diff options
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r-- | arch/x86/kernel/apic/io_apic.c | 3 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/intel_cacheinfo.c | 2 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/mcheck/mce.c | 6 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/mcheck/mce_amd.c | 10 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/perf_event.c | 16 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/perf_event_intel_uncore.c | 48 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/perf_event_knc.c | 93 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/perf_event_p6.c | 127 | ||||
-rw-r--r-- | arch/x86/kernel/e820.c | 3 | ||||
-rw-r--r-- | arch/x86/kernel/entry_32.S | 8 | ||||
-rw-r--r-- | arch/x86/kernel/entry_64.S | 2 | ||||
-rw-r--r-- | arch/x86/kernel/kvm.c | 3 | ||||
-rw-r--r-- | arch/x86/kernel/reboot.c | 8 | ||||
-rw-r--r-- | arch/x86/kernel/setup.c | 30 | ||||
-rw-r--r-- | arch/x86/kernel/signal.c | 4 | ||||
-rw-r--r-- | arch/x86/kernel/uprobes.c | 16 |
16 files changed, 289 insertions, 90 deletions
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index c265593ec2cd..1817fa911024 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2257,6 +2257,9 @@ asmlinkage void smp_irq_move_cleanup_interrupt(void) continue; cfg = irq_cfg(irq); + if (!cfg) + continue; + raw_spin_lock(&desc->lock); /* diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index 9a7c90d80bc4..93c5451bdd52 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -991,7 +991,7 @@ static struct attribute ** __cpuinit amd_l3_attrs(void) if (attrs) return attrs; - n = sizeof (default_attrs) / sizeof (struct attribute *); + n = ARRAY_SIZE(default_attrs); if (amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE)) n += 2; diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 29e87d3b2843..46cbf8689692 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -2209,11 +2209,6 @@ static struct dev_ext_attribute dev_attr_cmci_disabled = { &mce_cmci_disabled }; -static struct dev_ext_attribute dev_attr_bios_cmci_threshold = { - __ATTR(bios_cmci_threshold, 0444, device_show_int, NULL), - &mce_bios_cmci_threshold -}; - static struct device_attribute *mce_device_attrs[] = { &dev_attr_tolerant.attr, &dev_attr_check_interval.attr, @@ -2222,7 +2217,6 @@ static struct device_attribute *mce_device_attrs[] = { &dev_attr_dont_log_ce.attr, &dev_attr_ignore_ce.attr, &dev_attr_cmci_disabled.attr, - &dev_attr_bios_cmci_threshold.attr, NULL }; diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index c4e916d77378..698b6ec12e0f 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -576,12 +576,10 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) int err = 0; if (shared_bank[bank]) { - nb = node_to_amd_nb(amd_get_nb_id(cpu)); - WARN_ON(!nb); /* threshold descriptor already initialized on this node? */ - if (nb->bank4) { + if (nb && nb->bank4) { /* yes, use it */ b = nb->bank4; err = kobject_add(b->kobj, &dev->kobj, name); @@ -615,8 +613,10 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) atomic_set(&b->cpus, 1); /* nb is already initialized, see above */ - WARN_ON(nb->bank4); - nb->bank4 = b; + if (nb) { + WARN_ON(nb->bank4); + nb->bank4 = b; + } } err = allocate_threshold_blocks(cpu, bank, 0, diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 915b876edd1e..4a3374e61a93 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -208,12 +208,14 @@ static bool check_hw_exists(void) } /* - * Now write a value and read it back to see if it matches, - * this is needed to detect certain hardware emulators (qemu/kvm) - * that don't trap on the MSR access and always return 0s. + * Read the current value, change it and read it back to see if it + * matches, this is needed to detect certain hardware emulators + * (qemu/kvm) that don't trap on the MSR access and always return 0s. */ - val = 0xabcdUL; reg = x86_pmu_event_addr(0); + if (rdmsrl_safe(reg, &val)) + goto msr_fail; + val ^= 0xffffUL; ret = wrmsrl_safe(reg, val); ret |= rdmsrl_safe(reg, &val_new); if (ret || val != val_new) @@ -338,6 +340,9 @@ int x86_setup_perfctr(struct perf_event *event) /* BTS is currently only allowed for user-mode. */ if (!attr->exclude_kernel) return -EOPNOTSUPP; + + if (!attr->exclude_guest) + return -EOPNOTSUPP; } hwc->config |= config; @@ -380,6 +385,9 @@ int x86_pmu_hw_config(struct perf_event *event) if (event->attr.precise_ip) { int precise = 0; + if (!event->attr.exclude_guest) + return -EOPNOTSUPP; + /* Support for constant skid */ if (x86_pmu.pebs_active && !x86_pmu.pebs_broken) { precise++; diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 99d96a4978b5..3cf3d97cce3a 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -118,22 +118,24 @@ static void snbep_uncore_pci_disable_box(struct intel_uncore_box *box) { struct pci_dev *pdev = box->pci_dev; int box_ctl = uncore_pci_box_ctl(box); - u32 config; + u32 config = 0; - pci_read_config_dword(pdev, box_ctl, &config); - config |= SNBEP_PMON_BOX_CTL_FRZ; - pci_write_config_dword(pdev, box_ctl, config); + if (!pci_read_config_dword(pdev, box_ctl, &config)) { + config |= SNBEP_PMON_BOX_CTL_FRZ; + pci_write_config_dword(pdev, box_ctl, config); + } } static void snbep_uncore_pci_enable_box(struct intel_uncore_box *box) { struct pci_dev *pdev = box->pci_dev; int box_ctl = uncore_pci_box_ctl(box); - u32 config; + u32 config = 0; - pci_read_config_dword(pdev, box_ctl, &config); - config &= ~SNBEP_PMON_BOX_CTL_FRZ; - pci_write_config_dword(pdev, box_ctl, config); + if (!pci_read_config_dword(pdev, box_ctl, &config)) { + config &= ~SNBEP_PMON_BOX_CTL_FRZ; + pci_write_config_dword(pdev, box_ctl, config); + } } static void snbep_uncore_pci_enable_event(struct intel_uncore_box *box, struct perf_event *event) @@ -156,7 +158,7 @@ static u64 snbep_uncore_pci_read_counter(struct intel_uncore_box *box, struct pe { struct pci_dev *pdev = box->pci_dev; struct hw_perf_event *hwc = &event->hw; - u64 count; + u64 count = 0; pci_read_config_dword(pdev, hwc->event_base, (u32 *)&count); pci_read_config_dword(pdev, hwc->event_base + 4, (u32 *)&count + 1); @@ -603,11 +605,12 @@ static struct pci_driver snbep_uncore_pci_driver = { /* * build pci bus to socket mapping */ -static void snbep_pci2phy_map_init(void) +static int snbep_pci2phy_map_init(void) { struct pci_dev *ubox_dev = NULL; int i, bus, nodeid; - u32 config; + int err = 0; + u32 config = 0; while (1) { /* find the UBOX device */ @@ -618,10 +621,14 @@ static void snbep_pci2phy_map_init(void) break; bus = ubox_dev->bus->number; /* get the Node ID of the local register */ - pci_read_config_dword(ubox_dev, 0x40, &config); + err = pci_read_config_dword(ubox_dev, 0x40, &config); + if (err) + break; nodeid = config; /* get the Node ID mapping */ - pci_read_config_dword(ubox_dev, 0x54, &config); + err = pci_read_config_dword(ubox_dev, 0x54, &config); + if (err) + break; /* * every three bits in the Node ID mapping register maps * to a particular node. @@ -633,7 +640,11 @@ static void snbep_pci2phy_map_init(void) } } }; - return; + + if (ubox_dev) + pci_dev_put(ubox_dev); + + return err ? pcibios_err_to_errno(err) : 0; } /* end of Sandy Bridge-EP uncore support */ @@ -1547,7 +1558,6 @@ void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - int port; /* adjust the main event selector and extra register index */ if (reg1->idx % 2) { @@ -1559,7 +1569,6 @@ void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event) } /* adjust extra register config */ - port = reg1->idx / 6 + box->pmu->pmu_idx * 4; switch (reg1->idx % 6) { case 2: /* shift the 8~15 bits to the 0~7 bits */ @@ -2578,9 +2587,11 @@ static int __init uncore_pci_init(void) switch (boot_cpu_data.x86_model) { case 45: /* Sandy Bridge-EP */ + ret = snbep_pci2phy_map_init(); + if (ret) + return ret; pci_uncores = snbep_pci_uncores; uncore_pci_driver = &snbep_uncore_pci_driver; - snbep_pci2phy_map_init(); break; default: return 0; @@ -2926,6 +2937,9 @@ static int __init intel_uncore_init(void) if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) return -ENODEV; + if (cpu_has_hypervisor) + return -ENODEV; + ret = uncore_pci_init(); if (ret) goto fail; diff --git a/arch/x86/kernel/cpu/perf_event_knc.c b/arch/x86/kernel/cpu/perf_event_knc.c index 7c46bfdbc373..4b7731bf23a8 100644 --- a/arch/x86/kernel/cpu/perf_event_knc.c +++ b/arch/x86/kernel/cpu/perf_event_knc.c @@ -3,6 +3,8 @@ #include <linux/perf_event.h> #include <linux/types.h> +#include <asm/hardirq.h> + #include "perf_event.h" static const u64 knc_perfmon_event_map[] = @@ -173,30 +175,100 @@ static void knc_pmu_enable_all(int added) static inline void knc_pmu_disable_event(struct perf_event *event) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct hw_perf_event *hwc = &event->hw; u64 val; val = hwc->config; - if (cpuc->enabled) - val &= ~ARCH_PERFMON_EVENTSEL_ENABLE; + val &= ~ARCH_PERFMON_EVENTSEL_ENABLE; (void)wrmsrl_safe(hwc->config_base + hwc->idx, val); } static void knc_pmu_enable_event(struct perf_event *event) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct hw_perf_event *hwc = &event->hw; u64 val; val = hwc->config; - if (cpuc->enabled) - val |= ARCH_PERFMON_EVENTSEL_ENABLE; + val |= ARCH_PERFMON_EVENTSEL_ENABLE; (void)wrmsrl_safe(hwc->config_base + hwc->idx, val); } +static inline u64 knc_pmu_get_status(void) +{ + u64 status; + + rdmsrl(MSR_KNC_IA32_PERF_GLOBAL_STATUS, status); + + return status; +} + +static inline void knc_pmu_ack_status(u64 ack) +{ + wrmsrl(MSR_KNC_IA32_PERF_GLOBAL_OVF_CONTROL, ack); +} + +static int knc_pmu_handle_irq(struct pt_regs *regs) +{ + struct perf_sample_data data; + struct cpu_hw_events *cpuc; + int handled = 0; + int bit, loops; + u64 status; + + cpuc = &__get_cpu_var(cpu_hw_events); + + knc_pmu_disable_all(); + + status = knc_pmu_get_status(); + if (!status) { + knc_pmu_enable_all(0); + return handled; + } + + loops = 0; +again: + knc_pmu_ack_status(status); + if (++loops > 100) { + WARN_ONCE(1, "perf: irq loop stuck!\n"); + perf_event_print_debug(); + goto done; + } + + inc_irq_stat(apic_perf_irqs); + + for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) { + struct perf_event *event = cpuc->events[bit]; + + handled++; + + if (!test_bit(bit, cpuc->active_mask)) + continue; + + if (!intel_pmu_save_and_restart(event)) + continue; + + perf_sample_data_init(&data, 0, event->hw.last_period); + + if (perf_event_overflow(event, &data, regs)) + x86_pmu_stop(event, 0); + } + + /* + * Repeat if there is more work to be done: + */ + status = knc_pmu_get_status(); + if (status) + goto again; + +done: + knc_pmu_enable_all(0); + + return handled; +} + + PMU_FORMAT_ATTR(event, "config:0-7" ); PMU_FORMAT_ATTR(umask, "config:8-15" ); PMU_FORMAT_ATTR(edge, "config:18" ); @@ -214,7 +286,7 @@ static struct attribute *intel_knc_formats_attr[] = { static __initconst struct x86_pmu knc_pmu = { .name = "knc", - .handle_irq = x86_pmu_handle_irq, + .handle_irq = knc_pmu_handle_irq, .disable_all = knc_pmu_disable_all, .enable_all = knc_pmu_enable_all, .enable = knc_pmu_enable_event, @@ -226,12 +298,11 @@ static __initconst struct x86_pmu knc_pmu = { .event_map = knc_pmu_event_map, .max_events = ARRAY_SIZE(knc_perfmon_event_map), .apic = 1, - .max_period = (1ULL << 31) - 1, + .max_period = (1ULL << 39) - 1, .version = 0, .num_counters = 2, - /* in theory 40 bits, early silicon is buggy though */ - .cntval_bits = 32, - .cntval_mask = (1ULL << 32) - 1, + .cntval_bits = 40, + .cntval_mask = (1ULL << 40) - 1, .get_event_constraints = x86_get_event_constraints, .event_constraints = knc_event_constraints, .format_attrs = intel_knc_formats_attr, diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c index e4dd0f7a0453..7d0270bd793e 100644 --- a/arch/x86/kernel/cpu/perf_event_p6.c +++ b/arch/x86/kernel/cpu/perf_event_p6.c @@ -8,13 +8,106 @@ */ static const u64 p6_perfmon_event_map[] = { - [PERF_COUNT_HW_CPU_CYCLES] = 0x0079, - [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, - [PERF_COUNT_HW_CACHE_REFERENCES] = 0x0f2e, - [PERF_COUNT_HW_CACHE_MISSES] = 0x012e, - [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c4, - [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c5, - [PERF_COUNT_HW_BUS_CYCLES] = 0x0062, + [PERF_COUNT_HW_CPU_CYCLES] = 0x0079, /* CPU_CLK_UNHALTED */ + [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, /* INST_RETIRED */ + [PERF_COUNT_HW_CACHE_REFERENCES] = 0x0f2e, /* L2_RQSTS:M:E:S:I */ + [PERF_COUNT_HW_CACHE_MISSES] = 0x012e, /* L2_RQSTS:I */ + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c4, /* BR_INST_RETIRED */ + [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c5, /* BR_MISS_PRED_RETIRED */ + [PERF_COUNT_HW_BUS_CYCLES] = 0x0062, /* BUS_DRDY_CLOCKS */ + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00a2, /* RESOURCE_STALLS */ + +}; + +static __initconst u64 p6_hw_cache_event_ids + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = +{ + [ C(L1D) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0043, /* DATA_MEM_REFS */ + [ C(RESULT_MISS) ] = 0x0045, /* DCU_LINES_IN */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0x0f29, /* L2_LD:M:E:S:I */ + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(L1I ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0080, /* IFU_IFETCH */ + [ C(RESULT_MISS) ] = 0x0f28, /* L2_IFETCH:M:E:S:I */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(LL ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0x0025, /* L2_M_LINES_INM */ + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(DTLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0043, /* DATA_MEM_REFS */ + [ C(RESULT_MISS) ] = 0, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(ITLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0080, /* IFU_IFETCH */ + [ C(RESULT_MISS) ] = 0x0085, /* ITLB_MISS */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(BPU ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED */ + [ C(RESULT_MISS) ] = 0x00c5, /* BR_MISS_PRED_RETIRED */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, }; static u64 p6_pmu_event_map(int hw_event) @@ -34,7 +127,7 @@ static struct event_constraint p6_event_constraints[] = { INTEL_EVENT_CONSTRAINT(0xc1, 0x1), /* FLOPS */ INTEL_EVENT_CONSTRAINT(0x10, 0x1), /* FP_COMP_OPS_EXE */ - INTEL_EVENT_CONSTRAINT(0x11, 0x1), /* FP_ASSIST */ + INTEL_EVENT_CONSTRAINT(0x11, 0x2), /* FP_ASSIST */ INTEL_EVENT_CONSTRAINT(0x12, 0x2), /* MUL */ INTEL_EVENT_CONSTRAINT(0x13, 0x2), /* DIV */ INTEL_EVENT_CONSTRAINT(0x14, 0x1), /* CYCLES_DIV_BUSY */ @@ -64,25 +157,25 @@ static void p6_pmu_enable_all(int added) static inline void p6_pmu_disable_event(struct perf_event *event) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct hw_perf_event *hwc = &event->hw; u64 val = P6_NOP_EVENT; - if (cpuc->enabled) - val |= ARCH_PERFMON_EVENTSEL_ENABLE; - (void)wrmsrl_safe(hwc->config_base, val); } static void p6_pmu_enable_event(struct perf_event *event) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct hw_perf_event *hwc = &event->hw; u64 val; val = hwc->config; - if (cpuc->enabled) - val |= ARCH_PERFMON_EVENTSEL_ENABLE; + + /* + * p6 only has a global event enable, set on PerfEvtSel0 + * We "disable" events by programming P6_NOP_EVENT + * and we rely on p6_pmu_enable_all() being called + * to actually enable the events. + */ (void)wrmsrl_safe(hwc->config_base, val); } @@ -158,5 +251,9 @@ __init int p6_pmu_init(void) 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/e820.c b/arch/x86/kernel/e820.c index ed858e9e9a74..df06ade26bef 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1077,6 +1077,9 @@ void __init memblock_x86_fill(void) memblock_add(ei->addr, ei->size); } + /* throw away partial pages */ + memblock_trim_memory(PAGE_SIZE); + memblock_dump_all(); } diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index a1193aef6d7d..88b725aa1d52 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -1035,7 +1035,7 @@ ENTRY(xen_sysenter_target) ENTRY(xen_hypervisor_callback) CFI_STARTPROC - pushl_cfi $0 + pushl_cfi $-1 /* orig_ax = -1 => not a system call */ SAVE_ALL TRACE_IRQS_OFF @@ -1077,14 +1077,16 @@ ENTRY(xen_failsafe_callback) 2: mov 8(%esp),%es 3: mov 12(%esp),%fs 4: mov 16(%esp),%gs + /* EAX == 0 => Category 1 (Bad segment) + EAX != 0 => Category 2 (Bad IRET) */ testl %eax,%eax popl_cfi %eax lea 16(%esp),%esp CFI_ADJUST_CFA_OFFSET -16 jz 5f addl $16,%esp - jmp iret_exc # EAX != 0 => Category 2 (Bad IRET) -5: pushl_cfi $0 # EAX == 0 => Category 1 (Bad segment) + jmp iret_exc +5: pushl_cfi $-1 /* orig_ax = -1 => not a system call */ SAVE_ALL jmp ret_from_exception CFI_ENDPROC diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 0c58952d64e8..b51b2c7ee51f 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -1435,7 +1435,7 @@ ENTRY(xen_failsafe_callback) CFI_RESTORE r11 addq $0x30,%rsp CFI_ADJUST_CFA_OFFSET -0x30 - pushq_cfi $0 + pushq_cfi $-1 /* orig_ax = -1 => not a system call */ SAVE_ALL jmp error_exit CFI_ENDPROC diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index b3e5e51bc907..4180a874c764 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -247,7 +247,10 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code) break; case KVM_PV_REASON_PAGE_NOT_PRESENT: /* page is swapped out by the host. */ + rcu_irq_enter(); + exit_idle(); kvm_async_pf_task_wait((u32)read_cr2()); + rcu_irq_exit(); break; case KVM_PV_REASON_PAGE_READY: rcu_irq_enter(); diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 52190a938b4a..4e8ba39eaf0f 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -358,14 +358,6 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "VGN-Z540N"), }, }, - { /* Handle problems with rebooting on CompuLab SBC-FITPC2 */ - .callback = set_bios_reboot, - .ident = "CompuLab SBC-FITPC2", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "CompuLab"), - DMI_MATCH(DMI_PRODUCT_NAME, "SBC-FITPC2"), - }, - }, { /* Handle problems with rebooting on ASUS P4S800 */ .callback = set_bios_reboot, .ident = "ASUS P4S800", diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index a2bb18e02839..ca45696f30fb 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -920,8 +920,22 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_X86_64 if (max_pfn > max_low_pfn) { - max_pfn_mapped = init_memory_mapping(1UL<<32, - max_pfn<<PAGE_SHIFT); + int i; + unsigned long start, end; + unsigned long start_pfn, end_pfn; + + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, + NULL) { + + end = PFN_PHYS(end_pfn); + if (end <= (1UL<<32)) + continue; + + start = PFN_PHYS(start_pfn); + max_pfn_mapped = init_memory_mapping( + max((1UL<<32), start), end); + } + /* can we preseve max_low_pfn ?*/ max_low_pfn = max_pfn; } @@ -1035,6 +1049,18 @@ void __init setup_arch(char **cmdline_p) arch_init_ideal_nops(); register_refined_jiffies(CLOCK_TICK_RATE); + +#ifdef CONFIG_EFI + /* Once setup is done above, disable efi_enabled on mismatched + * firmware/kernel archtectures since there is no support for + * runtime services. + */ + if (efi_enabled && IS_ENABLED(CONFIG_X86_64) != efi_64bit) { + pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n"); + efi_unmap_memmap(); + efi_enabled = 0; + } +#endif } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 29ad351804e9..70b27ee6118e 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -824,10 +824,8 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags) mce_notify_process(); #endif /* CONFIG_X86_64 && CONFIG_X86_MCE */ - if (thread_info_flags & _TIF_UPROBE) { - clear_thread_flag(TIF_UPROBE); + if (thread_info_flags & _TIF_UPROBE) uprobe_notify_resume(regs); - } /* deal with pending signal delivery */ if (thread_info_flags & _TIF_SIGPENDING) diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 9538f00827a9..aafa5557b396 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -651,31 +651,19 @@ void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) /* * Skip these instructions as per the currently known x86 ISA. - * 0x66* { 0x90 | 0x0f 0x1f | 0x0f 0x19 | 0x87 0xc0 } + * rep=0x66*; nop=0x90 */ static bool __skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) { int i; for (i = 0; i < MAX_UINSN_BYTES; i++) { - if ((auprobe->insn[i] == 0x66)) + if (auprobe->insn[i] == 0x66) continue; if (auprobe->insn[i] == 0x90) return true; - if (i == (MAX_UINSN_BYTES - 1)) - break; - - if ((auprobe->insn[i] == 0x0f) && (auprobe->insn[i+1] == 0x1f)) - return true; - - if ((auprobe->insn[i] == 0x0f) && (auprobe->insn[i+1] == 0x19)) - return true; - - if ((auprobe->insn[i] == 0x87) && (auprobe->insn[i+1] == 0xc0)) - return true; - break; } return false; |