diff options
Diffstat (limited to 'arch/x86/kernel')
61 files changed, 2193 insertions, 336 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 9b0a34e2cd7..cb648c84b32 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -29,10 +29,11 @@ obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o obj-y += syscall_$(BITS).o obj-$(CONFIG_X86_64) += vsyscall_64.o obj-$(CONFIG_X86_64) += vsyscall_emu_64.o +obj-$(CONFIG_SYSFS) += ksysfs.o obj-y += bootflag.o e820.o obj-y += pci-dma.o quirks.o topology.o kdebugfs.o obj-y += alternative.o i8253.o pci-nommu.o hw_breakpoint.o -obj-y += tsc.o io_delay.o rtc.o +obj-y += tsc.o tsc_msr.o io_delay.o rtc.o obj-y += pci-iommu_table.o obj-y += resource.o @@ -91,15 +92,6 @@ obj-$(CONFIG_PARAVIRT_CLOCK) += pvclock.o obj-$(CONFIG_PCSPKR_PLATFORM) += pcspeaker.o -obj-$(CONFIG_MICROCODE_EARLY) += microcode_core_early.o -obj-$(CONFIG_MICROCODE_INTEL_EARLY) += microcode_intel_early.o -obj-$(CONFIG_MICROCODE_INTEL_LIB) += microcode_intel_lib.o -microcode-y := microcode_core.o -microcode-$(CONFIG_MICROCODE_INTEL) += microcode_intel.o -microcode-$(CONFIG_MICROCODE_AMD) += microcode_amd.o -obj-$(CONFIG_MICROCODE_AMD_EARLY) += microcode_amd_early.o -obj-$(CONFIG_MICROCODE) += microcode.o - obj-$(CONFIG_X86_CHECK_BIOS_CORRUPTION) += check.o obj-$(CONFIG_SWIOTLB) += pci-swiotlb.o @@ -111,6 +103,7 @@ obj-$(CONFIG_EFI) += sysfb_efi.o obj-$(CONFIG_PERF_EVENTS) += perf_regs.o obj-$(CONFIG_TRACING) += tracepoint.o +obj-$(CONFIG_IOSF_MBI) += iosf_mbi.o ### # 64 bit specific files diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 6c0b43bd024..1dac94265b5 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -46,7 +46,6 @@ #include "sleep.h" /* To include x86_acpi_suspend_lowlevel */ static int __initdata acpi_force = 0; -u32 acpi_rsdt_forced; int acpi_disabled; EXPORT_SYMBOL(acpi_disabled); @@ -1034,9 +1033,7 @@ static int mp_config_acpi_gsi(struct device *dev, u32 gsi, int trigger, if (!acpi_ioapic) return 0; - if (!dev) - return 0; - if (dev->bus != &pci_bus_type) + if (!dev || !dev_is_pci(dev)) return 0; pdev = to_pci_dev(dev); @@ -1564,7 +1561,7 @@ static int __init parse_acpi(char *arg) } /* acpi=rsdt use RSDT instead of XSDT */ else if (strcmp(arg, "rsdt") == 0) { - acpi_rsdt_forced = 1; + acpi_gbl_do_not_use_xsdt = TRUE; } /* "acpi=noirq" disables ACPI interrupt routing */ else if (strcmp(arg, "noirq") == 0) { diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c index d2b7f27781b..e69182fd01c 100644 --- a/arch/x86/kernel/acpi/cstate.c +++ b/arch/x86/kernel/acpi/cstate.c @@ -150,29 +150,6 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu, } EXPORT_SYMBOL_GPL(acpi_processor_ffh_cstate_probe); -/* - * This uses new MONITOR/MWAIT instructions on P4 processors with PNI, - * which can obviate IPI to trigger checking of need_resched. - * We execute MONITOR against need_resched and enter optimized wait state - * through MWAIT. Whenever someone changes need_resched, we would be woken - * up from MWAIT (without an IPI). - * - * New with Core Duo processors, MWAIT can take some hints based on CPU - * capability. - */ -void mwait_idle_with_hints(unsigned long ax, unsigned long cx) -{ - if (!need_resched()) { - if (this_cpu_has(X86_FEATURE_CLFLUSH_MONITOR)) - clflush((void *)¤t_thread_info()->flags); - - __monitor((void *)¤t_thread_info()->flags, 0, 0); - smp_mb(); - if (!need_resched()) - __mwait(ax, cx); - } -} - void acpi_processor_ffh_cstate_enter(struct acpi_processor_cx *cx) { unsigned int cpu = smp_processor_id(); diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index d278736bf77..7f26c9a70a9 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -75,6 +75,13 @@ unsigned int max_physical_apicid; physid_mask_t phys_cpu_present_map; /* + * Processor to be disabled specified by kernel parameter + * disable_cpu_apicid=<int>, mostly used for the kdump 2nd kernel to + * avoid undefined behaviour caused by sending INIT from AP to BSP. + */ +static unsigned int disabled_cpu_apicid __read_mostly = BAD_APICID; + +/* * Map cpu index to physical APIC ID */ DEFINE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid, BAD_APICID); @@ -1968,7 +1975,7 @@ __visible void smp_trace_spurious_interrupt(struct pt_regs *regs) */ static inline void __smp_error_interrupt(struct pt_regs *regs) { - u32 v0, v1; + u32 v; u32 i = 0; static const char * const error_interrupt_reason[] = { "Send CS error", /* APIC Error Bit 0 */ @@ -1982,21 +1989,20 @@ static inline void __smp_error_interrupt(struct pt_regs *regs) }; /* First tickle the hardware, only then report what went on. -- REW */ - v0 = apic_read(APIC_ESR); apic_write(APIC_ESR, 0); - v1 = apic_read(APIC_ESR); + v = apic_read(APIC_ESR); ack_APIC_irq(); atomic_inc(&irq_err_count); - apic_printk(APIC_DEBUG, KERN_DEBUG "APIC error on CPU%d: %02x(%02x)", - smp_processor_id(), v0 , v1); + apic_printk(APIC_DEBUG, KERN_DEBUG "APIC error on CPU%d: %02x", + smp_processor_id(), v); - v1 = v1 & 0xff; - while (v1) { - if (v1 & 0x1) + v &= 0xff; + while (v) { + if (v & 0x1) apic_printk(APIC_DEBUG, KERN_CONT " : %s", error_interrupt_reason[i]); i++; - v1 >>= 1; + v >>= 1; } apic_printk(APIC_DEBUG, KERN_CONT "\n"); @@ -2115,6 +2121,39 @@ int generic_processor_info(int apicid, int version) phys_cpu_present_map); /* + * boot_cpu_physical_apicid is designed to have the apicid + * returned by read_apic_id(), i.e, the apicid of the + * currently booting-up processor. However, on some platforms, + * it is temporarily modified by the apicid reported as BSP + * through MP table. Concretely: + * + * - arch/x86/kernel/mpparse.c: MP_processor_info() + * - arch/x86/mm/amdtopology.c: amd_numa_init() + * - arch/x86/platform/visws/visws_quirks.c: MP_processor_info() + * + * This function is executed with the modified + * boot_cpu_physical_apicid. So, disabled_cpu_apicid kernel + * parameter doesn't work to disable APs on kdump 2nd kernel. + * + * Since fixing handling of boot_cpu_physical_apicid requires + * another discussion and tests on each platform, we leave it + * for now and here we use read_apic_id() directly in this + * function, generic_processor_info(). + */ + if (disabled_cpu_apicid != BAD_APICID && + disabled_cpu_apicid != read_apic_id() && + disabled_cpu_apicid == apicid) { + int thiscpu = num_processors + disabled_cpus; + + pr_warning("APIC: Disabling requested cpu." + " Processor %d/0x%x ignored.\n", + thiscpu, apicid); + + disabled_cpus++; + return -ENODEV; + } + + /* * If boot cpu has not been detected yet, then only allow upto * nr_cpu_ids - 1 processors and keep one slot free for boot cpu */ @@ -2592,3 +2631,12 @@ static int __init lapic_insert_resource(void) * that is using request_resource */ late_initcall(lapic_insert_resource); + +static int __init apic_set_disabled_cpu_apicid(char *arg) +{ + if (!arg || !get_option(&arg, &disabled_cpu_apicid)) + return -EINVAL; + + return 0; +} +early_param("disable_cpu_apicid", apic_set_disabled_cpu_apicid); diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index 00c77cf78e9..2c621a6b901 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -14,16 +14,13 @@ #include <linux/string.h> #include <linux/kernel.h> #include <linux/ctype.h> -#include <linux/init.h> #include <linux/hardirq.h> #include <linux/module.h> #include <asm/smp.h> #include <asm/apic.h> #include <asm/ipi.h> -#ifdef CONFIG_ACPI -#include <acpi/acpi_bus.h> -#endif +#include <linux/acpi.h> static struct apic apic_physflat; static struct apic apic_flat; diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index e145f28b409..191ce75c0e5 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -15,7 +15,6 @@ #include <linux/string.h> #include <linux/kernel.h> #include <linux/ctype.h> -#include <linux/init.h> #include <linux/errno.h> #include <asm/fixmap.h> #include <asm/mpspec.h> diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index e63a5bd2a78..6ad4658de70 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -37,9 +37,6 @@ #include <linux/kthread.h> #include <linux/jiffies.h> /* time_after() */ #include <linux/slab.h> -#ifdef CONFIG_ACPI -#include <acpi/acpi_bus.h> -#endif #include <linux/bootmem.h> #include <linux/dmar.h> #include <linux/hpet.h> @@ -1142,9 +1139,10 @@ next: if (test_bit(vector, used_vectors)) goto next; - for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask) - if (per_cpu(vector_irq, new_cpu)[vector] != -1) + for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask) { + if (per_cpu(vector_irq, new_cpu)[vector] > VECTOR_UNDEFINED) goto next; + } /* Found one! */ current_vector = vector; current_offset = offset; @@ -1183,7 +1181,7 @@ static void __clear_irq_vector(int irq, struct irq_cfg *cfg) vector = cfg->vector; for_each_cpu_and(cpu, cfg->domain, cpu_online_mask) - per_cpu(vector_irq, cpu)[vector] = -1; + per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED; cfg->vector = 0; cpumask_clear(cfg->domain); @@ -1191,11 +1189,10 @@ static void __clear_irq_vector(int irq, struct irq_cfg *cfg) if (likely(!cfg->move_in_progress)) return; for_each_cpu_and(cpu, cfg->old_domain, cpu_online_mask) { - for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; - vector++) { + for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { if (per_cpu(vector_irq, cpu)[vector] != irq) continue; - per_cpu(vector_irq, cpu)[vector] = -1; + per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED; break; } } @@ -1228,12 +1225,12 @@ void __setup_vector_irq(int cpu) /* Mark the free vectors */ for (vector = 0; vector < NR_VECTORS; ++vector) { irq = per_cpu(vector_irq, cpu)[vector]; - if (irq < 0) + if (irq <= VECTOR_UNDEFINED) continue; cfg = irq_cfg(irq); if (!cpumask_test_cpu(cpu, cfg->domain)) - per_cpu(vector_irq, cpu)[vector] = -1; + per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED; } raw_spin_unlock(&vector_lock); } @@ -2202,13 +2199,13 @@ asmlinkage void smp_irq_move_cleanup_interrupt(void) me = smp_processor_id(); for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { - unsigned int irq; + int irq; unsigned int irr; struct irq_desc *desc; struct irq_cfg *cfg; irq = __this_cpu_read(vector_irq[vector]); - if (irq == -1) + if (irq <= VECTOR_UNDEFINED) continue; desc = irq_to_desc(irq); diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c index 7434d8556d0..62071569bd5 100644 --- a/arch/x86/kernel/apic/ipi.c +++ b/arch/x86/kernel/apic/ipi.c @@ -1,6 +1,5 @@ #include <linux/cpumask.h> #include <linux/interrupt.h> -#include <linux/init.h> #include <linux/mm.h> #include <linux/delay.h> diff --git a/arch/x86/kernel/apic/summit_32.c b/arch/x86/kernel/apic/summit_32.c index 77c95c0e1bf..00146f9b025 100644 --- a/arch/x86/kernel/apic/summit_32.c +++ b/arch/x86/kernel/apic/summit_32.c @@ -29,7 +29,6 @@ #define pr_fmt(fmt) "summit: %s: " fmt, __func__ #include <linux/mm.h> -#include <linux/init.h> #include <asm/io.h> #include <asm/bios_ebda.h> diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index 140e29db478..cac85ee6913 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -3,7 +3,6 @@ #include <linux/string.h> #include <linux/kernel.h> #include <linux/ctype.h> -#include <linux/init.h> #include <linux/dmar.h> #include <linux/cpu.h> diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index 562a76d433c..de231e328ca 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -3,7 +3,6 @@ #include <linux/string.h> #include <linux/kernel.h> #include <linux/ctype.h> -#include <linux/init.h> #include <linux/dmar.h> #include <asm/smp.h> diff --git a/arch/x86/kernel/check.c b/arch/x86/kernel/check.c index e2dbcb7dabd..83a7995625a 100644 --- a/arch/x86/kernel/check.c +++ b/arch/x86/kernel/check.c @@ -91,7 +91,7 @@ void __init setup_bios_corruption_check(void) corruption_check_size = round_up(corruption_check_size, PAGE_SIZE); - for_each_free_mem_range(i, MAX_NUMNODES, &start, &end, NULL) { + for_each_free_mem_range(i, NUMA_NO_NODE, &start, &end, NULL) { start = clamp_t(phys_addr_t, round_up(start, PAGE_SIZE), PAGE_SIZE, corruption_check_size); end = clamp_t(phys_addr_t, round_down(end, PAGE_SIZE), diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 47b56a7e99c..7fd54f09b01 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -36,12 +36,13 @@ obj-$(CONFIG_CPU_SUP_AMD) += perf_event_amd_iommu.o endif obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_p6.o perf_event_knc.o perf_event_p4.o obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o -obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_uncore.o +obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_uncore.o perf_event_intel_rapl.o endif obj-$(CONFIG_X86_MCE) += mcheck/ obj-$(CONFIG_MTRR) += mtrr/ +obj-$(CONFIG_MICROCODE) += microcode/ obj-$(CONFIG_X86_LOCAL_APIC) += perfctr-watchdog.o perf_event_amd_ibs.o diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index bca023bdd6b..d3153e281d7 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -1,5 +1,4 @@ #include <linux/export.h> -#include <linux/init.h> #include <linux/bitops.h> #include <linux/elf.h> #include <linux/mm.h> @@ -487,7 +486,7 @@ static void early_init_amd(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); if (!check_tsc_unstable()) - sched_clock_stable = 1; + set_sched_clock_stable(); } #ifdef CONFIG_X86_64 @@ -508,6 +507,16 @@ static void early_init_amd(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_EXTD_APICID); } #endif + + /* F16h erratum 793, CVE-2013-6885 */ + if (c->x86 == 0x16 && c->x86_model <= 0xf) { + u64 val; + + rdmsrl(MSR_AMD64_LS_CFG, val); + if (!(val & BIT(15))) + wrmsrl(MSR_AMD64_LS_CFG, val | BIT(15)); + } + } static const int amd_erratum_383[]; @@ -790,14 +799,10 @@ static void cpu_detect_tlb_amd(struct cpuinfo_x86 *c) } /* Handle DTLB 2M and 4M sizes, fall back to L1 if L2 is disabled */ - if (!((eax >> 16) & mask)) { - u32 a, b, c, d; - - cpuid(0x80000005, &a, &b, &c, &d); - tlb_lld_2m[ENTRIES] = (a >> 16) & 0xff; - } else { + if (!((eax >> 16) & mask)) + tlb_lld_2m[ENTRIES] = (cpuid_eax(0x80000005) >> 16) & 0xff; + else tlb_lld_2m[ENTRIES] = (eax >> 16) & mask; - } /* a 4M entry uses two 2M entries */ tlb_lld_4m[ENTRIES] = tlb_lld_2m[ENTRIES] >> 1; diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index 8d5652dc99d..8779edab684 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -1,6 +1,5 @@ #include <linux/bitops.h> #include <linux/kernel.h> -#include <linux/init.h> #include <asm/processor.h> #include <asm/e820.h> diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 6abc172b825..24b6fd10625 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -472,6 +472,7 @@ u16 __read_mostly tlb_lli_4m[NR_INFO]; u16 __read_mostly tlb_lld_4k[NR_INFO]; u16 __read_mostly tlb_lld_2m[NR_INFO]; u16 __read_mostly tlb_lld_4m[NR_INFO]; +u16 __read_mostly tlb_lld_1g[NR_INFO]; /* * tlb_flushall_shift shows the balance point in replacing cr3 write @@ -486,13 +487,13 @@ void cpu_detect_tlb(struct cpuinfo_x86 *c) if (this_cpu->c_detect_tlb) this_cpu->c_detect_tlb(c); - printk(KERN_INFO "Last level iTLB entries: 4KB %d, 2MB %d, 4MB %d\n" \ - "Last level dTLB entries: 4KB %d, 2MB %d, 4MB %d\n" \ + printk(KERN_INFO "Last level iTLB entries: 4KB %d, 2MB %d, 4MB %d\n" + "Last level dTLB entries: 4KB %d, 2MB %d, 4MB %d, 1GB %d\n" "tlb_flushall_shift: %d\n", tlb_lli_4k[ENTRIES], tlb_lli_2m[ENTRIES], tlb_lli_4m[ENTRIES], tlb_lld_4k[ENTRIES], tlb_lld_2m[ENTRIES], tlb_lld_4m[ENTRIES], - tlb_flushall_shift); + tlb_lld_1g[ENTRIES], tlb_flushall_shift); } void detect_ht(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index d0969c75ab5..aaf152e7963 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -1,4 +1,3 @@ -#include <linux/init.h> #include <linux/bitops.h> #include <linux/delay.h> #include <linux/pci.h> diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index dc1ec0dff93..3db61c644e4 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -1,4 +1,3 @@ -#include <linux/init.h> #include <linux/kernel.h> #include <linux/string.h> @@ -93,7 +92,7 @@ static void early_init_intel(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); if (!check_tsc_unstable()) - sched_clock_stable = 1; + set_sched_clock_stable(); } /* Penwell and Cloverview have the TSC which doesn't sleep on S3 */ @@ -387,7 +386,8 @@ static void init_intel(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_PEBS); } - if (c->x86 == 6 && c->x86_model == 29 && cpu_has_clflush) + if (c->x86 == 6 && cpu_has_clflush && + (c->x86_model == 29 || c->x86_model == 46 || c->x86_model == 47)) set_cpu_cap(c, X86_FEATURE_CLFLUSH_MONITOR); #ifdef CONFIG_X86_64 @@ -505,6 +505,7 @@ static unsigned int intel_size_cache(struct cpuinfo_x86 *c, unsigned int size) #define TLB_DATA0_2M_4M 0x23 #define STLB_4K 0x41 +#define STLB_4K_2M 0x42 static const struct _tlb_table intel_tlb_table[] = { { 0x01, TLB_INST_4K, 32, " TLB_INST 4 KByte pages, 4-way set associative" }, @@ -525,13 +526,20 @@ static const struct _tlb_table intel_tlb_table[] = { { 0x5b, TLB_DATA_4K_4M, 64, " TLB_DATA 4 KByte and 4 MByte pages" }, { 0x5c, TLB_DATA_4K_4M, 128, " TLB_DATA 4 KByte and 4 MByte pages" }, { 0x5d, TLB_DATA_4K_4M, 256, " TLB_DATA 4 KByte and 4 MByte pages" }, + { 0x61, TLB_INST_4K, 48, " TLB_INST 4 KByte pages, full associative" }, + { 0x63, TLB_DATA_1G, 4, " TLB_DATA 1 GByte pages, 4-way set associative" }, + { 0x76, TLB_INST_2M_4M, 8, " TLB_INST 2-MByte or 4-MByte pages, fully associative" }, { 0xb0, TLB_INST_4K, 128, " TLB_INST 4 KByte pages, 4-way set associative" }, { 0xb1, TLB_INST_2M_4M, 4, " TLB_INST 2M pages, 4-way, 8 entries or 4M pages, 4-way entries" }, { 0xb2, TLB_INST_4K, 64, " TLB_INST 4KByte pages, 4-way set associative" }, { 0xb3, TLB_DATA_4K, 128, " TLB_DATA 4 KByte pages, 4-way set associative" }, { 0xb4, TLB_DATA_4K, 256, " TLB_DATA 4 KByte pages, 4-way associative" }, + { 0xb5, TLB_INST_4K, 64, " TLB_INST 4 KByte pages, 8-way set ssociative" }, + { 0xb6, TLB_INST_4K, 128, " TLB_INST 4 KByte pages, 8-way set ssociative" }, { 0xba, TLB_DATA_4K, 64, " TLB_DATA 4 KByte pages, 4-way associative" }, { 0xc0, TLB_DATA_4K_4M, 8, " TLB_DATA 4 KByte and 4 MByte pages, 4-way associative" }, + { 0xc1, STLB_4K_2M, 1024, " STLB 4 KByte and 2 MByte pages, 8-way associative" }, + { 0xc2, TLB_DATA_2M_4M, 16, " DTLB 2 MByte/4MByte pages, 4-way associative" }, { 0xca, STLB_4K, 512, " STLB 4 KByte pages, 4-way associative" }, { 0x00, 0, 0 } }; @@ -557,6 +565,20 @@ static void intel_tlb_lookup(const unsigned char desc) if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries) tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries; break; + case STLB_4K_2M: + if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries) + tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries; + if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries) + tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries; + if (tlb_lli_2m[ENTRIES] < intel_tlb_table[k].entries) + tlb_lli_2m[ENTRIES] = intel_tlb_table[k].entries; + if (tlb_lld_2m[ENTRIES] < intel_tlb_table[k].entries) + tlb_lld_2m[ENTRIES] = intel_tlb_table[k].entries; + if (tlb_lli_4m[ENTRIES] < intel_tlb_table[k].entries) + tlb_lli_4m[ENTRIES] = intel_tlb_table[k].entries; + if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries) + tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries; + break; case TLB_INST_ALL: if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries) tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries; @@ -602,6 +624,10 @@ static void intel_tlb_lookup(const unsigned char desc) if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries) tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries; break; + case TLB_DATA_1G: + if (tlb_lld_1g[ENTRIES] < intel_tlb_table[k].entries) + tlb_lld_1g[ENTRIES] = intel_tlb_table[k].entries; + break; } } diff --git a/arch/x86/kernel/cpu/mcheck/mce-apei.c b/arch/x86/kernel/cpu/mcheck/mce-apei.c index de8b60a53f6..a1aef953315 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-apei.c +++ b/arch/x86/kernel/cpu/mcheck/mce-apei.c @@ -33,22 +33,28 @@ #include <linux/acpi.h> #include <linux/cper.h> #include <acpi/apei.h> +#include <acpi/ghes.h> #include <asm/mce.h> #include "mce-internal.h" -void apei_mce_report_mem_error(int corrected, struct cper_sec_mem_err *mem_err) +void apei_mce_report_mem_error(int severity, struct cper_sec_mem_err *mem_err) { struct mce m; - /* Only corrected MC is reported */ - if (!corrected || !(mem_err->validation_bits & CPER_MEM_VALID_PA)) + if (!(mem_err->validation_bits & CPER_MEM_VALID_PA)) return; mce_setup(&m); m.bank = 1; - /* Fake a memory read corrected error with unknown channel */ + /* Fake a memory read error with unknown channel */ m.status = MCI_STATUS_VAL | MCI_STATUS_EN | MCI_STATUS_ADDRV | 0x9f; + + if (severity >= GHES_SEV_RECOVERABLE) + m.status |= MCI_STATUS_UC; + if (severity >= GHES_SEV_PANIC) + m.status |= MCI_STATUS_PCC; + m.addr = mem_err->physical_addr; mce_log(&m); mce_notify_irq(); diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index b3218cdee95..4d5419b249d 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -1638,15 +1638,15 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) static void mce_start_timer(unsigned int cpu, struct timer_list *t) { - unsigned long iv = mce_adjust_timer(check_interval * HZ); - - __this_cpu_write(mce_next_interval, iv); + unsigned long iv = check_interval * HZ; if (mca_cfg.ignore_ce || !iv) return; + per_cpu(mce_next_interval, cpu) = iv; + t->expires = round_jiffies(jiffies + iv); - add_timer_on(t, smp_processor_id()); + add_timer_on(t, cpu); } static void __mcheck_cpu_init_timer(void) @@ -2272,8 +2272,10 @@ static int mce_device_create(unsigned int cpu) dev->release = &mce_device_release; err = device_register(dev); - if (err) + if (err) { + put_device(dev); return err; + } for (i = 0; mce_device_attrs[i]; i++) { err = device_create_file(dev, mce_device_attrs[i]); diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c index 4cfe0458ca6..fb6156fee6f 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c @@ -6,7 +6,6 @@ */ #include <linux/gfp.h> -#include <linux/init.h> #include <linux/interrupt.h> #include <linux/percpu.h> #include <linux/sched.h> diff --git a/arch/x86/kernel/cpu/mcheck/p5.c b/arch/x86/kernel/cpu/mcheck/p5.c index 1c044b1ccc5..a3042989398 100644 --- a/arch/x86/kernel/cpu/mcheck/p5.c +++ b/arch/x86/kernel/cpu/mcheck/p5.c @@ -5,7 +5,6 @@ #include <linux/interrupt.h> #include <linux/kernel.h> #include <linux/types.h> -#include <linux/init.h> #include <linux/smp.h> #include <asm/processor.h> diff --git a/arch/x86/kernel/cpu/mcheck/winchip.c b/arch/x86/kernel/cpu/mcheck/winchip.c index e9a701aecaa..7dc5564d0cd 100644 --- a/arch/x86/kernel/cpu/mcheck/winchip.c +++ b/arch/x86/kernel/cpu/mcheck/winchip.c @@ -5,7 +5,6 @@ #include <linux/interrupt.h> #include <linux/kernel.h> #include <linux/types.h> -#include <linux/init.h> #include <asm/processor.h> #include <asm/mce.h> diff --git a/arch/x86/kernel/cpu/microcode/Makefile b/arch/x86/kernel/cpu/microcode/Makefile new file mode 100644 index 00000000000..285c85427c3 --- /dev/null +++ b/arch/x86/kernel/cpu/microcode/Makefile @@ -0,0 +1,7 @@ +microcode-y := core.o +obj-$(CONFIG_MICROCODE) += microcode.o +microcode-$(CONFIG_MICROCODE_INTEL) += intel.o intel_lib.o +microcode-$(CONFIG_MICROCODE_AMD) += amd.o +obj-$(CONFIG_MICROCODE_EARLY) += core_early.o +obj-$(CONFIG_MICROCODE_INTEL_EARLY) += intel_early.o +obj-$(CONFIG_MICROCODE_AMD_EARLY) += amd_early.o diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/cpu/microcode/amd.c index c3d4cc972ec..8fffd845e22 100644 --- a/arch/x86/kernel/microcode_amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -182,10 +182,10 @@ int __apply_microcode_amd(struct microcode_amd *mc_amd) { u32 rev, dummy; - wrmsrl(MSR_AMD64_PATCH_LOADER, (u64)(long)&mc_amd->hdr.data_code); + native_wrmsrl(MSR_AMD64_PATCH_LOADER, (u64)(long)&mc_amd->hdr.data_code); /* verify patch application was successful */ - rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); + native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); if (rev != mc_amd->hdr.patch_id) return -1; @@ -332,6 +332,9 @@ static int verify_and_add_patch(u8 family, u8 *fw, unsigned int leftover) patch->patch_id = mc_hdr->patch_id; patch->equiv_cpu = proc_id; + pr_debug("%s: Added patch_id: 0x%08x, proc_id: 0x%04x\n", + __func__, patch->patch_id, proc_id); + /* ... and add to cache. */ update_cache(patch); @@ -390,9 +393,9 @@ enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size) if (cpu_data(smp_processor_id()).cpu_index == boot_cpu_data.cpu_index) { struct ucode_patch *p = find_patch(smp_processor_id()); if (p) { - memset(amd_bsp_mpb, 0, MPB_MAX_SIZE); - memcpy(amd_bsp_mpb, p->data, min_t(u32, ksize(p->data), - MPB_MAX_SIZE)); + memset(amd_ucode_patch, 0, PATCH_MAX_SIZE); + memcpy(amd_ucode_patch, p->data, min_t(u32, ksize(p->data), + PATCH_MAX_SIZE)); } } #endif @@ -430,7 +433,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device, if (c->x86 >= 0x15) snprintf(fw_name, sizeof(fw_name), "amd-ucode/microcode_amd_fam%.2xh.bin", c->x86); - if (request_firmware(&fw, (const char *)fw_name, device)) { + if (request_firmware_direct(&fw, (const char *)fw_name, device)) { pr_debug("failed to load file %s\n", fw_name); goto out; } diff --git a/arch/x86/kernel/microcode_amd_early.c b/arch/x86/kernel/cpu/microcode/amd_early.c index 6073104ccaa..8384c0fa206 100644 --- a/arch/x86/kernel/microcode_amd_early.c +++ b/arch/x86/kernel/cpu/microcode/amd_early.c @@ -2,6 +2,7 @@ * Copyright (C) 2013 Advanced Micro Devices, Inc. * * Author: Jacob Shin <jacob.shin@amd.com> + * Fixes: Borislav Petkov <bp@suse.de> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -15,10 +16,18 @@ #include <asm/setup.h> #include <asm/microcode_amd.h> -static bool ucode_loaded; +/* + * This points to the current valid container of microcode patches which we will + * save from the initrd before jettisoning its contents. + */ +static u8 *container; +static size_t container_size; + static u32 ucode_new_rev; -static unsigned long ucode_offset; -static size_t ucode_size; +u8 amd_ucode_patch[PATCH_MAX_SIZE]; +static u16 this_equiv_id; + +struct cpio_data ucode_cpio; /* * Microcode patch container file is prepended to the initrd in cpio format. @@ -32,9 +41,6 @@ static struct cpio_data __init find_ucode_in_initrd(void) char *path; void *start; size_t size; - unsigned long *uoffset; - size_t *usize; - struct cpio_data cd; #ifdef CONFIG_X86_32 struct boot_params *p; @@ -47,30 +53,50 @@ static struct cpio_data __init find_ucode_in_initrd(void) path = (char *)__pa_nodebug(ucode_path); start = (void *)p->hdr.ramdisk_image; size = p->hdr.ramdisk_size; - uoffset = (unsigned long *)__pa_nodebug(&ucode_offset); - usize = (size_t *)__pa_nodebug(&ucode_size); #else path = ucode_path; start = (void *)(boot_params.hdr.ramdisk_image + PAGE_OFFSET); size = boot_params.hdr.ramdisk_size; - uoffset = &ucode_offset; - usize = &ucode_size; #endif - cd = find_cpio_data(path, start, size, &offset); - if (!cd.data) - return cd; + return find_cpio_data(path, start, size, &offset); +} - if (*(u32 *)cd.data != UCODE_MAGIC) { - cd.data = NULL; - cd.size = 0; - return cd; - } +static size_t compute_container_size(u8 *data, u32 total_size) +{ + size_t size = 0; + u32 *header = (u32 *)data; - *uoffset = (u8 *)cd.data - (u8 *)start; - *usize = cd.size; + if (header[0] != UCODE_MAGIC || + header[1] != UCODE_EQUIV_CPU_TABLE_TYPE || /* type */ + header[2] == 0) /* size */ + return size; - return cd; + size = header[2] + CONTAINER_HDR_SZ; + total_size -= size; + data += size; + + while (total_size) { + u16 patch_size; + + header = (u32 *)data; + + if (header[0] != UCODE_UCODE_TYPE) + break; + + /* + * Sanity-check patch size. + */ + patch_size = header[1]; + if (patch_size > PATCH_MAX_SIZE) + break; + + size += patch_size + SECTION_HDR_SIZE; + data += patch_size + SECTION_HDR_SIZE; + total_size -= patch_size + SECTION_HDR_SIZE; + } + + return size; } /* @@ -85,23 +111,22 @@ static struct cpio_data __init find_ucode_in_initrd(void) static void apply_ucode_in_initrd(void *ucode, size_t size) { struct equiv_cpu_entry *eq; + size_t *cont_sz; u32 *header; - u8 *data; + u8 *data, **cont; u16 eq_id = 0; int offset, left; - u32 rev, eax; + u32 rev, eax, ebx, ecx, edx; u32 *new_rev; - unsigned long *uoffset; - size_t *usize; #ifdef CONFIG_X86_32 new_rev = (u32 *)__pa_nodebug(&ucode_new_rev); - uoffset = (unsigned long *)__pa_nodebug(&ucode_offset); - usize = (size_t *)__pa_nodebug(&ucode_size); + cont_sz = (size_t *)__pa_nodebug(&container_size); + cont = (u8 **)__pa_nodebug(&container); #else new_rev = &ucode_new_rev; - uoffset = &ucode_offset; - usize = &ucode_size; + cont_sz = &container_size; + cont = &container; #endif data = ucode; @@ -109,23 +134,37 @@ static void apply_ucode_in_initrd(void *ucode, size_t size) header = (u32 *)data; /* find equiv cpu table */ - - if (header[1] != UCODE_EQUIV_CPU_TABLE_TYPE || /* type */ + if (header[0] != UCODE_MAGIC || + header[1] != UCODE_EQUIV_CPU_TABLE_TYPE || /* type */ header[2] == 0) /* size */ return; - eax = cpuid_eax(0x00000001); + eax = 0x00000001; + ecx = 0; + native_cpuid(&eax, &ebx, &ecx, &edx); while (left > 0) { eq = (struct equiv_cpu_entry *)(data + CONTAINER_HDR_SZ); + *cont = data; + + /* Advance past the container header */ offset = header[2] + CONTAINER_HDR_SZ; data += offset; left -= offset; eq_id = find_equiv_id(eq, eax); - if (eq_id) + if (eq_id) { + this_equiv_id = eq_id; + *cont_sz = compute_container_size(*cont, left + offset); + + /* + * truncate how much we need to iterate over in the + * ucode update loop below + */ + left = *cont_sz - offset; break; + } /* * support multiple container files appended together. if this @@ -145,19 +184,18 @@ static void apply_ucode_in_initrd(void *ucode, size_t size) /* mark where the next microcode container file starts */ offset = data - (u8 *)ucode; - *uoffset += offset; - *usize -= offset; ucode = data; } if (!eq_id) { - *usize = 0; + *cont = NULL; + *cont_sz = 0; return; } /* find ucode and update if needed */ - rdmsr(MSR_AMD64_PATCH_LEVEL, rev, eax); + native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, eax); while (left > 0) { struct microcode_amd *mc; @@ -168,73 +206,83 @@ static void apply_ucode_in_initrd(void *ucode, size_t size) break; mc = (struct microcode_amd *)(data + SECTION_HDR_SIZE); - if (eq_id == mc->hdr.processor_rev_id && rev < mc->hdr.patch_id) - if (__apply_microcode_amd(mc) == 0) { + + if (eq_id == mc->hdr.processor_rev_id && rev < mc->hdr.patch_id) { + + if (!__apply_microcode_amd(mc)) { rev = mc->hdr.patch_id; *new_rev = rev; + + /* save ucode patch */ + memcpy(amd_ucode_patch, mc, + min_t(u32, header[1], PATCH_MAX_SIZE)); } + } offset = header[1] + SECTION_HDR_SIZE; data += offset; left -= offset; } - - /* mark where this microcode container file ends */ - offset = *usize - (data - (u8 *)ucode); - *usize -= offset; - - if (!(*new_rev)) - *usize = 0; } void __init load_ucode_amd_bsp(void) { - struct cpio_data cd = find_ucode_in_initrd(); - if (!cd.data) + struct cpio_data cp; + void **data; + size_t *size; + +#ifdef CONFIG_X86_32 + data = (void **)__pa_nodebug(&ucode_cpio.data); + size = (size_t *)__pa_nodebug(&ucode_cpio.size); +#else + data = &ucode_cpio.data; + size = &ucode_cpio.size; +#endif + + cp = find_ucode_in_initrd(); + if (!cp.data) return; - apply_ucode_in_initrd(cd.data, cd.size); + *data = cp.data; + *size = cp.size; + + apply_ucode_in_initrd(cp.data, cp.size); } #ifdef CONFIG_X86_32 -u8 amd_bsp_mpb[MPB_MAX_SIZE]; - /* * On 32-bit, since AP's early load occurs before paging is turned on, we * cannot traverse cpu_equiv_table and pcache in kernel heap memory. So during * cold boot, AP will apply_ucode_in_initrd() just like the BSP. During - * save_microcode_in_initrd_amd() BSP's patch is copied to amd_bsp_mpb, which - * is used upon resume from suspend. + * save_microcode_in_initrd_amd() BSP's patch is copied to amd_ucode_patch, + * which is used upon resume from suspend. */ void load_ucode_amd_ap(void) { struct microcode_amd *mc; - unsigned long *initrd; - unsigned long *uoffset; size_t *usize; - void *ucode; + void **ucode; - mc = (struct microcode_amd *)__pa(amd_bsp_mpb); + mc = (struct microcode_amd *)__pa(amd_ucode_patch); if (mc->hdr.patch_id && mc->hdr.processor_rev_id) { __apply_microcode_amd(mc); return; } - initrd = (unsigned long *)__pa(&initrd_start); - uoffset = (unsigned long *)__pa(&ucode_offset); - usize = (size_t *)__pa(&ucode_size); + ucode = (void *)__pa_nodebug(&container); + usize = (size_t *)__pa_nodebug(&container_size); - if (!*usize || !*initrd) + if (!*ucode || !*usize) return; - ucode = (void *)((unsigned long)__pa(*initrd) + *uoffset); - apply_ucode_in_initrd(ucode, *usize); + apply_ucode_in_initrd(*ucode, *usize); } static void __init collect_cpu_sig_on_bsp(void *arg) { unsigned int cpu = smp_processor_id(); struct ucode_cpu_info *uci = ucode_cpu_info + cpu; + uci->cpu_sig.sig = cpuid_eax(0x00000001); } #else @@ -242,36 +290,54 @@ void load_ucode_amd_ap(void) { unsigned int cpu = smp_processor_id(); struct ucode_cpu_info *uci = ucode_cpu_info + cpu; + struct equiv_cpu_entry *eq; + struct microcode_amd *mc; u32 rev, eax; + u16 eq_id; + + /* Exit if called on the BSP. */ + if (!cpu) + return; + + if (!container) + return; rdmsr(MSR_AMD64_PATCH_LEVEL, rev, eax); - eax = cpuid_eax(0x00000001); uci->cpu_sig.rev = rev; uci->cpu_sig.sig = eax; - if (cpu && !ucode_loaded) { - void *ucode; + eax = cpuid_eax(0x00000001); + eq = (struct equiv_cpu_entry *)(container + CONTAINER_HDR_SZ); - if (!ucode_size || !initrd_start) - return; + eq_id = find_equiv_id(eq, eax); + if (!eq_id) + return; + + if (eq_id == this_equiv_id) { + mc = (struct microcode_amd *)amd_ucode_patch; - ucode = (void *)(initrd_start + ucode_offset); - eax = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff); - if (load_microcode_amd(eax, ucode, ucode_size) != UCODE_OK) + if (mc && rev < mc->hdr.patch_id) { + if (!__apply_microcode_amd(mc)) + ucode_new_rev = mc->hdr.patch_id; + } + + } else { + if (!ucode_cpio.data) return; - ucode_loaded = true; + /* + * AP has a different equivalence ID than BSP, looks like + * mixed-steppings silicon so go through the ucode blob anew. + */ + apply_ucode_in_initrd(ucode_cpio.data, ucode_cpio.size); } - - apply_microcode_amd(cpu); } #endif int __init save_microcode_in_initrd_amd(void) { enum ucode_state ret; - void *ucode; u32 eax; #ifdef CONFIG_X86_32 @@ -280,22 +346,35 @@ int __init save_microcode_in_initrd_amd(void) if (!uci->cpu_sig.sig) smp_call_function_single(bsp, collect_cpu_sig_on_bsp, NULL, 1); + + /* + * Take into account the fact that the ramdisk might get relocated + * and therefore we need to recompute the container's position in + * virtual memory space. + */ + container = (u8 *)(__va((u32)relocated_ramdisk) + + ((u32)container - boot_params.hdr.ramdisk_image)); #endif if (ucode_new_rev) pr_info("microcode: updated early to new patch_level=0x%08x\n", ucode_new_rev); - if (ucode_loaded || !ucode_size || !initrd_start) - return 0; + if (!container) + return -EINVAL; - ucode = (void *)(initrd_start + ucode_offset); eax = cpuid_eax(0x00000001); eax = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff); - ret = load_microcode_amd(eax, ucode, ucode_size); + ret = load_microcode_amd(eax, container, container_size); if (ret != UCODE_OK) return -EINVAL; - ucode_loaded = true; + /* + * This will be freed any msec now, stash patches for the current + * family and switch to patch cache for cpu hotplug, etc later. + */ + container = NULL; + container_size = 0; + return 0; } diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/cpu/microcode/core.c index 15c987698b0..15c987698b0 100644 --- a/arch/x86/kernel/microcode_core.c +++ b/arch/x86/kernel/cpu/microcode/core.c diff --git a/arch/x86/kernel/microcode_core_early.c b/arch/x86/kernel/cpu/microcode/core_early.c index be7f8514f57..be7f8514f57 100644 --- a/arch/x86/kernel/microcode_core_early.c +++ b/arch/x86/kernel/cpu/microcode/core_early.c diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 5fb2cebf556..a276fa75d9b 100644 --- a/arch/x86/kernel/microcode_intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -278,7 +278,7 @@ static enum ucode_state request_microcode_fw(int cpu, struct device *device, sprintf(name, "intel-ucode/%02x-%02x-%02x", c->x86, c->x86_model, c->x86_mask); - if (request_firmware(&firmware, name, device)) { + if (request_firmware_direct(&firmware, name, device)) { pr_debug("data file %s load failed\n", name); return UCODE_NFOUND; } diff --git a/arch/x86/kernel/microcode_intel_early.c b/arch/x86/kernel/cpu/microcode/intel_early.c index 1575deb2e63..18f739129e7 100644 --- a/arch/x86/kernel/microcode_intel_early.c +++ b/arch/x86/kernel/cpu/microcode/intel_early.c @@ -365,16 +365,6 @@ out: return state; } -#define native_rdmsr(msr, val1, val2) \ -do { \ - u64 __val = native_read_msr((msr)); \ - (void)((val1) = (u32)__val); \ - (void)((val2) = (u32)(__val >> 32)); \ -} while (0) - -#define native_wrmsr(msr, low, high) \ - native_write_msr(msr, low, high); - static int collect_cpu_info_early(struct ucode_cpu_info *uci) { unsigned int val[2]; diff --git a/arch/x86/kernel/microcode_intel_lib.c b/arch/x86/kernel/cpu/microcode/intel_lib.c index ce69320d017..ce69320d017 100644 --- a/arch/x86/kernel/microcode_intel_lib.c +++ b/arch/x86/kernel/cpu/microcode/intel_lib.c diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 8e132931614..b88645191fe 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1883,21 +1883,27 @@ static struct pmu pmu = { void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now) { + struct cyc2ns_data *data; + userpg->cap_user_time = 0; userpg->cap_user_time_zero = 0; userpg->cap_user_rdpmc = x86_pmu.attr_rdpmc; userpg->pmc_width = x86_pmu.cntval_bits; - if (!sched_clock_stable) + if (!sched_clock_stable()) return; + data = cyc2ns_read_begin(); + userpg->cap_user_time = 1; - userpg->time_mult = this_cpu_read(cyc2ns); - userpg->time_shift = CYC2NS_SCALE_FACTOR; - userpg->time_offset = this_cpu_read(cyc2ns_offset) - now; + userpg->time_mult = data->cyc2ns_mul; + userpg->time_shift = data->cyc2ns_shift; + userpg->time_offset = data->cyc2ns_offset - now; userpg->cap_user_time_zero = 1; - userpg->time_zero = this_cpu_read(cyc2ns_offset); + userpg->time_zero = data->cyc2ns_offset; + + cyc2ns_read_end(data); } /* diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index fd00bb29425..c1a861829d8 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -262,11 +262,20 @@ struct cpu_hw_events { __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST_HSW) -#define EVENT_CONSTRAINT_END \ - EVENT_CONSTRAINT(0, 0, 0) +/* + * We define the end marker as having a weight of -1 + * to enable blacklisting of events using a counter bitmask + * of zero and thus a weight of zero. + * The end marker has a weight that cannot possibly be + * obtained from counting the bits in the bitmask. + */ +#define EVENT_CONSTRAINT_END { .weight = -1 } +/* + * Check for end marker with weight == -1 + */ #define for_each_event_constraint(e, c) \ - for ((e) = (c); (e)->weight; (e)++) + for ((e) = (c); (e)->weight != -1; (e)++) /* * Extra registers for specific events. diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c index e09f0bfb7b8..4b8e4d3cd6e 100644 --- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c +++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c @@ -10,6 +10,7 @@ #include <linux/module.h> #include <linux/pci.h> #include <linux/ptrace.h> +#include <linux/syscore_ops.h> #include <asm/apic.h> @@ -816,6 +817,18 @@ out: return ret; } +static void ibs_eilvt_setup(void) +{ + /* + * Force LVT offset assignment for family 10h: The offsets are + * not assigned by the BIOS for this family, so the OS is + * responsible for doing it. If the OS assignment fails, fall + * back to BIOS settings and try to setup this. + */ + if (boot_cpu_data.x86 == 0x10) + force_ibs_eilvt_setup(); +} + static inline int get_ibs_lvt_offset(void) { u64 val; @@ -851,6 +864,36 @@ static void clear_APIC_ibs(void *dummy) setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_FIX, 1); } +#ifdef CONFIG_PM + +static int perf_ibs_suspend(void) +{ + clear_APIC_ibs(NULL); + return 0; +} + +static void perf_ibs_resume(void) +{ + ibs_eilvt_setup(); + setup_APIC_ibs(NULL); +} + +static struct syscore_ops perf_ibs_syscore_ops = { + .resume = perf_ibs_resume, + .suspend = perf_ibs_suspend, +}; + +static void perf_ibs_pm_init(void) +{ + register_syscore_ops(&perf_ibs_syscore_ops); +} + +#else + +static inline void perf_ibs_pm_init(void) { } + +#endif + static int perf_ibs_cpu_notifier(struct notifier_block *self, unsigned long action, void *hcpu) { @@ -877,18 +920,12 @@ static __init int amd_ibs_init(void) if (!caps) return -ENODEV; /* ibs not supported by the cpu */ - /* - * Force LVT offset assignment for family 10h: The offsets are - * not assigned by the BIOS for this family, so the OS is - * responsible for doing it. If the OS assignment fails, fall - * back to BIOS settings and try to setup this. - */ - if (boot_cpu_data.x86 == 0x10) - force_ibs_eilvt_setup(); + ibs_eilvt_setup(); if (!ibs_eilvt_valid()) goto out; + perf_ibs_pm_init(); get_online_cpus(); ibs_caps = caps; /* make ibs_caps visible to other cpus: */ diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c new file mode 100644 index 00000000000..5ad35ad94d0 --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c @@ -0,0 +1,679 @@ +/* + * perf_event_intel_rapl.c: support Intel RAPL energy consumption counters + * Copyright (C) 2013 Google, Inc., Stephane Eranian + * + * Intel RAPL interface is specified in the IA-32 Manual Vol3b + * section 14.7.1 (September 2013) + * + * RAPL provides more controls than just reporting energy consumption + * however here we only expose the 3 energy consumption free running + * counters (pp0, pkg, dram). + * + * Each of those counters increments in a power unit defined by the + * RAPL_POWER_UNIT MSR. On SandyBridge, this unit is 1/(2^16) Joules + * but it can vary. + * + * Counter to rapl events mappings: + * + * pp0 counter: consumption of all physical cores (power plane 0) + * event: rapl_energy_cores + * perf code: 0x1 + * + * pkg counter: consumption of the whole processor package + * event: rapl_energy_pkg + * perf code: 0x2 + * + * dram counter: consumption of the dram domain (servers only) + * event: rapl_energy_dram + * perf code: 0x3 + * + * dram counter: consumption of the builtin-gpu domain (client only) + * event: rapl_energy_gpu + * perf code: 0x4 + * + * We manage those counters as free running (read-only). They may be + * use simultaneously by other tools, such as turbostat. + * + * The events only support system-wide mode counting. There is no + * sampling support because it does not make sense and is not + * supported by the RAPL hardware. + * + * Because we want to avoid floating-point operations in the kernel, + * the events are all reported in fixed point arithmetic (32.32). + * Tools must adjust the counts to convert them to Watts using + * the duration of the measurement. Tools may use a function such as + * ldexp(raw_count, -32); + */ +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/perf_event.h> +#include <asm/cpu_device_id.h> +#include "perf_event.h" + +/* + * RAPL energy status counters + */ +#define RAPL_IDX_PP0_NRG_STAT 0 /* all cores */ +#define INTEL_RAPL_PP0 0x1 /* pseudo-encoding */ +#define RAPL_IDX_PKG_NRG_STAT 1 /* entire package */ +#define INTEL_RAPL_PKG 0x2 /* pseudo-encoding */ +#define RAPL_IDX_RAM_NRG_STAT 2 /* DRAM */ +#define INTEL_RAPL_RAM 0x3 /* pseudo-encoding */ +#define RAPL_IDX_PP1_NRG_STAT 3 /* DRAM */ +#define INTEL_RAPL_PP1 0x4 /* pseudo-encoding */ + +/* Clients have PP0, PKG */ +#define RAPL_IDX_CLN (1<<RAPL_IDX_PP0_NRG_STAT|\ + 1<<RAPL_IDX_PKG_NRG_STAT|\ + 1<<RAPL_IDX_PP1_NRG_STAT) + +/* Servers have PP0, PKG, RAM */ +#define RAPL_IDX_SRV (1<<RAPL_IDX_PP0_NRG_STAT|\ + 1<<RAPL_IDX_PKG_NRG_STAT|\ + 1<<RAPL_IDX_RAM_NRG_STAT) + +/* + * event code: LSB 8 bits, passed in attr->config + * any other bit is reserved + */ +#define RAPL_EVENT_MASK 0xFFULL + +#define DEFINE_RAPL_FORMAT_ATTR(_var, _name, _format) \ +static ssize_t __rapl_##_var##_show(struct kobject *kobj, \ + struct kobj_attribute *attr, \ + char *page) \ +{ \ + BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ + return sprintf(page, _format "\n"); \ +} \ +static struct kobj_attribute format_attr_##_var = \ + __ATTR(_name, 0444, __rapl_##_var##_show, NULL) + +#define RAPL_EVENT_DESC(_name, _config) \ +{ \ + .attr = __ATTR(_name, 0444, rapl_event_show, NULL), \ + .config = _config, \ +} + +#define RAPL_CNTR_WIDTH 32 /* 32-bit rapl counters */ + +struct rapl_pmu { + spinlock_t lock; + int hw_unit; /* 1/2^hw_unit Joule */ + int n_active; /* number of active events */ + struct list_head active_list; + struct pmu *pmu; /* pointer to rapl_pmu_class */ + ktime_t timer_interval; /* in ktime_t unit */ + struct hrtimer hrtimer; +}; + +static struct pmu rapl_pmu_class; +static cpumask_t rapl_cpu_mask; +static int rapl_cntr_mask; + +static DEFINE_PER_CPU(struct rapl_pmu *, rapl_pmu); +static DEFINE_PER_CPU(struct rapl_pmu *, rapl_pmu_to_free); + +static inline u64 rapl_read_counter(struct perf_event *event) +{ + u64 raw; + rdmsrl(event->hw.event_base, raw); + return raw; +} + +static inline u64 rapl_scale(u64 v) +{ + /* + * scale delta to smallest unit (1/2^32) + * users must then scale back: count * 1/(1e9*2^32) to get Joules + * or use ldexp(count, -32). + * Watts = Joules/Time delta + */ + return v << (32 - __get_cpu_var(rapl_pmu)->hw_unit); +} + +static u64 rapl_event_update(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + u64 prev_raw_count, new_raw_count; + s64 delta, sdelta; + int shift = RAPL_CNTR_WIDTH; + +again: + prev_raw_count = local64_read(&hwc->prev_count); + rdmsrl(event->hw.event_base, new_raw_count); + + if (local64_cmpxchg(&hwc->prev_count, prev_raw_count, + new_raw_count) != prev_raw_count) { + cpu_relax(); + goto again; + } + + /* + * Now we have the new raw value and have updated the prev + * timestamp already. We can now calculate the elapsed delta + * (event-)time and add that to the generic event. + * + * Careful, not all hw sign-extends above the physical width + * of the count. + */ + delta = (new_raw_count << shift) - (prev_raw_count << shift); + delta >>= shift; + + sdelta = rapl_scale(delta); + + local64_add(sdelta, &event->count); + + return new_raw_count; +} + +static void rapl_start_hrtimer(struct rapl_pmu *pmu) +{ + __hrtimer_start_range_ns(&pmu->hrtimer, + pmu->timer_interval, 0, + HRTIMER_MODE_REL_PINNED, 0); +} + +static void rapl_stop_hrtimer(struct rapl_pmu *pmu) +{ + hrtimer_cancel(&pmu->hrtimer); +} + +static enum hrtimer_restart rapl_hrtimer_handle(struct hrtimer *hrtimer) +{ + struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu); + struct perf_event *event; + unsigned long flags; + + if (!pmu->n_active) + return HRTIMER_NORESTART; + + spin_lock_irqsave(&pmu->lock, flags); + + list_for_each_entry(event, &pmu->active_list, active_entry) { + rapl_event_update(event); + } + + spin_unlock_irqrestore(&pmu->lock, flags); + + hrtimer_forward_now(hrtimer, pmu->timer_interval); + + return HRTIMER_RESTART; +} + +static void rapl_hrtimer_init(struct rapl_pmu *pmu) +{ + struct hrtimer *hr = &pmu->hrtimer; + + hrtimer_init(hr, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hr->function = rapl_hrtimer_handle; +} + +static void __rapl_pmu_event_start(struct rapl_pmu *pmu, + struct perf_event *event) +{ + if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED))) + return; + + event->hw.state = 0; + + list_add_tail(&event->active_entry, &pmu->active_list); + + local64_set(&event->hw.prev_count, rapl_read_counter(event)); + + pmu->n_active++; + if (pmu->n_active == 1) + rapl_start_hrtimer(pmu); +} + +static void rapl_pmu_event_start(struct perf_event *event, int mode) +{ + struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu); + unsigned long flags; + + spin_lock_irqsave(&pmu->lock, flags); + __rapl_pmu_event_start(pmu, event); + spin_unlock_irqrestore(&pmu->lock, flags); +} + +static void rapl_pmu_event_stop(struct perf_event *event, int mode) +{ + struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu); + struct hw_perf_event *hwc = &event->hw; + unsigned long flags; + + spin_lock_irqsave(&pmu->lock, flags); + + /* mark event as deactivated and stopped */ + if (!(hwc->state & PERF_HES_STOPPED)) { + WARN_ON_ONCE(pmu->n_active <= 0); + pmu->n_active--; + if (pmu->n_active == 0) + rapl_stop_hrtimer(pmu); + + list_del(&event->active_entry); + + WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); + hwc->state |= PERF_HES_STOPPED; + } + + /* check if update of sw counter is necessary */ + if ((mode & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) { + /* + * Drain the remaining delta count out of a event + * that we are disabling: + */ + rapl_event_update(event); + hwc->state |= PERF_HES_UPTODATE; + } + + spin_unlock_irqrestore(&pmu->lock, flags); +} + +static int rapl_pmu_event_add(struct perf_event *event, int mode) +{ + struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu); + struct hw_perf_event *hwc = &event->hw; + unsigned long flags; + + spin_lock_irqsave(&pmu->lock, flags); + + hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED; + + if (mode & PERF_EF_START) + __rapl_pmu_event_start(pmu, event); + + spin_unlock_irqrestore(&pmu->lock, flags); + + return 0; +} + +static void rapl_pmu_event_del(struct perf_event *event, int flags) +{ + rapl_pmu_event_stop(event, PERF_EF_UPDATE); +} + +static int rapl_pmu_event_init(struct perf_event *event) +{ + u64 cfg = event->attr.config & RAPL_EVENT_MASK; + int bit, msr, ret = 0; + + /* only look at RAPL events */ + if (event->attr.type != rapl_pmu_class.type) + return -ENOENT; + + /* check only supported bits are set */ + if (event->attr.config & ~RAPL_EVENT_MASK) + return -EINVAL; + + /* + * check event is known (determines counter) + */ + switch (cfg) { + case INTEL_RAPL_PP0: + bit = RAPL_IDX_PP0_NRG_STAT; + msr = MSR_PP0_ENERGY_STATUS; + break; + case INTEL_RAPL_PKG: + bit = RAPL_IDX_PKG_NRG_STAT; + msr = MSR_PKG_ENERGY_STATUS; + break; + case INTEL_RAPL_RAM: + bit = RAPL_IDX_RAM_NRG_STAT; + msr = MSR_DRAM_ENERGY_STATUS; + break; + case INTEL_RAPL_PP1: + bit = RAPL_IDX_PP1_NRG_STAT; + msr = MSR_PP1_ENERGY_STATUS; + break; + default: + return -EINVAL; + } + /* check event supported */ + if (!(rapl_cntr_mask & (1 << bit))) + return -EINVAL; + + /* unsupported modes and filters */ + if (event->attr.exclude_user || + event->attr.exclude_kernel || + event->attr.exclude_hv || + event->attr.exclude_idle || + event->attr.exclude_host || + event->attr.exclude_guest || + event->attr.sample_period) /* no sampling */ + return -EINVAL; + + /* must be done before validate_group */ + event->hw.event_base = msr; + event->hw.config = cfg; + event->hw.idx = bit; + + return ret; +} + +static void rapl_pmu_event_read(struct perf_event *event) +{ + rapl_event_update(event); +} + +static ssize_t rapl_get_attr_cpumask(struct device *dev, + struct device_attribute *attr, char *buf) +{ + int n = cpulist_scnprintf(buf, PAGE_SIZE - 2, &rapl_cpu_mask); + + buf[n++] = '\n'; + buf[n] = '\0'; + return n; +} + +static DEVICE_ATTR(cpumask, S_IRUGO, rapl_get_attr_cpumask, NULL); + +static struct attribute *rapl_pmu_attrs[] = { + &dev_attr_cpumask.attr, + NULL, +}; + +static struct attribute_group rapl_pmu_attr_group = { + .attrs = rapl_pmu_attrs, +}; + +EVENT_ATTR_STR(energy-cores, rapl_cores, "event=0x01"); +EVENT_ATTR_STR(energy-pkg , rapl_pkg, "event=0x02"); +EVENT_ATTR_STR(energy-ram , rapl_ram, "event=0x03"); +EVENT_ATTR_STR(energy-gpu , rapl_gpu, "event=0x04"); + +EVENT_ATTR_STR(energy-cores.unit, rapl_cores_unit, "Joules"); +EVENT_ATTR_STR(energy-pkg.unit , rapl_pkg_unit, "Joules"); +EVENT_ATTR_STR(energy-ram.unit , rapl_ram_unit, "Joules"); +EVENT_ATTR_STR(energy-gpu.unit , rapl_gpu_unit, "Joules"); + +/* + * we compute in 0.23 nJ increments regardless of MSR + */ +EVENT_ATTR_STR(energy-cores.scale, rapl_cores_scale, "2.3283064365386962890625e-10"); +EVENT_ATTR_STR(energy-pkg.scale, rapl_pkg_scale, "2.3283064365386962890625e-10"); +EVENT_ATTR_STR(energy-ram.scale, rapl_ram_scale, "2.3283064365386962890625e-10"); +EVENT_ATTR_STR(energy-gpu.scale, rapl_gpu_scale, "2.3283064365386962890625e-10"); + +static struct attribute *rapl_events_srv_attr[] = { + EVENT_PTR(rapl_cores), + EVENT_PTR(rapl_pkg), + EVENT_PTR(rapl_ram), + + EVENT_PTR(rapl_cores_unit), + EVENT_PTR(rapl_pkg_unit), + EVENT_PTR(rapl_ram_unit), + + EVENT_PTR(rapl_cores_scale), + EVENT_PTR(rapl_pkg_scale), + EVENT_PTR(rapl_ram_scale), + NULL, +}; + +static struct attribute *rapl_events_cln_attr[] = { + EVENT_PTR(rapl_cores), + EVENT_PTR(rapl_pkg), + EVENT_PTR(rapl_gpu), + + EVENT_PTR(rapl_cores_unit), + EVENT_PTR(rapl_pkg_unit), + EVENT_PTR(rapl_gpu_unit), + + EVENT_PTR(rapl_cores_scale), + EVENT_PTR(rapl_pkg_scale), + EVENT_PTR(rapl_gpu_scale), + NULL, +}; + +static struct attribute_group rapl_pmu_events_group = { + .name = "events", + .attrs = NULL, /* patched at runtime */ +}; + +DEFINE_RAPL_FORMAT_ATTR(event, event, "config:0-7"); +static struct attribute *rapl_formats_attr[] = { + &format_attr_event.attr, + NULL, +}; + +static struct attribute_group rapl_pmu_format_group = { + .name = "format", + .attrs = rapl_formats_attr, +}; + +const struct attribute_group *rapl_attr_groups[] = { + &rapl_pmu_attr_group, + &rapl_pmu_format_group, + &rapl_pmu_events_group, + NULL, +}; + +static struct pmu rapl_pmu_class = { + .attr_groups = rapl_attr_groups, + .task_ctx_nr = perf_invalid_context, /* system-wide only */ + .event_init = rapl_pmu_event_init, + .add = rapl_pmu_event_add, /* must have */ + .del = rapl_pmu_event_del, /* must have */ + .start = rapl_pmu_event_start, + .stop = rapl_pmu_event_stop, + .read = rapl_pmu_event_read, +}; + +static void rapl_cpu_exit(int cpu) +{ + struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu); + int i, phys_id = topology_physical_package_id(cpu); + int target = -1; + + /* find a new cpu on same package */ + for_each_online_cpu(i) { + if (i == cpu) + continue; + if (phys_id == topology_physical_package_id(i)) { + target = i; + break; + } + } + /* + * clear cpu from cpumask + * if was set in cpumask and still some cpu on package, + * then move to new cpu + */ + if (cpumask_test_and_clear_cpu(cpu, &rapl_cpu_mask) && target >= 0) + cpumask_set_cpu(target, &rapl_cpu_mask); + + WARN_ON(cpumask_empty(&rapl_cpu_mask)); + /* + * migrate events and context to new cpu + */ + if (target >= 0) + perf_pmu_migrate_context(pmu->pmu, cpu, target); + + /* cancel overflow polling timer for CPU */ + rapl_stop_hrtimer(pmu); +} + +static void rapl_cpu_init(int cpu) +{ + int i, phys_id = topology_physical_package_id(cpu); + + /* check if phys_is is already covered */ + for_each_cpu(i, &rapl_cpu_mask) { + if (phys_id == topology_physical_package_id(i)) + return; + } + /* was not found, so add it */ + cpumask_set_cpu(cpu, &rapl_cpu_mask); +} + +static int rapl_cpu_prepare(int cpu) +{ + struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu); + int phys_id = topology_physical_package_id(cpu); + u64 ms; + + if (pmu) + return 0; + + if (phys_id < 0) + return -1; + + pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu)); + if (!pmu) + return -1; + + spin_lock_init(&pmu->lock); + + INIT_LIST_HEAD(&pmu->active_list); + + /* + * grab power unit as: 1/2^unit Joules + * + * we cache in local PMU instance + */ + rdmsrl(MSR_RAPL_POWER_UNIT, pmu->hw_unit); + pmu->hw_unit = (pmu->hw_unit >> 8) & 0x1FULL; + pmu->pmu = &rapl_pmu_class; + + /* + * use reference of 200W for scaling the timeout + * to avoid missing counter overflows. + * 200W = 200 Joules/sec + * divide interval by 2 to avoid lockstep (2 * 100) + * if hw unit is 32, then we use 2 ms 1/200/2 + */ + if (pmu->hw_unit < 32) + ms = (1000 / (2 * 100)) * (1ULL << (32 - pmu->hw_unit - 1)); + else + ms = 2; + + pmu->timer_interval = ms_to_ktime(ms); + + rapl_hrtimer_init(pmu); + + /* set RAPL pmu for this cpu for now */ + per_cpu(rapl_pmu, cpu) = pmu; + per_cpu(rapl_pmu_to_free, cpu) = NULL; + + return 0; +} + +static void rapl_cpu_kfree(int cpu) +{ + struct rapl_pmu *pmu = per_cpu(rapl_pmu_to_free, cpu); + + kfree(pmu); + + per_cpu(rapl_pmu_to_free, cpu) = NULL; +} + +static int rapl_cpu_dying(int cpu) +{ + struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu); + + if (!pmu) + return 0; + + per_cpu(rapl_pmu, cpu) = NULL; + + per_cpu(rapl_pmu_to_free, cpu) = pmu; + + return 0; +} + +static int rapl_cpu_notifier(struct notifier_block *self, + unsigned long action, void *hcpu) +{ + unsigned int cpu = (long)hcpu; + + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_UP_PREPARE: + rapl_cpu_prepare(cpu); + break; + case CPU_STARTING: + rapl_cpu_init(cpu); + break; + case CPU_UP_CANCELED: + case CPU_DYING: + rapl_cpu_dying(cpu); + break; + case CPU_ONLINE: + case CPU_DEAD: + rapl_cpu_kfree(cpu); + break; + case CPU_DOWN_PREPARE: + rapl_cpu_exit(cpu); + break; + default: + break; + } + + return NOTIFY_OK; +} + +static const struct x86_cpu_id rapl_cpu_match[] = { + [0] = { .vendor = X86_VENDOR_INTEL, .family = 6 }, + [1] = {}, +}; + +static int __init rapl_pmu_init(void) +{ + struct rapl_pmu *pmu; + int cpu, ret; + + /* + * check for Intel processor family 6 + */ + if (!x86_match_cpu(rapl_cpu_match)) + return 0; + + /* check supported CPU */ + switch (boot_cpu_data.x86_model) { + case 42: /* Sandy Bridge */ + case 58: /* Ivy Bridge */ + case 60: /* Haswell */ + case 69: /* Haswell-Celeron */ + rapl_cntr_mask = RAPL_IDX_CLN; + rapl_pmu_events_group.attrs = rapl_events_cln_attr; + break; + case 45: /* Sandy Bridge-EP */ + case 62: /* IvyTown */ + rapl_cntr_mask = RAPL_IDX_SRV; + rapl_pmu_events_group.attrs = rapl_events_srv_attr; + break; + + default: + /* unsupported */ + return 0; + } + get_online_cpus(); + + for_each_online_cpu(cpu) { + rapl_cpu_prepare(cpu); + rapl_cpu_init(cpu); + } + + perf_cpu_notifier(rapl_cpu_notifier); + + ret = perf_pmu_register(&rapl_pmu_class, "power", -1); + if (WARN_ON(ret)) { + pr_info("RAPL PMU detected, registration failed (%d), RAPL PMU disabled\n", ret); + put_online_cpus(); + return -1; + } + + pmu = __get_cpu_var(rapl_pmu); + + pr_info("RAPL PMU detected, hw unit 2^-%d Joules," + " API unit is 2^-32 Joules," + " %d fixed counters" + " %llu ms ovfl timer\n", + pmu->hw_unit, + hweight32(rapl_cntr_mask), + ktime_to_ms(pmu->timer_interval)); + + put_online_cpus(); + + return 0; +} +device_initcall(rapl_pmu_init); diff --git a/arch/x86/kernel/cpu/rdrand.c b/arch/x86/kernel/cpu/rdrand.c index 88db010845c..384df5105fb 100644 --- a/arch/x86/kernel/cpu/rdrand.c +++ b/arch/x86/kernel/cpu/rdrand.c @@ -31,20 +31,6 @@ static int __init x86_rdrand_setup(char *s) } __setup("nordrand", x86_rdrand_setup); -/* We can't use arch_get_random_long() here since alternatives haven't run */ -static inline int rdrand_long(unsigned long *v) -{ - int ok; - asm volatile("1: " RDRAND_LONG "\n\t" - "jc 2f\n\t" - "decl %0\n\t" - "jnz 1b\n\t" - "2:" - : "=r" (ok), "=a" (*v) - : "0" (RDRAND_RETRY_LOOPS)); - return ok; -} - /* * Force a reseed cycle; we are architecturally guaranteed a reseed * after no more than 512 128-bit chunks of random data. This also diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c index aa0430d69b9..3fa0e5ad86b 100644 --- a/arch/x86/kernel/cpu/transmeta.c +++ b/arch/x86/kernel/cpu/transmeta.c @@ -1,6 +1,5 @@ #include <linux/kernel.h> #include <linux/mm.h> -#include <linux/init.h> #include <asm/processor.h> #include <asm/msr.h> #include "cpu.h" diff --git a/arch/x86/kernel/cpu/umc.c b/arch/x86/kernel/cpu/umc.c index 75c5ad5d35c..ef9c2a0078b 100644 --- a/arch/x86/kernel/cpu/umc.c +++ b/arch/x86/kernel/cpu/umc.c @@ -1,5 +1,4 @@ #include <linux/kernel.h> -#include <linux/init.h> #include <asm/processor.h> #include "cpu.h" diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 18677a90d6a..a57902efe2d 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -7,7 +7,6 @@ * */ -#include <linux/init.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/smp.h> diff --git a/arch/x86/kernel/doublefault.c b/arch/x86/kernel/doublefault.c index 5d3fe8d36e4..f6dfd9334b6 100644 --- a/arch/x86/kernel/doublefault.c +++ b/arch/x86/kernel/doublefault.c @@ -1,6 +1,5 @@ #include <linux/mm.h> #include <linux/sched.h> -#include <linux/init.h> #include <linux/init_task.h> #include <linux/fs.h> diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 174da5fc5a7..988c00a1f60 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1120,7 +1120,7 @@ void __init memblock_find_dma_reserve(void) nr_pages += end_pfn - start_pfn; } - for_each_free_mem_range(u, MAX_NUMNODES, &start, &end, NULL) { + for_each_free_mem_range(u, NUMA_NO_NODE, &start, &end, NULL) { start_pfn = min_t(unsigned long, PFN_UP(start), MAX_DMA_PFN); end_pfn = min_t(unsigned long, PFN_DOWN(end), MAX_DMA_PFN); if (start_pfn < end_pfn) diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 51e2988c572..a2a4f469788 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -1082,7 +1082,7 @@ ENTRY(ftrace_caller) pushl $0 /* Pass NULL as regs pointer */ movl 4*4(%esp), %eax movl 0x4(%ebp), %edx - leal function_trace_op, %ecx + movl function_trace_op, %ecx subl $MCOUNT_INSN_SIZE, %eax .globl ftrace_call @@ -1140,7 +1140,7 @@ ENTRY(ftrace_regs_caller) movl 12*4(%esp), %eax /* Load ip (1st parameter) */ subl $MCOUNT_INSN_SIZE, %eax /* Adjust ip */ movl 0x4(%ebp), %edx /* Load parent ip (2nd parameter) */ - leal function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */ + movl function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */ pushl %esp /* Save pt_regs as 4th parameter */ GLOBAL(ftrace_regs_call) diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index e21b0785a85..1e96c3628bf 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -88,7 +88,7 @@ END(function_hook) MCOUNT_SAVE_FRAME \skip /* Load the ftrace_ops into the 3rd parameter */ - leaq function_trace_op, %rdx + movq function_trace_op(%rip), %rdx /* Load ip into the first parameter */ movq RIP(%rsp), %rdi diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index f66ff162dce..a67b47c3131 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -38,7 +38,6 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/sched.h> -#include <linux/init.h> #include <linux/smp.h> #include <asm/hw_breakpoint.h> diff --git a/arch/x86/kernel/iosf_mbi.c b/arch/x86/kernel/iosf_mbi.c new file mode 100644 index 00000000000..c3aae667284 --- /dev/null +++ b/arch/x86/kernel/iosf_mbi.c @@ -0,0 +1,226 @@ +/* + * IOSF-SB MailBox Interface Driver + * Copyright (c) 2013, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * + * The IOSF-SB is a fabric bus available on Atom based SOC's that uses a + * mailbox interface (MBI) to communicate with mutiple devices. This + * driver implements access to this interface for those platforms that can + * enumerate the device using PCI. + */ + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/spinlock.h> +#include <linux/pci.h> + +#include <asm/iosf_mbi.h> + +static DEFINE_SPINLOCK(iosf_mbi_lock); + +static inline u32 iosf_mbi_form_mcr(u8 op, u8 port, u8 offset) +{ + return (op << 24) | (port << 16) | (offset << 8) | MBI_ENABLE; +} + +static struct pci_dev *mbi_pdev; /* one mbi device */ + +static int iosf_mbi_pci_read_mdr(u32 mcrx, u32 mcr, u32 *mdr) +{ + int result; + + if (!mbi_pdev) + return -ENODEV; + + if (mcrx) { + result = pci_write_config_dword(mbi_pdev, MBI_MCRX_OFFSET, + mcrx); + if (result < 0) + goto fail_read; + } + + result = pci_write_config_dword(mbi_pdev, MBI_MCR_OFFSET, mcr); + if (result < 0) + goto fail_read; + + result = pci_read_config_dword(mbi_pdev, MBI_MDR_OFFSET, mdr); + if (result < 0) + goto fail_read; + + return 0; + +fail_read: + dev_err(&mbi_pdev->dev, "PCI config access failed with %d\n", result); + return result; +} + +static int iosf_mbi_pci_write_mdr(u32 mcrx, u32 mcr, u32 mdr) +{ + int result; + + if (!mbi_pdev) + return -ENODEV; + + result = pci_write_config_dword(mbi_pdev, MBI_MDR_OFFSET, mdr); + if (result < 0) + goto fail_write; + + if (mcrx) { + result = pci_write_config_dword(mbi_pdev, MBI_MCRX_OFFSET, + mcrx); + if (result < 0) + goto fail_write; + } + + result = pci_write_config_dword(mbi_pdev, MBI_MCR_OFFSET, mcr); + if (result < 0) + goto fail_write; + + return 0; + +fail_write: + dev_err(&mbi_pdev->dev, "PCI config access failed with %d\n", result); + return result; +} + +int iosf_mbi_read(u8 port, u8 opcode, u32 offset, u32 *mdr) +{ + u32 mcr, mcrx; + unsigned long flags; + int ret; + + /*Access to the GFX unit is handled by GPU code */ + if (port == BT_MBI_UNIT_GFX) { + WARN_ON(1); + return -EPERM; + } + + mcr = iosf_mbi_form_mcr(opcode, port, offset & MBI_MASK_LO); + mcrx = offset & MBI_MASK_HI; + + spin_lock_irqsave(&iosf_mbi_lock, flags); + ret = iosf_mbi_pci_read_mdr(mcrx, mcr, mdr); + spin_unlock_irqrestore(&iosf_mbi_lock, flags); + + return ret; +} +EXPORT_SYMBOL(iosf_mbi_read); + +int iosf_mbi_write(u8 port, u8 opcode, u32 offset, u32 mdr) +{ + u32 mcr, mcrx; + unsigned long flags; + int ret; + + /*Access to the GFX unit is handled by GPU code */ + if (port == BT_MBI_UNIT_GFX) { + WARN_ON(1); + return -EPERM; + } + + mcr = iosf_mbi_form_mcr(opcode, port, offset & MBI_MASK_LO); + mcrx = offset & MBI_MASK_HI; + + spin_lock_irqsave(&iosf_mbi_lock, flags); + ret = iosf_mbi_pci_write_mdr(mcrx, mcr, mdr); + spin_unlock_irqrestore(&iosf_mbi_lock, flags); + + return ret; +} +EXPORT_SYMBOL(iosf_mbi_write); + +int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask) +{ + u32 mcr, mcrx; + u32 value; + unsigned long flags; + int ret; + + /*Access to the GFX unit is handled by GPU code */ + if (port == BT_MBI_UNIT_GFX) { + WARN_ON(1); + return -EPERM; + } + + mcr = iosf_mbi_form_mcr(opcode, port, offset & MBI_MASK_LO); + mcrx = offset & MBI_MASK_HI; + + spin_lock_irqsave(&iosf_mbi_lock, flags); + + /* Read current mdr value */ + ret = iosf_mbi_pci_read_mdr(mcrx, mcr & MBI_RD_MASK, &value); + if (ret < 0) { + spin_unlock_irqrestore(&iosf_mbi_lock, flags); + return ret; + } + + /* Apply mask */ + value &= ~mask; + mdr &= mask; + value |= mdr; + + /* Write back */ + ret = iosf_mbi_pci_write_mdr(mcrx, mcr | MBI_WR_MASK, value); + + spin_unlock_irqrestore(&iosf_mbi_lock, flags); + + return ret; +} +EXPORT_SYMBOL(iosf_mbi_modify); + +static int iosf_mbi_probe(struct pci_dev *pdev, + const struct pci_device_id *unused) +{ + int ret; + + ret = pci_enable_device(pdev); + if (ret < 0) { + dev_err(&pdev->dev, "error: could not enable device\n"); + return ret; + } + + mbi_pdev = pci_dev_get(pdev); + return 0; +} + +static DEFINE_PCI_DEVICE_TABLE(iosf_mbi_pci_ids) = { + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x0F00) }, + { 0, }, +}; +MODULE_DEVICE_TABLE(pci, iosf_mbi_pci_ids); + +static struct pci_driver iosf_mbi_pci_driver = { + .name = "iosf_mbi_pci", + .probe = iosf_mbi_probe, + .id_table = iosf_mbi_pci_ids, +}; + +static int __init iosf_mbi_init(void) +{ + return pci_register_driver(&iosf_mbi_pci_driver); +} + +static void __exit iosf_mbi_exit(void) +{ + pci_unregister_driver(&iosf_mbi_pci_driver); + if (mbi_pdev) { + pci_dev_put(mbi_pdev); + mbi_pdev = NULL; + } +} + +module_init(iosf_mbi_init); +module_exit(iosf_mbi_exit); + +MODULE_AUTHOR("David E. Box <david.e.box@linux.intel.com>"); +MODULE_DESCRIPTION("IOSF Mailbox Interface accessor"); +MODULE_LICENSE("GPL v2"); diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 22d0687e7fd..dbb60878b74 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -193,9 +193,13 @@ __visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs) if (!handle_irq(irq, regs)) { ack_APIC_irq(); - if (printk_ratelimit()) - pr_emerg("%s: %d.%d No irq handler for vector (irq %d)\n", - __func__, smp_processor_id(), vector, irq); + if (irq != VECTOR_RETRIGGERED) { + pr_emerg_ratelimited("%s: %d.%d No irq handler for vector (irq %d)\n", + __func__, smp_processor_id(), + vector, irq); + } else { + __this_cpu_write(vector_irq[vector], VECTOR_UNDEFINED); + } } irq_exit(); @@ -262,6 +266,76 @@ __visible void smp_trace_x86_platform_ipi(struct pt_regs *regs) EXPORT_SYMBOL_GPL(vector_used_by_percpu_irq); #ifdef CONFIG_HOTPLUG_CPU +/* + * This cpu is going to be removed and its vectors migrated to the remaining + * online cpus. Check to see if there are enough vectors in the remaining cpus. + * This function is protected by stop_machine(). + */ +int check_irq_vectors_for_cpu_disable(void) +{ + int irq, cpu; + unsigned int this_cpu, vector, this_count, count; + struct irq_desc *desc; + struct irq_data *data; + struct cpumask affinity_new, online_new; + + this_cpu = smp_processor_id(); + cpumask_copy(&online_new, cpu_online_mask); + cpu_clear(this_cpu, online_new); + + this_count = 0; + for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { + irq = __this_cpu_read(vector_irq[vector]); + if (irq >= 0) { + desc = irq_to_desc(irq); + data = irq_desc_get_irq_data(desc); + cpumask_copy(&affinity_new, data->affinity); + cpu_clear(this_cpu, affinity_new); + + /* Do not count inactive or per-cpu irqs. */ + if (!irq_has_action(irq) || irqd_is_per_cpu(data)) + continue; + + /* + * A single irq may be mapped to multiple + * cpu's vector_irq[] (for example IOAPIC cluster + * mode). In this case we have two + * possibilities: + * + * 1) the resulting affinity mask is empty; that is + * this the down'd cpu is the last cpu in the irq's + * affinity mask, or + * + * 2) the resulting affinity mask is no longer + * a subset of the online cpus but the affinity + * mask is not zero; that is the down'd cpu is the + * last online cpu in a user set affinity mask. + */ + if (cpumask_empty(&affinity_new) || + !cpumask_subset(&affinity_new, &online_new)) + this_count++; + } + } + + count = 0; + for_each_online_cpu(cpu) { + if (cpu == this_cpu) + continue; + for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; + vector++) { + if (per_cpu(vector_irq, cpu)[vector] < 0) + count++; + } + } + + if (count < this_count) { + pr_warn("CPU %d disable failed: CPU has %u vectors assigned and there are only %u available.\n", + this_cpu, this_count, count); + return -ERANGE; + } + return 0; +} + /* A cpu has been removed from cpu_online_mask. Reset irq affinities. */ void fixup_irqs(void) { @@ -344,7 +418,7 @@ void fixup_irqs(void) for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { unsigned int irr; - if (__this_cpu_read(vector_irq[vector]) < 0) + if (__this_cpu_read(vector_irq[vector]) <= VECTOR_UNDEFINED) continue; irr = apic_read(APIC_IRR + (vector / 32 * 0x10)); @@ -355,11 +429,14 @@ void fixup_irqs(void) data = irq_desc_get_irq_data(desc); chip = irq_data_get_irq_chip(data); raw_spin_lock(&desc->lock); - if (chip->irq_retrigger) + if (chip->irq_retrigger) { chip->irq_retrigger(data); + __this_cpu_write(vector_irq[vector], VECTOR_RETRIGGERED); + } raw_spin_unlock(&desc->lock); } - __this_cpu_write(vector_irq[vector], -1); + if (__this_cpu_read(vector_irq[vector]) != VECTOR_RETRIGGERED) + __this_cpu_write(vector_irq[vector], VECTOR_UNDEFINED); } } #endif diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index a2a1fbc594f..7f50156542f 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -52,7 +52,7 @@ static struct irqaction irq2 = { }; DEFINE_PER_CPU(vector_irq_t, vector_irq) = { - [0 ... NR_VECTORS - 1] = -1, + [0 ... NR_VECTORS - 1] = VECTOR_UNDEFINED, }; int vector_used_by_percpu_irq(unsigned int vector) @@ -60,7 +60,7 @@ int vector_used_by_percpu_irq(unsigned int vector) int cpu; for_each_online_cpu(cpu) { - if (per_cpu(vector_irq, cpu)[vector] != -1) + if (per_cpu(vector_irq, cpu)[vector] > VECTOR_UNDEFINED) return 1; } diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 836f8322960..7ec1d5f8d28 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -39,7 +39,6 @@ #include <linux/sched.h> #include <linux/delay.h> #include <linux/kgdb.h> -#include <linux/init.h> #include <linux/smp.h> #include <linux/nmi.h> #include <linux/hw_breakpoint.h> diff --git a/arch/x86/kernel/ksysfs.c b/arch/x86/kernel/ksysfs.c new file mode 100644 index 00000000000..c2bedaea11f --- /dev/null +++ b/arch/x86/kernel/ksysfs.c @@ -0,0 +1,340 @@ +/* + * Architecture specific sysfs attributes in /sys/kernel + * + * Copyright (C) 2007, Intel Corp. + * Huang Ying <ying.huang@intel.com> + * Copyright (C) 2013, 2013 Red Hat, Inc. + * Dave Young <dyoung@redhat.com> + * + * This file is released under the GPLv2 + */ + +#include <linux/kobject.h> +#include <linux/string.h> +#include <linux/sysfs.h> +#include <linux/init.h> +#include <linux/stat.h> +#include <linux/slab.h> +#include <linux/mm.h> + +#include <asm/io.h> +#include <asm/setup.h> + +static ssize_t version_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "0x%04x\n", boot_params.hdr.version); +} + +static struct kobj_attribute boot_params_version_attr = __ATTR_RO(version); + +static ssize_t boot_params_data_read(struct file *fp, struct kobject *kobj, + struct bin_attribute *bin_attr, + char *buf, loff_t off, size_t count) +{ + memcpy(buf, (void *)&boot_params + off, count); + return count; +} + +static struct bin_attribute boot_params_data_attr = { + .attr = { + .name = "data", + .mode = S_IRUGO, + }, + .read = boot_params_data_read, + .size = sizeof(boot_params), +}; + +static struct attribute *boot_params_version_attrs[] = { + &boot_params_version_attr.attr, + NULL, +}; + +static struct bin_attribute *boot_params_data_attrs[] = { + &boot_params_data_attr, + NULL, +}; + +static struct attribute_group boot_params_attr_group = { + .attrs = boot_params_version_attrs, + .bin_attrs = boot_params_data_attrs, +}; + +static int kobj_to_setup_data_nr(struct kobject *kobj, int *nr) +{ + const char *name; + + name = kobject_name(kobj); + return kstrtoint(name, 10, nr); +} + +static int get_setup_data_paddr(int nr, u64 *paddr) +{ + int i = 0; + struct setup_data *data; + u64 pa_data = boot_params.hdr.setup_data; + + while (pa_data) { + if (nr == i) { + *paddr = pa_data; + return 0; + } + data = ioremap_cache(pa_data, sizeof(*data)); + if (!data) + return -ENOMEM; + + pa_data = data->next; + iounmap(data); + i++; + } + return -EINVAL; +} + +static int __init get_setup_data_size(int nr, size_t *size) +{ + int i = 0; + struct setup_data *data; + u64 pa_data = boot_params.hdr.setup_data; + + while (pa_data) { + data = ioremap_cache(pa_data, sizeof(*data)); + if (!data) + return -ENOMEM; + if (nr == i) { + *size = data->len; + iounmap(data); + return 0; + } + + pa_data = data->next; + iounmap(data); + i++; + } + return -EINVAL; +} + +static ssize_t type_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + int nr, ret; + u64 paddr; + struct setup_data *data; + + ret = kobj_to_setup_data_nr(kobj, &nr); + if (ret) + return ret; + + ret = get_setup_data_paddr(nr, &paddr); + if (ret) + return ret; + data = ioremap_cache(paddr, sizeof(*data)); + if (!data) + return -ENOMEM; + + ret = sprintf(buf, "0x%x\n", data->type); + iounmap(data); + return ret; +} + +static ssize_t setup_data_data_read(struct file *fp, + struct kobject *kobj, + struct bin_attribute *bin_attr, + char *buf, + loff_t off, size_t count) +{ + int nr, ret = 0; + u64 paddr; + struct setup_data *data; + void *p; + + ret = kobj_to_setup_data_nr(kobj, &nr); + if (ret) + return ret; + + ret = get_setup_data_paddr(nr, &paddr); + if (ret) + return ret; + data = ioremap_cache(paddr, sizeof(*data)); + if (!data) + return -ENOMEM; + + if (off > data->len) { + ret = -EINVAL; + goto out; + } + + if (count > data->len - off) + count = data->len - off; + + if (!count) + goto out; + + ret = count; + p = ioremap_cache(paddr + sizeof(*data), data->len); + if (!p) { + ret = -ENOMEM; + goto out; + } + memcpy(buf, p + off, count); + iounmap(p); +out: + iounmap(data); + return ret; +} + +static struct kobj_attribute type_attr = __ATTR_RO(type); + +static struct bin_attribute data_attr = { + .attr = { + .name = "data", + .mode = S_IRUGO, + }, + .read = setup_data_data_read, +}; + +static struct attribute *setup_data_type_attrs[] = { + &type_attr.attr, + NULL, +}; + +static struct bin_attribute *setup_data_data_attrs[] = { + &data_attr, + NULL, +}; + +static struct attribute_group setup_data_attr_group = { + .attrs = setup_data_type_attrs, + .bin_attrs = setup_data_data_attrs, +}; + +static int __init create_setup_data_node(struct kobject *parent, + struct kobject **kobjp, int nr) +{ + int ret = 0; + size_t size; + struct kobject *kobj; + char name[16]; /* should be enough for setup_data nodes numbers */ + snprintf(name, 16, "%d", nr); + + kobj = kobject_create_and_add(name, parent); + if (!kobj) + return -ENOMEM; + + ret = get_setup_data_size(nr, &size); + if (ret) + goto out_kobj; + + data_attr.size = size; + ret = sysfs_create_group(kobj, &setup_data_attr_group); + if (ret) + goto out_kobj; + *kobjp = kobj; + + return 0; +out_kobj: + kobject_put(kobj); + return ret; +} + +static void __init cleanup_setup_data_node(struct kobject *kobj) +{ + sysfs_remove_group(kobj, &setup_data_attr_group); + kobject_put(kobj); +} + +static int __init get_setup_data_total_num(u64 pa_data, int *nr) +{ + int ret = 0; + struct setup_data *data; + + *nr = 0; + while (pa_data) { + *nr += 1; + data = ioremap_cache(pa_data, sizeof(*data)); + if (!data) { + ret = -ENOMEM; + goto out; + } + pa_data = data->next; + iounmap(data); + } + +out: + return ret; +} + +static int __init create_setup_data_nodes(struct kobject *parent) +{ + struct kobject *setup_data_kobj, **kobjp; + u64 pa_data; + int i, j, nr, ret = 0; + + pa_data = boot_params.hdr.setup_data; + if (!pa_data) + return 0; + + setup_data_kobj = kobject_create_and_add("setup_data", parent); + if (!setup_data_kobj) { + ret = -ENOMEM; + goto out; + } + + ret = get_setup_data_total_num(pa_data, &nr); + if (ret) + goto out_setup_data_kobj; + + kobjp = kmalloc(sizeof(*kobjp) * nr, GFP_KERNEL); + if (!kobjp) { + ret = -ENOMEM; + goto out_setup_data_kobj; + } + + for (i = 0; i < nr; i++) { + ret = create_setup_data_node(setup_data_kobj, kobjp + i, i); + if (ret) + goto out_clean_nodes; + } + + kfree(kobjp); + return 0; + +out_clean_nodes: + for (j = i - 1; j > 0; j--) + cleanup_setup_data_node(*(kobjp + j)); + kfree(kobjp); +out_setup_data_kobj: + kobject_put(setup_data_kobj); +out: + return ret; +} + +static int __init boot_params_ksysfs_init(void) +{ + int ret; + struct kobject *boot_params_kobj; + + boot_params_kobj = kobject_create_and_add("boot_params", + kernel_kobj); + if (!boot_params_kobj) { + ret = -ENOMEM; + goto out; + } + + ret = sysfs_create_group(boot_params_kobj, &boot_params_attr_group); + if (ret) + goto out_boot_params_kobj; + + ret = create_setup_data_nodes(boot_params_kobj); + if (ret) + goto out_create_group; + + return 0; +out_create_group: + sysfs_remove_group(boot_params_kobj, &boot_params_attr_group); +out_boot_params_kobj: + kobject_put(boot_params_kobj); +out: + return ret; +} + +arch_initcall(boot_params_ksysfs_init); diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index 5b19e4d78b0..1667b1de8d5 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -9,7 +9,6 @@ #include <linux/mm.h> #include <linux/kexec.h> #include <linux/delay.h> -#include <linux/init.h> #include <linux/numa.h> #include <linux/ftrace.h> #include <linux/suspend.h> diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c index 871be4a84c7..da15918d1c8 100644 --- a/arch/x86/kernel/pci-nommu.c +++ b/arch/x86/kernel/pci-nommu.c @@ -3,7 +3,6 @@ #include <linux/dma-mapping.h> #include <linux/scatterlist.h> #include <linux/string.h> -#include <linux/init.h> #include <linux/gfp.h> #include <linux/pci.h> #include <linux/mm.h> diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 6f1236c29c4..0de43e98ce0 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -24,7 +24,6 @@ #include <linux/interrupt.h> #include <linux/delay.h> #include <linux/reboot.h> -#include <linux/init.h> #include <linux/mc146818rtc.h> #include <linux/module.h> #include <linux/kallsyms.h> diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index da3c599584a..c752cb43e52 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -558,6 +558,17 @@ void native_machine_shutdown(void) { /* Stop the cpus and apics */ #ifdef CONFIG_X86_IO_APIC + /* + * Disabling IO APIC before local APIC is a workaround for + * erratum AVR31 in "Intel Atom Processor C2000 Product Family + * Specification Update". In this situation, interrupts that target + * a Logical Processor whose Local APIC is either in the process of + * being hardware disabled or software disabled are neither delivered + * nor discarded. When this erratum occurs, the processor may hang. + * + * Even without the erratum, it still makes sense to quiet IO APIC + * before disabling Local APIC. + */ disable_IO_APIC(); #endif diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index cb233bc9dee..06853e67035 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -295,6 +295,8 @@ static void __init reserve_brk(void) _brk_start = 0; } +u64 relocated_ramdisk; + #ifdef CONFIG_BLK_DEV_INITRD static u64 __init get_ramdisk_image(void) @@ -321,25 +323,24 @@ static void __init relocate_initrd(void) u64 ramdisk_image = get_ramdisk_image(); u64 ramdisk_size = get_ramdisk_size(); u64 area_size = PAGE_ALIGN(ramdisk_size); - u64 ramdisk_here; unsigned long slop, clen, mapaddr; char *p, *q; /* We need to move the initrd down into directly mapped mem */ - ramdisk_here = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped), - area_size, PAGE_SIZE); + relocated_ramdisk = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped), + area_size, PAGE_SIZE); - if (!ramdisk_here) + if (!relocated_ramdisk) panic("Cannot find place for new RAMDISK of size %lld\n", - ramdisk_size); + ramdisk_size); /* Note: this includes all the mem currently occupied by the initrd, we rely on that fact to keep the data intact. */ - memblock_reserve(ramdisk_here, area_size); - initrd_start = ramdisk_here + PAGE_OFFSET; + memblock_reserve(relocated_ramdisk, area_size); + initrd_start = relocated_ramdisk + PAGE_OFFSET; initrd_end = initrd_start + ramdisk_size; printk(KERN_INFO "Allocated new RAMDISK: [mem %#010llx-%#010llx]\n", - ramdisk_here, ramdisk_here + ramdisk_size - 1); + relocated_ramdisk, relocated_ramdisk + ramdisk_size - 1); q = (char *)initrd_start; @@ -363,7 +364,7 @@ static void __init relocate_initrd(void) printk(KERN_INFO "Move RAMDISK from [mem %#010llx-%#010llx] to" " [mem %#010llx-%#010llx]\n", ramdisk_image, ramdisk_image + ramdisk_size - 1, - ramdisk_here, ramdisk_here + ramdisk_size - 1); + relocated_ramdisk, relocated_ramdisk + ramdisk_size - 1); } static void __init early_reserve_initrd(void) @@ -447,6 +448,9 @@ static void __init parse_setup_data(void) case SETUP_DTB: add_dtb(pa_data); break; + case SETUP_EFI: + parse_efi_setup(pa_data, data_len); + break; default: break; } @@ -824,6 +828,20 @@ static void __init trim_low_memory_range(void) } /* + * Dump out kernel offset information on panic. + */ +static int +dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p) +{ + pr_emerg("Kernel Offset: 0x%lx from 0x%lx " + "(relocation range: 0x%lx-0x%lx)\n", + (unsigned long)&_text - __START_KERNEL, __START_KERNEL, + __START_KERNEL_map, MODULES_VADDR-1); + + return 0; +} + +/* * Determine if we were loaded by an EFI loader. If so, then we have also been * passed the efi memmap, systab, etc., so we should use these data structures * for initialization. Note, the efi init code path is determined by the @@ -924,8 +942,6 @@ void __init setup_arch(char **cmdline_p) iomem_resource.end = (1ULL << boot_cpu_data.x86_phys_bits) - 1; setup_memory_map(); parse_setup_data(); - /* update the e820_saved too */ - e820_reserve_setup_data(); copy_edd(); @@ -987,6 +1003,8 @@ void __init setup_arch(char **cmdline_p) early_dump_pci_devices(); #endif + /* update the e820_saved too */ + e820_reserve_setup_data(); finish_e820_parsing(); if (efi_enabled(EFI_BOOT)) @@ -1248,3 +1266,15 @@ void __init i386_reserve_resources(void) } #endif /* CONFIG_X86_32 */ + +static struct notifier_block kernel_offset_notifier = { + .notifier_call = dump_kernel_offset +}; + +static int __init register_kernel_offset_dumper(void) +{ + atomic_notifier_chain_register(&panic_notifier_list, + &kernel_offset_notifier); + return 0; +} +__initcall(register_kernel_offset_dumper); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 85dc05a3aa0..a32da804252 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1312,6 +1312,12 @@ void cpu_disable_common(void) int native_cpu_disable(void) { + int ret; + + ret = check_irq_vectors_for_cpu_disable(); + if (ret) + return ret; + clear_local_APIC(); cpu_disable_common(); @@ -1417,7 +1423,9 @@ static inline void mwait_play_dead(void) * The WBINVD is insufficient due to the spurious-wakeup * case where we return around the loop. */ + mb(); clflush(mwait_ptr); + mb(); __monitor(mwait_ptr, 0, 0); mb(); __mwait(eax, 0); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index b857ed890b4..57409f6b8c6 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -211,21 +211,17 @@ dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \ exception_exit(prev_state); \ } -DO_ERROR_INFO(X86_TRAP_DE, SIGFPE, "divide error", divide_error, FPE_INTDIV, - regs->ip) -DO_ERROR(X86_TRAP_OF, SIGSEGV, "overflow", overflow) -DO_ERROR(X86_TRAP_BR, SIGSEGV, "bounds", bounds) -DO_ERROR_INFO(X86_TRAP_UD, SIGILL, "invalid opcode", invalid_op, ILL_ILLOPN, - regs->ip) -DO_ERROR(X86_TRAP_OLD_MF, SIGFPE, "coprocessor segment overrun", - coprocessor_segment_overrun) -DO_ERROR(X86_TRAP_TS, SIGSEGV, "invalid TSS", invalid_TSS) -DO_ERROR(X86_TRAP_NP, SIGBUS, "segment not present", segment_not_present) +DO_ERROR_INFO(X86_TRAP_DE, SIGFPE, "divide error", divide_error, FPE_INTDIV, regs->ip ) +DO_ERROR (X86_TRAP_OF, SIGSEGV, "overflow", overflow ) +DO_ERROR (X86_TRAP_BR, SIGSEGV, "bounds", bounds ) +DO_ERROR_INFO(X86_TRAP_UD, SIGILL, "invalid opcode", invalid_op, ILL_ILLOPN, regs->ip ) +DO_ERROR (X86_TRAP_OLD_MF, SIGFPE, "coprocessor segment overrun", coprocessor_segment_overrun ) +DO_ERROR (X86_TRAP_TS, SIGSEGV, "invalid TSS", invalid_TSS ) +DO_ERROR (X86_TRAP_NP, SIGBUS, "segment not present", segment_not_present ) #ifdef CONFIG_X86_32 -DO_ERROR(X86_TRAP_SS, SIGBUS, "stack segment", stack_segment) +DO_ERROR (X86_TRAP_SS, SIGBUS, "stack segment", stack_segment ) #endif -DO_ERROR_INFO(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check, - BUS_ADRALN, 0) +DO_ERROR_INFO(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0 ) #ifdef CONFIG_X86_64 /* Runs on IST stack */ diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 930e5d48f56..19e5adb49a2 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -11,6 +11,7 @@ #include <linux/clocksource.h> #include <linux/percpu.h> #include <linux/timex.h> +#include <linux/static_key.h> #include <asm/hpet.h> #include <asm/timer.h> @@ -37,13 +38,244 @@ static int __read_mostly tsc_unstable; erroneous rdtsc usage on !cpu_has_tsc processors */ static int __read_mostly tsc_disabled = -1; +static struct static_key __use_tsc = STATIC_KEY_INIT; + int tsc_clocksource_reliable; + +/* + * Use a ring-buffer like data structure, where a writer advances the head by + * writing a new data entry and a reader advances the tail when it observes a + * new entry. + * + * Writers are made to wait on readers until there's space to write a new + * entry. + * + * This means that we can always use an {offset, mul} pair to compute a ns + * value that is 'roughly' in the right direction, even if we're writing a new + * {offset, mul} pair during the clock read. + * + * The down-side is that we can no longer guarantee strict monotonicity anymore + * (assuming the TSC was that to begin with), because while we compute the + * intersection point of the two clock slopes and make sure the time is + * continuous at the point of switching; we can no longer guarantee a reader is + * strictly before or after the switch point. + * + * It does mean a reader no longer needs to disable IRQs in order to avoid + * CPU-Freq updates messing with his times, and similarly an NMI reader will + * no longer run the risk of hitting half-written state. + */ + +struct cyc2ns { + struct cyc2ns_data data[2]; /* 0 + 2*24 = 48 */ + struct cyc2ns_data *head; /* 48 + 8 = 56 */ + struct cyc2ns_data *tail; /* 56 + 8 = 64 */ +}; /* exactly fits one cacheline */ + +static DEFINE_PER_CPU_ALIGNED(struct cyc2ns, cyc2ns); + +struct cyc2ns_data *cyc2ns_read_begin(void) +{ + struct cyc2ns_data *head; + + preempt_disable(); + + head = this_cpu_read(cyc2ns.head); + /* + * Ensure we observe the entry when we observe the pointer to it. + * matches the wmb from cyc2ns_write_end(). + */ + smp_read_barrier_depends(); + head->__count++; + barrier(); + + return head; +} + +void cyc2ns_read_end(struct cyc2ns_data *head) +{ + barrier(); + /* + * If we're the outer most nested read; update the tail pointer + * when we're done. This notifies possible pending writers + * that we've observed the head pointer and that the other + * entry is now free. + */ + if (!--head->__count) { + /* + * x86-TSO does not reorder writes with older reads; + * therefore once this write becomes visible to another + * cpu, we must be finished reading the cyc2ns_data. + * + * matches with cyc2ns_write_begin(). + */ + this_cpu_write(cyc2ns.tail, head); + } + preempt_enable(); +} + +/* + * Begin writing a new @data entry for @cpu. + * + * Assumes some sort of write side lock; currently 'provided' by the assumption + * that cpufreq will call its notifiers sequentially. + */ +static struct cyc2ns_data *cyc2ns_write_begin(int cpu) +{ + struct cyc2ns *c2n = &per_cpu(cyc2ns, cpu); + struct cyc2ns_data *data = c2n->data; + + if (data == c2n->head) + data++; + + /* XXX send an IPI to @cpu in order to guarantee a read? */ + + /* + * When we observe the tail write from cyc2ns_read_end(), + * the cpu must be done with that entry and its safe + * to start writing to it. + */ + while (c2n->tail == data) + cpu_relax(); + + return data; +} + +static void cyc2ns_write_end(int cpu, struct cyc2ns_data *data) +{ + struct cyc2ns *c2n = &per_cpu(cyc2ns, cpu); + + /* + * Ensure the @data writes are visible before we publish the + * entry. Matches the data-depencency in cyc2ns_read_begin(). + */ + smp_wmb(); + + ACCESS_ONCE(c2n->head) = data; +} + +/* + * Accelerators for sched_clock() + * convert from cycles(64bits) => nanoseconds (64bits) + * basic equation: + * ns = cycles / (freq / ns_per_sec) + * ns = cycles * (ns_per_sec / freq) + * ns = cycles * (10^9 / (cpu_khz * 10^3)) + * ns = cycles * (10^6 / cpu_khz) + * + * Then we use scaling math (suggested by george@mvista.com) to get: + * ns = cycles * (10^6 * SC / cpu_khz) / SC + * ns = cycles * cyc2ns_scale / SC + * + * And since SC is a constant power of two, we can convert the div + * into a shift. + * + * We can use khz divisor instead of mhz to keep a better precision, since + * cyc2ns_scale is limited to 10^6 * 2^10, which fits in 32 bits. + * (mathieu.desnoyers@polymtl.ca) + * + * -johnstul@us.ibm.com "math is hard, lets go shopping!" + */ + +#define CYC2NS_SCALE_FACTOR 10 /* 2^10, carefully chosen */ + +static void cyc2ns_data_init(struct cyc2ns_data *data) +{ + data->cyc2ns_mul = 0; + data->cyc2ns_shift = CYC2NS_SCALE_FACTOR; + data->cyc2ns_offset = 0; + data->__count = 0; +} + +static void cyc2ns_init(int cpu) +{ + struct cyc2ns *c2n = &per_cpu(cyc2ns, cpu); + + cyc2ns_data_init(&c2n->data[0]); + cyc2ns_data_init(&c2n->data[1]); + + c2n->head = c2n->data; + c2n->tail = c2n->data; +} + +static inline unsigned long long cycles_2_ns(unsigned long long cyc) +{ + struct cyc2ns_data *data, *tail; + unsigned long long ns; + + /* + * See cyc2ns_read_*() for details; replicated in order to avoid + * an extra few instructions that came with the abstraction. + * Notable, it allows us to only do the __count and tail update + * dance when its actually needed. + */ + + preempt_disable(); + data = this_cpu_read(cyc2ns.head); + tail = this_cpu_read(cyc2ns.tail); + + if (likely(data == tail)) { + ns = data->cyc2ns_offset; + ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul, CYC2NS_SCALE_FACTOR); + } else { + data->__count++; + + barrier(); + + ns = data->cyc2ns_offset; + ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul, CYC2NS_SCALE_FACTOR); + + barrier(); + + if (!--data->__count) + this_cpu_write(cyc2ns.tail, data); + } + preempt_enable(); + + return ns; +} + +/* XXX surely we already have this someplace in the kernel?! */ +#define DIV_ROUND(n, d) (((n) + ((d) / 2)) / (d)) + +static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu) +{ + unsigned long long tsc_now, ns_now; + struct cyc2ns_data *data; + unsigned long flags; + + local_irq_save(flags); + sched_clock_idle_sleep_event(); + + if (!cpu_khz) + goto done; + + data = cyc2ns_write_begin(cpu); + + rdtscll(tsc_now); + ns_now = cycles_2_ns(tsc_now); + + /* + * Compute a new multiplier as per the above comment and ensure our + * time function is continuous; see the comment near struct + * cyc2ns_data. + */ + data->cyc2ns_mul = DIV_ROUND(NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR, cpu_khz); + data->cyc2ns_shift = CYC2NS_SCALE_FACTOR; + data->cyc2ns_offset = ns_now - + mul_u64_u32_shr(tsc_now, data->cyc2ns_mul, CYC2NS_SCALE_FACTOR); + + cyc2ns_write_end(cpu, data); + +done: + sched_clock_idle_wakeup_event(0); + local_irq_restore(flags); +} /* * Scheduler clock - returns current time in nanosec units. */ u64 native_sched_clock(void) { - u64 this_offset; + u64 tsc_now; /* * Fall back to jiffies if there's no TSC available: @@ -53,16 +285,16 @@ u64 native_sched_clock(void) * very important for it to be as fast as the platform * can achieve it. ) */ - if (unlikely(tsc_disabled)) { + if (!static_key_false(&__use_tsc)) { /* No locking but a rare wrong value is not a big deal: */ return (jiffies_64 - INITIAL_JIFFIES) * (1000000000 / HZ); } /* read the Time Stamp Counter: */ - rdtscll(this_offset); + rdtscll(tsc_now); /* return the value in ns */ - return __cycles_2_ns(this_offset); + return cycles_2_ns(tsc_now); } /* We need to define a real function for sched_clock, to override the @@ -419,6 +651,16 @@ unsigned long native_calibrate_tsc(void) unsigned long flags, latch, ms, fast_calibrate; int hpet = is_hpet_enabled(), i, loopmin; + /* Calibrate TSC using MSR for Intel Atom SoCs */ + local_irq_save(flags); + i = try_msr_calibrate_tsc(&fast_calibrate); + local_irq_restore(flags); + if (i >= 0) { + if (i == 0) + pr_warn("Fast TSC calibration using MSR failed\n"); + return fast_calibrate; + } + local_irq_save(flags); fast_calibrate = quick_pit_calibrate(); local_irq_restore(flags); @@ -589,61 +831,11 @@ int recalibrate_cpu_khz(void) EXPORT_SYMBOL(recalibrate_cpu_khz); -/* Accelerators for sched_clock() - * convert from cycles(64bits) => nanoseconds (64bits) - * basic equation: - * ns = cycles / (freq / ns_per_sec) - * ns = cycles * (ns_per_sec / freq) - * ns = cycles * (10^9 / (cpu_khz * 10^3)) - * ns = cycles * (10^6 / cpu_khz) - * - * Then we use scaling math (suggested by george@mvista.com) to get: - * ns = cycles * (10^6 * SC / cpu_khz) / SC - * ns = cycles * cyc2ns_scale / SC - * - * And since SC is a constant power of two, we can convert the div - * into a shift. - * - * We can use khz divisor instead of mhz to keep a better precision, since - * cyc2ns_scale is limited to 10^6 * 2^10, which fits in 32 bits. - * (mathieu.desnoyers@polymtl.ca) - * - * -johnstul@us.ibm.com "math is hard, lets go shopping!" - */ - -DEFINE_PER_CPU(unsigned long, cyc2ns); -DEFINE_PER_CPU(unsigned long long, cyc2ns_offset); - -static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu) -{ - unsigned long long tsc_now, ns_now, *offset; - unsigned long flags, *scale; - - local_irq_save(flags); - sched_clock_idle_sleep_event(); - - scale = &per_cpu(cyc2ns, cpu); - offset = &per_cpu(cyc2ns_offset, cpu); - - rdtscll(tsc_now); - ns_now = __cycles_2_ns(tsc_now); - - if (cpu_khz) { - *scale = ((NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR) + - cpu_khz / 2) / cpu_khz; - *offset = ns_now - mult_frac(tsc_now, *scale, - (1UL << CYC2NS_SCALE_FACTOR)); - } - - sched_clock_idle_wakeup_event(0); - local_irq_restore(flags); -} - static unsigned long long cyc2ns_suspend; void tsc_save_sched_clock_state(void) { - if (!sched_clock_stable) + if (!sched_clock_stable()) return; cyc2ns_suspend = sched_clock(); @@ -663,16 +855,26 @@ void tsc_restore_sched_clock_state(void) unsigned long flags; int cpu; - if (!sched_clock_stable) + if (!sched_clock_stable()) return; local_irq_save(flags); - __this_cpu_write(cyc2ns_offset, 0); + /* + * We're comming out of suspend, there's no concurrency yet; don't + * bother being nice about the RCU stuff, just write to both + * data fields. + */ + + this_cpu_write(cyc2ns.data[0].cyc2ns_offset, 0); + this_cpu_write(cyc2ns.data[1].cyc2ns_offset, 0); + offset = cyc2ns_suspend - sched_clock(); - for_each_possible_cpu(cpu) - per_cpu(cyc2ns_offset, cpu) = offset; + for_each_possible_cpu(cpu) { + per_cpu(cyc2ns.data[0].cyc2ns_offset, cpu) = offset; + per_cpu(cyc2ns.data[1].cyc2ns_offset, cpu) = offset; + } local_irq_restore(flags); } @@ -795,7 +997,7 @@ void mark_tsc_unstable(char *reason) { if (!tsc_unstable) { tsc_unstable = 1; - sched_clock_stable = 0; + clear_sched_clock_stable(); disable_sched_clock_irqtime(); pr_info("Marking TSC unstable due to %s\n", reason); /* Change only the rating, when not registered */ @@ -995,14 +1197,18 @@ void __init tsc_init(void) * speed as the bootup CPU. (cpufreq notifiers will fix this * up if their speed diverges) */ - for_each_possible_cpu(cpu) + for_each_possible_cpu(cpu) { + cyc2ns_init(cpu); set_cyc2ns_scale(cpu_khz, cpu); + } if (tsc_disabled > 0) return; /* now allow native_sched_clock() to use rdtsc */ + tsc_disabled = 0; + static_key_slow_inc(&__use_tsc); if (!no_sched_irq_time) enable_sched_clock_irqtime(); diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c new file mode 100644 index 00000000000..8b5434f4389 --- /dev/null +++ b/arch/x86/kernel/tsc_msr.c @@ -0,0 +1,127 @@ +/* + * tsc_msr.c - MSR based TSC calibration on Intel Atom SoC platforms. + * + * TSC in Intel Atom SoC runs at a constant rate which can be figured + * by this formula: + * <maximum core-clock to bus-clock ratio> * <maximum resolved frequency> + * See Intel 64 and IA-32 System Programming Guid section 16.12 and 30.11.5 + * for details. + * Especially some Intel Atom SoCs don't have PIT(i8254) or HPET, so MSR + * based calibration is the only option. + * + * + * Copyright (C) 2013 Intel Corporation + * Author: Bin Gao <bin.gao@intel.com> + * + * This file is released under the GPLv2. + */ + +#include <linux/kernel.h> +#include <asm/processor.h> +#include <asm/setup.h> +#include <asm/apic.h> +#include <asm/param.h> + +/* CPU reference clock frequency: in KHz */ +#define FREQ_83 83200 +#define FREQ_100 99840 +#define FREQ_133 133200 +#define FREQ_166 166400 + +#define MAX_NUM_FREQS 8 + +/* + * According to Intel 64 and IA-32 System Programming Guide, + * if MSR_PERF_STAT[31] is set, the maximum resolved bus ratio can be + * read in MSR_PLATFORM_ID[12:8], otherwise in MSR_PERF_STAT[44:40]. + * Unfortunately some Intel Atom SoCs aren't quite compliant to this, + * so we need manually differentiate SoC families. This is what the + * field msr_plat does. + */ +struct freq_desc { + u8 x86_family; /* CPU family */ + u8 x86_model; /* model */ + u8 msr_plat; /* 1: use MSR_PLATFORM_INFO, 0: MSR_IA32_PERF_STATUS */ + u32 freqs[MAX_NUM_FREQS]; +}; + +static struct freq_desc freq_desc_tables[] = { + /* PNW */ + { 6, 0x27, 0, { 0, 0, 0, 0, 0, FREQ_100, 0, FREQ_83 } }, + /* CLV+ */ + { 6, 0x35, 0, { 0, FREQ_133, 0, 0, 0, FREQ_100, 0, FREQ_83 } }, + /* TNG */ + { 6, 0x4a, 1, { 0, FREQ_100, FREQ_133, 0, 0, 0, 0, 0 } }, + /* VLV2 */ + { 6, 0x37, 1, { 0, FREQ_100, FREQ_133, FREQ_166, 0, 0, 0, 0 } }, + /* ANN */ + { 6, 0x5a, 1, { FREQ_83, FREQ_100, FREQ_133, FREQ_100, 0, 0, 0, 0 } }, +}; + +static int match_cpu(u8 family, u8 model) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(freq_desc_tables); i++) { + if ((family == freq_desc_tables[i].x86_family) && + (model == freq_desc_tables[i].x86_model)) + return i; + } + + return -1; +} + +/* Map CPU reference clock freq ID(0-7) to CPU reference clock freq(KHz) */ +#define id_to_freq(cpu_index, freq_id) \ + (freq_desc_tables[cpu_index].freqs[freq_id]) + +/* + * Do MSR calibration only for known/supported CPUs. + * Return values: + * -1: CPU is unknown/unsupported for MSR based calibration + * 0: CPU is known/supported, but calibration failed + * 1: CPU is known/supported, and calibration succeeded + */ +int try_msr_calibrate_tsc(unsigned long *fast_calibrate) +{ + int cpu_index; + u32 lo, hi, ratio, freq_id, freq; + + cpu_index = match_cpu(boot_cpu_data.x86, boot_cpu_data.x86_model); + if (cpu_index < 0) + return -1; + + *fast_calibrate = 0; + + if (freq_desc_tables[cpu_index].msr_plat) { + rdmsr(MSR_PLATFORM_INFO, lo, hi); + ratio = (lo >> 8) & 0x1f; + } else { + rdmsr(MSR_IA32_PERF_STATUS, lo, hi); + ratio = (hi >> 8) & 0x1f; + } + pr_info("Maximum core-clock to bus-clock ratio: 0x%x\n", ratio); + + if (!ratio) + return 0; + + /* Get FSB FREQ ID */ + rdmsr(MSR_FSB_FREQ, lo, hi); + freq_id = lo & 0x7; + freq = id_to_freq(cpu_index, freq_id); + pr_info("Resolved frequency ID: %u, frequency: %u KHz\n", + freq_id, freq); + if (!freq) + return 0; + + /* TSC frequency = maximum resolved freq * maximum resolved bus ratio */ + *fast_calibrate = freq * ratio; + pr_info("TSC runs at %lu KHz\n", *fast_calibrate); + +#ifdef CONFIG_X86_LOCAL_APIC + lapic_timer_frequency = (freq * 1000) / HZ; + pr_info("lapic_timer_frequency = %d\n", lapic_timer_frequency); +#endif + + return 1; +} diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index adfdf56a371..26488487bc6 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -16,7 +16,6 @@ */ #include <linux/spinlock.h> #include <linux/kernel.h> -#include <linux/init.h> #include <linux/smp.h> #include <linux/nmi.h> #include <asm/tsc.h> diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 021783b1f46..e48b674639c 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -136,9 +136,9 @@ void arch_teardown_msi_irq(unsigned int irq) x86_msi.teardown_msi_irq(irq); } -void arch_restore_msi_irqs(struct pci_dev *dev, int irq) +void arch_restore_msi_irqs(struct pci_dev *dev) { - x86_msi.restore_msi_irqs(dev, irq); + x86_msi.restore_msi_irqs(dev); } u32 arch_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) { diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index 422fd822347..a4b451c6add 100644 --- a/arch/x86/kernel/xsave.c +++ b/arch/x86/kernel/xsave.c @@ -562,6 +562,16 @@ static void __init xstate_enable_boot_cpu(void) if (cpu_has_xsaveopt && eagerfpu != DISABLE) eagerfpu = ENABLE; + if (pcntxt_mask & XSTATE_EAGER) { + if (eagerfpu == DISABLE) { + pr_err("eagerfpu not present, disabling some xstate features: 0x%llx\n", + pcntxt_mask & XSTATE_EAGER); + pcntxt_mask &= ~XSTATE_EAGER; + } else { + eagerfpu = ENABLE; + } + } + pr_info("enabled xstate_bv 0x%llx, cntxt size 0x%x\n", pcntxt_mask, xstate_size); } |