diff options
Diffstat (limited to 'arch/x86')
-rw-r--r-- | arch/x86/include/asm/mwait.h | 8 | ||||
-rw-r--r-- | arch/x86/kernel/process.c | 50 | ||||
-rw-r--r-- | arch/x86/kvm/emulate.c | 27 | ||||
-rw-r--r-- | arch/x86/kvm/mmu.c | 2 | ||||
-rw-r--r-- | arch/x86/mm/fault.c | 10 | ||||
-rw-r--r-- | arch/x86/power/hibernate_32.c | 4 | ||||
-rw-r--r-- | arch/x86/power/hibernate_64.c | 4 |
7 files changed, 72 insertions, 33 deletions
diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index 1da25a5f96f9..3ba047cbcf5b 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -30,6 +30,14 @@ static inline void __mwait(unsigned long eax, unsigned long ecx) :: "a" (eax), "c" (ecx)); } +static inline void __sti_mwait(unsigned long eax, unsigned long ecx) +{ + trace_hardirqs_on(); + /* "mwait %eax, %ecx;" */ + asm volatile("sti; .byte 0x0f, 0x01, 0xc9;" + :: "a" (eax), "c" (ecx)); +} + /* * This uses new MONITOR/MWAIT instructions on P4 processors with PNI, * which can obviate IPI to trigger checking of need_resched. diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index ed8975a3538e..cb194edb5c7e 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -28,6 +28,7 @@ #include <asm/fpu-internal.h> #include <asm/debugreg.h> #include <asm/nmi.h> +#include <asm/mwait.h> /* * per-CPU TSS segments. Threads are completely 'soft' on Linux, @@ -385,6 +386,52 @@ static void amd_e400_idle(void) default_idle(); } +/* + * Intel Core2 and older machines prefer MWAIT over HALT for C1. + * We can't rely on cpuidle installing MWAIT, because it will not load + * on systems that support only C1 -- so the boot default must be MWAIT. + * + * Some AMD machines are the opposite, they depend on using HALT. + * + * So for default C1, which is used during boot until cpuidle loads, + * use MWAIT-C1 on Intel HW that has it, else use HALT. + */ +static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c) +{ + if (c->x86_vendor != X86_VENDOR_INTEL) + return 0; + + if (!cpu_has(c, X86_FEATURE_MWAIT)) + return 0; + + return 1; +} + +/* + * MONITOR/MWAIT with no hints, used for default default C1 state. + * This invokes MWAIT with interrutps enabled and no flags, + * which is backwards compatible with the original MWAIT implementation. + */ + +static void mwait_idle(void) +{ + if (!current_set_polling_and_test()) { + if (static_cpu_has(X86_FEATURE_CLFLUSH_MONITOR)) { + mb(); + clflush((void *)¤t_thread_info()->flags); + mb(); + } + + __monitor((void *)¤t_thread_info()->flags, 0, 0); + if (!need_resched()) + __sti_mwait(0, 0); + else + local_irq_enable(); + } else + local_irq_enable(); + current_clr_polling(); +} + void select_idle_routine(const struct cpuinfo_x86 *c) { #ifdef CONFIG_SMP @@ -398,6 +445,9 @@ void select_idle_routine(const struct cpuinfo_x86 *c) /* E400: APIC timer interrupt does not wake up CPU from C1e */ pr_info("using AMD E400 aware idle routine\n"); x86_idle = amd_e400_idle; + } else if (prefer_mwait_c1_over_halt(c)) { + pr_info("using mwait in idle threads\n"); + x86_idle = mwait_idle; } else x86_idle = default_idle; } diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 09651d4a9038..cf1eeeafdfa3 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -2258,7 +2258,7 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt) * Not recognized on AMD in compat mode (but is recognized in legacy * mode). */ - if ((ctxt->mode == X86EMUL_MODE_PROT32) && (efer & EFER_LMA) + if ((ctxt->mode != X86EMUL_MODE_PROT64) && (efer & EFER_LMA) && !vendor_intel(ctxt)) return emulate_ud(ctxt); @@ -2271,25 +2271,13 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt) setup_syscalls_segments(ctxt, &cs, &ss); ops->get_msr(ctxt, MSR_IA32_SYSENTER_CS, &msr_data); - switch (ctxt->mode) { - case X86EMUL_MODE_PROT32: - if ((msr_data & 0xfffc) == 0x0) - return emulate_gp(ctxt, 0); - break; - case X86EMUL_MODE_PROT64: - if (msr_data == 0x0) - return emulate_gp(ctxt, 0); - break; - default: - break; - } + if ((msr_data & 0xfffc) == 0x0) + return emulate_gp(ctxt, 0); ctxt->eflags &= ~(EFLG_VM | EFLG_IF | EFLG_RF); - cs_sel = (u16)msr_data; - cs_sel &= ~SELECTOR_RPL_MASK; + cs_sel = (u16)msr_data & ~SELECTOR_RPL_MASK; ss_sel = cs_sel + 8; - ss_sel &= ~SELECTOR_RPL_MASK; - if (ctxt->mode == X86EMUL_MODE_PROT64 || (efer & EFER_LMA)) { + if (efer & EFER_LMA) { cs.d = 0; cs.l = 1; } @@ -2298,10 +2286,11 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt) ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS); ops->get_msr(ctxt, MSR_IA32_SYSENTER_EIP, &msr_data); - ctxt->_eip = msr_data; + ctxt->_eip = (efer & EFER_LMA) ? msr_data : (u32)msr_data; ops->get_msr(ctxt, MSR_IA32_SYSENTER_ESP, &msr_data); - *reg_write(ctxt, VCPU_REGS_RSP) = msr_data; + *reg_write(ctxt, VCPU_REGS_RSP) = (efer & EFER_LMA) ? msr_data : + (u32)msr_data; return X86EMUL_CONTINUE; } diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 32e5329ab0b6..5ba31d053088 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -4073,7 +4073,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, ++vcpu->kvm->stat.mmu_pte_write; kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE); - mask.cr0_wp = mask.cr4_pae = mask.nxe = 1; + mask.cr0_wp = mask.cr4_pae = mask.nxe = mask.smep_andnot_wp = 1; for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn) { if (detect_write_misaligned(sp, gpa, bytes) || detect_write_flooding(sp)) { diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index a10c8c792161..ebc551c82605 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -833,11 +833,8 @@ 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); - /* Kernel mode? Handle exceptions or die: */ if (!(error_code & PF_USER)) { no_context(regs, error_code, address, SIGBUS, BUS_ADRERR); @@ -868,7 +865,6 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code, unsigned long address, unsigned int fault) { if (fatal_signal_pending(current) && !(error_code & PF_USER)) { - up_read(¤t->mm->mmap_sem); no_context(regs, error_code, address, 0, 0); return; } @@ -876,14 +872,11 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code, if (fault & VM_FAULT_OOM) { /* Kernel mode? Handle exceptions or die: */ if (!(error_code & PF_USER)) { - up_read(¤t->mm->mmap_sem); no_context(regs, error_code, address, SIGSEGV, SEGV_MAPERR); return; } - up_read(¤t->mm->mmap_sem); - /* * We ran out of memory, call the OOM killer, and return the * userspace (which will retry the fault, or kill us if we got @@ -894,6 +887,8 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code, if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON| VM_FAULT_HWPOISON_LARGE)) do_sigbus(regs, error_code, address, fault); + else if (fault & VM_FAULT_SIGSEGV) + bad_area_nosemaphore(regs, error_code, address); else BUG(); } @@ -1216,6 +1211,7 @@ good_area: return; if (unlikely(fault & VM_FAULT_ERROR)) { + up_read(&mm->mmap_sem); mm_fault_error(regs, error_code, address, fault); return; } diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c index 7d28c885d238..291226b952a9 100644 --- a/arch/x86/power/hibernate_32.c +++ b/arch/x86/power/hibernate_32.c @@ -13,13 +13,11 @@ #include <asm/page.h> #include <asm/pgtable.h> #include <asm/mmzone.h> +#include <asm/sections.h> /* Defined in hibernate_asm_32.S */ extern int restore_image(void); -/* References to section boundaries */ -extern const void __nosave_begin, __nosave_end; - /* Pointer to the temporary resume page tables */ pgd_t *resume_pg_dir; diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c index 304fca20d96e..2276238fde6f 100644 --- a/arch/x86/power/hibernate_64.c +++ b/arch/x86/power/hibernate_64.c @@ -17,11 +17,9 @@ #include <asm/page.h> #include <asm/pgtable.h> #include <asm/mtrr.h> +#include <asm/sections.h> #include <asm/suspend.h> -/* References to section boundaries */ -extern __visible const void __nosave_begin, __nosave_end; - /* Defined in hibernate_asm_64.S */ extern asmlinkage int restore_image(void); |