From: Bjorn Helgaas Date: Mon, 2 Nov 2015 21:57:03 +0000 (-0600) Subject: Merge branches 'pci/aer', 'pci/hotplug', 'pci/misc', 'pci/msi', 'pci/resource' and... X-Git-Tag: v4.4-rc1~91^2~3 X-Git-Url: https://git.kernelconcepts.de/?p=karo-tx-linux.git;a=commitdiff_plain;h=1f9a30ec2a4acee9a4d664e7405c7eb26a7c4b5e;hp=8affb487d4a4e223d961d7034cb41cd31982b618 Merge branches 'pci/aer', 'pci/hotplug', 'pci/misc', 'pci/msi', 'pci/resource' and 'pci/virtualization' into next * pci/aer: PCI/AER: Clear error status registers during enumeration and restore * pci/hotplug: PCI: pciehp: Queue power work requests in dedicated function * pci/misc: PCI: Turn off Request Attributes to avoid Chelsio T5 Completion erratum x86/PCI: Make pci_subsys_init() static PCI: Add builtin_pci_driver() to avoid registration boilerplate PCI: Remove unnecessary "if" statement * pci/msi: x86/PCI: Don't alloc pcibios-irq when MSI is enabled PCI/MSI: Export all remapped MSIs to sysfs attributes PCI: Disable MSI on SiS 761 * pci/resource: sparc/PCI: Add mem64 resource parsing for root bus PCI: Expand Enhanced Allocation BAR output PCI: Make Enhanced Allocation bitmasks more obvious PCI: Handle Enhanced Allocation capability for SR-IOV devices PCI: Add support for Enhanced Allocation devices PCI: Add Enhanced Allocation register entries PCI: Handle IORESOURCE_PCI_FIXED when assigning resources PCI: Handle IORESOURCE_PCI_FIXED when sizing resources PCI: Clear IORESOURCE_UNSET when reverting to firmware-assigned address * pci/virtualization: PCI: Fix sriov_enable() error path for pcibios_enable_sriov() failures PCI: Wait 1 second between disabling VFs and clearing NumVFs PCI: Reorder pcibios_sriov_disable() PCI: Remove VFs in reverse order if virtfn_add() fails PCI: Remove redundant validation of SR-IOV offset/stride registers PCI: Set SR-IOV NumVFs to zero after enumeration PCI: Enable SR-IOV ARI Capable Hierarchy before reading TotalVFs PCI: Don't try to restore VF BARs --- diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c index b91d7f146175..badf0951d73c 100644 --- a/arch/sparc/kernel/pci.c +++ b/arch/sparc/kernel/pci.c @@ -185,8 +185,10 @@ static unsigned long pci_parse_of_flags(u32 addr0) if (addr0 & 0x02000000) { flags = IORESOURCE_MEM | PCI_BASE_ADDRESS_SPACE_MEMORY; - flags |= (addr0 >> 22) & PCI_BASE_ADDRESS_MEM_TYPE_64; flags |= (addr0 >> 28) & PCI_BASE_ADDRESS_MEM_TYPE_1M; + if (addr0 & 0x01000000) + flags |= IORESOURCE_MEM_64 + | PCI_BASE_ADDRESS_MEM_TYPE_64; if (addr0 & 0x40000000) flags |= IORESOURCE_PREFETCH | PCI_BASE_ADDRESS_MEM_PREFETCH; @@ -655,6 +657,9 @@ struct pci_bus *pci_scan_one_pbm(struct pci_pbm_info *pbm, pbm->io_space.start); pci_add_resource_offset(&resources, &pbm->mem_space, pbm->mem_space.start); + if (pbm->mem64_space.flags) + pci_add_resource_offset(&resources, &pbm->mem64_space, + pbm->mem_space.start); pbm->busn.start = pbm->pci_first_busno; pbm->busn.end = pbm->pci_last_busno; pbm->busn.flags = IORESOURCE_BUS; diff --git a/arch/sparc/kernel/pci_common.c b/arch/sparc/kernel/pci_common.c index 944a06536ecc..33524c1d5328 100644 --- a/arch/sparc/kernel/pci_common.c +++ b/arch/sparc/kernel/pci_common.c @@ -406,6 +406,7 @@ void pci_determine_mem_io_space(struct pci_pbm_info *pbm) } num_pbm_ranges = i / sizeof(*pbm_ranges); + memset(&pbm->mem64_space, 0, sizeof(struct resource)); for (i = 0; i < num_pbm_ranges; i++) { const struct linux_prom_pci_ranges *pr = &pbm_ranges[i]; @@ -451,7 +452,12 @@ void pci_determine_mem_io_space(struct pci_pbm_info *pbm) break; case 3: - /* XXX 64-bit MEM handling XXX */ + /* 64-bit MEM handling */ + pbm->mem64_space.start = a; + pbm->mem64_space.end = a + size - 1UL; + pbm->mem64_space.flags = IORESOURCE_MEM; + saw_mem = 1; + break; default: break; @@ -465,15 +471,22 @@ void pci_determine_mem_io_space(struct pci_pbm_info *pbm) prom_halt(); } - printk("%s: PCI IO[%llx] MEM[%llx]\n", + printk("%s: PCI IO[%llx] MEM[%llx]", pbm->name, pbm->io_space.start, pbm->mem_space.start); + if (pbm->mem64_space.flags) + printk(" MEM64[%llx]", + pbm->mem64_space.start); + printk("\n"); pbm->io_space.name = pbm->mem_space.name = pbm->name; + pbm->mem64_space.name = pbm->name; request_resource(&ioport_resource, &pbm->io_space); request_resource(&iomem_resource, &pbm->mem_space); + if (pbm->mem64_space.flags) + request_resource(&iomem_resource, &pbm->mem64_space); pci_register_legacy_regions(&pbm->io_space, &pbm->mem_space); diff --git a/arch/sparc/kernel/pci_impl.h b/arch/sparc/kernel/pci_impl.h index 75803c780af3..37222ca849df 100644 --- a/arch/sparc/kernel/pci_impl.h +++ b/arch/sparc/kernel/pci_impl.h @@ -97,6 +97,7 @@ struct pci_pbm_info { /* PBM I/O and Memory space resources. */ struct resource io_space; struct resource mem_space; + struct resource mem64_space; struct resource busn; /* Base of PCI Config space, can be per-PBM or shared. */ 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/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c index f3796124ad7c..4c8f4cde6854 100644 --- a/drivers/pci/hotplug/pciehp_ctrl.c +++ b/drivers/pci/hotplug/pciehp_ctrl.c @@ -204,36 +204,39 @@ static void pciehp_power_thread(struct work_struct *work) kfree(info); } -void pciehp_queue_pushbutton_work(struct work_struct *work) +static void pciehp_queue_power_work(struct slot *p_slot, int req) { - struct slot *p_slot = container_of(work, struct slot, work.work); struct power_work_info *info; + p_slot->state = (req == ENABLE_REQ) ? POWERON_STATE : POWEROFF_STATE; + info = kmalloc(sizeof(*info), GFP_KERNEL); if (!info) { - ctrl_err(p_slot->ctrl, "%s: Cannot allocate memory\n", - __func__); + ctrl_err(p_slot->ctrl, "no memory to queue %s request\n", + (req == ENABLE_REQ) ? "poweron" : "poweroff"); return; } info->p_slot = p_slot; INIT_WORK(&info->work, pciehp_power_thread); + info->req = req; + queue_work(p_slot->wq, &info->work); +} + +void pciehp_queue_pushbutton_work(struct work_struct *work) +{ + struct slot *p_slot = container_of(work, struct slot, work.work); mutex_lock(&p_slot->lock); switch (p_slot->state) { case BLINKINGOFF_STATE: - p_slot->state = POWEROFF_STATE; - info->req = DISABLE_REQ; + pciehp_queue_power_work(p_slot, DISABLE_REQ); break; case BLINKINGON_STATE: - p_slot->state = POWERON_STATE; - info->req = ENABLE_REQ; + pciehp_queue_power_work(p_slot, ENABLE_REQ); break; default: - kfree(info); - goto out; + break; } - queue_work(p_slot->wq, &info->work); - out: mutex_unlock(&p_slot->lock); } @@ -301,27 +304,12 @@ static void handle_button_press_event(struct slot *p_slot) static void handle_surprise_event(struct slot *p_slot) { u8 getstatus; - struct power_work_info *info; - - info = kmalloc(sizeof(*info), GFP_KERNEL); - if (!info) { - ctrl_err(p_slot->ctrl, "%s: Cannot allocate memory\n", - __func__); - return; - } - info->p_slot = p_slot; - INIT_WORK(&info->work, pciehp_power_thread); pciehp_get_adapter_status(p_slot, &getstatus); - if (!getstatus) { - p_slot->state = POWEROFF_STATE; - info->req = DISABLE_REQ; - } else { - p_slot->state = POWERON_STATE; - info->req = ENABLE_REQ; - } - - queue_work(p_slot->wq, &info->work); + if (!getstatus) + pciehp_queue_power_work(p_slot, DISABLE_REQ); + else + pciehp_queue_power_work(p_slot, ENABLE_REQ); } /* @@ -330,17 +318,6 @@ static void handle_surprise_event(struct slot *p_slot) static void handle_link_event(struct slot *p_slot, u32 event) { struct controller *ctrl = p_slot->ctrl; - struct power_work_info *info; - - info = kmalloc(sizeof(*info), GFP_KERNEL); - if (!info) { - ctrl_err(p_slot->ctrl, "%s: Cannot allocate memory\n", - __func__); - return; - } - info->p_slot = p_slot; - info->req = event == INT_LINK_UP ? ENABLE_REQ : DISABLE_REQ; - INIT_WORK(&info->work, pciehp_power_thread); switch (p_slot->state) { case BLINKINGON_STATE: @@ -348,22 +325,19 @@ static void handle_link_event(struct slot *p_slot, u32 event) cancel_delayed_work(&p_slot->work); /* Fall through */ case STATIC_STATE: - p_slot->state = event == INT_LINK_UP ? - POWERON_STATE : POWEROFF_STATE; - queue_work(p_slot->wq, &info->work); + pciehp_queue_power_work(p_slot, event == INT_LINK_UP ? + ENABLE_REQ : DISABLE_REQ); break; case POWERON_STATE: if (event == INT_LINK_UP) { ctrl_info(ctrl, "Link Up event ignored on slot(%s): already powering on\n", slot_name(p_slot)); - kfree(info); } else { ctrl_info(ctrl, "Link Down event queued on slot(%s): currently getting powered on\n", slot_name(p_slot)); - p_slot->state = POWEROFF_STATE; - queue_work(p_slot->wq, &info->work); + pciehp_queue_power_work(p_slot, DISABLE_REQ); } break; case POWEROFF_STATE: @@ -371,19 +345,16 @@ static void handle_link_event(struct slot *p_slot, u32 event) ctrl_info(ctrl, "Link Up event queued on slot(%s): currently getting powered off\n", slot_name(p_slot)); - p_slot->state = POWERON_STATE; - queue_work(p_slot->wq, &info->work); + pciehp_queue_power_work(p_slot, ENABLE_REQ); } else { ctrl_info(ctrl, "Link Down event ignored on slot(%s): already powering off\n", slot_name(p_slot)); - kfree(info); } break; default: ctrl_err(ctrl, "ignoring invalid state %#x on slot(%s)\n", p_slot->state, slot_name(p_slot)); - kfree(info); break; } } diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c index ee0ebff103a4..31f31d460fc9 100644 --- a/drivers/pci/iov.c +++ b/drivers/pci/iov.c @@ -54,24 +54,29 @@ static inline void pci_iov_set_numvfs(struct pci_dev *dev, int nr_virtfn) * The PF consumes one bus number. NumVFs, First VF Offset, and VF Stride * determine how many additional bus numbers will be consumed by VFs. * - * Iterate over all valid NumVFs and calculate the maximum number of bus - * numbers that could ever be required. + * Iterate over all valid NumVFs, validate offset and stride, and calculate + * the maximum number of bus numbers that could ever be required. */ -static inline u8 virtfn_max_buses(struct pci_dev *dev) +static int compute_max_vf_buses(struct pci_dev *dev) { struct pci_sriov *iov = dev->sriov; - int nr_virtfn; - u8 max = 0; - int busnr; + int nr_virtfn, busnr, rc = 0; - for (nr_virtfn = 1; nr_virtfn <= iov->total_VFs; nr_virtfn++) { + for (nr_virtfn = iov->total_VFs; nr_virtfn; nr_virtfn--) { pci_iov_set_numvfs(dev, nr_virtfn); + if (!iov->offset || (nr_virtfn > 1 && !iov->stride)) { + rc = -EIO; + goto out; + } + busnr = pci_iov_virtfn_bus(dev, nr_virtfn - 1); - if (busnr > max) - max = busnr; + if (busnr > iov->max_VF_buses) + iov->max_VF_buses = busnr; } - return max; +out: + pci_iov_set_numvfs(dev, 0); + return rc; } static struct pci_bus *virtfn_add_bus(struct pci_bus *bus, int busnr) @@ -222,21 +227,25 @@ static void virtfn_remove(struct pci_dev *dev, int id, int reset) int __weak pcibios_sriov_enable(struct pci_dev *pdev, u16 num_vfs) { - return 0; + return 0; +} + +int __weak pcibios_sriov_disable(struct pci_dev *pdev) +{ + return 0; } static int sriov_enable(struct pci_dev *dev, int nr_virtfn) { int rc; - int i, j; + int i; int nres; - u16 offset, stride, initial; + u16 initial; struct resource *res; struct pci_dev *pdev; struct pci_sriov *iov = dev->sriov; int bars = 0; int bus; - int retval; if (!nr_virtfn) return 0; @@ -253,11 +262,6 @@ static int sriov_enable(struct pci_dev *dev, int nr_virtfn) (!(iov->cap & PCI_SRIOV_CAP_VFM) && (nr_virtfn > initial))) return -EINVAL; - pci_read_config_word(dev, iov->pos + PCI_SRIOV_VF_OFFSET, &offset); - pci_read_config_word(dev, iov->pos + PCI_SRIOV_VF_STRIDE, &stride); - if (!offset || (nr_virtfn > 1 && !stride)) - return -EIO; - nres = 0; for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { bars |= (1 << (i + PCI_IOV_RESOURCES)); @@ -270,9 +274,6 @@ static int sriov_enable(struct pci_dev *dev, int nr_virtfn) return -ENOMEM; } - iov->offset = offset; - iov->stride = stride; - bus = pci_iov_virtfn_bus(dev, nr_virtfn - 1); if (bus > dev->bus->busn_res.end) { dev_err(&dev->dev, "can't enable %d VFs (bus %02x out of range of %pR)\n", @@ -313,10 +314,10 @@ static int sriov_enable(struct pci_dev *dev, int nr_virtfn) if (nr_virtfn < initial) initial = nr_virtfn; - if ((retval = pcibios_sriov_enable(dev, initial))) { - dev_err(&dev->dev, "failure %d from pcibios_sriov_enable()\n", - retval); - return retval; + rc = pcibios_sriov_enable(dev, initial); + if (rc) { + dev_err(&dev->dev, "failure %d from pcibios_sriov_enable()\n", rc); + goto err_pcibios; } for (i = 0; i < initial; i++) { @@ -331,27 +332,24 @@ static int sriov_enable(struct pci_dev *dev, int nr_virtfn) return 0; failed: - for (j = 0; j < i; j++) - virtfn_remove(dev, j, 0); + while (i--) + virtfn_remove(dev, i, 0); + pcibios_sriov_disable(dev); +err_pcibios: iov->ctrl &= ~(PCI_SRIOV_CTRL_VFE | PCI_SRIOV_CTRL_MSE); pci_cfg_access_lock(dev); pci_write_config_word(dev, iov->pos + PCI_SRIOV_CTRL, iov->ctrl); - pci_iov_set_numvfs(dev, 0); ssleep(1); pci_cfg_access_unlock(dev); if (iov->link != dev->devfn) sysfs_remove_link(&dev->dev.kobj, "dep_link"); + pci_iov_set_numvfs(dev, 0); return rc; } -int __weak pcibios_sriov_disable(struct pci_dev *pdev) -{ - return 0; -} - static void sriov_disable(struct pci_dev *dev) { int i; @@ -384,7 +382,7 @@ static int sriov_init(struct pci_dev *dev, int pos) int rc; int nres; u32 pgsz; - u16 ctrl, total, offset, stride; + u16 ctrl, total; struct pci_sriov *iov; struct resource *res; struct pci_dev *pdev; @@ -399,10 +397,6 @@ static int sriov_init(struct pci_dev *dev, int pos) ssleep(1); } - pci_read_config_word(dev, pos + PCI_SRIOV_TOTAL_VF, &total); - if (!total) - return 0; - ctrl = 0; list_for_each_entry(pdev, &dev->bus->devices, bus_list) if (pdev->is_physfn) @@ -414,11 +408,10 @@ static int sriov_init(struct pci_dev *dev, int pos) found: pci_write_config_word(dev, pos + PCI_SRIOV_CTRL, ctrl); - pci_write_config_word(dev, pos + PCI_SRIOV_NUM_VF, 0); - pci_read_config_word(dev, pos + PCI_SRIOV_VF_OFFSET, &offset); - pci_read_config_word(dev, pos + PCI_SRIOV_VF_STRIDE, &stride); - if (!offset || (total > 1 && !stride)) - return -EIO; + + pci_read_config_word(dev, pos + PCI_SRIOV_TOTAL_VF, &total); + if (!total) + return 0; pci_read_config_dword(dev, pos + PCI_SRIOV_SUP_PGSIZE, &pgsz); i = PAGE_SHIFT > 12 ? PAGE_SHIFT - 12 : 0; @@ -436,8 +429,15 @@ found: nres = 0; for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { res = &dev->resource[i + PCI_IOV_RESOURCES]; - bar64 = __pci_read_base(dev, pci_bar_unknown, res, - pos + PCI_SRIOV_BAR + i * 4); + /* + * If it is already FIXED, don't change it, something + * (perhaps EA or header fixups) wants it this way. + */ + if (res->flags & IORESOURCE_PCI_FIXED) + bar64 = (res->flags & IORESOURCE_MEM_64) ? 1 : 0; + else + bar64 = __pci_read_base(dev, pci_bar_unknown, res, + pos + PCI_SRIOV_BAR + i * 4); if (!res->flags) continue; if (resource_size(res) & (PAGE_SIZE - 1)) { @@ -456,8 +456,6 @@ found: iov->nres = nres; iov->ctrl = ctrl; iov->total_VFs = total; - iov->offset = offset; - iov->stride = stride; iov->pgsz = pgsz; iov->self = dev; pci_read_config_dword(dev, pos + PCI_SRIOV_CAP, &iov->cap); @@ -474,10 +472,15 @@ found: dev->sriov = iov; dev->is_physfn = 1; - iov->max_VF_buses = virtfn_max_buses(dev); + rc = compute_max_vf_buses(dev); + if (rc) + goto fail_max_buses; return 0; +fail_max_buses: + dev->sriov = NULL; + dev->is_physfn = 0; failed: for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { res = &dev->resource[i + PCI_IOV_RESOURCES]; diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index dd652f2ae03d..2865ba37e295 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -172,7 +172,7 @@ static ssize_t store_remove_id(struct device_driver *driver, const char *buf, __u32 vendor, device, subvendor = PCI_ANY_ID, subdevice = PCI_ANY_ID, class = 0, class_mask = 0; int fields = 0; - int retval = -ENODEV; + size_t retval = -ENODEV; fields = sscanf(buf, "%x %x %x %x %x %x", &vendor, &device, &subvendor, &subdevice, @@ -190,15 +190,13 @@ static ssize_t store_remove_id(struct device_driver *driver, const char *buf, !((id->class ^ class) & class_mask)) { list_del(&dynid->node); kfree(dynid); - retval = 0; + retval = count; break; } } spin_unlock(&pdrv->dynids.lock); - if (retval) - return retval; - return count; + return retval; } static DRIVER_ATTR(remove_id, S_IWUSR, NULL, store_remove_id); diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 6a9a1116f1eb..2b28a4e77ea4 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -27,6 +27,7 @@ #include #include #include +#include #include "pci.h" const char *pci_power_names[] = { @@ -457,6 +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 @@ -484,7 +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 @@ -494,6 +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); } @@ -1099,6 +1128,8 @@ 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); @@ -2148,6 +2179,198 @@ 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) { diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 24ba9dc8910a..a1607331693e 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -78,6 +78,7 @@ bool pci_dev_keep_suspended(struct pci_dev *dev); void pci_config_pm_runtime_get(struct pci_dev *dev); void pci_config_pm_runtime_put(struct pci_dev *dev); void pci_pm_init(struct pci_dev *dev); +void pci_ea_init(struct pci_dev *dev); void pci_allocate_cap_save_buffers(struct pci_dev *dev); void pci_free_cap_save_buffers(struct pci_dev *dev); diff --git a/drivers/pci/pcie/aer/aerdrv_core.c b/drivers/pci/pcie/aer/aerdrv_core.c index 9803e3d039fe..fba785e9df75 100644 --- a/drivers/pci/pcie/aer/aerdrv_core.c +++ b/drivers/pci/pcie/aer/aerdrv_core.c @@ -74,6 +74,34 @@ int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev) } EXPORT_SYMBOL_GPL(pci_cleanup_aer_uncorrect_error_status); +int pci_cleanup_aer_error_status_regs(struct pci_dev *dev) +{ + int pos; + u32 status; + int port_type; + + if (!pci_is_pcie(dev)) + return -ENODEV; + + pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR); + if (!pos) + return -EIO; + + port_type = pci_pcie_type(dev); + if (port_type == PCI_EXP_TYPE_ROOT_PORT) { + pci_read_config_dword(dev, pos + PCI_ERR_ROOT_STATUS, &status); + pci_write_config_dword(dev, pos + PCI_ERR_ROOT_STATUS, status); + } + + pci_read_config_dword(dev, pos + PCI_ERR_COR_STATUS, &status); + pci_write_config_dword(dev, pos + PCI_ERR_COR_STATUS, status); + + pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status); + pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, status); + + return 0; +} + /** * add_error_device - list device to be handled * @e_info: pointer to error info diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 0b2be174d981..6ae984da0b9c 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include "pci.h" @@ -1598,6 +1599,9 @@ static struct pci_dev *pci_scan_device(struct pci_bus *bus, int devfn) static void pci_init_capabilities(struct pci_dev *dev) { + /* Enhanced Allocation */ + pci_ea_init(dev); + /* MSI/MSI-X list */ pci_msi_init_pci_dev(dev); @@ -1621,6 +1625,8 @@ static void pci_init_capabilities(struct pci_dev *dev) /* Enable ACS P2P upstream forwarding */ pci_enable_acs(dev); + + pci_cleanup_aer_error_status_regs(dev); } static void pci_set_msi_domain(struct pci_dev *dev) diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 83be0e555548..7c591bc10884 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -3692,6 +3692,63 @@ DECLARE_PCI_FIXUP_CLASS_EARLY(0x1797, 0x6868, PCI_CLASS_NOT_DEFINED, 8, DECLARE_PCI_FIXUP_CLASS_EARLY(0x1797, 0x6869, PCI_CLASS_NOT_DEFINED, 8, quirk_tw686x_class); +/* + * Per PCIe r3.0, sec 2.2.9, "Completion headers must supply the same + * values for the Attribute as were supplied in the header of the + * corresponding Request, except as explicitly allowed when IDO is used." + * + * If a non-compliant device generates a completion with a different + * attribute than the request, the receiver may accept it (which itself + * seems non-compliant based on sec 2.3.2), or it may handle it as a + * Malformed TLP or an Unexpected Completion, which will probably lead to a + * device access timeout. + * + * If the non-compliant device generates completions with zero attributes + * (instead of copying the attributes from the request), we can work around + * this by disabling the "Relaxed Ordering" and "No Snoop" attributes in + * upstream devices so they always generate requests with zero attributes. + * + * This affects other devices under the same Root Port, but since these + * attributes are performance hints, there should be no functional problem. + * + * Note that Configuration Space accesses are never supposed to have TLP + * Attributes, so we're safe waiting till after any Configuration Space + * accesses to do the Root Port fixup. + */ +static void quirk_disable_root_port_attributes(struct pci_dev *pdev) +{ + struct pci_dev *root_port = pci_find_pcie_root_port(pdev); + + if (!root_port) { + dev_warn(&pdev->dev, "PCIe Completion erratum may cause device errors\n"); + return; + } + + dev_info(&root_port->dev, "Disabling No Snoop/Relaxed Ordering Attributes to avoid PCIe Completion erratum in %s\n", + dev_name(&pdev->dev)); + pcie_capability_clear_and_set_word(root_port, PCI_EXP_DEVCTL, + PCI_EXP_DEVCTL_RELAX_EN | + PCI_EXP_DEVCTL_NOSNOOP_EN, 0); +} + +/* + * The Chelsio T5 chip fails to copy TLP Attributes from a Request to the + * Completion it generates. + */ +static void quirk_chelsio_T5_disable_root_port_attributes(struct pci_dev *pdev) +{ + /* + * This mask/compare operation selects for Physical Function 4 on a + * T5. We only need to fix up the Root Port once for any of the + * PFs. PF[0..3] have PCI Device IDs of 0x50xx, but PF4 is uniquely + * 0x54xx so we use that one, + */ + if ((pdev->device & 0xff00) == 0x5400) + quirk_disable_root_port_attributes(pdev); +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_CHELSIO, PCI_ANY_ID, + quirk_chelsio_T5_disable_root_port_attributes); + /* * AMD has indicated that the devices below do not support peer-to-peer * in any system where they are found in the southbridge with an AMD diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c index 508cc56130e3..1723ac1b30e1 100644 --- a/drivers/pci/setup-bus.c +++ b/drivers/pci/setup-bus.c @@ -1037,9 +1037,10 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask, struct resource *r = &dev->resource[i]; resource_size_t r_size; - if (r->parent || ((r->flags & mask) != type && - (r->flags & mask) != type2 && - (r->flags & mask) != type3)) + if (r->parent || (r->flags & IORESOURCE_PCI_FIXED) || + ((r->flags & mask) != type && + (r->flags & mask) != type2 && + (r->flags & mask) != type3)) continue; r_size = resource_size(r); #ifdef CONFIG_PCI_IOV @@ -1340,6 +1341,47 @@ void pci_bus_size_bridges(struct pci_bus *bus) } EXPORT_SYMBOL(pci_bus_size_bridges); +static void assign_fixed_resource_on_bus(struct pci_bus *b, struct resource *r) +{ + int i; + struct resource *parent_r; + unsigned long mask = IORESOURCE_IO | IORESOURCE_MEM | + IORESOURCE_PREFETCH; + + pci_bus_for_each_resource(b, parent_r, i) { + if (!parent_r) + continue; + + if ((r->flags & mask) == (parent_r->flags & mask) && + resource_contains(parent_r, r)) + request_resource(parent_r, r); + } +} + +/* + * Try to assign any resources marked as IORESOURCE_PCI_FIXED, as they + * are skipped by pbus_assign_resources_sorted(). + */ +static void pdev_assign_fixed_resources(struct pci_dev *dev) +{ + int i; + + for (i = 0; i < PCI_NUM_RESOURCES; i++) { + struct pci_bus *b; + struct resource *r = &dev->resource[i]; + + if (r->parent || !(r->flags & IORESOURCE_PCI_FIXED) || + !(r->flags & (IORESOURCE_IO | IORESOURCE_MEM))) + continue; + + b = dev->bus; + while (b && !r->parent) { + assign_fixed_resource_on_bus(b, r); + b = b->parent; + } + } +} + void __pci_bus_assign_resources(const struct pci_bus *bus, struct list_head *realloc_head, struct list_head *fail_head) @@ -1350,6 +1392,8 @@ void __pci_bus_assign_resources(const struct pci_bus *bus, pbus_assign_resources_sorted(bus, realloc_head, fail_head); list_for_each_entry(dev, &bus->devices, bus_list) { + pdev_assign_fixed_resources(dev); + b = dev->subordinate; if (!b) continue; diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c index 232f9254c11a..604011e047d6 100644 --- a/drivers/pci/setup-res.c +++ b/drivers/pci/setup-res.c @@ -36,6 +36,11 @@ void pci_update_resource(struct pci_dev *dev, int resno) enum pci_bar_type type; struct resource *res = dev->resource + resno; + if (dev->is_virtfn) { + dev_warn(&dev->dev, "can't update VF BAR%d\n", resno); + return; + } + /* * Ignore resources for unimplemented BARs and unused resource slots * for 64 bit BARs. @@ -177,6 +182,7 @@ static int pci_revert_fw_address(struct resource *res, struct pci_dev *dev, end = res->end; res->start = fw_addr; res->end = res->start + size - 1; + res->flags &= ~IORESOURCE_UNSET; root = pci_find_parent_resource(dev, res); if (!root) { @@ -194,6 +200,7 @@ static int pci_revert_fw_address(struct resource *res, struct pci_dev *dev, resno, res, conflict->name, conflict); res->start = start; res->end = end; + res->flags |= IORESOURCE_UNSET; return -EBUSY; } return 0; diff --git a/include/linux/aer.h b/include/linux/aer.h index 4fef65e57023..744b997d6a94 100644 --- a/include/linux/aer.h +++ b/include/linux/aer.h @@ -42,6 +42,7 @@ struct aer_capability_regs { int pci_enable_pcie_error_reporting(struct pci_dev *dev); int pci_disable_pcie_error_reporting(struct pci_dev *dev); int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev); +int pci_cleanup_aer_error_status_regs(struct pci_dev *dev); #else static inline int pci_enable_pcie_error_reporting(struct pci_dev *dev) { @@ -55,6 +56,10 @@ static inline int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev) { return -EINVAL; } +static inline int pci_cleanup_aer_error_status_regs(struct pci_dev *dev) +{ + return -EINVAL; +} #endif void cper_print_aer(struct pci_dev *dev, int cper_severity, diff --git a/include/linux/pci.h b/include/linux/pci.h index e90eb22de628..e828e7b4afec 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -820,6 +820,7 @@ void pci_bus_add_device(struct pci_dev *dev); void pci_read_bridge_bases(struct pci_bus *child); struct resource *pci_find_parent_resource(const struct pci_dev *dev, struct resource *res); +struct pci_dev *pci_find_pcie_root_port(struct pci_dev *dev); u8 pci_swizzle_interrupt_pin(const struct pci_dev *dev, u8 pin); int pci_get_interrupt_pin(struct pci_dev *dev, struct pci_dev **bridge); u8 pci_common_swizzle(struct pci_dev *dev, u8 *pinp); @@ -1192,6 +1193,17 @@ void pci_unregister_driver(struct pci_driver *dev); module_driver(__pci_driver, pci_register_driver, \ pci_unregister_driver) +/** + * builtin_pci_driver() - Helper macro for registering a PCI driver + * @__pci_driver: pci_driver struct + * + * Helper macro for PCI drivers which do not do anything special in their + * init code. This eliminates a lot of boilerplate. Each driver may only + * use this macro once, and calling it replaces device_initcall(...) + */ +#define builtin_pci_driver(__pci_driver) \ + builtin_driver(__pci_driver, pci_register_driver) + struct pci_driver *pci_dev_driver(const struct pci_dev *dev); int pci_add_dynid(struct pci_driver *drv, unsigned int vendor, unsigned int device, diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 413417f3707b..1becea86c73c 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -216,7 +216,8 @@ #define PCI_CAP_ID_MSIX 0x11 /* MSI-X */ #define PCI_CAP_ID_SATA 0x12 /* SATA Data/Index Conf. */ #define PCI_CAP_ID_AF 0x13 /* PCI Advanced Features */ -#define PCI_CAP_ID_MAX PCI_CAP_ID_AF +#define PCI_CAP_ID_EA 0x14 /* PCI Enhanced Allocation */ +#define PCI_CAP_ID_MAX PCI_CAP_ID_EA #define PCI_CAP_LIST_NEXT 1 /* Next capability in the list */ #define PCI_CAP_FLAGS 2 /* Capability defined flags (16 bits) */ #define PCI_CAP_SIZEOF 4 @@ -353,6 +354,46 @@ #define PCI_AF_STATUS_TP 0x01 #define PCI_CAP_AF_SIZEOF 6 /* size of AF registers */ +/* PCI Enhanced Allocation registers */ + +#define PCI_EA_NUM_ENT 2 /* Number of Capability Entries */ +#define PCI_EA_NUM_ENT_MASK 0x3f /* Num Entries Mask */ +#define PCI_EA_FIRST_ENT 4 /* First EA Entry in List */ +#define PCI_EA_FIRST_ENT_BRIDGE 8 /* First EA Entry for Bridges */ +#define PCI_EA_ES 0x00000007 /* Entry Size */ +#define PCI_EA_BEI 0x000000f0 /* BAR Equivalent Indicator */ +/* 0-5 map to BARs 0-5 respectively */ +#define PCI_EA_BEI_BAR0 0 +#define PCI_EA_BEI_BAR5 5 +#define PCI_EA_BEI_BRIDGE 6 /* Resource behind bridge */ +#define PCI_EA_BEI_ENI 7 /* Equivalent Not Indicated */ +#define PCI_EA_BEI_ROM 8 /* Expansion ROM */ +/* 9-14 map to VF BARs 0-5 respectively */ +#define PCI_EA_BEI_VF_BAR0 9 +#define PCI_EA_BEI_VF_BAR5 14 +#define PCI_EA_BEI_RESERVED 15 /* Reserved - Treat like ENI */ +#define PCI_EA_PP 0x0000ff00 /* Primary Properties */ +#define PCI_EA_SP 0x00ff0000 /* Secondary Properties */ +#define PCI_EA_P_MEM 0x00 /* Non-Prefetch Memory */ +#define PCI_EA_P_MEM_PREFETCH 0x01 /* Prefetchable Memory */ +#define PCI_EA_P_IO 0x02 /* I/O Space */ +#define PCI_EA_P_VF_MEM_PREFETCH 0x03 /* VF Prefetchable Memory */ +#define PCI_EA_P_VF_MEM 0x04 /* VF Non-Prefetch Memory */ +#define PCI_EA_P_BRIDGE_MEM 0x05 /* Bridge Non-Prefetch Memory */ +#define PCI_EA_P_BRIDGE_MEM_PREFETCH 0x06 /* Bridge Prefetchable Memory */ +#define PCI_EA_P_BRIDGE_IO 0x07 /* Bridge I/O Space */ +/* 0x08-0xfc reserved */ +#define PCI_EA_P_MEM_RESERVED 0xfd /* Reserved Memory */ +#define PCI_EA_P_IO_RESERVED 0xfe /* Reserved I/O Space */ +#define PCI_EA_P_UNAVAILABLE 0xff /* Entry Unavailable */ +#define PCI_EA_WRITABLE 0x40000000 /* Writable: 1 = RW, 0 = HwInit */ +#define PCI_EA_ENABLE 0x80000000 /* Enable for this entry */ +#define PCI_EA_BASE 4 /* Base Address Offset */ +#define PCI_EA_MAX_OFFSET 8 /* MaxOffset (resource length) */ +/* bit 0 is reserved */ +#define PCI_EA_IS_64 0x00000002 /* 64-bit field flag */ +#define PCI_EA_FIELD_MASK 0xfffffffc /* For Base & Max Offset */ + /* PCI-X registers (Type 0 (non-bridge) devices) */ #define PCI_X_CMD 2 /* Modes & Features */