diff options
Diffstat (limited to 'arch/x86')
-rw-r--r-- | arch/x86/Kconfig | 1 | ||||
-rw-r--r-- | arch/x86/Makefile | 4 | ||||
-rw-r--r-- | arch/x86/events/intel/uncore.h | 33 | ||||
-rw-r--r-- | arch/x86/events/intel/uncore_snb.c | 121 | ||||
-rw-r--r-- | arch/x86/include/asm/kvm_host.h | 3 | ||||
-rw-r--r-- | arch/x86/include/asm/mce.h | 2 | ||||
-rw-r--r-- | arch/x86/include/asm/mshyperv.h | 2 | ||||
-rw-r--r-- | arch/x86/include/asm/page_64_types.h | 12 | ||||
-rw-r--r-- | arch/x86/include/asm/pgtable_64_types.h | 4 | ||||
-rw-r--r-- | arch/x86/include/asm/qspinlock.h | 13 | ||||
-rw-r--r-- | arch/x86/include/asm/xen/page.h | 35 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/mcheck/mce.c | 6 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/mshyperv.c | 11 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/vmware.c | 2 | ||||
-rw-r--r-- | arch/x86/kernel/ldt.c | 59 | ||||
-rw-r--r-- | arch/x86/kernel/vsmp_64.c | 84 | ||||
-rw-r--r-- | arch/x86/kvm/lapic.c | 7 | ||||
-rw-r--r-- | arch/x86/kvm/mmu.c | 27 | ||||
-rw-r--r-- | arch/x86/kvm/svm.c | 44 | ||||
-rw-r--r-- | arch/x86/kvm/vmx.c | 98 | ||||
-rw-r--r-- | arch/x86/kvm/x86.c | 10 | ||||
-rw-r--r-- | arch/x86/xen/mmu_pv.c | 6 | ||||
-rw-r--r-- | arch/x86/xen/p2m.c | 3 | ||||
-rw-r--r-- | arch/x86/xen/spinlock.c | 14 |
24 files changed, 385 insertions, 216 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index ba7e3464ee92..9d734f3c8234 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -525,7 +525,6 @@ config X86_VSMP bool "ScaleMP vSMP" select HYPERVISOR_GUEST select PARAVIRT - select PARAVIRT_XXL depends on X86_64 && PCI depends on X86_EXTENDED_PLATFORM depends on SMP diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 5b562e464009..88398fdf8129 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -213,8 +213,6 @@ ifdef CONFIG_X86_64 KBUILD_LDFLAGS += $(call ld-option, -z max-page-size=0x200000) endif -# Speed up the build -KBUILD_CFLAGS += -pipe # Workaround for a gcc prelease that unfortunately was shipped in a suse release KBUILD_CFLAGS += -Wno-sign-compare # @@ -239,7 +237,7 @@ archheaders: archmacros: $(Q)$(MAKE) $(build)=arch/x86/kernel arch/x86/kernel/macros.s -ASM_MACRO_FLAGS = -Wa,arch/x86/kernel/macros.s -Wa,- +ASM_MACRO_FLAGS = -Wa,arch/x86/kernel/macros.s export ASM_MACRO_FLAGS KBUILD_CFLAGS += $(ASM_MACRO_FLAGS) diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index e17ab885b1e9..cb46d602a6b8 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -129,8 +129,15 @@ struct intel_uncore_box { struct intel_uncore_extra_reg shared_regs[0]; }; -#define UNCORE_BOX_FLAG_INITIATED 0 -#define UNCORE_BOX_FLAG_CTL_OFFS8 1 /* event config registers are 8-byte apart */ +/* CFL uncore 8th cbox MSRs */ +#define CFL_UNC_CBO_7_PERFEVTSEL0 0xf70 +#define CFL_UNC_CBO_7_PER_CTR0 0xf76 + +#define UNCORE_BOX_FLAG_INITIATED 0 +/* event config registers are 8-byte apart */ +#define UNCORE_BOX_FLAG_CTL_OFFS8 1 +/* CFL 8th CBOX has different MSR space */ +#define UNCORE_BOX_FLAG_CFL8_CBOX_MSR_OFFS 2 struct uncore_event_desc { struct kobj_attribute attr; @@ -297,17 +304,27 @@ unsigned int uncore_freerunning_counter(struct intel_uncore_box *box, static inline unsigned uncore_msr_event_ctl(struct intel_uncore_box *box, int idx) { - return box->pmu->type->event_ctl + - (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) + - uncore_msr_box_offset(box); + if (test_bit(UNCORE_BOX_FLAG_CFL8_CBOX_MSR_OFFS, &box->flags)) { + return CFL_UNC_CBO_7_PERFEVTSEL0 + + (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx); + } else { + return box->pmu->type->event_ctl + + (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) + + uncore_msr_box_offset(box); + } } static inline unsigned uncore_msr_perf_ctr(struct intel_uncore_box *box, int idx) { - return box->pmu->type->perf_ctr + - (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) + - uncore_msr_box_offset(box); + if (test_bit(UNCORE_BOX_FLAG_CFL8_CBOX_MSR_OFFS, &box->flags)) { + return CFL_UNC_CBO_7_PER_CTR0 + + (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx); + } else { + return box->pmu->type->perf_ctr + + (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) + + uncore_msr_box_offset(box); + } } static inline diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index 8527c3e1038b..2593b0d7aeee 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -15,6 +15,25 @@ #define PCI_DEVICE_ID_INTEL_SKL_HQ_IMC 0x1910 #define PCI_DEVICE_ID_INTEL_SKL_SD_IMC 0x190f #define PCI_DEVICE_ID_INTEL_SKL_SQ_IMC 0x191f +#define PCI_DEVICE_ID_INTEL_KBL_Y_IMC 0x590c +#define PCI_DEVICE_ID_INTEL_KBL_U_IMC 0x5904 +#define PCI_DEVICE_ID_INTEL_KBL_UQ_IMC 0x5914 +#define PCI_DEVICE_ID_INTEL_KBL_SD_IMC 0x590f +#define PCI_DEVICE_ID_INTEL_KBL_SQ_IMC 0x591f +#define PCI_DEVICE_ID_INTEL_CFL_2U_IMC 0x3ecc +#define PCI_DEVICE_ID_INTEL_CFL_4U_IMC 0x3ed0 +#define PCI_DEVICE_ID_INTEL_CFL_4H_IMC 0x3e10 +#define PCI_DEVICE_ID_INTEL_CFL_6H_IMC 0x3ec4 +#define PCI_DEVICE_ID_INTEL_CFL_2S_D_IMC 0x3e0f +#define PCI_DEVICE_ID_INTEL_CFL_4S_D_IMC 0x3e1f +#define PCI_DEVICE_ID_INTEL_CFL_6S_D_IMC 0x3ec2 +#define PCI_DEVICE_ID_INTEL_CFL_8S_D_IMC 0x3e30 +#define PCI_DEVICE_ID_INTEL_CFL_4S_W_IMC 0x3e18 +#define PCI_DEVICE_ID_INTEL_CFL_6S_W_IMC 0x3ec6 +#define PCI_DEVICE_ID_INTEL_CFL_8S_W_IMC 0x3e31 +#define PCI_DEVICE_ID_INTEL_CFL_4S_S_IMC 0x3e33 +#define PCI_DEVICE_ID_INTEL_CFL_6S_S_IMC 0x3eca +#define PCI_DEVICE_ID_INTEL_CFL_8S_S_IMC 0x3e32 /* SNB event control */ #define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff @@ -202,6 +221,10 @@ static void skl_uncore_msr_init_box(struct intel_uncore_box *box) wrmsrl(SKL_UNC_PERF_GLOBAL_CTL, SNB_UNC_GLOBAL_CTL_EN | SKL_UNC_GLOBAL_CTL_CORE_ALL); } + + /* The 8th CBOX has different MSR space */ + if (box->pmu->pmu_idx == 7) + __set_bit(UNCORE_BOX_FLAG_CFL8_CBOX_MSR_OFFS, &box->flags); } static void skl_uncore_msr_enable_box(struct intel_uncore_box *box) @@ -228,7 +251,7 @@ static struct intel_uncore_ops skl_uncore_msr_ops = { static struct intel_uncore_type skl_uncore_cbox = { .name = "cbox", .num_counters = 4, - .num_boxes = 5, + .num_boxes = 8, .perf_ctr_bits = 44, .fixed_ctr_bits = 48, .perf_ctr = SNB_UNC_CBO_0_PER_CTR0, @@ -569,7 +592,82 @@ static const struct pci_device_id skl_uncore_pci_ids[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_SQ_IMC), .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), }, - + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_Y_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_U_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_UQ_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_SD_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_SQ_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_2U_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4U_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4H_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_6H_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_2S_D_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4S_D_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_6S_D_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_8S_D_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4S_W_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_6S_W_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_8S_W_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4S_S_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_6S_S_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_8S_S_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, { /* end: all zeroes */ }, }; @@ -618,6 +716,25 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = { IMC_DEV(SKL_HQ_IMC, &skl_uncore_pci_driver), /* 6th Gen Core H Quad Core */ IMC_DEV(SKL_SD_IMC, &skl_uncore_pci_driver), /* 6th Gen Core S Dual Core */ IMC_DEV(SKL_SQ_IMC, &skl_uncore_pci_driver), /* 6th Gen Core S Quad Core */ + IMC_DEV(KBL_Y_IMC, &skl_uncore_pci_driver), /* 7th Gen Core Y */ + IMC_DEV(KBL_U_IMC, &skl_uncore_pci_driver), /* 7th Gen Core U */ + IMC_DEV(KBL_UQ_IMC, &skl_uncore_pci_driver), /* 7th Gen Core U Quad Core */ + IMC_DEV(KBL_SD_IMC, &skl_uncore_pci_driver), /* 7th Gen Core S Dual Core */ + IMC_DEV(KBL_SQ_IMC, &skl_uncore_pci_driver), /* 7th Gen Core S Quad Core */ + IMC_DEV(CFL_2U_IMC, &skl_uncore_pci_driver), /* 8th Gen Core U 2 Cores */ + IMC_DEV(CFL_4U_IMC, &skl_uncore_pci_driver), /* 8th Gen Core U 4 Cores */ + IMC_DEV(CFL_4H_IMC, &skl_uncore_pci_driver), /* 8th Gen Core H 4 Cores */ + IMC_DEV(CFL_6H_IMC, &skl_uncore_pci_driver), /* 8th Gen Core H 6 Cores */ + IMC_DEV(CFL_2S_D_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 2 Cores Desktop */ + IMC_DEV(CFL_4S_D_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 4 Cores Desktop */ + IMC_DEV(CFL_6S_D_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 6 Cores Desktop */ + IMC_DEV(CFL_8S_D_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 8 Cores Desktop */ + IMC_DEV(CFL_4S_W_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 4 Cores Work Station */ + IMC_DEV(CFL_6S_W_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 6 Cores Work Station */ + IMC_DEV(CFL_8S_W_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 8 Cores Work Station */ + IMC_DEV(CFL_4S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 4 Cores Server */ + IMC_DEV(CFL_6S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 6 Cores Server */ + IMC_DEV(CFL_8S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 8 Cores Server */ { /* end marker */ } }; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 55e51ff7e421..fbda5a917c5b 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1094,7 +1094,8 @@ struct kvm_x86_ops { bool (*has_wbinvd_exit)(void); u64 (*read_l1_tsc_offset)(struct kvm_vcpu *vcpu); - void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset); + /* Returns actual tsc_offset set in active VMCS */ + u64 (*write_l1_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset); void (*get_exit_info)(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2); diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 4da9b1c58d28..c1a812bd5a27 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -221,6 +221,8 @@ static inline void mce_hygon_feature_init(struct cpuinfo_x86 *c) { return mce_am int mce_available(struct cpuinfo_x86 *c); bool mce_is_memory_error(struct mce *m); +bool mce_is_correctable(struct mce *m); +int mce_usable_address(struct mce *m); DECLARE_PER_CPU(unsigned, mce_exception_count); DECLARE_PER_CPU(unsigned, mce_poll_count); diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 0d6271cce198..1d0a7778e163 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -232,7 +232,7 @@ static inline u64 hv_do_fast_hypercall16(u16 code, u64 input1, u64 input2) : "cc"); } #endif - return hv_status; + return hv_status; } /* diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h index cd0cf1c568b4..8f657286d599 100644 --- a/arch/x86/include/asm/page_64_types.h +++ b/arch/x86/include/asm/page_64_types.h @@ -33,12 +33,14 @@ /* * Set __PAGE_OFFSET to the most negative possible address + - * PGDIR_SIZE*16 (pgd slot 272). The gap is to allow a space for a - * hypervisor to fit. Choosing 16 slots here is arbitrary, but it's - * what Xen requires. + * PGDIR_SIZE*17 (pgd slot 273). + * + * The gap is to allow a space for LDT remap for PTI (1 pgd slot) and space for + * a hypervisor (16 slots). Choosing 16 slots for a hypervisor is arbitrary, + * but it's what Xen requires. */ -#define __PAGE_OFFSET_BASE_L5 _AC(0xff10000000000000, UL) -#define __PAGE_OFFSET_BASE_L4 _AC(0xffff880000000000, UL) +#define __PAGE_OFFSET_BASE_L5 _AC(0xff11000000000000, UL) +#define __PAGE_OFFSET_BASE_L4 _AC(0xffff888000000000, UL) #ifdef CONFIG_DYNAMIC_MEMORY_LAYOUT #define __PAGE_OFFSET page_offset_base diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h index 04edd2d58211..84bd9bdc1987 100644 --- a/arch/x86/include/asm/pgtable_64_types.h +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -111,9 +111,7 @@ extern unsigned int ptrs_per_p4d; */ #define MAXMEM (1UL << MAX_PHYSMEM_BITS) -#define LDT_PGD_ENTRY_L4 -3UL -#define LDT_PGD_ENTRY_L5 -112UL -#define LDT_PGD_ENTRY (pgtable_l5_enabled() ? LDT_PGD_ENTRY_L5 : LDT_PGD_ENTRY_L4) +#define LDT_PGD_ENTRY -240UL #define LDT_BASE_ADDR (LDT_PGD_ENTRY << PGDIR_SHIFT) #define LDT_END_ADDR (LDT_BASE_ADDR + PGDIR_SIZE) diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h index 87623c6b13db..bd5ac6cc37db 100644 --- a/arch/x86/include/asm/qspinlock.h +++ b/arch/x86/include/asm/qspinlock.h @@ -13,12 +13,15 @@ #define queued_fetch_set_pending_acquire queued_fetch_set_pending_acquire static __always_inline u32 queued_fetch_set_pending_acquire(struct qspinlock *lock) { - u32 val = 0; - - if (GEN_BINARY_RMWcc(LOCK_PREFIX "btsl", lock->val.counter, c, - "I", _Q_PENDING_OFFSET)) - val |= _Q_PENDING_VAL; + u32 val; + /* + * We can't use GEN_BINARY_RMWcc() inside an if() stmt because asm goto + * and CONFIG_PROFILE_ALL_BRANCHES=y results in a label inside a + * statement expression, which GCC doesn't like. + */ + val = GEN_BINARY_RMWcc(LOCK_PREFIX "btsl", lock->val.counter, c, + "I", _Q_PENDING_OFFSET) * _Q_PENDING_VAL; val |= atomic_read(&lock->val) & ~_Q_PENDING_MASK; return val; diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 123e669bf363..790ce08e41f2 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -9,7 +9,7 @@ #include <linux/mm.h> #include <linux/device.h> -#include <linux/uaccess.h> +#include <asm/extable.h> #include <asm/page.h> #include <asm/pgtable.h> @@ -93,12 +93,39 @@ clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops, */ static inline int xen_safe_write_ulong(unsigned long *addr, unsigned long val) { - return __put_user(val, (unsigned long __user *)addr); + int ret = 0; + + asm volatile("1: mov %[val], %[ptr]\n" + "2:\n" + ".section .fixup, \"ax\"\n" + "3: sub $1, %[ret]\n" + " jmp 2b\n" + ".previous\n" + _ASM_EXTABLE(1b, 3b) + : [ret] "+r" (ret), [ptr] "=m" (*addr) + : [val] "r" (val)); + + return ret; } -static inline int xen_safe_read_ulong(unsigned long *addr, unsigned long *val) +static inline int xen_safe_read_ulong(const unsigned long *addr, + unsigned long *val) { - return __get_user(*val, (unsigned long __user *)addr); + int ret = 0; + unsigned long rval = ~0ul; + + asm volatile("1: mov %[ptr], %[rval]\n" + "2:\n" + ".section .fixup, \"ax\"\n" + "3: sub $1, %[ret]\n" + " jmp 2b\n" + ".previous\n" + _ASM_EXTABLE(1b, 3b) + : [ret] "+r" (ret), [rval] "+r" (rval) + : [ptr] "m" (*addr)); + *val = rval; + + return ret; } #ifdef CONFIG_XEN_PV diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 8c66d2fc8f81..36d2696c9563 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -485,7 +485,7 @@ static void mce_report_event(struct pt_regs *regs) * be somewhat complicated (e.g. segment offset would require an instruction * parser). So only support physical addresses up to page granuality for now. */ -static int mce_usable_address(struct mce *m) +int mce_usable_address(struct mce *m) { if (!(m->status & MCI_STATUS_ADDRV)) return 0; @@ -505,6 +505,7 @@ static int mce_usable_address(struct mce *m) return 1; } +EXPORT_SYMBOL_GPL(mce_usable_address); bool mce_is_memory_error(struct mce *m) { @@ -534,7 +535,7 @@ bool mce_is_memory_error(struct mce *m) } EXPORT_SYMBOL_GPL(mce_is_memory_error); -static bool mce_is_correctable(struct mce *m) +bool mce_is_correctable(struct mce *m) { if (m->cpuvendor == X86_VENDOR_AMD && m->status & MCI_STATUS_DEFERRED) return false; @@ -547,6 +548,7 @@ static bool mce_is_correctable(struct mce *m) return true; } +EXPORT_SYMBOL_GPL(mce_is_correctable); static bool cec_add_mce(struct mce *m) { diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 1c72f3819eb1..e81a2db42df7 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -20,6 +20,7 @@ #include <linux/interrupt.h> #include <linux/irq.h> #include <linux/kexec.h> +#include <linux/i8253.h> #include <asm/processor.h> #include <asm/hypervisor.h> #include <asm/hyperv-tlfs.h> @@ -295,6 +296,16 @@ static void __init ms_hyperv_init_platform(void) if (efi_enabled(EFI_BOOT)) x86_platform.get_nmi_reason = hv_get_nmi_reason; + /* + * Hyper-V VMs have a PIT emulation quirk such that zeroing the + * counter register during PIT shutdown restarts the PIT. So it + * continues to interrupt @18.2 HZ. Setting i8253_clear_counter + * to false tells pit_shutdown() not to zero the counter so that + * the PIT really is shutdown. Generation 2 VMs don't have a PIT, + * and setting this value has no effect. + */ + i8253_clear_counter_on_shutdown = false; + #if IS_ENABLED(CONFIG_HYPERV) /* * Setup the hook to get control post apic initialization. diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index d9ab49bed8af..0eda91f8eeac 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -77,7 +77,7 @@ static __init int setup_vmw_sched_clock(char *s) } early_param("no-vmw-sched-clock", setup_vmw_sched_clock); -static unsigned long long vmware_sched_clock(void) +static unsigned long long notrace vmware_sched_clock(void) { unsigned long long ns; diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index ab18e0884dc6..6135ae8ce036 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -199,14 +199,6 @@ static void sanity_check_ldt_mapping(struct mm_struct *mm) /* * If PTI is enabled, this maps the LDT into the kernelmode and * usermode tables for the given mm. - * - * There is no corresponding unmap function. Even if the LDT is freed, we - * leave the PTEs around until the slot is reused or the mm is destroyed. - * This is harmless: the LDT is always in ordinary memory, and no one will - * access the freed slot. - * - * If we wanted to unmap freed LDTs, we'd also need to do a flush to make - * it useful, and the flush would slow down modify_ldt(). */ static int map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) @@ -214,8 +206,7 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) unsigned long va; bool is_vmalloc; spinlock_t *ptl; - pgd_t *pgd; - int i; + int i, nr_pages; if (!static_cpu_has(X86_FEATURE_PTI)) return 0; @@ -229,16 +220,11 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) /* Check if the current mappings are sane */ sanity_check_ldt_mapping(mm); - /* - * Did we already have the top level entry allocated? We can't - * use pgd_none() for this because it doens't do anything on - * 4-level page table kernels. - */ - pgd = pgd_offset(mm, LDT_BASE_ADDR); - is_vmalloc = is_vmalloc_addr(ldt->entries); - for (i = 0; i * PAGE_SIZE < ldt->nr_entries * LDT_ENTRY_SIZE; i++) { + nr_pages = DIV_ROUND_UP(ldt->nr_entries * LDT_ENTRY_SIZE, PAGE_SIZE); + + for (i = 0; i < nr_pages; i++) { unsigned long offset = i << PAGE_SHIFT; const void *src = (char *)ldt->entries + offset; unsigned long pfn; @@ -272,13 +258,39 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) /* Propagate LDT mapping to the user page-table */ map_ldt_struct_to_user(mm); - va = (unsigned long)ldt_slot_va(slot); - flush_tlb_mm_range(mm, va, va + LDT_SLOT_STRIDE, PAGE_SHIFT, false); - ldt->slot = slot; return 0; } +static void unmap_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt) +{ + unsigned long va; + int i, nr_pages; + + if (!ldt) + return; + + /* LDT map/unmap is only required for PTI */ + if (!static_cpu_has(X86_FEATURE_PTI)) + return; + + nr_pages = DIV_ROUND_UP(ldt->nr_entries * LDT_ENTRY_SIZE, PAGE_SIZE); + + for (i = 0; i < nr_pages; i++) { + unsigned long offset = i << PAGE_SHIFT; + spinlock_t *ptl; + pte_t *ptep; + + va = (unsigned long)ldt_slot_va(ldt->slot) + offset; + ptep = get_locked_pte(mm, va, &ptl); + pte_clear(mm, va, ptep); + pte_unmap_unlock(ptep, ptl); + } + + va = (unsigned long)ldt_slot_va(ldt->slot); + flush_tlb_mm_range(mm, va, va + nr_pages * PAGE_SIZE, PAGE_SHIFT, false); +} + #else /* !CONFIG_PAGE_TABLE_ISOLATION */ static int @@ -286,6 +298,10 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) { return 0; } + +static void unmap_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt) +{ +} #endif /* CONFIG_PAGE_TABLE_ISOLATION */ static void free_ldt_pgtables(struct mm_struct *mm) @@ -524,6 +540,7 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) } install_ldt(mm, new_ldt); + unmap_ldt_struct(mm, old_ldt); free_ldt_struct(old_ldt); error = 0; diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c index 1eae5af491c2..891a75dbc131 100644 --- a/arch/x86/kernel/vsmp_64.c +++ b/arch/x86/kernel/vsmp_64.c @@ -26,65 +26,8 @@ #define TOPOLOGY_REGISTER_OFFSET 0x10 -#if defined CONFIG_PCI && defined CONFIG_PARAVIRT_XXL -/* - * Interrupt control on vSMPowered systems: - * ~AC is a shadow of IF. If IF is 'on' AC should be 'off' - * and vice versa. - */ - -asmlinkage __visible unsigned long vsmp_save_fl(void) -{ - unsigned long flags = native_save_fl(); - - if (!(flags & X86_EFLAGS_IF) || (flags & X86_EFLAGS_AC)) - flags &= ~X86_EFLAGS_IF; - return flags; -} -PV_CALLEE_SAVE_REGS_THUNK(vsmp_save_fl); - -__visible void vsmp_restore_fl(unsigned long flags) -{ - if (flags & X86_EFLAGS_IF) - flags &= ~X86_EFLAGS_AC; - else - flags |= X86_EFLAGS_AC; - native_restore_fl(flags); -} -PV_CALLEE_SAVE_REGS_THUNK(vsmp_restore_fl); - -asmlinkage __visible void vsmp_irq_disable(void) -{ - unsigned long flags = native_save_fl(); - - native_restore_fl((flags & ~X86_EFLAGS_IF) | X86_EFLAGS_AC); -} -PV_CALLEE_SAVE_REGS_THUNK(vsmp_irq_disable); - -asmlinkage __visible void vsmp_irq_enable(void) -{ - unsigned long flags = native_save_fl(); - - native_restore_fl((flags | X86_EFLAGS_IF) & (~X86_EFLAGS_AC)); -} -PV_CALLEE_SAVE_REGS_THUNK(vsmp_irq_enable); - -static unsigned __init vsmp_patch(u8 type, void *ibuf, - unsigned long addr, unsigned len) -{ - switch (type) { - case PARAVIRT_PATCH(irq.irq_enable): - case PARAVIRT_PATCH(irq.irq_disable): - case PARAVIRT_PATCH(irq.save_fl): - case PARAVIRT_PATCH(irq.restore_fl): - return paravirt_patch_default(type, ibuf, addr, len); - default: - return native_patch(type, ibuf, addr, len); - } - -} - -static void __init set_vsmp_pv_ops(void) +#ifdef CONFIG_PCI +static void __init set_vsmp_ctl(void) { void __iomem *address; unsigned int cap, ctl, cfg; @@ -109,28 +52,12 @@ static void __init set_vsmp_pv_ops(void) } #endif - if (cap & ctl & (1 << 4)) { - /* Setup irq ops and turn on vSMP IRQ fastpath handling */ - pv_ops.irq.irq_disable = PV_CALLEE_SAVE(vsmp_irq_disable); - pv_ops.irq.irq_enable = PV_CALLEE_SAVE(vsmp_irq_enable); - pv_ops.irq.save_fl = PV_CALLEE_SAVE(vsmp_save_fl); - pv_ops.irq.restore_fl = PV_CALLEE_SAVE(vsmp_restore_fl); - pv_ops.init.patch = vsmp_patch; - ctl &= ~(1 << 4); - } writel(ctl, address + 4); ctl = readl(address + 4); pr_info("vSMP CTL: control set to:0x%08x\n", ctl); early_iounmap(address, 8); } -#else -static void __init set_vsmp_pv_ops(void) -{ -} -#endif - -#ifdef CONFIG_PCI static int is_vsmp = -1; static void __init detect_vsmp_box(void) @@ -164,11 +91,14 @@ static int is_vsmp_box(void) { return 0; } +static void __init set_vsmp_ctl(void) +{ +} #endif static void __init vsmp_cap_cpus(void) { -#if !defined(CONFIG_X86_VSMP) && defined(CONFIG_SMP) +#if !defined(CONFIG_X86_VSMP) && defined(CONFIG_SMP) && defined(CONFIG_PCI) void __iomem *address; unsigned int cfg, topology, node_shift, maxcpus; @@ -221,6 +151,6 @@ void __init vsmp_init(void) vsmp_cap_cpus(); - set_vsmp_pv_ops(); + set_vsmp_ctl(); return; } diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 89db20f8cb70..c4533d05c214 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -55,7 +55,7 @@ #define PRIo64 "o" /* #define apic_debug(fmt,arg...) printk(KERN_WARNING fmt,##arg) */ -#define apic_debug(fmt, arg...) +#define apic_debug(fmt, arg...) do {} while (0) /* 14 is the version for Xeon and Pentium 8.4.8*/ #define APIC_VERSION (0x14UL | ((KVM_APIC_LVT_NUM - 1) << 16)) @@ -576,6 +576,11 @@ int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low, rcu_read_lock(); map = rcu_dereference(kvm->arch.apic_map); + if (unlikely(!map)) { + count = -EOPNOTSUPP; + goto out; + } + if (min > map->max_apic_id) goto out; /* Bits above cluster_size are masked in the caller. */ diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index cf5f572f2305..7c03c0f35444 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -5074,9 +5074,9 @@ static bool need_remote_flush(u64 old, u64 new) } static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa, - const u8 *new, int *bytes) + int *bytes) { - u64 gentry; + u64 gentry = 0; int r; /* @@ -5088,22 +5088,12 @@ static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa, /* Handle a 32-bit guest writing two halves of a 64-bit gpte */ *gpa &= ~(gpa_t)7; *bytes = 8; - r = kvm_vcpu_read_guest(vcpu, *gpa, &gentry, 8); - if (r) - gentry = 0; - new = (const u8 *)&gentry; } - switch (*bytes) { - case 4: - gentry = *(const u32 *)new; - break; - case 8: - gentry = *(const u64 *)new; - break; - default: - gentry = 0; - break; + if (*bytes == 4 || *bytes == 8) { + r = kvm_vcpu_read_guest_atomic(vcpu, *gpa, &gentry, *bytes); + if (r) + gentry = 0; } return gentry; @@ -5207,8 +5197,6 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, pgprintk("%s: gpa %llx bytes %d\n", __func__, gpa, bytes); - gentry = mmu_pte_write_fetch_gpte(vcpu, &gpa, new, &bytes); - /* * No need to care whether allocation memory is successful * or not since pte prefetch is skiped if it does not have @@ -5217,6 +5205,9 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, mmu_topup_memory_caches(vcpu); spin_lock(&vcpu->kvm->mmu_lock); + + gentry = mmu_pte_write_fetch_gpte(vcpu, &gpa, &bytes); + ++vcpu->kvm->stat.mmu_pte_write; kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 0e21ccc46792..cc6467b35a85 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1446,7 +1446,7 @@ static u64 svm_read_l1_tsc_offset(struct kvm_vcpu *vcpu) return vcpu->arch.tsc_offset; } -static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) +static u64 svm_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) { struct vcpu_svm *svm = to_svm(vcpu); u64 g_tsc_offset = 0; @@ -1464,6 +1464,7 @@ static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) svm->vmcb->control.tsc_offset = offset + g_tsc_offset; mark_dirty(svm->vmcb, VMCB_INTERCEPTS); + return svm->vmcb->control.tsc_offset; } static void avic_init_vmcb(struct vcpu_svm *svm) @@ -1664,20 +1665,23 @@ static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu, static int avic_init_access_page(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; - int ret; + int ret = 0; + mutex_lock(&kvm->slots_lock); if (kvm->arch.apic_access_page_done) - return 0; + goto out; - ret = x86_set_memory_region(kvm, - APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, - APIC_DEFAULT_PHYS_BASE, - PAGE_SIZE); + ret = __x86_set_memory_region(kvm, + APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, + APIC_DEFAULT_PHYS_BASE, + PAGE_SIZE); if (ret) - return ret; + goto out; kvm->arch.apic_access_page_done = true; - return 0; +out: + mutex_unlock(&kvm->slots_lock); + return ret; } static int avic_init_backing_page(struct kvm_vcpu *vcpu) @@ -2189,21 +2193,31 @@ out: return ERR_PTR(err); } +static void svm_clear_current_vmcb(struct vmcb *vmcb) +{ + int i; + + for_each_online_cpu(i) + cmpxchg(&per_cpu(svm_data, i)->current_vmcb, vmcb, NULL); +} + static void svm_free_vcpu(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + /* + * The vmcb page can be recycled, causing a false negative in + * svm_vcpu_load(). So, ensure that no logical CPU has this + * vmcb page recorded as its current vmcb. + */ + svm_clear_current_vmcb(svm->vmcb); + __free_page(pfn_to_page(__sme_clr(svm->vmcb_pa) >> PAGE_SHIFT)); __free_pages(virt_to_page(svm->msrpm), MSRPM_ALLOC_ORDER); __free_page(virt_to_page(svm->nested.hsave)); __free_pages(virt_to_page(svm->nested.msrpm), MSRPM_ALLOC_ORDER); kvm_vcpu_uninit(vcpu); kmem_cache_free(kvm_vcpu_cache, svm); - /* - * The vmcb page can be recycled, causing a false negative in - * svm_vcpu_load(). So do a full IBPB now. - */ - indirect_branch_prediction_barrier(); } static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) @@ -7149,7 +7163,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .has_wbinvd_exit = svm_has_wbinvd_exit, .read_l1_tsc_offset = svm_read_l1_tsc_offset, - .write_tsc_offset = svm_write_tsc_offset, + .write_l1_tsc_offset = svm_write_l1_tsc_offset, .set_tdp_cr3 = set_tdp_cr3, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 4555077d69ce..02edd9960e9d 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -174,6 +174,7 @@ module_param_named(preemption_timer, enable_preemption_timer, bool, S_IRUGO); * refer SDM volume 3b section 21.6.13 & 22.1.3. */ static unsigned int ple_gap = KVM_DEFAULT_PLE_GAP; +module_param(ple_gap, uint, 0444); static unsigned int ple_window = KVM_VMX_DEFAULT_PLE_WINDOW; module_param(ple_window, uint, 0444); @@ -984,6 +985,7 @@ struct vcpu_vmx { struct shared_msr_entry *guest_msrs; int nmsrs; int save_nmsrs; + bool guest_msrs_dirty; unsigned long host_idt_base; #ifdef CONFIG_X86_64 u64 msr_host_kernel_gs_base; @@ -1306,7 +1308,7 @@ static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked); static bool nested_vmx_is_page_fault_vmexit(struct vmcs12 *vmcs12, u16 error_code); static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu); -static void __always_inline vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, +static __always_inline void vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, u32 msr, int type); static DEFINE_PER_CPU(struct vmcs *, vmxarea); @@ -1610,12 +1612,6 @@ static int nested_enable_evmcs(struct kvm_vcpu *vcpu, { struct vcpu_vmx *vmx = to_vmx(vcpu); - /* We don't support disabling the feature for simplicity. */ - if (vmx->nested.enlightened_vmcs_enabled) - return 0; - - vmx->nested.enlightened_vmcs_enabled = true; - /* * vmcs_version represents the range of supported Enlightened VMCS * versions: lower 8 bits is the minimal version, higher 8 bits is the @@ -1625,6 +1621,12 @@ static int nested_enable_evmcs(struct kvm_vcpu *vcpu, if (vmcs_version) *vmcs_version = (KVM_EVMCS_VERSION << 8) | 1; + /* We don't support disabling the feature for simplicity. */ + if (vmx->nested.enlightened_vmcs_enabled) + return 0; + + vmx->nested.enlightened_vmcs_enabled = true; + vmx->nested.msrs.pinbased_ctls_high &= ~EVMCS1_UNSUPPORTED_PINCTRL; vmx->nested.msrs.entry_ctls_high &= ~EVMCS1_UNSUPPORTED_VMENTRY_CTRL; vmx->nested.msrs.exit_ctls_high &= ~EVMCS1_UNSUPPORTED_VMEXIT_CTRL; @@ -2897,6 +2899,20 @@ static void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) vmx->req_immediate_exit = false; + /* + * Note that guest MSRs to be saved/restored can also be changed + * when guest state is loaded. This happens when guest transitions + * to/from long-mode by setting MSR_EFER.LMA. + */ + if (!vmx->loaded_cpu_state || vmx->guest_msrs_dirty) { + vmx->guest_msrs_dirty = false; + for (i = 0; i < vmx->save_nmsrs; ++i) + kvm_set_shared_msr(vmx->guest_msrs[i].index, + vmx->guest_msrs[i].data, + vmx->guest_msrs[i].mask); + + } + if (vmx->loaded_cpu_state) return; @@ -2957,11 +2973,6 @@ static void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) vmcs_writel(HOST_GS_BASE, gs_base); host_state->gs_base = gs_base; } - - for (i = 0; i < vmx->save_nmsrs; ++i) - kvm_set_shared_msr(vmx->guest_msrs[i].index, - vmx->guest_msrs[i].data, - vmx->guest_msrs[i].mask); } static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx) @@ -3436,6 +3447,7 @@ static void setup_msrs(struct vcpu_vmx *vmx) move_msr_up(vmx, index, save_nmsrs++); vmx->save_nmsrs = save_nmsrs; + vmx->guest_msrs_dirty = true; if (cpu_has_vmx_msr_bitmap()) vmx_update_msr_bitmap(&vmx->vcpu); @@ -3452,11 +3464,9 @@ static u64 vmx_read_l1_tsc_offset(struct kvm_vcpu *vcpu) return vcpu->arch.tsc_offset; } -/* - * writes 'offset' into guest's timestamp counter offset register - */ -static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) +static u64 vmx_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) { + u64 active_offset = offset; if (is_guest_mode(vcpu)) { /* * We're here if L1 chose not to trap WRMSR to TSC. According @@ -3464,17 +3474,16 @@ static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) * set for L2 remains unchanged, and still needs to be added * to the newly set TSC to get L2's TSC. */ - struct vmcs12 *vmcs12; - /* recalculate vmcs02.TSC_OFFSET: */ - vmcs12 = get_vmcs12(vcpu); - vmcs_write64(TSC_OFFSET, offset + - (nested_cpu_has(vmcs12, CPU_BASED_USE_TSC_OFFSETING) ? - vmcs12->tsc_offset : 0)); + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + if (nested_cpu_has(vmcs12, CPU_BASED_USE_TSC_OFFSETING)) + active_offset += vmcs12->tsc_offset; } else { trace_kvm_write_tsc_offset(vcpu->vcpu_id, vmcs_read64(TSC_OFFSET), offset); - vmcs_write64(TSC_OFFSET, offset); } + + vmcs_write64(TSC_OFFSET, active_offset); + return active_offset; } /* @@ -5944,7 +5953,7 @@ static void free_vpid(int vpid) spin_unlock(&vmx_vpid_lock); } -static void __always_inline vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, +static __always_inline void vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, u32 msr, int type) { int f = sizeof(unsigned long); @@ -5982,7 +5991,7 @@ static void __always_inline vmx_disable_intercept_for_msr(unsigned long *msr_bit } } -static void __always_inline vmx_enable_intercept_for_msr(unsigned long *msr_bitmap, +static __always_inline void vmx_enable_intercept_for_msr(unsigned long *msr_bitmap, u32 msr, int type) { int f = sizeof(unsigned long); @@ -6020,7 +6029,7 @@ static void __always_inline vmx_enable_intercept_for_msr(unsigned long *msr_bitm } } -static void __always_inline vmx_set_intercept_for_msr(unsigned long *msr_bitmap, +static __always_inline void vmx_set_intercept_for_msr(unsigned long *msr_bitmap, u32 msr, int type, bool value) { if (value) @@ -8664,8 +8673,6 @@ static int copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx) struct vmcs12 *vmcs12 = vmx->nested.cached_vmcs12; struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs; - vmcs12->hdr.revision_id = evmcs->revision_id; - /* HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE */ vmcs12->tpr_threshold = evmcs->tpr_threshold; vmcs12->guest_rip = evmcs->guest_rip; @@ -9369,7 +9376,30 @@ static int nested_vmx_handle_enlightened_vmptrld(struct kvm_vcpu *vcpu, vmx->nested.hv_evmcs = kmap(vmx->nested.hv_evmcs_page); - if (vmx->nested.hv_evmcs->revision_id != VMCS12_REVISION) { + /* + * Currently, KVM only supports eVMCS version 1 + * (== KVM_EVMCS_VERSION) and thus we expect guest to set this + * value to first u32 field of eVMCS which should specify eVMCS + * VersionNumber. + * + * Guest should be aware of supported eVMCS versions by host by + * examining CPUID.0x4000000A.EAX[0:15]. Host userspace VMM is + * expected to set this CPUID leaf according to the value + * returned in vmcs_version from nested_enable_evmcs(). + * + * However, it turns out that Microsoft Hyper-V fails to comply + * to their own invented interface: When Hyper-V use eVMCS, it + * just sets first u32 field of eVMCS to revision_id specified + * in MSR_IA32_VMX_BASIC. Instead of used eVMCS version number + * which is one of the supported versions specified in + * CPUID.0x4000000A.EAX[0:15]. + * + * To overcome Hyper-V bug, we accept here either a supported + * eVMCS version or VMCS12 revision_id as valid values for first + * u32 field of eVMCS. + */ + if ((vmx->nested.hv_evmcs->revision_id != KVM_EVMCS_VERSION) && + (vmx->nested.hv_evmcs->revision_id != VMCS12_REVISION)) { nested_release_evmcs(vcpu); return 0; } @@ -9390,9 +9420,11 @@ static int nested_vmx_handle_enlightened_vmptrld(struct kvm_vcpu *vcpu, * present in struct hv_enlightened_vmcs, ...). Make sure there * are no leftovers. */ - if (from_launch) - memset(vmx->nested.cached_vmcs12, 0, - sizeof(*vmx->nested.cached_vmcs12)); + if (from_launch) { + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + memset(vmcs12, 0, sizeof(*vmcs12)); + vmcs12->hdr.revision_id = VMCS12_REVISION; + } } return 1; @@ -15062,7 +15094,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .has_wbinvd_exit = cpu_has_vmx_wbinvd_exit, .read_l1_tsc_offset = vmx_read_l1_tsc_offset, - .write_tsc_offset = vmx_write_tsc_offset, + .write_l1_tsc_offset = vmx_write_l1_tsc_offset, .set_tdp_cr3 = vmx_set_cr3, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 5cd5647120f2..d02937760c3b 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1665,8 +1665,7 @@ EXPORT_SYMBOL_GPL(kvm_read_l1_tsc); static void kvm_vcpu_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) { - kvm_x86_ops->write_tsc_offset(vcpu, offset); - vcpu->arch.tsc_offset = offset; + vcpu->arch.tsc_offset = kvm_x86_ops->write_l1_tsc_offset(vcpu, offset); } static inline bool kvm_check_tsc_unstable(void) @@ -1794,7 +1793,8 @@ EXPORT_SYMBOL_GPL(kvm_write_tsc); static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, s64 adjustment) { - kvm_vcpu_write_tsc_offset(vcpu, vcpu->arch.tsc_offset + adjustment); + u64 tsc_offset = kvm_x86_ops->read_l1_tsc_offset(vcpu); + kvm_vcpu_write_tsc_offset(vcpu, tsc_offset + adjustment); } static inline void adjust_tsc_offset_host(struct kvm_vcpu *vcpu, s64 adjustment) @@ -6918,6 +6918,7 @@ static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr, clock_pairing.nsec = ts.tv_nsec; clock_pairing.tsc = kvm_read_l1_tsc(vcpu, cycle); clock_pairing.flags = 0; + memset(&clock_pairing.pad, 0, sizeof(clock_pairing.pad)); ret = 0; if (kvm_write_guest(vcpu->kvm, paddr, &clock_pairing, @@ -7455,7 +7456,8 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) else { if (vcpu->arch.apicv_active) kvm_x86_ops->sync_pir_to_irr(vcpu); - kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors); + if (ioapic_in_kernel(vcpu->kvm)) + kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors); } if (is_guest_mode(vcpu)) diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 0d7b3ae4960b..a5d7ed125337 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -1905,7 +1905,7 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) init_top_pgt[0] = __pgd(0); /* Pre-constructed entries are in pfn, so convert to mfn */ - /* L4[272] -> level3_ident_pgt */ + /* L4[273] -> level3_ident_pgt */ /* L4[511] -> level3_kernel_pgt */ convert_pfn_mfn(init_top_pgt); @@ -1925,8 +1925,8 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) addr[0] = (unsigned long)pgd; addr[1] = (unsigned long)l3; addr[2] = (unsigned long)l2; - /* Graft it onto L4[272][0]. Note that we creating an aliasing problem: - * Both L4[272][0] and L4[511][510] have entries that point to the same + /* Graft it onto L4[273][0]. Note that we creating an aliasing problem: + * Both L4[273][0] and L4[511][510] have entries that point to the same * L2 (PMD) tables. Meaning that if you modify it in __va space * it will be also modified in the __ka space! (But if you just * modify the PMD table to point to other PTE's or none, then you diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index b06731705529..055e37e43541 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -656,8 +656,7 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn) /* * The interface requires atomic updates on p2m elements. - * xen_safe_write_ulong() is using __put_user which does an atomic - * store via asm(). + * xen_safe_write_ulong() is using an atomic store via asm(). */ if (likely(!xen_safe_write_ulong(xen_p2m_addr + pfn, mfn))) return true; diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index 441c88262169..1c8a8816a402 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -9,6 +9,7 @@ #include <linux/log2.h> #include <linux/gfp.h> #include <linux/slab.h> +#include <linux/atomic.h> #include <asm/paravirt.h> #include <asm/qspinlock.h> @@ -21,6 +22,7 @@ static DEFINE_PER_CPU(int, lock_kicker_irq) = -1; static DEFINE_PER_CPU(char *, irq_name); +static DEFINE_PER_CPU(atomic_t, xen_qlock_wait_nest); static bool xen_pvspin = true; static void xen_qlock_kick(int cpu) @@ -39,25 +41,25 @@ static void xen_qlock_kick(int cpu) */ static void xen_qlock_wait(u8 *byte, u8 val) { - unsigned long flags; int irq = __this_cpu_read(lock_kicker_irq); + atomic_t *nest_cnt = this_cpu_ptr(&xen_qlock_wait_nest); /* If kicker interrupts not initialized yet, just spin */ if (irq == -1 || in_nmi()) return; - /* Guard against reentry. */ - local_irq_save(flags); + /* Detect reentry. */ + atomic_inc(nest_cnt); - /* If irq pending already clear it. */ - if (xen_test_irq_pending(irq)) { + /* If irq pending already and no nested call clear it. */ + if (atomic_read(nest_cnt) == 1 && xen_test_irq_pending(irq)) { xen_clear_irq_pending(irq); } else if (READ_ONCE(*byte) == val) { /* Block until irq becomes pending (or a spurious wakeup) */ xen_poll_irq(irq); } - local_irq_restore(flags); + atomic_dec(nest_cnt); } static irqreturn_t dummy_handler(int irq, void *dev_id) |