diff options
98 files changed, 2039 insertions, 508 deletions
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 2522b11e593f..f2d26cb7e853 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -5197,6 +5197,30 @@ retain_initrd [RAM] Keep initrd memory after extraction + retbleed= [X86] Control mitigation of RETBleed (Arbitrary + Speculative Code Execution with Return Instructions) + vulnerability. + + off - no mitigation + auto - automatically select a migitation + auto,nosmt - automatically select a mitigation, + disabling SMT if necessary for + the full mitigation (only on Zen1 + and older without STIBP). + ibpb - mitigate short speculation windows on + basic block boundaries too. Safe, highest + perf impact. + unret - force enable untrained return thunks, + only effective on AMD f15h-f17h + based systems. + unret,nosmt - like unret, will disable SMT when STIBP + is not available. + + Selecting 'auto' will choose a mitigation method at run + time according to the CPU. + + Not specifying this option is equivalent to retbleed=auto. + rfkill.default_state= 0 "airplane mode". All wifi, bluetooth, wimax, gps, fm, etc. communication is blocked by default. @@ -5568,6 +5592,7 @@ eibrs - enhanced IBRS eibrs,retpoline - enhanced IBRS + Retpolines eibrs,lfence - enhanced IBRS + LFENCE + ibrs - use IBRS to protect kernel Not specifying this option is equivalent to spectre_v2=auto. diff --git a/Documentation/core-api/kernel-api.rst b/Documentation/core-api/kernel-api.rst index d6b3f94b9f1f..0793c400d4b0 100644 --- a/Documentation/core-api/kernel-api.rst +++ b/Documentation/core-api/kernel-api.rst @@ -223,7 +223,7 @@ Module Loading Inter Module support -------------------- -Refer to the file kernel/module.c for more information. +Refer to the files in kernel/module/ for more information. Hardware Interfaces =================== diff --git a/Documentation/core-api/symbol-namespaces.rst b/Documentation/core-api/symbol-namespaces.rst index 5ad9e0abe42c..12e4aecdae94 100644 --- a/Documentation/core-api/symbol-namespaces.rst +++ b/Documentation/core-api/symbol-namespaces.rst @@ -51,8 +51,8 @@ namespace ``USB_STORAGE``, use:: The corresponding ksymtab entry struct ``kernel_symbol`` will have the member ``namespace`` set accordingly. A symbol that is exported without a namespace will refer to ``NULL``. There is no default namespace if none is defined. ``modpost`` -and kernel/module.c make use the namespace at build time or module load time, -respectively. +and kernel/module/main.c make use the namespace at build time or module load +time, respectively. 2.2 Using the DEFAULT_SYMBOL_NAMESPACE define ============================================= diff --git a/Documentation/livepatch/module-elf-format.rst b/Documentation/livepatch/module-elf-format.rst index dbe9b400e39f..7347638895a0 100644 --- a/Documentation/livepatch/module-elf-format.rst +++ b/Documentation/livepatch/module-elf-format.rst @@ -210,11 +210,11 @@ module->symtab. ===================================== Normally, a stripped down copy of a module's symbol table (containing only "core" symbols) is made available through module->symtab (See layout_symtab() -in kernel/module.c). For livepatch modules, the symbol table copied into memory -on module load must be exactly the same as the symbol table produced when the -patch module was compiled. This is because the relocations in each livepatch -relocation section refer to their respective symbols with their symbol indices, -and the original symbol indices (and thus the symtab ordering) must be +in kernel/module/kallsyms.c). For livepatch modules, the symbol table copied +into memory on module load must be exactly the same as the symbol table produced +when the patch module was compiled. This is because the relocations in each +livepatch relocation section refer to their respective symbols with their symbol +indices, and the original symbol indices (and thus the symtab ordering) must be preserved in order for apply_relocate_add() to find the right symbol. For example, take this particular rela from a livepatch module::: diff --git a/Documentation/translations/it_IT/core-api/symbol-namespaces.rst b/Documentation/translations/it_IT/core-api/symbol-namespaces.rst index 42f5d04e38ec..0f6898860d6d 100644 --- a/Documentation/translations/it_IT/core-api/symbol-namespaces.rst +++ b/Documentation/translations/it_IT/core-api/symbol-namespaces.rst @@ -50,9 +50,9 @@ Di conseguenza, nella tabella dei simboli del kernel ci sarà una voce rappresentata dalla struttura ``kernel_symbol`` che avrà il campo ``namespace`` (spazio dei nomi) impostato. Un simbolo esportato senza uno spazio dei nomi avrà questo campo impostato a ``NULL``. Non esiste uno spazio dei nomi -di base. Il programma ``modpost`` e il codice in kernel/module.c usano lo spazio -dei nomi, rispettivamente, durante la compilazione e durante il caricamento -di un modulo. +di base. Il programma ``modpost`` e il codice in kernel/module/main.c usano lo +spazio dei nomi, rispettivamente, durante la compilazione e durante il +caricamento di un modulo. 2.2 Usare il simbolo di preprocessore DEFAULT_SYMBOL_NAMESPACE ============================================================== diff --git a/Documentation/translations/zh_CN/core-api/kernel-api.rst b/Documentation/translations/zh_CN/core-api/kernel-api.rst index e45fe80d1cd8..962d31d019d7 100644 --- a/Documentation/translations/zh_CN/core-api/kernel-api.rst +++ b/Documentation/translations/zh_CN/core-api/kernel-api.rst @@ -224,7 +224,7 @@ kernel/kmod.c 模块接口支持 ------------ -更多信息请参考文件kernel/module.c。 +更多信息请参阅kernel/module/目录下的文件。 硬件接口 ======== diff --git a/Documentation/translations/zh_CN/core-api/symbol-namespaces.rst b/Documentation/translations/zh_CN/core-api/symbol-namespaces.rst index 6abf7ed534ca..bb16f0611046 100644 --- a/Documentation/translations/zh_CN/core-api/symbol-namespaces.rst +++ b/Documentation/translations/zh_CN/core-api/symbol-namespaces.rst @@ -52,7 +52,7 @@ 相应的 ksymtab 条目结构体 ``kernel_symbol`` 将有相应的成员 ``命名空间`` 集。 导出时未指明命名空间的符号将指向 ``NULL`` 。如果没有定义命名空间，则默认没有。 -``modpost`` 和kernel/module.c分别在构建时或模块加载时使用名称空间。 +``modpost`` 和kernel/module/main.c分别在构建时或模块加载时使用名称空间。 2.2 使用DEFAULT_SYMBOL_NAMESPACE定义 ==================================== diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 32ffef9f6e5b..fcbb81feb7ad 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -38,7 +38,7 @@ config RISCV select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_SUPPORTS_DEBUG_PAGEALLOC if MMU select ARCH_SUPPORTS_HUGETLBFS if MMU - select ARCH_SUPPORTS_PAGE_TABLE_CHECK + select ARCH_SUPPORTS_PAGE_TABLE_CHECK if MMU select ARCH_USE_MEMTEST select ARCH_USE_QUEUED_RWLOCKS select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU diff --git a/arch/sh/include/asm/io.h b/arch/sh/include/asm/io.h index cf9a3ec32406..fba90e670ed4 100644 --- a/arch/sh/include/asm/io.h +++ b/arch/sh/include/asm/io.h @@ -271,8 +271,12 @@ static inline void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size, #endif /* CONFIG_HAVE_IOREMAP_PROT */ #else /* CONFIG_MMU */ -#define iounmap(addr) do { } while (0) -#define ioremap(offset, size) ((void __iomem *)(unsigned long)(offset)) +static inline void __iomem *ioremap(phys_addr_t offset, size_t size) +{ + return (void __iomem *)(unsigned long)offset; +} + +static inline void iounmap(volatile void __iomem *addr) { } #endif /* CONFIG_MMU */ #define ioremap_uc ioremap diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index be0b95e51df6..e58798f636d4 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -462,29 +462,6 @@ 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) @@ -2453,6 +2430,91 @@ 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 + 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 + 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 + 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 + 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..1f40dad30d50 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -21,6 +21,12 @@ 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 RETPOLINE_CFLAGS export RETPOLINE_VDSO_CFLAGS 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..285e043a3e40 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) @@ -725,6 +727,7 @@ native_irq_return_ldt: pushq %rdi /* Stash user RDI */ swapgs /* to kernel GS */ SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi /* to kernel CR3 */ + UNTRAIN_RET movq PER_CPU_VAR(espfix_waddr), %rdi movq %rax, (0*8)(%rdi) /* user RAX */ @@ -897,6 +900,9 @@ 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 +946,7 @@ 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 +965,16 @@ 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 +996,19 @@ 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 +1041,10 @@ 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 +1056,12 @@ 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 +1096,7 @@ 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 +1112,8 @@ 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 +1219,9 @@ 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 +1446,9 @@ 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/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 03acc823838a..00f5227c8459 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 +296,12 @@ #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 */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ @@ -316,6 +322,7 @@ #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 */ @@ -447,5 +454,6 @@ #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/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/msr-index.h b/arch/x86/include/asm/msr-index.h index d27e0581b777..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 @@ -140,6 +143,13 @@ * 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) /* @@ -567,6 +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 da251a5645b0..bb05ed4f46bd 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -76,6 +76,23 @@ .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 +122,34 @@ * 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 +161,20 @@ _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 +237,7 @@ 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 +280,9 @@ static inline void indirect_branch_prediction_barrier(void) /* The Intel SPEC CTRL MSR base value cache */ extern u64 x86_spec_ctrl_base; +extern 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 +292,16 @@ 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); \ } 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) 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/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/kernel/alternative.c b/arch/x86/kernel/alternative.c index e257f6c80372..d6858533e6e5 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 +508,76 @@ 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_ON_ONCE(dest != &__x86_return_thunk)) + 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 +928,7 @@ 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 74c62cc47a5f..0dd04713434b 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -38,6 +38,8 @@ 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); @@ -48,16 +50,40 @@ 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. @@ -114,13 +140,21 @@ 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(); md_clear_select_mitigation(); @@ -161,31 +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); @@ -752,12 +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, +}; + +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 = @@ -828,6 +1016,7 @@ 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 { @@ -868,13 +1057,15 @@ 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: @@ -900,15 +1091,16 @@ 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); @@ -921,7 +1113,7 @@ 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; @@ -969,12 +1161,12 @@ 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; /* @@ -986,6 +1178,13 @@ 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: @@ -999,6 +1198,7 @@ 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 { @@ -1016,6 +1216,7 @@ 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) @@ -1078,6 +1279,30 @@ 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; @@ -1093,6 +1318,22 @@ 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(); @@ -1117,6 +1358,15 @@ 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; @@ -1133,6 +1383,10 @@ 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; @@ -1149,10 +1403,9 @@ 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) { @@ -1160,6 +1413,10 @@ 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); + break; + case SPECTRE_V2_LFENCE: case SPECTRE_V2_EIBRS_LFENCE: setup_force_cpu_cap(X86_FEATURE_RETPOLINE_LFENCE); @@ -1171,43 +1428,107 @@ 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. * - * - RSB underflow (and switch to BTB) on Skylake+ - * - SpectreRSB variant of spectre v2 on X86_BUG_SPECTRE_V2 CPUs + * 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. + * + * 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(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. */ @@ -1424,16 +1745,6 @@ 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 @@ -1450,7 +1761,7 @@ 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); } } @@ -1701,7 +2012,7 @@ 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(); @@ -1938,7 +2249,7 @@ static ssize_t mmio_stale_data_show_state(char *buf) 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) { @@ -1994,6 +2305,24 @@ 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) { @@ -2039,6 +2368,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_MMIO_STALE_DATA: return mmio_stale_data_show_state(buf); + case X86_BUG_RETBLEED: + return retbleed_show_state(buf); + default: break; } @@ -2095,4 +2427,9 @@ ssize_t cpu_show_mmio_stale_data(struct device *dev, struct device_attribute *at { 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 4730b0a58f24..736262a76a12 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1205,48 +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, BIT(2) | BIT(4), MMIO), - VULNBL_INTEL_STEPPINGS(BROADWELL_D, X86_STEPPINGS(0x3, 0x5), MMIO), + 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_STEPPINGS(0x3, 0x3), SRBDS | MMIO), - VULNBL_INTEL_STEPPINGS(SKYLAKE_L, X86_STEPPING_ANY, SRBDS), - VULNBL_INTEL_STEPPINGS(SKYLAKE_X, BIT(3) | BIT(4) | BIT(6) | - BIT(7) | BIT(0xB), MMIO), - VULNBL_INTEL_STEPPINGS(SKYLAKE, X86_STEPPINGS(0x3, 0x3), SRBDS | MMIO), - VULNBL_INTEL_STEPPINGS(SKYLAKE, X86_STEPPING_ANY, SRBDS), - VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPINGS(0x9, 0xC), SRBDS | MMIO), - VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPINGS(0x0, 0x8), SRBDS), - VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPINGS(0x9, 0xD), SRBDS | MMIO), - VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPINGS(0x0, 0x8), SRBDS), - VULNBL_INTEL_STEPPINGS(ICELAKE_L, X86_STEPPINGS(0x5, 0x5), MMIO | MMIO_SBDS), - VULNBL_INTEL_STEPPINGS(ICELAKE_D, X86_STEPPINGS(0x1, 0x1), MMIO), - VULNBL_INTEL_STEPPINGS(ICELAKE_X, X86_STEPPINGS(0x4, 0x6), MMIO), - VULNBL_INTEL_STEPPINGS(COMETLAKE, BIT(2) | BIT(3) | BIT(5), MMIO | MMIO_SBDS), - VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPINGS(0x1, 0x1), MMIO | MMIO_SBDS), - VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPINGS(0x0, 0x0), MMIO), - VULNBL_INTEL_STEPPINGS(LAKEFIELD, X86_STEPPINGS(0x1, 0x1), MMIO | MMIO_SBDS), - VULNBL_INTEL_STEPPINGS(ROCKETLAKE, X86_STEPPINGS(0x1, 0x1), MMIO), - VULNBL_INTEL_STEPPINGS(ATOM_TREMONT, X86_STEPPINGS(0x1, 0x1), MMIO | MMIO_SBDS), + 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_STEPPINGS(0x0, 0x0), MMIO | MMIO_SBDS), + 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), {} }; @@ -1348,6 +1360,11 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) !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/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/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 9487ce8c13ee..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 diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 89b11e7dca8a..db96bf7d1122 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -325,13 +325,15 @@ 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") @@ -435,16 +437,15 @@ 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) +#define RET_LENGTH (1 + (4 * IS_ENABLED(CONFIG_RETHUNK)) + \ + IS_ENABLED(CONFIG_SLS)) +#define SETCC_LENGTH (ENDBR_INSN_SIZE + 3 + RET_LENGTH) +#define SETCC_ALIGN (4 << ((SETCC_LENGTH > 4) & 1) << ((SETCC_LENGTH > 8) & 1)) static_assert(SETCC_LENGTH <= SETCC_ALIGN); #define FOP_SETCC(op) \ @@ -453,9 +454,10 @@ 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/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..3a4e895269d7 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -3087,7 +3087,7 @@ 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 3a919e49129b..be7c19374fdd 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -383,9 +383,9 @@ static __always_inline void vmx_disable_fb_clear(struct vcpu_vmx *vmx) if (!vmx->disable_fb_clear) return; - rdmsrl(MSR_IA32_MCU_OPT_CTRL, msr); + msr = __rdmsr(MSR_IA32_MCU_OPT_CTRL); msr |= FB_CLEAR_DIS; - wrmsrl(MSR_IA32_MCU_OPT_CTRL, msr); + native_wrmsrl(MSR_IA32_MCU_OPT_CTRL, msr); /* Cache the MSR value to avoid reading it later */ vmx->msr_ia32_mcu_opt_ctrl = msr; } @@ -396,7 +396,7 @@ static __always_inline void vmx_enable_fb_clear(struct vcpu_vmx *vmx) return; vmx->msr_ia32_mcu_opt_ctrl &= ~FB_CLEAR_DIS; - wrmsrl(MSR_IA32_MCU_OPT_CTRL, vmx->msr_ia32_mcu_opt_ctrl); + 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) @@ -839,6 +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) { @@ -6813,6 +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) { @@ -6826,7 +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(); @@ -6845,7 +6889,7 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, 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(); @@ -6944,36 +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)) { diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 8d2342ede0c5..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 @@ -404,7 +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 1910e1e78b15..26d0cac32f73 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -12631,9 +12631,9 @@ 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/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/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 c98b8c0ed3b8..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; } @@ -1686,7 +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: @@ -2189,7 +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/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 13af6fe453e3..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. 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; diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index a97776ea9d99..4c98849577d4 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -570,6 +570,12 @@ ssize_t __weak cpu_show_mmio_stale_data(struct device *dev, return sysfs_emit(buf, "Not affected\n"); } +ssize_t __weak cpu_show_retbleed(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "Not affected\n"); +} + static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL); static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL); static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL); @@ -580,6 +586,7 @@ static DEVICE_ATTR(tsx_async_abort, 0444, cpu_show_tsx_async_abort, NULL); static DEVICE_ATTR(itlb_multihit, 0444, cpu_show_itlb_multihit, NULL); static DEVICE_ATTR(srbds, 0444, cpu_show_srbds, NULL); static DEVICE_ATTR(mmio_stale_data, 0444, cpu_show_mmio_stale_data, NULL); +static DEVICE_ATTR(retbleed, 0444, cpu_show_retbleed, NULL); static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_meltdown.attr, @@ -592,6 +599,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_itlb_multihit.attr, &dev_attr_srbds.attr, &dev_attr_mmio_stale_data.attr, + &dev_attr_retbleed.attr, NULL }; diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 424ef470223d..f5c6802aa6c3 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -47,11 +47,13 @@ #include <linux/tick.h> #include <trace/events/power.h> #include <linux/sched.h> +#include <linux/sched/smt.h> #include <linux/notifier.h> #include <linux/cpu.h> #include <linux/moduleparam.h> #include <asm/cpu_device_id.h> #include <asm/intel-family.h> +#include <asm/nospec-branch.h> #include <asm/mwait.h> #include <asm/msr.h> @@ -106,6 +108,12 @@ static unsigned int mwait_substates __initdata; #define CPUIDLE_FLAG_ALWAYS_ENABLE BIT(15) /* + * Disable IBRS across idle (when KERNEL_IBRS), is exclusive vs IRQ_ENABLE + * above. + */ +#define CPUIDLE_FLAG_IBRS BIT(16) + +/* * MWAIT takes an 8-bit "hint" in EAX "suggesting" * the C-state (top nibble) and sub-state (bottom nibble) * 0x00 means "MWAIT(C1)", 0x10 means "MWAIT(C2)" etc. @@ -159,6 +167,24 @@ static __cpuidle int intel_idle_irq(struct cpuidle_device *dev, return ret; } +static __cpuidle int intel_idle_ibrs(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) +{ + bool smt_active = sched_smt_active(); + u64 spec_ctrl = spec_ctrl_current(); + int ret; + + if (smt_active) + wrmsrl(MSR_IA32_SPEC_CTRL, 0); + + ret = __intel_idle(dev, drv, index); + + if (smt_active) + wrmsrl(MSR_IA32_SPEC_CTRL, spec_ctrl); + + return ret; +} + /** * intel_idle_s2idle - Ask the processor to enter the given idle state. * @dev: cpuidle device of the target CPU. @@ -680,7 +706,7 @@ static struct cpuidle_state skl_cstates[] __initdata = { { .name = "C6", .desc = "MWAIT 0x20", - .flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED, + .flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED | CPUIDLE_FLAG_IBRS, .exit_latency = 85, .target_residency = 200, .enter = &intel_idle, @@ -688,7 +714,7 @@ static struct cpuidle_state skl_cstates[] __initdata = { { .name = "C7s", .desc = "MWAIT 0x33", - .flags = MWAIT2flg(0x33) | CPUIDLE_FLAG_TLB_FLUSHED, + .flags = MWAIT2flg(0x33) | CPUIDLE_FLAG_TLB_FLUSHED | CPUIDLE_FLAG_IBRS, .exit_latency = 124, .target_residency = 800, .enter = &intel_idle, @@ -696,7 +722,7 @@ static struct cpuidle_state skl_cstates[] __initdata = { { .name = "C8", .desc = "MWAIT 0x40", - .flags = MWAIT2flg(0x40) | CPUIDLE_FLAG_TLB_FLUSHED, + .flags = MWAIT2flg(0x40) | CPUIDLE_FLAG_TLB_FLUSHED | CPUIDLE_FLAG_IBRS, .exit_latency = 200, .target_residency = 800, .enter = &intel_idle, @@ -704,7 +730,7 @@ static struct cpuidle_state skl_cstates[] __initdata = { { .name = "C9", .desc = "MWAIT 0x50", - .flags = MWAIT2flg(0x50) | CPUIDLE_FLAG_TLB_FLUSHED, + .flags = MWAIT2flg(0x50) | CPUIDLE_FLAG_TLB_FLUSHED | CPUIDLE_FLAG_IBRS, .exit_latency = 480, .target_residency = 5000, .enter = &intel_idle, @@ -712,7 +738,7 @@ static struct cpuidle_state skl_cstates[] __initdata = { { .name = "C10", .desc = "MWAIT 0x60", - .flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED, + .flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED | CPUIDLE_FLAG_IBRS, .exit_latency = 890, .target_residency = 5000, .enter = &intel_idle, @@ -741,7 +767,7 @@ static struct cpuidle_state skx_cstates[] __initdata = { { .name = "C6", .desc = "MWAIT 0x20", - .flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED, + .flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED | CPUIDLE_FLAG_IBRS, .exit_latency = 133, .target_residency = 600, .enter = &intel_idle, @@ -1819,6 +1845,12 @@ static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv) if (cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_IRQ_ENABLE) drv->states[drv->state_count].enter = intel_idle_irq; + if (cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS) && + cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_IBRS) { + WARN_ON_ONCE(cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_IRQ_ENABLE); + drv->states[drv->state_count].enter = intel_idle_ibrs; + } + if ((disabled_states_mask & BIT(drv->state_count)) || ((icpu->use_acpi || force_use_acpi) && intel_idle_off_by_default(mwait_hint) && diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 61e71c1154be..e60b06f2ac22 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -549,6 +549,16 @@ static struct vfio_group *vfio_group_find_or_alloc(struct device *dev) if (!iommu_group) return ERR_PTR(-EINVAL); + /* + * VFIO always sets IOMMU_CACHE because we offer no way for userspace to + * restore cache coherency. It has to be checked here because it is only + * valid for cases where we are using iommu groups. + */ + if (!iommu_capable(dev->bus, IOMMU_CAP_CACHE_COHERENCY)) { + iommu_group_put(iommu_group); + return ERR_PTR(-EINVAL); + } + group = vfio_group_get_from_iommu(iommu_group); if (!group) group = vfio_create_group(iommu_group, VFIO_IOMMU); @@ -601,13 +611,6 @@ static int __vfio_register_dev(struct vfio_device *device, int vfio_register_group_dev(struct vfio_device *device) { - /* - * VFIO always sets IOMMU_CACHE because we offer no way for userspace to - * restore cache coherency. - */ - if (!iommu_capable(device->dev->bus, IOMMU_CAP_CACHE_COHERENCY)) - return -EINVAL; - return __vfio_register_dev(device, vfio_group_find_or_alloc(device->dev)); } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 05e0c4a5affd..0172f75e051a 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7681,7 +7681,19 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start, if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags) || em->block_start == EXTENT_MAP_INLINE) { free_extent_map(em); - ret = -ENOTBLK; + /* + * If we are in a NOWAIT context, return -EAGAIN in order to + * fallback to buffered IO. This is not only because we can + * block with buffered IO (no support for NOWAIT semantics at + * the moment) but also to avoid returning short reads to user + * space - this happens if we were able to read some data from + * previous non-compressed extents and then when we fallback to + * buffered IO, at btrfs_file_read_iter() by calling + * filemap_read(), we fail to fault in pages for the read buffer, + * in which case filemap_read() returns a short read (the number + * of bytes previously read is > 0, so it does not return -EFAULT). + */ + ret = (flags & IOMAP_NOWAIT) ? -EAGAIN : -ENOTBLK; goto unlock_err; } diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 79e8c8cd75ed..d99026df6f67 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1735,12 +1735,14 @@ static int read_zone_info(struct btrfs_fs_info *fs_info, u64 logical, ret = btrfs_map_sblock(fs_info, BTRFS_MAP_GET_READ_MIRRORS, logical, &mapped_length, &bioc); if (ret || !bioc || mapped_length < PAGE_SIZE) { - btrfs_put_bioc(bioc); - return -EIO; + ret = -EIO; + goto out_put_bioc; } - if (bioc->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK) - return -EINVAL; + if (bioc->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK) { + ret = -EINVAL; + goto out_put_bioc; + } nofs_flag = memalloc_nofs_save(); nmirrors = (int)bioc->num_stripes; @@ -1759,7 +1761,8 @@ static int read_zone_info(struct btrfs_fs_info *fs_info, u64 logical, break; } memalloc_nofs_restore(nofs_flag); - +out_put_bioc: + btrfs_put_bioc(bioc); return ret; } @@ -1885,7 +1888,6 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ { struct btrfs_fs_info *fs_info = block_group->fs_info; struct map_lookup *map; - bool need_zone_finish; int ret = 0; int i; @@ -1942,12 +1944,6 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ } } - /* - * The block group is not fully allocated, so not fully written yet. We - * need to send ZONE_FINISH command to free up an active zone. - */ - need_zone_finish = !btrfs_zoned_bg_is_full(block_group); - block_group->zone_is_active = 0; block_group->alloc_offset = block_group->zone_capacity; block_group->free_space_ctl->free_space = 0; @@ -1963,15 +1959,13 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ if (device->zone_info->max_active_zones == 0) continue; - if (need_zone_finish) { - ret = blkdev_zone_mgmt(device->bdev, REQ_OP_ZONE_FINISH, - physical >> SECTOR_SHIFT, - device->zone_info->zone_size >> SECTOR_SHIFT, - GFP_NOFS); + ret = blkdev_zone_mgmt(device->bdev, REQ_OP_ZONE_FINISH, + physical >> SECTOR_SHIFT, + device->zone_info->zone_size >> SECTOR_SHIFT, + GFP_NOFS); - if (ret) - return ret; - } + if (ret) + return ret; btrfs_dev_clear_active_zone(device, physical); } diff --git a/fs/exec.c b/fs/exec.c index 0989fb8472a1..778123259e42 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1301,7 +1301,7 @@ int begin_new_exec(struct linux_binprm * bprm) bprm->mm = NULL; #ifdef CONFIG_POSIX_TIMERS - exit_itimers(me->signal); + exit_itimers(me); flush_itimer_signals(); #endif diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index 1344f7d475d3..aecda4fc95f5 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -198,6 +198,9 @@ static inline int nilfs_acl_chmod(struct inode *inode) static inline int nilfs_init_acl(struct inode *inode, struct inode *dir) { + if (S_ISLNK(inode->i_mode)) + return 0; + inode->i_mode &= ~current_umask(); return 0; } diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 2c7477354744..314802f98b9d 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -68,6 +68,8 @@ extern ssize_t cpu_show_srbds(struct device *dev, struct device_attribute *attr, extern ssize_t cpu_show_mmio_stale_data(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_retbleed(struct device *dev, + struct device_attribute *attr, char *buf); extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 3af34de54330..56d6a0196534 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -149,19 +149,19 @@ static inline void *kmap_local_folio(struct folio *folio, size_t offset); * It is used in atomic context when code wants to access the contents of a * page that might be allocated from high memory (see __GFP_HIGHMEM), for * example a page in the pagecache. The API has two functions, and they - * can be used in a manner similar to the following: + * can be used in a manner similar to the following:: * - * -- Find the page of interest. -- - * struct page *page = find_get_page(mapping, offset); + * // Find the page of interest. + * struct page *page = find_get_page(mapping, offset); * - * -- Gain access to the contents of that page. -- - * void *vaddr = kmap_atomic(page); + * // Gain access to the contents of that page. + * void *vaddr = kmap_atomic(page); * - * -- Do something to the contents of that page. -- - * memset(vaddr, 0, PAGE_SIZE); + * // Do something to the contents of that page. + * memset(vaddr, 0, PAGE_SIZE); * - * -- Unmap that page. -- - * kunmap_atomic(vaddr); + * // Unmap that page. + * kunmap_atomic(vaddr); * * Note that the kunmap_atomic() call takes the result of the kmap_atomic() * call, not the argument. diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index c20f2d55840c..83cf7fd842e0 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1513,7 +1513,7 @@ static inline void kvm_arch_end_assignment(struct kvm *kvm) { } -static inline bool kvm_arch_has_assigned_device(struct kvm *kvm) +static __always_inline bool kvm_arch_has_assigned_device(struct kvm *kvm) { return false; } diff --git a/include/linux/objtool.h b/include/linux/objtool.h index 15b940ec1eac..10bc88cc3bf6 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -32,11 +32,16 @@ struct unwind_hint { * * UNWIND_HINT_FUNC: Generate the unwind metadata of a callable function. * Useful for code which doesn't have an ELF function annotation. + * + * UNWIND_HINT_ENTRY: machine entry without stack, SYSCALL/SYSENTER etc. */ #define UNWIND_HINT_TYPE_CALL 0 #define UNWIND_HINT_TYPE_REGS 1 #define UNWIND_HINT_TYPE_REGS_PARTIAL 2 #define UNWIND_HINT_TYPE_FUNC 3 +#define UNWIND_HINT_TYPE_ENTRY 4 +#define UNWIND_HINT_TYPE_SAVE 5 +#define UNWIND_HINT_TYPE_RESTORE 6 #ifdef CONFIG_OBJTOOL @@ -124,7 +129,7 @@ struct unwind_hint { * the debuginfo as necessary. It will also warn if it sees any * inconsistencies. */ -.macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0 +.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 end=0 .Lunwind_hint_ip_\@: .pushsection .discard.unwind_hints /* struct unwind_hint */ @@ -177,7 +182,7 @@ struct unwind_hint { #define ASM_REACHABLE #else #define ANNOTATE_INTRA_FUNCTION_CALL -.macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0 +.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 end=0 .endm .macro STACK_FRAME_NON_STANDARD func:req .endm diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 505aaf9fe477..81cab4b01edc 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -85,7 +85,7 @@ static inline void exit_thread(struct task_struct *tsk) extern __noreturn void do_group_exit(int); extern void exit_files(struct task_struct *); -extern void exit_itimers(struct signal_struct *); +extern void exit_itimers(struct task_struct *); extern pid_t kernel_clone(struct kernel_clone_args *kargs); struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node); diff --git a/ipc/namespace.c b/ipc/namespace.c index 754f3237194a..e1fcaedba4fa 100644 --- a/ipc/namespace.c +++ b/ipc/namespace.c @@ -64,7 +64,7 @@ static struct ipc_namespace *create_ipc_ns(struct user_namespace *user_ns, goto fail_put; if (!setup_ipc_sysctls(ns)) - goto fail_put; + goto fail_mq; sem_init_ns(ns); msg_init_ns(ns); @@ -72,6 +72,9 @@ static struct ipc_namespace *create_ipc_ns(struct user_namespace *user_ns, return ns; +fail_mq: + retire_mq_sysctls(ns); + fail_put: put_user_ns(ns->user_ns); ns_free_inum(&ns->ns); diff --git a/kernel/exit.c b/kernel/exit.c index f072959fcab7..64c938ce36fe 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -766,7 +766,7 @@ void __noreturn do_exit(long code) #ifdef CONFIG_POSIX_TIMERS hrtimer_cancel(&tsk->signal->real_timer); - exit_itimers(tsk->signal); + exit_itimers(tsk); #endif if (tsk->mm) setmax_mm_hiwater_rss(&tsk->signal->maxrss, tsk->mm); diff --git a/kernel/module/internal.h b/kernel/module/internal.h index bc5507ab8450..ec104c2950c3 100644 --- a/kernel/module/internal.h +++ b/kernel/module/internal.h @@ -11,6 +11,7 @@ #include <linux/mutex.h> #include <linux/rculist.h> #include <linux/rcupdate.h> +#include <linux/mm.h> #ifndef ARCH_SHF_SMALL #define ARCH_SHF_SMALL 0 @@ -30,11 +31,13 @@ * to ensure complete separation of code and data, but * only when CONFIG_STRICT_MODULE_RWX=y */ -#ifdef CONFIG_STRICT_MODULE_RWX -# define strict_align(X) PAGE_ALIGN(X) -#else -# define strict_align(X) (X) -#endif +static inline unsigned int strict_align(unsigned int size) +{ + if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX)) + return PAGE_ALIGN(size); + else + return size; +} extern struct mutex module_mutex; extern struct list_head modules; diff --git a/kernel/module/kallsyms.c b/kernel/module/kallsyms.c index 3e11523bc6f6..77e75bead569 100644 --- a/kernel/module/kallsyms.c +++ b/kernel/module/kallsyms.c @@ -137,6 +137,7 @@ void layout_symtab(struct module *mod, struct load_info *info) info->symoffs = ALIGN(mod->data_layout.size, symsect->sh_addralign ?: 1); info->stroffs = mod->data_layout.size = info->symoffs + ndst * sizeof(Elf_Sym); mod->data_layout.size += strtab_size; + /* Note add_kallsyms() computes strtab_size as core_typeoffs - stroffs */ info->core_typeoffs = mod->data_layout.size; mod->data_layout.size += ndst * sizeof(char); mod->data_layout.size = strict_align(mod->data_layout.size); @@ -169,19 +170,20 @@ void add_kallsyms(struct module *mod, const struct load_info *info) Elf_Sym *dst; char *s; Elf_Shdr *symsec = &info->sechdrs[info->index.sym]; + unsigned long strtab_size; /* Set up to point into init section. */ mod->kallsyms = (void __rcu *)mod->init_layout.base + info->mod_kallsyms_init_off; - preempt_disable(); + rcu_read_lock(); /* The following is safe since this pointer cannot change */ - rcu_dereference_sched(mod->kallsyms)->symtab = (void *)symsec->sh_addr; - rcu_dereference_sched(mod->kallsyms)->num_symtab = symsec->sh_size / sizeof(Elf_Sym); + rcu_dereference(mod->kallsyms)->symtab = (void *)symsec->sh_addr; + rcu_dereference(mod->kallsyms)->num_symtab = symsec->sh_size / sizeof(Elf_Sym); /* Make sure we get permanent strtab: don't use info->strtab. */ - rcu_dereference_sched(mod->kallsyms)->strtab = + rcu_dereference(mod->kallsyms)->strtab = (void *)info->sechdrs[info->index.str].sh_addr; - rcu_dereference_sched(mod->kallsyms)->typetab = mod->init_layout.base + info->init_typeoffs; + rcu_dereference(mod->kallsyms)->typetab = mod->init_layout.base + info->init_typeoffs; /* * Now populate the cut down core kallsyms for after init @@ -190,22 +192,29 @@ void add_kallsyms(struct module *mod, const struct load_info *info) mod->core_kallsyms.symtab = dst = mod->data_layout.base + info->symoffs; mod->core_kallsyms.strtab = s = mod->data_layout.base + info->stroffs; mod->core_kallsyms.typetab = mod->data_layout.base + info->core_typeoffs; - src = rcu_dereference_sched(mod->kallsyms)->symtab; - for (ndst = i = 0; i < rcu_dereference_sched(mod->kallsyms)->num_symtab; i++) { - rcu_dereference_sched(mod->kallsyms)->typetab[i] = elf_type(src + i, info); + strtab_size = info->core_typeoffs - info->stroffs; + src = rcu_dereference(mod->kallsyms)->symtab; + for (ndst = i = 0; i < rcu_dereference(mod->kallsyms)->num_symtab; i++) { + rcu_dereference(mod->kallsyms)->typetab[i] = elf_type(src + i, info); if (i == 0 || is_livepatch_module(mod) || is_core_symbol(src + i, info->sechdrs, info->hdr->e_shnum, info->index.pcpu)) { + ssize_t ret; + mod->core_kallsyms.typetab[ndst] = - rcu_dereference_sched(mod->kallsyms)->typetab[i]; + rcu_dereference(mod->kallsyms)->typetab[i]; dst[ndst] = src[i]; dst[ndst++].st_name = s - mod->core_kallsyms.strtab; - s += strscpy(s, - &rcu_dereference_sched(mod->kallsyms)->strtab[src[i].st_name], - KSYM_NAME_LEN) + 1; + ret = strscpy(s, + &rcu_dereference(mod->kallsyms)->strtab[src[i].st_name], + strtab_size); + if (ret < 0) + break; + s += ret + 1; + strtab_size -= ret + 1; } } - preempt_enable(); + rcu_read_unlock(); mod->core_kallsyms.num_symtab = ndst; } diff --git a/kernel/module/main.c b/kernel/module/main.c index fed58d30725d..0548151dd933 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -2939,24 +2939,25 @@ static void cfi_init(struct module *mod) { #ifdef CONFIG_CFI_CLANG initcall_t *init; +#ifdef CONFIG_MODULE_UNLOAD exitcall_t *exit; +#endif rcu_read_lock_sched(); mod->cfi_check = (cfi_check_fn) find_kallsyms_symbol_value(mod, "__cfi_check"); init = (initcall_t *) find_kallsyms_symbol_value(mod, "__cfi_jt_init_module"); - exit = (exitcall_t *) - find_kallsyms_symbol_value(mod, "__cfi_jt_cleanup_module"); - rcu_read_unlock_sched(); - /* Fix init/exit functions to point to the CFI jump table */ if (init) mod->init = *init; #ifdef CONFIG_MODULE_UNLOAD + exit = (exitcall_t *) + find_kallsyms_symbol_value(mod, "__cfi_jt_cleanup_module"); if (exit) mod->exit = *exit; #endif + rcu_read_unlock_sched(); cfi_module_add(mod, mod_tree.addr_min); #endif diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 1cd10b102c51..5dead89308b7 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -1051,15 +1051,24 @@ retry_delete: } /* - * This is called by do_exit or de_thread, only when there are no more - * references to the shared signal_struct. + * This is called by do_exit or de_thread, only when nobody else can + * modify the signal->posix_timers list. Yet we need sighand->siglock + * to prevent the race with /proc/pid/timers. */ -void exit_itimers(struct signal_struct *sig) +void exit_itimers(struct task_struct *tsk) { + struct list_head timers; struct k_itimer *tmr; - while (!list_empty(&sig->posix_timers)) { - tmr = list_entry(sig->posix_timers.next, struct k_itimer, list); + if (list_empty(&tsk->signal->posix_timers)) + return; + + spin_lock_irq(&tsk->sighand->siglock); + list_replace_init(&tsk->signal->posix_timers, &timers); + spin_unlock_irq(&tsk->sighand->siglock); + + while (!list_empty(&timers)) { + tmr = list_first_entry(&timers, struct k_itimer, list); itimer_delete(tmr); } } diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index 59e1653799f8..3c7b9d6dca95 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -336,8 +336,7 @@ static void damon_hugetlb_mkold(pte_t *pte, struct mm_struct *mm, if (pte_young(entry)) { referenced = true; entry = pte_mkold(entry); - huge_ptep_set_access_flags(vma, addr, pte, entry, - vma->vm_flags & VM_WRITE); + set_huge_pte_at(mm, addr, pte, entry); } #ifdef CONFIG_MMU_NOTIFIER diff --git a/mm/memory.c b/mm/memory.c index 7a089145cad4..4cf7d4b6c950 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4802,6 +4802,19 @@ static vm_fault_t create_huge_pud(struct vm_fault *vmf) defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) /* No support for anonymous transparent PUD pages yet */ if (vma_is_anonymous(vmf->vma)) + return VM_FAULT_FALLBACK; + if (vmf->vma->vm_ops->huge_fault) + return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD); +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + return VM_FAULT_FALLBACK; +} + +static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud) +{ +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ + defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) + /* No support for anonymous transparent PUD pages yet */ + if (vma_is_anonymous(vmf->vma)) goto split; if (vmf->vma->vm_ops->huge_fault) { vm_fault_t ret = vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD); @@ -4812,19 +4825,7 @@ static vm_fault_t create_huge_pud(struct vm_fault *vmf) split: /* COW or write-notify not handled on PUD level: split pud.*/ __split_huge_pud(vmf->vma, vmf->pud, vmf->address); -#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ - return VM_FAULT_FALLBACK; -} - -static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud) -{ -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - /* No support for anonymous transparent PUD pages yet */ - if (vma_is_anonymous(vmf->vma)) - return VM_FAULT_FALLBACK; - if (vmf->vma->vm_ops->huge_fault) - return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD); -#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +#endif /* CONFIG_TRANSPARENT_HUGEPAGE && CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ return VM_FAULT_FALLBACK; } diff --git a/mm/rmap.c b/mm/rmap.c index 5bcb334cd6f2..746c05acad27 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1899,8 +1899,23 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, /* Unexpected PMD-mapped THP? */ VM_BUG_ON_FOLIO(!pvmw.pte, folio); - subpage = folio_page(folio, - pte_pfn(*pvmw.pte) - folio_pfn(folio)); + if (folio_is_zone_device(folio)) { + /* + * Our PTE is a non-present device exclusive entry and + * calculating the subpage as for the common case would + * result in an invalid pointer. + * + * Since only PAGE_SIZE pages can currently be + * migrated, just set it to page. This will need to be + * changed when hugepage migrations to device private + * memory are supported. + */ + VM_BUG_ON_FOLIO(folio_nr_pages(folio) > 1, folio); + subpage = &folio->page; + } else { + subpage = folio_page(folio, + pte_pfn(*pvmw.pte) - folio_pfn(folio)); + } address = pvmw.address; anon_exclusive = folio_test_anon(folio) && PageAnonExclusive(subpage); @@ -1993,15 +2008,7 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, /* * No need to invalidate here it will synchronize on * against the special swap migration pte. - * - * The assignment to subpage above was computed from a - * swap PTE which results in an invalid pointer. - * Since only PAGE_SIZE pages can currently be - * migrated, just set it to page. This will need to be - * changed when hugepage migrations to device private - * memory are supported. */ - subpage = &folio->page; } else if (PageHWPoison(subpage)) { pteval = swp_entry_to_pte(make_hwpoison_entry(subpage)); if (folio_test_hugetlb(folio)) { diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index f4fa61dbbee3..dbbd1a7e65f3 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -78,6 +78,14 @@ static int __split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start) spin_lock(&init_mm.page_table_lock); if (likely(pmd_leaf(*pmd))) { + /* + * Higher order allocations from buddy allocator must be able to + * be treated as indepdenent small pages (as they can be freed + * individually). + */ + if (!PageReserved(page)) + split_page(page, get_order(PMD_SIZE)); + /* Make pte visible before pmd. See comment in pmd_install(). */ smp_wmb(); pmd_populate_kernel(&init_mm, pmd, pgtable); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 4f4892a5f767..07d3befc80e4 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -246,7 +246,10 @@ static int mcontinue_atomic_pte(struct mm_struct *dst_mm, struct page *page; int ret; - ret = shmem_getpage(inode, pgoff, &page, SGP_READ); + ret = shmem_getpage(inode, pgoff, &page, SGP_NOALLOC); + /* Our caller expects us to return -EFAULT if we failed to find page. */ + if (ret == -ENOENT) + ret = -EFAULT; if (ret) goto out; if (!page) { diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index d1425778664b..3fb6a99e78c4 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -236,6 +236,7 @@ objtool_args = \ $(if $(CONFIG_FTRACE_MCOUNT_USE_OBJTOOL), --mcount) \ $(if $(CONFIG_UNWINDER_ORC), --orc) \ $(if $(CONFIG_RETPOLINE), --retpoline) \ + $(if $(CONFIG_RETHUNK), --rethunk) \ $(if $(CONFIG_SLS), --sls) \ $(if $(CONFIG_STACK_VALIDATION), --stackval) \ $(if $(CONFIG_HAVE_STATIC_CALL_INLINE), --static-call) \ diff --git a/scripts/Makefile.vmlinux_o b/scripts/Makefile.vmlinux_o index 3c97a1564947..84019814f33f 100644 --- a/scripts/Makefile.vmlinux_o +++ b/scripts/Makefile.vmlinux_o @@ -44,7 +44,7 @@ objtool-enabled := $(or $(delay-objtool),$(CONFIG_NOINSTR_VALIDATION)) objtool_args := \ $(if $(delay-objtool),$(objtool_args)) \ - $(if $(CONFIG_NOINSTR_VALIDATION), --noinstr) \ + $(if $(CONFIG_NOINSTR_VALIDATION), --noinstr $(if $(CONFIG_CPU_UNRET_ENTRY), --unret)) \ $(if $(CONFIG_GCOV_KERNEL), --no-unreachable) \ --link diff --git a/security/Kconfig b/security/Kconfig index f29e4c656983..e6db09a779b7 100644 --- a/security/Kconfig +++ b/security/Kconfig @@ -54,17 +54,6 @@ config SECURITY_NETWORK implement socket and networking access controls. If you are unsure how to answer this question, answer N. -config PAGE_TABLE_ISOLATION - bool "Remove the kernel mapping in user mode" - default y - depends on (X86_64 || X86_PAE) && !UML - 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 SECURITY_INFINIBAND bool "Infiniband Security Hooks" depends on SECURITY && INFINIBAND diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index d27e0581b777..2eab6a3a8a8c 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/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 */ @@ -140,6 +142,13 @@ * 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) /* diff --git a/tools/include/linux/objtool.h b/tools/include/linux/objtool.h index 15b940ec1eac..10bc88cc3bf6 100644 --- a/tools/include/linux/objtool.h +++ b/tools/include/linux/objtool.h @@ -32,11 +32,16 @@ struct unwind_hint { * * UNWIND_HINT_FUNC: Generate the unwind metadata of a callable function. * Useful for code which doesn't have an ELF function annotation. + * + * UNWIND_HINT_ENTRY: machine entry without stack, SYSCALL/SYSENTER etc. */ #define UNWIND_HINT_TYPE_CALL 0 #define UNWIND_HINT_TYPE_REGS 1 #define UNWIND_HINT_TYPE_REGS_PARTIAL 2 #define UNWIND_HINT_TYPE_FUNC 3 +#define UNWIND_HINT_TYPE_ENTRY 4 +#define UNWIND_HINT_TYPE_SAVE 5 +#define UNWIND_HINT_TYPE_RESTORE 6 #ifdef CONFIG_OBJTOOL @@ -124,7 +129,7 @@ struct unwind_hint { * the debuginfo as necessary. It will also warn if it sees any * inconsistencies. */ -.macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0 +.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 end=0 .Lunwind_hint_ip_\@: .pushsection .discard.unwind_hints /* struct unwind_hint */ @@ -177,7 +182,7 @@ struct unwind_hint { #define ASM_REACHABLE #else #define ANNOTATE_INTRA_FUNCTION_CALL -.macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0 +.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 end=0 .endm .macro STACK_FRAME_NON_STANDARD func:req .endm diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 8b990a52aada..c260006106be 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -787,3 +787,8 @@ bool arch_is_retpoline(struct symbol *sym) { return !strncmp(sym->name, "__x86_indirect_", 15); } + +bool arch_is_rethunk(struct symbol *sym) +{ + return !strcmp(sym->name, "__x86_return_thunk"); +} diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c index f4c3a5091737..24fbe803a0d3 100644 --- a/tools/objtool/builtin-check.c +++ b/tools/objtool/builtin-check.c @@ -68,6 +68,8 @@ const struct option check_options[] = { OPT_BOOLEAN('n', "noinstr", &opts.noinstr, "validate noinstr rules"), OPT_BOOLEAN('o', "orc", &opts.orc, "generate ORC metadata"), OPT_BOOLEAN('r', "retpoline", &opts.retpoline, "validate and annotate retpoline usage"), + OPT_BOOLEAN(0, "rethunk", &opts.rethunk, "validate and annotate rethunk usage"), + OPT_BOOLEAN(0, "unret", &opts.unret, "validate entry unret placement"), OPT_BOOLEAN('l', "sls", &opts.sls, "validate straight-line-speculation mitigations"), OPT_BOOLEAN('s', "stackval", &opts.stackval, "validate frame pointer rules"), OPT_BOOLEAN('t', "static-call", &opts.static_call, "annotate static calls"), @@ -123,6 +125,7 @@ static bool opts_valid(void) opts.noinstr || opts.orc || opts.retpoline || + opts.rethunk || opts.sls || opts.stackval || opts.static_call || @@ -135,6 +138,11 @@ static bool opts_valid(void) return true; } + if (opts.unret && !opts.rethunk) { + ERROR("--unret requires --rethunk"); + return false; + } + if (opts.dump_orc) return true; @@ -163,6 +171,11 @@ static bool link_opts_valid(struct objtool_file *file) return false; } + if (opts.unret) { + ERROR("--unret requires --link"); + return false; + } + return true; } diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 57153e00349c..b341f8a8c7c5 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -376,7 +376,8 @@ static int decode_instructions(struct objtool_file *file) sec->text = true; if (!strcmp(sec->name, ".noinstr.text") || - !strcmp(sec->name, ".entry.text")) + !strcmp(sec->name, ".entry.text") || + !strncmp(sec->name, ".text.__x86.", 12)) sec->noinstr = true; for (offset = 0; offset < sec->sh.sh_size; offset += insn->len) { @@ -749,6 +750,52 @@ static int create_retpoline_sites_sections(struct objtool_file *file) return 0; } +static int create_return_sites_sections(struct objtool_file *file) +{ + struct instruction *insn; + struct section *sec; + int idx; + + sec = find_section_by_name(file->elf, ".return_sites"); + if (sec) { + WARN("file already has .return_sites, skipping"); + return 0; + } + + idx = 0; + list_for_each_entry(insn, &file->return_thunk_list, call_node) + idx++; + + if (!idx) + return 0; + + sec = elf_create_section(file->elf, ".return_sites", 0, + sizeof(int), idx); + if (!sec) { + WARN("elf_create_section: .return_sites"); + return -1; + } + + idx = 0; + list_for_each_entry(insn, &file->return_thunk_list, call_node) { + + int *site = (int *)sec->data->d_buf + idx; + *site = 0; + + if (elf_add_reloc_to_insn(file->elf, sec, + idx * sizeof(int), + R_X86_64_PC32, + insn->sec, insn->offset)) { + WARN("elf_add_reloc_to_insn: .return_sites"); + return -1; + } + + idx++; + } + + return 0; +} + static int create_ibt_endbr_seal_sections(struct objtool_file *file) { struct instruction *insn; @@ -1083,6 +1130,11 @@ __weak bool arch_is_retpoline(struct symbol *sym) return false; } +__weak bool arch_is_rethunk(struct symbol *sym) +{ + return false; +} + #define NEGATIVE_RELOC ((void *)-1L) static struct reloc *insn_reloc(struct objtool_file *file, struct instruction *insn) @@ -1250,6 +1302,19 @@ static void add_retpoline_call(struct objtool_file *file, struct instruction *in annotate_call_site(file, insn, false); } +static void add_return_call(struct objtool_file *file, struct instruction *insn, bool add) +{ + /* + * Return thunk tail calls are really just returns in disguise, + * so convert them accordingly. + */ + insn->type = INSN_RETURN; + insn->retpoline_safe = true; + + if (add) + list_add_tail(&insn->call_node, &file->return_thunk_list); +} + static bool same_function(struct instruction *insn1, struct instruction *insn2) { return insn1->func->pfunc == insn2->func->pfunc; @@ -1302,6 +1367,9 @@ static int add_jump_destinations(struct objtool_file *file) } else if (reloc->sym->retpoline_thunk) { add_retpoline_call(file, insn); continue; + } else if (reloc->sym->return_thunk) { + add_return_call(file, insn, true); + continue; } else if (insn->func) { /* * External sibling call or internal sibling call with @@ -1320,6 +1388,21 @@ static int add_jump_destinations(struct objtool_file *file) jump_dest = find_insn(file, dest_sec, dest_off); if (!jump_dest) { + struct symbol *sym = find_symbol_by_offset(dest_sec, dest_off); + + /* + * This is a special case for zen_untrain_ret(). + * It jumps to __x86_return_thunk(), but objtool + * can't find the thunk's starting RET + * instruction, because the RET is also in the + * middle of another instruction. Objtool only + * knows about the outer instruction. + */ + if (sym && sym->return_thunk) { + add_return_call(file, insn, false); + continue; + } + WARN_FUNC("can't find jump dest instruction at %s+0x%lx", insn->sec, insn->offset, dest_sec->name, dest_off); @@ -1949,16 +2032,35 @@ static int read_unwind_hints(struct objtool_file *file) insn->hint = true; - if (opts.ibt && hint->type == UNWIND_HINT_TYPE_REGS_PARTIAL) { + if (hint->type == UNWIND_HINT_TYPE_SAVE) { + insn->hint = false; + insn->save = true; + continue; + } + + if (hint->type == UNWIND_HINT_TYPE_RESTORE) { + insn->restore = true; + continue; + } + + if (hint->type == UNWIND_HINT_TYPE_REGS_PARTIAL) { struct symbol *sym = find_symbol_by_offset(insn->sec, insn->offset); - if (sym && sym->bind == STB_GLOBAL && - insn->type != INSN_ENDBR && !insn->noendbr) { - WARN_FUNC("UNWIND_HINT_IRET_REGS without ENDBR", - insn->sec, insn->offset); + if (sym && sym->bind == STB_GLOBAL) { + if (opts.ibt && insn->type != INSN_ENDBR && !insn->noendbr) { + WARN_FUNC("UNWIND_HINT_IRET_REGS without ENDBR", + insn->sec, insn->offset); + } + + insn->entry = 1; } } + if (hint->type == UNWIND_HINT_TYPE_ENTRY) { + hint->type = UNWIND_HINT_TYPE_CALL; + insn->entry = 1; + } + if (hint->type == UNWIND_HINT_TYPE_FUNC) { insn->cfi = &func_cfi; continue; @@ -2032,8 +2134,10 @@ static int read_retpoline_hints(struct objtool_file *file) } if (insn->type != INSN_JUMP_DYNAMIC && - insn->type != INSN_CALL_DYNAMIC) { - WARN_FUNC("retpoline_safe hint not an indirect jump/call", + insn->type != INSN_CALL_DYNAMIC && + insn->type != INSN_RETURN && + insn->type != INSN_NOP) { + WARN_FUNC("retpoline_safe hint not an indirect jump/call/ret/nop", insn->sec, insn->offset); return -1; } @@ -2184,6 +2288,9 @@ static int classify_symbols(struct objtool_file *file) if (arch_is_retpoline(func)) func->retpoline_thunk = true; + if (arch_is_rethunk(func)) + func->return_thunk = true; + if (!strcmp(func->name, "__fentry__")) func->fentry = true; @@ -3218,8 +3325,8 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, return 1; } - visited = 1 << state.uaccess; - if (insn->visited) { + visited = VISITED_BRANCH << state.uaccess; + if (insn->visited & VISITED_BRANCH_MASK) { if (!insn->hint && !insn_cfi_match(insn, &state.cfi)) return 1; @@ -3233,6 +3340,35 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, state.instr += insn->instr; if (insn->hint) { + if (insn->restore) { + struct instruction *save_insn, *i; + + i = insn; + save_insn = NULL; + + sym_for_each_insn_continue_reverse(file, func, i) { + if (i->save) { + save_insn = i; + break; + } + } + + if (!save_insn) { + WARN_FUNC("no corresponding CFI save for CFI restore", + sec, insn->offset); + return 1; + } + + if (!save_insn->visited) { + WARN_FUNC("objtool isn't smart enough to handle this CFI save/restore combo", + sec, insn->offset); + return 1; + } + + insn->cfi = save_insn->cfi; + nr_cfi_reused++; + } + state.cfi = *insn->cfi; } else { /* XXX track if we actually changed state.cfi */ @@ -3433,6 +3569,145 @@ static int validate_unwind_hints(struct objtool_file *file, struct section *sec) return warnings; } +/* + * Validate rethunk entry constraint: must untrain RET before the first RET. + * + * Follow every branch (intra-function) and ensure ANNOTATE_UNRET_END comes + * before an actual RET instruction. + */ +static int validate_entry(struct objtool_file *file, struct instruction *insn) +{ + struct instruction *next, *dest; + int ret, warnings = 0; + + for (;;) { + next = next_insn_to_validate(file, insn); + + if (insn->visited & VISITED_ENTRY) + return 0; + + insn->visited |= VISITED_ENTRY; + + if (!insn->ignore_alts && !list_empty(&insn->alts)) { + struct alternative *alt; + bool skip_orig = false; + + list_for_each_entry(alt, &insn->alts, list) { + if (alt->skip_orig) + skip_orig = true; + + ret = validate_entry(file, alt->insn); + if (ret) { + if (opts.backtrace) + BT_FUNC("(alt)", insn); + return ret; + } + } + + if (skip_orig) + return 0; + } + + switch (insn->type) { + + case INSN_CALL_DYNAMIC: + case INSN_JUMP_DYNAMIC: + case INSN_JUMP_DYNAMIC_CONDITIONAL: + WARN_FUNC("early indirect call", insn->sec, insn->offset); + return 1; + + case INSN_JUMP_UNCONDITIONAL: + case INSN_JUMP_CONDITIONAL: + if (!is_sibling_call(insn)) { + if (!insn->jump_dest) { + WARN_FUNC("unresolved jump target after linking?!?", + insn->sec, insn->offset); + return -1; + } + ret = validate_entry(file, insn->jump_dest); + if (ret) { + if (opts.backtrace) { + BT_FUNC("(branch%s)", insn, + insn->type == INSN_JUMP_CONDITIONAL ? "-cond" : ""); + } + return ret; + } + + if (insn->type == INSN_JUMP_UNCONDITIONAL) + return 0; + + break; + } + + /* fallthrough */ + case INSN_CALL: + dest = find_insn(file, insn->call_dest->sec, + insn->call_dest->offset); + if (!dest) { + WARN("Unresolved function after linking!?: %s", + insn->call_dest->name); + return -1; + } + + ret = validate_entry(file, dest); + if (ret) { + if (opts.backtrace) + BT_FUNC("(call)", insn); + return ret; + } + /* + * If a call returns without error, it must have seen UNTRAIN_RET. + * Therefore any non-error return is a success. + */ + return 0; + + case INSN_RETURN: + WARN_FUNC("RET before UNTRAIN", insn->sec, insn->offset); + return 1; + + case INSN_NOP: + if (insn->retpoline_safe) + return 0; + break; + + default: + break; + } + + if (!next) { + WARN_FUNC("teh end!", insn->sec, insn->offset); + return -1; + } + insn = next; + } + + return warnings; +} + +/* + * Validate that all branches starting at 'insn->entry' encounter UNRET_END + * before RET. + */ +static int validate_unret(struct objtool_file *file) +{ + struct instruction *insn; + int ret, warnings = 0; + + for_each_insn(file, insn) { + if (!insn->entry) + continue; + + ret = validate_entry(file, insn); + if (ret < 0) { + WARN_FUNC("Failed UNRET validation", insn->sec, insn->offset); + return ret; + } + warnings += ret; + } + + return warnings; +} + static int validate_retpoline(struct objtool_file *file) { struct instruction *insn; @@ -3440,7 +3715,8 @@ static int validate_retpoline(struct objtool_file *file) for_each_insn(file, insn) { if (insn->type != INSN_JUMP_DYNAMIC && - insn->type != INSN_CALL_DYNAMIC) + insn->type != INSN_CALL_DYNAMIC && + insn->type != INSN_RETURN) continue; if (insn->retpoline_safe) @@ -3455,9 +3731,17 @@ static int validate_retpoline(struct objtool_file *file) if (!strcmp(insn->sec->name, ".init.text") && !opts.module) continue; - WARN_FUNC("indirect %s found in RETPOLINE build", - insn->sec, insn->offset, - insn->type == INSN_JUMP_DYNAMIC ? "jump" : "call"); + if (insn->type == INSN_RETURN) { + if (opts.rethunk) { + WARN_FUNC("'naked' return found in RETHUNK build", + insn->sec, insn->offset); + } else + continue; + } else { + WARN_FUNC("indirect %s found in RETPOLINE build", + insn->sec, insn->offset, + insn->type == INSN_JUMP_DYNAMIC ? "jump" : "call"); + } warnings++; } @@ -3945,6 +4229,17 @@ int check(struct objtool_file *file) warnings += ret; } + if (opts.unret) { + /* + * Must be after validate_branch() and friends, it plays + * further games with insn->visited. + */ + ret = validate_unret(file); + if (ret < 0) + return ret; + warnings += ret; + } + if (opts.ibt) { ret = validate_ibt(file); if (ret < 0) @@ -3973,6 +4268,13 @@ int check(struct objtool_file *file) warnings += ret; } + if (opts.rethunk) { + ret = create_return_sites_sections(file); + if (ret < 0) + goto out; + warnings += ret; + } + if (opts.mcount) { ret = create_mcount_loc_sections(file); if (ret < 0) diff --git a/tools/objtool/include/objtool/arch.h b/tools/objtool/include/objtool/arch.h index 9b19cc304195..beb2f3aa94ff 100644 --- a/tools/objtool/include/objtool/arch.h +++ b/tools/objtool/include/objtool/arch.h @@ -89,6 +89,7 @@ const char *arch_ret_insn(int len); int arch_decode_hint_reg(u8 sp_reg, int *base); bool arch_is_retpoline(struct symbol *sym); +bool arch_is_rethunk(struct symbol *sym); int arch_rewrite_retpolines(struct objtool_file *file); diff --git a/tools/objtool/include/objtool/builtin.h b/tools/objtool/include/objtool/builtin.h index 280ea18b7f2b..42a52f1a0add 100644 --- a/tools/objtool/include/objtool/builtin.h +++ b/tools/objtool/include/objtool/builtin.h @@ -19,6 +19,8 @@ struct opts { bool noinstr; bool orc; bool retpoline; + bool rethunk; + bool unret; bool sls; bool stackval; bool static_call; diff --git a/tools/objtool/include/objtool/check.h b/tools/objtool/include/objtool/check.h index f10d7374f388..036129cebeee 100644 --- a/tools/objtool/include/objtool/check.h +++ b/tools/objtool/include/objtool/check.h @@ -46,16 +46,19 @@ struct instruction { enum insn_type type; unsigned long immediate; - u8 dead_end : 1, - ignore : 1, - ignore_alts : 1, - hint : 1, - retpoline_safe : 1, - noendbr : 1; - /* 2 bit hole */ + u16 dead_end : 1, + ignore : 1, + ignore_alts : 1, + hint : 1, + save : 1, + restore : 1, + retpoline_safe : 1, + noendbr : 1, + entry : 1; + /* 7 bit hole */ + s8 instr; u8 visited; - /* u8 hole */ struct alt_group *alt_group; struct symbol *call_dest; @@ -69,6 +72,11 @@ struct instruction { struct cfi_state *cfi; }; +#define VISITED_BRANCH 0x01 +#define VISITED_BRANCH_UACCESS 0x02 +#define VISITED_BRANCH_MASK 0x03 +#define VISITED_ENTRY 0x04 + static inline bool is_static_jump(struct instruction *insn) { return insn->type == INSN_JUMP_CONDITIONAL || diff --git a/tools/objtool/include/objtool/elf.h b/tools/objtool/include/objtool/elf.h index adebfbc2b518..16f4067b82ae 100644 --- a/tools/objtool/include/objtool/elf.h +++ b/tools/objtool/include/objtool/elf.h @@ -57,6 +57,7 @@ struct symbol { u8 uaccess_safe : 1; u8 static_call_tramp : 1; u8 retpoline_thunk : 1; + u8 return_thunk : 1; u8 fentry : 1; u8 profiling_func : 1; struct list_head pv_target; diff --git a/tools/objtool/include/objtool/objtool.h b/tools/objtool/include/objtool/objtool.h index a6e72d916807..7f2d1b095333 100644 --- a/tools/objtool/include/objtool/objtool.h +++ b/tools/objtool/include/objtool/objtool.h @@ -24,6 +24,7 @@ struct objtool_file { struct list_head insn_list; DECLARE_HASHTABLE(insn_hash, 20); struct list_head retpoline_call_list; + struct list_head return_thunk_list; struct list_head static_call_list; struct list_head mcount_loc_list; struct list_head endbr_list; diff --git a/tools/objtool/objtool.c b/tools/objtool/objtool.c index 512669ce064c..a7ecc32e3512 100644 --- a/tools/objtool/objtool.c +++ b/tools/objtool/objtool.c @@ -102,6 +102,7 @@ struct objtool_file *objtool_open_read(const char *_objname) INIT_LIST_HEAD(&file.insn_list); hash_init(file.insn_hash); INIT_LIST_HEAD(&file.retpoline_call_list); + INIT_LIST_HEAD(&file.return_thunk_list); INIT_LIST_HEAD(&file.static_call_list); INIT_LIST_HEAD(&file.mcount_loc_list); INIT_LIST_HEAD(&file.endbr_list); |