diff options
Diffstat (limited to 'arch/x86')
52 files changed, 669 insertions, 388 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 1d6104ea8af0..2d3f963fd6f1 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -68,6 +68,7 @@ config X86 select ARCH_HAS_KCOV if X86_64 select ARCH_HAS_MEM_ENCRYPT select ARCH_HAS_MEMBARRIER_SYNC_CORE + select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE select ARCH_HAS_PMEM_API if X86_64 select ARCH_HAS_PTE_DEVMAP if X86_64 select ARCH_HAS_PTE_SPECIAL @@ -149,7 +150,7 @@ config X86 select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_TRANSPARENT_HUGEPAGE select HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD if X86_64 - select HAVE_ARCH_USERFAULTFD_WP if USERFAULTFD + select HAVE_ARCH_USERFAULTFD_WP if X86_64 && USERFAULTFD select HAVE_ARCH_VMAP_STACK if X86_64 select HAVE_ARCH_WITHIN_STACK_FRAMES select HAVE_ASM_MODVERSIONS diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c index 8f8c8e386cea..c8b8c1a8d1fc 100644 --- a/arch/x86/boot/tools/build.c +++ b/arch/x86/boot/tools/build.c @@ -59,14 +59,14 @@ u8 buf[SETUP_SECT_MAX*512]; #define PECOFF_COMPAT_RESERVE 0x0 #endif -unsigned long efi32_stub_entry; -unsigned long efi64_stub_entry; -unsigned long efi_pe_entry; -unsigned long efi32_pe_entry; -unsigned long kernel_info; -unsigned long startup_64; -unsigned long _ehead; -unsigned long _end; +static unsigned long efi32_stub_entry; +static unsigned long efi64_stub_entry; +static unsigned long efi_pe_entry; +static unsigned long efi32_pe_entry; +static unsigned long kernel_info; +static unsigned long startup_64; +static unsigned long _ehead; +static unsigned long _end; /*----------------------------------------------------------------------*/ diff --git a/arch/x86/crypto/blake2s-glue.c b/arch/x86/crypto/blake2s-glue.c index 06ef2d4a4701..6737bcea1fa1 100644 --- a/arch/x86/crypto/blake2s-glue.c +++ b/arch/x86/crypto/blake2s-glue.c @@ -32,16 +32,16 @@ void blake2s_compress_arch(struct blake2s_state *state, const u32 inc) { /* SIMD disables preemption, so relax after processing each page. */ - BUILD_BUG_ON(PAGE_SIZE / BLAKE2S_BLOCK_SIZE < 8); + BUILD_BUG_ON(SZ_4K / BLAKE2S_BLOCK_SIZE < 8); if (!static_branch_likely(&blake2s_use_ssse3) || !crypto_simd_usable()) { blake2s_compress_generic(state, block, nblocks, inc); return; } - for (;;) { + do { const size_t blocks = min_t(size_t, nblocks, - PAGE_SIZE / BLAKE2S_BLOCK_SIZE); + SZ_4K / BLAKE2S_BLOCK_SIZE); kernel_fpu_begin(); if (IS_ENABLED(CONFIG_AS_AVX512) && @@ -52,10 +52,8 @@ void blake2s_compress_arch(struct blake2s_state *state, kernel_fpu_end(); nblocks -= blocks; - if (!nblocks) - break; block += blocks * BLAKE2S_BLOCK_SIZE; - } + } while (nblocks); } EXPORT_SYMBOL(blake2s_compress_arch); diff --git a/arch/x86/crypto/chacha_glue.c b/arch/x86/crypto/chacha_glue.c index b412c21ee06e..22250091cdbe 100644 --- a/arch/x86/crypto/chacha_glue.c +++ b/arch/x86/crypto/chacha_glue.c @@ -153,9 +153,17 @@ void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes, bytes <= CHACHA_BLOCK_SIZE) return chacha_crypt_generic(state, dst, src, bytes, nrounds); - kernel_fpu_begin(); - chacha_dosimd(state, dst, src, bytes, nrounds); - kernel_fpu_end(); + do { + unsigned int todo = min_t(unsigned int, bytes, SZ_4K); + + kernel_fpu_begin(); + chacha_dosimd(state, dst, src, todo, nrounds); + kernel_fpu_end(); + + bytes -= todo; + src += todo; + dst += todo; + } while (bytes); } EXPORT_SYMBOL(chacha_crypt_arch); diff --git a/arch/x86/crypto/nhpoly1305-avx2-glue.c b/arch/x86/crypto/nhpoly1305-avx2-glue.c index f7567cbd35b6..80fcb85736e1 100644 --- a/arch/x86/crypto/nhpoly1305-avx2-glue.c +++ b/arch/x86/crypto/nhpoly1305-avx2-glue.c @@ -29,7 +29,7 @@ static int nhpoly1305_avx2_update(struct shash_desc *desc, return crypto_nhpoly1305_update(desc, src, srclen); do { - unsigned int n = min_t(unsigned int, srclen, PAGE_SIZE); + unsigned int n = min_t(unsigned int, srclen, SZ_4K); kernel_fpu_begin(); crypto_nhpoly1305_update_helper(desc, src, n, _nh_avx2); diff --git a/arch/x86/crypto/nhpoly1305-sse2-glue.c b/arch/x86/crypto/nhpoly1305-sse2-glue.c index a661ede3b5cf..cc6b7c1a2705 100644 --- a/arch/x86/crypto/nhpoly1305-sse2-glue.c +++ b/arch/x86/crypto/nhpoly1305-sse2-glue.c @@ -29,7 +29,7 @@ static int nhpoly1305_sse2_update(struct shash_desc *desc, return crypto_nhpoly1305_update(desc, src, srclen); do { - unsigned int n = min_t(unsigned int, srclen, PAGE_SIZE); + unsigned int n = min_t(unsigned int, srclen, SZ_4K); kernel_fpu_begin(); crypto_nhpoly1305_update_helper(desc, src, n, _nh_sse2); diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c index 6dfec19f7d57..dfe921efa9b2 100644 --- a/arch/x86/crypto/poly1305_glue.c +++ b/arch/x86/crypto/poly1305_glue.c @@ -91,8 +91,8 @@ static void poly1305_simd_blocks(void *ctx, const u8 *inp, size_t len, struct poly1305_arch_internal *state = ctx; /* SIMD disables preemption, so relax after processing each page. */ - BUILD_BUG_ON(PAGE_SIZE < POLY1305_BLOCK_SIZE || - PAGE_SIZE % POLY1305_BLOCK_SIZE); + BUILD_BUG_ON(SZ_4K < POLY1305_BLOCK_SIZE || + SZ_4K % POLY1305_BLOCK_SIZE); if (!static_branch_likely(&poly1305_use_avx) || (len < (POLY1305_BLOCK_SIZE * 18) && !state->is_base2_26) || @@ -102,8 +102,8 @@ static void poly1305_simd_blocks(void *ctx, const u8 *inp, size_t len, return; } - for (;;) { - const size_t bytes = min_t(size_t, len, PAGE_SIZE); + do { + const size_t bytes = min_t(size_t, len, SZ_4K); kernel_fpu_begin(); if (IS_ENABLED(CONFIG_AS_AVX512) && static_branch_likely(&poly1305_use_avx512)) @@ -113,11 +113,10 @@ static void poly1305_simd_blocks(void *ctx, const u8 *inp, size_t len, else poly1305_blocks_avx(ctx, inp, bytes, padbit); kernel_fpu_end(); + len -= bytes; - if (!len) - break; inp += bytes; - } + } while (len); } static void poly1305_simd_emit(void *ctx, u8 mac[POLY1305_DIGEST_SIZE], diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 0789e13ece90..1c7f13bb6728 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -98,13 +98,6 @@ For 32-bit we have the following conventions - kernel is built with #define SIZEOF_PTREGS 21*8 .macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax save_ret=0 - /* - * Push registers and sanitize registers of values that a - * speculation attack might otherwise want to exploit. The - * lower registers are likely clobbered well before they - * could be put to use in a speculative execution gadget. - * Interleave XOR with PUSH for better uop scheduling: - */ .if \save_ret pushq %rsi /* pt_regs->si */ movq 8(%rsp), %rsi /* temporarily store the return address in %rsi */ @@ -114,34 +107,43 @@ For 32-bit we have the following conventions - kernel is built with pushq %rsi /* pt_regs->si */ .endif pushq \rdx /* pt_regs->dx */ - xorl %edx, %edx /* nospec dx */ pushq %rcx /* pt_regs->cx */ - xorl %ecx, %ecx /* nospec cx */ pushq \rax /* pt_regs->ax */ pushq %r8 /* pt_regs->r8 */ - xorl %r8d, %r8d /* nospec r8 */ pushq %r9 /* pt_regs->r9 */ - xorl %r9d, %r9d /* nospec r9 */ pushq %r10 /* pt_regs->r10 */ - xorl %r10d, %r10d /* nospec r10 */ pushq %r11 /* pt_regs->r11 */ - xorl %r11d, %r11d /* nospec r11*/ pushq %rbx /* pt_regs->rbx */ - xorl %ebx, %ebx /* nospec rbx*/ pushq %rbp /* pt_regs->rbp */ - xorl %ebp, %ebp /* nospec rbp*/ pushq %r12 /* pt_regs->r12 */ - xorl %r12d, %r12d /* nospec r12*/ pushq %r13 /* pt_regs->r13 */ - xorl %r13d, %r13d /* nospec r13*/ pushq %r14 /* pt_regs->r14 */ - xorl %r14d, %r14d /* nospec r14*/ pushq %r15 /* pt_regs->r15 */ - xorl %r15d, %r15d /* nospec r15*/ UNWIND_HINT_REGS + .if \save_ret pushq %rsi /* return address on top of stack */ .endif + + /* + * Sanitize registers of values that a speculation attack might + * otherwise want to exploit. The lower registers are likely clobbered + * well before they could be put to use in a speculative execution + * gadget. + */ + xorl %edx, %edx /* nospec dx */ + xorl %ecx, %ecx /* nospec cx */ + xorl %r8d, %r8d /* nospec r8 */ + xorl %r9d, %r9d /* nospec r9 */ + xorl %r10d, %r10d /* nospec r10 */ + xorl %r11d, %r11d /* nospec r11 */ + xorl %ebx, %ebx /* nospec rbx */ + xorl %ebp, %ebp /* nospec rbp */ + xorl %r12d, %r12d /* nospec r12 */ + xorl %r13d, %r13d /* nospec r13 */ + xorl %r14d, %r14d /* nospec r14 */ + xorl %r15d, %r15d /* nospec r15 */ + .endm .macro POP_REGS pop_rdi=1 skip_r11rcx=0 diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 0e9504fabe52..3063aa9090f9 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -249,7 +249,6 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL) */ syscall_return_via_sysret: /* rcx and r11 are already restored (see code above) */ - UNWIND_HINT_EMPTY POP_REGS pop_rdi=0 skip_r11rcx=1 /* @@ -258,6 +257,7 @@ syscall_return_via_sysret: */ movq %rsp, %rdi movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp + UNWIND_HINT_EMPTY pushq RSP-RDI(%rdi) /* RSP */ pushq (%rdi) /* RDI */ @@ -279,8 +279,7 @@ SYM_CODE_END(entry_SYSCALL_64) * %rdi: prev task * %rsi: next task */ -SYM_CODE_START(__switch_to_asm) - UNWIND_HINT_FUNC +SYM_FUNC_START(__switch_to_asm) /* * Save callee-saved registers * This must match the order in inactive_task_frame @@ -321,7 +320,7 @@ SYM_CODE_START(__switch_to_asm) popq %rbp jmp __switch_to -SYM_CODE_END(__switch_to_asm) +SYM_FUNC_END(__switch_to_asm) /* * A newly forked process directly context switches into this address. @@ -512,7 +511,7 @@ SYM_CODE_END(spurious_entries_start) * +----------------------------------------------------+ */ SYM_CODE_START(interrupt_entry) - UNWIND_HINT_FUNC + UNWIND_HINT_IRET_REGS offset=16 ASM_CLAC cld @@ -544,9 +543,9 @@ SYM_CODE_START(interrupt_entry) pushq 5*8(%rdi) /* regs->eflags */ pushq 4*8(%rdi) /* regs->cs */ pushq 3*8(%rdi) /* regs->ip */ + UNWIND_HINT_IRET_REGS pushq 2*8(%rdi) /* regs->orig_ax */ pushq 8(%rdi) /* return address */ - UNWIND_HINT_FUNC movq (%rdi), %rdi jmp 2f @@ -637,6 +636,7 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL) */ movq %rsp, %rdi movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp + UNWIND_HINT_EMPTY /* Copy the IRET frame to the trampoline stack. */ pushq 6*8(%rdi) /* SS */ @@ -1739,7 +1739,7 @@ SYM_CODE_START(rewind_stack_do_exit) movq PER_CPU_VAR(cpu_current_top_of_stack), %rax leaq -PTREGS_SIZE(%rax), %rsp - UNWIND_HINT_FUNC sp_offset=PTREGS_SIZE + UNWIND_HINT_REGS call do_exit SYM_CODE_END(rewind_stack_do_exit) diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index e4aa20c0426f..442e1ed4acd4 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -643,6 +643,7 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_PLUS, &glm_cstates), X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, &glm_cstates), X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT, &glm_cstates), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_L, &glm_cstates), X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L, &icl_cstates), X86_MATCH_INTEL_FAM6_MODEL(ICELAKE, &icl_cstates), diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index b0da5320bcff..acf76b466db6 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -20,6 +20,7 @@ #include <linux/mm.h> #include <linux/hyperv.h> #include <linux/slab.h> +#include <linux/kernel.h> #include <linux/cpuhotplug.h> #include <linux/syscore_ops.h> #include <clocksource/hyperv_timer.h> @@ -72,7 +73,8 @@ static int hv_cpu_init(unsigned int cpu) struct page *pg; input_arg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg); - pg = alloc_page(GFP_KERNEL); + /* hv_cpu_init() can be called with IRQs disabled from hv_resume() */ + pg = alloc_page(irqs_disabled() ? GFP_ATOMIC : GFP_KERNEL); if (unlikely(!pg)) return -ENOMEM; *input_arg = page_address(pg); @@ -224,10 +226,18 @@ static int hv_cpu_die(unsigned int cpu) rdmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl)); if (re_ctrl.target_vp == hv_vp_index[cpu]) { - /* Reassign to some other online CPU */ + /* + * Reassign reenlightenment notifications to some other online + * CPU or just disable the feature if there are no online CPUs + * left (happens on hibernation). + */ new_cpu = cpumask_any_but(cpu_online_mask, cpu); - re_ctrl.target_vp = hv_vp_index[new_cpu]; + if (new_cpu < nr_cpu_ids) + re_ctrl.target_vp = hv_vp_index[new_cpu]; + else + re_ctrl.enabled = 0; + wrmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl)); } @@ -253,6 +263,7 @@ static int __init hv_pci_init(void) static int hv_suspend(void) { union hv_x64_msr_hypercall_contents hypercall_msr; + int ret; /* * Reset the hypercall page as it is going to be invalidated @@ -269,12 +280,17 @@ static int hv_suspend(void) hypercall_msr.enable = 0; wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); - return 0; + ret = hv_cpu_die(0); + return ret; } static void hv_resume(void) { union hv_x64_msr_hypercall_contents hypercall_msr; + int ret; + + ret = hv_cpu_init(0); + WARN_ON(ret); /* Re-enable the hypercall page */ rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); @@ -285,8 +301,16 @@ static void hv_resume(void) hv_hypercall_pg = hv_hypercall_pg_saved; hv_hypercall_pg_saved = NULL; + + /* + * Reenlightenment notifications are disabled by hv_cpu_die(0), + * reenable them here if hv_reenlightenment_cb was previously set. + */ + if (hv_reenlightenment_cb) + set_hv_tscchange_cb(hv_reenlightenment_cb); } +/* Note: when the ops are called, only CPU0 is online and IRQs are disabled. */ static struct syscore_ops hv_syscore_ops = { .suspend = hv_suspend, .resume = hv_resume, @@ -419,11 +443,14 @@ void hyperv_cleanup(void) } EXPORT_SYMBOL_GPL(hyperv_cleanup); -void hyperv_report_panic(struct pt_regs *regs, long err) +void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die) { static bool panic_reported; u64 guest_id; + if (in_die && !panic_on_oops) + return; + /* * We prefer to report panic on 'die' chain as we have proper * registers to report, but if we miss it (e.g. on BUG()) we need diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 53f246e9df5a..0367efdc5b7a 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -52,9 +52,9 @@ static __always_inline void arch_set_bit(long nr, volatile unsigned long *addr) { if (__builtin_constant_p(nr)) { - asm volatile(LOCK_PREFIX "orb %1,%0" + asm volatile(LOCK_PREFIX "orb %b1,%0" : CONST_MASK_ADDR(nr, addr) - : "iq" (CONST_MASK(nr) & 0xff) + : "iq" (CONST_MASK(nr)) : "memory"); } else { asm volatile(LOCK_PREFIX __ASM_SIZE(bts) " %1,%0" @@ -72,9 +72,9 @@ static __always_inline void arch_clear_bit(long nr, volatile unsigned long *addr) { if (__builtin_constant_p(nr)) { - asm volatile(LOCK_PREFIX "andb %1,%0" + asm volatile(LOCK_PREFIX "andb %b1,%0" : CONST_MASK_ADDR(nr, addr) - : "iq" (CONST_MASK(nr) ^ 0xff)); + : "iq" (~CONST_MASK(nr))); } else { asm volatile(LOCK_PREFIX __ASM_SIZE(btr) " %1,%0" : : RLONG_ADDR(addr), "Ir" (nr) : "memory"); @@ -123,9 +123,9 @@ static __always_inline void arch_change_bit(long nr, volatile unsigned long *addr) { if (__builtin_constant_p(nr)) { - asm volatile(LOCK_PREFIX "xorb %1,%0" + asm volatile(LOCK_PREFIX "xorb %b1,%0" : CONST_MASK_ADDR(nr, addr) - : "iq" ((u8)CONST_MASK(nr))); + : "iq" (CONST_MASK(nr))); } else { asm volatile(LOCK_PREFIX __ASM_SIZE(btc) " %1,%0" : : RLONG_ADDR(addr), "Ir" (nr) : "memory"); diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index cdcf48d52a12..8391c115c0ec 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -178,8 +178,10 @@ extern void efi_free_boot_services(void); extern pgd_t * __init efi_uv1_memmap_phys_prolog(void); extern void __init efi_uv1_memmap_phys_epilog(pgd_t *save_pgd); +/* kexec external ABI */ struct efi_setup_data { u64 fw_vendor; + u64 __unused; u64 tables; u64 smbios; u64 reserved[8]; diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index 85be2f506272..84b9449be080 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -56,16 +56,23 @@ struct dyn_arch_ftrace { #ifndef __ASSEMBLY__ +#if defined(CONFIG_FUNCTION_TRACER) && defined(CONFIG_DYNAMIC_FTRACE) +extern void set_ftrace_ops_ro(void); +#else +static inline void set_ftrace_ops_ro(void) { } +#endif + #define ARCH_HAS_SYSCALL_MATCH_SYM_NAME static inline bool arch_syscall_match_sym_name(const char *sym, const char *name) { /* * Compare the symbol name with the system call name. Skip the - * "__x64_sys", "__ia32_sys" or simple "sys" prefix. + * "__x64_sys", "__ia32_sys", "__do_sys" or simple "sys" prefix. */ return !strcmp(sym + 3, name + 3) || (!strncmp(sym, "__x64_", 6) && !strcmp(sym + 9, name + 3)) || - (!strncmp(sym, "__ia32_", 7) && !strcmp(sym + 10, name + 3)); + (!strncmp(sym, "__ia32_", 7) && !strcmp(sym + 10, name + 3)) || + (!strncmp(sym, "__do_sys", 8) && !strcmp(sym + 8, name + 3)); } #ifndef COMPILE_OFFSETS diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 42a2d0d3984a..0a6b35353fc7 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -578,6 +578,7 @@ struct kvm_vcpu_arch { unsigned long cr4; unsigned long cr4_guest_owned_bits; unsigned long cr8; + u32 host_pkru; u32 pkru; u32 hflags; u64 efer; @@ -1093,8 +1094,6 @@ struct kvm_x86_ops { void (*set_idt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void (*get_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void (*set_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); - u64 (*get_dr6)(struct kvm_vcpu *vcpu); - void (*set_dr6)(struct kvm_vcpu *vcpu, unsigned long value); void (*sync_dirty_debug_regs)(struct kvm_vcpu *vcpu); void (*set_dr7)(struct kvm_vcpu *vcpu, unsigned long value); void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg); @@ -1449,6 +1448,7 @@ bool kvm_rdpmc(struct kvm_vcpu *vcpu); void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr); void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code); +void kvm_queue_exception_p(struct kvm_vcpu *vcpu, unsigned nr, unsigned long payload); void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr); void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code); void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault); @@ -1663,8 +1663,8 @@ void kvm_set_msi_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, static inline bool kvm_irq_is_postable(struct kvm_lapic_irq *irq) { /* We can only post Fixed and LowPrio IRQs */ - return (irq->delivery_mode == dest_Fixed || - irq->delivery_mode == dest_LowestPrio); + return (irq->delivery_mode == APIC_DM_FIXED || + irq->delivery_mode == APIC_DM_LOWEST); } static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h index 6685e1218959..7063b5a43220 100644 --- a/arch/x86/include/asm/microcode_amd.h +++ b/arch/x86/include/asm/microcode_amd.h @@ -41,7 +41,7 @@ struct microcode_amd { unsigned int mpb[0]; }; -#define PATCH_MAX_SIZE PAGE_SIZE +#define PATCH_MAX_SIZE (3 * PAGE_SIZE) #ifdef CONFIG_MICROCODE_AMD extern void __init load_ucode_amd_bsp(unsigned int family); diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h index c215d2762488..e988bac0a4a1 100644 --- a/arch/x86/include/asm/module.h +++ b/arch/x86/include/asm/module.h @@ -13,64 +13,4 @@ struct mod_arch_specific { #endif }; -#ifdef CONFIG_X86_64 -/* X86_64 does not define MODULE_PROC_FAMILY */ -#elif defined CONFIG_M486SX -#define MODULE_PROC_FAMILY "486SX " -#elif defined CONFIG_M486 -#define MODULE_PROC_FAMILY "486 " -#elif defined CONFIG_M586 -#define MODULE_PROC_FAMILY "586 " -#elif defined CONFIG_M586TSC -#define MODULE_PROC_FAMILY "586TSC " -#elif defined CONFIG_M586MMX -#define MODULE_PROC_FAMILY "586MMX " -#elif defined CONFIG_MCORE2 -#define MODULE_PROC_FAMILY "CORE2 " -#elif defined CONFIG_MATOM -#define MODULE_PROC_FAMILY "ATOM " -#elif defined CONFIG_M686 -#define MODULE_PROC_FAMILY "686 " -#elif defined CONFIG_MPENTIUMII -#define MODULE_PROC_FAMILY "PENTIUMII " -#elif defined CONFIG_MPENTIUMIII -#define MODULE_PROC_FAMILY "PENTIUMIII " -#elif defined CONFIG_MPENTIUMM -#define MODULE_PROC_FAMILY "PENTIUMM " -#elif defined CONFIG_MPENTIUM4 -#define MODULE_PROC_FAMILY "PENTIUM4 " -#elif defined CONFIG_MK6 -#define MODULE_PROC_FAMILY "K6 " -#elif defined CONFIG_MK7 -#define MODULE_PROC_FAMILY "K7 " -#elif defined CONFIG_MK8 -#define MODULE_PROC_FAMILY "K8 " -#elif defined CONFIG_MELAN -#define MODULE_PROC_FAMILY "ELAN " -#elif defined CONFIG_MCRUSOE -#define MODULE_PROC_FAMILY "CRUSOE " -#elif defined CONFIG_MEFFICEON -#define MODULE_PROC_FAMILY "EFFICEON " -#elif defined CONFIG_MWINCHIPC6 -#define MODULE_PROC_FAMILY "WINCHIPC6 " -#elif defined CONFIG_MWINCHIP3D -#define MODULE_PROC_FAMILY "WINCHIP3D " -#elif defined CONFIG_MCYRIXIII -#define MODULE_PROC_FAMILY "CYRIXIII " -#elif defined CONFIG_MVIAC3_2 -#define MODULE_PROC_FAMILY "VIAC3-2 " -#elif defined CONFIG_MVIAC7 -#define MODULE_PROC_FAMILY "VIAC7 " -#elif defined CONFIG_MGEODEGX1 -#define MODULE_PROC_FAMILY "GEODEGX1 " -#elif defined CONFIG_MGEODE_LX -#define MODULE_PROC_FAMILY "GEODE " -#else -#error unknown processor family -#endif - -#ifdef CONFIG_X86_32 -# define MODULE_ARCH_VERMAGIC MODULE_PROC_FAMILY -#endif - #endif /* _ASM_X86_MODULE_H */ diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 1c42ecbe75cb..d30805ed323e 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -35,6 +35,8 @@ typedef int (*hyperv_fill_flush_list_func)( rdmsrl(HV_X64_MSR_SINT0 + int_num, val) #define hv_set_synint_state(int_num, val) \ wrmsrl(HV_X64_MSR_SINT0 + int_num, val) +#define hv_recommend_using_aeoi() \ + (!(ms_hyperv.hints & HV_DEPRECATING_AEOI_RECOMMENDED)) #define hv_get_crash_ctl(val) \ rdmsrl(HV_X64_MSR_CRASH_CTL, val) diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 07e95dcb40ad..7e9a281e2660 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -237,27 +237,6 @@ enum ssb_mitigation { extern char __indirect_thunk_start[]; extern char __indirect_thunk_end[]; -/* - * On VMEXIT we must ensure that no RSB predictions learned in the guest - * can be followed in the host, by overwriting the RSB completely. Both - * retpoline and IBRS mitigations for Spectre v2 need this; only on future - * CPUs with IBRS_ALL *might* it be avoided. - */ -static inline void vmexit_fill_RSB(void) -{ -#ifdef CONFIG_RETPOLINE - unsigned long loops; - - asm volatile (ANNOTATE_NOSPEC_ALTERNATIVE - ALTERNATIVE("jmp 910f", - __stringify(__FILL_RETURN_BUFFER(%0, RSB_CLEAR_LOOPS, %1)), - X86_FEATURE_RETPOLINE) - "910:" - : "=r" (loops), ASM_CALL_CONSTRAINT - : : "memory" ); -#endif -} - static __always_inline void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature) { diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h index 91e29b6a86a5..9804a7957f4e 100644 --- a/arch/x86/include/asm/stackprotector.h +++ b/arch/x86/include/asm/stackprotector.h @@ -55,8 +55,13 @@ /* * Initialize the stackprotector canary value. * - * NOTE: this must only be called from functions that never return, + * NOTE: this must only be called from functions that never return * and it must always be inlined. + * + * In addition, it should be called from a compilation unit for which + * stack protector is disabled. Alternatively, the caller should not end + * with a function call which gets tail-call optimized as that would + * lead to checking a modified canary value. */ static __always_inline void boot_init_stack_canary(void) { diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h index 499578f7e6d7..70fc159ebe69 100644 --- a/arch/x86/include/asm/unwind.h +++ b/arch/x86/include/asm/unwind.h @@ -19,7 +19,7 @@ struct unwind_state { #if defined(CONFIG_UNWINDER_ORC) bool signal, full_regs; unsigned long sp, bp, ip; - struct pt_regs *regs; + struct pt_regs *regs, *prev_regs; #elif defined(CONFIG_UNWINDER_FRAME_POINTER) bool got_irq; unsigned long *bp, *orig_sp, ip; diff --git a/arch/x86/include/asm/vermagic.h b/arch/x86/include/asm/vermagic.h new file mode 100644 index 000000000000..75884d2cdec3 --- /dev/null +++ b/arch/x86/include/asm/vermagic.h @@ -0,0 +1,68 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _ASM_VERMAGIC_H +#define _ASM_VERMAGIC_H + +#ifdef CONFIG_X86_64 +/* X86_64 does not define MODULE_PROC_FAMILY */ +#elif defined CONFIG_M486SX +#define MODULE_PROC_FAMILY "486SX " +#elif defined CONFIG_M486 +#define MODULE_PROC_FAMILY "486 " +#elif defined CONFIG_M586 +#define MODULE_PROC_FAMILY "586 " +#elif defined CONFIG_M586TSC +#define MODULE_PROC_FAMILY "586TSC " +#elif defined CONFIG_M586MMX +#define MODULE_PROC_FAMILY "586MMX " +#elif defined CONFIG_MCORE2 +#define MODULE_PROC_FAMILY "CORE2 " +#elif defined CONFIG_MATOM +#define MODULE_PROC_FAMILY "ATOM " +#elif defined CONFIG_M686 +#define MODULE_PROC_FAMILY "686 " +#elif defined CONFIG_MPENTIUMII +#define MODULE_PROC_FAMILY "PENTIUMII " +#elif defined CONFIG_MPENTIUMIII +#define MODULE_PROC_FAMILY "PENTIUMIII " +#elif defined CONFIG_MPENTIUMM +#define MODULE_PROC_FAMILY "PENTIUMM " +#elif defined CONFIG_MPENTIUM4 +#define MODULE_PROC_FAMILY "PENTIUM4 " +#elif defined CONFIG_MK6 +#define MODULE_PROC_FAMILY "K6 " +#elif defined CONFIG_MK7 +#define MODULE_PROC_FAMILY "K7 " +#elif defined CONFIG_MK8 +#define MODULE_PROC_FAMILY "K8 " +#elif defined CONFIG_MELAN +#define MODULE_PROC_FAMILY "ELAN " +#elif defined CONFIG_MCRUSOE +#define MODULE_PROC_FAMILY "CRUSOE " +#elif defined CONFIG_MEFFICEON +#define MODULE_PROC_FAMILY "EFFICEON " +#elif defined CONFIG_MWINCHIPC6 +#define MODULE_PROC_FAMILY "WINCHIPC6 " +#elif defined CONFIG_MWINCHIP3D +#define MODULE_PROC_FAMILY "WINCHIP3D " +#elif defined CONFIG_MCYRIXIII +#define MODULE_PROC_FAMILY "CYRIXIII " +#elif defined CONFIG_MVIAC3_2 +#define MODULE_PROC_FAMILY "VIAC3-2 " +#elif defined CONFIG_MVIAC7 +#define MODULE_PROC_FAMILY "VIAC7 " +#elif defined CONFIG_MGEODEGX1 +#define MODULE_PROC_FAMILY "GEODEGX1 " +#elif defined CONFIG_MGEODE_LX +#define MODULE_PROC_FAMILY "GEODE " +#else +#error unknown processor family +#endif + +#ifdef CONFIG_X86_32 +# define MODULE_ARCH_VERMAGIC MODULE_PROC_FAMILY +#else +# define MODULE_ARCH_VERMAGIC "" +#endif + +#endif /* _ASM_VERMAGIC_H */ diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 81b9c63dae1b..e53dda210cd7 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -352,8 +352,6 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen) * According to Intel, MFENCE can do the serialization here. */ asm volatile("mfence" : : : "memory"); - - printk_once(KERN_DEBUG "TSC deadline timer enabled\n"); return; } @@ -546,7 +544,7 @@ static struct clock_event_device lapic_clockevent = { }; static DEFINE_PER_CPU(struct clock_event_device, lapic_events); -static u32 hsx_deadline_rev(void) +static __init u32 hsx_deadline_rev(void) { switch (boot_cpu_data.x86_stepping) { case 0x02: return 0x3a; /* EP */ @@ -556,7 +554,7 @@ static u32 hsx_deadline_rev(void) return ~0U; } -static u32 bdx_deadline_rev(void) +static __init u32 bdx_deadline_rev(void) { switch (boot_cpu_data.x86_stepping) { case 0x02: return 0x00000011; @@ -568,7 +566,7 @@ static u32 bdx_deadline_rev(void) return ~0U; } -static u32 skx_deadline_rev(void) +static __init u32 skx_deadline_rev(void) { switch (boot_cpu_data.x86_stepping) { case 0x03: return 0x01000136; @@ -581,7 +579,7 @@ static u32 skx_deadline_rev(void) return ~0U; } -static const struct x86_cpu_id deadline_match[] = { +static const struct x86_cpu_id deadline_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL( HASWELL_X, &hsx_deadline_rev), X86_MATCH_INTEL_FAM6_MODEL( BROADWELL_X, 0x0b000020), X86_MATCH_INTEL_FAM6_MODEL( BROADWELL_D, &bdx_deadline_rev), @@ -603,18 +601,19 @@ static const struct x86_cpu_id deadline_match[] = { {}, }; -static void apic_check_deadline_errata(void) +static __init bool apic_validate_deadline_timer(void) { const struct x86_cpu_id *m; u32 rev; - if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER) || - boot_cpu_has(X86_FEATURE_HYPERVISOR)) - return; + if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) + return false; + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) + return true; m = x86_match_cpu(deadline_match); if (!m) - return; + return true; /* * Function pointers will have the MSB set due to address layout, @@ -626,11 +625,12 @@ static void apic_check_deadline_errata(void) rev = (u32)m->driver_data; if (boot_cpu_data.microcode >= rev) - return; + return true; setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); pr_err(FW_BUG "TSC_DEADLINE disabled due to Errata; " "please update microcode to version: 0x%x (or later)\n", rev); + return false; } /* @@ -2092,7 +2092,8 @@ void __init init_apic_mappings(void) { unsigned int new_apicid; - apic_check_deadline_errata(); + if (apic_validate_deadline_timer()) + pr_debug("TSC deadline timer available\n"); if (x2apic_mode) { boot_cpu_physical_apicid = read_apic_id(); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index bf08d4508ecb..a19a680542ce 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -1119,35 +1119,53 @@ void switch_to_sld(unsigned long tifn) sld_update_msr(!(tifn & _TIF_SLD)); } -#define SPLIT_LOCK_CPU(model) {X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY} - /* - * The following processors have the split lock detection feature. But - * since they don't have the IA32_CORE_CAPABILITIES MSR, the feature cannot - * be enumerated. Enable it by family and model matching on these - * processors. + * Bits in the IA32_CORE_CAPABILITIES are not architectural, so they should + * only be trusted if it is confirmed that a CPU model implements a + * specific feature at a particular bit position. + * + * The possible driver data field values: + * + * - 0: CPU models that are known to have the per-core split-lock detection + * feature even though they do not enumerate IA32_CORE_CAPABILITIES. + * + * - 1: CPU models which may enumerate IA32_CORE_CAPABILITIES and if so use + * bit 5 to enumerate the per-core split-lock detection feature. */ static const struct x86_cpu_id split_lock_cpu_ids[] __initconst = { - SPLIT_LOCK_CPU(INTEL_FAM6_ICELAKE_X), - SPLIT_LOCK_CPU(INTEL_FAM6_ICELAKE_L), + X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, 0), + X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L, 0), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT, 1), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, 1), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_L, 1), {} }; void __init cpu_set_core_cap_bits(struct cpuinfo_x86 *c) { - u64 ia32_core_caps = 0; + const struct x86_cpu_id *m; + u64 ia32_core_caps; + + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) + return; - if (c->x86_vendor != X86_VENDOR_INTEL) + m = x86_match_cpu(split_lock_cpu_ids); + if (!m) return; - if (cpu_has(c, X86_FEATURE_CORE_CAPABILITIES)) { - /* Enumerate features reported in IA32_CORE_CAPABILITIES MSR. */ + + switch (m->driver_data) { + case 0: + break; + case 1: + if (!cpu_has(c, X86_FEATURE_CORE_CAPABILITIES)) + return; rdmsrl(MSR_IA32_CORE_CAPS, ia32_core_caps); - } else if (!boot_cpu_has(X86_FEATURE_HYPERVISOR)) { - /* Enumerate split lock detection by family and model. */ - if (x86_match_cpu(split_lock_cpu_ids)) - ia32_core_caps |= MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT; + if (!(ia32_core_caps & MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT)) + return; + break; + default: + return; } - if (ia32_core_caps & MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT) - split_lock_setup(); + split_lock_setup(); } diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index caa032ce3fe3..ebf34c7bc8bc 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -227,8 +227,8 @@ static void __init ms_hyperv_init_platform(void) ms_hyperv.misc_features = cpuid_edx(HYPERV_CPUID_FEATURES); ms_hyperv.hints = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO); - pr_info("Hyper-V: features 0x%x, hints 0x%x\n", - ms_hyperv.features, ms_hyperv.hints); + pr_info("Hyper-V: features 0x%x, hints 0x%x, misc 0x%x\n", + ms_hyperv.features, ms_hyperv.hints, ms_hyperv.misc_features); ms_hyperv.max_vp_index = cpuid_eax(HYPERV_CPUID_IMPLEMENT_LIMITS); ms_hyperv.max_lp_index = cpuid_ebx(HYPERV_CPUID_IMPLEMENT_LIMITS); @@ -263,6 +263,16 @@ static void __init ms_hyperv_init_platform(void) cpuid_eax(HYPERV_CPUID_NESTED_FEATURES); } + /* + * Hyper-V expects to get crash register data or kmsg when + * crash enlightment is available and system crashes. Set + * crash_kexec_post_notifiers to be true to make sure that + * calling crash enlightment interface before running kdump + * kernel. + */ + if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) + crash_kexec_post_notifiers = true; + #ifdef CONFIG_X86_LOCAL_APIC if (ms_hyperv.features & HV_X64_ACCESS_FREQUENCY_MSRS && ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) { diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 89049b343c7a..d8cc5223b7ce 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -578,6 +578,8 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r) d->id = id; cpumask_set_cpu(cpu, &d->cpu_mask); + rdt_domain_reconfigure_cdp(r); + if (r->alloc_capable && domain_setup_ctrlval(r, d)) { kfree(d); return; diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 181c992f448c..3dd13f3a8b23 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -601,5 +601,6 @@ bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d); void __check_limbo(struct rdt_domain *d, bool force_free); bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r); bool cbm_validate_amd(char *buf, u32 *data, struct rdt_resource *r); +void rdt_domain_reconfigure_cdp(struct rdt_resource *r); #endif /* _ASM_X86_RESCTRL_INTERNAL_H */ diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 064e9ef44cd6..5a359d9fcc05 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -1859,6 +1859,19 @@ static int set_cache_qos_cfg(int level, bool enable) return 0; } +/* Restore the qos cfg state when a domain comes online */ +void rdt_domain_reconfigure_cdp(struct rdt_resource *r) +{ + if (!r->alloc_capable) + return; + + if (r == &rdt_resources_all[RDT_RESOURCE_L2DATA]) + l2_qos_cfg_update(&r->alloc_enabled); + + if (r == &rdt_resources_all[RDT_RESOURCE_L3DATA]) + l3_qos_cfg_update(&r->alloc_enabled); +} + /* * Enable or disable the MBA software controller * which helps user specify bandwidth in MBps. @@ -3072,7 +3085,8 @@ static int rdtgroup_rmdir(struct kernfs_node *kn) * If the rdtgroup is a mon group and parent directory * is a valid "mon_groups" directory, remove the mon group. */ - if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn) { + if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn && + rdtgrp != &rdtgroup_default) { if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP || rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { ret = rdtgroup_ctrl_remove(kn, rdtgrp); diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 87b97897a881..460ae7f66818 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -183,7 +183,8 @@ recursion_check: */ if (visit_mask) { if (*visit_mask & (1UL << info->type)) { - printk_deferred_once(KERN_WARNING "WARNING: stack recursion on stack type %d\n", info->type); + if (task == current) + printk_deferred_once(KERN_WARNING "WARNING: stack recursion on stack type %d\n", info->type); goto unknown; } *visit_mask |= 1UL << info->type; diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 37a0aeaf89e7..b0e641793be4 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -407,7 +407,8 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) set_vm_flush_reset_perms(trampoline); - set_memory_ro((unsigned long)trampoline, npages); + if (likely(system_state != SYSTEM_BOOTING)) + set_memory_ro((unsigned long)trampoline, npages); set_memory_x((unsigned long)trampoline, npages); return (unsigned long)trampoline; fail: @@ -415,6 +416,32 @@ fail: return 0; } +void set_ftrace_ops_ro(void) +{ + struct ftrace_ops *ops; + unsigned long start_offset; + unsigned long end_offset; + unsigned long npages; + unsigned long size; + + do_for_each_ftrace_op(ops, ftrace_ops_list) { + if (!(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP)) + continue; + + if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) { + start_offset = (unsigned long)ftrace_regs_caller; + end_offset = (unsigned long)ftrace_regs_caller_end; + } else { + start_offset = (unsigned long)ftrace_caller; + end_offset = (unsigned long)ftrace_epilogue; + } + size = end_offset - start_offset; + size = size + RET_SIZE + sizeof(void *); + npages = DIV_ROUND_UP(size, PAGE_SIZE); + set_memory_ro((unsigned long)ops->trampoline, npages); + } while_for_each_ftrace_op(ops); +} + static unsigned long calc_trampoline_call_offset(bool save_regs) { unsigned long start_offset; diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index fe3ab9632f3b..2f24c334a938 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -147,7 +147,7 @@ static inline void smpboot_restore_warm_reset_vector(void) *((volatile u32 *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = 0; } -static void init_freq_invariance(void); +static void init_freq_invariance(bool secondary); /* * Report back to the Boot Processor during boot time or to the caller processor @@ -185,7 +185,7 @@ static void smp_callin(void) */ set_cpu_sibling_map(raw_smp_processor_id()); - init_freq_invariance(); + init_freq_invariance(true); /* * Get our bogomips. @@ -266,6 +266,14 @@ static void notrace start_secondary(void *unused) wmb(); cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); + + /* + * Prevent tail call to cpu_startup_entry() because the stack protector + * guard has been changed a couple of function calls up, in + * boot_init_stack_canary() and must not be checked before tail calling + * another function. + */ + prevent_tail_call_optimization(); } /** @@ -1341,7 +1349,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) set_sched_topology(x86_topology); set_cpu_sibling_map(0); - init_freq_invariance(); + init_freq_invariance(false); smp_sanity_check(); switch (apic_intr_mode) { @@ -1877,9 +1885,6 @@ static bool knl_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, int err, i; u64 msr; - if (!x86_match_cpu(has_knl_turbo_ratio_limits)) - return false; - err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq); if (err) return false; @@ -1945,18 +1950,23 @@ static bool skx_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, int size) static bool core_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq) { + u64 msr; int err; err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq); if (err) return false; - err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, turbo_freq); + err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &msr); if (err) return false; - *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */ - *turbo_freq = (*turbo_freq >> 24) & 0xFF; /* 4C turbo */ + *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */ + *turbo_freq = (msr >> 24) & 0xFF; /* 4C turbo */ + + /* The CPU may have less than 4 cores */ + if (!*turbo_freq) + *turbo_freq = msr & 0xFF; /* 1C turbo */ return true; } @@ -1972,7 +1982,8 @@ static bool intel_set_max_freq_ratio(void) skx_set_max_freq_ratio(&base_freq, &turbo_freq, 1)) goto out; - if (knl_set_max_freq_ratio(&base_freq, &turbo_freq, 1)) + if (x86_match_cpu(has_knl_turbo_ratio_limits) && + knl_set_max_freq_ratio(&base_freq, &turbo_freq, 1)) goto out; if (x86_match_cpu(has_skx_turbo_ratio_limits) && @@ -1985,13 +1996,22 @@ static bool intel_set_max_freq_ratio(void) return false; out: + /* + * Some hypervisors advertise X86_FEATURE_APERFMPERF + * but then fill all MSR's with zeroes. + */ + if (!base_freq) { + pr_debug("Couldn't determine cpu base frequency, necessary for scale-invariant accounting.\n"); + return false; + } + arch_turbo_freq_ratio = div_u64(turbo_freq * SCHED_CAPACITY_SCALE, base_freq); arch_set_max_freq_ratio(turbo_disabled()); return true; } -static void init_counter_refs(void *arg) +static void init_counter_refs(void) { u64 aperf, mperf; @@ -2002,18 +2022,25 @@ static void init_counter_refs(void *arg) this_cpu_write(arch_prev_mperf, mperf); } -static void init_freq_invariance(void) +static void init_freq_invariance(bool secondary) { bool ret = false; - if (smp_processor_id() != 0 || !boot_cpu_has(X86_FEATURE_APERFMPERF)) + if (!boot_cpu_has(X86_FEATURE_APERFMPERF)) return; + if (secondary) { + if (static_branch_likely(&arch_scale_freq_key)) { + init_counter_refs(); + } + return; + } + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) ret = intel_set_max_freq_ratio(); if (ret) { - on_each_cpu(init_counter_refs, NULL, 1); + init_counter_refs(); static_branch_enable(&arch_scale_freq_key); } else { pr_debug("Couldn't determine max cpu frequency, necessary for scale-invariant accounting.\n"); diff --git a/arch/x86/kernel/umip.c b/arch/x86/kernel/umip.c index 4d732a444711..8d5cbe1bbb3b 100644 --- a/arch/x86/kernel/umip.c +++ b/arch/x86/kernel/umip.c @@ -81,7 +81,7 @@ #define UMIP_INST_SLDT 3 /* 0F 00 /0 */ #define UMIP_INST_STR 4 /* 0F 00 /1 */ -const char * const umip_insns[5] = { +static const char * const umip_insns[5] = { [UMIP_INST_SGDT] = "SGDT", [UMIP_INST_SIDT] = "SIDT", [UMIP_INST_SMSW] = "SMSW", diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c index a224b5ab103f..54226110bc7f 100644 --- a/arch/x86/kernel/unwind_frame.c +++ b/arch/x86/kernel/unwind_frame.c @@ -344,6 +344,9 @@ bad_address: if (IS_ENABLED(CONFIG_X86_32)) goto the_end; + if (state->task != current) + goto the_end; + if (state->regs) { printk_deferred_once(KERN_WARNING "WARNING: kernel stack regs at %p in %s:%d has bad 'bp' value %p\n", diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index e9cc182aa97e..7f969b2d240f 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -8,19 +8,21 @@ #include <asm/orc_lookup.h> #define orc_warn(fmt, ...) \ - printk_deferred_once(KERN_WARNING pr_fmt("WARNING: " fmt), ##__VA_ARGS__) + printk_deferred_once(KERN_WARNING "WARNING: " fmt, ##__VA_ARGS__) + +#define orc_warn_current(args...) \ +({ \ + if (state->task == current) \ + orc_warn(args); \ +}) extern int __start_orc_unwind_ip[]; extern int __stop_orc_unwind_ip[]; extern struct orc_entry __start_orc_unwind[]; extern struct orc_entry __stop_orc_unwind[]; -static DEFINE_MUTEX(sort_mutex); -int *cur_orc_ip_table = __start_orc_unwind_ip; -struct orc_entry *cur_orc_table = __start_orc_unwind; - -unsigned int lookup_num_blocks; -bool orc_init; +static bool orc_init __ro_after_init; +static unsigned int lookup_num_blocks __ro_after_init; static inline unsigned long orc_ip(const int *ip) { @@ -142,9 +144,6 @@ static struct orc_entry *orc_find(unsigned long ip) { static struct orc_entry *orc; - if (!orc_init) - return NULL; - if (ip == 0) return &null_orc_entry; @@ -189,6 +188,10 @@ static struct orc_entry *orc_find(unsigned long ip) #ifdef CONFIG_MODULES +static DEFINE_MUTEX(sort_mutex); +static int *cur_orc_ip_table = __start_orc_unwind_ip; +static struct orc_entry *cur_orc_table = __start_orc_unwind; + static void orc_sort_swap(void *_a, void *_b, int size) { struct orc_entry *orc_a, *orc_b; @@ -317,12 +320,19 @@ EXPORT_SYMBOL_GPL(unwind_get_return_address); unsigned long *unwind_get_return_address_ptr(struct unwind_state *state) { + struct task_struct *task = state->task; + if (unwind_done(state)) return NULL; if (state->regs) return &state->regs->ip; + if (task != current && state->sp == task->thread.sp) { + struct inactive_task_frame *frame = (void *)task->thread.sp; + return &frame->ret_addr; + } + if (state->sp) return (unsigned long *)state->sp - 1; @@ -381,9 +391,38 @@ static bool deref_stack_iret_regs(struct unwind_state *state, unsigned long addr return true; } +/* + * If state->regs is non-NULL, and points to a full pt_regs, just get the reg + * value from state->regs. + * + * Otherwise, if state->regs just points to IRET regs, and the previous frame + * had full regs, it's safe to get the value from the previous regs. This can + * happen when early/late IRQ entry code gets interrupted by an NMI. + */ +static bool get_reg(struct unwind_state *state, unsigned int reg_off, + unsigned long *val) +{ + unsigned int reg = reg_off/8; + + if (!state->regs) + return false; + + if (state->full_regs) { + *val = ((unsigned long *)state->regs)[reg]; + return true; + } + + if (state->prev_regs) { + *val = ((unsigned long *)state->prev_regs)[reg]; + return true; + } + + return false; +} + bool unwind_next_frame(struct unwind_state *state) { - unsigned long ip_p, sp, orig_ip = state->ip, prev_sp = state->sp; + unsigned long ip_p, sp, tmp, orig_ip = state->ip, prev_sp = state->sp; enum stack_type prev_type = state->stack_info.type; struct orc_entry *orc; bool indirect = false; @@ -445,43 +484,39 @@ bool unwind_next_frame(struct unwind_state *state) break; case ORC_REG_R10: - if (!state->regs || !state->full_regs) { - orc_warn("missing regs for base reg R10 at ip %pB\n", - (void *)state->ip); + if (!get_reg(state, offsetof(struct pt_regs, r10), &sp)) { + orc_warn_current("missing R10 value at %pB\n", + (void *)state->ip); goto err; } - sp = state->regs->r10; break; case ORC_REG_R13: - if (!state->regs || !state->full_regs) { - orc_warn("missing regs for base reg R13 at ip %pB\n", - (void *)state->ip); + if (!get_reg(state, offsetof(struct pt_regs, r13), &sp)) { + orc_warn_current("missing R13 value at %pB\n", + (void *)state->ip); goto err; } - sp = state->regs->r13; break; case ORC_REG_DI: - if (!state->regs || !state->full_regs) { - orc_warn("missing regs for base reg DI at ip %pB\n", - (void *)state->ip); + if (!get_reg(state, offsetof(struct pt_regs, di), &sp)) { + orc_warn_current("missing RDI value at %pB\n", + (void *)state->ip); goto err; } - sp = state->regs->di; break; case ORC_REG_DX: - if (!state->regs || !state->full_regs) { - orc_warn("missing regs for base reg DX at ip %pB\n", - (void *)state->ip); + if (!get_reg(state, offsetof(struct pt_regs, dx), &sp)) { + orc_warn_current("missing DX value at %pB\n", + (void *)state->ip); goto err; } - sp = state->regs->dx; break; default: - orc_warn("unknown SP base reg %d for ip %pB\n", + orc_warn("unknown SP base reg %d at %pB\n", orc->sp_reg, (void *)state->ip); goto err; } @@ -504,44 +539,48 @@ bool unwind_next_frame(struct unwind_state *state) state->sp = sp; state->regs = NULL; + state->prev_regs = NULL; state->signal = false; break; case ORC_TYPE_REGS: if (!deref_stack_regs(state, sp, &state->ip, &state->sp)) { - orc_warn("can't dereference registers at %p for ip %pB\n", - (void *)sp, (void *)orig_ip); + orc_warn_current("can't access registers at %pB\n", + (void *)orig_ip); goto err; } state->regs = (struct pt_regs *)sp; + state->prev_regs = NULL; state->full_regs = true; state->signal = true; break; case ORC_TYPE_REGS_IRET: if (!deref_stack_iret_regs(state, sp, &state->ip, &state->sp)) { - orc_warn("can't dereference iret registers at %p for ip %pB\n", - (void *)sp, (void *)orig_ip); + orc_warn_current("can't access iret registers at %pB\n", + (void *)orig_ip); goto err; } + if (state->full_regs) + state->prev_regs = state->regs; state->regs = (void *)sp - IRET_FRAME_OFFSET; state->full_regs = false; state->signal = true; break; default: - orc_warn("unknown .orc_unwind entry type %d for ip %pB\n", + orc_warn("unknown .orc_unwind entry type %d at %pB\n", orc->type, (void *)orig_ip); - break; + goto err; } /* Find BP: */ switch (orc->bp_reg) { case ORC_REG_UNDEFINED: - if (state->regs && state->full_regs) - state->bp = state->regs->bp; + if (get_reg(state, offsetof(struct pt_regs, bp), &tmp)) + state->bp = tmp; break; case ORC_REG_PREV_SP: @@ -564,8 +603,8 @@ bool unwind_next_frame(struct unwind_state *state) if (state->stack_info.type == prev_type && on_stack(&state->stack_info, (void *)state->sp, sizeof(long)) && state->sp <= prev_sp) { - orc_warn("stack going in the wrong direction? ip=%pB\n", - (void *)orig_ip); + orc_warn_current("stack going in the wrong direction? at %pB\n", + (void *)orig_ip); goto err; } @@ -588,17 +627,20 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, memset(state, 0, sizeof(*state)); state->task = task; + if (!orc_init) + goto err; + /* * Refuse to unwind the stack of a task while it's executing on another * CPU. This check is racy, but that's ok: the unwinder has other * checks to prevent it from going off the rails. */ if (task_on_another_cpu(task)) - goto done; + goto err; if (regs) { if (user_mode(regs)) - goto done; + goto the_end; state->ip = regs->ip; state->sp = regs->sp; @@ -631,6 +673,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, * generate some kind of backtrace if this happens. */ void *next_page = (void *)PAGE_ALIGN((unsigned long)state->sp); + state->error = true; if (get_stack_info(next_page, state->task, &state->stack_info, &state->stack_mask)) return; @@ -651,13 +694,14 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, /* Otherwise, skip ahead to the user-specified starting frame: */ while (!unwind_done(state) && (!on_stack(&state->stack_info, first_frame, sizeof(long)) || - state->sp <= (unsigned long)first_frame)) + state->sp < (unsigned long)first_frame)) unwind_next_frame(state); return; -done: +err: + state->error = true; +the_end: state->stack_info.type = STACK_TYPE_UNKNOWN; - return; } EXPORT_SYMBOL_GPL(__unwind_start); diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index a789759b7261..4a3081e9f4b5 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -3,6 +3,10 @@ ccflags-y += -Iarch/x86/kvm ccflags-$(CONFIG_KVM_WERROR) += -Werror +ifeq ($(CONFIG_FRAME_POINTER),y) +OBJECT_FILES_NON_STANDARD_vmenter.o := y +endif + KVM := ../../../virt/kvm kvm-y += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \ diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index bcefa9d4e57e..54d4b98b49e1 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1427,7 +1427,7 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *current_vcpu, u64 ingpa, */ kvm_make_vcpus_request_mask(kvm, KVM_REQ_TLB_FLUSH | KVM_REQUEST_NO_WAKEUP, - vcpu_mask, &hv_vcpu->tlb_flush); + NULL, vcpu_mask, &hv_vcpu->tlb_flush); ret_success: /* We always do full TLB flush, set rep_done = rep_cnt. */ diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 750ff0b29404..d057376bd3d3 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -225,12 +225,12 @@ static int ioapic_set_irq(struct kvm_ioapic *ioapic, unsigned int irq, } /* - * AMD SVM AVIC accelerate EOI write and do not trap, - * in-kernel IOAPIC will not be able to receive the EOI. - * In this case, we do lazy update of the pending EOI when - * trying to set IOAPIC irq. + * AMD SVM AVIC accelerate EOI write iff the interrupt is edge + * triggered, in which case the in-kernel IOAPIC will not be able + * to receive the EOI. In this case, we do a lazy update of the + * pending EOI when trying to set IOAPIC irq. */ - if (kvm_apicv_activated(ioapic->kvm)) + if (edge && kvm_apicv_activated(ioapic->kvm)) ioapic_lazy_update_eoi(ioapic, irq); /* diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 90a1ca939627..9a2a62e5afeb 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -19,6 +19,7 @@ #include <linux/kernel.h> #include <asm/msr-index.h> +#include <asm/debugreg.h> #include "kvm_emulate.h" #include "trace.h" @@ -267,7 +268,7 @@ void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa, svm->vmcb->save.rsp = nested_vmcb->save.rsp; svm->vmcb->save.rip = nested_vmcb->save.rip; svm->vmcb->save.dr7 = nested_vmcb->save.dr7; - svm->vmcb->save.dr6 = nested_vmcb->save.dr6; + svm->vcpu.arch.dr6 = nested_vmcb->save.dr6; svm->vmcb->save.cpl = nested_vmcb->save.cpl; svm->nested.vmcb_msrpm = nested_vmcb->control.msrpm_base_pa & ~0x0fffULL; @@ -482,7 +483,7 @@ int nested_svm_vmexit(struct vcpu_svm *svm) nested_vmcb->save.rsp = vmcb->save.rsp; nested_vmcb->save.rax = vmcb->save.rax; nested_vmcb->save.dr7 = vmcb->save.dr7; - nested_vmcb->save.dr6 = vmcb->save.dr6; + nested_vmcb->save.dr6 = svm->vcpu.arch.dr6; nested_vmcb->save.cpl = vmcb->save.cpl; nested_vmcb->control.int_ctl = vmcb->control.int_ctl; @@ -606,26 +607,45 @@ static int nested_svm_exit_handled_msr(struct vcpu_svm *svm) /* DB exceptions for our internal use must not cause vmexit */ static int nested_svm_intercept_db(struct vcpu_svm *svm) { - unsigned long dr6; + unsigned long dr6 = svm->vmcb->save.dr6; + + /* Always catch it and pass it to userspace if debugging. */ + if (svm->vcpu.guest_debug & + (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) + return NESTED_EXIT_HOST; /* if we're not singlestepping, it's not ours */ if (!svm->nmi_singlestep) - return NESTED_EXIT_DONE; + goto reflected_db; /* if it's not a singlestep exception, it's not ours */ - if (kvm_get_dr(&svm->vcpu, 6, &dr6)) - return NESTED_EXIT_DONE; if (!(dr6 & DR6_BS)) - return NESTED_EXIT_DONE; + goto reflected_db; /* if the guest is singlestepping, it should get the vmexit */ if (svm->nmi_singlestep_guest_rflags & X86_EFLAGS_TF) { disable_nmi_singlestep(svm); - return NESTED_EXIT_DONE; + goto reflected_db; } /* it's ours, the nested hypervisor must not see this one */ return NESTED_EXIT_HOST; + +reflected_db: + /* + * Synchronize guest DR6 here just like in kvm_deliver_exception_payload; + * it will be moved into the nested VMCB by nested_svm_vmexit. Once + * exceptions will be moved to svm_check_nested_events, all this stuff + * will just go away and we could just return NESTED_EXIT_HOST + * unconditionally. db_interception will queue the exception, which + * will be processed by svm_check_nested_events if a nested vmexit is + * required, and we will just use kvm_deliver_exception_payload to copy + * the payload to DR6 before vmexit. + */ + WARN_ON(svm->vcpu.arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT); + svm->vcpu.arch.dr6 &= ~(DR_TRAP_BITS | DR6_RTM); + svm->vcpu.arch.dr6 |= dr6 & ~DR6_FIXED_1; + return NESTED_EXIT_DONE; } static int nested_svm_intercept_ioio(struct vcpu_svm *svm) @@ -682,6 +702,9 @@ static int nested_svm_intercept(struct vcpu_svm *svm) if (svm->nested.intercept_exceptions & excp_bits) { if (exit_code == SVM_EXIT_EXCP_BASE + DB_VECTOR) vmexit = nested_svm_intercept_db(svm); + else if (exit_code == SVM_EXIT_EXCP_BASE + BP_VECTOR && + svm->vcpu.guest_debug & KVM_GUESTDBG_USE_SW_BP) + vmexit = NESTED_EXIT_HOST; else vmexit = NESTED_EXIT_DONE; } diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 0e3fc311d7da..89f7f3aebd31 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -12,6 +12,7 @@ #include <linux/kernel.h> #include <linux/highmem.h> #include <linux/psp-sev.h> +#include <linux/pagemap.h> #include <linux/swap.h> #include "x86.h" @@ -344,7 +345,7 @@ static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr, return NULL; /* Pin the user virtual address. */ - npinned = get_user_pages_fast(uaddr, npages, FOLL_WRITE, pages); + npinned = get_user_pages_fast(uaddr, npages, write ? FOLL_WRITE : 0, pages); if (npinned != npages) { pr_err("SEV: Failure locking %lu pages.\n", npages); goto err; @@ -1117,7 +1118,7 @@ int __init sev_hardware_setup(void) /* Maximum number of encrypted guests supported simultaneously */ max_sev_asid = cpuid_ecx(0x8000001F); - if (!max_sev_asid) + if (!svm_sev_enabled()) return 1; /* Minimum ASID value that should be used for SEV guest */ @@ -1156,6 +1157,9 @@ err: void sev_hardware_teardown(void) { + if (!svm_sev_enabled()) + return; + bitmap_free(sev_asid_bitmap); bitmap_free(sev_reclaim_asid_bitmap); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 2be5bbae3a40..a862c768fd54 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1672,17 +1672,14 @@ static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *sd) mark_dirty(svm->vmcb, VMCB_ASID); } -static u64 svm_get_dr6(struct kvm_vcpu *vcpu) +static void svm_set_dr6(struct vcpu_svm *svm, unsigned long value) { - return to_svm(vcpu)->vmcb->save.dr6; -} - -static void svm_set_dr6(struct kvm_vcpu *vcpu, unsigned long value) -{ - struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb *vmcb = svm->vmcb; - svm->vmcb->save.dr6 = value; - mark_dirty(svm->vmcb, VMCB_DR); + if (unlikely(value != vmcb->save.dr6)) { + vmcb->save.dr6 = value; + mark_dirty(vmcb, VMCB_DR); + } } static void svm_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) @@ -1693,9 +1690,12 @@ static void svm_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) get_debugreg(vcpu->arch.db[1], 1); get_debugreg(vcpu->arch.db[2], 2); get_debugreg(vcpu->arch.db[3], 3); - vcpu->arch.dr6 = svm_get_dr6(vcpu); + /* + * We cannot reset svm->vmcb->save.dr6 to DR6_FIXED_1|DR6_RTM here, + * because db_interception might need it. We can do it before vmentry. + */ + vcpu->arch.dr6 = svm->vmcb->save.dr6; vcpu->arch.dr7 = svm->vmcb->save.dr7; - vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_WONT_EXIT; set_dr_intercepts(svm); } @@ -1739,7 +1739,8 @@ static int db_interception(struct vcpu_svm *svm) if (!(svm->vcpu.guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) && !svm->nmi_singlestep) { - kvm_queue_exception(&svm->vcpu, DB_VECTOR); + u32 payload = (svm->vmcb->save.dr6 ^ DR6_RTM) & ~DR6_FIXED_1; + kvm_queue_exception_p(&svm->vcpu, DB_VECTOR, payload); return 1; } @@ -1752,6 +1753,8 @@ static int db_interception(struct vcpu_svm *svm) if (svm->vcpu.guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) { kvm_run->exit_reason = KVM_EXIT_DEBUG; + kvm_run->debug.arch.dr6 = svm->vmcb->save.dr6; + kvm_run->debug.arch.dr7 = svm->vmcb->save.dr7; kvm_run->debug.arch.pc = svm->vmcb->save.cs.base + svm->vmcb->save.rip; kvm_run->debug.arch.exception = DB_VECTOR; @@ -3276,7 +3279,7 @@ static void svm_cancel_injection(struct kvm_vcpu *vcpu) svm_complete_interrupts(svm); } -bool __svm_vcpu_run(unsigned long vmcb_pa, unsigned long *regs); +void __svm_vcpu_run(unsigned long vmcb_pa, unsigned long *regs); static void svm_vcpu_run(struct kvm_vcpu *vcpu) { @@ -3315,6 +3318,15 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) svm->vmcb->save.cr2 = vcpu->arch.cr2; + /* + * Run with all-zero DR6 unless needed, so that we can get the exact cause + * of a #DB. + */ + if (unlikely(svm->vcpu.arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) + svm_set_dr6(svm, vcpu->arch.dr6); + else + svm_set_dr6(svm, DR6_FIXED_1 | DR6_RTM); + clgi(); kvm_load_guest_xsave_state(vcpu); @@ -3330,13 +3342,8 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) */ x86_spec_ctrl_set_guest(svm->spec_ctrl, svm->virt_spec_ctrl); - local_irq_enable(); - __svm_vcpu_run(svm->vmcb_pa, (unsigned long *)&svm->vcpu.arch.regs); - /* Eliminate branch target predictions from guest mode */ - vmexit_fill_RSB(); - #ifdef CONFIG_X86_64 wrmsrl(MSR_GS_BASE, svm->host.gs_base); #else @@ -3366,8 +3373,6 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) reload_tss(vcpu); - local_irq_disable(); - x86_spec_ctrl_restore_host(svm->spec_ctrl, svm->virt_spec_ctrl); vcpu->arch.cr2 = svm->vmcb->save.cr2; @@ -3411,7 +3416,6 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) mark_all_clean(svm->vmcb); } -STACK_FRAME_NON_STANDARD(svm_vcpu_run); static void svm_load_mmu_pgd(struct kvm_vcpu *vcpu, unsigned long root) { @@ -3937,8 +3941,6 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .set_idt = svm_set_idt, .get_gdt = svm_get_gdt, .set_gdt = svm_set_gdt, - .get_dr6 = svm_get_dr6, - .set_dr6 = svm_set_dr6, .set_dr7 = svm_set_dr7, .sync_dirty_debug_regs = svm_sync_dirty_debug_regs, .cache_reg = svm_cache_reg, diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S index fa1af90067e9..bf944334003a 100644 --- a/arch/x86/kvm/svm/vmenter.S +++ b/arch/x86/kvm/svm/vmenter.S @@ -3,6 +3,7 @@ #include <asm/asm.h> #include <asm/bitsperlong.h> #include <asm/kvm_vcpu_regs.h> +#include <asm/nospec-branch.h> #define WORD_SIZE (BITS_PER_LONG / 8) @@ -35,7 +36,6 @@ */ SYM_FUNC_START(__svm_vcpu_run) push %_ASM_BP - mov %_ASM_SP, %_ASM_BP #ifdef CONFIG_X86_64 push %r15 push %r14 @@ -78,6 +78,7 @@ SYM_FUNC_START(__svm_vcpu_run) pop %_ASM_AX /* Enter guest mode */ + sti 1: vmload %_ASM_AX jmp 3f 2: cmpb $0, kvm_rebooting @@ -99,6 +100,13 @@ SYM_FUNC_START(__svm_vcpu_run) ud2 _ASM_EXTABLE(5b, 6b) 7: + cli + +#ifdef CONFIG_RETPOLINE + /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ + FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE +#endif + /* "POP" @regs to RAX. */ pop %_ASM_AX diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index cbc9ea2de28f..e44f33c82332 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -5165,7 +5165,7 @@ static int handle_invept(struct kvm_vcpu *vcpu) */ break; default: - BUG_ON(1); + BUG(); break; } @@ -5533,8 +5533,25 @@ static bool nested_vmx_exit_handled_vmcs_access(struct kvm_vcpu *vcpu, return 1 & (b >> (field & 7)); } +static bool nested_vmx_exit_handled_mtf(struct vmcs12 *vmcs12) +{ + u32 entry_intr_info = vmcs12->vm_entry_intr_info_field; + + if (nested_cpu_has_mtf(vmcs12)) + return true; + + /* + * An MTF VM-exit may be injected into the guest by setting the + * interruption-type to 7 (other event) and the vector field to 0. Such + * is the case regardless of the 'monitor trap flag' VM-execution + * control. + */ + return entry_intr_info == (INTR_INFO_VALID_MASK + | INTR_TYPE_OTHER_EVENT); +} + /* - * Return 1 if we should exit from L2 to L1 to handle an exit, or 0 if we + * Return true if we should exit from L2 to L1 to handle an exit, or false if we * should handle it ourselves in L0 (and then continue L2). Only call this * when in is_guest_mode (L2). */ @@ -5633,7 +5650,7 @@ bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason) case EXIT_REASON_MWAIT_INSTRUCTION: return nested_cpu_has(vmcs12, CPU_BASED_MWAIT_EXITING); case EXIT_REASON_MONITOR_TRAP_FLAG: - return nested_cpu_has_mtf(vmcs12); + return nested_vmx_exit_handled_mtf(vmcs12); case EXIT_REASON_MONITOR_INSTRUCTION: return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_EXITING); case EXIT_REASON_PAUSE_INSTRUCTION: diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 87f3f24fef37..51d1a82742fd 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -82,6 +82,9 @@ SYM_FUNC_START(vmx_vmexit) /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE + /* Clear RFLAGS.CF and RFLAGS.ZF to preserve VM-Exit, i.e. !VM-Fail. */ + or $1, %_ASM_AX + pop %_ASM_AX .Lvmexit_skip_rsb: #endif diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 83050977490c..89c766fad889 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1372,7 +1372,6 @@ void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) vmx_vcpu_pi_load(vcpu, cpu); - vmx->host_pkru = read_pkru(); vmx->host_debugctlmsr = get_debugctlmsr(); } @@ -4572,7 +4571,7 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu, */ static void kvm_machine_check(void) { -#if defined(CONFIG_X86_MCE) && defined(CONFIG_X86_64) +#if defined(CONFIG_X86_MCE) struct pt_regs regs = { .cs = 3, /* Fake ring 3 no matter what the guest ran on */ .flags = X86_EFLAGS_IF, @@ -4677,15 +4676,13 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) dr6 = vmcs_readl(EXIT_QUALIFICATION); if (!(vcpu->guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) { - vcpu->arch.dr6 &= ~DR_TRAP_BITS; - vcpu->arch.dr6 |= dr6 | DR6_RTM; if (is_icebp(intr_info)) WARN_ON(!skip_emulated_instruction(vcpu)); - kvm_queue_exception(vcpu, DB_VECTOR); + kvm_queue_exception_p(vcpu, DB_VECTOR, dr6); return 1; } - kvm_run->debug.arch.dr6 = dr6 | DR6_FIXED_1; + kvm_run->debug.arch.dr6 = dr6 | DR6_FIXED_1 | DR6_RTM; kvm_run->debug.arch.dr7 = vmcs_readl(GUEST_DR7); /* fall through */ case BP_VECTOR: @@ -4929,16 +4926,14 @@ static int handle_dr(struct kvm_vcpu *vcpu) * guest debugging itself. */ if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) { - vcpu->run->debug.arch.dr6 = vcpu->arch.dr6; + vcpu->run->debug.arch.dr6 = DR6_BD | DR6_RTM | DR6_FIXED_1; vcpu->run->debug.arch.dr7 = dr7; vcpu->run->debug.arch.pc = kvm_get_linear_rip(vcpu); vcpu->run->debug.arch.exception = DB_VECTOR; vcpu->run->exit_reason = KVM_EXIT_DEBUG; return 0; } else { - vcpu->arch.dr6 &= ~DR_TRAP_BITS; - vcpu->arch.dr6 |= DR6_BD | DR6_RTM; - kvm_queue_exception(vcpu, DB_VECTOR); + kvm_queue_exception_p(vcpu, DB_VECTOR, DR6_BD); return 1; } } @@ -4969,15 +4964,6 @@ static int handle_dr(struct kvm_vcpu *vcpu) return kvm_skip_emulated_instruction(vcpu); } -static u64 vmx_get_dr6(struct kvm_vcpu *vcpu) -{ - return vcpu->arch.dr6; -} - -static void vmx_set_dr6(struct kvm_vcpu *vcpu, unsigned long val) -{ -} - static void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) { get_debugreg(vcpu->arch.db[0], 0); @@ -6577,11 +6563,6 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) kvm_load_guest_xsave_state(vcpu); - if (static_cpu_has(X86_FEATURE_PKU) && - kvm_read_cr4_bits(vcpu, X86_CR4_PKE) && - vcpu->arch.pkru != vmx->host_pkru) - __write_pkru(vcpu->arch.pkru); - pt_guest_enter(vmx); if (vcpu_to_pmu(vcpu)->version) @@ -6671,18 +6652,6 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) pt_guest_exit(vmx); - /* - * eager fpu is enabled if PKEY is supported and CR4 is switched - * back on host, so it is safe to read guest PKRU from current - * XSAVE. - */ - if (static_cpu_has(X86_FEATURE_PKU) && - kvm_read_cr4_bits(vcpu, X86_CR4_PKE)) { - vcpu->arch.pkru = rdpkru(); - if (vcpu->arch.pkru != vmx->host_pkru) - __write_pkru(vmx->host_pkru); - } - kvm_load_host_xsave_state(vcpu); vmx->nested.nested_run_pending = 0; @@ -7740,8 +7709,6 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .set_idt = vmx_set_idt, .get_gdt = vmx_get_gdt, .set_gdt = vmx_set_gdt, - .get_dr6 = vmx_get_dr6, - .set_dr6 = vmx_set_dr6, .set_dr7 = vmx_set_dr7, .sync_dirty_debug_regs = vmx_sync_dirty_debug_regs, .cache_reg = vmx_cache_reg, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 3bf2ecafd027..c17e6eb9ad43 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -572,11 +572,12 @@ void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr) } EXPORT_SYMBOL_GPL(kvm_requeue_exception); -static void kvm_queue_exception_p(struct kvm_vcpu *vcpu, unsigned nr, - unsigned long payload) +void kvm_queue_exception_p(struct kvm_vcpu *vcpu, unsigned nr, + unsigned long payload) { kvm_multiple_exception(vcpu, nr, false, 0, true, payload, false); } +EXPORT_SYMBOL_GPL(kvm_queue_exception_p); static void kvm_queue_exception_e_p(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code, unsigned long payload) @@ -836,11 +837,25 @@ void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu) vcpu->arch.ia32_xss != host_xss) wrmsrl(MSR_IA32_XSS, vcpu->arch.ia32_xss); } + + if (static_cpu_has(X86_FEATURE_PKU) && + (kvm_read_cr4_bits(vcpu, X86_CR4_PKE) || + (vcpu->arch.xcr0 & XFEATURE_MASK_PKRU)) && + vcpu->arch.pkru != vcpu->arch.host_pkru) + __write_pkru(vcpu->arch.pkru); } EXPORT_SYMBOL_GPL(kvm_load_guest_xsave_state); void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu) { + if (static_cpu_has(X86_FEATURE_PKU) && + (kvm_read_cr4_bits(vcpu, X86_CR4_PKE) || + (vcpu->arch.xcr0 & XFEATURE_MASK_PKRU))) { + vcpu->arch.pkru = rdpkru(); + if (vcpu->arch.pkru != vcpu->arch.host_pkru) + __write_pkru(vcpu->arch.host_pkru); + } + if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) { if (vcpu->arch.xcr0 != host_xcr0) @@ -926,19 +941,6 @@ EXPORT_SYMBOL_GPL(kvm_set_xcr); __reserved_bits; \ }) -static u64 kvm_host_cr4_reserved_bits(struct cpuinfo_x86 *c) -{ - u64 reserved_bits = __cr4_reserved_bits(cpu_has, c); - - if (kvm_cpu_cap_has(X86_FEATURE_LA57)) - reserved_bits &= ~X86_CR4_LA57; - - if (kvm_cpu_cap_has(X86_FEATURE_UMIP)) - reserved_bits &= ~X86_CR4_UMIP; - - return reserved_bits; -} - static int kvm_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { if (cr4 & cr4_reserved_bits) @@ -1058,12 +1060,6 @@ static void kvm_update_dr0123(struct kvm_vcpu *vcpu) } } -static void kvm_update_dr6(struct kvm_vcpu *vcpu) -{ - if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) - kvm_x86_ops.set_dr6(vcpu, vcpu->arch.dr6); -} - static void kvm_update_dr7(struct kvm_vcpu *vcpu) { unsigned long dr7; @@ -1103,7 +1099,6 @@ static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) if (val & 0xffffffff00000000ULL) return -1; /* #GP */ vcpu->arch.dr6 = (val & DR6_VOLATILE) | kvm_dr6_fixed(vcpu); - kvm_update_dr6(vcpu); break; case 5: /* fall through */ @@ -1139,10 +1134,7 @@ int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val) case 4: /* fall through */ case 6: - if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) - *val = vcpu->arch.dr6; - else - *val = kvm_x86_ops.get_dr6(vcpu); + *val = vcpu->arch.dr6; break; case 5: /* fall through */ @@ -3060,6 +3052,17 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_PERF_CTL: case MSR_AMD64_DC_CFG: case MSR_F15H_EX_CFG: + /* + * Intel Sandy Bridge CPUs must support the RAPL (running average power + * limit) MSRs. Just return 0, as we do not want to expose the host + * data here. Do not conditionalize this on CPUID, as KVM does not do + * so for existing CPU-specific MSRs. + */ + case MSR_RAPL_POWER_UNIT: + case MSR_PP0_ENERGY_STATUS: /* Power plane 0 (core) */ + case MSR_PP1_ENERGY_STATUS: /* Power plane 1 (graphics uncore) */ + case MSR_PKG_ENERGY_STATUS: /* Total package */ + case MSR_DRAM_ENERGY_STATUS: /* DRAM controller */ msr_info->data = 0; break; case MSR_F15H_PERF_CTL0 ... MSR_F15H_PERF_CTR5: @@ -3374,6 +3377,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_GET_MSR_FEATURES: case KVM_CAP_MSR_PLATFORM_INFO: case KVM_CAP_EXCEPTION_PAYLOAD: + case KVM_CAP_SET_GUEST_DEBUG: r = 1; break; case KVM_CAP_SYNC_REGS: @@ -3559,6 +3563,9 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvm_x86_ops.vcpu_load(vcpu, cpu); + /* Save host pkru register if supported */ + vcpu->arch.host_pkru = read_pkru(); + /* Apply any externally detected TSC adjustments (due to suspend) */ if (unlikely(vcpu->arch.tsc_offset_adjustment)) { adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment); @@ -3752,7 +3759,7 @@ static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu, unsigned bank_num = mcg_cap & 0xff, bank; r = -EINVAL; - if (!bank_num || bank_num >= KVM_MAX_MCE_BANKS) + if (!bank_num || bank_num > KVM_MAX_MCE_BANKS) goto out; if (mcg_cap & ~(kvm_mce_cap_supported | 0xff | 0xff0000)) goto out; @@ -4010,7 +4017,6 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, memcpy(vcpu->arch.db, dbgregs->db, sizeof(vcpu->arch.db)); kvm_update_dr0123(vcpu); vcpu->arch.dr6 = dbgregs->dr6; - kvm_update_dr6(vcpu); vcpu->arch.dr7 = dbgregs->dr7; kvm_update_dr7(vcpu); @@ -5049,10 +5055,13 @@ set_identity_unlock: r = -EFAULT; if (copy_from_user(&u.ps, argp, sizeof(u.ps))) goto out; + mutex_lock(&kvm->lock); r = -ENXIO; if (!kvm->arch.vpit) - goto out; + goto set_pit_out; r = kvm_vm_ioctl_set_pit(kvm, &u.ps); +set_pit_out: + mutex_unlock(&kvm->lock); break; } case KVM_GET_PIT2: { @@ -5072,10 +5081,13 @@ set_identity_unlock: r = -EFAULT; if (copy_from_user(&u.ps2, argp, sizeof(u.ps2))) goto out; + mutex_lock(&kvm->lock); r = -ENXIO; if (!kvm->arch.vpit) - goto out; + goto set_pit2_out; r = kvm_vm_ioctl_set_pit2(kvm, &u.ps2); +set_pit2_out: + mutex_unlock(&kvm->lock); break; } case KVM_REINJECT_CONTROL: { @@ -6654,7 +6666,7 @@ static int kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu) if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { kvm_run->debug.arch.dr6 = DR6_BS | DR6_FIXED_1 | DR6_RTM; - kvm_run->debug.arch.pc = vcpu->arch.singlestep_rip; + kvm_run->debug.arch.pc = kvm_get_linear_rip(vcpu); kvm_run->debug.arch.exception = DB_VECTOR; kvm_run->exit_reason = KVM_EXIT_DEBUG; return 0; @@ -6714,9 +6726,7 @@ static bool kvm_vcpu_check_breakpoint(struct kvm_vcpu *vcpu, int *r) vcpu->arch.db); if (dr6 != 0) { - vcpu->arch.dr6 &= ~DR_TRAP_BITS; - vcpu->arch.dr6 |= dr6 | DR6_RTM; - kvm_queue_exception(vcpu, DB_VECTOR); + kvm_queue_exception_p(vcpu, DB_VECTOR, dr6); *r = 1; return true; } @@ -8037,7 +8047,7 @@ void kvm_make_scan_ioapic_request_mask(struct kvm *kvm, zalloc_cpumask_var(&cpus, GFP_ATOMIC); kvm_make_vcpus_request_mask(kvm, KVM_REQ_SCAN_IOAPIC, - vcpu_bitmap, cpus); + NULL, vcpu_bitmap, cpus); free_cpumask_var(cpus); } @@ -8067,6 +8077,7 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_update_apicv); */ void kvm_request_apicv_update(struct kvm *kvm, bool activate, ulong bit) { + struct kvm_vcpu *except; unsigned long old, new, expected; if (!kvm_x86_ops.check_apicv_inhibit_reasons || @@ -8091,7 +8102,17 @@ void kvm_request_apicv_update(struct kvm *kvm, bool activate, ulong bit) trace_kvm_apicv_update_request(activate, bit); if (kvm_x86_ops.pre_update_apicv_exec_ctrl) kvm_x86_ops.pre_update_apicv_exec_ctrl(kvm, activate); - kvm_make_all_cpus_request(kvm, KVM_REQ_APICV_UPDATE); + + /* + * Sending request to update APICV for all other vcpus, + * while update the calling vcpu immediately instead of + * waiting for another #VMEXIT to handle the request. + */ + except = kvm_get_running_vcpu(); + kvm_make_all_cpus_request_except(kvm, KVM_REQ_APICV_UPDATE, + except); + if (except) + kvm_vcpu_update_apicv(except); } EXPORT_SYMBOL_GPL(kvm_request_apicv_update); @@ -8415,7 +8436,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) WARN_ON(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP); kvm_x86_ops.sync_dirty_debug_regs(vcpu); kvm_update_dr0123(vcpu); - kvm_update_dr6(vcpu); kvm_update_dr7(vcpu); vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD; } @@ -9476,7 +9496,6 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) memset(vcpu->arch.db, 0, sizeof(vcpu->arch.db)); kvm_update_dr0123(vcpu); vcpu->arch.dr6 = DR6_INIT; - kvm_update_dr6(vcpu); vcpu->arch.dr7 = DR7_FIXED_1; kvm_update_dr7(vcpu); @@ -9658,7 +9677,9 @@ int kvm_arch_hardware_setup(void *opaque) if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES)) supported_xss = 0; - cr4_reserved_bits = kvm_host_cr4_reserved_bits(&boot_cpu_data); +#define __kvm_cpu_cap_has(UNUSED_, f) kvm_cpu_cap_has(f) + cr4_reserved_bits = __cr4_reserved_bits(__kvm_cpu_cap_has, UNUSED_); +#undef __kvm_cpu_cap_has if (kvm_has_tsc_control) { /* @@ -9690,7 +9711,8 @@ int kvm_arch_check_processor_compat(void *opaque) WARN_ON(!irqs_disabled()); - if (kvm_host_cr4_reserved_bits(c) != cr4_reserved_bits) + if (__cr4_reserved_bits(cpu_has, c) != + __cr4_reserved_bits(cpu_has, &boot_cpu_data)) return -EIO; return ops->check_processor_compatibility(); diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 3b289c2f75cd..8b5f73f5e207 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -54,6 +54,7 @@ #include <asm/init.h> #include <asm/uv/uv.h> #include <asm/setup.h> +#include <asm/ftrace.h> #include "mm_internal.h" @@ -1291,6 +1292,8 @@ void mark_rodata_ro(void) all_end = roundup((unsigned long)_brk_end, PMD_SIZE); set_memory_nx(text_end, (all_end - text_end) >> PAGE_SHIFT); + set_ftrace_ops_ro(); + #ifdef CONFIG_CPA_DEBUG printk(KERN_INFO "Testing CPA: undo %lx-%lx\n", start, end); set_memory_rw(start, (end-start) >> PAGE_SHIFT); diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c index 109325d77b3e..43fd19b3f118 100644 --- a/arch/x86/mm/mmio-mod.c +++ b/arch/x86/mm/mmio-mod.c @@ -372,7 +372,7 @@ static void enter_uniprocessor(void) int cpu; int err; - if (downed_cpus == NULL && + if (!cpumask_available(downed_cpus) && !alloc_cpumask_var(&downed_cpus, GFP_KERNEL)) { pr_notice("Failed to allocate mask\n"); goto out; @@ -402,7 +402,7 @@ static void leave_uniprocessor(void) int cpu; int err; - if (downed_cpus == NULL || cpumask_weight(downed_cpus) == 0) + if (!cpumask_available(downed_cpus) || cpumask_weight(downed_cpus) == 0) return; pr_notice("Re-enabling CPUs...\n"); for_each_cpu(cpu, downed_cpus) { diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index 59eca6a94ce7..b8c55a2e402d 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -43,7 +43,8 @@ struct cpa_data { unsigned long pfn; unsigned int flags; unsigned int force_split : 1, - force_static_prot : 1; + force_static_prot : 1, + force_flush_all : 1; struct page **pages; }; @@ -355,10 +356,10 @@ static void cpa_flush(struct cpa_data *data, int cache) return; } - if (cpa->numpages <= tlb_single_page_flush_ceiling) - on_each_cpu(__cpa_flush_tlb, cpa, 1); - else + if (cpa->force_flush_all || cpa->numpages > tlb_single_page_flush_ceiling) flush_tlb_all(); + else + on_each_cpu(__cpa_flush_tlb, cpa, 1); if (!cache) return; @@ -1598,6 +1599,8 @@ static int cpa_process_alias(struct cpa_data *cpa) alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY); alias_cpa.curpage = 0; + cpa->force_flush_all = 1; + ret = __change_page_attr_set_clr(&alias_cpa, 0); if (ret) return ret; @@ -1618,6 +1621,7 @@ static int cpa_process_alias(struct cpa_data *cpa) alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY); alias_cpa.curpage = 0; + cpa->force_flush_all = 1; /* * The high mapping range is imprecise, so ignore the * return value. diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 5ea7c2cf7ab4..42b6709e6dc7 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -158,6 +158,19 @@ static bool is_ereg(u32 reg) BIT(BPF_REG_AX)); } +/* + * is_ereg_8l() == true if BPF register 'reg' is mapped to access x86-64 + * lower 8-bit registers dil,sil,bpl,spl,r8b..r15b, which need extra byte + * of encoding. al,cl,dl,bl have simpler encoding. + */ +static bool is_ereg_8l(u32 reg) +{ + return is_ereg(reg) || + (1 << reg) & (BIT(BPF_REG_1) | + BIT(BPF_REG_2) | + BIT(BPF_REG_FP)); +} + static bool is_axreg(u32 reg) { return reg == BPF_REG_0; @@ -598,9 +611,8 @@ static void emit_stx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off) switch (size) { case BPF_B: /* Emit 'mov byte ptr [rax + off], al' */ - if (is_ereg(dst_reg) || is_ereg(src_reg) || - /* We have to add extra byte for x86 SIL, DIL regs */ - src_reg == BPF_REG_1 || src_reg == BPF_REG_2) + if (is_ereg(dst_reg) || is_ereg_8l(src_reg)) + /* Add extra byte for eregs or SIL,DIL,BPL in src_reg */ EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x88); else EMIT1(0x88); diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c index 4d2a7a764602..66cd150b7e54 100644 --- a/arch/x86/net/bpf_jit_comp32.c +++ b/arch/x86/net/bpf_jit_comp32.c @@ -1847,14 +1847,16 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, case BPF_B: case BPF_H: case BPF_W: - if (!bpf_prog->aux->verifier_zext) + if (bpf_prog->aux->verifier_zext) break; if (dstk) { EMIT3(0xC7, add_1reg(0x40, IA32_EBP), STACK_VAR(dst_hi)); EMIT(0x0, 4); } else { - EMIT3(0xC7, add_1reg(0xC0, dst_hi), 0); + /* xor dst_hi,dst_hi */ + EMIT2(0x33, + add_2reg(0xC0, dst_hi, dst_hi)); } break; case BPF_DW: @@ -2013,8 +2015,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, case BPF_JMP | BPF_JSET | BPF_X: case BPF_JMP32 | BPF_JSET | BPF_X: { bool is_jmp64 = BPF_CLASS(insn->code) == BPF_JMP; - u8 dreg_lo = dstk ? IA32_EAX : dst_lo; - u8 dreg_hi = dstk ? IA32_EDX : dst_hi; + u8 dreg_lo = IA32_EAX; + u8 dreg_hi = IA32_EDX; u8 sreg_lo = sstk ? IA32_ECX : src_lo; u8 sreg_hi = sstk ? IA32_EBX : src_hi; @@ -2026,6 +2028,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, add_2reg(0x40, IA32_EBP, IA32_EDX), STACK_VAR(dst_hi)); + } else { + /* mov dreg_lo,dst_lo */ + EMIT2(0x89, add_2reg(0xC0, dreg_lo, dst_lo)); + if (is_jmp64) + /* mov dreg_hi,dst_hi */ + EMIT2(0x89, + add_2reg(0xC0, dreg_hi, dst_hi)); } if (sstk) { @@ -2050,8 +2059,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, case BPF_JMP | BPF_JSET | BPF_K: case BPF_JMP32 | BPF_JSET | BPF_K: { bool is_jmp64 = BPF_CLASS(insn->code) == BPF_JMP; - u8 dreg_lo = dstk ? IA32_EAX : dst_lo; - u8 dreg_hi = dstk ? IA32_EDX : dst_hi; + u8 dreg_lo = IA32_EAX; + u8 dreg_hi = IA32_EDX; u8 sreg_lo = IA32_ECX; u8 sreg_hi = IA32_EBX; u32 hi; @@ -2064,6 +2073,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, add_2reg(0x40, IA32_EBP, IA32_EDX), STACK_VAR(dst_hi)); + } else { + /* mov dreg_lo,dst_lo */ + EMIT2(0x89, add_2reg(0xC0, dreg_lo, dst_lo)); + if (is_jmp64) + /* mov dreg_hi,dst_hi */ + EMIT2(0x89, + add_2reg(0xC0, dreg_hi, dst_hi)); } /* mov ecx,imm32 */ diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 211bb9358b73..c5e393f8bb3f 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -202,7 +202,7 @@ virt_to_phys_or_null_size(void *va, unsigned long size) int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) { - unsigned long pfn, text, pf; + unsigned long pfn, text, pf, rodata; struct page *page; unsigned npages; pgd_t *pgd = efi_mm.pgd; @@ -256,7 +256,7 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) efi_scratch.phys_stack = page_to_phys(page + 1); /* stack grows down */ - npages = (__end_rodata_aligned - _text) >> PAGE_SHIFT; + npages = (_etext - _text) >> PAGE_SHIFT; text = __pa(_text); pfn = text >> PAGE_SHIFT; @@ -266,6 +266,14 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) return 1; } + npages = (__end_rodata - __start_rodata) >> PAGE_SHIFT; + rodata = __pa(__start_rodata); + pfn = rodata >> PAGE_SHIFT; + if (kernel_map_pages_in_pgd(pgd, pfn, rodata, npages, pf)) { + pr_err("Failed to map kernel rodata 1:1\n"); + return 1; + } + return 0; } @@ -638,7 +646,7 @@ efi_thunk_set_variable(efi_char16_t *name, efi_guid_t *vendor, phys_vendor = virt_to_phys_or_null(vnd); phys_data = virt_to_phys_or_null_size(data, data_size); - if (!phys_name || !phys_data) + if (!phys_name || (data && !phys_data)) status = EFI_INVALID_PARAMETER; else status = efi_thunk(set_variable, phys_name, phys_vendor, @@ -669,7 +677,7 @@ efi_thunk_set_variable_nonblocking(efi_char16_t *name, efi_guid_t *vendor, phys_vendor = virt_to_phys_or_null(vnd); phys_data = virt_to_phys_or_null_size(data, data_size); - if (!phys_name || !phys_data) + if (!phys_name || (data && !phys_data)) status = EFI_INVALID_PARAMETER; else status = efi_thunk(set_variable, phys_name, phys_vendor, diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index 8fb8a50a28b4..f2adb63b2d7c 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -93,6 +93,7 @@ asmlinkage __visible void cpu_bringup_and_idle(void) cpu_bringup(); boot_init_stack_canary(); cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); + prevent_tail_call_optimization(); } void xen_smp_intr_free_pv(unsigned int cpu) |