Merge branch 'pci/host-vmd' into next

* pci/host-vmd:
  x86/PCI: VMD: Move VMD driver to drivers/pci/host
  x86/PCI: VMD: Synchronize with RCU freeing MSI IRQ descs
  x86/PCI: VMD: Eliminate index member from IRQ list
  x86/PCI: VMD: Eliminate vmd_vector member from list type
  x86/PCI: VMD: Convert to use pci_alloc_irq_vectors() API
  x86/PCI: VMD: Allocate IRQ lists with correct MSI-X count
  PCI: Use positive flags in pci_alloc_irq_vectors()
  PCI: Update "pci=resource_alignment" documentation

Conflicts:
	drivers/pci/host/Kconfig
	drivers/pci/host/Makefile

Author: bjorn-helgaas

Documentation/PCI/MSI-HOWTO.txt

@@ -94,14 +94,11 @@ has a requirements for a minimum number of vectors the driver can pass a
 min_vecs argument set to this limit, and the PCI core will return -ENOSPC
 if it can't meet the minimum number of vectors.
 
-The flags argument should normally be set to 0, but can be used to pass the
-PCI_IRQ_NOMSI and PCI_IRQ_NOMSIX flag in case a device claims to support
-MSI or MSI-X, but the support is broken, or to pass PCI_IRQ_NOLEGACY in
-case the device does not support legacy interrupt lines.
-
-By default this function will spread the interrupts around the available
-CPUs, but this feature can be disabled by passing the PCI_IRQ_NOAFFINITY
-flag.
+The flags argument is used to specify which type of interrupt can be used
+by the device and the driver (PCI_IRQ_LEGACY, PCI_IRQ_MSI, PCI_IRQ_MSIX).
+A convenient short-hand (PCI_IRQ_ALL_TYPES) is also available to ask for
+any possible kind of interrupt.  If the PCI_IRQ_AFFINITY flag is set,
+pci_alloc_irq_vectors() will spread the interrupts around the available CPUs.
 
 To get the Linux IRQ numbers passed to request_irq() and free_irq() and the
 vectors, use the following function:
@@ -131,7 +128,7 @@ larger than the number supported by the device it will automatically be
 capped to the supported limit, so there is no need to query the number of
 vectors supported beforehand:
 
-	nvec = pci_alloc_irq_vectors(pdev, 1, nvec, 0);
+	nvec = pci_alloc_irq_vectors(pdev, 1, nvec, PCI_IRQ_ALL_TYPES)
 	if (nvec < 0)
 		goto out_err;
 
@@ -140,23 +137,22 @@ interrupts it can request a particular number of interrupts by passing that
 number to pci_alloc_irq_vectors() function as both 'min_vecs' and
 'max_vecs' parameters:
 
-	ret = pci_alloc_irq_vectors(pdev, nvec, nvec, 0);
+	ret = pci_alloc_irq_vectors(pdev, nvec, nvec, PCI_IRQ_ALL_TYPES);
 	if (ret < 0)
 		goto out_err;
 
 The most notorious example of the request type described above is enabling
 the single MSI mode for a device.  It could be done by passing two 1s as
 'min_vecs' and 'max_vecs':
 
-	ret = pci_alloc_irq_vectors(pdev, 1, 1, 0);
+	ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES);
 	if (ret < 0)
 		goto out_err;
 
 Some devices might not support using legacy line interrupts, in which case
-the PCI_IRQ_NOLEGACY flag can be used to fail the request if the platform
-can't provide MSI or MSI-X interrupts:
+the driver can specify that only MSI or MSI-X is acceptable:
 
-	nvec = pci_alloc_irq_vectors(pdev, 1, nvec, PCI_IRQ_NOLEGACY);
+	nvec = pci_alloc_irq_vectors(pdev, 1, nvec, PCI_IRQ_MSI | PCI_IRQ_MSIX);
 	if (nvec < 0)
 		goto out_err;
 

Documentation/kernel-parameters.txt

@@ -3032,6 +3032,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 				PAGE_SIZE is used as alignment.
 				PCI-PCI bridge can be specified, if resource
 				windows need to be expanded.
+				To specify the alignment for several
+				instances of a device, the PCI vendor,
+				device, subvendor, and subdevice may be
+				specified, e.g., 4096@pci:8086:9c22:103c:198f
 		ecrc=		Enable/disable PCIe ECRC (transaction layer
 				end-to-end CRC checking).
 				bios: Use BIOS/firmware settings. This is the

arch/x86/Kconfig

@@ -2744,19 +2744,6 @@ config PMC_ATOM
 	def_bool y
         depends on PCI
 
-config VMD
-	depends on PCI_MSI
-	tristate "Volume Management Device Driver"
-	default N
-	---help---
-	  Adds support for the Intel Volume Management Device (VMD). VMD is a
-	  secondary PCI host bridge that allows PCI Express root ports,
-	  and devices attached to them, to be removed from the default
-	  PCI domain and placed within the VMD domain. This provides
-	  more bus resources than are otherwise possible with a
-	  single domain. If you know your system provides one of these and
-	  has devices attached to it, say Y; if you are not sure, say N.
-
 source "net/Kconfig"
 
 source "drivers/Kconfig"

arch/x86/pci/Makefile

@@ -23,8 +23,6 @@ obj-y				+= bus_numa.o
 obj-$(CONFIG_AMD_NB)		+= amd_bus.o
 obj-$(CONFIG_PCI_CNB20LE_QUIRK)	+= broadcom_bus.o
 
-obj-$(CONFIG_VMD) += vmd.o
-
 ifeq ($(CONFIG_PCI_DEBUG),y)
 EXTRA_CFLAGS += -DDEBUG
 endif

drivers/pci/host/Kconfig

@@ -285,4 +285,20 @@ config PCIE_ROCKCHIP
 	  There is 1 internal PCIe port available to support GEN2 with
 	  4 slots.
 
+config VMD
+	depends on PCI_MSI && X86_64
+	tristate "Intel Volume Management Device Driver"
+	default N
+	---help---
+	  Adds support for the Intel Volume Management Device (VMD). VMD is a
+	  secondary PCI host bridge that allows PCI Express root ports,
+	  and devices attached to them, to be removed from the default
+	  PCI domain and placed within the VMD domain. This provides
+	  more bus resources than are otherwise possible with a
+	  single domain. If you know your system provides one of these and
+	  has devices attached to it, say Y; if you are not sure, say N.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called vmd.
+
 endmenu

drivers/pci/host/Makefile

@@ -32,3 +32,4 @@ obj-$(CONFIG_PCI_HOST_THUNDER_PEM) += pci-thunder-pem.o
 obj-$(CONFIG_PCIE_ARMADA_8K) += pcie-armada8k.o
 obj-$(CONFIG_PCIE_ARTPEC6) += pcie-artpec6.o
 obj-$(CONFIG_PCIE_ROCKCHIP) += pcie-rockchip.o
+obj-$(CONFIG_VMD) += vmd.o

arch/x86/pci/vmd.c renamed to drivers/pci/host/vmd.c

@@ -56,16 +56,11 @@ struct vmd_irq {
 /**
  * struct vmd_irq_list - list of driver requested IRQs mapping to a VMD vector
  * @irq_list:	the list of irq's the VMD one demuxes to.
- * @vmd_vector:	the h/w IRQ assigned to the VMD.
- * @index:	index into the VMD MSI-X table; used for message routing.
  * @count:	number of child IRQs assigned to this vector; used to track
  *		sharing.
  */
 struct vmd_irq_list {
 	struct list_head	irq_list;
-	struct vmd_dev		*vmd;
-	unsigned int		vmd_vector;
-	unsigned int		index;
 	unsigned int		count;
 };
 
@@ -76,7 +71,6 @@ struct vmd_dev {
 	char __iomem		*cfgbar;
 
 	int msix_count;
-	struct msix_entry	*msix_entries;
 	struct vmd_irq_list	*irqs;
 
 	struct pci_sysdata	sysdata;
@@ -95,6 +89,12 @@ static inline struct vmd_dev *vmd_from_bus(struct pci_bus *bus)
 	return container_of(bus->sysdata, struct vmd_dev, sysdata);
 }
 
+static inline unsigned int index_from_irqs(struct vmd_dev *vmd,
+					   struct vmd_irq_list *irqs)
+{
+	return irqs - vmd->irqs;
+}
+
 /*
  * Drivers managing a device in a VMD domain allocate their own IRQs as before,
  * but the MSI entry for the hardware it's driving will be programmed with a
@@ -107,9 +107,11 @@ static void vmd_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 {
 	struct vmd_irq *vmdirq = data->chip_data;
 	struct vmd_irq_list *irq = vmdirq->irq;
+	struct vmd_dev *vmd = irq_data_get_irq_handler_data(data);
 
 	msg->address_hi = MSI_ADDR_BASE_HI;
-	msg->address_lo = MSI_ADDR_BASE_LO | MSI_ADDR_DEST_ID(irq->index);
+	msg->address_lo = MSI_ADDR_BASE_LO |
+			  MSI_ADDR_DEST_ID(index_from_irqs(vmd, irq));
 	msg->data = 0;
 }
 
@@ -194,16 +196,19 @@ static int vmd_msi_init(struct irq_domain *domain, struct msi_domain_info *info,
 	struct msi_desc *desc = arg->desc;
 	struct vmd_dev *vmd = vmd_from_bus(msi_desc_to_pci_dev(desc)->bus);
 	struct vmd_irq *vmdirq = kzalloc(sizeof(*vmdirq), GFP_KERNEL);
+	unsigned int index, vector;
 
 	if (!vmdirq)
 		return -ENOMEM;
 
 	INIT_LIST_HEAD(&vmdirq->node);
 	vmdirq->irq = vmd_next_irq(vmd, desc);
 	vmdirq->virq = virq;
+	index = index_from_irqs(vmd, vmdirq->irq);
+	vector = pci_irq_vector(vmd->dev, index);
 
-	irq_domain_set_info(domain, virq, vmdirq->irq->vmd_vector, info->chip,
-			    vmdirq, handle_untracked_irq, vmd, NULL);
+	irq_domain_set_info(domain, virq, vector, info->chip, vmdirq,
+			    handle_untracked_irq, vmd, NULL);
 	return 0;
 }
 
@@ -213,6 +218,8 @@ static void vmd_msi_free(struct irq_domain *domain,
 	struct vmd_irq *vmdirq = irq_get_chip_data(virq);
 	unsigned long flags;
 
+	synchronize_rcu();
+
 	/* XXX: Potential optimization to rebalance */
 	raw_spin_lock_irqsave(&list_lock, flags);
 	vmdirq->irq->count--;
@@ -672,30 +679,19 @@ static int vmd_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	if (vmd->msix_count < 0)
 		return -ENODEV;
 
+	vmd->msix_count = pci_alloc_irq_vectors(dev, 1, vmd->msix_count,
+					PCI_IRQ_MSIX | PCI_IRQ_AFFINITY);
+	if (vmd->msix_count < 0)
+		return vmd->msix_count;
+
 	vmd->irqs = devm_kcalloc(&dev->dev, vmd->msix_count, sizeof(*vmd->irqs),
 				 GFP_KERNEL);
 	if (!vmd->irqs)
 		return -ENOMEM;
 
-	vmd->msix_entries = devm_kcalloc(&dev->dev, vmd->msix_count,
-					 sizeof(*vmd->msix_entries),
-					 GFP_KERNEL);
-	if (!vmd->msix_entries)
-		return -ENOMEM;
-	for (i = 0; i < vmd->msix_count; i++)
-		vmd->msix_entries[i].entry = i;
-
-	vmd->msix_count = pci_enable_msix_range(vmd->dev, vmd->msix_entries, 1,
-						vmd->msix_count);
-	if (vmd->msix_count < 0)
-		return vmd->msix_count;
-
 	for (i = 0; i < vmd->msix_count; i++) {
 		INIT_LIST_HEAD(&vmd->irqs[i].irq_list);
-		vmd->irqs[i].vmd_vector = vmd->msix_entries[i].vector;
-		vmd->irqs[i].index = i;
-
-		err = devm_request_irq(&dev->dev, vmd->irqs[i].vmd_vector,
+		err = devm_request_irq(&dev->dev, pci_irq_vector(dev, i),
 				       vmd_irq, 0, "vmd", &vmd->irqs[i]);
 		if (err)
 			return err;

drivers/pci/msi.c

@@ -1069,7 +1069,7 @@ static int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec,
 		nvec = maxvec;
 
 	for (;;) {
-		if (!(flags & PCI_IRQ_NOAFFINITY)) {
+		if (flags & PCI_IRQ_AFFINITY) {
 			dev->irq_affinity = irq_create_affinity_mask(&nvec);
 			if (nvec < minvec)
 				return -ENOSPC;
@@ -1105,7 +1105,7 @@ static int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec,
  **/
 int pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec)
 {
-	return __pci_enable_msi_range(dev, minvec, maxvec, PCI_IRQ_NOAFFINITY);
+	return __pci_enable_msi_range(dev, minvec, maxvec, 0);
 }
 EXPORT_SYMBOL(pci_enable_msi_range);
 
@@ -1120,7 +1120,7 @@ static int __pci_enable_msix_range(struct pci_dev *dev,
 		return -ERANGE;
 
 	for (;;) {
-		if (!(flags & PCI_IRQ_NOAFFINITY)) {
+		if (flags & PCI_IRQ_AFFINITY) {
 			dev->irq_affinity = irq_create_affinity_mask(&nvec);
 			if (nvec < minvec)
 				return -ENOSPC;
@@ -1160,8 +1160,7 @@ 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,
-			PCI_IRQ_NOAFFINITY);
+	return __pci_enable_msix_range(dev, entries, minvec, maxvec, 0);
 }
 EXPORT_SYMBOL(pci_enable_msix_range);
 
@@ -1187,21 +1186,21 @@ int pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs,
 {
 	int vecs = -ENOSPC;
 
-	if (!(flags & PCI_IRQ_NOMSIX)) {
+	if (flags & PCI_IRQ_MSIX) {
 		vecs = __pci_enable_msix_range(dev, NULL, min_vecs, max_vecs,
 				flags);
 		if (vecs > 0)
 			return vecs;
 	}
 
-	if (!(flags & PCI_IRQ_NOMSI)) {
+	if (flags & PCI_IRQ_MSI) {
 		vecs = __pci_enable_msi_range(dev, min_vecs, max_vecs, flags);
 		if (vecs > 0)
 			return vecs;
 	}
 
 	/* use legacy irq if allowed */
-	if (!(flags & PCI_IRQ_NOLEGACY) && min_vecs == 1)
+	if ((flags & PCI_IRQ_LEGACY) && min_vecs == 1)
 		return 1;
 	return vecs;
 }

include/linux/pci.h

@@ -1264,10 +1264,12 @@ resource_size_t pcibios_iov_resource_alignment(struct pci_dev *dev, int resno);
 int pci_set_vga_state(struct pci_dev *pdev, bool decode,
 		      unsigned int command_bits, u32 flags);
 
-#define PCI_IRQ_NOLEGACY	(1 << 0) /* don't use legacy interrupts */
-#define PCI_IRQ_NOMSI		(1 << 1) /* don't use MSI interrupts */
-#define PCI_IRQ_NOMSIX		(1 << 2) /* don't use MSI-X interrupts */
-#define PCI_IRQ_NOAFFINITY	(1 << 3) /* don't auto-assign affinity */
+#define PCI_IRQ_LEGACY		(1 << 0) /* allow legacy interrupts */
+#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 */
+#define PCI_IRQ_ALL_TYPES \
+	(PCI_IRQ_LEGACY | PCI_IRQ_MSI | PCI_IRQ_MSIX)
 
 /* kmem_cache style wrapper around pci_alloc_consistent() */