diff options
Diffstat (limited to 'drivers/pci/pci.c')
| -rw-r--r-- | drivers/pci/pci.c | 2156 |
1 files changed, 971 insertions, 1185 deletions
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index fba95486caaf..13dbb405dc31 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> @@ -64,6 +62,21 @@ struct pci_pme_device { #define PME_TIMEOUT 1000 /* How long between PME checks */ +/* + * Following exit from Conventional Reset, devices must be ready within 1 sec + * (PCIe r6.0 sec 6.6.1). A D3cold to D0 transition implies a Conventional + * Reset (PCIe r6.0 sec 5.8). + */ +#define PCI_RESET_WAIT 1000 /* msec */ + +/* + * Devices may extend the 1 sec period through Request Retry Status + * completions (PCIe r6.0 sec 2.3.1). The spec does not provide an upper + * limit, but 60 sec ought to be enough for any device to become + * responsive. + */ +#define PCIE_RESET_READY_POLL_MS 60000 /* msec */ + static void pci_dev_d3_sleep(struct pci_dev *dev) { unsigned int delay_ms = max(dev->d3hot_delay, pci_pm_d3hot_delay); @@ -128,8 +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 @@ -167,9 +180,6 @@ static int __init pcie_port_pm_setup(char *str) } __setup("pcie_port_pm=", pcie_port_pm_setup); -/* Time to wait after a reset for device to become responsive */ -#define PCIE_RESET_READY_POLL_MS 60000 - /** * pci_bus_max_busnr - returns maximum PCI bus number of given bus' children * @bus: pointer to PCI bus structure to search @@ -413,36 +423,10 @@ found: return 1; } -static u8 __pci_find_next_cap_ttl(struct pci_bus *bus, unsigned int devfn, - u8 pos, int cap, int *ttl) -{ - u8 id; - u16 ent; - - pci_bus_read_config_byte(bus, devfn, pos, &pos); - - while ((*ttl)--) { - if (pos < 0x40) - break; - pos &= ~3; - pci_bus_read_config_word(bus, devfn, pos, &ent); - - id = ent & 0xff; - if (id == 0xff) - break; - if (id == cap) - return pos; - pos = (ent >> 8); - } - return 0; -} - static u8 __pci_find_next_cap(struct pci_bus *bus, unsigned int devfn, u8 pos, int cap) { - int ttl = PCI_FIND_CAP_TTL; - - return __pci_find_next_cap_ttl(bus, devfn, pos, cap, &ttl); + return PCI_FIND_NEXT_CAP(pci_bus_read_config, pos, cap, bus, devfn); } u8 pci_find_next_capability(struct pci_dev *dev, u8 pos, int cap) @@ -522,7 +506,7 @@ u8 pci_bus_find_capability(struct pci_bus *bus, unsigned int devfn, int cap) pci_bus_read_config_byte(bus, devfn, PCI_HEADER_TYPE, &hdr_type); - pos = __pci_bus_find_cap_start(bus, devfn, hdr_type & 0x7f); + pos = __pci_bus_find_cap_start(bus, devfn, hdr_type & PCI_HEADER_TYPE_MASK); if (pos) pos = __pci_find_next_cap(bus, devfn, pos, cap); @@ -543,42 +527,11 @@ EXPORT_SYMBOL(pci_bus_find_capability); */ u16 pci_find_next_ext_capability(struct pci_dev *dev, u16 start, int cap) { - u32 header; - int ttl; - u16 pos = PCI_CFG_SPACE_SIZE; - - /* minimum 8 bytes per capability */ - ttl = (PCI_CFG_SPACE_EXP_SIZE - PCI_CFG_SPACE_SIZE) / 8; - if (dev->cfg_size <= PCI_CFG_SPACE_SIZE) return 0; - if (start) - pos = start; - - if (pci_read_config_dword(dev, pos, &header) != PCIBIOS_SUCCESSFUL) - return 0; - - /* - * If we have no capabilities, this is indicated by cap ID, - * cap version and next pointer all being 0. - */ - if (header == 0) - return 0; - - while (ttl-- > 0) { - if (PCI_EXT_CAP_ID(header) == cap && pos != start) - return pos; - - pos = PCI_EXT_CAP_NEXT(header); - if (pos < PCI_CFG_SPACE_SIZE) - break; - - if (pci_read_config_dword(dev, pos, &header) != PCIBIOS_SUCCESSFUL) - break; - } - - return 0; + return PCI_FIND_NEXT_EXT_CAP(pci_bus_read_config, start, cap, + dev->bus, dev->devfn); } EXPORT_SYMBOL_GPL(pci_find_next_ext_capability); @@ -638,7 +591,7 @@ EXPORT_SYMBOL_GPL(pci_get_dsn); static u8 __pci_find_next_ht_cap(struct pci_dev *dev, u8 pos, int ht_cap) { - int rc, ttl = PCI_FIND_CAP_TTL; + int rc; u8 cap, mask; if (ht_cap == HT_CAPTYPE_SLAVE || ht_cap == HT_CAPTYPE_HOST) @@ -646,8 +599,8 @@ static u8 __pci_find_next_ht_cap(struct pci_dev *dev, u8 pos, int ht_cap) else mask = HT_5BIT_CAP_MASK; - pos = __pci_find_next_cap_ttl(dev->bus, dev->devfn, pos, - PCI_CAP_ID_HT, &ttl); + pos = PCI_FIND_NEXT_CAP(pci_bus_read_config, pos, + PCI_CAP_ID_HT, dev->bus, dev->devfn); while (pos) { rc = pci_read_config_byte(dev, pos + 3, &cap); if (rc != PCIBIOS_SUCCESSFUL) @@ -656,9 +609,10 @@ static u8 __pci_find_next_ht_cap(struct pci_dev *dev, u8 pos, int ht_cap) if ((cap & mask) == ht_cap) return pos; - pos = __pci_find_next_cap_ttl(dev->bus, dev->devfn, - pos + PCI_CAP_LIST_NEXT, - PCI_CAP_ID_HT, &ttl); + pos = PCI_FIND_NEXT_CAP(pci_bus_read_config, + pos + PCI_CAP_LIST_NEXT, + PCI_CAP_ID_HT, dev->bus, + dev->devfn); } return 0; @@ -720,15 +674,18 @@ u16 pci_find_vsec_capability(struct pci_dev *dev, u16 vendor, int cap) { u16 vsec = 0; u32 header; + int ret; if (vendor != dev->vendor) return 0; while ((vsec = pci_find_next_ext_capability(dev, vsec, PCI_EXT_CAP_ID_VNDR))) { - if (pci_read_config_dword(dev, vsec + PCI_VNDR_HEADER, - &header) == PCIBIOS_SUCCESSFUL && - PCI_VNDR_HEADER_ID(header) == cap) + ret = pci_read_config_dword(dev, vsec + PCI_VNDR_HEADER, &header); + if (ret != PCIBIOS_SUCCESSFUL) + continue; + + if (PCI_VNDR_HEADER_ID(header) == cap) return vsec; } @@ -782,9 +739,8 @@ struct resource *pci_find_parent_resource(const struct pci_dev *dev, { const struct pci_bus *bus = dev->bus; struct resource *r; - int i; - pci_bus_for_each_resource(bus, r, i) { + pci_bus_for_each_resource(bus, r) { if (!r) continue; if (resource_contains(r, res)) { @@ -837,6 +793,66 @@ struct resource *pci_find_resource(struct pci_dev *dev, struct resource *res) EXPORT_SYMBOL(pci_find_resource); /** + * pci_resource_name - Return the name of the PCI resource + * @dev: PCI device to query + * @i: index of the resource + * + * Return the standard PCI resource (BAR) name according to their index. + */ +const char *pci_resource_name(struct pci_dev *dev, unsigned int i) +{ + static const char * const bar_name[] = { + "BAR 0", + "BAR 1", + "BAR 2", + "BAR 3", + "BAR 4", + "BAR 5", + "ROM", +#ifdef CONFIG_PCI_IOV + "VF BAR 0", + "VF BAR 1", + "VF BAR 2", + "VF BAR 3", + "VF BAR 4", + "VF BAR 5", +#endif + "bridge window", /* "io" included in %pR */ + "bridge window", /* "mem" included in %pR */ + "bridge window", /* "mem pref" included in %pR */ + }; + static const char * const cardbus_name[] = { + "BAR 1", + "unknown", + "unknown", + "unknown", + "unknown", + "unknown", +#ifdef CONFIG_PCI_IOV + "unknown", + "unknown", + "unknown", + "unknown", + "unknown", + "unknown", +#endif + "CardBus bridge window 0", /* I/O */ + "CardBus bridge window 1", /* I/O */ + "CardBus bridge window 0", /* mem */ + "CardBus bridge window 1", /* mem */ + }; + + if (dev->hdr_type == PCI_HEADER_TYPE_CARDBUS && + i < ARRAY_SIZE(cardbus_name)) + return cardbus_name[i]; + + if (i < ARRAY_SIZE(bar_name)) + return bar_name[i]; + + return "unknown"; +} + +/** * pci_wait_for_pending - wait for @mask bit(s) to clear in status word @pos * @dev: the PCI device to operate on * @pos: config space offset of status word @@ -873,30 +889,71 @@ 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, const u16 acs_mask, const u16 acs_flags) { + u16 flags = acs_flags; + u16 mask = acs_mask; + 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 (!acs_mask) { + /* Check for ACS flags */ + delimit = strstr(p, "@"); + if (delimit) { + int end; + u32 shift = 0; + + end = delimit - p - 1; + mask = 0; + flags = 0; + + 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 */ @@ -916,56 +973,42 @@ 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_dbg(dev, "ACS mask = %#06x\n", mask); + pci_dbg(dev, "ACS flags = %#06x\n", flags); + pci_dbg(dev, "ACS control = %#06x\n", caps->ctrl); + pci_dbg(dev, "ACS fw_ctrl = %#06x\n", caps->fw_ctrl); - 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_write_config_word(dev, pos + PCI_ACS_CTRL, ctrl); + /* + * For mask bits that are 0, copy them from the firmware setting + * and apply flags for all the mask bits that are 1. + */ + caps->ctrl = (caps->fw_ctrl & ~mask) | (flags & mask); - 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); } /** @@ -974,23 +1017,37 @@ 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); } /** @@ -1152,40 +1209,82 @@ void pci_resume_bus(struct pci_bus *bus) static int pci_dev_wait(struct pci_dev *dev, char *reset_type, int timeout) { int delay = 1; - u32 id; + bool retrain = false; + struct pci_dev *root, *bridge; + + root = pcie_find_root_port(dev); + + if (pci_is_pcie(dev)) { + bridge = pci_upstream_bridge(dev); + if (bridge) + retrain = true; + } /* - * 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. */ - pci_read_config_dword(dev, PCI_COMMAND, &id); - while (PCI_POSSIBLE_ERROR(id)) { + for (;;) { + u32 id; + + 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", delay - 1, reset_type); return -ENOTTY; } - if (delay > 1000) + if (delay > PCI_RESET_WAIT) { + if (retrain) { + retrain = false; + if (pcie_failed_link_retrain(bridge) == 0) { + delay = 1; + continue; + } + } 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) + if (delay > PCI_RESET_WAIT) pci_info(dev, "ready %dms after %s\n", delay - 1, reset_type); + else + pci_dbg(dev, "ready %dms after %s\n", delay - 1, + reset_type); return 0; } @@ -1196,6 +1295,10 @@ static int pci_dev_wait(struct pci_dev *dev, char *reset_type, int timeout) * * On success, return 0 or 1, depending on whether or not it is necessary to * restore the device's BARs subsequently (1 is returned in that case). + * + * On failure, return a negative error code. Always return failure if @dev + * lacks a Power Management Capability, even if the platform was able to + * put the device in D0 via non-PCI means. */ int pci_power_up(struct pci_dev *dev) { @@ -1212,9 +1315,11 @@ int pci_power_up(struct pci_dev *dev) else dev->current_state = state; - if (state == PCI_D0) - return 0; + return -EIO; + } + if (pci_dev_is_disconnected(dev)) { + dev->current_state = PCI_D3cold; return -EIO; } @@ -1257,23 +1362,28 @@ end: /** * pci_set_full_power_state - Put a PCI device into D0 and update its state * @dev: PCI device to power up + * @locked: whether pci_bus_sem is held * * Call pci_power_up() to put @dev into D0, read from its PCI_PM_CTRL register * to confirm the state change, restore its BARs if they might be lost and - * reconfigure ASPM in acordance with the new power state. + * reconfigure ASPM in accordance with the new power state. * * If pci_restore_state() is going to be called right after a power state change * to D0, it is more efficient to use pci_power_up() directly instead of this * function. */ -static int pci_set_full_power_state(struct pci_dev *dev) +static int pci_set_full_power_state(struct pci_dev *dev, bool locked) { u16 pmcsr; int ret; ret = pci_power_up(dev); - if (ret < 0) + if (ret < 0) { + if (dev->current_state == PCI_D0) + return 0; + return ret; + } pci_read_config_word(dev, dev->pm_cap + PCI_PM_CTRL, &pmcsr); dev->current_state = pmcsr & PCI_PM_CTRL_STATE_MASK; @@ -1297,6 +1407,9 @@ static int pci_set_full_power_state(struct pci_dev *dev) pci_restore_bars(dev); } + if (dev->bus->self) + pcie_aspm_pm_state_change(dev->bus->self, locked); + return 0; } @@ -1324,10 +1437,22 @@ void pci_bus_set_current_state(struct pci_bus *bus, pci_power_t state) pci_walk_bus(bus, __pci_dev_set_current_state, &state); } +static void __pci_bus_set_current_state(struct pci_bus *bus, pci_power_t state, bool locked) +{ + if (!bus) + return; + + if (locked) + pci_walk_bus_locked(bus, __pci_dev_set_current_state, &state); + else + pci_walk_bus(bus, __pci_dev_set_current_state, &state); +} + /** * pci_set_low_power_state - Put a PCI device into a low-power state. * @dev: PCI device to handle. * @state: PCI power state (D1, D2, D3hot) to put the device into. + * @locked: whether pci_bus_sem is held * * Use the device's PCI_PM_CTRL register to put it into a low-power state. * @@ -1338,7 +1463,7 @@ void pci_bus_set_current_state(struct pci_bus *bus, pci_power_t state) * 0 if device already is in the requested state. * 0 if device's power state has been successfully changed. */ -static int pci_set_low_power_state(struct pci_dev *dev, pci_power_t state) +static int pci_set_low_power_state(struct pci_dev *dev, pci_power_t state, bool locked) { u16 pmcsr; @@ -1391,27 +1516,13 @@ static int pci_set_low_power_state(struct pci_dev *dev, pci_power_t state) pci_power_name(dev->current_state), pci_power_name(state)); + if (dev->bus->self) + pcie_aspm_pm_state_change(dev->bus->self, locked); + return 0; } -/** - * 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. - * - * Transition a device to a new power state, using the platform firmware and/or - * the device's PCI PM registers. - * - * RETURN VALUE: - * -EINVAL if the requested state is invalid. - * -EIO if device does not support PCI PM or its PM capabilities register has a - * wrong version, or device doesn't support the requested state. - * 0 if the transition is to D1 or D2 but D1 and D2 are not supported. - * 0 if device already is in the requested state. - * 0 if the transition is to D3 but D3 is not supported. - * 0 if device's power state has been successfully changed. - */ -int pci_set_power_state(struct pci_dev *dev, pci_power_t state) +static int __pci_set_power_state(struct pci_dev *dev, pci_power_t state, bool locked) { int error; @@ -1435,7 +1546,7 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state) return 0; if (state == PCI_D0) - return pci_set_full_power_state(dev); + return pci_set_full_power_state(dev, locked); /* * This device is quirked not to be put into D3, so don't put it in @@ -1449,16 +1560,16 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state) * To put the device in D3cold, put it into D3hot in the native * way, then put it into D3cold using platform ops. */ - error = pci_set_low_power_state(dev, PCI_D3hot); + error = pci_set_low_power_state(dev, PCI_D3hot, locked); if (pci_platform_power_transition(dev, PCI_D3cold)) return error; /* Powering off a bridge may power off the whole hierarchy */ if (dev->current_state == PCI_D3cold) - pci_bus_set_current_state(dev->subordinate, PCI_D3cold); + __pci_bus_set_current_state(dev->subordinate, PCI_D3cold, locked); } else { - error = pci_set_low_power_state(dev, state); + error = pci_set_low_power_state(dev, state, locked); if (pci_platform_power_transition(dev, state)) return error; @@ -1466,8 +1577,38 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state) return 0; } + +/** + * 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. + * + * Transition a device to a new power state, using the platform firmware and/or + * the device's PCI PM registers. + * + * RETURN VALUE: + * -EINVAL if the requested state is invalid. + * -EIO if device does not support PCI PM or its PM capabilities register has a + * wrong version, or device doesn't support the requested state. + * 0 if the transition is to D1 or D2 but D1 and D2 are not supported. + * 0 if device already is in the requested state. + * 0 if the transition is to D3 but D3 is not supported. + * 0 if device's power state has been successfully changed. + */ +int pci_set_power_state(struct pci_dev *dev, pci_power_t state) +{ + return __pci_set_power_state(dev, state, false); +} EXPORT_SYMBOL(pci_set_power_state); +int pci_set_power_state_locked(struct pci_dev *dev, pci_power_t state) +{ + lockdep_assert_held(&pci_bus_sem); + + return __pci_set_power_state(dev, state, true); +} +EXPORT_SYMBOL(pci_set_power_state_locked); + #define PCI_EXP_SAVE_REGS 7 static struct pci_cap_saved_state *_pci_find_saved_cap(struct pci_dev *pci_dev, @@ -1516,25 +1657,10 @@ 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) @@ -1543,6 +1669,13 @@ 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; @@ -1600,46 +1733,6 @@ 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 @@ -1651,7 +1744,7 @@ int pci_save_state(struct pci_dev *dev) /* XXX: 100% dword access ok here? */ for (i = 0; i < 16; i++) { pci_read_config_dword(dev, i * 4, &dev->saved_config_space[i]); - pci_dbg(dev, "saving config space at offset %#x (reading %#x)\n", + pci_dbg(dev, "save config %#04x: %#010x\n", i * 4, dev->saved_config_space[i]); } dev->state_saved = true; @@ -1664,11 +1757,10 @@ int pci_save_state(struct pci_dev *dev) if (i != 0) return i; - pci_save_ltr_state(dev); - pci_save_aspm_l1ss_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); @@ -1683,7 +1775,7 @@ static void pci_restore_config_dword(struct pci_dev *pdev, int offset, return; for (;;) { - pci_dbg(pdev, "restoring config space at offset %#x (was %#x, writing %#x)\n", + pci_dbg(pdev, "restore config %#04x: %#010x -> %#010x\n", offset, val, saved_val); pci_write_config_dword(pdev, offset, saved_val); if (retry-- <= 0) @@ -1731,49 +1823,12 @@ static void pci_restore_config_space(struct pci_dev *pdev) } } -static void pci_restore_rebar_state(struct pci_dev *pdev) -{ - unsigned int pos, nbars, i; - u32 ctrl; - - pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_REBAR); - if (!pos) - return; - - pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl); - nbars = (ctrl & PCI_REBAR_CTRL_NBAR_MASK) >> - PCI_REBAR_CTRL_NBAR_SHIFT; - - for (i = 0; i < nbars; i++, pos += 8) { - struct resource *res; - int bar_idx, size; - - pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl); - bar_idx = ctrl & PCI_REBAR_CTRL_BAR_IDX; - res = pdev->resource + bar_idx; - size = pci_rebar_bytes_to_size(resource_size(res)); - ctrl &= ~PCI_REBAR_CTRL_BAR_SIZE; - ctrl |= size << PCI_REBAR_CTRL_BAR_SHIFT; - pci_write_config_dword(pdev, pos + PCI_REBAR_CTRL, ctrl); - } -} - /** * pci_restore_state - Restore the saved state of a PCI device * @dev: PCI device that we're dealing with */ 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_aspm_l1ss_state(dev); - pci_restore_pcie_state(dev); pci_restore_pasid_state(dev); pci_restore_pri_state(dev); @@ -1782,6 +1837,7 @@ 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); @@ -1902,6 +1958,28 @@ 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; @@ -1917,9 +1995,13 @@ 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) @@ -1934,6 +2016,12 @@ static int do_pci_enable_device(struct pci_dev *dev, int bars) } return 0; + +err_enable: + pci_host_bridge_disable_device(dev); + + return err; + } /** @@ -2009,20 +2097,6 @@ 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 * @@ -2054,107 +2128,6 @@ 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 * @@ -2188,17 +2161,6 @@ 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; @@ -2237,18 +2199,14 @@ 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; @@ -2387,25 +2345,41 @@ static void pci_pme_list_scan(struct work_struct *work) mutex_lock(&pci_pme_list_mutex); list_for_each_entry_safe(pme_dev, n, &pci_pme_list, list) { - if (pme_dev->dev->pme_poll) { - struct pci_dev *bridge; + struct pci_dev *pdev = pme_dev->dev; + + if (pdev->pme_poll) { + struct pci_dev *bridge = pdev->bus->self; + struct device *dev = &pdev->dev; + struct device *bdev = bridge ? &bridge->dev : NULL; + int bref = 0; - bridge = pme_dev->dev->bus->self; /* - * If bridge is in low power state, the - * configuration space of subordinate devices - * may be not accessible + * If we have a bridge, it should be in an active/D0 + * state or the configuration space of subordinate + * devices may not be accessible or stable over the + * course of the call. */ - if (bridge && bridge->current_state != PCI_D0) - continue; + if (bdev) { + bref = pm_runtime_get_if_active(bdev); + if (!bref) + continue; + + if (bridge->current_state != PCI_D0) + goto put_bridge; + } + /* - * If the device is in D3cold it should not be - * polled either. + * The device itself should be suspended but config + * space must be accessible, therefore it cannot be in + * D3cold. */ - if (pme_dev->dev->current_state == PCI_D3cold) - continue; + if (pm_runtime_suspended(dev) && + pdev->current_state != PCI_D3cold) + pci_pme_wakeup(pdev, NULL); - pci_pme_wakeup(pme_dev->dev, NULL); +put_bridge: + if (bref > 0) + pm_runtime_put(bdev); } else { list_del(&pme_dev->list); kfree(pme_dev); @@ -2947,13 +2921,25 @@ static const struct dmi_system_id bridge_d3_blacklist[] = { { /* * Downstream device is not accessible after putting a root port - * into D3cold and back into D0 on Elo i2. + * into D3cold and back into D0 on Elo Continental Z2 board */ - .ident = "Elo i2", + .ident = "Elo Continental Z2", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Elo Touch Solutions"), - DMI_MATCH(DMI_PRODUCT_NAME, "Elo i2"), - DMI_MATCH(DMI_PRODUCT_VERSION, "RevB"), + DMI_MATCH(DMI_BOARD_VENDOR, "Elo Touch Solutions"), + DMI_MATCH(DMI_BOARD_NAME, "Geminilake"), + 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 @@ -2964,8 +2950,12 @@ static const struct dmi_system_id bridge_d3_blacklist[] = { * pci_bridge_d3_possible - Is it possible to put the bridge into D3 * @bridge: Bridge to check * - * This function checks if it is possible to move the bridge to D3. - * Currently we only allow D3 for recent enough PCIe ports and Thunderbolt. + * Currently we only allow D3 for some PCIe ports and for Thunderbolt. + * + * Return: Whether it is possible to move the bridge to D3. + * + * The return value is guaranteed to be constant across the entire lifetime + * of the bridge, including its hot-removal. */ bool pci_bridge_d3_possible(struct pci_dev *bridge) { @@ -2980,10 +2970,14 @@ bool pci_bridge_d3_possible(struct pci_dev *bridge) return false; /* - * Hotplug ports handled by firmware in System Management Mode - * may not be put into D3 by the OS (Thunderbolt on non-Macs). + * Hotplug ports handled by platform firmware may not be put + * into D3 by the OS, e.g. ACPI slots ... */ - if (bridge->is_hotplug_bridge && !pciehp_is_native(bridge)) + if (bridge->is_hotplug_bridge && !bridge->is_pciehp) + return false; + + /* ... or PCIe hotplug ports not handled natively by the OS. */ + if (bridge->is_pciehp && !pciehp_is_native(bridge)) return false; if (pci_bridge_d3_force) @@ -3002,17 +2996,17 @@ bool pci_bridge_d3_possible(struct pci_dev *bridge) * by vendors for runtime D3 at least until 2018 because there * was no OS support. */ - if (bridge->is_hotplug_bridge) + if (bridge->is_pciehp) return false; if (dmi_check_system(bridge_d3_blacklist)) return false; /* - * It should be safe to put PCIe ports from 2015 or newer - * to D3. + * Out of caution, we only allow PCIe ports from 2015 or newer + * into D3 on x86. */ - if (dmi_get_bios_year() >= 2015) + if (!IS_ENABLED(CONFIG_X86) || dmi_get_bios_year() >= 2015) return true; break; } @@ -3126,6 +3120,12 @@ void pci_d3cold_disable(struct pci_dev *dev) } EXPORT_SYMBOL_GPL(pci_d3cold_disable); +void pci_pm_power_up_and_verify_state(struct pci_dev *pci_dev) +{ + pci_power_up(pci_dev); + pci_update_current_state(pci_dev, PCI_D0); +} + /** * pci_pm_init - Initialize PM functions of given PCI device * @dev: PCI device to handle. @@ -3133,12 +3133,8 @@ EXPORT_SYMBOL_GPL(pci_d3cold_disable); void pci_pm_init(struct pci_dev *dev) { int pm; - u16 status; u16 pmc; - pm_runtime_forbid(&dev->dev); - pm_runtime_set_active(&dev->dev); - pm_runtime_enable(&dev->dev); device_enable_async_suspend(&dev->dev); dev->wakeup_prepared = false; @@ -3148,14 +3144,14 @@ void pci_pm_init(struct pci_dev *dev) /* find PCI PM capability in list */ pm = pci_find_capability(dev, PCI_CAP_ID_PM); if (!pm) - return; + goto poweron; /* Check device's ability to generate PME# */ pci_read_config_word(dev, pm + PCI_PM_PMC, &pmc); if ((pmc & PCI_PM_CAP_VER_MASK) > 3) { pci_err(dev, "unsupported PM cap regs version (%u)\n", pmc & PCI_PM_CAP_VER_MASK); - return; + goto poweron; } dev->pm_cap = pm; @@ -3186,7 +3182,7 @@ void pci_pm_init(struct pci_dev *dev) (pmc & PCI_PM_CAP_PME_D2) ? " D2" : "", (pmc & PCI_PM_CAP_PME_D3hot) ? " D3hot" : "", (pmc & PCI_PM_CAP_PME_D3cold) ? " D3cold" : ""); - dev->pme_support = pmc >> PCI_PM_CAP_PME_SHIFT; + dev->pme_support = FIELD_GET(PCI_PM_CAP_PME_MASK, pmc); dev->pme_poll = true; /* * Make device's PM flags reflect the wake-up capability, but @@ -3197,9 +3193,11 @@ void pci_pm_init(struct pci_dev *dev) pci_pme_active(dev, false); } - pci_read_config_word(dev, PCI_STATUS, &status); - if (status & PCI_STATUS_IMM_READY) - dev->imm_ready = 1; +poweron: + pci_pm_power_up_and_verify_state(dev); + pm_runtime_forbid(&dev->dev); + pm_runtime_set_active(&dev->dev); + pm_runtime_enable(&dev->dev); } static unsigned long pci_ea_flags(struct pci_dev *dev, u8 prop) @@ -3246,6 +3244,7 @@ static struct resource *pci_ea_get_resource(struct pci_dev *dev, u8 bei, static int pci_ea_read(struct pci_dev *dev, int offset) { struct resource *res; + const char *res_name; int ent_size, ent_offset = offset; resource_size_t start, end; unsigned long flags; @@ -3257,24 +3256,25 @@ static int pci_ea_read(struct pci_dev *dev, int offset) ent_offset += 4; /* Entry size field indicates DWORDs after 1st */ - ent_size = ((dw0 & PCI_EA_ES) + 1) << 2; + ent_size = (FIELD_GET(PCI_EA_ES, dw0) + 1) << 2; if (!(dw0 & PCI_EA_ENABLE)) /* Entry not enabled */ goto out; - bei = (dw0 & PCI_EA_BEI) >> 4; - prop = (dw0 & PCI_EA_PP) >> 8; + bei = FIELD_GET(PCI_EA_BEI, dw0); + prop = FIELD_GET(PCI_EA_PP, dw0); /* * If the Property is in the reserved range, try the Secondary * Property instead. */ if (prop > PCI_EA_P_BRIDGE_IO && prop < PCI_EA_P_MEM_RESERVED) - prop = (dw0 & PCI_EA_SP) >> 16; + prop = FIELD_GET(PCI_EA_SP, dw0); if (prop > PCI_EA_P_BRIDGE_IO) goto out; res = pci_ea_get_resource(dev, bei, prop); + res_name = pci_resource_name(dev, bei); if (!res) { pci_err(dev, "Unsupported EA entry BEI: %u\n", bei); goto out; @@ -3348,16 +3348,16 @@ static int pci_ea_read(struct pci_dev *dev, int offset) res->flags = flags; if (bei <= PCI_EA_BEI_BAR5) - pci_info(dev, "BAR %d: %pR (from Enhanced Allocation, properties %#02x)\n", - bei, res, prop); + pci_info(dev, "%s %pR: from Enhanced Allocation, properties %#02x\n", + res_name, res, prop); else if (bei == PCI_EA_BEI_ROM) - pci_info(dev, "ROM: %pR (from Enhanced Allocation, properties %#02x)\n", - res, prop); + pci_info(dev, "%s %pR: from Enhanced Allocation, properties %#02x\n", + res_name, res, prop); else if (bei >= PCI_EA_BEI_VF_BAR0 && bei <= PCI_EA_BEI_VF_BAR5) - pci_info(dev, "VF BAR %d: %pR (from Enhanced Allocation, properties %#02x)\n", - bei - PCI_EA_BEI_VF_BAR0, res, prop); + pci_info(dev, "%s %pR: from Enhanced Allocation, properties %#02x\n", + res_name, res, prop); else - pci_info(dev, "BEI %d res: %pR (from Enhanced Allocation, properties %#02x)\n", + pci_info(dev, "BEI %d %pR: from Enhanced Allocation, properties %#02x\n", bei, res, prop); out: @@ -3465,11 +3465,6 @@ void pci_allocate_cap_save_buffers(struct pci_dev *dev) if (error) pci_err(dev, "unable to allocate suspend buffer for LTR\n"); - error = pci_add_ext_cap_save_buffer(dev, PCI_EXT_CAP_ID_L1SS, - 2 * sizeof(u32)); - if (error) - pci_err(dev, "unable to allocate suspend buffer for ASPM-L1SS\n"); - pci_allocate_vc_save_buffers(dev); } @@ -3664,115 +3659,6 @@ void pci_acs_init(struct pci_dev *dev) } /** - * pci_rebar_find_pos - find position of resize ctrl reg for BAR - * @pdev: PCI device - * @bar: BAR to find - * - * Helper to find the position of the ctrl register for a BAR. - * Returns -ENOTSUPP if resizable BARs are not supported at all. - * Returns -ENOENT if no ctrl register for the BAR could be found. - */ -static int pci_rebar_find_pos(struct pci_dev *pdev, int bar) -{ - unsigned int pos, nbars, i; - u32 ctrl; - - pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_REBAR); - if (!pos) - return -ENOTSUPP; - - pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl); - nbars = (ctrl & PCI_REBAR_CTRL_NBAR_MASK) >> - PCI_REBAR_CTRL_NBAR_SHIFT; - - for (i = 0; i < nbars; i++, pos += 8) { - int bar_idx; - - pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl); - bar_idx = ctrl & PCI_REBAR_CTRL_BAR_IDX; - if (bar_idx == bar) - return pos; - } - - return -ENOENT; -} - -/** - * pci_rebar_get_possible_sizes - get possible sizes for BAR - * @pdev: PCI device - * @bar: BAR to query - * - * Get the possible sizes of a resizable BAR as bitmask defined in the spec - * (bit 0=1MB, bit 19=512GB). Returns 0 if BAR isn't resizable. - */ -u32 pci_rebar_get_possible_sizes(struct pci_dev *pdev, int bar) -{ - int pos; - u32 cap; - - pos = pci_rebar_find_pos(pdev, bar); - if (pos < 0) - return 0; - - pci_read_config_dword(pdev, pos + PCI_REBAR_CAP, &cap); - cap &= PCI_REBAR_CAP_SIZES; - - /* Sapphire RX 5600 XT Pulse has an invalid cap dword for BAR 0 */ - if (pdev->vendor == PCI_VENDOR_ID_ATI && pdev->device == 0x731f && - bar == 0 && cap == 0x7000) - cap = 0x3f000; - - return cap >> 4; -} -EXPORT_SYMBOL(pci_rebar_get_possible_sizes); - -/** - * pci_rebar_get_current_size - get the current size of a BAR - * @pdev: PCI device - * @bar: BAR to set size to - * - * Read the size of a BAR from the resizable BAR config. - * Returns size if found or negative error code. - */ -int pci_rebar_get_current_size(struct pci_dev *pdev, int bar) -{ - int pos; - u32 ctrl; - - pos = pci_rebar_find_pos(pdev, bar); - if (pos < 0) - return pos; - - pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl); - return (ctrl & PCI_REBAR_CTRL_BAR_SIZE) >> PCI_REBAR_CTRL_BAR_SHIFT; -} - -/** - * pci_rebar_set_size - set a new size for a BAR - * @pdev: PCI device - * @bar: BAR to set size to - * @size: new size as defined in the spec (0=1MB, 19=512GB) - * - * Set the new size of a BAR as defined in the spec. - * Returns zero if resizing was successful, error code otherwise. - */ -int pci_rebar_set_size(struct pci_dev *pdev, int bar, int size) -{ - int pos; - u32 ctrl; - - pos = pci_rebar_find_pos(pdev, bar); - if (pos < 0) - return pos; - - pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl); - ctrl &= ~PCI_REBAR_CTRL_BAR_SIZE; - ctrl |= size << PCI_REBAR_CTRL_BAR_SHIFT; - pci_write_config_dword(pdev, pos + PCI_REBAR_CTRL, ctrl); - return 0; -} - -/** * pci_enable_atomic_ops_to_root - enable AtomicOp requests to root port * @dev: the PCI device * @cap_mask: mask of desired AtomicOp sizes, including one or more of: @@ -3856,66 +3742,6 @@ 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() @@ -3927,7 +3753,8 @@ EXPORT_SYMBOL_GPL(pci_common_swizzle); */ void pci_release_region(struct pci_dev *pdev, int bar) { - struct pci_devres *dr; + if (!pci_bar_index_is_valid(bar)) + return; if (pci_resource_len(pdev, bar) == 0) return; @@ -3937,10 +3764,6 @@ 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); @@ -3948,13 +3771,14 @@ 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 @@ -3964,28 +3788,25 @@ 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_bar_index_is_valid(bar)) + return -EINVAL; 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: @@ -3998,19 +3819,20 @@ 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 * - * 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. * * Returns 0 on success, or %EBUSY on error. A warning * message is also printed on failure. */ -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); @@ -4033,13 +3855,13 @@ 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; @@ -4056,19 +3878,29 @@ 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. */ 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. + */ 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); @@ -4082,7 +3914,6 @@ 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); @@ -4092,30 +3923,31 @@ 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. */ -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 @@ -4124,10 +3956,10 @@ EXPORT_SYMBOL(pci_request_regions); * Returns 0 on success, or %EBUSY on error. A warning message is also * printed on failure. */ -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); @@ -4135,7 +3967,7 @@ 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; @@ -4168,16 +4000,12 @@ int pci_register_io_range(struct fwnode_handle *fwnode, phys_addr_t addr, phys_addr_t pci_pio_to_address(unsigned long pio) { - phys_addr_t address = (phys_addr_t)OF_BAD_ADDR; - #ifdef PCI_IOBASE - if (pio >= MMIO_UPPER_LIMIT) - return address; - - address = logic_pio_to_hwaddr(pio); + if (pio < MMIO_UPPER_LIMIT) + return logic_pio_to_hwaddr(pio); #endif - return address; + return (phys_addr_t) OF_BAD_ADDR; } EXPORT_SYMBOL_GPL(pci_pio_to_address); @@ -4206,7 +4034,7 @@ unsigned long __weak pci_address_to_pio(phys_addr_t address) #ifndef pci_remap_iospace int pci_remap_iospace(const struct resource *res, phys_addr_t phys_addr) { -#if defined(PCI_IOBASE) && defined(CONFIG_MMU) +#if defined(PCI_IOBASE) unsigned long vaddr = (unsigned long)PCI_IOBASE + res->start; if (!(res->flags & IORESOURCE_IO)) @@ -4215,8 +4043,8 @@ 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, @@ -4239,7 +4067,7 @@ EXPORT_SYMBOL(pci_remap_iospace); */ void pci_unmap_iospace(struct resource *res) { -#if defined(PCI_IOBASE) && defined(CONFIG_MMU) +#if defined(PCI_IOBASE) unsigned long vaddr = (unsigned long)PCI_IOBASE + res->start; vunmap_range(vaddr, vaddr + resource_size(res)); @@ -4247,133 +4075,6 @@ 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; @@ -4524,27 +4225,6 @@ 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 * @@ -4618,92 +4298,13 @@ 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 @@ -4860,6 +4461,101 @@ static int pci_pm_reset(struct pci_dev *dev, bool probe) } /** + * pcie_wait_for_link_status - Wait for link status change + * @pdev: Device whose link to wait for. + * @use_lt: Use the LT bit if TRUE, or the DLLLA bit if FALSE. + * @active: Waiting for active or inactive? + * + * Return 0 if successful, or -ETIMEDOUT if status has not changed within + * PCIE_LINK_RETRAIN_TIMEOUT_MS milliseconds. + */ +static int pcie_wait_for_link_status(struct pci_dev *pdev, + bool use_lt, bool active) +{ + u16 lnksta_mask, lnksta_match; + unsigned long end_jiffies; + u16 lnksta; + + lnksta_mask = use_lt ? PCI_EXP_LNKSTA_LT : PCI_EXP_LNKSTA_DLLLA; + lnksta_match = active ? lnksta_mask : 0; + + end_jiffies = jiffies + msecs_to_jiffies(PCIE_LINK_RETRAIN_TIMEOUT_MS); + do { + pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lnksta); + if ((lnksta & lnksta_mask) == lnksta_match) + return 0; + msleep(1); + } while (time_before(jiffies, end_jiffies)); + + return -ETIMEDOUT; +} + +/** + * pcie_retrain_link - Request a link retrain and wait for it to complete + * @pdev: Device whose link to retrain. + * @use_lt: Use the LT bit if TRUE, or the DLLLA bit if FALSE, for status. + * + * Trigger retraining of the PCIe Link and wait for the completion of the + * retraining. As link retraining is known to asserts LBMS and may change + * the Link Speed, LBMS is cleared after the retraining and the Link Speed + * of the subordinate bus is updated. + * + * Retrain completion status is retrieved from the Link Status Register + * according to @use_lt. It is not verified whether the use of the DLLLA + * bit is valid. + * + * Return 0 if successful, or -ETIMEDOUT if training has not completed + * within PCIE_LINK_RETRAIN_TIMEOUT_MS milliseconds. + */ +int pcie_retrain_link(struct pci_dev *pdev, bool use_lt) +{ + int rc; + + /* + * Ensure the updated LNKCTL parameters are used during link + * 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, true, false); + if (rc) + return rc; + + pcie_capability_set_word(pdev, PCI_EXP_LNKCTL, PCI_EXP_LNKCTL_RL); + if (pdev->clear_retrain_link) { + /* + * Due to an erratum in some devices the Retrain Link bit + * needs to be cleared again manually to allow the link + * training to succeed. + */ + pcie_capability_clear_word(pdev, PCI_EXP_LNKCTL, PCI_EXP_LNKCTL_RL); + } + + 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(pdev); + + /* + * Ensure the Link Speed updates after retraining in case the Link + * Speed was changed because of the retraining. While the bwctrl's + * IRQ handler normally picks up the new Link Speed, clearing LBMS + * races with the IRQ handler reading the Link Status register and + * can result in the handler returning early without updating the + * Link Speed. + */ + if (pdev->subordinate) + pcie_update_link_speed(pdev->subordinate); + + return rc; +} + +/** * pcie_wait_for_link_delay - Wait until link is active or inactive * @pdev: Bridge device * @active: waiting for active or inactive? @@ -4870,22 +4566,20 @@ static int pci_pm_reset(struct pci_dev *dev, bool probe) static bool pcie_wait_for_link_delay(struct pci_dev *pdev, bool active, int delay) { - int timeout = 1000; - bool ret; - u16 lnk_status; + int rc; /* * Some controllers might not implement link active reporting. In this * case, we wait for 1000 ms + any delay requested by the caller. */ if (!pdev->link_active_reporting) { - msleep(timeout + delay); + msleep(PCIE_LINK_RETRAIN_TIMEOUT_MS + delay); return true; } /* * PCIe r4.0 sec 6.6.1, a component must enter LTSSM Detect within 20ms, - * after which we should expect an link active if the reset was + * after which we should expect the link to be active if the reset was * successful. If so, software must wait a minimum 100ms before sending * configuration requests to devices downstream this port. * @@ -4894,20 +4588,21 @@ static bool pcie_wait_for_link_delay(struct pci_dev *pdev, bool active, */ if (active) msleep(20); - for (;;) { - pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lnk_status); - ret = !!(lnk_status & PCI_EXP_LNKSTA_DLLLA); - if (ret == active) - break; - if (timeout <= 0) - break; - msleep(10); - timeout -= 10; - } - if (active && ret) + rc = pcie_wait_for_link_status(pdev, false, active); + if (active) { + if (rc) + rc = pcie_failed_link_retrain(pdev); + if (rc) + return false; + msleep(delay); + return true; + } + + if (rc) + return false; - return ret == active; + return true; } /** @@ -4948,24 +4643,29 @@ static int pci_bus_max_d3cold_delay(const struct pci_bus *bus) /** * pci_bridge_wait_for_secondary_bus - Wait for secondary bus to be accessible * @dev: PCI bridge + * @reset_type: reset type in human-readable form * * Handle necessary delays before access to the devices on the secondary - * side of the bridge are permitted after D3cold to D0 transition. + * side of the bridge are permitted after D3cold to D0 transition + * or Conventional Reset. * * 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. + * + * Return 0 on success or -ENOTTY if the first device on the secondary bus + * failed to become accessible. */ -void pci_bridge_wait_for_secondary_bus(struct pci_dev *dev) +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)) - return; + return 0; - if (!pci_is_bridge(dev) || !dev->bridge_d3) - return; + if (!pci_is_bridge(dev)) + return 0; down_read(&pci_bus_sem); @@ -4977,30 +4677,28 @@ void pci_bridge_wait_for_secondary_bus(struct pci_dev *dev) */ if (!dev->subordinate || list_empty(&dev->subordinate->devices)) { up_read(&pci_bus_sem); - return; + return 0; } /* Take d3cold_delay requirements into account */ delay = pci_bus_max_d3cold_delay(dev->subordinate); if (!delay) { up_read(&pci_bus_sem); - return; + 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); /* * 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()). + * accessing the device after reset (that is 1000 ms + 100 ms). */ if (!pci_is_pcie(dev)) { pci_dbg(dev, "waiting %d ms for secondary bus\n", 1000 + delay); msleep(1000 + delay); - return; + return 0; } /* @@ -5011,35 +4709,51 @@ void pci_bridge_wait_for_secondary_bus(struct pci_dev *dev) * * 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). + * device that did not respond is a broken device. Also device can + * take longer than that to respond if it indicates so through Request + * Retry Status completions. * - * Therefore we wait for 100 ms and check for the device presence. - * If it is still not present give it an additional 100 ms. + * Therefore we wait for 100 ms and check for the device presence + * until the timeout expires. */ if (!pcie_downstream_port(dev)) - return; + return 0; if (pcie_get_speed_cap(dev) <= PCIE_SPEED_5_0GT) { + u16 status; + 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 */ - pci_info(dev, "Data Link Layer Link Active not set in 1000 msec\n"); - return; - } + + if (!pci_dev_wait(child, reset_type, PCI_RESET_WAIT - delay)) + return 0; + + /* + * If the port supports active link reporting we now check + * whether the link is active and if not bail out early with + * the assumption that the device is not present anymore. + */ + if (!dev->link_active_reporting) + return -ENOTTY; + + pcie_capability_read_word(dev, PCI_EXP_LNKSTA, &status); + if (!(status & PCI_EXP_LNKSTA_DLLLA)) + return -ENOTTY; + + return pci_dev_wait(child, reset_type, + PCIE_RESET_READY_POLL_MS - PCI_RESET_WAIT); } - if (!pci_device_is_present(child)) { - pci_dbg(child, "waiting additional %d ms to become accessible\n", delay); - msleep(delay); + 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 */ + pci_info(dev, "Data Link Layer Link Active not set in %d msec\n", delay); + return -ENOTTY; } + + return pci_dev_wait(child, reset_type, + PCIE_RESET_READY_POLL_MS - delay); } void pci_reset_secondary_bus(struct pci_dev *dev) @@ -5058,15 +4772,6 @@ void pci_reset_secondary_bus(struct pci_dev *dev) ctrl &= ~PCI_BRIDGE_CTL_BUS_RESET; pci_write_config_word(dev, PCI_BRIDGE_CONTROL, ctrl); - - /* - * Trhfa for conventional PCI is 2^25 clock cycles. - * Assuming a minimum 33MHz clock this results in a 1s - * delay before we can consider subordinate devices to - * be re-initialized. PCIe has some ways to shorten this, - * but we don't make use of them yet. - */ - ssleep(1); } void __weak pcibios_reset_secondary_bus(struct pci_dev *dev) @@ -5083,9 +4788,12 @@ 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_dev_wait(dev, "bus reset", PCIE_RESET_READY_POLL_MS); + return pci_bridge_wait_for_secondary_bus(dev, "bus reset"); } EXPORT_SYMBOL_GPL(pci_bridge_secondary_bus_reset); @@ -5131,16 +4839,96 @@ 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. */ @@ -5181,6 +4969,8 @@ 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 @@ -5214,10 +5004,12 @@ 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" }, @@ -5225,128 +5017,7 @@ 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" }, }; /** @@ -5372,6 +5043,7 @@ const struct attribute_group pci_dev_reset_method_attr_group = { int __pci_reset_function_locked(struct pci_dev *dev) { int i, m, rc; + const struct pci_reset_fn_method *method; might_sleep(); @@ -5388,9 +5060,13 @@ int __pci_reset_function_locked(struct pci_dev *dev) if (!m) return -ENOTTY; - rc = pci_reset_fn_methods[m].reset_fn(dev, PCI_RESET_DO_RESET); + method = &pci_reset_fn_methods[m]; + pci_dbg(dev, "reset via %s\n", method->name); + rc = method->reset_fn(dev, PCI_RESET_DO_RESET); if (!rc) return 0; + + pci_dbg(dev, "%s failed with %d\n", method->name, rc); if (rc != -ENOTTY) return rc; } @@ -5449,11 +5125,20 @@ 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); @@ -5462,6 +5147,9 @@ 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); @@ -5526,7 +5214,7 @@ int pci_try_reset_function(struct pci_dev *dev) EXPORT_SYMBOL_GPL(pci_try_reset_function); /* Do any devices on or below this bus prevent a bus reset? */ -static bool pci_bus_resetable(struct pci_bus *bus) +static bool pci_bus_resettable(struct pci_bus *bus) { struct pci_dev *dev; @@ -5536,7 +5224,7 @@ static bool pci_bus_resetable(struct pci_bus *bus) list_for_each_entry(dev, &bus->devices, bus_list) { if (dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET || - (dev->subordinate && !pci_bus_resetable(dev->subordinate))) + (dev->subordinate && !pci_bus_resettable(dev->subordinate))) return false; } @@ -5548,10 +5236,12 @@ 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); } } @@ -5563,8 +5253,10 @@ 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 */ @@ -5572,15 +5264,15 @@ 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; @@ -5588,13 +5280,15 @@ 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; } /* Do any devices on or below this slot prevent a bus reset? */ -static bool pci_slot_resetable(struct pci_slot *slot) +static bool pci_slot_resettable(struct pci_slot *slot) { struct pci_dev *dev; @@ -5606,7 +5300,7 @@ static bool pci_slot_resetable(struct pci_slot *slot) if (!dev->slot || dev->slot != slot) continue; if (dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET || - (dev->subordinate && !pci_bus_resetable(dev->subordinate))) + (dev->subordinate && !pci_bus_resettable(dev->subordinate))) return false; } @@ -5621,9 +5315,10 @@ 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); } } @@ -5637,7 +5332,8 @@ static void pci_slot_unlock(struct pci_slot *slot) continue; if (dev->subordinate) pci_bus_unlock(dev->subordinate); - pci_dev_unlock(dev); + else + pci_dev_unlock(dev); } } @@ -5649,14 +5345,13 @@ 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; @@ -5667,7 +5362,8 @@ unlock: continue; if (dev->subordinate) pci_bus_unlock(dev->subordinate); - pci_dev_unlock(dev); + else + pci_dev_unlock(dev); } return 0; } @@ -5698,8 +5394,10 @@ 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); + } } } @@ -5733,8 +5431,10 @@ 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); + } } } @@ -5742,7 +5442,7 @@ static int pci_slot_reset(struct pci_slot *slot, bool probe) { int rc; - if (!slot || !pci_slot_resetable(slot)) + if (!slot || !pci_slot_resettable(slot)) return -ENOTTY; if (!probe) @@ -5809,7 +5509,7 @@ static int pci_bus_reset(struct pci_bus *bus, bool probe) { int ret; - if (!bus->self || !pci_bus_resetable(bus)) + if (!bus->self || !pci_bus_resettable(bus)) return -ENOTTY; if (probe) @@ -5879,7 +5579,7 @@ 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; @@ -5931,7 +5631,7 @@ int pcix_get_max_mmrbc(struct pci_dev *dev) if (pci_read_config_dword(dev, cap + PCI_X_STATUS, &stat)) return -EINVAL; - return 512 << ((stat & PCI_X_STATUS_MAX_READ) >> 21); + return 512 << FIELD_GET(PCI_X_STATUS_MAX_READ, stat); } EXPORT_SYMBOL(pcix_get_max_mmrbc); @@ -5954,7 +5654,7 @@ int pcix_get_mmrbc(struct pci_dev *dev) if (pci_read_config_word(dev, cap + PCI_X_CMD, &cmd)) return -EINVAL; - return 512 << ((cmd & PCI_X_CMD_MAX_READ) >> 2); + return 512 << FIELD_GET(PCI_X_CMD_MAX_READ, cmd); } EXPORT_SYMBOL(pcix_get_mmrbc); @@ -5985,19 +5685,19 @@ int pcix_set_mmrbc(struct pci_dev *dev, int mmrbc) if (pci_read_config_dword(dev, cap + PCI_X_STATUS, &stat)) return -EINVAL; - if (v > (stat & PCI_X_STATUS_MAX_READ) >> 21) + if (v > FIELD_GET(PCI_X_STATUS_MAX_READ, stat)) return -E2BIG; if (pci_read_config_word(dev, cap + PCI_X_CMD, &cmd)) return -EINVAL; - o = (cmd & PCI_X_CMD_MAX_READ) >> 2; + o = FIELD_GET(PCI_X_CMD_MAX_READ, cmd); if (o != v) { if (v > o && (dev->bus->bus_flags & PCI_BUS_FLAGS_NO_MMRBC)) return -EIO; cmd &= ~PCI_X_CMD_MAX_READ; - cmd |= v << 2; + cmd |= FIELD_PREP(PCI_X_CMD_MAX_READ, v); if (pci_write_config_word(dev, cap + PCI_X_CMD, cmd)) return -EIO; } @@ -6017,7 +5717,7 @@ int pcie_get_readrq(struct pci_dev *dev) pcie_capability_read_word(dev, PCI_EXP_DEVCTL, &ctl); - return 128 << ((ctl & PCI_EXP_DEVCTL_READRQ) >> 12); + return 128 << FIELD_GET(PCI_EXP_DEVCTL_READRQ, ctl); } EXPORT_SYMBOL(pcie_get_readrq); @@ -6033,6 +5733,8 @@ int pcie_set_readrq(struct pci_dev *dev, int rq) { u16 v; int ret; + unsigned int firstbit; + struct pci_host_bridge *bridge = pci_find_host_bridge(dev->bus); if (rq < 128 || rq > 4096 || !is_power_of_2(rq)) return -EINVAL; @@ -6049,7 +5751,19 @@ int pcie_set_readrq(struct pci_dev *dev, int rq) rq = mps; } - v = (ffs(rq) - 8) << 12; + firstbit = ffs(rq); + if (firstbit < 8) + return -EINVAL; + v = FIELD_PREP(PCI_EXP_DEVCTL_READRQ, firstbit - 8); + + if (bridge->no_inc_mrrs) { + int max_mrrs = pcie_get_readrq(dev); + + if (rq > max_mrrs) { + pci_info(dev, "can't set Max_Read_Request_Size to %d; max is %d\n", rq, max_mrrs); + return -EINVAL; + } + } ret = pcie_capability_clear_and_set_word(dev, PCI_EXP_DEVCTL, PCI_EXP_DEVCTL_READRQ, v); @@ -6070,7 +5784,7 @@ int pcie_get_mps(struct pci_dev *dev) pcie_capability_read_word(dev, PCI_EXP_DEVCTL, &ctl); - return 128 << ((ctl & PCI_EXP_DEVCTL_PAYLOAD) >> 5); + return 128 << FIELD_GET(PCI_EXP_DEVCTL_PAYLOAD, ctl); } EXPORT_SYMBOL(pcie_get_mps); @@ -6093,7 +5807,7 @@ int pcie_set_mps(struct pci_dev *dev, int mps) v = ffs(mps) - 8; if (v > dev->pcie_mpss) return -EINVAL; - v <<= 5; + v = FIELD_PREP(PCI_EXP_DEVCTL_PAYLOAD, v); ret = pcie_capability_clear_and_set_word(dev, PCI_EXP_DEVCTL, PCI_EXP_DEVCTL_PAYLOAD, v); @@ -6102,6 +5816,24 @@ int pcie_set_mps(struct pci_dev *dev, int mps) } EXPORT_SYMBOL(pcie_set_mps); +static enum pci_bus_speed to_pcie_link_speed(u16 lnksta) +{ + return pcie_link_speed[FIELD_GET(PCI_EXP_LNKSTA_CLS, lnksta)]; +} + +int pcie_link_speed_mbps(struct pci_dev *pdev) +{ + u16 lnksta; + int err; + + err = pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lnksta); + if (err) + return err; + + return pcie_dev_speed_mbps(to_pcie_link_speed(lnksta)); +} +EXPORT_SYMBOL(pcie_link_speed_mbps); + /** * pcie_bandwidth_available - determine minimum link settings of a PCIe * device and its bandwidth limitation @@ -6135,9 +5867,8 @@ u32 pcie_bandwidth_available(struct pci_dev *dev, struct pci_dev **limiting_dev, while (dev) { pcie_capability_read_word(dev, PCI_EXP_LNKSTA, &lnksta); - next_speed = pcie_link_speed[lnksta & PCI_EXP_LNKSTA_CLS]; - next_width = (lnksta & PCI_EXP_LNKSTA_NLW) >> - PCI_EXP_LNKSTA_NLW_SHIFT; + next_speed = to_pcie_link_speed(lnksta); + next_width = FIELD_GET(PCI_EXP_LNKSTA_NLW, lnksta); next_bw = next_width * PCIE_SPEED2MBS_ENC(next_speed); @@ -6161,38 +5892,66 @@ 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); @@ -6209,7 +5968,7 @@ enum pcie_link_width pcie_get_width_cap(struct pci_dev *dev) pcie_capability_read_dword(dev, PCI_EXP_LNKCAP, &lnkcap); if (lnkcap) - return (lnkcap & PCI_EXP_LNKCAP_MLW) >> 4; + return FIELD_GET(PCI_EXP_LNKCAP_MLW, lnkcap); return PCIE_LNK_WIDTH_UNKNOWN; } @@ -6225,8 +5984,9 @@ 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); @@ -6253,21 +6013,25 @@ void __pcie_print_link_status(struct pci_dev *dev, bool verbose) enum pci_bus_speed speed, speed_cap; struct pci_dev *limiting_dev = NULL; u32 bw_avail, bw_cap; + char *flit_mode = ""; bw_cap = pcie_bandwidth_capable(dev, &speed_cap, &width_cap); bw_avail = pcie_bandwidth_available(dev, &limiting_dev, &speed, &width); + if (dev->bus && dev->bus->flit_mode) + flit_mode = ", in Flit mode"; + if (bw_avail >= bw_cap && verbose) - pci_info(dev, "%u.%03u Gb/s available PCIe bandwidth (%s x%d link)\n", + pci_info(dev, "%u.%03u Gb/s available PCIe bandwidth (%s x%d link)%s\n", bw_cap / 1000, bw_cap % 1000, - pci_speed_string(speed_cap), width_cap); + pci_speed_string(speed_cap), width_cap, flit_mode); else if (bw_avail < bw_cap) - pci_info(dev, "%u.%03u Gb/s available PCIe bandwidth, limited by %s x%d link at %s (capable of %u.%03u Gb/s with %s x%d link)\n", + pci_info(dev, "%u.%03u Gb/s available PCIe bandwidth, limited by %s x%d link at %s (capable of %u.%03u Gb/s with %s x%d link)%s\n", bw_avail / 1000, bw_avail % 1000, pci_speed_string(speed), width, limiting_dev ? pci_name(limiting_dev) : "<unknown>", bw_cap / 1000, bw_cap % 1000, - pci_speed_string(speed_cap), width_cap); + pci_speed_string(speed_cap), width_cap, flit_mode); } /** @@ -6567,14 +6331,15 @@ static void pci_request_resource_alignment(struct pci_dev *dev, int bar, resource_size_t align, bool resize) { struct resource *r = &dev->resource[bar]; + const char *r_name = pci_resource_name(dev, bar); resource_size_t size; if (!(r->flags & IORESOURCE_MEM)) return; if (r->flags & IORESOURCE_PCI_FIXED) { - pci_info(dev, "BAR%d %pR: ignoring requested alignment %#llx\n", - bar, r, (unsigned long long)align); + pci_info(dev, "%s %pR: ignoring requested alignment %#llx\n", + r_name, r, (unsigned long long)align); return; } @@ -6610,8 +6375,8 @@ static void pci_request_resource_alignment(struct pci_dev *dev, int bar, * devices and we use the second. */ - pci_info(dev, "BAR%d %pR: requesting alignment to %#llx\n", - bar, r, (unsigned long long)align); + pci_info(dev, "%s %pR: requesting alignment to %#llx\n", + r_name, r, (unsigned long long)align); if (resize) { r->start = 0; @@ -6619,8 +6384,7 @@ 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; } @@ -6685,7 +6449,7 @@ void pci_reassigndev_resource_alignment(struct pci_dev *dev) } } -static ssize_t resource_alignment_show(struct bus_type *bus, char *buf) +static ssize_t resource_alignment_show(const struct bus_type *bus, char *buf) { size_t count = 0; @@ -6697,7 +6461,7 @@ static ssize_t resource_alignment_show(struct bus_type *bus, char *buf) return count; } -static ssize_t resource_alignment_store(struct bus_type *bus, +static ssize_t resource_alignment_store(const struct bus_type *bus, const char *buf, size_t count) { char *param, *old, *end; @@ -6744,9 +6508,31 @@ static void pci_no_domains(void) #endif } +#ifdef CONFIG_PCI_DOMAINS +static DEFINE_IDA(pci_domain_nr_dynamic_ida); + +/** + * pci_bus_find_emul_domain_nr() - allocate a PCI domain number per constraints + * @hint: desired domain, 0 if any ID in the range of @min to @max is acceptable + * @min: minimum allowable domain + * @max: maximum allowable domain, no IDs higher than INT_MAX will be returned + */ +int pci_bus_find_emul_domain_nr(u32 hint, u32 min, u32 max) +{ + return ida_alloc_range(&pci_domain_nr_dynamic_ida, max(hint, min), max, + GFP_KERNEL); +} +EXPORT_SYMBOL_GPL(pci_bus_find_emul_domain_nr); + +void pci_bus_release_emul_domain_nr(int domain_nr) +{ + ida_free(&pci_domain_nr_dynamic_ida, domain_nr); +} +EXPORT_SYMBOL_GPL(pci_bus_release_emul_domain_nr); +#endif + #ifdef CONFIG_PCI_DOMAINS_GENERIC static DEFINE_IDA(pci_domain_nr_static_ida); -static DEFINE_IDA(pci_domain_nr_dynamic_ida); static void of_pci_reserve_static_domain_nr(void) { @@ -6799,16 +6585,16 @@ 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) @@ -6817,11 +6603,11 @@ 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 @@ -6837,11 +6623,6 @@ int __weak pci_ext_cfg_avail(void) return 1; } -void __weak pci_fixup_cardbus(struct pci_bus *bus) -{ -} -EXPORT_SYMBOL(pci_fixup_cardbus); - static int __init pci_setup(char *str) { while (str) { @@ -6866,6 +6647,8 @@ 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)) { @@ -6900,6 +6683,8 @@ 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); } @@ -6924,6 +6709,7 @@ 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; } |