diff options
Diffstat (limited to 'arch/powerpc/platforms/pseries')
23 files changed, 1029 insertions, 524 deletions
diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile index 8ae01038131..fbccac9cd2d 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 @@ -22,6 +22,7 @@ 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..1e561bef459 100644 --- a/arch/powerpc/platforms/pseries/cmm.c +++ b/arch/powerpc/platforms/pseries/cmm.c @@ -40,8 +40,7 @@ #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..a8fe5aa3d34 100644 --- a/arch/powerpc/platforms/pseries/dlpar.c +++ b/arch/powerpc/platforms/pseries/dlpar.c @@ -63,26 +63,32 @@ 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); + kref_init(&dn->kref); + return dn; } @@ -120,7 +126,8 @@ 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 +136,7 @@ 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 +170,7 @@ 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 +180,17 @@ 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 +214,7 @@ 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 +269,6 @@ 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 +286,15 @@ 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 +400,42 @@ 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 +508,27 @@ 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..5db66f1fbc2 100644 --- a/arch/powerpc/platforms/pseries/dtl.c +++ b/arch/powerpc/platforms/pseries/dtl.c @@ -29,8 +29,7 @@ #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 +86,7 @@ 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 7fbc25b1813..ccb633e077b 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -189,8 +189,9 @@ static void *pseries_eeh_of_probe(struct device_node *dn, void *flag) struct eeh_dev *edev; struct eeh_pe pe; struct pci_dn *pdn = PCI_DN(dn); - const u32 *class_code, *vendor_id, *device_id; - const u32 *regs; + const __be32 *classp, *vendorp, *devicep; + u32 class_code; + const __be32 *regs; u32 pcie_flags; int enable = 0; int ret; @@ -201,22 +202,24 @@ static void *pseries_eeh_of_probe(struct device_node *dn, void *flag) 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; + 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->class_code = class_code; edev->pcie_cap = pseries_eeh_find_cap(dn, PCI_CAP_ID_EXP); edev->mode &= 0xFFFFFF00; if ((edev->class_code >> 8) == PCI_CLASS_BRIDGE_PCI) { @@ -243,12 +246,12 @@ 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; 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..82789e79e53 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -30,7 +30,8 @@ #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 */ @@ -123,7 +124,7 @@ 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 +138,7 @@ 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; diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 9a432de363b..9590dbb756f 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -10,12 +10,14 @@ */ #include <linux/of.h> +#include <linux/of_address.h> #include <linux/memblock.h> #include <linux/vmalloc.h> #include <linux/memory.h> #include <asm/firmware.h> #include <asm/machdep.h> +#include <asm/prom.h> #include <asm/sparsemem.h> static unsigned long get_memblock_size(void) 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/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 23fc1dcf443..f253361552a 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; } @@ -530,7 +530,7 @@ 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; @@ -630,7 +630,7 @@ 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); @@ -781,7 +781,7 @@ 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; } } @@ -1046,11 +1046,11 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) dev_dbg(&dev->dev, "no free dynamic windows"); goto out_restore_window; } - 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", @@ -1060,7 +1060,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) /* 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); @@ -1086,7 +1086,7 @@ 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); @@ -1152,7 +1152,7 @@ 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)); @@ -1201,7 +1201,7 @@ 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 8bad880bd17..4fca3def9db 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; @@ -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) " @@ -239,6 +245,23 @@ 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 +747,7 @@ 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..e738007eae6 --- /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 int *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 && (*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 int *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 = *(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 unsigned int *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 = *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..cde4e0a095a 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); diff --git a/arch/powerpc/platforms/pseries/nvram.c b/arch/powerpc/platforms/pseries/nvram.c index 10630eac68e..7bfaf58d466 100644 --- a/arch/powerpc/platforms/pseries/nvram.c +++ b/arch/powerpc/platforms/pseries/nvram.c @@ -429,9 +429,6 @@ 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); @@ -795,6 +792,9 @@ 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; @@ -804,7 +804,7 @@ 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"); @@ -817,7 +817,7 @@ 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"); 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 index 4644efa0694..a166e38bd68 100644 --- a/arch/powerpc/platforms/pseries/processor_idle.c +++ b/arch/powerpc/platforms/pseries/processor_idle.c @@ -18,9 +18,7 @@ #include <asm/machdep.h> #include <asm/firmware.h> #include <asm/runlatch.h> - -#include "plpar_wrappers.h" -#include "pseries.h" +#include <asm/plpar_wrappers.h> struct cpuidle_driver pseries_idle_driver = { .name = "pseries_idle", @@ -45,7 +43,11 @@ static inline void idle_loop_prolog(unsigned long *in_purr) static inline void idle_loop_epilog(unsigned long in_purr) { - get_lppaca()->wait_state_cycles += mfspr(SPRN_PURR) - in_purr; + u64 wait_cycles; + + wait_cycles = be64_to_cpu(get_lppaca()->wait_state_cycles); + wait_cycles += mfspr(SPRN_PURR) - in_purr; + get_lppaca()->wait_state_cycles = cpu_to_be64(wait_cycles); get_lppaca()->idle = 0; } @@ -308,7 +310,7 @@ static int pseries_idle_probe(void) return -EPERM; } - if (get_lppaca()->shared_proc) + if (lppaca_shared_proc(get_lppaca())) cpuidle_state_table = shared_states; else cpuidle_state_table = dedicated_states; diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h index c2a3a258001..99219530ea4 100644 --- a/arch/powerpc/platforms/pseries/pseries.h +++ b/arch/powerpc/platforms/pseries/pseries.h @@ -56,13 +56,10 @@ 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); 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/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..c1f19085870 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -66,8 +66,8 @@ #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; @@ -183,7 +183,7 @@ 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 +323,7 @@ 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 " @@ -354,7 +354,7 @@ 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 @@ -362,10 +362,22 @@ static void pSeries_idle(void) if (cpuidle_idle_call()) { /* On error, execute default handler * to go into low thread priority and possibly - * low power mode. + * low power mode by cedeing processor to hypervisor */ - 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; } } @@ -430,6 +442,32 @@ 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; @@ -456,15 +494,14 @@ 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; @@ -687,6 +724,22 @@ 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 diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c index 306643cc9db..24f58cb0a54 100644 --- a/arch/powerpc/platforms/pseries/smp.c +++ b/arch/powerpc/platforms/pseries/smp.c @@ -43,8 +43,8 @@ #include <asm/cputhreads.h> #include <asm/xics.h> #include <asm/dbell.h> +#include <asm/plpar_wrappers.h> -#include "plpar_wrappers.h" #include "pseries.h" #include "offline_states.h" @@ -187,22 +187,6 @@ 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 +221,7 @@ 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 +233,24 @@ 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..16a255255d3 100644 --- a/arch/powerpc/platforms/pseries/suspend.c +++ b/arch/powerpc/platforms/pseries/suspend.c @@ -106,7 +106,7 @@ 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; } |