diff options
Diffstat (limited to 'arch/x86/pci')
-rw-r--r-- | arch/x86/pci/Makefile | 2 | ||||
-rw-r--r-- | arch/x86/pci/acpi.c | 296 | ||||
-rw-r--r-- | arch/x86/pci/bus_numa.c | 13 | ||||
-rw-r--r-- | arch/x86/pci/common.c | 59 | ||||
-rw-r--r-- | arch/x86/pci/fixup.c | 28 | ||||
-rw-r--r-- | arch/x86/pci/intel_mid_pci.c | 9 | ||||
-rw-r--r-- | arch/x86/pci/irq.c | 23 | ||||
-rw-r--r-- | arch/x86/pci/legacy.c | 2 | ||||
-rw-r--r-- | arch/x86/pci/pcbios.c | 108 | ||||
-rw-r--r-- | arch/x86/pci/vmd.c | 756 | ||||
-rw-r--r-- | arch/x86/pci/xen.c | 5 |
11 files changed, 985 insertions, 316 deletions
diff --git a/arch/x86/pci/Makefile b/arch/x86/pci/Makefile index 5c6fc3577a49..97062a635b77 100644 --- a/arch/x86/pci/Makefile +++ b/arch/x86/pci/Makefile @@ -23,6 +23,8 @@ 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 diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index ff9911707160..3cd69832d7f4 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -4,16 +4,15 @@ #include <linux/irq.h> #include <linux/dmi.h> #include <linux/slab.h> +#include <linux/pci-acpi.h> #include <asm/numa.h> #include <asm/pci_x86.h> struct pci_root_info { - struct acpi_device *bridge; - char name[16]; + struct acpi_pci_root_info common; struct pci_sysdata sd; #ifdef CONFIG_PCI_MMCONFIG bool mcfg_added; - u16 segment; u8 start_bus; u8 end_bus; #endif @@ -178,15 +177,18 @@ static int check_segment(u16 seg, struct device *dev, char *estr) return 0; } -static int setup_mcfg_map(struct pci_root_info *info, u16 seg, u8 start, - u8 end, phys_addr_t addr) +static int setup_mcfg_map(struct acpi_pci_root_info *ci) { - int result; - struct device *dev = &info->bridge->dev; + int result, seg; + struct pci_root_info *info; + struct acpi_pci_root *root = ci->root; + struct device *dev = &ci->bridge->dev; - info->start_bus = start; - info->end_bus = end; + info = container_of(ci, struct pci_root_info, common); + info->start_bus = (u8)root->secondary.start; + info->end_bus = (u8)root->secondary.end; info->mcfg_added = false; + seg = info->sd.domain; /* return success if MMCFG is not in use */ if (raw_pci_ext_ops && raw_pci_ext_ops != &pci_mmcfg) @@ -195,7 +197,8 @@ static int setup_mcfg_map(struct pci_root_info *info, u16 seg, u8 start, if (!(pci_probe & PCI_PROBE_MMCONF)) return check_segment(seg, dev, "MMCONFIG is disabled,"); - result = pci_mmconfig_insert(dev, seg, start, end, addr); + result = pci_mmconfig_insert(dev, seg, info->start_bus, info->end_bus, + root->mcfg_addr); if (result == 0) { /* enable MMCFG if it hasn't been enabled yet */ if (raw_pci_ext_ops == NULL) @@ -208,134 +211,55 @@ static int setup_mcfg_map(struct pci_root_info *info, u16 seg, u8 start, return 0; } -static void teardown_mcfg_map(struct pci_root_info *info) +static void teardown_mcfg_map(struct acpi_pci_root_info *ci) { + struct pci_root_info *info; + + info = container_of(ci, struct pci_root_info, common); if (info->mcfg_added) { - pci_mmconfig_delete(info->segment, info->start_bus, - info->end_bus); + pci_mmconfig_delete(info->sd.domain, + info->start_bus, info->end_bus); info->mcfg_added = false; } } #else -static int setup_mcfg_map(struct pci_root_info *info, - u16 seg, u8 start, u8 end, - phys_addr_t addr) +static int setup_mcfg_map(struct acpi_pci_root_info *ci) { return 0; } -static void teardown_mcfg_map(struct pci_root_info *info) + +static void teardown_mcfg_map(struct acpi_pci_root_info *ci) { } #endif -static void validate_resources(struct device *dev, struct list_head *crs_res, - unsigned long type) +static int pci_acpi_root_get_node(struct acpi_pci_root *root) { - LIST_HEAD(list); - struct resource *res1, *res2, *root = NULL; - struct resource_entry *tmp, *entry, *entry2; - - BUG_ON((type & (IORESOURCE_MEM | IORESOURCE_IO)) == 0); - root = (type & IORESOURCE_MEM) ? &iomem_resource : &ioport_resource; - - list_splice_init(crs_res, &list); - resource_list_for_each_entry_safe(entry, tmp, &list) { - bool free = false; - resource_size_t end; - - res1 = entry->res; - if (!(res1->flags & type)) - goto next; - - /* Exclude non-addressable range or non-addressable portion */ - end = min(res1->end, root->end); - if (end <= res1->start) { - dev_info(dev, "host bridge window %pR (ignored, not CPU addressable)\n", - res1); - free = true; - goto next; - } else if (res1->end != end) { - dev_info(dev, "host bridge window %pR ([%#llx-%#llx] ignored, not CPU addressable)\n", - res1, (unsigned long long)end + 1, - (unsigned long long)res1->end); - res1->end = end; - } - - resource_list_for_each_entry(entry2, crs_res) { - res2 = entry2->res; - if (!(res2->flags & type)) - continue; - - /* - * I don't like throwing away windows because then - * our resources no longer match the ACPI _CRS, but - * the kernel resource tree doesn't allow overlaps. - */ - if (resource_overlaps(res1, res2)) { - res2->start = min(res1->start, res2->start); - res2->end = max(res1->end, res2->end); - dev_info(dev, "host bridge window expanded to %pR; %pR ignored\n", - res2, res1); - free = true; - goto next; - } - } + int busnum = root->secondary.start; + struct acpi_device *device = root->device; + int node = acpi_get_node(device->handle); -next: - resource_list_del(entry); - if (free) - resource_list_free_entry(entry); - else - resource_list_add_tail(entry, crs_res); + if (node == NUMA_NO_NODE) { + node = x86_pci_root_bus_node(busnum); + if (node != 0 && node != NUMA_NO_NODE) + dev_info(&device->dev, FW_BUG "no _PXM; falling back to node %d from hardware (may be inconsistent with ACPI node numbers)\n", + node); } + if (node != NUMA_NO_NODE && !node_online(node)) + node = NUMA_NO_NODE; + + return node; } -static void add_resources(struct pci_root_info *info, - struct list_head *resources, - struct list_head *crs_res) +static int pci_acpi_root_init_info(struct acpi_pci_root_info *ci) { - struct resource_entry *entry, *tmp; - struct resource *res, *conflict, *root = NULL; - - validate_resources(&info->bridge->dev, crs_res, IORESOURCE_MEM); - validate_resources(&info->bridge->dev, crs_res, IORESOURCE_IO); - - resource_list_for_each_entry_safe(entry, tmp, crs_res) { - res = entry->res; - if (res->flags & IORESOURCE_MEM) - root = &iomem_resource; - else if (res->flags & IORESOURCE_IO) - root = &ioport_resource; - else - BUG_ON(res); - - conflict = insert_resource_conflict(root, res); - if (conflict) { - dev_info(&info->bridge->dev, - "ignoring host bridge window %pR (conflicts with %s %pR)\n", - res, conflict->name, conflict); - resource_list_destroy_entry(entry); - } - } - - list_splice_tail(crs_res, resources); + return setup_mcfg_map(ci); } -static void release_pci_root_info(struct pci_host_bridge *bridge) +static void pci_acpi_root_release_info(struct acpi_pci_root_info *ci) { - struct resource *res; - struct resource_entry *entry; - struct pci_root_info *info = bridge->release_data; - - resource_list_for_each_entry(entry, &bridge->windows) { - res = entry->res; - if (res->parent && - (res->flags & (IORESOURCE_MEM | IORESOURCE_IO))) - release_resource(res); - } - - teardown_mcfg_map(info); - kfree(info); + teardown_mcfg_map(ci); + kfree(container_of(ci, struct pci_root_info, common)); } /* @@ -358,50 +282,47 @@ static bool resource_is_pcicfg_ioport(struct resource *res) res->start == 0xCF8 && res->end == 0xCFF; } -static void probe_pci_root_info(struct pci_root_info *info, - struct acpi_device *device, - int busnum, int domain, - struct list_head *list) +static int pci_acpi_root_prepare_resources(struct acpi_pci_root_info *ci) { - int ret; + struct acpi_device *device = ci->bridge; + int busnum = ci->root->secondary.start; struct resource_entry *entry, *tmp; + int status; - sprintf(info->name, "PCI Bus %04x:%02x", domain, busnum); - info->bridge = device; - ret = acpi_dev_get_resources(device, list, - acpi_dev_filter_resource_type_cb, - (void *)(IORESOURCE_IO | IORESOURCE_MEM)); - if (ret < 0) - dev_warn(&device->dev, - "failed to parse _CRS method, error code %d\n", ret); - else if (ret == 0) - dev_dbg(&device->dev, - "no IO and memory resources present in _CRS\n"); - else - resource_list_for_each_entry_safe(entry, tmp, list) { - if ((entry->res->flags & IORESOURCE_DISABLED) || - resource_is_pcicfg_ioport(entry->res)) + status = acpi_pci_probe_root_resources(ci); + if (pci_use_crs) { + resource_list_for_each_entry_safe(entry, tmp, &ci->resources) + if (resource_is_pcicfg_ioport(entry->res)) resource_list_destroy_entry(entry); - else - entry->res->name = info->name; - } + return status; + } + + resource_list_for_each_entry_safe(entry, tmp, &ci->resources) { + dev_printk(KERN_DEBUG, &device->dev, + "host bridge window %pR (ignored)\n", entry->res); + resource_list_destroy_entry(entry); + } + x86_pci_root_bus_resources(busnum, &ci->resources); + + return 0; } +static struct acpi_pci_root_ops acpi_pci_root_ops = { + .pci_ops = &pci_root_ops, + .init_info = pci_acpi_root_init_info, + .release_info = pci_acpi_root_release_info, + .prepare_resources = pci_acpi_root_prepare_resources, +}; + struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) { - struct acpi_device *device = root->device; - struct pci_root_info *info; int domain = root->segment; int busnum = root->secondary.start; - struct resource_entry *res_entry; - LIST_HEAD(crs_res); - LIST_HEAD(resources); + int node = pci_acpi_root_get_node(root); struct pci_bus *bus; - struct pci_sysdata *sd; - int node; if (pci_ignore_seg) - domain = 0; + root->segment = domain = 0; if (domain && !pci_domains_supported) { printk(KERN_WARNING "pci_bus %04x:%02x: " @@ -410,71 +331,33 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) return NULL; } - node = acpi_get_node(device->handle); - if (node == NUMA_NO_NODE) { - node = x86_pci_root_bus_node(busnum); - if (node != 0 && node != NUMA_NO_NODE) - dev_info(&device->dev, FW_BUG "no _PXM; falling back to node %d from hardware (may be inconsistent with ACPI node numbers)\n", - node); - } - - if (node != NUMA_NO_NODE && !node_online(node)) - node = NUMA_NO_NODE; - - info = kzalloc_node(sizeof(*info), GFP_KERNEL, node); - if (!info) { - printk(KERN_WARNING "pci_bus %04x:%02x: " - "ignored (out of memory)\n", domain, busnum); - return NULL; - } - - sd = &info->sd; - sd->domain = domain; - sd->node = node; - sd->companion = device; - bus = pci_find_bus(domain, busnum); if (bus) { /* * If the desired bus has been scanned already, replace * its bus->sysdata. */ - memcpy(bus->sysdata, sd, sizeof(*sd)); - kfree(info); - } else { - /* insert busn res at first */ - pci_add_resource(&resources, &root->secondary); + struct pci_sysdata sd = { + .domain = domain, + .node = node, + .companion = root->device + }; - /* - * _CRS with no apertures is normal, so only fall back to - * defaults or native bridge info if we're ignoring _CRS. - */ - probe_pci_root_info(info, device, busnum, domain, &crs_res); - if (pci_use_crs) { - add_resources(info, &resources, &crs_res); - } else { - resource_list_for_each_entry(res_entry, &crs_res) - dev_printk(KERN_DEBUG, &device->dev, - "host bridge window %pR (ignored)\n", - res_entry->res); - resource_list_free(&crs_res); - x86_pci_root_bus_resources(busnum, &resources); - } - - if (!setup_mcfg_map(info, domain, (u8)root->secondary.start, - (u8)root->secondary.end, root->mcfg_addr)) - bus = pci_create_root_bus(NULL, busnum, &pci_root_ops, - sd, &resources); - - if (bus) { - pci_scan_child_bus(bus); - pci_set_host_bridge_release( - to_pci_host_bridge(bus->bridge), - release_pci_root_info, info); - } else { - resource_list_free(&resources); - teardown_mcfg_map(info); - kfree(info); + memcpy(bus->sysdata, &sd, sizeof(sd)); + } else { + struct pci_root_info *info; + + info = kzalloc_node(sizeof(*info), GFP_KERNEL, node); + if (!info) + dev_err(&root->device->dev, + "pci_bus %04x:%02x: ignored (out of memory)\n", + domain, busnum); + else { + info->sd.domain = domain; + info->sd.node = node; + info->sd.companion = root->device; + bus = acpi_pci_root_create(root, &acpi_pci_root_ops, + &info->common, &info->sd); } } @@ -487,9 +370,6 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) pcie_bus_configure_settings(child); } - if (bus && node != NUMA_NO_NODE) - dev_printk(KERN_DEBUG, &bus->dev, "on NUMA node %d\n", node); - return bus; } diff --git a/arch/x86/pci/bus_numa.c b/arch/x86/pci/bus_numa.c index 7bcf06a7cd12..6eb3c8af96e2 100644 --- a/arch/x86/pci/bus_numa.c +++ b/arch/x86/pci/bus_numa.c @@ -50,18 +50,9 @@ void x86_pci_root_bus_resources(int bus, struct list_head *resources) if (!found) pci_add_resource(resources, &info->busn); - list_for_each_entry(root_res, &info->resources, list) { - struct resource *res; - struct resource *root; + list_for_each_entry(root_res, &info->resources, list) + pci_add_resource(resources, &root_res->res); - res = &root_res->res; - pci_add_resource(resources, res); - if (res->flags & IORESOURCE_IO) - root = &ioport_resource; - else - root = &iomem_resource; - insert_resource(root, res); - } return; default_resources: diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index dc78a4a9a466..381a43c40bf7 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -12,7 +12,6 @@ #include <linux/dmi.h> #include <linux/slab.h> -#include <asm-generic/pci-bridge.h> #include <asm/acpi.h> #include <asm/segment.h> #include <asm/io.h> @@ -641,6 +640,43 @@ unsigned int pcibios_assign_all_busses(void) return (pci_probe & PCI_ASSIGN_ALL_BUSSES) ? 1 : 0; } +#if defined(CONFIG_X86_DEV_DMA_OPS) && defined(CONFIG_PCI_DOMAINS) +static LIST_HEAD(dma_domain_list); +static DEFINE_SPINLOCK(dma_domain_list_lock); + +void add_dma_domain(struct dma_domain *domain) +{ + spin_lock(&dma_domain_list_lock); + list_add(&domain->node, &dma_domain_list); + spin_unlock(&dma_domain_list_lock); +} +EXPORT_SYMBOL_GPL(add_dma_domain); + +void del_dma_domain(struct dma_domain *domain) +{ + spin_lock(&dma_domain_list_lock); + list_del(&domain->node); + spin_unlock(&dma_domain_list_lock); +} +EXPORT_SYMBOL_GPL(del_dma_domain); + +static void set_dma_domain_ops(struct pci_dev *pdev) +{ + struct dma_domain *domain; + + spin_lock(&dma_domain_list_lock); + list_for_each_entry(domain, &dma_domain_list, node) { + if (pci_domain_nr(pdev->bus) == domain->domain_nr) { + pdev->dev.archdata.dma_ops = domain->dma_ops; + break; + } + } + spin_unlock(&dma_domain_list_lock); +} +#else +static void set_dma_domain_ops(struct pci_dev *pdev) {} +#endif + int pcibios_add_device(struct pci_dev *dev) { struct setup_data *data; @@ -670,23 +706,26 @@ int pcibios_add_device(struct pci_dev *dev) pa_data = data->next; iounmap(data); } + set_dma_domain_ops(dev); return 0; } -int pcibios_alloc_irq(struct pci_dev *dev) +int pcibios_enable_device(struct pci_dev *dev, int mask) { - return pcibios_enable_irq(dev); -} + int err; -void pcibios_free_irq(struct pci_dev *dev) -{ - if (pcibios_disable_irq) - pcibios_disable_irq(dev); + if ((err = pci_enable_resources(dev, mask)) < 0) + return err; + + if (!pci_dev_msi_enabled(dev)) + return pcibios_enable_irq(dev); + return 0; } -int pcibios_enable_device(struct pci_dev *dev, int mask) +void pcibios_disable_device (struct pci_dev *dev) { - return pci_enable_resources(dev, mask); + if (!pci_dev_msi_enabled(dev) && pcibios_disable_irq) + pcibios_disable_irq(dev); } int pci_ext_cfg_avail(void) diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index e58565556703..b7de1929714b 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -297,14 +297,14 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_MCH_PC1, pcie_r * * The standard boot ROM sequence for an x86 machine uses the BIOS * to select an initial video card for boot display. This boot video - * card will have it's BIOS copied to C0000 in system RAM. + * card will have its BIOS copied to 0xC0000 in system RAM. * IORESOURCE_ROM_SHADOW is used to associate the boot video * card with this copy. On laptops this copy has to be used since * the main ROM may be compressed or combined with another image. * See pci_map_rom() for use of this flag. Before marking the device * with IORESOURCE_ROM_SHADOW check if a vga_default_device is already set - * by either arch cde or vga-arbitration, if so only apply the fixup to this - * already determined primary video card. + * by either arch code or vga-arbitration; if so only apply the fixup to this + * already-determined primary video card. */ static void pci_fixup_video(struct pci_dev *pdev) @@ -312,6 +312,7 @@ static void pci_fixup_video(struct pci_dev *pdev) struct pci_dev *bridge; struct pci_bus *bus; u16 config; + struct resource *res; /* Is VGA routed to us? */ bus = pdev->bus; @@ -336,8 +337,18 @@ static void pci_fixup_video(struct pci_dev *pdev) if (!vga_default_device() || pdev == vga_default_device()) { pci_read_config_word(pdev, PCI_COMMAND, &config); if (config & (PCI_COMMAND_IO | PCI_COMMAND_MEMORY)) { - pdev->resource[PCI_ROM_RESOURCE].flags |= IORESOURCE_ROM_SHADOW; - dev_printk(KERN_DEBUG, &pdev->dev, "Video device with shadowed ROM\n"); + res = &pdev->resource[PCI_ROM_RESOURCE]; + + pci_disable_rom(pdev); + if (res->parent) + release_resource(res); + + res->start = 0xC0000; + res->end = res->start + 0x20000 - 1; + res->flags = IORESOURCE_MEM | IORESOURCE_ROM_SHADOW | + IORESOURCE_PCI_FIXED; + dev_info(&pdev->dev, "Video device with shadowed ROM at %pR\n", + res); } } } @@ -540,3 +551,10 @@ static void twinhead_reserve_killing_zone(struct pci_dev *dev) } } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x27B9, twinhead_reserve_killing_zone); + +static void pci_bdwep_bar(struct pci_dev *dev) +{ + dev->non_compliant_bars = 1; +} +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fa0, pci_bdwep_bar); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, pci_bdwep_bar); diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c index 0d24e7c10145..8b93e634af84 100644 --- a/arch/x86/pci/intel_mid_pci.c +++ b/arch/x86/pci/intel_mid_pci.c @@ -215,7 +215,7 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev) int polarity; int ret; - if (pci_has_managed_irq(dev)) + if (dev->irq_managed && dev->irq > 0) return 0; switch (intel_mid_identify_cpu()) { @@ -256,13 +256,10 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev) static void intel_mid_pci_irq_disable(struct pci_dev *dev) { - if (pci_has_managed_irq(dev)) { + if (!mp_should_keep_irq(&dev->dev) && dev->irq_managed && + dev->irq > 0) { mp_unmap_irq(dev->irq); dev->irq_managed = 0; - /* - * Don't reset dev->irq here, otherwise - * intel_mid_pci_irq_enable() will fail on next call. - */ } } diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index 32e70343e6fd..9bd115484745 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -1202,7 +1202,7 @@ static int pirq_enable_irq(struct pci_dev *dev) struct pci_dev *temp_dev; int irq; - if (pci_has_managed_irq(dev)) + if (dev->irq_managed && dev->irq > 0) return 0; irq = IO_APIC_get_PCI_irq_vector(dev->bus->number, @@ -1230,7 +1230,8 @@ static int pirq_enable_irq(struct pci_dev *dev) } dev = temp_dev; if (irq >= 0) { - pci_set_managed_irq(dev, irq); + dev->irq_managed = 1; + dev->irq = irq; dev_info(&dev->dev, "PCI->APIC IRQ transform: " "INT %c -> IRQ %d\n", 'A' + pin - 1, irq); return 0; @@ -1256,10 +1257,24 @@ static int pirq_enable_irq(struct pci_dev *dev) return 0; } +bool mp_should_keep_irq(struct device *dev) +{ + if (dev->power.is_prepared) + return true; +#ifdef CONFIG_PM + if (dev->power.runtime_status == RPM_SUSPENDING) + return true; +#endif + + return false; +} + static void pirq_disable_irq(struct pci_dev *dev) { - if (io_apic_assign_pci_irqs && pci_has_managed_irq(dev)) { + if (io_apic_assign_pci_irqs && !mp_should_keep_irq(&dev->dev) && + dev->irq_managed && dev->irq) { mp_unmap_irq(dev->irq); - pci_reset_managed_irq(dev); + dev->irq = 0; + dev->irq_managed = 0; } } diff --git a/arch/x86/pci/legacy.c b/arch/x86/pci/legacy.c index 5b662c0faf8c..ea6f3802c17b 100644 --- a/arch/x86/pci/legacy.c +++ b/arch/x86/pci/legacy.c @@ -54,7 +54,7 @@ void pcibios_scan_specific_bus(int busn) } EXPORT_SYMBOL_GPL(pcibios_scan_specific_bus); -int __init pci_subsys_init(void) +static int __init pci_subsys_init(void) { /* * The init function returns an non zero value when diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c index 9b83b9051ae7..9770e55e768f 100644 --- a/arch/x86/pci/pcbios.c +++ b/arch/x86/pci/pcbios.c @@ -180,6 +180,7 @@ static int pci_bios_read(unsigned int seg, unsigned int bus, unsigned long result = 0; unsigned long flags; unsigned long bx = (bus << 8) | devfn; + u16 number = 0, mask = 0; WARN_ON(seg); if (!value || (bus > 255) || (devfn > 255) || (reg > 255)) @@ -189,53 +190,35 @@ static int pci_bios_read(unsigned int seg, unsigned int bus, switch (len) { case 1: - __asm__("lcall *(%%esi); cld\n\t" - "jc 1f\n\t" - "xor %%ah, %%ah\n" - "1:" - : "=c" (*value), - "=a" (result) - : "1" (PCIBIOS_READ_CONFIG_BYTE), - "b" (bx), - "D" ((long)reg), - "S" (&pci_indirect)); - /* - * Zero-extend the result beyond 8 bits, do not trust the - * BIOS having done it: - */ - *value &= 0xff; + number = PCIBIOS_READ_CONFIG_BYTE; + mask = 0xff; break; case 2: - __asm__("lcall *(%%esi); cld\n\t" - "jc 1f\n\t" - "xor %%ah, %%ah\n" - "1:" - : "=c" (*value), - "=a" (result) - : "1" (PCIBIOS_READ_CONFIG_WORD), - "b" (bx), - "D" ((long)reg), - "S" (&pci_indirect)); - /* - * Zero-extend the result beyond 16 bits, do not trust the - * BIOS having done it: - */ - *value &= 0xffff; + number = PCIBIOS_READ_CONFIG_WORD; + mask = 0xffff; break; case 4: - __asm__("lcall *(%%esi); cld\n\t" - "jc 1f\n\t" - "xor %%ah, %%ah\n" - "1:" - : "=c" (*value), - "=a" (result) - : "1" (PCIBIOS_READ_CONFIG_DWORD), - "b" (bx), - "D" ((long)reg), - "S" (&pci_indirect)); + number = PCIBIOS_READ_CONFIG_DWORD; break; } + __asm__("lcall *(%%esi); cld\n\t" + "jc 1f\n\t" + "xor %%ah, %%ah\n" + "1:" + : "=c" (*value), + "=a" (result) + : "1" (number), + "b" (bx), + "D" ((long)reg), + "S" (&pci_indirect)); + /* + * Zero-extend the result beyond 8 or 16 bits, do not trust the + * BIOS having done it: + */ + if (mask) + *value &= mask; + raw_spin_unlock_irqrestore(&pci_config_lock, flags); return (int)((result & 0xff00) >> 8); @@ -247,6 +230,7 @@ static int pci_bios_write(unsigned int seg, unsigned int bus, unsigned long result = 0; unsigned long flags; unsigned long bx = (bus << 8) | devfn; + u16 number = 0; WARN_ON(seg); if ((bus > 255) || (devfn > 255) || (reg > 255)) @@ -256,43 +240,27 @@ static int pci_bios_write(unsigned int seg, unsigned int bus, switch (len) { case 1: - __asm__("lcall *(%%esi); cld\n\t" - "jc 1f\n\t" - "xor %%ah, %%ah\n" - "1:" - : "=a" (result) - : "0" (PCIBIOS_WRITE_CONFIG_BYTE), - "c" (value), - "b" (bx), - "D" ((long)reg), - "S" (&pci_indirect)); + number = PCIBIOS_WRITE_CONFIG_BYTE; break; case 2: - __asm__("lcall *(%%esi); cld\n\t" - "jc 1f\n\t" - "xor %%ah, %%ah\n" - "1:" - : "=a" (result) - : "0" (PCIBIOS_WRITE_CONFIG_WORD), - "c" (value), - "b" (bx), - "D" ((long)reg), - "S" (&pci_indirect)); + number = PCIBIOS_WRITE_CONFIG_WORD; break; case 4: - __asm__("lcall *(%%esi); cld\n\t" - "jc 1f\n\t" - "xor %%ah, %%ah\n" - "1:" - : "=a" (result) - : "0" (PCIBIOS_WRITE_CONFIG_DWORD), - "c" (value), - "b" (bx), - "D" ((long)reg), - "S" (&pci_indirect)); + number = PCIBIOS_WRITE_CONFIG_DWORD; break; } + __asm__("lcall *(%%esi); cld\n\t" + "jc 1f\n\t" + "xor %%ah, %%ah\n" + "1:" + : "=a" (result) + : "0" (number), + "c" (value), + "b" (bx), + "D" ((long)reg), + "S" (&pci_indirect)); + raw_spin_unlock_irqrestore(&pci_config_lock, flags); return (int)((result & 0xff00) >> 8); diff --git a/arch/x86/pci/vmd.c b/arch/x86/pci/vmd.c new file mode 100644 index 000000000000..7792aba266df --- /dev/null +++ b/arch/x86/pci/vmd.c @@ -0,0 +1,756 @@ +/* + * Volume Management Device driver + * Copyright (c) 2015, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#include <linux/device.h> +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/msi.h> +#include <linux/pci.h> +#include <linux/rculist.h> +#include <linux/rcupdate.h> + +#include <asm/irqdomain.h> +#include <asm/device.h> +#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. + */ +static DEFINE_RAW_SPINLOCK(list_lock); + +/** + * 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. + * @irq: back pointer to parent. + * @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. + */ +struct vmd_irq { + struct list_head node; + struct rcu_head rcu; + struct vmd_irq_list *irq; + unsigned int virq; +}; + +/** + * 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; +}; + +struct vmd_dev { + struct pci_dev *dev; + + spinlock_t cfg_lock; + char __iomem *cfgbar; + + int msix_count; + struct msix_entry *msix_entries; + struct vmd_irq_list *irqs; + + struct pci_sysdata sysdata; + struct resource resources[3]; + struct irq_domain *irq_domain; + struct pci_bus *bus; + +#ifdef CONFIG_X86_DEV_DMA_OPS + struct dma_map_ops dma_ops; + struct dma_domain dma_domain; +#endif +}; + +static inline struct vmd_dev *vmd_from_bus(struct pci_bus *bus) +{ + return container_of(bus->sysdata, struct vmd_dev, sysdata); +} + +/* + * 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 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) +{ + struct vmd_irq *vmdirq = data->chip_data; + struct vmd_irq_list *irq = vmdirq->irq; + + msg->address_hi = MSI_ADDR_BASE_HI; + msg->address_lo = MSI_ADDR_BASE_LO | MSI_ADDR_DEST_ID(irq->index); + msg->data = 0; +} + +/* + * 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) +{ + struct vmd_irq *vmdirq = data->chip_data; + + raw_spin_lock(&list_lock); + list_add_tail_rcu(&vmdirq->node, &vmdirq->irq->irq_list); + raw_spin_unlock(&list_lock); + + data->chip->irq_unmask(data); +} + +static void vmd_irq_disable(struct irq_data *data) +{ + struct vmd_irq *vmdirq = data->chip_data; + + data->chip->irq_mask(data); + + raw_spin_lock(&list_lock); + list_del_rcu(&vmdirq->node); + raw_spin_unlock(&list_lock); +} + +/* + * XXX: Stubbed until we develop acceptable way to not create conflicts with + * other devices sharing the same vector. + */ +static int vmd_irq_set_affinity(struct irq_data *data, + const struct cpumask *dest, bool force) +{ + return -EINVAL; +} + +static struct irq_chip vmd_msi_controller = { + .name = "VMD-MSI", + .irq_enable = vmd_irq_enable, + .irq_disable = vmd_irq_disable, + .irq_compose_msi_msg = vmd_compose_msi_msg, + .irq_set_affinity = vmd_irq_set_affinity, +}; + +static irq_hw_number_t vmd_get_hwirq(struct msi_domain_info *info, + msi_alloc_info_t *arg) +{ + return 0; +} + +/* + * 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) +{ + int i, best = 0; + + raw_spin_lock(&list_lock); + for (i = 1; i < vmd->msix_count; i++) + if (vmd->irqs[i].count < vmd->irqs[best].count) + best = i; + vmd->irqs[best].count++; + raw_spin_unlock(&list_lock); + + return &vmd->irqs[best]; +} + +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) +{ + struct vmd_dev *vmd = vmd_from_bus(msi_desc_to_pci_dev(arg->desc)->bus); + struct vmd_irq *vmdirq = kzalloc(sizeof(*vmdirq), GFP_KERNEL); + + if (!vmdirq) + return -ENOMEM; + + INIT_LIST_HEAD(&vmdirq->node); + 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); + return 0; +} + +static void vmd_msi_free(struct irq_domain *domain, + struct msi_domain_info *info, unsigned int virq) +{ + struct vmd_irq *vmdirq = irq_get_chip_data(virq); + + /* XXX: Potential optimization to rebalance */ + raw_spin_lock(&list_lock); + vmdirq->irq->count--; + raw_spin_unlock(&list_lock); + + kfree_rcu(vmdirq, rcu); +} + +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; +} + +static void vmd_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc) +{ + arg->desc = desc; +} + +static struct msi_domain_ops vmd_msi_domain_ops = { + .get_hwirq = vmd_get_hwirq, + .msi_init = vmd_msi_init, + .msi_free = vmd_msi_free, + .msi_prepare = vmd_msi_prepare, + .set_desc = vmd_set_desc, +}; + +static struct msi_domain_info vmd_msi_domain_info = { + .flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | + MSI_FLAG_PCI_MSIX, + .ops = &vmd_msi_domain_ops, + .chip = &vmd_msi_controller, +}; + +#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, not the device requiring + * the mapping. + */ +static struct device *to_vmd_dev(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct vmd_dev *vmd = vmd_from_bus(pdev->bus); + + return &vmd->dev->dev; +} + +static struct dma_map_ops *vmd_dma_ops(struct device *dev) +{ + return to_vmd_dev(dev)->archdata.dma_ops; +} + +static void *vmd_alloc(struct device *dev, size_t size, dma_addr_t *addr, + gfp_t flag, struct dma_attrs *attrs) +{ + return vmd_dma_ops(dev)->alloc(to_vmd_dev(dev), size, addr, flag, + attrs); +} + +static void vmd_free(struct device *dev, size_t size, void *vaddr, + dma_addr_t addr, struct dma_attrs *attrs) +{ + return vmd_dma_ops(dev)->free(to_vmd_dev(dev), size, vaddr, addr, + 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) +{ + return vmd_dma_ops(dev)->mmap(to_vmd_dev(dev), vma, cpu_addr, addr, + 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) +{ + return vmd_dma_ops(dev)->get_sgtable(to_vmd_dev(dev), sgt, cpu_addr, + 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) +{ + return vmd_dma_ops(dev)->map_page(to_vmd_dev(dev), page, offset, size, + 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) +{ + 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) +{ + 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) +{ + 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) +{ + 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) +{ + vmd_dma_ops(dev)->sync_single_for_device(to_vmd_dev(dev), addr, size, + dir); +} + +static void vmd_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, + int nents, enum dma_data_direction dir) +{ + vmd_dma_ops(dev)->sync_sg_for_cpu(to_vmd_dev(dev), sg, nents, dir); +} + +static void vmd_sync_sg_for_device(struct device *dev, struct scatterlist *sg, + int nents, enum dma_data_direction dir) +{ + vmd_dma_ops(dev)->sync_sg_for_device(to_vmd_dev(dev), sg, nents, dir); +} + +static int vmd_mapping_error(struct device *dev, dma_addr_t addr) +{ + return vmd_dma_ops(dev)->mapping_error(to_vmd_dev(dev), addr); +} + +static int vmd_dma_supported(struct device *dev, u64 mask) +{ + return vmd_dma_ops(dev)->dma_supported(to_vmd_dev(dev), mask); +} + +#ifdef ARCH_HAS_DMA_GET_REQUIRED_MASK +static u64 vmd_get_required_mask(struct device *dev) +{ + return vmd_dma_ops(dev)->get_required_mask(to_vmd_dev(dev)); +} +#endif + +static void vmd_teardown_dma_ops(struct vmd_dev *vmd) +{ + struct dma_domain *domain = &vmd->dma_domain; + + if (vmd->dev->dev.archdata.dma_ops) + del_dma_domain(domain); +} + +#define ASSIGN_VMD_DMA_OPS(source, dest, fn) \ + do { \ + if (source->fn) \ + dest->fn = vmd_##fn; \ + } while (0) + +static void vmd_setup_dma_ops(struct vmd_dev *vmd) +{ + const struct dma_map_ops *source = vmd->dev->dev.archdata.dma_ops; + struct dma_map_ops *dest = &vmd->dma_ops; + struct dma_domain *domain = &vmd->dma_domain; + + domain->domain_nr = vmd->sysdata.domain; + domain->dma_ops = dest; + + if (!source) + return; + ASSIGN_VMD_DMA_OPS(source, dest, alloc); + ASSIGN_VMD_DMA_OPS(source, dest, free); + ASSIGN_VMD_DMA_OPS(source, dest, mmap); + ASSIGN_VMD_DMA_OPS(source, dest, get_sgtable); + ASSIGN_VMD_DMA_OPS(source, dest, map_page); + ASSIGN_VMD_DMA_OPS(source, dest, unmap_page); + ASSIGN_VMD_DMA_OPS(source, dest, map_sg); + ASSIGN_VMD_DMA_OPS(source, dest, unmap_sg); + ASSIGN_VMD_DMA_OPS(source, dest, sync_single_for_cpu); + ASSIGN_VMD_DMA_OPS(source, dest, sync_single_for_device); + ASSIGN_VMD_DMA_OPS(source, dest, sync_sg_for_cpu); + ASSIGN_VMD_DMA_OPS(source, dest, sync_sg_for_device); + ASSIGN_VMD_DMA_OPS(source, dest, mapping_error); + ASSIGN_VMD_DMA_OPS(source, dest, dma_supported); +#ifdef ARCH_HAS_DMA_GET_REQUIRED_MASK + ASSIGN_VMD_DMA_OPS(source, dest, get_required_mask); +#endif + add_dma_domain(domain); +} +#undef ASSIGN_VMD_DMA_OPS +#else +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) +{ + struct vmd_dev *vmd = vmd_from_bus(bus); + char __iomem *addr = vmd_cfg_addr(vmd, bus, devfn, reg, len); + unsigned long flags; + int ret = 0; + + if (!addr) + return -EFAULT; + + spin_lock_irqsave(&vmd->cfg_lock, flags); + switch (len) { + case 1: + *value = readb(addr); + break; + case 2: + *value = readw(addr); + break; + case 4: + *value = readl(addr); + break; + default: + ret = -EINVAL; + break; + } + spin_unlock_irqrestore(&vmd->cfg_lock, flags); + return ret; +} + +/* + * VMD h/w converts non-posted config writes to posted memory writes. The + * read-back in this function forces the completion so it returns only after + * 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) +{ + struct vmd_dev *vmd = vmd_from_bus(bus); + char __iomem *addr = vmd_cfg_addr(vmd, bus, devfn, reg, len); + unsigned long flags; + int ret = 0; + + if (!addr) + return -EFAULT; + + spin_lock_irqsave(&vmd->cfg_lock, flags); + switch (len) { + case 1: + writeb(value, addr); + readb(addr); + break; + case 2: + writew(value, addr); + readw(addr); + break; + case 4: + writel(value, addr); + readl(addr); + break; + default: + ret = -EINVAL; + break; + } + spin_unlock_irqrestore(&vmd->cfg_lock, flags); + return ret; +} + +static struct pci_ops vmd_ops = { + .read = vmd_pci_read, + .write = vmd_pci_write, +}; + +static void vmd_attach_resources(struct vmd_dev *vmd) +{ + vmd->dev->resource[VMD_MEMBAR1].child = &vmd->resources[1]; + vmd->dev->resource[VMD_MEMBAR2].child = &vmd->resources[2]; +} + +static void vmd_detach_resources(struct vmd_dev *vmd) +{ + vmd->dev->resource[VMD_MEMBAR1].child = NULL; + vmd->dev->resource[VMD_MEMBAR2].child = NULL; +} + +/* + * VMD domains start at 0x1000 to not clash with ACPI _SEG domains. + */ +static int vmd_find_free_domain(void) +{ + int domain = 0xffff; + struct pci_bus *bus = NULL; + + while ((bus = pci_find_next_bus(bus)) != NULL) + domain = max_t(int, domain, pci_domain_nr(bus)); + return domain + 1; +} + +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->dev->resource[VMD_CFGBAR]; + vmd->resources[0] = (struct resource) { + .name = "VMD CFGBAR", + .start = 0, + .end = (resource_size(res) >> 20) - 1, + .flags = IORESOURCE_BUS | IORESOURCE_PCI_FIXED, + }; + + /* + * If the window is below 4GB, clear IORESOURCE_MEM_64 so we can + * put 32-bit resources in the window. + * + * There's no hardware reason why a 64-bit window *couldn't* + * contain a 32-bit resource, but pbus_size_mem() computes the + * bridge window size assuming a 64-bit window will contain no + * 32-bit resources. __pci_assign_resource() enforces that + * artificial restriction to make sure everything will fit. + * + * The only way we could use a 64-bit non-prefechable MEMBAR is + * if its address is <4GB so that we can convert it to a 32-bit + * resource. To be visible to the host OS, all VMD endpoints must + * be initially configured by platform BIOS, which includes setting + * up these resources. We can assume the device is configured + * according to the platform needs. + */ + 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, + .parent = res, + }; + + 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, + .parent = res, + }; + + 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); + if (!vmd->irq_domain) + return -ENODEV; + + pci_add_resource(&resources, &vmd->resources[0]); + 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); + if (!vmd->bus) { + pci_free_resource_list(&resources); + irq_domain_remove(vmd->irq_domain); + return -ENODEV; + } + + vmd_attach_resources(vmd); + vmd_setup_dma_ops(vmd); + dev_set_msi_domain(&vmd->bus->dev, vmd->irq_domain); + 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"); + return 0; +} + +static irqreturn_t vmd_irq(int irq, void *data) +{ + struct vmd_irq_list *irqs = data; + struct vmd_irq *vmdirq; + + rcu_read_lock(); + list_for_each_entry_rcu(vmdirq, &irqs->irq_list, node) + generic_handle_irq(vmdirq->virq); + rcu_read_unlock(); + + return IRQ_HANDLED; +} + +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[VMD_CFGBAR]) < (1 << 20)) + return -ENOMEM; + + vmd = devm_kzalloc(&dev->dev, sizeof(*vmd), GFP_KERNEL); + if (!vmd) + return -ENOMEM; + + vmd->dev = dev; + err = pcim_enable_device(dev); + if (err < 0) + return err; + + vmd->cfgbar = pcim_iomap(dev, VMD_CFGBAR, 0); + if (!vmd->cfgbar) + return -ENOMEM; + + pci_set_master(dev); + if (dma_set_mask_and_coherent(&dev->dev, DMA_BIT_MASK(64)) && + dma_set_mask_and_coherent(&dev->dev, DMA_BIT_MASK(32))) + return -ENODEV; + + vmd->msix_count = pci_msix_vec_count(dev); + if (vmd->msix_count < 0) + return -ENODEV; + + 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, + vmd_irq, 0, "vmd", &vmd->irqs[i]); + if (err) + return err; + } + + spin_lock_init(&vmd->cfg_lock); + pci_set_drvdata(dev, vmd); + err = vmd_enable_domain(vmd); + if (err) + return err; + + dev_info(&vmd->dev->dev, "Bound to PCI domain %04x\n", + vmd->sysdata.domain); + return 0; +} + +static void vmd_remove(struct pci_dev *dev) +{ + struct vmd_dev *vmd = pci_get_drvdata(dev); + + vmd_detach_resources(vmd); + pci_set_drvdata(dev, NULL); + sysfs_remove_link(&vmd->dev->dev.kobj, "domain"); + pci_stop_root_bus(vmd->bus); + pci_remove_root_bus(vmd->bus); + vmd_teardown_dma_ops(vmd); + irq_domain_remove(vmd->irq_domain); +} + +#ifdef CONFIG_PM +static int vmd_suspend(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + + pci_save_state(pdev); + return 0; +} + +static int vmd_resume(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + + pci_restore_state(pdev); + return 0; +} +#endif +static SIMPLE_DEV_PM_OPS(vmd_dev_pm_ops, vmd_suspend, vmd_resume); + +static const struct pci_device_id vmd_ids[] = { + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x201d),}, + {0,} +}; +MODULE_DEVICE_TABLE(pci, vmd_ids); + +static struct pci_driver vmd_drv = { + .name = "vmd", + .id_table = vmd_ids, + .probe = vmd_probe, + .remove = vmd_remove, + .driver = { + .pm = &vmd_dev_pm_ops, + }, +}; +module_pci_driver(vmd_drv); + +MODULE_AUTHOR("Intel Corporation"); +MODULE_LICENSE("GPL v2"); +MODULE_VERSION("0.6"); diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index ff31ab464213..beac4dfdade6 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -196,7 +196,10 @@ static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) return 0; error: - dev_err(&dev->dev, "Xen PCI frontend has not registered MSI/MSI-X support!\n"); + if (ret == -ENOSYS) + dev_err(&dev->dev, "Xen PCI frontend has not registered MSI/MSI-X support!\n"); + else if (ret) + dev_err(&dev->dev, "Xen PCI frontend error: %d!\n", ret); free: kfree(v); return ret; |