diff options
Diffstat (limited to 'arch/x86')
54 files changed, 435 insertions, 252 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 940e50ebfafa..0af5250d914f 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -444,6 +444,7 @@ config X86_INTEL_MID bool "Intel MID platform support" depends on X86_32 depends on X86_EXTENDED_PLATFORM + depends on X86_PLATFORM_DEVICES depends on PCI depends on PCI_GOANY depends on X86_IO_APIC @@ -1051,9 +1052,9 @@ config MICROCODE_INTEL This options enables microcode patch loading support for Intel processors. - For latest news and information on obtaining all the required - Intel ingredients for this driver, check: - <http://www.urbanmyth.org/microcode/>. + For the current Intel microcode data package go to + <https://downloadcenter.intel.com> and search for + 'Linux Processor Microcode Data File'. config MICROCODE_AMD bool "AMD microcode loading support" diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index 0f3621ed1db6..321a52ccf63a 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -184,6 +184,7 @@ config HAVE_MMIOTRACE_SUPPORT config X86_DECODER_SELFTEST bool "x86 instruction decoder selftest" depends on DEBUG_KERNEL && KPROBES + depends on !COMPILE_TEST ---help--- Perform x86 instruction decoder selftests at build time. This option is useful for checking the sanity of x86 instruction diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 13b22e0f681d..eeda43abed6e 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -11,6 +11,28 @@ else KBUILD_DEFCONFIG := $(ARCH)_defconfig endif +# How to compile the 16-bit code. Note we always compile for -march=i386; +# that way we can complain to the user if the CPU is insufficient. +# +# The -m16 option is supported by GCC >= 4.9 and clang >= 3.5. For +# older versions of GCC, we need to play evil and unreliable tricks to +# attempt to ensure that our asm(".code16gcc") is first in the asm +# output. +CODE16GCC_CFLAGS := -m32 -include $(srctree)/arch/x86/boot/code16gcc.h \ + $(call cc-option, -fno-toplevel-reorder,\ + $(call cc-option, -fno-unit-at-a-time)) +M16_CFLAGS := $(call cc-option, -m16, $(CODE16GCC_CFLAGS)) + +REALMODE_CFLAGS := $(M16_CFLAGS) -g -Os -D__KERNEL__ \ + -DDISABLE_BRANCH_PROFILING \ + -Wall -Wstrict-prototypes -march=i386 -mregparm=3 \ + -fno-strict-aliasing -fomit-frame-pointer -fno-pic \ + -mno-mmx -mno-sse \ + $(call cc-option, -ffreestanding) \ + $(call cc-option, -fno-stack-protector) \ + $(call cc-option, -mpreferred-stack-boundary=2) +export REALMODE_CFLAGS + # BITS is used as extension for files which are available in a 32 bit # and a 64 bit version to simplify shared Makefiles. # e.g.: obj-y += foo_$(BITS).o diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index de7066918005..878df7e88cd4 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -51,20 +51,7 @@ $(obj)/cpustr.h: $(obj)/mkcpustr FORCE # --------------------------------------------------------------------------- -# How to compile the 16-bit code. Note we always compile for -march=i386, -# that way we can complain to the user if the CPU is insufficient. -KBUILD_CFLAGS := $(USERINCLUDE) -m32 -g -Os -D_SETUP -D__KERNEL__ \ - -DDISABLE_BRANCH_PROFILING \ - -Wall -Wstrict-prototypes \ - -march=i386 -mregparm=3 \ - -include $(srctree)/$(src)/code16gcc.h \ - -fno-strict-aliasing -fomit-frame-pointer -fno-pic \ - -mno-mmx -mno-sse \ - $(call cc-option, -ffreestanding) \ - $(call cc-option, -fno-toplevel-reorder,\ - $(call cc-option, -fno-unit-at-a-time)) \ - $(call cc-option, -fno-stack-protector) \ - $(call cc-option, -mpreferred-stack-boundary=2) +KBUILD_CFLAGS := $(USERINCLUDE) $(REALMODE_CFLAGS) -D_SETUP KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__ GCOV_PROFILE := n diff --git a/arch/x86/boot/cpuflags.c b/arch/x86/boot/cpuflags.c index a9fcb7cfb241..431fa5f84537 100644 --- a/arch/x86/boot/cpuflags.c +++ b/arch/x86/boot/cpuflags.c @@ -28,20 +28,35 @@ static int has_fpu(void) return fsw == 0 && (fcw & 0x103f) == 0x003f; } +/* + * For building the 16-bit code we want to explicitly specify 32-bit + * push/pop operations, rather than just saying 'pushf' or 'popf' and + * letting the compiler choose. But this is also included from the + * compressed/ directory where it may be 64-bit code, and thus needs + * to be 'pushfq' or 'popfq' in that case. + */ +#ifdef __x86_64__ +#define PUSHF "pushfq" +#define POPF "popfq" +#else +#define PUSHF "pushfl" +#define POPF "popfl" +#endif + int has_eflag(unsigned long mask) { unsigned long f0, f1; - asm volatile("pushf \n\t" - "pushf \n\t" + asm volatile(PUSHF " \n\t" + PUSHF " \n\t" "pop %0 \n\t" "mov %0,%1 \n\t" "xor %2,%1 \n\t" "push %1 \n\t" - "popf \n\t" - "pushf \n\t" + POPF " \n\t" + PUSHF " \n\t" "pop %1 \n\t" - "popf" + POPF : "=&r" (f0), "=&r" (f1) : "ri" (mask)); diff --git a/arch/x86/boot/video.h b/arch/x86/boot/video.h index ff339c5db311..0bb25491262d 100644 --- a/arch/x86/boot/video.h +++ b/arch/x86/boot/video.h @@ -80,7 +80,7 @@ struct card_info { u16 xmode_n; /* Size of unprobed mode range */ }; -#define __videocard struct card_info __attribute__((section(".videocards"))) +#define __videocard struct card_info __attribute__((used,section(".videocards"))) extern struct card_info video_cards[], video_cards_end[]; int mode_defined(u16 mode); /* video.c */ diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h index a54ee1d054d9..aaac3b2fb746 100644 --- a/arch/x86/include/asm/amd_nb.h +++ b/arch/x86/include/asm/amd_nb.h @@ -19,7 +19,7 @@ extern int amd_cache_northbridges(void); extern void amd_flush_garts(void); extern int amd_numa_init(void); extern int amd_get_subcaches(int); -extern int amd_set_subcaches(int, int); +extern int amd_set_subcaches(int, unsigned long); struct amd_l3_cache { unsigned indices; diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h index 1df115909758..c7678e43465b 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -85,28 +85,9 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1, return ret; } -static inline uint32_t kvm_cpuid_base(void) -{ - if (boot_cpu_data.cpuid_level < 0) - return 0; /* So we don't blow up on old processors */ - - if (cpu_has_hypervisor) - return hypervisor_cpuid_base("KVMKVMKVM\0\0\0", 0); - - return 0; -} - -static inline bool kvm_para_available(void) -{ - return kvm_cpuid_base() != 0; -} - -static inline unsigned int kvm_arch_para_features(void) -{ - return cpuid_eax(KVM_CPUID_FEATURES); -} - #ifdef CONFIG_KVM_GUEST +bool kvm_para_available(void); +unsigned int kvm_arch_para_features(void); void __init kvm_guest_init(void); void kvm_async_pf_task_wait(u32 token); void kvm_async_pf_task_wake(u32 token); @@ -126,6 +107,16 @@ static inline void kvm_spinlock_init(void) #define kvm_async_pf_task_wait(T) do {} while(0) #define kvm_async_pf_task_wake(T) do {} while(0) +static inline bool kvm_para_available(void) +{ + return 0; +} + +static inline unsigned int kvm_arch_para_features(void) +{ + return 0; +} + static inline u32 kvm_read_and_reset_pf_reason(void) { return 0; diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h index 2f59cce3b38a..f97fbe3abb67 100644 --- a/arch/x86/include/asm/page_types.h +++ b/arch/x86/include/asm/page_types.h @@ -51,9 +51,9 @@ extern int devmem_is_allowed(unsigned long pagenr); extern unsigned long max_low_pfn_mapped; extern unsigned long max_pfn_mapped; -static inline phys_addr_t get_max_low_mapped(void) +static inline phys_addr_t get_max_mapped(void) { - return (phys_addr_t)max_low_pfn_mapped << PAGE_SHIFT; + return (phys_addr_t)max_pfn_mapped << PAGE_SHIFT; } bool pfn_range_is_mapped(unsigned long start_pfn, unsigned long end_pfn); diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 401f350ef71b..cd6e1610e29e 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -781,9 +781,9 @@ static __always_inline void __ticket_unlock_kick(struct arch_spinlock *lock, */ #define PV_CALLEE_SAVE_REGS_THUNK(func) \ extern typeof(func) __raw_callee_save_##func; \ - static void *__##func##__ __used = func; \ \ asm(".pushsection .text;" \ + ".globl __raw_callee_save_" #func " ; " \ "__raw_callee_save_" #func ": " \ PV_SAVE_ALL_CALLER_REGS \ "call " #func ";" \ diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index aab8f671b523..7549b8b369e4 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -388,10 +388,11 @@ extern struct pv_lock_ops pv_lock_ops; _paravirt_alt(insn_string, "%c[paravirt_typenum]", "%c[paravirt_clobber]") /* Simple instruction patching code. */ -#define DEF_NATIVE(ops, name, code) \ - extern const char start_##ops##_##name[] __visible, \ - end_##ops##_##name[] __visible; \ - asm("start_" #ops "_" #name ": " code "; end_" #ops "_" #name ":") +#define NATIVE_LABEL(a,x,b) "\n\t.globl " a #x "_" #b "\n" a #x "_" #b ":\n\t" + +#define DEF_NATIVE(ops, name, code) \ + __visible extern const char start_##ops##_##name[], end_##ops##_##name[]; \ + asm(NATIVE_LABEL("start_", ops, name) code NATIVE_LABEL("end_", ops, name)) unsigned paravirt_patch_nop(void); unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len); diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index a83aa44bb1fb..1aa9ccd43223 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -121,7 +121,8 @@ /* Set of bits not changed in pte_modify */ #define _PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \ - _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY) + _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY | \ + _PAGE_SOFT_DIRTY) #define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE) #define _PAGE_CACHE_MASK (_PAGE_PCD | _PAGE_PWT) diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 3ba3de457d05..e1940c06ed02 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -163,9 +163,11 @@ struct thread_info { */ #ifndef __ASSEMBLY__ - -/* how to get the current stack pointer from C */ -register unsigned long current_stack_pointer asm("esp") __used; +#define current_stack_pointer ({ \ + unsigned long sp; \ + asm("mov %%esp,%0" : "=g" (sp)); \ + sp; \ +}) /* how to get the thread information struct from C */ static inline struct thread_info *current_thread_info(void) diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index e6d90babc245..04905bfc508b 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -62,7 +62,7 @@ static inline void __flush_tlb_all(void) static inline void __flush_tlb_one(unsigned long addr) { - count_vm_event(NR_TLB_LOCAL_FLUSH_ONE); + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE); __flush_tlb_single(addr); } @@ -93,13 +93,13 @@ static inline void __flush_tlb_one(unsigned long addr) */ static inline void __flush_tlb_up(void) { - count_vm_event(NR_TLB_LOCAL_FLUSH_ALL); + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); __flush_tlb(); } static inline void flush_tlb_all(void) { - count_vm_event(NR_TLB_LOCAL_FLUSH_ALL); + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); __flush_tlb_all(); } diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h index 6b964a0b86d1..062921ef34e9 100644 --- a/arch/x86/include/asm/uv/uv.h +++ b/arch/x86/include/asm/uv/uv.h @@ -12,7 +12,6 @@ extern enum uv_system_type get_uv_system_type(void); extern int is_uv_system(void); extern void uv_cpu_init(void); extern void uv_nmi_init(void); -extern void uv_register_nmi_notifier(void); extern void uv_system_init(void); extern const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, struct mm_struct *mm, @@ -26,7 +25,6 @@ static inline enum uv_system_type get_uv_system_type(void) { return UV_NONE; } static inline int is_uv_system(void) { return 0; } static inline void uv_cpu_init(void) { } static inline void uv_system_init(void) { } -static inline void uv_register_nmi_notifier(void) { } static inline const struct cpumask * uv_flush_tlb_others(const struct cpumask *cpumask, struct mm_struct *mm, unsigned long start, unsigned long end, unsigned int cpu) diff --git a/arch/x86/include/uapi/asm/sembuf.h b/arch/x86/include/uapi/asm/sembuf.h index ee50c801f7b7..cc2d6a3aeae7 100644 --- a/arch/x86/include/uapi/asm/sembuf.h +++ b/arch/x86/include/uapi/asm/sembuf.h @@ -13,12 +13,12 @@ struct semid64_ds { struct ipc64_perm sem_perm; /* permissions .. see ipc.h */ __kernel_time_t sem_otime; /* last semop time */ - unsigned long __unused1; + __kernel_ulong_t __unused1; __kernel_time_t sem_ctime; /* last change time */ - unsigned long __unused2; - unsigned long sem_nsems; /* no. of semaphores in array */ - unsigned long __unused3; - unsigned long __unused4; + __kernel_ulong_t __unused2; + __kernel_ulong_t sem_nsems; /* no. of semaphores in array */ + __kernel_ulong_t __unused3; + __kernel_ulong_t __unused4; }; #endif /* _ASM_X86_SEMBUF_H */ diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 59554dca96ec..dec8de4e1663 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -179,7 +179,7 @@ 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/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index ad0dc0428baf..d263b1307de1 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -980,7 +980,6 @@ void __init uv_system_init(void) uv_nmi_setup(); uv_cpu_init(); uv_scir_register_cpu_notifier(); - uv_register_nmi_notifier(); proc_mkdir("sgi_uv", NULL); /* register Legacy VGA I/O redirection handler */ diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index d3153e281d72..c67ffa686064 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -767,10 +767,7 @@ 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/intel.c b/arch/x86/kernel/cpu/intel.c index 3db61c644e44..5cd9bfabd645 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -640,21 +640,17 @@ 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/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/irq.c b/arch/x86/kernel/irq.c index dbb60878b744..d99f31d9a750 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -266,6 +266,14 @@ __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 +285,6 @@ 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/kvm.c b/arch/x86/kernel/kvm.c index 6dd802c6d780..713f1b3bad52 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -500,6 +500,38 @@ void __init kvm_guest_init(void) #endif } +static noinline uint32_t __kvm_cpuid_base(void) +{ + if (boot_cpu_data.cpuid_level < 0) + return 0; /* So we don't blow up on old processors */ + + if (cpu_has_hypervisor) + return hypervisor_cpuid_base("KVMKVMKVM\0\0\0", 0); + + return 0; +} + +static inline uint32_t kvm_cpuid_base(void) +{ + static int kvm_cpuid_base = -1; + + if (kvm_cpuid_base == -1) + kvm_cpuid_base = __kvm_cpuid_base(); + + return kvm_cpuid_base; +} + +bool kvm_para_available(void) +{ + return kvm_cpuid_base() != 0; +} +EXPORT_SYMBOL_GPL(kvm_para_available); + +unsigned int kvm_arch_para_features(void) +{ + return cpuid_eax(kvm_cpuid_base() | KVM_CPUID_FEATURES); +} + static uint32_t __init kvm_detect(void) { return kvm_cpuid_base(); @@ -673,7 +705,7 @@ static cpumask_t waiting_cpus; /* Track spinlock on which a cpu is waiting */ static DEFINE_PER_CPU(struct kvm_lock_waiting, klock_waiting); -static void kvm_lock_spinning(struct arch_spinlock *lock, __ticket_t want) +__visible void kvm_lock_spinning(struct arch_spinlock *lock, __ticket_t want) { struct kvm_lock_waiting *w; int cpu; diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index 04ee1e2e4c02..7c6acd4b8995 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -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/setup.c b/arch/x86/kernel/setup.c index c9675594d7ca..06853e670354 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1119,7 +1119,7 @@ void __init setup_arch(char **cmdline_p) setup_real_mode(); - memblock_set_current_limit(get_max_low_mapped()); + memblock_set_current_limit(get_max_mapped()); dma_contiguous_reserve(0); /* diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c index 992f890283e9..f6584a90aba3 100644 --- a/arch/x86/kernel/vsmp_64.c +++ b/arch/x86/kernel/vsmp_64.c @@ -33,7 +33,7 @@ * and vice versa. */ -static unsigned long vsmp_save_fl(void) +asmlinkage unsigned long vsmp_save_fl(void) { unsigned long flags = native_save_fl(); @@ -43,7 +43,7 @@ static unsigned long vsmp_save_fl(void) } PV_CALLEE_SAVE_REGS_THUNK(vsmp_save_fl); -static void vsmp_restore_fl(unsigned long flags) +__visible void vsmp_restore_fl(unsigned long flags) { if (flags & X86_EFLAGS_IF) flags &= ~X86_EFLAGS_AC; @@ -53,7 +53,7 @@ static void vsmp_restore_fl(unsigned long flags) } PV_CALLEE_SAVE_REGS_THUNK(vsmp_restore_fl); -static void vsmp_irq_disable(void) +asmlinkage void vsmp_irq_disable(void) { unsigned long flags = native_save_fl(); @@ -61,7 +61,7 @@ static void vsmp_irq_disable(void) } PV_CALLEE_SAVE_REGS_THUNK(vsmp_irq_disable); -static void vsmp_irq_enable(void) +asmlinkage void vsmp_irq_enable(void) { unsigned long flags = native_save_fl(); diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index f1e4895174b2..a2a1bb7ed8c1 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -72,4 +72,12 @@ static inline bool guest_cpuid_has_pcid(struct kvm_vcpu *vcpu) return best && (best->ecx & bit(X86_FEATURE_PCID)); } +static inline bool guest_cpuid_has_x2apic(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 1, 0); + return best && (best->ecx & bit(X86_FEATURE_X2APIC)); +} + #endif diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index c8b0d0d2da5c..6a11845fd8b9 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -65,7 +65,7 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, struct kvm_lapic_irq *irq, int *r, unsigned long *dest_map); u64 kvm_get_apic_base(struct kvm_vcpu *vcpu); -void kvm_set_apic_base(struct kvm_vcpu *vcpu, u64 data); +int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info); void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s); int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 5c8879127cfa..a06f101ef64b 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -4392,7 +4392,7 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) static void vmx_vcpu_reset(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - u64 msr; + struct msr_data apic_base_msr; vmx->rmode.vm86_active = 0; @@ -4400,10 +4400,11 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val(); kvm_set_cr8(&vmx->vcpu, 0); - msr = 0xfee00000 | MSR_IA32_APICBASE_ENABLE; + apic_base_msr.data = 0xfee00000 | MSR_IA32_APICBASE_ENABLE; if (kvm_vcpu_is_bsp(&vmx->vcpu)) - msr |= MSR_IA32_APICBASE_BSP; - kvm_set_apic_base(&vmx->vcpu, msr); + apic_base_msr.data |= MSR_IA32_APICBASE_BSP; + apic_base_msr.host_initiated = true; + kvm_set_apic_base(&vmx->vcpu, &apic_base_msr); vmx_segment_cache_clear(vmx); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 0c76f7cfdb32..39c28f09dfd5 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -257,10 +257,26 @@ u64 kvm_get_apic_base(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_get_apic_base); -void kvm_set_apic_base(struct kvm_vcpu *vcpu, u64 data) -{ - /* TODO: reserve bits check */ - kvm_lapic_set_base(vcpu, data); +int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info) +{ + u64 old_state = vcpu->arch.apic_base & + (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE); + u64 new_state = msr_info->data & + (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE); + u64 reserved_bits = ((~0ULL) << cpuid_maxphyaddr(vcpu)) | + 0x2ff | (guest_cpuid_has_x2apic(vcpu) ? 0 : X2APIC_ENABLE); + + if (!msr_info->host_initiated && + ((msr_info->data & reserved_bits) != 0 || + new_state == X2APIC_ENABLE || + (new_state == MSR_IA32_APICBASE_ENABLE && + old_state == (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE)) || + (new_state == (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE) && + old_state == 0))) + return 1; + + kvm_lapic_set_base(vcpu, msr_info->data); + return 0; } EXPORT_SYMBOL_GPL(kvm_set_apic_base); @@ -1840,6 +1856,7 @@ static int set_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data) if (__copy_to_user((void __user *)addr, instructions, 4)) return 1; kvm->arch.hv_hypercall = data; + mark_page_dirty(kvm, gfn); break; } case HV_X64_MSR_REFERENCE_TSC: { @@ -1868,19 +1885,21 @@ static int set_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 data) { switch (msr) { case HV_X64_MSR_APIC_ASSIST_PAGE: { + u64 gfn; unsigned long addr; if (!(data & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE)) { vcpu->arch.hv_vapic = data; break; } - addr = gfn_to_hva(vcpu->kvm, data >> - HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT); + gfn = data >> HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT; + addr = gfn_to_hva(vcpu->kvm, gfn); if (kvm_is_error_hva(addr)) return 1; if (__clear_user((void __user *)addr, PAGE_SIZE)) return 1; vcpu->arch.hv_vapic = data; + mark_page_dirty(vcpu->kvm, gfn); break; } case HV_X64_MSR_EOI: @@ -2006,8 +2025,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case 0x200 ... 0x2ff: return set_msr_mtrr(vcpu, msr, data); case MSR_IA32_APICBASE: - kvm_set_apic_base(vcpu, data); - break; + return kvm_set_apic_base(vcpu, msr_info); case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: return kvm_x2apic_msr_write(vcpu, msr, data); case MSR_IA32_TSCDEADLINE: @@ -2598,10 +2616,10 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_GET_TSC_KHZ: case KVM_CAP_KVMCLOCK_CTRL: case KVM_CAP_READONLY_MEM: + case KVM_CAP_HYPERV_TIME: #ifdef CONFIG_KVM_DEVICE_ASSIGNMENT case KVM_CAP_ASSIGN_DEV_IRQ: case KVM_CAP_PCI_2_3: - case KVM_CAP_HYPERV_TIME: #endif r = 1; break; @@ -6409,6 +6427,7 @@ EXPORT_SYMBOL_GPL(kvm_task_switch); int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { + struct msr_data apic_base_msr; int mmu_reset_needed = 0; int pending_vec, max_bits, idx; struct desc_ptr dt; @@ -6432,7 +6451,9 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, mmu_reset_needed |= vcpu->arch.efer != sregs->efer; kvm_x86_ops->set_efer(vcpu, sregs->efer); - kvm_set_apic_base(vcpu, sregs->apic_base); + apic_base_msr.data = sregs->apic_base; + apic_base_msr.host_initiated = true; + kvm_set_apic_base(vcpu, &apic_base_msr); mmu_reset_needed |= kvm_read_cr0(vcpu) != sregs->cr0; kvm_x86_ops->set_cr0(vcpu, sregs->cr0); diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index bdf8532494fe..ad1fb5f53925 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -233,13 +233,13 @@ static void lguest_end_context_switch(struct task_struct *next) * flags word contains all kind of stuff, but in practice Linux only cares * about the interrupt flag. Our "save_flags()" just returns that. */ -static unsigned long save_fl(void) +asmlinkage unsigned long lguest_save_fl(void) { return lguest_data.irq_enabled; } /* Interrupts go off... */ -static void irq_disable(void) +asmlinkage void lguest_irq_disable(void) { lguest_data.irq_enabled = 0; } @@ -253,8 +253,8 @@ static void irq_disable(void) * PV_CALLEE_SAVE_REGS_THUNK(), which pushes %eax onto the stack, calls the * C function, then restores it. */ -PV_CALLEE_SAVE_REGS_THUNK(save_fl); -PV_CALLEE_SAVE_REGS_THUNK(irq_disable); +PV_CALLEE_SAVE_REGS_THUNK(lguest_save_fl); +PV_CALLEE_SAVE_REGS_THUNK(lguest_irq_disable); /*:*/ /* These are in i386_head.S */ @@ -1291,9 +1291,9 @@ __init void lguest_init(void) */ /* Interrupt-related operations */ - pv_irq_ops.save_fl = PV_CALLEE_SAVE(save_fl); + pv_irq_ops.save_fl = PV_CALLEE_SAVE(lguest_save_fl); pv_irq_ops.restore_fl = __PV_IS_CALLEE_SAVE(lg_restore_fl); - pv_irq_ops.irq_disable = PV_CALLEE_SAVE(irq_disable); + pv_irq_ops.irq_disable = PV_CALLEE_SAVE(lguest_irq_disable); pv_irq_ops.irq_enable = __PV_IS_CALLEE_SAVE(lg_irq_enable); pv_irq_ops.safe_halt = lguest_safe_halt; diff --git a/arch/x86/math-emu/errors.c b/arch/x86/math-emu/errors.c index 59d353d2c599..a5449089cd9f 100644 --- a/arch/x86/math-emu/errors.c +++ b/arch/x86/math-emu/errors.c @@ -330,11 +330,6 @@ asmlinkage void FPU_exception(int n) RE_ENTRANT_CHECK_OFF; if ((~control_word & n & CW_Exceptions) || (n == EX_INTERNAL)) { -#ifdef PRINT_MESSAGES - /* My message from the sponsor */ - printk(FPU_VERSION " " __DATE__ " (C) W. Metzenthen.\n"); -#endif /* PRINT_MESSAGES */ - /* Get a name string for error reporting */ for (i = 0; exception_names[i].type; i++) if ((exception_names[i].type & n) == diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 81b2750f3666..27aa0455fab3 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -493,14 +493,6 @@ static int __init numa_register_memblks(struct numa_meminfo *mi) struct numa_memblk *mb = &mi->blk[i]; memblock_set_node(mb->start, mb->end - mb->start, &memblock.memory, mb->nid); - - /* - * At this time, all memory regions reserved by memblock are - * used by the kernel. Set the nid in memblock.reserved will - * mark out all the nodes the kernel resides in. - */ - memblock_set_node(mb->start, mb->end - mb->start, - &memblock.reserved, mb->nid); } /* @@ -565,10 +557,21 @@ static void __init numa_init_array(void) static void __init numa_clear_kernel_node_hotplug(void) { int i, nid; - nodemask_t numa_kernel_nodes; + nodemask_t numa_kernel_nodes = NODE_MASK_NONE; unsigned long start, end; struct memblock_type *type = &memblock.reserved; + /* + * At this time, all memory regions reserved by memblock are + * used by the kernel. Set the nid in memblock.reserved will + * mark out all the nodes the kernel resides in. + */ + for (i = 0; i < numa_meminfo.nr_blks; i++) { + struct numa_memblk *mb = &numa_meminfo.blk[i]; + memblock_set_node(mb->start, mb->end - mb->start, + &memblock.reserved, mb->nid); + } + /* Mark all kernel nodes. */ for (i = 0; i < type->cnt; i++) node_set(type->regions[i].nid, numa_kernel_nodes); diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c index 0342d27ca798..47b6436e41c2 100644 --- a/arch/x86/mm/numa_32.c +++ b/arch/x86/mm/numa_32.c @@ -52,6 +52,8 @@ void memory_present(int nid, unsigned long start, unsigned long end) nid, start, end); printk(KERN_DEBUG " Setting physnode_map array to node %d for pfns:\n", nid); printk(KERN_DEBUG " "); + start = round_down(start, PAGES_PER_SECTION); + end = round_up(end, PAGES_PER_SECTION); for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) { physnode_map[pfn / PAGES_PER_SECTION] = nid; printk(KERN_CONT "%lx ", pfn); diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c index 1a25187e151e..1953e9c9391a 100644 --- a/arch/x86/mm/srat.c +++ b/arch/x86/mm/srat.c @@ -42,15 +42,25 @@ static __init inline int srat_disabled(void) return acpi_numa < 0; } -/* Callback for SLIT parsing */ +/* + * Callback for SLIT parsing. pxm_to_node() returns NUMA_NO_NODE for + * I/O localities since SRAT does not list them. I/O localities are + * not supported at this point. + */ void __init acpi_numa_slit_init(struct acpi_table_slit *slit) { int i, j; - for (i = 0; i < slit->locality_count; i++) - for (j = 0; j < slit->locality_count; j++) + for (i = 0; i < slit->locality_count; i++) { + if (pxm_to_node(i) == NUMA_NO_NODE) + continue; + for (j = 0; j < slit->locality_count; j++) { + if (pxm_to_node(j) == NUMA_NO_NODE) + continue; numa_set_distance(pxm_to_node(i), pxm_to_node(j), slit->entry[slit->locality_count * i + j]); + } + } } /* Callback for Proximity Domain -> x2APIC mapping */ diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index ae699b3bbac8..dd8dda167a24 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -103,7 +103,7 @@ static void flush_tlb_func(void *info) if (f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm)) return; - count_vm_event(NR_TLB_REMOTE_FLUSH_RECEIVED); + count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) { if (f->flush_end == TLB_FLUSH_ALL) local_flush_tlb(); @@ -131,7 +131,7 @@ void native_flush_tlb_others(const struct cpumask *cpumask, info.flush_start = start; info.flush_end = end; - count_vm_event(NR_TLB_REMOTE_FLUSH); + count_vm_tlb_event(NR_TLB_REMOTE_FLUSH); if (is_uv_system()) { unsigned int cpu; @@ -151,44 +151,19 @@ void flush_tlb_current_task(void) preempt_disable(); - count_vm_event(NR_TLB_LOCAL_FLUSH_ALL); + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); local_flush_tlb(); if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL); preempt_enable(); } -/* - * It can find out the THP large page, or - * HUGETLB page in tlb_flush when THP disabled - */ -static inline unsigned long has_large_page(struct mm_struct *mm, - unsigned long start, unsigned long end) -{ - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - unsigned long addr = ALIGN(start, HPAGE_SIZE); - for (; addr < end; addr += HPAGE_SIZE) { - pgd = pgd_offset(mm, addr); - if (likely(!pgd_none(*pgd))) { - pud = pud_offset(pgd, addr); - if (likely(!pud_none(*pud))) { - pmd = pmd_offset(pud, addr); - if (likely(!pmd_none(*pmd))) - if (pmd_large(*pmd)) - return addr; - } - } - } - return 0; -} - void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, unsigned long end, unsigned long vmflag) { unsigned long addr; unsigned act_entries, tlb_entries = 0; + unsigned long nr_base_pages; preempt_disable(); if (current->active_mm != mm) @@ -210,21 +185,20 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, tlb_entries = tlb_lli_4k[ENTRIES]; else tlb_entries = tlb_lld_4k[ENTRIES]; + /* Assume all of TLB entries was occupied by this task */ - act_entries = mm->total_vm > tlb_entries ? tlb_entries : mm->total_vm; + act_entries = tlb_entries >> tlb_flushall_shift; + act_entries = mm->total_vm > act_entries ? act_entries : mm->total_vm; + nr_base_pages = (end - start) >> PAGE_SHIFT; /* tlb_flushall_shift is on balance point, details in commit log */ - if ((end - start) >> PAGE_SHIFT > act_entries >> tlb_flushall_shift) { - count_vm_event(NR_TLB_LOCAL_FLUSH_ALL); + if (nr_base_pages > act_entries) { + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); local_flush_tlb(); } else { - if (has_large_page(mm, start, end)) { - local_flush_tlb(); - goto flush_all; - } /* flush range by one by one 'invlpg' */ for (addr = start; addr < end; addr += PAGE_SIZE) { - count_vm_event(NR_TLB_LOCAL_FLUSH_ONE); + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE); __flush_tlb_single(addr); } @@ -262,7 +236,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long start) static void do_flush_tlb_all(void *info) { - count_vm_event(NR_TLB_REMOTE_FLUSH_RECEIVED); + count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); __flush_tlb_all(); if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_LAZY) leave_mm(smp_processor_id()); @@ -270,7 +244,7 @@ static void do_flush_tlb_all(void *info) void flush_tlb_all(void) { - count_vm_event(NR_TLB_REMOTE_FLUSH); + count_vm_tlb_event(NR_TLB_REMOTE_FLUSH); on_each_cpu(do_flush_tlb_all, NULL, 1); } diff --git a/arch/x86/platform/efi/efi-bgrt.c b/arch/x86/platform/efi/efi-bgrt.c index 7145ec63c520..4df9591eadad 100644 --- a/arch/x86/platform/efi/efi-bgrt.c +++ b/arch/x86/platform/efi/efi-bgrt.c @@ -49,7 +49,8 @@ void __init efi_bgrt_init(void) image = efi_lookup_mapped_addr(bgrt_tab->image_address); if (!image) { - image = ioremap(bgrt_tab->image_address, sizeof(bmp_header)); + image = early_memremap(bgrt_tab->image_address, + sizeof(bmp_header)); ioremapped = true; if (!image) return; @@ -57,7 +58,7 @@ void __init efi_bgrt_init(void) memcpy_fromio(&bmp_header, image, sizeof(bmp_header)); if (ioremapped) - iounmap(image); + early_iounmap(image, sizeof(bmp_header)); bgrt_image_size = bmp_header.size; bgrt_image = kmalloc(bgrt_image_size, GFP_KERNEL); @@ -65,7 +66,8 @@ void __init efi_bgrt_init(void) return; if (ioremapped) { - image = ioremap(bgrt_tab->image_address, bmp_header.size); + image = early_memremap(bgrt_tab->image_address, + bmp_header.size); if (!image) { kfree(bgrt_image); bgrt_image = NULL; @@ -75,5 +77,5 @@ void __init efi_bgrt_init(void) memcpy_fromio(bgrt_image, image, bgrt_image_size); if (ioremapped) - iounmap(image); + early_iounmap(image, bmp_header.size); } diff --git a/arch/x86/platform/intel-mid/device_libs/platform_ipc.h b/arch/x86/platform/intel-mid/device_libs/platform_ipc.h index 8f568dd79605..79bb09d4f718 100644 --- a/arch/x86/platform/intel-mid/device_libs/platform_ipc.h +++ b/arch/x86/platform/intel-mid/device_libs/platform_ipc.h @@ -12,6 +12,7 @@ #ifndef _PLATFORM_IPC_H_ #define _PLATFORM_IPC_H_ -extern void __init ipc_device_handler(struct sfi_device_table_entry *pentry, - struct devs_id *dev) __attribute__((weak)); +void __init +ipc_device_handler(struct sfi_device_table_entry *pentry, struct devs_id *dev); + #endif diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic.h b/arch/x86/platform/intel-mid/device_libs/platform_msic.h index 917eb56d77da..b7be1d041da2 100644 --- a/arch/x86/platform/intel-mid/device_libs/platform_msic.h +++ b/arch/x86/platform/intel-mid/device_libs/platform_msic.h @@ -14,6 +14,6 @@ extern struct intel_msic_platform_data msic_pdata; -extern void *msic_generic_platform_data(void *info, - enum intel_msic_block block) __attribute__((weak)); +void *msic_generic_platform_data(void *info, enum intel_msic_block block); + #endif diff --git a/arch/x86/platform/intel-mid/intel_mid_weak_decls.h b/arch/x86/platform/intel-mid/intel_mid_weak_decls.h index a537ffc16299..46aa25c8ce06 100644 --- a/arch/x86/platform/intel-mid/intel_mid_weak_decls.h +++ b/arch/x86/platform/intel-mid/intel_mid_weak_decls.h @@ -14,6 +14,6 @@ /* For every CPU addition a new get_<cpuname>_ops interface needs * to be added. */ -extern void * __cpuinit get_penwell_ops(void) __attribute__((weak)); -extern void * __cpuinit get_cloverview_ops(void) __attribute__((weak)); -extern void * __init get_tangier_ops(void) __attribute__((weak)); +extern void *get_penwell_ops(void) __attribute__((weak)); +extern void *get_cloverview_ops(void) __attribute__((weak)); +extern void *get_tangier_ops(void) __attribute__((weak)); diff --git a/arch/x86/platform/intel-mid/mfld.c b/arch/x86/platform/intel-mid/mfld.c index 4f7884eebc14..23381d2174ae 100644 --- a/arch/x86/platform/intel-mid/mfld.c +++ b/arch/x86/platform/intel-mid/mfld.c @@ -58,18 +58,18 @@ static unsigned long __init mfld_calibrate_tsc(void) return 0; } -static void __init penwell_arch_setup() +static void __init penwell_arch_setup(void) { x86_platform.calibrate_tsc = mfld_calibrate_tsc; pm_power_off = mfld_power_off; } -void * __cpuinit get_penwell_ops() +void *get_penwell_ops(void) { return &penwell_ops; } -void * __cpuinit get_cloverview_ops() +void *get_cloverview_ops(void) { return &penwell_ops; } diff --git a/arch/x86/platform/intel-mid/mrfl.c b/arch/x86/platform/intel-mid/mrfl.c index 09d10159e7b7..aaca91753d32 100644 --- a/arch/x86/platform/intel-mid/mrfl.c +++ b/arch/x86/platform/intel-mid/mrfl.c @@ -97,7 +97,7 @@ static struct intel_mid_ops tangier_ops = { .arch_setup = tangier_arch_setup, }; -void * __cpuinit get_tangier_ops() +void *get_tangier_ops(void) { return &tangier_ops; } diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c index 8eeccba73130..be27da60dc8f 100644 --- a/arch/x86/platform/uv/uv_nmi.c +++ b/arch/x86/platform/uv/uv_nmi.c @@ -74,7 +74,6 @@ static atomic_t uv_in_nmi; static atomic_t uv_nmi_cpu = ATOMIC_INIT(-1); static atomic_t uv_nmi_cpus_in_nmi = ATOMIC_INIT(-1); static atomic_t uv_nmi_slave_continue; -static atomic_t uv_nmi_kexec_failed; static cpumask_var_t uv_nmi_cpu_mask; /* Values for uv_nmi_slave_continue */ @@ -149,7 +148,8 @@ module_param_named(retry_count, uv_nmi_retry_count, int, 0644); * "dump" - dump process stack for each cpu * "ips" - dump IP info for each cpu * "kdump" - do crash dump - * "kdb" - enter KDB/KGDB (default) + * "kdb" - enter KDB (default) + * "kgdb" - enter KGDB */ static char uv_nmi_action[8] = "kdb"; module_param_string(action, uv_nmi_action, sizeof(uv_nmi_action), 0644); @@ -504,6 +504,7 @@ static void uv_nmi_touch_watchdogs(void) } #if defined(CONFIG_KEXEC) +static atomic_t uv_nmi_kexec_failed; static void uv_nmi_kdump(int cpu, int master, struct pt_regs *regs) { /* Call crash to dump system state */ @@ -537,18 +538,45 @@ static inline void uv_nmi_kdump(int cpu, int master, struct pt_regs *regs) } #endif /* !CONFIG_KEXEC */ +#ifdef CONFIG_KGDB #ifdef CONFIG_KGDB_KDB -/* Call KDB from NMI handler */ -static void uv_call_kdb(int cpu, struct pt_regs *regs, int master) +static inline int uv_nmi_kdb_reason(void) { - int ret; + return KDB_REASON_SYSTEM_NMI; +} +#else /* !CONFIG_KGDB_KDB */ +static inline int uv_nmi_kdb_reason(void) +{ + /* Insure user is expecting to attach gdb remote */ + if (uv_nmi_action_is("kgdb")) + return 0; + + pr_err("UV: NMI error: KDB is not enabled in this kernel\n"); + return -1; +} +#endif /* CONFIG_KGDB_KDB */ +/* + * Call KGDB/KDB from NMI handler + * + * Note that if both KGDB and KDB are configured, then the action of 'kgdb' or + * 'kdb' has no affect on which is used. See the KGDB documention for further + * information. + */ +static void uv_call_kgdb_kdb(int cpu, struct pt_regs *regs, int master) +{ if (master) { + int reason = uv_nmi_kdb_reason(); + int ret; + + if (reason < 0) + return; + /* call KGDB NMI handler as MASTER */ - ret = kgdb_nmicallin(cpu, X86_TRAP_NMI, regs, - &uv_nmi_slave_continue); + ret = kgdb_nmicallin(cpu, X86_TRAP_NMI, regs, reason, + &uv_nmi_slave_continue); if (ret) { - pr_alert("KDB returned error, is kgdboc set?\n"); + pr_alert("KGDB returned error, is kgdboc set?\n"); atomic_set(&uv_nmi_slave_continue, SLAVE_EXIT); } } else { @@ -567,12 +595,12 @@ static void uv_call_kdb(int cpu, struct pt_regs *regs, int master) uv_nmi_sync_exit(master); } -#else /* !CONFIG_KGDB_KDB */ -static inline void uv_call_kdb(int cpu, struct pt_regs *regs, int master) +#else /* !CONFIG_KGDB */ +static inline void uv_call_kgdb_kdb(int cpu, struct pt_regs *regs, int master) { - pr_err("UV: NMI error: KGDB/KDB is not enabled in this kernel\n"); + pr_err("UV: NMI error: KGDB is not enabled in this kernel\n"); } -#endif /* !CONFIG_KGDB_KDB */ +#endif /* !CONFIG_KGDB */ /* * UV NMI handler @@ -606,9 +634,9 @@ int uv_handle_nmi(unsigned int reason, struct pt_regs *regs) if (uv_nmi_action_is("ips") || uv_nmi_action_is("dump")) uv_nmi_dump_state(cpu, regs, master); - /* Call KDB if enabled */ - else if (uv_nmi_action_is("kdb")) - uv_call_kdb(cpu, regs, master); + /* Call KGDB/KDB if enabled */ + else if (uv_nmi_action_is("kdb") || uv_nmi_action_is("kgdb")) + uv_call_kgdb_kdb(cpu, regs, master); /* Clear per_cpu "in nmi" flag */ atomic_set(&uv_cpu_nmi.state, UV_NMI_STATE_OUT); @@ -634,7 +662,7 @@ int uv_handle_nmi(unsigned int reason, struct pt_regs *regs) /* * NMI handler for pulling in CPUs when perf events are grabbing our NMI */ -int uv_handle_nmi_ping(unsigned int reason, struct pt_regs *regs) +static int uv_handle_nmi_ping(unsigned int reason, struct pt_regs *regs) { int ret; @@ -651,7 +679,7 @@ int uv_handle_nmi_ping(unsigned int reason, struct pt_regs *regs) return ret; } -void uv_register_nmi_notifier(void) +static void uv_register_nmi_notifier(void) { if (register_nmi_handler(NMI_UNKNOWN, uv_handle_nmi, 0, "uv")) pr_warn("UV: NMI handler failed to register\n"); @@ -695,6 +723,5 @@ void uv_nmi_setup(void) uv_hub_nmi_per(cpu) = uv_hub_nmi_list[nid]; } BUG_ON(!alloc_cpumask_var(&uv_nmi_cpu_mask, GFP_KERNEL)); + uv_register_nmi_notifier(); } - - diff --git a/arch/x86/realmode/rm/Makefile b/arch/x86/realmode/rm/Makefile index 9cac82588cbc..3497f14e4dea 100644 --- a/arch/x86/realmode/rm/Makefile +++ b/arch/x86/realmode/rm/Makefile @@ -64,20 +64,7 @@ $(obj)/realmode.relocs: $(obj)/realmode.elf FORCE # --------------------------------------------------------------------------- -# How to compile the 16-bit code. Note we always compile for -march=i386, -# that way we can complain to the user if the CPU is insufficient. -KBUILD_CFLAGS := $(LINUXINCLUDE) -m32 -g -Os -D_SETUP -D__KERNEL__ -D_WAKEUP \ - -I$(srctree)/arch/x86/boot \ - -DDISABLE_BRANCH_PROFILING \ - -Wall -Wstrict-prototypes \ - -march=i386 -mregparm=3 \ - -include $(srctree)/$(src)/../../boot/code16gcc.h \ - -fno-strict-aliasing -fomit-frame-pointer -fno-pic \ - -mno-mmx -mno-sse \ - $(call cc-option, -ffreestanding) \ - $(call cc-option, -fno-toplevel-reorder,\ - $(call cc-option, -fno-unit-at-a-time)) \ - $(call cc-option, -fno-stack-protector) \ - $(call cc-option, -mpreferred-stack-boundary=2) +KBUILD_CFLAGS := $(LINUXINCLUDE) $(REALMODE_CFLAGS) -D_SETUP -D_WAKEUP \ + -I$(srctree)/arch/x86/boot KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__ GCOV_PROFILE := n diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c index 11f9285a2ff6..cfbdbdb4e173 100644 --- a/arch/x86/tools/relocs.c +++ b/arch/x86/tools/relocs.c @@ -1025,6 +1025,29 @@ static void emit_relocs(int as_text, int use_real_mode) } } +/* + * As an aid to debugging problems with different linkers + * print summary information about the relocs. + * Since different linkers tend to emit the sections in + * different orders we use the section names in the output. + */ +static int do_reloc_info(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym, + const char *symname) +{ + printf("%s\t%s\t%s\t%s\n", + sec_name(sec->shdr.sh_info), + rel_type(ELF_R_TYPE(rel->r_info)), + symname, + sec_name(sym->st_shndx)); + return 0; +} + +static void print_reloc_info(void) +{ + printf("reloc section\treloc type\tsymbol\tsymbol section\n"); + walk_relocs(do_reloc_info); +} + #if ELF_BITS == 64 # define process process_64 #else @@ -1032,7 +1055,8 @@ static void emit_relocs(int as_text, int use_real_mode) #endif void process(FILE *fp, int use_real_mode, int as_text, - int show_absolute_syms, int show_absolute_relocs) + int show_absolute_syms, int show_absolute_relocs, + int show_reloc_info) { regex_init(use_real_mode); read_ehdr(fp); @@ -1050,5 +1074,9 @@ void process(FILE *fp, int use_real_mode, int as_text, print_absolute_relocs(); return; } + if (show_reloc_info) { + print_reloc_info(); + return; + } emit_relocs(as_text, use_real_mode); } diff --git a/arch/x86/tools/relocs.h b/arch/x86/tools/relocs.h index 07cdb1eca4fa..f59590645b68 100644 --- a/arch/x86/tools/relocs.h +++ b/arch/x86/tools/relocs.h @@ -29,8 +29,9 @@ enum symtype { }; void process_32(FILE *fp, int use_real_mode, int as_text, - int show_absolute_syms, int show_absolute_relocs); + int show_absolute_syms, int show_absolute_relocs, + int show_reloc_info); void process_64(FILE *fp, int use_real_mode, int as_text, - int show_absolute_syms, int show_absolute_relocs); - + int show_absolute_syms, int show_absolute_relocs, + int show_reloc_info); #endif /* RELOCS_H */ diff --git a/arch/x86/tools/relocs_common.c b/arch/x86/tools/relocs_common.c index 44d396823a53..acab636bcb34 100644 --- a/arch/x86/tools/relocs_common.c +++ b/arch/x86/tools/relocs_common.c @@ -11,12 +11,13 @@ void die(char *fmt, ...) static void usage(void) { - die("relocs [--abs-syms|--abs-relocs|--text|--realmode] vmlinux\n"); + die("relocs [--abs-syms|--abs-relocs|--reloc-info|--text|--realmode]" \ + " vmlinux\n"); } int main(int argc, char **argv) { - int show_absolute_syms, show_absolute_relocs; + int show_absolute_syms, show_absolute_relocs, show_reloc_info; int as_text, use_real_mode; const char *fname; FILE *fp; @@ -25,6 +26,7 @@ int main(int argc, char **argv) show_absolute_syms = 0; show_absolute_relocs = 0; + show_reloc_info = 0; as_text = 0; use_real_mode = 0; fname = NULL; @@ -39,6 +41,10 @@ int main(int argc, char **argv) show_absolute_relocs = 1; continue; } + if (strcmp(arg, "--reloc-info") == 0) { + show_reloc_info = 1; + continue; + } if (strcmp(arg, "--text") == 0) { as_text = 1; continue; @@ -67,10 +73,12 @@ int main(int argc, char **argv) rewind(fp); if (e_ident[EI_CLASS] == ELFCLASS64) process_64(fp, use_real_mode, as_text, - show_absolute_syms, show_absolute_relocs); + show_absolute_syms, show_absolute_relocs, + show_reloc_info); else process_32(fp, use_real_mode, as_text, - show_absolute_syms, show_absolute_relocs); + show_absolute_syms, show_absolute_relocs, + show_reloc_info); fclose(fp); return 0; } diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index a4d7b647867f..201d09a7c46b 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1473,6 +1473,18 @@ static void xen_pvh_set_cr_flags(int cpu) * X86_CR0_TS, X86_CR0_PE, X86_CR0_ET are set by Xen for HVM guests * (which PVH shared codepaths), while X86_CR0_PG is for PVH. */ write_cr0(read_cr0() | X86_CR0_MP | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM); + + if (!cpu) + return; + /* + * For BSP, PSE PGE are set in probe_page_size_mask(), for APs + * set them here. For all, OSFXSR OSXMMEXCPT are set in fpu_init. + */ + if (cpu_has_pse) + set_in_cr4(X86_CR4_PSE); + + if (cpu_has_pge) + set_in_cr4(X86_CR4_PGE); } /* diff --git a/arch/x86/xen/grant-table.c b/arch/x86/xen/grant-table.c index 103c93f874b2..c98583588580 100644 --- a/arch/x86/xen/grant-table.c +++ b/arch/x86/xen/grant-table.c @@ -162,14 +162,15 @@ static int __init xlated_setup_gnttab_pages(void) rc = arch_gnttab_map_shared(pfns, nr_grant_frames, nr_grant_frames, &xen_auto_xlat_grant_frames.vaddr); - kfree(pages); if (rc) { pr_warn("%s Couldn't map %ld pfns rc:%d\n", __func__, nr_grant_frames, rc); free_xenballooned_pages(nr_grant_frames, pages); + kfree(pages); kfree(pfns); return rc; } + kfree(pages); xen_auto_xlat_grant_frames.pfn = pfns; xen_auto_xlat_grant_frames.count = nr_grant_frames; diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c index 76ca326105f7..08f763de26fe 100644 --- a/arch/x86/xen/irq.c +++ b/arch/x86/xen/irq.c @@ -23,7 +23,7 @@ void xen_force_evtchn_callback(void) (void)HYPERVISOR_xen_version(0, NULL); } -static unsigned long xen_save_fl(void) +asmlinkage unsigned long xen_save_fl(void) { struct vcpu_info *vcpu; unsigned long flags; @@ -41,7 +41,7 @@ static unsigned long xen_save_fl(void) } PV_CALLEE_SAVE_REGS_THUNK(xen_save_fl); -static void xen_restore_fl(unsigned long flags) +__visible void xen_restore_fl(unsigned long flags) { struct vcpu_info *vcpu; @@ -63,7 +63,7 @@ static void xen_restore_fl(unsigned long flags) } PV_CALLEE_SAVE_REGS_THUNK(xen_restore_fl); -static void xen_irq_disable(void) +asmlinkage void xen_irq_disable(void) { /* There's a one instruction preempt window here. We need to make sure we're don't switch CPUs between getting the vcpu @@ -74,7 +74,7 @@ static void xen_irq_disable(void) } PV_CALLEE_SAVE_REGS_THUNK(xen_irq_disable); -static void xen_irq_enable(void) +asmlinkage void xen_irq_enable(void) { struct vcpu_info *vcpu; diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index c1d406f35523..2423ef04ffea 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -431,7 +431,7 @@ static pteval_t iomap_pte(pteval_t val) return val; } -static pteval_t xen_pte_val(pte_t pte) +__visible pteval_t xen_pte_val(pte_t pte) { pteval_t pteval = pte.pte; #if 0 @@ -448,7 +448,7 @@ static pteval_t xen_pte_val(pte_t pte) } PV_CALLEE_SAVE_REGS_THUNK(xen_pte_val); -static pgdval_t xen_pgd_val(pgd_t pgd) +__visible pgdval_t xen_pgd_val(pgd_t pgd) { return pte_mfn_to_pfn(pgd.pgd); } @@ -479,7 +479,7 @@ void xen_set_pat(u64 pat) WARN_ON(pat != 0x0007010600070106ull); } -static pte_t xen_make_pte(pteval_t pte) +__visible pte_t xen_make_pte(pteval_t pte) { phys_addr_t addr = (pte & PTE_PFN_MASK); #if 0 @@ -514,14 +514,14 @@ static pte_t xen_make_pte(pteval_t pte) } PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte); -static pgd_t xen_make_pgd(pgdval_t pgd) +__visible pgd_t xen_make_pgd(pgdval_t pgd) { pgd = pte_pfn_to_mfn(pgd); return native_make_pgd(pgd); } PV_CALLEE_SAVE_REGS_THUNK(xen_make_pgd); -static pmdval_t xen_pmd_val(pmd_t pmd) +__visible pmdval_t xen_pmd_val(pmd_t pmd) { return pte_mfn_to_pfn(pmd.pmd); } @@ -580,7 +580,7 @@ static void xen_pmd_clear(pmd_t *pmdp) } #endif /* CONFIG_X86_PAE */ -static pmd_t xen_make_pmd(pmdval_t pmd) +__visible pmd_t xen_make_pmd(pmdval_t pmd) { pmd = pte_pfn_to_mfn(pmd); return native_make_pmd(pmd); @@ -588,13 +588,13 @@ static pmd_t xen_make_pmd(pmdval_t pmd) PV_CALLEE_SAVE_REGS_THUNK(xen_make_pmd); #if PAGETABLE_LEVELS == 4 -static pudval_t xen_pud_val(pud_t pud) +__visible pudval_t xen_pud_val(pud_t pud) { return pte_mfn_to_pfn(pud.pud); } PV_CALLEE_SAVE_REGS_THUNK(xen_pud_val); -static pud_t xen_make_pud(pudval_t pud) +__visible pud_t xen_make_pud(pudval_t pud) { pud = pte_pfn_to_mfn(pud); diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index dd5f905e33d5..0982233b9b84 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -35,7 +35,7 @@ extern const char xen_hypervisor_callback[]; extern const char xen_failsafe_callback[]; #ifdef CONFIG_X86_64 -extern const char nmi[]; +extern asmlinkage void nmi(void); #endif extern void xen_sysenter_target(void); extern void xen_syscall_target(void); @@ -577,7 +577,7 @@ void xen_enable_syscall(void) void xen_enable_nmi(void) { #ifdef CONFIG_X86_64 - if (register_callback(CALLBACKTYPE_nmi, nmi)) + if (register_callback(CALLBACKTYPE_nmi, (char *)nmi)) BUG(); #endif } diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index 0e36cde12f7e..581521c843a5 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -106,7 +106,7 @@ static DEFINE_PER_CPU(struct xen_lock_waiting, lock_waiting); static cpumask_t waiting_cpus; static bool xen_pvspin = true; -static void xen_lock_spinning(struct arch_spinlock *lock, __ticket_t want) +__visible void xen_lock_spinning(struct arch_spinlock *lock, __ticket_t want) { int irq = __this_cpu_read(lock_kicker_irq); struct xen_lock_waiting *w = &__get_cpu_var(lock_waiting); |