diff options
Diffstat (limited to 'arch/powerpc/platforms/pseries')
25 files changed, 334 insertions, 699 deletions
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig index 62b4f8025de..756b482f819 100644 --- a/arch/powerpc/platforms/pseries/Kconfig +++ b/arch/powerpc/platforms/pseries/Kconfig @@ -20,6 +20,8 @@ config PPC_PSERIES select PPC_DOORBELL select HAVE_CONTEXT_TRACKING select HOTPLUG_CPU if SMP + select ARCH_RANDOM + select PPC_DOORBELL default y config PPC_SPLPAR @@ -34,7 +36,7 @@ config PPC_SPLPAR config PSERIES_MSI bool - depends on PCI_MSI && EEH + depends on PCI_MSI && PPC_PSERIES && EEH default y config PSERIES_ENERGY @@ -110,6 +112,18 @@ config CMM will be reused for other LPARs. The interface allows firmware to balance memory across many LPARs. +config HV_PERF_CTRS + bool "Hypervisor supplied PMU events (24x7 & GPCI)" + default y + depends on PERF_EVENTS && PPC_PSERIES + help + Enable access to hypervisor supplied counters in perf. Currently, + this enables code that uses the hcall GetPerfCounterInfo and 24x7 + interfaces to retrieve counters. GPCI exists on Power 6 and later + systems. 24x7 is available on Power 8 systems. + + If unsure, select Y. + config DTL bool "Dispatch Trace Log" depends on PPC_SPLPAR && DEBUG_FS @@ -119,12 +133,3 @@ config DTL which are accessible through a debugfs file. Say N if you are unsure. - -config PSERIES_IDLE - bool "Cpuidle driver for pSeries platforms" - depends on CPU_IDLE - depends on PPC_PSERIES - default y - help - Select this option to enable processor idle state management - through cpuidle subsystem. diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile index fbccac9cd2d..03480796af9 100644 --- a/arch/powerpc/platforms/pseries/Makefile +++ b/arch/powerpc/platforms/pseries/Makefile @@ -21,7 +21,6 @@ obj-$(CONFIG_HCALL_STATS) += hvCall_inst.o obj-$(CONFIG_CMM) += cmm.o obj-$(CONFIG_DTL) += dtl.o obj-$(CONFIG_IO_EVENT_IRQ) += io_event_irq.o -obj-$(CONFIG_PSERIES_IDLE) += processor_idle.o obj-$(CONFIG_LPARCFG) += lparcfg.o ifeq ($(CONFIG_PPC_PSERIES),y) diff --git a/arch/powerpc/platforms/pseries/cmm.c b/arch/powerpc/platforms/pseries/cmm.c index 1e561bef459..2d8bf15879f 100644 --- a/arch/powerpc/platforms/pseries/cmm.c +++ b/arch/powerpc/platforms/pseries/cmm.c @@ -25,7 +25,6 @@ #include <linux/errno.h> #include <linux/fs.h> #include <linux/gfp.h> -#include <linux/init.h> #include <linux/kthread.h> #include <linux/module.h> #include <linux/oom.h> diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c index a8fe5aa3d34..2d0b4d68a40 100644 --- a/arch/powerpc/platforms/pseries/dlpar.c +++ b/arch/powerpc/platforms/pseries/dlpar.c @@ -11,7 +11,6 @@ */ #include <linux/kernel.h> -#include <linux/kref.h> #include <linux/notifier.h> #include <linux/spinlock.h> #include <linux/cpu.h> @@ -87,7 +86,7 @@ static struct device_node *dlpar_parse_cc_node(struct cc_workarea *ccwa, } of_node_set_flag(dn, OF_DYNAMIC); - kref_init(&dn->kref); + of_node_init(dn); return dn; } diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c index 5db66f1fbc2..7d61498e45c 100644 --- a/arch/powerpc/platforms/pseries/dtl.c +++ b/arch/powerpc/platforms/pseries/dtl.c @@ -20,7 +20,6 @@ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ -#include <linux/init.h> #include <linux/slab.h> #include <linux/debugfs.h> #include <linux/spinlock.h> diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index ccb633e077b..0bec0c02c5e 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -175,6 +175,36 @@ static int pseries_eeh_find_cap(struct device_node *dn, int cap) return 0; } +static int pseries_eeh_find_ecap(struct device_node *dn, int cap) +{ + struct pci_dn *pdn = PCI_DN(dn); + struct eeh_dev *edev = of_node_to_eeh_dev(dn); + u32 header; + int pos = 256; + int ttl = (4096 - 256) / 8; + + if (!edev || !edev->pcie_cap) + return 0; + if (rtas_read_config(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 (rtas_read_config(pdn, pos, 4, &header) != PCIBIOS_SUCCESSFUL) + break; + } + + return 0; +} + /** * pseries_eeh_of_probe - EEH probe on the given device * @dn: OF node @@ -220,7 +250,9 @@ static void *pseries_eeh_of_probe(struct device_node *dn, void *flag) * or PCIe switch downstream port. */ edev->class_code = class_code; + edev->pcix_cap = pseries_eeh_find_cap(dn, PCI_CAP_ID_PCIX); edev->pcie_cap = pseries_eeh_find_cap(dn, PCI_CAP_ID_EXP); + edev->aer_cap = pseries_eeh_find_ecap(dn, PCI_EXT_CAP_ID_ERR); edev->mode &= 0xFFFFFF00; if ((edev->class_code >> 8) == PCI_CLASS_BRIDGE_PCI) { edev->mode |= EEH_DEV_BRIDGE; @@ -265,7 +297,7 @@ static void *pseries_eeh_of_probe(struct device_node *dn, void *flag) enable = 1; if (enable) { - eeh_subsystem_enabled = 1; + eeh_set_enable(true); eeh_add_to_parent_pe(edev); pr_debug("%s: EEH enabled on %s PHB#%d-PE#%x, config addr#%x\n", @@ -464,6 +496,7 @@ static int pseries_eeh_get_state(struct eeh_pe *pe, int *state) } else { result = EEH_STATE_NOT_SUPPORT; } + break; default: result = EEH_STATE_NOT_SUPPORT; } @@ -499,11 +532,19 @@ static int pseries_eeh_reset(struct eeh_pe *pe, int option) /* If fundamental-reset not supported, try hot-reset */ if (option == EEH_RESET_FUNDAMENTAL && ret == -8) { + option = EEH_RESET_HOT; ret = rtas_call(ibm_set_slot_reset, 4, 1, NULL, config_addr, BUID_HI(pe->phb->buid), - BUID_LO(pe->phb->buid), EEH_RESET_HOT); + BUID_LO(pe->phb->buid), option); } + /* We need reset hold or settlement delay */ + if (option == EEH_RESET_FUNDAMENTAL || + option == EEH_RESET_HOT) + msleep(EEH_PE_RST_HOLD_TIME); + else + msleep(EEH_PE_RST_SETTLE_TIME); + return ret; } @@ -689,7 +730,9 @@ static struct eeh_ops pseries_eeh_ops = { .get_log = pseries_eeh_get_log, .configure_bridge = pseries_eeh_configure_bridge, .read_config = pseries_eeh_read_config, - .write_config = pseries_eeh_write_config + .write_config = pseries_eeh_write_config, + .next_error = NULL, + .restore_config = NULL }; /** diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index 82789e79e53..20d62975856 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -35,12 +35,7 @@ #include "offline_states.h" /* This version can't take the spinlock, because it never returns */ -static struct rtas_args rtas_stop_self_args = { - .token = RTAS_UNKNOWN_SERVICE, - .nargs = 0, - .nret = 1, - .rets = &rtas_stop_self_args.args[0], -}; +static int rtas_stop_self_token = RTAS_UNKNOWN_SERVICE; static DEFINE_PER_CPU(enum cpu_state_vals, preferred_offline_state) = CPU_STATE_OFFLINE; @@ -93,15 +88,21 @@ void set_default_offline_state(int cpu) static void rtas_stop_self(void) { - struct rtas_args *args = &rtas_stop_self_args; + static struct rtas_args args = { + .nargs = 0, + .nret = 1, + .rets = &args.args[0], + }; + + args.token = cpu_to_be32(rtas_stop_self_token); local_irq_disable(); - BUG_ON(args->token == RTAS_UNKNOWN_SERVICE); + BUG_ON(rtas_stop_self_token == RTAS_UNKNOWN_SERVICE); printk("cpu %u (hwid %u) Ready to die...\n", smp_processor_id(), hard_smp_processor_id()); - enter_rtas(__pa(args)); + enter_rtas(__pa(&args)); panic("Alas, I survived.\n"); } @@ -392,10 +393,10 @@ static int __init pseries_cpu_hotplug_init(void) } } - rtas_stop_self_args.token = rtas_token("stop-self"); + rtas_stop_self_token = rtas_token("stop-self"); qcss_tok = rtas_token("query-cpu-stopped-state"); - if (rtas_stop_self_args.token == RTAS_UNKNOWN_SERVICE || + if (rtas_stop_self_token == RTAS_UNKNOWN_SERVICE || qcss_tok == RTAS_UNKNOWN_SERVICE) { printk(KERN_INFO "CPU Hotplug not supported by firmware " "- disabling.\n"); @@ -420,4 +421,4 @@ static int __init pseries_cpu_hotplug_init(void) return 0; } -arch_initcall(pseries_cpu_hotplug_init); +machine_arch_initcall(pseries, pseries_cpu_hotplug_init); diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 9590dbb756f..7995135170a 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -14,13 +14,14 @@ #include <linux/memblock.h> #include <linux/vmalloc.h> #include <linux/memory.h> +#include <linux/memory_hotplug.h> #include <asm/firmware.h> #include <asm/machdep.h> #include <asm/prom.h> #include <asm/sparsemem.h> -static unsigned long get_memblock_size(void) +unsigned long pseries_memory_block_size(void) { struct device_node *np; unsigned int memblock_size = MIN_MEMORY_BLOCK_SIZE; @@ -63,72 +64,53 @@ static unsigned long get_memblock_size(void) return memblock_size; } -/* WARNING: This is going to override the generic definition whenever - * pseries is built-in regardless of what platform is active at boot - * time. This is fine for now as this is the only "option" and it - * should work everywhere. If not, we'll have to turn this into a - * ppc_md. callback - */ -unsigned long memory_block_size_bytes(void) +#ifdef CONFIG_MEMORY_HOTREMOVE +static int pseries_remove_memory(u64 start, u64 size) { - return get_memblock_size(); + int ret; + + /* Remove htab bolted mappings for this section of memory */ + start = (unsigned long)__va(start); + ret = remove_section_mapping(start, start + size); + + /* Ensure all vmalloc mappings are flushed in case they also + * hit that section of memory + */ + vm_unmap_aliases(); + + return ret; } -#ifdef CONFIG_MEMORY_HOTREMOVE static int pseries_remove_memblock(unsigned long base, unsigned int memblock_size) { - unsigned long start, start_pfn; - struct zone *zone; - int ret; - unsigned long section; - unsigned long sections_to_remove; + unsigned long block_sz, start_pfn; + int sections_per_block; + int i, nid; start_pfn = base >> PAGE_SHIFT; - if (!pfn_valid(start_pfn)) { - memblock_remove(base, memblock_size); - return 0; - } + lock_device_hotplug(); - zone = page_zone(pfn_to_page(start_pfn)); + if (!pfn_valid(start_pfn)) + goto out; - /* - * Remove section mappings and sysfs entries for the - * section of the memory we are removing. - * - * NOTE: Ideally, this should be done in generic code like - * remove_memory(). But remove_memory() gets called by writing - * to sysfs "state" file and we can't remove sysfs entries - * while writing to it. So we have to defer it to here. - */ - sections_to_remove = (memblock_size >> PAGE_SHIFT) / PAGES_PER_SECTION; - for (section = 0; section < sections_to_remove; section++) { - unsigned long pfn = start_pfn + section * PAGES_PER_SECTION; - ret = __remove_pages(zone, pfn, PAGES_PER_SECTION); - if (ret) - return ret; + block_sz = pseries_memory_block_size(); + sections_per_block = block_sz / MIN_MEMORY_BLOCK_SIZE; + nid = memory_add_physaddr_to_nid(base); + + for (i = 0; i < sections_per_block; i++) { + remove_memory(nid, base, MIN_MEMORY_BLOCK_SIZE); + base += MIN_MEMORY_BLOCK_SIZE; } - /* - * Update memory regions for memory remove - */ +out: + /* Update memory regions for memory remove */ memblock_remove(base, memblock_size); - - /* - * Remove htab bolted mappings for this section of memory - */ - start = (unsigned long)__va(base); - ret = remove_section_mapping(start, start + memblock_size); - - /* Ensure all vmalloc mappings are flushed in case they also - * hit that section of memory - */ - vm_unmap_aliases(); - - return ret; + unlock_device_hotplug(); + return 0; } -static int pseries_remove_memory(struct device_node *np) +static int pseries_remove_mem_node(struct device_node *np) { const char *type; const unsigned int *regs; @@ -153,8 +135,8 @@ static int pseries_remove_memory(struct device_node *np) base = *(unsigned long *)regs; lmb_size = regs[3]; - ret = pseries_remove_memblock(base, lmb_size); - return ret; + pseries_remove_memblock(base, lmb_size); + return 0; } #else static inline int pseries_remove_memblock(unsigned long base, @@ -162,13 +144,13 @@ static inline int pseries_remove_memblock(unsigned long base, { return -EOPNOTSUPP; } -static inline int pseries_remove_memory(struct device_node *np) +static inline int pseries_remove_mem_node(struct device_node *np) { return -EOPNOTSUPP; } #endif /* CONFIG_MEMORY_HOTREMOVE */ -static int pseries_add_memory(struct device_node *np) +static int pseries_add_mem_node(struct device_node *np) { const char *type; const unsigned int *regs; @@ -208,7 +190,7 @@ static int pseries_update_drconf_memory(struct of_prop_reconfig *pr) u32 *p; int i, rc = -EINVAL; - memblock_size = get_memblock_size(); + memblock_size = pseries_memory_block_size(); if (!memblock_size) return -EINVAL; @@ -254,10 +236,10 @@ static int pseries_memory_notifier(struct notifier_block *nb, switch (action) { case OF_RECONFIG_ATTACH_NODE: - err = pseries_add_memory(node); + err = pseries_add_mem_node(node); break; case OF_RECONFIG_DETACH_NODE: - err = pseries_remove_memory(node); + err = pseries_remove_mem_node(node); break; case OF_RECONFIG_UPDATE_PROPERTY: pr = (struct of_prop_reconfig *)node; @@ -277,6 +259,10 @@ static int __init pseries_memory_hotplug_init(void) if (firmware_has_feature(FW_FEATURE_LPAR)) of_reconfig_notifier_register(&pseries_mem_nb); +#ifdef CONFIG_MEMORY_HOTREMOVE + ppc_md.remove_memory = pseries_remove_memory; +#endif + return 0; } machine_device_initcall(pseries, pseries_memory_hotplug_init); diff --git a/arch/powerpc/platforms/pseries/hvCall.S b/arch/powerpc/platforms/pseries/hvCall.S index 444fe7759e5..99ecf0a5a92 100644 --- a/arch/powerpc/platforms/pseries/hvCall.S +++ b/arch/powerpc/platforms/pseries/hvCall.S @@ -49,7 +49,7 @@ END_FTR_SECTION(0, 1); \ std r0,16(r1); \ addi r4,r1,STK_PARAM(FIRST_REG); \ stdu r1,-STACK_FRAME_OVERHEAD(r1); \ - bl .__trace_hcall_entry; \ + bl __trace_hcall_entry; \ addi r1,r1,STACK_FRAME_OVERHEAD; \ ld r0,16(r1); \ ld r3,STK_PARAM(R3)(r1); \ @@ -83,7 +83,7 @@ END_FTR_SECTION(0, 1); \ mr r3,r6; \ std r0,16(r1); \ stdu r1,-STACK_FRAME_OVERHEAD(r1); \ - bl .__trace_hcall_exit; \ + bl __trace_hcall_exit; \ addi r1,r1,STACK_FRAME_OVERHEAD; \ ld r0,16(r1); \ ld r3,STK_PARAM(R3)(r1); \ @@ -106,7 +106,7 @@ END_FTR_SECTION(0, 1); \ .text -_GLOBAL(plpar_hcall_norets) +_GLOBAL_TOC(plpar_hcall_norets) HMT_MEDIUM mfcr r0 @@ -122,7 +122,7 @@ _GLOBAL(plpar_hcall_norets) mtcrf 0xff,r0 blr /* return r3 = status */ -_GLOBAL(plpar_hcall) +_GLOBAL_TOC(plpar_hcall) HMT_MEDIUM mfcr r0 @@ -188,7 +188,7 @@ _GLOBAL(plpar_hcall_raw) blr /* return r3 = status */ -_GLOBAL(plpar_hcall9) +_GLOBAL_TOC(plpar_hcall9) HMT_MEDIUM mfcr r0 diff --git a/arch/powerpc/platforms/pseries/io_event_irq.c b/arch/powerpc/platforms/pseries/io_event_irq.c index 5ea88d1541f..0240c4ff878 100644 --- a/arch/powerpc/platforms/pseries/io_event_irq.c +++ b/arch/powerpc/platforms/pseries/io_event_irq.c @@ -82,9 +82,9 @@ static struct pseries_io_event * ioei_find_event(struct rtas_error_log *elog) * RTAS_TYPE_IO only exists in extended event log version 6 or later. * No need to check event log version. */ - if (unlikely(elog->type != RTAS_TYPE_IO)) { - printk_once(KERN_WARNING "io_event_irq: Unexpected event type %d", - elog->type); + if (unlikely(rtas_error_type(elog) != RTAS_TYPE_IO)) { + printk_once(KERN_WARNING"io_event_irq: Unexpected event type %d", + rtas_error_type(elog)); return NULL; } diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index f253361552a..33b552ffbe5 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -486,9 +486,10 @@ static void iommu_table_setparms(struct pci_controller *phb, memset((void *)tbl->it_base, 0, *sizep); tbl->it_busno = phb->bus->number; + tbl->it_page_shift = IOMMU_PAGE_SHIFT_4K; /* Units of tce entries */ - tbl->it_offset = phb->dma_window_base_cur >> IOMMU_PAGE_SHIFT; + tbl->it_offset = phb->dma_window_base_cur >> tbl->it_page_shift; /* Test if we are going over 2GB of DMA space */ if (phb->dma_window_base_cur + phb->dma_window_size > 0x80000000ul) { @@ -499,7 +500,7 @@ static void iommu_table_setparms(struct pci_controller *phb, phb->dma_window_base_cur += phb->dma_window_size; /* Set the tce table size - measured in entries */ - tbl->it_size = phb->dma_window_size >> IOMMU_PAGE_SHIFT; + tbl->it_size = phb->dma_window_size >> tbl->it_page_shift; tbl->it_index = 0; tbl->it_blocksize = 16; @@ -537,11 +538,12 @@ static void iommu_table_setparms_lpar(struct pci_controller *phb, of_parse_dma_window(dn, dma_window, &tbl->it_index, &offset, &size); tbl->it_busno = phb->bus->number; + tbl->it_page_shift = IOMMU_PAGE_SHIFT_4K; tbl->it_base = 0; tbl->it_blocksize = 16; tbl->it_type = TCE_PCI; - tbl->it_offset = offset >> IOMMU_PAGE_SHIFT; - tbl->it_size = size >> IOMMU_PAGE_SHIFT; + tbl->it_offset = offset >> tbl->it_page_shift; + tbl->it_size = size >> tbl->it_page_shift; } static void pci_dma_bus_setup_pSeries(struct pci_bus *bus) @@ -687,7 +689,8 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev) iommu_table_setparms(phb, dn, tbl); PCI_DN(dn)->iommu_table = iommu_init_table(tbl, phb->node); iommu_register_group(tbl, pci_domain_nr(phb->bus), 0); - set_iommu_table_base(&dev->dev, PCI_DN(dn)->iommu_table); + set_iommu_table_base_and_group(&dev->dev, + PCI_DN(dn)->iommu_table); return; } @@ -699,7 +702,8 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev) dn = dn->parent; if (dn && PCI_DN(dn)) - set_iommu_table_base(&dev->dev, PCI_DN(dn)->iommu_table); + set_iommu_table_base_and_group(&dev->dev, + PCI_DN(dn)->iommu_table); else printk(KERN_WARNING "iommu: Device %s has no iommu table\n", pci_name(dev)); @@ -717,21 +721,6 @@ static int __init disable_ddw_setup(char *str) early_param("disable_ddw", disable_ddw_setup); -static inline void __remove_ddw(struct device_node *np, const u32 *ddw_avail, u64 liobn) -{ - int ret; - - ret = rtas_call(ddw_avail[2], 1, 1, NULL, liobn); - if (ret) - pr_warning("%s: failed to remove DMA window: rtas returned " - "%d to ibm,remove-pe-dma-window(%x) %llx\n", - np->full_name, ret, ddw_avail[2], liobn); - else - pr_debug("%s: successfully removed DMA window: rtas returned " - "%d to ibm,remove-pe-dma-window(%x) %llx\n", - np->full_name, ret, ddw_avail[2], liobn); -} - static void remove_ddw(struct device_node *np) { struct dynamic_dma_window_prop *dwp; @@ -761,7 +750,15 @@ static void remove_ddw(struct device_node *np) pr_debug("%s successfully cleared tces in window.\n", np->full_name); - __remove_ddw(np, ddw_avail, liobn); + ret = rtas_call(ddw_avail[2], 1, 1, NULL, liobn); + if (ret) + pr_warning("%s: failed to remove direct window: rtas returned " + "%d to ibm,remove-pe-dma-window(%x) %llx\n", + np->full_name, ret, ddw_avail[2], liobn); + else + pr_debug("%s: successfully removed direct window: rtas returned " + "%d to ibm,remove-pe-dma-window(%x) %llx\n", + np->full_name, ret, ddw_avail[2], liobn); delprop: ret = of_remove_property(np, win64); @@ -790,68 +787,33 @@ static u64 find_existing_ddw(struct device_node *pdn) return dma_addr; } -static void __restore_default_window(struct eeh_dev *edev, - u32 ddw_restore_token) -{ - u32 cfg_addr; - u64 buid; - int ret; - - /* - * Get the config address and phb buid of the PE window. - * Rely on eeh to retrieve this for us. - * Retrieve them from the pci device, not the node with the - * dma-window property - */ - cfg_addr = edev->config_addr; - if (edev->pe_config_addr) - cfg_addr = edev->pe_config_addr; - buid = edev->phb->buid; - - do { - ret = rtas_call(ddw_restore_token, 3, 1, NULL, cfg_addr, - BUID_HI(buid), BUID_LO(buid)); - } while (rtas_busy_delay(ret)); - pr_info("ibm,reset-pe-dma-windows(%x) %x %x %x returned %d\n", - ddw_restore_token, cfg_addr, BUID_HI(buid), BUID_LO(buid), ret); -} - static int find_existing_ddw_windows(void) { + int len; struct device_node *pdn; + struct direct_window *window; const struct dynamic_dma_window_prop *direct64; - const u32 *ddw_extensions; if (!firmware_has_feature(FW_FEATURE_LPAR)) return 0; for_each_node_with_property(pdn, DIRECT64_PROPNAME) { - direct64 = of_get_property(pdn, DIRECT64_PROPNAME, NULL); + direct64 = of_get_property(pdn, DIRECT64_PROPNAME, &len); if (!direct64) continue; - /* - * We need to ensure the IOMMU table is active when we - * return from the IOMMU setup so that the common code - * can clear the table or find the holes. To that end, - * first, remove any existing DDW configuration. - */ - remove_ddw(pdn); + window = kzalloc(sizeof(*window), GFP_KERNEL); + if (!window || len < sizeof(struct dynamic_dma_window_prop)) { + kfree(window); + remove_ddw(pdn); + continue; + } - /* - * Second, if we are running on a new enough level of - * firmware where the restore API is present, use it to - * restore the 32-bit window, which was removed in - * create_ddw. - * If the API is not present, then create_ddw couldn't - * have removed the 32-bit window in the first place, so - * removing the DDW configuration should be sufficient. - */ - ddw_extensions = of_get_property(pdn, "ibm,ddw-extensions", - NULL); - if (ddw_extensions && ddw_extensions[0] > 0) - __restore_default_window(of_node_to_eeh_dev(pdn), - ddw_extensions[1]); + window->device = pdn; + window->prop = direct64; + spin_lock(&direct_window_list_lock); + list_add(&window->list, &direct_window_list); + spin_unlock(&direct_window_list_lock); } return 0; @@ -921,12 +883,6 @@ static int create_ddw(struct pci_dev *dev, const u32 *ddw_avail, return ret; } -static void restore_default_window(struct pci_dev *dev, - u32 ddw_restore_token) -{ - __restore_default_window(pci_dev_to_eeh_dev(dev), ddw_restore_token); -} - struct failed_ddw_pdn { struct device_node *pdn; struct list_head list; @@ -954,13 +910,9 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) u64 dma_addr, max_addr; struct device_node *dn; const u32 *uninitialized_var(ddw_avail); - const u32 *uninitialized_var(ddw_extensions); - u32 ddw_restore_token = 0; struct direct_window *window; struct property *win64; struct dynamic_dma_window_prop *ddwprop; - const void *dma_window = NULL; - unsigned long liobn, offset, size; struct failed_ddw_pdn *fpdn; mutex_lock(&direct_window_init_mutex); @@ -991,42 +943,9 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) */ ddw_avail = of_get_property(pdn, "ibm,ddw-applicable", &len); if (!ddw_avail || len < 3 * sizeof(u32)) - goto out_unlock; - - /* - * the extensions property is only required to exist in certain - * levels of firmware and later - * the ibm,ddw-extensions property is a list with the first - * element containing the number of extensions and each - * subsequent entry is a value corresponding to that extension - */ - ddw_extensions = of_get_property(pdn, "ibm,ddw-extensions", &len); - if (ddw_extensions) { - /* - * each new defined extension length should be added to - * the top of the switch so the "earlier" entries also - * get picked up - */ - switch (ddw_extensions[0]) { - /* ibm,reset-pe-dma-windows */ - case 1: - ddw_restore_token = ddw_extensions[1]; - break; - } - } - - /* - * Only remove the existing DMA window if we can restore back to - * the default state. Removing the existing window maximizes the - * resources available to firmware for dynamic window creation. - */ - if (ddw_restore_token) { - dma_window = of_get_property(pdn, "ibm,dma-window", NULL); - of_parse_dma_window(pdn, dma_window, &liobn, &offset, &size); - __remove_ddw(pdn, ddw_avail, liobn); - } + goto out_failed; - /* + /* * Query if there is a second window of size to map the * whole partition. Query returns number of windows, largest * block assigned to PE (partition endpoint), and two bitmasks @@ -1035,7 +954,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) dn = pci_device_to_OF_node(dev); ret = query_ddw(dev, ddw_avail, &query); if (ret != 0) - goto out_restore_window; + goto out_failed; if (query.windows_available == 0) { /* @@ -1044,7 +963,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) * trading in for a larger page size. */ dev_dbg(&dev->dev, "no free dynamic windows"); - goto out_restore_window; + goto out_failed; } if (be32_to_cpu(query.page_size) & 4) { page_shift = 24; /* 16MB */ @@ -1055,7 +974,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) } else { dev_dbg(&dev->dev, "no supported direct page size in mask %x", query.page_size); - goto out_restore_window; + goto out_failed; } /* verify the window * number of ptes will map the partition */ /* check largest block * page size > max memory hotplug addr */ @@ -1064,14 +983,14 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) dev_dbg(&dev->dev, "can't map partiton max 0x%llx with %u " "%llu-sized pages\n", max_addr, query.largest_available_block, 1ULL << page_shift); - goto out_restore_window; + goto out_failed; } len = order_base_2(max_addr); win64 = kzalloc(sizeof(struct property), GFP_KERNEL); if (!win64) { dev_info(&dev->dev, "couldn't allocate property for 64bit dma window\n"); - goto out_restore_window; + goto out_failed; } win64->name = kstrdup(DIRECT64_PROPNAME, GFP_KERNEL); win64->value = ddwprop = kmalloc(sizeof(*ddwprop), GFP_KERNEL); @@ -1133,9 +1052,7 @@ out_free_prop: kfree(win64->value); kfree(win64); -out_restore_window: - if (ddw_restore_token) - restore_default_window(dev, ddw_restore_token); +out_failed: fpdn = kzalloc(sizeof(*fpdn), GFP_KERNEL); if (!fpdn) @@ -1193,7 +1110,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) pr_debug(" found DMA window, table: %p\n", pci->iommu_table); } - set_iommu_table_base(&dev->dev, pci->iommu_table); + set_iommu_table_base_and_group(&dev->dev, pci->iommu_table); } static int dma_set_mask_pSeriesLP(struct device *dev, u64 dma_mask) diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 4fca3def9db..b02af9ef3ff 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -92,7 +92,7 @@ void vpa_init(int cpu) * PAPR says this feature is SLB-Buffer but firmware never * reports that. All SPLPAR support SLB shadow buffer. */ - addr = __pa(&slb_shadow[cpu]); + addr = __pa(paca[cpu].slb_shadow_ptr); if (firmware_has_feature(FW_FEATURE_SPLPAR)) { ret = register_slb_shadow(hwcpu, addr); if (ret) @@ -153,7 +153,8 @@ static long pSeries_lpar_hpte_insert(unsigned long hpte_group, /* Make pHyp happy */ if ((rflags & _PAGE_NO_CACHE) && !(rflags & _PAGE_WRITETHRU)) - hpte_r &= ~_PAGE_COHERENT; + hpte_r &= ~HPTE_R_M; + if (firmware_has_feature(FW_FEATURE_XCMO) && !(hpte_r & HPTE_R_N)) flags |= H_COALESCE_CAND; diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c index e738007eae6..c9fecf09b8f 100644 --- a/arch/powerpc/platforms/pseries/lparcfg.c +++ b/arch/powerpc/platforms/pseries/lparcfg.c @@ -157,7 +157,7 @@ static void parse_ppp_data(struct seq_file *m) { struct hvcall_ppp_data ppp_data; struct device_node *root; - const int *perf_level; + const __be32 *perf_level; int rc; rc = h_get_ppp(&ppp_data); @@ -201,7 +201,7 @@ static void parse_ppp_data(struct seq_file *m) perf_level = of_get_property(root, "ibm,partition-performance-parameters-level", NULL); - if (perf_level && (*perf_level >= 1)) { + if (perf_level && (be32_to_cpup(perf_level) >= 1)) { seq_printf(m, "physical_procs_allocated_to_virtualization=%d\n", ppp_data.phys_platform_procs); @@ -435,7 +435,7 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v) int partition_potential_processors; int partition_active_processors; struct device_node *rtas_node; - const int *lrdrp = NULL; + const __be32 *lrdrp = NULL; rtas_node = of_find_node_by_path("/rtas"); if (rtas_node) @@ -444,7 +444,7 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v) if (lrdrp == NULL) { partition_potential_processors = vdso_data->processorCount; } else { - partition_potential_processors = *(lrdrp + 4); + partition_potential_processors = be32_to_cpup(lrdrp + 4); } of_node_put(rtas_node); @@ -654,7 +654,7 @@ static int lparcfg_data(struct seq_file *m, void *v) const char *model = ""; const char *system_id = ""; const char *tmp; - const unsigned int *lp_index_ptr; + const __be32 *lp_index_ptr; unsigned int lp_index = 0; seq_printf(m, "%s %s\n", MODULE_NAME, MODULE_VERS); @@ -670,7 +670,7 @@ static int lparcfg_data(struct seq_file *m, void *v) lp_index_ptr = of_get_property(rootdn, "ibm,partition-no", NULL); if (lp_index_ptr) - lp_index = *lp_index_ptr; + lp_index = be32_to_cpup(lp_index_ptr); of_node_put(rootdn); } seq_printf(m, "serial_number=%s\n", system_id); diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index cde4e0a095a..bde7ebad394 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -290,13 +290,6 @@ void post_mobility_fixup(void) int rc; int activate_fw_token; - rc = pseries_devicetree_update(MIGRATION_SCOPE); - if (rc) { - printk(KERN_ERR "Initial post-mobility device tree update " - "failed: %d\n", rc); - return; - } - activate_fw_token = rtas_token("ibm,activate-firmware"); if (activate_fw_token == RTAS_UNKNOWN_SERVICE) { printk(KERN_ERR "Could not make post-mobility " @@ -304,16 +297,17 @@ void post_mobility_fixup(void) return; } - rc = rtas_call(activate_fw_token, 0, 1, NULL); - if (!rc) { - rc = pseries_devicetree_update(MIGRATION_SCOPE); - if (rc) - printk(KERN_ERR "Secondary post-mobility device tree " - "update failed: %d\n", rc); - } else { + do { + rc = rtas_call(activate_fw_token, 0, 1, NULL); + } while (rtas_busy_delay(rc)); + + if (rc) printk(KERN_ERR "Post-mobility activate-fw failed: %d\n", rc); - return; - } + + rc = pseries_devicetree_update(MIGRATION_SCOPE); + if (rc) + printk(KERN_ERR "Post-mobility device tree update " + "failed: %d\n", rc); return; } diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c index 6d2f0abce6f..0c882e83c4c 100644 --- a/arch/powerpc/platforms/pseries/msi.c +++ b/arch/powerpc/platforms/pseries/msi.c @@ -130,7 +130,8 @@ static int check_req(struct pci_dev *pdev, int nvec, char *prop_name) { struct device_node *dn; struct pci_dn *pdn; - const u32 *req_msi; + const __be32 *p; + u32 req_msi; pdn = pci_get_pdn(pdev); if (!pdn) @@ -138,19 +139,20 @@ static int check_req(struct pci_dev *pdev, int nvec, char *prop_name) dn = pdn->node; - req_msi = of_get_property(dn, prop_name, NULL); - if (!req_msi) { + p = of_get_property(dn, prop_name, NULL); + if (!p) { pr_debug("rtas_msi: No %s on %s\n", prop_name, dn->full_name); return -ENOENT; } - if (*req_msi < nvec) { + req_msi = be32_to_cpup(p); + if (req_msi < nvec) { pr_debug("rtas_msi: %s requests < %d MSIs\n", prop_name, nvec); - if (*req_msi == 0) /* Be paranoid */ + if (req_msi == 0) /* Be paranoid */ return -ENOSPC; - return *req_msi; + return req_msi; } return 0; @@ -171,7 +173,7 @@ static int check_req_msix(struct pci_dev *pdev, int nvec) static struct device_node *find_pe_total_msi(struct pci_dev *dev, int *total) { struct device_node *dn; - const u32 *p; + const __be32 *p; dn = of_node_get(pci_device_to_OF_node(dev)); while (dn) { @@ -179,7 +181,7 @@ static struct device_node *find_pe_total_msi(struct pci_dev *dev, int *total) if (p) { pr_debug("rtas_msi: found prop on dn %s\n", dn->full_name); - *total = *p; + *total = be32_to_cpup(p); return dn; } @@ -232,13 +234,13 @@ struct msi_counts { static void *count_non_bridge_devices(struct device_node *dn, void *data) { struct msi_counts *counts = data; - const u32 *p; + const __be32 *p; u32 class; pr_debug("rtas_msi: counting %s\n", dn->full_name); p = of_get_property(dn, "class-code", NULL); - class = p ? *p : 0; + class = p ? be32_to_cpup(p) : 0; if ((class >> 8) != PCI_CLASS_BRIDGE_PCI) counts->num_devices++; @@ -249,7 +251,7 @@ static void *count_non_bridge_devices(struct device_node *dn, void *data) static void *count_spare_msis(struct device_node *dn, void *data) { struct msi_counts *counts = data; - const u32 *p; + const __be32 *p; int req; if (dn == counts->requestor) @@ -260,11 +262,11 @@ static void *count_spare_msis(struct device_node *dn, void *data) req = 0; p = of_get_property(dn, "ibm,req#msi", NULL); if (p) - req = *p; + req = be32_to_cpup(p); p = of_get_property(dn, "ibm,req#msi-x", NULL); if (p) - req = max(req, (int)*p); + req = max(req, (int)be32_to_cpup(p)); } if (req < counts->quota) diff --git a/arch/powerpc/platforms/pseries/nvram.c b/arch/powerpc/platforms/pseries/nvram.c index 7bfaf58d466..0cc240b7f69 100644 --- a/arch/powerpc/platforms/pseries/nvram.c +++ b/arch/powerpc/platforms/pseries/nvram.c @@ -43,8 +43,8 @@ static char nvram_buf[NVRW_CNT]; /* assume this is in the first 4GB */ static DEFINE_SPINLOCK(nvram_lock); struct err_log_info { - int error_type; - unsigned int seq_num; + __be32 error_type; + __be32 seq_num; }; struct nvram_os_partition { @@ -79,9 +79,9 @@ static const char *pseries_nvram_os_partitions[] = { }; struct oops_log_info { - u16 version; - u16 report_length; - u64 timestamp; + __be16 version; + __be16 report_length; + __be64 timestamp; } __attribute__((packed)); static void oops_to_nvram(struct kmsg_dumper *dumper, @@ -291,20 +291,20 @@ int nvram_write_os_partition(struct nvram_os_partition *part, char * buff, length = part->size; } - info.error_type = err_type; - info.seq_num = error_log_cnt; + info.error_type = cpu_to_be32(err_type); + info.seq_num = cpu_to_be32(error_log_cnt); tmp_index = part->index; rc = ppc_md.nvram_write((char *)&info, sizeof(struct err_log_info), &tmp_index); if (rc <= 0) { - pr_err("%s: Failed nvram_write (%d)\n", __FUNCTION__, rc); + pr_err("%s: Failed nvram_write (%d)\n", __func__, rc); return rc; } rc = ppc_md.nvram_write(buff, length, &tmp_index); if (rc <= 0) { - pr_err("%s: Failed nvram_write (%d)\n", __FUNCTION__, rc); + pr_err("%s: Failed nvram_write (%d)\n", __func__, rc); return rc; } @@ -351,21 +351,20 @@ int nvram_read_partition(struct nvram_os_partition *part, char *buff, sizeof(struct err_log_info), &tmp_index); if (rc <= 0) { - pr_err("%s: Failed nvram_read (%d)\n", __FUNCTION__, - rc); + pr_err("%s: Failed nvram_read (%d)\n", __func__, rc); return rc; } } rc = ppc_md.nvram_read(buff, length, &tmp_index); if (rc <= 0) { - pr_err("%s: Failed nvram_read (%d)\n", __FUNCTION__, rc); + pr_err("%s: Failed nvram_read (%d)\n", __func__, rc); return rc; } if (part->os_partition) { - *error_log_cnt = info.seq_num; - *err_type = info.error_type; + *error_log_cnt = be32_to_cpu(info.seq_num); + *err_type = be32_to_cpu(info.error_type); } return 0; @@ -529,9 +528,9 @@ static int zip_oops(size_t text_len) pr_err("nvram: logging uncompressed oops/panic report\n"); return -1; } - oops_hdr->version = OOPS_HDR_VERSION; - oops_hdr->report_length = (u16) zipped_len; - oops_hdr->timestamp = get_seconds(); + oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION); + oops_hdr->report_length = cpu_to_be16(zipped_len); + oops_hdr->timestamp = cpu_to_be64(get_seconds()); return 0; } @@ -574,9 +573,9 @@ static int nvram_pstore_write(enum pstore_type_id type, clobbering_unread_rtas_event()) return -1; - oops_hdr->version = OOPS_HDR_VERSION; - oops_hdr->report_length = (u16) size; - oops_hdr->timestamp = get_seconds(); + oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION); + oops_hdr->report_length = cpu_to_be16(size); + oops_hdr->timestamp = cpu_to_be64(get_seconds()); if (compressed) err_type = ERR_TYPE_KERNEL_PANIC_GZ; @@ -670,16 +669,16 @@ static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type, size_t length, hdr_size; oops_hdr = (struct oops_log_info *)buff; - if (oops_hdr->version < OOPS_HDR_VERSION) { + if (be16_to_cpu(oops_hdr->version) < OOPS_HDR_VERSION) { /* Old format oops header had 2-byte record size */ hdr_size = sizeof(u16); - length = oops_hdr->version; + length = be16_to_cpu(oops_hdr->version); time->tv_sec = 0; time->tv_nsec = 0; } else { hdr_size = sizeof(*oops_hdr); - length = oops_hdr->report_length; - time->tv_sec = oops_hdr->timestamp; + length = be16_to_cpu(oops_hdr->report_length); + time->tv_sec = be64_to_cpu(oops_hdr->timestamp); time->tv_nsec = 0; } *buf = kmalloc(length, GFP_KERNEL); @@ -869,7 +868,7 @@ static void oops_to_nvram(struct kmsg_dumper *dumper, break; default: pr_err("%s: ignoring unrecognized KMSG_DUMP_* reason %d\n", - __FUNCTION__, (int) reason); + __func__, (int) reason); return; } @@ -889,13 +888,13 @@ static void oops_to_nvram(struct kmsg_dumper *dumper, kmsg_dump_get_buffer(dumper, false, oops_data, oops_data_sz, &text_len); err_type = ERR_TYPE_KERNEL_PANIC; - oops_hdr->version = OOPS_HDR_VERSION; - oops_hdr->report_length = (u16) text_len; - oops_hdr->timestamp = get_seconds(); + oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION); + oops_hdr->report_length = cpu_to_be16(text_len); + oops_hdr->timestamp = cpu_to_be64(get_seconds()); } (void) nvram_write_os_partition(&oops_log_partition, oops_buf, - (int) (sizeof(*oops_hdr) + oops_hdr->report_length), err_type, + (int) (sizeof(*oops_hdr) + text_len), err_type, ++oops_count); spin_unlock_irqrestore(&lock, flags); diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c index 5f93856cdf4..c413ec158ff 100644 --- a/arch/powerpc/platforms/pseries/pci.c +++ b/arch/powerpc/platforms/pseries/pci.c @@ -113,7 +113,8 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge) { struct device_node *dn, *pdn; struct pci_bus *bus; - const uint32_t *pcie_link_speed_stats; + u32 pcie_link_speed_stats[2]; + int rc; bus = bridge->bus; @@ -122,15 +123,16 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge) return 0; for (pdn = dn; pdn != NULL; pdn = of_get_next_parent(pdn)) { - pcie_link_speed_stats = (const uint32_t *) of_get_property(pdn, - "ibm,pcie-link-speed-stats", NULL); - if (pcie_link_speed_stats) + rc = of_property_read_u32_array(pdn, + "ibm,pcie-link-speed-stats", + &pcie_link_speed_stats[0], 2); + if (!rc) break; } of_node_put(pdn); - if (!pcie_link_speed_stats) { + if (rc) { pr_err("no ibm,pcie-link-speed-stats property\n"); return 0; } @@ -142,6 +144,9 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge) case 0x02: bus->max_bus_speed = PCIE_SPEED_5_0GT; break; + case 0x04: + bus->max_bus_speed = PCIE_SPEED_8_0GT; + break; default: bus->max_bus_speed = PCI_SPEED_UNKNOWN; break; @@ -154,6 +159,9 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge) case 0x02: bus->cur_bus_speed = PCIE_SPEED_5_0GT; break; + case 0x04: + bus->cur_bus_speed = PCIE_SPEED_8_0GT; + break; default: bus->cur_bus_speed = PCI_SPEED_UNKNOWN; break; diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c index efe61374f6e..203cbf0dc10 100644 --- a/arch/powerpc/platforms/pseries/pci_dlpar.c +++ b/arch/powerpc/platforms/pseries/pci_dlpar.c @@ -37,15 +37,15 @@ find_bus_among_children(struct pci_bus *bus, struct device_node *dn) { struct pci_bus *child = NULL; - struct list_head *tmp; + struct pci_bus *tmp; struct device_node *busdn; busdn = pci_bus_to_OF_node(bus); if (busdn == dn) return bus; - list_for_each(tmp, &bus->children) { - child = find_bus_among_children(pci_bus_b(tmp), dn); + list_for_each_entry(tmp, &bus->children, node) { + child = find_bus_among_children(tmp, dn); if (child) break; }; diff --git a/arch/powerpc/platforms/pseries/processor_idle.c b/arch/powerpc/platforms/pseries/processor_idle.c deleted file mode 100644 index a166e38bd68..00000000000 --- a/arch/powerpc/platforms/pseries/processor_idle.c +++ /dev/null @@ -1,364 +0,0 @@ -/* - * processor_idle - idle state cpuidle driver. - * Adapted from drivers/idle/intel_idle.c and - * drivers/acpi/processor_idle.c - * - */ - -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/init.h> -#include <linux/moduleparam.h> -#include <linux/cpuidle.h> -#include <linux/cpu.h> -#include <linux/notifier.h> - -#include <asm/paca.h> -#include <asm/reg.h> -#include <asm/machdep.h> -#include <asm/firmware.h> -#include <asm/runlatch.h> -#include <asm/plpar_wrappers.h> - -struct cpuidle_driver pseries_idle_driver = { - .name = "pseries_idle", - .owner = THIS_MODULE, -}; - -#define MAX_IDLE_STATE_COUNT 2 - -static int max_idle_state = MAX_IDLE_STATE_COUNT - 1; -static struct cpuidle_device __percpu *pseries_cpuidle_devices; -static struct cpuidle_state *cpuidle_state_table; - -static inline void idle_loop_prolog(unsigned long *in_purr) -{ - *in_purr = mfspr(SPRN_PURR); - /* - * Indicate to the HV that we are idle. Now would be - * a good time to find other work to dispatch. - */ - get_lppaca()->idle = 1; -} - -static inline void idle_loop_epilog(unsigned long in_purr) -{ - u64 wait_cycles; - - wait_cycles = be64_to_cpu(get_lppaca()->wait_state_cycles); - wait_cycles += mfspr(SPRN_PURR) - in_purr; - get_lppaca()->wait_state_cycles = cpu_to_be64(wait_cycles); - get_lppaca()->idle = 0; -} - -static int snooze_loop(struct cpuidle_device *dev, - struct cpuidle_driver *drv, - int index) -{ - unsigned long in_purr; - int cpu = dev->cpu; - - idle_loop_prolog(&in_purr); - local_irq_enable(); - set_thread_flag(TIF_POLLING_NRFLAG); - - while ((!need_resched()) && cpu_online(cpu)) { - ppc64_runlatch_off(); - HMT_low(); - HMT_very_low(); - } - - HMT_medium(); - clear_thread_flag(TIF_POLLING_NRFLAG); - smp_mb(); - - idle_loop_epilog(in_purr); - - return index; -} - -static void check_and_cede_processor(void) -{ - /* - * Ensure our interrupt state is properly tracked, - * also checks if no interrupt has occurred while we - * were soft-disabled - */ - if (prep_irq_for_idle()) { - cede_processor(); -#ifdef CONFIG_TRACE_IRQFLAGS - /* Ensure that H_CEDE returns with IRQs on */ - if (WARN_ON(!(mfmsr() & MSR_EE))) - __hard_irq_enable(); -#endif - } -} - -static int dedicated_cede_loop(struct cpuidle_device *dev, - struct cpuidle_driver *drv, - int index) -{ - unsigned long in_purr; - - idle_loop_prolog(&in_purr); - get_lppaca()->donate_dedicated_cpu = 1; - - ppc64_runlatch_off(); - HMT_medium(); - check_and_cede_processor(); - - get_lppaca()->donate_dedicated_cpu = 0; - - idle_loop_epilog(in_purr); - - return index; -} - -static int shared_cede_loop(struct cpuidle_device *dev, - struct cpuidle_driver *drv, - int index) -{ - unsigned long in_purr; - - idle_loop_prolog(&in_purr); - - /* - * Yield the processor to the hypervisor. We return if - * an external interrupt occurs (which are driven prior - * to returning here) or if a prod occurs from another - * processor. When returning here, external interrupts - * are enabled. - */ - check_and_cede_processor(); - - idle_loop_epilog(in_purr); - - return index; -} - -/* - * States for dedicated partition case. - */ -static struct cpuidle_state dedicated_states[MAX_IDLE_STATE_COUNT] = { - { /* Snooze */ - .name = "snooze", - .desc = "snooze", - .flags = CPUIDLE_FLAG_TIME_VALID, - .exit_latency = 0, - .target_residency = 0, - .enter = &snooze_loop }, - { /* CEDE */ - .name = "CEDE", - .desc = "CEDE", - .flags = CPUIDLE_FLAG_TIME_VALID, - .exit_latency = 10, - .target_residency = 100, - .enter = &dedicated_cede_loop }, -}; - -/* - * States for shared partition case. - */ -static struct cpuidle_state shared_states[MAX_IDLE_STATE_COUNT] = { - { /* Shared Cede */ - .name = "Shared Cede", - .desc = "Shared Cede", - .flags = CPUIDLE_FLAG_TIME_VALID, - .exit_latency = 0, - .target_residency = 0, - .enter = &shared_cede_loop }, -}; - -void update_smt_snooze_delay(int cpu, int residency) -{ - struct cpuidle_driver *drv = cpuidle_get_driver(); - struct cpuidle_device *dev = per_cpu(cpuidle_devices, cpu); - - if (cpuidle_state_table != dedicated_states) - return; - - if (residency < 0) { - /* Disable the Nap state on that cpu */ - if (dev) - dev->states_usage[1].disable = 1; - } else - if (drv) - drv->states[1].target_residency = residency; -} - -static int pseries_cpuidle_add_cpu_notifier(struct notifier_block *n, - unsigned long action, void *hcpu) -{ - int hotcpu = (unsigned long)hcpu; - struct cpuidle_device *dev = - per_cpu_ptr(pseries_cpuidle_devices, hotcpu); - - if (dev && cpuidle_get_driver()) { - switch (action) { - case CPU_ONLINE: - case CPU_ONLINE_FROZEN: - cpuidle_pause_and_lock(); - cpuidle_enable_device(dev); - cpuidle_resume_and_unlock(); - break; - - case CPU_DEAD: - case CPU_DEAD_FROZEN: - cpuidle_pause_and_lock(); - cpuidle_disable_device(dev); - cpuidle_resume_and_unlock(); - break; - - default: - return NOTIFY_DONE; - } - } - return NOTIFY_OK; -} - -static struct notifier_block setup_hotplug_notifier = { - .notifier_call = pseries_cpuidle_add_cpu_notifier, -}; - -/* - * pseries_cpuidle_driver_init() - */ -static int pseries_cpuidle_driver_init(void) -{ - int idle_state; - struct cpuidle_driver *drv = &pseries_idle_driver; - - drv->state_count = 0; - - for (idle_state = 0; idle_state < MAX_IDLE_STATE_COUNT; ++idle_state) { - - if (idle_state > max_idle_state) - break; - - /* is the state not enabled? */ - if (cpuidle_state_table[idle_state].enter == NULL) - continue; - - drv->states[drv->state_count] = /* structure copy */ - cpuidle_state_table[idle_state]; - - drv->state_count += 1; - } - - return 0; -} - -/* pseries_idle_devices_uninit(void) - * unregister cpuidle devices and de-allocate memory - */ -static void pseries_idle_devices_uninit(void) -{ - int i; - struct cpuidle_device *dev; - - for_each_possible_cpu(i) { - dev = per_cpu_ptr(pseries_cpuidle_devices, i); - cpuidle_unregister_device(dev); - } - - free_percpu(pseries_cpuidle_devices); - return; -} - -/* pseries_idle_devices_init() - * allocate, initialize and register cpuidle device - */ -static int pseries_idle_devices_init(void) -{ - int i; - struct cpuidle_driver *drv = &pseries_idle_driver; - struct cpuidle_device *dev; - - pseries_cpuidle_devices = alloc_percpu(struct cpuidle_device); - if (pseries_cpuidle_devices == NULL) - return -ENOMEM; - - for_each_possible_cpu(i) { - dev = per_cpu_ptr(pseries_cpuidle_devices, i); - dev->state_count = drv->state_count; - dev->cpu = i; - if (cpuidle_register_device(dev)) { - printk(KERN_DEBUG \ - "cpuidle_register_device %d failed!\n", i); - return -EIO; - } - } - - return 0; -} - -/* - * pseries_idle_probe() - * Choose state table for shared versus dedicated partition - */ -static int pseries_idle_probe(void) -{ - - if (!firmware_has_feature(FW_FEATURE_SPLPAR)) - return -ENODEV; - - if (cpuidle_disable != IDLE_NO_OVERRIDE) - return -ENODEV; - - if (max_idle_state == 0) { - printk(KERN_DEBUG "pseries processor idle disabled.\n"); - return -EPERM; - } - - if (lppaca_shared_proc(get_lppaca())) - cpuidle_state_table = shared_states; - else - cpuidle_state_table = dedicated_states; - - return 0; -} - -static int __init pseries_processor_idle_init(void) -{ - int retval; - - retval = pseries_idle_probe(); - if (retval) - return retval; - - pseries_cpuidle_driver_init(); - retval = cpuidle_register_driver(&pseries_idle_driver); - if (retval) { - printk(KERN_DEBUG "Registration of pseries driver failed.\n"); - return retval; - } - - retval = pseries_idle_devices_init(); - if (retval) { - pseries_idle_devices_uninit(); - cpuidle_unregister_driver(&pseries_idle_driver); - return retval; - } - - register_cpu_notifier(&setup_hotplug_notifier); - printk(KERN_DEBUG "pseries_idle_driver registered\n"); - - return 0; -} - -static void __exit pseries_processor_idle_exit(void) -{ - - unregister_cpu_notifier(&setup_hotplug_notifier); - pseries_idle_devices_uninit(); - cpuidle_unregister_driver(&pseries_idle_driver); - - return; -} - -module_init(pseries_processor_idle_init); -module_exit(pseries_processor_idle_exit); - -MODULE_AUTHOR("Deepthi Dharwar <deepthi@linux.vnet.ibm.com>"); -MODULE_DESCRIPTION("Cpuidle driver for POWER"); -MODULE_LICENSE("GPL"); diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h index 99219530ea4..361add62abf 100644 --- a/arch/powerpc/platforms/pseries/pseries.h +++ b/arch/powerpc/platforms/pseries/pseries.h @@ -64,4 +64,6 @@ extern int dlpar_detach_node(struct device_node *); struct pci_host_bridge; int pseries_root_bridge_prepare(struct pci_host_bridge *bridge); +unsigned long pseries_memory_block_size(void); + #endif /* _PSERIES_PSERIES_H */ diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index 721c0586b28..9c5778e6ed4 100644 --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -236,7 +236,8 @@ static irqreturn_t ras_error_interrupt(int irq, void *dev_id) rtas_elog = (struct rtas_error_log *)ras_log_buf; - if ((status == 0) && (rtas_elog->severity >= RTAS_SEVERITY_ERROR_SYNC)) + if (status == 0 && + rtas_error_severity(rtas_elog) >= RTAS_SEVERITY_ERROR_SYNC) fatal = 1; else fatal = 0; @@ -300,13 +301,14 @@ static struct rtas_error_log *fwnmi_get_errinfo(struct pt_regs *regs) /* If it isn't an extended log we can use the per cpu 64bit buffer */ h = (struct rtas_error_log *)&savep[1]; - if (!h->extended) { + if (!rtas_error_extended(h)) { memcpy(&__get_cpu_var(mce_data_buf), h, sizeof(__u64)); errhdr = (struct rtas_error_log *)&__get_cpu_var(mce_data_buf); } else { - int len; + int len, error_log_length; - len = max_t(int, 8+h->extended_log_length, RTAS_ERROR_LOG_MAX); + error_log_length = 8 + rtas_error_extended_log_length(h); + len = max_t(int, error_log_length, RTAS_ERROR_LOG_MAX); memset(global_mce_data_buf, 0, RTAS_ERROR_LOG_MAX); memcpy(global_mce_data_buf, h, len); errhdr = (struct rtas_error_log *)global_mce_data_buf; @@ -350,23 +352,24 @@ int pSeries_system_reset_exception(struct pt_regs *regs) static int recover_mce(struct pt_regs *regs, struct rtas_error_log *err) { int recovered = 0; + int disposition = rtas_error_disposition(err); if (!(regs->msr & MSR_RI)) { /* If MSR_RI isn't set, we cannot recover */ recovered = 0; - } else if (err->disposition == RTAS_DISP_FULLY_RECOVERED) { + } else if (disposition == RTAS_DISP_FULLY_RECOVERED) { /* Platform corrected itself */ recovered = 1; - } else if (err->disposition == RTAS_DISP_LIMITED_RECOVERY) { + } else if (disposition == RTAS_DISP_LIMITED_RECOVERY) { /* Platform corrected itself but could be degraded */ printk(KERN_ERR "MCE: limited recovery, system may " "be degraded\n"); recovered = 1; } else if (user_mode(regs) && !is_global_init(current) && - err->severity == RTAS_SEVERITY_ERROR_SYNC) { + rtas_error_severity(err) == RTAS_SEVERITY_ERROR_SYNC) { /* * If we received a synchronous error when in userspace diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c index f93cdf55628..1c0a60d9886 100644 --- a/arch/powerpc/platforms/pseries/reconfig.c +++ b/arch/powerpc/platforms/pseries/reconfig.c @@ -12,7 +12,6 @@ */ #include <linux/kernel.h> -#include <linux/kref.h> #include <linux/notifier.h> #include <linux/proc_fs.h> #include <linux/slab.h> @@ -70,7 +69,7 @@ static int pSeries_reconfig_add_node(const char *path, struct property *proplist np->properties = proplist; of_node_set_flag(np, OF_DYNAMIC); - kref_init(&np->kref); + of_node_init(np); np->parent = derive_parent(path); if (IS_ERR(np->parent)) { diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index c1f19085870..f2f40e64658 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -39,7 +39,6 @@ #include <linux/irq.h> #include <linux/seq_file.h> #include <linux/root_dev.h> -#include <linux/cpuidle.h> #include <linux/of.h> #include <linux/kexec.h> @@ -72,7 +71,7 @@ int CMO_PrPSP = -1; int CMO_SecPSP = -1; -unsigned long CMO_PageSize = (ASM_CONST(1) << IOMMU_PAGE_SHIFT); +unsigned long CMO_PageSize = (ASM_CONST(1) << IOMMU_PAGE_SHIFT_4K); EXPORT_SYMBOL(CMO_PageSize); int fwnmi_active; /* TRUE if an FWNMI handler is present */ @@ -356,29 +355,24 @@ early_initcall(alloc_dispatch_log_kmem_cache); static void pseries_lpar_idle(void) { - /* This would call on the cpuidle framework, and the back-end pseries - * driver to go to idle states + /* + * Default handler to go into low thread priority and possibly + * low power mode by cedeing processor to hypervisor */ - if (cpuidle_idle_call()) { - /* On error, execute default handler - * to go into low thread priority and possibly - * low power mode by cedeing processor to hypervisor - */ - /* Indicate to hypervisor that we are idle. */ - get_lppaca()->idle = 1; + /* Indicate to hypervisor that we are idle. */ + get_lppaca()->idle = 1; - /* - * Yield the processor to the hypervisor. We return if - * an external interrupt occurs (which are driven prior - * to returning here) or if a prod occurs from another - * processor. When returning here, external interrupts - * are enabled. - */ - cede_processor(); + /* + * Yield the processor to the hypervisor. We return if + * an external interrupt occurs (which are driven prior + * to returning here) or if a prod occurs from another + * processor. When returning here, external interrupts + * are enabled. + */ + cede_processor(); - get_lppaca()->idle = 0; - } + get_lppaca()->idle = 0; } /* @@ -430,8 +424,7 @@ static void pSeries_machine_kexec(struct kimage *image) { long rc; - if (firmware_has_feature(FW_FEATURE_SET_MODE) && - (image->type != KEXEC_TYPE_CRASH)) { + if (firmware_has_feature(FW_FEATURE_SET_MODE)) { rc = pSeries_disable_reloc_on_exc(); if (rc != H_SUCCESS) pr_warning("Warning: Failed to disable relocation on " @@ -470,7 +463,7 @@ static long pseries_little_endian_exceptions(void) static void __init pSeries_setup_arch(void) { - panic_timeout = 10; + set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT); /* Discover PIC type and setup ppc_md accordingly */ pseries_discover_pic(); @@ -517,7 +510,11 @@ static void __init pSeries_setup_arch(void) static int __init pSeries_init_panel(void) { /* Manually leave the kernel version on the panel. */ +#ifdef __BIG_ENDIAN__ ppc_md.progress("Linux ppc64\n", 0); +#else + ppc_md.progress("Linux ppc64le\n", 0); +#endif ppc_md.progress(init_utsname()->version, 0); return 0; @@ -569,7 +566,7 @@ void pSeries_cmo_feature_init(void) { char *ptr, *key, *value, *end; int call_status; - int page_order = IOMMU_PAGE_SHIFT; + int page_order = IOMMU_PAGE_SHIFT_4K; pr_debug(" -> fw_cmo_feature_init()\n"); spin_lock(&rtas_data_buf_lock); @@ -672,7 +669,7 @@ static int __init pseries_probe_fw_features(unsigned long node, void *data) { const char *prop; - unsigned long len; + int len; static int hypertas_found; static int vec5_found; @@ -705,7 +702,7 @@ static int __init pseries_probe_fw_features(unsigned long node, static int __init pSeries_probe(void) { unsigned long root = of_get_flat_dt_root(); - char *dtype = of_get_flat_dt_prop(root, "device_type", NULL); + const char *dtype = of_get_flat_dt_prop(root, "device_type", NULL); if (dtype == NULL) return 0; @@ -813,4 +810,7 @@ define_machine(pseries) { #ifdef CONFIG_KEXEC .machine_kexec = pSeries_machine_kexec, #endif +#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE + .memory_block_size = pseries_memory_block_size, +#endif }; diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c index 24f58cb0a54..a3555b10c1a 100644 --- a/arch/powerpc/platforms/pseries/smp.c +++ b/arch/powerpc/platforms/pseries/smp.c @@ -44,6 +44,7 @@ #include <asm/xics.h> #include <asm/dbell.h> #include <asm/plpar_wrappers.h> +#include <asm/code-patching.h> #include "pseries.h" #include "offline_states.h" @@ -96,8 +97,8 @@ int smp_query_cpu_stopped(unsigned int pcpu) static inline int smp_startup_cpu(unsigned int lcpu) { int status; - unsigned long start_here = __pa((u32)*((unsigned long *) - generic_secondary_smp_init)); + unsigned long start_here = + __pa(ppc_function_entry(generic_secondary_smp_init)); unsigned int pcpu; int start_cpu; diff --git a/arch/powerpc/platforms/pseries/suspend.c b/arch/powerpc/platforms/pseries/suspend.c index 16a255255d3..b87b97849d4 100644 --- a/arch/powerpc/platforms/pseries/suspend.c +++ b/arch/powerpc/platforms/pseries/suspend.c @@ -26,6 +26,7 @@ #include <asm/mmu.h> #include <asm/rtas.h> #include <asm/topology.h> +#include "../../kernel/cacheinfo.h" static u64 stream_id; static struct device suspend_dev; @@ -79,6 +80,23 @@ static int pseries_suspend_cpu(void) } /** + * pseries_suspend_enable_irqs + * + * Post suspend configuration updates + * + **/ +static void pseries_suspend_enable_irqs(void) +{ + /* + * Update configuration which can be modified based on device tree + * changes during resume. + */ + cacheinfo_cpu_offline(smp_processor_id()); + post_mobility_fixup(); + cacheinfo_cpu_online(smp_processor_id()); +} + +/** * pseries_suspend_enter - Final phase of hibernation * * Return value: @@ -174,7 +192,30 @@ out: return rc; } -static DEVICE_ATTR(hibernate, S_IWUSR, NULL, store_hibernate); +#define USER_DT_UPDATE 0 +#define KERN_DT_UPDATE 1 + +/** + * show_hibernate - Report device tree update responsibilty + * @dev: subsys root device + * @attr: device attribute struct + * @buf: buffer + * + * Report whether a device tree update is performed by the kernel after a + * resume, or if drmgr must coordinate the update from user space. + * + * Return value: + * 0 if drmgr is to initiate update, and 1 otherwise + **/ +static ssize_t show_hibernate(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + return sprintf(buf, "%d\n", KERN_DT_UPDATE); +} + +static DEVICE_ATTR(hibernate, S_IWUSR | S_IRUGO, + show_hibernate, store_hibernate); static struct bus_type suspend_subsys = { .name = "power", @@ -235,6 +276,7 @@ static int __init pseries_suspend_init(void) return rc; ppc_md.suspend_disable_cpu = pseries_suspend_cpu; + ppc_md.suspend_enable_irqs = pseries_suspend_enable_irqs; suspend_set_ops(&pseries_suspend_ops); return 0; } |