diff options
Diffstat (limited to 'arch/x86/include/asm')
| -rw-r--r-- | arch/x86/include/asm/mmu.h | 2 | ||||
| -rw-r--r-- | arch/x86/include/asm/mmu_context.h | 33 | ||||
| -rw-r--r-- | arch/x86/include/asm/paravirt.h | 6 | ||||
| -rw-r--r-- | arch/x86/include/asm/processor.h | 33 | ||||
| -rw-r--r-- | arch/x86/include/asm/special_insns.h | 6 | ||||
| -rw-r--r-- | arch/x86/include/asm/tlbflush.h | 77 | ||||
| -rw-r--r-- | arch/x86/include/asm/virtext.h | 5 |
7 files changed, 108 insertions, 54 deletions
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h index 876e74e8eec7..09b9620a73b4 100644 --- a/arch/x86/include/asm/mmu.h +++ b/arch/x86/include/asm/mmu.h @@ -19,6 +19,8 @@ typedef struct { struct mutex lock; void __user *vdso; + + atomic_t perf_rdpmc_allowed; /* nonzero if rdpmc is allowed */ } mm_context_t; #ifdef CONFIG_SMP diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 4b75d591eb5e..883f6b933fa4 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -18,6 +18,21 @@ static inline void paravirt_activate_mm(struct mm_struct *prev, } #endif /* !CONFIG_PARAVIRT */ +#ifdef CONFIG_PERF_EVENTS +extern struct static_key rdpmc_always_available; + +static inline void load_mm_cr4(struct mm_struct *mm) +{ + if (static_key_true(&rdpmc_always_available) || + atomic_read(&mm->context.perf_rdpmc_allowed)) + cr4_set_bits(X86_CR4_PCE); + else + cr4_clear_bits(X86_CR4_PCE); +} +#else +static inline void load_mm_cr4(struct mm_struct *mm) {} +#endif + /* * Used for LDT copy/destruction. */ @@ -52,15 +67,20 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, /* Stop flush ipis for the previous mm */ cpumask_clear_cpu(cpu, mm_cpumask(prev)); + /* Load per-mm CR4 state */ + load_mm_cr4(next); + /* * Load the LDT, if the LDT is different. * - * It's possible leave_mm(prev) has been called. If so, - * then prev->context.ldt could be out of sync with the - * LDT descriptor or the LDT register. This can only happen - * if prev->context.ldt is non-null, since we never free - * an LDT. But LDTs can't be shared across mms, so - * prev->context.ldt won't be equal to next->context.ldt. + * It's possible that prev->context.ldt doesn't match + * the LDT register. This can happen if leave_mm(prev) + * was called and then modify_ldt changed + * prev->context.ldt but suppressed an IPI to this CPU. + * In this case, prev->context.ldt != NULL, because we + * never free an LDT while the mm still exists. That + * means that next->context.ldt != prev->context.ldt, + * because mms never share an LDT. */ if (unlikely(prev->context.ldt != next->context.ldt)) load_LDT_nolock(&next->context); @@ -85,6 +105,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, */ load_cr3(next->pgd); trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); + load_mm_cr4(next); load_LDT_nolock(&next->context); } } diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 32444ae939ca..965c47d254aa 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -80,16 +80,16 @@ static inline void write_cr3(unsigned long x) PVOP_VCALL1(pv_mmu_ops.write_cr3, x); } -static inline unsigned long read_cr4(void) +static inline unsigned long __read_cr4(void) { return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr4); } -static inline unsigned long read_cr4_safe(void) +static inline unsigned long __read_cr4_safe(void) { return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr4_safe); } -static inline void write_cr4(unsigned long x) +static inline void __write_cr4(unsigned long x) { PVOP_VCALL1(pv_cpu_ops.write_cr4, x); } diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index a092a0cce0b7..ec1c93588cef 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -579,39 +579,6 @@ static inline void load_sp0(struct tss_struct *tss, #define set_iopl_mask native_set_iopl_mask #endif /* CONFIG_PARAVIRT */ -/* - * Save the cr4 feature set we're using (ie - * Pentium 4MB enable and PPro Global page - * enable), so that any CPU's that boot up - * after us can get the correct flags. - */ -extern unsigned long mmu_cr4_features; -extern u32 *trampoline_cr4_features; - -static inline void set_in_cr4(unsigned long mask) -{ - unsigned long cr4; - - mmu_cr4_features |= mask; - if (trampoline_cr4_features) - *trampoline_cr4_features = mmu_cr4_features; - cr4 = read_cr4(); - cr4 |= mask; - write_cr4(cr4); -} - -static inline void clear_in_cr4(unsigned long mask) -{ - unsigned long cr4; - - mmu_cr4_features &= ~mask; - if (trampoline_cr4_features) - *trampoline_cr4_features = mmu_cr4_features; - cr4 = read_cr4(); - cr4 &= ~mask; - write_cr4(cr4); -} - typedef struct { unsigned long seg; } mm_segment_t; diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index e820c080a4e9..6a4b00fafb00 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -137,17 +137,17 @@ static inline void write_cr3(unsigned long x) native_write_cr3(x); } -static inline unsigned long read_cr4(void) +static inline unsigned long __read_cr4(void) { return native_read_cr4(); } -static inline unsigned long read_cr4_safe(void) +static inline unsigned long __read_cr4_safe(void) { return native_read_cr4_safe(); } -static inline void write_cr4(unsigned long x) +static inline void __write_cr4(unsigned long x) { native_write_cr4(x); } diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 04905bfc508b..cd791948b286 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -15,6 +15,75 @@ #define __flush_tlb_single(addr) __native_flush_tlb_single(addr) #endif +struct tlb_state { +#ifdef CONFIG_SMP + struct mm_struct *active_mm; + int state; +#endif + + /* + * Access to this CR4 shadow and to H/W CR4 is protected by + * disabling interrupts when modifying either one. + */ + unsigned long cr4; +}; +DECLARE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate); + +/* Initialize cr4 shadow for this CPU. */ +static inline void cr4_init_shadow(void) +{ + this_cpu_write(cpu_tlbstate.cr4, __read_cr4()); +} + +/* Set in this cpu's CR4. */ +static inline void cr4_set_bits(unsigned long mask) +{ + unsigned long cr4; + + cr4 = this_cpu_read(cpu_tlbstate.cr4); + if ((cr4 | mask) != cr4) { + cr4 |= mask; + this_cpu_write(cpu_tlbstate.cr4, cr4); + __write_cr4(cr4); + } +} + +/* Clear in this cpu's CR4. */ +static inline void cr4_clear_bits(unsigned long mask) +{ + unsigned long cr4; + + cr4 = this_cpu_read(cpu_tlbstate.cr4); + if ((cr4 & ~mask) != cr4) { + cr4 &= ~mask; + this_cpu_write(cpu_tlbstate.cr4, cr4); + __write_cr4(cr4); + } +} + +/* Read the CR4 shadow. */ +static inline unsigned long cr4_read_shadow(void) +{ + return this_cpu_read(cpu_tlbstate.cr4); +} + +/* + * Save some of cr4 feature set we're using (e.g. Pentium 4MB + * enable and PPro Global page enable), so that any CPU's that boot + * up after us can get the correct flags. This should only be used + * during boot on the boot cpu. + */ +extern unsigned long mmu_cr4_features; +extern u32 *trampoline_cr4_features; + +static inline void cr4_set_bits_and_update_boot(unsigned long mask) +{ + mmu_cr4_features |= mask; + if (trampoline_cr4_features) + *trampoline_cr4_features = mmu_cr4_features; + cr4_set_bits(mask); +} + static inline void __native_flush_tlb(void) { native_write_cr3(native_read_cr3()); @@ -24,7 +93,7 @@ static inline void __native_flush_tlb_global_irq_disabled(void) { unsigned long cr4; - cr4 = native_read_cr4(); + cr4 = this_cpu_read(cpu_tlbstate.cr4); /* clear PGE */ native_write_cr4(cr4 & ~X86_CR4_PGE); /* write old PGE again and flush TLBs */ @@ -184,12 +253,6 @@ void native_flush_tlb_others(const struct cpumask *cpumask, #define TLBSTATE_OK 1 #define TLBSTATE_LAZY 2 -struct tlb_state { - struct mm_struct *active_mm; - int state; -}; -DECLARE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate); - static inline void reset_lazy_tlbstate(void) { this_cpu_write(cpu_tlbstate.state, 0); diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h index 5da71c27cc59..cce9ee68e335 100644 --- a/arch/x86/include/asm/virtext.h +++ b/arch/x86/include/asm/virtext.h @@ -19,6 +19,7 @@ #include <asm/vmx.h> #include <asm/svm.h> +#include <asm/tlbflush.h> /* * VMX functions: @@ -40,12 +41,12 @@ static inline int cpu_has_vmx(void) static inline void cpu_vmxoff(void) { asm volatile (ASM_VMX_VMXOFF : : : "cc"); - write_cr4(read_cr4() & ~X86_CR4_VMXE); + cr4_clear_bits(X86_CR4_VMXE); } static inline int cpu_vmx_enabled(void) { - return read_cr4() & X86_CR4_VMXE; + return __read_cr4() & X86_CR4_VMXE; } /** Disable VMX if it is enabled on the current CPU |