diff options
Diffstat (limited to 'arch/powerpc/platforms/pseries')
| -rw-r--r-- | arch/powerpc/platforms/pseries/Kconfig | 9 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/eeh_pseries.c | 382 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/firmware.c | 1 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/hotplug-cpu.c | 190 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/hotplug-memory.c | 109 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/hvcserver.c | 2 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/lpar.c | 8 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/mobility.c | 43 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/offline_states.h | 38 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/papr_scm.c | 296 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/pci_dlpar.c | 2 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/pmem.c | 7 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/setup.c | 24 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/smp.c | 90 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/suspend.c | 27 |
15 files changed, 662 insertions, 566 deletions
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig index 24c18362e5ea..5e037df2a3a1 100644 --- a/arch/powerpc/platforms/pseries/Kconfig +++ b/arch/powerpc/platforms/pseries/Kconfig @@ -25,15 +25,22 @@ config PPC_PSERIES select SWIOTLB default y +config PARAVIRT_SPINLOCKS + bool + config PPC_SPLPAR - depends on PPC_PSERIES bool "Support for shared-processor logical partitions" + depends on PPC_PSERIES + select PARAVIRT_SPINLOCKS if PPC_QUEUED_SPINLOCKS + default y help Enabling this option will make the kernel run more efficiently on logically-partitioned pSeries systems which use shared processors, that is, which share physical processors between two or more partitions. + Say Y if you are unsure. + config DTL bool "Dispatch Trace Log" depends on PPC_SPLPAR && DEBUG_FS diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index ace117f99d94..cb2d9a970b7b 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -24,6 +24,7 @@ #include <linux/sched.h> #include <linux/seq_file.h> #include <linux/spinlock.h> +#include <linux/crash_dump.h> #include <asm/eeh.h> #include <asm/eeh_event.h> @@ -32,6 +33,8 @@ #include <asm/ppc-pci.h> #include <asm/rtas.h> +static int pseries_eeh_get_pe_addr(struct pci_dn *pdn); + /* RTAS tokens */ static int ibm_set_eeh_option; static int ibm_set_slot_reset; @@ -52,8 +55,6 @@ void pseries_pcibios_bus_add_device(struct pci_dev *pdev) dev_dbg(&pdev->dev, "EEH: Setting up device\n"); #ifdef CONFIG_PCI_IOV if (pdev->is_virtfn) { - struct pci_dn *physfn_pdn; - pdn->device_id = pdev->device; pdn->vendor_id = pdev->vendor; pdn->class_code = pdev->class; @@ -63,23 +64,172 @@ void pseries_pcibios_bus_add_device(struct pci_dev *pdev) * completion from platform. */ pdn->last_allow_rc = 0; - physfn_pdn = pci_get_pdn(pdev->physfn); - pdn->pe_number = physfn_pdn->pe_num_map[pdn->vf_index]; } #endif pseries_eeh_init_edev(pdn); #ifdef CONFIG_PCI_IOV if (pdev->is_virtfn) { + /* + * FIXME: This really should be handled by choosing the right + * parent PE in in pseries_eeh_init_edev(). + */ + struct eeh_pe *physfn_pe = pci_dev_to_eeh_dev(pdev->physfn)->pe; struct eeh_dev *edev = pdn_to_eeh_dev(pdn); edev->pe_config_addr = (pdn->busno << 16) | (pdn->devfn << 8); - eeh_rmv_from_parent_pe(edev); /* Remove as it is adding to bus pe */ - eeh_add_to_parent_pe(edev); /* Add as VF PE type */ + eeh_pe_tree_remove(edev); /* Remove as it is adding to bus pe */ + eeh_pe_tree_insert(edev, physfn_pe); /* Add as VF PE type */ } #endif eeh_probe_device(pdev); } + +/** + * pseries_eeh_get_config_addr - Retrieve config address + * + * Retrieve the assocated config address. Actually, there're 2 RTAS + * function calls dedicated for the purpose. We need implement + * it through the new function and then the old one. Besides, + * you should make sure the config address is figured out from + * FDT node before calling the function. + * + * It's notable that zero'ed return value means invalid PE config + * address. + */ +static int pseries_eeh_get_config_addr(struct pci_controller *phb, int config_addr) +{ + int ret = 0; + int rets[3]; + + if (ibm_get_config_addr_info2 != RTAS_UNKNOWN_SERVICE) { + /* + * First of all, we need to make sure there has one PE + * associated with the device. Otherwise, PE address is + * meaningless. + */ + ret = rtas_call(ibm_get_config_addr_info2, 4, 2, rets, + config_addr, BUID_HI(phb->buid), + BUID_LO(phb->buid), 1); + if (ret || (rets[0] == 0)) + return 0; + + /* Retrieve the associated PE config address */ + ret = rtas_call(ibm_get_config_addr_info2, 4, 2, rets, + config_addr, BUID_HI(phb->buid), + BUID_LO(phb->buid), 0); + if (ret) { + pr_warn("%s: Failed to get address for PHB#%x-PE#%x\n", + __func__, phb->global_number, config_addr); + return 0; + } + + return rets[0]; + } + + if (ibm_get_config_addr_info != RTAS_UNKNOWN_SERVICE) { + ret = rtas_call(ibm_get_config_addr_info, 4, 2, rets, + config_addr, BUID_HI(phb->buid), + BUID_LO(phb->buid), 0); + if (ret) { + pr_warn("%s: Failed to get address for PHB#%x-PE#%x\n", + __func__, phb->global_number, config_addr); + return 0; + } + + return rets[0]; + } + + return ret; +} + +/** + * pseries_eeh_phb_reset - Reset the specified PHB + * @phb: PCI controller + * @config_adddr: the associated config address + * @option: reset option + * + * Reset the specified PHB/PE + */ +static int pseries_eeh_phb_reset(struct pci_controller *phb, int config_addr, int option) +{ + int ret; + + /* Reset PE through RTAS call */ + ret = rtas_call(ibm_set_slot_reset, 4, 1, NULL, + config_addr, BUID_HI(phb->buid), + BUID_LO(phb->buid), option); + + /* If fundamental-reset not supported, try hot-reset */ + if (option == EEH_RESET_FUNDAMENTAL && + ret == -8) { + option = EEH_RESET_HOT; + ret = rtas_call(ibm_set_slot_reset, 4, 1, NULL, + config_addr, BUID_HI(phb->buid), + BUID_LO(phb->buid), option); + } + + /* We need reset hold or settlement delay */ + if (option == EEH_RESET_FUNDAMENTAL || + option == EEH_RESET_HOT) + msleep(EEH_PE_RST_HOLD_TIME); + else + msleep(EEH_PE_RST_SETTLE_TIME); + + return ret; +} + +/** + * pseries_eeh_phb_configure_bridge - Configure PCI bridges in the indicated PE + * @phb: PCI controller + * @config_adddr: the associated config address + * + * The function will be called to reconfigure the bridges included + * in the specified PE so that the mulfunctional PE would be recovered + * again. + */ +static int pseries_eeh_phb_configure_bridge(struct pci_controller *phb, int config_addr) +{ + int ret; + /* Waiting 0.2s maximum before skipping configuration */ + int max_wait = 200; + + while (max_wait > 0) { + ret = rtas_call(ibm_configure_pe, 3, 1, NULL, + config_addr, BUID_HI(phb->buid), + BUID_LO(phb->buid)); + + if (!ret) + return ret; + if (ret < 0) + break; + + /* + * If RTAS returns a delay value that's above 100ms, cut it + * down to 100ms in case firmware made a mistake. For more + * on how these delay values work see rtas_busy_delay_time + */ + if (ret > RTAS_EXTENDED_DELAY_MIN+2 && + ret <= RTAS_EXTENDED_DELAY_MAX) + ret = RTAS_EXTENDED_DELAY_MIN+2; + + max_wait -= rtas_busy_delay_time(ret); + + if (max_wait < 0) + break; + + rtas_busy_delay(ret); + } + + pr_warn("%s: Unable to configure bridge PHB#%x-PE#%x (%d)\n", + __func__, phb->global_number, config_addr, ret); + /* PAPR defines -3 as "Parameter Error" for this function: */ + if (ret == -3) + return -EINVAL; + else + return -EIO; +} + /* * Buffer for reporting slot-error-detail rtas calls. Its here * in BSS, and not dynamically alloced, so that it ends up in @@ -96,6 +246,10 @@ static int eeh_error_buf_size; */ static int pseries_eeh_init(void) { + struct pci_controller *phb; + struct pci_dn *pdn; + int addr, config_addr; + /* figure out EEH RTAS function call tokens */ ibm_set_eeh_option = rtas_token("ibm,set-eeh-option"); ibm_set_slot_reset = rtas_token("ibm,set-slot-reset"); @@ -148,6 +302,22 @@ static int pseries_eeh_init(void) /* Set EEH machine dependent code */ ppc_md.pcibios_bus_add_device = pseries_pcibios_bus_add_device; + if (is_kdump_kernel() || reset_devices) { + pr_info("Issue PHB reset ...\n"); + list_for_each_entry(phb, &hose_list, list_node) { + pdn = list_first_entry(&PCI_DN(phb->dn)->child_list, struct pci_dn, list); + addr = (pdn->busno << 16) | (pdn->devfn << 8); + config_addr = pseries_eeh_get_config_addr(phb, addr); + /* invalid PE config addr */ + if (config_addr == 0) + continue; + + pseries_eeh_phb_reset(phb, config_addr, EEH_RESET_FUNDAMENTAL); + pseries_eeh_phb_reset(phb, config_addr, EEH_RESET_DEACTIVATE); + pseries_eeh_phb_configure_bridge(phb, config_addr); + } + } + return 0; } @@ -221,6 +391,43 @@ static int pseries_eeh_find_ecap(struct pci_dn *pdn, int cap) } /** + * pseries_eeh_pe_get_parent - Retrieve the parent PE + * @edev: EEH device + * + * The whole PEs existing in the system are organized as hierarchy + * tree. The function is used to retrieve the parent PE according + * to the parent EEH device. + */ +static struct eeh_pe *pseries_eeh_pe_get_parent(struct eeh_dev *edev) +{ + struct eeh_dev *parent; + struct pci_dn *pdn = eeh_dev_to_pdn(edev); + + /* + * It might have the case for the indirect parent + * EEH device already having associated PE, but + * the direct parent EEH device doesn't have yet. + */ + if (edev->physfn) + pdn = pci_get_pdn(edev->physfn); + else + pdn = pdn ? pdn->parent : NULL; + while (pdn) { + /* We're poking out of PCI territory */ + parent = pdn_to_eeh_dev(pdn); + if (!parent) + return NULL; + + if (parent->pe) + return parent->pe; + + pdn = pdn->parent; + } + + return NULL; +} + +/** * pseries_eeh_init_edev - initialise the eeh_dev and eeh_pe for a pci_dn * * @pdn: PCI device node @@ -275,12 +482,11 @@ void pseries_eeh_init_edev(struct pci_dn *pdn) * correctly reflects that current device is root port * or PCIe switch downstream port. */ - edev->class_code = pdn->class_code; edev->pcix_cap = pseries_eeh_find_cap(pdn, PCI_CAP_ID_PCIX); edev->pcie_cap = pseries_eeh_find_cap(pdn, PCI_CAP_ID_EXP); edev->aer_cap = pseries_eeh_find_ecap(pdn, PCI_EXT_CAP_ID_ERR); edev->mode &= 0xFFFFFF00; - if ((edev->class_code >> 8) == PCI_CLASS_BRIDGE_PCI) { + if ((pdn->class_code >> 8) == PCI_CLASS_BRIDGE_PCI) { edev->mode |= EEH_DEV_BRIDGE; if (edev->pcie_cap) { rtas_read_config(pdn, edev->pcie_cap + PCI_EXP_FLAGS, @@ -304,8 +510,10 @@ void pseries_eeh_init_edev(struct pci_dn *pdn) if (ret) { eeh_edev_dbg(edev, "EEH failed to enable on device (code %d)\n", ret); } else { + struct eeh_pe *parent; + /* Retrieve PE address */ - edev->pe_config_addr = eeh_ops->get_pe_addr(&pe); + edev->pe_config_addr = pseries_eeh_get_pe_addr(pdn); pe.addr = edev->pe_config_addr; /* Some older systems (Power4) allow the ibm,set-eeh-option @@ -316,16 +524,19 @@ void pseries_eeh_init_edev(struct pci_dn *pdn) if (ret > 0 && ret != EEH_STATE_NOT_SUPPORT) enable = 1; - if (enable) { + /* + * This device doesn't support EEH, but it may have an + * EEH parent. In this case any error on the device will + * freeze the PE of it's upstream bridge, so added it to + * the upstream PE. + */ + parent = pseries_eeh_pe_get_parent(edev); + if (parent && !enable) + edev->pe_config_addr = parent->addr; + + if (enable || parent) { eeh_add_flag(EEH_ENABLED); - eeh_add_to_parent_pe(edev); - } else if (pdn->parent && pdn_to_eeh_dev(pdn->parent) && - (pdn_to_eeh_dev(pdn->parent))->pe) { - /* This device doesn't support EEH, but it may have an - * EEH parent, in which case we mark it as supported. - */ - edev->pe_config_addr = pdn_to_eeh_dev(pdn->parent)->pe_config_addr; - eeh_add_to_parent_pe(edev); + eeh_pe_tree_insert(edev, parent); } eeh_edev_dbg(edev, "EEH is %s on device (code %d)\n", (enable ? "enabled" : "unsupported"), ret); @@ -435,8 +646,10 @@ static int pseries_eeh_set_option(struct eeh_pe *pe, int option) * It's notable that zero'ed return value means invalid PE config * address. */ -static int pseries_eeh_get_pe_addr(struct eeh_pe *pe) +static int pseries_eeh_get_pe_addr(struct pci_dn *pdn) { + int config_addr = rtas_config_addr(pdn->busno, pdn->devfn, 0); + unsigned long buid = pdn->phb->buid; int ret = 0; int rets[3]; @@ -447,18 +660,16 @@ static int pseries_eeh_get_pe_addr(struct eeh_pe *pe) * meaningless. */ ret = rtas_call(ibm_get_config_addr_info2, 4, 2, rets, - pe->config_addr, BUID_HI(pe->phb->buid), - BUID_LO(pe->phb->buid), 1); + config_addr, BUID_HI(buid), BUID_LO(buid), 1); if (ret || (rets[0] == 0)) return 0; /* Retrieve the associated PE config address */ ret = rtas_call(ibm_get_config_addr_info2, 4, 2, rets, - pe->config_addr, BUID_HI(pe->phb->buid), - BUID_LO(pe->phb->buid), 0); + config_addr, BUID_HI(buid), BUID_LO(buid), 0); if (ret) { pr_warn("%s: Failed to get address for PHB#%x-PE#%x\n", - __func__, pe->phb->global_number, pe->config_addr); + __func__, pdn->phb->global_number, config_addr); return 0; } @@ -467,11 +678,10 @@ static int pseries_eeh_get_pe_addr(struct eeh_pe *pe) if (ibm_get_config_addr_info != RTAS_UNKNOWN_SERVICE) { ret = rtas_call(ibm_get_config_addr_info, 4, 2, rets, - pe->config_addr, BUID_HI(pe->phb->buid), - BUID_LO(pe->phb->buid), 0); + config_addr, BUID_HI(buid), BUID_LO(buid), 0); if (ret) { pr_warn("%s: Failed to get address for PHB#%x-PE#%x\n", - __func__, pe->phb->global_number, pe->config_addr); + __func__, pdn->phb->global_number, config_addr); return 0; } @@ -569,35 +779,13 @@ static int pseries_eeh_get_state(struct eeh_pe *pe, int *delay) static int pseries_eeh_reset(struct eeh_pe *pe, int option) { int config_addr; - int ret; /* Figure out PE address */ config_addr = pe->config_addr; if (pe->addr) config_addr = pe->addr; - /* Reset PE through RTAS call */ - ret = rtas_call(ibm_set_slot_reset, 4, 1, NULL, - config_addr, BUID_HI(pe->phb->buid), - BUID_LO(pe->phb->buid), option); - - /* If fundamental-reset not supported, try hot-reset */ - if (option == EEH_RESET_FUNDAMENTAL && - ret == -8) { - option = EEH_RESET_HOT; - ret = rtas_call(ibm_set_slot_reset, 4, 1, NULL, - config_addr, BUID_HI(pe->phb->buid), - BUID_LO(pe->phb->buid), option); - } - - /* We need reset hold or settlement delay */ - if (option == EEH_RESET_FUNDAMENTAL || - option == EEH_RESET_HOT) - msleep(EEH_PE_RST_HOLD_TIME); - else - msleep(EEH_PE_RST_SETTLE_TIME); - - return ret; + return pseries_eeh_phb_reset(pe->phb, config_addr, option); } /** @@ -641,108 +829,49 @@ static int pseries_eeh_get_log(struct eeh_pe *pe, int severity, char *drv_log, u * pseries_eeh_configure_bridge - Configure PCI bridges in the indicated PE * @pe: EEH PE * - * The function will be called to reconfigure the bridges included - * in the specified PE so that the mulfunctional PE would be recovered - * again. */ static int pseries_eeh_configure_bridge(struct eeh_pe *pe) { int config_addr; - int ret; - /* Waiting 0.2s maximum before skipping configuration */ - int max_wait = 200; /* Figure out the PE address */ config_addr = pe->config_addr; if (pe->addr) config_addr = pe->addr; - while (max_wait > 0) { - ret = rtas_call(ibm_configure_pe, 3, 1, NULL, - config_addr, BUID_HI(pe->phb->buid), - BUID_LO(pe->phb->buid)); - - if (!ret) - return ret; - if (ret < 0) - break; - - /* - * If RTAS returns a delay value that's above 100ms, cut it - * down to 100ms in case firmware made a mistake. For more - * on how these delay values work see rtas_busy_delay_time - */ - if (ret > RTAS_EXTENDED_DELAY_MIN+2 && - ret <= RTAS_EXTENDED_DELAY_MAX) - ret = RTAS_EXTENDED_DELAY_MIN+2; - - max_wait -= rtas_busy_delay_time(ret); - - if (max_wait < 0) - break; - - rtas_busy_delay(ret); - } - - pr_warn("%s: Unable to configure bridge PHB#%x-PE#%x (%d)\n", - __func__, pe->phb->global_number, pe->addr, ret); - /* PAPR defines -3 as "Parameter Error" for this function: */ - if (ret == -3) - return -EINVAL; - else - return -EIO; + return pseries_eeh_phb_configure_bridge(pe->phb, config_addr); } /** * pseries_eeh_read_config - Read PCI config space - * @pdn: PCI device node - * @where: PCI address + * @edev: EEH device handle + * @where: PCI config space offset * @size: size to read * @val: return value * * Read config space from the speicifed device */ -static int pseries_eeh_read_config(struct pci_dn *pdn, int where, int size, u32 *val) +static int pseries_eeh_read_config(struct eeh_dev *edev, int where, int size, u32 *val) { + struct pci_dn *pdn = eeh_dev_to_pdn(edev); + return rtas_read_config(pdn, where, size, val); } /** * pseries_eeh_write_config - Write PCI config space - * @pdn: PCI device node - * @where: PCI address + * @edev: EEH device handle + * @where: PCI config space offset * @size: size to write * @val: value to be written * * Write config space to the specified device */ -static int pseries_eeh_write_config(struct pci_dn *pdn, int where, int size, u32 val) +static int pseries_eeh_write_config(struct eeh_dev *edev, int where, int size, u32 val) { - return rtas_write_config(pdn, where, size, val); -} + struct pci_dn *pdn = eeh_dev_to_pdn(edev); -static int pseries_eeh_restore_config(struct pci_dn *pdn) -{ - struct eeh_dev *edev = pdn_to_eeh_dev(pdn); - s64 ret = 0; - - if (!edev) - return -EEXIST; - - /* - * FIXME: The MPS, error routing rules, timeout setting are worthy - * to be exported by firmware in extendible way. - */ - if (edev->physfn) - ret = eeh_restore_vf_config(pdn); - - if (ret) { - pr_warn("%s: Can't reinit PCI dev 0x%x (%lld)\n", - __func__, edev->pe_config_addr, ret); - return -EIO; - } - - return ret; + return rtas_write_config(pdn, where, size, val); } #ifdef CONFIG_PCI_IOV @@ -772,8 +901,8 @@ int pseries_send_allow_unfreeze(struct pci_dn *pdn, static int pseries_call_allow_unfreeze(struct eeh_dev *edev) { + int cur_vfs = 0, rc = 0, vf_index, bus, devfn, vf_pe_num; struct pci_dn *pdn, *tmp, *parent, *physfn_pdn; - int cur_vfs = 0, rc = 0, vf_index, bus, devfn; u16 *vf_pe_array; vf_pe_array = kzalloc(RTAS_DATA_BUF_SIZE, GFP_KERNEL); @@ -806,8 +935,10 @@ static int pseries_call_allow_unfreeze(struct eeh_dev *edev) } } else { pdn = pci_get_pdn(edev->pdev); - vf_pe_array[0] = cpu_to_be16(pdn->pe_number); physfn_pdn = pci_get_pdn(edev->physfn); + + vf_pe_num = physfn_pdn->pe_num_map[edev->vf_index]; + vf_pe_array[0] = cpu_to_be16(vf_pe_num); rc = pseries_send_allow_unfreeze(physfn_pdn, vf_pe_array, 1); pdn->last_allow_rc = rc; @@ -818,10 +949,8 @@ static int pseries_call_allow_unfreeze(struct eeh_dev *edev) return rc; } -static int pseries_notify_resume(struct pci_dn *pdn) +static int pseries_notify_resume(struct eeh_dev *edev) { - struct eeh_dev *edev = pdn_to_eeh_dev(pdn); - if (!edev) return -EEXIST; @@ -841,7 +970,6 @@ static struct eeh_ops pseries_eeh_ops = { .init = pseries_eeh_init, .probe = pseries_eeh_probe, .set_option = pseries_eeh_set_option, - .get_pe_addr = pseries_eeh_get_pe_addr, .get_state = pseries_eeh_get_state, .reset = pseries_eeh_reset, .get_log = pseries_eeh_get_log, @@ -850,7 +978,7 @@ static struct eeh_ops pseries_eeh_ops = { .read_config = pseries_eeh_read_config, .write_config = pseries_eeh_write_config, .next_error = NULL, - .restore_config = pseries_eeh_restore_config, + .restore_config = NULL, /* NB: configure_bridge() does this */ #ifdef CONFIG_PCI_IOV .notify_resume = pseries_notify_resume #endif diff --git a/arch/powerpc/platforms/pseries/firmware.c b/arch/powerpc/platforms/pseries/firmware.c index 3e49cc23a97a..4c7b7f5a2ebc 100644 --- a/arch/powerpc/platforms/pseries/firmware.c +++ b/arch/powerpc/platforms/pseries/firmware.c @@ -65,6 +65,7 @@ hypertas_fw_features_table[] = { {FW_FEATURE_HPT_RESIZE, "hcall-hpt-resize"}, {FW_FEATURE_BLOCK_REMOVE, "hcall-block-remove"}, {FW_FEATURE_PAPR_SCM, "hcall-scm"}, + {FW_FEATURE_RPT_INVALIDATE, "hcall-rpt-invalidate"}, }; /* Build up the firmware features bitmask using the contents of diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index 3e8cbfe7a80f..c6e0d8abf75e 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -35,54 +35,10 @@ #include <asm/topology.h> #include "pseries.h" -#include "offline_states.h" /* This version can't take the spinlock, because it never returns */ static int rtas_stop_self_token = RTAS_UNKNOWN_SERVICE; -static DEFINE_PER_CPU(enum cpu_state_vals, preferred_offline_state) = - CPU_STATE_OFFLINE; -static DEFINE_PER_CPU(enum cpu_state_vals, current_state) = CPU_STATE_OFFLINE; - -static enum cpu_state_vals default_offline_state = CPU_STATE_OFFLINE; - -static bool cede_offline_enabled __read_mostly = true; - -/* - * Enable/disable cede_offline when available. - */ -static int __init setup_cede_offline(char *str) -{ - return (kstrtobool(str, &cede_offline_enabled) == 0); -} - -__setup("cede_offline=", setup_cede_offline); - -enum cpu_state_vals get_cpu_current_state(int cpu) -{ - return per_cpu(current_state, cpu); -} - -void set_cpu_current_state(int cpu, enum cpu_state_vals state) -{ - per_cpu(current_state, cpu) = state; -} - -enum cpu_state_vals get_preferred_offline_state(int cpu) -{ - return per_cpu(preferred_offline_state, cpu); -} - -void set_preferred_offline_state(int cpu, enum cpu_state_vals state) -{ - per_cpu(preferred_offline_state, cpu) = state; -} - -void set_default_offline_state(int cpu) -{ - per_cpu(preferred_offline_state, cpu) = default_offline_state; -} - static void rtas_stop_self(void) { static struct rtas_args args; @@ -101,9 +57,7 @@ static void rtas_stop_self(void) static void pseries_mach_cpu_die(void) { - unsigned int cpu = smp_processor_id(); unsigned int hwcpu = hard_smp_processor_id(); - u8 cede_latency_hint = 0; local_irq_disable(); idle_task_exit(); @@ -112,49 +66,6 @@ static void pseries_mach_cpu_die(void) else xics_teardown_cpu(); - if (get_preferred_offline_state(cpu) == CPU_STATE_INACTIVE) { - set_cpu_current_state(cpu, CPU_STATE_INACTIVE); - if (ppc_md.suspend_disable_cpu) - ppc_md.suspend_disable_cpu(); - - cede_latency_hint = 2; - - get_lppaca()->idle = 1; - if (!lppaca_shared_proc(get_lppaca())) - get_lppaca()->donate_dedicated_cpu = 1; - - while (get_preferred_offline_state(cpu) == CPU_STATE_INACTIVE) { - while (!prep_irq_for_idle()) { - local_irq_enable(); - local_irq_disable(); - } - - extended_cede_processor(cede_latency_hint); - } - - local_irq_disable(); - - if (!lppaca_shared_proc(get_lppaca())) - get_lppaca()->donate_dedicated_cpu = 0; - get_lppaca()->idle = 0; - - if (get_preferred_offline_state(cpu) == CPU_STATE_ONLINE) { - unregister_slb_shadow(hwcpu); - - hard_irq_disable(); - /* - * Call to start_secondary_resume() will not return. - * Kernel stack will be reset and start_secondary() - * will be called to continue the online operation. - */ - start_secondary_resume(); - } - } - - /* Requested state is CPU_STATE_OFFLINE at this point */ - WARN_ON(get_preferred_offline_state(cpu) != CPU_STATE_OFFLINE); - - set_cpu_current_state(cpu, CPU_STATE_OFFLINE); unregister_slb_shadow(hwcpu); rtas_stop_self(); @@ -200,24 +111,13 @@ static void pseries_cpu_die(unsigned int cpu) int cpu_status = 1; unsigned int pcpu = get_hard_smp_processor_id(cpu); - if (get_preferred_offline_state(cpu) == CPU_STATE_INACTIVE) { - cpu_status = 1; - for (tries = 0; tries < 5000; tries++) { - if (get_cpu_current_state(cpu) == CPU_STATE_INACTIVE) { - cpu_status = 0; - break; - } - msleep(1); - } - } else if (get_preferred_offline_state(cpu) == CPU_STATE_OFFLINE) { + for (tries = 0; tries < 25; tries++) { + cpu_status = smp_query_cpu_stopped(pcpu); + if (cpu_status == QCSS_STOPPED || + cpu_status == QCSS_HARDWARE_ERROR) + break; + cpu_relax(); - for (tries = 0; tries < 25; tries++) { - cpu_status = smp_query_cpu_stopped(pcpu); - if (cpu_status == QCSS_STOPPED || - cpu_status == QCSS_HARDWARE_ERROR) - break; - cpu_relax(); - } } if (cpu_status != 0) { @@ -359,28 +259,14 @@ static int dlpar_offline_cpu(struct device_node *dn) if (get_hard_smp_processor_id(cpu) != thread) continue; - if (get_cpu_current_state(cpu) == CPU_STATE_OFFLINE) + if (!cpu_online(cpu)) break; - if (get_cpu_current_state(cpu) == CPU_STATE_ONLINE) { - set_preferred_offline_state(cpu, - CPU_STATE_OFFLINE); - cpu_maps_update_done(); - timed_topology_update(1); - rc = device_offline(get_cpu_device(cpu)); - if (rc) - goto out; - cpu_maps_update_begin(); - break; - } - - /* - * The cpu is in CPU_STATE_INACTIVE. - * Upgrade it's state to CPU_STATE_OFFLINE. - */ - set_preferred_offline_state(cpu, CPU_STATE_OFFLINE); - WARN_ON(plpar_hcall_norets(H_PROD, thread) != H_SUCCESS); - __cpu_die(cpu); + cpu_maps_update_done(); + rc = device_offline(get_cpu_device(cpu)); + if (rc) + goto out; + cpu_maps_update_begin(); break; } if (cpu == num_possible_cpus()) { @@ -414,10 +300,7 @@ static int dlpar_online_cpu(struct device_node *dn) for_each_present_cpu(cpu) { if (get_hard_smp_processor_id(cpu) != thread) continue; - BUG_ON(get_cpu_current_state(cpu) - != CPU_STATE_OFFLINE); cpu_maps_update_done(); - timed_topology_update(1); find_and_online_cpu_nid(cpu); rc = device_online(get_cpu_device(cpu)); if (rc) { @@ -854,7 +737,6 @@ static int dlpar_cpu_add_by_count(u32 cpus_to_add) parent = of_find_node_by_path("/cpus"); if (!parent) { pr_warn("Could not find CPU root node in device tree\n"); - kfree(cpu_drcs); return -1; } @@ -896,25 +778,6 @@ static int dlpar_cpu_add_by_count(u32 cpus_to_add) return rc; } -int dlpar_cpu_readd(int cpu) -{ - struct device_node *dn; - struct device *dev; - u32 drc_index; - int rc; - - dev = get_cpu_device(cpu); - dn = dev->of_node; - - rc = of_property_read_u32(dn, "ibm,my-drc-index", &drc_index); - - rc = dlpar_cpu_remove_by_index(drc_index); - if (!rc) - rc = dlpar_cpu_add(drc_index); - - return rc; -} - int dlpar_cpu(struct pseries_hp_errorlog *hp_elog) { u32 count, drc_index; @@ -1013,27 +876,8 @@ static struct notifier_block pseries_smp_nb = { .notifier_call = pseries_smp_notifier, }; -#define MAX_CEDE_LATENCY_LEVELS 4 -#define CEDE_LATENCY_PARAM_LENGTH 10 -#define CEDE_LATENCY_PARAM_MAX_LENGTH \ - (MAX_CEDE_LATENCY_LEVELS * CEDE_LATENCY_PARAM_LENGTH * sizeof(char)) -#define CEDE_LATENCY_TOKEN 45 - -static char cede_parameters[CEDE_LATENCY_PARAM_MAX_LENGTH]; - -static int parse_cede_parameters(void) -{ - memset(cede_parameters, 0, CEDE_LATENCY_PARAM_MAX_LENGTH); - return rtas_call(rtas_token("ibm,get-system-parameter"), 3, 1, - NULL, - CEDE_LATENCY_TOKEN, - __pa(cede_parameters), - CEDE_LATENCY_PARAM_MAX_LENGTH); -} - static int __init pseries_cpu_hotplug_init(void) { - int cpu; int qcss_tok; #ifdef CONFIG_ARCH_CPU_PROBE_RELEASE @@ -1056,16 +900,8 @@ static int __init pseries_cpu_hotplug_init(void) smp_ops->cpu_die = pseries_cpu_die; /* Processors can be added/removed only on LPAR */ - if (firmware_has_feature(FW_FEATURE_LPAR)) { + if (firmware_has_feature(FW_FEATURE_LPAR)) of_reconfig_notifier_register(&pseries_smp_nb); - cpu_maps_update_begin(); - if (cede_offline_enabled && parse_cede_parameters() == 0) { - default_offline_state = CPU_STATE_INACTIVE; - for_each_online_cpu(cpu) - set_default_offline_state(cpu); - } - cpu_maps_update_done(); - } return 0; } diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 5ace2f9a277e..5d545b78111f 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -22,12 +22,10 @@ #include <asm/drmem.h> #include "pseries.h" -static bool rtas_hp_event; - unsigned long pseries_memory_block_size(void) { struct device_node *np; - unsigned int memblock_size = MIN_MEMORY_BLOCK_SIZE; + u64 memblock_size = MIN_MEMORY_BLOCK_SIZE; struct resource r; np = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory"); @@ -487,40 +485,6 @@ static int dlpar_memory_remove_by_index(u32 drc_index) return rc; } -static int dlpar_memory_readd_by_index(u32 drc_index) -{ - struct drmem_lmb *lmb; - int lmb_found; - int rc; - - pr_info("Attempting to update LMB, drc index %x\n", drc_index); - - lmb_found = 0; - for_each_drmem_lmb(lmb) { - if (lmb->drc_index == drc_index) { - lmb_found = 1; - rc = dlpar_remove_lmb(lmb); - if (!rc) { - rc = dlpar_add_lmb(lmb); - if (rc) - dlpar_release_drc(lmb->drc_index); - } - break; - } - } - - if (!lmb_found) - rc = -EINVAL; - - if (rc) - pr_info("Failed to update memory at %llx\n", - lmb->base_addr); - else - pr_info("Memory at %llx was updated\n", lmb->base_addr); - - return rc; -} - static int dlpar_memory_remove_by_ic(u32 lmbs_to_remove, u32 drc_index) { struct drmem_lmb *lmb, *start_lmb, *end_lmb; @@ -617,10 +581,6 @@ static int dlpar_memory_remove_by_index(u32 drc_index) { return -EOPNOTSUPP; } -static int dlpar_memory_readd_by_index(u32 drc_index) -{ - return -EOPNOTSUPP; -} static int dlpar_memory_remove_by_ic(u32 lmbs_to_remove, u32 drc_index) { @@ -903,21 +863,14 @@ int dlpar_memory(struct pseries_hp_errorlog *hp_elog) } break; - case PSERIES_HP_ELOG_ACTION_READD: - drc_index = hp_elog->_drc_u.drc_index; - rc = dlpar_memory_readd_by_index(drc_index); - break; default: pr_err("Invalid action (%d) specified\n", hp_elog->action); rc = -EINVAL; break; } - if (!rc) { - rtas_hp_event = true; + if (!rc) rc = drmem_update_dt(); - rtas_hp_event = false; - } unlock_device_hotplug(); return rc; @@ -953,60 +906,6 @@ static int pseries_add_mem_node(struct device_node *np) return (ret < 0) ? -EINVAL : 0; } -static int pseries_update_drconf_memory(struct of_reconfig_data *pr) -{ - struct of_drconf_cell_v1 *new_drmem, *old_drmem; - unsigned long memblock_size; - u32 entries; - __be32 *p; - int i, rc = -EINVAL; - - if (rtas_hp_event) - return 0; - - memblock_size = pseries_memory_block_size(); - if (!memblock_size) - return -EINVAL; - - if (!pr->old_prop) - return 0; - - p = (__be32 *) pr->old_prop->value; - if (!p) - return -EINVAL; - - /* The first int of the property is the number of lmb's described - * by the property. This is followed by an array of of_drconf_cell - * entries. Get the number of entries and skip to the array of - * of_drconf_cell's. - */ - entries = be32_to_cpu(*p++); - old_drmem = (struct of_drconf_cell_v1 *)p; - - p = (__be32 *)pr->prop->value; - p++; - new_drmem = (struct of_drconf_cell_v1 *)p; - - for (i = 0; i < entries; i++) { - if ((be32_to_cpu(old_drmem[i].flags) & DRCONF_MEM_ASSIGNED) && - (!(be32_to_cpu(new_drmem[i].flags) & DRCONF_MEM_ASSIGNED))) { - rc = pseries_remove_memblock( - be64_to_cpu(old_drmem[i].base_addr), - memblock_size); - break; - } else if ((!(be32_to_cpu(old_drmem[i].flags) & - DRCONF_MEM_ASSIGNED)) && - (be32_to_cpu(new_drmem[i].flags) & - DRCONF_MEM_ASSIGNED)) { - rc = memblock_add(be64_to_cpu(old_drmem[i].base_addr), - memblock_size); - rc = (rc < 0) ? -EINVAL : 0; - break; - } - } - return rc; -} - static int pseries_memory_notifier(struct notifier_block *nb, unsigned long action, void *data) { @@ -1020,10 +919,6 @@ static int pseries_memory_notifier(struct notifier_block *nb, case OF_RECONFIG_DETACH_NODE: err = pseries_remove_mem_node(rd->dn); break; - case OF_RECONFIG_UPDATE_PROPERTY: - if (!strcmp(rd->prop->name, "ibm,dynamic-memory")) - err = pseries_update_drconf_memory(rd); - break; } return notifier_from_errno(err); } diff --git a/arch/powerpc/platforms/pseries/hvcserver.c b/arch/powerpc/platforms/pseries/hvcserver.c index 267139b13530..96e18d3b2fcf 100644 --- a/arch/powerpc/platforms/pseries/hvcserver.c +++ b/arch/powerpc/platforms/pseries/hvcserver.c @@ -45,7 +45,7 @@ static int hvcs_convert(long to_convert) case H_LONG_BUSY_ORDER_10_SEC: case H_LONG_BUSY_ORDER_100_SEC: return -EBUSY; - case H_FUNCTION: /* fall through */ + case H_FUNCTION: default: return -EPERM; } diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index f71ff2c94efe..baf24eacd268 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -1681,9 +1681,11 @@ static int pseries_lpar_register_process_table(unsigned long base, if (table_size) flags |= PROC_TABLE_NEW; - if (radix_enabled()) - flags |= PROC_TABLE_RADIX | PROC_TABLE_GTSE; - else + if (radix_enabled()) { + flags |= PROC_TABLE_RADIX; + if (mmu_has_feature(MMU_FTR_GTSE)) + flags |= PROC_TABLE_GTSE; + } else flags |= PROC_TABLE_HPT_SLB; for (;;) { rc = plpar_hcall_norets(H_REGISTER_PROC_TBL, flags, base, diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index 10d982997736..d6f4162478a5 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -6,6 +6,9 @@ * Copyright (C) 2010 IBM Corporation */ + +#define pr_fmt(fmt) "mobility: " fmt + #include <linux/cpu.h> #include <linux/kernel.h> #include <linux/kobject.h> @@ -64,6 +67,8 @@ static int delete_dt_node(__be32 phandle) if (!dn) return -ENOENT; + pr_debug("removing node %pOFfp\n", dn); + dlpar_detach_node(dn); of_node_put(dn); return 0; @@ -122,6 +127,7 @@ static int update_dt_property(struct device_node *dn, struct property **prop, } if (!more) { + pr_debug("updating node %pOF property %s\n", dn, name); of_update_property(dn, new_prop); *prop = NULL; } @@ -240,33 +246,12 @@ static int add_dt_node(__be32 parent_phandle, __be32 drc_index) if (rc) dlpar_free_cc_nodes(dn); + pr_debug("added node %pOFfp\n", dn); + of_node_put(parent_dn); return rc; } -static void prrn_update_node(__be32 phandle) -{ - struct pseries_hp_errorlog hp_elog; - struct device_node *dn; - - /* - * If a node is found from a the given phandle, the phandle does not - * represent the drc index of an LMB and we can ignore. - */ - dn = of_find_node_by_phandle(be32_to_cpu(phandle)); - if (dn) { - of_node_put(dn); - return; - } - - hp_elog.resource = PSERIES_HP_ELOG_RESOURCE_MEM; - hp_elog.action = PSERIES_HP_ELOG_ACTION_READD; - hp_elog.id_type = PSERIES_HP_ELOG_ID_DRC_INDEX; - hp_elog._drc_u.drc_index = phandle; - - handle_dlpar_errorlog(&hp_elog); -} - int pseries_devicetree_update(s32 scope) { char *rtas_buf; @@ -305,10 +290,6 @@ int pseries_devicetree_update(s32 scope) break; case UPDATE_DT_NODE: update_dt_node(phandle, scope); - - if (scope == PRRN_SCOPE) - prrn_update_node(phandle); - break; case ADD_DT_NODE: drc_index = *data++; @@ -388,8 +369,6 @@ static ssize_t migration_store(struct class *class, if (rc) return rc; - stop_topology_update(); - do { rc = rtas_ibm_suspend_me(streamid); if (rc == -EAGAIN) @@ -401,8 +380,6 @@ static ssize_t migration_store(struct class *class, post_mobility_fixup(); - start_topology_update(); - return count; } @@ -427,11 +404,11 @@ static int __init mobility_sysfs_init(void) rc = sysfs_create_file(mobility_kobj, &class_attr_migration.attr); if (rc) - pr_err("mobility: unable to create migration sysfs file (%d)\n", rc); + pr_err("unable to create migration sysfs file (%d)\n", rc); rc = sysfs_create_file(mobility_kobj, &class_attr_api_version.attr.attr); if (rc) - pr_err("mobility: unable to create api_version sysfs file (%d)\n", rc); + pr_err("unable to create api_version sysfs file (%d)\n", rc); return 0; } diff --git a/arch/powerpc/platforms/pseries/offline_states.h b/arch/powerpc/platforms/pseries/offline_states.h deleted file mode 100644 index 51414aee2862..000000000000 --- a/arch/powerpc/platforms/pseries/offline_states.h +++ /dev/null @@ -1,38 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _OFFLINE_STATES_H_ -#define _OFFLINE_STATES_H_ - -/* Cpu offline states go here */ -enum cpu_state_vals { - CPU_STATE_OFFLINE, - CPU_STATE_INACTIVE, - CPU_STATE_ONLINE, - CPU_MAX_OFFLINE_STATES -}; - -#ifdef CONFIG_HOTPLUG_CPU -extern enum cpu_state_vals get_cpu_current_state(int cpu); -extern void set_cpu_current_state(int cpu, enum cpu_state_vals state); -extern void set_preferred_offline_state(int cpu, enum cpu_state_vals state); -extern void set_default_offline_state(int cpu); -#else -static inline enum cpu_state_vals get_cpu_current_state(int cpu) -{ - return CPU_STATE_ONLINE; -} - -static inline void set_cpu_current_state(int cpu, enum cpu_state_vals state) -{ -} - -static inline void set_preferred_offline_state(int cpu, enum cpu_state_vals state) -{ -} - -static inline void set_default_offline_state(int cpu) -{ -} -#endif - -extern enum cpu_state_vals get_preferred_offline_state(int cpu); -#endif diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index 9c569078a09f..f439f0dfea7d 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -13,9 +13,11 @@ #include <linux/platform_device.h> #include <linux/delay.h> #include <linux/seq_buf.h> +#include <linux/nd.h> #include <asm/plpar_wrappers.h> #include <asm/papr_pdsm.h> +#include <asm/mce.h> #define BIND_ANY_ADDR (~0ul) @@ -62,6 +64,26 @@ PAPR_PMEM_HEALTH_FATAL | \ PAPR_PMEM_HEALTH_UNHEALTHY) +#define PAPR_SCM_PERF_STATS_EYECATCHER __stringify(SCMSTATS) +#define PAPR_SCM_PERF_STATS_VERSION 0x1 + +/* Struct holding a single performance metric */ +struct papr_scm_perf_stat { + u8 stat_id[8]; + __be64 stat_val; +} __packed; + +/* Struct exchanged between kernel and PHYP for fetching drc perf stats */ +struct papr_scm_perf_stats { + u8 eye_catcher[8]; + /* Should be PAPR_SCM_PERF_STATS_VERSION */ + __be32 stats_version; + /* Number of stats following */ + __be32 num_statistics; + /* zero or more performance matrics */ + struct papr_scm_perf_stat scm_statistic[]; +} __packed; + /* private struct associated with each region */ struct papr_scm_priv { struct platform_device *pdev; @@ -80,6 +102,7 @@ struct papr_scm_priv { struct resource res; struct nd_region *region; struct nd_interleave_set nd_set; + struct list_head region_list; /* Protect dimm health data from concurrent read/writes */ struct mutex health_mutex; @@ -89,8 +112,14 @@ struct papr_scm_priv { /* Health information for the dimm */ u64 health_bitmap; + + /* length of the stat buffer as expected by phyp */ + size_t stat_buffer_len; }; +static LIST_HEAD(papr_nd_regions); +static DEFINE_MUTEX(papr_ndr_lock); + static int drc_pmem_bind(struct papr_scm_priv *p) { unsigned long ret[PLPAR_HCALL_BUFSIZE]; @@ -195,6 +224,79 @@ err_out: } /* + * Query the Dimm performance stats from PHYP and copy them (if returned) to + * provided struct papr_scm_perf_stats instance 'stats' that can hold atleast + * (num_stats + header) bytes. + * - If buff_stats == NULL the return value is the size in byes of the buffer + * needed to hold all supported performance-statistics. + * - If buff_stats != NULL and num_stats == 0 then we copy all known + * performance-statistics to 'buff_stat' and expect to be large enough to + * hold them. + * - if buff_stats != NULL and num_stats > 0 then copy the requested + * performance-statistics to buff_stats. + */ +static ssize_t drc_pmem_query_stats(struct papr_scm_priv *p, + struct papr_scm_perf_stats *buff_stats, + unsigned int num_stats) +{ + unsigned long ret[PLPAR_HCALL_BUFSIZE]; + size_t size; + s64 rc; + + /* Setup the out buffer */ + if (buff_stats) { + memcpy(buff_stats->eye_catcher, + PAPR_SCM_PERF_STATS_EYECATCHER, 8); + buff_stats->stats_version = + cpu_to_be32(PAPR_SCM_PERF_STATS_VERSION); + buff_stats->num_statistics = + cpu_to_be32(num_stats); + + /* + * Calculate the buffer size based on num-stats provided + * or use the prefetched max buffer length + */ + if (num_stats) + /* Calculate size from the num_stats */ + size = sizeof(struct papr_scm_perf_stats) + + num_stats * sizeof(struct papr_scm_perf_stat); + else + size = p->stat_buffer_len; + } else { + /* In case of no out buffer ignore the size */ + size = 0; + } + + /* Do the HCALL asking PHYP for info */ + rc = plpar_hcall(H_SCM_PERFORMANCE_STATS, ret, p->drc_index, + buff_stats ? virt_to_phys(buff_stats) : 0, + size); + + /* Check if the error was due to an unknown stat-id */ + if (rc == H_PARTIAL) { + dev_err(&p->pdev->dev, + "Unknown performance stats, Err:0x%016lX\n", ret[0]); + return -ENOENT; + } else if (rc != H_SUCCESS) { + dev_err(&p->pdev->dev, + "Failed to query performance stats, Err:%lld\n", rc); + return -EIO; + + } else if (!size) { + /* Handle case where stat buffer size was requested */ + dev_dbg(&p->pdev->dev, + "Performance stats size %ld\n", ret[0]); + return ret[0]; + } + + /* Successfully fetched the requested stats from phyp */ + dev_dbg(&p->pdev->dev, + "Performance stats returned %d stats\n", + be32_to_cpu(buff_stats->num_statistics)); + return 0; +} + +/* * Issue hcall to retrieve dimm health info and populate papr_scm_priv with the * health information. */ @@ -416,6 +518,51 @@ static int is_cmd_valid(struct nvdimm *nvdimm, unsigned int cmd, void *buf, return 0; } +static int papr_pdsm_fuel_gauge(struct papr_scm_priv *p, + union nd_pdsm_payload *payload) +{ + int rc, size; + u64 statval; + struct papr_scm_perf_stat *stat; + struct papr_scm_perf_stats *stats; + + /* Silently fail if fetching performance metrics isn't supported */ + if (!p->stat_buffer_len) + return 0; + + /* Allocate request buffer enough to hold single performance stat */ + size = sizeof(struct papr_scm_perf_stats) + + sizeof(struct papr_scm_perf_stat); + + stats = kzalloc(size, GFP_KERNEL); + if (!stats) + return -ENOMEM; + + stat = &stats->scm_statistic[0]; + memcpy(&stat->stat_id, "MemLife ", sizeof(stat->stat_id)); + stat->stat_val = 0; + + /* Fetch the fuel gauge and populate it in payload */ + rc = drc_pmem_query_stats(p, stats, 1); + if (rc < 0) { + dev_dbg(&p->pdev->dev, "Err(%d) fetching fuel gauge\n", rc); + goto free_stats; + } + + statval = be64_to_cpu(stat->stat_val); + dev_dbg(&p->pdev->dev, + "Fetched fuel-gauge %llu", statval); + payload->health.extension_flags |= + PDSM_DIMM_HEALTH_RUN_GAUGE_VALID; + payload->health.dimm_fuel_gauge = statval; + + rc = sizeof(struct nd_papr_pdsm_health); + +free_stats: + kfree(stats); + return rc; +} + /* Fetch the DIMM health info and populate it in provided package. */ static int papr_pdsm_health(struct papr_scm_priv *p, union nd_pdsm_payload *payload) @@ -456,6 +603,10 @@ static int papr_pdsm_health(struct papr_scm_priv *p, /* struct populated hence can release the mutex now */ mutex_unlock(&p->health_mutex); + + /* Populate the fuel gauge meter in the payload */ + papr_pdsm_fuel_gauge(p, payload); + rc = sizeof(struct nd_papr_pdsm_health); out: @@ -631,6 +782,48 @@ static int papr_scm_ndctl(struct nvdimm_bus_descriptor *nd_desc, return 0; } +static ssize_t perf_stats_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + int index, rc; + struct seq_buf s; + struct papr_scm_perf_stat *stat; + struct papr_scm_perf_stats *stats; + struct nvdimm *dimm = to_nvdimm(dev); + struct papr_scm_priv *p = nvdimm_provider_data(dimm); + + if (!p->stat_buffer_len) + return -ENOENT; + + /* Allocate the buffer for phyp where stats are written */ + stats = kzalloc(p->stat_buffer_len, GFP_KERNEL); + if (!stats) + return -ENOMEM; + + /* Ask phyp to return all dimm perf stats */ + rc = drc_pmem_query_stats(p, stats, 0); + if (rc) + goto free_stats; + /* + * Go through the returned output buffer and print stats and + * values. Since stat_id is essentially a char string of + * 8 bytes, simply use the string format specifier to print it. + */ + seq_buf_init(&s, buf, PAGE_SIZE); + for (index = 0, stat = stats->scm_statistic; + index < be32_to_cpu(stats->num_statistics); + ++index, ++stat) { + seq_buf_printf(&s, "%.8s = 0x%016llX\n", + stat->stat_id, + be64_to_cpu(stat->stat_val)); + } + +free_stats: + kfree(stats); + return rc ? rc : seq_buf_used(&s); +} +DEVICE_ATTR_RO(perf_stats); + static ssize_t flags_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -676,6 +869,7 @@ DEVICE_ATTR_RO(flags); /* papr_scm specific dimm attributes */ static struct attribute *papr_nd_attributes[] = { &dev_attr_flags.attr, + &dev_attr_perf_stats.attr, NULL, }; @@ -696,6 +890,7 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p) struct nd_region_desc ndr_desc; unsigned long dimm_flags; int target_nid, online_nid; + ssize_t stat_size; p->bus_desc.ndctl = papr_scm_ndctl; p->bus_desc.module = THIS_MODULE; @@ -759,6 +954,20 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p) dev_info(dev, "Region registered with target node %d and online node %d", target_nid, online_nid); + mutex_lock(&papr_ndr_lock); + list_add_tail(&p->region_list, &papr_nd_regions); + mutex_unlock(&papr_ndr_lock); + + /* Try retriving the stat buffer and see if its supported */ + stat_size = drc_pmem_query_stats(p, NULL, 0); + if (stat_size > 0) { + p->stat_buffer_len = stat_size; + dev_dbg(&p->pdev->dev, "Max perf-stat size %lu-bytes\n", + p->stat_buffer_len); + } else { + dev_info(&p->pdev->dev, "Dimm performance stats unavailable\n"); + } + return 0; err: nvdimm_bus_unregister(p->bus); @@ -766,6 +975,68 @@ err: nvdimm_bus_unregister(p->bus); return -ENXIO; } +static void papr_scm_add_badblock(struct nd_region *region, + struct nvdimm_bus *bus, u64 phys_addr) +{ + u64 aligned_addr = ALIGN_DOWN(phys_addr, L1_CACHE_BYTES); + + if (nvdimm_bus_add_badrange(bus, aligned_addr, L1_CACHE_BYTES)) { + pr_err("Bad block registration for 0x%llx failed\n", phys_addr); + return; + } + + pr_debug("Add memory range (0x%llx - 0x%llx) as bad range\n", + aligned_addr, aligned_addr + L1_CACHE_BYTES); + + nvdimm_region_notify(region, NVDIMM_REVALIDATE_POISON); +} + +static int handle_mce_ue(struct notifier_block *nb, unsigned long val, + void *data) +{ + struct machine_check_event *evt = data; + struct papr_scm_priv *p; + u64 phys_addr; + bool found = false; + + if (evt->error_type != MCE_ERROR_TYPE_UE) + return NOTIFY_DONE; + + if (list_empty(&papr_nd_regions)) + return NOTIFY_DONE; + + /* + * The physical address obtained here is PAGE_SIZE aligned, so get the + * exact address from the effective address + */ + phys_addr = evt->u.ue_error.physical_address + + (evt->u.ue_error.effective_address & ~PAGE_MASK); + + if (!evt->u.ue_error.physical_address_provided || + !is_zone_device_page(pfn_to_page(phys_addr >> PAGE_SHIFT))) + return NOTIFY_DONE; + + /* mce notifier is called from a process context, so mutex is safe */ + mutex_lock(&papr_ndr_lock); + list_for_each_entry(p, &papr_nd_regions, region_list) { + if (phys_addr >= p->res.start && phys_addr <= p->res.end) { + found = true; + break; + } + } + + if (found) + papr_scm_add_badblock(p->region, p->bus, phys_addr); + + mutex_unlock(&papr_ndr_lock); + + return found ? NOTIFY_OK : NOTIFY_DONE; +} + +static struct notifier_block mce_ue_nb = { + .notifier_call = handle_mce_ue +}; + static int papr_scm_probe(struct platform_device *pdev) { struct device_node *dn = pdev->dev.of_node; @@ -866,6 +1137,10 @@ static int papr_scm_remove(struct platform_device *pdev) { struct papr_scm_priv *p = platform_get_drvdata(pdev); + mutex_lock(&papr_ndr_lock); + list_del(&p->region_list); + mutex_unlock(&papr_ndr_lock); + nvdimm_bus_unregister(p->bus); drc_pmem_unbind(p); kfree(p->bus_desc.provider_name); @@ -876,6 +1151,7 @@ static int papr_scm_remove(struct platform_device *pdev) static const struct of_device_id papr_scm_match[] = { { .compatible = "ibm,pmemory" }, + { .compatible = "ibm,pmemory-v2" }, { }, }; @@ -888,7 +1164,25 @@ static struct platform_driver papr_scm_driver = { }, }; -module_platform_driver(papr_scm_driver); +static int __init papr_scm_init(void) +{ + int ret; + + ret = platform_driver_register(&papr_scm_driver); + if (!ret) + mce_register_notifier(&mce_ue_nb); + + return ret; +} +module_init(papr_scm_init); + +static void __exit papr_scm_exit(void) +{ + mce_unregister_notifier(&mce_ue_nb); + platform_driver_unregister(&papr_scm_driver); +} +module_exit(papr_scm_exit); + MODULE_DEVICE_TABLE(of, papr_scm_match); MODULE_LICENSE("GPL"); MODULE_AUTHOR("IBM Corporation"); diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c index b3a38f5a6b68..f9ae17e8a0f4 100644 --- a/arch/powerpc/platforms/pseries/pci_dlpar.c +++ b/arch/powerpc/platforms/pseries/pci_dlpar.c @@ -34,7 +34,7 @@ struct pci_controller *init_phb_dynamic(struct device_node *dn) pci_devs_phb_init_dynamic(phb); /* Create EEH devices for the PHB */ - eeh_dev_phb_init_dynamic(phb); + eeh_phb_pe_create(phb); if (dn->child) pseries_eeh_init_edev_recursive(PCI_DN(dn)); diff --git a/arch/powerpc/platforms/pseries/pmem.c b/arch/powerpc/platforms/pseries/pmem.c index f860a897a9e0..e1dc5d3254df 100644 --- a/arch/powerpc/platforms/pseries/pmem.c +++ b/arch/powerpc/platforms/pseries/pmem.c @@ -24,7 +24,6 @@ #include <asm/topology.h> #include "pseries.h" -#include "offline_states.h" static struct device_node *pmem_node; @@ -147,6 +146,12 @@ const struct of_device_id drc_pmem_match[] = { static int pseries_pmem_init(void) { + /* + * Only supported on POWER8 and above. + */ + if (!cpu_has_feature(CPU_FTR_ARCH_207S)) + return 0; + pmem_node = of_find_node_by_type(NULL, "ibm,persistent-memory"); if (!pmem_node) return 0; diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 27094c872fd6..2f4ee0a90284 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -359,7 +359,7 @@ static void pseries_lpar_idle(void) * to ever be a problem in practice we can move this into a kernel thread to * finish off the process later in boot. */ -void pseries_enable_reloc_on_exc(void) +bool pseries_enable_reloc_on_exc(void) { long rc; unsigned int delay, total_delay = 0; @@ -370,11 +370,13 @@ void pseries_enable_reloc_on_exc(void) if (rc == H_P2) { pr_info("Relocation on exceptions not" " supported\n"); + return false; } else if (rc != H_SUCCESS) { pr_warn("Unable to enable relocation" " on exceptions: %ld\n", rc); + return false; } - break; + return true; } delay = get_longbusy_msecs(rc); @@ -383,7 +385,7 @@ void pseries_enable_reloc_on_exc(void) pr_warn("Warning: Giving up waiting to enable " "relocation on exceptions (%u msec)!\n", total_delay); - return; + return false; } mdelay(delay); @@ -746,6 +748,11 @@ static void __init pSeries_setup_arch(void) smp_init_pseries(); + if (radix_enabled() && !mmu_has_feature(MMU_FTR_GTSE)) + if (!firmware_has_feature(FW_FEATURE_RPT_INVALIDATE)) + panic("BUG: Radix support requires either GTSE or RPT_INVALIDATE\n"); + + /* openpic global configuration register (64-bit format). */ /* openpic Interrupt Source Unit pointer (64-bit format). */ /* python0 facility area (mmio) (64-bit format) REAL address. */ @@ -772,8 +779,10 @@ static void __init pSeries_setup_arch(void) if (firmware_has_feature(FW_FEATURE_LPAR)) { vpa_init(boot_cpuid); - if (lppaca_shared_proc(get_lppaca())) + if (lppaca_shared_proc(get_lppaca())) { static_branch_enable(&shared_processor); + pv_spinlocks_init(); + } ppc_md.power_save = pseries_lpar_idle; ppc_md.enable_pmcs = pseries_lpar_enable_pmcs; @@ -832,12 +841,15 @@ static int pseries_set_xdabr(unsigned long dabr, unsigned long dabrx) return plpar_hcall_norets(H_SET_XDABR, dabr, dabrx); } -static int pseries_set_dawr(unsigned long dawr, unsigned long dawrx) +static int pseries_set_dawr(int nr, unsigned long dawr, unsigned long dawrx) { /* PAPR says we can't set HYP */ dawrx &= ~DAWRX_HYP; - return plpar_set_watchpoint0(dawr, dawrx); + if (nr == 0) + return plpar_set_watchpoint0(dawr, dawrx); + else + return plpar_set_watchpoint1(dawr, dawrx); } #define CMO_CHARACTERISTICS_TOKEN 44 diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c index 6891710833be..92922491a81c 100644 --- a/arch/powerpc/platforms/pseries/smp.c +++ b/arch/powerpc/platforms/pseries/smp.c @@ -44,8 +44,6 @@ #include <asm/svm.h> #include "pseries.h" -#include "offline_states.h" - /* * The Primary thread of each non-boot processor was started from the OF client @@ -108,10 +106,7 @@ static inline int smp_startup_cpu(unsigned int lcpu) /* Fixup atomic count: it exited inside IRQ handler. */ task_thread_info(paca_ptrs[lcpu]->__current)->preempt_count = 0; -#ifdef CONFIG_HOTPLUG_CPU - if (get_cpu_current_state(lcpu) == CPU_STATE_INACTIVE) - goto out; -#endif + /* * If the RTAS start-cpu token does not exist then presume the * cpu is already spinning. @@ -126,9 +121,6 @@ static inline int smp_startup_cpu(unsigned int lcpu) return 0; } -#ifdef CONFIG_HOTPLUG_CPU -out: -#endif return 1; } @@ -143,10 +135,6 @@ static void smp_setup_cpu(int cpu) vpa_init(cpu); cpumask_clear_cpu(cpu, of_spin_mask); -#ifdef CONFIG_HOTPLUG_CPU - set_cpu_current_state(cpu, CPU_STATE_ONLINE); - set_default_offline_state(cpu); -#endif } static int smp_pSeries_kick_cpu(int nr) @@ -163,20 +151,6 @@ static int smp_pSeries_kick_cpu(int nr) * the processor will continue on to secondary_start */ paca_ptrs[nr]->cpu_start = 1; -#ifdef CONFIG_HOTPLUG_CPU - set_preferred_offline_state(nr, CPU_STATE_ONLINE); - - if (get_cpu_current_state(nr) == CPU_STATE_INACTIVE) { - long rc; - unsigned long hcpuid; - - hcpuid = get_hard_smp_processor_id(nr); - rc = plpar_hcall_norets(H_PROD, hcpuid); - if (rc != H_SUCCESS) - printk(KERN_ERR "Error: Prod to wake up processor %d " - "Ret= %ld\n", nr, rc); - } -#endif return 0; } @@ -188,13 +162,16 @@ static int pseries_smp_prepare_cpu(int cpu) return 0; } -static void smp_pseries_cause_ipi(int cpu) +/* Cause IPI as setup by the interrupt controller (xics or xive) */ +static void (*ic_cause_ipi)(int cpu) __ro_after_init; + +/* Use msgsndp doorbells target is a sibling, else use interrupt controller */ +static void dbell_or_ic_cause_ipi(int cpu) { - /* POWER9 should not use this handler */ if (doorbell_try_core_ipi(cpu)) return; - icp_ops->cause_ipi(cpu); + ic_cause_ipi(cpu); } static int pseries_cause_nmi_ipi(int cpu) @@ -218,26 +195,49 @@ static int pseries_cause_nmi_ipi(int cpu) return 0; } -static __init void pSeries_smp_probe_xics(void) -{ - xics_smp_probe(); - - if (cpu_has_feature(CPU_FTR_DBELL) && !is_secure_guest()) - smp_ops->cause_ipi = smp_pseries_cause_ipi; - else - smp_ops->cause_ipi = icp_ops->cause_ipi; -} - static __init void pSeries_smp_probe(void) { if (xive_enabled()) - /* - * Don't use P9 doorbells when XIVE is enabled. IPIs - * using MMIOs should be faster - */ xive_smp_probe(); else - pSeries_smp_probe_xics(); + xics_smp_probe(); + + /* No doorbell facility, must use the interrupt controller for IPIs */ + if (!cpu_has_feature(CPU_FTR_DBELL)) + return; + + /* Doorbells can only be used for IPIs between SMT siblings */ + if (!cpu_has_feature(CPU_FTR_SMT)) + return; + + if (is_kvm_guest()) { + /* + * KVM emulates doorbells by disabling FSCR[MSGP] so msgsndp + * faults to the hypervisor which then reads the instruction + * from guest memory, which tends to be slower than using XIVE. + */ + if (xive_enabled()) + return; + + /* + * XICS hcalls aren't as fast, so we can use msgsndp (which + * also helps exercise KVM emulation), however KVM can't + * emulate secure guests because it can't read the instruction + * out of their memory. + */ + if (is_secure_guest()) + return; + } + + /* + * Under PowerVM, FSCR[MSGP] is enabled as guest vCPU siblings are + * gang scheduled on the same physical core, so doorbells are always + * faster than the interrupt controller, and they can be used by + * secure guests. + */ + + ic_cause_ipi = smp_ops->cause_ipi; + smp_ops->cause_ipi = dbell_or_ic_cause_ipi; } static struct smp_ops_t pseries_smp_ops = { diff --git a/arch/powerpc/platforms/pseries/suspend.c b/arch/powerpc/platforms/pseries/suspend.c index 0a24a5a185f0..81e0ac58d620 100644 --- a/arch/powerpc/platforms/pseries/suspend.c +++ b/arch/powerpc/platforms/pseries/suspend.c @@ -132,15 +132,11 @@ static ssize_t store_hibernate(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - cpumask_var_t offline_mask; int rc; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!alloc_cpumask_var(&offline_mask, GFP_KERNEL)) - return -ENOMEM; - stream_id = simple_strtoul(buf, NULL, 16); do { @@ -149,33 +145,14 @@ static ssize_t store_hibernate(struct device *dev, ssleep(1); } while (rc == -EAGAIN); - if (!rc) { - /* All present CPUs must be online */ - cpumask_andnot(offline_mask, cpu_present_mask, - cpu_online_mask); - rc = rtas_online_cpus_mask(offline_mask); - if (rc) { - pr_err("%s: Could not bring present CPUs online.\n", - __func__); - goto out; - } - - stop_topology_update(); + if (!rc) rc = pm_suspend(PM_SUSPEND_MEM); - start_topology_update(); - - /* Take down CPUs not online prior to suspend */ - if (!rtas_offline_cpus_mask(offline_mask)) - pr_warn("%s: Could not restore CPUs to offline " - "state.\n", __func__); - } stream_id = 0; if (!rc) rc = count; -out: - free_cpumask_var(offline_mask); + return rc; } |