diff options
Diffstat (limited to 'drivers/pci')
27 files changed, 691 insertions, 428 deletions
diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig index a304f5ea11b9..77c1428cd945 100644 --- a/drivers/pci/Kconfig +++ b/drivers/pci/Kconfig @@ -52,7 +52,7 @@ config PCI_MSI If you don't know what to do here, say Y. config PCI_MSI_IRQ_DOMAIN - def_bool ARC || ARM || ARM64 || X86 || RISCV + def_bool y depends on PCI_MSI select GENERIC_MSI_IRQ_DOMAIN diff --git a/drivers/pci/Makefile b/drivers/pci/Makefile index 28cdd8c0213a..522d2b974e91 100644 --- a/drivers/pci/Makefile +++ b/drivers/pci/Makefile @@ -7,6 +7,8 @@ obj-$(CONFIG_PCI) += access.o bus.o probe.o host-bridge.o \ pci-sysfs.o rom.o setup-res.o irq.o vpd.o \ setup-bus.o vc.o mmap.o setup-irq.o +obj-$(CONFIG_PCI) += pcie/ + ifdef CONFIG_PCI obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_SYSFS) += slot.o @@ -15,7 +17,6 @@ endif obj-$(CONFIG_OF) += of.o obj-$(CONFIG_PCI_QUIRKS) += quirks.o -obj-$(CONFIG_PCIEPORTBUS) += pcie/ obj-$(CONFIG_HOTPLUG_PCI) += hotplug/ obj-$(CONFIG_PCI_MSI) += msi.o obj-$(CONFIG_PCI_ATS) += ats.o diff --git a/drivers/pci/access.c b/drivers/pci/access.c index 2fccb5762c76..79c4a2ef269a 100644 --- a/drivers/pci/access.c +++ b/drivers/pci/access.c @@ -355,7 +355,7 @@ static inline bool pcie_cap_has_sltctl(const struct pci_dev *dev) pcie_caps_reg(dev) & PCI_EXP_FLAGS_SLOT; } -static inline bool pcie_cap_has_rtctl(const struct pci_dev *dev) +bool pcie_cap_has_rtctl(const struct pci_dev *dev) { int type = pci_pcie_type(dev); diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c index 0f36a926059a..43ce6de70374 100644 --- a/drivers/pci/controller/dwc/pcie-designware-host.c +++ b/drivers/pci/controller/dwc/pcie-designware-host.c @@ -10,6 +10,7 @@ #include <linux/irqchip/chained_irq.h> #include <linux/irqdomain.h> +#include <linux/msi.h> #include <linux/of_address.h> #include <linux/of_pci.h> #include <linux/pci_regs.h> diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c index fc0fe4d4de49..3a05f6ca95b0 100644 --- a/drivers/pci/controller/pci-aardvark.c +++ b/drivers/pci/controller/pci-aardvark.c @@ -16,6 +16,7 @@ #include <linux/pci.h> #include <linux/init.h> #include <linux/platform_device.h> +#include <linux/msi.h> #include <linux/of_address.h> #include <linux/of_pci.h> diff --git a/drivers/pci/controller/pci-thunder-pem.c b/drivers/pci/controller/pci-thunder-pem.c index f127ce8bd4ef..9491e266b1ea 100644 --- a/drivers/pci/controller/pci-thunder-pem.c +++ b/drivers/pci/controller/pci-thunder-pem.c @@ -6,6 +6,7 @@ #include <linux/bitfield.h> #include <linux/kernel.h> #include <linux/init.h> +#include <linux/pci.h> #include <linux/of_address.h> #include <linux/of_pci.h> #include <linux/pci-acpi.h> diff --git a/drivers/pci/controller/pcie-cadence.h b/drivers/pci/controller/pcie-cadence.h index ae6bf2a2b3d3..f1cba3931b99 100644 --- a/drivers/pci/controller/pcie-cadence.h +++ b/drivers/pci/controller/pcie-cadence.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +/* SPDX-License-Identifier: GPL-2.0 */ // Copyright (c) 2017 Cadence // Cadence PCIe controller driver. // Author: Cyrille Pitchen <cyrille.pitchen@free-electrons.com> diff --git a/drivers/pci/controller/pcie-rockchip.h b/drivers/pci/controller/pcie-rockchip.h index 8e87a059ce73..53e4f9e59624 100644 --- a/drivers/pci/controller/pcie-rockchip.h +++ b/drivers/pci/controller/pcie-rockchip.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0+ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * Rockchip AXI PCIe controller driver * diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c index e4c46637f32f..b3869951c0eb 100644 --- a/drivers/pci/hotplug/acpiphp_glue.c +++ b/drivers/pci/hotplug/acpiphp_glue.c @@ -449,8 +449,15 @@ static void acpiphp_native_scan_bridge(struct pci_dev *bridge) /* Scan non-hotplug bridges that need to be reconfigured */ for_each_pci_bridge(dev, bus) { - if (!hotplug_is_native(dev)) - max = pci_scan_bridge(bus, dev, max, 1); + if (hotplug_is_native(dev)) + continue; + + max = pci_scan_bridge(bus, dev, max, 1); + if (dev->subordinate) { + pcibios_resource_survey_bus(dev->subordinate); + pci_bus_size_bridges(dev->subordinate); + pci_bus_assign_resources(dev->subordinate); + } } } @@ -480,7 +487,6 @@ static void enable_slot(struct acpiphp_slot *slot, bool bridge) if (PCI_SLOT(dev->devfn) == slot->device) acpiphp_native_scan_bridge(dev); } - pci_assign_unassigned_bridge_resources(bus->self); } else { LIST_HEAD(add_list); int max, pass; diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h index 654c972b8ea0..aa61d4c219d7 100644 --- a/drivers/pci/hotplug/pciehp.h +++ b/drivers/pci/hotplug/pciehp.h @@ -72,6 +72,7 @@ extern int pciehp_poll_time; * @reset_lock: prevents access to the Data Link Layer Link Active bit in the * Link Status register and to the Presence Detect State bit in the Slot * Status register during a slot reset which may cause them to flap + * @ist_running: flag to keep user request waiting while IRQ thread is running * @request_result: result of last user request submitted to the IRQ thread * @requester: wait queue to wake up on completion of user request, * used for synchronous slot enable/disable request via sysfs @@ -101,6 +102,7 @@ struct controller { struct hotplug_slot hotplug_slot; /* hotplug core interface */ struct rw_semaphore reset_lock; + unsigned int ist_running; int request_result; wait_queue_head_t requester; }; @@ -172,10 +174,10 @@ void pciehp_set_indicators(struct controller *ctrl, int pwr, int attn); void pciehp_get_latch_status(struct controller *ctrl, u8 *status); int pciehp_query_power_fault(struct controller *ctrl); -bool pciehp_card_present(struct controller *ctrl); -bool pciehp_card_present_or_link_active(struct controller *ctrl); +int pciehp_card_present(struct controller *ctrl); +int pciehp_card_present_or_link_active(struct controller *ctrl); int pciehp_check_link_status(struct controller *ctrl); -bool pciehp_check_link_active(struct controller *ctrl); +int pciehp_check_link_active(struct controller *ctrl); void pciehp_release_ctrl(struct controller *ctrl); int pciehp_sysfs_enable_slot(struct hotplug_slot *hotplug_slot); diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c index b3122c151b80..312cc45c44c7 100644 --- a/drivers/pci/hotplug/pciehp_core.c +++ b/drivers/pci/hotplug/pciehp_core.c @@ -139,10 +139,15 @@ static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value) { struct controller *ctrl = to_ctrl(hotplug_slot); struct pci_dev *pdev = ctrl->pcie->port; + int ret; pci_config_pm_runtime_get(pdev); - *value = pciehp_card_present_or_link_active(ctrl); + ret = pciehp_card_present_or_link_active(ctrl); pci_config_pm_runtime_put(pdev); + if (ret < 0) + return ret; + + *value = ret; return 0; } @@ -158,13 +163,13 @@ static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value) */ static void pciehp_check_presence(struct controller *ctrl) { - bool occupied; + int occupied; down_read(&ctrl->reset_lock); mutex_lock(&ctrl->state_lock); occupied = pciehp_card_present_or_link_active(ctrl); - if ((occupied && (ctrl->state == OFF_STATE || + if ((occupied > 0 && (ctrl->state == OFF_STATE || ctrl->state == BLINKINGON_STATE)) || (!occupied && (ctrl->state == ON_STATE || ctrl->state == BLINKINGOFF_STATE))) @@ -253,7 +258,7 @@ static bool pme_is_native(struct pcie_device *dev) return pcie_ports_native || host->native_pme; } -static int pciehp_suspend(struct pcie_device *dev) +static void pciehp_disable_interrupt(struct pcie_device *dev) { /* * Disable hotplug interrupt so that it does not trigger @@ -261,7 +266,19 @@ static int pciehp_suspend(struct pcie_device *dev) */ if (pme_is_native(dev)) pcie_disable_interrupt(get_service_data(dev)); +} + +#ifdef CONFIG_PM_SLEEP +static int pciehp_suspend(struct pcie_device *dev) +{ + /* + * If the port is already runtime suspended we can keep it that + * way. + */ + if (dev_pm_smart_suspend_and_suspended(&dev->port->dev)) + return 0; + pciehp_disable_interrupt(dev); return 0; } @@ -279,6 +296,7 @@ static int pciehp_resume_noirq(struct pcie_device *dev) return 0; } +#endif static int pciehp_resume(struct pcie_device *dev) { @@ -292,6 +310,12 @@ static int pciehp_resume(struct pcie_device *dev) return 0; } +static int pciehp_runtime_suspend(struct pcie_device *dev) +{ + pciehp_disable_interrupt(dev); + return 0; +} + static int pciehp_runtime_resume(struct pcie_device *dev) { struct controller *ctrl = get_service_data(dev); @@ -318,10 +342,12 @@ static struct pcie_port_service_driver hpdriver_portdrv = { .remove = pciehp_remove, #ifdef CONFIG_PM +#ifdef CONFIG_PM_SLEEP .suspend = pciehp_suspend, .resume_noirq = pciehp_resume_noirq, .resume = pciehp_resume, - .runtime_suspend = pciehp_suspend, +#endif + .runtime_suspend = pciehp_runtime_suspend, .runtime_resume = pciehp_runtime_resume, #endif /* PM */ }; diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c index 21af7b16d7a4..6503d15effbb 100644 --- a/drivers/pci/hotplug/pciehp_ctrl.c +++ b/drivers/pci/hotplug/pciehp_ctrl.c @@ -226,7 +226,7 @@ void pciehp_handle_disable_request(struct controller *ctrl) void pciehp_handle_presence_or_link_change(struct controller *ctrl, u32 events) { - bool present, link_active; + int present, link_active; /* * If the slot is on and presence or link has changed, turn it off. @@ -257,7 +257,7 @@ void pciehp_handle_presence_or_link_change(struct controller *ctrl, u32 events) mutex_lock(&ctrl->state_lock); present = pciehp_card_present(ctrl); link_active = pciehp_check_link_active(ctrl); - if (!present && !link_active) { + if (present <= 0 && link_active <= 0) { mutex_unlock(&ctrl->state_lock); return; } @@ -375,7 +375,8 @@ int pciehp_sysfs_enable_slot(struct hotplug_slot *hotplug_slot) ctrl->request_result = -ENODEV; pciehp_request(ctrl, PCI_EXP_SLTSTA_PDC); wait_event(ctrl->requester, - !atomic_read(&ctrl->pending_events)); + !atomic_read(&ctrl->pending_events) && + !ctrl->ist_running); return ctrl->request_result; case POWERON_STATE: ctrl_info(ctrl, "Slot(%s): Already in powering on state\n", @@ -408,7 +409,8 @@ int pciehp_sysfs_disable_slot(struct hotplug_slot *hotplug_slot) mutex_unlock(&ctrl->state_lock); pciehp_request(ctrl, DISABLE_SLOT); wait_event(ctrl->requester, - !atomic_read(&ctrl->pending_events)); + !atomic_read(&ctrl->pending_events) && + !ctrl->ist_running); return ctrl->request_result; case POWEROFF_STATE: ctrl_info(ctrl, "Slot(%s): Already in powering off state\n", diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c index 1a522c1c4177..8a2cb1764386 100644 --- a/drivers/pci/hotplug/pciehp_hpc.c +++ b/drivers/pci/hotplug/pciehp_hpc.c @@ -68,7 +68,7 @@ static int pcie_poll_cmd(struct controller *ctrl, int timeout) struct pci_dev *pdev = ctrl_dev(ctrl); u16 slot_status; - while (true) { + do { pcie_capability_read_word(pdev, PCI_EXP_SLTSTA, &slot_status); if (slot_status == (u16) ~0) { ctrl_info(ctrl, "%s: no response from device\n", @@ -81,11 +81,9 @@ static int pcie_poll_cmd(struct controller *ctrl, int timeout) PCI_EXP_SLTSTA_CC); return 1; } - if (timeout < 0) - break; msleep(10); timeout -= 10; - } + } while (timeout >= 0); return 0; /* timeout */ } @@ -201,17 +199,29 @@ static void pcie_write_cmd_nowait(struct controller *ctrl, u16 cmd, u16 mask) pcie_do_write_cmd(ctrl, cmd, mask, false); } -bool pciehp_check_link_active(struct controller *ctrl) +/** + * pciehp_check_link_active() - Is the link active + * @ctrl: PCIe hotplug controller + * + * Check whether the downstream link is currently active. Note it is + * possible that the card is removed immediately after this so the + * caller may need to take it into account. + * + * If the hotplug controller itself is not available anymore returns + * %-ENODEV. + */ +int pciehp_check_link_active(struct controller *ctrl) { struct pci_dev *pdev = ctrl_dev(ctrl); u16 lnk_status; - bool ret; + int ret; - pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lnk_status); - ret = !!(lnk_status & PCI_EXP_LNKSTA_DLLLA); + ret = pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lnk_status); + if (ret == PCIBIOS_DEVICE_NOT_FOUND || lnk_status == (u16)~0) + return -ENODEV; - if (ret) - ctrl_dbg(ctrl, "%s: lnk_status = %x\n", __func__, lnk_status); + ret = !!(lnk_status & PCI_EXP_LNKSTA_DLLLA); + ctrl_dbg(ctrl, "%s: lnk_status = %x\n", __func__, lnk_status); return ret; } @@ -373,13 +383,29 @@ void pciehp_get_latch_status(struct controller *ctrl, u8 *status) *status = !!(slot_status & PCI_EXP_SLTSTA_MRLSS); } -bool pciehp_card_present(struct controller *ctrl) +/** + * pciehp_card_present() - Is the card present + * @ctrl: PCIe hotplug controller + * + * Function checks whether the card is currently present in the slot and + * in that case returns true. Note it is possible that the card is + * removed immediately after the check so the caller may need to take + * this into account. + * + * It the hotplug controller itself is not available anymore returns + * %-ENODEV. + */ +int pciehp_card_present(struct controller *ctrl) { struct pci_dev *pdev = ctrl_dev(ctrl); u16 slot_status; + int ret; - pcie_capability_read_word(pdev, PCI_EXP_SLTSTA, &slot_status); - return slot_status & PCI_EXP_SLTSTA_PDS; + ret = pcie_capability_read_word(pdev, PCI_EXP_SLTSTA, &slot_status); + if (ret == PCIBIOS_DEVICE_NOT_FOUND || slot_status == (u16)~0) + return -ENODEV; + + return !!(slot_status & PCI_EXP_SLTSTA_PDS); } /** @@ -390,10 +416,19 @@ bool pciehp_card_present(struct controller *ctrl) * Presence Detect State bit, this helper also returns true if the Link Active * bit is set. This is a concession to broken hotplug ports which hardwire * Presence Detect State to zero, such as Wilocity's [1ae9:0200]. + * + * Returns: %1 if the slot is occupied and %0 if it is not. If the hotplug + * port is not present anymore returns %-ENODEV. */ -bool pciehp_card_present_or_link_active(struct controller *ctrl) +int pciehp_card_present_or_link_active(struct controller *ctrl) { - return pciehp_card_present(ctrl) || pciehp_check_link_active(ctrl); + int ret; + + ret = pciehp_card_present(ctrl); + if (ret) + return ret; + + return pciehp_check_link_active(ctrl); } int pciehp_query_power_fault(struct controller *ctrl) @@ -583,6 +618,7 @@ static irqreturn_t pciehp_ist(int irq, void *dev_id) irqreturn_t ret; u32 events; + ctrl->ist_running = true; pci_config_pm_runtime_get(pdev); /* rerun pciehp_isr() if the port was inaccessible on interrupt */ @@ -629,6 +665,7 @@ static irqreturn_t pciehp_ist(int irq, void *dev_id) up_read(&ctrl->reset_lock); pci_config_pm_runtime_put(pdev); + ctrl->ist_running = false; wake_up(&ctrl->requester); return IRQ_HANDLED; } diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index 0884bedcfc7a..c7709e49f0e4 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -213,12 +213,13 @@ u32 __pci_msix_desc_mask_irq(struct msi_desc *desc, u32 flag) if (pci_msi_ignore_mask) return 0; + desc_addr = pci_msix_desc_addr(desc); if (!desc_addr) return 0; mask_bits &= ~PCI_MSIX_ENTRY_CTRL_MASKBIT; - if (flag) + if (flag & PCI_MSIX_ENTRY_CTRL_MASKBIT) mask_bits |= PCI_MSIX_ENTRY_CTRL_MASKBIT; writel(mask_bits, desc_addr + PCI_MSIX_ENTRY_VECTOR_CTRL); @@ -861,7 +862,7 @@ static int pci_msi_supported(struct pci_dev *dev, int nvec) if (!pci_msi_enable) return 0; - if (!dev || dev->no_msi || dev->current_state != PCI_D0) + if (!dev || dev->no_msi) return 0; /* @@ -972,7 +973,7 @@ static int __pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries, int nr_entries; int i, j; - if (!pci_msi_supported(dev, nvec)) + if (!pci_msi_supported(dev, nvec) || dev->current_state != PCI_D0) return -EINVAL; nr_entries = pci_msix_vec_count(dev); @@ -1058,7 +1059,7 @@ static int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec, int nvec; int rc; - if (!pci_msi_supported(dev, minvec)) + if (!pci_msi_supported(dev, minvec) || dev->current_state != PCI_D0) return -EINVAL; /* Check whether driver already requested MSI-X IRQs */ @@ -1315,22 +1316,6 @@ const struct cpumask *pci_irq_get_affinity(struct pci_dev *dev, int nr) } EXPORT_SYMBOL(pci_irq_get_affinity); -/** - * pci_irq_get_node - return the NUMA node of a particular MSI vector - * @pdev: PCI device to operate on - * @vec: device-relative interrupt vector index (0-based). - */ -int pci_irq_get_node(struct pci_dev *pdev, int vec) -{ - const struct cpumask *mask; - - mask = pci_irq_get_affinity(pdev, vec); - if (mask) - return local_memory_node(cpu_to_node(cpumask_first(mask))); - return dev_to_node(&pdev->dev); -} -EXPORT_SYMBOL(pci_irq_get_node); - struct pci_dev *msi_desc_to_pci_dev(struct msi_desc *desc) { return to_pci_dev(desc->dev); diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index a8124e47bf6e..0454ca0e4e3f 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -315,7 +315,8 @@ static long local_pci_probe(void *_ddi) * Probe function should return < 0 for failure, 0 for success * Treat values > 0 as success, but warn. */ - dev_warn(dev, "Driver probe function unexpectedly returned %d\n", rc); + pci_warn(pci_dev, "Driver probe function unexpectedly returned %d\n", + rc); return 0; } @@ -517,6 +518,12 @@ static int pci_restore_standard_config(struct pci_dev *pci_dev) return 0; } +static void pci_pm_default_resume(struct pci_dev *pci_dev) +{ + pci_fixup_device(pci_fixup_resume, pci_dev); + pci_enable_wake(pci_dev, PCI_D0, false); +} + #endif #ifdef CONFIG_PM_SLEEP @@ -524,6 +531,7 @@ static int pci_restore_standard_config(struct pci_dev *pci_dev) static void pci_pm_default_resume_early(struct pci_dev *pci_dev) { pci_power_up(pci_dev); + pci_update_current_state(pci_dev, PCI_D0); pci_restore_state(pci_dev); pci_pme_restore(pci_dev); } @@ -578,9 +586,9 @@ static int pci_legacy_suspend(struct device *dev, pm_message_t state) if (!pci_dev->state_saved && pci_dev->current_state != PCI_D0 && pci_dev->current_state != PCI_UNKNOWN) { - WARN_ONCE(pci_dev->current_state != prev, - "PCI PM: Device state not saved by %pS\n", - drv->suspend); + pci_WARN_ONCE(pci_dev, pci_dev->current_state != prev, + "PCI PM: Device state not saved by %pS\n", + drv->suspend); } } @@ -592,46 +600,17 @@ static int pci_legacy_suspend(struct device *dev, pm_message_t state) static int pci_legacy_suspend_late(struct device *dev, pm_message_t state) { struct pci_dev *pci_dev = to_pci_dev(dev); - struct pci_driver *drv = pci_dev->driver; - - if (drv && drv->suspend_late) { - pci_power_t prev = pci_dev->current_state; - int error; - - error = drv->suspend_late(pci_dev, state); - suspend_report_result(drv->suspend_late, error); - if (error) - return error; - - if (!pci_dev->state_saved && pci_dev->current_state != PCI_D0 - && pci_dev->current_state != PCI_UNKNOWN) { - WARN_ONCE(pci_dev->current_state != prev, - "PCI PM: Device state not saved by %pS\n", - drv->suspend_late); - goto Fixup; - } - } if (!pci_dev->state_saved) pci_save_state(pci_dev); pci_pm_set_unknown_state(pci_dev); -Fixup: pci_fixup_device(pci_fixup_suspend_late, pci_dev); return 0; } -static int pci_legacy_resume_early(struct device *dev) -{ - struct pci_dev *pci_dev = to_pci_dev(dev); - struct pci_driver *drv = pci_dev->driver; - - return drv && drv->resume_early ? - drv->resume_early(pci_dev) : 0; -} - static int pci_legacy_resume(struct device *dev) { struct pci_dev *pci_dev = to_pci_dev(dev); @@ -645,12 +624,6 @@ static int pci_legacy_resume(struct device *dev) /* Auxiliary functions used by the new power management framework */ -static void pci_pm_default_resume(struct pci_dev *pci_dev) -{ - pci_fixup_device(pci_fixup_resume, pci_dev); - pci_enable_wake(pci_dev, PCI_D0, false); -} - static void pci_pm_default_suspend(struct pci_dev *pci_dev) { /* Disable non-bridge devices without PM support */ @@ -661,16 +634,15 @@ static void pci_pm_default_suspend(struct pci_dev *pci_dev) static bool pci_has_legacy_pm_support(struct pci_dev *pci_dev) { struct pci_driver *drv = pci_dev->driver; - bool ret = drv && (drv->suspend || drv->suspend_late || drv->resume - || drv->resume_early); + bool ret = drv && (drv->suspend || drv->resume); /* * Legacy PM support is used by default, so warn if the new framework is * supported as well. Drivers are supposed to support either the * former, or the latter, but not both at the same time. */ - WARN(ret && drv->driver.pm, "driver %s device %04x:%04x\n", - drv->name, pci_dev->vendor, pci_dev->device); + pci_WARN(pci_dev, ret && drv->driver.pm, "device %04x:%04x\n", + pci_dev->vendor, pci_dev->device); return ret; } @@ -679,11 +651,11 @@ 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); + const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - if (drv && drv->pm && drv->pm->prepare) { - int error = drv->pm->prepare(dev); + if (pm && pm->prepare) { + int error = pm->prepare(dev); if (error < 0) return error; @@ -793,9 +765,9 @@ static int pci_pm_suspend(struct device *dev) if (!pci_dev->state_saved && pci_dev->current_state != PCI_D0 && pci_dev->current_state != PCI_UNKNOWN) { - WARN_ONCE(pci_dev->current_state != prev, - "PCI PM: State of device not saved by %pS\n", - pm->suspend); + pci_WARN_ONCE(pci_dev, pci_dev->current_state != prev, + "PCI PM: State of device not saved by %pS\n", + pm->suspend); } } @@ -841,9 +813,9 @@ static int pci_pm_suspend_noirq(struct device *dev) if (!pci_dev->state_saved && pci_dev->current_state != PCI_D0 && pci_dev->current_state != PCI_UNKNOWN) { - WARN_ONCE(pci_dev->current_state != prev, - "PCI PM: State of device not saved by %pS\n", - pm->suspend_noirq); + pci_WARN_ONCE(pci_dev, pci_dev->current_state != prev, + "PCI PM: State of device not saved by %pS\n", + pm->suspend_noirq); goto Fixup; } } @@ -865,7 +837,7 @@ static int pci_pm_suspend_noirq(struct device *dev) pci_prepare_to_sleep(pci_dev); } - dev_dbg(dev, "PCI PM: Suspend power state: %s\n", + pci_dbg(pci_dev, "PCI PM: Suspend power state: %s\n", pci_power_name(pci_dev->current_state)); if (pci_dev->current_state == PCI_D0) { @@ -880,7 +852,7 @@ static int pci_pm_suspend_noirq(struct device *dev) } if (pci_dev->skip_bus_pm && pm_suspend_no_platform()) { - dev_dbg(dev, "PCI PM: Skipped\n"); + pci_dbg(pci_dev, "PCI PM: Skipped\n"); goto Fixup; } @@ -917,8 +889,9 @@ Fixup: static int pci_pm_resume_noirq(struct device *dev) { struct pci_dev *pci_dev = to_pci_dev(dev); - struct device_driver *drv = dev->driver; - int error = 0; + const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; + pci_power_t prev_state = pci_dev->current_state; + bool skip_bus_pm = pci_dev->skip_bus_pm; if (dev_pm_may_skip_resume(dev)) return 0; @@ -937,27 +910,28 @@ static int pci_pm_resume_noirq(struct device *dev) * 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())) + if (!(skip_bus_pm && pm_suspend_no_platform())) pci_pm_default_resume_early(pci_dev); pci_fixup_device(pci_fixup_resume_early, pci_dev); + pcie_pme_root_status_cleanup(pci_dev); - if (pci_has_legacy_pm_support(pci_dev)) - return pci_legacy_resume_early(dev); + if (!skip_bus_pm && prev_state == PCI_D3cold) + pci_bridge_wait_for_secondary_bus(pci_dev); - pcie_pme_root_status_cleanup(pci_dev); + if (pci_has_legacy_pm_support(pci_dev)) + return 0; - if (drv && drv->pm && drv->pm->resume_noirq) - error = drv->pm->resume_noirq(dev); + if (pm && pm->resume_noirq) + return pm->resume_noirq(dev); - return error; + return 0; } static int pci_pm_resume(struct device *dev) { struct pci_dev *pci_dev = to_pci_dev(dev); const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - int error = 0; /* * This is necessary for the suspend error path in which resume is @@ -973,12 +947,12 @@ static int pci_pm_resume(struct device *dev) if (pm) { if (pm->resume) - error = pm->resume(dev); + return pm->resume(dev); } else { pci_pm_reenable_device(pci_dev); } - return error; + return 0; } #else /* !CONFIG_SUSPEND */ @@ -993,7 +967,6 @@ static int pci_pm_resume(struct device *dev) #ifdef CONFIG_HIBERNATE_CALLBACKS - /* * pcibios_pm_ops - provide arch-specific hooks when a PCI device is doing * a hibernate transition @@ -1039,16 +1012,16 @@ static int pci_pm_freeze(struct device *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; + const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; if (pci_has_legacy_pm_support(pci_dev)) return pci_legacy_suspend_late(dev, PMSG_FREEZE); - if (drv && drv->pm && drv->pm->freeze_noirq) { + if (pm && pm->freeze_noirq) { int error; - error = drv->pm->freeze_noirq(dev); - suspend_report_result(drv->pm->freeze_noirq, error); + error = pm->freeze_noirq(dev); + suspend_report_result(pm->freeze_noirq, error); if (error) return error; } @@ -1067,8 +1040,8 @@ static int pci_pm_freeze_noirq(struct device *dev) static int pci_pm_thaw_noirq(struct device *dev) { struct pci_dev *pci_dev = to_pci_dev(dev); - struct device_driver *drv = dev->driver; - int error = 0; + const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; + int error; if (pcibios_pm_ops.thaw_noirq) { error = pcibios_pm_ops.thaw_noirq(dev); @@ -1076,21 +1049,25 @@ static int pci_pm_thaw_noirq(struct device *dev) return error; } - if (pci_has_legacy_pm_support(pci_dev)) - return pci_legacy_resume_early(dev); - /* - * pci_restore_state() requires the device to be in D0 (because of MSI - * restoration among other things), so force it into D0 in case the - * driver's "freeze" callbacks put it into a low-power state directly. + * The pm->thaw_noirq() callback assumes the device has been + * returned to D0 and its config state has been restored. + * + * In addition, pci_restore_state() restores MSI-X state in MMIO + * space, which requires the device to be in D0, so return it to D0 + * in case the driver's "freeze" callbacks put it into a low-power + * state. */ pci_set_power_state(pci_dev, PCI_D0); pci_restore_state(pci_dev); - if (drv && drv->pm && drv->pm->thaw_noirq) - error = drv->pm->thaw_noirq(dev); + if (pci_has_legacy_pm_support(pci_dev)) + return 0; + + if (pm && pm->thaw_noirq) + return pm->thaw_noirq(dev); - return error; + return 0; } static int pci_pm_thaw(struct device *dev) @@ -1161,24 +1138,24 @@ static int pci_pm_poweroff_late(struct device *dev) static int pci_pm_poweroff_noirq(struct device *dev) { struct pci_dev *pci_dev = to_pci_dev(dev); - struct device_driver *drv = dev->driver; + const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; if (dev_pm_smart_suspend_and_suspended(dev)) return 0; - if (pci_has_legacy_pm_support(to_pci_dev(dev))) + if (pci_has_legacy_pm_support(pci_dev)) return pci_legacy_suspend_late(dev, PMSG_HIBERNATE); - if (!drv || !drv->pm) { + if (!pm) { pci_fixup_device(pci_fixup_suspend_late, pci_dev); return 0; } - if (drv->pm->poweroff_noirq) { + if (pm->poweroff_noirq) { int error; - error = drv->pm->poweroff_noirq(dev); - suspend_report_result(drv->pm->poweroff_noirq, error); + error = pm->poweroff_noirq(dev); + suspend_report_result(pm->poweroff_noirq, error); if (error) return error; } @@ -1204,8 +1181,8 @@ static int pci_pm_poweroff_noirq(struct device *dev) static int pci_pm_restore_noirq(struct device *dev) { struct pci_dev *pci_dev = to_pci_dev(dev); - struct device_driver *drv = dev->driver; - int error = 0; + const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; + int error; if (pcibios_pm_ops.restore_noirq) { error = pcibios_pm_ops.restore_noirq(dev); @@ -1217,19 +1194,18 @@ static int pci_pm_restore_noirq(struct device *dev) pci_fixup_device(pci_fixup_resume_early, pci_dev); if (pci_has_legacy_pm_support(pci_dev)) - return pci_legacy_resume_early(dev); + return 0; - if (drv && drv->pm && drv->pm->restore_noirq) - error = drv->pm->restore_noirq(dev); + if (pm && pm->restore_noirq) + return pm->restore_noirq(dev); - return error; + return 0; } static int pci_pm_restore(struct device *dev) { struct pci_dev *pci_dev = to_pci_dev(dev); const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - int error = 0; /* * This is necessary for the hibernation error path in which restore is @@ -1245,12 +1221,12 @@ static int pci_pm_restore(struct device *dev) if (pm) { if (pm->restore) - error = pm->restore(dev); + return pm->restore(dev); } else { pci_pm_reenable_device(pci_dev); } - return error; + return 0; } #else /* !CONFIG_HIBERNATE_CALLBACKS */ @@ -1295,11 +1271,11 @@ static int pci_pm_runtime_suspend(struct device *dev) * log level. */ if (error == -EBUSY || error == -EAGAIN) { - dev_dbg(dev, "can't suspend now (%ps returned %d)\n", + pci_dbg(pci_dev, "can't suspend now (%ps returned %d)\n", pm->runtime_suspend, error); return error; } else if (error) { - dev_err(dev, "can't suspend (%ps returned %d)\n", + pci_err(pci_dev, "can't suspend (%ps returned %d)\n", pm->runtime_suspend, error); return error; } @@ -1310,9 +1286,9 @@ static int pci_pm_runtime_suspend(struct device *dev) if (pm && pm->runtime_suspend && !pci_dev->state_saved && pci_dev->current_state != PCI_D0 && pci_dev->current_state != PCI_UNKNOWN) { - WARN_ONCE(pci_dev->current_state != prev, - "PCI PM: State of device not saved by %pS\n", - pm->runtime_suspend); + pci_WARN_ONCE(pci_dev, pci_dev->current_state != prev, + "PCI PM: State of device not saved by %pS\n", + pm->runtime_suspend); return 0; } @@ -1326,9 +1302,10 @@ static int pci_pm_runtime_suspend(struct device *dev) static int pci_pm_runtime_resume(struct device *dev) { - int rc = 0; struct pci_dev *pci_dev = to_pci_dev(dev); const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; + pci_power_t prev_state = pci_dev->current_state; + int error = 0; /* * Restoring config space is necessary even if the device is not bound @@ -1341,22 +1318,23 @@ static int pci_pm_runtime_resume(struct device *dev) return 0; pci_fixup_device(pci_fixup_resume_early, pci_dev); - pci_enable_wake(pci_dev, PCI_D0, false); - pci_fixup_device(pci_fixup_resume, pci_dev); + pci_pm_default_resume(pci_dev); + + if (prev_state == PCI_D3cold) + pci_bridge_wait_for_secondary_bus(pci_dev); if (pm && pm->runtime_resume) - rc = pm->runtime_resume(dev); + error = pm->runtime_resume(dev); pci_dev->runtime_d3cold = false; - return rc; + return error; } static int pci_pm_runtime_idle(struct device *dev) { struct pci_dev *pci_dev = to_pci_dev(dev); const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - int ret = 0; /* * If pci_dev->driver is not set (unbound), the device should @@ -1369,9 +1347,9 @@ static int pci_pm_runtime_idle(struct device *dev) return -ENOSYS; if (pm->runtime_idle) - ret = pm->runtime_idle(dev); + return pm->runtime_idle(dev); - return ret; + return 0; } static const struct dev_pm_ops pci_dev_pm_ops = { diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index 07bd84c50238..13f766db0684 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -1330,7 +1330,6 @@ static int pci_create_capabilities_sysfs(struct pci_dev *dev) int retval; pcie_vpd_create_sysfs_dev_files(dev); - pcie_aspm_create_sysfs_dev_files(dev); if (dev->reset_fn) { retval = device_create_file(&dev->dev, &dev_attr_reset); @@ -1340,7 +1339,6 @@ static int pci_create_capabilities_sysfs(struct pci_dev *dev) return 0; error: - pcie_aspm_remove_sysfs_dev_files(dev); pcie_vpd_remove_sysfs_dev_files(dev); return retval; } @@ -1416,7 +1414,6 @@ err: static void pci_remove_capabilities_sysfs(struct pci_dev *dev) { pcie_vpd_remove_sysfs_dev_files(dev); - pcie_aspm_remove_sysfs_dev_files(dev); if (dev->reset_fn) { device_remove_file(&dev->dev, &dev_attr_reset); dev->reset_fn = 0; @@ -1539,24 +1536,6 @@ const struct attribute_group *pci_dev_groups[] = { NULL, }; -static const struct attribute_group pci_bridge_group = { - .attrs = pci_bridge_attrs, -}; - -const struct attribute_group *pci_bridge_groups[] = { - &pci_bridge_group, - NULL, -}; - -static const struct attribute_group pcie_dev_group = { - .attrs = pcie_dev_attrs, -}; - -const struct attribute_group *pcie_dev_groups[] = { - &pcie_dev_group, - NULL, -}; - static const struct attribute_group pci_dev_hp_attr_group = { .attrs = pci_dev_hp_attrs, .is_visible = pci_dev_hp_attrs_are_visible, @@ -1588,6 +1567,9 @@ static const struct attribute_group *pci_dev_attr_groups[] = { #ifdef CONFIG_PCIEAER &aer_stats_attr_group, #endif +#ifdef CONFIG_PCIEASPM + &aspm_ctrl_attr_group, +#endif NULL, }; diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 66ff1ca5b688..1ffe7364bb7f 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -13,6 +13,7 @@ #include <linux/delay.h> #include <linux/dmi.h> #include <linux/init.h> +#include <linux/msi.h> #include <linux/of.h> #include <linux/of_pci.h> #include <linux/pci.h> @@ -841,14 +842,16 @@ static int pci_raw_set_power_state(struct pci_dev *dev, pci_power_t state) return -EINVAL; /* - * Validate current state: - * Can enter D0 from any state, but if we can only go deeper - * to sleep if we're already in a low power state + * Validate transition: We can enter D0 from any state, but if + * we're already in a low-power state, we can only go deeper. E.g., + * we can go from D1 to D3, but we can't go directly from D3 to D1; + * we'd have to go from D3 to D0, then to D1. */ if (state != PCI_D0 && dev->current_state <= PCI_D3cold && dev->current_state > state) { - pci_err(dev, "invalid power transition (from state %d to %d)\n", - dev->current_state, state); + pci_err(dev, "invalid power transition (from %s to %s)\n", + pci_power_name(dev->current_state), + pci_power_name(state)); return -EINVAL; } @@ -858,6 +861,12 @@ static int pci_raw_set_power_state(struct pci_dev *dev, pci_power_t state) return -EIO; pci_read_config_word(dev, dev->pm_cap + PCI_PM_CTRL, &pmcsr); + if (pmcsr == (u16) ~0) { + pci_err(dev, "can't change power state from %s to %s (config space inaccessible)\n", + pci_power_name(dev->current_state), + pci_power_name(state)); + return -EIO; + } /* * If we're (effectively) in D3, force entire word to 0. @@ -893,13 +902,14 @@ static int pci_raw_set_power_state(struct pci_dev *dev, pci_power_t state) if (state == PCI_D3hot || dev->current_state == PCI_D3hot) pci_dev_d3_sleep(dev); else if (state == PCI_D2 || dev->current_state == PCI_D2) - udelay(PCI_PM_D2_DELAY); + msleep(PCI_PM_D2_DELAY); pci_read_config_word(dev, dev->pm_cap + PCI_PM_CTRL, &pmcsr); dev->current_state = (pmcsr & PCI_PM_CTRL_STATE_MASK); if (dev->current_state != state) - pci_info_ratelimited(dev, "Refused to change power state, currently in D%d\n", - dev->current_state); + pci_info_ratelimited(dev, "refused to change power state from %s to %s\n", + pci_power_name(dev->current_state), + pci_power_name(state)); /* * According to section 5.4.1 of the "PCI BUS POWER MANAGEMENT @@ -966,24 +976,11 @@ void pci_refresh_power_state(struct pci_dev *dev) } /** - * pci_power_up - Put the given device into D0 forcibly - * @dev: PCI device to power up - */ -void pci_power_up(struct pci_dev *dev) -{ - if (platform_pci_power_manageable(dev)) - platform_pci_set_power_state(dev, PCI_D0); - - pci_raw_set_power_state(dev, PCI_D0); - pci_update_current_state(dev, PCI_D0); -} - -/** * pci_platform_power_transition - Use platform to change device power state * @dev: PCI device to handle. * @state: State to put the device into. */ -static int pci_platform_power_transition(struct pci_dev *dev, pci_power_t state) +int pci_platform_power_transition(struct pci_dev *dev, pci_power_t state) { int error; @@ -999,6 +996,7 @@ static int pci_platform_power_transition(struct pci_dev *dev, pci_power_t state) return error; } +EXPORT_SYMBOL_GPL(pci_platform_power_transition); /** * pci_wakeup - Wake up a PCI device @@ -1022,34 +1020,70 @@ void pci_wakeup_bus(struct pci_bus *bus) pci_walk_bus(bus, pci_wakeup, NULL); } +static int pci_dev_wait(struct pci_dev *dev, char *reset_type, int timeout) +{ + int delay = 1; + u32 id; + + /* + * After reset, the device should not silently discard config + * requests, but it may still indicate that it needs more time by + * responding to them with CRS completions. The Root Port will + * generally synthesize ~0 data to complete the read (except when + * CRS SV is enabled and the read was for the Vendor ID; in that + * case it synthesizes 0x0001 data). + * + * Wait for the device to return a non-CRS completion. Read the + * Command register instead of Vendor ID so we don't have to + * contend with the CRS SV value. + */ + pci_read_config_dword(dev, PCI_COMMAND, &id); + while (id == ~0) { + if (delay > timeout) { + pci_warn(dev, "not ready %dms after %s; giving up\n", + delay - 1, reset_type); + return -ENOTTY; + } + + if (delay > 1000) + pci_info(dev, "not ready %dms after %s; waiting\n", + delay - 1, reset_type); + + msleep(delay); + delay *= 2; + pci_read_config_dword(dev, PCI_COMMAND, &id); + } + + if (delay > 1000) + pci_info(dev, "ready %dms after %s\n", delay - 1, + reset_type); + + return 0; +} + /** - * __pci_start_power_transition - Start power transition of a PCI device - * @dev: PCI device to handle. - * @state: State to put the device into. + * pci_power_up - Put the given device into D0 + * @dev: PCI device to power up */ -static void __pci_start_power_transition(struct pci_dev *dev, pci_power_t state) +int pci_power_up(struct pci_dev *dev) { - if (state == PCI_D0) { - pci_platform_power_transition(dev, PCI_D0); + pci_platform_power_transition(dev, PCI_D0); + + /* + * Mandatory power management transition delays are handled in + * pci_pm_resume_noirq() and pci_pm_runtime_resume() of the + * corresponding bridge. + */ + if (dev->runtime_d3cold) { /* - * 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. + * When powering on a bridge from D3cold, the whole hierarchy + * may be powered on into D0uninitialized state, resume them to + * give them a chance to suspend again */ - 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 - * D0uninitialized state, resume them to give - * them a chance to suspend again - */ - pci_wakeup_bus(dev->subordinate); - } + pci_wakeup_bus(dev->subordinate); } + + return pci_raw_set_power_state(dev, PCI_D0); } /** @@ -1077,27 +1111,6 @@ void pci_bus_set_current_state(struct pci_bus *bus, pci_power_t state) } /** - * __pci_complete_power_transition - Complete power transition of a PCI device - * @dev: PCI device to handle. - * @state: State to put the device into. - * - * This function should not be called directly by device drivers. - */ -int __pci_complete_power_transition(struct pci_dev *dev, pci_power_t state) -{ - int ret; - - if (state <= PCI_D0) - return -EINVAL; - ret = pci_platform_power_transition(dev, state); - /* Power off the bridge may power off the whole hierarchy */ - if (!ret && state == PCI_D3cold) - pci_bus_set_current_state(dev->subordinate, PCI_D3cold); - return ret; -} -EXPORT_SYMBOL_GPL(__pci_complete_power_transition); - -/** * pci_set_power_state - Set the power state of a PCI device * @dev: PCI device to handle. * @state: PCI power state (D0, D1, D2, D3hot) to put the device into. @@ -1137,7 +1150,8 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state) if (dev->current_state == state) return 0; - __pci_start_power_transition(dev, state); + if (state == PCI_D0) + return pci_power_up(dev); /* * This device is quirked not to be put into D3, so don't put it in @@ -1153,10 +1167,14 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state) error = pci_raw_set_power_state(dev, state > PCI_D3hot ? PCI_D3hot : state); - if (!__pci_complete_power_transition(dev, state)) - error = 0; + if (pci_platform_power_transition(dev, state)) + return error; - return error; + /* Powering off a bridge may power off the whole hierarchy */ + if (state == PCI_D3cold) + pci_bus_set_current_state(dev->subordinate, PCI_D3cold); + + return 0; } EXPORT_SYMBOL(pci_set_power_state); @@ -1368,6 +1386,7 @@ int pci_save_state(struct pci_dev *dev) pci_save_ltr_state(dev); pci_save_dpc_state(dev); + pci_save_aer_state(dev); return pci_save_vc_state(dev); } EXPORT_SYMBOL(pci_save_state); @@ -1481,6 +1500,7 @@ void pci_restore_state(struct pci_dev *dev) pci_restore_dpc_state(dev); pci_cleanup_aer_error_status_regs(dev); + pci_restore_aer_state(dev); pci_restore_config_space(dev); @@ -4438,47 +4458,6 @@ int pci_wait_for_pending_transaction(struct pci_dev *dev) } EXPORT_SYMBOL(pci_wait_for_pending_transaction); -static int pci_dev_wait(struct pci_dev *dev, char *reset_type, int timeout) -{ - int delay = 1; - u32 id; - - /* - * After reset, the device should not silently discard config - * requests, but it may still indicate that it needs more time by - * responding to them with CRS completions. The Root Port will - * generally synthesize ~0 data to complete the read (except when - * CRS SV is enabled and the read was for the Vendor ID; in that - * case it synthesizes 0x0001 data). - * - * Wait for the device to return a non-CRS completion. Read the - * Command register instead of Vendor ID so we don't have to - * contend with the CRS SV value. - */ - pci_read_config_dword(dev, PCI_COMMAND, &id); - while (id == ~0) { - if (delay > timeout) { - pci_warn(dev, "not ready %dms after %s; giving up\n", - delay - 1, reset_type); - return -ENOTTY; - } - - if (delay > 1000) - pci_info(dev, "not ready %dms after %s; waiting\n", - delay - 1, reset_type); - - msleep(delay); - delay *= 2; - pci_read_config_dword(dev, PCI_COMMAND, &id); - } - - if (delay > 1000) - pci_info(dev, "ready %dms after %s\n", delay - 1, - reset_type); - - return 0; -} - /** * pcie_has_flr - check if a device supports function level resets * @dev: device to check @@ -4613,16 +4592,19 @@ static int pci_pm_reset(struct pci_dev *dev, int probe) pci_write_config_word(dev, dev->pm_cap + PCI_PM_CTRL, csr); pci_dev_d3_sleep(dev); - return pci_dev_wait(dev, "PM D3->D0", PCIE_RESET_READY_POLL_MS); + return pci_dev_wait(dev, "PM D3hot->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) +static bool pcie_wait_for_link_delay(struct pci_dev *pdev, bool active, + int delay) { int timeout = 1000; bool ret; @@ -4659,13 +4641,144 @@ 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); +} + +/* + * Find maximum D3cold delay required by all the devices on the bus. The + * spec says 100 ms, but firmware can lower it and we allow drivers to + * increase it as well. + * + * Called with @pci_bus_sem locked for reading. + */ +static int pci_bus_max_d3cold_delay(const struct pci_bus *bus) +{ + const struct pci_dev *pdev; + int min_delay = 100; + int max_delay = 0; + + list_for_each_entry(pdev, &bus->devices, bus_list) { + 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); +} + +/** + * pci_bridge_wait_for_secondary_bus - Wait for secondary bus to be accessible + * @dev: PCI bridge + * + * Handle necessary delays before access to the devices on the secondary + * side of the bridge are permitted after D3cold to D0 transition. + * + * For PCIe this means the delays in PCIe 5.0 section 6.6.1. For + * conventional PCI it means Tpvrh + Trhfa specified in PCI 3.0 section + * 4.3.2. + */ +void pci_bridge_wait_for_secondary_bus(struct pci_dev *dev) +{ + struct pci_dev *child; + int delay; + + if (pci_dev_is_disconnected(dev)) + return; + + if (!pci_is_bridge(dev) || !dev->bridge_d3) + return; + + down_read(&pci_bus_sem); + + /* + * We only deal with devices that are present currently on the bus. + * For any hot-added devices the access delay is handled in pciehp + * board_added(). In case of ACPI hotplug the firmware is expected + * to configure the devices before OS is notified. + */ + if (!dev->subordinate || list_empty(&dev->subordinate->devices)) { + up_read(&pci_bus_sem); + return; + } + + /* Take d3cold_delay requirements into account */ + delay = pci_bus_max_d3cold_delay(dev->subordinate); + if (!delay) { + up_read(&pci_bus_sem); + return; + } + + child = list_first_entry(&dev->subordinate->devices, struct pci_dev, + bus_list); + up_read(&pci_bus_sem); + + /* + * Conventional PCI and PCI-X we need to wait Tpvrh + Trhfa before + * accessing the device after reset (that is 1000 ms + 100 ms). In + * practice this should not be needed because we don't do power + * management for them (see pci_bridge_d3_possible()). + */ + if (!pci_is_pcie(dev)) { + pci_dbg(dev, "waiting %d ms for secondary bus\n", 1000 + delay); + msleep(1000 + delay); + return; + } + + /* + * For PCIe downstream and root ports that do not support speeds + * greater than 5 GT/s need to wait minimum 100 ms. For higher + * speeds (gen3) we need to wait first for the data link layer to + * become active. + * + * However, 100 ms is the minimum and the PCIe spec says the + * software must allow at least 1s before it can determine that the + * device that did not respond is a broken device. There is + * evidence that 100 ms is not always enough, for example certain + * Titan Ridge xHCI controller does not always respond to + * configuration requests if we only wait for 100 ms (see + * https://bugzilla.kernel.org/show_bug.cgi?id=203885). + * + * Therefore we wait for 100 ms and check for the device presence. + * If it is still not present give it an additional 100 ms. + */ + if (!pcie_downstream_port(dev)) + return; + + if (pcie_get_speed_cap(dev) <= PCIE_SPEED_5_0GT) { + pci_dbg(dev, "waiting %d ms for downstream link\n", delay); + msleep(delay); + } else { + pci_dbg(dev, "waiting %d ms for downstream link, after activation\n", + delay); + if (!pcie_wait_for_link_delay(dev, true, delay)) { + /* Did not train, no need to wait any further */ + return; + } + } + + if (!pci_device_is_present(child)) { + pci_dbg(child, "waiting additional %d ms to become accessible\n", delay); + msleep(delay); + } +} + void pci_reset_secondary_bus(struct pci_dev *dev) { u16 ctrl; diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 9faa55a151cb..e16fdbd6f2c3 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -12,6 +12,7 @@ extern const unsigned char pcie_link_speed[]; extern bool pci_early_dump; bool pcie_cap_has_lnkctl(const struct pci_dev *dev); +bool pcie_cap_has_rtctl(const struct pci_dev *dev); /* Functions internal to the PCI core code */ @@ -85,7 +86,7 @@ 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); +int 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); @@ -104,6 +105,7 @@ void pci_allocate_cap_save_buffers(struct pci_dev *dev); void pci_free_cap_save_buffers(struct pci_dev *dev); bool pci_bridge_d3_possible(struct pci_dev *dev); void pci_bridge_d3_update(struct pci_dev *dev); +void pci_bridge_wait_for_secondary_bus(struct pci_dev *dev); static inline void pci_wakeup_event(struct pci_dev *dev) { @@ -542,14 +544,6 @@ static inline void pcie_aspm_pm_state_change(struct pci_dev *pdev) { } static inline void pcie_aspm_powersave_config_link(struct pci_dev *pdev) { } #endif -#ifdef CONFIG_PCIEASPM_DEBUG -void pcie_aspm_create_sysfs_dev_files(struct pci_dev *pdev); -void pcie_aspm_remove_sysfs_dev_files(struct pci_dev *pdev); -#else -static inline void pcie_aspm_create_sysfs_dev_files(struct pci_dev *pdev) { } -static inline void pcie_aspm_remove_sysfs_dev_files(struct pci_dev *pdev) { } -#endif - #ifdef CONFIG_PCIE_ECRC void pcie_set_ecrc_checking(struct pci_dev *dev); void pcie_ecrc_get_policy(char *str); @@ -668,4 +662,8 @@ static inline int pci_acpi_program_hp_params(struct pci_dev *dev) } #endif +#ifdef CONFIG_PCIEASPM +extern const struct attribute_group aspm_ctrl_attr_group; +#endif + #endif /* DRIVERS_PCI_H */ diff --git a/drivers/pci/pcie/Kconfig b/drivers/pci/pcie/Kconfig index 362eb8cfa53b..6e3c04b46fb1 100644 --- a/drivers/pci/pcie/Kconfig +++ b/drivers/pci/pcie/Kconfig @@ -4,7 +4,6 @@ # config PCIEPORTBUS bool "PCI Express Port Bus support" - depends on PCI help This enables PCI Express Port Bus support. Users can then enable support for Native Hot-Plug, Advanced Error Reporting, Power @@ -63,7 +62,6 @@ config PCIE_ECRC # config PCIEASPM bool "PCI Express ASPM control" if EXPERT - depends on PCI && PCIEPORTBUS default y help This enables OS control over PCI Express ASPM (Active State @@ -79,13 +77,6 @@ config PCIEASPM When in doubt, say Y. -config PCIEASPM_DEBUG - bool "Debug PCI Express ASPM" - depends on PCIEASPM - help - This enables PCI Express ASPM debug support. It will add per-device - interface to control ASPM. - choice prompt "Default ASPM policy" default PCIEASPM_DEFAULT @@ -135,7 +126,6 @@ config PCIE_DPC config PCIE_PTM bool "PCI Express Precision Time Measurement support" - depends on PCIEPORTBUS help This enables PCI Express Precision Time Measurement (PTM) support. diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c index b45bc47d04fe..1ca86f2e0166 100644 --- a/drivers/pci/pcie/aer.c +++ b/drivers/pci/pcie/aer.c @@ -15,6 +15,7 @@ #define pr_fmt(fmt) "AER: " fmt #define dev_fmt pr_fmt +#include <linux/bitops.h> #include <linux/cper.h> #include <linux/pci.h> #include <linux/pci-acpi.h> @@ -36,7 +37,7 @@ #define AER_ERROR_SOURCES_MAX 128 #define AER_MAX_TYPEOF_COR_ERRS 16 /* as per PCI_ERR_COR_STATUS */ -#define AER_MAX_TYPEOF_UNCOR_ERRS 26 /* as per PCI_ERR_UNCOR_STATUS*/ +#define AER_MAX_TYPEOF_UNCOR_ERRS 27 /* as per PCI_ERR_UNCOR_STATUS*/ struct aer_err_source { unsigned int status; @@ -201,6 +202,7 @@ void pcie_set_ecrc_checking(struct pci_dev *dev) /** * pcie_ecrc_get_policy - parse kernel command-line ecrc option + * @str: ECRC policy from kernel command line to use */ void pcie_ecrc_get_policy(char *str) { @@ -448,12 +450,70 @@ int pci_cleanup_aer_error_status_regs(struct pci_dev *dev) return 0; } +void pci_save_aer_state(struct pci_dev *dev) +{ + struct pci_cap_saved_state *save_state; + u32 *cap; + int pos; + + pos = dev->aer_cap; + if (!pos) + return; + + save_state = pci_find_saved_ext_cap(dev, PCI_EXT_CAP_ID_ERR); + if (!save_state) + return; + + cap = &save_state->cap.data[0]; + pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_MASK, cap++); + pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, cap++); + pci_read_config_dword(dev, pos + PCI_ERR_COR_MASK, cap++); + pci_read_config_dword(dev, pos + PCI_ERR_CAP, cap++); + if (pcie_cap_has_rtctl(dev)) + pci_read_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, cap++); +} + +void pci_restore_aer_state(struct pci_dev *dev) +{ + struct pci_cap_saved_state *save_state; + u32 *cap; + int pos; + + pos = dev->aer_cap; + if (!pos) + return; + + save_state = pci_find_saved_ext_cap(dev, PCI_EXT_CAP_ID_ERR); + if (!save_state) + return; + + cap = &save_state->cap.data[0]; + pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_MASK, *cap++); + pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, *cap++); + pci_write_config_dword(dev, pos + PCI_ERR_COR_MASK, *cap++); + pci_write_config_dword(dev, pos + PCI_ERR_CAP, *cap++); + if (pcie_cap_has_rtctl(dev)) + pci_write_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, *cap++); +} + void pci_aer_init(struct pci_dev *dev) { + int n; + dev->aer_cap = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR); + if (!dev->aer_cap) + return; - if (dev->aer_cap) - dev->aer_stats = kzalloc(sizeof(struct aer_stats), GFP_KERNEL); + dev->aer_stats = kzalloc(sizeof(struct aer_stats), GFP_KERNEL); + + /* + * We save/restore PCI_ERR_UNCOR_MASK, PCI_ERR_UNCOR_SEVER, + * PCI_ERR_COR_MASK, and PCI_ERR_CAP. Root and Root Complex Event + * Collectors also implement PCI_ERR_ROOT_COMMAND (PCIe r5.0, sec + * 7.8.4). + */ + n = pcie_cap_has_rtctl(dev) ? 5 : 4; + pci_add_ext_cap_save_buffer(dev, PCI_EXT_CAP_ID_ERR, sizeof(u32) * n); pci_cleanup_aer_error_status_regs(dev); } @@ -560,6 +620,7 @@ static const char *aer_uncorrectable_error_string[AER_MAX_TYPEOF_UNCOR_ERRS] = { "BlockedTLP", /* Bit Position 23 */ "AtomicOpBlocked", /* Bit Position 24 */ "TLPBlockedErr", /* Bit Position 25 */ + "PoisonTLPBlocked", /* Bit Position 26 */ }; static const char *aer_agent_string[] = { @@ -657,7 +718,8 @@ const struct attribute_group aer_stats_attr_group = { static void pci_dev_aer_stats_incr(struct pci_dev *pdev, struct aer_err_info *info) { - int status, i, max = -1; + unsigned long status = info->status & ~info->mask; + int i, max = -1; u64 *counter = NULL; struct aer_stats *aer_stats = pdev->aer_stats; @@ -682,10 +744,8 @@ static void pci_dev_aer_stats_incr(struct pci_dev *pdev, break; } - status = (info->status & ~info->mask); - for (i = 0; i < max; i++) - if (status & (1 << i)) - counter[i]++; + for_each_set_bit(i, &status, max) + counter[i]++; } static void pci_rootport_aer_stats_incr(struct pci_dev *pdev, @@ -717,14 +777,11 @@ static void __print_tlp_header(struct pci_dev *dev, static void __aer_print_error(struct pci_dev *dev, struct aer_err_info *info) { - int i, status; + unsigned long status = info->status & ~info->mask; const char *errmsg = NULL; - status = (info->status & ~info->mask); - - for (i = 0; i < 32; i++) { - if (!(status & (1 << i))) - continue; + int i; + for_each_set_bit(i, &status, 32) { if (info->severity == AER_CORRECTABLE) errmsg = i < ARRAY_SIZE(aer_correctable_error_string) ? aer_correctable_error_string[i] : NULL; @@ -1204,7 +1261,8 @@ static void aer_isr_one_error(struct aer_rpc *rpc, /** * aer_isr - consume errors detected by root port - * @work: definition of this work item + * @irq: IRQ assigned to Root Port + * @context: pointer to Root Port data structure * * Invoked, as DPC, when root port records new detected error */ diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index 652ef23bba35..0dcd44308228 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -64,6 +64,7 @@ struct pcie_link_state { u32 clkpm_capable:1; /* Clock PM capable? */ u32 clkpm_enabled:1; /* Current Clock PM state */ u32 clkpm_default:1; /* Default Clock PM state by BIOS */ + u32 clkpm_disable:1; /* Clock PM disabled */ /* Exit latencies */ struct aspm_latency latency_up; /* Upstream direction exit latency */ @@ -161,8 +162,11 @@ static void pcie_set_clkpm_nocheck(struct pcie_link_state *link, int enable) static void pcie_set_clkpm(struct pcie_link_state *link, int enable) { - /* Don't enable Clock PM if the link is not Clock PM capable */ - if (!link->clkpm_capable) + /* + * Don't enable Clock PM if the link is not Clock PM capable + * or Clock PM is disabled + */ + if (!link->clkpm_capable || link->clkpm_disable) enable = 0; /* Need nothing if the specified equals to current state */ if (link->clkpm_enabled == enable) @@ -192,7 +196,8 @@ static void pcie_clkpm_cap_init(struct pcie_link_state *link, int blacklist) } link->clkpm_enabled = enabled; link->clkpm_default = enabled; - link->clkpm_capable = (blacklist) ? 0 : capable; + link->clkpm_capable = capable; + link->clkpm_disable = blacklist ? 1 : 0; } static bool pcie_retrain_link(struct pcie_link_state *link) @@ -894,6 +899,14 @@ static struct pcie_link_state *alloc_pcie_link_state(struct pci_dev *pdev) return link; } +static void pcie_aspm_update_sysfs_visibility(struct pci_dev *pdev) +{ + struct pci_dev *child; + + list_for_each_entry(child, &pdev->subordinate->devices, bus_list) + sysfs_update_group(&child->dev.kobj, &aspm_ctrl_attr_group); +} + /* * pcie_aspm_init_link_state: Initiate PCI express link state. * It is called after the pcie and its children devices are scanned. @@ -955,6 +968,8 @@ void pcie_aspm_init_link_state(struct pci_dev *pdev) pcie_set_clkpm(link, policy_to_clkpm_state(link)); } + pcie_aspm_update_sysfs_visibility(pdev); + unlock: mutex_unlock(&aspm_lock); out: @@ -1061,19 +1076,26 @@ void pcie_aspm_powersave_config_link(struct pci_dev *pdev) up_read(&pci_bus_sem); } -static int __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem) +static struct pcie_link_state *pcie_aspm_get_link(struct pci_dev *pdev) { - struct pci_dev *parent = pdev->bus->self; - struct pcie_link_state *link; + struct pci_dev *bridge; if (!pci_is_pcie(pdev)) - return 0; + return NULL; - if (pcie_downstream_port(pdev)) - parent = pdev; - if (!parent || !parent->link_state) - return -EINVAL; + bridge = pci_upstream_bridge(pdev); + if (!bridge || !pci_is_pcie(bridge)) + return NULL; + return bridge->link_state; +} + +static int __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem) +{ + struct pcie_link_state *link = pcie_aspm_get_link(pdev); + + if (!link) + return -EINVAL; /* * A driver requested that ASPM be disabled on this device, but * if we don't have permission to manage ASPM (e.g., on ACPI @@ -1090,17 +1112,24 @@ static int __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem) if (sem) down_read(&pci_bus_sem); mutex_lock(&aspm_lock); - link = parent->link_state; if (state & PCIE_LINK_STATE_L0S) link->aspm_disable |= ASPM_STATE_L0S; if (state & PCIE_LINK_STATE_L1) - link->aspm_disable |= ASPM_STATE_L1; + /* L1 PM substates require L1 */ + link->aspm_disable |= ASPM_STATE_L1 | ASPM_STATE_L1SS; + if (state & PCIE_LINK_STATE_L1_1) + link->aspm_disable |= ASPM_STATE_L1_1; + if (state & PCIE_LINK_STATE_L1_2) + link->aspm_disable |= ASPM_STATE_L1_2; + if (state & PCIE_LINK_STATE_L1_1_PCIPM) + link->aspm_disable |= ASPM_STATE_L1_1_PCIPM; + if (state & PCIE_LINK_STATE_L1_2_PCIPM) + link->aspm_disable |= ASPM_STATE_L1_2_PCIPM; pcie_config_aspm_link(link, policy_to_aspm_state(link)); - if (state & PCIE_LINK_STATE_CLKPM) { - link->clkpm_capable = 0; - pcie_set_clkpm(link, 0); - } + if (state & PCIE_LINK_STATE_CLKPM) + link->clkpm_disable = 1; + pcie_set_clkpm(link, policy_to_clkpm_state(link)); mutex_unlock(&aspm_lock); if (sem) up_read(&pci_bus_sem); @@ -1172,127 +1201,161 @@ module_param_call(policy, pcie_aspm_set_policy, pcie_aspm_get_policy, /** * pcie_aspm_enabled - Check if PCIe ASPM has been enabled for a device. * @pdev: Target device. + * + * Relies on the upstream bridge's link_state being valid. The link_state + * is deallocated only when the last child of the bridge (i.e., @pdev or a + * sibling) is removed, and the caller should be holding a reference to + * @pdev, so this should be safe. */ bool pcie_aspm_enabled(struct pci_dev *pdev) { - struct pci_dev *bridge = pci_upstream_bridge(pdev); - bool ret; + struct pcie_link_state *link = pcie_aspm_get_link(pdev); - if (!bridge) + if (!link) return false; - mutex_lock(&aspm_lock); - ret = bridge->link_state ? !!bridge->link_state->aspm_enabled : false; - mutex_unlock(&aspm_lock); - - return ret; + return link->aspm_enabled; } EXPORT_SYMBOL_GPL(pcie_aspm_enabled); -#ifdef CONFIG_PCIEASPM_DEBUG -static ssize_t link_state_show(struct device *dev, - struct device_attribute *attr, - char *buf) +static ssize_t aspm_attr_show_common(struct device *dev, + struct device_attribute *attr, + char *buf, u8 state) { - struct pci_dev *pci_device = to_pci_dev(dev); - struct pcie_link_state *link_state = pci_device->link_state; + struct pci_dev *pdev = to_pci_dev(dev); + struct pcie_link_state *link = pcie_aspm_get_link(pdev); - return sprintf(buf, "%d\n", link_state->aspm_enabled); + return sprintf(buf, "%d\n", (link->aspm_enabled & state) ? 1 : 0); } -static ssize_t link_state_store(struct device *dev, - struct device_attribute *attr, - const char *buf, - size_t n) +static ssize_t aspm_attr_store_common(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len, u8 state) { struct pci_dev *pdev = to_pci_dev(dev); - struct pcie_link_state *link, *root = pdev->link_state->root; - u32 state; - - if (aspm_disabled) - return -EPERM; + struct pcie_link_state *link = pcie_aspm_get_link(pdev); + bool state_enable; - if (kstrtouint(buf, 10, &state)) - return -EINVAL; - if ((state & ~ASPM_STATE_ALL) != 0) + if (strtobool(buf, &state_enable) < 0) return -EINVAL; down_read(&pci_bus_sem); mutex_lock(&aspm_lock); - list_for_each_entry(link, &link_list, sibling) { - if (link->root != root) - continue; - pcie_config_aspm_link(link, state); + + if (state_enable) { + link->aspm_disable &= ~state; + /* need to enable L1 for substates */ + if (state & ASPM_STATE_L1SS) + link->aspm_disable &= ~ASPM_STATE_L1; + } else { + link->aspm_disable |= state; } + + pcie_config_aspm_link(link, policy_to_aspm_state(link)); + mutex_unlock(&aspm_lock); up_read(&pci_bus_sem); - return n; + + return len; } -static ssize_t clk_ctl_show(struct device *dev, - struct device_attribute *attr, - char *buf) +#define ASPM_ATTR(_f, _s) \ +static ssize_t _f##_show(struct device *dev, \ + struct device_attribute *attr, char *buf) \ +{ return aspm_attr_show_common(dev, attr, buf, ASPM_STATE_##_s); } \ + \ +static ssize_t _f##_store(struct device *dev, \ + struct device_attribute *attr, \ + const char *buf, size_t len) \ +{ return aspm_attr_store_common(dev, attr, buf, len, ASPM_STATE_##_s); } + +ASPM_ATTR(l0s_aspm, L0S) +ASPM_ATTR(l1_aspm, L1) +ASPM_ATTR(l1_1_aspm, L1_1) +ASPM_ATTR(l1_2_aspm, L1_2) +ASPM_ATTR(l1_1_pcipm, L1_1_PCIPM) +ASPM_ATTR(l1_2_pcipm, L1_2_PCIPM) + +static ssize_t clkpm_show(struct device *dev, + struct device_attribute *attr, char *buf) { - struct pci_dev *pci_device = to_pci_dev(dev); - struct pcie_link_state *link_state = pci_device->link_state; + struct pci_dev *pdev = to_pci_dev(dev); + struct pcie_link_state *link = pcie_aspm_get_link(pdev); - return sprintf(buf, "%d\n", link_state->clkpm_enabled); + return sprintf(buf, "%d\n", link->clkpm_enabled); } -static ssize_t clk_ctl_store(struct device *dev, - struct device_attribute *attr, - const char *buf, - size_t n) +static ssize_t clkpm_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len) { struct pci_dev *pdev = to_pci_dev(dev); - bool state; + struct pcie_link_state *link = pcie_aspm_get_link(pdev); + bool state_enable; - if (strtobool(buf, &state)) + if (strtobool(buf, &state_enable) < 0) return -EINVAL; down_read(&pci_bus_sem); mutex_lock(&aspm_lock); - pcie_set_clkpm_nocheck(pdev->link_state, state); + + link->clkpm_disable = !state_enable; + pcie_set_clkpm(link, policy_to_clkpm_state(link)); + mutex_unlock(&aspm_lock); up_read(&pci_bus_sem); - return n; + return len; } -static DEVICE_ATTR_RW(link_state); -static DEVICE_ATTR_RW(clk_ctl); +static DEVICE_ATTR_RW(clkpm); +static DEVICE_ATTR_RW(l0s_aspm); +static DEVICE_ATTR_RW(l1_aspm); +static DEVICE_ATTR_RW(l1_1_aspm); +static DEVICE_ATTR_RW(l1_2_aspm); +static DEVICE_ATTR_RW(l1_1_pcipm); +static DEVICE_ATTR_RW(l1_2_pcipm); + +static struct attribute *aspm_ctrl_attrs[] = { + &dev_attr_clkpm.attr, + &dev_attr_l0s_aspm.attr, + &dev_attr_l1_aspm.attr, + &dev_attr_l1_1_aspm.attr, + &dev_attr_l1_2_aspm.attr, + &dev_attr_l1_1_pcipm.attr, + &dev_attr_l1_2_pcipm.attr, + NULL +}; -static char power_group[] = "power"; -void pcie_aspm_create_sysfs_dev_files(struct pci_dev *pdev) +static umode_t aspm_ctrl_attrs_are_visible(struct kobject *kobj, + struct attribute *a, int n) { - struct pcie_link_state *link_state = pdev->link_state; - - if (!link_state) - return; - - if (link_state->aspm_support) - sysfs_add_file_to_group(&pdev->dev.kobj, - &dev_attr_link_state.attr, power_group); - if (link_state->clkpm_capable) - sysfs_add_file_to_group(&pdev->dev.kobj, - &dev_attr_clk_ctl.attr, power_group); -} + struct device *dev = kobj_to_dev(kobj); + struct pci_dev *pdev = to_pci_dev(dev); + struct pcie_link_state *link = pcie_aspm_get_link(pdev); + static const u8 aspm_state_map[] = { + ASPM_STATE_L0S, + ASPM_STATE_L1, + ASPM_STATE_L1_1, + ASPM_STATE_L1_2, + ASPM_STATE_L1_1_PCIPM, + ASPM_STATE_L1_2_PCIPM, + }; -void pcie_aspm_remove_sysfs_dev_files(struct pci_dev *pdev) -{ - struct pcie_link_state *link_state = pdev->link_state; + if (aspm_disabled || !link) + return 0; - if (!link_state) - return; + if (n == 0) + return link->clkpm_capable ? a->mode : 0; - if (link_state->aspm_support) - sysfs_remove_file_from_group(&pdev->dev.kobj, - &dev_attr_link_state.attr, power_group); - if (link_state->clkpm_capable) - sysfs_remove_file_from_group(&pdev->dev.kobj, - &dev_attr_clk_ctl.attr, power_group); + return link->aspm_capable & aspm_state_map[n - 1] ? a->mode : 0; } -#endif + +const struct attribute_group aspm_ctrl_attr_group = { + .name = "link", + .attrs = aspm_ctrl_attrs, + .is_visible = aspm_ctrl_attrs_are_visible, +}; static int __init pcie_aspm_disable(char *str) { diff --git a/drivers/pci/pcie/dpc.c b/drivers/pci/pcie/dpc.c index a32ec3487a8d..e06f42f58d3d 100644 --- a/drivers/pci/pcie/dpc.c +++ b/drivers/pci/pcie/dpc.c @@ -291,7 +291,7 @@ static int dpc_probe(struct pcie_device *dev) int status; u16 ctl, cap; - if (pcie_aer_get_firmware_first(pdev)) + if (pcie_aer_get_firmware_first(pdev) && !pcie_ports_dpc_native) return -ENOTSUPP; dpc = devm_kzalloc(device, sizeof(*dpc), GFP_KERNEL); diff --git a/drivers/pci/pcie/portdrv.h b/drivers/pci/pcie/portdrv.h index 944827a8c7d3..1e673619b101 100644 --- a/drivers/pci/pcie/portdrv.h +++ b/drivers/pci/pcie/portdrv.h @@ -25,6 +25,8 @@ #define PCIE_PORT_DEVICE_MAXSERVICES 5 +extern bool pcie_ports_dpc_native; + #ifdef CONFIG_PCIEAER int pcie_aer_init(void); #else diff --git a/drivers/pci/pcie/portdrv_core.c b/drivers/pci/pcie/portdrv_core.c index 1b330129089f..5075cb9e850c 100644 --- a/drivers/pci/pcie/portdrv_core.c +++ b/drivers/pci/pcie/portdrv_core.c @@ -250,8 +250,13 @@ static int get_port_device_capability(struct pci_dev *dev) pcie_pme_interrupt_enable(dev, false); } + /* + * With dpc-native, allow Linux to use DPC even if it doesn't have + * permission to use AER. + */ if (pci_find_ext_capability(dev, PCI_EXT_CAP_ID_DPC) && - pci_aer_available() && services & PCIE_PORT_SERVICE_AER) + pci_aer_available() && + (pcie_ports_dpc_native || (services & PCIE_PORT_SERVICE_AER))) services |= PCIE_PORT_SERVICE_DPC; if (pci_pcie_type(dev) == PCI_EXP_TYPE_DOWNSTREAM || diff --git a/drivers/pci/pcie/portdrv_pci.c b/drivers/pci/pcie/portdrv_pci.c index 0a87091a0800..160d67c59310 100644 --- a/drivers/pci/pcie/portdrv_pci.c +++ b/drivers/pci/pcie/portdrv_pci.c @@ -29,12 +29,20 @@ bool pcie_ports_disabled; */ bool pcie_ports_native; +/* + * If the user specified "pcie_ports=dpc-native", use the Linux DPC PCIe + * service even if the platform hasn't given us permission. + */ +bool pcie_ports_dpc_native; + static int __init pcie_port_setup(char *str) { if (!strncmp(str, "compat", 6)) pcie_ports_disabled = true; else if (!strncmp(str, "native", 6)) pcie_ports_native = true; + else if (!strncmp(str, "dpc-native", 10)) + pcie_ports_dpc_native = true; return 1; } diff --git a/drivers/pci/pcie/ptm.c b/drivers/pci/pcie/ptm.c index 98cfa30f3fae..9361f3aa26ab 100644 --- a/drivers/pci/pcie/ptm.c +++ b/drivers/pci/pcie/ptm.c @@ -21,7 +21,7 @@ static void pci_ptm_info(struct pci_dev *dev) snprintf(clock_desc, sizeof(clock_desc), ">254ns"); break; default: - snprintf(clock_desc, sizeof(clock_desc), "%udns", + snprintf(clock_desc, sizeof(clock_desc), "%uns", dev->ptm_granularity); break; } diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index d3033873395d..54a53e260391 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -7,6 +7,7 @@ #include <linux/delay.h> #include <linux/init.h> #include <linux/pci.h> +#include <linux/msi.h> #include <linux/of_device.h> #include <linux/of_pci.h> #include <linux/pci_hotplug.h> @@ -898,6 +899,9 @@ static int pci_register_host_bridge(struct pci_host_bridge *bridge) else pr_info("PCI host bridge to bus %s\n", name); + if (nr_node_ids > 1 && pcibus_to_node(bus) == NUMA_NO_NODE) + dev_warn(&bus->dev, "Unknown NUMA node; performance will be reduced\n"); + /* Add initial resources to the bus */ resource_list_for_each_entry_safe(window, n, &resources) { list_move_tail(&window->node, &bridge->windows); |