@@ -8216,7 +8216,7 @@ S: Maintained
F: Documentation/devicetree/bindings/pci/host-generic-pci.txt
F: drivers/pci/host/pci-host-generic.c
-PCI DRIVER FOR VMD
+PCI DRIVER FOR INTEL VOLUME MANAGEMENT DEVICE (VMD)
M: Keith Busch <keith.busch@intel.com>
L: linux-pci@vger.kernel.org
S: Supported
@@ -2670,13 +2670,13 @@ config VMD
tristate "Volume Management Device Driver"
default N
---help---
- Adds support for the Intel Volume Manage Device (VMD). VMD is a
+ 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
- additional bus resources than are otherwise possible with a
+ more bus resources than are otherwise possible with a
single domain. If you know your system provides one of these and
- have devices attached to it, say Y; if you are not sure, say N.
+ has devices attached to it, say Y; if you are not sure, say N.
source "net/Kconfig"
@@ -16,8 +16,8 @@ struct dma_domain {
struct dma_map_ops *dma_ops;
int domain_nr;
};
-extern void add_dma_domain(struct dma_domain *domain);
-extern void del_dma_domain(struct dma_domain *domain);
+void add_dma_domain(struct dma_domain *domain);
+void del_dma_domain(struct dma_domain *domain);
#endif
struct pdev_archdata {
@@ -642,8 +642,8 @@ unsigned int pcibios_assign_all_busses(void)
}
#if defined(CONFIG_X86_DEV_DMA_OPS) && defined(CONFIG_PCI_DOMAINS)
-LIST_HEAD(dma_domain_list);
-DEFINE_SPINLOCK(dma_domain_list_lock);
+static LIST_HEAD(dma_domain_list);
+static DEFINE_SPINLOCK(dma_domain_list_lock);
void add_dma_domain(struct dma_domain *domain)
{
@@ -27,20 +27,24 @@
#include <asm/msi.h>
#include <asm/msidef.h>
+#define VMD_CFGBAR 0
+#define VMD_MEMBAR1 2
+#define VMD_MEMBAR2 4
+
/*
- * Lock for manipulating vmd irq lists.
+ * Lock for manipulating VMD IRQ lists.
*/
static DEFINE_RAW_SPINLOCK(list_lock);
/**
- * struct vmd_irq - private data to map driver irq to the VMD shared vector
+ * struct vmd_irq - private data to map driver IRQ to the VMD shared vector
* @node: list item for parent traversal.
- * @rcu: rcu callback item for freeing.
+ * @rcu: RCU callback item for freeing.
* @irq: back pointer to parent.
- * @virq: the virtual irq value provided to the requesting driver.
+ * @virq: the virtual IRQ value provided to the requesting driver.
*
- * Every MSI/MSI-x irq requested for a device in a VMD domain will be mapped to
- * a VMD irq using this structure.
+ * Every MSI/MSI-X IRQ requested for a device in a VMD domain will be mapped to
+ * a VMD IRQ using this structure.
*/
struct vmd_irq {
struct list_head node;
@@ -50,11 +54,11 @@ struct vmd_irq {
};
/**
- * struct vmd_irq_list - list of driver requested irq's mapping to a vmd vector
+ * 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 device.
- * @index: index into the VMD MSI-x table; used for message routing.
- * @count: number of child irqs assigned to this vector; used to track
+ * @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 {
@@ -92,11 +96,11 @@ static inline struct vmd_dev *vmd_from_bus(struct pci_bus *bus)
}
/*
- * Drivers managing a device in a VMD domain allocate their own irqs as before,
+ * 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
- * destination id for the VMD MSI-x table. The VMD device muxes interrupts in
- * its domain into one of its own, and the VMD driver de-muxes these for the
- * handlers sharing that VMD irq. The vmd irq_domain provides the operations
+ * destination ID for the VMD MSI-X table. The VMD muxes interrupts in its
+ * domain into one of its own, and the VMD driver de-muxes these for the
+ * handlers sharing that VMD IRQ. The vmd irq_domain provides the operations
* and irq_chip to set this up.
*/
static void vmd_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
@@ -110,7 +114,7 @@ static void vmd_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
}
/*
- * We rely on MSI_FLAG_USE_DEF_CHIP_OPS to set the irq mask/unmask ops.
+ * We rely on MSI_FLAG_USE_DEF_CHIP_OPS to set the IRQ mask/unmask ops.
*/
static void vmd_irq_enable(struct irq_data *data)
{
@@ -139,7 +143,7 @@ static void vmd_irq_disable(struct irq_data *data)
* other devices sharing the same vector.
*/
static int vmd_irq_set_affinity(struct irq_data *data,
- const struct cpumask *dest, bool force)
+ const struct cpumask *dest, bool force)
{
return -EINVAL;
}
@@ -159,7 +163,7 @@ static irq_hw_number_t vmd_get_hwirq(struct msi_domain_info *info,
}
/*
- * XXX: We can be even smarter selecting the best irq once we solve the
+ * XXX: We can be even smarter selecting the best IRQ once we solve the
* affinity problem.
*/
static struct vmd_irq_list *vmd_next_irq(struct vmd_dev *vmd)
@@ -176,8 +180,7 @@ static struct vmd_irq_list *vmd_next_irq(struct vmd_dev *vmd)
return &vmd->irqs[best];
}
-static int vmd_msi_init(struct irq_domain *domain,
- struct msi_domain_info *info,
+static int vmd_msi_init(struct irq_domain *domain, struct msi_domain_info *info,
unsigned int virq, irq_hw_number_t hwirq,
msi_alloc_info_t *arg)
{
@@ -191,14 +194,13 @@ static int vmd_msi_init(struct irq_domain *domain,
vmdirq->irq = vmd_next_irq(vmd);
vmdirq->virq = virq;
- irq_domain_set_info(domain, virq, vmdirq->irq->vmd_vector,
- info->chip, vmdirq, handle_simple_irq, vmd, NULL);
+ irq_domain_set_info(domain, virq, vmdirq->irq->vmd_vector, info->chip,
+ vmdirq, handle_simple_irq, vmd, NULL);
return 0;
}
static void vmd_msi_free(struct irq_domain *domain,
- struct msi_domain_info *info,
- unsigned int virq)
+ struct msi_domain_info *info, unsigned int virq)
{
struct vmd_irq *vmdirq = irq_get_chip_data(virq);
@@ -210,15 +212,15 @@ static void vmd_msi_free(struct irq_domain *domain,
kfree_rcu(vmdirq, rcu);
}
-static int vmd_msi_prepare(struct irq_domain *domain,
- struct device *dev, int nvec,
- msi_alloc_info_t *arg)
+static int vmd_msi_prepare(struct irq_domain *domain, struct device *dev,
+ int nvec, msi_alloc_info_t *arg)
{
struct pci_dev *pdev = to_pci_dev(dev);
struct vmd_dev *vmd = vmd_from_bus(pdev->bus);
if (nvec > vmd->msix_count)
return vmd->msix_count;
+
memset(arg, 0, sizeof(*arg));
return 0;
}
@@ -245,8 +247,8 @@ static struct msi_domain_info vmd_msi_domain_info = {
#ifdef CONFIG_X86_DEV_DMA_OPS
/*
- * VMD replaces the requester id with its own. DMA mappings for devices in a
- * VMD domain need to be mapped for the VMD device, not the device requiring
+ * VMD replaces the requester ID with its own. DMA mappings for devices in a
+ * VMD domain need to be mapped for the VMD, not the device requiring
* the mapping.
*/
static struct device *to_vmd_dev(struct device *dev)
@@ -263,76 +265,73 @@ static struct dma_map_ops *vmd_dma_ops(struct device *dev)
}
static void *vmd_alloc(struct device *dev, size_t size, dma_addr_t *addr,
- gfp_t flag, struct dma_attrs *attrs)
+ gfp_t flag, struct dma_attrs *attrs)
{
return vmd_dma_ops(dev)->alloc(to_vmd_dev(dev), size, addr, flag,
- attrs);
+ attrs);
}
static void vmd_free(struct device *dev, size_t size, void *vaddr,
- dma_addr_t addr, struct dma_attrs *attrs)
+ dma_addr_t addr, struct dma_attrs *attrs)
{
return vmd_dma_ops(dev)->free(to_vmd_dev(dev), size, vaddr, addr,
- attrs);
+ attrs);
}
static int vmd_mmap(struct device *dev, struct vm_area_struct *vma,
- void *cpu_addr, dma_addr_t addr,
- size_t size, struct dma_attrs *attrs)
+ void *cpu_addr, dma_addr_t addr, size_t size,
+ struct dma_attrs *attrs)
{
return vmd_dma_ops(dev)->mmap(to_vmd_dev(dev), vma, cpu_addr, addr,
- size, attrs);
+ size, attrs);
}
static int vmd_get_sgtable(struct device *dev, struct sg_table *sgt,
- void *cpu_addr, dma_addr_t addr,
- size_t size, struct dma_attrs *attrs)
+ void *cpu_addr, dma_addr_t addr, size_t size,
+ struct dma_attrs *attrs)
{
return vmd_dma_ops(dev)->get_sgtable(to_vmd_dev(dev), sgt, cpu_addr,
- addr, size, attrs);
+ addr, size, attrs);
}
static dma_addr_t vmd_map_page(struct device *dev, struct page *page,
- unsigned long offset, size_t size,
- enum dma_data_direction dir,
- struct dma_attrs *attrs)
+ unsigned long offset, size_t size,
+ enum dma_data_direction dir,
+ struct dma_attrs *attrs)
{
return vmd_dma_ops(dev)->map_page(to_vmd_dev(dev), page, offset, size,
- dir, attrs);
+ dir, attrs);
}
static void vmd_unmap_page(struct device *dev, dma_addr_t addr, size_t size,
- enum dma_data_direction dir,
- struct dma_attrs *attrs)
+ enum dma_data_direction dir, struct dma_attrs *attrs)
{
vmd_dma_ops(dev)->unmap_page(to_vmd_dev(dev), addr, size, dir, attrs);
}
static int vmd_map_sg(struct device *dev, struct scatterlist *sg, int nents,
- enum dma_data_direction dir,
- struct dma_attrs *attrs)
+ enum dma_data_direction dir, struct dma_attrs *attrs)
{
return vmd_dma_ops(dev)->map_sg(to_vmd_dev(dev), sg, nents, dir, attrs);
}
static void vmd_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
- enum dma_data_direction dir,
- struct dma_attrs *attrs)
+ enum dma_data_direction dir, struct dma_attrs *attrs)
{
vmd_dma_ops(dev)->unmap_sg(to_vmd_dev(dev), sg, nents, dir, attrs);
}
static void vmd_sync_single_for_cpu(struct device *dev, dma_addr_t addr,
- size_t size, enum dma_data_direction dir)
+ size_t size, enum dma_data_direction dir)
{
vmd_dma_ops(dev)->sync_single_for_cpu(to_vmd_dev(dev), addr, size, dir);
}
static void vmd_sync_single_for_device(struct device *dev, dma_addr_t addr,
- size_t size, enum dma_data_direction dir)
+ size_t size, enum dma_data_direction dir)
{
vmd_dma_ops(dev)->sync_single_for_device(to_vmd_dev(dev), addr, size,
- dir);
+ dir);
}
static void vmd_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
@@ -342,7 +341,7 @@ static void vmd_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
}
static void vmd_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
- int nents, enum dma_data_direction dir)
+ int nents, enum dma_data_direction dir)
{
vmd_dma_ops(dev)->sync_sg_for_device(to_vmd_dev(dev), sg, nents, dir);
}
@@ -414,20 +413,32 @@ static void vmd_teardown_dma_ops(struct vmd_dev *vmd) {}
static void vmd_setup_dma_ops(struct vmd_dev *vmd) {}
#endif
+static char __iomem *vmd_cfg_addr(struct vmd_dev *vmd, struct pci_bus *bus,
+ unsigned int devfn, int reg, int len)
+{
+ char __iomem *addr = vmd->cfgbar +
+ (bus->number << 20) + (devfn << 12) + reg;
+
+ if ((addr - vmd->cfgbar) + len >=
+ resource_size(&vmd->dev->resource[VMD_CFGBAR]))
+ return NULL;
+
+ return addr;
+}
+
/*
* CPU may deadlock if config space is not serialized on some versions of this
* hardware, so all config space access is done under a spinlock.
*/
static int vmd_pci_read(struct pci_bus *bus, unsigned int devfn, int reg,
- int len, u32 *value)
+ int len, u32 *value)
{
- int ret = 0;
- unsigned long flags;
struct vmd_dev *vmd = vmd_from_bus(bus);
- char __iomem *addr = vmd->cfgbar + (bus->number << 20) +
- (devfn << 12) + reg;
+ char __iomem *addr = vmd_cfg_addr(vmd, bus, devfn, reg, len);
+ unsigned long flags;
+ int ret = 0;
- if ((addr - vmd->cfgbar) + len >= resource_size(&vmd->dev->resource[0]))
+ if (!addr)
return -EFAULT;
spin_lock_irqsave(&vmd->cfg_lock, flags);
@@ -455,15 +466,14 @@ static int vmd_pci_read(struct pci_bus *bus, unsigned int devfn, int reg,
* the config space was written, as expected.
*/
static int vmd_pci_write(struct pci_bus *bus, unsigned int devfn, int reg,
- int len, u32 value)
+ int len, u32 value)
{
- int ret = 0;
- unsigned long flags;
struct vmd_dev *vmd = vmd_from_bus(bus);
- char __iomem *addr = vmd->cfgbar + (bus->number << 20) +
- (devfn << 12) + reg;
+ char __iomem *addr = vmd_cfg_addr(vmd, bus, devfn, reg, len);
+ unsigned long flags;
+ int ret = 0;
- if ((addr - vmd->cfgbar) + len >= resource_size(&vmd->dev->resource[0]))
+ if (!addr)
return -EFAULT;
spin_lock_irqsave(&vmd->cfg_lock, flags);
@@ -494,7 +504,7 @@ static struct pci_ops vmd_ops = {
};
/*
- * VMD domains start at 10000h to not clash with domains defining ACPI _SEG.
+ * VMD domains start at 0x1000 to not clash with ACPI _SEG domains.
*/
static int vmd_find_free_domain(void)
{
@@ -510,37 +520,50 @@ static int vmd_enable_domain(struct vmd_dev *vmd)
{
struct pci_sysdata *sd = &vmd->sysdata;
struct resource *res;
+ u32 upper_bits;
+ unsigned long flags;
LIST_HEAD(resources);
- res = &vmd->resources[0];
- res->name = "VMD CFGBAR";
- res->start = 0;
- res->end = (resource_size(&vmd->dev->resource[0]) >> 20) - 1;
- res->flags = IORESOURCE_BUS | IORESOURCE_PCI_FIXED;
-
- res = &vmd->resources[1];
- res->name = "VMD MEMBAR1";
- res->start = vmd->dev->resource[2].start;
- res->end = vmd->dev->resource[2].end;
- res->flags = (vmd->dev->resource[2].flags & ~IORESOURCE_SIZEALIGN) &
- (!upper_32_bits(vmd->dev->resource[2].end) ?
- ~IORESOURCE_MEM_64 : ~0);
-
- res = &vmd->resources[2];
- res->name = "VMD MEMBAR2";
- res->start = vmd->dev->resource[4].start + 0x2000;
- res->end = vmd->dev->resource[4].end;
- res->flags = (vmd->dev->resource[4].flags & ~IORESOURCE_SIZEALIGN) &
- (!upper_32_bits(vmd->dev->resource[4].end) ?
- ~IORESOURCE_MEM_64 : ~0);
+ res = &vmd->dev->resource[VMD_CFGBAR];
+ vmd->resources[0] = (struct resource) {
+ .name = "VMD CFGBAR",
+ .start = res->start,
+ .end = (resource_size(res) >> 20) - 1,
+ .flags = IORESOURCE_BUS | IORESOURCE_PCI_FIXED,
+ };
+
+ res = &vmd->dev->resource[VMD_MEMBAR1];
+ upper_bits = upper_32_bits(res->end);
+ flags = res->flags & ~IORESOURCE_SIZEALIGN;
+ if (!upper_bits)
+ flags &= ~IORESOURCE_MEM_64;
+ vmd->resources[1] = (struct resource) {
+ .name = "VMD MEMBAR1",
+ .start = res->start,
+ .end = res->end,
+ .flags = flags,
+ };
+
+ res = &vmd->dev->resource[VMD_MEMBAR2];
+ upper_bits = upper_32_bits(res->end);
+ flags = res->flags & ~IORESOURCE_SIZEALIGN;
+ if (!upper_bits)
+ flags &= ~IORESOURCE_MEM_64;
+ vmd->resources[2] = (struct resource) {
+ .name = "VMD MEMBAR2",
+ .start = res->start + 0x2000,
+ .end = res->end,
+ .flags = flags,
+ };
sd->domain = vmd_find_free_domain();
if (sd->domain < 0)
return sd->domain;
+
sd->node = pcibus_to_node(vmd->dev->bus);
vmd->irq_domain = pci_msi_create_irq_domain(NULL, &vmd_msi_domain_info,
- NULL);
+ NULL);
if (!vmd->irq_domain)
return -ENODEV;
@@ -548,7 +571,7 @@ static int vmd_enable_domain(struct vmd_dev *vmd)
pci_add_resource(&resources, &vmd->resources[1]);
pci_add_resource(&resources, &vmd->resources[2]);
vmd->bus = pci_create_root_bus(&vmd->dev->dev, 0, &vmd_ops, sd,
- &resources);
+ &resources);
if (!vmd->bus) {
pci_free_resource_list(&resources);
irq_domain_remove(vmd->irq_domain);
@@ -560,8 +583,7 @@ static int vmd_enable_domain(struct vmd_dev *vmd)
pci_rescan_bus(vmd->bus);
WARN(sysfs_create_link(&vmd->dev->dev.kobj, &vmd->bus->dev.kobj,
- "domain"),
- "Can't create symlink to domain\n");
+ "domain"), "Can't create symlink to domain\n");
return 0;
}
@@ -583,7 +605,7 @@ static int vmd_probe(struct pci_dev *dev, const struct pci_device_id *id)
struct vmd_dev *vmd;
int i, err;
- if (resource_size(&dev->resource[0]) < (1 << 20))
+ if (resource_size(&dev->resource[VMD_CFGBAR]) < (1 << 20))
return -ENOMEM;
vmd = devm_kzalloc(&dev->dev, sizeof(*vmd), GFP_KERNEL);
@@ -595,7 +617,7 @@ static int vmd_probe(struct pci_dev *dev, const struct pci_device_id *id)
if (err < 0)
return err;
- vmd->cfgbar = pcim_iomap(dev, 0, 0);
+ vmd->cfgbar = pcim_iomap(dev, VMD_CFGBAR, 0);
if (!vmd->cfgbar)
return -ENOMEM;
@@ -609,19 +631,20 @@ static int vmd_probe(struct pci_dev *dev, const struct pci_device_id *id)
return -ENODEV;
vmd->irqs = devm_kcalloc(&dev->dev, vmd->msix_count, sizeof(*vmd->irqs),
- GFP_KERNEL);
+ GFP_KERNEL);
if (!vmd->irqs)
return -ENOMEM;
vmd->msix_entries = devm_kcalloc(&dev->dev, vmd->msix_count,
- sizeof(*vmd->msix_entries), GFP_KERNEL);
+ 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);
+ vmd->msix_count);
if (vmd->msix_count < 0)
return vmd->msix_count;
@@ -631,7 +654,7 @@ static int vmd_probe(struct pci_dev *dev, const struct pci_device_id *id)
vmd->irqs[i].index = i;
err = devm_request_irq(&dev->dev, vmd->irqs[i].vmd_vector,
- vmd_irq, 0, "vmd", &vmd->irqs[i]);
+ vmd_irq, 0, "vmd", &vmd->irqs[i]);
if (err)
return err;
}
@@ -641,8 +664,9 @@ static int vmd_probe(struct pci_dev *dev, const struct pci_device_id *id)
err = vmd_enable_domain(vmd);
if (err)
return err;
- dev_info(&vmd->dev->dev, "Bound to PCI domain:%x\n",
- vmd->sysdata.domain);
+
+ dev_info(&vmd->dev->dev, "Bound to PCI domain %04x\n",
+ vmd->sysdata.domain);
return 0;
}