diff options
Diffstat (limited to 'arch/x86/kernel')
106 files changed, 8048 insertions, 5718 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index ada2e2d6be3e..5d4502c8b983 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -28,8 +28,7 @@ obj-$(CONFIG_X86_32) += i386_ksyms_32.o obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o obj-$(CONFIG_X86_64) += mcount_64.o obj-y += syscall_$(BITS).o vsyscall_gtod.o -obj-$(CONFIG_X86_64) += vsyscall_64.o -obj-$(CONFIG_X86_64) += vsyscall_emu_64.o +obj-$(CONFIG_X86_VSYSCALL_EMULATION) += vsyscall_64.o vsyscall_emu_64.o obj-$(CONFIG_X86_ESPFIX64) += espfix_64.o obj-$(CONFIG_SYSFS) += ksysfs.o obj-y += bootflag.o e820.o @@ -39,8 +38,6 @@ obj-y += tsc.o tsc_msr.o io_delay.o rtc.o obj-y += pci-iommu_table.o obj-y += resource.o -obj-$(CONFIG_PREEMPT) += preempt.o - obj-y += process.o obj-y += i387.o xsave.o obj-y += ptrace.o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index b436fc735aa4..d1626364a28a 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -76,6 +76,19 @@ int acpi_fix_pin2_polarity __initdata; static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE; #endif +/* + * Locks related to IOAPIC hotplug + * Hotplug side: + * ->device_hotplug_lock + * ->acpi_ioapic_lock + * ->ioapic_lock + * Interrupt mapping side: + * ->acpi_ioapic_lock + * ->ioapic_mutex + * ->ioapic_lock + */ +static DEFINE_MUTEX(acpi_ioapic_lock); + /* -------------------------------------------------------------------------- Boot-time Configuration -------------------------------------------------------------------------- */ @@ -395,10 +408,6 @@ static int mp_register_gsi(struct device *dev, u32 gsi, int trigger, if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC) return gsi; - /* Don't set up the ACPI SCI because it's already set up */ - if (acpi_gbl_FADT.sci_interrupt == gsi) - return gsi; - trigger = trigger == ACPI_EDGE_SENSITIVE ? 0 : 1; polarity = polarity == ACPI_ACTIVE_HIGH ? 0 : 1; node = dev ? dev_to_node(dev) : NUMA_NO_NODE; @@ -411,7 +420,8 @@ static int mp_register_gsi(struct device *dev, u32 gsi, int trigger, if (irq < 0) return irq; - if (enable_update_mptable) + /* Don't set up the ACPI SCI because it's already set up */ + if (enable_update_mptable && acpi_gbl_FADT.sci_interrupt != gsi) mp_config_acpi_gsi(dev, gsi, trigger, polarity); return irq; @@ -424,9 +434,6 @@ static void mp_unregister_gsi(u32 gsi) if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC) return; - if (acpi_gbl_FADT.sci_interrupt == gsi) - return; - irq = mp_map_gsi_to_irq(gsi, 0); if (irq > 0) mp_unmap_irq(irq); @@ -604,14 +611,20 @@ void __init acpi_pic_sci_set_trigger(unsigned int irq, u16 trigger) int acpi_gsi_to_irq(u32 gsi, unsigned int *irqp) { - int irq = mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC | IOAPIC_MAP_CHECK); + int irq; - if (irq >= 0) { + if (acpi_irq_model == ACPI_IRQ_MODEL_PIC) { + *irqp = gsi; + } else { + mutex_lock(&acpi_ioapic_lock); + irq = mp_map_gsi_to_irq(gsi, + IOAPIC_MAP_ALLOC | IOAPIC_MAP_CHECK); + mutex_unlock(&acpi_ioapic_lock); + if (irq < 0) + return -1; *irqp = irq; - return 0; } - - return -1; + return 0; } EXPORT_SYMBOL_GPL(acpi_gsi_to_irq); @@ -646,7 +659,9 @@ static int acpi_register_gsi_ioapic(struct device *dev, u32 gsi, int irq = gsi; #ifdef CONFIG_X86_IO_APIC + mutex_lock(&acpi_ioapic_lock); irq = mp_register_gsi(dev, gsi, trigger, polarity); + mutex_unlock(&acpi_ioapic_lock); #endif return irq; @@ -655,7 +670,9 @@ static int acpi_register_gsi_ioapic(struct device *dev, u32 gsi, static void acpi_unregister_gsi_ioapic(u32 gsi) { #ifdef CONFIG_X86_IO_APIC + mutex_lock(&acpi_ioapic_lock); mp_unregister_gsi(gsi); + mutex_unlock(&acpi_ioapic_lock); #endif } @@ -686,6 +703,7 @@ void acpi_unregister_gsi(u32 gsi) } EXPORT_SYMBOL_GPL(acpi_unregister_gsi); +#ifdef CONFIG_X86_LOCAL_APIC static void __init acpi_set_irq_model_ioapic(void) { acpi_irq_model = ACPI_IRQ_MODEL_IOAPIC; @@ -693,6 +711,7 @@ static void __init acpi_set_irq_model_ioapic(void) __acpi_unregister_gsi = acpi_unregister_gsi_ioapic; acpi_ioapic = 1; } +#endif /* * ACPI based hotplug support for CPU @@ -731,13 +750,13 @@ static int _acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu) } /* wrapper to silence section mismatch warning */ -int __ref acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu) +int __ref acpi_map_cpu(acpi_handle handle, int physid, int *pcpu) { return _acpi_map_lsapic(handle, physid, pcpu); } -EXPORT_SYMBOL(acpi_map_lsapic); +EXPORT_SYMBOL(acpi_map_cpu); -int acpi_unmap_lsapic(int cpu) +int acpi_unmap_cpu(int cpu) { #ifdef CONFIG_ACPI_NUMA set_apicid_to_node(per_cpu(x86_cpu_to_apicid, cpu), NUMA_NO_NODE); @@ -749,26 +768,79 @@ int acpi_unmap_lsapic(int cpu) return (0); } - -EXPORT_SYMBOL(acpi_unmap_lsapic); +EXPORT_SYMBOL(acpi_unmap_cpu); #endif /* CONFIG_ACPI_HOTPLUG_CPU */ int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base) { - /* TBD */ - return -EINVAL; -} + int ret = -ENOSYS; +#ifdef CONFIG_ACPI_HOTPLUG_IOAPIC + int ioapic_id; + u64 addr; + struct ioapic_domain_cfg cfg = { + .type = IOAPIC_DOMAIN_DYNAMIC, + .ops = &acpi_irqdomain_ops, + }; + + ioapic_id = acpi_get_ioapic_id(handle, gsi_base, &addr); + if (ioapic_id < 0) { + unsigned long long uid; + acpi_status status; + + status = acpi_evaluate_integer(handle, METHOD_NAME__UID, + NULL, &uid); + if (ACPI_FAILURE(status)) { + acpi_handle_warn(handle, "failed to get IOAPIC ID.\n"); + return -EINVAL; + } + ioapic_id = (int)uid; + } + mutex_lock(&acpi_ioapic_lock); + ret = mp_register_ioapic(ioapic_id, phys_addr, gsi_base, &cfg); + mutex_unlock(&acpi_ioapic_lock); +#endif + + return ret; +} EXPORT_SYMBOL(acpi_register_ioapic); int acpi_unregister_ioapic(acpi_handle handle, u32 gsi_base) { - /* TBD */ - return -EINVAL; -} + int ret = -ENOSYS; + +#ifdef CONFIG_ACPI_HOTPLUG_IOAPIC + mutex_lock(&acpi_ioapic_lock); + ret = mp_unregister_ioapic(gsi_base); + mutex_unlock(&acpi_ioapic_lock); +#endif + return ret; +} EXPORT_SYMBOL(acpi_unregister_ioapic); +/** + * acpi_ioapic_registered - Check whether IOAPIC assoicatied with @gsi_base + * has been registered + * @handle: ACPI handle of the IOAPIC deivce + * @gsi_base: GSI base associated with the IOAPIC + * + * Assume caller holds some type of lock to serialize acpi_ioapic_registered() + * with acpi_register_ioapic()/acpi_unregister_ioapic(). + */ +int acpi_ioapic_registered(acpi_handle handle, u32 gsi_base) +{ + int ret = 0; + +#ifdef CONFIG_ACPI_HOTPLUG_IOAPIC + mutex_lock(&acpi_ioapic_lock); + ret = mp_ioapic_registered(gsi_base); + mutex_unlock(&acpi_ioapic_lock); +#endif + + return ret; +} + static int __init acpi_parse_sbf(struct acpi_table_header *table) { struct acpi_table_boot *sb; @@ -1181,7 +1253,9 @@ static void __init acpi_process_madt(void) /* * Parse MADT IO-APIC entries */ + mutex_lock(&acpi_ioapic_lock); error = acpi_parse_madt_ioapic_entries(); + mutex_unlock(&acpi_ioapic_lock); if (!error) { acpi_set_irq_model_ioapic(); diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index f04dbb3069b8..5caed1dd7ccf 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -21,6 +21,7 @@ const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M10H_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M30H_NB_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M60H_NB_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F3) }, {} @@ -30,6 +31,7 @@ EXPORT_SYMBOL(amd_nb_misc_ids); static const struct pci_device_id amd_nb_link_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M30H_NB_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M60H_NB_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F4) }, {} diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c index af5b08ab3b71..b708738d016e 100644 --- a/arch/x86/kernel/apb_timer.c +++ b/arch/x86/kernel/apb_timer.c @@ -146,7 +146,7 @@ static inline int is_apbt_capable(void) static int __init apbt_clockevent_register(void) { struct sfi_timer_table_entry *mtmr; - struct apbt_dev *adev = &__get_cpu_var(cpu_apbt_dev); + struct apbt_dev *adev = this_cpu_ptr(&cpu_apbt_dev); mtmr = sfi_get_mtmr(APBT_CLOCKEVENT0_NUM); if (mtmr == NULL) { @@ -185,8 +185,6 @@ static void apbt_setup_irq(struct apbt_dev *adev) irq_modify_status(adev->irq, 0, IRQ_MOVE_PCNTXT); irq_set_affinity(adev->irq, cpumask_of(adev->cpu)); - /* APB timer irqs are set up as mp_irqs, timer is edge type */ - __irq_set_handler(adev->irq, handle_edge_irq, 0, "edge"); } /* Should be called with per cpu */ @@ -200,7 +198,7 @@ void apbt_setup_secondary_clock(void) if (!cpu) return; - adev = &__get_cpu_var(cpu_apbt_dev); + adev = this_cpu_ptr(&cpu_apbt_dev); if (!adev->timer) { adev->timer = dw_apb_clockevent_init(cpu, adev->name, APBT_CLOCKEVENT_RATING, adev_virt_addr(adev), diff --git a/arch/x86/kernel/apic/Makefile b/arch/x86/kernel/apic/Makefile index dcb5b15401ce..8bb12ddc5db8 100644 --- a/arch/x86/kernel/apic/Makefile +++ b/arch/x86/kernel/apic/Makefile @@ -2,10 +2,12 @@ # Makefile for local APIC drivers and for the IO-APIC code # -obj-$(CONFIG_X86_LOCAL_APIC) += apic.o apic_noop.o ipi.o +obj-$(CONFIG_X86_LOCAL_APIC) += apic.o apic_noop.o ipi.o vector.o obj-y += hw_nmi.o obj-$(CONFIG_X86_IO_APIC) += io_apic.o +obj-$(CONFIG_PCI_MSI) += msi.o +obj-$(CONFIG_HT_IRQ) += htirq.o obj-$(CONFIG_SMP) += ipi.o ifeq ($(CONFIG_X86_64),y) diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 67760275544b..29b5b18afa27 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -196,7 +196,7 @@ static int disable_apic_timer __initdata; int local_apic_timer_c2_ok; EXPORT_SYMBOL_GPL(local_apic_timer_c2_ok); -int first_system_vector = 0xfe; +int first_system_vector = FIRST_SYSTEM_VECTOR; /* * Debug level, exported for io_apic.c @@ -561,7 +561,7 @@ static DEFINE_PER_CPU(struct clock_event_device, lapic_events); */ static void setup_APIC_timer(void) { - struct clock_event_device *levt = &__get_cpu_var(lapic_events); + struct clock_event_device *levt = this_cpu_ptr(&lapic_events); if (this_cpu_has(X86_FEATURE_ARAT)) { lapic_clockevent.features &= ~CLOCK_EVT_FEAT_C3STOP; @@ -696,7 +696,7 @@ calibrate_by_pmtimer(long deltapm, long *delta, long *deltatsc) static int __init calibrate_APIC_clock(void) { - struct clock_event_device *levt = &__get_cpu_var(lapic_events); + struct clock_event_device *levt = this_cpu_ptr(&lapic_events); void (*real_handler)(struct clock_event_device *dev); unsigned long deltaj; long delta, deltatsc; @@ -1297,7 +1297,7 @@ void setup_local_APIC(void) unsigned int value, queued; int i, j, acked = 0; unsigned long long tsc = 0, ntsc; - long long max_loops = cpu_khz; + long long max_loops = cpu_khz ? cpu_khz : 1000000; if (cpu_has_tsc) rdtscll(tsc); @@ -1383,7 +1383,7 @@ void setup_local_APIC(void) break; } if (queued) { - if (cpu_has_tsc) { + if (cpu_has_tsc && cpu_khz) { rdtscll(ntsc); max_loops = (cpu_khz << 10) - (ntsc - tsc); } else @@ -1930,7 +1930,7 @@ int __init APIC_init_uniprocessor(void) /* * This interrupt should _never_ happen with our APIC/SMP architecture */ -static inline void __smp_spurious_interrupt(void) +static inline void __smp_spurious_interrupt(u8 vector) { u32 v; @@ -1939,30 +1939,32 @@ static inline void __smp_spurious_interrupt(void) * if it is a vectored one. Just in case... * Spurious interrupts should not be ACKed. */ - v = apic_read(APIC_ISR + ((SPURIOUS_APIC_VECTOR & ~0x1f) >> 1)); - if (v & (1 << (SPURIOUS_APIC_VECTOR & 0x1f))) + v = apic_read(APIC_ISR + ((vector & ~0x1f) >> 1)); + if (v & (1 << (vector & 0x1f))) ack_APIC_irq(); inc_irq_stat(irq_spurious_count); /* see sw-dev-man vol 3, chapter 7.4.13.5 */ - pr_info("spurious APIC interrupt on CPU#%d, " - "should never happen.\n", smp_processor_id()); + pr_info("spurious APIC interrupt through vector %02x on CPU#%d, " + "should never happen.\n", vector, smp_processor_id()); } __visible void smp_spurious_interrupt(struct pt_regs *regs) { entering_irq(); - __smp_spurious_interrupt(); + __smp_spurious_interrupt(~regs->orig_ax); exiting_irq(); } __visible void smp_trace_spurious_interrupt(struct pt_regs *regs) { + u8 vector = ~regs->orig_ax; + entering_irq(); - trace_spurious_apic_entry(SPURIOUS_APIC_VECTOR); - __smp_spurious_interrupt(); - trace_spurious_apic_exit(SPURIOUS_APIC_VECTOR); + trace_spurious_apic_entry(vector); + __smp_spurious_interrupt(vector); + trace_spurious_apic_exit(vector); exiting_irq(); } diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index ae915391ebec..c2fd21fed002 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -32,7 +32,7 @@ static int numachip_system __read_mostly; -static const struct apic apic_numachip __read_mostly; +static const struct apic apic_numachip; static unsigned int get_apic_id(unsigned long x) { @@ -40,7 +40,7 @@ static unsigned int get_apic_id(unsigned long x) unsigned int id; rdmsrl(MSR_FAM10H_NODE_ID, value); - id = ((x >> 24) & 0xffU) | ((value << 2) & 0x3f00U); + id = ((x >> 24) & 0xffU) | ((value << 2) & 0xff00U); return id; } @@ -145,7 +145,7 @@ static void numachip_send_IPI_all(int vector) static void numachip_send_IPI_self(int vector) { - __default_send_IPI_shortcut(APIC_DEST_SELF, vector, APIC_DEST_PHYSICAL); + apic_write(APIC_SELF_IPI, vector); } static int __init numachip_probe(void) @@ -153,20 +153,8 @@ static int __init numachip_probe(void) return apic == &apic_numachip; } -static void __init map_csrs(void) -{ - printk(KERN_INFO "NumaChip: Mapping local CSR space (%016llx - %016llx)\n", - NUMACHIP_LCSR_BASE, NUMACHIP_LCSR_BASE + NUMACHIP_LCSR_SIZE - 1); - init_extra_mapping_uc(NUMACHIP_LCSR_BASE, NUMACHIP_LCSR_SIZE); - - printk(KERN_INFO "NumaChip: Mapping global CSR space (%016llx - %016llx)\n", - NUMACHIP_GCSR_BASE, NUMACHIP_GCSR_BASE + NUMACHIP_GCSR_SIZE - 1); - init_extra_mapping_uc(NUMACHIP_GCSR_BASE, NUMACHIP_GCSR_SIZE); -} - static void fixup_cpu_id(struct cpuinfo_x86 *c, int node) { - if (c->phys_proc_id != node) { c->phys_proc_id = node; per_cpu(cpu_llc_id, smp_processor_id()) = node; @@ -175,19 +163,15 @@ static void fixup_cpu_id(struct cpuinfo_x86 *c, int node) static int __init numachip_system_init(void) { - unsigned int val; - if (!numachip_system) return 0; + init_extra_mapping_uc(NUMACHIP_LCSR_BASE, NUMACHIP_LCSR_SIZE); + init_extra_mapping_uc(NUMACHIP_GCSR_BASE, NUMACHIP_GCSR_SIZE); + x86_cpuinit.fixup_cpu_id = fixup_cpu_id; x86_init.pci.arch_init = pci_numachip_init; - map_csrs(); - - val = read_lcsr(CSR_G0_NODE_IDS); - printk(KERN_INFO "NumaChip: Local NodeID = %08x\n", val); - return 0; } early_initcall(numachip_system_init); diff --git a/arch/x86/kernel/apic/htirq.c b/arch/x86/kernel/apic/htirq.c new file mode 100644 index 000000000000..816f36e979ad --- /dev/null +++ b/arch/x86/kernel/apic/htirq.c @@ -0,0 +1,107 @@ +/* + * Support Hypertransport IRQ + * + * Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo + * Moved from arch/x86/kernel/apic/io_apic.c. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include <linux/mm.h> +#include <linux/interrupt.h> +#include <linux/init.h> +#include <linux/device.h> +#include <linux/pci.h> +#include <linux/htirq.h> +#include <asm/hw_irq.h> +#include <asm/apic.h> +#include <asm/hypertransport.h> + +/* + * Hypertransport interrupt support + */ +static void target_ht_irq(unsigned int irq, unsigned int dest, u8 vector) +{ + struct ht_irq_msg msg; + + fetch_ht_irq_msg(irq, &msg); + + msg.address_lo &= ~(HT_IRQ_LOW_VECTOR_MASK | HT_IRQ_LOW_DEST_ID_MASK); + msg.address_hi &= ~(HT_IRQ_HIGH_DEST_ID_MASK); + + msg.address_lo |= HT_IRQ_LOW_VECTOR(vector) | HT_IRQ_LOW_DEST_ID(dest); + msg.address_hi |= HT_IRQ_HIGH_DEST_ID(dest); + + write_ht_irq_msg(irq, &msg); +} + +static int +ht_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) +{ + struct irq_cfg *cfg = irqd_cfg(data); + unsigned int dest; + int ret; + + ret = apic_set_affinity(data, mask, &dest); + if (ret) + return ret; + + target_ht_irq(data->irq, dest, cfg->vector); + return IRQ_SET_MASK_OK_NOCOPY; +} + +static struct irq_chip ht_irq_chip = { + .name = "PCI-HT", + .irq_mask = mask_ht_irq, + .irq_unmask = unmask_ht_irq, + .irq_ack = apic_ack_edge, + .irq_set_affinity = ht_set_affinity, + .irq_retrigger = apic_retrigger_irq, + .flags = IRQCHIP_SKIP_SET_WAKE, +}; + +int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev) +{ + struct irq_cfg *cfg; + struct ht_irq_msg msg; + unsigned dest; + int err; + + if (disable_apic) + return -ENXIO; + + cfg = irq_cfg(irq); + err = assign_irq_vector(irq, cfg, apic->target_cpus()); + if (err) + return err; + + err = apic->cpu_mask_to_apicid_and(cfg->domain, + apic->target_cpus(), &dest); + if (err) + return err; + + msg.address_hi = HT_IRQ_HIGH_DEST_ID(dest); + + msg.address_lo = + HT_IRQ_LOW_BASE | + HT_IRQ_LOW_DEST_ID(dest) | + HT_IRQ_LOW_VECTOR(cfg->vector) | + ((apic->irq_dest_mode == 0) ? + HT_IRQ_LOW_DM_PHYSICAL : + HT_IRQ_LOW_DM_LOGICAL) | + HT_IRQ_LOW_RQEOI_EDGE | + ((apic->irq_delivery_mode != dest_LowestPrio) ? + HT_IRQ_LOW_MT_FIXED : + HT_IRQ_LOW_MT_ARBITRATED) | + HT_IRQ_LOW_IRQ_MASKED; + + write_ht_irq_msg(irq, &msg); + + irq_set_chip_and_handler_name(irq, &ht_irq_chip, + handle_edge_irq, "edge"); + + dev_dbg(&dev->dev, "irq %d for HT\n", irq); + + return 0; +} diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c index 6a1e71bde323..6873ab925d00 100644 --- a/arch/x86/kernel/apic/hw_nmi.c +++ b/arch/x86/kernel/apic/hw_nmi.c @@ -18,6 +18,7 @@ #include <linux/nmi.h> #include <linux/module.h> #include <linux/delay.h> +#include <linux/seq_buf.h> #ifdef CONFIG_HARDLOCKUP_DETECTOR u64 hw_nmi_get_sample_period(int watchdog_thresh) @@ -29,14 +30,35 @@ u64 hw_nmi_get_sample_period(int watchdog_thresh) #ifdef arch_trigger_all_cpu_backtrace /* For reliability, we're prepared to waste bits here. */ static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly; +static cpumask_t printtrace_mask; + +#define NMI_BUF_SIZE 4096 + +struct nmi_seq_buf { + unsigned char buffer[NMI_BUF_SIZE]; + struct seq_buf seq; +}; + +/* Safe printing in NMI context */ +static DEFINE_PER_CPU(struct nmi_seq_buf, nmi_print_seq); /* "in progress" flag of arch_trigger_all_cpu_backtrace */ static unsigned long backtrace_flag; +static void print_seq_line(struct nmi_seq_buf *s, int start, int end) +{ + const char *buf = s->buffer + start; + + printk("%.*s", (end - start) + 1, buf); +} + void arch_trigger_all_cpu_backtrace(bool include_self) { + struct nmi_seq_buf *s; + int len; + int cpu; int i; - int cpu = get_cpu(); + int this_cpu = get_cpu(); if (test_and_set_bit(0, &backtrace_flag)) { /* @@ -49,7 +71,17 @@ void arch_trigger_all_cpu_backtrace(bool include_self) cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask); if (!include_self) - cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask)); + cpumask_clear_cpu(this_cpu, to_cpumask(backtrace_mask)); + + cpumask_copy(&printtrace_mask, to_cpumask(backtrace_mask)); + /* + * Set up per_cpu seq_buf buffers that the NMIs running on the other + * CPUs will write to. + */ + for_each_cpu(cpu, to_cpumask(backtrace_mask)) { + s = &per_cpu(nmi_print_seq, cpu); + seq_buf_init(&s->seq, s->buffer, NMI_BUF_SIZE); + } if (!cpumask_empty(to_cpumask(backtrace_mask))) { pr_info("sending NMI to %s CPUs:\n", @@ -65,11 +97,58 @@ void arch_trigger_all_cpu_backtrace(bool include_self) touch_softlockup_watchdog(); } + /* + * Now that all the NMIs have triggered, we can dump out their + * back traces safely to the console. + */ + for_each_cpu(cpu, &printtrace_mask) { + int last_i = 0; + + s = &per_cpu(nmi_print_seq, cpu); + len = seq_buf_used(&s->seq); + if (!len) + continue; + + /* Print line by line. */ + for (i = 0; i < len; i++) { + if (s->buffer[i] == '\n') { + print_seq_line(s, last_i, i); + last_i = i + 1; + } + } + /* Check if there was a partial line. */ + if (last_i < len) { + print_seq_line(s, last_i, len - 1); + pr_cont("\n"); + } + } + clear_bit(0, &backtrace_flag); smp_mb__after_atomic(); put_cpu(); } +/* + * It is not safe to call printk() directly from NMI handlers. + * It may be fine if the NMI detected a lock up and we have no choice + * but to do so, but doing a NMI on all other CPUs to get a back trace + * can be done with a sysrq-l. We don't want that to lock up, which + * can happen if the NMI interrupts a printk in progress. + * + * Instead, we redirect the vprintk() to this nmi_vprintk() that writes + * the content into a per cpu seq_buf buffer. Then when the NMIs are + * all done, we can safely dump the contents of the seq_buf to a printk() + * from a non NMI context. + */ +static int nmi_vprintk(const char *fmt, va_list args) +{ + struct nmi_seq_buf *s = this_cpu_ptr(&nmi_print_seq); + unsigned int len = seq_buf_used(&s->seq); + + seq_buf_vprintf(&s->seq, fmt, args); + return seq_buf_used(&s->seq) - len; +} + static int arch_trigger_all_cpu_backtrace_handler(unsigned int cmd, struct pt_regs *regs) { @@ -78,12 +157,14 @@ arch_trigger_all_cpu_backtrace_handler(unsigned int cmd, struct pt_regs *regs) cpu = smp_processor_id(); if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) { - static arch_spinlock_t lock = __ARCH_SPIN_LOCK_UNLOCKED; + printk_func_t printk_func_save = this_cpu_read(printk_func); - arch_spin_lock(&lock); + /* Replace printk to write into the NMI seq */ + this_cpu_write(printk_func, nmi_vprintk); printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu); show_regs(regs); - arch_spin_unlock(&lock); + this_cpu_write(printk_func, printk_func_save); + cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask)); return NMI_HANDLED; } diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 337ce5a9b15c..3f5f60406ab1 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -32,15 +32,11 @@ #include <linux/module.h> #include <linux/syscore_ops.h> #include <linux/irqdomain.h> -#include <linux/msi.h> -#include <linux/htirq.h> #include <linux/freezer.h> #include <linux/kthread.h> #include <linux/jiffies.h> /* time_after() */ #include <linux/slab.h> #include <linux/bootmem.h> -#include <linux/dmar.h> -#include <linux/hpet.h> #include <asm/idle.h> #include <asm/io.h> @@ -52,17 +48,12 @@ #include <asm/dma.h> #include <asm/timer.h> #include <asm/i8259.h> -#include <asm/msidef.h> -#include <asm/hypertransport.h> #include <asm/setup.h> #include <asm/irq_remapping.h> -#include <asm/hpet.h> #include <asm/hw_irq.h> #include <asm/apic.h> -#define __apicdebuginit(type) static type __init - #define for_each_ioapic(idx) \ for ((idx) = 0; (idx) < nr_ioapics; (idx)++) #define for_each_ioapic_reverse(idx) \ @@ -74,7 +65,7 @@ for_each_pin((idx), (pin)) #define for_each_irq_pin(entry, head) \ - for (entry = head; entry; entry = entry->next) + list_for_each_entry(entry, &head, list) /* * Is the SiS APIC rmw bug present ? @@ -83,7 +74,6 @@ int sis_apic_bug = -1; static DEFINE_RAW_SPINLOCK(ioapic_lock); -static DEFINE_RAW_SPINLOCK(vector_lock); static DEFINE_MUTEX(ioapic_mutex); static unsigned int ioapic_dynirq_base; static int ioapic_initialized; @@ -112,6 +102,7 @@ static struct ioapic { struct ioapic_domain_cfg irqdomain_cfg; struct irq_domain *irqdomain; struct mp_pin_info *pin_info; + struct resource *iomem_res; } ioapics[MAX_IO_APICS]; #define mpc_ioapic_ver(ioapic_idx) ioapics[ioapic_idx].mp_config.apicver @@ -205,8 +196,6 @@ static int __init parse_noapic(char *str) } early_param("noapic", parse_noapic); -static struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node); - /* Will be called in mpparse/acpi/sfi codes for saving IRQ info */ void mp_save_irq(struct mpc_intsrc *m) { @@ -228,8 +217,8 @@ void mp_save_irq(struct mpc_intsrc *m) } struct irq_pin_list { + struct list_head list; int apic, pin; - struct irq_pin_list *next; }; static struct irq_pin_list *alloc_irq_pin_list(int node) @@ -237,7 +226,26 @@ static struct irq_pin_list *alloc_irq_pin_list(int node) return kzalloc_node(sizeof(struct irq_pin_list), GFP_KERNEL, node); } -int __init arch_early_irq_init(void) +static void alloc_ioapic_saved_registers(int idx) +{ + size_t size; + + if (ioapics[idx].saved_registers) + return; + + size = sizeof(struct IO_APIC_route_entry) * ioapics[idx].nr_registers; + ioapics[idx].saved_registers = kzalloc(size, GFP_KERNEL); + if (!ioapics[idx].saved_registers) + pr_err("IOAPIC %d: suspend/resume impossible!\n", idx); +} + +static void free_ioapic_saved_registers(int idx) +{ + kfree(ioapics[idx].saved_registers); + ioapics[idx].saved_registers = NULL; +} + +int __init arch_early_ioapic_init(void) { struct irq_cfg *cfg; int i, node = cpu_to_node(0); @@ -245,13 +253,8 @@ int __init arch_early_irq_init(void) if (!nr_legacy_irqs()) io_apic_irqs = ~0UL; - for_each_ioapic(i) { - ioapics[i].saved_registers = - kzalloc(sizeof(struct IO_APIC_route_entry) * - ioapics[i].nr_registers, GFP_KERNEL); - if (!ioapics[i].saved_registers) - pr_err("IOAPIC %d: suspend/resume impossible!\n", i); - } + for_each_ioapic(i) + alloc_ioapic_saved_registers(i); /* * For legacy IRQ's, start with assigning irq0 to irq15 to @@ -266,61 +269,6 @@ int __init arch_early_irq_init(void) return 0; } -static inline struct irq_cfg *irq_cfg(unsigned int irq) -{ - return irq_get_chip_data(irq); -} - -static struct irq_cfg *alloc_irq_cfg(unsigned int irq, int node) -{ - struct irq_cfg *cfg; - - cfg = kzalloc_node(sizeof(*cfg), GFP_KERNEL, node); - if (!cfg) - return NULL; - if (!zalloc_cpumask_var_node(&cfg->domain, GFP_KERNEL, node)) - goto out_cfg; - if (!zalloc_cpumask_var_node(&cfg->old_domain, GFP_KERNEL, node)) - goto out_domain; - return cfg; -out_domain: - free_cpumask_var(cfg->domain); -out_cfg: - kfree(cfg); - return NULL; -} - -static void free_irq_cfg(unsigned int at, struct irq_cfg *cfg) -{ - if (!cfg) - return; - irq_set_chip_data(at, NULL); - free_cpumask_var(cfg->domain); - free_cpumask_var(cfg->old_domain); - kfree(cfg); -} - -static struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node) -{ - int res = irq_alloc_desc_at(at, node); - struct irq_cfg *cfg; - - if (res < 0) { - if (res != -EEXIST) - return NULL; - cfg = irq_cfg(at); - if (cfg) - return cfg; - } - - cfg = alloc_irq_cfg(at, node); - if (cfg) - irq_set_chip_data(at, cfg); - else - irq_free_desc(at); - return cfg; -} - struct io_apic { unsigned int index; unsigned int unused[3]; @@ -445,15 +393,12 @@ static void ioapic_mask_entry(int apic, int pin) */ static int __add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin) { - struct irq_pin_list **last, *entry; + struct irq_pin_list *entry; /* don't allow duplicates */ - last = &cfg->irq_2_pin; - for_each_irq_pin(entry, cfg->irq_2_pin) { + for_each_irq_pin(entry, cfg->irq_2_pin) if (entry->apic == apic && entry->pin == pin) return 0; - last = &entry->next; - } entry = alloc_irq_pin_list(node); if (!entry) { @@ -464,22 +409,19 @@ static int __add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pi entry->apic = apic; entry->pin = pin; - *last = entry; + list_add_tail(&entry->list, &cfg->irq_2_pin); return 0; } static void __remove_pin_from_irq(struct irq_cfg *cfg, int apic, int pin) { - struct irq_pin_list **last, *entry; + struct irq_pin_list *tmp, *entry; - last = &cfg->irq_2_pin; - for_each_irq_pin(entry, cfg->irq_2_pin) + list_for_each_entry_safe(entry, tmp, &cfg->irq_2_pin, list) if (entry->apic == apic && entry->pin == pin) { - *last = entry->next; + list_del(&entry->list); kfree(entry); return; - } else { - last = &entry->next; } } @@ -559,7 +501,7 @@ static void mask_ioapic(struct irq_cfg *cfg) static void mask_ioapic_irq(struct irq_data *data) { - mask_ioapic(data->chip_data); + mask_ioapic(irqd_cfg(data)); } static void __unmask_ioapic(struct irq_cfg *cfg) @@ -578,7 +520,7 @@ static void unmask_ioapic(struct irq_cfg *cfg) static void unmask_ioapic_irq(struct irq_data *data) { - unmask_ioapic(data->chip_data); + unmask_ioapic(irqd_cfg(data)); } /* @@ -1164,8 +1106,7 @@ void mp_unmap_irq(int irq) * Find a specific PCI IRQ entry. * Not an __init, possibly needed by modules */ -int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin, - struct io_apic_irq_attr *irq_attr) +int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin) { int irq, i, best_ioapic = -1, best_idx = -1; @@ -1219,195 +1160,11 @@ int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin, return -1; out: - irq = pin_2_irq(best_idx, best_ioapic, mp_irqs[best_idx].dstirq, - IOAPIC_MAP_ALLOC); - if (irq > 0) - set_io_apic_irq_attr(irq_attr, best_ioapic, - mp_irqs[best_idx].dstirq, - irq_trigger(best_idx), - irq_polarity(best_idx)); - return irq; + return pin_2_irq(best_idx, best_ioapic, mp_irqs[best_idx].dstirq, + IOAPIC_MAP_ALLOC); } EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector); -void lock_vector_lock(void) -{ - /* Used to the online set of cpus does not change - * during assign_irq_vector. - */ - raw_spin_lock(&vector_lock); -} - -void unlock_vector_lock(void) -{ - raw_spin_unlock(&vector_lock); -} - -static int -__assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask) -{ - /* - * NOTE! The local APIC isn't very good at handling - * multiple interrupts at the same interrupt level. - * As the interrupt level is determined by taking the - * vector number and shifting that right by 4, we - * want to spread these out a bit so that they don't - * all fall in the same interrupt level. - * - * Also, we've got to be careful not to trash gate - * 0x80, because int 0x80 is hm, kind of importantish. ;) - */ - static int current_vector = FIRST_EXTERNAL_VECTOR + VECTOR_OFFSET_START; - static int current_offset = VECTOR_OFFSET_START % 16; - int cpu, err; - cpumask_var_t tmp_mask; - - if (cfg->move_in_progress) - return -EBUSY; - - if (!alloc_cpumask_var(&tmp_mask, GFP_ATOMIC)) - return -ENOMEM; - - /* Only try and allocate irqs on cpus that are present */ - err = -ENOSPC; - cpumask_clear(cfg->old_domain); - cpu = cpumask_first_and(mask, cpu_online_mask); - while (cpu < nr_cpu_ids) { - int new_cpu, vector, offset; - - apic->vector_allocation_domain(cpu, tmp_mask, mask); - - if (cpumask_subset(tmp_mask, cfg->domain)) { - err = 0; - if (cpumask_equal(tmp_mask, cfg->domain)) - break; - /* - * New cpumask using the vector is a proper subset of - * the current in use mask. So cleanup the vector - * allocation for the members that are not used anymore. - */ - cpumask_andnot(cfg->old_domain, cfg->domain, tmp_mask); - cfg->move_in_progress = - cpumask_intersects(cfg->old_domain, cpu_online_mask); - cpumask_and(cfg->domain, cfg->domain, tmp_mask); - break; - } - - vector = current_vector; - offset = current_offset; -next: - vector += 16; - if (vector >= first_system_vector) { - offset = (offset + 1) % 16; - vector = FIRST_EXTERNAL_VECTOR + offset; - } - - if (unlikely(current_vector == vector)) { - cpumask_or(cfg->old_domain, cfg->old_domain, tmp_mask); - cpumask_andnot(tmp_mask, mask, cfg->old_domain); - cpu = cpumask_first_and(tmp_mask, cpu_online_mask); - continue; - } - - 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] > VECTOR_UNDEFINED) - goto next; - } - /* Found one! */ - current_vector = vector; - current_offset = offset; - if (cfg->vector) { - cpumask_copy(cfg->old_domain, cfg->domain); - cfg->move_in_progress = - cpumask_intersects(cfg->old_domain, cpu_online_mask); - } - for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask) - per_cpu(vector_irq, new_cpu)[vector] = irq; - cfg->vector = vector; - cpumask_copy(cfg->domain, tmp_mask); - err = 0; - break; - } - free_cpumask_var(tmp_mask); - return err; -} - -int assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask) -{ - int err; - unsigned long flags; - - raw_spin_lock_irqsave(&vector_lock, flags); - err = __assign_irq_vector(irq, cfg, mask); - raw_spin_unlock_irqrestore(&vector_lock, flags); - return err; -} - -static void __clear_irq_vector(int irq, struct irq_cfg *cfg) -{ - int cpu, vector; - - BUG_ON(!cfg->vector); - - vector = cfg->vector; - for_each_cpu_and(cpu, cfg->domain, cpu_online_mask) - per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED; - - cfg->vector = 0; - cpumask_clear(cfg->domain); - - 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++) { - if (per_cpu(vector_irq, cpu)[vector] != irq) - continue; - per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED; - break; - } - } - cfg->move_in_progress = 0; -} - -void __setup_vector_irq(int cpu) -{ - /* Initialize vector_irq on a new cpu */ - int irq, vector; - struct irq_cfg *cfg; - - /* - * vector_lock will make sure that we don't run into irq vector - * assignments that might be happening on another cpu in parallel, - * while we setup our initial vector to irq mappings. - */ - raw_spin_lock(&vector_lock); - /* Mark the inuse vectors */ - for_each_active_irq(irq) { - cfg = irq_cfg(irq); - if (!cfg) - continue; - - if (!cpumask_test_cpu(cpu, cfg->domain)) - continue; - vector = cfg->vector; - per_cpu(vector_irq, cpu)[vector] = irq; - } - /* Mark the free vectors */ - for (vector = 0; vector < NR_VECTORS; ++vector) { - irq = per_cpu(vector_irq, cpu)[vector]; - if (irq <= VECTOR_UNDEFINED) - continue; - - cfg = irq_cfg(irq); - if (!cpumask_test_cpu(cpu, cfg->domain)) - per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED; - } - raw_spin_unlock(&vector_lock); -} - static struct irq_chip ioapic_chip; #ifdef CONFIG_X86_32 @@ -1496,7 +1253,7 @@ static void setup_ioapic_irq(unsigned int irq, struct irq_cfg *cfg, &dest)) { pr_warn("Failed to obtain apicid for ioapic %d, pin %d\n", mpc_ioapic_id(attr->ioapic), attr->ioapic_pin); - __clear_irq_vector(irq, cfg); + clear_irq_vector(irq, cfg); return; } @@ -1510,7 +1267,7 @@ static void setup_ioapic_irq(unsigned int irq, struct irq_cfg *cfg, if (x86_io_apic_ops.setup_entry(irq, &entry, dest, cfg->vector, attr)) { pr_warn("Failed to setup ioapic entry for ioapic %d, pin %d\n", mpc_ioapic_id(attr->ioapic), attr->ioapic_pin); - __clear_irq_vector(irq, cfg); + clear_irq_vector(irq, cfg); return; } @@ -1641,7 +1398,7 @@ void ioapic_zap_locks(void) raw_spin_lock_init(&ioapic_lock); } -__apicdebuginit(void) print_IO_APIC(int ioapic_idx) +static void __init print_IO_APIC(int ioapic_idx) { union IO_APIC_reg_00 reg_00; union IO_APIC_reg_01 reg_01; @@ -1698,7 +1455,7 @@ __apicdebuginit(void) print_IO_APIC(int ioapic_idx) x86_io_apic_ops.print_entries(ioapic_idx, reg_01.bits.entries); } -__apicdebuginit(void) print_IO_APICs(void) +void __init print_IO_APICs(void) { int ioapic_idx; struct irq_cfg *cfg; @@ -1731,8 +1488,7 @@ __apicdebuginit(void) print_IO_APICs(void) cfg = irq_cfg(irq); if (!cfg) continue; - entry = cfg->irq_2_pin; - if (!entry) + if (list_empty(&cfg->irq_2_pin)) continue; printk(KERN_DEBUG "IRQ%d ", irq); for_each_irq_pin(entry, cfg->irq_2_pin) @@ -1743,205 +1499,6 @@ __apicdebuginit(void) print_IO_APICs(void) printk(KERN_INFO ".................................... done.\n"); } -__apicdebuginit(void) print_APIC_field(int base) -{ - int i; - - printk(KERN_DEBUG); - - for (i = 0; i < 8; i++) - pr_cont("%08x", apic_read(base + i*0x10)); - - pr_cont("\n"); -} - -__apicdebuginit(void) print_local_APIC(void *dummy) -{ - unsigned int i, v, ver, maxlvt; - u64 icr; - - printk(KERN_DEBUG "printing local APIC contents on CPU#%d/%d:\n", - smp_processor_id(), hard_smp_processor_id()); - v = apic_read(APIC_ID); - printk(KERN_INFO "... APIC ID: %08x (%01x)\n", v, read_apic_id()); - v = apic_read(APIC_LVR); - printk(KERN_INFO "... APIC VERSION: %08x\n", v); - ver = GET_APIC_VERSION(v); - maxlvt = lapic_get_maxlvt(); - - v = apic_read(APIC_TASKPRI); - printk(KERN_DEBUG "... APIC TASKPRI: %08x (%02x)\n", v, v & APIC_TPRI_MASK); - - if (APIC_INTEGRATED(ver)) { /* !82489DX */ - if (!APIC_XAPIC(ver)) { - v = apic_read(APIC_ARBPRI); - printk(KERN_DEBUG "... APIC ARBPRI: %08x (%02x)\n", v, - v & APIC_ARBPRI_MASK); - } - v = apic_read(APIC_PROCPRI); - printk(KERN_DEBUG "... APIC PROCPRI: %08x\n", v); - } - - /* - * Remote read supported only in the 82489DX and local APIC for - * Pentium processors. - */ - if (!APIC_INTEGRATED(ver) || maxlvt == 3) { - v = apic_read(APIC_RRR); - printk(KERN_DEBUG "... APIC RRR: %08x\n", v); - } - - v = apic_read(APIC_LDR); - printk(KERN_DEBUG "... APIC LDR: %08x\n", v); - if (!x2apic_enabled()) { - v = apic_read(APIC_DFR); - printk(KERN_DEBUG "... APIC DFR: %08x\n", v); - } - v = apic_read(APIC_SPIV); - printk(KERN_DEBUG "... APIC SPIV: %08x\n", v); - - printk(KERN_DEBUG "... APIC ISR field:\n"); - print_APIC_field(APIC_ISR); - printk(KERN_DEBUG "... APIC TMR field:\n"); - print_APIC_field(APIC_TMR); - printk(KERN_DEBUG "... APIC IRR field:\n"); - print_APIC_field(APIC_IRR); - - if (APIC_INTEGRATED(ver)) { /* !82489DX */ - if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */ - apic_write(APIC_ESR, 0); - - v = apic_read(APIC_ESR); - printk(KERN_DEBUG "... APIC ESR: %08x\n", v); - } - - icr = apic_icr_read(); - printk(KERN_DEBUG "... APIC ICR: %08x\n", (u32)icr); - printk(KERN_DEBUG "... APIC ICR2: %08x\n", (u32)(icr >> 32)); - - v = apic_read(APIC_LVTT); - printk(KERN_DEBUG "... APIC LVTT: %08x\n", v); - - if (maxlvt > 3) { /* PC is LVT#4. */ - v = apic_read(APIC_LVTPC); - printk(KERN_DEBUG "... APIC LVTPC: %08x\n", v); - } - v = apic_read(APIC_LVT0); - printk(KERN_DEBUG "... APIC LVT0: %08x\n", v); - v = apic_read(APIC_LVT1); - printk(KERN_DEBUG "... APIC LVT1: %08x\n", v); - - if (maxlvt > 2) { /* ERR is LVT#3. */ - v = apic_read(APIC_LVTERR); - printk(KERN_DEBUG "... APIC LVTERR: %08x\n", v); - } - - v = apic_read(APIC_TMICT); - printk(KERN_DEBUG "... APIC TMICT: %08x\n", v); - v = apic_read(APIC_TMCCT); - printk(KERN_DEBUG "... APIC TMCCT: %08x\n", v); - v = apic_read(APIC_TDCR); - printk(KERN_DEBUG "... APIC TDCR: %08x\n", v); - - if (boot_cpu_has(X86_FEATURE_EXTAPIC)) { - v = apic_read(APIC_EFEAT); - maxlvt = (v >> 16) & 0xff; - printk(KERN_DEBUG "... APIC EFEAT: %08x\n", v); - v = apic_read(APIC_ECTRL); - printk(KERN_DEBUG "... APIC ECTRL: %08x\n", v); - for (i = 0; i < maxlvt; i++) { - v = apic_read(APIC_EILVTn(i)); - printk(KERN_DEBUG "... APIC EILVT%d: %08x\n", i, v); - } - } - pr_cont("\n"); -} - -__apicdebuginit(void) print_local_APICs(int maxcpu) -{ - int cpu; - - if (!maxcpu) - return; - - preempt_disable(); - for_each_online_cpu(cpu) { - if (cpu >= maxcpu) - break; - smp_call_function_single(cpu, print_local_APIC, NULL, 1); - } - preempt_enable(); -} - -__apicdebuginit(void) print_PIC(void) -{ - unsigned int v; - unsigned long flags; - - if (!nr_legacy_irqs()) - return; - - printk(KERN_DEBUG "\nprinting PIC contents\n"); - - raw_spin_lock_irqsave(&i8259A_lock, flags); - - v = inb(0xa1) << 8 | inb(0x21); - printk(KERN_DEBUG "... PIC IMR: %04x\n", v); - - v = inb(0xa0) << 8 | inb(0x20); - printk(KERN_DEBUG "... PIC IRR: %04x\n", v); - - outb(0x0b,0xa0); - outb(0x0b,0x20); - v = inb(0xa0) << 8 | inb(0x20); - outb(0x0a,0xa0); - outb(0x0a,0x20); - - raw_spin_unlock_irqrestore(&i8259A_lock, flags); - - printk(KERN_DEBUG "... PIC ISR: %04x\n", v); - - v = inb(0x4d1) << 8 | inb(0x4d0); - printk(KERN_DEBUG "... PIC ELCR: %04x\n", v); -} - -static int __initdata show_lapic = 1; -static __init int setup_show_lapic(char *arg) -{ - int num = -1; - - if (strcmp(arg, "all") == 0) { - show_lapic = CONFIG_NR_CPUS; - } else { - get_option(&arg, &num); - if (num >= 0) - show_lapic = num; - } - - return 1; -} -__setup("show_lapic=", setup_show_lapic); - -__apicdebuginit(int) print_ICs(void) -{ - if (apic_verbosity == APIC_QUIET) - return 0; - - print_PIC(); - - /* don't print out if apic is not there */ - if (!cpu_has_apic && !apic_from_smp_config()) - return 0; - - print_local_APICs(show_lapic); - print_IO_APICs(); - - return 0; -} - -late_initcall(print_ICs); - - /* Where if anywhere is the i8259 connect in external int mode */ static struct { int pin, apic; } ioapic_i8259 = { -1, -1 }; @@ -2244,26 +1801,12 @@ static unsigned int startup_ioapic_irq(struct irq_data *data) if (legacy_pic->irq_pending(irq)) was_pending = 1; } - __unmask_ioapic(data->chip_data); + __unmask_ioapic(irqd_cfg(data)); raw_spin_unlock_irqrestore(&ioapic_lock, flags); return was_pending; } -static int ioapic_retrigger_irq(struct irq_data *data) -{ - struct irq_cfg *cfg = data->chip_data; - unsigned long flags; - int cpu; - - raw_spin_lock_irqsave(&vector_lock, flags); - cpu = cpumask_first_and(cfg->domain, cpu_online_mask); - apic->send_IPI_mask(cpumask_of(cpu), cfg->vector); - raw_spin_unlock_irqrestore(&vector_lock, flags); - - return 1; -} - /* * Level and edge triggered IO-APIC interrupts need different handling, * so we use two separate IRQ descriptors. Edge triggered IRQs can be @@ -2273,113 +1816,6 @@ static int ioapic_retrigger_irq(struct irq_data *data) * races. */ -#ifdef CONFIG_SMP -void send_cleanup_vector(struct irq_cfg *cfg) -{ - cpumask_var_t cleanup_mask; - - if (unlikely(!alloc_cpumask_var(&cleanup_mask, GFP_ATOMIC))) { - unsigned int i; - for_each_cpu_and(i, cfg->old_domain, cpu_online_mask) - apic->send_IPI_mask(cpumask_of(i), IRQ_MOVE_CLEANUP_VECTOR); - } else { - cpumask_and(cleanup_mask, cfg->old_domain, cpu_online_mask); - apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR); - free_cpumask_var(cleanup_mask); - } - cfg->move_in_progress = 0; -} - -asmlinkage __visible void smp_irq_move_cleanup_interrupt(void) -{ - unsigned vector, me; - - ack_APIC_irq(); - irq_enter(); - exit_idle(); - - me = smp_processor_id(); - for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { - int irq; - unsigned int irr; - struct irq_desc *desc; - struct irq_cfg *cfg; - irq = __this_cpu_read(vector_irq[vector]); - - if (irq <= VECTOR_UNDEFINED) - continue; - - desc = irq_to_desc(irq); - if (!desc) - continue; - - cfg = irq_cfg(irq); - if (!cfg) - continue; - - raw_spin_lock(&desc->lock); - - /* - * Check if the irq migration is in progress. If so, we - * haven't received the cleanup request yet for this irq. - */ - if (cfg->move_in_progress) - goto unlock; - - if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain)) - goto unlock; - - irr = apic_read(APIC_IRR + (vector / 32 * 0x10)); - /* - * Check if the vector that needs to be cleanedup is - * registered at the cpu's IRR. If so, then this is not - * the best time to clean it up. Lets clean it up in the - * next attempt by sending another IRQ_MOVE_CLEANUP_VECTOR - * to myself. - */ - if (irr & (1 << (vector % 32))) { - apic->send_IPI_self(IRQ_MOVE_CLEANUP_VECTOR); - goto unlock; - } - __this_cpu_write(vector_irq[vector], VECTOR_UNDEFINED); -unlock: - raw_spin_unlock(&desc->lock); - } - - irq_exit(); -} - -static void __irq_complete_move(struct irq_cfg *cfg, unsigned vector) -{ - unsigned me; - - if (likely(!cfg->move_in_progress)) - return; - - me = smp_processor_id(); - - if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain)) - send_cleanup_vector(cfg); -} - -static void irq_complete_move(struct irq_cfg *cfg) -{ - __irq_complete_move(cfg, ~get_irq_regs()->orig_ax); -} - -void irq_force_complete_move(int irq) -{ - struct irq_cfg *cfg = irq_cfg(irq); - - if (!cfg) - return; - - __irq_complete_move(cfg, cfg->vector); -} -#else -static inline void irq_complete_move(struct irq_cfg *cfg) { } -#endif - static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq_cfg *cfg) { int apic, pin; @@ -2400,41 +1836,6 @@ static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq } } -/* - * Either sets data->affinity to a valid value, and returns - * ->cpu_mask_to_apicid of that in dest_id, or returns -1 and - * leaves data->affinity untouched. - */ -int __ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, - unsigned int *dest_id) -{ - struct irq_cfg *cfg = data->chip_data; - unsigned int irq = data->irq; - int err; - - if (!config_enabled(CONFIG_SMP)) - return -EPERM; - - if (!cpumask_intersects(mask, cpu_online_mask)) - return -EINVAL; - - err = assign_irq_vector(irq, cfg, mask); - if (err) - return err; - - err = apic->cpu_mask_to_apicid_and(mask, cfg->domain, dest_id); - if (err) { - if (assign_irq_vector(irq, cfg, data->affinity)) - pr_err("Failed to recover vector for irq %d\n", irq); - return err; - } - - cpumask_copy(data->affinity, mask); - - return 0; -} - - int native_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) @@ -2447,24 +1848,17 @@ int native_ioapic_set_affinity(struct irq_data *data, return -EPERM; raw_spin_lock_irqsave(&ioapic_lock, flags); - ret = __ioapic_set_affinity(data, mask, &dest); + ret = apic_set_affinity(data, mask, &dest); if (!ret) { /* Only the high 8 bits are valid. */ dest = SET_APIC_LOGICAL_ID(dest); - __target_IO_APIC_irq(irq, dest, data->chip_data); + __target_IO_APIC_irq(irq, dest, irqd_cfg(data)); ret = IRQ_SET_MASK_OK_NOCOPY; } raw_spin_unlock_irqrestore(&ioapic_lock, flags); return ret; } -static void ack_apic_edge(struct irq_data *data) -{ - irq_complete_move(data->chip_data); - irq_move_irq(data); - ack_APIC_irq(); -} - atomic_t irq_mis_count; #ifdef CONFIG_GENERIC_PENDING_IRQ @@ -2547,9 +1941,9 @@ static inline void ioapic_irqd_unmask(struct irq_data *data, } #endif -static void ack_apic_level(struct irq_data *data) +static void ack_ioapic_level(struct irq_data *data) { - struct irq_cfg *cfg = data->chip_data; + struct irq_cfg *cfg = irqd_cfg(data); int i, irq = data->irq; unsigned long v; bool masked; @@ -2619,10 +2013,11 @@ static struct irq_chip ioapic_chip __read_mostly = { .irq_startup = startup_ioapic_irq, .irq_mask = mask_ioapic_irq, .irq_unmask = unmask_ioapic_irq, - .irq_ack = ack_apic_edge, - .irq_eoi = ack_apic_level, + .irq_ack = apic_ack_edge, + .irq_eoi = ack_ioapic_level, .irq_set_affinity = native_ioapic_set_affinity, - .irq_retrigger = ioapic_retrigger_irq, + .irq_retrigger = apic_retrigger_irq, + .flags = IRQCHIP_SKIP_SET_WAKE, }; static inline void init_IO_APIC_traps(void) @@ -2964,6 +2359,16 @@ static int mp_irqdomain_create(int ioapic) return 0; } +static void ioapic_destroy_irqdomain(int idx) +{ + if (ioapics[idx].irqdomain) { + irq_domain_remove(ioapics[idx].irqdomain); + ioapics[idx].irqdomain = NULL; + } + kfree(ioapics[idx].pin_info); + ioapics[idx].pin_info = NULL; +} + void __init setup_IO_APIC(void) { int ioapic; @@ -3043,395 +2448,6 @@ static int __init ioapic_init_ops(void) device_initcall(ioapic_init_ops); -/* - * Dynamic irq allocate and deallocation. Should be replaced by irq domains! - */ -int arch_setup_hwirq(unsigned int irq, int node) -{ - struct irq_cfg *cfg; - unsigned long flags; - int ret; - - cfg = alloc_irq_cfg(irq, node); - if (!cfg) - return -ENOMEM; - - raw_spin_lock_irqsave(&vector_lock, flags); - ret = __assign_irq_vector(irq, cfg, apic->target_cpus()); - raw_spin_unlock_irqrestore(&vector_lock, flags); - - if (!ret) - irq_set_chip_data(irq, cfg); - else - free_irq_cfg(irq, cfg); - return ret; -} - -void arch_teardown_hwirq(unsigned int irq) -{ - struct irq_cfg *cfg = irq_cfg(irq); - unsigned long flags; - - free_remapped_irq(irq); - raw_spin_lock_irqsave(&vector_lock, flags); - __clear_irq_vector(irq, cfg); - raw_spin_unlock_irqrestore(&vector_lock, flags); - free_irq_cfg(irq, cfg); -} - -/* - * MSI message composition - */ -void native_compose_msi_msg(struct pci_dev *pdev, - unsigned int irq, unsigned int dest, - struct msi_msg *msg, u8 hpet_id) -{ - struct irq_cfg *cfg = irq_cfg(irq); - - msg->address_hi = MSI_ADDR_BASE_HI; - - if (x2apic_enabled()) - msg->address_hi |= MSI_ADDR_EXT_DEST_ID(dest); - - msg->address_lo = - MSI_ADDR_BASE_LO | - ((apic->irq_dest_mode == 0) ? - MSI_ADDR_DEST_MODE_PHYSICAL: - MSI_ADDR_DEST_MODE_LOGICAL) | - ((apic->irq_delivery_mode != dest_LowestPrio) ? - MSI_ADDR_REDIRECTION_CPU: - MSI_ADDR_REDIRECTION_LOWPRI) | - MSI_ADDR_DEST_ID(dest); - - msg->data = - MSI_DATA_TRIGGER_EDGE | - MSI_DATA_LEVEL_ASSERT | - ((apic->irq_delivery_mode != dest_LowestPrio) ? - MSI_DATA_DELIVERY_FIXED: - MSI_DATA_DELIVERY_LOWPRI) | - MSI_DATA_VECTOR(cfg->vector); -} - -#ifdef CONFIG_PCI_MSI -static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, - struct msi_msg *msg, u8 hpet_id) -{ - struct irq_cfg *cfg; - int err; - unsigned dest; - - if (disable_apic) - return -ENXIO; - - cfg = irq_cfg(irq); - err = assign_irq_vector(irq, cfg, apic->target_cpus()); - if (err) - return err; - - err = apic->cpu_mask_to_apicid_and(cfg->domain, - apic->target_cpus(), &dest); - if (err) - return err; - - x86_msi.compose_msi_msg(pdev, irq, dest, msg, hpet_id); - - return 0; -} - -static int -msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) -{ - struct irq_cfg *cfg = data->chip_data; - struct msi_msg msg; - unsigned int dest; - int ret; - - ret = __ioapic_set_affinity(data, mask, &dest); - if (ret) - return ret; - - __get_cached_msi_msg(data->msi_desc, &msg); - - msg.data &= ~MSI_DATA_VECTOR_MASK; - msg.data |= MSI_DATA_VECTOR(cfg->vector); - msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK; - msg.address_lo |= MSI_ADDR_DEST_ID(dest); - - __write_msi_msg(data->msi_desc, &msg); - - return IRQ_SET_MASK_OK_NOCOPY; -} - -/* - * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices, - * which implement the MSI or MSI-X Capability Structure. - */ -static struct irq_chip msi_chip = { - .name = "PCI-MSI", - .irq_unmask = unmask_msi_irq, - .irq_mask = mask_msi_irq, - .irq_ack = ack_apic_edge, - .irq_set_affinity = msi_set_affinity, - .irq_retrigger = ioapic_retrigger_irq, -}; - -int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, - unsigned int irq_base, unsigned int irq_offset) -{ - struct irq_chip *chip = &msi_chip; - struct msi_msg msg; - unsigned int irq = irq_base + irq_offset; - int ret; - - ret = msi_compose_msg(dev, irq, &msg, -1); - if (ret < 0) - return ret; - - irq_set_msi_desc_off(irq_base, irq_offset, msidesc); - - /* - * MSI-X message is written per-IRQ, the offset is always 0. - * MSI message denotes a contiguous group of IRQs, written for 0th IRQ. - */ - if (!irq_offset) - write_msi_msg(irq, &msg); - - setup_remapped_irq(irq, irq_cfg(irq), chip); - - irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge"); - - dev_printk(KERN_DEBUG, &dev->dev, "irq %d for MSI/MSI-X\n", irq); - - return 0; -} - -int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) -{ - struct msi_desc *msidesc; - unsigned int irq; - int node, ret; - - /* Multiple MSI vectors only supported with interrupt remapping */ - if (type == PCI_CAP_ID_MSI && nvec > 1) - return 1; - - node = dev_to_node(&dev->dev); - - list_for_each_entry(msidesc, &dev->msi_list, list) { - irq = irq_alloc_hwirq(node); - if (!irq) - return -ENOSPC; - - ret = setup_msi_irq(dev, msidesc, irq, 0); - if (ret < 0) { - irq_free_hwirq(irq); - return ret; - } - - } - return 0; -} - -void native_teardown_msi_irq(unsigned int irq) -{ - irq_free_hwirq(irq); -} - -#ifdef CONFIG_DMAR_TABLE -static int -dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask, - bool force) -{ - struct irq_cfg *cfg = data->chip_data; - unsigned int dest, irq = data->irq; - struct msi_msg msg; - int ret; - - ret = __ioapic_set_affinity(data, mask, &dest); - if (ret) - return ret; - - dmar_msi_read(irq, &msg); - - msg.data &= ~MSI_DATA_VECTOR_MASK; - msg.data |= MSI_DATA_VECTOR(cfg->vector); - msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK; - msg.address_lo |= MSI_ADDR_DEST_ID(dest); - msg.address_hi = MSI_ADDR_BASE_HI | MSI_ADDR_EXT_DEST_ID(dest); - - dmar_msi_write(irq, &msg); - - return IRQ_SET_MASK_OK_NOCOPY; -} - -static struct irq_chip dmar_msi_type = { - .name = "DMAR_MSI", - .irq_unmask = dmar_msi_unmask, - .irq_mask = dmar_msi_mask, - .irq_ack = ack_apic_edge, - .irq_set_affinity = dmar_msi_set_affinity, - .irq_retrigger = ioapic_retrigger_irq, -}; - -int arch_setup_dmar_msi(unsigned int irq) -{ - int ret; - struct msi_msg msg; - - ret = msi_compose_msg(NULL, irq, &msg, -1); - if (ret < 0) - return ret; - dmar_msi_write(irq, &msg); - irq_set_chip_and_handler_name(irq, &dmar_msi_type, handle_edge_irq, - "edge"); - return 0; -} -#endif - -#ifdef CONFIG_HPET_TIMER - -static int hpet_msi_set_affinity(struct irq_data *data, - const struct cpumask *mask, bool force) -{ - struct irq_cfg *cfg = data->chip_data; - struct msi_msg msg; - unsigned int dest; - int ret; - - ret = __ioapic_set_affinity(data, mask, &dest); - if (ret) - return ret; - - hpet_msi_read(data->handler_data, &msg); - - msg.data &= ~MSI_DATA_VECTOR_MASK; - msg.data |= MSI_DATA_VECTOR(cfg->vector); - msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK; - msg.address_lo |= MSI_ADDR_DEST_ID(dest); - - hpet_msi_write(data->handler_data, &msg); - - return IRQ_SET_MASK_OK_NOCOPY; -} - -static struct irq_chip hpet_msi_type = { - .name = "HPET_MSI", - .irq_unmask = hpet_msi_unmask, - .irq_mask = hpet_msi_mask, - .irq_ack = ack_apic_edge, - .irq_set_affinity = hpet_msi_set_affinity, - .irq_retrigger = ioapic_retrigger_irq, -}; - -int default_setup_hpet_msi(unsigned int irq, unsigned int id) -{ - struct irq_chip *chip = &hpet_msi_type; - struct msi_msg msg; - int ret; - - ret = msi_compose_msg(NULL, irq, &msg, id); - if (ret < 0) - return ret; - - hpet_msi_write(irq_get_handler_data(irq), &msg); - irq_set_status_flags(irq, IRQ_MOVE_PCNTXT); - setup_remapped_irq(irq, irq_cfg(irq), chip); - - irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge"); - return 0; -} -#endif - -#endif /* CONFIG_PCI_MSI */ -/* - * Hypertransport interrupt support - */ -#ifdef CONFIG_HT_IRQ - -static void target_ht_irq(unsigned int irq, unsigned int dest, u8 vector) -{ - struct ht_irq_msg msg; - fetch_ht_irq_msg(irq, &msg); - - msg.address_lo &= ~(HT_IRQ_LOW_VECTOR_MASK | HT_IRQ_LOW_DEST_ID_MASK); - msg.address_hi &= ~(HT_IRQ_HIGH_DEST_ID_MASK); - - msg.address_lo |= HT_IRQ_LOW_VECTOR(vector) | HT_IRQ_LOW_DEST_ID(dest); - msg.address_hi |= HT_IRQ_HIGH_DEST_ID(dest); - - write_ht_irq_msg(irq, &msg); -} - -static int -ht_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) -{ - struct irq_cfg *cfg = data->chip_data; - unsigned int dest; - int ret; - - ret = __ioapic_set_affinity(data, mask, &dest); - if (ret) - return ret; - - target_ht_irq(data->irq, dest, cfg->vector); - return IRQ_SET_MASK_OK_NOCOPY; -} - -static struct irq_chip ht_irq_chip = { - .name = "PCI-HT", - .irq_mask = mask_ht_irq, - .irq_unmask = unmask_ht_irq, - .irq_ack = ack_apic_edge, - .irq_set_affinity = ht_set_affinity, - .irq_retrigger = ioapic_retrigger_irq, -}; - -int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev) -{ - struct irq_cfg *cfg; - struct ht_irq_msg msg; - unsigned dest; - int err; - - if (disable_apic) - return -ENXIO; - - cfg = irq_cfg(irq); - err = assign_irq_vector(irq, cfg, apic->target_cpus()); - if (err) - return err; - - err = apic->cpu_mask_to_apicid_and(cfg->domain, - apic->target_cpus(), &dest); - if (err) - return err; - - msg.address_hi = HT_IRQ_HIGH_DEST_ID(dest); - - msg.address_lo = - HT_IRQ_LOW_BASE | - HT_IRQ_LOW_DEST_ID(dest) | - HT_IRQ_LOW_VECTOR(cfg->vector) | - ((apic->irq_dest_mode == 0) ? - HT_IRQ_LOW_DM_PHYSICAL : - HT_IRQ_LOW_DM_LOGICAL) | - HT_IRQ_LOW_RQEOI_EDGE | - ((apic->irq_delivery_mode != dest_LowestPrio) ? - HT_IRQ_LOW_MT_FIXED : - HT_IRQ_LOW_MT_ARBITRATED) | - HT_IRQ_LOW_IRQ_MASKED; - - write_ht_irq_msg(irq, &msg); - - irq_set_chip_and_handler_name(irq, &ht_irq_chip, - handle_edge_irq, "edge"); - - dev_printk(KERN_DEBUG, &dev->dev, "irq %d for HT\n", irq); - - return 0; -} -#endif /* CONFIG_HT_IRQ */ - static int io_apic_setup_irq_pin(unsigned int irq, int node, struct io_apic_irq_attr *attr) { @@ -3446,7 +2462,7 @@ io_apic_setup_irq_pin(unsigned int irq, int node, struct io_apic_irq_attr *attr) return ret; } -static int __init io_apic_get_redir_entries(int ioapic) +static int io_apic_get_redir_entries(int ioapic) { union IO_APIC_reg_01 reg_01; unsigned long flags; @@ -3471,28 +2487,8 @@ unsigned int arch_dynirq_lower_bound(unsigned int from) return ioapic_initialized ? ioapic_dynirq_base : gsi_top; } -int __init arch_probe_nr_irqs(void) -{ - int nr; - - if (nr_irqs > (NR_VECTORS * nr_cpu_ids)) - nr_irqs = NR_VECTORS * nr_cpu_ids; - - nr = (gsi_top + nr_legacy_irqs()) + 8 * nr_cpu_ids; -#if defined(CONFIG_PCI_MSI) || defined(CONFIG_HT_IRQ) - /* - * for MSI and HT dyn irq - */ - nr += gsi_top * 16; -#endif - if (nr < nr_irqs) - nr_irqs = nr; - - return 0; -} - #ifdef CONFIG_X86_32 -static int __init io_apic_get_unique_id(int ioapic, int apic_id) +static int io_apic_get_unique_id(int ioapic, int apic_id) { union IO_APIC_reg_00 reg_00; static physid_mask_t apic_id_map = PHYSID_MASK_NONE; @@ -3567,30 +2563,63 @@ static int __init io_apic_get_unique_id(int ioapic, int apic_id) return apic_id; } -static u8 __init io_apic_unique_id(u8 id) +static u8 io_apic_unique_id(int idx, u8 id) { if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && !APIC_XAPIC(apic_version[boot_cpu_physical_apicid])) - return io_apic_get_unique_id(nr_ioapics, id); + return io_apic_get_unique_id(idx, id); else return id; } #else -static u8 __init io_apic_unique_id(u8 id) +static u8 io_apic_unique_id(int idx, u8 id) { - int i; + union IO_APIC_reg_00 reg_00; DECLARE_BITMAP(used, 256); + unsigned long flags; + u8 new_id; + int i; bitmap_zero(used, 256); for_each_ioapic(i) __set_bit(mpc_ioapic_id(i), used); + + /* Hand out the requested id if available */ if (!test_bit(id, used)) return id; - return find_first_zero_bit(used, 256); + + /* + * Read the current id from the ioapic and keep it if + * available. + */ + raw_spin_lock_irqsave(&ioapic_lock, flags); + reg_00.raw = io_apic_read(idx, 0); + raw_spin_unlock_irqrestore(&ioapic_lock, flags); + new_id = reg_00.bits.ID; + if (!test_bit(new_id, used)) { + apic_printk(APIC_VERBOSE, KERN_INFO + "IOAPIC[%d]: Using reg apic_id %d instead of %d\n", + idx, new_id, id); + return new_id; + } + + /* + * Get the next free id and write it to the ioapic. + */ + new_id = find_first_zero_bit(used, 256); + reg_00.bits.ID = new_id; + raw_spin_lock_irqsave(&ioapic_lock, flags); + io_apic_write(idx, 0, reg_00.raw); + reg_00.raw = io_apic_read(idx, 0); + raw_spin_unlock_irqrestore(&ioapic_lock, flags); + /* Sanity check */ + BUG_ON(reg_00.bits.ID != new_id); + + return new_id; } #endif -static int __init io_apic_get_version(int ioapic) +static int io_apic_get_version(int ioapic) { union IO_APIC_reg_01 reg_01; unsigned long flags; @@ -3697,6 +2726,7 @@ static struct resource * __init ioapic_setup_resources(void) snprintf(mem, IOAPIC_RESOURCE_NAME_SIZE, "IOAPIC %u", i); mem += IOAPIC_RESOURCE_NAME_SIZE; num++; + ioapics[i].iomem_res = res; } ioapic_resources = res; @@ -3794,21 +2824,7 @@ int mp_find_ioapic_pin(int ioapic, u32 gsi) return gsi - gsi_cfg->gsi_base; } -static __init int bad_ioapic(unsigned long address) -{ - if (nr_ioapics >= MAX_IO_APICS) { - pr_warn("WARNING: Max # of I/O APICs (%d) exceeded (found %d), skipping\n", - MAX_IO_APICS, nr_ioapics); - return 1; - } - if (!address) { - pr_warn("WARNING: Bogus (zero) I/O APIC address found in table, skipping!\n"); - return 1; - } - return 0; -} - -static __init int bad_ioapic_register(int idx) +static int bad_ioapic_register(int idx) { union IO_APIC_reg_00 reg_00; union IO_APIC_reg_01 reg_01; @@ -3827,32 +2843,61 @@ static __init int bad_ioapic_register(int idx) return 0; } -void __init mp_register_ioapic(int id, u32 address, u32 gsi_base, - struct ioapic_domain_cfg *cfg) +static int find_free_ioapic_entry(void) { - int idx = 0; - int entries; + int idx; + + for (idx = 0; idx < MAX_IO_APICS; idx++) + if (ioapics[idx].nr_registers == 0) + return idx; + + return MAX_IO_APICS; +} + +/** + * mp_register_ioapic - Register an IOAPIC device + * @id: hardware IOAPIC ID + * @address: physical address of IOAPIC register area + * @gsi_base: base of GSI associated with the IOAPIC + * @cfg: configuration information for the IOAPIC + */ +int mp_register_ioapic(int id, u32 address, u32 gsi_base, + struct ioapic_domain_cfg *cfg) +{ + bool hotplug = !!ioapic_initialized; struct mp_ioapic_gsi *gsi_cfg; + int idx, ioapic, entries; + u32 gsi_end; - if (bad_ioapic(address)) - return; + if (!address) { + pr_warn("Bogus (zero) I/O APIC address found, skipping!\n"); + return -EINVAL; + } + for_each_ioapic(ioapic) + if (ioapics[ioapic].mp_config.apicaddr == address) { + pr_warn("address 0x%x conflicts with IOAPIC%d\n", + address, ioapic); + return -EEXIST; + } - idx = nr_ioapics; + idx = find_free_ioapic_entry(); + if (idx >= MAX_IO_APICS) { + pr_warn("Max # of I/O APICs (%d) exceeded (found %d), skipping\n", + MAX_IO_APICS, idx); + return -ENOSPC; + } ioapics[idx].mp_config.type = MP_IOAPIC; ioapics[idx].mp_config.flags = MPC_APIC_USABLE; ioapics[idx].mp_config.apicaddr = address; - ioapics[idx].irqdomain = NULL; - ioapics[idx].irqdomain_cfg = *cfg; set_fixmap_nocache(FIX_IO_APIC_BASE_0 + idx, address); - if (bad_ioapic_register(idx)) { clear_fixmap(FIX_IO_APIC_BASE_0 + idx); - return; + return -ENODEV; } - ioapics[idx].mp_config.apicid = io_apic_unique_id(id); + ioapics[idx].mp_config.apicid = io_apic_unique_id(idx, id); ioapics[idx].mp_config.apicver = io_apic_get_version(idx); /* @@ -3860,24 +2905,112 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base, * and to prevent reprogramming of IOAPIC pins (PCI GSIs). */ entries = io_apic_get_redir_entries(idx); + gsi_end = gsi_base + entries - 1; + for_each_ioapic(ioapic) { + gsi_cfg = mp_ioapic_gsi_routing(ioapic); + if ((gsi_base >= gsi_cfg->gsi_base && + gsi_base <= gsi_cfg->gsi_end) || + (gsi_end >= gsi_cfg->gsi_base && + gsi_end <= gsi_cfg->gsi_end)) { + pr_warn("GSI range [%u-%u] for new IOAPIC conflicts with GSI[%u-%u]\n", + gsi_base, gsi_end, + gsi_cfg->gsi_base, gsi_cfg->gsi_end); + clear_fixmap(FIX_IO_APIC_BASE_0 + idx); + return -ENOSPC; + } + } gsi_cfg = mp_ioapic_gsi_routing(idx); gsi_cfg->gsi_base = gsi_base; - gsi_cfg->gsi_end = gsi_base + entries - 1; + gsi_cfg->gsi_end = gsi_end; + + ioapics[idx].irqdomain = NULL; + ioapics[idx].irqdomain_cfg = *cfg; /* - * The number of IO-APIC IRQ registers (== #pins): + * If mp_register_ioapic() is called during early boot stage when + * walking ACPI/SFI/DT tables, it's too early to create irqdomain, + * we are still using bootmem allocator. So delay it to setup_IO_APIC(). */ - ioapics[idx].nr_registers = entries; + if (hotplug) { + if (mp_irqdomain_create(idx)) { + clear_fixmap(FIX_IO_APIC_BASE_0 + idx); + return -ENOMEM; + } + alloc_ioapic_saved_registers(idx); + } if (gsi_cfg->gsi_end >= gsi_top) gsi_top = gsi_cfg->gsi_end + 1; + if (nr_ioapics <= idx) + nr_ioapics = idx + 1; + + /* Set nr_registers to mark entry present */ + ioapics[idx].nr_registers = entries; pr_info("IOAPIC[%d]: apic_id %d, version %d, address 0x%x, GSI %d-%d\n", idx, mpc_ioapic_id(idx), mpc_ioapic_ver(idx), mpc_ioapic_addr(idx), gsi_cfg->gsi_base, gsi_cfg->gsi_end); - nr_ioapics++; + return 0; +} + +int mp_unregister_ioapic(u32 gsi_base) +{ + int ioapic, pin; + int found = 0; + struct mp_pin_info *pin_info; + + for_each_ioapic(ioapic) + if (ioapics[ioapic].gsi_config.gsi_base == gsi_base) { + found = 1; + break; + } + if (!found) { + pr_warn("can't find IOAPIC for GSI %d\n", gsi_base); + return -ENODEV; + } + + for_each_pin(ioapic, pin) { + pin_info = mp_pin_info(ioapic, pin); + if (pin_info->count) { + pr_warn("pin%d on IOAPIC%d is still in use.\n", + pin, ioapic); + return -EBUSY; + } + } + + /* Mark entry not present */ + ioapics[ioapic].nr_registers = 0; + ioapic_destroy_irqdomain(ioapic); + free_ioapic_saved_registers(ioapic); + if (ioapics[ioapic].iomem_res) + release_resource(ioapics[ioapic].iomem_res); + clear_fixmap(FIX_IO_APIC_BASE_0 + ioapic); + memset(&ioapics[ioapic], 0, sizeof(ioapics[ioapic])); + + return 0; +} + +int mp_ioapic_registered(u32 gsi_base) +{ + int ioapic; + + for_each_ioapic(ioapic) + if (ioapics[ioapic].gsi_config.gsi_base == gsi_base) + return 1; + + return 0; +} + +static inline void set_io_apic_irq_attr(struct io_apic_irq_attr *irq_attr, + int ioapic, int ioapic_pin, + int trigger, int polarity) +{ + irq_attr->ioapic = ioapic; + irq_attr->ioapic_pin = ioapic_pin; + irq_attr->trigger = trigger; + irq_attr->polarity = polarity; } int mp_irqdomain_map(struct irq_domain *domain, unsigned int virq, @@ -3926,7 +3059,7 @@ void mp_irqdomain_unmap(struct irq_domain *domain, unsigned int virq) ioapic_mask_entry(ioapic, pin); __remove_pin_from_irq(cfg, ioapic, pin); - WARN_ON(cfg->irq_2_pin != NULL); + WARN_ON(!list_empty(&cfg->irq_2_pin)); arch_teardown_hwirq(virq); } @@ -3959,18 +3092,6 @@ int mp_set_gsi_attr(u32 gsi, int trigger, int polarity, int node) return ret; } -bool mp_should_keep_irq(struct device *dev) -{ - if (dev->power.is_prepared) - return true; -#ifdef CONFIG_PM_RUNTIME - if (dev->power.runtime_status == RPM_SUSPENDING) - return true; -#endif - - return false; -} - /* Enable IOAPIC early just for system timer */ void __init pre_init_apic_IRQ0(void) { diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c new file mode 100644 index 000000000000..d6ba2d660dc5 --- /dev/null +++ b/arch/x86/kernel/apic/msi.c @@ -0,0 +1,286 @@ +/* + * Support of MSI, HPET and DMAR interrupts. + * + * Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo + * Moved from arch/x86/kernel/apic/io_apic.c. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include <linux/mm.h> +#include <linux/interrupt.h> +#include <linux/pci.h> +#include <linux/dmar.h> +#include <linux/hpet.h> +#include <linux/msi.h> +#include <asm/msidef.h> +#include <asm/hpet.h> +#include <asm/hw_irq.h> +#include <asm/apic.h> +#include <asm/irq_remapping.h> + +void native_compose_msi_msg(struct pci_dev *pdev, + unsigned int irq, unsigned int dest, + struct msi_msg *msg, u8 hpet_id) +{ + struct irq_cfg *cfg = irq_cfg(irq); + + msg->address_hi = MSI_ADDR_BASE_HI; + + if (x2apic_enabled()) + msg->address_hi |= MSI_ADDR_EXT_DEST_ID(dest); + + msg->address_lo = + MSI_ADDR_BASE_LO | + ((apic->irq_dest_mode == 0) ? + MSI_ADDR_DEST_MODE_PHYSICAL : + MSI_ADDR_DEST_MODE_LOGICAL) | + ((apic->irq_delivery_mode != dest_LowestPrio) ? + MSI_ADDR_REDIRECTION_CPU : + MSI_ADDR_REDIRECTION_LOWPRI) | + MSI_ADDR_DEST_ID(dest); + + msg->data = + MSI_DATA_TRIGGER_EDGE | + MSI_DATA_LEVEL_ASSERT | + ((apic->irq_delivery_mode != dest_LowestPrio) ? + MSI_DATA_DELIVERY_FIXED : + MSI_DATA_DELIVERY_LOWPRI) | + MSI_DATA_VECTOR(cfg->vector); +} + +static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, + struct msi_msg *msg, u8 hpet_id) +{ + struct irq_cfg *cfg; + int err; + unsigned dest; + + if (disable_apic) + return -ENXIO; + + cfg = irq_cfg(irq); + err = assign_irq_vector(irq, cfg, apic->target_cpus()); + if (err) + return err; + + err = apic->cpu_mask_to_apicid_and(cfg->domain, + apic->target_cpus(), &dest); + if (err) + return err; + + x86_msi.compose_msi_msg(pdev, irq, dest, msg, hpet_id); + + return 0; +} + +static int +msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) +{ + struct irq_cfg *cfg = irqd_cfg(data); + struct msi_msg msg; + unsigned int dest; + int ret; + + ret = apic_set_affinity(data, mask, &dest); + if (ret) + return ret; + + __get_cached_msi_msg(data->msi_desc, &msg); + + msg.data &= ~MSI_DATA_VECTOR_MASK; + msg.data |= MSI_DATA_VECTOR(cfg->vector); + msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK; + msg.address_lo |= MSI_ADDR_DEST_ID(dest); + + __pci_write_msi_msg(data->msi_desc, &msg); + + return IRQ_SET_MASK_OK_NOCOPY; +} + +/* + * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices, + * which implement the MSI or MSI-X Capability Structure. + */ +static struct irq_chip msi_chip = { + .name = "PCI-MSI", + .irq_unmask = pci_msi_unmask_irq, + .irq_mask = pci_msi_mask_irq, + .irq_ack = apic_ack_edge, + .irq_set_affinity = msi_set_affinity, + .irq_retrigger = apic_retrigger_irq, + .flags = IRQCHIP_SKIP_SET_WAKE, +}; + +int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, + unsigned int irq_base, unsigned int irq_offset) +{ + struct irq_chip *chip = &msi_chip; + struct msi_msg msg; + unsigned int irq = irq_base + irq_offset; + int ret; + + ret = msi_compose_msg(dev, irq, &msg, -1); + if (ret < 0) + return ret; + + irq_set_msi_desc_off(irq_base, irq_offset, msidesc); + + /* + * MSI-X message is written per-IRQ, the offset is always 0. + * MSI message denotes a contiguous group of IRQs, written for 0th IRQ. + */ + if (!irq_offset) + pci_write_msi_msg(irq, &msg); + + setup_remapped_irq(irq, irq_cfg(irq), chip); + + irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge"); + + dev_dbg(&dev->dev, "irq %d for MSI/MSI-X\n", irq); + + return 0; +} + +int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) +{ + struct msi_desc *msidesc; + unsigned int irq; + int node, ret; + + /* Multiple MSI vectors only supported with interrupt remapping */ + if (type == PCI_CAP_ID_MSI && nvec > 1) + return 1; + + node = dev_to_node(&dev->dev); + + list_for_each_entry(msidesc, &dev->msi_list, list) { + irq = irq_alloc_hwirq(node); + if (!irq) + return -ENOSPC; + + ret = setup_msi_irq(dev, msidesc, irq, 0); + if (ret < 0) { + irq_free_hwirq(irq); + return ret; + } + + } + return 0; +} + +void native_teardown_msi_irq(unsigned int irq) +{ + irq_free_hwirq(irq); +} + +#ifdef CONFIG_DMAR_TABLE +static int +dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask, + bool force) +{ + struct irq_cfg *cfg = irqd_cfg(data); + unsigned int dest, irq = data->irq; + struct msi_msg msg; + int ret; + + ret = apic_set_affinity(data, mask, &dest); + if (ret) + return ret; + + dmar_msi_read(irq, &msg); + + msg.data &= ~MSI_DATA_VECTOR_MASK; + msg.data |= MSI_DATA_VECTOR(cfg->vector); + msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK; + msg.address_lo |= MSI_ADDR_DEST_ID(dest); + msg.address_hi = MSI_ADDR_BASE_HI | MSI_ADDR_EXT_DEST_ID(dest); + + dmar_msi_write(irq, &msg); + + return IRQ_SET_MASK_OK_NOCOPY; +} + +static struct irq_chip dmar_msi_type = { + .name = "DMAR_MSI", + .irq_unmask = dmar_msi_unmask, + .irq_mask = dmar_msi_mask, + .irq_ack = apic_ack_edge, + .irq_set_affinity = dmar_msi_set_affinity, + .irq_retrigger = apic_retrigger_irq, + .flags = IRQCHIP_SKIP_SET_WAKE, +}; + +int arch_setup_dmar_msi(unsigned int irq) +{ + int ret; + struct msi_msg msg; + + ret = msi_compose_msg(NULL, irq, &msg, -1); + if (ret < 0) + return ret; + dmar_msi_write(irq, &msg); + irq_set_chip_and_handler_name(irq, &dmar_msi_type, handle_edge_irq, + "edge"); + return 0; +} +#endif + +/* + * MSI message composition + */ +#ifdef CONFIG_HPET_TIMER + +static int hpet_msi_set_affinity(struct irq_data *data, + const struct cpumask *mask, bool force) +{ + struct irq_cfg *cfg = irqd_cfg(data); + struct msi_msg msg; + unsigned int dest; + int ret; + + ret = apic_set_affinity(data, mask, &dest); + if (ret) + return ret; + + hpet_msi_read(data->handler_data, &msg); + + msg.data &= ~MSI_DATA_VECTOR_MASK; + msg.data |= MSI_DATA_VECTOR(cfg->vector); + msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK; + msg.address_lo |= MSI_ADDR_DEST_ID(dest); + + hpet_msi_write(data->handler_data, &msg); + + return IRQ_SET_MASK_OK_NOCOPY; +} + +static struct irq_chip hpet_msi_type = { + .name = "HPET_MSI", + .irq_unmask = hpet_msi_unmask, + .irq_mask = hpet_msi_mask, + .irq_ack = apic_ack_edge, + .irq_set_affinity = hpet_msi_set_affinity, + .irq_retrigger = apic_retrigger_irq, + .flags = IRQCHIP_SKIP_SET_WAKE, +}; + +int default_setup_hpet_msi(unsigned int irq, unsigned int id) +{ + struct irq_chip *chip = &hpet_msi_type; + struct msi_msg msg; + int ret; + + ret = msi_compose_msg(NULL, irq, &msg, id); + if (ret < 0) + return ret; + + hpet_msi_write(irq_get_handler_data(irq), &msg); + irq_set_status_flags(irq, IRQ_MOVE_PCNTXT); + setup_remapped_irq(irq, irq_cfg(irq), chip); + + irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge"); + return 0; +} +#endif diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c new file mode 100644 index 000000000000..6cedd7914581 --- /dev/null +++ b/arch/x86/kernel/apic/vector.c @@ -0,0 +1,719 @@ +/* + * Local APIC related interfaces to support IOAPIC, MSI, HT_IRQ etc. + * + * Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo + * Moved from arch/x86/kernel/apic/io_apic.c. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include <linux/interrupt.h> +#include <linux/init.h> +#include <linux/compiler.h> +#include <linux/irqdomain.h> +#include <linux/slab.h> +#include <asm/hw_irq.h> +#include <asm/apic.h> +#include <asm/i8259.h> +#include <asm/desc.h> +#include <asm/irq_remapping.h> + +static DEFINE_RAW_SPINLOCK(vector_lock); + +void lock_vector_lock(void) +{ + /* Used to the online set of cpus does not change + * during assign_irq_vector. + */ + raw_spin_lock(&vector_lock); +} + +void unlock_vector_lock(void) +{ + raw_spin_unlock(&vector_lock); +} + +struct irq_cfg *irq_cfg(unsigned int irq) +{ + return irq_get_chip_data(irq); +} + +struct irq_cfg *irqd_cfg(struct irq_data *irq_data) +{ + return irq_data->chip_data; +} + +static struct irq_cfg *alloc_irq_cfg(unsigned int irq, int node) +{ + struct irq_cfg *cfg; + + cfg = kzalloc_node(sizeof(*cfg), GFP_KERNEL, node); + if (!cfg) + return NULL; + if (!zalloc_cpumask_var_node(&cfg->domain, GFP_KERNEL, node)) + goto out_cfg; + if (!zalloc_cpumask_var_node(&cfg->old_domain, GFP_KERNEL, node)) + goto out_domain; +#ifdef CONFIG_X86_IO_APIC + INIT_LIST_HEAD(&cfg->irq_2_pin); +#endif + return cfg; +out_domain: + free_cpumask_var(cfg->domain); +out_cfg: + kfree(cfg); + return NULL; +} + +struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node) +{ + int res = irq_alloc_desc_at(at, node); + struct irq_cfg *cfg; + + if (res < 0) { + if (res != -EEXIST) + return NULL; + cfg = irq_cfg(at); + if (cfg) + return cfg; + } + + cfg = alloc_irq_cfg(at, node); + if (cfg) + irq_set_chip_data(at, cfg); + else + irq_free_desc(at); + return cfg; +} + +static void free_irq_cfg(unsigned int at, struct irq_cfg *cfg) +{ + if (!cfg) + return; + irq_set_chip_data(at, NULL); + free_cpumask_var(cfg->domain); + free_cpumask_var(cfg->old_domain); + kfree(cfg); +} + +static int +__assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask) +{ + /* + * NOTE! The local APIC isn't very good at handling + * multiple interrupts at the same interrupt level. + * As the interrupt level is determined by taking the + * vector number and shifting that right by 4, we + * want to spread these out a bit so that they don't + * all fall in the same interrupt level. + * + * Also, we've got to be careful not to trash gate + * 0x80, because int 0x80 is hm, kind of importantish. ;) + */ + static int current_vector = FIRST_EXTERNAL_VECTOR + VECTOR_OFFSET_START; + static int current_offset = VECTOR_OFFSET_START % 16; + int cpu, err; + cpumask_var_t tmp_mask; + + if (cfg->move_in_progress) + return -EBUSY; + + if (!alloc_cpumask_var(&tmp_mask, GFP_ATOMIC)) + return -ENOMEM; + + /* Only try and allocate irqs on cpus that are present */ + err = -ENOSPC; + cpumask_clear(cfg->old_domain); + cpu = cpumask_first_and(mask, cpu_online_mask); + while (cpu < nr_cpu_ids) { + int new_cpu, vector, offset; + + apic->vector_allocation_domain(cpu, tmp_mask, mask); + + if (cpumask_subset(tmp_mask, cfg->domain)) { + err = 0; + if (cpumask_equal(tmp_mask, cfg->domain)) + break; + /* + * New cpumask using the vector is a proper subset of + * the current in use mask. So cleanup the vector + * allocation for the members that are not used anymore. + */ + cpumask_andnot(cfg->old_domain, cfg->domain, tmp_mask); + cfg->move_in_progress = + cpumask_intersects(cfg->old_domain, cpu_online_mask); + cpumask_and(cfg->domain, cfg->domain, tmp_mask); + break; + } + + vector = current_vector; + offset = current_offset; +next: + vector += 16; + if (vector >= first_system_vector) { + offset = (offset + 1) % 16; + vector = FIRST_EXTERNAL_VECTOR + offset; + } + + if (unlikely(current_vector == vector)) { + cpumask_or(cfg->old_domain, cfg->old_domain, tmp_mask); + cpumask_andnot(tmp_mask, mask, cfg->old_domain); + cpu = cpumask_first_and(tmp_mask, cpu_online_mask); + continue; + } + + 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] > + VECTOR_UNDEFINED) + goto next; + } + /* Found one! */ + current_vector = vector; + current_offset = offset; + if (cfg->vector) { + cpumask_copy(cfg->old_domain, cfg->domain); + cfg->move_in_progress = + cpumask_intersects(cfg->old_domain, cpu_online_mask); + } + for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask) + per_cpu(vector_irq, new_cpu)[vector] = irq; + cfg->vector = vector; + cpumask_copy(cfg->domain, tmp_mask); + err = 0; + break; + } + free_cpumask_var(tmp_mask); + + return err; +} + +int assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask) +{ + int err; + unsigned long flags; + + raw_spin_lock_irqsave(&vector_lock, flags); + err = __assign_irq_vector(irq, cfg, mask); + raw_spin_unlock_irqrestore(&vector_lock, flags); + return err; +} + +void clear_irq_vector(int irq, struct irq_cfg *cfg) +{ + int cpu, vector; + unsigned long flags; + + raw_spin_lock_irqsave(&vector_lock, flags); + BUG_ON(!cfg->vector); + + vector = cfg->vector; + for_each_cpu_and(cpu, cfg->domain, cpu_online_mask) + per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED; + + cfg->vector = 0; + cpumask_clear(cfg->domain); + + if (likely(!cfg->move_in_progress)) { + raw_spin_unlock_irqrestore(&vector_lock, flags); + return; + } + + for_each_cpu_and(cpu, cfg->old_domain, cpu_online_mask) { + for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; + vector++) { + if (per_cpu(vector_irq, cpu)[vector] != irq) + continue; + per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED; + break; + } + } + cfg->move_in_progress = 0; + raw_spin_unlock_irqrestore(&vector_lock, flags); +} + +int __init arch_probe_nr_irqs(void) +{ + int nr; + + if (nr_irqs > (NR_VECTORS * nr_cpu_ids)) + nr_irqs = NR_VECTORS * nr_cpu_ids; + + nr = (gsi_top + nr_legacy_irqs()) + 8 * nr_cpu_ids; +#if defined(CONFIG_PCI_MSI) || defined(CONFIG_HT_IRQ) + /* + * for MSI and HT dyn irq + */ + if (gsi_top <= NR_IRQS_LEGACY) + nr += 8 * nr_cpu_ids; + else + nr += gsi_top * 16; +#endif + if (nr < nr_irqs) + nr_irqs = nr; + + return nr_legacy_irqs(); +} + +int __init arch_early_irq_init(void) +{ + return arch_early_ioapic_init(); +} + +static void __setup_vector_irq(int cpu) +{ + /* Initialize vector_irq on a new cpu */ + int irq, vector; + struct irq_cfg *cfg; + + /* + * vector_lock will make sure that we don't run into irq vector + * assignments that might be happening on another cpu in parallel, + * while we setup our initial vector to irq mappings. + */ + raw_spin_lock(&vector_lock); + /* Mark the inuse vectors */ + for_each_active_irq(irq) { + cfg = irq_cfg(irq); + if (!cfg) + continue; + + if (!cpumask_test_cpu(cpu, cfg->domain)) + continue; + vector = cfg->vector; + per_cpu(vector_irq, cpu)[vector] = irq; + } + /* Mark the free vectors */ + for (vector = 0; vector < NR_VECTORS; ++vector) { + irq = per_cpu(vector_irq, cpu)[vector]; + if (irq <= VECTOR_UNDEFINED) + continue; + + cfg = irq_cfg(irq); + if (!cpumask_test_cpu(cpu, cfg->domain)) + per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED; + } + raw_spin_unlock(&vector_lock); +} + +/* + * Setup the vector to irq mappings. + */ +void setup_vector_irq(int cpu) +{ + int irq; + + /* + * On most of the platforms, legacy PIC delivers the interrupts on the + * boot cpu. But there are certain platforms where PIC interrupts are + * delivered to multiple cpu's. If the legacy IRQ is handled by the + * legacy PIC, for the new cpu that is coming online, setup the static + * legacy vector to irq mapping: + */ + for (irq = 0; irq < nr_legacy_irqs(); irq++) + per_cpu(vector_irq, cpu)[IRQ0_VECTOR + irq] = irq; + + __setup_vector_irq(cpu); +} + +int apic_retrigger_irq(struct irq_data *data) +{ + struct irq_cfg *cfg = irqd_cfg(data); + unsigned long flags; + int cpu; + + raw_spin_lock_irqsave(&vector_lock, flags); + cpu = cpumask_first_and(cfg->domain, cpu_online_mask); + apic->send_IPI_mask(cpumask_of(cpu), cfg->vector); + raw_spin_unlock_irqrestore(&vector_lock, flags); + + return 1; +} + +void apic_ack_edge(struct irq_data *data) +{ + irq_complete_move(irqd_cfg(data)); + irq_move_irq(data); + ack_APIC_irq(); +} + +/* + * Either sets data->affinity to a valid value, and returns + * ->cpu_mask_to_apicid of that in dest_id, or returns -1 and + * leaves data->affinity untouched. + */ +int apic_set_affinity(struct irq_data *data, const struct cpumask *mask, + unsigned int *dest_id) +{ + struct irq_cfg *cfg = irqd_cfg(data); + unsigned int irq = data->irq; + int err; + + if (!config_enabled(CONFIG_SMP)) + return -EPERM; + + if (!cpumask_intersects(mask, cpu_online_mask)) + return -EINVAL; + + err = assign_irq_vector(irq, cfg, mask); + if (err) + return err; + + err = apic->cpu_mask_to_apicid_and(mask, cfg->domain, dest_id); + if (err) { + if (assign_irq_vector(irq, cfg, data->affinity)) + pr_err("Failed to recover vector for irq %d\n", irq); + return err; + } + + cpumask_copy(data->affinity, mask); + + return 0; +} + +#ifdef CONFIG_SMP +void send_cleanup_vector(struct irq_cfg *cfg) +{ + cpumask_var_t cleanup_mask; + + if (unlikely(!alloc_cpumask_var(&cleanup_mask, GFP_ATOMIC))) { + unsigned int i; + + for_each_cpu_and(i, cfg->old_domain, cpu_online_mask) + apic->send_IPI_mask(cpumask_of(i), + IRQ_MOVE_CLEANUP_VECTOR); + } else { + cpumask_and(cleanup_mask, cfg->old_domain, cpu_online_mask); + apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR); + free_cpumask_var(cleanup_mask); + } + cfg->move_in_progress = 0; +} + +asmlinkage __visible void smp_irq_move_cleanup_interrupt(void) +{ + unsigned vector, me; + + ack_APIC_irq(); + irq_enter(); + exit_idle(); + + me = smp_processor_id(); + for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { + int irq; + unsigned int irr; + struct irq_desc *desc; + struct irq_cfg *cfg; + + irq = __this_cpu_read(vector_irq[vector]); + + if (irq <= VECTOR_UNDEFINED) + continue; + + desc = irq_to_desc(irq); + if (!desc) + continue; + + cfg = irq_cfg(irq); + if (!cfg) + continue; + + raw_spin_lock(&desc->lock); + + /* + * Check if the irq migration is in progress. If so, we + * haven't received the cleanup request yet for this irq. + */ + if (cfg->move_in_progress) + goto unlock; + + if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain)) + goto unlock; + + irr = apic_read(APIC_IRR + (vector / 32 * 0x10)); + /* + * Check if the vector that needs to be cleanedup is + * registered at the cpu's IRR. If so, then this is not + * the best time to clean it up. Lets clean it up in the + * next attempt by sending another IRQ_MOVE_CLEANUP_VECTOR + * to myself. + */ + if (irr & (1 << (vector % 32))) { + apic->send_IPI_self(IRQ_MOVE_CLEANUP_VECTOR); + goto unlock; + } + __this_cpu_write(vector_irq[vector], VECTOR_UNDEFINED); +unlock: + raw_spin_unlock(&desc->lock); + } + + irq_exit(); +} + +static void __irq_complete_move(struct irq_cfg *cfg, unsigned vector) +{ + unsigned me; + + if (likely(!cfg->move_in_progress)) + return; + + me = smp_processor_id(); + + if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain)) + send_cleanup_vector(cfg); +} + +void irq_complete_move(struct irq_cfg *cfg) +{ + __irq_complete_move(cfg, ~get_irq_regs()->orig_ax); +} + +void irq_force_complete_move(int irq) +{ + struct irq_cfg *cfg = irq_cfg(irq); + + if (!cfg) + return; + + __irq_complete_move(cfg, cfg->vector); +} +#endif + +/* + * Dynamic irq allocate and deallocation. Should be replaced by irq domains! + */ +int arch_setup_hwirq(unsigned int irq, int node) +{ + struct irq_cfg *cfg; + unsigned long flags; + int ret; + + cfg = alloc_irq_cfg(irq, node); + if (!cfg) + return -ENOMEM; + + raw_spin_lock_irqsave(&vector_lock, flags); + ret = __assign_irq_vector(irq, cfg, apic->target_cpus()); + raw_spin_unlock_irqrestore(&vector_lock, flags); + + if (!ret) + irq_set_chip_data(irq, cfg); + else + free_irq_cfg(irq, cfg); + return ret; +} + +void arch_teardown_hwirq(unsigned int irq) +{ + struct irq_cfg *cfg = irq_cfg(irq); + + free_remapped_irq(irq); + clear_irq_vector(irq, cfg); + free_irq_cfg(irq, cfg); +} + +static void __init print_APIC_field(int base) +{ + int i; + + printk(KERN_DEBUG); + + for (i = 0; i < 8; i++) + pr_cont("%08x", apic_read(base + i*0x10)); + + pr_cont("\n"); +} + +static void __init print_local_APIC(void *dummy) +{ + unsigned int i, v, ver, maxlvt; + u64 icr; + + pr_debug("printing local APIC contents on CPU#%d/%d:\n", + smp_processor_id(), hard_smp_processor_id()); + v = apic_read(APIC_ID); + pr_info("... APIC ID: %08x (%01x)\n", v, read_apic_id()); + v = apic_read(APIC_LVR); + pr_info("... APIC VERSION: %08x\n", v); + ver = GET_APIC_VERSION(v); + maxlvt = lapic_get_maxlvt(); + + v = apic_read(APIC_TASKPRI); + pr_debug("... APIC TASKPRI: %08x (%02x)\n", v, v & APIC_TPRI_MASK); + + /* !82489DX */ + if (APIC_INTEGRATED(ver)) { + if (!APIC_XAPIC(ver)) { + v = apic_read(APIC_ARBPRI); + pr_debug("... APIC ARBPRI: %08x (%02x)\n", + v, v & APIC_ARBPRI_MASK); + } + v = apic_read(APIC_PROCPRI); + pr_debug("... APIC PROCPRI: %08x\n", v); + } + + /* + * Remote read supported only in the 82489DX and local APIC for + * Pentium processors. + */ + if (!APIC_INTEGRATED(ver) || maxlvt == 3) { + v = apic_read(APIC_RRR); + pr_debug("... APIC RRR: %08x\n", v); + } + + v = apic_read(APIC_LDR); + pr_debug("... APIC LDR: %08x\n", v); + if (!x2apic_enabled()) { + v = apic_read(APIC_DFR); + pr_debug("... APIC DFR: %08x\n", v); + } + v = apic_read(APIC_SPIV); + pr_debug("... APIC SPIV: %08x\n", v); + + pr_debug("... APIC ISR field:\n"); + print_APIC_field(APIC_ISR); + pr_debug("... APIC TMR field:\n"); + print_APIC_field(APIC_TMR); + pr_debug("... APIC IRR field:\n"); + print_APIC_field(APIC_IRR); + + /* !82489DX */ + if (APIC_INTEGRATED(ver)) { + /* Due to the Pentium erratum 3AP. */ + if (maxlvt > 3) + apic_write(APIC_ESR, 0); + + v = apic_read(APIC_ESR); + pr_debug("... APIC ESR: %08x\n", v); + } + + icr = apic_icr_read(); + pr_debug("... APIC ICR: %08x\n", (u32)icr); + pr_debug("... APIC ICR2: %08x\n", (u32)(icr >> 32)); + + v = apic_read(APIC_LVTT); + pr_debug("... APIC LVTT: %08x\n", v); + + if (maxlvt > 3) { + /* PC is LVT#4. */ + v = apic_read(APIC_LVTPC); + pr_debug("... APIC LVTPC: %08x\n", v); + } + v = apic_read(APIC_LVT0); + pr_debug("... APIC LVT0: %08x\n", v); + v = apic_read(APIC_LVT1); + pr_debug("... APIC LVT1: %08x\n", v); + + if (maxlvt > 2) { + /* ERR is LVT#3. */ + v = apic_read(APIC_LVTERR); + pr_debug("... APIC LVTERR: %08x\n", v); + } + + v = apic_read(APIC_TMICT); + pr_debug("... APIC TMICT: %08x\n", v); + v = apic_read(APIC_TMCCT); + pr_debug("... APIC TMCCT: %08x\n", v); + v = apic_read(APIC_TDCR); + pr_debug("... APIC TDCR: %08x\n", v); + + if (boot_cpu_has(X86_FEATURE_EXTAPIC)) { + v = apic_read(APIC_EFEAT); + maxlvt = (v >> 16) & 0xff; + pr_debug("... APIC EFEAT: %08x\n", v); + v = apic_read(APIC_ECTRL); + pr_debug("... APIC ECTRL: %08x\n", v); + for (i = 0; i < maxlvt; i++) { + v = apic_read(APIC_EILVTn(i)); + pr_debug("... APIC EILVT%d: %08x\n", i, v); + } + } + pr_cont("\n"); +} + +static void __init print_local_APICs(int maxcpu) +{ + int cpu; + + if (!maxcpu) + return; + + preempt_disable(); + for_each_online_cpu(cpu) { + if (cpu >= maxcpu) + break; + smp_call_function_single(cpu, print_local_APIC, NULL, 1); + } + preempt_enable(); +} + +static void __init print_PIC(void) +{ + unsigned int v; + unsigned long flags; + + if (!nr_legacy_irqs()) + return; + + pr_debug("\nprinting PIC contents\n"); + + raw_spin_lock_irqsave(&i8259A_lock, flags); + + v = inb(0xa1) << 8 | inb(0x21); + pr_debug("... PIC IMR: %04x\n", v); + + v = inb(0xa0) << 8 | inb(0x20); + pr_debug("... PIC IRR: %04x\n", v); + + outb(0x0b, 0xa0); + outb(0x0b, 0x20); + v = inb(0xa0) << 8 | inb(0x20); + outb(0x0a, 0xa0); + outb(0x0a, 0x20); + + raw_spin_unlock_irqrestore(&i8259A_lock, flags); + + pr_debug("... PIC ISR: %04x\n", v); + + v = inb(0x4d1) << 8 | inb(0x4d0); + pr_debug("... PIC ELCR: %04x\n", v); +} + +static int show_lapic __initdata = 1; +static __init int setup_show_lapic(char *arg) +{ + int num = -1; + + if (strcmp(arg, "all") == 0) { + show_lapic = CONFIG_NR_CPUS; + } else { + get_option(&arg, &num); + if (num >= 0) + show_lapic = num; + } + + return 1; +} +__setup("show_lapic=", setup_show_lapic); + +static int __init print_ICs(void) +{ + if (apic_verbosity == APIC_QUIET) + return 0; + + print_PIC(); + + /* don't print out if apic is not there */ + if (!cpu_has_apic && !apic_from_smp_config()) + return 0; + + print_local_APICs(show_lapic); + print_IO_APICs(); + + return 0; +} + +late_initcall(print_ICs); diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index 6ce600f9bc78..e658f21681c8 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -42,7 +42,7 @@ __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest) * We are to modify mask, so we need an own copy * and be sure it's manipulated with irq off. */ - ipi_mask_ptr = __raw_get_cpu_var(ipi_mask); + ipi_mask_ptr = this_cpu_cpumask_var_ptr(ipi_mask); cpumask_copy(ipi_mask_ptr, mask); /* diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 004f017aa7b9..8e9dcfd630e4 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -204,7 +204,6 @@ EXPORT_SYMBOL(sn_rtc_cycles_per_second); static int uv_wakeup_secondary(int phys_apicid, unsigned long start_rip) { -#ifdef CONFIG_SMP unsigned long val; int pnode; @@ -223,7 +222,6 @@ static int uv_wakeup_secondary(int phys_apicid, unsigned long start_rip) uv_write_global_mmr64(pnode, UVH_IPI_INT, val); atomic_set(&init_deasserted, 1); -#endif return 0; } diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 584874451414..927ec9235947 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -378,7 +378,6 @@ static struct cpuidle_driver apm_idle_driver = { { /* entry 1 is for APM idle */ .name = "APM", .desc = "APM idle", - .flags = CPUIDLE_FLAG_TIME_VALID, .exit_latency = 250, /* WAG */ .target_residency = 500, /* WAG */ .enter = &apm_cpu_idle diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index d67c4be3e8b1..3b3b9d33ac1d 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -1,3 +1,7 @@ +#ifndef __LINUX_KBUILD_H +# error "Please do not build this file directly, build asm-offsets.c instead" +#endif + #include <asm/ucontext.h> #include <linux/lguest.h> diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index e7c798b354fa..fdcbb4d27c9f 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -1,3 +1,7 @@ +#ifndef __LINUX_KBUILD_H +# error "Please do not build this file directly, build asm-offsets.c instead" +#endif + #include <asm/ia32.h> #define __SYSCALL_64(nr, sym, compat) [nr] = 1, @@ -48,7 +52,6 @@ int main(void) #define ENTRY(entry) OFFSET(pt_regs_ ## entry, pt_regs, entry) ENTRY(bx); - ENTRY(bx); ENTRY(cx); ENTRY(dx); ENTRY(sp); diff --git a/arch/x86/kernel/audit_64.c b/arch/x86/kernel/audit_64.c index 06d3e5a14d9d..f3672508b249 100644 --- a/arch/x86/kernel/audit_64.c +++ b/arch/x86/kernel/audit_64.c @@ -50,6 +50,7 @@ int audit_classify_syscall(int abi, unsigned syscall) case __NR_openat: return 3; case __NR_execve: + case __NR_execveat: return 5; default: return 0; diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 7fd54f09b011..80091ae54c2b 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -13,10 +13,13 @@ nostackp := $(call cc-option, -fno-stack-protector) CFLAGS_common.o := $(nostackp) obj-y := intel_cacheinfo.o scattered.o topology.o -obj-y += proc.o capflags.o powerflags.o common.o +obj-y += common.o obj-y += rdrand.o obj-y += match.o +obj-$(CONFIG_PROC_FS) += proc.o +obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o + obj-$(CONFIG_X86_32) += bugs.o obj-$(CONFIG_X86_64) += bugs_64.o @@ -36,7 +39,12 @@ obj-$(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-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_uncore.o perf_event_intel_rapl.o +obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_rapl.o + +obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE) += perf_event_intel_uncore.o \ + perf_event_intel_uncore_snb.o \ + perf_event_intel_uncore_snbep.o \ + perf_event_intel_uncore_nhmex.o endif @@ -48,6 +56,7 @@ obj-$(CONFIG_X86_LOCAL_APIC) += perfctr-watchdog.o perf_event_amd_ibs.o obj-$(CONFIG_HYPERVISOR_GUEST) += vmware.o hypervisor.o mshyperv.o +ifdef CONFIG_X86_FEATURE_NAMES quiet_cmd_mkcapflags = MKCAP $@ cmd_mkcapflags = $(CONFIG_SHELL) $(srctree)/$(src)/mkcapflags.sh $< $@ @@ -56,3 +65,5 @@ cpufeature = $(src)/../../include/asm/cpufeature.h targets += capflags.c $(obj)/capflags.c: $(cpufeature) $(src)/mkcapflags.sh FORCE $(call if_changed,mkcapflags) +endif +clean-files += capflags.c diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 60e5497681f5..15c5df92f74e 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -525,6 +525,13 @@ static void early_init_amd(struct cpuinfo_x86 *c) } #endif + /* + * This is only needed to tell the kernel whether to use VMCALL + * and VMMCALL. VMMCALL is never executed except under virt, so + * we can set it unconditionally. + */ + set_cpu_cap(c, X86_FEATURE_VMMCALL); + /* F16h erratum 793, CVE-2013-6885 */ if (c->x86 == 0x16 && c->x86_model <= 0xf) msr_set_bit(MSR_AMD64_LS_CFG, 15); @@ -559,6 +566,17 @@ static void init_amd_k8(struct cpuinfo_x86 *c) if (!c->x86_model_id[0]) strcpy(c->x86_model_id, "Hammer"); + +#ifdef CONFIG_SMP + /* + * Disable TLB flush filter by setting HWCR.FFDIS on K8 + * bit 6 of msr C001_0015 + * + * Errata 63 for SH-B3 steppings + * Errata 122 for all steppings (F+ have it disabled by default) + */ + msr_set_bit(MSR_K7_HWCR, 6); +#endif } static void init_amd_gh(struct cpuinfo_x86 *c) @@ -629,18 +647,6 @@ static void init_amd(struct cpuinfo_x86 *c) { u32 dummy; -#ifdef CONFIG_SMP - /* - * Disable TLB flush filter by setting HWCR.FFDIS on K8 - * bit 6 of msr C001_0015 - * - * Errata 63 for SH-B3 steppings - * Errata 122 for all steppings (F+ have it disabled by default) - */ - if (c->x86 == 0xf) - msr_set_bit(MSR_K7_HWCR, 6); -#endif - early_init_amd(c); /* diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index e4ab2b42bd6f..c6049650c093 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -146,6 +146,8 @@ EXPORT_PER_CPU_SYMBOL_GPL(gdt_page); static int __init x86_xsave_setup(char *s) { + if (strlen(s)) + return 0; setup_clear_cpu_cap(X86_FEATURE_XSAVE); setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); setup_clear_cpu_cap(X86_FEATURE_XSAVES); @@ -346,8 +348,8 @@ static void filter_cpuid_features(struct cpuinfo_x86 *c, bool warn) continue; printk(KERN_WARNING - "CPU: CPU feature %s disabled, no CPUID level 0x%x\n", - x86_cap_flags[df->feature], df->level); + "CPU: CPU feature " X86_CAP_FMT " disabled, no CPUID level 0x%x\n", + x86_cap_flag(df->feature), df->level); } } @@ -956,14 +958,7 @@ static void identify_cpu(struct cpuinfo_x86 *c) } #ifdef CONFIG_X86_64 -static void vgetcpu_set_mode(void) -{ - if (cpu_has(&boot_cpu_data, X86_FEATURE_RDTSCP)) - vgetcpu_mode = VGETCPU_RDTSCP; - else - vgetcpu_mode = VGETCPU_LSL; -} - +#ifdef CONFIG_IA32_EMULATION /* May not be __init: called during resume */ static void syscall32_cpu_init(void) { @@ -975,7 +970,8 @@ static void syscall32_cpu_init(void) wrmsrl(MSR_CSTAR, ia32_cstar_target); } -#endif +#endif /* CONFIG_IA32_EMULATION */ +#endif /* CONFIG_X86_64 */ #ifdef CONFIG_X86_32 void enable_sep_cpu(void) @@ -1004,8 +1000,6 @@ void __init identify_boot_cpu(void) #ifdef CONFIG_X86_32 sysenter_setup(); enable_sep_cpu(); -#else - vgetcpu_set_mode(); #endif cpu_detect_tlb(&boot_cpu_data); } @@ -1184,7 +1178,7 @@ void syscall_init(void) /* Flags to clear on syscall */ wrmsrl(MSR_SYSCALL_MASK, X86_EFLAGS_TF|X86_EFLAGS_DF|X86_EFLAGS_IF| - X86_EFLAGS_IOPL|X86_EFLAGS_AC); + X86_EFLAGS_IOPL|X86_EFLAGS_AC|X86_EFLAGS_NT); } /* @@ -1198,9 +1192,9 @@ DEFINE_PER_CPU(int, debug_stack_usage); int is_debug_stack(unsigned long addr) { - return __get_cpu_var(debug_stack_usage) || - (addr <= __get_cpu_var(debug_stack_addr) && - addr > (__get_cpu_var(debug_stack_addr) - DEBUG_STKSZ)); + return __this_cpu_read(debug_stack_usage) || + (addr <= __this_cpu_read(debug_stack_addr) && + addr > (__this_cpu_read(debug_stack_addr) - DEBUG_STKSZ)); } NOKPROBE_SYMBOL(is_debug_stack); @@ -1266,6 +1260,19 @@ static void dbg_restore_debug_regs(void) #define dbg_restore_debug_regs() #endif /* ! CONFIG_KGDB */ +static void wait_for_master_cpu(int cpu) +{ +#ifdef CONFIG_SMP + /* + * wait for ACK from master CPU before continuing + * with AP initialization + */ + WARN_ON(cpumask_test_and_set_cpu(cpu, cpu_initialized_mask)); + while (!cpumask_test_cpu(cpu, cpu_callout_mask)) + cpu_relax(); +#endif +} + /* * cpu_init() initializes state that is per-CPU. Some data is already * initialized (naturally) in the bootstrap process, such as the GDT @@ -1281,16 +1288,17 @@ void cpu_init(void) struct task_struct *me; struct tss_struct *t; unsigned long v; - int cpu; + int cpu = stack_smp_processor_id(); int i; + wait_for_master_cpu(cpu); + /* * Load microcode on this cpu if a valid microcode is available. * This is early microcode loading procedure. */ load_ucode_ap(); - cpu = stack_smp_processor_id(); t = &per_cpu(init_tss, cpu); oist = &per_cpu(orig_ist, cpu); @@ -1302,9 +1310,6 @@ void cpu_init(void) me = current; - if (cpumask_test_and_set_cpu(cpu, cpu_initialized_mask)) - panic("CPU#%d already initialized!\n", cpu); - pr_debug("Initializing CPU#%d\n", cpu); clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE); @@ -1381,17 +1386,13 @@ void cpu_init(void) struct tss_struct *t = &per_cpu(init_tss, cpu); struct thread_struct *thread = &curr->thread; - show_ucode_info_early(); + wait_for_master_cpu(cpu); - if (cpumask_test_and_set_cpu(cpu, cpu_initialized_mask)) { - printk(KERN_WARNING "CPU#%d already initialized!\n", cpu); - for (;;) - local_irq_enable(); - } + show_ucode_info_early(); printk(KERN_INFO "Initializing CPU#%d\n", cpu); - if (cpu_has_vme || cpu_has_tsc || cpu_has_de) + if (cpu_feature_enabled(X86_FEATURE_VME) || cpu_has_tsc || cpu_has_de) clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE); load_current_idt(); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 74e804ddc5c7..9cc6b6f25f42 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -144,6 +144,21 @@ static void early_init_intel(struct cpuinfo_x86 *c) setup_clear_cpu_cap(X86_FEATURE_ERMS); } } + + /* + * Intel Quark Core DevMan_001.pdf section 6.4.11 + * "The operating system also is required to invalidate (i.e., flush) + * the TLB when any changes are made to any of the page table entries. + * The operating system must reload CR3 to cause the TLB to be flushed" + * + * As a result cpu_has_pge() in arch/x86/include/asm/tlbflush.h should + * be false so that __flush_tlb_all() causes CR3 insted of CR4.PGE + * to be modified + */ + if (c->x86 == 5 && c->x86_model == 9) { + pr_info("Disabling PGE capability bit\n"); + setup_clear_cpu_cap(X86_FEATURE_PGE); + } } #ifdef CONFIG_X86_32 @@ -198,12 +213,13 @@ static void intel_workarounds(struct cpuinfo_x86 *c) { #ifdef CONFIG_X86_F00F_BUG /* - * All current models of Pentium and Pentium with MMX technology CPUs + * All models of Pentium and Pentium with MMX technology CPUs * have the F0 0F bug, which lets nonprivileged users lock up the * system. Announce that the fault handler will be checking for it. + * The Quark is also family 5, but does not have the same bug. */ clear_cpu_bug(c, X86_BUG_F00F); - if (!paravirt_enabled() && c->x86 == 5) { + if (!paravirt_enabled() && c->x86 == 5 && c->x86_model < 9) { static int f00f_workaround_enabled; set_cpu_bug(c, X86_BUG_F00F); @@ -382,6 +398,13 @@ static void init_intel(struct cpuinfo_x86 *c) } l2 = init_intel_cacheinfo(c); + + /* Detect legacy cache sizes if init_intel_cacheinfo did not */ + if (l2 == 0) { + cpu_detect_cache_sizes(c); + l2 = c->x86_cache_size; + } + if (c->cpuid_level > 9) { unsigned eax = cpuid_eax(10); /* Check for version and the number of counters */ @@ -485,6 +508,13 @@ static unsigned int intel_size_cache(struct cpuinfo_x86 *c, unsigned int size) */ if ((c->x86 == 6) && (c->x86_model == 11) && (size == 0)) size = 256; + + /* + * Intel Quark SoC X1000 contains a 4-way set associative + * 16K cache with a 16 byte cache line and 256 lines per tag + */ + if ((c->x86 == 5) && (c->x86_model == 9)) + size = 16; return size; } #endif @@ -686,7 +716,8 @@ static const struct cpu_dev intel_cpu_dev = { [3] = "OverDrive PODP5V83", [4] = "Pentium MMX", [7] = "Mobile Pentium 75 - 200", - [8] = "Mobile Pentium MMX" + [8] = "Mobile Pentium MMX", + [9] = "Quark SoC X1000", } }, { .family = 6, .model_names = diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c index 5ac2d1fb28bc..4cfba4371a71 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-inject.c +++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c @@ -83,7 +83,7 @@ static DEFINE_MUTEX(mce_inject_mutex); static int mce_raise_notify(unsigned int cmd, struct pt_regs *regs) { int cpu = smp_processor_id(); - struct mce *m = &__get_cpu_var(injectm); + struct mce *m = this_cpu_ptr(&injectm); if (!cpumask_test_cpu(cpu, mce_inject_cpumask)) return NMI_DONE; cpumask_clear_cpu(cpu, mce_inject_cpumask); @@ -97,7 +97,7 @@ static int mce_raise_notify(unsigned int cmd, struct pt_regs *regs) static void mce_irq_ipi(void *info) { int cpu = smp_processor_id(); - struct mce *m = &__get_cpu_var(injectm); + struct mce *m = this_cpu_ptr(&injectm); if (cpumask_test_cpu(cpu, mce_inject_cpumask) && m->inject_flags & MCJ_EXCEPTION) { @@ -109,7 +109,7 @@ static void mce_irq_ipi(void *info) /* Inject mce on current CPU */ static int raise_local(void) { - struct mce *m = &__get_cpu_var(injectm); + struct mce *m = this_cpu_ptr(&injectm); int context = MCJ_CTX(m->inject_flags); int ret = 0; int cpu = m->extcpu; diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index 09edd0b65fef..10b46906767f 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -3,6 +3,8 @@ enum severity_level { MCE_NO_SEVERITY, + MCE_DEFERRED_SEVERITY, + MCE_UCNA_SEVERITY = MCE_DEFERRED_SEVERITY, MCE_KEEP_SEVERITY, MCE_SOME_SEVERITY, MCE_AO_SEVERITY, @@ -21,7 +23,7 @@ struct mce_bank { char attrname[ATTR_LEN]; /* attribute name */ }; -int mce_severity(struct mce *a, int tolerant, char **msg); +int mce_severity(struct mce *a, int tolerant, char **msg, bool is_excp); struct dentry *mce_get_debugfs_dir(void); extern struct mce_bank *mce_banks; diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c index c370e1c4468b..8bb433043a7f 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-severity.c +++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c @@ -31,6 +31,7 @@ enum context { IN_KERNEL = 1, IN_USER = 2 }; enum ser { SER_REQUIRED = 1, NO_SER = 2 }; +enum exception { EXCP_CONTEXT = 1, NO_EXCP = 2 }; static struct severity { u64 mask; @@ -40,6 +41,7 @@ static struct severity { unsigned char mcgres; unsigned char ser; unsigned char context; + unsigned char excp; unsigned char covered; char *msg; } severities[] = { @@ -48,6 +50,8 @@ static struct severity { #define USER .context = IN_USER #define SER .ser = SER_REQUIRED #define NOSER .ser = NO_SER +#define EXCP .excp = EXCP_CONTEXT +#define NOEXCP .excp = NO_EXCP #define BITCLR(x) .mask = x, .result = 0 #define BITSET(x) .mask = x, .result = x #define MCGMASK(x, y) .mcgmask = x, .mcgres = y @@ -62,7 +66,7 @@ static struct severity { ), MCESEV( NO, "Not enabled", - BITCLR(MCI_STATUS_EN) + EXCP, BITCLR(MCI_STATUS_EN) ), MCESEV( PANIC, "Processor context corrupt", @@ -71,16 +75,20 @@ static struct severity { /* When MCIP is not set something is very confused */ MCESEV( PANIC, "MCIP not set in MCA handler", - MCGMASK(MCG_STATUS_MCIP, 0) + EXCP, MCGMASK(MCG_STATUS_MCIP, 0) ), /* Neither return not error IP -- no chance to recover -> PANIC */ MCESEV( PANIC, "Neither restart nor error IP", - MCGMASK(MCG_STATUS_RIPV|MCG_STATUS_EIPV, 0) + EXCP, MCGMASK(MCG_STATUS_RIPV|MCG_STATUS_EIPV, 0) ), MCESEV( PANIC, "In kernel and no restart IP", - KERNEL, MCGMASK(MCG_STATUS_RIPV, 0) + EXCP, KERNEL, MCGMASK(MCG_STATUS_RIPV, 0) + ), + MCESEV( + DEFERRED, "Deferred error", + NOSER, MASK(MCI_STATUS_UC|MCI_STATUS_DEFERRED|MCI_STATUS_POISON, MCI_STATUS_DEFERRED) ), MCESEV( KEEP, "Corrected error", @@ -89,7 +97,7 @@ static struct severity { /* ignore OVER for UCNA */ MCESEV( - KEEP, "Uncorrected no action required", + UCNA, "Uncorrected no action required", SER, MASK(MCI_UC_SAR, MCI_STATUS_UC) ), MCESEV( @@ -178,8 +186,9 @@ static int error_context(struct mce *m) return ((m->cs & 3) == 3) ? IN_USER : IN_KERNEL; } -int mce_severity(struct mce *m, int tolerant, char **msg) +int mce_severity(struct mce *m, int tolerant, char **msg, bool is_excp) { + enum exception excp = (is_excp ? EXCP_CONTEXT : NO_EXCP); enum context ctx = error_context(m); struct severity *s; @@ -194,6 +203,8 @@ int mce_severity(struct mce *m, int tolerant, char **msg) continue; if (s->context && ctx != s->context) continue; + if (s->excp && excp != s->excp) + continue; if (msg) *msg = s->msg; s->covered = 1; diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index bd9ccda8087f..d2c611699cd9 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -292,10 +292,10 @@ static void print_mce(struct mce *m) #define PANIC_TIMEOUT 5 /* 5 seconds */ -static atomic_t mce_paniced; +static atomic_t mce_panicked; static int fake_panic; -static atomic_t mce_fake_paniced; +static atomic_t mce_fake_panicked; /* Panic in progress. Enable interrupts and wait for final IPI */ static void wait_for_panic(void) @@ -319,7 +319,7 @@ static void mce_panic(char *msg, struct mce *final, char *exp) /* * Make sure only one CPU runs in machine check panic */ - if (atomic_inc_return(&mce_paniced) > 1) + if (atomic_inc_return(&mce_panicked) > 1) wait_for_panic(); barrier(); @@ -327,7 +327,7 @@ static void mce_panic(char *msg, struct mce *final, char *exp) console_verbose(); } else { /* Don't log too much for fake panic */ - if (atomic_inc_return(&mce_fake_paniced) > 1) + if (atomic_inc_return(&mce_fake_panicked) > 1) return; } /* First print corrected ones that are still unlogged */ @@ -400,7 +400,7 @@ static u64 mce_rdmsrl(u32 msr) if (offset < 0) return 0; - return *(u64 *)((char *)&__get_cpu_var(injectm) + offset); + return *(u64 *)((char *)this_cpu_ptr(&injectm) + offset); } if (rdmsrl_safe(msr, &v)) { @@ -422,7 +422,7 @@ static void mce_wrmsrl(u32 msr, u64 v) int offset = msr_to_offset(msr); if (offset >= 0) - *(u64 *)((char *)&__get_cpu_var(injectm) + offset) = v; + *(u64 *)((char *)this_cpu_ptr(&injectm) + offset) = v; return; } wrmsrl(msr, v); @@ -478,7 +478,7 @@ static DEFINE_PER_CPU(struct mce_ring, mce_ring); /* Runs with CPU affinity in workqueue */ static int mce_ring_empty(void) { - struct mce_ring *r = &__get_cpu_var(mce_ring); + struct mce_ring *r = this_cpu_ptr(&mce_ring); return r->start == r->end; } @@ -490,7 +490,7 @@ static int mce_ring_get(unsigned long *pfn) *pfn = 0; get_cpu(); - r = &__get_cpu_var(mce_ring); + r = this_cpu_ptr(&mce_ring); if (r->start == r->end) goto out; *pfn = r->ring[r->start]; @@ -504,7 +504,7 @@ out: /* Always runs in MCE context with preempt off */ static int mce_ring_add(unsigned long pfn) { - struct mce_ring *r = &__get_cpu_var(mce_ring); + struct mce_ring *r = this_cpu_ptr(&mce_ring); unsigned next; next = (r->end + 1) % MCE_RING_SIZE; @@ -526,7 +526,7 @@ int mce_available(struct cpuinfo_x86 *c) static void mce_schedule_work(void) { if (!mce_ring_empty()) - schedule_work(&__get_cpu_var(mce_work)); + schedule_work(this_cpu_ptr(&mce_work)); } DEFINE_PER_CPU(struct irq_work, mce_irq_work); @@ -551,7 +551,7 @@ static void mce_report_event(struct pt_regs *regs) return; } - irq_work_queue(&__get_cpu_var(mce_irq_work)); + irq_work_queue(this_cpu_ptr(&mce_irq_work)); } /* @@ -575,6 +575,37 @@ static void mce_read_aux(struct mce *m, int i) } } +static bool memory_error(struct mce *m) +{ + struct cpuinfo_x86 *c = &boot_cpu_data; + + if (c->x86_vendor == X86_VENDOR_AMD) { + /* + * coming soon + */ + return false; + } else if (c->x86_vendor == X86_VENDOR_INTEL) { + /* + * Intel SDM Volume 3B - 15.9.2 Compound Error Codes + * + * Bit 7 of the MCACOD field of IA32_MCi_STATUS is used for + * indicating a memory error. Bit 8 is used for indicating a + * cache hierarchy error. The combination of bit 2 and bit 3 + * is used for indicating a `generic' cache hierarchy error + * But we can't just blindly check the above bits, because if + * bit 11 is set, then it is a bus/interconnect error - and + * either way the above bits just gives more detail on what + * bus/interconnect error happened. Note that bit 12 can be + * ignored, as it's the "filter" bit. + */ + return (m->status & 0xef80) == BIT(7) || + (m->status & 0xef00) == BIT(8) || + (m->status & 0xeffc) == 0xc; + } + + return false; +} + DEFINE_PER_CPU(unsigned, mce_poll_count); /* @@ -595,6 +626,7 @@ DEFINE_PER_CPU(unsigned, mce_poll_count); void machine_check_poll(enum mcp_flags flags, mce_banks_t *b) { struct mce m; + int severity; int i; this_cpu_inc(mce_poll_count); @@ -630,6 +662,20 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b) if (!(flags & MCP_TIMESTAMP)) m.tsc = 0; + + severity = mce_severity(&m, mca_cfg.tolerant, NULL, false); + + /* + * In the cases where we don't have a valid address after all, + * do not add it into the ring buffer. + */ + if (severity == MCE_DEFERRED_SEVERITY && memory_error(&m)) { + if (m.status & MCI_STATUS_ADDRV) { + mce_ring_add(m.addr >> PAGE_SHIFT); + mce_schedule_work(); + } + } + /* * Don't get the IP here because it's unlikely to * have anything to do with the actual error location. @@ -668,7 +714,8 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, if (quirk_no_way_out) quirk_no_way_out(i, m, regs); } - if (mce_severity(m, mca_cfg.tolerant, msg) >= MCE_PANIC_SEVERITY) + if (mce_severity(m, mca_cfg.tolerant, msg, true) >= + MCE_PANIC_SEVERITY) ret = 1; } return ret; @@ -697,7 +744,7 @@ static int mce_timed_out(u64 *t) * might have been modified by someone else. */ rmb(); - if (atomic_read(&mce_paniced)) + if (atomic_read(&mce_panicked)) wait_for_panic(); if (!mca_cfg.monarch_timeout) goto out; @@ -754,7 +801,7 @@ static void mce_reign(void) for_each_possible_cpu(cpu) { int severity = mce_severity(&per_cpu(mces_seen, cpu), mca_cfg.tolerant, - &nmsg); + &nmsg, true); if (severity > global_worst) { msg = nmsg; global_worst = severity; @@ -1045,7 +1092,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) mce_gather_info(&m, regs); - final = &__get_cpu_var(mces_seen); + final = this_cpu_ptr(&mces_seen); *final = m; memset(valid_banks, 0, sizeof(valid_banks)); @@ -1095,13 +1142,14 @@ void do_machine_check(struct pt_regs *regs, long error_code) */ add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); - severity = mce_severity(&m, cfg->tolerant, NULL); + severity = mce_severity(&m, cfg->tolerant, NULL, true); /* - * When machine check was for corrected handler don't touch, - * unless we're panicing. + * When machine check was for corrected/deferred handler don't + * touch, unless we're panicing. */ - if (severity == MCE_KEEP_SEVERITY && !no_way_out) + if ((severity == MCE_KEEP_SEVERITY || + severity == MCE_UCNA_SEVERITY) && !no_way_out) continue; __set_bit(i, toclear); if (severity == MCE_NO_SEVERITY) { @@ -1278,22 +1326,22 @@ static unsigned long (*mce_adjust_timer)(unsigned long interval) = static int cmc_error_seen(void) { - unsigned long *v = &__get_cpu_var(mce_polled_error); + unsigned long *v = this_cpu_ptr(&mce_polled_error); return test_and_clear_bit(0, v); } static void mce_timer_fn(unsigned long data) { - struct timer_list *t = &__get_cpu_var(mce_timer); + struct timer_list *t = this_cpu_ptr(&mce_timer); unsigned long iv; int notify; WARN_ON(smp_processor_id() != data); - if (mce_available(__this_cpu_ptr(&cpu_info))) { + if (mce_available(this_cpu_ptr(&cpu_info))) { machine_check_poll(MCP_TIMESTAMP, - &__get_cpu_var(mce_poll_banks)); + this_cpu_ptr(&mce_poll_banks)); mce_intel_cmci_poll(); } @@ -1323,7 +1371,7 @@ static void mce_timer_fn(unsigned long data) */ void mce_timer_kick(unsigned long interval) { - struct timer_list *t = &__get_cpu_var(mce_timer); + struct timer_list *t = this_cpu_ptr(&mce_timer); unsigned long when = jiffies + interval; unsigned long iv = __this_cpu_read(mce_next_interval); @@ -1659,7 +1707,7 @@ static void mce_start_timer(unsigned int cpu, struct timer_list *t) static void __mcheck_cpu_init_timer(void) { - struct timer_list *t = &__get_cpu_var(mce_timer); + struct timer_list *t = this_cpu_ptr(&mce_timer); unsigned int cpu = smp_processor_id(); setup_timer(t, mce_timer_fn, cpu); @@ -1702,8 +1750,8 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c) __mcheck_cpu_init_generic(); __mcheck_cpu_init_vendor(c); __mcheck_cpu_init_timer(); - INIT_WORK(&__get_cpu_var(mce_work), mce_process_work); - init_irq_work(&__get_cpu_var(mce_irq_work), &mce_irq_work_cb); + INIT_WORK(this_cpu_ptr(&mce_work), mce_process_work); + init_irq_work(this_cpu_ptr(&mce_irq_work), &mce_irq_work_cb); } /* @@ -1955,7 +2003,7 @@ static struct miscdevice mce_chrdev_device = { static void __mce_disable_bank(void *arg) { int bank = *((int *)arg); - __clear_bit(bank, __get_cpu_var(mce_poll_banks)); + __clear_bit(bank, this_cpu_ptr(mce_poll_banks)); cmci_disable_bank(bank); } @@ -2065,7 +2113,7 @@ static void mce_syscore_shutdown(void) static void mce_syscore_resume(void) { __mcheck_cpu_init_generic(); - __mcheck_cpu_init_vendor(__this_cpu_ptr(&cpu_info)); + __mcheck_cpu_init_vendor(raw_cpu_ptr(&cpu_info)); } static struct syscore_ops mce_syscore_ops = { @@ -2080,7 +2128,7 @@ static struct syscore_ops mce_syscore_ops = { static void mce_cpu_restart(void *data) { - if (!mce_available(__this_cpu_ptr(&cpu_info))) + if (!mce_available(raw_cpu_ptr(&cpu_info))) return; __mcheck_cpu_init_generic(); __mcheck_cpu_init_timer(); @@ -2096,14 +2144,14 @@ static void mce_restart(void) /* Toggle features for corrected errors */ static void mce_disable_cmci(void *data) { - if (!mce_available(__this_cpu_ptr(&cpu_info))) + if (!mce_available(raw_cpu_ptr(&cpu_info))) return; cmci_clear(); } static void mce_enable_ce(void *all) { - if (!mce_available(__this_cpu_ptr(&cpu_info))) + if (!mce_available(raw_cpu_ptr(&cpu_info))) return; cmci_reenable(); cmci_recheck(); @@ -2336,7 +2384,7 @@ static void mce_disable_cpu(void *h) unsigned long action = *(unsigned long *)h; int i; - if (!mce_available(__this_cpu_ptr(&cpu_info))) + if (!mce_available(raw_cpu_ptr(&cpu_info))) return; if (!(action & CPU_TASKS_FROZEN)) @@ -2354,7 +2402,7 @@ static void mce_reenable_cpu(void *h) unsigned long action = *(unsigned long *)h; int i; - if (!mce_available(__this_cpu_ptr(&cpu_info))) + if (!mce_available(raw_cpu_ptr(&cpu_info))) return; if (!(action & CPU_TASKS_FROZEN)) @@ -2520,7 +2568,7 @@ struct dentry *mce_get_debugfs_dir(void) static void mce_reset(void) { cpu_missing = 0; - atomic_set(&mce_fake_paniced, 0); + atomic_set(&mce_fake_panicked, 0); atomic_set(&mce_executing, 0); atomic_set(&mce_callin, 0); atomic_set(&global_nwo, 0); diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 1e49f8f41276..f1c3769bbd64 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -212,12 +212,12 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) unsigned int cpu = smp_processor_id(); u32 low = 0, high = 0, address = 0; unsigned int bank, block; - int offset = -1; + int offset = -1, new; for (bank = 0; bank < mca_cfg.banks; ++bank) { for (block = 0; block < NR_BLOCKS; ++block) { if (block == 0) - address = MSR_IA32_MC0_MISC + bank * 4; + address = MSR_IA32_MCx_MISC(bank); else if (block == 1) { address = (low & MASK_BLKPTR_LO) >> 21; if (!address) @@ -247,13 +247,18 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) b.address = address; b.interrupt_capable = lvt_interrupt_supported(bank, high); - if (b.interrupt_capable) { - int new = (high & MASK_LVTOFF_HI) >> 20; - offset = setup_APIC_mce(offset, new); - } + if (!b.interrupt_capable) + goto init; + + new = (high & MASK_LVTOFF_HI) >> 20; + offset = setup_APIC_mce(offset, new); + + if ((offset == new) && + (mce_threshold_vector != amd_threshold_interrupt)) + mce_threshold_vector = amd_threshold_interrupt; +init: mce_threshold_block_init(&b, offset); - mce_threshold_vector = amd_threshold_interrupt; } } } @@ -270,18 +275,17 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) static void amd_threshold_interrupt(void) { u32 low = 0, high = 0, address = 0; + int cpu = smp_processor_id(); unsigned int bank, block; struct mce m; - mce_setup(&m); - /* assume first bank caused it */ for (bank = 0; bank < mca_cfg.banks; ++bank) { - if (!(per_cpu(bank_map, m.cpu) & (1 << bank))) + if (!(per_cpu(bank_map, cpu) & (1 << bank))) continue; for (block = 0; block < NR_BLOCKS; ++block) { if (block == 0) { - address = MSR_IA32_MC0_MISC + bank * 4; + address = MSR_IA32_MCx_MISC(bank); } else if (block == 1) { address = (low & MASK_BLKPTR_LO) >> 21; if (!address) @@ -309,21 +313,20 @@ static void amd_threshold_interrupt(void) * Log the machine check that caused the threshold * event. */ - machine_check_poll(MCP_TIMESTAMP, - &__get_cpu_var(mce_poll_banks)); - - if (high & MASK_OVERFLOW_HI) { - rdmsrl(address, m.misc); - rdmsrl(MSR_IA32_MC0_STATUS + bank * 4, - m.status); - m.bank = K8_MCE_THRESHOLD_BASE - + bank * NR_BLOCKS - + block; - mce_log(&m); - return; - } + if (high & MASK_OVERFLOW_HI) + goto log; } } + return; + +log: + mce_setup(&m); + rdmsrl(MSR_IA32_MCx_STATUS(bank), m.status); + m.misc = ((u64)high << 32) | low; + m.bank = bank; + mce_log(&m); + + wrmsrl(MSR_IA32_MCx_STATUS(bank), 0); } /* @@ -617,8 +620,7 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank) } } - err = allocate_threshold_blocks(cpu, bank, 0, - MSR_IA32_MC0_MISC + bank * 4); + err = allocate_threshold_blocks(cpu, bank, 0, MSR_IA32_MCx_MISC(bank)); if (!err) goto out; diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c index 3bdb95ae8c43..b3c97bafc123 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c @@ -86,7 +86,7 @@ void mce_intel_cmci_poll(void) { if (__this_cpu_read(cmci_storm_state) == CMCI_STORM_NONE) return; - machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned)); + machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned)); } void mce_intel_hcpu_update(unsigned long cpu) @@ -145,7 +145,7 @@ static void cmci_storm_disable_banks(void) u64 val; raw_spin_lock_irqsave(&cmci_discover_lock, flags); - owned = __get_cpu_var(mce_banks_owned); + owned = this_cpu_ptr(mce_banks_owned); for_each_set_bit(bank, owned, MAX_NR_BANKS) { rdmsrl(MSR_IA32_MCx_CTL2(bank), val); val &= ~MCI_CTL2_CMCI_EN; @@ -195,7 +195,7 @@ static void intel_threshold_interrupt(void) { if (cmci_storm_detect()) return; - machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned)); + machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned)); mce_notify_irq(); } @@ -206,7 +206,7 @@ static void intel_threshold_interrupt(void) */ static void cmci_discover(int banks) { - unsigned long *owned = (void *)&__get_cpu_var(mce_banks_owned); + unsigned long *owned = (void *)this_cpu_ptr(&mce_banks_owned); unsigned long flags; int i; int bios_wrong_thresh = 0; @@ -228,7 +228,7 @@ static void cmci_discover(int banks) /* Already owned by someone else? */ if (val & MCI_CTL2_CMCI_EN) { clear_bit(i, owned); - __clear_bit(i, __get_cpu_var(mce_poll_banks)); + __clear_bit(i, this_cpu_ptr(mce_poll_banks)); continue; } @@ -252,7 +252,7 @@ static void cmci_discover(int banks) /* Did the enable bit stick? -- the bank supports CMCI */ if (val & MCI_CTL2_CMCI_EN) { set_bit(i, owned); - __clear_bit(i, __get_cpu_var(mce_poll_banks)); + __clear_bit(i, this_cpu_ptr(mce_poll_banks)); /* * We are able to set thresholds for some banks that * had a threshold of 0. This means the BIOS has not @@ -263,7 +263,7 @@ static void cmci_discover(int banks) (val & MCI_CTL2_CMCI_THRESHOLD_MASK)) bios_wrong_thresh = 1; } else { - WARN_ON(!test_bit(i, __get_cpu_var(mce_poll_banks))); + WARN_ON(!test_bit(i, this_cpu_ptr(mce_poll_banks))); } } raw_spin_unlock_irqrestore(&cmci_discover_lock, flags); @@ -284,10 +284,10 @@ void cmci_recheck(void) unsigned long flags; int banks; - if (!mce_available(__this_cpu_ptr(&cpu_info)) || !cmci_supported(&banks)) + if (!mce_available(raw_cpu_ptr(&cpu_info)) || !cmci_supported(&banks)) return; local_irq_save(flags); - machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned)); + machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned)); local_irq_restore(flags); } @@ -296,12 +296,12 @@ static void __cmci_disable_bank(int bank) { u64 val; - if (!test_bit(bank, __get_cpu_var(mce_banks_owned))) + if (!test_bit(bank, this_cpu_ptr(mce_banks_owned))) return; rdmsrl(MSR_IA32_MCx_CTL2(bank), val); val &= ~MCI_CTL2_CMCI_EN; wrmsrl(MSR_IA32_MCx_CTL2(bank), val); - __clear_bit(bank, __get_cpu_var(mce_banks_owned)); + __clear_bit(bank, this_cpu_ptr(mce_banks_owned)); } /* diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index 36a1bb6d1ee0..1af51b1586d7 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -498,8 +498,8 @@ void intel_init_thermal(struct cpuinfo_x86 *c) if ((l & MSR_IA32_MISC_ENABLE_TM1) && (h & APIC_DM_SMI)) { - printk(KERN_DEBUG - "CPU%d: Thermal monitoring handled by SMI\n", cpu); + if (system_state == SYSTEM_BOOTING) + printk(KERN_DEBUG "CPU%d: Thermal monitoring handled by SMI\n", cpu); return; } diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 8fffd845e22b..bfbbe6195e2d 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -376,7 +376,7 @@ static enum ucode_state __load_microcode_amd(u8 family, const u8 *data, return UCODE_OK; } -enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size) +enum ucode_state load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size) { enum ucode_state ret; @@ -390,8 +390,8 @@ enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size) #if defined(CONFIG_MICROCODE_AMD_EARLY) && defined(CONFIG_X86_32) /* save BSP's matching patch for early load */ - if (cpu_data(smp_processor_id()).cpu_index == boot_cpu_data.cpu_index) { - struct ucode_patch *p = find_patch(smp_processor_id()); + if (cpu_data(cpu).cpu_index == boot_cpu_data.cpu_index) { + struct ucode_patch *p = find_patch(cpu); if (p) { memset(amd_ucode_patch, 0, PATCH_MAX_SIZE); memcpy(amd_ucode_patch, p->data, min_t(u32, ksize(p->data), @@ -444,7 +444,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device, goto fw_release; } - ret = load_microcode_amd(c->x86, fw->data, fw->size); + ret = load_microcode_amd(cpu, c->x86, fw->data, fw->size); fw_release: release_firmware(fw); diff --git a/arch/x86/kernel/cpu/microcode/amd_early.c b/arch/x86/kernel/cpu/microcode/amd_early.c index 617a9e284245..737737edbd1e 100644 --- a/arch/x86/kernel/cpu/microcode/amd_early.c +++ b/arch/x86/kernel/cpu/microcode/amd_early.c @@ -27,7 +27,7 @@ static u32 ucode_new_rev; u8 amd_ucode_patch[PATCH_MAX_SIZE]; static u16 this_equiv_id; -struct cpio_data ucode_cpio; +static struct cpio_data ucode_cpio; /* * Microcode patch container file is prepended to the initrd in cpio format. @@ -108,12 +108,13 @@ static size_t compute_container_size(u8 *data, u32 total_size) * load_microcode_amd() to save equivalent cpu table and microcode patches in * kernel heap memory. */ -static void apply_ucode_in_initrd(void *ucode, size_t size) +static void apply_ucode_in_initrd(void *ucode, size_t size, bool save_patch) { struct equiv_cpu_entry *eq; size_t *cont_sz; u32 *header; u8 *data, **cont; + u8 (*patch)[PATCH_MAX_SIZE]; u16 eq_id = 0; int offset, left; u32 rev, eax, ebx, ecx, edx; @@ -123,10 +124,12 @@ static void apply_ucode_in_initrd(void *ucode, size_t size) new_rev = (u32 *)__pa_nodebug(&ucode_new_rev); cont_sz = (size_t *)__pa_nodebug(&container_size); cont = (u8 **)__pa_nodebug(&container); + patch = (u8 (*)[PATCH_MAX_SIZE])__pa_nodebug(&amd_ucode_patch); #else new_rev = &ucode_new_rev; cont_sz = &container_size; cont = &container; + patch = &amd_ucode_patch; #endif data = ucode; @@ -213,9 +216,9 @@ static void apply_ucode_in_initrd(void *ucode, size_t size) rev = mc->hdr.patch_id; *new_rev = rev; - /* save ucode patch */ - memcpy(amd_ucode_patch, mc, - min_t(u32, header[1], PATCH_MAX_SIZE)); + if (save_patch) + memcpy(patch, mc, + min_t(u32, header[1], PATCH_MAX_SIZE)); } } @@ -246,7 +249,7 @@ void __init load_ucode_amd_bsp(void) *data = cp.data; *size = cp.size; - apply_ucode_in_initrd(cp.data, cp.size); + apply_ucode_in_initrd(cp.data, cp.size, true); } #ifdef CONFIG_X86_32 @@ -263,7 +266,7 @@ void load_ucode_amd_ap(void) size_t *usize; void **ucode; - mc = (struct microcode_amd *)__pa(amd_ucode_patch); + mc = (struct microcode_amd *)__pa_nodebug(amd_ucode_patch); if (mc->hdr.patch_id && mc->hdr.processor_rev_id) { __apply_microcode_amd(mc); return; @@ -275,7 +278,7 @@ void load_ucode_amd_ap(void) if (!*ucode || !*usize) return; - apply_ucode_in_initrd(*ucode, *usize); + apply_ucode_in_initrd(*ucode, *usize, false); } static void __init collect_cpu_sig_on_bsp(void *arg) @@ -339,7 +342,7 @@ void load_ucode_amd_ap(void) * 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_ucode_in_initrd(ucode_cpio.data, ucode_cpio.size, false); } } #endif @@ -347,7 +350,9 @@ void load_ucode_amd_ap(void) int __init save_microcode_in_initrd_amd(void) { unsigned long cont; + int retval = 0; enum ucode_state ret; + u8 *cont_va; u32 eax; if (!container) @@ -355,13 +360,15 @@ int __init save_microcode_in_initrd_amd(void) #ifdef CONFIG_X86_32 get_bsp_sig(); - cont = (unsigned long)container; + cont = (unsigned long)container; + cont_va = __va(container); #else /* * We need the physical address of the container for both bitness since * boot_params.hdr.ramdisk_image is a physical address. */ - cont = __pa(container); + cont = __pa(container); + cont_va = container; #endif /* @@ -372,6 +379,8 @@ int __init save_microcode_in_initrd_amd(void) if (relocated_ramdisk) container = (u8 *)(__va(relocated_ramdisk) + (cont - boot_params.hdr.ramdisk_image)); + else + container = cont_va; if (ucode_new_rev) pr_info("microcode: updated early to new patch_level=0x%08x\n", @@ -380,9 +389,9 @@ int __init save_microcode_in_initrd_amd(void) eax = cpuid_eax(0x00000001); eax = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff); - ret = load_microcode_amd(eax, container, container_size); + ret = load_microcode_amd(smp_processor_id(), eax, container, container_size); if (ret != UCODE_OK) - return -EINVAL; + retval = -EINVAL; /* * This will be freed any msec now, stash patches for the current @@ -391,5 +400,23 @@ int __init save_microcode_in_initrd_amd(void) container = NULL; container_size = 0; - return 0; + return retval; +} + +void reload_ucode_amd(void) +{ + struct microcode_amd *mc; + u32 rev, eax; + + rdmsr(MSR_AMD64_PATCH_LEVEL, rev, eax); + + mc = (struct microcode_amd *)amd_ucode_patch; + + if (mc && rev < mc->hdr.patch_id) { + if (!__apply_microcode_amd(mc)) { + ucode_new_rev = mc->hdr.patch_id; + pr_info("microcode: reload patch_level=0x%08x\n", + ucode_new_rev); + } + } } diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index dd9d6190b08d..15c29096136b 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -465,6 +465,8 @@ static void mc_bp_resume(void) if (uci->valid && uci->mc) microcode_ops->apply_microcode(cpu); + else if (!uci->mc) + reload_early_microcode(); } static struct syscore_ops mc_syscore_ops = { @@ -549,7 +551,7 @@ static int __init microcode_init(void) struct cpuinfo_x86 *c = &cpu_data(0); int error; - if (dis_ucode_ldr) + if (paravirt_enabled() || dis_ucode_ldr) return 0; if (c->x86_vendor == X86_VENDOR_INTEL) diff --git a/arch/x86/kernel/cpu/microcode/core_early.c b/arch/x86/kernel/cpu/microcode/core_early.c index 5f28a64e71ea..d45df4bd16ab 100644 --- a/arch/x86/kernel/cpu/microcode/core_early.c +++ b/arch/x86/kernel/cpu/microcode/core_early.c @@ -124,7 +124,7 @@ void __init load_ucode_bsp(void) static bool check_loader_disabled_ap(void) { #ifdef CONFIG_X86_32 - return __pa_nodebug(dis_ucode_ldr); + return *((bool *)__pa_nodebug(&dis_ucode_ldr)); #else return dis_ucode_ldr; #endif @@ -176,3 +176,24 @@ int __init save_microcode_in_initrd(void) return 0; } + +void reload_early_microcode(void) +{ + int vendor, x86; + + vendor = x86_vendor(); + x86 = x86_family(); + + switch (vendor) { + case X86_VENDOR_INTEL: + if (x86 >= 6) + reload_ucode_intel(); + break; + case X86_VENDOR_AMD: + if (x86 >= 0x10) + reload_ucode_amd(); + break; + default: + break; + } +} diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index a276fa75d9b5..c6826d1e8082 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -127,7 +127,7 @@ static int get_matching_mc(struct microcode_intel *mc_intel, int cpu) return get_matching_microcode(csig, cpf, mc_intel, crev); } -int apply_microcode(int cpu) +static int apply_microcode_intel(int cpu) { struct microcode_intel *mc_intel; struct ucode_cpu_info *uci; @@ -314,7 +314,7 @@ static struct microcode_ops microcode_intel_ops = { .request_microcode_user = request_microcode_user, .request_microcode_fw = request_microcode_fw, .collect_cpu_info = collect_cpu_info, - .apply_microcode = apply_microcode, + .apply_microcode = apply_microcode_intel, .microcode_fini_cpu = microcode_fini_cpu, }; diff --git a/arch/x86/kernel/cpu/microcode/intel_early.c b/arch/x86/kernel/cpu/microcode/intel_early.c index 18f739129e72..ec9df6f9cd47 100644 --- a/arch/x86/kernel/cpu/microcode/intel_early.c +++ b/arch/x86/kernel/cpu/microcode/intel_early.c @@ -28,8 +28,8 @@ #include <asm/tlbflush.h> #include <asm/setup.h> -unsigned long mc_saved_in_initrd[MAX_UCODE_COUNT]; -struct mc_saved_data { +static unsigned long mc_saved_in_initrd[MAX_UCODE_COUNT]; +static struct mc_saved_data { unsigned int mc_saved_count; struct microcode_intel **mc_saved; } mc_saved_data; @@ -415,7 +415,7 @@ static void __ref show_saved_mc(void) struct ucode_cpu_info uci; if (mc_saved_data.mc_saved_count == 0) { - pr_debug("no micorcode data saved.\n"); + pr_debug("no microcode data saved.\n"); return; } pr_debug("Total microcode saved: %d\n", mc_saved_data.mc_saved_count); @@ -506,7 +506,7 @@ int save_mc_for_early(u8 *mc) if (mc_saved && mc_saved_count) memcpy(mc_saved_tmp, mc_saved, - mc_saved_count * sizeof(struct mirocode_intel *)); + mc_saved_count * sizeof(struct microcode_intel *)); /* * Save the microcode patch mc in mc_save_tmp structure if it's a newer * version. @@ -526,7 +526,7 @@ int save_mc_for_early(u8 *mc) show_saved_mc(); /* - * Free old saved microcod data. + * Free old saved microcode data. */ if (mc_saved) { for (i = 0; i < mc_saved_count_init; i++) @@ -650,8 +650,7 @@ static inline void print_ucode(struct ucode_cpu_info *uci) } #endif -static int apply_microcode_early(struct mc_saved_data *mc_saved_data, - struct ucode_cpu_info *uci) +static int apply_microcode_early(struct ucode_cpu_info *uci, bool early) { struct microcode_intel *mc_intel; unsigned int val[2]; @@ -680,7 +679,10 @@ static int apply_microcode_early(struct mc_saved_data *mc_saved_data, #endif uci->cpu_sig.rev = val[1]; - print_ucode(uci); + if (early) + print_ucode(uci); + else + print_ucode_info(uci, mc_intel->hdr.date); return 0; } @@ -715,12 +717,17 @@ _load_ucode_intel_bsp(struct mc_saved_data *mc_saved_data, unsigned long initrd_end_early, struct ucode_cpu_info *uci) { + enum ucode_state ret; + collect_cpu_info_early(uci); scan_microcode(initrd_start_early, initrd_end_early, mc_saved_data, mc_saved_in_initrd, uci); - load_microcode(mc_saved_data, mc_saved_in_initrd, - initrd_start_early, uci); - apply_microcode_early(mc_saved_data, uci); + + ret = load_microcode(mc_saved_data, mc_saved_in_initrd, + initrd_start_early, uci); + + if (ret == UCODE_OK) + apply_microcode_early(uci, true); } void __init @@ -749,7 +756,8 @@ load_ucode_intel_bsp(void) initrd_end_early = initrd_start_early + ramdisk_size; _load_ucode_intel_bsp(&mc_saved_data, mc_saved_in_initrd, - initrd_start_early, initrd_end_early, &uci); + initrd_start_early, initrd_end_early, + &uci); #endif } @@ -783,5 +791,23 @@ void load_ucode_intel_ap(void) collect_cpu_info_early(&uci); load_microcode(mc_saved_data_p, mc_saved_in_initrd_p, initrd_start_addr, &uci); - apply_microcode_early(mc_saved_data_p, &uci); + apply_microcode_early(&uci, true); +} + +void reload_ucode_intel(void) +{ + struct ucode_cpu_info uci; + enum ucode_state ret; + + if (!mc_saved_data.mc_saved_count) + return; + + collect_cpu_info_early(&uci); + + ret = generic_load_microcode_early(mc_saved_data.mc_saved, + mc_saved_data.mc_saved_count, &uci); + if (ret != UCODE_OK) + return; + + apply_microcode_early(&uci, false); } diff --git a/arch/x86/kernel/cpu/mkcapflags.sh b/arch/x86/kernel/cpu/mkcapflags.sh index e2b22df964cd..36d99a337b49 100644 --- a/arch/x86/kernel/cpu/mkcapflags.sh +++ b/arch/x86/kernel/cpu/mkcapflags.sh @@ -28,7 +28,7 @@ function dump_array() # If the /* comment */ starts with a quote string, grab that. VALUE="$(echo "$i" | sed -n 's@.*/\* *\("[^"]*"\).*\*/@\1@p')" [ -z "$VALUE" ] && VALUE="\"$NAME\"" - [ "$VALUE" == '""' ] && continue + [ "$VALUE" = '""' ] && continue # Name is uppercase, VALUE is all lowercase VALUE="$(echo "$VALUE" | tr A-Z a-z)" diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index f961de9964c7..ea5f363a1948 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -707,7 +707,7 @@ void __init mtrr_bp_init(void) } else { switch (boot_cpu_data.x86_vendor) { case X86_VENDOR_AMD: - if (cpu_has_k6_mtrr) { + if (cpu_feature_enabled(X86_FEATURE_K6_MTRR)) { /* Pre-Athlon (K6) AMD CPU MTRRs */ mtrr_if = mtrr_ops[X86_VENDOR_AMD]; size_or_mask = SIZE_OR_MASK_BITS(32); @@ -715,14 +715,14 @@ void __init mtrr_bp_init(void) } break; case X86_VENDOR_CENTAUR: - if (cpu_has_centaur_mcr) { + if (cpu_feature_enabled(X86_FEATURE_CENTAUR_MCR)) { mtrr_if = mtrr_ops[X86_VENDOR_CENTAUR]; size_or_mask = SIZE_OR_MASK_BITS(32); size_and_mask = 0; } break; case X86_VENDOR_CYRIX: - if (cpu_has_cyrix_arr) { + if (cpu_feature_enabled(X86_FEATURE_CYRIX_ARR)) { mtrr_if = mtrr_ops[X86_VENDOR_CYRIX]; size_or_mask = SIZE_OR_MASK_BITS(32); size_and_mask = 0; diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 2879ecdaac43..143e5f5dc855 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -243,7 +243,9 @@ static bool check_hw_exists(void) msr_fail: printk(KERN_CONT "Broken PMU hardware detected, using software events only.\n"); - printk(KERN_ERR "Failed to access perfctr msr (MSR %x is %Lx)\n", reg, val_new); + printk("%sFailed to access perfctr msr (MSR %x is %Lx)\n", + boot_cpu_has(X86_FEATURE_HYPERVISOR) ? KERN_INFO : KERN_ERR, + reg, val_new); return false; } @@ -387,7 +389,7 @@ int x86_pmu_hw_config(struct perf_event *event) precise++; /* Support for IP fixup */ - if (x86_pmu.lbr_nr) + if (x86_pmu.lbr_nr || x86_pmu.intel_cap.pebs_format >= 2) precise++; } @@ -487,7 +489,7 @@ static int __x86_pmu_event_init(struct perf_event *event) void x86_pmu_disable_all(void) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int idx; for (idx = 0; idx < x86_pmu.num_counters; idx++) { @@ -505,7 +507,7 @@ void x86_pmu_disable_all(void) static void x86_pmu_disable(struct pmu *pmu) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); if (!x86_pmu_initialized()) return; @@ -522,7 +524,7 @@ static void x86_pmu_disable(struct pmu *pmu) void x86_pmu_enable_all(int added) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int idx; for (idx = 0; idx < x86_pmu.num_counters; idx++) { @@ -869,7 +871,7 @@ static void x86_pmu_start(struct perf_event *event, int flags); static void x86_pmu_enable(struct pmu *pmu) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct perf_event *event; struct hw_perf_event *hwc; int i, added = cpuc->n_added; @@ -1020,7 +1022,7 @@ void x86_pmu_enable_event(struct perf_event *event) */ static int x86_pmu_add(struct perf_event *event, int flags) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc; int assign[X86_PMC_IDX_MAX]; int n, n0, ret; @@ -1071,7 +1073,7 @@ out: static void x86_pmu_start(struct perf_event *event, int flags) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int idx = event->hw.idx; if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED))) @@ -1150,7 +1152,7 @@ void perf_event_print_debug(void) void x86_pmu_stop(struct perf_event *event, int flags) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; if (__test_and_clear_bit(hwc->idx, cpuc->active_mask)) { @@ -1172,7 +1174,7 @@ void x86_pmu_stop(struct perf_event *event, int flags) static void x86_pmu_del(struct perf_event *event, int flags) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int i; /* @@ -1227,7 +1229,7 @@ int x86_pmu_handle_irq(struct pt_regs *regs) int idx, handled = 0; u64 val; - cpuc = &__get_cpu_var(cpu_hw_events); + cpuc = this_cpu_ptr(&cpu_hw_events); /* * Some chipsets need to unmask the LVTPC in a particular spot @@ -1636,7 +1638,7 @@ static void x86_pmu_cancel_txn(struct pmu *pmu) */ static int x86_pmu_commit_txn(struct pmu *pmu) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int assign[X86_PMC_IDX_MAX]; int n, ret; @@ -1995,7 +1997,7 @@ static unsigned long get_segment_base(unsigned int segment) if (idx > GDT_ENTRIES) return 0; - desc = __this_cpu_ptr(&gdt_page.gdt[0]); + desc = raw_cpu_ptr(gdt_page.gdt); } return get_desc_base(desc + idx); diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index 8ade93111e03..4e6cdb0ddc70 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -67,8 +67,10 @@ struct event_constraint { */ #define PERF_X86_EVENT_PEBS_LDLAT 0x1 /* ld+ldlat data address sampling */ #define PERF_X86_EVENT_PEBS_ST 0x2 /* st data address sampling */ -#define PERF_X86_EVENT_PEBS_ST_HSW 0x4 /* haswell style st data sampling */ +#define PERF_X86_EVENT_PEBS_ST_HSW 0x4 /* haswell style datala, store */ #define PERF_X86_EVENT_COMMITTED 0x8 /* event passed commit_txn */ +#define PERF_X86_EVENT_PEBS_LD_HSW 0x10 /* haswell style datala, load */ +#define PERF_X86_EVENT_PEBS_NA_HSW 0x20 /* haswell style datala, unknown */ struct amd_nb { int nb_id; /* NorthBridge id */ @@ -251,19 +253,57 @@ struct cpu_hw_events { #define INTEL_UEVENT_CONSTRAINT(c, n) \ EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK) +/* Like UEVENT_CONSTRAINT, but match flags too */ +#define INTEL_FLAGS_UEVENT_CONSTRAINT(c, n) \ + EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS) + #define INTEL_PLD_CONSTRAINT(c, n) \ - __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \ + __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LDLAT) #define INTEL_PST_CONSTRAINT(c, n) \ - __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \ + __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST) -/* DataLA version of store sampling without extra enable bit. */ -#define INTEL_PST_HSW_CONSTRAINT(c, n) \ - __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \ +/* Event constraint, but match on all event flags too. */ +#define INTEL_FLAGS_EVENT_CONSTRAINT(c, n) \ + EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS) + +/* Check only flags, but allow all event/umask */ +#define INTEL_ALL_EVENT_CONSTRAINT(code, n) \ + EVENT_CONSTRAINT(code, n, X86_ALL_EVENT_FLAGS) + +/* Check flags and event code, and set the HSW store flag */ +#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_ST(code, n) \ + __EVENT_CONSTRAINT(code, n, \ + ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST_HSW) +/* Check flags and event code, and set the HSW load flag */ +#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(code, n) \ + __EVENT_CONSTRAINT(code, n, \ + ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \ + HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW) + +/* Check flags and event code/umask, and set the HSW store flag */ +#define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(code, n) \ + __EVENT_CONSTRAINT(code, n, \ + INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \ + HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST_HSW) + +/* Check flags and event code/umask, and set the HSW load flag */ +#define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(code, n) \ + __EVENT_CONSTRAINT(code, n, \ + INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \ + HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW) + +/* Check flags and event code/umask, and set the HSW N/A flag */ +#define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(code, n) \ + __EVENT_CONSTRAINT(code, n, \ + INTEL_ARCH_EVENT_MASK|INTEL_ARCH_EVENT_MASK, \ + HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_NA_HSW) + + /* * We define the end marker as having a weight of -1 * to enable blacklisting of events using a counter bitmask diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index beeb7cc07044..28926311aac1 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -699,7 +699,7 @@ __init int amd_pmu_init(void) void amd_pmu_enable_virt(void) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); cpuc->perf_ctr_virt_mask = 0; @@ -711,7 +711,7 @@ EXPORT_SYMBOL_GPL(amd_pmu_enable_virt); void amd_pmu_disable_virt(void) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); /* * We only mask out the Host-only bit so that host-only counting works diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c index cbb1be3ed9e4..a61f5c6911da 100644 --- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c +++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c @@ -565,6 +565,21 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs) perf_ibs->offset_max, offset + 1); } while (offset < offset_max); + if (event->attr.sample_type & PERF_SAMPLE_RAW) { + /* + * Read IbsBrTarget and IbsOpData4 separately + * depending on their availability. + * Can't add to offset_max as they are staggered + */ + if (ibs_caps & IBS_CAPS_BRNTRGT) { + rdmsrl(MSR_AMD64_IBSBRTARGET, *buf++); + size++; + } + if (ibs_caps & IBS_CAPS_OPDATA4) { + rdmsrl(MSR_AMD64_IBSOPDATA4, *buf++); + size++; + } + } ibs_data.size = sizeof(u64) * size; regs = *iregs; diff --git a/arch/x86/kernel/cpu/perf_event_amd_iommu.c b/arch/x86/kernel/cpu/perf_event_amd_iommu.c index 639d1289b1ba..97242a9242bd 100644 --- a/arch/x86/kernel/cpu/perf_event_amd_iommu.c +++ b/arch/x86/kernel/cpu/perf_event_amd_iommu.c @@ -130,10 +130,7 @@ static ssize_t _iommu_cpumask_show(struct device *dev, struct device_attribute *attr, char *buf) { - int n = cpulist_scnprintf(buf, PAGE_SIZE - 2, &iommu_cpumask); - buf[n++] = '\n'; - buf[n] = '\0'; - return n; + return cpumap_print_to_pagebuf(true, buf, &iommu_cpumask); } static DEVICE_ATTR(cpumask, S_IRUGO, _iommu_cpumask_show, NULL); diff --git a/arch/x86/kernel/cpu/perf_event_amd_uncore.c b/arch/x86/kernel/cpu/perf_event_amd_uncore.c index 30790d798e6b..cc6cedb8f25d 100644 --- a/arch/x86/kernel/cpu/perf_event_amd_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_amd_uncore.c @@ -219,7 +219,6 @@ static ssize_t amd_uncore_attr_show_cpumask(struct device *dev, struct device_attribute *attr, char *buf) { - int n; cpumask_t *active_mask; struct pmu *pmu = dev_get_drvdata(dev); @@ -230,10 +229,7 @@ static ssize_t amd_uncore_attr_show_cpumask(struct device *dev, else return 0; - n = cpulist_scnprintf(buf, PAGE_SIZE - 2, active_mask); - buf[n++] = '\n'; - buf[n] = '\0'; - return n; + return cpumap_print_to_pagebuf(true, buf, active_mask); } static DEVICE_ATTR(cpumask, S_IRUGO, amd_uncore_attr_show_cpumask, NULL); diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 2502d0d9d246..944bf019b74f 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1045,7 +1045,7 @@ static inline bool intel_pmu_needs_lbr_smpl(struct perf_event *event) static void intel_pmu_disable_all(void) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0); @@ -1058,7 +1058,7 @@ static void intel_pmu_disable_all(void) static void intel_pmu_enable_all(int added) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); intel_pmu_pebs_enable_all(); intel_pmu_lbr_enable_all(); @@ -1092,7 +1092,7 @@ static void intel_pmu_enable_all(int added) */ static void intel_pmu_nhm_workaround(void) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); static const unsigned long nhm_magic[4] = { 0x4300B5, 0x4300D2, @@ -1191,7 +1191,7 @@ static inline bool event_is_checkpointed(struct perf_event *event) static void intel_pmu_disable_event(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); if (unlikely(hwc->idx == INTEL_PMC_IDX_FIXED_BTS)) { intel_pmu_disable_bts(); @@ -1255,7 +1255,7 @@ static void intel_pmu_enable_fixed(struct hw_perf_event *hwc) static void intel_pmu_enable_event(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); if (unlikely(hwc->idx == INTEL_PMC_IDX_FIXED_BTS)) { if (!__this_cpu_read(cpu_hw_events.enabled)) @@ -1349,7 +1349,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs) u64 status; int handled; - cpuc = &__get_cpu_var(cpu_hw_events); + cpuc = this_cpu_ptr(&cpu_hw_events); /* * No known reason to not always do late ACK, @@ -1781,7 +1781,7 @@ EXPORT_SYMBOL_GPL(perf_guest_get_msrs); static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct perf_guest_switch_msr *arr = cpuc->guest_switch_msrs; arr[0].msr = MSR_CORE_PERF_GLOBAL_CTRL; @@ -1802,7 +1802,7 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr) static struct perf_guest_switch_msr *core_guest_get_msrs(int *nr) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct perf_guest_switch_msr *arr = cpuc->guest_switch_msrs; int idx; @@ -1836,7 +1836,7 @@ static void core_pmu_enable_event(struct perf_event *event) static void core_pmu_enable_all(int added) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int idx; for (idx = 0; idx < x86_pmu.num_counters; idx++) { @@ -2367,15 +2367,15 @@ __init int intel_pmu_init(void) * Install the hw-cache-events table: */ switch (boot_cpu_data.x86_model) { - case 14: /* 65 nm core solo/duo, "Yonah" */ + case 14: /* 65nm Core "Yonah" */ pr_cont("Core events, "); break; - case 15: /* original 65 nm celeron/pentium/core2/xeon, "Merom"/"Conroe" */ + case 15: /* 65nm Core2 "Merom" */ x86_add_quirk(intel_clovertown_quirk); - case 22: /* single-core 65 nm celeron/core2solo "Merom-L"/"Conroe-L" */ - case 23: /* current 45 nm celeron/core2/xeon "Penryn"/"Wolfdale" */ - case 29: /* six-core 45 nm xeon "Dunnington" */ + case 22: /* 65nm Core2 "Merom-L" */ + case 23: /* 45nm Core2 "Penryn" */ + case 29: /* 45nm Core2 "Dunnington (MP) */ memcpy(hw_cache_event_ids, core2_hw_cache_event_ids, sizeof(hw_cache_event_ids)); @@ -2386,9 +2386,9 @@ __init int intel_pmu_init(void) pr_cont("Core2 events, "); break; - case 26: /* 45 nm nehalem, "Bloomfield" */ - case 30: /* 45 nm nehalem, "Lynnfield" */ - case 46: /* 45 nm nehalem-ex, "Beckton" */ + case 30: /* 45nm Nehalem */ + case 26: /* 45nm Nehalem-EP */ + case 46: /* 45nm Nehalem-EX */ memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids, sizeof(hw_cache_event_ids)); memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs, @@ -2415,11 +2415,11 @@ __init int intel_pmu_init(void) pr_cont("Nehalem events, "); break; - case 28: /* Atom */ - case 38: /* Lincroft */ - case 39: /* Penwell */ - case 53: /* Cloverview */ - case 54: /* Cedarview */ + case 28: /* 45nm Atom "Pineview" */ + case 38: /* 45nm Atom "Lincroft" */ + case 39: /* 32nm Atom "Penwell" */ + case 53: /* 32nm Atom "Cloverview" */ + case 54: /* 32nm Atom "Cedarview" */ memcpy(hw_cache_event_ids, atom_hw_cache_event_ids, sizeof(hw_cache_event_ids)); @@ -2430,8 +2430,8 @@ __init int intel_pmu_init(void) pr_cont("Atom events, "); break; - case 55: /* Atom 22nm "Silvermont" */ - case 77: /* Avoton "Silvermont" */ + case 55: /* 22nm Atom "Silvermont" */ + case 77: /* 22nm Atom "Silvermont Avoton/Rangely" */ memcpy(hw_cache_event_ids, slm_hw_cache_event_ids, sizeof(hw_cache_event_ids)); memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs, @@ -2446,9 +2446,9 @@ __init int intel_pmu_init(void) pr_cont("Silvermont events, "); break; - case 37: /* 32 nm nehalem, "Clarkdale" */ - case 44: /* 32 nm nehalem, "Gulftown" */ - case 47: /* 32 nm Xeon E7 */ + case 37: /* 32nm Westmere */ + case 44: /* 32nm Westmere-EP */ + case 47: /* 32nm Westmere-EX */ memcpy(hw_cache_event_ids, westmere_hw_cache_event_ids, sizeof(hw_cache_event_ids)); memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs, @@ -2474,8 +2474,8 @@ __init int intel_pmu_init(void) pr_cont("Westmere events, "); break; - case 42: /* SandyBridge */ - case 45: /* SandyBridge, "Romely-EP" */ + case 42: /* 32nm SandyBridge */ + case 45: /* 32nm SandyBridge-E/EN/EP */ x86_add_quirk(intel_sandybridge_quirk); memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids)); @@ -2506,8 +2506,9 @@ __init int intel_pmu_init(void) pr_cont("SandyBridge events, "); break; - case 58: /* IvyBridge */ - case 62: /* IvyBridge EP */ + + case 58: /* 22nm IvyBridge */ + case 62: /* 22nm IvyBridge-EP/EX */ memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids)); /* dTLB-load-misses on IVB is different than SNB */ @@ -2539,11 +2540,10 @@ __init int intel_pmu_init(void) break; - case 60: /* Haswell Client */ - case 70: - case 71: - case 63: - case 69: + case 60: /* 22nm Haswell Core */ + case 63: /* 22nm Haswell Server */ + case 69: /* 22nm Haswell ULT */ + case 70: /* 22nm Haswell + GT3e (Intel Iris Pro graphics) */ x86_pmu.late_ack = true; memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids)); memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); @@ -2552,7 +2552,7 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_hsw_event_constraints; x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints; - x86_pmu.extra_regs = intel_snb_extra_regs; + x86_pmu.extra_regs = intel_snbep_extra_regs; x86_pmu.pebs_aliases = intel_pebs_aliases_snb; /* all extra regs are per-cpu when HT is on */ x86_pmu.er_flags |= ERF_HAS_RSP_1; diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 696ade311ded..3c895d480cd7 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -108,14 +108,16 @@ static u64 precise_store_data(u64 status) return val; } -static u64 precise_store_data_hsw(struct perf_event *event, u64 status) +static u64 precise_datala_hsw(struct perf_event *event, u64 status) { union perf_mem_data_src dse; - u64 cfg = event->hw.config & INTEL_ARCH_EVENT_MASK; - dse.val = 0; - dse.mem_op = PERF_MEM_OP_STORE; - dse.mem_lvl = PERF_MEM_LVL_NA; + dse.val = PERF_MEM_NA; + + if (event->hw.flags & PERF_X86_EVENT_PEBS_ST_HSW) + dse.mem_op = PERF_MEM_OP_STORE; + else if (event->hw.flags & PERF_X86_EVENT_PEBS_LD_HSW) + dse.mem_op = PERF_MEM_OP_LOAD; /* * L1 info only valid for following events: @@ -125,15 +127,12 @@ static u64 precise_store_data_hsw(struct perf_event *event, u64 status) * MEM_UOPS_RETIRED.SPLIT_STORES * MEM_UOPS_RETIRED.ALL_STORES */ - if (cfg != 0x12d0 && cfg != 0x22d0 && cfg != 0x42d0 && cfg != 0x82d0) - return dse.mem_lvl; - - if (status & 1) - dse.mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_HIT; - else - dse.mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_MISS; - - /* Nothing else supported. Sorry. */ + if (event->hw.flags & PERF_X86_EVENT_PEBS_ST_HSW) { + if (status & 1) + dse.mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_HIT; + else + dse.mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_MISS; + } return dse.val; } @@ -475,7 +474,7 @@ void intel_pmu_enable_bts(u64 config) void intel_pmu_disable_bts(void) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); unsigned long debugctlmsr; if (!cpuc->ds) @@ -492,7 +491,7 @@ void intel_pmu_disable_bts(void) int intel_pmu_drain_bts_buffer(void) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct debug_store *ds = cpuc->ds; struct bts_record { u64 from; @@ -553,141 +552,99 @@ int intel_pmu_drain_bts_buffer(void) * PEBS */ struct event_constraint intel_core2_pebs_event_constraints[] = { - INTEL_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */ - INTEL_UEVENT_CONSTRAINT(0xfec1, 0x1), /* X87_OPS_RETIRED.ANY */ - INTEL_UEVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_RETIRED.MISPRED */ - INTEL_UEVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */ - INTEL_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */ + INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */ + INTEL_FLAGS_UEVENT_CONSTRAINT(0xfec1, 0x1), /* X87_OPS_RETIRED.ANY */ + INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_RETIRED.MISPRED */ + INTEL_FLAGS_UEVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */ + INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */ EVENT_CONSTRAINT_END }; struct event_constraint intel_atom_pebs_event_constraints[] = { - INTEL_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */ - INTEL_UEVENT_CONSTRAINT(0x00c5, 0x1), /* MISPREDICTED_BRANCH_RETIRED */ - INTEL_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */ + INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */ + INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c5, 0x1), /* MISPREDICTED_BRANCH_RETIRED */ + INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */ EVENT_CONSTRAINT_END }; struct event_constraint intel_slm_pebs_event_constraints[] = { - INTEL_UEVENT_CONSTRAINT(0x0103, 0x1), /* REHABQ.LD_BLOCK_ST_FORWARD_PS */ - INTEL_UEVENT_CONSTRAINT(0x0803, 0x1), /* REHABQ.LD_SPLITS_PS */ - INTEL_UEVENT_CONSTRAINT(0x0204, 0x1), /* MEM_UOPS_RETIRED.L2_HIT_LOADS_PS */ - INTEL_UEVENT_CONSTRAINT(0x0404, 0x1), /* MEM_UOPS_RETIRED.L2_MISS_LOADS_PS */ - INTEL_UEVENT_CONSTRAINT(0x0804, 0x1), /* MEM_UOPS_RETIRED.DTLB_MISS_LOADS_PS */ - INTEL_UEVENT_CONSTRAINT(0x2004, 0x1), /* MEM_UOPS_RETIRED.HITM_PS */ - INTEL_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY_PS */ - INTEL_UEVENT_CONSTRAINT(0x00c4, 0x1), /* BR_INST_RETIRED.ALL_BRANCHES_PS */ - INTEL_UEVENT_CONSTRAINT(0x7ec4, 0x1), /* BR_INST_RETIRED.JCC_PS */ - INTEL_UEVENT_CONSTRAINT(0xbfc4, 0x1), /* BR_INST_RETIRED.FAR_BRANCH_PS */ - INTEL_UEVENT_CONSTRAINT(0xebc4, 0x1), /* BR_INST_RETIRED.NON_RETURN_IND_PS */ - INTEL_UEVENT_CONSTRAINT(0xf7c4, 0x1), /* BR_INST_RETIRED.RETURN_PS */ - INTEL_UEVENT_CONSTRAINT(0xf9c4, 0x1), /* BR_INST_RETIRED.CALL_PS */ - INTEL_UEVENT_CONSTRAINT(0xfbc4, 0x1), /* BR_INST_RETIRED.IND_CALL_PS */ - INTEL_UEVENT_CONSTRAINT(0xfdc4, 0x1), /* BR_INST_RETIRED.REL_CALL_PS */ - INTEL_UEVENT_CONSTRAINT(0xfec4, 0x1), /* BR_INST_RETIRED.TAKEN_JCC_PS */ - INTEL_UEVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_MISP_RETIRED.ALL_BRANCHES_PS */ - INTEL_UEVENT_CONSTRAINT(0x7ec5, 0x1), /* BR_INST_MISP_RETIRED.JCC_PS */ - INTEL_UEVENT_CONSTRAINT(0xebc5, 0x1), /* BR_INST_MISP_RETIRED.NON_RETURN_IND_PS */ - INTEL_UEVENT_CONSTRAINT(0xf7c5, 0x1), /* BR_INST_MISP_RETIRED.RETURN_PS */ - INTEL_UEVENT_CONSTRAINT(0xfbc5, 0x1), /* BR_INST_MISP_RETIRED.IND_CALL_PS */ - INTEL_UEVENT_CONSTRAINT(0xfec5, 0x1), /* BR_INST_MISP_RETIRED.TAKEN_JCC_PS */ + /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + /* Allow all events as PEBS with no flags */ + INTEL_ALL_EVENT_CONSTRAINT(0, 0x1), EVENT_CONSTRAINT_END }; struct event_constraint intel_nehalem_pebs_event_constraints[] = { INTEL_PLD_CONSTRAINT(0x100b, 0xf), /* MEM_INST_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */ - INTEL_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */ - INTEL_EVENT_CONSTRAINT(0xc0, 0xf), /* INST_RETIRED.ANY */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */ + INTEL_FLAGS_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */ + INTEL_FLAGS_EVENT_CONSTRAINT(0xc0, 0xf), /* INST_RETIRED.ANY */ INTEL_EVENT_CONSTRAINT(0xc2, 0xf), /* UOPS_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */ - INTEL_UEVENT_CONSTRAINT(0x02c5, 0xf), /* BR_MISP_RETIRED.NEAR_CALL */ - INTEL_EVENT_CONSTRAINT(0xc7, 0xf), /* SSEX_UOPS_RETIRED.* */ - INTEL_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */ - INTEL_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */ + INTEL_FLAGS_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */ + INTEL_FLAGS_UEVENT_CONSTRAINT(0x02c5, 0xf), /* BR_MISP_RETIRED.NEAR_CALL */ + INTEL_FLAGS_EVENT_CONSTRAINT(0xc7, 0xf), /* SSEX_UOPS_RETIRED.* */ + INTEL_FLAGS_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */ + INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */ + INTEL_FLAGS_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */ EVENT_CONSTRAINT_END }; struct event_constraint intel_westmere_pebs_event_constraints[] = { INTEL_PLD_CONSTRAINT(0x100b, 0xf), /* MEM_INST_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */ - INTEL_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */ - INTEL_EVENT_CONSTRAINT(0xc0, 0xf), /* INSTR_RETIRED.* */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */ + INTEL_FLAGS_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */ + INTEL_FLAGS_EVENT_CONSTRAINT(0xc0, 0xf), /* INSTR_RETIRED.* */ INTEL_EVENT_CONSTRAINT(0xc2, 0xf), /* UOPS_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xc7, 0xf), /* SSEX_UOPS_RETIRED.* */ - INTEL_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */ - INTEL_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */ + INTEL_FLAGS_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */ + INTEL_FLAGS_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */ + INTEL_FLAGS_EVENT_CONSTRAINT(0xc7, 0xf), /* SSEX_UOPS_RETIRED.* */ + INTEL_FLAGS_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */ + INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */ + INTEL_FLAGS_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */ EVENT_CONSTRAINT_END }; struct event_constraint intel_snb_pebs_event_constraints[] = { - INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */ - INTEL_UEVENT_CONSTRAINT(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ - INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */ - INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */ + INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */ INTEL_PLD_CONSTRAINT(0x01cd, 0x8), /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */ INTEL_PST_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORES */ - INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xd3, 0xf), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */ - INTEL_UEVENT_CONSTRAINT(0x02d4, 0xf), /* MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS */ + /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + /* Allow all events as PEBS with no flags */ + INTEL_ALL_EVENT_CONSTRAINT(0, 0xf), EVENT_CONSTRAINT_END }; struct event_constraint intel_ivb_pebs_event_constraints[] = { - INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */ - INTEL_UEVENT_CONSTRAINT(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ - INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */ - INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */ + INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */ INTEL_PLD_CONSTRAINT(0x01cd, 0x8), /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */ INTEL_PST_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORES */ - INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xd3, 0xf), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */ + /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + /* Allow all events as PEBS with no flags */ + INTEL_ALL_EVENT_CONSTRAINT(0, 0xf), EVENT_CONSTRAINT_END }; struct event_constraint intel_hsw_pebs_event_constraints[] = { - INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */ - INTEL_PST_HSW_CONSTRAINT(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ - INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */ - INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */ - INTEL_UEVENT_CONSTRAINT(0x01c5, 0xf), /* BR_MISP_RETIRED.CONDITIONAL */ - INTEL_UEVENT_CONSTRAINT(0x04c5, 0xf), /* BR_MISP_RETIRED.ALL_BRANCHES */ - INTEL_UEVENT_CONSTRAINT(0x20c5, 0xf), /* BR_MISP_RETIRED.NEAR_TAKEN */ - INTEL_PLD_CONSTRAINT(0x01cd, 0x8), /* MEM_TRANS_RETIRED.* */ - /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */ - INTEL_UEVENT_CONSTRAINT(0x11d0, 0xf), - /* MEM_UOPS_RETIRED.STLB_MISS_STORES */ - INTEL_UEVENT_CONSTRAINT(0x12d0, 0xf), - INTEL_UEVENT_CONSTRAINT(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */ - INTEL_UEVENT_CONSTRAINT(0x41d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_LOADS */ - /* MEM_UOPS_RETIRED.SPLIT_STORES */ - INTEL_UEVENT_CONSTRAINT(0x42d0, 0xf), - INTEL_UEVENT_CONSTRAINT(0x81d0, 0xf), /* MEM_UOPS_RETIRED.ALL_LOADS */ - INTEL_PST_HSW_CONSTRAINT(0x82d0, 0xf), /* MEM_UOPS_RETIRED.ALL_STORES */ - INTEL_UEVENT_CONSTRAINT(0x01d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.L1_HIT */ - INTEL_UEVENT_CONSTRAINT(0x02d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.L2_HIT */ - INTEL_UEVENT_CONSTRAINT(0x04d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.L3_HIT */ - /* MEM_LOAD_UOPS_RETIRED.HIT_LFB */ - INTEL_UEVENT_CONSTRAINT(0x40d1, 0xf), - /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS */ - INTEL_UEVENT_CONSTRAINT(0x01d2, 0xf), - /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT */ - INTEL_UEVENT_CONSTRAINT(0x02d2, 0xf), - /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM */ - INTEL_UEVENT_CONSTRAINT(0x01d3, 0xf), - INTEL_UEVENT_CONSTRAINT(0x04c8, 0xf), /* HLE_RETIRED.Abort */ - INTEL_UEVENT_CONSTRAINT(0x04c9, 0xf), /* RTM_RETIRED.Abort */ - + INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */ + INTEL_PLD_CONSTRAINT(0x01cd, 0xf), /* MEM_TRANS_RETIRED.* */ + /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf), /* MEM_UOPS_RETIRED.ALL_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf), /* MEM_UOPS_RETIRED.ALL_STORES */ + INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ + INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd2, 0xf), /* MEM_LOAD_UOPS_L3_HIT_RETIRED.* */ + INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd3, 0xf), /* MEM_LOAD_UOPS_L3_MISS_RETIRED.* */ + /* Allow all events as PEBS with no flags */ + INTEL_ALL_EVENT_CONSTRAINT(0, 0xf), EVENT_CONSTRAINT_END }; @@ -712,7 +669,7 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event) void intel_pmu_pebs_enable(struct perf_event *event) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT; @@ -727,7 +684,7 @@ void intel_pmu_pebs_enable(struct perf_event *event) void intel_pmu_pebs_disable(struct perf_event *event) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; cpuc->pebs_enabled &= ~(1ULL << hwc->idx); @@ -745,7 +702,7 @@ void intel_pmu_pebs_disable(struct perf_event *event) void intel_pmu_pebs_enable_all(void) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); if (cpuc->pebs_enabled) wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled); @@ -753,7 +710,7 @@ void intel_pmu_pebs_enable_all(void) void intel_pmu_pebs_disable_all(void) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); if (cpuc->pebs_enabled) wrmsrl(MSR_IA32_PEBS_ENABLE, 0); @@ -761,12 +718,13 @@ void intel_pmu_pebs_disable_all(void) static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); unsigned long from = cpuc->lbr_entries[0].from; unsigned long old_to, to = cpuc->lbr_entries[0].to; unsigned long ip = regs->ip; int is_64bit = 0; void *kaddr; + int size; /* * We don't need to fixup if the PEBS assist is fault like @@ -801,11 +759,12 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs) return 1; } + size = ip - to; if (!kernel_ip(ip)) { - int size, bytes; + int bytes; u8 *buf = this_cpu_read(insn_buffer); - size = ip - to; /* Must fit our buffer, see above */ + /* 'size' must fit our buffer, see above */ bytes = copy_from_user_nmi(buf, (void __user *)to, size); if (bytes != 0) return 0; @@ -823,11 +782,20 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs) #ifdef CONFIG_X86_64 is_64bit = kernel_ip(to) || !test_thread_flag(TIF_IA32); #endif - insn_init(&insn, kaddr, is_64bit); + insn_init(&insn, kaddr, size, is_64bit); insn_get_length(&insn); + /* + * Make sure there was not a problem decoding the + * instruction and getting the length. This is + * doubly important because we have an infinite + * loop if insn.length=0. + */ + if (!insn.length) + break; to += insn.length; kaddr += insn.length; + size -= insn.length; } while (to < ip); if (to == ip) { @@ -864,51 +832,53 @@ static inline u64 intel_hsw_transaction(struct pebs_record_hsw *pebs) static void __intel_pmu_pebs_event(struct perf_event *event, struct pt_regs *iregs, void *__pebs) { +#define PERF_X86_EVENT_PEBS_HSW_PREC \ + (PERF_X86_EVENT_PEBS_ST_HSW | \ + PERF_X86_EVENT_PEBS_LD_HSW | \ + PERF_X86_EVENT_PEBS_NA_HSW) /* * We cast to the biggest pebs_record but are careful not to * unconditionally access the 'extra' entries. */ - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct pebs_record_hsw *pebs = __pebs; struct perf_sample_data data; struct pt_regs regs; u64 sample_type; - int fll, fst; + int fll, fst, dsrc; + int fl = event->hw.flags; if (!intel_pmu_save_and_restart(event)) return; - fll = event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT; - fst = event->hw.flags & (PERF_X86_EVENT_PEBS_ST | - PERF_X86_EVENT_PEBS_ST_HSW); + sample_type = event->attr.sample_type; + dsrc = sample_type & PERF_SAMPLE_DATA_SRC; + + fll = fl & PERF_X86_EVENT_PEBS_LDLAT; + fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC); perf_sample_data_init(&data, 0, event->hw.last_period); data.period = event->hw.last_period; - sample_type = event->attr.sample_type; /* - * if PEBS-LL or PreciseStore + * Use latency for weight (only avail with PEBS-LL) */ - if (fll || fst) { - /* - * Use latency for weight (only avail with PEBS-LL) - */ - if (fll && (sample_type & PERF_SAMPLE_WEIGHT)) - data.weight = pebs->lat; + if (fll && (sample_type & PERF_SAMPLE_WEIGHT)) + data.weight = pebs->lat; - /* - * data.data_src encodes the data source - */ - if (sample_type & PERF_SAMPLE_DATA_SRC) { - if (fll) - data.data_src.val = load_latency_data(pebs->dse); - else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST_HSW) - data.data_src.val = - precise_store_data_hsw(event, pebs->dse); - else - data.data_src.val = precise_store_data(pebs->dse); - } + /* + * data.data_src encodes the data source + */ + if (dsrc) { + u64 val = PERF_MEM_NA; + if (fll) + val = load_latency_data(pebs->dse); + else if (fst && (fl & PERF_X86_EVENT_PEBS_HSW_PREC)) + val = precise_datala_hsw(event, pebs->dse); + else if (fst) + val = precise_store_data(pebs->dse); + data.data_src.val = val; } /* @@ -927,6 +897,29 @@ static void __intel_pmu_pebs_event(struct perf_event *event, regs.bp = pebs->bp; regs.sp = pebs->sp; + if (sample_type & PERF_SAMPLE_REGS_INTR) { + regs.ax = pebs->ax; + regs.bx = pebs->bx; + regs.cx = pebs->cx; + regs.dx = pebs->dx; + regs.si = pebs->si; + regs.di = pebs->di; + regs.bp = pebs->bp; + regs.sp = pebs->sp; + + regs.flags = pebs->flags; +#ifndef CONFIG_X86_32 + regs.r8 = pebs->r8; + regs.r9 = pebs->r9; + regs.r10 = pebs->r10; + regs.r11 = pebs->r11; + regs.r12 = pebs->r12; + regs.r13 = pebs->r13; + regs.r14 = pebs->r14; + regs.r15 = pebs->r15; +#endif + } + if (event->attr.precise_ip > 1 && x86_pmu.intel_cap.pebs_format >= 2) { regs.ip = pebs->real_ip; regs.flags |= PERF_EFLAGS_EXACT; @@ -935,16 +928,16 @@ static void __intel_pmu_pebs_event(struct perf_event *event, else regs.flags &= ~PERF_EFLAGS_EXACT; - if ((event->attr.sample_type & PERF_SAMPLE_ADDR) && + if ((sample_type & PERF_SAMPLE_ADDR) && x86_pmu.intel_cap.pebs_format >= 1) data.addr = pebs->dla; if (x86_pmu.intel_cap.pebs_format >= 2) { /* Only set the TSX weight when no memory weight. */ - if ((event->attr.sample_type & PERF_SAMPLE_WEIGHT) && !fll) + if ((sample_type & PERF_SAMPLE_WEIGHT) && !fll) data.weight = intel_hsw_weight(pebs); - if (event->attr.sample_type & PERF_SAMPLE_TRANSACTION) + if (sample_type & PERF_SAMPLE_TRANSACTION) data.txn = intel_hsw_transaction(pebs); } @@ -957,7 +950,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event, static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct debug_store *ds = cpuc->ds; struct perf_event *event = cpuc->events[0]; /* PMC0 only */ struct pebs_record_core *at, *top; @@ -998,7 +991,7 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct debug_store *ds = cpuc->ds; struct perf_event *event = NULL; void *at, *top; @@ -1055,7 +1048,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) * BTS, PEBS probe and setup */ -void intel_ds_init(void) +void __init intel_ds_init(void) { /* * No support for 32bit formats diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c index 9dd2459a4c73..58f1a94beaf0 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -133,7 +133,7 @@ static void intel_pmu_lbr_filter(struct cpu_hw_events *cpuc); static void __intel_pmu_lbr_enable(void) { u64 debugctl; - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); if (cpuc->lbr_sel) wrmsrl(MSR_LBR_SELECT, cpuc->lbr_sel->config); @@ -183,7 +183,7 @@ void intel_pmu_lbr_reset(void) void intel_pmu_lbr_enable(struct perf_event *event) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); if (!x86_pmu.lbr_nr) return; @@ -203,7 +203,7 @@ void intel_pmu_lbr_enable(struct perf_event *event) void intel_pmu_lbr_disable(struct perf_event *event) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); if (!x86_pmu.lbr_nr) return; @@ -220,7 +220,7 @@ void intel_pmu_lbr_disable(struct perf_event *event) void intel_pmu_lbr_enable_all(void) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); if (cpuc->lbr_users) __intel_pmu_lbr_enable(); @@ -228,7 +228,7 @@ void intel_pmu_lbr_enable_all(void) void intel_pmu_lbr_disable_all(void) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); if (cpuc->lbr_users) __intel_pmu_lbr_disable(); @@ -332,7 +332,7 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) void intel_pmu_lbr_read(void) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); if (!cpuc->lbr_users) return; @@ -465,7 +465,7 @@ static int branch_type(unsigned long from, unsigned long to, int abort) { struct insn insn; void *addr; - int bytes, size = MAX_INSN_SIZE; + int bytes_read, bytes_left; int ret = X86_BR_NONE; int ext, to_plm, from_plm; u8 buf[MAX_INSN_SIZE]; @@ -493,8 +493,10 @@ static int branch_type(unsigned long from, unsigned long to, int abort) return X86_BR_NONE; /* may fail if text not present */ - bytes = copy_from_user_nmi(buf, (void __user *)from, size); - if (bytes != 0) + bytes_left = copy_from_user_nmi(buf, (void __user *)from, + MAX_INSN_SIZE); + bytes_read = MAX_INSN_SIZE - bytes_left; + if (!bytes_read) return X86_BR_NONE; addr = buf; @@ -505,10 +507,19 @@ static int branch_type(unsigned long from, unsigned long to, int abort) * Ensure we don't blindy read any address by validating it is * a known text address. */ - if (kernel_text_address(from)) + if (kernel_text_address(from)) { addr = (void *)from; - else + /* + * Assume we can get the maximum possible size + * when grabbing kernel data. This is not + * _strictly_ true since we could possibly be + * executing up next to a memory hole, but + * it is very unlikely to be a problem. + */ + bytes_read = MAX_INSN_SIZE; + } else { return X86_BR_NONE; + } } /* @@ -518,8 +529,10 @@ static int branch_type(unsigned long from, unsigned long to, int abort) #ifdef CONFIG_X86_64 is64 = kernel_ip((unsigned long)addr) || !test_thread_flag(TIF_IA32); #endif - insn_init(&insn, addr, is64); + insn_init(&insn, addr, bytes_read, is64); insn_get_opcode(&insn); + if (!insn.opcode.got) + return X86_BR_ABORT; switch (insn.opcode.bytes[0]) { case 0xf: @@ -697,7 +710,7 @@ static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = { }; /* core */ -void intel_pmu_lbr_init_core(void) +void __init intel_pmu_lbr_init_core(void) { x86_pmu.lbr_nr = 4; x86_pmu.lbr_tos = MSR_LBR_TOS; @@ -712,7 +725,7 @@ void intel_pmu_lbr_init_core(void) } /* nehalem/westmere */ -void intel_pmu_lbr_init_nhm(void) +void __init intel_pmu_lbr_init_nhm(void) { x86_pmu.lbr_nr = 16; x86_pmu.lbr_tos = MSR_LBR_TOS; @@ -733,7 +746,7 @@ void intel_pmu_lbr_init_nhm(void) } /* sandy bridge */ -void intel_pmu_lbr_init_snb(void) +void __init intel_pmu_lbr_init_snb(void) { x86_pmu.lbr_nr = 16; x86_pmu.lbr_tos = MSR_LBR_TOS; @@ -753,7 +766,7 @@ void intel_pmu_lbr_init_snb(void) } /* atom */ -void intel_pmu_lbr_init_atom(void) +void __init intel_pmu_lbr_init_atom(void) { /* * only models starting at stepping 10 seems diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c index 619f7699487a..673f930c700f 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c +++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c @@ -135,7 +135,7 @@ static inline u64 rapl_scale(u64 v) * or use ldexp(count, -32). * Watts = Joules/Time delta */ - return v << (32 - __get_cpu_var(rapl_pmu)->hw_unit); + return v << (32 - __this_cpu_read(rapl_pmu->hw_unit)); } static u64 rapl_event_update(struct perf_event *event) @@ -187,7 +187,7 @@ static void rapl_stop_hrtimer(struct rapl_pmu *pmu) static enum hrtimer_restart rapl_hrtimer_handle(struct hrtimer *hrtimer) { - struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu); + struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu); struct perf_event *event; unsigned long flags; @@ -234,7 +234,7 @@ static void __rapl_pmu_event_start(struct rapl_pmu *pmu, static void rapl_pmu_event_start(struct perf_event *event, int mode) { - struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu); + struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu); unsigned long flags; spin_lock_irqsave(&pmu->lock, flags); @@ -244,7 +244,7 @@ static void rapl_pmu_event_start(struct perf_event *event, int mode) static void rapl_pmu_event_stop(struct perf_event *event, int mode) { - struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu); + struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu); struct hw_perf_event *hwc = &event->hw; unsigned long flags; @@ -278,7 +278,7 @@ static void rapl_pmu_event_stop(struct perf_event *event, int mode) static int rapl_pmu_event_add(struct perf_event *event, int mode) { - struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu); + struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu); struct hw_perf_event *hwc = &event->hw; unsigned long flags; @@ -365,11 +365,7 @@ static void rapl_pmu_event_read(struct perf_event *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; + return cpumap_print_to_pagebuf(true, buf, &rapl_cpu_mask); } static DEVICE_ATTR(cpumask, S_IRUGO, rapl_get_attr_cpumask, NULL); @@ -696,7 +692,7 @@ static int __init rapl_pmu_init(void) return -1; } - pmu = __get_cpu_var(rapl_pmu); + pmu = __this_cpu_read(rapl_pmu); pr_info("RAPL PMU detected, hw unit 2^-%d Joules," " API unit is 2^-32 Joules," diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 0939f86f543d..10b8d3eaaf15 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -1,83 +1,39 @@ #include "perf_event_intel_uncore.h" static struct intel_uncore_type *empty_uncore[] = { NULL, }; -static struct intel_uncore_type **msr_uncores = empty_uncore; -static struct intel_uncore_type **pci_uncores = empty_uncore; -/* pci bus to socket mapping */ -static int pcibus_to_physid[256] = { [0 ... 255] = -1, }; +struct intel_uncore_type **uncore_msr_uncores = empty_uncore; +struct intel_uncore_type **uncore_pci_uncores = empty_uncore; -static struct pci_dev *extra_pci_dev[UNCORE_SOCKET_MAX][UNCORE_EXTRA_PCI_DEV_MAX]; +static bool pcidrv_registered; +struct pci_driver *uncore_pci_driver; +/* pci bus to socket mapping */ +int uncore_pcibus_to_physid[256] = { [0 ... 255] = -1, }; +struct pci_dev *uncore_extra_pci_dev[UNCORE_SOCKET_MAX][UNCORE_EXTRA_PCI_DEV_MAX]; static DEFINE_RAW_SPINLOCK(uncore_box_lock); - /* mask of cpus that collect uncore events */ static cpumask_t uncore_cpu_mask; /* constraint for the fixed counter */ -static struct event_constraint constraint_fixed = +static struct event_constraint uncore_constraint_fixed = EVENT_CONSTRAINT(~0ULL, 1 << UNCORE_PMC_IDX_FIXED, ~0ULL); -static struct event_constraint constraint_empty = +struct event_constraint uncore_constraint_empty = EVENT_CONSTRAINT(0, 0, 0); -#define __BITS_VALUE(x, i, n) ((typeof(x))(((x) >> ((i) * (n))) & \ - ((1ULL << (n)) - 1))) - -DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7"); -DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21"); -DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); -DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); -DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19"); -DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23"); -DEFINE_UNCORE_FORMAT_ATTR(cmask5, cmask, "config:24-28"); -DEFINE_UNCORE_FORMAT_ATTR(cmask8, cmask, "config:24-31"); -DEFINE_UNCORE_FORMAT_ATTR(thresh8, thresh, "config:24-31"); -DEFINE_UNCORE_FORMAT_ATTR(thresh5, thresh, "config:24-28"); -DEFINE_UNCORE_FORMAT_ATTR(occ_sel, occ_sel, "config:14-15"); -DEFINE_UNCORE_FORMAT_ATTR(occ_invert, occ_invert, "config:30"); -DEFINE_UNCORE_FORMAT_ATTR(occ_edge, occ_edge, "config:14-51"); -DEFINE_UNCORE_FORMAT_ATTR(filter_tid, filter_tid, "config1:0-4"); -DEFINE_UNCORE_FORMAT_ATTR(filter_link, filter_link, "config1:5-8"); -DEFINE_UNCORE_FORMAT_ATTR(filter_nid, filter_nid, "config1:10-17"); -DEFINE_UNCORE_FORMAT_ATTR(filter_nid2, filter_nid, "config1:32-47"); -DEFINE_UNCORE_FORMAT_ATTR(filter_state, filter_state, "config1:18-22"); -DEFINE_UNCORE_FORMAT_ATTR(filter_state2, filter_state, "config1:17-22"); -DEFINE_UNCORE_FORMAT_ATTR(filter_opc, filter_opc, "config1:23-31"); -DEFINE_UNCORE_FORMAT_ATTR(filter_opc2, filter_opc, "config1:52-60"); -DEFINE_UNCORE_FORMAT_ATTR(filter_band0, filter_band0, "config1:0-7"); -DEFINE_UNCORE_FORMAT_ATTR(filter_band1, filter_band1, "config1:8-15"); -DEFINE_UNCORE_FORMAT_ATTR(filter_band2, filter_band2, "config1:16-23"); -DEFINE_UNCORE_FORMAT_ATTR(filter_band3, filter_band3, "config1:24-31"); -DEFINE_UNCORE_FORMAT_ATTR(match_rds, match_rds, "config1:48-51"); -DEFINE_UNCORE_FORMAT_ATTR(match_rnid30, match_rnid30, "config1:32-35"); -DEFINE_UNCORE_FORMAT_ATTR(match_rnid4, match_rnid4, "config1:31"); -DEFINE_UNCORE_FORMAT_ATTR(match_dnid, match_dnid, "config1:13-17"); -DEFINE_UNCORE_FORMAT_ATTR(match_mc, match_mc, "config1:9-12"); -DEFINE_UNCORE_FORMAT_ATTR(match_opc, match_opc, "config1:5-8"); -DEFINE_UNCORE_FORMAT_ATTR(match_vnw, match_vnw, "config1:3-4"); -DEFINE_UNCORE_FORMAT_ATTR(match0, match0, "config1:0-31"); -DEFINE_UNCORE_FORMAT_ATTR(match1, match1, "config1:32-63"); -DEFINE_UNCORE_FORMAT_ATTR(mask_rds, mask_rds, "config2:48-51"); -DEFINE_UNCORE_FORMAT_ATTR(mask_rnid30, mask_rnid30, "config2:32-35"); -DEFINE_UNCORE_FORMAT_ATTR(mask_rnid4, mask_rnid4, "config2:31"); -DEFINE_UNCORE_FORMAT_ATTR(mask_dnid, mask_dnid, "config2:13-17"); -DEFINE_UNCORE_FORMAT_ATTR(mask_mc, mask_mc, "config2:9-12"); -DEFINE_UNCORE_FORMAT_ATTR(mask_opc, mask_opc, "config2:5-8"); -DEFINE_UNCORE_FORMAT_ATTR(mask_vnw, mask_vnw, "config2:3-4"); -DEFINE_UNCORE_FORMAT_ATTR(mask0, mask0, "config2:0-31"); -DEFINE_UNCORE_FORMAT_ATTR(mask1, mask1, "config2:32-63"); - -static void uncore_pmu_start_hrtimer(struct intel_uncore_box *box); -static void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box); -static void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *event); -static void uncore_pmu_event_read(struct perf_event *event); - -static struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event) +ssize_t uncore_event_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct uncore_event_desc *event = + container_of(attr, struct uncore_event_desc, attr); + return sprintf(buf, "%s", event->config); +} + +struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event) { return container_of(event->pmu, struct intel_uncore_pmu, pmu); } -static struct intel_uncore_box * -uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu) +struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu) { struct intel_uncore_box *box; @@ -86,6 +42,9 @@ uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu) return box; raw_spin_lock(&uncore_box_lock); + /* Recheck in lock to handle races. */ + if (*per_cpu_ptr(pmu->box, cpu)) + goto out; list_for_each_entry(box, &pmu->box_list, list) { if (box->phys_id == topology_physical_package_id(cpu)) { atomic_inc(&box->refcnt); @@ -93,12 +52,13 @@ uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu) break; } } +out: raw_spin_unlock(&uncore_box_lock); return *per_cpu_ptr(pmu->box, cpu); } -static struct intel_uncore_box *uncore_event_to_box(struct perf_event *event) +struct intel_uncore_box *uncore_event_to_box(struct perf_event *event) { /* * perf core schedules event on the basis of cpu, uncore events are @@ -107,7 +67,7 @@ static struct intel_uncore_box *uncore_event_to_box(struct perf_event *event) return uncore_pmu_to_box(uncore_event_to_pmu(event), smp_processor_id()); } -static u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event) +u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event) { u64 count; @@ -119,7 +79,7 @@ static u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_eve /* * generic get constraint function for shared match/mask registers. */ -static struct event_constraint * +struct event_constraint * uncore_get_constraint(struct intel_uncore_box *box, struct perf_event *event) { struct intel_uncore_extra_reg *er; @@ -154,10 +114,10 @@ uncore_get_constraint(struct intel_uncore_box *box, struct perf_event *event) return NULL; } - return &constraint_empty; + return &uncore_constraint_empty; } -static void uncore_put_constraint(struct intel_uncore_box *box, struct perf_event *event) +void uncore_put_constraint(struct intel_uncore_box *box, struct perf_event *event) { struct intel_uncore_extra_reg *er; struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; @@ -178,7 +138,7 @@ static void uncore_put_constraint(struct intel_uncore_box *box, struct perf_even reg1->alloc = 0; } -static u64 uncore_shared_reg_config(struct intel_uncore_box *box, int idx) +u64 uncore_shared_reg_config(struct intel_uncore_box *box, int idx) { struct intel_uncore_extra_reg *er; unsigned long flags; @@ -193,2936 +153,6 @@ static u64 uncore_shared_reg_config(struct intel_uncore_box *box, int idx) return config; } -/* Sandy Bridge-EP uncore support */ -static struct intel_uncore_type snbep_uncore_cbox; -static struct intel_uncore_type snbep_uncore_pcu; - -static void snbep_uncore_pci_disable_box(struct intel_uncore_box *box) -{ - struct pci_dev *pdev = box->pci_dev; - int box_ctl = uncore_pci_box_ctl(box); - u32 config = 0; - - if (!pci_read_config_dword(pdev, box_ctl, &config)) { - config |= SNBEP_PMON_BOX_CTL_FRZ; - pci_write_config_dword(pdev, box_ctl, config); - } -} - -static void snbep_uncore_pci_enable_box(struct intel_uncore_box *box) -{ - struct pci_dev *pdev = box->pci_dev; - int box_ctl = uncore_pci_box_ctl(box); - u32 config = 0; - - if (!pci_read_config_dword(pdev, box_ctl, &config)) { - config &= ~SNBEP_PMON_BOX_CTL_FRZ; - pci_write_config_dword(pdev, box_ctl, config); - } -} - -static void snbep_uncore_pci_enable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct pci_dev *pdev = box->pci_dev; - struct hw_perf_event *hwc = &event->hw; - - pci_write_config_dword(pdev, hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN); -} - -static void snbep_uncore_pci_disable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct pci_dev *pdev = box->pci_dev; - struct hw_perf_event *hwc = &event->hw; - - pci_write_config_dword(pdev, hwc->config_base, hwc->config); -} - -static u64 snbep_uncore_pci_read_counter(struct intel_uncore_box *box, struct perf_event *event) -{ - struct pci_dev *pdev = box->pci_dev; - struct hw_perf_event *hwc = &event->hw; - u64 count = 0; - - pci_read_config_dword(pdev, hwc->event_base, (u32 *)&count); - pci_read_config_dword(pdev, hwc->event_base + 4, (u32 *)&count + 1); - - return count; -} - -static void snbep_uncore_pci_init_box(struct intel_uncore_box *box) -{ - struct pci_dev *pdev = box->pci_dev; - - pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, SNBEP_PMON_BOX_CTL_INT); -} - -static void snbep_uncore_msr_disable_box(struct intel_uncore_box *box) -{ - u64 config; - unsigned msr; - - msr = uncore_msr_box_ctl(box); - if (msr) { - rdmsrl(msr, config); - config |= SNBEP_PMON_BOX_CTL_FRZ; - wrmsrl(msr, config); - } -} - -static void snbep_uncore_msr_enable_box(struct intel_uncore_box *box) -{ - u64 config; - unsigned msr; - - msr = uncore_msr_box_ctl(box); - if (msr) { - rdmsrl(msr, config); - config &= ~SNBEP_PMON_BOX_CTL_FRZ; - wrmsrl(msr, config); - } -} - -static void snbep_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - - if (reg1->idx != EXTRA_REG_NONE) - wrmsrl(reg1->reg, uncore_shared_reg_config(box, 0)); - - wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN); -} - -static void snbep_uncore_msr_disable_event(struct intel_uncore_box *box, - struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - - wrmsrl(hwc->config_base, hwc->config); -} - -static void snbep_uncore_msr_init_box(struct intel_uncore_box *box) -{ - unsigned msr = uncore_msr_box_ctl(box); - - if (msr) - wrmsrl(msr, SNBEP_PMON_BOX_CTL_INT); -} - -static struct attribute *snbep_uncore_formats_attr[] = { - &format_attr_event.attr, - &format_attr_umask.attr, - &format_attr_edge.attr, - &format_attr_inv.attr, - &format_attr_thresh8.attr, - NULL, -}; - -static struct attribute *snbep_uncore_ubox_formats_attr[] = { - &format_attr_event.attr, - &format_attr_umask.attr, - &format_attr_edge.attr, - &format_attr_inv.attr, - &format_attr_thresh5.attr, - NULL, -}; - -static struct attribute *snbep_uncore_cbox_formats_attr[] = { - &format_attr_event.attr, - &format_attr_umask.attr, - &format_attr_edge.attr, - &format_attr_tid_en.attr, - &format_attr_inv.attr, - &format_attr_thresh8.attr, - &format_attr_filter_tid.attr, - &format_attr_filter_nid.attr, - &format_attr_filter_state.attr, - &format_attr_filter_opc.attr, - NULL, -}; - -static struct attribute *snbep_uncore_pcu_formats_attr[] = { - &format_attr_event_ext.attr, - &format_attr_occ_sel.attr, - &format_attr_edge.attr, - &format_attr_inv.attr, - &format_attr_thresh5.attr, - &format_attr_occ_invert.attr, - &format_attr_occ_edge.attr, - &format_attr_filter_band0.attr, - &format_attr_filter_band1.attr, - &format_attr_filter_band2.attr, - &format_attr_filter_band3.attr, - NULL, -}; - -static struct attribute *snbep_uncore_qpi_formats_attr[] = { - &format_attr_event_ext.attr, - &format_attr_umask.attr, - &format_attr_edge.attr, - &format_attr_inv.attr, - &format_attr_thresh8.attr, - &format_attr_match_rds.attr, - &format_attr_match_rnid30.attr, - &format_attr_match_rnid4.attr, - &format_attr_match_dnid.attr, - &format_attr_match_mc.attr, - &format_attr_match_opc.attr, - &format_attr_match_vnw.attr, - &format_attr_match0.attr, - &format_attr_match1.attr, - &format_attr_mask_rds.attr, - &format_attr_mask_rnid30.attr, - &format_attr_mask_rnid4.attr, - &format_attr_mask_dnid.attr, - &format_attr_mask_mc.attr, - &format_attr_mask_opc.attr, - &format_attr_mask_vnw.attr, - &format_attr_mask0.attr, - &format_attr_mask1.attr, - NULL, -}; - -static struct uncore_event_desc snbep_uncore_imc_events[] = { - INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"), - INTEL_UNCORE_EVENT_DESC(cas_count_read, "event=0x04,umask=0x03"), - INTEL_UNCORE_EVENT_DESC(cas_count_write, "event=0x04,umask=0x0c"), - { /* end: all zeroes */ }, -}; - -static struct uncore_event_desc snbep_uncore_qpi_events[] = { - INTEL_UNCORE_EVENT_DESC(clockticks, "event=0x14"), - INTEL_UNCORE_EVENT_DESC(txl_flits_active, "event=0x00,umask=0x06"), - INTEL_UNCORE_EVENT_DESC(drs_data, "event=0x102,umask=0x08"), - INTEL_UNCORE_EVENT_DESC(ncb_data, "event=0x103,umask=0x04"), - { /* end: all zeroes */ }, -}; - -static struct attribute_group snbep_uncore_format_group = { - .name = "format", - .attrs = snbep_uncore_formats_attr, -}; - -static struct attribute_group snbep_uncore_ubox_format_group = { - .name = "format", - .attrs = snbep_uncore_ubox_formats_attr, -}; - -static struct attribute_group snbep_uncore_cbox_format_group = { - .name = "format", - .attrs = snbep_uncore_cbox_formats_attr, -}; - -static struct attribute_group snbep_uncore_pcu_format_group = { - .name = "format", - .attrs = snbep_uncore_pcu_formats_attr, -}; - -static struct attribute_group snbep_uncore_qpi_format_group = { - .name = "format", - .attrs = snbep_uncore_qpi_formats_attr, -}; - -#define SNBEP_UNCORE_MSR_OPS_COMMON_INIT() \ - .init_box = snbep_uncore_msr_init_box, \ - .disable_box = snbep_uncore_msr_disable_box, \ - .enable_box = snbep_uncore_msr_enable_box, \ - .disable_event = snbep_uncore_msr_disable_event, \ - .enable_event = snbep_uncore_msr_enable_event, \ - .read_counter = uncore_msr_read_counter - -static struct intel_uncore_ops snbep_uncore_msr_ops = { - SNBEP_UNCORE_MSR_OPS_COMMON_INIT(), -}; - -#define SNBEP_UNCORE_PCI_OPS_COMMON_INIT() \ - .init_box = snbep_uncore_pci_init_box, \ - .disable_box = snbep_uncore_pci_disable_box, \ - .enable_box = snbep_uncore_pci_enable_box, \ - .disable_event = snbep_uncore_pci_disable_event, \ - .read_counter = snbep_uncore_pci_read_counter - -static struct intel_uncore_ops snbep_uncore_pci_ops = { - SNBEP_UNCORE_PCI_OPS_COMMON_INIT(), - .enable_event = snbep_uncore_pci_enable_event, \ -}; - -static struct event_constraint snbep_uncore_cbox_constraints[] = { - UNCORE_EVENT_CONSTRAINT(0x01, 0x1), - UNCORE_EVENT_CONSTRAINT(0x02, 0x3), - UNCORE_EVENT_CONSTRAINT(0x04, 0x3), - UNCORE_EVENT_CONSTRAINT(0x05, 0x3), - UNCORE_EVENT_CONSTRAINT(0x07, 0x3), - UNCORE_EVENT_CONSTRAINT(0x09, 0x3), - UNCORE_EVENT_CONSTRAINT(0x11, 0x1), - UNCORE_EVENT_CONSTRAINT(0x12, 0x3), - UNCORE_EVENT_CONSTRAINT(0x13, 0x3), - UNCORE_EVENT_CONSTRAINT(0x1b, 0xc), - UNCORE_EVENT_CONSTRAINT(0x1c, 0xc), - UNCORE_EVENT_CONSTRAINT(0x1d, 0xc), - UNCORE_EVENT_CONSTRAINT(0x1e, 0xc), - EVENT_CONSTRAINT_OVERLAP(0x1f, 0xe, 0xff), - UNCORE_EVENT_CONSTRAINT(0x21, 0x3), - UNCORE_EVENT_CONSTRAINT(0x23, 0x3), - UNCORE_EVENT_CONSTRAINT(0x31, 0x3), - UNCORE_EVENT_CONSTRAINT(0x32, 0x3), - UNCORE_EVENT_CONSTRAINT(0x33, 0x3), - UNCORE_EVENT_CONSTRAINT(0x34, 0x3), - UNCORE_EVENT_CONSTRAINT(0x35, 0x3), - UNCORE_EVENT_CONSTRAINT(0x36, 0x1), - UNCORE_EVENT_CONSTRAINT(0x37, 0x3), - UNCORE_EVENT_CONSTRAINT(0x38, 0x3), - UNCORE_EVENT_CONSTRAINT(0x39, 0x3), - UNCORE_EVENT_CONSTRAINT(0x3b, 0x1), - EVENT_CONSTRAINT_END -}; - -static struct event_constraint snbep_uncore_r2pcie_constraints[] = { - UNCORE_EVENT_CONSTRAINT(0x10, 0x3), - UNCORE_EVENT_CONSTRAINT(0x11, 0x3), - UNCORE_EVENT_CONSTRAINT(0x12, 0x1), - UNCORE_EVENT_CONSTRAINT(0x23, 0x3), - UNCORE_EVENT_CONSTRAINT(0x24, 0x3), - UNCORE_EVENT_CONSTRAINT(0x25, 0x3), - UNCORE_EVENT_CONSTRAINT(0x26, 0x3), - UNCORE_EVENT_CONSTRAINT(0x32, 0x3), - UNCORE_EVENT_CONSTRAINT(0x33, 0x3), - UNCORE_EVENT_CONSTRAINT(0x34, 0x3), - EVENT_CONSTRAINT_END -}; - -static struct event_constraint snbep_uncore_r3qpi_constraints[] = { - UNCORE_EVENT_CONSTRAINT(0x10, 0x3), - UNCORE_EVENT_CONSTRAINT(0x11, 0x3), - UNCORE_EVENT_CONSTRAINT(0x12, 0x3), - UNCORE_EVENT_CONSTRAINT(0x13, 0x1), - UNCORE_EVENT_CONSTRAINT(0x20, 0x3), - UNCORE_EVENT_CONSTRAINT(0x21, 0x3), - UNCORE_EVENT_CONSTRAINT(0x22, 0x3), - UNCORE_EVENT_CONSTRAINT(0x23, 0x3), - UNCORE_EVENT_CONSTRAINT(0x24, 0x3), - UNCORE_EVENT_CONSTRAINT(0x25, 0x3), - UNCORE_EVENT_CONSTRAINT(0x26, 0x3), - UNCORE_EVENT_CONSTRAINT(0x28, 0x3), - UNCORE_EVENT_CONSTRAINT(0x29, 0x3), - UNCORE_EVENT_CONSTRAINT(0x2a, 0x3), - UNCORE_EVENT_CONSTRAINT(0x2b, 0x3), - UNCORE_EVENT_CONSTRAINT(0x2c, 0x3), - UNCORE_EVENT_CONSTRAINT(0x2d, 0x3), - UNCORE_EVENT_CONSTRAINT(0x2e, 0x3), - UNCORE_EVENT_CONSTRAINT(0x2f, 0x3), - UNCORE_EVENT_CONSTRAINT(0x30, 0x3), - UNCORE_EVENT_CONSTRAINT(0x31, 0x3), - UNCORE_EVENT_CONSTRAINT(0x32, 0x3), - UNCORE_EVENT_CONSTRAINT(0x33, 0x3), - UNCORE_EVENT_CONSTRAINT(0x34, 0x3), - UNCORE_EVENT_CONSTRAINT(0x36, 0x3), - UNCORE_EVENT_CONSTRAINT(0x37, 0x3), - UNCORE_EVENT_CONSTRAINT(0x38, 0x3), - UNCORE_EVENT_CONSTRAINT(0x39, 0x3), - EVENT_CONSTRAINT_END -}; - -static struct intel_uncore_type snbep_uncore_ubox = { - .name = "ubox", - .num_counters = 2, - .num_boxes = 1, - .perf_ctr_bits = 44, - .fixed_ctr_bits = 48, - .perf_ctr = SNBEP_U_MSR_PMON_CTR0, - .event_ctl = SNBEP_U_MSR_PMON_CTL0, - .event_mask = SNBEP_U_MSR_PMON_RAW_EVENT_MASK, - .fixed_ctr = SNBEP_U_MSR_PMON_UCLK_FIXED_CTR, - .fixed_ctl = SNBEP_U_MSR_PMON_UCLK_FIXED_CTL, - .ops = &snbep_uncore_msr_ops, - .format_group = &snbep_uncore_ubox_format_group, -}; - -static struct extra_reg snbep_uncore_cbox_extra_regs[] = { - SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN, - SNBEP_CBO_PMON_CTL_TID_EN, 0x1), - SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4), - SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0x6), - SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4), - SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0x6), - SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4), - SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0x6), - SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0x6), - SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x8), - SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x8), - SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0xa), - SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0xa), - SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x2), - SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x2), - SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x2), - SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x2), - SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x8), - SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x8), - SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0xa), - SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0xa), - SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x2), - SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x2), - SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x2), - SNBEP_CBO_EVENT_EXTRA_REG(0x4037, 0x40ff, 0x2), - EVENT_EXTRA_END -}; - -static void snbep_cbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; - struct intel_uncore_extra_reg *er = &box->shared_regs[0]; - int i; - - if (uncore_box_is_fake(box)) - return; - - for (i = 0; i < 5; i++) { - if (reg1->alloc & (0x1 << i)) - atomic_sub(1 << (i * 6), &er->ref); - } - reg1->alloc = 0; -} - -static struct event_constraint * -__snbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event, - u64 (*cbox_filter_mask)(int fields)) -{ - struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; - struct intel_uncore_extra_reg *er = &box->shared_regs[0]; - int i, alloc = 0; - unsigned long flags; - u64 mask; - - if (reg1->idx == EXTRA_REG_NONE) - return NULL; - - raw_spin_lock_irqsave(&er->lock, flags); - for (i = 0; i < 5; i++) { - if (!(reg1->idx & (0x1 << i))) - continue; - if (!uncore_box_is_fake(box) && (reg1->alloc & (0x1 << i))) - continue; - - mask = cbox_filter_mask(0x1 << i); - if (!__BITS_VALUE(atomic_read(&er->ref), i, 6) || - !((reg1->config ^ er->config) & mask)) { - atomic_add(1 << (i * 6), &er->ref); - er->config &= ~mask; - er->config |= reg1->config & mask; - alloc |= (0x1 << i); - } else { - break; - } - } - raw_spin_unlock_irqrestore(&er->lock, flags); - if (i < 5) - goto fail; - - if (!uncore_box_is_fake(box)) - reg1->alloc |= alloc; - - return NULL; -fail: - for (; i >= 0; i--) { - if (alloc & (0x1 << i)) - atomic_sub(1 << (i * 6), &er->ref); - } - return &constraint_empty; -} - -static u64 snbep_cbox_filter_mask(int fields) -{ - u64 mask = 0; - - if (fields & 0x1) - mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_TID; - if (fields & 0x2) - mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_NID; - if (fields & 0x4) - mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_STATE; - if (fields & 0x8) - mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_OPC; - - return mask; -} - -static struct event_constraint * -snbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event) -{ - return __snbep_cbox_get_constraint(box, event, snbep_cbox_filter_mask); -} - -static int snbep_cbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; - struct extra_reg *er; - int idx = 0; - - for (er = snbep_uncore_cbox_extra_regs; er->msr; er++) { - if (er->event != (event->hw.config & er->config_mask)) - continue; - idx |= er->idx; - } - - if (idx) { - reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER + - SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx; - reg1->config = event->attr.config1 & snbep_cbox_filter_mask(idx); - reg1->idx = idx; - } - return 0; -} - -static struct intel_uncore_ops snbep_uncore_cbox_ops = { - SNBEP_UNCORE_MSR_OPS_COMMON_INIT(), - .hw_config = snbep_cbox_hw_config, - .get_constraint = snbep_cbox_get_constraint, - .put_constraint = snbep_cbox_put_constraint, -}; - -static struct intel_uncore_type snbep_uncore_cbox = { - .name = "cbox", - .num_counters = 4, - .num_boxes = 8, - .perf_ctr_bits = 44, - .event_ctl = SNBEP_C0_MSR_PMON_CTL0, - .perf_ctr = SNBEP_C0_MSR_PMON_CTR0, - .event_mask = SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK, - .box_ctl = SNBEP_C0_MSR_PMON_BOX_CTL, - .msr_offset = SNBEP_CBO_MSR_OFFSET, - .num_shared_regs = 1, - .constraints = snbep_uncore_cbox_constraints, - .ops = &snbep_uncore_cbox_ops, - .format_group = &snbep_uncore_cbox_format_group, -}; - -static u64 snbep_pcu_alter_er(struct perf_event *event, int new_idx, bool modify) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - u64 config = reg1->config; - - if (new_idx > reg1->idx) - config <<= 8 * (new_idx - reg1->idx); - else - config >>= 8 * (reg1->idx - new_idx); - - if (modify) { - hwc->config += new_idx - reg1->idx; - reg1->config = config; - reg1->idx = new_idx; - } - return config; -} - -static struct event_constraint * -snbep_pcu_get_constraint(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; - struct intel_uncore_extra_reg *er = &box->shared_regs[0]; - unsigned long flags; - int idx = reg1->idx; - u64 mask, config1 = reg1->config; - bool ok = false; - - if (reg1->idx == EXTRA_REG_NONE || - (!uncore_box_is_fake(box) && reg1->alloc)) - return NULL; -again: - mask = 0xffULL << (idx * 8); - raw_spin_lock_irqsave(&er->lock, flags); - if (!__BITS_VALUE(atomic_read(&er->ref), idx, 8) || - !((config1 ^ er->config) & mask)) { - atomic_add(1 << (idx * 8), &er->ref); - er->config &= ~mask; - er->config |= config1 & mask; - ok = true; - } - raw_spin_unlock_irqrestore(&er->lock, flags); - - if (!ok) { - idx = (idx + 1) % 4; - if (idx != reg1->idx) { - config1 = snbep_pcu_alter_er(event, idx, false); - goto again; - } - return &constraint_empty; - } - - if (!uncore_box_is_fake(box)) { - if (idx != reg1->idx) - snbep_pcu_alter_er(event, idx, true); - reg1->alloc = 1; - } - return NULL; -} - -static void snbep_pcu_put_constraint(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; - struct intel_uncore_extra_reg *er = &box->shared_regs[0]; - - if (uncore_box_is_fake(box) || !reg1->alloc) - return; - - atomic_sub(1 << (reg1->idx * 8), &er->ref); - reg1->alloc = 0; -} - -static int snbep_pcu_hw_config(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - int ev_sel = hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK; - - if (ev_sel >= 0xb && ev_sel <= 0xe) { - reg1->reg = SNBEP_PCU_MSR_PMON_BOX_FILTER; - reg1->idx = ev_sel - 0xb; - reg1->config = event->attr.config1 & (0xff << reg1->idx); - } - return 0; -} - -static struct intel_uncore_ops snbep_uncore_pcu_ops = { - SNBEP_UNCORE_MSR_OPS_COMMON_INIT(), - .hw_config = snbep_pcu_hw_config, - .get_constraint = snbep_pcu_get_constraint, - .put_constraint = snbep_pcu_put_constraint, -}; - -static struct intel_uncore_type snbep_uncore_pcu = { - .name = "pcu", - .num_counters = 4, - .num_boxes = 1, - .perf_ctr_bits = 48, - .perf_ctr = SNBEP_PCU_MSR_PMON_CTR0, - .event_ctl = SNBEP_PCU_MSR_PMON_CTL0, - .event_mask = SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK, - .box_ctl = SNBEP_PCU_MSR_PMON_BOX_CTL, - .num_shared_regs = 1, - .ops = &snbep_uncore_pcu_ops, - .format_group = &snbep_uncore_pcu_format_group, -}; - -static struct intel_uncore_type *snbep_msr_uncores[] = { - &snbep_uncore_ubox, - &snbep_uncore_cbox, - &snbep_uncore_pcu, - NULL, -}; - -enum { - SNBEP_PCI_QPI_PORT0_FILTER, - SNBEP_PCI_QPI_PORT1_FILTER, -}; - -static int snbep_qpi_hw_config(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - struct hw_perf_event_extra *reg2 = &hwc->branch_reg; - - if ((hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK) == 0x38) { - reg1->idx = 0; - reg1->reg = SNBEP_Q_Py_PCI_PMON_PKT_MATCH0; - reg1->config = event->attr.config1; - reg2->reg = SNBEP_Q_Py_PCI_PMON_PKT_MASK0; - reg2->config = event->attr.config2; - } - return 0; -} - -static void snbep_qpi_enable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct pci_dev *pdev = box->pci_dev; - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - struct hw_perf_event_extra *reg2 = &hwc->branch_reg; - - if (reg1->idx != EXTRA_REG_NONE) { - int idx = box->pmu->pmu_idx + SNBEP_PCI_QPI_PORT0_FILTER; - struct pci_dev *filter_pdev = extra_pci_dev[box->phys_id][idx]; - WARN_ON_ONCE(!filter_pdev); - if (filter_pdev) { - pci_write_config_dword(filter_pdev, reg1->reg, - (u32)reg1->config); - pci_write_config_dword(filter_pdev, reg1->reg + 4, - (u32)(reg1->config >> 32)); - pci_write_config_dword(filter_pdev, reg2->reg, - (u32)reg2->config); - pci_write_config_dword(filter_pdev, reg2->reg + 4, - (u32)(reg2->config >> 32)); - } - } - - pci_write_config_dword(pdev, hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN); -} - -static struct intel_uncore_ops snbep_uncore_qpi_ops = { - SNBEP_UNCORE_PCI_OPS_COMMON_INIT(), - .enable_event = snbep_qpi_enable_event, - .hw_config = snbep_qpi_hw_config, - .get_constraint = uncore_get_constraint, - .put_constraint = uncore_put_constraint, -}; - -#define SNBEP_UNCORE_PCI_COMMON_INIT() \ - .perf_ctr = SNBEP_PCI_PMON_CTR0, \ - .event_ctl = SNBEP_PCI_PMON_CTL0, \ - .event_mask = SNBEP_PMON_RAW_EVENT_MASK, \ - .box_ctl = SNBEP_PCI_PMON_BOX_CTL, \ - .ops = &snbep_uncore_pci_ops, \ - .format_group = &snbep_uncore_format_group - -static struct intel_uncore_type snbep_uncore_ha = { - .name = "ha", - .num_counters = 4, - .num_boxes = 1, - .perf_ctr_bits = 48, - SNBEP_UNCORE_PCI_COMMON_INIT(), -}; - -static struct intel_uncore_type snbep_uncore_imc = { - .name = "imc", - .num_counters = 4, - .num_boxes = 4, - .perf_ctr_bits = 48, - .fixed_ctr_bits = 48, - .fixed_ctr = SNBEP_MC_CHy_PCI_PMON_FIXED_CTR, - .fixed_ctl = SNBEP_MC_CHy_PCI_PMON_FIXED_CTL, - .event_descs = snbep_uncore_imc_events, - SNBEP_UNCORE_PCI_COMMON_INIT(), -}; - -static struct intel_uncore_type snbep_uncore_qpi = { - .name = "qpi", - .num_counters = 4, - .num_boxes = 2, - .perf_ctr_bits = 48, - .perf_ctr = SNBEP_PCI_PMON_CTR0, - .event_ctl = SNBEP_PCI_PMON_CTL0, - .event_mask = SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK, - .box_ctl = SNBEP_PCI_PMON_BOX_CTL, - .num_shared_regs = 1, - .ops = &snbep_uncore_qpi_ops, - .event_descs = snbep_uncore_qpi_events, - .format_group = &snbep_uncore_qpi_format_group, -}; - - -static struct intel_uncore_type snbep_uncore_r2pcie = { - .name = "r2pcie", - .num_counters = 4, - .num_boxes = 1, - .perf_ctr_bits = 44, - .constraints = snbep_uncore_r2pcie_constraints, - SNBEP_UNCORE_PCI_COMMON_INIT(), -}; - -static struct intel_uncore_type snbep_uncore_r3qpi = { - .name = "r3qpi", - .num_counters = 3, - .num_boxes = 2, - .perf_ctr_bits = 44, - .constraints = snbep_uncore_r3qpi_constraints, - SNBEP_UNCORE_PCI_COMMON_INIT(), -}; - -enum { - SNBEP_PCI_UNCORE_HA, - SNBEP_PCI_UNCORE_IMC, - SNBEP_PCI_UNCORE_QPI, - SNBEP_PCI_UNCORE_R2PCIE, - SNBEP_PCI_UNCORE_R3QPI, -}; - -static struct intel_uncore_type *snbep_pci_uncores[] = { - [SNBEP_PCI_UNCORE_HA] = &snbep_uncore_ha, - [SNBEP_PCI_UNCORE_IMC] = &snbep_uncore_imc, - [SNBEP_PCI_UNCORE_QPI] = &snbep_uncore_qpi, - [SNBEP_PCI_UNCORE_R2PCIE] = &snbep_uncore_r2pcie, - [SNBEP_PCI_UNCORE_R3QPI] = &snbep_uncore_r3qpi, - NULL, -}; - -static const struct pci_device_id snbep_uncore_pci_ids[] = { - { /* Home Agent */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_HA), - .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_HA, 0), - }, - { /* MC Channel 0 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC0), - .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 0), - }, - { /* MC Channel 1 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC1), - .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 1), - }, - { /* MC Channel 2 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC2), - .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 2), - }, - { /* MC Channel 3 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC3), - .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 3), - }, - { /* QPI Port 0 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI0), - .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_QPI, 0), - }, - { /* QPI Port 1 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI1), - .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_QPI, 1), - }, - { /* R2PCIe */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R2PCIE), - .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R2PCIE, 0), - }, - { /* R3QPI Link 0 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI0), - .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R3QPI, 0), - }, - { /* R3QPI Link 1 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI1), - .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R3QPI, 1), - }, - { /* QPI Port 0 filter */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3c86), - .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, - SNBEP_PCI_QPI_PORT0_FILTER), - }, - { /* QPI Port 0 filter */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3c96), - .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, - SNBEP_PCI_QPI_PORT1_FILTER), - }, - { /* end: all zeroes */ } -}; - -static struct pci_driver snbep_uncore_pci_driver = { - .name = "snbep_uncore", - .id_table = snbep_uncore_pci_ids, -}; - -/* - * build pci bus to socket mapping - */ -static int snbep_pci2phy_map_init(int devid) -{ - struct pci_dev *ubox_dev = NULL; - int i, bus, nodeid; - int err = 0; - u32 config = 0; - - while (1) { - /* find the UBOX device */ - ubox_dev = pci_get_device(PCI_VENDOR_ID_INTEL, devid, ubox_dev); - if (!ubox_dev) - break; - bus = ubox_dev->bus->number; - /* get the Node ID of the local register */ - err = pci_read_config_dword(ubox_dev, 0x40, &config); - if (err) - break; - nodeid = config; - /* get the Node ID mapping */ - err = pci_read_config_dword(ubox_dev, 0x54, &config); - if (err) - break; - /* - * every three bits in the Node ID mapping register maps - * to a particular node. - */ - for (i = 0; i < 8; i++) { - if (nodeid == ((config >> (3 * i)) & 0x7)) { - pcibus_to_physid[bus] = i; - break; - } - } - } - - if (!err) { - /* - * For PCI bus with no UBOX device, find the next bus - * that has UBOX device and use its mapping. - */ - i = -1; - for (bus = 255; bus >= 0; bus--) { - if (pcibus_to_physid[bus] >= 0) - i = pcibus_to_physid[bus]; - else - pcibus_to_physid[bus] = i; - } - } - - if (ubox_dev) - pci_dev_put(ubox_dev); - - return err ? pcibios_err_to_errno(err) : 0; -} -/* end of Sandy Bridge-EP uncore support */ - -/* IvyTown uncore support */ -static void ivt_uncore_msr_init_box(struct intel_uncore_box *box) -{ - unsigned msr = uncore_msr_box_ctl(box); - if (msr) - wrmsrl(msr, IVT_PMON_BOX_CTL_INT); -} - -static void ivt_uncore_pci_init_box(struct intel_uncore_box *box) -{ - struct pci_dev *pdev = box->pci_dev; - - pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, IVT_PMON_BOX_CTL_INT); -} - -#define IVT_UNCORE_MSR_OPS_COMMON_INIT() \ - .init_box = ivt_uncore_msr_init_box, \ - .disable_box = snbep_uncore_msr_disable_box, \ - .enable_box = snbep_uncore_msr_enable_box, \ - .disable_event = snbep_uncore_msr_disable_event, \ - .enable_event = snbep_uncore_msr_enable_event, \ - .read_counter = uncore_msr_read_counter - -static struct intel_uncore_ops ivt_uncore_msr_ops = { - IVT_UNCORE_MSR_OPS_COMMON_INIT(), -}; - -static struct intel_uncore_ops ivt_uncore_pci_ops = { - .init_box = ivt_uncore_pci_init_box, - .disable_box = snbep_uncore_pci_disable_box, - .enable_box = snbep_uncore_pci_enable_box, - .disable_event = snbep_uncore_pci_disable_event, - .enable_event = snbep_uncore_pci_enable_event, - .read_counter = snbep_uncore_pci_read_counter, -}; - -#define IVT_UNCORE_PCI_COMMON_INIT() \ - .perf_ctr = SNBEP_PCI_PMON_CTR0, \ - .event_ctl = SNBEP_PCI_PMON_CTL0, \ - .event_mask = IVT_PMON_RAW_EVENT_MASK, \ - .box_ctl = SNBEP_PCI_PMON_BOX_CTL, \ - .ops = &ivt_uncore_pci_ops, \ - .format_group = &ivt_uncore_format_group - -static struct attribute *ivt_uncore_formats_attr[] = { - &format_attr_event.attr, - &format_attr_umask.attr, - &format_attr_edge.attr, - &format_attr_inv.attr, - &format_attr_thresh8.attr, - NULL, -}; - -static struct attribute *ivt_uncore_ubox_formats_attr[] = { - &format_attr_event.attr, - &format_attr_umask.attr, - &format_attr_edge.attr, - &format_attr_inv.attr, - &format_attr_thresh5.attr, - NULL, -}; - -static struct attribute *ivt_uncore_cbox_formats_attr[] = { - &format_attr_event.attr, - &format_attr_umask.attr, - &format_attr_edge.attr, - &format_attr_tid_en.attr, - &format_attr_thresh8.attr, - &format_attr_filter_tid.attr, - &format_attr_filter_link.attr, - &format_attr_filter_state2.attr, - &format_attr_filter_nid2.attr, - &format_attr_filter_opc2.attr, - NULL, -}; - -static struct attribute *ivt_uncore_pcu_formats_attr[] = { - &format_attr_event_ext.attr, - &format_attr_occ_sel.attr, - &format_attr_edge.attr, - &format_attr_thresh5.attr, - &format_attr_occ_invert.attr, - &format_attr_occ_edge.attr, - &format_attr_filter_band0.attr, - &format_attr_filter_band1.attr, - &format_attr_filter_band2.attr, - &format_attr_filter_band3.attr, - NULL, -}; - -static struct attribute *ivt_uncore_qpi_formats_attr[] = { - &format_attr_event_ext.attr, - &format_attr_umask.attr, - &format_attr_edge.attr, - &format_attr_thresh8.attr, - &format_attr_match_rds.attr, - &format_attr_match_rnid30.attr, - &format_attr_match_rnid4.attr, - &format_attr_match_dnid.attr, - &format_attr_match_mc.attr, - &format_attr_match_opc.attr, - &format_attr_match_vnw.attr, - &format_attr_match0.attr, - &format_attr_match1.attr, - &format_attr_mask_rds.attr, - &format_attr_mask_rnid30.attr, - &format_attr_mask_rnid4.attr, - &format_attr_mask_dnid.attr, - &format_attr_mask_mc.attr, - &format_attr_mask_opc.attr, - &format_attr_mask_vnw.attr, - &format_attr_mask0.attr, - &format_attr_mask1.attr, - NULL, -}; - -static struct attribute_group ivt_uncore_format_group = { - .name = "format", - .attrs = ivt_uncore_formats_attr, -}; - -static struct attribute_group ivt_uncore_ubox_format_group = { - .name = "format", - .attrs = ivt_uncore_ubox_formats_attr, -}; - -static struct attribute_group ivt_uncore_cbox_format_group = { - .name = "format", - .attrs = ivt_uncore_cbox_formats_attr, -}; - -static struct attribute_group ivt_uncore_pcu_format_group = { - .name = "format", - .attrs = ivt_uncore_pcu_formats_attr, -}; - -static struct attribute_group ivt_uncore_qpi_format_group = { - .name = "format", - .attrs = ivt_uncore_qpi_formats_attr, -}; - -static struct intel_uncore_type ivt_uncore_ubox = { - .name = "ubox", - .num_counters = 2, - .num_boxes = 1, - .perf_ctr_bits = 44, - .fixed_ctr_bits = 48, - .perf_ctr = SNBEP_U_MSR_PMON_CTR0, - .event_ctl = SNBEP_U_MSR_PMON_CTL0, - .event_mask = IVT_U_MSR_PMON_RAW_EVENT_MASK, - .fixed_ctr = SNBEP_U_MSR_PMON_UCLK_FIXED_CTR, - .fixed_ctl = SNBEP_U_MSR_PMON_UCLK_FIXED_CTL, - .ops = &ivt_uncore_msr_ops, - .format_group = &ivt_uncore_ubox_format_group, -}; - -static struct extra_reg ivt_uncore_cbox_extra_regs[] = { - SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN, - SNBEP_CBO_PMON_CTL_TID_EN, 0x1), - SNBEP_CBO_EVENT_EXTRA_REG(0x1031, 0x10ff, 0x2), - - SNBEP_CBO_EVENT_EXTRA_REG(0x1134, 0xffff, 0x4), - SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0xc), - SNBEP_CBO_EVENT_EXTRA_REG(0x5134, 0xffff, 0xc), - SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4), - SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0xc), - SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4), - SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0xc), - SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4), - SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0xc), - SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x10), - SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x10), - SNBEP_CBO_EVENT_EXTRA_REG(0x2135, 0xffff, 0x10), - SNBEP_CBO_EVENT_EXTRA_REG(0x2335, 0xffff, 0x10), - SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0x18), - SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0x18), - SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x8), - SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x8), - SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x8), - SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x8), - SNBEP_CBO_EVENT_EXTRA_REG(0x8135, 0xffff, 0x10), - SNBEP_CBO_EVENT_EXTRA_REG(0x8335, 0xffff, 0x10), - SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x10), - SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x10), - SNBEP_CBO_EVENT_EXTRA_REG(0x2136, 0xffff, 0x10), - SNBEP_CBO_EVENT_EXTRA_REG(0x2336, 0xffff, 0x10), - SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0x18), - SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0x18), - SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x8), - SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x8), - SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x8), - SNBEP_CBO_EVENT_EXTRA_REG(0x5036, 0xffff, 0x8), - SNBEP_CBO_EVENT_EXTRA_REG(0x8136, 0xffff, 0x10), - SNBEP_CBO_EVENT_EXTRA_REG(0x8336, 0xffff, 0x10), - SNBEP_CBO_EVENT_EXTRA_REG(0x4037, 0x40ff, 0x8), - EVENT_EXTRA_END -}; - -static u64 ivt_cbox_filter_mask(int fields) -{ - u64 mask = 0; - - if (fields & 0x1) - mask |= IVT_CB0_MSR_PMON_BOX_FILTER_TID; - if (fields & 0x2) - mask |= IVT_CB0_MSR_PMON_BOX_FILTER_LINK; - if (fields & 0x4) - mask |= IVT_CB0_MSR_PMON_BOX_FILTER_STATE; - if (fields & 0x8) - mask |= IVT_CB0_MSR_PMON_BOX_FILTER_NID; - if (fields & 0x10) - mask |= IVT_CB0_MSR_PMON_BOX_FILTER_OPC; - - return mask; -} - -static struct event_constraint * -ivt_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event) -{ - return __snbep_cbox_get_constraint(box, event, ivt_cbox_filter_mask); -} - -static int ivt_cbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; - struct extra_reg *er; - int idx = 0; - - for (er = ivt_uncore_cbox_extra_regs; er->msr; er++) { - if (er->event != (event->hw.config & er->config_mask)) - continue; - idx |= er->idx; - } - - if (idx) { - reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER + - SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx; - reg1->config = event->attr.config1 & ivt_cbox_filter_mask(idx); - reg1->idx = idx; - } - return 0; -} - -static void ivt_cbox_enable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - - if (reg1->idx != EXTRA_REG_NONE) { - u64 filter = uncore_shared_reg_config(box, 0); - wrmsrl(reg1->reg, filter & 0xffffffff); - wrmsrl(reg1->reg + 6, filter >> 32); - } - - wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN); -} - -static struct intel_uncore_ops ivt_uncore_cbox_ops = { - .init_box = ivt_uncore_msr_init_box, - .disable_box = snbep_uncore_msr_disable_box, - .enable_box = snbep_uncore_msr_enable_box, - .disable_event = snbep_uncore_msr_disable_event, - .enable_event = ivt_cbox_enable_event, - .read_counter = uncore_msr_read_counter, - .hw_config = ivt_cbox_hw_config, - .get_constraint = ivt_cbox_get_constraint, - .put_constraint = snbep_cbox_put_constraint, -}; - -static struct intel_uncore_type ivt_uncore_cbox = { - .name = "cbox", - .num_counters = 4, - .num_boxes = 15, - .perf_ctr_bits = 44, - .event_ctl = SNBEP_C0_MSR_PMON_CTL0, - .perf_ctr = SNBEP_C0_MSR_PMON_CTR0, - .event_mask = IVT_CBO_MSR_PMON_RAW_EVENT_MASK, - .box_ctl = SNBEP_C0_MSR_PMON_BOX_CTL, - .msr_offset = SNBEP_CBO_MSR_OFFSET, - .num_shared_regs = 1, - .constraints = snbep_uncore_cbox_constraints, - .ops = &ivt_uncore_cbox_ops, - .format_group = &ivt_uncore_cbox_format_group, -}; - -static struct intel_uncore_ops ivt_uncore_pcu_ops = { - IVT_UNCORE_MSR_OPS_COMMON_INIT(), - .hw_config = snbep_pcu_hw_config, - .get_constraint = snbep_pcu_get_constraint, - .put_constraint = snbep_pcu_put_constraint, -}; - -static struct intel_uncore_type ivt_uncore_pcu = { - .name = "pcu", - .num_counters = 4, - .num_boxes = 1, - .perf_ctr_bits = 48, - .perf_ctr = SNBEP_PCU_MSR_PMON_CTR0, - .event_ctl = SNBEP_PCU_MSR_PMON_CTL0, - .event_mask = IVT_PCU_MSR_PMON_RAW_EVENT_MASK, - .box_ctl = SNBEP_PCU_MSR_PMON_BOX_CTL, - .num_shared_regs = 1, - .ops = &ivt_uncore_pcu_ops, - .format_group = &ivt_uncore_pcu_format_group, -}; - -static struct intel_uncore_type *ivt_msr_uncores[] = { - &ivt_uncore_ubox, - &ivt_uncore_cbox, - &ivt_uncore_pcu, - NULL, -}; - -static struct intel_uncore_type ivt_uncore_ha = { - .name = "ha", - .num_counters = 4, - .num_boxes = 2, - .perf_ctr_bits = 48, - IVT_UNCORE_PCI_COMMON_INIT(), -}; - -static struct intel_uncore_type ivt_uncore_imc = { - .name = "imc", - .num_counters = 4, - .num_boxes = 8, - .perf_ctr_bits = 48, - .fixed_ctr_bits = 48, - .fixed_ctr = SNBEP_MC_CHy_PCI_PMON_FIXED_CTR, - .fixed_ctl = SNBEP_MC_CHy_PCI_PMON_FIXED_CTL, - IVT_UNCORE_PCI_COMMON_INIT(), -}; - -/* registers in IRP boxes are not properly aligned */ -static unsigned ivt_uncore_irp_ctls[] = {0xd8, 0xdc, 0xe0, 0xe4}; -static unsigned ivt_uncore_irp_ctrs[] = {0xa0, 0xb0, 0xb8, 0xc0}; - -static void ivt_uncore_irp_enable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct pci_dev *pdev = box->pci_dev; - struct hw_perf_event *hwc = &event->hw; - - pci_write_config_dword(pdev, ivt_uncore_irp_ctls[hwc->idx], - hwc->config | SNBEP_PMON_CTL_EN); -} - -static void ivt_uncore_irp_disable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct pci_dev *pdev = box->pci_dev; - struct hw_perf_event *hwc = &event->hw; - - pci_write_config_dword(pdev, ivt_uncore_irp_ctls[hwc->idx], hwc->config); -} - -static u64 ivt_uncore_irp_read_counter(struct intel_uncore_box *box, struct perf_event *event) -{ - struct pci_dev *pdev = box->pci_dev; - struct hw_perf_event *hwc = &event->hw; - u64 count = 0; - - pci_read_config_dword(pdev, ivt_uncore_irp_ctrs[hwc->idx], (u32 *)&count); - pci_read_config_dword(pdev, ivt_uncore_irp_ctrs[hwc->idx] + 4, (u32 *)&count + 1); - - return count; -} - -static struct intel_uncore_ops ivt_uncore_irp_ops = { - .init_box = ivt_uncore_pci_init_box, - .disable_box = snbep_uncore_pci_disable_box, - .enable_box = snbep_uncore_pci_enable_box, - .disable_event = ivt_uncore_irp_disable_event, - .enable_event = ivt_uncore_irp_enable_event, - .read_counter = ivt_uncore_irp_read_counter, -}; - -static struct intel_uncore_type ivt_uncore_irp = { - .name = "irp", - .num_counters = 4, - .num_boxes = 1, - .perf_ctr_bits = 48, - .event_mask = IVT_PMON_RAW_EVENT_MASK, - .box_ctl = SNBEP_PCI_PMON_BOX_CTL, - .ops = &ivt_uncore_irp_ops, - .format_group = &ivt_uncore_format_group, -}; - -static struct intel_uncore_ops ivt_uncore_qpi_ops = { - .init_box = ivt_uncore_pci_init_box, - .disable_box = snbep_uncore_pci_disable_box, - .enable_box = snbep_uncore_pci_enable_box, - .disable_event = snbep_uncore_pci_disable_event, - .enable_event = snbep_qpi_enable_event, - .read_counter = snbep_uncore_pci_read_counter, - .hw_config = snbep_qpi_hw_config, - .get_constraint = uncore_get_constraint, - .put_constraint = uncore_put_constraint, -}; - -static struct intel_uncore_type ivt_uncore_qpi = { - .name = "qpi", - .num_counters = 4, - .num_boxes = 3, - .perf_ctr_bits = 48, - .perf_ctr = SNBEP_PCI_PMON_CTR0, - .event_ctl = SNBEP_PCI_PMON_CTL0, - .event_mask = IVT_QPI_PCI_PMON_RAW_EVENT_MASK, - .box_ctl = SNBEP_PCI_PMON_BOX_CTL, - .num_shared_regs = 1, - .ops = &ivt_uncore_qpi_ops, - .format_group = &ivt_uncore_qpi_format_group, -}; - -static struct intel_uncore_type ivt_uncore_r2pcie = { - .name = "r2pcie", - .num_counters = 4, - .num_boxes = 1, - .perf_ctr_bits = 44, - .constraints = snbep_uncore_r2pcie_constraints, - IVT_UNCORE_PCI_COMMON_INIT(), -}; - -static struct intel_uncore_type ivt_uncore_r3qpi = { - .name = "r3qpi", - .num_counters = 3, - .num_boxes = 2, - .perf_ctr_bits = 44, - .constraints = snbep_uncore_r3qpi_constraints, - IVT_UNCORE_PCI_COMMON_INIT(), -}; - -enum { - IVT_PCI_UNCORE_HA, - IVT_PCI_UNCORE_IMC, - IVT_PCI_UNCORE_IRP, - IVT_PCI_UNCORE_QPI, - IVT_PCI_UNCORE_R2PCIE, - IVT_PCI_UNCORE_R3QPI, -}; - -static struct intel_uncore_type *ivt_pci_uncores[] = { - [IVT_PCI_UNCORE_HA] = &ivt_uncore_ha, - [IVT_PCI_UNCORE_IMC] = &ivt_uncore_imc, - [IVT_PCI_UNCORE_IRP] = &ivt_uncore_irp, - [IVT_PCI_UNCORE_QPI] = &ivt_uncore_qpi, - [IVT_PCI_UNCORE_R2PCIE] = &ivt_uncore_r2pcie, - [IVT_PCI_UNCORE_R3QPI] = &ivt_uncore_r3qpi, - NULL, -}; - -static const struct pci_device_id ivt_uncore_pci_ids[] = { - { /* Home Agent 0 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe30), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_HA, 0), - }, - { /* Home Agent 1 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe38), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_HA, 1), - }, - { /* MC0 Channel 0 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb4), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 0), - }, - { /* MC0 Channel 1 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb5), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 1), - }, - { /* MC0 Channel 3 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb0), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 2), - }, - { /* MC0 Channel 4 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb1), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 3), - }, - { /* MC1 Channel 0 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef4), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 4), - }, - { /* MC1 Channel 1 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef5), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 5), - }, - { /* MC1 Channel 3 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef0), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 6), - }, - { /* MC1 Channel 4 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef1), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 7), - }, - { /* IRP */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe39), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IRP, 0), - }, - { /* QPI0 Port 0 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe32), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 0), - }, - { /* QPI0 Port 1 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe33), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 1), - }, - { /* QPI1 Port 2 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3a), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 2), - }, - { /* R2PCIe */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe34), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R2PCIE, 0), - }, - { /* R3QPI0 Link 0 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe36), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 0), - }, - { /* R3QPI0 Link 1 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe37), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 1), - }, - { /* R3QPI1 Link 2 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3e), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 2), - }, - { /* QPI Port 0 filter */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe86), - .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, - SNBEP_PCI_QPI_PORT0_FILTER), - }, - { /* QPI Port 0 filter */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe96), - .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, - SNBEP_PCI_QPI_PORT1_FILTER), - }, - { /* end: all zeroes */ } -}; - -static struct pci_driver ivt_uncore_pci_driver = { - .name = "ivt_uncore", - .id_table = ivt_uncore_pci_ids, -}; -/* end of IvyTown uncore support */ - -/* Sandy Bridge uncore support */ -static void snb_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - - if (hwc->idx < UNCORE_PMC_IDX_FIXED) - wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN); - else - wrmsrl(hwc->config_base, SNB_UNC_CTL_EN); -} - -static void snb_uncore_msr_disable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - wrmsrl(event->hw.config_base, 0); -} - -static void snb_uncore_msr_init_box(struct intel_uncore_box *box) -{ - if (box->pmu->pmu_idx == 0) { - wrmsrl(SNB_UNC_PERF_GLOBAL_CTL, - SNB_UNC_GLOBAL_CTL_EN | SNB_UNC_GLOBAL_CTL_CORE_ALL); - } -} - -static struct uncore_event_desc snb_uncore_events[] = { - INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"), - { /* end: all zeroes */ }, -}; - -static struct attribute *snb_uncore_formats_attr[] = { - &format_attr_event.attr, - &format_attr_umask.attr, - &format_attr_edge.attr, - &format_attr_inv.attr, - &format_attr_cmask5.attr, - NULL, -}; - -static struct attribute_group snb_uncore_format_group = { - .name = "format", - .attrs = snb_uncore_formats_attr, -}; - -static struct intel_uncore_ops snb_uncore_msr_ops = { - .init_box = snb_uncore_msr_init_box, - .disable_event = snb_uncore_msr_disable_event, - .enable_event = snb_uncore_msr_enable_event, - .read_counter = uncore_msr_read_counter, -}; - -static struct event_constraint snb_uncore_cbox_constraints[] = { - UNCORE_EVENT_CONSTRAINT(0x80, 0x1), - UNCORE_EVENT_CONSTRAINT(0x83, 0x1), - EVENT_CONSTRAINT_END -}; - -static struct intel_uncore_type snb_uncore_cbox = { - .name = "cbox", - .num_counters = 2, - .num_boxes = 4, - .perf_ctr_bits = 44, - .fixed_ctr_bits = 48, - .perf_ctr = SNB_UNC_CBO_0_PER_CTR0, - .event_ctl = SNB_UNC_CBO_0_PERFEVTSEL0, - .fixed_ctr = SNB_UNC_FIXED_CTR, - .fixed_ctl = SNB_UNC_FIXED_CTR_CTRL, - .single_fixed = 1, - .event_mask = SNB_UNC_RAW_EVENT_MASK, - .msr_offset = SNB_UNC_CBO_MSR_OFFSET, - .constraints = snb_uncore_cbox_constraints, - .ops = &snb_uncore_msr_ops, - .format_group = &snb_uncore_format_group, - .event_descs = snb_uncore_events, -}; - -static struct intel_uncore_type *snb_msr_uncores[] = { - &snb_uncore_cbox, - NULL, -}; - -enum { - SNB_PCI_UNCORE_IMC, -}; - -static struct uncore_event_desc snb_uncore_imc_events[] = { - INTEL_UNCORE_EVENT_DESC(data_reads, "event=0x01"), - INTEL_UNCORE_EVENT_DESC(data_reads.scale, "6.103515625e-5"), - INTEL_UNCORE_EVENT_DESC(data_reads.unit, "MiB"), - - INTEL_UNCORE_EVENT_DESC(data_writes, "event=0x02"), - INTEL_UNCORE_EVENT_DESC(data_writes.scale, "6.103515625e-5"), - INTEL_UNCORE_EVENT_DESC(data_writes.unit, "MiB"), - - { /* end: all zeroes */ }, -}; - -#define SNB_UNCORE_PCI_IMC_EVENT_MASK 0xff -#define SNB_UNCORE_PCI_IMC_BAR_OFFSET 0x48 - -/* page size multiple covering all config regs */ -#define SNB_UNCORE_PCI_IMC_MAP_SIZE 0x6000 - -#define SNB_UNCORE_PCI_IMC_DATA_READS 0x1 -#define SNB_UNCORE_PCI_IMC_DATA_READS_BASE 0x5050 -#define SNB_UNCORE_PCI_IMC_DATA_WRITES 0x2 -#define SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE 0x5054 -#define SNB_UNCORE_PCI_IMC_CTR_BASE SNB_UNCORE_PCI_IMC_DATA_READS_BASE - -static struct attribute *snb_uncore_imc_formats_attr[] = { - &format_attr_event.attr, - NULL, -}; - -static struct attribute_group snb_uncore_imc_format_group = { - .name = "format", - .attrs = snb_uncore_imc_formats_attr, -}; - -static void snb_uncore_imc_init_box(struct intel_uncore_box *box) -{ - struct pci_dev *pdev = box->pci_dev; - int where = SNB_UNCORE_PCI_IMC_BAR_OFFSET; - resource_size_t addr; - u32 pci_dword; - - pci_read_config_dword(pdev, where, &pci_dword); - addr = pci_dword; - -#ifdef CONFIG_PHYS_ADDR_T_64BIT - pci_read_config_dword(pdev, where + 4, &pci_dword); - addr |= ((resource_size_t)pci_dword << 32); -#endif - - addr &= ~(PAGE_SIZE - 1); - - box->io_addr = ioremap(addr, SNB_UNCORE_PCI_IMC_MAP_SIZE); - box->hrtimer_duration = UNCORE_SNB_IMC_HRTIMER_INTERVAL; -} - -static void snb_uncore_imc_enable_box(struct intel_uncore_box *box) -{} - -static void snb_uncore_imc_disable_box(struct intel_uncore_box *box) -{} - -static void snb_uncore_imc_enable_event(struct intel_uncore_box *box, struct perf_event *event) -{} - -static void snb_uncore_imc_disable_event(struct intel_uncore_box *box, struct perf_event *event) -{} - -static u64 snb_uncore_imc_read_counter(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - - return (u64)*(unsigned int *)(box->io_addr + hwc->event_base); -} - -/* - * custom event_init() function because we define our own fixed, free - * running counters, so we do not want to conflict with generic uncore - * logic. Also simplifies processing - */ -static int snb_uncore_imc_event_init(struct perf_event *event) -{ - struct intel_uncore_pmu *pmu; - struct intel_uncore_box *box; - struct hw_perf_event *hwc = &event->hw; - u64 cfg = event->attr.config & SNB_UNCORE_PCI_IMC_EVENT_MASK; - int idx, base; - - if (event->attr.type != event->pmu->type) - return -ENOENT; - - pmu = uncore_event_to_pmu(event); - /* no device found for this pmu */ - if (pmu->func_id < 0) - return -ENOENT; - - /* Sampling not supported yet */ - if (hwc->sample_period) - 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; - - /* - * Place all uncore events for a particular physical package - * onto a single cpu - */ - if (event->cpu < 0) - return -EINVAL; - - /* check only supported bits are set */ - if (event->attr.config & ~SNB_UNCORE_PCI_IMC_EVENT_MASK) - return -EINVAL; - - box = uncore_pmu_to_box(pmu, event->cpu); - if (!box || box->cpu < 0) - return -EINVAL; - - event->cpu = box->cpu; - - event->hw.idx = -1; - event->hw.last_tag = ~0ULL; - event->hw.extra_reg.idx = EXTRA_REG_NONE; - event->hw.branch_reg.idx = EXTRA_REG_NONE; - /* - * check event is known (whitelist, determines counter) - */ - switch (cfg) { - case SNB_UNCORE_PCI_IMC_DATA_READS: - base = SNB_UNCORE_PCI_IMC_DATA_READS_BASE; - idx = UNCORE_PMC_IDX_FIXED; - break; - case SNB_UNCORE_PCI_IMC_DATA_WRITES: - base = SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE; - idx = UNCORE_PMC_IDX_FIXED + 1; - break; - default: - return -EINVAL; - } - - /* must be done before validate_group */ - event->hw.event_base = base; - event->hw.config = cfg; - event->hw.idx = idx; - - /* no group validation needed, we have free running counters */ - - return 0; -} - -static int snb_uncore_imc_hw_config(struct intel_uncore_box *box, struct perf_event *event) -{ - return 0; -} - -static void snb_uncore_imc_event_start(struct perf_event *event, int flags) -{ - struct intel_uncore_box *box = uncore_event_to_box(event); - u64 count; - - if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED))) - return; - - event->hw.state = 0; - box->n_active++; - - list_add_tail(&event->active_entry, &box->active_list); - - count = snb_uncore_imc_read_counter(box, event); - local64_set(&event->hw.prev_count, count); - - if (box->n_active == 1) - uncore_pmu_start_hrtimer(box); -} - -static void snb_uncore_imc_event_stop(struct perf_event *event, int flags) -{ - struct intel_uncore_box *box = uncore_event_to_box(event); - struct hw_perf_event *hwc = &event->hw; - - if (!(hwc->state & PERF_HES_STOPPED)) { - box->n_active--; - - WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); - hwc->state |= PERF_HES_STOPPED; - - list_del(&event->active_entry); - - if (box->n_active == 0) - uncore_pmu_cancel_hrtimer(box); - } - - if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) { - /* - * Drain the remaining delta count out of a event - * that we are disabling: - */ - uncore_perf_event_update(box, event); - hwc->state |= PERF_HES_UPTODATE; - } -} - -static int snb_uncore_imc_event_add(struct perf_event *event, int flags) -{ - struct intel_uncore_box *box = uncore_event_to_box(event); - struct hw_perf_event *hwc = &event->hw; - - if (!box) - return -ENODEV; - - hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED; - if (!(flags & PERF_EF_START)) - hwc->state |= PERF_HES_ARCH; - - snb_uncore_imc_event_start(event, 0); - - box->n_events++; - - return 0; -} - -static void snb_uncore_imc_event_del(struct perf_event *event, int flags) -{ - struct intel_uncore_box *box = uncore_event_to_box(event); - int i; - - snb_uncore_imc_event_stop(event, PERF_EF_UPDATE); - - for (i = 0; i < box->n_events; i++) { - if (event == box->event_list[i]) { - --box->n_events; - break; - } - } -} - -static int snb_pci2phy_map_init(int devid) -{ - struct pci_dev *dev = NULL; - int bus; - - dev = pci_get_device(PCI_VENDOR_ID_INTEL, devid, dev); - if (!dev) - return -ENOTTY; - - bus = dev->bus->number; - - pcibus_to_physid[bus] = 0; - - pci_dev_put(dev); - - return 0; -} - -static struct pmu snb_uncore_imc_pmu = { - .task_ctx_nr = perf_invalid_context, - .event_init = snb_uncore_imc_event_init, - .add = snb_uncore_imc_event_add, - .del = snb_uncore_imc_event_del, - .start = snb_uncore_imc_event_start, - .stop = snb_uncore_imc_event_stop, - .read = uncore_pmu_event_read, -}; - -static struct intel_uncore_ops snb_uncore_imc_ops = { - .init_box = snb_uncore_imc_init_box, - .enable_box = snb_uncore_imc_enable_box, - .disable_box = snb_uncore_imc_disable_box, - .disable_event = snb_uncore_imc_disable_event, - .enable_event = snb_uncore_imc_enable_event, - .hw_config = snb_uncore_imc_hw_config, - .read_counter = snb_uncore_imc_read_counter, -}; - -static struct intel_uncore_type snb_uncore_imc = { - .name = "imc", - .num_counters = 2, - .num_boxes = 1, - .fixed_ctr_bits = 32, - .fixed_ctr = SNB_UNCORE_PCI_IMC_CTR_BASE, - .event_descs = snb_uncore_imc_events, - .format_group = &snb_uncore_imc_format_group, - .perf_ctr = SNB_UNCORE_PCI_IMC_DATA_READS_BASE, - .event_mask = SNB_UNCORE_PCI_IMC_EVENT_MASK, - .ops = &snb_uncore_imc_ops, - .pmu = &snb_uncore_imc_pmu, -}; - -static struct intel_uncore_type *snb_pci_uncores[] = { - [SNB_PCI_UNCORE_IMC] = &snb_uncore_imc, - NULL, -}; - -static const struct pci_device_id snb_uncore_pci_ids[] = { - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SNB_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* end: all zeroes */ }, -}; - -static const struct pci_device_id ivb_uncore_pci_ids[] = { - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IVB_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* end: all zeroes */ }, -}; - -static const struct pci_device_id hsw_uncore_pci_ids[] = { - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_HSW_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* end: all zeroes */ }, -}; - -static struct pci_driver snb_uncore_pci_driver = { - .name = "snb_uncore", - .id_table = snb_uncore_pci_ids, -}; - -static struct pci_driver ivb_uncore_pci_driver = { - .name = "ivb_uncore", - .id_table = ivb_uncore_pci_ids, -}; - -static struct pci_driver hsw_uncore_pci_driver = { - .name = "hsw_uncore", - .id_table = hsw_uncore_pci_ids, -}; - -/* end of Sandy Bridge uncore support */ - -/* Nehalem uncore support */ -static void nhm_uncore_msr_disable_box(struct intel_uncore_box *box) -{ - wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, 0); -} - -static void nhm_uncore_msr_enable_box(struct intel_uncore_box *box) -{ - wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, NHM_UNC_GLOBAL_CTL_EN_PC_ALL | NHM_UNC_GLOBAL_CTL_EN_FC); -} - -static void nhm_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - - if (hwc->idx < UNCORE_PMC_IDX_FIXED) - wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN); - else - wrmsrl(hwc->config_base, NHM_UNC_FIXED_CTR_CTL_EN); -} - -static struct attribute *nhm_uncore_formats_attr[] = { - &format_attr_event.attr, - &format_attr_umask.attr, - &format_attr_edge.attr, - &format_attr_inv.attr, - &format_attr_cmask8.attr, - NULL, -}; - -static struct attribute_group nhm_uncore_format_group = { - .name = "format", - .attrs = nhm_uncore_formats_attr, -}; - -static struct uncore_event_desc nhm_uncore_events[] = { - INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"), - INTEL_UNCORE_EVENT_DESC(qmc_writes_full_any, "event=0x2f,umask=0x0f"), - INTEL_UNCORE_EVENT_DESC(qmc_normal_reads_any, "event=0x2c,umask=0x0f"), - INTEL_UNCORE_EVENT_DESC(qhl_request_ioh_reads, "event=0x20,umask=0x01"), - INTEL_UNCORE_EVENT_DESC(qhl_request_ioh_writes, "event=0x20,umask=0x02"), - INTEL_UNCORE_EVENT_DESC(qhl_request_remote_reads, "event=0x20,umask=0x04"), - INTEL_UNCORE_EVENT_DESC(qhl_request_remote_writes, "event=0x20,umask=0x08"), - INTEL_UNCORE_EVENT_DESC(qhl_request_local_reads, "event=0x20,umask=0x10"), - INTEL_UNCORE_EVENT_DESC(qhl_request_local_writes, "event=0x20,umask=0x20"), - { /* end: all zeroes */ }, -}; - -static struct intel_uncore_ops nhm_uncore_msr_ops = { - .disable_box = nhm_uncore_msr_disable_box, - .enable_box = nhm_uncore_msr_enable_box, - .disable_event = snb_uncore_msr_disable_event, - .enable_event = nhm_uncore_msr_enable_event, - .read_counter = uncore_msr_read_counter, -}; - -static struct intel_uncore_type nhm_uncore = { - .name = "", - .num_counters = 8, - .num_boxes = 1, - .perf_ctr_bits = 48, - .fixed_ctr_bits = 48, - .event_ctl = NHM_UNC_PERFEVTSEL0, - .perf_ctr = NHM_UNC_UNCORE_PMC0, - .fixed_ctr = NHM_UNC_FIXED_CTR, - .fixed_ctl = NHM_UNC_FIXED_CTR_CTRL, - .event_mask = NHM_UNC_RAW_EVENT_MASK, - .event_descs = nhm_uncore_events, - .ops = &nhm_uncore_msr_ops, - .format_group = &nhm_uncore_format_group, -}; - -static struct intel_uncore_type *nhm_msr_uncores[] = { - &nhm_uncore, - NULL, -}; -/* end of Nehalem uncore support */ - -/* Nehalem-EX uncore support */ -DEFINE_UNCORE_FORMAT_ATTR(event5, event, "config:1-5"); -DEFINE_UNCORE_FORMAT_ATTR(counter, counter, "config:6-7"); -DEFINE_UNCORE_FORMAT_ATTR(match, match, "config1:0-63"); -DEFINE_UNCORE_FORMAT_ATTR(mask, mask, "config2:0-63"); - -static void nhmex_uncore_msr_init_box(struct intel_uncore_box *box) -{ - wrmsrl(NHMEX_U_MSR_PMON_GLOBAL_CTL, NHMEX_U_PMON_GLOBAL_EN_ALL); -} - -static void nhmex_uncore_msr_disable_box(struct intel_uncore_box *box) -{ - unsigned msr = uncore_msr_box_ctl(box); - u64 config; - - if (msr) { - rdmsrl(msr, config); - config &= ~((1ULL << uncore_num_counters(box)) - 1); - /* WBox has a fixed counter */ - if (uncore_msr_fixed_ctl(box)) - config &= ~NHMEX_W_PMON_GLOBAL_FIXED_EN; - wrmsrl(msr, config); - } -} - -static void nhmex_uncore_msr_enable_box(struct intel_uncore_box *box) -{ - unsigned msr = uncore_msr_box_ctl(box); - u64 config; - - if (msr) { - rdmsrl(msr, config); - config |= (1ULL << uncore_num_counters(box)) - 1; - /* WBox has a fixed counter */ - if (uncore_msr_fixed_ctl(box)) - config |= NHMEX_W_PMON_GLOBAL_FIXED_EN; - wrmsrl(msr, config); - } -} - -static void nhmex_uncore_msr_disable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - wrmsrl(event->hw.config_base, 0); -} - -static void nhmex_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - - if (hwc->idx >= UNCORE_PMC_IDX_FIXED) - wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0); - else if (box->pmu->type->event_mask & NHMEX_PMON_CTL_EN_BIT0) - wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22); - else - wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0); -} - -#define NHMEX_UNCORE_OPS_COMMON_INIT() \ - .init_box = nhmex_uncore_msr_init_box, \ - .disable_box = nhmex_uncore_msr_disable_box, \ - .enable_box = nhmex_uncore_msr_enable_box, \ - .disable_event = nhmex_uncore_msr_disable_event, \ - .read_counter = uncore_msr_read_counter - -static struct intel_uncore_ops nhmex_uncore_ops = { - NHMEX_UNCORE_OPS_COMMON_INIT(), - .enable_event = nhmex_uncore_msr_enable_event, -}; - -static struct attribute *nhmex_uncore_ubox_formats_attr[] = { - &format_attr_event.attr, - &format_attr_edge.attr, - NULL, -}; - -static struct attribute_group nhmex_uncore_ubox_format_group = { - .name = "format", - .attrs = nhmex_uncore_ubox_formats_attr, -}; - -static struct intel_uncore_type nhmex_uncore_ubox = { - .name = "ubox", - .num_counters = 1, - .num_boxes = 1, - .perf_ctr_bits = 48, - .event_ctl = NHMEX_U_MSR_PMON_EV_SEL, - .perf_ctr = NHMEX_U_MSR_PMON_CTR, - .event_mask = NHMEX_U_PMON_RAW_EVENT_MASK, - .box_ctl = NHMEX_U_MSR_PMON_GLOBAL_CTL, - .ops = &nhmex_uncore_ops, - .format_group = &nhmex_uncore_ubox_format_group -}; - -static struct attribute *nhmex_uncore_cbox_formats_attr[] = { - &format_attr_event.attr, - &format_attr_umask.attr, - &format_attr_edge.attr, - &format_attr_inv.attr, - &format_attr_thresh8.attr, - NULL, -}; - -static struct attribute_group nhmex_uncore_cbox_format_group = { - .name = "format", - .attrs = nhmex_uncore_cbox_formats_attr, -}; - -/* msr offset for each instance of cbox */ -static unsigned nhmex_cbox_msr_offsets[] = { - 0x0, 0x80, 0x40, 0xc0, 0x20, 0xa0, 0x60, 0xe0, 0x240, 0x2c0, -}; - -static struct intel_uncore_type nhmex_uncore_cbox = { - .name = "cbox", - .num_counters = 6, - .num_boxes = 10, - .perf_ctr_bits = 48, - .event_ctl = NHMEX_C0_MSR_PMON_EV_SEL0, - .perf_ctr = NHMEX_C0_MSR_PMON_CTR0, - .event_mask = NHMEX_PMON_RAW_EVENT_MASK, - .box_ctl = NHMEX_C0_MSR_PMON_GLOBAL_CTL, - .msr_offsets = nhmex_cbox_msr_offsets, - .pair_ctr_ctl = 1, - .ops = &nhmex_uncore_ops, - .format_group = &nhmex_uncore_cbox_format_group -}; - -static struct uncore_event_desc nhmex_uncore_wbox_events[] = { - INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0"), - { /* end: all zeroes */ }, -}; - -static struct intel_uncore_type nhmex_uncore_wbox = { - .name = "wbox", - .num_counters = 4, - .num_boxes = 1, - .perf_ctr_bits = 48, - .event_ctl = NHMEX_W_MSR_PMON_CNT0, - .perf_ctr = NHMEX_W_MSR_PMON_EVT_SEL0, - .fixed_ctr = NHMEX_W_MSR_PMON_FIXED_CTR, - .fixed_ctl = NHMEX_W_MSR_PMON_FIXED_CTL, - .event_mask = NHMEX_PMON_RAW_EVENT_MASK, - .box_ctl = NHMEX_W_MSR_GLOBAL_CTL, - .pair_ctr_ctl = 1, - .event_descs = nhmex_uncore_wbox_events, - .ops = &nhmex_uncore_ops, - .format_group = &nhmex_uncore_cbox_format_group -}; - -static int nhmex_bbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - struct hw_perf_event_extra *reg2 = &hwc->branch_reg; - int ctr, ev_sel; - - ctr = (hwc->config & NHMEX_B_PMON_CTR_MASK) >> - NHMEX_B_PMON_CTR_SHIFT; - ev_sel = (hwc->config & NHMEX_B_PMON_CTL_EV_SEL_MASK) >> - NHMEX_B_PMON_CTL_EV_SEL_SHIFT; - - /* events that do not use the match/mask registers */ - if ((ctr == 0 && ev_sel > 0x3) || (ctr == 1 && ev_sel > 0x6) || - (ctr == 2 && ev_sel != 0x4) || ctr == 3) - return 0; - - if (box->pmu->pmu_idx == 0) - reg1->reg = NHMEX_B0_MSR_MATCH; - else - reg1->reg = NHMEX_B1_MSR_MATCH; - reg1->idx = 0; - reg1->config = event->attr.config1; - reg2->config = event->attr.config2; - return 0; -} - -static void nhmex_bbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - struct hw_perf_event_extra *reg2 = &hwc->branch_reg; - - if (reg1->idx != EXTRA_REG_NONE) { - wrmsrl(reg1->reg, reg1->config); - wrmsrl(reg1->reg + 1, reg2->config); - } - wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 | - (hwc->config & NHMEX_B_PMON_CTL_EV_SEL_MASK)); -} - -/* - * The Bbox has 4 counters, but each counter monitors different events. - * Use bits 6-7 in the event config to select counter. - */ -static struct event_constraint nhmex_uncore_bbox_constraints[] = { - EVENT_CONSTRAINT(0 , 1, 0xc0), - EVENT_CONSTRAINT(0x40, 2, 0xc0), - EVENT_CONSTRAINT(0x80, 4, 0xc0), - EVENT_CONSTRAINT(0xc0, 8, 0xc0), - EVENT_CONSTRAINT_END, -}; - -static struct attribute *nhmex_uncore_bbox_formats_attr[] = { - &format_attr_event5.attr, - &format_attr_counter.attr, - &format_attr_match.attr, - &format_attr_mask.attr, - NULL, -}; - -static struct attribute_group nhmex_uncore_bbox_format_group = { - .name = "format", - .attrs = nhmex_uncore_bbox_formats_attr, -}; - -static struct intel_uncore_ops nhmex_uncore_bbox_ops = { - NHMEX_UNCORE_OPS_COMMON_INIT(), - .enable_event = nhmex_bbox_msr_enable_event, - .hw_config = nhmex_bbox_hw_config, - .get_constraint = uncore_get_constraint, - .put_constraint = uncore_put_constraint, -}; - -static struct intel_uncore_type nhmex_uncore_bbox = { - .name = "bbox", - .num_counters = 4, - .num_boxes = 2, - .perf_ctr_bits = 48, - .event_ctl = NHMEX_B0_MSR_PMON_CTL0, - .perf_ctr = NHMEX_B0_MSR_PMON_CTR0, - .event_mask = NHMEX_B_PMON_RAW_EVENT_MASK, - .box_ctl = NHMEX_B0_MSR_PMON_GLOBAL_CTL, - .msr_offset = NHMEX_B_MSR_OFFSET, - .pair_ctr_ctl = 1, - .num_shared_regs = 1, - .constraints = nhmex_uncore_bbox_constraints, - .ops = &nhmex_uncore_bbox_ops, - .format_group = &nhmex_uncore_bbox_format_group -}; - -static int nhmex_sbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - struct hw_perf_event_extra *reg2 = &hwc->branch_reg; - - /* only TO_R_PROG_EV event uses the match/mask register */ - if ((hwc->config & NHMEX_PMON_CTL_EV_SEL_MASK) != - NHMEX_S_EVENT_TO_R_PROG_EV) - return 0; - - if (box->pmu->pmu_idx == 0) - reg1->reg = NHMEX_S0_MSR_MM_CFG; - else - reg1->reg = NHMEX_S1_MSR_MM_CFG; - reg1->idx = 0; - reg1->config = event->attr.config1; - reg2->config = event->attr.config2; - return 0; -} - -static void nhmex_sbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - struct hw_perf_event_extra *reg2 = &hwc->branch_reg; - - if (reg1->idx != EXTRA_REG_NONE) { - wrmsrl(reg1->reg, 0); - wrmsrl(reg1->reg + 1, reg1->config); - wrmsrl(reg1->reg + 2, reg2->config); - wrmsrl(reg1->reg, NHMEX_S_PMON_MM_CFG_EN); - } - wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22); -} - -static struct attribute *nhmex_uncore_sbox_formats_attr[] = { - &format_attr_event.attr, - &format_attr_umask.attr, - &format_attr_edge.attr, - &format_attr_inv.attr, - &format_attr_thresh8.attr, - &format_attr_match.attr, - &format_attr_mask.attr, - NULL, -}; - -static struct attribute_group nhmex_uncore_sbox_format_group = { - .name = "format", - .attrs = nhmex_uncore_sbox_formats_attr, -}; - -static struct intel_uncore_ops nhmex_uncore_sbox_ops = { - NHMEX_UNCORE_OPS_COMMON_INIT(), - .enable_event = nhmex_sbox_msr_enable_event, - .hw_config = nhmex_sbox_hw_config, - .get_constraint = uncore_get_constraint, - .put_constraint = uncore_put_constraint, -}; - -static struct intel_uncore_type nhmex_uncore_sbox = { - .name = "sbox", - .num_counters = 4, - .num_boxes = 2, - .perf_ctr_bits = 48, - .event_ctl = NHMEX_S0_MSR_PMON_CTL0, - .perf_ctr = NHMEX_S0_MSR_PMON_CTR0, - .event_mask = NHMEX_PMON_RAW_EVENT_MASK, - .box_ctl = NHMEX_S0_MSR_PMON_GLOBAL_CTL, - .msr_offset = NHMEX_S_MSR_OFFSET, - .pair_ctr_ctl = 1, - .num_shared_regs = 1, - .ops = &nhmex_uncore_sbox_ops, - .format_group = &nhmex_uncore_sbox_format_group -}; - -enum { - EXTRA_REG_NHMEX_M_FILTER, - EXTRA_REG_NHMEX_M_DSP, - EXTRA_REG_NHMEX_M_ISS, - EXTRA_REG_NHMEX_M_MAP, - EXTRA_REG_NHMEX_M_MSC_THR, - EXTRA_REG_NHMEX_M_PGT, - EXTRA_REG_NHMEX_M_PLD, - EXTRA_REG_NHMEX_M_ZDP_CTL_FVC, -}; - -static struct extra_reg nhmex_uncore_mbox_extra_regs[] = { - MBOX_INC_SEL_EXTAR_REG(0x0, DSP), - MBOX_INC_SEL_EXTAR_REG(0x4, MSC_THR), - MBOX_INC_SEL_EXTAR_REG(0x5, MSC_THR), - MBOX_INC_SEL_EXTAR_REG(0x9, ISS), - /* event 0xa uses two extra registers */ - MBOX_INC_SEL_EXTAR_REG(0xa, ISS), - MBOX_INC_SEL_EXTAR_REG(0xa, PLD), - MBOX_INC_SEL_EXTAR_REG(0xb, PLD), - /* events 0xd ~ 0x10 use the same extra register */ - MBOX_INC_SEL_EXTAR_REG(0xd, ZDP_CTL_FVC), - MBOX_INC_SEL_EXTAR_REG(0xe, ZDP_CTL_FVC), - MBOX_INC_SEL_EXTAR_REG(0xf, ZDP_CTL_FVC), - MBOX_INC_SEL_EXTAR_REG(0x10, ZDP_CTL_FVC), - MBOX_INC_SEL_EXTAR_REG(0x16, PGT), - MBOX_SET_FLAG_SEL_EXTRA_REG(0x0, DSP), - MBOX_SET_FLAG_SEL_EXTRA_REG(0x1, ISS), - MBOX_SET_FLAG_SEL_EXTRA_REG(0x5, PGT), - MBOX_SET_FLAG_SEL_EXTRA_REG(0x6, MAP), - EVENT_EXTRA_END -}; - -/* Nehalem-EX or Westmere-EX ? */ -static bool uncore_nhmex; - -static bool nhmex_mbox_get_shared_reg(struct intel_uncore_box *box, int idx, u64 config) -{ - struct intel_uncore_extra_reg *er; - unsigned long flags; - bool ret = false; - u64 mask; - - if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) { - er = &box->shared_regs[idx]; - raw_spin_lock_irqsave(&er->lock, flags); - if (!atomic_read(&er->ref) || er->config == config) { - atomic_inc(&er->ref); - er->config = config; - ret = true; - } - raw_spin_unlock_irqrestore(&er->lock, flags); - - return ret; - } - /* - * The ZDP_CTL_FVC MSR has 4 fields which are used to control - * events 0xd ~ 0x10. Besides these 4 fields, there are additional - * fields which are shared. - */ - idx -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC; - if (WARN_ON_ONCE(idx >= 4)) - return false; - - /* mask of the shared fields */ - if (uncore_nhmex) - mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK; - else - mask = WSMEX_M_PMON_ZDP_CTL_FVC_MASK; - er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC]; - - raw_spin_lock_irqsave(&er->lock, flags); - /* add mask of the non-shared field if it's in use */ - if (__BITS_VALUE(atomic_read(&er->ref), idx, 8)) { - if (uncore_nhmex) - mask |= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); - else - mask |= WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); - } - - if (!atomic_read(&er->ref) || !((er->config ^ config) & mask)) { - atomic_add(1 << (idx * 8), &er->ref); - if (uncore_nhmex) - mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK | - NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); - else - mask = WSMEX_M_PMON_ZDP_CTL_FVC_MASK | - WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); - er->config &= ~mask; - er->config |= (config & mask); - ret = true; - } - raw_spin_unlock_irqrestore(&er->lock, flags); - - return ret; -} - -static void nhmex_mbox_put_shared_reg(struct intel_uncore_box *box, int idx) -{ - struct intel_uncore_extra_reg *er; - - if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) { - er = &box->shared_regs[idx]; - atomic_dec(&er->ref); - return; - } - - idx -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC; - er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC]; - atomic_sub(1 << (idx * 8), &er->ref); -} - -static u64 nhmex_mbox_alter_er(struct perf_event *event, int new_idx, bool modify) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - u64 idx, orig_idx = __BITS_VALUE(reg1->idx, 0, 8); - u64 config = reg1->config; - - /* get the non-shared control bits and shift them */ - idx = orig_idx - EXTRA_REG_NHMEX_M_ZDP_CTL_FVC; - if (uncore_nhmex) - config &= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); - else - config &= WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); - if (new_idx > orig_idx) { - idx = new_idx - orig_idx; - config <<= 3 * idx; - } else { - idx = orig_idx - new_idx; - config >>= 3 * idx; - } - - /* add the shared control bits back */ - if (uncore_nhmex) - config |= NHMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config; - else - config |= WSMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config; - config |= NHMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config; - if (modify) { - /* adjust the main event selector */ - if (new_idx > orig_idx) - hwc->config += idx << NHMEX_M_PMON_CTL_INC_SEL_SHIFT; - else - hwc->config -= idx << NHMEX_M_PMON_CTL_INC_SEL_SHIFT; - reg1->config = config; - reg1->idx = ~0xff | new_idx; - } - return config; -} - -static struct event_constraint * -nhmex_mbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; - struct hw_perf_event_extra *reg2 = &event->hw.branch_reg; - int i, idx[2], alloc = 0; - u64 config1 = reg1->config; - - idx[0] = __BITS_VALUE(reg1->idx, 0, 8); - idx[1] = __BITS_VALUE(reg1->idx, 1, 8); -again: - for (i = 0; i < 2; i++) { - if (!uncore_box_is_fake(box) && (reg1->alloc & (0x1 << i))) - idx[i] = 0xff; - - if (idx[i] == 0xff) - continue; - - if (!nhmex_mbox_get_shared_reg(box, idx[i], - __BITS_VALUE(config1, i, 32))) - goto fail; - alloc |= (0x1 << i); - } - - /* for the match/mask registers */ - if (reg2->idx != EXTRA_REG_NONE && - (uncore_box_is_fake(box) || !reg2->alloc) && - !nhmex_mbox_get_shared_reg(box, reg2->idx, reg2->config)) - goto fail; - - /* - * If it's a fake box -- as per validate_{group,event}() we - * shouldn't touch event state and we can avoid doing so - * since both will only call get_event_constraints() once - * on each event, this avoids the need for reg->alloc. - */ - if (!uncore_box_is_fake(box)) { - if (idx[0] != 0xff && idx[0] != __BITS_VALUE(reg1->idx, 0, 8)) - nhmex_mbox_alter_er(event, idx[0], true); - reg1->alloc |= alloc; - if (reg2->idx != EXTRA_REG_NONE) - reg2->alloc = 1; - } - return NULL; -fail: - if (idx[0] != 0xff && !(alloc & 0x1) && - idx[0] >= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) { - /* - * events 0xd ~ 0x10 are functional identical, but are - * controlled by different fields in the ZDP_CTL_FVC - * register. If we failed to take one field, try the - * rest 3 choices. - */ - BUG_ON(__BITS_VALUE(reg1->idx, 1, 8) != 0xff); - idx[0] -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC; - idx[0] = (idx[0] + 1) % 4; - idx[0] += EXTRA_REG_NHMEX_M_ZDP_CTL_FVC; - if (idx[0] != __BITS_VALUE(reg1->idx, 0, 8)) { - config1 = nhmex_mbox_alter_er(event, idx[0], false); - goto again; - } - } - - if (alloc & 0x1) - nhmex_mbox_put_shared_reg(box, idx[0]); - if (alloc & 0x2) - nhmex_mbox_put_shared_reg(box, idx[1]); - return &constraint_empty; -} - -static void nhmex_mbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; - struct hw_perf_event_extra *reg2 = &event->hw.branch_reg; - - if (uncore_box_is_fake(box)) - return; - - if (reg1->alloc & 0x1) - nhmex_mbox_put_shared_reg(box, __BITS_VALUE(reg1->idx, 0, 8)); - if (reg1->alloc & 0x2) - nhmex_mbox_put_shared_reg(box, __BITS_VALUE(reg1->idx, 1, 8)); - reg1->alloc = 0; - - if (reg2->alloc) { - nhmex_mbox_put_shared_reg(box, reg2->idx); - reg2->alloc = 0; - } -} - -static int nhmex_mbox_extra_reg_idx(struct extra_reg *er) -{ - if (er->idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) - return er->idx; - return er->idx + (er->event >> NHMEX_M_PMON_CTL_INC_SEL_SHIFT) - 0xd; -} - -static int nhmex_mbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) -{ - struct intel_uncore_type *type = box->pmu->type; - struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; - struct hw_perf_event_extra *reg2 = &event->hw.branch_reg; - struct extra_reg *er; - unsigned msr; - int reg_idx = 0; - /* - * The mbox events may require 2 extra MSRs at the most. But only - * the lower 32 bits in these MSRs are significant, so we can use - * config1 to pass two MSRs' config. - */ - for (er = nhmex_uncore_mbox_extra_regs; er->msr; er++) { - if (er->event != (event->hw.config & er->config_mask)) - continue; - if (event->attr.config1 & ~er->valid_mask) - return -EINVAL; - - msr = er->msr + type->msr_offset * box->pmu->pmu_idx; - if (WARN_ON_ONCE(msr >= 0xffff || er->idx >= 0xff)) - return -EINVAL; - - /* always use the 32~63 bits to pass the PLD config */ - if (er->idx == EXTRA_REG_NHMEX_M_PLD) - reg_idx = 1; - else if (WARN_ON_ONCE(reg_idx > 0)) - return -EINVAL; - - reg1->idx &= ~(0xff << (reg_idx * 8)); - reg1->reg &= ~(0xffff << (reg_idx * 16)); - reg1->idx |= nhmex_mbox_extra_reg_idx(er) << (reg_idx * 8); - reg1->reg |= msr << (reg_idx * 16); - reg1->config = event->attr.config1; - reg_idx++; - } - /* - * The mbox only provides ability to perform address matching - * for the PLD events. - */ - if (reg_idx == 2) { - reg2->idx = EXTRA_REG_NHMEX_M_FILTER; - if (event->attr.config2 & NHMEX_M_PMON_MM_CFG_EN) - reg2->config = event->attr.config2; - else - reg2->config = ~0ULL; - if (box->pmu->pmu_idx == 0) - reg2->reg = NHMEX_M0_MSR_PMU_MM_CFG; - else - reg2->reg = NHMEX_M1_MSR_PMU_MM_CFG; - } - return 0; -} - -static u64 nhmex_mbox_shared_reg_config(struct intel_uncore_box *box, int idx) -{ - struct intel_uncore_extra_reg *er; - unsigned long flags; - u64 config; - - if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) - return box->shared_regs[idx].config; - - er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC]; - raw_spin_lock_irqsave(&er->lock, flags); - config = er->config; - raw_spin_unlock_irqrestore(&er->lock, flags); - return config; -} - -static void nhmex_mbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - struct hw_perf_event_extra *reg2 = &hwc->branch_reg; - int idx; - - idx = __BITS_VALUE(reg1->idx, 0, 8); - if (idx != 0xff) - wrmsrl(__BITS_VALUE(reg1->reg, 0, 16), - nhmex_mbox_shared_reg_config(box, idx)); - idx = __BITS_VALUE(reg1->idx, 1, 8); - if (idx != 0xff) - wrmsrl(__BITS_VALUE(reg1->reg, 1, 16), - nhmex_mbox_shared_reg_config(box, idx)); - - if (reg2->idx != EXTRA_REG_NONE) { - wrmsrl(reg2->reg, 0); - if (reg2->config != ~0ULL) { - wrmsrl(reg2->reg + 1, - reg2->config & NHMEX_M_PMON_ADDR_MATCH_MASK); - wrmsrl(reg2->reg + 2, NHMEX_M_PMON_ADDR_MASK_MASK & - (reg2->config >> NHMEX_M_PMON_ADDR_MASK_SHIFT)); - wrmsrl(reg2->reg, NHMEX_M_PMON_MM_CFG_EN); - } - } - - wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0); -} - -DEFINE_UNCORE_FORMAT_ATTR(count_mode, count_mode, "config:2-3"); -DEFINE_UNCORE_FORMAT_ATTR(storage_mode, storage_mode, "config:4-5"); -DEFINE_UNCORE_FORMAT_ATTR(wrap_mode, wrap_mode, "config:6"); -DEFINE_UNCORE_FORMAT_ATTR(flag_mode, flag_mode, "config:7"); -DEFINE_UNCORE_FORMAT_ATTR(inc_sel, inc_sel, "config:9-13"); -DEFINE_UNCORE_FORMAT_ATTR(set_flag_sel, set_flag_sel, "config:19-21"); -DEFINE_UNCORE_FORMAT_ATTR(filter_cfg_en, filter_cfg_en, "config2:63"); -DEFINE_UNCORE_FORMAT_ATTR(filter_match, filter_match, "config2:0-33"); -DEFINE_UNCORE_FORMAT_ATTR(filter_mask, filter_mask, "config2:34-61"); -DEFINE_UNCORE_FORMAT_ATTR(dsp, dsp, "config1:0-31"); -DEFINE_UNCORE_FORMAT_ATTR(thr, thr, "config1:0-31"); -DEFINE_UNCORE_FORMAT_ATTR(fvc, fvc, "config1:0-31"); -DEFINE_UNCORE_FORMAT_ATTR(pgt, pgt, "config1:0-31"); -DEFINE_UNCORE_FORMAT_ATTR(map, map, "config1:0-31"); -DEFINE_UNCORE_FORMAT_ATTR(iss, iss, "config1:0-31"); -DEFINE_UNCORE_FORMAT_ATTR(pld, pld, "config1:32-63"); - -static struct attribute *nhmex_uncore_mbox_formats_attr[] = { - &format_attr_count_mode.attr, - &format_attr_storage_mode.attr, - &format_attr_wrap_mode.attr, - &format_attr_flag_mode.attr, - &format_attr_inc_sel.attr, - &format_attr_set_flag_sel.attr, - &format_attr_filter_cfg_en.attr, - &format_attr_filter_match.attr, - &format_attr_filter_mask.attr, - &format_attr_dsp.attr, - &format_attr_thr.attr, - &format_attr_fvc.attr, - &format_attr_pgt.attr, - &format_attr_map.attr, - &format_attr_iss.attr, - &format_attr_pld.attr, - NULL, -}; - -static struct attribute_group nhmex_uncore_mbox_format_group = { - .name = "format", - .attrs = nhmex_uncore_mbox_formats_attr, -}; - -static struct uncore_event_desc nhmex_uncore_mbox_events[] = { - INTEL_UNCORE_EVENT_DESC(bbox_cmds_read, "inc_sel=0xd,fvc=0x2800"), - INTEL_UNCORE_EVENT_DESC(bbox_cmds_write, "inc_sel=0xd,fvc=0x2820"), - { /* end: all zeroes */ }, -}; - -static struct uncore_event_desc wsmex_uncore_mbox_events[] = { - INTEL_UNCORE_EVENT_DESC(bbox_cmds_read, "inc_sel=0xd,fvc=0x5000"), - INTEL_UNCORE_EVENT_DESC(bbox_cmds_write, "inc_sel=0xd,fvc=0x5040"), - { /* end: all zeroes */ }, -}; - -static struct intel_uncore_ops nhmex_uncore_mbox_ops = { - NHMEX_UNCORE_OPS_COMMON_INIT(), - .enable_event = nhmex_mbox_msr_enable_event, - .hw_config = nhmex_mbox_hw_config, - .get_constraint = nhmex_mbox_get_constraint, - .put_constraint = nhmex_mbox_put_constraint, -}; - -static struct intel_uncore_type nhmex_uncore_mbox = { - .name = "mbox", - .num_counters = 6, - .num_boxes = 2, - .perf_ctr_bits = 48, - .event_ctl = NHMEX_M0_MSR_PMU_CTL0, - .perf_ctr = NHMEX_M0_MSR_PMU_CNT0, - .event_mask = NHMEX_M_PMON_RAW_EVENT_MASK, - .box_ctl = NHMEX_M0_MSR_GLOBAL_CTL, - .msr_offset = NHMEX_M_MSR_OFFSET, - .pair_ctr_ctl = 1, - .num_shared_regs = 8, - .event_descs = nhmex_uncore_mbox_events, - .ops = &nhmex_uncore_mbox_ops, - .format_group = &nhmex_uncore_mbox_format_group, -}; - -static void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - - /* adjust the main event selector and extra register index */ - if (reg1->idx % 2) { - reg1->idx--; - hwc->config -= 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT; - } else { - reg1->idx++; - hwc->config += 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT; - } - - /* adjust extra register config */ - switch (reg1->idx % 6) { - case 2: - /* shift the 8~15 bits to the 0~7 bits */ - reg1->config >>= 8; - break; - case 3: - /* shift the 0~7 bits to the 8~15 bits */ - reg1->config <<= 8; - break; - }; -} - -/* - * Each rbox has 4 event set which monitor PQI port 0~3 or 4~7. - * An event set consists of 6 events, the 3rd and 4th events in - * an event set use the same extra register. So an event set uses - * 5 extra registers. - */ -static struct event_constraint * -nhmex_rbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - struct hw_perf_event_extra *reg2 = &hwc->branch_reg; - struct intel_uncore_extra_reg *er; - unsigned long flags; - int idx, er_idx; - u64 config1; - bool ok = false; - - if (!uncore_box_is_fake(box) && reg1->alloc) - return NULL; - - idx = reg1->idx % 6; - config1 = reg1->config; -again: - er_idx = idx; - /* the 3rd and 4th events use the same extra register */ - if (er_idx > 2) - er_idx--; - er_idx += (reg1->idx / 6) * 5; - - er = &box->shared_regs[er_idx]; - raw_spin_lock_irqsave(&er->lock, flags); - if (idx < 2) { - if (!atomic_read(&er->ref) || er->config == reg1->config) { - atomic_inc(&er->ref); - er->config = reg1->config; - ok = true; - } - } else if (idx == 2 || idx == 3) { - /* - * these two events use different fields in a extra register, - * the 0~7 bits and the 8~15 bits respectively. - */ - u64 mask = 0xff << ((idx - 2) * 8); - if (!__BITS_VALUE(atomic_read(&er->ref), idx - 2, 8) || - !((er->config ^ config1) & mask)) { - atomic_add(1 << ((idx - 2) * 8), &er->ref); - er->config &= ~mask; - er->config |= config1 & mask; - ok = true; - } - } else { - if (!atomic_read(&er->ref) || - (er->config == (hwc->config >> 32) && - er->config1 == reg1->config && - er->config2 == reg2->config)) { - atomic_inc(&er->ref); - er->config = (hwc->config >> 32); - er->config1 = reg1->config; - er->config2 = reg2->config; - ok = true; - } - } - raw_spin_unlock_irqrestore(&er->lock, flags); - - if (!ok) { - /* - * The Rbox events are always in pairs. The paired - * events are functional identical, but use different - * extra registers. If we failed to take an extra - * register, try the alternative. - */ - idx ^= 1; - if (idx != reg1->idx % 6) { - if (idx == 2) - config1 >>= 8; - else if (idx == 3) - config1 <<= 8; - goto again; - } - } else { - if (!uncore_box_is_fake(box)) { - if (idx != reg1->idx % 6) - nhmex_rbox_alter_er(box, event); - reg1->alloc = 1; - } - return NULL; - } - return &constraint_empty; -} - -static void nhmex_rbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event) -{ - struct intel_uncore_extra_reg *er; - struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; - int idx, er_idx; - - if (uncore_box_is_fake(box) || !reg1->alloc) - return; - - idx = reg1->idx % 6; - er_idx = idx; - if (er_idx > 2) - er_idx--; - er_idx += (reg1->idx / 6) * 5; - - er = &box->shared_regs[er_idx]; - if (idx == 2 || idx == 3) - atomic_sub(1 << ((idx - 2) * 8), &er->ref); - else - atomic_dec(&er->ref); - - reg1->alloc = 0; -} - -static int nhmex_rbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; - struct hw_perf_event_extra *reg2 = &event->hw.branch_reg; - int idx; - - idx = (event->hw.config & NHMEX_R_PMON_CTL_EV_SEL_MASK) >> - NHMEX_R_PMON_CTL_EV_SEL_SHIFT; - if (idx >= 0x18) - return -EINVAL; - - reg1->idx = idx; - reg1->config = event->attr.config1; - - switch (idx % 6) { - case 4: - case 5: - hwc->config |= event->attr.config & (~0ULL << 32); - reg2->config = event->attr.config2; - break; - }; - return 0; -} - -static void nhmex_rbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - struct hw_perf_event_extra *reg2 = &hwc->branch_reg; - int idx, port; - - idx = reg1->idx; - port = idx / 6 + box->pmu->pmu_idx * 4; - - switch (idx % 6) { - case 0: - wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG0(port), reg1->config); - break; - case 1: - wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG1(port), reg1->config); - break; - case 2: - case 3: - wrmsrl(NHMEX_R_MSR_PORTN_QLX_CFG(port), - uncore_shared_reg_config(box, 2 + (idx / 6) * 5)); - break; - case 4: - wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port), - hwc->config >> 32); - wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MATCH(port), reg1->config); - wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MASK(port), reg2->config); - break; - case 5: - wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(port), - hwc->config >> 32); - wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MATCH(port), reg1->config); - wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MASK(port), reg2->config); - break; - }; - - wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 | - (hwc->config & NHMEX_R_PMON_CTL_EV_SEL_MASK)); -} - -DEFINE_UNCORE_FORMAT_ATTR(xbr_mm_cfg, xbr_mm_cfg, "config:32-63"); -DEFINE_UNCORE_FORMAT_ATTR(xbr_match, xbr_match, "config1:0-63"); -DEFINE_UNCORE_FORMAT_ATTR(xbr_mask, xbr_mask, "config2:0-63"); -DEFINE_UNCORE_FORMAT_ATTR(qlx_cfg, qlx_cfg, "config1:0-15"); -DEFINE_UNCORE_FORMAT_ATTR(iperf_cfg, iperf_cfg, "config1:0-31"); - -static struct attribute *nhmex_uncore_rbox_formats_attr[] = { - &format_attr_event5.attr, - &format_attr_xbr_mm_cfg.attr, - &format_attr_xbr_match.attr, - &format_attr_xbr_mask.attr, - &format_attr_qlx_cfg.attr, - &format_attr_iperf_cfg.attr, - NULL, -}; - -static struct attribute_group nhmex_uncore_rbox_format_group = { - .name = "format", - .attrs = nhmex_uncore_rbox_formats_attr, -}; - -static struct uncore_event_desc nhmex_uncore_rbox_events[] = { - INTEL_UNCORE_EVENT_DESC(qpi0_flit_send, "event=0x0,iperf_cfg=0x80000000"), - INTEL_UNCORE_EVENT_DESC(qpi1_filt_send, "event=0x6,iperf_cfg=0x80000000"), - INTEL_UNCORE_EVENT_DESC(qpi0_idle_filt, "event=0x0,iperf_cfg=0x40000000"), - INTEL_UNCORE_EVENT_DESC(qpi1_idle_filt, "event=0x6,iperf_cfg=0x40000000"), - INTEL_UNCORE_EVENT_DESC(qpi0_date_response, "event=0x0,iperf_cfg=0xc4"), - INTEL_UNCORE_EVENT_DESC(qpi1_date_response, "event=0x6,iperf_cfg=0xc4"), - { /* end: all zeroes */ }, -}; - -static struct intel_uncore_ops nhmex_uncore_rbox_ops = { - NHMEX_UNCORE_OPS_COMMON_INIT(), - .enable_event = nhmex_rbox_msr_enable_event, - .hw_config = nhmex_rbox_hw_config, - .get_constraint = nhmex_rbox_get_constraint, - .put_constraint = nhmex_rbox_put_constraint, -}; - -static struct intel_uncore_type nhmex_uncore_rbox = { - .name = "rbox", - .num_counters = 8, - .num_boxes = 2, - .perf_ctr_bits = 48, - .event_ctl = NHMEX_R_MSR_PMON_CTL0, - .perf_ctr = NHMEX_R_MSR_PMON_CNT0, - .event_mask = NHMEX_R_PMON_RAW_EVENT_MASK, - .box_ctl = NHMEX_R_MSR_GLOBAL_CTL, - .msr_offset = NHMEX_R_MSR_OFFSET, - .pair_ctr_ctl = 1, - .num_shared_regs = 20, - .event_descs = nhmex_uncore_rbox_events, - .ops = &nhmex_uncore_rbox_ops, - .format_group = &nhmex_uncore_rbox_format_group -}; - -static struct intel_uncore_type *nhmex_msr_uncores[] = { - &nhmex_uncore_ubox, - &nhmex_uncore_cbox, - &nhmex_uncore_bbox, - &nhmex_uncore_sbox, - &nhmex_uncore_mbox, - &nhmex_uncore_rbox, - &nhmex_uncore_wbox, - NULL, -}; -/* end of Nehalem-EX uncore support */ - static void uncore_assign_hw_event(struct intel_uncore_box *box, struct perf_event *event, int idx) { struct hw_perf_event *hwc = &event->hw; @@ -3140,7 +170,7 @@ static void uncore_assign_hw_event(struct intel_uncore_box *box, struct perf_eve hwc->event_base = uncore_perf_ctr(box, hwc->idx); } -static void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *event) +void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *event) { u64 prev_count, new_count, delta; int shift; @@ -3201,14 +231,14 @@ static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer) return HRTIMER_RESTART; } -static void uncore_pmu_start_hrtimer(struct intel_uncore_box *box) +void uncore_pmu_start_hrtimer(struct intel_uncore_box *box) { __hrtimer_start_range_ns(&box->hrtimer, ns_to_ktime(box->hrtimer_duration), 0, HRTIMER_MODE_REL_PINNED, 0); } -static void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box) +void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box) { hrtimer_cancel(&box->hrtimer); } @@ -3246,6 +276,17 @@ static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, return box; } +/* + * Using uncore_pmu_event_init pmu event_init callback + * as a detection point for uncore events. + */ +static int uncore_pmu_event_init(struct perf_event *event); + +static bool is_uncore_event(struct perf_event *event) +{ + return event->pmu->event_init == uncore_pmu_event_init; +} + static int uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, bool dogrp) { @@ -3260,13 +301,18 @@ uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, b return -EINVAL; n = box->n_events; - box->event_list[n] = leader; - n++; + + if (is_uncore_event(leader)) { + box->event_list[n] = leader; + n++; + } + if (!dogrp) return n; list_for_each_entry(event, &leader->sibling_list, group_entry) { - if (event->state <= PERF_EVENT_STATE_OFF) + if (!is_uncore_event(event) || + event->state <= PERF_EVENT_STATE_OFF) continue; if (n >= max_count) @@ -3291,7 +337,7 @@ uncore_get_event_constraint(struct intel_uncore_box *box, struct perf_event *eve } if (event->attr.config == UNCORE_FIXED_EVENT) - return &constraint_fixed; + return &uncore_constraint_fixed; if (type->constraints) { for_each_event_constraint(c, type->constraints) { @@ -3496,7 +542,7 @@ static void uncore_pmu_event_del(struct perf_event *event, int flags) event->hw.last_tag = ~0ULL; } -static void uncore_pmu_event_read(struct perf_event *event) +void uncore_pmu_event_read(struct perf_event *event) { struct intel_uncore_box *box = uncore_event_to_box(event); uncore_perf_event_update(box, event); @@ -3617,11 +663,7 @@ static int uncore_pmu_event_init(struct perf_event *event) static ssize_t uncore_get_attr_cpumask(struct device *dev, struct device_attribute *attr, char *buf) { - int n = cpulist_scnprintf(buf, PAGE_SIZE - 2, &uncore_cpu_mask); - - buf[n++] = '\n'; - buf[n] = '\0'; - return n; + return cpumap_print_to_pagebuf(true, buf, &uncore_cpu_mask); } static DEVICE_ATTR(cpumask, S_IRUGO, uncore_get_attr_cpumask, NULL); @@ -3635,7 +677,7 @@ static struct attribute_group uncore_pmu_attr_group = { .attrs = uncore_pmu_attrs, }; -static int __init uncore_pmu_register(struct intel_uncore_pmu *pmu) +static int uncore_pmu_register(struct intel_uncore_pmu *pmu) { int ret; @@ -3758,9 +800,6 @@ fail: return ret; } -static struct pci_driver *uncore_pci_driver; -static bool pcidrv_registered; - /* * add a pci uncore device */ @@ -3770,18 +809,20 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id struct intel_uncore_box *box; struct intel_uncore_type *type; int phys_id; + bool first_box = false; - phys_id = pcibus_to_physid[pdev->bus->number]; + phys_id = uncore_pcibus_to_physid[pdev->bus->number]; if (phys_id < 0) return -ENODEV; if (UNCORE_PCI_DEV_TYPE(id->driver_data) == UNCORE_EXTRA_PCI_DEV) { - extra_pci_dev[phys_id][UNCORE_PCI_DEV_IDX(id->driver_data)] = pdev; + int idx = UNCORE_PCI_DEV_IDX(id->driver_data); + uncore_extra_pci_dev[phys_id][idx] = pdev; pci_set_drvdata(pdev, NULL); return 0; } - type = pci_uncores[UNCORE_PCI_DEV_TYPE(id->driver_data)]; + type = uncore_pci_uncores[UNCORE_PCI_DEV_TYPE(id->driver_data)]; box = uncore_alloc_box(type, NUMA_NO_NODE); if (!box) return -ENOMEM; @@ -3803,9 +844,13 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id pci_set_drvdata(pdev, box); raw_spin_lock(&uncore_box_lock); + if (list_empty(&pmu->box_list)) + first_box = true; list_add_tail(&box->list, &pmu->box_list); raw_spin_unlock(&uncore_box_lock); + if (first_box) + uncore_pmu_register(pmu); return 0; } @@ -3813,13 +858,14 @@ static void uncore_pci_remove(struct pci_dev *pdev) { struct intel_uncore_box *box = pci_get_drvdata(pdev); struct intel_uncore_pmu *pmu; - int i, cpu, phys_id = pcibus_to_physid[pdev->bus->number]; + int i, cpu, phys_id = uncore_pcibus_to_physid[pdev->bus->number]; + bool last_box = false; box = pci_get_drvdata(pdev); if (!box) { for (i = 0; i < UNCORE_EXTRA_PCI_DEV_MAX; i++) { - if (extra_pci_dev[phys_id][i] == pdev) { - extra_pci_dev[phys_id][i] = NULL; + if (uncore_extra_pci_dev[phys_id][i] == pdev) { + uncore_extra_pci_dev[phys_id][i] = NULL; break; } } @@ -3835,6 +881,8 @@ static void uncore_pci_remove(struct pci_dev *pdev) raw_spin_lock(&uncore_box_lock); list_del(&box->list); + if (list_empty(&pmu->box_list)) + last_box = true; raw_spin_unlock(&uncore_box_lock); for_each_possible_cpu(cpu) { @@ -3846,6 +894,9 @@ static void uncore_pci_remove(struct pci_dev *pdev) WARN_ON_ONCE(atomic_read(&box->refcnt) != 1); kfree(box); + + if (last_box) + perf_pmu_unregister(&pmu->pmu); } static int __init uncore_pci_init(void) @@ -3854,46 +905,32 @@ static int __init uncore_pci_init(void) switch (boot_cpu_data.x86_model) { case 45: /* Sandy Bridge-EP */ - ret = snbep_pci2phy_map_init(0x3ce0); - if (ret) - return ret; - pci_uncores = snbep_pci_uncores; - uncore_pci_driver = &snbep_uncore_pci_driver; + ret = snbep_uncore_pci_init(); break; - case 62: /* IvyTown */ - ret = snbep_pci2phy_map_init(0x0e1e); - if (ret) - return ret; - pci_uncores = ivt_pci_uncores; - uncore_pci_driver = &ivt_uncore_pci_driver; + case 62: /* Ivy Bridge-EP */ + ret = ivbep_uncore_pci_init(); + break; + case 63: /* Haswell-EP */ + ret = hswep_uncore_pci_init(); break; case 42: /* Sandy Bridge */ - ret = snb_pci2phy_map_init(PCI_DEVICE_ID_INTEL_SNB_IMC); - if (ret) - return ret; - pci_uncores = snb_pci_uncores; - uncore_pci_driver = &snb_uncore_pci_driver; + ret = snb_uncore_pci_init(); break; case 58: /* Ivy Bridge */ - ret = snb_pci2phy_map_init(PCI_DEVICE_ID_INTEL_IVB_IMC); - if (ret) - return ret; - pci_uncores = snb_pci_uncores; - uncore_pci_driver = &ivb_uncore_pci_driver; + ret = ivb_uncore_pci_init(); break; case 60: /* Haswell */ case 69: /* Haswell Celeron */ - ret = snb_pci2phy_map_init(PCI_DEVICE_ID_INTEL_HSW_IMC); - if (ret) - return ret; - pci_uncores = snb_pci_uncores; - uncore_pci_driver = &hsw_uncore_pci_driver; + ret = hsw_uncore_pci_init(); break; default: return 0; } - ret = uncore_types_init(pci_uncores); + if (ret) + return ret; + + ret = uncore_types_init(uncore_pci_uncores); if (ret) return ret; @@ -3904,7 +941,7 @@ static int __init uncore_pci_init(void) if (ret == 0) pcidrv_registered = true; else - uncore_types_exit(pci_uncores); + uncore_types_exit(uncore_pci_uncores); return ret; } @@ -3914,7 +951,7 @@ static void __init uncore_pci_exit(void) if (pcidrv_registered) { pcidrv_registered = false; pci_unregister_driver(uncore_pci_driver); - uncore_types_exit(pci_uncores); + uncore_types_exit(uncore_pci_uncores); } } @@ -3940,8 +977,8 @@ static void uncore_cpu_dying(int cpu) struct intel_uncore_box *box; int i, j; - for (i = 0; msr_uncores[i]; i++) { - type = msr_uncores[i]; + for (i = 0; uncore_msr_uncores[i]; i++) { + type = uncore_msr_uncores[i]; for (j = 0; j < type->num_boxes; j++) { pmu = &type->pmus[j]; box = *per_cpu_ptr(pmu->box, cpu); @@ -3961,8 +998,8 @@ static int uncore_cpu_starting(int cpu) phys_id = topology_physical_package_id(cpu); - for (i = 0; msr_uncores[i]; i++) { - type = msr_uncores[i]; + for (i = 0; uncore_msr_uncores[i]; i++) { + type = uncore_msr_uncores[i]; for (j = 0; j < type->num_boxes; j++) { pmu = &type->pmus[j]; box = *per_cpu_ptr(pmu->box, cpu); @@ -4002,8 +1039,8 @@ static int uncore_cpu_prepare(int cpu, int phys_id) struct intel_uncore_box *box; int i, j; - for (i = 0; msr_uncores[i]; i++) { - type = msr_uncores[i]; + for (i = 0; uncore_msr_uncores[i]; i++) { + type = uncore_msr_uncores[i]; for (j = 0; j < type->num_boxes; j++) { pmu = &type->pmus[j]; if (pmu->func_id < 0) @@ -4083,8 +1120,8 @@ static void uncore_event_exit_cpu(int cpu) if (target >= 0) cpumask_set_cpu(target, &uncore_cpu_mask); - uncore_change_context(msr_uncores, cpu, target); - uncore_change_context(pci_uncores, cpu, target); + uncore_change_context(uncore_msr_uncores, cpu, target); + uncore_change_context(uncore_pci_uncores, cpu, target); } static void uncore_event_init_cpu(int cpu) @@ -4099,8 +1136,8 @@ static void uncore_event_init_cpu(int cpu) cpumask_set_cpu(cpu, &uncore_cpu_mask); - uncore_change_context(msr_uncores, -1, cpu); - uncore_change_context(pci_uncores, -1, cpu); + uncore_change_context(uncore_msr_uncores, -1, cpu); + uncore_change_context(uncore_pci_uncores, -1, cpu); } static int uncore_cpu_notifier(struct notifier_block *self, @@ -4160,47 +1197,37 @@ static void __init uncore_cpu_setup(void *dummy) static int __init uncore_cpu_init(void) { - int ret, max_cores; + int ret; - max_cores = boot_cpu_data.x86_max_cores; switch (boot_cpu_data.x86_model) { case 26: /* Nehalem */ case 30: case 37: /* Westmere */ case 44: - msr_uncores = nhm_msr_uncores; + nhm_uncore_cpu_init(); break; case 42: /* Sandy Bridge */ case 58: /* Ivy Bridge */ - if (snb_uncore_cbox.num_boxes > max_cores) - snb_uncore_cbox.num_boxes = max_cores; - msr_uncores = snb_msr_uncores; + snb_uncore_cpu_init(); break; case 45: /* Sandy Bridge-EP */ - if (snbep_uncore_cbox.num_boxes > max_cores) - snbep_uncore_cbox.num_boxes = max_cores; - msr_uncores = snbep_msr_uncores; + snbep_uncore_cpu_init(); break; case 46: /* Nehalem-EX */ - uncore_nhmex = true; case 47: /* Westmere-EX aka. Xeon E7 */ - if (!uncore_nhmex) - nhmex_uncore_mbox.event_descs = wsmex_uncore_mbox_events; - if (nhmex_uncore_cbox.num_boxes > max_cores) - nhmex_uncore_cbox.num_boxes = max_cores; - msr_uncores = nhmex_msr_uncores; + nhmex_uncore_cpu_init(); break; - case 62: /* IvyTown */ - if (ivt_uncore_cbox.num_boxes > max_cores) - ivt_uncore_cbox.num_boxes = max_cores; - msr_uncores = ivt_msr_uncores; + case 62: /* Ivy Bridge-EP */ + ivbep_uncore_cpu_init(); + break; + case 63: /* Haswell-EP */ + hswep_uncore_cpu_init(); break; - default: return 0; } - ret = uncore_types_init(msr_uncores); + ret = uncore_types_init(uncore_msr_uncores); if (ret) return ret; @@ -4213,16 +1240,8 @@ static int __init uncore_pmus_register(void) struct intel_uncore_type *type; int i, j; - for (i = 0; msr_uncores[i]; i++) { - type = msr_uncores[i]; - for (j = 0; j < type->num_boxes; j++) { - pmu = &type->pmus[j]; - uncore_pmu_register(pmu); - } - } - - for (i = 0; pci_uncores[i]; i++) { - type = pci_uncores[i]; + for (i = 0; uncore_msr_uncores[i]; i++) { + type = uncore_msr_uncores[i]; for (j = 0; j < type->num_boxes; j++) { pmu = &type->pmus[j]; uncore_pmu_register(pmu); diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h index 90236f0c94a9..863d9b02563e 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h @@ -17,402 +17,13 @@ #define UNCORE_PCI_DEV_TYPE(data) ((data >> 8) & 0xff) #define UNCORE_PCI_DEV_IDX(data) (data & 0xff) #define UNCORE_EXTRA_PCI_DEV 0xff -#define UNCORE_EXTRA_PCI_DEV_MAX 2 +#define UNCORE_EXTRA_PCI_DEV_MAX 3 /* support up to 8 sockets */ #define UNCORE_SOCKET_MAX 8 #define UNCORE_EVENT_CONSTRAINT(c, n) EVENT_CONSTRAINT(c, n, 0xff) -/* SNB event control */ -#define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff -#define SNB_UNC_CTL_UMASK_MASK 0x0000ff00 -#define SNB_UNC_CTL_EDGE_DET (1 << 18) -#define SNB_UNC_CTL_EN (1 << 22) -#define SNB_UNC_CTL_INVERT (1 << 23) -#define SNB_UNC_CTL_CMASK_MASK 0x1f000000 -#define NHM_UNC_CTL_CMASK_MASK 0xff000000 -#define NHM_UNC_FIXED_CTR_CTL_EN (1 << 0) - -#define SNB_UNC_RAW_EVENT_MASK (SNB_UNC_CTL_EV_SEL_MASK | \ - SNB_UNC_CTL_UMASK_MASK | \ - SNB_UNC_CTL_EDGE_DET | \ - SNB_UNC_CTL_INVERT | \ - SNB_UNC_CTL_CMASK_MASK) - -#define NHM_UNC_RAW_EVENT_MASK (SNB_UNC_CTL_EV_SEL_MASK | \ - SNB_UNC_CTL_UMASK_MASK | \ - SNB_UNC_CTL_EDGE_DET | \ - SNB_UNC_CTL_INVERT | \ - NHM_UNC_CTL_CMASK_MASK) - -/* SNB global control register */ -#define SNB_UNC_PERF_GLOBAL_CTL 0x391 -#define SNB_UNC_FIXED_CTR_CTRL 0x394 -#define SNB_UNC_FIXED_CTR 0x395 - -/* SNB uncore global control */ -#define SNB_UNC_GLOBAL_CTL_CORE_ALL ((1 << 4) - 1) -#define SNB_UNC_GLOBAL_CTL_EN (1 << 29) - -/* SNB Cbo register */ -#define SNB_UNC_CBO_0_PERFEVTSEL0 0x700 -#define SNB_UNC_CBO_0_PER_CTR0 0x706 -#define SNB_UNC_CBO_MSR_OFFSET 0x10 - -/* NHM global control register */ -#define NHM_UNC_PERF_GLOBAL_CTL 0x391 -#define NHM_UNC_FIXED_CTR 0x394 -#define NHM_UNC_FIXED_CTR_CTRL 0x395 - -/* NHM uncore global control */ -#define NHM_UNC_GLOBAL_CTL_EN_PC_ALL ((1ULL << 8) - 1) -#define NHM_UNC_GLOBAL_CTL_EN_FC (1ULL << 32) - -/* NHM uncore register */ -#define NHM_UNC_PERFEVTSEL0 0x3c0 -#define NHM_UNC_UNCORE_PMC0 0x3b0 - -/* SNB-EP Box level control */ -#define SNBEP_PMON_BOX_CTL_RST_CTRL (1 << 0) -#define SNBEP_PMON_BOX_CTL_RST_CTRS (1 << 1) -#define SNBEP_PMON_BOX_CTL_FRZ (1 << 8) -#define SNBEP_PMON_BOX_CTL_FRZ_EN (1 << 16) -#define SNBEP_PMON_BOX_CTL_INT (SNBEP_PMON_BOX_CTL_RST_CTRL | \ - SNBEP_PMON_BOX_CTL_RST_CTRS | \ - SNBEP_PMON_BOX_CTL_FRZ_EN) -/* SNB-EP event control */ -#define SNBEP_PMON_CTL_EV_SEL_MASK 0x000000ff -#define SNBEP_PMON_CTL_UMASK_MASK 0x0000ff00 -#define SNBEP_PMON_CTL_RST (1 << 17) -#define SNBEP_PMON_CTL_EDGE_DET (1 << 18) -#define SNBEP_PMON_CTL_EV_SEL_EXT (1 << 21) -#define SNBEP_PMON_CTL_EN (1 << 22) -#define SNBEP_PMON_CTL_INVERT (1 << 23) -#define SNBEP_PMON_CTL_TRESH_MASK 0xff000000 -#define SNBEP_PMON_RAW_EVENT_MASK (SNBEP_PMON_CTL_EV_SEL_MASK | \ - SNBEP_PMON_CTL_UMASK_MASK | \ - SNBEP_PMON_CTL_EDGE_DET | \ - SNBEP_PMON_CTL_INVERT | \ - SNBEP_PMON_CTL_TRESH_MASK) - -/* SNB-EP Ubox event control */ -#define SNBEP_U_MSR_PMON_CTL_TRESH_MASK 0x1f000000 -#define SNBEP_U_MSR_PMON_RAW_EVENT_MASK \ - (SNBEP_PMON_CTL_EV_SEL_MASK | \ - SNBEP_PMON_CTL_UMASK_MASK | \ - SNBEP_PMON_CTL_EDGE_DET | \ - SNBEP_PMON_CTL_INVERT | \ - SNBEP_U_MSR_PMON_CTL_TRESH_MASK) - -#define SNBEP_CBO_PMON_CTL_TID_EN (1 << 19) -#define SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK (SNBEP_PMON_RAW_EVENT_MASK | \ - SNBEP_CBO_PMON_CTL_TID_EN) - -/* SNB-EP PCU event control */ -#define SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK 0x0000c000 -#define SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK 0x1f000000 -#define SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT (1 << 30) -#define SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET (1 << 31) -#define SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK \ - (SNBEP_PMON_CTL_EV_SEL_MASK | \ - SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \ - SNBEP_PMON_CTL_EDGE_DET | \ - SNBEP_PMON_CTL_EV_SEL_EXT | \ - SNBEP_PMON_CTL_INVERT | \ - SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK | \ - SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \ - SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET) - -#define SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK \ - (SNBEP_PMON_RAW_EVENT_MASK | \ - SNBEP_PMON_CTL_EV_SEL_EXT) - -/* SNB-EP pci control register */ -#define SNBEP_PCI_PMON_BOX_CTL 0xf4 -#define SNBEP_PCI_PMON_CTL0 0xd8 -/* SNB-EP pci counter register */ -#define SNBEP_PCI_PMON_CTR0 0xa0 - -/* SNB-EP home agent register */ -#define SNBEP_HA_PCI_PMON_BOX_ADDRMATCH0 0x40 -#define SNBEP_HA_PCI_PMON_BOX_ADDRMATCH1 0x44 -#define SNBEP_HA_PCI_PMON_BOX_OPCODEMATCH 0x48 -/* SNB-EP memory controller register */ -#define SNBEP_MC_CHy_PCI_PMON_FIXED_CTL 0xf0 -#define SNBEP_MC_CHy_PCI_PMON_FIXED_CTR 0xd0 -/* SNB-EP QPI register */ -#define SNBEP_Q_Py_PCI_PMON_PKT_MATCH0 0x228 -#define SNBEP_Q_Py_PCI_PMON_PKT_MATCH1 0x22c -#define SNBEP_Q_Py_PCI_PMON_PKT_MASK0 0x238 -#define SNBEP_Q_Py_PCI_PMON_PKT_MASK1 0x23c - -/* SNB-EP Ubox register */ -#define SNBEP_U_MSR_PMON_CTR0 0xc16 -#define SNBEP_U_MSR_PMON_CTL0 0xc10 - -#define SNBEP_U_MSR_PMON_UCLK_FIXED_CTL 0xc08 -#define SNBEP_U_MSR_PMON_UCLK_FIXED_CTR 0xc09 - -/* SNB-EP Cbo register */ -#define SNBEP_C0_MSR_PMON_CTR0 0xd16 -#define SNBEP_C0_MSR_PMON_CTL0 0xd10 -#define SNBEP_C0_MSR_PMON_BOX_CTL 0xd04 -#define SNBEP_C0_MSR_PMON_BOX_FILTER 0xd14 -#define SNBEP_CBO_MSR_OFFSET 0x20 - -#define SNBEP_CB0_MSR_PMON_BOX_FILTER_TID 0x1f -#define SNBEP_CB0_MSR_PMON_BOX_FILTER_NID 0x3fc00 -#define SNBEP_CB0_MSR_PMON_BOX_FILTER_STATE 0x7c0000 -#define SNBEP_CB0_MSR_PMON_BOX_FILTER_OPC 0xff800000 - -#define SNBEP_CBO_EVENT_EXTRA_REG(e, m, i) { \ - .event = (e), \ - .msr = SNBEP_C0_MSR_PMON_BOX_FILTER, \ - .config_mask = (m), \ - .idx = (i) \ -} - -/* SNB-EP PCU register */ -#define SNBEP_PCU_MSR_PMON_CTR0 0xc36 -#define SNBEP_PCU_MSR_PMON_CTL0 0xc30 -#define SNBEP_PCU_MSR_PMON_BOX_CTL 0xc24 -#define SNBEP_PCU_MSR_PMON_BOX_FILTER 0xc34 -#define SNBEP_PCU_MSR_PMON_BOX_FILTER_MASK 0xffffffff -#define SNBEP_PCU_MSR_CORE_C3_CTR 0x3fc -#define SNBEP_PCU_MSR_CORE_C6_CTR 0x3fd - -/* IVT event control */ -#define IVT_PMON_BOX_CTL_INT (SNBEP_PMON_BOX_CTL_RST_CTRL | \ - SNBEP_PMON_BOX_CTL_RST_CTRS) -#define IVT_PMON_RAW_EVENT_MASK (SNBEP_PMON_CTL_EV_SEL_MASK | \ - SNBEP_PMON_CTL_UMASK_MASK | \ - SNBEP_PMON_CTL_EDGE_DET | \ - SNBEP_PMON_CTL_TRESH_MASK) -/* IVT Ubox */ -#define IVT_U_MSR_PMON_GLOBAL_CTL 0xc00 -#define IVT_U_PMON_GLOBAL_FRZ_ALL (1 << 31) -#define IVT_U_PMON_GLOBAL_UNFRZ_ALL (1 << 29) - -#define IVT_U_MSR_PMON_RAW_EVENT_MASK \ - (SNBEP_PMON_CTL_EV_SEL_MASK | \ - SNBEP_PMON_CTL_UMASK_MASK | \ - SNBEP_PMON_CTL_EDGE_DET | \ - SNBEP_U_MSR_PMON_CTL_TRESH_MASK) -/* IVT Cbo */ -#define IVT_CBO_MSR_PMON_RAW_EVENT_MASK (IVT_PMON_RAW_EVENT_MASK | \ - SNBEP_CBO_PMON_CTL_TID_EN) - -#define IVT_CB0_MSR_PMON_BOX_FILTER_TID (0x1fULL << 0) -#define IVT_CB0_MSR_PMON_BOX_FILTER_LINK (0xfULL << 5) -#define IVT_CB0_MSR_PMON_BOX_FILTER_STATE (0x3fULL << 17) -#define IVT_CB0_MSR_PMON_BOX_FILTER_NID (0xffffULL << 32) -#define IVT_CB0_MSR_PMON_BOX_FILTER_OPC (0x1ffULL << 52) -#define IVT_CB0_MSR_PMON_BOX_FILTER_C6 (0x1ULL << 61) -#define IVT_CB0_MSR_PMON_BOX_FILTER_NC (0x1ULL << 62) -#define IVT_CB0_MSR_PMON_BOX_FILTER_IOSC (0x1ULL << 63) - -/* IVT home agent */ -#define IVT_HA_PCI_PMON_CTL_Q_OCC_RST (1 << 16) -#define IVT_HA_PCI_PMON_RAW_EVENT_MASK \ - (IVT_PMON_RAW_EVENT_MASK | \ - IVT_HA_PCI_PMON_CTL_Q_OCC_RST) -/* IVT PCU */ -#define IVT_PCU_MSR_PMON_RAW_EVENT_MASK \ - (SNBEP_PMON_CTL_EV_SEL_MASK | \ - SNBEP_PMON_CTL_EV_SEL_EXT | \ - SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \ - SNBEP_PMON_CTL_EDGE_DET | \ - SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK | \ - SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \ - SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET) -/* IVT QPI */ -#define IVT_QPI_PCI_PMON_RAW_EVENT_MASK \ - (IVT_PMON_RAW_EVENT_MASK | \ - SNBEP_PMON_CTL_EV_SEL_EXT) - -/* NHM-EX event control */ -#define NHMEX_PMON_CTL_EV_SEL_MASK 0x000000ff -#define NHMEX_PMON_CTL_UMASK_MASK 0x0000ff00 -#define NHMEX_PMON_CTL_EN_BIT0 (1 << 0) -#define NHMEX_PMON_CTL_EDGE_DET (1 << 18) -#define NHMEX_PMON_CTL_PMI_EN (1 << 20) -#define NHMEX_PMON_CTL_EN_BIT22 (1 << 22) -#define NHMEX_PMON_CTL_INVERT (1 << 23) -#define NHMEX_PMON_CTL_TRESH_MASK 0xff000000 -#define NHMEX_PMON_RAW_EVENT_MASK (NHMEX_PMON_CTL_EV_SEL_MASK | \ - NHMEX_PMON_CTL_UMASK_MASK | \ - NHMEX_PMON_CTL_EDGE_DET | \ - NHMEX_PMON_CTL_INVERT | \ - NHMEX_PMON_CTL_TRESH_MASK) - -/* NHM-EX Ubox */ -#define NHMEX_U_MSR_PMON_GLOBAL_CTL 0xc00 -#define NHMEX_U_MSR_PMON_CTR 0xc11 -#define NHMEX_U_MSR_PMON_EV_SEL 0xc10 - -#define NHMEX_U_PMON_GLOBAL_EN (1 << 0) -#define NHMEX_U_PMON_GLOBAL_PMI_CORE_SEL 0x0000001e -#define NHMEX_U_PMON_GLOBAL_EN_ALL (1 << 28) -#define NHMEX_U_PMON_GLOBAL_RST_ALL (1 << 29) -#define NHMEX_U_PMON_GLOBAL_FRZ_ALL (1 << 31) - -#define NHMEX_U_PMON_RAW_EVENT_MASK \ - (NHMEX_PMON_CTL_EV_SEL_MASK | \ - NHMEX_PMON_CTL_EDGE_DET) - -/* NHM-EX Cbox */ -#define NHMEX_C0_MSR_PMON_GLOBAL_CTL 0xd00 -#define NHMEX_C0_MSR_PMON_CTR0 0xd11 -#define NHMEX_C0_MSR_PMON_EV_SEL0 0xd10 -#define NHMEX_C_MSR_OFFSET 0x20 - -/* NHM-EX Bbox */ -#define NHMEX_B0_MSR_PMON_GLOBAL_CTL 0xc20 -#define NHMEX_B0_MSR_PMON_CTR0 0xc31 -#define NHMEX_B0_MSR_PMON_CTL0 0xc30 -#define NHMEX_B_MSR_OFFSET 0x40 -#define NHMEX_B0_MSR_MATCH 0xe45 -#define NHMEX_B0_MSR_MASK 0xe46 -#define NHMEX_B1_MSR_MATCH 0xe4d -#define NHMEX_B1_MSR_MASK 0xe4e - -#define NHMEX_B_PMON_CTL_EN (1 << 0) -#define NHMEX_B_PMON_CTL_EV_SEL_SHIFT 1 -#define NHMEX_B_PMON_CTL_EV_SEL_MASK \ - (0x1f << NHMEX_B_PMON_CTL_EV_SEL_SHIFT) -#define NHMEX_B_PMON_CTR_SHIFT 6 -#define NHMEX_B_PMON_CTR_MASK \ - (0x3 << NHMEX_B_PMON_CTR_SHIFT) -#define NHMEX_B_PMON_RAW_EVENT_MASK \ - (NHMEX_B_PMON_CTL_EV_SEL_MASK | \ - NHMEX_B_PMON_CTR_MASK) - -/* NHM-EX Sbox */ -#define NHMEX_S0_MSR_PMON_GLOBAL_CTL 0xc40 -#define NHMEX_S0_MSR_PMON_CTR0 0xc51 -#define NHMEX_S0_MSR_PMON_CTL0 0xc50 -#define NHMEX_S_MSR_OFFSET 0x80 -#define NHMEX_S0_MSR_MM_CFG 0xe48 -#define NHMEX_S0_MSR_MATCH 0xe49 -#define NHMEX_S0_MSR_MASK 0xe4a -#define NHMEX_S1_MSR_MM_CFG 0xe58 -#define NHMEX_S1_MSR_MATCH 0xe59 -#define NHMEX_S1_MSR_MASK 0xe5a - -#define NHMEX_S_PMON_MM_CFG_EN (0x1ULL << 63) -#define NHMEX_S_EVENT_TO_R_PROG_EV 0 - -/* NHM-EX Mbox */ -#define NHMEX_M0_MSR_GLOBAL_CTL 0xca0 -#define NHMEX_M0_MSR_PMU_DSP 0xca5 -#define NHMEX_M0_MSR_PMU_ISS 0xca6 -#define NHMEX_M0_MSR_PMU_MAP 0xca7 -#define NHMEX_M0_MSR_PMU_MSC_THR 0xca8 -#define NHMEX_M0_MSR_PMU_PGT 0xca9 -#define NHMEX_M0_MSR_PMU_PLD 0xcaa -#define NHMEX_M0_MSR_PMU_ZDP_CTL_FVC 0xcab -#define NHMEX_M0_MSR_PMU_CTL0 0xcb0 -#define NHMEX_M0_MSR_PMU_CNT0 0xcb1 -#define NHMEX_M_MSR_OFFSET 0x40 -#define NHMEX_M0_MSR_PMU_MM_CFG 0xe54 -#define NHMEX_M1_MSR_PMU_MM_CFG 0xe5c - -#define NHMEX_M_PMON_MM_CFG_EN (1ULL << 63) -#define NHMEX_M_PMON_ADDR_MATCH_MASK 0x3ffffffffULL -#define NHMEX_M_PMON_ADDR_MASK_MASK 0x7ffffffULL -#define NHMEX_M_PMON_ADDR_MASK_SHIFT 34 - -#define NHMEX_M_PMON_CTL_EN (1 << 0) -#define NHMEX_M_PMON_CTL_PMI_EN (1 << 1) -#define NHMEX_M_PMON_CTL_COUNT_MODE_SHIFT 2 -#define NHMEX_M_PMON_CTL_COUNT_MODE_MASK \ - (0x3 << NHMEX_M_PMON_CTL_COUNT_MODE_SHIFT) -#define NHMEX_M_PMON_CTL_STORAGE_MODE_SHIFT 4 -#define NHMEX_M_PMON_CTL_STORAGE_MODE_MASK \ - (0x3 << NHMEX_M_PMON_CTL_STORAGE_MODE_SHIFT) -#define NHMEX_M_PMON_CTL_WRAP_MODE (1 << 6) -#define NHMEX_M_PMON_CTL_FLAG_MODE (1 << 7) -#define NHMEX_M_PMON_CTL_INC_SEL_SHIFT 9 -#define NHMEX_M_PMON_CTL_INC_SEL_MASK \ - (0x1f << NHMEX_M_PMON_CTL_INC_SEL_SHIFT) -#define NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT 19 -#define NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK \ - (0x7 << NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT) -#define NHMEX_M_PMON_RAW_EVENT_MASK \ - (NHMEX_M_PMON_CTL_COUNT_MODE_MASK | \ - NHMEX_M_PMON_CTL_STORAGE_MODE_MASK | \ - NHMEX_M_PMON_CTL_WRAP_MODE | \ - NHMEX_M_PMON_CTL_FLAG_MODE | \ - NHMEX_M_PMON_CTL_INC_SEL_MASK | \ - NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK) - -#define NHMEX_M_PMON_ZDP_CTL_FVC_MASK (((1 << 11) - 1) | (1 << 23)) -#define NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n) (0x7ULL << (11 + 3 * (n))) - -#define WSMEX_M_PMON_ZDP_CTL_FVC_MASK (((1 << 12) - 1) | (1 << 24)) -#define WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n) (0x7ULL << (12 + 3 * (n))) - -/* - * use the 9~13 bits to select event If the 7th bit is not set, - * otherwise use the 19~21 bits to select event. - */ -#define MBOX_INC_SEL(x) ((x) << NHMEX_M_PMON_CTL_INC_SEL_SHIFT) -#define MBOX_SET_FLAG_SEL(x) (((x) << NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT) | \ - NHMEX_M_PMON_CTL_FLAG_MODE) -#define MBOX_INC_SEL_MASK (NHMEX_M_PMON_CTL_INC_SEL_MASK | \ - NHMEX_M_PMON_CTL_FLAG_MODE) -#define MBOX_SET_FLAG_SEL_MASK (NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK | \ - NHMEX_M_PMON_CTL_FLAG_MODE) -#define MBOX_INC_SEL_EXTAR_REG(c, r) \ - EVENT_EXTRA_REG(MBOX_INC_SEL(c), NHMEX_M0_MSR_PMU_##r, \ - MBOX_INC_SEL_MASK, (u64)-1, NHMEX_M_##r) -#define MBOX_SET_FLAG_SEL_EXTRA_REG(c, r) \ - EVENT_EXTRA_REG(MBOX_SET_FLAG_SEL(c), NHMEX_M0_MSR_PMU_##r, \ - MBOX_SET_FLAG_SEL_MASK, \ - (u64)-1, NHMEX_M_##r) - -/* NHM-EX Rbox */ -#define NHMEX_R_MSR_GLOBAL_CTL 0xe00 -#define NHMEX_R_MSR_PMON_CTL0 0xe10 -#define NHMEX_R_MSR_PMON_CNT0 0xe11 -#define NHMEX_R_MSR_OFFSET 0x20 - -#define NHMEX_R_MSR_PORTN_QLX_CFG(n) \ - ((n) < 4 ? (0xe0c + (n)) : (0xe2c + (n) - 4)) -#define NHMEX_R_MSR_PORTN_IPERF_CFG0(n) (0xe04 + (n)) -#define NHMEX_R_MSR_PORTN_IPERF_CFG1(n) (0xe24 + (n)) -#define NHMEX_R_MSR_PORTN_XBR_OFFSET(n) \ - (((n) < 4 ? 0 : 0x10) + (n) * 4) -#define NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) \ - (0xe60 + NHMEX_R_MSR_PORTN_XBR_OFFSET(n)) -#define NHMEX_R_MSR_PORTN_XBR_SET1_MATCH(n) \ - (NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) + 1) -#define NHMEX_R_MSR_PORTN_XBR_SET1_MASK(n) \ - (NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) + 2) -#define NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) \ - (0xe70 + NHMEX_R_MSR_PORTN_XBR_OFFSET(n)) -#define NHMEX_R_MSR_PORTN_XBR_SET2_MATCH(n) \ - (NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) + 1) -#define NHMEX_R_MSR_PORTN_XBR_SET2_MASK(n) \ - (NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) + 2) - -#define NHMEX_R_PMON_CTL_EN (1 << 0) -#define NHMEX_R_PMON_CTL_EV_SEL_SHIFT 1 -#define NHMEX_R_PMON_CTL_EV_SEL_MASK \ - (0x1f << NHMEX_R_PMON_CTL_EV_SEL_SHIFT) -#define NHMEX_R_PMON_CTL_PMI_EN (1 << 6) -#define NHMEX_R_PMON_RAW_EVENT_MASK NHMEX_R_PMON_CTL_EV_SEL_MASK - -/* NHM-EX Wbox */ -#define NHMEX_W_MSR_GLOBAL_CTL 0xc80 -#define NHMEX_W_MSR_PMON_CNT0 0xc90 -#define NHMEX_W_MSR_PMON_EVT_SEL0 0xc91 -#define NHMEX_W_MSR_PMON_FIXED_CTR 0x394 -#define NHMEX_W_MSR_PMON_FIXED_CTL 0x395 - -#define NHMEX_W_PMON_GLOBAL_FIXED_EN (1ULL << 31) - struct intel_uncore_ops; struct intel_uncore_pmu; struct intel_uncore_box; @@ -505,6 +116,9 @@ struct uncore_event_desc { const char *config; }; +ssize_t uncore_event_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf); + #define INTEL_UNCORE_EVENT_DESC(_name, _config) \ { \ .attr = __ATTR(_name, 0444, uncore_event_show, NULL), \ @@ -522,15 +136,6 @@ static ssize_t __uncore_##_var##_show(struct kobject *kobj, \ static struct kobj_attribute format_attr_##_var = \ __ATTR(_name, 0444, __uncore_##_var##_show, NULL) - -static ssize_t uncore_event_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf) -{ - struct uncore_event_desc *event = - container_of(attr, struct uncore_event_desc, attr); - return sprintf(buf, "%s", event->config); -} - static inline unsigned uncore_pci_box_ctl(struct intel_uncore_box *box) { return box->pmu->type->box_ctl; @@ -694,3 +299,41 @@ static inline bool uncore_box_is_fake(struct intel_uncore_box *box) { return (box->phys_id < 0); } + +struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event); +struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu); +struct intel_uncore_box *uncore_event_to_box(struct perf_event *event); +u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event); +void uncore_pmu_start_hrtimer(struct intel_uncore_box *box); +void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box); +void uncore_pmu_event_read(struct perf_event *event); +void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *event); +struct event_constraint * +uncore_get_constraint(struct intel_uncore_box *box, struct perf_event *event); +void uncore_put_constraint(struct intel_uncore_box *box, struct perf_event *event); +u64 uncore_shared_reg_config(struct intel_uncore_box *box, int idx); + +extern struct intel_uncore_type **uncore_msr_uncores; +extern struct intel_uncore_type **uncore_pci_uncores; +extern struct pci_driver *uncore_pci_driver; +extern int uncore_pcibus_to_physid[256]; +extern struct pci_dev *uncore_extra_pci_dev[UNCORE_SOCKET_MAX][UNCORE_EXTRA_PCI_DEV_MAX]; +extern struct event_constraint uncore_constraint_empty; + +/* perf_event_intel_uncore_snb.c */ +int snb_uncore_pci_init(void); +int ivb_uncore_pci_init(void); +int hsw_uncore_pci_init(void); +void snb_uncore_cpu_init(void); +void nhm_uncore_cpu_init(void); + +/* perf_event_intel_uncore_snbep.c */ +int snbep_uncore_pci_init(void); +void snbep_uncore_cpu_init(void); +int ivbep_uncore_pci_init(void); +void ivbep_uncore_cpu_init(void); +int hswep_uncore_pci_init(void); +void hswep_uncore_cpu_init(void); + +/* perf_event_intel_uncore_nhmex.c */ +void nhmex_uncore_cpu_init(void); diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_nhmex.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_nhmex.c new file mode 100644 index 000000000000..2749965afed0 --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_nhmex.c @@ -0,0 +1,1221 @@ +/* Nehalem-EX/Westmere-EX uncore support */ +#include "perf_event_intel_uncore.h" + +/* NHM-EX event control */ +#define NHMEX_PMON_CTL_EV_SEL_MASK 0x000000ff +#define NHMEX_PMON_CTL_UMASK_MASK 0x0000ff00 +#define NHMEX_PMON_CTL_EN_BIT0 (1 << 0) +#define NHMEX_PMON_CTL_EDGE_DET (1 << 18) +#define NHMEX_PMON_CTL_PMI_EN (1 << 20) +#define NHMEX_PMON_CTL_EN_BIT22 (1 << 22) +#define NHMEX_PMON_CTL_INVERT (1 << 23) +#define NHMEX_PMON_CTL_TRESH_MASK 0xff000000 +#define NHMEX_PMON_RAW_EVENT_MASK (NHMEX_PMON_CTL_EV_SEL_MASK | \ + NHMEX_PMON_CTL_UMASK_MASK | \ + NHMEX_PMON_CTL_EDGE_DET | \ + NHMEX_PMON_CTL_INVERT | \ + NHMEX_PMON_CTL_TRESH_MASK) + +/* NHM-EX Ubox */ +#define NHMEX_U_MSR_PMON_GLOBAL_CTL 0xc00 +#define NHMEX_U_MSR_PMON_CTR 0xc11 +#define NHMEX_U_MSR_PMON_EV_SEL 0xc10 + +#define NHMEX_U_PMON_GLOBAL_EN (1 << 0) +#define NHMEX_U_PMON_GLOBAL_PMI_CORE_SEL 0x0000001e +#define NHMEX_U_PMON_GLOBAL_EN_ALL (1 << 28) +#define NHMEX_U_PMON_GLOBAL_RST_ALL (1 << 29) +#define NHMEX_U_PMON_GLOBAL_FRZ_ALL (1 << 31) + +#define NHMEX_U_PMON_RAW_EVENT_MASK \ + (NHMEX_PMON_CTL_EV_SEL_MASK | \ + NHMEX_PMON_CTL_EDGE_DET) + +/* NHM-EX Cbox */ +#define NHMEX_C0_MSR_PMON_GLOBAL_CTL 0xd00 +#define NHMEX_C0_MSR_PMON_CTR0 0xd11 +#define NHMEX_C0_MSR_PMON_EV_SEL0 0xd10 +#define NHMEX_C_MSR_OFFSET 0x20 + +/* NHM-EX Bbox */ +#define NHMEX_B0_MSR_PMON_GLOBAL_CTL 0xc20 +#define NHMEX_B0_MSR_PMON_CTR0 0xc31 +#define NHMEX_B0_MSR_PMON_CTL0 0xc30 +#define NHMEX_B_MSR_OFFSET 0x40 +#define NHMEX_B0_MSR_MATCH 0xe45 +#define NHMEX_B0_MSR_MASK 0xe46 +#define NHMEX_B1_MSR_MATCH 0xe4d +#define NHMEX_B1_MSR_MASK 0xe4e + +#define NHMEX_B_PMON_CTL_EN (1 << 0) +#define NHMEX_B_PMON_CTL_EV_SEL_SHIFT 1 +#define NHMEX_B_PMON_CTL_EV_SEL_MASK \ + (0x1f << NHMEX_B_PMON_CTL_EV_SEL_SHIFT) +#define NHMEX_B_PMON_CTR_SHIFT 6 +#define NHMEX_B_PMON_CTR_MASK \ + (0x3 << NHMEX_B_PMON_CTR_SHIFT) +#define NHMEX_B_PMON_RAW_EVENT_MASK \ + (NHMEX_B_PMON_CTL_EV_SEL_MASK | \ + NHMEX_B_PMON_CTR_MASK) + +/* NHM-EX Sbox */ +#define NHMEX_S0_MSR_PMON_GLOBAL_CTL 0xc40 +#define NHMEX_S0_MSR_PMON_CTR0 0xc51 +#define NHMEX_S0_MSR_PMON_CTL0 0xc50 +#define NHMEX_S_MSR_OFFSET 0x80 +#define NHMEX_S0_MSR_MM_CFG 0xe48 +#define NHMEX_S0_MSR_MATCH 0xe49 +#define NHMEX_S0_MSR_MASK 0xe4a +#define NHMEX_S1_MSR_MM_CFG 0xe58 +#define NHMEX_S1_MSR_MATCH 0xe59 +#define NHMEX_S1_MSR_MASK 0xe5a + +#define NHMEX_S_PMON_MM_CFG_EN (0x1ULL << 63) +#define NHMEX_S_EVENT_TO_R_PROG_EV 0 + +/* NHM-EX Mbox */ +#define NHMEX_M0_MSR_GLOBAL_CTL 0xca0 +#define NHMEX_M0_MSR_PMU_DSP 0xca5 +#define NHMEX_M0_MSR_PMU_ISS 0xca6 +#define NHMEX_M0_MSR_PMU_MAP 0xca7 +#define NHMEX_M0_MSR_PMU_MSC_THR 0xca8 +#define NHMEX_M0_MSR_PMU_PGT 0xca9 +#define NHMEX_M0_MSR_PMU_PLD 0xcaa +#define NHMEX_M0_MSR_PMU_ZDP_CTL_FVC 0xcab +#define NHMEX_M0_MSR_PMU_CTL0 0xcb0 +#define NHMEX_M0_MSR_PMU_CNT0 0xcb1 +#define NHMEX_M_MSR_OFFSET 0x40 +#define NHMEX_M0_MSR_PMU_MM_CFG 0xe54 +#define NHMEX_M1_MSR_PMU_MM_CFG 0xe5c + +#define NHMEX_M_PMON_MM_CFG_EN (1ULL << 63) +#define NHMEX_M_PMON_ADDR_MATCH_MASK 0x3ffffffffULL +#define NHMEX_M_PMON_ADDR_MASK_MASK 0x7ffffffULL +#define NHMEX_M_PMON_ADDR_MASK_SHIFT 34 + +#define NHMEX_M_PMON_CTL_EN (1 << 0) +#define NHMEX_M_PMON_CTL_PMI_EN (1 << 1) +#define NHMEX_M_PMON_CTL_COUNT_MODE_SHIFT 2 +#define NHMEX_M_PMON_CTL_COUNT_MODE_MASK \ + (0x3 << NHMEX_M_PMON_CTL_COUNT_MODE_SHIFT) +#define NHMEX_M_PMON_CTL_STORAGE_MODE_SHIFT 4 +#define NHMEX_M_PMON_CTL_STORAGE_MODE_MASK \ + (0x3 << NHMEX_M_PMON_CTL_STORAGE_MODE_SHIFT) +#define NHMEX_M_PMON_CTL_WRAP_MODE (1 << 6) +#define NHMEX_M_PMON_CTL_FLAG_MODE (1 << 7) +#define NHMEX_M_PMON_CTL_INC_SEL_SHIFT 9 +#define NHMEX_M_PMON_CTL_INC_SEL_MASK \ + (0x1f << NHMEX_M_PMON_CTL_INC_SEL_SHIFT) +#define NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT 19 +#define NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK \ + (0x7 << NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT) +#define NHMEX_M_PMON_RAW_EVENT_MASK \ + (NHMEX_M_PMON_CTL_COUNT_MODE_MASK | \ + NHMEX_M_PMON_CTL_STORAGE_MODE_MASK | \ + NHMEX_M_PMON_CTL_WRAP_MODE | \ + NHMEX_M_PMON_CTL_FLAG_MODE | \ + NHMEX_M_PMON_CTL_INC_SEL_MASK | \ + NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK) + +#define NHMEX_M_PMON_ZDP_CTL_FVC_MASK (((1 << 11) - 1) | (1 << 23)) +#define NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n) (0x7ULL << (11 + 3 * (n))) + +#define WSMEX_M_PMON_ZDP_CTL_FVC_MASK (((1 << 12) - 1) | (1 << 24)) +#define WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n) (0x7ULL << (12 + 3 * (n))) + +/* + * use the 9~13 bits to select event If the 7th bit is not set, + * otherwise use the 19~21 bits to select event. + */ +#define MBOX_INC_SEL(x) ((x) << NHMEX_M_PMON_CTL_INC_SEL_SHIFT) +#define MBOX_SET_FLAG_SEL(x) (((x) << NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT) | \ + NHMEX_M_PMON_CTL_FLAG_MODE) +#define MBOX_INC_SEL_MASK (NHMEX_M_PMON_CTL_INC_SEL_MASK | \ + NHMEX_M_PMON_CTL_FLAG_MODE) +#define MBOX_SET_FLAG_SEL_MASK (NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK | \ + NHMEX_M_PMON_CTL_FLAG_MODE) +#define MBOX_INC_SEL_EXTAR_REG(c, r) \ + EVENT_EXTRA_REG(MBOX_INC_SEL(c), NHMEX_M0_MSR_PMU_##r, \ + MBOX_INC_SEL_MASK, (u64)-1, NHMEX_M_##r) +#define MBOX_SET_FLAG_SEL_EXTRA_REG(c, r) \ + EVENT_EXTRA_REG(MBOX_SET_FLAG_SEL(c), NHMEX_M0_MSR_PMU_##r, \ + MBOX_SET_FLAG_SEL_MASK, \ + (u64)-1, NHMEX_M_##r) + +/* NHM-EX Rbox */ +#define NHMEX_R_MSR_GLOBAL_CTL 0xe00 +#define NHMEX_R_MSR_PMON_CTL0 0xe10 +#define NHMEX_R_MSR_PMON_CNT0 0xe11 +#define NHMEX_R_MSR_OFFSET 0x20 + +#define NHMEX_R_MSR_PORTN_QLX_CFG(n) \ + ((n) < 4 ? (0xe0c + (n)) : (0xe2c + (n) - 4)) +#define NHMEX_R_MSR_PORTN_IPERF_CFG0(n) (0xe04 + (n)) +#define NHMEX_R_MSR_PORTN_IPERF_CFG1(n) (0xe24 + (n)) +#define NHMEX_R_MSR_PORTN_XBR_OFFSET(n) \ + (((n) < 4 ? 0 : 0x10) + (n) * 4) +#define NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) \ + (0xe60 + NHMEX_R_MSR_PORTN_XBR_OFFSET(n)) +#define NHMEX_R_MSR_PORTN_XBR_SET1_MATCH(n) \ + (NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) + 1) +#define NHMEX_R_MSR_PORTN_XBR_SET1_MASK(n) \ + (NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) + 2) +#define NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) \ + (0xe70 + NHMEX_R_MSR_PORTN_XBR_OFFSET(n)) +#define NHMEX_R_MSR_PORTN_XBR_SET2_MATCH(n) \ + (NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) + 1) +#define NHMEX_R_MSR_PORTN_XBR_SET2_MASK(n) \ + (NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) + 2) + +#define NHMEX_R_PMON_CTL_EN (1 << 0) +#define NHMEX_R_PMON_CTL_EV_SEL_SHIFT 1 +#define NHMEX_R_PMON_CTL_EV_SEL_MASK \ + (0x1f << NHMEX_R_PMON_CTL_EV_SEL_SHIFT) +#define NHMEX_R_PMON_CTL_PMI_EN (1 << 6) +#define NHMEX_R_PMON_RAW_EVENT_MASK NHMEX_R_PMON_CTL_EV_SEL_MASK + +/* NHM-EX Wbox */ +#define NHMEX_W_MSR_GLOBAL_CTL 0xc80 +#define NHMEX_W_MSR_PMON_CNT0 0xc90 +#define NHMEX_W_MSR_PMON_EVT_SEL0 0xc91 +#define NHMEX_W_MSR_PMON_FIXED_CTR 0x394 +#define NHMEX_W_MSR_PMON_FIXED_CTL 0x395 + +#define NHMEX_W_PMON_GLOBAL_FIXED_EN (1ULL << 31) + +#define __BITS_VALUE(x, i, n) ((typeof(x))(((x) >> ((i) * (n))) & \ + ((1ULL << (n)) - 1))) + +DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7"); +DEFINE_UNCORE_FORMAT_ATTR(event5, event, "config:1-5"); +DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); +DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); +DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23"); +DEFINE_UNCORE_FORMAT_ATTR(thresh8, thresh, "config:24-31"); +DEFINE_UNCORE_FORMAT_ATTR(counter, counter, "config:6-7"); +DEFINE_UNCORE_FORMAT_ATTR(match, match, "config1:0-63"); +DEFINE_UNCORE_FORMAT_ATTR(mask, mask, "config2:0-63"); + +static void nhmex_uncore_msr_init_box(struct intel_uncore_box *box) +{ + wrmsrl(NHMEX_U_MSR_PMON_GLOBAL_CTL, NHMEX_U_PMON_GLOBAL_EN_ALL); +} + +static void nhmex_uncore_msr_disable_box(struct intel_uncore_box *box) +{ + unsigned msr = uncore_msr_box_ctl(box); + u64 config; + + if (msr) { + rdmsrl(msr, config); + config &= ~((1ULL << uncore_num_counters(box)) - 1); + /* WBox has a fixed counter */ + if (uncore_msr_fixed_ctl(box)) + config &= ~NHMEX_W_PMON_GLOBAL_FIXED_EN; + wrmsrl(msr, config); + } +} + +static void nhmex_uncore_msr_enable_box(struct intel_uncore_box *box) +{ + unsigned msr = uncore_msr_box_ctl(box); + u64 config; + + if (msr) { + rdmsrl(msr, config); + config |= (1ULL << uncore_num_counters(box)) - 1; + /* WBox has a fixed counter */ + if (uncore_msr_fixed_ctl(box)) + config |= NHMEX_W_PMON_GLOBAL_FIXED_EN; + wrmsrl(msr, config); + } +} + +static void nhmex_uncore_msr_disable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + wrmsrl(event->hw.config_base, 0); +} + +static void nhmex_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + if (hwc->idx >= UNCORE_PMC_IDX_FIXED) + wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0); + else if (box->pmu->type->event_mask & NHMEX_PMON_CTL_EN_BIT0) + wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22); + else + wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0); +} + +#define NHMEX_UNCORE_OPS_COMMON_INIT() \ + .init_box = nhmex_uncore_msr_init_box, \ + .disable_box = nhmex_uncore_msr_disable_box, \ + .enable_box = nhmex_uncore_msr_enable_box, \ + .disable_event = nhmex_uncore_msr_disable_event, \ + .read_counter = uncore_msr_read_counter + +static struct intel_uncore_ops nhmex_uncore_ops = { + NHMEX_UNCORE_OPS_COMMON_INIT(), + .enable_event = nhmex_uncore_msr_enable_event, +}; + +static struct attribute *nhmex_uncore_ubox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_edge.attr, + NULL, +}; + +static struct attribute_group nhmex_uncore_ubox_format_group = { + .name = "format", + .attrs = nhmex_uncore_ubox_formats_attr, +}; + +static struct intel_uncore_type nhmex_uncore_ubox = { + .name = "ubox", + .num_counters = 1, + .num_boxes = 1, + .perf_ctr_bits = 48, + .event_ctl = NHMEX_U_MSR_PMON_EV_SEL, + .perf_ctr = NHMEX_U_MSR_PMON_CTR, + .event_mask = NHMEX_U_PMON_RAW_EVENT_MASK, + .box_ctl = NHMEX_U_MSR_PMON_GLOBAL_CTL, + .ops = &nhmex_uncore_ops, + .format_group = &nhmex_uncore_ubox_format_group +}; + +static struct attribute *nhmex_uncore_cbox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + NULL, +}; + +static struct attribute_group nhmex_uncore_cbox_format_group = { + .name = "format", + .attrs = nhmex_uncore_cbox_formats_attr, +}; + +/* msr offset for each instance of cbox */ +static unsigned nhmex_cbox_msr_offsets[] = { + 0x0, 0x80, 0x40, 0xc0, 0x20, 0xa0, 0x60, 0xe0, 0x240, 0x2c0, +}; + +static struct intel_uncore_type nhmex_uncore_cbox = { + .name = "cbox", + .num_counters = 6, + .num_boxes = 10, + .perf_ctr_bits = 48, + .event_ctl = NHMEX_C0_MSR_PMON_EV_SEL0, + .perf_ctr = NHMEX_C0_MSR_PMON_CTR0, + .event_mask = NHMEX_PMON_RAW_EVENT_MASK, + .box_ctl = NHMEX_C0_MSR_PMON_GLOBAL_CTL, + .msr_offsets = nhmex_cbox_msr_offsets, + .pair_ctr_ctl = 1, + .ops = &nhmex_uncore_ops, + .format_group = &nhmex_uncore_cbox_format_group +}; + +static struct uncore_event_desc nhmex_uncore_wbox_events[] = { + INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0"), + { /* end: all zeroes */ }, +}; + +static struct intel_uncore_type nhmex_uncore_wbox = { + .name = "wbox", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .event_ctl = NHMEX_W_MSR_PMON_CNT0, + .perf_ctr = NHMEX_W_MSR_PMON_EVT_SEL0, + .fixed_ctr = NHMEX_W_MSR_PMON_FIXED_CTR, + .fixed_ctl = NHMEX_W_MSR_PMON_FIXED_CTL, + .event_mask = NHMEX_PMON_RAW_EVENT_MASK, + .box_ctl = NHMEX_W_MSR_GLOBAL_CTL, + .pair_ctr_ctl = 1, + .event_descs = nhmex_uncore_wbox_events, + .ops = &nhmex_uncore_ops, + .format_group = &nhmex_uncore_cbox_format_group +}; + +static int nhmex_bbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; + int ctr, ev_sel; + + ctr = (hwc->config & NHMEX_B_PMON_CTR_MASK) >> + NHMEX_B_PMON_CTR_SHIFT; + ev_sel = (hwc->config & NHMEX_B_PMON_CTL_EV_SEL_MASK) >> + NHMEX_B_PMON_CTL_EV_SEL_SHIFT; + + /* events that do not use the match/mask registers */ + if ((ctr == 0 && ev_sel > 0x3) || (ctr == 1 && ev_sel > 0x6) || + (ctr == 2 && ev_sel != 0x4) || ctr == 3) + return 0; + + if (box->pmu->pmu_idx == 0) + reg1->reg = NHMEX_B0_MSR_MATCH; + else + reg1->reg = NHMEX_B1_MSR_MATCH; + reg1->idx = 0; + reg1->config = event->attr.config1; + reg2->config = event->attr.config2; + return 0; +} + +static void nhmex_bbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; + + if (reg1->idx != EXTRA_REG_NONE) { + wrmsrl(reg1->reg, reg1->config); + wrmsrl(reg1->reg + 1, reg2->config); + } + wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 | + (hwc->config & NHMEX_B_PMON_CTL_EV_SEL_MASK)); +} + +/* + * The Bbox has 4 counters, but each counter monitors different events. + * Use bits 6-7 in the event config to select counter. + */ +static struct event_constraint nhmex_uncore_bbox_constraints[] = { + EVENT_CONSTRAINT(0 , 1, 0xc0), + EVENT_CONSTRAINT(0x40, 2, 0xc0), + EVENT_CONSTRAINT(0x80, 4, 0xc0), + EVENT_CONSTRAINT(0xc0, 8, 0xc0), + EVENT_CONSTRAINT_END, +}; + +static struct attribute *nhmex_uncore_bbox_formats_attr[] = { + &format_attr_event5.attr, + &format_attr_counter.attr, + &format_attr_match.attr, + &format_attr_mask.attr, + NULL, +}; + +static struct attribute_group nhmex_uncore_bbox_format_group = { + .name = "format", + .attrs = nhmex_uncore_bbox_formats_attr, +}; + +static struct intel_uncore_ops nhmex_uncore_bbox_ops = { + NHMEX_UNCORE_OPS_COMMON_INIT(), + .enable_event = nhmex_bbox_msr_enable_event, + .hw_config = nhmex_bbox_hw_config, + .get_constraint = uncore_get_constraint, + .put_constraint = uncore_put_constraint, +}; + +static struct intel_uncore_type nhmex_uncore_bbox = { + .name = "bbox", + .num_counters = 4, + .num_boxes = 2, + .perf_ctr_bits = 48, + .event_ctl = NHMEX_B0_MSR_PMON_CTL0, + .perf_ctr = NHMEX_B0_MSR_PMON_CTR0, + .event_mask = NHMEX_B_PMON_RAW_EVENT_MASK, + .box_ctl = NHMEX_B0_MSR_PMON_GLOBAL_CTL, + .msr_offset = NHMEX_B_MSR_OFFSET, + .pair_ctr_ctl = 1, + .num_shared_regs = 1, + .constraints = nhmex_uncore_bbox_constraints, + .ops = &nhmex_uncore_bbox_ops, + .format_group = &nhmex_uncore_bbox_format_group +}; + +static int nhmex_sbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; + + /* only TO_R_PROG_EV event uses the match/mask register */ + if ((hwc->config & NHMEX_PMON_CTL_EV_SEL_MASK) != + NHMEX_S_EVENT_TO_R_PROG_EV) + return 0; + + if (box->pmu->pmu_idx == 0) + reg1->reg = NHMEX_S0_MSR_MM_CFG; + else + reg1->reg = NHMEX_S1_MSR_MM_CFG; + reg1->idx = 0; + reg1->config = event->attr.config1; + reg2->config = event->attr.config2; + return 0; +} + +static void nhmex_sbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; + + if (reg1->idx != EXTRA_REG_NONE) { + wrmsrl(reg1->reg, 0); + wrmsrl(reg1->reg + 1, reg1->config); + wrmsrl(reg1->reg + 2, reg2->config); + wrmsrl(reg1->reg, NHMEX_S_PMON_MM_CFG_EN); + } + wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22); +} + +static struct attribute *nhmex_uncore_sbox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + &format_attr_match.attr, + &format_attr_mask.attr, + NULL, +}; + +static struct attribute_group nhmex_uncore_sbox_format_group = { + .name = "format", + .attrs = nhmex_uncore_sbox_formats_attr, +}; + +static struct intel_uncore_ops nhmex_uncore_sbox_ops = { + NHMEX_UNCORE_OPS_COMMON_INIT(), + .enable_event = nhmex_sbox_msr_enable_event, + .hw_config = nhmex_sbox_hw_config, + .get_constraint = uncore_get_constraint, + .put_constraint = uncore_put_constraint, +}; + +static struct intel_uncore_type nhmex_uncore_sbox = { + .name = "sbox", + .num_counters = 4, + .num_boxes = 2, + .perf_ctr_bits = 48, + .event_ctl = NHMEX_S0_MSR_PMON_CTL0, + .perf_ctr = NHMEX_S0_MSR_PMON_CTR0, + .event_mask = NHMEX_PMON_RAW_EVENT_MASK, + .box_ctl = NHMEX_S0_MSR_PMON_GLOBAL_CTL, + .msr_offset = NHMEX_S_MSR_OFFSET, + .pair_ctr_ctl = 1, + .num_shared_regs = 1, + .ops = &nhmex_uncore_sbox_ops, + .format_group = &nhmex_uncore_sbox_format_group +}; + +enum { + EXTRA_REG_NHMEX_M_FILTER, + EXTRA_REG_NHMEX_M_DSP, + EXTRA_REG_NHMEX_M_ISS, + EXTRA_REG_NHMEX_M_MAP, + EXTRA_REG_NHMEX_M_MSC_THR, + EXTRA_REG_NHMEX_M_PGT, + EXTRA_REG_NHMEX_M_PLD, + EXTRA_REG_NHMEX_M_ZDP_CTL_FVC, +}; + +static struct extra_reg nhmex_uncore_mbox_extra_regs[] = { + MBOX_INC_SEL_EXTAR_REG(0x0, DSP), + MBOX_INC_SEL_EXTAR_REG(0x4, MSC_THR), + MBOX_INC_SEL_EXTAR_REG(0x5, MSC_THR), + MBOX_INC_SEL_EXTAR_REG(0x9, ISS), + /* event 0xa uses two extra registers */ + MBOX_INC_SEL_EXTAR_REG(0xa, ISS), + MBOX_INC_SEL_EXTAR_REG(0xa, PLD), + MBOX_INC_SEL_EXTAR_REG(0xb, PLD), + /* events 0xd ~ 0x10 use the same extra register */ + MBOX_INC_SEL_EXTAR_REG(0xd, ZDP_CTL_FVC), + MBOX_INC_SEL_EXTAR_REG(0xe, ZDP_CTL_FVC), + MBOX_INC_SEL_EXTAR_REG(0xf, ZDP_CTL_FVC), + MBOX_INC_SEL_EXTAR_REG(0x10, ZDP_CTL_FVC), + MBOX_INC_SEL_EXTAR_REG(0x16, PGT), + MBOX_SET_FLAG_SEL_EXTRA_REG(0x0, DSP), + MBOX_SET_FLAG_SEL_EXTRA_REG(0x1, ISS), + MBOX_SET_FLAG_SEL_EXTRA_REG(0x5, PGT), + MBOX_SET_FLAG_SEL_EXTRA_REG(0x6, MAP), + EVENT_EXTRA_END +}; + +/* Nehalem-EX or Westmere-EX ? */ +static bool uncore_nhmex; + +static bool nhmex_mbox_get_shared_reg(struct intel_uncore_box *box, int idx, u64 config) +{ + struct intel_uncore_extra_reg *er; + unsigned long flags; + bool ret = false; + u64 mask; + + if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) { + er = &box->shared_regs[idx]; + raw_spin_lock_irqsave(&er->lock, flags); + if (!atomic_read(&er->ref) || er->config == config) { + atomic_inc(&er->ref); + er->config = config; + ret = true; + } + raw_spin_unlock_irqrestore(&er->lock, flags); + + return ret; + } + /* + * The ZDP_CTL_FVC MSR has 4 fields which are used to control + * events 0xd ~ 0x10. Besides these 4 fields, there are additional + * fields which are shared. + */ + idx -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC; + if (WARN_ON_ONCE(idx >= 4)) + return false; + + /* mask of the shared fields */ + if (uncore_nhmex) + mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK; + else + mask = WSMEX_M_PMON_ZDP_CTL_FVC_MASK; + er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC]; + + raw_spin_lock_irqsave(&er->lock, flags); + /* add mask of the non-shared field if it's in use */ + if (__BITS_VALUE(atomic_read(&er->ref), idx, 8)) { + if (uncore_nhmex) + mask |= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); + else + mask |= WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); + } + + if (!atomic_read(&er->ref) || !((er->config ^ config) & mask)) { + atomic_add(1 << (idx * 8), &er->ref); + if (uncore_nhmex) + mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK | + NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); + else + mask = WSMEX_M_PMON_ZDP_CTL_FVC_MASK | + WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); + er->config &= ~mask; + er->config |= (config & mask); + ret = true; + } + raw_spin_unlock_irqrestore(&er->lock, flags); + + return ret; +} + +static void nhmex_mbox_put_shared_reg(struct intel_uncore_box *box, int idx) +{ + struct intel_uncore_extra_reg *er; + + if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) { + er = &box->shared_regs[idx]; + atomic_dec(&er->ref); + return; + } + + idx -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC; + er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC]; + atomic_sub(1 << (idx * 8), &er->ref); +} + +static u64 nhmex_mbox_alter_er(struct perf_event *event, int new_idx, bool modify) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + u64 idx, orig_idx = __BITS_VALUE(reg1->idx, 0, 8); + u64 config = reg1->config; + + /* get the non-shared control bits and shift them */ + idx = orig_idx - EXTRA_REG_NHMEX_M_ZDP_CTL_FVC; + if (uncore_nhmex) + config &= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); + else + config &= WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); + if (new_idx > orig_idx) { + idx = new_idx - orig_idx; + config <<= 3 * idx; + } else { + idx = orig_idx - new_idx; + config >>= 3 * idx; + } + + /* add the shared control bits back */ + if (uncore_nhmex) + config |= NHMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config; + else + config |= WSMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config; + config |= NHMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config; + if (modify) { + /* adjust the main event selector */ + if (new_idx > orig_idx) + hwc->config += idx << NHMEX_M_PMON_CTL_INC_SEL_SHIFT; + else + hwc->config -= idx << NHMEX_M_PMON_CTL_INC_SEL_SHIFT; + reg1->config = config; + reg1->idx = ~0xff | new_idx; + } + return config; +} + +static struct event_constraint * +nhmex_mbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct hw_perf_event_extra *reg2 = &event->hw.branch_reg; + int i, idx[2], alloc = 0; + u64 config1 = reg1->config; + + idx[0] = __BITS_VALUE(reg1->idx, 0, 8); + idx[1] = __BITS_VALUE(reg1->idx, 1, 8); +again: + for (i = 0; i < 2; i++) { + if (!uncore_box_is_fake(box) && (reg1->alloc & (0x1 << i))) + idx[i] = 0xff; + + if (idx[i] == 0xff) + continue; + + if (!nhmex_mbox_get_shared_reg(box, idx[i], + __BITS_VALUE(config1, i, 32))) + goto fail; + alloc |= (0x1 << i); + } + + /* for the match/mask registers */ + if (reg2->idx != EXTRA_REG_NONE && + (uncore_box_is_fake(box) || !reg2->alloc) && + !nhmex_mbox_get_shared_reg(box, reg2->idx, reg2->config)) + goto fail; + + /* + * If it's a fake box -- as per validate_{group,event}() we + * shouldn't touch event state and we can avoid doing so + * since both will only call get_event_constraints() once + * on each event, this avoids the need for reg->alloc. + */ + if (!uncore_box_is_fake(box)) { + if (idx[0] != 0xff && idx[0] != __BITS_VALUE(reg1->idx, 0, 8)) + nhmex_mbox_alter_er(event, idx[0], true); + reg1->alloc |= alloc; + if (reg2->idx != EXTRA_REG_NONE) + reg2->alloc = 1; + } + return NULL; +fail: + if (idx[0] != 0xff && !(alloc & 0x1) && + idx[0] >= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) { + /* + * events 0xd ~ 0x10 are functional identical, but are + * controlled by different fields in the ZDP_CTL_FVC + * register. If we failed to take one field, try the + * rest 3 choices. + */ + BUG_ON(__BITS_VALUE(reg1->idx, 1, 8) != 0xff); + idx[0] -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC; + idx[0] = (idx[0] + 1) % 4; + idx[0] += EXTRA_REG_NHMEX_M_ZDP_CTL_FVC; + if (idx[0] != __BITS_VALUE(reg1->idx, 0, 8)) { + config1 = nhmex_mbox_alter_er(event, idx[0], false); + goto again; + } + } + + if (alloc & 0x1) + nhmex_mbox_put_shared_reg(box, idx[0]); + if (alloc & 0x2) + nhmex_mbox_put_shared_reg(box, idx[1]); + return &uncore_constraint_empty; +} + +static void nhmex_mbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct hw_perf_event_extra *reg2 = &event->hw.branch_reg; + + if (uncore_box_is_fake(box)) + return; + + if (reg1->alloc & 0x1) + nhmex_mbox_put_shared_reg(box, __BITS_VALUE(reg1->idx, 0, 8)); + if (reg1->alloc & 0x2) + nhmex_mbox_put_shared_reg(box, __BITS_VALUE(reg1->idx, 1, 8)); + reg1->alloc = 0; + + if (reg2->alloc) { + nhmex_mbox_put_shared_reg(box, reg2->idx); + reg2->alloc = 0; + } +} + +static int nhmex_mbox_extra_reg_idx(struct extra_reg *er) +{ + if (er->idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) + return er->idx; + return er->idx + (er->event >> NHMEX_M_PMON_CTL_INC_SEL_SHIFT) - 0xd; +} + +static int nhmex_mbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct intel_uncore_type *type = box->pmu->type; + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct hw_perf_event_extra *reg2 = &event->hw.branch_reg; + struct extra_reg *er; + unsigned msr; + int reg_idx = 0; + /* + * The mbox events may require 2 extra MSRs at the most. But only + * the lower 32 bits in these MSRs are significant, so we can use + * config1 to pass two MSRs' config. + */ + for (er = nhmex_uncore_mbox_extra_regs; er->msr; er++) { + if (er->event != (event->hw.config & er->config_mask)) + continue; + if (event->attr.config1 & ~er->valid_mask) + return -EINVAL; + + msr = er->msr + type->msr_offset * box->pmu->pmu_idx; + if (WARN_ON_ONCE(msr >= 0xffff || er->idx >= 0xff)) + return -EINVAL; + + /* always use the 32~63 bits to pass the PLD config */ + if (er->idx == EXTRA_REG_NHMEX_M_PLD) + reg_idx = 1; + else if (WARN_ON_ONCE(reg_idx > 0)) + return -EINVAL; + + reg1->idx &= ~(0xff << (reg_idx * 8)); + reg1->reg &= ~(0xffff << (reg_idx * 16)); + reg1->idx |= nhmex_mbox_extra_reg_idx(er) << (reg_idx * 8); + reg1->reg |= msr << (reg_idx * 16); + reg1->config = event->attr.config1; + reg_idx++; + } + /* + * The mbox only provides ability to perform address matching + * for the PLD events. + */ + if (reg_idx == 2) { + reg2->idx = EXTRA_REG_NHMEX_M_FILTER; + if (event->attr.config2 & NHMEX_M_PMON_MM_CFG_EN) + reg2->config = event->attr.config2; + else + reg2->config = ~0ULL; + if (box->pmu->pmu_idx == 0) + reg2->reg = NHMEX_M0_MSR_PMU_MM_CFG; + else + reg2->reg = NHMEX_M1_MSR_PMU_MM_CFG; + } + return 0; +} + +static u64 nhmex_mbox_shared_reg_config(struct intel_uncore_box *box, int idx) +{ + struct intel_uncore_extra_reg *er; + unsigned long flags; + u64 config; + + if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) + return box->shared_regs[idx].config; + + er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC]; + raw_spin_lock_irqsave(&er->lock, flags); + config = er->config; + raw_spin_unlock_irqrestore(&er->lock, flags); + return config; +} + +static void nhmex_mbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; + int idx; + + idx = __BITS_VALUE(reg1->idx, 0, 8); + if (idx != 0xff) + wrmsrl(__BITS_VALUE(reg1->reg, 0, 16), + nhmex_mbox_shared_reg_config(box, idx)); + idx = __BITS_VALUE(reg1->idx, 1, 8); + if (idx != 0xff) + wrmsrl(__BITS_VALUE(reg1->reg, 1, 16), + nhmex_mbox_shared_reg_config(box, idx)); + + if (reg2->idx != EXTRA_REG_NONE) { + wrmsrl(reg2->reg, 0); + if (reg2->config != ~0ULL) { + wrmsrl(reg2->reg + 1, + reg2->config & NHMEX_M_PMON_ADDR_MATCH_MASK); + wrmsrl(reg2->reg + 2, NHMEX_M_PMON_ADDR_MASK_MASK & + (reg2->config >> NHMEX_M_PMON_ADDR_MASK_SHIFT)); + wrmsrl(reg2->reg, NHMEX_M_PMON_MM_CFG_EN); + } + } + + wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0); +} + +DEFINE_UNCORE_FORMAT_ATTR(count_mode, count_mode, "config:2-3"); +DEFINE_UNCORE_FORMAT_ATTR(storage_mode, storage_mode, "config:4-5"); +DEFINE_UNCORE_FORMAT_ATTR(wrap_mode, wrap_mode, "config:6"); +DEFINE_UNCORE_FORMAT_ATTR(flag_mode, flag_mode, "config:7"); +DEFINE_UNCORE_FORMAT_ATTR(inc_sel, inc_sel, "config:9-13"); +DEFINE_UNCORE_FORMAT_ATTR(set_flag_sel, set_flag_sel, "config:19-21"); +DEFINE_UNCORE_FORMAT_ATTR(filter_cfg_en, filter_cfg_en, "config2:63"); +DEFINE_UNCORE_FORMAT_ATTR(filter_match, filter_match, "config2:0-33"); +DEFINE_UNCORE_FORMAT_ATTR(filter_mask, filter_mask, "config2:34-61"); +DEFINE_UNCORE_FORMAT_ATTR(dsp, dsp, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(thr, thr, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(fvc, fvc, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(pgt, pgt, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(map, map, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(iss, iss, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(pld, pld, "config1:32-63"); + +static struct attribute *nhmex_uncore_mbox_formats_attr[] = { + &format_attr_count_mode.attr, + &format_attr_storage_mode.attr, + &format_attr_wrap_mode.attr, + &format_attr_flag_mode.attr, + &format_attr_inc_sel.attr, + &format_attr_set_flag_sel.attr, + &format_attr_filter_cfg_en.attr, + &format_attr_filter_match.attr, + &format_attr_filter_mask.attr, + &format_attr_dsp.attr, + &format_attr_thr.attr, + &format_attr_fvc.attr, + &format_attr_pgt.attr, + &format_attr_map.attr, + &format_attr_iss.attr, + &format_attr_pld.attr, + NULL, +}; + +static struct attribute_group nhmex_uncore_mbox_format_group = { + .name = "format", + .attrs = nhmex_uncore_mbox_formats_attr, +}; + +static struct uncore_event_desc nhmex_uncore_mbox_events[] = { + INTEL_UNCORE_EVENT_DESC(bbox_cmds_read, "inc_sel=0xd,fvc=0x2800"), + INTEL_UNCORE_EVENT_DESC(bbox_cmds_write, "inc_sel=0xd,fvc=0x2820"), + { /* end: all zeroes */ }, +}; + +static struct uncore_event_desc wsmex_uncore_mbox_events[] = { + INTEL_UNCORE_EVENT_DESC(bbox_cmds_read, "inc_sel=0xd,fvc=0x5000"), + INTEL_UNCORE_EVENT_DESC(bbox_cmds_write, "inc_sel=0xd,fvc=0x5040"), + { /* end: all zeroes */ }, +}; + +static struct intel_uncore_ops nhmex_uncore_mbox_ops = { + NHMEX_UNCORE_OPS_COMMON_INIT(), + .enable_event = nhmex_mbox_msr_enable_event, + .hw_config = nhmex_mbox_hw_config, + .get_constraint = nhmex_mbox_get_constraint, + .put_constraint = nhmex_mbox_put_constraint, +}; + +static struct intel_uncore_type nhmex_uncore_mbox = { + .name = "mbox", + .num_counters = 6, + .num_boxes = 2, + .perf_ctr_bits = 48, + .event_ctl = NHMEX_M0_MSR_PMU_CTL0, + .perf_ctr = NHMEX_M0_MSR_PMU_CNT0, + .event_mask = NHMEX_M_PMON_RAW_EVENT_MASK, + .box_ctl = NHMEX_M0_MSR_GLOBAL_CTL, + .msr_offset = NHMEX_M_MSR_OFFSET, + .pair_ctr_ctl = 1, + .num_shared_regs = 8, + .event_descs = nhmex_uncore_mbox_events, + .ops = &nhmex_uncore_mbox_ops, + .format_group = &nhmex_uncore_mbox_format_group, +}; + +static void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + + /* adjust the main event selector and extra register index */ + if (reg1->idx % 2) { + reg1->idx--; + hwc->config -= 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT; + } else { + reg1->idx++; + hwc->config += 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT; + } + + /* adjust extra register config */ + switch (reg1->idx % 6) { + case 2: + /* shift the 8~15 bits to the 0~7 bits */ + reg1->config >>= 8; + break; + case 3: + /* shift the 0~7 bits to the 8~15 bits */ + reg1->config <<= 8; + break; + } +} + +/* + * Each rbox has 4 event set which monitor PQI port 0~3 or 4~7. + * An event set consists of 6 events, the 3rd and 4th events in + * an event set use the same extra register. So an event set uses + * 5 extra registers. + */ +static struct event_constraint * +nhmex_rbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; + struct intel_uncore_extra_reg *er; + unsigned long flags; + int idx, er_idx; + u64 config1; + bool ok = false; + + if (!uncore_box_is_fake(box) && reg1->alloc) + return NULL; + + idx = reg1->idx % 6; + config1 = reg1->config; +again: + er_idx = idx; + /* the 3rd and 4th events use the same extra register */ + if (er_idx > 2) + er_idx--; + er_idx += (reg1->idx / 6) * 5; + + er = &box->shared_regs[er_idx]; + raw_spin_lock_irqsave(&er->lock, flags); + if (idx < 2) { + if (!atomic_read(&er->ref) || er->config == reg1->config) { + atomic_inc(&er->ref); + er->config = reg1->config; + ok = true; + } + } else if (idx == 2 || idx == 3) { + /* + * these two events use different fields in a extra register, + * the 0~7 bits and the 8~15 bits respectively. + */ + u64 mask = 0xff << ((idx - 2) * 8); + if (!__BITS_VALUE(atomic_read(&er->ref), idx - 2, 8) || + !((er->config ^ config1) & mask)) { + atomic_add(1 << ((idx - 2) * 8), &er->ref); + er->config &= ~mask; + er->config |= config1 & mask; + ok = true; + } + } else { + if (!atomic_read(&er->ref) || + (er->config == (hwc->config >> 32) && + er->config1 == reg1->config && + er->config2 == reg2->config)) { + atomic_inc(&er->ref); + er->config = (hwc->config >> 32); + er->config1 = reg1->config; + er->config2 = reg2->config; + ok = true; + } + } + raw_spin_unlock_irqrestore(&er->lock, flags); + + if (!ok) { + /* + * The Rbox events are always in pairs. The paired + * events are functional identical, but use different + * extra registers. If we failed to take an extra + * register, try the alternative. + */ + idx ^= 1; + if (idx != reg1->idx % 6) { + if (idx == 2) + config1 >>= 8; + else if (idx == 3) + config1 <<= 8; + goto again; + } + } else { + if (!uncore_box_is_fake(box)) { + if (idx != reg1->idx % 6) + nhmex_rbox_alter_er(box, event); + reg1->alloc = 1; + } + return NULL; + } + return &uncore_constraint_empty; +} + +static void nhmex_rbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + struct intel_uncore_extra_reg *er; + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + int idx, er_idx; + + if (uncore_box_is_fake(box) || !reg1->alloc) + return; + + idx = reg1->idx % 6; + er_idx = idx; + if (er_idx > 2) + er_idx--; + er_idx += (reg1->idx / 6) * 5; + + er = &box->shared_regs[er_idx]; + if (idx == 2 || idx == 3) + atomic_sub(1 << ((idx - 2) * 8), &er->ref); + else + atomic_dec(&er->ref); + + reg1->alloc = 0; +} + +static int nhmex_rbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct hw_perf_event_extra *reg2 = &event->hw.branch_reg; + int idx; + + idx = (event->hw.config & NHMEX_R_PMON_CTL_EV_SEL_MASK) >> + NHMEX_R_PMON_CTL_EV_SEL_SHIFT; + if (idx >= 0x18) + return -EINVAL; + + reg1->idx = idx; + reg1->config = event->attr.config1; + + switch (idx % 6) { + case 4: + case 5: + hwc->config |= event->attr.config & (~0ULL << 32); + reg2->config = event->attr.config2; + break; + } + return 0; +} + +static void nhmex_rbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; + int idx, port; + + idx = reg1->idx; + port = idx / 6 + box->pmu->pmu_idx * 4; + + switch (idx % 6) { + case 0: + wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG0(port), reg1->config); + break; + case 1: + wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG1(port), reg1->config); + break; + case 2: + case 3: + wrmsrl(NHMEX_R_MSR_PORTN_QLX_CFG(port), + uncore_shared_reg_config(box, 2 + (idx / 6) * 5)); + break; + case 4: + wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port), + hwc->config >> 32); + wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MATCH(port), reg1->config); + wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MASK(port), reg2->config); + break; + case 5: + wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(port), + hwc->config >> 32); + wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MATCH(port), reg1->config); + wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MASK(port), reg2->config); + break; + } + + wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 | + (hwc->config & NHMEX_R_PMON_CTL_EV_SEL_MASK)); +} + +DEFINE_UNCORE_FORMAT_ATTR(xbr_mm_cfg, xbr_mm_cfg, "config:32-63"); +DEFINE_UNCORE_FORMAT_ATTR(xbr_match, xbr_match, "config1:0-63"); +DEFINE_UNCORE_FORMAT_ATTR(xbr_mask, xbr_mask, "config2:0-63"); +DEFINE_UNCORE_FORMAT_ATTR(qlx_cfg, qlx_cfg, "config1:0-15"); +DEFINE_UNCORE_FORMAT_ATTR(iperf_cfg, iperf_cfg, "config1:0-31"); + +static struct attribute *nhmex_uncore_rbox_formats_attr[] = { + &format_attr_event5.attr, + &format_attr_xbr_mm_cfg.attr, + &format_attr_xbr_match.attr, + &format_attr_xbr_mask.attr, + &format_attr_qlx_cfg.attr, + &format_attr_iperf_cfg.attr, + NULL, +}; + +static struct attribute_group nhmex_uncore_rbox_format_group = { + .name = "format", + .attrs = nhmex_uncore_rbox_formats_attr, +}; + +static struct uncore_event_desc nhmex_uncore_rbox_events[] = { + INTEL_UNCORE_EVENT_DESC(qpi0_flit_send, "event=0x0,iperf_cfg=0x80000000"), + INTEL_UNCORE_EVENT_DESC(qpi1_filt_send, "event=0x6,iperf_cfg=0x80000000"), + INTEL_UNCORE_EVENT_DESC(qpi0_idle_filt, "event=0x0,iperf_cfg=0x40000000"), + INTEL_UNCORE_EVENT_DESC(qpi1_idle_filt, "event=0x6,iperf_cfg=0x40000000"), + INTEL_UNCORE_EVENT_DESC(qpi0_date_response, "event=0x0,iperf_cfg=0xc4"), + INTEL_UNCORE_EVENT_DESC(qpi1_date_response, "event=0x6,iperf_cfg=0xc4"), + { /* end: all zeroes */ }, +}; + +static struct intel_uncore_ops nhmex_uncore_rbox_ops = { + NHMEX_UNCORE_OPS_COMMON_INIT(), + .enable_event = nhmex_rbox_msr_enable_event, + .hw_config = nhmex_rbox_hw_config, + .get_constraint = nhmex_rbox_get_constraint, + .put_constraint = nhmex_rbox_put_constraint, +}; + +static struct intel_uncore_type nhmex_uncore_rbox = { + .name = "rbox", + .num_counters = 8, + .num_boxes = 2, + .perf_ctr_bits = 48, + .event_ctl = NHMEX_R_MSR_PMON_CTL0, + .perf_ctr = NHMEX_R_MSR_PMON_CNT0, + .event_mask = NHMEX_R_PMON_RAW_EVENT_MASK, + .box_ctl = NHMEX_R_MSR_GLOBAL_CTL, + .msr_offset = NHMEX_R_MSR_OFFSET, + .pair_ctr_ctl = 1, + .num_shared_regs = 20, + .event_descs = nhmex_uncore_rbox_events, + .ops = &nhmex_uncore_rbox_ops, + .format_group = &nhmex_uncore_rbox_format_group +}; + +static struct intel_uncore_type *nhmex_msr_uncores[] = { + &nhmex_uncore_ubox, + &nhmex_uncore_cbox, + &nhmex_uncore_bbox, + &nhmex_uncore_sbox, + &nhmex_uncore_mbox, + &nhmex_uncore_rbox, + &nhmex_uncore_wbox, + NULL, +}; + +void nhmex_uncore_cpu_init(void) +{ + if (boot_cpu_data.x86_model == 46) + uncore_nhmex = true; + else + nhmex_uncore_mbox.event_descs = wsmex_uncore_mbox_events; + if (nhmex_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) + nhmex_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; + uncore_msr_uncores = nhmex_msr_uncores; +} +/* end of Nehalem-EX uncore support */ diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c new file mode 100644 index 000000000000..3001015b755c --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c @@ -0,0 +1,636 @@ +/* Nehalem/SandBridge/Haswell uncore support */ +#include "perf_event_intel_uncore.h" + +/* SNB event control */ +#define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff +#define SNB_UNC_CTL_UMASK_MASK 0x0000ff00 +#define SNB_UNC_CTL_EDGE_DET (1 << 18) +#define SNB_UNC_CTL_EN (1 << 22) +#define SNB_UNC_CTL_INVERT (1 << 23) +#define SNB_UNC_CTL_CMASK_MASK 0x1f000000 +#define NHM_UNC_CTL_CMASK_MASK 0xff000000 +#define NHM_UNC_FIXED_CTR_CTL_EN (1 << 0) + +#define SNB_UNC_RAW_EVENT_MASK (SNB_UNC_CTL_EV_SEL_MASK | \ + SNB_UNC_CTL_UMASK_MASK | \ + SNB_UNC_CTL_EDGE_DET | \ + SNB_UNC_CTL_INVERT | \ + SNB_UNC_CTL_CMASK_MASK) + +#define NHM_UNC_RAW_EVENT_MASK (SNB_UNC_CTL_EV_SEL_MASK | \ + SNB_UNC_CTL_UMASK_MASK | \ + SNB_UNC_CTL_EDGE_DET | \ + SNB_UNC_CTL_INVERT | \ + NHM_UNC_CTL_CMASK_MASK) + +/* SNB global control register */ +#define SNB_UNC_PERF_GLOBAL_CTL 0x391 +#define SNB_UNC_FIXED_CTR_CTRL 0x394 +#define SNB_UNC_FIXED_CTR 0x395 + +/* SNB uncore global control */ +#define SNB_UNC_GLOBAL_CTL_CORE_ALL ((1 << 4) - 1) +#define SNB_UNC_GLOBAL_CTL_EN (1 << 29) + +/* SNB Cbo register */ +#define SNB_UNC_CBO_0_PERFEVTSEL0 0x700 +#define SNB_UNC_CBO_0_PER_CTR0 0x706 +#define SNB_UNC_CBO_MSR_OFFSET 0x10 + +/* NHM global control register */ +#define NHM_UNC_PERF_GLOBAL_CTL 0x391 +#define NHM_UNC_FIXED_CTR 0x394 +#define NHM_UNC_FIXED_CTR_CTRL 0x395 + +/* NHM uncore global control */ +#define NHM_UNC_GLOBAL_CTL_EN_PC_ALL ((1ULL << 8) - 1) +#define NHM_UNC_GLOBAL_CTL_EN_FC (1ULL << 32) + +/* NHM uncore register */ +#define NHM_UNC_PERFEVTSEL0 0x3c0 +#define NHM_UNC_UNCORE_PMC0 0x3b0 + +DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7"); +DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); +DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); +DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23"); +DEFINE_UNCORE_FORMAT_ATTR(cmask5, cmask, "config:24-28"); +DEFINE_UNCORE_FORMAT_ATTR(cmask8, cmask, "config:24-31"); + +/* Sandy Bridge uncore support */ +static void snb_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + if (hwc->idx < UNCORE_PMC_IDX_FIXED) + wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN); + else + wrmsrl(hwc->config_base, SNB_UNC_CTL_EN); +} + +static void snb_uncore_msr_disable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + wrmsrl(event->hw.config_base, 0); +} + +static void snb_uncore_msr_init_box(struct intel_uncore_box *box) +{ + if (box->pmu->pmu_idx == 0) { + wrmsrl(SNB_UNC_PERF_GLOBAL_CTL, + SNB_UNC_GLOBAL_CTL_EN | SNB_UNC_GLOBAL_CTL_CORE_ALL); + } +} + +static struct uncore_event_desc snb_uncore_events[] = { + INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"), + { /* end: all zeroes */ }, +}; + +static struct attribute *snb_uncore_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_cmask5.attr, + NULL, +}; + +static struct attribute_group snb_uncore_format_group = { + .name = "format", + .attrs = snb_uncore_formats_attr, +}; + +static struct intel_uncore_ops snb_uncore_msr_ops = { + .init_box = snb_uncore_msr_init_box, + .disable_event = snb_uncore_msr_disable_event, + .enable_event = snb_uncore_msr_enable_event, + .read_counter = uncore_msr_read_counter, +}; + +static struct event_constraint snb_uncore_cbox_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x80, 0x1), + UNCORE_EVENT_CONSTRAINT(0x83, 0x1), + EVENT_CONSTRAINT_END +}; + +static struct intel_uncore_type snb_uncore_cbox = { + .name = "cbox", + .num_counters = 2, + .num_boxes = 4, + .perf_ctr_bits = 44, + .fixed_ctr_bits = 48, + .perf_ctr = SNB_UNC_CBO_0_PER_CTR0, + .event_ctl = SNB_UNC_CBO_0_PERFEVTSEL0, + .fixed_ctr = SNB_UNC_FIXED_CTR, + .fixed_ctl = SNB_UNC_FIXED_CTR_CTRL, + .single_fixed = 1, + .event_mask = SNB_UNC_RAW_EVENT_MASK, + .msr_offset = SNB_UNC_CBO_MSR_OFFSET, + .constraints = snb_uncore_cbox_constraints, + .ops = &snb_uncore_msr_ops, + .format_group = &snb_uncore_format_group, + .event_descs = snb_uncore_events, +}; + +static struct intel_uncore_type *snb_msr_uncores[] = { + &snb_uncore_cbox, + NULL, +}; + +void snb_uncore_cpu_init(void) +{ + uncore_msr_uncores = snb_msr_uncores; + if (snb_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) + snb_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; +} + +enum { + SNB_PCI_UNCORE_IMC, +}; + +static struct uncore_event_desc snb_uncore_imc_events[] = { + INTEL_UNCORE_EVENT_DESC(data_reads, "event=0x01"), + INTEL_UNCORE_EVENT_DESC(data_reads.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(data_reads.unit, "MiB"), + + INTEL_UNCORE_EVENT_DESC(data_writes, "event=0x02"), + INTEL_UNCORE_EVENT_DESC(data_writes.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(data_writes.unit, "MiB"), + + { /* end: all zeroes */ }, +}; + +#define SNB_UNCORE_PCI_IMC_EVENT_MASK 0xff +#define SNB_UNCORE_PCI_IMC_BAR_OFFSET 0x48 + +/* page size multiple covering all config regs */ +#define SNB_UNCORE_PCI_IMC_MAP_SIZE 0x6000 + +#define SNB_UNCORE_PCI_IMC_DATA_READS 0x1 +#define SNB_UNCORE_PCI_IMC_DATA_READS_BASE 0x5050 +#define SNB_UNCORE_PCI_IMC_DATA_WRITES 0x2 +#define SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE 0x5054 +#define SNB_UNCORE_PCI_IMC_CTR_BASE SNB_UNCORE_PCI_IMC_DATA_READS_BASE + +static struct attribute *snb_uncore_imc_formats_attr[] = { + &format_attr_event.attr, + NULL, +}; + +static struct attribute_group snb_uncore_imc_format_group = { + .name = "format", + .attrs = snb_uncore_imc_formats_attr, +}; + +static void snb_uncore_imc_init_box(struct intel_uncore_box *box) +{ + struct pci_dev *pdev = box->pci_dev; + int where = SNB_UNCORE_PCI_IMC_BAR_OFFSET; + resource_size_t addr; + u32 pci_dword; + + pci_read_config_dword(pdev, where, &pci_dword); + addr = pci_dword; + +#ifdef CONFIG_PHYS_ADDR_T_64BIT + pci_read_config_dword(pdev, where + 4, &pci_dword); + addr |= ((resource_size_t)pci_dword << 32); +#endif + + addr &= ~(PAGE_SIZE - 1); + + box->io_addr = ioremap(addr, SNB_UNCORE_PCI_IMC_MAP_SIZE); + box->hrtimer_duration = UNCORE_SNB_IMC_HRTIMER_INTERVAL; +} + +static void snb_uncore_imc_enable_box(struct intel_uncore_box *box) +{} + +static void snb_uncore_imc_disable_box(struct intel_uncore_box *box) +{} + +static void snb_uncore_imc_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{} + +static void snb_uncore_imc_disable_event(struct intel_uncore_box *box, struct perf_event *event) +{} + +static u64 snb_uncore_imc_read_counter(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + return (u64)*(unsigned int *)(box->io_addr + hwc->event_base); +} + +/* + * custom event_init() function because we define our own fixed, free + * running counters, so we do not want to conflict with generic uncore + * logic. Also simplifies processing + */ +static int snb_uncore_imc_event_init(struct perf_event *event) +{ + struct intel_uncore_pmu *pmu; + struct intel_uncore_box *box; + struct hw_perf_event *hwc = &event->hw; + u64 cfg = event->attr.config & SNB_UNCORE_PCI_IMC_EVENT_MASK; + int idx, base; + + if (event->attr.type != event->pmu->type) + return -ENOENT; + + pmu = uncore_event_to_pmu(event); + /* no device found for this pmu */ + if (pmu->func_id < 0) + return -ENOENT; + + /* Sampling not supported yet */ + if (hwc->sample_period) + 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; + + /* + * Place all uncore events for a particular physical package + * onto a single cpu + */ + if (event->cpu < 0) + return -EINVAL; + + /* check only supported bits are set */ + if (event->attr.config & ~SNB_UNCORE_PCI_IMC_EVENT_MASK) + return -EINVAL; + + box = uncore_pmu_to_box(pmu, event->cpu); + if (!box || box->cpu < 0) + return -EINVAL; + + event->cpu = box->cpu; + + event->hw.idx = -1; + event->hw.last_tag = ~0ULL; + event->hw.extra_reg.idx = EXTRA_REG_NONE; + event->hw.branch_reg.idx = EXTRA_REG_NONE; + /* + * check event is known (whitelist, determines counter) + */ + switch (cfg) { + case SNB_UNCORE_PCI_IMC_DATA_READS: + base = SNB_UNCORE_PCI_IMC_DATA_READS_BASE; + idx = UNCORE_PMC_IDX_FIXED; + break; + case SNB_UNCORE_PCI_IMC_DATA_WRITES: + base = SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE; + idx = UNCORE_PMC_IDX_FIXED + 1; + break; + default: + return -EINVAL; + } + + /* must be done before validate_group */ + event->hw.event_base = base; + event->hw.config = cfg; + event->hw.idx = idx; + + /* no group validation needed, we have free running counters */ + + return 0; +} + +static int snb_uncore_imc_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + return 0; +} + +static void snb_uncore_imc_event_start(struct perf_event *event, int flags) +{ + struct intel_uncore_box *box = uncore_event_to_box(event); + u64 count; + + if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED))) + return; + + event->hw.state = 0; + box->n_active++; + + list_add_tail(&event->active_entry, &box->active_list); + + count = snb_uncore_imc_read_counter(box, event); + local64_set(&event->hw.prev_count, count); + + if (box->n_active == 1) + uncore_pmu_start_hrtimer(box); +} + +static void snb_uncore_imc_event_stop(struct perf_event *event, int flags) +{ + struct intel_uncore_box *box = uncore_event_to_box(event); + struct hw_perf_event *hwc = &event->hw; + + if (!(hwc->state & PERF_HES_STOPPED)) { + box->n_active--; + + WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); + hwc->state |= PERF_HES_STOPPED; + + list_del(&event->active_entry); + + if (box->n_active == 0) + uncore_pmu_cancel_hrtimer(box); + } + + if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) { + /* + * Drain the remaining delta count out of a event + * that we are disabling: + */ + uncore_perf_event_update(box, event); + hwc->state |= PERF_HES_UPTODATE; + } +} + +static int snb_uncore_imc_event_add(struct perf_event *event, int flags) +{ + struct intel_uncore_box *box = uncore_event_to_box(event); + struct hw_perf_event *hwc = &event->hw; + + if (!box) + return -ENODEV; + + hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED; + if (!(flags & PERF_EF_START)) + hwc->state |= PERF_HES_ARCH; + + snb_uncore_imc_event_start(event, 0); + + box->n_events++; + + return 0; +} + +static void snb_uncore_imc_event_del(struct perf_event *event, int flags) +{ + struct intel_uncore_box *box = uncore_event_to_box(event); + int i; + + snb_uncore_imc_event_stop(event, PERF_EF_UPDATE); + + for (i = 0; i < box->n_events; i++) { + if (event == box->event_list[i]) { + --box->n_events; + break; + } + } +} + +static int snb_pci2phy_map_init(int devid) +{ + struct pci_dev *dev = NULL; + int bus; + + dev = pci_get_device(PCI_VENDOR_ID_INTEL, devid, dev); + if (!dev) + return -ENOTTY; + + bus = dev->bus->number; + + uncore_pcibus_to_physid[bus] = 0; + + pci_dev_put(dev); + + return 0; +} + +static struct pmu snb_uncore_imc_pmu = { + .task_ctx_nr = perf_invalid_context, + .event_init = snb_uncore_imc_event_init, + .add = snb_uncore_imc_event_add, + .del = snb_uncore_imc_event_del, + .start = snb_uncore_imc_event_start, + .stop = snb_uncore_imc_event_stop, + .read = uncore_pmu_event_read, +}; + +static struct intel_uncore_ops snb_uncore_imc_ops = { + .init_box = snb_uncore_imc_init_box, + .enable_box = snb_uncore_imc_enable_box, + .disable_box = snb_uncore_imc_disable_box, + .disable_event = snb_uncore_imc_disable_event, + .enable_event = snb_uncore_imc_enable_event, + .hw_config = snb_uncore_imc_hw_config, + .read_counter = snb_uncore_imc_read_counter, +}; + +static struct intel_uncore_type snb_uncore_imc = { + .name = "imc", + .num_counters = 2, + .num_boxes = 1, + .fixed_ctr_bits = 32, + .fixed_ctr = SNB_UNCORE_PCI_IMC_CTR_BASE, + .event_descs = snb_uncore_imc_events, + .format_group = &snb_uncore_imc_format_group, + .perf_ctr = SNB_UNCORE_PCI_IMC_DATA_READS_BASE, + .event_mask = SNB_UNCORE_PCI_IMC_EVENT_MASK, + .ops = &snb_uncore_imc_ops, + .pmu = &snb_uncore_imc_pmu, +}; + +static struct intel_uncore_type *snb_pci_uncores[] = { + [SNB_PCI_UNCORE_IMC] = &snb_uncore_imc, + NULL, +}; + +static const struct pci_device_id snb_uncore_pci_ids[] = { + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SNB_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* end: all zeroes */ }, +}; + +static const struct pci_device_id ivb_uncore_pci_ids[] = { + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IVB_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IVB_E3_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* end: all zeroes */ }, +}; + +static const struct pci_device_id hsw_uncore_pci_ids[] = { + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_HSW_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* end: all zeroes */ }, +}; + +static struct pci_driver snb_uncore_pci_driver = { + .name = "snb_uncore", + .id_table = snb_uncore_pci_ids, +}; + +static struct pci_driver ivb_uncore_pci_driver = { + .name = "ivb_uncore", + .id_table = ivb_uncore_pci_ids, +}; + +static struct pci_driver hsw_uncore_pci_driver = { + .name = "hsw_uncore", + .id_table = hsw_uncore_pci_ids, +}; + +struct imc_uncore_pci_dev { + __u32 pci_id; + struct pci_driver *driver; +}; +#define IMC_DEV(a, d) \ + { .pci_id = PCI_DEVICE_ID_INTEL_##a, .driver = (d) } + +static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = { + IMC_DEV(SNB_IMC, &snb_uncore_pci_driver), + IMC_DEV(IVB_IMC, &ivb_uncore_pci_driver), /* 3rd Gen Core processor */ + IMC_DEV(IVB_E3_IMC, &ivb_uncore_pci_driver), /* Xeon E3-1200 v2/3rd Gen Core processor */ + IMC_DEV(HSW_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core Processor */ + { /* end marker */ } +}; + + +#define for_each_imc_pci_id(x, t) \ + for (x = (t); (x)->pci_id; x++) + +static struct pci_driver *imc_uncore_find_dev(void) +{ + const struct imc_uncore_pci_dev *p; + int ret; + + for_each_imc_pci_id(p, desktop_imc_pci_ids) { + ret = snb_pci2phy_map_init(p->pci_id); + if (ret == 0) + return p->driver; + } + return NULL; +} + +static int imc_uncore_pci_init(void) +{ + struct pci_driver *imc_drv = imc_uncore_find_dev(); + + if (!imc_drv) + return -ENODEV; + + uncore_pci_uncores = snb_pci_uncores; + uncore_pci_driver = imc_drv; + + return 0; +} + +int snb_uncore_pci_init(void) +{ + return imc_uncore_pci_init(); +} + +int ivb_uncore_pci_init(void) +{ + return imc_uncore_pci_init(); +} +int hsw_uncore_pci_init(void) +{ + return imc_uncore_pci_init(); +} + +/* end of Sandy Bridge uncore support */ + +/* Nehalem uncore support */ +static void nhm_uncore_msr_disable_box(struct intel_uncore_box *box) +{ + wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, 0); +} + +static void nhm_uncore_msr_enable_box(struct intel_uncore_box *box) +{ + wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, NHM_UNC_GLOBAL_CTL_EN_PC_ALL | NHM_UNC_GLOBAL_CTL_EN_FC); +} + +static void nhm_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + if (hwc->idx < UNCORE_PMC_IDX_FIXED) + wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN); + else + wrmsrl(hwc->config_base, NHM_UNC_FIXED_CTR_CTL_EN); +} + +static struct attribute *nhm_uncore_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_cmask8.attr, + NULL, +}; + +static struct attribute_group nhm_uncore_format_group = { + .name = "format", + .attrs = nhm_uncore_formats_attr, +}; + +static struct uncore_event_desc nhm_uncore_events[] = { + INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"), + INTEL_UNCORE_EVENT_DESC(qmc_writes_full_any, "event=0x2f,umask=0x0f"), + INTEL_UNCORE_EVENT_DESC(qmc_normal_reads_any, "event=0x2c,umask=0x0f"), + INTEL_UNCORE_EVENT_DESC(qhl_request_ioh_reads, "event=0x20,umask=0x01"), + INTEL_UNCORE_EVENT_DESC(qhl_request_ioh_writes, "event=0x20,umask=0x02"), + INTEL_UNCORE_EVENT_DESC(qhl_request_remote_reads, "event=0x20,umask=0x04"), + INTEL_UNCORE_EVENT_DESC(qhl_request_remote_writes, "event=0x20,umask=0x08"), + INTEL_UNCORE_EVENT_DESC(qhl_request_local_reads, "event=0x20,umask=0x10"), + INTEL_UNCORE_EVENT_DESC(qhl_request_local_writes, "event=0x20,umask=0x20"), + { /* end: all zeroes */ }, +}; + +static struct intel_uncore_ops nhm_uncore_msr_ops = { + .disable_box = nhm_uncore_msr_disable_box, + .enable_box = nhm_uncore_msr_enable_box, + .disable_event = snb_uncore_msr_disable_event, + .enable_event = nhm_uncore_msr_enable_event, + .read_counter = uncore_msr_read_counter, +}; + +static struct intel_uncore_type nhm_uncore = { + .name = "", + .num_counters = 8, + .num_boxes = 1, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .event_ctl = NHM_UNC_PERFEVTSEL0, + .perf_ctr = NHM_UNC_UNCORE_PMC0, + .fixed_ctr = NHM_UNC_FIXED_CTR, + .fixed_ctl = NHM_UNC_FIXED_CTR_CTRL, + .event_mask = NHM_UNC_RAW_EVENT_MASK, + .event_descs = nhm_uncore_events, + .ops = &nhm_uncore_msr_ops, + .format_group = &nhm_uncore_format_group, +}; + +static struct intel_uncore_type *nhm_msr_uncores[] = { + &nhm_uncore, + NULL, +}; + +void nhm_uncore_cpu_init(void) +{ + uncore_msr_uncores = nhm_msr_uncores; +} + +/* end of Nehalem uncore support */ diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c new file mode 100644 index 000000000000..21af6149edf2 --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c @@ -0,0 +1,2324 @@ +/* SandyBridge-EP/IvyTown uncore support */ +#include "perf_event_intel_uncore.h" + + +/* SNB-EP Box level control */ +#define SNBEP_PMON_BOX_CTL_RST_CTRL (1 << 0) +#define SNBEP_PMON_BOX_CTL_RST_CTRS (1 << 1) +#define SNBEP_PMON_BOX_CTL_FRZ (1 << 8) +#define SNBEP_PMON_BOX_CTL_FRZ_EN (1 << 16) +#define SNBEP_PMON_BOX_CTL_INT (SNBEP_PMON_BOX_CTL_RST_CTRL | \ + SNBEP_PMON_BOX_CTL_RST_CTRS | \ + SNBEP_PMON_BOX_CTL_FRZ_EN) +/* SNB-EP event control */ +#define SNBEP_PMON_CTL_EV_SEL_MASK 0x000000ff +#define SNBEP_PMON_CTL_UMASK_MASK 0x0000ff00 +#define SNBEP_PMON_CTL_RST (1 << 17) +#define SNBEP_PMON_CTL_EDGE_DET (1 << 18) +#define SNBEP_PMON_CTL_EV_SEL_EXT (1 << 21) +#define SNBEP_PMON_CTL_EN (1 << 22) +#define SNBEP_PMON_CTL_INVERT (1 << 23) +#define SNBEP_PMON_CTL_TRESH_MASK 0xff000000 +#define SNBEP_PMON_RAW_EVENT_MASK (SNBEP_PMON_CTL_EV_SEL_MASK | \ + SNBEP_PMON_CTL_UMASK_MASK | \ + SNBEP_PMON_CTL_EDGE_DET | \ + SNBEP_PMON_CTL_INVERT | \ + SNBEP_PMON_CTL_TRESH_MASK) + +/* SNB-EP Ubox event control */ +#define SNBEP_U_MSR_PMON_CTL_TRESH_MASK 0x1f000000 +#define SNBEP_U_MSR_PMON_RAW_EVENT_MASK \ + (SNBEP_PMON_CTL_EV_SEL_MASK | \ + SNBEP_PMON_CTL_UMASK_MASK | \ + SNBEP_PMON_CTL_EDGE_DET | \ + SNBEP_PMON_CTL_INVERT | \ + SNBEP_U_MSR_PMON_CTL_TRESH_MASK) + +#define SNBEP_CBO_PMON_CTL_TID_EN (1 << 19) +#define SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK (SNBEP_PMON_RAW_EVENT_MASK | \ + SNBEP_CBO_PMON_CTL_TID_EN) + +/* SNB-EP PCU event control */ +#define SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK 0x0000c000 +#define SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK 0x1f000000 +#define SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT (1 << 30) +#define SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET (1 << 31) +#define SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK \ + (SNBEP_PMON_CTL_EV_SEL_MASK | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \ + SNBEP_PMON_CTL_EDGE_DET | \ + SNBEP_PMON_CTL_EV_SEL_EXT | \ + SNBEP_PMON_CTL_INVERT | \ + SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET) + +#define SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK \ + (SNBEP_PMON_RAW_EVENT_MASK | \ + SNBEP_PMON_CTL_EV_SEL_EXT) + +/* SNB-EP pci control register */ +#define SNBEP_PCI_PMON_BOX_CTL 0xf4 +#define SNBEP_PCI_PMON_CTL0 0xd8 +/* SNB-EP pci counter register */ +#define SNBEP_PCI_PMON_CTR0 0xa0 + +/* SNB-EP home agent register */ +#define SNBEP_HA_PCI_PMON_BOX_ADDRMATCH0 0x40 +#define SNBEP_HA_PCI_PMON_BOX_ADDRMATCH1 0x44 +#define SNBEP_HA_PCI_PMON_BOX_OPCODEMATCH 0x48 +/* SNB-EP memory controller register */ +#define SNBEP_MC_CHy_PCI_PMON_FIXED_CTL 0xf0 +#define SNBEP_MC_CHy_PCI_PMON_FIXED_CTR 0xd0 +/* SNB-EP QPI register */ +#define SNBEP_Q_Py_PCI_PMON_PKT_MATCH0 0x228 +#define SNBEP_Q_Py_PCI_PMON_PKT_MATCH1 0x22c +#define SNBEP_Q_Py_PCI_PMON_PKT_MASK0 0x238 +#define SNBEP_Q_Py_PCI_PMON_PKT_MASK1 0x23c + +/* SNB-EP Ubox register */ +#define SNBEP_U_MSR_PMON_CTR0 0xc16 +#define SNBEP_U_MSR_PMON_CTL0 0xc10 + +#define SNBEP_U_MSR_PMON_UCLK_FIXED_CTL 0xc08 +#define SNBEP_U_MSR_PMON_UCLK_FIXED_CTR 0xc09 + +/* SNB-EP Cbo register */ +#define SNBEP_C0_MSR_PMON_CTR0 0xd16 +#define SNBEP_C0_MSR_PMON_CTL0 0xd10 +#define SNBEP_C0_MSR_PMON_BOX_CTL 0xd04 +#define SNBEP_C0_MSR_PMON_BOX_FILTER 0xd14 +#define SNBEP_CBO_MSR_OFFSET 0x20 + +#define SNBEP_CB0_MSR_PMON_BOX_FILTER_TID 0x1f +#define SNBEP_CB0_MSR_PMON_BOX_FILTER_NID 0x3fc00 +#define SNBEP_CB0_MSR_PMON_BOX_FILTER_STATE 0x7c0000 +#define SNBEP_CB0_MSR_PMON_BOX_FILTER_OPC 0xff800000 + +#define SNBEP_CBO_EVENT_EXTRA_REG(e, m, i) { \ + .event = (e), \ + .msr = SNBEP_C0_MSR_PMON_BOX_FILTER, \ + .config_mask = (m), \ + .idx = (i) \ +} + +/* SNB-EP PCU register */ +#define SNBEP_PCU_MSR_PMON_CTR0 0xc36 +#define SNBEP_PCU_MSR_PMON_CTL0 0xc30 +#define SNBEP_PCU_MSR_PMON_BOX_CTL 0xc24 +#define SNBEP_PCU_MSR_PMON_BOX_FILTER 0xc34 +#define SNBEP_PCU_MSR_PMON_BOX_FILTER_MASK 0xffffffff +#define SNBEP_PCU_MSR_CORE_C3_CTR 0x3fc +#define SNBEP_PCU_MSR_CORE_C6_CTR 0x3fd + +/* IVBEP event control */ +#define IVBEP_PMON_BOX_CTL_INT (SNBEP_PMON_BOX_CTL_RST_CTRL | \ + SNBEP_PMON_BOX_CTL_RST_CTRS) +#define IVBEP_PMON_RAW_EVENT_MASK (SNBEP_PMON_CTL_EV_SEL_MASK | \ + SNBEP_PMON_CTL_UMASK_MASK | \ + SNBEP_PMON_CTL_EDGE_DET | \ + SNBEP_PMON_CTL_TRESH_MASK) +/* IVBEP Ubox */ +#define IVBEP_U_MSR_PMON_GLOBAL_CTL 0xc00 +#define IVBEP_U_PMON_GLOBAL_FRZ_ALL (1 << 31) +#define IVBEP_U_PMON_GLOBAL_UNFRZ_ALL (1 << 29) + +#define IVBEP_U_MSR_PMON_RAW_EVENT_MASK \ + (SNBEP_PMON_CTL_EV_SEL_MASK | \ + SNBEP_PMON_CTL_UMASK_MASK | \ + SNBEP_PMON_CTL_EDGE_DET | \ + SNBEP_U_MSR_PMON_CTL_TRESH_MASK) +/* IVBEP Cbo */ +#define IVBEP_CBO_MSR_PMON_RAW_EVENT_MASK (IVBEP_PMON_RAW_EVENT_MASK | \ + SNBEP_CBO_PMON_CTL_TID_EN) + +#define IVBEP_CB0_MSR_PMON_BOX_FILTER_TID (0x1fULL << 0) +#define IVBEP_CB0_MSR_PMON_BOX_FILTER_LINK (0xfULL << 5) +#define IVBEP_CB0_MSR_PMON_BOX_FILTER_STATE (0x3fULL << 17) +#define IVBEP_CB0_MSR_PMON_BOX_FILTER_NID (0xffffULL << 32) +#define IVBEP_CB0_MSR_PMON_BOX_FILTER_OPC (0x1ffULL << 52) +#define IVBEP_CB0_MSR_PMON_BOX_FILTER_C6 (0x1ULL << 61) +#define IVBEP_CB0_MSR_PMON_BOX_FILTER_NC (0x1ULL << 62) +#define IVBEP_CB0_MSR_PMON_BOX_FILTER_ISOC (0x1ULL << 63) + +/* IVBEP home agent */ +#define IVBEP_HA_PCI_PMON_CTL_Q_OCC_RST (1 << 16) +#define IVBEP_HA_PCI_PMON_RAW_EVENT_MASK \ + (IVBEP_PMON_RAW_EVENT_MASK | \ + IVBEP_HA_PCI_PMON_CTL_Q_OCC_RST) +/* IVBEP PCU */ +#define IVBEP_PCU_MSR_PMON_RAW_EVENT_MASK \ + (SNBEP_PMON_CTL_EV_SEL_MASK | \ + SNBEP_PMON_CTL_EV_SEL_EXT | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \ + SNBEP_PMON_CTL_EDGE_DET | \ + SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET) +/* IVBEP QPI */ +#define IVBEP_QPI_PCI_PMON_RAW_EVENT_MASK \ + (IVBEP_PMON_RAW_EVENT_MASK | \ + SNBEP_PMON_CTL_EV_SEL_EXT) + +#define __BITS_VALUE(x, i, n) ((typeof(x))(((x) >> ((i) * (n))) & \ + ((1ULL << (n)) - 1))) + +/* Haswell-EP Ubox */ +#define HSWEP_U_MSR_PMON_CTR0 0x705 +#define HSWEP_U_MSR_PMON_CTL0 0x709 +#define HSWEP_U_MSR_PMON_FILTER 0x707 + +#define HSWEP_U_MSR_PMON_UCLK_FIXED_CTL 0x703 +#define HSWEP_U_MSR_PMON_UCLK_FIXED_CTR 0x704 + +#define HSWEP_U_MSR_PMON_BOX_FILTER_TID (0x1 << 0) +#define HSWEP_U_MSR_PMON_BOX_FILTER_CID (0x1fULL << 1) +#define HSWEP_U_MSR_PMON_BOX_FILTER_MASK \ + (HSWEP_U_MSR_PMON_BOX_FILTER_TID | \ + HSWEP_U_MSR_PMON_BOX_FILTER_CID) + +/* Haswell-EP CBo */ +#define HSWEP_C0_MSR_PMON_CTR0 0xe08 +#define HSWEP_C0_MSR_PMON_CTL0 0xe01 +#define HSWEP_C0_MSR_PMON_BOX_CTL 0xe00 +#define HSWEP_C0_MSR_PMON_BOX_FILTER0 0xe05 +#define HSWEP_CBO_MSR_OFFSET 0x10 + + +#define HSWEP_CB0_MSR_PMON_BOX_FILTER_TID (0x3fULL << 0) +#define HSWEP_CB0_MSR_PMON_BOX_FILTER_LINK (0xfULL << 6) +#define HSWEP_CB0_MSR_PMON_BOX_FILTER_STATE (0x7fULL << 17) +#define HSWEP_CB0_MSR_PMON_BOX_FILTER_NID (0xffffULL << 32) +#define HSWEP_CB0_MSR_PMON_BOX_FILTER_OPC (0x1ffULL << 52) +#define HSWEP_CB0_MSR_PMON_BOX_FILTER_C6 (0x1ULL << 61) +#define HSWEP_CB0_MSR_PMON_BOX_FILTER_NC (0x1ULL << 62) +#define HSWEP_CB0_MSR_PMON_BOX_FILTER_ISOC (0x1ULL << 63) + + +/* Haswell-EP Sbox */ +#define HSWEP_S0_MSR_PMON_CTR0 0x726 +#define HSWEP_S0_MSR_PMON_CTL0 0x721 +#define HSWEP_S0_MSR_PMON_BOX_CTL 0x720 +#define HSWEP_SBOX_MSR_OFFSET 0xa +#define HSWEP_S_MSR_PMON_RAW_EVENT_MASK (SNBEP_PMON_RAW_EVENT_MASK | \ + SNBEP_CBO_PMON_CTL_TID_EN) + +/* Haswell-EP PCU */ +#define HSWEP_PCU_MSR_PMON_CTR0 0x717 +#define HSWEP_PCU_MSR_PMON_CTL0 0x711 +#define HSWEP_PCU_MSR_PMON_BOX_CTL 0x710 +#define HSWEP_PCU_MSR_PMON_BOX_FILTER 0x715 + + +DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7"); +DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21"); +DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); +DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); +DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19"); +DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23"); +DEFINE_UNCORE_FORMAT_ATTR(thresh8, thresh, "config:24-31"); +DEFINE_UNCORE_FORMAT_ATTR(thresh5, thresh, "config:24-28"); +DEFINE_UNCORE_FORMAT_ATTR(occ_sel, occ_sel, "config:14-15"); +DEFINE_UNCORE_FORMAT_ATTR(occ_invert, occ_invert, "config:30"); +DEFINE_UNCORE_FORMAT_ATTR(occ_edge, occ_edge, "config:14-51"); +DEFINE_UNCORE_FORMAT_ATTR(filter_tid, filter_tid, "config1:0-4"); +DEFINE_UNCORE_FORMAT_ATTR(filter_tid2, filter_tid, "config1:0"); +DEFINE_UNCORE_FORMAT_ATTR(filter_tid3, filter_tid, "config1:0-5"); +DEFINE_UNCORE_FORMAT_ATTR(filter_cid, filter_cid, "config1:5"); +DEFINE_UNCORE_FORMAT_ATTR(filter_link, filter_link, "config1:5-8"); +DEFINE_UNCORE_FORMAT_ATTR(filter_link2, filter_link, "config1:6-8"); +DEFINE_UNCORE_FORMAT_ATTR(filter_nid, filter_nid, "config1:10-17"); +DEFINE_UNCORE_FORMAT_ATTR(filter_nid2, filter_nid, "config1:32-47"); +DEFINE_UNCORE_FORMAT_ATTR(filter_state, filter_state, "config1:18-22"); +DEFINE_UNCORE_FORMAT_ATTR(filter_state2, filter_state, "config1:17-22"); +DEFINE_UNCORE_FORMAT_ATTR(filter_state3, filter_state, "config1:17-23"); +DEFINE_UNCORE_FORMAT_ATTR(filter_opc, filter_opc, "config1:23-31"); +DEFINE_UNCORE_FORMAT_ATTR(filter_opc2, filter_opc, "config1:52-60"); +DEFINE_UNCORE_FORMAT_ATTR(filter_nc, filter_nc, "config1:62"); +DEFINE_UNCORE_FORMAT_ATTR(filter_c6, filter_c6, "config1:61"); +DEFINE_UNCORE_FORMAT_ATTR(filter_isoc, filter_isoc, "config1:63"); +DEFINE_UNCORE_FORMAT_ATTR(filter_band0, filter_band0, "config1:0-7"); +DEFINE_UNCORE_FORMAT_ATTR(filter_band1, filter_band1, "config1:8-15"); +DEFINE_UNCORE_FORMAT_ATTR(filter_band2, filter_band2, "config1:16-23"); +DEFINE_UNCORE_FORMAT_ATTR(filter_band3, filter_band3, "config1:24-31"); +DEFINE_UNCORE_FORMAT_ATTR(match_rds, match_rds, "config1:48-51"); +DEFINE_UNCORE_FORMAT_ATTR(match_rnid30, match_rnid30, "config1:32-35"); +DEFINE_UNCORE_FORMAT_ATTR(match_rnid4, match_rnid4, "config1:31"); +DEFINE_UNCORE_FORMAT_ATTR(match_dnid, match_dnid, "config1:13-17"); +DEFINE_UNCORE_FORMAT_ATTR(match_mc, match_mc, "config1:9-12"); +DEFINE_UNCORE_FORMAT_ATTR(match_opc, match_opc, "config1:5-8"); +DEFINE_UNCORE_FORMAT_ATTR(match_vnw, match_vnw, "config1:3-4"); +DEFINE_UNCORE_FORMAT_ATTR(match0, match0, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(match1, match1, "config1:32-63"); +DEFINE_UNCORE_FORMAT_ATTR(mask_rds, mask_rds, "config2:48-51"); +DEFINE_UNCORE_FORMAT_ATTR(mask_rnid30, mask_rnid30, "config2:32-35"); +DEFINE_UNCORE_FORMAT_ATTR(mask_rnid4, mask_rnid4, "config2:31"); +DEFINE_UNCORE_FORMAT_ATTR(mask_dnid, mask_dnid, "config2:13-17"); +DEFINE_UNCORE_FORMAT_ATTR(mask_mc, mask_mc, "config2:9-12"); +DEFINE_UNCORE_FORMAT_ATTR(mask_opc, mask_opc, "config2:5-8"); +DEFINE_UNCORE_FORMAT_ATTR(mask_vnw, mask_vnw, "config2:3-4"); +DEFINE_UNCORE_FORMAT_ATTR(mask0, mask0, "config2:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(mask1, mask1, "config2:32-63"); + +static void snbep_uncore_pci_disable_box(struct intel_uncore_box *box) +{ + struct pci_dev *pdev = box->pci_dev; + int box_ctl = uncore_pci_box_ctl(box); + u32 config = 0; + + if (!pci_read_config_dword(pdev, box_ctl, &config)) { + config |= SNBEP_PMON_BOX_CTL_FRZ; + pci_write_config_dword(pdev, box_ctl, config); + } +} + +static void snbep_uncore_pci_enable_box(struct intel_uncore_box *box) +{ + struct pci_dev *pdev = box->pci_dev; + int box_ctl = uncore_pci_box_ctl(box); + u32 config = 0; + + if (!pci_read_config_dword(pdev, box_ctl, &config)) { + config &= ~SNBEP_PMON_BOX_CTL_FRZ; + pci_write_config_dword(pdev, box_ctl, config); + } +} + +static void snbep_uncore_pci_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + + pci_write_config_dword(pdev, hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN); +} + +static void snbep_uncore_pci_disable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + + pci_write_config_dword(pdev, hwc->config_base, hwc->config); +} + +static u64 snbep_uncore_pci_read_counter(struct intel_uncore_box *box, struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + u64 count = 0; + + pci_read_config_dword(pdev, hwc->event_base, (u32 *)&count); + pci_read_config_dword(pdev, hwc->event_base + 4, (u32 *)&count + 1); + + return count; +} + +static void snbep_uncore_pci_init_box(struct intel_uncore_box *box) +{ + struct pci_dev *pdev = box->pci_dev; + + pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, SNBEP_PMON_BOX_CTL_INT); +} + +static void snbep_uncore_msr_disable_box(struct intel_uncore_box *box) +{ + u64 config; + unsigned msr; + + msr = uncore_msr_box_ctl(box); + if (msr) { + rdmsrl(msr, config); + config |= SNBEP_PMON_BOX_CTL_FRZ; + wrmsrl(msr, config); + } +} + +static void snbep_uncore_msr_enable_box(struct intel_uncore_box *box) +{ + u64 config; + unsigned msr; + + msr = uncore_msr_box_ctl(box); + if (msr) { + rdmsrl(msr, config); + config &= ~SNBEP_PMON_BOX_CTL_FRZ; + wrmsrl(msr, config); + } +} + +static void snbep_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + + if (reg1->idx != EXTRA_REG_NONE) + wrmsrl(reg1->reg, uncore_shared_reg_config(box, 0)); + + wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN); +} + +static void snbep_uncore_msr_disable_event(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + wrmsrl(hwc->config_base, hwc->config); +} + +static void snbep_uncore_msr_init_box(struct intel_uncore_box *box) +{ + unsigned msr = uncore_msr_box_ctl(box); + + if (msr) + wrmsrl(msr, SNBEP_PMON_BOX_CTL_INT); +} + +static struct attribute *snbep_uncore_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + NULL, +}; + +static struct attribute *snbep_uncore_ubox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh5.attr, + NULL, +}; + +static struct attribute *snbep_uncore_cbox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_tid_en.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + &format_attr_filter_tid.attr, + &format_attr_filter_nid.attr, + &format_attr_filter_state.attr, + &format_attr_filter_opc.attr, + NULL, +}; + +static struct attribute *snbep_uncore_pcu_formats_attr[] = { + &format_attr_event_ext.attr, + &format_attr_occ_sel.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh5.attr, + &format_attr_occ_invert.attr, + &format_attr_occ_edge.attr, + &format_attr_filter_band0.attr, + &format_attr_filter_band1.attr, + &format_attr_filter_band2.attr, + &format_attr_filter_band3.attr, + NULL, +}; + +static struct attribute *snbep_uncore_qpi_formats_attr[] = { + &format_attr_event_ext.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + &format_attr_match_rds.attr, + &format_attr_match_rnid30.attr, + &format_attr_match_rnid4.attr, + &format_attr_match_dnid.attr, + &format_attr_match_mc.attr, + &format_attr_match_opc.attr, + &format_attr_match_vnw.attr, + &format_attr_match0.attr, + &format_attr_match1.attr, + &format_attr_mask_rds.attr, + &format_attr_mask_rnid30.attr, + &format_attr_mask_rnid4.attr, + &format_attr_mask_dnid.attr, + &format_attr_mask_mc.attr, + &format_attr_mask_opc.attr, + &format_attr_mask_vnw.attr, + &format_attr_mask0.attr, + &format_attr_mask1.attr, + NULL, +}; + +static struct uncore_event_desc snbep_uncore_imc_events[] = { + INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"), + INTEL_UNCORE_EVENT_DESC(cas_count_read, "event=0x04,umask=0x03"), + INTEL_UNCORE_EVENT_DESC(cas_count_read.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(cas_count_read.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(cas_count_write, "event=0x04,umask=0x0c"), + INTEL_UNCORE_EVENT_DESC(cas_count_write.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(cas_count_write.unit, "MiB"), + { /* end: all zeroes */ }, +}; + +static struct uncore_event_desc snbep_uncore_qpi_events[] = { + INTEL_UNCORE_EVENT_DESC(clockticks, "event=0x14"), + INTEL_UNCORE_EVENT_DESC(txl_flits_active, "event=0x00,umask=0x06"), + INTEL_UNCORE_EVENT_DESC(drs_data, "event=0x102,umask=0x08"), + INTEL_UNCORE_EVENT_DESC(ncb_data, "event=0x103,umask=0x04"), + { /* end: all zeroes */ }, +}; + +static struct attribute_group snbep_uncore_format_group = { + .name = "format", + .attrs = snbep_uncore_formats_attr, +}; + +static struct attribute_group snbep_uncore_ubox_format_group = { + .name = "format", + .attrs = snbep_uncore_ubox_formats_attr, +}; + +static struct attribute_group snbep_uncore_cbox_format_group = { + .name = "format", + .attrs = snbep_uncore_cbox_formats_attr, +}; + +static struct attribute_group snbep_uncore_pcu_format_group = { + .name = "format", + .attrs = snbep_uncore_pcu_formats_attr, +}; + +static struct attribute_group snbep_uncore_qpi_format_group = { + .name = "format", + .attrs = snbep_uncore_qpi_formats_attr, +}; + +#define __SNBEP_UNCORE_MSR_OPS_COMMON_INIT() \ + .disable_box = snbep_uncore_msr_disable_box, \ + .enable_box = snbep_uncore_msr_enable_box, \ + .disable_event = snbep_uncore_msr_disable_event, \ + .enable_event = snbep_uncore_msr_enable_event, \ + .read_counter = uncore_msr_read_counter + +#define SNBEP_UNCORE_MSR_OPS_COMMON_INIT() \ + __SNBEP_UNCORE_MSR_OPS_COMMON_INIT(), \ + .init_box = snbep_uncore_msr_init_box \ + +static struct intel_uncore_ops snbep_uncore_msr_ops = { + SNBEP_UNCORE_MSR_OPS_COMMON_INIT(), +}; + +#define SNBEP_UNCORE_PCI_OPS_COMMON_INIT() \ + .init_box = snbep_uncore_pci_init_box, \ + .disable_box = snbep_uncore_pci_disable_box, \ + .enable_box = snbep_uncore_pci_enable_box, \ + .disable_event = snbep_uncore_pci_disable_event, \ + .read_counter = snbep_uncore_pci_read_counter + +static struct intel_uncore_ops snbep_uncore_pci_ops = { + SNBEP_UNCORE_PCI_OPS_COMMON_INIT(), + .enable_event = snbep_uncore_pci_enable_event, \ +}; + +static struct event_constraint snbep_uncore_cbox_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x01, 0x1), + UNCORE_EVENT_CONSTRAINT(0x02, 0x3), + UNCORE_EVENT_CONSTRAINT(0x04, 0x3), + UNCORE_EVENT_CONSTRAINT(0x05, 0x3), + UNCORE_EVENT_CONSTRAINT(0x07, 0x3), + UNCORE_EVENT_CONSTRAINT(0x09, 0x3), + UNCORE_EVENT_CONSTRAINT(0x11, 0x1), + UNCORE_EVENT_CONSTRAINT(0x12, 0x3), + UNCORE_EVENT_CONSTRAINT(0x13, 0x3), + UNCORE_EVENT_CONSTRAINT(0x1b, 0xc), + UNCORE_EVENT_CONSTRAINT(0x1c, 0xc), + UNCORE_EVENT_CONSTRAINT(0x1d, 0xc), + UNCORE_EVENT_CONSTRAINT(0x1e, 0xc), + EVENT_CONSTRAINT_OVERLAP(0x1f, 0xe, 0xff), + UNCORE_EVENT_CONSTRAINT(0x21, 0x3), + UNCORE_EVENT_CONSTRAINT(0x23, 0x3), + UNCORE_EVENT_CONSTRAINT(0x31, 0x3), + UNCORE_EVENT_CONSTRAINT(0x32, 0x3), + UNCORE_EVENT_CONSTRAINT(0x33, 0x3), + UNCORE_EVENT_CONSTRAINT(0x34, 0x3), + UNCORE_EVENT_CONSTRAINT(0x35, 0x3), + UNCORE_EVENT_CONSTRAINT(0x36, 0x1), + UNCORE_EVENT_CONSTRAINT(0x37, 0x3), + UNCORE_EVENT_CONSTRAINT(0x38, 0x3), + UNCORE_EVENT_CONSTRAINT(0x39, 0x3), + UNCORE_EVENT_CONSTRAINT(0x3b, 0x1), + EVENT_CONSTRAINT_END +}; + +static struct event_constraint snbep_uncore_r2pcie_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x10, 0x3), + UNCORE_EVENT_CONSTRAINT(0x11, 0x3), + UNCORE_EVENT_CONSTRAINT(0x12, 0x1), + UNCORE_EVENT_CONSTRAINT(0x23, 0x3), + UNCORE_EVENT_CONSTRAINT(0x24, 0x3), + UNCORE_EVENT_CONSTRAINT(0x25, 0x3), + UNCORE_EVENT_CONSTRAINT(0x26, 0x3), + UNCORE_EVENT_CONSTRAINT(0x32, 0x3), + UNCORE_EVENT_CONSTRAINT(0x33, 0x3), + UNCORE_EVENT_CONSTRAINT(0x34, 0x3), + EVENT_CONSTRAINT_END +}; + +static struct event_constraint snbep_uncore_r3qpi_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x10, 0x3), + UNCORE_EVENT_CONSTRAINT(0x11, 0x3), + UNCORE_EVENT_CONSTRAINT(0x12, 0x3), + UNCORE_EVENT_CONSTRAINT(0x13, 0x1), + UNCORE_EVENT_CONSTRAINT(0x20, 0x3), + UNCORE_EVENT_CONSTRAINT(0x21, 0x3), + UNCORE_EVENT_CONSTRAINT(0x22, 0x3), + UNCORE_EVENT_CONSTRAINT(0x23, 0x3), + UNCORE_EVENT_CONSTRAINT(0x24, 0x3), + UNCORE_EVENT_CONSTRAINT(0x25, 0x3), + UNCORE_EVENT_CONSTRAINT(0x26, 0x3), + UNCORE_EVENT_CONSTRAINT(0x28, 0x3), + UNCORE_EVENT_CONSTRAINT(0x29, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2a, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2b, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2c, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2d, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2e, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2f, 0x3), + UNCORE_EVENT_CONSTRAINT(0x30, 0x3), + UNCORE_EVENT_CONSTRAINT(0x31, 0x3), + UNCORE_EVENT_CONSTRAINT(0x32, 0x3), + UNCORE_EVENT_CONSTRAINT(0x33, 0x3), + UNCORE_EVENT_CONSTRAINT(0x34, 0x3), + UNCORE_EVENT_CONSTRAINT(0x36, 0x3), + UNCORE_EVENT_CONSTRAINT(0x37, 0x3), + UNCORE_EVENT_CONSTRAINT(0x38, 0x3), + UNCORE_EVENT_CONSTRAINT(0x39, 0x3), + EVENT_CONSTRAINT_END +}; + +static struct intel_uncore_type snbep_uncore_ubox = { + .name = "ubox", + .num_counters = 2, + .num_boxes = 1, + .perf_ctr_bits = 44, + .fixed_ctr_bits = 48, + .perf_ctr = SNBEP_U_MSR_PMON_CTR0, + .event_ctl = SNBEP_U_MSR_PMON_CTL0, + .event_mask = SNBEP_U_MSR_PMON_RAW_EVENT_MASK, + .fixed_ctr = SNBEP_U_MSR_PMON_UCLK_FIXED_CTR, + .fixed_ctl = SNBEP_U_MSR_PMON_UCLK_FIXED_CTL, + .ops = &snbep_uncore_msr_ops, + .format_group = &snbep_uncore_ubox_format_group, +}; + +static struct extra_reg snbep_uncore_cbox_extra_regs[] = { + SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN, + SNBEP_CBO_PMON_CTL_TID_EN, 0x1), + SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0x6), + SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0x6), + SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0x6), + SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0x6), + SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0xa), + SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0xa), + SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0xa), + SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0xa), + SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x4037, 0x40ff, 0x2), + EVENT_EXTRA_END +}; + +static void snbep_cbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct intel_uncore_extra_reg *er = &box->shared_regs[0]; + int i; + + if (uncore_box_is_fake(box)) + return; + + for (i = 0; i < 5; i++) { + if (reg1->alloc & (0x1 << i)) + atomic_sub(1 << (i * 6), &er->ref); + } + reg1->alloc = 0; +} + +static struct event_constraint * +__snbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event, + u64 (*cbox_filter_mask)(int fields)) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct intel_uncore_extra_reg *er = &box->shared_regs[0]; + int i, alloc = 0; + unsigned long flags; + u64 mask; + + if (reg1->idx == EXTRA_REG_NONE) + return NULL; + + raw_spin_lock_irqsave(&er->lock, flags); + for (i = 0; i < 5; i++) { + if (!(reg1->idx & (0x1 << i))) + continue; + if (!uncore_box_is_fake(box) && (reg1->alloc & (0x1 << i))) + continue; + + mask = cbox_filter_mask(0x1 << i); + if (!__BITS_VALUE(atomic_read(&er->ref), i, 6) || + !((reg1->config ^ er->config) & mask)) { + atomic_add(1 << (i * 6), &er->ref); + er->config &= ~mask; + er->config |= reg1->config & mask; + alloc |= (0x1 << i); + } else { + break; + } + } + raw_spin_unlock_irqrestore(&er->lock, flags); + if (i < 5) + goto fail; + + if (!uncore_box_is_fake(box)) + reg1->alloc |= alloc; + + return NULL; +fail: + for (; i >= 0; i--) { + if (alloc & (0x1 << i)) + atomic_sub(1 << (i * 6), &er->ref); + } + return &uncore_constraint_empty; +} + +static u64 snbep_cbox_filter_mask(int fields) +{ + u64 mask = 0; + + if (fields & 0x1) + mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_TID; + if (fields & 0x2) + mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_NID; + if (fields & 0x4) + mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_STATE; + if (fields & 0x8) + mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_OPC; + + return mask; +} + +static struct event_constraint * +snbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + return __snbep_cbox_get_constraint(box, event, snbep_cbox_filter_mask); +} + +static int snbep_cbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct extra_reg *er; + int idx = 0; + + for (er = snbep_uncore_cbox_extra_regs; er->msr; er++) { + if (er->event != (event->hw.config & er->config_mask)) + continue; + idx |= er->idx; + } + + if (idx) { + reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER + + SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx; + reg1->config = event->attr.config1 & snbep_cbox_filter_mask(idx); + reg1->idx = idx; + } + return 0; +} + +static struct intel_uncore_ops snbep_uncore_cbox_ops = { + SNBEP_UNCORE_MSR_OPS_COMMON_INIT(), + .hw_config = snbep_cbox_hw_config, + .get_constraint = snbep_cbox_get_constraint, + .put_constraint = snbep_cbox_put_constraint, +}; + +static struct intel_uncore_type snbep_uncore_cbox = { + .name = "cbox", + .num_counters = 4, + .num_boxes = 8, + .perf_ctr_bits = 44, + .event_ctl = SNBEP_C0_MSR_PMON_CTL0, + .perf_ctr = SNBEP_C0_MSR_PMON_CTR0, + .event_mask = SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_C0_MSR_PMON_BOX_CTL, + .msr_offset = SNBEP_CBO_MSR_OFFSET, + .num_shared_regs = 1, + .constraints = snbep_uncore_cbox_constraints, + .ops = &snbep_uncore_cbox_ops, + .format_group = &snbep_uncore_cbox_format_group, +}; + +static u64 snbep_pcu_alter_er(struct perf_event *event, int new_idx, bool modify) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + u64 config = reg1->config; + + if (new_idx > reg1->idx) + config <<= 8 * (new_idx - reg1->idx); + else + config >>= 8 * (reg1->idx - new_idx); + + if (modify) { + hwc->config += new_idx - reg1->idx; + reg1->config = config; + reg1->idx = new_idx; + } + return config; +} + +static struct event_constraint * +snbep_pcu_get_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct intel_uncore_extra_reg *er = &box->shared_regs[0]; + unsigned long flags; + int idx = reg1->idx; + u64 mask, config1 = reg1->config; + bool ok = false; + + if (reg1->idx == EXTRA_REG_NONE || + (!uncore_box_is_fake(box) && reg1->alloc)) + return NULL; +again: + mask = 0xffULL << (idx * 8); + raw_spin_lock_irqsave(&er->lock, flags); + if (!__BITS_VALUE(atomic_read(&er->ref), idx, 8) || + !((config1 ^ er->config) & mask)) { + atomic_add(1 << (idx * 8), &er->ref); + er->config &= ~mask; + er->config |= config1 & mask; + ok = true; + } + raw_spin_unlock_irqrestore(&er->lock, flags); + + if (!ok) { + idx = (idx + 1) % 4; + if (idx != reg1->idx) { + config1 = snbep_pcu_alter_er(event, idx, false); + goto again; + } + return &uncore_constraint_empty; + } + + if (!uncore_box_is_fake(box)) { + if (idx != reg1->idx) + snbep_pcu_alter_er(event, idx, true); + reg1->alloc = 1; + } + return NULL; +} + +static void snbep_pcu_put_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct intel_uncore_extra_reg *er = &box->shared_regs[0]; + + if (uncore_box_is_fake(box) || !reg1->alloc) + return; + + atomic_sub(1 << (reg1->idx * 8), &er->ref); + reg1->alloc = 0; +} + +static int snbep_pcu_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + int ev_sel = hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK; + + if (ev_sel >= 0xb && ev_sel <= 0xe) { + reg1->reg = SNBEP_PCU_MSR_PMON_BOX_FILTER; + reg1->idx = ev_sel - 0xb; + reg1->config = event->attr.config1 & (0xff << (reg1->idx * 8)); + } + return 0; +} + +static struct intel_uncore_ops snbep_uncore_pcu_ops = { + SNBEP_UNCORE_MSR_OPS_COMMON_INIT(), + .hw_config = snbep_pcu_hw_config, + .get_constraint = snbep_pcu_get_constraint, + .put_constraint = snbep_pcu_put_constraint, +}; + +static struct intel_uncore_type snbep_uncore_pcu = { + .name = "pcu", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .perf_ctr = SNBEP_PCU_MSR_PMON_CTR0, + .event_ctl = SNBEP_PCU_MSR_PMON_CTL0, + .event_mask = SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCU_MSR_PMON_BOX_CTL, + .num_shared_regs = 1, + .ops = &snbep_uncore_pcu_ops, + .format_group = &snbep_uncore_pcu_format_group, +}; + +static struct intel_uncore_type *snbep_msr_uncores[] = { + &snbep_uncore_ubox, + &snbep_uncore_cbox, + &snbep_uncore_pcu, + NULL, +}; + +void snbep_uncore_cpu_init(void) +{ + if (snbep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) + snbep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; + uncore_msr_uncores = snbep_msr_uncores; +} + +enum { + SNBEP_PCI_QPI_PORT0_FILTER, + SNBEP_PCI_QPI_PORT1_FILTER, + HSWEP_PCI_PCU_3, +}; + +static int snbep_qpi_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; + + if ((hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK) == 0x38) { + reg1->idx = 0; + reg1->reg = SNBEP_Q_Py_PCI_PMON_PKT_MATCH0; + reg1->config = event->attr.config1; + reg2->reg = SNBEP_Q_Py_PCI_PMON_PKT_MASK0; + reg2->config = event->attr.config2; + } + return 0; +} + +static void snbep_qpi_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; + + if (reg1->idx != EXTRA_REG_NONE) { + int idx = box->pmu->pmu_idx + SNBEP_PCI_QPI_PORT0_FILTER; + struct pci_dev *filter_pdev = uncore_extra_pci_dev[box->phys_id][idx]; + if (filter_pdev) { + pci_write_config_dword(filter_pdev, reg1->reg, + (u32)reg1->config); + pci_write_config_dword(filter_pdev, reg1->reg + 4, + (u32)(reg1->config >> 32)); + pci_write_config_dword(filter_pdev, reg2->reg, + (u32)reg2->config); + pci_write_config_dword(filter_pdev, reg2->reg + 4, + (u32)(reg2->config >> 32)); + } + } + + pci_write_config_dword(pdev, hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN); +} + +static struct intel_uncore_ops snbep_uncore_qpi_ops = { + SNBEP_UNCORE_PCI_OPS_COMMON_INIT(), + .enable_event = snbep_qpi_enable_event, + .hw_config = snbep_qpi_hw_config, + .get_constraint = uncore_get_constraint, + .put_constraint = uncore_put_constraint, +}; + +#define SNBEP_UNCORE_PCI_COMMON_INIT() \ + .perf_ctr = SNBEP_PCI_PMON_CTR0, \ + .event_ctl = SNBEP_PCI_PMON_CTL0, \ + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, \ + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, \ + .ops = &snbep_uncore_pci_ops, \ + .format_group = &snbep_uncore_format_group + +static struct intel_uncore_type snbep_uncore_ha = { + .name = "ha", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct intel_uncore_type snbep_uncore_imc = { + .name = "imc", + .num_counters = 4, + .num_boxes = 4, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .fixed_ctr = SNBEP_MC_CHy_PCI_PMON_FIXED_CTR, + .fixed_ctl = SNBEP_MC_CHy_PCI_PMON_FIXED_CTL, + .event_descs = snbep_uncore_imc_events, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct intel_uncore_type snbep_uncore_qpi = { + .name = "qpi", + .num_counters = 4, + .num_boxes = 2, + .perf_ctr_bits = 48, + .perf_ctr = SNBEP_PCI_PMON_CTR0, + .event_ctl = SNBEP_PCI_PMON_CTL0, + .event_mask = SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, + .num_shared_regs = 1, + .ops = &snbep_uncore_qpi_ops, + .event_descs = snbep_uncore_qpi_events, + .format_group = &snbep_uncore_qpi_format_group, +}; + + +static struct intel_uncore_type snbep_uncore_r2pcie = { + .name = "r2pcie", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 44, + .constraints = snbep_uncore_r2pcie_constraints, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct intel_uncore_type snbep_uncore_r3qpi = { + .name = "r3qpi", + .num_counters = 3, + .num_boxes = 2, + .perf_ctr_bits = 44, + .constraints = snbep_uncore_r3qpi_constraints, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +enum { + SNBEP_PCI_UNCORE_HA, + SNBEP_PCI_UNCORE_IMC, + SNBEP_PCI_UNCORE_QPI, + SNBEP_PCI_UNCORE_R2PCIE, + SNBEP_PCI_UNCORE_R3QPI, +}; + +static struct intel_uncore_type *snbep_pci_uncores[] = { + [SNBEP_PCI_UNCORE_HA] = &snbep_uncore_ha, + [SNBEP_PCI_UNCORE_IMC] = &snbep_uncore_imc, + [SNBEP_PCI_UNCORE_QPI] = &snbep_uncore_qpi, + [SNBEP_PCI_UNCORE_R2PCIE] = &snbep_uncore_r2pcie, + [SNBEP_PCI_UNCORE_R3QPI] = &snbep_uncore_r3qpi, + NULL, +}; + +static const struct pci_device_id snbep_uncore_pci_ids[] = { + { /* Home Agent */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_HA), + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_HA, 0), + }, + { /* MC Channel 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC0), + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 0), + }, + { /* MC Channel 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC1), + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 1), + }, + { /* MC Channel 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC2), + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 2), + }, + { /* MC Channel 3 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC3), + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 3), + }, + { /* QPI Port 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI0), + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_QPI, 0), + }, + { /* QPI Port 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI1), + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_QPI, 1), + }, + { /* R2PCIe */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R2PCIE), + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R2PCIE, 0), + }, + { /* R3QPI Link 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI0), + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R3QPI, 0), + }, + { /* R3QPI Link 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI1), + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R3QPI, 1), + }, + { /* QPI Port 0 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3c86), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + SNBEP_PCI_QPI_PORT0_FILTER), + }, + { /* QPI Port 0 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3c96), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + SNBEP_PCI_QPI_PORT1_FILTER), + }, + { /* end: all zeroes */ } +}; + +static struct pci_driver snbep_uncore_pci_driver = { + .name = "snbep_uncore", + .id_table = snbep_uncore_pci_ids, +}; + +/* + * build pci bus to socket mapping + */ +static int snbep_pci2phy_map_init(int devid) +{ + struct pci_dev *ubox_dev = NULL; + int i, bus, nodeid; + int err = 0; + u32 config = 0; + + while (1) { + /* find the UBOX device */ + ubox_dev = pci_get_device(PCI_VENDOR_ID_INTEL, devid, ubox_dev); + if (!ubox_dev) + break; + bus = ubox_dev->bus->number; + /* get the Node ID of the local register */ + err = pci_read_config_dword(ubox_dev, 0x40, &config); + if (err) + break; + nodeid = config; + /* get the Node ID mapping */ + err = pci_read_config_dword(ubox_dev, 0x54, &config); + if (err) + break; + /* + * every three bits in the Node ID mapping register maps + * to a particular node. + */ + for (i = 0; i < 8; i++) { + if (nodeid == ((config >> (3 * i)) & 0x7)) { + uncore_pcibus_to_physid[bus] = i; + break; + } + } + } + + if (!err) { + /* + * For PCI bus with no UBOX device, find the next bus + * that has UBOX device and use its mapping. + */ + i = -1; + for (bus = 255; bus >= 0; bus--) { + if (uncore_pcibus_to_physid[bus] >= 0) + i = uncore_pcibus_to_physid[bus]; + else + uncore_pcibus_to_physid[bus] = i; + } + } + + if (ubox_dev) + pci_dev_put(ubox_dev); + + return err ? pcibios_err_to_errno(err) : 0; +} + +int snbep_uncore_pci_init(void) +{ + int ret = snbep_pci2phy_map_init(0x3ce0); + if (ret) + return ret; + uncore_pci_uncores = snbep_pci_uncores; + uncore_pci_driver = &snbep_uncore_pci_driver; + return 0; +} +/* end of Sandy Bridge-EP uncore support */ + +/* IvyTown uncore support */ +static void ivbep_uncore_msr_init_box(struct intel_uncore_box *box) +{ + unsigned msr = uncore_msr_box_ctl(box); + if (msr) + wrmsrl(msr, IVBEP_PMON_BOX_CTL_INT); +} + +static void ivbep_uncore_pci_init_box(struct intel_uncore_box *box) +{ + struct pci_dev *pdev = box->pci_dev; + + pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, IVBEP_PMON_BOX_CTL_INT); +} + +#define IVBEP_UNCORE_MSR_OPS_COMMON_INIT() \ + .init_box = ivbep_uncore_msr_init_box, \ + .disable_box = snbep_uncore_msr_disable_box, \ + .enable_box = snbep_uncore_msr_enable_box, \ + .disable_event = snbep_uncore_msr_disable_event, \ + .enable_event = snbep_uncore_msr_enable_event, \ + .read_counter = uncore_msr_read_counter + +static struct intel_uncore_ops ivbep_uncore_msr_ops = { + IVBEP_UNCORE_MSR_OPS_COMMON_INIT(), +}; + +static struct intel_uncore_ops ivbep_uncore_pci_ops = { + .init_box = ivbep_uncore_pci_init_box, + .disable_box = snbep_uncore_pci_disable_box, + .enable_box = snbep_uncore_pci_enable_box, + .disable_event = snbep_uncore_pci_disable_event, + .enable_event = snbep_uncore_pci_enable_event, + .read_counter = snbep_uncore_pci_read_counter, +}; + +#define IVBEP_UNCORE_PCI_COMMON_INIT() \ + .perf_ctr = SNBEP_PCI_PMON_CTR0, \ + .event_ctl = SNBEP_PCI_PMON_CTL0, \ + .event_mask = IVBEP_PMON_RAW_EVENT_MASK, \ + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, \ + .ops = &ivbep_uncore_pci_ops, \ + .format_group = &ivbep_uncore_format_group + +static struct attribute *ivbep_uncore_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + NULL, +}; + +static struct attribute *ivbep_uncore_ubox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh5.attr, + NULL, +}; + +static struct attribute *ivbep_uncore_cbox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_tid_en.attr, + &format_attr_thresh8.attr, + &format_attr_filter_tid.attr, + &format_attr_filter_link.attr, + &format_attr_filter_state2.attr, + &format_attr_filter_nid2.attr, + &format_attr_filter_opc2.attr, + &format_attr_filter_nc.attr, + &format_attr_filter_c6.attr, + &format_attr_filter_isoc.attr, + NULL, +}; + +static struct attribute *ivbep_uncore_pcu_formats_attr[] = { + &format_attr_event_ext.attr, + &format_attr_occ_sel.attr, + &format_attr_edge.attr, + &format_attr_thresh5.attr, + &format_attr_occ_invert.attr, + &format_attr_occ_edge.attr, + &format_attr_filter_band0.attr, + &format_attr_filter_band1.attr, + &format_attr_filter_band2.attr, + &format_attr_filter_band3.attr, + NULL, +}; + +static struct attribute *ivbep_uncore_qpi_formats_attr[] = { + &format_attr_event_ext.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_thresh8.attr, + &format_attr_match_rds.attr, + &format_attr_match_rnid30.attr, + &format_attr_match_rnid4.attr, + &format_attr_match_dnid.attr, + &format_attr_match_mc.attr, + &format_attr_match_opc.attr, + &format_attr_match_vnw.attr, + &format_attr_match0.attr, + &format_attr_match1.attr, + &format_attr_mask_rds.attr, + &format_attr_mask_rnid30.attr, + &format_attr_mask_rnid4.attr, + &format_attr_mask_dnid.attr, + &format_attr_mask_mc.attr, + &format_attr_mask_opc.attr, + &format_attr_mask_vnw.attr, + &format_attr_mask0.attr, + &format_attr_mask1.attr, + NULL, +}; + +static struct attribute_group ivbep_uncore_format_group = { + .name = "format", + .attrs = ivbep_uncore_formats_attr, +}; + +static struct attribute_group ivbep_uncore_ubox_format_group = { + .name = "format", + .attrs = ivbep_uncore_ubox_formats_attr, +}; + +static struct attribute_group ivbep_uncore_cbox_format_group = { + .name = "format", + .attrs = ivbep_uncore_cbox_formats_attr, +}; + +static struct attribute_group ivbep_uncore_pcu_format_group = { + .name = "format", + .attrs = ivbep_uncore_pcu_formats_attr, +}; + +static struct attribute_group ivbep_uncore_qpi_format_group = { + .name = "format", + .attrs = ivbep_uncore_qpi_formats_attr, +}; + +static struct intel_uncore_type ivbep_uncore_ubox = { + .name = "ubox", + .num_counters = 2, + .num_boxes = 1, + .perf_ctr_bits = 44, + .fixed_ctr_bits = 48, + .perf_ctr = SNBEP_U_MSR_PMON_CTR0, + .event_ctl = SNBEP_U_MSR_PMON_CTL0, + .event_mask = IVBEP_U_MSR_PMON_RAW_EVENT_MASK, + .fixed_ctr = SNBEP_U_MSR_PMON_UCLK_FIXED_CTR, + .fixed_ctl = SNBEP_U_MSR_PMON_UCLK_FIXED_CTL, + .ops = &ivbep_uncore_msr_ops, + .format_group = &ivbep_uncore_ubox_format_group, +}; + +static struct extra_reg ivbep_uncore_cbox_extra_regs[] = { + SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN, + SNBEP_CBO_PMON_CTL_TID_EN, 0x1), + SNBEP_CBO_EVENT_EXTRA_REG(0x1031, 0x10ff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x1134, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0xc), + SNBEP_CBO_EVENT_EXTRA_REG(0x5134, 0xffff, 0xc), + SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0xc), + SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0xc), + SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0xc), + SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x2135, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x2335, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0x18), + SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0x18), + SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x8135, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x8335, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x2136, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x2336, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0x18), + SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0x18), + SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x5036, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x8136, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x8336, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x4037, 0x40ff, 0x8), + EVENT_EXTRA_END +}; + +static u64 ivbep_cbox_filter_mask(int fields) +{ + u64 mask = 0; + + if (fields & 0x1) + mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_TID; + if (fields & 0x2) + mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_LINK; + if (fields & 0x4) + mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_STATE; + if (fields & 0x8) + mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_NID; + if (fields & 0x10) { + mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_OPC; + mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_NC; + mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_C6; + mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_ISOC; + } + + return mask; +} + +static struct event_constraint * +ivbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + return __snbep_cbox_get_constraint(box, event, ivbep_cbox_filter_mask); +} + +static int ivbep_cbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct extra_reg *er; + int idx = 0; + + for (er = ivbep_uncore_cbox_extra_regs; er->msr; er++) { + if (er->event != (event->hw.config & er->config_mask)) + continue; + idx |= er->idx; + } + + if (idx) { + reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER + + SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx; + reg1->config = event->attr.config1 & ivbep_cbox_filter_mask(idx); + reg1->idx = idx; + } + return 0; +} + +static void ivbep_cbox_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + + if (reg1->idx != EXTRA_REG_NONE) { + u64 filter = uncore_shared_reg_config(box, 0); + wrmsrl(reg1->reg, filter & 0xffffffff); + wrmsrl(reg1->reg + 6, filter >> 32); + } + + wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN); +} + +static struct intel_uncore_ops ivbep_uncore_cbox_ops = { + .init_box = ivbep_uncore_msr_init_box, + .disable_box = snbep_uncore_msr_disable_box, + .enable_box = snbep_uncore_msr_enable_box, + .disable_event = snbep_uncore_msr_disable_event, + .enable_event = ivbep_cbox_enable_event, + .read_counter = uncore_msr_read_counter, + .hw_config = ivbep_cbox_hw_config, + .get_constraint = ivbep_cbox_get_constraint, + .put_constraint = snbep_cbox_put_constraint, +}; + +static struct intel_uncore_type ivbep_uncore_cbox = { + .name = "cbox", + .num_counters = 4, + .num_boxes = 15, + .perf_ctr_bits = 44, + .event_ctl = SNBEP_C0_MSR_PMON_CTL0, + .perf_ctr = SNBEP_C0_MSR_PMON_CTR0, + .event_mask = IVBEP_CBO_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_C0_MSR_PMON_BOX_CTL, + .msr_offset = SNBEP_CBO_MSR_OFFSET, + .num_shared_regs = 1, + .constraints = snbep_uncore_cbox_constraints, + .ops = &ivbep_uncore_cbox_ops, + .format_group = &ivbep_uncore_cbox_format_group, +}; + +static struct intel_uncore_ops ivbep_uncore_pcu_ops = { + IVBEP_UNCORE_MSR_OPS_COMMON_INIT(), + .hw_config = snbep_pcu_hw_config, + .get_constraint = snbep_pcu_get_constraint, + .put_constraint = snbep_pcu_put_constraint, +}; + +static struct intel_uncore_type ivbep_uncore_pcu = { + .name = "pcu", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .perf_ctr = SNBEP_PCU_MSR_PMON_CTR0, + .event_ctl = SNBEP_PCU_MSR_PMON_CTL0, + .event_mask = IVBEP_PCU_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCU_MSR_PMON_BOX_CTL, + .num_shared_regs = 1, + .ops = &ivbep_uncore_pcu_ops, + .format_group = &ivbep_uncore_pcu_format_group, +}; + +static struct intel_uncore_type *ivbep_msr_uncores[] = { + &ivbep_uncore_ubox, + &ivbep_uncore_cbox, + &ivbep_uncore_pcu, + NULL, +}; + +void ivbep_uncore_cpu_init(void) +{ + if (ivbep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) + ivbep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; + uncore_msr_uncores = ivbep_msr_uncores; +} + +static struct intel_uncore_type ivbep_uncore_ha = { + .name = "ha", + .num_counters = 4, + .num_boxes = 2, + .perf_ctr_bits = 48, + IVBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct intel_uncore_type ivbep_uncore_imc = { + .name = "imc", + .num_counters = 4, + .num_boxes = 8, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .fixed_ctr = SNBEP_MC_CHy_PCI_PMON_FIXED_CTR, + .fixed_ctl = SNBEP_MC_CHy_PCI_PMON_FIXED_CTL, + .event_descs = snbep_uncore_imc_events, + IVBEP_UNCORE_PCI_COMMON_INIT(), +}; + +/* registers in IRP boxes are not properly aligned */ +static unsigned ivbep_uncore_irp_ctls[] = {0xd8, 0xdc, 0xe0, 0xe4}; +static unsigned ivbep_uncore_irp_ctrs[] = {0xa0, 0xb0, 0xb8, 0xc0}; + +static void ivbep_uncore_irp_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + + pci_write_config_dword(pdev, ivbep_uncore_irp_ctls[hwc->idx], + hwc->config | SNBEP_PMON_CTL_EN); +} + +static void ivbep_uncore_irp_disable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + + pci_write_config_dword(pdev, ivbep_uncore_irp_ctls[hwc->idx], hwc->config); +} + +static u64 ivbep_uncore_irp_read_counter(struct intel_uncore_box *box, struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + u64 count = 0; + + pci_read_config_dword(pdev, ivbep_uncore_irp_ctrs[hwc->idx], (u32 *)&count); + pci_read_config_dword(pdev, ivbep_uncore_irp_ctrs[hwc->idx] + 4, (u32 *)&count + 1); + + return count; +} + +static struct intel_uncore_ops ivbep_uncore_irp_ops = { + .init_box = ivbep_uncore_pci_init_box, + .disable_box = snbep_uncore_pci_disable_box, + .enable_box = snbep_uncore_pci_enable_box, + .disable_event = ivbep_uncore_irp_disable_event, + .enable_event = ivbep_uncore_irp_enable_event, + .read_counter = ivbep_uncore_irp_read_counter, +}; + +static struct intel_uncore_type ivbep_uncore_irp = { + .name = "irp", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .event_mask = IVBEP_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, + .ops = &ivbep_uncore_irp_ops, + .format_group = &ivbep_uncore_format_group, +}; + +static struct intel_uncore_ops ivbep_uncore_qpi_ops = { + .init_box = ivbep_uncore_pci_init_box, + .disable_box = snbep_uncore_pci_disable_box, + .enable_box = snbep_uncore_pci_enable_box, + .disable_event = snbep_uncore_pci_disable_event, + .enable_event = snbep_qpi_enable_event, + .read_counter = snbep_uncore_pci_read_counter, + .hw_config = snbep_qpi_hw_config, + .get_constraint = uncore_get_constraint, + .put_constraint = uncore_put_constraint, +}; + +static struct intel_uncore_type ivbep_uncore_qpi = { + .name = "qpi", + .num_counters = 4, + .num_boxes = 3, + .perf_ctr_bits = 48, + .perf_ctr = SNBEP_PCI_PMON_CTR0, + .event_ctl = SNBEP_PCI_PMON_CTL0, + .event_mask = IVBEP_QPI_PCI_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, + .num_shared_regs = 1, + .ops = &ivbep_uncore_qpi_ops, + .format_group = &ivbep_uncore_qpi_format_group, +}; + +static struct intel_uncore_type ivbep_uncore_r2pcie = { + .name = "r2pcie", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 44, + .constraints = snbep_uncore_r2pcie_constraints, + IVBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct intel_uncore_type ivbep_uncore_r3qpi = { + .name = "r3qpi", + .num_counters = 3, + .num_boxes = 2, + .perf_ctr_bits = 44, + .constraints = snbep_uncore_r3qpi_constraints, + IVBEP_UNCORE_PCI_COMMON_INIT(), +}; + +enum { + IVBEP_PCI_UNCORE_HA, + IVBEP_PCI_UNCORE_IMC, + IVBEP_PCI_UNCORE_IRP, + IVBEP_PCI_UNCORE_QPI, + IVBEP_PCI_UNCORE_R2PCIE, + IVBEP_PCI_UNCORE_R3QPI, +}; + +static struct intel_uncore_type *ivbep_pci_uncores[] = { + [IVBEP_PCI_UNCORE_HA] = &ivbep_uncore_ha, + [IVBEP_PCI_UNCORE_IMC] = &ivbep_uncore_imc, + [IVBEP_PCI_UNCORE_IRP] = &ivbep_uncore_irp, + [IVBEP_PCI_UNCORE_QPI] = &ivbep_uncore_qpi, + [IVBEP_PCI_UNCORE_R2PCIE] = &ivbep_uncore_r2pcie, + [IVBEP_PCI_UNCORE_R3QPI] = &ivbep_uncore_r3qpi, + NULL, +}; + +static const struct pci_device_id ivbep_uncore_pci_ids[] = { + { /* Home Agent 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe30), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_HA, 0), + }, + { /* Home Agent 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe38), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_HA, 1), + }, + { /* MC0 Channel 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb4), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 0), + }, + { /* MC0 Channel 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb5), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 1), + }, + { /* MC0 Channel 3 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb0), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 2), + }, + { /* MC0 Channel 4 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb1), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 3), + }, + { /* MC1 Channel 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef4), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 4), + }, + { /* MC1 Channel 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef5), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 5), + }, + { /* MC1 Channel 3 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef0), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 6), + }, + { /* MC1 Channel 4 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef1), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 7), + }, + { /* IRP */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe39), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IRP, 0), + }, + { /* QPI0 Port 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe32), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_QPI, 0), + }, + { /* QPI0 Port 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe33), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_QPI, 1), + }, + { /* QPI1 Port 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3a), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_QPI, 2), + }, + { /* R2PCIe */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe34), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_R2PCIE, 0), + }, + { /* R3QPI0 Link 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe36), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_R3QPI, 0), + }, + { /* R3QPI0 Link 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe37), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_R3QPI, 1), + }, + { /* R3QPI1 Link 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3e), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_R3QPI, 2), + }, + { /* QPI Port 0 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe86), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + SNBEP_PCI_QPI_PORT0_FILTER), + }, + { /* QPI Port 0 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe96), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + SNBEP_PCI_QPI_PORT1_FILTER), + }, + { /* end: all zeroes */ } +}; + +static struct pci_driver ivbep_uncore_pci_driver = { + .name = "ivbep_uncore", + .id_table = ivbep_uncore_pci_ids, +}; + +int ivbep_uncore_pci_init(void) +{ + int ret = snbep_pci2phy_map_init(0x0e1e); + if (ret) + return ret; + uncore_pci_uncores = ivbep_pci_uncores; + uncore_pci_driver = &ivbep_uncore_pci_driver; + return 0; +} +/* end of IvyTown uncore support */ + +/* Haswell-EP uncore support */ +static struct attribute *hswep_uncore_ubox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh5.attr, + &format_attr_filter_tid2.attr, + &format_attr_filter_cid.attr, + NULL, +}; + +static struct attribute_group hswep_uncore_ubox_format_group = { + .name = "format", + .attrs = hswep_uncore_ubox_formats_attr, +}; + +static int hswep_ubox_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + reg1->reg = HSWEP_U_MSR_PMON_FILTER; + reg1->config = event->attr.config1 & HSWEP_U_MSR_PMON_BOX_FILTER_MASK; + reg1->idx = 0; + return 0; +} + +static struct intel_uncore_ops hswep_uncore_ubox_ops = { + SNBEP_UNCORE_MSR_OPS_COMMON_INIT(), + .hw_config = hswep_ubox_hw_config, + .get_constraint = uncore_get_constraint, + .put_constraint = uncore_put_constraint, +}; + +static struct intel_uncore_type hswep_uncore_ubox = { + .name = "ubox", + .num_counters = 2, + .num_boxes = 1, + .perf_ctr_bits = 44, + .fixed_ctr_bits = 48, + .perf_ctr = HSWEP_U_MSR_PMON_CTR0, + .event_ctl = HSWEP_U_MSR_PMON_CTL0, + .event_mask = SNBEP_U_MSR_PMON_RAW_EVENT_MASK, + .fixed_ctr = HSWEP_U_MSR_PMON_UCLK_FIXED_CTR, + .fixed_ctl = HSWEP_U_MSR_PMON_UCLK_FIXED_CTL, + .num_shared_regs = 1, + .ops = &hswep_uncore_ubox_ops, + .format_group = &hswep_uncore_ubox_format_group, +}; + +static struct attribute *hswep_uncore_cbox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_tid_en.attr, + &format_attr_thresh8.attr, + &format_attr_filter_tid3.attr, + &format_attr_filter_link2.attr, + &format_attr_filter_state3.attr, + &format_attr_filter_nid2.attr, + &format_attr_filter_opc2.attr, + &format_attr_filter_nc.attr, + &format_attr_filter_c6.attr, + &format_attr_filter_isoc.attr, + NULL, +}; + +static struct attribute_group hswep_uncore_cbox_format_group = { + .name = "format", + .attrs = hswep_uncore_cbox_formats_attr, +}; + +static struct event_constraint hswep_uncore_cbox_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x01, 0x1), + UNCORE_EVENT_CONSTRAINT(0x09, 0x1), + UNCORE_EVENT_CONSTRAINT(0x11, 0x1), + UNCORE_EVENT_CONSTRAINT(0x36, 0x1), + UNCORE_EVENT_CONSTRAINT(0x38, 0x3), + UNCORE_EVENT_CONSTRAINT(0x3b, 0x1), + UNCORE_EVENT_CONSTRAINT(0x3e, 0x1), + EVENT_CONSTRAINT_END +}; + +static struct extra_reg hswep_uncore_cbox_extra_regs[] = { + SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN, + SNBEP_CBO_PMON_CTL_TID_EN, 0x1), + SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x1134, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x2134, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4037, 0x40ff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4028, 0x40ff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4032, 0x40ff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4029, 0x40ff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4033, 0x40ff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x402A, 0x40ff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x12), + SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0x18), + SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0x18), + SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x2335, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x8335, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x2135, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x8135, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0x18), + SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0x18), + SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x2336, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x8336, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x2136, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x8136, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x5036, 0xffff, 0x8), + EVENT_EXTRA_END +}; + +static u64 hswep_cbox_filter_mask(int fields) +{ + u64 mask = 0; + if (fields & 0x1) + mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_TID; + if (fields & 0x2) + mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_LINK; + if (fields & 0x4) + mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_STATE; + if (fields & 0x8) + mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_NID; + if (fields & 0x10) { + mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_OPC; + mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_NC; + mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_C6; + mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_ISOC; + } + return mask; +} + +static struct event_constraint * +hswep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + return __snbep_cbox_get_constraint(box, event, hswep_cbox_filter_mask); +} + +static int hswep_cbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct extra_reg *er; + int idx = 0; + + for (er = hswep_uncore_cbox_extra_regs; er->msr; er++) { + if (er->event != (event->hw.config & er->config_mask)) + continue; + idx |= er->idx; + } + + if (idx) { + reg1->reg = HSWEP_C0_MSR_PMON_BOX_FILTER0 + + HSWEP_CBO_MSR_OFFSET * box->pmu->pmu_idx; + reg1->config = event->attr.config1 & hswep_cbox_filter_mask(idx); + reg1->idx = idx; + } + return 0; +} + +static void hswep_cbox_enable_event(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + + if (reg1->idx != EXTRA_REG_NONE) { + u64 filter = uncore_shared_reg_config(box, 0); + wrmsrl(reg1->reg, filter & 0xffffffff); + wrmsrl(reg1->reg + 1, filter >> 32); + } + + wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN); +} + +static struct intel_uncore_ops hswep_uncore_cbox_ops = { + .init_box = snbep_uncore_msr_init_box, + .disable_box = snbep_uncore_msr_disable_box, + .enable_box = snbep_uncore_msr_enable_box, + .disable_event = snbep_uncore_msr_disable_event, + .enable_event = hswep_cbox_enable_event, + .read_counter = uncore_msr_read_counter, + .hw_config = hswep_cbox_hw_config, + .get_constraint = hswep_cbox_get_constraint, + .put_constraint = snbep_cbox_put_constraint, +}; + +static struct intel_uncore_type hswep_uncore_cbox = { + .name = "cbox", + .num_counters = 4, + .num_boxes = 18, + .perf_ctr_bits = 44, + .event_ctl = HSWEP_C0_MSR_PMON_CTL0, + .perf_ctr = HSWEP_C0_MSR_PMON_CTR0, + .event_mask = SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = HSWEP_C0_MSR_PMON_BOX_CTL, + .msr_offset = HSWEP_CBO_MSR_OFFSET, + .num_shared_regs = 1, + .constraints = hswep_uncore_cbox_constraints, + .ops = &hswep_uncore_cbox_ops, + .format_group = &hswep_uncore_cbox_format_group, +}; + +/* + * Write SBOX Initialization register bit by bit to avoid spurious #GPs + */ +static void hswep_uncore_sbox_msr_init_box(struct intel_uncore_box *box) +{ + unsigned msr = uncore_msr_box_ctl(box); + + if (msr) { + u64 init = SNBEP_PMON_BOX_CTL_INT; + u64 flags = 0; + int i; + + for_each_set_bit(i, (unsigned long *)&init, 64) { + flags |= (1ULL << i); + wrmsrl(msr, flags); + } + } +} + +static struct intel_uncore_ops hswep_uncore_sbox_msr_ops = { + __SNBEP_UNCORE_MSR_OPS_COMMON_INIT(), + .init_box = hswep_uncore_sbox_msr_init_box +}; + +static struct attribute *hswep_uncore_sbox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_tid_en.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + NULL, +}; + +static struct attribute_group hswep_uncore_sbox_format_group = { + .name = "format", + .attrs = hswep_uncore_sbox_formats_attr, +}; + +static struct intel_uncore_type hswep_uncore_sbox = { + .name = "sbox", + .num_counters = 4, + .num_boxes = 4, + .perf_ctr_bits = 44, + .event_ctl = HSWEP_S0_MSR_PMON_CTL0, + .perf_ctr = HSWEP_S0_MSR_PMON_CTR0, + .event_mask = HSWEP_S_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = HSWEP_S0_MSR_PMON_BOX_CTL, + .msr_offset = HSWEP_SBOX_MSR_OFFSET, + .ops = &hswep_uncore_sbox_msr_ops, + .format_group = &hswep_uncore_sbox_format_group, +}; + +static int hswep_pcu_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + int ev_sel = hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK; + + if (ev_sel >= 0xb && ev_sel <= 0xe) { + reg1->reg = HSWEP_PCU_MSR_PMON_BOX_FILTER; + reg1->idx = ev_sel - 0xb; + reg1->config = event->attr.config1 & (0xff << reg1->idx); + } + return 0; +} + +static struct intel_uncore_ops hswep_uncore_pcu_ops = { + SNBEP_UNCORE_MSR_OPS_COMMON_INIT(), + .hw_config = hswep_pcu_hw_config, + .get_constraint = snbep_pcu_get_constraint, + .put_constraint = snbep_pcu_put_constraint, +}; + +static struct intel_uncore_type hswep_uncore_pcu = { + .name = "pcu", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .perf_ctr = HSWEP_PCU_MSR_PMON_CTR0, + .event_ctl = HSWEP_PCU_MSR_PMON_CTL0, + .event_mask = SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = HSWEP_PCU_MSR_PMON_BOX_CTL, + .num_shared_regs = 1, + .ops = &hswep_uncore_pcu_ops, + .format_group = &snbep_uncore_pcu_format_group, +}; + +static struct intel_uncore_type *hswep_msr_uncores[] = { + &hswep_uncore_ubox, + &hswep_uncore_cbox, + &hswep_uncore_sbox, + &hswep_uncore_pcu, + NULL, +}; + +void hswep_uncore_cpu_init(void) +{ + if (hswep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) + hswep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; + + /* Detect 6-8 core systems with only two SBOXes */ + if (uncore_extra_pci_dev[0][HSWEP_PCI_PCU_3]) { + u32 capid4; + + pci_read_config_dword(uncore_extra_pci_dev[0][HSWEP_PCI_PCU_3], + 0x94, &capid4); + if (((capid4 >> 6) & 0x3) == 0) + hswep_uncore_sbox.num_boxes = 2; + } + + uncore_msr_uncores = hswep_msr_uncores; +} + +static struct intel_uncore_type hswep_uncore_ha = { + .name = "ha", + .num_counters = 5, + .num_boxes = 2, + .perf_ctr_bits = 48, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct uncore_event_desc hswep_uncore_imc_events[] = { + INTEL_UNCORE_EVENT_DESC(clockticks, "event=0x00,umask=0x00"), + INTEL_UNCORE_EVENT_DESC(cas_count_read, "event=0x04,umask=0x03"), + INTEL_UNCORE_EVENT_DESC(cas_count_read.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(cas_count_read.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(cas_count_write, "event=0x04,umask=0x0c"), + INTEL_UNCORE_EVENT_DESC(cas_count_write.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(cas_count_write.unit, "MiB"), + { /* end: all zeroes */ }, +}; + +static struct intel_uncore_type hswep_uncore_imc = { + .name = "imc", + .num_counters = 5, + .num_boxes = 8, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .fixed_ctr = SNBEP_MC_CHy_PCI_PMON_FIXED_CTR, + .fixed_ctl = SNBEP_MC_CHy_PCI_PMON_FIXED_CTL, + .event_descs = hswep_uncore_imc_events, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static unsigned hswep_uncore_irp_ctrs[] = {0xa0, 0xa8, 0xb0, 0xb8}; + +static u64 hswep_uncore_irp_read_counter(struct intel_uncore_box *box, struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + u64 count = 0; + + pci_read_config_dword(pdev, hswep_uncore_irp_ctrs[hwc->idx], (u32 *)&count); + pci_read_config_dword(pdev, hswep_uncore_irp_ctrs[hwc->idx] + 4, (u32 *)&count + 1); + + return count; +} + +static struct intel_uncore_ops hswep_uncore_irp_ops = { + .init_box = snbep_uncore_pci_init_box, + .disable_box = snbep_uncore_pci_disable_box, + .enable_box = snbep_uncore_pci_enable_box, + .disable_event = ivbep_uncore_irp_disable_event, + .enable_event = ivbep_uncore_irp_enable_event, + .read_counter = hswep_uncore_irp_read_counter, +}; + +static struct intel_uncore_type hswep_uncore_irp = { + .name = "irp", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, + .ops = &hswep_uncore_irp_ops, + .format_group = &snbep_uncore_format_group, +}; + +static struct intel_uncore_type hswep_uncore_qpi = { + .name = "qpi", + .num_counters = 5, + .num_boxes = 3, + .perf_ctr_bits = 48, + .perf_ctr = SNBEP_PCI_PMON_CTR0, + .event_ctl = SNBEP_PCI_PMON_CTL0, + .event_mask = SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, + .num_shared_regs = 1, + .ops = &snbep_uncore_qpi_ops, + .format_group = &snbep_uncore_qpi_format_group, +}; + +static struct event_constraint hswep_uncore_r2pcie_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x10, 0x3), + UNCORE_EVENT_CONSTRAINT(0x11, 0x3), + UNCORE_EVENT_CONSTRAINT(0x13, 0x1), + UNCORE_EVENT_CONSTRAINT(0x23, 0x1), + UNCORE_EVENT_CONSTRAINT(0x24, 0x1), + UNCORE_EVENT_CONSTRAINT(0x25, 0x1), + UNCORE_EVENT_CONSTRAINT(0x26, 0x3), + UNCORE_EVENT_CONSTRAINT(0x27, 0x1), + UNCORE_EVENT_CONSTRAINT(0x28, 0x3), + UNCORE_EVENT_CONSTRAINT(0x29, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2a, 0x1), + UNCORE_EVENT_CONSTRAINT(0x2b, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2c, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2d, 0x3), + UNCORE_EVENT_CONSTRAINT(0x32, 0x3), + UNCORE_EVENT_CONSTRAINT(0x33, 0x3), + UNCORE_EVENT_CONSTRAINT(0x34, 0x3), + UNCORE_EVENT_CONSTRAINT(0x35, 0x3), + EVENT_CONSTRAINT_END +}; + +static struct intel_uncore_type hswep_uncore_r2pcie = { + .name = "r2pcie", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .constraints = hswep_uncore_r2pcie_constraints, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct event_constraint hswep_uncore_r3qpi_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x01, 0x3), + UNCORE_EVENT_CONSTRAINT(0x07, 0x7), + UNCORE_EVENT_CONSTRAINT(0x08, 0x7), + UNCORE_EVENT_CONSTRAINT(0x09, 0x7), + UNCORE_EVENT_CONSTRAINT(0x0a, 0x7), + UNCORE_EVENT_CONSTRAINT(0x0e, 0x7), + UNCORE_EVENT_CONSTRAINT(0x10, 0x3), + UNCORE_EVENT_CONSTRAINT(0x11, 0x3), + UNCORE_EVENT_CONSTRAINT(0x12, 0x3), + UNCORE_EVENT_CONSTRAINT(0x13, 0x1), + UNCORE_EVENT_CONSTRAINT(0x14, 0x3), + UNCORE_EVENT_CONSTRAINT(0x15, 0x3), + UNCORE_EVENT_CONSTRAINT(0x1f, 0x3), + UNCORE_EVENT_CONSTRAINT(0x20, 0x3), + UNCORE_EVENT_CONSTRAINT(0x21, 0x3), + UNCORE_EVENT_CONSTRAINT(0x22, 0x3), + UNCORE_EVENT_CONSTRAINT(0x23, 0x3), + UNCORE_EVENT_CONSTRAINT(0x25, 0x3), + UNCORE_EVENT_CONSTRAINT(0x26, 0x3), + UNCORE_EVENT_CONSTRAINT(0x28, 0x3), + UNCORE_EVENT_CONSTRAINT(0x29, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2c, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2d, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2e, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2f, 0x3), + UNCORE_EVENT_CONSTRAINT(0x31, 0x3), + UNCORE_EVENT_CONSTRAINT(0x32, 0x3), + UNCORE_EVENT_CONSTRAINT(0x33, 0x3), + UNCORE_EVENT_CONSTRAINT(0x34, 0x3), + UNCORE_EVENT_CONSTRAINT(0x36, 0x3), + UNCORE_EVENT_CONSTRAINT(0x37, 0x3), + UNCORE_EVENT_CONSTRAINT(0x38, 0x3), + UNCORE_EVENT_CONSTRAINT(0x39, 0x3), + EVENT_CONSTRAINT_END +}; + +static struct intel_uncore_type hswep_uncore_r3qpi = { + .name = "r3qpi", + .num_counters = 4, + .num_boxes = 3, + .perf_ctr_bits = 44, + .constraints = hswep_uncore_r3qpi_constraints, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +enum { + HSWEP_PCI_UNCORE_HA, + HSWEP_PCI_UNCORE_IMC, + HSWEP_PCI_UNCORE_IRP, + HSWEP_PCI_UNCORE_QPI, + HSWEP_PCI_UNCORE_R2PCIE, + HSWEP_PCI_UNCORE_R3QPI, +}; + +static struct intel_uncore_type *hswep_pci_uncores[] = { + [HSWEP_PCI_UNCORE_HA] = &hswep_uncore_ha, + [HSWEP_PCI_UNCORE_IMC] = &hswep_uncore_imc, + [HSWEP_PCI_UNCORE_IRP] = &hswep_uncore_irp, + [HSWEP_PCI_UNCORE_QPI] = &hswep_uncore_qpi, + [HSWEP_PCI_UNCORE_R2PCIE] = &hswep_uncore_r2pcie, + [HSWEP_PCI_UNCORE_R3QPI] = &hswep_uncore_r3qpi, + NULL, +}; + +static DEFINE_PCI_DEVICE_TABLE(hswep_uncore_pci_ids) = { + { /* Home Agent 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f30), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_HA, 0), + }, + { /* Home Agent 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f38), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_HA, 1), + }, + { /* MC0 Channel 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fb0), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 0), + }, + { /* MC0 Channel 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fb1), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 1), + }, + { /* MC0 Channel 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fb4), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 2), + }, + { /* MC0 Channel 3 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fb5), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 3), + }, + { /* MC1 Channel 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fd0), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 4), + }, + { /* MC1 Channel 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fd1), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 5), + }, + { /* MC1 Channel 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fd4), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 6), + }, + { /* MC1 Channel 3 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fd5), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 7), + }, + { /* IRP */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f39), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IRP, 0), + }, + { /* QPI0 Port 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f32), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_QPI, 0), + }, + { /* QPI0 Port 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f33), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_QPI, 1), + }, + { /* QPI1 Port 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f3a), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_QPI, 2), + }, + { /* R2PCIe */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f34), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_R2PCIE, 0), + }, + { /* R3QPI0 Link 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f36), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_R3QPI, 0), + }, + { /* R3QPI0 Link 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f37), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_R3QPI, 1), + }, + { /* R3QPI1 Link 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f3e), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_R3QPI, 2), + }, + { /* QPI Port 0 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f86), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + SNBEP_PCI_QPI_PORT0_FILTER), + }, + { /* QPI Port 1 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f96), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + SNBEP_PCI_QPI_PORT1_FILTER), + }, + { /* PCU.3 (for Capability registers) */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fc0), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + HSWEP_PCI_PCU_3), + }, + { /* end: all zeroes */ } +}; + +static struct pci_driver hswep_uncore_pci_driver = { + .name = "hswep_uncore", + .id_table = hswep_uncore_pci_ids, +}; + +int hswep_uncore_pci_init(void) +{ + int ret = snbep_pci2phy_map_init(0x2f1e); + if (ret) + return ret; + uncore_pci_uncores = hswep_pci_uncores; + uncore_pci_driver = &hswep_uncore_pci_driver; + return 0; +} +/* end of Haswell-EP uncore support */ diff --git a/arch/x86/kernel/cpu/perf_event_knc.c b/arch/x86/kernel/cpu/perf_event_knc.c index 838fa8772c62..5b0c232d1ee6 100644 --- a/arch/x86/kernel/cpu/perf_event_knc.c +++ b/arch/x86/kernel/cpu/perf_event_knc.c @@ -217,7 +217,7 @@ static int knc_pmu_handle_irq(struct pt_regs *regs) int bit, loops; u64 status; - cpuc = &__get_cpu_var(cpu_hw_events); + cpuc = this_cpu_ptr(&cpu_hw_events); knc_pmu_disable_all(); diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c index 5d466b7d8609..f2e56783af3d 100644 --- a/arch/x86/kernel/cpu/perf_event_p4.c +++ b/arch/x86/kernel/cpu/perf_event_p4.c @@ -915,7 +915,7 @@ static inline void p4_pmu_disable_event(struct perf_event *event) static void p4_pmu_disable_all(void) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int idx; for (idx = 0; idx < x86_pmu.num_counters; idx++) { @@ -984,7 +984,7 @@ static void p4_pmu_enable_event(struct perf_event *event) static void p4_pmu_enable_all(int added) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int idx; for (idx = 0; idx < x86_pmu.num_counters; idx++) { @@ -1004,7 +1004,7 @@ static int p4_pmu_handle_irq(struct pt_regs *regs) int idx, handled = 0; u64 val; - cpuc = &__get_cpu_var(cpu_hw_events); + cpuc = this_cpu_ptr(&cpu_hw_events); for (idx = 0; idx < x86_pmu.num_counters; idx++) { int overflow; diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index 5433658e598d..e7d8c7608471 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -72,7 +72,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) if (c->x86_mask || c->cpuid_level >= 0) seq_printf(m, "stepping\t: %d\n", c->x86_mask); else - seq_printf(m, "stepping\t: unknown\n"); + seq_puts(m, "stepping\t: unknown\n"); if (c->microcode) seq_printf(m, "microcode\t: 0x%x\n", c->microcode); @@ -92,12 +92,12 @@ static int show_cpuinfo(struct seq_file *m, void *v) show_cpuinfo_core(m, c, cpu); show_cpuinfo_misc(m, c); - seq_printf(m, "flags\t\t:"); + seq_puts(m, "flags\t\t:"); for (i = 0; i < 32*NCAPINTS; i++) if (cpu_has(c, i) && x86_cap_flags[i] != NULL) seq_printf(m, " %s", x86_cap_flags[i]); - seq_printf(m, "\nbugs\t\t:"); + seq_puts(m, "\nbugs\t\t:"); for (i = 0; i < 32*NBUGINTS; i++) { unsigned int bug_bit = 32*NCAPINTS + i; @@ -118,7 +118,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) seq_printf(m, "address sizes\t: %u bits physical, %u bits virtual\n", c->x86_phys_bits, c->x86_virt_bits); - seq_printf(m, "power management:"); + seq_puts(m, "power management:"); for (i = 0; i < 32; i++) { if (c->x86_power & (1 << i)) { if (i < ARRAY_SIZE(x86_power_flags) && @@ -131,7 +131,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) } } - seq_printf(m, "\n\n"); + seq_puts(m, "\n\n"); return 0; } diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 4a8013d55947..60639093d536 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -36,6 +36,11 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c) { X86_FEATURE_ARAT, CR_EAX, 2, 0x00000006, 0 }, { X86_FEATURE_PLN, CR_EAX, 4, 0x00000006, 0 }, { X86_FEATURE_PTS, CR_EAX, 6, 0x00000006, 0 }, + { X86_FEATURE_HWP, CR_EAX, 7, 0x00000006, 0 }, + { X86_FEATURE_HWP_NOITFY, CR_EAX, 8, 0x00000006, 0 }, + { X86_FEATURE_HWP_ACT_WINDOW, CR_EAX, 9, 0x00000006, 0 }, + { X86_FEATURE_HWP_EPP, CR_EAX,10, 0x00000006, 0 }, + { X86_FEATURE_HWP_PKG_REQ, CR_EAX,11, 0x00000006, 0 }, { X86_FEATURE_APERFMPERF, CR_ECX, 0, 0x00000006, 0 }, { X86_FEATURE_EPB, CR_ECX, 3, 0x00000006, 0 }, { X86_FEATURE_HW_PSTATE, CR_EDX, 7, 0x80000007, 0 }, diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c index 3225ae6c5180..83741a71558f 100644 --- a/arch/x86/kernel/cpuid.c +++ b/arch/x86/kernel/cpuid.c @@ -143,7 +143,7 @@ static int cpuid_device_create(int cpu) dev = device_create(cpuid_class, NULL, MKDEV(CPUID_MAJOR, cpu), NULL, "cpu%d", cpu); - return IS_ERR(dev) ? PTR_ERR(dev) : 0; + return PTR_ERR_OR_ZERO(dev); } static void cpuid_device_destroy(int cpu) diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index a618fcd2c07d..aceb2f90c716 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -28,6 +28,7 @@ #include <asm/nmi.h> #include <asm/hw_irq.h> #include <asm/apic.h> +#include <asm/io_apic.h> #include <asm/hpet.h> #include <linux/kdebug.h> #include <asm/cpu.h> @@ -237,7 +238,7 @@ static void fill_up_crash_elf_data(struct crash_elf_data *ced, ced->max_nr_ranges++; /* If crashk_low_res is not 0, another range split possible */ - if (crashk_low_res.end != 0) + if (crashk_low_res.end) ced->max_nr_ranges++; } @@ -335,9 +336,11 @@ static int elf_header_exclude_ranges(struct crash_elf_data *ced, if (ret) return ret; - ret = exclude_mem_range(cmem, crashk_low_res.start, crashk_low_res.end); - if (ret) - return ret; + if (crashk_low_res.end) { + ret = exclude_mem_range(cmem, crashk_low_res.start, crashk_low_res.end); + if (ret) + return ret; + } /* Exclude GART region */ if (ced->gart_end) { diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 1abcb50b48ae..ff86f19b5758 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -24,7 +24,6 @@ static char x86_stack_ids[][8] = { [ DEBUG_STACK-1 ] = "#DB", [ NMI_STACK-1 ] = "NMI", [ DOUBLEFAULT_STACK-1 ] = "#DF", - [ STACKFAULT_STACK-1 ] = "#SS", [ MCE_STACK-1 ] = "#MC", #if DEBUG_STKSZ > EXCEPTION_STKSZ [ N_EXCEPTION_STACKS ... diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 988c00a1f60d..dd2f07ae9d0c 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -682,15 +682,14 @@ void __init parse_e820_ext(u64 phys_addr, u32 data_len) * hibernation (32 bit) or software suspend and suspend to RAM (64 bit). * * This function requires the e820 map to be sorted and without any - * overlapping entries and assumes the first e820 area to be RAM. + * overlapping entries. */ void __init e820_mark_nosave_regions(unsigned long limit_pfn) { int i; - unsigned long pfn; + unsigned long pfn = 0; - pfn = PFN_DOWN(e820.map[0].addr + e820.map[0].size); - for (i = 1; i < e820.nr_map; i++) { + for (i = 0; i < e820.nr_map; i++) { struct e820entry *ei = &e820.map[i]; if (pfn < PFN_UP(ei->addr)) @@ -1115,8 +1114,8 @@ void __init memblock_find_dma_reserve(void) * at first, and assume boot_mem will not take below MAX_DMA_PFN */ for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) { - start_pfn = min_t(unsigned long, start_pfn, MAX_DMA_PFN); - end_pfn = min_t(unsigned long, end_pfn, MAX_DMA_PFN); + start_pfn = min(start_pfn, MAX_DMA_PFN); + end_pfn = min(end_pfn, MAX_DMA_PFN); nr_pages += end_pfn - start_pfn; } diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 2e1a6853e00c..fe9f0b79a18b 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -455,6 +455,23 @@ struct intel_stolen_funcs { u32 (*base)(int num, int slot, int func, size_t size); }; +static size_t __init gen9_stolen_size(int num, int slot, int func) +{ + u16 gmch_ctrl; + + gmch_ctrl = read_pci_config_16(num, slot, func, SNB_GMCH_CTRL); + gmch_ctrl >>= BDW_GMCH_GMS_SHIFT; + gmch_ctrl &= BDW_GMCH_GMS_MASK; + + if (gmch_ctrl < 0xf0) + return gmch_ctrl << 25; /* 32 MB units */ + else + /* 4MB increments starting at 0xf0 for 4MB */ + return (gmch_ctrl - 0xf0 + 1) << 22; +} + +typedef size_t (*stolen_size_fn)(int num, int slot, int func); + static const struct intel_stolen_funcs i830_stolen_funcs __initconst = { .base = i830_stolen_base, .size = i830_stolen_size, @@ -490,6 +507,11 @@ static const struct intel_stolen_funcs gen8_stolen_funcs __initconst = { .size = gen8_stolen_size, }; +static const struct intel_stolen_funcs gen9_stolen_funcs __initconst = { + .base = intel_stolen_base, + .size = gen9_stolen_size, +}; + static const struct intel_stolen_funcs chv_stolen_funcs __initconst = { .base = intel_stolen_base, .size = chv_stolen_size, @@ -523,6 +545,7 @@ static const struct pci_device_id intel_stolen_ids[] __initconst = { INTEL_BDW_M_IDS(&gen8_stolen_funcs), INTEL_BDW_D_IDS(&gen8_stolen_funcs), INTEL_CHV_IDS(&chv_stolen_funcs), + INTEL_SKL_IDS(&gen9_stolen_funcs), }; static void __init intel_graphics_stolen(int num, int slot, int func) diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 4b0e1dfa2226..000d4199b03e 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -447,16 +447,14 @@ sysenter_exit: sysenter_audit: testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags(%ebp) jnz syscall_trace_entry - addl $4,%esp - CFI_ADJUST_CFA_OFFSET -4 - /* %esi already in 8(%esp) 6th arg: 4th syscall arg */ - /* %edx already in 4(%esp) 5th arg: 3rd syscall arg */ - /* %ecx already in 0(%esp) 4th arg: 2nd syscall arg */ - movl %ebx,%ecx /* 3rd arg: 1st syscall arg */ - movl %eax,%edx /* 2nd arg: syscall number */ - movl $AUDIT_ARCH_I386,%eax /* 1st arg: audit arch */ + /* movl PT_EAX(%esp), %eax already set, syscall number: 1st arg to audit */ + movl PT_EBX(%esp), %edx /* ebx/a0: 2nd arg to audit */ + /* movl PT_ECX(%esp), %ecx already set, a1: 3nd arg to audit */ + pushl_cfi PT_ESI(%esp) /* a3: 5th arg */ + pushl_cfi PT_EDX+4(%esp) /* a2: 4th arg */ call __audit_syscall_entry - pushl_cfi %ebx + popl_cfi %ecx /* get that remapped edx off the stack */ + popl_cfi %ecx /* get that remapped esi off the stack */ movl PT_EAX(%esp),%eax /* reload syscall number */ jmp sysenter_do_call @@ -734,10 +732,10 @@ ENTRY(interrupt) ENTRY(irq_entries_start) RING0_INT_FRAME vector=FIRST_EXTERNAL_VECTOR -.rept (NR_VECTORS-FIRST_EXTERNAL_VECTOR+6)/7 +.rept (FIRST_SYSTEM_VECTOR-FIRST_EXTERNAL_VECTOR+6)/7 .balign 32 .rept 7 - .if vector < NR_VECTORS + .if vector < FIRST_SYSTEM_VECTOR .if vector <> FIRST_EXTERNAL_VECTOR CFI_ADJUST_CFA_OFFSET -4 .endif @@ -1193,10 +1191,10 @@ ENTRY(ftrace_graph_caller) pushl %eax pushl %ecx pushl %edx - movl 0xc(%esp), %edx - lea 0x4(%ebp), %eax + movl 0xc(%esp), %eax + lea 0x4(%ebp), %edx movl (%ebp), %ecx - subl $MCOUNT_INSN_SIZE, %edx + subl $MCOUNT_INSN_SIZE, %eax call prepare_ftrace_return popl %edx popl %ecx diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 2fac1343a90b..9ebaf63ba182 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -404,8 +404,8 @@ GLOBAL(system_call_after_swapgs) * and short: */ ENABLE_INTERRUPTS(CLBR_NONE) - SAVE_ARGS 8,0 - movq %rax,ORIG_RAX-ARGOFFSET(%rsp) + SAVE_ARGS 8, 0, rax_enosys=1 + movq_cfi rax,(ORIG_RAX-ARGOFFSET) movq %rcx,RIP-ARGOFFSET(%rsp) CFI_REL_OFFSET rip,RIP-ARGOFFSET testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) @@ -417,7 +417,7 @@ system_call_fastpath: andl $__SYSCALL_MASK,%eax cmpl $__NR_syscall_max,%eax #endif - ja badsys + ja ret_from_sys_call /* and return regs->ax */ movq %r10,%rcx call *sys_call_table(,%rax,8) # XXX: rip relative movq %rax,RAX-ARGOFFSET(%rsp) @@ -476,28 +476,8 @@ sysret_signal: FIXUP_TOP_OF_STACK %r11, -ARGOFFSET jmp int_check_syscall_exit_work -badsys: - movq $-ENOSYS,RAX-ARGOFFSET(%rsp) - jmp ret_from_sys_call - #ifdef CONFIG_AUDITSYSCALL /* - * Fast path for syscall audit without full syscall trace. - * We just call __audit_syscall_entry() directly, and then - * jump back to the normal fast path. - */ -auditsys: - movq %r10,%r9 /* 6th arg: 4th syscall arg */ - movq %rdx,%r8 /* 5th arg: 3rd syscall arg */ - movq %rsi,%rcx /* 4th arg: 2nd syscall arg */ - movq %rdi,%rdx /* 3rd arg: 1st syscall arg */ - movq %rax,%rsi /* 2nd arg: syscall number */ - movl $AUDIT_ARCH_X86_64,%edi /* 1st arg: audit arch */ - call __audit_syscall_entry - LOAD_ARGS 0 /* reload call-clobbered registers */ - jmp system_call_fastpath - - /* * Return fast path for syscall audit. Call __audit_syscall_exit() * directly and then jump back to the fast path with TIF_SYSCALL_AUDIT * masked off. @@ -514,18 +494,25 @@ sysret_audit: /* Do syscall tracing */ tracesys: -#ifdef CONFIG_AUDITSYSCALL - testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) - jz auditsys -#endif + leaq -REST_SKIP(%rsp), %rdi + movq $AUDIT_ARCH_X86_64, %rsi + call syscall_trace_enter_phase1 + test %rax, %rax + jnz tracesys_phase2 /* if needed, run the slow path */ + LOAD_ARGS 0 /* else restore clobbered regs */ + jmp system_call_fastpath /* and return to the fast path */ + +tracesys_phase2: SAVE_REST - movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */ FIXUP_TOP_OF_STACK %rdi - movq %rsp,%rdi - call syscall_trace_enter + movq %rsp, %rdi + movq $AUDIT_ARCH_X86_64, %rsi + movq %rax,%rdx + call syscall_trace_enter_phase2 + /* * Reload arg registers from stack in case ptrace changed them. - * We don't reload %rax because syscall_trace_enter() returned + * We don't reload %rax because syscall_trace_entry_phase2() returned * the value it wants us to use in the table lookup. */ LOAD_ARGS ARGOFFSET, 1 @@ -536,7 +523,7 @@ tracesys: andl $__SYSCALL_MASK,%eax cmpl $__NR_syscall_max,%eax #endif - ja int_ret_from_sys_call /* RAX(%rsp) set to -ENOSYS above */ + ja int_ret_from_sys_call /* RAX(%rsp) is already set */ movq %r10,%rcx /* fixup for C */ call *sys_call_table(,%rax,8) movq %rax,RAX-ARGOFFSET(%rsp) @@ -665,6 +652,20 @@ ENTRY(stub_execve) CFI_ENDPROC END(stub_execve) +ENTRY(stub_execveat) + CFI_STARTPROC + addq $8, %rsp + PARTIAL_FRAME 0 + SAVE_REST + FIXUP_TOP_OF_STACK %r11 + call sys_execveat + RESTORE_TOP_OF_STACK %r11 + movq %rax,RAX(%rsp) + RESTORE_REST + jmp int_ret_from_sys_call + CFI_ENDPROC +END(stub_execveat) + /* * sigreturn is special because it needs to restore all registers on return. * This cannot be done with SYSRET, so use the IRET return path instead. @@ -710,6 +711,20 @@ ENTRY(stub_x32_execve) CFI_ENDPROC END(stub_x32_execve) +ENTRY(stub_x32_execveat) + CFI_STARTPROC + addq $8, %rsp + PARTIAL_FRAME 0 + SAVE_REST + FIXUP_TOP_OF_STACK %r11 + call compat_sys_execveat + RESTORE_TOP_OF_STACK %r11 + movq %rax,RAX(%rsp) + RESTORE_REST + jmp int_ret_from_sys_call + CFI_ENDPROC +END(stub_x32_execveat) + #endif /* @@ -725,10 +740,10 @@ ENTRY(interrupt) ENTRY(irq_entries_start) INTR_FRAME vector=FIRST_EXTERNAL_VECTOR -.rept (NR_VECTORS-FIRST_EXTERNAL_VECTOR+6)/7 +.rept (FIRST_SYSTEM_VECTOR-FIRST_EXTERNAL_VECTOR+6)/7 .balign 32 .rept 7 - .if vector < NR_VECTORS + .if vector < FIRST_SYSTEM_VECTOR .if vector <> FIRST_EXTERNAL_VECTOR CFI_ADJUST_CFA_OFFSET -8 .endif @@ -841,9 +856,15 @@ ENTRY(native_iret) jnz native_irq_return_ldt #endif +.global native_irq_return_iret native_irq_return_iret: + /* + * This may fault. Non-paranoid faults on return to userspace are + * handled by fixup_bad_iret. These include #SS, #GP, and #NP. + * Double-faults due to espfix64 are handled in do_double_fault. + * Other faults here are fatal. + */ iretq - _ASM_EXTABLE(native_irq_return_iret, bad_iret) #ifdef CONFIG_X86_ESPFIX64 native_irq_return_ldt: @@ -871,25 +892,6 @@ native_irq_return_ldt: jmp native_irq_return_iret #endif - .section .fixup,"ax" -bad_iret: - /* - * The iret traps when the %cs or %ss being restored is bogus. - * We've lost the original trap vector and error code. - * #GPF is the most likely one to get for an invalid selector. - * So pretend we completed the iret and took the #GPF in user mode. - * - * We are now running with the kernel GS after exception recovery. - * But error_entry expects us to have user GS to match the user %cs, - * so swap back. - */ - pushq $0 - - SWAPGS - jmp general_protection - - .previous - /* edi: workmask, edx: work */ retint_careful: CFI_RESTORE_STATE @@ -935,37 +937,6 @@ ENTRY(retint_kernel) CFI_ENDPROC END(common_interrupt) - /* - * If IRET takes a fault on the espfix stack, then we - * end up promoting it to a doublefault. In that case, - * modify the stack to make it look like we just entered - * the #GP handler from user space, similar to bad_iret. - */ -#ifdef CONFIG_X86_ESPFIX64 - ALIGN -__do_double_fault: - XCPT_FRAME 1 RDI+8 - movq RSP(%rdi),%rax /* Trap on the espfix stack? */ - sarq $PGDIR_SHIFT,%rax - cmpl $ESPFIX_PGD_ENTRY,%eax - jne do_double_fault /* No, just deliver the fault */ - cmpl $__KERNEL_CS,CS(%rdi) - jne do_double_fault - movq RIP(%rdi),%rax - cmpq $native_irq_return_iret,%rax - jne do_double_fault /* This shouldn't happen... */ - movq PER_CPU_VAR(kernel_stack),%rax - subq $(6*8-KERNEL_STACK_OFFSET),%rax /* Reset to original stack */ - movq %rax,RSP(%rdi) - movq $0,(%rax) /* Missing (lost) #GP error code */ - movq $general_protection,RIP(%rdi) - retq - CFI_ENDPROC -END(__do_double_fault) -#else -# define __do_double_fault do_double_fault -#endif - /* * APIC interrupts. */ @@ -1137,7 +1108,7 @@ idtentry overflow do_overflow has_error_code=0 idtentry bounds do_bounds has_error_code=0 idtentry invalid_op do_invalid_op has_error_code=0 idtentry device_not_available do_device_not_available has_error_code=0 -idtentry double_fault __do_double_fault has_error_code=1 paranoid=1 +idtentry double_fault do_double_fault has_error_code=1 paranoid=1 idtentry coprocessor_segment_overrun do_coprocessor_segment_overrun has_error_code=0 idtentry invalid_TSS do_invalid_TSS has_error_code=1 idtentry segment_not_present do_segment_not_present has_error_code=1 @@ -1302,7 +1273,7 @@ apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \ idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK idtentry int3 do_int3 has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK -idtentry stack_segment do_stack_segment has_error_code=1 paranoid=1 +idtentry stack_segment do_stack_segment has_error_code=1 #ifdef CONFIG_XEN idtentry xen_debug do_debug has_error_code=0 idtentry xen_int3 do_int3 has_error_code=0 @@ -1412,17 +1383,16 @@ error_sti: /* * There are two places in the kernel that can potentially fault with - * usergs. Handle them here. The exception handlers after iret run with - * kernel gs again, so don't set the user space flag. B stepping K8s - * sometimes report an truncated RIP for IRET exceptions returning to - * compat mode. Check for these here too. + * usergs. Handle them here. B stepping K8s sometimes report a + * truncated RIP for IRET exceptions returning to compat mode. Check + * for these here too. */ error_kernelspace: CFI_REL_OFFSET rcx, RCX+8 incl %ebx leaq native_irq_return_iret(%rip),%rcx cmpq %rcx,RIP+8(%rsp) - je error_swapgs + je error_bad_iret movl %ecx,%eax /* zero extend */ cmpq %rax,RIP+8(%rsp) je bstep_iret @@ -1433,7 +1403,15 @@ error_kernelspace: bstep_iret: /* Fix truncated RIP */ movq %rcx,RIP+8(%rsp) - jmp error_swapgs + /* fall through */ + +error_bad_iret: + SWAPGS + mov %rsp,%rdi + call fixup_bad_iret + mov %rax,%rsp + decl %ebx /* Return to usergs */ + jmp error_sti CFI_ENDPROC END(error_entry) diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c index 94d857fb1033..f5d0730e7b08 100644 --- a/arch/x86/kernel/espfix_64.c +++ b/arch/x86/kernel/espfix_64.c @@ -122,9 +122,6 @@ static void init_espfix_random(void) void __init init_espfix_bsp(void) { pgd_t *pgd_p; - pteval_t ptemask; - - ptemask = __supported_pte_mask; /* Install the espfix pud into the kernel page directory */ pgd_p = &init_level4_pgt[pgd_index(ESPFIX_BASE_ADDR)]; diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 3386dc9aa333..2142376dc8c6 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -17,6 +17,7 @@ #include <linux/ftrace.h> #include <linux/percpu.h> #include <linux/sched.h> +#include <linux/slab.h> #include <linux/init.h> #include <linux/list.h> #include <linux/module.h> @@ -47,7 +48,7 @@ int ftrace_arch_code_modify_post_process(void) union ftrace_code_union { char code[MCOUNT_INSN_SIZE]; struct { - char e8; + unsigned char e8; int offset; } __attribute__((packed)); }; @@ -582,7 +583,7 @@ void ftrace_replace_code(int enable) remove_breakpoints: pr_warn("Failed on %s (%d):\n", report, count); - ftrace_bug(ret, rec ? rec->ip : 0); + ftrace_bug(ret, rec); for_ftrace_rec_iter(iter) { rec = ftrace_rec_iter_record(iter); /* @@ -644,13 +645,8 @@ int __init ftrace_dyn_arch_init(void) { return 0; } -#endif - -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - -#ifdef CONFIG_DYNAMIC_FTRACE -extern void ftrace_graph_call(void); +#if defined(CONFIG_X86_64) || defined(CONFIG_FUNCTION_GRAPH_TRACER) static unsigned char *ftrace_jmp_replace(unsigned long ip, unsigned long addr) { static union ftrace_code_union calc; @@ -664,6 +660,280 @@ static unsigned char *ftrace_jmp_replace(unsigned long ip, unsigned long addr) */ return calc.code; } +#endif + +/* Currently only x86_64 supports dynamic trampolines */ +#ifdef CONFIG_X86_64 + +#ifdef CONFIG_MODULES +#include <linux/moduleloader.h> +/* Module allocation simplifies allocating memory for code */ +static inline void *alloc_tramp(unsigned long size) +{ + return module_alloc(size); +} +static inline void tramp_free(void *tramp) +{ + module_free(NULL, tramp); +} +#else +/* Trampolines can only be created if modules are supported */ +static inline void *alloc_tramp(unsigned long size) +{ + return NULL; +} +static inline void tramp_free(void *tramp) { } +#endif + +/* Defined as markers to the end of the ftrace default trampolines */ +extern void ftrace_caller_end(void); +extern void ftrace_regs_caller_end(void); +extern void ftrace_return(void); +extern void ftrace_caller_op_ptr(void); +extern void ftrace_regs_caller_op_ptr(void); + +/* movq function_trace_op(%rip), %rdx */ +/* 0x48 0x8b 0x15 <offset-to-ftrace_trace_op (4 bytes)> */ +#define OP_REF_SIZE 7 + +/* + * The ftrace_ops is passed to the function callback. Since the + * trampoline only services a single ftrace_ops, we can pass in + * that ops directly. + * + * The ftrace_op_code_union is used to create a pointer to the + * ftrace_ops that will be passed to the callback function. + */ +union ftrace_op_code_union { + char code[OP_REF_SIZE]; + struct { + char op[3]; + int offset; + } __attribute__((packed)); +}; + +static unsigned long +create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) +{ + unsigned const char *jmp; + unsigned long start_offset; + unsigned long end_offset; + unsigned long op_offset; + unsigned long offset; + unsigned long size; + unsigned long ip; + unsigned long *ptr; + void *trampoline; + /* 48 8b 15 <offset> is movq <offset>(%rip), %rdx */ + unsigned const char op_ref[] = { 0x48, 0x8b, 0x15 }; + union ftrace_op_code_union op_ptr; + int ret; + + if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) { + start_offset = (unsigned long)ftrace_regs_caller; + end_offset = (unsigned long)ftrace_regs_caller_end; + op_offset = (unsigned long)ftrace_regs_caller_op_ptr; + } else { + start_offset = (unsigned long)ftrace_caller; + end_offset = (unsigned long)ftrace_caller_end; + op_offset = (unsigned long)ftrace_caller_op_ptr; + } + + size = end_offset - start_offset; + + /* + * Allocate enough size to store the ftrace_caller code, + * the jmp to ftrace_return, as well as the address of + * the ftrace_ops this trampoline is used for. + */ + trampoline = alloc_tramp(size + MCOUNT_INSN_SIZE + sizeof(void *)); + if (!trampoline) + return 0; + + *tramp_size = size + MCOUNT_INSN_SIZE + sizeof(void *); + + /* Copy ftrace_caller onto the trampoline memory */ + ret = probe_kernel_read(trampoline, (void *)start_offset, size); + if (WARN_ON(ret < 0)) { + tramp_free(trampoline); + return 0; + } + + ip = (unsigned long)trampoline + size; + + /* The trampoline ends with a jmp to ftrace_return */ + jmp = ftrace_jmp_replace(ip, (unsigned long)ftrace_return); + memcpy(trampoline + size, jmp, MCOUNT_INSN_SIZE); + + /* + * The address of the ftrace_ops that is used for this trampoline + * is stored at the end of the trampoline. This will be used to + * load the third parameter for the callback. Basically, that + * location at the end of the trampoline takes the place of + * the global function_trace_op variable. + */ + + ptr = (unsigned long *)(trampoline + size + MCOUNT_INSN_SIZE); + *ptr = (unsigned long)ops; + + op_offset -= start_offset; + memcpy(&op_ptr, trampoline + op_offset, OP_REF_SIZE); + + /* Are we pointing to the reference? */ + if (WARN_ON(memcmp(op_ptr.op, op_ref, 3) != 0)) { + tramp_free(trampoline); + return 0; + } + + /* Load the contents of ptr into the callback parameter */ + offset = (unsigned long)ptr; + offset -= (unsigned long)trampoline + op_offset + OP_REF_SIZE; + + op_ptr.offset = offset; + + /* put in the new offset to the ftrace_ops */ + memcpy(trampoline + op_offset, &op_ptr, OP_REF_SIZE); + + /* ALLOC_TRAMP flags lets us know we created it */ + ops->flags |= FTRACE_OPS_FL_ALLOC_TRAMP; + + return (unsigned long)trampoline; +} + +static unsigned long calc_trampoline_call_offset(bool save_regs) +{ + unsigned long start_offset; + unsigned long call_offset; + + if (save_regs) { + start_offset = (unsigned long)ftrace_regs_caller; + call_offset = (unsigned long)ftrace_regs_call; + } else { + start_offset = (unsigned long)ftrace_caller; + call_offset = (unsigned long)ftrace_call; + } + + return call_offset - start_offset; +} + +void arch_ftrace_update_trampoline(struct ftrace_ops *ops) +{ + ftrace_func_t func; + unsigned char *new; + unsigned long offset; + unsigned long ip; + unsigned int size; + int ret; + + if (ops->trampoline) { + /* + * The ftrace_ops caller may set up its own trampoline. + * In such a case, this code must not modify it. + */ + if (!(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP)) + return; + } else { + ops->trampoline = create_trampoline(ops, &size); + if (!ops->trampoline) + return; + ops->trampoline_size = size; + } + + offset = calc_trampoline_call_offset(ops->flags & FTRACE_OPS_FL_SAVE_REGS); + ip = ops->trampoline + offset; + + func = ftrace_ops_get_func(ops); + + /* Do a safe modify in case the trampoline is executing */ + new = ftrace_call_replace(ip, (unsigned long)func); + ret = update_ftrace_func(ip, new); + + /* The update should never fail */ + WARN_ON(ret); +} + +/* Return the address of the function the trampoline calls */ +static void *addr_from_call(void *ptr) +{ + union ftrace_code_union calc; + int ret; + + ret = probe_kernel_read(&calc, ptr, MCOUNT_INSN_SIZE); + if (WARN_ON_ONCE(ret < 0)) + return NULL; + + /* Make sure this is a call */ + if (WARN_ON_ONCE(calc.e8 != 0xe8)) { + pr_warn("Expected e8, got %x\n", calc.e8); + return NULL; + } + + return ptr + MCOUNT_INSN_SIZE + calc.offset; +} + +void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, + unsigned long frame_pointer); + +/* + * If the ops->trampoline was not allocated, then it probably + * has a static trampoline func, or is the ftrace caller itself. + */ +static void *static_tramp_func(struct ftrace_ops *ops, struct dyn_ftrace *rec) +{ + unsigned long offset; + bool save_regs = rec->flags & FTRACE_FL_REGS_EN; + void *ptr; + + if (ops && ops->trampoline) { +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + /* + * We only know about function graph tracer setting as static + * trampoline. + */ + if (ops->trampoline == FTRACE_GRAPH_ADDR) + return (void *)prepare_ftrace_return; +#endif + return NULL; + } + + offset = calc_trampoline_call_offset(save_regs); + + if (save_regs) + ptr = (void *)FTRACE_REGS_ADDR + offset; + else + ptr = (void *)FTRACE_ADDR + offset; + + return addr_from_call(ptr); +} + +void *arch_ftrace_trampoline_func(struct ftrace_ops *ops, struct dyn_ftrace *rec) +{ + unsigned long offset; + + /* If we didn't allocate this trampoline, consider it static */ + if (!ops || !(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP)) + return static_tramp_func(ops, rec); + + offset = calc_trampoline_call_offset(ops->flags & FTRACE_OPS_FL_SAVE_REGS); + return addr_from_call((void *)ops->trampoline + offset); +} + +void arch_ftrace_trampoline_free(struct ftrace_ops *ops) +{ + if (!ops || !(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP)) + return; + + tramp_free((void *)ops->trampoline); + ops->trampoline = 0; +} + +#endif /* CONFIG_X86_64 */ +#endif /* CONFIG_DYNAMIC_FTRACE */ + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + +#ifdef CONFIG_DYNAMIC_FTRACE +extern void ftrace_graph_call(void); static int ftrace_mod_jmp(unsigned long ip, void *func) { @@ -694,7 +964,7 @@ int ftrace_disable_ftrace_graph_caller(void) * Hook the return address and push it in the stack of return addrs * in current thread info. */ -void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, +void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, unsigned long frame_pointer) { unsigned long old; diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index 5f9cf20cdb68..3d5fb509bdeb 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -108,7 +108,7 @@ int arch_install_hw_breakpoint(struct perf_event *bp) int i; for (i = 0; i < HBP_NUM; i++) { - struct perf_event **slot = &__get_cpu_var(bp_per_reg[i]); + struct perf_event **slot = this_cpu_ptr(&bp_per_reg[i]); if (!*slot) { *slot = bp; @@ -122,7 +122,7 @@ int arch_install_hw_breakpoint(struct perf_event *bp) set_debugreg(info->address, i); __this_cpu_write(cpu_debugreg[i], info->address); - dr7 = &__get_cpu_var(cpu_dr7); + dr7 = this_cpu_ptr(&cpu_dr7); *dr7 |= encode_dr7(i, info->len, info->type); set_debugreg(*dr7, 7); @@ -146,7 +146,7 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp) int i; for (i = 0; i < HBP_NUM; i++) { - struct perf_event **slot = &__get_cpu_var(bp_per_reg[i]); + struct perf_event **slot = this_cpu_ptr(&bp_per_reg[i]); if (*slot == bp) { *slot = NULL; @@ -157,7 +157,7 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp) if (WARN_ONCE(i == HBP_NUM, "Can't find any breakpoint slot")) return; - dr7 = &__get_cpu_var(cpu_dr7); + dr7 = this_cpu_ptr(&cpu_dr7); *dr7 &= ~__encode_dr7(i, info->len, info->type); set_debugreg(*dr7, 7); diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c index 8af817105e29..e7cc5370cd2f 100644 --- a/arch/x86/kernel/i8259.c +++ b/arch/x86/kernel/i8259.c @@ -111,8 +111,7 @@ static void make_8259A_irq(unsigned int irq) { disable_irq_nosync(irq); io_apic_irqs &= ~(1<<irq); - irq_set_chip_and_handler_name(irq, &i8259A_chip, handle_level_irq, - i8259A_chip.name); + irq_set_chip_and_handler(irq, &i8259A_chip, handle_level_irq); enable_irq(irq); } diff --git a/arch/x86/kernel/iosf_mbi.c b/arch/x86/kernel/iosf_mbi.c index 9030e83db6ee..82f8d02f0df2 100644 --- a/arch/x86/kernel/iosf_mbi.c +++ b/arch/x86/kernel/iosf_mbi.c @@ -22,10 +22,13 @@ #include <linux/init.h> #include <linux/spinlock.h> #include <linux/pci.h> +#include <linux/debugfs.h> +#include <linux/capability.h> #include <asm/iosf_mbi.h> #define PCI_DEVICE_ID_BAYTRAIL 0x0F00 +#define PCI_DEVICE_ID_BRASWELL 0x2280 #define PCI_DEVICE_ID_QUARK_X1000 0x0958 static DEFINE_SPINLOCK(iosf_mbi_lock); @@ -187,6 +190,89 @@ bool iosf_mbi_available(void) } EXPORT_SYMBOL(iosf_mbi_available); +#ifdef CONFIG_IOSF_MBI_DEBUG +static u32 dbg_mdr; +static u32 dbg_mcr; +static u32 dbg_mcrx; + +static int mcr_get(void *data, u64 *val) +{ + *val = *(u32 *)data; + return 0; +} + +static int mcr_set(void *data, u64 val) +{ + u8 command = ((u32)val & 0xFF000000) >> 24, + port = ((u32)val & 0x00FF0000) >> 16, + offset = ((u32)val & 0x0000FF00) >> 8; + int err; + + *(u32 *)data = val; + + if (!capable(CAP_SYS_RAWIO)) + return -EACCES; + + if (command & 1u) + err = iosf_mbi_write(port, + command, + dbg_mcrx | offset, + dbg_mdr); + else + err = iosf_mbi_read(port, + command, + dbg_mcrx | offset, + &dbg_mdr); + + return err; +} +DEFINE_SIMPLE_ATTRIBUTE(iosf_mcr_fops, mcr_get, mcr_set , "%llx\n"); + +static struct dentry *iosf_dbg; + +static void iosf_sideband_debug_init(void) +{ + struct dentry *d; + + iosf_dbg = debugfs_create_dir("iosf_sb", NULL); + if (IS_ERR_OR_NULL(iosf_dbg)) + return; + + /* mdr */ + d = debugfs_create_x32("mdr", 0660, iosf_dbg, &dbg_mdr); + if (IS_ERR_OR_NULL(d)) + goto cleanup; + + /* mcrx */ + debugfs_create_x32("mcrx", 0660, iosf_dbg, &dbg_mcrx); + if (IS_ERR_OR_NULL(d)) + goto cleanup; + + /* mcr - initiates mailbox tranaction */ + debugfs_create_file("mcr", 0660, iosf_dbg, &dbg_mcr, &iosf_mcr_fops); + if (IS_ERR_OR_NULL(d)) + goto cleanup; + + return; + +cleanup: + debugfs_remove_recursive(d); +} + +static void iosf_debugfs_init(void) +{ + iosf_sideband_debug_init(); +} + +static void iosf_debugfs_remove(void) +{ + debugfs_remove_recursive(iosf_dbg); +} +#else +static inline void iosf_debugfs_init(void) { } +static inline void iosf_debugfs_remove(void) { } +#endif /* CONFIG_IOSF_MBI_DEBUG */ + static int iosf_mbi_probe(struct pci_dev *pdev, const struct pci_device_id *unused) { @@ -204,6 +290,7 @@ static int iosf_mbi_probe(struct pci_dev *pdev, static const struct pci_device_id iosf_mbi_pci_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_BAYTRAIL) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_BRASWELL) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_QUARK_X1000) }, { 0, }, }; @@ -217,11 +304,15 @@ static struct pci_driver iosf_mbi_pci_driver = { static int __init iosf_mbi_init(void) { + iosf_debugfs_init(); + return pci_register_driver(&iosf_mbi_pci_driver); } static void __exit iosf_mbi_exit(void) { + iosf_debugfs_remove(); + pci_unregister_driver(&iosf_mbi_pci_driver); if (mbi_pdev) { pci_dev_put(mbi_pdev); diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 922d28581024..6307a0f0cf17 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -59,78 +59,78 @@ int arch_show_interrupts(struct seq_file *p, int prec) seq_printf(p, "%*s: ", prec, "NMI"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->__nmi_count); - seq_printf(p, " Non-maskable interrupts\n"); + seq_puts(p, " Non-maskable interrupts\n"); #ifdef CONFIG_X86_LOCAL_APIC seq_printf(p, "%*s: ", prec, "LOC"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->apic_timer_irqs); - seq_printf(p, " Local timer interrupts\n"); + seq_puts(p, " Local timer interrupts\n"); seq_printf(p, "%*s: ", prec, "SPU"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->irq_spurious_count); - seq_printf(p, " Spurious interrupts\n"); + seq_puts(p, " Spurious interrupts\n"); seq_printf(p, "%*s: ", prec, "PMI"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->apic_perf_irqs); - seq_printf(p, " Performance monitoring interrupts\n"); + seq_puts(p, " Performance monitoring interrupts\n"); seq_printf(p, "%*s: ", prec, "IWI"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->apic_irq_work_irqs); - seq_printf(p, " IRQ work interrupts\n"); + seq_puts(p, " IRQ work interrupts\n"); seq_printf(p, "%*s: ", prec, "RTR"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->icr_read_retry_count); - seq_printf(p, " APIC ICR read retries\n"); + seq_puts(p, " APIC ICR read retries\n"); #endif if (x86_platform_ipi_callback) { seq_printf(p, "%*s: ", prec, "PLT"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->x86_platform_ipis); - seq_printf(p, " Platform interrupts\n"); + seq_puts(p, " Platform interrupts\n"); } #ifdef CONFIG_SMP seq_printf(p, "%*s: ", prec, "RES"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->irq_resched_count); - seq_printf(p, " Rescheduling interrupts\n"); + seq_puts(p, " Rescheduling interrupts\n"); seq_printf(p, "%*s: ", prec, "CAL"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->irq_call_count - irq_stats(j)->irq_tlb_count); - seq_printf(p, " Function call interrupts\n"); + seq_puts(p, " Function call interrupts\n"); seq_printf(p, "%*s: ", prec, "TLB"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->irq_tlb_count); - seq_printf(p, " TLB shootdowns\n"); + seq_puts(p, " TLB shootdowns\n"); #endif #ifdef CONFIG_X86_THERMAL_VECTOR seq_printf(p, "%*s: ", prec, "TRM"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->irq_thermal_count); - seq_printf(p, " Thermal event interrupts\n"); + seq_puts(p, " Thermal event interrupts\n"); #endif #ifdef CONFIG_X86_MCE_THRESHOLD seq_printf(p, "%*s: ", prec, "THR"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->irq_threshold_count); - seq_printf(p, " Threshold APIC interrupts\n"); + seq_puts(p, " Threshold APIC interrupts\n"); #endif #ifdef CONFIG_X86_MCE seq_printf(p, "%*s: ", prec, "MCE"); for_each_online_cpu(j) seq_printf(p, "%10u ", per_cpu(mce_exception_count, j)); - seq_printf(p, " Machine check exceptions\n"); + seq_puts(p, " Machine check exceptions\n"); seq_printf(p, "%*s: ", prec, "MCP"); for_each_online_cpu(j) seq_printf(p, "%10u ", per_cpu(mce_poll_count, j)); - seq_printf(p, " Machine check polls\n"); + seq_puts(p, " Machine check polls\n"); #endif #if IS_ENABLED(CONFIG_HYPERV) || defined(CONFIG_XEN) seq_printf(p, "%*s: ", prec, "THR"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->irq_hv_callback_count); - seq_printf(p, " Hypervisor callback interrupts\n"); + seq_puts(p, " Hypervisor callback interrupts\n"); #endif seq_printf(p, "%*s: %10u\n", prec, "ERR", atomic_read(&irq_err_count)); #if defined(CONFIG_X86_IO_APIC) diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index 4d1c746892eb..e4b503d5558c 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -52,13 +52,13 @@ static inline void stack_overflow_check(struct pt_regs *regs) regs->sp <= curbase + THREAD_SIZE) return; - irq_stack_top = (u64)__get_cpu_var(irq_stack_union.irq_stack) + + irq_stack_top = (u64)this_cpu_ptr(irq_stack_union.irq_stack) + STACK_TOP_MARGIN; - irq_stack_bottom = (u64)__get_cpu_var(irq_stack_ptr); + irq_stack_bottom = (u64)__this_cpu_read(irq_stack_ptr); if (regs->sp >= irq_stack_top && regs->sp <= irq_stack_bottom) return; - oist = &__get_cpu_var(orig_ist); + oist = this_cpu_ptr(&orig_ist); estack_top = (u64)oist->ist[0] - EXCEPTION_STKSZ + STACK_TOP_MARGIN; estack_bottom = (u64)oist->ist[N_EXCEPTION_STACKS - 1]; if (regs->sp >= estack_top && regs->sp <= estack_bottom) diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c index 1de84e3ab4e0..15d741ddfeeb 100644 --- a/arch/x86/kernel/irq_work.c +++ b/arch/x86/kernel/irq_work.c @@ -41,7 +41,7 @@ __visible void smp_trace_irq_work_interrupt(struct pt_regs *regs) void arch_irq_work_raise(void) { #ifdef CONFIG_X86_LOCAL_APIC - if (!cpu_has_apic) + if (!arch_irq_work_has_interrupt()) return; apic->send_IPI_self(IRQ_WORK_VECTOR); diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index 44f1ed42fdf2..70e181ea1eac 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -70,7 +70,6 @@ int vector_used_by_percpu_irq(unsigned int vector) void __init init_ISA_irqs(void) { struct irq_chip *chip = legacy_pic->chip; - const char *name = chip->name; int i; #if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC) @@ -79,7 +78,7 @@ void __init init_ISA_irqs(void) legacy_pic->init(0); for (i = 0; i < nr_legacy_irqs(); i++) - irq_set_chip_and_handler_name(i, chip, handle_level_irq, name); + irq_set_chip_and_handler(i, chip, handle_level_irq); } void __init init_IRQ(void) @@ -100,32 +99,9 @@ void __init init_IRQ(void) x86_init.irqs.intr_init(); } -/* - * Setup the vector to irq mappings. - */ -void setup_vector_irq(int cpu) -{ -#ifndef CONFIG_X86_IO_APIC - int irq; - - /* - * On most of the platforms, legacy PIC delivers the interrupts on the - * boot cpu. But there are certain platforms where PIC interrupts are - * delivered to multiple cpu's. If the legacy IRQ is handled by the - * legacy PIC, for the new cpu that is coming online, setup the static - * legacy vector to irq mapping: - */ - for (irq = 0; irq < nr_legacy_irqs(); irq++) - per_cpu(vector_irq, cpu)[IRQ0_VECTOR + irq] = irq; -#endif - - __setup_vector_irq(cpu); -} - static void __init smp_intr_init(void) { #ifdef CONFIG_SMP -#if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC) /* * The reschedule interrupt is a CPU-to-CPU reschedule-helper * IPI, driven by wakeup. @@ -145,7 +121,6 @@ static void __init smp_intr_init(void) /* IPI used for rebooting/stopping */ alloc_intr_gate(REBOOT_VECTOR, reboot_interrupt); -#endif #endif /* CONFIG_SMP */ } @@ -160,7 +135,7 @@ static void __init apic_intr_init(void) alloc_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt); #endif -#if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC) +#ifdef CONFIG_X86_LOCAL_APIC /* self generated IPI for local APIC timer */ alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt); @@ -198,10 +173,17 @@ void __init native_init_IRQ(void) * 'special' SMP interrupts) */ i = FIRST_EXTERNAL_VECTOR; - for_each_clear_bit_from(i, used_vectors, NR_VECTORS) { +#ifndef CONFIG_X86_LOCAL_APIC +#define first_system_vector NR_VECTORS +#endif + for_each_clear_bit_from(i, used_vectors, first_system_vector) { /* IA32_SYSCALL_VECTOR could be used in trap_init already. */ set_intr_gate(i, interrupt[i - FIRST_EXTERNAL_VECTOR]); } +#ifdef CONFIG_X86_LOCAL_APIC + for_each_clear_bit_from(i, used_vectors, NR_VECTORS) + set_intr_gate(i, spurious_interrupt); +#endif if (!acpi_ioapic && !of_ioapic && nr_legacy_irqs()) setup_irq(2, &irq2); diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index 9642b9b33655..ca05f86481aa 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -26,6 +26,7 @@ #include <asm/setup.h> #include <asm/crash.h> #include <asm/efi.h> +#include <asm/kexec-bzimage64.h> #define MAX_ELFCOREHDR_STR_LEN 30 /* elfcorehdr=0x<64bit-value> */ @@ -267,7 +268,7 @@ setup_boot_parameters(struct kimage *image, struct boot_params *params, return ret; } -int bzImage64_probe(const char *buf, unsigned long len) +static int bzImage64_probe(const char *buf, unsigned long len) { int ret = -ENOEXEC; struct setup_header *header; @@ -325,10 +326,10 @@ int bzImage64_probe(const char *buf, unsigned long len) return ret; } -void *bzImage64_load(struct kimage *image, char *kernel, - unsigned long kernel_len, char *initrd, - unsigned long initrd_len, char *cmdline, - unsigned long cmdline_len) +static void *bzImage64_load(struct kimage *image, char *kernel, + unsigned long kernel_len, char *initrd, + unsigned long initrd_len, char *cmdline, + unsigned long cmdline_len) { struct setup_header *header; @@ -514,7 +515,7 @@ out_free_params: } /* This cleanup function is called after various segments have been loaded */ -int bzImage64_cleanup(void *loader_data) +static int bzImage64_cleanup(void *loader_data) { struct bzimage64_data *ldata = loader_data; @@ -528,7 +529,7 @@ int bzImage64_cleanup(void *loader_data) } #ifdef CONFIG_KEXEC_BZIMAGE_VERIFY_SIG -int bzImage64_verify_sig(const char *kernel, unsigned long kernel_len) +static int bzImage64_verify_sig(const char *kernel, unsigned long kernel_len) { bool trusted; int ret; diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 67e6d19ef1be..f7e3cd50ece0 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -285,7 +285,7 @@ static int can_probe(unsigned long paddr) * normally used, we just go through if there is no kprobe. */ __addr = recover_probed_instruction(buf, addr); - kernel_insn_init(&insn, (void *)__addr); + kernel_insn_init(&insn, (void *)__addr, MAX_INSN_SIZE); insn_get_length(&insn); /* @@ -330,8 +330,10 @@ int __copy_instruction(u8 *dest, u8 *src) { struct insn insn; kprobe_opcode_t buf[MAX_INSN_SIZE]; + unsigned long recovered_insn = + recover_probed_instruction(buf, (unsigned long)src); - kernel_insn_init(&insn, (void *)recover_probed_instruction(buf, (unsigned long)src)); + kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE); insn_get_length(&insn); /* Another subsystem puts a breakpoint, failed to recover */ if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) @@ -342,7 +344,7 @@ int __copy_instruction(u8 *dest, u8 *src) if (insn_rip_relative(&insn)) { s64 newdisp; u8 *disp; - kernel_insn_init(&insn, dest); + kernel_insn_init(&insn, dest, insn.length); insn_get_displacement(&insn); /* * The copied instruction uses the %rip-relative addressing diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c index 717b02a22e67..5f8f0b3cc674 100644 --- a/arch/x86/kernel/kprobes/ftrace.c +++ b/arch/x86/kernel/kprobes/ftrace.c @@ -27,7 +27,7 @@ static nokprobe_inline int __skip_singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb) + struct kprobe_ctlblk *kcb, unsigned long orig_ip) { /* * Emulate singlestep (and also recover regs->ip) @@ -39,6 +39,8 @@ int __skip_singlestep(struct kprobe *p, struct pt_regs *regs, p->post_handler(p, regs, 0); } __this_cpu_write(current_kprobe, NULL); + if (orig_ip) + regs->ip = orig_ip; return 1; } @@ -46,7 +48,7 @@ int skip_singlestep(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb) { if (kprobe_ftrace(p)) - return __skip_singlestep(p, regs, kcb); + return __skip_singlestep(p, regs, kcb, 0); else return 0; } @@ -71,13 +73,14 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, if (kprobe_running()) { kprobes_inc_nmissed_count(p); } else { + unsigned long orig_ip = regs->ip; /* Kprobe handler expects regs->ip = ip + 1 as breakpoint hit */ regs->ip = ip + sizeof(kprobe_opcode_t); __this_cpu_write(current_kprobe, p); kcb->kprobe_status = KPROBE_HIT_ACTIVE; if (!p->pre_handler || !p->pre_handler(p, regs)) - __skip_singlestep(p, regs, kcb); + __skip_singlestep(p, regs, kcb, orig_ip); /* * If pre_handler returns !0, it sets regs->ip and * resets current kprobe. diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index f1314d0bcf0a..7c523bbf3dc8 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -251,13 +251,15 @@ static int can_optimize(unsigned long paddr) /* Decode instructions */ addr = paddr - offset; while (addr < paddr - offset + size) { /* Decode until function end */ + unsigned long recovered_insn; if (search_exception_tables(addr)) /* * Since some fixup code will jumps into this function, * we can't optimize kprobe in this function. */ return 0; - kernel_insn_init(&insn, (void *)recover_probed_instruction(buf, addr)); + recovered_insn = recover_probed_instruction(buf, addr); + kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE); insn_get_length(&insn); /* Another subsystem puts a breakpoint */ if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 3dd8e2c4d74a..94f643484300 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -35,6 +35,7 @@ #include <linux/slab.h> #include <linux/kprobes.h> #include <linux/debugfs.h> +#include <linux/nmi.h> #include <asm/timer.h> #include <asm/cpu.h> #include <asm/traps.h> @@ -243,9 +244,9 @@ u32 kvm_read_and_reset_pf_reason(void) { u32 reason = 0; - if (__get_cpu_var(apf_reason).enabled) { - reason = __get_cpu_var(apf_reason).reason; - __get_cpu_var(apf_reason).reason = 0; + if (__this_cpu_read(apf_reason.enabled)) { + reason = __this_cpu_read(apf_reason.reason); + __this_cpu_write(apf_reason.reason, 0); } return reason; @@ -282,7 +283,14 @@ NOKPROBE_SYMBOL(do_async_page_fault); static void __init paravirt_ops_setup(void) { pv_info.name = "KVM"; - pv_info.paravirt_enabled = 1; + + /* + * KVM isn't paravirt in the sense of paravirt_enabled. A KVM + * guest kernel works like a bare metal kernel with additional + * features, and paravirt_enabled is about features that are + * missing. + */ + pv_info.paravirt_enabled = 0; if (kvm_para_has_feature(KVM_FEATURE_NOP_IO_DELAY)) pv_cpu_ops.io_delay = kvm_io_delay; @@ -318,7 +326,7 @@ static void kvm_guest_apic_eoi_write(u32 reg, u32 val) * there's no need for lock or memory barriers. * An optimization barrier is implied in apic write. */ - if (__test_and_clear_bit(KVM_PV_EOI_BIT, &__get_cpu_var(kvm_apic_eoi))) + if (__test_and_clear_bit(KVM_PV_EOI_BIT, this_cpu_ptr(&kvm_apic_eoi))) return; apic_write(APIC_EOI, APIC_EOI_ACK); } @@ -329,13 +337,13 @@ void kvm_guest_cpu_init(void) return; if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF) && kvmapf) { - u64 pa = slow_virt_to_phys(&__get_cpu_var(apf_reason)); + u64 pa = slow_virt_to_phys(this_cpu_ptr(&apf_reason)); #ifdef CONFIG_PREEMPT pa |= KVM_ASYNC_PF_SEND_ALWAYS; #endif wrmsrl(MSR_KVM_ASYNC_PF_EN, pa | KVM_ASYNC_PF_ENABLED); - __get_cpu_var(apf_reason).enabled = 1; + __this_cpu_write(apf_reason.enabled, 1); printk(KERN_INFO"KVM setup async PF for cpu %d\n", smp_processor_id()); } @@ -344,8 +352,8 @@ void kvm_guest_cpu_init(void) unsigned long pa; /* Size alignment is implied but just to make it explicit. */ BUILD_BUG_ON(__alignof__(kvm_apic_eoi) < 4); - __get_cpu_var(kvm_apic_eoi) = 0; - pa = slow_virt_to_phys(&__get_cpu_var(kvm_apic_eoi)) + __this_cpu_write(kvm_apic_eoi, 0); + pa = slow_virt_to_phys(this_cpu_ptr(&kvm_apic_eoi)) | KVM_MSR_ENABLED; wrmsrl(MSR_KVM_PV_EOI_EN, pa); } @@ -356,11 +364,11 @@ void kvm_guest_cpu_init(void) static void kvm_pv_disable_apf(void) { - if (!__get_cpu_var(apf_reason).enabled) + if (!__this_cpu_read(apf_reason.enabled)) return; wrmsrl(MSR_KVM_ASYNC_PF_EN, 0); - __get_cpu_var(apf_reason).enabled = 0; + __this_cpu_write(apf_reason.enabled, 0); printk(KERN_INFO"Unregister pv shared memory for cpu %d\n", smp_processor_id()); @@ -499,6 +507,13 @@ void __init kvm_guest_init(void) #else kvm_guest_cpu_init(); #endif + + /* + * Hard lockup detection is enabled by default. Disable it, as guests + * can get false positives too easily, for example if the host is + * overcommitted. + */ + watchdog_enable_hardlockup_detector(false); } static noinline uint32_t __kvm_cpuid_base(void) @@ -716,7 +731,7 @@ __visible void kvm_lock_spinning(struct arch_spinlock *lock, __ticket_t want) if (in_nmi()) return; - w = &__get_cpu_var(klock_waiting); + w = this_cpu_ptr(&klock_waiting); cpu = smp_processor_id(); start = spin_time_start(); diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index d9156ceecdff..42caaef897c8 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -59,13 +59,12 @@ static void kvm_get_wallclock(struct timespec *now) native_write_msr(msr_kvm_wall_clock, low, high); - preempt_disable(); - cpu = smp_processor_id(); + cpu = get_cpu(); vcpu_time = &hv_clock[cpu].pvti; pvclock_read_wallclock(&wall_clock, vcpu_time, now); - preempt_enable(); + put_cpu(); } static int kvm_set_wallclock(const struct timespec *now) @@ -107,11 +106,10 @@ static unsigned long kvm_get_tsc_khz(void) int cpu; unsigned long tsc_khz; - preempt_disable(); - cpu = smp_processor_id(); + cpu = get_cpu(); src = &hv_clock[cpu].pvti; tsc_khz = pvclock_tsc_khz(src); - preempt_enable(); + put_cpu(); return tsc_khz; } @@ -263,7 +261,6 @@ void __init kvmclock_init(void) #endif kvm_get_preset_lpj(); clocksource_register_hz(&kvm_clock, NSEC_PER_SEC); - pv_info.paravirt_enabled = 1; pv_info.name = "KVM"; if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT)) @@ -284,23 +281,22 @@ int __init kvm_setup_vsyscall_timeinfo(void) size = PAGE_ALIGN(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS); - preempt_disable(); - cpu = smp_processor_id(); + cpu = get_cpu(); vcpu_time = &hv_clock[cpu].pvti; flags = pvclock_read_flags(vcpu_time); if (!(flags & PVCLOCK_TSC_STABLE_BIT)) { - preempt_enable(); + put_cpu(); return 1; } if ((ret = pvclock_init_vsyscall(hv_clock, size))) { - preempt_enable(); + put_cpu(); return ret; } - preempt_enable(); + put_cpu(); kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK; #endif diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index 1667b1de8d5d..469b23d6acc2 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -20,6 +20,7 @@ #include <asm/tlbflush.h> #include <asm/mmu_context.h> #include <asm/apic.h> +#include <asm/io_apic.h> #include <asm/cpufeature.h> #include <asm/desc.h> #include <asm/cacheflush.h> @@ -247,7 +248,8 @@ void machine_kexec(struct kimage *image) /* now call it */ image->start = relocate_kernel_ptr((unsigned long)image->head, (unsigned long)page_list, - image->start, cpu_has_pae, + image->start, + boot_cpu_has(X86_FEATURE_PAE), image->preserve_context); #ifdef CONFIG_KEXEC_JUMP diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 485981059a40..415480d3ea84 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -22,6 +22,7 @@ #include <asm/pgtable.h> #include <asm/tlbflush.h> #include <asm/mmu_context.h> +#include <asm/io_apic.h> #include <asm/debugreg.h> #include <asm/kexec-bzimage64.h> diff --git a/arch/x86/kernel/mcount_64.S b/arch/x86/kernel/mcount_64.S index c73aecf10d34..94ea120fa21f 100644 --- a/arch/x86/kernel/mcount_64.S +++ b/arch/x86/kernel/mcount_64.S @@ -21,40 +21,159 @@ # define function_hook mcount #endif +/* All cases save the original rbp (8 bytes) */ +#ifdef CONFIG_FRAME_POINTER +# ifdef CC_USING_FENTRY +/* Save parent and function stack frames (rip and rbp) */ +# define MCOUNT_FRAME_SIZE (8+16*2) +# else +/* Save just function stack frame (rip and rbp) */ +# define MCOUNT_FRAME_SIZE (8+16) +# endif +#else +/* No need to save a stack frame */ +# define MCOUNT_FRAME_SIZE 8 +#endif /* CONFIG_FRAME_POINTER */ + +/* Size of stack used to save mcount regs in save_mcount_regs */ +#define MCOUNT_REG_SIZE (SS+8 + MCOUNT_FRAME_SIZE) + +/* + * gcc -pg option adds a call to 'mcount' in most functions. + * When -mfentry is used, the call is to 'fentry' and not 'mcount' + * and is done before the function's stack frame is set up. + * They both require a set of regs to be saved before calling + * any C code and restored before returning back to the function. + * + * On boot up, all these calls are converted into nops. When tracing + * is enabled, the call can jump to either ftrace_caller or + * ftrace_regs_caller. Callbacks (tracing functions) that require + * ftrace_regs_caller (like kprobes) need to have pt_regs passed to + * it. For this reason, the size of the pt_regs structure will be + * allocated on the stack and the required mcount registers will + * be saved in the locations that pt_regs has them in. + */ + +/* + * @added: the amount of stack added before calling this + * + * After this is called, the following registers contain: + * + * %rdi - holds the address that called the trampoline + * %rsi - holds the parent function (traced function's return address) + * %rdx - holds the original %rbp + */ +.macro save_mcount_regs added=0 + + /* Always save the original rbp */ + pushq %rbp + +#ifdef CONFIG_FRAME_POINTER + /* + * Stack traces will stop at the ftrace trampoline if the frame pointer + * is not set up properly. If fentry is used, we need to save a frame + * pointer for the parent as well as the function traced, because the + * fentry is called before the stack frame is set up, where as mcount + * is called afterward. + */ +#ifdef CC_USING_FENTRY + /* Save the parent pointer (skip orig rbp and our return address) */ + pushq \added+8*2(%rsp) + pushq %rbp + movq %rsp, %rbp + /* Save the return address (now skip orig rbp, rbp and parent) */ + pushq \added+8*3(%rsp) +#else + /* Can't assume that rip is before this (unless added was zero) */ + pushq \added+8(%rsp) +#endif + pushq %rbp + movq %rsp, %rbp +#endif /* CONFIG_FRAME_POINTER */ + + /* + * We add enough stack to save all regs. + */ + subq $(MCOUNT_REG_SIZE - MCOUNT_FRAME_SIZE), %rsp + movq %rax, RAX(%rsp) + movq %rcx, RCX(%rsp) + movq %rdx, RDX(%rsp) + movq %rsi, RSI(%rsp) + movq %rdi, RDI(%rsp) + movq %r8, R8(%rsp) + movq %r9, R9(%rsp) + /* + * Save the original RBP. Even though the mcount ABI does not + * require this, it helps out callers. + */ + movq MCOUNT_REG_SIZE-8(%rsp), %rdx + movq %rdx, RBP(%rsp) + + /* Copy the parent address into %rsi (second parameter) */ +#ifdef CC_USING_FENTRY + movq MCOUNT_REG_SIZE+8+\added(%rsp), %rsi +#else + /* %rdx contains original %rbp */ + movq 8(%rdx), %rsi +#endif + + /* Move RIP to its proper location */ + movq MCOUNT_REG_SIZE+\added(%rsp), %rdi + movq %rdi, RIP(%rsp) + + /* + * Now %rdi (the first parameter) has the return address of + * where ftrace_call returns. But the callbacks expect the + * address of the call itself. + */ + subq $MCOUNT_INSN_SIZE, %rdi + .endm + +.macro restore_mcount_regs + movq R9(%rsp), %r9 + movq R8(%rsp), %r8 + movq RDI(%rsp), %rdi + movq RSI(%rsp), %rsi + movq RDX(%rsp), %rdx + movq RCX(%rsp), %rcx + movq RAX(%rsp), %rax + + /* ftrace_regs_caller can modify %rbp */ + movq RBP(%rsp), %rbp + + addq $MCOUNT_REG_SIZE, %rsp + + .endm + #ifdef CONFIG_DYNAMIC_FTRACE ENTRY(function_hook) retq END(function_hook) -/* skip is set if stack has been adjusted */ -.macro ftrace_caller_setup skip=0 - MCOUNT_SAVE_FRAME \skip +ENTRY(ftrace_caller) + /* save_mcount_regs fills in first two parameters */ + save_mcount_regs +GLOBAL(ftrace_caller_op_ptr) /* Load the ftrace_ops into the 3rd parameter */ movq function_trace_op(%rip), %rdx - /* Load ip into the first parameter */ - movq RIP(%rsp), %rdi - subq $MCOUNT_INSN_SIZE, %rdi - /* Load the parent_ip into the second parameter */ -#ifdef CC_USING_FENTRY - movq SS+16(%rsp), %rsi -#else - movq 8(%rbp), %rsi -#endif -.endm - -ENTRY(ftrace_caller) - ftrace_caller_setup /* regs go into 4th parameter (but make it NULL) */ movq $0, %rcx GLOBAL(ftrace_call) call ftrace_stub - MCOUNT_RESTORE_FRAME -ftrace_return: + restore_mcount_regs + + /* + * The copied trampoline must call ftrace_return as it + * still may need to call the function graph tracer. + */ +GLOBAL(ftrace_caller_end) + +GLOBAL(ftrace_return) #ifdef CONFIG_FUNCTION_GRAPH_TRACER GLOBAL(ftrace_graph_call) @@ -66,11 +185,16 @@ GLOBAL(ftrace_stub) END(ftrace_caller) ENTRY(ftrace_regs_caller) - /* Save the current flags before compare (in SS location)*/ + /* Save the current flags before any operations that can change them */ pushfq - /* skip=8 to skip flags saved in SS */ - ftrace_caller_setup 8 + /* added 8 bytes to save flags */ + save_mcount_regs 8 + /* save_mcount_regs fills in first two parameters */ + +GLOBAL(ftrace_regs_caller_op_ptr) + /* Load the ftrace_ops into the 3rd parameter */ + movq function_trace_op(%rip), %rdx /* Save the rest of pt_regs */ movq %r15, R15(%rsp) @@ -79,18 +203,17 @@ ENTRY(ftrace_regs_caller) movq %r12, R12(%rsp) movq %r11, R11(%rsp) movq %r10, R10(%rsp) - movq %rbp, RBP(%rsp) movq %rbx, RBX(%rsp) /* Copy saved flags */ - movq SS(%rsp), %rcx + movq MCOUNT_REG_SIZE(%rsp), %rcx movq %rcx, EFLAGS(%rsp) /* Kernel segments */ movq $__KERNEL_DS, %rcx movq %rcx, SS(%rsp) movq $__KERNEL_CS, %rcx movq %rcx, CS(%rsp) - /* Stack - skipping return address */ - leaq SS+16(%rsp), %rcx + /* Stack - skipping return address and flags */ + leaq MCOUNT_REG_SIZE+8*2(%rsp), %rcx movq %rcx, RSP(%rsp) /* regs go into 4th parameter */ @@ -101,11 +224,11 @@ GLOBAL(ftrace_regs_call) /* Copy flags back to SS, to restore them */ movq EFLAGS(%rsp), %rax - movq %rax, SS(%rsp) + movq %rax, MCOUNT_REG_SIZE(%rsp) /* Handlers can change the RIP */ movq RIP(%rsp), %rax - movq %rax, SS+8(%rsp) + movq %rax, MCOUNT_REG_SIZE+8(%rsp) /* restore the rest of pt_regs */ movq R15(%rsp), %r15 @@ -113,19 +236,22 @@ GLOBAL(ftrace_regs_call) movq R13(%rsp), %r13 movq R12(%rsp), %r12 movq R10(%rsp), %r10 - movq RBP(%rsp), %rbp movq RBX(%rsp), %rbx - /* skip=8 to skip flags saved in SS */ - MCOUNT_RESTORE_FRAME 8 + restore_mcount_regs /* Restore flags */ popfq - jmp ftrace_return + /* + * As this jmp to ftrace_return can be a short jump + * it must not be copied into the trampoline. + * The trampoline will add the code to jump + * to the return. + */ +GLOBAL(ftrace_regs_caller_end) - popfq - jmp ftrace_stub + jmp ftrace_return END(ftrace_regs_caller) @@ -136,6 +262,7 @@ ENTRY(function_hook) cmpq $ftrace_stub, ftrace_trace_function jnz trace +fgraph_trace: #ifdef CONFIG_FUNCTION_GRAPH_TRACER cmpq $ftrace_stub, ftrace_graph_return jnz ftrace_graph_caller @@ -148,42 +275,35 @@ GLOBAL(ftrace_stub) retq trace: - MCOUNT_SAVE_FRAME - - movq RIP(%rsp), %rdi -#ifdef CC_USING_FENTRY - movq SS+16(%rsp), %rsi -#else - movq 8(%rbp), %rsi -#endif - subq $MCOUNT_INSN_SIZE, %rdi + /* save_mcount_regs fills in first two parameters */ + save_mcount_regs call *ftrace_trace_function - MCOUNT_RESTORE_FRAME + restore_mcount_regs - jmp ftrace_stub + jmp fgraph_trace END(function_hook) #endif /* CONFIG_DYNAMIC_FTRACE */ #endif /* CONFIG_FUNCTION_TRACER */ #ifdef CONFIG_FUNCTION_GRAPH_TRACER ENTRY(ftrace_graph_caller) - MCOUNT_SAVE_FRAME + /* Saves rbp into %rdx and fills first parameter */ + save_mcount_regs #ifdef CC_USING_FENTRY - leaq SS+16(%rsp), %rdi + leaq MCOUNT_REG_SIZE+8(%rsp), %rsi movq $0, %rdx /* No framepointers needed */ #else - leaq 8(%rbp), %rdi - movq (%rbp), %rdx + /* Save address of the return address of traced function */ + leaq 8(%rdx), %rsi + /* ftrace does sanity checks against frame pointers */ + movq (%rdx), %rdx #endif - movq RIP(%rsp), %rsi - subq $MCOUNT_INSN_SIZE, %rsi - call prepare_ftrace_return - MCOUNT_RESTORE_FRAME + restore_mcount_regs retq END(ftrace_graph_caller) diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index c9603ac80de5..113e70784854 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -22,6 +22,8 @@ * an SMP box will direct the access to CPU %d. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/types.h> @@ -50,11 +52,11 @@ static loff_t msr_seek(struct file *file, loff_t offset, int orig) mutex_lock(&inode->i_mutex); switch (orig) { - case 0: + case SEEK_SET: file->f_pos = offset; ret = file->f_pos; break; - case 1: + case SEEK_CUR: file->f_pos += offset; ret = file->f_pos; break; @@ -206,7 +208,7 @@ static int msr_device_create(int cpu) dev = device_create(msr_class, NULL, MKDEV(MSR_MAJOR, cpu), NULL, "msr%d", cpu); - return IS_ERR(dev) ? PTR_ERR(dev) : 0; + return PTR_ERR_OR_ZERO(dev); } static void msr_device_destroy(int cpu) @@ -248,8 +250,7 @@ static int __init msr_init(void) i = 0; if (__register_chrdev(MSR_MAJOR, 0, NR_CPUS, "cpu/msr", &msr_fops)) { - printk(KERN_ERR "msr: unable to get major %d for msr\n", - MSR_MAJOR); + pr_err("unable to get major %d for msr\n", MSR_MAJOR); err = -EBUSY; goto out; } diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c index e309cc5c276e..781861cc5ee8 100644 --- a/arch/x86/kernel/perf_regs.c +++ b/arch/x86/kernel/perf_regs.c @@ -78,6 +78,14 @@ u64 perf_reg_abi(struct task_struct *task) { return PERF_SAMPLE_REGS_ABI_32; } + +void perf_get_regs_user(struct perf_regs *regs_user, + struct pt_regs *regs, + struct pt_regs *regs_user_copy) +{ + regs_user->regs = task_pt_regs(current); + regs_user->abi = perf_reg_abi(current); +} #else /* CONFIG_X86_64 */ #define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \ (1ULL << PERF_REG_X86_ES) | \ @@ -102,4 +110,86 @@ u64 perf_reg_abi(struct task_struct *task) else return PERF_SAMPLE_REGS_ABI_64; } + +void perf_get_regs_user(struct perf_regs *regs_user, + struct pt_regs *regs, + struct pt_regs *regs_user_copy) +{ + struct pt_regs *user_regs = task_pt_regs(current); + + /* + * If we're in an NMI that interrupted task_pt_regs setup, then + * we can't sample user regs at all. This check isn't really + * sufficient, though, as we could be in an NMI inside an interrupt + * that happened during task_pt_regs setup. + */ + if (regs->sp > (unsigned long)&user_regs->r11 && + regs->sp <= (unsigned long)(user_regs + 1)) { + regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE; + regs_user->regs = NULL; + return; + } + + /* + * RIP, flags, and the argument registers are usually saved. + * orig_ax is probably okay, too. + */ + regs_user_copy->ip = user_regs->ip; + regs_user_copy->cx = user_regs->cx; + regs_user_copy->dx = user_regs->dx; + regs_user_copy->si = user_regs->si; + regs_user_copy->di = user_regs->di; + regs_user_copy->r8 = user_regs->r8; + regs_user_copy->r9 = user_regs->r9; + regs_user_copy->r10 = user_regs->r10; + regs_user_copy->r11 = user_regs->r11; + regs_user_copy->orig_ax = user_regs->orig_ax; + regs_user_copy->flags = user_regs->flags; + + /* + * Don't even try to report the "rest" regs. + */ + regs_user_copy->bx = -1; + regs_user_copy->bp = -1; + regs_user_copy->r12 = -1; + regs_user_copy->r13 = -1; + regs_user_copy->r14 = -1; + regs_user_copy->r15 = -1; + + /* + * For this to be at all useful, we need a reasonable guess for + * sp and the ABI. Be careful: we're in NMI context, and we're + * considering current to be the current task, so we should + * be careful not to look at any other percpu variables that might + * change during context switches. + */ + if (IS_ENABLED(CONFIG_IA32_EMULATION) && + task_thread_info(current)->status & TS_COMPAT) { + /* Easy case: we're in a compat syscall. */ + regs_user->abi = PERF_SAMPLE_REGS_ABI_32; + regs_user_copy->sp = user_regs->sp; + regs_user_copy->cs = user_regs->cs; + regs_user_copy->ss = user_regs->ss; + } else if (user_regs->orig_ax != -1) { + /* + * We're probably in a 64-bit syscall. + * Warning: this code is severely racy. At least it's better + * than just blindly copying user_regs. + */ + regs_user->abi = PERF_SAMPLE_REGS_ABI_64; + regs_user_copy->sp = this_cpu_read(old_rsp); + regs_user_copy->cs = __USER_CS; + regs_user_copy->ss = __USER_DS; + regs_user_copy->cx = -1; /* usually contains garbage */ + } else { + /* We're probably in an interrupt or exception. */ + regs_user->abi = user_64bit_mode(user_regs) ? + PERF_SAMPLE_REGS_ABI_64 : PERF_SAMPLE_REGS_ABI_32; + regs_user_copy->sp = user_regs->sp; + regs_user_copy->cs = user_regs->cs; + regs_user_copy->ss = user_regs->ss; + } + + regs_user->regs = regs_user_copy; +} #endif /* CONFIG_X86_32 */ diff --git a/arch/x86/kernel/pmc_atom.c b/arch/x86/kernel/pmc_atom.c index 0c424a67985d..0ee5025e0fa4 100644 --- a/arch/x86/kernel/pmc_atom.c +++ b/arch/x86/kernel/pmc_atom.c @@ -235,6 +235,11 @@ err: pmc_dbgfs_unregister(pmc); return -ENODEV; } +#else +static int pmc_dbgfs_register(struct pmc_dev *pmc, struct pci_dev *pdev) +{ + return 0; +} #endif /* CONFIG_DEBUG_FS */ static int pmc_setup_dev(struct pci_dev *pdev) @@ -262,14 +267,12 @@ static int pmc_setup_dev(struct pci_dev *pdev) /* PMC hardware registers setup */ pmc_hw_reg_setup(pmc); -#ifdef CONFIG_DEBUG_FS ret = pmc_dbgfs_register(pmc, pdev); if (ret) { iounmap(pmc->regmap); - return ret; } -#endif /* CONFIG_DEBUG_FS */ - return 0; + + return ret; } /* diff --git a/arch/x86/kernel/preempt.S b/arch/x86/kernel/preempt.S deleted file mode 100644 index ca7f0d58a87d..000000000000 --- a/arch/x86/kernel/preempt.S +++ /dev/null @@ -1,25 +0,0 @@ - -#include <linux/linkage.h> -#include <asm/dwarf2.h> -#include <asm/asm.h> -#include <asm/calling.h> - -ENTRY(___preempt_schedule) - CFI_STARTPROC - SAVE_ALL - call preempt_schedule - RESTORE_ALL - ret - CFI_ENDPROC - -#ifdef CONFIG_CONTEXT_TRACKING - -ENTRY(___preempt_schedule_context) - CFI_STARTPROC - SAVE_ALL - call preempt_schedule_context - RESTORE_ALL - ret - CFI_ENDPROC - -#endif diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index f804dc935d2a..e127ddaa2d5a 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -64,14 +64,16 @@ EXPORT_SYMBOL_GPL(task_xstate_cachep); */ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { - int ret; - *dst = *src; - if (fpu_allocated(&src->thread.fpu)) { - memset(&dst->thread.fpu, 0, sizeof(dst->thread.fpu)); - ret = fpu_alloc(&dst->thread.fpu); - if (ret) - return ret; + + dst->thread.fpu_counter = 0; + dst->thread.fpu.has_fpu = 0; + dst->thread.fpu.last_cpu = ~0; + dst->thread.fpu.state = NULL; + if (tsk_used_math(src)) { + int err = fpu_alloc(&dst->thread.fpu); + if (err) + return err; fpu_copy(dst, src); } return 0; diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 7bc86bbe7485..8f3ebfe710d0 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -138,6 +138,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, p->thread.sp = (unsigned long) childregs; p->thread.sp0 = (unsigned long) (childregs+1); + memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); if (unlikely(p->flags & PF_KTHREAD)) { /* kernel thread */ @@ -152,9 +153,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, childregs->orig_ax = -1; childregs->cs = __KERNEL_CS | get_kernel_rpl(); childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_FIXED; - p->thread.fpu_counter = 0; p->thread.io_bitmap_ptr = NULL; - memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); return 0; } *childregs = *current_pt_regs(); @@ -165,13 +164,10 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, p->thread.ip = (unsigned long) ret_from_fork; task_user_gs(p) = get_user_gs(current_pt_regs()); - p->thread.fpu_counter = 0; p->thread.io_bitmap_ptr = NULL; tsk = current; err = -ENOMEM; - memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); - if (unlikely(test_tsk_thread_flag(tsk, TIF_IO_BITMAP))) { p->thread.io_bitmap_ptr = kmemdup(tsk->thread.io_bitmap_ptr, IO_BITMAP_BYTES, GFP_KERNEL); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index ca5b02d405c3..5a2c02913af3 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -163,7 +163,6 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, p->thread.sp = (unsigned long) childregs; p->thread.usersp = me->thread.usersp; set_tsk_thread_flag(p, TIF_FORK); - p->thread.fpu_counter = 0; p->thread.io_bitmap_ptr = NULL; savesegment(gs, p->thread.gsindex); @@ -193,8 +192,6 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, childregs->sp = sp; err = -ENOMEM; - memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); - if (unlikely(test_tsk_thread_flag(me, TIF_IO_BITMAP))) { p->thread.io_bitmap_ptr = kmemdup(me->thread.io_bitmap_ptr, IO_BITMAP_BYTES, GFP_KERNEL); @@ -286,24 +283,9 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) fpu = switch_fpu_prepare(prev_p, next_p, cpu); - /* - * Reload esp0, LDT and the page table pointer: - */ + /* Reload esp0 and ss1. */ load_sp0(tss, next); - /* - * Switch DS and ES. - * This won't pick up thread selector changes, but I guess that is ok. - */ - savesegment(es, prev->es); - if (unlikely(next->es | prev->es)) - loadsegment(es, next->es); - - savesegment(ds, prev->ds); - if (unlikely(next->ds | prev->ds)) - loadsegment(ds, next->ds); - - /* We must save %fs and %gs before load_TLS() because * %fs and %gs may be cleared by load_TLS(). * @@ -312,41 +294,101 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) savesegment(fs, fsindex); savesegment(gs, gsindex); + /* + * Load TLS before restoring any segments so that segment loads + * reference the correct GDT entries. + */ load_TLS(next, cpu); /* - * Leave lazy mode, flushing any hypercalls made here. - * This must be done before restoring TLS segments so - * the GDT and LDT are properly updated, and must be - * done before math_state_restore, so the TS bit is up - * to date. + * Leave lazy mode, flushing any hypercalls made here. This + * must be done after loading TLS entries in the GDT but before + * loading segments that might reference them, and and it must + * be done before math_state_restore, so the TS bit is up to + * date. */ arch_end_context_switch(next_p); + /* Switch DS and ES. + * + * Reading them only returns the selectors, but writing them (if + * nonzero) loads the full descriptor from the GDT or LDT. The + * LDT for next is loaded in switch_mm, and the GDT is loaded + * above. + * + * We therefore need to write new values to the segment + * registers on every context switch unless both the new and old + * values are zero. + * + * Note that we don't need to do anything for CS and SS, as + * those are saved and restored as part of pt_regs. + */ + savesegment(es, prev->es); + if (unlikely(next->es | prev->es)) + loadsegment(es, next->es); + + savesegment(ds, prev->ds); + if (unlikely(next->ds | prev->ds)) + loadsegment(ds, next->ds); + /* * Switch FS and GS. * - * Segment register != 0 always requires a reload. Also - * reload when it has changed. When prev process used 64bit - * base always reload to avoid an information leak. + * These are even more complicated than FS and GS: they have + * 64-bit bases are that controlled by arch_prctl. Those bases + * only differ from the values in the GDT or LDT if the selector + * is 0. + * + * Loading the segment register resets the hidden base part of + * the register to 0 or the value from the GDT / LDT. If the + * next base address zero, writing 0 to the segment register is + * much faster than using wrmsr to explicitly zero the base. + * + * The thread_struct.fs and thread_struct.gs values are 0 + * if the fs and gs bases respectively are not overridden + * from the values implied by fsindex and gsindex. They + * are nonzero, and store the nonzero base addresses, if + * the bases are overridden. + * + * (fs != 0 && fsindex != 0) || (gs != 0 && gsindex != 0) should + * be impossible. + * + * Therefore we need to reload the segment registers if either + * the old or new selector is nonzero, and we need to override + * the base address if next thread expects it to be overridden. + * + * This code is unnecessarily slow in the case where the old and + * new indexes are zero and the new base is nonzero -- it will + * unnecessarily write 0 to the selector before writing the new + * base address. + * + * Note: This all depends on arch_prctl being the only way that + * user code can override the segment base. Once wrfsbase and + * wrgsbase are enabled, most of this code will need to change. */ if (unlikely(fsindex | next->fsindex | prev->fs)) { loadsegment(fs, next->fsindex); + /* - * Check if the user used a selector != 0; if yes - * clear 64bit base, since overloaded base is always - * mapped to the Null selector + * If user code wrote a nonzero value to FS, then it also + * cleared the overridden base address. + * + * XXX: if user code wrote 0 to FS and cleared the base + * address itself, we won't notice and we'll incorrectly + * restore the prior base address next time we reschdule + * the process. */ if (fsindex) prev->fs = 0; } - /* when next process has a 64bit base use it */ if (next->fs) wrmsrl(MSR_FS_BASE, next->fs); prev->fsindex = fsindex; if (unlikely(gsindex | next->gsindex | prev->gs)) { load_gs_index(next->gsindex); + + /* This works (and fails) the same way as fsindex above. */ if (gsindex) prev->gs = 0; } diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 678c0ada3b3c..e510618b2e91 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -1441,24 +1441,126 @@ void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, force_sig_info(SIGTRAP, &info, tsk); } - -#ifdef CONFIG_X86_32 -# define IS_IA32 1 -#elif defined CONFIG_IA32_EMULATION -# define IS_IA32 is_compat_task() -#else -# define IS_IA32 0 +static void do_audit_syscall_entry(struct pt_regs *regs, u32 arch) +{ +#ifdef CONFIG_X86_64 + if (arch == AUDIT_ARCH_X86_64) { + audit_syscall_entry(regs->orig_ax, regs->di, + regs->si, regs->dx, regs->r10); + } else #endif + { + audit_syscall_entry(regs->orig_ax, regs->bx, + regs->cx, regs->dx, regs->si); + } +} /* - * We must return the syscall number to actually look up in the table. - * This can be -1L to skip running any syscall at all. + * We can return 0 to resume the syscall or anything else to go to phase + * 2. If we resume the syscall, we need to put something appropriate in + * regs->orig_ax. + * + * NB: We don't have full pt_regs here, but regs->orig_ax and regs->ax + * are fully functional. + * + * For phase 2's benefit, our return value is: + * 0: resume the syscall + * 1: go to phase 2; no seccomp phase 2 needed + * anything else: go to phase 2; pass return value to seccomp */ -long syscall_trace_enter(struct pt_regs *regs) +unsigned long syscall_trace_enter_phase1(struct pt_regs *regs, u32 arch) +{ + unsigned long ret = 0; + u32 work; + + BUG_ON(regs != task_pt_regs(current)); + + work = ACCESS_ONCE(current_thread_info()->flags) & + _TIF_WORK_SYSCALL_ENTRY; + + /* + * If TIF_NOHZ is set, we are required to call user_exit() before + * doing anything that could touch RCU. + */ + if (work & _TIF_NOHZ) { + user_exit(); + work &= ~_TIF_NOHZ; + } + +#ifdef CONFIG_SECCOMP + /* + * Do seccomp first -- it should minimize exposure of other + * code, and keeping seccomp fast is probably more valuable + * than the rest of this. + */ + if (work & _TIF_SECCOMP) { + struct seccomp_data sd; + + sd.arch = arch; + sd.nr = regs->orig_ax; + sd.instruction_pointer = regs->ip; +#ifdef CONFIG_X86_64 + if (arch == AUDIT_ARCH_X86_64) { + sd.args[0] = regs->di; + sd.args[1] = regs->si; + sd.args[2] = regs->dx; + sd.args[3] = regs->r10; + sd.args[4] = regs->r8; + sd.args[5] = regs->r9; + } else +#endif + { + sd.args[0] = regs->bx; + sd.args[1] = regs->cx; + sd.args[2] = regs->dx; + sd.args[3] = regs->si; + sd.args[4] = regs->di; + sd.args[5] = regs->bp; + } + + BUILD_BUG_ON(SECCOMP_PHASE1_OK != 0); + BUILD_BUG_ON(SECCOMP_PHASE1_SKIP != 1); + + ret = seccomp_phase1(&sd); + if (ret == SECCOMP_PHASE1_SKIP) { + regs->orig_ax = -1; + ret = 0; + } else if (ret != SECCOMP_PHASE1_OK) { + return ret; /* Go directly to phase 2 */ + } + + work &= ~_TIF_SECCOMP; + } +#endif + + /* Do our best to finish without phase 2. */ + if (work == 0) + return ret; /* seccomp and/or nohz only (ret == 0 here) */ + +#ifdef CONFIG_AUDITSYSCALL + if (work == _TIF_SYSCALL_AUDIT) { + /* + * If there is no more work to be done except auditing, + * then audit in phase 1. Phase 2 always audits, so, if + * we audit here, then we can't go on to phase 2. + */ + do_audit_syscall_entry(regs, arch); + return 0; + } +#endif + + return 1; /* Something is enabled that we can't handle in phase 1 */ +} + +/* Returns the syscall nr to run (which should match regs->orig_ax). */ +long syscall_trace_enter_phase2(struct pt_regs *regs, u32 arch, + unsigned long phase1_result) { long ret = 0; + u32 work = ACCESS_ONCE(current_thread_info()->flags) & + _TIF_WORK_SYSCALL_ENTRY; - user_exit(); + BUG_ON(regs != task_pt_regs(current)); /* * If we stepped into a sysenter/syscall insn, it trapped in @@ -1467,17 +1569,21 @@ long syscall_trace_enter(struct pt_regs *regs) * do_debug() and we need to set it again to restore the user * state. If we entered on the slow path, TF was already set. */ - if (test_thread_flag(TIF_SINGLESTEP)) + if (work & _TIF_SINGLESTEP) regs->flags |= X86_EFLAGS_TF; - /* do the secure computing check first */ - if (secure_computing(regs->orig_ax)) { +#ifdef CONFIG_SECCOMP + /* + * Call seccomp_phase2 before running the other hooks so that + * they can see any changes made by a seccomp tracer. + */ + if (phase1_result > 1 && seccomp_phase2(phase1_result)) { /* seccomp failures shouldn't expose any additional code. */ - ret = -1L; - goto out; + return -1; } +#endif - if (unlikely(test_thread_flag(TIF_SYSCALL_EMU))) + if (unlikely(work & _TIF_SYSCALL_EMU)) ret = -1L; if ((ret || test_thread_flag(TIF_SYSCALL_TRACE)) && @@ -1487,23 +1593,22 @@ long syscall_trace_enter(struct pt_regs *regs) if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) trace_sys_enter(regs, regs->orig_ax); - if (IS_IA32) - audit_syscall_entry(AUDIT_ARCH_I386, - regs->orig_ax, - regs->bx, regs->cx, - regs->dx, regs->si); -#ifdef CONFIG_X86_64 - else - audit_syscall_entry(AUDIT_ARCH_X86_64, - regs->orig_ax, - regs->di, regs->si, - regs->dx, regs->r10); -#endif + do_audit_syscall_entry(regs, arch); -out: return ret ?: regs->orig_ax; } +long syscall_trace_enter(struct pt_regs *regs) +{ + u32 arch = is_ia32_task() ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64; + unsigned long phase1_result = syscall_trace_enter_phase1(regs, arch); + + if (phase1_result == 0) + return regs->orig_ax; + else + return syscall_trace_enter_phase2(regs, arch, phase1_result); +} + void syscall_trace_leave(struct pt_regs *regs) { bool step; diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index ff898bbf579d..176a0f99d4da 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -498,6 +498,24 @@ void force_hpet_resume(void) } /* + * According to the datasheet e6xx systems have the HPET hardwired to + * 0xfed00000 + */ +static void e6xx_force_enable_hpet(struct pci_dev *dev) +{ + if (hpet_address || force_hpet_address) + return; + + force_hpet_address = 0xFED00000; + force_hpet_resume_type = NONE_FORCE_HPET_RESUME; + dev_printk(KERN_DEBUG, &dev->dev, "Force enabled HPET at " + "0x%lx\n", force_hpet_address); + return; +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_E6XX_CU, + e6xx_force_enable_hpet); + +/* * HPET MSI on some boards (ATI SB700/SB800) has side effect on * floppy DMA. Disable HPET MSI on such platforms. * See erratum #27 (Misinterpreted MSI Requests May Result in diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 17962e667a91..bae6c609888e 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -12,6 +12,7 @@ #include <acpi/reboot.h> #include <asm/io.h> #include <asm/apic.h> +#include <asm/io_apic.h> #include <asm/desc.h> #include <asm/hpet.h> #include <asm/pgtable.h> diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 41ead8d3bc0b..ab4734e5411d 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -879,6 +879,15 @@ void __init setup_arch(char **cmdline_p) KERNEL_PGD_PTRS); load_cr3(swapper_pg_dir); + /* + * Note: Quark X1000 CPUs advertise PGE incorrectly and require + * a cr3 based tlb flush, so the following __flush_tlb_all() + * will not flush anything because the cpu quirk which clears + * X86_FEATURE_PGE has not been invoked yet. Though due to the + * load_cr3() above the TLB has been flushed already. The + * quirk is invoked before subsequent calls to __flush_tlb_all() + * so proper operation is guaranteed. + */ __flush_tlb_all(); #else printk(KERN_INFO "Command line: %s\n", boot_command_line); @@ -951,6 +960,8 @@ void __init setup_arch(char **cmdline_p) init_mm.end_data = (unsigned long) _edata; init_mm.brk = _brk_end; + mpx_mm_init(&init_mm); + code_resource.start = __pa_symbol(_text); code_resource.end = __pa_symbol(_etext)-1; data_resource.start = __pa_symbol(_etext); @@ -1119,7 +1130,6 @@ void __init setup_arch(char **cmdline_p) setup_real_mode(); memblock_set_current_limit(get_max_mapped()); - dma_contiguous_reserve(max_pfn_mapped << PAGE_SHIFT); /* * NOTE: On x86-32, only from this point on, fixmaps are ready for use. @@ -1150,6 +1160,7 @@ void __init setup_arch(char **cmdline_p) early_acpi_boot_init(); initmem_init(); + dma_contiguous_reserve(max_pfn_mapped << PAGE_SHIFT); /* * Reserve memory for crash kernel after SRAT is parsed so that it @@ -1181,9 +1192,7 @@ void __init setup_arch(char **cmdline_p) tboot_probe(); -#ifdef CONFIG_X86_64 map_vsyscall(); -#endif generic_apic_probe(); diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 5cdff0357746..e4fcb87ba7a6 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -30,7 +30,7 @@ EXPORT_PER_CPU_SYMBOL(cpu_number); #define BOOT_PERCPU_OFFSET 0 #endif -DEFINE_PER_CPU(unsigned long, this_cpu_off) = BOOT_PERCPU_OFFSET; +DEFINE_PER_CPU_READ_MOSTLY(unsigned long, this_cpu_off) = BOOT_PERCPU_OFFSET; EXPORT_PER_CPU_SYMBOL(this_cpu_off); unsigned long __per_cpu_offset[NR_CPUS] __read_mostly = { diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 2851d63c1202..ed37a768d0fc 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -675,6 +675,11 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) * handler too. */ regs->flags &= ~(X86_EFLAGS_DF|X86_EFLAGS_RF|X86_EFLAGS_TF); + /* + * Ensure the signal handler starts with the new fpu state. + */ + if (used_math()) + drop_init_fpu(current); } signal_setup_done(failed, ksig, test_thread_flag(TIF_SINGLESTEP)); } diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 42a2dca984b3..6d7022c683e3 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -99,7 +99,7 @@ EXPORT_PER_CPU_SYMBOL(cpu_core_map); DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map); /* Per CPU bogomips and other parameters */ -DEFINE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info); +DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info); EXPORT_PER_CPU_SYMBOL(cpu_info); atomic_t init_deasserted; @@ -111,7 +111,6 @@ atomic_t init_deasserted; static void smp_callin(void) { int cpuid, phys_id; - unsigned long timeout; /* * If waken up by an INIT in an 82489DX configuration @@ -130,37 +129,6 @@ static void smp_callin(void) * (This works even if the APIC is not enabled.) */ phys_id = read_apic_id(); - if (cpumask_test_cpu(cpuid, cpu_callin_mask)) { - panic("%s: phys CPU#%d, CPU#%d already present??\n", __func__, - phys_id, cpuid); - } - pr_debug("CPU#%d (phys ID: %d) waiting for CALLOUT\n", cpuid, phys_id); - - /* - * STARTUP IPIs are fragile beasts as they might sometimes - * trigger some glue motherboard logic. Complete APIC bus - * silence for 1 second, this overestimates the time the - * boot CPU is spending to send the up to 2 STARTUP IPIs - * by a factor of two. This should be enough. - */ - - /* - * Waiting 2s total for startup (udelay is not yet working) - */ - timeout = jiffies + 2*HZ; - while (time_before(jiffies, timeout)) { - /* - * Has the boot CPU finished it's STARTUP sequence? - */ - if (cpumask_test_cpu(cpuid, cpu_callout_mask)) - break; - cpu_relax(); - } - - if (!time_before(jiffies, timeout)) { - panic("%s: CPU%d started up but did not get a callout!\n", - __func__, cpuid); - } /* * the boot CPU has finished the init stage and is spinning @@ -296,11 +264,19 @@ void smp_store_cpu_info(int id) } static bool +topology_same_node(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) +{ + int cpu1 = c->cpu_index, cpu2 = o->cpu_index; + + return (cpu_to_node(cpu1) == cpu_to_node(cpu2)); +} + +static bool topology_sane(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o, const char *name) { int cpu1 = c->cpu_index, cpu2 = o->cpu_index; - return !WARN_ONCE(cpu_to_node(cpu1) != cpu_to_node(cpu2), + return !WARN_ONCE(!topology_same_node(c, o), "sched: CPU #%d's %s-sibling CPU #%d is not on the same node! " "[node: %d != %d]. Ignoring dependency.\n", cpu1, name, cpu2, cpu_to_node(cpu1), cpu_to_node(cpu2)); @@ -341,17 +317,44 @@ static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) return false; } -static bool match_mc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) +/* + * Unlike the other levels, we do not enforce keeping a + * multicore group inside a NUMA node. If this happens, we will + * discard the MC level of the topology later. + */ +static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) { - if (c->phys_proc_id == o->phys_proc_id) { - if (cpu_has(c, X86_FEATURE_AMD_DCM)) - return true; - - return topology_sane(c, o, "mc"); - } + if (c->phys_proc_id == o->phys_proc_id) + return true; return false; } +static struct sched_domain_topology_level numa_inside_package_topology[] = { +#ifdef CONFIG_SCHED_SMT + { cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) }, +#endif +#ifdef CONFIG_SCHED_MC + { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) }, +#endif + { NULL, }, +}; +/* + * set_sched_topology() sets the topology internal to a CPU. The + * NUMA topologies are layered on top of it to build the full + * system topology. + * + * If NUMA nodes are observed to occur within a CPU package, this + * function should be called. It forces the sched domain code to + * only use the SMT level for the CPU portion of the topology. + * This essentially falls back to relying on NUMA information + * from the SRAT table to describe the entire system topology + * (except for hyperthreads). + */ +static void primarily_use_numa_for_topology(void) +{ + set_sched_topology(numa_inside_package_topology); +} + void set_cpu_sibling_map(int cpu) { bool has_smt = smp_num_siblings > 1; @@ -388,7 +391,7 @@ void set_cpu_sibling_map(int cpu) for_each_cpu(i, cpu_sibling_setup_mask) { o = &cpu_data(i); - if ((i == cpu) || (has_mp && match_mc(c, o))) { + if ((i == cpu) || (has_mp && match_die(c, o))) { link_mask(core, cpu, i); /* @@ -410,6 +413,8 @@ void set_cpu_sibling_map(int cpu) } else if (i != cpu && !c->booted_cores) c->booted_cores = cpu_data(i).booted_cores; } + if (match_die(c, o) && !topology_same_node(c, o)) + primarily_use_numa_for_topology(); } } @@ -753,8 +758,8 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) unsigned long start_ip = real_mode_header->trampoline_start; unsigned long boot_error = 0; - int timeout; int cpu0_nmi_registered = 0; + unsigned long timeout; /* Just in case we booted with a single CPU. */ alternatives_enable_smp(); @@ -802,6 +807,15 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) } /* + * AP might wait on cpu_callout_mask in cpu_init() with + * cpu_initialized_mask set if previous attempt to online + * it timed-out. Clear cpu_initialized_mask so that after + * INIT/SIPI it could start with a clean state. + */ + cpumask_clear_cpu(cpu, cpu_initialized_mask); + smp_mb(); + + /* * Wake up a CPU in difference cases: * - Use the method in the APIC driver if it's defined * Otherwise, @@ -815,53 +829,38 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) if (!boot_error) { /* - * allow APs to start initializing. + * Wait 10s total for a response from AP */ - pr_debug("Before Callout %d\n", cpu); - cpumask_set_cpu(cpu, cpu_callout_mask); - pr_debug("After Callout %d\n", cpu); + boot_error = -1; + timeout = jiffies + 10*HZ; + while (time_before(jiffies, timeout)) { + if (cpumask_test_cpu(cpu, cpu_initialized_mask)) { + /* + * Tell AP to proceed with initialization + */ + cpumask_set_cpu(cpu, cpu_callout_mask); + boot_error = 0; + break; + } + udelay(100); + schedule(); + } + } + if (!boot_error) { /* - * Wait 5s total for a response + * Wait till AP completes initial initialization */ - for (timeout = 0; timeout < 50000; timeout++) { - if (cpumask_test_cpu(cpu, cpu_callin_mask)) - break; /* It has booted */ - udelay(100); + while (!cpumask_test_cpu(cpu, cpu_callin_mask)) { /* * Allow other tasks to run while we wait for the * AP to come online. This also gives a chance * for the MTRR work(triggered by the AP coming online) * to be completed in the stop machine context. */ + udelay(100); schedule(); } - - if (cpumask_test_cpu(cpu, cpu_callin_mask)) { - print_cpu_msr(&cpu_data(cpu)); - pr_debug("CPU%d: has booted.\n", cpu); - } else { - boot_error = 1; - if (*trampoline_status == 0xA5A5A5A5) - /* trampoline started but...? */ - pr_err("CPU%d: Stuck ??\n", cpu); - else - /* trampoline code not run */ - pr_err("CPU%d: Not responding\n", cpu); - if (apic->inquire_remote_apic) - apic->inquire_remote_apic(apicid); - } - } - - if (boot_error) { - /* Try to put things back the way they were before ... */ - numa_remove_cpu(cpu); /* was set by numa_add_cpu */ - - /* was set by do_boot_cpu() */ - cpumask_clear_cpu(cpu, cpu_callout_mask); - - /* was set by cpu_init() */ - cpumask_clear_cpu(cpu, cpu_initialized_mask); } /* mark "stuck" area as not stuck */ @@ -1085,7 +1084,6 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) { unsigned int i; - preempt_disable(); smp_cpu_index_default(); /* @@ -1103,22 +1101,19 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) } set_cpu_sibling_map(0); - if (smp_sanity_check(max_cpus) < 0) { pr_info("SMP disabled\n"); disable_smp(); - goto out; + return; } default_setup_apic_routing(); - preempt_disable(); if (read_apic_id() != boot_cpu_physical_apicid) { panic("Boot APIC ID in local APIC unexpected (%d vs %d)", read_apic_id(), boot_cpu_physical_apicid); /* Or can we switch back to PIC here? */ } - preempt_enable(); connect_bsp_APIC(); @@ -1152,8 +1147,6 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) uv_system_init(); set_mtrr_aps_delayed_init(); -out: - preempt_enable(); } void arch_enable_nonboot_cpus_begin(void) @@ -1304,10 +1297,14 @@ static void __ref remove_cpu_from_maps(int cpu) numa_remove_cpu(cpu); } +static DEFINE_PER_CPU(struct completion, die_complete); + void cpu_disable_common(void) { int cpu = smp_processor_id(); + init_completion(&per_cpu(die_complete, smp_processor_id())); + remove_siblinginfo(cpu); /* It's now safe to remove this processor from the online map */ @@ -1326,26 +1323,29 @@ int native_cpu_disable(void) return ret; clear_local_APIC(); - cpu_disable_common(); + return 0; } +void cpu_die_common(unsigned int cpu) +{ + wait_for_completion_timeout(&per_cpu(die_complete, cpu), HZ); +} + void native_cpu_die(unsigned int cpu) { /* We don't do anything here: idle task is faking death itself. */ - unsigned int i; - for (i = 0; i < 10; i++) { - /* They ack this in play_dead by setting CPU_DEAD */ - if (per_cpu(cpu_state, cpu) == CPU_DEAD) { - if (system_state == SYSTEM_RUNNING) - pr_info("CPU %u is now offline\n", cpu); - return; - } - msleep(100); + cpu_die_common(cpu); + + /* They ack this in play_dead() by setting CPU_DEAD */ + if (per_cpu(cpu_state, cpu) == CPU_DEAD) { + if (system_state == SYSTEM_RUNNING) + pr_info("CPU %u is now offline\n", cpu); + } else { + pr_err("CPU %u didn't die...\n", cpu); } - pr_err("CPU %u didn't die...\n", cpu); } void play_dead_common(void) @@ -1357,6 +1357,7 @@ void play_dead_common(void) mb(); /* Ack it */ __this_cpu_write(cpu_state, CPU_DEAD); + complete(&per_cpu(die_complete, smp_processor_id())); /* * With physical CPU hotplug, we should halt the cpu diff --git a/arch/x86/kernel/sysfb.c b/arch/x86/kernel/sysfb.c index 193ec2ce46c7..160386e9fc17 100644 --- a/arch/x86/kernel/sysfb.c +++ b/arch/x86/kernel/sysfb.c @@ -67,7 +67,7 @@ static __init int sysfb_init(void) pd = platform_device_register_resndata(NULL, name, 0, NULL, 0, si, sizeof(*si)); - return IS_ERR(pd) ? PTR_ERR(pd) : 0; + return PTR_ERR_OR_ZERO(pd); } /* must execute after PCI subsystem for EFI quirks */ diff --git a/arch/x86/kernel/sysfb_simplefb.c b/arch/x86/kernel/sysfb_simplefb.c index 86179d409893..764a29f84de7 100644 --- a/arch/x86/kernel/sysfb_simplefb.c +++ b/arch/x86/kernel/sysfb_simplefb.c @@ -88,8 +88,5 @@ __init int create_simplefb(const struct screen_info *si, pd = platform_device_register_resndata(NULL, "simple-framebuffer", 0, &res, 1, mode, sizeof(*mode)); - if (IS_ERR(pd)) - return PTR_ERR(pd); - - return 0; + return PTR_ERR_OR_ZERO(pd); } diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c index 0fa29609b2c4..25adc0e16eaa 100644 --- a/arch/x86/kernel/time.c +++ b/arch/x86/kernel/time.c @@ -23,7 +23,7 @@ #include <asm/time.h> #ifdef CONFIG_X86_64 -__visible DEFINE_VVAR(volatile unsigned long, jiffies) = INITIAL_JIFFIES; +__visible volatile unsigned long jiffies __cacheline_aligned = INITIAL_JIFFIES; #endif unsigned long profile_pc(struct pt_regs *regs) diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c index f7fec09e3e3a..4e942f31b1a7 100644 --- a/arch/x86/kernel/tls.c +++ b/arch/x86/kernel/tls.c @@ -27,6 +27,37 @@ static int get_free_idx(void) return -ESRCH; } +static bool tls_desc_okay(const struct user_desc *info) +{ + if (LDT_empty(info)) + return true; + + /* + * espfix is required for 16-bit data segments, but espfix + * only works for LDT segments. + */ + if (!info->seg_32bit) + return false; + + /* Only allow data segments in the TLS array. */ + if (info->contents > 1) + return false; + + /* + * Non-present segments with DPL 3 present an interesting attack + * surface. The kernel should handle such segments correctly, + * but TLS is very difficult to protect in a sandbox, so prevent + * such segments from being created. + * + * If userspace needs to remove a TLS entry, it can still delete + * it outright. + */ + if (info->seg_not_present) + return false; + + return true; +} + static void set_tls_desc(struct task_struct *p, int idx, const struct user_desc *info, int n) { @@ -66,6 +97,9 @@ int do_set_thread_area(struct task_struct *p, int idx, if (copy_from_user(&info, u_info, sizeof(info))) return -EFAULT; + if (!tls_desc_okay(&info)) + return -EINVAL; + if (idx == -1) idx = info.entry_number; @@ -192,6 +226,7 @@ int regset_tls_set(struct task_struct *target, const struct user_regset *regset, { struct user_desc infobuf[GDT_ENTRY_TLS_ENTRIES]; const struct user_desc *info; + int i; if (pos >= GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) || (pos % sizeof(struct user_desc)) != 0 || @@ -205,6 +240,10 @@ int regset_tls_set(struct task_struct *target, const struct user_regset *regset, else info = infobuf; + for (i = 0; i < count / sizeof(struct user_desc); i++) + if (!tls_desc_okay(info + i)) + return -EINVAL; + set_tls_desc(target, GDT_ENTRY_TLS_MIN + (pos / sizeof(struct user_desc)), info, count / sizeof(struct user_desc)); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 0d0e922fafc1..88900e288021 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -60,6 +60,7 @@ #include <asm/fixmap.h> #include <asm/mach_traps.h> #include <asm/alternative.h> +#include <asm/mpx.h> #ifdef CONFIG_X86_64 #include <asm/x86_init.h> @@ -228,37 +229,44 @@ dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \ DO_ERROR(X86_TRAP_DE, SIGFPE, "divide error", divide_error) DO_ERROR(X86_TRAP_OF, SIGSEGV, "overflow", overflow) -DO_ERROR(X86_TRAP_BR, SIGSEGV, "bounds", bounds) DO_ERROR(X86_TRAP_UD, SIGILL, "invalid opcode", invalid_op) 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) -#endif DO_ERROR(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check) #ifdef CONFIG_X86_64 /* Runs on IST stack */ -dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code) -{ - enum ctx_state prev_state; - - prev_state = exception_enter(); - if (notify_die(DIE_TRAP, "stack segment", regs, error_code, - X86_TRAP_SS, SIGBUS) != NOTIFY_STOP) { - preempt_conditional_sti(regs); - do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL); - preempt_conditional_cli(regs); - } - exception_exit(prev_state); -} - dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) { static const char str[] = "double fault"; struct task_struct *tsk = current; +#ifdef CONFIG_X86_ESPFIX64 + extern unsigned char native_irq_return_iret[]; + + /* + * If IRET takes a non-IST fault on the espfix64 stack, then we + * end up promoting it to a doublefault. In that case, modify + * the stack to make it look like we just entered the #GP + * handler from user space, similar to bad_iret. + */ + if (((long)regs->sp >> PGDIR_SHIFT) == ESPFIX_PGD_ENTRY && + regs->cs == __KERNEL_CS && + regs->ip == (unsigned long)native_irq_return_iret) + { + struct pt_regs *normal_regs = task_pt_regs(current); + + /* Fake a #GP(0) from userspace. */ + memmove(&normal_regs->ip, (void *)regs->sp, 5*8); + normal_regs->orig_ax = 0; /* Missing (lost) #GP error code */ + regs->ip = (unsigned long)general_protection; + regs->sp = (unsigned long)&normal_regs->orig_ax; + return; + } +#endif + exception_enter(); /* Return not checked because double check cannot be ignored */ notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV); @@ -278,6 +286,89 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) } #endif +dotraplinkage void do_bounds(struct pt_regs *regs, long error_code) +{ + struct task_struct *tsk = current; + struct xsave_struct *xsave_buf; + enum ctx_state prev_state; + struct bndcsr *bndcsr; + siginfo_t *info; + + prev_state = exception_enter(); + if (notify_die(DIE_TRAP, "bounds", regs, error_code, + X86_TRAP_BR, SIGSEGV) == NOTIFY_STOP) + goto exit; + conditional_sti(regs); + + if (!user_mode(regs)) + die("bounds", regs, error_code); + + if (!cpu_feature_enabled(X86_FEATURE_MPX)) { + /* The exception is not from Intel MPX */ + goto exit_trap; + } + + /* + * We need to look at BNDSTATUS to resolve this exception. + * It is not directly accessible, though, so we need to + * do an xsave and then pull it out of the xsave buffer. + */ + fpu_save_init(&tsk->thread.fpu); + xsave_buf = &(tsk->thread.fpu.state->xsave); + bndcsr = get_xsave_addr(xsave_buf, XSTATE_BNDCSR); + if (!bndcsr) + goto exit_trap; + + /* + * The error code field of the BNDSTATUS register communicates status + * information of a bound range exception #BR or operation involving + * bound directory. + */ + switch (bndcsr->bndstatus & MPX_BNDSTA_ERROR_CODE) { + case 2: /* Bound directory has invalid entry. */ + if (mpx_handle_bd_fault(xsave_buf)) + goto exit_trap; + break; /* Success, it was handled */ + case 1: /* Bound violation. */ + info = mpx_generate_siginfo(regs, xsave_buf); + if (IS_ERR(info)) { + /* + * We failed to decode the MPX instruction. Act as if + * the exception was not caused by MPX. + */ + goto exit_trap; + } + /* + * Success, we decoded the instruction and retrieved + * an 'info' containing the address being accessed + * which caused the exception. This information + * allows and application to possibly handle the + * #BR exception itself. + */ + do_trap(X86_TRAP_BR, SIGSEGV, "bounds", regs, error_code, info); + kfree(info); + break; + case 0: /* No exception caused by Intel MPX operations. */ + goto exit_trap; + default: + die("bounds", regs, error_code); + } + +exit: + exception_exit(prev_state); + return; +exit_trap: + /* + * This path out is for all the cases where we could not + * handle the exception in some way (like allocating a + * table or telling userspace about it. We will also end + * up here if the kernel has MPX turned off at compile + * time.. + */ + do_trap(X86_TRAP_BR, SIGSEGV, "bounds", regs, error_code, NULL); + exception_exit(prev_state); +} + dotraplinkage void do_general_protection(struct pt_regs *regs, long error_code) { @@ -379,7 +470,7 @@ NOKPROBE_SYMBOL(do_int3); * for scheduling or signal handling. The actual stack switch is done in * entry.S */ -asmlinkage __visible struct pt_regs *sync_regs(struct pt_regs *eregs) +asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs) { struct pt_regs *regs = eregs; /* Did already sync */ @@ -399,6 +490,36 @@ asmlinkage __visible struct pt_regs *sync_regs(struct pt_regs *eregs) return regs; } NOKPROBE_SYMBOL(sync_regs); + +struct bad_iret_stack { + void *error_entry_ret; + struct pt_regs regs; +}; + +asmlinkage __visible notrace +struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s) +{ + /* + * This is called from entry_64.S early in handling a fault + * caused by a bad iret to user mode. To handle the fault + * correctly, we want move our stack frame to task_pt_regs + * and we want to pretend that the exception came from the + * iret target. + */ + struct bad_iret_stack *new_stack = + container_of(task_pt_regs(current), + struct bad_iret_stack, regs); + + /* Copy the IRET target to the new stack. */ + memmove(&new_stack->regs.ip, (void *)s->regs.sp, 5*8); + + /* Copy the remainder of the stack from the current stack. */ + memmove(new_stack, s, offsetof(struct bad_iret_stack, regs.ip)); + + BUG_ON(!user_mode_vm(&new_stack->regs)); + return new_stack; +} +NOKPROBE_SYMBOL(fixup_bad_iret); #endif /* @@ -778,7 +899,7 @@ void __init trap_init(void) set_intr_gate(X86_TRAP_OLD_MF, coprocessor_segment_overrun); set_intr_gate(X86_TRAP_TS, invalid_TSS); set_intr_gate(X86_TRAP_NP, segment_not_present); - set_intr_gate_ist(X86_TRAP_SS, &stack_segment, STACKFAULT_STACK); + set_intr_gate(X86_TRAP_SS, stack_segment); set_intr_gate(X86_TRAP_GP, general_protection); set_intr_gate(X86_TRAP_SPURIOUS, spurious_interrupt_bug); set_intr_gate(X86_TRAP_MF, coprocessor_error); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index b6025f9e36c6..b7e50bba3bbb 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -1166,14 +1166,17 @@ void __init tsc_init(void) x86_init.timers.tsc_pre_init(); - if (!cpu_has_tsc) + if (!cpu_has_tsc) { + setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); return; + } tsc_khz = x86_platform.calibrate_tsc(); cpu_khz = tsc_khz; if (!tsc_khz) { mark_tsc_unstable("could not calculate TSC khz"); + setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); return; } diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 5d1cbfe4ae58..8b96a947021f 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -219,7 +219,7 @@ static int uprobe_init_insn(struct arch_uprobe *auprobe, struct insn *insn, bool { u32 volatile *good_insns; - insn_init(insn, auprobe->insn, x86_64); + insn_init(insn, auprobe->insn, sizeof(auprobe->insn), x86_64); /* has the side-effect of processing the entire instruction */ insn_get_length(insn); if (WARN_ON_ONCE(!insn_complete(insn))) diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 49edf2dd3613..00bf300fd846 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -186,6 +186,8 @@ SECTIONS * start another segment - init. */ PERCPU_VADDR(INTERNODE_CACHE_BYTES, 0, :percpu) + ASSERT(SIZEOF(.data..percpu) < CONFIG_PHYSICAL_START, + "per-CPU data too large - increase CONFIG_PHYSICAL_START") #endif INIT_TEXT_SECTION(PAGE_SIZE) diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index e1e1e80fc6a6..2dcc6ff6fdcc 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -1,59 +1,43 @@ /* + * Copyright (c) 2012-2014 Andy Lutomirski <luto@amacapital.net> + * + * Based on the original implementation which is: * Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE * Copyright 2003 Andi Kleen, SuSE Labs. * - * [ NOTE: this mechanism is now deprecated in favor of the vDSO. ] + * Parts of the original code have been moved to arch/x86/vdso/vma.c + * + * This file implements vsyscall emulation. vsyscalls are a legacy ABI: + * Userspace can request certain kernel services by calling fixed + * addresses. This concept is problematic: * - * Thanks to hpa@transmeta.com for some useful hint. - * Special thanks to Ingo Molnar for his early experience with - * a different vsyscall implementation for Linux/IA32 and for the name. + * - It interferes with ASLR. + * - It's awkward to write code that lives in kernel addresses but is + * callable by userspace at fixed addresses. + * - The whole concept is impossible for 32-bit compat userspace. + * - UML cannot easily virtualize a vsyscall. * - * vsyscall 1 is located at -10Mbyte, vsyscall 2 is located - * at virtual address -10Mbyte+1024bytes etc... There are at max 4 - * vsyscalls. One vsyscall can reserve more than 1 slot to avoid - * jumping out of line if necessary. We cannot add more with this - * mechanism because older kernels won't return -ENOSYS. + * As of mid-2014, I believe that there is no new userspace code that + * will use a vsyscall if the vDSO is present. I hope that there will + * soon be no new userspace code that will ever use a vsyscall. * - * Note: the concept clashes with user mode linux. UML users should - * use the vDSO. + * The code in this file emulates vsyscalls when notified of a page + * fault to a vsyscall address. */ -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include <linux/time.h> -#include <linux/init.h> #include <linux/kernel.h> #include <linux/timer.h> -#include <linux/seqlock.h> -#include <linux/jiffies.h> -#include <linux/sysctl.h> -#include <linux/topology.h> -#include <linux/timekeeper_internal.h> -#include <linux/getcpu.h> -#include <linux/cpu.h> -#include <linux/smp.h> -#include <linux/notifier.h> #include <linux/syscalls.h> #include <linux/ratelimit.h> #include <asm/vsyscall.h> -#include <asm/pgtable.h> -#include <asm/compat.h> -#include <asm/page.h> #include <asm/unistd.h> #include <asm/fixmap.h> -#include <asm/errno.h> -#include <asm/io.h> -#include <asm/segment.h> -#include <asm/desc.h> -#include <asm/topology.h> #include <asm/traps.h> #define CREATE_TRACE_POINTS #include "vsyscall_trace.h" -DEFINE_VVAR(int, vgetcpu_mode); - static enum { EMULATE, NATIVE, NONE } vsyscall_mode = EMULATE; static int __init vsyscall_setup(char *str) @@ -216,12 +200,13 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) */ regs->orig_ax = syscall_nr; regs->ax = -ENOSYS; - tmp = secure_computing(syscall_nr); + tmp = secure_computing(); if ((!tmp && regs->orig_ax != syscall_nr) || regs->ip != address) { warn_bad_vsyscall(KERN_DEBUG, regs, "seccomp tried to change syscall nr or ip"); do_exit(SIGSYS); } + regs->orig_ax = -1; if (tmp) goto do_ret; /* skip requested */ @@ -284,46 +269,54 @@ sigsegv: } /* - * Assume __initcall executes before all user space. Hopefully kmod - * doesn't violate that. We'll find out if it does. + * A pseudo VMA to allow ptrace access for the vsyscall page. This only + * covers the 64bit vsyscall page now. 32bit has a real VMA now and does + * not need special handling anymore: */ -static void vsyscall_set_cpu(int cpu) +static const char *gate_vma_name(struct vm_area_struct *vma) { - unsigned long d; - unsigned long node = 0; -#ifdef CONFIG_NUMA - node = cpu_to_node(cpu); -#endif - if (cpu_has(&cpu_data(cpu), X86_FEATURE_RDTSCP)) - write_rdtscp_aux((node << 12) | cpu); - - /* - * Store cpu number in limit so that it can be loaded quickly - * in user space in vgetcpu. (12 bits for the CPU and 8 bits for the node) - */ - d = 0x0f40000000000ULL; - d |= cpu; - d |= (node & 0xf) << 12; - d |= (node >> 4) << 48; - - write_gdt_entry(get_cpu_gdt_table(cpu), GDT_ENTRY_PER_CPU, &d, DESCTYPE_S); + return "[vsyscall]"; } - -static void cpu_vsyscall_init(void *arg) +static struct vm_operations_struct gate_vma_ops = { + .name = gate_vma_name, +}; +static struct vm_area_struct gate_vma = { + .vm_start = VSYSCALL_ADDR, + .vm_end = VSYSCALL_ADDR + PAGE_SIZE, + .vm_page_prot = PAGE_READONLY_EXEC, + .vm_flags = VM_READ | VM_EXEC, + .vm_ops = &gate_vma_ops, +}; + +struct vm_area_struct *get_gate_vma(struct mm_struct *mm) { - /* preemption should be already off */ - vsyscall_set_cpu(raw_smp_processor_id()); +#ifdef CONFIG_IA32_EMULATION + if (!mm || mm->context.ia32_compat) + return NULL; +#endif + if (vsyscall_mode == NONE) + return NULL; + return &gate_vma; } -static int -cpu_vsyscall_notifier(struct notifier_block *n, unsigned long action, void *arg) +int in_gate_area(struct mm_struct *mm, unsigned long addr) { - long cpu = (long)arg; + struct vm_area_struct *vma = get_gate_vma(mm); + + if (!vma) + return 0; - if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN) - smp_call_function_single(cpu, cpu_vsyscall_init, NULL, 1); + return (addr >= vma->vm_start) && (addr < vma->vm_end); +} - return NOTIFY_DONE; +/* + * Use this when you have no reliable mm, typically from interrupt + * context. It is less reliable than using a task's mm and may give + * false positives. + */ +int in_gate_area_no_mm(unsigned long addr) +{ + return vsyscall_mode != NONE && (addr & PAGE_MASK) == VSYSCALL_ADDR; } void __init map_vsyscall(void) @@ -331,24 +324,12 @@ void __init map_vsyscall(void) extern char __vsyscall_page; unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page); - __set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall, - vsyscall_mode == NATIVE - ? PAGE_KERNEL_VSYSCALL - : PAGE_KERNEL_VVAR); + if (vsyscall_mode != NONE) + __set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall, + vsyscall_mode == NATIVE + ? PAGE_KERNEL_VSYSCALL + : PAGE_KERNEL_VVAR); + BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) != (unsigned long)VSYSCALL_ADDR); } - -static int __init vsyscall_init(void) -{ - cpu_notifier_register_begin(); - - on_each_cpu(cpu_vsyscall_init, NULL, 1); - /* notifier priority > KVM */ - __hotcpu_notifier(cpu_vsyscall_notifier, 30); - - cpu_notifier_register_done(); - - return 0; -} -__initcall(vsyscall_init); diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index e48b674639cc..234b0722de53 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -116,8 +116,6 @@ struct x86_msi_ops x86_msi = { .teardown_msi_irqs = default_teardown_msi_irqs, .restore_msi_irqs = default_restore_msi_irqs, .setup_hpet_msi = default_setup_hpet_msi, - .msi_mask_irq = default_msi_mask_irq, - .msix_mask_irq = default_msix_mask_irq, }; /* MSI arch specific hooks */ @@ -140,14 +138,6 @@ void arch_restore_msi_irqs(struct pci_dev *dev) { x86_msi.restore_msi_irqs(dev); } -u32 arch_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) -{ - return x86_msi.msi_mask_irq(desc, mask, flag); -} -u32 arch_msix_mask_irq(struct msi_desc *desc, u32 flag) -{ - return x86_msi.msix_mask_irq(desc, flag); -} #endif struct x86_io_apic_ops x86_io_apic_ops = { diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index 940b142cc11f..0de1fae2bdf0 100644 --- a/arch/x86/kernel/xsave.c +++ b/arch/x86/kernel/xsave.c @@ -271,8 +271,6 @@ int save_xstate_sig(void __user *buf, void __user *buf_fx, int size) if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate)) return -1; - drop_init_fpu(tsk); /* trigger finit */ - return 0; } @@ -402,8 +400,11 @@ int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size) set_used_math(); } - if (use_eager_fpu()) + if (use_eager_fpu()) { + preempt_disable(); math_state_restore(); + preempt_enable(); + } return err; } else { @@ -737,3 +738,4 @@ void *get_xsave_addr(struct xsave_struct *xsave, int xstate) return (void *)xsave + xstate_comp_offsets[feature]; } +EXPORT_SYMBOL_GPL(get_xsave_addr); |
