diff options
Diffstat (limited to 'arch/x86')
157 files changed, 1512 insertions, 1007 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 2fa55851d2a9..3a9add58d794 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -111,6 +111,7 @@ config X86 select HAVE_FUNCTION_GRAPH_FP_TEST select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER + select HAVE_GCC_PLUGINS select HAVE_GENERIC_DMA_COHERENT if X86_32 select HAVE_HW_BREAKPOINT select HAVE_IDE diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index be8e688fa0d4..12ea8f8384f4 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -96,7 +96,7 @@ $(obj)/zoffset.h: $(obj)/compressed/vmlinux FORCE $(call if_changed,zoffset) -AFLAGS_header.o += -I$(obj) +AFLAGS_header.o += -I$(objtree)/$(obj) $(obj)/header.o: $(obj)/zoffset.h LDFLAGS_setup.elf := -T diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index 6ba89a1ab0e5..d5409660f5de 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -75,7 +75,7 @@ CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \ -fno-omit-frame-pointer -foptimize-sibling-calls \ -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO -$(vobjs): KBUILD_CFLAGS += $(CFL) +$(vobjs): KBUILD_CFLAGS := $(filter-out $(GCC_PLUGINS_CFLAGS),$(KBUILD_CFLAGS)) $(CFL) # # vDSO code runs in userspace and -pg doesn't help with profiling anyway. @@ -145,6 +145,7 @@ KBUILD_CFLAGS_32 := $(filter-out -m64,$(KBUILD_CFLAGS)) KBUILD_CFLAGS_32 := $(filter-out -mcmodel=kernel,$(KBUILD_CFLAGS_32)) KBUILD_CFLAGS_32 := $(filter-out -fno-pic,$(KBUILD_CFLAGS_32)) KBUILD_CFLAGS_32 := $(filter-out -mfentry,$(KBUILD_CFLAGS_32)) +KBUILD_CFLAGS_32 := $(filter-out $(GCC_PLUGINS_CFLAGS),$(KBUILD_CFLAGS_32)) KBUILD_CFLAGS_32 += -m32 -msoft-float -mregparm=0 -fpic KBUILD_CFLAGS_32 += $(call cc-option, -fno-stack-protector) KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls) diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index 155ea5324ae0..b26ee32f73e8 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -7,7 +7,8 @@ */ #include <linux/perf_event.h> -#include <linux/module.h> +#include <linux/init.h> +#include <linux/export.h> #include <linux/pci.h> #include <linux/ptrace.h> #include <linux/syscore_ops.h> diff --git a/arch/x86/events/amd/iommu.c b/arch/x86/events/amd/iommu.c index 6011a573dd64..b28200dea715 100644 --- a/arch/x86/events/amd/iommu.c +++ b/arch/x86/events/amd/iommu.c @@ -12,7 +12,7 @@ */ #include <linux/perf_event.h> -#include <linux/module.h> +#include <linux/init.h> #include <linux/cpumask.h> #include <linux/slab.h> diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index c17f0de5fd39..fad97886d8b1 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -17,7 +17,8 @@ #include <linux/notifier.h> #include <linux/hardirq.h> #include <linux/kprobes.h> -#include <linux/module.h> +#include <linux/export.h> +#include <linux/init.h> #include <linux/kdebug.h> #include <linux/sched.h> #include <linux/uaccess.h> diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 3f3d0d67749b..463dc7a5a6c3 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1,3 +1,5 @@ +#include <linux/module.h> + #include <asm/cpu_device_id.h> #include <asm/intel-family.h> #include "uncore.h" diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index d6063e438158..78b9c23e2d8d 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -1,4 +1,3 @@ -#include <linux/module.h> #include <linux/slab.h> #include <linux/pci.h> #include <asm/apicdef.h> diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c index 50b3a056f96b..4bb3ec69e8ea 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -36,11 +36,11 @@ static bool test_intel(int idx) switch (boot_cpu_data.x86_model) { case INTEL_FAM6_NEHALEM: + case INTEL_FAM6_NEHALEM_G: case INTEL_FAM6_NEHALEM_EP: case INTEL_FAM6_NEHALEM_EX: case INTEL_FAM6_WESTMERE: - case INTEL_FAM6_WESTMERE2: case INTEL_FAM6_WESTMERE_EP: case INTEL_FAM6_WESTMERE_EX: diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 483fb547e3c0..1d2b69fc0ceb 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -49,43 +49,59 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; #define test_cpu_cap(c, bit) \ test_bit(bit, (unsigned long *)((c)->x86_capability)) -#define REQUIRED_MASK_BIT_SET(bit) \ - ( (((bit)>>5)==0 && (1UL<<((bit)&31) & REQUIRED_MASK0 )) || \ - (((bit)>>5)==1 && (1UL<<((bit)&31) & REQUIRED_MASK1 )) || \ - (((bit)>>5)==2 && (1UL<<((bit)&31) & REQUIRED_MASK2 )) || \ - (((bit)>>5)==3 && (1UL<<((bit)&31) & REQUIRED_MASK3 )) || \ - (((bit)>>5)==4 && (1UL<<((bit)&31) & REQUIRED_MASK4 )) || \ - (((bit)>>5)==5 && (1UL<<((bit)&31) & REQUIRED_MASK5 )) || \ - (((bit)>>5)==6 && (1UL<<((bit)&31) & REQUIRED_MASK6 )) || \ - (((bit)>>5)==7 && (1UL<<((bit)&31) & REQUIRED_MASK7 )) || \ - (((bit)>>5)==8 && (1UL<<((bit)&31) & REQUIRED_MASK8 )) || \ - (((bit)>>5)==9 && (1UL<<((bit)&31) & REQUIRED_MASK9 )) || \ - (((bit)>>5)==10 && (1UL<<((bit)&31) & REQUIRED_MASK10)) || \ - (((bit)>>5)==11 && (1UL<<((bit)&31) & REQUIRED_MASK11)) || \ - (((bit)>>5)==12 && (1UL<<((bit)&31) & REQUIRED_MASK12)) || \ - (((bit)>>5)==13 && (1UL<<((bit)&31) & REQUIRED_MASK13)) || \ - (((bit)>>5)==14 && (1UL<<((bit)&31) & REQUIRED_MASK14)) || \ - (((bit)>>5)==15 && (1UL<<((bit)&31) & REQUIRED_MASK15)) || \ - (((bit)>>5)==16 && (1UL<<((bit)&31) & REQUIRED_MASK16)) ) - -#define DISABLED_MASK_BIT_SET(bit) \ - ( (((bit)>>5)==0 && (1UL<<((bit)&31) & DISABLED_MASK0 )) || \ - (((bit)>>5)==1 && (1UL<<((bit)&31) & DISABLED_MASK1 )) || \ - (((bit)>>5)==2 && (1UL<<((bit)&31) & DISABLED_MASK2 )) || \ - (((bit)>>5)==3 && (1UL<<((bit)&31) & DISABLED_MASK3 )) || \ - (((bit)>>5)==4 && (1UL<<((bit)&31) & DISABLED_MASK4 )) || \ - (((bit)>>5)==5 && (1UL<<((bit)&31) & DISABLED_MASK5 )) || \ - (((bit)>>5)==6 && (1UL<<((bit)&31) & DISABLED_MASK6 )) || \ - (((bit)>>5)==7 && (1UL<<((bit)&31) & DISABLED_MASK7 )) || \ - (((bit)>>5)==8 && (1UL<<((bit)&31) & DISABLED_MASK8 )) || \ - (((bit)>>5)==9 && (1UL<<((bit)&31) & DISABLED_MASK9 )) || \ - (((bit)>>5)==10 && (1UL<<((bit)&31) & DISABLED_MASK10)) || \ - (((bit)>>5)==11 && (1UL<<((bit)&31) & DISABLED_MASK11)) || \ - (((bit)>>5)==12 && (1UL<<((bit)&31) & DISABLED_MASK12)) || \ - (((bit)>>5)==13 && (1UL<<((bit)&31) & DISABLED_MASK13)) || \ - (((bit)>>5)==14 && (1UL<<((bit)&31) & DISABLED_MASK14)) || \ - (((bit)>>5)==15 && (1UL<<((bit)&31) & DISABLED_MASK15)) || \ - (((bit)>>5)==16 && (1UL<<((bit)&31) & DISABLED_MASK16)) ) +/* + * There are 32 bits/features in each mask word. The high bits + * (selected with (bit>>5) give us the word number and the low 5 + * bits give us the bit/feature number inside the word. + * (1UL<<((bit)&31) gives us a mask for the feature_bit so we can + * see if it is set in the mask word. + */ +#define CHECK_BIT_IN_MASK_WORD(maskname, word, bit) \ + (((bit)>>5)==(word) && (1UL<<((bit)&31) & maskname##word )) + +#define REQUIRED_MASK_BIT_SET(feature_bit) \ + ( CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 0, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 1, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 2, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 3, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 4, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 5, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 6, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 7, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 8, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 9, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 10, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 11, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 12, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 13, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 14, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 15, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 16, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 17, feature_bit) || \ + REQUIRED_MASK_CHECK || \ + BUILD_BUG_ON_ZERO(NCAPINTS != 18)) + +#define DISABLED_MASK_BIT_SET(feature_bit) \ + ( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 0, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 1, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 2, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 3, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 4, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 5, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 6, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 7, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 8, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 9, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 10, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 11, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 12, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 13, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 14, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 15, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 16, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 17, feature_bit) || \ + DISABLED_MASK_CHECK || \ + BUILD_BUG_ON_ZERO(NCAPINTS != 18)) #define cpu_has(c, bit) \ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index d683993248c8..92a8308b96f6 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -309,5 +309,5 @@ #endif #define X86_BUG_NULL_SEG X86_BUG(10) /* Nulling a selector preserves the base */ #define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */ - +#define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index 911e9358ceb1..85599ad4d024 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -56,5 +56,7 @@ #define DISABLED_MASK14 0 #define DISABLED_MASK15 0 #define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE) +#define DISABLED_MASK17 0 +#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18) #endif /* _ASM_X86_DISABLED_FEATURES_H */ diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 6999f7d01a0d..627719475457 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -8,7 +8,7 @@ * "Extreme" ones, like Broadwell-E. * * Things ending in "2" are usually because we have no better - * name for them. There's no processor called "WESTMERE2". + * name for them. There's no processor called "SILVERMONT2". */ #define INTEL_FAM6_CORE_YONAH 0x0E @@ -18,10 +18,10 @@ #define INTEL_FAM6_CORE2_DUNNINGTON 0x1D #define INTEL_FAM6_NEHALEM 0x1E +#define INTEL_FAM6_NEHALEM_G 0x1F /* Auburndale / Havendale */ #define INTEL_FAM6_NEHALEM_EP 0x1A #define INTEL_FAM6_NEHALEM_EX 0x2E #define INTEL_FAM6_WESTMERE 0x25 -#define INTEL_FAM6_WESTMERE2 0x1F #define INTEL_FAM6_WESTMERE_EP 0x2C #define INTEL_FAM6_WESTMERE_EX 0x2F diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 69e62862b622..33ae3a4d0159 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -35,8 +35,9 @@ #include <asm/asm.h> #include <asm/kvm_page_track.h> -#define KVM_MAX_VCPUS 255 -#define KVM_SOFT_MAX_VCPUS 160 +#define KVM_MAX_VCPUS 288 +#define KVM_SOFT_MAX_VCPUS 240 +#define KVM_MAX_VCPU_ID 1023 #define KVM_USER_MEM_SLOTS 509 /* memory slots that are not exposed to userspace */ #define KVM_PRIVATE_MEM_SLOTS 3 @@ -599,6 +600,7 @@ struct kvm_vcpu_arch { u64 mcg_cap; u64 mcg_status; u64 mcg_ctl; + u64 mcg_ext_ctl; u64 *mce_banks; /* Cache MMIO info */ @@ -682,9 +684,12 @@ struct kvm_arch_memory_slot { struct kvm_apic_map { struct rcu_head rcu; u8 mode; - struct kvm_lapic *phys_map[256]; - /* first index is cluster id second is cpu id in a cluster */ - struct kvm_lapic *logical_map[16][16]; + u32 max_apic_id; + union { + struct kvm_lapic *xapic_flat_map[8]; + struct kvm_lapic *xapic_cluster_map[16][4]; + }; + struct kvm_lapic *phys_map[]; }; /* Hyper-V emulation context */ @@ -779,6 +784,9 @@ struct kvm_arch { u32 ldr_mode; struct page *avic_logical_id_table_page; struct page *avic_physical_id_table_page; + + bool x2apic_format; + bool x2apic_broadcast_quirk_disabled; }; struct kvm_vm_stat { @@ -1006,6 +1014,11 @@ struct kvm_x86_ops { int (*update_pi_irte)(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set); void (*apicv_post_state_restore)(struct kvm_vcpu *vcpu); + + int (*set_hv_timer)(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc); + void (*cancel_hv_timer)(struct kvm_vcpu *vcpu); + + void (*setup_mce)(struct kvm_vcpu *vcpu); }; struct kvm_arch_async_pf { @@ -1026,7 +1039,7 @@ void kvm_mmu_setup(struct kvm_vcpu *vcpu); void kvm_mmu_init_vm(struct kvm *kvm); void kvm_mmu_uninit_vm(struct kvm *kvm); void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, - u64 dirty_mask, u64 nx_mask, u64 x_mask); + u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 p_mask); void kvm_mmu_reset_context(struct kvm_vcpu *vcpu); void kvm_mmu_slot_remove_write_access(struct kvm *kvm, @@ -1077,6 +1090,10 @@ extern u32 kvm_max_guest_tsc_khz; extern u8 kvm_tsc_scaling_ratio_frac_bits; /* maximum allowed value of TSC scaling ratio */ extern u64 kvm_max_tsc_scaling_ratio; +/* 1ull << kvm_tsc_scaling_ratio_frac_bits */ +extern u64 kvm_default_tsc_scaling_ratio; + +extern u64 kvm_mce_cap_supported; enum emulation_result { EMULATE_DONE, /* no further processing */ @@ -1352,7 +1369,7 @@ bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu); bool kvm_intr_is_single_vcpu(struct kvm *kvm, struct kvm_lapic_irq *irq, struct kvm_vcpu **dest_vcpu); -void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e, +void kvm_set_msi_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, struct kvm_lapic_irq *irq); static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) diff --git a/arch/x86/include/asm/livepatch.h b/arch/x86/include/asm/livepatch.h index a7f9181f63f3..ed80003ce3e2 100644 --- a/arch/x86/include/asm/livepatch.h +++ b/arch/x86/include/asm/livepatch.h @@ -22,7 +22,6 @@ #define _ASM_X86_LIVEPATCH_H #include <asm/setup.h> -#include <linux/module.h> #include <linux/ftrace.h> static inline int klp_check_compiler_support(void) diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index 9d3a96c4da78..da0d81fa0b54 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -133,40 +133,14 @@ static inline unsigned int x86_cpuid_family(void) #ifdef CONFIG_MICROCODE extern void __init load_ucode_bsp(void); extern void load_ucode_ap(void); -extern int __init save_microcode_in_initrd(void); void reload_early_microcode(void); extern bool get_builtin_firmware(struct cpio_data *cd, const char *name); #else static inline void __init load_ucode_bsp(void) { } static inline void load_ucode_ap(void) { } -static inline int __init save_microcode_in_initrd(void) { return 0; } static inline void reload_early_microcode(void) { } static inline bool get_builtin_firmware(struct cpio_data *cd, const char *name) { return false; } #endif -static inline unsigned long get_initrd_start(void) -{ -#ifdef CONFIG_BLK_DEV_INITRD - return initrd_start; -#else - return 0; -#endif -} - -static inline unsigned long get_initrd_start_addr(void) -{ -#ifdef CONFIG_BLK_DEV_INITRD -#ifdef CONFIG_X86_32 - unsigned long *initrd_start_p = (unsigned long *)__pa_nodebug(&initrd_start); - - return (unsigned long)__pa_nodebug(*initrd_start_p); -#else - return get_initrd_start(); -#endif -#else /* CONFIG_BLK_DEV_INITRD */ - return 0; -#endif -} - #endif /* _ASM_X86_MICROCODE_H */ diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h index adfc847a395e..15eb75484cc0 100644 --- a/arch/x86/include/asm/microcode_amd.h +++ b/arch/x86/include/asm/microcode_amd.h @@ -62,7 +62,6 @@ extern int apply_microcode_amd(int cpu); extern enum ucode_state load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size); #define PATCH_MAX_SIZE PAGE_SIZE -extern u8 amd_ucode_patch[PATCH_MAX_SIZE]; #ifdef CONFIG_MICROCODE_AMD extern void __init load_ucode_amd_bsp(unsigned int family); diff --git a/arch/x86/include/asm/microcode_intel.h b/arch/x86/include/asm/microcode_intel.h index 603417f8dd6c..5e69154c9f07 100644 --- a/arch/x86/include/asm/microcode_intel.h +++ b/arch/x86/include/asm/microcode_intel.h @@ -70,9 +70,4 @@ static inline int __init save_microcode_in_initrd_intel(void) { return -EINVAL; static inline void reload_ucode_intel(void) {} #endif -#ifdef CONFIG_HOTPLUG_CPU -extern int save_mc_for_early(u8 *mc); -#else -static inline int save_mc_for_early(u8 *mc) { return 0; } -#endif #endif /* _ASM_X86_MICROCODE_INTEL_H */ diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index 0deeb2d26df7..f37f2d8a2989 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -97,7 +97,7 @@ static inline void __sti_mwait(unsigned long eax, unsigned long ecx) */ static inline void mwait_idle_with_hints(unsigned long eax, unsigned long ecx) { - if (!current_set_polling_and_test()) { + if (static_cpu_has_bug(X86_BUG_MONITOR) || !current_set_polling_and_test()) { if (static_cpu_has_bug(X86_BUG_CLFLUSH_MONITOR)) { mb(); clflush((void *)¤t_thread_info()->flags); diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h index 3a52ee0e726d..3bae4969ac65 100644 --- a/arch/x86/include/asm/page_32_types.h +++ b/arch/x86/include/asm/page_32_types.h @@ -13,7 +13,8 @@ * If you want more physical memory than this then see the CONFIG_HIGHMEM4G * and CONFIG_HIGHMEM64G options in the kernel configuration. */ -#define __PAGE_OFFSET _AC(CONFIG_PAGE_OFFSET, UL) +#define __PAGE_OFFSET_BASE _AC(CONFIG_PAGE_OFFSET, UL) +#define __PAGE_OFFSET __PAGE_OFFSET_BASE #define __START_KERNEL_map __PAGE_OFFSET diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h index 4916144e3c42..fac9a5c0abe9 100644 --- a/arch/x86/include/asm/required-features.h +++ b/arch/x86/include/asm/required-features.h @@ -99,5 +99,7 @@ #define REQUIRED_MASK14 0 #define REQUIRED_MASK15 0 #define REQUIRED_MASK16 0 +#define REQUIRED_MASK17 0 +#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18) #endif /* _ASM_X86_REQUIRED_FEATURES_H */ diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index d0fe23ec7e98..14824fc78f7e 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -193,7 +193,6 @@ struct __attribute__ ((__packed__)) vmcb { struct vmcb_save_area save; }; -#define SVM_CPUID_FEATURE_SHIFT 2 #define SVM_CPUID_FUNC 0x8000000a #define SVM_VM_CR_SVM_DISABLE 4 diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 89bff044a6f5..b45ffdda3549 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -219,32 +219,8 @@ static inline unsigned long current_stack_pointer(void) * have to worry about atomic accesses. */ #define TS_COMPAT 0x0002 /* 32bit syscall active (64BIT)*/ -#define TS_RESTORE_SIGMASK 0x0008 /* restore signal mask in do_signal() */ #ifndef __ASSEMBLY__ -#define HAVE_SET_RESTORE_SIGMASK 1 -static inline void set_restore_sigmask(void) -{ - struct thread_info *ti = current_thread_info(); - ti->status |= TS_RESTORE_SIGMASK; - WARN_ON(!test_bit(TIF_SIGPENDING, (unsigned long *)&ti->flags)); -} -static inline void clear_restore_sigmask(void) -{ - current_thread_info()->status &= ~TS_RESTORE_SIGMASK; -} -static inline bool test_restore_sigmask(void) -{ - return current_thread_info()->status & TS_RESTORE_SIGMASK; -} -static inline bool test_and_clear_restore_sigmask(void) -{ - struct thread_info *ti = current_thread_info(); - if (!(ti->status & TS_RESTORE_SIGMASK)) - return false; - ti->status &= ~TS_RESTORE_SIGMASK; - return true; -} static inline bool in_ia32_syscall(void) { diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 43e87a3dd95c..cf75871d2f81 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -36,6 +36,7 @@ #include <linux/cpumask.h> #include <asm/mpspec.h> +#include <asm/percpu.h> /* Mappings between logical cpu number and node number */ DECLARE_EARLY_PER_CPU(int, x86_cpu_to_node_map); diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h index cce9ee68e335..0116b2ee9e64 100644 --- a/arch/x86/include/asm/virtext.h +++ b/arch/x86/include/asm/virtext.h @@ -83,23 +83,19 @@ static inline void cpu_emergency_vmxoff(void) */ static inline int cpu_has_svm(const char **msg) { - uint32_t eax, ebx, ecx, edx; - if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) { if (msg) *msg = "not amd"; return 0; } - cpuid(0x80000000, &eax, &ebx, &ecx, &edx); - if (eax < SVM_CPUID_FUNC) { + if (boot_cpu_data.extended_cpuid_level < SVM_CPUID_FUNC) { if (msg) *msg = "can't execute cpuid_8000000a"; return 0; } - cpuid(0x80000001, &eax, &ebx, &ecx, &edx); - if (!(ecx & (1 << SVM_CPUID_FEATURE_SHIFT))) { + if (!boot_cpu_has(X86_FEATURE_SVM)) { if (msg) *msg = "svm not available"; return 0; diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 6738e5c82cca..90d84c3eee53 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -28,7 +28,7 @@ #include <linux/acpi_pmtmr.h> #include <linux/efi.h> #include <linux/cpumask.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/dmi.h> #include <linux/irq.h> #include <linux/slab.h> diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c index 4b28159e0421..bdfad642123f 100644 --- a/arch/x86/kernel/acpi/cstate.c +++ b/arch/x86/kernel/acpi/cstate.c @@ -5,7 +5,7 @@ */ #include <linux/kernel.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/init.h> #include <linux/acpi.h> #include <linux/cpu.h> diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c index 8e3842fc8bea..42d27a62a404 100644 --- a/arch/x86/kernel/amd_gart_64.c +++ b/arch/x86/kernel/amd_gart_64.c @@ -20,7 +20,6 @@ #include <linux/string.h> #include <linux/spinlock.h> #include <linux/pci.h> -#include <linux/module.h> #include <linux/topology.h> #include <linux/interrupt.h> #include <linux/bitmap.h> diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index e991d5c8bb3a..4fdf6230d93c 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -9,7 +9,7 @@ #include <linux/slab.h> #include <linux/init.h> #include <linux/errno.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/spinlock.h> #include <asm/amd_nb.h> @@ -219,24 +219,22 @@ int amd_set_subcaches(int cpu, unsigned long mask) return 0; } -static int amd_cache_gart(void) +static void amd_cache_gart(void) { u16 i; - if (!amd_nb_has_feature(AMD_NB_GART)) - return 0; - - flush_words = kmalloc(amd_nb_num() * sizeof(u32), GFP_KERNEL); - if (!flush_words) { - amd_northbridges.flags &= ~AMD_NB_GART; - return -ENOMEM; - } + if (!amd_nb_has_feature(AMD_NB_GART)) + return; - for (i = 0; i != amd_nb_num(); i++) - pci_read_config_dword(node_to_amd_nb(i)->misc, 0x9c, - &flush_words[i]); + flush_words = kmalloc(amd_nb_num() * sizeof(u32), GFP_KERNEL); + if (!flush_words) { + amd_northbridges.flags &= ~AMD_NB_GART; + pr_notice("Cannot initialize GART flush words, GART support disabled\n"); + return; + } - return 0; + for (i = 0; i != amd_nb_num(); i++) + pci_read_config_dword(node_to_amd_nb(i)->misc, 0x9c, &flush_words[i]); } void amd_flush_garts(void) @@ -278,17 +276,10 @@ EXPORT_SYMBOL_GPL(amd_flush_garts); static __init int init_amd_nbs(void) { - int err = 0; + amd_cache_northbridges(); + amd_cache_gart(); - err = amd_cache_northbridges(); - - if (err < 0) - pr_notice("Cannot enumerate AMD northbridges\n"); - - if (amd_cache_gart() < 0) - pr_notice("Cannot initialize GART flush words, GART support disabled\n"); - - return err; + return 0; } /* This has to go after the PCI subsystem */ diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index ac8d8ad8b009..7943d38c57ca 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -23,7 +23,7 @@ #include <linux/bootmem.h> #include <linux/ftrace.h> #include <linux/ioport.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/syscore_ops.h> #include <linux/delay.h> #include <linux/timex.h> diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index 048747778d37..5b2ae106bd4a 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -15,7 +15,7 @@ #include <linux/kernel.h> #include <linux/ctype.h> #include <linux/hardirq.h> -#include <linux/module.h> +#include <linux/export.h> #include <asm/smp.h> #include <asm/apic.h> #include <asm/ipi.h> diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index 2cebf59092d8..c05688b2deff 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -11,7 +11,6 @@ #include <linux/threads.h> #include <linux/cpumask.h> -#include <linux/module.h> #include <linux/string.h> #include <linux/kernel.h> #include <linux/ctype.h> diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c index 7788ce643bf4..f29501e1a5c1 100644 --- a/arch/x86/kernel/apic/hw_nmi.c +++ b/arch/x86/kernel/apic/hw_nmi.c @@ -16,7 +16,7 @@ #include <linux/notifier.h> #include <linux/kprobes.h> #include <linux/nmi.h> -#include <linux/module.h> +#include <linux/init.h> #include <linux/delay.h> #ifdef CONFIG_HARDLOCKUP_DETECTOR diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index f072b9572634..7491f417a8e4 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -39,7 +39,7 @@ #include <linux/mc146818rtc.h> #include <linux/compiler.h> #include <linux/acpi.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/syscore_ops.h> #include <linux/freezer.h> #include <linux/kthread.h> diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c index 2a0f225afebd..3a205d4a12d0 100644 --- a/arch/x86/kernel/apic/ipi.c +++ b/arch/x86/kernel/apic/ipi.c @@ -8,7 +8,6 @@ #include <linux/mc146818rtc.h> #include <linux/cache.h> #include <linux/cpu.h> -#include <linux/module.h> #include <asm/smp.h> #include <asm/mtrr.h> diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index 93edfa01b408..7c43e716c158 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -8,7 +8,7 @@ */ #include <linux/threads.h> #include <linux/cpumask.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/string.h> #include <linux/kernel.h> #include <linux/ctype.h> diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c index 1793dba7a741..c303054b90b5 100644 --- a/arch/x86/kernel/apic/probe_64.c +++ b/arch/x86/kernel/apic/probe_64.c @@ -11,10 +11,9 @@ #include <linux/threads.h> #include <linux/cpumask.h> #include <linux/string.h> -#include <linux/module.h> +#include <linux/init.h> #include <linux/kernel.h> #include <linux/ctype.h> -#include <linux/init.h> #include <linux/hardirq.h> #include <linux/dmar.h> diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 64dd38fbf218..09b59adaea3f 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -12,7 +12,7 @@ #include <linux/proc_fs.h> #include <linux/threads.h> #include <linux/kernel.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/string.h> #include <linux/ctype.h> #include <linux/sched.h> diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index d22a7b9c4f0e..809eda03c527 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -2,7 +2,7 @@ #include <linux/linkage.h> #include <linux/bitops.h> #include <linux/kernel.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/percpu.h> #include <linux/string.h> #include <linux/ctype.h> diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c index 73d391ae452f..27e46658ebe3 100644 --- a/arch/x86/kernel/cpu/hypervisor.c +++ b/arch/x86/kernel/cpu/hypervisor.c @@ -21,7 +21,8 @@ * */ -#include <linux/module.h> +#include <linux/init.h> +#include <linux/export.h> #include <asm/processor.h> #include <asm/hypervisor.h> diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index c1a89bc026ac..fcd484d2bb03 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -5,7 +5,7 @@ #include <linux/smp.h> #include <linux/sched.h> #include <linux/thread_info.h> -#include <linux/module.h> +#include <linux/init.h> #include <linux/uaccess.h> #include <asm/cpufeature.h> @@ -13,6 +13,7 @@ #include <asm/msr.h> #include <asm/bugs.h> #include <asm/cpu.h> +#include <asm/intel-family.h> #ifdef CONFIG_X86_64 #include <linux/topology.h> @@ -508,6 +509,10 @@ static void init_intel(struct cpuinfo_x86 *c) (c->x86_model == 29 || c->x86_model == 46 || c->x86_model == 47)) set_cpu_bug(c, X86_BUG_CLFLUSH_MONITOR); + if (c->x86 == 6 && boot_cpu_has(X86_FEATURE_MWAIT) && + ((c->x86_model == INTEL_FAM6_ATOM_GOLDMONT))) + set_cpu_bug(c, X86_BUG_MONITOR); + #ifdef CONFIG_X86_64 if (c->x86 == 15) c->x86_cache_alignment = c->x86_clflush_size * 2; diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c index fbb5e90557a5..e42117d5f4d7 100644 --- a/arch/x86/kernel/cpu/match.c +++ b/arch/x86/kernel/cpu/match.c @@ -1,7 +1,7 @@ #include <asm/cpu_device_id.h> #include <asm/cpufeature.h> #include <linux/cpu.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/slab.h> /** diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 8581963894c7..27a0228c9cae 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -56,24 +56,24 @@ static u8 *container; static size_t container_size; static u32 ucode_new_rev; -u8 amd_ucode_patch[PATCH_MAX_SIZE]; +static u8 amd_ucode_patch[PATCH_MAX_SIZE]; static u16 this_equiv_id; static struct cpio_data ucode_cpio; -/* - * Microcode patch container file is prepended to the initrd in cpio format. - * See Documentation/x86/early-microcode.txt - */ -static __initdata char ucode_path[] = "kernel/x86/microcode/AuthenticAMD.bin"; - static struct cpio_data __init find_ucode_in_initrd(void) { - long offset = 0; +#ifdef CONFIG_BLK_DEV_INITRD char *path; void *start; size_t size; + /* + * Microcode patch container file is prepended to the initrd in cpio + * format. See Documentation/x86/early-microcode.txt + */ + static __initdata char ucode_path[] = "kernel/x86/microcode/AuthenticAMD.bin"; + #ifdef CONFIG_X86_32 struct boot_params *p; @@ -89,9 +89,12 @@ static struct cpio_data __init find_ucode_in_initrd(void) path = ucode_path; start = (void *)(boot_params.hdr.ramdisk_image + PAGE_OFFSET); size = boot_params.hdr.ramdisk_size; -#endif +#endif /* !CONFIG_X86_32 */ - return find_cpio_data(path, start, size, &offset); + return find_cpio_data(path, start, size, NULL); +#else + return (struct cpio_data){ NULL, 0, "" }; +#endif } static size_t compute_container_size(u8 *data, u32 total_size) @@ -289,11 +292,11 @@ void __init load_ucode_amd_bsp(unsigned int family) size = &ucode_cpio.size; #endif - cp = find_ucode_in_initrd(); - if (!cp.data) { - if (!load_builtin_amd_microcode(&cp, family)) - return; - } + if (!load_builtin_amd_microcode(&cp, family)) + cp = find_ucode_in_initrd(); + + if (!(cp.data && cp.size)) + return; *data = cp.data; *size = cp.size; diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index ac360bfbbdb6..df04b2d033f6 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -60,7 +60,6 @@ static bool dis_ucode_ldr; static DEFINE_MUTEX(microcode_mutex); struct ucode_cpu_info ucode_cpu_info[NR_CPUS]; -EXPORT_SYMBOL_GPL(ucode_cpu_info); /* * Operations that are run on a target cpu: @@ -175,24 +174,24 @@ void load_ucode_ap(void) } } -int __init save_microcode_in_initrd(void) +static int __init save_microcode_in_initrd(void) { struct cpuinfo_x86 *c = &boot_cpu_data; switch (c->x86_vendor) { case X86_VENDOR_INTEL: if (c->x86 >= 6) - save_microcode_in_initrd_intel(); + return save_microcode_in_initrd_intel(); break; case X86_VENDOR_AMD: if (c->x86 >= 0x10) - save_microcode_in_initrd_amd(); + return save_microcode_in_initrd_amd(); break; default: break; } - return 0; + return -EINVAL; } void reload_early_microcode(void) @@ -691,4 +690,5 @@ int __init microcode_init(void) return error; } +fs_initcall(save_microcode_in_initrd); late_initcall(microcode_init); diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 65cbbcd48fe4..cdc0deab00c9 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -40,9 +40,13 @@ #include <asm/msr.h> /* - * Temporary microcode blobs pointers storage. We note here the pointers to - * microcode blobs we've got from whatever storage (detached initrd, builtin). - * Later on, we put those into final storage mc_saved_data.mc_saved. + * Temporary microcode blobs pointers storage. We note here during early load + * the pointers to microcode blobs we've got from whatever storage (detached + * initrd, builtin). Later on, we put those into final storage + * mc_saved_data.mc_saved. + * + * Important: those are offsets from the beginning of initrd or absolute + * addresses within the kernel image when built-in. */ static unsigned long mc_tmp_ptrs[MAX_UCODE_COUNT]; @@ -51,8 +55,15 @@ static struct mc_saved_data { struct microcode_intel **mc_saved; } mc_saved_data; +/* Microcode blobs within the initrd. 0 if builtin. */ +static struct ucode_blobs { + unsigned long start; + bool valid; +} blobs; + +/* Go through saved patches and find the one suitable for the current CPU. */ static enum ucode_state -load_microcode_early(struct microcode_intel **saved, +find_microcode_patch(struct microcode_intel **saved, unsigned int num_saved, struct ucode_cpu_info *uci) { struct microcode_intel *ucode_ptr, *new_mc = NULL; @@ -121,13 +132,13 @@ load_microcode(struct mc_saved_data *mcs, unsigned long *mc_ptrs, if (!mcs->mc_saved) { copy_ptrs(mc_saved_tmp, mc_ptrs, offset, count); - return load_microcode_early(mc_saved_tmp, count, uci); + return find_microcode_patch(mc_saved_tmp, count, uci); } else { #ifdef CONFIG_X86_32 microcode_phys(mc_saved_tmp, mcs); - return load_microcode_early(mc_saved_tmp, count, uci); + return find_microcode_patch(mc_saved_tmp, count, uci); #else - return load_microcode_early(mcs->mc_saved, count, uci); + return find_microcode_patch(mcs->mc_saved, count, uci); #endif } } @@ -450,8 +461,6 @@ static void show_saved_mc(void) #endif } -#ifdef 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. @@ -459,19 +468,18 @@ static DEFINE_MUTEX(x86_cpu_microcode_mutex); * Please make sure this mc should be a valid microcode patch before calling * this function. */ -int save_mc_for_early(u8 *mc) +static void save_mc_for_early(u8 *mc) { +#ifdef CONFIG_HOTPLUG_CPU + /* Synchronization during CPU hotplug. */ + static DEFINE_MUTEX(x86_cpu_microcode_mutex); + struct microcode_intel *mc_saved_tmp[MAX_UCODE_COUNT]; unsigned int mc_saved_count_init; unsigned int num_saved; struct microcode_intel **mc_saved; - int ret = 0; - int i; + int ret, i; - /* - * Hold hotplug lock so mc_saved_data is not accessed by a CPU in - * hotplug. - */ mutex_lock(&x86_cpu_microcode_mutex); mc_saved_count_init = mc_saved_data.num_saved; @@ -509,11 +517,8 @@ int save_mc_for_early(u8 *mc) out: mutex_unlock(&x86_cpu_microcode_mutex); - - return ret; -} -EXPORT_SYMBOL_GPL(save_mc_for_early); #endif +} static bool __init load_builtin_intel_microcode(struct cpio_data *cp) { @@ -532,37 +537,6 @@ static bool __init load_builtin_intel_microcode(struct cpio_data *cp) #endif } -static __initdata char ucode_name[] = "kernel/x86/microcode/GenuineIntel.bin"; -static __init enum ucode_state -scan_microcode(struct mc_saved_data *mcs, unsigned long *mc_ptrs, - unsigned long start, unsigned long size, - struct ucode_cpu_info *uci) -{ - struct cpio_data cd; - long offset = 0; -#ifdef CONFIG_X86_32 - char *p = (char *)__pa_nodebug(ucode_name); -#else - char *p = ucode_name; -#endif - - cd.data = NULL; - cd.size = 0; - - /* try built-in microcode if no initrd */ - if (!size) { - if (!load_builtin_intel_microcode(&cd)) - return UCODE_ERROR; - } else { - cd = find_cpio_data(p, (void *)start, size, &offset); - if (!cd.data) - return UCODE_ERROR; - } - - return get_matching_model_microcode(start, cd.data, cd.size, - mcs, mc_ptrs, uci); -} - /* * Print ucode update info. */ @@ -680,38 +654,117 @@ static int apply_microcode_early(struct ucode_cpu_info *uci, bool early) */ int __init save_microcode_in_initrd_intel(void) { - unsigned int count = mc_saved_data.num_saved; struct microcode_intel *mc_saved[MAX_UCODE_COUNT]; - int ret = 0; + unsigned int count = mc_saved_data.num_saved; + unsigned long offset = 0; + int ret; if (!count) - return ret; + return 0; + + /* + * We have found a valid initrd but it might've been relocated in the + * meantime so get its updated address. + */ + if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && blobs.valid) + offset = initrd_start; - copy_ptrs(mc_saved, mc_tmp_ptrs, get_initrd_start(), count); + copy_ptrs(mc_saved, mc_tmp_ptrs, offset, count); ret = save_microcode(&mc_saved_data, mc_saved, count); if (ret) pr_err("Cannot save microcode patches from initrd.\n"); - - show_saved_mc(); + else + show_saved_mc(); return ret; } +static __init enum ucode_state +__scan_microcode_initrd(struct cpio_data *cd, struct ucode_blobs *blbp) +{ +#ifdef CONFIG_BLK_DEV_INITRD + static __initdata char ucode_name[] = "kernel/x86/microcode/GenuineIntel.bin"; + char *p = IS_ENABLED(CONFIG_X86_32) ? (char *)__pa_nodebug(ucode_name) + : ucode_name; +# ifdef CONFIG_X86_32 + unsigned long start = 0, size; + struct boot_params *params; + + params = (struct boot_params *)__pa_nodebug(&boot_params); + size = params->hdr.ramdisk_size; + + /* + * Set start only if we have an initrd image. We cannot use initrd_start + * because it is not set that early yet. + */ + start = (size ? params->hdr.ramdisk_image : 0); + +# else /* CONFIG_X86_64 */ + unsigned long start = 0, size; + + size = (u64)boot_params.ext_ramdisk_size << 32; + size |= boot_params.hdr.ramdisk_size; + + if (size) { + start = (u64)boot_params.ext_ramdisk_image << 32; + start |= boot_params.hdr.ramdisk_image; + + start += PAGE_OFFSET; + } +# endif + + *cd = find_cpio_data(p, (void *)start, size, NULL); + if (cd->data) { + blbp->start = start; + blbp->valid = true; + + return UCODE_OK; + } else +#endif /* CONFIG_BLK_DEV_INITRD */ + return UCODE_ERROR; +} + +static __init enum ucode_state +scan_microcode(struct mc_saved_data *mcs, unsigned long *mc_ptrs, + struct ucode_cpu_info *uci, struct ucode_blobs *blbp) +{ + struct cpio_data cd = { NULL, 0, "" }; + enum ucode_state ret; + + /* try built-in microcode first */ + if (load_builtin_intel_microcode(&cd)) + /* + * Invalidate blobs as we might've gotten an initrd too, + * supplied by the boot loader, by mistake or simply forgotten + * there. That's fine, we ignore it since we've found builtin + * microcode already. + */ + blbp->valid = false; + else { + ret = __scan_microcode_initrd(&cd, blbp); + if (ret != UCODE_OK) + return ret; + } + + return get_matching_model_microcode(blbp->start, cd.data, cd.size, + mcs, mc_ptrs, uci); +} + static void __init _load_ucode_intel_bsp(struct mc_saved_data *mcs, unsigned long *mc_ptrs, - unsigned long start, unsigned long size) + struct ucode_blobs *blbp) { struct ucode_cpu_info uci; enum ucode_state ret; collect_cpu_info_early(&uci); - ret = scan_microcode(mcs, mc_ptrs, start, size, &uci); + ret = scan_microcode(mcs, mc_ptrs, &uci, blbp); if (ret != UCODE_OK) return; - ret = load_microcode(mcs, mc_ptrs, start, &uci); + ret = load_microcode(mcs, mc_ptrs, blbp->start, &uci); if (ret != UCODE_OK) return; @@ -720,54 +773,60 @@ _load_ucode_intel_bsp(struct mc_saved_data *mcs, unsigned long *mc_ptrs, void __init load_ucode_intel_bsp(void) { - u64 start, size; -#ifdef CONFIG_X86_32 - struct boot_params *p; - - p = (struct boot_params *)__pa_nodebug(&boot_params); - size = p->hdr.ramdisk_size; + struct ucode_blobs *blobs_p; + struct mc_saved_data *mcs; + unsigned long *ptrs; - /* - * Set start only if we have an initrd image. We cannot use initrd_start - * because it is not set that early yet. - */ - start = (size ? p->hdr.ramdisk_image : 0); - - _load_ucode_intel_bsp((struct mc_saved_data *)__pa_nodebug(&mc_saved_data), - (unsigned long *)__pa_nodebug(&mc_tmp_ptrs), - start, size); +#ifdef CONFIG_X86_32 + mcs = (struct mc_saved_data *)__pa_nodebug(&mc_saved_data); + ptrs = (unsigned long *)__pa_nodebug(&mc_tmp_ptrs); + blobs_p = (struct ucode_blobs *)__pa_nodebug(&blobs); #else - size = boot_params.hdr.ramdisk_size; - start = (size ? boot_params.hdr.ramdisk_image + PAGE_OFFSET : 0); - - _load_ucode_intel_bsp(&mc_saved_data, mc_tmp_ptrs, start, size); + mcs = &mc_saved_data; + ptrs = mc_tmp_ptrs; + blobs_p = &blobs; #endif + + _load_ucode_intel_bsp(mcs, ptrs, blobs_p); } void load_ucode_intel_ap(void) { - unsigned long *mcs_tmp_p; - struct mc_saved_data *mcs_p; + struct ucode_blobs *blobs_p; + unsigned long *ptrs, start = 0; + struct mc_saved_data *mcs; struct ucode_cpu_info uci; enum ucode_state ret; -#ifdef CONFIG_X86_32 - mcs_tmp_p = (unsigned long *)__pa_nodebug(mc_tmp_ptrs); - mcs_p = (struct mc_saved_data *)__pa_nodebug(&mc_saved_data); +#ifdef CONFIG_X86_32 + mcs = (struct mc_saved_data *)__pa_nodebug(&mc_saved_data); + ptrs = (unsigned long *)__pa_nodebug(mc_tmp_ptrs); + blobs_p = (struct ucode_blobs *)__pa_nodebug(&blobs); #else - mcs_tmp_p = mc_tmp_ptrs; - mcs_p = &mc_saved_data; + mcs = &mc_saved_data; + ptrs = mc_tmp_ptrs; + blobs_p = &blobs; #endif /* * If there is no valid ucode previously saved in memory, no need to * update ucode on this AP. */ - if (!mcs_p->num_saved) + if (!mcs->num_saved) return; + if (blobs_p->valid) { + start = blobs_p->start; + + /* + * Pay attention to CONFIG_RANDOMIZE_MEMORY=y as it shuffles + * physmem mapping too and there we have the initrd. + */ + start += PAGE_OFFSET - __PAGE_OFFSET_BASE; + } + collect_cpu_info_early(&uci); - ret = load_microcode(mcs_p, mcs_tmp_p, get_initrd_start_addr(), &uci); + ret = load_microcode(mcs, ptrs, start, &uci); if (ret != UCODE_OK) return; @@ -784,7 +843,7 @@ void reload_ucode_intel(void) collect_cpu_info_early(&uci); - ret = load_microcode_early(mc_saved_data.mc_saved, + ret = find_microcode_patch(mc_saved_data.mc_saved, mc_saved_data.num_saved, &uci); if (ret != UCODE_OK) return; @@ -794,6 +853,7 @@ void reload_ucode_intel(void) static int collect_cpu_info(int cpu_num, struct cpu_signature *csig) { + static struct cpu_signature prev; struct cpuinfo_x86 *c = &cpu_data(cpu_num); unsigned int val[2]; @@ -808,8 +868,13 @@ static int collect_cpu_info(int cpu_num, struct cpu_signature *csig) } csig->rev = c->microcode; - pr_info("CPU%d sig=0x%x, pf=0x%x, revision=0x%x\n", - cpu_num, csig->sig, csig->pf, csig->rev); + + /* No extra locking on prev, races are harmless. */ + if (csig->sig != prev.sig || csig->pf != prev.pf || csig->rev != prev.rev) { + pr_info("sig=0x%x, pf=0x%x, revision=0x%x\n", + csig->sig, csig->pf, csig->rev); + prev = *csig; + } return 0; } @@ -838,6 +903,7 @@ static int apply_microcode_intel(int cpu) struct ucode_cpu_info *uci; struct cpuinfo_x86 *c; unsigned int val[2]; + static int prev_rev; /* We should bind the task to the CPU */ if (WARN_ON(raw_smp_processor_id() != cpu)) @@ -872,11 +938,14 @@ static int apply_microcode_intel(int cpu) return -1; } - pr_info("CPU%d updated to revision 0x%x, date = %04x-%02x-%02x\n", - cpu, val[1], - mc->hdr.date & 0xffff, - mc->hdr.date >> 24, - (mc->hdr.date >> 16) & 0xff); + if (val[1] != prev_rev) { + pr_info("updated to revision 0x%x, date = %04x-%02x-%02x\n", + val[1], + mc->hdr.date & 0xffff, + mc->hdr.date >> 24, + (mc->hdr.date >> 16) & 0xff); + prev_rev = val[1]; + } c = &cpu_data(cpu); diff --git a/arch/x86/kernel/cpu/microcode/intel_lib.c b/arch/x86/kernel/cpu/microcode/intel_lib.c index 2ce1a7dc45b7..406cb6c0d9dd 100644 --- a/arch/x86/kernel/cpu/microcode/intel_lib.c +++ b/arch/x86/kernel/cpu/microcode/intel_lib.c @@ -141,7 +141,6 @@ int microcode_sanity_check(void *mc, int print_err) } return 0; } -EXPORT_SYMBOL_GPL(microcode_sanity_check); /* * Returns 1 if update has been found, 0 otherwise. @@ -183,4 +182,3 @@ int has_newer_microcode(void *mc, unsigned int csig, int cpf, int new_rev) return find_matching_signature(mc, csig, cpf); } -EXPORT_SYMBOL_GPL(has_newer_microcode); diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 10c11b4da31d..8f44c5a50ab8 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -13,7 +13,8 @@ #include <linux/types.h> #include <linux/time.h> #include <linux/clocksource.h> -#include <linux/module.h> +#include <linux/init.h> +#include <linux/export.h> #include <linux/hardirq.h> #include <linux/efi.h> #include <linux/interrupt.h> diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c index 31e951ce6dff..3b442b64c72d 100644 --- a/arch/x86/kernel/cpu/mtrr/cleanup.c +++ b/arch/x86/kernel/cpu/mtrr/cleanup.c @@ -17,7 +17,6 @@ * License along with this library; if not, write to the Free * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ -#include <linux/module.h> #include <linux/init.h> #include <linux/pci.h> #include <linux/smp.h> diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 16e37a2581ac..fdc55215d44d 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -4,7 +4,7 @@ */ #define DEBUG -#include <linux/module.h> +#include <linux/export.h> #include <linux/init.h> #include <linux/io.h> #include <linux/mm.h> diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c index d76f13d6d8d6..6d9b45549109 100644 --- a/arch/x86/kernel/cpu/mtrr/if.c +++ b/arch/x86/kernel/cpu/mtrr/if.c @@ -2,7 +2,6 @@ #include <linux/seq_file.h> #include <linux/uaccess.h> #include <linux/proc_fs.h> -#include <linux/module.h> #include <linux/ctype.h> #include <linux/string.h> #include <linux/slab.h> diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index 7d393ecdeee6..28f1b54b7fad 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -38,7 +38,7 @@ #include <linux/stop_machine.h> #include <linux/kvm_para.h> #include <linux/uaccess.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/mutex.h> #include <linux/init.h> #include <linux/sort.h> diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c index 2e8caf03f593..181eabecae25 100644 --- a/arch/x86/kernel/cpu/perfctr-watchdog.c +++ b/arch/x86/kernel/cpu/perfctr-watchdog.c @@ -12,7 +12,7 @@ */ #include <linux/percpu.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/kernel.h> #include <linux/bitops.h> #include <linux/smp.h> diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index 8cac429b6a1d..1ff0598d309c 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -22,7 +22,8 @@ */ #include <linux/dmi.h> -#include <linux/module.h> +#include <linux/init.h> +#include <linux/export.h> #include <asm/div64.h> #include <asm/x86_init.h> #include <asm/hypervisor.h> diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 9ef978d69c22..9616cf76940c 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -20,7 +20,7 @@ #include <linux/delay.h> #include <linux/elf.h> #include <linux/elfcore.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/slab.h> #include <linux/vmalloc.h> diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index 948d77da3881..09675712eba8 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -7,7 +7,7 @@ #include <linux/uaccess.h> #include <linux/hardirq.h> #include <linux/kdebug.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/ptrace.h> #include <linux/kexec.h> #include <linux/sysfs.h> diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 6dede08dd98b..9ee4520ce83c 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -7,7 +7,7 @@ #include <linux/uaccess.h> #include <linux/hardirq.h> #include <linux/kdebug.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/ptrace.h> #include <linux/kexec.h> #include <linux/sysfs.h> diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 57b71373bae3..de7501edb21c 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -237,36 +237,19 @@ static void __init intel_remapping_check(int num, int slot, int func) * despite the efforts of the "RAM buffer" approach, which simply rounds * memory boundaries up to 64M to try to catch space that may decode * as RAM and so is not suitable for MMIO. - * - * And yes, so far on current devices the base addr is always under 4G. */ -static u32 __init intel_stolen_base(int num, int slot, int func, size_t stolen_size) -{ - u32 base; - - /* - * For the PCI IDs in this quirk, the stolen base is always - * in 0x5c, aka the BDSM register (yes that's really what - * it's called). - */ - base = read_pci_config(num, slot, func, 0x5c); - base &= ~((1<<20) - 1); - - return base; -} #define KB(x) ((x) * 1024UL) #define MB(x) (KB (KB (x))) -#define GB(x) (MB (KB (x))) static size_t __init i830_tseg_size(void) { - u8 tmp = read_pci_config_byte(0, 0, 0, I830_ESMRAMC); + u8 esmramc = read_pci_config_byte(0, 0, 0, I830_ESMRAMC); - if (!(tmp & TSEG_ENABLE)) + if (!(esmramc & TSEG_ENABLE)) return 0; - if (tmp & I830_TSEG_SIZE_1M) + if (esmramc & I830_TSEG_SIZE_1M) return MB(1); else return KB(512); @@ -274,27 +257,26 @@ static size_t __init i830_tseg_size(void) static size_t __init i845_tseg_size(void) { - u8 tmp = read_pci_config_byte(0, 0, 0, I845_ESMRAMC); + u8 esmramc = read_pci_config_byte(0, 0, 0, I845_ESMRAMC); + u8 tseg_size = esmramc & I845_TSEG_SIZE_MASK; - if (!(tmp & TSEG_ENABLE)) + if (!(esmramc & TSEG_ENABLE)) return 0; - switch (tmp & I845_TSEG_SIZE_MASK) { - case I845_TSEG_SIZE_512K: - return KB(512); - case I845_TSEG_SIZE_1M: - return MB(1); + switch (tseg_size) { + case I845_TSEG_SIZE_512K: return KB(512); + case I845_TSEG_SIZE_1M: return MB(1); default: - WARN_ON(1); - return 0; + WARN(1, "Unknown ESMRAMC value: %x!\n", esmramc); } + return 0; } static size_t __init i85x_tseg_size(void) { - u8 tmp = read_pci_config_byte(0, 0, 0, I85X_ESMRAMC); + u8 esmramc = read_pci_config_byte(0, 0, 0, I85X_ESMRAMC); - if (!(tmp & TSEG_ENABLE)) + if (!(esmramc & TSEG_ENABLE)) return 0; return MB(1); @@ -314,285 +296,287 @@ static size_t __init i85x_mem_size(void) * On 830/845/85x the stolen memory base isn't available in any * register. We need to calculate it as TOM-TSEG_SIZE-stolen_size. */ -static u32 __init i830_stolen_base(int num, int slot, int func, size_t stolen_size) +static phys_addr_t __init i830_stolen_base(int num, int slot, int func, + size_t stolen_size) { - return i830_mem_size() - i830_tseg_size() - stolen_size; + return (phys_addr_t)i830_mem_size() - i830_tseg_size() - stolen_size; } -static u32 __init i845_stolen_base(int num, int slot, int func, size_t stolen_size) +static phys_addr_t __init i845_stolen_base(int num, int slot, int func, + size_t stolen_size) { - return i830_mem_size() - i845_tseg_size() - stolen_size; + return (phys_addr_t)i830_mem_size() - i845_tseg_size() - stolen_size; } -static u32 __init i85x_stolen_base(int num, int slot, int func, size_t stolen_size) +static phys_addr_t __init i85x_stolen_base(int num, int slot, int func, + size_t stolen_size) { - return i85x_mem_size() - i85x_tseg_size() - stolen_size; + return (phys_addr_t)i85x_mem_size() - i85x_tseg_size() - stolen_size; } -static u32 __init i865_stolen_base(int num, int slot, int func, size_t stolen_size) +static phys_addr_t __init i865_stolen_base(int num, int slot, int func, + size_t stolen_size) { + u16 toud; + /* * FIXME is the graphics stolen memory region * always at TOUD? Ie. is it always the last * one to be allocated by the BIOS? */ - return read_pci_config_16(0, 0, 0, I865_TOUD) << 16; + toud = read_pci_config_16(0, 0, 0, I865_TOUD); + + return (phys_addr_t)toud << 16; +} + +static phys_addr_t __init gen3_stolen_base(int num, int slot, int func, + size_t stolen_size) +{ + u32 bsm; + + /* Almost universally we can find the Graphics Base of Stolen Memory + * at register BSM (0x5c) in the igfx configuration space. On a few + * (desktop) machines this is also mirrored in the bridge device at + * different locations, or in the MCHBAR. + */ + bsm = read_pci_config(num, slot, func, INTEL_BSM); + + return (phys_addr_t)bsm & INTEL_BSM_MASK; } static size_t __init i830_stolen_size(int num, int slot, int func) { - size_t stolen_size; u16 gmch_ctrl; + u16 gms; gmch_ctrl = read_pci_config_16(0, 0, 0, I830_GMCH_CTRL); - - switch (gmch_ctrl & I830_GMCH_GMS_MASK) { - case I830_GMCH_GMS_STOLEN_512: - stolen_size = KB(512); - break; - case I830_GMCH_GMS_STOLEN_1024: - stolen_size = MB(1); - break; - case I830_GMCH_GMS_STOLEN_8192: - stolen_size = MB(8); - break; - case I830_GMCH_GMS_LOCAL: - /* local memory isn't part of the normal address space */ - stolen_size = 0; - break; + gms = gmch_ctrl & I830_GMCH_GMS_MASK; + + switch (gms) { + case I830_GMCH_GMS_STOLEN_512: return KB(512); + case I830_GMCH_GMS_STOLEN_1024: return MB(1); + case I830_GMCH_GMS_STOLEN_8192: return MB(8); + /* local memory isn't part of the normal address space */ + case I830_GMCH_GMS_LOCAL: return 0; default: - return 0; + WARN(1, "Unknown GMCH_CTRL value: %x!\n", gmch_ctrl); } - return stolen_size; + return 0; } static size_t __init gen3_stolen_size(int num, int slot, int func) { - size_t stolen_size; u16 gmch_ctrl; + u16 gms; gmch_ctrl = read_pci_config_16(0, 0, 0, I830_GMCH_CTRL); - - switch (gmch_ctrl & I855_GMCH_GMS_MASK) { - case I855_GMCH_GMS_STOLEN_1M: - stolen_size = MB(1); - break; - case I855_GMCH_GMS_STOLEN_4M: - stolen_size = MB(4); - break; - case I855_GMCH_GMS_STOLEN_8M: - stolen_size = MB(8); - break; - case I855_GMCH_GMS_STOLEN_16M: - stolen_size = MB(16); - break; - case I855_GMCH_GMS_STOLEN_32M: - stolen_size = MB(32); - break; - case I915_GMCH_GMS_STOLEN_48M: - stolen_size = MB(48); - break; - case I915_GMCH_GMS_STOLEN_64M: - stolen_size = MB(64); - break; - case G33_GMCH_GMS_STOLEN_128M: - stolen_size = MB(128); - break; - case G33_GMCH_GMS_STOLEN_256M: - stolen_size = MB(256); - break; - case INTEL_GMCH_GMS_STOLEN_96M: - stolen_size = MB(96); - break; - case INTEL_GMCH_GMS_STOLEN_160M: - stolen_size = MB(160); - break; - case INTEL_GMCH_GMS_STOLEN_224M: - stolen_size = MB(224); - break; - case INTEL_GMCH_GMS_STOLEN_352M: - stolen_size = MB(352); - break; + gms = gmch_ctrl & I855_GMCH_GMS_MASK; + + switch (gms) { + case I855_GMCH_GMS_STOLEN_1M: return MB(1); + case I855_GMCH_GMS_STOLEN_4M: return MB(4); + case I855_GMCH_GMS_STOLEN_8M: return MB(8); + case I855_GMCH_GMS_STOLEN_16M: return MB(16); + case I855_GMCH_GMS_STOLEN_32M: return MB(32); + case I915_GMCH_GMS_STOLEN_48M: return MB(48); + case I915_GMCH_GMS_STOLEN_64M: return MB(64); + case G33_GMCH_GMS_STOLEN_128M: return MB(128); + case G33_GMCH_GMS_STOLEN_256M: return MB(256); + case INTEL_GMCH_GMS_STOLEN_96M: return MB(96); + case INTEL_GMCH_GMS_STOLEN_160M:return MB(160); + case INTEL_GMCH_GMS_STOLEN_224M:return MB(224); + case INTEL_GMCH_GMS_STOLEN_352M:return MB(352); default: - stolen_size = 0; - break; + WARN(1, "Unknown GMCH_CTRL value: %x!\n", gmch_ctrl); } - return stolen_size; + return 0; } static size_t __init gen6_stolen_size(int num, int slot, int func) { u16 gmch_ctrl; + u16 gms; gmch_ctrl = read_pci_config_16(num, slot, func, SNB_GMCH_CTRL); - gmch_ctrl >>= SNB_GMCH_GMS_SHIFT; - gmch_ctrl &= SNB_GMCH_GMS_MASK; + gms = (gmch_ctrl >> SNB_GMCH_GMS_SHIFT) & SNB_GMCH_GMS_MASK; - return gmch_ctrl << 25; /* 32 MB units */ + return (size_t)gms * MB(32); } static size_t __init gen8_stolen_size(int num, int slot, int func) { u16 gmch_ctrl; + u16 gms; gmch_ctrl = read_pci_config_16(num, slot, func, SNB_GMCH_CTRL); - gmch_ctrl >>= BDW_GMCH_GMS_SHIFT; - gmch_ctrl &= BDW_GMCH_GMS_MASK; - return gmch_ctrl << 25; /* 32 MB units */ + gms = (gmch_ctrl >> BDW_GMCH_GMS_SHIFT) & BDW_GMCH_GMS_MASK; + + return (size_t)gms * MB(32); } static size_t __init chv_stolen_size(int num, int slot, int func) { u16 gmch_ctrl; + u16 gms; gmch_ctrl = read_pci_config_16(num, slot, func, SNB_GMCH_CTRL); - gmch_ctrl >>= SNB_GMCH_GMS_SHIFT; - gmch_ctrl &= SNB_GMCH_GMS_MASK; + gms = (gmch_ctrl >> SNB_GMCH_GMS_SHIFT) & SNB_GMCH_GMS_MASK; /* * 0x0 to 0x10: 32MB increments starting at 0MB * 0x11 to 0x16: 4MB increments starting at 8MB * 0x17 to 0x1d: 4MB increments start at 36MB */ - if (gmch_ctrl < 0x11) - return gmch_ctrl << 25; - else if (gmch_ctrl < 0x17) - return (gmch_ctrl - 0x11 + 2) << 22; + if (gms < 0x11) + return (size_t)gms * MB(32); + else if (gms < 0x17) + return (size_t)(gms - 0x11 + 2) * MB(4); else - return (gmch_ctrl - 0x17 + 9) << 22; + return (size_t)(gms - 0x17 + 9) * MB(4); } -struct intel_stolen_funcs { - size_t (*size)(int num, int slot, int func); - u32 (*base)(int num, int slot, int func, size_t size); -}; - static size_t __init gen9_stolen_size(int num, int slot, int func) { u16 gmch_ctrl; + u16 gms; gmch_ctrl = read_pci_config_16(num, slot, func, SNB_GMCH_CTRL); - gmch_ctrl >>= BDW_GMCH_GMS_SHIFT; - gmch_ctrl &= BDW_GMCH_GMS_MASK; + gms = (gmch_ctrl >> BDW_GMCH_GMS_SHIFT) & BDW_GMCH_GMS_MASK; - if (gmch_ctrl < 0xf0) - return gmch_ctrl << 25; /* 32 MB units */ + /* 0x0 to 0xef: 32MB increments starting at 0MB */ + /* 0xf0 to 0xfe: 4MB increments starting at 4MB */ + if (gms < 0xf0) + return (size_t)gms * MB(32); else - /* 4MB increments starting at 0xf0 for 4MB */ - return (gmch_ctrl - 0xf0 + 1) << 22; + return (size_t)(gms - 0xf0 + 1) * MB(4); } -typedef size_t (*stolen_size_fn)(int num, int slot, int func); +struct intel_early_ops { + size_t (*stolen_size)(int num, int slot, int func); + phys_addr_t (*stolen_base)(int num, int slot, int func, size_t size); +}; -static const struct intel_stolen_funcs i830_stolen_funcs __initconst = { - .base = i830_stolen_base, - .size = i830_stolen_size, +static const struct intel_early_ops i830_early_ops __initconst = { + .stolen_base = i830_stolen_base, + .stolen_size = i830_stolen_size, }; -static const struct intel_stolen_funcs i845_stolen_funcs __initconst = { - .base = i845_stolen_base, - .size = i830_stolen_size, +static const struct intel_early_ops i845_early_ops __initconst = { + .stolen_base = i845_stolen_base, + .stolen_size = i830_stolen_size, }; -static const struct intel_stolen_funcs i85x_stolen_funcs __initconst = { - .base = i85x_stolen_base, - .size = gen3_stolen_size, +static const struct intel_early_ops i85x_early_ops __initconst = { + .stolen_base = i85x_stolen_base, + .stolen_size = gen3_stolen_size, }; -static const struct intel_stolen_funcs i865_stolen_funcs __initconst = { - .base = i865_stolen_base, - .size = gen3_stolen_size, +static const struct intel_early_ops i865_early_ops __initconst = { + .stolen_base = i865_stolen_base, + .stolen_size = gen3_stolen_size, }; -static const struct intel_stolen_funcs gen3_stolen_funcs __initconst = { - .base = intel_stolen_base, - .size = gen3_stolen_size, +static const struct intel_early_ops gen3_early_ops __initconst = { + .stolen_base = gen3_stolen_base, + .stolen_size = gen3_stolen_size, }; -static const struct intel_stolen_funcs gen6_stolen_funcs __initconst = { - .base = intel_stolen_base, - .size = gen6_stolen_size, +static const struct intel_early_ops gen6_early_ops __initconst = { + .stolen_base = gen3_stolen_base, + .stolen_size = gen6_stolen_size, }; -static const struct intel_stolen_funcs gen8_stolen_funcs __initconst = { - .base = intel_stolen_base, - .size = gen8_stolen_size, +static const struct intel_early_ops gen8_early_ops __initconst = { + .stolen_base = gen3_stolen_base, + .stolen_size = gen8_stolen_size, }; -static const struct intel_stolen_funcs gen9_stolen_funcs __initconst = { - .base = intel_stolen_base, - .size = gen9_stolen_size, +static const struct intel_early_ops gen9_early_ops __initconst = { + .stolen_base = gen3_stolen_base, + .stolen_size = gen9_stolen_size, }; -static const struct intel_stolen_funcs chv_stolen_funcs __initconst = { - .base = intel_stolen_base, - .size = chv_stolen_size, +static const struct intel_early_ops chv_early_ops __initconst = { + .stolen_base = gen3_stolen_base, + .stolen_size = chv_stolen_size, }; -static const struct pci_device_id intel_stolen_ids[] __initconst = { - INTEL_I830_IDS(&i830_stolen_funcs), - INTEL_I845G_IDS(&i845_stolen_funcs), - INTEL_I85X_IDS(&i85x_stolen_funcs), - INTEL_I865G_IDS(&i865_stolen_funcs), - INTEL_I915G_IDS(&gen3_stolen_funcs), - INTEL_I915GM_IDS(&gen3_stolen_funcs), - INTEL_I945G_IDS(&gen3_stolen_funcs), - INTEL_I945GM_IDS(&gen3_stolen_funcs), - INTEL_VLV_M_IDS(&gen6_stolen_funcs), - INTEL_VLV_D_IDS(&gen6_stolen_funcs), - INTEL_PINEVIEW_IDS(&gen3_stolen_funcs), - INTEL_I965G_IDS(&gen3_stolen_funcs), - INTEL_G33_IDS(&gen3_stolen_funcs), - INTEL_I965GM_IDS(&gen3_stolen_funcs), - INTEL_GM45_IDS(&gen3_stolen_funcs), - INTEL_G45_IDS(&gen3_stolen_funcs), - INTEL_IRONLAKE_D_IDS(&gen3_stolen_funcs), - INTEL_IRONLAKE_M_IDS(&gen3_stolen_funcs), - INTEL_SNB_D_IDS(&gen6_stolen_funcs), - INTEL_SNB_M_IDS(&gen6_stolen_funcs), - INTEL_IVB_M_IDS(&gen6_stolen_funcs), - INTEL_IVB_D_IDS(&gen6_stolen_funcs), - INTEL_HSW_D_IDS(&gen6_stolen_funcs), - INTEL_HSW_M_IDS(&gen6_stolen_funcs), - INTEL_BDW_M_IDS(&gen8_stolen_funcs), - INTEL_BDW_D_IDS(&gen8_stolen_funcs), - INTEL_CHV_IDS(&chv_stolen_funcs), - INTEL_SKL_IDS(&gen9_stolen_funcs), - INTEL_BXT_IDS(&gen9_stolen_funcs), - INTEL_KBL_IDS(&gen9_stolen_funcs), +static const struct pci_device_id intel_early_ids[] __initconst = { + INTEL_I830_IDS(&i830_early_ops), + INTEL_I845G_IDS(&i845_early_ops), + INTEL_I85X_IDS(&i85x_early_ops), + INTEL_I865G_IDS(&i865_early_ops), + INTEL_I915G_IDS(&gen3_early_ops), + INTEL_I915GM_IDS(&gen3_early_ops), + INTEL_I945G_IDS(&gen3_early_ops), + INTEL_I945GM_IDS(&gen3_early_ops), + INTEL_VLV_M_IDS(&gen6_early_ops), + INTEL_VLV_D_IDS(&gen6_early_ops), + INTEL_PINEVIEW_IDS(&gen3_early_ops), + INTEL_I965G_IDS(&gen3_early_ops), + INTEL_G33_IDS(&gen3_early_ops), + INTEL_I965GM_IDS(&gen3_early_ops), + INTEL_GM45_IDS(&gen3_early_ops), + INTEL_G45_IDS(&gen3_early_ops), + INTEL_IRONLAKE_D_IDS(&gen3_early_ops), + INTEL_IRONLAKE_M_IDS(&gen3_early_ops), + INTEL_SNB_D_IDS(&gen6_early_ops), + INTEL_SNB_M_IDS(&gen6_early_ops), + INTEL_IVB_M_IDS(&gen6_early_ops), + INTEL_IVB_D_IDS(&gen6_early_ops), + INTEL_HSW_D_IDS(&gen6_early_ops), + INTEL_HSW_M_IDS(&gen6_early_ops), + INTEL_BDW_M_IDS(&gen8_early_ops), + INTEL_BDW_D_IDS(&gen8_early_ops), + INTEL_CHV_IDS(&chv_early_ops), + INTEL_SKL_IDS(&gen9_early_ops), + INTEL_BXT_IDS(&gen9_early_ops), + INTEL_KBL_IDS(&gen9_early_ops), }; -static void __init intel_graphics_stolen(int num, int slot, int func) +static void __init +intel_graphics_stolen(int num, int slot, int func, + const struct intel_early_ops *early_ops) { + phys_addr_t base, end; size_t size; + + size = early_ops->stolen_size(num, slot, func); + base = early_ops->stolen_base(num, slot, func, size); + + if (!size || !base) + return; + + end = base + size - 1; + printk(KERN_INFO "Reserving Intel graphics memory at %pa-%pa\n", + &base, &end); + + /* Mark this space as reserved */ + e820_add_region(base, size, E820_RESERVED); + sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); +} + +static void __init intel_graphics_quirks(int num, int slot, int func) +{ + const struct intel_early_ops *early_ops; + u16 device; int i; - u32 start; - u16 device, subvendor, subdevice; device = read_pci_config_16(num, slot, func, PCI_DEVICE_ID); - subvendor = read_pci_config_16(num, slot, func, - PCI_SUBSYSTEM_VENDOR_ID); - subdevice = read_pci_config_16(num, slot, func, PCI_SUBSYSTEM_ID); - - for (i = 0; i < ARRAY_SIZE(intel_stolen_ids); i++) { - if (intel_stolen_ids[i].device == device) { - const struct intel_stolen_funcs *stolen_funcs = - (const struct intel_stolen_funcs *)intel_stolen_ids[i].driver_data; - size = stolen_funcs->size(num, slot, func); - start = stolen_funcs->base(num, slot, func, size); - if (size && start) { - printk(KERN_INFO "Reserving Intel graphics stolen memory at 0x%x-0x%x\n", - start, start + (u32)size - 1); - /* Mark this space as reserved */ - e820_add_region(start, size, E820_RESERVED); - sanitize_e820_map(e820.map, - ARRAY_SIZE(e820.map), - &e820.nr_map); - } - return; - } + + for (i = 0; i < ARRAY_SIZE(intel_early_ids); i++) { + kernel_ulong_t driver_data = intel_early_ids[i].driver_data; + + if (intel_early_ids[i].device != device) + continue; + + early_ops = (typeof(early_ops))driver_data; + + intel_graphics_stolen(num, slot, func, early_ops); + + return; } } @@ -690,7 +674,7 @@ static struct chipset early_qrk[] __initdata = { { PCI_VENDOR_ID_INTEL, 0x3406, PCI_CLASS_BRIDGE_HOST, PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check }, { PCI_VENDOR_ID_INTEL, PCI_ANY_ID, PCI_CLASS_DISPLAY_VGA, PCI_ANY_ID, - QFLAG_APPLY_ONCE, intel_graphics_stolen }, + QFLAG_APPLY_ONCE, intel_graphics_quirks }, /* * HPET on the current version of the Baytrail platform has accuracy * problems: it will halt in deep idle state - so we disable it. diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index 2bcfb5f2bc44..8771766d46b6 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -36,13 +36,14 @@ #include <linux/percpu.h> #include <linux/kdebug.h> #include <linux/kernel.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/sched.h> #include <linux/smp.h> #include <asm/hw_breakpoint.h> #include <asm/processor.h> #include <asm/debugreg.h> +#include <asm/user.h> /* Per cpu debug control register value */ DEFINE_PER_CPU(unsigned long, cpu_dr7); diff --git a/arch/x86/kernel/i386_ksyms_32.c b/arch/x86/kernel/i386_ksyms_32.c index d40ee8a38fed..1f9b878ef5ef 100644 --- a/arch/x86/kernel/i386_ksyms_32.c +++ b/arch/x86/kernel/i386_ksyms_32.c @@ -1,4 +1,5 @@ -#include <linux/module.h> +#include <linux/export.h> +#include <linux/spinlock_types.h> #include <asm/checksum.h> #include <asm/pgtable.h> diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c index efb82f07b29c..6ebe00cb4a3b 100644 --- a/arch/x86/kernel/i8253.c +++ b/arch/x86/kernel/i8253.c @@ -3,7 +3,7 @@ * */ #include <linux/clockchips.h> -#include <linux/module.h> +#include <linux/init.h> #include <linux/timex.h> #include <linux/i8253.h> diff --git a/arch/x86/kernel/io_delay.c b/arch/x86/kernel/io_delay.c index a979b5bd2fc0..50c89e8a95f2 100644 --- a/arch/x86/kernel/io_delay.c +++ b/arch/x86/kernel/io_delay.c @@ -6,7 +6,7 @@ * outb_p/inb_p API uses. */ #include <linux/kernel.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/delay.h> #include <linux/init.h> #include <linux/dmi.h> diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index c627bf8d98ad..1f38d9a4d9de 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -8,7 +8,6 @@ * io_apic.c.) */ -#include <linux/module.h> #include <linux/seq_file.h> #include <linux/interrupt.h> #include <linux/kernel_stat.h> diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index 206d0b90a3ab..4a7903714065 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -11,7 +11,6 @@ #include <linux/kernel_stat.h> #include <linux/interrupt.h> #include <linux/seq_file.h> -#include <linux/module.h> #include <linux/delay.h> #include <linux/ftrace.h> #include <linux/uaccess.h> diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c index dc1404bf8e4b..bdb83e431d89 100644 --- a/arch/x86/kernel/kdebugfs.c +++ b/arch/x86/kernel/kdebugfs.c @@ -8,7 +8,7 @@ */ #include <linux/debugfs.h> #include <linux/uaccess.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/stat.h> diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 1ef5e48b3a36..1726c4c12336 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -21,7 +21,7 @@ */ #include <linux/context_tracking.h> -#include <linux/module.h> +#include <linux/init.h> #include <linux/kernel.h> #include <linux/kvm_para.h> #include <linux/cpu.h> diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 97340f2c437c..068c4a929de6 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -16,7 +16,6 @@ #include <linux/mc146818rtc.h> #include <linux/bitops.h> #include <linux/acpi.h> -#include <linux/module.h> #include <linux/smp.h> #include <linux/pci.h> diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c index 33ee3e0efd65..1939a0269377 100644 --- a/arch/x86/kernel/paravirt-spinlocks.c +++ b/arch/x86/kernel/paravirt-spinlocks.c @@ -3,7 +3,7 @@ * compiled in a FTRACE-compatible way. */ #include <linux/spinlock.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/jump_label.h> #include <asm/paravirt.h> diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 7b3b3f24c3ea..ad5bc9578a73 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -19,7 +19,8 @@ */ #include <linux/errno.h> -#include <linux/module.h> +#include <linux/init.h> +#include <linux/export.h> #include <linux/efi.h> #include <linux/bcd.h> #include <linux/highmem.h> diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c index 7c577a178859..5069ef560d83 100644 --- a/arch/x86/kernel/pci-swiotlb.c +++ b/arch/x86/kernel/pci-swiotlb.c @@ -2,7 +2,7 @@ #include <linux/pci.h> #include <linux/cache.h> -#include <linux/module.h> +#include <linux/init.h> #include <linux/swiotlb.h> #include <linux/bootmem.h> #include <linux/dma-mapping.h> diff --git a/arch/x86/kernel/pmem.c b/arch/x86/kernel/pmem.c index 92f70147a9a6..0c5315d322c8 100644 --- a/arch/x86/kernel/pmem.c +++ b/arch/x86/kernel/pmem.c @@ -3,7 +3,7 @@ * Copyright (c) 2015, Intel Corporation. */ #include <linux/platform_device.h> -#include <linux/module.h> +#include <linux/init.h> #include <linux/ioport.h> static int found(u64 start, u64 end, void *data) diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 96becbbb52e0..62c0b0ea2ce4 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -7,7 +7,8 @@ #include <linux/prctl.h> #include <linux/slab.h> #include <linux/sched.h> -#include <linux/module.h> +#include <linux/init.h> +#include <linux/export.h> #include <linux/pm.h> #include <linux/tick.h> #include <linux/random.h> @@ -404,7 +405,7 @@ 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)) + if (!cpu_has(c, X86_FEATURE_MWAIT) || static_cpu_has_bug(X86_BUG_MONITOR)) return 0; return 1; diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 9f950917528b..d86be29c38c7 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -25,7 +25,7 @@ #include <linux/delay.h> #include <linux/reboot.h> #include <linux/mc146818rtc.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/kallsyms.h> #include <linux/ptrace.h> #include <linux/personality.h> diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 6e789ca1f841..63236d8f84bf 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -26,7 +26,7 @@ #include <linux/user.h> #include <linux/interrupt.h> #include <linux/delay.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/ptrace.h> #include <linux/notifier.h> #include <linux/kprobes.h> diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 15ed70f8278b..63bf27d972b7 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -1,6 +1,6 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <linux/module.h> +#include <linux/export.h> #include <linux/reboot.h> #include <linux/init.h> #include <linux/pm.h> diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 6cb2b02fcc87..991b77986d57 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -36,7 +36,7 @@ #include <linux/console.h> #include <linux/root_dev.h> #include <linux/highmem.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/efi.h> #include <linux/init.h> #include <linux/edd.h> diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index c93609c97406..2a6e84a30a54 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -43,7 +43,7 @@ #include <linux/init.h> #include <linux/smp.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/sched.h> #include <linux/percpu.h> #include <linux/bootmem.h> diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index 9ee98eefc44d..4738f5e0f2ab 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -5,7 +5,7 @@ */ #include <linux/sched.h> #include <linux/stacktrace.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/uaccess.h> #include <asm/stacktrace.h> diff --git a/arch/x86/kernel/test_rodata.c b/arch/x86/kernel/test_rodata.c index cb4a01b41e27..222e84e2432e 100644 --- a/arch/x86/kernel/test_rodata.c +++ b/arch/x86/kernel/test_rodata.c @@ -9,7 +9,6 @@ * as published by the Free Software Foundation; version 2 * of the License. */ -#include <linux/module.h> #include <asm/cacheflush.h> #include <asm/sections.h> #include <asm/asm.h> @@ -74,7 +73,3 @@ int rodata_test(void) return 0; } - -MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("Testcase for marking rodata as read-only"); -MODULE_AUTHOR("Arjan van de Ven <arjan@linux.intel.com>"); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 00f03d82e69a..b70ca12dd389 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -21,7 +21,7 @@ #include <linux/kdebug.h> #include <linux/kgdb.h> #include <linux/kernel.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/ptrace.h> #include <linux/uprobes.h> #include <linux/string.h> diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index a804b5ab32d0..1ef87e887051 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -3,7 +3,7 @@ #include <linux/kernel.h> #include <linux/sched.h> #include <linux/init.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/timer.h> #include <linux/acpi_pmtmr.h> #include <linux/cpufreq.h> diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c index f1aebfb49c36..95e49f6e4fc3 100644 --- a/arch/x86/kernel/x8664_ksyms_64.c +++ b/arch/x86/kernel/x8664_ksyms_64.c @@ -1,7 +1,8 @@ /* Exports for assembly files. All C exports should go in the respective C files. */ -#include <linux/module.h> +#include <linux/export.h> +#include <linux/spinlock_types.h> #include <linux/smp.h> #include <net/checksum.h> diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 58b459296e13..76c5e52436c4 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -5,7 +5,7 @@ */ #include <linux/init.h> #include <linux/ioport.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/pci.h> #include <asm/bios_ebda.h> diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 639a6e34500c..ab8e32f7b9a8 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -32,7 +32,6 @@ config KVM select HAVE_KVM_IRQ_BYPASS select HAVE_KVM_IRQ_ROUTING select HAVE_KVM_EVENTFD - select KVM_APIC_ARCHITECTURE select KVM_ASYNC_PF select USER_RETURN_NOTIFIER select KVM_MMIO diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 643565364497..3235e0fe7792 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -13,7 +13,7 @@ */ #include <linux/kvm_host.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/vmalloc.h> #include <linux/uaccess.h> #include <asm/fpu/internal.h> /* For use_eager_fpu. Ugh! */ diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index a2f24af3c999..4e95d3eb2955 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -22,7 +22,6 @@ #include <linux/kvm_host.h> #include "kvm_cache_regs.h" -#include <linux/module.h> #include <asm/kvm_emulate.h> #include <linux/stringify.h> #include <asm/debugreg.h> diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index a4bf5b45d65a..5fb6c620180e 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -645,7 +645,6 @@ static const struct kvm_io_device_ops speaker_dev_ops = { .write = speaker_ioport_write, }; -/* Caller must hold slots_lock */ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags) { struct kvm_pit *pit; @@ -690,6 +689,7 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags) kvm_pit_set_reinject(pit, true); + mutex_lock(&kvm->slots_lock); kvm_iodevice_init(&pit->dev, &pit_dev_ops); ret = kvm_io_bus_register_dev(kvm, KVM_PIO_BUS, KVM_PIT_BASE_ADDRESS, KVM_PIT_MEM_LENGTH, &pit->dev); @@ -704,12 +704,14 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags) if (ret < 0) goto fail_register_speaker; } + mutex_unlock(&kvm->slots_lock); return pit; fail_register_speaker: kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &pit->dev); fail_register_pit: + mutex_unlock(&kvm->slots_lock); kvm_pit_set_reinject(pit, false); kthread_stop(pit->worker_task); fail_kthread: diff --git a/arch/x86/kvm/iommu.c b/arch/x86/kvm/iommu.c index 3069281904d3..b181426f67b4 100644 --- a/arch/x86/kvm/iommu.c +++ b/arch/x86/kvm/iommu.c @@ -25,12 +25,10 @@ #include <linux/list.h> #include <linux/kvm_host.h> -#include <linux/module.h> +#include <linux/moduleparam.h> #include <linux/pci.h> #include <linux/stat.h> -#include <linux/dmar.h> #include <linux/iommu.h> -#include <linux/intel-iommu.h> #include "assigned-dev.h" static bool allow_unsafe_assigned_interrupts; diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index 95fcc7b13866..60d91c9d160c 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -20,7 +20,7 @@ * */ -#include <linux/module.h> +#include <linux/export.h> #include <linux/kvm_host.h> #include "irq.h" diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index dfb4c6476877..25810b144b58 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -110,13 +110,17 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, return r; } -void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e, +void kvm_set_msi_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, struct kvm_lapic_irq *irq) { - trace_kvm_msi_set_irq(e->msi.address_lo, e->msi.data); + trace_kvm_msi_set_irq(e->msi.address_lo | (kvm->arch.x2apic_format ? + (u64)e->msi.address_hi << 32 : 0), + e->msi.data); irq->dest_id = (e->msi.address_lo & MSI_ADDR_DEST_ID_MASK) >> MSI_ADDR_DEST_ID_SHIFT; + if (kvm->arch.x2apic_format) + irq->dest_id |= MSI_ADDR_EXT_DEST_ID(e->msi.address_hi); irq->vector = (e->msi.data & MSI_DATA_VECTOR_MASK) >> MSI_DATA_VECTOR_SHIFT; irq->dest_mode = (1 << MSI_ADDR_DEST_MODE_SHIFT) & e->msi.address_lo; @@ -129,15 +133,24 @@ void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e, } EXPORT_SYMBOL_GPL(kvm_set_msi_irq); +static inline bool kvm_msi_route_invalid(struct kvm *kvm, + struct kvm_kernel_irq_routing_entry *e) +{ + return kvm->arch.x2apic_format && (e->msi.address_hi & 0xff); +} + int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, bool line_status) { struct kvm_lapic_irq irq; + if (kvm_msi_route_invalid(kvm, e)) + return -EINVAL; + if (!level) return -1; - kvm_set_msi_irq(e, &irq); + kvm_set_msi_irq(kvm, e, &irq); return kvm_irq_delivery_to_apic(kvm, NULL, &irq, NULL); } @@ -153,7 +166,10 @@ int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e, if (unlikely(e->type != KVM_IRQ_ROUTING_MSI)) return -EWOULDBLOCK; - kvm_set_msi_irq(e, &irq); + if (kvm_msi_route_invalid(kvm, e)) + return -EINVAL; + + kvm_set_msi_irq(kvm, e, &irq); if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r, NULL)) return r; @@ -248,7 +264,8 @@ static int kvm_hv_set_sint(struct kvm_kernel_irq_routing_entry *e, return kvm_hv_synic_set_irq(kvm, e->hv_sint.vcpu, e->hv_sint.sint); } -int kvm_set_routing_entry(struct kvm_kernel_irq_routing_entry *e, +int kvm_set_routing_entry(struct kvm *kvm, + struct kvm_kernel_irq_routing_entry *e, const struct kvm_irq_routing_entry *ue) { int r = -EINVAL; @@ -285,6 +302,9 @@ int kvm_set_routing_entry(struct kvm_kernel_irq_routing_entry *e, e->msi.address_lo = ue->u.msi.address_lo; e->msi.address_hi = ue->u.msi.address_hi; e->msi.data = ue->u.msi.data; + + if (kvm_msi_route_invalid(kvm, e)) + goto out; break; case KVM_IRQ_ROUTING_HV_SINT: e->set = kvm_hv_set_sint; @@ -388,21 +408,16 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, kvm->arch.nr_reserved_ioapic_pins); for (i = 0; i < nr_ioapic_pins; ++i) { hlist_for_each_entry(entry, &table->map[i], link) { - u32 dest_id, dest_mode; - bool level; + struct kvm_lapic_irq irq; if (entry->type != KVM_IRQ_ROUTING_MSI) continue; - dest_id = (entry->msi.address_lo >> 12) & 0xff; - dest_mode = (entry->msi.address_lo >> 2) & 0x1; - level = entry->msi.data & MSI_DATA_TRIGGER_LEVEL; - if (level && kvm_apic_match_dest(vcpu, NULL, 0, - dest_id, dest_mode)) { - u32 vector = entry->msi.data & 0xff; - - __set_bit(vector, - ioapic_handled_vectors); - } + + kvm_set_msi_irq(vcpu->kvm, entry, &irq); + + if (irq.level && kvm_apic_match_dest(vcpu, NULL, 0, + irq.dest_id, irq.dest_mode)) + __set_bit(irq.vector, ioapic_handled_vectors); } } srcu_read_unlock(&kvm->irq_srcu, idx); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index a397200281c1..730cf174090a 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -25,7 +25,7 @@ #include <linux/smp.h> #include <linux/hrtimer.h> #include <linux/io.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/math64.h> #include <linux/slab.h> #include <asm/processor.h> @@ -115,26 +115,43 @@ static inline int apic_enabled(struct kvm_lapic *apic) (LVT_MASK | APIC_MODE_MASK | APIC_INPUT_POLARITY | \ APIC_LVT_REMOTE_IRR | APIC_LVT_LEVEL_TRIGGER) -/* The logical map is definitely wrong if we have multiple - * modes at the same time. (Physical map is always right.) - */ -static inline bool kvm_apic_logical_map_valid(struct kvm_apic_map *map) -{ - return !(map->mode & (map->mode - 1)); +static inline bool kvm_apic_map_get_logical_dest(struct kvm_apic_map *map, + u32 dest_id, struct kvm_lapic ***cluster, u16 *mask) { + switch (map->mode) { + case KVM_APIC_MODE_X2APIC: { + u32 offset = (dest_id >> 16) * 16; + u32 max_apic_id = map->max_apic_id; + + if (offset <= max_apic_id) { + u8 cluster_size = min(max_apic_id - offset + 1, 16U); + + *cluster = &map->phys_map[offset]; + *mask = dest_id & (0xffff >> (16 - cluster_size)); + } else { + *mask = 0; + } + + return true; + } + case KVM_APIC_MODE_XAPIC_FLAT: + *cluster = map->xapic_flat_map; + *mask = dest_id & 0xff; + return true; + case KVM_APIC_MODE_XAPIC_CLUSTER: + *cluster = map->xapic_cluster_map[dest_id >> 4]; + *mask = dest_id & 0xf; + return true; + default: + /* Not optimized. */ + return false; + } } -static inline void -apic_logical_id(struct kvm_apic_map *map, u32 dest_id, u16 *cid, u16 *lid) +static void kvm_apic_map_free(struct rcu_head *rcu) { - unsigned lid_bits; - - BUILD_BUG_ON(KVM_APIC_MODE_XAPIC_CLUSTER != 4); - BUILD_BUG_ON(KVM_APIC_MODE_XAPIC_FLAT != 8); - BUILD_BUG_ON(KVM_APIC_MODE_X2APIC != 16); - lid_bits = map->mode; + struct kvm_apic_map *map = container_of(rcu, struct kvm_apic_map, rcu); - *cid = dest_id >> lid_bits; - *lid = dest_id & ((1 << lid_bits) - 1); + kvfree(map); } static void recalculate_apic_map(struct kvm *kvm) @@ -142,17 +159,26 @@ static void recalculate_apic_map(struct kvm *kvm) struct kvm_apic_map *new, *old = NULL; struct kvm_vcpu *vcpu; int i; - - new = kzalloc(sizeof(struct kvm_apic_map), GFP_KERNEL); + u32 max_id = 255; mutex_lock(&kvm->arch.apic_map_lock); + kvm_for_each_vcpu(i, vcpu, kvm) + if (kvm_apic_present(vcpu)) + max_id = max(max_id, kvm_apic_id(vcpu->arch.apic)); + + new = kvm_kvzalloc(sizeof(struct kvm_apic_map) + + sizeof(struct kvm_lapic *) * ((u64)max_id + 1)); + if (!new) goto out; + new->max_apic_id = max_id; + kvm_for_each_vcpu(i, vcpu, kvm) { struct kvm_lapic *apic = vcpu->arch.apic; - u16 cid, lid; + struct kvm_lapic **cluster; + u16 mask; u32 ldr, aid; if (!kvm_apic_present(vcpu)) @@ -161,7 +187,7 @@ static void recalculate_apic_map(struct kvm *kvm) aid = kvm_apic_id(apic); ldr = kvm_lapic_get_reg(apic, APIC_LDR); - if (aid < ARRAY_SIZE(new->phys_map)) + if (aid <= new->max_apic_id) new->phys_map[aid] = apic; if (apic_x2apic_mode(apic)) { @@ -174,13 +200,11 @@ static void recalculate_apic_map(struct kvm *kvm) new->mode |= KVM_APIC_MODE_XAPIC_CLUSTER; } - if (!kvm_apic_logical_map_valid(new)) + if (!kvm_apic_map_get_logical_dest(new, ldr, &cluster, &mask)) continue; - apic_logical_id(new, ldr, &cid, &lid); - - if (lid && cid < ARRAY_SIZE(new->logical_map)) - new->logical_map[cid][ffs(lid) - 1] = apic; + if (mask) + cluster[ffs(mask) - 1] = apic; } out: old = rcu_dereference_protected(kvm->arch.apic_map, @@ -189,7 +213,7 @@ out: mutex_unlock(&kvm->arch.apic_map_lock); if (old) - kfree_rcu(old, rcu); + call_rcu(&old->rcu, kvm_apic_map_free); kvm_make_scan_ioapic_request(kvm); } @@ -210,7 +234,7 @@ static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val) } } -static inline void kvm_apic_set_id(struct kvm_lapic *apic, u8 id) +static inline void kvm_apic_set_xapic_id(struct kvm_lapic *apic, u8 id) { kvm_lapic_set_reg(apic, APIC_ID, id << 24); recalculate_apic_map(apic->vcpu->kvm); @@ -222,11 +246,11 @@ static inline void kvm_apic_set_ldr(struct kvm_lapic *apic, u32 id) recalculate_apic_map(apic->vcpu->kvm); } -static inline void kvm_apic_set_x2apic_id(struct kvm_lapic *apic, u8 id) +static inline void kvm_apic_set_x2apic_id(struct kvm_lapic *apic, u32 id) { u32 ldr = ((id >> 4) << 16) | (1 << (id & 0xf)); - kvm_lapic_set_reg(apic, APIC_ID, id << 24); + kvm_lapic_set_reg(apic, APIC_ID, id); kvm_lapic_set_reg(apic, APIC_LDR, ldr); recalculate_apic_map(apic->vcpu->kvm); } @@ -599,17 +623,30 @@ static bool kvm_apic_match_logical_addr(struct kvm_lapic *apic, u32 mda) } } -/* KVM APIC implementation has two quirks - * - dest always begins at 0 while xAPIC MDA has offset 24, - * - IOxAPIC messages have to be delivered (directly) to x2APIC. +/* The KVM local APIC implementation has two quirks: + * + * - the xAPIC MDA stores the destination at bits 24-31, while this + * is not true of struct kvm_lapic_irq's dest_id field. This is + * just a quirk in the API and is not problematic. + * + * - in-kernel IOAPIC messages have to be delivered directly to + * x2APIC, because the kernel does not support interrupt remapping. + * In order to support broadcast without interrupt remapping, x2APIC + * rewrites the destination of non-IPI messages from APIC_BROADCAST + * to X2APIC_BROADCAST. + * + * The broadcast quirk can be disabled with KVM_CAP_X2APIC_API. This is + * important when userspace wants to use x2APIC-format MSIs, because + * APIC_BROADCAST (0xff) is a legal route for "cluster 0, CPUs 0-7". */ -static u32 kvm_apic_mda(unsigned int dest_id, struct kvm_lapic *source, - struct kvm_lapic *target) +static u32 kvm_apic_mda(struct kvm_vcpu *vcpu, unsigned int dest_id, + struct kvm_lapic *source, struct kvm_lapic *target) { bool ipi = source != NULL; bool x2apic_mda = apic_x2apic_mode(ipi ? source : target); - if (!ipi && dest_id == APIC_BROADCAST && x2apic_mda) + if (!vcpu->kvm->arch.x2apic_broadcast_quirk_disabled && + !ipi && dest_id == APIC_BROADCAST && x2apic_mda) return X2APIC_BROADCAST; return x2apic_mda ? dest_id : SET_APIC_DEST_FIELD(dest_id); @@ -619,7 +656,7 @@ bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, int short_hand, unsigned int dest, int dest_mode) { struct kvm_lapic *target = vcpu->arch.apic; - u32 mda = kvm_apic_mda(dest, source, target); + u32 mda = kvm_apic_mda(vcpu, dest, source, target); apic_debug("target %p, source %p, dest 0x%x, " "dest_mode 0x%x, short_hand 0x%x\n", @@ -671,102 +708,126 @@ static void kvm_apic_disabled_lapic_found(struct kvm *kvm) } } -bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, - struct kvm_lapic_irq *irq, int *r, struct dest_map *dest_map) +static bool kvm_apic_is_broadcast_dest(struct kvm *kvm, struct kvm_lapic **src, + struct kvm_lapic_irq *irq, struct kvm_apic_map *map) { - struct kvm_apic_map *map; - unsigned long bitmap = 1; - struct kvm_lapic **dst; - int i; - bool ret, x2apic_ipi; + if (kvm->arch.x2apic_broadcast_quirk_disabled) { + if ((irq->dest_id == APIC_BROADCAST && + map->mode != KVM_APIC_MODE_X2APIC)) + return true; + if (irq->dest_id == X2APIC_BROADCAST) + return true; + } else { + bool x2apic_ipi = src && *src && apic_x2apic_mode(*src); + if (irq->dest_id == (x2apic_ipi ? + X2APIC_BROADCAST : APIC_BROADCAST)) + return true; + } - *r = -1; + return false; +} - if (irq->shorthand == APIC_DEST_SELF) { - *r = kvm_apic_set_irq(src->vcpu, irq, dest_map); - return true; - } +/* Return true if the interrupt can be handled by using *bitmap as index mask + * for valid destinations in *dst array. + * Return false if kvm_apic_map_get_dest_lapic did nothing useful. + * Note: we may have zero kvm_lapic destinations when we return true, which + * means that the interrupt should be dropped. In this case, *bitmap would be + * zero and *dst undefined. + */ +static inline bool kvm_apic_map_get_dest_lapic(struct kvm *kvm, + struct kvm_lapic **src, struct kvm_lapic_irq *irq, + struct kvm_apic_map *map, struct kvm_lapic ***dst, + unsigned long *bitmap) +{ + int i, lowest; - if (irq->shorthand) + if (irq->shorthand == APIC_DEST_SELF && src) { + *dst = src; + *bitmap = 1; + return true; + } else if (irq->shorthand) return false; - x2apic_ipi = src && apic_x2apic_mode(src); - if (irq->dest_id == (x2apic_ipi ? X2APIC_BROADCAST : APIC_BROADCAST)) + if (!map || kvm_apic_is_broadcast_dest(kvm, src, irq, map)) return false; - ret = true; - rcu_read_lock(); - map = rcu_dereference(kvm->arch.apic_map); - - if (!map) { - ret = false; - goto out; + if (irq->dest_mode == APIC_DEST_PHYSICAL) { + if (irq->dest_id > map->max_apic_id) { + *bitmap = 0; + } else { + *dst = &map->phys_map[irq->dest_id]; + *bitmap = 1; + } + return true; } - if (irq->dest_mode == APIC_DEST_PHYSICAL) { - if (irq->dest_id >= ARRAY_SIZE(map->phys_map)) - goto out; + *bitmap = 0; + if (!kvm_apic_map_get_logical_dest(map, irq->dest_id, dst, + (u16 *)bitmap)) + return false; - dst = &map->phys_map[irq->dest_id]; - } else { - u16 cid; + if (!kvm_lowest_prio_delivery(irq)) + return true; - if (!kvm_apic_logical_map_valid(map)) { - ret = false; - goto out; + if (!kvm_vector_hashing_enabled()) { + lowest = -1; + for_each_set_bit(i, bitmap, 16) { + if (!(*dst)[i]) + continue; + if (lowest < 0) + lowest = i; + else if (kvm_apic_compare_prio((*dst)[i]->vcpu, + (*dst)[lowest]->vcpu) < 0) + lowest = i; } + } else { + if (!*bitmap) + return true; - apic_logical_id(map, irq->dest_id, &cid, (u16 *)&bitmap); + lowest = kvm_vector_to_index(irq->vector, hweight16(*bitmap), + bitmap, 16); - if (cid >= ARRAY_SIZE(map->logical_map)) - goto out; + if (!(*dst)[lowest]) { + kvm_apic_disabled_lapic_found(kvm); + *bitmap = 0; + return true; + } + } - dst = map->logical_map[cid]; + *bitmap = (lowest >= 0) ? 1 << lowest : 0; - if (!kvm_lowest_prio_delivery(irq)) - goto set_irq; + return true; +} - if (!kvm_vector_hashing_enabled()) { - int l = -1; - for_each_set_bit(i, &bitmap, 16) { - if (!dst[i]) - continue; - if (l < 0) - l = i; - else if (kvm_apic_compare_prio(dst[i]->vcpu, - dst[l]->vcpu) < 0) - l = i; - } - bitmap = (l >= 0) ? 1 << l : 0; - } else { - int idx; - unsigned int dest_vcpus; +bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, + struct kvm_lapic_irq *irq, int *r, struct dest_map *dest_map) +{ + struct kvm_apic_map *map; + unsigned long bitmap; + struct kvm_lapic **dst = NULL; + int i; + bool ret; - dest_vcpus = hweight16(bitmap); - if (dest_vcpus == 0) - goto out; + *r = -1; - idx = kvm_vector_to_index(irq->vector, - dest_vcpus, &bitmap, 16); + if (irq->shorthand == APIC_DEST_SELF) { + *r = kvm_apic_set_irq(src->vcpu, irq, dest_map); + return true; + } - if (!dst[idx]) { - kvm_apic_disabled_lapic_found(kvm); - goto out; - } + rcu_read_lock(); + map = rcu_dereference(kvm->arch.apic_map); - bitmap = (idx >= 0) ? 1 << idx : 0; + ret = kvm_apic_map_get_dest_lapic(kvm, &src, irq, map, &dst, &bitmap); + if (ret) + for_each_set_bit(i, &bitmap, 16) { + if (!dst[i]) + continue; + if (*r < 0) + *r = 0; + *r += kvm_apic_set_irq(dst[i]->vcpu, irq, dest_map); } - } -set_irq: - for_each_set_bit(i, &bitmap, 16) { - if (!dst[i]) - continue; - if (*r < 0) - *r = 0; - *r += kvm_apic_set_irq(dst[i]->vcpu, irq, dest_map); - } -out: rcu_read_unlock(); return ret; } @@ -789,8 +850,9 @@ bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq, struct kvm_vcpu **dest_vcpu) { struct kvm_apic_map *map; + unsigned long bitmap; + struct kvm_lapic **dst = NULL; bool ret = false; - struct kvm_lapic *dst = NULL; if (irq->shorthand) return false; @@ -798,69 +860,16 @@ bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq, rcu_read_lock(); map = rcu_dereference(kvm->arch.apic_map); - if (!map) - goto out; - - if (irq->dest_mode == APIC_DEST_PHYSICAL) { - if (irq->dest_id == 0xFF) - goto out; - - if (irq->dest_id >= ARRAY_SIZE(map->phys_map)) - goto out; - - dst = map->phys_map[irq->dest_id]; - if (dst && kvm_apic_present(dst->vcpu)) - *dest_vcpu = dst->vcpu; - else - goto out; - } else { - u16 cid; - unsigned long bitmap = 1; - int i, r = 0; - - if (!kvm_apic_logical_map_valid(map)) - goto out; - - apic_logical_id(map, irq->dest_id, &cid, (u16 *)&bitmap); - - if (cid >= ARRAY_SIZE(map->logical_map)) - goto out; + if (kvm_apic_map_get_dest_lapic(kvm, NULL, irq, map, &dst, &bitmap) && + hweight16(bitmap) == 1) { + unsigned long i = find_first_bit(&bitmap, 16); - if (kvm_vector_hashing_enabled() && - kvm_lowest_prio_delivery(irq)) { - int idx; - unsigned int dest_vcpus; - - dest_vcpus = hweight16(bitmap); - if (dest_vcpus == 0) - goto out; - - idx = kvm_vector_to_index(irq->vector, dest_vcpus, - &bitmap, 16); - - dst = map->logical_map[cid][idx]; - if (!dst) { - kvm_apic_disabled_lapic_found(kvm); - goto out; - } - - *dest_vcpu = dst->vcpu; - } else { - for_each_set_bit(i, &bitmap, 16) { - dst = map->logical_map[cid][i]; - if (++r == 2) - goto out; - } - - if (dst && kvm_apic_present(dst->vcpu)) - *dest_vcpu = dst->vcpu; - else - goto out; + if (dst[i]) { + *dest_vcpu = dst[i]->vcpu; + ret = true; } } - ret = true; -out: rcu_read_unlock(); return ret; } @@ -1127,12 +1136,6 @@ static u32 __apic_read(struct kvm_lapic *apic, unsigned int offset) return 0; switch (offset) { - case APIC_ID: - if (apic_x2apic_mode(apic)) - val = kvm_apic_id(apic); - else - val = kvm_apic_id(apic) << 24; - break; case APIC_ARBPRI: apic_debug("Access APIC ARBPRI register which is for P6\n"); break; @@ -1314,6 +1317,108 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu) nsec_to_cycles(vcpu, lapic_timer_advance_ns))); } +static void start_sw_tscdeadline(struct kvm_lapic *apic) +{ + u64 guest_tsc, tscdeadline = apic->lapic_timer.tscdeadline; + u64 ns = 0; + ktime_t expire; + struct kvm_vcpu *vcpu = apic->vcpu; + unsigned long this_tsc_khz = vcpu->arch.virtual_tsc_khz; + unsigned long flags; + ktime_t now; + + if (unlikely(!tscdeadline || !this_tsc_khz)) + return; + + local_irq_save(flags); + + now = apic->lapic_timer.timer.base->get_time(); + guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc()); + if (likely(tscdeadline > guest_tsc)) { + ns = (tscdeadline - guest_tsc) * 1000000ULL; + do_div(ns, this_tsc_khz); + expire = ktime_add_ns(now, ns); + expire = ktime_sub_ns(expire, lapic_timer_advance_ns); + hrtimer_start(&apic->lapic_timer.timer, + expire, HRTIMER_MODE_ABS_PINNED); + } else + apic_timer_expired(apic); + + local_irq_restore(flags); +} + +bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.apic->lapic_timer.hv_timer_in_use; +} +EXPORT_SYMBOL_GPL(kvm_lapic_hv_timer_in_use); + +static void cancel_hv_tscdeadline(struct kvm_lapic *apic) +{ + kvm_x86_ops->cancel_hv_timer(apic->vcpu); + apic->lapic_timer.hv_timer_in_use = false; +} + +void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + + WARN_ON(!apic->lapic_timer.hv_timer_in_use); + WARN_ON(swait_active(&vcpu->wq)); + cancel_hv_tscdeadline(apic); + apic_timer_expired(apic); +} +EXPORT_SYMBOL_GPL(kvm_lapic_expired_hv_timer); + +static bool start_hv_tscdeadline(struct kvm_lapic *apic) +{ + u64 tscdeadline = apic->lapic_timer.tscdeadline; + + if (atomic_read(&apic->lapic_timer.pending) || + kvm_x86_ops->set_hv_timer(apic->vcpu, tscdeadline)) { + if (apic->lapic_timer.hv_timer_in_use) + cancel_hv_tscdeadline(apic); + } else { + apic->lapic_timer.hv_timer_in_use = true; + hrtimer_cancel(&apic->lapic_timer.timer); + + /* In case the sw timer triggered in the window */ + if (atomic_read(&apic->lapic_timer.pending)) + cancel_hv_tscdeadline(apic); + } + trace_kvm_hv_timer_state(apic->vcpu->vcpu_id, + apic->lapic_timer.hv_timer_in_use); + return apic->lapic_timer.hv_timer_in_use; +} + +void kvm_lapic_switch_to_hv_timer(struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + + WARN_ON(apic->lapic_timer.hv_timer_in_use); + + if (apic_lvtt_tscdeadline(apic)) + start_hv_tscdeadline(apic); +} +EXPORT_SYMBOL_GPL(kvm_lapic_switch_to_hv_timer); + +void kvm_lapic_switch_to_sw_timer(struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + + /* Possibly the TSC deadline timer is not enabled yet */ + if (!apic->lapic_timer.hv_timer_in_use) + return; + + cancel_hv_tscdeadline(apic); + + if (atomic_read(&apic->lapic_timer.pending)) + return; + + start_sw_tscdeadline(apic); +} +EXPORT_SYMBOL_GPL(kvm_lapic_switch_to_sw_timer); + static void start_apic_timer(struct kvm_lapic *apic) { ktime_t now; @@ -1360,32 +1465,8 @@ static void start_apic_timer(struct kvm_lapic *apic) ktime_to_ns(ktime_add_ns(now, apic->lapic_timer.period))); } else if (apic_lvtt_tscdeadline(apic)) { - /* lapic timer in tsc deadline mode */ - u64 guest_tsc, tscdeadline = apic->lapic_timer.tscdeadline; - u64 ns = 0; - ktime_t expire; - struct kvm_vcpu *vcpu = apic->vcpu; - unsigned long this_tsc_khz = vcpu->arch.virtual_tsc_khz; - unsigned long flags; - - if (unlikely(!tscdeadline || !this_tsc_khz)) - return; - - local_irq_save(flags); - - now = apic->lapic_timer.timer.base->get_time(); - guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc()); - if (likely(tscdeadline > guest_tsc)) { - ns = (tscdeadline - guest_tsc) * 1000000ULL; - do_div(ns, this_tsc_khz); - expire = ktime_add_ns(now, ns); - expire = ktime_sub_ns(expire, lapic_timer_advance_ns); - hrtimer_start(&apic->lapic_timer.timer, - expire, HRTIMER_MODE_ABS_PINNED); - } else - apic_timer_expired(apic); - - local_irq_restore(flags); + if (!(kvm_x86_ops->set_hv_timer && start_hv_tscdeadline(apic))) + start_sw_tscdeadline(apic); } } @@ -1413,7 +1494,7 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) switch (reg) { case APIC_ID: /* Local APIC ID */ if (!apic_x2apic_mode(apic)) - kvm_apic_set_id(apic, val >> 24); + kvm_apic_set_xapic_id(apic, val >> 24); else ret = 1; break; @@ -1674,9 +1755,10 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) /* update jump label if enable bit changes */ if ((old_value ^ value) & MSR_IA32_APICBASE_ENABLE) { - if (value & MSR_IA32_APICBASE_ENABLE) + if (value & MSR_IA32_APICBASE_ENABLE) { + kvm_apic_set_xapic_id(apic, vcpu->vcpu_id); static_key_slow_dec_deferred(&apic_hw_disabled); - else + } else static_key_slow_inc(&apic_hw_disabled.key); recalculate_apic_map(vcpu->kvm); } @@ -1716,8 +1798,11 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) /* Stop the timer in case it's a reset to an active apic */ hrtimer_cancel(&apic->lapic_timer.timer); - if (!init_event) - kvm_apic_set_id(apic, vcpu->vcpu_id); + if (!init_event) { + kvm_lapic_set_base(vcpu, APIC_DEFAULT_PHYS_BASE | + MSR_IA32_APICBASE_ENABLE); + kvm_apic_set_xapic_id(apic, vcpu->vcpu_id); + } kvm_apic_set_version(apic->vcpu); for (i = 0; i < KVM_APIC_LVT_NUM; i++) @@ -1856,9 +1941,6 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu) * thinking that APIC satet has changed. */ vcpu->arch.apic_base = MSR_IA32_APICBASE_ENABLE; - kvm_lapic_set_base(vcpu, - APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE); - static_key_slow_inc(&apic_sw_disabled.key); /* sw disabled at reset */ kvm_lapic_reset(vcpu, false); kvm_iodevice_init(&apic->dev, &apic_mmio_ops); @@ -1938,17 +2020,48 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu) return vector; } -void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu, - struct kvm_lapic_state *s) +static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu, + struct kvm_lapic_state *s, bool set) +{ + if (apic_x2apic_mode(vcpu->arch.apic)) { + u32 *id = (u32 *)(s->regs + APIC_ID); + + if (vcpu->kvm->arch.x2apic_format) { + if (*id != vcpu->vcpu_id) + return -EINVAL; + } else { + if (set) + *id >>= 24; + else + *id <<= 24; + } + } + + return 0; +} + +int kvm_apic_get_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) +{ + memcpy(s->regs, vcpu->arch.apic->regs, sizeof(*s)); + return kvm_apic_state_fixup(vcpu, s, false); +} + +int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) { struct kvm_lapic *apic = vcpu->arch.apic; + int r; + kvm_lapic_set_base(vcpu, vcpu->arch.apic_base); /* set SPIV separately to get count of SW disabled APICs right */ apic_set_spiv(apic, *((u32 *)(s->regs + APIC_SPIV))); + + r = kvm_apic_state_fixup(vcpu, s, true); + if (r) + return r; memcpy(vcpu->arch.apic->regs, s->regs, sizeof *s); - /* call kvm_apic_set_id() to put apic into apic_map */ - kvm_apic_set_id(apic, kvm_apic_id(apic)); + + recalculate_apic_map(vcpu->kvm); kvm_apic_set_version(vcpu); apic_update_ppr(apic); @@ -1974,6 +2087,8 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu, kvm_rtc_eoi_tracking_restore_one(vcpu); vcpu->arch.apic_arb_prio = 0; + + return 0; } void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 891c6da7d4aa..f60d01c29d51 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -20,6 +20,7 @@ struct kvm_timer { u64 tscdeadline; u64 expired_tscdeadline; atomic_t pending; /* accumulated triggered timers */ + bool hv_timer_in_use; }; struct kvm_lapic { @@ -80,8 +81,8 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, u64 kvm_get_apic_base(struct kvm_vcpu *vcpu); int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info); -void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu, - struct kvm_lapic_state *s); +int kvm_apic_get_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s); +int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s); int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu); u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu); @@ -199,9 +200,15 @@ static inline int kvm_lapic_latched_init(struct kvm_vcpu *vcpu) return lapic_in_kernel(vcpu) && test_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); } -static inline int kvm_apic_id(struct kvm_lapic *apic) +static inline u32 kvm_apic_id(struct kvm_lapic *apic) { - return (kvm_lapic_get_reg(apic, APIC_ID) >> 24) & 0xff; + /* To avoid a race between apic_base and following APIC_ID update when + * switching to x2apic_mode, the x2apic mode returns initial x2apic id. + */ + if (apic_x2apic_mode(apic)) + return apic->vcpu->vcpu_id; + + return kvm_lapic_get_reg(apic, APIC_ID) >> 24; } bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector); @@ -212,4 +219,8 @@ bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq, struct kvm_vcpu **dest_vcpu); int kvm_vector_to_index(u32 vector, u32 dest_vcpus, const unsigned long *bitmap, u32 bitmap_size); +void kvm_lapic_switch_to_sw_timer(struct kvm_vcpu *vcpu); +void kvm_lapic_switch_to_hv_timer(struct kvm_vcpu *vcpu); +void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu); +bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu); #endif diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index def97b3a392b..3d4cc8cc56a3 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -29,7 +29,8 @@ #include <linux/string.h> #include <linux/mm.h> #include <linux/highmem.h> -#include <linux/module.h> +#include <linux/moduleparam.h> +#include <linux/export.h> #include <linux/swap.h> #include <linux/hugetlb.h> #include <linux/compiler.h> @@ -175,6 +176,7 @@ static u64 __read_mostly shadow_user_mask; static u64 __read_mostly shadow_accessed_mask; static u64 __read_mostly shadow_dirty_mask; static u64 __read_mostly shadow_mmio_mask; +static u64 __read_mostly shadow_present_mask; static void mmu_spte_set(u64 *sptep, u64 spte); static void mmu_free_roots(struct kvm_vcpu *vcpu); @@ -282,13 +284,14 @@ static bool check_mmio_spte(struct kvm_vcpu *vcpu, u64 spte) } void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, - u64 dirty_mask, u64 nx_mask, u64 x_mask) + u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 p_mask) { shadow_user_mask = user_mask; shadow_accessed_mask = accessed_mask; shadow_dirty_mask = dirty_mask; shadow_nx_mask = nx_mask; shadow_x_mask = x_mask; + shadow_present_mask = p_mask; } EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes); @@ -304,7 +307,7 @@ static int is_nx(struct kvm_vcpu *vcpu) static int is_shadow_present_pte(u64 pte) { - return pte & PT_PRESENT_MASK && !is_mmio_spte(pte); + return (pte & 0xFFFFFFFFull) && !is_mmio_spte(pte); } static int is_large_pte(u64 pte) @@ -523,7 +526,7 @@ static void mmu_spte_set(u64 *sptep, u64 new_spte) } /* Rules for using mmu_spte_update: - * Update the state bits, it means the mapped pfn is not changged. + * Update the state bits, it means the mapped pfn is not changed. * * Whenever we overwrite a writable spte with a read-only one we * should flush remote TLBs. Otherwise rmap_write_protect @@ -2245,10 +2248,9 @@ static void link_shadow_page(struct kvm_vcpu *vcpu, u64 *sptep, { u64 spte; - BUILD_BUG_ON(VMX_EPT_READABLE_MASK != PT_PRESENT_MASK || - VMX_EPT_WRITABLE_MASK != PT_WRITABLE_MASK); + BUILD_BUG_ON(VMX_EPT_WRITABLE_MASK != PT_WRITABLE_MASK); - spte = __pa(sp->spt) | PT_PRESENT_MASK | PT_WRITABLE_MASK | + spte = __pa(sp->spt) | shadow_present_mask | PT_WRITABLE_MASK | shadow_user_mask | shadow_x_mask | shadow_accessed_mask; mmu_spte_set(sptep, spte); @@ -2515,13 +2517,19 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, kvm_pfn_t pfn, bool speculative, bool can_unsync, bool host_writable) { - u64 spte; + u64 spte = 0; int ret = 0; if (set_mmio_spte(vcpu, sptep, gfn, pfn, pte_access)) return 0; - spte = PT_PRESENT_MASK; + /* + * For the EPT case, shadow_present_mask is 0 if hardware + * supports exec-only page table entries. In that case, + * ACC_USER_MASK and shadow_user_mask are used to represent + * read access. See FNAME(gpte_access) in paging_tmpl.h. + */ + spte |= shadow_present_mask; if (!speculative) spte |= shadow_accessed_mask; @@ -3189,7 +3197,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) MMU_WARN_ON(VALID_PAGE(root)); if (vcpu->arch.mmu.root_level == PT32E_ROOT_LEVEL) { pdptr = vcpu->arch.mmu.get_pdptr(vcpu, i); - if (!is_present_gpte(pdptr)) { + if (!(pdptr & PT_PRESENT_MASK)) { vcpu->arch.mmu.pae_root[i] = 0; continue; } @@ -3914,9 +3922,7 @@ static void update_permission_bitmask(struct kvm_vcpu *vcpu, * clearer. */ smap = cr4_smap && u && !uf && !ff; - } else - /* Not really needed: no U/S accesses on ept */ - u = 1; + } fault = (ff && !x) || (uf && !u) || (wf && !w) || (smapf && smap); diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 66b33b96a31b..ddc56e91f2e4 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -93,11 +93,6 @@ static inline int kvm_mmu_reload(struct kvm_vcpu *vcpu) return kvm_mmu_load(vcpu); } -static inline int is_present_gpte(unsigned long pte) -{ - return pte & PT_PRESENT_MASK; -} - /* * Currently, we have two sorts of write-protection, a) the first one * write-protects guest page to sync the guest modification, b) another one is diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index bc019f70e0b6..a01105485315 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -131,7 +131,7 @@ static inline void FNAME(protect_clean_gpte)(unsigned *access, unsigned gpte) static inline int FNAME(is_present_gpte)(unsigned long pte) { #if PTTYPE != PTTYPE_EPT - return is_present_gpte(pte); + return pte & PT_PRESENT_MASK; #else return pte & 7; #endif @@ -181,13 +181,19 @@ no_present: return true; } +/* + * For PTTYPE_EPT, a page table can be executable but not readable + * on supported processors. Therefore, set_spte does not automatically + * set bit 0 if execute only is supported. Here, we repurpose ACC_USER_MASK + * to signify readability since it isn't used in the EPT case + */ static inline unsigned FNAME(gpte_access)(struct kvm_vcpu *vcpu, u64 gpte) { unsigned access; #if PTTYPE == PTTYPE_EPT access = ((gpte & VMX_EPT_WRITABLE_MASK) ? ACC_WRITE_MASK : 0) | ((gpte & VMX_EPT_EXECUTABLE_MASK) ? ACC_EXEC_MASK : 0) | - ACC_USER_MASK; + ((gpte & VMX_EPT_READABLE_MASK) ? ACC_USER_MASK : 0); #else BUILD_BUG_ON(ACC_EXEC_MASK != PT_PRESENT_MASK); BUILD_BUG_ON(ACC_EXEC_MASK != 1); diff --git a/arch/x86/kvm/pmu_intel.c b/arch/x86/kvm/pmu_intel.c index ab38af4f4947..9d4a8504a95a 100644 --- a/arch/x86/kvm/pmu_intel.c +++ b/arch/x86/kvm/pmu_intel.c @@ -93,7 +93,7 @@ static unsigned intel_find_fixed_event(int idx) return intel_arch_events[fixed_pmc_events[idx]].event_type; } -/* check if a PMC is enabled by comparising it with globl_ctrl bits. */ +/* check if a PMC is enabled by comparing it with globl_ctrl bits. */ static bool intel_pmc_is_enabled(struct kvm_pmc *pmc) { struct kvm_pmu *pmu = pmc_to_pmu(pmc); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 16ef31b87452..af523d84d102 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1577,7 +1577,7 @@ static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu) static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) { /* - * Any change of EFLAGS.VM is accompained by a reload of SS + * Any change of EFLAGS.VM is accompanied by a reload of SS * (caused by either a task switch or an inter-privilege IRET), * so we do not need to update the CPL here. */ @@ -4940,6 +4940,12 @@ out: static void svm_handle_external_intr(struct kvm_vcpu *vcpu) { local_irq_enable(); + /* + * We must have an instruction with interrupts enabled, so + * the timer interrupt isn't delayed by the interrupt shadow. + */ + asm("nop"); + local_irq_disable(); } static void svm_sched_in(struct kvm_vcpu *vcpu, int cpu) diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 8de925031b5c..0a6cc6754ec5 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -1348,6 +1348,21 @@ TRACE_EVENT(kvm_avic_unaccelerated_access, __entry->vec) ); +TRACE_EVENT(kvm_hv_timer_state, + TP_PROTO(unsigned int vcpu_id, unsigned int hv_timer_in_use), + TP_ARGS(vcpu_id, hv_timer_in_use), + TP_STRUCT__entry( + __field(unsigned int, vcpu_id) + __field(unsigned int, hv_timer_in_use) + ), + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->hv_timer_in_use = hv_timer_in_use; + ), + TP_printk("vcpu_id %x hv_timer %x\n", + __entry->vcpu_id, + __entry->hv_timer_in_use) +); #endif /* _TRACE_KVM_H */ #undef TRACE_INCLUDE_PATH diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index df07a0a4611f..bc354f003ce1 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -110,6 +110,13 @@ module_param_named(pml, enable_pml, bool, S_IRUGO); #define KVM_VMX_TSC_MULTIPLIER_MAX 0xffffffffffffffffULL +/* Guest_tsc -> host_tsc conversion requires 64-bit division. */ +static int __read_mostly cpu_preemption_timer_multi; +static bool __read_mostly enable_preemption_timer = 1; +#ifdef CONFIG_X86_64 +module_param_named(preemption_timer, enable_preemption_timer, bool, S_IRUGO); +#endif + #define KVM_GUEST_CR0_MASK (X86_CR0_NW | X86_CR0_CD) #define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST (X86_CR0_WP | X86_CR0_NE) #define KVM_VM_CR0_ALWAYS_ON \ @@ -398,6 +405,12 @@ struct nested_vmx { /* The host-usable pointer to the above */ struct page *current_vmcs12_page; struct vmcs12 *current_vmcs12; + /* + * Cache of the guest's VMCS, existing outside of guest memory. + * Loaded from guest memory during VMPTRLD. Flushed to guest + * memory during VMXOFF, VMCLEAR, VMPTRLD. + */ + struct vmcs12 *cached_vmcs12; struct vmcs *current_shadow_vmcs; /* * Indicates if the shadow vmcs must be updated with the @@ -421,7 +434,6 @@ struct nested_vmx { struct pi_desc *pi_desc; bool pi_pending; u16 posted_intr_nv; - u64 msr_ia32_feature_control; struct hrtimer preemption_timer; bool preemption_timer_expired; @@ -597,11 +609,22 @@ struct vcpu_vmx { #define PML_ENTITY_NUM 512 struct page *pml_pg; + /* apic deadline value in host tsc */ + u64 hv_deadline_tsc; + u64 current_tsc_ratio; bool guest_pkru_valid; u32 guest_pkru; u32 host_pkru; + + /* + * Only bits masked by msr_ia32_feature_control_valid_bits can be set in + * msr_ia32_feature_control. FEATURE_CONTROL_LOCKED is always included + * in msr_ia32_feature_control_valid_bits. + */ + u64 msr_ia32_feature_control; + u64 msr_ia32_feature_control_valid_bits; }; enum segment_cache_field { @@ -841,7 +864,7 @@ static inline short vmcs_field_to_offset(unsigned long field) static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu) { - return to_vmx(vcpu)->nested.current_vmcs12; + return to_vmx(vcpu)->nested.cached_vmcs12; } static struct page *nested_get_page(struct kvm_vcpu *vcpu, gpa_t addr) @@ -1056,6 +1079,58 @@ static inline bool cpu_has_vmx_virtual_intr_delivery(void) SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY; } +/* + * Comment's format: document - errata name - stepping - processor name. + * Refer from + * https://www.virtualbox.org/svn/vbox/trunk/src/VBox/VMM/VMMR0/HMR0.cpp + */ +static u32 vmx_preemption_cpu_tfms[] = { +/* 323344.pdf - BA86 - D0 - Xeon 7500 Series */ +0x000206E6, +/* 323056.pdf - AAX65 - C2 - Xeon L3406 */ +/* 322814.pdf - AAT59 - C2 - i7-600, i5-500, i5-400 and i3-300 Mobile */ +/* 322911.pdf - AAU65 - C2 - i5-600, i3-500 Desktop and Pentium G6950 */ +0x00020652, +/* 322911.pdf - AAU65 - K0 - i5-600, i3-500 Desktop and Pentium G6950 */ +0x00020655, +/* 322373.pdf - AAO95 - B1 - Xeon 3400 Series */ +/* 322166.pdf - AAN92 - B1 - i7-800 and i5-700 Desktop */ +/* + * 320767.pdf - AAP86 - B1 - + * i7-900 Mobile Extreme, i7-800 and i7-700 Mobile + */ +0x000106E5, +/* 321333.pdf - AAM126 - C0 - Xeon 3500 */ +0x000106A0, +/* 321333.pdf - AAM126 - C1 - Xeon 3500 */ +0x000106A1, +/* 320836.pdf - AAJ124 - C0 - i7-900 Desktop Extreme and i7-900 Desktop */ +0x000106A4, + /* 321333.pdf - AAM126 - D0 - Xeon 3500 */ + /* 321324.pdf - AAK139 - D0 - Xeon 5500 */ + /* 320836.pdf - AAJ124 - D0 - i7-900 Extreme and i7-900 Desktop */ +0x000106A5, +}; + +static inline bool cpu_has_broken_vmx_preemption_timer(void) +{ + u32 eax = cpuid_eax(0x00000001), i; + + /* Clear the reserved bits */ + eax &= ~(0x3U << 14 | 0xfU << 28); + for (i = 0; i < ARRAY_SIZE(vmx_preemption_cpu_tfms); i++) + if (eax == vmx_preemption_cpu_tfms[i]) + return true; + + return false; +} + +static inline bool cpu_has_vmx_preemption_timer(void) +{ + return vmcs_config.pin_based_exec_ctrl & + PIN_BASED_VMX_PREEMPTION_TIMER; +} + static inline bool cpu_has_vmx_posted_intr(void) { return IS_ENABLED(CONFIG_X86_LOCAL_APIC) && @@ -1603,6 +1678,11 @@ static __always_inline void vmcs_set_bits(unsigned long field, u32 mask) __vmcs_writel(field, __vmcs_readl(field) | mask); } +static inline void vm_entry_controls_reset_shadow(struct vcpu_vmx *vmx) +{ + vmx->vm_entry_controls_shadow = vmcs_read32(VM_ENTRY_CONTROLS); +} + static inline void vm_entry_controls_init(struct vcpu_vmx *vmx, u32 val) { vmcs_write32(VM_ENTRY_CONTROLS, val); @@ -1631,6 +1711,11 @@ static inline void vm_entry_controls_clearbit(struct vcpu_vmx *vmx, u32 val) vm_entry_controls_set(vmx, vm_entry_controls_get(vmx) & ~val); } +static inline void vm_exit_controls_reset_shadow(struct vcpu_vmx *vmx) +{ + vmx->vm_exit_controls_shadow = vmcs_read32(VM_EXIT_CONTROLS); +} + static inline void vm_exit_controls_init(struct vcpu_vmx *vmx, u32 val) { vmcs_write32(VM_EXIT_CONTROLS, val); @@ -2121,22 +2206,14 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); u64 phys_addr = __pa(per_cpu(vmxarea, cpu)); + bool already_loaded = vmx->loaded_vmcs->cpu == cpu; if (!vmm_exclusive) kvm_cpu_vmxon(phys_addr); - else if (vmx->loaded_vmcs->cpu != cpu) + else if (!already_loaded) loaded_vmcs_clear(vmx->loaded_vmcs); - if (per_cpu(current_vmcs, cpu) != vmx->loaded_vmcs->vmcs) { - per_cpu(current_vmcs, cpu) = vmx->loaded_vmcs->vmcs; - vmcs_load(vmx->loaded_vmcs->vmcs); - } - - if (vmx->loaded_vmcs->cpu != cpu) { - struct desc_ptr *gdt = this_cpu_ptr(&host_gdt); - unsigned long sysenter_esp; - - kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); + if (!already_loaded) { local_irq_disable(); crash_disable_local_vmclear(cpu); @@ -2151,6 +2228,18 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) &per_cpu(loaded_vmcss_on_cpu, cpu)); crash_enable_local_vmclear(cpu); local_irq_enable(); + } + + if (per_cpu(current_vmcs, cpu) != vmx->loaded_vmcs->vmcs) { + per_cpu(current_vmcs, cpu) = vmx->loaded_vmcs->vmcs; + vmcs_load(vmx->loaded_vmcs->vmcs); + } + + if (!already_loaded) { + struct desc_ptr *gdt = this_cpu_ptr(&host_gdt); + unsigned long sysenter_esp; + + kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); /* * Linux uses per-cpu TSS and GDT, so set these when switching @@ -2716,6 +2805,9 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) vmx->nested.nested_vmx_ept_caps = VMX_EPT_PAGE_WALK_4_BIT | VMX_EPTP_WB_BIT | VMX_EPT_2MB_PAGE_BIT | VMX_EPT_INVEPT_BIT; + if (cpu_has_vmx_ept_execute_only()) + vmx->nested.nested_vmx_ept_caps |= + VMX_EPT_EXECUTE_ONLY_BIT; vmx->nested.nested_vmx_ept_caps &= vmx_capability.ept; /* * For nested guests, we don't do anything specific @@ -2864,6 +2956,14 @@ static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) return 0; } +static inline bool vmx_feature_control_msr_valid(struct kvm_vcpu *vcpu, + uint64_t val) +{ + uint64_t valid_bits = to_vmx(vcpu)->msr_ia32_feature_control_valid_bits; + + return !(val & ~valid_bits); +} + /* * Reads an msr value (of 'msr_index') into 'pdata'. * Returns 0 on success, non-0 otherwise. @@ -2905,10 +3005,15 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; msr_info->data = vmcs_read64(GUEST_BNDCFGS); break; - case MSR_IA32_FEATURE_CONTROL: - if (!nested_vmx_allowed(vcpu)) + case MSR_IA32_MCG_EXT_CTL: + if (!msr_info->host_initiated && + !(to_vmx(vcpu)->msr_ia32_feature_control & + FEATURE_CONTROL_LMCE)) return 1; - msr_info->data = to_vmx(vcpu)->nested.msr_ia32_feature_control; + msr_info->data = vcpu->arch.mcg_ext_ctl; + break; + case MSR_IA32_FEATURE_CONTROL: + msr_info->data = to_vmx(vcpu)->msr_ia32_feature_control; break; case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: if (!nested_vmx_allowed(vcpu)) @@ -2998,12 +3103,20 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_TSC_ADJUST: ret = kvm_set_msr_common(vcpu, msr_info); break; + case MSR_IA32_MCG_EXT_CTL: + if ((!msr_info->host_initiated && + !(to_vmx(vcpu)->msr_ia32_feature_control & + FEATURE_CONTROL_LMCE)) || + (data & ~MCG_EXT_CTL_LMCE_EN)) + return 1; + vcpu->arch.mcg_ext_ctl = data; + break; case MSR_IA32_FEATURE_CONTROL: - if (!nested_vmx_allowed(vcpu) || - (to_vmx(vcpu)->nested.msr_ia32_feature_control & + if (!vmx_feature_control_msr_valid(vcpu, data) || + (to_vmx(vcpu)->msr_ia32_feature_control & FEATURE_CONTROL_LOCKED && !msr_info->host_initiated)) return 1; - vmx->nested.msr_ia32_feature_control = data; + vmx->msr_ia32_feature_control = data; if (msr_info->host_initiated && data == 0) vmx_leave_nested(vcpu); break; @@ -3297,25 +3410,27 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) vmx_capability.ept, vmx_capability.vpid); } - min = VM_EXIT_SAVE_DEBUG_CONTROLS; + min = VM_EXIT_SAVE_DEBUG_CONTROLS | VM_EXIT_ACK_INTR_ON_EXIT; #ifdef CONFIG_X86_64 min |= VM_EXIT_HOST_ADDR_SPACE_SIZE; #endif opt = VM_EXIT_SAVE_IA32_PAT | VM_EXIT_LOAD_IA32_PAT | - VM_EXIT_ACK_INTR_ON_EXIT | VM_EXIT_CLEAR_BNDCFGS; + VM_EXIT_CLEAR_BNDCFGS; if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_EXIT_CTLS, &_vmexit_control) < 0) return -EIO; min = PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING; - opt = PIN_BASED_VIRTUAL_NMIS | PIN_BASED_POSTED_INTR; + opt = PIN_BASED_VIRTUAL_NMIS | PIN_BASED_POSTED_INTR | + PIN_BASED_VMX_PREEMPTION_TIMER; if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PINBASED_CTLS, &_pin_based_exec_control) < 0) return -EIO; + if (cpu_has_broken_vmx_preemption_timer()) + _pin_based_exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER; if (!(_cpu_based_2nd_exec_control & - SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY) || - !(_vmexit_control & VM_EXIT_ACK_INTR_ON_EXIT)) + SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY)) _pin_based_exec_control &= ~PIN_BASED_POSTED_INTR; min = VM_ENTRY_LOAD_DEBUG_CONTROLS; @@ -3364,7 +3479,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) /* * Some cpus support VM_ENTRY_(LOAD|SAVE)_IA32_PERF_GLOBAL_CTRL - * but due to arrata below it can't be used. Workaround is to use + * but due to errata below it can't be used. Workaround is to use * msr load mechanism to switch IA32_PERF_GLOBAL_CTRL. * * VM Exit May Incorrectly Clear IA32_PERF_GLOBAL_CTRL [34:32] @@ -4781,6 +4896,8 @@ static u32 vmx_pin_based_exec_ctrl(struct vcpu_vmx *vmx) if (!kvm_vcpu_apicv_active(&vmx->vcpu)) pin_based_exec_ctrl &= ~PIN_BASED_POSTED_INTR; + /* Enable the preemption timer dynamically */ + pin_based_exec_ctrl &= ~PIN_BASED_VMX_PREEMPTION_TIMER; return pin_based_exec_ctrl; } @@ -4896,6 +5013,7 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) /* Control */ vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, vmx_pin_based_exec_ctrl(vmx)); + vmx->hv_deadline_tsc = -1; vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, vmx_exec_control(vmx)); @@ -6016,12 +6134,14 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); trace_kvm_page_fault(gpa, exit_qualification); - /* It is a write fault? */ - error_code = exit_qualification & PFERR_WRITE_MASK; + /* it is a read fault? */ + error_code = (exit_qualification << 2) & PFERR_USER_MASK; + /* it is a write fault? */ + error_code |= exit_qualification & PFERR_WRITE_MASK; /* It is a fetch fault? */ error_code |= (exit_qualification << 2) & PFERR_FETCH_MASK; /* ept page table is present? */ - error_code |= (exit_qualification >> 3) & PFERR_PRESENT_MASK; + error_code |= (exit_qualification & 0x38) != 0; vcpu->arch.exit_qualification = exit_qualification; @@ -6355,9 +6475,6 @@ static __init int hardware_setup(void) for (msr = 0x800; msr <= 0x8ff; msr++) vmx_disable_intercept_msr_read_x2apic(msr); - /* According SDM, in x2apic mode, the whole id reg is used. But in - * KVM, it only use the highest eight bits. Need to intercept it */ - vmx_enable_intercept_msr_read_x2apic(0x802); /* TMCCT */ vmx_enable_intercept_msr_read_x2apic(0x839); /* TPR */ @@ -6368,10 +6485,12 @@ static __init int hardware_setup(void) vmx_disable_intercept_msr_write_x2apic(0x83f); if (enable_ept) { - kvm_mmu_set_mask_ptes(0ull, + kvm_mmu_set_mask_ptes(VMX_EPT_READABLE_MASK, (enable_ept_ad_bits) ? VMX_EPT_ACCESS_BIT : 0ull, (enable_ept_ad_bits) ? VMX_EPT_DIRTY_BIT : 0ull, - 0ull, VMX_EPT_EXECUTABLE_MASK); + 0ull, VMX_EPT_EXECUTABLE_MASK, + cpu_has_vmx_ept_execute_only() ? + 0ull : VMX_EPT_READABLE_MASK); ept_set_mmio_spte_mask(); kvm_enable_tdp(); } else @@ -6393,8 +6512,21 @@ static __init int hardware_setup(void) kvm_x86_ops->enable_log_dirty_pt_masked = NULL; } + if (cpu_has_vmx_preemption_timer() && enable_preemption_timer) { + u64 vmx_msr; + + rdmsrl(MSR_IA32_VMX_MISC, vmx_msr); + cpu_preemption_timer_multi = + vmx_msr & VMX_MISC_PREEMPTION_TIMER_RATE_MASK; + } else { + kvm_x86_ops->set_hv_timer = NULL; + kvm_x86_ops->cancel_hv_timer = NULL; + } + kvm_set_posted_intr_wakeup_handler(wakeup_handler); + kvm_mce_cap_supported |= MCG_LMCE_P; + return alloc_kvm_area(); out8: @@ -6862,16 +6994,22 @@ static int handle_vmon(struct kvm_vcpu *vcpu) return 1; } - if ((vmx->nested.msr_ia32_feature_control & VMXON_NEEDED_FEATURES) + if ((vmx->msr_ia32_feature_control & VMXON_NEEDED_FEATURES) != VMXON_NEEDED_FEATURES) { kvm_inject_gp(vcpu, 0); return 1; } + vmx->nested.cached_vmcs12 = kmalloc(VMCS12_SIZE, GFP_KERNEL); + if (!vmx->nested.cached_vmcs12) + return -ENOMEM; + if (enable_shadow_vmcs) { shadow_vmcs = alloc_vmcs(); - if (!shadow_vmcs) + if (!shadow_vmcs) { + kfree(vmx->nested.cached_vmcs12); return -ENOMEM; + } /* mark vmcs as shadow */ shadow_vmcs->revision_id |= (1u << 31); /* init shadow vmcs */ @@ -6942,6 +7080,11 @@ static inline void nested_release_vmcs12(struct vcpu_vmx *vmx) vmcs_write64(VMCS_LINK_POINTER, -1ull); } vmx->nested.posted_intr_nv = -1; + + /* Flush VMCS12 to guest memory */ + memcpy(vmx->nested.current_vmcs12, vmx->nested.cached_vmcs12, + VMCS12_SIZE); + kunmap(vmx->nested.current_vmcs12_page); nested_release_page(vmx->nested.current_vmcs12_page); vmx->nested.current_vmptr = -1ull; @@ -6962,6 +7105,7 @@ static void free_nested(struct vcpu_vmx *vmx) nested_release_vmcs12(vmx); if (enable_shadow_vmcs) free_vmcs(vmx->nested.current_shadow_vmcs); + kfree(vmx->nested.cached_vmcs12); /* Unpin physical memory we referred to in current vmcs02 */ if (vmx->nested.apic_access_page) { nested_release_page(vmx->nested.apic_access_page); @@ -7365,6 +7509,13 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) vmx->nested.current_vmptr = vmptr; vmx->nested.current_vmcs12 = new_vmcs12; vmx->nested.current_vmcs12_page = page; + /* + * Load VMCS12 from guest memory since it is not already + * cached. + */ + memcpy(vmx->nested.cached_vmcs12, + vmx->nested.current_vmcs12, VMCS12_SIZE); + if (enable_shadow_vmcs) { vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL, SECONDARY_EXEC_SHADOW_VMCS); @@ -7560,6 +7711,12 @@ static int handle_pml_full(struct kvm_vcpu *vcpu) return 1; } +static int handle_preemption_timer(struct kvm_vcpu *vcpu) +{ + kvm_lapic_expired_hv_timer(vcpu); + return 1; +} + /* * The exit handlers return 1 if the exit was handled fully and guest execution * may resume. Otherwise they set the kvm_run parameter to indicate what needs @@ -7610,6 +7767,7 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_XSAVES] = handle_xsaves, [EXIT_REASON_XRSTORS] = handle_xrstors, [EXIT_REASON_PML_FULL] = handle_pml_full, + [EXIT_REASON_PREEMPTION_TIMER] = handle_preemption_timer, }; static const int kvm_vmx_max_exit_handlers = @@ -7918,6 +8076,8 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) * the XSS exit bitmap in vmcs12. */ return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES); + case EXIT_REASON_PREEMPTION_TIMER: + return false; default: return true; } @@ -8303,7 +8463,7 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa) * the next L2->L1 exit. */ if (!is_guest_mode(vcpu) || - !nested_cpu_has2(vmx->nested.current_vmcs12, + !nested_cpu_has2(get_vmcs12(&vmx->vcpu), SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) vmcs_write64(APIC_ACCESS_ADDR, hpa); } @@ -8436,7 +8596,6 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu) "push %[sp]\n\t" #endif "pushf\n\t" - "orl $0x200, (%%" _ASM_SP ")\n\t" __ASM_SIZE(push) " $%c[cs]\n\t" "call *%[entry]\n\t" : @@ -8449,8 +8608,7 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu) [ss]"i"(__KERNEL_DS), [cs]"i"(__KERNEL_CS) ); - } else - local_irq_enable(); + } } static bool vmx_has_high_real_mode_segbase(void) @@ -8601,6 +8759,26 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx) msrs[i].host); } +void vmx_arm_hv_timer(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + u64 tscl; + u32 delta_tsc; + + if (vmx->hv_deadline_tsc == -1) + return; + + tscl = rdtsc(); + if (vmx->hv_deadline_tsc > tscl) + /* sure to be 32 bit only because checked on set_hv_timer */ + delta_tsc = (u32)((vmx->hv_deadline_tsc - tscl) >> + cpu_preemption_timer_multi); + else + delta_tsc = 0; + + vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, delta_tsc); +} + static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -8650,6 +8828,8 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) atomic_switch_perf_msrs(vmx); debugctlmsr = get_debugctlmsr(); + vmx_arm_hv_timer(vcpu); + vmx->__launched = vmx->loaded_vmcs->launched; asm( /* Store host registers */ @@ -8940,6 +9120,8 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) vmx->nested.current_vmptr = -1ull; vmx->nested.current_vmcs12 = NULL; + vmx->msr_ia32_feature_control_valid_bits = FEATURE_CONTROL_LOCKED; + return &vmx->vcpu; free_vmcs: @@ -9080,6 +9262,13 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) if (cpu_has_secondary_exec_ctrls()) vmcs_set_secondary_exec_control(secondary_exec_ctl); + + if (nested_vmx_allowed(vcpu)) + to_vmx(vcpu)->msr_ia32_feature_control_valid_bits |= + FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX; + else + to_vmx(vcpu)->msr_ia32_feature_control_valid_bits &= + ~FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX; } static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) @@ -9636,9 +9825,14 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmcs_write64(VMCS_LINK_POINTER, -1ull); exec_control = vmcs12->pin_based_vm_exec_control; - exec_control |= vmcs_config.pin_based_exec_ctrl; + + /* Preemption timer setting is only taken from vmcs01. */ exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER; + exec_control |= vmcs_config.pin_based_exec_ctrl; + if (vmx->hv_deadline_tsc == -1) + exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER; + /* Posted interrupts setting is only taken from vmcs12. */ if (nested_cpu_has_posted_intr(vmcs12)) { /* * Note that we use L0's vector here and in @@ -10556,8 +10750,8 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, vmcs12->vm_exit_intr_error_code, KVM_ISA_VMX); - vm_entry_controls_init(vmx, vmcs_read32(VM_ENTRY_CONTROLS)); - vm_exit_controls_init(vmx, vmcs_read32(VM_EXIT_CONTROLS)); + vm_entry_controls_reset_shadow(vmx); + vm_exit_controls_reset_shadow(vmx); vmx_segment_cache_clear(vmx); /* if no vmcs02 cache requested, remove the one we used */ @@ -10566,8 +10760,14 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, load_vmcs12_host_state(vcpu, vmcs12); - /* Update TSC_OFFSET if TSC was changed while L2 ran */ + /* Update any VMCS fields that might have changed while L2 ran */ vmcs_write64(TSC_OFFSET, vmx->nested.vmcs01_tsc_offset); + if (vmx->hv_deadline_tsc == -1) + vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL, + PIN_BASED_VMX_PREEMPTION_TIMER); + else + vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL, + PIN_BASED_VMX_PREEMPTION_TIMER); /* This is needed for same reason as it was needed in prepare_vmcs02 */ vmx->host_rsp = 0; @@ -10647,6 +10847,64 @@ static int vmx_check_intercept(struct kvm_vcpu *vcpu, return X86EMUL_CONTINUE; } +#ifdef CONFIG_X86_64 +/* (a << shift) / divisor, return 1 if overflow otherwise 0 */ +static inline int u64_shl_div_u64(u64 a, unsigned int shift, + u64 divisor, u64 *result) +{ + u64 low = a << shift, high = a >> (64 - shift); + + /* To avoid the overflow on divq */ + if (high >= divisor) + return 1; + + /* Low hold the result, high hold rem which is discarded */ + asm("divq %2\n\t" : "=a" (low), "=d" (high) : + "rm" (divisor), "0" (low), "1" (high)); + *result = low; + + return 0; +} + +static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + u64 tscl = rdtsc(); + u64 guest_tscl = kvm_read_l1_tsc(vcpu, tscl); + u64 delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl; + + /* Convert to host delta tsc if tsc scaling is enabled */ + if (vcpu->arch.tsc_scaling_ratio != kvm_default_tsc_scaling_ratio && + u64_shl_div_u64(delta_tsc, + kvm_tsc_scaling_ratio_frac_bits, + vcpu->arch.tsc_scaling_ratio, + &delta_tsc)) + return -ERANGE; + + /* + * If the delta tsc can't fit in the 32 bit after the multi shift, + * we can't use the preemption timer. + * It's possible that it fits on later vmentries, but checking + * on every vmentry is costly so we just use an hrtimer. + */ + if (delta_tsc >> (cpu_preemption_timer_multi + 32)) + return -ERANGE; + + vmx->hv_deadline_tsc = tscl + delta_tsc; + vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL, + PIN_BASED_VMX_PREEMPTION_TIMER); + return 0; +} + +static void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + vmx->hv_deadline_tsc = -1; + vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL, + PIN_BASED_VMX_PREEMPTION_TIMER); +} +#endif + static void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu) { if (ple_gap) @@ -10691,7 +10949,7 @@ static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm, * this case, return 1, otherwise, return 0. * */ -static int vmx_pre_block(struct kvm_vcpu *vcpu) +static int pi_pre_block(struct kvm_vcpu *vcpu) { unsigned long flags; unsigned int dest; @@ -10758,7 +11016,18 @@ static int vmx_pre_block(struct kvm_vcpu *vcpu) return 0; } -static void vmx_post_block(struct kvm_vcpu *vcpu) +static int vmx_pre_block(struct kvm_vcpu *vcpu) +{ + if (pi_pre_block(vcpu)) + return 1; + + if (kvm_lapic_hv_timer_in_use(vcpu)) + kvm_lapic_switch_to_sw_timer(vcpu); + + return 0; +} + +static void pi_post_block(struct kvm_vcpu *vcpu) { struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); struct pi_desc old, new; @@ -10800,6 +11069,14 @@ static void vmx_post_block(struct kvm_vcpu *vcpu) } } +static void vmx_post_block(struct kvm_vcpu *vcpu) +{ + if (kvm_x86_ops->set_hv_timer) + kvm_lapic_switch_to_hv_timer(vcpu); + + pi_post_block(vcpu); +} + /* * vmx_update_pi_irte - set IRTE for Posted-Interrupts * @@ -10844,7 +11121,7 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq, * We will support full lowest-priority interrupt later. */ - kvm_set_msi_irq(e, &irq); + kvm_set_msi_irq(kvm, e, &irq); if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu)) { /* * Make sure the IRTE is in remapped mode if @@ -10889,6 +11166,16 @@ out: return ret; } +static void vmx_setup_mce(struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.mcg_cap & MCG_LMCE_P) + to_vmx(vcpu)->msr_ia32_feature_control_valid_bits |= + FEATURE_CONTROL_LMCE; + else + to_vmx(vcpu)->msr_ia32_feature_control_valid_bits &= + ~FEATURE_CONTROL_LMCE; +} + static struct kvm_x86_ops vmx_x86_ops = { .cpu_has_kvm_support = cpu_has_kvm_support, .disabled_by_bios = vmx_disabled_by_bios, @@ -11013,6 +11300,13 @@ static struct kvm_x86_ops vmx_x86_ops = { .pmu_ops = &intel_pmu_ops, .update_pi_irte = vmx_update_pi_irte, + +#ifdef CONFIG_X86_64 + .set_hv_timer = vmx_set_hv_timer, + .cancel_hv_timer = vmx_cancel_hv_timer, +#endif + + .setup_mce = vmx_setup_mce, }; static int __init vmx_init(void) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 45608a7da9b3..19f9f9e05c2a 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -36,7 +36,8 @@ #include <linux/kvm.h> #include <linux/fs.h> #include <linux/vmalloc.h> -#include <linux/module.h> +#include <linux/export.h> +#include <linux/moduleparam.h> #include <linux/mman.h> #include <linux/highmem.h> #include <linux/iommu.h> @@ -70,7 +71,8 @@ #define MAX_IO_MSRS 256 #define KVM_MAX_MCE_BANKS 32 -#define KVM_MCE_CAP_SUPPORTED (MCG_CTL_P | MCG_SER_P) +u64 __read_mostly kvm_mce_cap_supported = MCG_CTL_P | MCG_SER_P; +EXPORT_SYMBOL_GPL(kvm_mce_cap_supported); #define emul_to_vcpu(ctxt) \ container_of(ctxt, struct kvm_vcpu, arch.emulate_ctxt) @@ -89,8 +91,12 @@ static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE); #define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM #define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU +#define KVM_X2APIC_API_VALID_FLAGS (KVM_X2APIC_API_USE_32BIT_IDS | \ + KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK) + static void update_cr8_intercept(struct kvm_vcpu *vcpu); static void process_nmi(struct kvm_vcpu *vcpu); +static void enter_smm(struct kvm_vcpu *vcpu); static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); struct kvm_x86_ops *kvm_x86_ops __read_mostly; @@ -113,7 +119,8 @@ u8 __read_mostly kvm_tsc_scaling_ratio_frac_bits; EXPORT_SYMBOL_GPL(kvm_tsc_scaling_ratio_frac_bits); u64 __read_mostly kvm_max_tsc_scaling_ratio; EXPORT_SYMBOL_GPL(kvm_max_tsc_scaling_ratio); -static u64 __read_mostly kvm_default_tsc_scaling_ratio; +u64 __read_mostly kvm_default_tsc_scaling_ratio; +EXPORT_SYMBOL_GPL(kvm_default_tsc_scaling_ratio); /* tsc tolerance in parts per million - default to 1/2 of the NTP threshold */ static u32 __read_mostly tsc_tolerance_ppm = 250; @@ -537,7 +544,7 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3) goto out; } for (i = 0; i < ARRAY_SIZE(pdpte); ++i) { - if (is_present_gpte(pdpte[i]) && + if ((pdpte[i] & PT_PRESENT_MASK) && (pdpte[i] & vcpu->arch.mmu.guest_rsvd_check.rsvd_bits_mask[0][2])) { ret = 0; @@ -982,6 +989,7 @@ static u32 emulated_msrs[] = { MSR_IA32_MISC_ENABLE, MSR_IA32_MCG_STATUS, MSR_IA32_MCG_CTL, + MSR_IA32_MCG_EXT_CTL, MSR_IA32_SMBASE, }; @@ -1161,7 +1169,7 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock) int version; int r; struct pvclock_wall_clock wc; - struct timespec boot; + struct timespec64 boot; if (!wall_clock) return; @@ -1184,13 +1192,13 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock) * wall clock specified here. guest system time equals host * system time for us, thus we must fill in host boot time here. */ - getboottime(&boot); + getboottime64(&boot); if (kvm->arch.kvmclock_offset) { - struct timespec ts = ns_to_timespec(kvm->arch.kvmclock_offset); - boot = timespec_sub(boot, ts); + struct timespec64 ts = ns_to_timespec64(kvm->arch.kvmclock_offset); + boot = timespec64_sub(boot, ts); } - wc.sec = boot.tv_sec; + wc.sec = (u32)boot.tv_sec; /* overflow in 2106 guest time */ wc.nsec = boot.tv_nsec; wc.version = version; @@ -2615,6 +2623,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_TSC_CONTROL: r = kvm_has_tsc_control; break; + case KVM_CAP_X2APIC_API: + r = KVM_X2APIC_API_VALID_FLAGS; + break; default: r = 0; break; @@ -2677,11 +2688,9 @@ long kvm_arch_dev_ioctl(struct file *filp, break; } case KVM_X86_GET_MCE_CAP_SUPPORTED: { - u64 mce_cap; - - mce_cap = KVM_MCE_CAP_SUPPORTED; r = -EFAULT; - if (copy_to_user(argp, &mce_cap, sizeof mce_cap)) + if (copy_to_user(argp, &kvm_mce_cap_supported, + sizeof(kvm_mce_cap_supported))) goto out; r = 0; break; @@ -2733,6 +2742,11 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) rdtsc() - vcpu->arch.last_host_tsc; if (tsc_delta < 0) mark_tsc_unstable("KVM discovered backwards TSC"); + + if (kvm_lapic_hv_timer_in_use(vcpu) && + kvm_x86_ops->set_hv_timer(vcpu, + kvm_get_lapic_tscdeadline_msr(vcpu))) + kvm_lapic_switch_to_sw_timer(vcpu); if (check_tsc_unstable()) { u64 offset = kvm_compute_tsc_offset(vcpu, vcpu->arch.last_guest_tsc); @@ -2766,15 +2780,17 @@ static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu, if (vcpu->arch.apicv_active) kvm_x86_ops->sync_pir_to_irr(vcpu); - memcpy(s->regs, vcpu->arch.apic->regs, sizeof *s); - - return 0; + return kvm_apic_get_state(vcpu, s); } static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) { - kvm_apic_post_state_restore(vcpu, s); + int r; + + r = kvm_apic_set_state(vcpu, s); + if (r) + return r; update_cr8_intercept(vcpu); return 0; @@ -2859,7 +2875,7 @@ static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu, r = -EINVAL; if (!bank_num || bank_num >= KVM_MAX_MCE_BANKS) goto out; - if (mcg_cap & ~(KVM_MCE_CAP_SUPPORTED | 0xff | 0xff0000)) + if (mcg_cap & ~(kvm_mce_cap_supported | 0xff | 0xff0000)) goto out; r = 0; vcpu->arch.mcg_cap = mcg_cap; @@ -2869,6 +2885,9 @@ static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu, /* Init IA32_MCi_CTL to all 1s */ for (bank = 0; bank < bank_num; bank++) vcpu->arch.mce_banks[bank*4] = ~(u64)0; + + if (kvm_x86_ops->setup_mce) + kvm_x86_ops->setup_mce(vcpu); out: return r; } @@ -3767,7 +3786,7 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, r = -EEXIST; if (irqchip_in_kernel(kvm)) goto split_irqchip_unlock; - if (atomic_read(&kvm->online_vcpus)) + if (kvm->created_vcpus) goto split_irqchip_unlock; r = kvm_setup_empty_irq_routing(kvm); if (r) @@ -3781,6 +3800,18 @@ split_irqchip_unlock: mutex_unlock(&kvm->lock); break; } + case KVM_CAP_X2APIC_API: + r = -EINVAL; + if (cap->args[0] & ~KVM_X2APIC_API_VALID_FLAGS) + break; + + if (cap->args[0] & KVM_X2APIC_API_USE_32BIT_IDS) + kvm->arch.x2apic_format = true; + if (cap->args[0] & KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK) + kvm->arch.x2apic_broadcast_quirk_disabled = true; + + r = 0; + break; default: r = -EINVAL; break; @@ -3832,7 +3863,7 @@ long kvm_arch_vm_ioctl(struct file *filp, if (kvm->arch.vpic) goto create_irqchip_unlock; r = -EINVAL; - if (atomic_read(&kvm->online_vcpus)) + if (kvm->created_vcpus) goto create_irqchip_unlock; r = -ENOMEM; vpic = kvm_create_pic(kvm); @@ -3872,7 +3903,7 @@ long kvm_arch_vm_ioctl(struct file *filp, sizeof(struct kvm_pit_config))) goto out; create_pit: - mutex_lock(&kvm->slots_lock); + mutex_lock(&kvm->lock); r = -EEXIST; if (kvm->arch.vpit) goto create_pit_unlock; @@ -3881,7 +3912,7 @@ long kvm_arch_vm_ioctl(struct file *filp, if (kvm->arch.vpit) r = 0; create_pit_unlock: - mutex_unlock(&kvm->slots_lock); + mutex_unlock(&kvm->lock); break; case KVM_GET_IRQCHIP: { /* 0: PIC master, 1: PIC slave, 2: IOAPIC */ @@ -3988,7 +4019,7 @@ long kvm_arch_vm_ioctl(struct file *filp, case KVM_SET_BOOT_CPU_ID: r = 0; mutex_lock(&kvm->lock); - if (atomic_read(&kvm->online_vcpus) != 0) + if (kvm->created_vcpus) r = -EBUSY; else kvm->arch.bsp_vcpu_id = arg; @@ -5296,13 +5327,8 @@ static void kvm_smm_changed(struct kvm_vcpu *vcpu) /* This is a good place to trace that we are exiting SMM. */ trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, false); - if (unlikely(vcpu->arch.smi_pending)) { - kvm_make_request(KVM_REQ_SMI, vcpu); - vcpu->arch.smi_pending = 0; - } else { - /* Process a latched INIT, if any. */ - kvm_make_request(KVM_REQ_EVENT, vcpu); - } + /* Process a latched INIT or SMI, if any. */ + kvm_make_request(KVM_REQ_EVENT, vcpu); } kvm_mmu_reset_context(vcpu); @@ -5848,8 +5874,8 @@ int kvm_arch_init(void *opaque) kvm_x86_ops = ops; kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK, - PT_DIRTY_MASK, PT64_NX_MASK, 0); - + PT_DIRTY_MASK, PT64_NX_MASK, 0, + PT_PRESENT_MASK); kvm_timer_init(); perf_register_guest_info_callbacks(&kvm_guest_cbs); @@ -6083,7 +6109,10 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win) } /* try to inject new event if pending */ - if (vcpu->arch.nmi_pending && kvm_x86_ops->nmi_allowed(vcpu)) { + if (vcpu->arch.smi_pending && !is_smm(vcpu)) { + vcpu->arch.smi_pending = false; + enter_smm(vcpu); + } else if (vcpu->arch.nmi_pending && kvm_x86_ops->nmi_allowed(vcpu)) { --vcpu->arch.nmi_pending; vcpu->arch.nmi_injected = true; kvm_x86_ops->set_nmi(vcpu); @@ -6106,6 +6135,7 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win) kvm_x86_ops->set_irq(vcpu); } } + return 0; } @@ -6129,7 +6159,7 @@ static void process_nmi(struct kvm_vcpu *vcpu) #define put_smstate(type, buf, offset, val) \ *(type *)((buf) + (offset) - 0x7e00) = val -static u32 process_smi_get_segment_flags(struct kvm_segment *seg) +static u32 enter_smm_get_segment_flags(struct kvm_segment *seg) { u32 flags = 0; flags |= seg->g << 23; @@ -6143,7 +6173,7 @@ static u32 process_smi_get_segment_flags(struct kvm_segment *seg) return flags; } -static void process_smi_save_seg_32(struct kvm_vcpu *vcpu, char *buf, int n) +static void enter_smm_save_seg_32(struct kvm_vcpu *vcpu, char *buf, int n) { struct kvm_segment seg; int offset; @@ -6158,11 +6188,11 @@ static void process_smi_save_seg_32(struct kvm_vcpu *vcpu, char *buf, int n) put_smstate(u32, buf, offset + 8, seg.base); put_smstate(u32, buf, offset + 4, seg.limit); - put_smstate(u32, buf, offset, process_smi_get_segment_flags(&seg)); + put_smstate(u32, buf, offset, enter_smm_get_segment_flags(&seg)); } #ifdef CONFIG_X86_64 -static void process_smi_save_seg_64(struct kvm_vcpu *vcpu, char *buf, int n) +static void enter_smm_save_seg_64(struct kvm_vcpu *vcpu, char *buf, int n) { struct kvm_segment seg; int offset; @@ -6171,7 +6201,7 @@ static void process_smi_save_seg_64(struct kvm_vcpu *vcpu, char *buf, int n) kvm_get_segment(vcpu, &seg, n); offset = 0x7e00 + n * 16; - flags = process_smi_get_segment_flags(&seg) >> 8; + flags = enter_smm_get_segment_flags(&seg) >> 8; put_smstate(u16, buf, offset, seg.selector); put_smstate(u16, buf, offset + 2, flags); put_smstate(u32, buf, offset + 4, seg.limit); @@ -6179,7 +6209,7 @@ static void process_smi_save_seg_64(struct kvm_vcpu *vcpu, char *buf, int n) } #endif -static void process_smi_save_state_32(struct kvm_vcpu *vcpu, char *buf) +static void enter_smm_save_state_32(struct kvm_vcpu *vcpu, char *buf) { struct desc_ptr dt; struct kvm_segment seg; @@ -6203,13 +6233,13 @@ static void process_smi_save_state_32(struct kvm_vcpu *vcpu, char *buf) put_smstate(u32, buf, 0x7fc4, seg.selector); put_smstate(u32, buf, 0x7f64, seg.base); put_smstate(u32, buf, 0x7f60, seg.limit); - put_smstate(u32, buf, 0x7f5c, process_smi_get_segment_flags(&seg)); + put_smstate(u32, buf, 0x7f5c, enter_smm_get_segment_flags(&seg)); kvm_get_segment(vcpu, &seg, VCPU_SREG_LDTR); put_smstate(u32, buf, 0x7fc0, seg.selector); put_smstate(u32, buf, 0x7f80, seg.base); put_smstate(u32, buf, 0x7f7c, seg.limit); - put_smstate(u32, buf, 0x7f78, process_smi_get_segment_flags(&seg)); + put_smstate(u32, buf, 0x7f78, enter_smm_get_segment_flags(&seg)); kvm_x86_ops->get_gdt(vcpu, &dt); put_smstate(u32, buf, 0x7f74, dt.address); @@ -6220,7 +6250,7 @@ static void process_smi_save_state_32(struct kvm_vcpu *vcpu, char *buf) put_smstate(u32, buf, 0x7f54, dt.size); for (i = 0; i < 6; i++) - process_smi_save_seg_32(vcpu, buf, i); + enter_smm_save_seg_32(vcpu, buf, i); put_smstate(u32, buf, 0x7f14, kvm_read_cr4(vcpu)); @@ -6229,7 +6259,7 @@ static void process_smi_save_state_32(struct kvm_vcpu *vcpu, char *buf) put_smstate(u32, buf, 0x7ef8, vcpu->arch.smbase); } -static void process_smi_save_state_64(struct kvm_vcpu *vcpu, char *buf) +static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf) { #ifdef CONFIG_X86_64 struct desc_ptr dt; @@ -6261,7 +6291,7 @@ static void process_smi_save_state_64(struct kvm_vcpu *vcpu, char *buf) kvm_get_segment(vcpu, &seg, VCPU_SREG_TR); put_smstate(u16, buf, 0x7e90, seg.selector); - put_smstate(u16, buf, 0x7e92, process_smi_get_segment_flags(&seg) >> 8); + put_smstate(u16, buf, 0x7e92, enter_smm_get_segment_flags(&seg) >> 8); put_smstate(u32, buf, 0x7e94, seg.limit); put_smstate(u64, buf, 0x7e98, seg.base); @@ -6271,7 +6301,7 @@ static void process_smi_save_state_64(struct kvm_vcpu *vcpu, char *buf) kvm_get_segment(vcpu, &seg, VCPU_SREG_LDTR); put_smstate(u16, buf, 0x7e70, seg.selector); - put_smstate(u16, buf, 0x7e72, process_smi_get_segment_flags(&seg) >> 8); + put_smstate(u16, buf, 0x7e72, enter_smm_get_segment_flags(&seg) >> 8); put_smstate(u32, buf, 0x7e74, seg.limit); put_smstate(u64, buf, 0x7e78, seg.base); @@ -6280,31 +6310,26 @@ static void process_smi_save_state_64(struct kvm_vcpu *vcpu, char *buf) put_smstate(u64, buf, 0x7e68, dt.address); for (i = 0; i < 6; i++) - process_smi_save_seg_64(vcpu, buf, i); + enter_smm_save_seg_64(vcpu, buf, i); #else WARN_ON_ONCE(1); #endif } -static void process_smi(struct kvm_vcpu *vcpu) +static void enter_smm(struct kvm_vcpu *vcpu) { struct kvm_segment cs, ds; struct desc_ptr dt; char buf[512]; u32 cr0; - if (is_smm(vcpu)) { - vcpu->arch.smi_pending = true; - return; - } - trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, true); vcpu->arch.hflags |= HF_SMM_MASK; memset(buf, 0, 512); if (guest_cpuid_has_longmode(vcpu)) - process_smi_save_state_64(vcpu, buf); + enter_smm_save_state_64(vcpu, buf); else - process_smi_save_state_32(vcpu, buf); + enter_smm_save_state_32(vcpu, buf); kvm_vcpu_write_guest(vcpu, vcpu->arch.smbase + 0xfe00, buf, sizeof(buf)); @@ -6360,6 +6385,12 @@ static void process_smi(struct kvm_vcpu *vcpu) kvm_mmu_reset_context(vcpu); } +static void process_smi(struct kvm_vcpu *vcpu) +{ + vcpu->arch.smi_pending = true; + kvm_make_request(KVM_REQ_EVENT, vcpu); +} + void kvm_make_scan_ioapic_request(struct kvm *kvm) { kvm_make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC); @@ -6554,8 +6585,18 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (inject_pending_event(vcpu, req_int_win) != 0) req_immediate_exit = true; - /* enable NMI/IRQ window open exits if needed */ else { + /* Enable NMI/IRQ window open exits if needed. + * + * SMIs have two cases: 1) they can be nested, and + * then there is nothing to do here because RSM will + * cause a vmexit anyway; 2) or the SMI can be pending + * because inject_pending_event has completed the + * injection of an IRQ or NMI from the previous vmexit, + * and then we request an immediate exit to inject the SMI. + */ + if (vcpu->arch.smi_pending && !is_smm(vcpu)) + req_immediate_exit = true; if (vcpu->arch.nmi_pending) kvm_x86_ops->enable_nmi_window(vcpu); if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win) @@ -6606,12 +6647,14 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) kvm_load_guest_xcr0(vcpu); - if (req_immediate_exit) + if (req_immediate_exit) { + kvm_make_request(KVM_REQ_EVENT, vcpu); smp_send_reschedule(vcpu->cpu); + } trace_kvm_entry(vcpu->vcpu_id); wait_lapic_expire(vcpu); - __kvm_guest_enter(); + guest_enter_irqoff(); if (unlikely(vcpu->arch.switch_db_regs)) { set_debugreg(0, 7); @@ -6662,16 +6705,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) ++vcpu->stat.exits; - /* - * We must have an instruction between local_irq_enable() and - * kvm_guest_exit(), so the timer interrupt isn't delayed by - * the interrupt shadow. The stat.exits increment will do nicely. - * But we need to prevent reordering, hence this barrier(): - */ - barrier(); - - kvm_guest_exit(); + guest_exit_irqoff(); + local_irq_enable(); preempt_enable(); vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); @@ -7408,6 +7444,7 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) { vcpu->arch.hflags = 0; + vcpu->arch.smi_pending = 0; atomic_set(&vcpu->arch.nmi_queued, 0); vcpu->arch.nmi_pending = 0; vcpu->arch.nmi_injected = false; @@ -7600,11 +7637,6 @@ bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu) return (vcpu->arch.apic_base & MSR_IA32_APICBASE_BSP) != 0; } -bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu) -{ - return irqchip_in_kernel(vcpu->kvm) == lapic_in_kernel(vcpu); -} - struct static_key kvm_no_apic_vcpu __read_mostly; EXPORT_SYMBOL_GPL(kvm_no_apic_vcpu); @@ -7871,7 +7903,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm) kfree(kvm->arch.vpic); kfree(kvm->arch.vioapic); kvm_free_vcpus(kvm); - kfree(rcu_dereference_check(kvm->arch.apic_map, 1)); + kvfree(rcu_dereference_check(kvm->arch.apic_map, 1)); kvm_mmu_uninit_vm(kvm); } @@ -8379,7 +8411,7 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons, /* * When producer of consumer is unregistered, we change back to * remapped mode, so we can re-use the current implementation - * when the irq is masked/disabed or the consumer side (KVM + * when the irq is masked/disabled or the consumer side (KVM * int this case doesn't want to receive the interrupts. */ ret = kvm_x86_ops->update_pi_irte(irqfd->kvm, prod->irq, irqfd->gsi, 0); diff --git a/arch/x86/lib/cache-smp.c b/arch/x86/lib/cache-smp.c index a3c668875038..216a629a4a1a 100644 --- a/arch/x86/lib/cache-smp.c +++ b/arch/x86/lib/cache-smp.c @@ -1,5 +1,5 @@ #include <linux/smp.h> -#include <linux/module.h> +#include <linux/export.h> static void __wbinvd(void *dummy) { diff --git a/arch/x86/lib/cpu.c b/arch/x86/lib/cpu.c index aa417a97511c..d6f848d1211d 100644 --- a/arch/x86/lib/cpu.c +++ b/arch/x86/lib/cpu.c @@ -1,4 +1,5 @@ -#include <linux/module.h> +#include <linux/types.h> +#include <linux/export.h> unsigned int x86_family(unsigned int sig) { diff --git a/arch/x86/lib/csum-partial_64.c b/arch/x86/lib/csum-partial_64.c index 9845371c5c36..9a7fe6a70491 100644 --- a/arch/x86/lib/csum-partial_64.c +++ b/arch/x86/lib/csum-partial_64.c @@ -6,7 +6,7 @@ */ #include <linux/compiler.h> -#include <linux/module.h> +#include <linux/export.h> #include <asm/checksum.h> static inline unsigned short from32to16(unsigned a) diff --git a/arch/x86/lib/csum-wrappers_64.c b/arch/x86/lib/csum-wrappers_64.c index b6fcb9a9ddbc..8bd53589ecfb 100644 --- a/arch/x86/lib/csum-wrappers_64.c +++ b/arch/x86/lib/csum-wrappers_64.c @@ -5,7 +5,7 @@ * Wrappers of assembly checksum functions for x86-64. */ #include <asm/checksum.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/uaccess.h> #include <asm/smap.h> diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c index 2f07c291dcc8..073d1f1a620b 100644 --- a/arch/x86/lib/delay.c +++ b/arch/x86/lib/delay.c @@ -11,7 +11,7 @@ * we have to worry about. */ -#include <linux/module.h> +#include <linux/export.h> #include <linux/sched.h> #include <linux/timex.h> #include <linux/preempt.h> diff --git a/arch/x86/lib/memcpy_32.c b/arch/x86/lib/memcpy_32.c index a404b4b75533..cad12634d6bd 100644 --- a/arch/x86/lib/memcpy_32.c +++ b/arch/x86/lib/memcpy_32.c @@ -1,5 +1,5 @@ #include <linux/string.h> -#include <linux/module.h> +#include <linux/export.h> #undef memcpy #undef memset diff --git a/arch/x86/lib/mmx_32.c b/arch/x86/lib/mmx_32.c index e5e3ed8dc079..c2311a678332 100644 --- a/arch/x86/lib/mmx_32.c +++ b/arch/x86/lib/mmx_32.c @@ -18,7 +18,7 @@ */ #include <linux/hardirq.h> #include <linux/string.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/sched.h> #include <linux/types.h> diff --git a/arch/x86/lib/msr-reg-export.c b/arch/x86/lib/msr-reg-export.c index 8d6ef78b5d01..ff29e8d39414 100644 --- a/arch/x86/lib/msr-reg-export.c +++ b/arch/x86/lib/msr-reg-export.c @@ -1,4 +1,4 @@ -#include <linux/module.h> +#include <linux/export.h> #include <asm/msr.h> EXPORT_SYMBOL(rdmsr_safe_regs); diff --git a/arch/x86/lib/msr-smp.c b/arch/x86/lib/msr-smp.c index 518532e6a3fa..ce68b6a9d7d1 100644 --- a/arch/x86/lib/msr-smp.c +++ b/arch/x86/lib/msr-smp.c @@ -1,4 +1,4 @@ -#include <linux/module.h> +#include <linux/export.h> #include <linux/preempt.h> #include <linux/smp.h> #include <asm/msr.h> diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c index 004c861b1648..d1dee753b949 100644 --- a/arch/x86/lib/msr.c +++ b/arch/x86/lib/msr.c @@ -1,4 +1,5 @@ -#include <linux/module.h> +#include <linux/export.h> +#include <linux/percpu.h> #include <linux/preempt.h> #include <asm/msr.h> #define CREATE_TRACE_POINTS diff --git a/arch/x86/lib/string_32.c b/arch/x86/lib/string_32.c index bd59090825db..dc0ad12f80bb 100644 --- a/arch/x86/lib/string_32.c +++ b/arch/x86/lib/string_32.c @@ -11,7 +11,7 @@ */ #include <linux/string.h> -#include <linux/module.h> +#include <linux/export.h> #ifdef __HAVE_ARCH_STRCPY char *strcpy(char *dest, const char *src) diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c index e342586db6e4..b4908789484e 100644 --- a/arch/x86/lib/usercopy.c +++ b/arch/x86/lib/usercopy.c @@ -5,7 +5,7 @@ */ #include <linux/highmem.h> -#include <linux/module.h> +#include <linux/export.h> #include <asm/word-at-a-time.h> #include <linux/sched.h> diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c index b559d9238781..3bc7baf2a711 100644 --- a/arch/x86/lib/usercopy_32.c +++ b/arch/x86/lib/usercopy_32.c @@ -8,7 +8,7 @@ #include <linux/mm.h> #include <linux/highmem.h> #include <linux/blkdev.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/backing-dev.h> #include <linux/interrupt.h> #include <asm/uaccess.h> diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index 9f760cdcaf40..69873589c0ba 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -5,7 +5,7 @@ * Copyright 1997 Linus Torvalds * Copyright 2002 Andi Kleen <ak@suse.de> */ -#include <linux/module.h> +#include <linux/export.h> #include <linux/uaccess.h> /* diff --git a/arch/x86/mm/amdtopology.c b/arch/x86/mm/amdtopology.c index 2ca15b59fb3f..ba47524f56e8 100644 --- a/arch/x86/mm/amdtopology.c +++ b/arch/x86/mm/amdtopology.c @@ -9,7 +9,6 @@ #include <linux/kernel.h> #include <linux/init.h> #include <linux/string.h> -#include <linux/module.h> #include <linux/nodemask.h> #include <linux/memblock.h> #include <linux/bootmem.h> diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index 9a17250bcbe0..ea9c49adaa1f 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -14,7 +14,7 @@ #include <linux/debugfs.h> #include <linux/mm.h> -#include <linux/module.h> +#include <linux/init.h> #include <linux/seq_file.h> #include <asm/pgtable.h> @@ -454,8 +454,4 @@ static int __init pt_dump_init(void) return 0; } - __initcall(pt_dump_init); -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Arjan van de Ven <arjan@linux.intel.com>"); -MODULE_DESCRIPTION("Kernel debugging helper that dumps pagetables"); diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c index a6d739258137..6d18b70ed5a9 100644 --- a/arch/x86/mm/highmem_32.c +++ b/arch/x86/mm/highmem_32.c @@ -1,5 +1,5 @@ #include <linux/highmem.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/swap.h> /* for totalram_pages */ #include <linux/bootmem.h> diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index cc82830bc8c4..620928903be3 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -208,7 +208,7 @@ static int __meminit save_mr(struct map_range *mr, int nr_range, * adjust the page_size_mask for small range to go with * big page size instead small one if nearby are ram too. */ -static void __init_refok adjust_range_page_size_mask(struct map_range *mr, +static void __ref adjust_range_page_size_mask(struct map_range *mr, int nr_range) { int i; @@ -396,7 +396,7 @@ bool pfn_range_is_mapped(unsigned long start_pfn, unsigned long end_pfn) * This runs before bootmem is initialized and gets pages directly from * the physical memory. To access them they are temporarily mapped. */ -unsigned long __init_refok init_memory_mapping(unsigned long start, +unsigned long __ref init_memory_mapping(unsigned long start, unsigned long end) { struct map_range mr[NR_RANGE_MR]; @@ -700,13 +700,6 @@ void free_initmem(void) void __init free_initrd_mem(unsigned long start, unsigned long end) { /* - * Remember, initrd memory may contain microcode or other useful things. - * Before we lose initrd mem, we need to find a place to hold them - * now that normal virtual memory is enabled. - */ - save_microcode_in_initrd(); - - /* * end could be not aligned, and We can not align that, * decompresser could be confused by aligned initrd_end * We already reserve the end partial page before in diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 84df150ee77e..cf8059016ec8 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -5,7 +5,6 @@ * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999 */ -#include <linux/module.h> #include <linux/signal.h> #include <linux/sched.h> #include <linux/kernel.h> diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 53cc2256cf23..14b9dd71d9e8 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -27,7 +27,6 @@ #include <linux/pfn.h> #include <linux/poison.h> #include <linux/dma-mapping.h> -#include <linux/module.h> #include <linux/memory.h> #include <linux/memory_hotplug.h> #include <linux/memremap.h> diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c index 9c0ff045fdd4..ada98b39b8ad 100644 --- a/arch/x86/mm/iomap_32.c +++ b/arch/x86/mm/iomap_32.c @@ -18,7 +18,7 @@ #include <asm/iomap.h> #include <asm/pat.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/highmem.h> static int is_io_mapping_possible(resource_size_t base, unsigned long size) diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index f0894910bdd7..7aaa2635862d 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -9,7 +9,6 @@ #include <linux/bootmem.h> #include <linux/init.h> #include <linux/io.h> -#include <linux/module.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/mmiotrace.h> diff --git a/arch/x86/mm/kmemcheck/kmemcheck.c b/arch/x86/mm/kmemcheck/kmemcheck.c index b4f2e7e9e907..4515bae36bbe 100644 --- a/arch/x86/mm/kmemcheck/kmemcheck.c +++ b/arch/x86/mm/kmemcheck/kmemcheck.c @@ -14,7 +14,6 @@ #include <linux/kernel.h> #include <linux/kmemcheck.h> #include <linux/mm.h> -#include <linux/module.h> #include <linux/page-flags.h> #include <linux/percpu.h> #include <linux/ptrace.h> diff --git a/arch/x86/mm/kmemcheck/shadow.c b/arch/x86/mm/kmemcheck/shadow.c index aec124214d97..c2638a7d2c10 100644 --- a/arch/x86/mm/kmemcheck/shadow.c +++ b/arch/x86/mm/kmemcheck/shadow.c @@ -1,5 +1,5 @@ #include <linux/kmemcheck.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/mm.h> #include <asm/page.h> diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c index ddb2244b06a1..afc47f5c9531 100644 --- a/arch/x86/mm/kmmio.c +++ b/arch/x86/mm/kmmio.c @@ -11,7 +11,7 @@ #include <linux/rculist.h> #include <linux/spinlock.h> #include <linux/hash.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/kernel.h> #include <linux/uaccess.h> #include <linux/ptrace.h> diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c index 0057a7accfb1..bef36622e408 100644 --- a/arch/x86/mm/mmio-mod.c +++ b/arch/x86/mm/mmio-mod.c @@ -24,7 +24,7 @@ #define DEBUG 1 -#include <linux/module.h> +#include <linux/moduleparam.h> #include <linux/debugfs.h> #include <linux/slab.h> #include <linux/uaccess.h> diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 968ac028c34e..fb682108f4dc 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -8,7 +8,6 @@ #include <linux/memblock.h> #include <linux/mmzone.h> #include <linux/ctype.h> -#include <linux/module.h> #include <linux/nodemask.h> #include <linux/sched.h> #include <linux/topology.h> diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c index 47b6436e41c2..6b7ce6279133 100644 --- a/arch/x86/mm/numa_32.c +++ b/arch/x86/mm/numa_32.c @@ -24,7 +24,7 @@ #include <linux/bootmem.h> #include <linux/memblock.h> -#include <linux/module.h> +#include <linux/init.h> #include "numa_internal.h" diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index db00e3e2f3dc..ecb1b69c1651 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -11,7 +11,6 @@ #include <linux/bootmem.h> #include <linux/debugfs.h> #include <linux/kernel.h> -#include <linux/module.h> #include <linux/pfn_t.h> #include <linux/slab.h> #include <linux/mm.h> diff --git a/arch/x86/mm/pat_rbtree.c b/arch/x86/mm/pat_rbtree.c index 2f7702253ccf..de391b7bc19a 100644 --- a/arch/x86/mm/pat_rbtree.c +++ b/arch/x86/mm/pat_rbtree.c @@ -11,7 +11,6 @@ #include <linux/seq_file.h> #include <linux/debugfs.h> #include <linux/kernel.h> -#include <linux/module.h> #include <linux/rbtree_augmented.h> #include <linux/sched.h> #include <linux/gfp.h> diff --git a/arch/x86/mm/pf_in.c b/arch/x86/mm/pf_in.c index 9f0614daea85..a235869532bc 100644 --- a/arch/x86/mm/pf_in.c +++ b/arch/x86/mm/pf_in.c @@ -26,7 +26,6 @@ * Bjorn Steinbrink (B.Steinbrink@gmx.de), 2007 */ -#include <linux/module.h> #include <linux/ptrace.h> /* struct pt_regs */ #include "pf_in.h" diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c index e67ae0e6c59d..9adce776852b 100644 --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -8,7 +8,6 @@ #include <linux/highmem.h> #include <linux/pagemap.h> #include <linux/spinlock.h> -#include <linux/module.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> diff --git a/arch/x86/mm/physaddr.c b/arch/x86/mm/physaddr.c index e666cbbb9261..cfc3b9121ce4 100644 --- a/arch/x86/mm/physaddr.c +++ b/arch/x86/mm/physaddr.c @@ -1,6 +1,6 @@ #include <linux/bootmem.h> #include <linux/mmdebug.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/mm.h> #include <asm/page.h> diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c index b1ecff460a46..35fe69529bc1 100644 --- a/arch/x86/mm/srat.c +++ b/arch/x86/mm/srat.c @@ -13,7 +13,7 @@ #include <linux/acpi.h> #include <linux/mmzone.h> #include <linux/bitmap.h> -#include <linux/module.h> +#include <linux/init.h> #include <linux/topology.h> #include <linux/mm.h> #include <asm/proto.h> diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 5643fd0b1a7d..4dbe65622810 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -4,7 +4,7 @@ #include <linux/spinlock.h> #include <linux/smp.h> #include <linux/interrupt.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/cpu.h> #include <asm/tlbflush.h> diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 8196054fedb0..7b6a9d14c8c0 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -133,7 +133,7 @@ static void pcibios_fixup_device_resources(struct pci_dev *dev) if (pci_probe & PCI_NOASSIGN_BARS) { /* * If the BIOS did not assign the BAR, zero out the - * resource so the kernel doesn't attmept to assign + * resource so the kernel doesn't attempt to assign * it later on in pci_assign_unassigned_resources */ for (bar = 0; bar <= PCI_STD_RESOURCE_END; bar++) { diff --git a/arch/x86/pci/vmd.c b/arch/x86/pci/vmd.c index 613cac7395c4..e88b4176260f 100644 --- a/arch/x86/pci/vmd.c +++ b/arch/x86/pci/vmd.c @@ -119,10 +119,11 @@ static void vmd_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) static void vmd_irq_enable(struct irq_data *data) { struct vmd_irq *vmdirq = data->chip_data; + unsigned long flags; - raw_spin_lock(&list_lock); + raw_spin_lock_irqsave(&list_lock, flags); list_add_tail_rcu(&vmdirq->node, &vmdirq->irq->irq_list); - raw_spin_unlock(&list_lock); + raw_spin_unlock_irqrestore(&list_lock, flags); data->chip->irq_unmask(data); } @@ -130,12 +131,14 @@ static void vmd_irq_enable(struct irq_data *data) static void vmd_irq_disable(struct irq_data *data) { struct vmd_irq *vmdirq = data->chip_data; + unsigned long flags; data->chip->irq_mask(data); - raw_spin_lock(&list_lock); + raw_spin_lock_irqsave(&list_lock, flags); list_del_rcu(&vmdirq->node); - raw_spin_unlock(&list_lock); + INIT_LIST_HEAD_RCU(&vmdirq->node); + raw_spin_unlock_irqrestore(&list_lock, flags); } /* @@ -166,16 +169,20 @@ static irq_hw_number_t vmd_get_hwirq(struct msi_domain_info *info, * XXX: We can be even smarter selecting the best IRQ once we solve the * affinity problem. */ -static struct vmd_irq_list *vmd_next_irq(struct vmd_dev *vmd) +static struct vmd_irq_list *vmd_next_irq(struct vmd_dev *vmd, struct msi_desc *desc) { - int i, best = 0; + int i, best = 1; + unsigned long flags; - raw_spin_lock(&list_lock); + if (!desc->msi_attrib.is_msix || vmd->msix_count == 1) + return &vmd->irqs[0]; + + raw_spin_lock_irqsave(&list_lock, flags); for (i = 1; i < vmd->msix_count; i++) if (vmd->irqs[i].count < vmd->irqs[best].count) best = i; vmd->irqs[best].count++; - raw_spin_unlock(&list_lock); + raw_spin_unlock_irqrestore(&list_lock, flags); return &vmd->irqs[best]; } @@ -184,14 +191,15 @@ static int vmd_msi_init(struct irq_domain *domain, struct msi_domain_info *info, unsigned int virq, irq_hw_number_t hwirq, msi_alloc_info_t *arg) { - struct vmd_dev *vmd = vmd_from_bus(msi_desc_to_pci_dev(arg->desc)->bus); + struct msi_desc *desc = arg->desc; + struct vmd_dev *vmd = vmd_from_bus(msi_desc_to_pci_dev(desc)->bus); struct vmd_irq *vmdirq = kzalloc(sizeof(*vmdirq), GFP_KERNEL); if (!vmdirq) return -ENOMEM; INIT_LIST_HEAD(&vmdirq->node); - vmdirq->irq = vmd_next_irq(vmd); + vmdirq->irq = vmd_next_irq(vmd, desc); vmdirq->virq = virq; irq_domain_set_info(domain, virq, vmdirq->irq->vmd_vector, info->chip, @@ -203,11 +211,12 @@ static void vmd_msi_free(struct irq_domain *domain, struct msi_domain_info *info, unsigned int virq) { struct vmd_irq *vmdirq = irq_get_chip_data(virq); + unsigned long flags; /* XXX: Potential optimization to rebalance */ - raw_spin_lock(&list_lock); + raw_spin_lock_irqsave(&list_lock, flags); vmdirq->irq->count--; - raw_spin_unlock(&list_lock); + raw_spin_unlock_irqrestore(&list_lock, flags); kfree_rcu(vmdirq, rcu); } @@ -261,7 +270,7 @@ static struct device *to_vmd_dev(struct device *dev) static struct dma_map_ops *vmd_dma_ops(struct device *dev) { - return to_vmd_dev(dev)->archdata.dma_ops; + return get_dma_ops(to_vmd_dev(dev)); } static void *vmd_alloc(struct device *dev, size_t size, dma_addr_t *addr, @@ -367,7 +376,7 @@ static void vmd_teardown_dma_ops(struct vmd_dev *vmd) { struct dma_domain *domain = &vmd->dma_domain; - if (vmd->dev->dev.archdata.dma_ops) + if (get_dma_ops(&vmd->dev->dev)) del_dma_domain(domain); } @@ -379,7 +388,7 @@ static void vmd_teardown_dma_ops(struct vmd_dev *vmd) static void vmd_setup_dma_ops(struct vmd_dev *vmd) { - const struct dma_map_ops *source = vmd->dev->dev.archdata.dma_ops; + const struct dma_map_ops *source = get_dma_ops(&vmd->dev->dev); struct dma_map_ops *dest = &vmd->dma_ops; struct dma_domain *domain = &vmd->dma_domain; @@ -594,7 +603,7 @@ static int vmd_enable_domain(struct vmd_dev *vmd) sd->node = pcibus_to_node(vmd->dev->bus); vmd->irq_domain = pci_msi_create_irq_domain(NULL, &vmd_msi_domain_info, - NULL); + x86_vector_domain); if (!vmd->irq_domain) return -ENODEV; diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 99ddab79215e..3a483cb5ac81 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -9,7 +9,7 @@ * Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> * Stefano Stabellini <stefano.stabellini@eu.citrix.com> */ -#include <linux/module.h> +#include <linux/export.h> #include <linux/init.h> #include <linux/pci.h> #include <linux/acpi.h> diff --git a/arch/x86/platform/ce4100/ce4100.c b/arch/x86/platform/ce4100/ce4100.c index 701fd5843c87..b27bccd4390f 100644 --- a/arch/x86/platform/ce4100/ce4100.c +++ b/arch/x86/platform/ce4100/ce4100.c @@ -11,11 +11,9 @@ #include <linux/init.h> #include <linux/kernel.h> #include <linux/irq.h> -#include <linux/module.h> #include <linux/reboot.h> #include <linux/serial_reg.h> #include <linux/serial_8250.h> -#include <linux/reboot.h> #include <asm/ce4100.h> #include <asm/prom.h> diff --git a/arch/x86/platform/efi/early_printk.c b/arch/x86/platform/efi/early_printk.c index 524142117296..5fdacb322ceb 100644 --- a/arch/x86/platform/efi/early_printk.c +++ b/arch/x86/platform/efi/early_printk.c @@ -44,7 +44,7 @@ early_initcall(early_efi_map_fb); * In case earlyprintk=efi,keep we have the whole framebuffer mapped already * so just return the offset efi_fb + start. */ -static __init_refok void *early_efi_map(unsigned long start, unsigned long len) +static __ref void *early_efi_map(unsigned long start, unsigned long len) { unsigned long base; @@ -56,7 +56,7 @@ static __init_refok void *early_efi_map(unsigned long start, unsigned long len) return early_ioremap(base + start, len); } -static __init_refok void early_efi_unmap(void *addr, unsigned long len) +static __ref void early_efi_unmap(void *addr, unsigned long len) { if (!efi_fb) early_iounmap(addr, len); diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 3e12c44f88a2..04db6fbce96d 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -24,7 +24,7 @@ #include <linux/spinlock.h> #include <linux/bootmem.h> #include <linux/ioport.h> -#include <linux/module.h> +#include <linux/init.h> #include <linux/efi.h> #include <linux/uaccess.h> #include <linux/io.h> diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c index abbf49c6e9d3..ce119d2ba0d0 100644 --- a/arch/x86/platform/intel-mid/intel-mid.c +++ b/arch/x86/platform/intel-mid/intel-mid.c @@ -20,7 +20,7 @@ #include <linux/scatterlist.h> #include <linux/sfi.h> #include <linux/irq.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/notifier.h> #include <asm/setup.h> diff --git a/arch/x86/platform/intel-mid/pwr.c b/arch/x86/platform/intel-mid/pwr.c index 5bc90dd102d4..c901a3423772 100644 --- a/arch/x86/platform/intel-mid/pwr.c +++ b/arch/x86/platform/intel-mid/pwr.c @@ -21,10 +21,9 @@ #include <linux/delay.h> #include <linux/errno.h> -#include <linux/init.h> #include <linux/interrupt.h> #include <linux/kernel.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/mutex.h> #include <linux/pci.h> @@ -407,7 +406,6 @@ static const struct pci_device_id mid_pwr_pci_ids[] = { { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_TANGIER), (kernel_ulong_t)&mid_info }, {} }; -MODULE_DEVICE_TABLE(pci, mid_pwr_pci_ids); static struct pci_driver mid_pwr_pci_driver = { .name = "intel_mid_pwr", diff --git a/arch/x86/platform/intel-mid/sfi.c b/arch/x86/platform/intel-mid/sfi.c index 1555672d436f..051d264fce2e 100644 --- a/arch/x86/platform/intel-mid/sfi.c +++ b/arch/x86/platform/intel-mid/sfi.c @@ -24,7 +24,7 @@ #include <linux/input.h> #include <linux/platform_device.h> #include <linux/irq.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/notifier.h> #include <linux/mmc/core.h> #include <linux/mmc/card.h> diff --git a/arch/x86/platform/olpc/olpc.c b/arch/x86/platform/olpc/olpc.c index 27376081ddec..7c3077e58fa0 100644 --- a/arch/x86/platform/olpc/olpc.c +++ b/arch/x86/platform/olpc/olpc.c @@ -12,7 +12,7 @@ #include <linux/kernel.h> #include <linux/init.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/delay.h> #include <linux/io.h> #include <linux/string.h> diff --git a/arch/x86/platform/olpc/olpc_ofw.c b/arch/x86/platform/olpc/olpc_ofw.c index e7604f62870d..f1aab8cdb33f 100644 --- a/arch/x86/platform/olpc/olpc_ofw.c +++ b/arch/x86/platform/olpc/olpc_ofw.c @@ -1,9 +1,12 @@ #include <linux/kernel.h> -#include <linux/module.h> +#include <linux/export.h> +#include <linux/spinlock_types.h> #include <linux/init.h> #include <asm/page.h> #include <asm/setup.h> #include <asm/io.h> +#include <asm/cpufeature.h> +#include <asm/special_insns.h> #include <asm/pgtable.h> #include <asm/olpc_ofw.h> diff --git a/arch/x86/platform/ts5500/ts5500.c b/arch/x86/platform/ts5500/ts5500.c index baf16e72e668..fd39301f25ac 100644 --- a/arch/x86/platform/ts5500/ts5500.c +++ b/arch/x86/platform/ts5500/ts5500.c @@ -23,7 +23,7 @@ #include <linux/io.h> #include <linux/kernel.h> #include <linux/leds.h> -#include <linux/module.h> +#include <linux/init.h> #include <linux/platform_data/gpio-ts5500.h> #include <linux/platform_data/max197.h> #include <linux/platform_device.h> @@ -345,7 +345,3 @@ error: return err; } device_initcall(ts5500_init); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Savoir-faire Linux Inc. <kernel@savoirfairelinux.com>"); -MODULE_DESCRIPTION("Technologic Systems TS-5500 platform driver"); diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c index e1c24631afbb..776c6592136c 100644 --- a/arch/x86/platform/uv/uv_irq.c +++ b/arch/x86/platform/uv/uv_irq.c @@ -8,7 +8,7 @@ * Copyright (C) 2008 Silicon Graphics, Inc. All rights reserved. */ -#include <linux/module.h> +#include <linux/export.h> #include <linux/rbtree.h> #include <linux/slab.h> #include <linux/irq.h> diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c index 8dd80050d705..cd5173a2733f 100644 --- a/arch/x86/platform/uv/uv_nmi.c +++ b/arch/x86/platform/uv/uv_nmi.c @@ -24,7 +24,7 @@ #include <linux/kdb.h> #include <linux/kexec.h> #include <linux/kgdb.h> -#include <linux/module.h> +#include <linux/moduleparam.h> #include <linux/nmi.h> #include <linux/sched.h> #include <linux/slab.h> diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile index 12734a96df47..ac58c1616408 100644 --- a/arch/x86/purgatory/Makefile +++ b/arch/x86/purgatory/Makefile @@ -8,6 +8,8 @@ PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y)) LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined -nostdlib -z nodefaultlib targets += purgatory.ro +KCOV_INSTRUMENT := n + # Default KBUILD_CFLAGS can have -pg option set when FTRACE is enabled. That # in turn leaves some undefined symbols like __fentry__ in purgatory and not # sure how to relocate those. Like kexec-tools, use custom flags. diff --git a/arch/x86/realmode/rm/Makefile b/arch/x86/realmode/rm/Makefile index c556c5ae8de5..25012abc3409 100644 --- a/arch/x86/realmode/rm/Makefile +++ b/arch/x86/realmode/rm/Makefile @@ -48,7 +48,7 @@ targets += realmode.lds $(obj)/realmode.lds: $(obj)/pasyms.h LDFLAGS_realmode.elf := --emit-relocs -T -CPPFLAGS_realmode.lds += -P -C -I$(obj) +CPPFLAGS_realmode.lds += -P -C -I$(objtree)/$(obj) targets += realmode.elf $(obj)/realmode.elf: $(obj)/realmode.lds $(REALMODE_OBJS) FORCE diff --git a/arch/x86/um/delay.c b/arch/x86/um/delay.c index f3fe1a688f7e..a8fb7ca4822b 100644 --- a/arch/x86/um/delay.c +++ b/arch/x86/um/delay.c @@ -7,7 +7,7 @@ * published by the Free Software Foundation. */ -#include <linux/module.h> +#include <linux/export.h> #include <linux/kernel.h> #include <linux/delay.h> #include <asm/param.h> diff --git a/arch/x86/xen/debugfs.c b/arch/x86/xen/debugfs.c index c8377fb26cdf..1daff5545c0a 100644 --- a/arch/x86/xen/debugfs.c +++ b/arch/x86/xen/debugfs.c @@ -1,7 +1,6 @@ #include <linux/init.h> #include <linux/debugfs.h> #include <linux/slab.h> -#include <linux/module.h> #include "debugfs.h" diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 69b4b6d29738..8ffb089b19a5 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -23,7 +23,7 @@ #include <linux/sched.h> #include <linux/kprobes.h> #include <linux/bootmem.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/mm.h> #include <linux/page-flags.h> #include <linux/highmem.h> @@ -34,9 +34,7 @@ #include <linux/edd.h> #include <linux/frame.h> -#ifdef CONFIG_KEXEC_CORE #include <linux/kexec.h> -#endif #include <xen/xen.h> #include <xen/events.h> @@ -1334,7 +1332,8 @@ static void xen_crash_shutdown(struct pt_regs *regs) static int xen_panic_event(struct notifier_block *this, unsigned long event, void *ptr) { - xen_reboot(SHUTDOWN_crash); + if (!kexec_crash_loaded()) + xen_reboot(SHUTDOWN_crash); return NOTIFY_DONE; } diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 67433714b791..7d5afdb417cc 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -43,7 +43,8 @@ #include <linux/debugfs.h> #include <linux/bug.h> #include <linux/vmalloc.h> -#include <linux/module.h> +#include <linux/export.h> +#include <linux/init.h> #include <linux/gfp.h> #include <linux/memblock.h> #include <linux/seq_file.h> diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index dd2a49a8aacc..37129db76d33 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -60,7 +60,7 @@ */ #include <linux/init.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/list.h> #include <linux/hash.h> #include <linux/sched.h> diff --git a/arch/x86/xen/platform-pci-unplug.c b/arch/x86/xen/platform-pci-unplug.c index 9586ff32810c..d37a0c7f82cb 100644 --- a/arch/x86/xen/platform-pci-unplug.c +++ b/arch/x86/xen/platform-pci-unplug.c @@ -21,7 +21,7 @@ #include <linux/init.h> #include <linux/io.h> -#include <linux/module.h> +#include <linux/export.h> #include <xen/platform_pci.h> #include "xen-ops.h" diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index e345891450c3..176425233e4d 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -4,7 +4,7 @@ * Jeremy Fitzhardinge <jeremy@xensource.com>, XenSource Inc, 2007 */ -#include <linux/module.h> +#include <linux/init.h> #include <linux/sched.h> #include <linux/mm.h> #include <linux/pm.h> |