diff options
Diffstat (limited to 'arch/ia64/kernel')
59 files changed, 1055 insertions, 2379 deletions
diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile index 395c2f216dd..20678a9ed11 100644 --- a/arch/ia64/kernel/Makefile +++ b/arch/ia64/kernel/Makefile @@ -23,7 +23,6 @@ obj-$(CONFIG_SMP) += smp.o smpboot.o obj-$(CONFIG_NUMA) += numa.o obj-$(CONFIG_PERFMON) += perfmon_default_smpl.o obj-$(CONFIG_IA64_CYCLONE) += cyclone.o -obj-$(CONFIG_CPU_FREQ) += cpufreq/ obj-$(CONFIG_IA64_MCA_RECOVERY) += mca_recovery.o obj-$(CONFIG_KPROBES) += kprobes.o jprobes.o obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o @@ -43,7 +42,7 @@ obj-$(CONFIG_IA64_ESI) += esi.o ifneq ($(CONFIG_IA64_ESI),) obj-y += esi_stub.o # must be in kernel proper endif -obj-$(CONFIG_DMAR) += pci-dma.o +obj-$(CONFIG_INTEL_IOMMU) += pci-dma.o obj-$(CONFIG_SWIOTLB) += pci-swiotlb.o obj-$(CONFIG_BINFMT_ELF) += elfcore.o diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c index c6c90f39f4d..615ef81def4 100644 --- a/arch/ia64/kernel/acpi.c +++ b/arch/ia64/kernel/acpi.c @@ -50,19 +50,13 @@ #include <asm/iosapic.h> #include <asm/machvec.h> #include <asm/page.h> -#include <asm/system.h> #include <asm/numa.h> #include <asm/sal.h> #include <asm/cyclone.h> -#include <asm/xen/hypervisor.h> - -#define BAD_MADT_ENTRY(entry, end) ( \ - (!entry) || (unsigned long)entry + sizeof(*entry) > end || \ - ((struct acpi_subtable_header *)entry)->length < sizeof(*entry)) #define PREFIX "ACPI: " -u32 acpi_rsdt_forced; +int acpi_lapic; unsigned int acpi_cpei_override; unsigned int acpi_cpei_phys_cpuid; @@ -88,7 +82,7 @@ acpi_get_sysname(void) struct acpi_table_rsdp *rsdp; struct acpi_table_xsdt *xsdt; struct acpi_table_header *hdr; -#ifdef CONFIG_DMAR +#ifdef CONFIG_INTEL_IOMMU u64 i, nentries; #endif @@ -121,11 +115,9 @@ acpi_get_sysname(void) return "uv"; else return "sn2"; - } else if (xen_pv_domain() && !strcmp(hdr->oem_id, "XEN")) { - return "xen"; } -#ifdef CONFIG_DMAR +#ifdef CONFIG_INTEL_IOMMU /* Look for Intel IOMMU */ nentries = (hdr->length - sizeof(*hdr)) / sizeof(xsdt->table_offset_entry[0]); @@ -349,11 +341,11 @@ acpi_parse_int_src_ovr(struct acpi_subtable_header * header, iosapic_override_isa_irq(p->source_irq, p->global_irq, ((p->inti_flags & ACPI_MADT_POLARITY_MASK) == - ACPI_MADT_POLARITY_ACTIVE_HIGH) ? - IOSAPIC_POL_HIGH : IOSAPIC_POL_LOW, + ACPI_MADT_POLARITY_ACTIVE_LOW) ? + IOSAPIC_POL_LOW : IOSAPIC_POL_HIGH, ((p->inti_flags & ACPI_MADT_TRIGGER_MASK) == - ACPI_MADT_TRIGGER_EDGE) ? - IOSAPIC_EDGE : IOSAPIC_LEVEL); + ACPI_MADT_TRIGGER_LEVEL) ? + IOSAPIC_LEVEL : IOSAPIC_EDGE); return 0; } @@ -423,28 +415,30 @@ static int __init acpi_parse_madt(struct acpi_table_header *table) #define PXM_FLAG_LEN ((MAX_PXM_DOMAINS + 1)/32) static int __initdata srat_num_cpus; /* number of cpus */ -static u32 __devinitdata pxm_flag[PXM_FLAG_LEN]; +static u32 pxm_flag[PXM_FLAG_LEN]; #define pxm_bit_set(bit) (set_bit(bit,(void *)pxm_flag)) #define pxm_bit_test(bit) (test_bit(bit,(void *)pxm_flag)) static struct acpi_table_slit __initdata *slit_table; cpumask_t early_cpu_possible_map = CPU_MASK_NONE; -static int get_processor_proximity_domain(struct acpi_srat_cpu_affinity *pa) +static int __init +get_processor_proximity_domain(struct acpi_srat_cpu_affinity *pa) { int pxm; pxm = pa->proximity_domain_lo; - if (ia64_platform_is("sn2")) + if (ia64_platform_is("sn2") || acpi_srat_revision >= 2) pxm += pa->proximity_domain_hi[0] << 8; return pxm; } -static int get_memory_proximity_domain(struct acpi_srat_mem_affinity *ma) +static int __init +get_memory_proximity_domain(struct acpi_srat_mem_affinity *ma) { int pxm; pxm = ma->proximity_domain; - if (!ia64_platform_is("sn2")) + if (!ia64_platform_is("sn2") && acpi_srat_revision <= 1) pxm &= 0xff; return pxm; @@ -477,6 +471,12 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) if (!(pa->flags & ACPI_SRAT_CPU_ENABLED)) return; + if (srat_num_cpus >= ARRAY_SIZE(node_cpuid)) { + printk_once(KERN_WARNING + "node_cpuid[%ld] is too small, may not be able to use all cpus\n", + ARRAY_SIZE(node_cpuid)); + return; + } pxm = get_processor_proximity_domain(pa); /* record this node in proximity bitmap */ @@ -490,7 +490,7 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) srat_num_cpus++; } -void __init +int __init acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) { unsigned long paddr, size; @@ -505,7 +505,7 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) /* Ignore disabled entries */ if (!(ma->flags & ACPI_SRAT_MEM_ENABLED)) - return; + return -1; /* record this node in proximity bitmap */ pxm_bit_set(pxm); @@ -524,6 +524,7 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) p->size = size; p->nid = pxm; num_node_memblks++; + return 0; } void __init acpi_numa_arch_fixup(void) @@ -625,6 +626,7 @@ int acpi_register_gsi(struct device *dev, u32 gsi, int triggering, int polarity) ACPI_EDGE_SENSITIVE) ? IOSAPIC_EDGE : IOSAPIC_LEVEL); } +EXPORT_SYMBOL_GPL(acpi_register_gsi); void acpi_unregister_gsi(u32 gsi) { @@ -636,6 +638,7 @@ void acpi_unregister_gsi(u32 gsi) iosapic_unregister_intr(gsi); } +EXPORT_SYMBOL_GPL(acpi_unregister_gsi); static int __init acpi_parse_fadt(struct acpi_table_header *table) { @@ -674,6 +677,8 @@ int __init early_acpi_boot_init(void) if (ret < 1) printk(KERN_ERR PREFIX "Error parsing MADT - no LAPIC entries\n"); + else + acpi_lapic = 1; #ifdef CONFIG_SMP if (available_cpus == 0) { @@ -797,14 +802,9 @@ int acpi_isa_irq_to_gsi(unsigned isa_irq, u32 *gsi) * ACPI based hotplug CPU support */ #ifdef CONFIG_ACPI_HOTPLUG_CPU -static -int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) +static int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) { #ifdef CONFIG_ACPI_NUMA - int pxm_id; - int nid; - - pxm_id = acpi_get_pxm(handle); /* * We don't have cpu-only-node hotadd. But if the system equips * SRAT table, pxm is already found and node is ready. @@ -812,11 +812,10 @@ int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) * This code here is for the system which doesn't have full SRAT * table for possible cpus. */ - nid = acpi_map_pxm_to_node(pxm_id); node_cpuid[cpu].phys_id = physid; - node_cpuid[cpu].nid = nid; + node_cpuid[cpu].nid = acpi_get_node(handle); #endif - return (0); + return 0; } int additional_cpus __initdata = -1; @@ -832,11 +831,11 @@ static __init int setup_additional_cpus(char *s) early_param("additional_cpus", setup_additional_cpus); /* - * cpu_possible_map should be static, it cannot change as CPUs + * cpu_possible_mask should be static, it cannot change as CPUs * are onlined, or offlined. The reason is per-cpu data-structures * are allocated by some modules at init time, and dont expect to * do this dynamically on cpu arrival/departure. - * cpu_present_map on the other hand can change dynamically. + * cpu_present_mask on the other hand can change dynamically. * In case when cpu_hotplug is not compiled, then we resort to current * behaviour, which is cpu_possible == cpu_present. * - Ashok Raj @@ -872,40 +871,10 @@ __init void prefill_possible_map(void) set_cpu_possible(i, true); } -int acpi_map_lsapic(acpi_handle handle, int *pcpu) +static int _acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu) { - struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; - union acpi_object *obj; - struct acpi_madt_local_sapic *lsapic; cpumask_t tmp_map; - int cpu, physid; - - if (ACPI_FAILURE(acpi_evaluate_object(handle, "_MAT", NULL, &buffer))) - return -EINVAL; - - if (!buffer.length || !buffer.pointer) - return -EINVAL; - - obj = buffer.pointer; - if (obj->type != ACPI_TYPE_BUFFER) - { - kfree(buffer.pointer); - return -EINVAL; - } - - lsapic = (struct acpi_madt_local_sapic *)obj->buffer.pointer; - - if ((lsapic->header.type != ACPI_MADT_TYPE_LOCAL_SAPIC) || - (!(lsapic->lapic_flags & ACPI_MADT_ENABLED))) { - kfree(buffer.pointer); - return -EINVAL; - } - - physid = ((lsapic->id << 8) | (lsapic->eid)); - - kfree(buffer.pointer); - buffer.length = ACPI_ALLOCATE_BUFFER; - buffer.pointer = NULL; + int cpu; cpumask_complement(&tmp_map, cpu_present_mask); cpu = cpumask_first(&tmp_map); @@ -914,7 +883,7 @@ int acpi_map_lsapic(acpi_handle handle, int *pcpu) acpi_map_cpu2node(handle, cpu, physid); - cpu_set(cpu, cpu_present_map); + set_cpu_present(cpu, true); ia64_cpu_to_sapicid[cpu] = physid; acpi_processor_set_pdc(handle); @@ -923,12 +892,17 @@ int acpi_map_lsapic(acpi_handle handle, int *pcpu) return (0); } +/* wrapper to silence section mismatch warning */ +int __ref acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu) +{ + return _acpi_map_lsapic(handle, physid, pcpu); +} EXPORT_SYMBOL(acpi_map_lsapic); int acpi_unmap_lsapic(int cpu) { ia64_cpu_to_sapicid[cpu] = -1; - cpu_clear(cpu, cpu_present_map); + set_cpu_present(cpu, false); #ifdef CONFIG_ACPI_NUMA /* NUMA specific cleanup's */ @@ -941,14 +915,14 @@ EXPORT_SYMBOL(acpi_unmap_lsapic); #endif /* CONFIG_ACPI_HOTPLUG_CPU */ #ifdef CONFIG_ACPI_NUMA -static acpi_status __devinit -acpi_map_iosapic(acpi_handle handle, u32 depth, void *context, void **ret) +static acpi_status acpi_map_iosapic(acpi_handle handle, u32 depth, + void *context, void **ret) { struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; union acpi_object *obj; struct acpi_madt_io_sapic *iosapic; unsigned int gsi_base; - int pxm, node; + int node; /* Only care about objects w/ a method that returns the MADT */ if (ACPI_FAILURE(acpi_evaluate_object(handle, "_MAT", NULL, &buffer))) @@ -975,17 +949,9 @@ acpi_map_iosapic(acpi_handle handle, u32 depth, void *context, void **ret) kfree(buffer.pointer); - /* - * OK, it's an IOSAPIC MADT entry, look for a _PXM value to tell - * us which node to associate this with. - */ - pxm = acpi_get_pxm(handle); - if (pxm < 0) - return AE_OK; - - node = pxm_to_node(pxm); - - if (node >= MAX_NUMNODES || !node_online(node) || + /* OK, it's an IOSAPIC MADT entry; associate it with a node */ + node = acpi_get_node(handle); + if (node == NUMA_NO_NODE || !node_online(node) || cpumask_empty(cpumask_of_node(node))) return AE_OK; @@ -1028,18 +994,8 @@ int acpi_unregister_ioapic(acpi_handle handle, u32 gsi_base) EXPORT_SYMBOL(acpi_unregister_ioapic); /* - * acpi_save_state_mem() - save kernel state + * acpi_suspend_lowlevel() - save kernel state and suspend. * * TBD when when IA64 starts to support suspend... */ -int acpi_save_state_mem(void) { return 0; } - -/* - * acpi_restore_state() - */ -void acpi_restore_state_mem(void) {} - -/* - * do_suspend_lowlevel() - */ -void do_suspend_lowlevel(void) {} +int acpi_suspend_lowlevel(void) { return 0; } diff --git a/arch/ia64/kernel/asm-offsets.c b/arch/ia64/kernel/asm-offsets.c index af565016904..60ef83e6db7 100644 --- a/arch/ia64/kernel/asm-offsets.c +++ b/arch/ia64/kernel/asm-offsets.c @@ -16,9 +16,6 @@ #include <asm/sigcontext.h> #include <asm/mca.h> -#include <asm/xen/interface.h> -#include <asm/xen/hypervisor.h> - #include "../kernel/sigframe.h" #include "../kernel/fsyscall_gtod_data.h" @@ -41,7 +38,7 @@ void foo(void) DEFINE(TI_FLAGS, offsetof(struct thread_info, flags)); DEFINE(TI_CPU, offsetof(struct thread_info, cpu)); DEFINE(TI_PRE_COUNT, offsetof(struct thread_info, preempt_count)); -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE DEFINE(TI_AC_STAMP, offsetof(struct thread_info, ac_stamp)); DEFINE(TI_AC_LEAVE, offsetof(struct thread_info, ac_leave)); DEFINE(TI_AC_STIME, offsetof(struct thread_info, ac_stime)); @@ -269,8 +266,8 @@ void foo(void) BLANK(); /* used by fsys_gettimeofday in arch/ia64/kernel/fsys.S */ - DEFINE(IA64_GTOD_LOCK_OFFSET, - offsetof (struct fsyscall_gtod_data_t, lock)); + DEFINE(IA64_GTOD_SEQ_OFFSET, + offsetof (struct fsyscall_gtod_data_t, seq)); DEFINE(IA64_GTOD_WALL_TIME_OFFSET, offsetof (struct fsyscall_gtod_data_t, wall_time)); DEFINE(IA64_GTOD_MONO_TIME_OFFSET, @@ -290,33 +287,4 @@ void foo(void) DEFINE(IA64_ITC_LASTCYCLE_OFFSET, offsetof (struct itc_jitter_data_t, itc_lastcycle)); -#ifdef CONFIG_XEN - BLANK(); - - DEFINE(XEN_NATIVE_ASM, XEN_NATIVE); - DEFINE(XEN_PV_DOMAIN_ASM, XEN_PV_DOMAIN); - -#define DEFINE_MAPPED_REG_OFS(sym, field) \ - DEFINE(sym, (XMAPPEDREGS_OFS + offsetof(struct mapped_regs, field))) - - DEFINE_MAPPED_REG_OFS(XSI_PSR_I_ADDR_OFS, interrupt_mask_addr); - DEFINE_MAPPED_REG_OFS(XSI_IPSR_OFS, ipsr); - DEFINE_MAPPED_REG_OFS(XSI_IIP_OFS, iip); - DEFINE_MAPPED_REG_OFS(XSI_IFS_OFS, ifs); - DEFINE_MAPPED_REG_OFS(XSI_PRECOVER_IFS_OFS, precover_ifs); - DEFINE_MAPPED_REG_OFS(XSI_ISR_OFS, isr); - DEFINE_MAPPED_REG_OFS(XSI_IFA_OFS, ifa); - DEFINE_MAPPED_REG_OFS(XSI_IIPA_OFS, iipa); - DEFINE_MAPPED_REG_OFS(XSI_IIM_OFS, iim); - DEFINE_MAPPED_REG_OFS(XSI_IHA_OFS, iha); - DEFINE_MAPPED_REG_OFS(XSI_ITIR_OFS, itir); - DEFINE_MAPPED_REG_OFS(XSI_PSR_IC_OFS, interrupt_collection_enabled); - DEFINE_MAPPED_REG_OFS(XSI_BANKNUM_OFS, banknum); - DEFINE_MAPPED_REG_OFS(XSI_BANK0_R16_OFS, bank0_regs[0]); - DEFINE_MAPPED_REG_OFS(XSI_BANK1_R16_OFS, bank1_regs[0]); - DEFINE_MAPPED_REG_OFS(XSI_B0NATS_OFS, vbnat); - DEFINE_MAPPED_REG_OFS(XSI_B1NATS_OFS, vnat); - DEFINE_MAPPED_REG_OFS(XSI_ITC_OFFSET_OFS, itc_offset); - DEFINE_MAPPED_REG_OFS(XSI_ITC_LAST_OFS, itc_last); -#endif /* CONFIG_XEN */ } diff --git a/arch/ia64/kernel/cpufreq/Kconfig b/arch/ia64/kernel/cpufreq/Kconfig deleted file mode 100644 index 2d9d5279b98..00000000000 --- a/arch/ia64/kernel/cpufreq/Kconfig +++ /dev/null @@ -1,29 +0,0 @@ - -# -# CPU Frequency scaling -# - -menu "CPU Frequency scaling" - -source "drivers/cpufreq/Kconfig" - -if CPU_FREQ - -comment "CPUFreq processor drivers" - -config IA64_ACPI_CPUFREQ - tristate "ACPI Processor P-States driver" - select CPU_FREQ_TABLE - depends on ACPI_PROCESSOR - help - This driver adds a CPUFreq driver which utilizes the ACPI - Processor Performance States. - - For details, take a look at <file:Documentation/cpu-freq/>. - - If in doubt, say N. - -endif # CPU_FREQ - -endmenu - diff --git a/arch/ia64/kernel/cpufreq/Makefile b/arch/ia64/kernel/cpufreq/Makefile deleted file mode 100644 index 4838f2a57c7..00000000000 --- a/arch/ia64/kernel/cpufreq/Makefile +++ /dev/null @@ -1,2 +0,0 @@ -obj-$(CONFIG_IA64_ACPI_CPUFREQ) += acpi-cpufreq.o - diff --git a/arch/ia64/kernel/cpufreq/acpi-cpufreq.c b/arch/ia64/kernel/cpufreq/acpi-cpufreq.c deleted file mode 100644 index 22f61526a8e..00000000000 --- a/arch/ia64/kernel/cpufreq/acpi-cpufreq.c +++ /dev/null @@ -1,439 +0,0 @@ -/* - * arch/ia64/kernel/cpufreq/acpi-cpufreq.c - * This file provides the ACPI based P-state support. This - * module works with generic cpufreq infrastructure. Most of - * the code is based on i386 version - * (arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c) - * - * Copyright (C) 2005 Intel Corp - * Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> - */ - -#include <linux/kernel.h> -#include <linux/slab.h> -#include <linux/module.h> -#include <linux/init.h> -#include <linux/cpufreq.h> -#include <linux/proc_fs.h> -#include <linux/seq_file.h> -#include <asm/io.h> -#include <asm/uaccess.h> -#include <asm/pal.h> - -#include <linux/acpi.h> -#include <acpi/processor.h> - -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "acpi-cpufreq", msg) - -MODULE_AUTHOR("Venkatesh Pallipadi"); -MODULE_DESCRIPTION("ACPI Processor P-States Driver"); -MODULE_LICENSE("GPL"); - - -struct cpufreq_acpi_io { - struct acpi_processor_performance acpi_data; - struct cpufreq_frequency_table *freq_table; - unsigned int resume; -}; - -static struct cpufreq_acpi_io *acpi_io_data[NR_CPUS]; - -static struct cpufreq_driver acpi_cpufreq_driver; - - -static int -processor_set_pstate ( - u32 value) -{ - s64 retval; - - dprintk("processor_set_pstate\n"); - - retval = ia64_pal_set_pstate((u64)value); - - if (retval) { - dprintk("Failed to set freq to 0x%x, with error 0x%lx\n", - value, retval); - return -ENODEV; - } - return (int)retval; -} - - -static int -processor_get_pstate ( - u32 *value) -{ - u64 pstate_index = 0; - s64 retval; - - dprintk("processor_get_pstate\n"); - - retval = ia64_pal_get_pstate(&pstate_index, - PAL_GET_PSTATE_TYPE_INSTANT); - *value = (u32) pstate_index; - - if (retval) - dprintk("Failed to get current freq with " - "error 0x%lx, idx 0x%x\n", retval, *value); - - return (int)retval; -} - - -/* To be used only after data->acpi_data is initialized */ -static unsigned -extract_clock ( - struct cpufreq_acpi_io *data, - unsigned value, - unsigned int cpu) -{ - unsigned long i; - - dprintk("extract_clock\n"); - - for (i = 0; i < data->acpi_data.state_count; i++) { - if (value == data->acpi_data.states[i].status) - return data->acpi_data.states[i].core_frequency; - } - return data->acpi_data.states[i-1].core_frequency; -} - - -static unsigned int -processor_get_freq ( - struct cpufreq_acpi_io *data, - unsigned int cpu) -{ - int ret = 0; - u32 value = 0; - cpumask_t saved_mask; - unsigned long clock_freq; - - dprintk("processor_get_freq\n"); - - saved_mask = current->cpus_allowed; - set_cpus_allowed_ptr(current, cpumask_of(cpu)); - if (smp_processor_id() != cpu) - goto migrate_end; - - /* processor_get_pstate gets the instantaneous frequency */ - ret = processor_get_pstate(&value); - - if (ret) { - set_cpus_allowed_ptr(current, &saved_mask); - printk(KERN_WARNING "get performance failed with error %d\n", - ret); - ret = 0; - goto migrate_end; - } - clock_freq = extract_clock(data, value, cpu); - ret = (clock_freq*1000); - -migrate_end: - set_cpus_allowed_ptr(current, &saved_mask); - return ret; -} - - -static int -processor_set_freq ( - struct cpufreq_acpi_io *data, - unsigned int cpu, - int state) -{ - int ret = 0; - u32 value = 0; - struct cpufreq_freqs cpufreq_freqs; - cpumask_t saved_mask; - int retval; - - dprintk("processor_set_freq\n"); - - saved_mask = current->cpus_allowed; - set_cpus_allowed_ptr(current, cpumask_of(cpu)); - if (smp_processor_id() != cpu) { - retval = -EAGAIN; - goto migrate_end; - } - - if (state == data->acpi_data.state) { - if (unlikely(data->resume)) { - dprintk("Called after resume, resetting to P%d\n", state); - data->resume = 0; - } else { - dprintk("Already at target state (P%d)\n", state); - retval = 0; - goto migrate_end; - } - } - - dprintk("Transitioning from P%d to P%d\n", - data->acpi_data.state, state); - - /* cpufreq frequency struct */ - cpufreq_freqs.cpu = cpu; - cpufreq_freqs.old = data->freq_table[data->acpi_data.state].frequency; - cpufreq_freqs.new = data->freq_table[state].frequency; - - /* notify cpufreq */ - cpufreq_notify_transition(&cpufreq_freqs, CPUFREQ_PRECHANGE); - - /* - * First we write the target state's 'control' value to the - * control_register. - */ - - value = (u32) data->acpi_data.states[state].control; - - dprintk("Transitioning to state: 0x%08x\n", value); - - ret = processor_set_pstate(value); - if (ret) { - unsigned int tmp = cpufreq_freqs.new; - cpufreq_notify_transition(&cpufreq_freqs, CPUFREQ_POSTCHANGE); - cpufreq_freqs.new = cpufreq_freqs.old; - cpufreq_freqs.old = tmp; - cpufreq_notify_transition(&cpufreq_freqs, CPUFREQ_PRECHANGE); - cpufreq_notify_transition(&cpufreq_freqs, CPUFREQ_POSTCHANGE); - printk(KERN_WARNING "Transition failed with error %d\n", ret); - retval = -ENODEV; - goto migrate_end; - } - - cpufreq_notify_transition(&cpufreq_freqs, CPUFREQ_POSTCHANGE); - - data->acpi_data.state = state; - - retval = 0; - -migrate_end: - set_cpus_allowed_ptr(current, &saved_mask); - return (retval); -} - - -static unsigned int -acpi_cpufreq_get ( - unsigned int cpu) -{ - struct cpufreq_acpi_io *data = acpi_io_data[cpu]; - - dprintk("acpi_cpufreq_get\n"); - - return processor_get_freq(data, cpu); -} - - -static int -acpi_cpufreq_target ( - struct cpufreq_policy *policy, - unsigned int target_freq, - unsigned int relation) -{ - struct cpufreq_acpi_io *data = acpi_io_data[policy->cpu]; - unsigned int next_state = 0; - unsigned int result = 0; - - dprintk("acpi_cpufreq_setpolicy\n"); - - result = cpufreq_frequency_table_target(policy, - data->freq_table, target_freq, relation, &next_state); - if (result) - return (result); - - result = processor_set_freq(data, policy->cpu, next_state); - - return (result); -} - - -static int -acpi_cpufreq_verify ( - struct cpufreq_policy *policy) -{ - unsigned int result = 0; - struct cpufreq_acpi_io *data = acpi_io_data[policy->cpu]; - - dprintk("acpi_cpufreq_verify\n"); - - result = cpufreq_frequency_table_verify(policy, - data->freq_table); - - return (result); -} - - -static int -acpi_cpufreq_cpu_init ( - struct cpufreq_policy *policy) -{ - unsigned int i; - unsigned int cpu = policy->cpu; - struct cpufreq_acpi_io *data; - unsigned int result = 0; - - dprintk("acpi_cpufreq_cpu_init\n"); - - data = kzalloc(sizeof(struct cpufreq_acpi_io), GFP_KERNEL); - if (!data) - return (-ENOMEM); - - acpi_io_data[cpu] = data; - - result = acpi_processor_register_performance(&data->acpi_data, cpu); - - if (result) - goto err_free; - - /* capability check */ - if (data->acpi_data.state_count <= 1) { - dprintk("No P-States\n"); - result = -ENODEV; - goto err_unreg; - } - - if ((data->acpi_data.control_register.space_id != - ACPI_ADR_SPACE_FIXED_HARDWARE) || - (data->acpi_data.status_register.space_id != - ACPI_ADR_SPACE_FIXED_HARDWARE)) { - dprintk("Unsupported address space [%d, %d]\n", - (u32) (data->acpi_data.control_register.space_id), - (u32) (data->acpi_data.status_register.space_id)); - result = -ENODEV; - goto err_unreg; - } - - /* alloc freq_table */ - data->freq_table = kmalloc(sizeof(struct cpufreq_frequency_table) * - (data->acpi_data.state_count + 1), - GFP_KERNEL); - if (!data->freq_table) { - result = -ENOMEM; - goto err_unreg; - } - - /* detect transition latency */ - policy->cpuinfo.transition_latency = 0; - for (i=0; i<data->acpi_data.state_count; i++) { - if ((data->acpi_data.states[i].transition_latency * 1000) > - policy->cpuinfo.transition_latency) { - policy->cpuinfo.transition_latency = - data->acpi_data.states[i].transition_latency * 1000; - } - } - policy->cur = processor_get_freq(data, policy->cpu); - - /* table init */ - for (i = 0; i <= data->acpi_data.state_count; i++) - { - data->freq_table[i].index = i; - if (i < data->acpi_data.state_count) { - data->freq_table[i].frequency = - data->acpi_data.states[i].core_frequency * 1000; - } else { - data->freq_table[i].frequency = CPUFREQ_TABLE_END; - } - } - - result = cpufreq_frequency_table_cpuinfo(policy, data->freq_table); - if (result) { - goto err_freqfree; - } - - /* notify BIOS that we exist */ - acpi_processor_notify_smm(THIS_MODULE); - - printk(KERN_INFO "acpi-cpufreq: CPU%u - ACPI performance management " - "activated.\n", cpu); - - for (i = 0; i < data->acpi_data.state_count; i++) - dprintk(" %cP%d: %d MHz, %d mW, %d uS, %d uS, 0x%x 0x%x\n", - (i == data->acpi_data.state?'*':' '), i, - (u32) data->acpi_data.states[i].core_frequency, - (u32) data->acpi_data.states[i].power, - (u32) data->acpi_data.states[i].transition_latency, - (u32) data->acpi_data.states[i].bus_master_latency, - (u32) data->acpi_data.states[i].status, - (u32) data->acpi_data.states[i].control); - - cpufreq_frequency_table_get_attr(data->freq_table, policy->cpu); - - /* the first call to ->target() should result in us actually - * writing something to the appropriate registers. */ - data->resume = 1; - - return (result); - - err_freqfree: - kfree(data->freq_table); - err_unreg: - acpi_processor_unregister_performance(&data->acpi_data, cpu); - err_free: - kfree(data); - acpi_io_data[cpu] = NULL; - - return (result); -} - - -static int -acpi_cpufreq_cpu_exit ( - struct cpufreq_policy *policy) -{ - struct cpufreq_acpi_io *data = acpi_io_data[policy->cpu]; - - dprintk("acpi_cpufreq_cpu_exit\n"); - - if (data) { - cpufreq_frequency_table_put_attr(policy->cpu); - acpi_io_data[policy->cpu] = NULL; - acpi_processor_unregister_performance(&data->acpi_data, - policy->cpu); - kfree(data); - } - - return (0); -} - - -static struct freq_attr* acpi_cpufreq_attr[] = { - &cpufreq_freq_attr_scaling_available_freqs, - NULL, -}; - - -static struct cpufreq_driver acpi_cpufreq_driver = { - .verify = acpi_cpufreq_verify, - .target = acpi_cpufreq_target, - .get = acpi_cpufreq_get, - .init = acpi_cpufreq_cpu_init, - .exit = acpi_cpufreq_cpu_exit, - .name = "acpi-cpufreq", - .owner = THIS_MODULE, - .attr = acpi_cpufreq_attr, -}; - - -static int __init -acpi_cpufreq_init (void) -{ - dprintk("acpi_cpufreq_init\n"); - - return cpufreq_register_driver(&acpi_cpufreq_driver); -} - - -static void __exit -acpi_cpufreq_exit (void) -{ - dprintk("acpi_cpufreq_exit\n"); - - cpufreq_unregister_driver(&acpi_cpufreq_driver); - return; -} - - -late_initcall(acpi_cpufreq_init); -module_exit(acpi_cpufreq_exit); - diff --git a/arch/ia64/kernel/crash.c b/arch/ia64/kernel/crash.c index b942f4032d7..2955f359e2a 100644 --- a/arch/ia64/kernel/crash.c +++ b/arch/ia64/kernel/crash.c @@ -237,7 +237,7 @@ kdump_init_notifier(struct notifier_block *self, unsigned long val, void *data) } #ifdef CONFIG_SYSCTL -static ctl_table kdump_ctl_table[] = { +static struct ctl_table kdump_ctl_table[] = { { .procname = "kdump_on_init", .data = &kdump_on_init, @@ -255,7 +255,7 @@ static ctl_table kdump_ctl_table[] = { { } }; -static ctl_table sys_table[] = { +static struct ctl_table sys_table[] = { { .procname = "kernel", .mode = 0555, diff --git a/arch/ia64/kernel/crash_dump.c b/arch/ia64/kernel/crash_dump.c index 23e91290e41..c8c9298666f 100644 --- a/arch/ia64/kernel/crash_dump.c +++ b/arch/ia64/kernel/crash_dump.c @@ -13,9 +13,6 @@ #include <asm/page.h> #include <asm/uaccess.h> -/* Stores the physical address of elf header of crash image. */ -unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX; - /** * copy_oldmem_page - copy one page from "oldmem" * @pfn: page frame number to be copied diff --git a/arch/ia64/kernel/cyclone.c b/arch/ia64/kernel/cyclone.c index d52f1f78eff..4826ff957a3 100644 --- a/arch/ia64/kernel/cyclone.c +++ b/arch/ia64/kernel/cyclone.c @@ -31,8 +31,6 @@ static struct clocksource clocksource_cyclone = { .rating = 300, .read = read_cyclone, .mask = (1LL << 40) - 1, - .mult = 0, /*to be caluclated*/ - .shift = 16, .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; @@ -117,10 +115,8 @@ int __init init_cyclone_clock(void) } /* initialize last tick */ cyclone_mc = cyclone_timer; - clocksource_cyclone.fsys_mmio = cyclone_timer; - clocksource_cyclone.mult = clocksource_hz2mult(CYCLONE_TIMER_FREQ, - clocksource_cyclone.shift); - clocksource_register(&clocksource_cyclone); + clocksource_cyclone.archdata.fsys_mmio = cyclone_timer; + clocksource_register_hz(&clocksource_cyclone, CYCLONE_TIMER_FREQ); return 0; } diff --git a/arch/ia64/kernel/dma-mapping.c b/arch/ia64/kernel/dma-mapping.c index f2c1600da09..7f791623820 100644 --- a/arch/ia64/kernel/dma-mapping.c +++ b/arch/ia64/kernel/dma-mapping.c @@ -1,4 +1,5 @@ #include <linux/dma-mapping.h> +#include <linux/export.h> /* Set this to 1 if there is a HW IOMMU in the system */ int iommu_detected __read_mostly; diff --git a/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c index a0f00192850..741b99c1a0b 100644 --- a/arch/ia64/kernel/efi.c +++ b/arch/ia64/kernel/efi.c @@ -23,6 +23,7 @@ */ #include <linux/module.h> #include <linux/bootmem.h> +#include <linux/crash_dump.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/types.h> @@ -38,14 +39,20 @@ #include <asm/pgtable.h> #include <asm/processor.h> #include <asm/mca.h> +#include <asm/setup.h> #include <asm/tlbflush.h> #define EFI_DEBUG 0 +static __initdata unsigned long palo_phys; + +static __initdata efi_config_table_type_t arch_tables[] = { + {PROCESSOR_ABSTRACTION_LAYER_OVERWRITE_GUID, "PALO", &palo_phys}, + {NULL_GUID, NULL, 0}, +}; + extern efi_status_t efi_call_phys (void *, ...); -struct efi efi; -EXPORT_SYMBOL(efi); static efi_runtime_services_t *runtime; static u64 mem_limit = ~0UL, max_addr = ~0UL, min_addr = 0UL; @@ -155,7 +162,7 @@ prefix##_get_next_variable (unsigned long *name_size, efi_char16_t *name, \ #define STUB_SET_VARIABLE(prefix, adjust_arg) \ static efi_status_t \ prefix##_set_variable (efi_char16_t *name, efi_guid_t *vendor, \ - unsigned long attr, unsigned long data_size, \ + u32 attr, unsigned long data_size, \ void *data) \ { \ struct ia64_fpreg fr[6]; \ @@ -421,9 +428,9 @@ static u8 __init palo_checksum(u8 *buffer, u32 length) * Parse and handle PALO table which is published at: * http://www.dig64.org/home/DIG64_PALO_R1_0.pdf */ -static void __init handle_palo(unsigned long palo_phys) +static void __init handle_palo(unsigned long phys_addr) { - struct palo_table *palo = __va(palo_phys); + struct palo_table *palo = __va(phys_addr); u8 checksum; if (strncmp(palo->signature, PALO_SIG, sizeof(PALO_SIG) - 1)) { @@ -465,12 +472,13 @@ void __init efi_init (void) { void *efi_map_start, *efi_map_end; - efi_config_table_t *config_tables; efi_char16_t *c16; u64 efi_desc_size; char *cp, vendor[100] = "unknown"; int i; - unsigned long palo_phys; + + set_bit(EFI_BOOT, &efi.flags); + set_bit(EFI_64BIT, &efi.flags); /* * It's too early to be able to use the standard kernel command line @@ -512,8 +520,6 @@ efi_init (void) efi.systab->hdr.revision >> 16, efi.systab->hdr.revision & 0xffff); - config_tables = __va(efi.systab->tables); - /* Show what we know for posterity */ c16 = __va(efi.systab->fw_vendor); if (c16) { @@ -526,43 +532,12 @@ efi_init (void) efi.systab->hdr.revision >> 16, efi.systab->hdr.revision & 0xffff, vendor); - efi.mps = EFI_INVALID_TABLE_ADDR; - efi.acpi = EFI_INVALID_TABLE_ADDR; - efi.acpi20 = EFI_INVALID_TABLE_ADDR; - efi.smbios = EFI_INVALID_TABLE_ADDR; - efi.sal_systab = EFI_INVALID_TABLE_ADDR; - efi.boot_info = EFI_INVALID_TABLE_ADDR; - efi.hcdp = EFI_INVALID_TABLE_ADDR; - efi.uga = EFI_INVALID_TABLE_ADDR; + set_bit(EFI_SYSTEM_TABLES, &efi.flags); palo_phys = EFI_INVALID_TABLE_ADDR; - for (i = 0; i < (int) efi.systab->nr_tables; i++) { - if (efi_guidcmp(config_tables[i].guid, MPS_TABLE_GUID) == 0) { - efi.mps = config_tables[i].table; - printk(" MPS=0x%lx", config_tables[i].table); - } else if (efi_guidcmp(config_tables[i].guid, ACPI_20_TABLE_GUID) == 0) { - efi.acpi20 = config_tables[i].table; - printk(" ACPI 2.0=0x%lx", config_tables[i].table); - } else if (efi_guidcmp(config_tables[i].guid, ACPI_TABLE_GUID) == 0) { - efi.acpi = config_tables[i].table; - printk(" ACPI=0x%lx", config_tables[i].table); - } else if (efi_guidcmp(config_tables[i].guid, SMBIOS_TABLE_GUID) == 0) { - efi.smbios = config_tables[i].table; - printk(" SMBIOS=0x%lx", config_tables[i].table); - } else if (efi_guidcmp(config_tables[i].guid, SAL_SYSTEM_TABLE_GUID) == 0) { - efi.sal_systab = config_tables[i].table; - printk(" SALsystab=0x%lx", config_tables[i].table); - } else if (efi_guidcmp(config_tables[i].guid, HCDP_TABLE_GUID) == 0) { - efi.hcdp = config_tables[i].table; - printk(" HCDP=0x%lx", config_tables[i].table); - } else if (efi_guidcmp(config_tables[i].guid, - PROCESSOR_ABSTRACTION_LAYER_OVERWRITE_GUID) == 0) { - palo_phys = config_tables[i].table; - printk(" PALO=0x%lx", config_tables[i].table); - } - } - printk("\n"); + if (efi_config_init(arch_tables) != 0) + return; if (palo_phys != EFI_INVALID_TABLE_ADDR) handle_palo(palo_phys); @@ -687,6 +662,8 @@ efi_enter_virtual_mode (void) return; } + set_bit(EFI_RUNTIME_SERVICES, &efi.flags); + /* * Now that EFI is in virtual mode, we call the EFI functions more * efficiently: @@ -868,7 +845,7 @@ kern_mem_attribute (unsigned long phys_addr, unsigned long size) EXPORT_SYMBOL(kern_mem_attribute); int -valid_phys_addr_range (unsigned long phys_addr, unsigned long size) +valid_phys_addr_range (phys_addr_t phys_addr, unsigned long size) { u64 attr; @@ -1114,11 +1091,6 @@ efi_memmap_init(u64 *s, u64 *e) if (!is_memory_available(md)) continue; -#ifdef CONFIG_CRASH_DUMP - /* saved_max_pfn should ignore max_addr= command line arg */ - if (saved_max_pfn < (efi_md_end(md) >> PAGE_SHIFT)) - saved_max_pfn = (efi_md_end(md) >> PAGE_SHIFT); -#endif /* * Round ends inward to granule boundaries * Give trimmings to uncached allocator diff --git a/arch/ia64/kernel/elfcore.c b/arch/ia64/kernel/elfcore.c index bac1639bc32..04bc8fd5f89 100644 --- a/arch/ia64/kernel/elfcore.c +++ b/arch/ia64/kernel/elfcore.c @@ -11,8 +11,7 @@ Elf64_Half elf_core_extra_phdrs(void) return GATE_EHDR->e_phnum; } -int elf_core_write_extra_phdrs(struct file *file, loff_t offset, size_t *size, - unsigned long limit) +int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset) { const struct elf_phdr *const gate_phdrs = (const struct elf_phdr *) (GATE_ADDR + GATE_EHDR->e_phoff); @@ -35,15 +34,13 @@ int elf_core_write_extra_phdrs(struct file *file, loff_t offset, size_t *size, phdr.p_offset += ofs; } phdr.p_paddr = 0; /* match other core phdrs */ - *size += sizeof(phdr); - if (*size > limit || !dump_write(file, &phdr, sizeof(phdr))) + if (!dump_emit(cprm, &phdr, sizeof(phdr))) return 0; } return 1; } -int elf_core_write_extra_data(struct file *file, size_t *size, - unsigned long limit) +int elf_core_write_extra_data(struct coredump_params *cprm) { const struct elf_phdr *const gate_phdrs = (const struct elf_phdr *) (GATE_ADDR + GATE_EHDR->e_phoff); @@ -54,8 +51,7 @@ int elf_core_write_extra_data(struct file *file, size_t *size, void *addr = (void *)gate_phdrs[i].p_vaddr; size_t memsz = PAGE_ALIGN(gate_phdrs[i].p_memsz); - *size += memsz; - if (*size > limit || !dump_write(file, addr, memsz)) + if (!dump_emit(cprm, addr, memsz)) return 0; break; } diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S index 244704a174d..ba3d03503e8 100644 --- a/arch/ia64/kernel/entry.S +++ b/arch/ia64/kernel/entry.S @@ -61,14 +61,13 @@ ENTRY(ia64_execve) * Allocate 8 input registers since ptrace() may clobber them */ .prologue ASM_UNW_PRLG_RP|ASM_UNW_PRLG_PFS, ASM_UNW_PRLG_GRSAVE(8) - alloc loc1=ar.pfs,8,2,4,0 + alloc loc1=ar.pfs,8,2,3,0 mov loc0=rp .body mov out0=in0 // filename ;; // stop bit between alloc and call mov out1=in1 // argv mov out2=in2 // envp - add out3=16,sp // regs br.call.sptk.many rp=sys_execve .ret0: cmp4.ge p6,p7=r8,r0 @@ -76,7 +75,6 @@ ENTRY(ia64_execve) sxt4 r8=r8 // return 64-bit result ;; stf.spill [sp]=f0 -(p6) cmp.ne pKStk,pUStk=r0,r0 // a successful execve() lands us in user-mode... mov rp=loc0 (p6) mov ar.pfs=r0 // clear ar.pfs on success (p7) br.ret.sptk.many rp @@ -118,13 +116,12 @@ GLOBAL_ENTRY(sys_clone2) mov loc1=r16 // save ar.pfs across do_fork .body mov out1=in1 - mov out3=in2 + mov out2=in2 tbit.nz p6,p0=in0,CLONE_SETTLS_BIT - mov out4=in3 // parent_tidptr: valid only w/CLONE_PARENT_SETTID + mov out3=in3 // parent_tidptr: valid only w/CLONE_PARENT_SETTID ;; (p6) st8 [r2]=in5 // store TLS in r16 for copy_thread() - mov out5=in4 // child_tidptr: valid only w/CLONE_CHILD_SETTID or CLONE_CHILD_CLEARTID - adds out2=IA64_SWITCH_STACK_SIZE+16,sp // out2 = ®s + mov out4=in4 // child_tidptr: valid only w/CLONE_CHILD_SETTID or CLONE_CHILD_CLEARTID mov out0=in0 // out0 = clone_flags br.call.sptk.many rp=do_fork .ret1: .restore sp @@ -150,13 +147,12 @@ GLOBAL_ENTRY(sys_clone) mov loc1=r16 // save ar.pfs across do_fork .body mov out1=in1 - mov out3=16 // stacksize (compensates for 16-byte scratch area) + mov out2=16 // stacksize (compensates for 16-byte scratch area) tbit.nz p6,p0=in0,CLONE_SETTLS_BIT - mov out4=in2 // parent_tidptr: valid only w/CLONE_PARENT_SETTID + mov out3=in2 // parent_tidptr: valid only w/CLONE_PARENT_SETTID ;; (p6) st8 [r2]=in4 // store TLS in r13 (tp) - mov out5=in3 // child_tidptr: valid only w/CLONE_CHILD_SETTID or CLONE_CHILD_CLEARTID - adds out2=IA64_SWITCH_STACK_SIZE+16,sp // out2 = ®s + mov out4=in3 // child_tidptr: valid only w/CLONE_CHILD_SETTID or CLONE_CHILD_CLEARTID mov out0=in0 // out0 = clone_flags br.call.sptk.many rp=do_fork .ret2: .restore sp @@ -484,19 +480,6 @@ GLOBAL_ENTRY(prefetch_stack) br.ret.sptk.many rp END(prefetch_stack) -GLOBAL_ENTRY(kernel_execve) - rum psr.ac - mov r15=__NR_execve // put syscall number in place - break __BREAK_SYSCALL - br.ret.sptk.many rp -END(kernel_execve) - -GLOBAL_ENTRY(clone) - mov r15=__NR_clone // put syscall number in place - break __BREAK_SYSCALL - br.ret.sptk.many rp -END(clone) - /* * Invoke a system call, but do some tracing before and after the call. * We MUST preserve the current register frame throughout this routine @@ -600,6 +583,27 @@ GLOBAL_ENTRY(ia64_strace_leave_kernel) .ret4: br.cond.sptk ia64_leave_kernel END(ia64_strace_leave_kernel) +ENTRY(call_payload) + .prologue ASM_UNW_PRLG_RP|ASM_UNW_PRLG_PFS, ASM_UNW_PRLG_GRSAVE(0) + /* call the kernel_thread payload; fn is in r4, arg - in r5 */ + alloc loc1=ar.pfs,0,3,1,0 + mov loc0=rp + mov loc2=gp + mov out0=r5 // arg + ld8 r14 = [r4], 8 // fn.address + ;; + mov b6 = r14 + ld8 gp = [r4] // fn.gp + ;; + br.call.sptk.many rp=b6 // fn(arg) +.ret12: mov gp=loc2 + mov rp=loc0 + mov ar.pfs=loc1 + /* ... and if it has returned, we are going to userland */ + cmp.ne pKStk,pUStk=r0,r0 + br.ret.sptk.many rp +END(call_payload) + GLOBAL_ENTRY(ia64_ret_from_clone) PT_REGS_UNWIND_INFO(0) { /* @@ -616,6 +620,7 @@ GLOBAL_ENTRY(ia64_ret_from_clone) br.call.sptk.many rp=ia64_invoke_schedule_tail } .ret8: +(pKStk) br.call.sptk.many rp=call_payload adds r2=TI_FLAGS+IA64_TASK_SIZE,r13 ;; ld4 r2=[r2] @@ -719,7 +724,7 @@ GLOBAL_ENTRY(__paravirt_leave_syscall) #endif .global __paravirt_work_processed_syscall; __paravirt_work_processed_syscall: -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE adds r2=PT(LOADRS)+16,r12 MOV_FROM_ITC(pUStk, p9, r22, r19) // fetch time at leave adds r18=TI_FLAGS+IA64_TASK_SIZE,r13 @@ -757,7 +762,7 @@ __paravirt_work_processed_syscall: ld8 r29=[r2],16 // M0|1 load cr.ipsr ld8 r28=[r3],16 // M0|1 load cr.iip -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE (pUStk) add r14=TI_AC_LEAVE+IA64_TASK_SIZE,r13 ;; ld8 r30=[r2],16 // M0|1 load cr.ifs @@ -788,7 +793,7 @@ __paravirt_work_processed_syscall: ld8.fill r1=[r3],16 // M0|1 load r1 (pUStk) mov r17=1 // A ;; -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE (pUStk) st1 [r15]=r17 // M2|3 #else (pUStk) st1 [r14]=r17 // M2|3 @@ -808,7 +813,7 @@ __paravirt_work_processed_syscall: shr.u r18=r19,16 // I0|1 get byte size of existing "dirty" partition COVER // B add current frame into dirty partition & set cr.ifs ;; -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE mov r19=ar.bsp // M2 get new backing store pointer st8 [r14]=r22 // M save time at leave mov f10=f0 // F clear f10 @@ -943,7 +948,7 @@ GLOBAL_ENTRY(__paravirt_leave_kernel) adds r16=PT(CR_IPSR)+16,r12 adds r17=PT(CR_IIP)+16,r12 -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE .pred.rel.mutex pUStk,pKStk MOV_FROM_PSR(pKStk, r22, r29) // M2 read PSR now that interrupts are disabled MOV_FROM_ITC(pUStk, p9, r22, r29) // M fetch time at leave @@ -976,7 +981,7 @@ GLOBAL_ENTRY(__paravirt_leave_kernel) ;; ld8.fill r12=[r16],16 ld8.fill r13=[r17],16 -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE (pUStk) adds r3=TI_AC_LEAVE+IA64_TASK_SIZE,r18 #else (pUStk) adds r18=IA64_TASK_THREAD_ON_USTACK_OFFSET,r18 @@ -984,7 +989,7 @@ GLOBAL_ENTRY(__paravirt_leave_kernel) ;; ld8 r20=[r16],16 // ar.fpsr ld8.fill r15=[r17],16 -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE (pUStk) adds r18=IA64_TASK_THREAD_ON_USTACK_OFFSET,r18 // deferred #endif ;; @@ -992,7 +997,7 @@ GLOBAL_ENTRY(__paravirt_leave_kernel) ld8.fill r2=[r17] (pUStk) mov r17=1 ;; -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE // mmi_ : ld8 st1 shr;; mmi_ : st8 st1 shr;; // mib : mov add br -> mib : ld8 add br // bbb_ : br nop cover;; mbb_ : mov br cover;; @@ -1164,21 +1169,8 @@ skip_rbs_switch: .work_pending: tbit.z p6,p0=r31,TIF_NEED_RESCHED // is resched not needed? (p6) br.cond.sptk.few .notify -#ifdef CONFIG_PREEMPT -(pKStk) dep r21=-1,r0,PREEMPT_ACTIVE_BIT,1 - ;; -(pKStk) st4 [r20]=r21 -#endif - SSM_PSR_I(p0, p6, r2) // enable interrupts - br.call.spnt.many rp=schedule + br.call.spnt.many rp=preempt_schedule_irq .ret9: cmp.eq p6,p0=r0,r0 // p6 <- 1 (re-check) - RSM_PSR_I(p0, r2, r20) // disable interrupts - ;; -#ifdef CONFIG_PREEMPT -(pKStk) adds r20=TI_PRE_COUNT+IA64_TASK_SIZE,r13 - ;; -(pKStk) st4 [r20]=r0 // preempt_count() <- 0 -#endif (pLvSys)br.cond.sptk.few __paravirt_pending_syscall_end br.cond.sptk.many .work_processed_kernel @@ -1614,7 +1606,7 @@ sys_call_table: data8 sys_sched_get_priority_min data8 sys_sched_rr_get_interval data8 sys_nanosleep - data8 sys_nfsservctl + data8 sys_ni_syscall // old nfsservctl data8 sys_prctl // 1170 data8 sys_getpagesize data8 sys_mmap2 @@ -1771,6 +1763,19 @@ sys_call_table: data8 sys_fanotify_init data8 sys_fanotify_mark data8 sys_prlimit64 // 1325 + data8 sys_name_to_handle_at + data8 sys_open_by_handle_at + data8 sys_clock_adjtime + data8 sys_syncfs + data8 sys_setns // 1330 + data8 sys_sendmmsg + data8 sys_process_vm_readv + data8 sys_process_vm_writev + data8 sys_accept4 + data8 sys_finit_module // 1335 + data8 sys_sched_setattr + data8 sys_sched_getattr + data8 sys_renameat2 .org sys_call_table + 8*NR_syscalls // guard against failures to increase NR_syscalls #endif /* __IA64_ASM_PARAVIRTUALIZED_NATIVE */ diff --git a/arch/ia64/kernel/err_inject.c b/arch/ia64/kernel/err_inject.c index c539c689493..0c161ed6d18 100644 --- a/arch/ia64/kernel/err_inject.c +++ b/arch/ia64/kernel/err_inject.c @@ -24,7 +24,7 @@ * Copyright (C) 2006, Intel Corp. All rights reserved. * */ -#include <linux/sysdev.h> +#include <linux/device.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/cpu.h> @@ -35,10 +35,10 @@ #define ERR_DATA_BUFFER_SIZE 3 // Three 8-byte; #define define_one_ro(name) \ -static SYSDEV_ATTR(name, 0444, show_##name, NULL) +static DEVICE_ATTR(name, 0444, show_##name, NULL) #define define_one_rw(name) \ -static SYSDEV_ATTR(name, 0644, show_##name, store_##name) +static DEVICE_ATTR(name, 0644, show_##name, store_##name) static u64 call_start[NR_CPUS]; static u64 phys_addr[NR_CPUS]; @@ -55,7 +55,7 @@ static u64 resources[NR_CPUS]; #define show(name) \ static ssize_t \ -show_##name(struct sys_device *dev, struct sysdev_attribute *attr, \ +show_##name(struct device *dev, struct device_attribute *attr, \ char *buf) \ { \ u32 cpu=dev->id; \ @@ -64,7 +64,7 @@ show_##name(struct sys_device *dev, struct sysdev_attribute *attr, \ #define store(name) \ static ssize_t \ -store_##name(struct sys_device *dev, struct sysdev_attribute *attr, \ +store_##name(struct device *dev, struct device_attribute *attr, \ const char *buf, size_t size) \ { \ unsigned int cpu=dev->id; \ @@ -78,7 +78,7 @@ show(call_start) * processor. The cpu number in driver is only used for storing data. */ static ssize_t -store_call_start(struct sys_device *dev, struct sysdev_attribute *attr, +store_call_start(struct device *dev, struct device_attribute *attr, const char *buf, size_t size) { unsigned int cpu=dev->id; @@ -127,7 +127,7 @@ show(err_type_info) store(err_type_info) static ssize_t -show_virtual_to_phys(struct sys_device *dev, struct sysdev_attribute *attr, +show_virtual_to_phys(struct device *dev, struct device_attribute *attr, char *buf) { unsigned int cpu=dev->id; @@ -135,7 +135,7 @@ show_virtual_to_phys(struct sys_device *dev, struct sysdev_attribute *attr, } static ssize_t -store_virtual_to_phys(struct sys_device *dev, struct sysdev_attribute *attr, +store_virtual_to_phys(struct device *dev, struct device_attribute *attr, const char *buf, size_t size) { unsigned int cpu=dev->id; @@ -159,8 +159,8 @@ show(err_struct_info) store(err_struct_info) static ssize_t -show_err_data_buffer(struct sys_device *dev, - struct sysdev_attribute *attr, char *buf) +show_err_data_buffer(struct device *dev, + struct device_attribute *attr, char *buf) { unsigned int cpu=dev->id; @@ -171,8 +171,8 @@ show_err_data_buffer(struct sys_device *dev, } static ssize_t -store_err_data_buffer(struct sys_device *dev, - struct sysdev_attribute *attr, +store_err_data_buffer(struct device *dev, + struct device_attribute *attr, const char *buf, size_t size) { unsigned int cpu=dev->id; @@ -209,14 +209,14 @@ define_one_ro(capabilities); define_one_ro(resources); static struct attribute *default_attrs[] = { - &attr_call_start.attr, - &attr_virtual_to_phys.attr, - &attr_err_type_info.attr, - &attr_err_struct_info.attr, - &attr_err_data_buffer.attr, - &attr_status.attr, - &attr_capabilities.attr, - &attr_resources.attr, + &dev_attr_call_start.attr, + &dev_attr_virtual_to_phys.attr, + &dev_attr_err_type_info.attr, + &dev_attr_err_struct_info.attr, + &dev_attr_err_data_buffer.attr, + &dev_attr_status.attr, + &dev_attr_capabilities.attr, + &dev_attr_resources.attr, NULL }; @@ -225,23 +225,23 @@ static struct attribute_group err_inject_attr_group = { .name = "err_inject" }; /* Add/Remove err_inject interface for CPU device */ -static int __cpuinit err_inject_add_dev(struct sys_device * sys_dev) +static int err_inject_add_dev(struct device *sys_dev) { return sysfs_create_group(&sys_dev->kobj, &err_inject_attr_group); } -static int __cpuinit err_inject_remove_dev(struct sys_device * sys_dev) +static int err_inject_remove_dev(struct device *sys_dev) { sysfs_remove_group(&sys_dev->kobj, &err_inject_attr_group); return 0; } -static int __cpuinit err_inject_cpu_callback(struct notifier_block *nfb, +static int err_inject_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { unsigned int cpu = (unsigned long)hcpu; - struct sys_device *sys_dev; + struct device *sys_dev; - sys_dev = get_cpu_sysdev(cpu); + sys_dev = get_cpu_device(cpu); switch (action) { case CPU_ONLINE: case CPU_ONLINE_FROZEN: @@ -256,7 +256,7 @@ static int __cpuinit err_inject_cpu_callback(struct notifier_block *nfb, return NOTIFY_OK; } -static struct notifier_block __cpuinitdata err_inject_cpu_notifier = +static struct notifier_block err_inject_cpu_notifier = { .notifier_call = err_inject_cpu_callback, }; @@ -269,12 +269,17 @@ err_inject_init(void) #ifdef ERR_INJ_DEBUG printk(KERN_INFO "Enter error injection driver.\n"); #endif + + cpu_notifier_register_begin(); + for_each_online_cpu(i) { err_inject_cpu_callback(&err_inject_cpu_notifier, CPU_ONLINE, (void *)(long)i); } - register_hotcpu_notifier(&err_inject_cpu_notifier); + __register_hotcpu_notifier(&err_inject_cpu_notifier); + + cpu_notifier_register_done(); return 0; } @@ -283,16 +288,22 @@ static void __exit err_inject_exit(void) { int i; - struct sys_device *sys_dev; + struct device *sys_dev; #ifdef ERR_INJ_DEBUG printk(KERN_INFO "Exit error injection driver.\n"); #endif + + cpu_notifier_register_begin(); + for_each_online_cpu(i) { - sys_dev = get_cpu_sysdev(i); + sys_dev = get_cpu_device(i); sysfs_remove_group(&sys_dev->kobj, &err_inject_attr_group); } - unregister_hotcpu_notifier(&err_inject_cpu_notifier); + + __unregister_hotcpu_notifier(&err_inject_cpu_notifier); + + cpu_notifier_register_done(); } module_init(err_inject_init); diff --git a/arch/ia64/kernel/fsys.S b/arch/ia64/kernel/fsys.S index 331d42bda77..abc6dee3799 100644 --- a/arch/ia64/kernel/fsys.S +++ b/arch/ia64/kernel/fsys.S @@ -21,7 +21,6 @@ #include <asm/thread_info.h> #include <asm/sal.h> #include <asm/signal.h> -#include <asm/system.h> #include <asm/unistd.h> #include "entry.h" @@ -91,53 +90,6 @@ ENTRY(fsys_getpid) FSYS_RETURN END(fsys_getpid) -ENTRY(fsys_getppid) - .prologue - .altrp b6 - .body - add r17=IA64_TASK_GROUP_LEADER_OFFSET,r16 - ;; - ld8 r17=[r17] // r17 = current->group_leader - add r9=TI_FLAGS+IA64_TASK_SIZE,r16 - ;; - - ld4 r9=[r9] - add r17=IA64_TASK_REAL_PARENT_OFFSET,r17 // r17 = ¤t->group_leader->real_parent - ;; - and r9=TIF_ALLWORK_MASK,r9 - -1: ld8 r18=[r17] // r18 = current->group_leader->real_parent - ;; - cmp.ne p8,p0=0,r9 - add r8=IA64_TASK_TGID_OFFSET,r18 // r8 = ¤t->group_leader->real_parent->tgid - ;; - - /* - * The .acq is needed to ensure that the read of tgid has returned its data before - * we re-check "real_parent". - */ - ld4.acq r8=[r8] // r8 = current->group_leader->real_parent->tgid -#ifdef CONFIG_SMP - /* - * Re-read current->group_leader->real_parent. - */ - ld8 r19=[r17] // r19 = current->group_leader->real_parent -(p8) br.spnt.many fsys_fallback_syscall - ;; - cmp.ne p6,p0=r18,r19 // did real_parent change? - mov r19=0 // i must not leak kernel bits... -(p6) br.cond.spnt.few 1b // yes -> redo the read of tgid and the check - ;; - mov r17=0 // i must not leak kernel bits... - mov r18=0 // i must not leak kernel bits... -#else - mov r17=0 // i must not leak kernel bits... - mov r18=0 // i must not leak kernel bits... - mov r19=0 // i must not leak kernel bits... -#endif - FSYS_RETURN -END(fsys_getppid) - ENTRY(fsys_set_tid_address) .prologue .altrp b6 @@ -174,7 +126,7 @@ ENTRY(fsys_set_tid_address) FSYS_RETURN END(fsys_set_tid_address) -#if IA64_GTOD_LOCK_OFFSET !=0 +#if IA64_GTOD_SEQ_OFFSET !=0 #error fsys_gettimeofday incompatible with changes to struct fsyscall_gtod_data_t #endif #if IA64_ITC_JITTER_OFFSET !=0 @@ -373,175 +325,6 @@ ENTRY(fsys_clock_gettime) END(fsys_clock_gettime) /* - * long fsys_rt_sigprocmask (int how, sigset_t *set, sigset_t *oset, size_t sigsetsize). - */ -#if _NSIG_WORDS != 1 -# error Sorry, fsys_rt_sigprocmask() needs to be updated for _NSIG_WORDS != 1. -#endif -ENTRY(fsys_rt_sigprocmask) - .prologue - .altrp b6 - .body - - add r2=IA64_TASK_BLOCKED_OFFSET,r16 - add r9=TI_FLAGS+IA64_TASK_SIZE,r16 - cmp4.ltu p6,p0=SIG_SETMASK,r32 - - cmp.ne p15,p0=r0,r34 // oset != NULL? - tnat.nz p8,p0=r34 - add r31=IA64_TASK_SIGHAND_OFFSET,r16 - ;; - ld8 r3=[r2] // read/prefetch current->blocked - ld4 r9=[r9] - tnat.nz.or p6,p0=r35 - - cmp.ne.or p6,p0=_NSIG_WORDS*8,r35 - tnat.nz.or p6,p0=r32 -(p6) br.spnt.few .fail_einval // fail with EINVAL - ;; -#ifdef CONFIG_SMP - ld8 r31=[r31] // r31 <- current->sighand -#endif - and r9=TIF_ALLWORK_MASK,r9 - tnat.nz.or p8,p0=r33 - ;; - cmp.ne p7,p0=0,r9 - cmp.eq p6,p0=r0,r33 // set == NULL? - add r31=IA64_SIGHAND_SIGLOCK_OFFSET,r31 // r31 <- current->sighand->siglock -(p8) br.spnt.few .fail_efault // fail with EFAULT -(p7) br.spnt.many fsys_fallback_syscall // got pending kernel work... -(p6) br.dpnt.many .store_mask // -> short-circuit to just reading the signal mask - - /* Argh, we actually have to do some work and _update_ the signal mask: */ - -EX(.fail_efault, probe.r.fault r33, 3) // verify user has read-access to *set -EX(.fail_efault, ld8 r14=[r33]) // r14 <- *set - mov r17=(1 << (SIGKILL - 1)) | (1 << (SIGSTOP - 1)) - ;; - - RSM_PSR_I(p0, r18, r19) // mask interrupt delivery - andcm r14=r14,r17 // filter out SIGKILL & SIGSTOP - mov r8=EINVAL // default to EINVAL - -#ifdef CONFIG_SMP - // __ticket_spin_trylock(r31) - ld4 r17=[r31] - ;; - mov.m ar.ccv=r17 - extr.u r9=r17,17,15 - adds r19=1,r17 - extr.u r18=r17,0,15 - ;; - cmp.eq p6,p7=r9,r18 - ;; -(p6) cmpxchg4.acq r9=[r31],r19,ar.ccv -(p6) dep.z r20=r19,1,15 // next serving ticket for unlock -(p7) br.cond.spnt.many .lock_contention - ;; - cmp4.eq p0,p7=r9,r17 - adds r31=2,r31 -(p7) br.cond.spnt.many .lock_contention - ld8 r3=[r2] // re-read current->blocked now that we hold the lock - ;; -#else - ld8 r3=[r2] // re-read current->blocked now that we hold the lock -#endif - add r18=IA64_TASK_PENDING_OFFSET+IA64_SIGPENDING_SIGNAL_OFFSET,r16 - add r19=IA64_TASK_SIGNAL_OFFSET,r16 - cmp4.eq p6,p0=SIG_BLOCK,r32 - ;; - ld8 r19=[r19] // r19 <- current->signal - cmp4.eq p7,p0=SIG_UNBLOCK,r32 - cmp4.eq p8,p0=SIG_SETMASK,r32 - ;; - ld8 r18=[r18] // r18 <- current->pending.signal - .pred.rel.mutex p6,p7,p8 -(p6) or r14=r3,r14 // SIG_BLOCK -(p7) andcm r14=r3,r14 // SIG_UNBLOCK - -(p8) mov r14=r14 // SIG_SETMASK -(p6) mov r8=0 // clear error code - // recalc_sigpending() - add r17=IA64_SIGNAL_GROUP_STOP_COUNT_OFFSET,r19 - - add r19=IA64_SIGNAL_SHARED_PENDING_OFFSET+IA64_SIGPENDING_SIGNAL_OFFSET,r19 - ;; - ld4 r17=[r17] // r17 <- current->signal->group_stop_count -(p7) mov r8=0 // clear error code - - ld8 r19=[r19] // r19 <- current->signal->shared_pending - ;; - cmp4.gt p6,p7=r17,r0 // p6/p7 <- (current->signal->group_stop_count > 0)? -(p8) mov r8=0 // clear error code - - or r18=r18,r19 // r18 <- current->pending | current->signal->shared_pending - ;; - // r18 <- (current->pending | current->signal->shared_pending) & ~current->blocked: - andcm r18=r18,r14 - add r9=TI_FLAGS+IA64_TASK_SIZE,r16 - ;; - -(p7) cmp.ne.or.andcm p6,p7=r18,r0 // p6/p7 <- signal pending - mov r19=0 // i must not leak kernel bits... -(p6) br.cond.dpnt.many .sig_pending - ;; - -1: ld4 r17=[r9] // r17 <- current->thread_info->flags - ;; - mov ar.ccv=r17 - and r18=~_TIF_SIGPENDING,r17 // r18 <- r17 & ~(1 << TIF_SIGPENDING) - ;; - - st8 [r2]=r14 // update current->blocked with new mask - cmpxchg4.acq r8=[r9],r18,ar.ccv // current->thread_info->flags <- r18 - ;; - cmp.ne p6,p0=r17,r8 // update failed? -(p6) br.cond.spnt.few 1b // yes -> retry - -#ifdef CONFIG_SMP - // __ticket_spin_unlock(r31) - st2.rel [r31]=r20 - mov r20=0 // i must not leak kernel bits... -#endif - SSM_PSR_I(p0, p9, r31) - ;; - - srlz.d // ensure psr.i is set again - mov r18=0 // i must not leak kernel bits... - -.store_mask: -EX(.fail_efault, (p15) probe.w.fault r34, 3) // verify user has write-access to *oset -EX(.fail_efault, (p15) st8 [r34]=r3) - mov r2=0 // i must not leak kernel bits... - mov r3=0 // i must not leak kernel bits... - mov r8=0 // return 0 - mov r9=0 // i must not leak kernel bits... - mov r14=0 // i must not leak kernel bits... - mov r17=0 // i must not leak kernel bits... - mov r31=0 // i must not leak kernel bits... - FSYS_RETURN - -.sig_pending: -#ifdef CONFIG_SMP - // __ticket_spin_unlock(r31) - st2.rel [r31]=r20 // release the lock -#endif - SSM_PSR_I(p0, p9, r17) - ;; - srlz.d - br.sptk.many fsys_fallback_syscall // with signal pending, do the heavy-weight syscall - -#ifdef CONFIG_SMP -.lock_contention: - /* Rather than spinning here, fall back on doing a heavy-weight syscall. */ - SSM_PSR_I(p0, p9, r17) - ;; - srlz.d - br.sptk.many fsys_fallback_syscall -#endif -END(fsys_rt_sigprocmask) - -/* * fsys_getcpu doesn't use the third parameter in this implementation. It reads * current_thread_info()->cpu and corresponding node in cpu_to_node_map. */ @@ -560,11 +343,15 @@ ENTRY(fsys_getcpu) ;; tnat.nz p7,p0 = r33 // I guard against NaT argument (p7) br.cond.spnt.few .fail_einval // B + ;; + cmp.ne p6,p0=r32,r0 + cmp.ne p7,p0=r33,r0 + ;; #ifdef CONFIG_NUMA movl r17=cpu_to_node_map ;; -EX(.fail_efault, probe.w.fault r32, 3) // M This takes 5 cycles -EX(.fail_efault, probe.w.fault r33, 3) // M This takes 5 cycles +EX(.fail_efault, (p6) probe.w.fault r32, 3) // M This takes 5 cycles +EX(.fail_efault, (p7) probe.w.fault r33, 3) // M This takes 5 cycles shladd r18=r3,1,r17 ;; ld2 r20=[r18] // r20 = cpu_to_node_map[cpu] @@ -574,20 +361,20 @@ EX(.fail_efault, probe.w.fault r33, 3) // M This takes 5 cycles (p8) br.spnt.many fsys_fallback_syscall ;; ;; -EX(.fail_efault, st4 [r32] = r3) -EX(.fail_efault, st2 [r33] = r20) +EX(.fail_efault, (p6) st4 [r32] = r3) +EX(.fail_efault, (p7) st2 [r33] = r20) mov r8=0 ;; #else -EX(.fail_efault, probe.w.fault r32, 3) // M This takes 5 cycles -EX(.fail_efault, probe.w.fault r33, 3) // M This takes 5 cycles +EX(.fail_efault, (p6) probe.w.fault r32, 3) // M This takes 5 cycles +EX(.fail_efault, (p7) probe.w.fault r33, 3) // M This takes 5 cycles and r2 = TIF_ALLWORK_MASK,r2 ;; cmp.ne p8,p0=0,r2 (p8) br.spnt.many fsys_fallback_syscall ;; -EX(.fail_efault, st4 [r32] = r3) -EX(.fail_efault, st2 [r33] = r0) +EX(.fail_efault, (p6) st4 [r32] = r3) +EX(.fail_efault, (p7) st2 [r33] = r0) mov r8=0 ;; #endif @@ -695,7 +482,7 @@ GLOBAL_ENTRY(paravirt_fsys_bubble_down) nop.i 0 ;; mov ar.rsc=0 // M2 set enforced lazy mode, pl 0, LE, loadrs=0 -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE MOV_FROM_ITC(p0, p6, r30, r23) // M get cycle for accounting #else nop.m 0 @@ -721,7 +508,7 @@ GLOBAL_ENTRY(paravirt_fsys_bubble_down) cmp.ne pKStk,pUStk=r0,r0 // A set pKStk <- 0, pUStk <- 1 br.call.sptk.many b7=ia64_syscall_setup // B ;; -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE // mov.m r30=ar.itc is called in advance add r16=TI_AC_STAMP+IA64_TASK_SIZE,r2 add r17=TI_AC_LEAVE+IA64_TASK_SIZE,r2 @@ -780,7 +567,7 @@ paravirt_fsyscall_table: data8 0 // chown data8 0 // lseek // 1040 data8 fsys_getpid // getpid - data8 fsys_getppid // getppid + data8 0 // getppid data8 0 // mount data8 0 // umount data8 0 // setuid // 1045 @@ -917,7 +704,7 @@ paravirt_fsyscall_table: data8 0 // sigaltstack data8 0 // rt_sigaction data8 0 // rt_sigpending - data8 fsys_rt_sigprocmask // rt_sigprocmask + data8 0 // rt_sigprocmask data8 0 // rt_sigqueueinfo // 1180 data8 0 // rt_sigreturn data8 0 // rt_sigsuspend diff --git a/arch/ia64/kernel/fsyscall_gtod_data.h b/arch/ia64/kernel/fsyscall_gtod_data.h index 57d2ee6c83e..146b15b5fec 100644 --- a/arch/ia64/kernel/fsyscall_gtod_data.h +++ b/arch/ia64/kernel/fsyscall_gtod_data.h @@ -6,7 +6,7 @@ */ struct fsyscall_gtod_data_t { - seqlock_t lock; + seqcount_t seq; struct timespec wall_time; struct timespec monotonic_time; cycle_t clk_mask; diff --git a/arch/ia64/kernel/ftrace.c b/arch/ia64/kernel/ftrace.c index 7fc8c961b1f..3b0c2aa0785 100644 --- a/arch/ia64/kernel/ftrace.c +++ b/arch/ia64/kernel/ftrace.c @@ -198,9 +198,7 @@ int ftrace_update_ftrace_func(ftrace_func_t func) } /* run from kstop_machine */ -int __init ftrace_dyn_arch_init(void *data) +int __init ftrace_dyn_arch_init(void) { - *(unsigned long *)data = 0; - return 0; } diff --git a/arch/ia64/kernel/gate.S b/arch/ia64/kernel/gate.S index 245d3e1ec7e..b5f8bdd8618 100644 --- a/arch/ia64/kernel/gate.S +++ b/arch/ia64/kernel/gate.S @@ -11,8 +11,9 @@ #include <asm/errno.h> #include <asm/asm-offsets.h> #include <asm/sigcontext.h> -#include <asm/system.h> #include <asm/unistd.h> +#include <asm/kregs.h> +#include <asm/page.h> #include "paravirt_inst.h" /* diff --git a/arch/ia64/kernel/gate.lds.S b/arch/ia64/kernel/gate.lds.S index d32b0855110..e518f7902af 100644 --- a/arch/ia64/kernel/gate.lds.S +++ b/arch/ia64/kernel/gate.lds.S @@ -5,8 +5,7 @@ * its layout. */ - -#include <asm/system.h> +#include <asm/page.h> #include "paravirt_patchlist.h" SECTIONS diff --git a/arch/ia64/kernel/head.S b/arch/ia64/kernel/head.S index 17a9fba3893..a4acddad0c7 100644 --- a/arch/ia64/kernel/head.S +++ b/arch/ia64/kernel/head.S @@ -30,7 +30,6 @@ #include <asm/pgtable.h> #include <asm/processor.h> #include <asm/ptrace.h> -#include <asm/system.h> #include <asm/mca_asm.h> #include <linux/init.h> #include <linux/linkage.h> @@ -260,7 +259,7 @@ start_ap: * Switch into virtual mode: */ movl r16=(IA64_PSR_IT|IA64_PSR_IC|IA64_PSR_DT|IA64_PSR_RT|IA64_PSR_DFH|IA64_PSR_BN \ - |IA64_PSR_DI|IA64_PSR_AC) + |IA64_PSR_DI) ;; mov cr.ipsr=r16 movl r17=1f @@ -417,8 +416,6 @@ start_ap: default_setup_hook = 0 // Currently nothing needs to be done. - .weak xen_setup_hook - .global hypervisor_type hypervisor_type: data8 PARAVIRT_HYPERVISOR_TYPE_DEFAULT @@ -427,7 +424,6 @@ hypervisor_type: hypervisor_setup_hooks: data8 default_setup_hook - data8 xen_setup_hook num_hypervisor_hooks = (. - hypervisor_setup_hooks) / 8 .previous @@ -1036,7 +1032,7 @@ END(ia64_delay_loop) * Return a CPU-local timestamp in nano-seconds. This timestamp is * NOT synchronized across CPUs its return value must never be * compared against the values returned on another CPU. The usage in - * kernel/sched.c ensures that. + * kernel/sched/core.c ensures that. * * The return-value of sched_clock() is NOT supposed to wrap-around. * If it did, it would cause some scheduling hiccups (at the worst). @@ -1074,7 +1070,7 @@ END(ia64_native_sched_clock) sched_clock = ia64_native_sched_clock #endif -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE GLOBAL_ENTRY(cycle_to_cputime) alloc r16=ar.pfs,1,0,0,0 addl r8=THIS_CPU(ia64_cpu_info) + IA64_CPUINFO_NSEC_PER_CYC_OFFSET,r0 @@ -1092,20 +1088,7 @@ GLOBAL_ENTRY(cycle_to_cputime) shrp r8=r9,r8,IA64_NSEC_PER_CYC_SHIFT br.ret.sptk.many rp END(cycle_to_cputime) -#endif /* CONFIG_VIRT_CPU_ACCOUNTING */ - -GLOBAL_ENTRY(start_kernel_thread) - .prologue - .save rp, r0 // this is the end of the call-chain - .body - alloc r2 = ar.pfs, 0, 0, 2, 0 - mov out0 = r9 - mov out1 = r11;; - br.call.sptk.many rp = kernel_thread_helper;; - mov out0 = r8 - br.call.sptk.many rp = sys_exit;; -1: br.sptk.few 1b // not reached -END(start_kernel_thread) +#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ #ifdef CONFIG_IA64_BRL_EMU diff --git a/arch/ia64/kernel/ia64_ksyms.c b/arch/ia64/kernel/ia64_ksyms.c index 7f4a0ed2415..5b7791dd396 100644 --- a/arch/ia64/kernel/ia64_ksyms.c +++ b/arch/ia64/kernel/ia64_ksyms.c @@ -12,7 +12,7 @@ EXPORT_SYMBOL(memset); EXPORT_SYMBOL(memcpy); EXPORT_SYMBOL(strlen); -#include<asm/pgtable.h> +#include <asm/pgtable.h> EXPORT_SYMBOL_GPL(empty_zero_page); #include <asm/checksum.h> diff --git a/arch/ia64/kernel/iosapic.c b/arch/ia64/kernel/iosapic.c index 22c38404f53..cd44a57c73b 100644 --- a/arch/ia64/kernel/iosapic.c +++ b/arch/ia64/kernel/iosapic.c @@ -76,7 +76,7 @@ * PCI pin -> global system interrupt (GSI) -> IA-64 vector <-> IRQ * * Note: The term "IRQ" is loosely used everywhere in Linux kernel to - * describeinterrupts. Now we use "IRQ" only for Linux IRQ's. ISA IRQ + * describe interrupts. Now we use "IRQ" only for Linux IRQ's. ISA IRQ * (isa_irq) is the only exception in this source code. */ @@ -98,7 +98,6 @@ #include <asm/machvec.h> #include <asm/processor.h> #include <asm/ptrace.h> -#include <asm/system.h> #undef DEBUG_INTERRUPT_ROUTING @@ -148,7 +147,7 @@ static struct iosapic_intr_info { unsigned char trigger : 1; /* trigger mode (see iosapic.h) */ } iosapic_intr_info[NR_IRQS]; -static unsigned char pcat_compat __devinitdata; /* 8259 compatibility flag */ +static unsigned char pcat_compat; /* 8259 compatibility flag */ static inline void iosapic_write(struct iosapic *iosapic, unsigned int reg, u32 val) @@ -257,7 +256,7 @@ set_rte (unsigned int gsi, unsigned int irq, unsigned int dest, int mask) } static void -nop (unsigned int irq) +nop (struct irq_data *data) { /* do nothing... */ } @@ -287,8 +286,9 @@ kexec_disable_iosapic(void) #endif static void -mask_irq (unsigned int irq) +mask_irq (struct irq_data *data) { + unsigned int irq = data->irq; u32 low32; int rte_index; struct iosapic_rte_info *rte; @@ -305,8 +305,9 @@ mask_irq (unsigned int irq) } static void -unmask_irq (unsigned int irq) +unmask_irq (struct irq_data *data) { + unsigned int irq = data->irq; u32 low32; int rte_index; struct iosapic_rte_info *rte; @@ -323,9 +324,11 @@ unmask_irq (unsigned int irq) static int -iosapic_set_affinity(unsigned int irq, const struct cpumask *mask) +iosapic_set_affinity(struct irq_data *data, const struct cpumask *mask, + bool force) { #ifdef CONFIG_SMP + unsigned int irq = data->irq; u32 high32, low32; int cpu, dest, rte_index; int redir = (irq & IA64_IRQ_REDIRECTED) ? 1 : 0; @@ -379,32 +382,33 @@ iosapic_set_affinity(unsigned int irq, const struct cpumask *mask) */ static unsigned int -iosapic_startup_level_irq (unsigned int irq) +iosapic_startup_level_irq (struct irq_data *data) { - unmask_irq(irq); + unmask_irq(data); return 0; } static void -iosapic_unmask_level_irq (unsigned int irq) +iosapic_unmask_level_irq (struct irq_data *data) { + unsigned int irq = data->irq; ia64_vector vec = irq_to_vector(irq); struct iosapic_rte_info *rte; int do_unmask_irq = 0; irq_complete_move(irq); - if (unlikely(irq_desc[irq].status & IRQ_MOVE_PENDING)) { + if (unlikely(irqd_is_setaffinity_pending(data))) { do_unmask_irq = 1; - mask_irq(irq); + mask_irq(data); } else - unmask_irq(irq); + unmask_irq(data); list_for_each_entry(rte, &iosapic_intr_info[irq].rtes, rte_list) iosapic_eoi(rte->iosapic->addr, vec); if (unlikely(do_unmask_irq)) { - move_masked_irq(irq); - unmask_irq(irq); + irq_move_masked_irq(data); + unmask_irq(data); } } @@ -414,15 +418,15 @@ iosapic_unmask_level_irq (unsigned int irq) #define iosapic_ack_level_irq nop static struct irq_chip irq_type_iosapic_level = { - .name = "IO-SAPIC-level", - .startup = iosapic_startup_level_irq, - .shutdown = iosapic_shutdown_level_irq, - .enable = iosapic_enable_level_irq, - .disable = iosapic_disable_level_irq, - .ack = iosapic_ack_level_irq, - .mask = mask_irq, - .unmask = iosapic_unmask_level_irq, - .set_affinity = iosapic_set_affinity + .name = "IO-SAPIC-level", + .irq_startup = iosapic_startup_level_irq, + .irq_shutdown = iosapic_shutdown_level_irq, + .irq_enable = iosapic_enable_level_irq, + .irq_disable = iosapic_disable_level_irq, + .irq_ack = iosapic_ack_level_irq, + .irq_mask = mask_irq, + .irq_unmask = iosapic_unmask_level_irq, + .irq_set_affinity = iosapic_set_affinity }; /* @@ -430,9 +434,9 @@ static struct irq_chip irq_type_iosapic_level = { */ static unsigned int -iosapic_startup_edge_irq (unsigned int irq) +iosapic_startup_edge_irq (struct irq_data *data) { - unmask_irq(irq); + unmask_irq(data); /* * IOSAPIC simply drops interrupts pended while the * corresponding pin was masked, so we can't know if an @@ -442,37 +446,25 @@ iosapic_startup_edge_irq (unsigned int irq) } static void -iosapic_ack_edge_irq (unsigned int irq) +iosapic_ack_edge_irq (struct irq_data *data) { - struct irq_desc *idesc = irq_desc + irq; - - irq_complete_move(irq); - move_native_irq(irq); - /* - * Once we have recorded IRQ_PENDING already, we can mask the - * interrupt for real. This prevents IRQ storms from unhandled - * devices. - */ - if ((idesc->status & (IRQ_PENDING|IRQ_DISABLED)) == - (IRQ_PENDING|IRQ_DISABLED)) - mask_irq(irq); + irq_complete_move(data->irq); + irq_move_irq(data); } #define iosapic_enable_edge_irq unmask_irq #define iosapic_disable_edge_irq nop -#define iosapic_end_edge_irq nop static struct irq_chip irq_type_iosapic_edge = { - .name = "IO-SAPIC-edge", - .startup = iosapic_startup_edge_irq, - .shutdown = iosapic_disable_edge_irq, - .enable = iosapic_enable_edge_irq, - .disable = iosapic_disable_edge_irq, - .ack = iosapic_ack_edge_irq, - .end = iosapic_end_edge_irq, - .mask = mask_irq, - .unmask = unmask_irq, - .set_affinity = iosapic_set_affinity + .name = "IO-SAPIC-edge", + .irq_startup = iosapic_startup_edge_irq, + .irq_shutdown = iosapic_disable_edge_irq, + .irq_enable = iosapic_enable_edge_irq, + .irq_disable = iosapic_disable_edge_irq, + .irq_ack = iosapic_ack_edge_irq, + .irq_mask = mask_irq, + .irq_unmask = unmask_irq, + .irq_set_affinity = iosapic_set_affinity }; static unsigned int @@ -562,8 +554,7 @@ static int register_intr (unsigned int gsi, int irq, unsigned char delivery, unsigned long polarity, unsigned long trigger) { - struct irq_desc *idesc; - struct irq_chip *irq_type; + struct irq_chip *chip, *irq_type; int index; struct iosapic_rte_info *rte; @@ -610,19 +601,18 @@ register_intr (unsigned int gsi, int irq, unsigned char delivery, irq_type = iosapic_get_irq_chip(trigger); - idesc = irq_desc + irq; - if (irq_type != NULL && idesc->chip != irq_type) { - if (idesc->chip != &no_irq_chip) + chip = irq_get_chip(irq); + if (irq_type != NULL && chip != irq_type) { + if (chip != &no_irq_chip) printk(KERN_WARNING "%s: changing vector %d from %s to %s\n", __func__, irq_to_vector(irq), - idesc->chip->name, irq_type->name); - idesc->chip = irq_type; + chip->name, irq_type->name); + chip = irq_type; } - if (trigger == IOSAPIC_EDGE) - __set_irq_handler_unlocked(irq, handle_edge_irq); - else - __set_irq_handler_unlocked(irq, handle_level_irq); + __irq_set_chip_handler_name_locked(irq, chip, trigger == IOSAPIC_EDGE ? + handle_edge_irq : handle_level_irq, + NULL); return 0; } @@ -732,6 +722,7 @@ iosapic_register_intr (unsigned int gsi, struct iosapic_rte_info *rte; u32 low32; unsigned char dmode; + struct irq_desc *desc; /* * If this GSI has already been registered (i.e., it's a @@ -744,7 +735,7 @@ iosapic_register_intr (unsigned int gsi, rte = find_rte(irq, gsi); if(iosapic_intr_info[irq].count == 0) { assign_irq_vector(irq); - dynamic_irq_init(irq); + irq_init_desc(irq); } else if (rte->refcnt != NO_REF_RTE) { rte->refcnt++; goto unlock_iosapic_lock; @@ -759,12 +750,13 @@ iosapic_register_intr (unsigned int gsi, goto unlock_iosapic_lock; } - raw_spin_lock(&irq_desc[irq].lock); + desc = irq_to_desc(irq); + raw_spin_lock(&desc->lock); dest = get_target_cpu(gsi, irq); dmode = choose_dmode(); err = register_intr(gsi, irq, dmode, polarity, trigger); if (err < 0) { - raw_spin_unlock(&irq_desc[irq].lock); + raw_spin_unlock(&desc->lock); irq = err; goto unlock_iosapic_lock; } @@ -783,7 +775,7 @@ iosapic_register_intr (unsigned int gsi, (polarity == IOSAPIC_POL_HIGH ? "high" : "low"), cpu_logical_id(dest), dest, irq_to_vector(irq)); - raw_spin_unlock(&irq_desc[irq].lock); + raw_spin_unlock(&desc->lock); unlock_iosapic_lock: spin_unlock_irqrestore(&iosapic_lock, flags); return irq; @@ -794,7 +786,6 @@ iosapic_unregister_intr (unsigned int gsi) { unsigned long flags; int irq, index; - struct irq_desc *idesc; u32 low32; unsigned long trigger, polarity; unsigned int dest; @@ -824,7 +815,6 @@ iosapic_unregister_intr (unsigned int gsi) if (--rte->refcnt > 0) goto out; - idesc = irq_desc + irq; rte->refcnt = NO_REF_RTE; /* Mask the interrupt */ @@ -848,7 +838,7 @@ iosapic_unregister_intr (unsigned int gsi) if (iosapic_intr_info[irq].count == 0) { #ifdef CONFIG_SMP /* Clear affinity */ - cpumask_setall(idesc->affinity); + cpumask_setall(irq_get_irq_data(irq)->affinity); #endif /* Clear the interrupt information */ iosapic_intr_info[irq].dest = 0; @@ -924,10 +914,8 @@ iosapic_register_platform_intr (u32 int_type, unsigned int gsi, /* * ACPI calls this when it finds an entry for a legacy ISA IRQ override. */ -void __devinit -iosapic_override_isa_irq (unsigned int isa_irq, unsigned int gsi, - unsigned long polarity, - unsigned long trigger) +void iosapic_override_isa_irq(unsigned int isa_irq, unsigned int gsi, + unsigned long polarity, unsigned long trigger) { int vector, irq; unsigned int dest = cpu_physical_id(smp_processor_id()); @@ -1022,8 +1010,27 @@ iosapic_check_gsi_range (unsigned int gsi_base, unsigned int ver) return 0; } -int __devinit -iosapic_init (unsigned long phys_addr, unsigned int gsi_base) +static int +iosapic_delete_rte(unsigned int irq, unsigned int gsi) +{ + struct iosapic_rte_info *rte, *temp; + + list_for_each_entry_safe(rte, temp, &iosapic_intr_info[irq].rtes, + rte_list) { + if (rte->iosapic->gsi_base + rte->rte_index == gsi) { + if (rte->refcnt) + return -EBUSY; + + list_del(&rte->rte_list); + kfree(rte); + return 0; + } + } + + return -EINVAL; +} + +int iosapic_init(unsigned long phys_addr, unsigned int gsi_base) { int num_rte, err, index; unsigned int isa_irq, ver; @@ -1080,11 +1087,9 @@ iosapic_init (unsigned long phys_addr, unsigned int gsi_base) return 0; } -#ifdef CONFIG_HOTPLUG -int -iosapic_remove (unsigned int gsi_base) +int iosapic_remove(unsigned int gsi_base) { - int index, err = 0; + int i, irq, index, err = 0; unsigned long flags; spin_lock_irqsave(&iosapic_lock, flags); @@ -1102,17 +1107,25 @@ iosapic_remove (unsigned int gsi_base) goto out; } + for (i = gsi_base; i < gsi_base + iosapic_lists[index].num_rte; i++) { + irq = __gsi_to_irq(i); + if (irq < 0) + continue; + + err = iosapic_delete_rte(irq, i); + if (err) + goto out; + } + iounmap(iosapic_lists[index].addr); iosapic_free(index); out: spin_unlock_irqrestore(&iosapic_lock, flags); return err; } -#endif /* CONFIG_HOTPLUG */ #ifdef CONFIG_NUMA -void __devinit -map_iosapic_to_node(unsigned int gsi_base, int node) +void map_iosapic_to_node(unsigned int gsi_base, int node) { int index; diff --git a/arch/ia64/kernel/irq.c b/arch/ia64/kernel/irq.c index 94ee9d067cb..f2c41828113 100644 --- a/arch/ia64/kernel/irq.c +++ b/arch/ia64/kernel/irq.c @@ -23,6 +23,8 @@ #include <linux/interrupt.h> #include <linux/kernel_stat.h> +#include <asm/mca.h> + /* * 'what should we do if we get a hw irq event on an illegal vector'. * each architecture has to answer this themselves. @@ -53,47 +55,9 @@ atomic_t irq_err_count; /* * /proc/interrupts printing: */ - -int show_interrupts(struct seq_file *p, void *v) +int arch_show_interrupts(struct seq_file *p, int prec) { - int i = *(loff_t *) v, j; - struct irqaction * action; - unsigned long flags; - - if (i == 0) { - char cpuname[16]; - seq_printf(p, " "); - for_each_online_cpu(j) { - snprintf(cpuname, 10, "CPU%d", j); - seq_printf(p, "%10s ", cpuname); - } - seq_putc(p, '\n'); - } - - if (i < NR_IRQS) { - raw_spin_lock_irqsave(&irq_desc[i].lock, flags); - action = irq_desc[i].action; - if (!action) - goto skip; - seq_printf(p, "%3d: ",i); -#ifndef CONFIG_SMP - seq_printf(p, "%10u ", kstat_irqs(i)); -#else - for_each_online_cpu(j) { - seq_printf(p, "%10u ", kstat_irqs_cpu(i, j)); - } -#endif - seq_printf(p, " %14s", irq_desc[i].chip->name); - seq_printf(p, " %s", action->name); - - for (action=action->next; action; action = action->next) - seq_printf(p, ", %s", action->name); - - seq_putc(p, '\n'); -skip: - raw_spin_unlock_irqrestore(&irq_desc[i].lock, flags); - } else if (i == NR_IRQS) - seq_printf(p, "ERR: %10u\n", atomic_read(&irq_err_count)); + seq_printf(p, "ERR: %10u\n", atomic_read(&irq_err_count)); return 0; } @@ -103,7 +67,7 @@ static char irq_redir [NR_IRQS]; // = { [0 ... NR_IRQS-1] = 1 }; void set_irq_affinity_info (unsigned int irq, int hwid, int redir) { if (irq < NR_IRQS) { - cpumask_copy(irq_desc[irq].affinity, + cpumask_copy(irq_get_irq_data(irq)->affinity, cpumask_of(cpu_logical_id(hwid))); irq_redir[irq] = (char) (redir & 0xff); } @@ -121,6 +85,12 @@ bool is_affinity_mask_valid(const struct cpumask *cpumask) #endif /* CONFIG_SMP */ +int __init arch_early_irq_init(void) +{ + ia64_mca_irq_init(); + return 0; +} + #ifdef CONFIG_HOTPLUG_CPU unsigned int vectors_in_migration[NR_IRQS]; @@ -130,13 +100,14 @@ unsigned int vectors_in_migration[NR_IRQS]; */ static void migrate_irqs(void) { - struct irq_desc *desc; int irq, new_cpu; for (irq=0; irq < NR_IRQS; irq++) { - desc = irq_desc + irq; + struct irq_desc *desc = irq_to_desc(irq); + struct irq_data *data = irq_desc_get_irq_data(desc); + struct irq_chip *chip = irq_data_get_irq_chip(data); - if (desc->status == IRQ_DISABLED) + if (irqd_irq_disabled(data)) continue; /* @@ -145,10 +116,10 @@ static void migrate_irqs(void) * tell CPU not to respond to these local intr sources. * such as ITV,CPEI,MCA etc. */ - if (desc->status == IRQ_PER_CPU) + if (irqd_is_per_cpu(data)) continue; - if (cpumask_any_and(irq_desc[irq].affinity, cpu_online_mask) + if (cpumask_any_and(data->affinity, cpu_online_mask) >= nr_cpu_ids) { /* * Save it for phase 2 processing @@ -160,16 +131,16 @@ static void migrate_irqs(void) /* * Al three are essential, currently WARN_ON.. maybe panic? */ - if (desc->chip && desc->chip->disable && - desc->chip->enable && desc->chip->set_affinity) { - desc->chip->disable(irq); - desc->chip->set_affinity(irq, - cpumask_of(new_cpu)); - desc->chip->enable(irq); + if (chip && chip->irq_disable && + chip->irq_enable && chip->irq_set_affinity) { + chip->irq_disable(data); + chip->irq_set_affinity(data, + cpumask_of(new_cpu), false); + chip->irq_enable(data); } else { - WARN_ON((!(desc->chip) || !(desc->chip->disable) || - !(desc->chip->enable) || - !(desc->chip->set_affinity))); + WARN_ON((!chip || !chip->irq_disable || + !chip->irq_enable || + !chip->irq_set_affinity)); } } } diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c index 9a26015c3e5..03ea78ed64a 100644 --- a/arch/ia64/kernel/irq_ia64.c +++ b/arch/ia64/kernel/irq_ia64.c @@ -23,7 +23,6 @@ #include <linux/ioport.h> #include <linux/kernel_stat.h> #include <linux/ptrace.h> -#include <linux/random.h> /* for rand_initialize_irq() */ #include <linux/signal.h> #include <linux/smp.h> #include <linux/threads.h> @@ -31,6 +30,7 @@ #include <linux/irq.h> #include <linux/ratelimit.h> #include <linux/acpi.h> +#include <linux/sched.h> #include <asm/delay.h> #include <asm/intrinsics.h> @@ -38,7 +38,6 @@ #include <asm/hw_irq.h> #include <asm/machvec.h> #include <asm/pgtable.h> -#include <asm/system.h> #include <asm/tlbflush.h> #ifdef CONFIG_PERFMON @@ -94,14 +93,6 @@ static int irq_status[NR_IRQS] = { [0 ... NR_IRQS -1] = IRQ_UNUSED }; -int check_irq_used(int irq) -{ - if (irq_status[irq] == IRQ_USED) - return 1; - - return -1; -} - static inline int find_unassigned_irq(void) { int irq; @@ -117,7 +108,7 @@ static inline int find_unassigned_vector(cpumask_t domain) cpumask_t mask; int pos, vector; - cpus_and(mask, domain, cpu_online_map); + cpumask_and(&mask, &domain, cpu_online_mask); if (cpus_empty(mask)) return -EINVAL; @@ -140,7 +131,7 @@ static int __bind_irq_vector(int irq, int vector, cpumask_t domain) BUG_ON((unsigned)irq >= NR_IRQS); BUG_ON((unsigned)vector >= IA64_NUM_VECTORS); - cpus_and(mask, domain, cpu_online_map); + cpumask_and(&mask, &domain, cpu_online_mask); if (cpus_empty(mask)) return -EINVAL; if ((cfg->vector == vector) && cpus_equal(cfg->domain, domain)) @@ -178,7 +169,7 @@ static void __clear_irq_vector(int irq) BUG_ON(cfg->vector == IRQ_VECTOR_UNASSIGNED); vector = cfg->vector; domain = cfg->domain; - cpus_and(mask, cfg->domain, cpu_online_map); + cpumask_and(&mask, &cfg->domain, cpu_online_mask); for_each_cpu_mask(cpu, mask) per_cpu(vector_irq, cpu)[vector] = -1; cfg->vector = IRQ_VECTOR_UNASSIGNED; @@ -321,7 +312,7 @@ void irq_complete_move(unsigned irq) if (unlikely(cpu_isset(smp_processor_id(), cfg->old_domain))) return; - cpus_and(cleanup_mask, cfg->old_domain, cpu_online_map); + cpumask_and(&cleanup_mask, &cfg->old_domain, cpu_online_mask); cfg->move_cleanup_count = cpus_weight(cleanup_mask); for_each_cpu_mask(i, cleanup_mask) platform_send_ipi(i, IA64_IRQ_MOVE_VECTOR, IA64_IPI_DM_INT, 0); @@ -343,7 +334,7 @@ static irqreturn_t smp_irq_move_cleanup_interrupt(int irq, void *dev_id) if (irq < 0) continue; - desc = irq_desc + irq; + desc = irq_to_desc(irq); cfg = irq_cfg + irq; raw_spin_lock(&desc->lock); if (!cfg->move_cleanup_count) @@ -365,7 +356,6 @@ static irqreturn_t smp_irq_move_cleanup_interrupt(int irq, void *dev_id) static struct irqaction irq_move_irqaction = { .handler = smp_irq_move_cleanup_interrupt, - .flags = IRQF_DISABLED, .name = "irq_move" }; @@ -392,8 +382,7 @@ void destroy_and_reserve_irq(unsigned int irq) { unsigned long flags; - dynamic_irq_cleanup(irq); - + irq_init_desc(irq); spin_lock_irqsave(&vector_lock, flags); __clear_irq_vector(irq); irq_status[irq] = IRQ_RSVD; @@ -426,13 +415,13 @@ int create_irq(void) out: spin_unlock_irqrestore(&vector_lock, flags); if (irq >= 0) - dynamic_irq_init(irq); + irq_init_desc(irq); return irq; } void destroy_irq(unsigned int irq) { - dynamic_irq_cleanup(irq); + irq_init_desc(irq); clear_irq_vector(irq); } @@ -490,13 +479,13 @@ ia64_handle_irq (ia64_vector vector, struct pt_regs *regs) ia64_srlz_d(); while (vector != IA64_SPURIOUS_INT_VECTOR) { int irq = local_vector_to_irq(vector); - struct irq_desc *desc = irq_to_desc(irq); if (unlikely(IS_LOCAL_TLB_FLUSH(vector))) { smp_local_flush_tlb(); - kstat_incr_irqs_this_cpu(irq, desc); + kstat_incr_irq_this_cpu(irq); } else if (unlikely(IS_RESCHEDULE(vector))) { - kstat_incr_irqs_this_cpu(irq, desc); + scheduler_ipi(); + kstat_incr_irq_this_cpu(irq); } else { ia64_setreg(_IA64_REG_CR_TPR, vector); ia64_srlz_d(); @@ -549,13 +538,12 @@ void ia64_process_pending_intr(void) */ while (vector != IA64_SPURIOUS_INT_VECTOR) { int irq = local_vector_to_irq(vector); - struct irq_desc *desc = irq_to_desc(irq); if (unlikely(IS_LOCAL_TLB_FLUSH(vector))) { smp_local_flush_tlb(); - kstat_incr_irqs_this_cpu(irq, desc); + kstat_incr_irq_this_cpu(irq); } else if (unlikely(IS_RESCHEDULE(vector))) { - kstat_incr_irqs_this_cpu(irq, desc); + kstat_incr_irq_this_cpu(irq); } else { struct pt_regs *old_regs = set_irq_regs(NULL); @@ -602,7 +590,6 @@ static irqreturn_t dummy_handler (int irq, void *dev_id) static struct irqaction ipi_irqaction = { .handler = handle_IPI, - .flags = IRQF_DISABLED, .name = "IPI" }; @@ -611,13 +598,11 @@ static struct irqaction ipi_irqaction = { */ static struct irqaction resched_irqaction = { .handler = dummy_handler, - .flags = IRQF_DISABLED, .name = "resched" }; static struct irqaction tlb_irqaction = { .handler = dummy_handler, - .flags = IRQF_DISABLED, .name = "tlb_flush" }; @@ -626,17 +611,15 @@ static struct irqaction tlb_irqaction = { void ia64_native_register_percpu_irq (ia64_vector vec, struct irqaction *action) { - struct irq_desc *desc; unsigned int irq; irq = vec; BUG_ON(bind_irq_vector(irq, vec, CPU_MASK_ALL)); - desc = irq_desc + irq; - desc->status |= IRQ_PER_CPU; - desc->chip = &irq_type_ia64_lsapic; + irq_set_status_flags(irq, IRQ_PER_CPU); + irq_set_chip(irq, &irq_type_ia64_lsapic); if (action) setup_irq(irq, action); - set_irq_handler(irq, handle_percpu_irq); + irq_set_handler(irq, handle_percpu_irq); } void __init diff --git a/arch/ia64/kernel/irq_lsapic.c b/arch/ia64/kernel/irq_lsapic.c index fc1549d4564..1b3a776e516 100644 --- a/arch/ia64/kernel/irq_lsapic.c +++ b/arch/ia64/kernel/irq_lsapic.c @@ -15,31 +15,30 @@ #include <linux/irq.h> static unsigned int -lsapic_noop_startup (unsigned int irq) +lsapic_noop_startup (struct irq_data *data) { return 0; } static void -lsapic_noop (unsigned int irq) +lsapic_noop (struct irq_data *data) { /* nothing to do... */ } -static int lsapic_retrigger(unsigned int irq) +static int lsapic_retrigger(struct irq_data *data) { - ia64_resend_irq(irq); + ia64_resend_irq(data->irq); return 1; } struct irq_chip irq_type_ia64_lsapic = { - .name = "LSAPIC", - .startup = lsapic_noop_startup, - .shutdown = lsapic_noop, - .enable = lsapic_noop, - .disable = lsapic_noop, - .ack = lsapic_noop, - .end = lsapic_noop, - .retrigger = lsapic_retrigger, + .name = "LSAPIC", + .irq_startup = lsapic_noop_startup, + .irq_shutdown = lsapic_noop, + .irq_enable = lsapic_noop, + .irq_disable = lsapic_noop, + .irq_ack = lsapic_noop, + .irq_retrigger = lsapic_retrigger, }; diff --git a/arch/ia64/kernel/ivt.S b/arch/ia64/kernel/ivt.S index d93e396bf59..18e794a5724 100644 --- a/arch/ia64/kernel/ivt.S +++ b/arch/ia64/kernel/ivt.S @@ -54,12 +54,11 @@ #include <asm/pgtable.h> #include <asm/processor.h> #include <asm/ptrace.h> -#include <asm/system.h> #include <asm/thread_info.h> #include <asm/unistd.h> #include <asm/errno.h> -#if 1 +#if 0 # define PSR_DEFAULT_BITS psr.ac #else # define PSR_DEFAULT_BITS 0 @@ -785,7 +784,7 @@ ENTRY(break_fault) (p8) adds r28=16,r28 // A switch cr.iip to next bundle (p9) adds r8=1,r8 // A increment ei to next slot -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE ;; mov b6=r30 // I0 setup syscall handler branch reg early #else @@ -802,7 +801,7 @@ ENTRY(break_fault) // /////////////////////////////////////////////////////////////////////// st1 [r16]=r0 // M2|3 clear current->thread.on_ustack flag -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE MOV_FROM_ITC(p0, p14, r30, r18) // M get cycle for accounting #else mov b6=r30 // I0 setup syscall handler branch reg early @@ -818,7 +817,7 @@ ENTRY(break_fault) cmp.eq p14,p0=r9,r0 // A are syscalls being traced/audited? br.call.sptk.many b7=ia64_syscall_setup // B 1: -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE // mov.m r30=ar.itc is called in advance, and r13 is current add r16=TI_AC_STAMP+IA64_TASK_SIZE,r13 // A add r17=TI_AC_LEAVE+IA64_TASK_SIZE,r13 // A @@ -1044,7 +1043,7 @@ END(ia64_syscall_setup) DBG_FAULT(16) FAULT(16) -#if defined(CONFIG_VIRT_CPU_ACCOUNTING) && defined(__IA64_ASM_PARAVIRTUALIZED_NATIVE) +#if defined(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE) && defined(__IA64_ASM_PARAVIRTUALIZED_NATIVE) /* * There is no particular reason for this code to be here, other than * that there happens to be space here that would go unused otherwise. diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c index 7026b29e277..074fde49c9e 100644 --- a/arch/ia64/kernel/kprobes.c +++ b/arch/ia64/kernel/kprobes.c @@ -423,7 +423,7 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) { struct kretprobe_instance *ri = NULL; struct hlist_head *head, empty_rp; - struct hlist_node *node, *tmp; + struct hlist_node *tmp; unsigned long flags, orig_ret_address = 0; unsigned long trampoline_address = ((struct fnptr *)kretprobe_trampoline)->ip; @@ -444,7 +444,7 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) * real return address, and all the rest will point to * kretprobe_trampoline */ - hlist_for_each_entry_safe(ri, node, tmp, head, hlist) { + hlist_for_each_entry_safe(ri, tmp, head, hlist) { if (ri->task != current) /* another task is sharing our hash bucket */ continue; @@ -461,7 +461,7 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) regs->cr_iip = orig_ret_address; - hlist_for_each_entry_safe(ri, node, tmp, head, hlist) { + hlist_for_each_entry_safe(ri, tmp, head, hlist) { if (ri->task != current) /* another task is sharing our hash bucket */ continue; @@ -487,7 +487,7 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) kretprobe_hash_unlock(current, &flags); preempt_enable_no_resched(); - hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) { + hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); kfree(ri); } @@ -947,7 +947,7 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr) case KPROBE_HIT_SSDONE: /* * We increment the nmissed count for accounting, - * we can also use npre/npostfault count for accouting + * we can also use npre/npostfault count for accounting * these specific fault cases. */ kprobes_inc_nmissed_count(cur); diff --git a/arch/ia64/kernel/machine_kexec.c b/arch/ia64/kernel/machine_kexec.c index 3d3aeef4694..5151a649c96 100644 --- a/arch/ia64/kernel/machine_kexec.c +++ b/arch/ia64/kernel/machine_kexec.c @@ -27,11 +27,11 @@ #include <asm/sal.h> #include <asm/mca.h> -typedef NORET_TYPE void (*relocate_new_kernel_t)( +typedef void (*relocate_new_kernel_t)( unsigned long indirection_page, unsigned long start_address, struct ia64_boot_param *boot_param, - unsigned long pal_addr) ATTRIB_NORET; + unsigned long pal_addr) __noreturn; struct kimage *ia64_kimage; @@ -85,12 +85,13 @@ static void ia64_machine_kexec(struct unw_frame_info *info, void *arg) struct kimage *image = arg; relocate_new_kernel_t rnk; void *pal_addr = efi_get_pal_addr(); - unsigned long code_addr = (unsigned long)page_address(image->control_code_page); + unsigned long code_addr; int ii; u64 fp, gp; ia64_fptr_t *init_handler = (ia64_fptr_t *)ia64_os_init_on_kdump; BUG_ON(!image); + code_addr = (unsigned long)page_address(image->control_code_page); if (image->type == KEXEC_TYPE_CRASH) { crash_save_this_cpu(); current->thread.ksp = (__u64)info->sw - 16; @@ -157,7 +158,7 @@ void arch_crash_save_vmcoreinfo(void) #endif #ifdef CONFIG_PGTABLE_3 VMCOREINFO_CONFIG(PGTABLE_3); -#elif CONFIG_PGTABLE_4 +#elif defined(CONFIG_PGTABLE_4) VMCOREINFO_CONFIG(PGTABLE_4); #endif } diff --git a/arch/ia64/kernel/machvec.c b/arch/ia64/kernel/machvec.c index d41a40ef80c..f5a1e5246b3 100644 --- a/arch/ia64/kernel/machvec.c +++ b/arch/ia64/kernel/machvec.c @@ -1,7 +1,6 @@ #include <linux/module.h> #include <linux/dma-mapping.h> #include <asm/machvec.h> -#include <asm/system.h> #ifdef CONFIG_IA64_GENERIC diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c index 1753f6a30d5..db7b36bb068 100644 --- a/arch/ia64/kernel/mca.c +++ b/arch/ia64/kernel/mca.c @@ -92,7 +92,6 @@ #include <asm/meminit.h> #include <asm/page.h> #include <asm/ptrace.h> -#include <asm/system.h> #include <asm/sal.h> #include <asm/mca.h> #include <asm/kexec.h> @@ -218,7 +217,7 @@ void ia64_mca_printk(const char *fmt, ...) /* Copy the output into mlogbuf */ if (oops_in_progress) { /* mlogbuf was abandoned, use printk directly instead. */ - printk(temp_buf); + printk("%s", temp_buf); } else { spin_lock(&mlogbuf_wlock); for (p = temp_buf; *p; p++) { @@ -269,7 +268,7 @@ void ia64_mlogbuf_dump(void) } *p = '\0'; if (temp_buf[0]) - printk(temp_buf); + printk("%s", temp_buf); mlogbuf_start = index; mlogbuf_timestamp = 0; @@ -582,6 +581,8 @@ out: /* Get the CPE error record and log it */ ia64_mca_log_sal_error_record(SAL_INFO_TYPE_CPE); + local_irq_disable(); + return IRQ_HANDLED; } @@ -630,7 +631,7 @@ ia64_mca_register_cpev (int cpev) * Outputs * None */ -void __cpuinit +void ia64_mca_cmc_vector_setup (void) { cmcv_reg_t cmcv; @@ -1445,6 +1446,8 @@ out: /* Get the CMC error record and log it */ ia64_mca_log_sal_error_record(SAL_INFO_TYPE_CMC); + local_irq_disable(); + return IRQ_HANDLED; } @@ -1511,7 +1514,8 @@ static void ia64_mca_cmc_poll (unsigned long dummy) { /* Trigger a CMC interrupt cascade */ - platform_send_ipi(first_cpu(cpu_online_map), IA64_CMCP_VECTOR, IA64_IPI_DM_INT, 0); + platform_send_ipi(cpumask_first(cpu_online_mask), IA64_CMCP_VECTOR, + IA64_IPI_DM_INT, 0); } /* @@ -1587,7 +1591,8 @@ static void ia64_mca_cpe_poll (unsigned long dummy) { /* Trigger a CPE interrupt cascade */ - platform_send_ipi(first_cpu(cpu_online_map), IA64_CPEP_VECTOR, IA64_IPI_DM_INT, 0); + platform_send_ipi(cpumask_first(cpu_online_mask), IA64_CPEP_VECTOR, + IA64_IPI_DM_INT, 0); } #endif /* CONFIG_ACPI */ @@ -1767,38 +1772,32 @@ __setup("disable_cpe_poll", ia64_mca_disable_cpe_polling); static struct irqaction cmci_irqaction = { .handler = ia64_mca_cmc_int_handler, - .flags = IRQF_DISABLED, .name = "cmc_hndlr" }; static struct irqaction cmcp_irqaction = { .handler = ia64_mca_cmc_int_caller, - .flags = IRQF_DISABLED, .name = "cmc_poll" }; static struct irqaction mca_rdzv_irqaction = { .handler = ia64_mca_rendez_int_handler, - .flags = IRQF_DISABLED, .name = "mca_rdzv" }; static struct irqaction mca_wkup_irqaction = { .handler = ia64_mca_wakeup_int_handler, - .flags = IRQF_DISABLED, .name = "mca_wkup" }; #ifdef CONFIG_ACPI static struct irqaction mca_cpe_irqaction = { .handler = ia64_mca_cpe_int_handler, - .flags = IRQF_DISABLED, .name = "cpe_hndlr" }; static struct irqaction mca_cpep_irqaction = { .handler = ia64_mca_cpe_int_caller, - .flags = IRQF_DISABLED, .name = "cpe_poll" }; #endif /* CONFIG_ACPI */ @@ -1809,7 +1808,7 @@ static struct irqaction mca_cpep_irqaction = { * format most of the fields. */ -static void __cpuinit +static void format_mca_init_stack(void *mca_data, unsigned long offset, const char *type, int cpu) { @@ -1839,7 +1838,7 @@ static void * __init_refok mca_bootmem(void) } /* Do per-CPU MCA-related initialization. */ -void __cpuinit +void ia64_mca_cpu_init(void *cpu_data) { void *pal_vaddr; @@ -1859,7 +1858,8 @@ ia64_mca_cpu_init(void *cpu_data) data = mca_bootmem(); first_time = 0; } else - data = __get_free_pages(GFP_KERNEL, get_order(sz)); + data = (void *)__get_free_pages(GFP_KERNEL, + get_order(sz)); if (!data) panic("Could not allocate MCA memory for cpu %d\n", cpu); @@ -1890,7 +1890,7 @@ ia64_mca_cpu_init(void *cpu_data) PAGE_KERNEL)); } -static void __cpuinit ia64_mca_cmc_vector_adjust(void *dummy) +static void ia64_mca_cmc_vector_adjust(void *dummy) { unsigned long flags; @@ -1900,7 +1900,7 @@ static void __cpuinit ia64_mca_cmc_vector_adjust(void *dummy) local_irq_restore(flags); } -static int __cpuinit mca_cpu_callback(struct notifier_block *nfb, +static int mca_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { @@ -1916,7 +1916,7 @@ static int __cpuinit mca_cpu_callback(struct notifier_block *nfb, return NOTIFY_OK; } -static struct notifier_block mca_cpu_notifier __cpuinitdata = { +static struct notifier_block mca_cpu_notifier = { .notifier_call = mca_cpu_callback }; @@ -2068,22 +2068,16 @@ ia64_mca_init(void) printk(KERN_INFO "MCA related initialization done\n"); } + /* - * ia64_mca_late_init - * - * Opportunity to setup things that require initialization later - * than ia64_mca_init. Setup a timer to poll for CPEs if the - * platform doesn't support an interrupt driven mechanism. - * - * Inputs : None - * Outputs : Status + * These pieces cannot be done in ia64_mca_init() because it is called before + * early_irq_init() which would wipe out our percpu irq registrations. But we + * cannot leave them until ia64_mca_late_init() because by then all the other + * processors have been brought online and have set their own CMC vectors to + * point at a non-existant action. Called from arch_early_irq_init(). */ -static int __init -ia64_mca_late_init(void) +void __init ia64_mca_irq_init(void) { - if (!mca_init) - return 0; - /* * Configure the CMCI/P vector and handler. Interrupts for CMC are * per-processor, so AP CMC interrupts are setup in smp_callin() (smpboot.c). @@ -2102,6 +2096,23 @@ ia64_mca_late_init(void) /* Setup the CPEI/P handler */ register_percpu_irq(IA64_CPEP_VECTOR, &mca_cpep_irqaction); #endif +} + +/* + * ia64_mca_late_init + * + * Opportunity to setup things that require initialization later + * than ia64_mca_init. Setup a timer to poll for CPEs if the + * platform doesn't support an interrupt driven mechanism. + * + * Inputs : None + * Outputs : Status + */ +static int __init +ia64_mca_late_init(void) +{ + if (!mca_init) + return 0; register_hotcpu_notifier(&mca_cpu_notifier); @@ -2122,7 +2133,6 @@ ia64_mca_late_init(void) cpe_poll_timer.function = ia64_mca_cpe_poll; { - struct irq_desc *desc; unsigned int irq; if (cpe_vector >= 0) { @@ -2130,8 +2140,7 @@ ia64_mca_late_init(void) irq = local_vector_to_irq(cpe_vector); if (irq > 0) { cpe_poll_enabled = 0; - desc = irq_desc + irq; - desc->status |= IRQ_PER_CPU; + irq_set_status_flags(irq, IRQ_PER_CPU); setup_irq(irq, &mca_cpe_irqaction); ia64_cpe_irq = irq; ia64_mca_register_cpev(cpe_vector); diff --git a/arch/ia64/kernel/mca_drv.c b/arch/ia64/kernel/mca_drv.c index 09b4d6828c4..94f8bf777af 100644 --- a/arch/ia64/kernel/mca_drv.c +++ b/arch/ia64/kernel/mca_drv.c @@ -28,7 +28,6 @@ #include <asm/machvec.h> #include <asm/page.h> #include <asm/ptrace.h> -#include <asm/system.h> #include <asm/sal.h> #include <asm/mca.h> @@ -159,7 +158,8 @@ mca_handler_bh(unsigned long paddr, void *iip, unsigned long ipsr) ia64_mlogbuf_dump(); printk(KERN_ERR "OS_MCA: process [cpu %d, pid: %d, uid: %d, " "iip: %p, psr: 0x%lx,paddr: 0x%lx](%s) encounters MCA.\n", - raw_smp_processor_id(), current->pid, current_uid(), + raw_smp_processor_id(), current->pid, + from_kuid(&init_user_ns, current_uid()), iip, ipsr, paddr, current->comm); spin_lock(&mca_bh_lock); @@ -349,7 +349,7 @@ init_record_index_pools(void) /* - 3 - */ slidx_pool.max_idx = (rec_max_size/sect_min_size) * 2 + 1; - slidx_pool.buffer = (slidx_list_t *) + slidx_pool.buffer = kmalloc(slidx_pool.max_idx * sizeof(slidx_list_t), GFP_KERNEL); return slidx_pool.buffer ? 0 : -ENOMEM; diff --git a/arch/ia64/kernel/minstate.h b/arch/ia64/kernel/minstate.h index d56753a1163..cc82a7d744c 100644 --- a/arch/ia64/kernel/minstate.h +++ b/arch/ia64/kernel/minstate.h @@ -4,7 +4,7 @@ #include "entry.h" #include "paravirt_inst.h" -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE /* read ar.itc in advance, and use it before leaving bank 0 */ #define ACCOUNT_GET_STAMP \ (pUStk) mov.m r20=ar.itc; diff --git a/arch/ia64/kernel/module.c b/arch/ia64/kernel/module.c index 1481b0a28ca..24603be24c1 100644 --- a/arch/ia64/kernel/module.c +++ b/arch/ia64/kernel/module.c @@ -304,14 +304,6 @@ plt_target (struct plt_entry *plt) #endif /* !USE_BRL */ -void * -module_alloc (unsigned long size) -{ - if (!size) - return NULL; - return vmalloc(size); -} - void module_free (struct module *mod, void *module_region) { @@ -853,14 +845,6 @@ apply_relocate_add (Elf64_Shdr *sechdrs, const char *strtab, unsigned int symind return 0; } -int -apply_relocate (Elf64_Shdr *sechdrs, const char *strtab, unsigned int symindex, - unsigned int relsec, struct module *mod) -{ - printk(KERN_ERR "module %s: REL relocs in section %u unsupported\n", mod->name, relsec); - return -ENOEXEC; -} - /* * Modules contain a single unwind table which covers both the core and the init text * sections but since the two are not contiguous, we need to split this table up such that diff --git a/arch/ia64/kernel/msi_ia64.c b/arch/ia64/kernel/msi_ia64.c index 00b19a416ea..c430f9198d1 100644 --- a/arch/ia64/kernel/msi_ia64.c +++ b/arch/ia64/kernel/msi_ia64.c @@ -12,15 +12,13 @@ static struct irq_chip ia64_msi_chip; #ifdef CONFIG_SMP -static int ia64_set_msi_irq_affinity(unsigned int irq, - const cpumask_t *cpu_mask) +static int ia64_set_msi_irq_affinity(struct irq_data *idata, + const cpumask_t *cpu_mask, bool force) { struct msi_msg msg; u32 addr, data; - int cpu = first_cpu(*cpu_mask); - - if (!cpu_online(cpu)) - return -1; + int cpu = cpumask_first_and(cpu_mask, cpu_online_mask); + unsigned int irq = idata->irq; if (irq_prepare_move(irq, cpu)) return -1; @@ -38,7 +36,7 @@ static int ia64_set_msi_irq_affinity(unsigned int irq, msg.data = data; write_msi_msg(irq, &msg); - cpumask_copy(irq_desc[irq].affinity, cpumask_of(cpu)); + cpumask_copy(idata->affinity, cpumask_of(cpu)); return 0; } @@ -55,8 +53,8 @@ int ia64_setup_msi_irq(struct pci_dev *pdev, struct msi_desc *desc) if (irq < 0) return irq; - set_irq_msi(irq, desc); - cpus_and(mask, irq_to_domain(irq), cpu_online_map); + irq_set_msi_desc(irq, desc); + cpumask_and(&mask, &(irq_to_domain(irq)), cpu_online_mask); dest_phys_id = cpu_physical_id(first_cpu(mask)); vector = irq_to_vector(irq); @@ -74,7 +72,7 @@ int ia64_setup_msi_irq(struct pci_dev *pdev, struct msi_desc *desc) MSI_DATA_VECTOR(vector); write_msi_msg(irq, &msg); - set_irq_chip_and_handler(irq, &ia64_msi_chip, handle_edge_irq); + irq_set_chip_and_handler(irq, &ia64_msi_chip, handle_edge_irq); return 0; } @@ -84,16 +82,16 @@ void ia64_teardown_msi_irq(unsigned int irq) destroy_irq(irq); } -static void ia64_ack_msi_irq(unsigned int irq) +static void ia64_ack_msi_irq(struct irq_data *data) { - irq_complete_move(irq); - move_native_irq(irq); + irq_complete_move(data->irq); + irq_move_irq(data); ia64_eoi(); } -static int ia64_msi_retrigger_irq(unsigned int irq) +static int ia64_msi_retrigger_irq(struct irq_data *data) { - unsigned int vector = irq_to_vector(irq); + unsigned int vector = irq_to_vector(data->irq); ia64_resend_irq(vector); return 1; @@ -103,14 +101,14 @@ static int ia64_msi_retrigger_irq(unsigned int irq) * Generic ops used on most IA64 platforms. */ static struct irq_chip ia64_msi_chip = { - .name = "PCI-MSI", - .irq_mask = mask_msi_irq, - .irq_unmask = unmask_msi_irq, - .ack = ia64_ack_msi_irq, + .name = "PCI-MSI", + .irq_mask = mask_msi_irq, + .irq_unmask = unmask_msi_irq, + .irq_ack = ia64_ack_msi_irq, #ifdef CONFIG_SMP - .set_affinity = ia64_set_msi_irq_affinity, + .irq_set_affinity = ia64_set_msi_irq_affinity, #endif - .retrigger = ia64_msi_retrigger_irq, + .irq_retrigger = ia64_msi_retrigger_irq, }; @@ -130,16 +128,15 @@ void arch_teardown_msi_irq(unsigned int irq) return ia64_teardown_msi_irq(irq); } -#ifdef CONFIG_DMAR +#ifdef CONFIG_INTEL_IOMMU #ifdef CONFIG_SMP -static int dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask) +static int dmar_msi_set_affinity(struct irq_data *data, + const struct cpumask *mask, bool force) { + unsigned int irq = data->irq; struct irq_cfg *cfg = irq_cfg + irq; struct msi_msg msg; - int cpu = cpumask_first(mask); - - if (!cpu_online(cpu)) - return -1; + int cpu = cpumask_first_and(mask, cpu_online_mask); if (irq_prepare_move(irq, cpu)) return -1; @@ -152,7 +149,7 @@ static int dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask) msg.address_lo |= MSI_ADDR_DEST_ID_CPU(cpu_physical_id(cpu)); dmar_msi_write(irq, &msg); - cpumask_copy(irq_desc[irq].affinity, mask); + cpumask_copy(data->affinity, mask); return 0; } @@ -162,11 +159,11 @@ static struct irq_chip dmar_msi_type = { .name = "DMAR_MSI", .irq_unmask = dmar_msi_unmask, .irq_mask = dmar_msi_mask, - .ack = ia64_ack_msi_irq, + .irq_ack = ia64_ack_msi_irq, #ifdef CONFIG_SMP - .set_affinity = dmar_msi_set_affinity, + .irq_set_affinity = dmar_msi_set_affinity, #endif - .retrigger = ia64_msi_retrigger_irq, + .irq_retrigger = ia64_msi_retrigger_irq, }; static int @@ -176,7 +173,7 @@ msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_msg *msg) unsigned dest; cpumask_t mask; - cpus_and(mask, irq_to_domain(irq), cpu_online_map); + cpumask_and(&mask, &(irq_to_domain(irq)), cpu_online_mask); dest = cpu_physical_id(first_cpu(mask)); msg->address_hi = 0; @@ -203,9 +200,9 @@ int arch_setup_dmar_msi(unsigned int irq) if (ret < 0) return ret; dmar_msi_write(irq, &msg); - set_irq_chip_and_handler_name(irq, &dmar_msi_type, handle_edge_irq, - "edge"); + irq_set_chip_and_handler_name(irq, &dmar_msi_type, handle_edge_irq, + "edge"); return 0; } -#endif /* CONFIG_DMAR */ +#endif /* CONFIG_INTEL_IOMMU */ diff --git a/arch/ia64/kernel/nr-irqs.c b/arch/ia64/kernel/nr-irqs.c index ee564575148..f6769cd54bd 100644 --- a/arch/ia64/kernel/nr-irqs.c +++ b/arch/ia64/kernel/nr-irqs.c @@ -10,15 +10,11 @@ #include <linux/kbuild.h> #include <linux/threads.h> #include <asm/native/irq.h> -#include <asm/xen/irq.h> void foo(void) { union paravirt_nr_irqs_max { char ia64_native_nr_irqs[IA64_NATIVE_NR_IRQS]; -#ifdef CONFIG_XEN - char xen_nr_irqs[XEN_NR_IRQS]; -#endif }; DEFINE(NR_IRQS, sizeof (union paravirt_nr_irqs_max)); diff --git a/arch/ia64/kernel/numa.c b/arch/ia64/kernel/numa.c index c93420c9740..d288cde9360 100644 --- a/arch/ia64/kernel/numa.c +++ b/arch/ia64/kernel/numa.c @@ -30,7 +30,7 @@ EXPORT_SYMBOL(cpu_to_node_map); cpumask_t node_to_cpu_mask[MAX_NUMNODES] __cacheline_aligned; EXPORT_SYMBOL(node_to_cpu_mask); -void __cpuinit map_cpu_to_node(int cpu, int nid) +void map_cpu_to_node(int cpu, int nid) { int oldnid; if (nid < 0) { /* just initialize by zero */ @@ -51,7 +51,7 @@ void __cpuinit map_cpu_to_node(int cpu, int nid) return; } -void __cpuinit unmap_cpu_from_node(int cpu, int nid) +void unmap_cpu_from_node(int cpu, int nid) { WARN_ON(!cpu_isset(cpu, node_to_cpu_mask[nid])); WARN_ON(cpu_to_node_map[cpu] != nid); diff --git a/arch/ia64/kernel/palinfo.c b/arch/ia64/kernel/palinfo.c index 77597e5ea60..c39c3cd3ac3 100644 --- a/arch/ia64/kernel/palinfo.c +++ b/arch/ia64/kernel/palinfo.c @@ -22,6 +22,7 @@ #include <linux/errno.h> #include <linux/init.h> #include <linux/proc_fs.h> +#include <linux/seq_file.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/efi.h> @@ -41,7 +42,7 @@ MODULE_LICENSE("GPL"); #define PALINFO_VERSION "0.5" -typedef int (*palinfo_func_t)(char*); +typedef int (*palinfo_func_t)(struct seq_file *); typedef struct { const char *name; /* name of the proc entry */ @@ -54,7 +55,7 @@ typedef struct { * A bunch of string array to get pretty printing */ -static char *cache_types[] = { +static const char *cache_types[] = { "", /* not used */ "Instruction", "Data", @@ -122,19 +123,16 @@ static const char *mem_attrib[]={ * - a pointer to the end of the buffer * */ -static char * -bitvector_process(char *p, u64 vector) +static void bitvector_process(struct seq_file *m, u64 vector) { int i,j; - const char *units[]={ "", "K", "M", "G", "T" }; + static const char *units[]={ "", "K", "M", "G", "T" }; for (i=0, j=0; i < 64; i++ , j=i/10) { - if (vector & 0x1) { - p += sprintf(p, "%d%s ", 1 << (i-j*10), units[j]); - } + if (vector & 0x1) + seq_printf(m, "%d%s ", 1 << (i-j*10), units[j]); vector >>= 1; } - return p; } /* @@ -149,8 +147,7 @@ bitvector_process(char *p, u64 vector) * - a pointer to the end of the buffer * */ -static char * -bitregister_process(char *p, u64 *reg_info, int max) +static void bitregister_process(struct seq_file *m, u64 *reg_info, int max) { int i, begin, skip = 0; u64 value = reg_info[0]; @@ -163,9 +160,9 @@ bitregister_process(char *p, u64 *reg_info, int max) if ((value & 0x1) == 0 && skip == 0) { if (begin <= i - 2) - p += sprintf(p, "%d-%d ", begin, i-1); + seq_printf(m, "%d-%d ", begin, i-1); else - p += sprintf(p, "%d ", i-1); + seq_printf(m, "%d ", i-1); skip = 1; begin = -1; } else if ((value & 0x1) && skip == 1) { @@ -176,19 +173,15 @@ bitregister_process(char *p, u64 *reg_info, int max) } if (begin > -1) { if (begin < 127) - p += sprintf(p, "%d-127", begin); + seq_printf(m, "%d-127", begin); else - p += sprintf(p, "127"); + seq_puts(m, "127"); } - - return p; } -static int -power_info(char *page) +static int power_info(struct seq_file *m) { s64 status; - char *p = page; u64 halt_info_buffer[8]; pal_power_mgmt_info_u_t *halt_info =(pal_power_mgmt_info_u_t *)halt_info_buffer; int i; @@ -198,26 +191,25 @@ power_info(char *page) for (i=0; i < 8 ; i++ ) { if (halt_info[i].pal_power_mgmt_info_s.im == 1) { - p += sprintf(p, "Power level %d:\n" - "\tentry_latency : %d cycles\n" - "\texit_latency : %d cycles\n" - "\tpower consumption : %d mW\n" - "\tCache+TLB coherency : %s\n", i, - halt_info[i].pal_power_mgmt_info_s.entry_latency, - halt_info[i].pal_power_mgmt_info_s.exit_latency, - halt_info[i].pal_power_mgmt_info_s.power_consumption, - halt_info[i].pal_power_mgmt_info_s.co ? "Yes" : "No"); + seq_printf(m, + "Power level %d:\n" + "\tentry_latency : %d cycles\n" + "\texit_latency : %d cycles\n" + "\tpower consumption : %d mW\n" + "\tCache+TLB coherency : %s\n", i, + halt_info[i].pal_power_mgmt_info_s.entry_latency, + halt_info[i].pal_power_mgmt_info_s.exit_latency, + halt_info[i].pal_power_mgmt_info_s.power_consumption, + halt_info[i].pal_power_mgmt_info_s.co ? "Yes" : "No"); } else { - p += sprintf(p,"Power level %d: not implemented\n",i); + seq_printf(m,"Power level %d: not implemented\n", i); } } - return p - page; + return 0; } -static int -cache_info(char *page) +static int cache_info(struct seq_file *m) { - char *p = page; unsigned long i, levels, unique_caches; pal_cache_config_info_t cci; int j, k; @@ -228,73 +220,74 @@ cache_info(char *page) return 0; } - p += sprintf(p, "Cache levels : %ld\nUnique caches : %ld\n\n", levels, unique_caches); + seq_printf(m, "Cache levels : %ld\nUnique caches : %ld\n\n", + levels, unique_caches); for (i=0; i < levels; i++) { - for (j=2; j >0 ; j--) { - /* even without unification some level may not be present */ - if ((status=ia64_pal_cache_config_info(i,j, &cci)) != 0) { + if ((status=ia64_pal_cache_config_info(i,j, &cci)) != 0) continue; - } - p += sprintf(p, - "%s Cache level %lu:\n" - "\tSize : %u bytes\n" - "\tAttributes : ", - cache_types[j+cci.pcci_unified], i+1, - cci.pcci_cache_size); - - if (cci.pcci_unified) p += sprintf(p, "Unified "); - - p += sprintf(p, "%s\n", cache_mattrib[cci.pcci_cache_attr]); - - p += sprintf(p, - "\tAssociativity : %d\n" - "\tLine size : %d bytes\n" - "\tStride : %d bytes\n", - cci.pcci_assoc, 1<<cci.pcci_line_size, 1<<cci.pcci_stride); + + seq_printf(m, + "%s Cache level %lu:\n" + "\tSize : %u bytes\n" + "\tAttributes : ", + cache_types[j+cci.pcci_unified], i+1, + cci.pcci_cache_size); + + if (cci.pcci_unified) + seq_puts(m, "Unified "); + + seq_printf(m, "%s\n", cache_mattrib[cci.pcci_cache_attr]); + + seq_printf(m, + "\tAssociativity : %d\n" + "\tLine size : %d bytes\n" + "\tStride : %d bytes\n", + cci.pcci_assoc, + 1<<cci.pcci_line_size, + 1<<cci.pcci_stride); if (j == 1) - p += sprintf(p, "\tStore latency : N/A\n"); + seq_puts(m, "\tStore latency : N/A\n"); else - p += sprintf(p, "\tStore latency : %d cycle(s)\n", - cci.pcci_st_latency); + seq_printf(m, "\tStore latency : %d cycle(s)\n", + cci.pcci_st_latency); - p += sprintf(p, - "\tLoad latency : %d cycle(s)\n" - "\tStore hints : ", cci.pcci_ld_latency); + seq_printf(m, + "\tLoad latency : %d cycle(s)\n" + "\tStore hints : ", cci.pcci_ld_latency); for(k=0; k < 8; k++ ) { if ( cci.pcci_st_hints & 0x1) - p += sprintf(p, "[%s]", cache_st_hints[k]); + seq_printf(m, "[%s]", cache_st_hints[k]); cci.pcci_st_hints >>=1; } - p += sprintf(p, "\n\tLoad hints : "); + seq_puts(m, "\n\tLoad hints : "); for(k=0; k < 8; k++ ) { if (cci.pcci_ld_hints & 0x1) - p += sprintf(p, "[%s]", cache_ld_hints[k]); + seq_printf(m, "[%s]", cache_ld_hints[k]); cci.pcci_ld_hints >>=1; } - p += sprintf(p, - "\n\tAlias boundary : %d byte(s)\n" - "\tTag LSB : %d\n" - "\tTag MSB : %d\n", - 1<<cci.pcci_alias_boundary, cci.pcci_tag_lsb, - cci.pcci_tag_msb); + seq_printf(m, + "\n\tAlias boundary : %d byte(s)\n" + "\tTag LSB : %d\n" + "\tTag MSB : %d\n", + 1<<cci.pcci_alias_boundary, cci.pcci_tag_lsb, + cci.pcci_tag_msb); /* when unified, data(j=2) is enough */ - if (cci.pcci_unified) break; + if (cci.pcci_unified) + break; } } - return p - page; + return 0; } -static int -vm_info(char *page) +static int vm_info(struct seq_file *m) { - char *p = page; u64 tr_pages =0, vw_pages=0, tc_pages; u64 attrib; pal_vm_info_1_u_t vm_info_1; @@ -309,7 +302,7 @@ vm_info(char *page) printk(KERN_ERR "ia64_pal_vm_summary=%ld\n", status); } else { - p += sprintf(p, + seq_printf(m, "Physical Address Space : %d bits\n" "Virtual Address Space : %d bits\n" "Protection Key Registers(PKR) : %d\n" @@ -324,49 +317,49 @@ vm_info(char *page) vm_info_1.pal_vm_info_1_s.hash_tag_id, vm_info_2.pal_vm_info_2_s.rid_size); if (vm_info_2.pal_vm_info_2_s.max_purges == PAL_MAX_PURGES) - p += sprintf(p, "unlimited\n"); + seq_puts(m, "unlimited\n"); else - p += sprintf(p, "%d\n", + seq_printf(m, "%d\n", vm_info_2.pal_vm_info_2_s.max_purges ? vm_info_2.pal_vm_info_2_s.max_purges : 1); } if (ia64_pal_mem_attrib(&attrib) == 0) { - p += sprintf(p, "Supported memory attributes : "); + seq_puts(m, "Supported memory attributes : "); sep = ""; for (i = 0; i < 8; i++) { if (attrib & (1 << i)) { - p += sprintf(p, "%s%s", sep, mem_attrib[i]); + seq_printf(m, "%s%s", sep, mem_attrib[i]); sep = ", "; } } - p += sprintf(p, "\n"); + seq_putc(m, '\n'); } if ((status = ia64_pal_vm_page_size(&tr_pages, &vw_pages)) !=0) { printk(KERN_ERR "ia64_pal_vm_page_size=%ld\n", status); } else { - p += sprintf(p, - "\nTLB walker : %simplemented\n" - "Number of DTR : %d\n" - "Number of ITR : %d\n" - "TLB insertable page sizes : ", - vm_info_1.pal_vm_info_1_s.vw ? "" : "not ", - vm_info_1.pal_vm_info_1_s.max_dtr_entry+1, - vm_info_1.pal_vm_info_1_s.max_itr_entry+1); + seq_printf(m, + "\nTLB walker : %simplemented\n" + "Number of DTR : %d\n" + "Number of ITR : %d\n" + "TLB insertable page sizes : ", + vm_info_1.pal_vm_info_1_s.vw ? "" : "not ", + vm_info_1.pal_vm_info_1_s.max_dtr_entry+1, + vm_info_1.pal_vm_info_1_s.max_itr_entry+1); + bitvector_process(m, tr_pages); - p = bitvector_process(p, tr_pages); + seq_puts(m, "\nTLB purgeable page sizes : "); - p += sprintf(p, "\nTLB purgeable page sizes : "); - - p = bitvector_process(p, vw_pages); + bitvector_process(m, vw_pages); } - if ((status=ia64_get_ptce(&ptce)) != 0) { + + if ((status = ia64_get_ptce(&ptce)) != 0) { printk(KERN_ERR "ia64_get_ptce=%ld\n", status); } else { - p += sprintf(p, + seq_printf(m, "\nPurge base address : 0x%016lx\n" "Purge outer loop count : %d\n" "Purge inner loop count : %d\n" @@ -375,7 +368,7 @@ vm_info(char *page) ptce.base, ptce.count[0], ptce.count[1], ptce.stride[0], ptce.stride[1]); - p += sprintf(p, + seq_printf(m, "TC Levels : %d\n" "Unique TC(s) : %d\n", vm_info_1.pal_vm_info_1_s.num_tc_levels, @@ -385,13 +378,11 @@ vm_info(char *page) for (j=2; j>0 ; j--) { tc_pages = 0; /* just in case */ - /* even without unification, some levels may not be present */ - if ((status=ia64_pal_vm_info(i,j, &tc_info, &tc_pages)) != 0) { + if ((status=ia64_pal_vm_info(i,j, &tc_info, &tc_pages)) != 0) continue; - } - p += sprintf(p, + seq_printf(m, "\n%s Translation Cache Level %d:\n" "\tHash sets : %d\n" "\tAssociativity : %d\n" @@ -403,15 +394,15 @@ vm_info(char *page) tc_info.tc_num_entries); if (tc_info.tc_pf) - p += sprintf(p, "PreferredPageSizeOptimized "); + seq_puts(m, "PreferredPageSizeOptimized "); if (tc_info.tc_unified) - p += sprintf(p, "Unified "); + seq_puts(m, "Unified "); if (tc_info.tc_reduce_tr) - p += sprintf(p, "TCReduction"); + seq_puts(m, "TCReduction"); - p += sprintf(p, "\n\tSupported page sizes: "); + seq_puts(m, "\n\tSupported page sizes: "); - p = bitvector_process(p, tc_pages); + bitvector_process(m, tc_pages); /* when unified date (j=2) is enough */ if (tc_info.tc_unified) @@ -419,16 +410,14 @@ vm_info(char *page) } } } - p += sprintf(p, "\n"); - return p - page; + seq_putc(m, '\n'); + return 0; } -static int -register_info(char *page) +static int register_info(struct seq_file *m) { - char *p = page; u64 reg_info[2]; u64 info; unsigned long phys_stacked; @@ -442,35 +431,31 @@ register_info(char *page) }; for(info=0; info < 4; info++) { - - if (ia64_pal_register_info(info, ®_info[0], ®_info[1]) != 0) return 0; - - p += sprintf(p, "%-32s : ", info_type[info]); - - p = bitregister_process(p, reg_info, 128); - - p += sprintf(p, "\n"); + if (ia64_pal_register_info(info, ®_info[0], ®_info[1]) != 0) + return 0; + seq_printf(m, "%-32s : ", info_type[info]); + bitregister_process(m, reg_info, 128); + seq_putc(m, '\n'); } - if (ia64_pal_rse_info(&phys_stacked, &hints) == 0) { + if (ia64_pal_rse_info(&phys_stacked, &hints) == 0) + seq_printf(m, + "RSE stacked physical registers : %ld\n" + "RSE load/store hints : %ld (%s)\n", + phys_stacked, hints.ph_data, + hints.ph_data < RSE_HINTS_COUNT ? rse_hints[hints.ph_data]: "(??)"); - p += sprintf(p, - "RSE stacked physical registers : %ld\n" - "RSE load/store hints : %ld (%s)\n", - phys_stacked, hints.ph_data, - hints.ph_data < RSE_HINTS_COUNT ? rse_hints[hints.ph_data]: "(??)"); - } if (ia64_pal_debug_info(&iregs, &dregs)) return 0; - p += sprintf(p, - "Instruction debug register pairs : %ld\n" - "Data debug register pairs : %ld\n", iregs, dregs); + seq_printf(m, + "Instruction debug register pairs : %ld\n" + "Data debug register pairs : %ld\n", iregs, dregs); - return p - page; + return 0; } -static char *proc_features_0[]={ /* Feature set 0 */ +static const char *const proc_features_0[]={ /* Feature set 0 */ NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL, NULL,NULL,NULL,NULL,NULL,NULL,NULL, NULL,NULL, NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL, @@ -502,7 +487,7 @@ static char *proc_features_0[]={ /* Feature set 0 */ "Enable BERR promotion" }; -static char *proc_features_16[]={ /* Feature set 16 */ +static const char *const proc_features_16[]={ /* Feature set 16 */ "Disable ETM", "Enable ETM", "Enable MCA on half-way timer", @@ -522,7 +507,7 @@ static char *proc_features_16[]={ /* Feature set 16 */ NULL, NULL, NULL, NULL, NULL }; -static char **proc_features[]={ +static const char *const *const proc_features[]={ proc_features_0, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, @@ -530,11 +515,10 @@ static char **proc_features[]={ NULL, NULL, NULL, NULL, }; -static char * feature_set_info(char *page, u64 avail, u64 status, u64 control, - unsigned long set) +static void feature_set_info(struct seq_file *m, u64 avail, u64 status, u64 control, + unsigned long set) { - char *p = page; - char **vf, **v; + const char *const *vf, *const *v; int i; vf = v = proc_features[set]; @@ -547,13 +531,13 @@ static char * feature_set_info(char *page, u64 avail, u64 status, u64 control, if (vf) v = vf + i; if ( v && *v ) { - p += sprintf(p, "%-40s : %s %s\n", *v, + seq_printf(m, "%-40s : %s %s\n", *v, avail & 0x1 ? (status & 0x1 ? - "On " : "Off"): "", + "On " : "Off"): "", avail & 0x1 ? (control & 0x1 ? "Ctrl" : "NoCtrl"): ""); } else { - p += sprintf(p, "Feature set %2ld bit %2d\t\t\t" + seq_printf(m, "Feature set %2ld bit %2d\t\t\t" " : %s %s\n", set, i, avail & 0x1 ? (status & 0x1 ? @@ -562,36 +546,32 @@ static char * feature_set_info(char *page, u64 avail, u64 status, u64 control, "Ctrl" : "NoCtrl"): ""); } } - return p; } -static int -processor_info(char *page) +static int processor_info(struct seq_file *m) { - char *p = page; u64 avail=1, status=1, control=1, feature_set=0; s64 ret; do { ret = ia64_pal_proc_get_features(&avail, &status, &control, feature_set); - if (ret < 0) { - return p - page; - } + if (ret < 0) + return 0; + if (ret == 1) { feature_set++; continue; } - p = feature_set_info(p, avail, status, control, feature_set); - + feature_set_info(m, avail, status, control, feature_set); feature_set++; } while(1); - return p - page; + return 0; } -static const char *bus_features[]={ +static const char *const bus_features[]={ NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL, NULL,NULL,NULL,NULL,NULL,NULL,NULL, NULL,NULL, NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL, @@ -617,125 +597,118 @@ static const char *bus_features[]={ }; -static int -bus_info(char *page) +static int bus_info(struct seq_file *m) { - char *p = page; - const char **v = bus_features; + const char *const *v = bus_features; pal_bus_features_u_t av, st, ct; u64 avail, status, control; int i; s64 ret; - if ((ret=ia64_pal_bus_get_features(&av, &st, &ct)) != 0) return 0; + if ((ret=ia64_pal_bus_get_features(&av, &st, &ct)) != 0) + return 0; avail = av.pal_bus_features_val; status = st.pal_bus_features_val; control = ct.pal_bus_features_val; for(i=0; i < 64; i++, v++, avail >>=1, status >>=1, control >>=1) { - if ( ! *v ) continue; - p += sprintf(p, "%-48s : %s%s %s\n", *v, - avail & 0x1 ? "" : "NotImpl", - avail & 0x1 ? (status & 0x1 ? "On" : "Off"): "", - avail & 0x1 ? (control & 0x1 ? "Ctrl" : "NoCtrl"): ""); + if ( ! *v ) + continue; + seq_printf(m, "%-48s : %s%s %s\n", *v, + avail & 0x1 ? "" : "NotImpl", + avail & 0x1 ? (status & 0x1 ? "On" : "Off"): "", + avail & 0x1 ? (control & 0x1 ? "Ctrl" : "NoCtrl"): ""); } - return p - page; + return 0; } -static int -version_info(char *page) +static int version_info(struct seq_file *m) { pal_version_u_t min_ver, cur_ver; - char *p = page; if (ia64_pal_version(&min_ver, &cur_ver) != 0) return 0; - p += sprintf(p, - "PAL_vendor : 0x%02x (min=0x%02x)\n" - "PAL_A : %02x.%02x (min=%02x.%02x)\n" - "PAL_B : %02x.%02x (min=%02x.%02x)\n", - cur_ver.pal_version_s.pv_pal_vendor, - min_ver.pal_version_s.pv_pal_vendor, - cur_ver.pal_version_s.pv_pal_a_model, - cur_ver.pal_version_s.pv_pal_a_rev, - min_ver.pal_version_s.pv_pal_a_model, - min_ver.pal_version_s.pv_pal_a_rev, - cur_ver.pal_version_s.pv_pal_b_model, - cur_ver.pal_version_s.pv_pal_b_rev, - min_ver.pal_version_s.pv_pal_b_model, - min_ver.pal_version_s.pv_pal_b_rev); - return p - page; + seq_printf(m, + "PAL_vendor : 0x%02x (min=0x%02x)\n" + "PAL_A : %02x.%02x (min=%02x.%02x)\n" + "PAL_B : %02x.%02x (min=%02x.%02x)\n", + cur_ver.pal_version_s.pv_pal_vendor, + min_ver.pal_version_s.pv_pal_vendor, + cur_ver.pal_version_s.pv_pal_a_model, + cur_ver.pal_version_s.pv_pal_a_rev, + min_ver.pal_version_s.pv_pal_a_model, + min_ver.pal_version_s.pv_pal_a_rev, + cur_ver.pal_version_s.pv_pal_b_model, + cur_ver.pal_version_s.pv_pal_b_rev, + min_ver.pal_version_s.pv_pal_b_model, + min_ver.pal_version_s.pv_pal_b_rev); + return 0; } -static int -perfmon_info(char *page) +static int perfmon_info(struct seq_file *m) { - char *p = page; u64 pm_buffer[16]; pal_perf_mon_info_u_t pm_info; - if (ia64_pal_perf_mon_info(pm_buffer, &pm_info) != 0) return 0; - - p += sprintf(p, - "PMC/PMD pairs : %d\n" - "Counter width : %d bits\n" - "Cycle event number : %d\n" - "Retired event number : %d\n" - "Implemented PMC : ", - pm_info.pal_perf_mon_info_s.generic, pm_info.pal_perf_mon_info_s.width, - pm_info.pal_perf_mon_info_s.cycles, pm_info.pal_perf_mon_info_s.retired); + if (ia64_pal_perf_mon_info(pm_buffer, &pm_info) != 0) + return 0; - p = bitregister_process(p, pm_buffer, 256); - p += sprintf(p, "\nImplemented PMD : "); - p = bitregister_process(p, pm_buffer+4, 256); - p += sprintf(p, "\nCycles count capable : "); - p = bitregister_process(p, pm_buffer+8, 256); - p += sprintf(p, "\nRetired bundles count capable : "); + seq_printf(m, + "PMC/PMD pairs : %d\n" + "Counter width : %d bits\n" + "Cycle event number : %d\n" + "Retired event number : %d\n" + "Implemented PMC : ", + pm_info.pal_perf_mon_info_s.generic, + pm_info.pal_perf_mon_info_s.width, + pm_info.pal_perf_mon_info_s.cycles, + pm_info.pal_perf_mon_info_s.retired); + + bitregister_process(m, pm_buffer, 256); + seq_puts(m, "\nImplemented PMD : "); + bitregister_process(m, pm_buffer+4, 256); + seq_puts(m, "\nCycles count capable : "); + bitregister_process(m, pm_buffer+8, 256); + seq_puts(m, "\nRetired bundles count capable : "); #ifdef CONFIG_ITANIUM /* * PAL_PERF_MON_INFO reports that only PMC4 can be used to count CPU_CYCLES * which is wrong, both PMC4 and PMD5 support it. */ - if (pm_buffer[12] == 0x10) pm_buffer[12]=0x30; + if (pm_buffer[12] == 0x10) + pm_buffer[12]=0x30; #endif - p = bitregister_process(p, pm_buffer+12, 256); - - p += sprintf(p, "\n"); - - return p - page; + bitregister_process(m, pm_buffer+12, 256); + seq_putc(m, '\n'); + return 0; } -static int -frequency_info(char *page) +static int frequency_info(struct seq_file *m) { - char *p = page; struct pal_freq_ratio proc, itc, bus; unsigned long base; if (ia64_pal_freq_base(&base) == -1) - p += sprintf(p, "Output clock : not implemented\n"); + seq_puts(m, "Output clock : not implemented\n"); else - p += sprintf(p, "Output clock : %ld ticks/s\n", base); + seq_printf(m, "Output clock : %ld ticks/s\n", base); if (ia64_pal_freq_ratios(&proc, &bus, &itc) != 0) return 0; - p += sprintf(p, + seq_printf(m, "Processor/Clock ratio : %d/%d\n" "Bus/Clock ratio : %d/%d\n" "ITC/Clock ratio : %d/%d\n", proc.num, proc.den, bus.num, bus.den, itc.num, itc.den); - - return p - page; + return 0; } -static int -tr_info(char *page) +static int tr_info(struct seq_file *m) { - char *p = page; long status; pal_tr_valid_u_t tr_valid; u64 tr_buffer[4]; @@ -794,39 +767,40 @@ tr_info(char *page) ifa_reg = (struct ifa_reg *)&tr_buffer[2]; - if (ifa_reg->valid == 0) continue; + if (ifa_reg->valid == 0) + continue; gr_reg = (struct gr_reg *)tr_buffer; itir_reg = (struct itir_reg *)&tr_buffer[1]; rid_reg = (struct rid_reg *)&tr_buffer[3]; pgm = -1 << (itir_reg->ps - 12); - p += sprintf(p, - "%cTR%lu: av=%d pv=%d dv=%d mv=%d\n" - "\tppn : 0x%lx\n" - "\tvpn : 0x%lx\n" - "\tps : ", - "ID"[i], j, - tr_valid.pal_tr_valid_s.access_rights_valid, - tr_valid.pal_tr_valid_s.priv_level_valid, - tr_valid.pal_tr_valid_s.dirty_bit_valid, - tr_valid.pal_tr_valid_s.mem_attr_valid, - (gr_reg->ppn & pgm)<< 12, (ifa_reg->vpn & pgm)<< 12); - - p = bitvector_process(p, 1<< itir_reg->ps); - - p += sprintf(p, - "\n\tpl : %d\n" - "\tar : %d\n" - "\trid : %x\n" - "\tp : %d\n" - "\tma : %d\n" - "\td : %d\n", - gr_reg->pl, gr_reg->ar, rid_reg->rid, gr_reg->p, gr_reg->ma, - gr_reg->d); + seq_printf(m, + "%cTR%lu: av=%d pv=%d dv=%d mv=%d\n" + "\tppn : 0x%lx\n" + "\tvpn : 0x%lx\n" + "\tps : ", + "ID"[i], j, + tr_valid.pal_tr_valid_s.access_rights_valid, + tr_valid.pal_tr_valid_s.priv_level_valid, + tr_valid.pal_tr_valid_s.dirty_bit_valid, + tr_valid.pal_tr_valid_s.mem_attr_valid, + (gr_reg->ppn & pgm)<< 12, (ifa_reg->vpn & pgm)<< 12); + + bitvector_process(m, 1<< itir_reg->ps); + + seq_printf(m, + "\n\tpl : %d\n" + "\tar : %d\n" + "\trid : %x\n" + "\tp : %d\n" + "\tma : %d\n" + "\td : %d\n", + gr_reg->pl, gr_reg->ar, rid_reg->rid, gr_reg->p, gr_reg->ma, + gr_reg->d); } } - return p - page; + return 0; } @@ -834,7 +808,7 @@ tr_info(char *page) /* * List {name,function} pairs for every entry in /proc/palinfo/cpu* */ -static palinfo_entry_t palinfo_entries[]={ +static const palinfo_entry_t palinfo_entries[]={ { "version_info", version_info, }, { "vm_info", vm_info, }, { "cache_info", cache_info, }, @@ -849,17 +823,6 @@ static palinfo_entry_t palinfo_entries[]={ #define NR_PALINFO_ENTRIES (int) ARRAY_SIZE(palinfo_entries) -/* - * this array is used to keep track of the proc entries we create. This is - * required in the module mode when we need to remove all entries. The procfs code - * does not do recursion of deletion - * - * Notes: - * - +1 accounts for the cpuN directory entry in /proc/pal - */ -#define NR_PALINFO_PROC_ENTRIES (NR_CPUS*(NR_PALINFO_ENTRIES+1)) - -static struct proc_dir_entry *palinfo_proc_entries[NR_PALINFO_PROC_ENTRIES]; static struct proc_dir_entry *palinfo_dir; /* @@ -887,7 +850,7 @@ typedef union { */ typedef struct { palinfo_func_t func; /* pointer to function to call */ - char *page; /* buffer to store results */ + struct seq_file *m; /* buffer to store results */ int ret; /* return value from call */ } palinfo_smp_data_t; @@ -900,7 +863,7 @@ static void palinfo_smp_call(void *info) { palinfo_smp_data_t *data = (palinfo_smp_data_t *)info; - data->ret = (*data->func)(data->page); + data->ret = (*data->func)(data->m); } /* @@ -910,13 +873,13 @@ palinfo_smp_call(void *info) * otherwise how many bytes in the "page" buffer were written */ static -int palinfo_handle_smp(pal_func_cpu_u_t *f, char *page) +int palinfo_handle_smp(struct seq_file *m, pal_func_cpu_u_t *f) { palinfo_smp_data_t ptr; int ret; ptr.func = palinfo_entries[f->func_id].proc_read; - ptr.page = page; + ptr.m = m; ptr.ret = 0; /* just in case */ @@ -930,7 +893,7 @@ int palinfo_handle_smp(pal_func_cpu_u_t *f, char *page) } #else /* ! CONFIG_SMP */ static -int palinfo_handle_smp(pal_func_cpu_u_t *f, char *page) +int palinfo_handle_smp(struct seq_file *m, pal_func_cpu_u_t *f) { printk(KERN_ERR "palinfo: should not be called with non SMP kernel\n"); return 0; @@ -940,94 +903,66 @@ int palinfo_handle_smp(pal_func_cpu_u_t *f, char *page) /* * Entry point routine: all calls go through this function */ -static int -palinfo_read_entry(char *page, char **start, off_t off, int count, int *eof, void *data) +static int proc_palinfo_show(struct seq_file *m, void *v) { - int len=0; - pal_func_cpu_u_t *f = (pal_func_cpu_u_t *)&data; + pal_func_cpu_u_t *f = (pal_func_cpu_u_t *)&m->private; /* * in SMP mode, we may need to call another CPU to get correct * information. PAL, by definition, is processor specific */ if (f->req_cpu == get_cpu()) - len = (*palinfo_entries[f->func_id].proc_read)(page); + (*palinfo_entries[f->func_id].proc_read)(m); else - len = palinfo_handle_smp(f, page); + palinfo_handle_smp(m, f); put_cpu(); + return 0; +} - if (len <= off+count) *eof = 1; - - *start = page + off; - len -= off; - - if (len>count) len = count; - if (len<0) len = 0; - - return len; +static int proc_palinfo_open(struct inode *inode, struct file *file) +{ + return single_open(file, proc_palinfo_show, PDE_DATA(inode)); } -static void __cpuinit +static const struct file_operations proc_palinfo_fops = { + .open = proc_palinfo_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static void create_palinfo_proc_entries(unsigned int cpu) { -# define CPUSTR "cpu%d" - pal_func_cpu_u_t f; - struct proc_dir_entry **pdir; struct proc_dir_entry *cpu_dir; int j; - char cpustr[sizeof(CPUSTR)]; - - - /* - * we keep track of created entries in a depth-first order for - * cleanup purposes. Each entry is stored into palinfo_proc_entries - */ - sprintf(cpustr,CPUSTR, cpu); + char cpustr[3+4+1]; /* cpu numbers are up to 4095 on itanic */ + sprintf(cpustr, "cpu%d", cpu); cpu_dir = proc_mkdir(cpustr, palinfo_dir); + if (!cpu_dir) + return; f.req_cpu = cpu; - /* - * Compute the location to store per cpu entries - * We dont store the top level entry in this list, but - * remove it finally after removing all cpu entries. - */ - pdir = &palinfo_proc_entries[cpu*(NR_PALINFO_ENTRIES+1)]; - *pdir++ = cpu_dir; for (j=0; j < NR_PALINFO_ENTRIES; j++) { f.func_id = j; - *pdir = create_proc_read_entry( - palinfo_entries[j].name, 0, cpu_dir, - palinfo_read_entry, (void *)f.value); - pdir++; + proc_create_data(palinfo_entries[j].name, 0, cpu_dir, + &proc_palinfo_fops, (void *)f.value); } } static void remove_palinfo_proc_entries(unsigned int hcpu) { - int j; - struct proc_dir_entry *cpu_dir, **pdir; - - pdir = &palinfo_proc_entries[hcpu*(NR_PALINFO_ENTRIES+1)]; - cpu_dir = *pdir; - *pdir++=NULL; - for (j=0; j < (NR_PALINFO_ENTRIES); j++) { - if ((*pdir)) { - remove_proc_entry ((*pdir)->name, cpu_dir); - *pdir ++= NULL; - } - } - - if (cpu_dir) { - remove_proc_entry(cpu_dir->name, palinfo_dir); - } + char cpustr[3+4+1]; /* cpu numbers are up to 4095 on itanic */ + sprintf(cpustr, "cpu%d", hcpu); + remove_proc_subtree(cpustr, palinfo_dir); } -static int __cpuinit palinfo_cpu_callback(struct notifier_block *nfb, +static int palinfo_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { unsigned int hotcpu = (unsigned long)hcpu; @@ -1058,6 +993,10 @@ palinfo_init(void) printk(KERN_INFO "PAL Information Facility v%s\n", PALINFO_VERSION); palinfo_dir = proc_mkdir("pal", NULL); + if (!palinfo_dir) + return -ENOMEM; + + cpu_notifier_register_begin(); /* Create palinfo dirs in /proc for all online cpus */ for_each_online_cpu(i) { @@ -1065,7 +1004,9 @@ palinfo_init(void) } /* Register for future delivery via notify registration */ - register_hotcpu_notifier(&palinfo_cpu_notifier); + __register_hotcpu_notifier(&palinfo_cpu_notifier); + + cpu_notifier_register_done(); return 0; } @@ -1073,22 +1014,8 @@ palinfo_init(void) static void __exit palinfo_exit(void) { - int i = 0; - - /* remove all nodes: depth first pass. Could optimize this */ - for_each_online_cpu(i) { - remove_palinfo_proc_entries(i); - } - - /* - * Remove the top level entry finally - */ - remove_proc_entry(palinfo_dir->name, NULL); - - /* - * Unregister from cpu notifier callbacks - */ unregister_hotcpu_notifier(&palinfo_cpu_notifier); + remove_proc_subtree("pal", NULL); } module_init(palinfo_init); diff --git a/arch/ia64/kernel/paravirt.c b/arch/ia64/kernel/paravirt.c index a21d7bb9c69..1b22f6de293 100644 --- a/arch/ia64/kernel/paravirt.c +++ b/arch/ia64/kernel/paravirt.c @@ -634,6 +634,8 @@ struct pv_irq_ops pv_irq_ops = { * pv_time_ops * time operations */ +struct static_key paravirt_steal_enabled; +struct static_key paravirt_steal_rq_enabled; static int ia64_native_do_steal_accounting(unsigned long *new_itm) diff --git a/arch/ia64/kernel/paravirt_inst.h b/arch/ia64/kernel/paravirt_inst.h index 64d6d810c64..1ad7512b5f6 100644 --- a/arch/ia64/kernel/paravirt_inst.h +++ b/arch/ia64/kernel/paravirt_inst.h @@ -22,9 +22,6 @@ #ifdef __IA64_ASM_PARAVIRTUALIZED_PVCHECK #include <asm/native/pvchk_inst.h> -#elif defined(__IA64_ASM_PARAVIRTUALIZED_XEN) -#include <asm/xen/inst.h> -#include <asm/xen/minstate.h> #else #include <asm/native/inst.h> #endif diff --git a/arch/ia64/kernel/paravirt_patchlist.h b/arch/ia64/kernel/paravirt_patchlist.h index 0684aa6c650..67cffc3643a 100644 --- a/arch/ia64/kernel/paravirt_patchlist.h +++ b/arch/ia64/kernel/paravirt_patchlist.h @@ -20,9 +20,5 @@ * */ -#if defined(__IA64_GATE_PARAVIRTUALIZED_XEN) -#include <asm/xen/patchlist.h> -#else #include <asm/native/patchlist.h> -#endif diff --git a/arch/ia64/kernel/patch.c b/arch/ia64/kernel/patch.c index 68a1311db80..1cf09179371 100644 --- a/arch/ia64/kernel/patch.c +++ b/arch/ia64/kernel/patch.c @@ -11,7 +11,6 @@ #include <asm/patch.h> #include <asm/processor.h> #include <asm/sections.h> -#include <asm/system.h> #include <asm/unistd.h> /* diff --git a/arch/ia64/kernel/pci-dma.c b/arch/ia64/kernel/pci-dma.c index f6b1ff0aea7..992c1098c52 100644 --- a/arch/ia64/kernel/pci-dma.c +++ b/arch/ia64/kernel/pci-dma.c @@ -12,9 +12,8 @@ #include <asm/machvec.h> #include <linux/dma-mapping.h> -#include <asm/system.h> -#ifdef CONFIG_DMAR +#ifdef CONFIG_INTEL_IOMMU #include <linux/kernel.h> @@ -34,15 +33,6 @@ int force_iommu __read_mostly; int iommu_pass_through; -/* Dummy device used for NULL arguments (normally ISA). Better would - be probably a smaller DMA mask, but this is bug-to-bug compatible - to i386. */ -struct device fallback_dev = { - .init_name = "fallback device", - .coherent_dma_mask = DMA_BIT_MASK(32), - .dma_mask = &fallback_dev.coherent_dma_mask, -}; - extern struct dma_map_ops intel_dma_ops; static int __init pci_iommu_init(void) diff --git a/arch/ia64/kernel/pci-swiotlb.c b/arch/ia64/kernel/pci-swiotlb.c index d9485d952ed..939260aeac9 100644 --- a/arch/ia64/kernel/pci-swiotlb.c +++ b/arch/ia64/kernel/pci-swiotlb.c @@ -15,16 +15,24 @@ int swiotlb __read_mostly; EXPORT_SYMBOL(swiotlb); static void *ia64_swiotlb_alloc_coherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp) + dma_addr_t *dma_handle, gfp_t gfp, + struct dma_attrs *attrs) { if (dev->coherent_dma_mask != DMA_BIT_MASK(64)) gfp |= GFP_DMA; return swiotlb_alloc_coherent(dev, size, dma_handle, gfp); } +static void ia64_swiotlb_free_coherent(struct device *dev, size_t size, + void *vaddr, dma_addr_t dma_addr, + struct dma_attrs *attrs) +{ + swiotlb_free_coherent(dev, size, vaddr, dma_addr); +} + struct dma_map_ops swiotlb_dma_ops = { - .alloc_coherent = ia64_swiotlb_alloc_coherent, - .free_coherent = swiotlb_free_coherent, + .alloc = ia64_swiotlb_alloc_coherent, + .free = ia64_swiotlb_free_coherent, .map_page = swiotlb_map_page, .unmap_page = swiotlb_unmap_page, .map_sg = swiotlb_map_sg_attrs, diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c index 39e534f5a3b..5845ffea67c 100644 --- a/arch/ia64/kernel/perfmon.c +++ b/arch/ia64/kernel/perfmon.c @@ -42,6 +42,7 @@ #include <linux/completion.h> #include <linux/tracehook.h> #include <linux/slab.h> +#include <linux/cpu.h> #include <asm/errno.h> #include <asm/intrinsics.h> @@ -49,7 +50,6 @@ #include <asm/perfmon.h> #include <asm/processor.h> #include <asm/signal.h> -#include <asm/system.h> #include <asm/uaccess.h> #include <asm/delay.h> @@ -521,7 +521,7 @@ static pmu_config_t *pmu_conf; pfm_sysctl_t pfm_sysctl; EXPORT_SYMBOL(pfm_sysctl); -static ctl_table pfm_ctl_table[]={ +static struct ctl_table pfm_ctl_table[] = { { .procname = "debug", .data = &pfm_sysctl.debug, @@ -552,7 +552,7 @@ static ctl_table pfm_ctl_table[]={ }, {} }; -static ctl_table pfm_sysctl_dir[] = { +static struct ctl_table pfm_sysctl_dir[] = { { .procname = "perfmon", .mode = 0555, @@ -560,7 +560,7 @@ static ctl_table pfm_sysctl_dir[] = { }, {} }; -static ctl_table pfm_sysctl_root[] = { +static struct ctl_table pfm_sysctl_root[] = { { .procname = "kernel", .mode = 0555, @@ -605,23 +605,14 @@ pfm_unprotect_ctx_ctxsw(pfm_context_t *x, unsigned long f) spin_unlock(&(x)->ctx_lock); } -static inline unsigned int -pfm_do_munmap(struct mm_struct *mm, unsigned long addr, size_t len, int acct) -{ - return do_munmap(mm, addr, len); -} - -static inline unsigned long -pfm_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, unsigned long exec) -{ - return get_unmapped_area(file, addr, len, pgoff, flags); -} - +/* forward declaration */ +static const struct dentry_operations pfmfs_dentry_operations; static struct dentry * pfmfs_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data) { - return mount_pseudo(fs_type, "pfm:", NULL, PFMFS_MAGIC); + return mount_pseudo(fs_type, "pfm:", NULL, &pfmfs_dentry_operations, + PFMFS_MAGIC); } static struct file_system_type pfm_fs_type = { @@ -629,6 +620,7 @@ static struct file_system_type pfm_fs_type = { .mount = pfmfs_mount, .kill_sb = kill_anon_super, }; +MODULE_ALIAS_FS("pfmfs"); DEFINE_PER_CPU(unsigned long, pfm_syst_info); DEFINE_PER_CPU(struct task_struct *, pmu_owner); @@ -829,10 +821,9 @@ pfm_rvmalloc(unsigned long size) unsigned long addr; size = PAGE_ALIGN(size); - mem = vmalloc(size); + mem = vzalloc(size); if (mem) { //printk("perfmon: CPU%d pfm_rvmalloc(%ld)=%p\n", smp_processor_id(), size, mem); - memset(mem, 0, size); addr = (unsigned long)mem; while (size > 0) { pfm_reserve_page(addr); @@ -1332,8 +1323,6 @@ out: } EXPORT_SYMBOL(pfm_unregister_buffer_fmt); -extern void update_pal_halt_status(int); - static int pfm_reserve_session(struct task_struct *task, int is_syswide, unsigned int cpu) { @@ -1381,9 +1370,9 @@ pfm_reserve_session(struct task_struct *task, int is_syswide, unsigned int cpu) cpu)); /* - * disable default_idle() to go to PAL_HALT + * Force idle() into poll mode */ - update_pal_halt_status(0); + cpu_idle_poll_ctrl(true); UNLOCK_PFS(flags); @@ -1440,11 +1429,8 @@ pfm_unreserve_session(pfm_context_t *ctx, int is_syswide, unsigned int cpu) is_syswide, cpu)); - /* - * if possible, enable default_idle() to go into PAL_HALT - */ - if (pfm_sessions.pfs_task_sessions == 0 && pfm_sessions.pfs_sys_sessions == 0) - update_pal_halt_status(1); + /* Undo forced polling. Last session reenables pal_halt */ + cpu_idle_poll_ctrl(false); UNLOCK_PFS(flags); @@ -1457,8 +1443,9 @@ pfm_unreserve_session(pfm_context_t *ctx, int is_syswide, unsigned int cpu) * a PROTECT_CTX() section. */ static int -pfm_remove_smpl_mapping(struct task_struct *task, void *vaddr, unsigned long size) +pfm_remove_smpl_mapping(void *vaddr, unsigned long size) { + struct task_struct *task = current; int r; /* sanity checks */ @@ -1472,13 +1459,8 @@ pfm_remove_smpl_mapping(struct task_struct *task, void *vaddr, unsigned long siz /* * does the actual unmapping */ - down_write(&task->mm->mmap_sem); - - DPRINT(("down_write done smpl_vaddr=%p size=%lu\n", vaddr, size)); - - r = pfm_do_munmap(task->mm, (unsigned long)vaddr, size, 0); + r = vm_munmap((unsigned long)vaddr, size); - up_write(&task->mm->mmap_sem); if (r !=0) { printk(KERN_ERR "perfmon: [%d] unable to unmap sampling buffer @%p size=%lu\n", task_pid_nr(task), vaddr, size); } @@ -1542,7 +1524,7 @@ pfm_exit_smpl_buffer(pfm_buffer_fmt_t *fmt) * any operations on the root directory. However, we need a non-trivial * d_name - pfm: will go nicely and kill the special-casing in procfs. */ -static struct vfsmount *pfmfs_mnt; +static struct vfsmount *pfmfs_mnt __read_mostly; static int __init init_pfm_fs(void) @@ -1944,7 +1926,7 @@ pfm_flush(struct file *filp, fl_owner_t id) * because some VM function reenables interrupts. * */ - if (smpl_buf_vaddr) pfm_remove_smpl_mapping(current, smpl_buf_vaddr, smpl_buf_size); + if (smpl_buf_vaddr) pfm_remove_smpl_mapping(smpl_buf_vaddr, smpl_buf_size); return 0; } @@ -2184,12 +2166,6 @@ static const struct file_operations pfm_file_ops = { .flush = pfm_flush }; -static int -pfmfs_delete_dentry(struct dentry *dentry) -{ - return 1; -} - static char *pfmfs_dname(struct dentry *dentry, char *buffer, int buflen) { return dynamic_dname(dentry, buffer, buflen, "pfm:[%lu]", @@ -2197,7 +2173,7 @@ static char *pfmfs_dname(struct dentry *dentry, char *buffer, int buflen) } static const struct dentry_operations pfmfs_dentry_operations = { - .d_delete = pfmfs_delete_dentry, + .d_delete = always_delete_dentry, .d_dname = pfmfs_dname, }; @@ -2226,20 +2202,19 @@ pfm_alloc_file(pfm_context_t *ctx) /* * allocate a new dcache entry */ - path.dentry = d_alloc(pfmfs_mnt->mnt_sb->s_root, &this); + path.dentry = d_alloc(pfmfs_mnt->mnt_root, &this); if (!path.dentry) { iput(inode); return ERR_PTR(-ENOMEM); } path.mnt = mntget(pfmfs_mnt); - path.dentry->d_op = &pfmfs_dentry_operations; d_add(path.dentry, inode); file = alloc_file(&path, FMODE_READ, &pfm_file_ops); - if (!file) { + if (IS_ERR(file)) { path_put(&path); - return ERR_PTR(-ENFILE); + return file; } file->f_flags = O_RDONLY; @@ -2322,8 +2297,8 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t * partially initialize the vma for the sampling buffer */ vma->vm_mm = mm; - vma->vm_file = filp; - vma->vm_flags = VM_READ| VM_MAYREAD |VM_RESERVED; + vma->vm_file = get_file(filp); + vma->vm_flags = VM_READ|VM_MAYREAD|VM_DONTEXPAND|VM_DONTDUMP; vma->vm_page_prot = PAGE_READONLY; /* XXX may need to change */ /* @@ -2343,8 +2318,8 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t down_write(&task->mm->mmap_sem); /* find some free area in address space, must have mmap sem held */ - vma->vm_start = pfm_get_unmapped_area(NULL, 0, size, 0, MAP_PRIVATE|MAP_ANONYMOUS, 0); - if (vma->vm_start == 0UL) { + vma->vm_start = get_unmapped_area(NULL, 0, size, 0, MAP_PRIVATE|MAP_ANONYMOUS); + if (IS_ERR_VALUE(vma->vm_start)) { DPRINT(("Cannot find unmapped area for size %ld\n", size)); up_write(&task->mm->mmap_sem); goto error; @@ -2361,15 +2336,12 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t goto error; } - get_file(filp); - /* * now insert the vma in the vm list for the process, must be * done with mmap lock held */ insert_vm_struct(mm, vma); - mm->total_vm += size >> PAGE_SHIFT; vm_stat_account(vma->vm_mm, vma->vm_flags, vma->vm_file, vma_pages(vma)); up_write(&task->mm->mmap_sem); @@ -2397,8 +2369,8 @@ static int pfm_bad_permissions(struct task_struct *task) { const struct cred *tcred; - uid_t uid = current_uid(); - gid_t gid = current_gid(); + kuid_t uid = current_uid(); + kgid_t gid = current_gid(); int ret; rcu_read_lock(); @@ -2406,20 +2378,20 @@ pfm_bad_permissions(struct task_struct *task) /* inspired by ptrace_attach() */ DPRINT(("cur: uid=%d gid=%d task: euid=%d suid=%d uid=%d egid=%d sgid=%d\n", - uid, - gid, - tcred->euid, - tcred->suid, - tcred->uid, - tcred->egid, - tcred->sgid)); - - ret = ((uid != tcred->euid) - || (uid != tcred->suid) - || (uid != tcred->uid) - || (gid != tcred->egid) - || (gid != tcred->sgid) - || (gid != tcred->gid)) && !capable(CAP_SYS_PTRACE); + from_kuid(&init_user_ns, uid), + from_kgid(&init_user_ns, gid), + from_kuid(&init_user_ns, tcred->euid), + from_kuid(&init_user_ns, tcred->suid), + from_kuid(&init_user_ns, tcred->uid), + from_kgid(&init_user_ns, tcred->egid), + from_kgid(&init_user_ns, tcred->sgid))); + + ret = ((!uid_eq(uid, tcred->euid)) + || (!uid_eq(uid, tcred->suid)) + || (!uid_eq(uid, tcred->uid)) + || (!gid_eq(gid, tcred->egid)) + || (!gid_eq(gid, tcred->sgid)) + || (!gid_eq(gid, tcred->gid))) && !capable(CAP_SYS_PTRACE); rcu_read_unlock(); return ret; @@ -4799,7 +4771,7 @@ recheck: asmlinkage long sys_perfmonctl (int fd, int cmd, void __user *arg, int count) { - struct file *file = NULL; + struct fd f = {NULL, 0}; pfm_context_t *ctx = NULL; unsigned long flags = 0UL; void *args_k = NULL; @@ -4896,17 +4868,17 @@ restart_args: ret = -EBADF; - file = fget(fd); - if (unlikely(file == NULL)) { + f = fdget(fd); + if (unlikely(f.file == NULL)) { DPRINT(("invalid fd %d\n", fd)); goto error_args; } - if (unlikely(PFM_IS_FILE(file) == 0)) { + if (unlikely(PFM_IS_FILE(f.file) == 0)) { DPRINT(("fd %d not related to perfmon\n", fd)); goto error_args; } - ctx = file->private_data; + ctx = f.file->private_data; if (unlikely(ctx == NULL)) { DPRINT(("no context for fd %d\n", fd)); goto error_args; @@ -4936,8 +4908,8 @@ abort_locked: if (call_made && PFM_CMD_RW_ARG(cmd) && copy_to_user(arg, args_k, base_sz*count)) ret = -EFAULT; error_args: - if (file) - fput(file); + if (f.file) + fdput(f); kfree(args_k); @@ -5669,24 +5641,8 @@ pfm_proc_show_header(struct seq_file *m) list_for_each(pos, &pfm_buffer_fmt_list) { entry = list_entry(pos, pfm_buffer_fmt_t, fmt_list); - seq_printf(m, "format : %02x-%02x-%02x-%02x-%02x-%02x-%02x-%02x-%02x-%02x-%02x-%02x-%02x-%02x-%02x-%02x %s\n", - entry->fmt_uuid[0], - entry->fmt_uuid[1], - entry->fmt_uuid[2], - entry->fmt_uuid[3], - entry->fmt_uuid[4], - entry->fmt_uuid[5], - entry->fmt_uuid[6], - entry->fmt_uuid[7], - entry->fmt_uuid[8], - entry->fmt_uuid[9], - entry->fmt_uuid[10], - entry->fmt_uuid[11], - entry->fmt_uuid[12], - entry->fmt_uuid[13], - entry->fmt_uuid[14], - entry->fmt_uuid[15], - entry->fmt_name); + seq_printf(m, "format : %16phD %s\n", + entry->fmt_uuid, entry->fmt_name); } spin_unlock(&pfm_buffer_fmt_lock); @@ -6431,7 +6387,6 @@ pfm_flush_pmds(struct task_struct *task, pfm_context_t *ctx) static struct irqaction perfmon_irqaction = { .handler = pfm_interrupt_handler, - .flags = IRQF_DISABLED, .name = "perfmon" }; diff --git a/arch/ia64/kernel/perfmon_default_smpl.c b/arch/ia64/kernel/perfmon_default_smpl.c index 5f637bbfccc..30c644ea44c 100644 --- a/arch/ia64/kernel/perfmon_default_smpl.c +++ b/arch/ia64/kernel/perfmon_default_smpl.c @@ -150,7 +150,7 @@ default_handler(struct task_struct *task, void *buf, pfm_ovfl_arg_t *arg, struct * current = task running at the time of the overflow. * * per-task mode: - * - this is ususally the task being monitored. + * - this is usually the task being monitored. * Under certain conditions, it might be a different task * * system-wide: diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index 16f1c7b04c6..55d4ba47a90 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -29,6 +29,7 @@ #include <linux/kdebug.h> #include <linux/utsname.h> #include <linux/tracehook.h> +#include <linux/rcupdate.h> #include <asm/cpu.h> #include <asm/delay.h> @@ -38,6 +39,7 @@ #include <asm/pgalloc.h> #include <asm/processor.h> #include <asm/sal.h> +#include <asm/switch_to.h> #include <asm/tlbflush.h> #include <asm/uaccess.h> #include <asm/unwind.h> @@ -53,14 +55,8 @@ void (*ia64_mark_idle)(int); -unsigned long boot_option_idle_override = 0; +unsigned long boot_option_idle_override = IDLE_NO_OVERRIDE; EXPORT_SYMBOL(boot_option_idle_override); -unsigned long idle_halt; -EXPORT_SYMBOL(idle_halt); -unsigned long idle_nomwait; -EXPORT_SYMBOL(idle_nomwait); -void (*pm_idle) (void); -EXPORT_SYMBOL(pm_idle); void (*pm_power_off) (void); EXPORT_SYMBOL(pm_power_off); @@ -100,21 +96,13 @@ show_stack (struct task_struct *task, unsigned long *sp) } void -dump_stack (void) -{ - show_stack(NULL, NULL); -} - -EXPORT_SYMBOL(dump_stack); - -void show_regs (struct pt_regs *regs) { unsigned long ip = regs->cr_iip + ia64_psr(regs)->ri; print_modules(); - printk("\nPid: %d, CPU %d, comm: %20s\n", task_pid_nr(current), - smp_processor_id(), current->comm); + printk("\n"); + show_regs_print_info(KERN_DEFAULT); printk("psr : %016lx ifs : %016lx ip : [<%016lx>] %s (%s)\n", regs->cr_ipsr, regs->cr_ifs, ip, print_tainted(), init_utsname()->release); @@ -199,11 +187,9 @@ do_notify_resume_user(sigset_t *unused, struct sigscratch *scr, long in_syscall) ia64_do_signal(scr, in_syscall); } - if (test_thread_flag(TIF_NOTIFY_RESUME)) { - clear_thread_flag(TIF_NOTIFY_RESUME); + if (test_and_clear_thread_flag(TIF_NOTIFY_RESUME)) { + local_irq_enable(); /* force interrupt enable */ tracehook_notify_resume(&scr->pt); - if (current->replacement_session_keyring) - key_replace_session_keyring(); } /* copy user rbs to kernel rbs */ @@ -215,41 +201,13 @@ do_notify_resume_user(sigset_t *unused, struct sigscratch *scr, long in_syscall) local_irq_disable(); /* force interrupt disable */ } -static int pal_halt = 1; -static int can_do_pal_halt = 1; - static int __init nohalt_setup(char * str) { - pal_halt = can_do_pal_halt = 0; + cpu_idle_poll_ctrl(true); return 1; } __setup("nohalt", nohalt_setup); -void -update_pal_halt_status(int status) -{ - can_do_pal_halt = pal_halt && status; -} - -/* - * We use this if we don't have any better idle routine.. - */ -void -default_idle (void) -{ - local_irq_enable(); - while (!need_resched()) { - if (can_do_pal_halt) { - local_irq_disable(); - if (!need_resched()) { - safe_halt(); - } - local_irq_enable(); - } else - cpu_relax(); - } -} - #ifdef CONFIG_HOTPLUG_CPU /* We don't actually take CPU down, just spin without interrupts. */ static inline void play_dead(void) @@ -276,71 +234,29 @@ static inline void play_dead(void) } #endif /* CONFIG_HOTPLUG_CPU */ -static void do_nothing(void *unused) -{ -} - -/* - * cpu_idle_wait - Used to ensure that all the CPUs discard old value of - * pm_idle and update to new pm_idle value. Required while changing pm_idle - * handler on SMP systems. - * - * Caller must have changed pm_idle to the new value before the call. Old - * pm_idle value will not be used by any CPU after the return of this function. - */ -void cpu_idle_wait(void) +void arch_cpu_idle_dead(void) { - smp_mb(); - /* kick all the CPUs so that they exit out of pm_idle */ - smp_call_function(do_nothing, NULL, 1); + play_dead(); } -EXPORT_SYMBOL_GPL(cpu_idle_wait); -void __attribute__((noreturn)) -cpu_idle (void) +void arch_cpu_idle(void) { void (*mark_idle)(int) = ia64_mark_idle; - int cpu = smp_processor_id(); - - /* endless idle loop with no priority at all */ - while (1) { - if (can_do_pal_halt) { - current_thread_info()->status &= ~TS_POLLING; - /* - * TS_POLLING-cleared state must be visible before we - * test NEED_RESCHED: - */ - smp_mb(); - } else { - current_thread_info()->status |= TS_POLLING; - } - if (!need_resched()) { - void (*idle)(void); #ifdef CONFIG_SMP - min_xtp(); + min_xtp(); #endif - rmb(); - if (mark_idle) - (*mark_idle)(1); - - idle = pm_idle; - if (!idle) - idle = default_idle; - (*idle)(); - if (mark_idle) - (*mark_idle)(0); + rmb(); + if (mark_idle) + (*mark_idle)(1); + + safe_halt(); + + if (mark_idle) + (*mark_idle)(0); #ifdef CONFIG_SMP - normal_xtp(); + normal_xtp(); #endif - } - preempt_enable_no_resched(); - schedule(); - preempt_disable(); - check_pgt_cache(); - if (cpu_is_offline(cpu)) - play_dead(); - } } void @@ -417,72 +333,24 @@ ia64_load_extra (struct task_struct *task) int copy_thread(unsigned long clone_flags, unsigned long user_stack_base, unsigned long user_stack_size, - struct task_struct *p, struct pt_regs *regs) + struct task_struct *p) { extern char ia64_ret_from_clone; struct switch_stack *child_stack, *stack; unsigned long rbs, child_rbs, rbs_size; struct pt_regs *child_ptregs; + struct pt_regs *regs = current_pt_regs(); int retval = 0; -#ifdef CONFIG_SMP - /* - * For SMP idle threads, fork_by_hand() calls do_fork with - * NULL regs. - */ - if (!regs) - return 0; -#endif - - stack = ((struct switch_stack *) regs) - 1; - child_ptregs = (struct pt_regs *) ((unsigned long) p + IA64_STK_OFFSET) - 1; child_stack = (struct switch_stack *) child_ptregs - 1; - /* copy parent's switch_stack & pt_regs to child: */ - memcpy(child_stack, stack, sizeof(*child_ptregs) + sizeof(*child_stack)); - rbs = (unsigned long) current + IA64_RBS_OFFSET; child_rbs = (unsigned long) p + IA64_RBS_OFFSET; - rbs_size = stack->ar_bspstore - rbs; - - /* copy the parent's register backing store to the child: */ - memcpy((void *) child_rbs, (void *) rbs, rbs_size); - - if (likely(user_mode(child_ptregs))) { - if (clone_flags & CLONE_SETTLS) - child_ptregs->r13 = regs->r16; /* see sys_clone2() in entry.S */ - if (user_stack_base) { - child_ptregs->r12 = user_stack_base + user_stack_size - 16; - child_ptregs->ar_bspstore = user_stack_base; - child_ptregs->ar_rnat = 0; - child_ptregs->loadrs = 0; - } - } else { - /* - * Note: we simply preserve the relative position of - * the stack pointer here. There is no need to - * allocate a scratch area here, since that will have - * been taken care of by the caller of sys_clone() - * already. - */ - child_ptregs->r12 = (unsigned long) child_ptregs - 16; /* kernel sp */ - child_ptregs->r13 = (unsigned long) p; /* set `current' pointer */ - } - child_stack->ar_bspstore = child_rbs + rbs_size; - child_stack->b0 = (unsigned long) &ia64_ret_from_clone; /* copy parts of thread_struct: */ p->thread.ksp = (unsigned long) child_stack - 16; - /* stop some PSR bits from being inherited. - * the psr.up/psr.pp bits must be cleared on fork but inherited on execve() - * therefore we must specify them explicitly here and not include them in - * IA64_PSR_BITS_TO_CLEAR. - */ - child_ptregs->cr_ipsr = ((child_ptregs->cr_ipsr | IA64_PSR_BITS_TO_SET) - & ~(IA64_PSR_BITS_TO_CLEAR | IA64_PSR_PP | IA64_PSR_UP)); - /* * NOTE: The calling convention considers all floating point * registers in the high partition (fph) to be scratch. Since @@ -504,8 +372,66 @@ copy_thread(unsigned long clone_flags, # define THREAD_FLAGS_TO_SET 0 p->thread.flags = ((current->thread.flags & ~THREAD_FLAGS_TO_CLEAR) | THREAD_FLAGS_TO_SET); + ia64_drop_fpu(p); /* don't pick up stale state from a CPU's fph */ + if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(!user_stack_base)) { + /* fork_idle() called us */ + return 0; + } + memset(child_stack, 0, sizeof(*child_ptregs) + sizeof(*child_stack)); + child_stack->r4 = user_stack_base; /* payload */ + child_stack->r5 = user_stack_size; /* argument */ + /* + * Preserve PSR bits, except for bits 32-34 and 37-45, + * which we can't read. + */ + child_ptregs->cr_ipsr = ia64_getreg(_IA64_REG_PSR) | IA64_PSR_BN; + /* mark as valid, empty frame */ + child_ptregs->cr_ifs = 1UL << 63; + child_stack->ar_fpsr = child_ptregs->ar_fpsr + = ia64_getreg(_IA64_REG_AR_FPSR); + child_stack->pr = (1 << PRED_KERNEL_STACK); + child_stack->ar_bspstore = child_rbs; + child_stack->b0 = (unsigned long) &ia64_ret_from_clone; + + /* stop some PSR bits from being inherited. + * the psr.up/psr.pp bits must be cleared on fork but inherited on execve() + * therefore we must specify them explicitly here and not include them in + * IA64_PSR_BITS_TO_CLEAR. + */ + child_ptregs->cr_ipsr = ((child_ptregs->cr_ipsr | IA64_PSR_BITS_TO_SET) + & ~(IA64_PSR_BITS_TO_CLEAR | IA64_PSR_PP | IA64_PSR_UP)); + + return 0; + } + stack = ((struct switch_stack *) regs) - 1; + /* copy parent's switch_stack & pt_regs to child: */ + memcpy(child_stack, stack, sizeof(*child_ptregs) + sizeof(*child_stack)); + + /* copy the parent's register backing store to the child: */ + rbs_size = stack->ar_bspstore - rbs; + memcpy((void *) child_rbs, (void *) rbs, rbs_size); + if (clone_flags & CLONE_SETTLS) + child_ptregs->r13 = regs->r16; /* see sys_clone2() in entry.S */ + if (user_stack_base) { + child_ptregs->r12 = user_stack_base + user_stack_size - 16; + child_ptregs->ar_bspstore = user_stack_base; + child_ptregs->ar_rnat = 0; + child_ptregs->loadrs = 0; + } + child_stack->ar_bspstore = child_rbs + rbs_size; + child_stack->b0 = (unsigned long) &ia64_ret_from_clone; + + /* stop some PSR bits from being inherited. + * the psr.up/psr.pp bits must be cleared on fork but inherited on execve() + * therefore we must specify them explicitly here and not include them in + * IA64_PSR_BITS_TO_CLEAR. + */ + child_ptregs->cr_ipsr = ((child_ptregs->cr_ipsr | IA64_PSR_BITS_TO_SET) + & ~(IA64_PSR_BITS_TO_CLEAR | IA64_PSR_PP | IA64_PSR_UP)); + #ifdef CONFIG_PERFMON if (current->thread.pfm_context) pfm_inherit(p, child_ptregs); @@ -632,57 +558,6 @@ dump_fpu (struct pt_regs *pt, elf_fpregset_t dst) return 1; /* f0-f31 are always valid so we always return 1 */ } -long -sys_execve (const char __user *filename, - const char __user *const __user *argv, - const char __user *const __user *envp, - struct pt_regs *regs) -{ - char *fname; - int error; - - fname = getname(filename); - error = PTR_ERR(fname); - if (IS_ERR(fname)) - goto out; - error = do_execve(fname, argv, envp, regs); - putname(fname); -out: - return error; -} - -pid_t -kernel_thread (int (*fn)(void *), void *arg, unsigned long flags) -{ - extern void start_kernel_thread (void); - unsigned long *helper_fptr = (unsigned long *) &start_kernel_thread; - struct { - struct switch_stack sw; - struct pt_regs pt; - } regs; - - memset(®s, 0, sizeof(regs)); - regs.pt.cr_iip = helper_fptr[0]; /* set entry point (IP) */ - regs.pt.r1 = helper_fptr[1]; /* set GP */ - regs.pt.r9 = (unsigned long) fn; /* 1st argument */ - regs.pt.r11 = (unsigned long) arg; /* 2nd argument */ - /* Preserve PSR bits, except for bits 32-34 and 37-45, which we can't read. */ - regs.pt.cr_ipsr = ia64_getreg(_IA64_REG_PSR) | IA64_PSR_BN; - regs.pt.cr_ifs = 1UL << 63; /* mark as valid, empty frame */ - regs.sw.ar_fpsr = regs.pt.ar_fpsr = ia64_getreg(_IA64_REG_AR_FPSR); - regs.sw.ar_bspstore = (unsigned long) current + IA64_RBS_OFFSET; - regs.sw.pr = (1 << PRED_KERNEL_STACK); - return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, ®s.pt, 0, NULL, NULL); -} -EXPORT_SYMBOL(kernel_thread); - -/* This gets called from kernel_thread() via ia64_invoke_thread_helper(). */ -int -kernel_thread_helper (int (*fn)(void *), void *arg) -{ - return (*fn)(arg); -} - /* * Flush thread state. This is called when a thread does an execve(). */ diff --git a/arch/ia64/kernel/ptrace.c b/arch/ia64/kernel/ptrace.c index 8848f43d819..b7a5fffe092 100644 --- a/arch/ia64/kernel/ptrace.c +++ b/arch/ia64/kernel/ptrace.c @@ -26,7 +26,6 @@ #include <asm/processor.h> #include <asm/ptrace_offsets.h> #include <asm/rse.h> -#include <asm/system.h> #include <asm/uaccess.h> #include <asm/unwind.h> #ifdef CONFIG_PERFMON @@ -673,33 +672,6 @@ ptrace_attach_sync_user_rbs (struct task_struct *child) read_unlock(&tasklist_lock); } -static inline int -thread_matches (struct task_struct *thread, unsigned long addr) -{ - unsigned long thread_rbs_end; - struct pt_regs *thread_regs; - - if (ptrace_check_attach(thread, 0) < 0) - /* - * If the thread is not in an attachable state, we'll - * ignore it. The net effect is that if ADDR happens - * to overlap with the portion of the thread's - * register backing store that is currently residing - * on the thread's kernel stack, then ptrace() may end - * up accessing a stale value. But if the thread - * isn't stopped, that's a problem anyhow, so we're - * doing as well as we can... - */ - return 0; - - thread_regs = task_pt_regs(thread); - thread_rbs_end = ia64_get_user_rbs_end(thread, thread_regs, NULL); - if (!on_kernel_rbs(addr, thread_regs->ar_bspstore, thread_rbs_end)) - return 0; - - return 1; /* looks like we've got a winner */ -} - /* * Write f32-f127 back to task->thread.fph if it has been modified. */ @@ -1246,15 +1218,8 @@ syscall_trace_enter (long arg0, long arg1, long arg2, long arg3, if (test_thread_flag(TIF_RESTORE_RSE)) ia64_sync_krbs(); - if (unlikely(current->audit_context)) { - long syscall; - int arch; - syscall = regs.r15; - arch = AUDIT_ARCH_IA64; - - audit_syscall_entry(arch, syscall, arg0, arg1, arg2, arg3); - } + audit_syscall_entry(AUDIT_ARCH_IA64, regs.r15, arg0, arg1, arg2, arg3); return 0; } @@ -1268,14 +1233,7 @@ syscall_trace_leave (long arg0, long arg1, long arg2, long arg3, { int step; - if (unlikely(current->audit_context)) { - int success = AUDITSC_RESULT(regs.r10); - long result = regs.r8; - - if (success != AUDITSC_SUCCESS) - result = -result; - audit_syscall_exit(success, result); - } + audit_syscall_exit(®s); step = test_thread_flag(TIF_SINGLESTEP); if (step || test_thread_flag(TIF_SYSCALL_TRACE)) diff --git a/arch/ia64/kernel/salinfo.c b/arch/ia64/kernel/salinfo.c index 79802e540e5..ee9719eebb1 100644 --- a/arch/ia64/kernel/salinfo.c +++ b/arch/ia64/kernel/salinfo.c @@ -40,6 +40,7 @@ #include <linux/cpu.h> #include <linux/types.h> #include <linux/proc_fs.h> +#include <linux/seq_file.h> #include <linux/module.h> #include <linux/smp.h> #include <linux/timer.h> @@ -53,7 +54,7 @@ MODULE_AUTHOR("Jesse Barnes <jbarnes@sgi.com>"); MODULE_DESCRIPTION("/proc interface to IA-64 SAL features"); MODULE_LICENSE("GPL"); -static int salinfo_read(char *page, char **start, off_t off, int count, int *eof, void *data); +static const struct file_operations proc_salinfo_fops; typedef struct { const char *name; /* name of the proc entry */ @@ -65,7 +66,7 @@ typedef struct { * List {name,feature} pairs for every entry in /proc/sal/<feature> * that this module exports */ -static salinfo_entry_t salinfo_entries[]={ +static const salinfo_entry_t salinfo_entries[]={ { "bus_lock", IA64_SAL_PLATFORM_FEATURE_BUS_LOCK, }, { "irq_redirection", IA64_SAL_PLATFORM_FEATURE_IRQ_REDIR_HINT, }, { "ipi_redirection", IA64_SAL_PLATFORM_FEATURE_IPI_REDIR_HINT, }, @@ -301,9 +302,7 @@ salinfo_event_open(struct inode *inode, struct file *file) static ssize_t salinfo_event_read(struct file *file, char __user *buffer, size_t count, loff_t *ppos) { - struct inode *inode = file->f_path.dentry->d_inode; - struct proc_dir_entry *entry = PDE(inode); - struct salinfo_data *data = entry->data; + struct salinfo_data *data = PDE_DATA(file_inode(file)); char cmd[32]; size_t size; int i, n, cpu = -1; @@ -360,8 +359,7 @@ static const struct file_operations salinfo_event_fops = { static int salinfo_log_open(struct inode *inode, struct file *file) { - struct proc_dir_entry *entry = PDE(inode); - struct salinfo_data *data = entry->data; + struct salinfo_data *data = PDE_DATA(inode); if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -386,8 +384,7 @@ salinfo_log_open(struct inode *inode, struct file *file) static int salinfo_log_release(struct inode *inode, struct file *file) { - struct proc_dir_entry *entry = PDE(inode); - struct salinfo_data *data = entry->data; + struct salinfo_data *data = PDE_DATA(inode); if (data->state == STATE_NO_DATA) { vfree(data->log_buffer); @@ -463,9 +460,7 @@ retry: static ssize_t salinfo_log_read(struct file *file, char __user *buffer, size_t count, loff_t *ppos) { - struct inode *inode = file->f_path.dentry->d_inode; - struct proc_dir_entry *entry = PDE(inode); - struct salinfo_data *data = entry->data; + struct salinfo_data *data = PDE_DATA(file_inode(file)); u8 *buf; u64 bufsize; @@ -524,9 +519,7 @@ salinfo_log_clear(struct salinfo_data *data, int cpu) static ssize_t salinfo_log_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { - struct inode *inode = file->f_path.dentry->d_inode; - struct proc_dir_entry *entry = PDE(inode); - struct salinfo_data *data = entry->data; + struct salinfo_data *data = PDE_DATA(file_inode(file)); char cmd[32]; size_t size; u32 offset; @@ -575,7 +568,7 @@ static const struct file_operations salinfo_data_fops = { .llseek = default_llseek, }; -static int __cpuinit +static int salinfo_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu) { unsigned int i, cpu = (unsigned long)hcpu; @@ -616,7 +609,7 @@ salinfo_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu return NOTIFY_OK; } -static struct notifier_block salinfo_cpu_notifier __cpuinitdata = +static struct notifier_block salinfo_cpu_notifier = { .notifier_call = salinfo_cpu_callback, .priority = 0, @@ -637,10 +630,13 @@ salinfo_init(void) for (i=0; i < NR_SALINFO_ENTRIES; i++) { /* pass the feature bit in question as misc data */ - *sdir++ = create_proc_read_entry (salinfo_entries[i].name, 0, salinfo_dir, - salinfo_read, (void *)salinfo_entries[i].feature); + *sdir++ = proc_create_data(salinfo_entries[i].name, 0, salinfo_dir, + &proc_salinfo_fops, + (void *)salinfo_entries[i].feature); } + cpu_notifier_register_begin(); + for (i = 0; i < ARRAY_SIZE(salinfo_log_name); i++) { data = salinfo_data + i; data->type = i; @@ -675,7 +671,9 @@ salinfo_init(void) salinfo_timer.function = &salinfo_timeout; add_timer(&salinfo_timer); - register_hotcpu_notifier(&salinfo_cpu_notifier); + __register_hotcpu_notifier(&salinfo_cpu_notifier); + + cpu_notifier_register_done(); return 0; } @@ -684,22 +682,23 @@ salinfo_init(void) * 'data' contains an integer that corresponds to the feature we're * testing */ -static int -salinfo_read(char *page, char **start, off_t off, int count, int *eof, void *data) +static int proc_salinfo_show(struct seq_file *m, void *v) { - int len = 0; - - len = sprintf(page, (sal_platform_features & (unsigned long)data) ? "1\n" : "0\n"); - - if (len <= off+count) *eof = 1; - - *start = page + off; - len -= off; - - if (len>count) len = count; - if (len<0) len = 0; + unsigned long data = (unsigned long)v; + seq_puts(m, (sal_platform_features & data) ? "1\n" : "0\n"); + return 0; +} - return len; +static int proc_salinfo_open(struct inode *inode, struct file *file) +{ + return single_open(file, proc_salinfo_show, PDE_DATA(inode)); } +static const struct file_operations proc_salinfo_fops = { + .open = proc_salinfo_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + module_init(salinfo_init); diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c index 911cf974970..d86669bcdfb 100644 --- a/arch/ia64/kernel/setup.c +++ b/arch/ia64/kernel/setup.c @@ -59,7 +59,6 @@ #include <asm/sections.h> #include <asm/setup.h> #include <asm/smp.h> -#include <asm/system.h> #include <asm/tlbflush.h> #include <asm/unistd.h> #include <asm/hpsim.h> @@ -220,6 +219,23 @@ sort_regions (struct rsvd_region *rsvd_region, int max) } } +/* merge overlaps */ +static int __init +merge_regions (struct rsvd_region *rsvd_region, int max) +{ + int i; + for (i = 1; i < max; ++i) { + if (rsvd_region[i].start >= rsvd_region[i-1].end) + continue; + if (rsvd_region[i].end > rsvd_region[i-1].end) + rsvd_region[i-1].end = rsvd_region[i].end; + --max; + memmove(&rsvd_region[i], &rsvd_region[i+1], + (max - i) * sizeof(struct rsvd_region)); + } + return max; +} + /* * Request address space for all standard resources */ @@ -270,6 +286,7 @@ static void __init setup_crashkernel(unsigned long total, int *n) if (ret == 0 && size > 0) { if (!base) { sort_regions(rsvd_region, *n); + *n = merge_regions(rsvd_region, *n); base = kdump_find_rsvd_region(size, rsvd_region, *n); } @@ -373,6 +390,7 @@ reserve_memory (void) BUG_ON(IA64_MAX_RSVD_REGIONS + 1 < n); sort_regions(rsvd_region, num_rsvd_regions); + num_rsvd_regions = merge_regions(rsvd_region, num_rsvd_regions); } @@ -467,7 +485,7 @@ mark_bsp_online (void) { #ifdef CONFIG_SMP /* If we register an early console, allow CPU 0 to printk */ - cpu_set(smp_processor_id(), cpu_online_map); + set_cpu_online(smp_processor_id(), true); #endif } @@ -479,25 +497,7 @@ static __init int setup_nomca(char *s) } early_param("nomca", setup_nomca); -/* - * Note: elfcorehdr_addr is not just limited to vmcore. It is also used by - * is_kdump_kernel() to determine if we are booting after a panic. Hence - * ifdef it under CONFIG_CRASH_DUMP and not CONFIG_PROC_VMCORE. - */ #ifdef CONFIG_CRASH_DUMP -/* elfcorehdr= specifies the location of elf core header - * stored by the crashed kernel. - */ -static int __init parse_elfcorehdr(char *arg) -{ - if (!arg) - return -EINVAL; - - elfcorehdr_addr = memparse(arg, &arg); - return 0; -} -early_param("elfcorehdr", parse_elfcorehdr); - int __init reserve_elfcorehdr(u64 *start, u64 *end) { u64 length; @@ -748,7 +748,7 @@ const struct seq_operations cpuinfo_op = { #define MAX_BRANDS 8 static char brandname[MAX_BRANDS][128]; -static char * __cpuinit +static char * get_model_name(__u8 family, __u8 model) { static int overflow; @@ -778,7 +778,7 @@ get_model_name(__u8 family, __u8 model) return "Unknown"; } -static void __cpuinit +static void identify_cpu (struct cpuinfo_ia64 *c) { union { @@ -850,7 +850,7 @@ identify_cpu (struct cpuinfo_ia64 *c) * 2. the minimum of the i-cache stride sizes for "flush_icache_range()". * 3. the minimum of the cache stride sizes for "clflush_cache_range()". */ -static void __cpuinit +static void get_cache_info(void) { unsigned long line_size, max = 1; @@ -915,10 +915,10 @@ get_cache_info(void) * cpu_init() initializes state that is per-CPU. This function acts * as a 'CPU state barrier', nothing should get across. */ -void __cpuinit +void cpu_init (void) { - extern void __cpuinit ia64_mmu_init (void *); + extern void ia64_mmu_init(void *); static unsigned long max_num_phys_stacked = IA64_NUM_PHYS_STACK_REG; unsigned long num_phys_stacked; pal_vm_info_2_u_t vmi; @@ -1051,7 +1051,6 @@ cpu_init (void) max_num_phys_stacked = num_phys_stacked; } platform_cpu_init(); - pm_idle = default_idle; } void __init @@ -1064,6 +1063,8 @@ check_bugs (void) static int __init run_dmi_scan(void) { dmi_scan_machine(); + dmi_memdev_walk(); + dmi_set_dump_stack_arch_desc(); return 0; } core_initcall(run_dmi_scan); diff --git a/arch/ia64/kernel/signal.c b/arch/ia64/kernel/signal.c index 7bdafc8788b..33cab9a8adf 100644 --- a/arch/ia64/kernel/signal.c +++ b/arch/ia64/kernel/signal.c @@ -30,7 +30,6 @@ #define DEBUG_SIG 0 #define STACK_ALIGN 16 /* minimal alignment for stack pointer */ -#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) #if _NSIG_WORDS > 1 # define PUT_SIGSET(k,u) __copy_to_user((u)->sig, (k)->sig, sizeof(sigset_t)) @@ -40,14 +39,6 @@ # define GET_SIGSET(k,u) __get_user((k)->sig[0], &(u)->sig[0]) #endif -asmlinkage long -sys_sigaltstack (const stack_t __user *uss, stack_t __user *uoss, long arg2, - long arg3, long arg4, long arg5, long arg6, long arg7, - struct pt_regs regs) -{ - return do_sigaltstack(uss, uoss, regs.r12); -} - static long restore_sigcontext (struct sigcontext __user *sc, struct sigscratch *scr) { @@ -114,7 +105,7 @@ restore_sigcontext (struct sigcontext __user *sc, struct sigscratch *scr) } int -copy_siginfo_to_user (siginfo_t __user *to, siginfo_t *from) +copy_siginfo_to_user (siginfo_t __user *to, const siginfo_t *from) { if (!access_ok(VERIFY_WRITE, to, sizeof(siginfo_t))) return -EFAULT; @@ -200,14 +191,7 @@ ia64_rt_sigreturn (struct sigscratch *scr) if (GET_SIGSET(&set, &sc->sc_mask)) goto give_sigsegv; - sigdelsetmask(&set, ~_BLOCKABLE); - - spin_lock_irq(¤t->sighand->siglock); - { - current->blocked = set; - recalc_sigpending(); - } - spin_unlock_irq(¤t->sighand->siglock); + set_current_blocked(&set); if (restore_sigcontext(sc, scr)) goto give_sigsegv; @@ -216,11 +200,8 @@ ia64_rt_sigreturn (struct sigscratch *scr) printk("SIG return (%s:%d): sp=%lx ip=%lx\n", current->comm, current->pid, scr->pt.r12, scr->pt.cr_iip); #endif - /* - * It is more difficult to avoid calling this function than to - * call it and ignore errors. - */ - do_sigaltstack(&sc->sc_stack, NULL, scr->pt.r12); + if (restore_altstack(&sc->sc_stack)) + goto give_sigsegv; return retval; give_sigsegv: @@ -228,7 +209,7 @@ ia64_rt_sigreturn (struct sigscratch *scr) si.si_errno = 0; si.si_code = SI_KERNEL; si.si_pid = task_pid_vnr(current); - si.si_uid = current_uid(); + si.si_uid = from_kuid_munged(current_user_ns(), current_uid()); si.si_addr = sc; force_sig_info(SIGSEGV, &si, current); return retval; @@ -325,7 +306,7 @@ force_sigsegv_info (int sig, void __user *addr) si.si_errno = 0; si.si_code = SI_KERNEL; si.si_pid = task_pid_vnr(current); - si.si_uid = current_uid(); + si.si_uid = from_kuid_munged(current_user_ns(), current_uid()); si.si_addr = addr; force_sig_info(SIGSEGV, &si, current); return 0; @@ -384,9 +365,7 @@ setup_frame (int sig, struct k_sigaction *ka, siginfo_t *info, sigset_t *set, err |= copy_siginfo_to_user(&frame->info, info); - err |= __put_user(current->sas_ss_sp, &frame->sc.sc_stack.ss_sp); - err |= __put_user(current->sas_ss_size, &frame->sc.sc_stack.ss_size); - err |= __put_user(sas_ss_flags(scr->pt.r12), &frame->sc.sc_stack.ss_flags); + err |= __save_altstack(&frame->sc.sc_stack, scr->pt.r12); err |= setup_sigcontext(&frame->sc, set, scr); if (unlikely(err)) @@ -421,23 +400,13 @@ setup_frame (int sig, struct k_sigaction *ka, siginfo_t *info, sigset_t *set, } static long -handle_signal (unsigned long sig, struct k_sigaction *ka, siginfo_t *info, sigset_t *oldset, +handle_signal (unsigned long sig, struct k_sigaction *ka, siginfo_t *info, struct sigscratch *scr) { - if (!setup_frame(sig, ka, info, oldset, scr)) + if (!setup_frame(sig, ka, info, sigmask_to_save(), scr)) return 0; - spin_lock_irq(¤t->sighand->siglock); - sigorsets(¤t->blocked, ¤t->blocked, &ka->sa.sa_mask); - if (!(ka->sa.sa_flags & SA_NODEFER)) - sigaddset(¤t->blocked, sig); - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); - - /* - * Let tracing know that we've done the handler setup. - */ - tracehook_signal_handler(sig, info, ka, &scr->pt, + signal_delivered(sig, info, ka, &scr->pt, test_thread_flag(TIF_SINGLESTEP)); return 1; @@ -451,25 +420,11 @@ void ia64_do_signal (struct sigscratch *scr, long in_syscall) { struct k_sigaction ka; - sigset_t *oldset; siginfo_t info; long restart = in_syscall; long errno = scr->pt.r8; /* - * In the ia64_leave_kernel code path, we want the common case to go fast, which - * is why we may in certain cases get here from kernel mode. Just return without - * doing anything if so. - */ - if (!user_mode(&scr->pt)) - return; - - if (current_thread_info()->status & TS_RESTORE_SIGMASK) - oldset = ¤t->saved_sigmask; - else - oldset = ¤t->blocked; - - /* * This only loops in the rare cases of handle_signal() failing, in which case we * need to push through a forced SIGSEGV. */ @@ -518,16 +473,8 @@ ia64_do_signal (struct sigscratch *scr, long in_syscall) * Whee! Actually deliver the signal. If the delivery failed, we need to * continue to iterate in this loop so we can deliver the SIGSEGV... */ - if (handle_signal(signr, &ka, &info, oldset, scr)) { - /* - * A signal was successfully delivered; the saved - * sigmask will have been stored in the signal frame, - * and will be restored by sigreturn, so we can simply - * clear the TS_RESTORE_SIGMASK flag. - */ - current_thread_info()->status &= ~TS_RESTORE_SIGMASK; + if (handle_signal(signr, &ka, &info, scr)) return; - } } /* Did we come from a system call? */ @@ -549,8 +496,5 @@ ia64_do_signal (struct sigscratch *scr, long in_syscall) /* if there's no signal to deliver, we just put the saved sigmask * back */ - if (current_thread_info()->status & TS_RESTORE_SIGMASK) { - current_thread_info()->status &= ~TS_RESTORE_SIGMASK; - sigprocmask(SIG_SETMASK, ¤t->saved_sigmask, NULL); - } + restore_saved_sigmask(); } diff --git a/arch/ia64/kernel/smp.c b/arch/ia64/kernel/smp.c index dabeefe2113..9fcd4e63048 100644 --- a/arch/ia64/kernel/smp.c +++ b/arch/ia64/kernel/smp.c @@ -32,7 +32,7 @@ #include <linux/bitops.h> #include <linux/kexec.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <asm/current.h> #include <asm/delay.h> #include <asm/machvec.h> @@ -44,7 +44,6 @@ #include <asm/processor.h> #include <asm/ptrace.h> #include <asm/sal.h> -#include <asm/system.h> #include <asm/tlbflush.h> #include <asm/unistd.h> #include <asm/mca.h> @@ -77,7 +76,7 @@ stop_this_cpu(void) /* * Remove this CPU: */ - cpu_clear(smp_processor_id(), cpu_online_map); + set_cpu_online(smp_processor_id(), false); max_xtp(); local_irq_disable(); cpu_halt(); @@ -293,6 +292,7 @@ smp_flush_tlb_all (void) void smp_flush_tlb_mm (struct mm_struct *mm) { + cpumask_var_t cpus; preempt_disable(); /* this happens for the common case of a single-threaded fork(): */ if (likely(mm == current->active_mm && atomic_read(&mm->mm_users) == 1)) @@ -301,9 +301,15 @@ smp_flush_tlb_mm (struct mm_struct *mm) preempt_enable(); return; } - - smp_call_function_many(mm_cpumask(mm), - (void (*)(void *))local_finish_flush_tlb_mm, mm, 1); + if (!alloc_cpumask_var(&cpus, GFP_ATOMIC)) { + smp_call_function((void (*)(void *))local_finish_flush_tlb_mm, + mm, 1); + } else { + cpumask_copy(cpus, mm_cpumask(mm)); + smp_call_function_many(cpus, + (void (*)(void *))local_finish_flush_tlb_mm, mm, 1); + free_cpumask_var(cpus); + } local_irq_disable(); local_finish_flush_tlb_mm(mm); local_irq_enable(); diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c index d003b502a43..547a48d78bd 100644 --- a/arch/ia64/kernel/smpboot.c +++ b/arch/ia64/kernel/smpboot.c @@ -40,7 +40,7 @@ #include <linux/percpu.h> #include <linux/bitops.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <asm/cache.h> #include <asm/current.h> #include <asm/delay.h> @@ -55,7 +55,6 @@ #include <asm/processor.h> #include <asm/ptrace.h> #include <asm/sal.h> -#include <asm/system.h> #include <asm/tlbflush.h> #include <asm/unistd.h> #include <asm/sn/arch.h> @@ -76,13 +75,6 @@ #endif /* - * Store all idle threads, this can be reused instead of creating - * a new thread. Also avoids complicated thread destroy functionality - * for idle threads. - */ -struct task_struct *idle_thread_array[NR_CPUS]; - -/* * Global array allocated for NR_CPUS at boot time */ struct sal_to_os_boot sal_boot_rendez_state[NR_CPUS]; @@ -95,13 +87,7 @@ struct sal_to_os_boot *sal_state_for_booting_cpu = &sal_boot_rendez_state[0]; #define set_brendez_area(x) (sal_state_for_booting_cpu = &sal_boot_rendez_state[(x)]); -#define get_idle_for_cpu(x) (idle_thread_array[(x)]) -#define set_idle_for_cpu(x,p) (idle_thread_array[(x)] = (p)) - #else - -#define get_idle_for_cpu(x) (NULL) -#define set_idle_for_cpu(x,p) #define set_brendez_area(x) #endif @@ -361,12 +347,11 @@ ia64_sync_itc (unsigned int master) /* * Ideally sets up per-cpu profiling hooks. Doesn't do much now... */ -static inline void __devinit -smp_setup_percpu_timer (void) +static inline void smp_setup_percpu_timer(void) { } -static void __cpuinit +static void smp_callin (void) { int cpuid, phys_id, itc_master; @@ -396,15 +381,13 @@ smp_callin (void) set_numa_node(cpu_to_node_map[cpuid]); set_numa_mem(local_memory_node(cpu_to_node_map[cpuid])); - ipi_call_lock_irq(); spin_lock(&vector_lock); /* Setup the per cpu irq handling data structures */ __setup_vector_irq(cpuid); notify_cpu_starting(cpuid); - cpu_set(cpuid, cpu_online_map); + set_cpu_online(cpuid, true); per_cpu(cpu_state, cpuid) = CPU_ONLINE; spin_unlock(&vector_lock); - ipi_call_unlock_irq(); smp_setup_percpu_timer(); @@ -459,7 +442,7 @@ smp_callin (void) /* * Activate a secondary processor. head.S calls this. */ -int __cpuinit +int start_secondary (void *unused) { /* Early console may use I/O ports */ @@ -472,63 +455,16 @@ start_secondary (void *unused) preempt_disable(); smp_callin(); - cpu_idle(); + cpu_startup_entry(CPUHP_ONLINE); return 0; } -struct pt_regs * __cpuinit idle_regs(struct pt_regs *regs) -{ - return NULL; -} - -struct create_idle { - struct work_struct work; - struct task_struct *idle; - struct completion done; - int cpu; -}; - -void __cpuinit -do_fork_idle(struct work_struct *work) -{ - struct create_idle *c_idle = - container_of(work, struct create_idle, work); - - c_idle->idle = fork_idle(c_idle->cpu); - complete(&c_idle->done); -} - -static int __cpuinit -do_boot_cpu (int sapicid, int cpu) +static int +do_boot_cpu (int sapicid, int cpu, struct task_struct *idle) { int timeout; - struct create_idle c_idle = { - .work = __WORK_INITIALIZER(c_idle.work, do_fork_idle), - .cpu = cpu, - .done = COMPLETION_INITIALIZER(c_idle.done), - }; - - /* - * We can't use kernel_thread since we must avoid to - * reschedule the child. - */ - c_idle.idle = get_idle_for_cpu(cpu); - if (c_idle.idle) { - init_idle(c_idle.idle, cpu); - goto do_rest; - } - - schedule_work(&c_idle.work); - wait_for_completion(&c_idle.done); - - if (IS_ERR(c_idle.idle)) - panic("failed fork for CPU %d", cpu); - - set_idle_for_cpu(cpu, c_idle.idle); - -do_rest: - task_for_booting_cpu = c_idle.idle; + task_for_booting_cpu = idle; Dprintk("Sending wakeup vector %lu to AP 0x%x/0x%x.\n", ap_wakeup_vector, cpu, sapicid); set_brendez_area(cpu); @@ -548,7 +484,7 @@ do_rest: if (!cpu_isset(cpu, cpu_callin_map)) { printk(KERN_ERR "Processor 0x%x/0x%x is stuck.\n", cpu, sapicid); ia64_cpu_to_sapicid[cpu] = -1; - cpu_clear(cpu, cpu_online_map); /* was set in smp_callin() */ + set_cpu_online(cpu, false); /* was set in smp_callin() */ return -EINVAL; } return 0; @@ -578,8 +514,7 @@ smp_build_cpu_map (void) } ia64_cpu_to_sapicid[0] = boot_cpu_id; - cpus_clear(cpu_present_map); - set_cpu_present(0, true); + init_cpu_present(cpumask_of(0)); set_cpu_possible(0, true); for (cpu = 1, i = 0; i < smp_boot_data.cpu_count; i++) { sapicid = smp_boot_data.cpu_phys_id[i]; @@ -606,10 +541,6 @@ smp_prepare_cpus (unsigned int max_cpus) smp_setup_percpu_timer(); - /* - * We have the boot CPU online for sure. - */ - cpu_set(0, cpu_online_map); cpu_set(0, cpu_callin_map); local_cpu_data->loops_per_jiffy = loops_per_jiffy; @@ -631,9 +562,9 @@ smp_prepare_cpus (unsigned int max_cpus) } } -void __devinit smp_prepare_boot_cpu(void) +void smp_prepare_boot_cpu(void) { - cpu_set(smp_processor_id(), cpu_online_map); + set_cpu_online(smp_processor_id(), true); cpu_set(smp_processor_id(), cpu_callin_map); set_numa_node(cpu_to_node_map[smp_processor_id()]); per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE; @@ -677,7 +608,7 @@ extern void fixup_irqs(void); int migrate_platform_irqs(unsigned int cpu) { int new_cpei_cpu; - struct irq_desc *desc = NULL; + struct irq_data *data = NULL; const struct cpumask *mask; int retval = 0; @@ -690,23 +621,23 @@ int migrate_platform_irqs(unsigned int cpu) /* * Now re-target the CPEI to a different processor */ - new_cpei_cpu = any_online_cpu(cpu_online_map); + new_cpei_cpu = cpumask_any(cpu_online_mask); mask = cpumask_of(new_cpei_cpu); set_cpei_target_cpu(new_cpei_cpu); - desc = irq_desc + ia64_cpe_irq; + data = irq_get_irq_data(ia64_cpe_irq); /* * Switch for now, immediately, we need to do fake intr * as other interrupts, but need to study CPEI behaviour with * polling before making changes. */ - if (desc) { - desc->chip->disable(ia64_cpe_irq); - desc->chip->set_affinity(ia64_cpe_irq, mask); - desc->chip->enable(ia64_cpe_irq); - printk ("Re-targetting CPEI to cpu %d\n", new_cpei_cpu); + if (data && data->chip) { + data->chip->irq_disable(data); + data->chip->irq_set_affinity(data, mask, false); + data->chip->irq_enable(data); + printk ("Re-targeting CPEI to cpu %d\n", new_cpei_cpu); } } - if (!desc) { + if (!data) { printk ("Unable to retarget CPEI, offline cpu [%d] failed\n", cpu); retval = -EBUSY; } @@ -732,10 +663,10 @@ int __cpu_disable(void) return -EBUSY; } - cpu_clear(cpu, cpu_online_map); + set_cpu_online(cpu, false); if (migrate_platform_irqs(cpu)) { - cpu_set(cpu, cpu_online_map); + set_cpu_online(cpu, true); return -EBUSY; } @@ -781,8 +712,7 @@ smp_cpus_done (unsigned int dummy) (int)num_online_cpus(), bogosum/(500000/HZ), (bogosum/(5000/HZ))%100); } -static inline void __devinit -set_cpu_sibling_map(int cpu) +static inline void set_cpu_sibling_map(int cpu) { int i; @@ -798,8 +728,8 @@ set_cpu_sibling_map(int cpu) } } -int __cpuinit -__cpu_up (unsigned int cpu) +int +__cpu_up(unsigned int cpu, struct task_struct *tidle) { int ret; int sapicid; @@ -817,7 +747,7 @@ __cpu_up (unsigned int cpu) per_cpu(cpu_state, cpu) = CPU_UP_PREPARE; /* Processor goes to start_secondary(), sets online flag */ - ret = do_boot_cpu(sapicid, cpu); + ret = do_boot_cpu(sapicid, cpu, tidle); if (ret < 0) return ret; @@ -861,8 +791,7 @@ init_smp_config(void) * identify_siblings(cpu) gets called from identify_cpu. This populates the * information related to logical execution units in per_cpu_data structure. */ -void __devinit -identify_siblings(struct cpuinfo_ia64 *c) +void identify_siblings(struct cpuinfo_ia64 *c) { long status; u16 pltid; diff --git a/arch/ia64/kernel/sys_ia64.c b/arch/ia64/kernel/sys_ia64.c index 609d50056a6..41e33f84c18 100644 --- a/arch/ia64/kernel/sys_ia64.c +++ b/arch/ia64/kernel/sys_ia64.c @@ -25,9 +25,9 @@ arch_get_unmapped_area (struct file *filp, unsigned long addr, unsigned long len unsigned long pgoff, unsigned long flags) { long map_shared = (flags & MAP_SHARED); - unsigned long start_addr, align_mask = PAGE_SIZE - 1; + unsigned long align_mask = 0; struct mm_struct *mm = current->mm; - struct vm_area_struct *vma; + struct vm_unmapped_area_info info; if (len > RGN_MAP_LIMIT) return -ENOMEM; @@ -44,7 +44,7 @@ arch_get_unmapped_area (struct file *filp, unsigned long addr, unsigned long len addr = 0; #endif if (!addr) - addr = mm->free_area_cache; + addr = TASK_UNMAPPED_BASE; if (map_shared && (TASK_SIZE > 0xfffffffful)) /* @@ -53,28 +53,15 @@ arch_get_unmapped_area (struct file *filp, unsigned long addr, unsigned long len * tasks, we prefer to avoid exhausting the address space too quickly by * limiting alignment to a single page. */ - align_mask = SHMLBA - 1; - - full_search: - start_addr = addr = (addr + align_mask) & ~align_mask; - - for (vma = find_vma(mm, addr); ; vma = vma->vm_next) { - /* At this point: (!vma || addr < vma->vm_end). */ - if (TASK_SIZE - len < addr || RGN_MAP_LIMIT - len < REGION_OFFSET(addr)) { - if (start_addr != TASK_UNMAPPED_BASE) { - /* Start a new search --- just in case we missed some holes. */ - addr = TASK_UNMAPPED_BASE; - goto full_search; - } - return -ENOMEM; - } - if (!vma || addr + len <= vma->vm_start) { - /* Remember the address where we stopped this search: */ - mm->free_area_cache = addr + len; - return addr; - } - addr = (vma->vm_end + align_mask) & ~align_mask; - } + align_mask = PAGE_MASK & (SHMLBA - 1); + + info.flags = 0; + info.length = len; + info.low_limit = addr; + info.high_limit = TASK_SIZE; + info.align_mask = align_mask; + info.align_offset = 0; + return vm_unmapped_area(&info); } asmlinkage long @@ -171,22 +158,9 @@ asmlinkage unsigned long ia64_mremap (unsigned long addr, unsigned long old_len, unsigned long new_len, unsigned long flags, unsigned long new_addr) { - extern unsigned long do_mremap (unsigned long addr, - unsigned long old_len, - unsigned long new_len, - unsigned long flags, - unsigned long new_addr); - - down_write(¤t->mm->mmap_sem); - { - addr = do_mremap(addr, old_len, new_len, flags, new_addr); - } - up_write(¤t->mm->mmap_sem); - - if (IS_ERR((void *) addr)) - return addr; - - force_successful_syscall_return(); + addr = sys_mremap(addr, old_len, new_len, flags, new_addr); + if (!IS_ERR((void *) addr)) + force_successful_syscall_return(); return addr; } diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c index ed6f22eb5b1..71c52bc7c28 100644 --- a/arch/ia64/kernel/time.c +++ b/arch/ia64/kernel/time.c @@ -19,7 +19,7 @@ #include <linux/interrupt.h> #include <linux/efi.h> #include <linux/timex.h> -#include <linux/clocksource.h> +#include <linux/timekeeper_internal.h> #include <linux/platform_device.h> #include <asm/machvec.h> @@ -29,15 +29,12 @@ #include <asm/ptrace.h> #include <asm/sal.h> #include <asm/sections.h> -#include <asm/system.h> #include "fsyscall_gtod_data.h" static cycle_t itc_get_cycles(struct clocksource *cs); -struct fsyscall_gtod_data_t fsyscall_gtod_data = { - .lock = SEQLOCK_UNLOCKED, -}; +struct fsyscall_gtod_data_t fsyscall_gtod_data; struct itc_jitter_data_t itc_jitter_data; @@ -73,8 +70,6 @@ static struct clocksource clocksource_itc = { .rating = 350, .read = itc_get_cycles, .mask = CLOCKSOURCE_MASK(64), - .mult = 0, /*to be calculated*/ - .shift = 16, .flags = CLOCK_SOURCE_IS_CONTINUOUS, #ifdef CONFIG_PARAVIRT .resume = paravirt_clocksource_resume, @@ -82,38 +77,35 @@ static struct clocksource clocksource_itc = { }; static struct clocksource *itc_clocksource; -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE #include <linux/kernel_stat.h> extern cputime_t cycle_to_cputime(u64 cyc); +void vtime_account_user(struct task_struct *tsk) +{ + cputime_t delta_utime; + struct thread_info *ti = task_thread_info(tsk); + + if (ti->ac_utime) { + delta_utime = cycle_to_cputime(ti->ac_utime); + account_user_time(tsk, delta_utime, delta_utime); + ti->ac_utime = 0; + } +} + /* * Called from the context switch with interrupts disabled, to charge all * accumulated times to the current process, and to prepare accounting on * the next process. */ -void ia64_account_on_switch(struct task_struct *prev, struct task_struct *next) +void arch_vtime_task_switch(struct task_struct *prev) { struct thread_info *pi = task_thread_info(prev); - struct thread_info *ni = task_thread_info(next); - cputime_t delta_stime, delta_utime; - __u64 now; - - now = ia64_get_itc(); - - delta_stime = cycle_to_cputime(pi->ac_stime + (now - pi->ac_stamp)); - if (idle_task(smp_processor_id()) != prev) - account_system_time(prev, 0, delta_stime, delta_stime); - else - account_idle_time(delta_stime); + struct thread_info *ni = task_thread_info(current); - if (pi->ac_utime) { - delta_utime = cycle_to_cputime(pi->ac_utime); - account_user_time(prev, delta_utime, delta_utime); - } - - pi->ac_stamp = ni->ac_stamp = now; + pi->ac_stamp = ni->ac_stamp; ni->ac_stime = ni->ac_utime = 0; } @@ -121,54 +113,44 @@ void ia64_account_on_switch(struct task_struct *prev, struct task_struct *next) * Account time for a transition between system, hard irq or soft irq state. * Note that this function is called with interrupts enabled. */ -void account_system_vtime(struct task_struct *tsk) +static cputime_t vtime_delta(struct task_struct *tsk) { struct thread_info *ti = task_thread_info(tsk); - unsigned long flags; cputime_t delta_stime; __u64 now; - local_irq_save(flags); + WARN_ON_ONCE(!irqs_disabled()); now = ia64_get_itc(); delta_stime = cycle_to_cputime(ti->ac_stime + (now - ti->ac_stamp)); - if (irq_count() || idle_task(smp_processor_id()) != tsk) - account_system_time(tsk, 0, delta_stime, delta_stime); - else - account_idle_time(delta_stime); ti->ac_stime = 0; - ti->ac_stamp = now; - local_irq_restore(flags); + return delta_stime; } -EXPORT_SYMBOL_GPL(account_system_vtime); -/* - * Called from the timer interrupt handler to charge accumulated user time - * to the current process. Must be called with interrupts disabled. - */ -void account_process_tick(struct task_struct *p, int user_tick) +void vtime_account_system(struct task_struct *tsk) { - struct thread_info *ti = task_thread_info(p); - cputime_t delta_utime; + cputime_t delta = vtime_delta(tsk); - if (ti->ac_utime) { - delta_utime = cycle_to_cputime(ti->ac_utime); - account_user_time(p, delta_utime, delta_utime); - ti->ac_utime = 0; - } + account_system_time(tsk, 0, delta, delta); } +EXPORT_SYMBOL_GPL(vtime_account_system); -#endif /* CONFIG_VIRT_CPU_ACCOUNTING */ +void vtime_account_idle(struct task_struct *tsk) +{ + account_idle_time(vtime_delta(tsk)); +} + +#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ static irqreturn_t timer_interrupt (int irq, void *dev_id) { unsigned long new_itm; - if (unlikely(cpu_is_offline(smp_processor_id()))) { + if (cpu_is_offline(smp_processor_id())) { return IRQ_HANDLED; } @@ -190,19 +172,10 @@ timer_interrupt (int irq, void *dev_id) new_itm += local_cpu_data->itm_delta; - if (smp_processor_id() == time_keeper_id) { - /* - * Here we are in the timer irq handler. We have irqs locally - * disabled, but we don't know if the timer_bh is running on - * another CPU. We need to avoid to SMP race by acquiring the - * xtime_lock. - */ - write_seqlock(&xtime_lock); - do_timer(1); - local_cpu_data->itm_next = new_itm; - write_sequnlock(&xtime_lock); - } else - local_cpu_data->itm_next = new_itm; + if (smp_processor_id() == time_keeper_id) + xtime_update(1); + + local_cpu_data->itm_next = new_itm; if (time_after(new_itm, ia64_get_itc())) break; @@ -222,7 +195,7 @@ skip_process_time_accounting: * comfort, we increase the safety margin by * intentionally dropping the next tick(s). We do NOT * update itm.next because that would force us to call - * do_timer() which in turn would let our clock run + * xtime_update() which in turn would let our clock run * too fast (with the potentially devastating effect * of losing monotony of time). */ @@ -271,8 +244,7 @@ static int __init nojitter_setup(char *str) __setup("nojitter", nojitter_setup); -void __devinit -ia64_init_itm (void) +void ia64_init_itm(void) { unsigned long platform_base_freq, itc_freq; struct pal_freq_ratio itc_ratio, proc_ratio; @@ -374,11 +346,8 @@ ia64_init_itm (void) ia64_cpu_local_tick(); if (!itc_clocksource) { - /* Sort out mult/shift values: */ - clocksource_itc.mult = - clocksource_hz2mult(local_cpu_data->itc_freq, - clocksource_itc.shift); - clocksource_register(&clocksource_itc); + clocksource_register_hz(&clocksource_itc, + local_cpu_data->itc_freq); itc_clocksource = &clocksource_itc; } } @@ -411,7 +380,7 @@ static cycle_t itc_get_cycles(struct clocksource *cs) static struct irqaction timer_irqaction = { .handler = timer_interrupt, - .flags = IRQF_DISABLED | IRQF_IRQPOLL, + .flags = IRQF_IRQPOLL, .name = "timer" }; @@ -471,18 +440,16 @@ void update_vsyscall_tz(void) { } -void update_vsyscall(struct timespec *wall, struct timespec *wtm, +void update_vsyscall_old(struct timespec *wall, struct timespec *wtm, struct clocksource *c, u32 mult) { - unsigned long flags; - - write_seqlock_irqsave(&fsyscall_gtod_data.lock, flags); + write_seqcount_begin(&fsyscall_gtod_data.seq); /* copy fsyscall clock data */ fsyscall_gtod_data.clk_mask = c->mask; fsyscall_gtod_data.clk_mult = mult; fsyscall_gtod_data.clk_shift = c->shift; - fsyscall_gtod_data.clk_fsys_mmio = c->fsys_mmio; + fsyscall_gtod_data.clk_fsys_mmio = c->archdata.fsys_mmio; fsyscall_gtod_data.clk_cycle_last = c->cycle_last; /* copy kernel time structures */ @@ -499,6 +466,6 @@ void update_vsyscall(struct timespec *wall, struct timespec *wtm, fsyscall_gtod_data.monotonic_time.tv_sec++; } - write_sequnlock_irqrestore(&fsyscall_gtod_data.lock, flags); + write_seqcount_end(&fsyscall_gtod_data.seq); } diff --git a/arch/ia64/kernel/topology.c b/arch/ia64/kernel/topology.c index 0baa1bbb65f..f295f9abba4 100644 --- a/arch/ia64/kernel/topology.c +++ b/arch/ia64/kernel/topology.c @@ -22,6 +22,7 @@ #include <linux/bootmem.h> #include <linux/nodemask.h> #include <linux/notifier.h> +#include <linux/export.h> #include <asm/mmzone.h> #include <asm/numa.h> #include <asm/cpu.h> @@ -43,7 +44,7 @@ int __ref arch_register_cpu(int num) { #ifdef CONFIG_ACPI /* - * If CPEI can be re-targetted or if this is not + * If CPEI can be re-targeted or if this is not * CPEI target, then it is hotpluggable */ if (can_cpei_retarget() || !is_cpu_cpei_target(num)) @@ -134,11 +135,11 @@ struct cpu_cache_info { struct kobject kobj; }; -static struct cpu_cache_info all_cpu_cache_info[NR_CPUS] __cpuinitdata; +static struct cpu_cache_info all_cpu_cache_info[NR_CPUS]; #define LEAF_KOBJECT_PTR(x,y) (&all_cpu_cache_info[x].cache_leaves[y]) #ifdef CONFIG_SMP -static void __cpuinit cache_shared_cpu_map_setup( unsigned int cpu, +static void cache_shared_cpu_map_setup(unsigned int cpu, struct cache_info * this_leaf) { pal_cache_shared_info_t csi; @@ -173,7 +174,7 @@ static void __cpuinit cache_shared_cpu_map_setup( unsigned int cpu, &csi) == PAL_STATUS_SUCCESS); } #else -static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, +static void cache_shared_cpu_map_setup(unsigned int cpu, struct cache_info * this_leaf) { cpu_set(cpu, this_leaf->shared_cpu_map); @@ -219,7 +220,8 @@ static ssize_t show_shared_cpu_map(struct cache_info *this_leaf, char *buf) ssize_t len; cpumask_t shared_cpu_map; - cpus_and(shared_cpu_map, this_leaf->shared_cpu_map, cpu_online_map); + cpumask_and(&shared_cpu_map, + &this_leaf->shared_cpu_map, cpu_online_mask); len = cpumask_scnprintf(buf, NR_CPUS+1, &shared_cpu_map); len += sprintf(buf+len, "\n"); return len; @@ -273,7 +275,7 @@ static struct attribute * cache_default_attrs[] = { #define to_object(k) container_of(k, struct cache_info, kobj) #define to_attr(a) container_of(a, struct cache_attr, attr) -static ssize_t cache_show(struct kobject * kobj, struct attribute * attr, char * buf) +static ssize_t ia64_cache_show(struct kobject * kobj, struct attribute * attr, char * buf) { struct cache_attr *fattr = to_attr(attr); struct cache_info *this_leaf = to_object(kobj); @@ -284,7 +286,7 @@ static ssize_t cache_show(struct kobject * kobj, struct attribute * attr, char * } static const struct sysfs_ops cache_sysfs_ops = { - .show = cache_show + .show = ia64_cache_show }; static struct kobj_type cache_ktype = { @@ -296,7 +298,7 @@ static struct kobj_type cache_ktype_percpu_entry = { .sysfs_ops = &cache_sysfs_ops, }; -static void __cpuinit cpu_cache_sysfs_exit(unsigned int cpu) +static void cpu_cache_sysfs_exit(unsigned int cpu) { kfree(all_cpu_cache_info[cpu].cache_leaves); all_cpu_cache_info[cpu].cache_leaves = NULL; @@ -305,7 +307,7 @@ static void __cpuinit cpu_cache_sysfs_exit(unsigned int cpu) return; } -static int __cpuinit cpu_cache_sysfs_init(unsigned int cpu) +static int cpu_cache_sysfs_init(unsigned int cpu) { unsigned long i, levels, unique_caches; pal_cache_config_info_t cci; @@ -349,7 +351,7 @@ static int __cpuinit cpu_cache_sysfs_init(unsigned int cpu) } /* Add cache interface for CPU device */ -static int __cpuinit cache_add_dev(struct sys_device * sys_dev) +static int cache_add_dev(struct device *sys_dev) { unsigned int cpu = sys_dev->id; unsigned long i, j; @@ -399,7 +401,7 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev) } /* Remove cache interface for CPU device */ -static int __cpuinit cache_remove_dev(struct sys_device * sys_dev) +static int cache_remove_dev(struct device *sys_dev) { unsigned int cpu = sys_dev->id; unsigned long i; @@ -423,13 +425,13 @@ static int __cpuinit cache_remove_dev(struct sys_device * sys_dev) * When a cpu is hot-plugged, do a check and initiate * cache kobject if necessary */ -static int __cpuinit cache_cpu_callback(struct notifier_block *nfb, +static int cache_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { unsigned int cpu = (unsigned long)hcpu; - struct sys_device *sys_dev; + struct device *sys_dev; - sys_dev = get_cpu_sysdev(cpu); + sys_dev = get_cpu_device(cpu); switch (action) { case CPU_ONLINE: case CPU_ONLINE_FROZEN: @@ -443,7 +445,7 @@ static int __cpuinit cache_cpu_callback(struct notifier_block *nfb, return NOTIFY_OK; } -static struct notifier_block __cpuinitdata cache_cpu_notifier = +static struct notifier_block cache_cpu_notifier = { .notifier_call = cache_cpu_callback }; @@ -452,12 +454,16 @@ static int __init cache_sysfs_init(void) { int i; + cpu_notifier_register_begin(); + for_each_online_cpu(i) { - struct sys_device *sys_dev = get_cpu_sysdev((unsigned int)i); + struct device *sys_dev = get_cpu_device((unsigned int)i); cache_add_dev(sys_dev); } - register_hotcpu_notifier(&cache_cpu_notifier); + __register_hotcpu_notifier(&cache_cpu_notifier); + + cpu_notifier_register_done(); return 0; } diff --git a/arch/ia64/kernel/traps.c b/arch/ia64/kernel/traps.c index fd80e70018a..d3636e67a98 100644 --- a/arch/ia64/kernel/traps.c +++ b/arch/ia64/kernel/traps.c @@ -22,6 +22,7 @@ #include <asm/intrinsics.h> #include <asm/processor.h> #include <asm/uaccess.h> +#include <asm/setup.h> fpswa_interface_t *fpswa_interface; EXPORT_SYMBOL(fpswa_interface); @@ -71,7 +72,7 @@ die (const char *str, struct pt_regs *regs, long err) bust_spinlocks(0); die.lock_owner = -1; - add_taint(TAINT_DIE); + add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE); spin_unlock_irq(&die.lock); if (!regs) @@ -629,7 +630,7 @@ ia64_fault (unsigned long vector, unsigned long isr, unsigned long ifa, printk(KERN_ERR " iip - 0x%lx, ifa - 0x%lx, isr - 0x%lx\n", iip, ifa, isr); force_sig(SIGSEGV, current); - break; + return; case 46: printk(KERN_ERR "Unexpected IA-32 intercept trap (Trap 46)\n"); diff --git a/arch/ia64/kernel/uncached.c b/arch/ia64/kernel/uncached.c index c4696d217ce..20e8a9b21d7 100644 --- a/arch/ia64/kernel/uncached.c +++ b/arch/ia64/kernel/uncached.c @@ -23,9 +23,8 @@ #include <linux/gfp.h> #include <asm/page.h> #include <asm/pal.h> -#include <asm/system.h> #include <asm/pgtable.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <asm/tlbflush.h> #include <asm/sn/arch.h> @@ -99,7 +98,7 @@ static int uncached_add_chunk(struct uncached_pool *uc_pool, int nid) /* attempt to allocate a granule's worth of cached memory pages */ page = alloc_pages_exact_node(nid, - GFP_KERNEL | __GFP_ZERO | GFP_THISNODE, + GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE, IA64_GRANULE_SHIFT-PAGE_SHIFT); if (!page) { mutex_unlock(&uc_pool->add_chunk_mutex); diff --git a/arch/ia64/kernel/unwind.c b/arch/ia64/kernel/unwind.c index fed6afa2e8a..8f66195999e 100644 --- a/arch/ia64/kernel/unwind.c +++ b/arch/ia64/kernel/unwind.c @@ -41,7 +41,6 @@ #include <asm/ptrace_offsets.h> #include <asm/rse.h> #include <asm/sections.h> -#include <asm/system.h> #include <asm/uaccess.h> #include "entry.h" diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S index 5a4d044dcb1..84f8a52ac5a 100644 --- a/arch/ia64/kernel/vmlinux.lds.S +++ b/arch/ia64/kernel/vmlinux.lds.S @@ -1,7 +1,6 @@ #include <asm/cache.h> #include <asm/ptrace.h> -#include <asm/system.h> #include <asm/pgtable.h> #include <asm-generic/vmlinux.lds.h> @@ -183,12 +182,6 @@ SECTIONS { __start_gate_section = .; *(.data..gate) __stop_gate_section = .; -#ifdef CONFIG_XEN - . = ALIGN(PAGE_SIZE); - __xen_start_gate_section = .; - *(.data..gate.xen) - __xen_stop_gate_section = .; -#endif } /* * make sure the gate page doesn't expose @@ -198,7 +191,7 @@ SECTIONS { /* Per-cpu data: */ . = ALIGN(PERCPU_PAGE_SIZE); - PERCPU_VADDR(PERCPU_ADDR, :percpu) + PERCPU_VADDR(SMP_CACHE_BYTES, PERCPU_ADDR, :percpu) __phys_per_cpu_start = __per_cpu_load; /* * ensure percpu data fits @@ -209,6 +202,7 @@ SECTIONS { data : { } :data .data : AT(ADDR(.data) - LOAD_OFFSET) { + _sdata = .; INIT_TASK_DATA(PAGE_SIZE) CACHELINE_ALIGNED_DATA(SMP_CACHE_BYTES) READ_MOSTLY_DATA(SMP_CACHE_BYTES) |