diff options
Diffstat (limited to 'drivers/pci')
29 files changed, 1245 insertions, 562 deletions
diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig index 37856f7c7781..848bfb84c04c 100644 --- a/drivers/pci/Kconfig +++ b/drivers/pci/Kconfig @@ -31,6 +31,19 @@ config PCI_DEBUG When in doubt, say N. +config PCI_REALLOC_ENABLE_AUTO + bool "Enable PCI resource re-allocation detection" + depends on PCI + help + Say Y here if you want the PCI core to detect if PCI resource + re-allocation needs to be enabled. You can always use pci=realloc=on + or pci=realloc=off to override it. Note this feature is a no-op + unless PCI_IOV support is also enabled; in that case it will + automatically re-allocate PCI resources if SR-IOV BARs have not + been allocated by the BIOS. + + When in doubt, say N. + config PCI_STUB tristate "PCI Stub driver" depends on PCI diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c index 398f5d859791..4ce5ef2f2826 100644 --- a/drivers/pci/bus.c +++ b/drivers/pci/bus.c @@ -18,28 +18,36 @@ #include "pci.h" -void pci_add_resource(struct list_head *resources, struct resource *res) +void pci_add_resource_offset(struct list_head *resources, struct resource *res, + resource_size_t offset) { - struct pci_bus_resource *bus_res; + struct pci_host_bridge_window *window; - bus_res = kzalloc(sizeof(struct pci_bus_resource), GFP_KERNEL); - if (!bus_res) { - printk(KERN_ERR "PCI: can't add bus resource %pR\n", res); + window = kzalloc(sizeof(struct pci_host_bridge_window), GFP_KERNEL); + if (!window) { + printk(KERN_ERR "PCI: can't add host bridge window %pR\n", res); return; } - bus_res->res = res; - list_add_tail(&bus_res->list, resources); + window->res = res; + window->offset = offset; + list_add_tail(&window->list, resources); +} +EXPORT_SYMBOL(pci_add_resource_offset); + +void pci_add_resource(struct list_head *resources, struct resource *res) +{ + pci_add_resource_offset(resources, res, 0); } EXPORT_SYMBOL(pci_add_resource); void pci_free_resource_list(struct list_head *resources) { - struct pci_bus_resource *bus_res, *tmp; + struct pci_host_bridge_window *window, *tmp; - list_for_each_entry_safe(bus_res, tmp, resources, list) { - list_del(&bus_res->list); - kfree(bus_res); + list_for_each_entry_safe(window, tmp, resources, list) { + list_del(&window->list); + kfree(window); } } EXPORT_SYMBOL(pci_free_resource_list); diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c index 9ddf69e3bbef..806c44fa645a 100644 --- a/drivers/pci/hotplug/acpiphp_glue.c +++ b/drivers/pci/hotplug/acpiphp_glue.c @@ -800,20 +800,10 @@ static int __ref enable_device(struct acpiphp_slot *slot) if (slot->flags & SLOT_ENABLED) goto err_exit; - /* sanity check: dev should be NULL when hot-plugged in */ - dev = pci_get_slot(bus, PCI_DEVFN(slot->device, 0)); - if (dev) { - /* This case shouldn't happen */ - err("pci_dev structure already exists.\n"); - pci_dev_put(dev); - retval = -1; - goto err_exit; - } - num = pci_scan_slot(bus, PCI_DEVFN(slot->device, 0)); if (num == 0) { - err("No new device found\n"); - retval = -1; + /* Maybe only part of funcs are added. */ + dbg("No new device found\n"); goto err_exit; } @@ -848,11 +838,16 @@ static int __ref enable_device(struct acpiphp_slot *slot) pci_bus_add_devices(bus); + slot->flags |= SLOT_ENABLED; list_for_each_entry(func, &slot->funcs, sibling) { dev = pci_get_slot(bus, PCI_DEVFN(slot->device, func->function)); - if (!dev) + if (!dev) { + /* Do not set SLOT_ENABLED flag if some funcs + are not added. */ + slot->flags &= (~SLOT_ENABLED); continue; + } if (dev->hdr_type != PCI_HEADER_TYPE_BRIDGE && dev->hdr_type != PCI_HEADER_TYPE_CARDBUS) { @@ -867,7 +862,6 @@ static int __ref enable_device(struct acpiphp_slot *slot) pci_dev_put(dev); } - slot->flags |= SLOT_ENABLED; err_exit: return retval; @@ -892,9 +886,12 @@ static int disable_device(struct acpiphp_slot *slot) { struct acpiphp_func *func; struct pci_dev *pdev; + struct pci_bus *bus = slot->bridge->pci_bus; - /* is this slot already disabled? */ - if (!(slot->flags & SLOT_ENABLED)) + /* The slot will be enabled when func 0 is added, so check + func 0 before disable the slot. */ + pdev = pci_get_slot(bus, PCI_DEVFN(slot->device, 0)); + if (!pdev) goto err_exit; list_for_each_entry(func, &slot->funcs, sibling) { @@ -913,7 +910,7 @@ static int disable_device(struct acpiphp_slot *slot) disable_bridges(pdev->subordinate); pci_disable_device(pdev); } - pci_remove_bus_device(pdev); + __pci_remove_bus_device(pdev); pci_dev_put(pdev); } } @@ -1070,7 +1067,7 @@ static void acpiphp_sanitize_bus(struct pci_bus *bus) res->end) { /* Could not assign a required resources * for this device, remove it */ - pci_remove_bus_device(dev); + pci_stop_and_remove_bus_device(dev); break; } } diff --git a/drivers/pci/hotplug/cpci_hotplug_pci.c b/drivers/pci/hotplug/cpci_hotplug_pci.c index 829c327cfb5e..ae853ccd0cd5 100644 --- a/drivers/pci/hotplug/cpci_hotplug_pci.c +++ b/drivers/pci/hotplug/cpci_hotplug_pci.c @@ -341,7 +341,7 @@ int cpci_unconfigure_slot(struct slot* slot) dev = pci_get_slot(slot->bus, PCI_DEVFN(PCI_SLOT(slot->devfn), i)); if (dev) { - pci_remove_bus_device(dev); + pci_stop_and_remove_bus_device(dev); pci_dev_put(dev); } } diff --git a/drivers/pci/hotplug/cpcihp_generic.c b/drivers/pci/hotplug/cpcihp_generic.c index fb3f84661bdc..81af764c629b 100644 --- a/drivers/pci/hotplug/cpcihp_generic.c +++ b/drivers/pci/hotplug/cpcihp_generic.c @@ -62,7 +62,7 @@ #define warn(format, arg...) printk(KERN_WARNING "%s: " format "\n", MY_NAME , ## arg) /* local variables */ -static int debug; +static bool debug; static char *bridge; static u8 bridge_busnr; static u8 bridge_slot; diff --git a/drivers/pci/hotplug/cpqphp_pci.c b/drivers/pci/hotplug/cpqphp_pci.c index 6173b9a4544e..1c8494021a42 100644 --- a/drivers/pci/hotplug/cpqphp_pci.c +++ b/drivers/pci/hotplug/cpqphp_pci.c @@ -127,7 +127,7 @@ int cpqhp_unconfigure_device(struct pci_func* func) struct pci_dev* temp = pci_get_bus_and_slot(func->bus, PCI_DEVFN(func->device, j)); if (temp) { pci_dev_put(temp); - pci_remove_bus_device(temp); + pci_stop_and_remove_bus_device(temp); } } return 0; diff --git a/drivers/pci/hotplug/fakephp.c b/drivers/pci/hotplug/fakephp.c index 17d10e2e8fb6..a019c9a712be 100644 --- a/drivers/pci/hotplug/fakephp.c +++ b/drivers/pci/hotplug/fakephp.c @@ -40,7 +40,7 @@ static ssize_t legacy_show(struct kobject *kobj, struct attribute *attr, static void remove_callback(void *data) { - pci_remove_bus_device((struct pci_dev *)data); + pci_stop_and_remove_bus_device((struct pci_dev *)data); } static ssize_t legacy_store(struct kobject *kobj, struct attribute *attr, diff --git a/drivers/pci/hotplug/ibmphp_core.c b/drivers/pci/hotplug/ibmphp_core.c index 5506e0e8fbc0..4fda7e6a86a7 100644 --- a/drivers/pci/hotplug/ibmphp_core.c +++ b/drivers/pci/hotplug/ibmphp_core.c @@ -721,7 +721,7 @@ static void ibm_unconfigure_device(struct pci_func *func) for (j = 0; j < 0x08; j++) { temp = pci_get_bus_and_slot(func->busno, (func->device << 3) | j); if (temp) { - pci_remove_bus_device(temp); + pci_stop_and_remove_bus_device(temp); pci_dev_put(temp); } } diff --git a/drivers/pci/hotplug/ibmphp_ebda.c b/drivers/pci/hotplug/ibmphp_ebda.c index 2850e64dedae..714ca5c4ed50 100644 --- a/drivers/pci/hotplug/ibmphp_ebda.c +++ b/drivers/pci/hotplug/ibmphp_ebda.c @@ -368,8 +368,10 @@ int __init ibmphp_access_ebda (void) debug ("rio blk id: %x\n", blk_id); rio_table_ptr = kzalloc(sizeof(struct rio_table_hdr), GFP_KERNEL); - if (!rio_table_ptr) - return -ENOMEM; + if (!rio_table_ptr) { + rc = -ENOMEM; + goto out; + } rio_table_ptr->ver_num = readb (io_mem + offset); rio_table_ptr->scal_count = readb (io_mem + offset + 1); rio_table_ptr->riodev_count = readb (io_mem + offset + 2); diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c index bcdbb1643621..a960faec1021 100644 --- a/drivers/pci/hotplug/pciehp_hpc.c +++ b/drivers/pci/hotplug/pciehp_hpc.c @@ -241,34 +241,79 @@ static int pcie_write_cmd(struct controller *ctrl, u16 cmd, u16 mask) return retval; } -static inline int check_link_active(struct controller *ctrl) +static bool check_link_active(struct controller *ctrl) { - u16 link_status; + bool ret = false; + u16 lnk_status; - if (pciehp_readw(ctrl, PCI_EXP_LNKSTA, &link_status)) - return 0; - return !!(link_status & PCI_EXP_LNKSTA_DLLLA); + if (pciehp_readw(ctrl, PCI_EXP_LNKSTA, &lnk_status)) + return ret; + + ret = !!(lnk_status & PCI_EXP_LNKSTA_DLLLA); + + if (ret) + ctrl_dbg(ctrl, "%s: lnk_status = %x\n", __func__, lnk_status); + + return ret; } -static void pcie_wait_link_active(struct controller *ctrl) +static void __pcie_wait_link_active(struct controller *ctrl, bool active) { int timeout = 1000; - if (check_link_active(ctrl)) + if (check_link_active(ctrl) == active) return; while (timeout > 0) { msleep(10); timeout -= 10; - if (check_link_active(ctrl)) + if (check_link_active(ctrl) == active) return; } - ctrl_dbg(ctrl, "Data Link Layer Link Active not set in 1000 msec\n"); + ctrl_dbg(ctrl, "Data Link Layer Link Active not %s in 1000 msec\n", + active ? "set" : "cleared"); +} + +static void pcie_wait_link_active(struct controller *ctrl) +{ + __pcie_wait_link_active(ctrl, true); +} + +static void pcie_wait_link_not_active(struct controller *ctrl) +{ + __pcie_wait_link_active(ctrl, false); +} + +static bool pci_bus_check_dev(struct pci_bus *bus, int devfn) +{ + u32 l; + int count = 0; + int delay = 1000, step = 20; + bool found = false; + + do { + found = pci_bus_read_dev_vendor_id(bus, devfn, &l, 0); + count++; + + if (found) + break; + + msleep(step); + delay -= step; + } while (delay > 0); + + if (count > 1 && pciehp_debug) + printk(KERN_DEBUG "pci %04x:%02x:%02x.%d id reading try %d times with interval %d ms to get %08x\n", + pci_domain_nr(bus), bus->number, PCI_SLOT(devfn), + PCI_FUNC(devfn), count, step, l); + + return found; } int pciehp_check_link_status(struct controller *ctrl) { u16 lnk_status; int retval = 0; + bool found = false; /* * Data Link Layer Link Active Reporting must be capable for @@ -280,13 +325,10 @@ int pciehp_check_link_status(struct controller *ctrl) else msleep(1000); - /* - * Need to wait for 1000 ms after Data Link Layer Link Active - * (DLLLA) bit reads 1b before sending configuration request. - * We need it before checking Link Training (LT) bit becuase - * LT is still set even after DLLLA bit is set on some platform. - */ - msleep(1000); + /* wait 100ms before read pci conf, and try in 1s */ + msleep(100); + found = pci_bus_check_dev(ctrl->pcie->port->subordinate, + PCI_DEVFN(0, 0)); retval = pciehp_readw(ctrl, PCI_EXP_LNKSTA, &lnk_status); if (retval) { @@ -302,19 +344,50 @@ int pciehp_check_link_status(struct controller *ctrl) return retval; } - /* - * If the port supports Link speeds greater than 5.0 GT/s, we - * must wait for 100 ms after Link training completes before - * sending configuration request. - */ - if (ctrl->pcie->port->subordinate->max_bus_speed > PCIE_SPEED_5_0GT) - msleep(100); - pcie_update_link_speed(ctrl->pcie->port->subordinate, lnk_status); + if (!found && !retval) + retval = -1; + return retval; } +static int __pciehp_link_set(struct controller *ctrl, bool enable) +{ + u16 lnk_ctrl; + int retval = 0; + + retval = pciehp_readw(ctrl, PCI_EXP_LNKCTL, &lnk_ctrl); + if (retval) { + ctrl_err(ctrl, "Cannot read LNKCTRL register\n"); + return retval; + } + + if (enable) + lnk_ctrl &= ~PCI_EXP_LNKCTL_LD; + else + lnk_ctrl |= PCI_EXP_LNKCTL_LD; + + retval = pciehp_writew(ctrl, PCI_EXP_LNKCTL, lnk_ctrl); + if (retval) { + ctrl_err(ctrl, "Cannot write LNKCTRL register\n"); + return retval; + } + ctrl_dbg(ctrl, "%s: lnk_ctrl = %x\n", __func__, lnk_ctrl); + + return retval; +} + +static int pciehp_link_enable(struct controller *ctrl) +{ + return __pciehp_link_set(ctrl, true); +} + +static int pciehp_link_disable(struct controller *ctrl) +{ + return __pciehp_link_set(ctrl, false); +} + int pciehp_get_attention_status(struct slot *slot, u8 *status) { struct controller *ctrl = slot->ctrl; @@ -533,6 +606,10 @@ int pciehp_power_on_slot(struct slot * slot) ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__, pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, slot_cmd); + retval = pciehp_link_enable(ctrl); + if (retval) + ctrl_err(ctrl, "%s: Can not enable the link!\n", __func__); + return retval; } @@ -543,6 +620,14 @@ int pciehp_power_off_slot(struct slot * slot) u16 cmd_mask; int retval; + /* Disable the link at first */ + pciehp_link_disable(ctrl); + /* wait the link is down */ + if (ctrl->link_active_reporting) + pcie_wait_link_not_active(ctrl); + else + msleep(1000); + slot_cmd = POWER_OFF; cmd_mask = PCI_EXP_SLTCTL_PCC; retval = pcie_write_cmd(ctrl, slot_cmd, cmd_mask); diff --git a/drivers/pci/hotplug/pciehp_pci.c b/drivers/pci/hotplug/pciehp_pci.c index a4031dfe938e..47d9dc06b109 100644 --- a/drivers/pci/hotplug/pciehp_pci.c +++ b/drivers/pci/hotplug/pciehp_pci.c @@ -141,7 +141,7 @@ int pciehp_unconfigure_device(struct slot *p_slot) break; } } - pci_remove_bus_device(temp); + pci_stop_and_remove_bus_device(temp); /* * Ensure that no new Requests will be generated from * the device. diff --git a/drivers/pci/hotplug/rpadlpar_core.c b/drivers/pci/hotplug/rpadlpar_core.c index c56a9413e1af..1e117c2a3cad 100644 --- a/drivers/pci/hotplug/rpadlpar_core.c +++ b/drivers/pci/hotplug/rpadlpar_core.c @@ -389,7 +389,7 @@ int dlpar_remove_pci_slot(char *drc_name, struct device_node *dn) BUG_ON(!bus->self); pr_debug("PCI: Now removing bridge device %s\n", pci_name(bus->self)); eeh_remove_bus_device(bus->self); - pci_remove_bus_device(bus->self); + pci_stop_and_remove_bus_device(bus->self); return 0; } diff --git a/drivers/pci/hotplug/sgi_hotplug.c b/drivers/pci/hotplug/sgi_hotplug.c index 72d507b6a2aa..de573113c102 100644 --- a/drivers/pci/hotplug/sgi_hotplug.c +++ b/drivers/pci/hotplug/sgi_hotplug.c @@ -554,7 +554,7 @@ static int disable_slot(struct hotplug_slot *bss_hotplug_slot) PCI_FUNC(func))); if (dev) { sn_bus_free_data(dev); - pci_remove_bus_device(dev); + pci_stop_and_remove_bus_device(dev); pci_dev_put(dev); } } diff --git a/drivers/pci/hotplug/shpchp_pci.c b/drivers/pci/hotplug/shpchp_pci.c index a2ccfcd3c298..df7e4bfadae3 100644 --- a/drivers/pci/hotplug/shpchp_pci.c +++ b/drivers/pci/hotplug/shpchp_pci.c @@ -124,7 +124,7 @@ int shpchp_unconfigure_device(struct slot *p_slot) break; } } - pci_remove_bus_device(temp); + pci_stop_and_remove_bus_device(temp); pci_dev_put(temp); } return rc; diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c index 0dab5ecf61bb..6554e1a0f634 100644 --- a/drivers/pci/iov.c +++ b/drivers/pci/iov.c @@ -142,7 +142,7 @@ failed2: failed1: pci_dev_put(dev); mutex_lock(&iov->dev->sriov->lock); - pci_remove_bus_device(virtfn); + pci_stop_and_remove_bus_device(virtfn); virtfn_remove_bus(dev->bus, virtfn_bus(dev, id)); mutex_unlock(&iov->dev->sriov->lock); @@ -173,10 +173,16 @@ static void virtfn_remove(struct pci_dev *dev, int id, int reset) sprintf(buf, "virtfn%u", id); sysfs_remove_link(&dev->dev.kobj, buf); - sysfs_remove_link(&virtfn->dev.kobj, "physfn"); + /* + * pci_stop_dev() could have been called for this virtfn already, + * so the directory for the virtfn may have been removed before. + * Double check to avoid spurious sysfs warnings. + */ + if (virtfn->dev.kobj.sd) + sysfs_remove_link(&virtfn->dev.kobj, "physfn"); mutex_lock(&iov->dev->sriov->lock); - pci_remove_bus_device(virtfn); + pci_stop_and_remove_bus_device(virtfn); virtfn_remove_bus(dev->bus, virtfn_bus(dev, id)); mutex_unlock(&iov->dev->sriov->lock); diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 3623d65f8b86..6b54b23b990b 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -72,9 +72,7 @@ int pci_add_dynid(struct pci_driver *drv, list_add_tail(&dynid->node, &drv->dynids.list); spin_unlock(&drv->dynids.lock); - get_driver(&drv->driver); retval = driver_attach(&drv->driver); - put_driver(&drv->driver); return retval; } @@ -190,43 +188,34 @@ store_remove_id(struct device_driver *driver, const char *buf, size_t count) static DRIVER_ATTR(remove_id, S_IWUSR, NULL, store_remove_id); static int -pci_create_newid_file(struct pci_driver *drv) +pci_create_newid_files(struct pci_driver *drv) { int error = 0; - if (drv->probe != NULL) - error = driver_create_file(&drv->driver, &driver_attr_new_id); - return error; -} -static void pci_remove_newid_file(struct pci_driver *drv) -{ - driver_remove_file(&drv->driver, &driver_attr_new_id); -} - -static int -pci_create_removeid_file(struct pci_driver *drv) -{ - int error = 0; - if (drv->probe != NULL) - error = driver_create_file(&drv->driver,&driver_attr_remove_id); + if (drv->probe != NULL) { + error = driver_create_file(&drv->driver, &driver_attr_new_id); + if (error == 0) { + error = driver_create_file(&drv->driver, + &driver_attr_remove_id); + if (error) + driver_remove_file(&drv->driver, + &driver_attr_new_id); + } + } return error; } -static void pci_remove_removeid_file(struct pci_driver *drv) +static void pci_remove_newid_files(struct pci_driver *drv) { driver_remove_file(&drv->driver, &driver_attr_remove_id); + driver_remove_file(&drv->driver, &driver_attr_new_id); } #else /* !CONFIG_HOTPLUG */ -static inline int pci_create_newid_file(struct pci_driver *drv) -{ - return 0; -} -static inline void pci_remove_newid_file(struct pci_driver *drv) {} -static inline int pci_create_removeid_file(struct pci_driver *drv) +static inline int pci_create_newid_files(struct pci_driver *drv) { return 0; } -static inline void pci_remove_removeid_file(struct pci_driver *drv) {} +static inline void pci_remove_newid_files(struct pci_driver *drv) {} #endif /** @@ -430,6 +419,16 @@ static void pci_device_shutdown(struct device *dev) drv->shutdown(pci_dev); pci_msi_shutdown(pci_dev); pci_msix_shutdown(pci_dev); + + /* + * Devices may be enabled to wake up by runtime PM, but they need not + * be supposed to wake up the system from its "power off" state (e.g. + * ACPI S5). Therefore disable wakeup for all devices that aren't + * supposed to wake up the system at this point. The state argument + * will be ignored by pci_enable_wake(). + */ + if (!device_may_wakeup(dev)) + pci_enable_wake(pci_dev, PCI_UNKNOWN, false); } #ifdef CONFIG_PM @@ -1138,18 +1137,12 @@ int __pci_register_driver(struct pci_driver *drv, struct module *owner, if (error) goto out; - error = pci_create_newid_file(drv); + error = pci_create_newid_files(drv); if (error) goto out_newid; - - error = pci_create_removeid_file(drv); - if (error) - goto out_removeid; out: return error; -out_removeid: - pci_remove_newid_file(drv); out_newid: driver_unregister(&drv->driver); goto out; @@ -1168,8 +1161,7 @@ out_newid: void pci_unregister_driver(struct pci_driver *drv) { - pci_remove_removeid_file(drv); - pci_remove_newid_file(drv); + pci_remove_newid_files(drv); driver_unregister(&drv->driver); pci_free_dynids(drv); } diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index a3cd8cad532a..a55e248618cd 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -330,7 +330,7 @@ static void remove_callback(struct device *dev) struct pci_dev *pdev = to_pci_dev(dev); mutex_lock(&pci_remove_rescan_mutex); - pci_remove_bus_device(pdev); + pci_stop_and_remove_bus_device(pdev); mutex_unlock(&pci_remove_rescan_mutex); } @@ -366,7 +366,10 @@ dev_bus_rescan_store(struct device *dev, struct device_attribute *attr, if (val) { mutex_lock(&pci_remove_rescan_mutex); - pci_rescan_bus(bus); + if (!pci_is_root_bus(bus) && list_empty(&bus->devices)) + pci_rescan_bus_bridge_resize(bus->self); + else + pci_rescan_bus(bus); mutex_unlock(&pci_remove_rescan_mutex); } return count; diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index af295bb21d62..815674415267 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -94,6 +94,9 @@ u8 pci_cache_line_size; */ unsigned int pcibios_max_latency = 255; +/* If set, the PCIe ARI capability will not be used. */ +static bool pcie_ari_disabled; + /** * pci_bus_max_busnr - returns maximum PCI bus number of given bus' children * @bus: pointer to PCI bus structure to search @@ -825,6 +828,19 @@ EXPORT_SYMBOL(pci_choose_state); #define pcie_cap_has_sltctl2(type, flags) \ ((flags & PCI_EXP_FLAGS_VERS) > 1) +static struct pci_cap_saved_state *pci_find_saved_cap( + struct pci_dev *pci_dev, char cap) +{ + struct pci_cap_saved_state *tmp; + struct hlist_node *pos; + + hlist_for_each_entry(tmp, pos, &pci_dev->saved_cap_space, next) { + if (tmp->cap.cap_nr == cap) + return tmp; + } + return NULL; +} + static int pci_save_pcie_state(struct pci_dev *dev) { int pos, i = 0; @@ -959,6 +975,7 @@ void pci_restore_state(struct pci_dev *dev) { int i; u32 val; + int tries; if (!dev->state_saved) return; @@ -973,12 +990,16 @@ void pci_restore_state(struct pci_dev *dev) */ for (i = 15; i >= 0; i--) { pci_read_config_dword(dev, i * 4, &val); - if (val != dev->saved_config_space[i]) { + tries = 10; + while (tries && val != dev->saved_config_space[i]) { dev_dbg(&dev->dev, "restoring config " "space at offset %#x (was %#x, writing %#x)\n", i, val, (int)dev->saved_config_space[i]); pci_write_config_dword(dev,i * 4, dev->saved_config_space[i]); + pci_read_config_dword(dev, i * 4, &val); + mdelay(10); + tries--; } } pci_restore_pcix_state(dev); @@ -1864,6 +1885,12 @@ void platform_pci_wakeup_init(struct pci_dev *dev) platform_pci_sleep_wake(dev, false); } +static void pci_add_saved_cap(struct pci_dev *pci_dev, + struct pci_cap_saved_state *new_cap) +{ + hlist_add_head(&new_cap->next, &pci_dev->saved_cap_space); +} + /** * pci_add_save_buffer - allocate buffer for saving given capability registers * @dev: the PCI device @@ -1911,6 +1938,15 @@ void pci_allocate_cap_save_buffers(struct pci_dev *dev) "unable to preallocate PCI-X save buffer\n"); } +void pci_free_cap_save_buffers(struct pci_dev *dev) +{ + struct pci_cap_saved_state *tmp; + struct hlist_node *pos, *n; + + hlist_for_each_entry_safe(tmp, pos, n, &dev->saved_cap_space, next) + kfree(tmp); +} + /** * pci_enable_ari - enable ARI forwarding if hardware support it * @dev: the PCI device @@ -1922,7 +1958,7 @@ void pci_enable_ari(struct pci_dev *dev) u16 flags, ctrl; struct pci_dev *bridge; - if (!pci_is_pcie(dev) || dev->devfn) + if (pcie_ari_disabled || !pci_is_pcie(dev) || dev->devfn) return; pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ARI); @@ -3163,6 +3199,31 @@ int __pci_reset_function(struct pci_dev *dev) EXPORT_SYMBOL_GPL(__pci_reset_function); /** + * __pci_reset_function_locked - reset a PCI device function while holding + * the @dev mutex lock. + * @dev: PCI device to reset + * + * Some devices allow an individual function to be reset without affecting + * other functions in the same device. The PCI device must be responsive + * to PCI config space in order to use this function. + * + * The device function is presumed to be unused and the caller is holding + * the device mutex lock when this function is called. + * Resetting the device will make the contents of PCI configuration space + * random, so any caller of this must be prepared to reinitialise the + * device including MSI, bus mastering, BARs, decoding IO and memory spaces, + * etc. + * + * Returns 0 if the device function was successfully reset or negative if the + * device doesn't support resetting a single function. + */ +int __pci_reset_function_locked(struct pci_dev *dev) +{ + return pci_dev_reset(dev, 1); +} +EXPORT_SYMBOL_GPL(__pci_reset_function_locked); + +/** * pci_probe_reset_function - check whether the device can be safely reset * @dev: PCI device to reset * @@ -3636,6 +3697,68 @@ int pci_is_reassigndev(struct pci_dev *dev) return (pci_specified_resource_alignment(dev) != 0); } +/* + * This function disables memory decoding and releases memory resources + * of the device specified by kernel's boot parameter 'pci=resource_alignment='. + * It also rounds up size to specified alignment. + * Later on, the kernel will assign page-aligned memory resource back + * to the device. + */ +void pci_reassigndev_resource_alignment(struct pci_dev *dev) +{ + int i; + struct resource *r; + resource_size_t align, size; + u16 command; + + if (!pci_is_reassigndev(dev)) + return; + + if (dev->hdr_type == PCI_HEADER_TYPE_NORMAL && + (dev->class >> 8) == PCI_CLASS_BRIDGE_HOST) { + dev_warn(&dev->dev, + "Can't reassign resources to host bridge.\n"); + return; + } + + dev_info(&dev->dev, + "Disabling memory decoding and releasing memory resources.\n"); + pci_read_config_word(dev, PCI_COMMAND, &command); + command &= ~PCI_COMMAND_MEMORY; + pci_write_config_word(dev, PCI_COMMAND, command); + + align = pci_specified_resource_alignment(dev); + for (i = 0; i < PCI_BRIDGE_RESOURCES; i++) { + r = &dev->resource[i]; + if (!(r->flags & IORESOURCE_MEM)) + continue; + size = resource_size(r); + if (size < align) { + size = align; + dev_info(&dev->dev, + "Rounding up size of resource #%d to %#llx.\n", + i, (unsigned long long)size); + } + r->end = size - 1; + r->start = 0; + } + /* Need to disable bridge's resource window, + * to enable the kernel to reassign new resource + * window later on. + */ + if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE && + (dev->class >> 8) == PCI_CLASS_BRIDGE_PCI) { + for (i = PCI_BRIDGE_RESOURCES; i < PCI_NUM_RESOURCES; i++) { + r = &dev->resource[i]; + if (!(r->flags & IORESOURCE_MEM)) + continue; + r->end = resource_size(r) - 1; + r->start = 0; + } + pci_disable_bridge_window(dev); + } +} + ssize_t pci_set_resource_alignment_param(const char *buf, size_t count) { if (count > RESOURCE_ALIGNMENT_PARAM_SIZE - 1) @@ -3714,10 +3837,14 @@ static int __init pci_setup(char *str) pci_no_msi(); } else if (!strcmp(str, "noaer")) { pci_no_aer(); + } else if (!strncmp(str, "realloc=", 8)) { + pci_realloc_get_opt(str + 8); } else if (!strncmp(str, "realloc", 7)) { - pci_realloc(); + pci_realloc_get_opt("on"); } else if (!strcmp(str, "nodomains")) { pci_no_domains(); + } else if (!strncmp(str, "noari", 5)) { + pcie_ari_disabled = true; } else if (!strncmp(str, "cbiosize=", 9)) { pci_cardbus_io_size = memparse(str + 9, &str); } else if (!strncmp(str, "cbmemsize=", 10)) { diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 1009a5e88e53..e4943479b234 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -73,6 +73,7 @@ extern int __pci_pme_wakeup(struct pci_dev *dev, void *ign); extern void pci_pm_init(struct pci_dev *dev); extern void platform_pci_wakeup_init(struct pci_dev *dev); extern void pci_allocate_cap_save_buffers(struct pci_dev *dev); +void pci_free_cap_save_buffers(struct pci_dev *dev); static inline void pci_wakeup_event(struct pci_dev *dev) { @@ -148,7 +149,7 @@ static inline void pci_no_msi(void) { } static inline void pci_msi_init_pci_dev(struct pci_dev *dev) { } #endif -extern void pci_realloc(void); +void pci_realloc_get_opt(char *); static inline int pci_no_d1d2(struct pci_dev *dev) { @@ -207,6 +208,8 @@ enum pci_bar_type { pci_bar_mem64, /* A 64-bit memory BAR */ }; +bool pci_bus_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *pl, + int crs_timeout); extern int pci_setup_device(struct pci_dev *dev); extern int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type, struct resource *res, unsigned int reg); @@ -225,11 +228,8 @@ static inline int pci_ari_enabled(struct pci_bus *bus) return bus->self && bus->self->ari_enabled; } -#ifdef CONFIG_PCI_QUIRKS -extern int pci_is_reassigndev(struct pci_dev *dev); -resource_size_t pci_specified_resource_alignment(struct pci_dev *dev); +void pci_reassigndev_resource_alignment(struct pci_dev *dev); extern void pci_disable_bridge_window(struct pci_dev *dev); -#endif /* Single Root I/O Virtualization */ struct pci_sriov { diff --git a/drivers/pci/pcie/Kconfig b/drivers/pci/pcie/Kconfig index 72962cc92e0a..6c8bc5809787 100644 --- a/drivers/pci/pcie/Kconfig +++ b/drivers/pci/pcie/Kconfig @@ -55,6 +55,31 @@ config PCIEASPM_DEBUG This enables PCI Express ASPM debug support. It will add per-device interface to control ASPM. +choice + prompt "Default ASPM policy" + default PCIEASPM_DEFAULT + depends on PCIEASPM + +config PCIEASPM_DEFAULT + bool "BIOS default" + depends on PCIEASPM + help + Use the BIOS defaults for PCI Express ASPM. + +config PCIEASPM_POWERSAVE + bool "Powersave" + depends on PCIEASPM + help + Enable PCI Express ASPM L0s and L1 where possible, even if the + BIOS did not. + +config PCIEASPM_PERFORMANCE + bool "Performance" + depends on PCIEASPM + help + Disable PCI Express ASPM L0s and L1, even if the BIOS enabled them. +endchoice + config PCIE_PME def_bool y depends on PCIEPORTBUS && PM_RUNTIME && EXPERIMENTAL && ACPI diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index 1cfbf228fbb1..4bdef24cd412 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -76,7 +76,15 @@ static LIST_HEAD(link_list); #define POLICY_DEFAULT 0 /* BIOS default setting */ #define POLICY_PERFORMANCE 1 /* high performance */ #define POLICY_POWERSAVE 2 /* high power saving */ + +#ifdef CONFIG_PCIEASPM_PERFORMANCE +static int aspm_policy = POLICY_PERFORMANCE; +#elif defined CONFIG_PCIEASPM_POWERSAVE +static int aspm_policy = POLICY_POWERSAVE; +#else static int aspm_policy; +#endif + static const char *policy_str[] = { [POLICY_DEFAULT] = "default", [POLICY_PERFORMANCE] = "performance", @@ -500,6 +508,9 @@ static int pcie_aspm_sanity_check(struct pci_dev *pdev) int pos; u32 reg32; + if (aspm_disabled) + return 0; + /* * Some functions in a slot might not all be PCIe functions, * very strange. Disable ASPM for the whole slot diff --git a/drivers/pci/pcie/portdrv.h b/drivers/pci/pcie/portdrv.h index bd00a01aef14..eea2ca2375e6 100644 --- a/drivers/pci/pcie/portdrv.h +++ b/drivers/pci/pcie/portdrv.h @@ -34,6 +34,18 @@ struct pci_dev; extern void pcie_clear_root_pme_status(struct pci_dev *dev); +#ifdef CONFIG_HOTPLUG_PCI_PCIE +extern bool pciehp_msi_disabled; + +static inline bool pciehp_no_msi(void) +{ + return pciehp_msi_disabled; +} + +#else /* !CONFIG_HOTPLUG_PCI_PCIE */ +static inline bool pciehp_no_msi(void) { return false; } +#endif /* !CONFIG_HOTPLUG_PCI_PCIE */ + #ifdef CONFIG_PCIE_PME extern bool pcie_pme_msi_disabled; diff --git a/drivers/pci/pcie/portdrv_core.c b/drivers/pci/pcie/portdrv_core.c index 595654a1a6a6..2f589a54f9bd 100644 --- a/drivers/pci/pcie/portdrv_core.c +++ b/drivers/pci/pcie/portdrv_core.c @@ -19,6 +19,17 @@ #include "../pci.h" #include "portdrv.h" +bool pciehp_msi_disabled; + +static int __init pciehp_setup(char *str) +{ + if (!strncmp(str, "nomsi", 5)) + pciehp_msi_disabled = true; + + return 1; +} +__setup("pcie_hp=", pciehp_setup); + /** * release_pcie_device - free PCI Express port service device structure * @dev: Port service device to release @@ -189,8 +200,9 @@ static int init_service_irqs(struct pci_dev *dev, int *irqs, int mask) { int i, irq = -1; - /* We have to use INTx if MSI cannot be used for PCIe PME. */ - if ((mask & PCIE_PORT_SERVICE_PME) && pcie_pme_no_msi()) { + /* We have to use INTx if MSI cannot be used for PCIe PME or pciehp. */ + if (((mask & PCIE_PORT_SERVICE_PME) && pcie_pme_no_msi()) || + ((mask & PCIE_PORT_SERVICE_HP) && pciehp_no_msi())) { if (dev->pin) irq = dev->irq; goto no_msi; diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 71eac9cd724d..5e1ca3c58a7d 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -15,6 +15,8 @@ #define CARDBUS_LATENCY_TIMER 176 /* secondary latency timer */ #define CARDBUS_RESERVE_BUSNR 3 +static LIST_HEAD(pci_host_bridges); + /* Ugh. Need to stop exporting this to modules. */ LIST_HEAD(pci_root_buses); EXPORT_SYMBOL(pci_root_buses); @@ -42,6 +44,82 @@ int no_pci_devices(void) } EXPORT_SYMBOL(no_pci_devices); +static struct pci_host_bridge *pci_host_bridge(struct pci_dev *dev) +{ + struct pci_bus *bus; + struct pci_host_bridge *bridge; + + bus = dev->bus; + while (bus->parent) + bus = bus->parent; + + list_for_each_entry(bridge, &pci_host_bridges, list) { + if (bridge->bus == bus) + return bridge; + } + + return NULL; +} + +static bool resource_contains(struct resource *res1, struct resource *res2) +{ + return res1->start <= res2->start && res1->end >= res2->end; +} + +void pcibios_resource_to_bus(struct pci_dev *dev, struct pci_bus_region *region, + struct resource *res) +{ + struct pci_host_bridge *bridge = pci_host_bridge(dev); + struct pci_host_bridge_window *window; + resource_size_t offset = 0; + + list_for_each_entry(window, &bridge->windows, list) { + if (resource_type(res) != resource_type(window->res)) + continue; + + if (resource_contains(window->res, res)) { + offset = window->offset; + break; + } + } + + region->start = res->start - offset; + region->end = res->end - offset; +} +EXPORT_SYMBOL(pcibios_resource_to_bus); + +static bool region_contains(struct pci_bus_region *region1, + struct pci_bus_region *region2) +{ + return region1->start <= region2->start && region1->end >= region2->end; +} + +void pcibios_bus_to_resource(struct pci_dev *dev, struct resource *res, + struct pci_bus_region *region) +{ + struct pci_host_bridge *bridge = pci_host_bridge(dev); + struct pci_host_bridge_window *window; + struct pci_bus_region bus_region; + resource_size_t offset = 0; + + list_for_each_entry(window, &bridge->windows, list) { + if (resource_type(res) != resource_type(window->res)) + continue; + + bus_region.start = window->res->start - window->offset; + bus_region.end = window->res->end - window->offset; + + if (region_contains(&bus_region, region)) { + offset = window->offset; + break; + } + } + + res->start = region->start + offset; + res->end = region->end + offset; +} +EXPORT_SYMBOL(pcibios_bus_to_resource); + /* * PCI Bus Class */ @@ -135,6 +213,7 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type, { u32 l, sz, mask; u16 orig_cmd; + struct pci_bus_region region; mask = type ? PCI_ROM_ADDRESS_MASK : ~0; @@ -214,11 +293,13 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type, /* Address above 32-bit boundary; disable the BAR */ pci_write_config_dword(dev, pos, 0); pci_write_config_dword(dev, pos + 4, 0); - res->start = 0; - res->end = sz64; + region.start = 0; + region.end = sz64; + pcibios_bus_to_resource(dev, res, ®ion); } else { - res->start = l64; - res->end = l64 + sz64; + region.start = l64; + region.end = l64 + sz64; + pcibios_bus_to_resource(dev, res, ®ion); dev_printk(KERN_DEBUG, &dev->dev, "reg %x: %pR\n", pos, res); } @@ -228,8 +309,9 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type, if (!sz) goto fail; - res->start = l; - res->end = l + sz; + region.start = l; + region.end = l + sz; + pcibios_bus_to_resource(dev, res, ®ion); dev_printk(KERN_DEBUG, &dev->dev, "reg %x: %pR\n", pos, res); } @@ -266,7 +348,8 @@ static void __devinit pci_read_bridge_io(struct pci_bus *child) struct pci_dev *dev = child->self; u8 io_base_lo, io_limit_lo; unsigned long base, limit; - struct resource *res; + struct pci_bus_region region; + struct resource *res, res2; res = child->resource[0]; pci_read_config_byte(dev, PCI_IO_BASE, &io_base_lo); @@ -284,10 +367,14 @@ static void __devinit pci_read_bridge_io(struct pci_bus *child) if (base && base <= limit) { res->flags = (io_base_lo & PCI_IO_RANGE_TYPE_MASK) | IORESOURCE_IO; + res2.flags = res->flags; + region.start = base; + region.end = limit + 0xfff; + pcibios_bus_to_resource(dev, &res2, ®ion); if (!res->start) - res->start = base; + res->start = res2.start; if (!res->end) - res->end = limit + 0xfff; + res->end = res2.end; dev_printk(KERN_DEBUG, &dev->dev, " bridge window %pR\n", res); } } @@ -297,6 +384,7 @@ static void __devinit pci_read_bridge_mmio(struct pci_bus *child) struct pci_dev *dev = child->self; u16 mem_base_lo, mem_limit_lo; unsigned long base, limit; + struct pci_bus_region region; struct resource *res; res = child->resource[1]; @@ -306,8 +394,9 @@ static void __devinit pci_read_bridge_mmio(struct pci_bus *child) limit = (mem_limit_lo & PCI_MEMORY_RANGE_MASK) << 16; if (base && base <= limit) { res->flags = (mem_base_lo & PCI_MEMORY_RANGE_TYPE_MASK) | IORESOURCE_MEM; - res->start = base; - res->end = limit + 0xfffff; + region.start = base; + region.end = limit + 0xfffff; + pcibios_bus_to_resource(dev, res, ®ion); dev_printk(KERN_DEBUG, &dev->dev, " bridge window %pR\n", res); } } @@ -317,6 +406,7 @@ static void __devinit pci_read_bridge_mmio_pref(struct pci_bus *child) struct pci_dev *dev = child->self; u16 mem_base_lo, mem_limit_lo; unsigned long base, limit; + struct pci_bus_region region; struct resource *res; res = child->resource[2]; @@ -353,8 +443,9 @@ static void __devinit pci_read_bridge_mmio_pref(struct pci_bus *child) IORESOURCE_MEM | IORESOURCE_PREFETCH; if (res->flags & PCI_PREF_RANGE_TYPE_64) res->flags |= IORESOURCE_MEM_64; - res->start = base; - res->end = limit + 0xfffff; + region.start = base; + region.end = limit + 0xfffff; + pcibios_bus_to_resource(dev, res, ®ion); dev_printk(KERN_DEBUG, &dev->dev, " bridge window %pR\n", res); } } @@ -900,6 +991,8 @@ int pci_setup_device(struct pci_dev *dev) u8 hdr_type; struct pci_slot *slot; int pos = 0; + struct pci_bus_region region; + struct resource *res; if (pci_read_config_byte(dev, PCI_HEADER_TYPE, &hdr_type)) return -EIO; @@ -926,12 +1019,10 @@ int pci_setup_device(struct pci_dev *dev) pci_read_config_dword(dev, PCI_CLASS_REVISION, &class); dev->revision = class & 0xff; - class >>= 8; /* upper 3 bytes */ - dev->class = class; - class >>= 8; + dev->class = class >> 8; /* upper 3 bytes */ - dev_printk(KERN_DEBUG, &dev->dev, "[%04x:%04x] type %d class %#08x\n", - dev->vendor, dev->device, dev->hdr_type, class); + dev_printk(KERN_DEBUG, &dev->dev, "[%04x:%04x] type %02x class %#08x\n", + dev->vendor, dev->device, dev->hdr_type, dev->class); /* need to have dev->class ready */ dev->cfg_size = pci_cfg_space_size(dev); @@ -963,20 +1054,28 @@ int pci_setup_device(struct pci_dev *dev) u8 progif; pci_read_config_byte(dev, PCI_CLASS_PROG, &progif); if ((progif & 1) == 0) { - dev->resource[0].start = 0x1F0; - dev->resource[0].end = 0x1F7; - dev->resource[0].flags = LEGACY_IO_RESOURCE; - dev->resource[1].start = 0x3F6; - dev->resource[1].end = 0x3F6; - dev->resource[1].flags = LEGACY_IO_RESOURCE; + region.start = 0x1F0; + region.end = 0x1F7; + res = &dev->resource[0]; + res->flags = LEGACY_IO_RESOURCE; + pcibios_bus_to_resource(dev, res, ®ion); + region.start = 0x3F6; + region.end = 0x3F6; + res = &dev->resource[1]; + res->flags = LEGACY_IO_RESOURCE; + pcibios_bus_to_resource(dev, res, ®ion); } if ((progif & 4) == 0) { - dev->resource[2].start = 0x170; - dev->resource[2].end = 0x177; - dev->resource[2].flags = LEGACY_IO_RESOURCE; - dev->resource[3].start = 0x376; - dev->resource[3].end = 0x376; - dev->resource[3].flags = LEGACY_IO_RESOURCE; + region.start = 0x170; + region.end = 0x177; + res = &dev->resource[2]; + res->flags = LEGACY_IO_RESOURCE; + pcibios_bus_to_resource(dev, res, ®ion); + region.start = 0x376; + region.end = 0x376; + res = &dev->resource[3]; + res->flags = LEGACY_IO_RESOURCE; + pcibios_bus_to_resource(dev, res, ®ion); } } break; @@ -1013,8 +1112,8 @@ int pci_setup_device(struct pci_dev *dev) return -EIO; bad: - dev_err(&dev->dev, "ignoring class %02x (doesn't match header " - "type %02x)\n", class, dev->hdr_type); + dev_err(&dev->dev, "ignoring class %#08x (doesn't match header " + "type %02x)\n", dev->class, dev->hdr_type); dev->class = PCI_CLASS_NOT_DEFINED; } @@ -1026,6 +1125,7 @@ static void pci_release_capabilities(struct pci_dev *dev) { pci_vpd_release(dev); pci_iov_release(dev); + pci_free_cap_save_buffers(dev); } /** @@ -1118,40 +1218,54 @@ struct pci_dev *alloc_pci_dev(void) } EXPORT_SYMBOL(alloc_pci_dev); -/* - * Read the config data for a PCI device, sanity-check it - * and fill in the dev structure... - */ -static struct pci_dev *pci_scan_device(struct pci_bus *bus, int devfn) +bool pci_bus_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *l, + int crs_timeout) { - struct pci_dev *dev; - u32 l; int delay = 1; - if (pci_bus_read_config_dword(bus, devfn, PCI_VENDOR_ID, &l)) - return NULL; + if (pci_bus_read_config_dword(bus, devfn, PCI_VENDOR_ID, l)) + return false; /* some broken boards return 0 or ~0 if a slot is empty: */ - if (l == 0xffffffff || l == 0x00000000 || - l == 0x0000ffff || l == 0xffff0000) - return NULL; + if (*l == 0xffffffff || *l == 0x00000000 || + *l == 0x0000ffff || *l == 0xffff0000) + return false; /* Configuration request Retry Status */ - while (l == 0xffff0001) { + while (*l == 0xffff0001) { + if (!crs_timeout) + return false; + msleep(delay); delay *= 2; - if (pci_bus_read_config_dword(bus, devfn, PCI_VENDOR_ID, &l)) - return NULL; + if (pci_bus_read_config_dword(bus, devfn, PCI_VENDOR_ID, l)) + return false; /* Card hasn't responded in 60 seconds? Must be stuck. */ - if (delay > 60 * 1000) { + if (delay > crs_timeout) { printk(KERN_WARNING "pci %04x:%02x:%02x.%d: not " "responding\n", pci_domain_nr(bus), bus->number, PCI_SLOT(devfn), PCI_FUNC(devfn)); - return NULL; + return false; } } + return true; +} +EXPORT_SYMBOL(pci_bus_read_dev_vendor_id); + +/* + * Read the config data for a PCI device, sanity-check it + * and fill in the dev structure... + */ +static struct pci_dev *pci_scan_device(struct pci_bus *bus, int devfn) +{ + struct pci_dev *dev; + u32 l; + + if (!pci_bus_read_dev_vendor_id(bus, devfn, &l, 60*1000)) + return NULL; + dev = alloc_pci_dev(); if (!dev) return NULL; @@ -1212,6 +1326,9 @@ void pci_device_add(struct pci_dev *dev, struct pci_bus *bus) /* Fix up broken headers */ pci_fixup_device(pci_fixup_header, dev); + /* moved out from quirk header fixup code */ + pci_reassigndev_resource_alignment(dev); + /* Clear the state_saved flag. */ dev->state_saved = false; @@ -1530,21 +1647,27 @@ unsigned int __devinit pci_scan_child_bus(struct pci_bus *bus) struct pci_bus *pci_create_root_bus(struct device *parent, int bus, struct pci_ops *ops, void *sysdata, struct list_head *resources) { - int error, i; + int error; + struct pci_host_bridge *bridge; struct pci_bus *b, *b2; struct device *dev; - struct pci_bus_resource *bus_res, *n; + struct pci_host_bridge_window *window, *n; struct resource *res; + resource_size_t offset; + char bus_addr[64]; + char *fmt; + + bridge = kzalloc(sizeof(*bridge), GFP_KERNEL); + if (!bridge) + return NULL; b = pci_alloc_bus(); if (!b) - return NULL; + goto err_bus; dev = kzalloc(sizeof(*dev), GFP_KERNEL); - if (!dev) { - kfree(b); - return NULL; - } + if (!dev) + goto err_dev; b->sysdata = sysdata; b->ops = ops; @@ -1556,10 +1679,6 @@ struct pci_bus *pci_create_root_bus(struct device *parent, int bus, goto err_out; } - down_write(&pci_bus_sem); - list_add_tail(&b->node, &pci_root_buses); - up_write(&pci_bus_sem); - dev->parent = parent; dev->release = pci_release_bus_bridge_dev; dev_set_name(dev, "pci%04x:%02x", pci_domain_nr(b), bus); @@ -1585,31 +1704,53 @@ struct pci_bus *pci_create_root_bus(struct device *parent, int bus, b->number = b->secondary = bus; - /* Add initial resources to the bus */ - list_for_each_entry_safe(bus_res, n, resources, list) - list_move_tail(&bus_res->list, &b->resources); + bridge->bus = b; + INIT_LIST_HEAD(&bridge->windows); if (parent) dev_info(parent, "PCI host bridge to bus %s\n", dev_name(&b->dev)); else printk(KERN_INFO "PCI host bridge to bus %s\n", dev_name(&b->dev)); - pci_bus_for_each_resource(b, res, i) { - if (res) - dev_info(&b->dev, "root bus resource %pR\n", res); + /* Add initial resources to the bus */ + list_for_each_entry_safe(window, n, resources, list) { + list_move_tail(&window->list, &bridge->windows); + res = window->res; + offset = window->offset; + pci_bus_add_resource(b, res, 0); + if (offset) { + if (resource_type(res) == IORESOURCE_IO) + fmt = " (bus address [%#06llx-%#06llx])"; + else + fmt = " (bus address [%#010llx-%#010llx])"; + snprintf(bus_addr, sizeof(bus_addr), fmt, + (unsigned long long) (res->start - offset), + (unsigned long long) (res->end - offset)); + } else + bus_addr[0] = '\0'; + dev_info(&b->dev, "root bus resource %pR%s\n", res, bus_addr); } + down_write(&pci_bus_sem); + list_add_tail(&bridge->list, &pci_host_bridges); + list_add_tail(&b->node, &pci_root_buses); + up_write(&pci_bus_sem); + return b; class_dev_reg_err: device_unregister(dev); dev_reg_err: down_write(&pci_bus_sem); + list_del(&bridge->list); list_del(&b->node); up_write(&pci_bus_sem); err_out: kfree(dev); +err_dev: kfree(b); +err_bus: + kfree(bridge); return NULL; } @@ -1667,36 +1808,29 @@ EXPORT_SYMBOL(pci_scan_bus); #ifdef CONFIG_HOTPLUG /** - * pci_rescan_bus - scan a PCI bus for devices. - * @bus: PCI bus to scan + * pci_rescan_bus_bridge_resize - scan a PCI bus for devices. + * @bridge: PCI bridge for the bus to scan * - * Scan a PCI bus and child buses for new devices, adds them, - * and enables them. + * Scan a PCI bus and child buses for new devices, add them, + * and enable them, resizing bridge mmio/io resource if necessary + * and possible. The caller must ensure the child devices are already + * removed for resizing to occur. * * Returns the max number of subordinate bus discovered. */ -unsigned int __ref pci_rescan_bus(struct pci_bus *bus) +unsigned int __ref pci_rescan_bus_bridge_resize(struct pci_dev *bridge) { unsigned int max; - struct pci_dev *dev; + struct pci_bus *bus = bridge->subordinate; max = pci_scan_child_bus(bus); - down_read(&pci_bus_sem); - list_for_each_entry(dev, &bus->devices, bus_list) - if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE || - dev->hdr_type == PCI_HEADER_TYPE_CARDBUS) - if (dev->subordinate) - pci_bus_size_bridges(dev->subordinate); - up_read(&pci_bus_sem); + pci_assign_unassigned_bridge_resources(bridge); - pci_bus_assign_resources(bus); - pci_enable_bridges(bus); pci_bus_add_devices(bus); return max; } -EXPORT_SYMBOL_GPL(pci_rescan_bus); EXPORT_SYMBOL(pci_add_new_bus); EXPORT_SYMBOL(pci_scan_slot); diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 64765474676f..4bf71028556b 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -26,73 +26,12 @@ #include <linux/dmi.h> #include <linux/pci-aspm.h> #include <linux/ioport.h> +#include <linux/sched.h> +#include <linux/ktime.h> #include <asm/dma.h> /* isa_dma_bridge_buggy */ #include "pci.h" /* - * This quirk function disables memory decoding and releases memory resources - * of the device specified by kernel's boot parameter 'pci=resource_alignment='. - * It also rounds up size to specified alignment. - * Later on, the kernel will assign page-aligned memory resource back - * to the device. - */ -static void __devinit quirk_resource_alignment(struct pci_dev *dev) -{ - int i; - struct resource *r; - resource_size_t align, size; - u16 command; - - if (!pci_is_reassigndev(dev)) - return; - - if (dev->hdr_type == PCI_HEADER_TYPE_NORMAL && - (dev->class >> 8) == PCI_CLASS_BRIDGE_HOST) { - dev_warn(&dev->dev, - "Can't reassign resources to host bridge.\n"); - return; - } - - dev_info(&dev->dev, - "Disabling memory decoding and releasing memory resources.\n"); - pci_read_config_word(dev, PCI_COMMAND, &command); - command &= ~PCI_COMMAND_MEMORY; - pci_write_config_word(dev, PCI_COMMAND, command); - - align = pci_specified_resource_alignment(dev); - for (i=0; i < PCI_BRIDGE_RESOURCES; i++) { - r = &dev->resource[i]; - if (!(r->flags & IORESOURCE_MEM)) - continue; - size = resource_size(r); - if (size < align) { - size = align; - dev_info(&dev->dev, - "Rounding up size of resource #%d to %#llx.\n", - i, (unsigned long long)size); - } - r->end = size - 1; - r->start = 0; - } - /* Need to disable bridge's resource window, - * to enable the kernel to reassign new resource - * window later on. - */ - if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE && - (dev->class >> 8) == PCI_CLASS_BRIDGE_PCI) { - for (i = PCI_BRIDGE_RESOURCES; i < PCI_NUM_RESOURCES; i++) { - r = &dev->resource[i]; - if (!(r->flags & IORESOURCE_MEM)) - continue; - r->end = resource_size(r) - 1; - r->start = 0; - } - pci_disable_bridge_window(dev); - } -} -DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, quirk_resource_alignment); - -/* * Decoding should be disabled for a PCI device during BAR sizing to avoid * conflict. But doing so may cause problems on host bridge and perhaps other * key system devices. For devices that need to have mmio decoding always-on, @@ -100,10 +39,10 @@ DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, quirk_resource_alignment); */ static void __devinit quirk_mmio_always_on(struct pci_dev *dev) { - if ((dev->class >> 8) == PCI_CLASS_BRIDGE_HOST) - dev->mmio_always_on = 1; + dev->mmio_always_on = 1; } -DECLARE_PCI_FIXUP_EARLY(PCI_ANY_ID, PCI_ANY_ID, quirk_mmio_always_on); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_ANY_ID, PCI_ANY_ID, + PCI_CLASS_BRIDGE_HOST, 8, quirk_mmio_always_on); /* The Mellanox Tavor device gives false positive parity errors * Mark this device with a broken_parity_status, to allow @@ -1002,12 +941,12 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_82C597_0, quirk_vt */ static void quirk_cardbus_legacy(struct pci_dev *dev) { - if ((PCI_CLASS_BRIDGE_CARDBUS << 8) ^ dev->class) - return; pci_write_config_dword(dev, PCI_CB_LEGACY_MODE_BASE, 0); } -DECLARE_PCI_FIXUP_FINAL(PCI_ANY_ID, PCI_ANY_ID, quirk_cardbus_legacy); -DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_ANY_ID, PCI_ANY_ID, quirk_cardbus_legacy); +DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_ANY_ID, PCI_ANY_ID, + PCI_CLASS_BRIDGE_CARDBUS, 8, quirk_cardbus_legacy); +DECLARE_PCI_FIXUP_CLASS_RESUME_EARLY(PCI_ANY_ID, PCI_ANY_ID, + PCI_CLASS_BRIDGE_CARDBUS, 8, quirk_cardbus_legacy); /* * Following the PCI ordering rules is optional on the AMD762. I'm not @@ -1164,17 +1103,20 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82801CA_10, qui static void __devinit quirk_no_ata_d3(struct pci_dev *pdev) { - /* Quirk the legacy ATA devices only. The AHCI ones are ok */ - if ((pdev->class >> 8) == PCI_CLASS_STORAGE_IDE) - pdev->dev_flags |= PCI_DEV_FLAGS_NO_D3; + pdev->dev_flags |= PCI_DEV_FLAGS_NO_D3; } -DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, PCI_ANY_ID, quirk_no_ata_d3); -DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_ATI, PCI_ANY_ID, quirk_no_ata_d3); +/* Quirk the legacy ATA devices only. The AHCI ones are ok */ +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_SERVERWORKS, PCI_ANY_ID, + PCI_CLASS_STORAGE_IDE, 8, quirk_no_ata_d3); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_ATI, PCI_ANY_ID, + PCI_CLASS_STORAGE_IDE, 8, quirk_no_ata_d3); /* ALi loses some register settings that we cannot then restore */ -DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AL, PCI_ANY_ID, quirk_no_ata_d3); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_AL, PCI_ANY_ID, + PCI_CLASS_STORAGE_IDE, 8, quirk_no_ata_d3); /* VIA comes back fine but we need to keep it alive or ACPI GTM failures occur when mode detecting */ -DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_VIA, PCI_ANY_ID, quirk_no_ata_d3); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_VIA, PCI_ANY_ID, + PCI_CLASS_STORAGE_IDE, 8, quirk_no_ata_d3); /* This was originally an Alpha specific thing, but it really fits here. * The i82375 PCI/EISA bridge appears as non-classified. Fix that. @@ -1873,8 +1815,7 @@ static void __devinit quirk_netmos(struct pci_dev *dev) case PCI_DEVICE_ID_NETMOS_9745: case PCI_DEVICE_ID_NETMOS_9845: case PCI_DEVICE_ID_NETMOS_9855: - if ((dev->class >> 8) == PCI_CLASS_COMMUNICATION_SERIAL && - num_parallel) { + if (num_parallel) { dev_info(&dev->dev, "Netmos %04x (%u parallel, " "%u serial); changing class SERIAL to OTHER " "(use parport_serial)\n", @@ -1884,7 +1825,8 @@ static void __devinit quirk_netmos(struct pci_dev *dev) } } } -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NETMOS, PCI_ANY_ID, quirk_netmos); +DECLARE_PCI_FIXUP_CLASS_HEADER(PCI_VENDOR_ID_NETMOS, PCI_ANY_ID, + PCI_CLASS_COMMUNICATION_SERIAL, 8, quirk_netmos); static void __devinit quirk_e100_interrupt(struct pci_dev *dev) { @@ -1952,7 +1894,8 @@ static void __devinit quirk_e100_interrupt(struct pci_dev *dev) iounmap(csr); } -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_ANY_ID, quirk_e100_interrupt); +DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_INTEL, PCI_ANY_ID, + PCI_CLASS_NETWORK_ETHERNET, 8, quirk_e100_interrupt); /* * The 82575 and 82598 may experience data corruption issues when transitioning @@ -2161,6 +2104,24 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_NX2_5709S, quirk_brcm_570x_limit_vpd); +static void __devinit quirk_brcm_5719_limit_mrrs(struct pci_dev *dev) +{ + u32 rev; + + pci_read_config_dword(dev, 0xf4, &rev); + + /* Only CAP the MRRS if the device is a 5719 A0 */ + if (rev == 0x05719000) { + int readrq = pcie_get_readrq(dev); + if (readrq > 2048) + pcie_set_readrq(dev, 2048); + } +} + +DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_BROADCOM, + PCI_DEVICE_ID_TIGON3_5719, + quirk_brcm_5719_limit_mrrs); + /* Originally in EDAC sources for i82875P: * Intel tells BIOS developers to hide device 6 which * configures the overflow device access containing @@ -2816,12 +2777,11 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x3c28, vtd_mask_spec_errors); 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; - } + 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); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_TI, 0xb800, + PCI_CLASS_NOT_DEFINED, 0, fixup_ti816x_class); /* Some PCIe devices do not work reliably with the claimed maximum * payload size supported. @@ -2906,17 +2866,73 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x65f8, quirk_intel_mc_errata); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x65f9, quirk_intel_mc_errata); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x65fa, quirk_intel_mc_errata); + +static void do_one_fixup_debug(void (*fn)(struct pci_dev *dev), struct pci_dev *dev) +{ + ktime_t calltime, delta, rettime; + unsigned long long duration; + + printk(KERN_DEBUG "calling %pF @ %i for %s\n", + fn, task_pid_nr(current), dev_name(&dev->dev)); + calltime = ktime_get(); + fn(dev); + rettime = ktime_get(); + delta = ktime_sub(rettime, calltime); + duration = (unsigned long long) ktime_to_ns(delta) >> 10; + printk(KERN_DEBUG "pci fixup %pF returned after %lld usecs for %s\n", + fn, duration, dev_name(&dev->dev)); +} + +/* + * Some BIOS implementations leave the Intel GPU interrupts enabled, + * even though no one is handling them (f.e. i915 driver is never loaded). + * Additionally the interrupt destination is not set up properly + * and the interrupt ends up -somewhere-. + * + * These spurious interrupts are "sticky" and the kernel disables + * the (shared) interrupt line after 100.000+ generated interrupts. + * + * Fix it by disabling the still enabled interrupts. + * This resolves crashes often seen on monitor unplug. + */ +#define I915_DEIER_REG 0x4400c +static void __devinit disable_igfx_irq(struct pci_dev *dev) +{ + void __iomem *regs = pci_iomap(dev, 0, 0); + if (regs == NULL) { + dev_warn(&dev->dev, "igfx quirk: Can't iomap PCI device\n"); + return; + } + + /* Check if any interrupt line is still enabled */ + if (readl(regs + I915_DEIER_REG) != 0) { + dev_warn(&dev->dev, "BIOS left Intel GPU interrupts enabled; " + "disabling\n"); + + writel(0, regs + I915_DEIER_REG); + } + + pci_iounmap(dev, regs); +} +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0102, disable_igfx_irq); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x010a, disable_igfx_irq); + static void pci_do_fixups(struct pci_dev *dev, struct pci_fixup *f, struct pci_fixup *end) { - while (f < end) { - if ((f->vendor == dev->vendor || f->vendor == (u16) PCI_ANY_ID) && - (f->device == dev->device || f->device == (u16) PCI_ANY_ID)) { + for (; f < end; f++) + if ((f->class == (u32) (dev->class >> f->class_shift) || + f->class == (u32) PCI_ANY_ID) && + (f->vendor == dev->vendor || + f->vendor == (u16) PCI_ANY_ID) && + (f->device == dev->device || + f->device == (u16) PCI_ANY_ID)) { dev_dbg(&dev->dev, "calling %pF\n", f->hook); - f->hook(dev); + if (initcall_debug) + do_one_fixup_debug(f->hook, dev); + else + f->hook(dev); } - f++; - } } extern struct pci_fixup __start_pci_fixups_early[]; diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c index ef8b18c48f26..fd77e2bde2e8 100644 --- a/drivers/pci/remove.c +++ b/drivers/pci/remove.c @@ -79,7 +79,7 @@ EXPORT_SYMBOL(pci_remove_bus); static void __pci_remove_behind_bridge(struct pci_dev *dev); /** - * pci_remove_bus_device - remove a PCI device and any children + * pci_stop_and_remove_bus_device - remove a PCI device and any children * @dev: the device to remove * * Remove a PCI device from the device lists, informing the drivers @@ -90,7 +90,7 @@ static void __pci_remove_behind_bridge(struct pci_dev *dev); * device lists, remove the /proc entry, and notify userspace * (/sbin/hotplug). */ -static void __pci_remove_bus_device(struct pci_dev *dev) +void __pci_remove_bus_device(struct pci_dev *dev) { if (dev->subordinate) { struct pci_bus *b = dev->subordinate; @@ -102,7 +102,9 @@ static void __pci_remove_bus_device(struct pci_dev *dev) pci_destroy_dev(dev); } -void pci_remove_bus_device(struct pci_dev *dev) +EXPORT_SYMBOL(__pci_remove_bus_device); + +void pci_stop_and_remove_bus_device(struct pci_dev *dev) { pci_stop_bus_device(dev); __pci_remove_bus_device(dev); @@ -127,14 +129,15 @@ static void pci_stop_behind_bridge(struct pci_dev *dev) } /** - * pci_remove_behind_bridge - remove all devices behind a PCI bridge + * pci_stop_and_remove_behind_bridge - stop and remove all devices behind + * a PCI bridge * @dev: PCI bridge device * * Remove all devices on the bus, except for the parent bridge. * This also removes any child buses, and any devices they may * contain in a depth-first manner. */ -void pci_remove_behind_bridge(struct pci_dev *dev) +void pci_stop_and_remove_behind_bridge(struct pci_dev *dev) { pci_stop_behind_bridge(dev); __pci_remove_behind_bridge(dev); @@ -144,7 +147,15 @@ static void pci_stop_bus_devices(struct pci_bus *bus) { struct list_head *l, *n; - list_for_each_safe(l, n, &bus->devices) { + /* + * VFs could be removed by pci_stop_and_remove_bus_device() in the + * pci_stop_bus_devices() code path for PF. + * aka, bus->devices get updated in the process. + * but VFs are inserted after PFs when SRIOV is enabled for PF, + * We can iterate the list backwards to get prev valid PF instead + * of removed VF. + */ + list_for_each_prev_safe(l, n, &bus->devices) { struct pci_dev *dev = pci_dev_b(l); pci_stop_bus_device(dev); } @@ -166,6 +177,6 @@ void pci_stop_bus_device(struct pci_dev *dev) pci_stop_dev(dev); } -EXPORT_SYMBOL(pci_remove_bus_device); -EXPORT_SYMBOL(pci_remove_behind_bridge); +EXPORT_SYMBOL(pci_stop_and_remove_bus_device); +EXPORT_SYMBOL(pci_stop_and_remove_behind_bridge); EXPORT_SYMBOL_GPL(pci_stop_bus_device); diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c index 86b69f85f900..8fa2d4be88de 100644 --- a/drivers/pci/setup-bus.c +++ b/drivers/pci/setup-bus.c @@ -25,10 +25,13 @@ #include <linux/ioport.h> #include <linux/cache.h> #include <linux/slab.h> +#include <asm-generic/pci-bridge.h> #include "pci.h" -struct resource_list_x { - struct resource_list_x *next; +unsigned int pci_flags; + +struct pci_dev_resource { + struct list_head list; struct resource *res; struct pci_dev *dev; resource_size_t start; @@ -38,21 +41,14 @@ struct resource_list_x { unsigned long flags; }; -#define free_list(type, head) do { \ - struct type *list, *tmp; \ - for (list = (head)->next; list;) { \ - tmp = list; \ - list = list->next; \ - kfree(tmp); \ - } \ - (head)->next = NULL; \ -} while (0) - -int pci_realloc_enable = 0; -#define pci_realloc_enabled() pci_realloc_enable -void pci_realloc(void) +static void free_list(struct list_head *head) { - pci_realloc_enable = 1; + struct pci_dev_resource *dev_res, *tmp; + + list_for_each_entry_safe(dev_res, tmp, head, list) { + list_del(&dev_res->list); + kfree(dev_res); + } } /** @@ -64,21 +60,18 @@ void pci_realloc(void) * @add_size: additional size to be optionally added * to the resource */ -static void add_to_list(struct resource_list_x *head, +static int add_to_list(struct list_head *head, struct pci_dev *dev, struct resource *res, resource_size_t add_size, resource_size_t min_align) { - struct resource_list_x *list = head; - struct resource_list_x *ln = list->next; - struct resource_list_x *tmp; + struct pci_dev_resource *tmp; - tmp = kmalloc(sizeof(*tmp), GFP_KERNEL); + tmp = kzalloc(sizeof(*tmp), GFP_KERNEL); if (!tmp) { pr_warning("add_to_list: kmalloc() failed!\n"); - return; + return -ENOMEM; } - tmp->next = ln; tmp->res = res; tmp->dev = dev; tmp->start = res->start; @@ -86,19 +79,100 @@ static void add_to_list(struct resource_list_x *head, tmp->flags = res->flags; tmp->add_size = add_size; tmp->min_align = min_align; - list->next = tmp; + + list_add(&tmp->list, head); + + return 0; } -static void add_to_failed_list(struct resource_list_x *head, - struct pci_dev *dev, struct resource *res) +static void remove_from_list(struct list_head *head, + struct resource *res) { - add_to_list(head, dev, res, - 0 /* dont care */, - 0 /* dont care */); + struct pci_dev_resource *dev_res, *tmp; + + list_for_each_entry_safe(dev_res, tmp, head, list) { + if (dev_res->res == res) { + list_del(&dev_res->list); + kfree(dev_res); + break; + } + } +} + +static resource_size_t get_res_add_size(struct list_head *head, + struct resource *res) +{ + struct pci_dev_resource *dev_res; + + list_for_each_entry(dev_res, head, list) { + if (dev_res->res == res) { + int idx = res - &dev_res->dev->resource[0]; + + dev_printk(KERN_DEBUG, &dev_res->dev->dev, + "res[%d]=%pR get_res_add_size add_size %llx\n", + idx, dev_res->res, + (unsigned long long)dev_res->add_size); + + return dev_res->add_size; + } + } + + return 0; +} + +/* Sort resources by alignment */ +static void pdev_sort_resources(struct pci_dev *dev, struct list_head *head) +{ + int i; + + for (i = 0; i < PCI_NUM_RESOURCES; i++) { + struct resource *r; + struct pci_dev_resource *dev_res, *tmp; + resource_size_t r_align; + struct list_head *n; + + r = &dev->resource[i]; + + if (r->flags & IORESOURCE_PCI_FIXED) + continue; + + if (!(r->flags) || r->parent) + continue; + + r_align = pci_resource_alignment(dev, r); + if (!r_align) { + dev_warn(&dev->dev, "BAR %d: %pR has bogus alignment\n", + i, r); + continue; + } + + tmp = kzalloc(sizeof(*tmp), GFP_KERNEL); + if (!tmp) + panic("pdev_sort_resources(): " + "kmalloc() failed!\n"); + tmp->res = r; + tmp->dev = dev; + + /* fallback is smallest one or list is empty*/ + n = head; + list_for_each_entry(dev_res, head, list) { + resource_size_t align; + + align = pci_resource_alignment(dev_res->dev, + dev_res->res); + + if (r_align > align) { + n = &dev_res->list; + break; + } + } + /* Insert it just before n*/ + list_add_tail(&tmp->list, n); + } } static void __dev_sort_resources(struct pci_dev *dev, - struct resource_list *head) + struct list_head *head) { u16 class = dev->class >> 8; @@ -136,49 +210,54 @@ static inline void reset_resource(struct resource *res) * additional resources for the element, provided the element * is in the head list. */ -static void reassign_resources_sorted(struct resource_list_x *realloc_head, - struct resource_list *head) +static void reassign_resources_sorted(struct list_head *realloc_head, + struct list_head *head) { struct resource *res; - struct resource_list_x *list, *tmp, *prev; - struct resource_list *hlist; + struct pci_dev_resource *add_res, *tmp; + struct pci_dev_resource *dev_res; resource_size_t add_size; int idx; - prev = realloc_head; - for (list = realloc_head->next; list;) { - res = list->res; + list_for_each_entry_safe(add_res, tmp, realloc_head, list) { + bool found_match = false; + + res = add_res->res; /* skip resource that has been reset */ if (!res->flags) goto out; /* skip this resource if not found in head list */ - for (hlist = head->next; hlist && hlist->res != res; - hlist = hlist->next); - if (!hlist) { /* just skip */ - prev = list; - list = list->next; - continue; + list_for_each_entry(dev_res, head, list) { + if (dev_res->res == res) { + found_match = true; + break; + } } + if (!found_match)/* just skip */ + continue; - idx = res - &list->dev->resource[0]; - add_size=list->add_size; + idx = res - &add_res->dev->resource[0]; + add_size = add_res->add_size; if (!resource_size(res)) { - res->start = list->start; + res->start = add_res->start; res->end = res->start + add_size - 1; - if(pci_assign_resource(list->dev, idx)) + if (pci_assign_resource(add_res->dev, idx)) reset_resource(res); } else { - resource_size_t align = list->min_align; - res->flags |= list->flags & (IORESOURCE_STARTALIGN|IORESOURCE_SIZEALIGN); - if (pci_reassign_resource(list->dev, idx, add_size, align)) - dev_printk(KERN_DEBUG, &list->dev->dev, "failed to add optional resources res=%pR\n", - res); + resource_size_t align = add_res->min_align; + res->flags |= add_res->flags & + (IORESOURCE_STARTALIGN|IORESOURCE_SIZEALIGN); + if (pci_reassign_resource(add_res->dev, idx, + add_size, align)) + dev_printk(KERN_DEBUG, &add_res->dev->dev, + "failed to add %llx res[%d]=%pR\n", + (unsigned long long)add_size, + idx, res); } out: - tmp = list; - prev->next = list = list->next; - kfree(tmp); + list_del(&add_res->list); + kfree(add_res); } } @@ -192,35 +271,99 @@ out: * Satisfy resource requests of each element in the list. Add * requests that could not satisfied to the failed_list. */ -static void assign_requested_resources_sorted(struct resource_list *head, - struct resource_list_x *fail_head) +static void assign_requested_resources_sorted(struct list_head *head, + struct list_head *fail_head) { struct resource *res; - struct resource_list *list; + struct pci_dev_resource *dev_res; int idx; - for (list = head->next; list; list = list->next) { - res = list->res; - idx = res - &list->dev->resource[0]; - if (resource_size(res) && pci_assign_resource(list->dev, idx)) { - if (fail_head && !pci_is_root_bus(list->dev->bus)) { + list_for_each_entry(dev_res, head, list) { + res = dev_res->res; + idx = res - &dev_res->dev->resource[0]; + if (resource_size(res) && + pci_assign_resource(dev_res->dev, idx)) { + if (fail_head && !pci_is_root_bus(dev_res->dev->bus)) { /* * if the failed res is for ROM BAR, and it will * be enabled later, don't add it to the list */ if (!((idx == PCI_ROM_RESOURCE) && (!(res->flags & IORESOURCE_ROM_ENABLE)))) - add_to_failed_list(fail_head, list->dev, res); + add_to_list(fail_head, + dev_res->dev, res, + 0 /* dont care */, + 0 /* dont care */); } reset_resource(res); } } } -static void __assign_resources_sorted(struct resource_list *head, - struct resource_list_x *realloc_head, - struct resource_list_x *fail_head) +static void __assign_resources_sorted(struct list_head *head, + struct list_head *realloc_head, + struct list_head *fail_head) { + /* + * Should not assign requested resources at first. + * they could be adjacent, so later reassign can not reallocate + * them one by one in parent resource window. + * Try to assign requested + add_size at begining + * if could do that, could get out early. + * if could not do that, we still try to assign requested at first, + * then try to reassign add_size for some resources. + */ + LIST_HEAD(save_head); + LIST_HEAD(local_fail_head); + struct pci_dev_resource *save_res; + struct pci_dev_resource *dev_res; + + /* Check if optional add_size is there */ + if (!realloc_head || list_empty(realloc_head)) + goto requested_and_reassign; + + /* Save original start, end, flags etc at first */ + list_for_each_entry(dev_res, head, list) { + if (add_to_list(&save_head, dev_res->dev, dev_res->res, 0, 0)) { + free_list(&save_head); + goto requested_and_reassign; + } + } + + /* Update res in head list with add_size in realloc_head list */ + list_for_each_entry(dev_res, head, list) + dev_res->res->end += get_res_add_size(realloc_head, + dev_res->res); + + /* Try updated head list with add_size added */ + assign_requested_resources_sorted(head, &local_fail_head); + + /* all assigned with add_size ? */ + if (list_empty(&local_fail_head)) { + /* Remove head list from realloc_head list */ + list_for_each_entry(dev_res, head, list) + remove_from_list(realloc_head, dev_res->res); + free_list(&save_head); + free_list(head); + return; + } + + free_list(&local_fail_head); + /* Release assigned resource */ + list_for_each_entry(dev_res, head, list) + if (dev_res->res->parent) + release_resource(dev_res->res); + /* Restore start/end/flags from saved list */ + list_for_each_entry(save_res, &save_head, list) { + struct resource *res = save_res->res; + + res->start = save_res->start; + res->end = save_res->end; + res->flags = save_res->flags; + } + free_list(&save_head); + +requested_and_reassign: /* Satisfy the must-have resource requests */ assign_requested_resources_sorted(head, fail_head); @@ -228,28 +371,27 @@ static void __assign_resources_sorted(struct resource_list *head, requests */ if (realloc_head) reassign_resources_sorted(realloc_head, head); - free_list(resource_list, head); + free_list(head); } static void pdev_assign_resources_sorted(struct pci_dev *dev, - struct resource_list_x *fail_head) + struct list_head *add_head, + struct list_head *fail_head) { - struct resource_list head; + LIST_HEAD(head); - head.next = NULL; __dev_sort_resources(dev, &head); - __assign_resources_sorted(&head, NULL, fail_head); + __assign_resources_sorted(&head, add_head, fail_head); } static void pbus_assign_resources_sorted(const struct pci_bus *bus, - struct resource_list_x *realloc_head, - struct resource_list_x *fail_head) + struct list_head *realloc_head, + struct list_head *fail_head) { struct pci_dev *dev; - struct resource_list head; + LIST_HEAD(head); - head.next = NULL; list_for_each_entry(dev, &bus->devices, bus_list) __dev_sort_resources(dev, &head); @@ -548,20 +690,6 @@ static resource_size_t calculate_memsize(resource_size_t size, return size; } -static resource_size_t get_res_add_size(struct resource_list_x *realloc_head, - struct resource *res) -{ - struct resource_list_x *list; - - /* check if it is in realloc_head list */ - for (list = realloc_head->next; list && list->res != res; - list = list->next); - if (list) - return list->add_size; - - return 0; -} - /** * pbus_size_io() - size the io window of a given bus * @@ -576,7 +704,7 @@ static resource_size_t get_res_add_size(struct resource_list_x *realloc_head, * We must be careful with the ISA aliasing though. */ static void pbus_size_io(struct pci_bus *bus, resource_size_t min_size, - resource_size_t add_size, struct resource_list_x *realloc_head) + resource_size_t add_size, struct list_head *realloc_head) { struct pci_dev *dev; struct resource *b_res = find_free_bus_resource(bus, IORESOURCE_IO); @@ -612,7 +740,7 @@ static void pbus_size_io(struct pci_bus *bus, resource_size_t min_size, if (children_add_size > add_size) add_size = children_add_size; size1 = (!realloc_head || (realloc_head && !add_size)) ? size0 : - calculate_iosize(size, min_size+add_size, size1, + calculate_iosize(size, min_size, add_size + size1, resource_size(b_res), 4096); if (!size0 && !size1) { if (b_res->start || b_res->end) @@ -626,8 +754,12 @@ static void pbus_size_io(struct pci_bus *bus, resource_size_t min_size, b_res->start = 4096; b_res->end = b_res->start + size0 - 1; b_res->flags |= IORESOURCE_STARTALIGN; - if (size1 > size0 && realloc_head) + if (size1 > size0 && realloc_head) { add_to_list(realloc_head, bus->self, b_res, size1-size0, 4096); + dev_printk(KERN_DEBUG, &bus->self->dev, "bridge window " + "%pR to [bus %02x-%02x] add_size %lx\n", b_res, + bus->secondary, bus->subordinate, size1-size0); + } } /** @@ -644,7 +776,7 @@ static void pbus_size_io(struct pci_bus *bus, resource_size_t min_size, static int pbus_size_mem(struct pci_bus *bus, unsigned long mask, unsigned long type, resource_size_t min_size, resource_size_t add_size, - struct resource_list_x *realloc_head) + struct list_head *realloc_head) { struct pci_dev *dev; resource_size_t min_align, align, size, size0, size1; @@ -726,7 +858,7 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask, if (children_add_size > add_size) add_size = children_add_size; size1 = (!realloc_head || (realloc_head && !add_size)) ? size0 : - calculate_memsize(size, min_size+add_size, 0, + calculate_memsize(size, min_size, add_size, resource_size(b_res), min_align); if (!size0 && !size1) { if (b_res->start || b_res->end) @@ -739,8 +871,12 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask, b_res->start = min_align; b_res->end = size0 + min_align - 1; b_res->flags |= IORESOURCE_STARTALIGN | mem64_mask; - if (size1 > size0 && realloc_head) + if (size1 > size0 && realloc_head) { add_to_list(realloc_head, bus->self, b_res, size1-size0, min_align); + dev_printk(KERN_DEBUG, &bus->self->dev, "bridge window " + "%pR to [bus %02x-%02x] add_size %llx\n", b_res, + bus->secondary, bus->subordinate, (unsigned long long)size1-size0); + } return 1; } @@ -754,25 +890,48 @@ unsigned long pci_cardbus_resource_alignment(struct resource *res) } static void pci_bus_size_cardbus(struct pci_bus *bus, - struct resource_list_x *realloc_head) + struct list_head *realloc_head) { struct pci_dev *bridge = bus->self; struct resource *b_res = &bridge->resource[PCI_BRIDGE_RESOURCES]; + resource_size_t b_res_3_size = pci_cardbus_mem_size * 2; u16 ctrl; + if (b_res[0].parent) + goto handle_b_res_1; /* * Reserve some resources for CardBus. We reserve * a fixed amount of bus space for CardBus bridges. */ - b_res[0].start = 0; - b_res[0].flags |= IORESOURCE_IO | IORESOURCE_SIZEALIGN; - if (realloc_head) - add_to_list(realloc_head, bridge, b_res, pci_cardbus_io_size, 0 /* dont care */); + b_res[0].start = pci_cardbus_io_size; + b_res[0].end = b_res[0].start + pci_cardbus_io_size - 1; + b_res[0].flags |= IORESOURCE_IO | IORESOURCE_STARTALIGN; + if (realloc_head) { + b_res[0].end -= pci_cardbus_io_size; + add_to_list(realloc_head, bridge, b_res, pci_cardbus_io_size, + pci_cardbus_io_size); + } - b_res[1].start = 0; - b_res[1].flags |= IORESOURCE_IO | IORESOURCE_SIZEALIGN; - if (realloc_head) - add_to_list(realloc_head, bridge, b_res+1, pci_cardbus_io_size, 0 /* dont care */); +handle_b_res_1: + if (b_res[1].parent) + goto handle_b_res_2; + b_res[1].start = pci_cardbus_io_size; + b_res[1].end = b_res[1].start + pci_cardbus_io_size - 1; + b_res[1].flags |= IORESOURCE_IO | IORESOURCE_STARTALIGN; + if (realloc_head) { + b_res[1].end -= pci_cardbus_io_size; + add_to_list(realloc_head, bridge, b_res+1, pci_cardbus_io_size, + pci_cardbus_io_size); + } + +handle_b_res_2: + /* MEM1 must not be pref mmio */ + pci_read_config_word(bridge, PCI_CB_BRIDGE_CONTROL, &ctrl); + if (ctrl & PCI_CB_BRIDGE_CTL_PREFETCH_MEM1) { + ctrl &= ~PCI_CB_BRIDGE_CTL_PREFETCH_MEM1; + pci_write_config_word(bridge, PCI_CB_BRIDGE_CONTROL, ctrl); + pci_read_config_word(bridge, PCI_CB_BRIDGE_CONTROL, &ctrl); + } /* * Check whether prefetchable memory is supported @@ -785,38 +944,46 @@ static void pci_bus_size_cardbus(struct pci_bus *bus, pci_read_config_word(bridge, PCI_CB_BRIDGE_CONTROL, &ctrl); } + if (b_res[2].parent) + goto handle_b_res_3; /* * If we have prefetchable memory support, allocate * two regions. Otherwise, allocate one region of * twice the size. */ if (ctrl & PCI_CB_BRIDGE_CTL_PREFETCH_MEM0) { - b_res[2].start = 0; - b_res[2].flags |= IORESOURCE_MEM | IORESOURCE_PREFETCH | IORESOURCE_SIZEALIGN; - if (realloc_head) - add_to_list(realloc_head, bridge, b_res+2, pci_cardbus_mem_size, 0 /* dont care */); - - b_res[3].start = 0; - b_res[3].flags |= IORESOURCE_MEM | IORESOURCE_SIZEALIGN; - if (realloc_head) - add_to_list(realloc_head, bridge, b_res+3, pci_cardbus_mem_size, 0 /* dont care */); - } else { - b_res[3].start = 0; - b_res[3].flags |= IORESOURCE_MEM | IORESOURCE_SIZEALIGN; - if (realloc_head) - add_to_list(realloc_head, bridge, b_res+3, pci_cardbus_mem_size * 2, 0 /* dont care */); + b_res[2].start = pci_cardbus_mem_size; + b_res[2].end = b_res[2].start + pci_cardbus_mem_size - 1; + b_res[2].flags |= IORESOURCE_MEM | IORESOURCE_PREFETCH | + IORESOURCE_STARTALIGN; + if (realloc_head) { + b_res[2].end -= pci_cardbus_mem_size; + add_to_list(realloc_head, bridge, b_res+2, + pci_cardbus_mem_size, pci_cardbus_mem_size); + } + + /* reduce that to half */ + b_res_3_size = pci_cardbus_mem_size; + } + +handle_b_res_3: + if (b_res[3].parent) + goto handle_done; + b_res[3].start = pci_cardbus_mem_size; + b_res[3].end = b_res[3].start + b_res_3_size - 1; + b_res[3].flags |= IORESOURCE_MEM | IORESOURCE_STARTALIGN; + if (realloc_head) { + b_res[3].end -= b_res_3_size; + add_to_list(realloc_head, bridge, b_res+3, b_res_3_size, + pci_cardbus_mem_size); } - /* set the size of the resource to zero, so that the resource does not - * get assigned during required-resource allocation cycle but gets assigned - * during the optional-resource allocation cycle. - */ - b_res[0].start = b_res[1].start = b_res[2].start = b_res[3].start = 1; - b_res[0].end = b_res[1].end = b_res[2].end = b_res[3].end = 0; +handle_done: + ; } void __ref __pci_bus_size_bridges(struct pci_bus *bus, - struct resource_list_x *realloc_head) + struct list_head *realloc_head) { struct pci_dev *dev; unsigned long mask, prefmask; @@ -858,7 +1025,8 @@ void __ref __pci_bus_size_bridges(struct pci_bus *bus, * Follow thru */ default: - pbus_size_io(bus, 0, additional_io_size, realloc_head); + pbus_size_io(bus, realloc_head ? 0 : additional_io_size, + additional_io_size, realloc_head); /* If the bridge supports prefetchable range, size it separately. If it doesn't, or its prefetchable window has already been allocated by arch code, try @@ -866,11 +1034,15 @@ void __ref __pci_bus_size_bridges(struct pci_bus *bus, resources. */ mask = IORESOURCE_MEM; prefmask = IORESOURCE_MEM | IORESOURCE_PREFETCH; - if (pbus_size_mem(bus, prefmask, prefmask, 0, additional_mem_size, realloc_head)) + if (pbus_size_mem(bus, prefmask, prefmask, + realloc_head ? 0 : additional_mem_size, + additional_mem_size, realloc_head)) mask = prefmask; /* Success, size non-prefetch only. */ else additional_mem_size += additional_mem_size; - pbus_size_mem(bus, mask, IORESOURCE_MEM, 0, additional_mem_size, realloc_head); + pbus_size_mem(bus, mask, IORESOURCE_MEM, + realloc_head ? 0 : additional_mem_size, + additional_mem_size, realloc_head); break; } } @@ -882,8 +1054,8 @@ void __ref pci_bus_size_bridges(struct pci_bus *bus) EXPORT_SYMBOL(pci_bus_size_bridges); static void __ref __pci_bus_assign_resources(const struct pci_bus *bus, - struct resource_list_x *realloc_head, - struct resource_list_x *fail_head) + struct list_head *realloc_head, + struct list_head *fail_head) { struct pci_bus *b; struct pci_dev *dev; @@ -922,17 +1094,19 @@ void __ref pci_bus_assign_resources(const struct pci_bus *bus) EXPORT_SYMBOL(pci_bus_assign_resources); static void __ref __pci_bridge_assign_resources(const struct pci_dev *bridge, - struct resource_list_x *fail_head) + struct list_head *add_head, + struct list_head *fail_head) { struct pci_bus *b; - pdev_assign_resources_sorted((struct pci_dev *)bridge, fail_head); + pdev_assign_resources_sorted((struct pci_dev *)bridge, + add_head, fail_head); b = bridge->subordinate; if (!b) return; - __pci_bus_assign_resources(b, NULL, fail_head); + __pci_bus_assign_resources(b, add_head, fail_head); switch (bridge->class >> 8) { case PCI_CLASS_BRIDGE_PCI: @@ -1095,6 +1269,58 @@ static int __init pci_get_max_depth(void) return depth; } +/* + * -1: undefined, will auto detect later + * 0: disabled by user + * 1: disabled by auto detect + * 2: enabled by user + * 3: enabled by auto detect + */ +enum enable_type { + undefined = -1, + user_disabled, + auto_disabled, + user_enabled, + auto_enabled, +}; + +static enum enable_type pci_realloc_enable __initdata = undefined; +void __init pci_realloc_get_opt(char *str) +{ + if (!strncmp(str, "off", 3)) + pci_realloc_enable = user_disabled; + else if (!strncmp(str, "on", 2)) + pci_realloc_enable = user_enabled; +} +static bool __init pci_realloc_enabled(void) +{ + return pci_realloc_enable >= user_enabled; +} + +static void __init pci_realloc_detect(void) +{ +#if defined(CONFIG_PCI_IOV) && defined(CONFIG_PCI_REALLOC_ENABLE_AUTO) + struct pci_dev *dev = NULL; + + if (pci_realloc_enable != undefined) + return; + + for_each_pci_dev(dev) { + int i; + + for (i = PCI_IOV_RESOURCES; i <= PCI_IOV_RESOURCE_END; i++) { + struct resource *r = &dev->resource[i]; + + /* Not assigned, or rejected by kernel ? */ + if (r->flags && !r->start) { + pci_realloc_enable = auto_enabled; + + return; + } + } + } +#endif +} /* * first try will not touch pci bridge res @@ -1105,59 +1331,57 @@ void __init pci_assign_unassigned_resources(void) { struct pci_bus *bus; - struct resource_list_x realloc_list; /* list of resources that + LIST_HEAD(realloc_head); /* list of resources that want additional resources */ + struct list_head *add_list = NULL; int tried_times = 0; enum release_type rel_type = leaf_only; - struct resource_list_x head, *list; + LIST_HEAD(fail_head); + struct pci_dev_resource *fail_res; 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; - + int pci_try_num = 1; - head.next = NULL; - realloc_list.next = NULL; + /* don't realloc if asked to do so */ + pci_realloc_detect(); + if (pci_realloc_enabled()) { + int max_depth = pci_get_max_depth(); - pci_try_num = max_depth + 1; - printk(KERN_DEBUG "PCI: max bus depth: %d pci_try_num: %d\n", - max_depth, pci_try_num); + 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: + /* + * last try will use add_list, otherwise will try good to have as + * must have, so can realloc parent bridge resource + */ + if (tried_times + 1 == pci_try_num) + add_list = &realloc_head; /* Depth first, calculate sizes and alignments of all subordinate buses. */ list_for_each_entry(bus, &pci_root_buses, node) - __pci_bus_size_bridges(bus, &realloc_list); + __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, &realloc_list, &head); - BUG_ON(realloc_list.next); + __pci_bus_assign_resources(bus, add_list, &fail_head); + if (add_list) + BUG_ON(!list_empty(add_list)); tried_times++; /* any device complain? */ - if (!head.next) + if (list_empty(&fail_head)) goto enable_and_dump; - /* don't realloc if asked to do so */ - if (!pci_realloc_enabled()) { - free_list(resource_list_x, &head); - goto enable_and_dump; - } + if (tried_times >= pci_try_num) { + if (pci_realloc_enable == undefined) + printk(KERN_INFO "Some PCI device resources are unassigned, try booting with pci=realloc\n"); + else if (pci_realloc_enable == auto_enabled) + printk(KERN_INFO "Automatically enabled pci realloc, if you have problem, try booting with pci=realloc=off\n"); - 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); + free_list(&fail_head); goto enable_and_dump; } @@ -1172,25 +1396,23 @@ again: * 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; + list_for_each_entry(fail_res, &fail_head, list) { + bus = fail_res->dev->bus; + pci_bus_release_bridge_resources(bus, + fail_res->flags & type_mask, + rel_type); } /* restore size and flags */ - for (list = head.next; list;) { - struct resource *res = list->res; + list_for_each_entry(fail_res, &fail_head, list) { + struct resource *res = fail_res->res; - res->start = list->start; - res->end = list->end; - res->flags = list->flags; - if (list->dev->subordinate) + res->start = fail_res->start; + res->end = fail_res->end; + res->flags = fail_res->flags; + if (fail_res->dev->subordinate) res->flags = 0; - - list = list->next; } - free_list(resource_list_x, &head); + free_list(&fail_head); goto again; @@ -1207,26 +1429,27 @@ enable_and_dump: void pci_assign_unassigned_bridge_resources(struct pci_dev *bridge) { struct pci_bus *parent = bridge->subordinate; + LIST_HEAD(add_list); /* list of resources that + want additional resources */ int tried_times = 0; - struct resource_list_x head, *list; + LIST_HEAD(fail_head); + struct pci_dev_resource *fail_res; int retval; unsigned long type_mask = IORESOURCE_IO | IORESOURCE_MEM | IORESOURCE_PREFETCH; - head.next = NULL; - again: - pci_bus_size_bridges(parent); - __pci_bridge_assign_resources(bridge, &head); - + __pci_bus_size_bridges(parent, &add_list); + __pci_bridge_assign_resources(bridge, &add_list, &fail_head); + BUG_ON(!list_empty(&add_list)); tried_times++; - if (!head.next) + if (list_empty(&fail_head)) goto enable_all; if (tried_times >= 2) { /* still fail, don't need to try more */ - free_list(resource_list_x, &head); + free_list(&fail_head); goto enable_all; } @@ -1237,27 +1460,24 @@ again: * Try to release leaf bridge's resources that doesn't fit resource of * child device under that bridge */ - for (list = head.next; list;) { - struct pci_bus *bus = list->dev->bus; - unsigned long flags = list->flags; + list_for_each_entry(fail_res, &fail_head, list) { + struct pci_bus *bus = fail_res->dev->bus; + unsigned long flags = fail_res->flags; pci_bus_release_bridge_resources(bus, flags & type_mask, whole_subtree); - list = list->next; } /* restore size and flags */ - for (list = head.next; list;) { - struct resource *res = list->res; + list_for_each_entry(fail_res, &fail_head, list) { + struct resource *res = fail_res->res; - res->start = list->start; - res->end = list->end; - res->flags = list->flags; - if (list->dev->subordinate) + res->start = fail_res->start; + res->end = fail_res->end; + res->flags = fail_res->flags; + if (fail_res->dev->subordinate) res->flags = 0; - - list = list->next; } - free_list(resource_list_x, &head); + free_list(&fail_head); goto again; @@ -1267,3 +1487,41 @@ enable_all: pci_enable_bridges(parent); } EXPORT_SYMBOL_GPL(pci_assign_unassigned_bridge_resources); + +#ifdef CONFIG_HOTPLUG +/** + * pci_rescan_bus - scan a PCI bus for devices. + * @bus: PCI bus to scan + * + * Scan a PCI bus and child buses for new devices, adds them, + * and enables them. + * + * Returns the max number of subordinate bus discovered. + */ +unsigned int __ref pci_rescan_bus(struct pci_bus *bus) +{ + unsigned int max; + struct pci_dev *dev; + LIST_HEAD(add_list); /* list of resources that + want additional resources */ + + max = pci_scan_child_bus(bus); + + down_read(&pci_bus_sem); + list_for_each_entry(dev, &bus->devices, bus_list) + if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE || + dev->hdr_type == PCI_HEADER_TYPE_CARDBUS) + if (dev->subordinate) + __pci_bus_size_bridges(dev->subordinate, + &add_list); + up_read(&pci_bus_sem); + __pci_bus_assign_resources(bus, &add_list, NULL); + BUG_ON(!list_empty(&add_list)); + + pci_enable_bridges(bus); + pci_bus_add_devices(bus); + + return max; +} +EXPORT_SYMBOL_GPL(pci_rescan_bus); +#endif diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c index b66bfdbd21f7..eea85dafc763 100644 --- a/drivers/pci/setup-res.c +++ b/drivers/pci/setup-res.c @@ -114,7 +114,6 @@ int pci_claim_resource(struct pci_dev *dev, int resource) } EXPORT_SYMBOL(pci_claim_resource); -#ifdef CONFIG_PCI_QUIRKS void pci_disable_bridge_window(struct pci_dev *dev) { dev_info(&dev->dev, "disabling bridge mem windows\n"); @@ -127,9 +126,6 @@ void pci_disable_bridge_window(struct pci_dev *dev) pci_write_config_dword(dev, PCI_PREF_MEMORY_BASE, 0x0000fff0); pci_write_config_dword(dev, PCI_PREF_BASE_UPPER32, 0xffffffff); } -#endif /* CONFIG_PCI_QUIRKS */ - - static int __pci_assign_resource(struct pci_bus *bus, struct pci_dev *dev, int resno, resource_size_t size, resource_size_t align) @@ -158,22 +154,44 @@ static int __pci_assign_resource(struct pci_bus *bus, struct pci_dev *dev, return ret; } +/* + * Generic function that returns a value indicating that the device's + * original BIOS BAR address was not saved and so is not available for + * reinstatement. + * + * Can be over-ridden by architecture specific code that implements + * reinstatement functionality rather than leaving it disabled when + * normal allocation attempts fail. + */ +resource_size_t __weak pcibios_retrieve_fw_addr(struct pci_dev *dev, int idx) +{ + return 0; +} + static int pci_revert_fw_address(struct resource *res, struct pci_dev *dev, int resno, resource_size_t size) { struct resource *root, *conflict; - resource_size_t start, end; + resource_size_t fw_addr, start, end; int ret = 0; - if (res->flags & IORESOURCE_IO) - root = &ioport_resource; - else - root = &iomem_resource; + fw_addr = pcibios_retrieve_fw_addr(dev, resno); + if (!fw_addr) + return 1; start = res->start; end = res->end; - res->start = dev->fw_addr[resno]; + res->start = fw_addr; res->end = res->start + size - 1; + + root = pci_find_parent_resource(dev, res); + if (!root) { + if (res->flags & IORESOURCE_IO) + root = &ioport_resource; + else + root = &iomem_resource; + } + dev_info(&dev->dev, "BAR %d: trying firmware assignment %pR\n", resno, res); conflict = request_resource_conflict(root, res); @@ -228,16 +246,17 @@ int pci_reassign_resource(struct pci_dev *dev, int resno, resource_size_t addsiz int ret; if (!res->parent) { - dev_info(&dev->dev, "BAR %d: can't reassign an unassigned resouce %pR " + dev_info(&dev->dev, "BAR %d: can't reassign an unassigned resource %pR " "\n", resno, res); return -EINVAL; } - new_size = resource_size(res) + addsize + min_align; + /* already aligned with min_align */ + new_size = resource_size(res) + addsize; ret = _pci_assign_resource(dev, resno, new_size, min_align); if (!ret) { res->flags &= ~IORESOURCE_STARTALIGN; - dev_info(&dev->dev, "BAR %d: assigned %pR\n", resno, res); + dev_info(&dev->dev, "BAR %d: reassigned %pR\n", resno, res); if (resno < PCI_BRIDGE_RESOURCES) pci_update_resource(dev, resno); } @@ -267,7 +286,7 @@ int pci_assign_resource(struct pci_dev *dev, int resno) * where firmware left it. That at least has a chance of * working, which is better than just leaving it disabled. */ - if (ret < 0 && dev->fw_addr[resno]) + if (ret < 0) ret = pci_revert_fw_address(res, dev, resno, size); if (!ret) { @@ -279,53 +298,6 @@ int pci_assign_resource(struct pci_dev *dev, int resno) return ret; } - -/* Sort resources by alignment */ -void pdev_sort_resources(struct pci_dev *dev, struct resource_list *head) -{ - int i; - - for (i = 0; i < PCI_NUM_RESOURCES; i++) { - struct resource *r; - struct resource_list *list, *tmp; - resource_size_t r_align; - - r = &dev->resource[i]; - - if (r->flags & IORESOURCE_PCI_FIXED) - continue; - - if (!(r->flags) || r->parent) - continue; - - r_align = pci_resource_alignment(dev, r); - if (!r_align) { - dev_warn(&dev->dev, "BAR %d: %pR has bogus alignment\n", - i, r); - continue; - } - for (list = head; ; list = list->next) { - resource_size_t align = 0; - struct resource_list *ln = list->next; - - if (ln) - align = pci_resource_alignment(ln->dev, ln->res); - - if (r_align > align) { - tmp = kmalloc(sizeof(*tmp), GFP_KERNEL); - if (!tmp) - panic("pdev_sort_resources(): " - "kmalloc() failed!\n"); - tmp->next = ln; - tmp->res = r; - tmp->dev = dev; - list->next = tmp; - break; - } - } - } -} - int pci_enable_resources(struct pci_dev *dev, int mask) { u16 cmd, old_cmd; diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c index 1620088a0e7e..fd00ff02ab4d 100644 --- a/drivers/pci/xen-pcifront.c +++ b/drivers/pci/xen-pcifront.c @@ -544,7 +544,7 @@ static void free_root_bus_devs(struct pci_bus *bus) dev = container_of(bus->devices.next, struct pci_dev, bus_list); dev_dbg(&dev->dev, "removing device\n"); - pci_remove_bus_device(dev); + pci_stop_and_remove_bus_device(dev); } } @@ -593,7 +593,7 @@ static pci_ers_result_t pcifront_common_process(int cmd, } pdrv = pcidev->driver; - if (get_driver(&pdrv->driver)) { + if (pdrv) { if (pdrv->err_handler && pdrv->err_handler->error_detected) { dev_dbg(&pcidev->dev, "trying to call AER service\n"); @@ -623,7 +623,6 @@ static pci_ers_result_t pcifront_common_process(int cmd, } } } - put_driver(&pdrv->driver); } if (!flag) result = PCI_ERS_RESULT_NONE; @@ -1045,7 +1044,7 @@ static int pcifront_detach_devices(struct pcifront_device *pdev) domain, bus, slot, func); continue; } - pci_remove_bus_device(pci_dev); + pci_stop_and_remove_bus_device(pci_dev); pci_dev_put(pci_dev); dev_dbg(&pdev->xdev->dev, |