1 files changed, 102 insertions, 205 deletions

diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index e5e75331b415..0099a00af361 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -129,94 +129,95 @@ void __weak arch_restore_msi_irqs(struct pci_dev *dev)
 	return default_restore_msi_irqs(dev);
 }
 
-static inline __attribute_const__ u32 msi_mask(unsigned x)
-{
-	/* Don't shift by >= width of type */
-	if (x >= 5)
-		return 0xffffffff;
-	return (1 << (1 << x)) - 1;
-}
-
 /*
  * 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.
  */
-void __pci_msi_desc_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
+static inline __attribute_const__ u32 msi_multi_mask(struct msi_desc *desc)
+{
+	/* Don't shift by >= width of type */
+	if (desc->msi_attrib.multi_cap >= 5)
+		return 0xffffffff;
+	return (1 << (1 << desc->msi_attrib.multi_cap)) - 1;
+}
+
+static noinline void pci_msi_update_mask(struct msi_desc *desc, u32 clear, u32 set)
 {
 	raw_spinlock_t *lock = &desc->dev->msi_lock;
 	unsigned long flags;
 
-	if (pci_msi_ignore_mask || !desc->msi_attrib.maskbit)
-		return;
-
 	raw_spin_lock_irqsave(lock, flags);
-	desc->masked &= ~mask;
-	desc->masked |= flag;
+	desc->msi_mask &= ~clear;
+	desc->msi_mask |= set;
 	pci_write_config_dword(msi_desc_to_pci_dev(desc), desc->mask_pos,
-			       desc->masked);
+			       desc->msi_mask);
 	raw_spin_unlock_irqrestore(lock, flags);
 }
 
-static void msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
+static inline void pci_msi_mask(struct msi_desc *desc, u32 mask)
 {
-	__pci_msi_desc_mask_irq(desc, mask, flag);
+	pci_msi_update_mask(desc, 0, mask);
 }
 
-static void __iomem *pci_msix_desc_addr(struct msi_desc *desc)
+static inline void pci_msi_unmask(struct msi_desc *desc, u32 mask)
 {
-	if (desc->msi_attrib.is_virtual)
-		return NULL;
+	pci_msi_update_mask(desc, mask, 0);
+}
 
-	return desc->mask_base +
-		desc->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE;
+static inline void __iomem *pci_msix_desc_addr(struct msi_desc *desc)
+{
+	return desc->mask_base + desc->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE;
 }
 
 /*
- * 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.
+ * 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.
+ * It does not affect the msi_desc::msix_ctrl cache either. Use with care!
  */
-u32 __pci_msix_desc_mask_irq(struct msi_desc *desc, u32 flag)
+static void pci_msix_write_vector_ctrl(struct msi_desc *desc, u32 ctrl)
 {
-	u32 mask_bits = desc->masked;
-	void __iomem *desc_addr;
-
-	if (pci_msi_ignore_mask)
-		return 0;
-
-	desc_addr = pci_msix_desc_addr(desc);
-	if (!desc_addr)
-		return 0;
+	void __iomem *desc_addr = pci_msix_desc_addr(desc);
 
-	mask_bits &= ~PCI_MSIX_ENTRY_CTRL_MASKBIT;
-	if (flag & PCI_MSIX_ENTRY_CTRL_MASKBIT)
-		mask_bits |= PCI_MSIX_ENTRY_CTRL_MASKBIT;
+	writel(ctrl, desc_addr + PCI_MSIX_ENTRY_VECTOR_CTRL);
+}
 
-	writel(mask_bits, desc_addr + PCI_MSIX_ENTRY_VECTOR_CTRL);
+static inline void pci_msix_mask(struct msi_desc *desc)
+{
+	desc->msix_ctrl |= PCI_MSIX_ENTRY_CTRL_MASKBIT;
+	pci_msix_write_vector_ctrl(desc, desc->msix_ctrl);
+	/* Flush write to device */
+	readl(desc->mask_base);
+}
 
-	return mask_bits;
+static inline void pci_msix_unmask(struct msi_desc *desc)
+{
+	desc->msix_ctrl &= ~PCI_MSIX_ENTRY_CTRL_MASKBIT;
+	pci_msix_write_vector_ctrl(desc, desc->msix_ctrl);
 }
 
-static void msix_mask_irq(struct msi_desc *desc, u32 flag)
+static void __pci_msi_mask_desc(struct msi_desc *desc, u32 mask)
 {
-	desc->masked = __pci_msix_desc_mask_irq(desc, flag);
+	if (pci_msi_ignore_mask || desc->msi_attrib.is_virtual)
+		return;
+
+	if (desc->msi_attrib.is_msix)
+		pci_msix_mask(desc);
+	else if (desc->msi_attrib.maskbit)
+		pci_msi_mask(desc, mask);
 }
 
-static void msi_set_mask_bit(struct irq_data *data, u32 flag)
+static void __pci_msi_unmask_desc(struct msi_desc *desc, u32 mask)
 {
-	struct msi_desc *desc = irq_data_get_msi_desc(data);
+	if (pci_msi_ignore_mask || desc->msi_attrib.is_virtual)
+		return;
 
-	if (desc->msi_attrib.is_msix) {
-		msix_mask_irq(desc, flag);
-		readl(desc->mask_base);		/* Flush write to device */
-	} else {
-		unsigned offset = data->irq - desc->irq;
-		msi_mask_irq(desc, 1 << offset, flag << offset);
-	}
+	if (desc->msi_attrib.is_msix)
+		pci_msix_unmask(desc);
+	else if (desc->msi_attrib.maskbit)
+		pci_msi_unmask(desc, mask);
 }
 
 /**
@@ -225,7 +226,9 @@ static void msi_set_mask_bit(struct irq_data *data, u32 flag)
  */
 void pci_msi_mask_irq(struct irq_data *data)
 {
-	msi_set_mask_bit(data, 1);
+	struct msi_desc *desc = irq_data_get_msi_desc(data);
+
+	__pci_msi_mask_desc(desc, BIT(data->irq - desc->irq));
 }
 EXPORT_SYMBOL_GPL(pci_msi_mask_irq);
 
@@ -235,7 +238,9 @@ EXPORT_SYMBOL_GPL(pci_msi_mask_irq);
  */
 void pci_msi_unmask_irq(struct irq_data *data)
 {
-	msi_set_mask_bit(data, 0);
+	struct msi_desc *desc = irq_data_get_msi_desc(data);
+
+	__pci_msi_unmask_desc(desc, BIT(data->irq - desc->irq));
 }
 EXPORT_SYMBOL_GPL(pci_msi_unmask_irq);
 
@@ -256,10 +261,8 @@ void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
 	if (entry->msi_attrib.is_msix) {
 		void __iomem *base = pci_msix_desc_addr(entry);
 
-		if (!base) {
-			WARN_ON(1);
+		if (WARN_ON_ONCE(entry->msi_attrib.is_virtual))
 			return;
-		}
 
 		msg->address_lo = readl(base + PCI_MSIX_ENTRY_LOWER_ADDR);
 		msg->address_hi = readl(base + PCI_MSIX_ENTRY_UPPER_ADDR);
@@ -290,9 +293,10 @@ void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
 		/* Don't touch the hardware now */
 	} else if (entry->msi_attrib.is_msix) {
 		void __iomem *base = pci_msix_desc_addr(entry);
-		bool unmasked = !(entry->masked & PCI_MSIX_ENTRY_CTRL_MASKBIT);
+		u32 ctrl = entry->msix_ctrl;
+		bool unmasked = !(ctrl & PCI_MSIX_ENTRY_CTRL_MASKBIT);
 
-		if (!base)
+		if (entry->msi_attrib.is_virtual)
 			goto skip;
 
 		/*
@@ -304,14 +308,14 @@ void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
 		 * undefined."
 		 */
 		if (unmasked)
-			__pci_msix_desc_mask_irq(entry, PCI_MSIX_ENTRY_CTRL_MASKBIT);
+			pci_msix_write_vector_ctrl(entry, ctrl | PCI_MSIX_ENTRY_CTRL_MASKBIT);
 
 		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);
 
 		if (unmasked)
-			__pci_msix_desc_mask_irq(entry, 0);
+			pci_msix_write_vector_ctrl(entry, ctrl);
 
 		/* Ensure that the writes are visible in the device */
 		readl(base + PCI_MSIX_ENTRY_DATA);
@@ -359,9 +363,7 @@ static void free_msi_irqs(struct pci_dev *dev)
 {
 	struct list_head *msi_list = dev_to_msi_list(&dev->dev);
 	struct msi_desc *entry, *tmp;
-	struct attribute **msi_attrs;
-	struct device_attribute *dev_attr;
-	int i, count = 0;
+	int i;
 
 	for_each_pci_msi_entry(entry, dev)
 		if (entry->irq)
@@ -381,18 +383,7 @@ static void free_msi_irqs(struct pci_dev *dev)
 	}
 
 	if (dev->msi_irq_groups) {
-		sysfs_remove_groups(&dev->dev.kobj, dev->msi_irq_groups);
-		msi_attrs = dev->msi_irq_groups[0]->attrs;
-		while (msi_attrs[count]) {
-			dev_attr = container_of(msi_attrs[count],
-						struct device_attribute, attr);
-			kfree(dev_attr->attr.name);
-			kfree(dev_attr);
-			++count;
-		}
-		kfree(msi_attrs);
-		kfree(dev->msi_irq_groups[0]);
-		kfree(dev->msi_irq_groups);
+		msi_destroy_sysfs(&dev->dev, dev->msi_irq_groups);
 		dev->msi_irq_groups = NULL;
 	}
 }
@@ -429,8 +420,7 @@ static void __pci_restore_msi_state(struct pci_dev *dev)
 	arch_restore_msi_irqs(dev);
 
 	pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &control);
-	msi_mask_irq(entry, msi_mask(entry->msi_attrib.multi_cap),
-		     entry->masked);
+	pci_msi_update_mask(entry, 0, 0);
 	control &= ~PCI_MSI_FLAGS_QSIZE;
 	control |= (entry->msi_attrib.multiple << 4) | PCI_MSI_FLAGS_ENABLE;
 	pci_write_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, control);
@@ -461,7 +451,7 @@ static void __pci_restore_msix_state(struct pci_dev *dev)
 
 	arch_restore_msi_irqs(dev);
 	for_each_pci_msi_entry(entry, dev)
-		msix_mask_irq(entry, entry->masked);
+		pci_msix_write_vector_ctrl(entry, entry->msix_ctrl);
 
 	pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL, 0);
 }
@@ -473,102 +463,6 @@ void pci_restore_msi_state(struct pci_dev *dev)
 }
 EXPORT_SYMBOL_GPL(pci_restore_msi_state);
 
-static ssize_t msi_mode_show(struct device *dev, struct device_attribute *attr,
-			     char *buf)
-{
-	struct msi_desc *entry;
-	unsigned long irq;
-	int retval;
-
-	retval = kstrtoul(attr->attr.name, 10, &irq);
-	if (retval)
-		return retval;
-
-	entry = irq_get_msi_desc(irq);
-	if (!entry)
-		return -ENODEV;
-
-	return sysfs_emit(buf, "%s\n",
-			  entry->msi_attrib.is_msix ? "msix" : "msi");
-}
-
-static int populate_msi_sysfs(struct pci_dev *pdev)
-{
-	struct attribute **msi_attrs;
-	struct attribute *msi_attr;
-	struct device_attribute *msi_dev_attr;
-	struct attribute_group *msi_irq_group;
-	const struct attribute_group **msi_irq_groups;
-	struct msi_desc *entry;
-	int ret = -ENOMEM;
-	int num_msi = 0;
-	int count = 0;
-	int i;
-
-	/* Determine how many msi entries we have */
-	for_each_pci_msi_entry(entry, pdev)
-		num_msi += entry->nvec_used;
-	if (!num_msi)
-		return 0;
-
-	/* Dynamically create the MSI attributes for the PCI device */
-	msi_attrs = kcalloc(num_msi + 1, sizeof(void *), GFP_KERNEL);
-	if (!msi_attrs)
-		return -ENOMEM;
-	for_each_pci_msi_entry(entry, pdev) {
-		for (i = 0; i < entry->nvec_used; i++) {
-			msi_dev_attr = kzalloc(sizeof(*msi_dev_attr), GFP_KERNEL);
-			if (!msi_dev_attr)
-				goto error_attrs;
-			msi_attrs[count] = &msi_dev_attr->attr;
-
-			sysfs_attr_init(&msi_dev_attr->attr);
-			msi_dev_attr->attr.name = kasprintf(GFP_KERNEL, "%d",
-							    entry->irq + i);
-			if (!msi_dev_attr->attr.name)
-				goto error_attrs;
-			msi_dev_attr->attr.mode = S_IRUGO;
-			msi_dev_attr->show = msi_mode_show;
-			++count;
-		}
-	}
-
-	msi_irq_group = kzalloc(sizeof(*msi_irq_group), GFP_KERNEL);
-	if (!msi_irq_group)
-		goto error_attrs;
-	msi_irq_group->name = "msi_irqs";
-	msi_irq_group->attrs = msi_attrs;
-
-	msi_irq_groups = kcalloc(2, sizeof(void *), GFP_KERNEL);
-	if (!msi_irq_groups)
-		goto error_irq_group;
-	msi_irq_groups[0] = msi_irq_group;
-
-	ret = sysfs_create_groups(&pdev->dev.kobj, msi_irq_groups);
-	if (ret)
-		goto error_irq_groups;
-	pdev->msi_irq_groups = msi_irq_groups;
-
-	return 0;
-
-error_irq_groups:
-	kfree(msi_irq_groups);
-error_irq_group:
-	kfree(msi_irq_group);
-error_attrs:
-	count = 0;
-	msi_attr = msi_attrs[count];
-	while (msi_attr) {
-		msi_dev_attr = container_of(msi_attr, struct device_attribute, attr);
-		kfree(msi_attr->name);
-		kfree(msi_dev_attr);
-		++count;
-		msi_attr = msi_attrs[count];
-	}
-	kfree(msi_attrs);
-	return ret;
-}
-
 static struct msi_desc *
 msi_setup_entry(struct pci_dev *dev, int nvec, struct irq_affinity *affd)
 {
@@ -602,7 +496,7 @@ msi_setup_entry(struct pci_dev *dev, int nvec, struct irq_affinity *affd)
 
 	/* Save the initial mask status */
 	if (entry->msi_attrib.maskbit)
-		pci_read_config_dword(dev, entry->mask_pos, &entry->masked);
+		pci_read_config_dword(dev, entry->mask_pos, &entry->msi_mask);
 
 out:
 	kfree(masks);
@@ -613,8 +507,11 @@ static int msi_verify_entries(struct pci_dev *dev)
 {
 	struct msi_desc *entry;
 
+	if (!dev->no_64bit_msi)
+		return 0;
+
 	for_each_pci_msi_entry(entry, dev) {
-		if (entry->msg.address_hi && dev->no_64bit_msi) {
+		if (entry->msg.address_hi) {
 			pci_err(dev, "arch assigned 64-bit MSI address %#x%08x but device only supports 32 bits\n",
 				entry->msg.address_hi, entry->msg.address_lo);
 			return -EIO;
@@ -640,7 +537,6 @@ static int msi_capability_init(struct pci_dev *dev, int nvec,
 {
 	struct msi_desc *entry;
 	int ret;
-	unsigned mask;
 
 	pci_msi_set_enable(dev, 0);	/* Disable MSI during set up */
 
@@ -649,31 +545,23 @@ static int msi_capability_init(struct pci_dev *dev, int nvec,
 		return -ENOMEM;
 
 	/* All MSIs are unmasked by default; mask them all */
-	mask = msi_mask(entry->msi_attrib.multi_cap);
-	msi_mask_irq(entry, mask, mask);
+	pci_msi_mask(entry, msi_multi_mask(entry));
 
 	list_add_tail(&entry->list, dev_to_msi_list(&dev->dev));
 
 	/* Configure MSI capability structure */
 	ret = pci_msi_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSI);
-	if (ret) {
-		msi_mask_irq(entry, mask, 0);
-		free_msi_irqs(dev);
-		return ret;
-	}
+	if (ret)
+		goto err;
 
 	ret = msi_verify_entries(dev);
-	if (ret) {
-		msi_mask_irq(entry, mask, 0);
-		free_msi_irqs(dev);
-		return ret;
-	}
+	if (ret)
+		goto err;
 
-	ret = populate_msi_sysfs(dev);
-	if (ret) {
-		msi_mask_irq(entry, mask, 0);
-		free_msi_irqs(dev);
-		return ret;
+	dev->msi_irq_groups = msi_populate_sysfs(&dev->dev);
+	if (IS_ERR(dev->msi_irq_groups)) {
+		ret = PTR_ERR(dev->msi_irq_groups);
+		goto err;
 	}
 
 	/* Set MSI enabled bits	*/
@@ -684,6 +572,11 @@ static int msi_capability_init(struct pci_dev *dev, int nvec,
 	pcibios_free_irq(dev);
 	dev->irq = entry->irq;
 	return 0;
+
+err:
+	pci_msi_unmask(entry, msi_multi_mask(entry));
+	free_msi_irqs(dev);
+	return ret;
 }
 
 static void __iomem *msix_map_region(struct pci_dev *dev, unsigned nr_entries)
@@ -745,9 +638,10 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base,
 		entry->msi_attrib.default_irq	= dev->irq;
 		entry->mask_base		= base;
 
-		addr = pci_msix_desc_addr(entry);
-		if (addr)
-			entry->masked = readl(addr + PCI_MSIX_ENTRY_VECTOR_CTRL);
+		if (!entry->msi_attrib.is_virtual) {
+			addr = pci_msix_desc_addr(entry);
+			entry->msix_ctrl = readl(addr + PCI_MSIX_ENTRY_VECTOR_CTRL);
+		}
 
 		list_add_tail(&entry->list, dev_to_msi_list(&dev->dev));
 		if (masks)
@@ -776,6 +670,9 @@ static void msix_mask_all(void __iomem *base, int tsize)
 	u32 ctrl = PCI_MSIX_ENTRY_CTRL_MASKBIT;
 	int i;
 
+	if (pci_msi_ignore_mask)
+		return;
+
 	for (i = 0; i < tsize; i++, base += PCI_MSIX_ENTRY_SIZE)
 		writel(ctrl, base + PCI_MSIX_ENTRY_VECTOR_CTRL);
 }
@@ -833,9 +730,11 @@ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries,
 
 	msix_update_entries(dev, entries);
 
-	ret = populate_msi_sysfs(dev);
-	if (ret)
+	dev->msi_irq_groups = msi_populate_sysfs(&dev->dev);
+	if (IS_ERR(dev->msi_irq_groups)) {
+		ret = PTR_ERR(dev->msi_irq_groups);
 		goto out_free;
+	}
 
 	/* Set MSI-X enabled bits and unmask the function */
 	pci_intx_for_msi(dev, 0);
@@ -948,7 +847,6 @@ EXPORT_SYMBOL(pci_msi_vec_count);
 static void pci_msi_shutdown(struct pci_dev *dev)
 {
 	struct msi_desc *desc;
-	u32 mask;
 
 	if (!pci_msi_enable || !dev || !dev->msi_enabled)
 		return;
@@ -961,8 +859,7 @@ static void pci_msi_shutdown(struct pci_dev *dev)
 	dev->msi_enabled = 0;
 
 	/* Return the device with MSI unmasked as initial states */
-	mask = msi_mask(desc->msi_attrib.multi_cap);
-	msi_mask_irq(desc, mask, 0);
+	pci_msi_unmask(desc, msi_multi_mask(desc));
 
 	/* Restore dev->irq to its default pin-assertion IRQ */
 	dev->irq = desc->msi_attrib.default_irq;
@@ -1048,7 +945,7 @@ static void pci_msix_shutdown(struct pci_dev *dev)
 
 	/* Return the device with MSI-X masked as initial states */
 	for_each_pci_msi_entry(entry, dev)
-		__pci_msix_desc_mask_irq(entry, 1);
+		pci_msix_mask(entry);
 
 	pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0);
 	pci_intx_for_msi(dev, 1);