diff options
Diffstat (limited to 'arch/powerpc/platforms/powernv')
-rw-r--r-- | arch/powerpc/platforms/powernv/Kconfig | 6 | ||||
-rw-r--r-- | arch/powerpc/platforms/powernv/opal-wrappers.S | 1 | ||||
-rw-r--r-- | arch/powerpc/platforms/powernv/opal.c | 45 | ||||
-rw-r--r-- | arch/powerpc/platforms/powernv/pci-ioda.c | 351 | ||||
-rw-r--r-- | arch/powerpc/platforms/powernv/pci-p5ioc2.c | 15 | ||||
-rw-r--r-- | arch/powerpc/platforms/powernv/pci.c | 125 | ||||
-rw-r--r-- | arch/powerpc/platforms/powernv/pci.h | 26 | ||||
-rw-r--r-- | arch/powerpc/platforms/powernv/powernv.h | 2 | ||||
-rw-r--r-- | arch/powerpc/platforms/powernv/setup.c | 16 | ||||
-rw-r--r-- | arch/powerpc/platforms/powernv/smp.c | 66 |
10 files changed, 460 insertions, 193 deletions
diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig index 74fea5c..c24684c 100644 --- a/arch/powerpc/platforms/powernv/Kconfig +++ b/arch/powerpc/platforms/powernv/Kconfig @@ -6,6 +6,12 @@ config PPC_POWERNV select PPC_ICP_NATIVE select PPC_P7_NAP select PPC_PCI_CHOICE if EMBEDDED + select EPAPR_BOOT + default y + +config POWERNV_MSI + bool "Support PCI MSI on PowerNV platform" + depends on PCI_MSI default y config PPC_POWERNV_RTAS diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S index 3bb07e5..6fabe92 100644 --- a/arch/powerpc/platforms/powernv/opal-wrappers.S +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S @@ -107,3 +107,4 @@ OPAL_CALL(opal_pci_mask_pe_error, OPAL_PCI_MASK_PE_ERROR); OPAL_CALL(opal_set_slot_led_status, OPAL_SET_SLOT_LED_STATUS); OPAL_CALL(opal_get_epow_status, OPAL_GET_EPOW_STATUS); OPAL_CALL(opal_set_system_attention_led, OPAL_SET_SYSTEM_ATTENTION_LED); +OPAL_CALL(opal_pci_msi_eoi, OPAL_PCI_MSI_EOI); diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index aaa0dba..628c564 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -15,6 +15,7 @@ #include <linux/of.h> #include <linux/of_platform.h> #include <linux/interrupt.h> +#include <linux/slab.h> #include <asm/opal.h> #include <asm/firmware.h> @@ -28,13 +29,14 @@ struct opal { static struct device_node *opal_node; static DEFINE_SPINLOCK(opal_write_lock); extern u64 opal_mc_secondary_handler[]; +static unsigned int *opal_irqs; +static unsigned int opal_irq_count; int __init early_init_dt_scan_opal(unsigned long node, const char *uname, int depth, void *data) { const void *basep, *entryp; unsigned long basesz, entrysz; - u64 glue; if (depth != 1 || strcmp(uname, "ibm,opal") != 0) return 0; @@ -54,13 +56,27 @@ int __init early_init_dt_scan_opal(unsigned long node, opal.entry, entryp, entrysz); powerpc_firmware_features |= FW_FEATURE_OPAL; - if (of_flat_dt_is_compatible(node, "ibm,opal-v2")) { + if (of_flat_dt_is_compatible(node, "ibm,opal-v3")) { + powerpc_firmware_features |= FW_FEATURE_OPALv2; + powerpc_firmware_features |= FW_FEATURE_OPALv3; + printk("OPAL V3 detected !\n"); + } else if (of_flat_dt_is_compatible(node, "ibm,opal-v2")) { powerpc_firmware_features |= FW_FEATURE_OPALv2; printk("OPAL V2 detected !\n"); } else { printk("OPAL V1 detected !\n"); } + return 1; +} + +static int __init opal_register_exception_handlers(void) +{ + u64 glue; + + if (!(powerpc_firmware_features & FW_FEATURE_OPAL)) + return -ENODEV; + /* Hookup some exception handlers. We use the fwnmi area at 0x7000 * to provide the glue space to OPAL */ @@ -74,9 +90,11 @@ int __init early_init_dt_scan_opal(unsigned long node, glue += 128; opal_register_exception_handler(OPAL_SOFTPATCH_HANDLER, 0, glue); - return 1; + return 0; } +early_initcall(opal_register_exception_handlers); + int opal_get_chars(uint32_t vtermno, char *buf, int count) { s64 len, rc; @@ -133,6 +151,13 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len) rc == OPAL_BUSY_EVENT || rc == OPAL_SUCCESS)) { len = total_len; rc = opal_console_write(vtermno, &len, data); + + /* Closed or other error drop */ + if (rc != OPAL_SUCCESS && rc != OPAL_BUSY && + rc != OPAL_BUSY_EVENT) { + written = total_len; + break; + } if (rc == OPAL_SUCCESS) { total_len -= len; data += len; @@ -305,6 +330,8 @@ static int __init opal_init(void) irqs = of_get_property(opal_node, "opal-interrupts", &irqlen); pr_debug("opal: Found %d interrupts reserved for OPAL\n", irqs ? (irqlen / 4) : 0); + opal_irq_count = irqlen / 4; + opal_irqs = kzalloc(opal_irq_count * sizeof(unsigned int), GFP_KERNEL); for (i = 0; irqs && i < (irqlen / 4); i++, irqs++) { unsigned int hwirq = be32_to_cpup(irqs); unsigned int irq = irq_create_mapping(NULL, hwirq); @@ -316,7 +343,19 @@ static int __init opal_init(void) if (rc) pr_warning("opal: Error %d requesting irq %d" " (0x%x)\n", rc, irq, hwirq); + opal_irqs[i] = irq; } return 0; } subsys_initcall(opal_init); + +void opal_shutdown(void) +{ + unsigned int i; + + for (i = 0; i < opal_irq_count; i++) { + if (opal_irqs[i]) + free_irq(opal_irqs[i], 0); + opal_irqs[i] = 0; + } +} diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 8e90e89..9c9d15e 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -26,10 +26,12 @@ #include <asm/prom.h> #include <asm/pci-bridge.h> #include <asm/machdep.h> +#include <asm/msi_bitmap.h> #include <asm/ppc-pci.h> #include <asm/opal.h> #include <asm/iommu.h> #include <asm/tce.h> +#include <asm/xics.h> #include "powernv.h" #include "pci.h" @@ -66,16 +68,6 @@ define_pe_printk_level(pe_err, KERN_ERR); define_pe_printk_level(pe_warn, KERN_WARNING); define_pe_printk_level(pe_info, KERN_INFO); -static struct pci_dn *pnv_ioda_get_pdn(struct pci_dev *dev) -{ - struct device_node *np; - - np = pci_device_to_OF_node(dev); - if (!np) - return NULL; - return PCI_DN(np); -} - static int pnv_ioda_alloc_pe(struct pnv_phb *phb) { unsigned long pe; @@ -87,6 +79,7 @@ static int pnv_ioda_alloc_pe(struct pnv_phb *phb) return IODA_INVALID_PE; } while(test_and_set_bit(pe, phb->ioda.pe_alloc)); + phb->ioda.pe_array[pe].phb = phb; phb->ioda.pe_array[pe].pe_number = pe; return pe; } @@ -107,7 +100,7 @@ static struct pnv_ioda_pe *pnv_ioda_get_pe(struct pci_dev *dev) { struct pci_controller *hose = pci_bus_to_host(dev->bus); struct pnv_phb *phb = hose->private_data; - struct pci_dn *pdn = pnv_ioda_get_pdn(dev); + struct pci_dn *pdn = pci_get_pdn(dev); if (!pdn) return NULL; @@ -170,7 +163,7 @@ static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe) /* Add to all parents PELT-V */ while (parent) { - struct pci_dn *pdn = pnv_ioda_get_pdn(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_ADD_PE_TO_DOMAIN); @@ -249,7 +242,7 @@ static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev) { struct pci_controller *hose = pci_bus_to_host(dev->bus); struct pnv_phb *phb = hose->private_data; - struct pci_dn *pdn = pnv_ioda_get_pdn(dev); + struct pci_dn *pdn = pci_get_pdn(dev); struct pnv_ioda_pe *pe; int pe_num; @@ -320,7 +313,7 @@ static void pnv_ioda_setup_same_PE(struct pci_bus *bus, struct pnv_ioda_pe *pe) struct pci_dev *dev; list_for_each_entry(dev, &bus->devices, bus_list) { - struct pci_dn *pdn = pnv_ioda_get_pdn(dev); + struct pci_dn *pdn = pci_get_pdn(dev); if (pdn == NULL) { pr_warn("%s: No device node associated with device !\n", @@ -431,22 +424,102 @@ static void pnv_pci_ioda_setup_PEs(void) } } -static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *dev) +static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev) { - /* We delay DMA setup after we have assigned all PE# */ + struct pci_dn *pdn = pci_get_pdn(pdev); + struct pnv_ioda_pe *pe; + + /* + * The function can be called while the PE# + * hasn't been assigned. Do nothing for the + * case. + */ + if (!pdn || pdn->pe_number == IODA_INVALID_PE) + return; + + pe = &phb->ioda.pe_array[pdn->pe_number]; + set_iommu_table_base(&pdev->dev, &pe->tce32_table); } -static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus) +static void pnv_pci_ioda1_tce_invalidate(struct iommu_table *tbl, + u64 *startp, u64 *endp) { - struct pci_dev *dev; + u64 __iomem *invalidate = (u64 __iomem *)tbl->it_index; + unsigned long start, end, inc; + + start = __pa(startp); + end = __pa(endp); + + /* BML uses this case for p6/p7/galaxy2: Shift addr and put in node */ + if (tbl->it_busno) { + start <<= 12; + end <<= 12; + inc = 128 << 12; + start |= tbl->it_busno; + end |= tbl->it_busno; + } else if (tbl->it_type & TCE_PCI_SWINV_PAIR) { + /* p7ioc-style invalidation, 2 TCEs per write */ + start |= (1ull << 63); + end |= (1ull << 63); + inc = 16; + } else { + /* Default (older HW) */ + inc = 128; + } - list_for_each_entry(dev, &bus->devices, bus_list) { - set_iommu_table_base(&dev->dev, &pe->tce32_table); - if (dev->subordinate) - pnv_ioda_setup_bus_dma(pe, dev->subordinate); + end |= inc - 1; /* round up end to be different than start */ + + mb(); /* Ensure above stores are visible */ + while (start <= end) { + __raw_writeq(start, invalidate); + start += inc; + } + + /* + * The iommu layer will do another mb() for us on build() + * and we don't care on free() + */ +} + +static void pnv_pci_ioda2_tce_invalidate(struct pnv_ioda_pe *pe, + struct iommu_table *tbl, + u64 *startp, u64 *endp) +{ + unsigned long start, end, inc; + u64 __iomem *invalidate = (u64 __iomem *)tbl->it_index; + + /* We'll invalidate DMA address in PE scope */ + start = 0x2ul << 60; + start |= (pe->pe_number & 0xFF); + end = start; + + /* Figure out the start, end and step */ + inc = tbl->it_offset + (((u64)startp - tbl->it_base) / sizeof(u64)); + start |= (inc << 12); + inc = tbl->it_offset + (((u64)endp - tbl->it_base) / sizeof(u64)); + end |= (inc << 12); + inc = (0x1ul << 12); + mb(); + + while (start <= end) { + __raw_writeq(start, invalidate); + start += inc; } } +void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl, + u64 *startp, u64 *endp) +{ + struct pnv_ioda_pe *pe = container_of(tbl, struct pnv_ioda_pe, + tce32_table); + struct pnv_phb *phb = pe->phb; + + if (phb->type == PNV_PHB_IODA1) + pnv_pci_ioda1_tce_invalidate(tbl, startp, endp); + else + pnv_pci_ioda2_tce_invalidate(pe, tbl, startp, endp); +} + static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe, unsigned int base, unsigned int segs) @@ -518,16 +591,11 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, */ tbl->it_busno = 0; tbl->it_index = (unsigned long)ioremap(be64_to_cpup(swinvp), 8); - tbl->it_type = TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE - | TCE_PCI_SWINV_PAIR; + tbl->it_type = TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE | + TCE_PCI_SWINV_PAIR; } iommu_init_table(tbl, phb->hose->node); - if (pe->pdev) - set_iommu_table_base(&pe->pdev->dev, tbl); - else - pnv_ioda_setup_bus_dma(pe, pe->pbus); - return; fail: /* XXX Failure: Try to fallback to 64-bit only ? */ @@ -537,6 +605,76 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, __free_pages(tce_mem, get_order(TCE32_TABLE_SIZE * segs)); } +static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, + struct pnv_ioda_pe *pe) +{ + struct page *tce_mem = NULL; + void *addr; + const __be64 *swinvp; + struct iommu_table *tbl; + unsigned int tce_table_size, end; + int64_t rc; + + /* We shouldn't already have a 32-bit DMA associated */ + if (WARN_ON(pe->tce32_seg >= 0)) + return; + + /* The PE will reserve all possible 32-bits space */ + pe->tce32_seg = 0; + end = (1 << ilog2(phb->ioda.m32_pci_base)); + tce_table_size = (end / 0x1000) * 8; + pe_info(pe, "Setting up 32-bit TCE table at 0..%08x\n", + end); + + /* Allocate TCE table */ + tce_mem = alloc_pages_node(phb->hose->node, GFP_KERNEL, + get_order(tce_table_size)); + if (!tce_mem) { + pe_err(pe, "Failed to allocate a 32-bit TCE memory\n"); + goto fail; + } + addr = page_address(tce_mem); + memset(addr, 0, tce_table_size); + + /* + * Map TCE table through TVT. The TVE index is the PE number + * shifted by 1 bit for 32-bits DMA space. + */ + rc = opal_pci_map_pe_dma_window(phb->opal_id, pe->pe_number, + pe->pe_number << 1, 1, __pa(addr), + tce_table_size, 0x1000); + if (rc) { + pe_err(pe, "Failed to configure 32-bit TCE table," + " err %ld\n", rc); + goto fail; + } + + /* Setup linux iommu table */ + tbl = &pe->tce32_table; + pnv_pci_setup_iommu_table(tbl, addr, tce_table_size, 0); + + /* OPAL variant of PHB3 invalidated TCEs */ + swinvp = of_get_property(phb->hose->dn, "ibm,opal-tce-kill", NULL); + if (swinvp) { + /* We need a couple more fields -- an address and a data + * to or. Since the bus is only printed out on table free + * errors, and on the first pass the data will be a relative + * bus number, print that out instead. + */ + tbl->it_busno = 0; + tbl->it_index = (unsigned long)ioremap(be64_to_cpup(swinvp), 8); + tbl->it_type = TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE; + } + iommu_init_table(tbl, phb->hose->node); + + return; +fail: + if (pe->tce32_seg >= 0) + pe->tce32_seg = -1; + if (tce_mem) + __free_pages(tce_mem, get_order(tce_table_size)); +} + static void pnv_ioda_setup_dma(struct pnv_phb *phb) { struct pci_controller *hose = phb->hose; @@ -579,20 +717,50 @@ static void pnv_ioda_setup_dma(struct pnv_phb *phb) if (segs > remaining) segs = remaining; } - pe_info(pe, "DMA weight %d, assigned %d DMA32 segments\n", - pe->dma_weight, segs); - pnv_pci_ioda_setup_dma_pe(phb, pe, base, segs); + + /* + * For IODA2 compliant PHB3, we needn't care about the weight. + * The all available 32-bits DMA space will be assigned to + * the specific PE. + */ + if (phb->type == PNV_PHB_IODA1) { + pe_info(pe, "DMA weight %d, assigned %d DMA32 segments\n", + pe->dma_weight, segs); + pnv_pci_ioda_setup_dma_pe(phb, pe, base, segs); + } else { + pe_info(pe, "Assign DMA32 space\n"); + segs = 0; + pnv_pci_ioda2_setup_dma_pe(phb, pe); + } + remaining -= segs; base += segs; } } #ifdef CONFIG_PCI_MSI +static void pnv_ioda2_msi_eoi(struct irq_data *d) +{ + unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d); + struct irq_chip *chip = irq_data_get_irq_chip(d); + struct pnv_phb *phb = container_of(chip, struct pnv_phb, + ioda.irq_chip); + int64_t rc; + + rc = opal_pci_msi_eoi(phb->opal_id, hw_irq); + WARN_ON_ONCE(rc); + + icp_native_eoi(d); +} + static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev, - unsigned int hwirq, unsigned int is_64, - struct msi_msg *msg) + unsigned int hwirq, unsigned int virq, + unsigned int is_64, struct msi_msg *msg) { struct pnv_ioda_pe *pe = pnv_ioda_get_pe(dev); + struct pci_dn *pdn = pci_get_pdn(dev); + struct irq_data *idata; + struct irq_chip *ichip; unsigned int xive_num = hwirq - phb->msi_base; uint64_t addr64; uint32_t addr32, data; @@ -606,6 +774,10 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev, if (pe->mve_number < 0) return -ENXIO; + /* Force 32-bit MSI on some broken devices */ + if (pdn && pdn->force_32bit_msi) + is_64 = 0; + /* Assign XIVE to PE */ rc = opal_pci_set_xive_pe(phb->opal_id, pe->pe_number, xive_num); if (rc) { @@ -637,6 +809,23 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev, } msg->data = data; + /* + * Change the IRQ chip for the MSI interrupts on PHB3. + * The corresponding IRQ chip should be populated for + * the first time. + */ + if (phb->type == PNV_PHB_IODA2) { + if (!phb->ioda.irq_chip_init) { + idata = irq_get_irq_data(virq); + ichip = irq_data_get_irq_chip(idata); + phb->ioda.irq_chip_init = 1; + phb->ioda.irq_chip = *ichip; + phb->ioda.irq_chip.irq_eoi = pnv_ioda2_msi_eoi; + } + + irq_set_chip(virq, &phb->ioda.irq_chip); + } + pr_devel("%s: %s-bit MSI on hwirq %x (xive #%d)," " address=%x_%08x data=%x PE# %d\n", pci_name(dev), is_64 ? "64" : "32", hwirq, xive_num, @@ -647,7 +836,7 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev, static void pnv_pci_init_ioda_msis(struct pnv_phb *phb) { - unsigned int bmap_size; + unsigned int count; const __be32 *prop = of_get_property(phb->hose->dn, "ibm,opal-msi-ranges", NULL); if (!prop) { @@ -658,18 +847,17 @@ static void pnv_pci_init_ioda_msis(struct pnv_phb *phb) return; phb->msi_base = be32_to_cpup(prop); - phb->msi_count = be32_to_cpup(prop + 1); - bmap_size = BITS_TO_LONGS(phb->msi_count) * sizeof(unsigned long); - phb->msi_map = zalloc_maybe_bootmem(bmap_size, GFP_KERNEL); - if (!phb->msi_map) { + count = be32_to_cpup(prop + 1); + if (msi_bitmap_alloc(&phb->msi_bmp, count, phb->hose->dn)) { pr_err("PCI %d: Failed to allocate MSI bitmap !\n", phb->hose->global_number); return; } + phb->msi_setup = pnv_pci_ioda_msi_setup; phb->msi32_support = 1; pr_info(" Allocated bitmap for %d MSIs (base IRQ 0x%x)\n", - phb->msi_count, phb->msi_base); + count, phb->msi_base); } #else static void pnv_pci_init_ioda_msis(struct pnv_phb *phb) { } @@ -722,11 +910,14 @@ static void pnv_ioda_setup_pe_seg(struct pci_controller *hose, index++; } } else if (res->flags & IORESOURCE_MEM) { + /* WARNING: Assumes M32 is mem region 0 in PHB. We need to + * harden that algorithm when we start supporting M64 + */ region.start = res->start - - hose->pci_mem_offset - + hose->mem_offset[0] - phb->ioda.m32_pci_base; region.end = res->end - - hose->pci_mem_offset - + hose->mem_offset[0] - phb->ioda.m32_pci_base; index = region.start / phb->ioda.m32_segsize; @@ -839,7 +1030,7 @@ static int pnv_pci_enable_device_hook(struct pci_dev *dev) if (!phb->initialized) return 0; - pdn = pnv_ioda_get_pdn(dev); + pdn = pci_get_pdn(dev); if (!pdn || pdn->pe_number == IODA_INVALID_PE) return -EINVAL; @@ -852,18 +1043,25 @@ static u32 pnv_ioda_bdfn_to_pe(struct pnv_phb *phb, struct pci_bus *bus, return phb->ioda.pe_rmap[(bus->number << 8) | devfn]; } -void __init pnv_pci_init_ioda1_phb(struct device_node *np) +static void pnv_pci_ioda_shutdown(struct pnv_phb *phb) +{ + opal_pci_reset(phb->opal_id, OPAL_PCI_IODA_TABLE_RESET, + OPAL_ASSERT_RESET); +} + +void __init pnv_pci_init_ioda_phb(struct device_node *np, int ioda_type) { struct pci_controller *hose; static int primary = 1; struct pnv_phb *phb; unsigned long size, m32map_off, iomap_off, pemap_off; const u64 *prop64; + const u32 *prop32; u64 phb_id; void *aux; long rc; - pr_info(" Initializing IODA OPAL PHB %s\n", np->full_name); + pr_info(" Initializing IODA%d OPAL PHB %s\n", ioda_type, np->full_name); prop64 = of_get_property(np, "ibm,opal-phbid", NULL); if (!prop64) { @@ -890,47 +1088,46 @@ void __init pnv_pci_init_ioda1_phb(struct device_node *np) hose->last_busno = 0xff; hose->private_data = phb; phb->opal_id = phb_id; - phb->type = PNV_PHB_IODA1; + phb->type = ioda_type; /* Detect specific models for error handling */ if (of_device_is_compatible(np, "ibm,p7ioc-pciex")) phb->model = PNV_PHB_MODEL_P7IOC; + else if (of_device_is_compatible(np, "ibm,power8-pciex")) + phb->model = PNV_PHB_MODEL_PHB3; else phb->model = PNV_PHB_MODEL_UNKNOWN; - /* We parse "ranges" now since we need to deduce the register base - * from the IO base - */ + /* Parse 32-bit and IO ranges (if any) */ pci_process_bridge_OF_ranges(phb->hose, np, primary); primary = 0; - /* Magic formula from Milton */ + /* Get registers */ phb->regs = of_iomap(np, 0); if (phb->regs == NULL) pr_err(" Failed to map registers !\n"); - - /* XXX This is hack-a-thon. This needs to be changed so that: - * - we obtain stuff like PE# etc... from device-tree - * - we properly re-allocate M32 ourselves - * (the OFW one isn't very good) - */ - /* Initialize more IODA stuff */ - phb->ioda.total_pe = 128; + prop32 = of_get_property(np, "ibm,opal-num-pes", NULL); + if (!prop32) + phb->ioda.total_pe = 1; + else + phb->ioda.total_pe = *prop32; phb->ioda.m32_size = resource_size(&hose->mem_resources[0]); - /* OFW Has already off top 64k of M32 space (MSI space) */ + /* FW Has already off top 64k of M32 space (MSI space) */ phb->ioda.m32_size += 0x10000; phb->ioda.m32_segsize = phb->ioda.m32_size / phb->ioda.total_pe; - phb->ioda.m32_pci_base = hose->mem_resources[0].start - - hose->pci_mem_offset; + phb->ioda.m32_pci_base = hose->mem_resources[0].start - hose->mem_offset[0]; phb->ioda.io_size = hose->pci_io_size; phb->ioda.io_segsize = phb->ioda.io_size / phb->ioda.total_pe; phb->ioda.io_pci_base = 0; /* XXX calculate this ? */ - /* Allocate aux data & arrays */ + /* Allocate aux data & arrays + * + * XXX TODO: Don't allocate io segmap on PHB3 + */ size = _ALIGN_UP(phb->ioda.total_pe / 8, sizeof(unsigned long)); m32map_off = size; size += phb->ioda.total_pe * sizeof(phb->ioda.m32_segmap[0]); @@ -960,7 +1157,7 @@ void __init pnv_pci_init_ioda1_phb(struct device_node *np) hose->mem_resources[2].start = 0; hose->mem_resources[2].end = 0; -#if 0 +#if 0 /* We should really do that ... */ rc = opal_pci_set_phb_mem_window(opal->phb_id, window_type, window_num, @@ -974,16 +1171,6 @@ void __init pnv_pci_init_ioda1_phb(struct device_node *np) phb->ioda.m32_size, phb->ioda.m32_segsize, phb->ioda.io_size, phb->ioda.io_segsize); - if (phb->regs) { - pr_devel(" BUID = 0x%016llx\n", in_be64(phb->regs + 0x100)); - pr_devel(" PHB2_CR = 0x%016llx\n", in_be64(phb->regs + 0x160)); - pr_devel(" IO_BAR = 0x%016llx\n", in_be64(phb->regs + 0x170)); - pr_devel(" IO_BAMR = 0x%016llx\n", in_be64(phb->regs + 0x178)); - pr_devel(" IO_SAR = 0x%016llx\n", in_be64(phb->regs + 0x180)); - pr_devel(" M32_BAR = 0x%016llx\n", in_be64(phb->regs + 0x190)); - pr_devel(" M32_BAMR = 0x%016llx\n", in_be64(phb->regs + 0x198)); - pr_devel(" M32_SAR = 0x%016llx\n", in_be64(phb->regs + 0x1a0)); - } phb->hose->ops = &pnv_pci_ops; /* Setup RID -> PE mapping function */ @@ -992,6 +1179,9 @@ void __init pnv_pci_init_ioda1_phb(struct device_node *np) /* Setup TCEs */ phb->dma_dev_setup = pnv_pci_ioda_dma_dev_setup; + /* Setup shutdown function for kexec */ + phb->shutdown = pnv_pci_ioda_shutdown; + /* Setup MSI support */ pnv_pci_init_ioda_msis(phb); @@ -1011,7 +1201,18 @@ void __init pnv_pci_init_ioda1_phb(struct device_node *np) rc = opal_pci_reset(phb_id, OPAL_PCI_IODA_TABLE_RESET, OPAL_ASSERT_RESET); if (rc) pr_warning(" OPAL Error %ld performing IODA table reset !\n", rc); - opal_pci_set_pe(phb_id, 0, 0, 7, 1, 1 , OPAL_MAP_PE); + + /* + * On IODA1 map everything to PE#0, on IODA2 we assume the IODA reset + * has cleared the RTT which has the same effect + */ + if (ioda_type == PNV_PHB_IODA1) + opal_pci_set_pe(phb_id, 0, 0, 7, 1, 1 , OPAL_MAP_PE); +} + +void pnv_pci_init_ioda2_phb(struct device_node *np) +{ + pnv_pci_init_ioda_phb(np, PNV_PHB_IODA2); } void __init pnv_pci_init_ioda_hub(struct device_node *np) @@ -1034,6 +1235,6 @@ void __init pnv_pci_init_ioda_hub(struct device_node *np) for_each_child_of_node(np, phbn) { /* Look for IODA1 PHBs */ if (of_device_is_compatible(phbn, "ibm,ioda-phb")) - pnv_pci_init_ioda1_phb(phbn); + pnv_pci_init_ioda_phb(phbn, PNV_PHB_IODA1); } } diff --git a/arch/powerpc/platforms/powernv/pci-p5ioc2.c b/arch/powerpc/platforms/powernv/pci-p5ioc2.c index 7db8771..92b37a0 100644 --- a/arch/powerpc/platforms/powernv/pci-p5ioc2.c +++ b/arch/powerpc/platforms/powernv/pci-p5ioc2.c @@ -26,6 +26,7 @@ #include <asm/prom.h> #include <asm/pci-bridge.h> #include <asm/machdep.h> +#include <asm/msi_bitmap.h> #include <asm/ppc-pci.h> #include <asm/opal.h> #include <asm/iommu.h> @@ -41,8 +42,8 @@ #ifdef CONFIG_PCI_MSI static int pnv_pci_p5ioc2_msi_setup(struct pnv_phb *phb, struct pci_dev *dev, - unsigned int hwirq, unsigned int is_64, - struct msi_msg *msg) + unsigned int hwirq, unsigned int virq, + unsigned int is_64, struct msi_msg *msg) { if (WARN_ON(!is_64)) return -ENXIO; @@ -55,7 +56,7 @@ static int pnv_pci_p5ioc2_msi_setup(struct pnv_phb *phb, struct pci_dev *dev, static void pnv_pci_init_p5ioc2_msis(struct pnv_phb *phb) { - unsigned int bmap_size; + unsigned int count; const __be32 *prop = of_get_property(phb->hose->dn, "ibm,opal-msi-ranges", NULL); if (!prop) @@ -67,10 +68,8 @@ static void pnv_pci_init_p5ioc2_msis(struct pnv_phb *phb) if (of_device_is_compatible(phb->hose->dn, "ibm,p5ioc2-pcix")) return; phb->msi_base = be32_to_cpup(prop); - phb->msi_count = be32_to_cpup(prop + 1); - bmap_size = BITS_TO_LONGS(phb->msi_count) * sizeof(unsigned long); - phb->msi_map = zalloc_maybe_bootmem(bmap_size, GFP_KERNEL); - if (!phb->msi_map) { + count = be32_to_cpup(prop + 1); + if (msi_bitmap_alloc(&phb->msi_bmp, count, phb->hose->dn)) { pr_err("PCI %d: Failed to allocate MSI bitmap !\n", phb->hose->global_number); return; @@ -78,7 +77,7 @@ static void pnv_pci_init_p5ioc2_msis(struct pnv_phb *phb) phb->msi_setup = pnv_pci_p5ioc2_msi_setup; phb->msi32_support = 0; pr_info(" Allocated bitmap for %d MSIs (base IRQ 0x%x)\n", - phb->msi_count, phb->msi_base); + count, phb->msi_base); } #else static void pnv_pci_init_p5ioc2_msis(struct pnv_phb *phb) { } diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index b8b8e0b..277343c 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -26,6 +26,7 @@ #include <asm/prom.h> #include <asm/pci-bridge.h> #include <asm/machdep.h> +#include <asm/msi_bitmap.h> #include <asm/ppc-pci.h> #include <asm/opal.h> #include <asm/iommu.h> @@ -46,44 +47,12 @@ static int pnv_msi_check_device(struct pci_dev* pdev, int nvec, int type) { struct pci_controller *hose = pci_bus_to_host(pdev->bus); struct pnv_phb *phb = hose->private_data; + struct pci_dn *pdn = pci_get_pdn(pdev); - return (phb && phb->msi_map) ? 0 : -ENODEV; -} - -static unsigned int pnv_get_one_msi(struct pnv_phb *phb) -{ - unsigned long flags; - unsigned int id, rc; - - spin_lock_irqsave(&phb->lock, flags); - - id = find_next_zero_bit(phb->msi_map, phb->msi_count, phb->msi_next); - if (id >= phb->msi_count && phb->msi_next) - id = find_next_zero_bit(phb->msi_map, phb->msi_count, 0); - if (id >= phb->msi_count) { - rc = 0; - goto out; - } - __set_bit(id, phb->msi_map); - rc = id + phb->msi_base; -out: - spin_unlock_irqrestore(&phb->lock, flags); - return rc; -} - -static void pnv_put_msi(struct pnv_phb *phb, unsigned int hwirq) -{ - unsigned long flags; - unsigned int id; - - if (WARN_ON(hwirq < phb->msi_base || - hwirq >= (phb->msi_base + phb->msi_count))) - return; - id = hwirq - phb->msi_base; + if (pdn && pdn->force_32bit_msi && !phb->msi32_support) + return -ENODEV; - spin_lock_irqsave(&phb->lock, flags); - __clear_bit(id, phb->msi_map); - spin_unlock_irqrestore(&phb->lock, flags); + return (phb && phb->msi_bmp.bitmap) ? 0 : -ENODEV; } static int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) @@ -92,7 +61,8 @@ static int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) struct pnv_phb *phb = hose->private_data; struct msi_desc *entry; struct msi_msg msg; - unsigned int hwirq, virq; + int hwirq; + unsigned int virq; int rc; if (WARN_ON(!phb)) @@ -104,25 +74,25 @@ static int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) pci_name(pdev)); return -ENXIO; } - hwirq = pnv_get_one_msi(phb); - if (!hwirq) { + hwirq = msi_bitmap_alloc_hwirqs(&phb->msi_bmp, 1); + if (hwirq < 0) { pr_warn("%s: Failed to find a free MSI\n", pci_name(pdev)); return -ENOSPC; } - virq = irq_create_mapping(NULL, hwirq); + virq = irq_create_mapping(NULL, phb->msi_base + hwirq); if (virq == NO_IRQ) { pr_warn("%s: Failed to map MSI to linux irq\n", pci_name(pdev)); - pnv_put_msi(phb, hwirq); + msi_bitmap_free_hwirqs(&phb->msi_bmp, hwirq, 1); return -ENOMEM; } - rc = phb->msi_setup(phb, pdev, hwirq, entry->msi_attrib.is_64, - &msg); + rc = phb->msi_setup(phb, pdev, phb->msi_base + hwirq, + virq, entry->msi_attrib.is_64, &msg); if (rc) { pr_warn("%s: Failed to setup MSI\n", pci_name(pdev)); irq_dispose_mapping(virq); - pnv_put_msi(phb, hwirq); + msi_bitmap_free_hwirqs(&phb->msi_bmp, hwirq, 1); return rc; } irq_set_msi_desc(virq, entry); @@ -144,7 +114,8 @@ static void pnv_teardown_msi_irqs(struct pci_dev *pdev) if (entry->irq == NO_IRQ) continue; irq_set_msi_desc(entry->irq, NULL); - pnv_put_msi(phb, virq_to_hw(entry->irq)); + msi_bitmap_free_hwirqs(&phb->msi_bmp, + virq_to_hw(entry->irq) - phb->msi_base, 1); irq_dispose_mapping(entry->irq); } } @@ -362,48 +333,6 @@ struct pci_ops pnv_pci_ops = { .write = pnv_pci_write_config, }; - -static void pnv_tce_invalidate(struct iommu_table *tbl, - u64 *startp, u64 *endp) -{ - u64 __iomem *invalidate = (u64 __iomem *)tbl->it_index; - unsigned long start, end, inc; - - start = __pa(startp); - end = __pa(endp); - - - /* BML uses this case for p6/p7/galaxy2: Shift addr and put in node */ - if (tbl->it_busno) { - start <<= 12; - end <<= 12; - inc = 128 << 12; - start |= tbl->it_busno; - end |= tbl->it_busno; - } - /* p7ioc-style invalidation, 2 TCEs per write */ - else if (tbl->it_type & TCE_PCI_SWINV_PAIR) { - start |= (1ull << 63); - end |= (1ull << 63); - inc = 16; - } - /* Default (older HW) */ - else - inc = 128; - - end |= inc - 1; /* round up end to be different than start */ - - mb(); /* Ensure above stores are visible */ - while (start <= end) { - __raw_writeq(start, invalidate); - start += inc; - } - /* The iommu layer will do another mb() for us on build() and - * we don't care on free() - */ -} - - static int pnv_tce_build(struct iommu_table *tbl, long index, long npages, unsigned long uaddr, enum dma_data_direction direction, struct dma_attrs *attrs) @@ -428,7 +357,7 @@ static int pnv_tce_build(struct iommu_table *tbl, long index, long npages, * of flags if that becomes the case */ if (tbl->it_type & TCE_PCI_SWINV_CREATE) - pnv_tce_invalidate(tbl, tces, tcep - 1); + pnv_pci_ioda_tce_invalidate(tbl, tces, tcep - 1); return 0; } @@ -443,7 +372,7 @@ static void pnv_tce_free(struct iommu_table *tbl, long index, long npages) *(tcep++) = 0; if (tbl->it_type & TCE_PCI_SWINV_FREE) - pnv_tce_invalidate(tbl, tces, tcep - 1); + pnv_pci_ioda_tce_invalidate(tbl, tces, tcep - 1); } static unsigned long pnv_tce_get(struct iommu_table *tbl, long index) @@ -525,7 +454,19 @@ static void pnv_pci_dma_dev_setup(struct pci_dev *pdev) pnv_pci_dma_fallback_setup(hose, pdev); } -/* Fixup wrong class code in p7ioc root complex */ +void pnv_pci_shutdown(void) +{ + struct pci_controller *hose; + + list_for_each_entry(hose, &hose_list, list_node) { + struct pnv_phb *phb = hose->private_data; + + if (phb && phb->shutdown) + phb->shutdown(phb); + } +} + +/* Fixup wrong class code in p7ioc and p8 root complex */ static void pnv_p7ioc_rc_quirk(struct pci_dev *dev) { dev->class = PCI_CLASS_BRIDGE_PCI << 8; @@ -591,6 +532,10 @@ void __init pnv_pci_init(void) 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); } /* Setup the linkage between OF nodes and PHBs */ diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h index 7cfb7c8..25d76c4 100644 --- a/arch/powerpc/platforms/powernv/pci.h +++ b/arch/powerpc/platforms/powernv/pci.h @@ -4,9 +4,9 @@ struct pci_dn; enum pnv_phb_type { - PNV_PHB_P5IOC2, - PNV_PHB_IODA1, - PNV_PHB_IODA2, + PNV_PHB_P5IOC2 = 0, + PNV_PHB_IODA1 = 1, + PNV_PHB_IODA2 = 2, }; /* Precise PHB model for error management */ @@ -14,6 +14,7 @@ enum pnv_phb_model { PNV_PHB_MODEL_UNKNOWN, PNV_PHB_MODEL_P5IOC2, PNV_PHB_MODEL_P7IOC, + PNV_PHB_MODEL_PHB3, }; #define PNV_PCI_DIAG_BUF_SIZE 4096 @@ -22,8 +23,10 @@ enum pnv_phb_model { #define PNV_IODA_PE_BUS_ALL (1 << 2) /* PE has subordinate buses */ /* Data associated with a PE, including IOMMU tracking etc.. */ +struct pnv_phb; struct pnv_ioda_pe { unsigned long flags; + struct pnv_phb *phb; /* A PE can be associated with a single device or an * entire bus (& children). In the former case, pdev @@ -73,18 +76,17 @@ struct pnv_phb { spinlock_t lock; #ifdef CONFIG_PCI_MSI - unsigned long *msi_map; unsigned int msi_base; - unsigned int msi_count; - unsigned int msi_next; unsigned int msi32_support; + struct msi_bitmap msi_bmp; #endif int (*msi_setup)(struct pnv_phb *phb, struct pci_dev *dev, - unsigned int hwirq, unsigned int is_64, - struct msi_msg *msg); + unsigned int hwirq, unsigned int virq, + unsigned int is_64, struct msi_msg *msg); void (*dma_dev_setup)(struct pnv_phb *phb, struct pci_dev *pdev); void (*fixup_phb)(struct pci_controller *hose); u32 (*bdfn_to_pe)(struct pnv_phb *phb, struct pci_bus *bus, u32 devfn); + void (*shutdown)(struct pnv_phb *phb); union { struct { @@ -109,6 +111,10 @@ struct pnv_phb { unsigned int *io_segmap; struct pnv_ioda_pe *pe_array; + /* IRQ chip */ + int irq_chip_init; + struct irq_chip irq_chip; + /* Sorted list of used PE's based * on the sequence of creation */ @@ -150,6 +156,8 @@ extern void pnv_pci_setup_iommu_table(struct iommu_table *tbl, u64 dma_offset); extern void pnv_pci_init_p5ioc2_hub(struct device_node *np); extern void pnv_pci_init_ioda_hub(struct device_node *np); - +extern void pnv_pci_init_ioda2_phb(struct device_node *np); +extern void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl, + u64 *startp, u64 *endp); #endif /* __POWERNV_PCI_H */ diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h index 8a9df7f..a1c6f83 100644 --- a/arch/powerpc/platforms/powernv/powernv.h +++ b/arch/powerpc/platforms/powernv/powernv.h @@ -9,8 +9,10 @@ static inline void pnv_smp_init(void) { } #ifdef CONFIG_PCI extern void pnv_pci_init(void); +extern void pnv_pci_shutdown(void); #else static inline void pnv_pci_init(void) { } +static inline void pnv_pci_shutdown(void) { } #endif #endif /* _POWERNV_H */ diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index db1ad1c..d4459bf 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -78,7 +78,9 @@ static void pnv_show_cpuinfo(struct seq_file *m) if (root) model = of_get_property(root, "model", NULL); seq_printf(m, "machine\t\t: PowerNV %s\n", model); - if (firmware_has_feature(FW_FEATURE_OPALv2)) + if (firmware_has_feature(FW_FEATURE_OPALv3)) + seq_printf(m, "firmware\t: OPAL v3\n"); + else if (firmware_has_feature(FW_FEATURE_OPALv2)) seq_printf(m, "firmware\t: OPAL v2\n"); else if (firmware_has_feature(FW_FEATURE_OPAL)) seq_printf(m, "firmware\t: OPAL v1\n"); @@ -126,6 +128,17 @@ static void pnv_progress(char *s, unsigned short hex) { } +static void pnv_shutdown(void) +{ + /* Let the PCI code clear up IODA tables */ + pnv_pci_shutdown(); + + /* And unregister all OPAL interrupts so they don't fire + * up while we kexec + */ + opal_shutdown(); +} + #ifdef CONFIG_KEXEC static void pnv_kexec_cpu_down(int crash_shutdown, int secondary) { @@ -187,6 +200,7 @@ define_machine(powernv) { .init_IRQ = pnv_init_IRQ, .show_cpuinfo = pnv_show_cpuinfo, .progress = pnv_progress, + .machine_shutdown = pnv_shutdown, .power_save = power7_idle, .calibrate_decr = generic_calibrate_decr, #ifdef CONFIG_KEXEC diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index c916432..8cbaa59 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -55,16 +55,68 @@ int pnv_smp_kick_cpu(int nr) BUG_ON(nr < 0 || nr >= NR_CPUS); - /* On OPAL v2 the CPU are still spinning inside OPAL itself, - * get them back now + /* + * If we already started or OPALv2 is not supported, we just + * kick the CPU via the PACA */ - if (!paca[nr].cpu_start && firmware_has_feature(FW_FEATURE_OPALv2)) { - pr_devel("OPAL: Starting CPU %d (HW 0x%x)...\n", nr, pcpu); - rc = opal_start_cpu(pcpu, start_here); - if (rc != OPAL_SUCCESS) - pr_warn("OPAL Error %ld starting CPU %d\n", + if (paca[nr].cpu_start || !firmware_has_feature(FW_FEATURE_OPALv2)) + goto kick; + + /* + * At this point, the CPU can either be spinning on the way in + * from kexec or be inside OPAL waiting to be started for the + * first time. OPAL v3 allows us to query OPAL to know if it + * has the CPUs, so we do that + */ + if (firmware_has_feature(FW_FEATURE_OPALv3)) { + uint8_t status; + + rc = opal_query_cpu_status(pcpu, &status); + if (rc != OPAL_SUCCESS) { + pr_warn("OPAL Error %ld querying CPU %d state\n", rc, nr); + return -ENODEV; + } + + /* + * Already started, just kick it, probably coming from + * kexec and spinning + */ + if (status == OPAL_THREAD_STARTED) + goto kick; + + /* + * Available/inactive, let's kick it + */ + if (status == OPAL_THREAD_INACTIVE) { + pr_devel("OPAL: Starting CPU %d (HW 0x%x)...\n", + nr, pcpu); + rc = opal_start_cpu(pcpu, start_here); + if (rc != OPAL_SUCCESS) { + pr_warn("OPAL Error %ld starting CPU %d\n", + rc, nr); + return -ENODEV; + } + } else { + /* + * An unavailable CPU (or any other unknown status) + * shouldn't be started. It should also + * not be in the possible map but currently it can + * happen + */ + pr_devel("OPAL: CPU %d (HW 0x%x) is unavailable" + " (status %d)...\n", nr, pcpu, status); + return -ENODEV; + } + } else { + /* + * On OPAL v2, we just kick it and hope for the best, + * we must not test the error from opal_start_cpu() or + * we would fail to get CPUs from kexec. + */ + opal_start_cpu(pcpu, start_here); } + kick: return smp_generic_kick_cpu(nr); } |