From c482feefe1aeb150156248ba0fd3e029bc886605 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Mon, 4 Dec 2017 15:07:29 +0100 Subject: x86/entry/64: Make cpu_entry_area.tss read-only The TSS is a fairly juicy target for exploits, and, now that the TSS is in the cpu_entry_area, it's no longer protected by kASLR. Make it read-only on x86_64. On x86_32, it can't be RO because it's written by the CPU during task switches, and we use a task gate for double faults. I'd also be nervous about errata if we tried to make it RO even on configurations without double fault handling. [ tglx: AMD confirmed that there is no problem on 64-bit with TSS RO. So it's probably safe to assume that it's a non issue, though Intel might have been creative in that area. Still waiting for confirmation. ] Signed-off-by: Andy Lutomirski Signed-off-by: Thomas Gleixner Reviewed-by: Borislav Petkov Cc: Boris Ostrovsky Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Hansen Cc: Dave Hansen Cc: David Laight Cc: Denys Vlasenko Cc: Eduardo Valentin Cc: Greg KH Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Juergen Gross Cc: Kees Cook Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Rik van Riel Cc: Will Deacon Cc: aliguori@amazon.com Cc: daniel.gruss@iaik.tugraz.at Cc: hughd@google.com Cc: keescook@google.com Link: https://lkml.kernel.org/r/20171204150606.733700132@linutronix.de Signed-off-by: Ingo Molnar --- arch/x86/lib/delay.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86/lib') diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c index 553f8fd23cc4..4846eff7e4c8 100644 --- a/arch/x86/lib/delay.c +++ b/arch/x86/lib/delay.c @@ -107,10 +107,10 @@ static void delay_mwaitx(unsigned long __loops) delay = min_t(u64, MWAITX_MAX_LOOPS, loops); /* - * Use cpu_tss as a cacheline-aligned, seldomly + * Use cpu_tss_rw as a cacheline-aligned, seldomly * accessed per-cpu variable as the monitor target. */ - __monitorx(raw_cpu_ptr(&cpu_tss), 0, 0); + __monitorx(raw_cpu_ptr(&cpu_tss_rw), 0, 0); /* * AMD, like Intel, supports the EAX hint and EAX=0xf -- cgit v1.2.3 From 76b043848fd22dbf7f8bf3a1452f8c70d557b860 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Thu, 11 Jan 2018 21:46:25 +0000 Subject: x86/retpoline: Add initial retpoline support Enable the use of -mindirect-branch=thunk-extern in newer GCC, and provide the corresponding thunks. Provide assembler macros for invoking the thunks in the same way that GCC does, from native and inline assembler. This adds X86_FEATURE_RETPOLINE and sets it by default on all CPUs. In some circumstances, IBRS microcode features may be used instead, and the retpoline can be disabled. On AMD CPUs if lfence is serialising, the retpoline can be dramatically simplified to a simple "lfence; jmp *\reg". A future patch, after it has been verified that lfence really is serialising in all circumstances, can enable this by setting the X86_FEATURE_RETPOLINE_AMD feature bit in addition to X86_FEATURE_RETPOLINE. Do not align the retpoline in the altinstr section, because there is no guarantee that it stays aligned when it's copied over the oldinstr during alternative patching. [ Andi Kleen: Rename the macros, add CONFIG_RETPOLINE option, export thunks] [ tglx: Put actual function CALL/JMP in front of the macros, convert to symbolic labels ] [ dwmw2: Convert back to numeric labels, merge objtool fixes ] Signed-off-by: David Woodhouse Signed-off-by: Thomas Gleixner Acked-by: Arjan van de Ven Acked-by: Ingo Molnar Cc: gnomes@lxorguk.ukuu.org.uk Cc: Rik van Riel Cc: Andi Kleen Cc: Josh Poimboeuf Cc: thomas.lendacky@amd.com Cc: Peter Zijlstra Cc: Linus Torvalds Cc: Jiri Kosina Cc: Andy Lutomirski Cc: Dave Hansen Cc: Kees Cook Cc: Tim Chen Cc: Greg Kroah-Hartman Cc: Paul Turner Link: https://lkml.kernel.org/r/1515707194-20531-4-git-send-email-dwmw@amazon.co.uk --- arch/x86/Kconfig | 13 ++++ arch/x86/Makefile | 10 +++ arch/x86/include/asm/asm-prototypes.h | 25 +++++++ arch/x86/include/asm/cpufeatures.h | 2 + arch/x86/include/asm/nospec-branch.h | 128 ++++++++++++++++++++++++++++++++++ arch/x86/kernel/cpu/common.c | 4 ++ arch/x86/lib/Makefile | 1 + arch/x86/lib/retpoline.S | 48 +++++++++++++ 8 files changed, 231 insertions(+) create mode 100644 arch/x86/include/asm/nospec-branch.h create mode 100644 arch/x86/lib/retpoline.S (limited to 'arch/x86/lib') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index e23d21ac745a..d1819161cc6c 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -429,6 +429,19 @@ config GOLDFISH def_bool y depends on X86_GOLDFISH +config RETPOLINE + bool "Avoid speculative indirect branches in kernel" + 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. + + Without compiler support, at least indirect branches in assembler + code are eliminated. Since this includes the syscall entry path, + it is not entirely pointless. + config INTEL_RDT bool "Intel Resource Director Technology support" default n diff --git a/arch/x86/Makefile b/arch/x86/Makefile index a20eacd9c7e9..974c61864978 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -235,6 +235,16 @@ KBUILD_CFLAGS += -Wno-sign-compare # KBUILD_CFLAGS += -fno-asynchronous-unwind-tables +# Avoid indirect branches in kernel to deal with Spectre +ifdef CONFIG_RETPOLINE + RETPOLINE_CFLAGS += $(call cc-option,-mindirect-branch=thunk-extern -mindirect-branch-register) + ifneq ($(RETPOLINE_CFLAGS),) + KBUILD_CFLAGS += $(RETPOLINE_CFLAGS) -DRETPOLINE + else + $(warning CONFIG_RETPOLINE=y, but not supported by the compiler. Toolchain update recommended.) + endif +endif + archscripts: scripts_basic $(Q)$(MAKE) $(build)=arch/x86/tools relocs diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h index ff700d81e91e..0927cdc4f946 100644 --- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -11,7 +11,32 @@ #include #include #include +#include #ifndef CONFIG_X86_CMPXCHG64 extern void cmpxchg8b_emu(void); #endif + +#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_X86_32 +#define INDIRECT_THUNK(reg) extern asmlinkage void __x86_indirect_thunk_e ## reg(void); +#else +#define INDIRECT_THUNK(reg) extern asmlinkage void __x86_indirect_thunk_r ## reg(void); +INDIRECT_THUNK(8) +INDIRECT_THUNK(9) +INDIRECT_THUNK(10) +INDIRECT_THUNK(11) +INDIRECT_THUNK(12) +INDIRECT_THUNK(13) +INDIRECT_THUNK(14) +INDIRECT_THUNK(15) +#endif +INDIRECT_THUNK(ax) +INDIRECT_THUNK(bx) +INDIRECT_THUNK(cx) +INDIRECT_THUNK(dx) +INDIRECT_THUNK(si) +INDIRECT_THUNK(di) +INDIRECT_THUNK(bp) +INDIRECT_THUNK(sp) +#endif /* CONFIG_RETPOLINE */ diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 1641c2f96363..f275447862f4 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -203,6 +203,8 @@ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ #define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */ #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_AMD ( 7*32+13) /* AMD Retpoline mitigation for Spectre variant 2 */ #define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ #define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */ #define X86_FEATURE_AVX512_4VNNIW ( 7*32+16) /* AVX-512 Neural Network Instructions */ diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h new file mode 100644 index 000000000000..e20e92ef2ca8 --- /dev/null +++ b/arch/x86/include/asm/nospec-branch.h @@ -0,0 +1,128 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __NOSPEC_BRANCH_H__ +#define __NOSPEC_BRANCH_H__ + +#include +#include +#include + +#ifdef __ASSEMBLY__ + +/* + * This should be used immediately before a retpoline alternative. It tells + * objtool where the retpolines are so that it can make sense of the control + * flow by just reading the original instruction(s) and ignoring the + * alternatives. + */ +.macro ANNOTATE_NOSPEC_ALTERNATIVE + .Lannotate_\@: + .pushsection .discard.nospec + .long .Lannotate_\@ - . + .popsection +.endm + +/* + * These are the bare retpoline primitives for indirect jmp and call. + * Do not use these directly; they only exist to make the ALTERNATIVE + * invocation below less ugly. + */ +.macro RETPOLINE_JMP reg:req + call .Ldo_rop_\@ +.Lspec_trap_\@: + pause + jmp .Lspec_trap_\@ +.Ldo_rop_\@: + mov \reg, (%_ASM_SP) + ret +.endm + +/* + * This is a wrapper around RETPOLINE_JMP so the called function in reg + * returns to the instruction after the macro. + */ +.macro RETPOLINE_CALL reg:req + jmp .Ldo_call_\@ +.Ldo_retpoline_jmp_\@: + RETPOLINE_JMP \reg +.Ldo_call_\@: + call .Ldo_retpoline_jmp_\@ +.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. + */ +.macro JMP_NOSPEC reg:req +#ifdef CONFIG_RETPOLINE + ANNOTATE_NOSPEC_ALTERNATIVE + ALTERNATIVE_2 __stringify(jmp *\reg), \ + __stringify(RETPOLINE_JMP \reg), X86_FEATURE_RETPOLINE, \ + __stringify(lfence; jmp *\reg), X86_FEATURE_RETPOLINE_AMD +#else + jmp *\reg +#endif +.endm + +.macro CALL_NOSPEC reg:req +#ifdef CONFIG_RETPOLINE + ANNOTATE_NOSPEC_ALTERNATIVE + ALTERNATIVE_2 __stringify(call *\reg), \ + __stringify(RETPOLINE_CALL \reg), X86_FEATURE_RETPOLINE,\ + __stringify(lfence; call *\reg), X86_FEATURE_RETPOLINE_AMD +#else + call *\reg +#endif +.endm + +#else /* __ASSEMBLY__ */ + +#define ANNOTATE_NOSPEC_ALTERNATIVE \ + "999:\n\t" \ + ".pushsection .discard.nospec\n\t" \ + ".long 999b - .\n\t" \ + ".popsection\n\t" + +#if defined(CONFIG_X86_64) && defined(RETPOLINE) + +/* + * Since the inline asm uses the %V modifier which is only in newer GCC, + * the 64-bit one is dependent on RETPOLINE not CONFIG_RETPOLINE. + */ +# define CALL_NOSPEC \ + ANNOTATE_NOSPEC_ALTERNATIVE \ + ALTERNATIVE( \ + "call *%[thunk_target]\n", \ + "call __x86_indirect_thunk_%V[thunk_target]\n", \ + X86_FEATURE_RETPOLINE) +# define THUNK_TARGET(addr) [thunk_target] "r" (addr) + +#elif defined(CONFIG_X86_32) && defined(CONFIG_RETPOLINE) +/* + * For i386 we use the original ret-equivalent retpoline, because + * otherwise we'll run out of registers. We don't care about CET + * here, anyway. + */ +# define CALL_NOSPEC ALTERNATIVE("call *%[thunk_target]\n", \ + " jmp 904f;\n" \ + " .align 16\n" \ + "901: call 903f;\n" \ + "902: pause;\n" \ + " jmp 902b;\n" \ + " .align 16\n" \ + "903: addl $4, %%esp;\n" \ + " pushl %[thunk_target];\n" \ + " ret;\n" \ + " .align 16\n" \ + "904: call 901b;\n", \ + X86_FEATURE_RETPOLINE) + +# define THUNK_TARGET(addr) [thunk_target] "rm" (addr) +#else /* No retpoline */ +# define CALL_NOSPEC "call *%[thunk_target]\n" +# define THUNK_TARGET(addr) [thunk_target] "rm" (addr) +#endif + +#endif /* __ASSEMBLY__ */ +#endif /* __NOSPEC_BRANCH_H__ */ diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 372ba3fb400f..7a671d1ae3cb 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -905,6 +905,10 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) setup_force_cpu_bug(X86_BUG_SPECTRE_V1); setup_force_cpu_bug(X86_BUG_SPECTRE_V2); +#ifdef CONFIG_RETPOLINE + setup_force_cpu_cap(X86_FEATURE_RETPOLINE); +#endif + fpu__init_system(c); #ifdef CONFIG_X86_32 diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index 457f681ef379..d435c89875c1 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -26,6 +26,7 @@ lib-y += memcpy_$(BITS).o lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o +lib-$(CONFIG_RETPOLINE) += retpoline.o obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S new file mode 100644 index 000000000000..cb45c6cb465f --- /dev/null +++ b/arch/x86/lib/retpoline.S @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#include +#include +#include +#include +#include +#include +#include + +.macro THUNK reg + .section .text.__x86.indirect_thunk.\reg + +ENTRY(__x86_indirect_thunk_\reg) + CFI_STARTPROC + JMP_NOSPEC %\reg + CFI_ENDPROC +ENDPROC(__x86_indirect_thunk_\reg) +.endm + +/* + * Despite being an assembler file we can't just use .irp here + * because __KSYM_DEPS__ only uses the C preprocessor and would + * only see one instance of "__x86_indirect_thunk_\reg" rather + * than one per register with the correct names. So we do it + * the simple and nasty way... + */ +#define EXPORT_THUNK(reg) EXPORT_SYMBOL(__x86_indirect_thunk_ ## reg) +#define GENERATE_THUNK(reg) THUNK reg ; EXPORT_THUNK(reg) + +GENERATE_THUNK(_ASM_AX) +GENERATE_THUNK(_ASM_BX) +GENERATE_THUNK(_ASM_CX) +GENERATE_THUNK(_ASM_DX) +GENERATE_THUNK(_ASM_SI) +GENERATE_THUNK(_ASM_DI) +GENERATE_THUNK(_ASM_BP) +GENERATE_THUNK(_ASM_SP) +#ifdef CONFIG_64BIT +GENERATE_THUNK(r8) +GENERATE_THUNK(r9) +GENERATE_THUNK(r10) +GENERATE_THUNK(r11) +GENERATE_THUNK(r12) +GENERATE_THUNK(r13) +GENERATE_THUNK(r14) +GENERATE_THUNK(r15) +#endif -- cgit v1.2.3 From 5096732f6f695001fa2d6f1335a2680b37912c69 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Thu, 11 Jan 2018 21:46:32 +0000 Subject: x86/retpoline/checksum32: Convert assembler indirect jumps Convert all indirect jumps in 32bit checksum assembler code to use non-speculative sequences when CONFIG_RETPOLINE is enabled. Signed-off-by: David Woodhouse Signed-off-by: Thomas Gleixner Acked-by: Arjan van de Ven Acked-by: Ingo Molnar Cc: gnomes@lxorguk.ukuu.org.uk Cc: Rik van Riel Cc: Andi Kleen Cc: Josh Poimboeuf Cc: thomas.lendacky@amd.com Cc: Peter Zijlstra Cc: Linus Torvalds Cc: Jiri Kosina Cc: Andy Lutomirski Cc: Dave Hansen Cc: Kees Cook Cc: Tim Chen Cc: Greg Kroah-Hartman Cc: Paul Turner Link: https://lkml.kernel.org/r/1515707194-20531-11-git-send-email-dwmw@amazon.co.uk --- arch/x86/lib/checksum_32.S | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'arch/x86/lib') diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S index 4d34bb548b41..46e71a74e612 100644 --- a/arch/x86/lib/checksum_32.S +++ b/arch/x86/lib/checksum_32.S @@ -29,7 +29,8 @@ #include #include #include - +#include + /* * computes a partial checksum, e.g. for TCP/UDP fragments */ @@ -156,7 +157,7 @@ ENTRY(csum_partial) negl %ebx lea 45f(%ebx,%ebx,2), %ebx testl %esi, %esi - jmp *%ebx + JMP_NOSPEC %ebx # Handle 2-byte-aligned regions 20: addw (%esi), %ax @@ -439,7 +440,7 @@ ENTRY(csum_partial_copy_generic) andl $-32,%edx lea 3f(%ebx,%ebx), %ebx testl %esi, %esi - jmp *%ebx + JMP_NOSPEC %ebx 1: addl $64,%esi addl $64,%edi SRC(movb -32(%edx),%bl) ; SRC(movb (%edx),%bl) -- cgit v1.2.3