diff options
Diffstat (limited to 'arch/powerpc/platforms/pseries')
| -rw-r--r-- | arch/powerpc/platforms/pseries/Kconfig | 22 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/Makefile | 1 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/eeh.c | 2 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/eeh_sysfs.c | 1 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/firmware.c | 1 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/hvCall.S | 1 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/hvCall_inst.c | 2 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/iommu.c | 49 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/kexec.c | 10 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/lpar.c | 12 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/nvram.c | 205 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/pci_dlpar.c | 2 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/pseries_energy.c | 326 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/ras.c | 102 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/suspend.c | 2 |
15 files changed, 657 insertions, 81 deletions
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig index c667f0f02c34..5b3da4b4ea79 100644 --- a/arch/powerpc/platforms/pseries/Kconfig +++ b/arch/powerpc/platforms/pseries/Kconfig @@ -10,7 +10,7 @@ config PPC_PSERIES select RTAS_ERROR_LOGGING select PPC_UDBG_16550 select PPC_NATIVE - select PPC_PCI_CHOICE if EMBEDDED + select PPC_PCI_CHOICE if EXPERT default y config PPC_SPLPAR @@ -24,15 +24,25 @@ config PPC_SPLPAR two or more partitions. config EEH - bool "PCI Extended Error Handling (EEH)" if EMBEDDED + bool "PCI Extended Error Handling (EEH)" if EXPERT depends on PPC_PSERIES && PCI - default y if !EMBEDDED + default y if !EXPERT config PSERIES_MSI bool depends on PCI_MSI && EEH default y +config PSERIES_ENERGY + tristate "pSeries energy management capabilities driver" + depends on PPC_PSERIES + default y + help + Provides interface to platform energy management capabilities + on supported PSERIES platforms. + Provides: /sys/devices/system/cpu/pseries_(de)activation_hint_list + and /sys/devices/system/cpu/cpuN/pseries_(de)activation_hint + config SCANLOG tristate "Scanlog dump interface" depends on RTAS_PROC && PPC_PSERIES @@ -47,6 +57,12 @@ config LPARCFG config PPC_PSERIES_DEBUG depends on PPC_PSERIES && PPC_EARLY_DEBUG bool "Enable extra debug logging in platforms/pseries" + help + Say Y here if you want the pseries core to produce a bunch of + debug messages to the system log. Select this if you are having a + problem with the pseries core and want to see more of what is + going on. This does not enable debugging in lpar.c, which must + be manually done due to its verbosity. default y config PPC_SMLPAR diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile index 59eb8bdaa79d..fc5237810ece 100644 --- a/arch/powerpc/platforms/pseries/Makefile +++ b/arch/powerpc/platforms/pseries/Makefile @@ -11,6 +11,7 @@ obj-$(CONFIG_EEH) += eeh.o eeh_cache.o eeh_driver.o eeh_event.o eeh_sysfs.o obj-$(CONFIG_KEXEC) += kexec.o obj-$(CONFIG_PCI) += pci.o pci_dlpar.o obj-$(CONFIG_PSERIES_MSI) += msi.o +obj-$(CONFIG_PSERIES_ENERGY) += pseries_energy.o obj-$(CONFIG_HOTPLUG_CPU) += hotplug-cpu.o obj-$(CONFIG_MEMORY_HOTPLUG) += hotplug-memory.o diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c index 34b7dc12e731..17a11c82e6f8 100644 --- a/arch/powerpc/platforms/pseries/eeh.c +++ b/arch/powerpc/platforms/pseries/eeh.c @@ -21,8 +21,6 @@ * Please address comments and feedback to Linas Vepstas <linas@austin.ibm.com> */ -#undef DEBUG - #include <linux/delay.h> #include <linux/init.h> #include <linux/list.h> diff --git a/arch/powerpc/platforms/pseries/eeh_sysfs.c b/arch/powerpc/platforms/pseries/eeh_sysfs.c index 15e13b568904..23982c7892d2 100644 --- a/arch/powerpc/platforms/pseries/eeh_sysfs.c +++ b/arch/powerpc/platforms/pseries/eeh_sysfs.c @@ -25,7 +25,6 @@ #include <linux/pci.h> #include <asm/ppc-pci.h> #include <asm/pci-bridge.h> -#include <linux/kobject.h> /** * EEH_SHOW_ATTR -- create sysfs entry for eeh statistic diff --git a/arch/powerpc/platforms/pseries/firmware.c b/arch/powerpc/platforms/pseries/firmware.c index 0a14d8cd314f..0b0eff0cce35 100644 --- a/arch/powerpc/platforms/pseries/firmware.c +++ b/arch/powerpc/platforms/pseries/firmware.c @@ -55,6 +55,7 @@ firmware_features_table[FIRMWARE_MAX_FEATURES] = { {FW_FEATURE_XDABR, "hcall-xdabr"}, {FW_FEATURE_MULTITCE, "hcall-multi-tce"}, {FW_FEATURE_SPLPAR, "hcall-splpar"}, + {FW_FEATURE_VPHN, "hcall-vphn"}, }; /* Build up the firmware features bitmask using the contents of diff --git a/arch/powerpc/platforms/pseries/hvCall.S b/arch/powerpc/platforms/pseries/hvCall.S index 48d20573e4de..fd05fdee576a 100644 --- a/arch/powerpc/platforms/pseries/hvCall.S +++ b/arch/powerpc/platforms/pseries/hvCall.S @@ -11,6 +11,7 @@ #include <asm/processor.h> #include <asm/ppc_asm.h> #include <asm/asm-offsets.h> +#include <asm/ptrace.h> #define STK_PARM(i) (48 + ((i)-3)*8) diff --git a/arch/powerpc/platforms/pseries/hvCall_inst.c b/arch/powerpc/platforms/pseries/hvCall_inst.c index e19ff021e711..f106662f4381 100644 --- a/arch/powerpc/platforms/pseries/hvCall_inst.c +++ b/arch/powerpc/platforms/pseries/hvCall_inst.c @@ -55,7 +55,7 @@ static void hc_stop(struct seq_file *m, void *p) static int hc_show(struct seq_file *m, void *p) { unsigned long h_num = (unsigned long)p; - struct hcall_stats *hs = (struct hcall_stats *)m->private; + struct hcall_stats *hs = m->private; if (hs[h_num].num_calls) { if (cpu_has_feature(CPU_FTR_PURR)) diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index a77bcaed80af..edea60b7ee90 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -140,7 +140,7 @@ static int tce_build_pSeriesLP(struct iommu_table *tbl, long tcenum, return ret; } -static DEFINE_PER_CPU(u64 *, tce_page) = NULL; +static DEFINE_PER_CPU(u64 *, tce_page); static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, long npages, unsigned long uaddr, @@ -323,14 +323,13 @@ 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, - int bussubno) + const void *dma_window) { unsigned long offset, size; - tbl->it_busno = bussubno; of_parse_dma_window(dn, dma_window, &tbl->it_index, &offset, &size); + tbl->it_busno = phb->bus->number; tbl->it_base = 0; tbl->it_blocksize = 16; tbl->it_type = TCE_PCI; @@ -450,14 +449,10 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus) if (!ppci->iommu_table) { tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL, ppci->phb->node); - iommu_table_setparms_lpar(ppci->phb, pdn, tbl, dma_window, - bus->number); + iommu_table_setparms_lpar(ppci->phb, pdn, tbl, dma_window); ppci->iommu_table = iommu_init_table(tbl, ppci->phb->node); pr_debug(" created table: %p\n", ppci->iommu_table); } - - if (pdn != dn) - PCI_DN(dn)->iommu_table = ppci->iommu_table; } @@ -533,21 +528,11 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) } pr_debug(" parent is %s\n", pdn->full_name); - /* Check for parent == NULL so we don't try to setup the empty EADS - * slots on POWER4 machines. - */ - if (dma_window == NULL || pdn->parent == NULL) { - pr_debug(" no dma window for device, linking to parent\n"); - set_iommu_table_base(&dev->dev, PCI_DN(pdn)->iommu_table); - return; - } - pci = PCI_DN(pdn); if (!pci->iommu_table) { tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL, pci->phb->node); - iommu_table_setparms_lpar(pci->phb, pdn, tbl, dma_window, - pci->phb->bus->number); + iommu_table_setparms_lpar(pci->phb, pdn, tbl, dma_window); pci->iommu_table = iommu_init_table(tbl, pci->phb->node); pr_debug(" created table: %p\n", pci->iommu_table); } else { @@ -571,8 +556,7 @@ static int iommu_reconfig_notifier(struct notifier_block *nb, unsigned long acti switch (action) { case PSERIES_RECONFIG_REMOVE: - if (pci && pci->iommu_table && - of_get_property(np, "ibm,dma-window", NULL)) + if (pci && pci->iommu_table) iommu_free_table(pci->iommu_table, np->full_name); break; default: @@ -589,13 +573,8 @@ static struct notifier_block iommu_reconfig_nb = { /* These are called very early. */ void iommu_init_early_pSeries(void) { - if (of_chosen && of_get_property(of_chosen, "linux,iommu-off", NULL)) { - /* Direct I/O, IOMMU off */ - ppc_md.pci_dma_dev_setup = NULL; - ppc_md.pci_dma_bus_setup = NULL; - set_pci_dma_ops(&dma_direct_ops); + if (of_chosen && of_get_property(of_chosen, "linux,iommu-off", NULL)) return; - } if (firmware_has_feature(FW_FEATURE_LPAR)) { if (firmware_has_feature(FW_FEATURE_MULTITCE)) { @@ -622,3 +601,17 @@ void iommu_init_early_pSeries(void) set_pci_dma_ops(&dma_iommu_ops); } +static int __init disable_multitce(char *str) +{ + if (strcmp(str, "off") == 0 && + firmware_has_feature(FW_FEATURE_LPAR) && + firmware_has_feature(FW_FEATURE_MULTITCE)) { + printk(KERN_INFO "Disabling MULTITCE firmware feature\n"); + ppc_md.tce_build = tce_build_pSeriesLP; + ppc_md.tce_free = tce_free_pSeriesLP; + powerpc_firmware_features &= ~FW_FEATURE_MULTITCE; + } + return 1; +} + +__setup("multitce=", disable_multitce); diff --git a/arch/powerpc/platforms/pseries/kexec.c b/arch/powerpc/platforms/pseries/kexec.c index 53cbd53d8740..77d38a5e2ff9 100644 --- a/arch/powerpc/platforms/pseries/kexec.c +++ b/arch/powerpc/platforms/pseries/kexec.c @@ -61,13 +61,3 @@ void __init setup_kexec_cpu_down_xics(void) { ppc_md.kexec_cpu_down = pseries_kexec_cpu_down_xics; } - -static int __init pseries_kexec_setup(void) -{ - ppc_md.machine_kexec = default_machine_kexec; - ppc_md.machine_kexec_prepare = default_machine_kexec_prepare; - ppc_md.machine_crash_shutdown = default_machine_crash_shutdown; - - return 0; -} -machine_device_initcall(pseries, pseries_kexec_setup); diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index f129040d974c..5d3ea9f60dd7 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -627,6 +627,18 @@ static void pSeries_lpar_flush_hash_range(unsigned long number, int local) spin_unlock_irqrestore(&pSeries_lpar_tlbie_lock, flags); } +static int __init disable_bulk_remove(char *str) +{ + if (strcmp(str, "off") == 0 && + firmware_has_feature(FW_FEATURE_BULK_REMOVE)) { + printk(KERN_INFO "Disabling BULK_REMOVE firmware feature"); + powerpc_firmware_features &= ~FW_FEATURE_BULK_REMOVE; + } + return 1; +} + +__setup("bulk_remove=", disable_bulk_remove); + void __init hpte_init_lpar(void) { ppc_md.hpte_invalidate = pSeries_lpar_hpte_invalidate; diff --git a/arch/powerpc/platforms/pseries/nvram.c b/arch/powerpc/platforms/pseries/nvram.c index bc3c7f2abd79..7e828ba29bc3 100644 --- a/arch/powerpc/platforms/pseries/nvram.c +++ b/arch/powerpc/platforms/pseries/nvram.c @@ -22,11 +22,25 @@ #include <asm/prom.h> #include <asm/machdep.h> +/* Max bytes to read/write in one go */ +#define NVRW_CNT 0x20 + static unsigned int nvram_size; static int nvram_fetch, nvram_store; static char nvram_buf[NVRW_CNT]; /* assume this is in the first 4GB */ static DEFINE_SPINLOCK(nvram_lock); +static long nvram_error_log_index = -1; +static long nvram_error_log_size = 0; + +struct err_log_info { + int error_type; + unsigned int seq_num; +}; +#define NVRAM_MAX_REQ 2079 +#define NVRAM_MIN_REQ 1055 + +#define NVRAM_LOG_PART_NAME "ibm,rtas-log" static ssize_t pSeries_nvram_read(char *buf, size_t count, loff_t *index) { @@ -119,6 +133,197 @@ static ssize_t pSeries_nvram_get_size(void) return nvram_size ? nvram_size : -ENODEV; } + +/* nvram_write_error_log + * + * We need to buffer the error logs into nvram to ensure that we have + * the failure information to decode. If we have a severe error there + * is no way to guarantee that the OS or the machine is in a state to + * get back to user land and write the error to disk. For example if + * the SCSI device driver causes a Machine Check by writing to a bad + * IO address, there is no way of guaranteeing that the device driver + * is in any state that is would also be able to write the error data + * captured to disk, thus we buffer it in NVRAM for analysis on the + * next boot. + * + * In NVRAM the partition containing the error log buffer will looks like: + * Header (in bytes): + * +-----------+----------+--------+------------+------------------+ + * | signature | checksum | length | name | data | + * |0 |1 |2 3|4 15|16 length-1| + * +-----------+----------+--------+------------+------------------+ + * + * The 'data' section would look like (in bytes): + * +--------------+------------+-----------------------------------+ + * | event_logged | sequence # | error log | + * |0 3|4 7|8 nvram_error_log_size-1| + * +--------------+------------+-----------------------------------+ + * + * event_logged: 0 if event has not been logged to syslog, 1 if it has + * sequence #: The unique sequence # for each event. (until it wraps) + * error log: The error log from event_scan + */ +int nvram_write_error_log(char * buff, int length, + unsigned int err_type, unsigned int error_log_cnt) +{ + int rc; + loff_t tmp_index; + struct err_log_info info; + + if (nvram_error_log_index == -1) { + return -ESPIPE; + } + + if (length > nvram_error_log_size) { + length = nvram_error_log_size; + } + + info.error_type = err_type; + info.seq_num = error_log_cnt; + + tmp_index = nvram_error_log_index; + + rc = ppc_md.nvram_write((char *)&info, sizeof(struct err_log_info), &tmp_index); + if (rc <= 0) { + printk(KERN_ERR "nvram_write_error_log: Failed nvram_write (%d)\n", rc); + return rc; + } + + rc = ppc_md.nvram_write(buff, length, &tmp_index); + if (rc <= 0) { + printk(KERN_ERR "nvram_write_error_log: Failed nvram_write (%d)\n", rc); + return rc; + } + + return 0; +} + +/* nvram_read_error_log + * + * Reads nvram for error log for at most 'length' + */ +int nvram_read_error_log(char * buff, int length, + unsigned int * err_type, unsigned int * error_log_cnt) +{ + int rc; + loff_t tmp_index; + struct err_log_info info; + + if (nvram_error_log_index == -1) + return -1; + + if (length > nvram_error_log_size) + length = nvram_error_log_size; + + tmp_index = nvram_error_log_index; + + rc = ppc_md.nvram_read((char *)&info, sizeof(struct err_log_info), &tmp_index); + if (rc <= 0) { + printk(KERN_ERR "nvram_read_error_log: Failed nvram_read (%d)\n", rc); + return rc; + } + + rc = ppc_md.nvram_read(buff, length, &tmp_index); + if (rc <= 0) { + printk(KERN_ERR "nvram_read_error_log: Failed nvram_read (%d)\n", rc); + return rc; + } + + *error_log_cnt = info.seq_num; + *err_type = info.error_type; + + return 0; +} + +/* This doesn't actually zero anything, but it sets the event_logged + * word to tell that this event is safely in syslog. + */ +int nvram_clear_error_log(void) +{ + loff_t tmp_index; + int clear_word = ERR_FLAG_ALREADY_LOGGED; + int rc; + + if (nvram_error_log_index == -1) + return -1; + + tmp_index = nvram_error_log_index; + + rc = ppc_md.nvram_write((char *)&clear_word, sizeof(int), &tmp_index); + if (rc <= 0) { + printk(KERN_ERR "nvram_clear_error_log: Failed nvram_write (%d)\n", rc); + return rc; + } + + return 0; +} + +/* pseries_nvram_init_log_partition + * + * This will setup the partition we need for buffering the + * error logs and cleanup partitions if needed. + * + * The general strategy is the following: + * 1.) If there is log partition large enough then use it. + * 2.) If there is none large enough, search + * for a free partition that is large enough. + * 3.) If there is not a free partition large enough remove + * _all_ OS partitions and consolidate the space. + * 4.) Will first try getting a chunk that will satisfy the maximum + * error log size (NVRAM_MAX_REQ). + * 5.) If the max chunk cannot be allocated then try finding a chunk + * that will satisfy the minum needed (NVRAM_MIN_REQ). + */ +static int __init pseries_nvram_init_log_partition(void) +{ + loff_t p; + int size; + + /* Scan nvram for partitions */ + nvram_scan_partitions(); + + /* Lookg for ours */ + p = nvram_find_partition(NVRAM_LOG_PART_NAME, NVRAM_SIG_OS, &size); + + /* Found one but too small, remove it */ + if (p && size < NVRAM_MIN_REQ) { + pr_info("nvram: Found too small "NVRAM_LOG_PART_NAME" partition" + ",removing it..."); + nvram_remove_partition(NVRAM_LOG_PART_NAME, NVRAM_SIG_OS); + p = 0; + } + + /* Create one if we didn't find */ + if (!p) { + p = nvram_create_partition(NVRAM_LOG_PART_NAME, NVRAM_SIG_OS, + NVRAM_MAX_REQ, NVRAM_MIN_REQ); + /* No room for it, try to get rid of any OS partition + * and try again + */ + if (p == -ENOSPC) { + pr_info("nvram: No room to create "NVRAM_LOG_PART_NAME + " partition, deleting all OS partitions..."); + nvram_remove_partition(NULL, NVRAM_SIG_OS); + p = nvram_create_partition(NVRAM_LOG_PART_NAME, + NVRAM_SIG_OS, NVRAM_MAX_REQ, + NVRAM_MIN_REQ); + } + } + + if (p <= 0) { + pr_err("nvram: Failed to find or create "NVRAM_LOG_PART_NAME + " partition, err %d\n", (int)p); + return 0; + } + + nvram_error_log_index = p; + nvram_error_log_size = nvram_get_partition_size(p) - + sizeof(struct err_log_info); + + return 0; +} +machine_arch_initcall(pseries, pseries_nvram_init_log_partition); + int __init pSeries_nvram_init(void) { struct device_node *nvram; diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c index 4b7a062dee15..5fcc92a12d3e 100644 --- a/arch/powerpc/platforms/pseries/pci_dlpar.c +++ b/arch/powerpc/platforms/pseries/pci_dlpar.c @@ -25,8 +25,6 @@ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ -#undef DEBUG - #include <linux/pci.h> #include <asm/pci-bridge.h> #include <asm/ppc-pci.h> diff --git a/arch/powerpc/platforms/pseries/pseries_energy.c b/arch/powerpc/platforms/pseries/pseries_energy.c new file mode 100644 index 000000000000..c8b3c69fe891 --- /dev/null +++ b/arch/powerpc/platforms/pseries/pseries_energy.c @@ -0,0 +1,326 @@ +/* + * POWER platform energy management driver + * Copyright (C) 2010 IBM Corporation + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + * + * This pseries platform device driver provides access to + * platform energy management capabilities. + */ + +#include <linux/module.h> +#include <linux/types.h> +#include <linux/errno.h> +#include <linux/init.h> +#include <linux/seq_file.h> +#include <linux/sysdev.h> +#include <linux/cpu.h> +#include <linux/of.h> +#include <asm/cputhreads.h> +#include <asm/page.h> +#include <asm/hvcall.h> + + +#define MODULE_VERS "1.0" +#define MODULE_NAME "pseries_energy" + +/* Driver flags */ + +static int sysfs_entries; + +/* Helper routines */ + +/* + * Routine to detect firmware support for hcall + * return 1 if H_BEST_ENERGY is supported + * else return 0 + */ + +static int check_for_h_best_energy(void) +{ + struct device_node *rtas = NULL; + const char *hypertas, *s; + int length; + int rc = 0; + + rtas = of_find_node_by_path("/rtas"); + if (!rtas) + return 0; + + hypertas = of_get_property(rtas, "ibm,hypertas-functions", &length); + if (!hypertas) { + of_node_put(rtas); + return 0; + } + + /* hypertas will have list of strings with hcall names */ + for (s = hypertas; s < hypertas + length; s += strlen(s) + 1) { + if (!strncmp("hcall-best-energy-1", s, 19)) { + rc = 1; /* Found the string */ + break; + } + } + of_node_put(rtas); + return rc; +} + +/* Helper Routines to convert between drc_index to cpu numbers */ + +static u32 cpu_to_drc_index(int cpu) +{ + struct device_node *dn = NULL; + const int *indexes; + int i; + int rc = 1; + u32 ret = 0; + + dn = of_find_node_by_path("/cpus"); + if (dn == NULL) + goto err; + indexes = of_get_property(dn, "ibm,drc-indexes", NULL); + if (indexes == NULL) + goto err_of_node_put; + /* Convert logical cpu number to core number */ + i = cpu_core_index_of_thread(cpu); + /* + * The first element indexes[0] is the number of drc_indexes + * returned in the list. Hence i+1 will get the drc_index + * corresponding to core number i. + */ + WARN_ON(i > indexes[0]); + ret = indexes[i + 1]; + rc = 0; + +err_of_node_put: + of_node_put(dn); +err: + if (rc) + printk(KERN_WARNING "cpu_to_drc_index(%d) failed", cpu); + return ret; +} + +static int drc_index_to_cpu(u32 drc_index) +{ + struct device_node *dn = NULL; + const int *indexes; + int i, cpu = 0; + int rc = 1; + + dn = of_find_node_by_path("/cpus"); + if (dn == NULL) + goto err; + indexes = of_get_property(dn, "ibm,drc-indexes", NULL); + if (indexes == NULL) + goto err_of_node_put; + /* + * First element in the array is the number of drc_indexes + * returned. Search through the list to find the matching + * drc_index and get the core number + */ + for (i = 0; i < indexes[0]; i++) { + if (indexes[i + 1] == drc_index) + break; + } + /* Convert core number to logical cpu number */ + cpu = cpu_first_thread_of_core(i); + rc = 0; + +err_of_node_put: + of_node_put(dn); +err: + if (rc) + printk(KERN_WARNING "drc_index_to_cpu(%d) failed", drc_index); + return cpu; +} + +/* + * pseries hypervisor call H_BEST_ENERGY provides hints to OS on + * preferred logical cpus to activate or deactivate for optimized + * energy consumption. + */ + +#define FLAGS_MODE1 0x004E200000080E01 +#define FLAGS_MODE2 0x004E200000080401 +#define FLAGS_ACTIVATE 0x100 + +static ssize_t get_best_energy_list(char *page, int activate) +{ + int rc, cnt, i, cpu; + unsigned long retbuf[PLPAR_HCALL9_BUFSIZE]; + unsigned long flags = 0; + u32 *buf_page; + char *s = page; + + buf_page = (u32 *) get_zeroed_page(GFP_KERNEL); + if (!buf_page) + return -ENOMEM; + + flags = FLAGS_MODE1; + if (activate) + flags |= FLAGS_ACTIVATE; + + rc = plpar_hcall9(H_BEST_ENERGY, retbuf, flags, 0, __pa(buf_page), + 0, 0, 0, 0, 0, 0); + if (rc != H_SUCCESS) { + free_page((unsigned long) buf_page); + return -EINVAL; + } + + cnt = retbuf[0]; + for (i = 0; i < cnt; i++) { + cpu = drc_index_to_cpu(buf_page[2*i+1]); + if ((cpu_online(cpu) && !activate) || + (!cpu_online(cpu) && activate)) + s += sprintf(s, "%d,", cpu); + } + if (s > page) { /* Something to show */ + s--; /* Suppress last comma */ + s += sprintf(s, "\n"); + } + + free_page((unsigned long) buf_page); + return s-page; +} + +static ssize_t get_best_energy_data(struct sys_device *dev, + char *page, int activate) +{ + int rc; + unsigned long retbuf[PLPAR_HCALL9_BUFSIZE]; + unsigned long flags = 0; + + flags = FLAGS_MODE2; + if (activate) + flags |= FLAGS_ACTIVATE; + + rc = plpar_hcall9(H_BEST_ENERGY, retbuf, flags, + cpu_to_drc_index(dev->id), + 0, 0, 0, 0, 0, 0, 0); + + if (rc != H_SUCCESS) + return -EINVAL; + + return sprintf(page, "%lu\n", retbuf[1] >> 32); +} + +/* Wrapper functions */ + +static ssize_t cpu_activate_hint_list_show(struct sysdev_class *class, + struct sysdev_class_attribute *attr, char *page) +{ + return get_best_energy_list(page, 1); +} + +static ssize_t cpu_deactivate_hint_list_show(struct sysdev_class *class, + struct sysdev_class_attribute *attr, char *page) +{ + return get_best_energy_list(page, 0); +} + +static ssize_t percpu_activate_hint_show(struct sys_device *dev, + struct sysdev_attribute *attr, char *page) +{ + return get_best_energy_data(dev, page, 1); +} + +static ssize_t percpu_deactivate_hint_show(struct sys_device *dev, + struct sysdev_attribute *attr, char *page) +{ + return get_best_energy_data(dev, page, 0); +} + +/* + * Create sysfs interface: + * /sys/devices/system/cpu/pseries_activate_hint_list + * /sys/devices/system/cpu/pseries_deactivate_hint_list + * Comma separated list of cpus to activate or deactivate + * /sys/devices/system/cpu/cpuN/pseries_activate_hint + * /sys/devices/system/cpu/cpuN/pseries_deactivate_hint + * Per-cpu value of the hint + */ + +struct sysdev_class_attribute attr_cpu_activate_hint_list = + _SYSDEV_CLASS_ATTR(pseries_activate_hint_list, 0444, + cpu_activate_hint_list_show, NULL); + +struct sysdev_class_attribute attr_cpu_deactivate_hint_list = + _SYSDEV_CLASS_ATTR(pseries_deactivate_hint_list, 0444, + cpu_deactivate_hint_list_show, NULL); + +struct sysdev_attribute attr_percpu_activate_hint = + _SYSDEV_ATTR(pseries_activate_hint, 0444, + percpu_activate_hint_show, NULL); + +struct sysdev_attribute attr_percpu_deactivate_hint = + _SYSDEV_ATTR(pseries_deactivate_hint, 0444, + percpu_deactivate_hint_show, NULL); + +static int __init pseries_energy_init(void) +{ + int cpu, err; + struct sys_device *cpu_sys_dev; + + if (!check_for_h_best_energy()) { + printk(KERN_INFO "Hypercall H_BEST_ENERGY not supported\n"); + return 0; + } + /* Create the sysfs files */ + err = sysfs_create_file(&cpu_sysdev_class.kset.kobj, + &attr_cpu_activate_hint_list.attr); + if (!err) + err = sysfs_create_file(&cpu_sysdev_class.kset.kobj, + &attr_cpu_deactivate_hint_list.attr); + + if (err) + return err; + for_each_possible_cpu(cpu) { + cpu_sys_dev = get_cpu_sysdev(cpu); + err = sysfs_create_file(&cpu_sys_dev->kobj, + &attr_percpu_activate_hint.attr); + if (err) + break; + err = sysfs_create_file(&cpu_sys_dev->kobj, + &attr_percpu_deactivate_hint.attr); + if (err) + break; + } + + if (err) + return err; + + sysfs_entries = 1; /* Removed entries on cleanup */ + return 0; + +} + +static void __exit pseries_energy_cleanup(void) +{ + int cpu; + struct sys_device *cpu_sys_dev; + + if (!sysfs_entries) + return; + + /* Remove the sysfs files */ + sysfs_remove_file(&cpu_sysdev_class.kset.kobj, + &attr_cpu_activate_hint_list.attr); + + sysfs_remove_file(&cpu_sysdev_class.kset.kobj, + &attr_cpu_deactivate_hint_list.attr); + + for_each_possible_cpu(cpu) { + cpu_sys_dev = get_cpu_sysdev(cpu); + sysfs_remove_file(&cpu_sys_dev->kobj, + &attr_percpu_activate_hint.attr); + sysfs_remove_file(&cpu_sys_dev->kobj, + &attr_percpu_deactivate_hint.attr); + } +} + +module_init(pseries_energy_init); +module_exit(pseries_energy_cleanup); +MODULE_DESCRIPTION("Driver for pSeries platform energy management"); +MODULE_AUTHOR("Vaidyanathan Srinivasan"); +MODULE_LICENSE("GPL"); diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index a4fc6da87c2e..c55d7ad9c648 100644 --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -54,7 +54,8 @@ static unsigned char ras_log_buf[RTAS_ERROR_LOG_MAX]; static DEFINE_SPINLOCK(ras_log_buf_lock); -static char mce_data_buf[RTAS_ERROR_LOG_MAX]; +static char global_mce_data_buf[RTAS_ERROR_LOG_MAX]; +static DEFINE_PER_CPU(__u64, mce_data_buf); static int ras_get_sensor_state_token; static int ras_check_exception_token; @@ -196,12 +197,24 @@ static irqreturn_t ras_error_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -/* Get the error information for errors coming through the +/* + * Some versions of FWNMI place the buffer inside the 4kB page starting at + * 0x7000. Other versions place it inside the rtas buffer. We check both. + */ +#define VALID_FWNMI_BUFFER(A) \ + ((((A) >= 0x7000) && ((A) < 0x7ff0)) || \ + (((A) >= rtas.base) && ((A) < (rtas.base + rtas.size - 16)))) + +/* + * Get the error information for errors coming through the * FWNMI vectors. The pt_regs' r3 will be updated to reflect * the actual r3 if possible, and a ptr to the error log entry * will be returned if found. * - * The mce_data_buf does not have any locks or protection around it, + * If the RTAS error is not of the extended type, then we put it in a per + * cpu 64bit buffer. If it is the extended type we use global_mce_data_buf. + * + * The global_mce_data_buf does not have any locks or protection around it, * if a second machine check comes in, or a system reset is done * before we have logged the error, then we will get corruption in the * error log. This is preferable over holding off on calling @@ -210,20 +223,31 @@ static irqreturn_t ras_error_interrupt(int irq, void *dev_id) */ static struct rtas_error_log *fwnmi_get_errinfo(struct pt_regs *regs) { - unsigned long errdata = regs->gpr[3]; - struct rtas_error_log *errhdr = NULL; unsigned long *savep; + struct rtas_error_log *h, *errhdr = NULL; + + if (!VALID_FWNMI_BUFFER(regs->gpr[3])) { + printk(KERN_ERR "FWNMI: corrupt r3\n"); + return NULL; + } - if ((errdata >= 0x7000 && errdata < 0x7fff0) || - (errdata >= rtas.base && errdata < rtas.base + rtas.size - 16)) { - savep = __va(errdata); - regs->gpr[3] = savep[0]; /* restore original r3 */ - memset(mce_data_buf, 0, RTAS_ERROR_LOG_MAX); - memcpy(mce_data_buf, (char *)(savep + 1), RTAS_ERROR_LOG_MAX); - errhdr = (struct rtas_error_log *)mce_data_buf; + savep = __va(regs->gpr[3]); + regs->gpr[3] = savep[0]; /* restore original r3 */ + + /* 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) { + memcpy(&__get_cpu_var(mce_data_buf), h, sizeof(__u64)); + errhdr = (struct rtas_error_log *)&__get_cpu_var(mce_data_buf); } else { - printk("FWNMI: corrupt r3\n"); + int len; + + len = max_t(int, 8+h->extended_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; } + return errhdr; } @@ -235,7 +259,7 @@ static void fwnmi_release_errinfo(void) { int ret = rtas_call(rtas_token("ibm,nmi-interlock"), 0, 1, NULL); if (ret != 0) - printk("FWNMI: nmi-interlock failed: %d\n", ret); + printk(KERN_ERR "FWNMI: nmi-interlock failed: %d\n", ret); } int pSeries_system_reset_exception(struct pt_regs *regs) @@ -259,31 +283,43 @@ int pSeries_system_reset_exception(struct pt_regs *regs) * Return 1 if corrected (or delivered a signal). * Return 0 if there is nothing we can do. */ -static int recover_mce(struct pt_regs *regs, struct rtas_error_log * err) +static int recover_mce(struct pt_regs *regs, struct rtas_error_log *err) { - int nonfatal = 0; + int recovered = 0; - if (err->disposition == RTAS_DISP_FULLY_RECOVERED) { + if (!(regs->msr & MSR_RI)) { + /* If MSR_RI isn't set, we cannot recover */ + recovered = 0; + + } else if (err->disposition == RTAS_DISP_FULLY_RECOVERED) { /* Platform corrected itself */ - nonfatal = 1; - } else if ((regs->msr & MSR_RI) && - user_mode(regs) && - err->severity == RTAS_SEVERITY_ERROR_SYNC && - err->disposition == RTAS_DISP_NOT_RECOVERED && - err->target == RTAS_TARGET_MEMORY && - err->type == RTAS_TYPE_ECC_UNCORR && - !(current->pid == 0 || is_global_init(current))) { - /* Kill off a user process with an ECC error */ - printk(KERN_ERR "MCE: uncorrectable ecc error for pid %d\n", - current->pid); - /* XXX something better for ECC error? */ - _exception(SIGBUS, regs, BUS_ADRERR, regs->nip); - nonfatal = 1; + recovered = 1; + + } else if (err->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) { + + /* + * If we received a synchronous error when in userspace + * kill the task. Firmware may report details of the fail + * asynchronously, so we can't rely on the target and type + * fields being valid here. + */ + printk(KERN_ERR "MCE: uncorrectable error, killing task " + "%s:%d\n", current->comm, current->pid); + + _exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip); + recovered = 1; } - log_error((char *)err, ERR_TYPE_RTAS_LOG, !nonfatal); + log_error((char *)err, ERR_TYPE_RTAS_LOG, 0); - return nonfatal; + return recovered; } /* diff --git a/arch/powerpc/platforms/pseries/suspend.c b/arch/powerpc/platforms/pseries/suspend.c index ed72098bb4e3..a8ca289ff267 100644 --- a/arch/powerpc/platforms/pseries/suspend.c +++ b/arch/powerpc/platforms/pseries/suspend.c @@ -153,7 +153,7 @@ static struct sysdev_class suspend_sysdev_class = { .name = "power", }; -static struct platform_suspend_ops pseries_suspend_ops = { +static const struct platform_suspend_ops pseries_suspend_ops = { .valid = suspend_valid_only_mem, .begin = pseries_suspend_begin, .prepare_late = pseries_prepare_late, |