diff options
Diffstat (limited to 'arch/x86')
94 files changed, 2518 insertions, 755 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 9783ebc4e021..52a7f91527fe 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -245,6 +245,7 @@ config X86 select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP select MMU_GATHER_RCU_TABLE_FREE if PARAVIRT + select MMU_GATHER_MERGE_VMAS select HAVE_POSIX_CPU_TIMERS_TASK_WORK select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RELIABLE_STACKTRACE if UNWINDER_ORC || STACK_VALIDATION @@ -462,29 +463,6 @@ config GOLDFISH def_bool y depends on X86_GOLDFISH -config RETPOLINE - bool "Avoid speculative indirect branches in kernel" - select OBJTOOL if HAVE_OBJTOOL - default y - help - Compile kernel with the retpoline compiler options to guard against - kernel-to-user data leaks by avoiding speculative indirect - branches. Requires a compiler with -mindirect-branch=thunk-extern - support for full protection. The kernel may run slower. - -config CC_HAS_SLS - def_bool $(cc-option,-mharden-sls=all) - -config SLS - bool "Mitigate Straight-Line-Speculation" - depends on CC_HAS_SLS && X86_64 - select OBJTOOL if HAVE_OBJTOOL - default n - help - Compile the kernel with straight-line-speculation options to guard - against straight line speculation. The kernel image might be slightly - larger. - config X86_CPU_RESCTRL bool "x86 CPU resource control support" depends on X86 && (CPU_SUP_INTEL || CPU_SUP_AMD) @@ -1542,7 +1520,6 @@ config X86_CPA_STATISTICS config X86_MEM_ENCRYPT select ARCH_HAS_FORCE_DMA_UNENCRYPTED select DYNAMIC_PHYSICAL_MASK - select ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS def_bool n config AMD_MEM_ENCRYPT @@ -2454,6 +2431,91 @@ source "kernel/livepatch/Kconfig" endmenu +config CC_HAS_SLS + def_bool $(cc-option,-mharden-sls=all) + +config CC_HAS_RETURN_THUNK + def_bool $(cc-option,-mfunction-return=thunk-extern) + +menuconfig SPECULATION_MITIGATIONS + bool "Mitigations for speculative execution vulnerabilities" + default y + help + Say Y here to enable options which enable mitigations for + speculative execution hardware vulnerabilities. + + If you say N, all mitigations will be disabled. You really + should know what you are doing to say so. + +if SPECULATION_MITIGATIONS + +config PAGE_TABLE_ISOLATION + bool "Remove the kernel mapping in user mode" + default y + depends on (X86_64 || X86_PAE) + help + This feature reduces the number of hardware side channels by + ensuring that the majority of kernel addresses are not mapped + into userspace. + + See Documentation/x86/pti.rst for more details. + +config RETPOLINE + bool "Avoid speculative indirect branches in kernel" + select OBJTOOL if HAVE_OBJTOOL + default y + help + Compile kernel with the retpoline compiler options to guard against + kernel-to-user data leaks by avoiding speculative indirect + branches. Requires a compiler with -mindirect-branch=thunk-extern + support for full protection. The kernel may run slower. + +config RETHUNK + bool "Enable return-thunks" + depends on RETPOLINE && CC_HAS_RETURN_THUNK + select OBJTOOL if HAVE_OBJTOOL + default y if X86_64 + help + Compile the kernel with the return-thunks compiler option to guard + against kernel-to-user data leaks by avoiding return speculation. + Requires a compiler with -mfunction-return=thunk-extern + support for full protection. The kernel may run slower. + +config CPU_UNRET_ENTRY + bool "Enable UNRET on kernel entry" + depends on CPU_SUP_AMD && RETHUNK && X86_64 + default y + help + Compile the kernel with support for the retbleed=unret mitigation. + +config CPU_IBPB_ENTRY + bool "Enable IBPB on kernel entry" + depends on CPU_SUP_AMD && X86_64 + default y + help + Compile the kernel with support for the retbleed=ibpb mitigation. + +config CPU_IBRS_ENTRY + bool "Enable IBRS on kernel entry" + depends on CPU_SUP_INTEL && X86_64 + default y + help + Compile the kernel with support for the spectre_v2=ibrs mitigation. + This mitigates both spectre_v2 and retbleed at great cost to + performance. + +config SLS + bool "Mitigate Straight-Line-Speculation" + depends on CC_HAS_SLS && X86_64 + select OBJTOOL if HAVE_OBJTOOL + default n + help + Compile the kernel with straight-line-speculation options to guard + against straight line speculation. The kernel image might be slightly + larger. + +endif + config ARCH_HAS_ADD_PAGES def_bool y depends on ARCH_ENABLE_MEMORY_HOTPLUG diff --git a/arch/x86/Makefile b/arch/x86/Makefile index a74886aed349..7854685c5f25 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -21,6 +21,13 @@ ifdef CONFIG_CC_IS_CLANG RETPOLINE_CFLAGS := -mretpoline-external-thunk RETPOLINE_VDSO_CFLAGS := -mretpoline endif + +ifdef CONFIG_RETHUNK +RETHUNK_CFLAGS := -mfunction-return=thunk-extern +RETPOLINE_CFLAGS += $(RETHUNK_CFLAGS) +endif + +export RETHUNK_CFLAGS export RETPOLINE_CFLAGS export RETPOLINE_VDSO_CFLAGS diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index 44c350d627c7..d4a314cc50d6 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -110,6 +110,7 @@ void kernel_add_identity_map(unsigned long start, unsigned long end) void initialize_identity_maps(void *rmode) { unsigned long cmdline; + struct setup_data *sd; /* Exclude the encryption mask from __PHYSICAL_MASK */ physical_mask &= ~sme_me_mask; @@ -163,6 +164,18 @@ void initialize_identity_maps(void *rmode) cmdline = get_cmd_line_ptr(); kernel_add_identity_map(cmdline, cmdline + COMMAND_LINE_SIZE); + /* + * Also map the setup_data entries passed via boot_params in case they + * need to be accessed by uncompressed kernel via the identity mapping. + */ + sd = (struct setup_data *)boot_params->hdr.setup_data; + while (sd) { + unsigned long sd_addr = (unsigned long)sd; + + kernel_add_identity_map(sd_addr, sd_addr + sizeof(*sd) + sd->len); + sd = (struct setup_data *)sd->next; + } + sev_prep_identity_maps(top_level_pgt); /* Load the new page-table. */ diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c index 03deb4d6920d..928dcf7a20d9 100644 --- a/arch/x86/coco/tdx/tdx.c +++ b/arch/x86/coco/tdx/tdx.c @@ -124,6 +124,51 @@ static u64 get_cc_mask(void) return BIT_ULL(gpa_width - 1); } +/* + * The TDX module spec states that #VE may be injected for a limited set of + * reasons: + * + * - Emulation of the architectural #VE injection on EPT violation; + * + * - As a result of guest TD execution of a disallowed instruction, + * a disallowed MSR access, or CPUID virtualization; + * + * - A notification to the guest TD about anomalous behavior; + * + * The last one is opt-in and is not used by the kernel. + * + * The Intel Software Developer's Manual describes cases when instruction + * length field can be used in section "Information for VM Exits Due to + * Instruction Execution". + * + * For TDX, it ultimately means GET_VEINFO provides reliable instruction length + * information if #VE occurred due to instruction execution, but not for EPT + * violations. + */ +static int ve_instr_len(struct ve_info *ve) +{ + switch (ve->exit_reason) { + case EXIT_REASON_HLT: + case EXIT_REASON_MSR_READ: + case EXIT_REASON_MSR_WRITE: + case EXIT_REASON_CPUID: + case EXIT_REASON_IO_INSTRUCTION: + /* It is safe to use ve->instr_len for #VE due instructions */ + return ve->instr_len; + case EXIT_REASON_EPT_VIOLATION: + /* + * For EPT violations, ve->insn_len is not defined. For those, + * the kernel must decode instructions manually and should not + * be using this function. + */ + WARN_ONCE(1, "ve->instr_len is not defined for EPT violations"); + return 0; + default: + WARN_ONCE(1, "Unexpected #VE-type: %lld\n", ve->exit_reason); + return ve->instr_len; + } +} + static u64 __cpuidle __halt(const bool irq_disabled, const bool do_sti) { struct tdx_hypercall_args args = { @@ -147,7 +192,7 @@ static u64 __cpuidle __halt(const bool irq_disabled, const bool do_sti) return __tdx_hypercall(&args, do_sti ? TDX_HCALL_ISSUE_STI : 0); } -static bool handle_halt(void) +static int handle_halt(struct ve_info *ve) { /* * Since non safe halt is mainly used in CPU offlining @@ -158,9 +203,9 @@ static bool handle_halt(void) const bool do_sti = false; if (__halt(irq_disabled, do_sti)) - return false; + return -EIO; - return true; + return ve_instr_len(ve); } void __cpuidle tdx_safe_halt(void) @@ -180,7 +225,7 @@ void __cpuidle tdx_safe_halt(void) WARN_ONCE(1, "HLT instruction emulation failed\n"); } -static bool read_msr(struct pt_regs *regs) +static int read_msr(struct pt_regs *regs, struct ve_info *ve) { struct tdx_hypercall_args args = { .r10 = TDX_HYPERCALL_STANDARD, @@ -194,14 +239,14 @@ static bool read_msr(struct pt_regs *regs) * (GHCI), section titled "TDG.VP.VMCALL<Instruction.RDMSR>". */ if (__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT)) - return false; + return -EIO; regs->ax = lower_32_bits(args.r11); regs->dx = upper_32_bits(args.r11); - return true; + return ve_instr_len(ve); } -static bool write_msr(struct pt_regs *regs) +static int write_msr(struct pt_regs *regs, struct ve_info *ve) { struct tdx_hypercall_args args = { .r10 = TDX_HYPERCALL_STANDARD, @@ -215,10 +260,13 @@ static bool write_msr(struct pt_regs *regs) * can be found in TDX Guest-Host-Communication Interface * (GHCI) section titled "TDG.VP.VMCALL<Instruction.WRMSR>". */ - return !__tdx_hypercall(&args, 0); + if (__tdx_hypercall(&args, 0)) + return -EIO; + + return ve_instr_len(ve); } -static bool handle_cpuid(struct pt_regs *regs) +static int handle_cpuid(struct pt_regs *regs, struct ve_info *ve) { struct tdx_hypercall_args args = { .r10 = TDX_HYPERCALL_STANDARD, @@ -236,7 +284,7 @@ static bool handle_cpuid(struct pt_regs *regs) */ if (regs->ax < 0x40000000 || regs->ax > 0x4FFFFFFF) { regs->ax = regs->bx = regs->cx = regs->dx = 0; - return true; + return ve_instr_len(ve); } /* @@ -245,7 +293,7 @@ static bool handle_cpuid(struct pt_regs *regs) * (GHCI), section titled "VP.VMCALL<Instruction.CPUID>". */ if (__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT)) - return false; + return -EIO; /* * As per TDX GHCI CPUID ABI, r12-r15 registers contain contents of @@ -257,7 +305,7 @@ static bool handle_cpuid(struct pt_regs *regs) regs->cx = args.r14; regs->dx = args.r15; - return true; + return ve_instr_len(ve); } static bool mmio_read(int size, unsigned long addr, unsigned long *val) @@ -283,10 +331,10 @@ static bool mmio_write(int size, unsigned long addr, unsigned long val) EPT_WRITE, addr, val); } -static bool handle_mmio(struct pt_regs *regs, struct ve_info *ve) +static int handle_mmio(struct pt_regs *regs, struct ve_info *ve) { + unsigned long *reg, val, vaddr; char buffer[MAX_INSN_SIZE]; - unsigned long *reg, val; struct insn insn = {}; enum mmio_type mmio; int size, extend_size; @@ -294,34 +342,49 @@ static bool handle_mmio(struct pt_regs *regs, struct ve_info *ve) /* Only in-kernel MMIO is supported */ if (WARN_ON_ONCE(user_mode(regs))) - return false; + return -EFAULT; if (copy_from_kernel_nofault(buffer, (void *)regs->ip, MAX_INSN_SIZE)) - return false; + return -EFAULT; if (insn_decode(&insn, buffer, MAX_INSN_SIZE, INSN_MODE_64)) - return false; + return -EINVAL; mmio = insn_decode_mmio(&insn, &size); if (WARN_ON_ONCE(mmio == MMIO_DECODE_FAILED)) - return false; + return -EINVAL; if (mmio != MMIO_WRITE_IMM && mmio != MMIO_MOVS) { reg = insn_get_modrm_reg_ptr(&insn, regs); if (!reg) - return false; + return -EINVAL; } - ve->instr_len = insn.length; + /* + * Reject EPT violation #VEs that split pages. + * + * MMIO accesses are supposed to be naturally aligned and therefore + * never cross page boundaries. Seeing split page accesses indicates + * a bug or a load_unaligned_zeropad() that stepped into an MMIO page. + * + * load_unaligned_zeropad() will recover using exception fixups. + */ + vaddr = (unsigned long)insn_get_addr_ref(&insn, regs); + if (vaddr / PAGE_SIZE != (vaddr + size - 1) / PAGE_SIZE) + return -EFAULT; /* Handle writes first */ switch (mmio) { case MMIO_WRITE: memcpy(&val, reg, size); - return mmio_write(size, ve->gpa, val); + if (!mmio_write(size, ve->gpa, val)) + return -EIO; + return insn.length; case MMIO_WRITE_IMM: val = insn.immediate.value; - return mmio_write(size, ve->gpa, val); + if (!mmio_write(size, ve->gpa, val)) + return -EIO; + return insn.length; case MMIO_READ: case MMIO_READ_ZERO_EXTEND: case MMIO_READ_SIGN_EXTEND: @@ -334,15 +397,15 @@ static bool handle_mmio(struct pt_regs *regs, struct ve_info *ve) * decoded or handled properly. It was likely not using io.h * helpers or accessed MMIO accidentally. */ - return false; + return -EINVAL; default: WARN_ONCE(1, "Unknown insn_decode_mmio() decode value?"); - return false; + return -EINVAL; } /* Handle reads */ if (!mmio_read(size, ve->gpa, &val)) - return false; + return -EIO; switch (mmio) { case MMIO_READ: @@ -364,13 +427,13 @@ static bool handle_mmio(struct pt_regs *regs, struct ve_info *ve) default: /* All other cases has to be covered with the first switch() */ WARN_ON_ONCE(1); - return false; + return -EINVAL; } if (extend_size) memset(reg, extend_val, extend_size); memcpy(reg, &val, size); - return true; + return insn.length; } static bool handle_in(struct pt_regs *regs, int size, int port) @@ -421,13 +484,14 @@ static bool handle_out(struct pt_regs *regs, int size, int port) * * Return True on success or False on failure. */ -static bool handle_io(struct pt_regs *regs, u32 exit_qual) +static int handle_io(struct pt_regs *regs, struct ve_info *ve) { + u32 exit_qual = ve->exit_qual; int size, port; - bool in; + bool in, ret; if (VE_IS_IO_STRING(exit_qual)) - return false; + return -EIO; in = VE_IS_IO_IN(exit_qual); size = VE_GET_IO_SIZE(exit_qual); @@ -435,9 +499,13 @@ static bool handle_io(struct pt_regs *regs, u32 exit_qual) if (in) - return handle_in(regs, size, port); + ret = handle_in(regs, size, port); else - return handle_out(regs, size, port); + ret = handle_out(regs, size, port); + if (!ret) + return -EIO; + + return ve_instr_len(ve); } /* @@ -447,13 +515,19 @@ static bool handle_io(struct pt_regs *regs, u32 exit_qual) __init bool tdx_early_handle_ve(struct pt_regs *regs) { struct ve_info ve; + int insn_len; tdx_get_ve_info(&ve); if (ve.exit_reason != EXIT_REASON_IO_INSTRUCTION) return false; - return handle_io(regs, ve.exit_qual); + insn_len = handle_io(regs, &ve); + if (insn_len < 0) + return false; + + regs->ip += insn_len; + return true; } void tdx_get_ve_info(struct ve_info *ve) @@ -486,54 +560,65 @@ void tdx_get_ve_info(struct ve_info *ve) ve->instr_info = upper_32_bits(out.r10); } -/* Handle the user initiated #VE */ -static bool virt_exception_user(struct pt_regs *regs, struct ve_info *ve) +/* + * Handle the user initiated #VE. + * + * On success, returns the number of bytes RIP should be incremented (>=0) + * or -errno on error. + */ +static int virt_exception_user(struct pt_regs *regs, struct ve_info *ve) { switch (ve->exit_reason) { case EXIT_REASON_CPUID: - return handle_cpuid(regs); + return handle_cpuid(regs, ve); default: pr_warn("Unexpected #VE: %lld\n", ve->exit_reason); - return false; + return -EIO; } } -/* Handle the kernel #VE */ -static bool virt_exception_kernel(struct pt_regs *regs, struct ve_info *ve) +/* + * Handle the kernel #VE. + * + * On success, returns the number of bytes RIP should be incremented (>=0) + * or -errno on error. + */ +static int virt_exception_kernel(struct pt_regs *regs, struct ve_info *ve) { switch (ve->exit_reason) { case EXIT_REASON_HLT: - return handle_halt(); + return handle_halt(ve); case EXIT_REASON_MSR_READ: - return read_msr(regs); + return read_msr(regs, ve); case EXIT_REASON_MSR_WRITE: - return write_msr(regs); + return write_msr(regs, ve); case EXIT_REASON_CPUID: - return handle_cpuid(regs); + return handle_cpuid(regs, ve); case EXIT_REASON_EPT_VIOLATION: return handle_mmio(regs, ve); case EXIT_REASON_IO_INSTRUCTION: - return handle_io(regs, ve->exit_qual); + return handle_io(regs, ve); default: pr_warn("Unexpected #VE: %lld\n", ve->exit_reason); - return false; + return -EIO; } } bool tdx_handle_virt_exception(struct pt_regs *regs, struct ve_info *ve) { - bool ret; + int insn_len; if (user_mode(regs)) - ret = virt_exception_user(regs, ve); + insn_len = virt_exception_user(regs, ve); else - ret = virt_exception_kernel(regs, ve); + insn_len = virt_exception_kernel(regs, ve); + if (insn_len < 0) + return false; /* After successful #VE handling, move the IP */ - if (ret) - regs->ip += ve->instr_len; + regs->ip += insn_len; - return ret; + return true; } static bool tdx_tlb_flush_required(bool private) diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile index 7fec5dcf6438..eeadbd7d92cc 100644 --- a/arch/x86/entry/Makefile +++ b/arch/x86/entry/Makefile @@ -11,7 +11,7 @@ CFLAGS_REMOVE_common.o = $(CC_FLAGS_FTRACE) CFLAGS_common.o += -fno-stack-protector -obj-y := entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o +obj-y := entry.o entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o obj-y += common.o obj-y += vdso/ diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 29b36e9e4e74..f6907627172b 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -7,6 +7,8 @@ #include <asm/asm-offsets.h> #include <asm/processor-flags.h> #include <asm/ptrace-abi.h> +#include <asm/msr.h> +#include <asm/nospec-branch.h> /* @@ -283,6 +285,66 @@ For 32-bit we have the following conventions - kernel is built with #endif /* + * IBRS kernel mitigation for Spectre_v2. + * + * Assumes full context is established (PUSH_REGS, CR3 and GS) and it clobbers + * the regs it uses (AX, CX, DX). Must be called before the first RET + * instruction (NOTE! UNTRAIN_RET includes a RET instruction) + * + * The optional argument is used to save/restore the current value, + * which is used on the paranoid paths. + * + * Assumes x86_spec_ctrl_{base,current} to have SPEC_CTRL_IBRS set. + */ +.macro IBRS_ENTER save_reg +#ifdef CONFIG_CPU_IBRS_ENTRY + ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_KERNEL_IBRS + movl $MSR_IA32_SPEC_CTRL, %ecx + +.ifnb \save_reg + rdmsr + shl $32, %rdx + or %rdx, %rax + mov %rax, \save_reg + test $SPEC_CTRL_IBRS, %eax + jz .Ldo_wrmsr_\@ + lfence + jmp .Lend_\@ +.Ldo_wrmsr_\@: +.endif + + movq PER_CPU_VAR(x86_spec_ctrl_current), %rdx + movl %edx, %eax + shr $32, %rdx + wrmsr +.Lend_\@: +#endif +.endm + +/* + * Similar to IBRS_ENTER, requires KERNEL GS,CR3 and clobbers (AX, CX, DX) + * regs. Must be called after the last RET. + */ +.macro IBRS_EXIT save_reg +#ifdef CONFIG_CPU_IBRS_ENTRY + ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_KERNEL_IBRS + movl $MSR_IA32_SPEC_CTRL, %ecx + +.ifnb \save_reg + mov \save_reg, %rdx +.else + movq PER_CPU_VAR(x86_spec_ctrl_current), %rdx + andl $(~SPEC_CTRL_IBRS), %edx +.endif + + movl %edx, %eax + shr $32, %rdx + wrmsr +.Lend_\@: +#endif +.endm + +/* * Mitigate Spectre v1 for conditional swapgs code paths. * * FENCE_SWAPGS_USER_ENTRY is used in the user entry swapgs code path, to diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S new file mode 100644 index 000000000000..bfb7bcb362bc --- /dev/null +++ b/arch/x86/entry/entry.S @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Common place for both 32- and 64-bit entry routines. + */ + +#include <linux/linkage.h> +#include <asm/export.h> +#include <asm/msr-index.h> + +.pushsection .noinstr.text, "ax" + +SYM_FUNC_START(entry_ibpb) + movl $MSR_IA32_PRED_CMD, %ecx + movl $PRED_CMD_IBPB, %eax + xorl %edx, %edx + wrmsr + RET +SYM_FUNC_END(entry_ibpb) +/* For KVM */ +EXPORT_SYMBOL_GPL(entry_ibpb); + +.popsection diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 887420844066..e309e7156038 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -698,7 +698,6 @@ SYM_CODE_START(__switch_to_asm) movl %ebx, PER_CPU_VAR(__stack_chk_guard) #endif -#ifdef CONFIG_RETPOLINE /* * When switching from a shallower to a deeper call stack * the RSB may either underflow or use entries populated @@ -707,7 +706,6 @@ SYM_CODE_START(__switch_to_asm) * speculative execution to prevent attack. */ FILL_RETURN_BUFFER %ebx, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW -#endif /* Restore flags or the incoming task to restore AC state. */ popfl diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 4300ba49b5ee..9953d966d124 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -85,7 +85,7 @@ */ SYM_CODE_START(entry_SYSCALL_64) - UNWIND_HINT_EMPTY + UNWIND_HINT_ENTRY ENDBR swapgs @@ -112,6 +112,11 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL) movq %rsp, %rdi /* Sign extend the lower 32bit as syscall numbers are treated as int */ movslq %eax, %rsi + + /* clobbers %rax, make sure it is after saving the syscall nr */ + IBRS_ENTER + UNTRAIN_RET + call do_syscall_64 /* returns with IRQs disabled */ /* @@ -191,6 +196,7 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL) * perf profiles. Nothing jumps here. */ syscall_return_via_sysret: + IBRS_EXIT POP_REGS pop_rdi=0 /* @@ -249,7 +255,6 @@ SYM_FUNC_START(__switch_to_asm) movq %rbx, PER_CPU_VAR(fixed_percpu_data) + stack_canary_offset #endif -#ifdef CONFIG_RETPOLINE /* * When switching from a shallower to a deeper call stack * the RSB may either underflow or use entries populated @@ -258,7 +263,6 @@ SYM_FUNC_START(__switch_to_asm) * speculative execution to prevent attack. */ FILL_RETURN_BUFFER %r12, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW -#endif /* restore callee-saved registers */ popq %r15 @@ -322,13 +326,13 @@ SYM_CODE_END(ret_from_fork) #endif .endm -/* Save all registers in pt_regs */ -SYM_CODE_START_LOCAL(push_and_clear_regs) +SYM_CODE_START_LOCAL(xen_error_entry) UNWIND_HINT_FUNC PUSH_AND_CLEAR_REGS save_ret=1 ENCODE_FRAME_POINTER 8 + UNTRAIN_RET RET -SYM_CODE_END(push_and_clear_regs) +SYM_CODE_END(xen_error_entry) /** * idtentry_body - Macro to emit code calling the C function @@ -337,9 +341,6 @@ SYM_CODE_END(push_and_clear_regs) */ .macro idtentry_body cfunc has_error_code:req - call push_and_clear_regs - UNWIND_HINT_REGS - /* * Call error_entry() and switch to the task stack if from userspace. * @@ -349,7 +350,7 @@ SYM_CODE_END(push_and_clear_regs) * switch the CR3. So it can skip invoking error_entry(). */ ALTERNATIVE "call error_entry; movq %rax, %rsp", \ - "", X86_FEATURE_XENPV + "call xen_error_entry", X86_FEATURE_XENPV ENCODE_FRAME_POINTER UNWIND_HINT_REGS @@ -612,6 +613,7 @@ __irqentry_text_end: SYM_CODE_START_LOCAL(common_interrupt_return) SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL) + IBRS_EXIT #ifdef CONFIG_DEBUG_ENTRY /* Assert that pt_regs indicates user mode. */ testb $3, CS(%rsp) @@ -897,6 +899,9 @@ SYM_CODE_END(xen_failsafe_callback) * 1 -> no SWAPGS on exit * * Y GSBASE value at entry, must be restored in paranoid_exit + * + * R14 - old CR3 + * R15 - old SPEC_CTRL */ SYM_CODE_START_LOCAL(paranoid_entry) UNWIND_HINT_FUNC @@ -940,7 +945,7 @@ SYM_CODE_START_LOCAL(paranoid_entry) * is needed here. */ SAVE_AND_SET_GSBASE scratch_reg=%rax save_reg=%rbx - RET + jmp .Lparanoid_gsbase_done .Lparanoid_entry_checkgs: /* EBX = 1 -> kernel GSBASE active, no restore required */ @@ -959,8 +964,16 @@ SYM_CODE_START_LOCAL(paranoid_entry) xorl %ebx, %ebx swapgs .Lparanoid_kernel_gsbase: - FENCE_SWAPGS_KERNEL_ENTRY +.Lparanoid_gsbase_done: + + /* + * Once we have CR3 and %GS setup save and set SPEC_CTRL. Just like + * CR3 above, keep the old value in a callee saved register. + */ + IBRS_ENTER save_reg=%r15 + UNTRAIN_RET + RET SYM_CODE_END(paranoid_entry) @@ -982,9 +995,19 @@ SYM_CODE_END(paranoid_entry) * 1 -> no SWAPGS on exit * * Y User space GSBASE, must be restored unconditionally + * + * R14 - old CR3 + * R15 - old SPEC_CTRL */ SYM_CODE_START_LOCAL(paranoid_exit) UNWIND_HINT_REGS + + /* + * Must restore IBRS state before both CR3 and %GS since we need access + * to the per-CPU x86_spec_ctrl_shadow variable. + */ + IBRS_EXIT save_reg=%r15 + /* * The order of operations is important. RESTORE_CR3 requires * kernel GSBASE. @@ -1017,6 +1040,10 @@ SYM_CODE_END(paranoid_exit) */ SYM_CODE_START_LOCAL(error_entry) UNWIND_HINT_FUNC + + PUSH_AND_CLEAR_REGS save_ret=1 + ENCODE_FRAME_POINTER 8 + testb $3, CS+8(%rsp) jz .Lerror_kernelspace @@ -1028,9 +1055,12 @@ SYM_CODE_START_LOCAL(error_entry) FENCE_SWAPGS_USER_ENTRY /* We have user CR3. Change to kernel CR3. */ SWITCH_TO_KERNEL_CR3 scratch_reg=%rax + IBRS_ENTER + UNTRAIN_RET leaq 8(%rsp), %rdi /* arg0 = pt_regs pointer */ .Lerror_entry_from_usermode_after_swapgs: + /* Put us onto the real thread stack. */ call sync_regs RET @@ -1065,6 +1095,7 @@ SYM_CODE_START_LOCAL(error_entry) .Lerror_entry_done_lfence: FENCE_SWAPGS_KERNEL_ENTRY leaq 8(%rsp), %rax /* return pt_regs pointer */ + ANNOTATE_UNRET_END RET .Lbstep_iret: @@ -1080,6 +1111,8 @@ SYM_CODE_START_LOCAL(error_entry) swapgs FENCE_SWAPGS_USER_ENTRY SWITCH_TO_KERNEL_CR3 scratch_reg=%rax + IBRS_ENTER + UNTRAIN_RET /* * Pretend that the exception came from user mode: set up pt_regs @@ -1185,6 +1218,9 @@ SYM_CODE_START(asm_exc_nmi) PUSH_AND_CLEAR_REGS rdx=(%rdx) ENCODE_FRAME_POINTER + IBRS_ENTER + UNTRAIN_RET + /* * At this point we no longer need to worry about stack damage * due to nesting -- we're on the normal thread stack and we're @@ -1409,6 +1445,9 @@ end_repeat_nmi: movq $-1, %rsi call exc_nmi + /* Always restore stashed SPEC_CTRL value (see paranoid_entry) */ + IBRS_EXIT save_reg=%r15 + /* Always restore stashed CR3 value (see paranoid_entry) */ RESTORE_CR3 scratch_reg=%r15 save_reg=%r14 diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index d1052742ad0c..682338e7e2a3 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -4,7 +4,6 @@ * * Copyright 2000-2002 Andi Kleen, SuSE Labs. */ -#include "calling.h" #include <asm/asm-offsets.h> #include <asm/current.h> #include <asm/errno.h> @@ -14,9 +13,12 @@ #include <asm/irqflags.h> #include <asm/asm.h> #include <asm/smap.h> +#include <asm/nospec-branch.h> #include <linux/linkage.h> #include <linux/err.h> +#include "calling.h" + .section .entry.text, "ax" /* @@ -47,7 +49,7 @@ * 0(%ebp) arg6 */ SYM_CODE_START(entry_SYSENTER_compat) - UNWIND_HINT_EMPTY + UNWIND_HINT_ENTRY ENDBR /* Interrupts are off on entry. */ swapgs @@ -88,6 +90,9 @@ SYM_INNER_LABEL(entry_SYSENTER_compat_after_hwframe, SYM_L_GLOBAL) cld + IBRS_ENTER + UNTRAIN_RET + /* * SYSENTER doesn't filter flags, so we need to clear NT and AC * ourselves. To save a few cycles, we can check whether @@ -174,7 +179,7 @@ SYM_CODE_END(entry_SYSENTER_compat) * 0(%esp) arg6 */ SYM_CODE_START(entry_SYSCALL_compat) - UNWIND_HINT_EMPTY + UNWIND_HINT_ENTRY ENDBR /* Interrupts are off on entry. */ swapgs @@ -203,6 +208,9 @@ SYM_INNER_LABEL(entry_SYSCALL_compat_after_hwframe, SYM_L_GLOBAL) PUSH_AND_CLEAR_REGS rcx=%rbp rax=$-ENOSYS UNWIND_HINT_REGS + IBRS_ENTER + UNTRAIN_RET + movq %rsp, %rdi call do_fast_syscall_32 /* XEN PV guests always use IRET path */ @@ -217,6 +225,8 @@ sysret32_from_system_call: */ STACKLEAK_ERASE + IBRS_EXIT + movq RBX(%rsp), %rbx /* pt_regs->rbx */ movq RBP(%rsp), %rbp /* pt_regs->rbp */ movq EFLAGS(%rsp), %r11 /* pt_regs->flags (in r11) */ @@ -295,7 +305,7 @@ SYM_CODE_END(entry_SYSCALL_compat) * ebp arg6 */ SYM_CODE_START(entry_INT80_compat) - UNWIND_HINT_EMPTY + UNWIND_HINT_ENTRY ENDBR /* * Interrupts are off on entry. @@ -337,6 +347,9 @@ SYM_CODE_START(entry_INT80_compat) cld + IBRS_ENTER + UNTRAIN_RET + movq %rsp, %rdi call do_int80_syscall_32 jmp swapgs_restore_regs_and_return_to_usermode diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index c2a8b76ae0bc..76cd790ed0bd 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -92,6 +92,7 @@ endif endif $(vobjs): KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO) $(RANDSTRUCT_CFLAGS) $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL) +$(vobjs): KBUILD_AFLAGS += -DBUILD_VDSO # # vDSO code runs in userspace and -pg doesn't help with profiling anyway. diff --git a/arch/x86/entry/vsyscall/vsyscall_emu_64.S b/arch/x86/entry/vsyscall/vsyscall_emu_64.S index 15e35159ebb6..ef2dd1827243 100644 --- a/arch/x86/entry/vsyscall/vsyscall_emu_64.S +++ b/arch/x86/entry/vsyscall/vsyscall_emu_64.S @@ -19,17 +19,20 @@ __vsyscall_page: mov $__NR_gettimeofday, %rax syscall - RET + ret + int3 .balign 1024, 0xcc mov $__NR_time, %rax syscall - RET + ret + int3 .balign 1024, 0xcc mov $__NR_getcpu, %rax syscall - RET + ret + int3 .balign 4096, 0xcc diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 13179f31fe10..4f70fb6c2c1e 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -278,9 +278,9 @@ enum { }; /* - * For formats with LBR_TSX flags (e.g. LBR_FORMAT_EIP_FLAGS2), bits 61:62 in - * MSR_LAST_BRANCH_FROM_x are the TSX flags when TSX is supported, but when - * TSX is not supported they have no consistent behavior: + * For format LBR_FORMAT_EIP_FLAGS2, bits 61:62 in MSR_LAST_BRANCH_FROM_x + * are the TSX flags when TSX is supported, but when TSX is not supported + * they have no consistent behavior: * * - For wrmsr(), bits 61:62 are considered part of the sign extension. * - For HW updates (branch captures) bits 61:62 are always OFF and are not @@ -288,7 +288,7 @@ enum { * * Therefore, if: * - * 1) LBR has TSX format + * 1) LBR format LBR_FORMAT_EIP_FLAGS2 * 2) CPU has no TSX support enabled * * ... then any value passed to wrmsr() must be sign extended to 63 bits and any @@ -300,7 +300,7 @@ static inline bool lbr_from_signext_quirk_needed(void) bool tsx_support = boot_cpu_has(X86_FEATURE_HLE) || boot_cpu_has(X86_FEATURE_RTM); - return !tsx_support && x86_pmu.lbr_has_tsx; + return !tsx_support; } static DEFINE_STATIC_KEY_FALSE(lbr_from_quirk_key); @@ -1609,9 +1609,6 @@ void intel_pmu_lbr_init_hsw(void) x86_pmu.lbr_sel_map = hsw_lbr_sel_map; x86_get_pmu(smp_processor_id())->task_ctx_cache = create_lbr_kmem_cache(size, 0); - - if (lbr_from_signext_quirk_needed()) - static_branch_enable(&lbr_from_quirk_key); } /* skylake */ @@ -1702,7 +1699,11 @@ void intel_pmu_lbr_init(void) switch (x86_pmu.intel_cap.lbr_format) { case LBR_FORMAT_EIP_FLAGS2: x86_pmu.lbr_has_tsx = 1; - fallthrough; + x86_pmu.lbr_from_flags = 1; + if (lbr_from_signext_quirk_needed()) + static_branch_enable(&lbr_from_quirk_key); + break; + case LBR_FORMAT_EIP_FLAGS: x86_pmu.lbr_from_flags = 1; break; diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 8b392b6b7b93..3de6d8b53367 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -13,6 +13,7 @@ #include <linux/io.h> #include <asm/apic.h> #include <asm/desc.h> +#include <asm/sev.h> #include <asm/hypervisor.h> #include <asm/hyperv-tlfs.h> #include <asm/mshyperv.h> @@ -405,6 +406,11 @@ void __init hyperv_init(void) } if (hv_isolation_type_snp()) { + /* Negotiate GHCB Version. */ + if (!hv_ghcb_negotiate_protocol()) + hv_ghcb_terminate(SEV_TERM_SET_GEN, + GHCB_SEV_ES_PROT_UNSUPPORTED); + hv_ghcb_pg = alloc_percpu(union hv_ghcb *); if (!hv_ghcb_pg) goto free_vp_assist_page; diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c index 2b994117581e..1dbcbd9da74d 100644 --- a/arch/x86/hyperv/ivm.c +++ b/arch/x86/hyperv/ivm.c @@ -53,6 +53,8 @@ union hv_ghcb { } hypercall; } __packed __aligned(HV_HYP_PAGE_SIZE); +static u16 hv_ghcb_version __ro_after_init; + u64 hv_ghcb_hypercall(u64 control, void *input, void *output, u32 input_size) { union hv_ghcb *hv_ghcb; @@ -96,12 +98,85 @@ u64 hv_ghcb_hypercall(u64 control, void *input, void *output, u32 input_size) return status; } +static inline u64 rd_ghcb_msr(void) +{ + return __rdmsr(MSR_AMD64_SEV_ES_GHCB); +} + +static inline void wr_ghcb_msr(u64 val) +{ + native_wrmsrl(MSR_AMD64_SEV_ES_GHCB, val); +} + +static enum es_result hv_ghcb_hv_call(struct ghcb *ghcb, u64 exit_code, + u64 exit_info_1, u64 exit_info_2) +{ + /* Fill in protocol and format specifiers */ + ghcb->protocol_version = hv_ghcb_version; + ghcb->ghcb_usage = GHCB_DEFAULT_USAGE; + + ghcb_set_sw_exit_code(ghcb, exit_code); + ghcb_set_sw_exit_info_1(ghcb, exit_info_1); + ghcb_set_sw_exit_info_2(ghcb, exit_info_2); + + VMGEXIT(); + + if (ghcb->save.sw_exit_info_1 & GENMASK_ULL(31, 0)) + return ES_VMM_ERROR; + else + return ES_OK; +} + +void hv_ghcb_terminate(unsigned int set, unsigned int reason) +{ + u64 val = GHCB_MSR_TERM_REQ; + + /* Tell the hypervisor what went wrong. */ + val |= GHCB_SEV_TERM_REASON(set, reason); + + /* Request Guest Termination from Hypvervisor */ + wr_ghcb_msr(val); + VMGEXIT(); + + while (true) + asm volatile("hlt\n" : : : "memory"); +} + +bool hv_ghcb_negotiate_protocol(void) +{ + u64 ghcb_gpa; + u64 val; + + /* Save ghcb page gpa. */ + ghcb_gpa = rd_ghcb_msr(); + + /* Do the GHCB protocol version negotiation */ + wr_ghcb_msr(GHCB_MSR_SEV_INFO_REQ); + VMGEXIT(); + val = rd_ghcb_msr(); + + if (GHCB_MSR_INFO(val) != GHCB_MSR_SEV_INFO_RESP) + return false; + + if (GHCB_MSR_PROTO_MAX(val) < GHCB_PROTOCOL_MIN || + GHCB_MSR_PROTO_MIN(val) > GHCB_PROTOCOL_MAX) + return false; + + hv_ghcb_version = min_t(size_t, GHCB_MSR_PROTO_MAX(val), + GHCB_PROTOCOL_MAX); + + /* Write ghcb page back after negotiating protocol. */ + wr_ghcb_msr(ghcb_gpa); + VMGEXIT(); + + return true; +} + void hv_ghcb_msr_write(u64 msr, u64 value) { union hv_ghcb *hv_ghcb; void **ghcb_base; unsigned long flags; - struct es_em_ctxt ctxt; if (!hv_ghcb_pg) return; @@ -120,8 +195,7 @@ void hv_ghcb_msr_write(u64 msr, u64 value) ghcb_set_rax(&hv_ghcb->ghcb, lower_32_bits(value)); ghcb_set_rdx(&hv_ghcb->ghcb, upper_32_bits(value)); - if (sev_es_ghcb_hv_call(&hv_ghcb->ghcb, false, &ctxt, - SVM_EXIT_MSR, 1, 0)) + if (hv_ghcb_hv_call(&hv_ghcb->ghcb, SVM_EXIT_MSR, 1, 0)) pr_warn("Fail to write msr via ghcb %llx.\n", msr); local_irq_restore(flags); @@ -133,7 +207,6 @@ void hv_ghcb_msr_read(u64 msr, u64 *value) union hv_ghcb *hv_ghcb; void **ghcb_base; unsigned long flags; - struct es_em_ctxt ctxt; /* Check size of union hv_ghcb here. */ BUILD_BUG_ON(sizeof(union hv_ghcb) != HV_HYP_PAGE_SIZE); @@ -152,8 +225,7 @@ void hv_ghcb_msr_read(u64 msr, u64 *value) } ghcb_set_rcx(&hv_ghcb->ghcb, msr); - if (sev_es_ghcb_hv_call(&hv_ghcb->ghcb, false, &ctxt, - SVM_EXIT_MSR, 0, 0)) + if (hv_ghcb_hv_call(&hv_ghcb->ghcb, SVM_EXIT_MSR, 0, 0)) pr_warn("Fail to read msr via ghcb %llx.\n", msr); else *value = (u64)lower_32_bits(hv_ghcb->ghcb.save.rax) diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 9b10c8c76087..9542c582d546 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -76,6 +76,7 @@ extern int alternatives_patched; extern void alternative_instructions(void); extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end); extern void apply_retpolines(s32 *start, s32 *end); +extern void apply_returns(s32 *start, s32 *end); extern void apply_ibt_endbr(s32 *start, s32 *end); struct module; diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 393f2bbb5e3a..a77b915d36a8 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -203,8 +203,8 @@ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ #define X86_FEATURE_XCOMPACTED ( 7*32+10) /* "" Use compacted XSTATE (XSAVES or XSAVEC) */ #define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */ -#define X86_FEATURE_RETPOLINE ( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */ -#define X86_FEATURE_RETPOLINE_LFENCE ( 7*32+13) /* "" Use LFENCE for Spectre variant 2 */ +#define X86_FEATURE_KERNEL_IBRS ( 7*32+12) /* "" Set/clear IBRS on kernel entry/exit */ +#define X86_FEATURE_RSB_VMEXIT ( 7*32+13) /* "" Fill RSB on VM-Exit */ #define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ #define X86_FEATURE_CDP_L2 ( 7*32+15) /* Code and Data Prioritization L2 */ #define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* "" MSR SPEC_CTRL is implemented */ @@ -296,6 +296,13 @@ #define X86_FEATURE_PER_THREAD_MBA (11*32+ 7) /* "" Per-thread Memory Bandwidth Allocation */ #define X86_FEATURE_SGX1 (11*32+ 8) /* "" Basic SGX */ #define X86_FEATURE_SGX2 (11*32+ 9) /* "" SGX Enclave Dynamic Memory Management (EDMM) */ +#define X86_FEATURE_ENTRY_IBPB (11*32+10) /* "" Issue an IBPB on kernel entry */ +#define X86_FEATURE_RRSBA_CTRL (11*32+11) /* "" RET prediction control */ +#define X86_FEATURE_RETPOLINE (11*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */ +#define X86_FEATURE_RETPOLINE_LFENCE (11*32+13) /* "" Use LFENCE for Spectre variant 2 */ +#define X86_FEATURE_RETHUNK (11*32+14) /* "" Use REturn THUNK */ +#define X86_FEATURE_UNRET (11*32+15) /* "" AMD BTB untrain return */ +#define X86_FEATURE_USE_IBPB_FW (11*32+16) /* "" Use IBPB during runtime firmware calls */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ @@ -316,6 +323,7 @@ #define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */ #define X86_FEATURE_AMD_SSB_NO (13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */ #define X86_FEATURE_CPPC (13*32+27) /* Collaborative Processor Performance Control */ +#define X86_FEATURE_BTC_NO (13*32+29) /* "" Not vulnerable to Branch Type Confusion */ #define X86_FEATURE_BRS (13*32+31) /* Branch Sampling available */ /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */ @@ -446,5 +454,7 @@ #define X86_BUG_TAA X86_BUG(22) /* CPU is affected by TSX Async Abort(TAA) */ #define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */ #define X86_BUG_SRBDS X86_BUG(24) /* CPU may leak RNG bits if not mitigated */ +#define X86_BUG_MMIO_STALE_DATA X86_BUG(25) /* CPU is affected by Processor MMIO Stale Data vulnerabilities */ +#define X86_BUG_RETBLEED X86_BUG(26) /* CPU is affected by RETBleed */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index 36369e76cc63..33d2cd04d254 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -50,6 +50,25 @@ # define DISABLE_PTI (1 << (X86_FEATURE_PTI & 31)) #endif +#ifdef CONFIG_RETPOLINE +# define DISABLE_RETPOLINE 0 +#else +# define DISABLE_RETPOLINE ((1 << (X86_FEATURE_RETPOLINE & 31)) | \ + (1 << (X86_FEATURE_RETPOLINE_LFENCE & 31))) +#endif + +#ifdef CONFIG_RETHUNK +# define DISABLE_RETHUNK 0 +#else +# define DISABLE_RETHUNK (1 << (X86_FEATURE_RETHUNK & 31)) +#endif + +#ifdef CONFIG_CPU_UNRET_ENTRY +# define DISABLE_UNRET 0 +#else +# define DISABLE_UNRET (1 << (X86_FEATURE_UNRET & 31)) +#endif + #ifdef CONFIG_INTEL_IOMMU_SVM # define DISABLE_ENQCMD 0 #else @@ -82,7 +101,7 @@ #define DISABLED_MASK8 (DISABLE_TDX_GUEST) #define DISABLED_MASK9 (DISABLE_SGX) #define DISABLED_MASK10 0 -#define DISABLED_MASK11 0 +#define DISABLED_MASK11 (DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET) #define DISABLED_MASK12 0 #define DISABLED_MASK13 0 #define DISABLED_MASK14 0 diff --git a/arch/x86/include/asm/e820/api.h b/arch/x86/include/asm/e820/api.h index 5a39ed59b6db..e8f58ddd06d9 100644 --- a/arch/x86/include/asm/e820/api.h +++ b/arch/x86/include/asm/e820/api.h @@ -4,9 +4,6 @@ #include <asm/e820/types.h> -struct device; -struct resource; - extern struct e820_table *e820_table; extern struct e820_table *e820_table_kexec; extern struct e820_table *e820_table_firmware; @@ -46,8 +43,6 @@ extern void e820__register_nosave_regions(unsigned long limit_pfn); extern int e820__get_entry_type(u64 start, u64 end); -extern void remove_e820_regions(struct device *dev, struct resource *avail); - /* * Returns true iff the specified range [start,end) is completely contained inside * the ISA region. diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 71943dce691e..9636742a80f2 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -323,7 +323,7 @@ static inline u32 efi64_convert_status(efi_status_t status) #define __efi64_argmap_get_memory_space_descriptor(phys, desc) \ (__efi64_split(phys), (desc)) -#define __efi64_argmap_set_memory_space_descriptor(phys, size, flags) \ +#define __efi64_argmap_set_memory_space_attributes(phys, size, flags) \ (__efi64_split(phys), __efi64_split(size), __efi64_split(flags)) /* diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 959d66b9be94..9217bd6cf0d1 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -653,6 +653,7 @@ struct kvm_vcpu_arch { u64 ia32_misc_enable_msr; u64 smbase; u64 smi_count; + bool at_instruction_boundary; bool tpr_access_reporting; bool xsaves_enabled; bool xfd_no_write_intercept; @@ -1046,14 +1047,77 @@ struct kvm_x86_msr_filter { }; enum kvm_apicv_inhibit { + + /********************************************************************/ + /* INHIBITs that are relevant to both Intel's APICv and AMD's AVIC. */ + /********************************************************************/ + + /* + * APIC acceleration is disabled by a module parameter + * and/or not supported in hardware. + */ APICV_INHIBIT_REASON_DISABLE, + + /* + * APIC acceleration is inhibited because AutoEOI feature is + * being used by a HyperV guest. + */ APICV_INHIBIT_REASON_HYPERV, + + /* + * APIC acceleration is inhibited because the userspace didn't yet + * enable the kernel/split irqchip. + */ + APICV_INHIBIT_REASON_ABSENT, + + /* APIC acceleration is inhibited because KVM_GUESTDBG_BLOCKIRQ + * (out of band, debug measure of blocking all interrupts on this vCPU) + * was enabled, to avoid AVIC/APICv bypassing it. + */ + APICV_INHIBIT_REASON_BLOCKIRQ, + + /* + * For simplicity, the APIC acceleration is inhibited + * first time either APIC ID or APIC base are changed by the guest + * from their reset values. + */ + APICV_INHIBIT_REASON_APIC_ID_MODIFIED, + APICV_INHIBIT_REASON_APIC_BASE_MODIFIED, + + /******************************************************/ + /* INHIBITs that are relevant only to the AMD's AVIC. */ + /******************************************************/ + + /* + * AVIC is inhibited on a vCPU because it runs a nested guest. + * + * This is needed because unlike APICv, the peers of this vCPU + * cannot use the doorbell mechanism to signal interrupts via AVIC when + * a vCPU runs nested. + */ APICV_INHIBIT_REASON_NESTED, + + /* + * On SVM, the wait for the IRQ window is implemented with pending vIRQ, + * which cannot be injected when the AVIC is enabled, thus AVIC + * is inhibited while KVM waits for IRQ window. + */ APICV_INHIBIT_REASON_IRQWIN, + + /* + * PIT (i8254) 're-inject' mode, relies on EOI intercept, + * which AVIC doesn't support for edge triggered interrupts. + */ APICV_INHIBIT_REASON_PIT_REINJ, + + /* + * AVIC is inhibited because the guest has x2apic in its CPUID. + */ APICV_INHIBIT_REASON_X2APIC, - APICV_INHIBIT_REASON_BLOCKIRQ, - APICV_INHIBIT_REASON_ABSENT, + + /* + * AVIC is disabled because SEV doesn't support it. + */ APICV_INHIBIT_REASON_SEV, }; @@ -1300,6 +1364,8 @@ struct kvm_vcpu_stat { u64 nested_run; u64 directed_yield_attempted; u64 directed_yield_successful; + u64 preemption_reported; + u64 preemption_other; u64 guest_mode; }; diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h index 85865f1645bd..73ca20049835 100644 --- a/arch/x86/include/asm/linkage.h +++ b/arch/x86/include/asm/linkage.h @@ -19,19 +19,27 @@ #define __ALIGN_STR __stringify(__ALIGN) #endif +#if defined(CONFIG_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO) +#define RET jmp __x86_return_thunk +#else /* CONFIG_RETPOLINE */ #ifdef CONFIG_SLS #define RET ret; int3 #else #define RET ret #endif +#endif /* CONFIG_RETPOLINE */ #else /* __ASSEMBLY__ */ +#if defined(CONFIG_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO) +#define ASM_RET "jmp __x86_return_thunk\n\t" +#else /* CONFIG_RETPOLINE */ #ifdef CONFIG_SLS #define ASM_RET "ret; int3\n\t" #else #define ASM_RET "ret\n\t" #endif +#endif /* CONFIG_RETPOLINE */ #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index a82f603d4312..61f0c206bff0 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -179,9 +179,13 @@ int hv_set_mem_host_visibility(unsigned long addr, int numpages, bool visible); #ifdef CONFIG_AMD_MEM_ENCRYPT void hv_ghcb_msr_write(u64 msr, u64 value); void hv_ghcb_msr_read(u64 msr, u64 *value); +bool hv_ghcb_negotiate_protocol(void); +void hv_ghcb_terminate(unsigned int set, unsigned int reason); #else static inline void hv_ghcb_msr_write(u64 msr, u64 value) {} static inline void hv_ghcb_msr_read(u64 msr, u64 *value) {} +static inline bool hv_ghcb_negotiate_protocol(void) { return false; } +static inline void hv_ghcb_terminate(unsigned int set, unsigned int reason) {} #endif extern bool hv_isolation_type_snp(void); diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 403e83b4adc8..cc615be27a54 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -51,6 +51,8 @@ #define SPEC_CTRL_STIBP BIT(SPEC_CTRL_STIBP_SHIFT) /* STIBP mask */ #define SPEC_CTRL_SSBD_SHIFT 2 /* Speculative Store Bypass Disable bit */ #define SPEC_CTRL_SSBD BIT(SPEC_CTRL_SSBD_SHIFT) /* Speculative Store Bypass Disable */ +#define SPEC_CTRL_RRSBA_DIS_S_SHIFT 6 /* Disable RRSBA behavior */ +#define SPEC_CTRL_RRSBA_DIS_S BIT(SPEC_CTRL_RRSBA_DIS_S_SHIFT) #define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ #define PRED_CMD_IBPB BIT(0) /* Indirect Branch Prediction Barrier */ @@ -93,6 +95,7 @@ #define MSR_IA32_ARCH_CAPABILITIES 0x0000010a #define ARCH_CAP_RDCL_NO BIT(0) /* Not susceptible to Meltdown */ #define ARCH_CAP_IBRS_ALL BIT(1) /* Enhanced IBRS support */ +#define ARCH_CAP_RSBA BIT(2) /* RET may use alternative branch predictors */ #define ARCH_CAP_SKIP_VMENTRY_L1DFLUSH BIT(3) /* Skip L1D flush on vmentry */ #define ARCH_CAP_SSB_NO BIT(4) /* * Not susceptible to Speculative Store Bypass @@ -116,6 +119,37 @@ * Not susceptible to * TSX Async Abort (TAA) vulnerabilities. */ +#define ARCH_CAP_SBDR_SSDP_NO BIT(13) /* + * Not susceptible to SBDR and SSDP + * variants of Processor MMIO stale data + * vulnerabilities. + */ +#define ARCH_CAP_FBSDP_NO BIT(14) /* + * Not susceptible to FBSDP variant of + * Processor MMIO stale data + * vulnerabilities. + */ +#define ARCH_CAP_PSDP_NO BIT(15) /* + * Not susceptible to PSDP variant of + * Processor MMIO stale data + * vulnerabilities. + */ +#define ARCH_CAP_FB_CLEAR BIT(17) /* + * VERW clears CPU fill buffer + * even on MDS_NO CPUs. + */ +#define ARCH_CAP_FB_CLEAR_CTRL BIT(18) /* + * MSR_IA32_MCU_OPT_CTRL[FB_CLEAR_DIS] + * bit available to control VERW + * behavior. + */ +#define ARCH_CAP_RRSBA BIT(19) /* + * Indicates RET may use predictors + * other than the RSB. With eIBRS + * enabled predictions in kernel mode + * are restricted to targets in + * kernel. + */ #define MSR_IA32_FLUSH_CMD 0x0000010b #define L1D_FLUSH BIT(0) /* @@ -133,6 +167,7 @@ #define MSR_IA32_MCU_OPT_CTRL 0x00000123 #define RNGDS_MITG_DIS BIT(0) /* SRBDS support */ #define RTM_ALLOW BIT(1) /* TSX development mode */ +#define FB_CLEAR_DIS BIT(3) /* CPU Fill buffer clear disable */ #define MSR_IA32_SYSENTER_CS 0x00000174 #define MSR_IA32_SYSENTER_ESP 0x00000175 @@ -542,6 +577,9 @@ /* Fam 17h MSRs */ #define MSR_F17H_IRPERF 0xc00000e9 +#define MSR_ZEN2_SPECTRAL_CHICKEN 0xc00110e3 +#define MSR_ZEN2_SPECTRAL_CHICKEN_BIT BIT_ULL(1) + /* Fam 16h MSRs */ #define MSR_F16H_L2I_PERF_CTL 0xc0010230 #define MSR_F16H_L2I_PERF_CTR 0xc0010231 diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index acbaeaf83b61..38a3e86e665e 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -11,6 +11,7 @@ #include <asm/cpufeatures.h> #include <asm/msr-index.h> #include <asm/unwind_hints.h> +#include <asm/percpu.h> #define RETPOLINE_THUNK_SIZE 32 @@ -76,6 +77,23 @@ .endm /* + * (ab)use RETPOLINE_SAFE on RET to annotate away 'bare' RET instructions + * vs RETBleed validation. + */ +#define ANNOTATE_UNRET_SAFE ANNOTATE_RETPOLINE_SAFE + +/* + * Abuse ANNOTATE_RETPOLINE_SAFE on a NOP to indicate UNRET_END, should + * eventually turn into it's own annotation. + */ +.macro ANNOTATE_UNRET_END +#ifdef CONFIG_DEBUG_ENTRY + ANNOTATE_RETPOLINE_SAFE + nop +#endif +.endm + +/* * JMP_NOSPEC and CALL_NOSPEC macros can be used instead of a simple * indirect jmp/call which may be susceptible to the Spectre variant 2 * attack. @@ -105,10 +123,34 @@ * monstrosity above, manually. */ .macro FILL_RETURN_BUFFER reg:req nr:req ftr:req -#ifdef CONFIG_RETPOLINE ALTERNATIVE "jmp .Lskip_rsb_\@", "", \ftr __FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP) .Lskip_rsb_\@: +.endm + +#ifdef CONFIG_CPU_UNRET_ENTRY +#define CALL_ZEN_UNTRAIN_RET "call zen_untrain_ret" +#else +#define CALL_ZEN_UNTRAIN_RET "" +#endif + +/* + * Mitigate RETBleed for AMD/Hygon Zen uarch. Requires KERNEL CR3 because the + * return thunk isn't mapped into the userspace tables (then again, AMD + * typically has NO_MELTDOWN). + * + * While zen_untrain_ret() doesn't clobber anything but requires stack, + * entry_ibpb() will clobber AX, CX, DX. + * + * As such, this must be placed after every *SWITCH_TO_KERNEL_CR3 at a point + * where we have a stack but before any RET instruction. + */ +.macro UNTRAIN_RET +#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) + ANNOTATE_UNRET_END + ALTERNATIVE_2 "", \ + CALL_ZEN_UNTRAIN_RET, X86_FEATURE_UNRET, \ + "call entry_ibpb", X86_FEATURE_ENTRY_IBPB #endif .endm @@ -120,17 +162,20 @@ _ASM_PTR " 999b\n\t" \ ".popsection\n\t" -#ifdef CONFIG_RETPOLINE - typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE]; +extern retpoline_thunk_t __x86_indirect_thunk_array[]; + +extern void __x86_return_thunk(void); +extern void zen_untrain_ret(void); +extern void entry_ibpb(void); + +#ifdef CONFIG_RETPOLINE #define GEN(reg) \ extern retpoline_thunk_t __x86_indirect_thunk_ ## reg; #include <asm/GEN-for-each-reg.h> #undef GEN -extern retpoline_thunk_t __x86_indirect_thunk_array[]; - #ifdef CONFIG_X86_64 /* @@ -193,6 +238,7 @@ enum spectre_v2_mitigation { SPECTRE_V2_EIBRS, SPECTRE_V2_EIBRS_RETPOLINE, SPECTRE_V2_EIBRS_LFENCE, + SPECTRE_V2_IBRS, }; /* The indirect branch speculation control variants */ @@ -235,6 +281,9 @@ static inline void indirect_branch_prediction_barrier(void) /* The Intel SPEC CTRL MSR base value cache */ extern u64 x86_spec_ctrl_base; +DECLARE_PER_CPU(u64, x86_spec_ctrl_current); +extern void write_spec_ctrl_current(u64 val, bool force); +extern u64 spec_ctrl_current(void); /* * With retpoline, we must use IBRS to restrict branch prediction @@ -244,18 +293,18 @@ extern u64 x86_spec_ctrl_base; */ #define firmware_restrict_branch_speculation_start() \ do { \ - u64 val = x86_spec_ctrl_base | SPEC_CTRL_IBRS; \ - \ preempt_disable(); \ - alternative_msr_write(MSR_IA32_SPEC_CTRL, val, \ + alternative_msr_write(MSR_IA32_SPEC_CTRL, \ + spec_ctrl_current() | SPEC_CTRL_IBRS, \ X86_FEATURE_USE_IBRS_FW); \ + alternative_msr_write(MSR_IA32_PRED_CMD, PRED_CMD_IBPB, \ + X86_FEATURE_USE_IBPB_FW); \ } while (0) #define firmware_restrict_branch_speculation_end() \ do { \ - u64 val = x86_spec_ctrl_base; \ - \ - alternative_msr_write(MSR_IA32_SPEC_CTRL, val, \ + alternative_msr_write(MSR_IA32_SPEC_CTRL, \ + spec_ctrl_current(), \ X86_FEATURE_USE_IBRS_FW); \ preempt_enable(); \ } while (0) @@ -269,6 +318,8 @@ DECLARE_STATIC_KEY_FALSE(mds_idle_clear); DECLARE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush); +DECLARE_STATIC_KEY_FALSE(mmio_stale_data_clear); + #include <asm/segment.h> /** diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h index f52a886d35cf..70533fdcbf02 100644 --- a/arch/x86/include/asm/pci_x86.h +++ b/arch/x86/include/asm/pci_x86.h @@ -69,6 +69,8 @@ void pcibios_scan_specific_bus(int busn); /* pci-irq.c */ +struct pci_dev; + struct irq_info { u8 bus, devfn; /* Bus, device and function */ struct { @@ -246,3 +248,9 @@ static inline void mmio_config_writel(void __iomem *pos, u32 val) # define x86_default_pci_init_irq NULL # define x86_default_pci_fixup_irqs NULL #endif + +#if defined(CONFIG_PCI) && defined(CONFIG_ACPI) +extern bool pci_use_e820; +#else +#define pci_use_e820 false +#endif diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 7590ac2570b9..f37cbff7354c 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -108,21 +108,21 @@ extern unsigned long _brk_end; void *extend_brk(size_t size, size_t align); /* - * Reserve space in the brk section. The name must be unique within the file, - * and somewhat descriptive. The size is in bytes. + * Reserve space in the .brk section, which is a block of memory from which the + * caller is allowed to allocate very early (before even memblock is available) + * by calling extend_brk(). All allocated memory will be eventually converted + * to memblock. Any leftover unallocated memory will be freed. * - * The allocation is done using inline asm (rather than using a section - * attribute on a normal variable) in order to allow the use of @nobits, so - * that it doesn't take up any space in the vmlinux file. + * The size is in bytes. */ -#define RESERVE_BRK(name, size) \ - asm(".pushsection .brk_reservation,\"aw\",@nobits\n\t" \ - ".brk." #name ":\n\t" \ - ".skip " __stringify(size) "\n\t" \ - ".size .brk." #name ", " __stringify(size) "\n\t" \ - ".popsection\n\t") +#define RESERVE_BRK(name, size) \ + __section(".bss..brk") __aligned(1) __used \ + static char __brk_##name[size] extern void probe_roms(void); + +void clear_bss(void); + #ifdef __i386__ asmlinkage void __init i386_start_kernel(void); @@ -133,12 +133,19 @@ asmlinkage void __init x86_64_start_reservations(char *real_mode_data); #endif /* __i386__ */ #endif /* _SETUP */ -#else -#define RESERVE_BRK(name,sz) \ - .pushsection .brk_reservation,"aw",@nobits; \ -.brk.name: \ -1: .skip sz; \ - .size .brk.name,.-1b; \ + +#else /* __ASSEMBLY */ + +.macro __RESERVE_BRK name, size + .pushsection .bss..brk, "aw" +SYM_DATA_START(__brk_\name) + .skip \size +SYM_DATA_END(__brk_\name) .popsection +.endm + +#define RESERVE_BRK(name, size) __RESERVE_BRK name, size + #endif /* __ASSEMBLY__ */ + #endif /* _ASM_X86_SETUP_H */ diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h index 19514524f0f8..4a23e52fe0ee 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -72,7 +72,6 @@ static inline u64 lower_bits(u64 val, unsigned int bits) struct real_mode_header; enum stack_type; -struct ghcb; /* Early IDT entry points for #VC handler */ extern void vc_no_ghcb(void); @@ -156,11 +155,7 @@ static __always_inline void sev_es_nmi_complete(void) __sev_es_nmi_complete(); } extern int __init sev_es_efi_map_ghcbs(pgd_t *pgd); -extern enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb, - bool set_ghcb_msr, - struct es_em_ctxt *ctxt, - u64 exit_code, u64 exit_info_1, - u64 exit_info_2); + static inline int rmpadjust(unsigned long vaddr, bool rmp_psize, unsigned long attrs) { int rc; diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h index 2d8dacd02643..343b722ccaf2 100644 --- a/arch/x86/include/asm/static_call.h +++ b/arch/x86/include/asm/static_call.h @@ -21,6 +21,16 @@ * relative displacement across sections. */ +/* + * The trampoline is 8 bytes and of the general form: + * + * jmp.d32 \func + * ud1 %esp, %ecx + * + * That trailing #UD provides both a speculation stop and serves as a unique + * 3 byte signature identifying static call trampolines. Also see tramp_ud[] + * and __static_call_fixup(). + */ #define __ARCH_DEFINE_STATIC_CALL_TRAMP(name, insns) \ asm(".pushsection .static_call.text, \"ax\" \n" \ ".align 4 \n" \ @@ -28,7 +38,7 @@ STATIC_CALL_TRAMP_STR(name) ": \n" \ ANNOTATE_NOENDBR \ insns " \n" \ - ".byte 0x53, 0x43, 0x54 \n" \ + ".byte 0x0f, 0xb9, 0xcc \n" \ ".type " STATIC_CALL_TRAMP_STR(name) ", @function \n" \ ".size " STATIC_CALL_TRAMP_STR(name) ", . - " STATIC_CALL_TRAMP_STR(name) " \n" \ ".popsection \n") @@ -36,8 +46,13 @@ #define ARCH_DEFINE_STATIC_CALL_TRAMP(name, func) \ __ARCH_DEFINE_STATIC_CALL_TRAMP(name, ".byte 0xe9; .long " #func " - (. + 4)") +#ifdef CONFIG_RETHUNK +#define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) \ + __ARCH_DEFINE_STATIC_CALL_TRAMP(name, "jmp __x86_return_thunk") +#else #define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) \ __ARCH_DEFINE_STATIC_CALL_TRAMP(name, "ret; int3; nop; nop; nop") +#endif #define ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name) \ ARCH_DEFINE_STATIC_CALL_TRAMP(name, __static_call_return0) @@ -48,4 +63,6 @@ ".long " STATIC_CALL_KEY_STR(name) " - . \n" \ ".popsection \n") +extern bool __static_call_fixup(void *tramp, u8 op, void *dest); + #endif /* _ASM_STATIC_CALL_H */ diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h index 1bfe979bb9bc..580636cdc257 100644 --- a/arch/x86/include/asm/tlb.h +++ b/arch/x86/include/asm/tlb.h @@ -2,9 +2,6 @@ #ifndef _ASM_X86_TLB_H #define _ASM_X86_TLB_H -#define tlb_start_vma(tlb, vma) do { } while (0) -#define tlb_end_vma(tlb, vma) do { } while (0) - #define tlb_flush tlb_flush static inline void tlb_flush(struct mmu_gather *tlb); diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 35f222aa66bf..913e593a3b45 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -439,7 +439,7 @@ do { \ [ptr] "+m" (*_ptr), \ [old] "+a" (__old) \ : [new] ltype (__new) \ - : "memory", "cc"); \ + : "memory"); \ if (unlikely(__err)) \ goto label; \ if (unlikely(!success)) \ diff --git a/arch/x86/include/asm/unwind_hints.h b/arch/x86/include/asm/unwind_hints.h index 8b33674288ea..f66fbe6537dd 100644 --- a/arch/x86/include/asm/unwind_hints.h +++ b/arch/x86/include/asm/unwind_hints.h @@ -8,7 +8,11 @@ #ifdef __ASSEMBLY__ .macro UNWIND_HINT_EMPTY - UNWIND_HINT sp_reg=ORC_REG_UNDEFINED type=UNWIND_HINT_TYPE_CALL end=1 + UNWIND_HINT type=UNWIND_HINT_TYPE_CALL end=1 +.endm + +.macro UNWIND_HINT_ENTRY + UNWIND_HINT type=UNWIND_HINT_TYPE_ENTRY end=1 .endm .macro UNWIND_HINT_REGS base=%rsp offset=0 indirect=0 extra=1 partial=0 @@ -52,6 +56,14 @@ UNWIND_HINT sp_reg=ORC_REG_SP sp_offset=8 type=UNWIND_HINT_TYPE_FUNC .endm +.macro UNWIND_HINT_SAVE + UNWIND_HINT type=UNWIND_HINT_TYPE_SAVE +.endm + +.macro UNWIND_HINT_RESTORE + UNWIND_HINT type=UNWIND_HINT_TYPE_RESTORE +.endm + #else #define UNWIND_HINT_FUNC \ diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h index bea5cdcdf532..e02a8a8ef23c 100644 --- a/arch/x86/include/uapi/asm/bootparam.h +++ b/arch/x86/include/uapi/asm/bootparam.h @@ -15,7 +15,7 @@ #define SETUP_INDIRECT (1<<31) /* SETUP_INDIRECT | max(SETUP_*) */ -#define SETUP_TYPE_MAX (SETUP_INDIRECT | SETUP_JAILHOUSE) +#define SETUP_TYPE_MAX (SETUP_INDIRECT | SETUP_CC_BLOB) /* ram_size flags */ #define RAMDISK_IMAGE_START_MASK 0x07FF diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 03364dc40d8d..4c8b6ae802ac 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -36,10 +36,6 @@ KCSAN_SANITIZE := n OBJECT_FILES_NON_STANDARD_test_nx.o := y -ifdef CONFIG_FRAME_POINTER -OBJECT_FILES_NON_STANDARD_ftrace_$(BITS).o := y -endif - # If instrumentation of this dir is enabled, boot hangs during first second. # Probably could be more selective here, but note that files related to irqs, # boot, dumpstack/stacktrace, etc are either non-interesting or can lead to diff --git a/arch/x86/kernel/acpi/cppc.c b/arch/x86/kernel/acpi/cppc.c index 8b8cbf22461a..8d8752b44f11 100644 --- a/arch/x86/kernel/acpi/cppc.c +++ b/arch/x86/kernel/acpi/cppc.c @@ -11,6 +11,22 @@ /* Refer to drivers/acpi/cppc_acpi.c for the description of functions */ +bool cpc_supported_by_cpu(void) +{ + switch (boot_cpu_data.x86_vendor) { + case X86_VENDOR_AMD: + case X86_VENDOR_HYGON: + if (boot_cpu_data.x86 == 0x19 && ((boot_cpu_data.x86_model <= 0x0f) || + (boot_cpu_data.x86_model >= 0x20 && boot_cpu_data.x86_model <= 0x2f))) + return true; + else if (boot_cpu_data.x86 == 0x17 && + boot_cpu_data.x86_model >= 0x70 && boot_cpu_data.x86_model <= 0x7f) + return true; + return boot_cpu_has(X86_FEATURE_CPPC); + } + return false; +} + bool cpc_ffh_supported(void) { return true; diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index e257f6c80372..62f6b8b7c4a5 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -115,6 +115,7 @@ static void __init_or_module add_nops(void *insns, unsigned int len) } extern s32 __retpoline_sites[], __retpoline_sites_end[]; +extern s32 __return_sites[], __return_sites_end[]; extern s32 __ibt_endbr_seal[], __ibt_endbr_seal_end[]; extern struct alt_instr __alt_instructions[], __alt_instructions_end[]; extern s32 __smp_locks[], __smp_locks_end[]; @@ -507,9 +508,78 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) } } +#ifdef CONFIG_RETHUNK +/* + * Rewrite the compiler generated return thunk tail-calls. + * + * For example, convert: + * + * JMP __x86_return_thunk + * + * into: + * + * RET + */ +static int patch_return(void *addr, struct insn *insn, u8 *bytes) +{ + int i = 0; + + if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) + return -1; + + bytes[i++] = RET_INSN_OPCODE; + + for (; i < insn->length;) + bytes[i++] = INT3_INSN_OPCODE; + + return i; +} + +void __init_or_module noinline apply_returns(s32 *start, s32 *end) +{ + s32 *s; + + for (s = start; s < end; s++) { + void *dest = NULL, *addr = (void *)s + *s; + struct insn insn; + int len, ret; + u8 bytes[16]; + u8 op; + + ret = insn_decode_kernel(&insn, addr); + if (WARN_ON_ONCE(ret < 0)) + continue; + + op = insn.opcode.bytes[0]; + if (op == JMP32_INSN_OPCODE) + dest = addr + insn.length + insn.immediate.value; + + if (__static_call_fixup(addr, op, dest) || + WARN_ONCE(dest != &__x86_return_thunk, + "missing return thunk: %pS-%pS: %*ph", + addr, dest, 5, addr)) + continue; + + DPRINTK("return thunk at: %pS (%px) len: %d to: %pS", + addr, addr, insn.length, + addr + insn.length + insn.immediate.value); + + len = patch_return(addr, &insn, bytes); + if (len == insn.length) { + DUMP_BYTES(((u8*)addr), len, "%px: orig: ", addr); + DUMP_BYTES(((u8*)bytes), len, "%px: repl: ", addr); + text_poke_early(addr, bytes, len); + } + } +} +#else +void __init_or_module noinline apply_returns(s32 *start, s32 *end) { } +#endif /* CONFIG_RETHUNK */ + #else /* !CONFIG_RETPOLINE || !CONFIG_OBJTOOL */ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) { } +void __init_or_module noinline apply_returns(s32 *start, s32 *end) { } #endif /* CONFIG_RETPOLINE && CONFIG_OBJTOOL */ @@ -860,6 +930,7 @@ void __init alternative_instructions(void) * those can rewrite the retpoline thunks. */ apply_retpolines(__retpoline_sites, __retpoline_sites_end); + apply_returns(__return_sites, __return_sites_end); /* * Then patch alternatives, such that those paravirt calls that are in diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 437308004ef2..cb50589a7102 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -19,6 +19,7 @@ #include <asm/suspend.h> #include <asm/tlbflush.h> #include <asm/tdx.h> +#include "../kvm/vmx/vmx.h" #ifdef CONFIG_XEN #include <xen/interface/xen.h> @@ -107,4 +108,9 @@ static void __used common(void) OFFSET(TSS_sp0, tss_struct, x86_tss.sp0); OFFSET(TSS_sp1, tss_struct, x86_tss.sp1); OFFSET(TSS_sp2, tss_struct, x86_tss.sp2); + + if (IS_ENABLED(CONFIG_KVM_INTEL)) { + BLANK(); + OFFSET(VMX_spec_ctrl, vcpu_vmx, spec_ctrl); + } } diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 0c0b09796ced..35d5288394cb 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -862,6 +862,28 @@ static void init_amd_bd(struct cpuinfo_x86 *c) clear_rdrand_cpuid_bit(c); } +void init_spectral_chicken(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_CPU_UNRET_ENTRY + u64 value; + + /* + * On Zen2 we offer this chicken (bit) on the altar of Speculation. + * + * This suppresses speculation from the middle of a basic block, i.e. it + * suppresses non-branch predictions. + * + * We use STIBP as a heuristic to filter out Zen2 from the rest of F17H + */ + if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && cpu_has(c, X86_FEATURE_AMD_STIBP)) { + if (!rdmsrl_safe(MSR_ZEN2_SPECTRAL_CHICKEN, &value)) { + value |= MSR_ZEN2_SPECTRAL_CHICKEN_BIT; + wrmsrl_safe(MSR_ZEN2_SPECTRAL_CHICKEN, value); + } + } +#endif +} + static void init_amd_zn(struct cpuinfo_x86 *c) { set_cpu_cap(c, X86_FEATURE_ZEN); @@ -870,12 +892,21 @@ static void init_amd_zn(struct cpuinfo_x86 *c) node_reclaim_distance = 32; #endif - /* - * Fix erratum 1076: CPB feature bit not being set in CPUID. - * Always set it, except when running under a hypervisor. - */ - if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && !cpu_has(c, X86_FEATURE_CPB)) - set_cpu_cap(c, X86_FEATURE_CPB); + /* Fix up CPUID bits, but only if not virtualised. */ + if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) { + + /* Erratum 1076: CPB feature bit not being set in CPUID. */ + if (!cpu_has(c, X86_FEATURE_CPB)) + set_cpu_cap(c, X86_FEATURE_CPB); + + /* + * Zen3 (Fam19 model < 0x10) parts are not susceptible to + * Branch Type Confusion, but predate the allocation of the + * BTC_NO bit. + */ + if (c->x86 == 0x19 && !cpu_has(c, X86_FEATURE_BTC_NO)) + set_cpu_cap(c, X86_FEATURE_BTC_NO); + } } static void init_amd(struct cpuinfo_x86 *c) @@ -907,7 +938,8 @@ static void init_amd(struct cpuinfo_x86 *c) case 0x12: init_amd_ln(c); break; case 0x15: init_amd_bd(c); break; case 0x16: init_amd_jg(c); break; - case 0x17: fallthrough; + case 0x17: init_spectral_chicken(c); + fallthrough; case 0x19: init_amd_zn(c); break; } diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index d879a6c93609..6761668100b9 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -38,24 +38,52 @@ static void __init spectre_v1_select_mitigation(void); static void __init spectre_v2_select_mitigation(void); +static void __init retbleed_select_mitigation(void); +static void __init spectre_v2_user_select_mitigation(void); static void __init ssb_select_mitigation(void); static void __init l1tf_select_mitigation(void); static void __init mds_select_mitigation(void); -static void __init mds_print_mitigation(void); +static void __init md_clear_update_mitigation(void); +static void __init md_clear_select_mitigation(void); static void __init taa_select_mitigation(void); +static void __init mmio_select_mitigation(void); static void __init srbds_select_mitigation(void); static void __init l1d_flush_select_mitigation(void); -/* The base value of the SPEC_CTRL MSR that always has to be preserved. */ +/* The base value of the SPEC_CTRL MSR without task-specific bits set */ u64 x86_spec_ctrl_base; EXPORT_SYMBOL_GPL(x86_spec_ctrl_base); + +/* The current value of the SPEC_CTRL MSR with task-specific bits set */ +DEFINE_PER_CPU(u64, x86_spec_ctrl_current); +EXPORT_SYMBOL_GPL(x86_spec_ctrl_current); + static DEFINE_MUTEX(spec_ctrl_mutex); /* - * The vendor and possibly platform specific bits which can be modified in - * x86_spec_ctrl_base. + * Keep track of the SPEC_CTRL MSR value for the current task, which may differ + * from x86_spec_ctrl_base due to STIBP/SSB in __speculation_ctrl_update(). */ -static u64 __ro_after_init x86_spec_ctrl_mask = SPEC_CTRL_IBRS; +void write_spec_ctrl_current(u64 val, bool force) +{ + if (this_cpu_read(x86_spec_ctrl_current) == val) + return; + + this_cpu_write(x86_spec_ctrl_current, val); + + /* + * When KERNEL_IBRS this MSR is written on return-to-user, unless + * forced the update can be delayed until that time. + */ + if (force || !cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS)) + wrmsrl(MSR_IA32_SPEC_CTRL, val); +} + +u64 spec_ctrl_current(void) +{ + return this_cpu_read(x86_spec_ctrl_current); +} +EXPORT_SYMBOL_GPL(spec_ctrl_current); /* * AMD specific MSR info for Speculative Store Bypass control. @@ -85,6 +113,10 @@ EXPORT_SYMBOL_GPL(mds_idle_clear); */ DEFINE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush); +/* Controls CPU Fill buffer clear before KVM guest MMIO accesses */ +DEFINE_STATIC_KEY_FALSE(mmio_stale_data_clear); +EXPORT_SYMBOL_GPL(mmio_stale_data_clear); + void __init check_bugs(void) { identify_boot_cpu(); @@ -108,26 +140,27 @@ void __init check_bugs(void) if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) rdmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); - /* Allow STIBP in MSR_SPEC_CTRL if supported */ - if (boot_cpu_has(X86_FEATURE_STIBP)) - x86_spec_ctrl_mask |= SPEC_CTRL_STIBP; - /* Select the proper CPU mitigations before patching alternatives: */ spectre_v1_select_mitigation(); spectre_v2_select_mitigation(); + /* + * retbleed_select_mitigation() relies on the state set by + * spectre_v2_select_mitigation(); specifically it wants to know about + * spectre_v2=ibrs. + */ + retbleed_select_mitigation(); + /* + * spectre_v2_user_select_mitigation() relies on the state set by + * retbleed_select_mitigation(); specifically the STIBP selection is + * forced for UNRET. + */ + spectre_v2_user_select_mitigation(); ssb_select_mitigation(); l1tf_select_mitigation(); - mds_select_mitigation(); - taa_select_mitigation(); + md_clear_select_mitigation(); srbds_select_mitigation(); l1d_flush_select_mitigation(); - /* - * As MDS and TAA mitigations are inter-related, print MDS - * mitigation until after TAA mitigation selection is done. - */ - mds_print_mitigation(); - arch_smt_update(); #ifdef CONFIG_X86_32 @@ -162,31 +195,17 @@ void __init check_bugs(void) #endif } +/* + * NOTE: This function is *only* called for SVM. VMX spec_ctrl handling is + * done in vmenter.S. + */ void x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest) { - u64 msrval, guestval, hostval = x86_spec_ctrl_base; + u64 msrval, guestval = guest_spec_ctrl, hostval = spec_ctrl_current(); struct thread_info *ti = current_thread_info(); - /* Is MSR_SPEC_CTRL implemented ? */ if (static_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) { - /* - * Restrict guest_spec_ctrl to supported values. Clear the - * modifiable bits in the host base value and or the - * modifiable bits from the guest value. - */ - guestval = hostval & ~x86_spec_ctrl_mask; - guestval |= guest_spec_ctrl & x86_spec_ctrl_mask; - - /* SSBD controlled in MSR_SPEC_CTRL */ - if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || - static_cpu_has(X86_FEATURE_AMD_SSBD)) - hostval |= ssbd_tif_to_spec_ctrl(ti->flags); - - /* Conditional STIBP enabled? */ - if (static_branch_unlikely(&switch_to_cond_stibp)) - hostval |= stibp_tif_to_spec_ctrl(ti->flags); - if (hostval != guestval) { msrval = setguest ? guestval : hostval; wrmsrl(MSR_IA32_SPEC_CTRL, msrval); @@ -267,14 +286,6 @@ static void __init mds_select_mitigation(void) } } -static void __init mds_print_mitigation(void) -{ - if (!boot_cpu_has_bug(X86_BUG_MDS) || cpu_mitigations_off()) - return; - - pr_info("%s\n", mds_strings[mds_mitigation]); -} - static int __init mds_cmdline(char *str) { if (!boot_cpu_has_bug(X86_BUG_MDS)) @@ -329,7 +340,7 @@ static void __init taa_select_mitigation(void) /* TSX previously disabled by tsx=off */ if (!boot_cpu_has(X86_FEATURE_RTM)) { taa_mitigation = TAA_MITIGATION_TSX_DISABLED; - goto out; + return; } if (cpu_mitigations_off()) { @@ -343,7 +354,7 @@ static void __init taa_select_mitigation(void) */ if (taa_mitigation == TAA_MITIGATION_OFF && mds_mitigation == MDS_MITIGATION_OFF) - goto out; + return; if (boot_cpu_has(X86_FEATURE_MD_CLEAR)) taa_mitigation = TAA_MITIGATION_VERW; @@ -375,18 +386,6 @@ static void __init taa_select_mitigation(void) if (taa_nosmt || cpu_mitigations_auto_nosmt()) cpu_smt_disable(false); - - /* - * Update MDS mitigation, if necessary, as the mds_user_clear is - * now enabled for TAA mitigation. - */ - if (mds_mitigation == MDS_MITIGATION_OFF && - boot_cpu_has_bug(X86_BUG_MDS)) { - mds_mitigation = MDS_MITIGATION_FULL; - mds_select_mitigation(); - } -out: - pr_info("%s\n", taa_strings[taa_mitigation]); } static int __init tsx_async_abort_parse_cmdline(char *str) @@ -411,6 +410,151 @@ static int __init tsx_async_abort_parse_cmdline(char *str) early_param("tsx_async_abort", tsx_async_abort_parse_cmdline); #undef pr_fmt +#define pr_fmt(fmt) "MMIO Stale Data: " fmt + +enum mmio_mitigations { + MMIO_MITIGATION_OFF, + MMIO_MITIGATION_UCODE_NEEDED, + MMIO_MITIGATION_VERW, +}; + +/* Default mitigation for Processor MMIO Stale Data vulnerabilities */ +static enum mmio_mitigations mmio_mitigation __ro_after_init = MMIO_MITIGATION_VERW; +static bool mmio_nosmt __ro_after_init = false; + +static const char * const mmio_strings[] = { + [MMIO_MITIGATION_OFF] = "Vulnerable", + [MMIO_MITIGATION_UCODE_NEEDED] = "Vulnerable: Clear CPU buffers attempted, no microcode", + [MMIO_MITIGATION_VERW] = "Mitigation: Clear CPU buffers", +}; + +static void __init mmio_select_mitigation(void) +{ + u64 ia32_cap; + + if (!boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA) || + cpu_mitigations_off()) { + mmio_mitigation = MMIO_MITIGATION_OFF; + return; + } + + if (mmio_mitigation == MMIO_MITIGATION_OFF) + return; + + ia32_cap = x86_read_arch_cap_msr(); + + /* + * Enable CPU buffer clear mitigation for host and VMM, if also affected + * by MDS or TAA. Otherwise, enable mitigation for VMM only. + */ + if (boot_cpu_has_bug(X86_BUG_MDS) || (boot_cpu_has_bug(X86_BUG_TAA) && + boot_cpu_has(X86_FEATURE_RTM))) + static_branch_enable(&mds_user_clear); + else + static_branch_enable(&mmio_stale_data_clear); + + /* + * If Processor-MMIO-Stale-Data bug is present and Fill Buffer data can + * be propagated to uncore buffers, clearing the Fill buffers on idle + * is required irrespective of SMT state. + */ + if (!(ia32_cap & ARCH_CAP_FBSDP_NO)) + static_branch_enable(&mds_idle_clear); + + /* + * Check if the system has the right microcode. + * + * CPU Fill buffer clear mitigation is enumerated by either an explicit + * FB_CLEAR or by the presence of both MD_CLEAR and L1D_FLUSH on MDS + * affected systems. + */ + if ((ia32_cap & ARCH_CAP_FB_CLEAR) || + (boot_cpu_has(X86_FEATURE_MD_CLEAR) && + boot_cpu_has(X86_FEATURE_FLUSH_L1D) && + !(ia32_cap & ARCH_CAP_MDS_NO))) + mmio_mitigation = MMIO_MITIGATION_VERW; + else + mmio_mitigation = MMIO_MITIGATION_UCODE_NEEDED; + + if (mmio_nosmt || cpu_mitigations_auto_nosmt()) + cpu_smt_disable(false); +} + +static int __init mmio_stale_data_parse_cmdline(char *str) +{ + if (!boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) + return 0; + + if (!str) + return -EINVAL; + + if (!strcmp(str, "off")) { + mmio_mitigation = MMIO_MITIGATION_OFF; + } else if (!strcmp(str, "full")) { + mmio_mitigation = MMIO_MITIGATION_VERW; + } else if (!strcmp(str, "full,nosmt")) { + mmio_mitigation = MMIO_MITIGATION_VERW; + mmio_nosmt = true; + } + + return 0; +} +early_param("mmio_stale_data", mmio_stale_data_parse_cmdline); + +#undef pr_fmt +#define pr_fmt(fmt) "" fmt + +static void __init md_clear_update_mitigation(void) +{ + if (cpu_mitigations_off()) + return; + + if (!static_key_enabled(&mds_user_clear)) + goto out; + + /* + * mds_user_clear is now enabled. Update MDS, TAA and MMIO Stale Data + * mitigation, if necessary. + */ + if (mds_mitigation == MDS_MITIGATION_OFF && + boot_cpu_has_bug(X86_BUG_MDS)) { + mds_mitigation = MDS_MITIGATION_FULL; + mds_select_mitigation(); + } + if (taa_mitigation == TAA_MITIGATION_OFF && + boot_cpu_has_bug(X86_BUG_TAA)) { + taa_mitigation = TAA_MITIGATION_VERW; + taa_select_mitigation(); + } + if (mmio_mitigation == MMIO_MITIGATION_OFF && + boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) { + mmio_mitigation = MMIO_MITIGATION_VERW; + mmio_select_mitigation(); + } +out: + if (boot_cpu_has_bug(X86_BUG_MDS)) + pr_info("MDS: %s\n", mds_strings[mds_mitigation]); + if (boot_cpu_has_bug(X86_BUG_TAA)) + pr_info("TAA: %s\n", taa_strings[taa_mitigation]); + if (boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) + pr_info("MMIO Stale Data: %s\n", mmio_strings[mmio_mitigation]); +} + +static void __init md_clear_select_mitigation(void) +{ + mds_select_mitigation(); + taa_select_mitigation(); + mmio_select_mitigation(); + + /* + * As MDS, TAA and MMIO Stale Data mitigations are inter-related, update + * and print their mitigation after MDS, TAA and MMIO Stale Data + * mitigation selection is done. + */ + md_clear_update_mitigation(); +} + +#undef pr_fmt #define pr_fmt(fmt) "SRBDS: " fmt enum srbds_mitigations { @@ -478,11 +622,13 @@ static void __init srbds_select_mitigation(void) return; /* - * Check to see if this is one of the MDS_NO systems supporting - * TSX that are only exposed to SRBDS when TSX is enabled. + * Check to see if this is one of the MDS_NO systems supporting TSX that + * are only exposed to SRBDS when TSX is enabled or when CPU is affected + * by Processor MMIO Stale Data vulnerability. */ ia32_cap = x86_read_arch_cap_msr(); - if ((ia32_cap & ARCH_CAP_MDS_NO) && !boot_cpu_has(X86_FEATURE_RTM)) + if ((ia32_cap & ARCH_CAP_MDS_NO) && !boot_cpu_has(X86_FEATURE_RTM) && + !boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) srbds_mitigation = SRBDS_MITIGATION_TSX_OFF; else if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) srbds_mitigation = SRBDS_MITIGATION_HYPERVISOR; @@ -626,12 +772,180 @@ static int __init nospectre_v1_cmdline(char *str) } early_param("nospectre_v1", nospectre_v1_cmdline); -#undef pr_fmt -#define pr_fmt(fmt) "Spectre V2 : " fmt - static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init = SPECTRE_V2_NONE; +#undef pr_fmt +#define pr_fmt(fmt) "RETBleed: " fmt + +enum retbleed_mitigation { + RETBLEED_MITIGATION_NONE, + RETBLEED_MITIGATION_UNRET, + RETBLEED_MITIGATION_IBPB, + RETBLEED_MITIGATION_IBRS, + RETBLEED_MITIGATION_EIBRS, +}; + +enum retbleed_mitigation_cmd { + RETBLEED_CMD_OFF, + RETBLEED_CMD_AUTO, + RETBLEED_CMD_UNRET, + RETBLEED_CMD_IBPB, +}; + +static const char * const retbleed_strings[] = { + [RETBLEED_MITIGATION_NONE] = "Vulnerable", + [RETBLEED_MITIGATION_UNRET] = "Mitigation: untrained return thunk", + [RETBLEED_MITIGATION_IBPB] = "Mitigation: IBPB", + [RETBLEED_MITIGATION_IBRS] = "Mitigation: IBRS", + [RETBLEED_MITIGATION_EIBRS] = "Mitigation: Enhanced IBRS", +}; + +static enum retbleed_mitigation retbleed_mitigation __ro_after_init = + RETBLEED_MITIGATION_NONE; +static enum retbleed_mitigation_cmd retbleed_cmd __ro_after_init = + RETBLEED_CMD_AUTO; + +static int __ro_after_init retbleed_nosmt = false; + +static int __init retbleed_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + while (str) { + char *next = strchr(str, ','); + if (next) { + *next = 0; + next++; + } + + if (!strcmp(str, "off")) { + retbleed_cmd = RETBLEED_CMD_OFF; + } else if (!strcmp(str, "auto")) { + retbleed_cmd = RETBLEED_CMD_AUTO; + } else if (!strcmp(str, "unret")) { + retbleed_cmd = RETBLEED_CMD_UNRET; + } else if (!strcmp(str, "ibpb")) { + retbleed_cmd = RETBLEED_CMD_IBPB; + } else if (!strcmp(str, "nosmt")) { + retbleed_nosmt = true; + } else { + pr_err("Ignoring unknown retbleed option (%s).", str); + } + + str = next; + } + + return 0; +} +early_param("retbleed", retbleed_parse_cmdline); + +#define RETBLEED_UNTRAIN_MSG "WARNING: BTB untrained return thunk mitigation is only effective on AMD/Hygon!\n" +#define RETBLEED_INTEL_MSG "WARNING: Spectre v2 mitigation leaves CPU vulnerable to RETBleed attacks, data leaks possible!\n" + +static void __init retbleed_select_mitigation(void) +{ + bool mitigate_smt = false; + + if (!boot_cpu_has_bug(X86_BUG_RETBLEED) || cpu_mitigations_off()) + return; + + switch (retbleed_cmd) { + case RETBLEED_CMD_OFF: + return; + + case RETBLEED_CMD_UNRET: + if (IS_ENABLED(CONFIG_CPU_UNRET_ENTRY)) { + retbleed_mitigation = RETBLEED_MITIGATION_UNRET; + } else { + pr_err("WARNING: kernel not compiled with CPU_UNRET_ENTRY.\n"); + goto do_cmd_auto; + } + break; + + case RETBLEED_CMD_IBPB: + if (!boot_cpu_has(X86_FEATURE_IBPB)) { + pr_err("WARNING: CPU does not support IBPB.\n"); + goto do_cmd_auto; + } else if (IS_ENABLED(CONFIG_CPU_IBPB_ENTRY)) { + retbleed_mitigation = RETBLEED_MITIGATION_IBPB; + } else { + pr_err("WARNING: kernel not compiled with CPU_IBPB_ENTRY.\n"); + goto do_cmd_auto; + } + break; + +do_cmd_auto: + case RETBLEED_CMD_AUTO: + default: + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) { + if (IS_ENABLED(CONFIG_CPU_UNRET_ENTRY)) + retbleed_mitigation = RETBLEED_MITIGATION_UNRET; + else if (IS_ENABLED(CONFIG_CPU_IBPB_ENTRY) && boot_cpu_has(X86_FEATURE_IBPB)) + retbleed_mitigation = RETBLEED_MITIGATION_IBPB; + } + + /* + * The Intel mitigation (IBRS or eIBRS) was already selected in + * spectre_v2_select_mitigation(). 'retbleed_mitigation' will + * be set accordingly below. + */ + + break; + } + + switch (retbleed_mitigation) { + case RETBLEED_MITIGATION_UNRET: + setup_force_cpu_cap(X86_FEATURE_RETHUNK); + setup_force_cpu_cap(X86_FEATURE_UNRET); + + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && + boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) + pr_err(RETBLEED_UNTRAIN_MSG); + + mitigate_smt = true; + break; + + case RETBLEED_MITIGATION_IBPB: + setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB); + mitigate_smt = true; + break; + + default: + break; + } + + if (mitigate_smt && !boot_cpu_has(X86_FEATURE_STIBP) && + (retbleed_nosmt || cpu_mitigations_auto_nosmt())) + cpu_smt_disable(false); + + /* + * Let IBRS trump all on Intel without affecting the effects of the + * retbleed= cmdline option. + */ + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) { + switch (spectre_v2_enabled) { + case SPECTRE_V2_IBRS: + retbleed_mitigation = RETBLEED_MITIGATION_IBRS; + break; + case SPECTRE_V2_EIBRS: + case SPECTRE_V2_EIBRS_RETPOLINE: + case SPECTRE_V2_EIBRS_LFENCE: + retbleed_mitigation = RETBLEED_MITIGATION_EIBRS; + break; + default: + pr_err(RETBLEED_INTEL_MSG); + } + } + + pr_info("%s\n", retbleed_strings[retbleed_mitigation]); +} + +#undef pr_fmt +#define pr_fmt(fmt) "Spectre V2 : " fmt + static enum spectre_v2_user_mitigation spectre_v2_user_stibp __ro_after_init = SPECTRE_V2_USER_NONE; static enum spectre_v2_user_mitigation spectre_v2_user_ibpb __ro_after_init = @@ -661,6 +975,7 @@ static inline const char *spectre_v2_module_string(void) { return ""; } #define SPECTRE_V2_LFENCE_MSG "WARNING: LFENCE mitigation is not recommended for this CPU, data leaks possible!\n" #define SPECTRE_V2_EIBRS_EBPF_MSG "WARNING: Unprivileged eBPF is enabled with eIBRS on, data leaks possible via Spectre v2 BHB attacks!\n" #define SPECTRE_V2_EIBRS_LFENCE_EBPF_SMT_MSG "WARNING: Unprivileged eBPF is enabled with eIBRS+LFENCE mitigation and SMT, data leaks possible via Spectre v2 BHB attacks!\n" +#define SPECTRE_V2_IBRS_PERF_MSG "WARNING: IBRS mitigation selected on Enhanced IBRS CPU, this may cause unnecessary performance loss\n" #ifdef CONFIG_BPF_SYSCALL void unpriv_ebpf_notify(int new_state) @@ -702,6 +1017,7 @@ enum spectre_v2_mitigation_cmd { SPECTRE_V2_CMD_EIBRS, SPECTRE_V2_CMD_EIBRS_RETPOLINE, SPECTRE_V2_CMD_EIBRS_LFENCE, + SPECTRE_V2_CMD_IBRS, }; enum spectre_v2_user_cmd { @@ -742,13 +1058,15 @@ static void __init spec_v2_user_print_cond(const char *reason, bool secure) pr_info("spectre_v2_user=%s forced on command line.\n", reason); } +static __ro_after_init enum spectre_v2_mitigation_cmd spectre_v2_cmd; + static enum spectre_v2_user_cmd __init -spectre_v2_parse_user_cmdline(enum spectre_v2_mitigation_cmd v2_cmd) +spectre_v2_parse_user_cmdline(void) { char arg[20]; int ret, i; - switch (v2_cmd) { + switch (spectre_v2_cmd) { case SPECTRE_V2_CMD_NONE: return SPECTRE_V2_USER_CMD_NONE; case SPECTRE_V2_CMD_FORCE: @@ -774,15 +1092,16 @@ spectre_v2_parse_user_cmdline(enum spectre_v2_mitigation_cmd v2_cmd) return SPECTRE_V2_USER_CMD_AUTO; } -static inline bool spectre_v2_in_eibrs_mode(enum spectre_v2_mitigation mode) +static inline bool spectre_v2_in_ibrs_mode(enum spectre_v2_mitigation mode) { - return (mode == SPECTRE_V2_EIBRS || - mode == SPECTRE_V2_EIBRS_RETPOLINE || - mode == SPECTRE_V2_EIBRS_LFENCE); + return mode == SPECTRE_V2_IBRS || + mode == SPECTRE_V2_EIBRS || + mode == SPECTRE_V2_EIBRS_RETPOLINE || + mode == SPECTRE_V2_EIBRS_LFENCE; } static void __init -spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd) +spectre_v2_user_select_mitigation(void) { enum spectre_v2_user_mitigation mode = SPECTRE_V2_USER_NONE; bool smt_possible = IS_ENABLED(CONFIG_SMP); @@ -795,7 +1114,7 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd) cpu_smt_control == CPU_SMT_NOT_SUPPORTED) smt_possible = false; - cmd = spectre_v2_parse_user_cmdline(v2_cmd); + cmd = spectre_v2_parse_user_cmdline(); switch (cmd) { case SPECTRE_V2_USER_CMD_NONE: goto set_mode; @@ -843,12 +1162,12 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd) } /* - * If no STIBP, enhanced IBRS is enabled or SMT impossible, STIBP is not - * required. + * If no STIBP, IBRS or enhanced IBRS is enabled, or SMT impossible, + * STIBP is not required. */ if (!boot_cpu_has(X86_FEATURE_STIBP) || !smt_possible || - spectre_v2_in_eibrs_mode(spectre_v2_enabled)) + spectre_v2_in_ibrs_mode(spectre_v2_enabled)) return; /* @@ -860,6 +1179,13 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd) boot_cpu_has(X86_FEATURE_AMD_STIBP_ALWAYS_ON)) mode = SPECTRE_V2_USER_STRICT_PREFERRED; + if (retbleed_mitigation == RETBLEED_MITIGATION_UNRET) { + if (mode != SPECTRE_V2_USER_STRICT && + mode != SPECTRE_V2_USER_STRICT_PREFERRED) + pr_info("Selecting STIBP always-on mode to complement retbleed mitigation\n"); + mode = SPECTRE_V2_USER_STRICT_PREFERRED; + } + spectre_v2_user_stibp = mode; set_mode: @@ -873,6 +1199,7 @@ static const char * const spectre_v2_strings[] = { [SPECTRE_V2_EIBRS] = "Mitigation: Enhanced IBRS", [SPECTRE_V2_EIBRS_LFENCE] = "Mitigation: Enhanced IBRS + LFENCE", [SPECTRE_V2_EIBRS_RETPOLINE] = "Mitigation: Enhanced IBRS + Retpolines", + [SPECTRE_V2_IBRS] = "Mitigation: IBRS", }; static const struct { @@ -890,6 +1217,7 @@ static const struct { { "eibrs,lfence", SPECTRE_V2_CMD_EIBRS_LFENCE, false }, { "eibrs,retpoline", SPECTRE_V2_CMD_EIBRS_RETPOLINE, false }, { "auto", SPECTRE_V2_CMD_AUTO, false }, + { "ibrs", SPECTRE_V2_CMD_IBRS, false }, }; static void __init spec_v2_print_cond(const char *reason, bool secure) @@ -952,6 +1280,30 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) return SPECTRE_V2_CMD_AUTO; } + if (cmd == SPECTRE_V2_CMD_IBRS && !IS_ENABLED(CONFIG_CPU_IBRS_ENTRY)) { + pr_err("%s selected but not compiled in. Switching to AUTO select\n", + mitigation_options[i].option); + return SPECTRE_V2_CMD_AUTO; + } + + if (cmd == SPECTRE_V2_CMD_IBRS && boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) { + pr_err("%s selected but not Intel CPU. Switching to AUTO select\n", + mitigation_options[i].option); + return SPECTRE_V2_CMD_AUTO; + } + + if (cmd == SPECTRE_V2_CMD_IBRS && !boot_cpu_has(X86_FEATURE_IBRS)) { + pr_err("%s selected but CPU doesn't have IBRS. Switching to AUTO select\n", + mitigation_options[i].option); + return SPECTRE_V2_CMD_AUTO; + } + + if (cmd == SPECTRE_V2_CMD_IBRS && boot_cpu_has(X86_FEATURE_XENPV)) { + pr_err("%s selected but running as XenPV guest. Switching to AUTO select\n", + mitigation_options[i].option); + return SPECTRE_V2_CMD_AUTO; + } + spec_v2_print_cond(mitigation_options[i].option, mitigation_options[i].secure); return cmd; @@ -967,6 +1319,22 @@ static enum spectre_v2_mitigation __init spectre_v2_select_retpoline(void) return SPECTRE_V2_RETPOLINE; } +/* Disable in-kernel use of non-RSB RET predictors */ +static void __init spec_ctrl_disable_kernel_rrsba(void) +{ + u64 ia32_cap; + + if (!boot_cpu_has(X86_FEATURE_RRSBA_CTRL)) + return; + + ia32_cap = x86_read_arch_cap_msr(); + + if (ia32_cap & ARCH_CAP_RRSBA) { + x86_spec_ctrl_base |= SPEC_CTRL_RRSBA_DIS_S; + write_spec_ctrl_current(x86_spec_ctrl_base, true); + } +} + static void __init spectre_v2_select_mitigation(void) { enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline(); @@ -991,6 +1359,15 @@ static void __init spectre_v2_select_mitigation(void) break; } + if (IS_ENABLED(CONFIG_CPU_IBRS_ENTRY) && + boot_cpu_has_bug(X86_BUG_RETBLEED) && + retbleed_cmd != RETBLEED_CMD_OFF && + boot_cpu_has(X86_FEATURE_IBRS) && + boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) { + mode = SPECTRE_V2_IBRS; + break; + } + mode = spectre_v2_select_retpoline(); break; @@ -1007,6 +1384,10 @@ static void __init spectre_v2_select_mitigation(void) mode = spectre_v2_select_retpoline(); break; + case SPECTRE_V2_CMD_IBRS: + mode = SPECTRE_V2_IBRS; + break; + case SPECTRE_V2_CMD_EIBRS: mode = SPECTRE_V2_EIBRS; break; @@ -1023,10 +1404,9 @@ static void __init spectre_v2_select_mitigation(void) if (mode == SPECTRE_V2_EIBRS && unprivileged_ebpf_enabled()) pr_err(SPECTRE_V2_EIBRS_EBPF_MSG); - if (spectre_v2_in_eibrs_mode(mode)) { - /* Force it so VMEXIT will restore correctly */ + if (spectre_v2_in_ibrs_mode(mode)) { x86_spec_ctrl_base |= SPEC_CTRL_IBRS; - wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); + write_spec_ctrl_current(x86_spec_ctrl_base, true); } switch (mode) { @@ -1034,6 +1414,12 @@ static void __init spectre_v2_select_mitigation(void) case SPECTRE_V2_EIBRS: break; + case SPECTRE_V2_IBRS: + setup_force_cpu_cap(X86_FEATURE_KERNEL_IBRS); + if (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED)) + pr_warn(SPECTRE_V2_IBRS_PERF_MSG); + break; + case SPECTRE_V2_LFENCE: case SPECTRE_V2_EIBRS_LFENCE: setup_force_cpu_cap(X86_FEATURE_RETPOLINE_LFENCE); @@ -1045,43 +1431,117 @@ static void __init spectre_v2_select_mitigation(void) break; } + /* + * Disable alternate RSB predictions in kernel when indirect CALLs and + * JMPs gets protection against BHI and Intramode-BTI, but RET + * prediction from a non-RSB predictor is still a risk. + */ + if (mode == SPECTRE_V2_EIBRS_LFENCE || + mode == SPECTRE_V2_EIBRS_RETPOLINE || + mode == SPECTRE_V2_RETPOLINE) + spec_ctrl_disable_kernel_rrsba(); + spectre_v2_enabled = mode; pr_info("%s\n", spectre_v2_strings[mode]); /* - * If spectre v2 protection has been enabled, unconditionally fill - * RSB during a context switch; this protects against two independent - * issues: + * If Spectre v2 protection has been enabled, fill the RSB during a + * context switch. In general there are two types of RSB attacks + * across context switches, for which the CALLs/RETs may be unbalanced. + * + * 1) RSB underflow + * + * Some Intel parts have "bottomless RSB". When the RSB is empty, + * speculated return targets may come from the branch predictor, + * which could have a user-poisoned BTB or BHB entry. + * + * AMD has it even worse: *all* returns are speculated from the BTB, + * regardless of the state of the RSB. + * + * When IBRS or eIBRS is enabled, the "user -> kernel" attack + * scenario is mitigated by the IBRS branch prediction isolation + * properties, so the RSB buffer filling wouldn't be necessary to + * protect against this type of attack. + * + * The "user -> user" attack scenario is mitigated by RSB filling. + * + * 2) Poisoned RSB entry + * + * If the 'next' in-kernel return stack is shorter than 'prev', + * 'next' could be tricked into speculating with a user-poisoned RSB + * entry. + * + * The "user -> kernel" attack scenario is mitigated by SMEP and + * eIBRS. * - * - RSB underflow (and switch to BTB) on Skylake+ - * - SpectreRSB variant of spectre v2 on X86_BUG_SPECTRE_V2 CPUs + * The "user -> user" scenario, also known as SpectreBHB, requires + * RSB clearing. + * + * So to mitigate all cases, unconditionally fill RSB on context + * switches. + * + * FIXME: Is this pointless for retbleed-affected AMD? */ setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW); pr_info("Spectre v2 / SpectreRSB mitigation: Filling RSB on context switch\n"); /* - * Retpoline means the kernel is safe because it has no indirect - * branches. Enhanced IBRS protects firmware too, so, enable restricted - * speculation around firmware calls only when Enhanced IBRS isn't - * supported. + * Similar to context switches, there are two types of RSB attacks + * after vmexit: + * + * 1) RSB underflow + * + * 2) Poisoned RSB entry + * + * When retpoline is enabled, both are mitigated by filling/clearing + * the RSB. + * + * When IBRS is enabled, while #1 would be mitigated by the IBRS branch + * prediction isolation protections, RSB still needs to be cleared + * because of #2. Note that SMEP provides no protection here, unlike + * user-space-poisoned RSB entries. + * + * eIBRS, on the other hand, has RSB-poisoning protections, so it + * doesn't need RSB clearing after vmexit. + */ + if (boot_cpu_has(X86_FEATURE_RETPOLINE) || + boot_cpu_has(X86_FEATURE_KERNEL_IBRS)) + setup_force_cpu_cap(X86_FEATURE_RSB_VMEXIT); + + /* + * Retpoline protects the kernel, but doesn't protect firmware. IBRS + * and Enhanced IBRS protect firmware too, so enable IBRS around + * firmware calls only when IBRS / Enhanced IBRS aren't otherwise + * enabled. * * Use "mode" to check Enhanced IBRS instead of boot_cpu_has(), because * the user might select retpoline on the kernel command line and if * the CPU supports Enhanced IBRS, kernel might un-intentionally not * enable IBRS around firmware calls. */ - if (boot_cpu_has(X86_FEATURE_IBRS) && !spectre_v2_in_eibrs_mode(mode)) { + if (boot_cpu_has_bug(X86_BUG_RETBLEED) && + boot_cpu_has(X86_FEATURE_IBPB) && + (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)) { + + if (retbleed_cmd != RETBLEED_CMD_IBPB) { + setup_force_cpu_cap(X86_FEATURE_USE_IBPB_FW); + pr_info("Enabling Speculation Barrier for firmware calls\n"); + } + + } else if (boot_cpu_has(X86_FEATURE_IBRS) && !spectre_v2_in_ibrs_mode(mode)) { setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW); pr_info("Enabling Restricted Speculation for firmware calls\n"); } /* Set up IBPB and STIBP depending on the general spectre V2 command */ - spectre_v2_user_select_mitigation(cmd); + spectre_v2_cmd = cmd; } static void update_stibp_msr(void * __unused) { - wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); + u64 val = spec_ctrl_current() | (x86_spec_ctrl_base & SPEC_CTRL_STIBP); + write_spec_ctrl_current(val, true); } /* Update x86_spec_ctrl_base in case SMT state changed. */ @@ -1116,6 +1576,8 @@ static void update_indir_branch_cond(void) /* Update the static key controlling the MDS CPU buffer clear in idle */ static void update_mds_branch_idle(void) { + u64 ia32_cap = x86_read_arch_cap_msr(); + /* * Enable the idle clearing if SMT is active on CPUs which are * affected only by MSBDS and not any other MDS variant. @@ -1127,14 +1589,17 @@ static void update_mds_branch_idle(void) if (!boot_cpu_has_bug(X86_BUG_MSBDS_ONLY)) return; - if (sched_smt_active()) + if (sched_smt_active()) { static_branch_enable(&mds_idle_clear); - else + } else if (mmio_mitigation == MMIO_MITIGATION_OFF || + (ia32_cap & ARCH_CAP_FBSDP_NO)) { static_branch_disable(&mds_idle_clear); + } } #define MDS_MSG_SMT "MDS CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/mds.html for more details.\n" #define TAA_MSG_SMT "TAA CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/tsx_async_abort.html for more details.\n" +#define MMIO_MSG_SMT "MMIO Stale Data CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/processor_mmio_stale_data.html for more details.\n" void cpu_bugs_smt_update(void) { @@ -1179,6 +1644,16 @@ void cpu_bugs_smt_update(void) break; } + switch (mmio_mitigation) { + case MMIO_MITIGATION_VERW: + case MMIO_MITIGATION_UCODE_NEEDED: + if (sched_smt_active()) + pr_warn_once(MMIO_MSG_SMT); + break; + case MMIO_MITIGATION_OFF: + break; + } + mutex_unlock(&spec_ctrl_mutex); } @@ -1283,16 +1758,6 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void) } /* - * If SSBD is controlled by the SPEC_CTRL MSR, then set the proper - * bit in the mask to allow guests to use the mitigation even in the - * case where the host does not enable it. - */ - if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || - static_cpu_has(X86_FEATURE_AMD_SSBD)) { - x86_spec_ctrl_mask |= SPEC_CTRL_SSBD; - } - - /* * We have three CPU feature flags that are in play here: * - X86_BUG_SPEC_STORE_BYPASS - CPU is susceptible. * - X86_FEATURE_SSBD - CPU is able to turn off speculative store bypass @@ -1309,7 +1774,7 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void) x86_amd_ssb_disable(); } else { x86_spec_ctrl_base |= SPEC_CTRL_SSBD; - wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); + write_spec_ctrl_current(x86_spec_ctrl_base, true); } } @@ -1560,7 +2025,7 @@ int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which) void x86_spec_ctrl_setup_ap(void) { if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) - wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); + write_spec_ctrl_current(x86_spec_ctrl_base, true); if (ssb_mode == SPEC_STORE_BYPASS_DISABLE) x86_amd_ssb_disable(); @@ -1781,9 +2246,23 @@ static ssize_t tsx_async_abort_show_state(char *buf) sched_smt_active() ? "vulnerable" : "disabled"); } +static ssize_t mmio_stale_data_show_state(char *buf) +{ + if (mmio_mitigation == MMIO_MITIGATION_OFF) + return sysfs_emit(buf, "%s\n", mmio_strings[mmio_mitigation]); + + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { + return sysfs_emit(buf, "%s; SMT Host state unknown\n", + mmio_strings[mmio_mitigation]); + } + + return sysfs_emit(buf, "%s; SMT %s\n", mmio_strings[mmio_mitigation], + sched_smt_active() ? "vulnerable" : "disabled"); +} + static char *stibp_state(void) { - if (spectre_v2_in_eibrs_mode(spectre_v2_enabled)) + if (spectre_v2_in_ibrs_mode(spectre_v2_enabled)) return ""; switch (spectre_v2_user_stibp) { @@ -1839,6 +2318,24 @@ static ssize_t srbds_show_state(char *buf) return sprintf(buf, "%s\n", srbds_strings[srbds_mitigation]); } +static ssize_t retbleed_show_state(char *buf) +{ + if (retbleed_mitigation == RETBLEED_MITIGATION_UNRET) { + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && + boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) + return sprintf(buf, "Vulnerable: untrained return thunk on non-Zen uarch\n"); + + return sprintf(buf, "%s; SMT %s\n", + retbleed_strings[retbleed_mitigation], + !sched_smt_active() ? "disabled" : + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED ? + "enabled with STIBP protection" : "vulnerable"); + } + + return sprintf(buf, "%s\n", retbleed_strings[retbleed_mitigation]); +} + static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, char *buf, unsigned int bug) { @@ -1881,6 +2378,12 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_SRBDS: return srbds_show_state(buf); + case X86_BUG_MMIO_STALE_DATA: + return mmio_stale_data_show_state(buf); + + case X86_BUG_RETBLEED: + return retbleed_show_state(buf); + default: break; } @@ -1932,4 +2435,14 @@ ssize_t cpu_show_srbds(struct device *dev, struct device_attribute *attr, char * { return cpu_show_common(dev, attr, buf, X86_BUG_SRBDS); } + +ssize_t cpu_show_mmio_stale_data(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_STALE_DATA); +} + +ssize_t cpu_show_retbleed(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_RETBLEED); +} #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index c296cb1c0113..736262a76a12 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1205,24 +1205,60 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { {} }; +#define VULNBL(vendor, family, model, blacklist) \ + X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, blacklist) + #define VULNBL_INTEL_STEPPINGS(model, steppings, issues) \ X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(INTEL, 6, \ INTEL_FAM6_##model, steppings, \ X86_FEATURE_ANY, issues) +#define VULNBL_AMD(family, blacklist) \ + VULNBL(AMD, family, X86_MODEL_ANY, blacklist) + +#define VULNBL_HYGON(family, blacklist) \ + VULNBL(HYGON, family, X86_MODEL_ANY, blacklist) + #define SRBDS BIT(0) +/* CPU is affected by X86_BUG_MMIO_STALE_DATA */ +#define MMIO BIT(1) +/* CPU is affected by Shared Buffers Data Sampling (SBDS), a variant of X86_BUG_MMIO_STALE_DATA */ +#define MMIO_SBDS BIT(2) +/* CPU is affected by RETbleed, speculating where you would not expect it */ +#define RETBLEED BIT(3) static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(IVYBRIDGE, X86_STEPPING_ANY, SRBDS), VULNBL_INTEL_STEPPINGS(HASWELL, X86_STEPPING_ANY, SRBDS), VULNBL_INTEL_STEPPINGS(HASWELL_L, X86_STEPPING_ANY, SRBDS), VULNBL_INTEL_STEPPINGS(HASWELL_G, X86_STEPPING_ANY, SRBDS), + VULNBL_INTEL_STEPPINGS(HASWELL_X, X86_STEPPING_ANY, MMIO), + VULNBL_INTEL_STEPPINGS(BROADWELL_D, X86_STEPPING_ANY, MMIO), VULNBL_INTEL_STEPPINGS(BROADWELL_G, X86_STEPPING_ANY, SRBDS), + VULNBL_INTEL_STEPPINGS(BROADWELL_X, X86_STEPPING_ANY, MMIO), VULNBL_INTEL_STEPPINGS(BROADWELL, X86_STEPPING_ANY, SRBDS), - VULNBL_INTEL_STEPPINGS(SKYLAKE_L, X86_STEPPING_ANY, SRBDS), - VULNBL_INTEL_STEPPINGS(SKYLAKE, X86_STEPPING_ANY, SRBDS), - VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPINGS(0x0, 0xC), SRBDS), - VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPINGS(0x0, 0xD), SRBDS), + VULNBL_INTEL_STEPPINGS(SKYLAKE_L, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED), + VULNBL_INTEL_STEPPINGS(SKYLAKE_X, X86_STEPPING_ANY, MMIO | RETBLEED), + VULNBL_INTEL_STEPPINGS(SKYLAKE, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED), + VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED), + VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED), + VULNBL_INTEL_STEPPINGS(CANNONLAKE_L, X86_STEPPING_ANY, RETBLEED), + VULNBL_INTEL_STEPPINGS(ICELAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), + VULNBL_INTEL_STEPPINGS(ICELAKE_D, X86_STEPPING_ANY, MMIO), + VULNBL_INTEL_STEPPINGS(ICELAKE_X, X86_STEPPING_ANY, MMIO), + VULNBL_INTEL_STEPPINGS(COMETLAKE, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), + VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPINGS(0x0, 0x0), MMIO | RETBLEED), + VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), + VULNBL_INTEL_STEPPINGS(LAKEFIELD, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), + VULNBL_INTEL_STEPPINGS(ROCKETLAKE, X86_STEPPING_ANY, MMIO | RETBLEED), + VULNBL_INTEL_STEPPINGS(ATOM_TREMONT, X86_STEPPING_ANY, MMIO | MMIO_SBDS), + VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO), + VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS), + + VULNBL_AMD(0x15, RETBLEED), + VULNBL_AMD(0x16, RETBLEED), + VULNBL_AMD(0x17, RETBLEED), + VULNBL_HYGON(0x18, RETBLEED), {} }; @@ -1243,6 +1279,13 @@ u64 x86_read_arch_cap_msr(void) return ia32_cap; } +static bool arch_cap_mmio_immune(u64 ia32_cap) +{ + return (ia32_cap & ARCH_CAP_FBSDP_NO && + ia32_cap & ARCH_CAP_PSDP_NO && + ia32_cap & ARCH_CAP_SBDR_SSDP_NO); +} + static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) { u64 ia32_cap = x86_read_arch_cap_msr(); @@ -1296,12 +1339,32 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) /* * SRBDS affects CPUs which support RDRAND or RDSEED and are listed * in the vulnerability blacklist. + * + * Some of the implications and mitigation of Shared Buffers Data + * Sampling (SBDS) are similar to SRBDS. Give SBDS same treatment as + * SRBDS. */ if ((cpu_has(c, X86_FEATURE_RDRAND) || cpu_has(c, X86_FEATURE_RDSEED)) && - cpu_matches(cpu_vuln_blacklist, SRBDS)) + cpu_matches(cpu_vuln_blacklist, SRBDS | MMIO_SBDS)) setup_force_cpu_bug(X86_BUG_SRBDS); + /* + * Processor MMIO Stale Data bug enumeration + * + * Affected CPU list is generally enough to enumerate the vulnerability, + * but for virtualization case check for ARCH_CAP MSR bits also, VMM may + * not want the guest to enumerate the bug. + */ + if (cpu_matches(cpu_vuln_blacklist, MMIO) && + !arch_cap_mmio_immune(ia32_cap)) + setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA); + + if (!cpu_has(c, X86_FEATURE_BTC_NO)) { + if (cpu_matches(cpu_vuln_blacklist, RETBLEED) || (ia32_cap & ARCH_CAP_RSBA)) + setup_force_cpu_bug(X86_BUG_RETBLEED); + } + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index 2a8e584fc991..7c9b5893c30a 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -61,6 +61,8 @@ static inline void tsx_init(void) { } static inline void tsx_ap_init(void) { } #endif /* CONFIG_CPU_SUP_INTEL */ +extern void init_spectral_chicken(struct cpuinfo_x86 *c); + extern void get_cpu_cap(struct cpuinfo_x86 *c); extern void get_cpu_address_sizes(struct cpuinfo_x86 *c); extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c); diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c index 3fcdda4c1e11..21fd425088fe 100644 --- a/arch/x86/kernel/cpu/hygon.c +++ b/arch/x86/kernel/cpu/hygon.c @@ -302,6 +302,12 @@ static void init_hygon(struct cpuinfo_x86 *c) /* get apicid instead of initial apic id from cpuid */ c->apicid = hard_smp_processor_id(); + /* + * XXX someone from Hygon needs to confirm this DTRT + * + init_spectral_chicken(c); + */ + set_cpu_cap(c, X86_FEATURE_ZEN); set_cpu_cap(c, X86_FEATURE_CPB); diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index dbaa8326d6f2..fd44b54c90d5 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -27,6 +27,7 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_APERFMPERF, CPUID_ECX, 0, 0x00000006, 0 }, { X86_FEATURE_EPB, CPUID_ECX, 3, 0x00000006, 0 }, { X86_FEATURE_INTEL_PPIN, CPUID_EBX, 0, 0x00000007, 1 }, + { X86_FEATURE_RRSBA_CTRL, CPUID_EDX, 2, 0x00000007, 2 }, { X86_FEATURE_CQM_LLC, CPUID_EDX, 1, 0x0000000f, 0 }, { X86_FEATURE_CQM_OCCUP_LLC, CPUID_EDX, 0, 0x0000000f, 1 }, { X86_FEATURE_CQM_MBM_TOTAL, CPUID_EDX, 1, 0x0000000f, 1 }, diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 5b4efc927d80..24b9fa89aa27 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -301,7 +301,7 @@ union ftrace_op_code_union { } __attribute__((packed)); }; -#define RET_SIZE 1 + IS_ENABLED(CONFIG_SLS) +#define RET_SIZE (IS_ENABLED(CONFIG_RETPOLINE) ? 5 : 1 + IS_ENABLED(CONFIG_SLS)) static unsigned long create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) @@ -357,7 +357,10 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) goto fail; ip = trampoline + size; - memcpy(ip, retq, RET_SIZE); + if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) + __text_gen_insn(ip, JMP32_INSN_OPCODE, ip, &__x86_return_thunk, JMP32_INSN_SIZE); + else + memcpy(ip, retq, sizeof(retq)); /* No need to test direct calls on created trampolines */ if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) { diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index 4ec13608d3c6..dfeb227de561 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -175,6 +175,7 @@ SYM_INNER_LABEL(ftrace_caller_end, SYM_L_GLOBAL) jmp ftrace_epilogue SYM_FUNC_END(ftrace_caller); +STACK_FRAME_NON_STANDARD_FP(ftrace_caller) SYM_FUNC_START(ftrace_epilogue) /* @@ -282,6 +283,7 @@ SYM_INNER_LABEL(ftrace_regs_caller_end, SYM_L_GLOBAL) jmp ftrace_epilogue SYM_FUNC_END(ftrace_regs_caller) +STACK_FRAME_NON_STANDARD_FP(ftrace_regs_caller) #else /* ! CONFIG_DYNAMIC_FTRACE */ @@ -311,10 +313,14 @@ trace: jmp ftrace_stub SYM_FUNC_END(__fentry__) EXPORT_SYMBOL(__fentry__) +STACK_FRAME_NON_STANDARD_FP(__fentry__) + #endif /* CONFIG_DYNAMIC_FTRACE */ #ifdef CONFIG_FUNCTION_GRAPH_TRACER -SYM_FUNC_START(return_to_handler) +SYM_CODE_START(return_to_handler) + UNWIND_HINT_EMPTY + ANNOTATE_NOENDBR subq $16, %rsp /* Save the return values */ @@ -339,7 +345,6 @@ SYM_FUNC_START(return_to_handler) int3 .Ldo_rop: mov %rdi, (%rsp) - UNWIND_HINT_FUNC RET -SYM_FUNC_END(return_to_handler) +SYM_CODE_END(return_to_handler) #endif diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index bd4a34100ed0..6a3cfaf6b72a 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -426,10 +426,12 @@ void __init do_early_exception(struct pt_regs *regs, int trapnr) /* Don't add a printk in there. printk relies on the PDA which is not initialized yet. */ -static void __init clear_bss(void) +void __init clear_bss(void) { memset(__bss_start, 0, (unsigned long) __bss_stop - (unsigned long) __bss_start); + memset(__brk_base, 0, + (unsigned long) __brk_limit - (unsigned long) __brk_base); } static unsigned long get_cmd_line_ptr(void) diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index eb8656bac99b..9b7acc9c7874 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -23,6 +23,7 @@ #include <asm/cpufeatures.h> #include <asm/percpu.h> #include <asm/nops.h> +#include <asm/nospec-branch.h> #include <asm/bootparam.h> #include <asm/export.h> #include <asm/pgtable_32.h> diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 92c4afa2b729..d860d437631b 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -389,6 +389,8 @@ SYM_CODE_START_NOALIGN(vc_boot_ghcb) UNWIND_HINT_IRET_REGS offset=8 ENDBR + ANNOTATE_UNRET_END + /* Build pt_regs */ PUSH_AND_CLEAR_REGS @@ -448,6 +450,7 @@ SYM_CODE_END(early_idt_handler_array) SYM_CODE_START_LOCAL(early_idt_handler_common) UNWIND_HINT_IRET_REGS offset=16 + ANNOTATE_UNRET_END /* * The stack is the hardware frame, an error code or zero, and the * vector number. @@ -497,6 +500,8 @@ SYM_CODE_START_NOALIGN(vc_no_ghcb) UNWIND_HINT_IRET_REGS offset=8 ENDBR + ANNOTATE_UNRET_END + /* Build pt_regs */ PUSH_AND_CLEAR_REGS diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index b98ffcf4d250..67828d973389 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -253,7 +253,7 @@ int module_finalize(const Elf_Ehdr *hdr, { const Elf_Shdr *s, *text = NULL, *alt = NULL, *locks = NULL, *para = NULL, *orc = NULL, *orc_ip = NULL, - *retpolines = NULL, *ibt_endbr = NULL; + *retpolines = NULL, *returns = NULL, *ibt_endbr = NULL; char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) { @@ -271,6 +271,8 @@ int module_finalize(const Elf_Ehdr *hdr, orc_ip = s; if (!strcmp(".retpoline_sites", secstrings + s->sh_name)) retpolines = s; + if (!strcmp(".return_sites", secstrings + s->sh_name)) + returns = s; if (!strcmp(".ibt_endbr_seal", secstrings + s->sh_name)) ibt_endbr = s; } @@ -287,6 +289,10 @@ int module_finalize(const Elf_Ehdr *hdr, void *rseg = (void *)retpolines->sh_addr; apply_retpolines(rseg, rseg + retpolines->sh_size); } + if (returns) { + void *rseg = (void *)returns->sh_addr; + apply_returns(rseg, rseg + returns->sh_size); + } if (alt) { /* patch .altinstructions */ void *aseg = (void *)alt->sh_addr; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 9b2772b7e1f3..d456ce21c255 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -600,7 +600,7 @@ static __always_inline void __speculation_ctrl_update(unsigned long tifp, } if (updmsr) - wrmsrl(MSR_IA32_SPEC_CTRL, msr); + write_spec_ctrl_current(msr, false); } static unsigned long speculation_ctrl_update_tif(struct task_struct *tsk) diff --git a/arch/x86/kernel/relocate_kernel_32.S b/arch/x86/kernel/relocate_kernel_32.S index fcc8a7699103..c7c4b1917336 100644 --- a/arch/x86/kernel/relocate_kernel_32.S +++ b/arch/x86/kernel/relocate_kernel_32.S @@ -7,10 +7,12 @@ #include <linux/linkage.h> #include <asm/page_types.h> #include <asm/kexec.h> +#include <asm/nospec-branch.h> #include <asm/processor-flags.h> /* - * Must be relocatable PIC code callable as a C function + * Must be relocatable PIC code callable as a C function, in particular + * there must be a plain RET and not jump to return thunk. */ #define PTR(x) (x << 2) @@ -91,7 +93,9 @@ SYM_CODE_START_NOALIGN(relocate_kernel) movl %edi, %eax addl $(identity_mapped - relocate_kernel), %eax pushl %eax - RET + ANNOTATE_UNRET_SAFE + ret + int3 SYM_CODE_END(relocate_kernel) SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) @@ -159,12 +163,15 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) xorl %edx, %edx xorl %esi, %esi xorl %ebp, %ebp - RET + ANNOTATE_UNRET_SAFE + ret + int3 1: popl %edx movl CP_PA_SWAP_PAGE(%edi), %esp addl $PAGE_SIZE, %esp 2: + ANNOTATE_RETPOLINE_SAFE call *%edx /* get the re-entry point of the peer system */ @@ -190,7 +197,9 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) movl %edi, %eax addl $(virtual_mapped - relocate_kernel), %eax pushl %eax - RET + ANNOTATE_UNRET_SAFE + ret + int3 SYM_CODE_END(identity_mapped) SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped) @@ -208,7 +217,9 @@ SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped) popl %edi popl %esi popl %ebx - RET + ANNOTATE_UNRET_SAFE + ret + int3 SYM_CODE_END(virtual_mapped) /* Do the copies */ @@ -271,7 +282,9 @@ SYM_CODE_START_LOCAL_NOALIGN(swap_pages) popl %edi popl %ebx popl %ebp - RET + ANNOTATE_UNRET_SAFE + ret + int3 SYM_CODE_END(swap_pages) .globl kexec_control_code_size diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S index c1d8626c53b6..4809c0dc4eb0 100644 --- a/arch/x86/kernel/relocate_kernel_64.S +++ b/arch/x86/kernel/relocate_kernel_64.S @@ -13,7 +13,8 @@ #include <asm/unwind_hints.h> /* - * Must be relocatable PIC code callable as a C function + * Must be relocatable PIC code callable as a C function, in particular + * there must be a plain RET and not jump to return thunk. */ #define PTR(x) (x << 3) @@ -105,7 +106,9 @@ SYM_CODE_START_NOALIGN(relocate_kernel) /* jump to identity mapped page */ addq $(identity_mapped - relocate_kernel), %r8 pushq %r8 - RET + ANNOTATE_UNRET_SAFE + ret + int3 SYM_CODE_END(relocate_kernel) SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) @@ -200,7 +203,9 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) xorl %r14d, %r14d xorl %r15d, %r15d - RET + ANNOTATE_UNRET_SAFE + ret + int3 1: popq %rdx @@ -219,7 +224,9 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) call swap_pages movq $virtual_mapped, %rax pushq %rax - RET + ANNOTATE_UNRET_SAFE + ret + int3 SYM_CODE_END(identity_mapped) SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped) @@ -241,7 +248,9 @@ SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped) popq %r12 popq %rbp popq %rbx - RET + ANNOTATE_UNRET_SAFE + ret + int3 SYM_CODE_END(virtual_mapped) /* Do the copies */ @@ -298,7 +307,9 @@ SYM_CODE_START_LOCAL_NOALIGN(swap_pages) lea PAGE_SIZE(%rax), %rsi jmp 0b 3: - RET + ANNOTATE_UNRET_SAFE + ret + int3 SYM_CODE_END(swap_pages) .globl kexec_control_code_size diff --git a/arch/x86/kernel/resource.c b/arch/x86/kernel/resource.c index db2b350a37b7..bba1abd05bfe 100644 --- a/arch/x86/kernel/resource.c +++ b/arch/x86/kernel/resource.c @@ -1,7 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 -#include <linux/dev_printk.h> #include <linux/ioport.h> +#include <linux/printk.h> #include <asm/e820/api.h> +#include <asm/pci_x86.h> static void resource_clip(struct resource *res, resource_size_t start, resource_size_t end) @@ -24,14 +25,14 @@ static void resource_clip(struct resource *res, resource_size_t start, res->start = end + 1; } -void remove_e820_regions(struct device *dev, struct resource *avail) +static void remove_e820_regions(struct resource *avail) { int i; struct e820_entry *entry; u64 e820_start, e820_end; struct resource orig = *avail; - if (!(avail->flags & IORESOURCE_MEM)) + if (!pci_use_e820) return; for (i = 0; i < e820_table->nr_entries; i++) { @@ -41,7 +42,7 @@ void remove_e820_regions(struct device *dev, struct resource *avail) resource_clip(avail, e820_start, e820_end); if (orig.start != avail->start || orig.end != avail->end) { - dev_info(dev, "clipped %pR to %pR for e820 entry [mem %#010Lx-%#010Lx]\n", + pr_info("clipped %pR to %pR for e820 entry [mem %#010Lx-%#010Lx]\n", &orig, avail, e820_start, e820_end); orig = *avail; } @@ -55,6 +56,9 @@ void arch_remove_reservations(struct resource *avail) * the low 1MB unconditionally, as this area is needed for some ISA * cards requiring a memory range, e.g. the i82365 PCMCIA controller. */ - if (avail->flags & IORESOURCE_MEM) + if (avail->flags & IORESOURCE_MEM) { resource_clip(avail, BIOS_ROM_BASE, BIOS_ROM_END); + + remove_e820_regions(avail); + } } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 3ebb85327edb..bd6c6fd373ae 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -67,11 +67,6 @@ RESERVE_BRK(dmi_alloc, 65536); #endif -/* - * Range of the BSS area. The size of the BSS area is determined - * at link time, with RESERVE_BRK() facility reserving additional - * chunks. - */ unsigned long _brk_start = (unsigned long)__brk_base; unsigned long _brk_end = (unsigned long)__brk_base; diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c index b478edf43bec..3a5b0c9c4fcc 100644 --- a/arch/x86/kernel/sev-shared.c +++ b/arch/x86/kernel/sev-shared.c @@ -219,9 +219,10 @@ static enum es_result verify_exception_info(struct ghcb *ghcb, struct es_em_ctxt return ES_VMM_ERROR; } -enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb, bool set_ghcb_msr, - struct es_em_ctxt *ctxt, u64 exit_code, - u64 exit_info_1, u64 exit_info_2) +static enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb, + struct es_em_ctxt *ctxt, + u64 exit_code, u64 exit_info_1, + u64 exit_info_2) { /* Fill in protocol and format specifiers */ ghcb->protocol_version = ghcb_version; @@ -231,14 +232,7 @@ enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb, bool set_ghcb_msr, ghcb_set_sw_exit_info_1(ghcb, exit_info_1); ghcb_set_sw_exit_info_2(ghcb, exit_info_2); - /* - * Hyper-V unenlightened guests use a paravisor for communicating and - * GHCB pages are being allocated and set up by that paravisor. Linux - * should not change the GHCB page's physical address. - */ - if (set_ghcb_msr) - sev_es_wr_ghcb_msr(__pa(ghcb)); - + sev_es_wr_ghcb_msr(__pa(ghcb)); VMGEXIT(); return verify_exception_info(ghcb, ctxt); @@ -795,7 +789,7 @@ static enum es_result vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) */ sw_scratch = __pa(ghcb) + offsetof(struct ghcb, shared_buffer); ghcb_set_sw_scratch(ghcb, sw_scratch); - ret = sev_es_ghcb_hv_call(ghcb, true, ctxt, SVM_EXIT_IOIO, + ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_IOIO, exit_info_1, exit_info_2); if (ret != ES_OK) return ret; @@ -837,8 +831,7 @@ static enum es_result vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) ghcb_set_rax(ghcb, rax); - ret = sev_es_ghcb_hv_call(ghcb, true, ctxt, - SVM_EXIT_IOIO, exit_info_1, 0); + ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_IOIO, exit_info_1, 0); if (ret != ES_OK) return ret; @@ -894,7 +887,7 @@ static enum es_result vc_handle_cpuid(struct ghcb *ghcb, /* xgetbv will cause #GP - use reset value for xcr0 */ ghcb_set_xcr0(ghcb, 1); - ret = sev_es_ghcb_hv_call(ghcb, true, ctxt, SVM_EXIT_CPUID, 0, 0); + ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_CPUID, 0, 0); if (ret != ES_OK) return ret; @@ -919,7 +912,7 @@ static enum es_result vc_handle_rdtsc(struct ghcb *ghcb, bool rdtscp = (exit_code == SVM_EXIT_RDTSCP); enum es_result ret; - ret = sev_es_ghcb_hv_call(ghcb, true, ctxt, exit_code, 0, 0); + ret = sev_es_ghcb_hv_call(ghcb, ctxt, exit_code, 0, 0); if (ret != ES_OK) return ret; diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c index c05f0124c410..63dc626627a0 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/kernel/sev.c @@ -786,7 +786,7 @@ static int vmgexit_psc(struct snp_psc_desc *desc) ghcb_set_sw_scratch(ghcb, (u64)__pa(data)); /* This will advance the shared buffer data points to. */ - ret = sev_es_ghcb_hv_call(ghcb, true, &ctxt, SVM_VMGEXIT_PSC, 0, 0); + ret = sev_es_ghcb_hv_call(ghcb, &ctxt, SVM_VMGEXIT_PSC, 0, 0); /* * Page State Change VMGEXIT can pass error code through @@ -1212,8 +1212,7 @@ static enum es_result vc_handle_msr(struct ghcb *ghcb, struct es_em_ctxt *ctxt) ghcb_set_rdx(ghcb, regs->dx); } - ret = sev_es_ghcb_hv_call(ghcb, true, ctxt, SVM_EXIT_MSR, - exit_info_1, 0); + ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_MSR, exit_info_1, 0); if ((ret == ES_OK) && (!exit_info_1)) { regs->ax = ghcb->save.rax; @@ -1452,7 +1451,7 @@ static enum es_result vc_do_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt, ghcb_set_sw_scratch(ghcb, ghcb_pa + offsetof(struct ghcb, shared_buffer)); - return sev_es_ghcb_hv_call(ghcb, true, ctxt, exit_code, exit_info_1, exit_info_2); + return sev_es_ghcb_hv_call(ghcb, ctxt, exit_code, exit_info_1, exit_info_2); } /* @@ -1628,7 +1627,7 @@ static enum es_result vc_handle_dr7_write(struct ghcb *ghcb, /* Using a value of 0 for ExitInfo1 means RAX holds the value */ ghcb_set_rax(ghcb, val); - ret = sev_es_ghcb_hv_call(ghcb, true, ctxt, SVM_EXIT_WRITE_DR7, 0, 0); + ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_WRITE_DR7, 0, 0); if (ret != ES_OK) return ret; @@ -1658,7 +1657,7 @@ static enum es_result vc_handle_dr7_read(struct ghcb *ghcb, static enum es_result vc_handle_wbinvd(struct ghcb *ghcb, struct es_em_ctxt *ctxt) { - return sev_es_ghcb_hv_call(ghcb, true, ctxt, SVM_EXIT_WBINVD, 0, 0); + return sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_WBINVD, 0, 0); } static enum es_result vc_handle_rdpmc(struct ghcb *ghcb, struct es_em_ctxt *ctxt) @@ -1667,7 +1666,7 @@ static enum es_result vc_handle_rdpmc(struct ghcb *ghcb, struct es_em_ctxt *ctxt ghcb_set_rcx(ghcb, ctxt->regs->cx); - ret = sev_es_ghcb_hv_call(ghcb, true, ctxt, SVM_EXIT_RDPMC, 0, 0); + ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_RDPMC, 0, 0); if (ret != ES_OK) return ret; @@ -1708,7 +1707,7 @@ static enum es_result vc_handle_vmmcall(struct ghcb *ghcb, if (x86_platform.hyper.sev_es_hcall_prepare) x86_platform.hyper.sev_es_hcall_prepare(ghcb, ctxt->regs); - ret = sev_es_ghcb_hv_call(ghcb, true, ctxt, SVM_EXIT_VMMCALL, 0, 0); + ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_VMMCALL, 0, 0); if (ret != ES_OK) return ret; @@ -2197,7 +2196,7 @@ int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, unsigned ghcb_set_rbx(ghcb, input->data_npages); } - ret = sev_es_ghcb_hv_call(ghcb, true, &ctxt, exit_code, input->req_gpa, input->resp_gpa); + ret = sev_es_ghcb_hv_call(ghcb, &ctxt, exit_code, input->req_gpa, input->resp_gpa); if (ret) goto e_put; diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index aa72cefdd5be..aaaba85d6d7f 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -12,13 +12,21 @@ enum insn_type { }; /* + * ud1 %esp, %ecx - a 3 byte #UD that is unique to trampolines, chosen such + * that there is no false-positive trampoline identification while also being a + * speculation stop. + */ +static const u8 tramp_ud[] = { 0x0f, 0xb9, 0xcc }; + +/* * cs cs cs xorl %eax, %eax - a single 5 byte instruction that clears %[er]ax */ static const u8 xor5rax[] = { 0x2e, 0x2e, 0x2e, 0x31, 0xc0 }; static const u8 retinsn[] = { RET_INSN_OPCODE, 0xcc, 0xcc, 0xcc, 0xcc }; -static void __ref __static_call_transform(void *insn, enum insn_type type, void *func) +static void __ref __static_call_transform(void *insn, enum insn_type type, + void *func, bool modinit) { const void *emulate = NULL; int size = CALL_INSN_SIZE; @@ -43,14 +51,17 @@ static void __ref __static_call_transform(void *insn, enum insn_type type, void break; case RET: - code = &retinsn; + if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) + code = text_gen_insn(JMP32_INSN_OPCODE, insn, &__x86_return_thunk); + else + code = &retinsn; break; } if (memcmp(insn, code, size) == 0) return; - if (unlikely(system_state == SYSTEM_BOOTING)) + if (system_state == SYSTEM_BOOTING || modinit) return text_poke_early(insn, code, size); text_poke_bp(insn, code, size, emulate); @@ -60,7 +71,7 @@ static void __static_call_validate(void *insn, bool tail, bool tramp) { u8 opcode = *(u8 *)insn; - if (tramp && memcmp(insn+5, "SCT", 3)) { + if (tramp && memcmp(insn+5, tramp_ud, 3)) { pr_err("trampoline signature fail"); BUG(); } @@ -104,14 +115,42 @@ void arch_static_call_transform(void *site, void *tramp, void *func, bool tail) if (tramp) { __static_call_validate(tramp, true, true); - __static_call_transform(tramp, __sc_insn(!func, true), func); + __static_call_transform(tramp, __sc_insn(!func, true), func, false); } if (IS_ENABLED(CONFIG_HAVE_STATIC_CALL_INLINE) && site) { __static_call_validate(site, tail, false); - __static_call_transform(site, __sc_insn(!func, tail), func); + __static_call_transform(site, __sc_insn(!func, tail), func, false); } mutex_unlock(&text_mutex); } EXPORT_SYMBOL_GPL(arch_static_call_transform); + +#ifdef CONFIG_RETHUNK +/* + * This is called by apply_returns() to fix up static call trampolines, + * specifically ARCH_DEFINE_STATIC_CALL_NULL_TRAMP which is recorded as + * having a return trampoline. + * + * The problem is that static_call() is available before determining + * X86_FEATURE_RETHUNK and, by implication, running alternatives. + * + * This means that __static_call_transform() above can have overwritten the + * return trampoline and we now need to fix things up to be consistent. + */ +bool __static_call_fixup(void *tramp, u8 op, void *dest) +{ + if (memcmp(tramp+5, tramp_ud, 3)) { + /* Not a trampoline site, not our problem. */ + return false; + } + + mutex_lock(&text_mutex); + if (op == RET_INSN_OPCODE || dest == &__x86_return_thunk) + __static_call_transform(tramp, RET, NULL, true); + mutex_unlock(&text_mutex); + + return true; +} +#endif diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index f5f6dc2e8007..15f29053cec4 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -141,7 +141,7 @@ SECTIONS #ifdef CONFIG_RETPOLINE __indirect_thunk_start = .; - *(.text.__x86.indirect_thunk) + *(.text.__x86.*) __indirect_thunk_end = .; #endif } :text =0xcccc @@ -283,6 +283,13 @@ SECTIONS *(.retpoline_sites) __retpoline_sites_end = .; } + + . = ALIGN(8); + .return_sites : AT(ADDR(.return_sites) - LOAD_OFFSET) { + __return_sites = .; + *(.return_sites) + __return_sites_end = .; + } #endif #ifdef CONFIG_X86_KERNEL_IBT @@ -388,7 +395,7 @@ SECTIONS .brk : AT(ADDR(.brk) - LOAD_OFFSET) { __brk_base = .; . += 64 * 1024; /* 64k alignment slop space */ - *(.brk_reservation) /* areas brk users have reserved */ + *(.bss..brk) /* areas brk users have reserved */ __brk_limit = .; } diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 89b11e7dca8a..f8382abe22ff 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -189,9 +189,6 @@ #define X8(x...) X4(x), X4(x) #define X16(x...) X8(x), X8(x) -#define NR_FASTOP (ilog2(sizeof(ulong)) + 1) -#define FASTOP_SIZE (8 * (1 + HAS_KERNEL_IBT)) - struct opcode { u64 flags; u8 intercept; @@ -306,9 +303,15 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt) * Moreover, they are all exactly FASTOP_SIZE bytes long, so functions for * different operand sizes can be reached by calculation, rather than a jump * table (which would be bigger than the code). + * + * The 16 byte alignment, considering 5 bytes for the RET thunk, 3 for ENDBR + * and 1 for the straight line speculation INT3, leaves 7 bytes for the + * body of the function. Currently none is larger than 4. */ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop); +#define FASTOP_SIZE 16 + #define __FOP_FUNC(name) \ ".align " __stringify(FASTOP_SIZE) " \n\t" \ ".type " name ", @function \n\t" \ @@ -325,13 +328,15 @@ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop); #define FOP_RET(name) \ __FOP_RET(#name) -#define FOP_START(op) \ +#define __FOP_START(op, align) \ extern void em_##op(struct fastop *fake); \ asm(".pushsection .text, \"ax\" \n\t" \ ".global em_" #op " \n\t" \ - ".align " __stringify(FASTOP_SIZE) " \n\t" \ + ".align " __stringify(align) " \n\t" \ "em_" #op ":\n\t" +#define FOP_START(op) __FOP_START(op, FASTOP_SIZE) + #define FOP_END \ ".popsection") @@ -435,17 +440,12 @@ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop); /* * Depending on .config the SETcc functions look like: * - * ENDBR [4 bytes; CONFIG_X86_KERNEL_IBT] - * SETcc %al [3 bytes] - * RET [1 byte] - * INT3 [1 byte; CONFIG_SLS] - * - * Which gives possible sizes 4, 5, 8 or 9. When rounded up to the - * next power-of-two alignment they become 4, 8 or 16 resp. + * ENDBR [4 bytes; CONFIG_X86_KERNEL_IBT] + * SETcc %al [3 bytes] + * RET | JMP __x86_return_thunk [1,5 bytes; CONFIG_RETHUNK] + * INT3 [1 byte; CONFIG_SLS] */ -#define SETCC_LENGTH (ENDBR_INSN_SIZE + 4 + IS_ENABLED(CONFIG_SLS)) -#define SETCC_ALIGN (4 << IS_ENABLED(CONFIG_SLS) << HAS_KERNEL_IBT) -static_assert(SETCC_LENGTH <= SETCC_ALIGN); +#define SETCC_ALIGN 16 #define FOP_SETCC(op) \ ".align " __stringify(SETCC_ALIGN) " \n\t" \ @@ -453,9 +453,10 @@ static_assert(SETCC_LENGTH <= SETCC_ALIGN); #op ": \n\t" \ ASM_ENDBR \ #op " %al \n\t" \ - __FOP_RET(#op) + __FOP_RET(#op) \ + ".skip " __stringify(SETCC_ALIGN) " - (.-" #op "), 0xcc \n\t" -FOP_START(setcc) +__FOP_START(setcc, SETCC_ALIGN) FOP_SETCC(seto) FOP_SETCC(setno) FOP_SETCC(setc) diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index f1bdac3f5aa8..0e68b4c937fc 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2039,6 +2039,19 @@ static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val) } } +static void kvm_lapic_xapic_id_updated(struct kvm_lapic *apic) +{ + struct kvm *kvm = apic->vcpu->kvm; + + if (KVM_BUG_ON(apic_x2apic_mode(apic), kvm)) + return; + + if (kvm_xapic_id(apic) == apic->vcpu->vcpu_id) + return; + + kvm_set_apicv_inhibit(apic->vcpu->kvm, APICV_INHIBIT_REASON_APIC_ID_MODIFIED); +} + static int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) { int ret = 0; @@ -2047,10 +2060,12 @@ static int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) switch (reg) { case APIC_ID: /* Local APIC ID */ - if (!apic_x2apic_mode(apic)) + if (!apic_x2apic_mode(apic)) { kvm_apic_set_xapic_id(apic, val >> 24); - else + kvm_lapic_xapic_id_updated(apic); + } else { ret = 1; + } break; case APIC_TASKPRI: @@ -2336,8 +2351,10 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) MSR_IA32_APICBASE_BASE; if ((value & MSR_IA32_APICBASE_ENABLE) && - apic->base_address != APIC_DEFAULT_PHYS_BASE) - pr_warn_once("APIC base relocation is unsupported by KVM"); + apic->base_address != APIC_DEFAULT_PHYS_BASE) { + kvm_set_apicv_inhibit(apic->vcpu->kvm, + APICV_INHIBIT_REASON_APIC_BASE_MODIFIED); + } } void kvm_apic_update_apicv(struct kvm_vcpu *vcpu) @@ -2648,6 +2665,8 @@ static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu, icr = __kvm_lapic_get_reg64(s->regs, APIC_ICR); __kvm_lapic_set_reg(s->regs, APIC_ICR2, icr >> 32); } + } else { + kvm_lapic_xapic_id_updated(vcpu->arch.apic); } return 0; diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index f4653688fa6d..17252f39bd7c 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3411,7 +3411,7 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu) root = mmu_alloc_root(vcpu, i << (30 - PAGE_SHIFT), i << 30, PT32_ROOT_LEVEL, true); mmu->pae_root[i] = root | PT_PRESENT_MASK | - shadow_me_mask; + shadow_me_value; } mmu->root.hpa = __pa(mmu->pae_root); } else { @@ -5179,7 +5179,7 @@ static void __kvm_mmu_free_obsolete_roots(struct kvm *kvm, struct kvm_mmu *mmu) roots_to_free |= KVM_MMU_ROOT_CURRENT; for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) { - if (is_obsolete_root(kvm, mmu->root.hpa)) + if (is_obsolete_root(kvm, mmu->prev_roots[i].hpa)) roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i); } diff --git a/arch/x86/kvm/mmu/tdp_iter.c b/arch/x86/kvm/mmu/tdp_iter.c index 6d3b3e5a5533..ee4802d7b36c 100644 --- a/arch/x86/kvm/mmu/tdp_iter.c +++ b/arch/x86/kvm/mmu/tdp_iter.c @@ -146,6 +146,15 @@ static bool try_step_up(struct tdp_iter *iter) } /* + * Step the iterator back up a level in the paging structure. Should only be + * used when the iterator is below the root level. + */ +void tdp_iter_step_up(struct tdp_iter *iter) +{ + WARN_ON(!try_step_up(iter)); +} + +/* * Step to the next SPTE in a pre-order traversal of the paging structure. * To get to the next SPTE, the iterator either steps down towards the goal * GFN, if at a present, non-last-level SPTE, or over to a SPTE mapping a diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h index f0af385c56e0..adfca0cf94d3 100644 --- a/arch/x86/kvm/mmu/tdp_iter.h +++ b/arch/x86/kvm/mmu/tdp_iter.h @@ -114,5 +114,6 @@ void tdp_iter_start(struct tdp_iter *iter, struct kvm_mmu_page *root, int min_level, gfn_t next_last_level_gfn); void tdp_iter_next(struct tdp_iter *iter); void tdp_iter_restart(struct tdp_iter *iter); +void tdp_iter_step_up(struct tdp_iter *iter); #endif /* __KVM_X86_MMU_TDP_ITER_H */ diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 841feaa48be5..7b9265d67131 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -1742,12 +1742,12 @@ static void zap_collapsible_spte_range(struct kvm *kvm, gfn_t start = slot->base_gfn; gfn_t end = start + slot->npages; struct tdp_iter iter; + int max_mapping_level; kvm_pfn_t pfn; rcu_read_lock(); tdp_root_for_each_pte(iter, root, start, end) { -retry: if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true)) continue; @@ -1755,15 +1755,41 @@ retry: !is_last_spte(iter.old_spte, iter.level)) continue; + /* + * This is a leaf SPTE. Check if the PFN it maps can + * be mapped at a higher level. + */ pfn = spte_to_pfn(iter.old_spte); - if (kvm_is_reserved_pfn(pfn) || - iter.level >= kvm_mmu_max_mapping_level(kvm, slot, iter.gfn, - pfn, PG_LEVEL_NUM)) + + if (kvm_is_reserved_pfn(pfn)) continue; + max_mapping_level = kvm_mmu_max_mapping_level(kvm, slot, + iter.gfn, pfn, PG_LEVEL_NUM); + + WARN_ON(max_mapping_level < iter.level); + + /* + * If this page is already mapped at the highest + * viable level, there's nothing more to do. + */ + if (max_mapping_level == iter.level) + continue; + + /* + * The page can be remapped at a higher level, so step + * up to zap the parent SPTE. + */ + while (max_mapping_level > iter.level) + tdp_iter_step_up(&iter); + /* Note, a successful atomic zap also does a remote TLB flush. */ - if (tdp_mmu_zap_spte_atomic(kvm, &iter)) - goto retry; + tdp_mmu_zap_spte_atomic(kvm, &iter); + + /* + * If the atomic zap fails, the iter will recurse back into + * the same subtree to retry. + */ } rcu_read_unlock(); diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 54fe03714f8a..d1bc5820ea46 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -291,58 +291,91 @@ void avic_ring_doorbell(struct kvm_vcpu *vcpu) static int avic_kick_target_vcpus_fast(struct kvm *kvm, struct kvm_lapic *source, u32 icrl, u32 icrh, u32 index) { - u32 dest, apic_id; - struct kvm_vcpu *vcpu; + u32 l1_physical_id, dest; + struct kvm_vcpu *target_vcpu; int dest_mode = icrl & APIC_DEST_MASK; int shorthand = icrl & APIC_SHORT_MASK; struct kvm_svm *kvm_svm = to_kvm_svm(kvm); - u32 *avic_logical_id_table = page_address(kvm_svm->avic_logical_id_table_page); if (shorthand != APIC_DEST_NOSHORT) return -EINVAL; - /* - * The AVIC incomplete IPI #vmexit info provides index into - * the physical APIC ID table, which can be used to derive - * guest physical APIC ID. - */ + if (apic_x2apic_mode(source)) + dest = icrh; + else + dest = GET_APIC_DEST_FIELD(icrh); + if (dest_mode == APIC_DEST_PHYSICAL) { - apic_id = index; + /* broadcast destination, use slow path */ + if (apic_x2apic_mode(source) && dest == X2APIC_BROADCAST) + return -EINVAL; + if (!apic_x2apic_mode(source) && dest == APIC_BROADCAST) + return -EINVAL; + + l1_physical_id = dest; + + if (WARN_ON_ONCE(l1_physical_id != index)) + return -EINVAL; + } else { - if (!apic_x2apic_mode(source)) { - /* For xAPIC logical mode, the index is for logical APIC table. */ - apic_id = avic_logical_id_table[index] & 0x1ff; + u32 bitmap, cluster; + int logid_index; + + if (apic_x2apic_mode(source)) { + /* 16 bit dest mask, 16 bit cluster id */ + bitmap = dest & 0xFFFF0000; + cluster = (dest >> 16) << 4; + } else if (kvm_lapic_get_reg(source, APIC_DFR) == APIC_DFR_FLAT) { + /* 8 bit dest mask*/ + bitmap = dest; + cluster = 0; } else { - return -EINVAL; + /* 4 bit desk mask, 4 bit cluster id */ + bitmap = dest & 0xF; + cluster = (dest >> 4) << 2; } - } - /* - * Assuming vcpu ID is the same as physical apic ID, - * and use it to retrieve the target vCPU. - */ - vcpu = kvm_get_vcpu_by_id(kvm, apic_id); - if (!vcpu) - return -EINVAL; + if (unlikely(!bitmap)) + /* guest bug: nobody to send the logical interrupt to */ + return 0; - if (apic_x2apic_mode(vcpu->arch.apic)) - dest = icrh; - else - dest = GET_APIC_DEST_FIELD(icrh); + if (!is_power_of_2(bitmap)) + /* multiple logical destinations, use slow path */ + return -EINVAL; - /* - * Try matching the destination APIC ID with the vCPU. - */ - if (kvm_apic_match_dest(vcpu, source, shorthand, dest, dest_mode)) { - vcpu->arch.apic->irr_pending = true; - svm_complete_interrupt_delivery(vcpu, - icrl & APIC_MODE_MASK, - icrl & APIC_INT_LEVELTRIG, - icrl & APIC_VECTOR_MASK); - return 0; + logid_index = cluster + __ffs(bitmap); + + if (apic_x2apic_mode(source)) { + l1_physical_id = logid_index; + } else { + u32 *avic_logical_id_table = + page_address(kvm_svm->avic_logical_id_table_page); + + u32 logid_entry = avic_logical_id_table[logid_index]; + + if (WARN_ON_ONCE(index != logid_index)) + return -EINVAL; + + /* guest bug: non existing/reserved logical destination */ + if (unlikely(!(logid_entry & AVIC_LOGICAL_ID_ENTRY_VALID_MASK))) + return 0; + + l1_physical_id = logid_entry & + AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK; + } } - return -EINVAL; + target_vcpu = kvm_get_vcpu_by_id(kvm, l1_physical_id); + if (unlikely(!target_vcpu)) + /* guest bug: non existing vCPU is a target of this IPI*/ + return 0; + + target_vcpu->arch.apic->irr_pending = true; + svm_complete_interrupt_delivery(target_vcpu, + icrl & APIC_MODE_MASK, + icrl & APIC_INT_LEVELTRIG, + icrl & APIC_VECTOR_MASK); + return 0; } static void avic_kick_target_vcpus(struct kvm *kvm, struct kvm_lapic *source, @@ -508,35 +541,6 @@ static int avic_handle_ldr_update(struct kvm_vcpu *vcpu) return ret; } -static int avic_handle_apic_id_update(struct kvm_vcpu *vcpu) -{ - u64 *old, *new; - struct vcpu_svm *svm = to_svm(vcpu); - u32 id = kvm_xapic_id(vcpu->arch.apic); - - if (vcpu->vcpu_id == id) - return 0; - - old = avic_get_physical_id_entry(vcpu, vcpu->vcpu_id); - new = avic_get_physical_id_entry(vcpu, id); - if (!new || !old) - return 1; - - /* We need to move physical_id_entry to new offset */ - *new = *old; - *old = 0ULL; - to_svm(vcpu)->avic_physical_id_cache = new; - - /* - * Also update the guest physical APIC ID in the logical - * APIC ID table entry if already setup the LDR. - */ - if (svm->ldr_reg) - avic_handle_ldr_update(vcpu); - - return 0; -} - static void avic_handle_dfr_update(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -555,10 +559,6 @@ static int avic_unaccel_trap_write(struct kvm_vcpu *vcpu) AVIC_UNACCEL_ACCESS_OFFSET_MASK; switch (offset) { - case APIC_ID: - if (avic_handle_apic_id_update(vcpu)) - return 0; - break; case APIC_LDR: if (avic_handle_ldr_update(vcpu)) return 0; @@ -650,8 +650,6 @@ int avic_init_vcpu(struct vcpu_svm *svm) void avic_apicv_post_state_restore(struct kvm_vcpu *vcpu) { - if (avic_handle_apic_id_update(vcpu) != 0) - return; avic_handle_dfr_update(vcpu); avic_handle_ldr_update(vcpu); } @@ -910,7 +908,9 @@ bool avic_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason) BIT(APICV_INHIBIT_REASON_PIT_REINJ) | BIT(APICV_INHIBIT_REASON_X2APIC) | BIT(APICV_INHIBIT_REASON_BLOCKIRQ) | - BIT(APICV_INHIBIT_REASON_SEV); + BIT(APICV_INHIBIT_REASON_SEV) | + BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) | + BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED); return supported & BIT(reason); } @@ -946,7 +946,7 @@ out: return ret; } -void __avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu) +void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { u64 entry; int h_physical_id = kvm_cpu_get_apicid(cpu); @@ -978,7 +978,7 @@ void __avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu) avic_update_iommu_vcpu_affinity(vcpu, h_physical_id, true); } -void __avic_vcpu_put(struct kvm_vcpu *vcpu) +void avic_vcpu_put(struct kvm_vcpu *vcpu) { u64 entry; struct vcpu_svm *svm = to_svm(vcpu); @@ -997,25 +997,6 @@ void __avic_vcpu_put(struct kvm_vcpu *vcpu) WRITE_ONCE(*(svm->avic_physical_id_cache), entry); } -static void avic_vcpu_load(struct kvm_vcpu *vcpu) -{ - int cpu = get_cpu(); - - WARN_ON(cpu != vcpu->cpu); - - __avic_vcpu_load(vcpu, cpu); - - put_cpu(); -} - -static void avic_vcpu_put(struct kvm_vcpu *vcpu) -{ - preempt_disable(); - - __avic_vcpu_put(vcpu); - - preempt_enable(); -} void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) { @@ -1042,7 +1023,7 @@ void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) vmcb_mark_dirty(vmcb, VMCB_AVIC); if (activated) - avic_vcpu_load(vcpu); + avic_vcpu_load(vcpu, vcpu->cpu); else avic_vcpu_put(vcpu); @@ -1075,5 +1056,5 @@ void avic_vcpu_unblocking(struct kvm_vcpu *vcpu) if (!kvm_vcpu_apicv_active(vcpu)) return; - avic_vcpu_load(vcpu); + avic_vcpu_load(vcpu, vcpu->cpu); } diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index bed5e1692cef..ba7cd26f438f 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -616,6 +616,8 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm) struct kvm_vcpu *vcpu = &svm->vcpu; struct vmcb *vmcb01 = svm->vmcb01.ptr; struct vmcb *vmcb02 = svm->nested.vmcb02.ptr; + u32 pause_count12; + u32 pause_thresh12; /* * Filled at exit: exit_code, exit_code_hi, exit_info_1, exit_info_2, @@ -671,27 +673,25 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm) if (!nested_vmcb_needs_vls_intercept(svm)) vmcb02->control.virt_ext |= VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK; + pause_count12 = svm->pause_filter_enabled ? svm->nested.ctl.pause_filter_count : 0; + pause_thresh12 = svm->pause_threshold_enabled ? svm->nested.ctl.pause_filter_thresh : 0; if (kvm_pause_in_guest(svm->vcpu.kvm)) { - /* use guest values since host doesn't use them */ - vmcb02->control.pause_filter_count = - svm->pause_filter_enabled ? - svm->nested.ctl.pause_filter_count : 0; + /* use guest values since host doesn't intercept PAUSE */ + vmcb02->control.pause_filter_count = pause_count12; + vmcb02->control.pause_filter_thresh = pause_thresh12; - vmcb02->control.pause_filter_thresh = - svm->pause_threshold_enabled ? - svm->nested.ctl.pause_filter_thresh : 0; - - } else if (!vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_PAUSE)) { - /* use host values when guest doesn't use them */ + } else { + /* start from host values otherwise */ vmcb02->control.pause_filter_count = vmcb01->control.pause_filter_count; vmcb02->control.pause_filter_thresh = vmcb01->control.pause_filter_thresh; - } else { - /* - * Intercept every PAUSE otherwise and - * ignore both host and guest values - */ - vmcb02->control.pause_filter_count = 0; - vmcb02->control.pause_filter_thresh = 0; + + /* ... but ensure filtering is disabled if so requested. */ + if (vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_PAUSE)) { + if (!pause_count12) + vmcb02->control.pause_filter_count = 0; + if (!pause_thresh12) + vmcb02->control.pause_filter_thresh = 0; + } } nested_svm_transition_tlb_flush(vcpu); @@ -951,8 +951,11 @@ int nested_svm_vmexit(struct vcpu_svm *svm) vmcb12->control.event_inj = svm->nested.ctl.event_inj; vmcb12->control.event_inj_err = svm->nested.ctl.event_inj_err; - if (!kvm_pause_in_guest(vcpu->kvm) && vmcb02->control.pause_filter_count) + if (!kvm_pause_in_guest(vcpu->kvm)) { vmcb01->control.pause_filter_count = vmcb02->control.pause_filter_count; + vmcb_mark_dirty(vmcb01, VMCB_INTERCEPTS); + + } nested_svm_copy_common_state(svm->nested.vmcb02.ptr, svm->vmcb01.ptr); @@ -982,7 +985,7 @@ int nested_svm_vmexit(struct vcpu_svm *svm) if (svm->tsc_ratio_msr != kvm_default_tsc_scaling_ratio) { WARN_ON(!svm->tsc_scaling_enabled); vcpu->arch.tsc_scaling_ratio = vcpu->arch.l1_tsc_scaling_ratio; - svm_write_tsc_multiplier(vcpu, vcpu->arch.tsc_scaling_ratio); + __svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio); } svm->nested.ctl.nested_cr3 = 0; @@ -1387,7 +1390,7 @@ void nested_svm_update_tsc_ratio_msr(struct kvm_vcpu *vcpu) vcpu->arch.tsc_scaling_ratio = kvm_calc_nested_tsc_multiplier(vcpu->arch.l1_tsc_scaling_ratio, svm->tsc_ratio_msr); - svm_write_tsc_multiplier(vcpu, vcpu->arch.tsc_scaling_ratio); + __svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio); } /* Inverse operation of nested_copy_vmcb_control_to_cache(). asid is copied too. */ diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 51fd985cf21d..0c240ed04f96 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -844,7 +844,7 @@ static int __sev_dbg_encrypt_user(struct kvm *kvm, unsigned long paddr, /* If source buffer is not aligned then use an intermediate buffer */ if (!IS_ALIGNED((unsigned long)vaddr, 16)) { - src_tpage = alloc_page(GFP_KERNEL); + src_tpage = alloc_page(GFP_KERNEL_ACCOUNT); if (!src_tpage) return -ENOMEM; @@ -865,7 +865,7 @@ static int __sev_dbg_encrypt_user(struct kvm *kvm, unsigned long paddr, if (!IS_ALIGNED((unsigned long)dst_vaddr, 16) || !IS_ALIGNED(size, 16)) { int dst_offset; - dst_tpage = alloc_page(GFP_KERNEL); + dst_tpage = alloc_page(GFP_KERNEL_ACCOUNT); if (!dst_tpage) { ret = -ENOMEM; goto e_free; @@ -1665,19 +1665,24 @@ static void sev_migrate_from(struct kvm *dst_kvm, struct kvm *src_kvm) { struct kvm_sev_info *dst = &to_kvm_svm(dst_kvm)->sev_info; struct kvm_sev_info *src = &to_kvm_svm(src_kvm)->sev_info; + struct kvm_vcpu *dst_vcpu, *src_vcpu; + struct vcpu_svm *dst_svm, *src_svm; struct kvm_sev_info *mirror; + unsigned long i; dst->active = true; dst->asid = src->asid; dst->handle = src->handle; dst->pages_locked = src->pages_locked; dst->enc_context_owner = src->enc_context_owner; + dst->es_active = src->es_active; src->asid = 0; src->active = false; src->handle = 0; src->pages_locked = 0; src->enc_context_owner = NULL; + src->es_active = false; list_cut_before(&dst->regions_list, &src->regions_list, &src->regions_list); @@ -1704,26 +1709,21 @@ static void sev_migrate_from(struct kvm *dst_kvm, struct kvm *src_kvm) list_del(&src->mirror_entry); list_add_tail(&dst->mirror_entry, &owner_sev_info->mirror_vms); } -} -static int sev_es_migrate_from(struct kvm *dst, struct kvm *src) -{ - unsigned long i; - struct kvm_vcpu *dst_vcpu, *src_vcpu; - struct vcpu_svm *dst_svm, *src_svm; + kvm_for_each_vcpu(i, dst_vcpu, dst_kvm) { + dst_svm = to_svm(dst_vcpu); - if (atomic_read(&src->online_vcpus) != atomic_read(&dst->online_vcpus)) - return -EINVAL; + sev_init_vmcb(dst_svm); - kvm_for_each_vcpu(i, src_vcpu, src) { - if (!src_vcpu->arch.guest_state_protected) - return -EINVAL; - } + if (!dst->es_active) + continue; - kvm_for_each_vcpu(i, src_vcpu, src) { + /* + * Note, the source is not required to have the same number of + * vCPUs as the destination when migrating a vanilla SEV VM. + */ + src_vcpu = kvm_get_vcpu(dst_kvm, i); src_svm = to_svm(src_vcpu); - dst_vcpu = kvm_get_vcpu(dst, i); - dst_svm = to_svm(dst_vcpu); /* * Transfer VMSA and GHCB state to the destination. Nullify and @@ -1740,8 +1740,23 @@ static int sev_es_migrate_from(struct kvm *dst, struct kvm *src) src_svm->vmcb->control.vmsa_pa = INVALID_PAGE; src_vcpu->arch.guest_state_protected = false; } - to_kvm_svm(src)->sev_info.es_active = false; - to_kvm_svm(dst)->sev_info.es_active = true; +} + +static int sev_check_source_vcpus(struct kvm *dst, struct kvm *src) +{ + struct kvm_vcpu *src_vcpu; + unsigned long i; + + if (!sev_es_guest(src)) + return 0; + + if (atomic_read(&src->online_vcpus) != atomic_read(&dst->online_vcpus)) + return -EINVAL; + + kvm_for_each_vcpu(i, src_vcpu, src) { + if (!src_vcpu->arch.guest_state_protected) + return -EINVAL; + } return 0; } @@ -1789,11 +1804,9 @@ int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd) if (ret) goto out_dst_vcpu; - if (sev_es_guest(source_kvm)) { - ret = sev_es_migrate_from(kvm, source_kvm); - if (ret) - goto out_source_vcpu; - } + ret = sev_check_source_vcpus(kvm, source_kvm); + if (ret) + goto out_source_vcpu; sev_migrate_from(kvm, source_kvm); kvm_vm_dead(source_kvm); @@ -2914,7 +2927,7 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in) count, in); } -void sev_es_init_vmcb(struct vcpu_svm *svm) +static void sev_es_init_vmcb(struct vcpu_svm *svm) { struct kvm_vcpu *vcpu = &svm->vcpu; @@ -2967,6 +2980,15 @@ void sev_es_init_vmcb(struct vcpu_svm *svm) } } +void sev_init_vmcb(struct vcpu_svm *svm) +{ + svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ENABLE; + clr_exception_intercept(svm, UD_VECTOR); + + if (sev_es_guest(svm->vcpu.kvm)) + sev_es_init_vmcb(svm); +} + void sev_es_vcpu_reset(struct vcpu_svm *svm) { /* diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 200045f71df0..44bbf25dfeb9 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -465,11 +465,24 @@ static int has_svm(void) return 1; } +void __svm_write_tsc_multiplier(u64 multiplier) +{ + preempt_disable(); + + if (multiplier == __this_cpu_read(current_tsc_ratio)) + goto out; + + wrmsrl(MSR_AMD64_TSC_RATIO, multiplier); + __this_cpu_write(current_tsc_ratio, multiplier); +out: + preempt_enable(); +} + static void svm_hardware_disable(void) { /* Make sure we clean up behind us */ if (tsc_scaling) - wrmsrl(MSR_AMD64_TSC_RATIO, SVM_TSC_RATIO_DEFAULT); + __svm_write_tsc_multiplier(SVM_TSC_RATIO_DEFAULT); cpu_svm_disable(); @@ -515,8 +528,7 @@ static int svm_hardware_enable(void) * Set the default value, even if we don't use TSC scaling * to avoid having stale value in the msr */ - wrmsrl(MSR_AMD64_TSC_RATIO, SVM_TSC_RATIO_DEFAULT); - __this_cpu_write(current_tsc_ratio, SVM_TSC_RATIO_DEFAULT); + __svm_write_tsc_multiplier(SVM_TSC_RATIO_DEFAULT); } @@ -909,7 +921,7 @@ static void grow_ple_window(struct kvm_vcpu *vcpu) struct vmcb_control_area *control = &svm->vmcb->control; int old = control->pause_filter_count; - if (kvm_pause_in_guest(vcpu->kvm) || !old) + if (kvm_pause_in_guest(vcpu->kvm)) return; control->pause_filter_count = __grow_ple_window(old, @@ -930,7 +942,7 @@ static void shrink_ple_window(struct kvm_vcpu *vcpu) struct vmcb_control_area *control = &svm->vmcb->control; int old = control->pause_filter_count; - if (kvm_pause_in_guest(vcpu->kvm) || !old) + if (kvm_pause_in_guest(vcpu->kvm)) return; control->pause_filter_count = @@ -999,11 +1011,12 @@ static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) vmcb_mark_dirty(svm->vmcb, VMCB_INTERCEPTS); } -void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 multiplier) +static void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 multiplier) { - wrmsrl(MSR_AMD64_TSC_RATIO, multiplier); + __svm_write_tsc_multiplier(multiplier); } + /* Evaluate instruction intercepts that depend on guest CPUID features. */ static void svm_recalc_instruction_intercepts(struct kvm_vcpu *vcpu, struct vcpu_svm *svm) @@ -1199,15 +1212,8 @@ static void init_vmcb(struct kvm_vcpu *vcpu) svm->vmcb->control.int_ctl |= V_GIF_ENABLE_MASK; } - if (sev_guest(vcpu->kvm)) { - svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ENABLE; - clr_exception_intercept(svm, UD_VECTOR); - - if (sev_es_guest(vcpu->kvm)) { - /* Perform SEV-ES specific VMCB updates */ - sev_es_init_vmcb(svm); - } - } + if (sev_guest(vcpu->kvm)) + sev_init_vmcb(svm); svm_hv_init_vmcb(vmcb); init_vmcb_after_set_cpuid(vcpu); @@ -1363,13 +1369,8 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu) sev_es_prepare_switch_to_guest(hostsa); } - if (tsc_scaling) { - u64 tsc_ratio = vcpu->arch.tsc_scaling_ratio; - if (tsc_ratio != __this_cpu_read(current_tsc_ratio)) { - __this_cpu_write(current_tsc_ratio, tsc_ratio); - wrmsrl(MSR_AMD64_TSC_RATIO, tsc_ratio); - } - } + if (tsc_scaling) + __svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio); if (likely(tsc_aux_uret_slot >= 0)) kvm_set_user_return_msr(tsc_aux_uret_slot, svm->tsc_aux, -1ull); @@ -1392,13 +1393,13 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) indirect_branch_prediction_barrier(); } if (kvm_vcpu_apicv_active(vcpu)) - __avic_vcpu_load(vcpu, cpu); + avic_vcpu_load(vcpu, cpu); } static void svm_vcpu_put(struct kvm_vcpu *vcpu) { if (kvm_vcpu_apicv_active(vcpu)) - __avic_vcpu_put(vcpu); + avic_vcpu_put(vcpu); svm_prepare_host_switch(vcpu); @@ -4255,6 +4256,8 @@ out: static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu) { + if (to_svm(vcpu)->vmcb->control.exit_code == SVM_EXIT_INTR) + vcpu->arch.at_instruction_boundary = true; } static void svm_sched_in(struct kvm_vcpu *vcpu, int cpu) diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 21c5460e947a..9223ac100ef5 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -590,7 +590,7 @@ int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, bool has_error_code, u32 error_code); int nested_svm_exit_special(struct vcpu_svm *svm); void nested_svm_update_tsc_ratio_msr(struct kvm_vcpu *vcpu); -void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 multiplier); +void __svm_write_tsc_multiplier(u64 multiplier); void nested_copy_vmcb_control_to_cache(struct vcpu_svm *svm, struct vmcb_control_area *control); void nested_copy_vmcb_save_to_cache(struct vcpu_svm *svm, @@ -610,8 +610,8 @@ void avic_init_vmcb(struct vcpu_svm *svm, struct vmcb *vmcb); int avic_incomplete_ipi_interception(struct kvm_vcpu *vcpu); int avic_unaccelerated_access_interception(struct kvm_vcpu *vcpu); int avic_init_vcpu(struct vcpu_svm *svm); -void __avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu); -void __avic_vcpu_put(struct kvm_vcpu *vcpu); +void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu); +void avic_vcpu_put(struct kvm_vcpu *vcpu); void avic_apicv_post_state_restore(struct kvm_vcpu *vcpu); void avic_set_virtual_apic_mode(struct kvm_vcpu *vcpu); void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu); @@ -649,10 +649,10 @@ void __init sev_set_cpu_caps(void); void __init sev_hardware_setup(void); void sev_hardware_unsetup(void); int sev_cpu_init(struct svm_cpu_data *sd); +void sev_init_vmcb(struct vcpu_svm *svm); void sev_free_vcpu(struct kvm_vcpu *vcpu); int sev_handle_vmgexit(struct kvm_vcpu *vcpu); int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in); -void sev_es_init_vmcb(struct vcpu_svm *svm); void sev_es_vcpu_reset(struct vcpu_svm *svm); void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector); void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa); diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S index dfaeb47fcf2a..723f8534986c 100644 --- a/arch/x86/kvm/svm/vmenter.S +++ b/arch/x86/kvm/svm/vmenter.S @@ -111,6 +111,15 @@ SYM_FUNC_START(__svm_vcpu_run) #endif /* + * Mitigate RETBleed for AMD/Hygon Zen uarch. RET should be + * untrained as soon as we exit the VM and are back to the + * kernel. This should be done before re-enabling interrupts + * because interrupt handlers won't sanitize 'ret' if the return is + * from the kernel. + */ + UNTRAIN_RET + + /* * Clear all general purpose registers except RSP and RAX to prevent * speculative use of the guest's values, even those that are reloaded * via the stack. In theory, an L1 cache miss when restoring registers @@ -190,6 +199,15 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run) FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE #endif + /* + * Mitigate RETBleed for AMD/Hygon Zen uarch. RET should be + * untrained as soon as we exit the VM and are back to the + * kernel. This should be done before re-enabling interrupts + * because interrupt handlers won't sanitize RET if the return is + * from the kernel. + */ + UNTRAIN_RET + pop %_ASM_BX #ifdef CONFIG_X86_64 diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index 3f430e218375..c0e24826a86f 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -4,8 +4,8 @@ #include <asm/vmx.h> -#include "lapic.h" -#include "x86.h" +#include "../lapic.h" +#include "../x86.h" extern bool __read_mostly enable_vpid; extern bool __read_mostly flexpriority_enabled; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index f5cb18e00e78..ab135f9ef52f 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -2278,7 +2278,6 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs0 SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_ENABLE_VMFUNC | - SECONDARY_EXEC_TSC_SCALING | SECONDARY_EXEC_DESC); if (nested_cpu_has(vmcs12, @@ -3087,7 +3086,7 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) } vm_fail = __vmx_vcpu_run(vmx, (unsigned long *)&vcpu->arch.regs, - vmx->loaded_vmcs->launched); + __vmx_vcpu_run_flags(vmx)); if (vmx->msr_autoload.host.nr) vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr); diff --git a/arch/x86/kvm/vmx/run_flags.h b/arch/x86/kvm/vmx/run_flags.h new file mode 100644 index 000000000000..edc3f16cc189 --- /dev/null +++ b/arch/x86/kvm/vmx/run_flags.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __KVM_X86_VMX_RUN_FLAGS_H +#define __KVM_X86_VMX_RUN_FLAGS_H + +#define VMX_RUN_VMRESUME (1 << 0) +#define VMX_RUN_SAVE_SPEC_CTRL (1 << 1) + +#endif /* __KVM_X86_VMX_RUN_FLAGS_H */ diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 435c187927c4..4182c7ffc909 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -1,10 +1,13 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/linkage.h> #include <asm/asm.h> +#include <asm/asm-offsets.h> #include <asm/bitsperlong.h> #include <asm/kvm_vcpu_regs.h> #include <asm/nospec-branch.h> +#include <asm/percpu.h> #include <asm/segment.h> +#include "run_flags.h" #define WORD_SIZE (BITS_PER_LONG / 8) @@ -31,72 +34,11 @@ .section .noinstr.text, "ax" /** - * vmx_vmenter - VM-Enter the current loaded VMCS - * - * %RFLAGS.ZF: !VMCS.LAUNCHED, i.e. controls VMLAUNCH vs. VMRESUME - * - * Returns: - * %RFLAGS.CF is set on VM-Fail Invalid - * %RFLAGS.ZF is set on VM-Fail Valid - * %RFLAGS.{CF,ZF} are cleared on VM-Success, i.e. VM-Exit - * - * Note that VMRESUME/VMLAUNCH fall-through and return directly if - * they VM-Fail, whereas a successful VM-Enter + VM-Exit will jump - * to vmx_vmexit. - */ -SYM_FUNC_START_LOCAL(vmx_vmenter) - /* EFLAGS.ZF is set if VMCS.LAUNCHED == 0 */ - je 2f - -1: vmresume - RET - -2: vmlaunch - RET - -3: cmpb $0, kvm_rebooting - je 4f - RET -4: ud2 - - _ASM_EXTABLE(1b, 3b) - _ASM_EXTABLE(2b, 3b) - -SYM_FUNC_END(vmx_vmenter) - -/** - * vmx_vmexit - Handle a VMX VM-Exit - * - * Returns: - * %RFLAGS.{CF,ZF} are cleared on VM-Success, i.e. VM-Exit - * - * This is vmx_vmenter's partner in crime. On a VM-Exit, control will jump - * here after hardware loads the host's state, i.e. this is the destination - * referred to by VMCS.HOST_RIP. - */ -SYM_FUNC_START(vmx_vmexit) -#ifdef CONFIG_RETPOLINE - ALTERNATIVE "jmp .Lvmexit_skip_rsb", "", X86_FEATURE_RETPOLINE - /* Preserve guest's RAX, it's used to stuff the RSB. */ - push %_ASM_AX - - /* 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 - RET -SYM_FUNC_END(vmx_vmexit) - -/** * __vmx_vcpu_run - Run a vCPU via a transition to VMX guest mode - * @vmx: struct vcpu_vmx * (forwarded to vmx_update_host_rsp) + * @vmx: struct vcpu_vmx * * @regs: unsigned long * (to guest registers) - * @launched: %true if the VMCS has been launched + * @flags: VMX_RUN_VMRESUME: use VMRESUME instead of VMLAUNCH + * VMX_RUN_SAVE_SPEC_CTRL: save guest SPEC_CTRL into vmx->spec_ctrl * * Returns: * 0 on VM-Exit, 1 on VM-Fail @@ -115,24 +57,56 @@ SYM_FUNC_START(__vmx_vcpu_run) #endif push %_ASM_BX + /* Save @vmx for SPEC_CTRL handling */ + push %_ASM_ARG1 + + /* Save @flags for SPEC_CTRL handling */ + push %_ASM_ARG3 + /* * Save @regs, _ASM_ARG2 may be modified by vmx_update_host_rsp() and * @regs is needed after VM-Exit to save the guest's register values. */ push %_ASM_ARG2 - /* Copy @launched to BL, _ASM_ARG3 is volatile. */ + /* Copy @flags to BL, _ASM_ARG3 is volatile. */ mov %_ASM_ARG3B, %bl - /* Adjust RSP to account for the CALL to vmx_vmenter(). */ - lea -WORD_SIZE(%_ASM_SP), %_ASM_ARG2 + lea (%_ASM_SP), %_ASM_ARG2 call vmx_update_host_rsp + ALTERNATIVE "jmp .Lspec_ctrl_done", "", X86_FEATURE_MSR_SPEC_CTRL + + /* + * SPEC_CTRL handling: if the guest's SPEC_CTRL value differs from the + * host's, write the MSR. + * + * IMPORTANT: To avoid RSB underflow attacks and any other nastiness, + * there must not be any returns or indirect branches between this code + * and vmentry. + */ + mov 2*WORD_SIZE(%_ASM_SP), %_ASM_DI + movl VMX_spec_ctrl(%_ASM_DI), %edi + movl PER_CPU_VAR(x86_spec_ctrl_current), %esi + cmp %edi, %esi + je .Lspec_ctrl_done + mov $MSR_IA32_SPEC_CTRL, %ecx + xor %edx, %edx + mov %edi, %eax + wrmsr + +.Lspec_ctrl_done: + + /* + * Since vmentry is serializing on affected CPUs, there's no need for + * an LFENCE to stop speculation from skipping the wrmsr. + */ + /* Load @regs to RAX. */ mov (%_ASM_SP), %_ASM_AX /* Check if vmlaunch or vmresume is needed */ - testb %bl, %bl + testb $VMX_RUN_VMRESUME, %bl /* Load guest registers. Don't clobber flags. */ mov VCPU_RCX(%_ASM_AX), %_ASM_CX @@ -154,11 +128,37 @@ SYM_FUNC_START(__vmx_vcpu_run) /* Load guest RAX. This kills the @regs pointer! */ mov VCPU_RAX(%_ASM_AX), %_ASM_AX - /* Enter guest mode */ - call vmx_vmenter + /* Check EFLAGS.ZF from 'testb' above */ + jz .Lvmlaunch + + /* + * After a successful VMRESUME/VMLAUNCH, control flow "magically" + * resumes below at 'vmx_vmexit' due to the VMCS HOST_RIP setting. + * So this isn't a typical function and objtool needs to be told to + * save the unwind state here and restore it below. + */ + UNWIND_HINT_SAVE + +/* + * If VMRESUME/VMLAUNCH and corresponding vmexit succeed, execution resumes at + * the 'vmx_vmexit' label below. + */ +.Lvmresume: + vmresume + jmp .Lvmfail + +.Lvmlaunch: + vmlaunch + jmp .Lvmfail - /* Jump on VM-Fail. */ - jbe 2f + _ASM_EXTABLE(.Lvmresume, .Lfixup) + _ASM_EXTABLE(.Lvmlaunch, .Lfixup) + +SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL) + + /* Restore unwind state from before the VMRESUME/VMLAUNCH. */ + UNWIND_HINT_RESTORE + ENDBR /* Temporarily save guest's RAX. */ push %_ASM_AX @@ -185,21 +185,23 @@ SYM_FUNC_START(__vmx_vcpu_run) mov %r15, VCPU_R15(%_ASM_AX) #endif - /* Clear RAX to indicate VM-Exit (as opposed to VM-Fail). */ - xor %eax, %eax + /* Clear return value to indicate VM-Exit (as opposed to VM-Fail). */ + xor %ebx, %ebx +.Lclear_regs: /* - * Clear all general purpose registers except RSP and RAX to prevent + * Clear all general purpose registers except RSP and RBX to prevent * speculative use of the guest's values, even those that are reloaded * via the stack. In theory, an L1 cache miss when restoring registers * could lead to speculative execution with the guest's values. * Zeroing XORs are dirt cheap, i.e. the extra paranoia is essentially * free. RSP and RAX are exempt as RSP is restored by hardware during - * VM-Exit and RAX is explicitly loaded with 0 or 1 to return VM-Fail. + * VM-Exit and RBX is explicitly loaded with 0 or 1 to hold the return + * value. */ -1: xor %ecx, %ecx + xor %eax, %eax + xor %ecx, %ecx xor %edx, %edx - xor %ebx, %ebx xor %ebp, %ebp xor %esi, %esi xor %edi, %edi @@ -216,8 +218,30 @@ SYM_FUNC_START(__vmx_vcpu_run) /* "POP" @regs. */ add $WORD_SIZE, %_ASM_SP - pop %_ASM_BX + /* + * IMPORTANT: RSB filling and SPEC_CTRL handling must be done before + * the first unbalanced RET after vmexit! + * + * For retpoline or IBRS, RSB filling is needed to prevent poisoned RSB + * entries and (in some cases) RSB underflow. + * + * eIBRS has its own protection against poisoned RSB, so it doesn't + * need the RSB filling sequence. But it does need to be enabled + * before the first unbalanced RET. + */ + + FILL_RETURN_BUFFER %_ASM_CX, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_VMEXIT + + pop %_ASM_ARG2 /* @flags */ + pop %_ASM_ARG1 /* @vmx */ + + call vmx_spec_ctrl_restore_host + + /* Put return value in AX */ + mov %_ASM_BX, %_ASM_AX + + pop %_ASM_BX #ifdef CONFIG_X86_64 pop %r12 pop %r13 @@ -230,9 +254,15 @@ SYM_FUNC_START(__vmx_vcpu_run) pop %_ASM_BP RET - /* VM-Fail. Out-of-line to avoid a taken Jcc after VM-Exit. */ -2: mov $1, %eax - jmp 1b +.Lfixup: + cmpb $0, kvm_rebooting + jne .Lvmfail + ud2 +.Lvmfail: + /* VM-Fail: set return value to 1 */ + mov $1, %_ASM_BX + jmp .Lclear_regs + SYM_FUNC_END(__vmx_vcpu_run) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index a07e8cd753ec..be7c19374fdd 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -229,6 +229,9 @@ static const struct { #define L1D_CACHE_ORDER 4 static void *vmx_l1d_flush_pages; +/* Control for disabling CPU Fill buffer clear */ +static bool __read_mostly vmx_fb_clear_ctrl_available; + static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf) { struct page *page; @@ -360,6 +363,60 @@ static int vmentry_l1d_flush_get(char *s, const struct kernel_param *kp) return sprintf(s, "%s\n", vmentry_l1d_param[l1tf_vmx_mitigation].option); } +static void vmx_setup_fb_clear_ctrl(void) +{ + u64 msr; + + if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES) && + !boot_cpu_has_bug(X86_BUG_MDS) && + !boot_cpu_has_bug(X86_BUG_TAA)) { + rdmsrl(MSR_IA32_ARCH_CAPABILITIES, msr); + if (msr & ARCH_CAP_FB_CLEAR_CTRL) + vmx_fb_clear_ctrl_available = true; + } +} + +static __always_inline void vmx_disable_fb_clear(struct vcpu_vmx *vmx) +{ + u64 msr; + + if (!vmx->disable_fb_clear) + return; + + msr = __rdmsr(MSR_IA32_MCU_OPT_CTRL); + msr |= FB_CLEAR_DIS; + native_wrmsrl(MSR_IA32_MCU_OPT_CTRL, msr); + /* Cache the MSR value to avoid reading it later */ + vmx->msr_ia32_mcu_opt_ctrl = msr; +} + +static __always_inline void vmx_enable_fb_clear(struct vcpu_vmx *vmx) +{ + if (!vmx->disable_fb_clear) + return; + + vmx->msr_ia32_mcu_opt_ctrl &= ~FB_CLEAR_DIS; + native_wrmsrl(MSR_IA32_MCU_OPT_CTRL, vmx->msr_ia32_mcu_opt_ctrl); +} + +static void vmx_update_fb_clear_dis(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx) +{ + vmx->disable_fb_clear = vmx_fb_clear_ctrl_available; + + /* + * If guest will not execute VERW, there is no need to set FB_CLEAR_DIS + * at VMEntry. Skip the MSR read/write when a guest has no use case to + * execute VERW. + */ + if ((vcpu->arch.arch_capabilities & ARCH_CAP_FB_CLEAR) || + ((vcpu->arch.arch_capabilities & ARCH_CAP_MDS_NO) && + (vcpu->arch.arch_capabilities & ARCH_CAP_TAA_NO) && + (vcpu->arch.arch_capabilities & ARCH_CAP_PSDP_NO) && + (vcpu->arch.arch_capabilities & ARCH_CAP_FBSDP_NO) && + (vcpu->arch.arch_capabilities & ARCH_CAP_SBDR_SSDP_NO))) + vmx->disable_fb_clear = false; +} + static const struct kernel_param_ops vmentry_l1d_flush_ops = { .set = vmentry_l1d_flush_set, .get = vmentry_l1d_flush_get, @@ -782,6 +839,24 @@ static bool msr_write_intercepted(struct vcpu_vmx *vmx, u32 msr) MSR_IA32_SPEC_CTRL); } +unsigned int __vmx_vcpu_run_flags(struct vcpu_vmx *vmx) +{ + unsigned int flags = 0; + + if (vmx->loaded_vmcs->launched) + flags |= VMX_RUN_VMRESUME; + + /* + * If writes to the SPEC_CTRL MSR aren't intercepted, the guest is free + * to change it directly without causing a vmexit. In that case read + * it after vmexit and store it in vmx->spec_ctrl. + */ + if (unlikely(!msr_write_intercepted(vmx, MSR_IA32_SPEC_CTRL))) + flags |= VMX_RUN_SAVE_SPEC_CTRL; + + return flags; +} + static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx, unsigned long entry, unsigned long exit) { @@ -2252,6 +2327,10 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) ret = kvm_set_msr_common(vcpu, msr_info); } + /* FB_CLEAR may have changed, also update the FB_CLEAR_DIS behavior */ + if (msr_index == MSR_IA32_ARCH_CAPABILITIES) + vmx_update_fb_clear_dis(vcpu, vmx); + return ret; } @@ -4553,6 +4632,8 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); vpid_sync_context(vmx->vpid); + + vmx_update_fb_clear_dis(vcpu, vmx); } static void vmx_enable_irq_window(struct kvm_vcpu *vcpu) @@ -6547,6 +6628,7 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu) return; handle_interrupt_nmi_irqoff(vcpu, gate_offset(desc)); + vcpu->arch.at_instruction_boundary = true; } static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu) @@ -6749,6 +6831,31 @@ void noinstr vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp) } } +void noinstr vmx_spec_ctrl_restore_host(struct vcpu_vmx *vmx, + unsigned int flags) +{ + u64 hostval = this_cpu_read(x86_spec_ctrl_current); + + if (!cpu_feature_enabled(X86_FEATURE_MSR_SPEC_CTRL)) + return; + + if (flags & VMX_RUN_SAVE_SPEC_CTRL) + vmx->spec_ctrl = __rdmsr(MSR_IA32_SPEC_CTRL); + + /* + * If the guest/host SPEC_CTRL values differ, restore the host value. + * + * For legacy IBRS, the IBRS bit always needs to be written after + * transitioning from a less privileged predictor mode, regardless of + * whether the guest/host values differ. + */ + if (cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS) || + vmx->spec_ctrl != hostval) + native_wrmsrl(MSR_IA32_SPEC_CTRL, hostval); + + barrier_nospec(); +} + static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu) { switch (to_vmx(vcpu)->exit_reason.basic) { @@ -6762,7 +6869,8 @@ static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu) } static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, - struct vcpu_vmx *vmx) + struct vcpu_vmx *vmx, + unsigned long flags) { guest_state_enter_irqoff(); @@ -6771,15 +6879,22 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, vmx_l1d_flush(vcpu); else if (static_branch_unlikely(&mds_user_clear)) mds_clear_cpu_buffers(); + else if (static_branch_unlikely(&mmio_stale_data_clear) && + kvm_arch_has_assigned_device(vcpu->kvm)) + mds_clear_cpu_buffers(); + + vmx_disable_fb_clear(vmx); if (vcpu->arch.cr2 != native_read_cr2()) native_write_cr2(vcpu->arch.cr2); vmx->fail = __vmx_vcpu_run(vmx, (unsigned long *)&vcpu->arch.regs, - vmx->loaded_vmcs->launched); + flags); vcpu->arch.cr2 = native_read_cr2(); + vmx_enable_fb_clear(vmx); + guest_state_exit_irqoff(); } @@ -6873,36 +6988,8 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) kvm_wait_lapic_expire(vcpu); - /* - * If this vCPU has touched SPEC_CTRL, restore the guest's value if - * it's non-zero. Since vmentry is serialising on affected CPUs, there - * is no need to worry about the conditional branch over the wrmsr - * being speculatively taken. - */ - x86_spec_ctrl_set_guest(vmx->spec_ctrl, 0); - /* The actual VMENTER/EXIT is in the .noinstr.text section. */ - vmx_vcpu_enter_exit(vcpu, vmx); - - /* - * We do not use IBRS in the kernel. If this vCPU has used the - * SPEC_CTRL MSR it may have left it on; save the value and - * turn it off. This is much more efficient than blindly adding - * it to the atomic save/restore list. Especially as the former - * (Saving guest MSRs on vmexit) doesn't even exist in KVM. - * - * For non-nested case: - * If the L01 MSR bitmap does not intercept the MSR, then we need to - * save it. - * - * For nested case: - * If the L02 MSR bitmap does not intercept the MSR, then we need to - * save it. - */ - if (unlikely(!msr_write_intercepted(vmx, MSR_IA32_SPEC_CTRL))) - vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL); - - x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0); + vmx_vcpu_enter_exit(vcpu, vmx, __vmx_vcpu_run_flags(vmx)); /* All fields are clean at this point */ if (static_branch_unlikely(&enable_evmcs)) { @@ -7708,7 +7795,9 @@ static bool vmx_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason) ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) | BIT(APICV_INHIBIT_REASON_ABSENT) | BIT(APICV_INHIBIT_REASON_HYPERV) | - BIT(APICV_INHIBIT_REASON_BLOCKIRQ); + BIT(APICV_INHIBIT_REASON_BLOCKIRQ) | + BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) | + BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED); return supported & BIT(reason); } @@ -8211,6 +8300,8 @@ static int __init vmx_init(void) return r; } + vmx_setup_fb_clear_ctrl(); + for_each_possible_cpu(cpu) { INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu)); diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index b98c7e96697a..1e7f9453894b 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -8,11 +8,12 @@ #include <asm/intel_pt.h> #include "capabilities.h" -#include "kvm_cache_regs.h" +#include "../kvm_cache_regs.h" #include "posted_intr.h" #include "vmcs.h" #include "vmx_ops.h" -#include "cpuid.h" +#include "../cpuid.h" +#include "run_flags.h" #define MSR_TYPE_R 1 #define MSR_TYPE_W 2 @@ -348,6 +349,8 @@ struct vcpu_vmx { u64 msr_ia32_feature_control_valid_bits; /* SGX Launch Control public key hash */ u64 msr_ia32_sgxlepubkeyhash[4]; + u64 msr_ia32_mcu_opt_ctrl; + bool disable_fb_clear; struct pt_desc pt_desc; struct lbr_desc lbr_desc; @@ -402,7 +405,10 @@ void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu); struct vmx_uret_msr *vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr); void pt_update_intercept_for_msr(struct kvm_vcpu *vcpu); void vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp); -bool __vmx_vcpu_run(struct vcpu_vmx *vmx, unsigned long *regs, bool launched); +void vmx_spec_ctrl_restore_host(struct vcpu_vmx *vmx, unsigned int flags); +unsigned int __vmx_vcpu_run_flags(struct vcpu_vmx *vmx); +bool __vmx_vcpu_run(struct vcpu_vmx *vmx, unsigned long *regs, + unsigned int flags); int vmx_find_loadstore_msr_slot(struct vmx_msrs *m, u32 msr); void vmx_ept_load_pdptrs(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/vmx/vmx_ops.h b/arch/x86/kvm/vmx/vmx_ops.h index 5e7f41225780..5cfc49ddb1b4 100644 --- a/arch/x86/kvm/vmx/vmx_ops.h +++ b/arch/x86/kvm/vmx/vmx_ops.h @@ -8,7 +8,7 @@ #include "evmcs.h" #include "vmcs.h" -#include "x86.h" +#include "../x86.h" asmlinkage void vmread_error(unsigned long field, bool fault); __attribute__((regparm(0))) void vmread_error_trampoline(unsigned long field, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index e9473c7c7390..e5fa335a4ea7 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -296,7 +296,9 @@ const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { STATS_DESC_COUNTER(VCPU, nested_run), STATS_DESC_COUNTER(VCPU, directed_yield_attempted), STATS_DESC_COUNTER(VCPU, directed_yield_successful), - STATS_DESC_ICOUNTER(VCPU, guest_mode) + STATS_DESC_COUNTER(VCPU, preemption_reported), + STATS_DESC_COUNTER(VCPU, preemption_other), + STATS_DESC_IBOOLEAN(VCPU, guest_mode) }; const struct kvm_stats_header kvm_vcpu_stats_header = { @@ -1615,6 +1617,9 @@ static u64 kvm_get_arch_capabilities(void) */ } + /* Guests don't need to know "Fill buffer clear control" exists */ + data &= ~ARCH_CAP_FB_CLEAR_CTRL; + return data; } @@ -4625,6 +4630,19 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) struct kvm_memslots *slots; static const u8 preempted = KVM_VCPU_PREEMPTED; + /* + * The vCPU can be marked preempted if and only if the VM-Exit was on + * an instruction boundary and will not trigger guest emulation of any + * kind (see vcpu_run). Vendor specific code controls (conservatively) + * when this is true, for example allowing the vCPU to be marked + * preempted if and only if the VM-Exit was due to a host interrupt. + */ + if (!vcpu->arch.at_instruction_boundary) { + vcpu->stat.preemption_other++; + return; + } + + vcpu->stat.preemption_reported++; if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; @@ -4654,19 +4672,21 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { int idx; - if (vcpu->preempted && !vcpu->arch.guest_state_protected) - vcpu->arch.preempted_in_kernel = !static_call(kvm_x86_get_cpl)(vcpu); + if (vcpu->preempted) { + if (!vcpu->arch.guest_state_protected) + vcpu->arch.preempted_in_kernel = !static_call(kvm_x86_get_cpl)(vcpu); - /* - * Take the srcu lock as memslots will be accessed to check the gfn - * cache generation against the memslots generation. - */ - idx = srcu_read_lock(&vcpu->kvm->srcu); - if (kvm_xen_msr_enabled(vcpu->kvm)) - kvm_xen_runstate_set_preempted(vcpu); - else - kvm_steal_time_set_preempted(vcpu); - srcu_read_unlock(&vcpu->kvm->srcu, idx); + /* + * Take the srcu lock as memslots will be accessed to check the gfn + * cache generation against the memslots generation. + */ + idx = srcu_read_lock(&vcpu->kvm->srcu); + if (kvm_xen_msr_enabled(vcpu->kvm)) + kvm_xen_runstate_set_preempted(vcpu); + else + kvm_steal_time_set_preempted(vcpu); + srcu_read_unlock(&vcpu->kvm->srcu, idx); + } static_call(kvm_x86_vcpu_put)(vcpu); vcpu->arch.last_host_tsc = rdtsc(); @@ -6009,6 +6029,11 @@ split_irqchip_unlock: r = 0; break; case KVM_CAP_X86_USER_SPACE_MSR: + r = -EINVAL; + if (cap->args[0] & ~(KVM_MSR_EXIT_REASON_INVAL | + KVM_MSR_EXIT_REASON_UNKNOWN | + KVM_MSR_EXIT_REASON_FILTER)) + break; kvm->arch.user_space_msr_mask = cap->args[0]; r = 0; break; @@ -6163,6 +6188,9 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp) if (copy_from_user(&filter, user_msr_filter, sizeof(filter))) return -EFAULT; + if (filter.flags & ~KVM_MSR_FILTER_DEFAULT_DENY) + return -EINVAL; + for (i = 0; i < ARRAY_SIZE(filter.ranges); i++) empty &= !filter.ranges[i].nmsrs; @@ -9123,15 +9151,17 @@ static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr, */ static void kvm_pv_kick_cpu_op(struct kvm *kvm, int apicid) { - struct kvm_lapic_irq lapic_irq; - - lapic_irq.shorthand = APIC_DEST_NOSHORT; - lapic_irq.dest_mode = APIC_DEST_PHYSICAL; - lapic_irq.level = 0; - lapic_irq.dest_id = apicid; - lapic_irq.msi_redir_hint = false; + /* + * All other fields are unused for APIC_DM_REMRD, but may be consumed by + * common code, e.g. for tracing. Defer initialization to the compiler. + */ + struct kvm_lapic_irq lapic_irq = { + .delivery_mode = APIC_DM_REMRD, + .dest_mode = APIC_DEST_PHYSICAL, + .shorthand = APIC_DEST_NOSHORT, + .dest_id = apicid, + }; - lapic_irq.delivery_mode = APIC_DM_REMRD; kvm_irq_delivery_to_apic(kvm, NULL, &lapic_irq, NULL); } @@ -9833,6 +9863,7 @@ void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) return; down_read(&vcpu->kvm->arch.apicv_update_lock); + preempt_disable(); activate = kvm_vcpu_apicv_activated(vcpu); @@ -9853,6 +9884,7 @@ void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) kvm_make_request(KVM_REQ_EVENT, vcpu); out: + preempt_enable(); up_read(&vcpu->kvm->arch.apicv_update_lock); } EXPORT_SYMBOL_GPL(kvm_vcpu_update_apicv); @@ -10422,6 +10454,13 @@ static int vcpu_run(struct kvm_vcpu *vcpu) vcpu->arch.l1tf_flush_l1d = true; for (;;) { + /* + * If another guest vCPU requests a PV TLB flush in the middle + * of instruction emulation, the rest of the emulation could + * use a stale page translation. Assume that any code after + * this point can start executing an instruction. + */ + vcpu->arch.at_instruction_boundary = false; if (kvm_vcpu_running(vcpu)) { r = vcpu_enter_guest(vcpu); } else { @@ -12602,9 +12641,9 @@ void kvm_arch_end_assignment(struct kvm *kvm) } EXPORT_SYMBOL_GPL(kvm_arch_end_assignment); -bool kvm_arch_has_assigned_device(struct kvm *kvm) +bool noinstr kvm_arch_has_assigned_device(struct kvm *kvm) { - return atomic_read(&kvm->arch.assigned_device_count); + return arch_atomic_read(&kvm->arch.assigned_device_count); } EXPORT_SYMBOL_GPL(kvm_arch_has_assigned_device); diff --git a/arch/x86/kvm/xen.h b/arch/x86/kvm/xen.h index ee5c4ae0755c..532a535a9e99 100644 --- a/arch/x86/kvm/xen.h +++ b/arch/x86/kvm/xen.h @@ -159,8 +159,10 @@ static inline void kvm_xen_runstate_set_preempted(struct kvm_vcpu *vcpu) * behalf of the vCPU. Only if the VMM does actually block * does it need to enter RUNSTATE_blocked. */ - if (vcpu->preempted) - kvm_xen_update_runstate_guest(vcpu, RUNSTATE_runnable); + if (WARN_ON_ONCE(!vcpu->preempted)) + return; + + kvm_xen_update_runstate_guest(vcpu, RUNSTATE_runnable); } /* 32-bit compatibility definitions, also used natively in 32-bit build */ diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S index d83cba364e31..724bbf83eb5b 100644 --- a/arch/x86/lib/memmove_64.S +++ b/arch/x86/lib/memmove_64.S @@ -39,7 +39,7 @@ SYM_FUNC_START(__memmove) /* FSRM implies ERMS => no length checks, do the copy directly */ .Lmemmove_begin_forward: ALTERNATIVE "cmp $0x20, %rdx; jb 1f", "", X86_FEATURE_FSRM - ALTERNATIVE "", __stringify(movq %rdx, %rcx; rep movsb; RET), X86_FEATURE_ERMS + ALTERNATIVE "", "jmp .Lmemmove_erms", X86_FEATURE_ERMS /* * movsq instruction have many startup latency @@ -205,6 +205,11 @@ SYM_FUNC_START(__memmove) movb %r11b, (%rdi) 13: RET + +.Lmemmove_erms: + movq %rdx, %rcx + rep movsb + RET SYM_FUNC_END(__memmove) EXPORT_SYMBOL(__memmove) diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index b2b2366885a2..073289a55f84 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -33,9 +33,9 @@ SYM_INNER_LABEL(__x86_indirect_thunk_\reg, SYM_L_GLOBAL) UNWIND_HINT_EMPTY ANNOTATE_NOENDBR - ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), \ - __stringify(RETPOLINE \reg), X86_FEATURE_RETPOLINE, \ - __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg; int3), X86_FEATURE_RETPOLINE_LFENCE + ALTERNATIVE_2 __stringify(RETPOLINE \reg), \ + __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg; int3), X86_FEATURE_RETPOLINE_LFENCE, \ + __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), ALT_NOT(X86_FEATURE_RETPOLINE) .endm @@ -67,3 +67,76 @@ SYM_CODE_END(__x86_indirect_thunk_array) #define GEN(reg) EXPORT_THUNK(reg) #include <asm/GEN-for-each-reg.h> #undef GEN + +/* + * This function name is magical and is used by -mfunction-return=thunk-extern + * for the compiler to generate JMPs to it. + */ +#ifdef CONFIG_RETHUNK + + .section .text.__x86.return_thunk + +/* + * Safety details here pertain to the AMD Zen{1,2} microarchitecture: + * 1) The RET at __x86_return_thunk must be on a 64 byte boundary, for + * alignment within the BTB. + * 2) The instruction at zen_untrain_ret must contain, and not + * end with, the 0xc3 byte of the RET. + * 3) STIBP must be enabled, or SMT disabled, to prevent the sibling thread + * from re-poisioning the BTB prediction. + */ + .align 64 + .skip 63, 0xcc +SYM_FUNC_START_NOALIGN(zen_untrain_ret); + + /* + * As executed from zen_untrain_ret, this is: + * + * TEST $0xcc, %bl + * LFENCE + * JMP __x86_return_thunk + * + * Executing the TEST instruction has a side effect of evicting any BTB + * prediction (potentially attacker controlled) attached to the RET, as + * __x86_return_thunk + 1 isn't an instruction boundary at the moment. + */ + .byte 0xf6 + + /* + * As executed from __x86_return_thunk, this is a plain RET. + * + * As part of the TEST above, RET is the ModRM byte, and INT3 the imm8. + * + * We subsequently jump backwards and architecturally execute the RET. + * This creates a correct BTB prediction (type=ret), but in the + * meantime we suffer Straight Line Speculation (because the type was + * no branch) which is halted by the INT3. + * + * With SMT enabled and STIBP active, a sibling thread cannot poison + * RET's prediction to a type of its choice, but can evict the + * prediction due to competitive sharing. If the prediction is + * evicted, __x86_return_thunk will suffer Straight Line Speculation + * which will be contained safely by the INT3. + */ +SYM_INNER_LABEL(__x86_return_thunk, SYM_L_GLOBAL) + ret + int3 +SYM_CODE_END(__x86_return_thunk) + + /* + * Ensure the TEST decoding / BTB invalidation is complete. + */ + lfence + + /* + * Jump back and execute the RET in the middle of the TEST instruction. + * INT3 is for SLS protection. + */ + jmp __x86_return_thunk + int3 +SYM_FUNC_END(zen_untrain_ret) +__EXPORT_THUNK(zen_untrain_ret) + +EXPORT_SYMBOL(__x86_return_thunk) + +#endif /* CONFIG_RETHUNK */ diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index d8cfce221275..57ba5502aecf 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -77,10 +77,20 @@ static uint8_t __pte2cachemode_tbl[8] = { [__pte2cm_idx(_PAGE_PWT | _PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC, }; -/* Check that the write-protect PAT entry is set for write-protect */ +/* + * Check that the write-protect PAT entry is set for write-protect. + * To do this without making assumptions how PAT has been set up (Xen has + * another layout than the kernel), translate the _PAGE_CACHE_MODE_WP cache + * mode via the __cachemode2pte_tbl[] into protection bits (those protection + * bits will select a cache mode of WP or better), and then translate the + * protection bits back into the cache mode using __pte2cm_idx() and the + * __pte2cachemode_tbl[] array. This will return the really used cache mode. + */ bool x86_has_pat_wp(void) { - return __pte2cachemode_tbl[_PAGE_CACHE_MODE_WP] == _PAGE_CACHE_MODE_WP; + uint16_t prot = __cachemode2pte_tbl[_PAGE_CACHE_MODE_WP]; + + return __pte2cachemode_tbl[__pte2cm_idx(prot)] == _PAGE_CACHE_MODE_WP; } enum page_cache_mode pgprot2cachemode(pgprot_t pgprot) diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index 11350e2fd736..9f27e14e185f 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -12,7 +12,6 @@ #include <linux/swiotlb.h> #include <linux/cc_platform.h> #include <linux/mem_encrypt.h> -#include <linux/virtio_config.h> /* Override for DMA direct allocation check - ARCH_HAS_FORCE_DMA_UNENCRYPTED */ bool force_dma_unencrypted(struct device *dev) @@ -87,9 +86,3 @@ void __init mem_encrypt_init(void) print_mem_encrypt_feature_info(); } - -int arch_has_restricted_virtio_memory_access(void) -{ - return cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT); -} -EXPORT_SYMBOL_GPL(arch_has_restricted_virtio_memory_access); diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c index e8f7953fda83..f6d038e2cd8e 100644 --- a/arch/x86/mm/mem_encrypt_amd.c +++ b/arch/x86/mm/mem_encrypt_amd.c @@ -21,6 +21,7 @@ #include <linux/dma-mapping.h> #include <linux/virtio_config.h> #include <linux/cc_platform.h> +#include <linux/platform-feature.h> #include <asm/tlbflush.h> #include <asm/fixmap.h> @@ -242,6 +243,9 @@ void __init sev_setup_arch(void) size = total_mem * 6 / 100; size = clamp_val(size, IO_TLB_DEFAULT_SIZE, SZ_1G); swiotlb_adjust_size(size); + + /* Set restricted memory access for virtio. */ + platform_set(PLATFORM_VIRTIO_RESTRICTED_MEM_ACCESS); } static unsigned long pg_level_to_pfn(int level, pte_t *kpte, pgprot_t *ret_prot) diff --git a/arch/x86/mm/mem_encrypt_boot.S b/arch/x86/mm/mem_encrypt_boot.S index 3d1dba05fce4..9de3d900bc92 100644 --- a/arch/x86/mm/mem_encrypt_boot.S +++ b/arch/x86/mm/mem_encrypt_boot.S @@ -65,7 +65,10 @@ SYM_FUNC_START(sme_encrypt_execute) movq %rbp, %rsp /* Restore original stack pointer */ pop %rbp - RET + /* Offset to __x86_return_thunk would be wrong here */ + ANNOTATE_UNRET_SAFE + ret + int3 SYM_FUNC_END(sme_encrypt_execute) SYM_FUNC_START(__enc_copy) @@ -151,6 +154,9 @@ SYM_FUNC_START(__enc_copy) pop %r12 pop %r15 - RET + /* Offset to __x86_return_thunk would be wrong here */ + ANNOTATE_UNRET_SAFE + ret + int3 .L__enc_copy_end: SYM_FUNC_END(__enc_copy) diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index f298b18a9a3d..b808c9a80d1b 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -412,16 +412,30 @@ static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip) { u8 *prog = *pprog; -#ifdef CONFIG_RETPOLINE if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) { EMIT_LFENCE(); EMIT2(0xFF, 0xE0 + reg); } else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE)) { OPTIMIZER_HIDE_VAR(reg); emit_jump(&prog, &__x86_indirect_thunk_array[reg], ip); - } else -#endif - EMIT2(0xFF, 0xE0 + reg); + } else { + EMIT2(0xFF, 0xE0 + reg); + } + + *pprog = prog; +} + +static void emit_return(u8 **pprog, u8 *ip) +{ + u8 *prog = *pprog; + + if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) { + emit_jump(&prog, &__x86_return_thunk, ip); + } else { + EMIT1(0xC3); /* ret */ + if (IS_ENABLED(CONFIG_SLS)) + EMIT1(0xCC); /* int3 */ + } *pprog = prog; } @@ -1420,8 +1434,9 @@ st: if (is_imm8(insn->off)) case BPF_JMP | BPF_CALL: func = (u8 *) __bpf_call_base + imm32; if (tail_call_reachable) { + /* mov rax, qword ptr [rbp - rounded_stack_depth - 8] */ EMIT3_off32(0x48, 0x8B, 0x85, - -(bpf_prog->aux->stack_depth + 8)); + -round_up(bpf_prog->aux->stack_depth, 8) - 8); if (!imm32 || emit_call(&prog, func, image + addrs[i - 1] + 7)) return -EINVAL; } else { @@ -1685,7 +1700,7 @@ emit_jmp: ctx->cleanup_addr = proglen; pop_callee_regs(&prog, callee_regs_used); EMIT1(0xC9); /* leave */ - EMIT1(0xC3); /* ret */ + emit_return(&prog, image + addrs[i - 1] + (prog - temp)); break; default: @@ -2188,7 +2203,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i if (flags & BPF_TRAMP_F_SKIP_FRAME) /* skip our return address and return to parent */ EMIT4(0x48, 0x83, 0xC4, 8); /* add rsp, 8 */ - EMIT1(0xC3); /* ret */ + emit_return(&prog, prog); /* Make sure the trampoline generation logic doesn't overflow */ if (WARN_ON_ONCE(prog > (u8 *)image_end - BPF_INSN_SAFETY)) { ret = -EFAULT; diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index a4f43054bc79..2f82480fd430 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -8,7 +8,6 @@ #include <linux/pci-acpi.h> #include <asm/numa.h> #include <asm/pci_x86.h> -#include <asm/e820/api.h> struct pci_root_info { struct acpi_pci_root_info common; @@ -20,7 +19,7 @@ struct pci_root_info { #endif }; -static bool pci_use_e820 = true; +bool pci_use_e820 = true; static bool pci_use_crs = true; static bool pci_ignore_seg; @@ -387,11 +386,6 @@ static int pci_acpi_root_prepare_resources(struct acpi_pci_root_info *ci) status = acpi_pci_probe_root_resources(ci); - if (pci_use_e820) { - resource_list_for_each_entry(entry, &ci->resources) - remove_e820_regions(&device->dev, entry->res); - } - if (pci_use_crs) { resource_list_for_each_entry_safe(entry, tmp, &ci->resources) if (resource_is_pcicfg_ioport(entry->res)) diff --git a/arch/x86/platform/efi/efi_thunk_64.S b/arch/x86/platform/efi/efi_thunk_64.S index 9ffe2bad27d5..4e5257a4811b 100644 --- a/arch/x86/platform/efi/efi_thunk_64.S +++ b/arch/x86/platform/efi/efi_thunk_64.S @@ -23,6 +23,7 @@ #include <linux/objtool.h> #include <asm/page_types.h> #include <asm/segment.h> +#include <asm/nospec-branch.h> .text .code64 @@ -75,7 +76,9 @@ STACK_FRAME_NON_STANDARD __efi64_thunk 1: movq 0x20(%rsp), %rsp pop %rbx pop %rbp - RET + ANNOTATE_UNRET_SAFE + ret + int3 .code32 2: pushl $__KERNEL_CS diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c index 517a9d8d8f94..8b71b1dd7639 100644 --- a/arch/x86/xen/enlighten_hvm.c +++ b/arch/x86/xen/enlighten_hvm.c @@ -195,6 +195,8 @@ static void __init xen_hvm_guest_init(void) if (xen_pv_domain()) return; + xen_set_restricted_virtio_memory_access(); + init_hvm_pv_info(); reserve_shared_info(); diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index f33a4421e7cd..70fb2ea85e90 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -109,6 +109,8 @@ static DEFINE_PER_CPU(struct tls_descs, shadow_tls_desc); static void __init xen_pv_init_platform(void) { + xen_set_restricted_virtio_memory_access(); + populate_extra_pte(fix_to_virt(FIX_PARAVIRT_BOOTMAP)); set_fixmap(FIX_PARAVIRT_BOOTMAP, xen_start_info->shared_info); @@ -1181,15 +1183,19 @@ static void __init xen_domu_set_legacy_features(void) extern void early_xen_iret_patch(void); /* First C function to be called on Xen boot */ -asmlinkage __visible void __init xen_start_kernel(void) +asmlinkage __visible void __init xen_start_kernel(struct start_info *si) { struct physdev_set_iopl set_iopl; unsigned long initrd_start = 0; int rc; - if (!xen_start_info) + if (!si) return; + clear_bss(); + + xen_start_info = si; + __text_gen_insn(&early_xen_iret_patch, JMP32_INSN_OPCODE, &early_xen_iret_patch, &xen_iret, JMP32_INSN_SIZE); diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 81aa46f770c5..cfa99e8f054b 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -918,7 +918,7 @@ void xen_enable_sysenter(void) if (!boot_cpu_has(sysenter_feature)) return; - ret = register_callback(CALLBACKTYPE_sysenter, xen_sysenter_target); + ret = register_callback(CALLBACKTYPE_sysenter, xen_entry_SYSENTER_compat); if(ret != 0) setup_clear_cpu_cap(sysenter_feature); } @@ -927,7 +927,7 @@ void xen_enable_syscall(void) { int ret; - ret = register_callback(CALLBACKTYPE_syscall, xen_syscall_target); + ret = register_callback(CALLBACKTYPE_syscall, xen_entry_SYSCALL_64); if (ret != 0) { printk(KERN_ERR "Failed to set syscall callback: %d\n", ret); /* Pretty fatal; 64-bit userspace has no other @@ -936,7 +936,7 @@ void xen_enable_syscall(void) if (boot_cpu_has(X86_FEATURE_SYSCALL32)) { ret = register_callback(CALLBACKTYPE_syscall32, - xen_syscall32_target); + xen_entry_SYSCALL_compat); if (ret != 0) setup_clear_cpu_cap(X86_FEATURE_SYSCALL32); } diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index caa9bc2fa100..6b4fdf6b9542 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -121,7 +121,7 @@ SYM_FUNC_END(xen_read_cr2_direct); .macro xen_pv_trap name SYM_CODE_START(xen_\name) - UNWIND_HINT_EMPTY + UNWIND_HINT_ENTRY ENDBR pop %rcx pop %r11 @@ -234,8 +234,8 @@ SYM_CODE_END(xenpv_restore_regs_and_return_to_usermode) */ /* Normal 64-bit system call target */ -SYM_CODE_START(xen_syscall_target) - UNWIND_HINT_EMPTY +SYM_CODE_START(xen_entry_SYSCALL_64) + UNWIND_HINT_ENTRY ENDBR popq %rcx popq %r11 @@ -249,13 +249,13 @@ SYM_CODE_START(xen_syscall_target) movq $__USER_CS, 1*8(%rsp) jmp entry_SYSCALL_64_after_hwframe -SYM_CODE_END(xen_syscall_target) +SYM_CODE_END(xen_entry_SYSCALL_64) #ifdef CONFIG_IA32_EMULATION /* 32-bit compat syscall target */ -SYM_CODE_START(xen_syscall32_target) - UNWIND_HINT_EMPTY +SYM_CODE_START(xen_entry_SYSCALL_compat) + UNWIND_HINT_ENTRY ENDBR popq %rcx popq %r11 @@ -269,11 +269,11 @@ SYM_CODE_START(xen_syscall32_target) movq $__USER32_CS, 1*8(%rsp) jmp entry_SYSCALL_compat_after_hwframe -SYM_CODE_END(xen_syscall32_target) +SYM_CODE_END(xen_entry_SYSCALL_compat) /* 32-bit compat sysenter target */ -SYM_CODE_START(xen_sysenter_target) - UNWIND_HINT_EMPTY +SYM_CODE_START(xen_entry_SYSENTER_compat) + UNWIND_HINT_ENTRY ENDBR /* * NB: Xen is polite and clears TF from EFLAGS for us. This means @@ -291,19 +291,19 @@ SYM_CODE_START(xen_sysenter_target) movq $__USER32_CS, 1*8(%rsp) jmp entry_SYSENTER_compat_after_hwframe -SYM_CODE_END(xen_sysenter_target) +SYM_CODE_END(xen_entry_SYSENTER_compat) #else /* !CONFIG_IA32_EMULATION */ -SYM_CODE_START(xen_syscall32_target) -SYM_CODE_START(xen_sysenter_target) - UNWIND_HINT_EMPTY +SYM_CODE_START(xen_entry_SYSCALL_compat) +SYM_CODE_START(xen_entry_SYSENTER_compat) + UNWIND_HINT_ENTRY ENDBR lea 16(%rsp), %rsp /* strip %rcx, %r11 */ mov $-ENOSYS, %rax pushq $0 jmp hypercall_iret -SYM_CODE_END(xen_sysenter_target) -SYM_CODE_END(xen_syscall32_target) +SYM_CODE_END(xen_entry_SYSENTER_compat) +SYM_CODE_END(xen_entry_SYSCALL_compat) #endif /* CONFIG_IA32_EMULATION */ diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index 3a2cd93bf059..ffaa62167f6e 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -26,6 +26,7 @@ SYM_CODE_START(hypercall_page) .rept (PAGE_SIZE / 32) UNWIND_HINT_FUNC ANNOTATE_NOENDBR + ANNOTATE_UNRET_SAFE ret /* * Xen will write the hypercall page, and sort out ENDBR. @@ -48,15 +49,6 @@ SYM_CODE_START(startup_xen) ANNOTATE_NOENDBR cld - /* Clear .bss */ - xor %eax,%eax - mov $__bss_start, %rdi - mov $__bss_stop, %rcx - sub %rdi, %rcx - shr $3, %rcx - rep stosq - - mov %rsi, xen_start_info mov initial_stack(%rip), %rsp /* Set up %gs. @@ -71,6 +63,7 @@ SYM_CODE_START(startup_xen) cdq wrmsr + mov %rsi, %rdi call xen_start_kernel SYM_CODE_END(startup_xen) __FINIT diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index fd0fec6e92f4..9a8bb972193d 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -10,10 +10,10 @@ /* These are code, but not functions. Defined in entry.S */ extern const char xen_failsafe_callback[]; -void xen_sysenter_target(void); +void xen_entry_SYSENTER_compat(void); #ifdef CONFIG_X86_64 -void xen_syscall_target(void); -void xen_syscall32_target(void); +void xen_entry_SYSCALL_64(void); +void xen_entry_SYSCALL_compat(void); #endif extern void *xen_initial_gdt; |