diff options
Diffstat (limited to 'drivers/pci/pci.c')
| -rw-r--r-- | drivers/pci/pci.c | 1293 |
1 files changed, 487 insertions, 806 deletions
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index c3585229c12a..869d204a70a3 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -23,8 +23,6 @@ #include <linux/string.h> #include <linux/log2.h> #include <linux/logic_pio.h> -#include <linux/pm_wakeup.h> -#include <linux/interrupt.h> #include <linux/device.h> #include <linux/pm_runtime.h> #include <linux/pci_hotplug.h> @@ -143,8 +141,8 @@ enum pcie_bus_config_types pcie_bus_config = PCIE_BUS_DEFAULT; * the dfl or actual value as it sees fit. Don't forget this is * measured in 32-bit words, not bytes. */ -u8 pci_dfl_cache_line_size = L1_CACHE_BYTES >> 2; -u8 pci_cache_line_size; +u8 pci_dfl_cache_line_size __ro_after_init = L1_CACHE_BYTES >> 2; +u8 pci_cache_line_size __ro_after_init ; /* * If we set up a device for bus mastering, we need to check the latency @@ -947,30 +945,67 @@ void pci_request_acs(void) } static const char *disable_acs_redir_param; +static const char *config_acs_param; -/** - * pci_disable_acs_redir - disable ACS redirect capabilities - * @dev: the PCI device - * - * For only devices specified in the disable_acs_redir parameter. - */ -static void pci_disable_acs_redir(struct pci_dev *dev) +struct pci_acs { + u16 cap; + u16 ctrl; + u16 fw_ctrl; +}; + +static void __pci_config_acs(struct pci_dev *dev, struct pci_acs *caps, + const char *p, u16 mask, u16 flags) { + char *delimit; int ret = 0; - const char *p; - int pos; - u16 ctrl; - if (!disable_acs_redir_param) + if (!p) return; - p = disable_acs_redir_param; while (*p) { + if (!mask) { + /* Check for ACS flags */ + delimit = strstr(p, "@"); + if (delimit) { + int end; + u32 shift = 0; + + end = delimit - p - 1; + + while (end > -1) { + if (*(p + end) == '0') { + mask |= 1 << shift; + shift++; + end--; + } else if (*(p + end) == '1') { + mask |= 1 << shift; + flags |= 1 << shift; + shift++; + end--; + } else if ((*(p + end) == 'x') || (*(p + end) == 'X')) { + shift++; + end--; + } else { + pci_err(dev, "Invalid ACS flags... Ignoring\n"); + return; + } + } + p = delimit + 1; + } else { + pci_err(dev, "ACS Flags missing\n"); + return; + } + } + + if (mask & ~(PCI_ACS_SV | PCI_ACS_TB | PCI_ACS_RR | PCI_ACS_CR | + PCI_ACS_UF | PCI_ACS_EC | PCI_ACS_DT)) { + pci_err(dev, "Invalid ACS flags specified\n"); + return; + } + ret = pci_dev_str_match(dev, p, &p); if (ret < 0) { - pr_info_once("PCI: Can't parse disable_acs_redir parameter: %s\n", - disable_acs_redir_param); - + pr_info_once("PCI: Can't parse ACS command line parameter\n"); break; } else if (ret == 1) { /* Found a match */ @@ -990,56 +1025,38 @@ static void pci_disable_acs_redir(struct pci_dev *dev) if (!pci_dev_specific_disable_acs_redir(dev)) return; - pos = dev->acs_cap; - if (!pos) { - pci_warn(dev, "cannot disable ACS redirect for this hardware as it does not have ACS capabilities\n"); - return; - } - - pci_read_config_word(dev, pos + PCI_ACS_CTRL, &ctrl); - - /* P2P Request & Completion Redirect */ - ctrl &= ~(PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_EC); + pci_dbg(dev, "ACS mask = %#06x\n", mask); + pci_dbg(dev, "ACS flags = %#06x\n", flags); - pci_write_config_word(dev, pos + PCI_ACS_CTRL, ctrl); + /* If mask is 0 then we copy the bit from the firmware setting. */ + caps->ctrl = (caps->ctrl & ~mask) | (caps->fw_ctrl & mask); + caps->ctrl |= flags; - pci_info(dev, "disabled ACS redirect\n"); + pci_info(dev, "Configured ACS to %#06x\n", caps->ctrl); } /** * pci_std_enable_acs - enable ACS on devices using standard ACS capabilities * @dev: the PCI device + * @caps: default ACS controls */ -static void pci_std_enable_acs(struct pci_dev *dev) +static void pci_std_enable_acs(struct pci_dev *dev, struct pci_acs *caps) { - int pos; - u16 cap; - u16 ctrl; - - pos = dev->acs_cap; - if (!pos) - return; - - pci_read_config_word(dev, pos + PCI_ACS_CAP, &cap); - pci_read_config_word(dev, pos + PCI_ACS_CTRL, &ctrl); - /* Source Validation */ - ctrl |= (cap & PCI_ACS_SV); + caps->ctrl |= (caps->cap & PCI_ACS_SV); /* P2P Request Redirect */ - ctrl |= (cap & PCI_ACS_RR); + caps->ctrl |= (caps->cap & PCI_ACS_RR); /* P2P Completion Redirect */ - ctrl |= (cap & PCI_ACS_CR); + caps->ctrl |= (caps->cap & PCI_ACS_CR); /* Upstream Forwarding */ - ctrl |= (cap & PCI_ACS_UF); + caps->ctrl |= (caps->cap & PCI_ACS_UF); /* Enable Translation Blocking for external devices and noats */ if (pci_ats_disabled() || dev->external_facing || dev->untrusted) - ctrl |= (cap & PCI_ACS_TB); - - pci_write_config_word(dev, pos + PCI_ACS_CTRL, ctrl); + caps->ctrl |= (caps->cap & PCI_ACS_TB); } /** @@ -1048,23 +1065,37 @@ static void pci_std_enable_acs(struct pci_dev *dev) */ static void pci_enable_acs(struct pci_dev *dev) { - if (!pci_acs_enable) - goto disable_acs_redir; + struct pci_acs caps; + bool enable_acs = false; + int pos; + + /* If an iommu is present we start with kernel default caps */ + if (pci_acs_enable) { + if (pci_dev_specific_enable_acs(dev)) + enable_acs = true; + } + + pos = dev->acs_cap; + if (!pos) + return; - if (!pci_dev_specific_enable_acs(dev)) - goto disable_acs_redir; + pci_read_config_word(dev, pos + PCI_ACS_CAP, &caps.cap); + pci_read_config_word(dev, pos + PCI_ACS_CTRL, &caps.ctrl); + caps.fw_ctrl = caps.ctrl; - pci_std_enable_acs(dev); + if (enable_acs) + pci_std_enable_acs(dev, &caps); -disable_acs_redir: /* - * Note: pci_disable_acs_redir() must be called even if ACS was not - * enabled by the kernel because it may have been enabled by - * platform firmware. So if we are told to disable it, we should - * always disable it after setting the kernel's default - * preferences. + * Always apply caps from the command line, even if there is no iommu. + * Trust that the admin has a reason to change the ACS settings. */ - pci_disable_acs_redir(dev); + __pci_config_acs(dev, &caps, disable_acs_redir_param, + PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_EC, + ~(PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_EC)); + __pci_config_acs(dev, &caps, config_acs_param, 0, 0); + + pci_write_config_word(dev, pos + PCI_ACS_CTRL, caps.ctrl); } /** @@ -1227,7 +1258,9 @@ static int pci_dev_wait(struct pci_dev *dev, char *reset_type, int timeout) { int delay = 1; bool retrain = false; - struct pci_dev *bridge; + struct pci_dev *root, *bridge; + + root = pcie_find_root_port(dev); if (pci_is_pcie(dev)) { bridge = pci_upstream_bridge(dev); @@ -1236,23 +1269,41 @@ static int pci_dev_wait(struct pci_dev *dev, char *reset_type, int timeout) } /* - * 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 (PCI_ERROR_RESPONSE) 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). + * The caller has already waited long enough after a reset that the + * device should respond to config requests, but it may respond + * with Request Retry Status (RRS) if it needs more time to + * initialize. * - * 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. + * If the device is below a Root Port with Configuration RRS + * Software Visibility enabled, reading the Vendor ID returns a + * special data value if the device responded with RRS. Read the + * Vendor ID until we get non-RRS status. + * + * If there's no Root Port or Configuration RRS Software Visibility + * is not enabled, the device may still respond with RRS, but + * hardware may retry the config request. If no retries receive + * Successful Completion, hardware generally synthesizes ~0 + * (PCI_ERROR_RESPONSE) data to complete the read. Reading Vendor + * ID for VFs and non-existent devices also returns ~0, so read the + * Command register until it returns something other than ~0. */ for (;;) { u32 id; - pci_read_config_dword(dev, PCI_COMMAND, &id); - if (!PCI_POSSIBLE_ERROR(id)) - break; + if (pci_dev_is_disconnected(dev)) { + pci_dbg(dev, "disconnected; not waiting\n"); + return -ENOTTY; + } + + if (root && root->config_rrs_sv) { + pci_read_config_dword(dev, PCI_VENDOR_ID, &id); + if (!pci_bus_rrs_vendor_id(id)) + break; + } else { + pci_read_config_dword(dev, PCI_COMMAND, &id); + if (!PCI_POSSIBLE_ERROR(id)) + break; + } if (delay > timeout) { pci_warn(dev, "not ready %dms after %s; giving up\n", @@ -1263,7 +1314,7 @@ static int pci_dev_wait(struct pci_dev *dev, char *reset_type, int timeout) if (delay > PCI_RESET_WAIT) { if (retrain) { retrain = false; - if (pcie_failed_link_retrain(bridge)) { + if (pcie_failed_link_retrain(bridge) == 0) { delay = 1; continue; } @@ -1649,25 +1700,10 @@ static int pci_save_pcie_state(struct pci_dev *dev) pcie_capability_read_word(dev, PCI_EXP_LNKCTL2, &cap[i++]); pcie_capability_read_word(dev, PCI_EXP_SLTCTL2, &cap[i++]); - return 0; -} - -void pci_bridge_reconfigure_ltr(struct pci_dev *dev) -{ -#ifdef CONFIG_PCIEASPM - struct pci_dev *bridge; - u32 ctl; + pci_save_aspm_l1ss_state(dev); + pci_save_ltr_state(dev); - bridge = pci_upstream_bridge(dev); - if (bridge && bridge->ltr_path) { - pcie_capability_read_dword(bridge, PCI_EXP_DEVCTL2, &ctl); - if (!(ctl & PCI_EXP_DEVCTL2_LTR_EN)) { - pci_dbg(bridge, "re-enabling LTR\n"); - pcie_capability_set_word(bridge, PCI_EXP_DEVCTL2, - PCI_EXP_DEVCTL2_LTR_EN); - } - } -#endif + return 0; } static void pci_restore_pcie_state(struct pci_dev *dev) @@ -1676,6 +1712,13 @@ static void pci_restore_pcie_state(struct pci_dev *dev) struct pci_cap_saved_state *save_state; u16 *cap; + /* + * Restore max latencies (in the LTR capability) before enabling + * LTR itself in PCI_EXP_DEVCTL2. + */ + pci_restore_ltr_state(dev); + pci_restore_aspm_l1ss_state(dev); + save_state = pci_find_saved_cap(dev, PCI_CAP_ID_EXP); if (!save_state) return; @@ -1733,46 +1776,6 @@ static void pci_restore_pcix_state(struct pci_dev *dev) pci_write_config_word(dev, pos + PCI_X_CMD, cap[i++]); } -static void pci_save_ltr_state(struct pci_dev *dev) -{ - int ltr; - struct pci_cap_saved_state *save_state; - u32 *cap; - - if (!pci_is_pcie(dev)) - return; - - ltr = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_LTR); - if (!ltr) - return; - - save_state = pci_find_saved_ext_cap(dev, PCI_EXT_CAP_ID_LTR); - if (!save_state) { - pci_err(dev, "no suspend buffer for LTR; ASPM issues possible after resume\n"); - return; - } - - /* Some broken devices only support dword access to LTR */ - cap = &save_state->cap.data[0]; - pci_read_config_dword(dev, ltr + PCI_LTR_MAX_SNOOP_LAT, cap); -} - -static void pci_restore_ltr_state(struct pci_dev *dev) -{ - struct pci_cap_saved_state *save_state; - int ltr; - u32 *cap; - - save_state = pci_find_saved_ext_cap(dev, PCI_EXT_CAP_ID_LTR); - ltr = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_LTR); - if (!save_state || !ltr) - return; - - /* Some broken devices only support dword access to LTR */ - cap = &save_state->cap.data[0]; - pci_write_config_dword(dev, ltr + PCI_LTR_MAX_SNOOP_LAT, *cap); -} - /** * pci_save_state - save the PCI configuration space of a device before * suspending @@ -1797,10 +1800,10 @@ int pci_save_state(struct pci_dev *dev) if (i != 0) return i; - pci_save_ltr_state(dev); pci_save_dpc_state(dev); pci_save_aer_state(dev); pci_save_ptm_state(dev); + pci_save_tph_state(dev); return pci_save_vc_state(dev); } EXPORT_SYMBOL(pci_save_state); @@ -1898,12 +1901,6 @@ void pci_restore_state(struct pci_dev *dev) if (!dev->state_saved) return; - /* - * Restore max latencies (in the LTR capability) before enabling - * LTR itself (in the PCIe capability). - */ - pci_restore_ltr_state(dev); - pci_restore_pcie_state(dev); pci_restore_pasid_state(dev); pci_restore_pri_state(dev); @@ -1912,6 +1909,7 @@ void pci_restore_state(struct pci_dev *dev) pci_restore_rebar_state(dev); pci_restore_dpc_state(dev); pci_restore_ptm_state(dev); + pci_restore_tph_state(dev); pci_aer_clear_status(dev); pci_restore_aer_state(dev); @@ -2032,6 +2030,28 @@ int __weak pcibios_enable_device(struct pci_dev *dev, int bars) return pci_enable_resources(dev, bars); } +static int pci_host_bridge_enable_device(struct pci_dev *dev) +{ + struct pci_host_bridge *host_bridge = pci_find_host_bridge(dev->bus); + int err; + + if (host_bridge && host_bridge->enable_device) { + err = host_bridge->enable_device(host_bridge, dev); + if (err) + return err; + } + + return 0; +} + +static void pci_host_bridge_disable_device(struct pci_dev *dev) +{ + struct pci_host_bridge *host_bridge = pci_find_host_bridge(dev->bus); + + if (host_bridge && host_bridge->disable_device) + host_bridge->disable_device(host_bridge, dev); +} + static int do_pci_enable_device(struct pci_dev *dev, int bars) { int err; @@ -2047,9 +2067,13 @@ static int do_pci_enable_device(struct pci_dev *dev, int bars) if (bridge) pcie_aspm_powersave_config_link(bridge); + err = pci_host_bridge_enable_device(dev); + if (err) + return err; + err = pcibios_enable_device(dev, bars); if (err < 0) - return err; + goto err_enable; pci_fixup_device(pci_fixup_enable, dev); if (dev->msi_enabled || dev->msix_enabled) @@ -2064,6 +2088,12 @@ static int do_pci_enable_device(struct pci_dev *dev, int bars) } return 0; + +err_enable: + pci_host_bridge_disable_device(dev); + + return err; + } /** @@ -2139,20 +2169,6 @@ static int pci_enable_device_flags(struct pci_dev *dev, unsigned long flags) } /** - * pci_enable_device_io - Initialize a device for use with IO space - * @dev: PCI device to be initialized - * - * Initialize device before it's used by a driver. Ask low-level code - * to enable I/O resources. Wake up the device if it was suspended. - * Beware, this function can fail. - */ -int pci_enable_device_io(struct pci_dev *dev) -{ - return pci_enable_device_flags(dev, IORESOURCE_IO); -} -EXPORT_SYMBOL(pci_enable_device_io); - -/** * pci_enable_device_mem - Initialize a device for use with Memory space * @dev: PCI device to be initialized * @@ -2184,107 +2200,6 @@ int pci_enable_device(struct pci_dev *dev) EXPORT_SYMBOL(pci_enable_device); /* - * Managed PCI resources. This manages device on/off, INTx/MSI/MSI-X - * on/off and BAR regions. pci_dev itself records MSI/MSI-X status, so - * there's no need to track it separately. pci_devres is initialized - * when a device is enabled using managed PCI device enable interface. - */ -struct pci_devres { - unsigned int enabled:1; - unsigned int pinned:1; - unsigned int orig_intx:1; - unsigned int restore_intx:1; - unsigned int mwi:1; - u32 region_mask; -}; - -static void pcim_release(struct device *gendev, void *res) -{ - struct pci_dev *dev = to_pci_dev(gendev); - struct pci_devres *this = res; - int i; - - for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) - if (this->region_mask & (1 << i)) - pci_release_region(dev, i); - - if (this->mwi) - pci_clear_mwi(dev); - - if (this->restore_intx) - pci_intx(dev, this->orig_intx); - - if (this->enabled && !this->pinned) - pci_disable_device(dev); -} - -static struct pci_devres *get_pci_dr(struct pci_dev *pdev) -{ - struct pci_devres *dr, *new_dr; - - dr = devres_find(&pdev->dev, pcim_release, NULL, NULL); - if (dr) - return dr; - - new_dr = devres_alloc(pcim_release, sizeof(*new_dr), GFP_KERNEL); - if (!new_dr) - return NULL; - return devres_get(&pdev->dev, new_dr, NULL, NULL); -} - -static struct pci_devres *find_pci_dr(struct pci_dev *pdev) -{ - if (pci_is_managed(pdev)) - return devres_find(&pdev->dev, pcim_release, NULL, NULL); - return NULL; -} - -/** - * pcim_enable_device - Managed pci_enable_device() - * @pdev: PCI device to be initialized - * - * Managed pci_enable_device(). - */ -int pcim_enable_device(struct pci_dev *pdev) -{ - struct pci_devres *dr; - int rc; - - dr = get_pci_dr(pdev); - if (unlikely(!dr)) - return -ENOMEM; - if (dr->enabled) - return 0; - - rc = pci_enable_device(pdev); - if (!rc) { - pdev->is_managed = 1; - dr->enabled = 1; - } - return rc; -} -EXPORT_SYMBOL(pcim_enable_device); - -/** - * pcim_pin_device - Pin managed PCI device - * @pdev: PCI device to pin - * - * Pin managed PCI device @pdev. Pinned device won't be disabled on - * driver detach. @pdev must have been enabled with - * pcim_enable_device(). - */ -void pcim_pin_device(struct pci_dev *pdev) -{ - struct pci_devres *dr; - - dr = find_pci_dr(pdev); - WARN_ON(!dr || !dr->enabled); - if (dr) - dr->pinned = 1; -} -EXPORT_SYMBOL(pcim_pin_device); - -/* * pcibios_device_add - provide arch specific hooks when adding device dev * @dev: the PCI device being added * @@ -2318,17 +2233,6 @@ void __weak pcibios_release_device(struct pci_dev *dev) {} */ void __weak pcibios_disable_device(struct pci_dev *dev) {} -/** - * pcibios_penalize_isa_irq - penalize an ISA IRQ - * @irq: ISA IRQ to penalize - * @active: IRQ active or not - * - * Permits the platform to provide architecture-specific functionality when - * penalizing ISA IRQs. This is the default implementation. Architecture - * implementations can override this. - */ -void __weak pcibios_penalize_isa_irq(int irq, int active) {} - static void do_pci_disable_device(struct pci_dev *dev) { u16 pci_command; @@ -2367,18 +2271,14 @@ void pci_disable_enabled_device(struct pci_dev *dev) */ void pci_disable_device(struct pci_dev *dev) { - struct pci_devres *dr; - - dr = find_pci_dr(dev); - if (dr) - dr->enabled = 0; - dev_WARN_ONCE(&dev->dev, atomic_read(&dev->enable_cnt) <= 0, "disabling already-disabled device"); if (atomic_dec_return(&dev->enable_cnt) != 0) return; + pci_host_bridge_disable_device(dev); + do_pci_disable_device(dev); dev->is_busmaster = 0; @@ -2532,7 +2432,7 @@ static void pci_pme_list_scan(struct work_struct *work) * course of the call. */ if (bdev) { - bref = pm_runtime_get_if_active(bdev, true); + bref = pm_runtime_get_if_active(bdev); if (!bref) continue; @@ -3102,6 +3002,18 @@ static const struct dmi_system_id bridge_d3_blacklist[] = { DMI_MATCH(DMI_BOARD_VERSION, "Continental Z2"), }, }, + { + /* + * Changing power state of root port dGPU is connected fails + * https://gitlab.freedesktop.org/drm/amd/-/issues/3229 + */ + .ident = "Hewlett-Packard HP Pavilion 17 Notebook PC/1972", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_BOARD_NAME, "1972"), + DMI_MATCH(DMI_BOARD_VERSION, "95.33"), + }, + }, #endif { } }; @@ -3998,66 +3910,6 @@ int pci_enable_atomic_ops_to_root(struct pci_dev *dev, u32 cap_mask) EXPORT_SYMBOL(pci_enable_atomic_ops_to_root); /** - * pci_swizzle_interrupt_pin - swizzle INTx for device behind bridge - * @dev: the PCI device - * @pin: the INTx pin (1=INTA, 2=INTB, 3=INTC, 4=INTD) - * - * Perform INTx swizzling for a device behind one level of bridge. This is - * required by section 9.1 of the PCI-to-PCI bridge specification for devices - * behind bridges on add-in cards. For devices with ARI enabled, the slot - * number is always 0 (see the Implementation Note in section 2.2.8.1 of - * the PCI Express Base Specification, Revision 2.1) - */ -u8 pci_swizzle_interrupt_pin(const struct pci_dev *dev, u8 pin) -{ - int slot; - - if (pci_ari_enabled(dev->bus)) - slot = 0; - else - slot = PCI_SLOT(dev->devfn); - - return (((pin - 1) + slot) % 4) + 1; -} - -int pci_get_interrupt_pin(struct pci_dev *dev, struct pci_dev **bridge) -{ - u8 pin; - - pin = dev->pin; - if (!pin) - return -1; - - while (!pci_is_root_bus(dev->bus)) { - pin = pci_swizzle_interrupt_pin(dev, pin); - dev = dev->bus->self; - } - *bridge = dev; - return pin; -} - -/** - * pci_common_swizzle - swizzle INTx all the way to root bridge - * @dev: the PCI device - * @pinp: pointer to the INTx pin value (1=INTA, 2=INTB, 3=INTD, 4=INTD) - * - * Perform INTx swizzling for a device. This traverses through all PCI-to-PCI - * bridges all the way up to a PCI root bus. - */ -u8 pci_common_swizzle(struct pci_dev *dev, u8 *pinp) -{ - u8 pin = *pinp; - - while (!pci_is_root_bus(dev->bus)) { - pin = pci_swizzle_interrupt_pin(dev, pin); - dev = dev->bus->self; - } - *pinp = pin; - return PCI_SLOT(dev->devfn); -} -EXPORT_SYMBOL_GPL(pci_common_swizzle); - -/** * pci_release_region - Release a PCI bar * @pdev: PCI device whose resources were previously reserved by * pci_request_region() @@ -4069,7 +3921,15 @@ EXPORT_SYMBOL_GPL(pci_common_swizzle); */ void pci_release_region(struct pci_dev *pdev, int bar) { - struct pci_devres *dr; + /* + * This is done for backwards compatibility, because the old PCI devres + * API had a mode in which the function became managed if it had been + * enabled with pcim_enable_device() instead of pci_enable_device(). + */ + if (pci_is_managed(pdev)) { + pcim_release_region(pdev, bar); + return; + } if (pci_resource_len(pdev, bar) == 0) return; @@ -4079,10 +3939,6 @@ void pci_release_region(struct pci_dev *pdev, int bar) else if (pci_resource_flags(pdev, bar) & IORESOURCE_MEM) release_mem_region(pci_resource_start(pdev, bar), pci_resource_len(pdev, bar)); - - dr = find_pci_dr(pdev); - if (dr) - dr->region_mask &= ~(1 << bar); } EXPORT_SYMBOL(pci_release_region); @@ -4090,13 +3946,14 @@ EXPORT_SYMBOL(pci_release_region); * __pci_request_region - Reserved PCI I/O and memory resource * @pdev: PCI device whose resources are to be reserved * @bar: BAR to be reserved - * @res_name: Name to be associated with resource. + * @name: name of the driver requesting the resource * @exclusive: whether the region access is exclusive or not * - * Mark the PCI region associated with PCI device @pdev BAR @bar as - * being reserved by owner @res_name. Do not access any - * address inside the PCI regions unless this call returns - * successfully. + * Returns: 0 on success, negative error code on failure. + * + * Mark the PCI region associated with PCI device @pdev BAR @bar as being + * reserved by owner @name. Do not access any address inside the PCI regions + * unless this call returns successfully. * * If @exclusive is set, then the region is marked so that userspace * is explicitly not allowed to map the resource via /dev/mem or @@ -4106,28 +3963,29 @@ EXPORT_SYMBOL(pci_release_region); * message is also printed on failure. */ static int __pci_request_region(struct pci_dev *pdev, int bar, - const char *res_name, int exclusive) + const char *name, int exclusive) { - struct pci_devres *dr; + if (pci_is_managed(pdev)) { + if (exclusive == IORESOURCE_EXCLUSIVE) + return pcim_request_region_exclusive(pdev, bar, name); + + return pcim_request_region(pdev, bar, name); + } if (pci_resource_len(pdev, bar) == 0) return 0; if (pci_resource_flags(pdev, bar) & IORESOURCE_IO) { if (!request_region(pci_resource_start(pdev, bar), - pci_resource_len(pdev, bar), res_name)) + pci_resource_len(pdev, bar), name)) goto err_out; } else if (pci_resource_flags(pdev, bar) & IORESOURCE_MEM) { if (!__request_mem_region(pci_resource_start(pdev, bar), - pci_resource_len(pdev, bar), res_name, + pci_resource_len(pdev, bar), name, exclusive)) goto err_out; } - dr = find_pci_dr(pdev); - if (dr) - dr->region_mask |= 1 << bar; - return 0; err_out: @@ -4140,19 +3998,25 @@ err_out: * pci_request_region - Reserve PCI I/O and memory resource * @pdev: PCI device whose resources are to be reserved * @bar: BAR to be reserved - * @res_name: Name to be associated with resource + * @name: name of the driver requesting the resource + * + * Returns: 0 on success, negative error code on failure. * - * Mark the PCI region associated with PCI device @pdev BAR @bar as - * being reserved by owner @res_name. Do not access any - * address inside the PCI regions unless this call returns - * successfully. + * Mark the PCI region associated with PCI device @pdev BAR @bar as being + * reserved by owner @name. Do not access any address inside the PCI regions + * unless this call returns successfully. * * Returns 0 on success, or %EBUSY on error. A warning * message is also printed on failure. + * + * NOTE: + * This is a "hybrid" function: It's normally unmanaged, but becomes managed + * when pcim_enable_device() has been called in advance. This hybrid feature is + * DEPRECATED! If you want managed cleanup, use the pcim_* functions instead. */ -int pci_request_region(struct pci_dev *pdev, int bar, const char *res_name) +int pci_request_region(struct pci_dev *pdev, int bar, const char *name) { - return __pci_request_region(pdev, bar, res_name, 0); + return __pci_request_region(pdev, bar, name, 0); } EXPORT_SYMBOL(pci_request_region); @@ -4175,13 +4039,13 @@ void pci_release_selected_regions(struct pci_dev *pdev, int bars) EXPORT_SYMBOL(pci_release_selected_regions); static int __pci_request_selected_regions(struct pci_dev *pdev, int bars, - const char *res_name, int excl) + const char *name, int excl) { int i; for (i = 0; i < PCI_STD_NUM_BARS; i++) if (bars & (1 << i)) - if (__pci_request_region(pdev, i, res_name, excl)) + if (__pci_request_region(pdev, i, name, excl)) goto err_out; return 0; @@ -4198,19 +4062,39 @@ err_out: * pci_request_selected_regions - Reserve selected PCI I/O and memory resources * @pdev: PCI device whose resources are to be reserved * @bars: Bitmask of BARs to be requested - * @res_name: Name to be associated with resource + * @name: Name of the driver requesting the resources + * + * Returns: 0 on success, negative error code on failure. + * + * NOTE: + * This is a "hybrid" function: It's normally unmanaged, but becomes managed + * when pcim_enable_device() has been called in advance. This hybrid feature is + * DEPRECATED! If you want managed cleanup, use the pcim_* functions instead. */ int pci_request_selected_regions(struct pci_dev *pdev, int bars, - const char *res_name) + const char *name) { - return __pci_request_selected_regions(pdev, bars, res_name, 0); + return __pci_request_selected_regions(pdev, bars, name, 0); } EXPORT_SYMBOL(pci_request_selected_regions); +/** + * pci_request_selected_regions_exclusive - Request regions exclusively + * @pdev: PCI device to request regions from + * @bars: bit mask of BARs to request + * @name: name of the driver requesting the resources + * + * Returns: 0 on success, negative error code on failure. + * + * NOTE: + * This is a "hybrid" function: It's normally unmanaged, but becomes managed + * when pcim_enable_device() has been called in advance. This hybrid feature is + * DEPRECATED! If you want managed cleanup, use the pcim_* functions instead. + */ int pci_request_selected_regions_exclusive(struct pci_dev *pdev, int bars, - const char *res_name) + const char *name) { - return __pci_request_selected_regions(pdev, bars, res_name, + return __pci_request_selected_regions(pdev, bars, name, IORESOURCE_EXCLUSIVE); } EXPORT_SYMBOL(pci_request_selected_regions_exclusive); @@ -4224,7 +4108,6 @@ EXPORT_SYMBOL(pci_request_selected_regions_exclusive); * successful call to pci_request_regions(). Call this function only * after all use of the PCI regions has ceased. */ - void pci_release_regions(struct pci_dev *pdev) { pci_release_selected_regions(pdev, (1 << PCI_STD_NUM_BARS) - 1); @@ -4234,30 +4117,36 @@ EXPORT_SYMBOL(pci_release_regions); /** * pci_request_regions - Reserve PCI I/O and memory resources * @pdev: PCI device whose resources are to be reserved - * @res_name: Name to be associated with resource. + * @name: name of the driver requesting the resources * - * Mark all PCI regions associated with PCI device @pdev as - * being reserved by owner @res_name. Do not access any - * address inside the PCI regions unless this call returns - * successfully. + * Mark all PCI regions associated with PCI device @pdev as being reserved by + * owner @name. Do not access any address inside the PCI regions unless this + * call returns successfully. * * Returns 0 on success, or %EBUSY on error. A warning * message is also printed on failure. + * + * NOTE: + * This is a "hybrid" function: It's normally unmanaged, but becomes managed + * when pcim_enable_device() has been called in advance. This hybrid feature is + * DEPRECATED! If you want managed cleanup, use the pcim_* functions instead. */ -int pci_request_regions(struct pci_dev *pdev, const char *res_name) +int pci_request_regions(struct pci_dev *pdev, const char *name) { return pci_request_selected_regions(pdev, - ((1 << PCI_STD_NUM_BARS) - 1), res_name); + ((1 << PCI_STD_NUM_BARS) - 1), name); } EXPORT_SYMBOL(pci_request_regions); /** * pci_request_regions_exclusive - Reserve PCI I/O and memory resources * @pdev: PCI device whose resources are to be reserved - * @res_name: Name to be associated with resource. + * @name: name of the driver requesting the resources + * + * Returns: 0 on success, negative error code on failure. * * Mark all PCI regions associated with PCI device @pdev as being reserved - * by owner @res_name. Do not access any address inside the PCI regions + * by owner @name. Do not access any address inside the PCI regions * unless this call returns successfully. * * pci_request_regions_exclusive() will mark the region so that /dev/mem @@ -4265,11 +4154,16 @@ EXPORT_SYMBOL(pci_request_regions); * * Returns 0 on success, or %EBUSY on error. A warning message is also * printed on failure. + * + * NOTE: + * This is a "hybrid" function: It's normally unmanaged, but becomes managed + * when pcim_enable_device() has been called in advance. This hybrid feature is + * DEPRECATED! If you want managed cleanup, use the pcim_* functions instead. */ -int pci_request_regions_exclusive(struct pci_dev *pdev, const char *res_name) +int pci_request_regions_exclusive(struct pci_dev *pdev, const char *name) { return pci_request_selected_regions_exclusive(pdev, - ((1 << PCI_STD_NUM_BARS) - 1), res_name); + ((1 << PCI_STD_NUM_BARS) - 1), name); } EXPORT_SYMBOL(pci_request_regions_exclusive); @@ -4277,7 +4171,7 @@ EXPORT_SYMBOL(pci_request_regions_exclusive); * Record the PCI IO range (expressed as CPU physical address + size). * Return a negative value if an error has occurred, zero otherwise */ -int pci_register_io_range(struct fwnode_handle *fwnode, phys_addr_t addr, +int pci_register_io_range(const struct fwnode_handle *fwnode, phys_addr_t addr, resource_size_t size) { int ret = 0; @@ -4353,8 +4247,8 @@ int pci_remap_iospace(const struct resource *res, phys_addr_t phys_addr) if (res->end > IO_SPACE_LIMIT) return -EINVAL; - return ioremap_page_range(vaddr, vaddr + resource_size(res), phys_addr, - pgprot_device(PAGE_KERNEL)); + return vmap_page_range(vaddr, vaddr + resource_size(res), phys_addr, + pgprot_device(PAGE_KERNEL)); #else /* * This architecture does not have memory mapped I/O space, @@ -4385,133 +4279,6 @@ void pci_unmap_iospace(struct resource *res) } EXPORT_SYMBOL(pci_unmap_iospace); -static void devm_pci_unmap_iospace(struct device *dev, void *ptr) -{ - struct resource **res = ptr; - - pci_unmap_iospace(*res); -} - -/** - * devm_pci_remap_iospace - Managed pci_remap_iospace() - * @dev: Generic device to remap IO address for - * @res: Resource describing the I/O space - * @phys_addr: physical address of range to be mapped - * - * Managed pci_remap_iospace(). Map is automatically unmapped on driver - * detach. - */ -int devm_pci_remap_iospace(struct device *dev, const struct resource *res, - phys_addr_t phys_addr) -{ - const struct resource **ptr; - int error; - - ptr = devres_alloc(devm_pci_unmap_iospace, sizeof(*ptr), GFP_KERNEL); - if (!ptr) - return -ENOMEM; - - error = pci_remap_iospace(res, phys_addr); - if (error) { - devres_free(ptr); - } else { - *ptr = res; - devres_add(dev, ptr); - } - - return error; -} -EXPORT_SYMBOL(devm_pci_remap_iospace); - -/** - * devm_pci_remap_cfgspace - Managed pci_remap_cfgspace() - * @dev: Generic device to remap IO address for - * @offset: Resource address to map - * @size: Size of map - * - * Managed pci_remap_cfgspace(). Map is automatically unmapped on driver - * detach. - */ -void __iomem *devm_pci_remap_cfgspace(struct device *dev, - resource_size_t offset, - resource_size_t size) -{ - void __iomem **ptr, *addr; - - ptr = devres_alloc(devm_ioremap_release, sizeof(*ptr), GFP_KERNEL); - if (!ptr) - return NULL; - - addr = pci_remap_cfgspace(offset, size); - if (addr) { - *ptr = addr; - devres_add(dev, ptr); - } else - devres_free(ptr); - - return addr; -} -EXPORT_SYMBOL(devm_pci_remap_cfgspace); - -/** - * devm_pci_remap_cfg_resource - check, request region and ioremap cfg resource - * @dev: generic device to handle the resource for - * @res: configuration space resource to be handled - * - * Checks that a resource is a valid memory region, requests the memory - * region and ioremaps with pci_remap_cfgspace() API that ensures the - * proper PCI configuration space memory attributes are guaranteed. - * - * All operations are managed and will be undone on driver detach. - * - * Returns a pointer to the remapped memory or an ERR_PTR() encoded error code - * on failure. Usage example:: - * - * res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - * base = devm_pci_remap_cfg_resource(&pdev->dev, res); - * if (IS_ERR(base)) - * return PTR_ERR(base); - */ -void __iomem *devm_pci_remap_cfg_resource(struct device *dev, - struct resource *res) -{ - resource_size_t size; - const char *name; - void __iomem *dest_ptr; - - BUG_ON(!dev); - - if (!res || resource_type(res) != IORESOURCE_MEM) { - dev_err(dev, "invalid resource\n"); - return IOMEM_ERR_PTR(-EINVAL); - } - - size = resource_size(res); - - if (res->name) - name = devm_kasprintf(dev, GFP_KERNEL, "%s %s", dev_name(dev), - res->name); - else - name = devm_kstrdup(dev, dev_name(dev), GFP_KERNEL); - if (!name) - return IOMEM_ERR_PTR(-ENOMEM); - - if (!devm_request_mem_region(dev, res->start, size, name)) { - dev_err(dev, "can't request region for resource %pR\n", res); - return IOMEM_ERR_PTR(-EBUSY); - } - - dest_ptr = devm_pci_remap_cfgspace(dev, res->start, size); - if (!dest_ptr) { - dev_err(dev, "ioremap failed for resource %pR\n", res); - devm_release_mem_region(dev, res->start, size); - dest_ptr = IOMEM_ERR_PTR(-ENOMEM); - } - - return dest_ptr; -} -EXPORT_SYMBOL(devm_pci_remap_cfg_resource); - static void __pci_set_master(struct pci_dev *dev, bool enable) { u16 old_cmd, cmd; @@ -4662,27 +4429,6 @@ int pci_set_mwi(struct pci_dev *dev) EXPORT_SYMBOL(pci_set_mwi); /** - * pcim_set_mwi - a device-managed pci_set_mwi() - * @dev: the PCI device for which MWI is enabled - * - * Managed pci_set_mwi(). - * - * RETURNS: An appropriate -ERRNO error value on error, or zero for success. - */ -int pcim_set_mwi(struct pci_dev *dev) -{ - struct pci_devres *dr; - - dr = find_pci_dr(dev); - if (!dr) - return -ENOMEM; - - dr->mwi = 1; - return pci_set_mwi(dev); -} -EXPORT_SYMBOL(pcim_set_mwi); - -/** * pci_try_set_mwi - enables memory-write-invalidate PCI transaction * @dev: the PCI device for which MWI is enabled * @@ -4756,92 +4502,13 @@ void pci_intx(struct pci_dev *pdev, int enable) else new = pci_command | PCI_COMMAND_INTX_DISABLE; - if (new != pci_command) { - struct pci_devres *dr; - - pci_write_config_word(pdev, PCI_COMMAND, new); + if (new == pci_command) + return; - dr = find_pci_dr(pdev); - if (dr && !dr->restore_intx) { - dr->restore_intx = 1; - dr->orig_intx = !enable; - } - } + pci_write_config_word(pdev, PCI_COMMAND, new); } EXPORT_SYMBOL_GPL(pci_intx); -static bool pci_check_and_set_intx_mask(struct pci_dev *dev, bool mask) -{ - struct pci_bus *bus = dev->bus; - bool mask_updated = true; - u32 cmd_status_dword; - u16 origcmd, newcmd; - unsigned long flags; - bool irq_pending; - - /* - * We do a single dword read to retrieve both command and status. - * Document assumptions that make this possible. - */ - BUILD_BUG_ON(PCI_COMMAND % 4); - BUILD_BUG_ON(PCI_COMMAND + 2 != PCI_STATUS); - - raw_spin_lock_irqsave(&pci_lock, flags); - - bus->ops->read(bus, dev->devfn, PCI_COMMAND, 4, &cmd_status_dword); - - irq_pending = (cmd_status_dword >> 16) & PCI_STATUS_INTERRUPT; - - /* - * Check interrupt status register to see whether our device - * triggered the interrupt (when masking) or the next IRQ is - * already pending (when unmasking). - */ - if (mask != irq_pending) { - mask_updated = false; - goto done; - } - - origcmd = cmd_status_dword; - newcmd = origcmd & ~PCI_COMMAND_INTX_DISABLE; - if (mask) - newcmd |= PCI_COMMAND_INTX_DISABLE; - if (newcmd != origcmd) - bus->ops->write(bus, dev->devfn, PCI_COMMAND, 2, newcmd); - -done: - raw_spin_unlock_irqrestore(&pci_lock, flags); - - return mask_updated; -} - -/** - * pci_check_and_mask_intx - mask INTx on pending interrupt - * @dev: the PCI device to operate on - * - * Check if the device dev has its INTx line asserted, mask it and return - * true in that case. False is returned if no interrupt was pending. - */ -bool pci_check_and_mask_intx(struct pci_dev *dev) -{ - return pci_check_and_set_intx_mask(dev, true); -} -EXPORT_SYMBOL_GPL(pci_check_and_mask_intx); - -/** - * pci_check_and_unmask_intx - unmask INTx if no interrupt is pending - * @dev: the PCI device to operate on - * - * Check if the device dev has its INTx line asserted, unmask it if not and - * return true. False is returned and the mask remains active if there was - * still an interrupt pending. - */ -bool pci_check_and_unmask_intx(struct pci_dev *dev) -{ - return pci_check_and_set_intx_mask(dev, false); -} -EXPORT_SYMBOL_GPL(pci_check_and_unmask_intx); - /** * pci_wait_for_pending_transaction - wait for pending transaction * @dev: the PCI device to operate on @@ -5045,11 +4712,12 @@ int pcie_retrain_link(struct pci_dev *pdev, bool use_lt) /* * Ensure the updated LNKCTL parameters are used during link - * training by checking that there is no ongoing link training to - * avoid LTSSM race as recommended in Implementation Note at the - * end of PCIe r6.0.1 sec 7.5.3.7. + * training by checking that there is no ongoing link training that + * may have started before link parameters were changed, so as to + * avoid LTSSM race as recommended in Implementation Note at the end + * of PCIe r6.1 sec 7.5.3.7. */ - rc = pcie_wait_for_link_status(pdev, use_lt, !use_lt); + rc = pcie_wait_for_link_status(pdev, true, false); if (rc) return rc; @@ -5063,7 +4731,15 @@ int pcie_retrain_link(struct pci_dev *pdev, bool use_lt) pcie_capability_clear_word(pdev, PCI_EXP_LNKCTL, PCI_EXP_LNKCTL_RL); } - return pcie_wait_for_link_status(pdev, use_lt, !use_lt); + rc = pcie_wait_for_link_status(pdev, use_lt, !use_lt); + + /* + * Clear LBMS after a manual retrain so that the bit can be used + * to track link speed or width changes made by hardware itself + * in attempt to correct unreliable link operation. + */ + pcie_reset_lbms_count(pdev); + return rc; } /** @@ -5169,7 +4845,7 @@ static int pci_bus_max_d3cold_delay(const struct pci_bus *bus) */ int pci_bridge_wait_for_secondary_bus(struct pci_dev *dev, char *reset_type) { - struct pci_dev *child; + struct pci_dev *child __free(pci_dev_put) = NULL; int delay; if (pci_dev_is_disconnected(dev)) @@ -5198,8 +4874,8 @@ int pci_bridge_wait_for_secondary_bus(struct pci_dev *dev, char *reset_type) return 0; } - child = list_first_entry(&dev->subordinate->devices, struct pci_dev, - bus_list); + child = pci_dev_get(list_first_entry(&dev->subordinate->devices, + struct pci_dev, bus_list)); up_read(&pci_bus_sem); /* @@ -5299,6 +4975,9 @@ void __weak pcibios_reset_secondary_bus(struct pci_dev *dev) */ int pci_bridge_secondary_bus_reset(struct pci_dev *dev) { + if (!dev->block_cfg_access) + pci_warn_once(dev, "unlocked secondary bus reset via: %pS\n", + __builtin_return_address(0)); pcibios_reset_secondary_bus(dev); return pci_bridge_wait_for_secondary_bus(dev, "bus reset"); @@ -5347,16 +5026,96 @@ static int pci_dev_reset_slot_function(struct pci_dev *dev, bool probe) return pci_reset_hotplug_slot(dev->slot->hotplug, probe); } +static u16 cxl_port_dvsec(struct pci_dev *dev) +{ + return pci_find_dvsec_capability(dev, PCI_VENDOR_ID_CXL, + PCI_DVSEC_CXL_PORT); +} + +static bool cxl_sbr_masked(struct pci_dev *dev) +{ + u16 dvsec, reg; + int rc; + + dvsec = cxl_port_dvsec(dev); + if (!dvsec) + return false; + + rc = pci_read_config_word(dev, dvsec + PCI_DVSEC_CXL_PORT_CTL, ®); + if (rc || PCI_POSSIBLE_ERROR(reg)) + return false; + + /* + * Per CXL spec r3.1, sec 8.1.5.2, when "Unmask SBR" is 0, the SBR + * bit in Bridge Control has no effect. When 1, the Port generates + * hot reset when the SBR bit is set to 1. + */ + if (reg & PCI_DVSEC_CXL_PORT_CTL_UNMASK_SBR) + return false; + + return true; +} + static int pci_reset_bus_function(struct pci_dev *dev, bool probe) { + struct pci_dev *bridge = pci_upstream_bridge(dev); int rc; + /* + * If "dev" is below a CXL port that has SBR control masked, SBR + * won't do anything, so return error. + */ + if (bridge && cxl_sbr_masked(bridge)) { + if (probe) + return 0; + + return -ENOTTY; + } + rc = pci_dev_reset_slot_function(dev, probe); if (rc != -ENOTTY) return rc; return pci_parent_bus_reset(dev, probe); } +static int cxl_reset_bus_function(struct pci_dev *dev, bool probe) +{ + struct pci_dev *bridge; + u16 dvsec, reg, val; + int rc; + + bridge = pci_upstream_bridge(dev); + if (!bridge) + return -ENOTTY; + + dvsec = cxl_port_dvsec(bridge); + if (!dvsec) + return -ENOTTY; + + if (probe) + return 0; + + rc = pci_read_config_word(bridge, dvsec + PCI_DVSEC_CXL_PORT_CTL, ®); + if (rc) + return -ENOTTY; + + if (reg & PCI_DVSEC_CXL_PORT_CTL_UNMASK_SBR) { + val = reg; + } else { + val = reg | PCI_DVSEC_CXL_PORT_CTL_UNMASK_SBR; + pci_write_config_word(bridge, dvsec + PCI_DVSEC_CXL_PORT_CTL, + val); + } + + rc = pci_reset_bus_function(dev, probe); + + if (reg != val) + pci_write_config_word(bridge, dvsec + PCI_DVSEC_CXL_PORT_CTL, + reg); + + return rc; +} + void pci_dev_lock(struct pci_dev *dev) { /* block PM suspend, driver probe, etc. */ @@ -5397,6 +5156,8 @@ static void pci_dev_save_and_disable(struct pci_dev *dev) */ if (err_handler && err_handler->reset_prepare) err_handler->reset_prepare(dev); + else if (dev->driver) + pci_warn(dev, "resetting"); /* * Wake-up device prior to save. PM registers default to D0 after @@ -5430,10 +5191,12 @@ static void pci_dev_restore(struct pci_dev *dev) */ if (err_handler && err_handler->reset_done) err_handler->reset_done(dev); + else if (dev->driver) + pci_warn(dev, "reset done"); } /* dev->reset_methods[] is a 0-terminated list of indices into this array */ -static const struct pci_reset_fn_method pci_reset_fn_methods[] = { +const struct pci_reset_fn_method pci_reset_fn_methods[] = { { }, { pci_dev_specific_reset, .name = "device_specific" }, { pci_dev_acpi_reset, .name = "acpi" }, @@ -5441,128 +5204,7 @@ static const struct pci_reset_fn_method pci_reset_fn_methods[] = { { pci_af_flr, .name = "af_flr" }, { pci_pm_reset, .name = "pm" }, { pci_reset_bus_function, .name = "bus" }, -}; - -static ssize_t reset_method_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct pci_dev *pdev = to_pci_dev(dev); - ssize_t len = 0; - int i, m; - - for (i = 0; i < PCI_NUM_RESET_METHODS; i++) { - m = pdev->reset_methods[i]; - if (!m) - break; - - len += sysfs_emit_at(buf, len, "%s%s", len ? " " : "", - pci_reset_fn_methods[m].name); - } - - if (len) - len += sysfs_emit_at(buf, len, "\n"); - - return len; -} - -static int reset_method_lookup(const char *name) -{ - int m; - - for (m = 1; m < PCI_NUM_RESET_METHODS; m++) { - if (sysfs_streq(name, pci_reset_fn_methods[m].name)) - return m; - } - - return 0; /* not found */ -} - -static ssize_t reset_method_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) -{ - struct pci_dev *pdev = to_pci_dev(dev); - char *options, *name; - int m, n; - u8 reset_methods[PCI_NUM_RESET_METHODS] = { 0 }; - - if (sysfs_streq(buf, "")) { - pdev->reset_methods[0] = 0; - pci_warn(pdev, "All device reset methods disabled by user"); - return count; - } - - if (sysfs_streq(buf, "default")) { - pci_init_reset_methods(pdev); - return count; - } - - options = kstrndup(buf, count, GFP_KERNEL); - if (!options) - return -ENOMEM; - - n = 0; - while ((name = strsep(&options, " ")) != NULL) { - if (sysfs_streq(name, "")) - continue; - - name = strim(name); - - m = reset_method_lookup(name); - if (!m) { - pci_err(pdev, "Invalid reset method '%s'", name); - goto error; - } - - if (pci_reset_fn_methods[m].reset_fn(pdev, PCI_RESET_PROBE)) { - pci_err(pdev, "Unsupported reset method '%s'", name); - goto error; - } - - if (n == PCI_NUM_RESET_METHODS - 1) { - pci_err(pdev, "Too many reset methods\n"); - goto error; - } - - reset_methods[n++] = m; - } - - reset_methods[n] = 0; - - /* Warn if dev-specific supported but not highest priority */ - if (pci_reset_fn_methods[1].reset_fn(pdev, PCI_RESET_PROBE) == 0 && - reset_methods[0] != 1) - pci_warn(pdev, "Device-specific reset disabled/de-prioritized by user"); - memcpy(pdev->reset_methods, reset_methods, sizeof(pdev->reset_methods)); - kfree(options); - return count; - -error: - /* Leave previous methods unchanged */ - kfree(options); - return -EINVAL; -} -static DEVICE_ATTR_RW(reset_method); - -static struct attribute *pci_dev_reset_method_attrs[] = { - &dev_attr_reset_method.attr, - NULL, -}; - -static umode_t pci_dev_reset_method_attr_is_visible(struct kobject *kobj, - struct attribute *a, int n) -{ - struct pci_dev *pdev = to_pci_dev(kobj_to_dev(kobj)); - - if (!pci_reset_supported(pdev)) - return 0; - - return a->mode; -} - -const struct attribute_group pci_dev_reset_method_attr_group = { - .attrs = pci_dev_reset_method_attrs, - .is_visible = pci_dev_reset_method_attr_is_visible, + { cxl_reset_bus_function, .name = "cxl_bus" }, }; /** @@ -5665,11 +5307,20 @@ void pci_init_reset_methods(struct pci_dev *dev) */ int pci_reset_function(struct pci_dev *dev) { + struct pci_dev *bridge; int rc; if (!pci_reset_supported(dev)) return -ENOTTY; + /* + * If there's no upstream bridge, no locking is needed since there is + * no upstream bridge configuration to hold consistent. + */ + bridge = pci_upstream_bridge(dev); + if (bridge) + pci_dev_lock(bridge); + pci_dev_lock(dev); pci_dev_save_and_disable(dev); @@ -5678,6 +5329,9 @@ int pci_reset_function(struct pci_dev *dev) pci_dev_restore(dev); pci_dev_unlock(dev); + if (bridge) + pci_dev_unlock(bridge); + return rc; } EXPORT_SYMBOL_GPL(pci_reset_function); @@ -5764,10 +5418,12 @@ static void pci_bus_lock(struct pci_bus *bus) { struct pci_dev *dev; + pci_dev_lock(bus->self); list_for_each_entry(dev, &bus->devices, bus_list) { - pci_dev_lock(dev); if (dev->subordinate) pci_bus_lock(dev->subordinate); + else + pci_dev_lock(dev); } } @@ -5779,8 +5435,10 @@ static void pci_bus_unlock(struct pci_bus *bus) list_for_each_entry(dev, &bus->devices, bus_list) { if (dev->subordinate) pci_bus_unlock(dev->subordinate); - pci_dev_unlock(dev); + else + pci_dev_unlock(dev); } + pci_dev_unlock(bus->self); } /* Return 1 on successful lock, 0 on contention */ @@ -5788,15 +5446,15 @@ static int pci_bus_trylock(struct pci_bus *bus) { struct pci_dev *dev; + if (!pci_dev_trylock(bus->self)) + return 0; + list_for_each_entry(dev, &bus->devices, bus_list) { - if (!pci_dev_trylock(dev)) - goto unlock; if (dev->subordinate) { - if (!pci_bus_trylock(dev->subordinate)) { - pci_dev_unlock(dev); + if (!pci_bus_trylock(dev->subordinate)) goto unlock; - } - } + } else if (!pci_dev_trylock(dev)) + goto unlock; } return 1; @@ -5804,8 +5462,10 @@ unlock: list_for_each_entry_continue_reverse(dev, &bus->devices, bus_list) { if (dev->subordinate) pci_bus_unlock(dev->subordinate); - pci_dev_unlock(dev); + else + pci_dev_unlock(dev); } + pci_dev_unlock(bus->self); return 0; } @@ -5837,9 +5497,10 @@ static void pci_slot_lock(struct pci_slot *slot) list_for_each_entry(dev, &slot->bus->devices, bus_list) { if (!dev->slot || dev->slot != slot) continue; - pci_dev_lock(dev); if (dev->subordinate) pci_bus_lock(dev->subordinate); + else + pci_dev_lock(dev); } } @@ -5865,14 +5526,13 @@ static int pci_slot_trylock(struct pci_slot *slot) list_for_each_entry(dev, &slot->bus->devices, bus_list) { if (!dev->slot || dev->slot != slot) continue; - if (!pci_dev_trylock(dev)) - goto unlock; if (dev->subordinate) { if (!pci_bus_trylock(dev->subordinate)) { pci_dev_unlock(dev); goto unlock; } - } + } else if (!pci_dev_trylock(dev)) + goto unlock; } return 1; @@ -5883,7 +5543,8 @@ unlock: continue; if (dev->subordinate) pci_bus_unlock(dev->subordinate); - pci_dev_unlock(dev); + else + pci_dev_unlock(dev); } return 0; } @@ -5914,8 +5575,10 @@ static void pci_bus_restore_locked(struct pci_bus *bus) list_for_each_entry(dev, &bus->devices, bus_list) { pci_dev_restore(dev); - if (dev->subordinate) + if (dev->subordinate) { + pci_bridge_wait_for_secondary_bus(dev, "bus reset"); pci_bus_restore_locked(dev->subordinate); + } } } @@ -5949,8 +5612,10 @@ static void pci_slot_restore_locked(struct pci_slot *slot) if (!dev->slot || dev->slot != slot) continue; pci_dev_restore(dev); - if (dev->subordinate) + if (dev->subordinate) { + pci_bridge_wait_for_secondary_bus(dev, "slot reset"); pci_bus_restore_locked(dev->subordinate); + } } } @@ -6095,7 +5760,7 @@ EXPORT_SYMBOL_GPL(pci_probe_reset_bus); * * Same as above except return -EAGAIN if the bus cannot be locked */ -static int __pci_reset_bus(struct pci_bus *bus) +int __pci_reset_bus(struct pci_bus *bus) { int rc; @@ -6342,24 +6007,7 @@ int pcie_link_speed_mbps(struct pci_dev *pdev) if (err) return err; - switch (to_pcie_link_speed(lnksta)) { - case PCIE_SPEED_2_5GT: - return 2500; - case PCIE_SPEED_5_0GT: - return 5000; - case PCIE_SPEED_8_0GT: - return 8000; - case PCIE_SPEED_16_0GT: - return 16000; - case PCIE_SPEED_32_0GT: - return 32000; - case PCIE_SPEED_64_0GT: - return 64000; - default: - break; - } - - return -EINVAL; + return pcie_dev_speed_mbps(to_pcie_link_speed(lnksta)); } EXPORT_SYMBOL(pcie_link_speed_mbps); @@ -6421,38 +6069,66 @@ u32 pcie_bandwidth_available(struct pci_dev *dev, struct pci_dev **limiting_dev, EXPORT_SYMBOL(pcie_bandwidth_available); /** - * pcie_get_speed_cap - query for the PCI device's link speed capability + * pcie_get_supported_speeds - query Supported Link Speed Vector * @dev: PCI device to query * - * Query the PCI device speed capability. Return the maximum link speed - * supported by the device. + * Query @dev supported link speeds. + * + * Implementation Note in PCIe r6.0 sec 7.5.3.18 recommends determining + * supported link speeds using the Supported Link Speeds Vector in the Link + * Capabilities 2 Register (when available). + * + * Link Capabilities 2 was added in PCIe r3.0, sec 7.8.18. + * + * Without Link Capabilities 2, i.e., prior to PCIe r3.0, Supported Link + * Speeds field in Link Capabilities is used and only 2.5 GT/s and 5.0 GT/s + * speeds were defined. + * + * For @dev without Supported Link Speed Vector, the field is synthesized + * from the Max Link Speed field in the Link Capabilities Register. + * + * Return: Supported Link Speeds Vector (+ reserved 0 at LSB). */ -enum pci_bus_speed pcie_get_speed_cap(struct pci_dev *dev) +u8 pcie_get_supported_speeds(struct pci_dev *dev) { u32 lnkcap2, lnkcap; + u8 speeds; /* - * Link Capabilities 2 was added in PCIe r3.0, sec 7.8.18. The - * implementation note there recommends using the Supported Link - * Speeds Vector in Link Capabilities 2 when supported. - * - * Without Link Capabilities 2, i.e., prior to PCIe r3.0, software - * should use the Supported Link Speeds field in Link Capabilities, - * where only 2.5 GT/s and 5.0 GT/s speeds were defined. + * Speeds retain the reserved 0 at LSB before PCIe Supported Link + * Speeds Vector to allow using SLS Vector bit defines directly. */ pcie_capability_read_dword(dev, PCI_EXP_LNKCAP2, &lnkcap2); + speeds = lnkcap2 & PCI_EXP_LNKCAP2_SLS; + + /* Ignore speeds higher than Max Link Speed */ + pcie_capability_read_dword(dev, PCI_EXP_LNKCAP, &lnkcap); + speeds &= GENMASK(lnkcap & PCI_EXP_LNKCAP_SLS, 0); /* PCIe r3.0-compliant */ - if (lnkcap2) - return PCIE_LNKCAP2_SLS2SPEED(lnkcap2); + if (speeds) + return speeds; - pcie_capability_read_dword(dev, PCI_EXP_LNKCAP, &lnkcap); + /* Synthesize from the Max Link Speed field */ if ((lnkcap & PCI_EXP_LNKCAP_SLS) == PCI_EXP_LNKCAP_SLS_5_0GB) - return PCIE_SPEED_5_0GT; + speeds = PCI_EXP_LNKCAP2_SLS_5_0GB | PCI_EXP_LNKCAP2_SLS_2_5GB; else if ((lnkcap & PCI_EXP_LNKCAP_SLS) == PCI_EXP_LNKCAP_SLS_2_5GB) - return PCIE_SPEED_2_5GT; + speeds = PCI_EXP_LNKCAP2_SLS_2_5GB; + + return speeds; +} - return PCI_SPEED_UNKNOWN; +/** + * pcie_get_speed_cap - query for the PCI device's link speed capability + * @dev: PCI device to query + * + * Query the PCI device speed capability. + * + * Return: the maximum link speed supported by the device. + */ +enum pci_bus_speed pcie_get_speed_cap(struct pci_dev *dev) +{ + return PCIE_LNKCAP2_SLS2SPEED(dev->supported_speeds); } EXPORT_SYMBOL(pcie_get_speed_cap); @@ -6485,8 +6161,9 @@ EXPORT_SYMBOL(pcie_get_width_cap); * and width, multiplying them, and applying encoding overhead. The result * is in Mb/s, i.e., megabits/second of raw bandwidth. */ -u32 pcie_bandwidth_capable(struct pci_dev *dev, enum pci_bus_speed *speed, - enum pcie_link_width *width) +static u32 pcie_bandwidth_capable(struct pci_dev *dev, + enum pci_bus_speed *speed, + enum pcie_link_width *width) { *speed = pcie_get_speed_cap(dev); *width = pcie_get_width_cap(dev); @@ -6880,8 +6557,7 @@ static void pci_request_resource_alignment(struct pci_dev *dev, int bar, } else { r->flags &= ~IORESOURCE_SIZEALIGN; r->flags |= IORESOURCE_STARTALIGN; - r->start = align; - r->end = r->start + size - 1; + resource_set_range(r, align, size); } r->flags |= IORESOURCE_UNSET; } @@ -7060,16 +6736,16 @@ static int of_pci_bus_find_domain_nr(struct device *parent) return ida_alloc(&pci_domain_nr_dynamic_ida, GFP_KERNEL); } -static void of_pci_bus_release_domain_nr(struct pci_bus *bus, struct device *parent) +static void of_pci_bus_release_domain_nr(struct device *parent, int domain_nr) { - if (bus->domain_nr < 0) + if (domain_nr < 0) return; /* Release domain from IDA where it was allocated. */ - if (of_get_pci_domain_nr(parent->of_node) == bus->domain_nr) - ida_free(&pci_domain_nr_static_ida, bus->domain_nr); + if (of_get_pci_domain_nr(parent->of_node) == domain_nr) + ida_free(&pci_domain_nr_static_ida, domain_nr); else - ida_free(&pci_domain_nr_dynamic_ida, bus->domain_nr); + ida_free(&pci_domain_nr_dynamic_ida, domain_nr); } int pci_bus_find_domain_nr(struct pci_bus *bus, struct device *parent) @@ -7078,11 +6754,11 @@ int pci_bus_find_domain_nr(struct pci_bus *bus, struct device *parent) acpi_pci_bus_find_domain_nr(bus); } -void pci_bus_release_domain_nr(struct pci_bus *bus, struct device *parent) +void pci_bus_release_domain_nr(struct device *parent, int domain_nr) { if (!acpi_disabled) return; - of_pci_bus_release_domain_nr(bus, parent); + of_pci_bus_release_domain_nr(parent, domain_nr); } #endif @@ -7127,6 +6803,8 @@ static int __init pci_setup(char *str) pci_no_domains(); } else if (!strncmp(str, "noari", 5)) { pcie_ari_disabled = true; + } else if (!strncmp(str, "notph", 5)) { + pci_no_tph(); } else if (!strncmp(str, "cbiosize=", 9)) { pci_cardbus_io_size = memparse(str + 9, &str); } else if (!strncmp(str, "cbmemsize=", 10)) { @@ -7161,6 +6839,8 @@ static int __init pci_setup(char *str) pci_add_flags(PCI_SCAN_ALL_PCIE_DEVS); } else if (!strncmp(str, "disable_acs_redir=", 18)) { disable_acs_redir_param = str + 18; + } else if (!strncmp(str, "config_acs=", 11)) { + config_acs_param = str + 11; } else { pr_err("PCI: Unknown option `%s'\n", str); } @@ -7185,6 +6865,7 @@ static int __init pci_realloc_setup_params(void) resource_alignment_param = kstrdup(resource_alignment_param, GFP_KERNEL); disable_acs_redir_param = kstrdup(disable_acs_redir_param, GFP_KERNEL); + config_acs_param = kstrdup(config_acs_param, GFP_KERNEL); return 0; } |