN_ON(!list_is_singular(&dev->msi_list));
+	msidesc = list_entry(dev->msi_list.next, struct msi_desc, list);
+	WARN_ON(msidesc->irq);
+	WARN_ON(msidesc->msi_attrib.multiple);
+
+	node = dev_to_node(&dev->dev);
+	irq = create_irqs(nr_irqs_gsi, nvec, node);
+	if (irq == 0)
+		return -ENOSPC;
+
+	if (!irq_remapping_enabled) {
+		ret = setup_msi_irq(dev, msidesc, irq, 0);
+		if (ret < 0)
+			goto error;
+		return 0;
+	}
+
+	msidesc->msi_attrib.multiple = ilog2(nvec);
+	for (sub_handle = 0; sub_handle < nvec; sub_handle++) {
+		if (!sub_handle) {
+			index = msi_alloc_remapped_irq(dev, irq, nvec);
+			if (index < 0) {
+				ret = index;
+				goto error;
+			}
+		} else {
+			ret = msi_setup_remapped_irq(dev, irq + sub_handle,
+						     index, sub_handle);
+			if (ret < 0)
+				goto error;
+		}
+		ret = setup_msi_irq(dev, msidesc, irq, sub_handle);
+		if (ret < 0)
+			goto error;
+	}
+	return 0;
+
+error:
+	destroy_irqs(irq, nvec);
+
+	/* Restore altered MSI descriptor fields and prevent just destroyed
+	 * IRQs from tearing down again in default_teardown_msi_irqs()
+	 */
+	msidesc->irq = 0;
+	msidesc->msi_attrib.multiple = 0;
+
+	return ret;
+}
+
+int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+{
+	if (type == PCI_CAP_ID_MSI)
+		return setup_msi_irqs(dev, nvec);
+	return setup_msix_irqs(dev, nvec);
+}
+
 void native_teardown_msi_irq(unsigned int irq)
 {
 	destroy_irq(irq);

@@ -522,6 +522,8 @@ extern int irq_set_handler_data(unsigned int irq, void *data);
 extern int irq_set_chip_data(unsigned int irq, void *data);
 extern int irq_set_irq_type(unsigned int irq, unsigned int type);
 extern int irq_set_msi_desc(unsigned int irq, struct msi_desc *entry);
+extern int irq_set_msi_desc_off(unsigned int irq_base, unsigned int irq_offset,
+				struct msi_desc *entry);
 extern struct irq_data *irq_get_irq_data(unsigned int irq);
 
 static inline struct irq_chip *irq_get_chip(unsigned int irq)

@@ -584,8 +586,12 @@ int __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node,
 #define irq_alloc_desc_from(from, node)		\
 	irq_alloc_descs(-1, from, 1, node)
 
+#define irq_alloc_descs_from(from, cnt, node)	\
+	irq_alloc_descs(-1, from, cnt, node)
+
 void irq_free_descs(unsigned int irq, unsigned int cnt);
 int irq_reserve_irqs(unsigned int from, unsigned int cnt);
+int irq_can_alloc_irqs(unsigned int from, unsigned int cnt);
 
 static inline void irq_free_desc(unsigned int irq)
 {

@@ -90,27 +90,41 @@ int irq_set_handler_data(unsigned int irq, void *data)
 EXPORT_SYMBOL(irq_set_handler_data);
 
 /**
- *	irq_set_msi_desc - set MSI descriptor data for an irq
- *	@irq:	Interrupt number
- *	@entry:	Pointer to MSI descriptor data
+ *	irq_set_msi_desc_off - set MSI descriptor data for an irq at offset
+ *	@irq_base:	Interrupt number base
+ *	@irq_offset:	Interrupt number offset
+ *	@entry:		Pointer to MSI descriptor data
  *
- *	Set the MSI descriptor entry for an irq
+ *	Set the MSI descriptor entry for an irq at offset
  */
-int irq_set_msi_desc(unsigned int irq, struct msi_desc *entry)
+int irq_set_msi_desc_off(unsigned int irq_base, unsigned int irq_offset,
+			 struct msi_desc *entry)
 {
 	unsigned long flags;
-	struct irq_desc *desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL);
+	struct irq_desc *desc = irq_get_desc_lock(irq_base + irq_offset, &flags, IRQ_GET_DESC_CHECK_GLOBAL);
 
 	if (!desc)
 		return -EINVAL;
 	desc->irq_data.msi_desc = entry;
-	if (entry)
-		entry->irq = irq;
+	if (entry && !irq_offset)
+		entry->irq = irq_base;
 	irq_put_desc_unlock(desc, flags);
 	return 0;
 }
 
 /**
+ *	irq_set_msi_desc - set MSI descriptor data for an irq
+ *	@irq:	Interrupt number
+ *	@entry:	Pointer to MSI descriptor data
+ *
+ *	Set the MSI descriptor entry for an irq
+ */
+int irq_set_msi_desc(unsigned int irq, struct msi_desc *entry)
+{
+	return irq_set_msi_desc_off(irq, 0, entry);
+}
+
+/**
  *	irq_set_chip_data - set irq chip data for an irq
  *	@irq:	Interrupt number
  *	@data:	Pointer to chip specific data

@@ -210,6 +210,13 @@ static int irq_expand_nr_irqs(unsigned int nr)
 	return 0;
 }
 
+static int irq_can_expand_nr_irqs(unsigned int nr)
+{
+	if (nr > IRQ_BITMAP_BITS)
+		return -ENOMEM;
+	return 0;
+}
+
 int __init early_irq_init(void)
 {
 	int i, initcnt, node = first_online_node;

@@ -414,6 +421,30 @@ int irq_reserve_irqs(unsigned int from, unsigned int cnt)
 }
 
 /**
+ * irq_can_alloc_irqs - checks if a range of irqs could be allocated
+ * @from:	check from irq number
+ * @cnt:	number of irqs to check
+ *
+ * Returns 0 on success or an appropriate error code
+ */
+int irq_can_alloc_irqs(unsigned int from, unsigned int cnt)
+{
+	unsigned int start;
+	int ret = 0;
+
+	if (!cnt)
+		return -EINVAL;
+
+	mutex_lock(&sparse_irq_lock);
+	start = bitmap_find_next_zero_area(allocated_irqs, IRQ_BITMAP_BITS,
+					   from, cnt, 0);
+	mutex_unlock(&sparse_irq_lock);
+	if (start + cnt > nr_irqs)
+		ret = irq_can_expand_nr_irqs(start + cnt);
+	return ret;
+}
+
+/**
  * irq_get_next_irq - get next allocated irq number
  * @offset:	where to start the search
  *

@@ -3116,16 +3116,12 @@ static inline void destroy_irqs(unsigned int irq, unsigned int count)
 }
 
 static inline int
-can_create_pow_of_two_irqs(unsigned int from, unsigned int count)
+can_create_irqs(unsigned int from, unsigned int count)
 {
-	if ((count > 1) && (count % 2))
-		return -EINVAL;
-
-	for (; count; count = count / 2) {
+	for (; count; count = count - 1) {
 		if (!irq_can_alloc_irqs(from, count))
 			return count;
 	}
-
 	return -ENOSPC;
 }
 

@@ -3307,8 +3303,7 @@ int setup_msi_irqs(struct pci_dev *dev, int nvec)
 	if (nvec > 1 && !irq_remapping_enabled)
 		return 1;
 
-	nvec = __roundup_pow_of_two(nvec);
-	ret = can_create_pow_of_two_irqs(nr_irqs_gsi, nvec);
+	ret = can_create_irqs(nr_irqs_gsi, nvec);
 	if (ret != nvec)
 		return ret;
 

@@ -3316,11 +3311,13 @@ int setup_msi_irqs(struct pci_dev *dev, int nvec)
 	msidesc = list_entry(dev->msi_list.next, struct msi_desc, list);
 	WARN_ON(msidesc->irq);
 	WARN_ON(msidesc->msi_attrib.multiple);
+	WARN_ON(msidesc->nvec);
 
 	node = dev_to_node(&dev->dev);
 	irq = create_irqs(nr_irqs_gsi, nvec, node);
 	if (irq == 0)
 		return -ENOSPC;
+	msidesc->nvec = nvec;
 
 	if (!irq_remapping_enabled) {
 		ret = setup_msi_irq(dev, msidesc, irq, 0);

@@ -3329,7 +3326,7 @@ int setup_msi_irqs(struct pci_dev *dev, int nvec)
 		return 0;
 	}
 
-	msidesc->msi_attrib.multiple = ilog2(nvec);
+	msidesc->msi_attrib.multiple = ilog2(__roundup_pow_of_two(nvec));
 	for (sub_handle = 0; sub_handle < nvec; sub_handle++) {
 		if (!sub_handle) {
 			index = msi_alloc_remapped_irq(dev, irq, nvec);

@@ -3357,6 +3354,7 @@ error:
 	 */
 	msidesc->irq = 0;
 	msidesc->msi_attrib.multiple = 0;
+	msidesc->nvec = 0;
 
 	return ret;
 }

@@ -79,7 +79,10 @@ void default_teardown_msi_irqs(struct pci_dev *dev)
 		int i, nvec;
 		if (entry->irq == 0)
 			continue;
-		nvec = 1 << entry->msi_attrib.multiple;
+		if (entry->nvec)
+			nvec = entry->nvec;
+		else
+			nvec = 1 << entry->msi_attrib.multiple;
 		for (i = 0; i < nvec; i++)
 			arch_teardown_msi_irq(entry->irq + i);
 	}

@@ -336,7 +339,10 @@ static void free_msi_irqs(struct pci_dev *dev)
 		int i, nvec;
 		if (!entry->irq)
 			continue;
-		nvec = 1 << entry->msi_attrib.multiple;
+		if (entry->nvec)
+			nvec = entry->nvec;
+		else
+			nvec = 1 << entry->msi_attrib.multiple;
 		for (i = 0; i < nvec; i++)
 			BUG_ON(irq_has_action(entry->irq + i));
 	}

@@ -35,6 +35,7 @@ struct msi_desc {
 
 	u32 masked;			/* mask bits */
 	unsigned int irq;
+	unsigned int nvec;
 	struct list_head list;
 
 	union {

@@ -3151,7 +3151,7 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq,
 
 	if (irq_remapped(cfg)) {
 		compose_remapped_msi_msg(pdev, irq, dest, msg, hpet_id);
-		return err;
+		return 0;
 	}
 
 	if (x2apic_enabled())

@@ -3178,7 +3178,7 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq,
 			MSI_DATA_DELIVERY_LOWPRI) |
 		MSI_DATA_VECTOR(cfg->vector);
 
-	return err;
+	return 0;
 }
 
 static int

@@ -3260,7 +3260,7 @@ int setup_msix_irqs(struct pci_dev *dev, int nvec)
 	list_for_each_entry(msidesc, &dev->msi_list, list) {
 		irq = create_irq_nr(irq_want, node);
 		if (irq == 0)
-			return -1;
+			return -ENOSPC;
 		irq_want = irq + 1;
 		if (!irq_remapping_enabled)
 			goto no_ir;

@@ -127,15 +127,42 @@ on the number of vectors that can be allocated; pci_enable_msi_block()
 returns as soon as it finds any constraint that doesn't allow the
 call to succeed.
 
-4.2.3 pci_disable_msi
+4.2.3 pci_enable_msi_block_auto
+
+int pci_enable_msi_block_auto(struct pci_dev *dev, unsigned int *count)
+
+This variation on pci_enable_msi() call allows a device driver to request
+the maximum possible number of MSIs.  The MSI specification only allows
+interrupts to be allocated in powers of two, up to a maximum of 2^5 (32).
+
+If this function returns a positive number, it indicates that it has
+succeeded and the returned value is the number of allocated interrupts. In
+this case, the function enables MSI on this device and updates dev->irq to
+be the lowest of the new interrupts assigned to it.  The other interrupts
+assigned to the device are in the range dev->irq to dev->irq + returned
+value - 1.
+
+If this function returns a negative number, it indicates an error and
+the driver should not attempt to request any more MSI interrupts for
+this device.
+
+If the device driver needs to know the number of interrupts the device
+supports it can pass the pointer count where that number is stored. The
+device driver must decide what action to take if pci_enable_msi_block_auto()
+succeeds, but returns a value less than the number of interrupts supported.
+If the device driver does not need to know the number of interrupts
+supported, it can set the pointer count to NULL.
+
+4.2.4 pci_disable_msi
 
 void pci_disable_msi(struct pci_dev *dev)
 
 This function should be used to undo the effect of pci_enable_msi() or
-pci_enable_msi_block().  Calling it restores dev->irq to the pin-based
-interrupt number and frees the previously allocated message signaled
-interrupt(s).  The interrupt may subsequently be assigned to another
-device, so drivers should not cache the value of dev->irq.
+pci_enable_msi_block() or pci_enable_msi_block_auto().  Calling it restores
+dev->irq to the pin-based interrupt number and frees the previously
+allocated message signaled interrupt(s).  The interrupt may subsequently be
+assigned to another device, so drivers should not cache the value of
+dev->irq.
 
 Before calling this function, a device driver must always call free_irq()
 on any interrupt for which it previously called request_irq().

@@ -845,6 +845,32 @@ int pci_enable_msi_block(struct pci_dev *dev, unsigned int nvec)
 }
 EXPORT_SYMBOL(pci_enable_msi_block);
 
+int pci_enable_msi_block_auto(struct pci_dev *dev, unsigned int *maxvec)
+{
+	int ret, pos, nvec;
+	u16 msgctl;
+
+	pos = pci_find_capability(dev, PCI_CAP_ID_MSI);
+	if (!pos)
+		return -EINVAL;
+
+	pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &msgctl);
+	ret = 1 << ((msgctl & PCI_MSI_FLAGS_QMASK) >> 1);
+
+	if (maxvec)
+		*maxvec = ret;
+
+	do {
+		nvec = ret;
+		ret = pci_enable_msi_block(dev, nvec);
+	} while (ret > 0);
+
+	if (ret < 0)
+		return ret;
+	return nvec;
+}
+EXPORT_SYMBOL(pci_enable_msi_block_auto);
+
 void pci_msi_shutdown(struct pci_dev *dev)
 {
 	struct msi_desc *desc;

@@ -1070,6 +1070,12 @@ static inline int pci_enable_msi_block(struct pci_dev *dev, unsigned int nvec)
 	return -1;
 }
 
+static inline int
+pci_enable_msi_block_auto(struct pci_dev *dev, unsigned int *maxvec)
+{
+	return -1;
+}
+
 static inline void pci_msi_shutdown(struct pci_dev *dev)
 { }
 static inline void pci_disable_msi(struct pci_dev *dev)

@@ -1101,6 +1107,7 @@ static inline int pci_msi_enabled(void)
 }
 #else
 extern int pci_enable_msi_block(struct pci_dev *dev, unsigned int nvec);
+extern int pci_enable_msi_block_auto(struct pci_dev *dev, unsigned int *maxvec);
 extern void pci_msi_shutdown(struct pci_dev *dev);
 extern void pci_disable_msi(struct pci_dev *dev);
 extern int pci_msix_table_size(struct pci_dev *dev);

@@ -1057,7 +1057,7 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	struct device *dev = &pdev->dev;
 	struct ahci_host_priv *hpriv;
 	struct ata_host *host;
-	int n_ports, i, rc;
+	int n_ports, n_msis, i, rc;
 	int ahci_pci_bar = AHCI_PCI_BAR_STANDARD;
 
 	VPRINTK("ENTER\n");

@@ -1142,11 +1142,10 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (ahci_sb600_enable_64bit(pdev))
 		hpriv->flags &= ~AHCI_HFLAG_32BIT_ONLY;
 
-	if ((hpriv->flags & AHCI_HFLAG_NO_MSI) || pci_enable_msi(pdev))
-		pci_intx(pdev, 1);
-
 	hpriv->mmio = pcim_iomap_table(pdev)[ahci_pci_bar];
 
+	n_msis = ahci_init_interrupts(pdev, hpriv);
+
 	/* save initial config */
 	ahci_pci_save_initial_config(pdev, hpriv);
 

@@ -1242,8 +1241,11 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	ahci_pci_print_info(host);
 
 	pci_set_master(pdev);
-	return ata_host_activate(host, pdev->irq, ahci_interrupt, IRQF_SHARED,
-				 &ahci_sht);
+
+	if (!pdev->irq || (n_msis < 2))
+		return ata_host_activate(host, pdev->irq, ahci_interrupt,
+					 IRQF_SHARED, &ahci_sht);
+	return ahci_host_activate(host, pdev->irq, n_msis, &ahci_sht);
 }
 
 module_pci_driver(ahci_pci_driver);

@@ -282,6 +282,8 @@ struct ahci_port_priv {
 	unsigned int		ncq_saw_d2h:1;
 	unsigned int		ncq_saw_dmas:1;
 	unsigned int		ncq_saw_sdb:1;
+	u32			intr_status;	/* interrupts to handle */
+	spinlock_t		lock;
 	u32 			intr_mask;	/* interrupts to enable */
 	bool			fbs_supported;	/* set iff FBS is supported */
 	bool			fbs_enabled;	/* set iff FBS is enabled */

@@ -329,6 +331,7 @@ void ahci_save_initial_config(struct device *dev,
 			      unsigned int mask_port_map);
 void ahci_init_controller(struct ata_host *host);
 int ahci_reset_controller(struct ata_host *host);
+int ahci_init_interrupts(struct pci_dev *pdev, struct ahci_host_priv *hpriv);
 
 int ahci_do_softreset(struct ata_link *link, unsigned int *class,
 		      int pmp, unsigned long deadline,

@@ -344,6 +347,8 @@ void ahci_set_em_messages(struct ahci_host_priv *hpriv,
 int ahci_reset_em(struct ata_host *host);
 irqreturn_t ahci_interrupt(int irq, void *dev_instance);
 void ahci_print_info(struct ata_host *host, const char *scc_s);
+int ahci_host_activate(struct ata_host *host, int irq, unsigned int n_msis,
+		       struct scsi_host_template *sht);
 
 static inline void __iomem *__ahci_port_base(struct ata_host *host,
 					     unsigned int port_no)

@@ -39,6 +39,7 @@
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
+#include <linux/pci.h>
 #include <linux/dma-mapping.h>
 #include <linux/device.h>
 #include <scsi/scsi_host.h>

@@ -1128,6 +1129,29 @@ void ahci_init_controller(struct ata_host *host)
 }
 EXPORT_SYMBOL_GPL(ahci_init_controller);
 
+int ahci_init_interrupts(struct pci_dev *pdev, struct ahci_host_priv *hpriv)
+{
+	int rc;
+	unsigned int maxvec;
+
+	if (!(hpriv->flags & AHCI_HFLAG_NO_MSI)) {
+		rc = pci_enable_msi_block_auto(pdev, &maxvec);
+		if (rc > 0) {
+			if ((rc == maxvec) || (rc == 1))
+				return rc;
+			/* assume that advantage of multipe MSIs is negated,
+			 * so fallback to single MSI mode to save resources */
+			pci_disable_msi(pdev);
+			if (!pci_enable_msi(pdev))
+				return 1;
+		}
+	}
+
+	pci_intx(pdev, 1);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ahci_init_interrupts);
+
 static void ahci_dev_config(struct ata_device *dev)
 {
 	struct ahci_host_priv *hpriv = dev->link->ap->host->private_data;

@@ -1639,19 +1663,16 @@ static void ahci_error_intr(struct ata_port *ap, u32 irq_stat)
 		ata_port_abort(ap);
 }
 
-static void ahci_port_intr(struct ata_port *ap)
+static void ahci_handle_port_interrupt(struct ata_port *ap,
+				       void __iomem *port_mmio, u32 status)
 {
-	void __iomem *port_mmio = ahci_port_base(ap);
 	struct ata_eh_info *ehi = &ap->link.eh_info;
 	struct ahci_port_priv *pp = ap->private_data;
 	struct ahci_host_priv *hpriv = ap->host->private_data;
 	int resetting = !!(ap->pflags & ATA_PFLAG_RESETTING);
-	u32 status, qc_active = 0;
+	u32 qc_active = 0;
 	int rc;
 
-	status = readl(port_mmio + PORT_IRQ_STAT);
-	writel(status, port_mmio + PORT_IRQ_STAT);
-
 	/* ignore BAD_PMP while resetting */
 	if (unlikely(resetting))
 		status &= ~PORT_IRQ_BAD_PMP;

@@ -1727,6 +1748,105 @@ static void ahci_port_intr(struct ata_port *ap)
 	}
 }
 
+static inline void ahci_port_intr(struct ata_port *ap)
+{
+	void __iomem *port_mmio = ahci_port_base(ap);
+	u32 status;
+
+	status = readl(port_mmio + PORT_IRQ_STAT);
+	writel(status, port_mmio + PORT_IRQ_STAT);
+
+	ahci_handle_port_interrupt(ap, port_mmio, status);
+}
+
+irqreturn_t ahci_thread_fn(int irq, void *dev_instance)
+{
+	struct ata_port *ap = dev_instance;
+	struct ahci_port_priv *pp = ap->private_data;
+	void __iomem *port_mmio = ahci_port_base(ap);
+	unsigned long flags;
+	u32 status;
+
+	spin_lock_irqsave(&ap->host->lock, flags);
+	status = pp->intr_status;
+	if (status)
+		pp->intr_status = 0;
+	spin_unlock_irqrestore(&ap->host->lock, flags);
+
+	spin_lock_bh(ap->lock);
+	ahci_handle_port_interrupt(ap, port_mmio, status);
+	spin_unlock_bh(ap->lock);
+
+	return IRQ_HANDLED;
+}
+
+static inline void ahci_hw_port_interrupt(struct ata_port *ap)
+{
+	void __iomem *port_mmio = ahci_port_base(ap);
+	struct ahci_port_priv *pp = ap->private_data;
+	u32 status;
+
+	status = readl(port_mmio + PORT_IRQ_STAT);
+	writel(status, port_mmio + PORT_IRQ_STAT);
+
+	pp->intr_status |= status;
+}
+
+irqreturn_t ahci_hw_interrupt(int irq, void *dev_instance)
+{
+	struct ata_port *ap_this = dev_instance;
+	struct ahci_port_priv *pp = ap_this->private_data;
+	struct ata_host *host = ap_this->host;
+	struct ahci_host_priv *hpriv = host->private_data;
+	void __iomem *mmio = hpriv->mmio;
+	unsigned int i;
+	u32 irq_stat, irq_masked;
+
+	VPRINTK("ENTER\n");
+
+	spin_lock(&host->lock);
+
+	irq_stat = readl(mmio + HOST_IRQ_STAT);
+
+	if (!irq_stat) {
+		u32 status = pp->intr_status;
+
+		spin_unlock(&host->lock);
+
+		VPRINTK("EXIT\n");
+
+		return status ? IRQ_WAKE_THREAD : IRQ_NONE;
+	}
+
+	irq_masked = irq_stat & hpriv->port_map;
+
+	for (i = 0; i < host->n_ports; i++) {
+		struct ata_port *ap;
+
+		if (!(irq_masked & (1 << i)))
+			continue;
+
+		ap = host->ports[i];
+		if (ap) {
+			ahci_hw_port_interrupt(ap);
+			VPRINTK("port %u\n", i);
+		} else {
+			VPRINTK("port %u (no irq)\n", i);
+			if (ata_ratelimit())
+				dev_warn(host->dev,
+					 "interrupt on disabled port %u\n", i);
+		}
+	}
+
+	writel(irq_stat, mmio + HOST_IRQ_STAT);
+
+	spin_unlock(&host->lock);
+
+	VPRINTK("EXIT\n");
+
+	return IRQ_WAKE_THREAD;
+}
+
 irqreturn_t ahci_interrupt(int irq, void *dev_instance)
 {
 	struct ata_host *host = dev_instance;

@@ -2216,6 +2336,85 @@ void ahci_set_em_messages(struct ahci_host_priv *hpriv,
 }
 EXPORT_SYMBOL_GPL(ahci_set_em_messages);
 
+static inline void ahci_set_per_port_locking(struct ata_host *host)
+{
+	struct ata_port *ap;
+	struct ahci_port_priv *pp;
+	int i;
+
+	for (i = 0; i < host->n_ports; i++) {
+		ap = host->ports[i];
+		pp = ap->private_data;
+
+		spin_lock_init(&pp->lock);
+		ap->lock = &pp->lock;
+	}
+}
+
+/**
+ *	ahci_host_activate - start AHCI host, request IRQs and register it
+ *	@host: target ATA host
+ *	@irq: base IRQ number to request
+ *	@n_msis: number of MSIs allocated for this host
+ *	@irq_handler: irq_handler used when requesting IRQs
+ *	@irq_flags: irq_flags used when requesting IRQs
+ *	@sht: scsi_host_template to use when registering the host
+ *
+ *	Similar to ata_host_activate, but requests IRQs according to AHCI-1.1
+ *	when multiple MSIs were allocated. That is one MSI per port, starting
+ *	from @irq. Also, when number of MSIs is less than number of ports,
+ *	last MSI is shared among those ports which did not get their personal
+ *	MSI vector - see 10.6.2.3.1.
+ *
+ *	LOCKING:
+ *	Inherited from calling layer (may sleep).
+ *
+ *	RETURNS:
+ *	0 on success, -errno otherwise.
+ */
+int ahci_host_activate(struct ata_host *host, int irq, unsigned int n_msis,
+		       struct scsi_host_template *sht)
+{
+	int i, rc;
+	unsigned int n_irqs;
+
+	rc = ata_host_start(host);
+	if (rc)
+		return rc;
+
+	ahci_set_per_port_locking(host);
+
+	n_irqs = min(host->n_ports, n_msis);
+
+	for (i = 0; i < n_irqs; i++) {
+		rc = devm_request_threaded_irq(host->dev,
+			irq + i, ahci_hw_interrupt, ahci_thread_fn, IRQF_SHARED,
+			dev_driver_string(host->dev), host->ports[i]);
+		if (rc)
+			goto out_free_irqs;
+	}
+
+	for (i = 0; i < n_irqs; i++)
+		ata_port_desc(host->ports[i], "irq %d", irq + i);
+	for (; i < host->n_ports; i++)
+		ata_port_desc(host->ports[i], "irq %d", n_irqs - 1);
+
+	rc = ata_host_register(host, sht);
+	if (rc)
+		goto out_free_all_irqs;
+
+	return 0;
+
+out_free_all_irqs:
+	i = n_irqs;
+out_free_irqs:
+	for (; i; i--)
+		devm_free_irq(host->dev, irq + i - 1, host);
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(ahci_host_activate);
+
 MODULE_AUTHOR("Jeff Garzik");
 MODULE_DESCRIPTION("Common AHCI SATA low-level routines");
 MODULE_LICENSE("GPL");