X-Git-Url: https://gerrit.opnfv.org/gerrit/gitweb?a=blobdiff_plain;f=kernel%2Fdrivers%2Fpci%2Fpci.c;fp=kernel%2Fdrivers%2Fpci%2Fpci.c;h=42d8617352ae8dff39ce7b56d75b3ac9631fa6f4;hb=e09b41010ba33a20a87472ee821fa407a5b8da36;hp=c44393f26fd377730dccb52d75b20b7c0937399f;hpb=f93b97fd65072de626c074dbe099a1fff05ce060;p=kvmfornfv.git diff --git a/kernel/drivers/pci/pci.c b/kernel/drivers/pci/pci.c index c44393f26..42d861735 100644 --- a/kernel/drivers/pci/pci.c +++ b/kernel/drivers/pci/pci.c @@ -27,6 +27,7 @@ #include #include #include +#include #include "pci.h" const char *pci_power_names[] = { @@ -81,7 +82,7 @@ unsigned long pci_cardbus_mem_size = DEFAULT_CARDBUS_MEM_SIZE; unsigned long pci_hotplug_io_size = DEFAULT_HOTPLUG_IO_SIZE; unsigned long pci_hotplug_mem_size = DEFAULT_HOTPLUG_MEM_SIZE; -enum pcie_bus_config_types pcie_bus_config = PCIE_BUS_TUNE_OFF; +enum pcie_bus_config_types pcie_bus_config = PCIE_BUS_DEFAULT; /* * The default CLS is used if arch didn't set CLS explicitly and not @@ -138,9 +139,22 @@ void __iomem *pci_ioremap_bar(struct pci_dev *pdev, int bar) return ioremap_nocache(res->start, resource_size(res)); } EXPORT_SYMBOL_GPL(pci_ioremap_bar); + +void __iomem *pci_ioremap_wc_bar(struct pci_dev *pdev, int bar) +{ + /* + * Make sure the BAR is actually a memory resource, not an IO resource + */ + if (!(pci_resource_flags(pdev, bar) & IORESOURCE_MEM)) { + WARN_ON(1); + return NULL; + } + return ioremap_wc(pci_resource_start(pdev, bar), + pci_resource_len(pdev, bar)); +} +EXPORT_SYMBOL_GPL(pci_ioremap_wc_bar); #endif -#define PCI_FIND_CAP_TTL 48 static int __pci_find_next_cap_ttl(struct pci_bus *bus, unsigned int devfn, u8 pos, int cap, int *ttl) @@ -196,8 +210,6 @@ static int __pci_bus_find_cap_start(struct pci_bus *bus, return PCI_CAPABILITY_LIST; case PCI_HEADER_TYPE_CARDBUS: return PCI_CB_CAPABILITY_LIST; - default: - return 0; } return 0; @@ -446,6 +458,30 @@ struct resource *pci_find_parent_resource(const struct pci_dev *dev, } EXPORT_SYMBOL(pci_find_parent_resource); +/** + * pci_find_pcie_root_port - return PCIe Root Port + * @dev: PCI device to query + * + * Traverse up the parent chain and return the PCIe Root Port PCI Device + * for a given PCI Device. + */ +struct pci_dev *pci_find_pcie_root_port(struct pci_dev *dev) +{ + struct pci_dev *bridge, *highest_pcie_bridge = NULL; + + bridge = pci_upstream_bridge(dev); + while (bridge && pci_is_pcie(bridge)) { + highest_pcie_bridge = bridge; + bridge = pci_upstream_bridge(bridge); + } + + if (pci_pcie_type(highest_pcie_bridge) != PCI_EXP_TYPE_ROOT_PORT) + return NULL; + + return highest_pcie_bridge; +} +EXPORT_SYMBOL(pci_find_pcie_root_port); + /** * pci_wait_for_pending - wait for @mask bit(s) to clear in status word @pos * @dev: the PCI device to operate on @@ -473,7 +509,7 @@ int pci_wait_for_pending(struct pci_dev *dev, int pos, u16 mask) } /** - * pci_restore_bars - restore a devices BAR values (e.g. after wake-up) + * pci_restore_bars - restore a device's BAR values (e.g. after wake-up) * @dev: PCI device to have its BARs restored * * Restore the BAR values for a given device, so as to make it @@ -483,6 +519,10 @@ static void pci_restore_bars(struct pci_dev *dev) { int i; + /* Per SR-IOV spec 3.4.1.11, VF BARs are RO zero */ + if (dev->is_virtfn) + return; + for (i = 0; i < PCI_BRIDGE_RESOURCES; i++) pci_update_resource(dev, i); } @@ -972,7 +1012,7 @@ static int pci_save_pcix_state(struct pci_dev *dev) struct pci_cap_saved_state *save_state; pos = pci_find_capability(dev, PCI_CAP_ID_PCIX); - if (pos <= 0) + if (!pos) return 0; save_state = pci_find_saved_cap(dev, PCI_CAP_ID_PCIX); @@ -995,7 +1035,7 @@ static void pci_restore_pcix_state(struct pci_dev *dev) save_state = pci_find_saved_cap(dev, PCI_CAP_ID_PCIX); pos = pci_find_capability(dev, PCI_CAP_ID_PCIX); - if (!save_state || pos <= 0) + if (!save_state || !pos) return; cap = (u16 *)&save_state->cap.data[0]; @@ -1088,10 +1128,15 @@ void pci_restore_state(struct pci_dev *dev) pci_restore_ats_state(dev); pci_restore_vc_state(dev); + pci_cleanup_aer_error_status_regs(dev); + pci_restore_config_space(dev); pci_restore_pcix_state(dev); pci_restore_msi_state(dev); + + /* Restore ACS and IOV configuration state */ + pci_enable_acs(dev); pci_restore_iov_state(dev); dev->state_saved = false; @@ -1696,15 +1741,7 @@ static void pci_pme_list_scan(struct work_struct *work) mutex_unlock(&pci_pme_list_mutex); } -/** - * pci_pme_active - enable or disable PCI device's PME# function - * @dev: PCI device to handle. - * @enable: 'true' to enable PME# generation; 'false' to disable it. - * - * The caller must verify that the device is capable of generating PME# before - * calling this function with @enable equal to 'true'. - */ -void pci_pme_active(struct pci_dev *dev, bool enable) +static void __pci_pme_active(struct pci_dev *dev, bool enable) { u16 pmcsr; @@ -1718,6 +1755,19 @@ void pci_pme_active(struct pci_dev *dev, bool enable) pmcsr &= ~PCI_PM_CTRL_PME_ENABLE; pci_write_config_word(dev, dev->pm_cap + PCI_PM_CTRL, pmcsr); +} + +/** + * pci_pme_active - enable or disable PCI device's PME# function + * @dev: PCI device to handle. + * @enable: 'true' to enable PME# generation; 'false' to disable it. + * + * The caller must verify that the device is capable of generating PME# before + * calling this function with @enable equal to 'true'. + */ +void pci_pme_active(struct pci_dev *dev, bool enable) +{ + __pci_pme_active(dev, enable); /* * PCI (as opposed to PCIe) PME requires that the device have @@ -2018,17 +2068,60 @@ EXPORT_SYMBOL_GPL(pci_dev_run_wake); * reconfigured due to wakeup settings difference between system and runtime * suspend and the current power state of it is suitable for the upcoming * (system) transition. + * + * If the device is not configured for system wakeup, disable PME for it before + * returning 'true' to prevent it from waking up the system unnecessarily. */ bool pci_dev_keep_suspended(struct pci_dev *pci_dev) { struct device *dev = &pci_dev->dev; if (!pm_runtime_suspended(dev) - || (device_can_wakeup(dev) && !device_may_wakeup(dev)) + || pci_target_state(pci_dev) != pci_dev->current_state || platform_pci_need_resume(pci_dev)) return false; - return pci_target_state(pci_dev) == pci_dev->current_state; + /* + * At this point the device is good to go unless it's been configured + * to generate PME at the runtime suspend time, but it is not supposed + * to wake up the system. In that case, simply disable PME for it + * (it will have to be re-enabled on exit from system resume). + * + * If the device's power state is D3cold and the platform check above + * hasn't triggered, the device's configuration is suitable and we don't + * need to manipulate it at all. + */ + spin_lock_irq(&dev->power.lock); + + if (pm_runtime_suspended(dev) && pci_dev->current_state < PCI_D3cold && + !device_may_wakeup(dev)) + __pci_pme_active(pci_dev, false); + + spin_unlock_irq(&dev->power.lock); + return true; +} + +/** + * pci_dev_complete_resume - Finalize resume from system sleep for a device. + * @pci_dev: Device to handle. + * + * If the device is runtime suspended and wakeup-capable, enable PME for it as + * it might have been disabled during the prepare phase of system suspend if + * the device was not configured for system wakeup. + */ +void pci_dev_complete_resume(struct pci_dev *pci_dev) +{ + struct device *dev = &pci_dev->dev; + + if (!pci_dev_run_wake(pci_dev)) + return; + + spin_lock_irq(&dev->power.lock); + + if (pm_runtime_suspended(dev) && pci_dev->current_state < PCI_D3cold) + __pci_pme_active(pci_dev, true); + + spin_unlock_irq(&dev->power.lock); } void pci_config_pm_runtime_get(struct pci_dev *pdev) @@ -2134,6 +2227,198 @@ void pci_pm_init(struct pci_dev *dev) } } +static unsigned long pci_ea_flags(struct pci_dev *dev, u8 prop) +{ + unsigned long flags = IORESOURCE_PCI_FIXED; + + switch (prop) { + case PCI_EA_P_MEM: + case PCI_EA_P_VF_MEM: + flags |= IORESOURCE_MEM; + break; + case PCI_EA_P_MEM_PREFETCH: + case PCI_EA_P_VF_MEM_PREFETCH: + flags |= IORESOURCE_MEM | IORESOURCE_PREFETCH; + break; + case PCI_EA_P_IO: + flags |= IORESOURCE_IO; + break; + default: + return 0; + } + + return flags; +} + +static struct resource *pci_ea_get_resource(struct pci_dev *dev, u8 bei, + u8 prop) +{ + if (bei <= PCI_EA_BEI_BAR5 && prop <= PCI_EA_P_IO) + return &dev->resource[bei]; +#ifdef CONFIG_PCI_IOV + else if (bei >= PCI_EA_BEI_VF_BAR0 && bei <= PCI_EA_BEI_VF_BAR5 && + (prop == PCI_EA_P_VF_MEM || prop == PCI_EA_P_VF_MEM_PREFETCH)) + return &dev->resource[PCI_IOV_RESOURCES + + bei - PCI_EA_BEI_VF_BAR0]; +#endif + else if (bei == PCI_EA_BEI_ROM) + return &dev->resource[PCI_ROM_RESOURCE]; + else + return NULL; +} + +/* Read an Enhanced Allocation (EA) entry */ +static int pci_ea_read(struct pci_dev *dev, int offset) +{ + struct resource *res; + int ent_size, ent_offset = offset; + resource_size_t start, end; + unsigned long flags; + u32 dw0, bei, base, max_offset; + u8 prop; + bool support_64 = (sizeof(resource_size_t) >= 8); + + pci_read_config_dword(dev, ent_offset, &dw0); + ent_offset += 4; + + /* Entry size field indicates DWORDs after 1st */ + ent_size = ((dw0 & PCI_EA_ES) + 1) << 2; + + if (!(dw0 & PCI_EA_ENABLE)) /* Entry not enabled */ + goto out; + + bei = (dw0 & PCI_EA_BEI) >> 4; + prop = (dw0 & PCI_EA_PP) >> 8; + + /* + * If the Property is in the reserved range, try the Secondary + * Property instead. + */ + if (prop > PCI_EA_P_BRIDGE_IO && prop < PCI_EA_P_MEM_RESERVED) + prop = (dw0 & PCI_EA_SP) >> 16; + if (prop > PCI_EA_P_BRIDGE_IO) + goto out; + + res = pci_ea_get_resource(dev, bei, prop); + if (!res) { + dev_err(&dev->dev, "Unsupported EA entry BEI: %u\n", bei); + goto out; + } + + flags = pci_ea_flags(dev, prop); + if (!flags) { + dev_err(&dev->dev, "Unsupported EA properties: %#x\n", prop); + goto out; + } + + /* Read Base */ + pci_read_config_dword(dev, ent_offset, &base); + start = (base & PCI_EA_FIELD_MASK); + ent_offset += 4; + + /* Read MaxOffset */ + pci_read_config_dword(dev, ent_offset, &max_offset); + ent_offset += 4; + + /* Read Base MSBs (if 64-bit entry) */ + if (base & PCI_EA_IS_64) { + u32 base_upper; + + pci_read_config_dword(dev, ent_offset, &base_upper); + ent_offset += 4; + + flags |= IORESOURCE_MEM_64; + + /* entry starts above 32-bit boundary, can't use */ + if (!support_64 && base_upper) + goto out; + + if (support_64) + start |= ((u64)base_upper << 32); + } + + end = start + (max_offset | 0x03); + + /* Read MaxOffset MSBs (if 64-bit entry) */ + if (max_offset & PCI_EA_IS_64) { + u32 max_offset_upper; + + pci_read_config_dword(dev, ent_offset, &max_offset_upper); + ent_offset += 4; + + flags |= IORESOURCE_MEM_64; + + /* entry too big, can't use */ + if (!support_64 && max_offset_upper) + goto out; + + if (support_64) + end += ((u64)max_offset_upper << 32); + } + + if (end < start) { + dev_err(&dev->dev, "EA Entry crosses address boundary\n"); + goto out; + } + + if (ent_size != ent_offset - offset) { + dev_err(&dev->dev, + "EA Entry Size (%d) does not match length read (%d)\n", + ent_size, ent_offset - offset); + goto out; + } + + res->name = pci_name(dev); + res->start = start; + res->end = end; + res->flags = flags; + + if (bei <= PCI_EA_BEI_BAR5) + dev_printk(KERN_DEBUG, &dev->dev, "BAR %d: %pR (from Enhanced Allocation, properties %#02x)\n", + bei, res, prop); + else if (bei == PCI_EA_BEI_ROM) + dev_printk(KERN_DEBUG, &dev->dev, "ROM: %pR (from Enhanced Allocation, properties %#02x)\n", + res, prop); + else if (bei >= PCI_EA_BEI_VF_BAR0 && bei <= PCI_EA_BEI_VF_BAR5) + dev_printk(KERN_DEBUG, &dev->dev, "VF BAR %d: %pR (from Enhanced Allocation, properties %#02x)\n", + bei - PCI_EA_BEI_VF_BAR0, res, prop); + else + dev_printk(KERN_DEBUG, &dev->dev, "BEI %d res: %pR (from Enhanced Allocation, properties %#02x)\n", + bei, res, prop); + +out: + return offset + ent_size; +} + +/* Enhanced Allocation Initalization */ +void pci_ea_init(struct pci_dev *dev) +{ + int ea; + u8 num_ent; + int offset; + int i; + + /* find PCI EA capability in list */ + ea = pci_find_capability(dev, PCI_CAP_ID_EA); + if (!ea) + return; + + /* determine the number of entries */ + pci_bus_read_config_byte(dev->bus, dev->devfn, ea + PCI_EA_NUM_ENT, + &num_ent); + num_ent &= PCI_EA_NUM_ENT_MASK; + + offset = ea + PCI_EA_FIRST_ENT; + + /* Skip DWORD 2 for type 1 functions */ + if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) + offset += 4; + + /* parse each EA entry */ + for (i = 0; i < num_ent; ++i) + offset = pci_ea_read(dev, offset); +} + static void pci_add_saved_cap(struct pci_dev *pci_dev, struct pci_cap_saved_state *new_cap) { @@ -2159,7 +2444,7 @@ static int _pci_add_cap_save_buffer(struct pci_dev *dev, u16 cap, else pos = pci_find_capability(dev, cap); - if (pos <= 0) + if (!pos) return 0; save_state = kzalloc(sizeof(*save_state) + size, GFP_KERNEL); @@ -3101,39 +3386,6 @@ bool pci_check_and_unmask_intx(struct pci_dev *dev) } EXPORT_SYMBOL_GPL(pci_check_and_unmask_intx); -/** - * pci_msi_off - disables any MSI or MSI-X capabilities - * @dev: the PCI device to operate on - * - * If you want to use MSI, see pci_enable_msi() and friends. - * This is a lower-level primitive that allows us to disable - * MSI operation at the device level. - */ -void pci_msi_off(struct pci_dev *dev) -{ - int pos; - u16 control; - - /* - * This looks like it could go in msi.c, but we need it even when - * CONFIG_PCI_MSI=n. For the same reason, we can't use - * dev->msi_cap or dev->msix_cap here. - */ - pos = pci_find_capability(dev, PCI_CAP_ID_MSI); - if (pos) { - pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &control); - control &= ~PCI_MSI_FLAGS_ENABLE; - pci_write_config_word(dev, pos + PCI_MSI_FLAGS, control); - } - pos = pci_find_capability(dev, PCI_CAP_ID_MSIX); - if (pos) { - pci_read_config_word(dev, pos + PCI_MSIX_FLAGS, &control); - control &= ~PCI_MSIX_FLAGS_ENABLE; - pci_write_config_word(dev, pos + PCI_MSIX_FLAGS, control); - } -} -EXPORT_SYMBOL_GPL(pci_msi_off); - int pci_set_dma_max_seg_size(struct pci_dev *dev, unsigned int size) { return dma_set_max_seg_size(&dev->dev, size); @@ -4520,8 +4772,10 @@ int pci_get_new_domain_nr(void) void pci_bus_assign_domain_nr(struct pci_bus *bus, struct device *parent) { static int use_dt_domains = -1; - int domain = of_get_pci_domain_nr(parent->of_node); + int domain = -1; + if (parent) + domain = of_get_pci_domain_nr(parent->of_node); /* * Check DT domain and use_dt_domains values. *