diff options
Diffstat (limited to 'arch/x86/kernel')
54 files changed, 1196 insertions, 784 deletions
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 1dac94265b59..8e61d23b8f64 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -53,10 +53,6 @@ EXPORT_SYMBOL(acpi_disabled); # include <asm/proto.h> #endif /* X86 */ -#define BAD_MADT_ENTRY(entry, end) ( \ - (!entry) || (unsigned long)entry + sizeof(*entry) > end || \ - ((struct acpi_subtable_header *)entry)->length < sizeof(*entry)) - #define PREFIX "ACPI: " int acpi_noirq; /* skip ACPI IRQ initialization */ @@ -613,10 +609,10 @@ static void acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) int nid; nid = acpi_get_node(handle); - if (nid == -1 || !node_online(nid)) - return; - set_apicid_to_node(physid, nid); - numa_set_node(cpu, nid); + if (nid != -1) { + set_apicid_to_node(physid, nid); + numa_set_node(cpu, nid); + } #endif } diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 6523534671b6..f04dbb3069b8 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -181,7 +181,7 @@ int amd_get_subcaches(int cpu) return (mask >> (4 * cuid)) & 0xf; } -int amd_set_subcaches(int cpu, int mask) +int amd_set_subcaches(int cpu, unsigned long mask) { static unsigned int reset, ban; struct amd_northbridge *nb = node_to_amd_nb(amd_get_nb_id(cpu)); diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index fd972a3e4cbb..9fa8aa051f54 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -18,7 +18,6 @@ #include <linux/pci_ids.h> #include <linux/pci.h> #include <linux/bitops.h> -#include <linux/ioport.h> #include <linux/suspend.h> #include <asm/e820.h> #include <asm/io.h> @@ -54,18 +53,6 @@ int fallback_aper_force __initdata; int fix_aperture __initdata = 1; -static struct resource gart_resource = { - .name = "GART", - .flags = IORESOURCE_MEM, -}; - -static void __init insert_aperture_resource(u32 aper_base, u32 aper_size) -{ - gart_resource.start = aper_base; - gart_resource.end = aper_base + aper_size - 1; - insert_resource(&iomem_resource, &gart_resource); -} - /* This code runs before the PCI subsystem is initialized, so just access the northbridge directly. */ @@ -96,7 +83,6 @@ static u32 __init allocate_aperture(void) memblock_reserve(addr, aper_size); printk(KERN_INFO "Mapping aperture over %d KB of RAM @ %lx\n", aper_size >> 10, addr); - insert_aperture_resource((u32)addr, aper_size); register_nosave_region(addr >> PAGE_SHIFT, (addr+aper_size) >> PAGE_SHIFT); @@ -444,12 +430,8 @@ int __init gart_iommu_hole_init(void) out: if (!fix && !fallback_aper_force) { - if (last_aper_base) { - unsigned long n = (32 * 1024 * 1024) << last_aper_order; - - insert_aperture_resource((u32)last_aper_base, n); + if (last_aper_base) return 1; - } return 0; } diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 7f26c9a70a9e..53e20531470e 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -133,6 +133,10 @@ static inline void imcr_apic_to_pic(void) * +1=force-enable */ static int force_enable_local_apic __initdata; + +/* Control whether x2APIC mode is enabled or not */ +static bool nox2apic __initdata; + /* * APIC command line parameters */ @@ -162,8 +166,7 @@ int x2apic_mode; /* x2apic enabled before OS handover */ int x2apic_preenabled; static int x2apic_disabled; -static int nox2apic; -static __init int setup_nox2apic(char *str) +static int __init setup_nox2apic(char *str) { if (x2apic_enabled()) { int apicid = native_apic_msr_read(APIC_ID); @@ -178,7 +181,7 @@ static __init int setup_nox2apic(char *str) } else setup_clear_cpu_cap(X86_FEATURE_X2APIC); - nox2apic = 1; + nox2apic = true; return 0; } @@ -283,8 +286,12 @@ u32 native_safe_apic_wait_icr_idle(void) void native_apic_icr_write(u32 low, u32 id) { + unsigned long flags; + + local_irq_save(flags); apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(id)); apic_write(APIC_ICR, low); + local_irq_restore(flags); } u64 native_apic_icr_read(void) diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index 2c621a6b901a..7c1b29479513 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -198,7 +198,7 @@ static struct apic apic_flat = { .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, - .wait_for_init_deassert = NULL, + .wait_for_init_deassert = false, .smp_callin_clear_local_apic = NULL, .inquire_remote_apic = default_inquire_remote_apic, @@ -314,7 +314,7 @@ static struct apic apic_physflat = { .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, - .wait_for_init_deassert = NULL, + .wait_for_init_deassert = false, .smp_callin_clear_local_apic = NULL, .inquire_remote_apic = default_inquire_remote_apic, diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index 191ce75c0e54..8c7c98249c20 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -172,8 +172,7 @@ struct apic apic_noop = { .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, - .wait_for_init_deassert = NULL, - + .wait_for_init_deassert = false, .smp_callin_clear_local_apic = NULL, .inquire_remote_apic = NULL, diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index 3e67f9e3d7ef..a5b45df8bc88 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -248,7 +248,7 @@ static const struct apic apic_numachip __refconst = { .wakeup_secondary_cpu = numachip_wakeup_secondary, .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, - .wait_for_init_deassert = NULL, + .wait_for_init_deassert = false, .smp_callin_clear_local_apic = NULL, .inquire_remote_apic = NULL, /* REMRD not supported */ diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c index d50e3640d5ae..e4840aa7a255 100644 --- a/arch/x86/kernel/apic/bigsmp_32.c +++ b/arch/x86/kernel/apic/bigsmp_32.c @@ -199,8 +199,7 @@ static struct apic apic_bigsmp = { .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, - .wait_for_init_deassert = default_wait_for_init_deassert, - + .wait_for_init_deassert = true, .smp_callin_clear_local_apic = NULL, .inquire_remote_apic = default_inquire_remote_apic, diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c index c55224731b2d..6f8f8b348a39 100644 --- a/arch/x86/kernel/apic/es7000_32.c +++ b/arch/x86/kernel/apic/es7000_32.c @@ -394,12 +394,6 @@ static void es7000_enable_apic_mode(void) WARN(1, "Command failed, status = %x\n", mip_status); } -static void es7000_wait_for_init_deassert(atomic_t *deassert) -{ - while (!atomic_read(deassert)) - cpu_relax(); -} - static unsigned int es7000_get_apic_id(unsigned long x) { return (x >> 24) & 0xFF; @@ -658,8 +652,7 @@ static struct apic __refdata apic_es7000_cluster = { .trampoline_phys_low = 0x467, .trampoline_phys_high = 0x469, - .wait_for_init_deassert = NULL, - + .wait_for_init_deassert = false, /* Nothing to do for most platforms, since cleared by the INIT cycle: */ .smp_callin_clear_local_apic = NULL, .inquire_remote_apic = default_inquire_remote_apic, @@ -722,8 +715,7 @@ static struct apic __refdata apic_es7000 = { .trampoline_phys_low = 0x467, .trampoline_phys_high = 0x469, - .wait_for_init_deassert = es7000_wait_for_init_deassert, - + .wait_for_init_deassert = true, /* Nothing to do for most platforms, since cleared by the INIT cycle: */ .smp_callin_clear_local_apic = NULL, .inquire_remote_apic = default_inquire_remote_apic, diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c index 1e42e8f305ee..030ea1c04f72 100644 --- a/arch/x86/kernel/apic/numaq_32.c +++ b/arch/x86/kernel/apic/numaq_32.c @@ -505,8 +505,7 @@ static struct apic __refdata apic_numaq = { .trampoline_phys_high = NUMAQ_TRAMPOLINE_PHYS_HIGH, /* We don't do anything here because we use NMI's to boot instead */ - .wait_for_init_deassert = NULL, - + .wait_for_init_deassert = false, .smp_callin_clear_local_apic = numaq_smp_callin_clear_local_apic, .inquire_remote_apic = NULL, diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index eb35ef9ee63f..cceb352c968c 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -119,8 +119,7 @@ static struct apic apic_default = { .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, - .wait_for_init_deassert = default_wait_for_init_deassert, - + .wait_for_init_deassert = true, .smp_callin_clear_local_apic = NULL, .inquire_remote_apic = default_inquire_remote_apic, diff --git a/arch/x86/kernel/apic/summit_32.c b/arch/x86/kernel/apic/summit_32.c index 00146f9b0254..b656128611cd 100644 --- a/arch/x86/kernel/apic/summit_32.c +++ b/arch/x86/kernel/apic/summit_32.c @@ -532,8 +532,7 @@ static struct apic apic_summit = { .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, - .wait_for_init_deassert = default_wait_for_init_deassert, - + .wait_for_init_deassert = true, .smp_callin_clear_local_apic = NULL, .inquire_remote_apic = default_inquire_remote_apic, diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index cac85ee6913f..e66766bf1641 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -279,7 +279,7 @@ static struct apic apic_x2apic_cluster = { .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, - .wait_for_init_deassert = NULL, + .wait_for_init_deassert = false, .smp_callin_clear_local_apic = NULL, .inquire_remote_apic = NULL, diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index de231e328cae..6d600ebf6c12 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -133,7 +133,7 @@ static struct apic apic_x2apic_phys = { .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, - .wait_for_init_deassert = NULL, + .wait_for_init_deassert = false, .smp_callin_clear_local_apic = NULL, .inquire_remote_apic = NULL, diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index d263b1307de1..7834389ba5be 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -396,7 +396,7 @@ static struct apic __refdata apic_x2apic_uv_x = { .wakeup_secondary_cpu = uv_wakeup_secondary, .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, - .wait_for_init_deassert = NULL, + .wait_for_init_deassert = false, .smp_callin_clear_local_apic = NULL, .inquire_remote_apic = NULL, diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index d3153e281d72..ce8b8ff0e0ef 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -218,7 +218,7 @@ static void amd_k7_smp_check(struct cpuinfo_x86 *c) */ WARN_ONCE(1, "WARNING: This combination of AMD" " processors is not suitable for SMP.\n"); - add_taint(TAINT_UNSAFE_SMP, LOCKDEP_NOW_UNRELIABLE); + add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_NOW_UNRELIABLE); } static void init_amd_k7(struct cpuinfo_x86 *c) @@ -233,9 +233,7 @@ static void init_amd_k7(struct cpuinfo_x86 *c) if (c->x86_model >= 6 && c->x86_model <= 10) { if (!cpu_has(c, X86_FEATURE_XMM)) { printk(KERN_INFO "Enabling disabled K7/SSE Support.\n"); - rdmsr(MSR_K7_HWCR, l, h); - l &= ~0x00008000; - wrmsr(MSR_K7_HWCR, l, h); + msr_clear_bit(MSR_K7_HWCR, 15); set_cpu_cap(c, X86_FEATURE_XMM); } } @@ -509,14 +507,8 @@ static void early_init_amd(struct cpuinfo_x86 *c) #endif /* F16h erratum 793, CVE-2013-6885 */ - if (c->x86 == 0x16 && c->x86_model <= 0xf) { - u64 val; - - rdmsrl(MSR_AMD64_LS_CFG, val); - if (!(val & BIT(15))) - wrmsrl(MSR_AMD64_LS_CFG, val | BIT(15)); - } - + if (c->x86 == 0x16 && c->x86_model <= 0xf) + msr_set_bit(MSR_AMD64_LS_CFG, 15); } static const int amd_erratum_383[]; @@ -536,11 +528,8 @@ static void init_amd(struct cpuinfo_x86 *c) * Errata 63 for SH-B3 steppings * Errata 122 for all steppings (F+ have it disabled by default) */ - if (c->x86 == 0xf) { - rdmsrl(MSR_K7_HWCR, value); - value |= 1 << 6; - wrmsrl(MSR_K7_HWCR, value); - } + if (c->x86 == 0xf) + msr_set_bit(MSR_K7_HWCR, 6); #endif early_init_amd(c); @@ -623,14 +612,11 @@ static void init_amd(struct cpuinfo_x86 *c) (c->x86_model >= 0x10) && (c->x86_model <= 0x1f) && !cpu_has(c, X86_FEATURE_TOPOEXT)) { - if (!rdmsrl_safe(0xc0011005, &value)) { - value |= 1ULL << 54; - wrmsrl_safe(0xc0011005, value); + if (msr_set_bit(0xc0011005, 54) > 0) { rdmsrl(0xc0011005, value); - if (value & (1ULL << 54)) { + if (value & BIT_64(54)) { set_cpu_cap(c, X86_FEATURE_TOPOEXT); - printk(KERN_INFO FW_INFO "CPU: Re-enabling " - "disabled Topology Extensions Support\n"); + pr_info(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n"); } } } @@ -709,19 +695,12 @@ static void init_amd(struct cpuinfo_x86 *c) * Disable GART TLB Walk Errors on Fam10h. We do this here * because this is always needed when GART is enabled, even in a * kernel which has no MCE support built in. - * BIOS should disable GartTlbWlk Errors themself. If - * it doesn't do it here as suggested by the BKDG. + * BIOS should disable GartTlbWlk Errors already. If + * it doesn't, do it here as suggested by the BKDG. * * Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=33012 */ - u64 mask; - int err; - - err = rdmsrl_safe(MSR_AMD64_MCx_MASK(4), &mask); - if (err == 0) { - mask |= (1 << 10); - wrmsrl_safe(MSR_AMD64_MCx_MASK(4), mask); - } + msr_set_bit(MSR_AMD64_MCx_MASK(4), 10); /* * On family 10h BIOS may not have properly enabled WC+ support, @@ -733,10 +712,7 @@ static void init_amd(struct cpuinfo_x86 *c) * NOTE: we want to use the _safe accessors so as not to #GP kvm * guests on older kvm hosts. */ - - rdmsrl_safe(MSR_AMD64_BU_CFG2, &value); - value &= ~(1ULL << 24); - wrmsrl_safe(MSR_AMD64_BU_CFG2, value); + msr_clear_bit(MSR_AMD64_BU_CFG2, 24); if (cpu_has_amd_erratum(c, amd_erratum_383)) set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH); @@ -767,10 +743,7 @@ static unsigned int amd_size_cache(struct cpuinfo_x86 *c, unsigned int size) static void cpu_set_tlb_flushall_shift(struct cpuinfo_x86 *c) { - tlb_flushall_shift = 5; - - if (c->x86 <= 0x11) - tlb_flushall_shift = 4; + tlb_flushall_shift = 6; } static void cpu_detect_tlb_amd(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index 8779edab684e..d8fba5c15fbd 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -8,236 +8,6 @@ #include "cpu.h" -#ifdef CONFIG_X86_OOSTORE - -static u32 power2(u32 x) -{ - u32 s = 1; - - while (s <= x) - s <<= 1; - - return s >>= 1; -} - - -/* - * Set up an actual MCR - */ -static void centaur_mcr_insert(int reg, u32 base, u32 size, int key) -{ - u32 lo, hi; - - hi = base & ~0xFFF; - lo = ~(size-1); /* Size is a power of 2 so this makes a mask */ - lo &= ~0xFFF; /* Remove the ctrl value bits */ - lo |= key; /* Attribute we wish to set */ - wrmsr(reg+MSR_IDT_MCR0, lo, hi); - mtrr_centaur_report_mcr(reg, lo, hi); /* Tell the mtrr driver */ -} - -/* - * Figure what we can cover with MCR's - * - * Shortcut: We know you can't put 4Gig of RAM on a winchip - */ -static u32 ramtop(void) -{ - u32 clip = 0xFFFFFFFFUL; - u32 top = 0; - int i; - - for (i = 0; i < e820.nr_map; i++) { - unsigned long start, end; - - if (e820.map[i].addr > 0xFFFFFFFFUL) - continue; - /* - * Don't MCR over reserved space. Ignore the ISA hole - * we frob around that catastrophe already - */ - if (e820.map[i].type == E820_RESERVED) { - if (e820.map[i].addr >= 0x100000UL && - e820.map[i].addr < clip) - clip = e820.map[i].addr; - continue; - } - start = e820.map[i].addr; - end = e820.map[i].addr + e820.map[i].size; - if (start >= end) - continue; - if (end > top) - top = end; - } - /* - * Everything below 'top' should be RAM except for the ISA hole. - * Because of the limited MCR's we want to map NV/ACPI into our - * MCR range for gunk in RAM - * - * Clip might cause us to MCR insufficient RAM but that is an - * acceptable failure mode and should only bite obscure boxes with - * a VESA hole at 15Mb - * - * The second case Clip sometimes kicks in is when the EBDA is marked - * as reserved. Again we fail safe with reasonable results - */ - if (top > clip) - top = clip; - - return top; -} - -/* - * Compute a set of MCR's to give maximum coverage - */ -static int centaur_mcr_compute(int nr, int key) -{ - u32 mem = ramtop(); - u32 root = power2(mem); - u32 base = root; - u32 top = root; - u32 floor = 0; - int ct = 0; - - while (ct < nr) { - u32 fspace = 0; - u32 high; - u32 low; - - /* - * Find the largest block we will fill going upwards - */ - high = power2(mem-top); - - /* - * Find the largest block we will fill going downwards - */ - low = base/2; - - /* - * Don't fill below 1Mb going downwards as there - * is an ISA hole in the way. - */ - if (base <= 1024*1024) - low = 0; - - /* - * See how much space we could cover by filling below - * the ISA hole - */ - - if (floor == 0) - fspace = 512*1024; - else if (floor == 512*1024) - fspace = 128*1024; - - /* And forget ROM space */ - - /* - * Now install the largest coverage we get - */ - if (fspace > high && fspace > low) { - centaur_mcr_insert(ct, floor, fspace, key); - floor += fspace; - } else if (high > low) { - centaur_mcr_insert(ct, top, high, key); - top += high; - } else if (low > 0) { - base -= low; - centaur_mcr_insert(ct, base, low, key); - } else - break; - ct++; - } - /* - * We loaded ct values. We now need to set the mask. The caller - * must do this bit. - */ - return ct; -} - -static void centaur_create_optimal_mcr(void) -{ - int used; - int i; - - /* - * Allocate up to 6 mcrs to mark as much of ram as possible - * as write combining and weak write ordered. - * - * To experiment with: Linux never uses stack operations for - * mmio spaces so we could globally enable stack operation wc - * - * Load the registers with type 31 - full write combining, all - * writes weakly ordered. - */ - used = centaur_mcr_compute(6, 31); - - /* - * Wipe unused MCRs - */ - for (i = used; i < 8; i++) - wrmsr(MSR_IDT_MCR0+i, 0, 0); -} - -static void winchip2_create_optimal_mcr(void) -{ - u32 lo, hi; - int used; - int i; - - /* - * Allocate up to 6 mcrs to mark as much of ram as possible - * as write combining, weak store ordered. - * - * Load the registers with type 25 - * 8 - weak write ordering - * 16 - weak read ordering - * 1 - write combining - */ - used = centaur_mcr_compute(6, 25); - - /* - * Mark the registers we are using. - */ - rdmsr(MSR_IDT_MCR_CTRL, lo, hi); - for (i = 0; i < used; i++) - lo |= 1<<(9+i); - wrmsr(MSR_IDT_MCR_CTRL, lo, hi); - - /* - * Wipe unused MCRs - */ - - for (i = used; i < 8; i++) - wrmsr(MSR_IDT_MCR0+i, 0, 0); -} - -/* - * Handle the MCR key on the Winchip 2. - */ -static void winchip2_unprotect_mcr(void) -{ - u32 lo, hi; - u32 key; - - rdmsr(MSR_IDT_MCR_CTRL, lo, hi); - lo &= ~0x1C0; /* blank bits 8-6 */ - key = (lo>>17) & 7; - lo |= key<<6; /* replace with unlock key */ - wrmsr(MSR_IDT_MCR_CTRL, lo, hi); -} - -static void winchip2_protect_mcr(void) -{ - u32 lo, hi; - - rdmsr(MSR_IDT_MCR_CTRL, lo, hi); - lo &= ~0x1C0; /* blank bits 8-6 */ - wrmsr(MSR_IDT_MCR_CTRL, lo, hi); -} -#endif /* CONFIG_X86_OOSTORE */ - #define ACE_PRESENT (1 << 6) #define ACE_ENABLED (1 << 7) #define ACE_FCR (1 << 28) /* MSR_VIA_FCR */ @@ -362,20 +132,6 @@ static void init_centaur(struct cpuinfo_x86 *c) fcr_clr = DPDC; printk(KERN_NOTICE "Disabling bugged TSC.\n"); clear_cpu_cap(c, X86_FEATURE_TSC); -#ifdef CONFIG_X86_OOSTORE - centaur_create_optimal_mcr(); - /* - * Enable: - * write combining on non-stack, non-string - * write combining on string, all types - * weak write ordering - * - * The C6 original lacks weak read order - * - * Note 0x120 is write only on Winchip 1 - */ - wrmsr(MSR_IDT_MCR_CTRL, 0x01F0001F, 0); -#endif break; case 8: switch (c->x86_mask) { @@ -392,40 +148,12 @@ static void init_centaur(struct cpuinfo_x86 *c) fcr_set = ECX8|DSMC|DTLOCK|EMMX|EBRPRED|ERETSTK| E2MMX|EAMD3D; fcr_clr = DPDC; -#ifdef CONFIG_X86_OOSTORE - winchip2_unprotect_mcr(); - winchip2_create_optimal_mcr(); - rdmsr(MSR_IDT_MCR_CTRL, lo, hi); - /* - * Enable: - * write combining on non-stack, non-string - * write combining on string, all types - * weak write ordering - */ - lo |= 31; - wrmsr(MSR_IDT_MCR_CTRL, lo, hi); - winchip2_protect_mcr(); -#endif break; case 9: name = "3"; fcr_set = ECX8|DSMC|DTLOCK|EMMX|EBRPRED|ERETSTK| E2MMX|EAMD3D; fcr_clr = DPDC; -#ifdef CONFIG_X86_OOSTORE - winchip2_unprotect_mcr(); - winchip2_create_optimal_mcr(); - rdmsr(MSR_IDT_MCR_CTRL, lo, hi); - /* - * Enable: - * write combining on non-stack, non-string - * write combining on string, all types - * weak write ordering - */ - lo |= 31; - wrmsr(MSR_IDT_MCR_CTRL, lo, hi); - winchip2_protect_mcr(); -#endif break; default: name = "??"; diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 24b6fd10625a..a135239badb7 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -284,8 +284,13 @@ static __always_inline void setup_smap(struct cpuinfo_x86 *c) raw_local_save_flags(eflags); BUG_ON(eflags & X86_EFLAGS_AC); - if (cpu_has(c, X86_FEATURE_SMAP)) + if (cpu_has(c, X86_FEATURE_SMAP)) { +#ifdef CONFIG_X86_SMAP set_in_cr4(X86_CR4_SMAP); +#else + clear_in_cr4(X86_CR4_SMAP); +#endif + } } /* @@ -1020,7 +1025,8 @@ __setup("show_msr=", setup_show_msr); static __init int setup_noclflush(char *arg) { - setup_clear_cpu_cap(X86_FEATURE_CLFLSH); + setup_clear_cpu_cap(X86_FEATURE_CLFLUSH); + setup_clear_cpu_cap(X86_FEATURE_CLFLUSHOPT); return 1; } __setup("noclflush", setup_noclflush); @@ -1073,6 +1079,10 @@ static __init int setup_disablecpuid(char *arg) } __setup("clearcpuid=", setup_disablecpuid); +DEFINE_PER_CPU(unsigned long, kernel_stack) = + (unsigned long)&init_thread_union - KERNEL_STACK_OFFSET + THREAD_SIZE; +EXPORT_PER_CPU_SYMBOL(kernel_stack); + #ifdef CONFIG_X86_64 struct desc_ptr idt_descr = { NR_VECTORS * 16 - 1, (unsigned long) idt_table }; struct desc_ptr debug_idt_descr = { NR_VECTORS * 16 - 1, @@ -1089,10 +1099,6 @@ DEFINE_PER_CPU(struct task_struct *, current_task) ____cacheline_aligned = &init_task; EXPORT_PER_CPU_SYMBOL(current_task); -DEFINE_PER_CPU(unsigned long, kernel_stack) = - (unsigned long)&init_thread_union - KERNEL_STACK_OFFSET + THREAD_SIZE; -EXPORT_PER_CPU_SYMBOL(kernel_stack); - DEFINE_PER_CPU(char *, irq_stack_ptr) = init_per_cpu_var(irq_stack_union.irq_stack) + IRQ_STACK_SIZE - 64; diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 3db61c644e44..897d6201ef10 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -31,11 +31,8 @@ static void early_init_intel(struct cpuinfo_x86 *c) /* Unmask CPUID levels if masked: */ if (c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xd)) { - rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable); - - if (misc_enable & MSR_IA32_MISC_ENABLE_LIMIT_CPUID) { - misc_enable &= ~MSR_IA32_MISC_ENABLE_LIMIT_CPUID; - wrmsrl(MSR_IA32_MISC_ENABLE, misc_enable); + if (msr_clear_bit(MSR_IA32_MISC_ENABLE, + MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT) > 0) { c->cpuid_level = cpuid_eax(0); get_cpu_cap(c); } @@ -129,16 +126,10 @@ static void early_init_intel(struct cpuinfo_x86 *c) * Ingo Molnar reported a Pentium D (model 6) and a Xeon * (model 2) with the same problem. */ - if (c->x86 == 15) { - rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable); - - if (misc_enable & MSR_IA32_MISC_ENABLE_FAST_STRING) { - printk(KERN_INFO "kmemcheck: Disabling fast string operations\n"); - - misc_enable &= ~MSR_IA32_MISC_ENABLE_FAST_STRING; - wrmsrl(MSR_IA32_MISC_ENABLE, misc_enable); - } - } + if (c->x86 == 15) + if (msr_clear_bit(MSR_IA32_MISC_ENABLE, + MSR_IA32_MISC_ENABLE_FAST_STRING_BIT) > 0) + pr_info("kmemcheck: Disabling fast string operations\n"); #endif /* @@ -195,10 +186,16 @@ static void intel_smp_check(struct cpuinfo_x86 *c) } } -static void intel_workarounds(struct cpuinfo_x86 *c) +static int forcepae; +static int __init forcepae_setup(char *__unused) { - unsigned long lo, hi; + forcepae = 1; + return 1; +} +__setup("forcepae", forcepae_setup); +static void intel_workarounds(struct cpuinfo_x86 *c) +{ #ifdef CONFIG_X86_F00F_BUG /* * All current models of Pentium and Pentium with MMX technology CPUs @@ -225,16 +222,26 @@ static void intel_workarounds(struct cpuinfo_x86 *c) clear_cpu_cap(c, X86_FEATURE_SEP); /* + * PAE CPUID issue: many Pentium M report no PAE but may have a + * functionally usable PAE implementation. + * Forcefully enable PAE if kernel parameter "forcepae" is present. + */ + if (forcepae) { + printk(KERN_WARNING "PAE forced!\n"); + set_cpu_cap(c, X86_FEATURE_PAE); + add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_NOW_UNRELIABLE); + } + + /* * P4 Xeon errata 037 workaround. * Hardware prefetcher may cause stale data to be loaded into the cache. */ if ((c->x86 == 15) && (c->x86_model == 1) && (c->x86_mask == 1)) { - rdmsr(MSR_IA32_MISC_ENABLE, lo, hi); - if ((lo & MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE) == 0) { - printk (KERN_INFO "CPU: C0 stepping P4 Xeon detected.\n"); - printk (KERN_INFO "CPU: Disabling hardware prefetching (Errata 037)\n"); - lo |= MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE; - wrmsr(MSR_IA32_MISC_ENABLE, lo, hi); + if (msr_set_bit(MSR_IA32_MISC_ENABLE, + MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT) + > 0) { + pr_info("CPU: C0 stepping P4 Xeon detected.\n"); + pr_info("CPU: Disabling hardware prefetching (Errata 037)\n"); } } @@ -640,21 +647,17 @@ static void intel_tlb_flushall_shift_set(struct cpuinfo_x86 *c) case 0x61d: /* six-core 45 nm xeon "Dunnington" */ tlb_flushall_shift = -1; break; + case 0x63a: /* Ivybridge */ + tlb_flushall_shift = 2; + break; case 0x61a: /* 45 nm nehalem, "Bloomfield" */ case 0x61e: /* 45 nm nehalem, "Lynnfield" */ case 0x625: /* 32 nm nehalem, "Clarkdale" */ case 0x62c: /* 32 nm nehalem, "Gulftown" */ case 0x62e: /* 45 nm nehalem-ex, "Beckton" */ case 0x62f: /* 32 nm Xeon E7 */ - tlb_flushall_shift = 6; - break; case 0x62a: /* SandyBridge */ case 0x62d: /* SandyBridge, "Romely-EP" */ - tlb_flushall_shift = 5; - break; - case 0x63a: /* Ivybridge */ - tlb_flushall_shift = 1; - break; default: tlb_flushall_shift = 6; } diff --git a/arch/x86/kernel/cpu/microcode/amd_early.c b/arch/x86/kernel/cpu/microcode/amd_early.c index 8384c0fa206f..617a9e284245 100644 --- a/arch/x86/kernel/cpu/microcode/amd_early.c +++ b/arch/x86/kernel/cpu/microcode/amd_early.c @@ -285,6 +285,15 @@ static void __init collect_cpu_sig_on_bsp(void *arg) uci->cpu_sig.sig = cpuid_eax(0x00000001); } + +static void __init get_bsp_sig(void) +{ + unsigned int bsp = boot_cpu_data.cpu_index; + struct ucode_cpu_info *uci = ucode_cpu_info + bsp; + + if (!uci->cpu_sig.sig) + smp_call_function_single(bsp, collect_cpu_sig_on_bsp, NULL, 1); +} #else void load_ucode_amd_ap(void) { @@ -337,31 +346,37 @@ void load_ucode_amd_ap(void) int __init save_microcode_in_initrd_amd(void) { + unsigned long cont; enum ucode_state ret; u32 eax; -#ifdef CONFIG_X86_32 - unsigned int bsp = boot_cpu_data.cpu_index; - struct ucode_cpu_info *uci = ucode_cpu_info + bsp; - - if (!uci->cpu_sig.sig) - smp_call_function_single(bsp, collect_cpu_sig_on_bsp, NULL, 1); + if (!container) + return -EINVAL; +#ifdef CONFIG_X86_32 + get_bsp_sig(); + cont = (unsigned long)container; +#else /* - * Take into account the fact that the ramdisk might get relocated - * and therefore we need to recompute the container's position in - * virtual memory space. + * We need the physical address of the container for both bitness since + * boot_params.hdr.ramdisk_image is a physical address. */ - container = (u8 *)(__va((u32)relocated_ramdisk) + - ((u32)container - boot_params.hdr.ramdisk_image)); + cont = __pa(container); #endif + + /* + * Take into account the fact that the ramdisk might get relocated and + * therefore we need to recompute the container's position in virtual + * memory space. + */ + if (relocated_ramdisk) + container = (u8 *)(__va(relocated_ramdisk) + + (cont - boot_params.hdr.ramdisk_image)); + if (ucode_new_rev) pr_info("microcode: updated early to new patch_level=0x%08x\n", ucode_new_rev); - if (!container) - return -EINVAL; - eax = cpuid_eax(0x00000001); eax = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff); diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 9f7ca266864a..76f98fe5b35c 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -17,6 +17,7 @@ #include <linux/hardirq.h> #include <linux/efi.h> #include <linux/interrupt.h> +#include <linux/irq.h> #include <asm/processor.h> #include <asm/hypervisor.h> #include <asm/hyperv.h> @@ -26,10 +27,50 @@ #include <asm/irq_regs.h> #include <asm/i8259.h> #include <asm/apic.h> +#include <asm/timer.h> struct ms_hyperv_info ms_hyperv; EXPORT_SYMBOL_GPL(ms_hyperv); +#if IS_ENABLED(CONFIG_HYPERV) +static void (*vmbus_handler)(void); + +void hyperv_vector_handler(struct pt_regs *regs) +{ + struct pt_regs *old_regs = set_irq_regs(regs); + + irq_enter(); + exit_idle(); + + inc_irq_stat(irq_hv_callback_count); + if (vmbus_handler) + vmbus_handler(); + + irq_exit(); + set_irq_regs(old_regs); +} + +void hv_setup_vmbus_irq(void (*handler)(void)) +{ + vmbus_handler = handler; + /* + * Setup the IDT for hypervisor callback. Prevent reallocation + * at module reload. + */ + if (!test_bit(HYPERVISOR_CALLBACK_VECTOR, used_vectors)) + alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, + hyperv_callback_vector); +} + +void hv_remove_vmbus_irq(void) +{ + /* We have no way to deallocate the interrupt gate */ + vmbus_handler = NULL; +} +EXPORT_SYMBOL_GPL(hv_setup_vmbus_irq); +EXPORT_SYMBOL_GPL(hv_remove_vmbus_irq); +#endif + static uint32_t __init ms_hyperv_platform(void) { u32 eax; @@ -105,6 +146,11 @@ static void __init ms_hyperv_init_platform(void) if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE) clocksource_register_hz(&hyperv_cs, NSEC_PER_SEC/100); + +#ifdef CONFIG_X86_IO_APIC + no_timer_check = 1; +#endif + } const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = { @@ -113,41 +159,3 @@ const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = { .init_platform = ms_hyperv_init_platform, }; EXPORT_SYMBOL(x86_hyper_ms_hyperv); - -#if IS_ENABLED(CONFIG_HYPERV) -static int vmbus_irq = -1; -static irq_handler_t vmbus_isr; - -void hv_register_vmbus_handler(int irq, irq_handler_t handler) -{ - /* - * Setup the IDT for hypervisor callback. - */ - alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, hyperv_callback_vector); - - vmbus_irq = irq; - vmbus_isr = handler; -} - -void hyperv_vector_handler(struct pt_regs *regs) -{ - struct pt_regs *old_regs = set_irq_regs(regs); - struct irq_desc *desc; - - irq_enter(); - exit_idle(); - - desc = irq_to_desc(vmbus_irq); - - if (desc) - generic_handle_irq_desc(vmbus_irq, desc); - - irq_exit(); - set_irq_regs(old_regs); -} -#else -void hv_register_vmbus_handler(int irq, irq_handler_t handler) -{ -} -#endif -EXPORT_SYMBOL_GPL(hv_register_vmbus_handler); diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index ce2d0a2c3e4f..0e25a1bc5ab5 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -683,7 +683,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock) } /* Flush all TLBs via a mov %cr3, %reg; mov %reg, %cr3 */ - count_vm_event(NR_TLB_LOCAL_FLUSH_ALL); + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); __flush_tlb(); /* Save MTRR state */ @@ -697,7 +697,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock) static void post_set(void) __releases(set_atomicity_lock) { /* Flush TLBs (no need to flush caches - they are disabled) */ - count_vm_event(NR_TLB_LOCAL_FLUSH_ALL); + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); __flush_tlb(); /* Intel (P6) standard MTRRs */ diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index b88645191fe5..ae407f7226c8 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -892,7 +892,6 @@ static void x86_pmu_enable(struct pmu *pmu) * hw_perf_group_sched_in() or x86_pmu_enable() * * step1: save events moving to new counters - * step2: reprogram moved events into new counters */ for (i = 0; i < n_running; i++) { event = cpuc->event_list[i]; @@ -918,6 +917,9 @@ static void x86_pmu_enable(struct pmu *pmu) x86_pmu_stop(event, PERF_EF_UPDATE); } + /* + * step2: reprogram moved events into new counters + */ for (i = 0; i < cpuc->n_events; i++) { event = cpuc->event_list[i]; hwc = &event->hw; @@ -1043,7 +1045,7 @@ static int x86_pmu_add(struct perf_event *event, int flags) /* * If group events scheduling transaction was started, * skip the schedulability test here, it will be performed - * at commit time (->commit_txn) as a whole + * at commit time (->commit_txn) as a whole. */ if (cpuc->group_flag & PERF_EVENT_TXN) goto done_collect; @@ -1058,6 +1060,10 @@ static int x86_pmu_add(struct perf_event *event, int flags) memcpy(cpuc->assign, assign, n*sizeof(int)); done_collect: + /* + * Commit the collect_events() state. See x86_pmu_del() and + * x86_pmu_*_txn(). + */ cpuc->n_events = n; cpuc->n_added += n - n0; cpuc->n_txn += n - n0; @@ -1183,25 +1189,38 @@ static void x86_pmu_del(struct perf_event *event, int flags) * If we're called during a txn, we don't need to do anything. * The events never got scheduled and ->cancel_txn will truncate * the event_list. + * + * XXX assumes any ->del() called during a TXN will only be on + * an event added during that same TXN. */ if (cpuc->group_flag & PERF_EVENT_TXN) return; + /* + * Not a TXN, therefore cleanup properly. + */ x86_pmu_stop(event, PERF_EF_UPDATE); for (i = 0; i < cpuc->n_events; i++) { - if (event == cpuc->event_list[i]) { + if (event == cpuc->event_list[i]) + break; + } - if (x86_pmu.put_event_constraints) - x86_pmu.put_event_constraints(cpuc, event); + if (WARN_ON_ONCE(i == cpuc->n_events)) /* called ->del() without ->add() ? */ + return; - while (++i < cpuc->n_events) - cpuc->event_list[i-1] = cpuc->event_list[i]; + /* If we have a newly added event; make sure to decrease n_added. */ + if (i >= cpuc->n_events - cpuc->n_added) + --cpuc->n_added; + + if (x86_pmu.put_event_constraints) + x86_pmu.put_event_constraints(cpuc, event); + + /* Delete the array entry. */ + while (++i < cpuc->n_events) + cpuc->event_list[i-1] = cpuc->event_list[i]; + --cpuc->n_events; - --cpuc->n_events; - break; - } - } perf_event_update_userpage(event); } @@ -1521,6 +1540,8 @@ static int __init init_hw_perf_events(void) pr_cont("%s PMU driver.\n", x86_pmu.name); + x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */ + for (quirk = x86_pmu.quirks; quirk; quirk = quirk->next) quirk->func(); @@ -1534,7 +1555,6 @@ static int __init init_hw_perf_events(void) __EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_counters) - 1, 0, x86_pmu.num_counters, 0, 0); - x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */ x86_pmu_format_group.attrs = x86_pmu.format_attrs; if (x86_pmu.event_attrs) @@ -1594,7 +1614,8 @@ static void x86_pmu_cancel_txn(struct pmu *pmu) { __this_cpu_and(cpu_hw_events.group_flag, ~PERF_EVENT_TXN); /* - * Truncate the collected events. + * Truncate collected array by the number of events added in this + * transaction. See x86_pmu_add() and x86_pmu_*_txn(). */ __this_cpu_sub(cpu_hw_events.n_added, __this_cpu_read(cpu_hw_events.n_txn)); __this_cpu_sub(cpu_hw_events.n_events, __this_cpu_read(cpu_hw_events.n_txn)); @@ -1605,6 +1626,8 @@ static void x86_pmu_cancel_txn(struct pmu *pmu) * Commit group events scheduling transaction * Perform the group schedulability test as a whole * Return 0 if success + * + * Does not cancel the transaction on failure; expects the caller to do this. */ static int x86_pmu_commit_txn(struct pmu *pmu) { @@ -1820,9 +1843,12 @@ static ssize_t set_attr_rdpmc(struct device *cdev, if (ret) return ret; + if (x86_pmu.attr_rdpmc_broken) + return -ENOTSUPP; + if (!!val != !!x86_pmu.attr_rdpmc) { x86_pmu.attr_rdpmc = !!val; - smp_call_function(change_rdpmc, (void *)val, 1); + on_each_cpu(change_rdpmc, (void *)val, 1); } return count; diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index c1a861829d81..3b2f9bdd974b 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -130,9 +130,11 @@ struct cpu_hw_events { unsigned long running[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; int enabled; - int n_events; - int n_added; - int n_txn; + int n_events; /* the # of events in the below arrays */ + int n_added; /* the # last events in the below arrays; + they've never been enabled yet */ + int n_txn; /* the # last events in the below arrays; + added in the current transaction */ int assign[X86_PMC_IDX_MAX]; /* event to counter assignment */ u64 tags[X86_PMC_IDX_MAX]; struct perf_event *event_list[X86_PMC_IDX_MAX]; /* in enabled order */ @@ -409,6 +411,7 @@ struct x86_pmu { /* * sysfs attrs */ + int attr_rdpmc_broken; int attr_rdpmc; struct attribute **format_attrs; struct attribute **event_attrs; diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 0fa4f242f050..aa333d966886 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1361,10 +1361,8 @@ static int intel_pmu_handle_irq(struct pt_regs *regs) intel_pmu_disable_all(); handled = intel_pmu_drain_bts_buffer(); status = intel_pmu_get_status(); - if (!status) { - intel_pmu_enable_all(0); - return handled; - } + if (!status) + goto done; loops = 0; again: @@ -2310,10 +2308,7 @@ __init int intel_pmu_init(void) if (version > 1) x86_pmu.num_counters_fixed = max((int)edx.split.num_counters_fixed, 3); - /* - * v2 and above have a perf capabilities MSR - */ - if (version > 1) { + if (boot_cpu_has(X86_FEATURE_PDCM)) { u64 capabilities; rdmsrl(MSR_IA32_PERF_CAPABILITIES, capabilities); diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 29c248799ced..bd2253d40cff 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -66,6 +66,47 @@ 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) +{ + 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 *box; + + box = *per_cpu_ptr(pmu->box, cpu); + if (box) + return box; + + raw_spin_lock(&uncore_box_lock); + list_for_each_entry(box, &pmu->box_list, list) { + if (box->phys_id == topology_physical_package_id(cpu)) { + atomic_inc(&box->refcnt); + *per_cpu_ptr(pmu->box, cpu) = box; + break; + } + } + 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) +{ + /* + * perf core schedules event on the basis of cpu, uncore events are + * collected by one of the cpus inside a physical package. + */ + 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 count; @@ -501,8 +542,11 @@ 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), @@ -1178,10 +1222,15 @@ 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(0x4134, 0xffff, 0xc), + 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), @@ -1631,6 +1680,349 @@ 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 DEFINE_PCI_DEVICE_TABLE(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 DEFINE_PCI_DEVICE_TABLE(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 DEFINE_PCI_DEVICE_TABLE(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 */ @@ -2781,6 +3173,7 @@ again: static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer) { struct intel_uncore_box *box; + struct perf_event *event; unsigned long flags; int bit; @@ -2793,19 +3186,27 @@ static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer) */ local_irq_save(flags); + /* + * handle boxes with an active event list as opposed to active + * counters + */ + list_for_each_entry(event, &box->active_list, active_entry) { + uncore_perf_event_update(box, event); + } + for_each_set_bit(bit, box->active_mask, UNCORE_PMC_IDX_MAX) uncore_perf_event_update(box, box->events[bit]); local_irq_restore(flags); - hrtimer_forward_now(hrtimer, ns_to_ktime(UNCORE_PMU_HRTIMER_INTERVAL)); + hrtimer_forward_now(hrtimer, ns_to_ktime(box->hrtimer_duration)); return HRTIMER_RESTART; } static void uncore_pmu_start_hrtimer(struct intel_uncore_box *box) { __hrtimer_start_range_ns(&box->hrtimer, - ns_to_ktime(UNCORE_PMU_HRTIMER_INTERVAL), 0, + ns_to_ktime(box->hrtimer_duration), 0, HRTIMER_MODE_REL_PINNED, 0); } @@ -2839,43 +3240,12 @@ static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, box->cpu = -1; box->phys_id = -1; - return box; -} - -static struct intel_uncore_box * -uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu) -{ - struct intel_uncore_box *box; - - box = *per_cpu_ptr(pmu->box, cpu); - if (box) - return box; + /* set default hrtimer timeout */ + box->hrtimer_duration = UNCORE_PMU_HRTIMER_INTERVAL; - raw_spin_lock(&uncore_box_lock); - list_for_each_entry(box, &pmu->box_list, list) { - if (box->phys_id == topology_physical_package_id(cpu)) { - atomic_inc(&box->refcnt); - *per_cpu_ptr(pmu->box, cpu) = box; - break; - } - } - raw_spin_unlock(&uncore_box_lock); + INIT_LIST_HEAD(&box->active_list); - return *per_cpu_ptr(pmu->box, cpu); -} - -static 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_event_to_box(struct perf_event *event) -{ - /* - * perf core schedules event on the basis of cpu, uncore events are - * collected by one of the cpus inside a physical package. - */ - return uncore_pmu_to_box(uncore_event_to_pmu(event), smp_processor_id()); + return box; } static int @@ -3271,16 +3641,21 @@ static int __init uncore_pmu_register(struct intel_uncore_pmu *pmu) { int ret; - pmu->pmu = (struct pmu) { - .attr_groups = pmu->type->attr_groups, - .task_ctx_nr = perf_invalid_context, - .event_init = uncore_pmu_event_init, - .add = uncore_pmu_event_add, - .del = uncore_pmu_event_del, - .start = uncore_pmu_event_start, - .stop = uncore_pmu_event_stop, - .read = uncore_pmu_event_read, - }; + if (!pmu->type->pmu) { + pmu->pmu = (struct pmu) { + .attr_groups = pmu->type->attr_groups, + .task_ctx_nr = perf_invalid_context, + .event_init = uncore_pmu_event_init, + .add = uncore_pmu_event_add, + .del = uncore_pmu_event_del, + .start = uncore_pmu_event_start, + .stop = uncore_pmu_event_stop, + .read = uncore_pmu_event_read, + }; + } else { + pmu->pmu = *pmu->type->pmu; + pmu->pmu.attr_groups = pmu->type->attr_groups; + } if (pmu->type->num_boxes == 1) { if (strlen(pmu->type->name) > 0) @@ -3326,6 +3701,8 @@ static int __init uncore_type_init(struct intel_uncore_type *type) if (!pmus) return -ENOMEM; + type->pmus = pmus; + type->unconstrainted = (struct event_constraint) __EVENT_CONSTRAINT(0, (1ULL << type->num_counters) - 1, 0, type->num_counters, 0, 0); @@ -3361,7 +3738,6 @@ static int __init uncore_type_init(struct intel_uncore_type *type) } type->pmu_group = &uncore_pmu_attr_group; - type->pmus = pmus; return 0; fail: uncore_type_exit(type); @@ -3493,6 +3869,28 @@ static int __init uncore_pci_init(void) pci_uncores = ivt_pci_uncores; uncore_pci_driver = &ivt_uncore_pci_driver; 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; + 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; + 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; + break; default: return 0; } @@ -3764,7 +4162,7 @@ static void __init uncore_cpu_setup(void *dummy) static int __init uncore_cpu_init(void) { - int ret, cpu, max_cores; + int ret, max_cores; max_cores = boot_cpu_data.x86_max_cores; switch (boot_cpu_data.x86_model) { @@ -3808,29 +4206,6 @@ static int __init uncore_cpu_init(void) if (ret) return ret; - get_online_cpus(); - - for_each_online_cpu(cpu) { - int i, phys_id = topology_physical_package_id(cpu); - - for_each_cpu(i, &uncore_cpu_mask) { - if (phys_id == topology_physical_package_id(i)) { - phys_id = -1; - break; - } - } - if (phys_id < 0) - continue; - - uncore_cpu_prepare(cpu, phys_id); - uncore_event_init_cpu(cpu); - } - on_each_cpu(uncore_cpu_setup, NULL, 1); - - register_cpu_notifier(&uncore_cpu_nb); - - put_online_cpus(); - return 0; } @@ -3859,6 +4234,41 @@ static int __init uncore_pmus_register(void) return 0; } +static void __init uncore_cpumask_init(void) +{ + int cpu; + + /* + * ony invoke once from msr or pci init code + */ + if (!cpumask_empty(&uncore_cpu_mask)) + return; + + get_online_cpus(); + + for_each_online_cpu(cpu) { + int i, phys_id = topology_physical_package_id(cpu); + + for_each_cpu(i, &uncore_cpu_mask) { + if (phys_id == topology_physical_package_id(i)) { + phys_id = -1; + break; + } + } + if (phys_id < 0) + continue; + + uncore_cpu_prepare(cpu, phys_id); + uncore_event_init_cpu(cpu); + } + on_each_cpu(uncore_cpu_setup, NULL, 1); + + register_cpu_notifier(&uncore_cpu_nb); + + put_online_cpus(); +} + + static int __init intel_uncore_init(void) { int ret; @@ -3877,6 +4287,7 @@ static int __init intel_uncore_init(void) uncore_pci_exit(); goto fail; } + uncore_cpumask_init(); uncore_pmus_register(); return 0; diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h index a80ab71a883d..90236f0c94a9 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h @@ -6,6 +6,7 @@ #define UNCORE_PMU_NAME_LEN 32 #define UNCORE_PMU_HRTIMER_INTERVAL (60LL * NSEC_PER_SEC) +#define UNCORE_SNB_IMC_HRTIMER_INTERVAL (5ULL * NSEC_PER_SEC) #define UNCORE_FIXED_EVENT 0xff #define UNCORE_PMC_IDX_MAX_GENERIC 8 @@ -440,6 +441,7 @@ struct intel_uncore_type { struct intel_uncore_ops *ops; struct uncore_event_desc *event_descs; const struct attribute_group *attr_groups[4]; + struct pmu *pmu; /* for custom pmu ops */ }; #define pmu_group attr_groups[0] @@ -488,8 +490,11 @@ struct intel_uncore_box { u64 tags[UNCORE_PMC_IDX_MAX]; struct pci_dev *pci_dev; struct intel_uncore_pmu *pmu; + u64 hrtimer_duration; /* hrtimer timeout for this box */ struct hrtimer hrtimer; struct list_head list; + struct list_head active_list; + void *io_addr; struct intel_uncore_extra_reg shared_regs[0]; }; diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c index 3486e6660357..5d466b7d8609 100644 --- a/arch/x86/kernel/cpu/perf_event_p4.c +++ b/arch/x86/kernel/cpu/perf_event_p4.c @@ -1257,7 +1257,24 @@ again: pass++; goto again; } - + /* + * Perf does test runs to see if a whole group can be assigned + * together succesfully. There can be multiple rounds of this. + * Unfortunately, p4_pmu_swap_config_ts touches the hwc->config + * bits, such that the next round of group assignments will + * cause the above p4_should_swap_ts to pass instead of fail. + * This leads to counters exclusive to thread0 being used by + * thread1. + * + * Solve this with a cheap hack, reset the idx back to -1 to + * force a new lookup (p4_next_cntr) to get the right counter + * for the right thread. + * + * This probably doesn't comply with the general spirit of how + * perf wants to work, but P4 is special. :-( + */ + if (p4_should_swap_ts(hwc->config, cpu)) + hwc->idx = -1; p4_pmu_swap_config_ts(hwc, cpu); if (assign) assign[i] = cntr_idx; @@ -1322,6 +1339,7 @@ static __initconst const struct x86_pmu p4_pmu = { __init int p4_pmu_init(void) { unsigned int low, high; + int i, reg; /* If we get stripped -- indexing fails */ BUILD_BUG_ON(ARCH_P4_MAX_CCCR > INTEL_PMC_MAX_GENERIC); @@ -1340,5 +1358,19 @@ __init int p4_pmu_init(void) x86_pmu = p4_pmu; + /* + * Even though the counters are configured to interrupt a particular + * logical processor when an overflow happens, testing has shown that + * on kdump kernels (which uses a single cpu), thread1's counter + * continues to run and will report an NMI on thread0. Due to the + * overflow bug, this leads to a stream of unknown NMIs. + * + * Solve this by zero'ing out the registers to mimic a reset. + */ + for (i = 0; i < x86_pmu.num_counters; i++) { + reg = x86_pmu_config_addr(i); + wrmsrl_safe(reg, 0ULL); + } + return 0; } diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c index b1e2fe115323..7c1a0c07b607 100644 --- a/arch/x86/kernel/cpu/perf_event_p6.c +++ b/arch/x86/kernel/cpu/perf_event_p6.c @@ -231,31 +231,49 @@ static __initconst const struct x86_pmu p6_pmu = { }; +static __init void p6_pmu_rdpmc_quirk(void) +{ + if (boot_cpu_data.x86_mask < 9) { + /* + * PPro erratum 26; fixed in stepping 9 and above. + */ + pr_warn("Userspace RDPMC support disabled due to a CPU erratum\n"); + x86_pmu.attr_rdpmc_broken = 1; + x86_pmu.attr_rdpmc = 0; + } +} + __init int p6_pmu_init(void) { + x86_pmu = p6_pmu; + switch (boot_cpu_data.x86_model) { - case 1: - case 3: /* Pentium Pro */ - case 5: - case 6: /* Pentium II */ - case 7: - case 8: - case 11: /* Pentium III */ - case 9: - case 13: - /* Pentium M */ + case 1: /* Pentium Pro */ + x86_add_quirk(p6_pmu_rdpmc_quirk); + break; + + case 3: /* Pentium II - Klamath */ + case 5: /* Pentium II - Deschutes */ + case 6: /* Pentium II - Mendocino */ break; + + case 7: /* Pentium III - Katmai */ + case 8: /* Pentium III - Coppermine */ + case 10: /* Pentium III Xeon */ + case 11: /* Pentium III - Tualatin */ + break; + + case 9: /* Pentium M - Banias */ + case 13: /* Pentium M - Dothan */ + break; + default: - pr_cont("unsupported p6 CPU model %d ", - boot_cpu_data.x86_model); + pr_cont("unsupported p6 CPU model %d ", boot_cpu_data.x86_model); return -ENODEV; } - x86_pmu = p6_pmu; - memcpy(hw_cache_event_ids, p6_hw_cache_event_ids, sizeof(hw_cache_event_ids)); - return 0; } diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index a57902efe2d5..507de8066594 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -57,9 +57,7 @@ static void kdump_nmi_callback(int cpu, struct pt_regs *regs) { #ifdef CONFIG_X86_32 struct pt_regs fixed_regs; -#endif -#ifdef CONFIG_X86_32 if (!user_mode_vm(regs)) { crash_fixup_ss_esp(&fixed_regs, regs); regs = &fixed_regs; diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index f2a1770ca176..5abd4cd4230c 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -16,12 +16,35 @@ #include <asm/stacktrace.h> +static void *is_irq_stack(void *p, void *irq) +{ + if (p < irq || p >= (irq + THREAD_SIZE)) + return NULL; + return irq + THREAD_SIZE; +} + + +static void *is_hardirq_stack(unsigned long *stack, int cpu) +{ + void *irq = per_cpu(hardirq_stack, cpu); + + return is_irq_stack(stack, irq); +} + +static void *is_softirq_stack(unsigned long *stack, int cpu) +{ + void *irq = per_cpu(softirq_stack, cpu); + + return is_irq_stack(stack, irq); +} void dump_trace(struct task_struct *task, struct pt_regs *regs, unsigned long *stack, unsigned long bp, const struct stacktrace_ops *ops, void *data) { + const unsigned cpu = get_cpu(); int graph = 0; + u32 *prev_esp; if (!task) task = current; @@ -30,7 +53,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, unsigned long dummy; stack = &dummy; - if (task && task != current) + if (task != current) stack = (unsigned long *)task->thread.sp; } @@ -39,18 +62,31 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, for (;;) { struct thread_info *context; + void *end_stack; + + end_stack = is_hardirq_stack(stack, cpu); + if (!end_stack) + end_stack = is_softirq_stack(stack, cpu); - context = (struct thread_info *) - ((unsigned long)stack & (~(THREAD_SIZE - 1))); - bp = ops->walk_stack(context, stack, bp, ops, data, NULL, &graph); + context = task_thread_info(task); + bp = ops->walk_stack(context, stack, bp, ops, data, + end_stack, &graph); - stack = (unsigned long *)context->previous_esp; + /* Stop if not on irq stack */ + if (!end_stack) + break; + + /* The previous esp is saved on the bottom of the stack */ + prev_esp = (u32 *)(end_stack - THREAD_SIZE); + stack = (unsigned long *)*prev_esp; if (!stack) break; + if (ops->stack(data, "IRQ") < 0) break; touch_nmi_watchdog(); } + put_cpu(); } EXPORT_SYMBOL(dump_trace); diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index addb207dab92..346b1df2412e 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -104,6 +104,45 @@ in_irq_stack(unsigned long *stack, unsigned long *irq_stack, return (stack >= irq_stack && stack < irq_stack_end); } +static const unsigned long irq_stack_size = + (IRQ_STACK_SIZE - 64) / sizeof(unsigned long); + +enum stack_type { + STACK_IS_UNKNOWN, + STACK_IS_NORMAL, + STACK_IS_EXCEPTION, + STACK_IS_IRQ, +}; + +static enum stack_type +analyze_stack(int cpu, struct task_struct *task, + unsigned long *stack, unsigned long **stack_end, char **id) +{ + unsigned long *irq_stack; + unsigned long addr; + unsigned used = 0; + + addr = ((unsigned long)stack & (~(THREAD_SIZE - 1))); + if ((unsigned long)task_stack_page(task) == addr) + return STACK_IS_NORMAL; + + *stack_end = in_exception_stack(cpu, (unsigned long)stack, + &used, id); + if (*stack_end) + return STACK_IS_EXCEPTION; + + *stack_end = (unsigned long *)per_cpu(irq_stack_ptr, cpu); + if (!*stack_end) + return STACK_IS_UNKNOWN; + + irq_stack = *stack_end - irq_stack_size; + + if (in_irq_stack(stack, irq_stack, *stack_end)) + return STACK_IS_IRQ; + + return STACK_IS_UNKNOWN; +} + /* * x86-64 can have up to three kernel stacks: * process stack @@ -116,12 +155,11 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, const struct stacktrace_ops *ops, void *data) { const unsigned cpu = get_cpu(); - unsigned long *irq_stack_end = - (unsigned long *)per_cpu(irq_stack_ptr, cpu); - unsigned used = 0; struct thread_info *tinfo; - int graph = 0; + unsigned long *irq_stack; unsigned long dummy; + int graph = 0; + int done = 0; if (!task) task = current; @@ -143,49 +181,60 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, * exceptions */ tinfo = task_thread_info(task); - for (;;) { + while (!done) { + unsigned long *stack_end; + enum stack_type stype; char *id; - unsigned long *estack_end; - estack_end = in_exception_stack(cpu, (unsigned long)stack, - &used, &id); - if (estack_end) { + stype = analyze_stack(cpu, task, stack, &stack_end, &id); + + /* Default finish unless specified to continue */ + done = 1; + + switch (stype) { + + /* Break out early if we are on the thread stack */ + case STACK_IS_NORMAL: + break; + + case STACK_IS_EXCEPTION: + if (ops->stack(data, id) < 0) break; bp = ops->walk_stack(tinfo, stack, bp, ops, - data, estack_end, &graph); + data, stack_end, &graph); ops->stack(data, "<EOE>"); /* * We link to the next stack via the * second-to-last pointer (index -2 to end) in the * exception stack: */ - stack = (unsigned long *) estack_end[-2]; - continue; - } - if (irq_stack_end) { - unsigned long *irq_stack; - irq_stack = irq_stack_end - - (IRQ_STACK_SIZE - 64) / sizeof(*irq_stack); - - if (in_irq_stack(stack, irq_stack, irq_stack_end)) { - if (ops->stack(data, "IRQ") < 0) - break; - bp = ops->walk_stack(tinfo, stack, bp, - ops, data, irq_stack_end, &graph); - /* - * We link to the next stack (which would be - * the process stack normally) the last - * pointer (index -1 to end) in the IRQ stack: - */ - stack = (unsigned long *) (irq_stack_end[-1]); - irq_stack_end = NULL; - ops->stack(data, "EOI"); - continue; - } + stack = (unsigned long *) stack_end[-2]; + done = 0; + break; + + case STACK_IS_IRQ: + + if (ops->stack(data, "IRQ") < 0) + break; + bp = ops->walk_stack(tinfo, stack, bp, + ops, data, stack_end, &graph); + /* + * We link to the next stack (which would be + * the process stack normally) the last + * pointer (index -1 to end) in the IRQ stack: + */ + stack = (unsigned long *) (stack_end[-1]); + irq_stack = stack_end - irq_stack_size; + ops->stack(data, "EOI"); + done = 0; + break; + + case STACK_IS_UNKNOWN: + ops->stack(data, "UNK"); + break; } - break; } /* diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index bc4a088f9023..6d7d5a1260a6 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -203,18 +203,15 @@ static void __init intel_remapping_check(int num, int slot, int func) revision = read_pci_config_byte(num, slot, func, PCI_REVISION_ID); /* - * Revision 13 of all triggering devices id in this quirk have - * a problem draining interrupts when irq remapping is enabled, - * and should be flagged as broken. Additionally revisions 0x12 - * and 0x22 of device id 0x3405 has this problem. + * Revision <= 13 of all triggering devices id in this quirk + * have a problem draining interrupts when irq remapping is + * enabled, and should be flagged as broken. Additionally + * revision 0x22 of device id 0x3405 has this problem. */ - if (revision == 0x13) + if (revision <= 0x13) set_irq_remapping_broken(); - else if ((device == 0x3405) && - ((revision == 0x12) || - (revision == 0x22))) + else if (device == 0x3405 && revision == 0x22) set_irq_remapping_broken(); - } /* diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index d4bdd253fea7..e6253195a301 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -77,8 +77,7 @@ within(unsigned long addr, unsigned long start, unsigned long end) return addr >= start && addr < end; } -static int -do_ftrace_mod_code(unsigned long ip, const void *new_code) +static unsigned long text_ip_addr(unsigned long ip) { /* * On x86_64, kernel text mappings are mapped read-only with @@ -91,7 +90,7 @@ do_ftrace_mod_code(unsigned long ip, const void *new_code) if (within(ip, (unsigned long)_text, (unsigned long)_etext)) ip = (unsigned long)__va(__pa_symbol(ip)); - return probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE); + return ip; } static const unsigned char *ftrace_nop_replace(void) @@ -123,8 +122,10 @@ ftrace_modify_code_direct(unsigned long ip, unsigned const char *old_code, if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0) return -EINVAL; + ip = text_ip_addr(ip); + /* replace the text with the new text */ - if (do_ftrace_mod_code(ip, new_code)) + if (probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE)) return -EPERM; sync_core(); @@ -221,37 +222,51 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, return -EINVAL; } -int ftrace_update_ftrace_func(ftrace_func_t func) +static unsigned long ftrace_update_func; + +static int update_ftrace_func(unsigned long ip, void *new) { - unsigned long ip = (unsigned long)(&ftrace_call); - unsigned char old[MCOUNT_INSN_SIZE], *new; + unsigned char old[MCOUNT_INSN_SIZE]; int ret; - memcpy(old, &ftrace_call, MCOUNT_INSN_SIZE); - new = ftrace_call_replace(ip, (unsigned long)func); + memcpy(old, (void *)ip, MCOUNT_INSN_SIZE); + + ftrace_update_func = ip; + /* Make sure the breakpoints see the ftrace_update_func update */ + smp_wmb(); /* See comment above by declaration of modifying_ftrace_code */ atomic_inc(&modifying_ftrace_code); ret = ftrace_modify_code(ip, old, new); + atomic_dec(&modifying_ftrace_code); + + return ret; +} + +int ftrace_update_ftrace_func(ftrace_func_t func) +{ + unsigned long ip = (unsigned long)(&ftrace_call); + unsigned char *new; + int ret; + + new = ftrace_call_replace(ip, (unsigned long)func); + ret = update_ftrace_func(ip, new); + /* Also update the regs callback function */ if (!ret) { ip = (unsigned long)(&ftrace_regs_call); - memcpy(old, &ftrace_regs_call, MCOUNT_INSN_SIZE); new = ftrace_call_replace(ip, (unsigned long)func); - ret = ftrace_modify_code(ip, old, new); + ret = update_ftrace_func(ip, new); } - atomic_dec(&modifying_ftrace_code); - return ret; } static int is_ftrace_caller(unsigned long ip) { - if (ip == (unsigned long)(&ftrace_call) || - ip == (unsigned long)(&ftrace_regs_call)) + if (ip == ftrace_update_func) return 1; return 0; @@ -677,45 +692,41 @@ int __init ftrace_dyn_arch_init(void *data) #ifdef CONFIG_DYNAMIC_FTRACE extern void ftrace_graph_call(void); -static int ftrace_mod_jmp(unsigned long ip, - int old_offset, int new_offset) +static unsigned char *ftrace_jmp_replace(unsigned long ip, unsigned long addr) { - unsigned char code[MCOUNT_INSN_SIZE]; + static union ftrace_code_union calc; - if (probe_kernel_read(code, (void *)ip, MCOUNT_INSN_SIZE)) - return -EFAULT; + /* Jmp not a call (ignore the .e8) */ + calc.e8 = 0xe9; + calc.offset = ftrace_calc_offset(ip + MCOUNT_INSN_SIZE, addr); - if (code[0] != 0xe9 || old_offset != *(int *)(&code[1])) - return -EINVAL; + /* + * ftrace external locks synchronize the access to the static variable. + */ + return calc.code; +} - *(int *)(&code[1]) = new_offset; +static int ftrace_mod_jmp(unsigned long ip, void *func) +{ + unsigned char *new; - if (do_ftrace_mod_code(ip, &code)) - return -EPERM; + new = ftrace_jmp_replace(ip, (unsigned long)func); - return 0; + return update_ftrace_func(ip, new); } int ftrace_enable_ftrace_graph_caller(void) { unsigned long ip = (unsigned long)(&ftrace_graph_call); - int old_offset, new_offset; - old_offset = (unsigned long)(&ftrace_stub) - (ip + MCOUNT_INSN_SIZE); - new_offset = (unsigned long)(&ftrace_graph_caller) - (ip + MCOUNT_INSN_SIZE); - - return ftrace_mod_jmp(ip, old_offset, new_offset); + return ftrace_mod_jmp(ip, &ftrace_graph_caller); } int ftrace_disable_ftrace_graph_caller(void) { unsigned long ip = (unsigned long)(&ftrace_graph_call); - int old_offset, new_offset; - - old_offset = (unsigned long)(&ftrace_graph_caller) - (ip + MCOUNT_INSN_SIZE); - new_offset = (unsigned long)(&ftrace_stub) - (ip + MCOUNT_INSN_SIZE); - return ftrace_mod_jmp(ip, old_offset, new_offset); + return ftrace_mod_jmp(ip, &ftrace_stub); } #endif /* !CONFIG_DYNAMIC_FTRACE */ diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 81ba27679f18..f36bd42d6f0c 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -544,6 +544,10 @@ ENDPROC(early_idt_handlers) /* This is global to keep gas from relaxing the jumps */ ENTRY(early_idt_handler) cld + + cmpl $2,(%esp) # X86_TRAP_NMI + je is_nmi # Ignore NMI + cmpl $2,%ss:early_recursion_flag je hlt_loop incl %ss:early_recursion_flag @@ -594,8 +598,9 @@ ex_entry: pop %edx pop %ecx pop %eax - addl $8,%esp /* drop vector number and error code */ decl %ss:early_recursion_flag +is_nmi: + addl $8,%esp /* drop vector number and error code */ iret ENDPROC(early_idt_handler) diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index e1aabdb314c8..a468c0a65c42 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -343,6 +343,9 @@ early_idt_handlers: ENTRY(early_idt_handler) cld + cmpl $2,(%rsp) # X86_TRAP_NMI + je is_nmi # Ignore NMI + cmpl $2,early_recursion_flag(%rip) jz 1f incl early_recursion_flag(%rip) @@ -405,8 +408,9 @@ ENTRY(early_idt_handler) popq %rdx popq %rcx popq %rax - addq $16,%rsp # drop vector number and error code decl early_recursion_flag(%rip) +is_nmi: + addq $16,%rsp # drop vector number and error code INTERRUPT_RETURN ENDPROC(early_idt_handler) diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index da85a8e830a1..014618dbaa7b 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -521,7 +521,7 @@ static int hpet_setup_irq(struct hpet_dev *dev) { if (request_irq(dev->irq, hpet_interrupt_handler, - IRQF_TIMER | IRQF_DISABLED | IRQF_NOBALANCING, + IRQF_TIMER | IRQF_NOBALANCING, dev->name, dev)) return -1; @@ -699,7 +699,7 @@ static int hpet_cpuhp_notify(struct notifier_block *n, /* FIXME: add schedule_work_on() */ schedule_delayed_work_on(cpu, &work.work, 0); wait_for_completion(&work.complete); - destroy_timer_on_stack(&work.work.timer); + destroy_delayed_work_on_stack(&work.work); break; case CPU_DEAD: if (hdev) { diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index e8368c6dd2a2..d5dd80814419 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -86,10 +86,19 @@ EXPORT_SYMBOL(__kernel_fpu_begin); void __kernel_fpu_end(void) { - if (use_eager_fpu()) - math_state_restore(); - else + if (use_eager_fpu()) { + /* + * For eager fpu, most the time, tsk_used_math() is true. + * Restore the user math as we are done with the kernel usage. + * At few instances during thread exit, signal handling etc, + * tsk_used_math() is false. Those few places will take proper + * actions, so we don't need to restore the math here. + */ + if (likely(tsk_used_math(current))) + math_state_restore(); + } else { stts(); + } } EXPORT_SYMBOL(__kernel_fpu_end); diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index dbb60878b744..42805fac0092 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -125,6 +125,12 @@ int arch_show_interrupts(struct seq_file *p, int prec) seq_printf(p, "%10u ", per_cpu(mce_poll_count, j)); seq_printf(p, " Machine check polls\n"); #endif +#if defined(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"); +#endif seq_printf(p, "%*s: %10u\n", prec, "ERR", atomic_read(&irq_err_count)); #if defined(CONFIG_X86_IO_APIC) seq_printf(p, "%*s: %10u\n", prec, "MIS", atomic_read(&irq_mis_count)); @@ -266,6 +272,14 @@ __visible void smp_trace_x86_platform_ipi(struct pt_regs *regs) EXPORT_SYMBOL_GPL(vector_used_by_percpu_irq); #ifdef CONFIG_HOTPLUG_CPU + +/* These two declarations are only used in check_irq_vectors_for_cpu_disable() + * below, which is protected by stop_machine(). Putting them on the stack + * results in a stack frame overflow. Dynamically allocating could result in a + * failure so declare these two cpumasks as global. + */ +static struct cpumask affinity_new, online_new; + /* * This cpu is going to be removed and its vectors migrated to the remaining * online cpus. Check to see if there are enough vectors in the remaining cpus. @@ -277,7 +291,6 @@ int check_irq_vectors_for_cpu_disable(void) unsigned int this_cpu, vector, this_count, count; struct irq_desc *desc; struct irq_data *data; - struct cpumask affinity_new, online_new; this_cpu = smp_processor_id(); cpumask_copy(&online_new, cpu_online_mask); diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index d7fcbedc9c43..63ce838e5a54 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -55,16 +55,8 @@ static inline int check_stack_overflow(void) { return 0; } static inline void print_stack_overflow(void) { } #endif -/* - * per-CPU IRQ handling contexts (thread information and stack) - */ -union irq_ctx { - struct thread_info tinfo; - u32 stack[THREAD_SIZE/sizeof(u32)]; -} __attribute__((aligned(THREAD_SIZE))); - -static DEFINE_PER_CPU(union irq_ctx *, hardirq_ctx); -static DEFINE_PER_CPU(union irq_ctx *, softirq_ctx); +DEFINE_PER_CPU(struct irq_stack *, hardirq_stack); +DEFINE_PER_CPU(struct irq_stack *, softirq_stack); static void call_on_stack(void *func, void *stack) { @@ -77,14 +69,26 @@ static void call_on_stack(void *func, void *stack) : "memory", "cc", "edx", "ecx", "eax"); } +/* how to get the current stack pointer from C */ +#define current_stack_pointer ({ \ + unsigned long sp; \ + asm("mov %%esp,%0" : "=g" (sp)); \ + sp; \ +}) + +static inline void *current_stack(void) +{ + return (void *)(current_stack_pointer & ~(THREAD_SIZE - 1)); +} + static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq) { - union irq_ctx *curctx, *irqctx; - u32 *isp, arg1, arg2; + struct irq_stack *curstk, *irqstk; + u32 *isp, *prev_esp, arg1, arg2; - curctx = (union irq_ctx *) current_thread_info(); - irqctx = __this_cpu_read(hardirq_ctx); + curstk = (struct irq_stack *) current_stack(); + irqstk = __this_cpu_read(hardirq_stack); /* * this is where we switch to the IRQ stack. However, if we are @@ -92,13 +96,14 @@ execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq) * handler) we can't do that and just have to keep using the * current stack (which is the irq stack already after all) */ - if (unlikely(curctx == irqctx)) + if (unlikely(curstk == irqstk)) return 0; - /* build the stack frame on the IRQ stack */ - isp = (u32 *) ((char *)irqctx + sizeof(*irqctx)); - irqctx->tinfo.task = curctx->tinfo.task; - irqctx->tinfo.previous_esp = current_stack_pointer; + isp = (u32 *) ((char *)irqstk + sizeof(*irqstk)); + + /* Save the next esp at the bottom of the stack */ + prev_esp = (u32 *)irqstk; + *prev_esp = current_stack_pointer; if (unlikely(overflow)) call_on_stack(print_stack_overflow, isp); @@ -118,46 +123,40 @@ execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq) */ void irq_ctx_init(int cpu) { - union irq_ctx *irqctx; + struct irq_stack *irqstk; - if (per_cpu(hardirq_ctx, cpu)) + if (per_cpu(hardirq_stack, cpu)) return; - irqctx = page_address(alloc_pages_node(cpu_to_node(cpu), + irqstk = page_address(alloc_pages_node(cpu_to_node(cpu), THREADINFO_GFP, THREAD_SIZE_ORDER)); - memset(&irqctx->tinfo, 0, sizeof(struct thread_info)); - irqctx->tinfo.cpu = cpu; - irqctx->tinfo.addr_limit = MAKE_MM_SEG(0); - - per_cpu(hardirq_ctx, cpu) = irqctx; + per_cpu(hardirq_stack, cpu) = irqstk; - irqctx = page_address(alloc_pages_node(cpu_to_node(cpu), + irqstk = page_address(alloc_pages_node(cpu_to_node(cpu), THREADINFO_GFP, THREAD_SIZE_ORDER)); - memset(&irqctx->tinfo, 0, sizeof(struct thread_info)); - irqctx->tinfo.cpu = cpu; - irqctx->tinfo.addr_limit = MAKE_MM_SEG(0); - - per_cpu(softirq_ctx, cpu) = irqctx; + per_cpu(softirq_stack, cpu) = irqstk; printk(KERN_DEBUG "CPU %u irqstacks, hard=%p soft=%p\n", - cpu, per_cpu(hardirq_ctx, cpu), per_cpu(softirq_ctx, cpu)); + cpu, per_cpu(hardirq_stack, cpu), per_cpu(softirq_stack, cpu)); } void do_softirq_own_stack(void) { - struct thread_info *curctx; - union irq_ctx *irqctx; - u32 *isp; + struct thread_info *curstk; + struct irq_stack *irqstk; + u32 *isp, *prev_esp; - curctx = current_thread_info(); - irqctx = __this_cpu_read(softirq_ctx); - irqctx->tinfo.task = curctx->task; - irqctx->tinfo.previous_esp = current_stack_pointer; + curstk = current_stack(); + irqstk = __this_cpu_read(softirq_stack); /* build the stack frame on the softirq stack */ - isp = (u32 *) ((char *)irqctx + sizeof(*irqctx)); + isp = (u32 *) ((char *)irqstk + sizeof(*irqstk)); + + /* Push the previous esp onto the stack */ + prev_esp = (u32 *)irqstk; + *prev_esp = current_stack_pointer; call_on_stack(__do_softirq, isp); } diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 4eabc160696f..679cef0791cd 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -279,5 +279,7 @@ void arch_crash_save_vmcoreinfo(void) VMCOREINFO_SYMBOL(node_data); VMCOREINFO_LENGTH(node_data, MAX_NUMNODES); #endif + vmcoreinfo_append_str("KERNELOFFSET=%lx\n", + (unsigned long)&_text - __START_KERNEL); } diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index 18be189368bb..e69f9882bf95 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -28,6 +28,7 @@ #include <linux/mm.h> #include <linux/gfp.h> #include <linux/jump_label.h> +#include <linux/random.h> #include <asm/page.h> #include <asm/pgtable.h> @@ -43,13 +44,52 @@ do { \ } while (0) #endif +#ifdef CONFIG_RANDOMIZE_BASE +static unsigned long module_load_offset; +static int randomize_modules = 1; + +/* Mutex protects the module_load_offset. */ +static DEFINE_MUTEX(module_kaslr_mutex); + +static int __init parse_nokaslr(char *p) +{ + randomize_modules = 0; + return 0; +} +early_param("nokaslr", parse_nokaslr); + +static unsigned long int get_module_load_offset(void) +{ + if (randomize_modules) { + mutex_lock(&module_kaslr_mutex); + /* + * Calculate the module_load_offset the first time this + * code is called. Once calculated it stays the same until + * reboot. + */ + if (module_load_offset == 0) + module_load_offset = + (get_random_int() % 1024 + 1) * PAGE_SIZE; + mutex_unlock(&module_kaslr_mutex); + } + return module_load_offset; +} +#else +static unsigned long int get_module_load_offset(void) +{ + return 0; +} +#endif + void *module_alloc(unsigned long size) { if (PAGE_ALIGN(size) > MODULES_LEN) return NULL; - return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END, - GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL_EXEC, - NUMA_NO_NODE, __builtin_return_address(0)); + return __vmalloc_node_range(size, 1, + MODULES_VADDR + get_module_load_offset(), + MODULES_END, GFP_KERNEL | __GFP_HIGHMEM, + PAGE_KERNEL_EXEC, NUMA_NO_NODE, + __builtin_return_address(0)); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 6fcb49ce50a1..b4872b999a71 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -87,6 +87,7 @@ __setup("unknown_nmi_panic", setup_unknown_nmi_panic); #define nmi_to_desc(type) (&nmi_desc[type]) static u64 nmi_longest_ns = 1 * NSEC_PER_MSEC; + static int __init nmi_warning_debugfs(void) { debugfs_create_u64("nmi_longest_ns", 0644, @@ -95,6 +96,20 @@ static int __init nmi_warning_debugfs(void) } fs_initcall(nmi_warning_debugfs); +static void nmi_max_handler(struct irq_work *w) +{ + struct nmiaction *a = container_of(w, struct nmiaction, irq_work); + int remainder_ns, decimal_msecs; + u64 whole_msecs = ACCESS_ONCE(a->max_duration); + + remainder_ns = do_div(whole_msecs, (1000 * 1000)); + decimal_msecs = remainder_ns / 1000; + + printk_ratelimited(KERN_INFO + "INFO: NMI handler (%ps) took too long to run: %lld.%03d msecs\n", + a->handler, whole_msecs, decimal_msecs); +} + static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2b) { struct nmi_desc *desc = nmi_to_desc(type); @@ -110,26 +125,20 @@ static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2 * to handle those situations. */ list_for_each_entry_rcu(a, &desc->head, list) { - u64 before, delta, whole_msecs; - int remainder_ns, decimal_msecs, thishandled; + int thishandled; + u64 delta; - before = sched_clock(); + delta = sched_clock(); thishandled = a->handler(type, regs); handled += thishandled; - delta = sched_clock() - before; + delta = sched_clock() - delta; trace_nmi_handler(a->handler, (int)delta, thishandled); - if (delta < nmi_longest_ns) + if (delta < nmi_longest_ns || delta < a->max_duration) continue; - nmi_longest_ns = delta; - whole_msecs = delta; - remainder_ns = do_div(whole_msecs, (1000 * 1000)); - decimal_msecs = remainder_ns / 1000; - printk_ratelimited(KERN_INFO - "INFO: NMI handler (%ps) took too long to run: " - "%lld.%03d msecs\n", a->handler, whole_msecs, - decimal_msecs); + a->max_duration = delta; + irq_work_queue(&a->irq_work); } rcu_read_unlock(); @@ -146,6 +155,8 @@ int __register_nmi_handler(unsigned int type, struct nmiaction *action) if (!action->handler) return -EINVAL; + init_irq_work(&action->irq_work, nmi_max_handler); + spin_lock_irqsave(&desc->lock, flags); /* diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 872079a67e4d..f7d0672481fd 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -100,8 +100,10 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size, flag |= __GFP_ZERO; again: page = NULL; - if (!(flag & GFP_ATOMIC)) + /* CMA can be used only in the context which permits sleeping */ + if (flag & __GFP_WAIT) page = dma_alloc_from_contiguous(dev, count, get_order(size)); + /* fallback */ if (!page) page = alloc_pages_node(dev_to_node(dev), flag, get_order(size)); if (!page) diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 3fb8d95ab8b5..4505e2a950d8 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -298,10 +298,7 @@ void arch_cpu_idle_dead(void) */ void arch_cpu_idle(void) { - if (cpuidle_idle_call()) - x86_idle(); - else - local_irq_enable(); + x86_idle(); } /* diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 0de43e98ce08..7bc86bbe7485 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -314,6 +314,10 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) */ arch_end_context_switch(next_p); + this_cpu_write(kernel_stack, + (unsigned long)task_stack_page(next_p) + + THREAD_SIZE - KERNEL_STACK_OFFSET); + /* * Restore %gs if needed (which is common) */ diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 7461f50d5bb1..678c0ada3b3c 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -184,14 +184,14 @@ unsigned long kernel_stack_pointer(struct pt_regs *regs) { unsigned long context = (unsigned long)regs & ~(THREAD_SIZE - 1); unsigned long sp = (unsigned long)®s->sp; - struct thread_info *tinfo; + u32 *prev_esp; if (context == (sp & ~(THREAD_SIZE - 1))) return sp; - tinfo = (struct thread_info *)context; - if (tinfo->previous_esp) - return tinfo->previous_esp; + prev_esp = (u32 *)(context); + if (prev_esp) + return (unsigned long)prev_esp; return (unsigned long)regs; } diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index 04ee1e2e4c02..ff898bbf579d 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -529,7 +529,7 @@ static void quirk_amd_nb_node(struct pci_dev *dev) return; pci_read_config_dword(nb_ht, 0x60, &val); - node = val & 7; + node = pcibus_to_node(dev->bus) | (val & 7); /* * Some hardware may return an invalid node ID, * so check it first: @@ -571,3 +571,40 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F5, quirk_amd_nb_node); #endif + +#ifdef CONFIG_PCI +/* + * Processor does not ensure DRAM scrub read/write sequence + * is atomic wrt accesses to CC6 save state area. Therefore + * if a concurrent scrub read/write access is to same address + * the entry may appear as if it is not written. This quirk + * applies to Fam16h models 00h-0Fh + * + * See "Revision Guide" for AMD F16h models 00h-0fh, + * document 51810 rev. 3.04, Nov 2013 + */ +static void amd_disable_seq_and_redirect_scrub(struct pci_dev *dev) +{ + u32 val; + + /* + * Suggested workaround: + * set D18F3x58[4:0] = 00h and set D18F3x5C[0] = 0b + */ + pci_read_config_dword(dev, 0x58, &val); + if (val & 0x1F) { + val &= ~(0x1F); + pci_write_config_dword(dev, 0x58, val); + } + + pci_read_config_dword(dev, 0x5C, &val); + if (val & BIT(0)) { + val &= ~BIT(0); + pci_write_config_dword(dev, 0x5c, val); + } +} + +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3, + amd_disable_seq_and_redirect_scrub); + +#endif diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index c752cb43e52f..654b46574b91 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -464,9 +464,12 @@ void __attribute__((weak)) mach_reboot_fixups(void) * 2) If still alive, write to the keyboard controller * 3) If still alive, write to the ACPI reboot register again * 4) If still alive, write to the keyboard controller again + * 5) If still alive, call the EFI runtime service to reboot + * 6) If still alive, write to the PCI IO port 0xCF9 to reboot + * 7) If still alive, inform BIOS to do a proper reboot * * If the machine is still alive at this stage, it gives up. We default to - * following the same pattern, except that if we're still alive after (4) we'll + * following the same pattern, except that if we're still alive after (7) we'll * try to force a triple fault and then cycle between hitting the keyboard * controller and doing that */ @@ -502,7 +505,7 @@ static void native_machine_emergency_restart(void) attempt = 1; reboot_type = BOOT_ACPI; } else { - reboot_type = BOOT_TRIPLE; + reboot_type = BOOT_EFI; } break; @@ -510,13 +513,15 @@ static void native_machine_emergency_restart(void) load_idt(&no_idt); __asm__ __volatile__("int3"); + /* We're probably dead after this, but... */ reboot_type = BOOT_KBD; break; case BOOT_BIOS: machine_real_restart(MRR_BIOS); - reboot_type = BOOT_KBD; + /* We're probably dead after this, but... */ + reboot_type = BOOT_TRIPLE; break; case BOOT_ACPI: @@ -530,7 +535,7 @@ static void native_machine_emergency_restart(void) EFI_RESET_WARM : EFI_RESET_COLD, EFI_SUCCESS, 0, NULL); - reboot_type = BOOT_KBD; + reboot_type = BOOT_CF9_COND; break; case BOOT_CF9: @@ -548,7 +553,7 @@ static void native_machine_emergency_restart(void) outb(cf9|reboot_code, 0xcf9); udelay(50); } - reboot_type = BOOT_KBD; + reboot_type = BOOT_BIOS; break; } } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 06853e670354..fa511acff7e6 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -926,11 +926,11 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_EFI if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature, "EL32", 4)) { - set_bit(EFI_BOOT, &x86_efi_facility); + set_bit(EFI_BOOT, &efi.flags); } else if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature, "EL64", 4)) { - set_bit(EFI_BOOT, &x86_efi_facility); - set_bit(EFI_64BIT, &x86_efi_facility); + set_bit(EFI_BOOT, &efi.flags); + set_bit(EFI_64BIT, &efi.flags); } if (efi_enabled(EFI_BOOT)) @@ -1239,14 +1239,8 @@ void __init setup_arch(char **cmdline_p) register_refined_jiffies(CLOCK_TICK_RATE); #ifdef CONFIG_EFI - /* Once setup is done above, unmap the EFI memory map on - * mismatched firmware/kernel archtectures since there is no - * support for runtime services. - */ - if (efi_enabled(EFI_BOOT) && !efi_is_native()) { - pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n"); - efi_unmap_memmap(); - } + if (efi_enabled(EFI_BOOT)) + efi_apply_memmap_quirks(); #endif } diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index a32da804252e..34826934d4a7 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -122,8 +122,9 @@ static void smp_callin(void) * Since CPU0 is not wakened up by INIT, it doesn't wait for the IPI. */ cpuid = smp_processor_id(); - if (apic->wait_for_init_deassert && cpuid != 0) - apic->wait_for_init_deassert(&init_deasserted); + if (apic->wait_for_init_deassert && cpuid) + while (!atomic_read(&init_deasserted)) + cpu_relax(); /* * (This works even if the APIC is not enabled.) @@ -701,11 +702,15 @@ wakeup_cpu_via_init_nmi(int cpu, unsigned long start_ip, int apicid, int id; int boot_error; + preempt_disable(); + /* * Wake up AP by INIT, INIT, STARTUP sequence. */ - if (cpu) - return wakeup_secondary_cpu_via_init(apicid, start_ip); + if (cpu) { + boot_error = wakeup_secondary_cpu_via_init(apicid, start_ip); + goto out; + } /* * Wake up BSP by nmi. @@ -725,6 +730,9 @@ wakeup_cpu_via_init_nmi(int cpu, unsigned long start_ip, int apicid, boot_error = wakeup_secondary_cpu_via_nmi(id, start_ip); } +out: + preempt_enable(); + return boot_error; } @@ -758,10 +766,10 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) #else clear_tsk_thread_flag(idle, TIF_FORK); initial_gs = per_cpu_offset(cpu); +#endif per_cpu(kernel_stack, cpu) = (unsigned long)task_stack_page(idle) - KERNEL_STACK_OFFSET + THREAD_SIZE; -#endif early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu); initial_code = (unsigned long)start_secondary; stack_start = idle->thread.sp; @@ -1379,7 +1387,7 @@ static inline void mwait_play_dead(void) if (!this_cpu_has(X86_FEATURE_MWAIT)) return; - if (!this_cpu_has(X86_FEATURE_CLFLSH)) + if (!this_cpu_has(X86_FEATURE_CLFLUSH)) return; if (__this_cpu_read(cpu_info.cpuid_level) < CPUID_MWAIT_LEAF) return; diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c index 24d3c91e9812..bf7ef5ce29df 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 -DEFINE_VVAR(volatile unsigned long, jiffies) = INITIAL_JIFFIES; +__visible DEFINE_VVAR(volatile unsigned long, jiffies) = INITIAL_JIFFIES; #endif unsigned long profile_pc(struct pt_regs *regs) @@ -62,7 +62,7 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id) static struct irqaction irq0 = { .handler = timer_interrupt, - .flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL | IRQF_TIMER, + .flags = IRQF_NOBALANCING | IRQF_IRQPOLL | IRQF_TIMER, .name = "timer" }; diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 19e5adb49a27..7a9296ab8834 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -209,7 +209,7 @@ static inline unsigned long long cycles_2_ns(unsigned long long cyc) * dance when its actually needed. */ - preempt_disable(); + preempt_disable_notrace(); data = this_cpu_read(cyc2ns.head); tail = this_cpu_read(cyc2ns.tail); @@ -229,7 +229,7 @@ static inline unsigned long long cycles_2_ns(unsigned long long cyc) if (!--data->__count) this_cpu_write(cyc2ns.tail, data); } - preempt_enable(); + preempt_enable_notrace(); return ns; } @@ -653,13 +653,10 @@ unsigned long native_calibrate_tsc(void) /* Calibrate TSC using MSR for Intel Atom SoCs */ local_irq_save(flags); - i = try_msr_calibrate_tsc(&fast_calibrate); + fast_calibrate = try_msr_calibrate_tsc(); local_irq_restore(flags); - if (i >= 0) { - if (i == 0) - pr_warn("Fast TSC calibration using MSR failed\n"); + if (fast_calibrate) return fast_calibrate; - } local_irq_save(flags); fast_calibrate = quick_pit_calibrate(); @@ -917,8 +914,7 @@ static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val, tsc_khz_ref = tsc_khz; } if ((val == CPUFREQ_PRECHANGE && freq->old < freq->new) || - (val == CPUFREQ_POSTCHANGE && freq->old > freq->new) || - (val == CPUFREQ_RESUMECHANGE)) { + (val == CPUFREQ_POSTCHANGE && freq->old > freq->new)) { *lpj = cpufreq_scale(loops_per_jiffy_ref, ref_freq, freq->new); tsc_khz = cpufreq_scale(tsc_khz_ref, ref_freq, freq->new); diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c index 8b5434f4389f..92ae6acac8a7 100644 --- a/arch/x86/kernel/tsc_msr.c +++ b/arch/x86/kernel/tsc_msr.c @@ -53,7 +53,7 @@ static struct freq_desc freq_desc_tables[] = { /* TNG */ { 6, 0x4a, 1, { 0, FREQ_100, FREQ_133, 0, 0, 0, 0, 0 } }, /* VLV2 */ - { 6, 0x37, 1, { 0, FREQ_100, FREQ_133, FREQ_166, 0, 0, 0, 0 } }, + { 6, 0x37, 1, { FREQ_83, FREQ_100, FREQ_133, FREQ_166, 0, 0, 0, 0 } }, /* ANN */ { 6, 0x5a, 1, { FREQ_83, FREQ_100, FREQ_133, FREQ_100, 0, 0, 0, 0 } }, }; @@ -77,21 +77,18 @@ static int match_cpu(u8 family, u8 model) /* * Do MSR calibration only for known/supported CPUs. - * Return values: - * -1: CPU is unknown/unsupported for MSR based calibration - * 0: CPU is known/supported, but calibration failed - * 1: CPU is known/supported, and calibration succeeded + * + * Returns the calibration value or 0 if MSR calibration failed. */ -int try_msr_calibrate_tsc(unsigned long *fast_calibrate) +unsigned long try_msr_calibrate_tsc(void) { - int cpu_index; u32 lo, hi, ratio, freq_id, freq; + unsigned long res; + int cpu_index; cpu_index = match_cpu(boot_cpu_data.x86, boot_cpu_data.x86_model); if (cpu_index < 0) - return -1; - - *fast_calibrate = 0; + return 0; if (freq_desc_tables[cpu_index].msr_plat) { rdmsr(MSR_PLATFORM_INFO, lo, hi); @@ -103,7 +100,7 @@ int try_msr_calibrate_tsc(unsigned long *fast_calibrate) pr_info("Maximum core-clock to bus-clock ratio: 0x%x\n", ratio); if (!ratio) - return 0; + goto fail; /* Get FSB FREQ ID */ rdmsr(MSR_FSB_FREQ, lo, hi); @@ -112,16 +109,19 @@ int try_msr_calibrate_tsc(unsigned long *fast_calibrate) pr_info("Resolved frequency ID: %u, frequency: %u KHz\n", freq_id, freq); if (!freq) - return 0; + goto fail; /* TSC frequency = maximum resolved freq * maximum resolved bus ratio */ - *fast_calibrate = freq * ratio; - pr_info("TSC runs at %lu KHz\n", *fast_calibrate); + res = freq * ratio; + pr_info("TSC runs at %lu KHz\n", res); #ifdef CONFIG_X86_LOCAL_APIC lapic_timer_frequency = (freq * 1000) / HZ; pr_info("lapic_timer_frequency = %d\n", lapic_timer_frequency); #endif + return res; - return 1; +fail: + pr_warn("Fast TSC calibration using MSR failed\n"); + return 0; } |