X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=drivers%2Fpci%2Fmsi.c;h=057f8b4f50c3babd3fbd0f591d36887613861c42;hb=97bf2856c6014879bd04983a3e9dfcdac1e7fe85;hp=48723d6fa60f249343ee4bc7b065aed0150d8c01;hpb=76828883507a47dae78837ab5dec5a5b4513c667;p=linux-2.6.git

diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 48723d6fa..057f8b4f5 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -6,15 +6,16 @@
  * Copyright (C) Tom Long Nguyen (tom.l.nguyen@intel.com)
  */
 
+#include <linux/err.h>
 #include <linux/mm.h>
 #include <linux/irq.h>
 #include <linux/interrupt.h>
 #include <linux/init.h>
-#include <linux/config.h>
 #include <linux/ioport.h>
 #include <linux/smp_lock.h>
 #include <linux/pci.h>
 #include <linux/proc_fs.h>
+#include <linux/msi.h>
 
 #include <asm/errno.h>
 #include <asm/io.h>
@@ -23,338 +24,178 @@
 #include "pci.h"
 #include "msi.h"
 
-#define MSI_TARGET_CPU		first_cpu(cpu_online_map)
-
 static DEFINE_SPINLOCK(msi_lock);
 static struct msi_desc* msi_desc[NR_IRQS] = { [0 ... NR_IRQS-1] = NULL };
-static kmem_cache_t* msi_cachep;
-
-static int pci_msi_enable = 1;
-static int last_alloc_vector;
-static int nr_released_vectors;
-static int nr_reserved_vectors = NR_HP_RESERVED_VECTORS;
-static int nr_msix_devices;
+static struct kmem_cache* msi_cachep;
 
-#ifndef CONFIG_X86_IO_APIC
-int vector_irq[NR_VECTORS] = { [0 ... NR_VECTORS - 1] = -1};
-u8 irq_vector[NR_IRQ_VECTORS] = { FIRST_DEVICE_VECTOR , 0 };
-#endif
-
-static void msi_cache_ctor(void *p, kmem_cache_t *cache, unsigned long flags)
-{
-	memset(p, 0, NR_IRQS * sizeof(struct msi_desc));
-}
+static int pci_msi_enable = 0;
 
 static int msi_cache_init(void)
 {
-	msi_cachep = kmem_cache_create("msi_cache",
-			NR_IRQS * sizeof(struct msi_desc),
-		       	0, SLAB_HWCACHE_ALIGN, msi_cache_ctor, NULL);
+	msi_cachep = kmem_cache_create("msi_cache", sizeof(struct msi_desc),
+					0, SLAB_HWCACHE_ALIGN, NULL, NULL);
 	if (!msi_cachep)
 		return -ENOMEM;
 
 	return 0;
 }
 
-static void msi_set_mask_bit(unsigned int vector, int flag)
+void msix_flush_writes(unsigned int irq)
 {
 	struct msi_desc *entry;
 
-	entry = (struct msi_desc *)msi_desc[vector];
-	if (!entry || !entry->dev || !entry->mask_base)
-		return;
+	entry = msi_desc[irq];
+	BUG_ON(!entry || !entry->dev);
 	switch (entry->msi_attrib.type) {
 	case PCI_CAP_ID_MSI:
-	{
-		int		pos;
-		u32		mask_bits;
-
-		pos = (long)entry->mask_base;
-		pci_read_config_dword(entry->dev, pos, &mask_bits);
-		mask_bits &= ~(1);
-		mask_bits |= flag;
-		pci_write_config_dword(entry->dev, pos, mask_bits);
+		/* nothing to do */
 		break;
-	}
 	case PCI_CAP_ID_MSIX:
 	{
 		int offset = entry->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE +
 			PCI_MSIX_ENTRY_VECTOR_CTRL_OFFSET;
-		writel(flag, entry->mask_base + offset);
+		readl(entry->mask_base + offset);
 		break;
 	}
 	default:
+		BUG();
 		break;
 	}
 }
 
-#ifdef CONFIG_SMP
-static void set_msi_affinity(unsigned int vector, cpumask_t cpu_mask)
+static void msi_set_mask_bit(unsigned int irq, int flag)
 {
 	struct msi_desc *entry;
-	struct msg_address address;
-	unsigned int irq = vector;
-	unsigned int dest_cpu = first_cpu(cpu_mask);
-
-	entry = (struct msi_desc *)msi_desc[vector];
-	if (!entry || !entry->dev)
-		return;
 
+	entry = msi_desc[irq];
+	BUG_ON(!entry || !entry->dev);
 	switch (entry->msi_attrib.type) {
 	case PCI_CAP_ID_MSI:
-	{
-		int pos;
-
-   		if (!(pos = pci_find_capability(entry->dev, PCI_CAP_ID_MSI)))
-			return;
-
-		pci_read_config_dword(entry->dev, msi_lower_address_reg(pos),
-			&address.lo_address.value);
-		address.lo_address.value &= MSI_ADDRESS_DEST_ID_MASK;
-		address.lo_address.value |= (cpu_physical_id(dest_cpu) <<
-									MSI_TARGET_CPU_SHIFT);
-		entry->msi_attrib.current_cpu = cpu_physical_id(dest_cpu);
-		pci_write_config_dword(entry->dev, msi_lower_address_reg(pos),
-			address.lo_address.value);
-		set_native_irq_info(irq, cpu_mask);
+		if (entry->msi_attrib.maskbit) {
+			int		pos;
+			u32		mask_bits;
+
+			pos = (long)entry->mask_base;
+			pci_read_config_dword(entry->dev, pos, &mask_bits);
+			mask_bits &= ~(1);
+			mask_bits |= flag;
+			pci_write_config_dword(entry->dev, pos, mask_bits);
+		}
 		break;
-	}
 	case PCI_CAP_ID_MSIX:
 	{
 		int offset = entry->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE +
-			PCI_MSIX_ENTRY_LOWER_ADDR_OFFSET;
-
-		address.lo_address.value = readl(entry->mask_base + offset);
-		address.lo_address.value &= MSI_ADDRESS_DEST_ID_MASK;
-		address.lo_address.value |= (cpu_physical_id(dest_cpu) <<
-									MSI_TARGET_CPU_SHIFT);
-		entry->msi_attrib.current_cpu = cpu_physical_id(dest_cpu);
-		writel(address.lo_address.value, entry->mask_base + offset);
-		set_native_irq_info(irq, cpu_mask);
+			PCI_MSIX_ENTRY_VECTOR_CTRL_OFFSET;
+		writel(flag, entry->mask_base + offset);
 		break;
 	}
 	default:
+		BUG();
 		break;
 	}
 }
-#else
-#define set_msi_affinity NULL
-#endif /* CONFIG_SMP */
 
-static void mask_MSI_irq(unsigned int vector)
+void read_msi_msg(unsigned int irq, struct msi_msg *msg)
 {
-	msi_set_mask_bit(vector, 1);
-}
-
-static void unmask_MSI_irq(unsigned int vector)
-{
-	msi_set_mask_bit(vector, 0);
-}
-
-static unsigned int startup_msi_irq_wo_maskbit(unsigned int vector)
-{
-	struct msi_desc *entry;
-	unsigned long flags;
-
-	spin_lock_irqsave(&msi_lock, flags);
-	entry = msi_desc[vector];
-	if (!entry || !entry->dev) {
-		spin_unlock_irqrestore(&msi_lock, flags);
-		return 0;
+	struct msi_desc *entry = get_irq_data(irq);
+	switch(entry->msi_attrib.type) {
+	case PCI_CAP_ID_MSI:
+	{
+		struct pci_dev *dev = entry->dev;
+		int pos = entry->msi_attrib.pos;
+		u16 data;
+
+		pci_read_config_dword(dev, msi_lower_address_reg(pos),
+					&msg->address_lo);
+		if (entry->msi_attrib.is_64) {
+			pci_read_config_dword(dev, msi_upper_address_reg(pos),
+						&msg->address_hi);
+			pci_read_config_word(dev, msi_data_reg(pos, 1), &data);
+		} else {
+			msg->address_hi = 0;
+			pci_read_config_word(dev, msi_data_reg(pos, 1), &data);
+		}
+		msg->data = data;
+		break;
 	}
-	entry->msi_attrib.state = 1;	/* Mark it active */
-	spin_unlock_irqrestore(&msi_lock, flags);
-
-	return 0;	/* never anything pending */
-}
-
-static unsigned int startup_msi_irq_w_maskbit(unsigned int vector)
-{
-	startup_msi_irq_wo_maskbit(vector);
-	unmask_MSI_irq(vector);
-	return 0;	/* never anything pending */
-}
-
-static void shutdown_msi_irq(unsigned int vector)
-{
-	struct msi_desc *entry;
-	unsigned long flags;
+	case PCI_CAP_ID_MSIX:
+	{
+		void __iomem *base;
+		base = entry->mask_base +
+			entry->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE;
 
-	spin_lock_irqsave(&msi_lock, flags);
-	entry = msi_desc[vector];
-	if (entry && entry->dev)
-		entry->msi_attrib.state = 0;	/* Mark it not active */
-	spin_unlock_irqrestore(&msi_lock, flags);
+		msg->address_lo = readl(base + PCI_MSIX_ENTRY_LOWER_ADDR_OFFSET);
+		msg->address_hi = readl(base + PCI_MSIX_ENTRY_UPPER_ADDR_OFFSET);
+		msg->data = readl(base + PCI_MSIX_ENTRY_DATA_OFFSET);
+ 		break;
+ 	}
+ 	default:
+		BUG();
+	}
 }
 
-static void end_msi_irq_wo_maskbit(unsigned int vector)
+void write_msi_msg(unsigned int irq, struct msi_msg *msg)
 {
-	move_native_irq(vector);
-	ack_APIC_irq();
+	struct msi_desc *entry = get_irq_data(irq);
+	switch (entry->msi_attrib.type) {
+	case PCI_CAP_ID_MSI:
+	{
+		struct pci_dev *dev = entry->dev;
+		int pos = entry->msi_attrib.pos;
+
+		pci_write_config_dword(dev, msi_lower_address_reg(pos),
+					msg->address_lo);
+		if (entry->msi_attrib.is_64) {
+			pci_write_config_dword(dev, msi_upper_address_reg(pos),
+						msg->address_hi);
+			pci_write_config_word(dev, msi_data_reg(pos, 1),
+						msg->data);
+		} else {
+			pci_write_config_word(dev, msi_data_reg(pos, 0),
+						msg->data);
+		}
+		break;
+	}
+	case PCI_CAP_ID_MSIX:
+	{
+		void __iomem *base;
+		base = entry->mask_base +
+			entry->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE;
+
+		writel(msg->address_lo,
+			base + PCI_MSIX_ENTRY_LOWER_ADDR_OFFSET);
+		writel(msg->address_hi,
+			base + PCI_MSIX_ENTRY_UPPER_ADDR_OFFSET);
+		writel(msg->data, base + PCI_MSIX_ENTRY_DATA_OFFSET);
+		break;
+	}
+	default:
+		BUG();
+	}
 }
 
-static void end_msi_irq_w_maskbit(unsigned int vector)
+void mask_msi_irq(unsigned int irq)
 {
-	move_native_irq(vector);
-	unmask_MSI_irq(vector);
-	ack_APIC_irq();
+	msi_set_mask_bit(irq, 1);
 }
 
-static void do_nothing(unsigned int vector)
+void unmask_msi_irq(unsigned int irq)
 {
+	msi_set_mask_bit(irq, 0);
 }
 
-/*
- * Interrupt Type for MSI-X PCI/PCI-X/PCI-Express Devices,
- * which implement the MSI-X Capability Structure.
- */
-static struct hw_interrupt_type msix_irq_type = {
-	.typename	= "PCI-MSI-X",
-	.startup	= startup_msi_irq_w_maskbit,
-	.shutdown	= shutdown_msi_irq,
-	.enable		= unmask_MSI_irq,
-	.disable	= mask_MSI_irq,
-	.ack		= mask_MSI_irq,
-	.end		= end_msi_irq_w_maskbit,
-	.set_affinity	= set_msi_affinity
-};
-
-/*
- * Interrupt Type for MSI PCI/PCI-X/PCI-Express Devices,
- * which implement the MSI Capability Structure with
- * Mask-and-Pending Bits.
- */
-static struct hw_interrupt_type msi_irq_w_maskbit_type = {
-	.typename	= "PCI-MSI",
-	.startup	= startup_msi_irq_w_maskbit,
-	.shutdown	= shutdown_msi_irq,
-	.enable		= unmask_MSI_irq,
-	.disable	= mask_MSI_irq,
-	.ack		= mask_MSI_irq,
-	.end		= end_msi_irq_w_maskbit,
-	.set_affinity	= set_msi_affinity
-};
-
-/*
- * Interrupt Type for MSI PCI/PCI-X/PCI-Express Devices,
- * which implement the MSI Capability Structure without
- * Mask-and-Pending Bits.
- */
-static struct hw_interrupt_type msi_irq_wo_maskbit_type = {
-	.typename	= "PCI-MSI",
-	.startup	= startup_msi_irq_wo_maskbit,
-	.shutdown	= shutdown_msi_irq,
-	.enable		= do_nothing,
-	.disable	= do_nothing,
-	.ack		= do_nothing,
-	.end		= end_msi_irq_wo_maskbit,
-	.set_affinity	= set_msi_affinity
-};
-
-static void msi_data_init(struct msg_data *msi_data,
-			  unsigned int vector)
+void disable_msi_irq(unsigned int irq)
 {
-	memset(msi_data, 0, sizeof(struct msg_data));
-	msi_data->vector = (u8)vector;
-	msi_data->delivery_mode = MSI_DELIVERY_MODE;
-	msi_data->level = MSI_LEVEL_MODE;
-	msi_data->trigger = MSI_TRIGGER_MODE;
+	msi_set_mask_bit(irq, 1);
+	msix_flush_writes(irq);
 }
 
-static void msi_address_init(struct msg_address *msi_address)
+void enable_msi_irq(unsigned int irq)
 {
-	unsigned int	dest_id;
-	unsigned long	dest_phys_id = cpu_physical_id(MSI_TARGET_CPU);
-
-	memset(msi_address, 0, sizeof(struct msg_address));
-	msi_address->hi_address = (u32)0;
-	dest_id = (MSI_ADDRESS_HEADER << MSI_ADDRESS_HEADER_SHIFT);
-	msi_address->lo_address.u.dest_mode = MSI_PHYSICAL_MODE;
-	msi_address->lo_address.u.redirection_hint = MSI_REDIRECTION_HINT_MODE;
-	msi_address->lo_address.u.dest_id = dest_id;
-	msi_address->lo_address.value |= (dest_phys_id << MSI_TARGET_CPU_SHIFT);
+	msi_set_mask_bit(irq, 0);
+	msix_flush_writes(irq);
 }
-
-static int msi_free_vector(struct pci_dev* dev, int vector, int reassign);
-static int assign_msi_vector(void)
-{
-	static int new_vector_avail = 1;
-	int vector;
-	unsigned long flags;
-
-	/*
-	 * msi_lock is provided to ensure that successful allocation of MSI
-	 * vector is assigned unique among drivers.
-	 */
-	spin_lock_irqsave(&msi_lock, flags);
-
-	if (!new_vector_avail) {
-		int free_vector = 0;
-
-		/*
-	 	 * vector_irq[] = -1 indicates that this specific vector is:
-	 	 * - assigned for MSI (since MSI have no associated IRQ) or
-	 	 * - assigned for legacy if less than 16, or
-	 	 * - having no corresponding 1:1 vector-to-IOxAPIC IRQ mapping
-	 	 * vector_irq[] = 0 indicates that this vector, previously
-		 * assigned for MSI, is freed by hotplug removed operations.
-		 * This vector will be reused for any subsequent hotplug added
-		 * operations.
-	 	 * vector_irq[] > 0 indicates that this vector is assigned for
-		 * IOxAPIC IRQs. This vector and its value provides a 1-to-1
-		 * vector-to-IOxAPIC IRQ mapping.
-	 	 */
-		for (vector = FIRST_DEVICE_VECTOR; vector < NR_IRQS; vector++) {
-			if (vector_irq[vector] != 0)
-				continue;
-			free_vector = vector;
-			if (!msi_desc[vector])
-			      	break;
-			else
-				continue;
-		}
-		if (!free_vector) {
-			spin_unlock_irqrestore(&msi_lock, flags);
-			return -EBUSY;
-		}
-		vector_irq[free_vector] = -1;
-		nr_released_vectors--;
-		spin_unlock_irqrestore(&msi_lock, flags);
-		if (msi_desc[free_vector] != NULL) {
-			struct pci_dev *dev;
-			int tail;
-
-			/* free all linked vectors before re-assign */
-			do {
-				spin_lock_irqsave(&msi_lock, flags);
-				dev = msi_desc[free_vector]->dev;
-				tail = msi_desc[free_vector]->link.tail;
-				spin_unlock_irqrestore(&msi_lock, flags);
-				msi_free_vector(dev, tail, 1);
-			} while (free_vector != tail);
-		}
-
-		return free_vector;
-	}
-	vector = assign_irq_vector(AUTO_ASSIGN);
-	last_alloc_vector = vector;
-	if (vector  == LAST_DEVICE_VECTOR)
-		new_vector_avail = 0;
-
-	spin_unlock_irqrestore(&msi_lock, flags);
-	return vector;
-}
-
-static int get_new_vector(void)
-{
-	int vector;
-
-	if ((vector = assign_msi_vector()) > 0)
-		set_intr_gate(vector, interrupt[vector]);
-
-	return vector;
-}
-
+static int msi_free_irq(struct pci_dev* dev, int irq);
 static int msi_init(void)
 {
 	static int status = -ENOMEM;
@@ -369,67 +210,68 @@ static int msi_init(void)
 		return status;
 	}
 
-	if ((status = msi_cache_init()) < 0) {
+	status = msi_cache_init();
+	if (status < 0) {
 		pci_msi_enable = 0;
 		printk(KERN_WARNING "PCI: MSI cache init failed\n");
 		return status;
 	}
-	last_alloc_vector = assign_irq_vector(AUTO_ASSIGN);
-	if (last_alloc_vector < 0) {
-		pci_msi_enable = 0;
-		printk(KERN_WARNING "PCI: No interrupt vectors available for MSI\n");
-		status = -EBUSY;
-		return status;
-	}
-	vector_irq[last_alloc_vector] = 0;
-	nr_released_vectors++;
 
 	return status;
 }
 
-static int get_msi_vector(struct pci_dev *dev)
-{
-	return get_new_vector();
-}
-
 static struct msi_desc* alloc_msi_entry(void)
 {
 	struct msi_desc *entry;
 
-	entry = kmem_cache_alloc(msi_cachep, SLAB_KERNEL);
+	entry = kmem_cache_zalloc(msi_cachep, GFP_KERNEL);
 	if (!entry)
 		return NULL;
 
-	memset(entry, 0, sizeof(struct msi_desc));
 	entry->link.tail = entry->link.head = 0;	/* single message */
 	entry->dev = NULL;
 
 	return entry;
 }
 
-static void attach_msi_entry(struct msi_desc *entry, int vector)
+static void attach_msi_entry(struct msi_desc *entry, int irq)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(&msi_lock, flags);
-	msi_desc[vector] = entry;
+	msi_desc[irq] = entry;
 	spin_unlock_irqrestore(&msi_lock, flags);
 }
 
-static void irq_handler_init(int cap_id, int pos, int mask)
+static int create_msi_irq(void)
 {
-	unsigned long flags;
+	struct msi_desc *entry;
+	int irq;
+
+	entry = alloc_msi_entry();
+	if (!entry)
+		return -ENOMEM;
 
-	spin_lock_irqsave(&irq_desc[pos].lock, flags);
-	if (cap_id == PCI_CAP_ID_MSIX)
-		irq_desc[pos].handler = &msix_irq_type;
-	else {
-		if (!mask)
-			irq_desc[pos].handler = &msi_irq_wo_maskbit_type;
-		else
-			irq_desc[pos].handler = &msi_irq_w_maskbit_type;
+	irq = create_irq();
+	if (irq < 0) {
+		kmem_cache_free(msi_cachep, entry);
+		return -EBUSY;
 	}
-	spin_unlock_irqrestore(&irq_desc[pos].lock, flags);
+
+	set_irq_data(irq, entry);
+
+	return irq;
+}
+
+static void destroy_msi_irq(unsigned int irq)
+{
+	struct msi_desc *entry;
+
+	entry = get_irq_data(irq);
+	set_irq_chip(irq, NULL);
+	set_irq_data(irq, NULL);
+	destroy_irq(irq);
+	kmem_cache_free(msi_cachep, entry);
 }
 
 static void enable_msi_mode(struct pci_dev *dev, int pos, int type)
@@ -441,14 +283,14 @@ static void enable_msi_mode(struct pci_dev *dev, int pos, int type)
 		/* Set enabled bits to single MSI & enable MSI_enable bit */
 		msi_enable(control, 1);
 		pci_write_config_word(dev, msi_control_reg(pos), control);
+		dev->msi_enabled = 1;
 	} else {
 		msix_enable(control);
 		pci_write_config_word(dev, msi_control_reg(pos), control);
+		dev->msix_enabled = 1;
 	}
-    	if (pci_find_capability(dev, PCI_CAP_ID_EXP)) {
-		/* PCI Express Endpoint device detected */
-		pci_intx(dev, 0);  /* disable intx */
-	}
+
+	pci_intx(dev, 0);  /* disable intx */
 }
 
 void disable_msi_mode(struct pci_dev *dev, int pos, int type)
@@ -460,31 +302,31 @@ void disable_msi_mode(struct pci_dev *dev, int pos, int type)
 		/* Set enabled bits to single MSI & enable MSI_enable bit */
 		msi_disable(control);
 		pci_write_config_word(dev, msi_control_reg(pos), control);
+		dev->msi_enabled = 0;
 	} else {
 		msix_disable(control);
 		pci_write_config_word(dev, msi_control_reg(pos), control);
+		dev->msix_enabled = 0;
 	}
-    	if (pci_find_capability(dev, PCI_CAP_ID_EXP)) {
-		/* PCI Express Endpoint device detected */
-		pci_intx(dev, 1);  /* enable intx */
-	}
+
+	pci_intx(dev, 1);  /* enable intx */
 }
 
-static int msi_lookup_vector(struct pci_dev *dev, int type)
+static int msi_lookup_irq(struct pci_dev *dev, int type)
 {
-	int vector;
+	int irq;
 	unsigned long flags;
 
 	spin_lock_irqsave(&msi_lock, flags);
-	for (vector = FIRST_DEVICE_VECTOR; vector < NR_IRQS; vector++) {
-		if (!msi_desc[vector] || msi_desc[vector]->dev != dev ||
-			msi_desc[vector]->msi_attrib.type != type ||
-			msi_desc[vector]->msi_attrib.default_vector != dev->irq)
+	for (irq = 0; irq < NR_IRQS; irq++) {
+		if (!msi_desc[irq] || msi_desc[irq]->dev != dev ||
+			msi_desc[irq]->msi_attrib.type != type ||
+			msi_desc[irq]->msi_attrib.default_irq != dev->irq)
 			continue;
 		spin_unlock_irqrestore(&msi_lock, flags);
-		/* This pre-assigned MSI vector for this device
-		   already exits. Override dev->irq with this vector */
-		dev->irq = vector;
+		/* This pre-assigned MSI irq for this device
+		   already exits. Override dev->irq with this irq */
+		dev->irq = irq;
 		return 0;
 	}
 	spin_unlock_irqrestore(&msi_lock, flags);
@@ -496,70 +338,199 @@ void pci_scan_msi_device(struct pci_dev *dev)
 {
 	if (!dev)
 		return;
+}
+
+#ifdef CONFIG_PM
+int pci_save_msi_state(struct pci_dev *dev)
+{
+	int pos, i = 0;
+	u16 control;
+	struct pci_cap_saved_state *save_state;
+	u32 *cap;
+
+	pos = pci_find_capability(dev, PCI_CAP_ID_MSI);
+	if (pos <= 0 || dev->no_msi)
+		return 0;
+
+	pci_read_config_word(dev, msi_control_reg(pos), &control);
+	if (!(control & PCI_MSI_FLAGS_ENABLE))
+		return 0;
+
+	save_state = kzalloc(sizeof(struct pci_cap_saved_state) + sizeof(u32) * 5,
+		GFP_KERNEL);
+	if (!save_state) {
+		printk(KERN_ERR "Out of memory in pci_save_msi_state\n");
+		return -ENOMEM;
+	}
+	cap = &save_state->data[0];
+
+	pci_read_config_dword(dev, pos, &cap[i++]);
+	control = cap[0] >> 16;
+	pci_read_config_dword(dev, pos + PCI_MSI_ADDRESS_LO, &cap[i++]);
+	if (control & PCI_MSI_FLAGS_64BIT) {
+		pci_read_config_dword(dev, pos + PCI_MSI_ADDRESS_HI, &cap[i++]);
+		pci_read_config_dword(dev, pos + PCI_MSI_DATA_64, &cap[i++]);
+	} else
+		pci_read_config_dword(dev, pos + PCI_MSI_DATA_32, &cap[i++]);
+	if (control & PCI_MSI_FLAGS_MASKBIT)
+		pci_read_config_dword(dev, pos + PCI_MSI_MASK_BIT, &cap[i++]);
+	save_state->cap_nr = PCI_CAP_ID_MSI;
+	pci_add_saved_cap(dev, save_state);
+	return 0;
+}
+
+void pci_restore_msi_state(struct pci_dev *dev)
+{
+	int i = 0, pos;
+	u16 control;
+	struct pci_cap_saved_state *save_state;
+	u32 *cap;
+
+	save_state = pci_find_saved_cap(dev, PCI_CAP_ID_MSI);
+	pos = pci_find_capability(dev, PCI_CAP_ID_MSI);
+	if (!save_state || pos <= 0)
+		return;
+	cap = &save_state->data[0];
 
-   	if (pci_find_capability(dev, PCI_CAP_ID_MSIX) > 0)
-		nr_msix_devices++;
-	else if (pci_find_capability(dev, PCI_CAP_ID_MSI) > 0)
-		nr_reserved_vectors++;
+	control = cap[i++] >> 16;
+	pci_write_config_dword(dev, pos + PCI_MSI_ADDRESS_LO, cap[i++]);
+	if (control & PCI_MSI_FLAGS_64BIT) {
+		pci_write_config_dword(dev, pos + PCI_MSI_ADDRESS_HI, cap[i++]);
+		pci_write_config_dword(dev, pos + PCI_MSI_DATA_64, cap[i++]);
+	} else
+		pci_write_config_dword(dev, pos + PCI_MSI_DATA_32, cap[i++]);
+	if (control & PCI_MSI_FLAGS_MASKBIT)
+		pci_write_config_dword(dev, pos + PCI_MSI_MASK_BIT, cap[i++]);
+	pci_write_config_word(dev, pos + PCI_MSI_FLAGS, control);
+	enable_msi_mode(dev, pos, PCI_CAP_ID_MSI);
+	pci_remove_saved_cap(save_state);
+	kfree(save_state);
 }
 
+int pci_save_msix_state(struct pci_dev *dev)
+{
+	int pos;
+	int temp;
+	int irq, head, tail = 0;
+	u16 control;
+	struct pci_cap_saved_state *save_state;
+
+	pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
+	if (pos <= 0 || dev->no_msi)
+		return 0;
+
+	/* save the capability */
+	pci_read_config_word(dev, msi_control_reg(pos), &control);
+	if (!(control & PCI_MSIX_FLAGS_ENABLE))
+		return 0;
+	save_state = kzalloc(sizeof(struct pci_cap_saved_state) + sizeof(u16),
+		GFP_KERNEL);
+	if (!save_state) {
+		printk(KERN_ERR "Out of memory in pci_save_msix_state\n");
+		return -ENOMEM;
+	}
+	*((u16 *)&save_state->data[0]) = control;
+
+	/* save the table */
+	temp = dev->irq;
+	if (msi_lookup_irq(dev, PCI_CAP_ID_MSIX)) {
+		kfree(save_state);
+		return -EINVAL;
+	}
+
+	irq = head = dev->irq;
+	while (head != tail) {
+		struct msi_desc *entry;
+
+		entry = msi_desc[irq];
+		read_msi_msg(irq, &entry->msg_save);
+
+		tail = msi_desc[irq]->link.tail;
+		irq = tail;
+	}
+	dev->irq = temp;
+
+	save_state->cap_nr = PCI_CAP_ID_MSIX;
+	pci_add_saved_cap(dev, save_state);
+	return 0;
+}
+
+void pci_restore_msix_state(struct pci_dev *dev)
+{
+	u16 save;
+	int pos;
+	int irq, head, tail = 0;
+	struct msi_desc *entry;
+	int temp;
+	struct pci_cap_saved_state *save_state;
+
+	save_state = pci_find_saved_cap(dev, PCI_CAP_ID_MSIX);
+	if (!save_state)
+		return;
+	save = *((u16 *)&save_state->data[0]);
+	pci_remove_saved_cap(save_state);
+	kfree(save_state);
+
+	pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
+	if (pos <= 0)
+		return;
+
+	/* route the table */
+	temp = dev->irq;
+	if (msi_lookup_irq(dev, PCI_CAP_ID_MSIX))
+		return;
+	irq = head = dev->irq;
+	while (head != tail) {
+		entry = msi_desc[irq];
+		write_msi_msg(irq, &entry->msg_save);
+
+		tail = msi_desc[irq]->link.tail;
+		irq = tail;
+	}
+	dev->irq = temp;
+
+	pci_write_config_word(dev, msi_control_reg(pos), save);
+	enable_msi_mode(dev, pos, PCI_CAP_ID_MSIX);
+}
+#endif
+
 /**
  * msi_capability_init - configure device's MSI capability structure
  * @dev: pointer to the pci_dev data structure of MSI device function
  *
  * Setup the MSI capability structure of device function with a single
- * MSI vector, regardless of device function is capable of handling
+ * MSI irq, regardless of device function is capable of handling
  * multiple messages. A return of zero indicates the successful setup
- * of an entry zero with the new MSI vector or non-zero for otherwise.
+ * of an entry zero with the new MSI irq or non-zero for otherwise.
  **/
 static int msi_capability_init(struct pci_dev *dev)
 {
+	int status;
 	struct msi_desc *entry;
-	struct msg_address address;
-	struct msg_data data;
-	int pos, vector;
+	int pos, irq;
 	u16 control;
 
    	pos = pci_find_capability(dev, PCI_CAP_ID_MSI);
 	pci_read_config_word(dev, msi_control_reg(pos), &control);
 	/* MSI Entry Initialization */
-	if (!(entry = alloc_msi_entry()))
-		return -ENOMEM;
+	irq = create_msi_irq();
+	if (irq < 0)
+		return irq;
 
-	if ((vector = get_msi_vector(dev)) < 0) {
-		kmem_cache_free(msi_cachep, entry);
-		return -EBUSY;
-	}
-	entry->link.head = vector;
-	entry->link.tail = vector;
+	entry = get_irq_data(irq);
+	entry->link.head = irq;
+	entry->link.tail = irq;
 	entry->msi_attrib.type = PCI_CAP_ID_MSI;
-	entry->msi_attrib.state = 0;			/* Mark it not active */
+	entry->msi_attrib.is_64 = is_64bit_address(control);
 	entry->msi_attrib.entry_nr = 0;
 	entry->msi_attrib.maskbit = is_mask_bit_support(control);
-	entry->msi_attrib.default_vector = dev->irq;	/* Save IOAPIC IRQ */
-	dev->irq = vector;
-	entry->dev = dev;
+	entry->msi_attrib.default_irq = dev->irq;	/* Save IOAPIC IRQ */
+	entry->msi_attrib.pos = pos;
 	if (is_mask_bit_support(control)) {
 		entry->mask_base = (void __iomem *)(long)msi_mask_bits_reg(pos,
 				is_64bit_address(control));
 	}
-	/* Replace with MSI handler */
-	irq_handler_init(PCI_CAP_ID_MSI, vector, entry->msi_attrib.maskbit);
-	/* Configure MSI capability structure */
-	msi_address_init(&address);
-	msi_data_init(&data, vector);
-	entry->msi_attrib.current_cpu = ((address.lo_address.u.dest_id >>
-				MSI_TARGET_CPU_SHIFT) & MSI_TARGET_CPU_MASK);
-	pci_write_config_dword(dev, msi_lower_address_reg(pos),
-			address.lo_address.value);
-	if (is_64bit_address(control)) {
-		pci_write_config_dword(dev,
-			msi_upper_address_reg(pos), address.hi_address);
-		pci_write_config_word(dev,
-			msi_data_reg(pos, 1), *((u32*)&data));
-	} else
-		pci_write_config_word(dev,
-			msi_data_reg(pos, 0), *((u32*)&data));
+	entry->dev = dev;
 	if (entry->msi_attrib.maskbit) {
 		unsigned int maskbits, temp;
 		/* All MSIs are unmasked by default, Mask them all */
@@ -573,10 +544,18 @@ static int msi_capability_init(struct pci_dev *dev)
 			msi_mask_bits_reg(pos, is_64bit_address(control)),
 			maskbits);
 	}
-	attach_msi_entry(entry, vector);
+	/* Configure MSI capability structure */
+	status = arch_setup_msi_irq(irq, dev);
+	if (status < 0) {
+		destroy_msi_irq(irq);
+		return status;
+	}
+
+	attach_msi_entry(entry, irq);
 	/* Set MSI enabled bits	 */
 	enable_msi_mode(dev, pos, PCI_CAP_ID_MSI);
 
+	dev->irq = irq;
 	return 0;
 }
 
@@ -587,17 +566,17 @@ static int msi_capability_init(struct pci_dev *dev)
  * @nvec: number of @entries
  *
  * Setup the MSI-X capability structure of device function with a
- * single MSI-X vector. A return of zero indicates the successful setup of
- * requested MSI-X entries with allocated vectors or non-zero for otherwise.
+ * single MSI-X irq. A return of zero indicates the successful setup of
+ * requested MSI-X entries with allocated irqs or non-zero for otherwise.
  **/
 static int msix_capability_init(struct pci_dev *dev,
 				struct msix_entry *entries, int nvec)
 {
 	struct msi_desc *head = NULL, *tail = NULL, *entry = NULL;
-	struct msg_address address;
-	struct msg_data data;
-	int vector, pos, i, j, nr_entries, temp = 0;
-	u32 phys_addr, table_offset;
+	int status;
+	int irq, pos, i, j, nr_entries, temp = 0;
+	unsigned long phys_addr;
+	u32 table_offset;
  	u16 control;
 	u8 bir;
 	void __iomem *base;
@@ -606,71 +585,67 @@ static int msix_capability_init(struct pci_dev *dev,
 	/* Request & Map MSI-X table region */
  	pci_read_config_word(dev, msi_control_reg(pos), &control);
 	nr_entries = multi_msix_capable(control);
- 	pci_read_config_dword(dev, msix_table_offset_reg(pos),
- 		&table_offset);
+
+ 	pci_read_config_dword(dev, msix_table_offset_reg(pos), &table_offset);
 	bir = (u8)(table_offset & PCI_MSIX_FLAGS_BIRMASK);
-	phys_addr = pci_resource_start (dev, bir);
-	phys_addr += (u32)(table_offset & ~PCI_MSIX_FLAGS_BIRMASK);
+	table_offset &= ~PCI_MSIX_FLAGS_BIRMASK;
+	phys_addr = pci_resource_start (dev, bir) + table_offset;
 	base = ioremap_nocache(phys_addr, nr_entries * PCI_MSIX_ENTRY_SIZE);
 	if (base == NULL)
 		return -ENOMEM;
 
 	/* MSI-X Table Initialization */
 	for (i = 0; i < nvec; i++) {
-		entry = alloc_msi_entry();
-		if (!entry)
-			break;
-		if ((vector = get_msi_vector(dev)) < 0)
+		irq = create_msi_irq();
+		if (irq < 0)
 			break;
 
+		entry = get_irq_data(irq);
  		j = entries[i].entry;
- 		entries[i].vector = vector;
+ 		entries[i].vector = irq;
 		entry->msi_attrib.type = PCI_CAP_ID_MSIX;
- 		entry->msi_attrib.state = 0;		/* Mark it not active */
+		entry->msi_attrib.is_64 = 1;
 		entry->msi_attrib.entry_nr = j;
 		entry->msi_attrib.maskbit = 1;
-		entry->msi_attrib.default_vector = dev->irq;
+		entry->msi_attrib.default_irq = dev->irq;
+		entry->msi_attrib.pos = pos;
 		entry->dev = dev;
 		entry->mask_base = base;
 		if (!head) {
-			entry->link.head = vector;
-			entry->link.tail = vector;
+			entry->link.head = irq;
+			entry->link.tail = irq;
 			head = entry;
 		} else {
 			entry->link.head = temp;
 			entry->link.tail = tail->link.tail;
-			tail->link.tail = vector;
-			head->link.head = vector;
+			tail->link.tail = irq;
+			head->link.head = irq;
 		}
-		temp = vector;
+		temp = irq;
 		tail = entry;
-		/* Replace with MSI-X handler */
-		irq_handler_init(PCI_CAP_ID_MSIX, vector, 1);
 		/* Configure MSI-X capability structure */
-		msi_address_init(&address);
-		msi_data_init(&data, vector);
-		entry->msi_attrib.current_cpu =
-			((address.lo_address.u.dest_id >>
-			MSI_TARGET_CPU_SHIFT) & MSI_TARGET_CPU_MASK);
-		writel(address.lo_address.value,
-			base + j * PCI_MSIX_ENTRY_SIZE +
-			PCI_MSIX_ENTRY_LOWER_ADDR_OFFSET);
-		writel(address.hi_address,
-			base + j * PCI_MSIX_ENTRY_SIZE +
-			PCI_MSIX_ENTRY_UPPER_ADDR_OFFSET);
-		writel(*(u32*)&data,
-			base + j * PCI_MSIX_ENTRY_SIZE +
-			PCI_MSIX_ENTRY_DATA_OFFSET);
-		attach_msi_entry(entry, vector);
+		status = arch_setup_msi_irq(irq, dev);
+		if (status < 0) {
+			destroy_msi_irq(irq);
+			break;
+		}
+
+		attach_msi_entry(entry, irq);
 	}
 	if (i != nvec) {
+		int avail = i - 1;
 		i--;
 		for (; i >= 0; i--) {
-			vector = (entries + i)->vector;
-			msi_free_vector(dev, vector, 0);
+			irq = (entries + i)->vector;
+			msi_free_irq(dev, irq);
 			(entries + i)->vector = 0;
 		}
-		return -EBUSY;
+		/* If we had some success report the number of irqs
+		 * we succeeded in setting up.
+		 */
+		if (avail <= 0)
+			avail = -EBUSY;
+		return avail;
 	}
 	/* Set MSI-X enabled bits */
 	enable_msi_mode(dev, pos, PCI_CAP_ID_MSIX);
@@ -678,123 +653,132 @@ static int msix_capability_init(struct pci_dev *dev,
 	return 0;
 }
 
+/**
+ * pci_msi_supported - check whether MSI may be enabled on device
+ * @dev: pointer to the pci_dev data structure of MSI device function
+ *
+ * Look at global flags, the device itself, and its parent busses
+ * to return 0 if MSI are supported for the device.
+ **/
+static
+int pci_msi_supported(struct pci_dev * dev)
+{
+	struct pci_bus *bus;
+
+	/* MSI must be globally enabled and supported by the device */
+	if (!pci_msi_enable || !dev || dev->no_msi)
+		return -EINVAL;
+
+	/* Any bridge which does NOT route MSI transactions from it's
+	 * secondary bus to it's primary bus must set NO_MSI flag on
+	 * the secondary pci_bus.
+	 * We expect only arch-specific PCI host bus controller driver
+	 * or quirks for specific PCI bridges to be setting NO_MSI.
+	 */
+	for (bus = dev->bus; bus; bus = bus->parent)
+		if (bus->bus_flags & PCI_BUS_FLAGS_NO_MSI)
+			return -EINVAL;
+
+	return 0;
+}
+
 /**
  * pci_enable_msi - configure device's MSI capability structure
  * @dev: pointer to the pci_dev data structure of MSI device function
  *
  * Setup the MSI capability structure of device function with
- * a single MSI vector upon its software driver call to request for
+ * a single MSI irq upon its software driver call to request for
  * MSI mode enabled on its hardware device function. A return of zero
  * indicates the successful setup of an entry zero with the new MSI
- * vector or non-zero for otherwise.
+ * irq or non-zero for otherwise.
  **/
 int pci_enable_msi(struct pci_dev* dev)
 {
-	int pos, temp, status = -EINVAL;
-	u16 control;
+	int pos, temp, status;
 
-	if (!pci_msi_enable || !dev)
- 		return status;
-
-	if (dev->no_msi)
-		return status;
+	if (pci_msi_supported(dev) < 0)
+		return -EINVAL;
 
 	temp = dev->irq;
 
-	if ((status = msi_init()) < 0)
+	status = msi_init();
+	if (status < 0)
 		return status;
 
-   	if (!(pos = pci_find_capability(dev, PCI_CAP_ID_MSI)))
+	pos = pci_find_capability(dev, PCI_CAP_ID_MSI);
+	if (!pos)
 		return -EINVAL;
 
-	pci_read_config_word(dev, msi_control_reg(pos), &control);
-	if (control & PCI_MSI_FLAGS_ENABLE)
-		return 0;			/* Already in MSI mode */
-
-	if (!msi_lookup_vector(dev, PCI_CAP_ID_MSI)) {
-		/* Lookup Sucess */
-		unsigned long flags;
+	WARN_ON(!msi_lookup_irq(dev, PCI_CAP_ID_MSI));
 
-		spin_lock_irqsave(&msi_lock, flags);
-		if (!vector_irq[dev->irq]) {
-			msi_desc[dev->irq]->msi_attrib.state = 0;
-			vector_irq[dev->irq] = -1;
-			nr_released_vectors--;
-			spin_unlock_irqrestore(&msi_lock, flags);
-			enable_msi_mode(dev, pos, PCI_CAP_ID_MSI);
-			return 0;
-		}
-		spin_unlock_irqrestore(&msi_lock, flags);
-		dev->irq = temp;
-	}
-	/* Check whether driver already requested for MSI-X vectors */
-   	if ((pos = pci_find_capability(dev, PCI_CAP_ID_MSIX)) > 0 &&
-		!msi_lookup_vector(dev, PCI_CAP_ID_MSIX)) {
+	/* Check whether driver already requested for MSI-X irqs */
+	pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
+	if (pos > 0 && !msi_lookup_irq(dev, PCI_CAP_ID_MSIX)) {
 			printk(KERN_INFO "PCI: %s: Can't enable MSI.  "
-			       "Device already has MSI-X vectors assigned\n",
+			       "Device already has MSI-X irq assigned\n",
 			       pci_name(dev));
 			dev->irq = temp;
 			return -EINVAL;
 	}
 	status = msi_capability_init(dev);
-	if (!status) {
-   		if (!pos)
-			nr_reserved_vectors--;	/* Only MSI capable */
-		else if (nr_msix_devices > 0)
-			nr_msix_devices--;	/* Both MSI and MSI-X capable,
-						   but choose enabling MSI */
-	}
-
 	return status;
 }
 
 void pci_disable_msi(struct pci_dev* dev)
 {
 	struct msi_desc *entry;
-	int pos, default_vector;
+	int pos, default_irq;
 	u16 control;
 	unsigned long flags;
 
-   	if (!dev || !(pos = pci_find_capability(dev, PCI_CAP_ID_MSI)))
+	if (!pci_msi_enable)
+		return;
+	if (!dev)
+		return;
+
+	pos = pci_find_capability(dev, PCI_CAP_ID_MSI);
+	if (!pos)
 		return;
 
 	pci_read_config_word(dev, msi_control_reg(pos), &control);
 	if (!(control & PCI_MSI_FLAGS_ENABLE))
 		return;
 
+	disable_msi_mode(dev, pos, PCI_CAP_ID_MSI);
+
 	spin_lock_irqsave(&msi_lock, flags);
 	entry = msi_desc[dev->irq];
 	if (!entry || !entry->dev || entry->msi_attrib.type != PCI_CAP_ID_MSI) {
 		spin_unlock_irqrestore(&msi_lock, flags);
 		return;
 	}
-	if (entry->msi_attrib.state) {
+	if (irq_has_action(dev->irq)) {
 		spin_unlock_irqrestore(&msi_lock, flags);
 		printk(KERN_WARNING "PCI: %s: pci_disable_msi() called without "
-		       "free_irq() on MSI vector %d\n",
+		       "free_irq() on MSI irq %d\n",
 		       pci_name(dev), dev->irq);
-		BUG_ON(entry->msi_attrib.state > 0);
+		BUG_ON(irq_has_action(dev->irq));
 	} else {
-		vector_irq[dev->irq] = 0; /* free it */
-		nr_released_vectors++;
-		default_vector = entry->msi_attrib.default_vector;
+		default_irq = entry->msi_attrib.default_irq;
 		spin_unlock_irqrestore(&msi_lock, flags);
-		/* Restore dev->irq to its default pin-assertion vector */
-		dev->irq = default_vector;
-		disable_msi_mode(dev, pci_find_capability(dev, PCI_CAP_ID_MSI),
-					PCI_CAP_ID_MSI);
+		msi_free_irq(dev, dev->irq);
+
+		/* Restore dev->irq to its default pin-assertion irq */
+		dev->irq = default_irq;
 	}
 }
 
-static int msi_free_vector(struct pci_dev* dev, int vector, int reassign)
+static int msi_free_irq(struct pci_dev* dev, int irq)
 {
 	struct msi_desc *entry;
 	int head, entry_nr, type;
 	void __iomem *base;
 	unsigned long flags;
 
+	arch_teardown_msi_irq(irq);
+
 	spin_lock_irqsave(&msi_lock, flags);
-	entry = msi_desc[vector];
+	entry = msi_desc[irq];
 	if (!entry || entry->dev != dev) {
 		spin_unlock_irqrestore(&msi_lock, flags);
 		return -EINVAL;
@@ -806,134 +790,55 @@ static int msi_free_vector(struct pci_dev* dev, int vector, int reassign)
 	msi_desc[entry->link.head]->link.tail = entry->link.tail;
 	msi_desc[entry->link.tail]->link.head = entry->link.head;
 	entry->dev = NULL;
-	if (!reassign) {
-		vector_irq[vector] = 0;
-		nr_released_vectors++;
-	}
-	msi_desc[vector] = NULL;
+	msi_desc[irq] = NULL;
 	spin_unlock_irqrestore(&msi_lock, flags);
 
-	kmem_cache_free(msi_cachep, entry);
+	destroy_msi_irq(irq);
 
 	if (type == PCI_CAP_ID_MSIX) {
-		if (!reassign)
-			writel(1, base +
-				entry_nr * PCI_MSIX_ENTRY_SIZE +
-				PCI_MSIX_ENTRY_VECTOR_CTRL_OFFSET);
-
-		if (head == vector) {
-			/*
-			 * Detect last MSI-X vector to be released.
-			 * Release the MSI-X memory-mapped table.
-			 */
-			int pos, nr_entries;
-			u32 phys_addr, table_offset;
-			u16 control;
-			u8 bir;
-
-   			pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
-			pci_read_config_word(dev, msi_control_reg(pos),
-				&control);
-			nr_entries = multi_msix_capable(control);
-			pci_read_config_dword(dev, msix_table_offset_reg(pos),
-				&table_offset);
-			bir = (u8)(table_offset & PCI_MSIX_FLAGS_BIRMASK);
-			phys_addr = pci_resource_start (dev, bir);
-			phys_addr += (u32)(table_offset &
-				~PCI_MSIX_FLAGS_BIRMASK);
+		writel(1, base + entry_nr * PCI_MSIX_ENTRY_SIZE +
+			PCI_MSIX_ENTRY_VECTOR_CTRL_OFFSET);
+
+		if (head == irq)
 			iounmap(base);
-		}
 	}
 
 	return 0;
 }
 
-static int reroute_msix_table(int head, struct msix_entry *entries, int *nvec)
-{
-	int vector = head, tail = 0;
-	int i, j = 0, nr_entries = 0;
-	void __iomem *base;
-	unsigned long flags;
-
-	spin_lock_irqsave(&msi_lock, flags);
-	while (head != tail) {
-		nr_entries++;
-		tail = msi_desc[vector]->link.tail;
-		if (entries[0].entry == msi_desc[vector]->msi_attrib.entry_nr)
-			j = vector;
-		vector = tail;
-	}
-	if (*nvec > nr_entries) {
-		spin_unlock_irqrestore(&msi_lock, flags);
-		*nvec = nr_entries;
-		return -EINVAL;
-	}
-	vector = ((j > 0) ? j : head);
-	for (i = 0; i < *nvec; i++) {
-		j = msi_desc[vector]->msi_attrib.entry_nr;
-		msi_desc[vector]->msi_attrib.state = 0;	/* Mark it not active */
-		vector_irq[vector] = -1;		/* Mark it busy */
-		nr_released_vectors--;
-		entries[i].vector = vector;
-		if (j != (entries + i)->entry) {
-			base = msi_desc[vector]->mask_base;
-			msi_desc[vector]->msi_attrib.entry_nr =
-				(entries + i)->entry;
-			writel( readl(base + j * PCI_MSIX_ENTRY_SIZE +
-				PCI_MSIX_ENTRY_LOWER_ADDR_OFFSET), base +
-				(entries + i)->entry * PCI_MSIX_ENTRY_SIZE +
-				PCI_MSIX_ENTRY_LOWER_ADDR_OFFSET);
-			writel(	readl(base + j * PCI_MSIX_ENTRY_SIZE +
-				PCI_MSIX_ENTRY_UPPER_ADDR_OFFSET), base +
-				(entries + i)->entry * PCI_MSIX_ENTRY_SIZE +
-				PCI_MSIX_ENTRY_UPPER_ADDR_OFFSET);
-			writel( (readl(base + j * PCI_MSIX_ENTRY_SIZE +
-				PCI_MSIX_ENTRY_DATA_OFFSET) & 0xff00) | vector,
-				base + (entries+i)->entry*PCI_MSIX_ENTRY_SIZE +
-				PCI_MSIX_ENTRY_DATA_OFFSET);
-		}
-		vector = msi_desc[vector]->link.tail;
-	}
-	spin_unlock_irqrestore(&msi_lock, flags);
-
-	return 0;
-}
-
 /**
  * pci_enable_msix - configure device's MSI-X capability structure
  * @dev: pointer to the pci_dev data structure of MSI-X device function
  * @entries: pointer to an array of MSI-X entries
- * @nvec: number of MSI-X vectors requested for allocation by device driver
+ * @nvec: number of MSI-X irqs requested for allocation by device driver
  *
  * Setup the MSI-X capability structure of device function with the number
- * of requested vectors upon its software driver call to request for
+ * of requested irqs upon its software driver call to request for
  * MSI-X mode enabled on its hardware device function. A return of zero
  * indicates the successful configuration of MSI-X capability structure
- * with new allocated MSI-X vectors. A return of < 0 indicates a failure.
+ * with new allocated MSI-X irqs. A return of < 0 indicates a failure.
  * Or a return of > 0 indicates that driver request is exceeding the number
- * of vectors available. Driver should use the returned value to re-send
+ * of irqs available. Driver should use the returned value to re-send
  * its request.
  **/
 int pci_enable_msix(struct pci_dev* dev, struct msix_entry *entries, int nvec)
 {
-	int status, pos, nr_entries, free_vectors;
+	int status, pos, nr_entries;
 	int i, j, temp;
 	u16 control;
-	unsigned long flags;
 
-	if (!pci_msi_enable || !dev || !entries)
+	if (!entries || pci_msi_supported(dev) < 0)
  		return -EINVAL;
 
-	if ((status = msi_init()) < 0)
+	status = msi_init();
+	if (status < 0)
 		return status;
 
-   	if (!(pos = pci_find_capability(dev, PCI_CAP_ID_MSIX)))
+	pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
+	if (!pos)
  		return -EINVAL;
 
 	pci_read_config_word(dev, msi_control_reg(pos), &control);
-	if (control & PCI_MSIX_FLAGS_ENABLE)
-		return -EINVAL;			/* Already in MSI-X mode */
-
 	nr_entries = multi_msix_capable(control);
 	if (nvec > nr_entries)
 		return -EINVAL;
@@ -948,56 +853,18 @@ int pci_enable_msix(struct pci_dev* dev, struct msix_entry *entries, int nvec)
 		}
 	}
 	temp = dev->irq;
-	if (!msi_lookup_vector(dev, PCI_CAP_ID_MSIX)) {
-		/* Lookup Sucess */
-		nr_entries = nvec;
-		/* Reroute MSI-X table */
-		if (reroute_msix_table(dev->irq, entries, &nr_entries)) {
-			/* #requested > #previous-assigned */
-			dev->irq = temp;
-			return nr_entries;
-		}
-		dev->irq = temp;
-		enable_msi_mode(dev, pos, PCI_CAP_ID_MSIX);
-		return 0;
-	}
-	/* Check whether driver already requested for MSI vector */
+	WARN_ON(!msi_lookup_irq(dev, PCI_CAP_ID_MSIX));
+
+	/* Check whether driver already requested for MSI irq */
    	if (pci_find_capability(dev, PCI_CAP_ID_MSI) > 0 &&
-		!msi_lookup_vector(dev, PCI_CAP_ID_MSI)) {
+		!msi_lookup_irq(dev, PCI_CAP_ID_MSI)) {
 		printk(KERN_INFO "PCI: %s: Can't enable MSI-X.  "
-		       "Device already has an MSI vector assigned\n",
+		       "Device already has an MSI irq assigned\n",
 		       pci_name(dev));
 		dev->irq = temp;
 		return -EINVAL;
 	}
-
-	spin_lock_irqsave(&msi_lock, flags);
-	/*
-	 * msi_lock is provided to ensure that enough vectors resources are
-	 * available before granting.
-	 */
-	free_vectors = pci_vector_resources(last_alloc_vector,
-				nr_released_vectors);
-	/* Ensure that each MSI/MSI-X device has one vector reserved by
-	   default to avoid any MSI-X driver to take all available
- 	   resources */
-	free_vectors -= nr_reserved_vectors;
-	/* Find the average of free vectors among MSI-X devices */
-	if (nr_msix_devices > 0)
-		free_vectors /= nr_msix_devices;
-	spin_unlock_irqrestore(&msi_lock, flags);
-
-	if (nvec > free_vectors) {
-		if (free_vectors > 0)
-			return free_vectors;
-		else
-			return -EBUSY;
-	}
-
 	status = msix_capability_init(dev, entries, nvec);
-	if (!status && nr_msix_devices > 0)
-		nr_msix_devices--;
-
 	return status;
 }
 
@@ -1006,116 +873,99 @@ void pci_disable_msix(struct pci_dev* dev)
 	int pos, temp;
 	u16 control;
 
-   	if (!dev || !(pos = pci_find_capability(dev, PCI_CAP_ID_MSIX)))
+	if (!pci_msi_enable)
+		return;
+	if (!dev)
+		return;
+
+	pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
+	if (!pos)
 		return;
 
 	pci_read_config_word(dev, msi_control_reg(pos), &control);
 	if (!(control & PCI_MSIX_FLAGS_ENABLE))
 		return;
 
+	disable_msi_mode(dev, pos, PCI_CAP_ID_MSIX);
+
 	temp = dev->irq;
-	if (!msi_lookup_vector(dev, PCI_CAP_ID_MSIX)) {
-		int state, vector, head, tail = 0, warning = 0;
+	if (!msi_lookup_irq(dev, PCI_CAP_ID_MSIX)) {
+		int irq, head, tail = 0, warning = 0;
 		unsigned long flags;
 
-		vector = head = dev->irq;
-		spin_lock_irqsave(&msi_lock, flags);
+		irq = head = dev->irq;
+		dev->irq = temp;			/* Restore pin IRQ */
 		while (head != tail) {
-			state = msi_desc[vector]->msi_attrib.state;
-			if (state)
+			spin_lock_irqsave(&msi_lock, flags);
+			tail = msi_desc[irq]->link.tail;
+			spin_unlock_irqrestore(&msi_lock, flags);
+			if (irq_has_action(irq))
 				warning = 1;
-			else {
-				vector_irq[vector] = 0; /* free it */
-				nr_released_vectors++;
-			}
-			tail = msi_desc[vector]->link.tail;
-			vector = tail;
+			else if (irq != head)	/* Release MSI-X irq */
+				msi_free_irq(dev, irq);
+			irq = tail;
 		}
-		spin_unlock_irqrestore(&msi_lock, flags);
+		msi_free_irq(dev, irq);
 		if (warning) {
-			dev->irq = temp;
 			printk(KERN_WARNING "PCI: %s: pci_disable_msix() called without "
-			       "free_irq() on all MSI-X vectors\n",
+			       "free_irq() on all MSI-X irqs\n",
 			       pci_name(dev));
 			BUG_ON(warning > 0);
-		} else {
-			dev->irq = temp;
-			disable_msi_mode(dev,
-				pci_find_capability(dev, PCI_CAP_ID_MSIX),
-				PCI_CAP_ID_MSIX);
-
 		}
 	}
 }
 
 /**
- * msi_remove_pci_irq_vectors - reclaim MSI(X) vectors to unused state
+ * msi_remove_pci_irq_vectors - reclaim MSI(X) irqs to unused state
  * @dev: pointer to the pci_dev data structure of MSI(X) device function
  *
  * Being called during hotplug remove, from which the device function
- * is hot-removed. All previous assigned MSI/MSI-X vectors, if
+ * is hot-removed. All previous assigned MSI/MSI-X irqs, if
  * allocated for this device function, are reclaimed to unused state,
  * which may be used later on.
  **/
 void msi_remove_pci_irq_vectors(struct pci_dev* dev)
 {
-	int state, pos, temp;
+	int pos, temp;
 	unsigned long flags;
 
 	if (!pci_msi_enable || !dev)
  		return;
 
 	temp = dev->irq;		/* Save IOAPIC IRQ */
-   	if ((pos = pci_find_capability(dev, PCI_CAP_ID_MSI)) > 0 &&
-		!msi_lookup_vector(dev, PCI_CAP_ID_MSI)) {
-		spin_lock_irqsave(&msi_lock, flags);
-		state = msi_desc[dev->irq]->msi_attrib.state;
-		spin_unlock_irqrestore(&msi_lock, flags);
-		if (state) {
+	pos = pci_find_capability(dev, PCI_CAP_ID_MSI);
+	if (pos > 0 && !msi_lookup_irq(dev, PCI_CAP_ID_MSI)) {
+		if (irq_has_action(dev->irq)) {
 			printk(KERN_WARNING "PCI: %s: msi_remove_pci_irq_vectors() "
-			       "called without free_irq() on MSI vector %d\n",
+			       "called without free_irq() on MSI irq %d\n",
 			       pci_name(dev), dev->irq);
-			BUG_ON(state > 0);
-		} else /* Release MSI vector assigned to this device */
-			msi_free_vector(dev, dev->irq, 0);
+			BUG_ON(irq_has_action(dev->irq));
+		} else /* Release MSI irq assigned to this device */
+			msi_free_irq(dev, dev->irq);
 		dev->irq = temp;		/* Restore IOAPIC IRQ */
 	}
-   	if ((pos = pci_find_capability(dev, PCI_CAP_ID_MSIX)) > 0 &&
-		!msi_lookup_vector(dev, PCI_CAP_ID_MSIX)) {
-		int vector, head, tail = 0, warning = 0;
+	pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
+	if (pos > 0 && !msi_lookup_irq(dev, PCI_CAP_ID_MSIX)) {
+		int irq, head, tail = 0, warning = 0;
 		void __iomem *base = NULL;
 
-		vector = head = dev->irq;
+		irq = head = dev->irq;
 		while (head != tail) {
 			spin_lock_irqsave(&msi_lock, flags);
-			state = msi_desc[vector]->msi_attrib.state;
-			tail = msi_desc[vector]->link.tail;
-			base = msi_desc[vector]->mask_base;
+			tail = msi_desc[irq]->link.tail;
+			base = msi_desc[irq]->mask_base;
 			spin_unlock_irqrestore(&msi_lock, flags);
-			if (state)
+			if (irq_has_action(irq))
 				warning = 1;
-			else if (vector != head) /* Release MSI-X vector */
-				msi_free_vector(dev, vector, 0);
-			vector = tail;
+			else if (irq != head) /* Release MSI-X irq */
+				msi_free_irq(dev, irq);
+			irq = tail;
 		}
-		msi_free_vector(dev, vector, 0);
+		msi_free_irq(dev, irq);
 		if (warning) {
-			/* Force to release the MSI-X memory-mapped table */
-			u32 phys_addr, table_offset;
-			u16 control;
-			u8 bir;
-
-			pci_read_config_word(dev, msi_control_reg(pos),
-				&control);
-			pci_read_config_dword(dev, msix_table_offset_reg(pos),
-				&table_offset);
-			bir = (u8)(table_offset & PCI_MSIX_FLAGS_BIRMASK);
-			phys_addr = pci_resource_start (dev, bir);
-			phys_addr += (u32)(table_offset &
-				~PCI_MSIX_FLAGS_BIRMASK);
 			iounmap(base);
 			printk(KERN_WARNING "PCI: %s: msi_remove_pci_irq_vectors() "
-			       "called without free_irq() on all MSI-X vectors\n",
+			       "called without free_irq() on all MSI-X irqs\n",
 			       pci_name(dev));
 			BUG_ON(warning > 0);
 		}
@@ -1123,6 +973,15 @@ void msi_remove_pci_irq_vectors(struct pci_dev* dev)
 	}
 }
 
+void pci_no_msi(void)
+{
+	pci_msi_enable = 0;
+}
+void pci_yes_msi(void)
+{
+	pci_msi_enable = 1;
+}
+
 EXPORT_SYMBOL(pci_enable_msi);
 EXPORT_SYMBOL(pci_disable_msi);
 EXPORT_SYMBOL(pci_enable_msix);