diff options
Diffstat (limited to 'arch/x86')
31 files changed, 349 insertions, 221 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 1197b5596d5a..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 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/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index fd51bac11b46..acf76b466db6 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -226,10 +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)); } @@ -293,6 +301,13 @@ 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. */ 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/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/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/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 8c89e4d9ad28..2f24c334a938 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -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(); } /** 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..fa79e4227d3d 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; @@ -381,9 +384,38 @@ 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 +477,39 @@ 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 +532,48 @@ 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 +596,8 @@ 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 +620,20 @@ 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 +666,7 @@ 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 +687,14 @@ 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/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 cf912b4aaba8..89f7f3aebd31 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -345,7 +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; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 2f379bacbb26..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; @@ -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); @@ -3929,8 +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/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index fd78ffbde644..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; } 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 c2c6335a998c..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(); } @@ -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 c5835f9cb9ad..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 */ @@ -3385,6 +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: @@ -3570,6 +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); @@ -3763,7 +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; @@ -4021,7 +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); @@ -6671,7 +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; @@ -6731,9 +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; } @@ -8054,7 +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); } @@ -8084,6 +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 || @@ -8108,7 +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); @@ -8432,7 +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; } @@ -9493,7 +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); @@ -9675,7 +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) { /* @@ -9707,7 +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/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/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) |