diff options
Diffstat (limited to 'arch/powerpc/platforms/pseries')
31 files changed, 1442 insertions, 1321 deletions
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig index 1bd3399146e..756b482f819 100644 --- a/arch/powerpc/platforms/pseries/Kconfig +++ b/arch/powerpc/platforms/pseries/Kconfig @@ -19,8 +19,9 @@ config PPC_PSERIES select ZLIB_DEFLATE select PPC_DOORBELL select HAVE_CONTEXT_TRACKING - select HOTPLUG if SMP select HOTPLUG_CPU if SMP + select ARCH_RANDOM + select PPC_DOORBELL default y config PPC_SPLPAR @@ -35,7 +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 @@ -111,6 +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 @@ -120,12 +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 8ae01038131..03480796af9 100644 --- a/arch/powerpc/platforms/pseries/Makefile +++ b/arch/powerpc/platforms/pseries/Makefile @@ -3,7 +3,7 @@ ccflags-$(CONFIG_PPC_PSERIES_DEBUG) += -DDEBUG obj-y := lpar.o hvCall.o nvram.o reconfig.o \ setup.o iommu.o event_sources.o ras.o \ - firmware.o power.o dlpar.o mobility.o + firmware.o power.o dlpar.o mobility.o rng.o obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_SCANLOG) += scanlog.o obj-$(CONFIG_EEH) += eeh_pseries.o @@ -21,7 +21,7 @@ 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 ($(CONFIG_PPC_PSERIES),y) obj-$(CONFIG_SUSPEND) += suspend.o diff --git a/arch/powerpc/platforms/pseries/cmm.c b/arch/powerpc/platforms/pseries/cmm.c index c638535753d..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> @@ -40,8 +39,7 @@ #include <asm/pgalloc.h> #include <asm/uaccess.h> #include <linux/memory.h> - -#include "plpar_wrappers.h" +#include <asm/plpar_wrappers.h> #define CMM_DRIVER_VERSION "1.0.0" #define CMM_DEFAULT_DELAY 1 diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c index a1a7b9a67ff..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> @@ -63,26 +62,32 @@ static struct property *dlpar_parse_cc_property(struct cc_workarea *ccwa) return prop; } -static struct device_node *dlpar_parse_cc_node(struct cc_workarea *ccwa) +static struct device_node *dlpar_parse_cc_node(struct cc_workarea *ccwa, + const char *path) { struct device_node *dn; char *name; + /* If parent node path is "/" advance path to NULL terminator to + * prevent double leading slashs in full_name. + */ + if (!path[1]) + path++; + dn = kzalloc(sizeof(*dn), GFP_KERNEL); if (!dn) return NULL; - /* The configure connector reported name does not contain a - * preceding '/', so we allocate a buffer large enough to - * prepend this to the full_name. - */ name = (char *)ccwa + ccwa->name_offset; - dn->full_name = kasprintf(GFP_KERNEL, "/%s", name); + dn->full_name = kasprintf(GFP_KERNEL, "%s/%s", path, name); if (!dn->full_name) { kfree(dn); return NULL; } + of_node_set_flag(dn, OF_DYNAMIC); + of_node_init(dn); + return dn; } @@ -120,7 +125,8 @@ void dlpar_free_cc_nodes(struct device_node *dn) #define CALL_AGAIN -2 #define ERR_CFG_USE -9003 -struct device_node *dlpar_configure_connector(u32 drc_index) +struct device_node *dlpar_configure_connector(u32 drc_index, + struct device_node *parent) { struct device_node *dn; struct device_node *first_dn = NULL; @@ -129,6 +135,7 @@ struct device_node *dlpar_configure_connector(u32 drc_index) struct property *last_property = NULL; struct cc_workarea *ccwa; char *data_buf; + const char *parent_path = parent->full_name; int cc_token; int rc = -1; @@ -162,7 +169,7 @@ struct device_node *dlpar_configure_connector(u32 drc_index) break; case NEXT_SIBLING: - dn = dlpar_parse_cc_node(ccwa); + dn = dlpar_parse_cc_node(ccwa, parent_path); if (!dn) goto cc_error; @@ -172,13 +179,17 @@ struct device_node *dlpar_configure_connector(u32 drc_index) break; case NEXT_CHILD: - dn = dlpar_parse_cc_node(ccwa); + if (first_dn) + parent_path = last_dn->full_name; + + dn = dlpar_parse_cc_node(ccwa, parent_path); if (!dn) goto cc_error; - if (!first_dn) + if (!first_dn) { + dn->parent = parent; first_dn = dn; - else { + } else { dn->parent = last_dn; if (last_dn) last_dn->child = dn; @@ -202,6 +213,7 @@ struct device_node *dlpar_configure_connector(u32 drc_index) case PREV_PARENT: last_dn = last_dn->parent; + parent_path = last_dn->parent->full_name; break; case CALL_AGAIN: @@ -256,8 +268,6 @@ int dlpar_attach_node(struct device_node *dn) { int rc; - of_node_set_flag(dn, OF_DYNAMIC); - kref_init(&dn->kref); dn->parent = derive_parent(dn->full_name); if (!dn->parent) return -ENOMEM; @@ -275,8 +285,15 @@ int dlpar_attach_node(struct device_node *dn) int dlpar_detach_node(struct device_node *dn) { + struct device_node *child; int rc; + child = of_get_next_child(dn, NULL); + while (child) { + dlpar_detach_node(child); + child = of_get_next_child(dn, child); + } + rc = of_detach_node(dn); if (rc) return rc; @@ -382,57 +399,42 @@ out: static ssize_t dlpar_cpu_probe(const char *buf, size_t count) { - struct device_node *dn; + struct device_node *dn, *parent; unsigned long drc_index; - char *cpu_name; int rc; - cpu_hotplug_driver_lock(); rc = strict_strtoul(buf, 0, &drc_index); - if (rc) { - rc = -EINVAL; - goto out; - } + if (rc) + return -EINVAL; - dn = dlpar_configure_connector(drc_index); - if (!dn) { - rc = -EINVAL; - goto out; - } + parent = of_find_node_by_path("/cpus"); + if (!parent) + return -ENODEV; - /* configure-connector reports cpus as living in the base - * directory of the device tree. CPUs actually live in the - * cpus directory so we need to fixup the full_name. - */ - cpu_name = kasprintf(GFP_KERNEL, "/cpus%s", dn->full_name); - if (!cpu_name) { - dlpar_free_cc_nodes(dn); - rc = -ENOMEM; - goto out; - } + dn = dlpar_configure_connector(drc_index, parent); + if (!dn) + return -EINVAL; - kfree(dn->full_name); - dn->full_name = cpu_name; + of_node_put(parent); rc = dlpar_acquire_drc(drc_index); if (rc) { dlpar_free_cc_nodes(dn); - rc = -EINVAL; - goto out; + return -EINVAL; } rc = dlpar_attach_node(dn); if (rc) { dlpar_release_drc(drc_index); dlpar_free_cc_nodes(dn); - goto out; + return rc; } rc = dlpar_online_cpu(dn); -out: - cpu_hotplug_driver_unlock(); + if (rc) + return rc; - return rc ? rc : count; + return count; } static int dlpar_offline_cpu(struct device_node *dn) @@ -505,30 +507,27 @@ static ssize_t dlpar_cpu_release(const char *buf, size_t count) return -EINVAL; } - cpu_hotplug_driver_lock(); rc = dlpar_offline_cpu(dn); if (rc) { of_node_put(dn); - rc = -EINVAL; - goto out; + return -EINVAL; } rc = dlpar_release_drc(*drc_index); if (rc) { of_node_put(dn); - goto out; + return rc; } rc = dlpar_detach_node(dn); if (rc) { dlpar_acquire_drc(*drc_index); - goto out; + return rc; } of_node_put(dn); -out: - cpu_hotplug_driver_unlock(); - return rc ? rc : count; + + return count; } static int __init pseries_dlpar_init(void) diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c index 0cc0ac07a55..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> @@ -29,8 +28,7 @@ #include <asm/firmware.h> #include <asm/lppaca.h> #include <asm/debug.h> - -#include "plpar_wrappers.h" +#include <asm/plpar_wrappers.h> struct dtl { struct dtl_entry *buf; @@ -87,7 +85,7 @@ static void consume_dtle(struct dtl_entry *dtle, u64 index) barrier(); /* check for hypervisor ring buffer overflow, ignore this entry if so */ - if (index + N_DISPATCH_LOG < vpa->dtl_idx) + if (index + N_DISPATCH_LOG < be64_to_cpu(vpa->dtl_idx)) return; ++wp; diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index b456b157d33..0bec0c02c5e 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -133,6 +133,78 @@ static int pseries_eeh_init(void) return 0; } +static int pseries_eeh_cap_start(struct device_node *dn) +{ + struct pci_dn *pdn = PCI_DN(dn); + u32 status; + + if (!pdn) + return 0; + + rtas_read_config(pdn, PCI_STATUS, 2, &status); + if (!(status & PCI_STATUS_CAP_LIST)) + return 0; + + return PCI_CAPABILITY_LIST; +} + + +static int pseries_eeh_find_cap(struct device_node *dn, int cap) +{ + struct pci_dn *pdn = PCI_DN(dn); + int pos = pseries_eeh_cap_start(dn); + int cnt = 48; /* Maximal number of capabilities */ + u32 id; + + if (!pos) + return 0; + + while (cnt--) { + rtas_read_config(pdn, pos, 1, &pos); + if (pos < 0x40) + break; + pos &= ~3; + rtas_read_config(pdn, pos + PCI_CAP_LIST_ID, 1, &id); + if (id == 0xff) + break; + if (id == cap) + return pos; + pos += PCI_CAP_LIST_NEXT; + } + + 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 @@ -146,30 +218,54 @@ static void *pseries_eeh_of_probe(struct device_node *dn, void *flag) { struct eeh_dev *edev; struct eeh_pe pe; - const u32 *class_code, *vendor_id, *device_id; - const u32 *regs; + struct pci_dn *pdn = PCI_DN(dn); + const __be32 *classp, *vendorp, *devicep; + u32 class_code; + const __be32 *regs; + u32 pcie_flags; int enable = 0; int ret; /* Retrieve OF node and eeh device */ edev = of_node_to_eeh_dev(dn); - if (!of_device_is_available(dn)) + if (edev->pe || !of_device_is_available(dn)) return NULL; /* Retrieve class/vendor/device IDs */ - class_code = of_get_property(dn, "class-code", NULL); - vendor_id = of_get_property(dn, "vendor-id", NULL); - device_id = of_get_property(dn, "device-id", NULL); + classp = of_get_property(dn, "class-code", NULL); + vendorp = of_get_property(dn, "vendor-id", NULL); + devicep = of_get_property(dn, "device-id", NULL); /* Skip for bad OF node or PCI-ISA bridge */ - if (!class_code || !vendor_id || !device_id) + if (!classp || !vendorp || !devicep) return NULL; if (dn->type && !strcmp(dn->type, "isa")) return NULL; - /* Update class code and mode of eeh device */ - edev->class_code = *class_code; - edev->mode = 0; + class_code = of_read_number(classp, 1); + + /* + * Update class code and mode of eeh device. We need + * correctly reflects that current device is root port + * 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; + if (edev->pcie_cap) { + rtas_read_config(pdn, edev->pcie_cap + PCI_EXP_FLAGS, + 2, &pcie_flags); + pcie_flags = (pcie_flags & PCI_EXP_FLAGS_TYPE) >> 4; + if (pcie_flags == PCI_EXP_TYPE_ROOT_PORT) + edev->mode |= EEH_DEV_ROOT_PORT; + else if (pcie_flags == PCI_EXP_TYPE_DOWNSTREAM) + edev->mode |= EEH_DEV_DS_PORT; + } + } /* Retrieve the device address */ regs = of_get_property(dn, "reg", NULL); @@ -182,12 +278,12 @@ static void *pseries_eeh_of_probe(struct device_node *dn, void *flag) /* Initialize the fake PE */ memset(&pe, 0, sizeof(struct eeh_pe)); pe.phb = edev->phb; - pe.config_addr = regs[0]; + pe.config_addr = of_read_number(regs, 1); /* Enable EEH on the device */ ret = eeh_ops->set_option(&pe, EEH_OPT_ENABLE); if (!ret) { - edev->config_addr = regs[0]; + edev->config_addr = of_read_number(regs, 1); /* Retrieve PE address */ edev->pe_config_addr = eeh_ops->get_pe_addr(&pe); pe.addr = edev->pe_config_addr; @@ -201,7 +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", @@ -400,6 +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; } @@ -435,11 +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; } @@ -625,7 +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/event_sources.c b/arch/powerpc/platforms/pseries/event_sources.c index 2605c310166..18380e8f6df 100644 --- a/arch/powerpc/platforms/pseries/event_sources.c +++ b/arch/powerpc/platforms/pseries/event_sources.c @@ -25,7 +25,7 @@ void request_event_sources_irqs(struct device_node *np, const char *name) { int i, index, count = 0; - struct of_irq oirq; + struct of_phandle_args oirq; const u32 *opicprop; unsigned int opicplen; unsigned int virqs[16]; @@ -55,13 +55,11 @@ void request_event_sources_irqs(struct device_node *np, /* Else use normal interrupt tree parsing */ else { /* First try to do a proper OF tree parsing */ - for (index = 0; of_irq_map_one(np, index, &oirq) == 0; + for (index = 0; of_irq_parse_one(np, index, &oirq) == 0; index++) { if (count > 15) break; - virqs[count] = irq_create_of_mapping(oirq.controller, - oirq.specifier, - oirq.size); + virqs[count] = irq_create_of_mapping(&oirq); if (virqs[count] == NO_IRQ) { pr_err("event-sources: Unable to allocate " "interrupt number for %s\n", diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index 217ca5c75b2..20d62975856 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -30,16 +30,12 @@ #include <asm/machdep.h> #include <asm/vdso_datapage.h> #include <asm/xics.h> -#include "plpar_wrappers.h" +#include <asm/plpar_wrappers.h> + #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; @@ -92,15 +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"); } @@ -123,7 +125,7 @@ static void pseries_mach_cpu_die(void) cede_latency_hint = 2; get_lppaca()->idle = 1; - if (!get_lppaca()->shared_proc) + if (!lppaca_shared_proc(get_lppaca())) get_lppaca()->donate_dedicated_cpu = 1; while (get_preferred_offline_state(cpu) == CPU_STATE_INACTIVE) { @@ -137,7 +139,7 @@ static void pseries_mach_cpu_die(void) local_irq_disable(); - if (!get_lppaca()->shared_proc) + if (!lppaca_shared_proc(get_lppaca())) get_lppaca()->donate_dedicated_cpu = 0; get_lppaca()->idle = 0; @@ -391,10 +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"); @@ -419,4 +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 9a432de363b..7995135170a 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -10,15 +10,18 @@ */ #include <linux/of.h> +#include <linux/of_address.h> #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; @@ -61,72 +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; @@ -151,8 +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, @@ -160,13 +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; @@ -206,7 +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; @@ -252,10 +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; @@ -275,6 +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/hvconsole.c b/arch/powerpc/platforms/pseries/hvconsole.c index b344f94b040..849b29b3e9a 100644 --- a/arch/powerpc/platforms/pseries/hvconsole.c +++ b/arch/powerpc/platforms/pseries/hvconsole.c @@ -28,7 +28,7 @@ #include <linux/errno.h> #include <asm/hvcall.h> #include <asm/hvconsole.h> -#include "plpar_wrappers.h" +#include <asm/plpar_wrappers.h> /** * hvc_get_chars - retrieve characters from firmware for denoted vterm adatper @@ -40,10 +40,16 @@ */ int hvc_get_chars(uint32_t vtermno, char *buf, int count) { - unsigned long got; + long ret; + unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; + unsigned long *lbuf = (unsigned long *)buf; + + ret = plpar_hcall(H_GET_TERM_CHAR, retbuf, vtermno); + lbuf[0] = be64_to_cpu(retbuf[1]); + lbuf[1] = be64_to_cpu(retbuf[2]); - if (plpar_get_term_char(vtermno, &got, buf) == H_SUCCESS) - return got; + if (ret == H_SUCCESS) + return retbuf[0]; return 0; } @@ -69,8 +75,9 @@ int hvc_put_chars(uint32_t vtermno, const char *buf, int count) if (count > MAX_VIO_PUT_CHARS) count = MAX_VIO_PUT_CHARS; - ret = plpar_hcall_norets(H_PUT_TERM_CHAR, vtermno, count, lbuf[0], - lbuf[1]); + ret = plpar_hcall_norets(H_PUT_TERM_CHAR, vtermno, count, + cpu_to_be64(lbuf[0]), + cpu_to_be64(lbuf[1])); if (ret == H_SUCCESS) return count; if (ret == H_BUSY) 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 23fc1dcf443..33b552ffbe5 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -48,12 +48,11 @@ #include <asm/ppc-pci.h> #include <asm/udbg.h> #include <asm/mmzone.h> - -#include "plpar_wrappers.h" +#include <asm/plpar_wrappers.h> static void tce_invalidate_pSeries_sw(struct iommu_table *tbl, - u64 *startp, u64 *endp) + __be64 *startp, __be64 *endp) { u64 __iomem *invalidate = (u64 __iomem *)tbl->it_index; unsigned long start, end, inc; @@ -87,7 +86,7 @@ static int tce_build_pSeries(struct iommu_table *tbl, long index, struct dma_attrs *attrs) { u64 proto_tce; - u64 *tcep, *tces; + __be64 *tcep, *tces; u64 rpn; proto_tce = TCE_PCI_READ; // Read allowed @@ -95,12 +94,12 @@ static int tce_build_pSeries(struct iommu_table *tbl, long index, if (direction != DMA_TO_DEVICE) proto_tce |= TCE_PCI_WRITE; - tces = tcep = ((u64 *)tbl->it_base) + index; + tces = tcep = ((__be64 *)tbl->it_base) + index; while (npages--) { /* can't move this out since we might cross MEMBLOCK boundary */ rpn = __pa(uaddr) >> TCE_SHIFT; - *tcep = proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT; + *tcep = cpu_to_be64(proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT); uaddr += TCE_PAGE_SIZE; tcep++; @@ -114,9 +113,9 @@ static int tce_build_pSeries(struct iommu_table *tbl, long index, static void tce_free_pSeries(struct iommu_table *tbl, long index, long npages) { - u64 *tcep, *tces; + __be64 *tcep, *tces; - tces = tcep = ((u64 *)tbl->it_base) + index; + tces = tcep = ((__be64 *)tbl->it_base) + index; while (npages--) *(tcep++) = 0; @@ -127,11 +126,11 @@ static void tce_free_pSeries(struct iommu_table *tbl, long index, long npages) static unsigned long tce_get_pseries(struct iommu_table *tbl, long index) { - u64 *tcep; + __be64 *tcep; - tcep = ((u64 *)tbl->it_base) + index; + tcep = ((__be64 *)tbl->it_base) + index; - return *tcep; + return be64_to_cpu(*tcep); } static void tce_free_pSeriesLP(struct iommu_table*, long, long); @@ -178,7 +177,7 @@ static int tce_build_pSeriesLP(struct iommu_table *tbl, long tcenum, return ret; } -static DEFINE_PER_CPU(u64 *, tce_page); +static DEFINE_PER_CPU(__be64 *, tce_page); static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, long npages, unsigned long uaddr, @@ -187,7 +186,7 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, { u64 rc = 0; u64 proto_tce; - u64 *tcep; + __be64 *tcep; u64 rpn; long l, limit; long tcenum_start = tcenum, npages_start = npages; @@ -207,7 +206,7 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, * from iommu_alloc{,_sg}() */ if (!tcep) { - tcep = (u64 *)__get_free_page(GFP_ATOMIC); + tcep = (__be64 *)__get_free_page(GFP_ATOMIC); /* If allocation fails, fall back to the loop implementation */ if (!tcep) { local_irq_restore(flags); @@ -231,7 +230,7 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, limit = min_t(long, npages, 4096/TCE_ENTRY_SIZE); for (l = 0; l < limit; l++) { - tcep[l] = proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT; + tcep[l] = cpu_to_be64(proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT); rpn++; } @@ -330,16 +329,16 @@ struct direct_window { /* Dynamic DMA Window support */ struct ddw_query_response { - u32 windows_available; - u32 largest_available_block; - u32 page_size; - u32 migration_capable; + __be32 windows_available; + __be32 largest_available_block; + __be32 page_size; + __be32 migration_capable; }; struct ddw_create_response { - u32 liobn; - u32 addr_hi; - u32 addr_lo; + __be32 liobn; + __be32 addr_hi; + __be32 addr_lo; }; static LIST_HEAD(direct_window_list); @@ -393,7 +392,8 @@ static int tce_setrange_multi_pSeriesLP(unsigned long start_pfn, unsigned long num_pfn, const void *arg) { const struct dynamic_dma_window_prop *maprange = arg; - u64 *tcep, tce_size, num_tce, dma_offset, next, proto_tce, liobn; + u64 tce_size, num_tce, dma_offset, next, proto_tce, liobn; + __be64 *tcep; u32 tce_shift; u64 rc = 0; long l, limit; @@ -402,7 +402,7 @@ static int tce_setrange_multi_pSeriesLP(unsigned long start_pfn, tcep = __get_cpu_var(tce_page); if (!tcep) { - tcep = (u64 *)__get_free_page(GFP_ATOMIC); + tcep = (__be64 *)__get_free_page(GFP_ATOMIC); if (!tcep) { local_irq_enable(); return -ENOMEM; @@ -436,7 +436,7 @@ static int tce_setrange_multi_pSeriesLP(unsigned long start_pfn, dma_offset = next + be64_to_cpu(maprange->dma_base); for (l = 0; l < limit; l++) { - tcep[l] = proto_tce | next; + tcep[l] = cpu_to_be64(proto_tce | next); next += tce_size; } @@ -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; @@ -530,18 +531,19 @@ static void iommu_table_setparms(struct pci_controller *phb, static void iommu_table_setparms_lpar(struct pci_controller *phb, struct device_node *dn, struct iommu_table *tbl, - const void *dma_window) + const __be32 *dma_window) { unsigned long offset, size; 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) @@ -630,7 +632,7 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus) struct iommu_table *tbl; struct device_node *dn, *pdn; struct pci_dn *ppci; - const void *dma_window = NULL; + const __be32 *dma_window = NULL; dn = pci_bus_to_OF_node(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); @@ -781,7 +778,7 @@ static u64 find_existing_ddw(struct device_node *pdn) list_for_each_entry(window, &direct_window_list, list) { if (window->device == pdn) { direct64 = window->prop; - dma_addr = direct64->dma_base; + dma_addr = be64_to_cpu(direct64->dma_base); break; } } @@ -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) { /* @@ -1044,34 +963,34 @@ 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 (query.page_size & 4) { + if (be32_to_cpu(query.page_size) & 4) { page_shift = 24; /* 16MB */ - } else if (query.page_size & 2) { + } else if (be32_to_cpu(query.page_size) & 2) { page_shift = 16; /* 64kB */ - } else if (query.page_size & 1) { + } else if (be32_to_cpu(query.page_size) & 1) { page_shift = 12; /* 4kB */ } 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 */ max_addr = memory_hotplug_max(); - if (query.largest_available_block < (max_addr >> page_shift)) { + if (be32_to_cpu(query.largest_available_block) < (max_addr >> page_shift)) { 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); @@ -1086,7 +1005,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) if (ret != 0) goto out_free_prop; - ddwprop->liobn = cpu_to_be32(create.liobn); + ddwprop->liobn = create.liobn; ddwprop->dma_base = cpu_to_be64(of_read_number(&create.addr_hi, 2)); ddwprop->tce_shift = cpu_to_be32(page_shift); ddwprop->window_shift = cpu_to_be32(len); @@ -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) @@ -1152,7 +1069,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) { struct device_node *pdn, *dn; struct iommu_table *tbl; - const void *dma_window = NULL; + const __be32 *dma_window = NULL; struct pci_dn *pci; pr_debug("pci_dma_dev_setup_pSeriesLP: %s\n", pci_name(dev)); @@ -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) @@ -1201,7 +1118,7 @@ static int dma_set_mask_pSeriesLP(struct device *dev, u64 dma_mask) bool ddw_enabled = false; struct device_node *pdn, *dn; struct pci_dev *pdev; - const void *dma_window = NULL; + const __be32 *dma_window = NULL; u64 dma_offset; if (!dev->dma_mask) diff --git a/arch/powerpc/platforms/pseries/kexec.c b/arch/powerpc/platforms/pseries/kexec.c index 7d94bdc63d5..13fa95b3aa8 100644 --- a/arch/powerpc/platforms/pseries/kexec.c +++ b/arch/powerpc/platforms/pseries/kexec.c @@ -17,9 +17,9 @@ #include <asm/mpic.h> #include <asm/xics.h> #include <asm/smp.h> +#include <asm/plpar_wrappers.h> #include "pseries.h" -#include "plpar_wrappers.h" static void pseries_kexec_cpu_down(int crash_shutdown, int secondary) { diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 02d6e21619b..b02af9ef3ff 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -41,8 +41,8 @@ #include <asm/smp.h> #include <asm/trace.h> #include <asm/firmware.h> +#include <asm/plpar_wrappers.h> -#include "plpar_wrappers.h" #include "pseries.h" /* Flag bits for H_BULK_REMOVE */ @@ -68,6 +68,12 @@ void vpa_init(int cpu) struct paca_struct *pp; struct dtl_entry *dtl; + /* + * The spec says it "may be problematic" if CPU x registers the VPA of + * CPU y. We should never do that, but wail if we ever do. + */ + WARN_ON(cpu != smp_processor_id()); + if (cpu_has_feature(CPU_FTR_ALTIVEC)) lppaca_of(cpu).vmxregs_in_use = 1; @@ -86,7 +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) @@ -106,7 +112,7 @@ void vpa_init(int cpu) lppaca_of(cpu).dtl_idx = 0; /* hypervisor reads buffer length from this field */ - dtl->enqueue_to_dispatch_time = DISPATCH_LOG_BYTES; + dtl->enqueue_to_dispatch_time = cpu_to_be32(DISPATCH_LOG_BYTES); ret = register_dtl(hwcpu, __pa(dtl)); if (ret) pr_err("WARNING: DTL registration of cpu %d (hw %d) " @@ -146,8 +152,9 @@ static long pSeries_lpar_hpte_insert(unsigned long hpte_group, flags = 0; /* Make pHyp happy */ - if ((rflags & _PAGE_NO_CACHE) & !(rflags & _PAGE_WRITETHRU)) - hpte_r &= ~_PAGE_COHERENT; + if ((rflags & _PAGE_NO_CACHE) && !(rflags & _PAGE_WRITETHRU)) + hpte_r &= ~HPTE_R_M; + if (firmware_has_feature(FW_FEATURE_XCMO) && !(hpte_r & HPTE_R_N)) flags |= H_COALESCE_CAND; @@ -239,6 +246,23 @@ static void pSeries_lpar_hptab_clear(void) &(ptes[j].pteh), &(ptes[j].ptel)); } } + +#ifdef __LITTLE_ENDIAN__ + /* Reset exceptions to big endian */ + if (firmware_has_feature(FW_FEATURE_SET_MODE)) { + long rc; + + rc = pseries_big_endian_exceptions(); + /* + * At this point it is unlikely panic() will get anything + * out to the user, but at least this will stop us from + * continuing on further and creating an even more + * difficult to debug situation. + */ + if (rc) + panic("Could not enable big endian exceptions"); + } +#endif } /* @@ -724,7 +748,7 @@ int h_get_mpp(struct hvcall_mpp_data *mpp_data) mpp_data->mem_weight = (retbuf[3] >> 7 * 8) & 0xff; mpp_data->unallocated_mem_weight = (retbuf[3] >> 6 * 8) & 0xff; - mpp_data->unallocated_entitlement = retbuf[3] & 0xffffffffffff; + mpp_data->unallocated_entitlement = retbuf[3] & 0xffffffffffffUL; mpp_data->pool_size = retbuf[4]; mpp_data->loan_request = retbuf[5]; diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c new file mode 100644 index 00000000000..c9fecf09b8f --- /dev/null +++ b/arch/powerpc/platforms/pseries/lparcfg.c @@ -0,0 +1,710 @@ +/* + * PowerPC64 LPAR Configuration Information Driver + * + * Dave Engebretsen engebret@us.ibm.com + * Copyright (c) 2003 Dave Engebretsen + * Will Schmidt willschm@us.ibm.com + * SPLPAR updates, Copyright (c) 2003 Will Schmidt IBM Corporation. + * seq_file updates, Copyright (c) 2004 Will Schmidt IBM Corporation. + * Nathan Lynch nathanl@austin.ibm.com + * Added lparcfg_write, Copyright (C) 2004 Nathan Lynch IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * This driver creates a proc file at /proc/ppc64/lparcfg which contains + * keyword - value pairs that specify the configuration of the partition. + */ + +#include <linux/module.h> +#include <linux/types.h> +#include <linux/errno.h> +#include <linux/proc_fs.h> +#include <linux/init.h> +#include <linux/seq_file.h> +#include <linux/slab.h> +#include <asm/uaccess.h> +#include <asm/lppaca.h> +#include <asm/hvcall.h> +#include <asm/firmware.h> +#include <asm/rtas.h> +#include <asm/time.h> +#include <asm/prom.h> +#include <asm/vdso_datapage.h> +#include <asm/vio.h> +#include <asm/mmu.h> +#include <asm/machdep.h> + + +/* + * This isn't a module but we expose that to userspace + * via /proc so leave the definitions here + */ +#define MODULE_VERS "1.9" +#define MODULE_NAME "lparcfg" + +/* #define LPARCFG_DEBUG */ + +/* + * Track sum of all purrs across all processors. This is used to further + * calculate usage values by different applications + */ +static unsigned long get_purr(void) +{ + unsigned long sum_purr = 0; + int cpu; + + for_each_possible_cpu(cpu) { + struct cpu_usage *cu; + + cu = &per_cpu(cpu_usage_array, cpu); + sum_purr += cu->current_tb; + } + return sum_purr; +} + +/* + * Methods used to fetch LPAR data when running on a pSeries platform. + */ + +struct hvcall_ppp_data { + u64 entitlement; + u64 unallocated_entitlement; + u16 group_num; + u16 pool_num; + u8 capped; + u8 weight; + u8 unallocated_weight; + u16 active_procs_in_pool; + u16 active_system_procs; + u16 phys_platform_procs; + u32 max_proc_cap_avail; + u32 entitled_proc_cap_avail; +}; + +/* + * H_GET_PPP hcall returns info in 4 parms. + * entitled_capacity,unallocated_capacity, + * aggregation, resource_capability). + * + * R4 = Entitled Processor Capacity Percentage. + * R5 = Unallocated Processor Capacity Percentage. + * R6 (AABBCCDDEEFFGGHH). + * XXXX - reserved (0) + * XXXX - reserved (0) + * XXXX - Group Number + * XXXX - Pool Number. + * R7 (IIJJKKLLMMNNOOPP). + * XX - reserved. (0) + * XX - bit 0-6 reserved (0). bit 7 is Capped indicator. + * XX - variable processor Capacity Weight + * XX - Unallocated Variable Processor Capacity Weight. + * XXXX - Active processors in Physical Processor Pool. + * XXXX - Processors active on platform. + * R8 (QQQQRRRRRRSSSSSS). if ibm,partition-performance-parameters-level >= 1 + * XXXX - Physical platform procs allocated to virtualization. + * XXXXXX - Max procs capacity % available to the partitions pool. + * XXXXXX - Entitled procs capacity % available to the + * partitions pool. + */ +static unsigned int h_get_ppp(struct hvcall_ppp_data *ppp_data) +{ + unsigned long rc; + unsigned long retbuf[PLPAR_HCALL9_BUFSIZE]; + + rc = plpar_hcall9(H_GET_PPP, retbuf); + + ppp_data->entitlement = retbuf[0]; + ppp_data->unallocated_entitlement = retbuf[1]; + + ppp_data->group_num = (retbuf[2] >> 2 * 8) & 0xffff; + ppp_data->pool_num = retbuf[2] & 0xffff; + + ppp_data->capped = (retbuf[3] >> 6 * 8) & 0x01; + ppp_data->weight = (retbuf[3] >> 5 * 8) & 0xff; + ppp_data->unallocated_weight = (retbuf[3] >> 4 * 8) & 0xff; + ppp_data->active_procs_in_pool = (retbuf[3] >> 2 * 8) & 0xffff; + ppp_data->active_system_procs = retbuf[3] & 0xffff; + + ppp_data->phys_platform_procs = retbuf[4] >> 6 * 8; + ppp_data->max_proc_cap_avail = (retbuf[4] >> 3 * 8) & 0xffffff; + ppp_data->entitled_proc_cap_avail = retbuf[4] & 0xffffff; + + return rc; +} + +static unsigned h_pic(unsigned long *pool_idle_time, + unsigned long *num_procs) +{ + unsigned long rc; + unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; + + rc = plpar_hcall(H_PIC, retbuf); + + *pool_idle_time = retbuf[0]; + *num_procs = retbuf[1]; + + return rc; +} + +/* + * parse_ppp_data + * Parse out the data returned from h_get_ppp and h_pic + */ +static void parse_ppp_data(struct seq_file *m) +{ + struct hvcall_ppp_data ppp_data; + struct device_node *root; + const __be32 *perf_level; + int rc; + + rc = h_get_ppp(&ppp_data); + if (rc) + return; + + seq_printf(m, "partition_entitled_capacity=%lld\n", + ppp_data.entitlement); + seq_printf(m, "group=%d\n", ppp_data.group_num); + seq_printf(m, "system_active_processors=%d\n", + ppp_data.active_system_procs); + + /* pool related entries are appropriate for shared configs */ + if (lppaca_shared_proc(get_lppaca())) { + unsigned long pool_idle_time, pool_procs; + + seq_printf(m, "pool=%d\n", ppp_data.pool_num); + + /* report pool_capacity in percentage */ + seq_printf(m, "pool_capacity=%d\n", + ppp_data.active_procs_in_pool * 100); + + h_pic(&pool_idle_time, &pool_procs); + seq_printf(m, "pool_idle_time=%ld\n", pool_idle_time); + seq_printf(m, "pool_num_procs=%ld\n", pool_procs); + } + + seq_printf(m, "unallocated_capacity_weight=%d\n", + ppp_data.unallocated_weight); + seq_printf(m, "capacity_weight=%d\n", ppp_data.weight); + seq_printf(m, "capped=%d\n", ppp_data.capped); + seq_printf(m, "unallocated_capacity=%lld\n", + ppp_data.unallocated_entitlement); + + /* The last bits of information returned from h_get_ppp are only + * valid if the ibm,partition-performance-parameters-level + * property is >= 1. + */ + root = of_find_node_by_path("/"); + if (root) { + perf_level = of_get_property(root, + "ibm,partition-performance-parameters-level", + NULL); + if (perf_level && (be32_to_cpup(perf_level) >= 1)) { + seq_printf(m, + "physical_procs_allocated_to_virtualization=%d\n", + ppp_data.phys_platform_procs); + seq_printf(m, "max_proc_capacity_available=%d\n", + ppp_data.max_proc_cap_avail); + seq_printf(m, "entitled_proc_capacity_available=%d\n", + ppp_data.entitled_proc_cap_avail); + } + + of_node_put(root); + } +} + +/** + * parse_mpp_data + * Parse out data returned from h_get_mpp + */ +static void parse_mpp_data(struct seq_file *m) +{ + struct hvcall_mpp_data mpp_data; + int rc; + + rc = h_get_mpp(&mpp_data); + if (rc) + return; + + seq_printf(m, "entitled_memory=%ld\n", mpp_data.entitled_mem); + + if (mpp_data.mapped_mem != -1) + seq_printf(m, "mapped_entitled_memory=%ld\n", + mpp_data.mapped_mem); + + seq_printf(m, "entitled_memory_group_number=%d\n", mpp_data.group_num); + seq_printf(m, "entitled_memory_pool_number=%d\n", mpp_data.pool_num); + + seq_printf(m, "entitled_memory_weight=%d\n", mpp_data.mem_weight); + seq_printf(m, "unallocated_entitled_memory_weight=%d\n", + mpp_data.unallocated_mem_weight); + seq_printf(m, "unallocated_io_mapping_entitlement=%ld\n", + mpp_data.unallocated_entitlement); + + if (mpp_data.pool_size != -1) + seq_printf(m, "entitled_memory_pool_size=%ld bytes\n", + mpp_data.pool_size); + + seq_printf(m, "entitled_memory_loan_request=%ld\n", + mpp_data.loan_request); + + seq_printf(m, "backing_memory=%ld bytes\n", mpp_data.backing_mem); +} + +/** + * parse_mpp_x_data + * Parse out data returned from h_get_mpp_x + */ +static void parse_mpp_x_data(struct seq_file *m) +{ + struct hvcall_mpp_x_data mpp_x_data; + + if (!firmware_has_feature(FW_FEATURE_XCMO)) + return; + if (h_get_mpp_x(&mpp_x_data)) + return; + + seq_printf(m, "coalesced_bytes=%ld\n", mpp_x_data.coalesced_bytes); + + if (mpp_x_data.pool_coalesced_bytes) + seq_printf(m, "pool_coalesced_bytes=%ld\n", + mpp_x_data.pool_coalesced_bytes); + if (mpp_x_data.pool_purr_cycles) + seq_printf(m, "coalesce_pool_purr=%ld\n", mpp_x_data.pool_purr_cycles); + if (mpp_x_data.pool_spurr_cycles) + seq_printf(m, "coalesce_pool_spurr=%ld\n", mpp_x_data.pool_spurr_cycles); +} + +#define SPLPAR_CHARACTERISTICS_TOKEN 20 +#define SPLPAR_MAXLENGTH 1026*(sizeof(char)) + +/* + * parse_system_parameter_string() + * Retrieve the potential_processors, max_entitled_capacity and friends + * through the get-system-parameter rtas call. Replace keyword strings as + * necessary. + */ +static void parse_system_parameter_string(struct seq_file *m) +{ + int call_status; + + unsigned char *local_buffer = kmalloc(SPLPAR_MAXLENGTH, GFP_KERNEL); + if (!local_buffer) { + printk(KERN_ERR "%s %s kmalloc failure at line %d\n", + __FILE__, __func__, __LINE__); + return; + } + + spin_lock(&rtas_data_buf_lock); + memset(rtas_data_buf, 0, SPLPAR_MAXLENGTH); + call_status = rtas_call(rtas_token("ibm,get-system-parameter"), 3, 1, + NULL, + SPLPAR_CHARACTERISTICS_TOKEN, + __pa(rtas_data_buf), + RTAS_DATA_BUF_SIZE); + memcpy(local_buffer, rtas_data_buf, SPLPAR_MAXLENGTH); + local_buffer[SPLPAR_MAXLENGTH - 1] = '\0'; + spin_unlock(&rtas_data_buf_lock); + + if (call_status != 0) { + printk(KERN_INFO + "%s %s Error calling get-system-parameter (0x%x)\n", + __FILE__, __func__, call_status); + } else { + int splpar_strlen; + int idx, w_idx; + char *workbuffer = kzalloc(SPLPAR_MAXLENGTH, GFP_KERNEL); + if (!workbuffer) { + printk(KERN_ERR "%s %s kmalloc failure at line %d\n", + __FILE__, __func__, __LINE__); + kfree(local_buffer); + return; + } +#ifdef LPARCFG_DEBUG + printk(KERN_INFO "success calling get-system-parameter\n"); +#endif + splpar_strlen = local_buffer[0] * 256 + local_buffer[1]; + local_buffer += 2; /* step over strlen value */ + + w_idx = 0; + idx = 0; + while ((*local_buffer) && (idx < splpar_strlen)) { + workbuffer[w_idx++] = local_buffer[idx++]; + if ((local_buffer[idx] == ',') + || (local_buffer[idx] == '\0')) { + workbuffer[w_idx] = '\0'; + if (w_idx) { + /* avoid the empty string */ + seq_printf(m, "%s\n", workbuffer); + } + memset(workbuffer, 0, SPLPAR_MAXLENGTH); + idx++; /* skip the comma */ + w_idx = 0; + } else if (local_buffer[idx] == '=') { + /* code here to replace workbuffer contents + with different keyword strings */ + if (0 == strcmp(workbuffer, "MaxEntCap")) { + strcpy(workbuffer, + "partition_max_entitled_capacity"); + w_idx = strlen(workbuffer); + } + if (0 == strcmp(workbuffer, "MaxPlatProcs")) { + strcpy(workbuffer, + "system_potential_processors"); + w_idx = strlen(workbuffer); + } + } + } + kfree(workbuffer); + local_buffer -= 2; /* back up over strlen value */ + } + kfree(local_buffer); +} + +/* Return the number of processors in the system. + * This function reads through the device tree and counts + * the virtual processors, this does not include threads. + */ +static int lparcfg_count_active_processors(void) +{ + struct device_node *cpus_dn = NULL; + int count = 0; + + while ((cpus_dn = of_find_node_by_type(cpus_dn, "cpu"))) { +#ifdef LPARCFG_DEBUG + printk(KERN_ERR "cpus_dn %p\n", cpus_dn); +#endif + count++; + } + return count; +} + +static void pseries_cmo_data(struct seq_file *m) +{ + int cpu; + unsigned long cmo_faults = 0; + unsigned long cmo_fault_time = 0; + + seq_printf(m, "cmo_enabled=%d\n", firmware_has_feature(FW_FEATURE_CMO)); + + if (!firmware_has_feature(FW_FEATURE_CMO)) + return; + + for_each_possible_cpu(cpu) { + cmo_faults += be64_to_cpu(lppaca_of(cpu).cmo_faults); + cmo_fault_time += be64_to_cpu(lppaca_of(cpu).cmo_fault_time); + } + + seq_printf(m, "cmo_faults=%lu\n", cmo_faults); + seq_printf(m, "cmo_fault_time_usec=%lu\n", + cmo_fault_time / tb_ticks_per_usec); + seq_printf(m, "cmo_primary_psp=%d\n", cmo_get_primary_psp()); + seq_printf(m, "cmo_secondary_psp=%d\n", cmo_get_secondary_psp()); + seq_printf(m, "cmo_page_size=%lu\n", cmo_get_page_size()); +} + +static void splpar_dispatch_data(struct seq_file *m) +{ + int cpu; + unsigned long dispatches = 0; + unsigned long dispatch_dispersions = 0; + + for_each_possible_cpu(cpu) { + dispatches += be32_to_cpu(lppaca_of(cpu).yield_count); + dispatch_dispersions += + be32_to_cpu(lppaca_of(cpu).dispersion_count); + } + + seq_printf(m, "dispatches=%lu\n", dispatches); + seq_printf(m, "dispatch_dispersions=%lu\n", dispatch_dispersions); +} + +static void parse_em_data(struct seq_file *m) +{ + unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; + + if (firmware_has_feature(FW_FEATURE_LPAR) && + plpar_hcall(H_GET_EM_PARMS, retbuf) == H_SUCCESS) + seq_printf(m, "power_mode_data=%016lx\n", retbuf[0]); +} + +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 __be32 *lrdrp = NULL; + + rtas_node = of_find_node_by_path("/rtas"); + if (rtas_node) + lrdrp = of_get_property(rtas_node, "ibm,lrdr-capacity", NULL); + + if (lrdrp == NULL) { + partition_potential_processors = vdso_data->processorCount; + } else { + partition_potential_processors = be32_to_cpup(lrdrp + 4); + } + of_node_put(rtas_node); + + partition_active_processors = lparcfg_count_active_processors(); + + if (firmware_has_feature(FW_FEATURE_SPLPAR)) { + /* this call handles the ibm,get-system-parameter contents */ + parse_system_parameter_string(m); + parse_ppp_data(m); + parse_mpp_data(m); + parse_mpp_x_data(m); + pseries_cmo_data(m); + splpar_dispatch_data(m); + + seq_printf(m, "purr=%ld\n", get_purr()); + } else { /* non SPLPAR case */ + + seq_printf(m, "system_active_processors=%d\n", + partition_potential_processors); + + seq_printf(m, "system_potential_processors=%d\n", + partition_potential_processors); + + seq_printf(m, "partition_max_entitled_capacity=%d\n", + partition_potential_processors * 100); + + seq_printf(m, "partition_entitled_capacity=%d\n", + partition_active_processors * 100); + } + + seq_printf(m, "partition_active_processors=%d\n", + partition_active_processors); + + seq_printf(m, "partition_potential_processors=%d\n", + partition_potential_processors); + + seq_printf(m, "shared_processor_mode=%d\n", + lppaca_shared_proc(get_lppaca())); + + seq_printf(m, "slb_size=%d\n", mmu_slb_size); + + parse_em_data(m); + + return 0; +} + +static ssize_t update_ppp(u64 *entitlement, u8 *weight) +{ + struct hvcall_ppp_data ppp_data; + u8 new_weight; + u64 new_entitled; + ssize_t retval; + + /* Get our current parameters */ + retval = h_get_ppp(&ppp_data); + if (retval) + return retval; + + if (entitlement) { + new_weight = ppp_data.weight; + new_entitled = *entitlement; + } else if (weight) { + new_weight = *weight; + new_entitled = ppp_data.entitlement; + } else + return -EINVAL; + + pr_debug("%s: current_entitled = %llu, current_weight = %u\n", + __func__, ppp_data.entitlement, ppp_data.weight); + + pr_debug("%s: new_entitled = %llu, new_weight = %u\n", + __func__, new_entitled, new_weight); + + retval = plpar_hcall_norets(H_SET_PPP, new_entitled, new_weight); + return retval; +} + +/** + * update_mpp + * + * Update the memory entitlement and weight for the partition. Caller must + * specify either a new entitlement or weight, not both, to be updated + * since the h_set_mpp call takes both entitlement and weight as parameters. + */ +static ssize_t update_mpp(u64 *entitlement, u8 *weight) +{ + struct hvcall_mpp_data mpp_data; + u64 new_entitled; + u8 new_weight; + ssize_t rc; + + if (entitlement) { + /* Check with vio to ensure the new memory entitlement + * can be handled. + */ + rc = vio_cmo_entitlement_update(*entitlement); + if (rc) + return rc; + } + + rc = h_get_mpp(&mpp_data); + if (rc) + return rc; + + if (entitlement) { + new_weight = mpp_data.mem_weight; + new_entitled = *entitlement; + } else if (weight) { + new_weight = *weight; + new_entitled = mpp_data.entitled_mem; + } else + return -EINVAL; + + pr_debug("%s: current_entitled = %lu, current_weight = %u\n", + __func__, mpp_data.entitled_mem, mpp_data.mem_weight); + + pr_debug("%s: new_entitled = %llu, new_weight = %u\n", + __func__, new_entitled, new_weight); + + rc = plpar_hcall_norets(H_SET_MPP, new_entitled, new_weight); + return rc; +} + +/* + * Interface for changing system parameters (variable capacity weight + * and entitled capacity). Format of input is "param_name=value"; + * anything after value is ignored. Valid parameters at this time are + * "partition_entitled_capacity" and "capacity_weight". We use + * H_SET_PPP to alter parameters. + * + * This function should be invoked only on systems with + * FW_FEATURE_SPLPAR. + */ +static ssize_t lparcfg_write(struct file *file, const char __user * buf, + size_t count, loff_t * off) +{ + int kbuf_sz = 64; + char kbuf[kbuf_sz]; + char *tmp; + u64 new_entitled, *new_entitled_ptr = &new_entitled; + u8 new_weight, *new_weight_ptr = &new_weight; + ssize_t retval; + + if (!firmware_has_feature(FW_FEATURE_SPLPAR)) + return -EINVAL; + + if (count > kbuf_sz) + return -EINVAL; + + if (copy_from_user(kbuf, buf, count)) + return -EFAULT; + + kbuf[count - 1] = '\0'; + tmp = strchr(kbuf, '='); + if (!tmp) + return -EINVAL; + + *tmp++ = '\0'; + + if (!strcmp(kbuf, "partition_entitled_capacity")) { + char *endp; + *new_entitled_ptr = (u64) simple_strtoul(tmp, &endp, 10); + if (endp == tmp) + return -EINVAL; + + retval = update_ppp(new_entitled_ptr, NULL); + } else if (!strcmp(kbuf, "capacity_weight")) { + char *endp; + *new_weight_ptr = (u8) simple_strtoul(tmp, &endp, 10); + if (endp == tmp) + return -EINVAL; + + retval = update_ppp(NULL, new_weight_ptr); + } else if (!strcmp(kbuf, "entitled_memory")) { + char *endp; + *new_entitled_ptr = (u64) simple_strtoul(tmp, &endp, 10); + if (endp == tmp) + return -EINVAL; + + retval = update_mpp(new_entitled_ptr, NULL); + } else if (!strcmp(kbuf, "entitled_memory_weight")) { + char *endp; + *new_weight_ptr = (u8) simple_strtoul(tmp, &endp, 10); + if (endp == tmp) + return -EINVAL; + + retval = update_mpp(NULL, new_weight_ptr); + } else + return -EINVAL; + + if (retval == H_SUCCESS || retval == H_CONSTRAINED) { + retval = count; + } else if (retval == H_BUSY) { + retval = -EBUSY; + } else if (retval == H_HARDWARE) { + retval = -EIO; + } else if (retval == H_PARAMETER) { + retval = -EINVAL; + } + + return retval; +} + +static int lparcfg_data(struct seq_file *m, void *v) +{ + struct device_node *rootdn; + const char *model = ""; + const char *system_id = ""; + const char *tmp; + const __be32 *lp_index_ptr; + unsigned int lp_index = 0; + + seq_printf(m, "%s %s\n", MODULE_NAME, MODULE_VERS); + + rootdn = of_find_node_by_path("/"); + if (rootdn) { + tmp = of_get_property(rootdn, "model", NULL); + if (tmp) + model = tmp; + tmp = of_get_property(rootdn, "system-id", NULL); + if (tmp) + system_id = tmp; + lp_index_ptr = of_get_property(rootdn, "ibm,partition-no", + NULL); + if (lp_index_ptr) + lp_index = be32_to_cpup(lp_index_ptr); + of_node_put(rootdn); + } + seq_printf(m, "serial_number=%s\n", system_id); + seq_printf(m, "system_type=%s\n", model); + seq_printf(m, "partition_id=%d\n", (int)lp_index); + + return pseries_lparcfg_data(m, v); +} + +static int lparcfg_open(struct inode *inode, struct file *file) +{ + return single_open(file, lparcfg_data, NULL); +} + +static const struct file_operations lparcfg_fops = { + .read = seq_read, + .write = lparcfg_write, + .open = lparcfg_open, + .release = single_release, + .llseek = seq_lseek, +}; + +static int __init lparcfg_init(void) +{ + umode_t mode = S_IRUSR | S_IRGRP | S_IROTH; + + /* Allow writing if we have FW_FEATURE_SPLPAR */ + if (firmware_has_feature(FW_FEATURE_SPLPAR)) + mode |= S_IWUSR; + + if (!proc_create("powerpc/lparcfg", mode, NULL, &lparcfg_fops)) { + printk(KERN_ERR "Failed to create powerpc/lparcfg\n"); + return -EIO; + } + return 0; +} +machine_device_initcall(pseries, lparcfg_init); diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index 3d01eee9ffb..bde7ebad394 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -28,7 +28,7 @@ struct update_props_workarea { u32 state; u64 reserved; u32 nprops; -}; +} __packed; #define NODE_ACTION_MASK 0xff000000 #define NODE_COUNT_MASK 0x00ffffff @@ -62,6 +62,7 @@ static int delete_dt_node(u32 phandle) return -ENOENT; dlpar_detach_node(dn); + of_node_put(dn); return 0; } @@ -119,7 +120,7 @@ static int update_dt_property(struct device_node *dn, struct property **prop, if (!more) { of_update_property(dn, new_prop); - new_prop = NULL; + *prop = NULL; } return 0; @@ -130,7 +131,7 @@ static int update_dt_node(u32 phandle, s32 scope) struct update_props_workarea *upwa; struct device_node *dn; struct property *prop = NULL; - int i, rc; + int i, rc, rtas_rc; char *prop_data; char *rtas_buf; int update_properties_token; @@ -154,25 +155,26 @@ static int update_dt_node(u32 phandle, s32 scope) upwa->phandle = phandle; do { - rc = mobility_rtas_call(update_properties_token, rtas_buf, + rtas_rc = mobility_rtas_call(update_properties_token, rtas_buf, scope); - if (rc < 0) + if (rtas_rc < 0) break; prop_data = rtas_buf + sizeof(*upwa); - /* The first element of the buffer is the path of the node - * being updated in the form of a 8 byte string length - * followed by the string. Skip past this to get to the - * properties being updated. + /* On the first call to ibm,update-properties for a node the + * the first property value descriptor contains an empty + * property name, the property value length encoded as u32, + * and the property value is the node path being updated. */ - vd = *prop_data++; - prop_data += vd; + if (*prop_data == 0) { + prop_data++; + vd = *(u32 *)prop_data; + prop_data += vd + sizeof(vd); + upwa->nprops--; + } - /* The path we skipped over is counted as one of the elements - * returned so start counting at one. - */ - for (i = 1; i < upwa->nprops; i++) { + for (i = 0; i < upwa->nprops; i++) { char *prop_name; prop_name = prop_data; @@ -202,7 +204,7 @@ static int update_dt_node(u32 phandle, s32 scope) prop_data += vd; } } - } while (rc == 1); + } while (rtas_rc == 1); of_node_put(dn); kfree(rtas_buf); @@ -215,17 +217,14 @@ static int add_dt_node(u32 parent_phandle, u32 drc_index) struct device_node *parent_dn; int rc; - dn = dlpar_configure_connector(drc_index); - if (!dn) + parent_dn = of_find_node_by_phandle(parent_phandle); + if (!parent_dn) return -ENOENT; - parent_dn = of_find_node_by_phandle(parent_phandle); - if (!parent_dn) { - dlpar_free_cc_nodes(dn); + dn = dlpar_configure_connector(drc_index, parent_dn); + if (!dn) return -ENOENT; - } - dn->parent = parent_dn; rc = dlpar_attach_node(dn); if (rc) dlpar_free_cc_nodes(dn); @@ -291,13 +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 " @@ -305,16 +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 9f8671a4455..0cc240b7f69 100644 --- a/arch/powerpc/platforms/pseries/nvram.c +++ b/arch/powerpc/platforms/pseries/nvram.c @@ -31,7 +31,7 @@ #define NVRW_CNT 0x20 /* - * Set oops header version to distingush between old and new format header. + * Set oops header version to distinguish between old and new format header. * lnx,oops-log partition max size is 4000, header version > 4000 will * help in identifying new header. */ @@ -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; @@ -429,9 +428,6 @@ static int __init pseries_nvram_init_os_partition(struct nvram_os_partition loff_t p; int size; - /* Scan nvram for partitions */ - nvram_scan_partitions(); - /* Look for ours */ p = nvram_find_partition(part->name, NVRAM_SIG_OS, &size); @@ -532,72 +528,13 @@ 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; } #ifdef CONFIG_PSTORE -/* Derived from logfs_uncompress */ -int nvram_decompress(void *in, void *out, size_t inlen, size_t outlen) -{ - int err, ret; - - ret = -EIO; - err = zlib_inflateInit(&stream); - if (err != Z_OK) - goto error; - - stream.next_in = in; - stream.avail_in = inlen; - stream.total_in = 0; - stream.next_out = out; - stream.avail_out = outlen; - stream.total_out = 0; - - err = zlib_inflate(&stream, Z_FINISH); - if (err != Z_STREAM_END) - goto error; - - err = zlib_inflateEnd(&stream); - if (err != Z_OK) - goto error; - - ret = stream.total_out; -error: - return ret; -} - -static int unzip_oops(char *oops_buf, char *big_buf) -{ - struct oops_log_info *oops_hdr = (struct oops_log_info *)oops_buf; - u64 timestamp = oops_hdr->timestamp; - char *big_oops_data = NULL; - char *oops_data_buf = NULL; - size_t big_oops_data_sz; - int unzipped_len; - - big_oops_data = big_buf + sizeof(struct oops_log_info); - big_oops_data_sz = big_oops_buf_sz - sizeof(struct oops_log_info); - oops_data_buf = oops_buf + sizeof(struct oops_log_info); - - unzipped_len = nvram_decompress(oops_data_buf, big_oops_data, - oops_hdr->report_length, - big_oops_data_sz); - - if (unzipped_len < 0) { - pr_err("nvram: decompression failed; returned %d\n", - unzipped_len); - return -1; - } - oops_hdr = (struct oops_log_info *)big_buf; - oops_hdr->version = OOPS_HDR_VERSION; - oops_hdr->report_length = (u16) unzipped_len; - oops_hdr->timestamp = timestamp; - return 0; -} - static int nvram_pstore_open(struct pstore_info *psi) { /* Reset the iterator to start reading partitions again */ @@ -613,7 +550,7 @@ static int nvram_pstore_open(struct pstore_info *psi) * @part: pstore writes data to registered buffer in parts, * part number will indicate the same. * @count: Indicates oops count - * @hsize: Size of header added by pstore + * @compressed: Flag to indicate the log is compressed * @size: number of bytes written to the registered buffer * @psi: registered pstore_info structure * @@ -624,7 +561,7 @@ static int nvram_pstore_open(struct pstore_info *psi) static int nvram_pstore_write(enum pstore_type_id type, enum kmsg_dump_reason reason, u64 *id, unsigned int part, int count, - size_t hsize, size_t size, + bool compressed, size_t size, struct pstore_info *psi) { int rc; @@ -636,34 +573,15 @@ 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 (big_oops_buf) { - rc = zip_oops(size); - /* - * If compression fails copy recent log messages from - * big_oops_buf to oops_data. - */ - if (rc != 0) { - size_t diff = size - oops_data_sz + hsize; - - if (size > oops_data_sz) { - memcpy(oops_data, big_oops_buf, hsize); - memcpy(oops_data + hsize, big_oops_buf + diff, - oops_data_sz - hsize); - - oops_hdr->report_length = (u16) oops_data_sz; - } else - memcpy(oops_data, big_oops_buf, size); - } else - err_type = ERR_TYPE_KERNEL_PANIC_GZ; - } + if (compressed) + err_type = ERR_TYPE_KERNEL_PANIC_GZ; rc = nvram_write_os_partition(&oops_log_partition, oops_buf, - (int) (sizeof(*oops_hdr) + oops_hdr->report_length), err_type, - count); + (int) (sizeof(*oops_hdr) + size), err_type, count); if (rc != 0) return rc; @@ -679,16 +597,15 @@ static int nvram_pstore_write(enum pstore_type_id type, */ static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type, int *count, struct timespec *time, char **buf, - struct pstore_info *psi) + bool *compressed, struct pstore_info *psi) { struct oops_log_info *oops_hdr; unsigned int err_type, id_no, size = 0; struct nvram_os_partition *part = NULL; - char *buff = NULL, *big_buff = NULL; - int rc, sig = 0; + char *buff = NULL; + int sig = 0; loff_t p; -read_partition: read_type++; switch (nvram_type_ids[read_type]) { @@ -749,30 +666,32 @@ read_partition: *id = id_no; if (nvram_type_ids[read_type] == PSTORE_TYPE_DMESG) { - oops_hdr = (struct oops_log_info *)buff; - *buf = buff + sizeof(*oops_hdr); + size_t length, hdr_size; - if (err_type == ERR_TYPE_KERNEL_PANIC_GZ) { - big_buff = kmalloc(big_oops_buf_sz, GFP_KERNEL); - if (!big_buff) - return -ENOMEM; - - rc = unzip_oops(buff, big_buff); - - if (rc != 0) { - kfree(buff); - kfree(big_buff); - goto read_partition; - } - - oops_hdr = (struct oops_log_info *)big_buff; - *buf = big_buff + sizeof(*oops_hdr); - kfree(buff); + oops_hdr = (struct oops_log_info *)buff; + if (be16_to_cpu(oops_hdr->version) < OOPS_HDR_VERSION) { + /* Old format oops header had 2-byte record size */ + hdr_size = sizeof(u16); + length = be16_to_cpu(oops_hdr->version); + time->tv_sec = 0; + time->tv_nsec = 0; + } else { + hdr_size = sizeof(*oops_hdr); + 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); + if (*buf == NULL) + return -ENOMEM; + memcpy(*buf, buff + hdr_size, length); + kfree(buff); - time->tv_sec = oops_hdr->timestamp; - time->tv_nsec = 0; - return oops_hdr->report_length; + if (err_type == ERR_TYPE_KERNEL_PANIC_GZ) + *compressed = true; + else + *compressed = false; + return length; } *buf = buff; @@ -791,13 +710,8 @@ static int nvram_pstore_init(void) { int rc = 0; - if (big_oops_buf) { - nvram_pstore_info.buf = big_oops_buf; - nvram_pstore_info.bufsize = big_oops_buf_sz; - } else { - nvram_pstore_info.buf = oops_data; - nvram_pstore_info.bufsize = oops_data_sz; - } + nvram_pstore_info.buf = oops_data; + nvram_pstore_info.bufsize = oops_data_sz; rc = pstore_register(&nvram_pstore_info); if (rc != 0) @@ -836,6 +750,11 @@ static void __init nvram_init_oops_partition(int rtas_partition_exists) oops_data = oops_buf + sizeof(struct oops_log_info); oops_data_sz = oops_log_partition.size - sizeof(struct oops_log_info); + rc = nvram_pstore_init(); + + if (!rc) + return; + /* * Figure compression (preceded by elimination of each line's <n> * severity prefix) will reduce the oops/panic report to at most @@ -844,8 +763,8 @@ static void __init nvram_init_oops_partition(int rtas_partition_exists) big_oops_buf_sz = (oops_data_sz * 100) / 45; big_oops_buf = kmalloc(big_oops_buf_sz, GFP_KERNEL); if (big_oops_buf) { - stream.workspace = kmalloc(zlib_deflate_workspacesize( - WINDOW_BITS, MEM_LEVEL), GFP_KERNEL); + stream.workspace = kmalloc(zlib_deflate_workspacesize( + WINDOW_BITS, MEM_LEVEL), GFP_KERNEL); if (!stream.workspace) { pr_err("nvram: No memory for compression workspace; " "skipping compression of %s partition data\n", @@ -859,11 +778,6 @@ static void __init nvram_init_oops_partition(int rtas_partition_exists) stream.workspace = NULL; } - rc = nvram_pstore_init(); - - if (!rc) - return; - rc = kmsg_dump_register(&nvram_kmsg_dumper); if (rc != 0) { pr_err("nvram: kmsg_dump_register() failed; returned %d\n", rc); @@ -877,6 +791,9 @@ static int __init pseries_nvram_init_log_partitions(void) { int rc; + /* Scan nvram for partitions */ + nvram_scan_partitions(); + rc = pseries_nvram_init_os_partition(&rtas_log_partition); nvram_init_oops_partition(rc == 0); return 0; @@ -886,7 +803,7 @@ machine_arch_initcall(pseries, pseries_nvram_init_log_partitions); int __init pSeries_nvram_init(void) { struct device_node *nvram; - const unsigned int *nbytes_p; + const __be32 *nbytes_p; unsigned int proplen; nvram = of_find_node_by_type(NULL, "nvram"); @@ -899,7 +816,7 @@ int __init pSeries_nvram_init(void) return -EIO; } - nvram_size = *nbytes_p; + nvram_size = be32_to_cpup(nbytes_p); nvram_fetch = rtas_token("nvram-fetch"); nvram_store = rtas_token("nvram-store"); @@ -951,7 +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; } @@ -971,13 +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/plpar_wrappers.h b/arch/powerpc/platforms/pseries/plpar_wrappers.h deleted file mode 100644 index f35787b6a5e..00000000000 --- a/arch/powerpc/platforms/pseries/plpar_wrappers.h +++ /dev/null @@ -1,324 +0,0 @@ -#ifndef _PSERIES_PLPAR_WRAPPERS_H -#define _PSERIES_PLPAR_WRAPPERS_H - -#include <linux/string.h> -#include <linux/irqflags.h> - -#include <asm/hvcall.h> -#include <asm/paca.h> -#include <asm/page.h> - -/* Get state of physical CPU from query_cpu_stopped */ -int smp_query_cpu_stopped(unsigned int pcpu); -#define QCSS_STOPPED 0 -#define QCSS_STOPPING 1 -#define QCSS_NOT_STOPPED 2 -#define QCSS_HARDWARE_ERROR -1 -#define QCSS_HARDWARE_BUSY -2 - -static inline long poll_pending(void) -{ - return plpar_hcall_norets(H_POLL_PENDING); -} - -static inline u8 get_cede_latency_hint(void) -{ - return get_lppaca()->cede_latency_hint; -} - -static inline void set_cede_latency_hint(u8 latency_hint) -{ - get_lppaca()->cede_latency_hint = latency_hint; -} - -static inline long cede_processor(void) -{ - return plpar_hcall_norets(H_CEDE); -} - -static inline long extended_cede_processor(unsigned long latency_hint) -{ - long rc; - u8 old_latency_hint = get_cede_latency_hint(); - - set_cede_latency_hint(latency_hint); - - rc = cede_processor(); -#ifdef CONFIG_TRACE_IRQFLAGS - /* Ensure that H_CEDE returns with IRQs on */ - if (WARN_ON(!(mfmsr() & MSR_EE))) - __hard_irq_enable(); -#endif - - set_cede_latency_hint(old_latency_hint); - - return rc; -} - -static inline long vpa_call(unsigned long flags, unsigned long cpu, - unsigned long vpa) -{ - flags = flags << H_VPA_FUNC_SHIFT; - - return plpar_hcall_norets(H_REGISTER_VPA, flags, cpu, vpa); -} - -static inline long unregister_vpa(unsigned long cpu) -{ - return vpa_call(H_VPA_DEREG_VPA, cpu, 0); -} - -static inline long register_vpa(unsigned long cpu, unsigned long vpa) -{ - return vpa_call(H_VPA_REG_VPA, cpu, vpa); -} - -static inline long unregister_slb_shadow(unsigned long cpu) -{ - return vpa_call(H_VPA_DEREG_SLB, cpu, 0); -} - -static inline long register_slb_shadow(unsigned long cpu, unsigned long vpa) -{ - return vpa_call(H_VPA_REG_SLB, cpu, vpa); -} - -static inline long unregister_dtl(unsigned long cpu) -{ - return vpa_call(H_VPA_DEREG_DTL, cpu, 0); -} - -static inline long register_dtl(unsigned long cpu, unsigned long vpa) -{ - return vpa_call(H_VPA_REG_DTL, cpu, vpa); -} - -static inline long plpar_page_set_loaned(unsigned long vpa) -{ - unsigned long cmo_page_sz = cmo_get_page_size(); - long rc = 0; - int i; - - for (i = 0; !rc && i < PAGE_SIZE; i += cmo_page_sz) - rc = plpar_hcall_norets(H_PAGE_INIT, H_PAGE_SET_LOANED, vpa + i, 0); - - for (i -= cmo_page_sz; rc && i != 0; i -= cmo_page_sz) - plpar_hcall_norets(H_PAGE_INIT, H_PAGE_SET_ACTIVE, - vpa + i - cmo_page_sz, 0); - - return rc; -} - -static inline long plpar_page_set_active(unsigned long vpa) -{ - unsigned long cmo_page_sz = cmo_get_page_size(); - long rc = 0; - int i; - - for (i = 0; !rc && i < PAGE_SIZE; i += cmo_page_sz) - rc = plpar_hcall_norets(H_PAGE_INIT, H_PAGE_SET_ACTIVE, vpa + i, 0); - - for (i -= cmo_page_sz; rc && i != 0; i -= cmo_page_sz) - plpar_hcall_norets(H_PAGE_INIT, H_PAGE_SET_LOANED, - vpa + i - cmo_page_sz, 0); - - return rc; -} - -extern void vpa_init(int cpu); - -static inline long plpar_pte_enter(unsigned long flags, - unsigned long hpte_group, unsigned long hpte_v, - unsigned long hpte_r, unsigned long *slot) -{ - long rc; - unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; - - rc = plpar_hcall(H_ENTER, retbuf, flags, hpte_group, hpte_v, hpte_r); - - *slot = retbuf[0]; - - return rc; -} - -static inline long plpar_pte_remove(unsigned long flags, unsigned long ptex, - unsigned long avpn, unsigned long *old_pteh_ret, - unsigned long *old_ptel_ret) -{ - long rc; - unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; - - rc = plpar_hcall(H_REMOVE, retbuf, flags, ptex, avpn); - - *old_pteh_ret = retbuf[0]; - *old_ptel_ret = retbuf[1]; - - return rc; -} - -/* plpar_pte_remove_raw can be called in real mode. It calls plpar_hcall_raw */ -static inline long plpar_pte_remove_raw(unsigned long flags, unsigned long ptex, - unsigned long avpn, unsigned long *old_pteh_ret, - unsigned long *old_ptel_ret) -{ - long rc; - unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; - - rc = plpar_hcall_raw(H_REMOVE, retbuf, flags, ptex, avpn); - - *old_pteh_ret = retbuf[0]; - *old_ptel_ret = retbuf[1]; - - return rc; -} - -static inline long plpar_pte_read(unsigned long flags, unsigned long ptex, - unsigned long *old_pteh_ret, unsigned long *old_ptel_ret) -{ - long rc; - unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; - - rc = plpar_hcall(H_READ, retbuf, flags, ptex); - - *old_pteh_ret = retbuf[0]; - *old_ptel_ret = retbuf[1]; - - return rc; -} - -/* plpar_pte_read_raw can be called in real mode. It calls plpar_hcall_raw */ -static inline long plpar_pte_read_raw(unsigned long flags, unsigned long ptex, - unsigned long *old_pteh_ret, unsigned long *old_ptel_ret) -{ - long rc; - unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; - - rc = plpar_hcall_raw(H_READ, retbuf, flags, ptex); - - *old_pteh_ret = retbuf[0]; - *old_ptel_ret = retbuf[1]; - - return rc; -} - -/* - * plpar_pte_read_4_raw can be called in real mode. - * ptes must be 8*sizeof(unsigned long) - */ -static inline long plpar_pte_read_4_raw(unsigned long flags, unsigned long ptex, - unsigned long *ptes) - -{ - long rc; - unsigned long retbuf[PLPAR_HCALL9_BUFSIZE]; - - rc = plpar_hcall9_raw(H_READ, retbuf, flags | H_READ_4, ptex); - - memcpy(ptes, retbuf, 8*sizeof(unsigned long)); - - return rc; -} - -static inline long plpar_pte_protect(unsigned long flags, unsigned long ptex, - unsigned long avpn) -{ - return plpar_hcall_norets(H_PROTECT, flags, ptex, avpn); -} - -static inline long plpar_tce_get(unsigned long liobn, unsigned long ioba, - unsigned long *tce_ret) -{ - long rc; - unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; - - rc = plpar_hcall(H_GET_TCE, retbuf, liobn, ioba); - - *tce_ret = retbuf[0]; - - return rc; -} - -static inline long plpar_tce_put(unsigned long liobn, unsigned long ioba, - unsigned long tceval) -{ - return plpar_hcall_norets(H_PUT_TCE, liobn, ioba, tceval); -} - -static inline long plpar_tce_put_indirect(unsigned long liobn, - unsigned long ioba, unsigned long page, unsigned long count) -{ - return plpar_hcall_norets(H_PUT_TCE_INDIRECT, liobn, ioba, page, count); -} - -static inline long plpar_tce_stuff(unsigned long liobn, unsigned long ioba, - unsigned long tceval, unsigned long count) -{ - return plpar_hcall_norets(H_STUFF_TCE, liobn, ioba, tceval, count); -} - -static inline long plpar_get_term_char(unsigned long termno, - unsigned long *len_ret, char *buf_ret) -{ - long rc; - unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; - unsigned long *lbuf = (unsigned long *)buf_ret; /* TODO: alignment? */ - - rc = plpar_hcall(H_GET_TERM_CHAR, retbuf, termno); - - *len_ret = retbuf[0]; - lbuf[0] = retbuf[1]; - lbuf[1] = retbuf[2]; - - return rc; -} - -static inline long plpar_put_term_char(unsigned long termno, unsigned long len, - const char *buffer) -{ - unsigned long *lbuf = (unsigned long *)buffer; /* TODO: alignment? */ - return plpar_hcall_norets(H_PUT_TERM_CHAR, termno, len, lbuf[0], - lbuf[1]); -} - -/* Set various resource mode parameters */ -static inline long plpar_set_mode(unsigned long mflags, unsigned long resource, - unsigned long value1, unsigned long value2) -{ - return plpar_hcall_norets(H_SET_MODE, mflags, resource, value1, value2); -} - -/* - * Enable relocation on exceptions on this partition - * - * Note: this call has a partition wide scope and can take a while to complete. - * If it returns H_LONG_BUSY_* it should be retried periodically until it - * returns H_SUCCESS. - */ -static inline long enable_reloc_on_exceptions(void) -{ - /* mflags = 3: Exceptions at 0xC000000000004000 */ - return plpar_set_mode(3, 3, 0, 0); -} - -/* - * Disable relocation on exceptions on this partition - * - * Note: this call has a partition wide scope and can take a while to complete. - * If it returns H_LONG_BUSY_* it should be retried periodically until it - * returns H_SUCCESS. - */ -static inline long disable_reloc_on_exceptions(void) { - return plpar_set_mode(0, 3, 0, 0); -} - -static inline long plapr_set_ciabr(unsigned long ciabr) -{ - return plpar_set_mode(0, 1, ciabr, 0); -} - -static inline long plapr_set_watchpoint0(unsigned long dawr0, unsigned long dawrx0) -{ - return plpar_set_mode(0, 2, dawr0, dawrx0); -} - -#endif /* _PSERIES_PLPAR_WRAPPERS_H */ diff --git a/arch/powerpc/platforms/pseries/processor_idle.c b/arch/powerpc/platforms/pseries/processor_idle.c deleted file mode 100644 index 4644efa0694..00000000000 --- a/arch/powerpc/platforms/pseries/processor_idle.c +++ /dev/null @@ -1,362 +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 "plpar_wrappers.h" -#include "pseries.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) -{ - get_lppaca()->wait_state_cycles += mfspr(SPRN_PURR) - in_purr; - 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 (get_lppaca()->shared_proc) - 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 c2a3a258001..361add62abf 100644 --- a/arch/powerpc/platforms/pseries/pseries.h +++ b/arch/powerpc/platforms/pseries/pseries.h @@ -56,15 +56,14 @@ extern void hvc_vio_init_early(void); /* Dynamic logical Partitioning/Mobility */ extern void dlpar_free_cc_nodes(struct device_node *); extern void dlpar_free_cc_property(struct property *); -extern struct device_node *dlpar_configure_connector(u32); +extern struct device_node *dlpar_configure_connector(u32, struct device_node *); extern int dlpar_attach_node(struct device_node *); extern int dlpar_detach_node(struct device_node *); -/* Snooze Delay, pseries_idle */ -DECLARE_PER_CPU(long, smt_snooze_delay); - /* PCI root bridge prepare function override for pseries */ 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/pseries_energy.c b/arch/powerpc/platforms/pseries/pseries_energy.c index a91e6dadda2..92767791f93 100644 --- a/arch/powerpc/platforms/pseries/pseries_energy.c +++ b/arch/powerpc/platforms/pseries/pseries_energy.c @@ -108,8 +108,8 @@ err: * energy consumption. */ -#define FLAGS_MODE1 0x004E200000080E01 -#define FLAGS_MODE2 0x004E200000080401 +#define FLAGS_MODE1 0x004E200000080E01UL +#define FLAGS_MODE2 0x004E200000080401UL #define FLAGS_ACTIVATE 0x100 static ssize_t get_best_energy_list(char *page, int activate) diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index 7b3cbde8c78..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; @@ -287,6 +288,9 @@ static struct rtas_error_log *fwnmi_get_errinfo(struct pt_regs *regs) unsigned long *savep; struct rtas_error_log *h, *errhdr = NULL; + /* Mask top two bits */ + regs->gpr[3] &= ~(0x3UL << 62); + if (!VALID_FWNMI_BUFFER(regs->gpr[3])) { printk(KERN_ERR "FWNMI: corrupt r3 0x%016lx\n", regs->gpr[3]); return NULL; @@ -297,13 +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; @@ -347,23 +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/rng.c b/arch/powerpc/platforms/pseries/rng.c new file mode 100644 index 00000000000..72a102758d4 --- /dev/null +++ b/arch/powerpc/platforms/pseries/rng.c @@ -0,0 +1,45 @@ +/* + * Copyright 2013, Michael Ellerman, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#define pr_fmt(fmt) "pseries-rng: " fmt + +#include <linux/kernel.h> +#include <linux/of.h> +#include <asm/archrandom.h> +#include <asm/machdep.h> +#include <asm/plpar_wrappers.h> + + +static int pseries_get_random_long(unsigned long *v) +{ + unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; + + if (plpar_hcall(H_RANDOM, retbuf) == H_SUCCESS) { + *v = retbuf[0]; + return 1; + } + + return 0; +} + +static __init int rng_init(void) +{ + struct device_node *dn; + + dn = of_find_compatible_node(NULL, NULL, "ibm,random"); + if (!dn) + return -ENODEV; + + pr_info("Registering arch random hook.\n"); + + ppc_md.get_random_long = pseries_get_random_long; + + return 0; +} +subsys_initcall(rng_init); diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index c11c8238797..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> @@ -66,13 +65,13 @@ #include <asm/firmware.h> #include <asm/eeh.h> #include <asm/reg.h> +#include <asm/plpar_wrappers.h> -#include "plpar_wrappers.h" #include "pseries.h" 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 */ @@ -183,7 +182,7 @@ static void __init pseries_mpic_init_IRQ(void) np = of_find_node_by_path("/"); naddr = of_n_addr_cells(np); opprop = of_get_property(np, "platform-open-pic", &opplen); - if (opprop != 0) { + if (opprop != NULL) { openpic_addr = of_read_number(opprop, naddr); printk(KERN_DEBUG "OpenPIC addr: %lx\n", openpic_addr); } @@ -323,7 +322,7 @@ static int alloc_dispatch_logs(void) get_paca()->lppaca_ptr->dtl_idx = 0; /* hypervisor reads buffer length from this field */ - dtl->enqueue_to_dispatch_time = DISPATCH_LOG_BYTES; + dtl->enqueue_to_dispatch_time = cpu_to_be32(DISPATCH_LOG_BYTES); ret = register_dtl(hard_smp_processor_id(), __pa(dtl)); if (ret) pr_err("WARNING: DTL registration of cpu %d (hw %d) failed " @@ -354,19 +353,26 @@ static int alloc_dispatch_log_kmem_cache(void) } early_initcall(alloc_dispatch_log_kmem_cache); -static void pSeries_idle(void) +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. - */ - HMT_low(); - HMT_very_low(); - } + + /* 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(); + + get_lppaca()->idle = 0; } /* @@ -418,8 +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 " @@ -430,9 +435,35 @@ static void pSeries_machine_kexec(struct kimage *image) } #endif +#ifdef __LITTLE_ENDIAN__ +long pseries_big_endian_exceptions(void) +{ + long rc; + + while (1) { + rc = enable_big_endian_exceptions(); + if (!H_IS_LONG_BUSY(rc)) + return rc; + mdelay(get_longbusy_msecs(rc)); + } +} + +static long pseries_little_endian_exceptions(void) +{ + long rc; + + while (1) { + rc = enable_little_endian_exceptions(); + if (!H_IS_LONG_BUSY(rc)) + return rc; + mdelay(get_longbusy_msecs(rc)); + } +} +#endif + 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(); @@ -456,15 +487,14 @@ static void __init pSeries_setup_arch(void) pSeries_nvram_init(); - if (firmware_has_feature(FW_FEATURE_SPLPAR)) { + if (firmware_has_feature(FW_FEATURE_LPAR)) { vpa_init(boot_cpuid); - ppc_md.power_save = pSeries_idle; - } - - if (firmware_has_feature(FW_FEATURE_LPAR)) + ppc_md.power_save = pseries_lpar_idle; ppc_md.enable_pmcs = pseries_lpar_enable_pmcs; - else + } else { + /* No special idle routine */ ppc_md.enable_pmcs = power4_enable_pmcs; + } ppc_md.pcibios_root_bridge_prepare = pseries_root_bridge_prepare; @@ -480,7 +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; @@ -532,7 +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); @@ -635,7 +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; @@ -668,7 +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; @@ -687,6 +721,22 @@ static int __init pSeries_probe(void) /* Now try to figure out if we are running on LPAR */ of_scan_flat_dt(pseries_probe_fw_features, NULL); +#ifdef __LITTLE_ENDIAN__ + if (firmware_has_feature(FW_FEATURE_SET_MODE)) { + long rc; + /* + * Tell the hypervisor that we want our exceptions to + * be taken in little endian mode. If this fails we don't + * want to use BUG() because it will trigger an exception. + */ + rc = pseries_little_endian_exceptions(); + if (rc) { + ppc_md.progress("H_SET_MODE LE exception fail", 0); + panic("Could not enable little endian exceptions"); + } + } +#endif + if (firmware_has_feature(FW_FEATURE_LPAR)) hpte_init_lpar(); else @@ -760,4 +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 306643cc9db..a3555b10c1a 100644 --- a/arch/powerpc/platforms/pseries/smp.c +++ b/arch/powerpc/platforms/pseries/smp.c @@ -43,8 +43,9 @@ #include <asm/cputhreads.h> #include <asm/xics.h> #include <asm/dbell.h> +#include <asm/plpar_wrappers.h> +#include <asm/code-patching.h> -#include "plpar_wrappers.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; @@ -187,22 +188,6 @@ static int smp_pSeries_kick_cpu(int nr) return 0; } -static int smp_pSeries_cpu_bootable(unsigned int nr) -{ - /* Special case - we inhibit secondary thread startup - * during boot if the user requests it. - */ - if (system_state == SYSTEM_BOOTING && cpu_has_feature(CPU_FTR_SMT)) { - if (!smt_enabled_at_boot && cpu_thread_in_core(nr) != 0) - return 0; - if (smt_enabled_at_boot - && cpu_thread_in_core(nr) >= smt_enabled_at_boot) - return 0; - } - - return 1; -} - /* Only used on systems that support multiple IPI mechanisms */ static void pSeries_cause_ipi_mux(int cpu, unsigned long data) { @@ -237,7 +222,7 @@ static struct smp_ops_t pSeries_xics_smp_ops = { .probe = pSeries_smp_probe, .kick_cpu = smp_pSeries_kick_cpu, .setup_cpu = smp_xics_setup_cpu, - .cpu_bootable = smp_pSeries_cpu_bootable, + .cpu_bootable = smp_generic_cpu_bootable, }; /* This is called very early */ @@ -249,18 +234,24 @@ static void __init smp_init_pseries(void) alloc_bootmem_cpumask_var(&of_spin_mask); - /* Mark threads which are still spinning in hold loops. */ - if (cpu_has_feature(CPU_FTR_SMT)) { - for_each_present_cpu(i) { - if (cpu_thread_in_core(i) == 0) - cpumask_set_cpu(i, of_spin_mask); - } - } else { - cpumask_copy(of_spin_mask, cpu_present_mask); + /* + * Mark threads which are still spinning in hold loops + * + * We know prom_init will not have started them if RTAS supports + * query-cpu-stopped-state. + */ + if (rtas_token("query-cpu-stopped-state") == RTAS_UNKNOWN_SERVICE) { + if (cpu_has_feature(CPU_FTR_SMT)) { + for_each_present_cpu(i) { + if (cpu_thread_in_core(i) == 0) + cpumask_set_cpu(i, of_spin_mask); + } + } else + cpumask_copy(of_spin_mask, cpu_present_mask); + + cpumask_clear_cpu(boot_cpuid, of_spin_mask); } - cpumask_clear_cpu(boot_cpuid, of_spin_mask); - /* Non-lpar has additional take/give timebase */ if (rtas_token("freeze-time-base") != RTAS_UNKNOWN_SERVICE) { smp_ops->give_timebase = rtas_give_timebase; diff --git a/arch/powerpc/platforms/pseries/suspend.c b/arch/powerpc/platforms/pseries/suspend.c index 5f997e79d57..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: @@ -106,7 +124,7 @@ static int pseries_prepare_late(void) atomic_set(&suspend_data.done, 0); atomic_set(&suspend_data.error, 0); suspend_data.complete = &suspend_work; - INIT_COMPLETION(suspend_work); + reinit_completion(&suspend_work); return 0; } @@ -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; } |