diff options
30 files changed, 818 insertions, 177 deletions
diff --git a/Documentation/ABI/testing/sysfs-bus-pci b/Documentation/ABI/testing/sysfs-bus-pci index 36bf454..349ecf2 100644 --- a/Documentation/ABI/testing/sysfs-bus-pci +++ b/Documentation/ABI/testing/sysfs-bus-pci @@ -74,6 +74,15 @@ Description: hot-remove the PCI device and any of its children. Depends on CONFIG_HOTPLUG. +What: /sys/bus/pci/devices/.../pci_bus/.../rescan +Date: May 2011 +Contact: Linux PCI developers <linux-pci@vger.kernel.org> +Description: + Writing a non-zero value to this attribute will + force a rescan of the bus and all child buses, + and re-discover devices removed earlier from this + part of the device tree. Depends on CONFIG_HOTPLUG. + What: /sys/bus/pci/devices/.../rescan Date: January 2009 Contact: Linux PCI developers <linux-pci@vger.kernel.org> diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index 6761292..d498943 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm/pci.h @@ -135,8 +135,6 @@ void default_teardown_msi_irqs(struct pci_dev *dev); #include "pci_64.h" #endif -void dma32_reserve_bootmem(void); - /* implement the pci_ DMA API in terms of the generic device dma_ one */ #include <asm-generic/pci-dma-compat.h> diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 9ea999a..b49d00d 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -68,74 +68,10 @@ int dma_set_mask(struct device *dev, u64 mask) } EXPORT_SYMBOL(dma_set_mask); -#if defined(CONFIG_X86_64) && !defined(CONFIG_NUMA) -static __initdata void *dma32_bootmem_ptr; -static unsigned long dma32_bootmem_size __initdata = (128ULL<<20); - -static int __init parse_dma32_size_opt(char *p) -{ - if (!p) - return -EINVAL; - dma32_bootmem_size = memparse(p, &p); - return 0; -} -early_param("dma32_size", parse_dma32_size_opt); - -void __init dma32_reserve_bootmem(void) -{ - unsigned long size, align; - if (max_pfn <= MAX_DMA32_PFN) - return; - - /* - * check aperture_64.c allocate_aperture() for reason about - * using 512M as goal - */ - align = 64ULL<<20; - size = roundup(dma32_bootmem_size, align); - dma32_bootmem_ptr = __alloc_bootmem_nopanic(size, align, - 512ULL<<20); - /* - * Kmemleak should not scan this block as it may not be mapped via the - * kernel direct mapping. - */ - kmemleak_ignore(dma32_bootmem_ptr); - if (dma32_bootmem_ptr) - dma32_bootmem_size = size; - else - dma32_bootmem_size = 0; -} -static void __init dma32_free_bootmem(void) -{ - - if (max_pfn <= MAX_DMA32_PFN) - return; - - if (!dma32_bootmem_ptr) - return; - - free_bootmem(__pa(dma32_bootmem_ptr), dma32_bootmem_size); - - dma32_bootmem_ptr = NULL; - dma32_bootmem_size = 0; -} -#else -void __init dma32_reserve_bootmem(void) -{ -} -static void __init dma32_free_bootmem(void) -{ -} - -#endif - void __init pci_iommu_alloc(void) { struct iommu_table_entry *p; - /* free the range so iommu could get some range less than 4G */ - dma32_free_bootmem(); - sort_iommu_table(__iommu_table, __iommu_table_end); check_iommu_entries(__iommu_table, __iommu_table_end); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index c3050af..605e5ae 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -964,7 +964,6 @@ void __init setup_arch(char **cmdline_p) initmem_init(); memblock_find_dma_reserve(); - dma32_reserve_bootmem(); #ifdef CONFIG_KVM_CLOCK kvmclock_init(); diff --git a/arch/x86/pci/direct.c b/arch/x86/pci/direct.c index bd33620..e6fd847 100644 --- a/arch/x86/pci/direct.c +++ b/arch/x86/pci/direct.c @@ -280,12 +280,9 @@ void __init pci_direct_init(int type) int __init pci_direct_probe(void) { - struct resource *region, *region2; - if ((pci_probe & PCI_PROBE_CONF1) == 0) goto type2; - region = request_region(0xCF8, 8, "PCI conf1"); - if (!region) + if (!request_region(0xCF8, 8, "PCI conf1")) goto type2; if (pci_check_type1()) { @@ -293,16 +290,14 @@ int __init pci_direct_probe(void) port_cf9_safe = true; return 1; } - release_resource(region); + release_region(0xCF8, 8); type2: if ((pci_probe & PCI_PROBE_CONF2) == 0) return 0; - region = request_region(0xCF8, 4, "PCI conf2"); - if (!region) + if (!request_region(0xCF8, 4, "PCI conf2")) return 0; - region2 = request_region(0xC000, 0x1000, "PCI conf2"); - if (!region2) + if (!request_region(0xC000, 0x1000, "PCI conf2")) goto fail2; if (pci_check_type2()) { @@ -311,8 +306,8 @@ int __init pci_direct_probe(void) return 2; } - release_resource(region2); + release_region(0xC000, 0x1000); fail2: - release_resource(region); + release_region(0xCF8, 4); return 0; } diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index 8201165..372e9b8 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -602,7 +602,9 @@ static __init int intel_router_probe(struct irq_router *r, struct pci_dev *route || (device >= PCI_DEVICE_ID_INTEL_COUGARPOINT_LPC_MIN && device <= PCI_DEVICE_ID_INTEL_COUGARPOINT_LPC_MAX) || (device >= PCI_DEVICE_ID_INTEL_DH89XXCC_LPC_MIN && - device <= PCI_DEVICE_ID_INTEL_DH89XXCC_LPC_MAX)) { + device <= PCI_DEVICE_ID_INTEL_DH89XXCC_LPC_MAX) + || (device >= PCI_DEVICE_ID_INTEL_PANTHERPOINT_LPC_MIN && + device <= PCI_DEVICE_ID_INTEL_PANTHERPOINT_LPC_MAX)) { r->name = "PIIX/ICH"; r->get = pirq_piix_get; r->set = pirq_piix_set; diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c index e282886..750c346 100644 --- a/arch/x86/pci/mmconfig-shared.c +++ b/arch/x86/pci/mmconfig-shared.c @@ -606,6 +606,16 @@ static void __init __pci_mmcfg_init(int early) if (list_empty(&pci_mmcfg_list)) return; + if (pcibios_last_bus < 0) { + const struct pci_mmcfg_region *cfg; + + list_for_each_entry(cfg, &pci_mmcfg_list, list) { + if (cfg->segment) + break; + pcibios_last_bus = cfg->end_bus; + } + } + if (pci_mmcfg_arch_init()) pci_probe = (pci_probe & ~PCI_PROBE_MASK) | PCI_PROBE_MMCONF; else { diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c index f911a2f..d06078d 100644 --- a/drivers/acpi/pci_root.c +++ b/drivers/acpi/pci_root.c @@ -596,12 +596,18 @@ static int __devinit acpi_pci_root_add(struct acpi_device *device) dev_info(root->bus->bridge, "ACPI _OSC control (0x%02x) granted\n", flags); } else { - dev_dbg(root->bus->bridge, - "ACPI _OSC request failed (code %d)\n", status); - printk(KERN_INFO "Unable to assume _OSC PCIe control. " - "Disabling ASPM\n"); + dev_info(root->bus->bridge, + "ACPI _OSC request failed (%s), " + "returned control mask: 0x%02x\n", + acpi_format_exception(status), flags); + pr_info("ACPI _OSC control for PCIe not granted, " + "disabling ASPM\n"); pcie_no_aspm(); } + } else { + dev_info(root->bus->bridge, + "Unable to request _OSC control " + "(_OSC support mask: 0x%02x)\n", flags); } pci_acpi_add_bus_pm_notifier(device, root->bus); diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index 455e909..ec36208 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -137,6 +137,7 @@ /* Older devices have their ID defined in <linux/pci_ids.h> */ #define PCI_DEVICE_ID_INTEL_COUGARPOINT_SMBUS 0x1c22 #define PCI_DEVICE_ID_INTEL_PATSBURG_SMBUS 0x1d22 +#define PCI_DEVICE_ID_INTEL_PANTHERPOINT_SMBUS 0x1e22 /* Patsburg also has three 'Integrated Device Function' SMBus controllers */ #define PCI_DEVICE_ID_INTEL_PATSBURG_SMBUS_IDF0 0x1d70 #define PCI_DEVICE_ID_INTEL_PATSBURG_SMBUS_IDF1 0x1d71 diff --git a/drivers/net/e1000e/netdev.c b/drivers/net/e1000e/netdev.c index d960056..3310c3d 100644 --- a/drivers/net/e1000e/netdev.c +++ b/drivers/net/e1000e/netdev.c @@ -5361,7 +5361,7 @@ static void e1000_complete_shutdown(struct pci_dev *pdev, bool sleep, #ifdef CONFIG_PCIEASPM static void __e1000e_disable_aspm(struct pci_dev *pdev, u16 state) { - pci_disable_link_state(pdev, state); + pci_disable_link_state_locked(pdev, state); } #else static void __e1000e_disable_aspm(struct pci_dev *pdev, u16 state) diff --git a/drivers/pci/access.c b/drivers/pci/access.c index 531bc69..fdaa42a 100644 --- a/drivers/pci/access.c +++ b/drivers/pci/access.c @@ -143,33 +143,41 @@ static noinline void pci_wait_ucfg(struct pci_dev *dev) __remove_wait_queue(&pci_ucfg_wait, &wait); } +/* Returns 0 on success, negative values indicate error. */ #define PCI_USER_READ_CONFIG(size,type) \ int pci_user_read_config_##size \ (struct pci_dev *dev, int pos, type *val) \ { \ int ret = 0; \ u32 data = -1; \ - if (PCI_##size##_BAD) return PCIBIOS_BAD_REGISTER_NUMBER; \ + if (PCI_##size##_BAD) \ + return -EINVAL; \ raw_spin_lock_irq(&pci_lock); \ if (unlikely(dev->block_ucfg_access)) pci_wait_ucfg(dev); \ ret = dev->bus->ops->read(dev->bus, dev->devfn, \ pos, sizeof(type), &data); \ raw_spin_unlock_irq(&pci_lock); \ *val = (type)data; \ + if (ret > 0) \ + ret = -EINVAL; \ return ret; \ } +/* Returns 0 on success, negative values indicate error. */ #define PCI_USER_WRITE_CONFIG(size,type) \ int pci_user_write_config_##size \ (struct pci_dev *dev, int pos, type val) \ { \ int ret = -EIO; \ - if (PCI_##size##_BAD) return PCIBIOS_BAD_REGISTER_NUMBER; \ + if (PCI_##size##_BAD) \ + return -EINVAL; \ raw_spin_lock_irq(&pci_lock); \ if (unlikely(dev->block_ucfg_access)) pci_wait_ucfg(dev); \ ret = dev->bus->ops->write(dev->bus, dev->devfn, \ pos, sizeof(type), val); \ raw_spin_unlock_irq(&pci_lock); \ + if (ret > 0) \ + ret = -EINVAL; \ return ret; \ } @@ -197,6 +205,8 @@ struct pci_vpd_pci22 { * This code has to spin since there is no other notification from the PCI * hardware. Since the VPD is often implemented by serial attachment to an * EEPROM, it may take many milliseconds to complete. + * + * Returns 0 on success, negative values indicate error. */ static int pci_vpd_pci22_wait(struct pci_dev *dev) { @@ -212,7 +222,7 @@ static int pci_vpd_pci22_wait(struct pci_dev *dev) for (;;) { ret = pci_user_read_config_word(dev, vpd->cap + PCI_VPD_ADDR, &status); - if (ret) + if (ret < 0) return ret; if ((status & PCI_VPD_ADDR_F) == vpd->flag) { @@ -324,6 +334,8 @@ static ssize_t pci_vpd_pci22_write(struct pci_dev *dev, loff_t pos, size_t count vpd->busy = true; vpd->flag = 0; ret = pci_vpd_pci22_wait(dev); + if (ret < 0) + break; pos += sizeof(u32); } diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c index 69546e9..1e2ad92 100644 --- a/drivers/pci/bus.c +++ b/drivers/pci/bus.c @@ -163,12 +163,6 @@ int pci_bus_add_child(struct pci_bus *bus) bus->is_added = 1; - retval = device_create_file(&bus->dev, &dev_attr_cpuaffinity); - if (retval) - return retval; - - retval = device_create_file(&bus->dev, &dev_attr_cpulistaffinity); - /* Create legacy_io and legacy_mem files for this bus */ pci_create_legacy_files(bus); diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c index 2f67e9b..a70fa89 100644 --- a/drivers/pci/hotplug/acpiphp_glue.c +++ b/drivers/pci/hotplug/acpiphp_glue.c @@ -827,6 +827,13 @@ static int __ref enable_device(struct acpiphp_slot *slot) acpiphp_set_hpp_values(bus); acpiphp_set_acpi_region(slot); pci_enable_bridges(bus); + + list_for_each_entry(dev, &bus->devices, bus_list) { + /* Assume that newly added devices are powered on already. */ + if (!dev->is_added) + dev->current_state = PCI_D0; + } + pci_bus_add_devices(bus); list_for_each_entry(func, &slot->funcs, sibling) { diff --git a/drivers/pci/hotplug/pcihp_slot.c b/drivers/pci/hotplug/pcihp_slot.c index 80b461c..749fdf0 100644 --- a/drivers/pci/hotplug/pcihp_slot.c +++ b/drivers/pci/hotplug/pcihp_slot.c @@ -158,6 +158,47 @@ static void program_hpp_type2(struct pci_dev *dev, struct hpp_type2 *hpp) */ } +/* Program PCIE MaxPayload setting on device: ensure parent maxpayload <= device */ +static int pci_set_payload(struct pci_dev *dev) +{ + int pos, ppos; + u16 pctl, psz; + u16 dctl, dsz, dcap, dmax; + struct pci_dev *parent; + + parent = dev->bus->self; + pos = pci_find_capability(dev, PCI_CAP_ID_EXP); + if (!pos) + return 0; + + /* Read Device MaxPayload capability and setting */ + pci_read_config_word(dev, pos + PCI_EXP_DEVCTL, &dctl); + pci_read_config_word(dev, pos + PCI_EXP_DEVCAP, &dcap); + dsz = (dctl & PCI_EXP_DEVCTL_PAYLOAD) >> 5; + dmax = (dcap & PCI_EXP_DEVCAP_PAYLOAD); + + /* Read Parent MaxPayload setting */ + ppos = pci_find_capability(parent, PCI_CAP_ID_EXP); + if (!ppos) + return 0; + pci_read_config_word(parent, ppos + PCI_EXP_DEVCTL, &pctl); + psz = (pctl & PCI_EXP_DEVCTL_PAYLOAD) >> 5; + + /* If parent payload > device max payload -> error + * If parent payload > device payload -> set speed + * If parent payload <= device payload -> do nothing + */ + if (psz > dmax) + return -1; + else if (psz > dsz) { + dev_info(&dev->dev, "Setting MaxPayload to %d\n", 128 << psz); + pci_write_config_word(dev, pos + PCI_EXP_DEVCTL, + (dctl & ~PCI_EXP_DEVCTL_PAYLOAD) + + (psz << 5)); + } + return 0; +} + void pci_configure_slot(struct pci_dev *dev) { struct pci_dev *cdev; @@ -169,6 +210,10 @@ void pci_configure_slot(struct pci_dev *dev) (dev->class >> 8) == PCI_CLASS_BRIDGE_PCI))) return; + ret = pci_set_payload(dev); + if (ret) + dev_warn(&dev->dev, "could not set device max payload\n"); + memset(&hpp, 0, sizeof(hpp)); ret = pci_get_hp_params(dev, &hpp); if (ret) diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index f8deb3e..7bcf12a 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -108,6 +108,40 @@ static ssize_t local_cpulist_show(struct device *dev, return len; } +/* + * PCI Bus Class Devices + */ +static ssize_t pci_bus_show_cpuaffinity(struct device *dev, + int type, + struct device_attribute *attr, + char *buf) +{ + int ret; + const struct cpumask *cpumask; + + cpumask = cpumask_of_pcibus(to_pci_bus(dev)); + ret = type ? + cpulist_scnprintf(buf, PAGE_SIZE-2, cpumask) : + cpumask_scnprintf(buf, PAGE_SIZE-2, cpumask); + buf[ret++] = '\n'; + buf[ret] = '\0'; + return ret; +} + +static inline ssize_t pci_bus_show_cpumaskaffinity(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + return pci_bus_show_cpuaffinity(dev, 0, attr, buf); +} + +static inline ssize_t pci_bus_show_cpulistaffinity(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + return pci_bus_show_cpuaffinity(dev, 1, attr, buf); +} + /* show resources */ static ssize_t resource_show(struct device * dev, struct device_attribute *attr, char * buf) @@ -318,6 +352,25 @@ remove_store(struct device *dev, struct device_attribute *dummy, count = ret; return count; } + +static ssize_t +dev_bus_rescan_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + unsigned long val; + struct pci_bus *bus = to_pci_bus(dev); + + if (strict_strtoul(buf, 0, &val) < 0) + return -EINVAL; + + if (val) { + mutex_lock(&pci_remove_rescan_mutex); + pci_rescan_bus(bus); + mutex_unlock(&pci_remove_rescan_mutex); + } + return count; +} + #endif struct device_attribute pci_dev_attrs[] = { @@ -347,6 +400,15 @@ struct device_attribute pci_dev_attrs[] = { __ATTR_NULL, }; +struct device_attribute pcibus_dev_attrs[] = { +#ifdef CONFIG_HOTPLUG + __ATTR(rescan, (S_IWUSR|S_IWGRP), NULL, dev_bus_rescan_store), +#endif + __ATTR(cpuaffinity, S_IRUGO, pci_bus_show_cpumaskaffinity, NULL), + __ATTR(cpulistaffinity, S_IRUGO, pci_bus_show_cpulistaffinity, NULL), + __ATTR_NULL, +}; + static ssize_t boot_vga_show(struct device *dev, struct device_attribute *attr, char *buf) { diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 2472e71..22c9b27 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -830,7 +830,7 @@ static int pci_save_pcie_state(struct pci_dev *dev) dev_err(&dev->dev, "buffer not found in %s\n", __func__); return -ENOMEM; } - cap = (u16 *)&save_state->data[0]; + cap = (u16 *)&save_state->cap.data[0]; pci_read_config_word(dev, pos + PCI_EXP_FLAGS, &flags); @@ -863,7 +863,7 @@ static void pci_restore_pcie_state(struct pci_dev *dev) pos = pci_find_capability(dev, PCI_CAP_ID_EXP); if (!save_state || pos <= 0) return; - cap = (u16 *)&save_state->data[0]; + cap = (u16 *)&save_state->cap.data[0]; pci_read_config_word(dev, pos + PCI_EXP_FLAGS, &flags); @@ -899,7 +899,8 @@ static int pci_save_pcix_state(struct pci_dev *dev) return -ENOMEM; } - pci_read_config_word(dev, pos + PCI_X_CMD, (u16 *)save_state->data); + pci_read_config_word(dev, pos + PCI_X_CMD, + (u16 *)save_state->cap.data); return 0; } @@ -914,7 +915,7 @@ static void pci_restore_pcix_state(struct pci_dev *dev) pos = pci_find_capability(dev, PCI_CAP_ID_PCIX); if (!save_state || pos <= 0) return; - cap = (u16 *)&save_state->data[0]; + cap = (u16 *)&save_state->cap.data[0]; pci_write_config_word(dev, pos + PCI_X_CMD, cap[i++]); } @@ -975,6 +976,104 @@ void pci_restore_state(struct pci_dev *dev) dev->state_saved = false; } +struct pci_saved_state { + u32 config_space[16]; + struct pci_cap_saved_data cap[0]; +}; + +/** + * pci_store_saved_state - Allocate and return an opaque struct containing + * the device saved state. + * @dev: PCI device that we're dealing with + * + * Rerturn NULL if no state or error. + */ +struct pci_saved_state *pci_store_saved_state(struct pci_dev *dev) +{ + struct pci_saved_state *state; + struct pci_cap_saved_state *tmp; + struct pci_cap_saved_data *cap; + struct hlist_node *pos; + size_t size; + + if (!dev->state_saved) + return NULL; + + size = sizeof(*state) + sizeof(struct pci_cap_saved_data); + + hlist_for_each_entry(tmp, pos, &dev->saved_cap_space, next) + size += sizeof(struct pci_cap_saved_data) + tmp->cap.size; + + state = kzalloc(size, GFP_KERNEL); + if (!state) + return NULL; + + memcpy(state->config_space, dev->saved_config_space, + sizeof(state->config_space)); + + cap = state->cap; + hlist_for_each_entry(tmp, pos, &dev->saved_cap_space, next) { + size_t len = sizeof(struct pci_cap_saved_data) + tmp->cap.size; + memcpy(cap, &tmp->cap, len); + cap = (struct pci_cap_saved_data *)((u8 *)cap + len); + } + /* Empty cap_save terminates list */ + + return state; +} +EXPORT_SYMBOL_GPL(pci_store_saved_state); + +/** + * pci_load_saved_state - Reload the provided save state into struct pci_dev. + * @dev: PCI device that we're dealing with + * @state: Saved state returned from pci_store_saved_state() + */ +int pci_load_saved_state(struct pci_dev *dev, struct pci_saved_state *state) +{ + struct pci_cap_saved_data *cap; + + dev->state_saved = false; + + if (!state) + return 0; + + memcpy(dev->saved_config_space, state->config_space, + sizeof(state->config_space)); + + cap = state->cap; + while (cap->size) { + struct pci_cap_saved_state *tmp; + + tmp = pci_find_saved_cap(dev, cap->cap_nr); + if (!tmp || tmp->cap.size != cap->size) + return -EINVAL; + + memcpy(tmp->cap.data, cap->data, tmp->cap.size); + cap = (struct pci_cap_saved_data *)((u8 *)cap + + sizeof(struct pci_cap_saved_data) + cap->size); + } + + dev->state_saved = true; + return 0; +} +EXPORT_SYMBOL_GPL(pci_load_saved_state); + +/** + * pci_load_and_free_saved_state - Reload the save state pointed to by state, + * and free the memory allocated for it. + * @dev: PCI device that we're dealing with + * @state: Pointer to saved state returned from pci_store_saved_state() + */ +int pci_load_and_free_saved_state(struct pci_dev *dev, + struct pci_saved_state **state) +{ + int ret = pci_load_saved_state(dev, *state); + kfree(*state); + *state = NULL; + return ret; +} +EXPORT_SYMBOL_GPL(pci_load_and_free_saved_state); + static int do_pci_enable_device(struct pci_dev *dev, int bars) { int err; @@ -1771,7 +1870,8 @@ static int pci_add_cap_save_buffer( if (!save_state) return -ENOMEM; - save_state->cap_nr = cap; + save_state->cap.cap_nr = cap; + save_state->cap.size = size; pci_add_saved_cap(dev, save_state); return 0; @@ -1834,6 +1934,300 @@ void pci_enable_ari(struct pci_dev *dev) bridge->ari_enabled = 1; } +/** + * pci_enable_ido - enable ID-based ordering on a device + * @dev: the PCI device + * @type: which types of IDO to enable + * + * Enable ID-based ordering on @dev. @type can contain the bits + * %PCI_EXP_IDO_REQUEST and/or %PCI_EXP_IDO_COMPLETION to indicate + * which types of transactions are allowed to be re-ordered. + */ +void pci_enable_ido(struct pci_dev *dev, unsigned long type) +{ + int pos; + u16 ctrl; + + pos = pci_pcie_cap(dev); + if (!pos) + return; + + pci_read_config_word(dev, pos + PCI_EXP_DEVCTL2, &ctrl); + if (type & PCI_EXP_IDO_REQUEST) + ctrl |= PCI_EXP_IDO_REQ_EN; + if (type & PCI_EXP_IDO_COMPLETION) + ctrl |= PCI_EXP_IDO_CMP_EN; + pci_write_config_word(dev, pos + PCI_EXP_DEVCTL2, ctrl); +} +EXPORT_SYMBOL(pci_enable_ido); + +/** + * pci_disable_ido - disable ID-based ordering on a device + * @dev: the PCI device + * @type: which types of IDO to disable + */ +void pci_disable_ido(struct pci_dev *dev, unsigned long type) +{ + int pos; + u16 ctrl; + + if (!pci_is_pcie(dev)) + return; + + pos = pci_pcie_cap(dev); + if (!pos) + return; + + pci_read_config_word(dev, pos + PCI_EXP_DEVCTL2, &ctrl); + if (type & PCI_EXP_IDO_REQUEST) + ctrl &= ~PCI_EXP_IDO_REQ_EN; + if (type & PCI_EXP_IDO_COMPLETION) + ctrl &= ~PCI_EXP_IDO_CMP_EN; + pci_write_config_word(dev, pos + PCI_EXP_DEVCTL2, ctrl); +} +EXPORT_SYMBOL(pci_disable_ido); + +/** + * pci_enable_obff - enable optimized buffer flush/fill + * @dev: PCI device + * @type: type of signaling to use + * + * Try to enable @type OBFF signaling on @dev. It will try using WAKE# + * signaling if possible, falling back to message signaling only if + * WAKE# isn't supported. @type should indicate whether the PCIe link + * be brought out of L0s or L1 to send the message. It should be either + * %PCI_EXP_OBFF_SIGNAL_ALWAYS or %PCI_OBFF_SIGNAL_L0. + * + * If your device can benefit from receiving all messages, even at the + * power cost of bringing the link back up from a low power state, use + * %PCI_EXP_OBFF_SIGNAL_ALWAYS. Otherwise, use %PCI_OBFF_SIGNAL_L0 (the + * preferred type). + * + * RETURNS: + * Zero on success, appropriate error number on failure. + */ +int pci_enable_obff(struct pci_dev *dev, enum pci_obff_signal_type type) +{ + int pos; + u32 cap; + u16 ctrl; + int ret; + + if (!pci_is_pcie(dev)) + return -ENOTSUPP; + + pos = pci_pcie_cap(dev); + if (!pos) + return -ENOTSUPP; + + pci_read_config_dword(dev, pos + PCI_EXP_DEVCAP2, &cap); + if (!(cap & PCI_EXP_OBFF_MASK)) + return -ENOTSUPP; /* no OBFF support at all */ + + /* Make sure the topology supports OBFF as well */ + if (dev->bus) { + ret = pci_enable_obff(dev->bus->self, type); + if (ret) + return ret; + } + + pci_read_config_word(dev, pos + PCI_EXP_DEVCTL2, &ctrl); + if (cap & PCI_EXP_OBFF_WAKE) + ctrl |= PCI_EXP_OBFF_WAKE_EN; + else { + switch (type) { + case PCI_EXP_OBFF_SIGNAL_L0: + if (!(ctrl & PCI_EXP_OBFF_WAKE_EN)) + ctrl |= PCI_EXP_OBFF_MSGA_EN; + break; + case PCI_EXP_OBFF_SIGNAL_ALWAYS: + ctrl &= ~PCI_EXP_OBFF_WAKE_EN; + ctrl |= PCI_EXP_OBFF_MSGB_EN; + break; + default: + WARN(1, "bad OBFF signal type\n"); + return -ENOTSUPP; + } + } + pci_write_config_word(dev, pos + PCI_EXP_DEVCTL2, ctrl); + + return 0; +} +EXPORT_SYMBOL(pci_enable_obff); + +/** + * pci_disable_obff - disable optimized buffer flush/fill + * @dev: PCI device + * + * Disable OBFF on @dev. + */ +void pci_disable_obff(struct pci_dev *dev) +{ + int pos; + u16 ctrl; + + if (!pci_is_pcie(dev)) + return; + + pos = pci_pcie_cap(dev); + if (!pos) + return; + + pci_read_config_word(dev, pos + PCI_EXP_DEVCTL2, &ctrl); + ctrl &= ~PCI_EXP_OBFF_WAKE_EN; + pci_write_config_word(dev, pos + PCI_EXP_DEVCTL2, ctrl); +} +EXPORT_SYMBOL(pci_disable_obff); + +/** + * pci_ltr_supported - check whether a device supports LTR + * @dev: PCI device + * + * RETURNS: + * True if @dev supports latency tolerance reporting, false otherwise. + */ +bool pci_ltr_supported(struct pci_dev *dev) +{ + int pos; + u32 cap; + + if (!pci_is_pcie(dev)) + return false; + + pos = pci_pcie_cap(dev); + if (!pos) + return false; + + pci_read_config_dword(dev, pos + PCI_EXP_DEVCAP2, &cap); + + return cap & PCI_EXP_DEVCAP2_LTR; +} +EXPORT_SYMBOL(pci_ltr_supported); + +/** + * pci_enable_ltr - enable latency tolerance reporting + * @dev: PCI device + * + * Enable LTR on @dev if possible, which means enabling it first on + * upstream ports. + * + * RETURNS: + * Zero on success, errno on failure. + */ +int pci_enable_ltr(struct pci_dev *dev) +{ + int pos; + u16 ctrl; + int ret; + + if (!pci_ltr_supported(dev)) + return -ENOTSUPP; + + pos = pci_pcie_cap(dev); + if (!pos) + return -ENOTSUPP; + + /* Only primary function can enable/disable LTR */ + if (PCI_FUNC(dev->devfn) != 0) + return -EINVAL; + + /* Enable upstream ports first */ + if (dev->bus) { + ret = pci_enable_ltr(dev->bus->self); + if (ret) + return ret; + } + + pci_read_config_word(dev, pos + PCI_EXP_DEVCTL2, &ctrl); + ctrl |= PCI_EXP_LTR_EN; + pci_write_config_word(dev, pos + PCI_EXP_DEVCTL2, ctrl); + + return 0; +} +EXPORT_SYMBOL(pci_enable_ltr); + +/** + * pci_disable_ltr - disable latency tolerance reporting + * @dev: PCI device + */ +void pci_disable_ltr(struct pci_dev *dev) +{ + int pos; + u16 ctrl; + + if (!pci_ltr_supported(dev)) + return; + + pos = pci_pcie_cap(dev); + if (!pos) + return; + + /* Only primary function can enable/disable LTR */ + if (PCI_FUNC(dev->devfn) != 0) + return; + + pci_read_config_word(dev, pos + PCI_EXP_DEVCTL2, &ctrl); + ctrl &= ~PCI_EXP_LTR_EN; + pci_write_config_word(dev, pos + PCI_EXP_DEVCTL2, ctrl); +} +EXPORT_SYMBOL(pci_disable_ltr); + +static int __pci_ltr_scale(int *val) +{ + int scale = 0; + + while (*val > 1023) { + *val = (*val + 31) / 32; + scale++; + } + return scale; +} + +/** + * pci_set_ltr - set LTR latency values + * @dev: PCI device + * @snoop_lat_ns: snoop latency in nanoseconds + * @nosnoop_lat_ns: nosnoop latency in nanoseconds + * + * Figure out the scale and set the LTR values accordingly. + */ +int pci_set_ltr(struct pci_dev *dev, int snoop_lat_ns, int nosnoop_lat_ns) +{ + int pos, ret, snoop_scale, nosnoop_scale; + u16 val; + + if (!pci_ltr_supported(dev)) + return -ENOTSUPP; + + snoop_scale = __pci_ltr_scale(&snoop_lat_ns); + nosnoop_scale = __pci_ltr_scale(&nosnoop_lat_ns); + + if (snoop_lat_ns > PCI_LTR_VALUE_MASK || + nosnoop_lat_ns > PCI_LTR_VALUE_MASK) + return -EINVAL; + + if ((snoop_scale > (PCI_LTR_SCALE_MASK >> PCI_LTR_SCALE_SHIFT)) || + (nosnoop_scale > (PCI_LTR_SCALE_MASK >> PCI_LTR_SCALE_SHIFT))) + return -EINVAL; + + pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_LTR); + if (!pos) + return -ENOTSUPP; + + val = (snoop_scale << PCI_LTR_SCALE_SHIFT) | snoop_lat_ns; + ret = pci_write_config_word(dev, pos + PCI_LTR_MAX_SNOOP_LAT, val); + if (ret != 4) + return -EIO; + + val = (nosnoop_scale << PCI_LTR_SCALE_SHIFT) | nosnoop_lat_ns; + ret = pci_write_config_word(dev, pos + PCI_LTR_MAX_NOSNOOP_LAT, val); + if (ret != 4) + return -EIO; + + return 0; +} +EXPORT_SYMBOL(pci_set_ltr); + static int pci_acs_enable; /** @@ -2479,6 +2873,21 @@ clear: return 0; } +/** + * pci_pm_reset - Put device into PCI_D3 and back into PCI_D0. + * @dev: Device to reset. + * @probe: If set, only check if the device can be reset this way. + * + * If @dev supports native PCI PM and its PCI_PM_CTRL_NO_SOFT_RESET flag is + * unset, it will be reinitialized internally when going from PCI_D3hot to + * PCI_D0. If that's the case and the device is not in a low-power state + * already, force it into PCI_D3hot and back to PCI_D0, causing it to be reset. + * + * NOTE: This causes the caller to sleep for twice the device power transition + * cooldown period, which for the D0->D3hot and D3hot->D0 transitions is 10 ms + * by devault (i.e. unless the @dev's d3_delay field has a different value). + * Moreover, only devices in D0 can be reset by this function. + */ static int pci_pm_reset(struct pci_dev *dev, int probe) { u16 csr; diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 4020025..731e202 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -156,8 +156,7 @@ static inline int pci_no_d1d2(struct pci_dev *dev) } extern struct device_attribute pci_dev_attrs[]; -extern struct device_attribute dev_attr_cpuaffinity; -extern struct device_attribute dev_attr_cpulistaffinity; +extern struct device_attribute pcibus_dev_attrs[]; #ifdef CONFIG_HOTPLUG extern struct bus_attribute pci_bus_attrs[]; #else diff --git a/drivers/pci/pcie/aer/aer_inject.c b/drivers/pci/pcie/aer/aer_inject.c index f62079f..95489cd 100644 --- a/drivers/pci/pcie/aer/aer_inject.c +++ b/drivers/pci/pcie/aer/aer_inject.c @@ -326,7 +326,7 @@ static int aer_inject(struct aer_error_inj *einj) unsigned long flags; unsigned int devfn = PCI_DEVFN(einj->dev, einj->fn); int pos_cap_err, rp_pos_cap_err; - u32 sever, cor_mask, uncor_mask, cor_mask_orig, uncor_mask_orig; + u32 sever, cor_mask, uncor_mask, cor_mask_orig = 0, uncor_mask_orig = 0; int ret = 0; dev = pci_get_domain_bus_and_slot((int)einj->domain, einj->bus, devfn); diff --git a/drivers/pci/pcie/aer/aerdrv.h b/drivers/pci/pcie/aer/aerdrv.h index 3eb7708..94a7598 100644 --- a/drivers/pci/pcie/aer/aerdrv.h +++ b/drivers/pci/pcie/aer/aerdrv.h @@ -114,15 +114,6 @@ extern void aer_print_error(struct pci_dev *dev, struct aer_err_info *info); extern void aer_print_port_info(struct pci_dev *dev, struct aer_err_info *info); extern irqreturn_t aer_irq(int irq, void *context); -#ifdef CONFIG_ACPI -extern int aer_osc_setup(struct pcie_device *pciedev); -#else -static inline int aer_osc_setup(struct pcie_device *pciedev) -{ - return 0; -} -#endif - #ifdef CONFIG_ACPI_APEI extern int pcie_aer_get_firmware_first(struct pci_dev *pci_dev); #else diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index eee09f7..6892601 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -608,7 +608,7 @@ void pcie_aspm_init_link_state(struct pci_dev *pdev) * the BIOS's expectation, we'll do so once pci_enable_device() is * called. */ - if (aspm_policy != POLICY_POWERSAVE) { + if (aspm_policy != POLICY_POWERSAVE || aspm_clear_state) { pcie_config_aspm_path(link); pcie_set_clkpm(link, policy_to_clkpm_state(link)); } @@ -734,7 +734,7 @@ void pcie_aspm_powersave_config_link(struct pci_dev *pdev) * pci_disable_link_state - disable pci device's link state, so the link will * never enter specific states */ -void pci_disable_link_state(struct pci_dev *pdev, int state) +static void __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem) { struct pci_dev *parent = pdev->bus->self; struct pcie_link_state *link; @@ -747,7 +747,8 @@ void pci_disable_link_state(struct pci_dev *pdev, int state) if (!parent || !parent->link_state) return; - down_read(&pci_bus_sem); + if (sem) + down_read(&pci_bus_sem); mutex_lock(&aspm_lock); link = parent->link_state; if (state & PCIE_LINK_STATE_L0S) @@ -761,7 +762,19 @@ void pci_disable_link_state(struct pci_dev *pdev, int state) pcie_set_clkpm(link, 0); } mutex_unlock(&aspm_lock); - up_read(&pci_bus_sem); + if (sem) + up_read(&pci_bus_sem); +} + +void pci_disable_link_state_locked(struct pci_dev *pdev, int state) +{ + __pci_disable_link_state(pdev, state, false); +} +EXPORT_SYMBOL(pci_disable_link_state_locked); + +void pci_disable_link_state(struct pci_dev *pdev, int state) +{ + __pci_disable_link_state(pdev, state, true); } EXPORT_SYMBOL(pci_disable_link_state); diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 44cbbba..48849ff 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -43,43 +43,6 @@ int no_pci_devices(void) EXPORT_SYMBOL(no_pci_devices); /* - * PCI Bus Class Devices - */ -static ssize_t pci_bus_show_cpuaffinity(struct device *dev, - int type, - struct device_attribute *attr, - char *buf) -{ - int ret; - const struct cpumask *cpumask; - - cpumask = cpumask_of_pcibus(to_pci_bus(dev)); - ret = type? - cpulist_scnprintf(buf, PAGE_SIZE-2, cpumask) : - cpumask_scnprintf(buf, PAGE_SIZE-2, cpumask); - buf[ret++] = '\n'; - buf[ret] = '\0'; - return ret; -} - -static ssize_t inline pci_bus_show_cpumaskaffinity(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - return pci_bus_show_cpuaffinity(dev, 0, attr, buf); -} - -static ssize_t inline pci_bus_show_cpulistaffinity(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - return pci_bus_show_cpuaffinity(dev, 1, attr, buf); -} - -DEVICE_ATTR(cpuaffinity, S_IRUGO, pci_bus_show_cpumaskaffinity, NULL); -DEVICE_ATTR(cpulistaffinity, S_IRUGO, pci_bus_show_cpulistaffinity, NULL); - -/* * PCI Bus Class */ static void release_pcibus_dev(struct device *dev) @@ -95,6 +58,7 @@ static void release_pcibus_dev(struct device *dev) static struct class pcibus_class = { .name = "pci_bus", .dev_release = &release_pcibus_dev, + .dev_attrs = pcibus_dev_attrs, }; static int __init pcibus_class_init(void) @@ -1455,9 +1419,6 @@ struct pci_bus * pci_create_bus(struct device *parent, error = device_register(&b->dev); if (error) goto class_dev_reg_err; - error = device_create_file(&b->dev, &dev_attr_cpuaffinity); - if (error) - goto dev_create_file_err; /* Create legacy_io and legacy_mem files for this bus */ pci_create_legacy_files(b); @@ -1468,8 +1429,6 @@ struct pci_bus * pci_create_bus(struct device *parent, return b; -dev_create_file_err: - device_unregister(&b->dev); class_dev_reg_err: device_unregister(dev); dev_reg_err: diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 5129ed6..e8a1406 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -606,7 +606,7 @@ static void __devinit ich6_lpc_acpi_gpio(struct pci_dev *dev) } pci_read_config_byte(dev, ICH6_GPIO_CNTL, &enable); - if (enable & ICH4_GPIO_EN) { + if (enable & ICH6_GPIO_EN) { pci_read_config_dword(dev, ICH6_GPIOBASE, ®ion); region &= PCI_BASE_ADDRESS_IO_MASK; if (region >= PCIBIOS_MIN_IO) @@ -681,7 +681,7 @@ static void __devinit ich7_lpc_generic_decode(struct pci_dev *dev, unsigned reg, /* ICH7-10 has the same common LPC generic IO decode registers */ static void __devinit quirk_ich7_lpc(struct pci_dev *dev) { - /* We share the common ACPI/DPIO decode with ICH6 */ + /* We share the common ACPI/GPIO decode with ICH6 */ ich6_lpc_acpi_gpio(dev); /* And have 4 ICH7+ generic decodes */ @@ -2349,8 +2349,11 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_8132_BRIDGE, */ static void __devinit nvenet_msi_disable(struct pci_dev *dev) { - if (dmi_name_in_vendors("P5N32-SLI PREMIUM") || - dmi_name_in_vendors("P5N32-E SLI")) { + const char *board_name = dmi_get_system_info(DMI_BOARD_NAME); + + if (board_name && + (strstr(board_name, "P5N32-SLI PREMIUM") || + strstr(board_name, "P5N32-E SLI"))) { dev_info(&dev->dev, "Disabling msi for MCP55 NIC on P5N32-SLI\n"); dev->no_msi = 1; @@ -2784,6 +2787,16 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x342e, vtd_mask_spec_errors); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x3c28, vtd_mask_spec_errors); #endif +static void __devinit fixup_ti816x_class(struct pci_dev* dev) +{ + /* TI 816x devices do not have class code set when in PCIe boot mode */ + if (dev->class == PCI_CLASS_NOT_DEFINED) { + dev_info(&dev->dev, "Setting PCI class for 816x PCIe device\n"); + dev->class = PCI_CLASS_MULTIMEDIA_VIDEO; + } +} +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_TI, 0xb800, fixup_ti816x_class); + static void pci_do_fixups(struct pci_dev *dev, struct pci_fixup *f, struct pci_fixup *end) { diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c index 176615e..7f87bee 100644 --- a/drivers/pci/remove.c +++ b/drivers/pci/remove.c @@ -73,8 +73,6 @@ void pci_remove_bus(struct pci_bus *pci_bus) return; pci_remove_legacy_files(pci_bus); - device_remove_file(&pci_bus->dev, &dev_attr_cpuaffinity); - device_remove_file(&pci_bus->dev, &dev_attr_cpulistaffinity); device_unregister(&pci_bus->dev); } EXPORT_SYMBOL(pci_remove_bus); diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c index a806cb3..1e9e5a5 100644 --- a/drivers/pci/setup-bus.c +++ b/drivers/pci/setup-bus.c @@ -991,30 +991,139 @@ static void pci_bus_dump_resources(struct pci_bus *bus) } } +static int __init pci_bus_get_depth(struct pci_bus *bus) +{ + int depth = 0; + struct pci_dev *dev; + + list_for_each_entry(dev, &bus->devices, bus_list) { + int ret; + struct pci_bus *b = dev->subordinate; + if (!b) + continue; + + ret = pci_bus_get_depth(b); + if (ret + 1 > depth) + depth = ret + 1; + } + + return depth; +} +static int __init pci_get_max_depth(void) +{ + int depth = 0; + struct pci_bus *bus; + + list_for_each_entry(bus, &pci_root_buses, node) { + int ret; + + ret = pci_bus_get_depth(bus); + if (ret > depth) + depth = ret; + } + + return depth; +} + +/* + * first try will not touch pci bridge res + * second and later try will clear small leaf bridge res + * will stop till to the max deepth if can not find good one + */ void __init pci_assign_unassigned_resources(void) { struct pci_bus *bus; struct resource_list_x add_list; /* list of resources that want additional resources */ + int tried_times = 0; + enum release_type rel_type = leaf_only; + struct resource_list_x head, *list; + unsigned long type_mask = IORESOURCE_IO | IORESOURCE_MEM | + IORESOURCE_PREFETCH; + unsigned long failed_type; + int max_depth = pci_get_max_depth(); + int pci_try_num; + + + head.next = NULL; add_list.next = NULL; + + pci_try_num = max_depth + 1; + printk(KERN_DEBUG "PCI: max bus depth: %d pci_try_num: %d\n", + max_depth, pci_try_num); + +again: /* Depth first, calculate sizes and alignments of all subordinate buses. */ - list_for_each_entry(bus, &pci_root_buses, node) { + list_for_each_entry(bus, &pci_root_buses, node) __pci_bus_size_bridges(bus, &add_list); - } /* Depth last, allocate resources and update the hardware. */ - list_for_each_entry(bus, &pci_root_buses, node) { - __pci_bus_assign_resources(bus, &add_list, NULL); - pci_enable_bridges(bus); - } + list_for_each_entry(bus, &pci_root_buses, node) + __pci_bus_assign_resources(bus, &add_list, &head); BUG_ON(add_list.next); + tried_times++; + + /* any device complain? */ + if (!head.next) + goto enable_and_dump; + failed_type = 0; + for (list = head.next; list;) { + failed_type |= list->flags; + list = list->next; + } + /* + * io port are tight, don't try extra + * or if reach the limit, don't want to try more + */ + failed_type &= type_mask; + if ((failed_type == IORESOURCE_IO) || (tried_times >= pci_try_num)) { + free_list(resource_list_x, &head); + goto enable_and_dump; + } + + printk(KERN_DEBUG "PCI: No. %d try to assign unassigned res\n", + tried_times + 1); + + /* third times and later will not check if it is leaf */ + if ((tried_times + 1) > 2) + rel_type = whole_subtree; + + /* + * Try to release leaf bridge's resources that doesn't fit resource of + * child device under that bridge + */ + for (list = head.next; list;) { + bus = list->dev->bus; + pci_bus_release_bridge_resources(bus, list->flags & type_mask, + rel_type); + list = list->next; + } + /* restore size and flags */ + for (list = head.next; list;) { + struct resource *res = list->res; + + res->start = list->start; + res->end = list->end; + res->flags = list->flags; + if (list->dev->subordinate) + res->flags = 0; + + list = list->next; + } + free_list(resource_list_x, &head); + + goto again; + +enable_and_dump: + /* Depth last, update the hardware. */ + list_for_each_entry(bus, &pci_root_buses, node) + pci_enable_bridges(bus); /* dump the resource on buses */ - list_for_each_entry(bus, &pci_root_buses, node) { + list_for_each_entry(bus, &pci_root_buses, node) pci_bus_dump_resources(bus); - } } void pci_assign_unassigned_bridge_resources(struct pci_dev *bridge) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index b9c3299..31ebb59 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -517,6 +517,7 @@ struct kvm_assigned_dev_kernel { struct kvm *kvm; spinlock_t intx_lock; char irq_name[32]; + struct pci_saved_state *pci_saved_state; }; struct kvm_irq_mask_notifier { diff --git a/include/linux/pci-aspm.h b/include/linux/pci-aspm.h index 67cb3ae..7cea7b6 100644 --- a/include/linux/pci-aspm.h +++ b/include/linux/pci-aspm.h @@ -28,6 +28,7 @@ extern void pcie_aspm_exit_link_state(struct pci_dev *pdev); extern void pcie_aspm_pm_state_change(struct pci_dev *pdev); extern void pcie_aspm_powersave_config_link(struct pci_dev *pdev); extern void pci_disable_link_state(struct pci_dev *pdev, int state); +extern void pci_disable_link_state_locked(struct pci_dev *pdev, int state); extern void pcie_clear_aspm(void); extern void pcie_no_aspm(void); #else diff --git a/include/linux/pci.h b/include/linux/pci.h index 96f70d7..4604d1d 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -214,12 +214,17 @@ enum pci_bus_speed { PCI_SPEED_UNKNOWN = 0xff, }; -struct pci_cap_saved_state { - struct hlist_node next; +struct pci_cap_saved_data { char cap_nr; + unsigned int size; u32 data[0]; }; +struct pci_cap_saved_state { + struct hlist_node next; + struct pci_cap_saved_data cap; +}; + struct pcie_link_state; struct pci_vpd; struct pci_sriov; @@ -366,7 +371,7 @@ static inline struct pci_cap_saved_state *pci_find_saved_cap( struct hlist_node *pos; hlist_for_each_entry(tmp, pos, &pci_dev->saved_cap_space, next) { - if (tmp->cap_nr == cap) + if (tmp->cap.cap_nr == cap) return tmp; } return NULL; @@ -807,6 +812,10 @@ size_t pci_get_rom_size(struct pci_dev *pdev, void __iomem *rom, size_t size); /* Power management related routines */ int pci_save_state(struct pci_dev *dev); void pci_restore_state(struct pci_dev *dev); +struct pci_saved_state *pci_store_saved_state(struct pci_dev *dev); +int pci_load_saved_state(struct pci_dev *dev, struct pci_saved_state *state); +int pci_load_and_free_saved_state(struct pci_dev *dev, + struct pci_saved_state **state); int __pci_complete_power_transition(struct pci_dev *dev, pci_power_t state); int pci_set_power_state(struct pci_dev *dev, pci_power_t state); pci_power_t pci_choose_state(struct pci_dev *dev, pm_message_t state); @@ -828,6 +837,23 @@ static inline int pci_enable_wake(struct pci_dev *dev, pci_power_t state, return __pci_enable_wake(dev, state, false, enable); } +#define PCI_EXP_IDO_REQUEST (1<<0) +#define PCI_EXP_IDO_COMPLETION (1<<1) +void pci_enable_ido(struct pci_dev *dev, unsigned long type); +void pci_disable_ido(struct pci_dev *dev, unsigned long type); + +enum pci_obff_signal_type { + PCI_EXP_OBFF_SIGNAL_L0, + PCI_EXP_OBFF_SIGNAL_ALWAYS, +}; +int pci_enable_obff(struct pci_dev *dev, enum pci_obff_signal_type); +void pci_disable_obff(struct pci_dev *dev); + +bool pci_ltr_supported(struct pci_dev *dev); +int pci_enable_ltr(struct pci_dev *dev); +void pci_disable_ltr(struct pci_dev *dev); +int pci_set_ltr(struct pci_dev *dev, int snoop_lat_ns, int nosnoop_lat_ns); + /* For use by arch with custom probe code */ void set_pcie_port_type(struct pci_dev *pdev); void set_pcie_hotplug_bridge(struct pci_dev *pdev); @@ -1207,6 +1233,23 @@ static inline int pci_enable_wake(struct pci_dev *dev, pci_power_t state, return 0; } +static inline void pci_enable_ido(struct pci_dev *dev, unsigned long type) +{ +} + +static inline void pci_disable_ido(struct pci_dev *dev, unsigned long type) +{ +} + +static inline int pci_enable_obff(struct pci_dev *dev, unsigned long type) +{ + return 0; +} + +static inline void pci_disable_obff(struct pci_dev *dev) +{ +} + static inline int pci_request_regions(struct pci_dev *dev, const char *res_name) { return -EIO; diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 8652a4f..24787b7 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2483,6 +2483,8 @@ #define PCI_DEVICE_ID_INTEL_COUGARPOINT_LPC_MAX 0x1c5f #define PCI_DEVICE_ID_INTEL_PATSBURG_LPC_0 0x1d40 #define PCI_DEVICE_ID_INTEL_PATSBURG_LPC_1 0x1d41 +#define PCI_DEVICE_ID_INTEL_PANTHERPOINT_LPC_MIN 0x1e40 +#define PCI_DEVICE_ID_INTEL_PANTHERPOINT_LPC_MAX 0x1e5f #define PCI_DEVICE_ID_INTEL_DH89XXCC_LPC_MIN 0x2310 #define PCI_DEVICE_ID_INTEL_DH89XXCC_LPC_MAX 0x231f #define PCI_DEVICE_ID_INTEL_82801AA_0 0x2410 diff --git a/include/linux/pci_regs.h b/include/linux/pci_regs.h index be01380..e884096 100644 --- a/include/linux/pci_regs.h +++ b/include/linux/pci_regs.h @@ -508,8 +508,18 @@ #define PCI_EXP_RTSTA_PENDING 0x20000 /* PME pending */ #define PCI_EXP_DEVCAP2 36 /* Device Capabilities 2 */ #define PCI_EXP_DEVCAP2_ARI 0x20 /* Alternative Routing-ID */ +#define PCI_EXP_DEVCAP2_LTR 0x800 /* Latency tolerance reporting */ +#define PCI_EXP_OBFF_MASK 0xc0000 /* OBFF support mechanism */ +#define PCI_EXP_OBFF_MSG 0x40000 /* New message signaling */ +#define PCI_EXP_OBFF_WAKE 0x80000 /* Re-use WAKE# for OBFF */ #define PCI_EXP_DEVCTL2 40 /* Device Control 2 */ #define PCI_EXP_DEVCTL2_ARI 0x20 /* Alternative Routing-ID */ +#define PCI_EXP_IDO_REQ_EN 0x100 /* ID-based ordering request enable */ +#define PCI_EXP_IDO_CMP_EN 0x200 /* ID-based ordering completion enable */ +#define PCI_EXP_LTR_EN 0x400 /* Latency tolerance reporting */ +#define PCI_EXP_OBFF_MSGA_EN 0x2000 /* OBFF enable with Message type A */ +#define PCI_EXP_OBFF_MSGB_EN 0x4000 /* OBFF enable with Message type B */ +#define PCI_EXP_OBFF_WAKE_EN 0x6000 /* OBFF using WAKE# signaling */ #define PCI_EXP_LNKCTL2 48 /* Link Control 2 */ #define PCI_EXP_SLTCTL2 56 /* Slot Control 2 */ @@ -527,6 +537,7 @@ #define PCI_EXT_CAP_ID_ARI 14 #define PCI_EXT_CAP_ID_ATS 15 #define PCI_EXT_CAP_ID_SRIOV 16 +#define PCI_EXT_CAP_ID_LTR 24 /* Advanced Error Reporting */ #define PCI_ERR_UNCOR_STATUS 4 /* Uncorrectable Error Status */ @@ -683,6 +694,12 @@ #define PCI_SRIOV_VFM_MO 0x2 /* Active.MigrateOut */ #define PCI_SRIOV_VFM_AV 0x3 /* Active.Available */ +#define PCI_LTR_MAX_SNOOP_LAT 0x4 +#define PCI_LTR_MAX_NOSNOOP_LAT 0x6 +#define PCI_LTR_VALUE_MASK 0x000003ff +#define PCI_LTR_SCALE_MASK 0x00001c00 +#define PCI_LTR_SCALE_SHIFT 10 + /* Access Control Service */ #define PCI_ACS_CAP 0x04 /* ACS Capability Register */ #define PCI_ACS_SV 0x01 /* Source Validation */ diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c index ae72ae6..6cc4b97 100644 --- a/virt/kvm/assigned-dev.c +++ b/virt/kvm/assigned-dev.c @@ -197,8 +197,13 @@ static void kvm_free_assigned_device(struct kvm *kvm, { kvm_free_assigned_irq(kvm, assigned_dev); - __pci_reset_function(assigned_dev->dev); - pci_restore_state(assigned_dev->dev); + pci_reset_function(assigned_dev->dev); + if (pci_load_and_free_saved_state(assigned_dev->dev, + &assigned_dev->pci_saved_state)) + printk(KERN_INFO "%s: Couldn't reload %s saved state\n", + __func__, dev_name(&assigned_dev->dev->dev)); + else + pci_restore_state(assigned_dev->dev); pci_release_regions(assigned_dev->dev); pci_disable_device(assigned_dev->dev); @@ -516,7 +521,10 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm, pci_reset_function(dev); pci_save_state(dev); - + match->pci_saved_state = pci_store_saved_state(dev); + if (!match->pci_saved_state) + printk(KERN_DEBUG "%s: Couldn't store %s saved state\n", + __func__, dev_name(&dev->dev)); match->assigned_dev_id = assigned_dev->assigned_dev_id; match->host_segnr = assigned_dev->segnr; match->host_busnr = assigned_dev->busnr; @@ -546,7 +554,9 @@ out: mutex_unlock(&kvm->lock); return r; out_list_del: - pci_restore_state(dev); + if (pci_load_and_free_saved_state(dev, &match->pci_saved_state)) + printk(KERN_INFO "%s: Couldn't reload %s saved state\n", + __func__, dev_name(&dev->dev)); list_del(&match->list); pci_release_regions(dev); out_disable: |