diff options
Diffstat (limited to 'arch/x86')
71 files changed, 548 insertions, 366 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 93698794aa3a..c876bace8fdc 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -86,10 +86,6 @@ config STACKTRACE_SUPPORT config HAVE_LATENCYTOP_SUPPORT def_bool y -config FAST_CMPXCHG_LOCAL - bool - default y - config MMU def_bool y @@ -432,6 +428,17 @@ config X86_NUMAQ of Flat Logical. You will need a new lynxer.elf file to flash your firmware with - send email to <Martin.Bligh@us.ibm.com>. +config X86_SUPPORTS_MEMORY_FAILURE + bool + # MCE code calls memory_failure(): + depends on X86_MCE + # On 32-bit this adds too big of NODES_SHIFT and we run out of page flags: + depends on !X86_NUMAQ + # On 32-bit SPARSEMEM adds too big of SECTIONS_WIDTH: + depends on X86_64 || !SPARSEMEM + select ARCH_SUPPORTS_MEMORY_FAILURE + default y + config X86_VISWS bool "SGI 320/540 (Visual Workstation)" depends on X86_32 && PCI && X86_MPPARSE && PCI_GODIRECT diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 527519b8a9f9..f2824fb8c79c 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -400,7 +400,7 @@ config X86_TSC config X86_CMPXCHG64 def_bool y - depends on X86_PAE || X86_64 + depends on X86_PAE || X86_64 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MATOM # this should be set for all -march=.. options where the compiler # generates cmov. @@ -412,6 +412,7 @@ config X86_MINIMUM_CPU_FAMILY int default "64" if X86_64 default "6" if X86_32 && X86_P6_NOP + default "5" if X86_32 && X86_CMPXCHG64 default "4" if X86_32 && (X86_XADD || X86_CMPXCHG || X86_BSWAP || X86_WP_WORKS_OK) default "3" diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 7983c420eaf2..a012ee8ef803 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -179,8 +179,8 @@ archclean: define archhelp echo '* bzImage - Compressed kernel image (arch/x86/boot/bzImage)' echo ' install - Install kernel using' - echo ' (your) ~/bin/installkernel or' - echo ' (distribution) /sbin/installkernel or' + echo ' (your) ~/bin/$(INSTALLKERNEL) or' + echo ' (distribution) /sbin/$(INSTALLKERNEL) or' echo ' install to $$(INSTALL_PATH) and run lilo' echo ' fdimage - Create 1.4MB boot floppy image (arch/x86/boot/fdimage)' echo ' fdimage144 - Create 1.4MB boot floppy image (arch/x86/boot/fdimage)' diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index 75e4f001e706..f543b70ffae2 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -23,13 +23,14 @@ */ .text +#include <linux/init.h> #include <linux/linkage.h> #include <asm/segment.h> #include <asm/page_types.h> #include <asm/boot.h> #include <asm/asm-offsets.h> - .section ".text.head","ax",@progbits + __HEAD ENTRY(startup_32) cld /* diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index f62c284db9eb..077e1b69198e 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -24,6 +24,7 @@ .code32 .text +#include <linux/init.h> #include <linux/linkage.h> #include <asm/segment.h> #include <asm/pgtable_types.h> @@ -33,7 +34,7 @@ #include <asm/processor-flags.h> #include <asm/asm-offsets.h> - .section ".text.head" + __HEAD .code32 ENTRY(startup_32) cld diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S index cc353e1b3ffd..f4193bb48782 100644 --- a/arch/x86/boot/compressed/vmlinux.lds.S +++ b/arch/x86/boot/compressed/vmlinux.lds.S @@ -1,3 +1,5 @@ +#include <asm-generic/vmlinux.lds.h> + OUTPUT_FORMAT(CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT) #undef i386 @@ -18,9 +20,9 @@ SECTIONS * address 0. */ . = 0; - .text.head : { + .head.text : { _head = . ; - *(.text.head) + HEAD_TEXT _ehead = . ; } .rodata.compressed : { diff --git a/arch/x86/boot/install.sh b/arch/x86/boot/install.sh index 8d60ee15dfd9..d13ec1c38640 100644 --- a/arch/x86/boot/install.sh +++ b/arch/x86/boot/install.sh @@ -33,8 +33,8 @@ verify "$3" # User may have a custom install script -if [ -x ~/bin/${CROSS_COMPILE}installkernel ]; then exec ~/bin/${CROSS_COMPILE}installkernel "$@"; fi -if [ -x /sbin/${CROSS_COMPILE}installkernel ]; then exec /sbin/${CROSS_COMPILE}installkernel "$@"; fi +if [ -x ~/bin/${INSTALLKERNEL} ]; then exec ~/bin/${INSTALLKERNEL} "$@"; fi +if [ -x /sbin/${INSTALLKERNEL} ]; then exec /sbin/${INSTALLKERNEL} "$@"; fi # Default install - same as make zlilo diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 74619c4f9fda..1733f9f65e82 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -21,8 +21,8 @@ #define __AUDIT_ARCH_LE 0x40000000 #ifndef CONFIG_AUDITSYSCALL -#define sysexit_audit int_ret_from_sys_call -#define sysretl_audit int_ret_from_sys_call +#define sysexit_audit ia32_ret_from_sys_call +#define sysretl_audit ia32_ret_from_sys_call #endif #define IA32_NR_syscalls ((ia32_syscall_end - ia32_sys_call_table)/8) @@ -39,12 +39,12 @@ .endm /* clobbers %eax */ - .macro CLEAR_RREGS _r9=rax + .macro CLEAR_RREGS offset=0, _r9=rax xorl %eax,%eax - movq %rax,R11(%rsp) - movq %rax,R10(%rsp) - movq %\_r9,R9(%rsp) - movq %rax,R8(%rsp) + movq %rax,\offset+R11(%rsp) + movq %rax,\offset+R10(%rsp) + movq %\_r9,\offset+R9(%rsp) + movq %rax,\offset+R8(%rsp) .endm /* @@ -172,6 +172,10 @@ sysexit_from_sys_call: movl RIP-R11(%rsp),%edx /* User %eip */ CFI_REGISTER rip,rdx RESTORE_ARGS 1,24,1,1,1,1 + xorq %r8,%r8 + xorq %r9,%r9 + xorq %r10,%r10 + xorq %r11,%r11 popfq CFI_ADJUST_CFA_OFFSET -8 /*CFI_RESTORE rflags*/ @@ -202,7 +206,7 @@ sysexit_from_sys_call: .macro auditsys_exit exit,ebpsave=RBP testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),TI_flags(%r10) - jnz int_ret_from_sys_call + jnz ia32_ret_from_sys_call TRACE_IRQS_ON sti movl %eax,%esi /* second arg, syscall return value */ @@ -218,8 +222,9 @@ sysexit_from_sys_call: cli TRACE_IRQS_OFF testl %edi,TI_flags(%r10) - jnz int_with_check - jmp \exit + jz \exit + CLEAR_RREGS -ARGOFFSET + jmp int_with_check .endm sysenter_auditsys: @@ -329,6 +334,9 @@ sysretl_from_sys_call: CFI_REGISTER rip,rcx movl EFLAGS-ARGOFFSET(%rsp),%r11d /*CFI_REGISTER rflags,r11*/ + xorq %r10,%r10 + xorq %r9,%r9 + xorq %r8,%r8 TRACE_IRQS_ON movl RSP-ARGOFFSET(%rsp),%esp CFI_RESTORE rsp @@ -353,7 +361,7 @@ cstar_tracesys: #endif xchgl %r9d,%ebp SAVE_REST - CLEAR_RREGS r9 + CLEAR_RREGS 0, r9 movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */ movq %rsp,%rdi /* &pt_regs -> arg1 */ call syscall_trace_enter @@ -425,6 +433,8 @@ ia32_do_call: call *ia32_sys_call_table(,%rax,8) # xxx: rip relative ia32_sysret: movq %rax,RAX-ARGOFFSET(%rsp) +ia32_ret_from_sys_call: + CLEAR_RREGS -ARGOFFSET jmp int_ret_from_sys_call ia32_tracesys: @@ -442,8 +452,8 @@ END(ia32_syscall) ia32_badsys: movq $0,ORIG_RAX-ARGOFFSET(%rsp) - movq $-ENOSYS,RAX-ARGOFFSET(%rsp) - jmp int_ret_from_sys_call + movq $-ENOSYS,%rax + jmp ia32_sysret quiet_ni_syscall: movq $-ENOSYS,%rax diff --git a/arch/x86/include/asm/cache.h b/arch/x86/include/asm/cache.h index 5d367caa0e36..549860d3be8f 100644 --- a/arch/x86/include/asm/cache.h +++ b/arch/x86/include/asm/cache.h @@ -1,6 +1,8 @@ #ifndef _ASM_X86_CACHE_H #define _ASM_X86_CACHE_H +#include <linux/linkage.h> + /* L1 cache line size */ #define L1_CACHE_SHIFT (CONFIG_X86_L1_CACHE_SHIFT) #define L1_CACHE_BYTES (1 << L1_CACHE_SHIFT) @@ -13,7 +15,7 @@ #ifdef CONFIG_SMP #define __cacheline_aligned_in_smp \ __attribute__((__aligned__(1 << (INTERNODE_CACHE_SHIFT)))) \ - __attribute__((__section__(".data.page_aligned"))) + __page_aligned_data #endif #endif diff --git a/arch/x86/include/asm/checksum_32.h b/arch/x86/include/asm/checksum_32.h index 7c5ef8b14d92..46fc474fd819 100644 --- a/arch/x86/include/asm/checksum_32.h +++ b/arch/x86/include/asm/checksum_32.h @@ -161,7 +161,8 @@ static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr, "adcl $0, %0 ;\n" : "=&r" (sum) : "r" (saddr), "r" (daddr), - "r" (htonl(len)), "r" (htonl(proto)), "0" (sum)); + "r" (htonl(len)), "r" (htonl(proto)), "0" (sum) + : "memory"); return csum_fold(sum); } diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h index 82ceb788a981..ee1931be6593 100644 --- a/arch/x86/include/asm/cmpxchg_32.h +++ b/arch/x86/include/asm/cmpxchg_32.h @@ -312,19 +312,23 @@ static inline unsigned long cmpxchg_386(volatile void *ptr, unsigned long old, extern unsigned long long cmpxchg_486_u64(volatile void *, u64, u64); -#define cmpxchg64(ptr, o, n) \ -({ \ - __typeof__(*(ptr)) __ret; \ - if (likely(boot_cpu_data.x86 > 4)) \ - __ret = (__typeof__(*(ptr)))__cmpxchg64((ptr), \ - (unsigned long long)(o), \ - (unsigned long long)(n)); \ - else \ - __ret = (__typeof__(*(ptr)))cmpxchg_486_u64((ptr), \ - (unsigned long long)(o), \ - (unsigned long long)(n)); \ - __ret; \ -}) +#define cmpxchg64(ptr, o, n) \ +({ \ + __typeof__(*(ptr)) __ret; \ + __typeof__(*(ptr)) __old = (o); \ + __typeof__(*(ptr)) __new = (n); \ + alternative_io("call cmpxchg8b_emu", \ + "lock; cmpxchg8b (%%esi)" , \ + X86_FEATURE_CX8, \ + "=A" (__ret), \ + "S" ((ptr)), "0" (__old), \ + "b" ((unsigned int)__new), \ + "c" ((unsigned int)(__new>>32)) \ + : "memory"); \ + __ret; }) + + + #define cmpxchg64_local(ptr, o, n) \ ({ \ __typeof__(*(ptr)) __ret; \ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 3be000435fad..d83892226f73 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -796,6 +796,7 @@ asmlinkage void kvm_handle_fault_on_reboot(void); #define KVM_ARCH_WANT_MMU_NOTIFIER int kvm_unmap_hva(struct kvm *kvm, unsigned long hva); int kvm_age_hva(struct kvm *kvm, unsigned long hva); +void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); int cpuid_maxphyaddr(struct kvm_vcpu *vcpu); int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu); int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu); diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index b608a64c5814..f1363b72364f 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -133,6 +133,8 @@ static inline void winchip_mcheck_init(struct cpuinfo_x86 *c) {} static inline void enable_p5_mce(void) {} #endif +extern void (*x86_mce_decode_callback)(struct mce *m); + void mce_setup(struct mce *m); void mce_log(struct mce *m); DECLARE_PER_CPU(struct sys_device, mce_dev); diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index f923203dc39a..4a2d4e0c18d9 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -37,12 +37,12 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, if (likely(prev != next)) { /* stop flush ipis for the previous mm */ - cpu_clear(cpu, prev->cpu_vm_mask); + cpumask_clear_cpu(cpu, mm_cpumask(prev)); #ifdef CONFIG_SMP percpu_write(cpu_tlbstate.state, TLBSTATE_OK); percpu_write(cpu_tlbstate.active_mm, next); #endif - cpu_set(cpu, next->cpu_vm_mask); + cpumask_set_cpu(cpu, mm_cpumask(next)); /* Re-load page tables */ load_cr3(next->pgd); @@ -58,7 +58,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, percpu_write(cpu_tlbstate.state, TLBSTATE_OK); BUG_ON(percpu_read(cpu_tlbstate.active_mm) != next); - if (!cpu_test_and_set(cpu, next->cpu_vm_mask)) { + if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next))) { /* We were in lazy tlb mode and leave_mm disabled * tlb flush IPI delivery. We must reload CR3 * to make sure to use no freed page tables. diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h index e63cf7d441e1..139d4c1a33a7 100644 --- a/arch/x86/include/asm/nmi.h +++ b/arch/x86/include/asm/nmi.h @@ -40,8 +40,7 @@ extern unsigned int nmi_watchdog; #define NMI_INVALID 3 struct ctl_table; -struct file; -extern int proc_nmi_enabled(struct ctl_table *, int , struct file *, +extern int proc_nmi_enabled(struct ctl_table *, int , void __user *, size_t *, loff_t *); extern int unknown_nmi_panic; diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index f76a162c082c..ada8c201d513 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm/pci.h @@ -143,7 +143,11 @@ static inline int __pcibus_to_node(const struct pci_bus *bus) static inline const struct cpumask * cpumask_of_pcibus(const struct pci_bus *bus) { - return cpumask_of_node(__pcibus_to_node(bus)); + int node; + + node = __pcibus_to_node(bus); + return (node == -1) ? cpu_online_mask : + cpumask_of_node(node); } #endif diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 7b467bf3c680..d1f4a760be23 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -277,6 +277,7 @@ static inline pteval_t pte_flags(pte_t pte) typedef struct page *pgtable_t; extern pteval_t __supported_pte_mask; +extern void set_nx(void); extern int nx_enabled; #define pgprot_writecombine pgprot_writecombine diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 6a84ed166aec..1e796782cd7b 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -121,7 +121,6 @@ static inline void arch_send_call_function_single_ipi(int cpu) smp_ops.send_call_func_single_ipi(cpu); } -#define arch_send_call_function_ipi_mask arch_send_call_function_ipi_mask static inline void arch_send_call_function_ipi_mask(const struct cpumask *mask) { smp_ops.send_call_func_ipi(mask); diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 6f0695d744bf..25a92842dd99 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -165,21 +165,11 @@ static inline int numa_node_id(void) return 0; } -static inline int cpu_to_node(int cpu) -{ - return 0; -} - static inline int early_cpu_to_node(int cpu) { return 0; } -static inline const struct cpumask *cpumask_of_node(int node) -{ - return cpu_online_mask; -} - static inline void setup_node_to_cpumask_map(void) { } #endif diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c index 8c44c232efcb..59cdfa4686b2 100644 --- a/arch/x86/kernel/acpi/cstate.c +++ b/arch/x86/kernel/acpi/cstate.c @@ -48,7 +48,7 @@ void acpi_processor_power_init_bm_check(struct acpi_processor_flags *flags, * P4, Core and beyond CPUs */ if (c->x86_vendor == X86_VENDOR_INTEL && - (c->x86 > 0x6 || (c->x86 == 6 && c->x86_model >= 14))) + (c->x86 > 0xf || (c->x86 == 6 && c->x86_model >= 14))) flags->bm_control = 0; } EXPORT_SYMBOL(acpi_processor_power_init_bm_check); diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 64970b9885f2..dc69f28489f5 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -227,17 +227,14 @@ static struct irq_cfg *get_one_free_irq_cfg(int node) cfg = kzalloc_node(sizeof(*cfg), GFP_ATOMIC, node); if (cfg) { - if (!alloc_cpumask_var_node(&cfg->domain, GFP_ATOMIC, node)) { + if (!zalloc_cpumask_var_node(&cfg->domain, GFP_ATOMIC, node)) { kfree(cfg); cfg = NULL; - } else if (!alloc_cpumask_var_node(&cfg->old_domain, + } else if (!zalloc_cpumask_var_node(&cfg->old_domain, GFP_ATOMIC, node)) { free_cpumask_var(cfg->domain); kfree(cfg); cfg = NULL; - } else { - cpumask_clear(cfg->domain); - cpumask_clear(cfg->old_domain); } } diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c index cb66a22d98ad..7ff61d6a188a 100644 --- a/arch/x86/kernel/apic/nmi.c +++ b/arch/x86/kernel/apic/nmi.c @@ -508,14 +508,14 @@ static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu) /* * proc handler for /proc/sys/kernel/nmi */ -int proc_nmi_enabled(struct ctl_table *table, int write, struct file *file, +int proc_nmi_enabled(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { int old_state; nmi_watchdog_enabled = (atomic_read(&nmi_active) > 0) ? 1 : 0; old_state = nmi_watchdog_enabled; - proc_dointvec(table, write, file, buffer, length, ppos); + proc_dointvec(table, write, buffer, length, ppos); if (!!old_state == !!nmi_watchdog_enabled) return 0; diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c index 7029f0e2acad..472763d92098 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-inject.c +++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c @@ -98,8 +98,9 @@ static struct notifier_block mce_raise_nb = { }; /* Inject mce on current CPU */ -static int raise_local(struct mce *m) +static int raise_local(void) { + struct mce *m = &__get_cpu_var(injectm); int context = MCJ_CTX(m->inject_flags); int ret = 0; int cpu = m->extcpu; @@ -167,12 +168,12 @@ static void raise_mce(struct mce *m) } cpu_relax(); } - raise_local(m); + raise_local(); put_cpu(); put_online_cpus(); } else #endif - raise_local(m); + raise_local(); } /* Error injection interface */ diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 2f5aab26320e..b1598a9436d0 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -85,6 +85,18 @@ static DECLARE_WAIT_QUEUE_HEAD(mce_wait); static DEFINE_PER_CPU(struct mce, mces_seen); static int cpu_missing; +static void default_decode_mce(struct mce *m) +{ + pr_emerg("No human readable MCE decoding support on this CPU type.\n"); + pr_emerg("Run the message through 'mcelog --ascii' to decode.\n"); +} + +/* + * CPU/chipset specific EDAC code can register a callback here to print + * MCE errors in a human-readable form: + */ +void (*x86_mce_decode_callback)(struct mce *m) = default_decode_mce; +EXPORT_SYMBOL(x86_mce_decode_callback); /* MCA banks polled by the period polling timer for corrected events */ DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = { @@ -165,49 +177,46 @@ void mce_log(struct mce *mce) set_bit(0, &mce_need_notify); } -void __weak decode_mce(struct mce *m) -{ - return; -} - static void print_mce(struct mce *m) { - printk(KERN_EMERG - "CPU %d: Machine Check Exception: %16Lx Bank %d: %016Lx\n", + pr_emerg("CPU %d: Machine Check Exception: %16Lx Bank %d: %016Lx\n", m->extcpu, m->mcgstatus, m->bank, m->status); + if (m->ip) { - printk(KERN_EMERG "RIP%s %02x:<%016Lx> ", - !(m->mcgstatus & MCG_STATUS_EIPV) ? " !INEXACT!" : "", - m->cs, m->ip); + pr_emerg("RIP%s %02x:<%016Lx> ", + !(m->mcgstatus & MCG_STATUS_EIPV) ? " !INEXACT!" : "", + m->cs, m->ip); + if (m->cs == __KERNEL_CS) print_symbol("{%s}", m->ip); - printk(KERN_CONT "\n"); + pr_cont("\n"); } - printk(KERN_EMERG "TSC %llx ", m->tsc); + + pr_emerg("TSC %llx ", m->tsc); if (m->addr) - printk(KERN_CONT "ADDR %llx ", m->addr); + pr_cont("ADDR %llx ", m->addr); if (m->misc) - printk(KERN_CONT "MISC %llx ", m->misc); - printk(KERN_CONT "\n"); - printk(KERN_EMERG "PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x\n", - m->cpuvendor, m->cpuid, m->time, m->socketid, - m->apicid); + pr_cont("MISC %llx ", m->misc); + + pr_cont("\n"); + pr_emerg("PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x\n", + m->cpuvendor, m->cpuid, m->time, m->socketid, m->apicid); - decode_mce(m); + /* + * Print out human-readable details about the MCE error, + * (if the CPU has an implementation for that): + */ + x86_mce_decode_callback(m); } static void print_mce_head(void) { - printk(KERN_EMERG "\nHARDWARE ERROR\n"); + pr_emerg("\nHARDWARE ERROR\n"); } static void print_mce_tail(void) { - printk(KERN_EMERG "This is not a software problem!\n" -#if (!defined(CONFIG_EDAC) || !defined(CONFIG_CPU_SUP_AMD)) - "Run through mcelog --ascii to decode and contact your hardware vendor\n" -#endif - ); + pr_emerg("This is not a software problem!\n"); } #define PANIC_TIMEOUT 5 /* 5 seconds */ @@ -221,6 +230,7 @@ static atomic_t mce_fake_paniced; static void wait_for_panic(void) { long timeout = PANIC_TIMEOUT*USEC_PER_SEC; + preempt_disable(); local_irq_enable(); while (timeout-- > 0) @@ -288,6 +298,7 @@ static void mce_panic(char *msg, struct mce *final, char *exp) static int msr_to_offset(u32 msr) { unsigned bank = __get_cpu_var(injectm.bank); + if (msr == rip_msr) return offsetof(struct mce, ip); if (msr == MSR_IA32_MCx_STATUS(bank)) @@ -305,13 +316,25 @@ static int msr_to_offset(u32 msr) static u64 mce_rdmsrl(u32 msr) { u64 v; + if (__get_cpu_var(injectm).finished) { int offset = msr_to_offset(msr); + if (offset < 0) return 0; return *(u64 *)((char *)&__get_cpu_var(injectm) + offset); } - rdmsrl(msr, v); + + if (rdmsrl_safe(msr, &v)) { + WARN_ONCE(1, "mce: Unable to read msr %d!\n", msr); + /* + * Return zero in case the access faulted. This should + * not happen normally but can happen if the CPU does + * something weird, or if the code is buggy. + */ + v = 0; + } + return v; } @@ -319,6 +342,7 @@ static void mce_wrmsrl(u32 msr, u64 v) { if (__get_cpu_var(injectm).finished) { int offset = msr_to_offset(msr); + if (offset >= 0) *(u64 *)((char *)&__get_cpu_var(injectm) + offset) = v; return; @@ -415,7 +439,7 @@ static inline void mce_get_rip(struct mce *m, struct pt_regs *regs) m->ip = mce_rdmsrl(rip_msr); } -#ifdef CONFIG_X86_LOCAL_APIC +#ifdef CONFIG_X86_LOCAL_APIC /* * Called after interrupts have been reenabled again * when a MCE happened during an interrupts off region @@ -1172,6 +1196,7 @@ static int mce_banks_init(void) return -ENOMEM; for (i = 0; i < banks; i++) { struct mce_bank *b = &mce_banks[i]; + b->ctl = -1ULL; b->init = 1; } @@ -1203,6 +1228,7 @@ static int __cpuinit mce_cap_init(void) banks = b; if (!mce_banks) { int err = mce_banks_init(); + if (err) return err; } @@ -1237,6 +1263,7 @@ static void mce_init(void) for (i = 0; i < banks; i++) { struct mce_bank *b = &mce_banks[i]; + if (!b->init) continue; wrmsrl(MSR_IA32_MCx_CTL(i), b->ctl); @@ -1626,6 +1653,7 @@ static int mce_disable(void) for (i = 0; i < banks; i++) { struct mce_bank *b = &mce_banks[i]; + if (b->init) wrmsrl(MSR_IA32_MCx_CTL(i), 0); } @@ -1911,6 +1939,7 @@ static void mce_disable_cpu(void *h) cmci_clear(); for (i = 0; i < banks; i++) { struct mce_bank *b = &mce_banks[i]; + if (b->init) wrmsrl(MSR_IA32_MCx_CTL(i), 0); } @@ -1928,6 +1957,7 @@ static void mce_reenable_cpu(void *h) cmci_reenable(); for (i = 0; i < banks; i++) { struct mce_bank *b = &mce_banks[i]; + if (b->init) wrmsrl(MSR_IA32_MCx_CTL(i), b->ctl); } diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c index 889f665fe93d..7c785634af2b 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c @@ -8,6 +8,7 @@ #include <linux/init.h> #include <linux/interrupt.h> #include <linux/percpu.h> +#include <linux/sched.h> #include <asm/apic.h> #include <asm/processor.h> #include <asm/msr.h> diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index 63a56d147e4a..b3a1dba75330 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -34,20 +34,31 @@ /* How long to wait between reporting thermal events */ #define CHECK_INTERVAL (300 * HZ) -static DEFINE_PER_CPU(__u64, next_check) = INITIAL_JIFFIES; -static DEFINE_PER_CPU(unsigned long, thermal_throttle_count); -static DEFINE_PER_CPU(bool, thermal_throttle_active); +/* + * Current thermal throttling state: + */ +struct thermal_state { + bool is_throttled; + + u64 next_check; + unsigned long throttle_count; + unsigned long last_throttle_count; +}; + +static DEFINE_PER_CPU(struct thermal_state, thermal_state); -static atomic_t therm_throt_en = ATOMIC_INIT(0); +static atomic_t therm_throt_en = ATOMIC_INIT(0); #ifdef CONFIG_SYSFS #define define_therm_throt_sysdev_one_ro(_name) \ static SYSDEV_ATTR(_name, 0444, therm_throt_sysdev_show_##_name, NULL) #define define_therm_throt_sysdev_show_func(name) \ -static ssize_t therm_throt_sysdev_show_##name(struct sys_device *dev, \ - struct sysdev_attribute *attr, \ - char *buf) \ + \ +static ssize_t therm_throt_sysdev_show_##name( \ + struct sys_device *dev, \ + struct sysdev_attribute *attr, \ + char *buf) \ { \ unsigned int cpu = dev->id; \ ssize_t ret; \ @@ -55,7 +66,7 @@ static ssize_t therm_throt_sysdev_show_##name(struct sys_device *dev, \ preempt_disable(); /* CPU hotplug */ \ if (cpu_online(cpu)) \ ret = sprintf(buf, "%lu\n", \ - per_cpu(thermal_throttle_##name, cpu)); \ + per_cpu(thermal_state, cpu).name); \ else \ ret = 0; \ preempt_enable(); \ @@ -63,11 +74,11 @@ static ssize_t therm_throt_sysdev_show_##name(struct sys_device *dev, \ return ret; \ } -define_therm_throt_sysdev_show_func(count); -define_therm_throt_sysdev_one_ro(count); +define_therm_throt_sysdev_show_func(throttle_count); +define_therm_throt_sysdev_one_ro(throttle_count); static struct attribute *thermal_throttle_attrs[] = { - &attr_count.attr, + &attr_throttle_count.attr, NULL }; @@ -93,33 +104,39 @@ static struct attribute_group thermal_throttle_attr_group = { * 1 : Event should be logged further, and a message has been * printed to the syslog. */ -static int therm_throt_process(int curr) +static int therm_throt_process(bool is_throttled) { - unsigned int cpu = smp_processor_id(); - __u64 tmp_jiffs = get_jiffies_64(); - bool was_throttled = __get_cpu_var(thermal_throttle_active); - bool is_throttled = __get_cpu_var(thermal_throttle_active) = curr; + struct thermal_state *state; + unsigned int this_cpu; + bool was_throttled; + u64 now; + + this_cpu = smp_processor_id(); + now = get_jiffies_64(); + state = &per_cpu(thermal_state, this_cpu); + + was_throttled = state->is_throttled; + state->is_throttled = is_throttled; if (is_throttled) - __get_cpu_var(thermal_throttle_count)++; + state->throttle_count++; - if (!(was_throttled ^ is_throttled) && - time_before64(tmp_jiffs, __get_cpu_var(next_check))) + if (time_before64(now, state->next_check) && + state->throttle_count != state->last_throttle_count) return 0; - __get_cpu_var(next_check) = tmp_jiffs + CHECK_INTERVAL; + state->next_check = now + CHECK_INTERVAL; + state->last_throttle_count = state->throttle_count; /* if we just entered the thermal event */ if (is_throttled) { - printk(KERN_CRIT "CPU%d: Temperature above threshold, " - "cpu clock throttled (total events = %lu)\n", - cpu, __get_cpu_var(thermal_throttle_count)); + printk(KERN_CRIT "CPU%d: Temperature above threshold, cpu clock throttled (total events = %lu)\n", this_cpu, state->throttle_count); add_taint(TAINT_MACHINE_CHECK); return 1; } if (was_throttled) { - printk(KERN_INFO "CPU%d: Temperature/speed normal\n", cpu); + printk(KERN_INFO "CPU%d: Temperature/speed normal\n", this_cpu); return 1; } @@ -213,7 +230,7 @@ static void intel_thermal_interrupt(void) __u64 msr_val; rdmsrl(MSR_IA32_THERM_STATUS, msr_val); - if (therm_throt_process(msr_val & THERM_STATUS_PROCHOT)) + if (therm_throt_process((msr_val & THERM_STATUS_PROCHOT) != 0)) mce_log_therm_throt_event(msr_val); } diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c index f04e72527604..3c1b12d461d1 100644 --- a/arch/x86/kernel/cpu/mtrr/if.c +++ b/arch/x86/kernel/cpu/mtrr/if.c @@ -96,17 +96,24 @@ mtrr_write(struct file *file, const char __user *buf, size_t len, loff_t * ppos) unsigned long long base, size; char *ptr; char line[LINE_SIZE]; + int length; size_t linelen; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!len) - return -EINVAL; memset(line, 0, LINE_SIZE); - if (len > LINE_SIZE) - len = LINE_SIZE; - if (copy_from_user(line, buf, len - 1)) + + length = len; + length--; + + if (length > LINE_SIZE - 1) + length = LINE_SIZE - 1; + + if (length < 0) + return -EINVAL; + + if (copy_from_user(line, buf, length)) return -EFAULT; linelen = strlen(line); diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index a3c7adb06b78..b5801c311846 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1790,6 +1790,9 @@ void smp_perf_pending_interrupt(struct pt_regs *regs) void set_perf_event_pending(void) { #ifdef CONFIG_X86_LOCAL_APIC + if (!x86_pmu.apic || !x86_pmu_initialized()) + return; + apic->send_IPI_self(LOCAL_PENDING_VECTOR); #endif } diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index bca5fba91c9e..f7dd2a7c3bf4 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -5,7 +5,6 @@ #include <linux/kallsyms.h> #include <linux/kprobes.h> #include <linux/uaccess.h> -#include <linux/utsname.h> #include <linux/hardirq.h> #include <linux/kdebug.h> #include <linux/module.h> diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 54b0a3276766..a071e6be177e 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -5,7 +5,6 @@ #include <linux/kallsyms.h> #include <linux/kprobes.h> #include <linux/uaccess.h> -#include <linux/utsname.h> #include <linux/hardirq.h> #include <linux/kdebug.h> #include <linux/module.h> diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 85419bb7d4ab..d17d482a04f4 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1378,8 +1378,8 @@ static unsigned long ram_alignment(resource_size_t pos) if (mb < 16) return 1024*1024; - /* To 32MB for anything above that */ - return 32*1024*1024; + /* To 64MB for anything above that */ + return 64*1024*1024; } #define MAX_RESOURCE_SIZE ((resource_size_t)-1) diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c index 2acfd3fdc0cc..b9c830c12b4a 100644 --- a/arch/x86/kernel/early_printk.c +++ b/arch/x86/kernel/early_printk.c @@ -178,6 +178,11 @@ asmlinkage void early_printk(const char *fmt, ...) static inline void early_console_register(struct console *con, int keep_early) { + if (early_console->index != -1) { + printk(KERN_CRIT "ERROR: earlyprintk= %s already used\n", + con->name); + return; + } early_console = con; if (keep_early) early_console->flags &= ~CON_BOOT; @@ -201,8 +206,11 @@ static int __init setup_early_printk(char *buf) while (*buf != '\0') { if (!strncmp(buf, "serial", 6)) { - early_serial_init(buf + 6); + buf += 6; + early_serial_init(buf); early_console_register(&early_serial_console, keep); + if (!strncmp(buf, ",ttyS", 5)) + buf += 5; } if (!strncmp(buf, "ttyS", 4)) { early_serial_init(buf + 4); diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 681c3fda7391..b5c061f8f358 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -536,20 +536,13 @@ sysret_signal: bt $TIF_SYSCALL_AUDIT,%edx jc sysret_audit #endif - /* edx: work flags (arg3) */ - leaq -ARGOFFSET(%rsp),%rdi # &pt_regs -> arg1 - xorl %esi,%esi # oldset -> arg2 - SAVE_REST - FIXUP_TOP_OF_STACK %r11 - call do_notify_resume - RESTORE_TOP_OF_STACK %r11 - RESTORE_REST - movl $_TIF_WORK_MASK,%edi - /* Use IRET because user could have changed frame. This - works because ptregscall_common has called FIXUP_TOP_OF_STACK. */ - DISABLE_INTERRUPTS(CLBR_NONE) - TRACE_IRQS_OFF - jmp int_with_check + /* + * We have a signal, or exit tracing or single-step. + * These all wind up with the iret return path anyway, + * so just join that path right now. + */ + FIXUP_TOP_OF_STACK %r11, -ARGOFFSET + jmp int_check_syscall_exit_work badsys: movq $-ENOSYS,RAX-ARGOFFSET(%rsp) @@ -654,6 +647,7 @@ int_careful: int_very_careful: TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) +int_check_syscall_exit_work: SAVE_REST /* Check for syscall exit trace */ testl $_TIF_WORK_SYSCALL_EXIT,%edx diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index b766e8c7252d..050c278481b1 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -79,7 +79,7 @@ RESERVE_BRK(pagetables, INIT_MAP_SIZE) * any particular GDT layout, because we load our own as soon as we * can. */ -.section .text.head,"ax",@progbits +__HEAD ENTRY(startup_32) /* test KEEP_SEGMENTS flag to see if the bootloader is asking us to not reload segments */ @@ -608,7 +608,7 @@ ENTRY(initial_code) /* * BSS section */ -.section ".bss.page_aligned","wa" +__PAGE_ALIGNED_BSS .align PAGE_SIZE_asm #ifdef CONFIG_X86_PAE swapper_pg_pmd: @@ -626,7 +626,7 @@ ENTRY(empty_zero_page) * This starts the data section. */ #ifdef CONFIG_X86_PAE -.section ".data.page_aligned","wa" +__PAGE_ALIGNED_DATA /* Page-aligned for the benefit of paravirt? */ .align PAGE_SIZE_asm ENTRY(swapper_pg_dir) diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index fa54f78e2a05..780cd928fcd5 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -40,7 +40,7 @@ L4_START_KERNEL = pgd_index(__START_KERNEL_map) L3_START_KERNEL = pud_index(__START_KERNEL_map) .text - .section .text.head + __HEAD .code64 .globl startup_64 startup_64: @@ -418,7 +418,7 @@ ENTRY(phys_base) ENTRY(idt_table) .skip IDT_ENTRIES * 16 - .section .bss.page_aligned, "aw", @nobits + __PAGE_ALIGNED_BSS .align PAGE_SIZE ENTRY(empty_zero_page) .skip PAGE_SIZE diff --git a/arch/x86/kernel/i386_ksyms_32.c b/arch/x86/kernel/i386_ksyms_32.c index 43cec6bdda63..9c3bd4a2050e 100644 --- a/arch/x86/kernel/i386_ksyms_32.c +++ b/arch/x86/kernel/i386_ksyms_32.c @@ -10,6 +10,16 @@ EXPORT_SYMBOL(mcount); #endif +/* + * Note, this is a prototype to get at the symbol for + * the export, but dont use it from C code, it is used + * by assembly code and is not using C calling convention! + */ +#ifndef CONFIG_X86_CMPXCHG64 +extern void cmpxchg8b_emu(void); +EXPORT_SYMBOL(cmpxchg8b_emu); +#endif + /* Networking helper routines. */ EXPORT_SYMBOL(csum_partial_copy_generic); diff --git a/arch/x86/kernel/init_task.c b/arch/x86/kernel/init_task.c index 270ff83efc11..3a54dcb9cd0e 100644 --- a/arch/x86/kernel/init_task.c +++ b/arch/x86/kernel/init_task.c @@ -20,9 +20,8 @@ static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); * way process stacks are handled. This is done by having a special * "init_task" linker map entry.. */ -union thread_union init_thread_union - __attribute__((__section__(".data.init_task"))) = - { INIT_THREAD_INFO(init_task) }; +union thread_union init_thread_union __init_task_data = + { INIT_THREAD_INFO(init_task) }; /* * Initial task structure. diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 74656d1d4e30..391206199515 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -244,6 +244,7 @@ unsigned int __irq_entry do_IRQ(struct pt_regs *regs) __func__, smp_processor_id(), vector, irq); } + run_local_timers(); irq_exit(); set_irq_regs(old_regs); @@ -268,6 +269,7 @@ void smp_generic_interrupt(struct pt_regs *regs) if (generic_interrupt_extension) generic_interrupt_extension(); + run_local_timers(); irq_exit(); set_irq_regs(old_regs); diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index 71f1d99a635d..ec6ef60cbd17 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -67,8 +67,8 @@ static int alloc_ldt(mm_context_t *pc, int mincount, int reload) #ifdef CONFIG_SMP preempt_disable(); load_LDT(pc); - if (!cpus_equal(current->mm->cpu_vm_mask, - cpumask_of_cpu(smp_processor_id()))) + if (!cpumask_equal(mm_cpumask(current->mm), + cpumask_of(smp_processor_id()))) smp_call_function(flush_ldt, current->mm, 1); preempt_enable(); #else diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index e0d9199d0eb9..b2a71dca5642 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -35,7 +35,7 @@ int iommu_detected __read_mostly = 0; /* * This variable becomes 1 if iommu=pt is passed on the kernel command line. - * If this variable is 1, IOMMU implementations do no DMA ranslation for + * If this variable is 1, IOMMU implementations do no DMA translation for * devices and allow every device to access to whole physical memory. This is * useful if a user want to use an IOMMU only for KVM device assignment to * guests and not for driver dma translation. diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c index 98a827ee9ed7..a7f1b64f86e0 100644 --- a/arch/x86/kernel/pci-gart_64.c +++ b/arch/x86/kernel/pci-gart_64.c @@ -16,6 +16,7 @@ #include <linux/agp_backend.h> #include <linux/init.h> #include <linux/mm.h> +#include <linux/sched.h> #include <linux/string.h> #include <linux/spinlock.h> #include <linux/pci.h> diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 847ab4160315..5284cd2b5776 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -555,10 +555,8 @@ void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c) void __init init_c1e_mask(void) { /* If we're using c1e_idle, we need to allocate c1e_mask. */ - if (pm_idle == c1e_idle) { - alloc_cpumask_var(&c1e_mask, GFP_KERNEL); - cpumask_clear(c1e_mask); - } + if (pm_idle == c1e_idle) + zalloc_cpumask_var(&c1e_mask, GFP_KERNEL); } static int __init idle_setup(char *str) diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 27349f92a6d7..a1a3cdda06e1 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -4,6 +4,7 @@ #include <linux/pm.h> #include <linux/efi.h> #include <linux/dmi.h> +#include <linux/sched.h> #include <linux/tboot.h> #include <acpi/reboot.h> #include <asm/io.h> diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index ec1de97600e7..d915d956e66d 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -198,6 +198,7 @@ void smp_reschedule_interrupt(struct pt_regs *regs) { ack_APIC_irq(); inc_irq_stat(irq_resched_count); + run_local_timers(); /* * KVM uses this interrupt to force a cpu out of guest mode */ diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 09c5e077dff7..565ebc65920e 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1059,12 +1059,9 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) #endif current_thread_info()->cpu = 0; /* needed? */ for_each_possible_cpu(i) { - alloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL); - alloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL); - alloc_cpumask_var(&cpu_data(i).llc_shared_map, GFP_KERNEL); - cpumask_clear(per_cpu(cpu_core_map, i)); - cpumask_clear(per_cpu(cpu_sibling_map, i)); - cpumask_clear(cpu_data(i).llc_shared_map); + zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL); + zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL); + zalloc_cpumask_var(&cpu_data(i).llc_shared_map, GFP_KERNEL); } set_cpu_sibling_map(0); diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c index e293ac56c723..dcb00d278512 100644 --- a/arch/x86/kernel/time.c +++ b/arch/x86/kernel/time.c @@ -93,7 +93,6 @@ static struct irqaction irq0 = { void __init setup_default_timer_irq(void) { - irq0.mask = cpumask_of_cpu(0); setup_irq(0, &irq0); } diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 9346e102338d..7e37dcee0cc3 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -14,7 +14,6 @@ #include <linux/spinlock.h> #include <linux/kprobes.h> #include <linux/uaccess.h> -#include <linux/utsname.h> #include <linux/kdebug.h> #include <linux/kernel.h> #include <linux/module.h> @@ -73,11 +72,9 @@ char ignore_fpu_irq; /* * The IDT has to be page-aligned to simplify the Pentium - * F0 0F bug workaround.. We have a special link segment - * for this. + * F0 0F bug workaround. */ -gate_desc idt_table[NR_VECTORS] - __attribute__((__section__(".data.idt"))) = { { { { 0, 0 } } }, }; +gate_desc idt_table[NR_VECTORS] __page_aligned_data = { { { { 0, 0 } } }, }; #endif DECLARE_BITMAP(used_vectors, NR_VECTORS); diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index 027b5b498993..f37930954d15 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -114,7 +114,7 @@ void __cpuinit check_tsc_sync_source(int cpu) return; if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE)) { - pr_info("Skipping synchronization checks as TSC is reliable.\n"); + printk_once(KERN_INFO "Skipping synchronization checks as TSC is reliable.\n"); return; } diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index a46acccec38a..92929fb3f9fa 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -65,17 +65,11 @@ SECTIONS #endif /* Text and read-only data */ - - /* bootstrapping code */ - .text.head : AT(ADDR(.text.head) - LOAD_OFFSET) { - _text = .; - *(.text.head) - } :text = 0x9090 - - /* The rest of the text */ .text : AT(ADDR(.text) - LOAD_OFFSET) { + _text = .; + /* bootstrapping code */ + HEAD_TEXT #ifdef CONFIG_X86_32 - /* not really needed, already page aligned */ . = ALIGN(PAGE_SIZE); *(.text.page_aligned) #endif @@ -94,13 +88,7 @@ SECTIONS NOTES :text :note - /* Exception table */ - . = ALIGN(16); - __ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET) { - __start___ex_table = .; - *(__ex_table) - __stop___ex_table = .; - } :text = 0x9090 + EXCEPTION_TABLE(16) :text = 0x9090 RO_DATA(PAGE_SIZE) @@ -118,7 +106,6 @@ SECTIONS #endif PAGE_ALIGNED_DATA(PAGE_SIZE) - *(.data.idt) CACHELINE_ALIGNED_DATA(CONFIG_X86_L1_CACHE_BYTES) @@ -135,24 +122,21 @@ SECTIONS #ifdef CONFIG_X86_64 #define VSYSCALL_ADDR (-10*1024*1024) -#define VSYSCALL_PHYS_ADDR ((LOADADDR(.data) + SIZEOF(.data) + \ - PAGE_SIZE - 1) & ~(PAGE_SIZE - 1)) -#define VSYSCALL_VIRT_ADDR ((ADDR(.data) + SIZEOF(.data) + \ - PAGE_SIZE - 1) & ~(PAGE_SIZE - 1)) -#define VLOAD_OFFSET (VSYSCALL_ADDR - VSYSCALL_PHYS_ADDR) +#define VLOAD_OFFSET (VSYSCALL_ADDR - __vsyscall_0 + LOAD_OFFSET) #define VLOAD(x) (ADDR(x) - VLOAD_OFFSET) -#define VVIRT_OFFSET (VSYSCALL_ADDR - VSYSCALL_VIRT_ADDR) +#define VVIRT_OFFSET (VSYSCALL_ADDR - __vsyscall_0) #define VVIRT(x) (ADDR(x) - VVIRT_OFFSET) + . = ALIGN(4096); + __vsyscall_0 = .; + . = VSYSCALL_ADDR; - .vsyscall_0 : AT(VSYSCALL_PHYS_ADDR) { + .vsyscall_0 : AT(VLOAD(.vsyscall_0)) { *(.vsyscall_0) } :user - __vsyscall_0 = VSYSCALL_VIRT_ADDR; - . = ALIGN(CONFIG_X86_L1_CACHE_BYTES); .vsyscall_fn : AT(VLOAD(.vsyscall_fn)) { *(.vsyscall_fn) @@ -192,11 +176,9 @@ SECTIONS *(.vsyscall_3) } - . = VSYSCALL_VIRT_ADDR + PAGE_SIZE; + . = __vsyscall_0 + PAGE_SIZE; #undef VSYSCALL_ADDR -#undef VSYSCALL_PHYS_ADDR -#undef VSYSCALL_VIRT_ADDR #undef VLOAD_OFFSET #undef VLOAD #undef VVIRT_OFFSET @@ -219,36 +201,12 @@ SECTIONS PERCPU_VADDR(0, :percpu) #endif - .init.text : AT(ADDR(.init.text) - LOAD_OFFSET) { - _sinittext = .; - INIT_TEXT - _einittext = .; - } + INIT_TEXT_SECTION(PAGE_SIZE) #ifdef CONFIG_X86_64 :init #endif - .init.data : AT(ADDR(.init.data) - LOAD_OFFSET) { - INIT_DATA - } - - . = ALIGN(16); - .init.setup : AT(ADDR(.init.setup) - LOAD_OFFSET) { - __setup_start = .; - *(.init.setup) - __setup_end = .; - } - .initcall.init : AT(ADDR(.initcall.init) - LOAD_OFFSET) { - __initcall_start = .; - INITCALLS - __initcall_end = .; - } - - .con_initcall.init : AT(ADDR(.con_initcall.init) - LOAD_OFFSET) { - __con_initcall_start = .; - *(.con_initcall.init) - __con_initcall_end = .; - } + INIT_DATA_SECTION(16) .x86_cpu_dev.init : AT(ADDR(.x86_cpu_dev.init) - LOAD_OFFSET) { __x86_cpu_dev_start = .; @@ -256,8 +214,6 @@ SECTIONS __x86_cpu_dev_end = .; } - SECURITY_INIT - . = ALIGN(8); .parainstructions : AT(ADDR(.parainstructions) - LOAD_OFFSET) { __parainstructions = .; @@ -288,15 +244,6 @@ SECTIONS EXIT_DATA } -#ifdef CONFIG_BLK_DEV_INITRD - . = ALIGN(PAGE_SIZE); - .init.ramfs : AT(ADDR(.init.ramfs) - LOAD_OFFSET) { - __initramfs_start = .; - *(.init.ramfs) - __initramfs_end = .; - } -#endif - #if !defined(CONFIG_X86_64) || !defined(CONFIG_SMP) PERCPU(PAGE_SIZE) #endif diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index cf53a78e2dcf..8cb4974ff599 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -228,19 +228,11 @@ static long __vsyscall(3) venosys_1(void) } #ifdef CONFIG_SYSCTL - -static int -vsyscall_sysctl_change(ctl_table *ctl, int write, struct file * filp, - void __user *buffer, size_t *lenp, loff_t *ppos) -{ - return proc_dointvec(ctl, write, filp, buffer, lenp, ppos); -} - static ctl_table kernel_table2[] = { { .procname = "vsyscall64", .data = &vsyscall_gtod_data.sysctl_enabled, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = vsyscall_sysctl_change }, + .proc_handler = proc_dointvec }, {} }; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 1ae5ceba7eb2..7024224f0fc8 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -664,7 +664,7 @@ static void start_apic_timer(struct kvm_lapic *apic) { ktime_t now = apic->lapic_timer.timer.base->get_time(); - apic->lapic_timer.period = apic_get_reg(apic, APIC_TMICT) * + apic->lapic_timer.period = (u64)apic_get_reg(apic, APIC_TMICT) * APIC_BUS_CYCLE_NS * apic->divide_count; atomic_set(&apic->lapic_timer.pending, 0); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index eca41ae9f453..685a4ffac8e6 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -156,6 +156,8 @@ module_param(oos_shadow, bool, 0644); #define CREATE_TRACE_POINTS #include "mmutrace.h" +#define SPTE_HOST_WRITEABLE (1ULL << PT_FIRST_AVAIL_BITS_SHIFT) + #define SHADOW_PT_INDEX(addr, level) PT64_INDEX(addr, level) struct kvm_rmap_desc { @@ -634,9 +636,7 @@ static void rmap_remove(struct kvm *kvm, u64 *spte) if (*spte & shadow_accessed_mask) kvm_set_pfn_accessed(pfn); if (is_writeble_pte(*spte)) - kvm_release_pfn_dirty(pfn); - else - kvm_release_pfn_clean(pfn); + kvm_set_pfn_dirty(pfn); rmapp = gfn_to_rmap(kvm, sp->gfns[spte - sp->spt], sp->role.level); if (!*rmapp) { printk(KERN_ERR "rmap_remove: %p %llx 0->BUG\n", spte, *spte); @@ -748,7 +748,7 @@ static int rmap_write_protect(struct kvm *kvm, u64 gfn) return write_protected; } -static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp) +static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp, u64 data) { u64 *spte; int need_tlb_flush = 0; @@ -763,8 +763,45 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp) return need_tlb_flush; } -static int kvm_handle_hva(struct kvm *kvm, unsigned long hva, - int (*handler)(struct kvm *kvm, unsigned long *rmapp)) +static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp, u64 data) +{ + int need_flush = 0; + u64 *spte, new_spte; + pte_t *ptep = (pte_t *)data; + pfn_t new_pfn; + + WARN_ON(pte_huge(*ptep)); + new_pfn = pte_pfn(*ptep); + spte = rmap_next(kvm, rmapp, NULL); + while (spte) { + BUG_ON(!is_shadow_present_pte(*spte)); + rmap_printk("kvm_set_pte_rmapp: spte %p %llx\n", spte, *spte); + need_flush = 1; + if (pte_write(*ptep)) { + rmap_remove(kvm, spte); + __set_spte(spte, shadow_trap_nonpresent_pte); + spte = rmap_next(kvm, rmapp, NULL); + } else { + new_spte = *spte &~ (PT64_BASE_ADDR_MASK); + new_spte |= (u64)new_pfn << PAGE_SHIFT; + + new_spte &= ~PT_WRITABLE_MASK; + new_spte &= ~SPTE_HOST_WRITEABLE; + if (is_writeble_pte(*spte)) + kvm_set_pfn_dirty(spte_to_pfn(*spte)); + __set_spte(spte, new_spte); + spte = rmap_next(kvm, rmapp, spte); + } + } + if (need_flush) + kvm_flush_remote_tlbs(kvm); + + return 0; +} + +static int kvm_handle_hva(struct kvm *kvm, unsigned long hva, u64 data, + int (*handler)(struct kvm *kvm, unsigned long *rmapp, + u64 data)) { int i, j; int retval = 0; @@ -786,13 +823,15 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva, if (hva >= start && hva < end) { gfn_t gfn_offset = (hva - start) >> PAGE_SHIFT; - retval |= handler(kvm, &memslot->rmap[gfn_offset]); + retval |= handler(kvm, &memslot->rmap[gfn_offset], + data); for (j = 0; j < KVM_NR_PAGE_SIZES - 1; ++j) { int idx = gfn_offset; idx /= KVM_PAGES_PER_HPAGE(PT_DIRECTORY_LEVEL + j); retval |= handler(kvm, - &memslot->lpage_info[j][idx].rmap_pde); + &memslot->lpage_info[j][idx].rmap_pde, + data); } } } @@ -802,10 +841,15 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva, int kvm_unmap_hva(struct kvm *kvm, unsigned long hva) { - return kvm_handle_hva(kvm, hva, kvm_unmap_rmapp); + return kvm_handle_hva(kvm, hva, 0, kvm_unmap_rmapp); } -static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp) +void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte) +{ + kvm_handle_hva(kvm, hva, (u64)&pte, kvm_set_pte_rmapp); +} + +static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp, u64 data) { u64 *spte; int young = 0; @@ -841,13 +885,13 @@ static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) gfn = unalias_gfn(vcpu->kvm, gfn); rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp->role.level); - kvm_unmap_rmapp(vcpu->kvm, rmapp); + kvm_unmap_rmapp(vcpu->kvm, rmapp, 0); kvm_flush_remote_tlbs(vcpu->kvm); } int kvm_age_hva(struct kvm *kvm, unsigned long hva) { - return kvm_handle_hva(kvm, hva, kvm_age_rmapp); + return kvm_handle_hva(kvm, hva, 0, kvm_age_rmapp); } #ifdef MMU_DEBUG @@ -1756,7 +1800,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, int user_fault, int write_fault, int dirty, int level, gfn_t gfn, pfn_t pfn, bool speculative, - bool can_unsync) + bool can_unsync, bool reset_host_protection) { u64 spte; int ret = 0; @@ -1783,6 +1827,9 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, spte |= kvm_x86_ops->get_mt_mask(vcpu, gfn, kvm_is_mmio_pfn(pfn)); + if (reset_host_protection) + spte |= SPTE_HOST_WRITEABLE; + spte |= (u64)pfn << PAGE_SHIFT; if ((pte_access & ACC_WRITE_MASK) @@ -1828,7 +1875,8 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pt_access, unsigned pte_access, int user_fault, int write_fault, int dirty, int *ptwrite, int level, gfn_t gfn, - pfn_t pfn, bool speculative) + pfn_t pfn, bool speculative, + bool reset_host_protection) { int was_rmapped = 0; int was_writeble = is_writeble_pte(*sptep); @@ -1860,7 +1908,8 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, } if (set_spte(vcpu, sptep, pte_access, user_fault, write_fault, - dirty, level, gfn, pfn, speculative, true)) { + dirty, level, gfn, pfn, speculative, true, + reset_host_protection)) { if (write_fault) *ptwrite = 1; kvm_x86_ops->tlb_flush(vcpu); @@ -1877,8 +1926,7 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, page_header_update_slot(vcpu->kvm, sptep, gfn); if (!was_rmapped) { rmap_count = rmap_add(vcpu, sptep, gfn); - if (!is_rmap_spte(*sptep)) - kvm_release_pfn_clean(pfn); + kvm_release_pfn_clean(pfn); if (rmap_count > RMAP_RECYCLE_THRESHOLD) rmap_recycle(vcpu, sptep, gfn); } else { @@ -1909,7 +1957,7 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write, if (iterator.level == level) { mmu_set_spte(vcpu, iterator.sptep, ACC_ALL, ACC_ALL, 0, write, 1, &pt_write, - level, gfn, pfn, false); + level, gfn, pfn, false, true); ++vcpu->stat.pf_fixed; break; } diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index d2fec9c12d22..72558f8ff3f5 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -273,9 +273,13 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page, if (mmu_notifier_retry(vcpu, vcpu->arch.update_pte.mmu_seq)) return; kvm_get_pfn(pfn); + /* + * we call mmu_set_spte() with reset_host_protection = true beacuse that + * vcpu->arch.update_pte.pfn was fetched from get_user_pages(write = 1). + */ mmu_set_spte(vcpu, spte, page->role.access, pte_access, 0, 0, gpte & PT_DIRTY_MASK, NULL, PT_PAGE_TABLE_LEVEL, - gpte_to_gfn(gpte), pfn, true); + gpte_to_gfn(gpte), pfn, true, true); } /* @@ -308,7 +312,7 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, user_fault, write_fault, gw->ptes[gw->level-1] & PT_DIRTY_MASK, ptwrite, level, - gw->gfn, pfn, false); + gw->gfn, pfn, false, true); break; } @@ -558,6 +562,7 @@ static void FNAME(prefetch_page)(struct kvm_vcpu *vcpu, static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) { int i, offset, nr_present; + bool reset_host_protection; offset = nr_present = 0; @@ -595,9 +600,16 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) nr_present++; pte_access = sp->role.access & FNAME(gpte_access)(vcpu, gpte); + if (!(sp->spt[i] & SPTE_HOST_WRITEABLE)) { + pte_access &= ~ACC_WRITE_MASK; + reset_host_protection = 0; + } else { + reset_host_protection = 1; + } set_spte(vcpu, &sp->spt[i], pte_access, 0, 0, is_dirty_gpte(gpte), PT_PAGE_TABLE_LEVEL, gfn, - spte_to_pfn(sp->spt[i]), true, false); + spte_to_pfn(sp->spt[i]), true, false, + reset_host_protection); } return !nr_present; diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 944cc9c04b3c..c17404add91f 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -767,6 +767,8 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) rdtscll(tsc_this); delta = vcpu->arch.host_tsc - tsc_this; svm->vmcb->control.tsc_offset += delta; + if (is_nested(svm)) + svm->nested.hsave->control.tsc_offset += delta; vcpu->cpu = cpu; kvm_migrate_timers(vcpu); svm->asid_generation = 0; @@ -2057,10 +2059,14 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) switch (ecx) { case MSR_IA32_TSC: { - u64 tsc; + u64 tsc_offset; + + if (is_nested(svm)) + tsc_offset = svm->nested.hsave->control.tsc_offset; + else + tsc_offset = svm->vmcb->control.tsc_offset; - rdtscll(tsc); - *data = svm->vmcb->control.tsc_offset + tsc; + *data = tsc_offset + native_read_tsc(); break; } case MSR_K6_STAR: @@ -2146,10 +2152,17 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data) switch (ecx) { case MSR_IA32_TSC: { - u64 tsc; + u64 tsc_offset = data - native_read_tsc(); + u64 g_tsc_offset = 0; + + if (is_nested(svm)) { + g_tsc_offset = svm->vmcb->control.tsc_offset - + svm->nested.hsave->control.tsc_offset; + svm->nested.hsave->control.tsc_offset = tsc_offset; + } + + svm->vmcb->control.tsc_offset = tsc_offset + g_tsc_offset; - rdtscll(tsc); - svm->vmcb->control.tsc_offset = data - tsc; break; } case MSR_K6_STAR: diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index f3812014bd0b..ed53b42caba1 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -709,7 +709,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (vcpu->cpu != cpu) { vcpu_clear(vmx); kvm_migrate_timers(vcpu); - vpid_sync_vcpu_all(vmx); + set_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests); local_irq_disable(); list_add(&vmx->local_vcpus_link, &per_cpu(vcpus_on_cpu, cpu)); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index be451ee44249..9b9695322f56 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1591,6 +1591,8 @@ static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, if (cpuid->nent < 1) goto out; + if (cpuid->nent > KVM_MAX_CPUID_ENTRIES) + cpuid->nent = KVM_MAX_CPUID_ENTRIES; r = -ENOMEM; cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry2) * cpuid->nent); if (!cpuid_entries) diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index 9e609206fac9..85f5db95c60f 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -16,7 +16,9 @@ ifeq ($(CONFIG_X86_32),y) lib-y += checksum_32.o lib-y += strstr_32.o lib-y += semaphore_32.o string_32.o - +ifneq ($(CONFIG_X86_CMPXCHG64),y) + lib-y += cmpxchg8b_emu.o +endif lib-$(CONFIG_X86_USE_3DNOW) += mmx_32.o else obj-y += io_64.o iomap_copy_64.o diff --git a/arch/x86/lib/cmpxchg8b_emu.S b/arch/x86/lib/cmpxchg8b_emu.S new file mode 100644 index 000000000000..828cb710dec2 --- /dev/null +++ b/arch/x86/lib/cmpxchg8b_emu.S @@ -0,0 +1,57 @@ +/* + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + * + */ + +#include <linux/linkage.h> +#include <asm/alternative-asm.h> +#include <asm/frame.h> +#include <asm/dwarf2.h> + + +.text + +/* + * Inputs: + * %esi : memory location to compare + * %eax : low 32 bits of old value + * %edx : high 32 bits of old value + * %ebx : low 32 bits of new value + * %ecx : high 32 bits of new value + */ +ENTRY(cmpxchg8b_emu) +CFI_STARTPROC + +# +# Emulate 'cmpxchg8b (%esi)' on UP except we don't +# set the whole ZF thing (caller will just compare +# eax:edx with the expected value) +# +cmpxchg8b_emu: + pushfl + cli + + cmpl (%esi), %eax + jne not_same + cmpl 4(%esi), %edx + jne half_same + + movl %ebx, (%esi) + movl %ecx, 4(%esi) + + popfl + ret + + not_same: + movl (%esi), %eax + half_same: + movl 4(%esi), %edx + + popfl + ret + +CFI_ENDPROC +ENDPROC(cmpxchg8b_emu) diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 9b5a9f59a478..06630d26e56d 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -1,9 +1,10 @@ obj-y := init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \ - pat.o pgtable.o physaddr.o gup.o + pat.o pgtable.o physaddr.o gup.o setup_nx.o # Make sure __phys_addr has no stackprotector nostackp := $(call cc-option, -fno-stack-protector) CFLAGS_physaddr.o := $(nostackp) +CFLAGS_setup_nx.o := $(nostackp) obj-$(CONFIG_SMP) += tlb.o diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 82728f2c6d55..f4cee9028cf0 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -167,6 +167,7 @@ force_sig_info_fault(int si_signo, int si_code, unsigned long address, info.si_errno = 0; info.si_code = si_code; info.si_addr = (void __user *)address; + info.si_addr_lsb = si_code == BUS_MCEERR_AR ? PAGE_SHIFT : 0; force_sig_info(si_signo, &info, tsk); } @@ -790,10 +791,12 @@ out_of_memory(struct pt_regs *regs, unsigned long error_code, } static void -do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address) +do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address, + unsigned int fault) { struct task_struct *tsk = current; struct mm_struct *mm = tsk->mm; + int code = BUS_ADRERR; up_read(&mm->mmap_sem); @@ -809,7 +812,15 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address) tsk->thread.error_code = error_code; tsk->thread.trap_no = 14; - force_sig_info_fault(SIGBUS, BUS_ADRERR, address, tsk); +#ifdef CONFIG_MEMORY_FAILURE + if (fault & VM_FAULT_HWPOISON) { + printk(KERN_ERR + "MCE: Killing %s:%d due to hardware memory corruption fault at %lx\n", + tsk->comm, tsk->pid, address); + code = BUS_MCEERR_AR; + } +#endif + force_sig_info_fault(SIGBUS, code, address, tsk); } static noinline void @@ -819,8 +830,8 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code, if (fault & VM_FAULT_OOM) { out_of_memory(regs, error_code, address); } else { - if (fault & VM_FAULT_SIGBUS) - do_sigbus(regs, error_code, address); + if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON)) + do_sigbus(regs, error_code, address, fault); else BUG(); } diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 0607119cef94..73ffd5536f62 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -28,69 +28,6 @@ int direct_gbpages #endif ; -int nx_enabled; - -#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) -static int disable_nx __cpuinitdata; - -/* - * noexec = on|off - * - * Control non-executable mappings for processes. - * - * on Enable - * off Disable - */ -static int __init noexec_setup(char *str) -{ - if (!str) - return -EINVAL; - if (!strncmp(str, "on", 2)) { - __supported_pte_mask |= _PAGE_NX; - disable_nx = 0; - } else if (!strncmp(str, "off", 3)) { - disable_nx = 1; - __supported_pte_mask &= ~_PAGE_NX; - } - return 0; -} -early_param("noexec", noexec_setup); -#endif - -#ifdef CONFIG_X86_PAE -static void __init set_nx(void) -{ - unsigned int v[4], l, h; - - if (cpu_has_pae && (cpuid_eax(0x80000000) > 0x80000001)) { - cpuid(0x80000001, &v[0], &v[1], &v[2], &v[3]); - - if ((v[3] & (1 << 20)) && !disable_nx) { - rdmsr(MSR_EFER, l, h); - l |= EFER_NX; - wrmsr(MSR_EFER, l, h); - nx_enabled = 1; - __supported_pte_mask |= _PAGE_NX; - } - } -} -#else -static inline void set_nx(void) -{ -} -#endif - -#ifdef CONFIG_X86_64 -void __cpuinit check_efer(void) -{ - unsigned long efer; - - rdmsrl(MSR_EFER, efer); - if (!(efer & EFER_NX) || disable_nx) - __supported_pte_mask &= ~_PAGE_NX; -} -#endif - static void __init find_early_table_space(unsigned long end, int use_pse, int use_gbpages) { diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 24952fdc7e40..dd38bfbefd1f 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -144,6 +144,7 @@ void clflush_cache_range(void *vaddr, unsigned int size) mb(); } +EXPORT_SYMBOL_GPL(clflush_cache_range); static void __cpa_flush_all(void *arg) { diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 7257cf3decf9..e78cd0ec2bcf 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -81,6 +81,7 @@ enum { void pat_init(void) { u64 pat; + bool boot_cpu = !boot_pat_state; if (!pat_enabled) return; @@ -122,8 +123,10 @@ void pat_init(void) rdmsrl(MSR_IA32_CR_PAT, boot_pat_state); wrmsrl(MSR_IA32_CR_PAT, pat); - printk(KERN_INFO "x86 PAT enabled: cpu %d, old 0x%Lx, new 0x%Lx\n", - smp_processor_id(), boot_pat_state, pat); + + if (boot_cpu) + printk(KERN_INFO "x86 PAT enabled: cpu %d, old 0x%Lx, new 0x%Lx\n", + smp_processor_id(), boot_pat_state, pat); } #undef PAT diff --git a/arch/x86/mm/setup_nx.c b/arch/x86/mm/setup_nx.c new file mode 100644 index 000000000000..513d8ed5d2ec --- /dev/null +++ b/arch/x86/mm/setup_nx.c @@ -0,0 +1,69 @@ +#include <linux/spinlock.h> +#include <linux/errno.h> +#include <linux/init.h> + +#include <asm/pgtable.h> + +int nx_enabled; + +#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) +static int disable_nx __cpuinitdata; + +/* + * noexec = on|off + * + * Control non-executable mappings for processes. + * + * on Enable + * off Disable + */ +static int __init noexec_setup(char *str) +{ + if (!str) + return -EINVAL; + if (!strncmp(str, "on", 2)) { + __supported_pte_mask |= _PAGE_NX; + disable_nx = 0; + } else if (!strncmp(str, "off", 3)) { + disable_nx = 1; + __supported_pte_mask &= ~_PAGE_NX; + } + return 0; +} +early_param("noexec", noexec_setup); +#endif + +#ifdef CONFIG_X86_PAE +void __init set_nx(void) +{ + unsigned int v[4], l, h; + + if (cpu_has_pae && (cpuid_eax(0x80000000) > 0x80000001)) { + cpuid(0x80000001, &v[0], &v[1], &v[2], &v[3]); + + if ((v[3] & (1 << 20)) && !disable_nx) { + rdmsr(MSR_EFER, l, h); + l |= EFER_NX; + wrmsr(MSR_EFER, l, h); + nx_enabled = 1; + __supported_pte_mask |= _PAGE_NX; + } + } +} +#else +void set_nx(void) +{ +} +#endif + +#ifdef CONFIG_X86_64 +void __cpuinit check_efer(void) +{ + unsigned long efer; + + rdmsrl(MSR_EFER, efer); + if (!(efer & EFER_NX) || disable_nx) + __supported_pte_mask &= ~_PAGE_NX; +} +#endif + diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index c814e144a3f0..36fe08eeb5c3 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -59,7 +59,8 @@ void leave_mm(int cpu) { if (percpu_read(cpu_tlbstate.state) == TLBSTATE_OK) BUG(); - cpu_clear(cpu, percpu_read(cpu_tlbstate.active_mm)->cpu_vm_mask); + cpumask_clear_cpu(cpu, + mm_cpumask(percpu_read(cpu_tlbstate.active_mm))); load_cr3(swapper_pg_dir); } EXPORT_SYMBOL_GPL(leave_mm); @@ -234,8 +235,8 @@ void flush_tlb_current_task(void) preempt_disable(); local_flush_tlb(); - if (cpumask_any_but(&mm->cpu_vm_mask, smp_processor_id()) < nr_cpu_ids) - flush_tlb_others(&mm->cpu_vm_mask, mm, TLB_FLUSH_ALL); + if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) + flush_tlb_others(mm_cpumask(mm), mm, TLB_FLUSH_ALL); preempt_enable(); } @@ -249,8 +250,8 @@ void flush_tlb_mm(struct mm_struct *mm) else leave_mm(smp_processor_id()); } - if (cpumask_any_but(&mm->cpu_vm_mask, smp_processor_id()) < nr_cpu_ids) - flush_tlb_others(&mm->cpu_vm_mask, mm, TLB_FLUSH_ALL); + if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) + flush_tlb_others(mm_cpumask(mm), mm, TLB_FLUSH_ALL); preempt_enable(); } @@ -268,8 +269,8 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long va) leave_mm(smp_processor_id()); } - if (cpumask_any_but(&mm->cpu_vm_mask, smp_processor_id()) < nr_cpu_ids) - flush_tlb_others(&mm->cpu_vm_mask, mm, va); + if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) + flush_tlb_others(mm_cpumask(mm), mm, va); preempt_enable(); } diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 5db96d4304de..1331fcf26143 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -646,7 +646,7 @@ int get_mp_bus_to_node(int busnum) #else /* CONFIG_X86_32 */ -static unsigned char mp_bus_to_node[BUS_NR] = { +static int mp_bus_to_node[BUS_NR] = { [0 ... BUS_NR - 1] = -1 }; diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c index 52e62e57fedd..b22d13b0c71d 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -266,7 +266,7 @@ void pcibios_set_master(struct pci_dev *dev) pci_write_config_byte(dev, PCI_LATENCY_TIMER, lat); } -static struct vm_operations_struct pci_mmap_ops = { +static const struct vm_operations_struct pci_mmap_ops = { .access = generic_access_phys, }; diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile index 88112b49f02c..6b4ffedb93c9 100644 --- a/arch/x86/vdso/Makefile +++ b/arch/x86/vdso/Makefile @@ -122,7 +122,7 @@ quiet_cmd_vdso = VDSO $@ $(VDSO_LDFLAGS) $(VDSO_LDFLAGS_$(filter %.lds,$(^F))) \ -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) -VDSO_LDFLAGS = -fPIC -shared $(call ld-option, -Wl$(comma)--hash-style=sysv) +VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) GCOV_PROFILE := n # diff --git a/arch/x86/xen/debugfs.c b/arch/x86/xen/debugfs.c index b53225d2cac3..e133ce25e290 100644 --- a/arch/x86/xen/debugfs.c +++ b/arch/x86/xen/debugfs.c @@ -100,7 +100,7 @@ static int xen_array_release(struct inode *inode, struct file *file) return 0; } -static struct file_operations u32_array_fops = { +static const struct file_operations u32_array_fops = { .owner = THIS_MODULE, .open = u32_array_open, .release= xen_array_release, diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 544eb7496531..3439616d69f1 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1082,6 +1082,11 @@ asmlinkage void __init xen_start_kernel(void) __supported_pte_mask |= _PAGE_IOMAP; +#ifdef CONFIG_X86_64 + /* Work out if we support NX */ + check_efer(); +#endif + xen_setup_features(); /* Get mfn list */ @@ -1123,11 +1128,6 @@ asmlinkage void __init xen_start_kernel(void) pgd = (pgd_t *)xen_start_info->pt_base; -#ifdef CONFIG_X86_64 - /* Work out if we support NX */ - check_efer(); -#endif - /* Don't do the full vcpu_info placement stuff until we have a possible map and a non-dummy shared_info. */ per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0]; diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 093dd59b5385..3bf7b1d250ce 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -1165,14 +1165,14 @@ static void xen_drop_mm_ref(struct mm_struct *mm) /* Get the "official" set of cpus referring to our pagetable. */ if (!alloc_cpumask_var(&mask, GFP_ATOMIC)) { for_each_online_cpu(cpu) { - if (!cpumask_test_cpu(cpu, &mm->cpu_vm_mask) + if (!cpumask_test_cpu(cpu, mm_cpumask(mm)) && per_cpu(xen_current_cr3, cpu) != __pa(mm->pgd)) continue; smp_call_function_single(cpu, drop_other_mm_ref, mm, 1); } return; } - cpumask_copy(mask, &mm->cpu_vm_mask); + cpumask_copy(mask, mm_cpumask(mm)); /* It's possible that a vcpu may have a stale reference to our cr3, because its in lazy mode, and it hasn't yet flushed |