diff options
Diffstat (limited to 'arch/powerpc/platforms/powernv')
| -rw-r--r-- | arch/powerpc/platforms/powernv/Kconfig | 7 | ||||
| -rw-r--r-- | arch/powerpc/platforms/powernv/Makefile | 2 | ||||
| -rw-r--r-- | arch/powerpc/platforms/powernv/eeh-ioda.c | 1149 | ||||
| -rw-r--r-- | arch/powerpc/platforms/powernv/eeh-powernv.c | 1300 | ||||
| -rw-r--r-- | arch/powerpc/platforms/powernv/opal-dump.c | 3 | ||||
| -rw-r--r-- | arch/powerpc/platforms/powernv/opal-elog.c | 3 | ||||
| -rw-r--r-- | arch/powerpc/platforms/powernv/opal-flash.c | 8 | ||||
| -rw-r--r-- | arch/powerpc/platforms/powernv/opal-nvram.c | 10 | ||||
| -rw-r--r-- | arch/powerpc/platforms/powernv/opal-sensor.c | 30 | ||||
| -rw-r--r-- | arch/powerpc/platforms/powernv/opal-wrappers.S | 5 | ||||
| -rw-r--r-- | arch/powerpc/platforms/powernv/opal.c | 92 | ||||
| -rw-r--r-- | arch/powerpc/platforms/powernv/pci-ioda.c | 797 | ||||
| -rw-r--r-- | arch/powerpc/platforms/powernv/pci-p5ioc2.c | 1 | ||||
| -rw-r--r-- | arch/powerpc/platforms/powernv/pci.c | 190 | ||||
| -rw-r--r-- | arch/powerpc/platforms/powernv/pci.h | 38 | ||||
| -rw-r--r-- | arch/powerpc/platforms/powernv/powernv.h | 2 | ||||
| -rw-r--r-- | arch/powerpc/platforms/powernv/setup.c | 54 | ||||
| -rw-r--r-- | arch/powerpc/platforms/powernv/smp.c | 13 |
18 files changed, 2136 insertions, 1568 deletions
diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig index 45a8ed0585cd..4b044d8cb49a 100644 --- a/arch/powerpc/platforms/powernv/Kconfig +++ b/arch/powerpc/platforms/powernv/Kconfig @@ -19,10 +19,3 @@ config PPC_POWERNV select CPU_FREQ_GOV_CONSERVATIVE select PPC_DOORBELL default y - -config PPC_POWERNV_RTAS - depends on PPC_POWERNV - bool "Support for RTAS based PowerNV platforms such as BML" - default y - select PPC_ICS_RTAS - select PPC_RTAS diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile index 6f3c5d33c3af..33e44f37212f 100644 --- a/arch/powerpc/platforms/powernv/Makefile +++ b/arch/powerpc/platforms/powernv/Makefile @@ -5,7 +5,7 @@ obj-y += opal-msglog.o opal-hmi.o opal-power.o obj-$(CONFIG_SMP) += smp.o subcore.o subcore-asm.o obj-$(CONFIG_PCI) += pci.o pci-p5ioc2.o pci-ioda.o -obj-$(CONFIG_EEH) += eeh-ioda.o eeh-powernv.o +obj-$(CONFIG_EEH) += eeh-powernv.o obj-$(CONFIG_PPC_SCOM) += opal-xscom.o obj-$(CONFIG_MEMORY_FAILURE) += opal-memory-errors.o obj-$(CONFIG_TRACEPOINTS) += opal-tracepoints.o diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c deleted file mode 100644 index 2809c9895288..000000000000 --- a/arch/powerpc/platforms/powernv/eeh-ioda.c +++ /dev/null @@ -1,1149 +0,0 @@ -/* - * The file intends to implement the functions needed by EEH, which is - * built on IODA compliant chip. Actually, lots of functions related - * to EEH would be built based on the OPAL APIs. - * - * Copyright Benjamin Herrenschmidt & Gavin Shan, IBM Corporation 2013. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ - -#include <linux/debugfs.h> -#include <linux/delay.h> -#include <linux/io.h> -#include <linux/irq.h> -#include <linux/kernel.h> -#include <linux/msi.h> -#include <linux/notifier.h> -#include <linux/pci.h> -#include <linux/string.h> - -#include <asm/eeh.h> -#include <asm/eeh_event.h> -#include <asm/io.h> -#include <asm/iommu.h> -#include <asm/msi_bitmap.h> -#include <asm/opal.h> -#include <asm/pci-bridge.h> -#include <asm/ppc-pci.h> -#include <asm/tce.h> - -#include "powernv.h" -#include "pci.h" - -static int ioda_eeh_nb_init = 0; - -static int ioda_eeh_event(struct notifier_block *nb, - unsigned long events, void *change) -{ - uint64_t changed_evts = (uint64_t)change; - - /* - * We simply send special EEH event if EEH has - * been enabled, or clear pending events in - * case that we enable EEH soon - */ - if (!(changed_evts & OPAL_EVENT_PCI_ERROR) || - !(events & OPAL_EVENT_PCI_ERROR)) - return 0; - - if (eeh_enabled()) - eeh_send_failure_event(NULL); - else - opal_notifier_update_evt(OPAL_EVENT_PCI_ERROR, 0x0ul); - - return 0; -} - -static struct notifier_block ioda_eeh_nb = { - .notifier_call = ioda_eeh_event, - .next = NULL, - .priority = 0 -}; - -#ifdef CONFIG_DEBUG_FS -static ssize_t ioda_eeh_ei_write(struct file *filp, - const char __user *user_buf, - size_t count, loff_t *ppos) -{ - struct pci_controller *hose = filp->private_data; - struct pnv_phb *phb = hose->private_data; - struct eeh_dev *edev; - struct eeh_pe *pe; - int pe_no, type, func; - unsigned long addr, mask; - char buf[50]; - int ret; - - if (!phb->eeh_ops || !phb->eeh_ops->err_inject) - return -ENXIO; - - ret = simple_write_to_buffer(buf, sizeof(buf), ppos, user_buf, count); - if (!ret) - return -EFAULT; - - /* Retrieve parameters */ - ret = sscanf(buf, "%x:%x:%x:%lx:%lx", - &pe_no, &type, &func, &addr, &mask); - if (ret != 5) - return -EINVAL; - - /* Retrieve PE */ - edev = kzalloc(sizeof(*edev), GFP_KERNEL); - if (!edev) - return -ENOMEM; - edev->phb = hose; - edev->pe_config_addr = pe_no; - pe = eeh_pe_get(edev); - kfree(edev); - if (!pe) - return -ENODEV; - - /* Do error injection */ - ret = phb->eeh_ops->err_inject(pe, type, func, addr, mask); - return ret < 0 ? ret : count; -} - -static const struct file_operations ioda_eeh_ei_fops = { - .open = simple_open, - .llseek = no_llseek, - .write = ioda_eeh_ei_write, -}; - -static int ioda_eeh_dbgfs_set(void *data, int offset, u64 val) -{ - struct pci_controller *hose = data; - struct pnv_phb *phb = hose->private_data; - - out_be64(phb->regs + offset, val); - return 0; -} - -static int ioda_eeh_dbgfs_get(void *data, int offset, u64 *val) -{ - struct pci_controller *hose = data; - struct pnv_phb *phb = hose->private_data; - - *val = in_be64(phb->regs + offset); - return 0; -} - -static int ioda_eeh_outb_dbgfs_set(void *data, u64 val) -{ - return ioda_eeh_dbgfs_set(data, 0xD10, val); -} - -static int ioda_eeh_outb_dbgfs_get(void *data, u64 *val) -{ - return ioda_eeh_dbgfs_get(data, 0xD10, val); -} - -static int ioda_eeh_inbA_dbgfs_set(void *data, u64 val) -{ - return ioda_eeh_dbgfs_set(data, 0xD90, val); -} - -static int ioda_eeh_inbA_dbgfs_get(void *data, u64 *val) -{ - return ioda_eeh_dbgfs_get(data, 0xD90, val); -} - -static int ioda_eeh_inbB_dbgfs_set(void *data, u64 val) -{ - return ioda_eeh_dbgfs_set(data, 0xE10, val); -} - -static int ioda_eeh_inbB_dbgfs_get(void *data, u64 *val) -{ - return ioda_eeh_dbgfs_get(data, 0xE10, val); -} - -DEFINE_SIMPLE_ATTRIBUTE(ioda_eeh_outb_dbgfs_ops, ioda_eeh_outb_dbgfs_get, - ioda_eeh_outb_dbgfs_set, "0x%llx\n"); -DEFINE_SIMPLE_ATTRIBUTE(ioda_eeh_inbA_dbgfs_ops, ioda_eeh_inbA_dbgfs_get, - ioda_eeh_inbA_dbgfs_set, "0x%llx\n"); -DEFINE_SIMPLE_ATTRIBUTE(ioda_eeh_inbB_dbgfs_ops, ioda_eeh_inbB_dbgfs_get, - ioda_eeh_inbB_dbgfs_set, "0x%llx\n"); -#endif /* CONFIG_DEBUG_FS */ - - -/** - * ioda_eeh_post_init - Chip dependent post initialization - * @hose: PCI controller - * - * The function will be called after eeh PEs and devices - * have been built. That means the EEH is ready to supply - * service with I/O cache. - */ -static int ioda_eeh_post_init(struct pci_controller *hose) -{ - struct pnv_phb *phb = hose->private_data; - int ret; - - /* Register OPAL event notifier */ - if (!ioda_eeh_nb_init) { - ret = opal_notifier_register(&ioda_eeh_nb); - if (ret) { - pr_err("%s: Can't register OPAL event notifier (%d)\n", - __func__, ret); - return ret; - } - - ioda_eeh_nb_init = 1; - } - -#ifdef CONFIG_DEBUG_FS - if (!phb->has_dbgfs && phb->dbgfs) { - phb->has_dbgfs = 1; - - debugfs_create_file("err_injct", 0200, - phb->dbgfs, hose, - &ioda_eeh_ei_fops); - - debugfs_create_file("err_injct_outbound", 0600, - phb->dbgfs, hose, - &ioda_eeh_outb_dbgfs_ops); - debugfs_create_file("err_injct_inboundA", 0600, - phb->dbgfs, hose, - &ioda_eeh_inbA_dbgfs_ops); - debugfs_create_file("err_injct_inboundB", 0600, - phb->dbgfs, hose, - &ioda_eeh_inbB_dbgfs_ops); - } -#endif - - /* If EEH is enabled, we're going to rely on that. - * Otherwise, we restore to conventional mechanism - * to clear frozen PE during PCI config access. - */ - if (eeh_enabled()) - phb->flags |= PNV_PHB_FLAG_EEH; - else - phb->flags &= ~PNV_PHB_FLAG_EEH; - - return 0; -} - -/** - * ioda_eeh_set_option - Set EEH operation or I/O setting - * @pe: EEH PE - * @option: options - * - * Enable or disable EEH option for the indicated PE. The - * function also can be used to enable I/O or DMA for the - * PE. - */ -static int ioda_eeh_set_option(struct eeh_pe *pe, int option) -{ - struct pci_controller *hose = pe->phb; - struct pnv_phb *phb = hose->private_data; - bool freeze_pe = false; - int enable, ret = 0; - s64 rc; - - /* Check on PE number */ - if (pe->addr < 0 || pe->addr >= phb->ioda.total_pe) { - pr_err("%s: PE address %x out of range [0, %x] " - "on PHB#%x\n", - __func__, pe->addr, phb->ioda.total_pe, - hose->global_number); - return -EINVAL; - } - - switch (option) { - case EEH_OPT_DISABLE: - return -EPERM; - case EEH_OPT_ENABLE: - return 0; - case EEH_OPT_THAW_MMIO: - enable = OPAL_EEH_ACTION_CLEAR_FREEZE_MMIO; - break; - case EEH_OPT_THAW_DMA: - enable = OPAL_EEH_ACTION_CLEAR_FREEZE_DMA; - break; - case EEH_OPT_FREEZE_PE: - freeze_pe = true; - enable = OPAL_EEH_ACTION_SET_FREEZE_ALL; - break; - default: - pr_warn("%s: Invalid option %d\n", - __func__, option); - return -EINVAL; - } - - /* If PHB supports compound PE, to handle it */ - if (freeze_pe) { - if (phb->freeze_pe) { - phb->freeze_pe(phb, pe->addr); - } else { - rc = opal_pci_eeh_freeze_set(phb->opal_id, - pe->addr, - enable); - if (rc != OPAL_SUCCESS) { - pr_warn("%s: Failure %lld freezing " - "PHB#%x-PE#%x\n", - __func__, rc, - phb->hose->global_number, pe->addr); - ret = -EIO; - } - } - } else { - if (phb->unfreeze_pe) { - ret = phb->unfreeze_pe(phb, pe->addr, enable); - } else { - rc = opal_pci_eeh_freeze_clear(phb->opal_id, - pe->addr, - enable); - if (rc != OPAL_SUCCESS) { - pr_warn("%s: Failure %lld enable %d " - "for PHB#%x-PE#%x\n", - __func__, rc, option, - phb->hose->global_number, pe->addr); - ret = -EIO; - } - } - } - - return ret; -} - -static void ioda_eeh_phb_diag(struct eeh_pe *pe) -{ - struct pnv_phb *phb = pe->phb->private_data; - long rc; - - rc = opal_pci_get_phb_diag_data2(phb->opal_id, pe->data, - PNV_PCI_DIAG_BUF_SIZE); - if (rc != OPAL_SUCCESS) - pr_warn("%s: Failed to get diag-data for PHB#%x (%ld)\n", - __func__, pe->phb->global_number, rc); -} - -static int ioda_eeh_get_phb_state(struct eeh_pe *pe) -{ - struct pnv_phb *phb = pe->phb->private_data; - u8 fstate; - __be16 pcierr; - s64 rc; - int result = 0; - - rc = opal_pci_eeh_freeze_status(phb->opal_id, - pe->addr, - &fstate, - &pcierr, - NULL); - if (rc != OPAL_SUCCESS) { - pr_warn("%s: Failure %lld getting PHB#%x state\n", - __func__, rc, phb->hose->global_number); - return EEH_STATE_NOT_SUPPORT; - } - - /* - * Check PHB state. If the PHB is frozen for the - * first time, to dump the PHB diag-data. - */ - if (be16_to_cpu(pcierr) != OPAL_EEH_PHB_ERROR) { - result = (EEH_STATE_MMIO_ACTIVE | - EEH_STATE_DMA_ACTIVE | - EEH_STATE_MMIO_ENABLED | - EEH_STATE_DMA_ENABLED); - } else if (!(pe->state & EEH_PE_ISOLATED)) { - eeh_pe_state_mark(pe, EEH_PE_ISOLATED); - ioda_eeh_phb_diag(pe); - - if (eeh_has_flag(EEH_EARLY_DUMP_LOG)) - pnv_pci_dump_phb_diag_data(pe->phb, pe->data); - } - - return result; -} - -static int ioda_eeh_get_pe_state(struct eeh_pe *pe) -{ - struct pnv_phb *phb = pe->phb->private_data; - u8 fstate; - __be16 pcierr; - s64 rc; - int result; - - /* - * We don't clobber hardware frozen state until PE - * reset is completed. In order to keep EEH core - * moving forward, we have to return operational - * state during PE reset. - */ - if (pe->state & EEH_PE_RESET) { - result = (EEH_STATE_MMIO_ACTIVE | - EEH_STATE_DMA_ACTIVE | - EEH_STATE_MMIO_ENABLED | - EEH_STATE_DMA_ENABLED); - return result; - } - - /* - * Fetch PE state from hardware. If the PHB - * supports compound PE, let it handle that. - */ - if (phb->get_pe_state) { - fstate = phb->get_pe_state(phb, pe->addr); - } else { - rc = opal_pci_eeh_freeze_status(phb->opal_id, - pe->addr, - &fstate, - &pcierr, - NULL); - if (rc != OPAL_SUCCESS) { - pr_warn("%s: Failure %lld getting PHB#%x-PE%x state\n", - __func__, rc, phb->hose->global_number, pe->addr); - return EEH_STATE_NOT_SUPPORT; - } - } - - /* Figure out state */ - switch (fstate) { - case OPAL_EEH_STOPPED_NOT_FROZEN: - result = (EEH_STATE_MMIO_ACTIVE | - EEH_STATE_DMA_ACTIVE | - EEH_STATE_MMIO_ENABLED | - EEH_STATE_DMA_ENABLED); - break; - case OPAL_EEH_STOPPED_MMIO_FREEZE: - result = (EEH_STATE_DMA_ACTIVE | - EEH_STATE_DMA_ENABLED); - break; - case OPAL_EEH_STOPPED_DMA_FREEZE: - result = (EEH_STATE_MMIO_ACTIVE | - EEH_STATE_MMIO_ENABLED); - break; - case OPAL_EEH_STOPPED_MMIO_DMA_FREEZE: - result = 0; - break; - case OPAL_EEH_STOPPED_RESET: - result = EEH_STATE_RESET_ACTIVE; - break; - case OPAL_EEH_STOPPED_TEMP_UNAVAIL: - result = EEH_STATE_UNAVAILABLE; - break; - case OPAL_EEH_STOPPED_PERM_UNAVAIL: - result = EEH_STATE_NOT_SUPPORT; - break; - default: - result = EEH_STATE_NOT_SUPPORT; - pr_warn("%s: Invalid PHB#%x-PE#%x state %x\n", - __func__, phb->hose->global_number, - pe->addr, fstate); - } - - /* - * If PHB supports compound PE, to freeze all - * slave PEs for consistency. - * - * If the PE is switching to frozen state for the - * first time, to dump the PHB diag-data. - */ - if (!(result & EEH_STATE_NOT_SUPPORT) && - !(result & EEH_STATE_UNAVAILABLE) && - !(result & EEH_STATE_MMIO_ACTIVE) && - !(result & EEH_STATE_DMA_ACTIVE) && - !(pe->state & EEH_PE_ISOLATED)) { - if (phb->freeze_pe) - phb->freeze_pe(phb, pe->addr); - - eeh_pe_state_mark(pe, EEH_PE_ISOLATED); - ioda_eeh_phb_diag(pe); - - if (eeh_has_flag(EEH_EARLY_DUMP_LOG)) - pnv_pci_dump_phb_diag_data(pe->phb, pe->data); - } - - return result; -} - -/** - * ioda_eeh_get_state - Retrieve the state of PE - * @pe: EEH PE - * - * The PE's state should be retrieved from the PEEV, PEST - * IODA tables. Since the OPAL has exported the function - * to do it, it'd better to use that. - */ -static int ioda_eeh_get_state(struct eeh_pe *pe) -{ - struct pnv_phb *phb = pe->phb->private_data; - - /* Sanity check on PE number. PHB PE should have 0 */ - if (pe->addr < 0 || - pe->addr >= phb->ioda.total_pe) { - pr_warn("%s: PHB#%x-PE#%x out of range [0, %x]\n", - __func__, phb->hose->global_number, - pe->addr, phb->ioda.total_pe); - return EEH_STATE_NOT_SUPPORT; - } - - if (pe->type & EEH_PE_PHB) - return ioda_eeh_get_phb_state(pe); - - return ioda_eeh_get_pe_state(pe); -} - -static s64 ioda_eeh_phb_poll(struct pnv_phb *phb) -{ - s64 rc = OPAL_HARDWARE; - - while (1) { - rc = opal_pci_poll(phb->opal_id); - if (rc <= 0) - break; - - if (system_state < SYSTEM_RUNNING) - udelay(1000 * rc); - else - msleep(rc); - } - - return rc; -} - -int ioda_eeh_phb_reset(struct pci_controller *hose, int option) -{ - struct pnv_phb *phb = hose->private_data; - s64 rc = OPAL_HARDWARE; - - pr_debug("%s: Reset PHB#%x, option=%d\n", - __func__, hose->global_number, option); - - /* Issue PHB complete reset request */ - if (option == EEH_RESET_FUNDAMENTAL || - option == EEH_RESET_HOT) - rc = opal_pci_reset(phb->opal_id, - OPAL_RESET_PHB_COMPLETE, - OPAL_ASSERT_RESET); - else if (option == EEH_RESET_DEACTIVATE) - rc = opal_pci_reset(phb->opal_id, - OPAL_RESET_PHB_COMPLETE, - OPAL_DEASSERT_RESET); - if (rc < 0) - goto out; - - /* - * Poll state of the PHB until the request is done - * successfully. The PHB reset is usually PHB complete - * reset followed by hot reset on root bus. So we also - * need the PCI bus settlement delay. - */ - rc = ioda_eeh_phb_poll(phb); - if (option == EEH_RESET_DEACTIVATE) { - if (system_state < SYSTEM_RUNNING) - udelay(1000 * EEH_PE_RST_SETTLE_TIME); - else - msleep(EEH_PE_RST_SETTLE_TIME); - } -out: - if (rc != OPAL_SUCCESS) - return -EIO; - - return 0; -} - -static int ioda_eeh_root_reset(struct pci_controller *hose, int option) -{ - struct pnv_phb *phb = hose->private_data; - s64 rc = OPAL_SUCCESS; - - pr_debug("%s: Reset PHB#%x, option=%d\n", - __func__, hose->global_number, option); - - /* - * During the reset deassert time, we needn't care - * the reset scope because the firmware does nothing - * for fundamental or hot reset during deassert phase. - */ - if (option == EEH_RESET_FUNDAMENTAL) - rc = opal_pci_reset(phb->opal_id, - OPAL_RESET_PCI_FUNDAMENTAL, - OPAL_ASSERT_RESET); - else if (option == EEH_RESET_HOT) - rc = opal_pci_reset(phb->opal_id, - OPAL_RESET_PCI_HOT, - OPAL_ASSERT_RESET); - else if (option == EEH_RESET_DEACTIVATE) - rc = opal_pci_reset(phb->opal_id, - OPAL_RESET_PCI_HOT, - OPAL_DEASSERT_RESET); - if (rc < 0) - goto out; - - /* Poll state of the PHB until the request is done */ - rc = ioda_eeh_phb_poll(phb); - if (option == EEH_RESET_DEACTIVATE) - msleep(EEH_PE_RST_SETTLE_TIME); -out: - if (rc != OPAL_SUCCESS) - return -EIO; - - return 0; -} - -static int ioda_eeh_bridge_reset(struct pci_dev *dev, int option) - -{ - struct device_node *dn = pci_device_to_OF_node(dev); - struct eeh_dev *edev = of_node_to_eeh_dev(dn); - int aer = edev ? edev->aer_cap : 0; - u32 ctrl; - - pr_debug("%s: Reset PCI bus %04x:%02x with option %d\n", - __func__, pci_domain_nr(dev->bus), - dev->bus->number, option); - - switch (option) { - case EEH_RESET_FUNDAMENTAL: - case EEH_RESET_HOT: - /* Don't report linkDown event */ - if (aer) { - eeh_ops->read_config(dn, aer + PCI_ERR_UNCOR_MASK, - 4, &ctrl); - ctrl |= PCI_ERR_UNC_SURPDN; - eeh_ops->write_config(dn, aer + PCI_ERR_UNCOR_MASK, - 4, ctrl); - } - - eeh_ops->read_config(dn, PCI_BRIDGE_CONTROL, 2, &ctrl); - ctrl |= PCI_BRIDGE_CTL_BUS_RESET; - eeh_ops->write_config(dn, PCI_BRIDGE_CONTROL, 2, ctrl); - msleep(EEH_PE_RST_HOLD_TIME); - - break; - case EEH_RESET_DEACTIVATE: - eeh_ops->read_config(dn, PCI_BRIDGE_CONTROL, 2, &ctrl); - ctrl &= ~PCI_BRIDGE_CTL_BUS_RESET; - eeh_ops->write_config(dn, PCI_BRIDGE_CONTROL, 2, ctrl); - msleep(EEH_PE_RST_SETTLE_TIME); - - /* Continue reporting linkDown event */ - if (aer) { - eeh_ops->read_config(dn, aer + PCI_ERR_UNCOR_MASK, - 4, &ctrl); - ctrl &= ~PCI_ERR_UNC_SURPDN; - eeh_ops->write_config(dn, aer + PCI_ERR_UNCOR_MASK, - 4, ctrl); - } - - break; - } - - return 0; -} - -void pnv_pci_reset_secondary_bus(struct pci_dev *dev) -{ - struct pci_controller *hose; - - if (pci_is_root_bus(dev->bus)) { - hose = pci_bus_to_host(dev->bus); - ioda_eeh_root_reset(hose, EEH_RESET_HOT); - ioda_eeh_root_reset(hose, EEH_RESET_DEACTIVATE); - } else { - ioda_eeh_bridge_reset(dev, EEH_RESET_HOT); - ioda_eeh_bridge_reset(dev, EEH_RESET_DEACTIVATE); - } -} - -/** - * ioda_eeh_reset - Reset the indicated PE - * @pe: EEH PE - * @option: reset option - * - * Do reset on the indicated PE. For PCI bus sensitive PE, - * we need to reset the parent p2p bridge. The PHB has to - * be reinitialized if the p2p bridge is root bridge. For - * PCI device sensitive PE, we will try to reset the device - * through FLR. For now, we don't have OPAL APIs to do HARD - * reset yet, so all reset would be SOFT (HOT) reset. - */ -static int ioda_eeh_reset(struct eeh_pe *pe, int option) -{ - struct pci_controller *hose = pe->phb; - struct pci_bus *bus; - int ret; - - /* - * For PHB reset, we always have complete reset. For those PEs whose - * primary bus derived from root complex (root bus) or root port - * (usually bus#1), we apply hot or fundamental reset on the root port. - * For other PEs, we always have hot reset on the PE primary bus. - * - * Here, we have different design to pHyp, which always clear the - * frozen state during PE reset. However, the good idea here from - * benh is to keep frozen state before we get PE reset done completely - * (until BAR restore). With the frozen state, HW drops illegal IO - * or MMIO access, which can incur recrusive frozen PE during PE - * reset. The side effect is that EEH core has to clear the frozen - * state explicitly after BAR restore. - */ - if (pe->type & EEH_PE_PHB) { - ret = ioda_eeh_phb_reset(hose, option); - } else { - struct pnv_phb *phb; - s64 rc; - - /* - * The frozen PE might be caused by PAPR error injection - * registers, which are expected to be cleared after hitting - * frozen PE as stated in the hardware spec. Unfortunately, - * that's not true on P7IOC. So we have to clear it manually - * to avoid recursive EEH errors during recovery. - */ - phb = hose->private_data; - if (phb->model == PNV_PHB_MODEL_P7IOC && - (option == EEH_RESET_HOT || - option == EEH_RESET_FUNDAMENTAL)) { - rc = opal_pci_reset(phb->opal_id, - OPAL_RESET_PHB_ERROR, - OPAL_ASSERT_RESET); - if (rc != OPAL_SUCCESS) { - pr_warn("%s: Failure %lld clearing " - "error injection registers\n", - __func__, rc); - return -EIO; - } - } - - bus = eeh_pe_bus_get(pe); - if (pci_is_root_bus(bus) || - pci_is_root_bus(bus->parent)) - ret = ioda_eeh_root_reset(hose, option); - else - ret = ioda_eeh_bridge_reset(bus->self, option); - } - - return ret; -} - -/** - * ioda_eeh_get_log - Retrieve error log - * @pe: frozen PE - * @severity: permanent or temporary error - * @drv_log: device driver log - * @len: length of device driver log - * - * Retrieve error log, which contains log from device driver - * and firmware. - */ -static int ioda_eeh_get_log(struct eeh_pe *pe, int severity, - char *drv_log, unsigned long len) -{ - if (!eeh_has_flag(EEH_EARLY_DUMP_LOG)) - pnv_pci_dump_phb_diag_data(pe->phb, pe->data); - - return 0; -} - -/** - * ioda_eeh_configure_bridge - Configure the PCI bridges for the indicated PE - * @pe: EEH PE - * - * For particular PE, it might have included PCI bridges. In order - * to make the PE work properly, those PCI bridges should be configured - * correctly. However, we need do nothing on P7IOC since the reset - * function will do everything that should be covered by the function. - */ -static int ioda_eeh_configure_bridge(struct eeh_pe *pe) -{ - return 0; -} - -static int ioda_eeh_err_inject(struct eeh_pe *pe, int type, int func, - unsigned long addr, unsigned long mask) -{ - struct pci_controller *hose = pe->phb; - struct pnv_phb *phb = hose->private_data; - s64 ret; - - /* Sanity check on error type */ - if (type != OPAL_ERR_INJECT_TYPE_IOA_BUS_ERR && - type != OPAL_ERR_INJECT_TYPE_IOA_BUS_ERR64) { - pr_warn("%s: Invalid error type %d\n", - __func__, type); - return -ERANGE; - } - - if (func < OPAL_ERR_INJECT_FUNC_IOA_LD_MEM_ADDR || - func > OPAL_ERR_INJECT_FUNC_IOA_DMA_WR_TARGET) { - pr_warn("%s: Invalid error function %d\n", - __func__, func); - return -ERANGE; - } - - /* Firmware supports error injection ? */ - if (!opal_check_token(OPAL_PCI_ERR_INJECT)) { - pr_warn("%s: Firmware doesn't support error injection\n", - __func__); - return -ENXIO; - } - - /* Do error injection */ - ret = opal_pci_err_inject(phb->opal_id, pe->addr, - type, func, addr, mask); - if (ret != OPAL_SUCCESS) { - pr_warn("%s: Failure %lld injecting error " - "%d-%d to PHB#%x-PE#%x\n", - __func__, ret, type, func, - hose->global_number, pe->addr); - return -EIO; - } - - return 0; -} - -static void ioda_eeh_hub_diag_common(struct OpalIoP7IOCErrorData *data) -{ - /* GEM */ - if (data->gemXfir || data->gemRfir || - data->gemRirqfir || data->gemMask || data->gemRwof) - pr_info(" GEM: %016llx %016llx %016llx %016llx %016llx\n", - be64_to_cpu(data->gemXfir), - be64_to_cpu(data->gemRfir), - be64_to_cpu(data->gemRirqfir), - be64_to_cpu(data->gemMask), - be64_to_cpu(data->gemRwof)); - - /* LEM */ - if (data->lemFir || data->lemErrMask || - data->lemAction0 || data->lemAction1 || data->lemWof) - pr_info(" LEM: %016llx %016llx %016llx %016llx %016llx\n", - be64_to_cpu(data->lemFir), - be64_to_cpu(data->lemErrMask), - be64_to_cpu(data->lemAction0), - be64_to_cpu(data->lemAction1), - be64_to_cpu(data->lemWof)); -} - -static void ioda_eeh_hub_diag(struct pci_controller *hose) -{ - struct pnv_phb *phb = hose->private_data; - struct OpalIoP7IOCErrorData *data = &phb->diag.hub_diag; - long rc; - - rc = opal_pci_get_hub_diag_data(phb->hub_id, data, sizeof(*data)); - if (rc != OPAL_SUCCESS) { - pr_warn("%s: Failed to get HUB#%llx diag-data (%ld)\n", - __func__, phb->hub_id, rc); - return; - } - - switch (data->type) { - case OPAL_P7IOC_DIAG_TYPE_RGC: - pr_info("P7IOC diag-data for RGC\n\n"); - ioda_eeh_hub_diag_common(data); - if (data->rgc.rgcStatus || data->rgc.rgcLdcp) - pr_info(" RGC: %016llx %016llx\n", - be64_to_cpu(data->rgc.rgcStatus), - be64_to_cpu(data->rgc.rgcLdcp)); - break; - case OPAL_P7IOC_DIAG_TYPE_BI: - pr_info("P7IOC diag-data for BI %s\n\n", - data->bi.biDownbound ? "Downbound" : "Upbound"); - ioda_eeh_hub_diag_common(data); - if (data->bi.biLdcp0 || data->bi.biLdcp1 || - data->bi.biLdcp2 || data->bi.biFenceStatus) - pr_info(" BI: %016llx %016llx %016llx %016llx\n", - be64_to_cpu(data->bi.biLdcp0), - be64_to_cpu(data->bi.biLdcp1), - be64_to_cpu(data->bi.biLdcp2), - be64_to_cpu(data->bi.biFenceStatus)); - break; - case OPAL_P7IOC_DIAG_TYPE_CI: - pr_info("P7IOC diag-data for CI Port %d\n\n", - data->ci.ciPort); - ioda_eeh_hub_diag_common(data); - if (data->ci.ciPortStatus || data->ci.ciPortLdcp) - pr_info(" CI: %016llx %016llx\n", - be64_to_cpu(data->ci.ciPortStatus), - be64_to_cpu(data->ci.ciPortLdcp)); - break; - case OPAL_P7IOC_DIAG_TYPE_MISC: - pr_info("P7IOC diag-data for MISC\n\n"); - ioda_eeh_hub_diag_common(data); - break; - case OPAL_P7IOC_DIAG_TYPE_I2C: - pr_info("P7IOC diag-data for I2C\n\n"); - ioda_eeh_hub_diag_common(data); - break; - default: - pr_warn("%s: Invalid type of HUB#%llx diag-data (%d)\n", - __func__, phb->hub_id, data->type); - } -} - -static int ioda_eeh_get_pe(struct pci_controller *hose, - u16 pe_no, struct eeh_pe **pe) -{ - struct pnv_phb *phb = hose->private_data; - struct pnv_ioda_pe *pnv_pe; - struct eeh_pe *dev_pe; - struct eeh_dev edev; - - /* - * If PHB supports compound PE, to fetch - * the master PE because slave PE is invisible - * to EEH core. - */ - pnv_pe = &phb->ioda.pe_array[pe_no]; - if (pnv_pe->flags & PNV_IODA_PE_SLAVE) { - pnv_pe = pnv_pe->master; - WARN_ON(!pnv_pe || - !(pnv_pe->flags & PNV_IODA_PE_MASTER)); - pe_no = pnv_pe->pe_number; - } - - /* Find the PE according to PE# */ - memset(&edev, 0, sizeof(struct eeh_dev)); - edev.phb = hose; - edev.pe_config_addr = pe_no; - dev_pe = eeh_pe_get(&edev); - if (!dev_pe) - return -EEXIST; - - /* Freeze the (compound) PE */ - *pe = dev_pe; - if (!(dev_pe->state & EEH_PE_ISOLATED)) - phb->freeze_pe(phb, pe_no); - - /* - * At this point, we're sure the (compound) PE should - * have been frozen. However, we still need poke until - * hitting the frozen PE on top level. - */ - dev_pe = dev_pe->parent; - while (dev_pe && !(dev_pe->type & EEH_PE_PHB)) { - int ret; - int active_flags = (EEH_STATE_MMIO_ACTIVE | - EEH_STATE_DMA_ACTIVE); - - ret = eeh_ops->get_state(dev_pe, NULL); - if (ret <= 0 || (ret & active_flags) == active_flags) { - dev_pe = dev_pe->parent; - continue; - } - - /* Frozen parent PE */ - *pe = dev_pe; - if (!(dev_pe->state & EEH_PE_ISOLATED)) - phb->freeze_pe(phb, dev_pe->addr); - - /* Next one */ - dev_pe = dev_pe->parent; - } - - return 0; -} - -/** - * ioda_eeh_next_error - Retrieve next error for EEH core to handle - * @pe: The affected PE - * - * The function is expected to be called by EEH core while it gets - * special EEH event (without binding PE). The function calls to - * OPAL APIs for next error to handle. The informational error is - * handled internally by platform. However, the dead IOC, dead PHB, - * fenced PHB and frozen PE should be handled by EEH core eventually. - */ -static int ioda_eeh_next_error(struct eeh_pe **pe) -{ - struct pci_controller *hose; - struct pnv_phb *phb; - struct eeh_pe *phb_pe, *parent_pe; - __be64 frozen_pe_no; - __be16 err_type, severity; - int active_flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE); - long rc; - int state, ret = EEH_NEXT_ERR_NONE; - - /* - * While running here, it's safe to purge the event queue. - * And we should keep the cached OPAL notifier event sychronized - * between the kernel and firmware. - */ - eeh_remove_event(NULL, false); - opal_notifier_update_evt(OPAL_EVENT_PCI_ERROR, 0x0ul); - - list_for_each_entry(hose, &hose_list, list_node) { - /* - * If the subordinate PCI buses of the PHB has been - * removed or is exactly under error recovery, we - * needn't take care of it any more. - */ - phb = hose->private_data; - phb_pe = eeh_phb_pe_get(hose); - if (!phb_pe || (phb_pe->state & EEH_PE_ISOLATED)) - continue; - - rc = opal_pci_next_error(phb->opal_id, - &frozen_pe_no, &err_type, &severity); - - /* If OPAL API returns error, we needn't proceed */ - if (rc != OPAL_SUCCESS) { - pr_devel("%s: Invalid return value on " - "PHB#%x (0x%lx) from opal_pci_next_error", - __func__, hose->global_number, rc); - continue; - } - - /* If the PHB doesn't have error, stop processing */ - if (be16_to_cpu(err_type) == OPAL_EEH_NO_ERROR || - be16_to_cpu(severity) == OPAL_EEH_SEV_NO_ERROR) { - pr_devel("%s: No error found on PHB#%x\n", - __func__, hose->global_number); - continue; - } - - /* - * Processing the error. We're expecting the error with - * highest priority reported upon multiple errors on the - * specific PHB. - */ - pr_devel("%s: Error (%d, %d, %llu) on PHB#%x\n", - __func__, be16_to_cpu(err_type), be16_to_cpu(severity), - be64_to_cpu(frozen_pe_no), hose->global_number); - switch (be16_to_cpu(err_type)) { - case OPAL_EEH_IOC_ERROR: - if (be16_to_cpu(severity) == OPAL_EEH_SEV_IOC_DEAD) { - pr_err("EEH: dead IOC detected\n"); - ret = EEH_NEXT_ERR_DEAD_IOC; - } else if (be16_to_cpu(severity) == OPAL_EEH_SEV_INF) { - pr_info("EEH: IOC informative error " - "detected\n"); - ioda_eeh_hub_diag(hose); - ret = EEH_NEXT_ERR_NONE; - } - - break; - case OPAL_EEH_PHB_ERROR: - if (be16_to_cpu(severity) == OPAL_EEH_SEV_PHB_DEAD) { - *pe = phb_pe; - pr_err("EEH: dead PHB#%x detected, " - "location: %s\n", - hose->global_number, - eeh_pe_loc_get(phb_pe)); - ret = EEH_NEXT_ERR_DEAD_PHB; - } else if (be16_to_cpu(severity) == - OPAL_EEH_SEV_PHB_FENCED) { - *pe = phb_pe; - pr_err("EEH: Fenced PHB#%x detected, " - "location: %s\n", - hose->global_number, - eeh_pe_loc_get(phb_pe)); - ret = EEH_NEXT_ERR_FENCED_PHB; - } else if (be16_to_cpu(severity) == OPAL_EEH_SEV_INF) { - pr_info("EEH: PHB#%x informative error " - "detected, location: %s\n", - hose->global_number, - eeh_pe_loc_get(phb_pe)); - ioda_eeh_phb_diag(phb_pe); - pnv_pci_dump_phb_diag_data(hose, phb_pe->data); - ret = EEH_NEXT_ERR_NONE; - } - - break; - case OPAL_EEH_PE_ERROR: - /* - * If we can't find the corresponding PE, we - * just try to unfreeze. - */ - if (ioda_eeh_get_pe(hose, - be64_to_cpu(frozen_pe_no), pe)) { - /* Try best to clear it */ - pr_info("EEH: Clear non-existing PHB#%x-PE#%llx\n", - hose->global_number, frozen_pe_no); - pr_info("EEH: PHB location: %s\n", - eeh_pe_loc_get(phb_pe)); - opal_pci_eeh_freeze_clear(phb->opal_id, frozen_pe_no, - OPAL_EEH_ACTION_CLEAR_FREEZE_ALL); - ret = EEH_NEXT_ERR_NONE; - } else if ((*pe)->state & EEH_PE_ISOLATED || - eeh_pe_passed(*pe)) { - ret = EEH_NEXT_ERR_NONE; - } else { - pr_err("EEH: Frozen PE#%x on PHB#%x detected\n", - (*pe)->addr, (*pe)->phb->global_number); - pr_err("EEH: PE location: %s, PHB location: %s\n", - eeh_pe_loc_get(*pe), eeh_pe_loc_get(phb_pe)); - ret = EEH_NEXT_ERR_FROZEN_PE; - } - - break; - default: - pr_warn("%s: Unexpected error type %d\n", - __func__, be16_to_cpu(err_type)); - } - - /* - * EEH core will try recover from fenced PHB or - * frozen PE. In the time for frozen PE, EEH core - * enable IO path for that before collecting logs, - * but it ruins the site. So we have to dump the - * log in advance here. - */ - if ((ret == EEH_NEXT_ERR_FROZEN_PE || - ret == EEH_NEXT_ERR_FENCED_PHB) && - !((*pe)->state & EEH_PE_ISOLATED)) { - eeh_pe_state_mark(*pe, EEH_PE_ISOLATED); - ioda_eeh_phb_diag(*pe); - - if (eeh_has_flag(EEH_EARLY_DUMP_LOG)) - pnv_pci_dump_phb_diag_data((*pe)->phb, - (*pe)->data); - } - - /* - * We probably have the frozen parent PE out there and - * we need have to handle frozen parent PE firstly. - */ - if (ret == EEH_NEXT_ERR_FROZEN_PE) { - parent_pe = (*pe)->parent; - while (parent_pe) { - /* Hit the ceiling ? */ - if (parent_pe->type & EEH_PE_PHB) - break; - - /* Frozen parent PE ? */ - state = ioda_eeh_get_state(parent_pe); - if (state > 0 && - (state & active_flags) != active_flags) - *pe = parent_pe; - - /* Next parent level */ - parent_pe = parent_pe->parent; - } - - /* We possibly migrate to another PE */ - eeh_pe_state_mark(*pe, EEH_PE_ISOLATED); - } - - /* - * If we have no errors on the specific PHB or only - * informative error there, we continue poking it. - * Otherwise, we need actions to be taken by upper - * layer. - */ - if (ret > EEH_NEXT_ERR_INF) - break; - } - - return ret; -} - -struct pnv_eeh_ops ioda_eeh_ops = { - .post_init = ioda_eeh_post_init, - .set_option = ioda_eeh_set_option, - .get_state = ioda_eeh_get_state, - .reset = ioda_eeh_reset, - .get_log = ioda_eeh_get_log, - .configure_bridge = ioda_eeh_configure_bridge, - .err_inject = ioda_eeh_err_inject, - .next_error = ioda_eeh_next_error -}; diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index e261869adc86..ce738ab3d5a9 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -12,6 +12,7 @@ */ #include <linux/atomic.h> +#include <linux/debugfs.h> #include <linux/delay.h> #include <linux/export.h> #include <linux/init.h> @@ -38,12 +39,14 @@ #include "powernv.h" #include "pci.h" +static bool pnv_eeh_nb_init = false; + /** - * powernv_eeh_init - EEH platform dependent initialization + * pnv_eeh_init - EEH platform dependent initialization * * EEH platform dependent initialization on powernv */ -static int powernv_eeh_init(void) +static int pnv_eeh_init(void) { struct pci_controller *hose; struct pnv_phb *phb; @@ -85,37 +88,280 @@ static int powernv_eeh_init(void) return 0; } +static int pnv_eeh_event(struct notifier_block *nb, + unsigned long events, void *change) +{ + uint64_t changed_evts = (uint64_t)change; + + /* + * We simply send special EEH event if EEH has + * been enabled, or clear pending events in + * case that we enable EEH soon + */ + if (!(changed_evts & OPAL_EVENT_PCI_ERROR) || + !(events & OPAL_EVENT_PCI_ERROR)) + return 0; + + if (eeh_enabled()) + eeh_send_failure_event(NULL); + else + opal_notifier_update_evt(OPAL_EVENT_PCI_ERROR, 0x0ul); + + return 0; +} + +static struct notifier_block pnv_eeh_nb = { + .notifier_call = pnv_eeh_event, + .next = NULL, + .priority = 0 +}; + +#ifdef CONFIG_DEBUG_FS +static ssize_t pnv_eeh_ei_write(struct file *filp, + const char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct pci_controller *hose = filp->private_data; + struct eeh_dev *edev; + struct eeh_pe *pe; + int pe_no, type, func; + unsigned long addr, mask; + char buf[50]; + int ret; + + if (!eeh_ops || !eeh_ops->err_inject) + return -ENXIO; + + /* Copy over argument buffer */ + ret = simple_write_to_buffer(buf, sizeof(buf), ppos, user_buf, count); + if (!ret) + return -EFAULT; + + /* Retrieve parameters */ + ret = sscanf(buf, "%x:%x:%x:%lx:%lx", + &pe_no, &type, &func, &addr, &mask); + if (ret != 5) + return -EINVAL; + + /* Retrieve PE */ + edev = kzalloc(sizeof(*edev), GFP_KERNEL); + if (!edev) + return -ENOMEM; + edev->phb = hose; + edev->pe_config_addr = pe_no; + pe = eeh_pe_get(edev); + kfree(edev); + if (!pe) + return -ENODEV; + + /* Do error injection */ + ret = eeh_ops->err_inject(pe, type, func, addr, mask); + return ret < 0 ? ret : count; +} + +static const struct file_operations pnv_eeh_ei_fops = { + .open = simple_open, + .llseek = no_llseek, + .write = pnv_eeh_ei_write, +}; + +static int pnv_eeh_dbgfs_set(void *data, int offset, u64 val) +{ + struct pci_controller *hose = data; + struct pnv_phb *phb = hose->private_data; + + out_be64(phb->regs + offset, val); + return 0; +} + +static int pnv_eeh_dbgfs_get(void *data, int offset, u64 *val) +{ + struct pci_controller *hose = data; + struct pnv_phb *phb = hose->private_data; + + *val = in_be64(phb->regs + offset); + return 0; +} + +static int pnv_eeh_outb_dbgfs_set(void *data, u64 val) +{ + return pnv_eeh_dbgfs_set(data, 0xD10, val); +} + +static int pnv_eeh_outb_dbgfs_get(void *data, u64 *val) +{ + return pnv_eeh_dbgfs_get(data, 0xD10, val); +} + +static int pnv_eeh_inbA_dbgfs_set(void *data, u64 val) +{ + return pnv_eeh_dbgfs_set(data, 0xD90, val); +} + +static int pnv_eeh_inbA_dbgfs_get(void *data, u64 *val) +{ + return pnv_eeh_dbgfs_get(data, 0xD90, val); +} + +static int pnv_eeh_inbB_dbgfs_set(void *data, u64 val) +{ + return pnv_eeh_dbgfs_set(data, 0xE10, val); +} + +static int pnv_eeh_inbB_dbgfs_get(void *data, u64 *val) +{ + return pnv_eeh_dbgfs_get(data, 0xE10, val); +} + +DEFINE_SIMPLE_ATTRIBUTE(pnv_eeh_outb_dbgfs_ops, pnv_eeh_outb_dbgfs_get, + pnv_eeh_outb_dbgfs_set, "0x%llx\n"); +DEFINE_SIMPLE_ATTRIBUTE(pnv_eeh_inbA_dbgfs_ops, pnv_eeh_inbA_dbgfs_get, + pnv_eeh_inbA_dbgfs_set, "0x%llx\n"); +DEFINE_SIMPLE_ATTRIBUTE(pnv_eeh_inbB_dbgfs_ops, pnv_eeh_inbB_dbgfs_get, + pnv_eeh_inbB_dbgfs_set, "0x%llx\n"); +#endif /* CONFIG_DEBUG_FS */ + /** - * powernv_eeh_post_init - EEH platform dependent post initialization + * pnv_eeh_post_init - EEH platform dependent post initialization * * EEH platform dependent post initialization on powernv. When * the function is called, the EEH PEs and devices should have * been built. If the I/O cache staff has been built, EEH is * ready to supply service. */ -static int powernv_eeh_post_init(void) +static int pnv_eeh_post_init(void) { struct pci_controller *hose; struct pnv_phb *phb; int ret = 0; + /* Register OPAL event notifier */ + if (!pnv_eeh_nb_init) { + ret = opal_notifier_register(&pnv_eeh_nb); + if (ret) { + pr_warn("%s: Can't register OPAL event notifier (%d)\n", + __func__, ret); + return ret; + } + + pnv_eeh_nb_init = true; + } + list_for_each_entry(hose, &hose_list, list_node) { phb = hose->private_data; - if (phb->eeh_ops && phb->eeh_ops->post_init) { - ret = phb->eeh_ops->post_init(hose); - if (ret) - break; - } + /* + * If EEH is enabled, we're going to rely on that. + * Otherwise, we restore to conventional mechanism + * to clear frozen PE during PCI config access. + */ + if (eeh_enabled()) + phb->flags |= PNV_PHB_FLAG_EEH; + else + phb->flags &= ~PNV_PHB_FLAG_EEH; + + /* Create debugfs entries */ +#ifdef CONFIG_DEBUG_FS + if (phb->has_dbgfs || !phb->dbgfs) + continue; + + phb->has_dbgfs = 1; + debugfs_create_file("err_injct", 0200, + phb->dbgfs, hose, + &pnv_eeh_ei_fops); + + debugfs_create_file("err_injct_outbound", 0600, + phb->dbgfs, hose, + &pnv_eeh_outb_dbgfs_ops); + debugfs_create_file("err_injct_inboundA", 0600, + phb->dbgfs, hose, + &pnv_eeh_inbA_dbgfs_ops); + debugfs_create_file("err_injct_inboundB", 0600, + phb->dbgfs, hose, + &pnv_eeh_inbB_dbgfs_ops); +#endif /* CONFIG_DEBUG_FS */ } + return ret; } +static int pnv_eeh_cap_start(struct pci_dn *pdn) +{ + u32 status; + + if (!pdn) + return 0; + + pnv_pci_cfg_read(pdn, PCI_STATUS, 2, &status); + if (!(status & PCI_STATUS_CAP_LIST)) + return 0; + + return PCI_CAPABILITY_LIST; +} + +static int pnv_eeh_find_cap(struct pci_dn *pdn, int cap) +{ + int pos = pnv_eeh_cap_start(pdn); + int cnt = 48; /* Maximal number of capabilities */ + u32 id; + + if (!pos) + return 0; + + while (cnt--) { + pnv_pci_cfg_read(pdn, pos, 1, &pos); + if (pos < 0x40) + break; + + pos &= ~3; + pnv_pci_cfg_read(pdn, pos + PCI_CAP_LIST_ID, 1, &id); + if (id == 0xff) + break; + + /* Found */ + if (id == cap) + return pos; + + /* Next one */ + pos += PCI_CAP_LIST_NEXT; + } + + return 0; +} + +static int pnv_eeh_find_ecap(struct pci_dn *pdn, int cap) +{ + struct eeh_dev *edev = pdn_to_eeh_dev(pdn); + u32 header; + int pos = 256, ttl = (4096 - 256) / 8; + + if (!edev || !edev->pcie_cap) + return 0; + if (pnv_pci_cfg_read(pdn, pos, 4, &header) != PCIBIOS_SUCCESSFUL) + return 0; + else if (!header) + return 0; + + while (ttl-- > 0) { + if (PCI_EXT_CAP_ID(header) == cap && pos) + return pos; + + pos = PCI_EXT_CAP_NEXT(header); + if (pos < 256) + break; + + if (pnv_pci_cfg_read(pdn, pos, 4, &header) != PCIBIOS_SUCCESSFUL) + break; + } + + return 0; +} + /** - * powernv_eeh_dev_probe - Do probe on PCI device - * @dev: PCI device - * @flag: unused + * pnv_eeh_probe - Do probe on PCI device + * @pdn: PCI device node + * @data: unused * * When EEH module is installed during system boot, all PCI devices * are checked one by one to see if it supports EEH. The function @@ -129,12 +375,12 @@ static int powernv_eeh_post_init(void) * was possiblly triggered by EEH core, the binding between EEH device * and the PCI device isn't built yet. */ -static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag) +static void *pnv_eeh_probe(struct pci_dn *pdn, void *data) { - struct pci_controller *hose = pci_bus_to_host(dev->bus); + struct pci_controller *hose = pdn->phb; struct pnv_phb *phb = hose->private_data; - struct device_node *dn = pci_device_to_OF_node(dev); - struct eeh_dev *edev = of_node_to_eeh_dev(dn); + struct eeh_dev *edev = pdn_to_eeh_dev(pdn); + uint32_t pcie_flags; int ret; /* @@ -143,40 +389,42 @@ static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag) * the root bridge. So it's not reasonable to continue * the probing. */ - if (!dn || !edev || edev->pe) - return 0; + if (!edev || edev->pe) + return NULL; /* Skip for PCI-ISA bridge */ - if ((dev->class >> 8) == PCI_CLASS_BRIDGE_ISA) - return 0; + if ((pdn->class_code >> 8) == PCI_CLASS_BRIDGE_ISA) + return NULL; /* Initialize eeh device */ - edev->class_code = dev->class; + edev->class_code = pdn->class_code; edev->mode &= 0xFFFFFF00; - if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) + edev->pcix_cap = pnv_eeh_find_cap(pdn, PCI_CAP_ID_PCIX); + edev->pcie_cap = pnv_eeh_find_cap(pdn, PCI_CAP_ID_EXP); + edev->aer_cap = pnv_eeh_find_ecap(pdn, PCI_EXT_CAP_ID_ERR); + if ((edev->class_code >> 8) == PCI_CLASS_BRIDGE_PCI) { edev->mode |= EEH_DEV_BRIDGE; - edev->pcix_cap = pci_find_capability(dev, PCI_CAP_ID_PCIX); - if (pci_is_pcie(dev)) { - edev->pcie_cap = pci_pcie_cap(dev); - - if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT) - edev->mode |= EEH_DEV_ROOT_PORT; - else if (pci_pcie_type(dev) == PCI_EXP_TYPE_DOWNSTREAM) - edev->mode |= EEH_DEV_DS_PORT; - - edev->aer_cap = pci_find_ext_capability(dev, - PCI_EXT_CAP_ID_ERR); + if (edev->pcie_cap) { + pnv_pci_cfg_read(pdn, edev->pcie_cap + PCI_EXP_FLAGS, + 2, &pcie_flags); + pcie_flags = (pcie_flags & PCI_EXP_FLAGS_TYPE) >> 4; + if (pcie_flags == PCI_EXP_TYPE_ROOT_PORT) + edev->mode |= EEH_DEV_ROOT_PORT; + else if (pcie_flags == PCI_EXP_TYPE_DOWNSTREAM) + edev->mode |= EEH_DEV_DS_PORT; + } } - edev->config_addr = ((dev->bus->number << 8) | dev->devfn); - edev->pe_config_addr = phb->bdfn_to_pe(phb, dev->bus, dev->devfn & 0xff); + edev->config_addr = (pdn->busno << 8) | (pdn->devfn); + edev->pe_config_addr = phb->ioda.pe_rmap[edev->config_addr]; /* Create PE */ ret = eeh_add_to_parent_pe(edev); if (ret) { - pr_warn("%s: Can't add PCI dev %s to parent PE (%d)\n", - __func__, pci_name(dev), ret); - return ret; + pr_warn("%s: Can't add PCI dev %04x:%02x:%02x.%01x to parent PE (%d)\n", + __func__, hose->global_number, pdn->busno, + PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn), ret); + return NULL; } /* @@ -195,8 +443,10 @@ static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag) * Broadcom Austin 4-ports NICs (14e4:1657) * Broadcom Shiner 2-ports 10G NICs (14e4:168e) */ - if ((dev->vendor == PCI_VENDOR_ID_BROADCOM && dev->device == 0x1657) || - (dev->vendor == PCI_VENDOR_ID_BROADCOM && dev->device == 0x168e)) + if ((pdn->vendor_id == PCI_VENDOR_ID_BROADCOM && + pdn->device_id == 0x1657) || + (pdn->vendor_id == PCI_VENDOR_ID_BROADCOM && + pdn->device_id == 0x168e)) edev->pe->state |= EEH_PE_CFG_RESTRICTED; /* @@ -206,7 +456,8 @@ static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag) * to PE reset. */ if (!edev->pe->bus) - edev->pe->bus = dev->bus; + edev->pe->bus = pci_find_bus(hose->global_number, + pdn->busno); /* * Enable EEH explicitly so that we will do EEH check @@ -217,11 +468,11 @@ static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag) /* Save memory bars */ eeh_save_bars(edev); - return 0; + return NULL; } /** - * powernv_eeh_set_option - Initialize EEH or MMIO/DMA reenable + * pnv_eeh_set_option - Initialize EEH or MMIO/DMA reenable * @pe: EEH PE * @option: operation to be issued * @@ -229,36 +480,236 @@ static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag) * Currently, following options are support according to PAPR: * Enable EEH, Disable EEH, Enable MMIO and Enable DMA */ -static int powernv_eeh_set_option(struct eeh_pe *pe, int option) +static int pnv_eeh_set_option(struct eeh_pe *pe, int option) { struct pci_controller *hose = pe->phb; struct pnv_phb *phb = hose->private_data; - int ret = -EEXIST; + bool freeze_pe = false; + int opt, ret = 0; + s64 rc; + + /* Sanity check on option */ + switch (option) { + case EEH_OPT_DISABLE: + return -EPERM; + case EEH_OPT_ENABLE: + return 0; + case EEH_OPT_THAW_MMIO: + opt = OPAL_EEH_ACTION_CLEAR_FREEZE_MMIO; + break; + case EEH_OPT_THAW_DMA: + opt = OPAL_EEH_ACTION_CLEAR_FREEZE_DMA; + break; + case EEH_OPT_FREEZE_PE: + freeze_pe = true; + opt = OPAL_EEH_ACTION_SET_FREEZE_ALL; + break; + default: + pr_warn("%s: Invalid option %d\n", __func__, option); + return -EINVAL; + } - /* - * What we need do is pass it down for hardware - * implementation to handle it. - */ - if (phb->eeh_ops && phb->eeh_ops->set_option) - ret = phb->eeh_ops->set_option(pe, option); + /* If PHB supports compound PE, to handle it */ + if (freeze_pe) { + if (phb->freeze_pe) { + phb->freeze_pe(phb, pe->addr); + } else { + rc = opal_pci_eeh_freeze_set(phb->opal_id, + pe->addr, opt); + if (rc != OPAL_SUCCESS) { + pr_warn("%s: Failure %lld freezing " + "PHB#%x-PE#%x\n", + __func__, rc, + phb->hose->global_number, pe->addr); + ret = -EIO; + } + } + } else { + if (phb->unfreeze_pe) { + ret = phb->unfreeze_pe(phb, pe->addr, opt); + } else { + rc = opal_pci_eeh_freeze_clear(phb->opal_id, + pe->addr, opt); + if (rc != OPAL_SUCCESS) { + pr_warn("%s: Failure %lld enable %d " + "for PHB#%x-PE#%x\n", + __func__, rc, option, + phb->hose->global_number, pe->addr); + ret = -EIO; + } + } + } return ret; } /** - * powernv_eeh_get_pe_addr - Retrieve PE address + * pnv_eeh_get_pe_addr - Retrieve PE address * @pe: EEH PE * * Retrieve the PE address according to the given tranditional * PCI BDF (Bus/Device/Function) address. */ -static int powernv_eeh_get_pe_addr(struct eeh_pe *pe) +static int pnv_eeh_get_pe_addr(struct eeh_pe *pe) { return pe->addr; } +static void pnv_eeh_get_phb_diag(struct eeh_pe *pe) +{ + struct pnv_phb *phb = pe->phb->private_data; + s64 rc; + + rc = opal_pci_get_phb_diag_data2(phb->opal_id, pe->data, + PNV_PCI_DIAG_BUF_SIZE); + if (rc != OPAL_SUCCESS) + pr_warn("%s: Failure %lld getting PHB#%x diag-data\n", + __func__, rc, pe->phb->global_number); +} + +static int pnv_eeh_get_phb_state(struct eeh_pe *pe) +{ + struct pnv_phb *phb = pe->phb->private_data; + u8 fstate; + __be16 pcierr; + s64 rc; + int result = 0; + + rc = opal_pci_eeh_freeze_status(phb->opal_id, + pe->addr, + &fstate, + &pcierr, + NULL); + if (rc != OPAL_SUCCESS) { + pr_warn("%s: Failure %lld getting PHB#%x state\n", + __func__, rc, phb->hose->global_number); + return EEH_STATE_NOT_SUPPORT; + } + + /* + * Check PHB state. If the PHB is frozen for the + * first time, to dump the PHB diag-data. + */ + if (be16_to_cpu(pcierr) != OPAL_EEH_PHB_ERROR) { + result = (EEH_STATE_MMIO_ACTIVE | + EEH_STATE_DMA_ACTIVE | + EEH_STATE_MMIO_ENABLED | + EEH_STATE_DMA_ENABLED); + } else if (!(pe->state & EEH_PE_ISOLATED)) { + eeh_pe_state_mark(pe, EEH_PE_ISOLATED); + pnv_eeh_get_phb_diag(pe); + + if (eeh_has_flag(EEH_EARLY_DUMP_LOG)) + pnv_pci_dump_phb_diag_data(pe->phb, pe->data); + } + + return result; +} + +static int pnv_eeh_get_pe_state(struct eeh_pe *pe) +{ + struct pnv_phb *phb = pe->phb->private_data; + u8 fstate; + __be16 pcierr; + s64 rc; + int result; + + /* + * We don't clobber hardware frozen state until PE + * reset is completed. In order to keep EEH core + * moving forward, we have to return operational + * state during PE reset. + */ + if (pe->state & EEH_PE_RESET) { + result = (EEH_STATE_MMIO_ACTIVE | + EEH_STATE_DMA_ACTIVE | + EEH_STATE_MMIO_ENABLED | + EEH_STATE_DMA_ENABLED); + return result; + } + + /* + * Fetch PE state from hardware. If the PHB + * supports compound PE, let it handle that. + */ + if (phb->get_pe_state) { + fstate = phb->get_pe_state(phb, pe->addr); + } else { + rc = opal_pci_eeh_freeze_status(phb->opal_id, + pe->addr, + &fstate, + &pcierr, + NULL); + if (rc != OPAL_SUCCESS) { + pr_warn("%s: Failure %lld getting PHB#%x-PE%x state\n", + __func__, rc, phb->hose->global_number, + pe->addr); + return EEH_STATE_NOT_SUPPORT; + } + } + + /* Figure out state */ + switch (fstate) { + case OPAL_EEH_STOPPED_NOT_FROZEN: + result = (EEH_STATE_MMIO_ACTIVE | + EEH_STATE_DMA_ACTIVE | + EEH_STATE_MMIO_ENABLED | + EEH_STATE_DMA_ENABLED); + break; + case OPAL_EEH_STOPPED_MMIO_FREEZE: + result = (EEH_STATE_DMA_ACTIVE | + EEH_STATE_DMA_ENABLED); + break; + case OPAL_EEH_STOPPED_DMA_FREEZE: + result = (EEH_STATE_MMIO_ACTIVE | + EEH_STATE_MMIO_ENABLED); + break; + case OPAL_EEH_STOPPED_MMIO_DMA_FREEZE: + result = 0; + break; + case OPAL_EEH_STOPPED_RESET: + result = EEH_STATE_RESET_ACTIVE; + break; + case OPAL_EEH_STOPPED_TEMP_UNAVAIL: + result = EEH_STATE_UNAVAILABLE; + break; + case OPAL_EEH_STOPPED_PERM_UNAVAIL: + result = EEH_STATE_NOT_SUPPORT; + break; + default: + result = EEH_STATE_NOT_SUPPORT; + pr_warn("%s: Invalid PHB#%x-PE#%x state %x\n", + __func__, phb->hose->global_number, + pe->addr, fstate); + } + + /* + * If PHB supports compound PE, to freeze all + * slave PEs for consistency. + * + * If the PE is switching to frozen state for the + * first time, to dump the PHB diag-data. + */ + if (!(result & EEH_STATE_NOT_SUPPORT) && + !(result & EEH_STATE_UNAVAILABLE) && + !(result & EEH_STATE_MMIO_ACTIVE) && + !(result & EEH_STATE_DMA_ACTIVE) && + !(pe->state & EEH_PE_ISOLATED)) { + if (phb->freeze_pe) + phb->freeze_pe(phb, pe->addr); + + eeh_pe_state_mark(pe, EEH_PE_ISOLATED); + pnv_eeh_get_phb_diag(pe); + + if (eeh_has_flag(EEH_EARLY_DUMP_LOG)) + pnv_pci_dump_phb_diag_data(pe->phb, pe->data); + } + + return result; +} + /** - * powernv_eeh_get_state - Retrieve PE state + * pnv_eeh_get_state - Retrieve PE state * @pe: EEH PE * @delay: delay while PE state is temporarily unavailable * @@ -267,64 +718,279 @@ static int powernv_eeh_get_pe_addr(struct eeh_pe *pe) * we prefer passing down to hardware implementation to handle * it. */ -static int powernv_eeh_get_state(struct eeh_pe *pe, int *delay) +static int pnv_eeh_get_state(struct eeh_pe *pe, int *delay) +{ + int ret; + + if (pe->type & EEH_PE_PHB) + ret = pnv_eeh_get_phb_state(pe); + else + ret = pnv_eeh_get_pe_state(pe); + + if (!delay) + return ret; + + /* + * If the PE state is temporarily unavailable, + * to inform the EEH core delay for default + * period (1 second) + */ + *delay = 0; + if (ret & EEH_STATE_UNAVAILABLE) + *delay = 1000; + + return ret; +} + +static s64 pnv_eeh_phb_poll(struct pnv_phb *phb) +{ + s64 rc = OPAL_HARDWARE; + + while (1) { + rc = opal_pci_poll(phb->opal_id); + if (rc <= 0) + break; + + if (system_state < SYSTEM_RUNNING) + udelay(1000 * rc); + else + msleep(rc); + } + + return rc; +} + +int pnv_eeh_phb_reset(struct pci_controller *hose, int option) { - struct pci_controller *hose = pe->phb; struct pnv_phb *phb = hose->private_data; - int ret = EEH_STATE_NOT_SUPPORT; + s64 rc = OPAL_HARDWARE; + + pr_debug("%s: Reset PHB#%x, option=%d\n", + __func__, hose->global_number, option); + + /* Issue PHB complete reset request */ + if (option == EEH_RESET_FUNDAMENTAL || + option == EEH_RESET_HOT) + rc = opal_pci_reset(phb->opal_id, + OPAL_RESET_PHB_COMPLETE, + OPAL_ASSERT_RESET); + else if (option == EEH_RESET_DEACTIVATE) + rc = opal_pci_reset(phb->opal_id, + OPAL_RESET_PHB_COMPLETE, + OPAL_DEASSERT_RESET); + if (rc < 0) + goto out; - if (phb->eeh_ops && phb->eeh_ops->get_state) { - ret = phb->eeh_ops->get_state(pe); + /* + * Poll state of the PHB until the request is done + * successfully. The PHB reset is usually PHB complete + * reset followed by hot reset on root bus. So we also + * need the PCI bus settlement delay. + */ + rc = pnv_eeh_phb_poll(phb); + if (option == EEH_RESET_DEACTIVATE) { + if (system_state < SYSTEM_RUNNING) + udelay(1000 * EEH_PE_RST_SETTLE_TIME); + else + msleep(EEH_PE_RST_SETTLE_TIME); + } +out: + if (rc != OPAL_SUCCESS) + return -EIO; - /* - * If the PE state is temporarily unavailable, - * to inform the EEH core delay for default - * period (1 second) - */ - if (delay) { - *delay = 0; - if (ret & EEH_STATE_UNAVAILABLE) - *delay = 1000; + return 0; +} + +static int pnv_eeh_root_reset(struct pci_controller *hose, int option) +{ + struct pnv_phb *phb = hose->private_data; + s64 rc = OPAL_HARDWARE; + + pr_debug("%s: Reset PHB#%x, option=%d\n", + __func__, hose->global_number, option); + + /* + * During the reset deassert time, we needn't care + * the reset scope because the firmware does nothing + * for fundamental or hot reset during deassert phase. + */ + if (option == EEH_RESET_FUNDAMENTAL) + rc = opal_pci_reset(phb->opal_id, + OPAL_RESET_PCI_FUNDAMENTAL, + OPAL_ASSERT_RESET); + else if (option == EEH_RESET_HOT) + rc = opal_pci_reset(phb->opal_id, + OPAL_RESET_PCI_HOT, + OPAL_ASSERT_RESET); + else if (option == EEH_RESET_DEACTIVATE) + rc = opal_pci_reset(phb->opal_id, + OPAL_RESET_PCI_HOT, + OPAL_DEASSERT_RESET); + if (rc < 0) + goto out; + + /* Poll state of the PHB until the request is done */ + rc = pnv_eeh_phb_poll(phb); + if (option == EEH_RESET_DEACTIVATE) + msleep(EEH_PE_RST_SETTLE_TIME); +out: + if (rc != OPAL_SUCCESS) + return -EIO; + + return 0; +} + +static int pnv_eeh_bridge_reset(struct pci_dev *dev, int option) +{ + struct pci_dn *pdn = pci_get_pdn_by_devfn(dev->bus, dev->devfn); + struct eeh_dev *edev = pdn_to_eeh_dev(pdn); + int aer = edev ? edev->aer_cap : 0; + u32 ctrl; + + pr_debug("%s: Reset PCI bus %04x:%02x with option %d\n", + __func__, pci_domain_nr(dev->bus), + dev->bus->number, option); + + switch (option) { + case EEH_RESET_FUNDAMENTAL: + case EEH_RESET_HOT: + /* Don't report linkDown event */ + if (aer) { + eeh_ops->read_config(pdn, aer + PCI_ERR_UNCOR_MASK, + 4, &ctrl); + ctrl |= PCI_ERR_UNC_SURPDN; + eeh_ops->write_config(pdn, aer + PCI_ERR_UNCOR_MASK, + 4, ctrl); } + + eeh_ops->read_config(pdn, PCI_BRIDGE_CONTROL, 2, &ctrl); + ctrl |= PCI_BRIDGE_CTL_BUS_RESET; + eeh_ops->write_config(pdn, PCI_BRIDGE_CONTROL, 2, ctrl); + + msleep(EEH_PE_RST_HOLD_TIME); + break; + case EEH_RESET_DEACTIVATE: + eeh_ops->read_config(pdn, PCI_BRIDGE_CONTROL, 2, &ctrl); + ctrl &= ~PCI_BRIDGE_CTL_BUS_RESET; + eeh_ops->write_config(pdn, PCI_BRIDGE_CONTROL, 2, ctrl); + + msleep(EEH_PE_RST_SETTLE_TIME); + + /* Continue reporting linkDown event */ + if (aer) { + eeh_ops->read_config(pdn, aer + PCI_ERR_UNCOR_MASK, + 4, &ctrl); + ctrl &= ~PCI_ERR_UNC_SURPDN; + eeh_ops->write_config(pdn, aer + PCI_ERR_UNCOR_MASK, + 4, ctrl); + } + + break; } - return ret; + return 0; +} + +void pnv_pci_reset_secondary_bus(struct pci_dev *dev) +{ + struct pci_controller *hose; + + if (pci_is_root_bus(dev->bus)) { + hose = pci_bus_to_host(dev->bus); + pnv_eeh_root_reset(hose, EEH_RESET_HOT); + pnv_eeh_root_reset(hose, EEH_RESET_DEACTIVATE); + } else { + pnv_eeh_bridge_reset(dev, EEH_RESET_HOT); + pnv_eeh_bridge_reset(dev, EEH_RESET_DEACTIVATE); + } } /** - * powernv_eeh_reset - Reset the specified PE + * pnv_eeh_reset - Reset the specified PE * @pe: EEH PE * @option: reset option * - * Reset the specified PE + * Do reset on the indicated PE. For PCI bus sensitive PE, + * we need to reset the parent p2p bridge. The PHB has to + * be reinitialized if the p2p bridge is root bridge. For + * PCI device sensitive PE, we will try to reset the device + * through FLR. For now, we don't have OPAL APIs to do HARD + * reset yet, so all reset would be SOFT (HOT) reset. */ -static int powernv_eeh_reset(struct eeh_pe *pe, int option) +static int pnv_eeh_reset(struct eeh_pe *pe, int option) { struct pci_controller *hose = pe->phb; - struct pnv_phb *phb = hose->private_data; - int ret = -EEXIST; + struct pci_bus *bus; + int ret; + + /* + * For PHB reset, we always have complete reset. For those PEs whose + * primary bus derived from root complex (root bus) or root port + * (usually bus#1), we apply hot or fundamental reset on the root port. + * For other PEs, we always have hot reset on the PE primary bus. + * + * Here, we have different design to pHyp, which always clear the + * frozen state during PE reset. However, the good idea here from + * benh is to keep frozen state before we get PE reset done completely + * (until BAR restore). With the frozen state, HW drops illegal IO + * or MMIO access, which can incur recrusive frozen PE during PE + * reset. The side effect is that EEH core has to clear the frozen + * state explicitly after BAR restore. + */ + if (pe->type & EEH_PE_PHB) { + ret = pnv_eeh_phb_reset(hose, option); + } else { + struct pnv_phb *phb; + s64 rc; - if (phb->eeh_ops && phb->eeh_ops->reset) - ret = phb->eeh_ops->reset(pe, option); + /* + * The frozen PE might be caused by PAPR error injection + * registers, which are expected to be cleared after hitting + * frozen PE as stated in the hardware spec. Unfortunately, + * that's not true on P7IOC. So we have to clear it manually + * to avoid recursive EEH errors during recovery. + */ + phb = hose->private_data; + if (phb->model == PNV_PHB_MODEL_P7IOC && + (option == EEH_RESET_HOT || + option == EEH_RESET_FUNDAMENTAL)) { + rc = opal_pci_reset(phb->opal_id, + OPAL_RESET_PHB_ERROR, + OPAL_ASSERT_RESET); + if (rc != OPAL_SUCCESS) { + pr_warn("%s: Failure %lld clearing " + "error injection registers\n", + __func__, rc); + return -EIO; + } + } + + bus = eeh_pe_bus_get(pe); + if (pci_is_root_bus(bus) || + pci_is_root_bus(bus->parent)) + ret = pnv_eeh_root_reset(hose, option); + else + ret = pnv_eeh_bridge_reset(bus->self, option); + } return ret; } /** - * powernv_eeh_wait_state - Wait for PE state + * pnv_eeh_wait_state - Wait for PE state * @pe: EEH PE * @max_wait: maximal period in microsecond * * Wait for the state of associated PE. It might take some time * to retrieve the PE's state. */ -static int powernv_eeh_wait_state(struct eeh_pe *pe, int max_wait) +static int pnv_eeh_wait_state(struct eeh_pe *pe, int max_wait) { int ret; int mwait; while (1) { - ret = powernv_eeh_get_state(pe, &mwait); + ret = pnv_eeh_get_state(pe, &mwait); /* * If the PE's state is temporarily unavailable, @@ -348,7 +1014,7 @@ static int powernv_eeh_wait_state(struct eeh_pe *pe, int max_wait) } /** - * powernv_eeh_get_log - Retrieve error log + * pnv_eeh_get_log - Retrieve error log * @pe: EEH PE * @severity: temporary or permanent error log * @drv_log: driver log to be combined with retrieved error log @@ -356,41 +1022,30 @@ static int powernv_eeh_wait_state(struct eeh_pe *pe, int max_wait) * * Retrieve the temporary or permanent error from the PE. */ -static int powernv_eeh_get_log(struct eeh_pe *pe, int severity, - char *drv_log, unsigned long len) +static int pnv_eeh_get_log(struct eeh_pe *pe, int severity, + char *drv_log, unsigned long len) { - struct pci_controller *hose = pe->phb; - struct pnv_phb *phb = hose->private_data; - int ret = -EEXIST; + if (!eeh_has_flag(EEH_EARLY_DUMP_LOG)) + pnv_pci_dump_phb_diag_data(pe->phb, pe->data); - if (phb->eeh_ops && phb->eeh_ops->get_log) - ret = phb->eeh_ops->get_log(pe, severity, drv_log, len); - - return ret; + return 0; } /** - * powernv_eeh_configure_bridge - Configure PCI bridges in the indicated PE + * pnv_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 powernv_eeh_configure_bridge(struct eeh_pe *pe) +static int pnv_eeh_configure_bridge(struct eeh_pe *pe) { - struct pci_controller *hose = pe->phb; - struct pnv_phb *phb = hose->private_data; - int ret = 0; - - if (phb->eeh_ops && phb->eeh_ops->configure_bridge) - ret = phb->eeh_ops->configure_bridge(pe); - - return ret; + return 0; } /** - * powernv_pe_err_inject - Inject specified error to the indicated PE + * pnv_pe_err_inject - Inject specified error to the indicated PE * @pe: the indicated PE * @type: error type * @func: specific error type @@ -401,22 +1056,52 @@ static int powernv_eeh_configure_bridge(struct eeh_pe *pe) * determined by @type and @func, to the indicated PE for * testing purpose. */ -static int powernv_eeh_err_inject(struct eeh_pe *pe, int type, int func, - unsigned long addr, unsigned long mask) +static int pnv_eeh_err_inject(struct eeh_pe *pe, int type, int func, + unsigned long addr, unsigned long mask) { struct pci_controller *hose = pe->phb; struct pnv_phb *phb = hose->private_data; - int ret = -EEXIST; + s64 rc; + + /* Sanity check on error type */ + if (type != OPAL_ERR_INJECT_TYPE_IOA_BUS_ERR && + type != OPAL_ERR_INJECT_TYPE_IOA_BUS_ERR64) { + pr_warn("%s: Invalid error type %d\n", + __func__, type); + return -ERANGE; + } - if (phb->eeh_ops && phb->eeh_ops->err_inject) - ret = phb->eeh_ops->err_inject(pe, type, func, addr, mask); + if (func < OPAL_ERR_INJECT_FUNC_IOA_LD_MEM_ADDR || + func > OPAL_ERR_INJECT_FUNC_IOA_DMA_WR_TARGET) { + pr_warn("%s: Invalid error function %d\n", + __func__, func); + return -ERANGE; + } - return ret; + /* Firmware supports error injection ? */ + if (!opal_check_token(OPAL_PCI_ERR_INJECT)) { + pr_warn("%s: Firmware doesn't support error injection\n", + __func__); + return -ENXIO; + } + + /* Do error injection */ + rc = opal_pci_err_inject(phb->opal_id, pe->addr, + type, func, addr, mask); + if (rc != OPAL_SUCCESS) { + pr_warn("%s: Failure %lld injecting error " + "%d-%d to PHB#%x-PE#%x\n", + __func__, rc, type, func, + hose->global_number, pe->addr); + return -EIO; + } + + return 0; } -static inline bool powernv_eeh_cfg_blocked(struct device_node *dn) +static inline bool pnv_eeh_cfg_blocked(struct pci_dn *pdn) { - struct eeh_dev *edev = of_node_to_eeh_dev(dn); + struct eeh_dev *edev = pdn_to_eeh_dev(pdn); if (!edev || !edev->pe) return false; @@ -427,51 +1112,377 @@ static inline bool powernv_eeh_cfg_blocked(struct device_node *dn) return false; } -static int powernv_eeh_read_config(struct device_node *dn, - int where, int size, u32 *val) +static int pnv_eeh_read_config(struct pci_dn *pdn, + int where, int size, u32 *val) { - if (powernv_eeh_cfg_blocked(dn)) { + if (!pdn) + return PCIBIOS_DEVICE_NOT_FOUND; + + if (pnv_eeh_cfg_blocked(pdn)) { *val = 0xFFFFFFFF; return PCIBIOS_SET_FAILED; } - return pnv_pci_cfg_read(dn, where, size, val); + return pnv_pci_cfg_read(pdn, where, size, val); } -static int powernv_eeh_write_config(struct device_node *dn, - int where, int size, u32 val) +static int pnv_eeh_write_config(struct pci_dn *pdn, + int where, int size, u32 val) { - if (powernv_eeh_cfg_blocked(dn)) + if (!pdn) + return PCIBIOS_DEVICE_NOT_FOUND; + + if (pnv_eeh_cfg_blocked(pdn)) return PCIBIOS_SET_FAILED; - return pnv_pci_cfg_write(dn, where, size, val); + return pnv_pci_cfg_write(pdn, where, size, val); +} + +static void pnv_eeh_dump_hub_diag_common(struct OpalIoP7IOCErrorData *data) +{ + /* GEM */ + if (data->gemXfir || data->gemRfir || + data->gemRirqfir || data->gemMask || data->gemRwof) + pr_info(" GEM: %016llx %016llx %016llx %016llx %016llx\n", + be64_to_cpu(data->gemXfir), + be64_to_cpu(data->gemRfir), + be64_to_cpu(data->gemRirqfir), + be64_to_cpu(data->gemMask), + be64_to_cpu(data->gemRwof)); + + /* LEM */ + if (data->lemFir || data->lemErrMask || + data->lemAction0 || data->lemAction1 || data->lemWof) + pr_info(" LEM: %016llx %016llx %016llx %016llx %016llx\n", + be64_to_cpu(data->lemFir), + be64_to_cpu(data->lemErrMask), + be64_to_cpu(data->lemAction0), + be64_to_cpu(data->lemAction1), + be64_to_cpu(data->lemWof)); +} + +static void pnv_eeh_get_and_dump_hub_diag(struct pci_controller *hose) +{ + struct pnv_phb *phb = hose->private_data; + struct OpalIoP7IOCErrorData *data = &phb->diag.hub_diag; + long rc; + + rc = opal_pci_get_hub_diag_data(phb->hub_id, data, sizeof(*data)); + if (rc != OPAL_SUCCESS) { + pr_warn("%s: Failed to get HUB#%llx diag-data (%ld)\n", + __func__, phb->hub_id, rc); + return; + } + + switch (data->type) { + case OPAL_P7IOC_DIAG_TYPE_RGC: + pr_info("P7IOC diag-data for RGC\n\n"); + pnv_eeh_dump_hub_diag_common(data); + if (data->rgc.rgcStatus || data->rgc.rgcLdcp) + pr_info(" RGC: %016llx %016llx\n", + be64_to_cpu(data->rgc.rgcStatus), + be64_to_cpu(data->rgc.rgcLdcp)); + break; + case OPAL_P7IOC_DIAG_TYPE_BI: + pr_info("P7IOC diag-data for BI %s\n\n", + data->bi.biDownbound ? "Downbound" : "Upbound"); + pnv_eeh_dump_hub_diag_common(data); + if (data->bi.biLdcp0 || data->bi.biLdcp1 || + data->bi.biLdcp2 || data->bi.biFenceStatus) + pr_info(" BI: %016llx %016llx %016llx %016llx\n", + be64_to_cpu(data->bi.biLdcp0), + be64_to_cpu(data->bi.biLdcp1), + be64_to_cpu(data->bi.biLdcp2), + be64_to_cpu(data->bi.biFenceStatus)); + break; + case OPAL_P7IOC_DIAG_TYPE_CI: + pr_info("P7IOC diag-data for CI Port %d\n\n", + data->ci.ciPort); + pnv_eeh_dump_hub_diag_common(data); + if (data->ci.ciPortStatus || data->ci.ciPortLdcp) + pr_info(" CI: %016llx %016llx\n", + be64_to_cpu(data->ci.ciPortStatus), + be64_to_cpu(data->ci.ciPortLdcp)); + break; + case OPAL_P7IOC_DIAG_TYPE_MISC: + pr_info("P7IOC diag-data for MISC\n\n"); + pnv_eeh_dump_hub_diag_common(data); + break; + case OPAL_P7IOC_DIAG_TYPE_I2C: + pr_info("P7IOC diag-data for I2C\n\n"); + pnv_eeh_dump_hub_diag_common(data); + break; + default: + pr_warn("%s: Invalid type of HUB#%llx diag-data (%d)\n", + __func__, phb->hub_id, data->type); + } +} + +static int pnv_eeh_get_pe(struct pci_controller *hose, + u16 pe_no, struct eeh_pe **pe) +{ + struct pnv_phb *phb = hose->private_data; + struct pnv_ioda_pe *pnv_pe; + struct eeh_pe *dev_pe; + struct eeh_dev edev; + + /* + * If PHB supports compound PE, to fetch + * the master PE because slave PE is invisible + * to EEH core. + */ + pnv_pe = &phb->ioda.pe_array[pe_no]; + if (pnv_pe->flags & PNV_IODA_PE_SLAVE) { + pnv_pe = pnv_pe->master; + WARN_ON(!pnv_pe || + !(pnv_pe->flags & PNV_IODA_PE_MASTER)); + pe_no = pnv_pe->pe_number; + } + + /* Find the PE according to PE# */ + memset(&edev, 0, sizeof(struct eeh_dev)); + edev.phb = hose; + edev.pe_config_addr = pe_no; + dev_pe = eeh_pe_get(&edev); + if (!dev_pe) + return -EEXIST; + + /* Freeze the (compound) PE */ + *pe = dev_pe; + if (!(dev_pe->state & EEH_PE_ISOLATED)) + phb->freeze_pe(phb, pe_no); + + /* + * At this point, we're sure the (compound) PE should + * have been frozen. However, we still need poke until + * hitting the frozen PE on top level. + */ + dev_pe = dev_pe->parent; + while (dev_pe && !(dev_pe->type & EEH_PE_PHB)) { + int ret; + int active_flags = (EEH_STATE_MMIO_ACTIVE | + EEH_STATE_DMA_ACTIVE); + + ret = eeh_ops->get_state(dev_pe, NULL); + if (ret <= 0 || (ret & active_flags) == active_flags) { + dev_pe = dev_pe->parent; + continue; + } + + /* Frozen parent PE */ + *pe = dev_pe; + if (!(dev_pe->state & EEH_PE_ISOLATED)) + phb->freeze_pe(phb, dev_pe->addr); + + /* Next one */ + dev_pe = dev_pe->parent; + } + + return 0; } /** - * powernv_eeh_next_error - Retrieve next EEH error to handle + * pnv_eeh_next_error - Retrieve next EEH error to handle * @pe: Affected PE * - * Using OPAL API, to retrieve next EEH error for EEH core to handle + * The function is expected to be called by EEH core while it gets + * special EEH event (without binding PE). The function calls to + * OPAL APIs for next error to handle. The informational error is + * handled internally by platform. However, the dead IOC, dead PHB, + * fenced PHB and frozen PE should be handled by EEH core eventually. */ -static int powernv_eeh_next_error(struct eeh_pe **pe) +static int pnv_eeh_next_error(struct eeh_pe **pe) { struct pci_controller *hose; - struct pnv_phb *phb = NULL; + struct pnv_phb *phb; + struct eeh_pe *phb_pe, *parent_pe; + __be64 frozen_pe_no; + __be16 err_type, severity; + int active_flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE); + long rc; + int state, ret = EEH_NEXT_ERR_NONE; + + /* + * While running here, it's safe to purge the event queue. + * And we should keep the cached OPAL notifier event sychronized + * between the kernel and firmware. + */ + eeh_remove_event(NULL, false); + opal_notifier_update_evt(OPAL_EVENT_PCI_ERROR, 0x0ul); list_for_each_entry(hose, &hose_list, list_node) { + /* + * If the subordinate PCI buses of the PHB has been + * removed or is exactly under error recovery, we + * needn't take care of it any more. + */ phb = hose->private_data; - break; - } + phb_pe = eeh_phb_pe_get(hose); + if (!phb_pe || (phb_pe->state & EEH_PE_ISOLATED)) + continue; + + rc = opal_pci_next_error(phb->opal_id, + &frozen_pe_no, &err_type, &severity); + if (rc != OPAL_SUCCESS) { + pr_devel("%s: Invalid return value on " + "PHB#%x (0x%lx) from opal_pci_next_error", + __func__, hose->global_number, rc); + continue; + } + + /* If the PHB doesn't have error, stop processing */ + if (be16_to_cpu(err_type) == OPAL_EEH_NO_ERROR || + be16_to_cpu(severity) == OPAL_EEH_SEV_NO_ERROR) { + pr_devel("%s: No error found on PHB#%x\n", + __func__, hose->global_number); + continue; + } + + /* + * Processing the error. We're expecting the error with + * highest priority reported upon multiple errors on the + * specific PHB. + */ + pr_devel("%s: Error (%d, %d, %llu) on PHB#%x\n", + __func__, be16_to_cpu(err_type), + be16_to_cpu(severity), be64_to_cpu(frozen_pe_no), + hose->global_number); + switch (be16_to_cpu(err_type)) { + case OPAL_EEH_IOC_ERROR: + if (be16_to_cpu(severity) == OPAL_EEH_SEV_IOC_DEAD) { + pr_err("EEH: dead IOC detected\n"); + ret = EEH_NEXT_ERR_DEAD_IOC; + } else if (be16_to_cpu(severity) == OPAL_EEH_SEV_INF) { + pr_info("EEH: IOC informative error " + "detected\n"); + pnv_eeh_get_and_dump_hub_diag(hose); + ret = EEH_NEXT_ERR_NONE; + } + + break; + case OPAL_EEH_PHB_ERROR: + if (be16_to_cpu(severity) == OPAL_EEH_SEV_PHB_DEAD) { + *pe = phb_pe; + pr_err("EEH: dead PHB#%x detected, " + "location: %s\n", + hose->global_number, + eeh_pe_loc_get(phb_pe)); + ret = EEH_NEXT_ERR_DEAD_PHB; + } else if (be16_to_cpu(severity) == + OPAL_EEH_SEV_PHB_FENCED) { + *pe = phb_pe; + pr_err("EEH: Fenced PHB#%x detected, " + "location: %s\n", + hose->global_number, + eeh_pe_loc_get(phb_pe)); + ret = EEH_NEXT_ERR_FENCED_PHB; + } else if (be16_to_cpu(severity) == OPAL_EEH_SEV_INF) { + pr_info("EEH: PHB#%x informative error " + "detected, location: %s\n", + hose->global_number, + eeh_pe_loc_get(phb_pe)); + pnv_eeh_get_phb_diag(phb_pe); + pnv_pci_dump_phb_diag_data(hose, phb_pe->data); + ret = EEH_NEXT_ERR_NONE; + } + + break; + case OPAL_EEH_PE_ERROR: + /* + * If we can't find the corresponding PE, we + * just try to unfreeze. + */ + if (pnv_eeh_get_pe(hose, + be64_to_cpu(frozen_pe_no), pe)) { + /* Try best to clear it */ + pr_info("EEH: Clear non-existing PHB#%x-PE#%llx\n", + hose->global_number, frozen_pe_no); + pr_info("EEH: PHB location: %s\n", + eeh_pe_loc_get(phb_pe)); + opal_pci_eeh_freeze_clear(phb->opal_id, + frozen_pe_no, + OPAL_EEH_ACTION_CLEAR_FREEZE_ALL); + ret = EEH_NEXT_ERR_NONE; + } else if ((*pe)->state & EEH_PE_ISOLATED || + eeh_pe_passed(*pe)) { + ret = EEH_NEXT_ERR_NONE; + } else { + pr_err("EEH: Frozen PE#%x " + "on PHB#%x detected\n", + (*pe)->addr, + (*pe)->phb->global_number); + pr_err("EEH: PE location: %s, " + "PHB location: %s\n", + eeh_pe_loc_get(*pe), + eeh_pe_loc_get(phb_pe)); + ret = EEH_NEXT_ERR_FROZEN_PE; + } + + break; + default: + pr_warn("%s: Unexpected error type %d\n", + __func__, be16_to_cpu(err_type)); + } - if (phb && phb->eeh_ops->next_error) - return phb->eeh_ops->next_error(pe); + /* + * EEH core will try recover from fenced PHB or + * frozen PE. In the time for frozen PE, EEH core + * enable IO path for that before collecting logs, + * but it ruins the site. So we have to dump the + * log in advance here. + */ + if ((ret == EEH_NEXT_ERR_FROZEN_PE || + ret == EEH_NEXT_ERR_FENCED_PHB) && + !((*pe)->state & EEH_PE_ISOLATED)) { + eeh_pe_state_mark(*pe, EEH_PE_ISOLATED); + pnv_eeh_get_phb_diag(*pe); + + if (eeh_has_flag(EEH_EARLY_DUMP_LOG)) + pnv_pci_dump_phb_diag_data((*pe)->phb, + (*pe)->data); + } - return -EEXIST; + /* + * We probably have the frozen parent PE out there and + * we need have to handle frozen parent PE firstly. + */ + if (ret == EEH_NEXT_ERR_FROZEN_PE) { + parent_pe = (*pe)->parent; + while (parent_pe) { + /* Hit the ceiling ? */ + if (parent_pe->type & EEH_PE_PHB) + break; + + /* Frozen parent PE ? */ + state = eeh_ops->get_state(parent_pe, NULL); + if (state > 0 && + (state & active_flags) != active_flags) + *pe = parent_pe; + + /* Next parent level */ + parent_pe = parent_pe->parent; + } + + /* We possibly migrate to another PE */ + eeh_pe_state_mark(*pe, EEH_PE_ISOLATED); + } + + /* + * If we have no errors on the specific PHB or only + * informative error there, we continue poking it. + * Otherwise, we need actions to be taken by upper + * layer. + */ + if (ret > EEH_NEXT_ERR_INF) + break; + } + + return ret; } -static int powernv_eeh_restore_config(struct device_node *dn) +static int pnv_eeh_restore_config(struct pci_dn *pdn) { - struct eeh_dev *edev = of_node_to_eeh_dev(dn); + struct eeh_dev *edev = pdn_to_eeh_dev(pdn); struct pnv_phb *phb; s64 ret; @@ -490,24 +1501,23 @@ static int powernv_eeh_restore_config(struct device_node *dn) return 0; } -static struct eeh_ops powernv_eeh_ops = { +static struct eeh_ops pnv_eeh_ops = { .name = "powernv", - .init = powernv_eeh_init, - .post_init = powernv_eeh_post_init, - .of_probe = NULL, - .dev_probe = powernv_eeh_dev_probe, - .set_option = powernv_eeh_set_option, - .get_pe_addr = powernv_eeh_get_pe_addr, - .get_state = powernv_eeh_get_state, - .reset = powernv_eeh_reset, - .wait_state = powernv_eeh_wait_state, - .get_log = powernv_eeh_get_log, - .configure_bridge = powernv_eeh_configure_bridge, - .err_inject = powernv_eeh_err_inject, - .read_config = powernv_eeh_read_config, - .write_config = powernv_eeh_write_config, - .next_error = powernv_eeh_next_error, - .restore_config = powernv_eeh_restore_config + .init = pnv_eeh_init, + .post_init = pnv_eeh_post_init, + .probe = pnv_eeh_probe, + .set_option = pnv_eeh_set_option, + .get_pe_addr = pnv_eeh_get_pe_addr, + .get_state = pnv_eeh_get_state, + .reset = pnv_eeh_reset, + .wait_state = pnv_eeh_wait_state, + .get_log = pnv_eeh_get_log, + .configure_bridge = pnv_eeh_configure_bridge, + .err_inject = pnv_eeh_err_inject, + .read_config = pnv_eeh_read_config, + .write_config = pnv_eeh_write_config, + .next_error = pnv_eeh_next_error, + .restore_config = pnv_eeh_restore_config }; /** @@ -521,7 +1531,7 @@ static int __init eeh_powernv_init(void) int ret = -EINVAL; eeh_set_pe_aux_size(PNV_PCI_DIAG_BUF_SIZE); - ret = eeh_ops_register(&powernv_eeh_ops); + ret = eeh_ops_register(&pnv_eeh_ops); if (!ret) pr_info("EEH: PowerNV platform initialized\n"); else diff --git a/arch/powerpc/platforms/powernv/opal-dump.c b/arch/powerpc/platforms/powernv/opal-dump.c index 23260f7dfa7a..5aa9c1ce4de3 100644 --- a/arch/powerpc/platforms/powernv/opal-dump.c +++ b/arch/powerpc/platforms/powernv/opal-dump.c @@ -452,5 +452,6 @@ void __init opal_platform_dump_init(void) return; } - opal_dump_resend_notification(); + if (opal_check_token(OPAL_DUMP_RESEND)) + opal_dump_resend_notification(); } diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c index 518fe95dbf24..38ce757e5e2a 100644 --- a/arch/powerpc/platforms/powernv/opal-elog.c +++ b/arch/powerpc/platforms/powernv/opal-elog.c @@ -313,7 +313,8 @@ int __init opal_elog_init(void) } /* We are now ready to pull error logs from opal. */ - opal_resend_pending_logs(); + if (opal_check_token(OPAL_ELOG_RESEND)) + opal_resend_pending_logs(); return 0; } diff --git a/arch/powerpc/platforms/powernv/opal-flash.c b/arch/powerpc/platforms/powernv/opal-flash.c index 5c21d9c07f45..4ec6219287fc 100644 --- a/arch/powerpc/platforms/powernv/opal-flash.c +++ b/arch/powerpc/platforms/powernv/opal-flash.c @@ -120,7 +120,11 @@ static struct image_header_t image_header; static struct image_data_t image_data; static struct validate_flash_t validate_flash_data; static struct manage_flash_t manage_flash_data; -static struct update_flash_t update_flash_data; + +/* Initialize update_flash_data status to No Operation */ +static struct update_flash_t update_flash_data = { + .status = FLASH_NO_OP, +}; static DEFINE_MUTEX(image_data_mutex); @@ -542,7 +546,7 @@ static struct attribute_group image_op_attr_group = { .attrs = image_op_attrs, }; -void __init opal_flash_init(void) +void __init opal_flash_update_init(void) { int ret; diff --git a/arch/powerpc/platforms/powernv/opal-nvram.c b/arch/powerpc/platforms/powernv/opal-nvram.c index f9896fd5d04a..9db4398ded5d 100644 --- a/arch/powerpc/platforms/powernv/opal-nvram.c +++ b/arch/powerpc/platforms/powernv/opal-nvram.c @@ -16,6 +16,7 @@ #include <linux/of.h> #include <asm/opal.h> +#include <asm/nvram.h> #include <asm/machdep.h> static unsigned int nvram_size; @@ -62,6 +63,15 @@ static ssize_t opal_nvram_write(char *buf, size_t count, loff_t *index) return count; } +static int __init opal_nvram_init_log_partitions(void) +{ + /* Scan nvram for partitions */ + nvram_scan_partitions(); + nvram_init_oops_partition(0); + return 0; +} +machine_arch_initcall(powernv, opal_nvram_init_log_partitions); + void __init opal_nvram_init(void) { struct device_node *np; diff --git a/arch/powerpc/platforms/powernv/opal-sensor.c b/arch/powerpc/platforms/powernv/opal-sensor.c index 4ab67ef7abc9..655250499d18 100644 --- a/arch/powerpc/platforms/powernv/opal-sensor.c +++ b/arch/powerpc/platforms/powernv/opal-sensor.c @@ -46,18 +46,28 @@ int opal_get_sensor_data(u32 sensor_hndl, u32 *sensor_data) mutex_lock(&opal_sensor_mutex); ret = opal_sensor_read(sensor_hndl, token, &data); - if (ret != OPAL_ASYNC_COMPLETION) - goto out_token; + switch (ret) { + case OPAL_ASYNC_COMPLETION: + ret = opal_async_wait_response(token, &msg); + if (ret) { + pr_err("%s: Failed to wait for the async response, %d\n", + __func__, ret); + goto out_token; + } - ret = opal_async_wait_response(token, &msg); - if (ret) { - pr_err("%s: Failed to wait for the async response, %d\n", - __func__, ret); - goto out_token; - } + ret = opal_error_code(be64_to_cpu(msg.params[1])); + *sensor_data = be32_to_cpu(data); + break; + + case OPAL_SUCCESS: + ret = 0; + *sensor_data = be32_to_cpu(data); + break; - *sensor_data = be32_to_cpu(data); - ret = be64_to_cpu(msg.params[1]); + default: + ret = opal_error_code(ret); + break; + } out_token: mutex_unlock(&opal_sensor_mutex); diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S index fcbe899fe299..a7ade94cdf87 100644 --- a/arch/powerpc/platforms/powernv/opal-wrappers.S +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S @@ -286,9 +286,12 @@ OPAL_CALL(opal_handle_hmi, OPAL_HANDLE_HMI); OPAL_CALL(opal_slw_set_reg, OPAL_SLW_SET_REG); OPAL_CALL(opal_register_dump_region, OPAL_REGISTER_DUMP_REGION); OPAL_CALL(opal_unregister_dump_region, OPAL_UNREGISTER_DUMP_REGION); -OPAL_CALL(opal_pci_set_phb_cxl_mode, OPAL_PCI_SET_PHB_CXL_MODE); +OPAL_CALL(opal_pci_set_phb_cxl_mode, OPAL_PCI_SET_PHB_CAPI_MODE); OPAL_CALL(opal_tpo_write, OPAL_WRITE_TPO); OPAL_CALL(opal_tpo_read, OPAL_READ_TPO); OPAL_CALL(opal_ipmi_send, OPAL_IPMI_SEND); OPAL_CALL(opal_ipmi_recv, OPAL_IPMI_RECV); OPAL_CALL(opal_i2c_request, OPAL_I2C_REQUEST); +OPAL_CALL(opal_flash_read, OPAL_FLASH_READ); +OPAL_CALL(opal_flash_write, OPAL_FLASH_WRITE); +OPAL_CALL(opal_flash_erase, OPAL_FLASH_ERASE); diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 18fd4e71c9c1..2241565b0739 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -23,6 +23,8 @@ #include <linux/kobject.h> #include <linux/delay.h> #include <linux/memblock.h> +#include <linux/kthread.h> +#include <linux/freezer.h> #include <asm/machdep.h> #include <asm/opal.h> @@ -58,6 +60,7 @@ static struct atomic_notifier_head opal_msg_notifier_head[OPAL_MSG_TYPE_MAX]; static DEFINE_SPINLOCK(opal_notifier_lock); static uint64_t last_notified_mask = 0x0ul; static atomic_t opal_notifier_hold = ATOMIC_INIT(0); +static uint32_t opal_heartbeat; static void opal_reinit_cores(void) { @@ -302,23 +305,26 @@ void opal_notifier_disable(void) * Opal message notifier based on message type. Allow subscribers to get * notified for specific messgae type. */ -int opal_message_notifier_register(enum OpalMessageType msg_type, +int opal_message_notifier_register(enum opal_msg_type msg_type, struct notifier_block *nb) { - if (!nb) { - pr_warning("%s: Invalid argument (%p)\n", - __func__, nb); - return -EINVAL; - } - if (msg_type > OPAL_MSG_TYPE_MAX) { - pr_warning("%s: Invalid message type argument (%d)\n", + if (!nb || msg_type >= OPAL_MSG_TYPE_MAX) { + pr_warning("%s: Invalid arguments, msg_type:%d\n", __func__, msg_type); return -EINVAL; } + return atomic_notifier_chain_register( &opal_msg_notifier_head[msg_type], nb); } +int opal_message_notifier_unregister(enum opal_msg_type msg_type, + struct notifier_block *nb) +{ + return atomic_notifier_chain_unregister( + &opal_msg_notifier_head[msg_type], nb); +} + static void opal_message_do_notify(uint32_t msg_type, void *msg) { /* notify subscribers */ @@ -351,7 +357,7 @@ static void opal_handle_message(void) type = be32_to_cpu(msg.msg_type); /* Sanity check */ - if (type > OPAL_MSG_TYPE_MAX) { + if (type >= OPAL_MSG_TYPE_MAX) { pr_warning("%s: Unknown message type: %u\n", __func__, type); return; } @@ -665,6 +671,9 @@ static void __init opal_dump_region_init(void) uint64_t size; int rc; + if (!opal_check_token(OPAL_REGISTER_DUMP_REGION)) + return; + /* Register kernel log buffer */ addr = log_buf_addr_get(); if (addr == NULL) @@ -684,6 +693,15 @@ static void __init opal_dump_region_init(void) "rc = %d\n", rc); } +static void opal_flash_init(struct device_node *opal_node) +{ + struct device_node *np; + + for_each_child_of_node(opal_node, np) + if (of_device_is_compatible(np, "ibm,opal-flash")) + of_platform_device_create(np, NULL, NULL); +} + static void opal_ipmi_init(struct device_node *opal_node) { struct device_node *np; @@ -741,6 +759,29 @@ static void __init opal_irq_init(struct device_node *dn) } } +static int kopald(void *unused) +{ + set_freezable(); + do { + try_to_freeze(); + opal_poll_events(NULL); + msleep_interruptible(opal_heartbeat); + } while (!kthread_should_stop()); + + return 0; +} + +static void opal_init_heartbeat(void) +{ + /* Old firwmware, we assume the HVC heartbeat is sufficient */ + if (of_property_read_u32(opal_node, "ibm,heartbeat-ms", + &opal_heartbeat) != 0) + opal_heartbeat = 0; + + if (opal_heartbeat) + kthread_run(kopald, NULL, "kopald"); +} + static int __init opal_init(void) { struct device_node *np, *consoles; @@ -769,6 +810,9 @@ static int __init opal_init(void) /* Create i2c platform devices */ opal_i2c_create_devs(); + /* Setup a heatbeat thread if requested by OPAL */ + opal_init_heartbeat(); + /* Find all OPAL interrupts and request them */ opal_irq_init(opal_node); @@ -782,7 +826,7 @@ static int __init opal_init(void) /* Setup error log interface */ rc = opal_elog_init(); /* Setup code update interface */ - opal_flash_init(); + opal_flash_update_init(); /* Setup platform dump extract interface */ opal_platform_dump_init(); /* Setup system parameters interface */ @@ -791,8 +835,11 @@ static int __init opal_init(void) opal_msglog_init(); } + /* Initialize OPAL IPMI backend */ opal_ipmi_init(opal_node); + opal_flash_init(opal_node); + return 0; } machine_subsys_initcall(powernv, opal_init); @@ -823,13 +870,17 @@ void opal_shutdown(void) } /* Unregister memory dump region */ - opal_unregister_dump_region(OPAL_DUMP_REGION_LOG_BUF); + if (opal_check_token(OPAL_UNREGISTER_DUMP_REGION)) + opal_unregister_dump_region(OPAL_DUMP_REGION_LOG_BUF); } /* Export this so that test modules can use it */ EXPORT_SYMBOL_GPL(opal_invalid_call); EXPORT_SYMBOL_GPL(opal_ipmi_send); EXPORT_SYMBOL_GPL(opal_ipmi_recv); +EXPORT_SYMBOL_GPL(opal_flash_read); +EXPORT_SYMBOL_GPL(opal_flash_write); +EXPORT_SYMBOL_GPL(opal_flash_erase); /* Convert a region of vmalloc memory to an opal sg list */ struct opal_sg_list *opal_vmalloc_to_sg_list(void *vmalloc_addr, @@ -894,6 +945,25 @@ void opal_free_sg_list(struct opal_sg_list *sg) } } +int opal_error_code(int rc) +{ + switch (rc) { + case OPAL_SUCCESS: return 0; + + case OPAL_PARAMETER: return -EINVAL; + case OPAL_ASYNC_COMPLETION: return -EINPROGRESS; + case OPAL_BUSY_EVENT: return -EBUSY; + case OPAL_NO_MEM: return -ENOMEM; + + case OPAL_UNSUPPORTED: return -EIO; + case OPAL_HARDWARE: return -EIO; + case OPAL_INTERNAL_ERROR: return -EIO; + default: + pr_err("%s: unexpected OPAL error %d\n", __func__, rc); + return -EIO; + } +} + EXPORT_SYMBOL_GPL(opal_poll_events); EXPORT_SYMBOL_GPL(opal_rtc_read); EXPORT_SYMBOL_GPL(opal_rtc_write); diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 6c9ff2b95119..920c252d1f49 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -44,6 +44,9 @@ #include "powernv.h" #include "pci.h" +/* 256M DMA window, 4K TCE pages, 8 bytes TCE */ +#define TCE32_TABLE_SIZE ((0x10000000 / 0x1000) * 8) + static void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level, const char *fmt, ...) { @@ -56,11 +59,18 @@ static void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level, vaf.fmt = fmt; vaf.va = &args; - if (pe->pdev) + if (pe->flags & PNV_IODA_PE_DEV) strlcpy(pfix, dev_name(&pe->pdev->dev), sizeof(pfix)); - else + else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)) sprintf(pfix, "%04x:%02x ", pci_domain_nr(pe->pbus), pe->pbus->number); +#ifdef CONFIG_PCI_IOV + else if (pe->flags & PNV_IODA_PE_VF) + sprintf(pfix, "%04x:%02x:%2x.%d", + pci_domain_nr(pe->parent_dev->bus), + (pe->rid & 0xff00) >> 8, + PCI_SLOT(pe->rid), PCI_FUNC(pe->rid)); +#endif /* CONFIG_PCI_IOV*/ printk("%spci %s: [PE# %.3d] %pV", level, pfix, pe->pe_number, &vaf); @@ -591,7 +601,7 @@ static int pnv_ioda_set_peltv(struct pnv_phb *phb, bool is_add) { struct pnv_ioda_pe *slave; - struct pci_dev *pdev; + struct pci_dev *pdev = NULL; int ret; /* @@ -630,8 +640,12 @@ static int pnv_ioda_set_peltv(struct pnv_phb *phb, if (pe->flags & (PNV_IODA_PE_BUS_ALL | PNV_IODA_PE_BUS)) pdev = pe->pbus->self; - else + else if (pe->flags & PNV_IODA_PE_DEV) pdev = pe->pdev->bus->self; +#ifdef CONFIG_PCI_IOV + else if (pe->flags & PNV_IODA_PE_VF) + pdev = pe->parent_dev->bus->self; +#endif /* CONFIG_PCI_IOV */ while (pdev) { struct pci_dn *pdn = pci_get_pdn(pdev); struct pnv_ioda_pe *parent; @@ -649,6 +663,87 @@ static int pnv_ioda_set_peltv(struct pnv_phb *phb, return 0; } +#ifdef CONFIG_PCI_IOV +static int pnv_ioda_deconfigure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe) +{ + struct pci_dev *parent; + uint8_t bcomp, dcomp, fcomp; + int64_t rc; + long rid_end, rid; + + /* Currently, we just deconfigure VF PE. Bus PE will always there.*/ + if (pe->pbus) { + int count; + + dcomp = OPAL_IGNORE_RID_DEVICE_NUMBER; + fcomp = OPAL_IGNORE_RID_FUNCTION_NUMBER; + parent = pe->pbus->self; + if (pe->flags & PNV_IODA_PE_BUS_ALL) + count = pe->pbus->busn_res.end - pe->pbus->busn_res.start + 1; + else + count = 1; + + switch(count) { + case 1: bcomp = OpalPciBusAll; break; + case 2: bcomp = OpalPciBus7Bits; break; + case 4: bcomp = OpalPciBus6Bits; break; + case 8: bcomp = OpalPciBus5Bits; break; + case 16: bcomp = OpalPciBus4Bits; break; + case 32: bcomp = OpalPciBus3Bits; break; + default: + dev_err(&pe->pbus->dev, "Number of subordinate buses %d unsupported\n", + count); + /* Do an exact match only */ + bcomp = OpalPciBusAll; + } + rid_end = pe->rid + (count << 8); + } else { + if (pe->flags & PNV_IODA_PE_VF) + parent = pe->parent_dev; + else + parent = pe->pdev->bus->self; + bcomp = OpalPciBusAll; + dcomp = OPAL_COMPARE_RID_DEVICE_NUMBER; + fcomp = OPAL_COMPARE_RID_FUNCTION_NUMBER; + rid_end = pe->rid + 1; + } + + /* Clear the reverse map */ + for (rid = pe->rid; rid < rid_end; rid++) + phb->ioda.pe_rmap[rid] = 0; + + /* Release from all parents PELT-V */ + while (parent) { + struct pci_dn *pdn = pci_get_pdn(parent); + if (pdn && pdn->pe_number != IODA_INVALID_PE) { + rc = opal_pci_set_peltv(phb->opal_id, pdn->pe_number, + pe->pe_number, OPAL_REMOVE_PE_FROM_DOMAIN); + /* XXX What to do in case of error ? */ + } + parent = parent->bus->self; + } + + opal_pci_eeh_freeze_set(phb->opal_id, pe->pe_number, + OPAL_EEH_ACTION_CLEAR_FREEZE_ALL); + + /* Disassociate PE in PELT */ + rc = opal_pci_set_peltv(phb->opal_id, pe->pe_number, + pe->pe_number, OPAL_REMOVE_PE_FROM_DOMAIN); + if (rc) + pe_warn(pe, "OPAL error %ld remove self from PELTV\n", rc); + rc = opal_pci_set_pe(phb->opal_id, pe->pe_number, pe->rid, + bcomp, dcomp, fcomp, OPAL_UNMAP_PE); + if (rc) + pe_err(pe, "OPAL error %ld trying to setup PELT table\n", rc); + + pe->pbus = NULL; + pe->pdev = NULL; + pe->parent_dev = NULL; + + return 0; +} +#endif /* CONFIG_PCI_IOV */ + static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe) { struct pci_dev *parent; @@ -675,15 +770,19 @@ static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe) case 16: bcomp = OpalPciBus4Bits; break; case 32: bcomp = OpalPciBus3Bits; break; default: - pr_err("%s: Number of subordinate busses %d" - " unsupported\n", - pci_name(pe->pbus->self), count); + dev_err(&pe->pbus->dev, "Number of subordinate buses %d unsupported\n", + count); /* Do an exact match only */ bcomp = OpalPciBusAll; } rid_end = pe->rid + (count << 8); } else { - parent = pe->pdev->bus->self; +#ifdef CONFIG_PCI_IOV + if (pe->flags & PNV_IODA_PE_VF) + parent = pe->parent_dev; + else +#endif /* CONFIG_PCI_IOV */ + parent = pe->pdev->bus->self; bcomp = OpalPciBusAll; dcomp = OPAL_COMPARE_RID_DEVICE_NUMBER; fcomp = OPAL_COMPARE_RID_FUNCTION_NUMBER; @@ -774,6 +873,78 @@ static unsigned int pnv_ioda_dma_weight(struct pci_dev *dev) return 10; } +#ifdef CONFIG_PCI_IOV +static int pnv_pci_vf_resource_shift(struct pci_dev *dev, int offset) +{ + struct pci_dn *pdn = pci_get_pdn(dev); + int i; + struct resource *res, res2; + resource_size_t size; + u16 num_vfs; + + if (!dev->is_physfn) + return -EINVAL; + + /* + * "offset" is in VFs. The M64 windows are sized so that when they + * are segmented, each segment is the same size as the IOV BAR. + * Each segment is in a separate PE, and the high order bits of the + * address are the PE number. Therefore, each VF's BAR is in a + * separate PE, and changing the IOV BAR start address changes the + * range of PEs the VFs are in. + */ + num_vfs = pdn->num_vfs; + for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { + res = &dev->resource[i + PCI_IOV_RESOURCES]; + if (!res->flags || !res->parent) + continue; + + if (!pnv_pci_is_mem_pref_64(res->flags)) + continue; + + /* + * The actual IOV BAR range is determined by the start address + * and the actual size for num_vfs VFs BAR. This check is to + * make sure that after shifting, the range will not overlap + * with another device. + */ + size = pci_iov_resource_size(dev, i + PCI_IOV_RESOURCES); + res2.flags = res->flags; + res2.start = res->start + (size * offset); + res2.end = res2.start + (size * num_vfs) - 1; + + if (res2.end > res->end) { + dev_err(&dev->dev, "VF BAR%d: %pR would extend past %pR (trying to enable %d VFs shifted by %d)\n", + i, &res2, res, num_vfs, offset); + return -EBUSY; + } + } + + /* + * After doing so, there would be a "hole" in the /proc/iomem when + * offset is a positive value. It looks like the device return some + * mmio back to the system, which actually no one could use it. + */ + for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { + res = &dev->resource[i + PCI_IOV_RESOURCES]; + if (!res->flags || !res->parent) + continue; + + if (!pnv_pci_is_mem_pref_64(res->flags)) + continue; + + size = pci_iov_resource_size(dev, i + PCI_IOV_RESOURCES); + res2 = *res; + res->start += size * offset; + + dev_info(&dev->dev, "VF BAR%d: %pR shifted to %pR (enabling %d VFs shifted by %d)\n", + i, &res2, res, num_vfs, offset); + pci_update_resource(dev, i + PCI_IOV_RESOURCES); + } + return 0; +} +#endif /* CONFIG_PCI_IOV */ + #if 0 static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev) { @@ -857,7 +1028,6 @@ static void pnv_ioda_setup_same_PE(struct pci_bus *bus, struct pnv_ioda_pe *pe) pci_name(dev)); continue; } - pdn->pcidev = dev; pdn->pe_number = pe->pe_number; pe->dma_weight += pnv_ioda_dma_weight(dev); if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate) @@ -916,6 +1086,10 @@ static void pnv_ioda_setup_bus_PE(struct pci_bus *bus, int all) return; } + pe->tce32_table = kzalloc_node(sizeof(struct iommu_table), + GFP_KERNEL, hose->node); + pe->tce32_table->data = pe; + /* Associate it with all child devices */ pnv_ioda_setup_same_PE(bus, pe); @@ -974,6 +1148,441 @@ static void pnv_pci_ioda_setup_PEs(void) } } +#ifdef CONFIG_PCI_IOV +static int pnv_pci_vf_release_m64(struct pci_dev *pdev) +{ + struct pci_bus *bus; + struct pci_controller *hose; + struct pnv_phb *phb; + struct pci_dn *pdn; + int i, j; + + bus = pdev->bus; + hose = pci_bus_to_host(bus); + phb = hose->private_data; + pdn = pci_get_pdn(pdev); + + for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) + for (j = 0; j < M64_PER_IOV; j++) { + if (pdn->m64_wins[i][j] == IODA_INVALID_M64) + continue; + opal_pci_phb_mmio_enable(phb->opal_id, + OPAL_M64_WINDOW_TYPE, pdn->m64_wins[i][j], 0); + clear_bit(pdn->m64_wins[i][j], &phb->ioda.m64_bar_alloc); + pdn->m64_wins[i][j] = IODA_INVALID_M64; + } + + return 0; +} + +static int pnv_pci_vf_assign_m64(struct pci_dev *pdev, u16 num_vfs) +{ + struct pci_bus *bus; + struct pci_controller *hose; + struct pnv_phb *phb; + struct pci_dn *pdn; + unsigned int win; + struct resource *res; + int i, j; + int64_t rc; + int total_vfs; + resource_size_t size, start; + int pe_num; + int vf_groups; + int vf_per_group; + + bus = pdev->bus; + hose = pci_bus_to_host(bus); + phb = hose->private_data; + pdn = pci_get_pdn(pdev); + total_vfs = pci_sriov_get_totalvfs(pdev); + + /* Initialize the m64_wins to IODA_INVALID_M64 */ + for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) + for (j = 0; j < M64_PER_IOV; j++) + pdn->m64_wins[i][j] = IODA_INVALID_M64; + + if (pdn->m64_per_iov == M64_PER_IOV) { + vf_groups = (num_vfs <= M64_PER_IOV) ? num_vfs: M64_PER_IOV; + vf_per_group = (num_vfs <= M64_PER_IOV)? 1: + roundup_pow_of_two(num_vfs) / pdn->m64_per_iov; + } else { + vf_groups = 1; + vf_per_group = 1; + } + + for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { + res = &pdev->resource[i + PCI_IOV_RESOURCES]; + if (!res->flags || !res->parent) + continue; + + if (!pnv_pci_is_mem_pref_64(res->flags)) + continue; + + for (j = 0; j < vf_groups; j++) { + do { + win = find_next_zero_bit(&phb->ioda.m64_bar_alloc, + phb->ioda.m64_bar_idx + 1, 0); + + if (win >= phb->ioda.m64_bar_idx + 1) + goto m64_failed; + } while (test_and_set_bit(win, &phb->ioda.m64_bar_alloc)); + + pdn->m64_wins[i][j] = win; + + if (pdn->m64_per_iov == M64_PER_IOV) { + size = pci_iov_resource_size(pdev, + PCI_IOV_RESOURCES + i); + size = size * vf_per_group; + start = res->start + size * j; + } else { + size = resource_size(res); + start = res->start; + } + + /* Map the M64 here */ + if (pdn->m64_per_iov == M64_PER_IOV) { + pe_num = pdn->offset + j; + rc = opal_pci_map_pe_mmio_window(phb->opal_id, + pe_num, OPAL_M64_WINDOW_TYPE, + pdn->m64_wins[i][j], 0); + } + + rc = opal_pci_set_phb_mem_window(phb->opal_id, + OPAL_M64_WINDOW_TYPE, + pdn->m64_wins[i][j], + start, + 0, /* unused */ + size); + + + if (rc != OPAL_SUCCESS) { + dev_err(&pdev->dev, "Failed to map M64 window #%d: %lld\n", + win, rc); + goto m64_failed; + } + + if (pdn->m64_per_iov == M64_PER_IOV) + rc = opal_pci_phb_mmio_enable(phb->opal_id, + OPAL_M64_WINDOW_TYPE, pdn->m64_wins[i][j], 2); + else + rc = opal_pci_phb_mmio_enable(phb->opal_id, + OPAL_M64_WINDOW_TYPE, pdn->m64_wins[i][j], 1); + + if (rc != OPAL_SUCCESS) { + dev_err(&pdev->dev, "Failed to enable M64 window #%d: %llx\n", + win, rc); + goto m64_failed; + } + } + } + return 0; + +m64_failed: + pnv_pci_vf_release_m64(pdev); + return -EBUSY; +} + +static void pnv_pci_ioda2_release_dma_pe(struct pci_dev *dev, struct pnv_ioda_pe *pe) +{ + struct pci_bus *bus; + struct pci_controller *hose; + struct pnv_phb *phb; + struct iommu_table *tbl; + unsigned long addr; + int64_t rc; + + bus = dev->bus; + hose = pci_bus_to_host(bus); + phb = hose->private_data; + tbl = pe->tce32_table; + addr = tbl->it_base; + + opal_pci_map_pe_dma_window(phb->opal_id, pe->pe_number, + pe->pe_number << 1, 1, __pa(addr), + 0, 0x1000); + + rc = opal_pci_map_pe_dma_window_real(pe->phb->opal_id, + pe->pe_number, + (pe->pe_number << 1) + 1, + pe->tce_bypass_base, + 0); + if (rc) + pe_warn(pe, "OPAL error %ld release DMA window\n", rc); + + iommu_free_table(tbl, of_node_full_name(dev->dev.of_node)); + free_pages(addr, get_order(TCE32_TABLE_SIZE)); + pe->tce32_table = NULL; +} + +static void pnv_ioda_release_vf_PE(struct pci_dev *pdev, u16 num_vfs) +{ + struct pci_bus *bus; + struct pci_controller *hose; + struct pnv_phb *phb; + struct pnv_ioda_pe *pe, *pe_n; + struct pci_dn *pdn; + u16 vf_index; + int64_t rc; + + bus = pdev->bus; + hose = pci_bus_to_host(bus); + phb = hose->private_data; + pdn = pci_get_pdn(pdev); + + if (!pdev->is_physfn) + return; + + if (pdn->m64_per_iov == M64_PER_IOV && num_vfs > M64_PER_IOV) { + int vf_group; + int vf_per_group; + int vf_index1; + + vf_per_group = roundup_pow_of_two(num_vfs) / pdn->m64_per_iov; + + for (vf_group = 0; vf_group < M64_PER_IOV; vf_group++) + for (vf_index = vf_group * vf_per_group; + vf_index < (vf_group + 1) * vf_per_group && + vf_index < num_vfs; + vf_index++) + for (vf_index1 = vf_group * vf_per_group; + vf_index1 < (vf_group + 1) * vf_per_group && + vf_index1 < num_vfs; + vf_index1++){ + + rc = opal_pci_set_peltv(phb->opal_id, + pdn->offset + vf_index, + pdn->offset + vf_index1, + OPAL_REMOVE_PE_FROM_DOMAIN); + + if (rc) + dev_warn(&pdev->dev, "%s: Failed to unlink same group PE#%d(%lld)\n", + __func__, + pdn->offset + vf_index1, rc); + } + } + + list_for_each_entry_safe(pe, pe_n, &phb->ioda.pe_list, list) { + if (pe->parent_dev != pdev) + continue; + + pnv_pci_ioda2_release_dma_pe(pdev, pe); + + /* Remove from list */ + mutex_lock(&phb->ioda.pe_list_mutex); + list_del(&pe->list); + mutex_unlock(&phb->ioda.pe_list_mutex); + + pnv_ioda_deconfigure_pe(phb, pe); + + pnv_ioda_free_pe(phb, pe->pe_number); + } +} + +void pnv_pci_sriov_disable(struct pci_dev *pdev) +{ + struct pci_bus *bus; + struct pci_controller *hose; + struct pnv_phb *phb; + struct pci_dn *pdn; + struct pci_sriov *iov; + u16 num_vfs; + + bus = pdev->bus; + hose = pci_bus_to_host(bus); + phb = hose->private_data; + pdn = pci_get_pdn(pdev); + iov = pdev->sriov; + num_vfs = pdn->num_vfs; + + /* Release VF PEs */ + pnv_ioda_release_vf_PE(pdev, num_vfs); + + if (phb->type == PNV_PHB_IODA2) { + if (pdn->m64_per_iov == 1) + pnv_pci_vf_resource_shift(pdev, -pdn->offset); + + /* Release M64 windows */ + pnv_pci_vf_release_m64(pdev); + + /* Release PE numbers */ + bitmap_clear(phb->ioda.pe_alloc, pdn->offset, num_vfs); + pdn->offset = 0; + } +} + +static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, + struct pnv_ioda_pe *pe); +static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs) +{ + struct pci_bus *bus; + struct pci_controller *hose; + struct pnv_phb *phb; + struct pnv_ioda_pe *pe; + int pe_num; + u16 vf_index; + struct pci_dn *pdn; + int64_t rc; + + bus = pdev->bus; + hose = pci_bus_to_host(bus); + phb = hose->private_data; + pdn = pci_get_pdn(pdev); + + if (!pdev->is_physfn) + return; + + /* Reserve PE for each VF */ + for (vf_index = 0; vf_index < num_vfs; vf_index++) { + pe_num = pdn->offset + vf_index; + + pe = &phb->ioda.pe_array[pe_num]; + pe->pe_number = pe_num; + pe->phb = phb; + pe->flags = PNV_IODA_PE_VF; + pe->pbus = NULL; + pe->parent_dev = pdev; + pe->tce32_seg = -1; + pe->mve_number = -1; + pe->rid = (pci_iov_virtfn_bus(pdev, vf_index) << 8) | + pci_iov_virtfn_devfn(pdev, vf_index); + + pe_info(pe, "VF %04d:%02d:%02d.%d associated with PE#%d\n", + hose->global_number, pdev->bus->number, + PCI_SLOT(pci_iov_virtfn_devfn(pdev, vf_index)), + PCI_FUNC(pci_iov_virtfn_devfn(pdev, vf_index)), pe_num); + + if (pnv_ioda_configure_pe(phb, pe)) { + /* XXX What do we do here ? */ + if (pe_num) + pnv_ioda_free_pe(phb, pe_num); + pe->pdev = NULL; + continue; + } + + pe->tce32_table = kzalloc_node(sizeof(struct iommu_table), + GFP_KERNEL, hose->node); + pe->tce32_table->data = pe; + + /* Put PE to the list */ + mutex_lock(&phb->ioda.pe_list_mutex); + list_add_tail(&pe->list, &phb->ioda.pe_list); + mutex_unlock(&phb->ioda.pe_list_mutex); + + pnv_pci_ioda2_setup_dma_pe(phb, pe); + } + + if (pdn->m64_per_iov == M64_PER_IOV && num_vfs > M64_PER_IOV) { + int vf_group; + int vf_per_group; + int vf_index1; + + vf_per_group = roundup_pow_of_two(num_vfs) / pdn->m64_per_iov; + + for (vf_group = 0; vf_group < M64_PER_IOV; vf_group++) { + for (vf_index = vf_group * vf_per_group; + vf_index < (vf_group + 1) * vf_per_group && + vf_index < num_vfs; + vf_index++) { + for (vf_index1 = vf_group * vf_per_group; + vf_index1 < (vf_group + 1) * vf_per_group && + vf_index1 < num_vfs; + vf_index1++) { + + rc = opal_pci_set_peltv(phb->opal_id, + pdn->offset + vf_index, + pdn->offset + vf_index1, + OPAL_ADD_PE_TO_DOMAIN); + + if (rc) + dev_warn(&pdev->dev, "%s: Failed to link same group PE#%d(%lld)\n", + __func__, + pdn->offset + vf_index1, rc); + } + } + } + } +} + +int pnv_pci_sriov_enable(struct pci_dev *pdev, u16 num_vfs) +{ + struct pci_bus *bus; + struct pci_controller *hose; + struct pnv_phb *phb; + struct pci_dn *pdn; + int ret; + + bus = pdev->bus; + hose = pci_bus_to_host(bus); + phb = hose->private_data; + pdn = pci_get_pdn(pdev); + + if (phb->type == PNV_PHB_IODA2) { + /* Calculate available PE for required VFs */ + mutex_lock(&phb->ioda.pe_alloc_mutex); + pdn->offset = bitmap_find_next_zero_area( + phb->ioda.pe_alloc, phb->ioda.total_pe, + 0, num_vfs, 0); + if (pdn->offset >= phb->ioda.total_pe) { + mutex_unlock(&phb->ioda.pe_alloc_mutex); + dev_info(&pdev->dev, "Failed to enable VF%d\n", num_vfs); + pdn->offset = 0; + return -EBUSY; + } + bitmap_set(phb->ioda.pe_alloc, pdn->offset, num_vfs); + pdn->num_vfs = num_vfs; + mutex_unlock(&phb->ioda.pe_alloc_mutex); + + /* Assign M64 window accordingly */ + ret = pnv_pci_vf_assign_m64(pdev, num_vfs); + if (ret) { + dev_info(&pdev->dev, "Not enough M64 window resources\n"); + goto m64_failed; + } + + /* + * When using one M64 BAR to map one IOV BAR, we need to shift + * the IOV BAR according to the PE# allocated to the VFs. + * Otherwise, the PE# for the VF will conflict with others. + */ + if (pdn->m64_per_iov == 1) { + ret = pnv_pci_vf_resource_shift(pdev, pdn->offset); + if (ret) + goto m64_failed; + } + } + + /* Setup VF PEs */ + pnv_ioda_setup_vf_PE(pdev, num_vfs); + + return 0; + +m64_failed: + bitmap_clear(phb->ioda.pe_alloc, pdn->offset, num_vfs); + pdn->offset = 0; + + return ret; +} + +int pcibios_sriov_disable(struct pci_dev *pdev) +{ + pnv_pci_sriov_disable(pdev); + + /* Release PCI data */ + remove_dev_pci_data(pdev); + return 0; +} + +int pcibios_sriov_enable(struct pci_dev *pdev, u16 num_vfs) +{ + /* Allocate PCI data */ + add_dev_pci_data(pdev); + + pnv_pci_sriov_enable(pdev, num_vfs); + return 0; +} +#endif /* CONFIG_PCI_IOV */ + static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev) { struct pci_dn *pdn = pci_get_pdn(pdev); @@ -989,7 +1598,7 @@ static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev pe = &phb->ioda.pe_array[pdn->pe_number]; WARN_ON(get_dma_ops(&pdev->dev) != &dma_iommu_ops); - set_iommu_table_base_and_group(&pdev->dev, &pe->tce32_table); + set_iommu_table_base_and_group(&pdev->dev, pe->tce32_table); } static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb, @@ -1016,7 +1625,7 @@ static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb, } else { dev_info(&pdev->dev, "Using 32-bit DMA via iommu\n"); set_dma_ops(&pdev->dev, &dma_iommu_ops); - set_iommu_table_base(&pdev->dev, &pe->tce32_table); + set_iommu_table_base(&pdev->dev, pe->tce32_table); } *pdev->dev.dma_mask = dma_mask; return 0; @@ -1053,9 +1662,9 @@ static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, list_for_each_entry(dev, &bus->devices, bus_list) { if (add_to_iommu_group) set_iommu_table_base_and_group(&dev->dev, - &pe->tce32_table); + pe->tce32_table); else - set_iommu_table_base(&dev->dev, &pe->tce32_table); + set_iommu_table_base(&dev->dev, pe->tce32_table); if (dev->subordinate) pnv_ioda_setup_bus_dma(pe, dev->subordinate, @@ -1145,8 +1754,7 @@ static void pnv_pci_ioda2_tce_invalidate(struct pnv_ioda_pe *pe, void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl, __be64 *startp, __be64 *endp, bool rm) { - struct pnv_ioda_pe *pe = container_of(tbl, struct pnv_ioda_pe, - tce32_table); + struct pnv_ioda_pe *pe = tbl->data; struct pnv_phb *phb = pe->phb; if (phb->type == PNV_PHB_IODA1) @@ -1167,9 +1775,6 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, int64_t rc; void *addr; - /* 256M DMA window, 4K TCE pages, 8 bytes TCE */ -#define TCE32_TABLE_SIZE ((0x10000000 / 0x1000) * 8) - /* XXX FIXME: Handle 64-bit only DMA devices */ /* XXX FIXME: Provide 64-bit DMA facilities & non-4K TCE tables etc.. */ /* XXX FIXME: Allocate multi-level tables on PHB3 */ @@ -1212,7 +1817,7 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, } /* Setup linux iommu table */ - tbl = &pe->tce32_table; + tbl = pe->tce32_table; pnv_pci_setup_iommu_table(tbl, addr, TCE32_TABLE_SIZE * segs, base << 28, IOMMU_PAGE_SHIFT_4K); @@ -1232,12 +1837,19 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, TCE_PCI_SWINV_PAIR); } iommu_init_table(tbl, phb->hose->node); - iommu_register_group(tbl, phb->hose->global_number, pe->pe_number); - if (pe->pdev) + if (pe->flags & PNV_IODA_PE_DEV) { + iommu_register_group(tbl, phb->hose->global_number, + pe->pe_number); set_iommu_table_base_and_group(&pe->pdev->dev, tbl); - else + } else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)) { + iommu_register_group(tbl, phb->hose->global_number, + pe->pe_number); pnv_ioda_setup_bus_dma(pe, pe->pbus, true); + } else if (pe->flags & PNV_IODA_PE_VF) { + iommu_register_group(tbl, phb->hose->global_number, + pe->pe_number); + } return; fail: @@ -1250,8 +1862,7 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, static void pnv_pci_ioda2_set_bypass(struct iommu_table *tbl, bool enable) { - struct pnv_ioda_pe *pe = container_of(tbl, struct pnv_ioda_pe, - tce32_table); + struct pnv_ioda_pe *pe = tbl->data; uint16_t window_id = (pe->pe_number << 1 ) + 1; int64_t rc; @@ -1296,10 +1907,10 @@ static void pnv_pci_ioda2_setup_bypass_pe(struct pnv_phb *phb, pe->tce_bypass_base = 1ull << 59; /* Install set_bypass callback for VFIO */ - pe->tce32_table.set_bypass = pnv_pci_ioda2_set_bypass; + pe->tce32_table->set_bypass = pnv_pci_ioda2_set_bypass; /* Enable bypass by default */ - pnv_pci_ioda2_set_bypass(&pe->tce32_table, true); + pnv_pci_ioda2_set_bypass(pe->tce32_table, true); } static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, @@ -1347,7 +1958,7 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, } /* Setup linux iommu table */ - tbl = &pe->tce32_table; + tbl = pe->tce32_table; pnv_pci_setup_iommu_table(tbl, addr, tce_table_size, 0, IOMMU_PAGE_SHIFT_4K); @@ -1365,12 +1976,19 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, tbl->it_type |= (TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE); } iommu_init_table(tbl, phb->hose->node); - iommu_register_group(tbl, phb->hose->global_number, pe->pe_number); - if (pe->pdev) + if (pe->flags & PNV_IODA_PE_DEV) { + iommu_register_group(tbl, phb->hose->global_number, + pe->pe_number); set_iommu_table_base_and_group(&pe->pdev->dev, tbl); - else + } else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)) { + iommu_register_group(tbl, phb->hose->global_number, + pe->pe_number); pnv_ioda_setup_bus_dma(pe, pe->pbus, true); + } else if (pe->flags & PNV_IODA_PE_VF) { + iommu_register_group(tbl, phb->hose->global_number, + pe->pe_number); + } /* Also create a bypass window */ if (!pnv_iommu_bypass_disabled) @@ -1731,6 +2349,73 @@ static void pnv_pci_init_ioda_msis(struct pnv_phb *phb) static void pnv_pci_init_ioda_msis(struct pnv_phb *phb) { } #endif /* CONFIG_PCI_MSI */ +#ifdef CONFIG_PCI_IOV +static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev) +{ + struct pci_controller *hose; + struct pnv_phb *phb; + struct resource *res; + int i; + resource_size_t size; + struct pci_dn *pdn; + int mul, total_vfs; + + if (!pdev->is_physfn || pdev->is_added) + return; + + hose = pci_bus_to_host(pdev->bus); + phb = hose->private_data; + + pdn = pci_get_pdn(pdev); + pdn->vfs_expanded = 0; + + total_vfs = pci_sriov_get_totalvfs(pdev); + pdn->m64_per_iov = 1; + mul = phb->ioda.total_pe; + + for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { + res = &pdev->resource[i + PCI_IOV_RESOURCES]; + if (!res->flags || res->parent) + continue; + if (!pnv_pci_is_mem_pref_64(res->flags)) { + dev_warn(&pdev->dev, " non M64 VF BAR%d: %pR\n", + i, res); + continue; + } + + size = pci_iov_resource_size(pdev, i + PCI_IOV_RESOURCES); + + /* bigger than 64M */ + if (size > (1 << 26)) { + dev_info(&pdev->dev, "PowerNV: VF BAR%d: %pR IOV size is bigger than 64M, roundup power2\n", + i, res); + pdn->m64_per_iov = M64_PER_IOV; + mul = roundup_pow_of_two(total_vfs); + break; + } + } + + for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { + res = &pdev->resource[i + PCI_IOV_RESOURCES]; + if (!res->flags || res->parent) + continue; + if (!pnv_pci_is_mem_pref_64(res->flags)) { + dev_warn(&pdev->dev, "Skipping expanding VF BAR%d: %pR\n", + i, res); + continue; + } + + dev_dbg(&pdev->dev, " Fixing VF BAR%d: %pR to\n", i, res); + size = pci_iov_resource_size(pdev, i + PCI_IOV_RESOURCES); + res->end = res->start + size * mul - 1; + dev_dbg(&pdev->dev, " %pR\n", res); + dev_info(&pdev->dev, "VF BAR%d: %pR (expanded to %d VFs for PE alignment)", + i, res, mul); + } + pdn->vfs_expanded = mul; +} +#endif /* CONFIG_PCI_IOV */ + /* * This function is supposed to be called on basis of PE from top * to bottom style. So the the I/O or MMIO segment assigned to @@ -1777,7 +2462,8 @@ static void pnv_ioda_setup_pe_seg(struct pci_controller *hose, region.start += phb->ioda.io_segsize; index++; } - } else if (res->flags & IORESOURCE_MEM) { + } else if ((res->flags & IORESOURCE_MEM) && + !pnv_pci_is_mem_pref_64(res->flags)) { region.start = res->start - hose->mem_offset[0] - phb->ioda.m32_pci_base; @@ -1907,10 +2593,29 @@ static resource_size_t pnv_pci_window_alignment(struct pci_bus *bus, return phb->ioda.io_segsize; } +#ifdef CONFIG_PCI_IOV +static resource_size_t pnv_pci_iov_resource_alignment(struct pci_dev *pdev, + int resno) +{ + struct pci_dn *pdn = pci_get_pdn(pdev); + resource_size_t align, iov_align; + + iov_align = resource_size(&pdev->resource[resno]); + if (iov_align) + return iov_align; + + align = pci_iov_resource_size(pdev, resno); + if (pdn->vfs_expanded) + return pdn->vfs_expanded * align; + + return align; +} +#endif /* CONFIG_PCI_IOV */ + /* Prevent enabling devices for which we couldn't properly * assign a PE */ -static int pnv_pci_enable_device_hook(struct pci_dev *dev) +static bool pnv_pci_enable_device_hook(struct pci_dev *dev) { struct pci_controller *hose = pci_bus_to_host(dev->bus); struct pnv_phb *phb = hose->private_data; @@ -1922,13 +2627,13 @@ static int pnv_pci_enable_device_hook(struct pci_dev *dev) * PEs isn't ready. */ if (!phb->initialized) - return 0; + return true; pdn = pci_get_pdn(dev); if (!pdn || pdn->pe_number == IODA_INVALID_PE) - return -EINVAL; + return false; - return 0; + return true; } static u32 pnv_ioda_bdfn_to_pe(struct pnv_phb *phb, struct pci_bus *bus, @@ -1988,9 +2693,11 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, hose->last_busno = 0xff; } hose->private_data = phb; + hose->controller_ops = pnv_pci_controller_ops; phb->hub_id = hub_id; phb->opal_id = phb_id; phb->type = ioda_type; + mutex_init(&phb->ioda.pe_alloc_mutex); /* Detect specific models for error handling */ if (of_device_is_compatible(np, "ibm,p7ioc-pciex")) @@ -2050,6 +2757,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, INIT_LIST_HEAD(&phb->ioda.pe_dma_list); INIT_LIST_HEAD(&phb->ioda.pe_list); + mutex_init(&phb->ioda.pe_list_mutex); /* Calculate how many 32-bit TCE segments we have */ phb->ioda.tce32_count = phb->ioda.m32_pci_base >> 28; @@ -2078,9 +2786,6 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, phb->get_pe_state = pnv_ioda_get_pe_state; phb->freeze_pe = pnv_ioda_freeze_pe; phb->unfreeze_pe = pnv_ioda_unfreeze_pe; -#ifdef CONFIG_EEH - phb->eeh_ops = &ioda_eeh_ops; -#endif /* Setup RID -> PE mapping function */ phb->bdfn_to_pe = pnv_ioda_bdfn_to_pe; @@ -2104,9 +2809,15 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, * the child P2P bridges) can form individual PE. */ ppc_md.pcibios_fixup = pnv_pci_ioda_fixup; - ppc_md.pcibios_enable_device_hook = pnv_pci_enable_device_hook; - ppc_md.pcibios_window_alignment = pnv_pci_window_alignment; - ppc_md.pcibios_reset_secondary_bus = pnv_pci_reset_secondary_bus; + pnv_pci_controller_ops.enable_device_hook = pnv_pci_enable_device_hook; + pnv_pci_controller_ops.window_alignment = pnv_pci_window_alignment; + pnv_pci_controller_ops.reset_secondary_bus = pnv_pci_reset_secondary_bus; + +#ifdef CONFIG_PCI_IOV + ppc_md.pcibios_fixup_sriov = pnv_pci_ioda_fixup_iov_resources; + ppc_md.pcibios_iov_resource_alignment = pnv_pci_iov_resource_alignment; +#endif + pci_add_flags(PCI_REASSIGN_ALL_RSRC); /* Reset IODA tables to a clean state */ @@ -2121,8 +2832,8 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, */ if (is_kdump_kernel()) { pr_info(" Issue PHB reset ...\n"); - ioda_eeh_phb_reset(hose, EEH_RESET_FUNDAMENTAL); - ioda_eeh_phb_reset(hose, EEH_RESET_DEACTIVATE); + pnv_eeh_phb_reset(hose, EEH_RESET_FUNDAMENTAL); + pnv_eeh_phb_reset(hose, EEH_RESET_DEACTIVATE); } /* Remove M64 resource if we can't configure it successfully */ diff --git a/arch/powerpc/platforms/powernv/pci-p5ioc2.c b/arch/powerpc/platforms/powernv/pci-p5ioc2.c index 6ef6d4d8e7e2..4729ca793813 100644 --- a/arch/powerpc/platforms/powernv/pci-p5ioc2.c +++ b/arch/powerpc/platforms/powernv/pci-p5ioc2.c @@ -133,6 +133,7 @@ static void __init pnv_pci_init_p5ioc2_phb(struct device_node *np, u64 hub_id, phb->hose->first_busno = 0; phb->hose->last_busno = 0xff; phb->hose->private_data = phb; + phb->hose->controller_ops = pnv_pci_controller_ops; phb->hub_id = hub_id; phb->opal_id = phb_id; phb->type = PNV_PHB_P5IOC2; diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index 54323d6b5166..bca2aeb6e4b6 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -366,9 +366,9 @@ static void pnv_pci_handle_eeh_config(struct pnv_phb *phb, u32 pe_no) spin_unlock_irqrestore(&phb->lock, flags); } -static void pnv_pci_config_check_eeh(struct pnv_phb *phb, - struct device_node *dn) +static void pnv_pci_config_check_eeh(struct pci_dn *pdn) { + struct pnv_phb *phb = pdn->phb->private_data; u8 fstate; __be16 pcierr; int pe_no; @@ -379,7 +379,7 @@ static void pnv_pci_config_check_eeh(struct pnv_phb *phb, * setup that yet. So all ER errors should be mapped to * reserved PE. */ - pe_no = PCI_DN(dn)->pe_number; + pe_no = pdn->pe_number; if (pe_no == IODA_INVALID_PE) { if (phb->type == PNV_PHB_P5IOC2) pe_no = 0; @@ -407,8 +407,7 @@ static void pnv_pci_config_check_eeh(struct pnv_phb *phb, } cfg_dbg(" -> EEH check, bdfn=%04x PE#%d fstate=%x\n", - (PCI_DN(dn)->busno << 8) | (PCI_DN(dn)->devfn), - pe_no, fstate); + (pdn->busno << 8) | (pdn->devfn), pe_no, fstate); /* Clear the frozen state if applicable */ if (fstate == OPAL_EEH_STOPPED_MMIO_FREEZE || @@ -425,10 +424,9 @@ static void pnv_pci_config_check_eeh(struct pnv_phb *phb, } } -int pnv_pci_cfg_read(struct device_node *dn, +int pnv_pci_cfg_read(struct pci_dn *pdn, int where, int size, u32 *val) { - struct pci_dn *pdn = PCI_DN(dn); struct pnv_phb *phb = pdn->phb->private_data; u32 bdfn = (pdn->busno << 8) | pdn->devfn; s64 rc; @@ -462,10 +460,9 @@ int pnv_pci_cfg_read(struct device_node *dn, return PCIBIOS_SUCCESSFUL; } -int pnv_pci_cfg_write(struct device_node *dn, +int pnv_pci_cfg_write(struct pci_dn *pdn, int where, int size, u32 val) { - struct pci_dn *pdn = PCI_DN(dn); struct pnv_phb *phb = pdn->phb->private_data; u32 bdfn = (pdn->busno << 8) | pdn->devfn; @@ -489,18 +486,17 @@ int pnv_pci_cfg_write(struct device_node *dn, } #if CONFIG_EEH -static bool pnv_pci_cfg_check(struct pci_controller *hose, - struct device_node *dn) +static bool pnv_pci_cfg_check(struct pci_dn *pdn) { struct eeh_dev *edev = NULL; - struct pnv_phb *phb = hose->private_data; + struct pnv_phb *phb = pdn->phb->private_data; /* EEH not enabled ? */ if (!(phb->flags & PNV_PHB_FLAG_EEH)) return true; /* PE reset or device removed ? */ - edev = of_node_to_eeh_dev(dn); + edev = pdn->edev; if (edev) { if (edev->pe && (edev->pe->state & EEH_PE_CFG_BLOCKED)) @@ -513,8 +509,7 @@ static bool pnv_pci_cfg_check(struct pci_controller *hose, return true; } #else -static inline pnv_pci_cfg_check(struct pci_controller *hose, - struct device_node *dn) +static inline pnv_pci_cfg_check(struct pci_dn *pdn) { return true; } @@ -524,32 +519,26 @@ static int pnv_pci_read_config(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 *val) { - struct device_node *dn, *busdn = pci_bus_to_OF_node(bus); struct pci_dn *pdn; struct pnv_phb *phb; - bool found = false; int ret; *val = 0xFFFFFFFF; - for (dn = busdn->child; dn; dn = dn->sibling) { - pdn = PCI_DN(dn); - if (pdn && pdn->devfn == devfn) { - phb = pdn->phb->private_data; - found = true; - break; - } - } + pdn = pci_get_pdn_by_devfn(bus, devfn); + if (!pdn) + return PCIBIOS_DEVICE_NOT_FOUND; - if (!found || !pnv_pci_cfg_check(pdn->phb, dn)) + if (!pnv_pci_cfg_check(pdn)) return PCIBIOS_DEVICE_NOT_FOUND; - ret = pnv_pci_cfg_read(dn, where, size, val); - if (phb->flags & PNV_PHB_FLAG_EEH) { + ret = pnv_pci_cfg_read(pdn, where, size, val); + phb = pdn->phb->private_data; + if (phb->flags & PNV_PHB_FLAG_EEH && pdn->edev) { if (*val == EEH_IO_ERROR_VALUE(size) && - eeh_dev_check_failure(of_node_to_eeh_dev(dn))) + eeh_dev_check_failure(pdn->edev)) return PCIBIOS_DEVICE_NOT_FOUND; } else { - pnv_pci_config_check_eeh(phb, dn); + pnv_pci_config_check_eeh(pdn); } return ret; @@ -559,27 +548,21 @@ static int pnv_pci_write_config(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 val) { - struct device_node *dn, *busdn = pci_bus_to_OF_node(bus); struct pci_dn *pdn; struct pnv_phb *phb; - bool found = false; int ret; - for (dn = busdn->child; dn; dn = dn->sibling) { - pdn = PCI_DN(dn); - if (pdn && pdn->devfn == devfn) { - phb = pdn->phb->private_data; - found = true; - break; - } - } + pdn = pci_get_pdn_by_devfn(bus, devfn); + if (!pdn) + return PCIBIOS_DEVICE_NOT_FOUND; - if (!found || !pnv_pci_cfg_check(pdn->phb, dn)) + if (!pnv_pci_cfg_check(pdn)) return PCIBIOS_DEVICE_NOT_FOUND; - ret = pnv_pci_cfg_write(dn, where, size, val); + ret = pnv_pci_cfg_write(pdn, where, size, val); + phb = pdn->phb->private_data; if (!(phb->flags & PNV_PHB_FLAG_EEH)) - pnv_pci_config_check_eeh(phb, dn); + pnv_pci_config_check_eeh(pdn); return ret; } @@ -679,66 +662,31 @@ void pnv_pci_setup_iommu_table(struct iommu_table *tbl, tbl->it_type = TCE_PCI; } -static struct iommu_table *pnv_pci_setup_bml_iommu(struct pci_controller *hose) -{ - struct iommu_table *tbl; - const __be64 *basep, *swinvp; - const __be32 *sizep; - - basep = of_get_property(hose->dn, "linux,tce-base", NULL); - sizep = of_get_property(hose->dn, "linux,tce-size", NULL); - if (basep == NULL || sizep == NULL) { - pr_err("PCI: %s has missing tce entries !\n", - hose->dn->full_name); - return NULL; - } - tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL, hose->node); - if (WARN_ON(!tbl)) - return NULL; - pnv_pci_setup_iommu_table(tbl, __va(be64_to_cpup(basep)), - be32_to_cpup(sizep), 0, IOMMU_PAGE_SHIFT_4K); - iommu_init_table(tbl, hose->node); - iommu_register_group(tbl, pci_domain_nr(hose->bus), 0); - - /* Deal with SW invalidated TCEs when needed (BML way) */ - swinvp = of_get_property(hose->dn, "linux,tce-sw-invalidate-info", - NULL); - if (swinvp) { - tbl->it_busno = be64_to_cpu(swinvp[1]); - tbl->it_index = (unsigned long)ioremap(be64_to_cpup(swinvp), 8); - tbl->it_type = TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE; - } - return tbl; -} - -static void pnv_pci_dma_fallback_setup(struct pci_controller *hose, - struct pci_dev *pdev) -{ - struct device_node *np = pci_bus_to_OF_node(hose->bus); - struct pci_dn *pdn; - - if (np == NULL) - return; - pdn = PCI_DN(np); - if (!pdn->iommu_table) - pdn->iommu_table = pnv_pci_setup_bml_iommu(hose); - if (!pdn->iommu_table) - return; - set_iommu_table_base_and_group(&pdev->dev, pdn->iommu_table); -} - static void pnv_pci_dma_dev_setup(struct pci_dev *pdev) { struct pci_controller *hose = pci_bus_to_host(pdev->bus); struct pnv_phb *phb = hose->private_data; +#ifdef CONFIG_PCI_IOV + struct pnv_ioda_pe *pe; + struct pci_dn *pdn; + + /* Fix the VF pdn PE number */ + if (pdev->is_virtfn) { + pdn = pci_get_pdn(pdev); + WARN_ON(pdn->pe_number != IODA_INVALID_PE); + list_for_each_entry(pe, &phb->ioda.pe_list, list) { + if (pe->rid == ((pdev->bus->number << 8) | + (pdev->devfn & 0xff))) { + pdn->pe_number = pe->pe_number; + pe->pdev = pdev; + break; + } + } + } +#endif /* CONFIG_PCI_IOV */ - /* If we have no phb structure, try to setup a fallback based on - * the device-tree (RTAS PCI for example) - */ if (phb && phb->dma_dev_setup) phb->dma_dev_setup(phb, pdev); - else - pnv_pci_dma_fallback_setup(hose, pdev); } int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask) @@ -784,44 +732,36 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_IBM, 0x3b9, pnv_p7ioc_rc_quirk); void __init pnv_pci_init(void) { struct device_node *np; + bool found_ioda = false; pci_add_flags(PCI_CAN_SKIP_ISA_ALIGN); - /* OPAL absent, try POPAL first then RTAS detection of PHBs */ - if (!firmware_has_feature(FW_FEATURE_OPAL)) { -#ifdef CONFIG_PPC_POWERNV_RTAS - init_pci_config_tokens(); - find_and_init_phbs(); -#endif /* CONFIG_PPC_POWERNV_RTAS */ - } - /* OPAL is here, do our normal stuff */ - else { - int found_ioda = 0; + /* If we don't have OPAL, eg. in sim, just skip PCI probe */ + if (!firmware_has_feature(FW_FEATURE_OPAL)) + return; - /* Look for IODA IO-Hubs. We don't support mixing IODA - * and p5ioc2 due to the need to change some global - * probing flags - */ - for_each_compatible_node(np, NULL, "ibm,ioda-hub") { - pnv_pci_init_ioda_hub(np); - found_ioda = 1; - } + /* Look for IODA IO-Hubs. We don't support mixing IODA + * and p5ioc2 due to the need to change some global + * probing flags + */ + for_each_compatible_node(np, NULL, "ibm,ioda-hub") { + pnv_pci_init_ioda_hub(np); + found_ioda = true; + } - /* Look for p5ioc2 IO-Hubs */ - if (!found_ioda) - for_each_compatible_node(np, NULL, "ibm,p5ioc2") - pnv_pci_init_p5ioc2_hub(np); + /* Look for p5ioc2 IO-Hubs */ + if (!found_ioda) + for_each_compatible_node(np, NULL, "ibm,p5ioc2") + pnv_pci_init_p5ioc2_hub(np); - /* Look for ioda2 built-in PHB3's */ - for_each_compatible_node(np, NULL, "ibm,ioda2-phb") - pnv_pci_init_ioda2_phb(np); - } + /* Look for ioda2 built-in PHB3's */ + for_each_compatible_node(np, NULL, "ibm,ioda2-phb") + pnv_pci_init_ioda2_phb(np); /* Setup the linkage between OF nodes and PHBs */ pci_devs_phb_init(); /* Configure IOMMU DMA hooks */ - ppc_md.pci_dma_dev_setup = pnv_pci_dma_dev_setup; ppc_md.tce_build = pnv_tce_build_vm; ppc_md.tce_free = pnv_tce_free_vm; ppc_md.tce_build_rm = pnv_tce_build_rm; @@ -837,3 +777,7 @@ void __init pnv_pci_init(void) } machine_subsys_initcall_sync(powernv, tce_iommu_bus_notifier_init); + +struct pci_controller_ops pnv_pci_controller_ops = { + .dma_dev_setup = pnv_pci_dma_dev_setup, +}; diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h index 6c02ff8dd69f..070ee888fc95 100644 --- a/arch/powerpc/platforms/powernv/pci.h +++ b/arch/powerpc/platforms/powernv/pci.h @@ -23,6 +23,7 @@ enum pnv_phb_model { #define PNV_IODA_PE_BUS_ALL (1 << 2) /* PE has subordinate buses */ #define PNV_IODA_PE_MASTER (1 << 3) /* Master PE in compound case */ #define PNV_IODA_PE_SLAVE (1 << 4) /* Slave PE in compound case */ +#define PNV_IODA_PE_VF (1 << 5) /* PE for one VF */ /* Data associated with a PE, including IOMMU tracking etc.. */ struct pnv_phb; @@ -34,6 +35,9 @@ struct pnv_ioda_pe { * entire bus (& children). In the former case, pdev * is populated, in the later case, pbus is. */ +#ifdef CONFIG_PCI_IOV + struct pci_dev *parent_dev; +#endif struct pci_dev *pdev; struct pci_bus *pbus; @@ -53,7 +57,7 @@ struct pnv_ioda_pe { /* "Base" iommu table, ie, 4K TCEs, 32-bit DMA */ int tce32_seg; int tce32_segcount; - struct iommu_table tce32_table; + struct iommu_table *tce32_table; phys_addr_t tce_inval_reg_phys; /* 64-bit TCE bypass region */ @@ -75,22 +79,6 @@ struct pnv_ioda_pe { struct list_head list; }; -/* IOC dependent EEH operations */ -#ifdef CONFIG_EEH -struct pnv_eeh_ops { - int (*post_init)(struct pci_controller *hose); - int (*set_option)(struct eeh_pe *pe, int option); - int (*get_state)(struct eeh_pe *pe); - int (*reset)(struct eeh_pe *pe, int option); - int (*get_log)(struct eeh_pe *pe, int severity, - char *drv_log, unsigned long len); - int (*configure_bridge)(struct eeh_pe *pe); - int (*err_inject)(struct eeh_pe *pe, int type, int func, - unsigned long addr, unsigned long mask); - int (*next_error)(struct eeh_pe **pe); -}; -#endif /* CONFIG_EEH */ - #define PNV_PHB_FLAG_EEH (1 << 0) struct pnv_phb { @@ -104,10 +92,6 @@ struct pnv_phb { int initialized; spinlock_t lock; -#ifdef CONFIG_EEH - struct pnv_eeh_ops *eeh_ops; -#endif - #ifdef CONFIG_DEBUG_FS int has_dbgfs; struct dentry *dbgfs; @@ -165,6 +149,8 @@ struct pnv_phb { /* PE allocation bitmap */ unsigned long *pe_alloc; + /* PE allocation mutex */ + struct mutex pe_alloc_mutex; /* M32 & IO segment maps */ unsigned int *m32_segmap; @@ -179,6 +165,7 @@ struct pnv_phb { * on the sequence of creation */ struct list_head pe_list; + struct mutex pe_list_mutex; /* Reverse map of PEs, will have to extend if * we are to support more than 256 PEs, indexed @@ -213,15 +200,12 @@ struct pnv_phb { }; extern struct pci_ops pnv_pci_ops; -#ifdef CONFIG_EEH -extern struct pnv_eeh_ops ioda_eeh_ops; -#endif void pnv_pci_dump_phb_diag_data(struct pci_controller *hose, unsigned char *log_buff); -int pnv_pci_cfg_read(struct device_node *dn, +int pnv_pci_cfg_read(struct pci_dn *pdn, int where, int size, u32 *val); -int pnv_pci_cfg_write(struct device_node *dn, +int pnv_pci_cfg_write(struct pci_dn *pdn, int where, int size, u32 val); extern void pnv_pci_setup_iommu_table(struct iommu_table *tbl, void *tce_mem, u64 tce_size, @@ -232,6 +216,6 @@ extern void pnv_pci_init_ioda2_phb(struct device_node *np); extern void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl, __be64 *startp, __be64 *endp, bool rm); extern void pnv_pci_reset_secondary_bus(struct pci_dev *dev); -extern int ioda_eeh_phb_reset(struct pci_controller *hose, int option); +extern int pnv_eeh_phb_reset(struct pci_controller *hose, int option); #endif /* __POWERNV_PCI_H */ diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h index 604c48e7879a..826d2c9bea56 100644 --- a/arch/powerpc/platforms/powernv/powernv.h +++ b/arch/powerpc/platforms/powernv/powernv.h @@ -29,6 +29,8 @@ static inline u64 pnv_pci_dma_get_required_mask(struct pci_dev *pdev) } #endif +extern struct pci_controller_ops pnv_pci_controller_ops; + extern u32 pnv_get_supported_cpuidle_states(void); extern void pnv_lpc_init(void); diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index d2de7d5d7574..16fdcb23f4c3 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -32,7 +32,6 @@ #include <asm/machdep.h> #include <asm/firmware.h> #include <asm/xics.h> -#include <asm/rtas.h> #include <asm/opal.h> #include <asm/kexec.h> #include <asm/smp.h> @@ -278,20 +277,6 @@ static void __init pnv_setup_machdep_opal(void) ppc_md.handle_hmi_exception = opal_handle_hmi_exception; } -#ifdef CONFIG_PPC_POWERNV_RTAS -static void __init pnv_setup_machdep_rtas(void) -{ - if (rtas_token("get-time-of-day") != RTAS_UNKNOWN_SERVICE) { - ppc_md.get_boot_time = rtas_get_boot_time; - ppc_md.get_rtc_time = rtas_get_rtc_time; - ppc_md.set_rtc_time = rtas_set_rtc_time; - } - ppc_md.restart = rtas_restart; - pm_power_off = rtas_power_off; - ppc_md.halt = rtas_halt; -} -#endif /* CONFIG_PPC_POWERNV_RTAS */ - static u32 supported_cpuidle_states; int pnv_save_sprs_for_winkle(void) @@ -409,37 +394,39 @@ static int __init pnv_init_idle_states(void) { struct device_node *power_mgt; int dt_idle_states; - const __be32 *idle_state_flags; - u32 len_flags, flags; + u32 *flags; int i; supported_cpuidle_states = 0; if (cpuidle_disable != IDLE_NO_OVERRIDE) - return 0; + goto out; if (!firmware_has_feature(FW_FEATURE_OPALv3)) - return 0; + goto out; power_mgt = of_find_node_by_path("/ibm,opal/power-mgt"); if (!power_mgt) { pr_warn("opal: PowerMgmt Node not found\n"); - return 0; + goto out; + } + dt_idle_states = of_property_count_u32_elems(power_mgt, + "ibm,cpu-idle-state-flags"); + if (dt_idle_states < 0) { + pr_warn("cpuidle-powernv: no idle states found in the DT\n"); + goto out; } - idle_state_flags = of_get_property(power_mgt, - "ibm,cpu-idle-state-flags", &len_flags); - if (!idle_state_flags) { - pr_warn("DT-PowerMgmt: missing ibm,cpu-idle-state-flags\n"); - return 0; + flags = kzalloc(sizeof(*flags) * dt_idle_states, GFP_KERNEL); + if (of_property_read_u32_array(power_mgt, + "ibm,cpu-idle-state-flags", flags, dt_idle_states)) { + pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-flags in DT\n"); + goto out_free; } - dt_idle_states = len_flags / sizeof(u32); + for (i = 0; i < dt_idle_states; i++) + supported_cpuidle_states |= flags[i]; - for (i = 0; i < dt_idle_states; i++) { - flags = be32_to_cpu(idle_state_flags[i]); - supported_cpuidle_states |= flags; - } if (!(supported_cpuidle_states & OPAL_PM_SLEEP_ENABLED_ER1)) { patch_instruction( (unsigned int *)pnv_fastsleep_workaround_at_entry, @@ -449,6 +436,9 @@ static int __init pnv_init_idle_states(void) PPC_INST_NOP); } pnv_alloc_idle_core_states(); +out_free: + kfree(flags); +out: return 0; } @@ -465,10 +455,6 @@ static int __init pnv_probe(void) if (firmware_has_feature(FW_FEATURE_OPAL)) pnv_setup_machdep_opal(); -#ifdef CONFIG_PPC_POWERNV_RTAS - else if (rtas.base) - pnv_setup_machdep_rtas(); -#endif /* CONFIG_PPC_POWERNV_RTAS */ pr_debug("PowerNV detected !\n"); diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index 38a45088f633..8f70ba681a78 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -25,7 +25,6 @@ #include <asm/machdep.h> #include <asm/cputable.h> #include <asm/firmware.h> -#include <asm/rtas.h> #include <asm/vdso_datapage.h> #include <asm/cputhreads.h> #include <asm/xics.h> @@ -251,18 +250,6 @@ void __init pnv_smp_init(void) { smp_ops = &pnv_smp_ops; - /* XXX We don't yet have a proper entry point from HAL, for - * now we rely on kexec-style entry from BML - */ - -#ifdef CONFIG_PPC_RTAS - /* Non-lpar has additional take/give timebase */ - if (rtas_token("freeze-time-base") != RTAS_UNKNOWN_SERVICE) { - smp_ops->give_timebase = rtas_give_timebase; - smp_ops->take_timebase = rtas_take_timebase; - } -#endif /* CONFIG_PPC_RTAS */ - #ifdef CONFIG_HOTPLUG_CPU ppc_md.cpu_die = pnv_smp_cpu_kill_self; #endif |