diff options
Diffstat (limited to 'drivers/pci')
| -rw-r--r-- | drivers/pci/p2pdma.c | 93 | ||||
| -rw-r--r-- | drivers/pci/pci-acpi.c | 17 | ||||
| -rw-r--r-- | drivers/pci/pci-driver.c | 118 | ||||
| -rw-r--r-- | drivers/pci/pci.c | 116 | ||||
| -rw-r--r-- | drivers/pci/pci.h | 8 | ||||
| -rw-r--r-- | drivers/pci/pcie/aspm.c | 20 | ||||
| -rw-r--r-- | drivers/pci/pcie/portdrv_core.c | 66 | ||||
| -rw-r--r-- | drivers/pci/probe.c | 2 | ||||
| -rw-r--r-- | drivers/pci/search.c | 4 |
9 files changed, 300 insertions, 144 deletions
diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c index 4311278aaa98..234476226529 100644 --- a/drivers/pci/p2pdma.c +++ b/drivers/pci/p2pdma.c @@ -18,10 +18,9 @@ #include <linux/percpu-refcount.h> #include <linux/random.h> #include <linux/seq_buf.h> +#include <linux/iommu.h> struct pci_p2pdma { - struct percpu_ref devmap_ref; - struct completion devmap_ref_done; struct gen_pool *pool; bool p2pmem_published; }; @@ -74,41 +73,20 @@ static const struct attribute_group p2pmem_group = { .name = "p2pmem", }; -static void pci_p2pdma_percpu_release(struct percpu_ref *ref) -{ - struct pci_p2pdma *p2p = - container_of(ref, struct pci_p2pdma, devmap_ref); - - complete_all(&p2p->devmap_ref_done); -} - -static void pci_p2pdma_percpu_kill(struct percpu_ref *ref) -{ - /* - * pci_p2pdma_add_resource() may be called multiple times - * by a driver and may register the percpu_kill devm action multiple - * times. We only want the first action to actually kill the - * percpu_ref. - */ - if (percpu_ref_is_dying(ref)) - return; - - percpu_ref_kill(ref); -} - static void pci_p2pdma_release(void *data) { struct pci_dev *pdev = data; + struct pci_p2pdma *p2pdma = pdev->p2pdma; - if (!pdev->p2pdma) + if (!p2pdma) return; - wait_for_completion(&pdev->p2pdma->devmap_ref_done); - percpu_ref_exit(&pdev->p2pdma->devmap_ref); + /* Flush and disable pci_alloc_p2p_mem() */ + pdev->p2pdma = NULL; + synchronize_rcu(); - gen_pool_destroy(pdev->p2pdma->pool); + gen_pool_destroy(p2pdma->pool); sysfs_remove_group(&pdev->dev.kobj, &p2pmem_group); - pdev->p2pdma = NULL; } static int pci_p2pdma_setup(struct pci_dev *pdev) @@ -124,12 +102,6 @@ static int pci_p2pdma_setup(struct pci_dev *pdev) if (!p2p->pool) goto out; - init_completion(&p2p->devmap_ref_done); - error = percpu_ref_init(&p2p->devmap_ref, - pci_p2pdma_percpu_release, 0, GFP_KERNEL); - if (error) - goto out_pool_destroy; - error = devm_add_action_or_reset(&pdev->dev, pci_p2pdma_release, pdev); if (error) goto out_pool_destroy; @@ -188,15 +160,12 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size, pgmap = devm_kzalloc(&pdev->dev, sizeof(*pgmap), GFP_KERNEL); if (!pgmap) return -ENOMEM; - pgmap->res.start = pci_resource_start(pdev, bar) + offset; pgmap->res.end = pgmap->res.start + size - 1; pgmap->res.flags = pci_resource_flags(pdev, bar); - pgmap->ref = &pdev->p2pdma->devmap_ref; pgmap->type = MEMORY_DEVICE_PCI_P2PDMA; pgmap->pci_p2pdma_bus_offset = pci_bus_address(pdev, bar) - pci_resource_start(pdev, bar); - pgmap->kill = pci_p2pdma_percpu_kill; addr = devm_memremap_pages(&pdev->dev, pgmap); if (IS_ERR(addr)) { @@ -204,17 +173,20 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size, goto pgmap_free; } - error = gen_pool_add_virt(pdev->p2pdma->pool, (unsigned long)addr, + error = gen_pool_add_owner(pdev->p2pdma->pool, (unsigned long)addr, pci_bus_address(pdev, bar) + offset, - resource_size(&pgmap->res), dev_to_node(&pdev->dev)); + resource_size(&pgmap->res), dev_to_node(&pdev->dev), + pgmap->ref); if (error) - goto pgmap_free; + goto pages_free; pci_info(pdev, "added peer-to-peer DMA memory %pR\n", &pgmap->res); return 0; +pages_free: + devm_memunmap_pages(&pdev->dev, pgmap); pgmap_free: devm_kfree(&pdev->dev, pgmap); return error; @@ -284,6 +256,9 @@ static bool root_complex_whitelist(struct pci_dev *dev) struct pci_dev *root = pci_get_slot(host->bus, PCI_DEVFN(0, 0)); unsigned short vendor, device; + if (iommu_present(dev->dev.bus)) + return false; + if (!root) return false; @@ -593,19 +568,30 @@ EXPORT_SYMBOL_GPL(pci_p2pmem_find_many); */ void *pci_alloc_p2pmem(struct pci_dev *pdev, size_t size) { - void *ret; + void *ret = NULL; + struct percpu_ref *ref; + /* + * Pairs with synchronize_rcu() in pci_p2pdma_release() to + * ensure pdev->p2pdma is non-NULL for the duration of the + * read-lock. + */ + rcu_read_lock(); if (unlikely(!pdev->p2pdma)) - return NULL; - - if (unlikely(!percpu_ref_tryget_live(&pdev->p2pdma->devmap_ref))) - return NULL; - - ret = (void *)gen_pool_alloc(pdev->p2pdma->pool, size); + goto out; - if (unlikely(!ret)) - percpu_ref_put(&pdev->p2pdma->devmap_ref); + ret = (void *)gen_pool_alloc_owner(pdev->p2pdma->pool, size, + (void **) &ref); + if (!ret) + goto out; + if (unlikely(!percpu_ref_tryget_live(ref))) { + gen_pool_free(pdev->p2pdma->pool, (unsigned long) ret, size); + ret = NULL; + goto out; + } +out: + rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(pci_alloc_p2pmem); @@ -618,8 +604,11 @@ EXPORT_SYMBOL_GPL(pci_alloc_p2pmem); */ void pci_free_p2pmem(struct pci_dev *pdev, void *addr, size_t size) { - gen_pool_free(pdev->p2pdma->pool, (uintptr_t)addr, size); - percpu_ref_put(&pdev->p2pdma->devmap_ref); + struct percpu_ref *ref; + + gen_pool_free_owner(pdev->p2pdma->pool, (uintptr_t)addr, size, + (void **) &ref); + percpu_ref_put(ref); } EXPORT_SYMBOL_GPL(pci_free_p2pmem); diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c index c5e1a097d7e3..45049f558860 100644 --- a/drivers/pci/pci-acpi.c +++ b/drivers/pci/pci-acpi.c @@ -685,12 +685,21 @@ static pci_power_t acpi_pci_get_power_state(struct pci_dev *dev) if (!adev || !acpi_device_power_manageable(adev)) return PCI_UNKNOWN; - if (acpi_device_get_power(adev, &state) || state == ACPI_STATE_UNKNOWN) + state = adev->power.state; + if (state == ACPI_STATE_UNKNOWN) return PCI_UNKNOWN; return state_conv[state]; } +static void acpi_pci_refresh_power_state(struct pci_dev *dev) +{ + struct acpi_device *adev = ACPI_COMPANION(&dev->dev); + + if (adev && acpi_device_power_manageable(adev)) + acpi_device_update_power(adev, NULL); +} + static int acpi_pci_propagate_wakeup(struct pci_bus *bus, bool enable) { while (bus->parent) { @@ -733,7 +742,8 @@ static bool acpi_pci_need_resume(struct pci_dev *dev) if (!adev || !acpi_device_power_manageable(adev)) return false; - if (device_may_wakeup(&dev->dev) != !!adev->wakeup.prepare_count) + if (adev->wakeup.flags.valid && + device_may_wakeup(&dev->dev) != !!adev->wakeup.prepare_count) return true; if (acpi_target_system_state() == ACPI_STATE_S0) @@ -747,6 +757,7 @@ static const struct pci_platform_pm_ops acpi_pci_platform_pm = { .is_manageable = acpi_pci_power_manageable, .set_state = acpi_pci_set_power_state, .get_state = acpi_pci_get_power_state, + .refresh_state = acpi_pci_refresh_power_state, .choose_state = acpi_pci_choose_state, .set_wakeup = acpi_pci_wakeup, .need_resume = acpi_pci_need_resume, @@ -900,6 +911,7 @@ static void pci_acpi_setup(struct device *dev) device_wakeup_enable(dev); acpi_pci_wakeup(pci_dev, false); + acpi_device_power_add_dependent(adev, dev); } static void pci_acpi_cleanup(struct device *dev) @@ -912,6 +924,7 @@ static void pci_acpi_cleanup(struct device *dev) pci_acpi_remove_pm_notifier(adev); if (adev->wakeup.flags.valid) { + acpi_device_power_remove_dependent(adev, dev); if (pci_dev->bridge_d3) device_wakeup_disable(dev); diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index b6a3a51801f0..a8124e47bf6e 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -526,7 +526,6 @@ static void pci_pm_default_resume_early(struct pci_dev *pci_dev) pci_power_up(pci_dev); pci_restore_state(pci_dev); pci_pme_restore(pci_dev); - pci_fixup_device(pci_fixup_resume_early, pci_dev); } /* @@ -681,6 +680,7 @@ static bool pci_has_legacy_pm_support(struct pci_dev *pci_dev) static int pci_pm_prepare(struct device *dev) { struct device_driver *drv = dev->driver; + struct pci_dev *pci_dev = to_pci_dev(dev); if (drv && drv->pm && drv->pm->prepare) { int error = drv->pm->prepare(dev); @@ -690,7 +690,15 @@ static int pci_pm_prepare(struct device *dev) if (!error && dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_PREPARE)) return 0; } - return pci_dev_keep_suspended(to_pci_dev(dev)); + if (pci_dev_need_resume(pci_dev)) + return 0; + + /* + * The PME setting needs to be adjusted here in case the direct-complete + * optimization is used with respect to this device. + */ + pci_dev_adjust_pme(pci_dev); + return 1; } static void pci_pm_complete(struct device *dev) @@ -704,7 +712,14 @@ static void pci_pm_complete(struct device *dev) if (pm_runtime_suspended(dev) && pm_resume_via_firmware()) { pci_power_t pre_sleep_state = pci_dev->current_state; - pci_update_current_state(pci_dev, pci_dev->current_state); + pci_refresh_power_state(pci_dev); + /* + * On platforms with ACPI this check may also trigger for + * devices sharing power resources if one of those power + * resources has been activated as a result of a change of the + * power state of another device sharing it. However, in that + * case it is also better to resume the device, in general. + */ if (pci_dev->current_state < pre_sleep_state) pm_request_resume(dev); } @@ -736,6 +751,8 @@ static int pci_pm_suspend(struct device *dev) struct pci_dev *pci_dev = to_pci_dev(dev); const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; + pci_dev->skip_bus_pm = false; + if (pci_has_legacy_pm_support(pci_dev)) return pci_legacy_suspend(dev, PMSG_SUSPEND); @@ -758,9 +775,11 @@ static int pci_pm_suspend(struct device *dev) * better to resume the device from runtime suspend here. */ if (!dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND) || - !pci_dev_keep_suspended(pci_dev)) { + pci_dev_need_resume(pci_dev)) { pm_runtime_resume(dev); pci_dev->state_saved = false; + } else { + pci_dev_adjust_pme(pci_dev); } if (pm->suspend) { @@ -829,7 +848,18 @@ static int pci_pm_suspend_noirq(struct device *dev) } } - if (!pci_dev->state_saved) { + if (pci_dev->skip_bus_pm) { + /* + * Either the device is a bridge with a child in D0 below it, or + * the function is running for the second time in a row without + * going through full resume, which is possible only during + * suspend-to-idle in a spurious wakeup case. The device should + * be in D0 at this point, but if it is a bridge, it may be + * necessary to save its state. + */ + if (!pci_dev->state_saved) + pci_save_state(pci_dev); + } else if (!pci_dev->state_saved) { pci_save_state(pci_dev); if (pci_power_manageable(pci_dev)) pci_prepare_to_sleep(pci_dev); @@ -838,6 +868,22 @@ static int pci_pm_suspend_noirq(struct device *dev) dev_dbg(dev, "PCI PM: Suspend power state: %s\n", pci_power_name(pci_dev->current_state)); + if (pci_dev->current_state == PCI_D0) { + pci_dev->skip_bus_pm = true; + /* + * Per PCI PM r1.2, table 6-1, a bridge must be in D0 if any + * downstream device is in D0, so avoid changing the power state + * of the parent bridge by setting the skip_bus_pm flag for it. + */ + if (pci_dev->bus->self) + pci_dev->bus->self->skip_bus_pm = true; + } + + if (pci_dev->skip_bus_pm && pm_suspend_no_platform()) { + dev_dbg(dev, "PCI PM: Skipped\n"); + goto Fixup; + } + pci_pm_set_unknown_state(pci_dev); /* @@ -885,7 +931,16 @@ static int pci_pm_resume_noirq(struct device *dev) if (dev_pm_smart_suspend_and_suspended(dev)) pm_runtime_set_active(dev); - pci_pm_default_resume_early(pci_dev); + /* + * In the suspend-to-idle case, devices left in D0 during suspend will + * stay in D0, so it is not necessary to restore or update their + * configuration here and attempting to put them into D0 again is + * pointless, so avoid doing that. + */ + if (!(pci_dev->skip_bus_pm && pm_suspend_no_platform())) + pci_pm_default_resume_early(pci_dev); + + pci_fixup_device(pci_fixup_resume_early, pci_dev); if (pci_has_legacy_pm_support(pci_dev)) return pci_legacy_resume_early(dev); @@ -959,15 +1014,15 @@ static int pci_pm_freeze(struct device *dev) } /* - * This used to be done in pci_pm_prepare() for all devices and some - * drivers may depend on it, so do it here. Ideally, runtime-suspended - * devices should not be touched during freeze/thaw transitions, - * however. + * Resume all runtime-suspended devices before creating a snapshot + * image of system memory, because the restore kernel generally cannot + * be expected to always handle them consistently and they need to be + * put into the runtime-active metastate during system resume anyway, + * so it is better to ensure that the state saved in the image will be + * always consistent with that. */ - if (!dev_pm_smart_suspend_and_suspended(dev)) { - pm_runtime_resume(dev); - pci_dev->state_saved = false; - } + pm_runtime_resume(dev); + pci_dev->state_saved = false; if (pm->freeze) { int error; @@ -981,22 +1036,11 @@ static int pci_pm_freeze(struct device *dev) return 0; } -static int pci_pm_freeze_late(struct device *dev) -{ - if (dev_pm_smart_suspend_and_suspended(dev)) - return 0; - - return pm_generic_freeze_late(dev); -} - static int pci_pm_freeze_noirq(struct device *dev) { struct pci_dev *pci_dev = to_pci_dev(dev); struct device_driver *drv = dev->driver; - if (dev_pm_smart_suspend_and_suspended(dev)) - return 0; - if (pci_has_legacy_pm_support(pci_dev)) return pci_legacy_suspend_late(dev, PMSG_FREEZE); @@ -1026,16 +1070,6 @@ static int pci_pm_thaw_noirq(struct device *dev) struct device_driver *drv = dev->driver; int error = 0; - /* - * If the device is in runtime suspend, the code below may not work - * correctly with it, so skip that code and make the PM core skip all of - * the subsequent "thaw" callbacks for the device. - */ - if (dev_pm_smart_suspend_and_suspended(dev)) { - dev_pm_skip_next_resume_phases(dev); - return 0; - } - if (pcibios_pm_ops.thaw_noirq) { error = pcibios_pm_ops.thaw_noirq(dev); if (error) @@ -1095,10 +1129,13 @@ static int pci_pm_poweroff(struct device *dev) /* The reason to do that is the same as in pci_pm_suspend(). */ if (!dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND) || - !pci_dev_keep_suspended(pci_dev)) + pci_dev_need_resume(pci_dev)) { pm_runtime_resume(dev); + pci_dev->state_saved = false; + } else { + pci_dev_adjust_pme(pci_dev); + } - pci_dev->state_saved = false; if (pm->poweroff) { int error; @@ -1170,10 +1207,6 @@ static int pci_pm_restore_noirq(struct device *dev) struct device_driver *drv = dev->driver; int error = 0; - /* This is analogous to the pci_pm_resume_noirq() case. */ - if (dev_pm_smart_suspend_and_suspended(dev)) - pm_runtime_set_active(dev); - if (pcibios_pm_ops.restore_noirq) { error = pcibios_pm_ops.restore_noirq(dev); if (error) @@ -1181,6 +1214,7 @@ static int pci_pm_restore_noirq(struct device *dev) } pci_pm_default_resume_early(pci_dev); + pci_fixup_device(pci_fixup_resume_early, pci_dev); if (pci_has_legacy_pm_support(pci_dev)) return pci_legacy_resume_early(dev); @@ -1222,7 +1256,6 @@ static int pci_pm_restore(struct device *dev) #else /* !CONFIG_HIBERNATE_CALLBACKS */ #define pci_pm_freeze NULL -#define pci_pm_freeze_late NULL #define pci_pm_freeze_noirq NULL #define pci_pm_thaw NULL #define pci_pm_thaw_noirq NULL @@ -1348,7 +1381,6 @@ static const struct dev_pm_ops pci_dev_pm_ops = { .suspend_late = pci_pm_suspend_late, .resume = pci_pm_resume, .freeze = pci_pm_freeze, - .freeze_late = pci_pm_freeze_late, .thaw = pci_pm_thaw, .poweroff = pci_pm_poweroff, .poweroff_late = pci_pm_poweroff_late, diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 1c2a5ff5b095..29ed5ec1ac27 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -777,6 +777,12 @@ static inline pci_power_t platform_pci_get_power_state(struct pci_dev *dev) return pci_platform_pm ? pci_platform_pm->get_state(dev) : PCI_UNKNOWN; } +static inline void platform_pci_refresh_power_state(struct pci_dev *dev) +{ + if (pci_platform_pm && pci_platform_pm->refresh_state) + pci_platform_pm->refresh_state(dev); +} + static inline pci_power_t platform_pci_choose_state(struct pci_dev *dev) { return pci_platform_pm ? @@ -938,6 +944,21 @@ void pci_update_current_state(struct pci_dev *dev, pci_power_t state) } /** + * pci_refresh_power_state - Refresh the given device's power state data + * @dev: Target PCI device. + * + * Ask the platform to refresh the devices power state information and invoke + * pci_update_current_state() to update its current PCI power state. + */ +void pci_refresh_power_state(struct pci_dev *dev) +{ + if (platform_pci_power_manageable(dev)) + platform_pci_refresh_power_state(dev); + + pci_update_current_state(dev, dev->current_state); +} + +/** * pci_power_up - Put the given device into D0 forcibly * @dev: PCI device to power up */ @@ -1004,15 +1025,10 @@ static void __pci_start_power_transition(struct pci_dev *dev, pci_power_t state) if (state == PCI_D0) { pci_platform_power_transition(dev, PCI_D0); /* - * Mandatory power management transition delays, see - * PCI Express Base Specification Revision 2.0 Section - * 6.6.1: Conventional Reset. Do not delay for - * devices powered on/off by corresponding bridge, - * because have already delayed for the bridge. + * Mandatory power management transition delays are + * handled in the PCIe portdrv resume hooks. */ if (dev->runtime_d3cold) { - if (dev->d3cold_delay && !dev->imm_ready) - msleep(dev->d3cold_delay); /* * When powering on a bridge from D3cold, the * whole hierarchy may be powered on into @@ -2065,6 +2081,13 @@ static void pci_pme_list_scan(struct work_struct *work) */ if (bridge && bridge->current_state != PCI_D0) continue; + /* + * If the device is in D3cold it should not be + * polled either. + */ + if (pme_dev->dev->current_state == PCI_D3cold) + continue; + pci_pme_wakeup(pme_dev->dev, NULL); } else { list_del(&pme_dev->list); @@ -2459,45 +2482,56 @@ bool pci_dev_run_wake(struct pci_dev *dev) EXPORT_SYMBOL_GPL(pci_dev_run_wake); /** - * pci_dev_keep_suspended - Check if the device can stay in the suspended state. + * pci_dev_need_resume - Check if it is necessary to resume the device. * @pci_dev: Device to check. * - * Return 'true' if the device is runtime-suspended, it doesn't have to be + * Return 'true' if the device is not runtime-suspended or it has to be * reconfigured due to wakeup settings difference between system and runtime - * suspend and the current power state of it is suitable for the upcoming - * (system) transition. - * - * If the device is not configured for system wakeup, disable PME for it before - * returning 'true' to prevent it from waking up the system unnecessarily. + * suspend, or the current power state of it is not suitable for the upcoming + * (system-wide) transition. */ -bool pci_dev_keep_suspended(struct pci_dev *pci_dev) +bool pci_dev_need_resume(struct pci_dev *pci_dev) { struct device *dev = &pci_dev->dev; - bool wakeup = device_may_wakeup(dev); + pci_power_t target_state; - if (!pm_runtime_suspended(dev) - || pci_target_state(pci_dev, wakeup) != pci_dev->current_state - || platform_pci_need_resume(pci_dev)) - return false; + if (!pm_runtime_suspended(dev) || platform_pci_need_resume(pci_dev)) + return true; + + target_state = pci_target_state(pci_dev, device_may_wakeup(dev)); /* - * At this point the device is good to go unless it's been configured - * to generate PME at the runtime suspend time, but it is not supposed - * to wake up the system. In that case, simply disable PME for it - * (it will have to be re-enabled on exit from system resume). - * - * If the device's power state is D3cold and the platform check above - * hasn't triggered, the device's configuration is suitable and we don't - * need to manipulate it at all. + * If the earlier platform check has not triggered, D3cold is just power + * removal on top of D3hot, so no need to resume the device in that + * case. */ + return target_state != pci_dev->current_state && + target_state != PCI_D3cold && + pci_dev->current_state != PCI_D3hot; +} + +/** + * pci_dev_adjust_pme - Adjust PME setting for a suspended device. + * @pci_dev: Device to check. + * + * If the device is suspended and it is not configured for system wakeup, + * disable PME for it to prevent it from waking up the system unnecessarily. + * + * Note that if the device's power state is D3cold and the platform check in + * pci_dev_need_resume() has not triggered, the device's configuration need not + * be changed. + */ +void pci_dev_adjust_pme(struct pci_dev *pci_dev) +{ + struct device *dev = &pci_dev->dev; + spin_lock_irq(&dev->power.lock); - if (pm_runtime_suspended(dev) && pci_dev->current_state < PCI_D3cold && - !wakeup) + if (pm_runtime_suspended(dev) && !device_may_wakeup(dev) && + pci_dev->current_state < PCI_D3cold) __pci_pme_active(pci_dev, false); spin_unlock_irq(&dev->power.lock); - return true; } /** @@ -4568,14 +4602,16 @@ static int pci_pm_reset(struct pci_dev *dev, int probe) return pci_dev_wait(dev, "PM D3->D0", PCIE_RESET_READY_POLL_MS); } + /** - * pcie_wait_for_link - Wait until link is active or inactive + * pcie_wait_for_link_delay - Wait until link is active or inactive * @pdev: Bridge device * @active: waiting for active or inactive? + * @delay: Delay to wait after link has become active (in ms) * * Use this to wait till link becomes active or inactive. */ -bool pcie_wait_for_link(struct pci_dev *pdev, bool active) +bool pcie_wait_for_link_delay(struct pci_dev *pdev, bool active, int delay) { int timeout = 1000; bool ret; @@ -4612,13 +4648,25 @@ bool pcie_wait_for_link(struct pci_dev *pdev, bool active) timeout -= 10; } if (active && ret) - msleep(100); + msleep(delay); else if (ret != active) pci_info(pdev, "Data Link Layer Link Active not %s in 1000 msec\n", active ? "set" : "cleared"); return ret == active; } +/** + * pcie_wait_for_link - Wait until link is active or inactive + * @pdev: Bridge device + * @active: waiting for active or inactive? + * + * Use this to wait till link becomes active or inactive. + */ +bool pcie_wait_for_link(struct pci_dev *pdev, bool active) +{ + return pcie_wait_for_link_delay(pdev, active, 100); +} + void pci_reset_secondary_bus(struct pci_dev *dev) { u16 ctrl; diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 3fc227ef0815..1be03a97cb92 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -51,6 +51,8 @@ int pci_bus_error_reset(struct pci_dev *dev); * * @get_state: queries the platform firmware for a device's current power state * + * @refresh_state: asks the platform to refresh the device's power state data + * * @choose_state: returns PCI power state of given device preferred by the * platform; to be used during system-wide transitions from a * sleeping state to the working state and vice versa @@ -69,6 +71,7 @@ struct pci_platform_pm_ops { bool (*is_manageable)(struct pci_dev *dev); int (*set_state)(struct pci_dev *dev, pci_power_t state); pci_power_t (*get_state)(struct pci_dev *dev); + void (*refresh_state)(struct pci_dev *dev); pci_power_t (*choose_state)(struct pci_dev *dev); int (*set_wakeup)(struct pci_dev *dev, bool enable); bool (*need_resume)(struct pci_dev *dev); @@ -76,13 +79,15 @@ struct pci_platform_pm_ops { int pci_set_platform_pm(const struct pci_platform_pm_ops *ops); void pci_update_current_state(struct pci_dev *dev, pci_power_t state); +void pci_refresh_power_state(struct pci_dev *dev); void pci_power_up(struct pci_dev *dev); void pci_disable_enabled_device(struct pci_dev *dev); int pci_finish_runtime_suspend(struct pci_dev *dev); void pcie_clear_root_pme_status(struct pci_dev *dev); int __pci_pme_wakeup(struct pci_dev *dev, void *ign); void pci_pme_restore(struct pci_dev *dev); -bool pci_dev_keep_suspended(struct pci_dev *dev); +bool pci_dev_need_resume(struct pci_dev *dev); +void pci_dev_adjust_pme(struct pci_dev *dev); void pci_dev_complete_resume(struct pci_dev *pci_dev); void pci_config_pm_runtime_get(struct pci_dev *dev); void pci_config_pm_runtime_put(struct pci_dev *dev); @@ -492,6 +497,7 @@ static inline int pci_dev_specific_disable_acs_redir(struct pci_dev *dev) void pcie_do_recovery(struct pci_dev *dev, enum pci_channel_state state, u32 service); +bool pcie_wait_for_link_delay(struct pci_dev *pdev, bool active, int delay); bool pcie_wait_for_link(struct pci_dev *pdev, bool active); #ifdef CONFIG_PCIEASPM void pcie_aspm_init_link_state(struct pci_dev *pdev); diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index fd4cb75088f9..e44af7f4d37f 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -1062,18 +1062,18 @@ void pcie_aspm_powersave_config_link(struct pci_dev *pdev) up_read(&pci_bus_sem); } -static void __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem) +static int __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem) { struct pci_dev *parent = pdev->bus->self; struct pcie_link_state *link; if (!pci_is_pcie(pdev)) - return; + return 0; if (pdev->has_secondary_link) parent = pdev; if (!parent || !parent->link_state) - return; + return -EINVAL; /* * A driver requested that ASPM be disabled on this device, but @@ -1085,7 +1085,7 @@ static void __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem) */ if (aspm_disabled) { pci_warn(pdev, "can't disable ASPM; OS doesn't have ASPM control\n"); - return; + return -EPERM; } if (sem) @@ -1105,11 +1105,13 @@ static void __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem) mutex_unlock(&aspm_lock); if (sem) up_read(&pci_bus_sem); + + return 0; } -void pci_disable_link_state_locked(struct pci_dev *pdev, int state) +int pci_disable_link_state_locked(struct pci_dev *pdev, int state) { - __pci_disable_link_state(pdev, state, false); + return __pci_disable_link_state(pdev, state, false); } EXPORT_SYMBOL(pci_disable_link_state_locked); @@ -1117,14 +1119,14 @@ EXPORT_SYMBOL(pci_disable_link_state_locked); * pci_disable_link_state - Disable device's link state, so the link will * never enter specific states. Note that if the BIOS didn't grant ASPM * control to the OS, this does nothing because we can't touch the LNKCTL - * register. + * register. Returns 0 or a negative errno. * * @pdev: PCI device * @state: ASPM link state to disable */ -void pci_disable_link_state(struct pci_dev *pdev, int state) +int pci_disable_link_state(struct pci_dev *pdev, int state) { - __pci_disable_link_state(pdev, state, true); + return __pci_disable_link_state(pdev, state, true); } EXPORT_SYMBOL(pci_disable_link_state); diff --git a/drivers/pci/pcie/portdrv_core.c b/drivers/pci/pcie/portdrv_core.c index 1b330129089f..308c3e0c4a34 100644 --- a/drivers/pci/pcie/portdrv_core.c +++ b/drivers/pci/pcie/portdrv_core.c @@ -9,6 +9,7 @@ #include <linux/module.h> #include <linux/pci.h> #include <linux/kernel.h> +#include <linux/delay.h> #include <linux/errno.h> #include <linux/pm.h> #include <linux/pm_runtime.h> @@ -378,6 +379,67 @@ static int pm_iter(struct device *dev, void *data) return 0; } +static int get_downstream_delay(struct pci_bus *bus) +{ + struct pci_dev *pdev; + int min_delay = 100; + int max_delay = 0; + + list_for_each_entry(pdev, &bus->devices, bus_list) { + if (!pdev->imm_ready) + min_delay = 0; + else if (pdev->d3cold_delay < min_delay) + min_delay = pdev->d3cold_delay; + if (pdev->d3cold_delay > max_delay) + max_delay = pdev->d3cold_delay; + } + + return max(min_delay, max_delay); +} + +/* + * wait_for_downstream_link - Wait for downstream link to establish + * @pdev: PCIe port whose downstream link is waited + * + * Handle delays according to PCIe 4.0 section 6.6.1 before configuration + * access to the downstream component is permitted. + * + * This blocks PCI core resume of the hierarchy below this port until the + * link is trained. Should be called before resuming port services to + * prevent pciehp from starting to tear-down the hierarchy too soon. + */ +static void wait_for_downstream_link(struct pci_dev *pdev) +{ + int delay; + + if (pci_pcie_type(pdev) != PCI_EXP_TYPE_ROOT_PORT && + pci_pcie_type(pdev) != PCI_EXP_TYPE_DOWNSTREAM) + return; + + if (pci_dev_is_disconnected(pdev)) + return; + + if (!pdev->subordinate || list_empty(&pdev->subordinate->devices) || + !pdev->bridge_d3) + return; + + delay = get_downstream_delay(pdev->subordinate); + if (!delay) + return; + + dev_dbg(&pdev->dev, "waiting downstream link for %d ms\n", delay); + + /* + * If downstream port does not support speeds greater than 5 GT/s + * need to wait 100ms. For higher speeds (gen3) we need to wait + * first for the data link layer to become active. + */ + if (pcie_get_speed_cap(pdev) <= PCIE_SPEED_5_0GT) + msleep(delay); + else + pcie_wait_for_link_delay(pdev, true, delay); +} + /** * pcie_port_device_suspend - suspend port services associated with a PCIe port * @dev: PCI Express port to handle @@ -391,6 +453,8 @@ int pcie_port_device_suspend(struct device *dev) int pcie_port_device_resume_noirq(struct device *dev) { size_t off = offsetof(struct pcie_port_service_driver, resume_noirq); + + wait_for_downstream_link(to_pci_dev(dev)); return device_for_each_child(dev, &off, pm_iter); } @@ -421,6 +485,8 @@ int pcie_port_device_runtime_suspend(struct device *dev) int pcie_port_device_runtime_resume(struct device *dev) { size_t off = offsetof(struct pcie_port_service_driver, runtime_resume); + + wait_for_downstream_link(to_pci_dev(dev)); return device_for_each_child(dev, &off, pm_iter); } #endif /* PM */ diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 5a0b07428425..a3c7338fad86 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -64,7 +64,7 @@ static struct resource *get_pci_domain_busn_res(int domain_nr) return &r->res; } -static int find_anything(struct device *dev, void *data) +static int find_anything(struct device *dev, const void *data) { return 1; } diff --git a/drivers/pci/search.c b/drivers/pci/search.c index 5c7922612733..7f4e65872b8d 100644 --- a/drivers/pci/search.c +++ b/drivers/pci/search.c @@ -236,10 +236,10 @@ struct pci_dev *pci_get_domain_bus_and_slot(int domain, unsigned int bus, } EXPORT_SYMBOL(pci_get_domain_bus_and_slot); -static int match_pci_dev_by_id(struct device *dev, void *data) +static int match_pci_dev_by_id(struct device *dev, const void *data) { struct pci_dev *pdev = to_pci_dev(dev); - struct pci_device_id *id = data; + const struct pci_device_id *id = data; if (pci_match_one_device(id, pdev)) return 1; |