diff options
Diffstat (limited to 'arch/x86')
28 files changed, 286 insertions, 219 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index ba2657c49217..8ec3a1aa4abd 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1527,7 +1527,7 @@ config SECCOMP If unsure, say Y. Only embedded should say N here. config CC_STACKPROTECTOR - bool "Enable -fstack-protector buffer overflow detection (EXPERIMENTAL)" + bool "Enable -fstack-protector buffer overflow detection" ---help--- This option turns on the -fstack-protector GCC feature. This feature puts, at the beginning of functions, a canary value on diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 441520e4174f..a3ac52b29cbf 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -33,6 +33,14 @@ #define MCI_STATUS_PCC (1ULL<<57) /* processor context corrupt */ #define MCI_STATUS_S (1ULL<<56) /* Signaled machine check */ #define MCI_STATUS_AR (1ULL<<55) /* Action required */ +#define MCACOD 0xffff /* MCA Error Code */ + +/* Architecturally defined codes from SDM Vol. 3B Chapter 15 */ +#define MCACOD_SCRUB 0x00C0 /* 0xC0-0xCF Memory Scrubbing */ +#define MCACOD_SCRUBMSK 0xfff0 +#define MCACOD_L3WB 0x017A /* L3 Explicit Writeback */ +#define MCACOD_DATA 0x0134 /* Data Load */ +#define MCACOD_INSTR 0x0150 /* Instruction Fetch */ /* MCi_MISC register defines */ #define MCI_MISC_ADDR_LSB(m) ((m) & 0x3f) diff --git a/arch/x86/include/asm/olpc.h b/arch/x86/include/asm/olpc.h index 87bdbca72f94..72f9adf6eca4 100644 --- a/arch/x86/include/asm/olpc.h +++ b/arch/x86/include/asm/olpc.h @@ -100,25 +100,6 @@ extern void olpc_xo1_pm_wakeup_clear(u16 value); extern int pci_olpc_init(void); -/* EC related functions */ - -extern int olpc_ec_cmd(unsigned char cmd, unsigned char *inbuf, size_t inlen, - unsigned char *outbuf, size_t outlen); - -/* EC commands */ - -#define EC_FIRMWARE_REV 0x08 -#define EC_WRITE_SCI_MASK 0x1b -#define EC_WAKE_UP_WLAN 0x24 -#define EC_WLAN_LEAVE_RESET 0x25 -#define EC_READ_EB_MODE 0x2a -#define EC_SET_SCI_INHIBIT 0x32 -#define EC_SET_SCI_INHIBIT_RELEASE 0x34 -#define EC_WLAN_ENTER_RESET 0x35 -#define EC_WRITE_EXT_SCI_MASK 0x38 -#define EC_SCI_QUERY 0x84 -#define EC_EXT_SCI_QUERY 0x85 - /* SCI source values */ #define EC_SCI_SRC_EMPTY 0x00 diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index dab39350e51e..cb4e43bce98a 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -196,11 +196,16 @@ static inline u32 get_ibs_caps(void) { return 0; } extern void perf_events_lapic_init(void); /* - * Abuse bit 3 of the cpu eflags register to indicate proper PEBS IP fixups. - * This flag is otherwise unused and ABI specified to be 0, so nobody should - * care what we do with it. + * Abuse bits {3,5} of the cpu eflags register. These flags are otherwise + * unused and ABI specified to be 0, so nobody should care what we do with + * them. + * + * EXACT - the IP points to the exact instruction that triggered the + * event (HW bugs exempt). + * VM - original X86_VM_MASK; see set_linear_ip(). */ #define PERF_EFLAGS_EXACT (1UL << 3) +#define PERF_EFLAGS_VM (1UL << 5) struct pt_regs; extern unsigned long perf_instruction_pointer(struct pt_regs *regs); diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index 95bf99de9058..1b8e5a03d942 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -25,10 +25,6 @@ unsigned long acpi_realmode_flags; static char temp_stack[4096]; #endif -asmlinkage void acpi_enter_s3(void) -{ - acpi_enter_sleep_state(3, wake_sleep_flags); -} /** * acpi_suspend_lowlevel - save kernel state * diff --git a/arch/x86/kernel/acpi/sleep.h b/arch/x86/kernel/acpi/sleep.h index 5653a5791ec9..67f59f8c6956 100644 --- a/arch/x86/kernel/acpi/sleep.h +++ b/arch/x86/kernel/acpi/sleep.h @@ -2,7 +2,6 @@ * Variables and functions used by the code in sleep.c */ -#include <linux/linkage.h> #include <asm/realmode.h> extern unsigned long saved_video_mode; @@ -11,7 +10,6 @@ extern long saved_magic; extern int wakeup_pmode_return; extern u8 wake_sleep_flags; -extern asmlinkage void acpi_enter_s3(void); extern unsigned long acpi_copy_wakeup_routine(unsigned long); extern void wakeup_long64(void); diff --git a/arch/x86/kernel/acpi/wakeup_32.S b/arch/x86/kernel/acpi/wakeup_32.S index 72610839f03b..13ab720573e3 100644 --- a/arch/x86/kernel/acpi/wakeup_32.S +++ b/arch/x86/kernel/acpi/wakeup_32.S @@ -74,7 +74,9 @@ restore_registers: ENTRY(do_suspend_lowlevel) call save_processor_state call save_registers - call acpi_enter_s3 + pushl $3 + call acpi_enter_sleep_state + addl $4, %esp # In case of S3 failure, we'll emerge here. Jump # to ret_point to recover diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S index 014d1d28c397..8ea5164cbd04 100644 --- a/arch/x86/kernel/acpi/wakeup_64.S +++ b/arch/x86/kernel/acpi/wakeup_64.S @@ -71,7 +71,9 @@ ENTRY(do_suspend_lowlevel) movq %rsi, saved_rsi addq $8, %rsp - call acpi_enter_s3 + movl $3, %edi + xorl %eax, %eax + call acpi_enter_sleep_state /* in case something went wrong, restore the machine status and go on */ jmp resume_point diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 931280ff8299..afb7ff79a29f 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -224,7 +224,7 @@ void __init arch_init_ideal_nops(void) ideal_nops = intel_nops; #endif } - + break; default: #ifdef CONFIG_X86_64 ideal_nops = k8_nops; diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 406eee784684..a6c64aaddf9a 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1204,7 +1204,7 @@ static void __clear_irq_vector(int irq, struct irq_cfg *cfg) BUG_ON(!cfg->vector); vector = cfg->vector; - for_each_cpu(cpu, cfg->domain) + for_each_cpu_and(cpu, cfg->domain, cpu_online_mask) per_cpu(vector_irq, cpu)[vector] = -1; cfg->vector = 0; @@ -1212,7 +1212,7 @@ static void __clear_irq_vector(int irq, struct irq_cfg *cfg) if (likely(!cfg->move_in_progress)) return; - for_each_cpu(cpu, cfg->old_domain) { + for_each_cpu_and(cpu, cfg->old_domain, cpu_online_mask) { for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { if (per_cpu(vector_irq, cpu)[vector] != irq) diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c index 413c2ced887c..13017626f9a8 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-severity.c +++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c @@ -55,13 +55,6 @@ static struct severity { #define MCI_UC_S (MCI_STATUS_UC|MCI_STATUS_S) #define MCI_UC_SAR (MCI_STATUS_UC|MCI_STATUS_S|MCI_STATUS_AR) #define MCI_ADDR (MCI_STATUS_ADDRV|MCI_STATUS_MISCV) -#define MCACOD 0xffff -/* Architecturally defined codes from SDM Vol. 3B Chapter 15 */ -#define MCACOD_SCRUB 0x00C0 /* 0xC0-0xCF Memory Scrubbing */ -#define MCACOD_SCRUBMSK 0xfff0 -#define MCACOD_L3WB 0x017A /* L3 Explicit Writeback */ -#define MCACOD_DATA 0x0134 /* Data Load */ -#define MCACOD_INSTR 0x0150 /* Instruction Fetch */ MCESEV( NO, "Invalid", diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 5e095f873e3e..292d0258311c 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -103,6 +103,8 @@ DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = { static DEFINE_PER_CPU(struct work_struct, mce_work); +static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs); + /* * CPU/chipset specific EDAC code can register a notifier call here to print * MCE errors in a human-readable form. @@ -650,14 +652,18 @@ EXPORT_SYMBOL_GPL(machine_check_poll); * Do a quick check if any of the events requires a panic. * This decides if we keep the events around or clear them. */ -static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp) +static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, + struct pt_regs *regs) { int i, ret = 0; for (i = 0; i < banks; i++) { m->status = mce_rdmsrl(MSR_IA32_MCx_STATUS(i)); - if (m->status & MCI_STATUS_VAL) + if (m->status & MCI_STATUS_VAL) { __set_bit(i, validp); + if (quirk_no_way_out) + quirk_no_way_out(i, m, regs); + } if (mce_severity(m, tolerant, msg) >= MCE_PANIC_SEVERITY) ret = 1; } @@ -1040,7 +1046,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) *final = m; memset(valid_banks, 0, sizeof(valid_banks)); - no_way_out = mce_no_way_out(&m, &msg, valid_banks); + no_way_out = mce_no_way_out(&m, &msg, valid_banks, regs); barrier(); @@ -1418,6 +1424,34 @@ static void __mcheck_cpu_init_generic(void) } } +/* + * During IFU recovery Sandy Bridge -EP4S processors set the RIPV and + * EIPV bits in MCG_STATUS to zero on the affected logical processor (SDM + * Vol 3B Table 15-20). But this confuses both the code that determines + * whether the machine check occurred in kernel or user mode, and also + * the severity assessment code. Pretend that EIPV was set, and take the + * ip/cs values from the pt_regs that mce_gather_info() ignored earlier. + */ +static void quirk_sandybridge_ifu(int bank, struct mce *m, struct pt_regs *regs) +{ + if (bank != 0) + return; + if ((m->mcgstatus & (MCG_STATUS_EIPV|MCG_STATUS_RIPV)) != 0) + return; + if ((m->status & (MCI_STATUS_OVER|MCI_STATUS_UC| + MCI_STATUS_EN|MCI_STATUS_MISCV|MCI_STATUS_ADDRV| + MCI_STATUS_PCC|MCI_STATUS_S|MCI_STATUS_AR| + MCACOD)) != + (MCI_STATUS_UC|MCI_STATUS_EN| + MCI_STATUS_MISCV|MCI_STATUS_ADDRV|MCI_STATUS_S| + MCI_STATUS_AR|MCACOD_INSTR)) + return; + + m->mcgstatus |= MCG_STATUS_EIPV; + m->ip = regs->ip; + m->cs = regs->cs; +} + /* Add per CPU specific workarounds here */ static int __cpuinit __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) { @@ -1515,6 +1549,9 @@ static int __cpuinit __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) */ if (c->x86 == 6 && c->x86_model <= 13 && mce_bootlog < 0) mce_bootlog = 0; + + if (c->x86 == 6 && c->x86_model == 45) + quirk_no_way_out = quirk_sandybridge_ifu; } if (monarch_timeout < 0) monarch_timeout = 0; diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 29557aa06dda..915b876edd1e 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -32,6 +32,8 @@ #include <asm/smp.h> #include <asm/alternative.h> #include <asm/timer.h> +#include <asm/desc.h> +#include <asm/ldt.h> #include "perf_event.h" @@ -1738,6 +1740,29 @@ valid_user_frame(const void __user *fp, unsigned long size) return (__range_not_ok(fp, size, TASK_SIZE) == 0); } +static unsigned long get_segment_base(unsigned int segment) +{ + struct desc_struct *desc; + int idx = segment >> 3; + + if ((segment & SEGMENT_TI_MASK) == SEGMENT_LDT) { + if (idx > LDT_ENTRIES) + return 0; + + if (idx > current->active_mm->context.size) + return 0; + + desc = current->active_mm->context.ldt; + } else { + if (idx > GDT_ENTRIES) + return 0; + + desc = __this_cpu_ptr(&gdt_page.gdt[0]); + } + + return get_desc_base(desc + idx); +} + #ifdef CONFIG_COMPAT #include <asm/compat.h> @@ -1746,13 +1771,17 @@ static inline int perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry) { /* 32-bit process in 64-bit kernel. */ + unsigned long ss_base, cs_base; struct stack_frame_ia32 frame; const void __user *fp; if (!test_thread_flag(TIF_IA32)) return 0; - fp = compat_ptr(regs->bp); + cs_base = get_segment_base(regs->cs); + ss_base = get_segment_base(regs->ss); + + fp = compat_ptr(ss_base + regs->bp); while (entry->nr < PERF_MAX_STACK_DEPTH) { unsigned long bytes; frame.next_frame = 0; @@ -1765,8 +1794,8 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry) if (!valid_user_frame(fp, sizeof(frame))) break; - perf_callchain_store(entry, frame.return_address); - fp = compat_ptr(frame.next_frame); + perf_callchain_store(entry, cs_base + frame.return_address); + fp = compat_ptr(ss_base + frame.next_frame); } return 1; } @@ -1789,6 +1818,12 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) return; } + /* + * We don't know what to do with VM86 stacks.. ignore them for now. + */ + if (regs->flags & (X86_VM_MASK | PERF_EFLAGS_VM)) + return; + fp = (void __user *)regs->bp; perf_callchain_store(entry, regs->ip); @@ -1816,16 +1851,50 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) } } -unsigned long perf_instruction_pointer(struct pt_regs *regs) +/* + * Deal with code segment offsets for the various execution modes: + * + * VM86 - the good olde 16 bit days, where the linear address is + * 20 bits and we use regs->ip + 0x10 * regs->cs. + * + * IA32 - Where we need to look at GDT/LDT segment descriptor tables + * to figure out what the 32bit base address is. + * + * X32 - has TIF_X32 set, but is running in x86_64 + * + * X86_64 - CS,DS,SS,ES are all zero based. + */ +static unsigned long code_segment_base(struct pt_regs *regs) { - unsigned long ip; + /* + * If we are in VM86 mode, add the segment offset to convert to a + * linear address. + */ + if (regs->flags & X86_VM_MASK) + return 0x10 * regs->cs; + + /* + * For IA32 we look at the GDT/LDT segment base to convert the + * effective IP to a linear address. + */ +#ifdef CONFIG_X86_32 + if (user_mode(regs) && regs->cs != __USER_CS) + return get_segment_base(regs->cs); +#else + if (test_thread_flag(TIF_IA32)) { + if (user_mode(regs) && regs->cs != __USER32_CS) + return get_segment_base(regs->cs); + } +#endif + return 0; +} +unsigned long perf_instruction_pointer(struct pt_regs *regs) +{ if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) - ip = perf_guest_cbs->get_guest_ip(); - else - ip = instruction_pointer(regs); + return perf_guest_cbs->get_guest_ip(); - return ip; + return regs->ip + code_segment_base(regs); } unsigned long perf_misc_flags(struct pt_regs *regs) @@ -1838,7 +1907,7 @@ unsigned long perf_misc_flags(struct pt_regs *regs) else misc |= PERF_RECORD_MISC_GUEST_KERNEL; } else { - if (!kernel_ip(regs->ip)) + if (user_mode(regs)) misc |= PERF_RECORD_MISC_USER; else misc |= PERF_RECORD_MISC_KERNEL; diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index 821d53b696d1..6605a81ba339 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -516,6 +516,26 @@ static inline bool kernel_ip(unsigned long ip) #endif } +/* + * Not all PMUs provide the right context information to place the reported IP + * into full context. Specifically segment registers are typically not + * supplied. + * + * Assuming the address is a linear address (it is for IBS), we fake the CS and + * vm86 mode using the known zero-based code segment and 'fix up' the registers + * to reflect this. + * + * Intel PEBS/LBR appear to typically provide the effective address, nothing + * much we can do about that but pray and treat it like a linear address. + */ +static inline void set_linear_ip(struct pt_regs *regs, unsigned long ip) +{ + regs->cs = kernel_ip(ip) ? __KERNEL_CS : __USER_CS; + if (regs->flags & X86_VM_MASK) + regs->flags ^= (PERF_EFLAGS_VM | X86_VM_MASK); + regs->ip = ip; +} + #ifdef CONFIG_CPU_SUP_AMD int amd_pmu_init(void); diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c index da9bcdcd9856..7bfb5bec8630 100644 --- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c +++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c @@ -13,6 +13,8 @@ #include <asm/apic.h> +#include "perf_event.h" + static u32 ibs_caps; #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_AMD) @@ -536,7 +538,7 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs) if (check_rip && (ibs_data.regs[2] & IBS_RIP_INVALID)) { regs.flags &= ~PERF_EFLAGS_EXACT; } else { - instruction_pointer_set(®s, ibs_data.regs[1]); + set_linear_ip(®s, ibs_data.regs[1]); regs.flags |= PERF_EFLAGS_EXACT; } diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 629ae0b7ad90..e38d97bf4259 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -499,7 +499,7 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs) * We sampled a branch insn, rewind using the LBR stack */ if (ip == to) { - regs->ip = from; + set_linear_ip(regs, from); return 1; } @@ -529,7 +529,7 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs) } while (to < ip); if (to == ip) { - regs->ip = old_to; + set_linear_ip(regs, old_to); return 1; } @@ -569,7 +569,8 @@ static void __intel_pmu_pebs_event(struct perf_event *event, * A possible PERF_SAMPLE_REGS will have to transfer all regs. */ regs = *iregs; - regs.ip = pebs->ip; + regs.flags = pebs->flags; + set_linear_ip(®s, pebs->ip); regs.bp = pebs->bp; regs.sp = pebs->sp; diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h index f3851892e077..c9e5dc56630a 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h @@ -5,7 +5,7 @@ #include "perf_event.h" #define UNCORE_PMU_NAME_LEN 32 -#define UNCORE_PMU_HRTIMER_INTERVAL (60 * NSEC_PER_SEC) +#define UNCORE_PMU_HRTIMER_INTERVAL (60LL * NSEC_PER_SEC) #define UNCORE_FIXED_EVENT 0xff #define UNCORE_PMC_IDX_MAX_GENERIC 8 diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 1f5f1d5d2a02..7ad683d78645 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -328,6 +328,7 @@ void fixup_irqs(void) chip->irq_retrigger(data); raw_spin_unlock(&desc->lock); } + __this_cpu_write(vector_irq[vector], -1); } } #endif diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c index 1d5d31ea686b..dc1404bf8e4b 100644 --- a/arch/x86/kernel/kdebugfs.c +++ b/arch/x86/kernel/kdebugfs.c @@ -107,7 +107,7 @@ static int __init create_setup_data_nodes(struct dentry *parent) { struct setup_data_node *node; struct setup_data *data; - int error = -ENOMEM; + int error; struct dentry *d; struct page *pg; u64 pa_data; @@ -121,8 +121,10 @@ static int __init create_setup_data_nodes(struct dentry *parent) while (pa_data) { node = kmalloc(sizeof(*node), GFP_KERNEL); - if (!node) + if (!node) { + error = -ENOMEM; goto err_dir; + } pg = pfn_to_page((pa_data+sizeof(*data)-1) >> PAGE_SHIFT); if (PageHighMem(pg)) { diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index 1df8fb9e1d5d..e498b18f010c 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -316,6 +316,11 @@ static void pic_ioport_write(void *opaque, u32 addr, u32 val) addr &= 1; if (addr == 0) { if (val & 0x10) { + u8 edge_irr = s->irr & ~s->elcr; + int i; + bool found; + struct kvm_vcpu *vcpu; + s->init4 = val & 1; s->last_irr = 0; s->irr &= s->elcr; @@ -333,6 +338,18 @@ static void pic_ioport_write(void *opaque, u32 addr, u32 val) if (val & 0x08) pr_pic_unimpl( "level sensitive irq not supported"); + + kvm_for_each_vcpu(i, vcpu, s->pics_state->kvm) + if (kvm_apic_accept_pic_intr(vcpu)) { + found = true; + break; + } + + + if (found) + for (irq = 0; irq < PIC_NUM_PINS/2; irq++) + if (edge_irr & (1 << irq)) + pic_clear_isr(s, irq); } else if (val & 0x08) { if (val & 0x04) s->poll = 1; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index c39b60707e02..c00f03de1b79 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -1488,13 +1488,6 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx) loadsegment(ds, vmx->host_state.ds_sel); loadsegment(es, vmx->host_state.es_sel); } -#else - /* - * The sysexit path does not restore ds/es, so we must set them to - * a reasonable value ourselves. - */ - loadsegment(ds, __USER_DS); - loadsegment(es, __USER_DS); #endif reload_tss(); #ifdef CONFIG_X86_64 @@ -6370,6 +6363,19 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) #endif ); +#ifndef CONFIG_X86_64 + /* + * The sysexit path does not restore ds/es, so we must set them to + * a reasonable value ourselves. + * + * We can't defer this to vmx_load_host_state() since that function + * may be executed in interrupt context, which saves and restore segments + * around it, nullifying its effect. + */ + loadsegment(ds, __USER_DS); + loadsegment(es, __USER_DS); +#endif + vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP) | (1 << VCPU_EXREG_RFLAGS) | (1 << VCPU_EXREG_CPL) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 59b59508ff07..42bce48f6928 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -925,6 +925,10 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock) */ getboottime(&boot); + if (kvm->arch.kvmclock_offset) { + struct timespec ts = ns_to_timespec(kvm->arch.kvmclock_offset); + boot = timespec_sub(boot, ts); + } wc.sec = boot.tv_sec; wc.nsec = boot.tv_nsec; wc.version = version; diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c index 4599c3e8bcb6..4ddf497ca65b 100644 --- a/arch/x86/mm/srat.c +++ b/arch/x86/mm/srat.c @@ -142,23 +142,23 @@ static inline int save_add_info(void) {return 0;} #endif /* Callback for parsing of the Proximity Domain <-> Memory Area mappings */ -void __init +int __init acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) { u64 start, end; int node, pxm; if (srat_disabled()) - return; + return -1; if (ma->header.length != sizeof(struct acpi_srat_mem_affinity)) { bad_srat(); - return; + return -1; } if ((ma->flags & ACPI_SRAT_MEM_ENABLED) == 0) - return; + return -1; if ((ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) && !save_add_info()) - return; + return -1; start = ma->base_address; end = start + ma->length; pxm = ma->proximity_domain; @@ -168,12 +168,12 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) if (node < 0) { printk(KERN_ERR "SRAT: Too many proximity domains.\n"); bad_srat(); - return; + return -1; } if (numa_add_memblk(node, start, end) < 0) { bad_srat(); - return; + return -1; } node_set(node, numa_nodes_parsed); @@ -181,6 +181,7 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) printk(KERN_INFO "SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]\n", node, pxm, (unsigned long long) start, (unsigned long long) end - 1); + return 0; } void __init acpi_numa_arch_fixup(void) {} diff --git a/arch/x86/platform/olpc/olpc-xo1-pm.c b/arch/x86/platform/olpc/olpc-xo1-pm.c index 0ce8616c88ae..d75582d1aa55 100644 --- a/arch/x86/platform/olpc/olpc-xo1-pm.c +++ b/arch/x86/platform/olpc/olpc-xo1-pm.c @@ -18,6 +18,7 @@ #include <linux/pm.h> #include <linux/mfd/core.h> #include <linux/suspend.h> +#include <linux/olpc-ec.h> #include <asm/io.h> #include <asm/olpc.h> @@ -51,16 +52,11 @@ EXPORT_SYMBOL_GPL(olpc_xo1_pm_wakeup_clear); static int xo1_power_state_enter(suspend_state_t pm_state) { unsigned long saved_sci_mask; - int r; /* Only STR is supported */ if (pm_state != PM_SUSPEND_MEM) return -EINVAL; - r = olpc_ec_cmd(EC_SET_SCI_INHIBIT, NULL, 0, NULL, 0); - if (r) - return r; - /* * Save SCI mask (this gets lost since PM1_EN is used as a mask for * wakeup events, which is not necessarily the same event set) @@ -76,16 +72,6 @@ static int xo1_power_state_enter(suspend_state_t pm_state) /* Restore SCI mask (using dword access to CS5536_PM1_EN) */ outl(saved_sci_mask, acpi_base + CS5536_PM1_STS); - /* Tell the EC to stop inhibiting SCIs */ - olpc_ec_cmd(EC_SET_SCI_INHIBIT_RELEASE, NULL, 0, NULL, 0); - - /* - * Tell the wireless module to restart USB communication. - * Must be done twice. - */ - olpc_ec_cmd(EC_WAKE_UP_WLAN, NULL, 0, NULL, 0); - olpc_ec_cmd(EC_WAKE_UP_WLAN, NULL, 0, NULL, 0); - return 0; } diff --git a/arch/x86/platform/olpc/olpc-xo1-sci.c b/arch/x86/platform/olpc/olpc-xo1-sci.c index 04b8c73659c5..63d4aa40956e 100644 --- a/arch/x86/platform/olpc/olpc-xo1-sci.c +++ b/arch/x86/platform/olpc/olpc-xo1-sci.c @@ -23,6 +23,7 @@ #include <linux/power_supply.h> #include <linux/suspend.h> #include <linux/workqueue.h> +#include <linux/olpc-ec.h> #include <asm/io.h> #include <asm/msr.h> diff --git a/arch/x86/platform/olpc/olpc-xo15-sci.c b/arch/x86/platform/olpc/olpc-xo15-sci.c index 599be499fdf7..2fdca25905ae 100644 --- a/arch/x86/platform/olpc/olpc-xo15-sci.c +++ b/arch/x86/platform/olpc/olpc-xo15-sci.c @@ -13,6 +13,7 @@ #include <linux/slab.h> #include <linux/workqueue.h> #include <linux/power_supply.h> +#include <linux/olpc-ec.h> #include <acpi/acpi_bus.h> #include <acpi/acpi_drivers.h> diff --git a/arch/x86/platform/olpc/olpc.c b/arch/x86/platform/olpc/olpc.c index a4bee53c2e54..27376081ddec 100644 --- a/arch/x86/platform/olpc/olpc.c +++ b/arch/x86/platform/olpc/olpc.c @@ -14,14 +14,13 @@ #include <linux/init.h> #include <linux/module.h> #include <linux/delay.h> -#include <linux/spinlock.h> #include <linux/io.h> #include <linux/string.h> #include <linux/platform_device.h> #include <linux/of.h> #include <linux/syscore_ops.h> -#include <linux/debugfs.h> #include <linux/mutex.h> +#include <linux/olpc-ec.h> #include <asm/geode.h> #include <asm/setup.h> @@ -31,17 +30,6 @@ struct olpc_platform_t olpc_platform_info; EXPORT_SYMBOL_GPL(olpc_platform_info); -static DEFINE_SPINLOCK(ec_lock); - -/* debugfs interface to EC commands */ -#define EC_MAX_CMD_ARGS (5 + 1) /* cmd byte + 5 args */ -#define EC_MAX_CMD_REPLY (8) - -static struct dentry *ec_debugfs_dir; -static DEFINE_MUTEX(ec_debugfs_cmd_lock); -static unsigned char ec_debugfs_resp[EC_MAX_CMD_REPLY]; -static unsigned int ec_debugfs_resp_bytes; - /* EC event mask to be applied during suspend (defining wakeup sources). */ static u16 ec_wakeup_mask; @@ -125,16 +113,13 @@ static int __wait_on_obf(unsigned int line, unsigned int port, int desired) * <http://wiki.laptop.org/go/Ec_specification>. Unfortunately, while * OpenFirmware's source is available, the EC's is not. */ -int olpc_ec_cmd(unsigned char cmd, unsigned char *inbuf, size_t inlen, - unsigned char *outbuf, size_t outlen) +static int olpc_xo1_ec_cmd(u8 cmd, u8 *inbuf, size_t inlen, u8 *outbuf, + size_t outlen, void *arg) { - unsigned long flags; int ret = -EIO; int i; int restarts = 0; - spin_lock_irqsave(&ec_lock, flags); - /* Clear OBF */ for (i = 0; i < 10 && (obf_status(0x6c) == 1); i++) inb(0x68); @@ -198,10 +183,8 @@ restart: ret = 0; err: - spin_unlock_irqrestore(&ec_lock, flags); return ret; } -EXPORT_SYMBOL_GPL(olpc_ec_cmd); void olpc_ec_wakeup_set(u16 value) { @@ -280,96 +263,6 @@ int olpc_ec_sci_query(u16 *sci_value) } EXPORT_SYMBOL_GPL(olpc_ec_sci_query); -static ssize_t ec_debugfs_cmd_write(struct file *file, const char __user *buf, - size_t size, loff_t *ppos) -{ - int i, m; - unsigned char ec_cmd[EC_MAX_CMD_ARGS]; - unsigned int ec_cmd_int[EC_MAX_CMD_ARGS]; - char cmdbuf[64]; - int ec_cmd_bytes; - - mutex_lock(&ec_debugfs_cmd_lock); - - size = simple_write_to_buffer(cmdbuf, sizeof(cmdbuf), ppos, buf, size); - - m = sscanf(cmdbuf, "%x:%u %x %x %x %x %x", &ec_cmd_int[0], - &ec_debugfs_resp_bytes, - &ec_cmd_int[1], &ec_cmd_int[2], &ec_cmd_int[3], - &ec_cmd_int[4], &ec_cmd_int[5]); - if (m < 2 || ec_debugfs_resp_bytes > EC_MAX_CMD_REPLY) { - /* reset to prevent overflow on read */ - ec_debugfs_resp_bytes = 0; - - printk(KERN_DEBUG "olpc-ec: bad ec cmd: " - "cmd:response-count [arg1 [arg2 ...]]\n"); - size = -EINVAL; - goto out; - } - - /* convert scanf'd ints to char */ - ec_cmd_bytes = m - 2; - for (i = 0; i <= ec_cmd_bytes; i++) - ec_cmd[i] = ec_cmd_int[i]; - - printk(KERN_DEBUG "olpc-ec: debugfs cmd 0x%02x with %d args " - "%02x %02x %02x %02x %02x, want %d returns\n", - ec_cmd[0], ec_cmd_bytes, ec_cmd[1], ec_cmd[2], ec_cmd[3], - ec_cmd[4], ec_cmd[5], ec_debugfs_resp_bytes); - - olpc_ec_cmd(ec_cmd[0], (ec_cmd_bytes == 0) ? NULL : &ec_cmd[1], - ec_cmd_bytes, ec_debugfs_resp, ec_debugfs_resp_bytes); - - printk(KERN_DEBUG "olpc-ec: response " - "%02x %02x %02x %02x %02x %02x %02x %02x (%d bytes expected)\n", - ec_debugfs_resp[0], ec_debugfs_resp[1], ec_debugfs_resp[2], - ec_debugfs_resp[3], ec_debugfs_resp[4], ec_debugfs_resp[5], - ec_debugfs_resp[6], ec_debugfs_resp[7], ec_debugfs_resp_bytes); - -out: - mutex_unlock(&ec_debugfs_cmd_lock); - return size; -} - -static ssize_t ec_debugfs_cmd_read(struct file *file, char __user *buf, - size_t size, loff_t *ppos) -{ - unsigned int i, r; - char *rp; - char respbuf[64]; - - mutex_lock(&ec_debugfs_cmd_lock); - rp = respbuf; - rp += sprintf(rp, "%02x", ec_debugfs_resp[0]); - for (i = 1; i < ec_debugfs_resp_bytes; i++) - rp += sprintf(rp, ", %02x", ec_debugfs_resp[i]); - mutex_unlock(&ec_debugfs_cmd_lock); - rp += sprintf(rp, "\n"); - - r = rp - respbuf; - return simple_read_from_buffer(buf, size, ppos, respbuf, r); -} - -static const struct file_operations ec_debugfs_genops = { - .write = ec_debugfs_cmd_write, - .read = ec_debugfs_cmd_read, -}; - -static void setup_debugfs(void) -{ - ec_debugfs_dir = debugfs_create_dir("olpc-ec", 0); - if (ec_debugfs_dir == ERR_PTR(-ENODEV)) - return; - - debugfs_create_file("cmd", 0600, ec_debugfs_dir, NULL, - &ec_debugfs_genops); -} - -static int olpc_ec_suspend(void) -{ - return olpc_ec_mask_write(ec_wakeup_mask); -} - static bool __init check_ofw_architecture(struct device_node *root) { const char *olpc_arch; @@ -424,8 +317,59 @@ static int __init add_xo1_platform_devices(void) return 0; } -static struct syscore_ops olpc_syscore_ops = { - .suspend = olpc_ec_suspend, +static int olpc_xo1_ec_probe(struct platform_device *pdev) +{ + /* get the EC revision */ + olpc_ec_cmd(EC_FIRMWARE_REV, NULL, 0, + (unsigned char *) &olpc_platform_info.ecver, 1); + + /* EC version 0x5f adds support for wide SCI mask */ + if (olpc_platform_info.ecver >= 0x5f) + olpc_platform_info.flags |= OLPC_F_EC_WIDE_SCI; + + pr_info("OLPC board revision %s%X (EC=%x)\n", + ((olpc_platform_info.boardrev & 0xf) < 8) ? "pre" : "", + olpc_platform_info.boardrev >> 4, + olpc_platform_info.ecver); + + return 0; +} +static int olpc_xo1_ec_suspend(struct platform_device *pdev) +{ + olpc_ec_mask_write(ec_wakeup_mask); + + /* + * Squelch SCIs while suspended. This is a fix for + * <http://dev.laptop.org/ticket/1835>. + */ + return olpc_ec_cmd(EC_SET_SCI_INHIBIT, NULL, 0, NULL, 0); +} + +static int olpc_xo1_ec_resume(struct platform_device *pdev) +{ + /* Tell the EC to stop inhibiting SCIs */ + olpc_ec_cmd(EC_SET_SCI_INHIBIT_RELEASE, NULL, 0, NULL, 0); + + /* + * Tell the wireless module to restart USB communication. + * Must be done twice. + */ + olpc_ec_cmd(EC_WAKE_UP_WLAN, NULL, 0, NULL, 0); + olpc_ec_cmd(EC_WAKE_UP_WLAN, NULL, 0, NULL, 0); + + return 0; +} + +static struct olpc_ec_driver ec_xo1_driver = { + .probe = olpc_xo1_ec_probe, + .suspend = olpc_xo1_ec_suspend, + .resume = olpc_xo1_ec_resume, + .ec_cmd = olpc_xo1_ec_cmd, +}; + +static struct olpc_ec_driver ec_xo1_5_driver = { + .probe = olpc_xo1_ec_probe, + .ec_cmd = olpc_xo1_ec_cmd, }; static int __init olpc_init(void) @@ -435,16 +379,17 @@ static int __init olpc_init(void) if (!olpc_ofw_present() || !platform_detect()) return 0; - spin_lock_init(&ec_lock); + /* register the XO-1 and 1.5-specific EC handler */ + if (olpc_platform_info.boardrev < olpc_board_pre(0xd0)) /* XO-1 */ + olpc_ec_driver_register(&ec_xo1_driver, NULL); + else + olpc_ec_driver_register(&ec_xo1_5_driver, NULL); + platform_device_register_simple("olpc-ec", -1, NULL, 0); /* assume B1 and above models always have a DCON */ if (olpc_board_at_least(olpc_board(0xb1))) olpc_platform_info.flags |= OLPC_F_DCON; - /* get the EC revision */ - olpc_ec_cmd(EC_FIRMWARE_REV, NULL, 0, - (unsigned char *) &olpc_platform_info.ecver, 1); - #ifdef CONFIG_PCI_OLPC /* If the VSA exists let it emulate PCI, if not emulate in kernel. * XO-1 only. */ @@ -452,14 +397,6 @@ static int __init olpc_init(void) !cs5535_has_vsa2()) x86_init.pci.arch_init = pci_olpc_init; #endif - /* EC version 0x5f adds support for wide SCI mask */ - if (olpc_platform_info.ecver >= 0x5f) - olpc_platform_info.flags |= OLPC_F_EC_WIDE_SCI; - - printk(KERN_INFO "OLPC board revision %s%X (EC=%x)\n", - ((olpc_platform_info.boardrev & 0xf) < 8) ? "pre" : "", - olpc_platform_info.boardrev >> 4, - olpc_platform_info.ecver); if (olpc_platform_info.boardrev < olpc_board_pre(0xd0)) { /* XO-1 */ r = add_xo1_platform_devices(); @@ -467,9 +404,6 @@ static int __init olpc_init(void) return r; } - register_syscore_ops(&olpc_syscore_ops); - setup_debugfs(); - return 0; } diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl index 51171aeff0dc..29aed7ac2c02 100644 --- a/arch/x86/syscalls/syscall_64.tbl +++ b/arch/x86/syscalls/syscall_64.tbl @@ -318,7 +318,7 @@ 309 common getcpu sys_getcpu 310 64 process_vm_readv sys_process_vm_readv 311 64 process_vm_writev sys_process_vm_writev -312 64 kcmp sys_kcmp +312 common kcmp sys_kcmp # # x32-specific system call numbers start at 512 to avoid cache impact |