diff options
Diffstat (limited to 'arch/x86')
34 files changed, 271 insertions, 274 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 6a154a91c7e7..fe120da25625 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -108,7 +108,6 @@ config X86 select GENERIC_CLOCKEVENTS_BROADCAST if X86_64 || (X86_32 && X86_LOCAL_APIC) select GENERIC_TIME_VSYSCALL if X86_64 select KTIME_SCALAR if X86_32 - select ALWAYS_USE_PERSISTENT_CLOCK select GENERIC_STRNCPY_FROM_USER select GENERIC_STRNLEN_USER select HAVE_CONTEXT_TRACKING if X86_64 @@ -2266,6 +2265,7 @@ source "fs/Kconfig.binfmt" config IA32_EMULATION bool "IA32 Emulation" depends on X86_64 + select BINFMT_ELF select COMPAT_BINFMT_ELF select HAVE_UID16 ---help--- diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index 35ee62fccf98..c205035a6b96 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -251,51 +251,6 @@ static void find_bits(unsigned long mask, u8 *pos, u8 *size) *size = len; } -static efi_status_t setup_efi_vars(struct boot_params *params) -{ - struct setup_data *data; - struct efi_var_bootdata *efidata; - u64 store_size, remaining_size, var_size; - efi_status_t status; - - if (sys_table->runtime->hdr.revision < EFI_2_00_SYSTEM_TABLE_REVISION) - return EFI_UNSUPPORTED; - - data = (struct setup_data *)(unsigned long)params->hdr.setup_data; - - while (data && data->next) - data = (struct setup_data *)(unsigned long)data->next; - - status = efi_call_phys4((void *)sys_table->runtime->query_variable_info, - EFI_VARIABLE_NON_VOLATILE | - EFI_VARIABLE_BOOTSERVICE_ACCESS | - EFI_VARIABLE_RUNTIME_ACCESS, &store_size, - &remaining_size, &var_size); - - if (status != EFI_SUCCESS) - return status; - - status = efi_call_phys3(sys_table->boottime->allocate_pool, - EFI_LOADER_DATA, sizeof(*efidata), &efidata); - - if (status != EFI_SUCCESS) - return status; - - efidata->data.type = SETUP_EFI_VARS; - efidata->data.len = sizeof(struct efi_var_bootdata) - - sizeof(struct setup_data); - efidata->data.next = 0; - efidata->store_size = store_size; - efidata->remaining_size = remaining_size; - efidata->max_var_size = var_size; - - if (data) - data->next = (unsigned long)efidata; - else - params->hdr.setup_data = (unsigned long)efidata; - -} - static efi_status_t setup_efi_pci(struct boot_params *params) { efi_pci_io_protocol *pci; @@ -1202,8 +1157,6 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table, setup_graphics(boot_params); - setup_efi_vars(boot_params); - setup_efi_pci(boot_params); status = efi_call_phys3(sys_table->boottime->allocate_pool, diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S index 62fe22cd4cba..477e9d75149b 100644 --- a/arch/x86/crypto/aesni-intel_asm.S +++ b/arch/x86/crypto/aesni-intel_asm.S @@ -2681,56 +2681,68 @@ ENTRY(aesni_xts_crypt8) addq %rcx, KEYP movdqa IV, STATE1 - pxor 0x00(INP), STATE1 + movdqu 0x00(INP), INC + pxor INC, STATE1 movdqu IV, 0x00(OUTP) _aesni_gf128mul_x_ble() movdqa IV, STATE2 - pxor 0x10(INP), STATE2 + movdqu 0x10(INP), INC + pxor INC, STATE2 movdqu IV, 0x10(OUTP) _aesni_gf128mul_x_ble() movdqa IV, STATE3 - pxor 0x20(INP), STATE3 + movdqu 0x20(INP), INC + pxor INC, STATE3 movdqu IV, 0x20(OUTP) _aesni_gf128mul_x_ble() movdqa IV, STATE4 - pxor 0x30(INP), STATE4 + movdqu 0x30(INP), INC + pxor INC, STATE4 movdqu IV, 0x30(OUTP) call *%r11 - pxor 0x00(OUTP), STATE1 + movdqu 0x00(OUTP), INC + pxor INC, STATE1 movdqu STATE1, 0x00(OUTP) _aesni_gf128mul_x_ble() movdqa IV, STATE1 - pxor 0x40(INP), STATE1 + movdqu 0x40(INP), INC + pxor INC, STATE1 movdqu IV, 0x40(OUTP) - pxor 0x10(OUTP), STATE2 + movdqu 0x10(OUTP), INC + pxor INC, STATE2 movdqu STATE2, 0x10(OUTP) _aesni_gf128mul_x_ble() movdqa IV, STATE2 - pxor 0x50(INP), STATE2 + movdqu 0x50(INP), INC + pxor INC, STATE2 movdqu IV, 0x50(OUTP) - pxor 0x20(OUTP), STATE3 + movdqu 0x20(OUTP), INC + pxor INC, STATE3 movdqu STATE3, 0x20(OUTP) _aesni_gf128mul_x_ble() movdqa IV, STATE3 - pxor 0x60(INP), STATE3 + movdqu 0x60(INP), INC + pxor INC, STATE3 movdqu IV, 0x60(OUTP) - pxor 0x30(OUTP), STATE4 + movdqu 0x30(OUTP), INC + pxor INC, STATE4 movdqu STATE4, 0x30(OUTP) _aesni_gf128mul_x_ble() movdqa IV, STATE4 - pxor 0x70(INP), STATE4 + movdqu 0x70(INP), INC + pxor INC, STATE4 movdqu IV, 0x70(OUTP) _aesni_gf128mul_x_ble() @@ -2738,16 +2750,20 @@ ENTRY(aesni_xts_crypt8) call *%r11 - pxor 0x40(OUTP), STATE1 + movdqu 0x40(OUTP), INC + pxor INC, STATE1 movdqu STATE1, 0x40(OUTP) - pxor 0x50(OUTP), STATE2 + movdqu 0x50(OUTP), INC + pxor INC, STATE2 movdqu STATE2, 0x50(OUTP) - pxor 0x60(OUTP), STATE3 + movdqu 0x60(OUTP), INC + pxor INC, STATE3 movdqu STATE3, 0x60(OUTP) - pxor 0x70(OUTP), STATE4 + movdqu 0x70(OUTP), INC + pxor INC, STATE4 movdqu STATE4, 0x70(OUTP) ret diff --git a/arch/x86/crypto/crc32-pclmul_asm.S b/arch/x86/crypto/crc32-pclmul_asm.S index 94c27df8a549..f247304299a2 100644 --- a/arch/x86/crypto/crc32-pclmul_asm.S +++ b/arch/x86/crypto/crc32-pclmul_asm.S @@ -240,7 +240,7 @@ fold_64: pand %xmm3, %xmm1 PCLMULQDQ 0x00, CONSTANT, %xmm1 pxor %xmm2, %xmm1 - pextrd $0x01, %xmm1, %eax + PEXTRD 0x01, %xmm1, %eax ret ENDPROC(crc32_pclmul_le_16) diff --git a/arch/x86/crypto/sha256-avx-asm.S b/arch/x86/crypto/sha256-avx-asm.S index 56610c4bf31b..642f15687a0a 100644 --- a/arch/x86/crypto/sha256-avx-asm.S +++ b/arch/x86/crypto/sha256-avx-asm.S @@ -118,7 +118,7 @@ y2 = %r15d _INP_END_SIZE = 8 _INP_SIZE = 8 -_XFER_SIZE = 8 +_XFER_SIZE = 16 _XMM_SAVE_SIZE = 0 _INP_END = 0 diff --git a/arch/x86/crypto/sha256-ssse3-asm.S b/arch/x86/crypto/sha256-ssse3-asm.S index 98d3c391da81..f833b74d902b 100644 --- a/arch/x86/crypto/sha256-ssse3-asm.S +++ b/arch/x86/crypto/sha256-ssse3-asm.S @@ -111,7 +111,7 @@ y2 = %r15d _INP_END_SIZE = 8 _INP_SIZE = 8 -_XFER_SIZE = 8 +_XFER_SIZE = 16 _XMM_SAVE_SIZE = 0 _INP_END = 0 diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c index 805078e08013..52ff81cce008 100644 --- a/arch/x86/ia32/ia32_aout.c +++ b/arch/x86/ia32/ia32_aout.c @@ -192,7 +192,7 @@ static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file, /* struct user */ DUMP_WRITE(&dump, sizeof(dump)); /* Now dump all of the user data. Include malloced stuff as well */ - DUMP_SEEK(PAGE_SIZE); + DUMP_SEEK(PAGE_SIZE - sizeof(dump)); /* now we start writing out the user space info */ set_fs(USER_DS); /* Dump the data area */ diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 2fb5d5884e23..60c89f30c727 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -102,13 +102,6 @@ extern void efi_call_phys_epilog(void); extern void efi_unmap_memmap(void); extern void efi_memory_uc(u64 addr, unsigned long size); -struct efi_var_bootdata { - struct setup_data data; - u64 store_size; - u64 remaining_size; - u64 max_var_size; -}; - #ifdef CONFIG_EFI static inline bool efi_is_native(void) diff --git a/arch/x86/include/asm/inst.h b/arch/x86/include/asm/inst.h index 280bf7fb6aba..3e115273ed88 100644 --- a/arch/x86/include/asm/inst.h +++ b/arch/x86/include/asm/inst.h @@ -9,12 +9,68 @@ #define REG_NUM_INVALID 100 -#define REG_TYPE_R64 0 -#define REG_TYPE_XMM 1 +#define REG_TYPE_R32 0 +#define REG_TYPE_R64 1 +#define REG_TYPE_XMM 2 #define REG_TYPE_INVALID 100 + .macro R32_NUM opd r32 + \opd = REG_NUM_INVALID + .ifc \r32,%eax + \opd = 0 + .endif + .ifc \r32,%ecx + \opd = 1 + .endif + .ifc \r32,%edx + \opd = 2 + .endif + .ifc \r32,%ebx + \opd = 3 + .endif + .ifc \r32,%esp + \opd = 4 + .endif + .ifc \r32,%ebp + \opd = 5 + .endif + .ifc \r32,%esi + \opd = 6 + .endif + .ifc \r32,%edi + \opd = 7 + .endif +#ifdef CONFIG_X86_64 + .ifc \r32,%r8d + \opd = 8 + .endif + .ifc \r32,%r9d + \opd = 9 + .endif + .ifc \r32,%r10d + \opd = 10 + .endif + .ifc \r32,%r11d + \opd = 11 + .endif + .ifc \r32,%r12d + \opd = 12 + .endif + .ifc \r32,%r13d + \opd = 13 + .endif + .ifc \r32,%r14d + \opd = 14 + .endif + .ifc \r32,%r15d + \opd = 15 + .endif +#endif + .endm + .macro R64_NUM opd r64 \opd = REG_NUM_INVALID +#ifdef CONFIG_X86_64 .ifc \r64,%rax \opd = 0 .endif @@ -63,6 +119,7 @@ .ifc \r64,%r15 \opd = 15 .endif +#endif .endm .macro XMM_NUM opd xmm @@ -118,10 +175,13 @@ .endm .macro REG_TYPE type reg + R32_NUM reg_type_r32 \reg R64_NUM reg_type_r64 \reg XMM_NUM reg_type_xmm \reg .if reg_type_r64 <> REG_NUM_INVALID \type = REG_TYPE_R64 + .elseif reg_type_r32 <> REG_NUM_INVALID + \type = REG_TYPE_R32 .elseif reg_type_xmm <> REG_NUM_INVALID \type = REG_TYPE_XMM .else @@ -162,6 +222,16 @@ .byte \imm8 .endm + .macro PEXTRD imm8 xmm gpr + R32_NUM extrd_opd1 \gpr + XMM_NUM extrd_opd2 \xmm + PFX_OPD_SIZE + PFX_REX extrd_opd1 extrd_opd2 + .byte 0x0f, 0x3a, 0x16 + MODRM 0xc0 extrd_opd1 extrd_opd2 + .byte \imm8 + .endm + .macro AESKEYGENASSIST rcon xmm1 xmm2 XMM_NUM aeskeygen_opd1 \xmm1 XMM_NUM aeskeygen_opd2 \xmm2 diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h index ba870bb6dd8e..57873beb3292 100644 --- a/arch/x86/include/asm/irq.h +++ b/arch/x86/include/asm/irq.h @@ -41,4 +41,9 @@ extern int vector_used_by_percpu_irq(unsigned int vector); extern void init_ISA_irqs(void); +#ifdef CONFIG_X86_LOCAL_APIC +void arch_trigger_all_cpu_backtrace(void); +#define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace +#endif + #endif /* _ASM_X86_IRQ_H */ diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index 6825e2efd1b4..6bc3985ee473 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -60,11 +60,11 @@ static inline void __exit exit_amd_microcode(void) {} #ifdef CONFIG_MICROCODE_EARLY #define MAX_UCODE_COUNT 128 extern void __init load_ucode_bsp(void); -extern __init void load_ucode_ap(void); +extern void __cpuinit load_ucode_ap(void); extern int __init save_microcode_in_initrd(void); #else static inline void __init load_ucode_bsp(void) {} -static inline __init void load_ucode_ap(void) {} +static inline void __cpuinit load_ucode_ap(void) {} static inline int __init save_microcode_in_initrd(void) { return 0; diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h index c0fa356e90de..86f9301903c8 100644 --- a/arch/x86/include/asm/nmi.h +++ b/arch/x86/include/asm/nmi.h @@ -18,9 +18,7 @@ extern int proc_nmi_enabled(struct ctl_table *, int , void __user *, size_t *, loff_t *); extern int unknown_nmi_panic; -void arch_trigger_all_cpu_backtrace(void); -#define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace -#endif +#endif /* CONFIG_X86_LOCAL_APIC */ #define NMI_FLAG_FIRST 1 diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h index 08744242b8d2..c15ddaf90710 100644 --- a/arch/x86/include/uapi/asm/bootparam.h +++ b/arch/x86/include/uapi/asm/bootparam.h @@ -6,7 +6,6 @@ #define SETUP_E820_EXT 1 #define SETUP_DTB 2 #define SETUP_PCI 3 -#define SETUP_EFI_VARS 4 /* ram_size flags */ #define RAMDISK_IMAGE_START_MASK 0x07FF diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c index 31cb9ae992b7..a698d7165c96 100644 --- a/arch/x86/kernel/apic/hw_nmi.c +++ b/arch/x86/kernel/apic/hw_nmi.c @@ -9,6 +9,7 @@ * */ #include <asm/apic.h> +#include <asm/nmi.h> #include <linux/cpumask.h> #include <linux/kdebug.h> diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c index 35ffda5d0727..5f90b85ff22e 100644 --- a/arch/x86/kernel/cpu/mtrr/cleanup.c +++ b/arch/x86/kernel/cpu/mtrr/cleanup.c @@ -714,15 +714,15 @@ int __init mtrr_cleanup(unsigned address_bits) if (mtrr_tom2) x_remove_size = (mtrr_tom2 >> PAGE_SHIFT) - x_remove_base; - nr_range = x86_get_mtrr_mem_range(range, 0, x_remove_base, x_remove_size); /* * [0, 1M) should always be covered by var mtrr with WB * and fixed mtrrs should take effect before var mtrr for it: */ - nr_range = add_range_with_merge(range, RANGE_NUM, nr_range, 0, + nr_range = add_range_with_merge(range, RANGE_NUM, 0, 0, 1ULL<<(20 - PAGE_SHIFT)); - /* Sort the ranges: */ - sort_range(range, nr_range); + /* add from var mtrr at last */ + nr_range = x86_get_mtrr_mem_range(range, nr_range, + x_remove_base, x_remove_size); range_sums = sum_ranges(range, nr_range); printk(KERN_INFO "total RAM covered: %ldM\n", diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index f60d41ff9a97..a9e22073bd56 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -165,13 +165,13 @@ static struct extra_reg intel_snb_extra_regs[] __read_mostly = { INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0), INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3f807f8fffull, RSP_1), INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), - INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), EVENT_EXTRA_END }; static struct extra_reg intel_snbep_extra_regs[] __read_mostly = { INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0), INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1), + INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), EVENT_EXTRA_END }; diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index dab95a85f7f8..55b67614ed94 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -34,7 +34,7 @@ extern pgd_t early_level4_pgt[PTRS_PER_PGD]; extern pmd_t early_dynamic_pgts[EARLY_DYNAMIC_PAGE_TABLES][PTRS_PER_PMD]; static unsigned int __initdata next_early_pgt = 2; -pmdval_t __initdata early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX); +pmdval_t early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX); /* Wipe all early page tables except for the kernel symbol map */ static void __init reset_early_page_tables(void) diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 08f7e8039099..321d65ebaffe 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -115,8 +115,10 @@ startup_64: movq %rdi, %rax shrq $PUD_SHIFT, %rax andl $(PTRS_PER_PUD-1), %eax - movq %rdx, (4096+0)(%rbx,%rax,8) - movq %rdx, (4096+8)(%rbx,%rax,8) + movq %rdx, 4096(%rbx,%rax,8) + incl %eax + andl $(PTRS_PER_PUD-1), %eax + movq %rdx, 4096(%rbx,%rax,8) addq $8192, %rbx movq %rdi, %rax diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index 245a71db401a..cb339097b9ea 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -22,23 +22,19 @@ /* * Were we in an interrupt that interrupted kernel mode? * - * For now, with eagerfpu we will return interrupted kernel FPU - * state as not-idle. TBD: Ideally we can change the return value - * to something like __thread_has_fpu(current). But we need to - * be careful of doing __thread_clear_has_fpu() before saving - * the FPU etc for supporting nested uses etc. For now, take - * the simple route! - * * On others, we can do a kernel_fpu_begin/end() pair *ONLY* if that * pair does nothing at all: the thread must not have fpu (so * that we don't try to save the FPU state), and TS must * be set (so that the clts/stts pair does nothing that is * visible in the interrupted kernel thread). + * + * Except for the eagerfpu case when we return 1 unless we've already + * been eager and saved the state in kernel_fpu_begin(). */ static inline bool interrupted_kernel_fpu_idle(void) { if (use_eager_fpu()) - return 0; + return __thread_has_fpu(current); return !__thread_has_fpu(current) && (read_cr0() & X86_CR0_TS); @@ -78,8 +74,8 @@ void __kernel_fpu_begin(void) struct task_struct *me = current; if (__thread_has_fpu(me)) { - __save_init_fpu(me); __thread_clear_has_fpu(me); + __save_init_fpu(me); /* We do 'stts()' in __kernel_fpu_end() */ } else if (!use_eager_fpu()) { this_cpu_write(fpu_owner_task, NULL); diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index d2c381280e3c..3dd37ebd591b 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -242,6 +242,7 @@ void __init kvmclock_init(void) if (!mem) return; hv_clock = __va(mem); + memset(hv_clock, 0, size); if (kvm_register_clock("boot clock")) { hv_clock = NULL; diff --git a/arch/x86/kernel/microcode_intel_early.c b/arch/x86/kernel/microcode_intel_early.c index d893e8ed8ac9..2e9e12871c2b 100644 --- a/arch/x86/kernel/microcode_intel_early.c +++ b/arch/x86/kernel/microcode_intel_early.c @@ -487,6 +487,7 @@ static inline void show_saved_mc(void) #endif #if defined(CONFIG_MICROCODE_INTEL_EARLY) && defined(CONFIG_HOTPLUG_CPU) +static DEFINE_MUTEX(x86_cpu_microcode_mutex); /* * Save this mc into mc_saved_data. So it will be loaded early when a CPU is * hot added or resumes. @@ -507,7 +508,7 @@ int save_mc_for_early(u8 *mc) * Hold hotplug lock so mc_saved_data is not accessed by a CPU in * hotplug. */ - cpu_hotplug_driver_lock(); + mutex_lock(&x86_cpu_microcode_mutex); mc_saved_count_init = mc_saved_data.mc_saved_count; mc_saved_count = mc_saved_data.mc_saved_count; @@ -544,7 +545,7 @@ int save_mc_for_early(u8 *mc) } out: - cpu_hotplug_driver_unlock(); + mutex_unlock(&x86_cpu_microcode_mutex); return ret; } diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 607af0d4d5ef..81a5f5e8f142 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -277,18 +277,6 @@ void exit_idle(void) } #endif -void arch_cpu_idle_prepare(void) -{ - /* - * If we're the non-boot CPU, nothing set the stack canary up - * for us. CPU0 already has it initialized but no harm in - * doing it again. This is a good place for updating it, as - * we wont ever return from this function (so the invalid - * canaries already on the stack wont ever trigger). - */ - boot_init_stack_canary(); -} - void arch_cpu_idle_enter(void) { local_touch_nmi(); @@ -312,6 +300,8 @@ void arch_cpu_idle(void) { if (cpuidle_idle_call()) x86_idle(); + else + local_irq_enable(); } /* @@ -368,9 +358,6 @@ void amd_e400_remove_cpu(int cpu) */ static void amd_e400_idle(void) { - if (need_resched()) - return; - if (!amd_e400_c1e_detected) { u32 lo, hi; diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S index 7a6f3b3be3cf..f2bb9c96720a 100644 --- a/arch/x86/kernel/relocate_kernel_64.S +++ b/arch/x86/kernel/relocate_kernel_64.S @@ -160,7 +160,7 @@ identity_mapped: xorq %rbp, %rbp xorq %r8, %r8 xorq %r9, %r9 - xorq %r10, %r9 + xorq %r10, %r10 xorq %r11, %r11 xorq %r12, %r12 xorq %r13, %r13 diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 9c73b51817e4..bfd348e99369 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -372,15 +372,15 @@ static bool __cpuinit match_mc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) void __cpuinit set_cpu_sibling_map(int cpu) { - bool has_mc = boot_cpu_data.x86_max_cores > 1; bool has_smt = smp_num_siblings > 1; + bool has_mp = has_smt || boot_cpu_data.x86_max_cores > 1; struct cpuinfo_x86 *c = &cpu_data(cpu); struct cpuinfo_x86 *o; int i; cpumask_set_cpu(cpu, cpu_sibling_setup_mask); - if (!has_smt && !has_mc) { + if (!has_mp) { cpumask_set_cpu(cpu, cpu_sibling_mask(cpu)); cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu)); cpumask_set_cpu(cpu, cpu_core_mask(cpu)); @@ -394,7 +394,7 @@ void __cpuinit set_cpu_sibling_map(int cpu) if ((i == cpu) || (has_smt && match_smt(c, o))) link_mask(sibling, cpu, i); - if ((i == cpu) || (has_mc && match_llc(c, o))) + if ((i == cpu) || (has_mp && match_llc(c, o))) link_mask(llc_shared, cpu, i); } @@ -406,7 +406,7 @@ void __cpuinit set_cpu_sibling_map(int cpu) for_each_cpu(i, cpu_sibling_setup_mask) { o = &cpu_data(i); - if ((i == cpu) || (has_mc && match_mc(c, o))) { + if ((i == cpu) || (has_mp && match_mc(c, o))) { link_mask(core, cpu, i); /* diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 8db0010ed150..5953dcea752d 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -1240,9 +1240,12 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt, ctxt->modrm_seg = VCPU_SREG_DS; if (ctxt->modrm_mod == 3) { + int highbyte_regs = ctxt->rex_prefix == 0; + op->type = OP_REG; op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; - op->addr.reg = decode_register(ctxt, ctxt->modrm_rm, ctxt->d & ByteOp); + op->addr.reg = decode_register(ctxt, ctxt->modrm_rm, + highbyte_regs && (ctxt->d & ByteOp)); if (ctxt->d & Sse) { op->type = OP_XMM; op->bytes = 16; @@ -3997,7 +4000,8 @@ static const struct opcode twobyte_table[256] = { DI(ImplicitOps | Priv, invd), DI(ImplicitOps | Priv, wbinvd), N, N, N, D(ImplicitOps | ModRM), N, N, /* 0x10 - 0x1F */ - N, N, N, N, N, N, N, N, D(ImplicitOps | ModRM), N, N, N, N, N, N, N, + N, N, N, N, N, N, N, N, + D(ImplicitOps | ModRM), N, N, N, N, N, N, D(ImplicitOps | ModRM), /* 0x20 - 0x2F */ DIP(ModRM | DstMem | Priv | Op3264, cr_read, check_cr_read), DIP(ModRM | DstMem | Priv | Op3264, dr_read, check_dr_read), @@ -4836,6 +4840,7 @@ twobyte_insn: case 0x08: /* invd */ case 0x0d: /* GrpP (prefetch) */ case 0x18: /* Grp16 (prefetch/nop) */ + case 0x1f: /* nop */ break; case 0x20: /* mov cr, reg */ ctxt->dst.val = ops->get_cr(ctxt, ctxt->modrm_reg); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index e1adbb4aca75..0eee2c8b64d1 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1861,11 +1861,14 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; unsigned int sipi_vector; + unsigned long pe; - if (!kvm_vcpu_has_lapic(vcpu)) + if (!kvm_vcpu_has_lapic(vcpu) || !apic->pending_events) return; - if (test_and_clear_bit(KVM_APIC_INIT, &apic->pending_events)) { + pe = xchg(&apic->pending_events, 0); + + if (test_bit(KVM_APIC_INIT, &pe)) { kvm_lapic_reset(vcpu); kvm_vcpu_reset(vcpu); if (kvm_vcpu_is_bsp(apic->vcpu)) @@ -1873,7 +1876,7 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu) else vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED; } - if (test_and_clear_bit(KVM_APIC_SIPI, &apic->pending_events) && + if (test_bit(KVM_APIC_SIPI, &pe) && vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) { /* evaluate pending_events before reading the vector */ smp_rmb(); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 094b5d96ab14..e8ba99c34180 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -582,8 +582,6 @@ int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) if (index != XCR_XFEATURE_ENABLED_MASK) return 1; xcr0 = xcr; - if (kvm_x86_ops->get_cpl(vcpu) != 0) - return 1; if (!(xcr0 & XSTATE_FP)) return 1; if ((xcr0 & XSTATE_YMM) && !(xcr0 & XSTATE_SSE)) @@ -597,7 +595,8 @@ int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) { - if (__kvm_set_xcr(vcpu, index, xcr)) { + if (kvm_x86_ops->get_cpl(vcpu) != 0 || + __kvm_set_xcr(vcpu, index, xcr)) { kvm_inject_gp(vcpu, 0); return 1; } diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index fdc5dca14fb3..1f34e9219775 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -277,6 +277,9 @@ static int __meminit split_mem_range(struct map_range *mr, int nr_range, end_pfn = limit_pfn; nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0); + if (!after_bootmem) + adjust_range_page_size_mask(mr, nr_range); + /* try to merge same page size and continuous */ for (i = 0; nr_range > 1 && i < nr_range - 1; i++) { unsigned long old_start; @@ -291,9 +294,6 @@ static int __meminit split_mem_range(struct map_range *mr, int nr_range, nr_range--; } - if (!after_bootmem) - adjust_range_page_size_mask(mr, nr_range); - for (i = 0; i < nr_range; i++) printk(KERN_DEBUG " [mem %#010lx-%#010lx] page %s\n", mr[i].start, mr[i].end - 1, @@ -359,7 +359,17 @@ unsigned long __init_refok init_memory_mapping(unsigned long start, } /* - * would have hole in the middle or ends, and only ram parts will be mapped. + * We need to iterate through the E820 memory map and create direct mappings + * for only E820_RAM and E820_KERN_RESERVED regions. We cannot simply + * create direct mappings for all pfns from [0 to max_low_pfn) and + * [4GB to max_pfn) because of possible memory holes in high addresses + * that cannot be marked as UC by fixed/variable range MTRRs. + * Depending on the alignment of E820 ranges, this may possibly result + * in using smaller size (i.e. 4K instead of 2M or 1G) page tables. + * + * init_mem_mapping() calls init_range_memory_mapping() with big range. + * That range would have hole in the middle or ends, and only ram parts + * will be mapped in init_range_memory_mapping(). */ static unsigned long __init init_range_memory_mapping( unsigned long r_start, @@ -419,6 +429,13 @@ void __init init_mem_mapping(void) max_pfn_mapped = 0; /* will get exact value next */ min_pfn_mapped = real_end >> PAGE_SHIFT; last_start = start = real_end; + + /* + * We start from the top (end of memory) and go to the bottom. + * The memblock_find_in_range() gets us a block of RAM from the + * end of RAM in [min_pfn_mapped, max_pfn_mapped) used as new pages + * for page table. + */ while (last_start > ISA_END_ADDRESS) { if (last_start > step_size) { start = round_down(last_start - 1, step_size); diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 305c68b8d538..981c2dbd72cc 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -628,7 +628,9 @@ int pcibios_add_device(struct pci_dev *dev) pa_data = boot_params.hdr.setup_data; while (pa_data) { - data = phys_to_virt(pa_data); + data = ioremap(pa_data, sizeof(*rom)); + if (!data) + return -ENOMEM; if (data->type == SETUP_PCI) { rom = (struct pci_setup_rom *)data; @@ -645,6 +647,7 @@ int pcibios_add_device(struct pci_dev *dev) } } pa_data = data->next; + iounmap(data); } return 0; } diff --git a/arch/x86/pci/mrst.c b/arch/x86/pci/mrst.c index 0e0fabf17342..6eb18c42a28a 100644 --- a/arch/x86/pci/mrst.c +++ b/arch/x86/pci/mrst.c @@ -141,11 +141,6 @@ static int pci_device_update_fixed(struct pci_bus *bus, unsigned int devfn, */ static bool type1_access_ok(unsigned int bus, unsigned int devfn, int reg) { - if (bus == 0 && (devfn == PCI_DEVFN(2, 0) - || devfn == PCI_DEVFN(0, 0) - || devfn == PCI_DEVFN(3, 0))) - return 1; - /* This is a workaround for A0 LNC bug where PCI status register does * not have new CAP bit set. can not be written by SW either. * @@ -155,7 +150,10 @@ static bool type1_access_ok(unsigned int bus, unsigned int devfn, int reg) */ if (reg >= 0x100 || reg == PCI_STATUS || reg == PCI_HEADER_TYPE) return 0; - + if (bus == 0 && (devfn == PCI_DEVFN(2, 0) + || devfn == PCI_DEVFN(0, 0) + || devfn == PCI_DEVFN(3, 0))) + return 1; return 0; /* langwell on others */ } diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 55856b2310d3..d2fbcedcf6ea 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -42,7 +42,6 @@ #include <linux/io.h> #include <linux/reboot.h> #include <linux/bcd.h> -#include <linux/ucs2_string.h> #include <asm/setup.h> #include <asm/efi.h> @@ -54,12 +53,12 @@ #define EFI_DEBUG 1 -/* - * There's some additional metadata associated with each - * variable. Intel's reference implementation is 60 bytes - bump that - * to account for potential alignment constraints - */ -#define VAR_METADATA_SIZE 64 +#define EFI_MIN_RESERVE 5120 + +#define EFI_DUMMY_GUID \ + EFI_GUID(0x4424ac57, 0xbe4b, 0x47dd, 0x9e, 0x97, 0xed, 0x50, 0xf0, 0x9f, 0x92, 0xa9) + +static efi_char16_t efi_dummy_name[6] = { 'D', 'U', 'M', 'M', 'Y', 0 }; struct efi __read_mostly efi = { .mps = EFI_INVALID_TABLE_ADDR, @@ -79,13 +78,6 @@ struct efi_memory_map memmap; static struct efi efi_phys __initdata; static efi_system_table_t efi_systab __initdata; -static u64 efi_var_store_size; -static u64 efi_var_remaining_size; -static u64 efi_var_max_var_size; -static u64 boot_used_size; -static u64 boot_var_size; -static u64 active_size; - unsigned long x86_efi_facility; /* @@ -188,53 +180,8 @@ static efi_status_t virt_efi_get_next_variable(unsigned long *name_size, efi_char16_t *name, efi_guid_t *vendor) { - efi_status_t status; - static bool finished = false; - static u64 var_size; - - status = efi_call_virt3(get_next_variable, - name_size, name, vendor); - - if (status == EFI_NOT_FOUND) { - finished = true; - if (var_size < boot_used_size) { - boot_var_size = boot_used_size - var_size; - active_size += boot_var_size; - } else { - printk(KERN_WARNING FW_BUG "efi: Inconsistent initial sizes\n"); - } - } - - if (boot_used_size && !finished) { - unsigned long size; - u32 attr; - efi_status_t s; - void *tmp; - - s = virt_efi_get_variable(name, vendor, &attr, &size, NULL); - - if (s != EFI_BUFFER_TOO_SMALL || !size) - return status; - - tmp = kmalloc(size, GFP_ATOMIC); - - if (!tmp) - return status; - - s = virt_efi_get_variable(name, vendor, &attr, &size, tmp); - - if (s == EFI_SUCCESS && (attr & EFI_VARIABLE_NON_VOLATILE)) { - var_size += size; - var_size += ucs2_strsize(name, 1024); - active_size += size; - active_size += VAR_METADATA_SIZE; - active_size += ucs2_strsize(name, 1024); - } - - kfree(tmp); - } - - return status; + return efi_call_virt3(get_next_variable, + name_size, name, vendor); } static efi_status_t virt_efi_set_variable(efi_char16_t *name, @@ -243,34 +190,9 @@ static efi_status_t virt_efi_set_variable(efi_char16_t *name, unsigned long data_size, void *data) { - efi_status_t status; - u32 orig_attr = 0; - unsigned long orig_size = 0; - - status = virt_efi_get_variable(name, vendor, &orig_attr, &orig_size, - NULL); - - if (status != EFI_BUFFER_TOO_SMALL) - orig_size = 0; - - status = efi_call_virt5(set_variable, - name, vendor, attr, - data_size, data); - - if (status == EFI_SUCCESS) { - if (orig_size) { - active_size -= orig_size; - active_size -= ucs2_strsize(name, 1024); - active_size -= VAR_METADATA_SIZE; - } - if (data_size) { - active_size += data_size; - active_size += ucs2_strsize(name, 1024); - active_size += VAR_METADATA_SIZE; - } - } - - return status; + return efi_call_virt5(set_variable, + name, vendor, attr, + data_size, data); } static efi_status_t virt_efi_query_variable_info(u32 attr, @@ -786,9 +708,6 @@ void __init efi_init(void) char vendor[100] = "unknown"; int i = 0; void *tmp; - struct setup_data *data; - struct efi_var_bootdata *efi_var_data; - u64 pa_data; #ifdef CONFIG_X86_32 if (boot_params.efi_info.efi_systab_hi || @@ -806,22 +725,6 @@ void __init efi_init(void) if (efi_systab_init(efi_phys.systab)) return; - pa_data = boot_params.hdr.setup_data; - while (pa_data) { - data = early_ioremap(pa_data, sizeof(*efi_var_data)); - if (data->type == SETUP_EFI_VARS) { - efi_var_data = (struct efi_var_bootdata *)data; - - efi_var_store_size = efi_var_data->store_size; - efi_var_remaining_size = efi_var_data->remaining_size; - efi_var_max_var_size = efi_var_data->max_var_size; - } - pa_data = data->next; - early_iounmap(data, sizeof(*efi_var_data)); - } - - boot_used_size = efi_var_store_size - efi_var_remaining_size; - set_bit(EFI_SYSTEM_TABLES, &x86_efi_facility); /* @@ -1085,6 +988,13 @@ void __init efi_enter_virtual_mode(void) runtime_code_page_mkexec(); kfree(new_memmap); + + /* clean DUMMY object */ + efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID, + EFI_VARIABLE_NON_VOLATILE | + EFI_VARIABLE_BOOTSERVICE_ACCESS | + EFI_VARIABLE_RUNTIME_ACCESS, + 0, NULL); } /* @@ -1136,33 +1046,70 @@ efi_status_t efi_query_variable_store(u32 attributes, unsigned long size) efi_status_t status; u64 storage_size, remaining_size, max_size; + if (!(attributes & EFI_VARIABLE_NON_VOLATILE)) + return 0; + status = efi.query_variable_info(attributes, &storage_size, &remaining_size, &max_size); if (status != EFI_SUCCESS) return status; - if (!max_size && remaining_size > size) - printk_once(KERN_ERR FW_BUG "Broken EFI implementation" - " is returning MaxVariableSize=0\n"); /* * Some firmware implementations refuse to boot if there's insufficient * space in the variable store. We account for that by refusing the * write if permitting it would reduce the available space to under - * 50%. However, some firmware won't reclaim variable space until - * after the used (not merely the actively used) space drops below - * a threshold. We can approximate that case with the value calculated - * above. If both the firmware and our calculations indicate that the - * available space would drop below 50%, refuse the write. + * 5KB. This figure was provided by Samsung, so should be safe. */ + if ((remaining_size - size < EFI_MIN_RESERVE) && + !efi_no_storage_paranoia) { + + /* + * Triggering garbage collection may require that the firmware + * generate a real EFI_OUT_OF_RESOURCES error. We can force + * that by attempting to use more space than is available. + */ + unsigned long dummy_size = remaining_size + 1024; + void *dummy = kzalloc(dummy_size, GFP_ATOMIC); + + if (!dummy) + return EFI_OUT_OF_RESOURCES; + + status = efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID, + EFI_VARIABLE_NON_VOLATILE | + EFI_VARIABLE_BOOTSERVICE_ACCESS | + EFI_VARIABLE_RUNTIME_ACCESS, + dummy_size, dummy); + + if (status == EFI_SUCCESS) { + /* + * This should have failed, so if it didn't make sure + * that we delete it... + */ + efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID, + EFI_VARIABLE_NON_VOLATILE | + EFI_VARIABLE_BOOTSERVICE_ACCESS | + EFI_VARIABLE_RUNTIME_ACCESS, + 0, dummy); + } + + kfree(dummy); - if (!storage_size || size > remaining_size || - (max_size && size > max_size)) - return EFI_OUT_OF_RESOURCES; + /* + * The runtime code may now have triggered a garbage collection + * run, so check the variable info again + */ + status = efi.query_variable_info(attributes, &storage_size, + &remaining_size, &max_size); - if (!efi_no_storage_paranoia && - ((active_size + size + VAR_METADATA_SIZE > storage_size / 2) && - (remaining_size - size < storage_size / 2))) - return EFI_OUT_OF_RESOURCES; + if (status != EFI_SUCCESS) + return status; + + /* + * There still isn't enough room, so return an error + */ + if (remaining_size - size < EFI_MIN_RESERVE) + return EFI_OUT_OF_RESOURCES; + } return EFI_SUCCESS; } diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c index 590be1090892..f7bab68a4b83 100644 --- a/arch/x86/tools/relocs.c +++ b/arch/x86/tools/relocs.c @@ -42,9 +42,6 @@ static const char * const sym_regex_kernel[S_NSYMTYPES] = { "^(xen_irq_disable_direct_reloc$|" "xen_save_fl_direct_reloc$|" "VDSO|" -#if ELF_BITS == 64 - "__vvar_page|" -#endif "__crc_)", /* @@ -72,6 +69,7 @@ static const char * const sym_regex_kernel[S_NSYMTYPES] = { "__per_cpu_load|" "init_per_cpu__.*|" "__end_rodata_hpage_align|" + "__vvar_page|" #endif "_end)$" }; diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 8ff37995d54e..d99cae8147d1 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -17,6 +17,7 @@ #include <linux/slab.h> #include <linux/smp.h> #include <linux/irq_work.h> +#include <linux/tick.h> #include <asm/paravirt.h> #include <asm/desc.h> @@ -447,6 +448,13 @@ static void __cpuinit xen_play_dead(void) /* used only with HOTPLUG_CPU */ play_dead_common(); HYPERVISOR_vcpu_op(VCPUOP_down, smp_processor_id(), NULL); cpu_bringup(); + /* + * commit 4b0c0f294 (tick: Cleanup NOHZ per cpu data on cpu down) + * clears certain data that the cpu_idle loop (which called us + * and that we return from) expects. The only way to get that + * data back is to call: + */ + tick_nohz_idle_enter(); } #else /* !CONFIG_HOTPLUG_CPU */ @@ -576,24 +584,22 @@ void xen_send_IPI_mask_allbutself(const struct cpumask *mask, { unsigned cpu; unsigned int this_cpu = smp_processor_id(); + int xen_vector = xen_map_vector(vector); - if (!(num_online_cpus() > 1)) + if (!(num_online_cpus() > 1) || (xen_vector < 0)) return; for_each_cpu_and(cpu, mask, cpu_online_mask) { if (this_cpu == cpu) continue; - xen_smp_send_call_function_single_ipi(cpu); + xen_send_IPI_one(cpu, xen_vector); } } void xen_send_IPI_allbutself(int vector) { - int xen_vector = xen_map_vector(vector); - - if (xen_vector >= 0) - xen_send_IPI_mask_allbutself(cpu_online_mask, xen_vector); + xen_send_IPI_mask_allbutself(cpu_online_mask, vector); } static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id) diff --git a/arch/x86/xen/smp.h b/arch/x86/xen/smp.h index 8981a76d081a..c7c2d89efd76 100644 --- a/arch/x86/xen/smp.h +++ b/arch/x86/xen/smp.h @@ -5,7 +5,6 @@ extern void xen_send_IPI_mask(const struct cpumask *mask, extern void xen_send_IPI_mask_allbutself(const struct cpumask *mask, int vector); extern void xen_send_IPI_allbutself(int vector); -extern void physflat_send_IPI_allbutself(int vector); extern void xen_send_IPI_all(int vector); extern void xen_send_IPI_self(int vector); |