X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=drivers%2Fpci%2Fmsi.c;h=77b68eaf021e43152c4bbd257bd190a4a210473c;hb=89713422a768458a0d375f0c2f3586cd5ccde6a1;hp=88362f1bd9cfceaf9575215c96865e314e3bed8a;hpb=7fe3730de729b758e9f69b862b9255d998671b5f;p=safe%2Fjmp%2Flinux-2.6

diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 88362f1..77b68ea 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -12,34 +12,81 @@
 #include <linux/interrupt.h>
 #include <linux/init.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>
-#include <asm/smp.h>
+#include <linux/smp.h>
+#include <linux/errno.h>
+#include <linux/io.h>
+#include <linux/slab.h>
 
 #include "pci.h"
 #include "msi.h"
 
 static int pci_msi_enable = 1;
 
-static void msi_set_enable(struct pci_dev *dev, int enable)
+/* Arch hooks */
+
+#ifndef arch_msi_check_device
+int arch_msi_check_device(struct pci_dev *dev, int nvec, int type)
 {
-	int pos;
-	u16 control;
+	return 0;
+}
+#endif
 
-	pos = pci_find_capability(dev, PCI_CAP_ID_MSI);
-	if (pos) {
-		pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &control);
-		control &= ~PCI_MSI_FLAGS_ENABLE;
-		if (enable)
-			control |= PCI_MSI_FLAGS_ENABLE;
-		pci_write_config_word(dev, pos + PCI_MSI_FLAGS, control);
+#ifndef arch_setup_msi_irqs
+int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+{
+	struct msi_desc *entry;
+	int ret;
+
+	/*
+	 * If an architecture wants to support multiple MSI, it needs to
+	 * override arch_setup_msi_irqs()
+	 */
+	if (type == PCI_CAP_ID_MSI && nvec > 1)
+		return 1;
+
+	list_for_each_entry(entry, &dev->msi_list, list) {
+		ret = arch_setup_msi_irq(dev, entry);
+		if (ret < 0)
+			return ret;
+		if (ret > 0)
+			return -ENOSPC;
+	}
+
+	return 0;
+}
+#endif
+
+#ifndef arch_teardown_msi_irqs
+void arch_teardown_msi_irqs(struct pci_dev *dev)
+{
+	struct msi_desc *entry;
+
+	list_for_each_entry(entry, &dev->msi_list, list) {
+		int i, nvec;
+		if (entry->irq == 0)
+			continue;
+		nvec = 1 << entry->msi_attrib.multiple;
+		for (i = 0; i < nvec; i++)
+			arch_teardown_msi_irq(entry->irq + i);
 	}
 }
+#endif
+
+static void msi_set_enable(struct pci_dev *dev, int pos, int enable)
+{
+	u16 control;
+
+	BUG_ON(!pos);
+
+	pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &control);
+	control &= ~PCI_MSI_FLAGS_ENABLE;
+	if (enable)
+		control |= PCI_MSI_FLAGS_ENABLE;
+	pci_write_config_word(dev, pos + PCI_MSI_FLAGS, control);
+}
 
 static void msix_set_enable(struct pci_dev *dev, int enable)
 {
@@ -56,71 +103,107 @@ static void msix_set_enable(struct pci_dev *dev, int enable)
 	}
 }
 
-static void msix_flush_writes(unsigned int irq)
+static inline __attribute_const__ u32 msi_mask(unsigned x)
 {
-	struct msi_desc *entry;
+	/* Don't shift by >= width of type */
+	if (x >= 5)
+		return 0xffffffff;
+	return (1 << (1 << x)) - 1;
+}
 
-	entry = get_irq_msi(irq);
-	BUG_ON(!entry || !entry->dev);
-	switch (entry->msi_attrib.type) {
-	case PCI_CAP_ID_MSI:
-		/* 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;
-		readl(entry->mask_base + offset);
-		break;
-	}
-	default:
-		BUG();
-		break;
-	}
+static inline __attribute_const__ u32 msi_capable_mask(u16 control)
+{
+	return msi_mask((control >> 1) & 7);
 }
 
-static void msi_set_mask_bit(unsigned int irq, int flag)
+static inline __attribute_const__ u32 msi_enabled_mask(u16 control)
 {
-	struct msi_desc *entry;
+	return msi_mask((control >> 4) & 7);
+}
 
-	entry = get_irq_msi(irq);
-	BUG_ON(!entry || !entry->dev);
-	switch (entry->msi_attrib.type) {
-	case PCI_CAP_ID_MSI:
-		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);
-		} else {
-			msi_set_enable(entry->dev, !flag);
-		}
-		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;
+/*
+ * PCI 2.3 does not specify mask bits for each MSI interrupt.  Attempting to
+ * mask all MSI interrupts by clearing the MSI enable bit does not work
+ * reliably as devices without an INTx disable bit will then generate a
+ * level IRQ which will never be cleared.
+ */
+static u32 __msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
+{
+	u32 mask_bits = desc->masked;
+
+	if (!desc->msi_attrib.maskbit)
+		return 0;
+
+	mask_bits &= ~mask;
+	mask_bits |= flag;
+	pci_write_config_dword(desc->dev, desc->mask_pos, mask_bits);
+
+	return mask_bits;
+}
+
+static void msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
+{
+	desc->masked = __msi_mask_irq(desc, mask, flag);
+}
+
+/*
+ * This internal function does not flush PCI writes to the device.
+ * All users must ensure that they read from the device before either
+ * assuming that the device state is up to date, or returning out of this
+ * file.  This saves a few milliseconds when initialising devices with lots
+ * of MSI-X interrupts.
+ */
+static u32 __msix_mask_irq(struct msi_desc *desc, u32 flag)
+{
+	u32 mask_bits = desc->masked;
+	unsigned offset = desc->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE +
+						PCI_MSIX_ENTRY_VECTOR_CTRL;
+	mask_bits &= ~1;
+	mask_bits |= flag;
+	writel(mask_bits, desc->mask_base + offset);
+
+	return mask_bits;
+}
+
+static void msix_mask_irq(struct msi_desc *desc, u32 flag)
+{
+	desc->masked = __msix_mask_irq(desc, flag);
+}
+
+static void msi_set_mask_bit(unsigned irq, u32 flag)
+{
+	struct msi_desc *desc = get_irq_msi(irq);
+
+	if (desc->msi_attrib.is_msix) {
+		msix_mask_irq(desc, flag);
+		readl(desc->mask_base);		/* Flush write to device */
+	} else {
+		unsigned offset = irq - desc->dev->irq;
+		msi_mask_irq(desc, 1 << offset, flag << offset);
 	}
-	entry->msi_attrib.masked = !!flag;
 }
 
-void read_msi_msg(unsigned int irq, struct msi_msg *msg)
+void mask_msi_irq(unsigned int irq)
 {
-	struct msi_desc *entry = get_irq_msi(irq);
-	switch(entry->msi_attrib.type) {
-	case PCI_CAP_ID_MSI:
-	{
+	msi_set_mask_bit(irq, 1);
+}
+
+void unmask_msi_irq(unsigned int irq)
+{
+	msi_set_mask_bit(irq, 0);
+}
+
+void read_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg)
+{
+	struct msi_desc *entry = get_irq_desc_msi(desc);
+	if (entry->msi_attrib.is_msix) {
+		void __iomem *base = entry->mask_base +
+			entry->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE;
+
+		msg->address_lo = readl(base + PCI_MSIX_ENTRY_LOWER_ADDR);
+		msg->address_hi = readl(base + PCI_MSIX_ENTRY_UPPER_ADDR);
+		msg->data = readl(base + PCI_MSIX_ENTRY_DATA);
+	} else {
 		struct pci_dev *dev = entry->dev;
 		int pos = entry->msi_attrib.pos;
 		u16 data;
@@ -133,35 +216,39 @@ void read_msi_msg(unsigned int irq, struct msi_msg *msg)
 			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);
+			pci_read_config_word(dev, msi_data_reg(pos, 0), &data);
 		}
 		msg->data = data;
-		break;
 	}
-	case PCI_CAP_ID_MSIX:
-	{
-		void __iomem *base;
-		base = entry->mask_base +
-			entry->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE;
+}
 
-		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();
-	}
+void read_msi_msg(unsigned int irq, struct msi_msg *msg)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+
+	read_msi_msg_desc(desc, msg);
 }
 
-void write_msi_msg(unsigned int irq, struct msi_msg *msg)
+void write_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg)
 {
-	struct msi_desc *entry = get_irq_msi(irq);
-	switch (entry->msi_attrib.type) {
-	case PCI_CAP_ID_MSI:
-	{
+	struct msi_desc *entry = get_irq_desc_msi(desc);
+	if (entry->msi_attrib.is_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);
+		writel(msg->address_hi, base + PCI_MSIX_ENTRY_UPPER_ADDR);
+		writel(msg->data, base + PCI_MSIX_ENTRY_DATA);
+	} else {
 		struct pci_dev *dev = entry->dev;
 		int pos = entry->msi_attrib.pos;
+		u16 msgctl;
+
+		pci_read_config_word(dev, msi_control_reg(pos), &msgctl);
+		msgctl &= ~PCI_MSI_FLAGS_QSIZE;
+		msgctl |= entry->msi_attrib.multiple << 4;
+		pci_write_config_word(dev, msi_control_reg(pos), msgctl);
 
 		pci_write_config_dword(dev, msi_lower_address_reg(pos),
 					msg->address_lo);
@@ -174,58 +261,60 @@ void write_msi_msg(unsigned int irq, struct msi_msg *msg)
 			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();
 	}
 	entry->msg = *msg;
 }
 
-void mask_msi_irq(unsigned int irq)
+void write_msi_msg(unsigned int irq, struct msi_msg *msg)
 {
-	msi_set_mask_bit(irq, 1);
-	msix_flush_writes(irq);
+	struct irq_desc *desc = irq_to_desc(irq);
+
+	write_msi_msg_desc(desc, msg);
 }
 
-void unmask_msi_irq(unsigned int irq)
+static void free_msi_irqs(struct pci_dev *dev)
 {
-	msi_set_mask_bit(irq, 0);
-	msix_flush_writes(irq);
-}
+	struct msi_desc *entry, *tmp;
 
-static int msi_free_irq(struct pci_dev* dev, int irq);
+	list_for_each_entry(entry, &dev->msi_list, list) {
+		int i, nvec;
+		if (!entry->irq)
+			continue;
+		nvec = 1 << entry->msi_attrib.multiple;
+		for (i = 0; i < nvec; i++)
+			BUG_ON(irq_has_action(entry->irq + i));
+	}
 
+	arch_teardown_msi_irqs(dev);
 
-static struct msi_desc* alloc_msi_entry(void)
-{
-	struct msi_desc *entry;
+	list_for_each_entry_safe(entry, tmp, &dev->msi_list, list) {
+		if (entry->msi_attrib.is_msix) {
+			if (list_is_last(&entry->list, &dev->msi_list))
+				iounmap(entry->mask_base);
+		}
+		list_del(&entry->list);
+		kfree(entry);
+	}
+}
 
-	entry = kzalloc(sizeof(struct msi_desc), GFP_KERNEL);
-	if (!entry)
+static struct msi_desc *alloc_msi_entry(struct pci_dev *dev)
+{
+	struct msi_desc *desc = kzalloc(sizeof(*desc), GFP_KERNEL);
+	if (!desc)
 		return NULL;
 
-	INIT_LIST_HEAD(&entry->list);
-	entry->irq = 0;
-	entry->dev = NULL;
+	INIT_LIST_HEAD(&desc->list);
+	desc->dev = dev;
 
-	return entry;
+	return desc;
+}
+
+static void pci_intx_for_msi(struct pci_dev *dev, int enable)
+{
+	if (!(dev->dev_flags & PCI_DEV_FLAGS_MSI_INTX_DISABLE_BUG))
+		pci_intx(dev, enable);
 }
 
-#ifdef CONFIG_PM
 static void __pci_restore_msi_state(struct pci_dev *dev)
 {
 	int pos;
@@ -238,16 +327,14 @@ static void __pci_restore_msi_state(struct pci_dev *dev)
 	entry = get_irq_msi(dev->irq);
 	pos = entry->msi_attrib.pos;
 
-	pci_intx(dev, 0);		/* disable intx */
-	msi_set_enable(dev, 0);
+	pci_intx_for_msi(dev, 0);
+	msi_set_enable(dev, pos, 0);
 	write_msi_msg(dev->irq, &entry->msg);
-	if (entry->msi_attrib.maskbit)
-		msi_set_mask_bit(dev->irq, entry->msi_attrib.masked);
 
 	pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &control);
-	control &= ~(PCI_MSI_FLAGS_QSIZE | PCI_MSI_FLAGS_ENABLE);
-	if (entry->msi_attrib.maskbit || !entry->msi_attrib.masked)
-		control |= PCI_MSI_FLAGS_ENABLE;
+	msi_mask_irq(entry, msi_capable_mask(control), entry->masked);
+	control &= ~PCI_MSI_FLAGS_QSIZE;
+	control |= (entry->msi_attrib.multiple << 4) | PCI_MSI_FLAGS_ENABLE;
 	pci_write_config_word(dev, pos + PCI_MSI_FLAGS, control);
 }
 
@@ -259,22 +346,22 @@ static void __pci_restore_msix_state(struct pci_dev *dev)
 
 	if (!dev->msix_enabled)
 		return;
+	BUG_ON(list_empty(&dev->msi_list));
+	entry = list_first_entry(&dev->msi_list, struct msi_desc, list);
+	pos = entry->msi_attrib.pos;
+	pci_read_config_word(dev, pos + PCI_MSIX_FLAGS, &control);
 
 	/* route the table */
-	pci_intx(dev, 0);		/* disable intx */
-	msix_set_enable(dev, 0);
+	pci_intx_for_msi(dev, 0);
+	control |= PCI_MSIX_FLAGS_ENABLE | PCI_MSIX_FLAGS_MASKALL;
+	pci_write_config_word(dev, pos + PCI_MSIX_FLAGS, control);
 
 	list_for_each_entry(entry, &dev->msi_list, list) {
 		write_msi_msg(entry->irq, &entry->msg);
-		msi_set_mask_bit(entry->irq, entry->msi_attrib.masked);
+		msix_mask_irq(entry, entry->masked);
 	}
 
-	BUG_ON(list_empty(&dev->msi_list));
-	entry = list_entry(dev->msi_list.next, struct msi_desc, list);
-	pos = entry->msi_attrib.pos;
-	pci_read_config_word(dev, pos + PCI_MSIX_FLAGS, &control);
 	control &= ~PCI_MSIX_FLAGS_MASKALL;
-	control |= PCI_MSIX_FLAGS_ENABLE;
 	pci_write_config_word(dev, pos + PCI_MSIX_FLAGS, control);
 }
 
@@ -283,74 +370,132 @@ void pci_restore_msi_state(struct pci_dev *dev)
 	__pci_restore_msi_state(dev);
 	__pci_restore_msix_state(dev);
 }
-#endif	/* CONFIG_PM */
+EXPORT_SYMBOL_GPL(pci_restore_msi_state);
 
 /**
  * msi_capability_init - configure device's MSI capability structure
  * @dev: pointer to the pci_dev data structure of MSI device function
+ * @nvec: number of interrupts to allocate
  *
- * Setup the MSI capability structure of device function with a single
- * 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 irq or non-zero for otherwise.
- **/
-static int msi_capability_init(struct pci_dev *dev)
+ * Setup the MSI capability structure of the device with the requested
+ * number of interrupts.  A return value of zero indicates the successful
+ * setup of an entry with the new MSI irq.  A negative return value indicates
+ * an error, and a positive return value indicates the number of interrupts
+ * which could have been allocated.
+ */
+static int msi_capability_init(struct pci_dev *dev, int nvec)
 {
 	struct msi_desc *entry;
 	int pos, ret;
 	u16 control;
+	unsigned mask;
 
-	msi_set_enable(dev, 0);	/* Ensure msi is disabled as I set it up */
+	pos = pci_find_capability(dev, PCI_CAP_ID_MSI);
+	msi_set_enable(dev, pos, 0);	/* Disable MSI during set up */
 
-   	pos = pci_find_capability(dev, PCI_CAP_ID_MSI);
 	pci_read_config_word(dev, msi_control_reg(pos), &control);
 	/* MSI Entry Initialization */
-	entry = alloc_msi_entry();
+	entry = alloc_msi_entry(dev);
 	if (!entry)
 		return -ENOMEM;
 
-	entry->msi_attrib.type = PCI_CAP_ID_MSI;
-	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.masked = 1;
-	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));
-	}
-	entry->dev = dev;
-	if (entry->msi_attrib.maskbit) {
-		unsigned int maskbits, temp;
-		/* All MSIs are unmasked by default, Mask them all */
-		pci_read_config_dword(dev,
-			msi_mask_bits_reg(pos, is_64bit_address(control)),
-			&maskbits);
-		temp = (1 << multi_msi_capable(control));
-		temp = ((temp - 1) & ~temp);
-		maskbits |= temp;
-		pci_write_config_dword(dev,
-			msi_mask_bits_reg(pos, is_64bit_address(control)),
-			maskbits);
-	}
+	entry->msi_attrib.is_msix	= 0;
+	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_irq	= dev->irq;	/* Save IOAPIC IRQ */
+	entry->msi_attrib.pos		= pos;
+
+	entry->mask_pos = msi_mask_reg(pos, entry->msi_attrib.is_64);
+	/* All MSIs are unmasked by default, Mask them all */
+	if (entry->msi_attrib.maskbit)
+		pci_read_config_dword(dev, entry->mask_pos, &entry->masked);
+	mask = msi_capable_mask(control);
+	msi_mask_irq(entry, mask, mask);
+
+	list_add_tail(&entry->list, &dev->msi_list);
+
 	/* Configure MSI capability structure */
-	ret = arch_setup_msi_irq(dev, entry);
+	ret = arch_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSI);
 	if (ret) {
-		kfree(entry);
+		msi_mask_irq(entry, mask, ~mask);
+		free_msi_irqs(dev);
 		return ret;
 	}
-	list_add(&entry->list, &dev->msi_list);
 
 	/* Set MSI enabled bits	 */
-	pci_intx(dev, 0);		/* disable intx */
-	msi_set_enable(dev, 1);
+	pci_intx_for_msi(dev, 0);
+	msi_set_enable(dev, pos, 1);
 	dev->msi_enabled = 1;
 
 	dev->irq = entry->irq;
 	return 0;
 }
 
+static void __iomem *msix_map_region(struct pci_dev *dev, unsigned pos,
+							unsigned nr_entries)
+{
+	unsigned long phys_addr;
+	u32 table_offset;
+	u8 bir;
+
+	pci_read_config_dword(dev, msix_table_offset_reg(pos), &table_offset);
+	bir = (u8)(table_offset & PCI_MSIX_FLAGS_BIRMASK);
+	table_offset &= ~PCI_MSIX_FLAGS_BIRMASK;
+	phys_addr = pci_resource_start(dev, bir) + table_offset;
+
+	return ioremap_nocache(phys_addr, nr_entries * PCI_MSIX_ENTRY_SIZE);
+}
+
+static int msix_setup_entries(struct pci_dev *dev, unsigned pos,
+				void __iomem *base, struct msix_entry *entries,
+				int nvec)
+{
+	struct msi_desc *entry;
+	int i;
+
+	for (i = 0; i < nvec; i++) {
+		entry = alloc_msi_entry(dev);
+		if (!entry) {
+			if (!i)
+				iounmap(base);
+			else
+				free_msi_irqs(dev);
+			/* No enough memory. Don't try again */
+			return -ENOMEM;
+		}
+
+		entry->msi_attrib.is_msix	= 1;
+		entry->msi_attrib.is_64		= 1;
+		entry->msi_attrib.entry_nr	= entries[i].entry;
+		entry->msi_attrib.default_irq	= dev->irq;
+		entry->msi_attrib.pos		= pos;
+		entry->mask_base		= base;
+
+		list_add_tail(&entry->list, &dev->msi_list);
+	}
+
+	return 0;
+}
+
+static void msix_program_entries(struct pci_dev *dev,
+					struct msix_entry *entries)
+{
+	struct msi_desc *entry;
+	int i = 0;
+
+	list_for_each_entry(entry, &dev->msi_list, list) {
+		int offset = entries[i].entry * PCI_MSIX_ENTRY_SIZE +
+						PCI_MSIX_ENTRY_VECTOR_CTRL;
+
+		entries[i].vector = entry->irq;
+		set_irq_msi(entry->irq, entry);
+		entry->masked = readl(entry->mask_base + offset);
+		msix_mask_irq(entry, 1);
+		i++;
+	}
+}
+
 /**
  * msix_capability_init - configure device's MSI-X capability
  * @dev: pointer to the pci_dev data structure of MSI-X device function
@@ -364,76 +509,69 @@ static int msi_capability_init(struct pci_dev *dev)
 static int msix_capability_init(struct pci_dev *dev,
 				struct msix_entry *entries, int nvec)
 {
-	struct msi_desc *entry;
-	int irq, pos, i, j, nr_entries, ret;
-	unsigned long phys_addr;
-	u32 table_offset;
- 	u16 control;
-	u8 bir;
+	int pos, ret;
+	u16 control;
 	void __iomem *base;
 
-	msix_set_enable(dev, 0);/* Ensure msix is disabled as I set it up */
+	pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
+	pci_read_config_word(dev, pos + PCI_MSIX_FLAGS, &control);
 
-   	pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
-	/* Request & Map MSI-X table region */
- 	pci_read_config_word(dev, msi_control_reg(pos), &control);
-	nr_entries = multi_msix_capable(control);
+	/* Ensure MSI-X is disabled while it is set up */
+	control &= ~PCI_MSIX_FLAGS_ENABLE;
+	pci_write_config_word(dev, pos + PCI_MSIX_FLAGS, control);
 
- 	pci_read_config_dword(dev, msix_table_offset_reg(pos), &table_offset);
-	bir = (u8)(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)
+	/* Request & Map MSI-X table region */
+	base = msix_map_region(dev, pos, multi_msix_capable(control));
+	if (!base)
 		return -ENOMEM;
 
-	/* MSI-X Table Initialization */
-	for (i = 0; i < nvec; i++) {
-		entry = alloc_msi_entry();
-		if (!entry)
-			break;
-
- 		j = entries[i].entry;
-		entry->msi_attrib.type = PCI_CAP_ID_MSIX;
-		entry->msi_attrib.is_64 = 1;
-		entry->msi_attrib.entry_nr = j;
-		entry->msi_attrib.maskbit = 1;
-		entry->msi_attrib.masked = 1;
-		entry->msi_attrib.default_irq = dev->irq;
-		entry->msi_attrib.pos = pos;
-		entry->dev = dev;
-		entry->mask_base = base;
-
-		/* Configure MSI-X capability structure */
-		ret = arch_setup_msi_irq(dev, entry);
-		if (ret) {
-			kfree(entry);
-			break;
-		}
- 		entries[i].vector = entry->irq;
-		list_add(&entry->list, &dev->msi_list);
-	}
-	if (i != nvec) {
-		int avail = i - 1;
-		i--;
-		for (; i >= 0; i--) {
-			irq = (entries + i)->vector;
-			msi_free_irq(dev, irq);
-			(entries + i)->vector = 0;
-		}
-		/* If we had some success report the number of irqs
+	ret = msix_setup_entries(dev, pos, base, entries, nvec);
+	if (ret)
+		return ret;
+
+	ret = arch_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSIX);
+	if (ret)
+		goto error;
+
+	/*
+	 * Some devices require MSI-X to be enabled before we can touch the
+	 * MSI-X registers.  We need to mask all the vectors to prevent
+	 * interrupts coming in before they're fully set up.
+	 */
+	control |= PCI_MSIX_FLAGS_MASKALL | PCI_MSIX_FLAGS_ENABLE;
+	pci_write_config_word(dev, pos + PCI_MSIX_FLAGS, control);
+
+	msix_program_entries(dev, entries);
+
+	/* Set MSI-X enabled bits and unmask the function */
+	pci_intx_for_msi(dev, 0);
+	dev->msix_enabled = 1;
+
+	control &= ~PCI_MSIX_FLAGS_MASKALL;
+	pci_write_config_word(dev, pos + PCI_MSIX_FLAGS, control);
+
+	return 0;
+
+error:
+	if (ret < 0) {
+		/*
+		 * If we had some success, report the number of irqs
 		 * we succeeded in setting up.
 		 */
-		if (avail <= 0)
-			avail = -EBUSY;
-		return avail;
+		struct msi_desc *entry;
+		int avail = 0;
+
+		list_for_each_entry(entry, &dev->msi_list, list) {
+			if (entry->irq != 0)
+				avail++;
+		}
+		if (avail != 0)
+			ret = avail;
 	}
-	/* Set MSI-X enabled bits */
-	pci_intx(dev, 0);		/* disable intx */
-	msix_set_enable(dev, 1);
-	dev->msix_enabled = 1;
 
-	return 0;
+	free_msi_irqs(dev);
+
+	return ret;
 }
 
 /**
@@ -446,7 +584,7 @@ static int msix_capability_init(struct pci_dev *dev,
  * to determine if MSI/-X are supported for the device. If MSI/-X is
  * supported return 0, else return an error code.
  **/
-static int pci_msi_check_device(struct pci_dev* dev, int nvec, int type)
+static int pci_msi_check_device(struct pci_dev *dev, int nvec, int type)
 {
 	struct pci_bus *bus;
 	int ret;
@@ -463,8 +601,9 @@ static int pci_msi_check_device(struct pci_dev* dev, int nvec, int type)
 	if (nvec < 1)
 		return -ERANGE;
 
-	/* Any bridge which does NOT route MSI transactions from it's
-	 * secondary bus to it's primary bus must set NO_MSI flag on
+	/*
+	 * Any bridge which does NOT route MSI transactions from its
+	 * secondary bus to its 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.
@@ -484,92 +623,102 @@ static int pci_msi_check_device(struct pci_dev* dev, int nvec, int type)
 }
 
 /**
- * pci_enable_msi - configure device's MSI capability structure
- * @dev: pointer to the pci_dev data structure of MSI device function
+ * pci_enable_msi_block - configure device's MSI capability structure
+ * @dev: device to configure
+ * @nvec: number of interrupts to configure
  *
- * Setup the MSI capability structure of device function with
- * 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
- * irq or non-zero for otherwise.
- **/
-int pci_enable_msi(struct pci_dev* dev)
+ * Allocate IRQs for a device with the MSI capability.
+ * This function returns a negative errno if an error occurs.  If it
+ * is unable to allocate the number of interrupts requested, it returns
+ * the number of interrupts it might be able to allocate.  If it successfully
+ * allocates at least the number of interrupts requested, it returns 0 and
+ * updates the @dev's irq member to the lowest new interrupt number; the
+ * other interrupt numbers allocated to this device are consecutive.
+ */
+int pci_enable_msi_block(struct pci_dev *dev, unsigned int nvec)
 {
-	int status;
+	int status, pos, maxvec;
+	u16 msgctl;
 
-	status = pci_msi_check_device(dev, 1, PCI_CAP_ID_MSI);
+	pos = pci_find_capability(dev, PCI_CAP_ID_MSI);
+	if (!pos)
+		return -EINVAL;
+	pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &msgctl);
+	maxvec = 1 << ((msgctl & PCI_MSI_FLAGS_QMASK) >> 1);
+	if (nvec > maxvec)
+		return maxvec;
+
+	status = pci_msi_check_device(dev, nvec, PCI_CAP_ID_MSI);
 	if (status)
 		return status;
 
 	WARN_ON(!!dev->msi_enabled);
 
-	/* Check whether driver already requested for MSI-X irqs */
+	/* Check whether driver already requested MSI-X irqs */
 	if (dev->msix_enabled) {
-		printk(KERN_INFO "PCI: %s: Can't enable MSI.  "
-			"Device already has MSI-X enabled\n",
-			pci_name(dev));
+		dev_info(&dev->dev, "can't enable MSI "
+			 "(MSI-X already enabled)\n");
 		return -EINVAL;
 	}
-	status = msi_capability_init(dev);
+
+	status = msi_capability_init(dev, nvec);
 	return status;
 }
-EXPORT_SYMBOL(pci_enable_msi);
+EXPORT_SYMBOL(pci_enable_msi_block);
 
-void pci_disable_msi(struct pci_dev* dev)
+void pci_msi_shutdown(struct pci_dev *dev)
 {
-	struct msi_desc *entry;
-	int default_irq;
+	struct msi_desc *desc;
+	u32 mask;
+	u16 ctrl;
+	unsigned pos;
 
 	if (!pci_msi_enable || !dev || !dev->msi_enabled)
 		return;
 
-	msi_set_enable(dev, 0);
-	pci_intx(dev, 1);		/* enable intx */
-	dev->msi_enabled = 0;
-
 	BUG_ON(list_empty(&dev->msi_list));
-	entry = list_entry(dev->msi_list.next, struct msi_desc, list);
-	if (!entry->dev || entry->msi_attrib.type != PCI_CAP_ID_MSI) {
-		return;
-	}
+	desc = list_first_entry(&dev->msi_list, struct msi_desc, list);
+	pos = desc->msi_attrib.pos;
 
-	default_irq = entry->msi_attrib.default_irq;
-	msi_free_irq(dev, entry->irq);
+	msi_set_enable(dev, pos, 0);
+	pci_intx_for_msi(dev, 1);
+	dev->msi_enabled = 0;
+
+	/* Return the device with MSI unmasked as initial states */
+	pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &ctrl);
+	mask = msi_capable_mask(ctrl);
+	/* Keep cached state to be restored */
+	__msi_mask_irq(desc, mask, ~mask);
 
 	/* Restore dev->irq to its default pin-assertion irq */
-	dev->irq = default_irq;
+	dev->irq = desc->msi_attrib.default_irq;
 }
-EXPORT_SYMBOL(pci_disable_msi);
 
-static int msi_free_irq(struct pci_dev* dev, int irq)
+void pci_disable_msi(struct pci_dev *dev)
 {
-	struct msi_desc *entry;
-	int entry_nr, type;
-	void __iomem *base;
-
-	BUG_ON(irq_has_action(irq));
-
-	entry = get_irq_msi(irq);
-	if (!entry || entry->dev != dev) {
-		return -EINVAL;
-	}
-	type = entry->msi_attrib.type;
-	entry_nr = entry->msi_attrib.entry_nr;
-	base = entry->mask_base;
-	list_del(&entry->list);
+	if (!pci_msi_enable || !dev || !dev->msi_enabled)
+		return;
 
-	arch_teardown_msi_irq(irq);
-	kfree(entry);
+	pci_msi_shutdown(dev);
+	free_msi_irqs(dev);
+}
+EXPORT_SYMBOL(pci_disable_msi);
 
-	if (type == PCI_CAP_ID_MSIX) {
-		writel(1, base + entry_nr * PCI_MSIX_ENTRY_SIZE +
-			PCI_MSIX_ENTRY_VECTOR_CTRL_OFFSET);
+/**
+ * pci_msix_table_size - return the number of device's MSI-X table entries
+ * @dev: pointer to the pci_dev data structure of MSI-X device function
+ */
+int pci_msix_table_size(struct pci_dev *dev)
+{
+	int pos;
+	u16 control;
 
-		if (list_empty(&dev->msi_list))
-			iounmap(base);
-	}
+	pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
+	if (!pos)
+		return 0;
 
-	return 0;
+	pci_read_config_word(dev, msi_control_reg(pos), &control);
+	return multi_msix_capable(control);
 }
 
 /**
@@ -584,27 +733,24 @@ static int msi_free_irq(struct pci_dev* dev, int irq)
  * indicates the successful configuration of MSI-X capability structure
  * 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 irqs available. Driver should use the returned value to re-send
- * its request.
+ * of irqs or MSI-X vectors 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 pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries, int nvec)
 {
-	int status, pos, nr_entries;
+	int status, nr_entries;
 	int i, j;
-	u16 control;
 
 	if (!entries)
- 		return -EINVAL;
+		return -EINVAL;
 
 	status = pci_msi_check_device(dev, nvec, PCI_CAP_ID_MSIX);
 	if (status)
 		return status;
 
-	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);
+	nr_entries = pci_msix_table_size(dev);
 	if (nvec > nr_entries)
-		return -EINVAL;
+		return nr_entries;
 
 	/* Check for any invalid entries */
 	for (i = 0; i < nvec; i++) {
@@ -618,10 +764,9 @@ int pci_enable_msix(struct pci_dev* dev, struct msix_entry *entries, int nvec)
 	WARN_ON(!!dev->msix_enabled);
 
 	/* Check whether driver already requested for MSI irq */
-   	if (dev->msi_enabled) {
-		printk(KERN_INFO "PCI: %s: Can't enable MSI-X.  "
-		       "Device already has an MSI irq assigned\n",
-		       pci_name(dev));
+	if (dev->msi_enabled) {
+		dev_info(&dev->dev, "can't enable MSI-X "
+		       "(MSI IRQ already assigned)\n");
 		return -EINVAL;
 	}
 	status = msix_capability_init(dev, entries, nvec);
@@ -629,24 +774,31 @@ int pci_enable_msix(struct pci_dev* dev, struct msix_entry *entries, int nvec)
 }
 EXPORT_SYMBOL(pci_enable_msix);
 
-static void msix_free_all_irqs(struct pci_dev *dev)
+void pci_msix_shutdown(struct pci_dev *dev)
 {
 	struct msi_desc *entry;
 
-	list_for_each_entry(entry, &dev->msi_list, list)
-		msi_free_irq(dev, entry->irq);
-}
-
-void pci_disable_msix(struct pci_dev* dev)
-{
 	if (!pci_msi_enable || !dev || !dev->msix_enabled)
 		return;
 
+	/* Return the device with MSI-X masked as initial states */
+	list_for_each_entry(entry, &dev->msi_list, list) {
+		/* Keep cached states to be restored */
+		__msix_mask_irq(entry, 1);
+	}
+
 	msix_set_enable(dev, 0);
-	pci_intx(dev, 1);		/* enable intx */
+	pci_intx_for_msi(dev, 1);
 	dev->msix_enabled = 0;
+}
+
+void pci_disable_msix(struct pci_dev *dev)
+{
+	if (!pci_msi_enable || !dev || !dev->msix_enabled)
+		return;
 
-	msix_free_all_irqs(dev);
+	pci_msix_shutdown(dev);
+	free_msi_irqs(dev);
 }
 EXPORT_SYMBOL(pci_disable_msix);
 
@@ -659,20 +811,13 @@ EXPORT_SYMBOL(pci_disable_msix);
  * 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)
+void msi_remove_pci_irq_vectors(struct pci_dev *dev)
 {
 	if (!pci_msi_enable || !dev)
- 		return;
-
-	if (dev->msi_enabled) {
-		struct msi_desc *entry;
-		BUG_ON(list_empty(&dev->msi_list));
-		entry = list_entry(dev->msi_list.next, struct msi_desc, list);
-		msi_free_irq(dev, entry->irq);
-	}
+		return;
 
-	if (dev->msix_enabled)
-		msix_free_all_irqs(dev);
+	if (dev->msi_enabled || dev->msix_enabled)
+		free_msi_irqs(dev);
 }
 
 void pci_no_msi(void)
@@ -680,17 +825,19 @@ void pci_no_msi(void)
 	pci_msi_enable = 0;
 }
 
-void pci_msi_init_pci_dev(struct pci_dev *dev)
+/**
+ * pci_msi_enabled - is MSI enabled?
+ *
+ * Returns true if MSI has not been disabled by the command-line option
+ * pci=nomsi.
+ **/
+int pci_msi_enabled(void)
 {
-	INIT_LIST_HEAD(&dev->msi_list);
+	return pci_msi_enable;
 }
+EXPORT_SYMBOL(pci_msi_enabled);
 
-
-/* Arch hooks */
-
-int __attribute__ ((weak))
-arch_msi_check_device(struct pci_dev* dev, int nvec, int type)
+void pci_msi_init_pci_dev(struct pci_dev *dev)
 {
-	return 0;
+	INIT_LIST_HEAD(&dev->msi_list);
 }
-