[PATCH 2/9] PCI/MSI: Support allocating virtual MSI interrupts

[Logan Gunthorpe <logang@deltatee.com>]

For NTB devices, we want to be able to trigger MSI interrupts
through a memory window. In these cases we may want to use
more interrupts than the NTB PCI device has available in its MSI-X
table.

We allow for this by creating a new 'virtual' interrupt. These
interrupts are allocated as usual but are not programmed into the
MSI-X table (as there may not be space for them).

The MSI address and data will then handled through an NTB MSI library
introduced later in this series.

Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/msi.c   | 51 +++++++++++++++++++++++++++++++++++++--------
 include/linux/msi.h |  1 +
 include/linux/pci.h |  9 ++++++++
 3 files changed, 52 insertions(+), 9 deletions(-)

diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 4c0b47867258..145587da686c 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -192,6 +192,9 @@ static void msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
 
 static void __iomem *pci_msix_desc_addr(struct msi_desc *desc)
 {
+	if (desc->msi_attrib.is_virtual)
+		return NULL;
+
 	return desc->mask_base +
 		desc->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE;
 }
@@ -206,14 +209,19 @@ static void __iomem *pci_msix_desc_addr(struct msi_desc *desc)
 u32 __pci_msix_desc_mask_irq(struct msi_desc *desc, u32 flag)
 {
 	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;
 
 	mask_bits &= ~PCI_MSIX_ENTRY_CTRL_MASKBIT;
 	if (flag)
 		mask_bits |= PCI_MSIX_ENTRY_CTRL_MASKBIT;
-	writel(mask_bits, pci_msix_desc_addr(desc) + PCI_MSIX_ENTRY_VECTOR_CTRL);
+
+	writel(mask_bits, desc_addr + PCI_MSIX_ENTRY_VECTOR_CTRL);
 
 	return mask_bits;
 }
@@ -273,6 +281,11 @@ 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);
+			return;
+		}
+
 		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);
@@ -303,6 +316,9 @@ void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
 	} else if (entry->msi_attrib.is_msix) {
 		void __iomem *base = pci_msix_desc_addr(entry);
 
+		if (!base)
+			goto skip;
+
 		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);
@@ -327,6 +343,8 @@ void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
 					      msg->data);
 		}
 	}
+
+skip:
 	entry->msg = *msg;
 }
 
@@ -550,6 +568,7 @@ msi_setup_entry(struct pci_dev *dev, int nvec, const struct irq_affinity *affd)
 
 	entry->msi_attrib.is_msix	= 0;
 	entry->msi_attrib.is_64		= !!(control & PCI_MSI_FLAGS_64BIT);
+	entry->msi_attrib.is_virtual    = 0;
 	entry->msi_attrib.entry_nr	= 0;
 	entry->msi_attrib.maskbit	= !!(control & PCI_MSI_FLAGS_MASKBIT);
 	entry->msi_attrib.default_irq	= dev->irq;	/* Save IOAPIC IRQ */
@@ -674,6 +693,7 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base,
 	struct irq_affinity_desc *curmsk, *masks = NULL;
 	struct msi_desc *entry;
 	int ret, i;
+	int vec_count = pci_msix_vec_count(dev);
 
 	if (affd)
 		masks = irq_create_affinity_masks(nvec, affd);
@@ -696,6 +716,10 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base,
 			entry->msi_attrib.entry_nr = entries[i].entry;
 		else
 			entry->msi_attrib.entry_nr = i;
+
+		entry->msi_attrib.is_virtual =
+			entry->msi_attrib.entry_nr >= vec_count;
+
 		entry->msi_attrib.default_irq	= dev->irq;
 		entry->mask_base		= base;
 
@@ -714,12 +738,19 @@ static void msix_program_entries(struct pci_dev *dev,
 {
 	struct msi_desc *entry;
 	int i = 0;
+	void __iomem *desc_addr;
 
 	for_each_pci_msi_entry(entry, dev) {
 		if (entries)
 			entries[i++].vector = entry->irq;
-		entry->masked = readl(pci_msix_desc_addr(entry) +
-				PCI_MSIX_ENTRY_VECTOR_CTRL);
+
+		desc_addr = pci_msix_desc_addr(entry);
+		if (desc_addr)
+			entry->masked = readl(desc_addr +
+					      PCI_MSIX_ENTRY_VECTOR_CTRL);
+		else
+			entry->masked = 0;
+
 		msix_mask_irq(entry, 1);
 	}
 }
@@ -932,7 +963,8 @@ int pci_msix_vec_count(struct pci_dev *dev)
 EXPORT_SYMBOL(pci_msix_vec_count);
 
 static int __pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries,
-			     int nvec, const struct irq_affinity *affd)
+			     int nvec, const struct irq_affinity *affd,
+			     int flags)
 {
 	int nr_entries;
 	int i, j;
@@ -943,7 +975,7 @@ static int __pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries,
 	nr_entries = pci_msix_vec_count(dev);
 	if (nr_entries < 0)
 		return nr_entries;
-	if (nvec > nr_entries)
+	if (nvec > nr_entries && !(flags & PCI_IRQ_VIRTUAL))
 		return nr_entries;
 
 	if (entries) {
@@ -1086,7 +1118,8 @@ EXPORT_SYMBOL(pci_enable_msi);
 
 static int __pci_enable_msix_range(struct pci_dev *dev,
 				   struct msix_entry *entries, int minvec,
-				   int maxvec, const struct irq_affinity *affd)
+				   int maxvec, const struct irq_affinity *affd,
+				   int flags)
 {
 	int rc, nvec = maxvec;
 
@@ -1110,7 +1143,7 @@ static int __pci_enable_msix_range(struct pci_dev *dev,
 				return -ENOSPC;
 		}
 
-		rc = __pci_enable_msix(dev, entries, nvec, affd);
+		rc = __pci_enable_msix(dev, entries, nvec, affd, flags);
 		if (rc == 0)
 			return nvec;
 
@@ -1141,7 +1174,7 @@ static int __pci_enable_msix_range(struct pci_dev *dev,
 int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries,
 		int minvec, int maxvec)
 {
-	return __pci_enable_msix_range(dev, entries, minvec, maxvec, NULL);
+	return __pci_enable_msix_range(dev, entries, minvec, maxvec, NULL, 0);
 }
 EXPORT_SYMBOL(pci_enable_msix_range);
 
@@ -1181,7 +1214,7 @@ int pci_alloc_irq_vectors_affinity(struct pci_dev *dev, unsigned int min_vecs,
 
 	if (flags & PCI_IRQ_MSIX) {
 		msix_vecs = __pci_enable_msix_range(dev, NULL, min_vecs,
-						    max_vecs, affd);
+						    max_vecs, affd, flags);
 		if (msix_vecs > 0)
 			return msix_vecs;
 	}
diff --git a/include/linux/msi.h b/include/linux/msi.h
index 784fb52b9900..6458ab049852 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -88,6 +88,7 @@ struct msi_desc {
 				__u8	multi_cap	: 3;
 				__u8	maskbit		: 1;
 				__u8	is_64		: 1;
+				__u8    is_virtual      : 1;
 				__u16	entry_nr;
 				unsigned default_irq;
 			} msi_attrib;
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 65f1d8c2f082..ce0815c2c498 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1352,6 +1352,15 @@ int pci_set_vga_state(struct pci_dev *pdev, bool decode,
 #define PCI_IRQ_MSI		(1 << 1) /* Allow MSI interrupts */
 #define PCI_IRQ_MSIX		(1 << 2) /* Allow MSI-X interrupts */
 #define PCI_IRQ_AFFINITY	(1 << 3) /* Auto-assign affinity */
+
+/*
+ * Virtual interrupts allow for more interrupts to be allocated
+ * than the device has interrupts for. These are not programmed
+ * into the devices MSI-X table and must be handled by some
+ * other driver means.
+ */
+#define PCI_IRQ_VIRTUAL		(1 << 4)
+
 #define PCI_IRQ_ALL_TYPES \
 	(PCI_IRQ_LEGACY | PCI_IRQ_MSI | PCI_IRQ_MSIX)
 
-- 
2.19.0